diff options
Diffstat (limited to 'include')
486 files changed, 11252 insertions, 4936 deletions
diff --git a/include/system/accel-ops.h b/include/accel/accel-cpu-ops.h index 4c99d25..0674764 100644 --- a/include/system/accel-ops.h +++ b/include/accel/accel-cpu-ops.h @@ -1,5 +1,5 @@ /* - * Accelerator OPS, used for cpus.c module + * Accelerator per-vCPU handlers * * Copyright 2021 SUSE LLC * @@ -7,9 +7,10 @@ * See the COPYING file in the top-level directory. */ -#ifndef ACCEL_OPS_H -#define ACCEL_OPS_H +#ifndef QEMU_ACCEL_CPU_OPS_H +#define QEMU_ACCEL_CPU_OPS_H +#include "qemu/accel.h" #include "exec/vaddr.h" #include "qom/object.h" @@ -31,7 +32,7 @@ struct AccelOpsClass { /*< public >*/ /* initialization function called when accel is chosen */ - void (*ops_init)(AccelOpsClass *ops); + void (*ops_init)(AccelClass *ac); bool (*cpus_are_resettable)(void); void (*cpu_reset_hold)(CPUState *cpu); @@ -40,14 +41,33 @@ struct AccelOpsClass { void (*kick_vcpu_thread)(CPUState *cpu); bool (*cpu_thread_is_idle)(CPUState *cpu); + /** + * synchronize_post_reset: + * synchronize_post_init: + * @cpu: The vCPU to synchronize. + * + * Request to synchronize QEMU vCPU registers to the hardware accelerator + * (QEMU is the reference). + */ void (*synchronize_post_reset)(CPUState *cpu); void (*synchronize_post_init)(CPUState *cpu); + /** + * synchronize_state: + * synchronize_pre_loadvm: + * @cpu: The vCPU to synchronize. + * + * Request to synchronize QEMU vCPU registers from the hardware accelerator + * (the hardware accelerator is the reference). + */ void (*synchronize_state)(CPUState *cpu); void (*synchronize_pre_loadvm)(CPUState *cpu); - void (*synchronize_pre_resume)(bool step_pending); + /* handle_interrupt is mandatory. */ void (*handle_interrupt)(CPUState *cpu, int mask); + /* get_vcpu_stats: Append statistics of this @cpu to @buf */ + void (*get_vcpu_stats)(CPUState *cpu, GString *buf); + /** * @get_virtual_clock: fetch virtual clock * @set_virtual_clock: set virtual clock @@ -70,4 +90,6 @@ struct AccelOpsClass { void (*remove_all_breakpoints)(CPUState *cpu); }; -#endif /* ACCEL_OPS_H */ +void generic_handle_interrupt(CPUState *cpu, int mask); + +#endif /* QEMU_ACCEL_CPU_OPS_H */ diff --git a/include/accel/accel-cpu-target.h b/include/accel/accel-cpu-target.h index 37dde7f..6feb344 100644 --- a/include/accel/accel-cpu-target.h +++ b/include/accel/accel-cpu-target.h @@ -21,21 +21,11 @@ */ #include "qom/object.h" +#include "accel/accel-cpu.h" #include "cpu.h" #define TYPE_ACCEL_CPU "accel-" CPU_RESOLVING_TYPE #define ACCEL_CPU_NAME(name) (name "-" TYPE_ACCEL_CPU) -typedef struct AccelCPUClass AccelCPUClass; DECLARE_CLASS_CHECKERS(AccelCPUClass, ACCEL_CPU, TYPE_ACCEL_CPU) -typedef struct AccelCPUClass { - /*< private >*/ - ObjectClass parent_class; - /*< public >*/ - - void (*cpu_class_init)(CPUClass *cc); - void (*cpu_instance_init)(CPUState *cpu); - bool (*cpu_target_realize)(CPUState *cpu, Error **errp); -} AccelCPUClass; - #endif /* ACCEL_CPU_H */ diff --git a/include/accel/accel-cpu.h b/include/accel/accel-cpu.h new file mode 100644 index 0000000..9e7eede --- /dev/null +++ b/include/accel/accel-cpu.h @@ -0,0 +1,23 @@ +/* + * Accelerator interface, specializes CPUClass + * + * Copyright 2021 SUSE LLC + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef ACCEL_CPU_H +#define ACCEL_CPU_H + +#include "qom/object.h" +#include "hw/core/cpu.h" + +typedef struct AccelCPUClass { + ObjectClass parent_class; + + void (*cpu_class_init)(CPUClass *cc); + void (*cpu_instance_init)(CPUState *cpu); + bool (*cpu_target_realize)(CPUState *cpu, Error **errp); +} AccelCPUClass; + +#endif /* ACCEL_CPU_H */ diff --git a/include/accel/accel-ops.h b/include/accel/accel-ops.h new file mode 100644 index 0000000..23a8c24 --- /dev/null +++ b/include/accel/accel-ops.h @@ -0,0 +1,51 @@ +/* + * Accelerator handlers + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef ACCEL_OPS_H +#define ACCEL_OPS_H + +#include "exec/hwaddr.h" +#include "qemu/accel.h" +#include "qom/object.h" + +struct AccelState { + Object parent_obj; +}; + +struct AccelClass { + ObjectClass parent_class; + + const char *name; + /* Cached by accel_init_ops_interfaces() when created */ + AccelOpsClass *ops; + + int (*init_machine)(AccelState *as, MachineState *ms); + bool (*cpu_common_realize)(CPUState *cpu, Error **errp); + void (*cpu_common_unrealize)(CPUState *cpu); + /* get_stats: Append statistics to @buf */ + void (*get_stats)(AccelState *as, GString *buf); + + /* system related hooks */ + void (*setup_post)(AccelState *as); + void (*pre_resume_vm)(AccelState *as, bool step_pending); + bool (*has_memory)(AccelState *accel, AddressSpace *as, + hwaddr start_addr, hwaddr size); + + /* gdbstub related hooks */ + int (*gdbstub_supported_sstep_flags)(AccelState *as); + + bool *allowed; + /* + * Array of global properties that would be applied when specific + * accelerator is chosen. It works like MachineClass.compat_props + * but it's for accelerators not machines. Accelerator-provided + * global properties may be overridden by machine-type + * compat_props or user-provided global properties. + */ + GPtrArray *compat_props; +}; + +#endif /* ACCEL_OPS_H */ diff --git a/include/accel/tcg/cpu-ldst-common.h b/include/accel/tcg/cpu-ldst-common.h new file mode 100644 index 0000000..17a3250 --- /dev/null +++ b/include/accel/tcg/cpu-ldst-common.h @@ -0,0 +1,129 @@ +/* + * Software MMU support + * + * SPDX-License-Identifier: LGPL-2.1-or-later + */ + +#ifndef ACCEL_TCG_CPU_LDST_COMMON_H +#define ACCEL_TCG_CPU_LDST_COMMON_H + +#ifndef CONFIG_TCG +#error Can only include this header with TCG +#endif + +#include "exec/memopidx.h" +#include "exec/vaddr.h" +#include "exec/mmu-access-type.h" +#include "qemu/int128.h" + +uint8_t cpu_ldb_mmu(CPUArchState *env, vaddr ptr, MemOpIdx oi, uintptr_t ra); +uint16_t cpu_ldw_mmu(CPUArchState *env, vaddr ptr, MemOpIdx oi, uintptr_t ra); +uint32_t cpu_ldl_mmu(CPUArchState *env, vaddr ptr, MemOpIdx oi, uintptr_t ra); +uint64_t cpu_ldq_mmu(CPUArchState *env, vaddr ptr, MemOpIdx oi, uintptr_t ra); +Int128 cpu_ld16_mmu(CPUArchState *env, vaddr addr, MemOpIdx oi, uintptr_t ra); + +void cpu_stb_mmu(CPUArchState *env, vaddr ptr, uint8_t val, + MemOpIdx oi, uintptr_t ra); +void cpu_stw_mmu(CPUArchState *env, vaddr ptr, uint16_t val, + MemOpIdx oi, uintptr_t ra); +void cpu_stl_mmu(CPUArchState *env, vaddr ptr, uint32_t val, + MemOpIdx oi, uintptr_t ra); +void cpu_stq_mmu(CPUArchState *env, vaddr ptr, uint64_t val, + MemOpIdx oi, uintptr_t ra); +void cpu_st16_mmu(CPUArchState *env, vaddr addr, Int128 val, + MemOpIdx oi, uintptr_t ra); + +uint32_t cpu_atomic_cmpxchgb_mmu(CPUArchState *env, vaddr addr, + uint32_t cmpv, uint32_t newv, + MemOpIdx oi, uintptr_t retaddr); +uint32_t cpu_atomic_cmpxchgw_le_mmu(CPUArchState *env, vaddr addr, + uint32_t cmpv, uint32_t newv, + MemOpIdx oi, uintptr_t retaddr); +uint32_t cpu_atomic_cmpxchgl_le_mmu(CPUArchState *env, vaddr addr, + uint32_t cmpv, uint32_t newv, + MemOpIdx oi, uintptr_t retaddr); +uint64_t cpu_atomic_cmpxchgq_le_mmu(CPUArchState *env, vaddr addr, + uint64_t cmpv, uint64_t newv, + MemOpIdx oi, uintptr_t retaddr); +uint32_t cpu_atomic_cmpxchgw_be_mmu(CPUArchState *env, vaddr addr, + uint32_t cmpv, uint32_t newv, + MemOpIdx oi, uintptr_t retaddr); +uint32_t cpu_atomic_cmpxchgl_be_mmu(CPUArchState *env, vaddr addr, + uint32_t cmpv, uint32_t newv, + MemOpIdx oi, uintptr_t retaddr); +uint64_t cpu_atomic_cmpxchgq_be_mmu(CPUArchState *env, vaddr addr, + uint64_t cmpv, uint64_t newv, + MemOpIdx oi, uintptr_t retaddr); + +#define GEN_ATOMIC_HELPER(NAME, TYPE, SUFFIX) \ +TYPE cpu_atomic_ ## NAME ## SUFFIX ## _mmu \ + (CPUArchState *env, vaddr addr, TYPE val, \ + MemOpIdx oi, uintptr_t retaddr); + +#ifdef CONFIG_ATOMIC64 +#define GEN_ATOMIC_HELPER_ALL(NAME) \ + GEN_ATOMIC_HELPER(NAME, uint32_t, b) \ + GEN_ATOMIC_HELPER(NAME, uint32_t, w_le) \ + GEN_ATOMIC_HELPER(NAME, uint32_t, w_be) \ + GEN_ATOMIC_HELPER(NAME, uint32_t, l_le) \ + GEN_ATOMIC_HELPER(NAME, uint32_t, l_be) \ + GEN_ATOMIC_HELPER(NAME, uint64_t, q_le) \ + GEN_ATOMIC_HELPER(NAME, uint64_t, q_be) +#else +#define GEN_ATOMIC_HELPER_ALL(NAME) \ + GEN_ATOMIC_HELPER(NAME, uint32_t, b) \ + GEN_ATOMIC_HELPER(NAME, uint32_t, w_le) \ + GEN_ATOMIC_HELPER(NAME, uint32_t, w_be) \ + GEN_ATOMIC_HELPER(NAME, uint32_t, l_le) \ + GEN_ATOMIC_HELPER(NAME, uint32_t, l_be) +#endif + +GEN_ATOMIC_HELPER_ALL(fetch_add) +GEN_ATOMIC_HELPER_ALL(fetch_sub) +GEN_ATOMIC_HELPER_ALL(fetch_and) +GEN_ATOMIC_HELPER_ALL(fetch_or) +GEN_ATOMIC_HELPER_ALL(fetch_xor) +GEN_ATOMIC_HELPER_ALL(fetch_smin) +GEN_ATOMIC_HELPER_ALL(fetch_umin) +GEN_ATOMIC_HELPER_ALL(fetch_smax) +GEN_ATOMIC_HELPER_ALL(fetch_umax) + +GEN_ATOMIC_HELPER_ALL(add_fetch) +GEN_ATOMIC_HELPER_ALL(sub_fetch) +GEN_ATOMIC_HELPER_ALL(and_fetch) +GEN_ATOMIC_HELPER_ALL(or_fetch) +GEN_ATOMIC_HELPER_ALL(xor_fetch) +GEN_ATOMIC_HELPER_ALL(smin_fetch) +GEN_ATOMIC_HELPER_ALL(umin_fetch) +GEN_ATOMIC_HELPER_ALL(smax_fetch) +GEN_ATOMIC_HELPER_ALL(umax_fetch) + +GEN_ATOMIC_HELPER_ALL(xchg) + +Int128 cpu_atomic_cmpxchgo_le_mmu(CPUArchState *env, vaddr addr, + Int128 cmpv, Int128 newv, + MemOpIdx oi, uintptr_t retaddr); +Int128 cpu_atomic_cmpxchgo_be_mmu(CPUArchState *env, vaddr addr, + Int128 cmpv, Int128 newv, + MemOpIdx oi, uintptr_t retaddr); + +GEN_ATOMIC_HELPER(xchg, Int128, o_le) +GEN_ATOMIC_HELPER(xchg, Int128, o_be) +GEN_ATOMIC_HELPER(fetch_and, Int128, o_le) +GEN_ATOMIC_HELPER(fetch_and, Int128, o_be) +GEN_ATOMIC_HELPER(fetch_or, Int128, o_le) +GEN_ATOMIC_HELPER(fetch_or, Int128, o_be) + +#undef GEN_ATOMIC_HELPER_ALL +#undef GEN_ATOMIC_HELPER + +uint8_t cpu_ldb_code_mmu(CPUArchState *env, vaddr addr, + MemOpIdx oi, uintptr_t ra); +uint16_t cpu_ldw_code_mmu(CPUArchState *env, vaddr addr, + MemOpIdx oi, uintptr_t ra); +uint32_t cpu_ldl_code_mmu(CPUArchState *env, vaddr addr, + MemOpIdx oi, uintptr_t ra); +uint64_t cpu_ldq_code_mmu(CPUArchState *env, vaddr addr, + MemOpIdx oi, uintptr_t ra); + +#endif /* ACCEL_TCG_CPU_LDST_COMMON_H */ diff --git a/include/accel/tcg/cpu-ldst.h b/include/accel/tcg/cpu-ldst.h new file mode 100644 index 0000000..0de7f5e --- /dev/null +++ b/include/accel/tcg/cpu-ldst.h @@ -0,0 +1,505 @@ +/* + * Software MMU support (per-target) + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + * + */ + +/* + * Generate inline load/store functions for all MMU modes (typically + * at least _user and _kernel) as well as _data versions, for all data + * sizes. + * + * Used by target op helpers. + * + * The syntax for the accessors is: + * + * load: cpu_ld{sign}{size}{end}_{mmusuffix}(env, ptr) + * cpu_ld{sign}{size}{end}_{mmusuffix}_ra(env, ptr, retaddr) + * cpu_ld{sign}{size}{end}_mmuidx_ra(env, ptr, mmu_idx, retaddr) + * cpu_ld{sign}{size}{end}_mmu(env, ptr, oi, retaddr) + * + * store: cpu_st{size}{end}_{mmusuffix}(env, ptr, val) + * cpu_st{size}{end}_{mmusuffix}_ra(env, ptr, val, retaddr) + * cpu_st{size}{end}_mmuidx_ra(env, ptr, val, mmu_idx, retaddr) + * cpu_st{size}{end}_mmu(env, ptr, val, oi, retaddr) + * + * sign is: + * (empty): for 32 and 64 bit sizes + * u : unsigned + * s : signed + * + * size is: + * b: 8 bits + * w: 16 bits + * l: 32 bits + * q: 64 bits + * + * end is: + * (empty): for target native endian, or for 8 bit access + * _be: for forced big endian + * _le: for forced little endian + * + * mmusuffix is one of the generic suffixes "data" or "code", or "mmuidx". + * The "mmuidx" suffix carries an extra mmu_idx argument that specifies + * the index to use; the "data" and "code" suffixes take the index from + * cpu_mmu_index(). + * + * The "mmu" suffix carries the full MemOpIdx, with both mmu_idx and the + * MemOp including alignment requirements. The alignment will be enforced. + */ +#ifndef ACCEL_TCG_CPU_LDST_H +#define ACCEL_TCG_CPU_LDST_H + +#ifndef CONFIG_TCG +#error Can only include this header with TCG +#endif + +#include "exec/cpu-common.h" +#include "accel/tcg/cpu-ldst-common.h" +#include "accel/tcg/cpu-mmu-index.h" +#include "exec/abi_ptr.h" + +#if defined(CONFIG_USER_ONLY) +#include "user/guest-host.h" +#endif /* CONFIG_USER_ONLY */ + +static inline uint32_t +cpu_ldub_mmuidx_ra(CPUArchState *env, abi_ptr addr, int mmu_idx, uintptr_t ra) +{ + MemOpIdx oi = make_memop_idx(MO_UB, mmu_idx); + return cpu_ldb_mmu(env, addr, oi, ra); +} + +static inline int +cpu_ldsb_mmuidx_ra(CPUArchState *env, abi_ptr addr, int mmu_idx, uintptr_t ra) +{ + return (int8_t)cpu_ldub_mmuidx_ra(env, addr, mmu_idx, ra); +} + +static inline uint32_t +cpu_lduw_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra) +{ + MemOpIdx oi = make_memop_idx(MO_BEUW | MO_UNALN, mmu_idx); + return cpu_ldw_mmu(env, addr, oi, ra); +} + +static inline int +cpu_ldsw_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra) +{ + return (int16_t)cpu_lduw_be_mmuidx_ra(env, addr, mmu_idx, ra); +} + +static inline uint32_t +cpu_ldl_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra) +{ + MemOpIdx oi = make_memop_idx(MO_BEUL | MO_UNALN, mmu_idx); + return cpu_ldl_mmu(env, addr, oi, ra); +} + +static inline uint64_t +cpu_ldq_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra) +{ + MemOpIdx oi = make_memop_idx(MO_BEUQ | MO_UNALN, mmu_idx); + return cpu_ldq_mmu(env, addr, oi, ra); +} + +static inline uint32_t +cpu_lduw_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra) +{ + MemOpIdx oi = make_memop_idx(MO_LEUW | MO_UNALN, mmu_idx); + return cpu_ldw_mmu(env, addr, oi, ra); +} + +static inline int +cpu_ldsw_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra) +{ + return (int16_t)cpu_lduw_le_mmuidx_ra(env, addr, mmu_idx, ra); +} + +static inline uint32_t +cpu_ldl_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra) +{ + MemOpIdx oi = make_memop_idx(MO_LEUL | MO_UNALN, mmu_idx); + return cpu_ldl_mmu(env, addr, oi, ra); +} + +static inline uint64_t +cpu_ldq_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, + int mmu_idx, uintptr_t ra) +{ + MemOpIdx oi = make_memop_idx(MO_LEUQ | MO_UNALN, mmu_idx); + return cpu_ldq_mmu(env, addr, oi, ra); +} + +static inline void +cpu_stb_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val, + int mmu_idx, uintptr_t ra) +{ + MemOpIdx oi = make_memop_idx(MO_UB, mmu_idx); + cpu_stb_mmu(env, addr, val, oi, ra); +} + +static inline void +cpu_stw_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val, + int mmu_idx, uintptr_t ra) +{ + MemOpIdx oi = make_memop_idx(MO_BEUW | MO_UNALN, mmu_idx); + cpu_stw_mmu(env, addr, val, oi, ra); +} + +static inline void +cpu_stl_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val, + int mmu_idx, uintptr_t ra) +{ + MemOpIdx oi = make_memop_idx(MO_BEUL | MO_UNALN, mmu_idx); + cpu_stl_mmu(env, addr, val, oi, ra); +} + +static inline void +cpu_stq_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint64_t val, + int mmu_idx, uintptr_t ra) +{ + MemOpIdx oi = make_memop_idx(MO_BEUQ | MO_UNALN, mmu_idx); + cpu_stq_mmu(env, addr, val, oi, ra); +} + +static inline void +cpu_stw_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val, + int mmu_idx, uintptr_t ra) +{ + MemOpIdx oi = make_memop_idx(MO_LEUW | MO_UNALN, mmu_idx); + cpu_stw_mmu(env, addr, val, oi, ra); +} + +static inline void +cpu_stl_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint32_t val, + int mmu_idx, uintptr_t ra) +{ + MemOpIdx oi = make_memop_idx(MO_LEUL | MO_UNALN, mmu_idx); + cpu_stl_mmu(env, addr, val, oi, ra); +} + +static inline void +cpu_stq_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, uint64_t val, + int mmu_idx, uintptr_t ra) +{ + MemOpIdx oi = make_memop_idx(MO_LEUQ | MO_UNALN, mmu_idx); + cpu_stq_mmu(env, addr, val, oi, ra); +} + +/*--------------------------*/ + +static inline uint32_t +cpu_ldub_data_ra(CPUArchState *env, abi_ptr addr, uintptr_t ra) +{ + int mmu_index = cpu_mmu_index(env_cpu(env), false); + return cpu_ldub_mmuidx_ra(env, addr, mmu_index, ra); +} + +static inline int +cpu_ldsb_data_ra(CPUArchState *env, abi_ptr addr, uintptr_t ra) +{ + return (int8_t)cpu_ldub_data_ra(env, addr, ra); +} + +static inline uint32_t +cpu_lduw_be_data_ra(CPUArchState *env, abi_ptr addr, uintptr_t ra) +{ + int mmu_index = cpu_mmu_index(env_cpu(env), false); + return cpu_lduw_be_mmuidx_ra(env, addr, mmu_index, ra); +} + +static inline int +cpu_ldsw_be_data_ra(CPUArchState *env, abi_ptr addr, uintptr_t ra) +{ + return (int16_t)cpu_lduw_be_data_ra(env, addr, ra); +} + +static inline uint32_t +cpu_ldl_be_data_ra(CPUArchState *env, abi_ptr addr, uintptr_t ra) +{ + int mmu_index = cpu_mmu_index(env_cpu(env), false); + return cpu_ldl_be_mmuidx_ra(env, addr, mmu_index, ra); +} + +static inline uint64_t +cpu_ldq_be_data_ra(CPUArchState *env, abi_ptr addr, uintptr_t ra) +{ + int mmu_index = cpu_mmu_index(env_cpu(env), false); + return cpu_ldq_be_mmuidx_ra(env, addr, mmu_index, ra); +} + +static inline uint32_t +cpu_lduw_le_data_ra(CPUArchState *env, abi_ptr addr, uintptr_t ra) +{ + int mmu_index = cpu_mmu_index(env_cpu(env), false); + return cpu_lduw_le_mmuidx_ra(env, addr, mmu_index, ra); +} + +static inline int +cpu_ldsw_le_data_ra(CPUArchState *env, abi_ptr addr, uintptr_t ra) +{ + return (int16_t)cpu_lduw_le_data_ra(env, addr, ra); +} + +static inline uint32_t +cpu_ldl_le_data_ra(CPUArchState *env, abi_ptr addr, uintptr_t ra) +{ + int mmu_index = cpu_mmu_index(env_cpu(env), false); + return cpu_ldl_le_mmuidx_ra(env, addr, mmu_index, ra); +} + +static inline uint64_t +cpu_ldq_le_data_ra(CPUArchState *env, abi_ptr addr, uintptr_t ra) +{ + int mmu_index = cpu_mmu_index(env_cpu(env), false); + return cpu_ldq_le_mmuidx_ra(env, addr, mmu_index, ra); +} + +static inline void +cpu_stb_data_ra(CPUArchState *env, abi_ptr addr, uint32_t val, uintptr_t ra) +{ + int mmu_index = cpu_mmu_index(env_cpu(env), false); + cpu_stb_mmuidx_ra(env, addr, val, mmu_index, ra); +} + +static inline void +cpu_stw_be_data_ra(CPUArchState *env, abi_ptr addr, uint32_t val, uintptr_t ra) +{ + int mmu_index = cpu_mmu_index(env_cpu(env), false); + cpu_stw_be_mmuidx_ra(env, addr, val, mmu_index, ra); +} + +static inline void +cpu_stl_be_data_ra(CPUArchState *env, abi_ptr addr, uint32_t val, uintptr_t ra) +{ + int mmu_index = cpu_mmu_index(env_cpu(env), false); + cpu_stl_be_mmuidx_ra(env, addr, val, mmu_index, ra); +} + +static inline void +cpu_stq_be_data_ra(CPUArchState *env, abi_ptr addr, uint64_t val, uintptr_t ra) +{ + int mmu_index = cpu_mmu_index(env_cpu(env), false); + cpu_stq_be_mmuidx_ra(env, addr, val, mmu_index, ra); +} + +static inline void +cpu_stw_le_data_ra(CPUArchState *env, abi_ptr addr, uint32_t val, uintptr_t ra) +{ + int mmu_index = cpu_mmu_index(env_cpu(env), false); + cpu_stw_le_mmuidx_ra(env, addr, val, mmu_index, ra); +} + +static inline void +cpu_stl_le_data_ra(CPUArchState *env, abi_ptr addr, uint32_t val, uintptr_t ra) +{ + int mmu_index = cpu_mmu_index(env_cpu(env), false); + cpu_stl_le_mmuidx_ra(env, addr, val, mmu_index, ra); +} + +static inline void +cpu_stq_le_data_ra(CPUArchState *env, abi_ptr addr, uint64_t val, uintptr_t ra) +{ + int mmu_index = cpu_mmu_index(env_cpu(env), false); + cpu_stq_le_mmuidx_ra(env, addr, val, mmu_index, ra); +} + +/*--------------------------*/ + +static inline uint32_t +cpu_ldub_data(CPUArchState *env, abi_ptr addr) +{ + return cpu_ldub_data_ra(env, addr, 0); +} + +static inline int +cpu_ldsb_data(CPUArchState *env, abi_ptr addr) +{ + return (int8_t)cpu_ldub_data(env, addr); +} + +static inline uint32_t +cpu_lduw_be_data(CPUArchState *env, abi_ptr addr) +{ + return cpu_lduw_be_data_ra(env, addr, 0); +} + +static inline int +cpu_ldsw_be_data(CPUArchState *env, abi_ptr addr) +{ + return (int16_t)cpu_lduw_be_data(env, addr); +} + +static inline uint32_t +cpu_ldl_be_data(CPUArchState *env, abi_ptr addr) +{ + return cpu_ldl_be_data_ra(env, addr, 0); +} + +static inline uint64_t +cpu_ldq_be_data(CPUArchState *env, abi_ptr addr) +{ + return cpu_ldq_be_data_ra(env, addr, 0); +} + +static inline uint32_t +cpu_lduw_le_data(CPUArchState *env, abi_ptr addr) +{ + return cpu_lduw_le_data_ra(env, addr, 0); +} + +static inline int +cpu_ldsw_le_data(CPUArchState *env, abi_ptr addr) +{ + return (int16_t)cpu_lduw_le_data(env, addr); +} + +static inline uint32_t +cpu_ldl_le_data(CPUArchState *env, abi_ptr addr) +{ + return cpu_ldl_le_data_ra(env, addr, 0); +} + +static inline uint64_t +cpu_ldq_le_data(CPUArchState *env, abi_ptr addr) +{ + return cpu_ldq_le_data_ra(env, addr, 0); +} + +static inline void +cpu_stb_data(CPUArchState *env, abi_ptr addr, uint32_t val) +{ + cpu_stb_data_ra(env, addr, val, 0); +} + +static inline void +cpu_stw_be_data(CPUArchState *env, abi_ptr addr, uint32_t val) +{ + cpu_stw_be_data_ra(env, addr, val, 0); +} + +static inline void +cpu_stl_be_data(CPUArchState *env, abi_ptr addr, uint32_t val) +{ + cpu_stl_be_data_ra(env, addr, val, 0); +} + +static inline void +cpu_stq_be_data(CPUArchState *env, abi_ptr addr, uint64_t val) +{ + cpu_stq_be_data_ra(env, addr, val, 0); +} + +static inline void +cpu_stw_le_data(CPUArchState *env, abi_ptr addr, uint32_t val) +{ + cpu_stw_le_data_ra(env, addr, val, 0); +} + +static inline void +cpu_stl_le_data(CPUArchState *env, abi_ptr addr, uint32_t val) +{ + cpu_stl_le_data_ra(env, addr, val, 0); +} + +static inline void +cpu_stq_le_data(CPUArchState *env, abi_ptr addr, uint64_t val) +{ + cpu_stq_le_data_ra(env, addr, val, 0); +} + +#if TARGET_BIG_ENDIAN +# define cpu_lduw_data cpu_lduw_be_data +# define cpu_ldsw_data cpu_ldsw_be_data +# define cpu_ldl_data cpu_ldl_be_data +# define cpu_ldq_data cpu_ldq_be_data +# define cpu_lduw_data_ra cpu_lduw_be_data_ra +# define cpu_ldsw_data_ra cpu_ldsw_be_data_ra +# define cpu_ldl_data_ra cpu_ldl_be_data_ra +# define cpu_ldq_data_ra cpu_ldq_be_data_ra +# define cpu_lduw_mmuidx_ra cpu_lduw_be_mmuidx_ra +# define cpu_ldsw_mmuidx_ra cpu_ldsw_be_mmuidx_ra +# define cpu_ldl_mmuidx_ra cpu_ldl_be_mmuidx_ra +# define cpu_ldq_mmuidx_ra cpu_ldq_be_mmuidx_ra +# define cpu_stw_data cpu_stw_be_data +# define cpu_stl_data cpu_stl_be_data +# define cpu_stq_data cpu_stq_be_data +# define cpu_stw_data_ra cpu_stw_be_data_ra +# define cpu_stl_data_ra cpu_stl_be_data_ra +# define cpu_stq_data_ra cpu_stq_be_data_ra +# define cpu_stw_mmuidx_ra cpu_stw_be_mmuidx_ra +# define cpu_stl_mmuidx_ra cpu_stl_be_mmuidx_ra +# define cpu_stq_mmuidx_ra cpu_stq_be_mmuidx_ra +#else +# define cpu_lduw_data cpu_lduw_le_data +# define cpu_ldsw_data cpu_ldsw_le_data +# define cpu_ldl_data cpu_ldl_le_data +# define cpu_ldq_data cpu_ldq_le_data +# define cpu_lduw_data_ra cpu_lduw_le_data_ra +# define cpu_ldsw_data_ra cpu_ldsw_le_data_ra +# define cpu_ldl_data_ra cpu_ldl_le_data_ra +# define cpu_ldq_data_ra cpu_ldq_le_data_ra +# define cpu_lduw_mmuidx_ra cpu_lduw_le_mmuidx_ra +# define cpu_ldsw_mmuidx_ra cpu_ldsw_le_mmuidx_ra +# define cpu_ldl_mmuidx_ra cpu_ldl_le_mmuidx_ra +# define cpu_ldq_mmuidx_ra cpu_ldq_le_mmuidx_ra +# define cpu_stw_data cpu_stw_le_data +# define cpu_stl_data cpu_stl_le_data +# define cpu_stq_data cpu_stq_le_data +# define cpu_stw_data_ra cpu_stw_le_data_ra +# define cpu_stl_data_ra cpu_stl_le_data_ra +# define cpu_stq_data_ra cpu_stq_le_data_ra +# define cpu_stw_mmuidx_ra cpu_stw_le_mmuidx_ra +# define cpu_stl_mmuidx_ra cpu_stl_le_mmuidx_ra +# define cpu_stq_mmuidx_ra cpu_stq_le_mmuidx_ra +#endif + +static inline uint32_t cpu_ldub_code(CPUArchState *env, abi_ptr addr) +{ + CPUState *cs = env_cpu(env); + MemOpIdx oi = make_memop_idx(MO_UB, cpu_mmu_index(cs, true)); + return cpu_ldb_code_mmu(env, addr, oi, 0); +} + +static inline uint32_t cpu_lduw_code(CPUArchState *env, abi_ptr addr) +{ + CPUState *cs = env_cpu(env); + MemOpIdx oi = make_memop_idx(MO_TEUW, cpu_mmu_index(cs, true)); + return cpu_ldw_code_mmu(env, addr, oi, 0); +} + +static inline uint32_t cpu_ldl_code(CPUArchState *env, abi_ptr addr) +{ + CPUState *cs = env_cpu(env); + MemOpIdx oi = make_memop_idx(MO_TEUL, cpu_mmu_index(cs, true)); + return cpu_ldl_code_mmu(env, addr, oi, 0); +} + +static inline uint64_t cpu_ldq_code(CPUArchState *env, abi_ptr addr) +{ + CPUState *cs = env_cpu(env); + MemOpIdx oi = make_memop_idx(MO_TEUQ, cpu_mmu_index(cs, true)); + return cpu_ldq_code_mmu(env, addr, oi, 0); +} + +#endif /* ACCEL_TCG_CPU_LDST_H */ diff --git a/include/accel/tcg/cpu-mmu-index.h b/include/accel/tcg/cpu-mmu-index.h new file mode 100644 index 0000000..e681a90 --- /dev/null +++ b/include/accel/tcg/cpu-mmu-index.h @@ -0,0 +1,42 @@ +/* + * cpu_mmu_index() + * + * Copyright (c) 2003 Fabrice Bellard + * + * SPDX-License-Identifier: LGPL-2.1-or-later + */ + +#ifndef ACCEL_TCG_CPU_MMU_INDEX_H +#define ACCEL_TCG_CPU_MMU_INDEX_H + +#include "hw/core/cpu.h" +#include "accel/tcg/cpu-ops.h" +#include "tcg/debug-assert.h" +#ifdef COMPILING_PER_TARGET +# ifdef CONFIG_USER_ONLY +# include "cpu.h" +# endif +#endif + +/** + * cpu_mmu_index: + * @env: The cpu environment + * @ifetch: True for code access, false for data access. + * + * Return the core mmu index for the current translation regime. + * This function is used by generic TCG code paths. + */ +static inline int cpu_mmu_index(CPUState *cs, bool ifetch) +{ +#ifdef COMPILING_PER_TARGET +# ifdef CONFIG_USER_ONLY + return MMU_USER_IDX; +# endif +#endif + + int ret = cs->cc->tcg_ops->mmu_index(cs, ifetch); + tcg_debug_assert(ret >= 0 && ret < NB_MMU_MODES); + return ret; +} + +#endif /* ACCEL_TCG_CPU_MMU_INDEX_H */ diff --git a/include/accel/tcg/cpu-ops.h b/include/accel/tcg/cpu-ops.h index f60e530..dd8ea30 100644 --- a/include/accel/tcg/cpu-ops.h +++ b/include/accel/tcg/cpu-ops.h @@ -16,9 +16,33 @@ #include "exec/memop.h" #include "exec/mmu-access-type.h" #include "exec/vaddr.h" +#include "accel/tcg/tb-cpu-state.h" +#include "tcg/tcg-mo.h" struct TCGCPUOps { /** + * mttcg_supported: multi-threaded TCG is supported + * + * Target (TCG frontend) supports: + * - atomic instructions + * - memory ordering primitives (barriers) + */ + bool mttcg_supported; + + /** + * @precise_smc: Stores which modify code within the current TB force + * the TB to exit; the next executed instruction will see + * the result of the store. + */ + bool precise_smc; + + /** + * @guest_default_memory_order: default barrier that is required + * for the guest memory ordering. + */ + TCGBar guest_default_memory_order; + + /** * @initialize: Initialize TCG state * * Called when the first CPU is realized. @@ -38,6 +62,12 @@ struct TCGCPUOps { void (*translate_code)(CPUState *cpu, TranslationBlock *tb, int *max_insns, vaddr pc, void *host_pc); /** + * @get_tb_cpu_state: Extract CPU state for a TCG #TranslationBlock + * + * Fill in all data required to select or compile a TranslationBlock. + */ + TCGTBCPUState (*get_tb_cpu_state)(CPUState *cs); + /** * @synchronize_from_tb: Synchronize state from a TCG #TranslationBlock * * This is called when we abandon execution of a TB before starting it, @@ -67,6 +97,9 @@ struct TCGCPUOps { /** @debug_excp_handler: Callback for handling debug exceptions */ void (*debug_excp_handler)(CPUState *cpu); + /** @mmu_index: Callback for choosing softmmu mmu index */ + int (*mmu_index)(CPUState *cpu, bool ifetch); + #ifdef CONFIG_USER_ONLY /** * @fake_user_interrupt: Callback for 'fake exception' handling. @@ -124,11 +157,20 @@ struct TCGCPUOps { */ void (*record_sigbus)(CPUState *cpu, vaddr addr, MMUAccessType access_type, uintptr_t ra); + + /** + * untagged_addr: Remove an ignored tag from an address + * @cpu: cpu context + * @addr: tagged guest address + */ + vaddr (*untagged_addr)(CPUState *cs, vaddr addr); #else /** @do_interrupt: Callback for interrupt handling. */ void (*do_interrupt)(CPUState *cpu); /** @cpu_exec_interrupt: Callback for processing interrupts in cpu_exec */ bool (*cpu_exec_interrupt)(CPUState *cpu, int interrupt_request); + /** @cpu_exec_reset: Callback for reset in cpu_exec. */ + void (*cpu_exec_reset)(CPUState *cpu); /** * @cpu_exec_halt: Callback for handling halt in cpu_exec. * @@ -181,6 +223,13 @@ struct TCGCPUOps { MMUAccessType access_type, int mmu_idx, bool probe, uintptr_t retaddr); /** + * @pointer_wrap: + * + * We have incremented @base to @result, resulting in a page change. + * For the current cpu state, adjust @result for possible overflow. + */ + vaddr (*pointer_wrap)(CPUState *cpu, int mmu_idx, vaddr result, vaddr base); + /** * @do_transaction_failed: Callback for handling failed memory transactions * (ie bus faults or external aborts; not MMU faults) */ @@ -273,6 +322,12 @@ void cpu_check_watchpoint(CPUState *cpu, vaddr addr, vaddr len, */ int cpu_watchpoint_address_matches(CPUState *cpu, vaddr addr, vaddr len); +/* + * Common pointer_wrap implementations. + */ +vaddr cpu_pointer_wrap_notreached(CPUState *, int, vaddr, vaddr); +vaddr cpu_pointer_wrap_uint32(CPUState *, int, vaddr, vaddr); + #endif #endif /* TCG_CPU_OPS_H */ diff --git a/include/accel/tcg/getpc.h b/include/accel/tcg/getpc.h index 8a97ce3..0fc08ad 100644 --- a/include/accel/tcg/getpc.h +++ b/include/accel/tcg/getpc.h @@ -8,10 +8,6 @@ #ifndef ACCEL_TCG_GETPC_H #define ACCEL_TCG_GETPC_H -#ifndef CONFIG_TCG -#error Can only include this header with TCG -#endif - /* GETPC is the true target of the return instruction that we'll execute. */ #ifdef CONFIG_TCG_INTERPRETER extern __thread uintptr_t tci_tb_ptr; diff --git a/include/accel/tcg/helper-retaddr.h b/include/accel/tcg/helper-retaddr.h new file mode 100644 index 0000000..037fda2 --- /dev/null +++ b/include/accel/tcg/helper-retaddr.h @@ -0,0 +1,43 @@ +/* + * Get user helper pc for memory unwinding. + * SPDX-License-Identifier: LGPL-2.1-or-later + */ + +#ifndef ACCEL_TCG_HELPER_RETADDR_H +#define ACCEL_TCG_HELPER_RETADDR_H + +/* + * For user-only, helpers that use guest to host address translation + * must protect the actual host memory access by recording 'retaddr' + * for the signal handler. This is required for a race condition in + * which another thread unmaps the page between a probe and the + * actual access. + */ +#ifdef CONFIG_USER_ONLY +extern __thread uintptr_t helper_retaddr; + +static inline void set_helper_retaddr(uintptr_t ra) +{ + helper_retaddr = ra; + /* + * Ensure that this write is visible to the SIGSEGV handler that + * may be invoked due to a subsequent invalid memory operation. + */ + signal_barrier(); +} + +static inline void clear_helper_retaddr(void) +{ + /* + * Ensure that previous memory operations have succeeded before + * removing the data visible to the signal handler. + */ + signal_barrier(); + helper_retaddr = 0; +} +#else +#define set_helper_retaddr(ra) do { } while (0) +#define clear_helper_retaddr() do { } while (0) +#endif + +#endif /* ACCEL_TCG_HELPER_RETADDR_H */ diff --git a/include/accel/tcg/iommu.h b/include/accel/tcg/iommu.h new file mode 100644 index 0000000..90cfd6c --- /dev/null +++ b/include/accel/tcg/iommu.h @@ -0,0 +1,41 @@ +/* + * TCG IOMMU translations. + * + * Copyright (c) 2003 Fabrice Bellard + * SPDX-License-Identifier: LGPL-2.1-or-later + */ +#ifndef ACCEL_TCG_IOMMU_H +#define ACCEL_TCG_IOMMU_H + +#ifdef CONFIG_USER_ONLY +#error Cannot include accel/tcg/iommu.h from user emulation +#endif + +#include "exec/hwaddr.h" +#include "exec/memattrs.h" + +/** + * iotlb_to_section: + * @cpu: CPU performing the access + * @index: TCG CPU IOTLB entry + * + * Given a TCG CPU IOTLB entry, return the MemoryRegionSection that + * it refers to. @index will have been initially created and returned + * by memory_region_section_get_iotlb(). + */ +MemoryRegionSection *iotlb_to_section(CPUState *cpu, + hwaddr index, MemTxAttrs attrs); + +MemoryRegionSection *address_space_translate_for_iotlb(CPUState *cpu, + int asidx, + hwaddr addr, + hwaddr *xlat, + hwaddr *plen, + MemTxAttrs attrs, + int *prot); + +hwaddr memory_region_section_get_iotlb(CPUState *cpu, + MemoryRegionSection *section); + +#endif + diff --git a/include/accel/tcg/probe.h b/include/accel/tcg/probe.h new file mode 100644 index 0000000..dd9ecbb --- /dev/null +++ b/include/accel/tcg/probe.h @@ -0,0 +1,122 @@ +/* + * Probe guest virtual addresses for access permissions. + * + * Copyright (c) 2003 Fabrice Bellard + * SPDX-License-Identifier: LGPL-2.1-or-later + */ +#ifndef ACCEL_TCG_PROBE_H +#define ACCEL_TCG_PROBE_H + +#include "exec/mmu-access-type.h" +#include "exec/vaddr.h" + +/** + * probe_access: + * @env: CPUArchState + * @addr: guest virtual address to look up + * @size: size of the access + * @access_type: read, write or execute permission + * @mmu_idx: MMU index to use for lookup + * @retaddr: return address for unwinding + * + * Look up the guest virtual address @addr. Raise an exception if the + * page does not satisfy @access_type. Raise an exception if the + * access (@addr, @size) hits a watchpoint. For writes, mark a clean + * page as dirty. + * + * Finally, return the host address for a page that is backed by RAM, + * or NULL if the page requires I/O. + */ +void *probe_access(CPUArchState *env, vaddr addr, int size, + MMUAccessType access_type, int mmu_idx, uintptr_t retaddr); + +static inline void *probe_write(CPUArchState *env, vaddr addr, int size, + int mmu_idx, uintptr_t retaddr) +{ + return probe_access(env, addr, size, MMU_DATA_STORE, mmu_idx, retaddr); +} + +static inline void *probe_read(CPUArchState *env, vaddr addr, int size, + int mmu_idx, uintptr_t retaddr) +{ + return probe_access(env, addr, size, MMU_DATA_LOAD, mmu_idx, retaddr); +} + +/** + * probe_access_flags: + * @env: CPUArchState + * @addr: guest virtual address to look up + * @size: size of the access + * @access_type: read, write or execute permission + * @mmu_idx: MMU index to use for lookup + * @nonfault: suppress the fault + * @phost: return value for host address + * @retaddr: return address for unwinding + * + * Similar to probe_access, loosely returning the TLB_FLAGS_MASK for + * the page, and storing the host address for RAM in @phost. + * + * If @nonfault is set, do not raise an exception but return TLB_INVALID_MASK. + * Do not handle watchpoints, but include TLB_WATCHPOINT in the returned flags. + * Do handle clean pages, so exclude TLB_NOTDIRY from the returned flags. + * For simplicity, all "mmio-like" flags are folded to TLB_MMIO. + */ +int probe_access_flags(CPUArchState *env, vaddr addr, int size, + MMUAccessType access_type, int mmu_idx, + bool nonfault, void **phost, uintptr_t retaddr); + +#ifndef CONFIG_USER_ONLY + +/** + * probe_access_full: + * Like probe_access_flags, except also return into @pfull. + * + * The CPUTLBEntryFull structure returned via @pfull is transient + * and must be consumed or copied immediately, before any further + * access or changes to TLB @mmu_idx. + * + * This function will not fault if @nonfault is set, but will + * return TLB_INVALID_MASK if the page is not mapped, or is not + * accessible with @access_type. + * + * This function will return TLB_MMIO in order to force the access + * to be handled out-of-line if plugins wish to instrument the access. + */ +int probe_access_full(CPUArchState *env, vaddr addr, int size, + MMUAccessType access_type, int mmu_idx, + bool nonfault, void **phost, + CPUTLBEntryFull **pfull, uintptr_t retaddr); + +/** + * probe_access_full_mmu: + * Like probe_access_full, except: + * + * This function is intended to be used for page table accesses by + * the target mmu itself. Since such page walking happens while + * handling another potential mmu fault, this function never raises + * exceptions (akin to @nonfault true for probe_access_full). + * Likewise this function does not trigger plugin instrumentation. + */ +int probe_access_full_mmu(CPUArchState *env, vaddr addr, int size, + MMUAccessType access_type, int mmu_idx, + void **phost, CPUTLBEntryFull **pfull); + +#endif /* !CONFIG_USER_ONLY */ + +/** + * tlb_vaddr_to_host: + * @env: CPUArchState + * @addr: guest virtual address to look up + * @access_type: 0 for read, 1 for write, 2 for execute + * @mmu_idx: MMU index to use for lookup + * + * Look up the specified guest virtual index in the TCG softmmu TLB. + * If we can translate a host virtual address suitable for direct RAM + * access, without causing a guest exception, then return it. + * Otherwise (TLB entry is for an I/O access, guest software + * TLB fill required, etc) return NULL. + */ +void *tlb_vaddr_to_host(CPUArchState *env, vaddr addr, + MMUAccessType access_type, int mmu_idx); + +#endif diff --git a/include/accel/tcg/tb-cpu-state.h b/include/accel/tcg/tb-cpu-state.h new file mode 100644 index 0000000..8f91290 --- /dev/null +++ b/include/accel/tcg/tb-cpu-state.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: LGPL-2.1-or-later */ +/* + * Definition of TCGTBCPUState. + */ + +#ifndef EXEC_TB_CPU_STATE_H +#define EXEC_TB_CPU_STATE_H + +#include "exec/vaddr.h" + +typedef struct TCGTBCPUState { + vaddr pc; + uint32_t flags; + uint32_t cflags; + uint64_t cs_base; +} TCGTBCPUState; + +#endif diff --git a/include/block/accounting.h b/include/block/accounting.h index a59e39f..b1cf417 100644 --- a/include/block/accounting.h +++ b/include/block/accounting.h @@ -101,8 +101,9 @@ typedef struct BlockAcctCookie { } BlockAcctCookie; void block_acct_init(BlockAcctStats *stats); -void block_acct_setup(BlockAcctStats *stats, enum OnOffAuto account_invalid, - enum OnOffAuto account_failed); +bool block_acct_setup(BlockAcctStats *stats, enum OnOffAuto account_invalid, + enum OnOffAuto account_failed, uint32_t *stats_intervals, + uint32_t num_stats_intervals, Error **errp); void block_acct_cleanup(BlockAcctStats *stats); void block_acct_add_interval(BlockAcctStats *stats, unsigned interval_length); BlockAcctTimedStats *block_acct_interval_next(BlockAcctStats *stats, diff --git a/include/block/aio.h b/include/block/aio.h index 99ff484..6049e6a 100644 --- a/include/block/aio.h +++ b/include/block/aio.h @@ -61,6 +61,27 @@ typedef struct LuringState LuringState; /* Is polling disabled? */ bool aio_poll_disabled(AioContext *ctx); +#ifdef CONFIG_LINUX_IO_URING +/* + * Each io_uring request must have a unique CqeHandler that processes the cqe. + * The lifetime of a CqeHandler must be at least from aio_add_sqe() until + * ->cb() invocation. + */ +typedef struct CqeHandler CqeHandler; +struct CqeHandler { + /* Called by the AioContext when the request has completed */ + void (*cb)(CqeHandler *handler); + + /* Used internally, do not access this */ + QSIMPLEQ_ENTRY(CqeHandler) next; + + /* This field is filled in before ->cb() is called */ + struct io_uring_cqe cqe; +}; + +typedef QSIMPLEQ_HEAD(, CqeHandler) CqeHandlerSimpleQ; +#endif /* CONFIG_LINUX_IO_URING */ + /* Callbacks for file descriptor monitoring implementations */ typedef struct { /* @@ -106,6 +127,78 @@ typedef struct { * Returns: true if ->wait() should be called, false otherwise. */ bool (*need_wait)(AioContext *ctx); + + /* + * dispatch: + * @ctx: the AioContext + * + * Dispatch any work that is specific to this file descriptor monitoring + * implementation. Usually the event loop's generic file descriptor + * monitoring, BH, and timer dispatching code is sufficient, but file + * descriptor monitoring implementations offering additional functionality + * may need to implement this function for custom behavior. Called at a + * point in the event loop when it is safe to invoke user-defined + * callbacks. + * + * This function is optional and may be NULL. + * + * Returns: true if progress was made (see aio_poll()'s return value), + * false otherwise. + */ + bool (*dispatch)(AioContext *ctx); + + /* + * gsource_prepare: + * @ctx: the AioContext + * + * Prepare for the glib event loop to wait for events instead of the usual + * ->wait() call. See glib's GSourceFuncs->prepare(). + */ + void (*gsource_prepare)(AioContext *ctx); + + /* + * gsource_check: + * @ctx: the AioContext + * + * Called by the glib event loop from glib's GSourceFuncs->check() after + * waiting for events. + * + * Returns: true when ready to be dispatched. + */ + bool (*gsource_check)(AioContext *ctx); + + /* + * gsource_dispatch: + * @ctx: the AioContext + * @ready_list: list for handlers that become ready + * + * Place ready AioHandlers on ready_list. Called as part of the glib event + * loop from glib's GSourceFuncs->dispatch(). + * + * Called with list_lock incremented. + */ + void (*gsource_dispatch)(AioContext *ctx, AioHandlerList *ready_list); + +#ifdef CONFIG_LINUX_IO_URING + /** + * add_sqe: Add an io_uring sqe for submission. + * @prep_sqe: invoked with an sqe that should be prepared for submission + * @opaque: user-defined argument to @prep_sqe() + * @cqe_handler: the unique cqe handler associated with this request + * + * The caller's @prep_sqe() function is invoked to fill in the details of + * the sqe. Do not call io_uring_sqe_set_data() on this sqe. + * + * The kernel may see the sqe as soon as @prep_sqe() returns or it may take + * until the next event loop iteration. + * + * This function is called from the current AioContext and is not + * thread-safe. + */ + void (*add_sqe)(AioContext *ctx, + void (*prep_sqe)(struct io_uring_sqe *sqe, void *opaque), + void *opaque, CqeHandler *cqe_handler); +#endif /* CONFIG_LINUX_IO_URING */ } FDMonOps; /* @@ -217,12 +310,14 @@ struct AioContext { struct LinuxAioState *linux_aio; #endif #ifdef CONFIG_LINUX_IO_URING - LuringState *linux_io_uring; - /* State for file descriptor monitoring using Linux io_uring */ struct io_uring fdmon_io_uring; AioHandlerSList submit_list; -#endif + void *io_uring_fd_tag; + + /* Pending callback state for cqe handlers */ + CqeHandlerSimpleQ cqe_handler_ready_list; +#endif /* CONFIG_LINUX_IO_URING */ /* TimerLists for calling timers - one per clock type. Has its own * locking. @@ -254,7 +349,13 @@ struct AioContext { /* epoll(7) state used when built with CONFIG_EPOLL */ int epollfd; + /* The GSource unix fd tag for epollfd */ + void *epollfd_tag; + const FDMonOps *fdmon_ops; + + /* Was aio_context_new() successful? */ + bool initialized; }; /** @@ -512,11 +613,6 @@ struct LinuxAioState *aio_setup_linux_aio(AioContext *ctx, Error **errp); /* Return the LinuxAioState bound to this AioContext */ struct LinuxAioState *aio_get_linux_aio(AioContext *ctx); -/* Setup the LuringState bound to this AioContext */ -LuringState *aio_setup_linux_io_uring(AioContext *ctx, Error **errp); - -/* Return the LuringState bound to this AioContext */ -LuringState *aio_get_linux_io_uring(AioContext *ctx); /** * aio_timer_new_with_attrs: * @ctx: the aio context @@ -650,6 +746,21 @@ void coroutine_fn aio_co_reschedule_self(AioContext *new_ctx); * aio_co_wake may be executed either in coroutine or non-coroutine * context. The coroutine must not be entered by anyone else while * aio_co_wake() is active. + * + * If `co`'s AioContext differs from the current AioContext, this will call + * aio_co_schedule(), which makes this safe to use even when `co` has not + * yielded yet. In such a case, it will be entered once it yields. + * + * In contrast, if `co`'s AioContext is equal to the current one, it is + * required for `co` to currently be yielding. This is generally the case + * if the caller is not in `co` (i.e. invoked by `co`), because the only + * other way for the caller to be running then is for `co` to currently be + * yielding. + * + * Therefore, if there is no way for the caller to be invoked/entered by + * `co`, it is generally safe to call this regardless of whether `co` is + * known to already be yielding or not -- it only has to yield at some + * point. */ void aio_co_wake(Coroutine *co); @@ -679,10 +790,13 @@ void qemu_set_current_aio_context(AioContext *ctx); /** * aio_context_setup: * @ctx: the aio context + * @errp: error pointer * * Initialize the aio context. + * + * Returns: true on success, false otherwise */ -void aio_context_setup(AioContext *ctx); +bool aio_context_setup(AioContext *ctx, Error **errp); /** * aio_context_destroy: @@ -692,9 +806,6 @@ void aio_context_setup(AioContext *ctx); */ void aio_context_destroy(AioContext *ctx); -/* Used internally, do not call outside AioContext code */ -void aio_context_use_g_source(AioContext *ctx); - /** * aio_context_set_poll_params: * @ctx: the aio context @@ -724,4 +835,40 @@ void aio_context_set_aio_params(AioContext *ctx, int64_t max_batch); */ void aio_context_set_thread_pool_params(AioContext *ctx, int64_t min, int64_t max, Error **errp); + +#ifdef CONFIG_LINUX_IO_URING +/** + * aio_has_io_uring: Return whether io_uring is available. + * + * io_uring is either available in all AioContexts or in none, so this only + * needs to be called once from within any thread's AioContext. + */ +static inline bool aio_has_io_uring(void) +{ + AioContext *ctx = qemu_get_current_aio_context(); + return ctx->fdmon_ops->add_sqe; +} + +/** + * aio_add_sqe: Add an io_uring sqe for submission. + * @prep_sqe: invoked with an sqe that should be prepared for submission + * @opaque: user-defined argument to @prep_sqe() + * @cqe_handler: the unique cqe handler associated with this request + * + * The caller's @prep_sqe() function is invoked to fill in the details of the + * sqe. Do not call io_uring_sqe_set_data() on this sqe. + * + * The sqe is submitted by the current AioContext. The kernel may see the sqe + * as soon as @prep_sqe() returns or it may take until the next event loop + * iteration. + * + * When the AioContext is destroyed, pending sqes are ignored and their + * CqeHandlers are not invoked. + * + * This function must be called only when aio_has_io_uring() returns true. + */ +void aio_add_sqe(void (*prep_sqe)(struct io_uring_sqe *sqe, void *opaque), + void *opaque, CqeHandler *cqe_handler); +#endif /* CONFIG_LINUX_IO_URING */ + #endif diff --git a/include/block/block-common.h b/include/block/block-common.h index 0b831ef..c8c626d 100644 --- a/include/block/block-common.h +++ b/include/block/block-common.h @@ -333,6 +333,17 @@ typedef enum { #define BDRV_BLOCK_RECURSE 0x40 #define BDRV_BLOCK_COMPRESSED 0x80 +/* + * Block status hints: the bitwise-or of these flags emphasize what + * the caller hopes to learn, and some drivers may be able to give + * faster answers by doing less work when the hint permits. + */ +#define BDRV_WANT_ZERO BDRV_BLOCK_ZERO +#define BDRV_WANT_OFFSET_VALID BDRV_BLOCK_OFFSET_VALID +#define BDRV_WANT_ALLOCATED BDRV_BLOCK_ALLOCATED +#define BDRV_WANT_PRECISE (BDRV_WANT_ZERO | BDRV_WANT_OFFSET_VALID | \ + BDRV_WANT_OFFSET_VALID) + typedef QTAILQ_HEAD(BlockReopenQueue, BlockReopenQueueEntry) BlockReopenQueue; typedef struct BDRVReopenState { diff --git a/include/block/block-global-state.h b/include/block/block-global-state.h index 9be34b3..479ca28 100644 --- a/include/block/block-global-state.h +++ b/include/block/block-global-state.h @@ -65,7 +65,8 @@ int co_wrapper bdrv_create(BlockDriver *drv, const char *filename, QemuOpts *opts, Error **errp); int coroutine_fn GRAPH_UNLOCKED -bdrv_co_create_file(const char *filename, QemuOpts *opts, Error **errp); +bdrv_co_create_file(const char *filename, QemuOpts *opts, + bool allow_protocol_prefix, Error **errp); BlockDriverState *bdrv_new(void); int bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top, @@ -74,13 +75,14 @@ int bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top, int GRAPH_WRLOCK bdrv_replace_node(BlockDriverState *from, BlockDriverState *to, Error **errp); -int bdrv_replace_child_bs(BdrvChild *child, BlockDriverState *new_bs, - Error **errp); -BlockDriverState *bdrv_insert_node(BlockDriverState *bs, QDict *node_options, - int flags, Error **errp); +int GRAPH_UNLOCKED +bdrv_replace_child_bs(BdrvChild *child, BlockDriverState *new_bs, Error **errp); +BlockDriverState * GRAPH_UNLOCKED +bdrv_insert_node(BlockDriverState *bs, QDict *node_options, int flags, + Error **errp); int bdrv_drop_filter(BlockDriverState *bs, Error **errp); -BdrvChild * no_coroutine_fn +BdrvChild * no_coroutine_fn GRAPH_UNLOCKED bdrv_open_child(const char *filename, QDict *options, const char *bdref_key, BlockDriverState *parent, const BdrvChildClass *child_class, BdrvChildRole child_role, bool allow_none, Error **errp); @@ -90,9 +92,10 @@ bdrv_co_open_child(const char *filename, QDict *options, const char *bdref_key, BlockDriverState *parent, const BdrvChildClass *child_class, BdrvChildRole child_role, bool allow_none, Error **errp); -int bdrv_open_file_child(const char *filename, - QDict *options, const char *bdref_key, - BlockDriverState *parent, Error **errp); +int GRAPH_UNLOCKED +bdrv_open_file_child(const char *filename, QDict *options, + const char *bdref_key, BlockDriverState *parent, + Error **errp); BlockDriverState * no_coroutine_fn bdrv_open_blockdev_ref(BlockdevRef *ref, Error **errp); @@ -100,11 +103,9 @@ bdrv_open_blockdev_ref(BlockdevRef *ref, Error **errp); BlockDriverState * coroutine_fn no_co_wrapper bdrv_co_open_blockdev_ref(BlockdevRef *ref, Error **errp); -int bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd, - Error **errp); int GRAPH_WRLOCK -bdrv_set_backing_hd_drained(BlockDriverState *bs, BlockDriverState *backing_hd, - Error **errp); +bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd, + Error **errp); int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options, const char *bdref_key, Error **errp); @@ -123,11 +124,12 @@ BlockDriverState *bdrv_new_open_driver_opts(BlockDriver *drv, Error **errp); BlockDriverState *bdrv_new_open_driver(BlockDriver *drv, const char *node_name, int flags, Error **errp); -BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue, - BlockDriverState *bs, QDict *options, - bool keep_old_opts); +BlockReopenQueue * GRAPH_UNLOCKED +bdrv_reopen_queue(BlockReopenQueue *bs_queue, BlockDriverState *bs, + QDict *options, bool keep_old_opts); void bdrv_reopen_queue_free(BlockReopenQueue *bs_queue); -int bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp); +int GRAPH_UNLOCKED +bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp); int bdrv_reopen(BlockDriverState *bs, QDict *opts, bool keep_old_opts, Error **errp); int bdrv_reopen_set_read_only(BlockDriverState *bs, bool read_only, @@ -143,9 +145,10 @@ int bdrv_commit(BlockDriverState *bs); int GRAPH_RDLOCK bdrv_make_empty(BdrvChild *c, Error **errp); void bdrv_register(BlockDriver *bdrv); -int bdrv_drop_intermediate(BlockDriverState *top, BlockDriverState *base, - const char *backing_file_str, - bool backing_mask_protocol); +int GRAPH_UNLOCKED +bdrv_drop_intermediate(BlockDriverState *top, BlockDriverState *base, + const char *backing_file_str, + bool backing_mask_protocol); BlockDriverState * GRAPH_RDLOCK bdrv_find_overlay(BlockDriverState *active, BlockDriverState *bs); @@ -184,18 +187,18 @@ bdrv_activate(BlockDriverState *bs, Error **errp); int coroutine_fn no_co_wrapper_bdrv_rdlock bdrv_co_activate(BlockDriverState *bs, Error **errp); -int no_coroutine_fn +int no_coroutine_fn GRAPH_RDLOCK bdrv_inactivate(BlockDriverState *bs, Error **errp); void bdrv_activate_all(Error **errp); -int bdrv_inactivate_all(void); +int GRAPH_UNLOCKED bdrv_inactivate_all(void); int bdrv_flush_all(void); -void bdrv_close_all(void); -void bdrv_drain_all_begin(void); +void GRAPH_UNLOCKED bdrv_close_all(void); +void GRAPH_UNLOCKED bdrv_drain_all_begin(void); void bdrv_drain_all_begin_nopoll(void); void bdrv_drain_all_end(void); -void bdrv_drain_all(void); +void GRAPH_UNLOCKED bdrv_drain_all(void); void bdrv_aio_cancel(BlockAIOCB *acb); @@ -274,11 +277,16 @@ int bdrv_debug_remove_breakpoint(BlockDriverState *bs, const char *tag); int bdrv_debug_resume(BlockDriverState *bs, const char *tag); bool bdrv_debug_is_suspended(BlockDriverState *bs, const char *tag); -bool bdrv_child_change_aio_context(BdrvChild *c, AioContext *ctx, - GHashTable *visited, Transaction *tran, - Error **errp); -int bdrv_try_change_aio_context(BlockDriverState *bs, AioContext *ctx, - BdrvChild *ignore_child, Error **errp); +bool GRAPH_RDLOCK +bdrv_child_change_aio_context(BdrvChild *c, AioContext *ctx, + GHashTable *visited, Transaction *tran, + Error **errp); +int GRAPH_UNLOCKED +bdrv_try_change_aio_context(BlockDriverState *bs, AioContext *ctx, + BdrvChild *ignore_child, Error **errp); +int GRAPH_RDLOCK +bdrv_try_change_aio_context_locked(BlockDriverState *bs, AioContext *ctx, + BdrvChild *ignore_child, Error **errp); int GRAPH_RDLOCK bdrv_probe_blocksizes(BlockDriverState *bs, BlockSizes *bsz); int bdrv_probe_geometry(BlockDriverState *bs, HDGeometry *geo); diff --git a/include/block/block-io.h b/include/block/block-io.h index b49e053..4cf83fb 100644 --- a/include/block/block-io.h +++ b/include/block/block-io.h @@ -161,6 +161,8 @@ bdrv_is_allocated_above(BlockDriverState *bs, BlockDriverState *base, int coroutine_fn GRAPH_RDLOCK bdrv_co_is_zero_fast(BlockDriverState *bs, int64_t offset, int64_t bytes); +int coroutine_fn GRAPH_RDLOCK +bdrv_co_is_all_zeroes(BlockDriverState *bs); int GRAPH_RDLOCK bdrv_apply_auto_read_only(BlockDriverState *bs, const char *errmsg, @@ -429,7 +431,7 @@ bdrv_drain_poll(BlockDriverState *bs, BdrvChild *ignore_parent, * * This function can be recursive. */ -void bdrv_drained_begin(BlockDriverState *bs); +void GRAPH_UNLOCKED bdrv_drained_begin(BlockDriverState *bs); /** * bdrv_do_drained_begin_quiesce: diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h index ebb4e56..cb0143e 100644 --- a/include/block/block_int-common.h +++ b/include/block/block_int-common.h @@ -248,7 +248,7 @@ struct BlockDriver { int GRAPH_UNLOCKED_PTR (*bdrv_open)( BlockDriverState *bs, QDict *options, int flags, Error **errp); - void (*bdrv_close)(BlockDriverState *bs); + void GRAPH_UNLOCKED_PTR (*bdrv_close)(BlockDriverState *bs); int coroutine_fn GRAPH_UNLOCKED_PTR (*bdrv_co_create)( BlockdevCreateOptions *opts, Error **errp); @@ -396,9 +396,23 @@ struct BlockDriver { int GRAPH_RDLOCK_PTR (*bdrv_probe_geometry)( BlockDriverState *bs, HDGeometry *geo); + /** + * Hot add a BDS's child. Used in combination with bdrv_del_child, so the + * user can take a child offline when it is broken and take a new child + * online. + * + * All block nodes must be drained. + */ void GRAPH_WRLOCK_PTR (*bdrv_add_child)( BlockDriverState *parent, BlockDriverState *child, Error **errp); + /** + * Hot remove a BDS's child. Used in combination with bdrv_add_child, so the + * user can take a child offline when it is broken and take a new child + * online. + * + * All block nodes must be drained. + */ void GRAPH_WRLOCK_PTR (*bdrv_del_child)( BlockDriverState *parent, BdrvChild *child, Error **errp); @@ -494,7 +508,12 @@ struct BlockDriver { BlockDriverState *bs, BlockdevAmendOptions *opts, bool force, Error **errp); - /* aio */ + /* + * AIO + * The given completion callback will be run in the same AioContext as the + * one in which the AIO function was called. + */ + BlockAIOCB * GRAPH_RDLOCK_PTR (*bdrv_aio_preadv)(BlockDriverState *bs, int64_t offset, int64_t bytes, QEMUIOVector *qiov, BdrvRequestFlags flags, BlockCompletionFunc *cb, void *opaque); @@ -506,10 +525,6 @@ struct BlockDriver { BlockAIOCB * GRAPH_RDLOCK_PTR (*bdrv_aio_flush)( BlockDriverState *bs, BlockCompletionFunc *cb, void *opaque); - BlockAIOCB * GRAPH_RDLOCK_PTR (*bdrv_aio_pdiscard)( - BlockDriverState *bs, int64_t offset, int bytes, - BlockCompletionFunc *cb, void *opaque); - int coroutine_fn GRAPH_RDLOCK_PTR (*bdrv_co_readv)(BlockDriverState *bs, int64_t sector_num, int nb_sectors, QEMUIOVector *qiov); @@ -608,15 +623,16 @@ struct BlockDriver { * according to the current layer, and should only need to set * BDRV_BLOCK_DATA, BDRV_BLOCK_ZERO, BDRV_BLOCK_OFFSET_VALID, * and/or BDRV_BLOCK_RAW; if the current layer defers to a backing - * layer, the result should be 0 (and not BDRV_BLOCK_ZERO). See - * block.h for the overall meaning of the bits. As a hint, the - * flag want_zero is true if the caller cares more about precise - * mappings (favor accurate _OFFSET_VALID/_ZERO) or false for - * overall allocation (favor larger *pnum, perhaps by reporting - * _DATA instead of _ZERO). The block layer guarantees input - * clamped to bdrv_getlength() and aligned to request_alignment, - * as well as non-NULL pnum, map, and file; in turn, the driver - * must return an error or set pnum to an aligned non-zero value. + * layer, the result should be 0 (and not BDRV_BLOCK_ZERO). The + * caller will synthesize BDRV_BLOCK_ALLOCATED based on the + * non-zero results. See block.h for the overall meaning of the + * bits. As a hint, the flags in @mode may include a bitwise-or + * of BDRV_WANT_ALLOCATED, BDRV_WANT_OFFSET_VALID, or + * BDRV_WANT_ZERO based on what the caller is looking for in the + * results. The block layer guarantees input clamped to + * bdrv_getlength() and aligned to request_alignment, as well as + * non-NULL pnum, map, and file; in turn, the driver must return + * an error or set pnum to an aligned non-zero value. * * Note that @bytes is just a hint on how big of a region the * caller wants to inspect. It is not a limit on *pnum. @@ -628,8 +644,8 @@ struct BlockDriver { * to clamping *pnum for return to its caller. */ int coroutine_fn GRAPH_RDLOCK_PTR (*bdrv_co_block_status)( - BlockDriverState *bs, - bool want_zero, int64_t offset, int64_t bytes, int64_t *pnum, + BlockDriverState *bs, unsigned int mode, + int64_t offset, int64_t bytes, int64_t *pnum, int64_t *map, BlockDriverState **file); /* @@ -653,8 +669,8 @@ struct BlockDriver { QEMUIOVector *qiov, size_t qiov_offset); int coroutine_fn GRAPH_RDLOCK_PTR (*bdrv_co_snapshot_block_status)( - BlockDriverState *bs, bool want_zero, int64_t offset, int64_t bytes, - int64_t *pnum, int64_t *map, BlockDriverState **file); + BlockDriverState *bs, unsigned int mode, int64_t offset, + int64_t bytes, int64_t *pnum, int64_t *map, BlockDriverState **file); int coroutine_fn GRAPH_RDLOCK_PTR (*bdrv_co_pdiscard_snapshot)( BlockDriverState *bs, int64_t offset, int64_t bytes); @@ -806,10 +822,10 @@ typedef struct BlockLimits { int64_t max_pdiscard; /* - * Optimal alignment for discard requests in bytes. A power of 2 - * is best but not mandatory. Must be a multiple of - * bl.request_alignment, and must be less than max_pdiscard if - * that is set. May be 0 if bl.request_alignment is good enough + * Optimal alignment for discard requests in bytes. Note that this doesn't + * have to be a power of two. Must be a multiple of bl.request_alignment, + * and must be less than max_pdiscard if that is set. May be 0 if + * bl.request_alignment is good enough. */ uint32_t pdiscard_alignment; @@ -820,11 +836,10 @@ typedef struct BlockLimits { int64_t max_pwrite_zeroes; /* - * Optimal alignment for write zeroes requests in bytes. A power - * of 2 is best but not mandatory. Must be a multiple of - * bl.request_alignment, and must be less than max_pwrite_zeroes - * if that is set. May be 0 if bl.request_alignment is good - * enough + * Optimal alignment for write zeroes requests in bytes. Note that this + * doesn't have to be a power of two. Must be a multiple of + * bl.request_alignment, and must be less than max_pwrite_zeroes if that is + * set. May be 0 if bl.request_alignment is good enough. */ uint32_t pwrite_zeroes_alignment; @@ -852,18 +867,23 @@ typedef struct BlockLimits { uint64_t max_hw_transfer; /* - * Maximal number of scatter/gather elements allowed by the hardware. + * Maximum number of scatter/gather elements allowed by the hardware. * Applies whenever transfers to the device bypass the kernel I/O * scheduler, for example with SG_IO. If larger than max_iov * or if zero, blk_get_max_hw_iov will fall back to max_iov. */ int max_hw_iov; - - /* memory alignment, in bytes so that no bounce buffer is needed */ + /* + * Minimal required memory alignment in bytes for zero-copy I/O to succeed. + * For unaligned requests, a bounce buffer will be used. + */ size_t min_mem_alignment; - /* memory alignment, in bytes, for bounce buffer */ + /* + * Optimal memory alignment in bytes. This is the alignment used for any + * buffer allocations QEMU performs internally. + */ size_t opt_mem_alignment; /* maximum number of iovec elements */ @@ -986,9 +1006,21 @@ struct BdrvChildClass { bool backing_mask_protocol, Error **errp); - bool (*change_aio_ctx)(BdrvChild *child, AioContext *ctx, - GHashTable *visited, Transaction *tran, - Error **errp); + /* + * Notifies the parent that the child is trying to change its AioContext. + * The parent may in turn change the AioContext of other nodes in the same + * transaction. Returns true if the change is possible and the transaction + * can be continued. Returns false and sets @errp if not and the transaction + * must be aborted. + * + * @visited will accumulate all visited BdrvChild objects. The caller is + * responsible for freeing the list afterwards. + * + * Must be called with the affected block nodes drained. + */ + bool GRAPH_RDLOCK_PTR (*change_aio_ctx)(BdrvChild *child, AioContext *ctx, + GHashTable *visited, + Transaction *tran, Error **errp); /* * I/O API functions. These functions are thread-safe. @@ -997,7 +1029,10 @@ struct BdrvChildClass { * the I/O API. */ - void (*resize)(BdrvChild *child); + /* + * Notifies the parent that the child was resized. + */ + void GRAPH_RDLOCK_PTR (*resize)(BdrvChild *child); /* * Returns a name that is supposedly more useful for human users than the @@ -1230,7 +1265,7 @@ struct BlockDriverState { /* do we need to tell the quest if we have a volatile write cache? */ int enable_write_cache; - /* Accessed with atomic ops. */ + /* Accessed only in the main thread. */ int quiesce_counter; unsigned int write_gen; /* Current data generation */ diff --git a/include/block/block_int-global-state.h b/include/block/block_int-global-state.h index eb2d92a..e7c8f1a 100644 --- a/include/block/block_int-global-state.h +++ b/include/block/block_int-global-state.h @@ -139,7 +139,7 @@ BlockJob *commit_active_start(const char *job_id, BlockDriverState *bs, * @buf_size: The amount of data that can be in flight at one time. * @mode: Whether to collapse all images in the chain to the target. * @backing_mode: How to establish the target's backing chain after completion. - * @zero_target: Whether the target should be explicitly zero-initialized + * @target_is_zero: Whether the target already is zero-initialized. * @on_source_error: The action to take upon error reading from the source. * @on_target_error: The action to take upon error writing to the target. * @unmap: Whether to unmap target where source sectors only contain zeroes. @@ -159,7 +159,7 @@ void mirror_start(const char *job_id, BlockDriverState *bs, int creation_flags, int64_t speed, uint32_t granularity, int64_t buf_size, MirrorSyncMode mode, BlockMirrorBackingMode backing_mode, - bool zero_target, + bool target_is_zero, BlockdevOnError on_source_error, BlockdevOnError on_target_error, bool unmap, const char *filter_node_name, @@ -179,6 +179,7 @@ void mirror_start(const char *job_id, BlockDriverState *bs, * all ".has_*" fields are ignored. * @on_source_error: The action to take upon error reading from the source. * @on_target_error: The action to take upon error writing to the target. + * @on_cbw_error: The action to take upon error in copy-before-write operations. * @creation_flags: Flags that control the behavior of the Job lifetime. * See @BlockJobCreateFlags * @cb: Completion function for the job. @@ -198,6 +199,7 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs, BackupPerf *perf, BlockdevOnError on_source_error, BlockdevOnError on_target_error, + OnCbwError on_cbw_error, int creation_flags, BlockCompletionFunc *cb, void *opaque, JobTxn *txn, Error **errp); diff --git a/include/block/block_int-io.h b/include/block/block_int-io.h index 4a7cf2b..ed8b565 100644 --- a/include/block/block_int-io.h +++ b/include/block/block_int-io.h @@ -38,8 +38,8 @@ int coroutine_fn GRAPH_RDLOCK bdrv_co_preadv_snapshot(BdrvChild *child, int64_t offset, int64_t bytes, QEMUIOVector *qiov, size_t qiov_offset); int coroutine_fn GRAPH_RDLOCK bdrv_co_snapshot_block_status( - BlockDriverState *bs, bool want_zero, int64_t offset, int64_t bytes, - int64_t *pnum, int64_t *map, BlockDriverState **file); + BlockDriverState *bs, unsigned int mode, int64_t offset, + int64_t bytes, int64_t *pnum, int64_t *map, BlockDriverState **file); int coroutine_fn GRAPH_RDLOCK bdrv_co_pdiscard_snapshot(BlockDriverState *bs, int64_t offset, int64_t bytes); @@ -191,4 +191,10 @@ void bdrv_bsc_invalidate_range(BlockDriverState *bs, */ void bdrv_bsc_fill(BlockDriverState *bs, int64_t offset, int64_t bytes); +/* + * Notify all parents that the size of the child changed. + */ +void coroutine_fn GRAPH_RDLOCK +bdrv_co_parent_cb_resize(BlockDriverState *bs); + #endif /* BLOCK_INT_IO_H */ diff --git a/include/block/blockjob.h b/include/block/blockjob.h index 7061ab7..85284cb 100644 --- a/include/block/blockjob.h +++ b/include/block/blockjob.h @@ -137,6 +137,8 @@ BlockJob *block_job_get_locked(const char *id); * Add @bs to the list of BlockDriverState that are involved in * @job. This means that all operations will be blocked on @bs while * @job exists. + * + * All block nodes must be drained. */ int GRAPH_WRLOCK block_job_add_bdrv(BlockJob *job, const char *name, BlockDriverState *bs, @@ -149,7 +151,7 @@ block_job_add_bdrv(BlockJob *job, const char *name, BlockDriverState *bs, * Remove all BlockDriverStates from the list of nodes that are involved in the * job. This removes the blockers added with block_job_add_bdrv(). */ -void block_job_remove_all_bdrv(BlockJob *job); +void GRAPH_UNLOCKED block_job_remove_all_bdrv(BlockJob *job); /** * block_job_has_bdrv: diff --git a/include/block/graph-lock.h b/include/block/graph-lock.h index 2c26c72..95bf5ed 100644 --- a/include/block/graph-lock.h +++ b/include/block/graph-lock.h @@ -113,9 +113,20 @@ void no_coroutine_fn TSA_ACQUIRE(graph_lock) TSA_NO_TSA bdrv_graph_wrlock(void); /* + * bdrv_graph_wrlock_drained: + * Similar to bdrv_graph_wrlock, but will begin a drained section before + * locking. + */ +void no_coroutine_fn TSA_ACQUIRE(graph_lock) TSA_NO_TSA +bdrv_graph_wrlock_drained(void); + +/* * bdrv_graph_wrunlock: * Write finished, reset global has_writer to 0 and restart * all readers that are waiting. + * + * Also ends the drained section if bdrv_graph_wrlock_drained() was used to lock + * the graph. */ void no_coroutine_fn TSA_RELEASE(graph_lock) TSA_NO_TSA bdrv_graph_wrunlock(void); diff --git a/include/block/nbd.h b/include/block/nbd.h index 92987c7..ab40842 100644 --- a/include/block/nbd.h +++ b/include/block/nbd.h @@ -296,7 +296,7 @@ enum { NBD_CMD_BLOCK_STATUS = 7, }; -#define NBD_DEFAULT_PORT 10809 +#define NBD_DEFAULT_PORT 10809 /* Maximum size of a single READ/WRITE data buffer */ #define NBD_MAX_BUFFER_SIZE (32 * 1024 * 1024) diff --git a/include/block/nvme.h b/include/block/nvme.h index 358e516..8640dfa 100644 --- a/include/block/nvme.h +++ b/include/block/nvme.h @@ -1589,7 +1589,7 @@ enum NvmeIdNsMc { enum NvmeIdNsNsfeat { NVME_ID_NS_NSFEAT_THINP = 1 << 0, - NVME_ID_NS_NSFEAT_NSABPNS = 1 << 1, + NVME_ID_NS_NSFEAT_NSABP = 1 << 1, NVME_ID_NS_NSFEAT_DAE = 1 << 2, NVME_ID_NS_NSFEAT_UIDREUSE = 1 << 3, NVME_ID_NS_NSFEAT_OPTPERF_ALL = 3 << 4, @@ -1779,6 +1779,21 @@ enum NvmeDirectiveOperations { NVME_DIRECTIVE_RETURN_PARAMS = 0x1, }; +typedef enum SfscSecurityProtocol { + SFSC_SECURITY_PROT_INFO = 0x00, +} SfscSecurityProtocol; + +typedef enum NvmeSecurityProtocols { + NVME_SEC_PROT_DMTF_SPDM = 0xE8, +} NvmeSecurityProtocols; + +typedef enum SpdmOperationCodes { + SPDM_STORAGE_DISCOVERY = 0x1, /* Mandatory */ + SPDM_STORAGE_PENDING_INFO = 0x2, /* Optional */ + SPDM_STORAGE_MSG = 0x5, /* Mandatory */ + SPDM_STORAGE_SEC_MSG = 0x6, /* Optional */ +} SpdmOperationCodes; + typedef struct QEMU_PACKED NvmeFdpConfsHdr { uint16_t num_confs; uint8_t version; diff --git a/include/block/qapi.h b/include/block/qapi.h index 54c48de..be554e5 100644 --- a/include/block/qapi.h +++ b/include/block/qapi.h @@ -42,7 +42,7 @@ bdrv_query_image_info(BlockDriverState *bs, ImageInfo **p_info, bool flat, bool skip_implicit_filters, Error **errp); void GRAPH_RDLOCK bdrv_query_block_graph_info(BlockDriverState *bs, BlockGraphInfo **p_info, - Error **errp); + bool limits, Error **errp); void bdrv_snapshot_dump(QEMUSnapshotInfo *sn); void bdrv_image_info_specific_dump(ImageInfoSpecific *info_spec, diff --git a/include/block/raw-aio.h b/include/block/raw-aio.h index 6570244..30e5fc9 100644 --- a/include/block/raw-aio.h +++ b/include/block/raw-aio.h @@ -74,15 +74,10 @@ static inline bool laio_has_fua(void) #endif /* io_uring.c - Linux io_uring implementation */ #ifdef CONFIG_LINUX_IO_URING -LuringState *luring_init(Error **errp); -void luring_cleanup(LuringState *s); - /* luring_co_submit: submit I/O requests in the thread's current AioContext. */ int coroutine_fn luring_co_submit(BlockDriverState *bs, int fd, uint64_t offset, QEMUIOVector *qiov, int type, BdrvRequestFlags flags); -void luring_detach_aio_context(LuringState *s, AioContext *old_context); -void luring_attach_aio_context(LuringState *s, AioContext *new_context); bool luring_has_fua(void); #else static inline bool luring_has_fua(void) diff --git a/include/block/snapshot.h b/include/block/snapshot.h index 304cc6e..2316a43 100644 --- a/include/block/snapshot.h +++ b/include/block/snapshot.h @@ -90,9 +90,9 @@ int bdrv_snapshot_load_tmp_by_id_or_name(BlockDriverState *bs, bool bdrv_all_can_snapshot(bool has_devices, strList *devices, Error **errp); -int bdrv_all_delete_snapshot(const char *name, - bool has_devices, strList *devices, - Error **errp); +int GRAPH_UNLOCKED +bdrv_all_delete_snapshot(const char *name, bool has_devices, strList *devices, + Error **errp); int bdrv_all_goto_snapshot(const char *name, bool has_devices, strList *devices, Error **errp); diff --git a/include/chardev/char-fd.h b/include/chardev/char-fd.h index 9de0e44..6fe4306 100644 --- a/include/chardev/char-fd.h +++ b/include/chardev/char-fd.h @@ -41,7 +41,7 @@ typedef struct FDChardev FDChardev; DECLARE_INSTANCE_CHECKER(FDChardev, FD_CHARDEV, TYPE_CHARDEV_FD) -void qemu_chr_open_fd(Chardev *chr, int fd_in, int fd_out); +bool qemu_chr_open_fd(Chardev *chr, int fd_in, int fd_out, Error **errp); int qmp_chardev_open_file_source(char *src, int flags, Error **errp); #endif /* CHAR_FD_H */ diff --git a/include/chardev/char-fe.h b/include/chardev/char-fe.h index 8ef05b3..5f8a6df 100644 --- a/include/chardev/char-fe.h +++ b/include/chardev/char-fe.h @@ -8,12 +8,12 @@ typedef void IOEventHandler(void *opaque, QEMUChrEvent event); typedef int BackendChangeHandler(void *opaque); /** - * struct CharBackend - back end as seen by front end + * struct CharFrontend - Chardev as seen by front end * @fe_is_open: the front end is ready for IO * * The actual backend is Chardev */ -struct CharBackend { +struct CharFrontend { Chardev *chr; IOEventHandler *chr_event; IOCanReadHandler *chr_can_read; @@ -27,53 +27,52 @@ struct CharBackend { /** * qemu_chr_fe_init: * - * Initializes a front end for the given CharBackend and - * Chardev. Call qemu_chr_fe_deinit() to remove the association and - * release the driver. + * Initializes the frontend @c for the given Chardev backend @s. Call + * qemu_chr_fe_deinit() to remove the association and release the backend. * * Returns: false on error. */ -bool qemu_chr_fe_init(CharBackend *b, Chardev *s, Error **errp); +bool qemu_chr_fe_init(CharFrontend *c, Chardev *be, Error **errp); /** * qemu_chr_fe_deinit: - * @b: a CharBackend + * @c: a CharFrontend * @del: if true, delete the chardev backend * - * Dissociate the CharBackend from the Chardev. + * Dissociate the CharFrontend from the Chardev. * * Safe to call without associated Chardev. */ -void qemu_chr_fe_deinit(CharBackend *b, bool del); +void qemu_chr_fe_deinit(CharFrontend *c, bool del); /** * qemu_chr_fe_get_driver: * - * Returns: the driver associated with a CharBackend or NULL if no + * Returns: the driver associated with a CharFrontend or NULL if no * associated Chardev. * Note: avoid this function as the driver should never be accessed directly, * especially by the frontends that support chardevice hotswap. * Consider qemu_chr_fe_backend_connected() to check for driver existence */ -Chardev *qemu_chr_fe_get_driver(CharBackend *be); +Chardev *qemu_chr_fe_get_driver(CharFrontend *c); /** * qemu_chr_fe_backend_connected: * - * Returns: true if there is a chardevice associated with @be. + * Returns: true if there is a backend associated with @c. */ -bool qemu_chr_fe_backend_connected(CharBackend *be); +bool qemu_chr_fe_backend_connected(CharFrontend *c); /** * qemu_chr_fe_backend_open: * - * Returns: true if chardevice associated with @be is open. + * Returns: true if the backend associated with @c is open. */ -bool qemu_chr_fe_backend_open(CharBackend *be); +bool qemu_chr_fe_backend_open(CharFrontend *c); /** * qemu_chr_fe_set_handlers_full: - * @b: a CharBackend + * @c: a CharFrontend * @fd_can_read: callback to get the amount of data the frontend may * receive * @fd_read: callback to receive data from char @@ -91,7 +90,7 @@ bool qemu_chr_fe_backend_open(CharBackend *be); * * Without associated Chardev, nothing is changed. */ -void qemu_chr_fe_set_handlers_full(CharBackend *b, +void qemu_chr_fe_set_handlers_full(CharFrontend *c, IOCanReadHandler *fd_can_read, IOReadHandler *fd_read, IOEventHandler *fd_event, @@ -106,7 +105,7 @@ void qemu_chr_fe_set_handlers_full(CharBackend *b, * * Version of qemu_chr_fe_set_handlers_full() with sync_state = true. */ -void qemu_chr_fe_set_handlers(CharBackend *b, +void qemu_chr_fe_set_handlers(CharFrontend *c, IOCanReadHandler *fd_can_read, IOReadHandler *fd_read, IOEventHandler *fd_event, @@ -122,14 +121,14 @@ void qemu_chr_fe_set_handlers(CharBackend *b, * * Without associated Chardev, nothing is changed. */ -void qemu_chr_fe_take_focus(CharBackend *b); +void qemu_chr_fe_take_focus(CharFrontend *c); /** * qemu_chr_fe_accept_input: * * Notify that the frontend is ready to receive data */ -void qemu_chr_fe_accept_input(CharBackend *be); +void qemu_chr_fe_accept_input(CharFrontend *c); /** * qemu_chr_fe_disconnect: @@ -137,7 +136,7 @@ void qemu_chr_fe_accept_input(CharBackend *be); * Close a fd accepted by character backend. * Without associated Chardev, do nothing. */ -void qemu_chr_fe_disconnect(CharBackend *be); +void qemu_chr_fe_disconnect(CharFrontend *c); /** * qemu_chr_fe_wait_connected: @@ -145,7 +144,7 @@ void qemu_chr_fe_disconnect(CharBackend *be); * Wait for character backend to be connected, return < 0 on error or * if no associated Chardev. */ -int qemu_chr_fe_wait_connected(CharBackend *be, Error **errp); +int qemu_chr_fe_wait_connected(CharFrontend *c, Error **errp); /** * qemu_chr_fe_set_echo: @@ -156,17 +155,17 @@ int qemu_chr_fe_wait_connected(CharBackend *be, Error **errp); * can see what you type if you try to type QMP commands. * Without associated Chardev, do nothing. */ -void qemu_chr_fe_set_echo(CharBackend *be, bool echo); +void qemu_chr_fe_set_echo(CharFrontend *c, bool echo); /** * qemu_chr_fe_set_open: - * @be: a CharBackend + * @c: a CharFrontend * @is_open: the front end open status * * This is an indication that the front end is ready (or not) to begin * doing I/O. Without associated Chardev, do nothing. */ -void qemu_chr_fe_set_open(CharBackend *be, bool is_open); +void qemu_chr_fe_set_open(CharFrontend *c, bool is_open); /** * qemu_chr_fe_printf: @@ -176,7 +175,7 @@ void qemu_chr_fe_set_open(CharBackend *be, bool is_open); * function is thread-safe. It does nothing without associated * Chardev. */ -void qemu_chr_fe_printf(CharBackend *be, const char *fmt, ...) +void qemu_chr_fe_printf(CharFrontend *c, const char *fmt, ...) G_GNUC_PRINTF(2, 3); @@ -215,7 +214,7 @@ typedef gboolean (*FEWatchFunc)(void *do_not_use, GIOCondition condition, void * * * Returns: the source tag */ -guint qemu_chr_fe_add_watch(CharBackend *be, GIOCondition cond, +guint qemu_chr_fe_add_watch(CharFrontend *c, GIOCondition cond, FEWatchFunc func, void *user_data); /** @@ -230,7 +229,7 @@ guint qemu_chr_fe_add_watch(CharBackend *be, GIOCondition cond, * Returns: the number of bytes consumed (0 if no associated Chardev) * or -1 on error. */ -int qemu_chr_fe_write(CharBackend *be, const uint8_t *buf, int len); +int qemu_chr_fe_write(CharFrontend *c, const uint8_t *buf, int len); /** * qemu_chr_fe_write_all: @@ -245,7 +244,7 @@ int qemu_chr_fe_write(CharBackend *be, const uint8_t *buf, int len); * Returns: the number of bytes consumed (0 if no associated Chardev) * or -1 on error. */ -int qemu_chr_fe_write_all(CharBackend *be, const uint8_t *buf, int len); +int qemu_chr_fe_write_all(CharFrontend *c, const uint8_t *buf, int len); /** * qemu_chr_fe_read_all: @@ -257,7 +256,7 @@ int qemu_chr_fe_write_all(CharBackend *be, const uint8_t *buf, int len); * Returns: the number of bytes read (0 if no associated Chardev) * or -1 on error. */ -int qemu_chr_fe_read_all(CharBackend *be, uint8_t *buf, int len); +int qemu_chr_fe_read_all(CharFrontend *c, uint8_t *buf, int len); /** * qemu_chr_fe_ioctl: @@ -270,7 +269,7 @@ int qemu_chr_fe_read_all(CharBackend *be, uint8_t *buf, int len); * associated Chardev, -ENOTSUP, otherwise the return * value depends on the semantics of @cmd */ -int qemu_chr_fe_ioctl(CharBackend *be, int cmd, void *arg); +int qemu_chr_fe_ioctl(CharFrontend *c, int cmd, void *arg); /** * qemu_chr_fe_get_msgfd: @@ -283,7 +282,7 @@ int qemu_chr_fe_ioctl(CharBackend *be, int cmd, void *arg); * this function will return -1 until a client sends a new file * descriptor. */ -int qemu_chr_fe_get_msgfd(CharBackend *be); +int qemu_chr_fe_get_msgfd(CharFrontend *c); /** * qemu_chr_fe_get_msgfds: @@ -296,7 +295,7 @@ int qemu_chr_fe_get_msgfd(CharBackend *be); * this function will return -1 until a client sends a new set of file * descriptors. */ -int qemu_chr_fe_get_msgfds(CharBackend *be, int *fds, int num); +int qemu_chr_fe_get_msgfds(CharFrontend *c, int *fds, int num); /** * qemu_chr_fe_set_msgfds: @@ -309,6 +308,6 @@ int qemu_chr_fe_get_msgfds(CharBackend *be, int *fds, int num); * * Returns: -1 if fd passing isn't supported or no associated Chardev. */ -int qemu_chr_fe_set_msgfds(CharBackend *be, int *fds, int num); +int qemu_chr_fe_set_msgfds(CharFrontend *c, int *fds, int num); #endif /* QEMU_CHAR_FE_H */ diff --git a/include/chardev/char.h b/include/chardev/char.h index 429852f..b65e998 100644 --- a/include/chardev/char.h +++ b/include/chardev/char.h @@ -15,7 +15,7 @@ #define IAC 255 /* character device */ -typedef struct CharBackend CharBackend; +typedef struct CharFrontend CharFrontend; typedef enum { CHR_EVENT_BREAK, /* serial break char */ @@ -60,7 +60,7 @@ struct Chardev { Object parent_obj; QemuMutex chr_write_lock; - CharBackend *be; + CharFrontend *fe; char *label; char *filename; int logfd; diff --git a/include/crypto/hash.h b/include/crypto/hash.h index 1868d4a..4352509 100644 --- a/include/crypto/hash.h +++ b/include/crypto/hash.h @@ -122,7 +122,7 @@ int qcrypto_hash_bytesv(QCryptoHashAlgo alg, * Returns: 0 on success, -1 on error */ int qcrypto_hash_bytes(QCryptoHashAlgo alg, - const char *buf, + const void *buf, size_t len, uint8_t **result, size_t *resultlen, @@ -180,7 +180,7 @@ int qcrypto_hash_updatev(QCryptoHash *hash, * Returns: 0 on success, -1 on error */ int qcrypto_hash_update(QCryptoHash *hash, - const char *buf, + const void *buf, size_t len, Error **errp); @@ -289,7 +289,7 @@ G_DEFINE_AUTOPTR_CLEANUP_FUNC(QCryptoHash, qcrypto_hash_free) * Returns: 0 on success, -1 on error */ int qcrypto_hash_digest(QCryptoHashAlgo alg, - const char *buf, + const void *buf, size_t len, char **digest, Error **errp); @@ -335,7 +335,7 @@ int qcrypto_hash_base64v(QCryptoHashAlgo alg, * Returns: 0 on success, -1 on error */ int qcrypto_hash_base64(QCryptoHashAlgo alg, - const char *buf, + const void *buf, size_t len, char **base64, Error **errp); diff --git a/include/crypto/hmac.h b/include/crypto/hmac.h index da8a1e3..0885ae2 100644 --- a/include/crypto/hmac.h +++ b/include/crypto/hmac.h @@ -90,6 +90,12 @@ G_DEFINE_AUTOPTR_CLEANUP_FUNC(QCryptoHmac, qcrypto_hmac_free) * The memory referenced in @result must be released with a call * to g_free() when no longer required by the caller. * + * If @result_len is set to a NULL pointer, no result will be returned, and + * the hmac object can be used for further invocations of qcrypto_hmac_bytes() + * or qcrypto_hmac_bytesv() until a non-NULL pointer is provided. This allows + * to build the hmac across memory regions that are not available at the same + * time. + * * Returns: * 0 on success, -1 on error */ @@ -123,11 +129,17 @@ int qcrypto_hmac_bytesv(QCryptoHmac *hmac, * The memory referenced in @result must be released with a call * to g_free() when no longer required by the caller. * + * If @result_len is set to a NULL pointer, no result will be returned, and + * the hmac object can be used for further invocations of qcrypto_hmac_bytes() + * or qcrypto_hmac_bytesv() until a non-NULL pointer is provided. This allows + * to build the hmac across memory regions that are not available at the same + * time. + * * Returns: * 0 on success, -1 on error */ int qcrypto_hmac_bytes(QCryptoHmac *hmac, - const char *buf, + const void *buf, size_t len, uint8_t **result, size_t *resultlen, @@ -175,7 +187,7 @@ int qcrypto_hmac_digestv(QCryptoHmac *hmac, * Returns: 0 on success, -1 on error */ int qcrypto_hmac_digest(QCryptoHmac *hmac, - const char *buf, + const void *buf, size_t len, char **digest, Error **errp); diff --git a/include/crypto/tlscreds.h b/include/crypto/tlscreds.h index 2a8a857..bb9280e 100644 --- a/include/crypto/tlscreds.h +++ b/include/crypto/tlscreds.h @@ -47,6 +47,7 @@ typedef bool (*CryptoTLSCredsReload)(QCryptoTLSCreds *, Error **); struct QCryptoTLSCredsClass { ObjectClass parent_class; CryptoTLSCredsReload reload; + const char *prioritySuffix; }; /** @@ -64,4 +65,29 @@ bool qcrypto_tls_creds_check_endpoint(QCryptoTLSCreds *creds, QCryptoTLSCredsEndpoint endpoint, Error **errp); + +/** + * qcrypto_tls_creds_get_priority: + * @creds: pointer to a TLS credentials object + * + * Get the TLS credentials priority string. The caller + * must free the returned string when no longer required. + * + * Returns: a non-NULL priority string + */ +char *qcrypto_tls_creds_get_priority(QCryptoTLSCreds *creds); + + +/** + * qcrypto_tls_creds_reload: + * @creds: pointer to a TLS credentials object + * @errp: pointer to a NULL-initialized error object + * + * Request a reload of the TLS credentials, if supported + * + * Returns: true on success, false on error or if not supported + */ +bool qcrypto_tls_creds_reload(QCryptoTLSCreds *creds, + Error **errp); + #endif /* QCRYPTO_TLSCREDS_H */ diff --git a/include/crypto/tlscredsx509.h b/include/crypto/tlscredsx509.h index c4daba2..61b7f73 100644 --- a/include/crypto/tlscredsx509.h +++ b/include/crypto/tlscredsx509.h @@ -37,7 +37,13 @@ typedef struct QCryptoTLSCredsX509Class QCryptoTLSCredsX509Class; #define QCRYPTO_TLS_CREDS_X509_SERVER_CERT "server-cert.pem" #define QCRYPTO_TLS_CREDS_X509_CLIENT_KEY "client-key.pem" #define QCRYPTO_TLS_CREDS_X509_CLIENT_CERT "client-cert.pem" +#define QCRYPTO_TLS_CREDS_X509_SERVER_KEY_N "server-key-%zu.pem" +#define QCRYPTO_TLS_CREDS_X509_SERVER_CERT_N "server-cert-%zu.pem" +#define QCRYPTO_TLS_CREDS_X509_CLIENT_KEY_N "client-key-%zu.pem" +#define QCRYPTO_TLS_CREDS_X509_CLIENT_CERT_N "client-cert-%zu.pem" +/* Max number of additional cert/key pairs (ie _N constants) */ +#define QCRYPTO_TLS_CREDS_X509_IDENTITY_MAX 4 /** * QCryptoTLSCredsX509: diff --git a/include/crypto/tlssession.h b/include/crypto/tlssession.h index d77ae0d..28e4196 100644 --- a/include/crypto/tlssession.h +++ b/include/crypto/tlssession.h @@ -110,6 +110,7 @@ typedef struct QCryptoTLSSession QCryptoTLSSession; #define QCRYPTO_TLS_SESSION_ERR_BLOCK -2 +#define QCRYPTO_TLS_SESSION_PREMATURE_TERMINATION -3 /** * qcrypto_tls_session_new: @@ -166,6 +167,20 @@ void qcrypto_tls_session_free(QCryptoTLSSession *sess); G_DEFINE_AUTOPTR_CLEANUP_FUNC(QCryptoTLSSession, qcrypto_tls_session_free) /** + * qcrypto_tls_session_require_thread_safety: + * @sess: the TLS session object + * + * Mark that this TLS session will require thread safety + * for concurrent I/O in both directions. This must be + * called before the handshake is performed. + * + * This will activate a workaround for GNUTLS thread + * safety issues, where appropriate for the negotiated + * TLS session parameters. + */ +void qcrypto_tls_session_require_thread_safety(QCryptoTLSSession *sess); + +/** * qcrypto_tls_session_check_credentials: * @sess: the TLS session object * @errp: pointer to a NULL-initialized error object @@ -184,11 +199,11 @@ int qcrypto_tls_session_check_credentials(QCryptoTLSSession *sess, * These must return QCRYPTO_TLS_SESSION_ERR_BLOCK if the I/O * would block, but on other errors, must fill 'errp' */ -typedef ssize_t (*QCryptoTLSSessionWriteFunc)(const char *buf, +typedef ssize_t (*QCryptoTLSSessionWriteFunc)(const void *buf, size_t len, void *opaque, Error **errp); -typedef ssize_t (*QCryptoTLSSessionReadFunc)(char *buf, +typedef ssize_t (*QCryptoTLSSessionReadFunc)(void *buf, size_t len, void *opaque, Error **errp); @@ -245,7 +260,6 @@ ssize_t qcrypto_tls_session_write(QCryptoTLSSession *sess, * @sess: the TLS session object * @buf: to fill with plain text received * @len: the length of @buf - * @gracefulTermination: treat premature termination as graceful EOF * @errp: pointer to hold returned error object * * Receive up to @len bytes of data from the remote peer @@ -253,22 +267,18 @@ ssize_t qcrypto_tls_session_write(QCryptoTLSSession *sess, * qcrypto_tls_session_set_callbacks(), decrypt it and * store it in @buf. * - * If @gracefulTermination is true, then a premature termination - * of the TLS session will be treated as indicating EOF, as - * opposed to an error. - * * It is an error to call this before * qcrypto_tls_session_handshake() returns * QCRYPTO_TLS_HANDSHAKE_COMPLETE * * Returns: the number of bytes received, * or QCRYPTO_TLS_SESSION_ERR_BLOCK if the receive would block, - * or -1 on error. + * or QCRYPTO_TLS_SESSION_PREMATURE_TERMINATION if a premature termination + * is detected, or -1 on error. */ ssize_t qcrypto_tls_session_read(QCryptoTLSSession *sess, char *buf, size_t len, - bool gracefulTermination, Error **errp); /** diff --git a/include/crypto/xts.h b/include/crypto/xts.h deleted file mode 100644 index f267b78..0000000 --- a/include/crypto/xts.h +++ /dev/null @@ -1,82 +0,0 @@ -/* - * QEMU Crypto XTS cipher mode - * - * Copyright (c) 2015-2016 Red Hat, Inc. - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see <http://www.gnu.org/licenses/>. - * - * This code is originally derived from public domain / WTFPL code in - * LibTomCrypt crytographic library http://libtom.org. The XTS code - * was donated by Elliptic Semiconductor Inc (www.ellipticsemi.com) - * to the LibTom Projects - * - */ - -#ifndef QCRYPTO_XTS_H -#define QCRYPTO_XTS_H - - -#define XTS_BLOCK_SIZE 16 - -typedef void xts_cipher_func(const void *ctx, - size_t length, - uint8_t *dst, - const uint8_t *src); - -/** - * xts_decrypt: - * @datactx: the cipher context for data decryption - * @tweakctx: the cipher context for tweak decryption - * @encfunc: the cipher function for encryption - * @decfunc: the cipher function for decryption - * @iv: the initialization vector tweak of XTS_BLOCK_SIZE bytes - * @length: the length of @dst and @src - * @dst: buffer to hold the decrypted plaintext - * @src: buffer providing the ciphertext - * - * Decrypts @src into @dst - */ -void xts_decrypt(const void *datactx, - const void *tweakctx, - xts_cipher_func *encfunc, - xts_cipher_func *decfunc, - uint8_t *iv, - size_t length, - uint8_t *dst, - const uint8_t *src); - -/** - * xts_decrypt: - * @datactx: the cipher context for data encryption - * @tweakctx: the cipher context for tweak encryption - * @encfunc: the cipher function for encryption - * @decfunc: the cipher function for decryption - * @iv: the initialization vector tweak of XTS_BLOCK_SIZE bytes - * @length: the length of @dst and @src - * @dst: buffer to hold the encrypted ciphertext - * @src: buffer providing the plaintext - * - * Decrypts @src into @dst - */ -void xts_encrypt(const void *datactx, - const void *tweakctx, - xts_cipher_func *encfunc, - xts_cipher_func *decfunc, - uint8_t *iv, - size_t length, - uint8_t *dst, - const uint8_t *src); - - -#endif /* QCRYPTO_XTS_H */ diff --git a/include/elf.h b/include/elf.h index e7259ec..bbfac05 100644 --- a/include/elf.h +++ b/include/elf.h @@ -56,6 +56,13 @@ typedef int64_t Elf64_Sxword; #define EF_MIPS_ARCH_32R6 0x90000000 /* MIPS32r6 code. */ #define EF_MIPS_ARCH_64R6 0xa0000000 /* MIPS64r6 code. */ +/* MIPS Architectural Extensions. */ +#define EF_MIPS_ARCH_ASE 0x0f000000 + +#define EF_MIPS_ARCH_ASE_MICROMIPS 0x02000000 +#define EF_MIPS_ARCH_ASE_M16 0x04000000 +#define EF_MIPS_ARCH_ASE_MDMX 0x08000000 + /* The ABI of a file. */ #define EF_MIPS_ABI_O32 0x00001000 /* O32 ABI. */ #define EF_MIPS_ABI_O64 0x00002000 /* O32 extended for 64 bit. */ diff --git a/include/exec/cpu-all.h b/include/exec/cpu-all.h deleted file mode 100644 index 47b1444..0000000 --- a/include/exec/cpu-all.h +++ /dev/null @@ -1,176 +0,0 @@ -/* - * defines common to all virtual CPUs - * - * Copyright (c) 2003 Fabrice Bellard - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see <http://www.gnu.org/licenses/>. - */ -#ifndef CPU_ALL_H -#define CPU_ALL_H - -#include "exec/page-protection.h" -#include "exec/cpu-common.h" -#include "exec/cpu-interrupt.h" -#include "exec/memory.h" -#include "exec/tswap.h" -#include "hw/core/cpu.h" - -/* Target-endianness CPU memory access functions. These fit into the - * {ld,st}{type}{sign}{size}{endian}_p naming scheme described in bswap.h. - */ -#if TARGET_BIG_ENDIAN -#define lduw_p(p) lduw_be_p(p) -#define ldsw_p(p) ldsw_be_p(p) -#define ldl_p(p) ldl_be_p(p) -#define ldq_p(p) ldq_be_p(p) -#define stw_p(p, v) stw_be_p(p, v) -#define stl_p(p, v) stl_be_p(p, v) -#define stq_p(p, v) stq_be_p(p, v) -#define ldn_p(p, sz) ldn_be_p(p, sz) -#define stn_p(p, sz, v) stn_be_p(p, sz, v) -#else -#define lduw_p(p) lduw_le_p(p) -#define ldsw_p(p) ldsw_le_p(p) -#define ldl_p(p) ldl_le_p(p) -#define ldq_p(p) ldq_le_p(p) -#define stw_p(p, v) stw_le_p(p, v) -#define stl_p(p, v) stl_le_p(p, v) -#define stq_p(p, v) stq_le_p(p, v) -#define ldn_p(p, sz) ldn_le_p(p, sz) -#define stn_p(p, sz, v) stn_le_p(p, sz, v) -#endif - -/* MMU memory access macros */ - -#if !defined(CONFIG_USER_ONLY) - -#include "exec/hwaddr.h" - -#define SUFFIX -#define ARG1 as -#define ARG1_DECL AddressSpace *as -#define TARGET_ENDIANNESS -#include "exec/memory_ldst.h.inc" - -#define SUFFIX _cached_slow -#define ARG1 cache -#define ARG1_DECL MemoryRegionCache *cache -#define TARGET_ENDIANNESS -#include "exec/memory_ldst.h.inc" - -static inline void stl_phys_notdirty(AddressSpace *as, hwaddr addr, uint32_t val) -{ - address_space_stl_notdirty(as, addr, val, - MEMTXATTRS_UNSPECIFIED, NULL); -} - -#define SUFFIX -#define ARG1 as -#define ARG1_DECL AddressSpace *as -#define TARGET_ENDIANNESS -#include "exec/memory_ldst_phys.h.inc" - -/* Inline fast path for direct RAM access. */ -#define ENDIANNESS -#include "exec/memory_ldst_cached.h.inc" - -#define SUFFIX _cached -#define ARG1 cache -#define ARG1_DECL MemoryRegionCache *cache -#define TARGET_ENDIANNESS -#include "exec/memory_ldst_phys.h.inc" -#endif - -/* page related stuff */ -#include "exec/cpu-defs.h" -#include "exec/target_page.h" - -CPUArchState *cpu_copy(CPUArchState *env); - -#include "cpu.h" - -#ifdef CONFIG_USER_ONLY - -static inline int cpu_mmu_index(CPUState *cs, bool ifetch); - -/* - * Allow some level of source compatibility with softmmu. We do not - * support any of the more exotic features, so only invalid pages may - * be signaled by probe_access_flags(). - */ -#define TLB_INVALID_MASK (1 << (TARGET_PAGE_BITS_MIN - 1)) -#define TLB_MMIO (1 << (TARGET_PAGE_BITS_MIN - 2)) -#define TLB_WATCHPOINT 0 - -static inline int cpu_mmu_index(CPUState *cs, bool ifetch) -{ - return MMU_USER_IDX; -} -#else - -/* - * Flags stored in the low bits of the TLB virtual address. - * These are defined so that fast path ram access is all zeros. - * The flags all must be between TARGET_PAGE_BITS and - * maximum address alignment bit. - * - * Use TARGET_PAGE_BITS_MIN so that these bits are constant - * when TARGET_PAGE_BITS_VARY is in effect. - * - * The count, if not the placement of these bits is known - * to tcg/tcg-op-ldst.c, check_max_alignment(). - */ -/* Zero if TLB entry is valid. */ -#define TLB_INVALID_MASK (1 << (TARGET_PAGE_BITS_MIN - 1)) -/* Set if TLB entry references a clean RAM page. The iotlb entry will - contain the page physical address. */ -#define TLB_NOTDIRTY (1 << (TARGET_PAGE_BITS_MIN - 2)) -/* Set if TLB entry is an IO callback. */ -#define TLB_MMIO (1 << (TARGET_PAGE_BITS_MIN - 3)) -/* Set if TLB entry writes ignored. */ -#define TLB_DISCARD_WRITE (1 << (TARGET_PAGE_BITS_MIN - 4)) -/* Set if the slow path must be used; more flags in CPUTLBEntryFull. */ -#define TLB_FORCE_SLOW (1 << (TARGET_PAGE_BITS_MIN - 5)) - -/* - * Use this mask to check interception with an alignment mask - * in a TCG backend. - */ -#define TLB_FLAGS_MASK \ - (TLB_INVALID_MASK | TLB_NOTDIRTY | TLB_MMIO \ - | TLB_FORCE_SLOW | TLB_DISCARD_WRITE) - -/* - * Flags stored in CPUTLBEntryFull.slow_flags[x]. - * TLB_FORCE_SLOW must be set in CPUTLBEntry.addr_idx[x]. - */ -/* Set if TLB entry requires byte swap. */ -#define TLB_BSWAP (1 << 0) -/* Set if TLB entry contains a watchpoint. */ -#define TLB_WATCHPOINT (1 << 1) -/* Set if TLB entry requires aligned accesses. */ -#define TLB_CHECK_ALIGNED (1 << 2) - -#define TLB_SLOW_FLAGS_MASK (TLB_BSWAP | TLB_WATCHPOINT | TLB_CHECK_ALIGNED) - -/* The two sets of flags must not overlap. */ -QEMU_BUILD_BUG_ON(TLB_FLAGS_MASK & TLB_SLOW_FLAGS_MASK); - -#endif /* !CONFIG_USER_ONLY */ - -/* Validate correct placement of CPUArchState. */ -QEMU_BUILD_BUG_ON(offsetof(ArchCPU, parent_obj) != 0); -QEMU_BUILD_BUG_ON(offsetof(ArchCPU, env) != sizeof(CPUState)); - -#endif /* CPU_ALL_H */ diff --git a/include/exec/cpu-common.h b/include/exec/cpu-common.h index 3771b21..e0be4ee 100644 --- a/include/exec/cpu-common.h +++ b/include/exec/cpu-common.h @@ -9,9 +9,7 @@ #define CPU_COMMON_H #include "exec/vaddr.h" -#ifndef CONFIG_USER_ONLY #include "exec/hwaddr.h" -#endif #include "hw/core/cpu.h" #include "tcg/debug-assert.h" #include "exec/page-protection.h" @@ -40,20 +38,12 @@ int cpu_get_free_index(void); void tcg_iommu_init_notifier_list(CPUState *cpu); void tcg_iommu_free_notifier_list(CPUState *cpu); -#if !defined(CONFIG_USER_ONLY) - enum device_endian { DEVICE_NATIVE_ENDIAN, DEVICE_BIG_ENDIAN, DEVICE_LITTLE_ENDIAN, }; -#if HOST_BIG_ENDIAN -#define DEVICE_HOST_ENDIAN DEVICE_BIG_ENDIAN -#else -#define DEVICE_HOST_ENDIAN DEVICE_LITTLE_ENDIAN -#endif - /* address in the RAM (different from a physical address) */ #if defined(CONFIG_XEN_BACKEND) typedef uint64_t ram_addr_t; @@ -95,6 +85,7 @@ void qemu_ram_unset_idstr(RAMBlock *block); const char *qemu_ram_get_idstr(RAMBlock *rb); void *qemu_ram_get_host_addr(RAMBlock *rb); ram_addr_t qemu_ram_get_offset(RAMBlock *rb); +ram_addr_t qemu_ram_get_fd_offset(RAMBlock *rb); ram_addr_t qemu_ram_get_used_length(RAMBlock *rb); ram_addr_t qemu_ram_get_max_length(RAMBlock *rb); bool qemu_ram_is_shared(RAMBlock *rb); @@ -132,34 +123,22 @@ size_t qemu_ram_pagesize_largest(void); void cpu_address_space_init(CPUState *cpu, int asidx, const char *prefix, MemoryRegion *mr); /** - * cpu_address_space_destroy: - * @cpu: CPU for which address space needs to be destroyed - * @asidx: integer index of this address space + * cpu_destroy_address_spaces: + * @cpu: CPU for which address spaces need to be destroyed * - * Note that with KVM only one address space is supported. + * Destroy all address spaces associated with this CPU; this + * is called as part of unrealizing the CPU. */ -void cpu_address_space_destroy(CPUState *cpu, int asidx); +void cpu_destroy_address_spaces(CPUState *cpu); -void cpu_physical_memory_rw(hwaddr addr, void *buf, - hwaddr len, bool is_write); -static inline void cpu_physical_memory_read(hwaddr addr, - void *buf, hwaddr len) -{ - cpu_physical_memory_rw(addr, buf, len, false); -} -static inline void cpu_physical_memory_write(hwaddr addr, - const void *buf, hwaddr len) -{ - cpu_physical_memory_rw(addr, (void *)buf, len, true); -} +void cpu_physical_memory_read(hwaddr addr, void *buf, hwaddr len); +void cpu_physical_memory_write(hwaddr addr, const void *buf, hwaddr len); void *cpu_physical_memory_map(hwaddr addr, hwaddr *plen, bool is_write); void cpu_physical_memory_unmap(void *buffer, hwaddr len, bool is_write, hwaddr access_len); -bool cpu_physical_memory_is_io(hwaddr phys_addr); - /* Coalesced MMIO regions are areas where write operations can be reordered. * This usually implies that write operations are side-effect free. This allows * batching which can make a major impact on performance when using @@ -167,20 +146,9 @@ bool cpu_physical_memory_is_io(hwaddr phys_addr); */ void qemu_flush_coalesced_mmio_buffer(void); -void cpu_flush_icache_range(hwaddr start, hwaddr len); - typedef int (RAMBlockIterFunc)(RAMBlock *rb, void *opaque); int qemu_ram_foreach_block(RAMBlockIterFunc func, void *opaque); -int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length); -int ram_block_discard_guest_memfd_range(RAMBlock *rb, uint64_t start, - size_t length); - -#endif - -/* Returns: 0 on success, -1 on error */ -int cpu_memory_rw_debug(CPUState *cpu, vaddr addr, - void *ptr, size_t len, bool is_write); /* vl.c */ void list_cpus(void); @@ -194,7 +162,7 @@ void list_cpus(void); * @host_pc: the host pc within the translation * @data: output data * - * Attempt to load the the unwind state for a host pc occurring in + * Attempt to load the unwind state for a host pc occurring in * translated code. If @host_pc is not in translated code, the * function returns false; otherwise @data is loaded. * This is the same unwind info as given to restore_state_to_opc. @@ -232,9 +200,9 @@ static inline bool cpu_loop_exit_requested(CPUState *cpu) G_NORETURN void cpu_loop_exit_noexc(CPUState *cpu); G_NORETURN void cpu_loop_exit_atomic(CPUState *cpu, uintptr_t pc); +G_NORETURN void cpu_loop_exit_restore(CPUState *cpu, uintptr_t pc); #endif /* CONFIG_TCG */ G_NORETURN void cpu_loop_exit(CPUState *cpu); -G_NORETURN void cpu_loop_exit_restore(CPUState *cpu, uintptr_t pc); /* accel/tcg/cpu-exec.c */ int cpu_exec(CPUState *cpu); @@ -272,24 +240,4 @@ static inline CPUState *env_cpu(CPUArchState *env) return (CPUState *)env_cpu_const(env); } -#ifndef CONFIG_USER_ONLY -/** - * cpu_mmu_index: - * @env: The cpu environment - * @ifetch: True for code access, false for data access. - * - * Return the core mmu index for the current translation regime. - * This function is used by generic TCG code paths. - * - * The user-only version of this function is inline in cpu-all.h, - * where it always returns MMU_USER_IDX. - */ -static inline int cpu_mmu_index(CPUState *cs, bool ifetch) -{ - int ret = cs->cc->mmu_index(cs, ifetch); - tcg_debug_assert(ret >= 0 && ret < NB_MMU_MODES); - return ret; -} -#endif /* !CONFIG_USER_ONLY */ - #endif /* CPU_COMMON_H */ diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h index 9f955f5..e01acb7 100644 --- a/include/exec/cpu-defs.h +++ b/include/exec/cpu-defs.h @@ -34,14 +34,8 @@ #ifndef TARGET_VIRT_ADDR_SPACE_BITS # error TARGET_VIRT_ADDR_SPACE_BITS must be defined in cpu-param.h #endif -#ifndef TARGET_PAGE_BITS -# ifdef TARGET_PAGE_BITS_VARY -# ifndef TARGET_PAGE_BITS_MIN -# error TARGET_PAGE_BITS_MIN must be defined in cpu-param.h -# endif -# else -# error TARGET_PAGE_BITS must be defined in cpu-param.h -# endif +#if !defined(TARGET_PAGE_BITS) && !defined(TARGET_PAGE_BITS_VARY) +# error TARGET_PAGE_BITS must be defined in cpu-param.h #endif #include "exec/target_long.h" diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h deleted file mode 100644 index 769e9fc..0000000 --- a/include/exec/cpu_ldst.h +++ /dev/null @@ -1,372 +0,0 @@ -/* - * Software MMU support (per-target) - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see <http://www.gnu.org/licenses/>. - * - */ - -/* - * Generate inline load/store functions for all MMU modes (typically - * at least _user and _kernel) as well as _data versions, for all data - * sizes. - * - * Used by target op helpers. - * - * The syntax for the accessors is: - * - * load: cpu_ld{sign}{size}{end}_{mmusuffix}(env, ptr) - * cpu_ld{sign}{size}{end}_{mmusuffix}_ra(env, ptr, retaddr) - * cpu_ld{sign}{size}{end}_mmuidx_ra(env, ptr, mmu_idx, retaddr) - * cpu_ld{sign}{size}{end}_mmu(env, ptr, oi, retaddr) - * - * store: cpu_st{size}{end}_{mmusuffix}(env, ptr, val) - * cpu_st{size}{end}_{mmusuffix}_ra(env, ptr, val, retaddr) - * cpu_st{size}{end}_mmuidx_ra(env, ptr, val, mmu_idx, retaddr) - * cpu_st{size}{end}_mmu(env, ptr, val, oi, retaddr) - * - * sign is: - * (empty): for 32 and 64 bit sizes - * u : unsigned - * s : signed - * - * size is: - * b: 8 bits - * w: 16 bits - * l: 32 bits - * q: 64 bits - * - * end is: - * (empty): for target native endian, or for 8 bit access - * _be: for forced big endian - * _le: for forced little endian - * - * mmusuffix is one of the generic suffixes "data" or "code", or "mmuidx". - * The "mmuidx" suffix carries an extra mmu_idx argument that specifies - * the index to use; the "data" and "code" suffixes take the index from - * cpu_mmu_index(). - * - * The "mmu" suffix carries the full MemOpIdx, with both mmu_idx and the - * MemOp including alignment requirements. The alignment will be enforced. - */ -#ifndef CPU_LDST_H -#define CPU_LDST_H - -#ifndef CONFIG_TCG -#error Can only include this header with TCG -#endif - -#include "exec/memopidx.h" -#include "exec/vaddr.h" -#include "exec/abi_ptr.h" -#include "exec/mmu-access-type.h" -#include "qemu/int128.h" - -#if defined(CONFIG_USER_ONLY) -#include "user/guest-host.h" -#endif /* CONFIG_USER_ONLY */ - -uint32_t cpu_ldub_data(CPUArchState *env, abi_ptr ptr); -int cpu_ldsb_data(CPUArchState *env, abi_ptr ptr); -uint32_t cpu_lduw_be_data(CPUArchState *env, abi_ptr ptr); -int cpu_ldsw_be_data(CPUArchState *env, abi_ptr ptr); -uint32_t cpu_ldl_be_data(CPUArchState *env, abi_ptr ptr); -uint64_t cpu_ldq_be_data(CPUArchState *env, abi_ptr ptr); -uint32_t cpu_lduw_le_data(CPUArchState *env, abi_ptr ptr); -int cpu_ldsw_le_data(CPUArchState *env, abi_ptr ptr); -uint32_t cpu_ldl_le_data(CPUArchState *env, abi_ptr ptr); -uint64_t cpu_ldq_le_data(CPUArchState *env, abi_ptr ptr); - -uint32_t cpu_ldub_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t ra); -int cpu_ldsb_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t ra); -uint32_t cpu_lduw_be_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t ra); -int cpu_ldsw_be_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t ra); -uint32_t cpu_ldl_be_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t ra); -uint64_t cpu_ldq_be_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t ra); -uint32_t cpu_lduw_le_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t ra); -int cpu_ldsw_le_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t ra); -uint32_t cpu_ldl_le_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t ra); -uint64_t cpu_ldq_le_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t ra); - -void cpu_stb_data(CPUArchState *env, abi_ptr ptr, uint32_t val); -void cpu_stw_be_data(CPUArchState *env, abi_ptr ptr, uint32_t val); -void cpu_stl_be_data(CPUArchState *env, abi_ptr ptr, uint32_t val); -void cpu_stq_be_data(CPUArchState *env, abi_ptr ptr, uint64_t val); -void cpu_stw_le_data(CPUArchState *env, abi_ptr ptr, uint32_t val); -void cpu_stl_le_data(CPUArchState *env, abi_ptr ptr, uint32_t val); -void cpu_stq_le_data(CPUArchState *env, abi_ptr ptr, uint64_t val); - -void cpu_stb_data_ra(CPUArchState *env, abi_ptr ptr, - uint32_t val, uintptr_t ra); -void cpu_stw_be_data_ra(CPUArchState *env, abi_ptr ptr, - uint32_t val, uintptr_t ra); -void cpu_stl_be_data_ra(CPUArchState *env, abi_ptr ptr, - uint32_t val, uintptr_t ra); -void cpu_stq_be_data_ra(CPUArchState *env, abi_ptr ptr, - uint64_t val, uintptr_t ra); -void cpu_stw_le_data_ra(CPUArchState *env, abi_ptr ptr, - uint32_t val, uintptr_t ra); -void cpu_stl_le_data_ra(CPUArchState *env, abi_ptr ptr, - uint32_t val, uintptr_t ra); -void cpu_stq_le_data_ra(CPUArchState *env, abi_ptr ptr, - uint64_t val, uintptr_t ra); - -uint32_t cpu_ldub_mmuidx_ra(CPUArchState *env, abi_ptr ptr, - int mmu_idx, uintptr_t ra); -int cpu_ldsb_mmuidx_ra(CPUArchState *env, abi_ptr ptr, - int mmu_idx, uintptr_t ra); -uint32_t cpu_lduw_be_mmuidx_ra(CPUArchState *env, abi_ptr ptr, - int mmu_idx, uintptr_t ra); -int cpu_ldsw_be_mmuidx_ra(CPUArchState *env, abi_ptr ptr, - int mmu_idx, uintptr_t ra); -uint32_t cpu_ldl_be_mmuidx_ra(CPUArchState *env, abi_ptr ptr, - int mmu_idx, uintptr_t ra); -uint64_t cpu_ldq_be_mmuidx_ra(CPUArchState *env, abi_ptr ptr, - int mmu_idx, uintptr_t ra); -uint32_t cpu_lduw_le_mmuidx_ra(CPUArchState *env, abi_ptr ptr, - int mmu_idx, uintptr_t ra); -int cpu_ldsw_le_mmuidx_ra(CPUArchState *env, abi_ptr ptr, - int mmu_idx, uintptr_t ra); -uint32_t cpu_ldl_le_mmuidx_ra(CPUArchState *env, abi_ptr ptr, - int mmu_idx, uintptr_t ra); -uint64_t cpu_ldq_le_mmuidx_ra(CPUArchState *env, abi_ptr ptr, - int mmu_idx, uintptr_t ra); - -void cpu_stb_mmuidx_ra(CPUArchState *env, abi_ptr ptr, uint32_t val, - int mmu_idx, uintptr_t ra); -void cpu_stw_be_mmuidx_ra(CPUArchState *env, abi_ptr ptr, uint32_t val, - int mmu_idx, uintptr_t ra); -void cpu_stl_be_mmuidx_ra(CPUArchState *env, abi_ptr ptr, uint32_t val, - int mmu_idx, uintptr_t ra); -void cpu_stq_be_mmuidx_ra(CPUArchState *env, abi_ptr ptr, uint64_t val, - int mmu_idx, uintptr_t ra); -void cpu_stw_le_mmuidx_ra(CPUArchState *env, abi_ptr ptr, uint32_t val, - int mmu_idx, uintptr_t ra); -void cpu_stl_le_mmuidx_ra(CPUArchState *env, abi_ptr ptr, uint32_t val, - int mmu_idx, uintptr_t ra); -void cpu_stq_le_mmuidx_ra(CPUArchState *env, abi_ptr ptr, uint64_t val, - int mmu_idx, uintptr_t ra); - -uint8_t cpu_ldb_mmu(CPUArchState *env, abi_ptr ptr, MemOpIdx oi, uintptr_t ra); -uint16_t cpu_ldw_mmu(CPUArchState *env, abi_ptr ptr, MemOpIdx oi, uintptr_t ra); -uint32_t cpu_ldl_mmu(CPUArchState *env, abi_ptr ptr, MemOpIdx oi, uintptr_t ra); -uint64_t cpu_ldq_mmu(CPUArchState *env, abi_ptr ptr, MemOpIdx oi, uintptr_t ra); -Int128 cpu_ld16_mmu(CPUArchState *env, abi_ptr addr, MemOpIdx oi, uintptr_t ra); - -void cpu_stb_mmu(CPUArchState *env, abi_ptr ptr, uint8_t val, - MemOpIdx oi, uintptr_t ra); -void cpu_stw_mmu(CPUArchState *env, abi_ptr ptr, uint16_t val, - MemOpIdx oi, uintptr_t ra); -void cpu_stl_mmu(CPUArchState *env, abi_ptr ptr, uint32_t val, - MemOpIdx oi, uintptr_t ra); -void cpu_stq_mmu(CPUArchState *env, abi_ptr ptr, uint64_t val, - MemOpIdx oi, uintptr_t ra); -void cpu_st16_mmu(CPUArchState *env, abi_ptr addr, Int128 val, - MemOpIdx oi, uintptr_t ra); - -uint32_t cpu_atomic_cmpxchgb_mmu(CPUArchState *env, abi_ptr addr, - uint32_t cmpv, uint32_t newv, - MemOpIdx oi, uintptr_t retaddr); -uint32_t cpu_atomic_cmpxchgw_le_mmu(CPUArchState *env, abi_ptr addr, - uint32_t cmpv, uint32_t newv, - MemOpIdx oi, uintptr_t retaddr); -uint32_t cpu_atomic_cmpxchgl_le_mmu(CPUArchState *env, abi_ptr addr, - uint32_t cmpv, uint32_t newv, - MemOpIdx oi, uintptr_t retaddr); -uint64_t cpu_atomic_cmpxchgq_le_mmu(CPUArchState *env, abi_ptr addr, - uint64_t cmpv, uint64_t newv, - MemOpIdx oi, uintptr_t retaddr); -uint32_t cpu_atomic_cmpxchgw_be_mmu(CPUArchState *env, abi_ptr addr, - uint32_t cmpv, uint32_t newv, - MemOpIdx oi, uintptr_t retaddr); -uint32_t cpu_atomic_cmpxchgl_be_mmu(CPUArchState *env, abi_ptr addr, - uint32_t cmpv, uint32_t newv, - MemOpIdx oi, uintptr_t retaddr); -uint64_t cpu_atomic_cmpxchgq_be_mmu(CPUArchState *env, abi_ptr addr, - uint64_t cmpv, uint64_t newv, - MemOpIdx oi, uintptr_t retaddr); - -#define GEN_ATOMIC_HELPER(NAME, TYPE, SUFFIX) \ -TYPE cpu_atomic_ ## NAME ## SUFFIX ## _mmu \ - (CPUArchState *env, abi_ptr addr, TYPE val, \ - MemOpIdx oi, uintptr_t retaddr); - -#ifdef CONFIG_ATOMIC64 -#define GEN_ATOMIC_HELPER_ALL(NAME) \ - GEN_ATOMIC_HELPER(NAME, uint32_t, b) \ - GEN_ATOMIC_HELPER(NAME, uint32_t, w_le) \ - GEN_ATOMIC_HELPER(NAME, uint32_t, w_be) \ - GEN_ATOMIC_HELPER(NAME, uint32_t, l_le) \ - GEN_ATOMIC_HELPER(NAME, uint32_t, l_be) \ - GEN_ATOMIC_HELPER(NAME, uint64_t, q_le) \ - GEN_ATOMIC_HELPER(NAME, uint64_t, q_be) -#else -#define GEN_ATOMIC_HELPER_ALL(NAME) \ - GEN_ATOMIC_HELPER(NAME, uint32_t, b) \ - GEN_ATOMIC_HELPER(NAME, uint32_t, w_le) \ - GEN_ATOMIC_HELPER(NAME, uint32_t, w_be) \ - GEN_ATOMIC_HELPER(NAME, uint32_t, l_le) \ - GEN_ATOMIC_HELPER(NAME, uint32_t, l_be) -#endif - -GEN_ATOMIC_HELPER_ALL(fetch_add) -GEN_ATOMIC_HELPER_ALL(fetch_sub) -GEN_ATOMIC_HELPER_ALL(fetch_and) -GEN_ATOMIC_HELPER_ALL(fetch_or) -GEN_ATOMIC_HELPER_ALL(fetch_xor) -GEN_ATOMIC_HELPER_ALL(fetch_smin) -GEN_ATOMIC_HELPER_ALL(fetch_umin) -GEN_ATOMIC_HELPER_ALL(fetch_smax) -GEN_ATOMIC_HELPER_ALL(fetch_umax) - -GEN_ATOMIC_HELPER_ALL(add_fetch) -GEN_ATOMIC_HELPER_ALL(sub_fetch) -GEN_ATOMIC_HELPER_ALL(and_fetch) -GEN_ATOMIC_HELPER_ALL(or_fetch) -GEN_ATOMIC_HELPER_ALL(xor_fetch) -GEN_ATOMIC_HELPER_ALL(smin_fetch) -GEN_ATOMIC_HELPER_ALL(umin_fetch) -GEN_ATOMIC_HELPER_ALL(smax_fetch) -GEN_ATOMIC_HELPER_ALL(umax_fetch) - -GEN_ATOMIC_HELPER_ALL(xchg) - -#undef GEN_ATOMIC_HELPER_ALL -#undef GEN_ATOMIC_HELPER - -Int128 cpu_atomic_cmpxchgo_le_mmu(CPUArchState *env, abi_ptr addr, - Int128 cmpv, Int128 newv, - MemOpIdx oi, uintptr_t retaddr); -Int128 cpu_atomic_cmpxchgo_be_mmu(CPUArchState *env, abi_ptr addr, - Int128 cmpv, Int128 newv, - MemOpIdx oi, uintptr_t retaddr); - -#if TARGET_BIG_ENDIAN -# define cpu_lduw_data cpu_lduw_be_data -# define cpu_ldsw_data cpu_ldsw_be_data -# define cpu_ldl_data cpu_ldl_be_data -# define cpu_ldq_data cpu_ldq_be_data -# define cpu_lduw_data_ra cpu_lduw_be_data_ra -# define cpu_ldsw_data_ra cpu_ldsw_be_data_ra -# define cpu_ldl_data_ra cpu_ldl_be_data_ra -# define cpu_ldq_data_ra cpu_ldq_be_data_ra -# define cpu_lduw_mmuidx_ra cpu_lduw_be_mmuidx_ra -# define cpu_ldsw_mmuidx_ra cpu_ldsw_be_mmuidx_ra -# define cpu_ldl_mmuidx_ra cpu_ldl_be_mmuidx_ra -# define cpu_ldq_mmuidx_ra cpu_ldq_be_mmuidx_ra -# define cpu_stw_data cpu_stw_be_data -# define cpu_stl_data cpu_stl_be_data -# define cpu_stq_data cpu_stq_be_data -# define cpu_stw_data_ra cpu_stw_be_data_ra -# define cpu_stl_data_ra cpu_stl_be_data_ra -# define cpu_stq_data_ra cpu_stq_be_data_ra -# define cpu_stw_mmuidx_ra cpu_stw_be_mmuidx_ra -# define cpu_stl_mmuidx_ra cpu_stl_be_mmuidx_ra -# define cpu_stq_mmuidx_ra cpu_stq_be_mmuidx_ra -#else -# define cpu_lduw_data cpu_lduw_le_data -# define cpu_ldsw_data cpu_ldsw_le_data -# define cpu_ldl_data cpu_ldl_le_data -# define cpu_ldq_data cpu_ldq_le_data -# define cpu_lduw_data_ra cpu_lduw_le_data_ra -# define cpu_ldsw_data_ra cpu_ldsw_le_data_ra -# define cpu_ldl_data_ra cpu_ldl_le_data_ra -# define cpu_ldq_data_ra cpu_ldq_le_data_ra -# define cpu_lduw_mmuidx_ra cpu_lduw_le_mmuidx_ra -# define cpu_ldsw_mmuidx_ra cpu_ldsw_le_mmuidx_ra -# define cpu_ldl_mmuidx_ra cpu_ldl_le_mmuidx_ra -# define cpu_ldq_mmuidx_ra cpu_ldq_le_mmuidx_ra -# define cpu_stw_data cpu_stw_le_data -# define cpu_stl_data cpu_stl_le_data -# define cpu_stq_data cpu_stq_le_data -# define cpu_stw_data_ra cpu_stw_le_data_ra -# define cpu_stl_data_ra cpu_stl_le_data_ra -# define cpu_stq_data_ra cpu_stq_le_data_ra -# define cpu_stw_mmuidx_ra cpu_stw_le_mmuidx_ra -# define cpu_stl_mmuidx_ra cpu_stl_le_mmuidx_ra -# define cpu_stq_mmuidx_ra cpu_stq_le_mmuidx_ra -#endif - -uint8_t cpu_ldb_code_mmu(CPUArchState *env, abi_ptr addr, - MemOpIdx oi, uintptr_t ra); -uint16_t cpu_ldw_code_mmu(CPUArchState *env, abi_ptr addr, - MemOpIdx oi, uintptr_t ra); -uint32_t cpu_ldl_code_mmu(CPUArchState *env, abi_ptr addr, - MemOpIdx oi, uintptr_t ra); -uint64_t cpu_ldq_code_mmu(CPUArchState *env, abi_ptr addr, - MemOpIdx oi, uintptr_t ra); - -uint32_t cpu_ldub_code(CPUArchState *env, abi_ptr addr); -uint32_t cpu_lduw_code(CPUArchState *env, abi_ptr addr); -uint32_t cpu_ldl_code(CPUArchState *env, abi_ptr addr); -uint64_t cpu_ldq_code(CPUArchState *env, abi_ptr addr); - -/** - * tlb_vaddr_to_host: - * @env: CPUArchState - * @addr: guest virtual address to look up - * @access_type: 0 for read, 1 for write, 2 for execute - * @mmu_idx: MMU index to use for lookup - * - * Look up the specified guest virtual index in the TCG softmmu TLB. - * If we can translate a host virtual address suitable for direct RAM - * access, without causing a guest exception, then return it. - * Otherwise (TLB entry is for an I/O access, guest software - * TLB fill required, etc) return NULL. - */ -#ifdef CONFIG_USER_ONLY -static inline void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr, - MMUAccessType access_type, int mmu_idx) -{ - return g2h(env_cpu(env), addr); -} -#else -void *tlb_vaddr_to_host(CPUArchState *env, vaddr addr, - MMUAccessType access_type, int mmu_idx); -#endif - -/* - * For user-only, helpers that use guest to host address translation - * must protect the actual host memory access by recording 'retaddr' - * for the signal handler. This is required for a race condition in - * which another thread unmaps the page between a probe and the - * actual access. - */ -#ifdef CONFIG_USER_ONLY -extern __thread uintptr_t helper_retaddr; - -static inline void set_helper_retaddr(uintptr_t ra) -{ - helper_retaddr = ra; - /* - * Ensure that this write is visible to the SIGSEGV handler that - * may be invoked due to a subsequent invalid memory operation. - */ - signal_barrier(); -} - -static inline void clear_helper_retaddr(void) -{ - /* - * Ensure that previous memory operations have succeeded before - * removing the data visible to the signal handler. - */ - signal_barrier(); - helper_retaddr = 0; -} -#else -#define set_helper_retaddr(ra) do { } while (0) -#define clear_helper_retaddr() do { } while (0) -#endif - -#endif /* CPU_LDST_H */ diff --git a/include/exec/cputlb.h b/include/exec/cputlb.h index 8125f68..9bec0e7 100644 --- a/include/exec/cputlb.h +++ b/include/exec/cputlb.h @@ -31,7 +31,7 @@ void tlb_unprotect_code(ram_addr_t ram_addr); #endif #ifndef CONFIG_USER_ONLY -void tlb_reset_dirty(CPUState *cpu, ram_addr_t start1, ram_addr_t length); +void tlb_reset_dirty(CPUState *cpu, uintptr_t start, uintptr_t length); void tlb_reset_dirty_range_all(ram_addr_t start, ram_addr_t length); #endif @@ -150,7 +150,7 @@ void tlb_flush_all_cpus_synced(CPUState *src_cpu); * MMU indexes. */ void tlb_flush_page_by_mmuidx(CPUState *cpu, vaddr addr, - uint16_t idxmap); + MMUIdxMap idxmap); /** * tlb_flush_page_by_mmuidx_all_cpus_synced: @@ -165,7 +165,7 @@ void tlb_flush_page_by_mmuidx(CPUState *cpu, vaddr addr, * translations using the flushed TLBs. */ void tlb_flush_page_by_mmuidx_all_cpus_synced(CPUState *cpu, vaddr addr, - uint16_t idxmap); + MMUIdxMap idxmap); /** * tlb_flush_by_mmuidx: @@ -176,7 +176,7 @@ void tlb_flush_page_by_mmuidx_all_cpus_synced(CPUState *cpu, vaddr addr, * Flush all entries from the TLB of the specified CPU, for the specified * MMU indexes. */ -void tlb_flush_by_mmuidx(CPUState *cpu, uint16_t idxmap); +void tlb_flush_by_mmuidx(CPUState *cpu, MMUIdxMap idxmap); /** * tlb_flush_by_mmuidx_all_cpus_synced: @@ -189,7 +189,7 @@ void tlb_flush_by_mmuidx(CPUState *cpu, uint16_t idxmap); * When this function returns, no CPUs will subsequently perform * translations using the flushed TLBs. */ -void tlb_flush_by_mmuidx_all_cpus_synced(CPUState *cpu, uint16_t idxmap); +void tlb_flush_by_mmuidx_all_cpus_synced(CPUState *cpu, MMUIdxMap idxmap); /** * tlb_flush_page_bits_by_mmuidx @@ -201,11 +201,11 @@ void tlb_flush_by_mmuidx_all_cpus_synced(CPUState *cpu, uint16_t idxmap); * Similar to tlb_flush_page_mask, but with a bitmap of indexes. */ void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, vaddr addr, - uint16_t idxmap, unsigned bits); + MMUIdxMap idxmap, unsigned bits); /* Similarly, with broadcast and syncing. */ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *cpu, vaddr addr, - uint16_t idxmap, + MMUIdxMap idxmap, unsigned bits); /** @@ -220,14 +220,14 @@ void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *cpu, vaddr addr, * comparing only the low @bits worth of each virtual page. */ void tlb_flush_range_by_mmuidx(CPUState *cpu, vaddr addr, - vaddr len, uint16_t idxmap, + vaddr len, MMUIdxMap idxmap, unsigned bits); /* Similarly, with broadcast and syncing. */ void tlb_flush_range_by_mmuidx_all_cpus_synced(CPUState *cpu, vaddr addr, vaddr len, - uint16_t idxmap, + MMUIdxMap idxmap, unsigned bits); #else static inline void tlb_flush_page(CPUState *cpu, vaddr addr) @@ -243,42 +243,42 @@ static inline void tlb_flush_all_cpus_synced(CPUState *src_cpu) { } static inline void tlb_flush_page_by_mmuidx(CPUState *cpu, - vaddr addr, uint16_t idxmap) + vaddr addr, MMUIdxMap idxmap) { } -static inline void tlb_flush_by_mmuidx(CPUState *cpu, uint16_t idxmap) +static inline void tlb_flush_by_mmuidx(CPUState *cpu, MMUIdxMap idxmap) { } static inline void tlb_flush_page_by_mmuidx_all_cpus_synced(CPUState *cpu, vaddr addr, - uint16_t idxmap) + MMUIdxMap idxmap) { } static inline void tlb_flush_by_mmuidx_all_cpus_synced(CPUState *cpu, - uint16_t idxmap) + MMUIdxMap idxmap) { } static inline void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, vaddr addr, - uint16_t idxmap, + MMUIdxMap idxmap, unsigned bits) { } static inline void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *cpu, vaddr addr, - uint16_t idxmap, unsigned bits) + MMUIdxMap idxmap, unsigned bits) { } static inline void tlb_flush_range_by_mmuidx(CPUState *cpu, vaddr addr, - vaddr len, uint16_t idxmap, + vaddr len, MMUIdxMap idxmap, unsigned bits) { } static inline void tlb_flush_range_by_mmuidx_all_cpus_synced(CPUState *cpu, vaddr addr, vaddr len, - uint16_t idxmap, + MMUIdxMap idxmap, unsigned bits) { } diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h deleted file mode 100644 index dd5c40f..0000000 --- a/include/exec/exec-all.h +++ /dev/null @@ -1,240 +0,0 @@ -/* - * internal execution defines for qemu - * - * Copyright (c) 2003 Fabrice Bellard - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see <http://www.gnu.org/licenses/>. - */ - -#ifndef EXEC_ALL_H -#define EXEC_ALL_H - -#include "cpu.h" -#if defined(CONFIG_USER_ONLY) -#include "exec/cpu_ldst.h" -#endif -#include "exec/mmu-access-type.h" -#include "exec/translation-block.h" - -#if defined(CONFIG_TCG) -#include "accel/tcg/getpc.h" - -/** - * probe_access: - * @env: CPUArchState - * @addr: guest virtual address to look up - * @size: size of the access - * @access_type: read, write or execute permission - * @mmu_idx: MMU index to use for lookup - * @retaddr: return address for unwinding - * - * Look up the guest virtual address @addr. Raise an exception if the - * page does not satisfy @access_type. Raise an exception if the - * access (@addr, @size) hits a watchpoint. For writes, mark a clean - * page as dirty. - * - * Finally, return the host address for a page that is backed by RAM, - * or NULL if the page requires I/O. - */ -void *probe_access(CPUArchState *env, vaddr addr, int size, - MMUAccessType access_type, int mmu_idx, uintptr_t retaddr); - -static inline void *probe_write(CPUArchState *env, vaddr addr, int size, - int mmu_idx, uintptr_t retaddr) -{ - return probe_access(env, addr, size, MMU_DATA_STORE, mmu_idx, retaddr); -} - -static inline void *probe_read(CPUArchState *env, vaddr addr, int size, - int mmu_idx, uintptr_t retaddr) -{ - return probe_access(env, addr, size, MMU_DATA_LOAD, mmu_idx, retaddr); -} - -/** - * probe_access_flags: - * @env: CPUArchState - * @addr: guest virtual address to look up - * @size: size of the access - * @access_type: read, write or execute permission - * @mmu_idx: MMU index to use for lookup - * @nonfault: suppress the fault - * @phost: return value for host address - * @retaddr: return address for unwinding - * - * Similar to probe_access, loosely returning the TLB_FLAGS_MASK for - * the page, and storing the host address for RAM in @phost. - * - * If @nonfault is set, do not raise an exception but return TLB_INVALID_MASK. - * Do not handle watchpoints, but include TLB_WATCHPOINT in the returned flags. - * Do handle clean pages, so exclude TLB_NOTDIRY from the returned flags. - * For simplicity, all "mmio-like" flags are folded to TLB_MMIO. - */ -int probe_access_flags(CPUArchState *env, vaddr addr, int size, - MMUAccessType access_type, int mmu_idx, - bool nonfault, void **phost, uintptr_t retaddr); - -#ifndef CONFIG_USER_ONLY - -/** - * probe_access_full: - * Like probe_access_flags, except also return into @pfull. - * - * The CPUTLBEntryFull structure returned via @pfull is transient - * and must be consumed or copied immediately, before any further - * access or changes to TLB @mmu_idx. - * - * This function will not fault if @nonfault is set, but will - * return TLB_INVALID_MASK if the page is not mapped, or is not - * accessible with @access_type. - * - * This function will return TLB_MMIO in order to force the access - * to be handled out-of-line if plugins wish to instrument the access. - */ -int probe_access_full(CPUArchState *env, vaddr addr, int size, - MMUAccessType access_type, int mmu_idx, - bool nonfault, void **phost, - CPUTLBEntryFull **pfull, uintptr_t retaddr); - -/** - * probe_access_full_mmu: - * Like probe_access_full, except: - * - * This function is intended to be used for page table accesses by - * the target mmu itself. Since such page walking happens while - * handling another potential mmu fault, this function never raises - * exceptions (akin to @nonfault true for probe_access_full). - * Likewise this function does not trigger plugin instrumentation. - */ -int probe_access_full_mmu(CPUArchState *env, vaddr addr, int size, - MMUAccessType access_type, int mmu_idx, - void **phost, CPUTLBEntryFull **pfull); - -#endif /* !CONFIG_USER_ONLY */ -#endif /* CONFIG_TCG */ - -static inline tb_page_addr_t tb_page_addr0(const TranslationBlock *tb) -{ -#ifdef CONFIG_USER_ONLY - return tb->itree.start; -#else - return tb->page_addr[0]; -#endif -} - -static inline tb_page_addr_t tb_page_addr1(const TranslationBlock *tb) -{ -#ifdef CONFIG_USER_ONLY - tb_page_addr_t next = tb->itree.last & TARGET_PAGE_MASK; - return next == (tb->itree.start & TARGET_PAGE_MASK) ? -1 : next; -#else - return tb->page_addr[1]; -#endif -} - -static inline void tb_set_page_addr0(TranslationBlock *tb, - tb_page_addr_t addr) -{ -#ifdef CONFIG_USER_ONLY - tb->itree.start = addr; - /* - * To begin, we record an interval of one byte. When the translation - * loop encounters a second page, the interval will be extended to - * include the first byte of the second page, which is sufficient to - * allow tb_page_addr1() above to work properly. The final corrected - * interval will be set by tb_page_add() from tb->size before the - * node is added to the interval tree. - */ - tb->itree.last = addr; -#else - tb->page_addr[0] = addr; -#endif -} - -static inline void tb_set_page_addr1(TranslationBlock *tb, - tb_page_addr_t addr) -{ -#ifdef CONFIG_USER_ONLY - /* Extend the interval to the first byte of the second page. See above. */ - tb->itree.last = addr; -#else - tb->page_addr[1] = addr; -#endif -} - -/* TranslationBlock invalidate API */ -void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr); -void tb_invalidate_phys_range(tb_page_addr_t start, tb_page_addr_t last); -void tb_set_jmp_target(TranslationBlock *tb, int n, uintptr_t addr); - -#if !defined(CONFIG_USER_ONLY) - -/** - * iotlb_to_section: - * @cpu: CPU performing the access - * @index: TCG CPU IOTLB entry - * - * Given a TCG CPU IOTLB entry, return the MemoryRegionSection that - * it refers to. @index will have been initially created and returned - * by memory_region_section_get_iotlb(). - */ -struct MemoryRegionSection *iotlb_to_section(CPUState *cpu, - hwaddr index, MemTxAttrs attrs); -#endif - -/** - * get_page_addr_code_hostp() - * @env: CPUArchState - * @addr: guest virtual address of guest code - * - * See get_page_addr_code() (full-system version) for documentation on the - * return value. - * - * Sets *@hostp (when @hostp is non-NULL) as follows. - * If the return value is -1, sets *@hostp to NULL. Otherwise, sets *@hostp - * to the host address where @addr's content is kept. - * - * Note: this function can trigger an exception. - */ -tb_page_addr_t get_page_addr_code_hostp(CPUArchState *env, vaddr addr, - void **hostp); - -/** - * get_page_addr_code() - * @env: CPUArchState - * @addr: guest virtual address of guest code - * - * If we cannot translate and execute from the entire RAM page, or if - * the region is not backed by RAM, returns -1. Otherwise, returns the - * ram_addr_t corresponding to the guest code at @addr. - * - * Note: this function can trigger an exception. - */ -static inline tb_page_addr_t get_page_addr_code(CPUArchState *env, - vaddr addr) -{ - return get_page_addr_code_hostp(env, addr, NULL); -} - -#if !defined(CONFIG_USER_ONLY) - -MemoryRegionSection * -address_space_translate_for_iotlb(CPUState *cpu, int asidx, hwaddr addr, - hwaddr *xlat, hwaddr *plen, - MemTxAttrs attrs, int *prot); -hwaddr memory_region_section_get_iotlb(CPUState *cpu, - MemoryRegionSection *section); -#endif - -#endif diff --git a/include/exec/gdbstub.h b/include/exec/gdbstub.h index 0675b0b..bd7182c 100644 --- a/include/exec/gdbstub.h +++ b/include/exec/gdbstub.h @@ -55,9 +55,6 @@ void gdb_unregister_coprocessor_all(CPUState *cpu); * system emulation you can use a full chardev spec for your gdbserver * port. * - * The error handle should be either &error_fatal (for start-up) or - * &error_warn (for QMP/HMP initiated sessions). - * * Returns true when server successfully started. */ bool gdbserver_start(const char *port_or_device, Error **errp); @@ -125,6 +122,20 @@ const GDBFeature *gdb_find_static_feature(const char *xmlname); int gdb_read_register(CPUState *cpu, GByteArray *buf, int reg); /** + * gdb_write_register() - Write a register associated with a CPU. + * @cpu: The CPU associated with the register. + * @buf: The buffer that the register contents will be set to. + * @reg: The register's number returned by gdb_find_feature_register(). + * + * The size of @buf must be at least the size of the register being + * written. + * + * Return: The number of written bytes, or 0 if an error occurred (for + * example, an unknown register was provided). + */ +int gdb_write_register(CPUState *cpu, uint8_t *mem_buf, int reg); + +/** * typedef GDBRegDesc - a register description from gdbstub */ typedef struct { diff --git a/include/exec/helper-head.h.inc b/include/exec/helper-head.h.inc index bce5db0..5b248fd 100644 --- a/include/exec/helper-head.h.inc +++ b/include/exec/helper-head.h.inc @@ -58,6 +58,17 @@ # define dh_ctype_tl target_ulong #endif /* COMPILING_PER_TARGET */ +#if __SIZEOF_POINTER__ == 4 +# define dh_alias_vaddr i32 +# define dh_typecode_vaddr dh_typecode_i32 +#elif __SIZEOF_POINTER__ == 8 +# define dh_alias_vaddr i64 +# define dh_typecode_vaddr dh_typecode_i64 +#else +# error "sizeof pointer is different from {4,8}" +#endif /* __SIZEOF_POINTER__ */ +# define dh_ctype_vaddr uintptr_t + /* We can't use glue() here because it falls foul of C preprocessor recursive expansion rules. */ #define dh_retvar_decl0_void void diff --git a/include/exec/helper-proto-common.h b/include/exec/helper-proto-common.h index 16782ef..76e6c25 100644 --- a/include/exec/helper-proto-common.h +++ b/include/exec/helper-proto-common.h @@ -13,4 +13,6 @@ #include "exec/helper-proto.h.inc" #undef HELPER_H +#include "accel/tcg/getpc.h" + #endif /* HELPER_PROTO_COMMON_H */ diff --git a/include/exec/icount.h b/include/exec/icount.h new file mode 100644 index 0000000..7a26b40 --- /dev/null +++ b/include/exec/icount.h @@ -0,0 +1,76 @@ +/* + * icount - Instruction Counter API + * CPU timers state API + * + * Copyright 2020 SUSE LLC + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef EXEC_ICOUNT_H +#define EXEC_ICOUNT_H + +/** + * ICountMode: icount enablement state: + * + * @ICOUNT_DISABLED: Disabled - Do not count executed instructions. + * @ICOUNT_PRECISE: Enabled - Fixed conversion of insn to ns via "shift" option + * @ICOUNT_ADAPTATIVE: Enabled - Runtime adaptive algorithm to compute shift + */ +typedef enum { + ICOUNT_DISABLED = 0, + ICOUNT_PRECISE, + ICOUNT_ADAPTATIVE, +} ICountMode; + +#ifdef CONFIG_TCG +extern ICountMode use_icount; +#define icount_enabled() (use_icount) +#else +#define icount_enabled() ICOUNT_DISABLED +#endif + +/* Protect the CONFIG_USER_ONLY test vs poisoning. */ +#if defined(COMPILING_PER_TARGET) || defined(COMPILING_SYSTEM_VS_USER) +# ifdef CONFIG_USER_ONLY +# undef icount_enabled +# define icount_enabled() ICOUNT_DISABLED +# endif +#endif + +/* + * Update the icount with the executed instructions. Called by + * cpus-tcg vCPU thread so the main-loop can see time has moved forward. + */ +void icount_update(CPUState *cpu); + +/* get raw icount value */ +int64_t icount_get_raw(void); + +/* return the virtual CPU time in ns, based on the instruction counter. */ +int64_t icount_get(void); +/* + * convert an instruction counter value to ns, based on the icount shift. + * This shift is set as a fixed value with the icount "shift" option + * (precise mode), or it is constantly approximated and corrected at + * runtime in adaptive mode. + */ +int64_t icount_to_ns(int64_t icount); + +/** + * icount_configure: configure the icount options, including "shift" + * @opts: Options to parse + * @errp: pointer to a NULL-initialized error object + * + * Return: true on success, else false setting @errp with error + */ +bool icount_configure(QemuOpts *opts, Error **errp); + +/* used by tcg vcpu thread to calc icount budget */ +int64_t icount_round(int64_t count); + +/* if the CPUs are idle, start accounting real time to virtual clock. */ +void icount_start_warp_timer(void); +void icount_account_warp_timer(void); +void icount_notify_exit(void); + +#endif /* EXEC_ICOUNT_H */ diff --git a/include/exec/memattrs.h b/include/exec/memattrs.h index 8db1d30..52ee955 100644 --- a/include/exec/memattrs.h +++ b/include/exec/memattrs.h @@ -54,6 +54,9 @@ typedef struct MemTxAttrs { */ unsigned int pid:8; + /* PCI - IOMMU operations, see PCIAddressType */ + unsigned int address_type:1; + /* * Bus masters which don't specify any attributes will get this * (via the MEMTXATTRS_UNSPECIFIED constant), so that we can diff --git a/include/exec/memop.h b/include/exec/memop.h index 407a47d..799b5b4 100644 --- a/include/exec/memop.h +++ b/include/exec/memop.h @@ -73,6 +73,16 @@ typedef enum MemOp { MO_ALIGN = MO_AMASK, /* + * MO_ALIGN_TLB_ONLY: + * Apply MO_AMASK only along the TCG slow path if TLB_CHECK_ALIGNED + * is set; otherwise unaligned access is permitted. + * This is used by target/arm, where unaligned accesses are + * permitted for pages marked Normal but aligned accesses are + * required for pages marked Device. + */ + MO_ALIGN_TLB_ONLY = 1 << 8, + + /* * MO_ATOM_* describes the atomicity requirements of the operation: * MO_ATOM_IFALIGN: the operation must be single-copy atomic if it * is aligned; if unaligned there is no atomicity. @@ -104,7 +114,7 @@ typedef enum MemOp { * size of the operation, if aligned. This retains the behaviour * from before this field was introduced. */ - MO_ATOM_SHIFT = 8, + MO_ATOM_SHIFT = 9, MO_ATOM_IFALIGN = 0 << MO_ATOM_SHIFT, MO_ATOM_IFALIGN_PAIR = 1 << MO_ATOM_SHIFT, MO_ATOM_WITHIN16 = 2 << MO_ATOM_SHIFT, @@ -162,23 +172,23 @@ static inline unsigned memop_size(MemOp op) static inline MemOp size_memop(unsigned size) { #ifdef CONFIG_DEBUG_TCG - /* Power of 2 up to 8. */ - assert((size & (size - 1)) == 0 && size >= 1 && size <= 8); + /* Power of 2 up to 1024 */ + assert(is_power_of_2(size) && size >= 1 && size <= (1 << MO_SIZE)); #endif return (MemOp)ctz32(size); } /** - * memop_alignment_bits: + * memop_tlb_alignment_bits: * @memop: MemOp value * - * Extract the alignment size from the memop. + * Extract the alignment size for use with TLB_CHECK_ALIGNED. */ -static inline unsigned memop_alignment_bits(MemOp memop) +static inline unsigned memop_tlb_alignment_bits(MemOp memop, bool tlb_check) { unsigned a = memop & MO_AMASK; - if (a == MO_UNALN) { + if (a == MO_UNALN || (!tlb_check && (memop & MO_ALIGN_TLB_ONLY))) { /* No alignment required. */ a = 0; } else if (a == MO_ALIGN) { @@ -191,28 +201,15 @@ static inline unsigned memop_alignment_bits(MemOp memop) return a; } -/* - * memop_atomicity_bits: +/** + * memop_alignment_bits: * @memop: MemOp value * - * Extract the atomicity size from the memop. + * Extract the alignment size from the memop. */ -static inline unsigned memop_atomicity_bits(MemOp memop) +static inline unsigned memop_alignment_bits(MemOp memop) { - unsigned size = memop & MO_SIZE; - - switch (memop & MO_ATOM_MASK) { - case MO_ATOM_NONE: - size = MO_8; - break; - case MO_ATOM_IFALIGN_PAIR: - case MO_ATOM_WITHIN16_PAIR: - size = size ? size - 1 : 0; - break; - default: - break; - } - return size; + return memop_tlb_alignment_bits(memop, false); } #endif diff --git a/include/exec/memopidx.h b/include/exec/memopidx.h index eb7f159..66d9c58 100644 --- a/include/exec/memopidx.h +++ b/include/exec/memopidx.h @@ -25,9 +25,10 @@ typedef uint32_t MemOpIdx; static inline MemOpIdx make_memop_idx(MemOp op, unsigned idx) { #ifdef CONFIG_DEBUG_TCG - assert(idx <= 15); + assert(idx <= 31); + assert(clz32(op) >= 5); #endif - return (op << 4) | idx; + return (op << 5) | idx; } /** @@ -38,7 +39,7 @@ static inline MemOpIdx make_memop_idx(MemOp op, unsigned idx) */ static inline MemOp get_memop(MemOpIdx oi) { - return oi >> 4; + return oi >> 5; } /** @@ -49,7 +50,7 @@ static inline MemOp get_memop(MemOpIdx oi) */ static inline unsigned get_mmuidx(MemOpIdx oi) { - return oi & 15; + return oi & 31; } #endif diff --git a/include/exec/memory-internal.h b/include/exec/memory-internal.h deleted file mode 100644 index 100c123..0000000 --- a/include/exec/memory-internal.h +++ /dev/null @@ -1,49 +0,0 @@ -/* - * Declarations for functions which are internal to the memory subsystem. - * - * Copyright 2011 Red Hat, Inc. and/or its affiliates - * - * Authors: - * Avi Kivity <avi@redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or - * later. See the COPYING file in the top-level directory. - * - */ - -/* - * This header is for use by exec.c, memory.c and accel/tcg/cputlb.c ONLY, - * for declarations which are shared between the memory subsystem's - * internals and the TCG TLB code. Do not include it from elsewhere. - */ - -#ifndef MEMORY_INTERNAL_H -#define MEMORY_INTERNAL_H - -#include "cpu.h" - -#ifndef CONFIG_USER_ONLY -static inline AddressSpaceDispatch *flatview_to_dispatch(FlatView *fv) -{ - return fv->dispatch; -} - -static inline AddressSpaceDispatch *address_space_to_dispatch(AddressSpace *as) -{ - return flatview_to_dispatch(address_space_to_flatview(as)); -} - -FlatView *address_space_get_flatview(AddressSpace *as); -void flatview_unref(FlatView *view); - -extern const MemoryRegionOps unassigned_mem_ops; - -void flatview_add_to_dispatch(FlatView *fv, MemoryRegionSection *section); -AddressSpaceDispatch *address_space_dispatch_new(FlatView *fv); -void address_space_dispatch_compact(AddressSpaceDispatch *d); -void address_space_dispatch_free(AddressSpaceDispatch *d); - -void mtree_print_dispatch(struct AddressSpaceDispatch *d, - MemoryRegion *root); -#endif -#endif diff --git a/include/exec/memory_ldst.h.inc b/include/exec/memory_ldst.h.inc index 92ad74e..7270235 100644 --- a/include/exec/memory_ldst.h.inc +++ b/include/exec/memory_ldst.h.inc @@ -19,7 +19,6 @@ * License along with this library; if not, see <http://www.gnu.org/licenses/>. */ -#ifdef TARGET_ENDIANNESS uint16_t glue(address_space_lduw, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result); uint32_t glue(address_space_ldl, SUFFIX)(ARG1_DECL, @@ -34,7 +33,6 @@ void glue(address_space_stl, SUFFIX)(ARG1_DECL, hwaddr addr, uint32_t val, MemTxAttrs attrs, MemTxResult *result); void glue(address_space_stq, SUFFIX)(ARG1_DECL, hwaddr addr, uint64_t val, MemTxAttrs attrs, MemTxResult *result); -#else uint8_t glue(address_space_ldub, SUFFIX)(ARG1_DECL, hwaddr addr, MemTxAttrs attrs, MemTxResult *result); uint16_t glue(address_space_lduw_le, SUFFIX)(ARG1_DECL, @@ -63,9 +61,7 @@ void glue(address_space_stq_le, SUFFIX)(ARG1_DECL, hwaddr addr, uint64_t val, MemTxAttrs attrs, MemTxResult *result); void glue(address_space_stq_be, SUFFIX)(ARG1_DECL, hwaddr addr, uint64_t val, MemTxAttrs attrs, MemTxResult *result); -#endif #undef ARG1_DECL #undef ARG1 #undef SUFFIX -#undef TARGET_ENDIANNESS diff --git a/include/exec/memory_ldst_phys.h.inc b/include/exec/memory_ldst_phys.h.inc index ecd6786..db67de7 100644 --- a/include/exec/memory_ldst_phys.h.inc +++ b/include/exec/memory_ldst_phys.h.inc @@ -19,7 +19,6 @@ * License along with this library; if not, see <http://www.gnu.org/licenses/>. */ -#ifdef TARGET_ENDIANNESS static inline uint16_t glue(lduw_phys, SUFFIX)(ARG1_DECL, hwaddr addr) { return glue(address_space_lduw, SUFFIX)(ARG1, addr, @@ -55,7 +54,7 @@ static inline void glue(stq_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint64_t val) glue(address_space_stq, SUFFIX)(ARG1, addr, val, MEMTXATTRS_UNSPECIFIED, NULL); } -#else + static inline uint8_t glue(ldub_phys, SUFFIX)(ARG1_DECL, hwaddr addr) { return glue(address_space_ldub, SUFFIX)(ARG1, addr, @@ -139,9 +138,7 @@ static inline void glue(stq_be_phys, SUFFIX)(ARG1_DECL, hwaddr addr, uint64_t va glue(address_space_stq_be, SUFFIX)(ARG1, addr, val, MEMTXATTRS_UNSPECIFIED, NULL); } -#endif #undef ARG1_DECL #undef ARG1 #undef SUFFIX -#undef TARGET_ENDIANNESS diff --git a/include/exec/mmap-lock.h b/include/exec/mmap-lock.h new file mode 100644 index 0000000..50ffdab --- /dev/null +++ b/include/exec/mmap-lock.h @@ -0,0 +1,33 @@ +/* + * QEMU user-only mmap lock, with stubs for system mode + * + * Copyright (c) 2003 Fabrice Bellard + * + * SPDX-License-Identifier: LGPL-2.1-or-later + */ +#ifndef EXEC_MMAP_LOCK_H +#define EXEC_MMAP_LOCK_H + +#ifdef CONFIG_USER_ONLY + +void TSA_NO_TSA mmap_lock(void); +void TSA_NO_TSA mmap_unlock(void); +bool have_mmap_lock(void); + +static inline void mmap_unlock_guard(void *unused) +{ + mmap_unlock(); +} + +#define WITH_MMAP_LOCK_GUARD() \ + for (int _mmap_lock_iter __attribute__((cleanup(mmap_unlock_guard))) \ + = (mmap_lock(), 0); _mmap_lock_iter == 0; _mmap_lock_iter = 1) + +#else + +static inline void mmap_lock(void) {} +static inline void mmap_unlock(void) {} +#define WITH_MMAP_LOCK_GUARD() + +#endif /* CONFIG_USER_ONLY */ +#endif /* EXEC_MMAP_LOCK_H */ diff --git a/include/exec/page-protection.h b/include/exec/page-protection.h index 3e0a8a0..c50ce57 100644 --- a/include/exec/page-protection.h +++ b/include/exec/page-protection.h @@ -23,41 +23,20 @@ * Low-Address-Protection. Used with PAGE_WRITE in tlb_set_page_with_attrs() */ #define PAGE_WRITE_INV 0x0020 -/* For use with page_set_flags: page is being replaced; target_data cleared. */ -#define PAGE_RESET 0x0040 +/* + * For linux-user, indicates that the page is mapped with the same semantics + * in both guest and host. + */ +#define PAGE_PASSTHROUGH 0x40 /* For linux-user, indicates that the page is MAP_ANON. */ #define PAGE_ANON 0x0080 - +/* + * For linux-user, indicates that the page should not be + * included in a core dump. + */ +#define PAGE_DONTDUMP 0x0100 /* Target-specific bits that will be used via page_get_flags(). */ #define PAGE_TARGET_1 0x0200 #define PAGE_TARGET_2 0x0400 -/* - * For linux-user, indicates that the page is mapped with the same semantics - * in both guest and host. - */ -#define PAGE_PASSTHROUGH 0x0800 - -#ifdef CONFIG_USER_ONLY - -void TSA_NO_TSA mmap_lock(void); -void TSA_NO_TSA mmap_unlock(void); -bool have_mmap_lock(void); - -static inline void mmap_unlock_guard(void *unused) -{ - mmap_unlock(); -} - -#define WITH_MMAP_LOCK_GUARD() \ - for (int _mmap_lock_iter __attribute__((cleanup(mmap_unlock_guard))) \ - = (mmap_lock(), 0); _mmap_lock_iter == 0; _mmap_lock_iter = 1) -#else - -static inline void mmap_lock(void) {} -static inline void mmap_unlock(void) {} -#define WITH_MMAP_LOCK_GUARD() - -#endif /* !CONFIG_USER_ONLY */ - #endif diff --git a/include/exec/page-vary.h b/include/exec/page-vary.h index 54ddde3..101c259 100644 --- a/include/exec/page-vary.h +++ b/include/exec/page-vary.h @@ -49,4 +49,13 @@ bool set_preferred_target_page_bits(int bits); */ void finalize_target_page_bits(void); +/** + * migration_legacy_page_bits + * + * For migration compatibility with qemu v2.9, prior to the introduction + * of the configuration/target-page-bits section, return the value of + * TARGET_PAGE_BITS that the target had then. + */ +int migration_legacy_page_bits(void); + #endif /* EXEC_PAGE_VARY_H */ diff --git a/include/exec/poison.h b/include/exec/poison.h index 2c151fd..a779adb 100644 --- a/include/exec/poison.h +++ b/include/exec/poison.h @@ -35,8 +35,8 @@ #pragma GCC poison TARGET_HAS_BFLT #pragma GCC poison TARGET_NAME -#pragma GCC poison TARGET_SUPPORTS_MTTCG #pragma GCC poison TARGET_BIG_ENDIAN +#pragma GCC poison TCG_GUEST_DEFAULT_MO #pragma GCC poison TARGET_LONG_BITS #pragma GCC poison TARGET_FMT_lx @@ -66,4 +66,11 @@ #pragma GCC poison CONFIG_WHPX #pragma GCC poison CONFIG_XEN +#ifndef COMPILING_SYSTEM_VS_USER +#pragma GCC poison CONFIG_USER_ONLY +#pragma GCC poison CONFIG_SOFTMMU +#endif + +#pragma GCC poison KVM_HAVE_MCE_INJECTION + #endif diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h deleted file mode 100644 index e4c28fb..0000000 --- a/include/exec/ram_addr.h +++ /dev/null @@ -1,558 +0,0 @@ -/* - * Declarations for cpu physical memory functions - * - * Copyright 2011 Red Hat, Inc. and/or its affiliates - * - * Authors: - * Avi Kivity <avi@redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2 or - * later. See the COPYING file in the top-level directory. - * - */ - -/* - * This header is for use by exec.c and memory.c ONLY. Do not include it. - * The functions declared here will be removed soon. - */ - -#ifndef RAM_ADDR_H -#define RAM_ADDR_H - -#ifndef CONFIG_USER_ONLY -#include "cpu.h" -#include "system/xen.h" -#include "system/tcg.h" -#include "exec/cputlb.h" -#include "exec/ramlist.h" -#include "exec/ramblock.h" -#include "exec/exec-all.h" -#include "qemu/rcu.h" - -#include "exec/hwaddr.h" -#include "exec/cpu-common.h" - -extern uint64_t total_dirty_pages; - -/** - * clear_bmap_size: calculate clear bitmap size - * - * @pages: number of guest pages - * @shift: guest page number shift - * - * Returns: number of bits for the clear bitmap - */ -static inline long clear_bmap_size(uint64_t pages, uint8_t shift) -{ - return DIV_ROUND_UP(pages, 1UL << shift); -} - -/** - * clear_bmap_set: set clear bitmap for the page range. Must be with - * bitmap_mutex held. - * - * @rb: the ramblock to operate on - * @start: the start page number - * @size: number of pages to set in the bitmap - * - * Returns: None - */ -static inline void clear_bmap_set(RAMBlock *rb, uint64_t start, - uint64_t npages) -{ - uint8_t shift = rb->clear_bmap_shift; - - bitmap_set(rb->clear_bmap, start >> shift, clear_bmap_size(npages, shift)); -} - -/** - * clear_bmap_test_and_clear: test clear bitmap for the page, clear if set. - * Must be with bitmap_mutex held. - * - * @rb: the ramblock to operate on - * @page: the page number to check - * - * Returns: true if the bit was set, false otherwise - */ -static inline bool clear_bmap_test_and_clear(RAMBlock *rb, uint64_t page) -{ - uint8_t shift = rb->clear_bmap_shift; - - return bitmap_test_and_clear(rb->clear_bmap, page >> shift, 1); -} - -static inline bool offset_in_ramblock(RAMBlock *b, ram_addr_t offset) -{ - return (b && b->host && offset < b->used_length) ? true : false; -} - -static inline void *ramblock_ptr(RAMBlock *block, ram_addr_t offset) -{ - assert(offset_in_ramblock(block, offset)); - return (char *)block->host + offset; -} - -static inline unsigned long int ramblock_recv_bitmap_offset(void *host_addr, - RAMBlock *rb) -{ - uint64_t host_addr_offset = - (uint64_t)(uintptr_t)(host_addr - (void *)rb->host); - return host_addr_offset >> TARGET_PAGE_BITS; -} - -bool ramblock_is_pmem(RAMBlock *rb); - -/** - * qemu_ram_alloc_from_file, - * qemu_ram_alloc_from_fd: Allocate a ram block from the specified backing - * file or device - * - * Parameters: - * @size: the size in bytes of the ram block - * @max_size: the maximum size of the block after resizing - * @mr: the memory region where the ram block is - * @resized: callback after calls to qemu_ram_resize - * @ram_flags: RamBlock flags. Supported flags: RAM_SHARED, RAM_PMEM, - * RAM_NORESERVE, RAM_PROTECTED, RAM_NAMED_FILE, RAM_READONLY, - * RAM_READONLY_FD, RAM_GUEST_MEMFD - * @mem_path or @fd: specify the backing file or device - * @offset: Offset into target file - * @grow: extend file if necessary (but an empty file is always extended). - * @errp: pointer to Error*, to store an error if it happens - * - * Return: - * On success, return a pointer to the ram block. - * On failure, return NULL. - */ -typedef void (*qemu_ram_resize_cb)(const char *, uint64_t length, void *host); - -RAMBlock *qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr, - uint32_t ram_flags, const char *mem_path, - off_t offset, Error **errp); -RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, ram_addr_t max_size, - qemu_ram_resize_cb resized, MemoryRegion *mr, - uint32_t ram_flags, int fd, off_t offset, - bool grow, - Error **errp); - -RAMBlock *qemu_ram_alloc_from_ptr(ram_addr_t size, void *host, - MemoryRegion *mr, Error **errp); -RAMBlock *qemu_ram_alloc(ram_addr_t size, uint32_t ram_flags, MemoryRegion *mr, - Error **errp); -RAMBlock *qemu_ram_alloc_resizeable(ram_addr_t size, ram_addr_t max_size, - qemu_ram_resize_cb resized, - MemoryRegion *mr, Error **errp); -void qemu_ram_free(RAMBlock *block); - -int qemu_ram_resize(RAMBlock *block, ram_addr_t newsize, Error **errp); - -void qemu_ram_msync(RAMBlock *block, ram_addr_t start, ram_addr_t length); - -/* Clear whole block of mem */ -static inline void qemu_ram_block_writeback(RAMBlock *block) -{ - qemu_ram_msync(block, 0, block->used_length); -} - -#define DIRTY_CLIENTS_ALL ((1 << DIRTY_MEMORY_NUM) - 1) -#define DIRTY_CLIENTS_NOCODE (DIRTY_CLIENTS_ALL & ~(1 << DIRTY_MEMORY_CODE)) - -static inline bool cpu_physical_memory_get_dirty(ram_addr_t start, - ram_addr_t length, - unsigned client) -{ - DirtyMemoryBlocks *blocks; - unsigned long end, page; - unsigned long idx, offset, base; - bool dirty = false; - - assert(client < DIRTY_MEMORY_NUM); - - end = TARGET_PAGE_ALIGN(start + length) >> TARGET_PAGE_BITS; - page = start >> TARGET_PAGE_BITS; - - WITH_RCU_READ_LOCK_GUARD() { - blocks = qatomic_rcu_read(&ram_list.dirty_memory[client]); - - idx = page / DIRTY_MEMORY_BLOCK_SIZE; - offset = page % DIRTY_MEMORY_BLOCK_SIZE; - base = page - offset; - while (page < end) { - unsigned long next = MIN(end, base + DIRTY_MEMORY_BLOCK_SIZE); - unsigned long num = next - base; - unsigned long found = find_next_bit(blocks->blocks[idx], - num, offset); - if (found < num) { - dirty = true; - break; - } - - page = next; - idx++; - offset = 0; - base += DIRTY_MEMORY_BLOCK_SIZE; - } - } - - return dirty; -} - -static inline bool cpu_physical_memory_all_dirty(ram_addr_t start, - ram_addr_t length, - unsigned client) -{ - DirtyMemoryBlocks *blocks; - unsigned long end, page; - unsigned long idx, offset, base; - bool dirty = true; - - assert(client < DIRTY_MEMORY_NUM); - - end = TARGET_PAGE_ALIGN(start + length) >> TARGET_PAGE_BITS; - page = start >> TARGET_PAGE_BITS; - - RCU_READ_LOCK_GUARD(); - - blocks = qatomic_rcu_read(&ram_list.dirty_memory[client]); - - idx = page / DIRTY_MEMORY_BLOCK_SIZE; - offset = page % DIRTY_MEMORY_BLOCK_SIZE; - base = page - offset; - while (page < end) { - unsigned long next = MIN(end, base + DIRTY_MEMORY_BLOCK_SIZE); - unsigned long num = next - base; - unsigned long found = find_next_zero_bit(blocks->blocks[idx], num, offset); - if (found < num) { - dirty = false; - break; - } - - page = next; - idx++; - offset = 0; - base += DIRTY_MEMORY_BLOCK_SIZE; - } - - return dirty; -} - -static inline bool cpu_physical_memory_get_dirty_flag(ram_addr_t addr, - unsigned client) -{ - return cpu_physical_memory_get_dirty(addr, 1, client); -} - -static inline bool cpu_physical_memory_is_clean(ram_addr_t addr) -{ - bool vga = cpu_physical_memory_get_dirty_flag(addr, DIRTY_MEMORY_VGA); - bool code = cpu_physical_memory_get_dirty_flag(addr, DIRTY_MEMORY_CODE); - bool migration = - cpu_physical_memory_get_dirty_flag(addr, DIRTY_MEMORY_MIGRATION); - return !(vga && code && migration); -} - -static inline uint8_t cpu_physical_memory_range_includes_clean(ram_addr_t start, - ram_addr_t length, - uint8_t mask) -{ - uint8_t ret = 0; - - if (mask & (1 << DIRTY_MEMORY_VGA) && - !cpu_physical_memory_all_dirty(start, length, DIRTY_MEMORY_VGA)) { - ret |= (1 << DIRTY_MEMORY_VGA); - } - if (mask & (1 << DIRTY_MEMORY_CODE) && - !cpu_physical_memory_all_dirty(start, length, DIRTY_MEMORY_CODE)) { - ret |= (1 << DIRTY_MEMORY_CODE); - } - if (mask & (1 << DIRTY_MEMORY_MIGRATION) && - !cpu_physical_memory_all_dirty(start, length, DIRTY_MEMORY_MIGRATION)) { - ret |= (1 << DIRTY_MEMORY_MIGRATION); - } - return ret; -} - -static inline void cpu_physical_memory_set_dirty_flag(ram_addr_t addr, - unsigned client) -{ - unsigned long page, idx, offset; - DirtyMemoryBlocks *blocks; - - assert(client < DIRTY_MEMORY_NUM); - - page = addr >> TARGET_PAGE_BITS; - idx = page / DIRTY_MEMORY_BLOCK_SIZE; - offset = page % DIRTY_MEMORY_BLOCK_SIZE; - - RCU_READ_LOCK_GUARD(); - - blocks = qatomic_rcu_read(&ram_list.dirty_memory[client]); - - set_bit_atomic(offset, blocks->blocks[idx]); -} - -static inline void cpu_physical_memory_set_dirty_range(ram_addr_t start, - ram_addr_t length, - uint8_t mask) -{ - DirtyMemoryBlocks *blocks[DIRTY_MEMORY_NUM]; - unsigned long end, page; - unsigned long idx, offset, base; - int i; - - if (!mask && !xen_enabled()) { - return; - } - - end = TARGET_PAGE_ALIGN(start + length) >> TARGET_PAGE_BITS; - page = start >> TARGET_PAGE_BITS; - - WITH_RCU_READ_LOCK_GUARD() { - for (i = 0; i < DIRTY_MEMORY_NUM; i++) { - blocks[i] = qatomic_rcu_read(&ram_list.dirty_memory[i]); - } - - idx = page / DIRTY_MEMORY_BLOCK_SIZE; - offset = page % DIRTY_MEMORY_BLOCK_SIZE; - base = page - offset; - while (page < end) { - unsigned long next = MIN(end, base + DIRTY_MEMORY_BLOCK_SIZE); - - if (likely(mask & (1 << DIRTY_MEMORY_MIGRATION))) { - bitmap_set_atomic(blocks[DIRTY_MEMORY_MIGRATION]->blocks[idx], - offset, next - page); - } - if (unlikely(mask & (1 << DIRTY_MEMORY_VGA))) { - bitmap_set_atomic(blocks[DIRTY_MEMORY_VGA]->blocks[idx], - offset, next - page); - } - if (unlikely(mask & (1 << DIRTY_MEMORY_CODE))) { - bitmap_set_atomic(blocks[DIRTY_MEMORY_CODE]->blocks[idx], - offset, next - page); - } - - page = next; - idx++; - offset = 0; - base += DIRTY_MEMORY_BLOCK_SIZE; - } - } - - xen_hvm_modified_memory(start, length); -} - -#if !defined(_WIN32) - -/* - * Contrary to cpu_physical_memory_sync_dirty_bitmap() this function returns - * the number of dirty pages in @bitmap passed as argument. On the other hand, - * cpu_physical_memory_sync_dirty_bitmap() returns newly dirtied pages that - * weren't set in the global migration bitmap. - */ -static inline -uint64_t cpu_physical_memory_set_dirty_lebitmap(unsigned long *bitmap, - ram_addr_t start, - ram_addr_t pages) -{ - unsigned long i, j; - unsigned long page_number, c, nbits; - hwaddr addr; - ram_addr_t ram_addr; - uint64_t num_dirty = 0; - unsigned long len = (pages + HOST_LONG_BITS - 1) / HOST_LONG_BITS; - unsigned long hpratio = qemu_real_host_page_size() / TARGET_PAGE_SIZE; - unsigned long page = BIT_WORD(start >> TARGET_PAGE_BITS); - - /* start address is aligned at the start of a word? */ - if ((((page * BITS_PER_LONG) << TARGET_PAGE_BITS) == start) && - (hpratio == 1)) { - unsigned long **blocks[DIRTY_MEMORY_NUM]; - unsigned long idx; - unsigned long offset; - long k; - long nr = BITS_TO_LONGS(pages); - - idx = (start >> TARGET_PAGE_BITS) / DIRTY_MEMORY_BLOCK_SIZE; - offset = BIT_WORD((start >> TARGET_PAGE_BITS) % - DIRTY_MEMORY_BLOCK_SIZE); - - WITH_RCU_READ_LOCK_GUARD() { - for (i = 0; i < DIRTY_MEMORY_NUM; i++) { - blocks[i] = - qatomic_rcu_read(&ram_list.dirty_memory[i])->blocks; - } - - for (k = 0; k < nr; k++) { - if (bitmap[k]) { - unsigned long temp = leul_to_cpu(bitmap[k]); - - nbits = ctpopl(temp); - qatomic_or(&blocks[DIRTY_MEMORY_VGA][idx][offset], temp); - - if (global_dirty_tracking) { - qatomic_or( - &blocks[DIRTY_MEMORY_MIGRATION][idx][offset], - temp); - if (unlikely( - global_dirty_tracking & GLOBAL_DIRTY_DIRTY_RATE)) { - total_dirty_pages += nbits; - } - } - - num_dirty += nbits; - - if (tcg_enabled()) { - qatomic_or(&blocks[DIRTY_MEMORY_CODE][idx][offset], - temp); - } - } - - if (++offset >= BITS_TO_LONGS(DIRTY_MEMORY_BLOCK_SIZE)) { - offset = 0; - idx++; - } - } - } - - xen_hvm_modified_memory(start, pages << TARGET_PAGE_BITS); - } else { - uint8_t clients = tcg_enabled() ? DIRTY_CLIENTS_ALL : DIRTY_CLIENTS_NOCODE; - - if (!global_dirty_tracking) { - clients &= ~(1 << DIRTY_MEMORY_MIGRATION); - } - - /* - * bitmap-traveling is faster than memory-traveling (for addr...) - * especially when most of the memory is not dirty. - */ - for (i = 0; i < len; i++) { - if (bitmap[i] != 0) { - c = leul_to_cpu(bitmap[i]); - nbits = ctpopl(c); - if (unlikely(global_dirty_tracking & GLOBAL_DIRTY_DIRTY_RATE)) { - total_dirty_pages += nbits; - } - num_dirty += nbits; - do { - j = ctzl(c); - c &= ~(1ul << j); - page_number = (i * HOST_LONG_BITS + j) * hpratio; - addr = page_number * TARGET_PAGE_SIZE; - ram_addr = start + addr; - cpu_physical_memory_set_dirty_range(ram_addr, - TARGET_PAGE_SIZE * hpratio, clients); - } while (c != 0); - } - } - } - - return num_dirty; -} -#endif /* not _WIN32 */ - -static inline void cpu_physical_memory_dirty_bits_cleared(ram_addr_t start, - ram_addr_t length) -{ - if (tcg_enabled()) { - tlb_reset_dirty_range_all(start, length); - } - -} -bool cpu_physical_memory_test_and_clear_dirty(ram_addr_t start, - ram_addr_t length, - unsigned client); - -DirtyBitmapSnapshot *cpu_physical_memory_snapshot_and_clear_dirty - (MemoryRegion *mr, hwaddr offset, hwaddr length, unsigned client); - -bool cpu_physical_memory_snapshot_get_dirty(DirtyBitmapSnapshot *snap, - ram_addr_t start, - ram_addr_t length); - -static inline void cpu_physical_memory_clear_dirty_range(ram_addr_t start, - ram_addr_t length) -{ - cpu_physical_memory_test_and_clear_dirty(start, length, DIRTY_MEMORY_MIGRATION); - cpu_physical_memory_test_and_clear_dirty(start, length, DIRTY_MEMORY_VGA); - cpu_physical_memory_test_and_clear_dirty(start, length, DIRTY_MEMORY_CODE); -} - - -/* Called with RCU critical section */ -static inline -uint64_t cpu_physical_memory_sync_dirty_bitmap(RAMBlock *rb, - ram_addr_t start, - ram_addr_t length) -{ - ram_addr_t addr; - unsigned long word = BIT_WORD((start + rb->offset) >> TARGET_PAGE_BITS); - uint64_t num_dirty = 0; - unsigned long *dest = rb->bmap; - - /* start address and length is aligned at the start of a word? */ - if (((word * BITS_PER_LONG) << TARGET_PAGE_BITS) == - (start + rb->offset) && - !(length & ((BITS_PER_LONG << TARGET_PAGE_BITS) - 1))) { - int k; - int nr = BITS_TO_LONGS(length >> TARGET_PAGE_BITS); - unsigned long * const *src; - unsigned long idx = (word * BITS_PER_LONG) / DIRTY_MEMORY_BLOCK_SIZE; - unsigned long offset = BIT_WORD((word * BITS_PER_LONG) % - DIRTY_MEMORY_BLOCK_SIZE); - unsigned long page = BIT_WORD(start >> TARGET_PAGE_BITS); - - src = qatomic_rcu_read( - &ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION])->blocks; - - for (k = page; k < page + nr; k++) { - if (src[idx][offset]) { - unsigned long bits = qatomic_xchg(&src[idx][offset], 0); - unsigned long new_dirty; - new_dirty = ~dest[k]; - dest[k] |= bits; - new_dirty &= bits; - num_dirty += ctpopl(new_dirty); - } - - if (++offset >= BITS_TO_LONGS(DIRTY_MEMORY_BLOCK_SIZE)) { - offset = 0; - idx++; - } - } - if (num_dirty) { - cpu_physical_memory_dirty_bits_cleared(start, length); - } - - if (rb->clear_bmap) { - /* - * Postpone the dirty bitmap clear to the point before we - * really send the pages, also we will split the clear - * dirty procedure into smaller chunks. - */ - clear_bmap_set(rb, start >> TARGET_PAGE_BITS, - length >> TARGET_PAGE_BITS); - } else { - /* Slow path - still do that in a huge chunk */ - memory_region_clear_dirty_bitmap(rb->mr, start, length); - } - } else { - ram_addr_t offset = rb->offset; - - for (addr = 0; addr < length; addr += TARGET_PAGE_SIZE) { - if (cpu_physical_memory_test_and_clear_dirty( - start + addr + offset, - TARGET_PAGE_SIZE, - DIRTY_MEMORY_MIGRATION)) { - long k = (start + addr) >> TARGET_PAGE_BITS; - if (!test_and_set_bit(k, dest)) { - num_dirty++; - } - } - } - } - - return num_dirty; -} -#endif -#endif diff --git a/include/exec/target_page.h b/include/exec/target_page.h index 8e89e5c..813591c 100644 --- a/include/exec/target_page.h +++ b/include/exec/target_page.h @@ -41,7 +41,6 @@ extern const TargetPageBits target_page; # endif # define TARGET_PAGE_SIZE (-(int)TARGET_PAGE_MASK) #else -# define TARGET_PAGE_BITS_MIN TARGET_PAGE_BITS # define TARGET_PAGE_SIZE (1 << TARGET_PAGE_BITS) # define TARGET_PAGE_MASK ((TARGET_PAGE_TYPE)-1 << TARGET_PAGE_BITS) #endif @@ -63,7 +62,15 @@ static inline int qemu_target_page_bits(void) return TARGET_PAGE_BITS; } -int qemu_target_page_bits_min(void); -size_t qemu_target_pages_to_MiB(size_t pages); +/* Convert target pages to MiB (2**20). */ +static inline size_t qemu_target_pages_to_MiB(size_t pages) +{ + int page_bits = TARGET_PAGE_BITS; + + /* So far, the largest (non-huge) page size is 64k, i.e. 16 bits. */ + g_assert(page_bits < 20); + + return pages >> (20 - page_bits); +} #endif diff --git a/include/exec/tb-flush.h b/include/exec/tb-flush.h index 142c240..e971d4b 100644 --- a/include/exec/tb-flush.h +++ b/include/exec/tb-flush.h @@ -9,19 +9,29 @@ #define _TB_FLUSH_H_ /** - * tb_flush() - flush all translation blocks - * @cs: CPUState (must be valid, but treated as anonymous pointer) + * tb_flush__exclusive_or_serial() * - * Used to flush all the translation blocks in the system. Sometimes - * it is simpler to flush everything than work out which individual - * translations are now invalid and ensure they are not called - * anymore. + * Used to flush all the translation blocks in the system. Mostly this is + * used to empty the code generation buffer after it is full. Sometimes it + * is used when it is simpler to flush everything than work out which + * individual translations are now invalid. * - * tb_flush() takes care of running the flush in an exclusive context - * if it is not already running in one. This means no guest code will - * run until this complete. + * Must be called from an exclusive or serial context, e.g. start_exclusive, + * vm_stop, or when there is only one vcpu. Note that start_exclusive cannot + * be called from within the cpu run loop, so this cannot be called from + * within target code. */ -void tb_flush(CPUState *cs); +void tb_flush__exclusive_or_serial(void); + +/** + * queue_tb_flush() - add flush to the cpu work queue + * @cs: CPUState + * + * Flush all translation blocks the next time @cs processes the work queue. + * This should generally be followed by cpu_loop_exit(), so that the work + * queue is processed promptly. + */ +void queue_tb_flush(CPUState *cs); void tcg_flush_jmp_cache(CPUState *cs); diff --git a/include/exec/tlb-flags.h b/include/exec/tlb-flags.h new file mode 100644 index 0000000..357e790 --- /dev/null +++ b/include/exec/tlb-flags.h @@ -0,0 +1,86 @@ +/* + * TLB flags definition + * + * Copyright (c) 2003 Fabrice Bellard + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ +#ifndef TLB_FLAGS_H +#define TLB_FLAGS_H + +/* + * Flags returned for lookup of a TLB virtual address. + */ + +#ifdef CONFIG_USER_ONLY + +/* + * Allow some level of source compatibility with softmmu. + * Invalid is set when the page does not have requested permissions. + * MMIO is set when we want the target helper to use the functional + * interface for load/store so that plugins see the access. + */ +#define TLB_INVALID_MASK (1 << 0) +#define TLB_MMIO (1 << 1) +#define TLB_WATCHPOINT 0 + +#else + +/* + * Flags stored in CPUTLBEntryFull.slow_flags[x]. + * TLB_FORCE_SLOW must be set in CPUTLBEntry.addr_idx[x]. + */ + +/* Set if TLB entry requires byte swap. */ +#define TLB_BSWAP (1 << 0) +/* Set if TLB entry contains a watchpoint. */ +#define TLB_WATCHPOINT (1 << 1) +/* Set if TLB entry requires aligned accesses. */ +#define TLB_CHECK_ALIGNED (1 << 2) +/* Set if TLB entry writes ignored. */ +#define TLB_DISCARD_WRITE (1 << 3) +/* Set if TLB entry is an IO callback. */ +#define TLB_MMIO (1 << 4) + +#define TLB_SLOW_FLAGS_MASK \ + (TLB_BSWAP | TLB_WATCHPOINT | TLB_CHECK_ALIGNED | \ + TLB_DISCARD_WRITE | TLB_MMIO) + +/* + * Flags stored in CPUTLBEntry.addr_idx[x]. + * These must be above the largest alignment (64 bytes), + * and below the smallest page size (1024 bytes). + * This leaves bits [9:6] available for use. + */ + +/* Zero if TLB entry is valid. */ +#define TLB_INVALID_MASK (1 << 6) +/* Set if TLB entry references a clean RAM page. */ +#define TLB_NOTDIRTY (1 << 7) +/* Set if the slow path must be used; more flags in CPUTLBEntryFull. */ +#define TLB_FORCE_SLOW (1 << 8) + +/* + * Use this mask to check interception with an alignment mask + * in a TCG backend. + */ +#define TLB_FLAGS_MASK \ + (TLB_INVALID_MASK | TLB_NOTDIRTY | TLB_FORCE_SLOW) + +/* The two sets of flags must not overlap. */ +QEMU_BUILD_BUG_ON(TLB_FLAGS_MASK & TLB_SLOW_FLAGS_MASK); + +#endif /* !CONFIG_USER_ONLY */ + +#endif /* TLB_FLAGS_H */ diff --git a/include/exec/translation-block.h b/include/exec/translation-block.h index 3c69bc7..cdce399 100644 --- a/include/exec/translation-block.h +++ b/include/exec/translation-block.h @@ -13,6 +13,7 @@ #include "exec/vaddr.h" #ifdef CONFIG_USER_ONLY #include "qemu/interval-tree.h" +#include "exec/target_page.h" #endif /* @@ -157,4 +158,57 @@ static inline uint32_t tb_cflags(const TranslationBlock *tb) bool tcg_cflags_has(CPUState *cpu, uint32_t flags); void tcg_cflags_set(CPUState *cpu, uint32_t flags); +static inline tb_page_addr_t tb_page_addr0(const TranslationBlock *tb) +{ +#ifdef CONFIG_USER_ONLY + return tb->itree.start; +#else + return tb->page_addr[0]; +#endif +} + +static inline tb_page_addr_t tb_page_addr1(const TranslationBlock *tb) +{ +#ifdef CONFIG_USER_ONLY + tb_page_addr_t next = tb->itree.last & TARGET_PAGE_MASK; + return next == (tb->itree.start & TARGET_PAGE_MASK) ? -1 : next; +#else + return tb->page_addr[1]; +#endif +} + +static inline void tb_set_page_addr0(TranslationBlock *tb, + tb_page_addr_t addr) +{ +#ifdef CONFIG_USER_ONLY + tb->itree.start = addr; + /* + * To begin, we record an interval of one byte. When the translation + * loop encounters a second page, the interval will be extended to + * include the first byte of the second page, which is sufficient to + * allow tb_page_addr1() above to work properly. The final corrected + * interval will be set by tb_page_add() from tb->size before the + * node is added to the interval tree. + */ + tb->itree.last = addr; +#else + tb->page_addr[0] = addr; +#endif +} + +static inline void tb_set_page_addr1(TranslationBlock *tb, + tb_page_addr_t addr) +{ +#ifdef CONFIG_USER_ONLY + /* Extend the interval to the first byte of the second page. See above. */ + tb->itree.last = addr; +#else + tb->page_addr[1] = addr; +#endif +} + +/* TranslationBlock invalidate API */ +void tb_invalidate_phys_range(CPUState *cpu, tb_page_addr_t start, + tb_page_addr_t last); + #endif /* EXEC_TRANSLATION_BLOCK_H */ diff --git a/include/exec/translator.h b/include/exec/translator.h index d70942a..3c32655 100644 --- a/include/exec/translator.h +++ b/include/exec/translator.h @@ -18,7 +18,7 @@ * member in your target-specific DisasContext. */ -#include "qemu/bswap.h" +#include "exec/memop.h" #include "exec/vaddr.h" /** @@ -73,6 +73,7 @@ struct DisasContextBase { int max_insns; bool plugin_enabled; bool fake_insn; + uint8_t code_mmuidx; struct TCGOp *insn_start; void *host_addr[2]; @@ -180,42 +181,53 @@ bool translator_io_start(DisasContextBase *db); */ uint8_t translator_ldub(CPUArchState *env, DisasContextBase *db, vaddr pc); -uint16_t translator_lduw(CPUArchState *env, DisasContextBase *db, vaddr pc); -uint32_t translator_ldl(CPUArchState *env, DisasContextBase *db, vaddr pc); -uint64_t translator_ldq(CPUArchState *env, DisasContextBase *db, vaddr pc); +uint16_t translator_lduw_end(CPUArchState *env, DisasContextBase *db, + vaddr pc, MemOp endian); +uint32_t translator_ldl_end(CPUArchState *env, DisasContextBase *db, + vaddr pc, MemOp endian); +uint64_t translator_ldq_end(CPUArchState *env, DisasContextBase *db, + vaddr pc, MemOp endian); + +#ifdef COMPILING_PER_TARGET +static inline uint16_t +translator_lduw(CPUArchState *env, DisasContextBase *db, vaddr pc) +{ + return translator_lduw_end(env, db, pc, MO_TE); +} + +static inline uint32_t +translator_ldl(CPUArchState *env, DisasContextBase *db, vaddr pc) +{ + return translator_ldl_end(env, db, pc, MO_TE); +} + +static inline uint64_t +translator_ldq(CPUArchState *env, DisasContextBase *db, vaddr pc) +{ + return translator_ldq_end(env, db, pc, MO_TE); +} static inline uint16_t translator_lduw_swap(CPUArchState *env, DisasContextBase *db, vaddr pc, bool do_swap) { - uint16_t ret = translator_lduw(env, db, pc); - if (do_swap) { - ret = bswap16(ret); - } - return ret; + return translator_lduw_end(env, db, pc, MO_TE ^ (do_swap * MO_BSWAP)); } static inline uint32_t translator_ldl_swap(CPUArchState *env, DisasContextBase *db, vaddr pc, bool do_swap) { - uint32_t ret = translator_ldl(env, db, pc); - if (do_swap) { - ret = bswap32(ret); - } - return ret; + return translator_ldl_end(env, db, pc, MO_TE ^ (do_swap * MO_BSWAP)); } static inline uint64_t translator_ldq_swap(CPUArchState *env, DisasContextBase *db, vaddr pc, bool do_swap) { - uint64_t ret = translator_ldq(env, db, pc); - if (do_swap) { - ret = bswap64(ret); - } - return ret; + return translator_ldq_end(env, db, pc, MO_TE ^ (do_swap * MO_BSWAP)); } +#endif /* COMPILING_PER_TARGET */ /** * translator_fake_ld - fake instruction load diff --git a/include/exec/tswap.h b/include/exec/tswap.h index ecd4fae..72219e2 100644 --- a/include/exec/tswap.h +++ b/include/exec/tswap.h @@ -9,17 +9,7 @@ #define TSWAP_H #include "qemu/bswap.h" - -/** - * target_words_bigendian: - * Returns true if the (default) endianness of the target is big endian, - * false otherwise. Note that in target-specific code, you can use - * TARGET_BIG_ENDIAN directly instead. On the other hand, common - * code should normally never need to know about the endianness of the - * target, so please do *not* use this function unless you know very well - * what you are doing! - */ -bool target_words_bigendian(void); +#include "qemu/target-info.h" /* * If we're in target-specific code, we can hard-code the swapping @@ -28,7 +18,7 @@ bool target_words_bigendian(void); #ifdef COMPILING_PER_TARGET #define target_needs_bswap() (HOST_BIG_ENDIAN != TARGET_BIG_ENDIAN) #else -#define target_needs_bswap() (HOST_BIG_ENDIAN != target_words_bigendian()) +#define target_needs_bswap() (HOST_BIG_ENDIAN != target_big_endian()) #endif /* COMPILING_PER_TARGET */ static inline uint16_t tswap16(uint16_t s) diff --git a/include/exec/watchpoint.h b/include/exec/watchpoint.h new file mode 100644 index 0000000..4b66688 --- /dev/null +++ b/include/exec/watchpoint.h @@ -0,0 +1,41 @@ +/* + * CPU watchpoints + * + * Copyright (c) 2012 SUSE LINUX Products GmbH + * SPDX-License-Identifier: LGPL-2.1-or-later + */ + +#ifndef EXEC_WATCHPOINT_H +#define EXEC_WATCHPOINT_H + +#if defined(CONFIG_USER_ONLY) +static inline int cpu_watchpoint_insert(CPUState *cpu, vaddr addr, vaddr len, + int flags, CPUWatchpoint **watchpoint) +{ + return -ENOSYS; +} + +static inline int cpu_watchpoint_remove(CPUState *cpu, vaddr addr, + vaddr len, int flags) +{ + return -ENOSYS; +} + +static inline void cpu_watchpoint_remove_by_ref(CPUState *cpu, + CPUWatchpoint *wp) +{ +} + +static inline void cpu_watchpoint_remove_all(CPUState *cpu, int mask) +{ +} +#else +int cpu_watchpoint_insert(CPUState *cpu, vaddr addr, vaddr len, + int flags, CPUWatchpoint **watchpoint); +int cpu_watchpoint_remove(CPUState *cpu, vaddr addr, + vaddr len, int flags); +void cpu_watchpoint_remove_by_ref(CPUState *cpu, CPUWatchpoint *watchpoint); +void cpu_watchpoint_remove_all(CPUState *cpu, int mask); +#endif + +#endif /* EXEC_WATCHPOINT_H */ diff --git a/include/gdbstub/commands.h b/include/gdbstub/commands.h index 40f0514..bff3674 100644 --- a/include/gdbstub/commands.h +++ b/include/gdbstub/commands.h @@ -1,5 +1,5 @@ #ifndef GDBSTUB_COMMANDS_H -#define GDBSTUB +#define GDBSTUB_COMMANDS_H typedef void (*GdbCmdHandler)(GArray *params, void *user_ctx); diff --git a/include/gdbstub/helpers.h b/include/gdbstub/helpers.h index 6f7cc48..b685afa 100644 --- a/include/gdbstub/helpers.h +++ b/include/gdbstub/helpers.h @@ -16,7 +16,8 @@ #error "gdbstub helpers should only be included by target specific code" #endif -#include "exec/tswap.h" +#include "qemu/bswap.h" +#include "qemu/target-info.h" #include "cpu-param.h" /* @@ -33,40 +34,49 @@ static inline int gdb_get_reg8(GByteArray *buf, uint8_t val) static inline int gdb_get_reg16(GByteArray *buf, uint16_t val) { - uint16_t to_word = tswap16(val); - g_byte_array_append(buf, (uint8_t *) &to_word, 2); + if (target_big_endian()) { + cpu_to_be16s(&val); + } else { + cpu_to_le16s(&val); + } + g_byte_array_append(buf, (uint8_t *) &val, 2); return 2; } static inline int gdb_get_reg32(GByteArray *buf, uint32_t val) { - uint32_t to_long = tswap32(val); - g_byte_array_append(buf, (uint8_t *) &to_long, 4); + if (target_big_endian()) { + cpu_to_be32s(&val); + } else { + cpu_to_le32s(&val); + } + g_byte_array_append(buf, (uint8_t *) &val, 4); return 4; } static inline int gdb_get_reg64(GByteArray *buf, uint64_t val) { - uint64_t to_quad = tswap64(val); - g_byte_array_append(buf, (uint8_t *) &to_quad, 8); + if (target_big_endian()) { + cpu_to_be64s(&val); + } else { + cpu_to_le64s(&val); + } + g_byte_array_append(buf, (uint8_t *) &val, 8); return 8; } static inline int gdb_get_reg128(GByteArray *buf, uint64_t val_hi, uint64_t val_lo) { - uint64_t to_quad; -#if TARGET_BIG_ENDIAN - to_quad = tswap64(val_hi); - g_byte_array_append(buf, (uint8_t *) &to_quad, 8); - to_quad = tswap64(val_lo); - g_byte_array_append(buf, (uint8_t *) &to_quad, 8); -#else - to_quad = tswap64(val_lo); - g_byte_array_append(buf, (uint8_t *) &to_quad, 8); - to_quad = tswap64(val_hi); - g_byte_array_append(buf, (uint8_t *) &to_quad, 8); -#endif + uint64_t tmp[2]; + if (target_big_endian()) { + tmp[0] = cpu_to_be64(val_hi); + tmp[1] = cpu_to_be64(val_lo); + } else { + tmp[0] = cpu_to_le64(val_lo); + tmp[1] = cpu_to_le64(val_hi); + } + g_byte_array_append(buf, (uint8_t *)&tmp, 16); return 16; } diff --git a/include/glib-compat.h b/include/glib-compat.h index 86be439..2e32b90 100644 --- a/include/glib-compat.h +++ b/include/glib-compat.h @@ -37,6 +37,13 @@ #endif /* + * These functions perform function pointer casts which can cause function call + * failure on Emscripten. Use g_slist_sort_with_data and g_list_sort_with_data + * instead of these functions. + */ +#pragma GCC poison g_slist_sort g_list_sort + +/* * Note that because of the GLIB_VERSION_MAX_ALLOWED constant above, allowing * use of functions from newer GLib via this compat header needs a little * trickery to prevent warnings being emitted. diff --git a/include/hw/acpi/acpi.h b/include/hw/acpi/acpi.h index d1a4fa2..4b8ee09 100644 --- a/include/hw/acpi/acpi.h +++ b/include/hw/acpi/acpi.h @@ -21,7 +21,7 @@ */ #include "qemu/notify.h" -#include "exec/memory.h" +#include "system/memory.h" #include "hw/acpi/acpi_dev_interface.h" /* diff --git a/include/hw/acpi/acpi_dev_interface.h b/include/hw/acpi/acpi_dev_interface.h index 68d9d15..8294f8f 100644 --- a/include/hw/acpi/acpi_dev_interface.h +++ b/include/hw/acpi/acpi_dev_interface.h @@ -13,6 +13,7 @@ typedef enum { ACPI_NVDIMM_HOTPLUG_STATUS = 16, ACPI_VMGENID_CHANGE_STATUS = 32, ACPI_POWER_DOWN_STATUS = 64, + ACPI_GENERIC_ERROR = 128, } AcpiEventStatusBits; #define TYPE_ACPI_DEVICE_IF "acpi-device-interface" diff --git a/include/hw/acpi/aml-build.h b/include/hw/acpi/aml-build.h index c18f681..f38e129 100644 --- a/include/hw/acpi/aml-build.h +++ b/include/hw/acpi/aml-build.h @@ -252,6 +252,7 @@ struct CrsRangeSet { /* Consumer/Producer */ #define AML_SERIAL_BUS_FLAG_CONSUME_ONLY (1 << 1) +#define ACPI_APEI_ERROR_DEVICE "GEDD" /** * init_aml_allocator: * @@ -382,6 +383,7 @@ Aml *aml_dma(AmlDmaType typ, AmlDmaBusMaster bm, AmlTransferSize sz, uint8_t channel); Aml *aml_sleep(uint64_t msec); Aml *aml_i2c_serial_bus_device(uint16_t address, const char *resource_source); +Aml *aml_error_device(void); /* Block AML object primitives */ Aml *aml_scope(const char *name_format, ...) G_GNUC_PRINTF(1, 2); diff --git a/include/hw/acpi/generic_event_device.h b/include/hw/acpi/generic_event_device.h index d2dac87..130c014 100644 --- a/include/hw/acpi/generic_event_device.h +++ b/include/hw/acpi/generic_event_device.h @@ -63,12 +63,13 @@ #include "hw/acpi/memory_hotplug.h" #include "hw/acpi/ghes.h" #include "hw/acpi/cpu.h" +#include "hw/acpi/pcihp.h" #include "qom/object.h" #define ACPI_POWER_BUTTON_DEVICE "PWRB" #define TYPE_ACPI_GED "acpi-ged" -OBJECT_DECLARE_SIMPLE_TYPE(AcpiGedState, ACPI_GED) +OBJECT_DECLARE_TYPE(AcpiGedState, AcpiGedClass, ACPI_GED) #define ACPI_GED_EVT_SEL_OFFSET 0x0 #define ACPI_GED_EVT_SEL_LEN 0x4 @@ -101,6 +102,8 @@ OBJECT_DECLARE_SIMPLE_TYPE(AcpiGedState, ACPI_GED) #define ACPI_GED_PWR_DOWN_EVT 0x2 #define ACPI_GED_NVDIMM_HOTPLUG_EVT 0x4 #define ACPI_GED_CPU_HOTPLUG_EVT 0x8 +#define ACPI_GED_PCI_HOTPLUG_EVT 0x10 +#define ACPI_GED_ERROR_EVT 0x20 typedef struct GEDState { MemoryRegion evt; @@ -108,18 +111,31 @@ typedef struct GEDState { uint32_t sel; } GEDState; +#define ACPI_PCIHP_REGION_NAME "pcihp container" +#define ACPI_MEMHP_REGION_NAME "memhp container" + struct AcpiGedState { SysBusDevice parent_obj; MemHotplugState memhp_state; MemoryRegion container_memhp; CPUHotplugState cpuhp_state; MemoryRegion container_cpuhp; + AcpiPciHpState pcihp_state; + MemoryRegion container_pcihp; GEDState ged_state; uint32_t ged_event_bitmap; qemu_irq irq; AcpiGhesState ghes_state; }; +typedef struct AcpiGedClass { + /* <private> */ + SysBusDeviceClass parent_class; + + /*< public >*/ + ResettablePhases parent_phases; +} AcpiGedClass; + void build_ged_aml(Aml *table, const char* name, HotplugHandler *hotplug_dev, uint32_t ged_irq, AmlRegionSpace rs, hwaddr ged_base); void acpi_dsdt_add_power_button(Aml *scope); diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h index 578a582..df2ecbf 100644 --- a/include/hw/acpi/ghes.h +++ b/include/hw/acpi/ghes.h @@ -24,6 +24,9 @@ #include "hw/acpi/bios-linker-loader.h" #include "qapi/error.h" +#include "qemu/notify.h" + +extern NotifierList acpi_generic_error_notifiers; /* * Values for Hardware Error Notification Type field @@ -57,30 +60,54 @@ enum AcpiGhesNotifyType { ACPI_GHES_NOTIFY_RESERVED = 12 }; -enum { - ACPI_HEST_SRC_ID_SEA = 0, - /* future ids go here */ - - ACPI_GHES_ERROR_SOURCE_COUNT +/* + * ID numbers used to fill HEST source ID field + */ +enum AcpiGhesSourceID { + ACPI_HEST_SRC_ID_SYNC, + ACPI_HEST_SRC_ID_QMP, /* Use it only for QMP injected errors */ }; +typedef struct AcpiNotificationSourceId { + enum AcpiGhesSourceID source_id; + enum AcpiGhesNotifyType notify; +} AcpiNotificationSourceId; + +/* + * AcpiGhesState stores GPA values that will be used to fill HEST entries. + * + * When use_hest_addr is false, the GPA of the etc/hardware_errors firmware + * is stored at hw_error_le. This is the default on QEMU 9.x. + * + * When use_hest_addr is true, the GPA of the HEST table is stored at + * hest_addr_le. This is the default for QEMU 10.x and above. + * + * Whe both GPA values are equal to zero means that GHES is not present. + */ typedef struct AcpiGhesState { + uint64_t hest_addr_le; uint64_t hw_error_le; - bool present; /* True if GHES is present at all on this board */ + bool use_hest_addr; /* True if HEST address is present */ } AcpiGhesState; -void acpi_build_hest(GArray *table_data, GArray *hardware_errors, +void acpi_build_hest(AcpiGhesState *ags, GArray *table_data, + GArray *hardware_errors, BIOSLinker *linker, + const AcpiNotificationSourceId * const notif_source, + int num_sources, const char *oem_id, const char *oem_table_id); void acpi_ghes_add_fw_cfg(AcpiGhesState *vms, FWCfgState *s, GArray *hardware_errors); -int acpi_ghes_memory_errors(uint16_t source_id, uint64_t error_physical_addr); +int acpi_ghes_memory_errors(AcpiGhesState *ags, uint16_t source_id, + uint64_t error_physical_addr); +void ghes_record_cper_errors(AcpiGhesState *ags, const void *cper, size_t len, + uint16_t source_id, Error **errp); /** - * acpi_ghes_present: Report whether ACPI GHES table is present + * acpi_ghes_get_state: Get a pointer for ACPI ghes state * - * Returns: true if the system has an ACPI GHES table and it is - * safe to call acpi_ghes_memory_errors() to record a memory error. + * Returns: a pointer to ghes state if the system has an ACPI GHES table, + * NULL, otherwise. */ -bool acpi_ghes_present(void); +AcpiGhesState *acpi_ghes_get_state(void); #endif diff --git a/include/hw/acpi/ich9_tco.h b/include/hw/acpi/ich9_tco.h index 2562a7c..b3c3f69 100644 --- a/include/hw/acpi/ich9_tco.h +++ b/include/hw/acpi/ich9_tco.h @@ -10,7 +10,7 @@ #ifndef HW_ACPI_TCO_H #define HW_ACPI_TCO_H -#include "exec/memory.h" +#include "system/memory.h" #include "migration/vmstate.h" /* As per ICH9 spec, the internal timer has an error of ~0.6s on every tick */ diff --git a/include/hw/acpi/pci.h b/include/hw/acpi/pci.h index 6359d57..20b6725 100644 --- a/include/hw/acpi/pci.h +++ b/include/hw/acpi/pci.h @@ -36,11 +36,12 @@ typedef struct AcpiMcfgInfo { void build_mcfg(GArray *table_data, BIOSLinker *linker, AcpiMcfgInfo *info, const char *oem_id, const char *oem_table_id); -Aml *aml_pci_device_dsm(void); -void build_append_pci_bus_devices(Aml *parent_scope, PCIBus *bus); void build_pci_bridge_aml(AcpiDevAmlIf *adev, Aml *scope); void build_srat_generic_affinity_structures(GArray *table_data); +Aml *build_pci_host_bridge_osc_method(bool enable_native_pcie_hotplug); +Aml *build_pci_bridge_edsm(void); + #endif diff --git a/include/hw/acpi/pcihp.h b/include/hw/acpi/pcihp.h index ac21a95..ca6a258 100644 --- a/include/hw/acpi/pcihp.h +++ b/include/hw/acpi/pcihp.h @@ -3,7 +3,7 @@ * * QEMU supports PCI hotplug via ACPI. This module * implements the interface between QEMU and the ACPI BIOS. - * Interface specification - see docs/specs/acpi_pci_hotplug.txt + * Interface specification - see docs/specs/acpi_pci_hotplug.rst * * Copyright (c) 2013, Red Hat Inc, Michael S. Tsirkin (mst@redhat.com) * Copyright (c) 2006 Fabrice Bellard @@ -28,11 +28,18 @@ #define HW_ACPI_PCIHP_H #include "hw/acpi/acpi.h" +#include "hw/acpi/aml-build.h" #include "hw/hotplug.h" #define ACPI_PCIHP_IO_BASE_PROP "acpi-pcihp-io-base" #define ACPI_PCIHP_IO_LEN_PROP "acpi-pcihp-io-len" +/* PCI Hot-plug registers bases. See docs/specs/acpi_pci_hotplug.rst */ +#define ACPI_PCIHP_SEJ_BASE 0x8 +#define ACPI_PCIHP_BNMR_BASE 0x10 + +#define ACPI_PCIHP_SIZE 0x0018 + typedef struct AcpiPciHpPciStatus { uint32_t up; uint32_t down; @@ -55,10 +62,10 @@ typedef struct AcpiPciHpState { bool use_acpi_root_pci_hotplug; } AcpiPciHpState; -void acpi_pcihp_init(Object *owner, AcpiPciHpState *, PCIBus *root, +void acpi_pcihp_init(Object *owner, AcpiPciHpState *, MemoryRegion *io, uint16_t io_base); -bool acpi_pcihp_is_hotpluggbale_bus(AcpiPciHpState *s, BusState *bus); +bool acpi_pcihp_is_hotpluggable_bus(AcpiPciHpState *s, BusState *bus); void acpi_pcihp_device_pre_plug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp); void acpi_pcihp_device_plug_cb(HotplugHandler *hotplug_dev, AcpiPciHpState *s, @@ -69,6 +76,14 @@ void acpi_pcihp_device_unplug_request_cb(HotplugHandler *hotplug_dev, AcpiPciHpState *s, DeviceState *dev, Error **errp); +void build_acpi_pci_hotplug(Aml *table, AmlRegionSpace rs, uint64_t pcihp_addr); +void build_append_pci_dsm_func0_common(Aml *ctx, Aml *retvar); +void build_append_pcihp_resources(Aml *table, + uint64_t io_addr, uint64_t io_len); +bool build_append_notification_callback(Aml *parent_scope, const PCIBus *bus); + +void build_append_pci_bus_devices(Aml *parent_scope, PCIBus *bus); + /* Called on reset */ void acpi_pcihp_reset(AcpiPciHpState *s); diff --git a/include/hw/arm/aspeed.h b/include/hw/arm/aspeed.h index 9cae45a..714bbd3 100644 --- a/include/hw/arm/aspeed.h +++ b/include/hw/arm/aspeed.h @@ -11,6 +11,7 @@ #include "hw/boards.h" #include "qom/object.h" +#include "hw/arm/aspeed_soc.h" typedef struct AspeedMachineState AspeedMachineState; @@ -24,6 +25,24 @@ DECLARE_OBJ_CHECKERS(AspeedMachineState, AspeedMachineClass, #define ASPEED_MAC2_ON (1 << 2) #define ASPEED_MAC3_ON (1 << 3) +/* On 32-bit hosts, lower RAM to 1G because of the 2047 MB limit */ +#if HOST_LONG_BITS == 32 +#define ASPEED_RAM_SIZE(sz) MIN((sz), 1 * GiB) +#else +#define ASPEED_RAM_SIZE(sz) (sz) +#endif + +struct AspeedMachineState { + MachineState parent_obj; + + AspeedSoCState *soc; + MemoryRegion boot_rom; + bool mmio_exec; + uint32_t uart_chosen; + char *fmc_model; + char *spi_model; + uint32_t hw_strap1; +}; struct AspeedMachineClass { MachineClass parent_obj; @@ -35,12 +54,75 @@ struct AspeedMachineClass { uint32_t hw_strap2; const char *fmc_model; const char *spi_model; + const char *spi2_model; uint32_t num_cs; + uint32_t num_cs2; uint32_t macs_mask; void (*i2c_init)(AspeedMachineState *bmc); uint32_t uart_default; bool sdhci_wp_inverted; + bool vbootrom; }; +/* + * aspeed_machine_class_init_cpus_defaults: + * @mc: the #MachineClass to be initialized. + * + * Initialize the default CPU configuration for an Aspeed machine class. + * This function sets the default, minimum, and maximum CPU counts + * to match the number of CPUs defined in the associated SoC class, + * and copies its list of valid CPU types. + */ +void aspeed_machine_class_init_cpus_defaults(MachineClass *mc); + +/* + * aspeed_create_pca9552: + * @soc: pointer to the #AspeedSoCState. + * @bus_id: the I2C bus index to attach the device. + * @addr: the I2C address of the PCA9552 device. + * + * Create and attach a PCA9552 LED controller device to the specified I2C bus + * of the given Aspeed SoC. The device is instantiated using + * i2c_slave_create_simple() with the PCA9552 device type. + */ +void aspeed_create_pca9552(AspeedSoCState *soc, int bus_id, int addr); + +/* + * aspeed_create_pca9554: + * @soc: pointer to the #AspeedSoCState. + * @bus_id: the I2C bus index to attach the device. + * @addr: the I2C address of the PCA9554 device. + * + * Create and attach a PCA9554 I/O expander to the specified I2C bus + * of the given Aspeed SoC. The device is created via + * i2c_slave_create_simple() and returned as an #I2CSlave pointer. + * + * Returns: a pointer to the newly created #I2CSlave instance. + */ +I2CSlave *aspeed_create_pca9554(AspeedSoCState *soc, int bus_id, int addr); + +/* + * aspeed_machine_ast2600_class_emmc_init: + * @oc: the #ObjectClass to initialize. + * + * Initialize eMMC-related properties for the AST2600 Aspeed machine class. + * This function is typically invoked during class initialization to set up + * default configuration or attach eMMC-specific devices for AST2600 platforms. + */ +void aspeed_machine_ast2600_class_emmc_init(ObjectClass *oc); + +/* + * aspeed_connect_serial_hds_to_uarts: + * @bmc: pointer to the #AspeedMachineState. + * + * Connect host serial backends (character devices) to the UART interfaces + * of the Aspeed SoC used by the given BMC machine. + * + * The function assigns `serial_hd(0)` to the primary UART channel + * (either chosen via `bmc->uart_chosen` or the machine class default), + * and iteratively connects remaining serial ports to other available UARTs + * on the SoC based on their index. + */ +void aspeed_connect_serial_hds_to_uarts(AspeedMachineState *bmc); #endif diff --git a/include/hw/arm/aspeed_coprocessor.h b/include/hw/arm/aspeed_coprocessor.h new file mode 100644 index 0000000..4a50f68 --- /dev/null +++ b/include/hw/arm/aspeed_coprocessor.h @@ -0,0 +1,63 @@ +/* + * ASPEED Coprocessor + * + * Copyright (C) 2025 ASPEED Technology Inc. + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef ASPEED_COPROCESSOR_H +#define ASPEED_COPROCESSOR_H + +#include "qom/object.h" +#include "hw/arm/aspeed_soc.h" + +struct AspeedCoprocessorState { + DeviceState parent; + + MemoryRegion *memory; + MemoryRegion sdram; + MemoryRegion *sram; + MemoryRegion sram_alias; + MemoryRegion uart_alias; + MemoryRegion scu_alias; + Clock *sysclk; + + AspeedSCUState *scu; + AspeedSCUState scuio; + AspeedTimerCtrlState timerctrl; + SerialMM *uart; + int uart_dev; +}; + +#define TYPE_ASPEED_COPROCESSOR "aspeed-coprocessor" +OBJECT_DECLARE_TYPE(AspeedCoprocessorState, AspeedCoprocessorClass, + ASPEED_COPROCESSOR) + +struct AspeedCoprocessorClass { + DeviceClass parent_class; + + /** valid_cpu_types: NULL terminated array of a single CPU type. */ + const char * const *valid_cpu_types; + const hwaddr *memmap; + const int *irqmap; +}; + +struct Aspeed27x0CoprocessorState { + AspeedCoprocessorState parent; + AspeedINTCState intc[2]; + UnimplementedDeviceState ipc[2]; + UnimplementedDeviceState scuio; + + ARMv7MState armv7m; +}; + +#define TYPE_ASPEED27X0SSP_COPROCESSOR "aspeed27x0ssp-coprocessor" +OBJECT_DECLARE_SIMPLE_TYPE(Aspeed27x0CoprocessorState, + ASPEED27X0SSP_COPROCESSOR) + +#define TYPE_ASPEED27X0TSP_COPROCESSOR "aspeed27x0tsp-coprocessor" +DECLARE_OBJ_CHECKERS(Aspeed27x0CoprocessorState, AspeedCoprocessorClass, + ASPEED27X0TSP_COPROCESSOR, TYPE_ASPEED27X0TSP_COPROCESSOR) + +#endif /* ASPEED_COPROCESSOR_H */ diff --git a/include/hw/arm/aspeed_soc.h b/include/hw/arm/aspeed_soc.h index f069d17..4b8e599 100644 --- a/include/hw/arm/aspeed_soc.h +++ b/include/hw/arm/aspeed_soc.h @@ -37,18 +37,22 @@ #include "qom/object.h" #include "hw/misc/aspeed_lpc.h" #include "hw/misc/unimp.h" +#include "hw/pci-host/aspeed_pcie.h" #include "hw/misc/aspeed_peci.h" #include "hw/fsi/aspeed_apb2opb.h" #include "hw/char/serial-mm.h" #include "hw/intc/arm_gicv3.h" +#define VBOOTROM_FILE_NAME "ast27x0_bootrom.bin" + #define ASPEED_SPIS_NUM 3 -#define ASPEED_EHCIS_NUM 2 +#define ASPEED_EHCIS_NUM 4 #define ASPEED_WDTS_NUM 8 #define ASPEED_CPUS_NUM 4 #define ASPEED_MACS_NUM 4 #define ASPEED_UARTS_NUM 13 #define ASPEED_JTAG_NUM 2 +#define ASPEED_PCIE_NUM 3 struct AspeedSoCState { DeviceState parent; @@ -59,6 +63,8 @@ struct AspeedSoCState { MemoryRegion sram; MemoryRegion spi_boot_container; MemoryRegion spi_boot; + MemoryRegion vbootrom; + MemoryRegion pcie_mmio_alias[ASPEED_PCIE_NUM]; AddressSpace dram_as; AspeedRtcState rtc; AspeedTimerCtrlState timerctrl; @@ -86,10 +92,14 @@ struct AspeedSoCState { AspeedSDHCIState sdhci; AspeedSDHCIState emmc; AspeedLPCState lpc; + AspeedPCIECfgState pcie[ASPEED_PCIE_NUM]; + AspeedPCIEPhyState pcie_phy[ASPEED_PCIE_NUM]; AspeedPECIState peci; SerialMM uart[ASPEED_UARTS_NUM]; Clock *sysclk; UnimplementedDeviceState iomem; + UnimplementedDeviceState iomem0; + UnimplementedDeviceState iomem1; UnimplementedDeviceState video; UnimplementedDeviceState emmc_boot_controller; UnimplementedDeviceState dpmcu; @@ -97,6 +107,7 @@ struct AspeedSoCState { UnimplementedDeviceState espi; UnimplementedDeviceState udc; UnimplementedDeviceState sgpiom; + UnimplementedDeviceState ltpi; UnimplementedDeviceState jtag[ASPEED_JTAG_NUM]; AspeedAPB2OPBState fsi[2]; }; @@ -153,6 +164,7 @@ struct AspeedSoCClass { uint32_t silicon_rev; uint64_t sram_size; uint64_t secsram_size; + int pcie_num; int spis_num; int ehcis_num; int wdts_num; @@ -162,15 +174,16 @@ struct AspeedSoCClass { const int *irqmap; const hwaddr *memmap; uint32_t num_cpus; - qemu_irq (*get_irq)(AspeedSoCState *s, int dev); bool (*boot_from_emmc)(AspeedSoCState *s); }; -const char *aspeed_soc_cpu_type(AspeedSoCClass *sc); - enum { + ASPEED_DEV_VBOOTROM, ASPEED_DEV_SPI_BOOT, ASPEED_DEV_IOMEM, + ASPEED_DEV_IOMEM0, + ASPEED_DEV_IOMEM1, + ASPEED_DEV_LTPI, ASPEED_DEV_UART0, ASPEED_DEV_UART1, ASPEED_DEV_UART2, @@ -192,6 +205,8 @@ enum { ASPEED_DEV_SPI2, ASPEED_DEV_EHCI1, ASPEED_DEV_EHCI2, + ASPEED_DEV_EHCI3, + ASPEED_DEV_EHCI4, ASPEED_DEV_VIC, ASPEED_DEV_INTC, ASPEED_DEV_INTCIO, @@ -220,6 +235,15 @@ enum { ASPEED_DEV_LPC, ASPEED_DEV_IBT, ASPEED_DEV_I2C, + ASPEED_DEV_PCIE0, + ASPEED_DEV_PCIE1, + ASPEED_DEV_PCIE2, + ASPEED_DEV_PCIE_PHY0, + ASPEED_DEV_PCIE_PHY1, + ASPEED_DEV_PCIE_PHY2, + ASPEED_DEV_PCIE_MMIO0, + ASPEED_DEV_PCIE_MMIO1, + ASPEED_DEV_PCIE_MMIO2, ASPEED_DEV_PECI, ASPEED_DEV_ETH1, ASPEED_DEV_ETH2, @@ -249,32 +273,43 @@ enum { ASPEED_DEV_SLIIO, ASPEED_GIC_DIST, ASPEED_GIC_REDIST, + ASPEED_DEV_IPC0, + ASPEED_DEV_IPC1, }; -qemu_irq aspeed_soc_get_irq(AspeedSoCState *s, int dev); -bool aspeed_soc_uart_realize(AspeedSoCState *s, Error **errp); -void aspeed_soc_uart_set_chr(AspeedSoCState *s, int dev, Chardev *chr); +const char *aspeed_soc_cpu_type(const char * const *valid_cpu_types); +bool aspeed_soc_uart_realize(MemoryRegion *memory, SerialMM *smm, + const hwaddr addr, Error **errp); +void aspeed_soc_uart_set_chr(SerialMM *uart, int dev, int uarts_base, + int uarts_num, Chardev *chr); bool aspeed_soc_dram_init(AspeedSoCState *s, Error **errp); -void aspeed_mmio_map(AspeedSoCState *s, SysBusDevice *dev, int n, hwaddr addr); -void aspeed_mmio_map_unimplemented(AspeedSoCState *s, SysBusDevice *dev, +void aspeed_mmio_map(MemoryRegion *memory, SysBusDevice *dev, int n, + hwaddr addr); +void aspeed_mmio_map_unimplemented(MemoryRegion *memory, SysBusDevice *dev, const char *name, hwaddr addr, uint64_t size); void aspeed_board_init_flashes(AspeedSMCState *s, const char *flashtype, unsigned int count, int unit0); +void aspeed_write_boot_rom(BlockBackend *blk, hwaddr addr, size_t rom_size, + Error **errp); +void aspeed_install_boot_rom(AspeedSoCState *soc, BlockBackend *blk, + MemoryRegion *boot_rom, uint64_t rom_size); +void aspeed_load_vbootrom(AspeedSoCState *soc, const char *bios_name, + Error **errp); static inline int aspeed_uart_index(int uart_dev) { return uart_dev - ASPEED_DEV_UART0; } -static inline int aspeed_uart_first(AspeedSoCClass *sc) +static inline int aspeed_uart_first(int uarts_base) { - return aspeed_uart_index(sc->uarts_base); + return aspeed_uart_index(uarts_base); } -static inline int aspeed_uart_last(AspeedSoCClass *sc) +static inline int aspeed_uart_last(int uarts_base, int uarts_num) { - return aspeed_uart_first(sc) + sc->uarts_num - 1; + return aspeed_uart_first(uarts_base) + uarts_num - 1; } #endif /* ASPEED_SOC_H */ diff --git a/include/hw/arm/boot.h b/include/hw/arm/boot.h index b12bf61..a2e22bd 100644 --- a/include/hw/arm/boot.h +++ b/include/hw/arm/boot.h @@ -132,6 +132,9 @@ struct arm_boot_info { bool secure_board_setup; arm_endianness endianness; + + /* CPU having load the kernel and that should be the first to boot. */ + ARMCPU *primary_cpu; }; /** diff --git a/include/hw/arm/fsl-imx25.h b/include/hw/arm/fsl-imx25.h index df2f839..b68d433 100644 --- a/include/hw/arm/fsl-imx25.h +++ b/include/hw/arm/fsl-imx25.h @@ -29,7 +29,7 @@ #include "hw/sd/sdhci.h" #include "hw/usb/chipidea.h" #include "hw/watchdog/wdt_imx2.h" -#include "exec/memory.h" +#include "system/memory.h" #include "target/arm/cpu.h" #include "qom/object.h" diff --git a/include/hw/arm/fsl-imx31.h b/include/hw/arm/fsl-imx31.h index 40c593a..41232a2 100644 --- a/include/hw/arm/fsl-imx31.h +++ b/include/hw/arm/fsl-imx31.h @@ -25,7 +25,7 @@ #include "hw/i2c/imx_i2c.h" #include "hw/gpio/imx_gpio.h" #include "hw/watchdog/wdt_imx2.h" -#include "exec/memory.h" +#include "system/memory.h" #include "target/arm/cpu.h" #include "qom/object.h" diff --git a/include/hw/arm/fsl-imx6.h b/include/hw/arm/fsl-imx6.h index 9da32fc..124bbd4 100644 --- a/include/hw/arm/fsl-imx6.h +++ b/include/hw/arm/fsl-imx6.h @@ -34,7 +34,7 @@ #include "hw/usb/imx-usb-phy.h" #include "hw/pci-host/designware.h" #include "hw/or-irq.h" -#include "exec/memory.h" +#include "system/memory.h" #include "cpu.h" #include "qom/object.h" diff --git a/include/hw/arm/fsl-imx6ul.h b/include/hw/arm/fsl-imx6ul.h index 8277b0e..4e3209b 100644 --- a/include/hw/arm/fsl-imx6ul.h +++ b/include/hw/arm/fsl-imx6ul.h @@ -33,7 +33,7 @@ #include "hw/net/imx_fec.h" #include "hw/usb/chipidea.h" #include "hw/usb/imx-usb-phy.h" -#include "exec/memory.h" +#include "system/memory.h" #include "cpu.h" #include "qom/object.h" #include "qemu/units.h" diff --git a/include/hw/arm/machines-qom.h b/include/hw/arm/machines-qom.h new file mode 100644 index 0000000..3f64d5e --- /dev/null +++ b/include/hw/arm/machines-qom.h @@ -0,0 +1,46 @@ +/* + * QOM type definitions for ARM / Aarch64 machines + * + * Copyright (c) Linaro + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_ARM_MACHINES_QOM_H +#define HW_ARM_MACHINES_QOM_H + +#include "hw/boards.h" + +#define TYPE_TARGET_ARM_MACHINE \ + "target-info-arm-machine" + +#define TYPE_TARGET_AARCH64_MACHINE \ + "target-info-aarch64-machine" + +/* + * A machine filtered with arm_machine_interfaces[] or + * arm_aarch64_machine_interfaces[] will be available + * in both qemu-system-arm and qemu-system-aarch64 binaries. + * + * One filtered with aarch64_machine_interfaces[] will only + * be available in the qemu-system-aarch64 binary. + */ +extern const InterfaceInfo arm_machine_interfaces[]; +extern const InterfaceInfo arm_aarch64_machine_interfaces[]; +extern const InterfaceInfo aarch64_machine_interfaces[]; + +/* + * A machine defined with the DEFINE_MACHINE_ARM() macro will be + * available in both qemu-system-arm and qemu-system-aarch64 binaries. + * + * One defined with DEFINE_MACHINE_AARCH64() will only be available in + * the qemu-system-aarch64 binary. + */ +#define DEFINE_MACHINE_ARM(namestr, machine_initfn) \ + DEFINE_MACHINE_WITH_INTERFACE_ARRAY(namestr, machine_initfn, \ + arm_machine_interfaces) +#define DEFINE_MACHINE_AARCH64(namestr, machine_initfn) \ + DEFINE_MACHINE_WITH_INTERFACE_ARRAY(namestr, machine_initfn, \ + aarch64_machine_interfaces) + +#endif diff --git a/include/hw/arm/max78000_soc.h b/include/hw/arm/max78000_soc.h new file mode 100644 index 0000000..a203079 --- /dev/null +++ b/include/hw/arm/max78000_soc.h @@ -0,0 +1,50 @@ +/* + * MAX78000 SOC + * + * Copyright (c) 2025 Jackson Donaldson <jcksn@duck.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_ARM_MAX78000_SOC_H +#define HW_ARM_MAX78000_SOC_H + +#include "hw/or-irq.h" +#include "hw/arm/armv7m.h" +#include "hw/misc/max78000_aes.h" +#include "hw/misc/max78000_gcr.h" +#include "hw/misc/max78000_icc.h" +#include "hw/char/max78000_uart.h" +#include "hw/misc/max78000_trng.h" +#include "qom/object.h" + +#define TYPE_MAX78000_SOC "max78000-soc" +OBJECT_DECLARE_SIMPLE_TYPE(MAX78000State, MAX78000_SOC) + +#define FLASH_BASE_ADDRESS 0x10000000 +#define FLASH_SIZE (512 * 1024) +#define SRAM_BASE_ADDRESS 0x20000000 +#define SRAM_SIZE (128 * 1024) + +/* The MAX78k has 2 instruction caches; only icc0 matters, icc1 is for RISC */ +#define MAX78000_NUM_ICC 2 +#define MAX78000_NUM_UART 3 + +struct MAX78000State { + SysBusDevice parent_obj; + + ARMv7MState armv7m; + + MemoryRegion sram; + MemoryRegion flash; + + Max78000GcrState gcr; + Max78000IccState icc[MAX78000_NUM_ICC]; + Max78000UartState uart[MAX78000_NUM_UART]; + Max78000TrngState trng; + Max78000AesState aes; + + Clock *sysclk; +}; + +#endif diff --git a/include/hw/arm/npcm8xx.h b/include/hw/arm/npcm8xx.h index 9812e6f..a8377db 100644 --- a/include/hw/arm/npcm8xx.h +++ b/include/hw/arm/npcm8xx.h @@ -28,7 +28,8 @@ #include "hw/misc/npcm7xx_mft.h" #include "hw/misc/npcm7xx_pwm.h" #include "hw/misc/npcm7xx_rng.h" -#include "hw/net/npcm7xx_emc.h" +#include "hw/net/npcm_gmac.h" +#include "hw/net/npcm_pcs.h" #include "hw/nvram/npcm7xx_otp.h" #include "hw/sd/npcm7xx_sdhci.h" #include "hw/timer/npcm7xx_timer.h" @@ -36,6 +37,7 @@ #include "hw/usb/hcd-ehci.h" #include "hw/usb/hcd-ohci.h" #include "target/arm/cpu.h" +#include "hw/ssi/npcm_pspi.h" #define NPCM8XX_MAX_NUM_CPUS (4) @@ -98,7 +100,10 @@ struct NPCM8xxState { EHCISysBusState ehci[2]; OHCISysBusState ohci[2]; NPCM7xxFIUState fiu[3]; + NPCMGMACState gmac[4]; + NPCMPCSState pcs; NPCM7xxSDHCIState mmc; + NPCMPSPIState pspi; }; struct NPCM8xxClass { diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index 7cb87ea..bdb2e88 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -20,29 +20,29 @@ #ifndef HW_ARM_OMAP_H #define HW_ARM_OMAP_H -#include "exec/memory.h" +#include "system/memory.h" #include "target/arm/cpu-qom.h" #include "qemu/log.h" #include "qom/object.h" -# define OMAP_EMIFS_BASE 0x00000000 -# define OMAP_CS0_BASE 0x00000000 -# define OMAP_CS1_BASE 0x04000000 -# define OMAP_CS2_BASE 0x08000000 -# define OMAP_CS3_BASE 0x0c000000 -# define OMAP_EMIFF_BASE 0x10000000 -# define OMAP_IMIF_BASE 0x20000000 -# define OMAP_LOCALBUS_BASE 0x30000000 -# define OMAP_MPUI_BASE 0xe1000000 - -# define OMAP730_SRAM_SIZE 0x00032000 -# define OMAP15XX_SRAM_SIZE 0x00030000 -# define OMAP16XX_SRAM_SIZE 0x00004000 -# define OMAP1611_SRAM_SIZE 0x0003e800 -# define OMAP_CS0_SIZE 0x04000000 -# define OMAP_CS1_SIZE 0x04000000 -# define OMAP_CS2_SIZE 0x04000000 -# define OMAP_CS3_SIZE 0x04000000 +#define OMAP_EMIFS_BASE 0x00000000 +#define OMAP_CS0_BASE 0x00000000 +#define OMAP_CS1_BASE 0x04000000 +#define OMAP_CS2_BASE 0x08000000 +#define OMAP_CS3_BASE 0x0c000000 +#define OMAP_EMIFF_BASE 0x10000000 +#define OMAP_IMIF_BASE 0x20000000 +#define OMAP_LOCALBUS_BASE 0x30000000 +#define OMAP_MPUI_BASE 0xe1000000 + +#define OMAP730_SRAM_SIZE 0x00032000 +#define OMAP15XX_SRAM_SIZE 0x00030000 +#define OMAP16XX_SRAM_SIZE 0x00004000 +#define OMAP1611_SRAM_SIZE 0x0003e800 +#define OMAP_CS0_SIZE 0x04000000 +#define OMAP_CS1_SIZE 0x04000000 +#define OMAP_CS2_SIZE 0x04000000 +#define OMAP_CS3_SIZE 0x04000000 /* omap_clk.c */ struct omap_mpu_state_s; @@ -103,228 +103,228 @@ void omap_gpio_set_clk(Omap1GpioState *gpio, omap_clk clk); * Common IRQ numbers for level 1 interrupt handler * See /usr/include/asm-arm/arch-omap/irqs.h in Linux. */ -# define OMAP_INT_CAMERA 1 -# define OMAP_INT_FIQ 3 -# define OMAP_INT_RTDX 6 -# define OMAP_INT_DSP_MMU_ABORT 7 -# define OMAP_INT_HOST 8 -# define OMAP_INT_ABORT 9 -# define OMAP_INT_BRIDGE_PRIV 13 -# define OMAP_INT_GPIO_BANK1 14 -# define OMAP_INT_UART3 15 -# define OMAP_INT_TIMER3 16 -# define OMAP_INT_DMA_CH0_6 19 -# define OMAP_INT_DMA_CH1_7 20 -# define OMAP_INT_DMA_CH2_8 21 -# define OMAP_INT_DMA_CH3 22 -# define OMAP_INT_DMA_CH4 23 -# define OMAP_INT_DMA_CH5 24 -# define OMAP_INT_DMA_LCD 25 -# define OMAP_INT_TIMER1 26 -# define OMAP_INT_WD_TIMER 27 -# define OMAP_INT_BRIDGE_PUB 28 -# define OMAP_INT_TIMER2 30 -# define OMAP_INT_LCD_CTRL 31 +#define OMAP_INT_CAMERA 1 +#define OMAP_INT_FIQ 3 +#define OMAP_INT_RTDX 6 +#define OMAP_INT_DSP_MMU_ABORT 7 +#define OMAP_INT_HOST 8 +#define OMAP_INT_ABORT 9 +#define OMAP_INT_BRIDGE_PRIV 13 +#define OMAP_INT_GPIO_BANK1 14 +#define OMAP_INT_UART3 15 +#define OMAP_INT_TIMER3 16 +#define OMAP_INT_DMA_CH0_6 19 +#define OMAP_INT_DMA_CH1_7 20 +#define OMAP_INT_DMA_CH2_8 21 +#define OMAP_INT_DMA_CH3 22 +#define OMAP_INT_DMA_CH4 23 +#define OMAP_INT_DMA_CH5 24 +#define OMAP_INT_DMA_LCD 25 +#define OMAP_INT_TIMER1 26 +#define OMAP_INT_WD_TIMER 27 +#define OMAP_INT_BRIDGE_PUB 28 +#define OMAP_INT_TIMER2 30 +#define OMAP_INT_LCD_CTRL 31 /* * Common OMAP-15xx IRQ numbers for level 1 interrupt handler */ -# define OMAP_INT_15XX_IH2_IRQ 0 -# define OMAP_INT_15XX_LB_MMU 17 -# define OMAP_INT_15XX_LOCAL_BUS 29 +#define OMAP_INT_15XX_IH2_IRQ 0 +#define OMAP_INT_15XX_LB_MMU 17 +#define OMAP_INT_15XX_LOCAL_BUS 29 /* * OMAP-1510 specific IRQ numbers for level 1 interrupt handler */ -# define OMAP_INT_1510_SPI_TX 4 -# define OMAP_INT_1510_SPI_RX 5 -# define OMAP_INT_1510_DSP_MAILBOX1 10 -# define OMAP_INT_1510_DSP_MAILBOX2 11 +#define OMAP_INT_1510_SPI_TX 4 +#define OMAP_INT_1510_SPI_RX 5 +#define OMAP_INT_1510_DSP_MAILBOX1 10 +#define OMAP_INT_1510_DSP_MAILBOX2 11 /* * OMAP-310 specific IRQ numbers for level 1 interrupt handler */ -# define OMAP_INT_310_McBSP2_TX 4 -# define OMAP_INT_310_McBSP2_RX 5 -# define OMAP_INT_310_HSB_MAILBOX1 12 -# define OMAP_INT_310_HSAB_MMU 18 +#define OMAP_INT_310_McBSP2_TX 4 +#define OMAP_INT_310_McBSP2_RX 5 +#define OMAP_INT_310_HSB_MAILBOX1 12 +#define OMAP_INT_310_HSAB_MMU 18 /* * OMAP-1610 specific IRQ numbers for level 1 interrupt handler */ -# define OMAP_INT_1610_IH2_IRQ 0 -# define OMAP_INT_1610_IH2_FIQ 2 -# define OMAP_INT_1610_McBSP2_TX 4 -# define OMAP_INT_1610_McBSP2_RX 5 -# define OMAP_INT_1610_DSP_MAILBOX1 10 -# define OMAP_INT_1610_DSP_MAILBOX2 11 -# define OMAP_INT_1610_LCD_LINE 12 -# define OMAP_INT_1610_GPTIMER1 17 -# define OMAP_INT_1610_GPTIMER2 18 -# define OMAP_INT_1610_SSR_FIFO_0 29 +#define OMAP_INT_1610_IH2_IRQ 0 +#define OMAP_INT_1610_IH2_FIQ 2 +#define OMAP_INT_1610_McBSP2_TX 4 +#define OMAP_INT_1610_McBSP2_RX 5 +#define OMAP_INT_1610_DSP_MAILBOX1 10 +#define OMAP_INT_1610_DSP_MAILBOX2 11 +#define OMAP_INT_1610_LCD_LINE 12 +#define OMAP_INT_1610_GPTIMER1 17 +#define OMAP_INT_1610_GPTIMER2 18 +#define OMAP_INT_1610_SSR_FIFO_0 29 /* * OMAP-730 specific IRQ numbers for level 1 interrupt handler */ -# define OMAP_INT_730_IH2_FIQ 0 -# define OMAP_INT_730_IH2_IRQ 1 -# define OMAP_INT_730_USB_NON_ISO 2 -# define OMAP_INT_730_USB_ISO 3 -# define OMAP_INT_730_ICR 4 -# define OMAP_INT_730_EAC 5 -# define OMAP_INT_730_GPIO_BANK1 6 -# define OMAP_INT_730_GPIO_BANK2 7 -# define OMAP_INT_730_GPIO_BANK3 8 -# define OMAP_INT_730_McBSP2TX 10 -# define OMAP_INT_730_McBSP2RX 11 -# define OMAP_INT_730_McBSP2RX_OVF 12 -# define OMAP_INT_730_LCD_LINE 14 -# define OMAP_INT_730_GSM_PROTECT 15 -# define OMAP_INT_730_TIMER3 16 -# define OMAP_INT_730_GPIO_BANK5 17 -# define OMAP_INT_730_GPIO_BANK6 18 -# define OMAP_INT_730_SPGIO_WR 29 +#define OMAP_INT_730_IH2_FIQ 0 +#define OMAP_INT_730_IH2_IRQ 1 +#define OMAP_INT_730_USB_NON_ISO 2 +#define OMAP_INT_730_USB_ISO 3 +#define OMAP_INT_730_ICR 4 +#define OMAP_INT_730_EAC 5 +#define OMAP_INT_730_GPIO_BANK1 6 +#define OMAP_INT_730_GPIO_BANK2 7 +#define OMAP_INT_730_GPIO_BANK3 8 +#define OMAP_INT_730_McBSP2TX 10 +#define OMAP_INT_730_McBSP2RX 11 +#define OMAP_INT_730_McBSP2RX_OVF 12 +#define OMAP_INT_730_LCD_LINE 14 +#define OMAP_INT_730_GSM_PROTECT 15 +#define OMAP_INT_730_TIMER3 16 +#define OMAP_INT_730_GPIO_BANK5 17 +#define OMAP_INT_730_GPIO_BANK6 18 +#define OMAP_INT_730_SPGIO_WR 29 /* * Common IRQ numbers for level 2 interrupt handler */ -# define OMAP_INT_KEYBOARD 1 -# define OMAP_INT_uWireTX 2 -# define OMAP_INT_uWireRX 3 -# define OMAP_INT_I2C 4 -# define OMAP_INT_MPUIO 5 -# define OMAP_INT_USB_HHC_1 6 -# define OMAP_INT_McBSP3TX 10 -# define OMAP_INT_McBSP3RX 11 -# define OMAP_INT_McBSP1TX 12 -# define OMAP_INT_McBSP1RX 13 -# define OMAP_INT_UART1 14 -# define OMAP_INT_UART2 15 -# define OMAP_INT_USB_W2FC 20 -# define OMAP_INT_1WIRE 21 -# define OMAP_INT_OS_TIMER 22 -# define OMAP_INT_OQN 23 -# define OMAP_INT_GAUGE_32K 24 -# define OMAP_INT_RTC_TIMER 25 -# define OMAP_INT_RTC_ALARM 26 -# define OMAP_INT_DSP_MMU 28 +#define OMAP_INT_KEYBOARD 1 +#define OMAP_INT_uWireTX 2 +#define OMAP_INT_uWireRX 3 +#define OMAP_INT_I2C 4 +#define OMAP_INT_MPUIO 5 +#define OMAP_INT_USB_HHC_1 6 +#define OMAP_INT_McBSP3TX 10 +#define OMAP_INT_McBSP3RX 11 +#define OMAP_INT_McBSP1TX 12 +#define OMAP_INT_McBSP1RX 13 +#define OMAP_INT_UART1 14 +#define OMAP_INT_UART2 15 +#define OMAP_INT_USB_W2FC 20 +#define OMAP_INT_1WIRE 21 +#define OMAP_INT_OS_TIMER 22 +#define OMAP_INT_OQN 23 +#define OMAP_INT_GAUGE_32K 24 +#define OMAP_INT_RTC_TIMER 25 +#define OMAP_INT_RTC_ALARM 26 +#define OMAP_INT_DSP_MMU 28 /* * OMAP-1510 specific IRQ numbers for level 2 interrupt handler */ -# define OMAP_INT_1510_BT_MCSI1TX 16 -# define OMAP_INT_1510_BT_MCSI1RX 17 -# define OMAP_INT_1510_SoSSI_MATCH 19 -# define OMAP_INT_1510_MEM_STICK 27 -# define OMAP_INT_1510_COM_SPI_RO 31 +#define OMAP_INT_1510_BT_MCSI1TX 16 +#define OMAP_INT_1510_BT_MCSI1RX 17 +#define OMAP_INT_1510_SoSSI_MATCH 19 +#define OMAP_INT_1510_MEM_STICK 27 +#define OMAP_INT_1510_COM_SPI_RO 31 /* * OMAP-310 specific IRQ numbers for level 2 interrupt handler */ -# define OMAP_INT_310_FAC 0 -# define OMAP_INT_310_USB_HHC_2 7 -# define OMAP_INT_310_MCSI1_FE 16 -# define OMAP_INT_310_MCSI2_FE 17 -# define OMAP_INT_310_USB_W2FC_ISO 29 -# define OMAP_INT_310_USB_W2FC_NON_ISO 30 -# define OMAP_INT_310_McBSP2RX_OF 31 +#define OMAP_INT_310_FAC 0 +#define OMAP_INT_310_USB_HHC_2 7 +#define OMAP_INT_310_MCSI1_FE 16 +#define OMAP_INT_310_MCSI2_FE 17 +#define OMAP_INT_310_USB_W2FC_ISO 29 +#define OMAP_INT_310_USB_W2FC_NON_ISO 30 +#define OMAP_INT_310_McBSP2RX_OF 31 /* * OMAP-1610 specific IRQ numbers for level 2 interrupt handler */ -# define OMAP_INT_1610_FAC 0 -# define OMAP_INT_1610_USB_HHC_2 7 -# define OMAP_INT_1610_USB_OTG 8 -# define OMAP_INT_1610_SoSSI 9 -# define OMAP_INT_1610_BT_MCSI1TX 16 -# define OMAP_INT_1610_BT_MCSI1RX 17 -# define OMAP_INT_1610_SoSSI_MATCH 19 -# define OMAP_INT_1610_MEM_STICK 27 -# define OMAP_INT_1610_McBSP2RX_OF 31 -# define OMAP_INT_1610_STI 32 -# define OMAP_INT_1610_STI_WAKEUP 33 -# define OMAP_INT_1610_GPTIMER3 34 -# define OMAP_INT_1610_GPTIMER4 35 -# define OMAP_INT_1610_GPTIMER5 36 -# define OMAP_INT_1610_GPTIMER6 37 -# define OMAP_INT_1610_GPTIMER7 38 -# define OMAP_INT_1610_GPTIMER8 39 -# define OMAP_INT_1610_GPIO_BANK2 40 -# define OMAP_INT_1610_GPIO_BANK3 41 -# define OMAP_INT_1610_MMC2 42 -# define OMAP_INT_1610_CF 43 -# define OMAP_INT_1610_WAKE_UP_REQ 46 -# define OMAP_INT_1610_GPIO_BANK4 48 -# define OMAP_INT_1610_SPI 49 -# define OMAP_INT_1610_DMA_CH6 53 -# define OMAP_INT_1610_DMA_CH7 54 -# define OMAP_INT_1610_DMA_CH8 55 -# define OMAP_INT_1610_DMA_CH9 56 -# define OMAP_INT_1610_DMA_CH10 57 -# define OMAP_INT_1610_DMA_CH11 58 -# define OMAP_INT_1610_DMA_CH12 59 -# define OMAP_INT_1610_DMA_CH13 60 -# define OMAP_INT_1610_DMA_CH14 61 -# define OMAP_INT_1610_DMA_CH15 62 -# define OMAP_INT_1610_NAND 63 +#define OMAP_INT_1610_FAC 0 +#define OMAP_INT_1610_USB_HHC_2 7 +#define OMAP_INT_1610_USB_OTG 8 +#define OMAP_INT_1610_SoSSI 9 +#define OMAP_INT_1610_BT_MCSI1TX 16 +#define OMAP_INT_1610_BT_MCSI1RX 17 +#define OMAP_INT_1610_SoSSI_MATCH 19 +#define OMAP_INT_1610_MEM_STICK 27 +#define OMAP_INT_1610_McBSP2RX_OF 31 +#define OMAP_INT_1610_STI 32 +#define OMAP_INT_1610_STI_WAKEUP 33 +#define OMAP_INT_1610_GPTIMER3 34 +#define OMAP_INT_1610_GPTIMER4 35 +#define OMAP_INT_1610_GPTIMER5 36 +#define OMAP_INT_1610_GPTIMER6 37 +#define OMAP_INT_1610_GPTIMER7 38 +#define OMAP_INT_1610_GPTIMER8 39 +#define OMAP_INT_1610_GPIO_BANK2 40 +#define OMAP_INT_1610_GPIO_BANK3 41 +#define OMAP_INT_1610_MMC2 42 +#define OMAP_INT_1610_CF 43 +#define OMAP_INT_1610_WAKE_UP_REQ 46 +#define OMAP_INT_1610_GPIO_BANK4 48 +#define OMAP_INT_1610_SPI 49 +#define OMAP_INT_1610_DMA_CH6 53 +#define OMAP_INT_1610_DMA_CH7 54 +#define OMAP_INT_1610_DMA_CH8 55 +#define OMAP_INT_1610_DMA_CH9 56 +#define OMAP_INT_1610_DMA_CH10 57 +#define OMAP_INT_1610_DMA_CH11 58 +#define OMAP_INT_1610_DMA_CH12 59 +#define OMAP_INT_1610_DMA_CH13 60 +#define OMAP_INT_1610_DMA_CH14 61 +#define OMAP_INT_1610_DMA_CH15 62 +#define OMAP_INT_1610_NAND 63 /* * OMAP-730 specific IRQ numbers for level 2 interrupt handler */ -# define OMAP_INT_730_HW_ERRORS 0 -# define OMAP_INT_730_NFIQ_PWR_FAIL 1 -# define OMAP_INT_730_CFCD 2 -# define OMAP_INT_730_CFIREQ 3 -# define OMAP_INT_730_I2C 4 -# define OMAP_INT_730_PCC 5 -# define OMAP_INT_730_MPU_EXT_NIRQ 6 -# define OMAP_INT_730_SPI_100K_1 7 -# define OMAP_INT_730_SYREN_SPI 8 -# define OMAP_INT_730_VLYNQ 9 -# define OMAP_INT_730_GPIO_BANK4 10 -# define OMAP_INT_730_McBSP1TX 11 -# define OMAP_INT_730_McBSP1RX 12 -# define OMAP_INT_730_McBSP1RX_OF 13 -# define OMAP_INT_730_UART_MODEM_IRDA_2 14 -# define OMAP_INT_730_UART_MODEM_1 15 -# define OMAP_INT_730_MCSI 16 -# define OMAP_INT_730_uWireTX 17 -# define OMAP_INT_730_uWireRX 18 -# define OMAP_INT_730_SMC_CD 19 -# define OMAP_INT_730_SMC_IREQ 20 -# define OMAP_INT_730_HDQ_1WIRE 21 -# define OMAP_INT_730_TIMER32K 22 -# define OMAP_INT_730_MMC_SDIO 23 -# define OMAP_INT_730_UPLD 24 -# define OMAP_INT_730_USB_HHC_1 27 -# define OMAP_INT_730_USB_HHC_2 28 -# define OMAP_INT_730_USB_GENI 29 -# define OMAP_INT_730_USB_OTG 30 -# define OMAP_INT_730_CAMERA_IF 31 -# define OMAP_INT_730_RNG 32 -# define OMAP_INT_730_DUAL_MODE_TIMER 33 -# define OMAP_INT_730_DBB_RF_EN 34 -# define OMAP_INT_730_MPUIO_KEYPAD 35 -# define OMAP_INT_730_SHA1_MD5 36 -# define OMAP_INT_730_SPI_100K_2 37 -# define OMAP_INT_730_RNG_IDLE 38 -# define OMAP_INT_730_MPUIO 39 -# define OMAP_INT_730_LLPC_LCD_CTRL_OFF 40 -# define OMAP_INT_730_LLPC_OE_FALLING 41 -# define OMAP_INT_730_LLPC_OE_RISING 42 -# define OMAP_INT_730_LLPC_VSYNC 43 -# define OMAP_INT_730_WAKE_UP_REQ 46 -# define OMAP_INT_730_DMA_CH6 53 -# define OMAP_INT_730_DMA_CH7 54 -# define OMAP_INT_730_DMA_CH8 55 -# define OMAP_INT_730_DMA_CH9 56 -# define OMAP_INT_730_DMA_CH10 57 -# define OMAP_INT_730_DMA_CH11 58 -# define OMAP_INT_730_DMA_CH12 59 -# define OMAP_INT_730_DMA_CH13 60 -# define OMAP_INT_730_DMA_CH14 61 -# define OMAP_INT_730_DMA_CH15 62 -# define OMAP_INT_730_NAND 63 +#define OMAP_INT_730_HW_ERRORS 0 +#define OMAP_INT_730_NFIQ_PWR_FAIL 1 +#define OMAP_INT_730_CFCD 2 +#define OMAP_INT_730_CFIREQ 3 +#define OMAP_INT_730_I2C 4 +#define OMAP_INT_730_PCC 5 +#define OMAP_INT_730_MPU_EXT_NIRQ 6 +#define OMAP_INT_730_SPI_100K_1 7 +#define OMAP_INT_730_SYREN_SPI 8 +#define OMAP_INT_730_VLYNQ 9 +#define OMAP_INT_730_GPIO_BANK4 10 +#define OMAP_INT_730_McBSP1TX 11 +#define OMAP_INT_730_McBSP1RX 12 +#define OMAP_INT_730_McBSP1RX_OF 13 +#define OMAP_INT_730_UART_MODEM_IRDA_2 14 +#define OMAP_INT_730_UART_MODEM_1 15 +#define OMAP_INT_730_MCSI 16 +#define OMAP_INT_730_uWireTX 17 +#define OMAP_INT_730_uWireRX 18 +#define OMAP_INT_730_SMC_CD 19 +#define OMAP_INT_730_SMC_IREQ 20 +#define OMAP_INT_730_HDQ_1WIRE 21 +#define OMAP_INT_730_TIMER32K 22 +#define OMAP_INT_730_MMC_SDIO 23 +#define OMAP_INT_730_UPLD 24 +#define OMAP_INT_730_USB_HHC_1 27 +#define OMAP_INT_730_USB_HHC_2 28 +#define OMAP_INT_730_USB_GENI 29 +#define OMAP_INT_730_USB_OTG 30 +#define OMAP_INT_730_CAMERA_IF 31 +#define OMAP_INT_730_RNG 32 +#define OMAP_INT_730_DUAL_MODE_TIMER 33 +#define OMAP_INT_730_DBB_RF_EN 34 +#define OMAP_INT_730_MPUIO_KEYPAD 35 +#define OMAP_INT_730_SHA1_MD5 36 +#define OMAP_INT_730_SPI_100K_2 37 +#define OMAP_INT_730_RNG_IDLE 38 +#define OMAP_INT_730_MPUIO 39 +#define OMAP_INT_730_LLPC_LCD_CTRL_OFF 40 +#define OMAP_INT_730_LLPC_OE_FALLING 41 +#define OMAP_INT_730_LLPC_OE_RISING 42 +#define OMAP_INT_730_LLPC_VSYNC 43 +#define OMAP_INT_730_WAKE_UP_REQ 46 +#define OMAP_INT_730_DMA_CH6 53 +#define OMAP_INT_730_DMA_CH7 54 +#define OMAP_INT_730_DMA_CH8 55 +#define OMAP_INT_730_DMA_CH9 56 +#define OMAP_INT_730_DMA_CH10 57 +#define OMAP_INT_730_DMA_CH11 58 +#define OMAP_INT_730_DMA_CH12 59 +#define OMAP_INT_730_DMA_CH13 60 +#define OMAP_INT_730_DMA_CH14 61 +#define OMAP_INT_730_DMA_CH15 62 +#define OMAP_INT_730_NAND 63 /* omap_dma.c */ enum omap_dma_model { @@ -353,9 +353,9 @@ struct dma_irq_map { enum omap_dma_port { emiff = 0, emifs, - imif, /* omap16xx: ocp_t1 */ + imif, /* omap16xx: ocp_t1 */ tipb, - local, /* omap16xx: ocp_t2 */ + local, /* omap16xx: ocp_t2 */ tipb_mpui, __omap_dma_port_last, }; @@ -418,65 +418,65 @@ struct omap_dma_lcd_channel_s { * DMA request numbers for OMAP1 * See /usr/include/asm-arm/arch-omap/dma.h in Linux. */ -# define OMAP_DMA_NO_DEVICE 0 -# define OMAP_DMA_MCSI1_TX 1 -# define OMAP_DMA_MCSI1_RX 2 -# define OMAP_DMA_I2C_RX 3 -# define OMAP_DMA_I2C_TX 4 -# define OMAP_DMA_EXT_NDMA_REQ0 5 -# define OMAP_DMA_EXT_NDMA_REQ1 6 -# define OMAP_DMA_UWIRE_TX 7 -# define OMAP_DMA_MCBSP1_TX 8 -# define OMAP_DMA_MCBSP1_RX 9 -# define OMAP_DMA_MCBSP3_TX 10 -# define OMAP_DMA_MCBSP3_RX 11 -# define OMAP_DMA_UART1_TX 12 -# define OMAP_DMA_UART1_RX 13 -# define OMAP_DMA_UART2_TX 14 -# define OMAP_DMA_UART2_RX 15 -# define OMAP_DMA_MCBSP2_TX 16 -# define OMAP_DMA_MCBSP2_RX 17 -# define OMAP_DMA_UART3_TX 18 -# define OMAP_DMA_UART3_RX 19 -# define OMAP_DMA_CAMERA_IF_RX 20 -# define OMAP_DMA_MMC_TX 21 -# define OMAP_DMA_MMC_RX 22 -# define OMAP_DMA_NAND 23 /* Not in OMAP310 */ -# define OMAP_DMA_IRQ_LCD_LINE 24 /* Not in OMAP310 */ -# define OMAP_DMA_MEMORY_STICK 25 /* Not in OMAP310 */ -# define OMAP_DMA_USB_W2FC_RX0 26 -# define OMAP_DMA_USB_W2FC_RX1 27 -# define OMAP_DMA_USB_W2FC_RX2 28 -# define OMAP_DMA_USB_W2FC_TX0 29 -# define OMAP_DMA_USB_W2FC_TX1 30 -# define OMAP_DMA_USB_W2FC_TX2 31 +#define OMAP_DMA_NO_DEVICE 0 +#define OMAP_DMA_MCSI1_TX 1 +#define OMAP_DMA_MCSI1_RX 2 +#define OMAP_DMA_I2C_RX 3 +#define OMAP_DMA_I2C_TX 4 +#define OMAP_DMA_EXT_NDMA_REQ0 5 +#define OMAP_DMA_EXT_NDMA_REQ1 6 +#define OMAP_DMA_UWIRE_TX 7 +#define OMAP_DMA_MCBSP1_TX 8 +#define OMAP_DMA_MCBSP1_RX 9 +#define OMAP_DMA_MCBSP3_TX 10 +#define OMAP_DMA_MCBSP3_RX 11 +#define OMAP_DMA_UART1_TX 12 +#define OMAP_DMA_UART1_RX 13 +#define OMAP_DMA_UART2_TX 14 +#define OMAP_DMA_UART2_RX 15 +#define OMAP_DMA_MCBSP2_TX 16 +#define OMAP_DMA_MCBSP2_RX 17 +#define OMAP_DMA_UART3_TX 18 +#define OMAP_DMA_UART3_RX 19 +#define OMAP_DMA_CAMERA_IF_RX 20 +#define OMAP_DMA_MMC_TX 21 +#define OMAP_DMA_MMC_RX 22 +#define OMAP_DMA_NAND 23 /* Not in OMAP310 */ +#define OMAP_DMA_IRQ_LCD_LINE 24 /* Not in OMAP310 */ +#define OMAP_DMA_MEMORY_STICK 25 /* Not in OMAP310 */ +#define OMAP_DMA_USB_W2FC_RX0 26 +#define OMAP_DMA_USB_W2FC_RX1 27 +#define OMAP_DMA_USB_W2FC_RX2 28 +#define OMAP_DMA_USB_W2FC_TX0 29 +#define OMAP_DMA_USB_W2FC_TX1 30 +#define OMAP_DMA_USB_W2FC_TX2 31 /* These are only for 1610 */ -# define OMAP_DMA_CRYPTO_DES_IN 32 -# define OMAP_DMA_SPI_TX 33 -# define OMAP_DMA_SPI_RX 34 -# define OMAP_DMA_CRYPTO_HASH 35 -# define OMAP_DMA_CCP_ATTN 36 -# define OMAP_DMA_CCP_FIFO_NOT_EMPTY 37 -# define OMAP_DMA_CMT_APE_TX_CHAN_0 38 -# define OMAP_DMA_CMT_APE_RV_CHAN_0 39 -# define OMAP_DMA_CMT_APE_TX_CHAN_1 40 -# define OMAP_DMA_CMT_APE_RV_CHAN_1 41 -# define OMAP_DMA_CMT_APE_TX_CHAN_2 42 -# define OMAP_DMA_CMT_APE_RV_CHAN_2 43 -# define OMAP_DMA_CMT_APE_TX_CHAN_3 44 -# define OMAP_DMA_CMT_APE_RV_CHAN_3 45 -# define OMAP_DMA_CMT_APE_TX_CHAN_4 46 -# define OMAP_DMA_CMT_APE_RV_CHAN_4 47 -# define OMAP_DMA_CMT_APE_TX_CHAN_5 48 -# define OMAP_DMA_CMT_APE_RV_CHAN_5 49 -# define OMAP_DMA_CMT_APE_TX_CHAN_6 50 -# define OMAP_DMA_CMT_APE_RV_CHAN_6 51 -# define OMAP_DMA_CMT_APE_TX_CHAN_7 52 -# define OMAP_DMA_CMT_APE_RV_CHAN_7 53 -# define OMAP_DMA_MMC2_TX 54 -# define OMAP_DMA_MMC2_RX 55 -# define OMAP_DMA_CRYPTO_DES_OUT 56 +#define OMAP_DMA_CRYPTO_DES_IN 32 +#define OMAP_DMA_SPI_TX 33 +#define OMAP_DMA_SPI_RX 34 +#define OMAP_DMA_CRYPTO_HASH 35 +#define OMAP_DMA_CCP_ATTN 36 +#define OMAP_DMA_CCP_FIFO_NOT_EMPTY 37 +#define OMAP_DMA_CMT_APE_TX_CHAN_0 38 +#define OMAP_DMA_CMT_APE_RV_CHAN_0 39 +#define OMAP_DMA_CMT_APE_TX_CHAN_1 40 +#define OMAP_DMA_CMT_APE_RV_CHAN_1 41 +#define OMAP_DMA_CMT_APE_TX_CHAN_2 42 +#define OMAP_DMA_CMT_APE_RV_CHAN_2 43 +#define OMAP_DMA_CMT_APE_TX_CHAN_3 44 +#define OMAP_DMA_CMT_APE_RV_CHAN_3 45 +#define OMAP_DMA_CMT_APE_TX_CHAN_4 46 +#define OMAP_DMA_CMT_APE_RV_CHAN_4 47 +#define OMAP_DMA_CMT_APE_TX_CHAN_5 48 +#define OMAP_DMA_CMT_APE_RV_CHAN_5 49 +#define OMAP_DMA_CMT_APE_TX_CHAN_6 50 +#define OMAP_DMA_CMT_APE_RV_CHAN_6 51 +#define OMAP_DMA_CMT_APE_TX_CHAN_7 52 +#define OMAP_DMA_CMT_APE_RV_CHAN_7 53 +#define OMAP_DMA_MMC2_TX 54 +#define OMAP_DMA_MMC2_RX 55 +#define OMAP_DMA_CRYPTO_DES_OUT 56 struct omap_uart_s; struct omap_uart_s *omap_uart_init(hwaddr base, @@ -542,14 +542,14 @@ void omap_mmc_set_clk(DeviceState *dev, omap_clk clk); /* omap_i2c.c */ I2CBus *omap_i2c_bus(DeviceState *omap_i2c); -# define cpu_is_omap310(cpu) (cpu->mpu_model == omap310) -# define cpu_is_omap1510(cpu) (cpu->mpu_model == omap1510) -# define cpu_is_omap1610(cpu) (cpu->mpu_model == omap1610) -# define cpu_is_omap1710(cpu) (cpu->mpu_model == omap1710) +#define cpu_is_omap310(cpu) (cpu->mpu_model == omap310) +#define cpu_is_omap1510(cpu) (cpu->mpu_model == omap1510) +#define cpu_is_omap1610(cpu) (cpu->mpu_model == omap1610) +#define cpu_is_omap1710(cpu) (cpu->mpu_model == omap1710) -# define cpu_is_omap15xx(cpu) \ +#define cpu_is_omap15xx(cpu) \ (cpu_is_omap310(cpu) || cpu_is_omap1510(cpu)) -# define cpu_is_omap16xx(cpu) \ +#define cpu_is_omap16xx(cpu) \ (cpu_is_omap1610(cpu) || cpu_is_omap1710(cpu)) struct omap_mpu_state_s { @@ -685,14 +685,14 @@ void omap_badwidth_write32(void *opaque, hwaddr addr, void omap_mpu_wakeup(void *opaque, int irq, int req); -# define OMAP_BAD_REG(paddr) \ +#define OMAP_BAD_REG(paddr) \ qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad register %#08"HWADDR_PRIx"\n", \ __func__, paddr) -# define OMAP_RO_REG(paddr) \ +#define OMAP_RO_REG(paddr) \ qemu_log_mask(LOG_GUEST_ERROR, "%s: Read-only register %#08" \ HWADDR_PRIx "\n", \ __func__, paddr) -# define OMAP_MPUI_REG_MASK 0x000007ff +#define OMAP_MPUI_REG_MASK 0x000007ff #endif diff --git a/include/hw/arm/sharpsl.h b/include/hw/arm/sharpsl.h deleted file mode 100644 index e986b28..0000000 --- a/include/hw/arm/sharpsl.h +++ /dev/null @@ -1,17 +0,0 @@ -/* - * Common declarations for the Zaurii. - * - * This file is licensed under the GNU GPL. - */ - -#ifndef QEMU_SHARPSL_H -#define QEMU_SHARPSL_H - -#include "exec/hwaddr.h" - -/* zaurus.c */ - -#define SL_PXA_PARAM_BASE 0xa0000a00 -void sl_bootparam_write(hwaddr ptr); - -#endif diff --git a/include/hw/arm/smmu-common.h b/include/hw/arm/smmu-common.h index e5e2d09..80d0fec 100644 --- a/include/hw/arm/smmu-common.h +++ b/include/hw/arm/smmu-common.h @@ -161,6 +161,7 @@ struct SMMUState { QLIST_HEAD(, SMMUDevice) devices_with_notifiers; uint8_t bus_num; PCIBus *primary_bus; + bool smmu_per_bus; /* SMMU is specific to the primary_bus */ }; struct SMMUBaseClass { diff --git a/include/hw/arm/soc_dma.h b/include/hw/arm/soc_dma.h index e93a749..bcdb914 100644 --- a/include/hw/arm/soc_dma.h +++ b/include/hw/arm/soc_dma.h @@ -54,7 +54,7 @@ struct soc_dma_ch_s { int bytes; /* Initialised by the DMA module, call soc_dma_ch_update after writing. */ enum soc_dma_access_type type[2]; - hwaddr vaddr[2]; /* Updated by .transfer_fn(). */ + hwaddr vaddr[2]; /* Updated by .transfer_fn(). */ /* Private */ void *paddr[2]; soc_dma_io_t io_fn[2]; @@ -70,7 +70,7 @@ struct soc_dma_ch_s { struct soc_dma_s { /* Following fields are set by the SoC DMA module and can be used * by anybody. */ - uint64_t drqbmp; /* Is zeroed by soc_dma_reset() */ + uint64_t drqbmp; /* Is zeroed by soc_dma_reset() */ qemu_irq *drq; void *opaque; int64_t freq; diff --git a/include/hw/arm/stm32f205_soc.h b/include/hw/arm/stm32f205_soc.h index 4f4c8bb..46eda34 100644 --- a/include/hw/arm/stm32f205_soc.h +++ b/include/hw/arm/stm32f205_soc.h @@ -59,7 +59,7 @@ struct STM32F205State { STM32F2XXADCState adc[STM_NUM_ADCS]; STM32F2XXSPIState spi[STM_NUM_SPIS]; - OrIRQState *adc_irqs; + OrIRQState adc_irqs; MemoryRegion sram; MemoryRegion flash; diff --git a/include/hw/arm/stm32l4x5_soc.h b/include/hw/arm/stm32l4x5_soc.h index c243fb0..c2fae6e 100644 --- a/include/hw/arm/stm32l4x5_soc.h +++ b/include/hw/arm/stm32l4x5_soc.h @@ -24,7 +24,7 @@ #ifndef HW_ARM_STM32L4x5_SOC_H #define HW_ARM_STM32L4x5_SOC_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/arm/armv7m.h" #include "hw/or-irq.h" #include "hw/misc/stm32l4x5_syscfg.h" diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h index c8e94e6..c77a33f 100644 --- a/include/hw/arm/virt.h +++ b/include/hw/arm/virt.h @@ -33,9 +33,11 @@ #include "exec/hwaddr.h" #include "qemu/notify.h" #include "hw/boards.h" +#include "hw/acpi/ghes.h" #include "hw/arm/boot.h" #include "hw/arm/bsa.h" #include "hw/block/flash.h" +#include "hw/cxl/cxl.h" #include "system/kvm.h" #include "hw/intc/arm_gicv3_common.h" #include "qom/object.h" @@ -79,12 +81,14 @@ enum { VIRT_ACPI_GED, VIRT_NVDIMM_ACPI, VIRT_PVTIME, + VIRT_ACPI_PCIHP, VIRT_LOWMEMMAP_LAST, }; /* indices of IO regions located after the RAM */ enum { VIRT_HIGH_GIC_REDIST2 = VIRT_LOWMEMMAP_LAST, + VIRT_CXL_HOST, VIRT_HIGH_PCIE_ECAM, VIRT_HIGH_PCIE_MMIO, }; @@ -117,16 +121,8 @@ typedef enum VirtGICType { struct VirtMachineClass { MachineClass parent; - bool disallow_affinity_adjustment; - bool no_its; bool no_tcg_its; - bool no_pmu; - bool claim_edge_triggered_timers; - bool smbios_old_sys_ver; bool no_highmem_compact; - bool no_highmem_ecam; - bool no_ged; /* Machines < 4.2 have no support for ACPI GED device */ - bool kvm_no_adjvtime; bool no_kvm_steal_time; bool acpi_expose_flash; bool no_secure_gpio; @@ -146,6 +142,7 @@ struct VirtMachineState { bool secure; bool highmem; bool highmem_compact; + bool highmem_cxl; bool highmem_ecam; bool highmem_mmio; bool highmem_redists; @@ -176,10 +173,13 @@ struct VirtMachineState { DeviceState *gic; DeviceState *acpi_dev; Notifier powerdown_notifier; + Notifier generic_error_notifier; PCIBus *bus; char *oem_id; char *oem_table_id; bool ns_el2_virt_timer_irq; + CXLState cxl_devices_state; + bool legacy_smmuv3_present; }; #define VIRT_ECAM_ID(high) (high ? VIRT_HIGH_PCIE_ECAM : VIRT_PCIE_ECAM) diff --git a/include/hw/arm/xen_arch_hvm.h b/include/hw/arm/xen_arch_hvm.h deleted file mode 100644 index 8fd645e..0000000 --- a/include/hw/arm/xen_arch_hvm.h +++ /dev/null @@ -1,9 +0,0 @@ -#ifndef HW_XEN_ARCH_ARM_HVM_H -#define HW_XEN_ARCH_ARM_HVM_H - -#include <xen/hvm/ioreq.h> -void arch_handle_ioreq(XenIOState *state, ioreq_t *req); -void arch_xen_set_memory(XenIOState *state, - MemoryRegionSection *section, - bool add); -#endif diff --git a/include/hw/arm/xlnx-versal-version.h b/include/hw/arm/xlnx-versal-version.h new file mode 100644 index 0000000..5b6b6e5 --- /dev/null +++ b/include/hw/arm/xlnx-versal-version.h @@ -0,0 +1,16 @@ +/* + * AMD Versal versions + * + * Copyright (c) 2025 Advanced Micro Devices, Inc. + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_ARM_XLNX_VERSAL_VERSION_H +#define HW_ARM_XLNX_VERSAL_VERSION_H + +typedef enum VersalVersion { + VERSAL_VER_VERSAL, + VERSAL_VER_VERSAL2, +} VersalVersion; + +#endif diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h index 05ed641..e1fb1f4 100644 --- a/include/hw/arm/xlnx-versal.h +++ b/include/hw/arm/xlnx-versal.h @@ -1,7 +1,8 @@ /* - * Model of the Xilinx Versal + * AMD/Xilinx Versal family SoC model. * * Copyright (c) 2018 Xilinx Inc. + * Copyright (c) 2025 Advanced Micro Devices, Inc. * Written by Edgar E. Iglesias * * This program is free software; you can redistribute it and/or modify @@ -13,326 +14,77 @@ #define XLNX_VERSAL_H #include "hw/sysbus.h" -#include "hw/cpu/cluster.h" -#include "hw/or-irq.h" -#include "hw/sd/sdhci.h" -#include "hw/intc/arm_gicv3.h" -#include "hw/char/pl011.h" -#include "hw/dma/xlnx-zdma.h" -#include "hw/net/cadence_gem.h" -#include "hw/rtc/xlnx-zynqmp-rtc.h" #include "qom/object.h" -#include "hw/usb/xlnx-usb-subsystem.h" -#include "hw/misc/xlnx-versal-xramc.h" -#include "hw/nvram/xlnx-bbram.h" -#include "hw/nvram/xlnx-versal-efuse.h" -#include "hw/ssi/xlnx-versal-ospi.h" -#include "hw/dma/xlnx_csu_dma.h" -#include "hw/misc/xlnx-versal-crl.h" -#include "hw/misc/xlnx-versal-pmc-iou-slcr.h" -#include "hw/misc/xlnx-versal-trng.h" -#include "hw/net/xlnx-versal-canfd.h" -#include "hw/misc/xlnx-versal-cfu.h" -#include "hw/misc/xlnx-versal-cframe-reg.h" -#include "target/arm/cpu.h" +#include "net/can_emu.h" +#include "hw/arm/xlnx-versal-version.h" -#define TYPE_XLNX_VERSAL "xlnx-versal" -OBJECT_DECLARE_SIMPLE_TYPE(Versal, XLNX_VERSAL) +#define TYPE_XLNX_VERSAL_BASE "xlnx-versal-base" +OBJECT_DECLARE_TYPE(Versal, VersalClass, XLNX_VERSAL_BASE) -#define XLNX_VERSAL_NR_ACPUS 2 -#define XLNX_VERSAL_NR_RCPUS 2 -#define XLNX_VERSAL_NR_UARTS 2 -#define XLNX_VERSAL_NR_GEMS 2 -#define XLNX_VERSAL_NR_ADMAS 8 -#define XLNX_VERSAL_NR_SDS 2 -#define XLNX_VERSAL_NR_XRAM 4 -#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 +#define TYPE_XLNX_VERSAL "xlnx-versal" +#define TYPE_XLNX_VERSAL2 "xlnx-versal2" struct Versal { /*< private >*/ SysBusDevice parent_obj; /*< public >*/ - struct { - struct { - MemoryRegion mr; - CPUClusterState cluster; - ARMCPU cpu[XLNX_VERSAL_NR_ACPUS]; - GICv3State gic; - } apu; - } fpd; - + GArray *intc; MemoryRegion mr_ps; struct { - /* 4 ranges to access DDR. */ - MemoryRegion mr_ddr_ranges[4]; - } noc; - - struct { - MemoryRegion mr_ocm; - - struct { - PL011State uart[XLNX_VERSAL_NR_UARTS]; - CadenceGEMState gem[XLNX_VERSAL_NR_GEMS]; - OrIRQState gem_irq_orgate[XLNX_VERSAL_NR_GEMS]; - XlnxZDMA adma[XLNX_VERSAL_NR_ADMAS]; - VersalUsb2 usb; - CanBusState *canbus[XLNX_VERSAL_NR_CANFD]; - XlnxVersalCANFDState canfd[XLNX_VERSAL_NR_CANFD]; - } iou; - - /* Real-time Processing Unit. */ - struct { - MemoryRegion mr; - MemoryRegion mr_ps_alias; - - CPUClusterState cluster; - ARMCPU cpu[XLNX_VERSAL_NR_RCPUS]; - } rpu; - - struct { - OrIRQState irq_orgate; - XlnxXramCtrl ctrl[XLNX_VERSAL_NR_XRAM]; - } xram; - - XlnxVersalCRL crl; - } lpd; - - /* The Platform Management Controller subsystem. */ - struct { - struct { - SDHCIState sd[XLNX_VERSAL_NR_SDS]; - XlnxVersalPmcIouSlcr slcr; - - struct { - XlnxVersalOspi ospi; - XlnxCSUDMA dma_src; - XlnxCSUDMA dma_dst; - MemoryRegion linear_mr; - OrIRQState irq_orgate; - } ospi; - } iou; - - XlnxZynqMPRTC rtc; - XlnxVersalTRng trng; - XlnxBBRam bbram; - XlnxEFuse efuse; - XlnxVersalEFuseCtrl efuse_ctrl; - XlnxVersalEFuseCache efuse_cache; - XlnxVersalCFUAPB cfu_apb; - XlnxVersalCFUFDRO cfu_fdro; - XlnxVersalCFUSFR cfu_sfr; - XlnxVersalCFrameReg cframe[XLNX_VERSAL_NR_CFRAME]; - XlnxVersalCFrameBcastReg cframe_bcast; - - OrIRQState apb_irq_orgate; - } pmc; + uint32_t clk_25mhz; + uint32_t clk_125mhz; + uint32_t gic; + } phandle; struct { MemoryRegion *mr_ddr; + CanBusState **canbus; + void *fdt; } cfg; }; -/* Memory-map and IRQ definitions. Copied a subset from - * auto-generated files. */ - -#define VERSAL_GIC_MAINT_IRQ 9 -#define VERSAL_TIMER_VIRT_IRQ 11 -#define VERSAL_TIMER_S_EL1_IRQ 13 -#define VERSAL_TIMER_NS_EL1_IRQ 14 -#define VERSAL_TIMER_NS_EL2_IRQ 10 - -#define VERSAL_CRL_IRQ 10 -#define VERSAL_UART0_IRQ_0 18 -#define VERSAL_UART1_IRQ_0 19 -#define VERSAL_CANFD0_IRQ_0 20 -#define VERSAL_CANFD1_IRQ_0 21 -#define VERSAL_USB0_IRQ_0 22 -#define VERSAL_GEM0_IRQ_0 56 -#define VERSAL_GEM0_WAKE_IRQ_0 57 -#define VERSAL_GEM1_IRQ_0 58 -#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 -#define VERSAL_EFUSE_IRQ 139 -#define VERSAL_TRNG_IRQ 141 -#define VERSAL_RTC_ALARM_IRQ 142 -#define VERSAL_RTC_SECONDS_IRQ 143 - -/* Architecturally reserved IRQs suitable for virtualization. */ -#define VERSAL_RSVD_IRQ_FIRST 111 -#define VERSAL_RSVD_IRQ_LAST 118 - -#define MM_TOP_RSVD 0xa0000000U -#define MM_TOP_RSVD_SIZE 0x4000000 -#define MM_GIC_APU_DIST_MAIN 0xf9000000U -#define MM_GIC_APU_DIST_MAIN_SIZE 0x10000 -#define MM_GIC_APU_REDIST_0 0xf9080000U -#define MM_GIC_APU_REDIST_0_SIZE 0x80000 - -#define MM_UART0 0xff000000U -#define MM_UART0_SIZE 0x10000 -#define MM_UART1 0xff010000U -#define MM_UART1_SIZE 0x10000 - -#define MM_CANFD0 0xff060000U -#define MM_CANFD0_SIZE 0x10000 -#define MM_CANFD1 0xff070000U -#define MM_CANFD1_SIZE 0x10000 - -#define MM_GEM0 0xff0c0000U -#define MM_GEM0_SIZE 0x10000 -#define MM_GEM1 0xff0d0000U -#define MM_GEM1_SIZE 0x10000 +struct VersalClass { + SysBusDeviceClass parent; -#define MM_ADMA_CH0 0xffa80000U -#define MM_ADMA_CH0_SIZE 0x10000 - -#define MM_OCM 0xfffc0000U -#define MM_OCM_SIZE 0x40000 - -#define MM_XRAM 0xfe800000 -#define MM_XRAMC 0xff8e0000 -#define MM_XRAMC_SIZE 0x10000 - -#define MM_USB2_CTRL_REGS 0xFF9D0000 -#define MM_USB2_CTRL_REGS_SIZE 0x10000 - -#define MM_USB_0 0xFE200000 -#define MM_USB_0_SIZE 0x10000 - -#define MM_TOP_DDR 0x0 -#define MM_TOP_DDR_SIZE 0x80000000U -#define MM_TOP_DDR_2 0x800000000ULL -#define MM_TOP_DDR_2_SIZE 0x800000000ULL -#define MM_TOP_DDR_3 0xc000000000ULL -#define MM_TOP_DDR_3_SIZE 0x4000000000ULL -#define MM_TOP_DDR_4 0x10000000000ULL -#define MM_TOP_DDR_4_SIZE 0xb780000000ULL - -#define MM_PSM_START 0xffc80000U -#define MM_PSM_END 0xffcf0000U + VersalVersion version; +}; -#define MM_CRL 0xff5e0000U -#define MM_CRL_SIZE 0x300000 -#define MM_IOU_SCNTR 0xff130000U -#define MM_IOU_SCNTR_SIZE 0x10000 -#define MM_IOU_SCNTRS 0xff140000U -#define MM_IOU_SCNTRS_SIZE 0x10000 -#define MM_FPD_CRF 0xfd1a0000U -#define MM_FPD_CRF_SIZE 0x140000 -#define MM_FPD_FPD_APU 0xfd5c0000 -#define MM_FPD_FPD_APU_SIZE 0x100 +static inline void versal_set_fdt(Versal *s, void *fdt) +{ + g_assert(!qdev_is_realized(DEVICE(s))); + s->cfg.fdt = fdt; +} -#define MM_PMC_PMC_IOU_SLCR 0xf1060000 -#define MM_PMC_PMC_IOU_SLCR_SIZE 0x10000 +void versal_fdt_add_memory_nodes(Versal *s, uint64_t ram_size); -#define MM_PMC_OSPI 0xf1010000 -#define MM_PMC_OSPI_SIZE 0x10000 +DeviceState *versal_get_boot_cpu(Versal *s); +void versal_sdhci_plug_card(Versal *s, int sd_idx, BlockBackend *blk); +void versal_efuse_attach_drive(Versal *s, BlockBackend *blk); +void versal_bbram_attach_drive(Versal *s, BlockBackend *blk); +void versal_ospi_create_flash(Versal *s, int flash_idx, const char *flash_mdl, + BlockBackend *blk); -#define MM_PMC_OSPI_DAC 0xc0000000 -#define MM_PMC_OSPI_DAC_SIZE 0x20000000 +qemu_irq versal_get_reserved_irq(Versal *s, int idx, int *dtb_idx); +hwaddr versal_get_reserved_mmio_addr(Versal *s); -#define MM_PMC_OSPI_DMA_DST 0xf1011800 -#define MM_PMC_OSPI_DMA_SRC 0xf1011000 +int versal_get_num_cpu(VersalVersion version); +int versal_get_num_can(VersalVersion version); +int versal_get_num_sdhci(VersalVersion version); -#define MM_PMC_SD0 0xf1040000U -#define MM_PMC_SD0_SIZE 0x10000 -#define MM_PMC_BBRAM_CTRL 0xf11f0000 -#define MM_PMC_BBRAM_CTRL_SIZE 0x00050 -#define MM_PMC_EFUSE_CTRL 0xf1240000 -#define MM_PMC_EFUSE_CTRL_SIZE 0x00104 -#define MM_PMC_EFUSE_CACHE 0xf1250000 -#define MM_PMC_EFUSE_CACHE_SIZE 0x00C00 +static inline const char *versal_get_class(VersalVersion version) +{ + switch (version) { + case VERSAL_VER_VERSAL: + return TYPE_XLNX_VERSAL; -#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 + case VERSAL_VER_VERSAL2: + return TYPE_XLNX_VERSAL2; -#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 + default: + g_assert_not_reached(); + } +} -#define MM_PMC_CRP 0xf1260000U -#define MM_PMC_CRP_SIZE 0x10000 -#define MM_PMC_RTC 0xf12a0000 -#define MM_PMC_RTC_SIZE 0x10000 -#define MM_PMC_TRNG 0xf1230000 -#define MM_PMC_TRNG_SIZE 0x10000 #endif diff --git a/include/hw/arm/xlnx-zynqmp.h b/include/hw/arm/xlnx-zynqmp.h index c137ac5..a3117bd 100644 --- a/include/hw/arm/xlnx-zynqmp.h +++ b/include/hw/arm/xlnx-zynqmp.h @@ -42,6 +42,7 @@ #include "hw/misc/xlnx-zynqmp-crf.h" #include "hw/timer/cadence_ttc.h" #include "hw/usb/hcd-dwc3.h" +#include "hw/core/split-irq.h" #define TYPE_XLNX_ZYNQMP "xlnx-zynqmp" OBJECT_DECLARE_SIMPLE_TYPE(XlnxZynqMPState, XLNX_ZYNQMP) @@ -67,6 +68,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(XlnxZynqMPState, XLNX_ZYNQMP) #define XLNX_ZYNQMP_OCM_RAM_SIZE 0x10000 #define XLNX_ZYNQMP_GIC_REGIONS 6 +#define XLNX_ZYNQMP_GIC_NUM_SPI_INTR 160 /* * ZynqMP maps the ARM GIC regions (GICC, GICD ...) at consecutive 64k offsets @@ -105,6 +107,9 @@ struct XlnxZynqMPState { GICState gic; MemoryRegion gic_mr[XLNX_ZYNQMP_GIC_REGIONS][XLNX_ZYNQMP_GIC_ALIASES]; + GICState rpu_gic; + SplitIRQ splitter[XLNX_ZYNQMP_GIC_NUM_SPI_INTR]; + MemoryRegion ocm_ram[XLNX_ZYNQMP_NUM_OCM_BANKS]; MemoryRegion *ddr_ram; diff --git a/include/hw/audio/asc.h b/include/hw/audio/asc.h index 04fac27..bb51e9a 100644 --- a/include/hw/audio/asc.h +++ b/include/hw/audio/asc.h @@ -14,7 +14,7 @@ #define HW_AUDIO_ASC_H #include "hw/sysbus.h" -#include "audio/audio.h" +#include "qemu/audio.h" #define ASC_FREQ 22257 @@ -61,7 +61,7 @@ struct ASCState { MemoryRegion mem_regs; MemoryRegion mem_extregs; - QEMUSoundCard card; + AudioBackend *audio_be; SWVoiceOut *voice; uint8_t *mixbuf; int samples; diff --git a/include/hw/audio/model.h b/include/hw/audio/model.h new file mode 100644 index 0000000..c38b359 --- /dev/null +++ b/include/hw/audio/model.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef HW_AUDIO_MODEL_H +#define HW_AUDIO_MODEL_H + +void audio_register_model_with_cb(const char *name, const char *descr, + void (*init_audio_model)(const char *audiodev)); +void audio_register_model(const char *name, const char *descr, + const char *typename); + +void audio_model_init(void); +void audio_print_available_models(void); +void audio_set_model(const char *name, const char *audiodev); + +#endif diff --git a/include/hw/audio/soundhw.h b/include/hw/audio/soundhw.h deleted file mode 100644 index 474c5ff..0000000 --- a/include/hw/audio/soundhw.h +++ /dev/null @@ -1,13 +0,0 @@ -#ifndef HW_SOUNDHW_H -#define HW_SOUNDHW_H - -void pci_register_soundhw(const char *name, const char *descr, - int (*init_pci)(PCIBus *bus, const char *audiodev)); -void deprecated_register_soundhw(const char *name, const char *descr, - int isa, const char *typename); - -void soundhw_init(void); -void show_valid_soundhw(void); -void select_soundhw(const char *name, const char *audiodev); - -#endif diff --git a/include/hw/audio/virtio-snd.h b/include/hw/audio/virtio-snd.h index 8dafedb..c176066 100644 --- a/include/hw/audio/virtio-snd.h +++ b/include/hw/audio/virtio-snd.h @@ -17,7 +17,7 @@ #define QEMU_VIRTIO_SOUND_H #include "hw/virtio/virtio.h" -#include "audio/audio.h" +#include "qemu/audio.h" #include "standard-headers/linux/virtio_ids.h" #include "standard-headers/linux/virtio_snd.h" @@ -216,7 +216,7 @@ struct VirtIOSound { VirtQueue *queues[VIRTIO_SND_VQ_MAX]; uint64_t features; VirtIOSoundPCM *pcm; - QEMUSoundCard card; + AudioBackend *audio_be; VMChangeStateEntry *vmstate; virtio_snd_config snd_conf; QemuMutex cmdq_mutex; diff --git a/include/hw/block/block.h b/include/hw/block/block.h index de3946a..b4d9146 100644 --- a/include/hw/block/block.h +++ b/include/hw/block/block.h @@ -34,6 +34,8 @@ typedef struct BlockConf { OnOffAuto account_invalid, account_failed; BlockdevOnError rerror; BlockdevOnError werror; + uint32_t num_stats_intervals; + uint32_t *stats_intervals; } BlockConf; static inline unsigned int get_physical_block_exp(BlockConf *conf) @@ -66,7 +68,10 @@ static inline unsigned int get_physical_block_exp(BlockConf *conf) DEFINE_PROP_ON_OFF_AUTO("account-invalid", _state, \ _conf.account_invalid, ON_OFF_AUTO_AUTO), \ DEFINE_PROP_ON_OFF_AUTO("account-failed", _state, \ - _conf.account_failed, ON_OFF_AUTO_AUTO) + _conf.account_failed, ON_OFF_AUTO_AUTO), \ + DEFINE_PROP_ARRAY("stats-intervals", _state, \ + _conf.num_stats_intervals, _conf.stats_intervals, \ + qdev_prop_uint32, uint32_t) #define DEFINE_BLOCK_PROPERTIES(_state, _conf) \ DEFINE_PROP_DRIVE("drive", _state, _conf.blk), \ diff --git a/include/hw/block/flash.h b/include/hw/block/flash.h index 5fd67f5..3671f01 100644 --- a/include/hw/block/flash.h +++ b/include/hw/block/flash.h @@ -44,24 +44,6 @@ PFlashCFI02 *pflash_cfi02_register(hwaddr base, uint16_t unlock_addr1, int be); -/* nand.c */ -DeviceState *nand_init(BlockBackend *blk, int manf_id, int chip_id); -void nand_setpins(DeviceState *dev, uint8_t cle, uint8_t ale, - uint8_t ce, uint8_t wp, uint8_t gnd); -void nand_getpins(DeviceState *dev, int *rb); -void nand_setio(DeviceState *dev, uint32_t value); -uint32_t nand_getio(DeviceState *dev); -uint32_t nand_getbuswidth(DeviceState *dev); - -#define NAND_MFR_TOSHIBA 0x98 -#define NAND_MFR_SAMSUNG 0xec -#define NAND_MFR_FUJITSU 0x04 -#define NAND_MFR_NATIONAL 0x8f -#define NAND_MFR_RENESAS 0x07 -#define NAND_MFR_STMICRO 0x20 -#define NAND_MFR_HYNIX 0xad -#define NAND_MFR_MICRON 0x2c - /* m25p80.c */ #define TYPE_M25P80 "m25p80-generic" diff --git a/include/hw/boards.h b/include/hw/boards.h index f22b2e7..a48ed4f 100644 --- a/include/hw/boards.h +++ b/include/hw/boards.h @@ -3,7 +3,7 @@ #ifndef HW_BOARDS_H #define HW_BOARDS_H -#include "exec/memory.h" +#include "system/memory.h" #include "system/hostmem.h" #include "system/blockdev.h" #include "qapi/qapi-types-machine.h" @@ -26,6 +26,11 @@ OBJECT_DECLARE_TYPE(MachineState, MachineClass, MACHINE) extern MachineState *current_machine; /** + * machine_default_cpu_type: Return the machine default CPU type. + * @ms: Machine state + */ +const char *machine_default_cpu_type(const MachineState *ms); +/** * machine_class_default_cpu_type: Return the machine default CPU type. * @mc: Machine class */ @@ -250,15 +255,12 @@ typedef struct { * It also will be used as a way to option into "-m" option support. * If it's not set by board, '-m' will be ignored and generic code will * not create default RAM MemoryRegion. - * @fixup_ram_size: - * Amends user provided ram size (with -m option) using machine - * specific algorithm. To be used by old machine types for compat - * purposes only. - * Applies only to default memory backend, i.e., explicit memory backend - * wasn't used. * @smbios_memory_device_size: * Default size of memory device, * SMBIOS 3.1.0 "7.18 Memory Device (Type 17)" + * @get_valid_cpu_types: + * Returns a list of valid CPU types for this board. May be NULL + * if not needed. */ struct MachineClass { /*< private >*/ @@ -286,8 +288,7 @@ struct MachineClass { no_parallel:1, no_floppy:1, no_cdrom:1, - pci_allow_0_address:1, - legacy_fw_cfg_order:1; + pci_allow_0_address:1; bool auto_create_sdcard; bool is_default; const char *default_machine_opts; @@ -306,6 +307,8 @@ struct MachineClass { bool ignore_memory_transaction_failures; int numa_mem_align_shift; const char * const *valid_cpu_types; + GPtrArray *(*get_valid_cpu_types)(const MachineState *ms); + const char *(*get_default_cpu_type)(const MachineState *ms); strList *allowed_dynamic_sysbus_devices; bool auto_enable_numa_with_memhp; bool auto_enable_numa_with_memdev; @@ -326,7 +329,6 @@ struct MachineClass { unsigned cpu_index); const CPUArchIdList *(*possible_cpu_arch_ids)(MachineState *machine); int64_t (*get_default_cpu_node_id)(const MachineState *ms, int idx); - ram_addr_t (*fixup_ram_size)(ram_addr_t size); uint64_t smbios_memory_device_size; bool (*create_default_memdev)(MachineState *ms, const char *path, Error **errp); @@ -444,6 +446,7 @@ struct MachineState { SmpCache smp_cache; struct NVDIMMState *nvdimms_state; struct NumaState *numa_state; + bool acpi_spcr_enabled; }; /* @@ -503,6 +506,39 @@ struct MachineState { * DEFINE_VIRT_MACHINE_IMPL(false, major, minor, micro, _, tag) */ +#define DEFINE_MACHINE_EXTENDED(namestr, PARENT_NAME, InstanceName, \ + machine_initfn, ABSTRACT, ifaces...) \ + static void machine_initfn##_class_init(ObjectClass *oc, const void *data) \ + { \ + MachineClass *mc = MACHINE_CLASS(oc); \ + machine_initfn(mc); \ + } \ + static const TypeInfo machine_initfn##_typeinfo = { \ + .name = MACHINE_TYPE_NAME(namestr), \ + .parent = TYPE_##PARENT_NAME, \ + .class_init = machine_initfn##_class_init, \ + .instance_size = sizeof(InstanceName), \ + .abstract = ABSTRACT, \ + .interfaces = ifaces, \ + }; \ + static void machine_initfn##_register_types(void) \ + { \ + type_register_static(&machine_initfn##_typeinfo); \ + } \ + type_init(machine_initfn##_register_types) + +#define DEFINE_MACHINE(namestr, machine_initfn) \ + DEFINE_MACHINE_EXTENDED(namestr, MACHINE, MachineState, machine_initfn, \ + false, NULL) + +#define DEFINE_MACHINE_WITH_INTERFACE_ARRAY(namestr, machine_initfn, ifaces...)\ + DEFINE_MACHINE_EXTENDED(namestr, MACHINE, MachineState, machine_initfn, \ + false, ifaces) + +#define DEFINE_MACHINE_WITH_INTERFACES(namestr, machine_initfn, ...) \ + DEFINE_MACHINE_WITH_INTERFACE_ARRAY(namestr, machine_initfn, \ + (const InterfaceInfo[]) { __VA_ARGS__ }) + /* * Helper for dispatching different macros based on how * many __VA_ARGS__ are passed. Supports 1 to 5 variadic @@ -636,7 +672,11 @@ struct MachineState { /* * How many years/major releases for each phase * of the life cycle. Assumes use of versioning - * scheme where major is bumped each year + * scheme where major is bumped each year. + * + * These values must match the ver_machine_deprecation_version + * and ver_machine_deletion_version logic in docs/conf.py and + * the text in docs/about/deprecated.rst */ #define MACHINE_VER_DELETION_MAJOR 6 #define MACHINE_VER_DEPRECATION_MAJOR 3 @@ -650,11 +690,42 @@ struct MachineState { " years old are subject to deletion after " \ stringify(MACHINE_VER_DELETION_MAJOR) " years" -#define _MACHINE_VER_IS_EXPIRED_IMPL(cutoff, major, minor) \ +#define _MACHINE_VER_IS_CURRENT_EXPIRED(cutoff, major, minor) \ (((QEMU_VERSION_MAJOR - major) > cutoff) || \ (((QEMU_VERSION_MAJOR - major) == cutoff) && \ (QEMU_VERSION_MINOR - minor) >= 0)) +#define _MACHINE_VER_IS_NEXT_MINOR_EXPIRED(cutoff, major, minor) \ + (((QEMU_VERSION_MAJOR - major) > cutoff) || \ + (((QEMU_VERSION_MAJOR - major) == cutoff) && \ + ((QEMU_VERSION_MINOR + 1) - minor) >= 0)) + +#define _MACHINE_VER_IS_NEXT_MAJOR_EXPIRED(cutoff, major, minor) \ + ((((QEMU_VERSION_MAJOR + 1) - major) > cutoff) || \ + ((((QEMU_VERSION_MAJOR + 1) - major) == cutoff) && \ + (0 - minor) >= 0)) + +/* + * - The first check applies to formal releases + * - The second check applies to dev snapshots / release candidates + * where the next major version is the same. + * e.g. 9.0.50, 9.1.50, 9.0.90, 9.1.90 + * - The third check applies to dev snapshots / release candidates + * where the next major version will change. + * e.g. 9.2.50, 9.2.90 + * + * NB: this assumes we do 3 minor releases per year, before bumping major, + * and dev snapshots / release candidates are numbered with micro >= 50 + * If this ever changes the logic below will need modifying.... + */ +#define _MACHINE_VER_IS_EXPIRED_IMPL(cutoff, major, minor) \ + ((QEMU_VERSION_MICRO < 50 && \ + _MACHINE_VER_IS_CURRENT_EXPIRED(cutoff, major, minor)) || \ + (QEMU_VERSION_MICRO >= 50 && QEMU_VERSION_MINOR < 2 && \ + _MACHINE_VER_IS_NEXT_MINOR_EXPIRED(cutoff, major, minor)) || \ + (QEMU_VERSION_MICRO >= 50 && QEMU_VERSION_MINOR == 2 && \ + _MACHINE_VER_IS_NEXT_MAJOR_EXPIRED(cutoff, major, minor))) + #define _MACHINE_VER_IS_EXPIRED2(cutoff, major, minor) \ _MACHINE_VER_IS_EXPIRED_IMPL(cutoff, major, minor) #define _MACHINE_VER_IS_EXPIRED3(cutoff, major, minor, micro) \ @@ -719,47 +790,19 @@ struct MachineState { * suitable period of time has passed, it will cause * execution of the method to return, avoiding registration * of the machine - * - * The new deprecation and deletion policy for versioned - * machine types was introduced in QEMU 9.1.0. - * - * Under the new policy a number of old machine types (any - * prior to 2.12) would be liable for immediate deletion - * which would be a violation of our historical deprecation - * and removal policy - * - * Thus deletions are temporarily gated on existance of - * the env variable "QEMU_DELETE_MACHINES" / QEMU version - * number >= 10.1.0. This gate can be deleted in the 10.1.0 - * dev cycle */ #define MACHINE_VER_DELETION(...) \ do { \ if (MACHINE_VER_SHOULD_DELETE(__VA_ARGS__)) { \ - if (getenv("QEMU_DELETE_MACHINES") || \ - QEMU_VERSION_MAJOR > 10 || (QEMU_VERSION_MAJOR == 10 && \ - QEMU_VERSION_MINOR >= 1)) { \ - return; \ - } \ + return; \ } \ } while (0) -#define DEFINE_MACHINE(namestr, machine_initfn) \ - static void machine_initfn##_class_init(ObjectClass *oc, void *data) \ - { \ - MachineClass *mc = MACHINE_CLASS(oc); \ - machine_initfn(mc); \ - } \ - static const TypeInfo machine_initfn##_typeinfo = { \ - .name = MACHINE_TYPE_NAME(namestr), \ - .parent = TYPE_MACHINE, \ - .class_init = machine_initfn##_class_init, \ - }; \ - static void machine_initfn##_register_types(void) \ - { \ - type_register_static(&machine_initfn##_typeinfo); \ - } \ - type_init(machine_initfn##_register_types) +extern GlobalProperty hw_compat_10_1[]; +extern const size_t hw_compat_10_1_len; + +extern GlobalProperty hw_compat_10_0[]; +extern const size_t hw_compat_10_0_len; extern GlobalProperty hw_compat_9_2[]; extern const size_t hw_compat_9_2_len; @@ -842,10 +885,4 @@ extern const size_t hw_compat_2_7_len; extern GlobalProperty hw_compat_2_6[]; extern const size_t hw_compat_2_6_len; -extern GlobalProperty hw_compat_2_5[]; -extern const size_t hw_compat_2_5_len; - -extern GlobalProperty hw_compat_2_4[]; -extern const size_t hw_compat_2_4_len; - #endif diff --git a/include/hw/char/avr_usart.h b/include/hw/char/avr_usart.h index 0cc599e..bd2d488 100644 --- a/include/hw/char/avr_usart.h +++ b/include/hw/char/avr_usart.h @@ -66,7 +66,7 @@ struct AVRUsartState { /* <public> */ MemoryRegion mmio; - CharBackend chr; + CharFrontend chr; bool enabled; diff --git a/include/hw/char/bcm2835_aux.h b/include/hw/char/bcm2835_aux.h index 9e08179..a11134f 100644 --- a/include/hw/char/bcm2835_aux.h +++ b/include/hw/char/bcm2835_aux.h @@ -24,7 +24,7 @@ struct BCM2835AuxState { /*< public >*/ MemoryRegion iomem; - CharBackend chr; + CharFrontend chr; qemu_irq irq; uint8_t read_fifo[BCM2835_AUX_RX_FIFO_LEN]; diff --git a/include/hw/char/cadence_uart.h b/include/hw/char/cadence_uart.h index e7f7cd8..c87c327 100644 --- a/include/hw/char/cadence_uart.h +++ b/include/hw/char/cadence_uart.h @@ -47,7 +47,7 @@ struct CadenceUARTState { uint32_t rx_count; uint32_t tx_count; uint64_t char_tx_time; - CharBackend chr; + CharFrontend chr; qemu_irq irq; QEMUTimer *fifo_trigger_handle; Clock *refclk; diff --git a/include/hw/char/cmsdk-apb-uart.h b/include/hw/char/cmsdk-apb-uart.h index 7de8f8d..3d0af26 100644 --- a/include/hw/char/cmsdk-apb-uart.h +++ b/include/hw/char/cmsdk-apb-uart.h @@ -25,7 +25,7 @@ struct CMSDKAPBUART { /*< public >*/ MemoryRegion iomem; - CharBackend chr; + CharFrontend chr; qemu_irq txint; qemu_irq rxint; qemu_irq txovrint; diff --git a/include/hw/char/digic-uart.h b/include/hw/char/digic-uart.h index f710a1a..3eebdab 100644 --- a/include/hw/char/digic-uart.h +++ b/include/hw/char/digic-uart.h @@ -38,7 +38,7 @@ struct DigicUartState { /*< public >*/ MemoryRegion regs_region; - CharBackend chr; + CharFrontend chr; uint32_t reg_rx; uint32_t reg_st; diff --git a/include/hw/char/escc.h b/include/hw/char/escc.h index 8c4c6a7..857f646 100644 --- a/include/hw/char/escc.h +++ b/include/hw/char/escc.h @@ -36,7 +36,7 @@ typedef struct ESCCChannelState { uint32_t reg; uint8_t wregs[ESCC_SERIAL_REGS], rregs[ESCC_SERIAL_REGS]; ESCCSERIOQueue queue; - CharBackend chr; + CharFrontend chr; int e0_mode, led_mode, caps_lock_mode, num_lock_mode; int disabled; int clock; diff --git a/include/hw/char/goldfish_tty.h b/include/hw/char/goldfish_tty.h index d59733e..70fdedd 100644 --- a/include/hw/char/goldfish_tty.h +++ b/include/hw/char/goldfish_tty.h @@ -24,7 +24,7 @@ struct GoldfishTTYState { MemoryRegion iomem; qemu_irq irq; - CharBackend chr; + CharFrontend chr; uint32_t data_len; uint64_t data_ptr; diff --git a/include/hw/char/ibex_uart.h b/include/hw/char/ibex_uart.h index 9deadf2..1ccbb60 100644 --- a/include/hw/char/ibex_uart.h +++ b/include/hw/char/ibex_uart.h @@ -64,7 +64,7 @@ struct IbexUartState { Clock *f_clk; - CharBackend chr; + CharFrontend chr; qemu_irq tx_watermark; qemu_irq rx_watermark; qemu_irq tx_empty; diff --git a/include/hw/char/imx_serial.h b/include/hw/char/imx_serial.h index 90ba3ff..2dcd2e6 100644 --- a/include/hw/char/imx_serial.h +++ b/include/hw/char/imx_serial.h @@ -122,7 +122,7 @@ struct IMXSerialState { uint32_t ucr4; qemu_irq irq; - CharBackend chr; + CharFrontend chr; }; #endif diff --git a/include/hw/char/max78000_uart.h b/include/hw/char/max78000_uart.h new file mode 100644 index 0000000..ac93f83 --- /dev/null +++ b/include/hw/char/max78000_uart.h @@ -0,0 +1,78 @@ +/* + * MAX78000 UART + * + * Copyright (c) 2025 Jackson Donaldson <jcksn@duck.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_MAX78000_UART_H +#define HW_MAX78000_UART_H + +#include "hw/sysbus.h" +#include "chardev/char-fe.h" +#include "qemu/fifo8.h" +#include "qom/object.h" + +#define UART_CTRL 0x0 +#define UART_STATUS 0x4 +#define UART_INT_EN 0x8 +#define UART_INT_FL 0xc +#define UART_CLKDIV 0x10 +#define UART_OSR 0x14 +#define UART_TXPEEK 0x18 +#define UART_PNR 0x1c +#define UART_FIFO 0x20 +#define UART_DMA 0x30 +#define UART_WKEN 0x34 +#define UART_WKFL 0x38 + +/* CTRL */ +#define UART_CTF_DIS (1 << 7) +#define UART_FLUSH_TX (1 << 8) +#define UART_FLUSH_RX (1 << 9) +#define UART_BCLKEN (1 << 15) +#define UART_BCLKRDY (1 << 19) + +/* STATUS */ +#define UART_RX_LVL 8 +#define UART_TX_EM (1 << 6) +#define UART_RX_FULL (1 << 5) +#define UART_RX_EM (1 << 4) + +/* PNR (Pin Control Register) */ +#define UART_CTS 1 +#define UART_RTS (1 << 1) + +/* INT_EN / INT_FL */ +#define UART_RX_THD (1 << 4) +#define UART_TX_HE (1 << 6) + +#define UART_RXBUFLEN 0x100 +#define TYPE_MAX78000_UART "max78000-uart" +OBJECT_DECLARE_SIMPLE_TYPE(Max78000UartState, MAX78000_UART) + +struct Max78000UartState { + SysBusDevice parent_obj; + + MemoryRegion mmio; + + uint32_t ctrl; + uint32_t status; + uint32_t int_en; + uint32_t int_fl; + uint32_t clkdiv; + uint32_t osr; + uint32_t txpeek; + uint32_t pnr; + uint32_t fifo; + uint32_t dma; + uint32_t wken; + uint32_t wkfl; + + Fifo8 rx_fifo; + + CharFrontend chr; + qemu_irq irq; +}; +#endif /* HW_STM32F2XX_USART_H */ diff --git a/include/hw/char/nrf51_uart.h b/include/hw/char/nrf51_uart.h index 561b638..03d8c2a 100644 --- a/include/hw/char/nrf51_uart.h +++ b/include/hw/char/nrf51_uart.h @@ -59,7 +59,7 @@ struct NRF51UARTState { SysBusDevice parent_obj; MemoryRegion iomem; - CharBackend chr; + CharFrontend chr; qemu_irq irq; guint watch_tag; diff --git a/include/hw/char/parallel-isa.h b/include/hw/char/parallel-isa.h index 5284b2f..3edaf9d 100644 --- a/include/hw/char/parallel-isa.h +++ b/include/hw/char/parallel-isa.h @@ -12,7 +12,7 @@ #include "parallel.h" -#include "exec/ioport.h" +#include "system/ioport.h" #include "hw/isa/isa.h" #include "qom/object.h" diff --git a/include/hw/char/parallel.h b/include/hw/char/parallel.h index cfb97cc..3f8d9b5 100644 --- a/include/hw/char/parallel.h +++ b/include/hw/char/parallel.h @@ -1,7 +1,7 @@ #ifndef HW_PARALLEL_H #define HW_PARALLEL_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/isa/isa.h" #include "hw/irq.h" #include "chardev/char-fe.h" @@ -15,7 +15,7 @@ typedef struct ParallelState { uint8_t control; qemu_irq irq; int irq_pending; - CharBackend chr; + CharFrontend chr; int hw_driver; int epp_timeout; uint32_t last_read_offset; /* For debugging */ diff --git a/include/hw/char/pl011.h b/include/hw/char/pl011.h index 299ca9b..2d4ff01 100644 --- a/include/hw/char/pl011.h +++ b/include/hw/char/pl011.h @@ -47,7 +47,7 @@ struct PL011State { int read_pos; int read_count; int read_trigger; - CharBackend chr; + CharFrontend chr; qemu_irq irq[6]; Clock *clk; bool migrate_clk; diff --git a/include/hw/char/renesas_sci.h b/include/hw/char/renesas_sci.h index a4764e3..90e784f 100644 --- a/include/hw/char/renesas_sci.h +++ b/include/hw/char/renesas_sci.h @@ -33,7 +33,7 @@ struct RSCIState { MemoryRegion memory; QEMUTimer timer; - CharBackend chr; + CharFrontend chr; qemu_irq irq[SCI_NR_IRQ]; uint8_t smr; diff --git a/include/hw/char/riscv_htif.h b/include/hw/char/riscv_htif.h index df493fd..9d61e60 100644 --- a/include/hw/char/riscv_htif.h +++ b/include/hw/char/riscv_htif.h @@ -22,7 +22,7 @@ #include "chardev/char.h" #include "chardev/char-fe.h" -#include "exec/memory.h" +#include "system/memory.h" #define TYPE_HTIF_UART "riscv.htif.uart" @@ -36,7 +36,7 @@ typedef struct HTIFState { hwaddr fromhost_offset; MemoryRegion mmio; - CharBackend chr; + CharFrontend chr; uint64_t pending_read; } HTIFState; diff --git a/include/hw/char/serial-mm.h b/include/hw/char/serial-mm.h index 62a8489..77abd09 100644 --- a/include/hw/char/serial-mm.h +++ b/include/hw/char/serial-mm.h @@ -27,7 +27,7 @@ #define HW_SERIAL_MM_H #include "hw/char/serial.h" -#include "exec/memory.h" +#include "system/memory.h" #include "chardev/char.h" #include "hw/sysbus.h" #include "qom/object.h" diff --git a/include/hw/char/serial.h b/include/hw/char/serial.h index 942b372..b804e22 100644 --- a/include/hw/char/serial.h +++ b/include/hw/char/serial.h @@ -27,7 +27,7 @@ #define HW_SERIAL_H #include "chardev/char-fe.h" -#include "exec/memory.h" +#include "system/memory.h" #include "qemu/fifo8.h" #include "qom/object.h" @@ -54,7 +54,7 @@ struct SerialState { it can be reset while reading iir */ int thr_ipending; qemu_irq irq; - CharBackend chr; + CharFrontend chr; int last_break_enable; uint32_t baudbase; uint32_t tsr_retry; @@ -77,7 +77,6 @@ struct SerialState { QEMUTimer *modem_status_poll; MemoryRegion io; }; -typedef struct SerialState SerialState; extern const VMStateDescription vmstate_serial; extern const MemoryRegionOps serial_io_ops; diff --git a/include/hw/char/shakti_uart.h b/include/hw/char/shakti_uart.h index 526c408..e5e775d 100644 --- a/include/hw/char/shakti_uart.h +++ b/include/hw/char/shakti_uart.h @@ -68,7 +68,7 @@ typedef struct { uint32_t uart_iq_cycles; uint32_t uart_rx_threshold; - CharBackend chr; + CharFrontend chr; } ShaktiUartState; #endif /* HW_SHAKTI_UART_H */ diff --git a/include/hw/char/sifive_uart.h b/include/hw/char/sifive_uart.h index 0846cf6..6486c3f 100644 --- a/include/hw/char/sifive_uart.h +++ b/include/hw/char/sifive_uart.h @@ -67,7 +67,7 @@ struct SiFiveUARTState { /*< public >*/ qemu_irq irq; MemoryRegion mmio; - CharBackend chr; + CharFrontend chr; uint32_t txfifo; uint32_t ie; diff --git a/include/hw/char/stm32f2xx_usart.h b/include/hw/char/stm32f2xx_usart.h index fdfa742..f9018b8 100644 --- a/include/hw/char/stm32f2xx_usart.h +++ b/include/hw/char/stm32f2xx_usart.h @@ -73,7 +73,7 @@ struct STM32F2XXUsartState { uint32_t usart_cr3; uint32_t usart_gtpr; - CharBackend chr; + CharFrontend chr; qemu_irq irq; }; #endif /* HW_STM32F2XX_USART_H */ diff --git a/include/hw/char/stm32l4x5_usart.h b/include/hw/char/stm32l4x5_usart.h index dd38666..cdf7419 100644 --- a/include/hw/char/stm32l4x5_usart.h +++ b/include/hw/char/stm32l4x5_usart.h @@ -53,7 +53,7 @@ struct Stm32l4x5UsartBaseState { uint32_t tdr; Clock *clk; - CharBackend chr; + CharFrontend chr; qemu_irq irq; guint watch_tag; }; diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h index abd8764..9615051 100644 --- a/include/hw/core/cpu.h +++ b/include/hw/core/cpu.h @@ -102,10 +102,9 @@ struct SysemuCPUOps; * CPUClass: * @class_by_name: Callback to map -cpu command line model name to an * instantiatable CPU type. + * @list_cpus: list available CPU models and flags. * @parse_features: Callback to parse command line arguments. * @reset_dump_flags: #CPUDumpFlags to use for reset logging. - * @mmu_index: Callback for choosing softmmu mmu index; - * may be used internally by memory_rw_debug without TCG. * @memory_rw_debug: Callback for GDB memory access. * @dump_state: Callback for dumping state. * @query_cpu_fast: @@ -132,10 +131,15 @@ struct SysemuCPUOps; * @gdb_num_core_regs: Number of core registers accessible to GDB or 0 to infer * from @gdb_core_xml_file. * @gdb_core_xml_file: File name for core registers GDB XML description. + * @gdb_get_core_xml_file: Optional callback that returns the file name for + * the core registers GDB XML description. The returned value is expected to + * be a simple constant string: the caller will not g_free() it. If this + * is NULL then @gdb_core_xml_file will be used instead. * @gdb_stop_before_watchpoint: Indicates whether GDB expects the CPU to stop * before the insn which triggers a watchpoint rather than after it. * @gdb_arch_name: Optional callback that returns the architecture name known - * to GDB. The caller must free the returned string with g_free. + * to GDB. The returned value is expected to be a simple constant string: + * the caller will not g_free() it. * @disas_set_info: Setup architecture specific components of disassembly info * @adjust_watchpoint_address: Perform a target-specific adjustment to an * address before attempting to match it against watchpoints. @@ -150,9 +154,9 @@ struct CPUClass { /*< public >*/ ObjectClass *(*class_by_name)(const char *cpu_model); + void (*list_cpus)(void); void (*parse_features)(const char *typename, char *str, Error **errp); - int (*mmu_index)(CPUState *cpu, bool ifetch); int (*memory_rw_debug)(CPUState *cpu, vaddr addr, uint8_t *buf, size_t len, bool is_write); void (*dump_state)(CPUState *cpu, FILE *, int flags); @@ -165,7 +169,8 @@ struct CPUClass { vaddr (*gdb_adjust_breakpoint)(CPUState *cpu, vaddr addr); const char *gdb_core_xml_file; - const gchar * (*gdb_arch_name)(CPUState *cpu); + const char * (*gdb_arch_name)(CPUState *cpu); + const char * (*gdb_get_core_xml_file)(CPUState *cpu); void (*disas_set_info)(CPUState *cpu, disassemble_info *info); @@ -193,10 +198,11 @@ struct CPUClass { }; /* - * Fix the number of mmu modes to 16, which is also the maximum - * supported by the softmmu tlb api. + * Fix the number of mmu modes across all targets. + * Current maximum is target/arm/. */ -#define NB_MMU_MODES 16 +#define NB_MMU_MODES 22 +typedef uint32_t MMUIdxMap; /* Use a fully associative victim tlb of 8 entries. */ #define CPU_VTLB_SIZE 8 @@ -301,7 +307,7 @@ typedef struct CPUTLBCommon { * mmu_idx N since the last time that mmu_idx was flushed. * Protected by tlb_c.lock. */ - uint16_t dirty; + MMUIdxMap dirty; /* * Statistics. These are not lock protected, but are read and * written atomically. This allows the monitor to print a snapshot @@ -363,6 +369,7 @@ typedef struct CPUNegativeOffsetState { GArray *plugin_mem_cbs; uint64_t plugin_mem_value_low; uint64_t plugin_mem_value_high; + int32_t plugin_cb_flags; #endif IcountDecr icount_decr; bool can_do_io; @@ -416,7 +423,17 @@ struct qemu_work_item; * valid under cpu_list_lock. * @created: Indicates whether the CPU thread has been successfully created. * @halt_cond: condition variable sleeping threads can wait on. + * @exit_request: Another thread requests the CPU to call qemu_process_cpu_events(). + * Should be read only by CPU thread with load-acquire, to synchronize with + * other threads' store-release operation. + * + * In some cases, accelerator-specific code will write exit_request from + * within the same thread, to "bump" the effect of qemu_cpu_kick() to + * the one provided by cpu_exit(), especially when processing interrupt + * flags. In this case, the write and read happen in the same thread + * and the write therefore can use qemu_atomic_set(). * @interrupt_request: Indicates a pending interrupt request. + * Only used by system emulation. * @halted: Nonzero if the CPU is in suspended state. * @stop: Indicates a pending stop request. * @stopped: Indicates the CPU has been artificially stopped. @@ -436,6 +453,7 @@ struct qemu_work_item; * @opaque: User data. * @mem_io_pc: Host Program Counter at which the memory was accessed. * @accel: Pointer to accelerator specific state. + * @vcpu_dirty: Hardware accelerator is not synchronized with QEMU state * @kvm_fd: vCPU file descriptor for KVM. * @work_mutex: Lock to prevent multiple access to @work_list. * @work_list: List of pending asynchronous work. @@ -487,7 +505,6 @@ struct CPUState { bool exit_request; int exclusive_context_count; uint32_t cflags_next_tb; - /* updates protected by BQL */ uint32_t interrupt_request; int singlestep_enabled; int64_t icount_budget; @@ -499,7 +516,6 @@ struct CPUState { QSIMPLEQ_HEAD(, qemu_work_item) work_list; struct CPUAddressSpace *cpu_ases; - int cpu_ases_count; int num_ases; AddressSpace *as; MemoryRegion *memory; @@ -532,7 +548,6 @@ struct CPUState { uint32_t kvm_fetch_index; uint64_t dirty_pages; int kvm_vcpu_stats_fd; - bool vcpu_dirty; /* Use by accel-block: CPU is executing an ioctl() */ QemuLockCnt in_ioctl_lock; @@ -548,6 +563,7 @@ struct CPUState { uint32_t halted; int32_t exception_index; + bool vcpu_dirty; AccelCPUState *accel; /* Used to keep track of an outstanding cpu throttle thread for migration @@ -582,10 +598,26 @@ QEMU_BUILD_BUG_ON(offsetof(CPUState, neg) != static inline CPUArchState *cpu_env(CPUState *cpu) { - /* We validate that CPUArchState follows CPUState in cpu-all.h. */ + /* We validate that CPUArchState follows CPUState in cpu-target.c */ return (CPUArchState *)(cpu + 1); } +#ifdef CONFIG_TCG +/* + * Invert the index order of the CPUTLBDescFast array so that lower + * mmu_idx have offsets from env with smaller magnitude. + */ +static inline int mmuidx_to_fast_index(int mmu_idx) +{ + return NB_MMU_MODES - 1 - mmu_idx; +} + +static inline CPUTLBDescFast *cpu_tlb_fast(CPUState *cpu, int mmu_idx) +{ + return &cpu->neg.tlb.f[mmuidx_to_fast_index(mmu_idx)]; +} +#endif + typedef QTAILQ_HEAD(CPUTailQ, CPUState) CPUTailQ; extern CPUTailQ cpus_queue; @@ -598,15 +630,6 @@ extern CPUTailQ cpus_queue; extern __thread CPUState *current_cpu; /** - * qemu_tcg_mttcg_enabled: - * Check whether we are running MultiThread TCG or not. - * - * Returns: %true if we are in MTTCG mode %false otherwise. - */ -extern bool mttcg_enabled; -#define qemu_tcg_mttcg_enabled() (mttcg_enabled) - -/** * cpu_paging_enabled: * @cpu: The CPU whose state is to be inspected. * @@ -614,8 +637,6 @@ extern bool mttcg_enabled; */ bool cpu_paging_enabled(const CPUState *cpu); -#if !defined(CONFIG_USER_ONLY) - /** * cpu_get_memory_mapping: * @cpu: The CPU whose memory mappings are to be obtained. @@ -668,6 +689,26 @@ int cpu_write_elf32_qemunote(WriteCoreDumpFunction f, CPUState *cpu, void *opaque); /** + * cpu_memory_rw_debug: + * @cpu: The CPU whose memory is to be accessed + * @addr: guest virtual address + * @ptr: buffer with the data transferred + * @len: the number of bytes to read or write + * @is_write: indicates the transfer direction + * + * Take a virtual address, convert it to a physical address via + * an MMU lookup using the current settings of the specified CPU, + * and then perform the access (using address_space_rw() for + * reads or address_space_write_rom() for writes). + * + * This function is intended for use by the GDB stub and similar code. + * + * Returns: 0 on success, -1 on error + */ +int cpu_memory_rw_debug(CPUState *cpu, vaddr addr, + void *ptr, size_t len, bool is_write); + +/** * cpu_get_crash_info: * @cpu: The CPU to get crash information for * @@ -676,8 +717,6 @@ int cpu_write_elf32_qemunote(WriteCoreDumpFunction f, CPUState *cpu, */ GuestPanicInformation *cpu_get_crash_info(CPUState *cpu); -#endif /* !CONFIG_USER_ONLY */ - /** * CPUDumpFlags: * @CPU_DUMP_CODE: @@ -701,7 +740,6 @@ enum CPUDumpFlags { */ void cpu_dump_state(CPUState *cpu, FILE *f, int flags); -#ifndef CONFIG_USER_ONLY /** * cpu_get_phys_page_attrs_debug: * @cpu: The CPU to obtain the physical page address for. @@ -758,8 +796,6 @@ bool cpu_virtio_is_big_endian(CPUState *cpu); */ bool cpu_has_work(CPUState *cpu); -#endif /* CONFIG_USER_ONLY */ - /** * cpu_list_add: * @cpu: The CPU to be added to the list of CPUs. @@ -838,7 +874,8 @@ bool qemu_cpu_is_self(CPUState *cpu); * qemu_cpu_kick: * @cpu: The vCPU to kick. * - * Kicks @cpu's thread. + * Kicks @cpu's thread to exit the accelerator. For accelerators that + * can do that, the target vCPU thread will try not to take the BQL. */ void qemu_cpu_kick(CPUState *cpu); @@ -952,6 +989,28 @@ CPUState *cpu_by_arch_id(int64_t id); void cpu_interrupt(CPUState *cpu, int mask); /** + * cpu_test_interrupt: + * @cpu: The CPU to check interrupt(s) on. + * @mask: The interrupts to check. + * + * Checks if any of interrupts in @mask are pending on @cpu. + */ +static inline bool cpu_test_interrupt(CPUState *cpu, int mask) +{ + return qatomic_load_acquire(&cpu->interrupt_request) & mask; +} + +/** + * cpu_set_interrupt: + * @cpu: The CPU to set pending interrupt(s) on. + * @mask: The interrupts to set. + * + * Sets interrupts in @mask as pending on @cpu. Unlike @cpu_interrupt, + * this does not kick the vCPU. + */ +void cpu_set_interrupt(CPUState *cpu, int mask); + +/** * cpu_set_pc: * @cpu: The CPU to set the program counter for. * @addr: Program counter value. @@ -1109,36 +1168,6 @@ static inline bool cpu_breakpoint_test(CPUState *cpu, vaddr pc, int mask) return false; } -#if defined(CONFIG_USER_ONLY) -static inline int cpu_watchpoint_insert(CPUState *cpu, vaddr addr, vaddr len, - int flags, CPUWatchpoint **watchpoint) -{ - return -ENOSYS; -} - -static inline int cpu_watchpoint_remove(CPUState *cpu, vaddr addr, - vaddr len, int flags) -{ - return -ENOSYS; -} - -static inline void cpu_watchpoint_remove_by_ref(CPUState *cpu, - CPUWatchpoint *wp) -{ -} - -static inline void cpu_watchpoint_remove_all(CPUState *cpu, int mask) -{ -} -#else -int cpu_watchpoint_insert(CPUState *cpu, vaddr addr, vaddr len, - int flags, CPUWatchpoint **watchpoint); -int cpu_watchpoint_remove(CPUState *cpu, vaddr addr, - vaddr len, int flags); -void cpu_watchpoint_remove_by_ref(CPUState *cpu, CPUWatchpoint *watchpoint); -void cpu_watchpoint_remove_all(CPUState *cpu, int mask); -#endif - /** * cpu_get_address_space: * @cpu: CPU to get address space from @@ -1152,6 +1181,15 @@ AddressSpace *cpu_get_address_space(CPUState *cpu, int asidx); G_NORETURN void cpu_abort(CPUState *cpu, const char *fmt, ...) G_GNUC_PRINTF(2, 3); +/** + * qemu_process_cpu_events: + * @cpu: CPU that left the execution loop + * + * Perform accelerator-independent work after the CPU has left + * the inner execution loop. + */ +void qemu_process_cpu_events(CPUState *cpu); + /* $(top_srcdir)/cpu.c */ void cpu_class_init_props(DeviceClass *dc); void cpu_exec_class_post_init(CPUClass *cc); @@ -1162,26 +1200,15 @@ bool cpu_exec_realizefn(CPUState *cpu, Error **errp); void cpu_exec_unrealizefn(CPUState *cpu); void cpu_exec_reset_hold(CPUState *cpu); -const char *target_name(void); - -#ifdef COMPILING_PER_TARGET - -#ifndef CONFIG_USER_ONLY - extern const VMStateDescription vmstate_cpu_common; -#define VMSTATE_CPU() { \ - .name = "parent_obj", \ - .size = sizeof(CPUState), \ - .vmsd = &vmstate_cpu_common, \ - .flags = VMS_STRUCT, \ - .offset = 0, \ -} -#endif /* !CONFIG_USER_ONLY */ - -#endif /* COMPILING_PER_TARGET */ - #define UNASSIGNED_CPU_INDEX -1 #define UNASSIGNED_CLUSTER_INDEX -1 +enum CacheType { + DATA_CACHE, + INSTRUCTION_CACHE, + UNIFIED_CACHE +}; + #endif diff --git a/include/hw/core/resetcontainer.h b/include/hw/core/resetcontainer.h index 23db0c7..daeb18c 100644 --- a/include/hw/core/resetcontainer.h +++ b/include/hw/core/resetcontainer.h @@ -20,7 +20,7 @@ #include "qom/object.h" #define TYPE_RESETTABLE_CONTAINER "resettable-container" -OBJECT_DECLARE_TYPE(ResettableContainer, ResettableContainerClass, RESETTABLE_CONTAINER) +OBJECT_DECLARE_SIMPLE_TYPE(ResettableContainer, RESETTABLE_CONTAINER) /** * resettable_container_add: Add a resettable object to the container diff --git a/include/hw/cxl/cxl.h b/include/hw/cxl/cxl.h index 75e47b6..998f495 100644 --- a/include/hw/cxl/cxl.h +++ b/include/hw/cxl/cxl.h @@ -23,10 +23,13 @@ #define CXL_DEVICE_REG_BAR_IDX 2 #define CXL_WINDOW_MAX 10 +#define CXL_NUM_EXTENTS_SUPPORTED 512 typedef struct PXBCXLDev PXBCXLDev; typedef struct CXLFixedWindow { + SysBusDevice parent_obj; + int index; uint64_t size; char **targets; PXBCXLDev *target_hbs[16]; @@ -37,12 +40,13 @@ typedef struct CXLFixedWindow { MemoryRegion mr; hwaddr base; } CXLFixedWindow; +#define TYPE_CXL_FMW "cxl-fmw" +OBJECT_DECLARE_SIMPLE_TYPE(CXLFixedWindow, CXL_FMW) typedef struct CXLState { bool is_enabled; MemoryRegion host_mr; unsigned int next_mr_idx; - GList *fixed_windows; CXLFixedMemoryWindowOptionsList *cfmw_list; } CXLState; diff --git a/include/hw/cxl/cxl_device.h b/include/hw/cxl/cxl_device.h index 3a0ee7e..89411c8 100644 --- a/include/hw/cxl/cxl_device.h +++ b/include/hw/cxl/cxl_device.h @@ -133,6 +133,15 @@ typedef enum { CXL_MBOX_MAX = 0x20 } CXLRetCode; +/* r3.2 Section 7.6.7.6.2: Table 7-66: DSMAS Flags Bits */ +typedef enum { + CXL_DSMAS_FLAGS_NONVOLATILE = 2, + CXL_DSMAS_FLAGS_SHARABLE = 3, + CXL_DSMAS_FLAGS_HW_MANAGED_COHERENCY = 4, + CXL_DSMAS_FLAGS_IC_SPECIFIC_DC_MANAGEMENT = 5, + CXL_DSMAS_FLAGS_RDONLY = 6, +} CXLDSMASFlags; + typedef struct CXLCCI CXLCCI; typedef struct cxl_device_state CXLDeviceState; struct cxl_cmd; @@ -176,10 +185,12 @@ typedef struct CXLCCI { uint16_t opcode; uint16_t complete_pct; uint16_t ret_code; /* Current value of retcode */ + bool aborted; uint64_t starttime; /* set by each bg cmd, cleared by the bg_timer when complete */ uint64_t runtime; QEMUTimer *timer; + QemuMutex lock; /* serializes mbox abort vs timer cb */ } bg; /* firmware update */ @@ -201,6 +212,7 @@ typedef struct CXLCCI { DeviceState *d; /* Pointer to the device hosting the protocol conversion */ DeviceState *intf; + bool initialized; } CXLCCI; typedef struct cxl_device_state { @@ -316,6 +328,7 @@ void cxl_initialize_mailbox_t3(CXLCCI *cci, DeviceState *d, size_t payload_max); void cxl_initialize_mailbox_swcci(CXLCCI *cci, DeviceState *intf, DeviceState *d, size_t payload_max); void cxl_init_cci(CXLCCI *cci, size_t payload_max); +void cxl_destroy_cci(CXLCCI *cci); void cxl_add_cci_commands(CXLCCI *cci, const struct cxl_cmd (*cxl_cmd_set)[256], size_t payload_max); int cxl_process_cci_message(CXLCCI *cci, uint8_t set, uint8_t cmd, @@ -526,6 +539,14 @@ typedef struct CXLDCRegion { uint32_t dsmadhandle; uint8_t flags; unsigned long *blk_bitmap; + uint64_t supported_blk_size_bitmask; + QemuMutex bitmap_lock; + /* Following bools make up dsmas flags, as defined in the CDAT */ + bool nonvolatile; + bool sharable; + bool hw_managed_coherency; + bool ic_specific_dc_management; + bool rdonly; } CXLDCRegion; typedef struct CXLSetFeatureInfo { @@ -536,6 +557,21 @@ typedef struct CXLSetFeatureInfo { size_t data_size; } CXLSetFeatureInfo; +struct CXLSanitizeInfo; + +typedef struct CXLAlertConfig { + uint8_t valid_alerts; + uint8_t enable_alerts; + uint8_t life_used_crit_alert_thresh; + uint8_t life_used_warn_thresh; + uint16_t over_temp_crit_alert_thresh; + uint16_t under_temp_crit_alert_thresh; + uint16_t over_temp_warn_thresh; + uint16_t under_temp_warn_thresh; + uint16_t cor_vmem_err_warn_thresh; + uint16_t cor_pmem_err_warn_thresh; +} QEMU_PACKED CXLAlertConfig; + struct CXLType3Dev { /* Private */ PCIDevice parent_obj; @@ -557,6 +593,8 @@ struct CXLType3Dev { CXLCCI vdm_fm_owned_ld_mctp_cci; CXLCCI ld0_cci; + CXLAlertConfig alert_config; + /* PCIe link characteristics */ PCIExpLinkSpeed speed; PCIExpLinkWidth width; @@ -597,11 +635,14 @@ struct CXLType3Dev { CXLDCExtentList extents; CXLDCExtentGroupList extents_pending; uint32_t total_extent_count; + uint32_t nr_extents_accepted; uint32_t ext_list_gen_seq; uint8_t num_regions; /* 0-8 regions */ CXLDCRegion regions[DCD_MAX_NUM_REGION]; } dc; + + struct CXLSanitizeInfo *media_op_sanitize; }; #define TYPE_CXL_TYPE3 "cxl-type3" @@ -673,11 +714,22 @@ CXLDCExtentGroup *cxl_insert_extent_to_extent_group(CXLDCExtentGroup *group, uint16_t shared_seq); void cxl_extent_group_list_insert_tail(CXLDCExtentGroupList *list, CXLDCExtentGroup *group); -void cxl_extent_group_list_delete_front(CXLDCExtentGroupList *list); +uint32_t cxl_extent_group_list_delete_front(CXLDCExtentGroupList *list); void ct3_set_region_block_backed(CXLType3Dev *ct3d, uint64_t dpa, uint64_t len); void ct3_clear_region_block_backed(CXLType3Dev *ct3d, uint64_t dpa, uint64_t len); bool ct3_test_region_block_backed(CXLType3Dev *ct3d, uint64_t dpa, uint64_t len); +void cxl_assign_event_header(CXLEventRecordHdr *hdr, + const QemuUUID *uuid, uint32_t flags, + uint8_t length, uint64_t timestamp); +void cxl_create_dc_event_records_for_extents(CXLType3Dev *ct3d, + CXLDCEventType type, + CXLDCExtentRaw extents[], + uint32_t ext_count); +bool cxl_extents_overlaps_dpa_range(CXLDCExtentList *list, + uint64_t dpa, uint64_t len); +bool cxl_extent_groups_overlaps_dpa_range(CXLDCExtentGroupList *list, + uint64_t dpa, uint64_t len); #endif diff --git a/include/hw/cxl/cxl_events.h b/include/hw/cxl/cxl_events.h index 38cadaa..758b075 100644 --- a/include/hw/cxl/cxl_events.h +++ b/include/hw/cxl/cxl_events.h @@ -184,4 +184,19 @@ typedef struct CXLEventDynamicCapacity { uint32_t tags_avail; } QEMU_PACKED CXLEventDynamicCapacity; +/* CXL r3.1 Table 8-50: Dynamic Capacity Event Record */ +static const QemuUUID dynamic_capacity_uuid = { + .data = UUID(0xca95afa7, 0xf183, 0x4018, 0x8c, 0x2f, + 0x95, 0x26, 0x8e, 0x10, 0x1a, 0x2a), +}; + +typedef enum CXLDCEventType { + DC_EVENT_ADD_CAPACITY = 0x0, + DC_EVENT_RELEASE_CAPACITY = 0x1, + DC_EVENT_FORCED_RELEASE_CAPACITY = 0x2, + DC_EVENT_REGION_CONFIG_UPDATED = 0x3, + DC_EVENT_ADD_CAPACITY_RSP = 0x4, + DC_EVENT_CAPACITY_RELEASED = 0x5, +} CXLDCEventType; + #endif /* CXL_EVENTS_H */ diff --git a/include/hw/cxl/cxl_host.h b/include/hw/cxl/cxl_host.h index c9bc9c7..cd3c368 100644 --- a/include/hw/cxl/cxl_host.h +++ b/include/hw/cxl/cxl_host.h @@ -14,8 +14,11 @@ #define CXL_HOST_H void cxl_machine_init(Object *obj, CXLState *state); -void cxl_fmws_link_targets(CXLState *stat, Error **errp); +void cxl_fmws_link_targets(Error **errp); void cxl_hook_up_pxb_registers(PCIBus *bus, CXLState *state, Error **errp); +hwaddr cxl_fmws_set_memmap(hwaddr base, hwaddr max_addr); +void cxl_fmws_update_mmio(void); +GSList *cxl_fmws_get_all_sorted(void); extern const MemoryRegionOps cfmws_ops; diff --git a/include/hw/cxl/cxl_mailbox.h b/include/hw/cxl/cxl_mailbox.h index beb0480..a05d7cb 100644 --- a/include/hw/cxl/cxl_mailbox.h +++ b/include/hw/cxl/cxl_mailbox.h @@ -8,11 +8,18 @@ #ifndef CXL_MAILBOX_H #define CXL_MAILBOX_H +#define CXL_MBOX_CONFIG_CHANGE_COLD_RESET (1) #define CXL_MBOX_IMMEDIATE_CONFIG_CHANGE (1 << 1) #define CXL_MBOX_IMMEDIATE_DATA_CHANGE (1 << 2) #define CXL_MBOX_IMMEDIATE_POLICY_CHANGE (1 << 3) #define CXL_MBOX_IMMEDIATE_LOG_CHANGE (1 << 4) #define CXL_MBOX_SECURITY_STATE_CHANGE (1 << 5) #define CXL_MBOX_BACKGROUND_OPERATION (1 << 6) +#define CXL_MBOX_BACKGROUND_OPERATION_ABORT (1 << 7) +#define CXL_MBOX_SECONDARY_MBOX_SUPPORTED (1 << 8) +#define CXL_MBOX_REQUEST_ABORT_BACKGROUND_OP_SUPPORTED (1 << 9) +#define CXL_MBOX_CEL_10_TO_11_VALID (1 << 10) +#define CXL_MBOX_CONFIG_CHANGE_CONV_RESET (1 << 11) +#define CXL_MBOX_CONFIG_CHANGE_CXL_RESET (1 << 12) #endif diff --git a/include/hw/display/bcm2835_fb.h b/include/hw/display/bcm2835_fb.h index 49541bf..acc9230 100644 --- a/include/hw/display/bcm2835_fb.h +++ b/include/hw/display/bcm2835_fb.h @@ -13,7 +13,6 @@ #define BCM2835_FB_H #include "hw/sysbus.h" -#include "ui/console.h" #include "qom/object.h" #define UPPER_RAM_BASE 0x40000000 diff --git a/include/hw/display/edid.h b/include/hw/display/edid.h index 520f8ec..91c0a42 100644 --- a/include/hw/display/edid.h +++ b/include/hw/display/edid.h @@ -1,6 +1,8 @@ #ifndef EDID_H #define EDID_H +#define EDID_NAME_MAX_LENGTH 12 + typedef struct qemu_edid_info { const char *vendor; /* http://www.uefi.org/pnp_id_list */ const char *name; diff --git a/include/hw/display/macfb.h b/include/hw/display/macfb.h index 27cebef..0fae1f3 100644 --- a/include/hw/display/macfb.h +++ b/include/hw/display/macfb.h @@ -13,7 +13,7 @@ #ifndef MACFB_H #define MACFB_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/irq.h" #include "hw/nubus/nubus.h" #include "hw/sysbus.h" diff --git a/include/hw/display/ramfb.h b/include/hw/display/ramfb.h index a7e0019..172aa6d 100644 --- a/include/hw/display/ramfb.h +++ b/include/hw/display/ramfb.h @@ -6,7 +6,7 @@ /* ramfb.c */ typedef struct RAMFBState RAMFBState; void ramfb_display_update(QemuConsole *con, RAMFBState *s); -RAMFBState *ramfb_setup(Error **errp); +RAMFBState *ramfb_setup(bool romfile, Error **errp); extern const VMStateDescription ramfb_vmstate; diff --git a/include/hw/display/xlnx_dp.h b/include/hw/display/xlnx_dp.h index e86a87f..af859e4 100644 --- a/include/hw/display/xlnx_dp.h +++ b/include/hw/display/xlnx_dp.h @@ -33,7 +33,7 @@ #include "qemu/fifo8.h" #include "qemu/units.h" #include "hw/dma/xlnx_dpdma.h" -#include "audio/audio.h" +#include "qemu/audio.h" #include "qom/object.h" #include "hw/ptimer.h" @@ -84,7 +84,7 @@ struct XlnxDPState { struct PixmanPlane v_plane; struct PixmanPlane bout_plane; - QEMUSoundCard aud_card; + AudioBackend *audio_be; SWVoiceOut *amixer_output_stream; int16_t audio_buffer_0[AUD_CHBUF_MAX_DEPTH]; int16_t audio_buffer_1[AUD_CHBUF_MAX_DEPTH]; diff --git a/include/hw/dma/i8257.h b/include/hw/dma/i8257.h index 4342e4a..33b6286 100644 --- a/include/hw/dma/i8257.h +++ b/include/hw/dma/i8257.h @@ -2,7 +2,7 @@ #define HW_I8257_H #include "hw/isa/isa.h" -#include "exec/ioport.h" +#include "system/ioport.h" #include "qom/object.h" #define TYPE_I8257 "i8257" diff --git a/include/hw/dma/xlnx_dpdma.h b/include/hw/dma/xlnx_dpdma.h index 1ec0d26..484b2e3 100644 --- a/include/hw/dma/xlnx_dpdma.h +++ b/include/hw/dma/xlnx_dpdma.h @@ -26,7 +26,6 @@ #define XLNX_DPDMA_H #include "hw/sysbus.h" -#include "ui/console.h" #include "system/dma.h" #include "qom/object.h" diff --git a/include/hw/firmware/smbios.h b/include/hw/firmware/smbios.h index f066ab7..3ea732f 100644 --- a/include/hw/firmware/smbios.h +++ b/include/hw/firmware/smbios.h @@ -22,7 +22,7 @@ extern GArray *usr_blobs_sizes; typedef struct { const char *vendor, *version, *date; - bool have_major_minor, uefi; + bool have_major_minor, uefi, vm; uint8_t major, minor; } smbios_type0_t; extern smbios_type0_t smbios_type0; diff --git a/include/hw/fsi/aspeed_apb2opb.h b/include/hw/fsi/aspeed_apb2opb.h index f6a2387..878619e 100644 --- a/include/hw/fsi/aspeed_apb2opb.h +++ b/include/hw/fsi/aspeed_apb2opb.h @@ -8,7 +8,7 @@ #ifndef FSI_ASPEED_APB2OPB_H #define FSI_ASPEED_APB2OPB_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/fsi/fsi-master.h" #include "hw/sysbus.h" diff --git a/include/hw/fsi/cfam.h b/include/hw/fsi/cfam.h index 7abc3b2..cceb4bd 100644 --- a/include/hw/fsi/cfam.h +++ b/include/hw/fsi/cfam.h @@ -7,7 +7,7 @@ #ifndef FSI_CFAM_H #define FSI_CFAM_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/fsi/fsi.h" #include "hw/fsi/lbus.h" diff --git a/include/hw/fsi/fsi-master.h b/include/hw/fsi/fsi-master.h index 68e5f56..b634ecd 100644 --- a/include/hw/fsi/fsi-master.h +++ b/include/hw/fsi/fsi-master.h @@ -7,7 +7,7 @@ #ifndef FSI_FSI_MASTER_H #define FSI_FSI_MASTER_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/qdev-core.h" #include "hw/fsi/fsi.h" #include "hw/fsi/cfam.h" diff --git a/include/hw/fsi/fsi.h b/include/hw/fsi/fsi.h index e00f6ef..f34765e 100644 --- a/include/hw/fsi/fsi.h +++ b/include/hw/fsi/fsi.h @@ -7,7 +7,7 @@ #ifndef FSI_FSI_H #define FSI_FSI_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/qdev-core.h" #include "hw/fsi/lbus.h" #include "qemu/bitops.h" diff --git a/include/hw/fsi/lbus.h b/include/hw/fsi/lbus.h index 558268c..1251907 100644 --- a/include/hw/fsi/lbus.h +++ b/include/hw/fsi/lbus.h @@ -9,7 +9,7 @@ #include "hw/qdev-core.h" #include "qemu/units.h" -#include "exec/memory.h" +#include "system/memory.h" #define TYPE_FSI_LBUS_DEVICE "fsi.lbus.device" OBJECT_DECLARE_SIMPLE_TYPE(FSILBusDevice, FSI_LBUS_DEVICE) diff --git a/include/hw/gpio/aspeed_gpio.h b/include/hw/gpio/aspeed_gpio.h index e1e6c54..e6b2fe7 100644 --- a/include/hw/gpio/aspeed_gpio.h +++ b/include/hw/gpio/aspeed_gpio.h @@ -70,7 +70,7 @@ typedef struct AspeedGPIOReg { } AspeedGPIOReg; struct AspeedGPIOClass { - SysBusDevice parent_obj; + SysBusDeviceClass parent_class; const GPIOSetProperties *props; uint32_t nr_gpio_pins; uint32_t nr_gpio_sets; diff --git a/include/hw/gpio/npcm7xx_gpio.h b/include/hw/gpio/npcm7xx_gpio.h index b1d771b..7c0bf61 100644 --- a/include/hw/gpio/npcm7xx_gpio.h +++ b/include/hw/gpio/npcm7xx_gpio.h @@ -15,7 +15,7 @@ #ifndef NPCM7XX_GPIO_H #define NPCM7XX_GPIO_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/sysbus.h" /* Number of pins managed by each controller. */ diff --git a/include/hw/hw.h b/include/hw/hw.h index 045c1c8..1b33d12 100644 --- a/include/hw/hw.h +++ b/include/hw/hw.h @@ -1,10 +1,6 @@ #ifndef QEMU_HW_H #define QEMU_HW_H -#ifdef CONFIG_USER_ONLY -#error Cannot include hw/hw.h from user emulation -#endif - G_NORETURN void hw_error(const char *fmt, ...) G_GNUC_PRINTF(1, 2); #endif diff --git a/include/hw/hyperv/hvgdk.h b/include/hw/hyperv/hvgdk.h new file mode 100644 index 0000000..71161f4 --- /dev/null +++ b/include/hw/hyperv/hvgdk.h @@ -0,0 +1,20 @@ +/* + * Type definitions for the mshv guest interface. + * + * Copyright Microsoft, Corp. 2025 + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_HYPERV_HVGDK_H +#define HW_HYPERV_HVGDK_H + +#define HVGDK_H_VERSION (25125) + +enum hv_unimplemented_msr_action { + HV_UNIMPLEMENTED_MSR_ACTION_FAULT = 0, + HV_UNIMPLEMENTED_MSR_ACTION_IGNORE_WRITE_READ_ZERO = 1, + HV_UNIMPLEMENTED_MSR_ACTION_COUNT = 2, +}; + +#endif /* HW_HYPERV_HVGDK_H */ diff --git a/include/hw/hyperv/hvgdk_mini.h b/include/hw/hyperv/hvgdk_mini.h new file mode 100644 index 0000000..d89315f --- /dev/null +++ b/include/hw/hyperv/hvgdk_mini.h @@ -0,0 +1,817 @@ +/* + * Userspace interfaces for /dev/mshv* devices and derived fds + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_HYPERV_HVGDK_MINI_H +#define HW_HYPERV_HVGDK_MINI_H + +#define MSHV_IOCTL 0xB8 + +typedef enum hv_register_name { + /* Pending Interruption Register */ + HV_REGISTER_PENDING_INTERRUPTION = 0x00010002, + + /* X64 User-Mode Registers */ + HV_X64_REGISTER_RAX = 0x00020000, + HV_X64_REGISTER_RCX = 0x00020001, + HV_X64_REGISTER_RDX = 0x00020002, + HV_X64_REGISTER_RBX = 0x00020003, + HV_X64_REGISTER_RSP = 0x00020004, + HV_X64_REGISTER_RBP = 0x00020005, + HV_X64_REGISTER_RSI = 0x00020006, + HV_X64_REGISTER_RDI = 0x00020007, + HV_X64_REGISTER_R8 = 0x00020008, + HV_X64_REGISTER_R9 = 0x00020009, + HV_X64_REGISTER_R10 = 0x0002000A, + HV_X64_REGISTER_R11 = 0x0002000B, + HV_X64_REGISTER_R12 = 0x0002000C, + HV_X64_REGISTER_R13 = 0x0002000D, + HV_X64_REGISTER_R14 = 0x0002000E, + HV_X64_REGISTER_R15 = 0x0002000F, + HV_X64_REGISTER_RIP = 0x00020010, + HV_X64_REGISTER_RFLAGS = 0x00020011, + + /* X64 Floating Point and Vector Registers */ + HV_X64_REGISTER_XMM0 = 0x00030000, + HV_X64_REGISTER_XMM1 = 0x00030001, + HV_X64_REGISTER_XMM2 = 0x00030002, + HV_X64_REGISTER_XMM3 = 0x00030003, + HV_X64_REGISTER_XMM4 = 0x00030004, + HV_X64_REGISTER_XMM5 = 0x00030005, + HV_X64_REGISTER_XMM6 = 0x00030006, + HV_X64_REGISTER_XMM7 = 0x00030007, + HV_X64_REGISTER_XMM8 = 0x00030008, + HV_X64_REGISTER_XMM9 = 0x00030009, + HV_X64_REGISTER_XMM10 = 0x0003000A, + HV_X64_REGISTER_XMM11 = 0x0003000B, + HV_X64_REGISTER_XMM12 = 0x0003000C, + HV_X64_REGISTER_XMM13 = 0x0003000D, + HV_X64_REGISTER_XMM14 = 0x0003000E, + HV_X64_REGISTER_XMM15 = 0x0003000F, + HV_X64_REGISTER_FP_MMX0 = 0x00030010, + HV_X64_REGISTER_FP_MMX1 = 0x00030011, + HV_X64_REGISTER_FP_MMX2 = 0x00030012, + HV_X64_REGISTER_FP_MMX3 = 0x00030013, + HV_X64_REGISTER_FP_MMX4 = 0x00030014, + HV_X64_REGISTER_FP_MMX5 = 0x00030015, + HV_X64_REGISTER_FP_MMX6 = 0x00030016, + HV_X64_REGISTER_FP_MMX7 = 0x00030017, + HV_X64_REGISTER_FP_CONTROL_STATUS = 0x00030018, + HV_X64_REGISTER_XMM_CONTROL_STATUS = 0x00030019, + + /* X64 Control Registers */ + HV_X64_REGISTER_CR0 = 0x00040000, + HV_X64_REGISTER_CR2 = 0x00040001, + HV_X64_REGISTER_CR3 = 0x00040002, + HV_X64_REGISTER_CR4 = 0x00040003, + HV_X64_REGISTER_CR8 = 0x00040004, + HV_X64_REGISTER_XFEM = 0x00040005, + + /* X64 Segment Registers */ + HV_X64_REGISTER_ES = 0x00060000, + HV_X64_REGISTER_CS = 0x00060001, + HV_X64_REGISTER_SS = 0x00060002, + HV_X64_REGISTER_DS = 0x00060003, + HV_X64_REGISTER_FS = 0x00060004, + HV_X64_REGISTER_GS = 0x00060005, + HV_X64_REGISTER_LDTR = 0x00060006, + HV_X64_REGISTER_TR = 0x00060007, + + /* X64 Table Registers */ + HV_X64_REGISTER_IDTR = 0x00070000, + HV_X64_REGISTER_GDTR = 0x00070001, + + /* X64 Virtualized MSRs */ + HV_X64_REGISTER_TSC = 0x00080000, + HV_X64_REGISTER_EFER = 0x00080001, + HV_X64_REGISTER_KERNEL_GS_BASE = 0x00080002, + HV_X64_REGISTER_APIC_BASE = 0x00080003, + HV_X64_REGISTER_PAT = 0x00080004, + HV_X64_REGISTER_SYSENTER_CS = 0x00080005, + HV_X64_REGISTER_SYSENTER_EIP = 0x00080006, + HV_X64_REGISTER_SYSENTER_ESP = 0x00080007, + HV_X64_REGISTER_STAR = 0x00080008, + HV_X64_REGISTER_LSTAR = 0x00080009, + HV_X64_REGISTER_CSTAR = 0x0008000A, + HV_X64_REGISTER_SFMASK = 0x0008000B, + HV_X64_REGISTER_INITIAL_APIC_ID = 0x0008000C, + + /* X64 Cache control MSRs */ + HV_X64_REGISTER_MSR_MTRR_CAP = 0x0008000D, + HV_X64_REGISTER_MSR_MTRR_DEF_TYPE = 0x0008000E, + HV_X64_REGISTER_MSR_MTRR_PHYS_BASE0 = 0x00080010, + HV_X64_REGISTER_MSR_MTRR_PHYS_BASE1 = 0x00080011, + HV_X64_REGISTER_MSR_MTRR_PHYS_BASE2 = 0x00080012, + HV_X64_REGISTER_MSR_MTRR_PHYS_BASE3 = 0x00080013, + HV_X64_REGISTER_MSR_MTRR_PHYS_BASE4 = 0x00080014, + HV_X64_REGISTER_MSR_MTRR_PHYS_BASE5 = 0x00080015, + HV_X64_REGISTER_MSR_MTRR_PHYS_BASE6 = 0x00080016, + HV_X64_REGISTER_MSR_MTRR_PHYS_BASE7 = 0x00080017, + HV_X64_REGISTER_MSR_MTRR_PHYS_BASE8 = 0x00080018, + HV_X64_REGISTER_MSR_MTRR_PHYS_BASE9 = 0x00080019, + HV_X64_REGISTER_MSR_MTRR_PHYS_BASEA = 0x0008001A, + HV_X64_REGISTER_MSR_MTRR_PHYS_BASEB = 0x0008001B, + HV_X64_REGISTER_MSR_MTRR_PHYS_BASEC = 0x0008001C, + HV_X64_REGISTER_MSR_MTRR_PHYS_BASED = 0x0008001D, + HV_X64_REGISTER_MSR_MTRR_PHYS_BASEE = 0x0008001E, + HV_X64_REGISTER_MSR_MTRR_PHYS_BASEF = 0x0008001F, + HV_X64_REGISTER_MSR_MTRR_PHYS_MASK0 = 0x00080040, + HV_X64_REGISTER_MSR_MTRR_PHYS_MASK1 = 0x00080041, + HV_X64_REGISTER_MSR_MTRR_PHYS_MASK2 = 0x00080042, + HV_X64_REGISTER_MSR_MTRR_PHYS_MASK3 = 0x00080043, + HV_X64_REGISTER_MSR_MTRR_PHYS_MASK4 = 0x00080044, + HV_X64_REGISTER_MSR_MTRR_PHYS_MASK5 = 0x00080045, + HV_X64_REGISTER_MSR_MTRR_PHYS_MASK6 = 0x00080046, + HV_X64_REGISTER_MSR_MTRR_PHYS_MASK7 = 0x00080047, + HV_X64_REGISTER_MSR_MTRR_PHYS_MASK8 = 0x00080048, + HV_X64_REGISTER_MSR_MTRR_PHYS_MASK9 = 0x00080049, + HV_X64_REGISTER_MSR_MTRR_PHYS_MASKA = 0x0008004A, + HV_X64_REGISTER_MSR_MTRR_PHYS_MASKB = 0x0008004B, + HV_X64_REGISTER_MSR_MTRR_PHYS_MASKC = 0x0008004C, + HV_X64_REGISTER_MSR_MTRR_PHYS_MASKD = 0x0008004D, + HV_X64_REGISTER_MSR_MTRR_PHYS_MASKE = 0x0008004E, + HV_X64_REGISTER_MSR_MTRR_PHYS_MASKF = 0x0008004F, + HV_X64_REGISTER_MSR_MTRR_FIX64K00000 = 0x00080070, + HV_X64_REGISTER_MSR_MTRR_FIX16K80000 = 0x00080071, + HV_X64_REGISTER_MSR_MTRR_FIX16KA0000 = 0x00080072, + HV_X64_REGISTER_MSR_MTRR_FIX4KC0000 = 0x00080073, + HV_X64_REGISTER_MSR_MTRR_FIX4KC8000 = 0x00080074, + HV_X64_REGISTER_MSR_MTRR_FIX4KD0000 = 0x00080075, + HV_X64_REGISTER_MSR_MTRR_FIX4KD8000 = 0x00080076, + HV_X64_REGISTER_MSR_MTRR_FIX4KE0000 = 0x00080077, + HV_X64_REGISTER_MSR_MTRR_FIX4KE8000 = 0x00080078, + HV_X64_REGISTER_MSR_MTRR_FIX4KF0000 = 0x00080079, + HV_X64_REGISTER_MSR_MTRR_FIX4KF8000 = 0x0008007A, + + HV_X64_REGISTER_TSC_AUX = 0x0008007B, + HV_X64_REGISTER_BNDCFGS = 0x0008007C, + HV_X64_REGISTER_DEBUG_CTL = 0x0008007D, + + /* Available */ + + HV_X64_REGISTER_SPEC_CTRL = 0x00080084, + HV_X64_REGISTER_TSC_ADJUST = 0x00080096, + + /* Other MSRs */ + HV_X64_REGISTER_MSR_IA32_MISC_ENABLE = 0x000800A0, + + /* Misc */ + HV_REGISTER_GUEST_OS_ID = 0x00090002, + HV_REGISTER_REFERENCE_TSC = 0x00090017, + + /* Hypervisor-defined Registers (Synic) */ + HV_REGISTER_SINT0 = 0x000A0000, + HV_REGISTER_SINT1 = 0x000A0001, + HV_REGISTER_SINT2 = 0x000A0002, + HV_REGISTER_SINT3 = 0x000A0003, + HV_REGISTER_SINT4 = 0x000A0004, + HV_REGISTER_SINT5 = 0x000A0005, + HV_REGISTER_SINT6 = 0x000A0006, + HV_REGISTER_SINT7 = 0x000A0007, + HV_REGISTER_SINT8 = 0x000A0008, + HV_REGISTER_SINT9 = 0x000A0009, + HV_REGISTER_SINT10 = 0x000A000A, + HV_REGISTER_SINT11 = 0x000A000B, + HV_REGISTER_SINT12 = 0x000A000C, + HV_REGISTER_SINT13 = 0x000A000D, + HV_REGISTER_SINT14 = 0x000A000E, + HV_REGISTER_SINT15 = 0x000A000F, + HV_REGISTER_SCONTROL = 0x000A0010, + HV_REGISTER_SVERSION = 0x000A0011, + HV_REGISTER_SIEFP = 0x000A0012, + HV_REGISTER_SIMP = 0x000A0013, + HV_REGISTER_EOM = 0x000A0014, + HV_REGISTER_SIRBP = 0x000A0015, +} hv_register_name; + +enum hv_intercept_type { + HV_INTERCEPT_TYPE_X64_IO_PORT = 0X00000000, + HV_INTERCEPT_TYPE_X64_MSR = 0X00000001, + HV_INTERCEPT_TYPE_X64_CPUID = 0X00000002, + HV_INTERCEPT_TYPE_EXCEPTION = 0X00000003, + + /* Used to be HV_INTERCEPT_TYPE_REGISTER */ + HV_INTERCEPT_TYPE_RESERVED0 = 0X00000004, + HV_INTERCEPT_TYPE_MMIO = 0X00000005, + HV_INTERCEPT_TYPE_X64_GLOBAL_CPUID = 0X00000006, + HV_INTERCEPT_TYPE_X64_APIC_SMI = 0X00000007, + HV_INTERCEPT_TYPE_HYPERCALL = 0X00000008, + + HV_INTERCEPT_TYPE_X64_APIC_INIT_SIPI = 0X00000009, + HV_INTERCEPT_MC_UPDATE_PATCH_LEVEL_MSR_READ = 0X0000000A, + + HV_INTERCEPT_TYPE_X64_APIC_WRITE = 0X0000000B, + HV_INTERCEPT_TYPE_X64_MSR_INDEX = 0X0000000C, + HV_INTERCEPT_TYPE_MAX, + HV_INTERCEPT_TYPE_INVALID = 0XFFFFFFFF, +}; + +struct hv_u128 { + uint64_t low_part; + uint64_t high_part; +}; + +union hv_x64_xmm_control_status_register { + struct hv_u128 as_uint128; + struct { + union { + /* long mode */ + uint64_t last_fp_rdp; + /* 32 bit mode */ + struct { + uint32_t last_fp_dp; + uint16_t last_fp_ds; + uint16_t padding; + }; + }; + uint32_t xmm_status_control; + uint32_t xmm_status_control_mask; + }; +}; + +union hv_x64_fp_register { + struct hv_u128 as_uint128; + struct { + uint64_t mantissa; + uint64_t biased_exponent:15; + uint64_t sign:1; + uint64_t reserved:48; + }; +}; + +union hv_x64_pending_exception_event { + uint64_t as_uint64[2]; + struct { + uint32_t event_pending:1; + uint32_t event_type:3; + uint32_t reserved0:4; + uint32_t deliver_error_code:1; + uint32_t reserved1:7; + uint32_t vector:16; + uint32_t error_code; + uint64_t exception_parameter; + }; +}; + +union hv_x64_pending_virtualization_fault_event { + uint64_t as_uint64[2]; + struct { + uint32_t event_pending:1; + uint32_t event_type:3; + uint32_t reserved0:4; + uint32_t reserved1:8; + uint32_t parameter0:16; + uint32_t code; + uint64_t parameter1; + }; +}; + +union hv_x64_pending_interruption_register { + uint64_t as_uint64; + struct { + uint32_t interruption_pending:1; + uint32_t interruption_type:3; + uint32_t deliver_error_code:1; + uint32_t instruction_length:4; + uint32_t nested_event:1; + uint32_t reserved:6; + uint32_t interruption_vector:16; + uint32_t error_code; + }; +}; + +union hv_x64_register_sev_control { + uint64_t as_uint64; + struct { + uint64_t enable_encrypted_state:1; + uint64_t reserved_z:11; + uint64_t vmsa_gpa_page_number:52; + }; +}; + +union hv_x64_msr_npiep_config_contents { + uint64_t as_uint64; + struct { + /* + * These bits enable instruction execution prevention for + * specific instructions. + */ + uint64_t prevents_gdt:1; + uint64_t prevents_idt:1; + uint64_t prevents_ldt:1; + uint64_t prevents_tr:1; + + /* The reserved bits must always be 0. */ + uint64_t reserved:60; + }; +}; + +typedef struct hv_x64_segment_register { + uint64_t base; + uint32_t limit; + uint16_t selector; + union { + struct { + uint16_t segment_type:4; + uint16_t non_system_segment:1; + uint16_t descriptor_privilege_level:2; + uint16_t present:1; + uint16_t reserved:4; + uint16_t available:1; + uint16_t _long:1; + uint16_t _default:1; + uint16_t granularity:1; + }; + uint16_t attributes; + }; +} hv_x64_segment_register; + +typedef struct hv_x64_table_register { + uint16_t pad[3]; + uint16_t limit; + uint64_t base; +} hv_x64_table_register; + +union hv_x64_fp_control_status_register { + struct hv_u128 as_uint128; + struct { + uint16_t fp_control; + uint16_t fp_status; + uint8_t fp_tag; + uint8_t reserved; + uint16_t last_fp_op; + union { + /* long mode */ + uint64_t last_fp_rip; + /* 32 bit mode */ + struct { + uint32_t last_fp_eip; + uint16_t last_fp_cs; + uint16_t padding; + }; + }; + }; +}; + +/* General Hypervisor Register Content Definitions */ + +union hv_explicit_suspend_register { + uint64_t as_uint64; + struct { + uint64_t suspended:1; + uint64_t reserved:63; + }; +}; + +union hv_internal_activity_register { + uint64_t as_uint64; + + struct { + uint64_t startup_suspend:1; + uint64_t halt_suspend:1; + uint64_t idle_suspend:1; + uint64_t rsvd_z:61; + }; +}; + +union hv_x64_interrupt_state_register { + uint64_t as_uint64; + struct { + uint64_t interrupt_shadow:1; + uint64_t nmi_masked:1; + uint64_t reserved:62; + }; +}; + +union hv_intercept_suspend_register { + uint64_t as_uint64; + struct { + uint64_t suspended:1; + uint64_t reserved:63; + }; +}; + +typedef union hv_register_value { + struct hv_u128 reg128; + uint64_t reg64; + uint32_t reg32; + uint16_t reg16; + uint8_t reg8; + union hv_x64_fp_register fp; + union hv_x64_fp_control_status_register fp_control_status; + union hv_x64_xmm_control_status_register xmm_control_status; + struct hv_x64_segment_register segment; + struct hv_x64_table_register table; + union hv_explicit_suspend_register explicit_suspend; + union hv_intercept_suspend_register intercept_suspend; + union hv_internal_activity_register internal_activity; + union hv_x64_interrupt_state_register interrupt_state; + union hv_x64_pending_interruption_register pending_interruption; + union hv_x64_msr_npiep_config_contents npiep_config; + union hv_x64_pending_exception_event pending_exception_event; + union hv_x64_pending_virtualization_fault_event + pending_virtualization_fault_event; + union hv_x64_register_sev_control sev_control; +} hv_register_value; + +typedef struct hv_register_assoc { + uint32_t name; /* enum hv_register_name */ + uint32_t reserved1; + uint64_t reserved2; + union hv_register_value value; +} hv_register_assoc; + +union hv_input_vtl { + uint8_t as_uint8; + struct { + uint8_t target_vtl:4; + uint8_t use_target_vtl:1; + uint8_t reserved_z:3; + }; +}; + +typedef struct hv_input_get_vp_registers { + uint64_t partition_id; + uint32_t vp_index; + union hv_input_vtl input_vtl; + uint8_t rsvd_z8; + uint16_t rsvd_z16; + uint32_t names[]; +} hv_input_get_vp_registers; + +typedef struct hv_input_set_vp_registers { + uint64_t partition_id; + uint32_t vp_index; + union hv_input_vtl input_vtl; + uint8_t rsvd_z8; + uint16_t rsvd_z16; + struct hv_register_assoc elements[]; +} hv_input_set_vp_registers; + +#define MSHV_VP_MAX_REGISTERS 128 + +struct mshv_vp_registers { + int count; /* at most MSHV_VP_MAX_REGISTERS */ + struct hv_register_assoc *regs; +}; + +union hv_interrupt_control { + uint64_t as_uint64; + struct { + uint32_t interrupt_type; /* enum hv_interrupt type */ + uint32_t level_triggered:1; + uint32_t logical_dest_mode:1; + uint32_t rsvd:30; + }; +}; + +struct hv_input_assert_virtual_interrupt { + uint64_t partition_id; + union hv_interrupt_control control; + uint64_t dest_addr; /* cpu's apic id */ + uint32_t vector; + uint8_t target_vtl; + uint8_t rsvd_z0; + uint16_t rsvd_z1; +}; + +/* /dev/mshv */ +#define MSHV_CREATE_PARTITION _IOW(MSHV_IOCTL, 0x00, struct mshv_create_partition) +#define MSHV_CREATE_VP _IOW(MSHV_IOCTL, 0x01, struct mshv_create_vp) + +/* Partition fds created with MSHV_CREATE_PARTITION */ +#define MSHV_INITIALIZE_PARTITION _IO(MSHV_IOCTL, 0x00) +#define MSHV_SET_GUEST_MEMORY _IOW(MSHV_IOCTL, 0x02, struct mshv_user_mem_region) +#define MSHV_IRQFD _IOW(MSHV_IOCTL, 0x03, struct mshv_user_irqfd) +#define MSHV_IOEVENTFD _IOW(MSHV_IOCTL, 0x04, struct mshv_user_ioeventfd) +#define MSHV_SET_MSI_ROUTING _IOW(MSHV_IOCTL, 0x05, struct mshv_user_irq_table) + +/* + ******************************** + * VP APIs for child partitions * + ******************************** + */ + +struct hv_local_interrupt_controller_state { + /* HV_X64_INTERRUPT_CONTROLLER_STATE */ + uint32_t apic_id; + uint32_t apic_version; + uint32_t apic_ldr; + uint32_t apic_dfr; + uint32_t apic_spurious; + uint32_t apic_isr[8]; + uint32_t apic_tmr[8]; + uint32_t apic_irr[8]; + uint32_t apic_esr; + uint32_t apic_icr_high; + uint32_t apic_icr_low; + uint32_t apic_lvt_timer; + uint32_t apic_lvt_thermal; + uint32_t apic_lvt_perfmon; + uint32_t apic_lvt_lint0; + uint32_t apic_lvt_lint1; + uint32_t apic_lvt_error; + uint32_t apic_lvt_cmci; + uint32_t apic_error_status; + uint32_t apic_initial_count; + uint32_t apic_counter_value; + uint32_t apic_divide_configuration; + uint32_t apic_remote_read; +}; + +/* Generic hypercall */ +#define MSHV_ROOT_HVCALL _IOWR(MSHV_IOCTL, 0x07, struct mshv_root_hvcall) + +/* From hvgdk_mini.h */ + +#define HV_X64_MSR_GUEST_OS_ID 0x40000000 +#define HV_X64_MSR_SINT0 0x40000090 +#define HV_X64_MSR_SINT1 0x40000091 +#define HV_X64_MSR_SINT2 0x40000092 +#define HV_X64_MSR_SINT3 0x40000093 +#define HV_X64_MSR_SINT4 0x40000094 +#define HV_X64_MSR_SINT5 0x40000095 +#define HV_X64_MSR_SINT6 0x40000096 +#define HV_X64_MSR_SINT7 0x40000097 +#define HV_X64_MSR_SINT8 0x40000098 +#define HV_X64_MSR_SINT9 0x40000099 +#define HV_X64_MSR_SINT10 0x4000009A +#define HV_X64_MSR_SINT11 0x4000009B +#define HV_X64_MSR_SINT12 0x4000009C +#define HV_X64_MSR_SINT13 0x4000009D +#define HV_X64_MSR_SINT14 0x4000009E +#define HV_X64_MSR_SINT15 0x4000009F +#define HV_X64_MSR_SCONTROL 0x40000080 +#define HV_X64_MSR_SIEFP 0x40000082 +#define HV_X64_MSR_SIMP 0x40000083 +#define HV_X64_MSR_REFERENCE_TSC 0x40000021 +#define HV_X64_MSR_EOM 0x40000084 + +/* Define port identifier type. */ +union hv_port_id { + uint32_t asuint32_t; + struct { + uint32_t id:24; + uint32_t reserved:8; + }; +}; + +#define HV_MESSAGE_SIZE (256) +#define HV_MESSAGE_PAYLOAD_BYTE_COUNT (240) +#define HV_MESSAGE_PAYLOAD_QWORD_COUNT (30) + +/* Define hypervisor message types. */ +enum hv_message_type { + HVMSG_NONE = 0x00000000, + + /* Memory access messages. */ + HVMSG_UNMAPPED_GPA = 0x80000000, + HVMSG_GPA_INTERCEPT = 0x80000001, + HVMSG_UNACCEPTED_GPA = 0x80000003, + HVMSG_GPA_ATTRIBUTE_INTERCEPT = 0x80000004, + + /* Timer notification messages. */ + HVMSG_TIMER_EXPIRED = 0x80000010, + + /* Error messages. */ + HVMSG_INVALID_VP_REGISTER_VALUE = 0x80000020, + HVMSG_UNRECOVERABLE_EXCEPTION = 0x80000021, + HVMSG_UNSUPPORTED_FEATURE = 0x80000022, + + /* + * Opaque intercept message. The original intercept message is only + * accessible from the mapped intercept message page. + */ + HVMSG_OPAQUE_INTERCEPT = 0x8000003F, + + /* Trace buffer complete messages. */ + HVMSG_EVENTLOG_BUFFERCOMPLETE = 0x80000040, + + /* Hypercall intercept */ + HVMSG_HYPERCALL_INTERCEPT = 0x80000050, + + /* SynIC intercepts */ + HVMSG_SYNIC_EVENT_INTERCEPT = 0x80000060, + HVMSG_SYNIC_SINT_INTERCEPT = 0x80000061, + HVMSG_SYNIC_SINT_DELIVERABLE = 0x80000062, + + /* Async call completion intercept */ + HVMSG_ASYNC_CALL_COMPLETION = 0x80000070, + + /* Root scheduler messages */ + HVMSG_SCHEDULER_VP_SIGNAL_BITSE = 0x80000100, + HVMSG_SCHEDULER_VP_SIGNAL_PAIR = 0x80000101, + + /* Platform-specific processor intercept messages. */ + HVMSG_X64_IO_PORT_INTERCEPT = 0x80010000, + HVMSG_X64_MSR_INTERCEPT = 0x80010001, + HVMSG_X64_CPUID_INTERCEPT = 0x80010002, + HVMSG_X64_EXCEPTION_INTERCEPT = 0x80010003, + HVMSG_X64_APIC_EOI = 0x80010004, + HVMSG_X64_LEGACY_FP_ERROR = 0x80010005, + HVMSG_X64_IOMMU_PRQ = 0x80010006, + HVMSG_X64_HALT = 0x80010007, + HVMSG_X64_INTERRUPTION_DELIVERABLE = 0x80010008, + HVMSG_X64_SIPI_INTERCEPT = 0x80010009, + HVMSG_X64_SEV_VMGEXIT_INTERCEPT = 0x80010013, +}; + +union hv_x64_vp_execution_state { + uint16_t as_uint16; + struct { + uint16_t cpl:2; + uint16_t cr0_pe:1; + uint16_t cr0_am:1; + uint16_t efer_lma:1; + uint16_t debug_active:1; + uint16_t interruption_pending:1; + uint16_t vtl:4; + uint16_t enclave_mode:1; + uint16_t interrupt_shadow:1; + uint16_t virtualization_fault_active:1; + uint16_t reserved:2; + }; +}; + +/* From openvmm::hvdef */ +enum hv_x64_intercept_access_type { + HV_X64_INTERCEPT_ACCESS_TYPE_READ = 0, + HV_X64_INTERCEPT_ACCESS_TYPE_WRITE = 1, + HV_X64_INTERCEPT_ACCESS_TYPE_EXECUTE = 2, +}; + +struct hv_x64_intercept_message_header { + uint32_t vp_index; + uint8_t instruction_length:4; + uint8_t cr8:4; /* Only set for exo partitions */ + uint8_t intercept_access_type; + union hv_x64_vp_execution_state execution_state; + struct hv_x64_segment_register cs_segment; + uint64_t rip; + uint64_t rflags; +}; + +union hv_x64_io_port_access_info { + uint8_t as_uint8; + struct { + uint8_t access_size:3; + uint8_t string_op:1; + uint8_t rep_prefix:1; + uint8_t reserved:3; + }; +}; + +typedef struct hv_x64_io_port_intercept_message { + struct hv_x64_intercept_message_header header; + uint16_t port_number; + union hv_x64_io_port_access_info access_info; + uint8_t instruction_byte_count; + uint32_t reserved; + uint64_t rax; + uint8_t instruction_bytes[16]; + struct hv_x64_segment_register ds_segment; + struct hv_x64_segment_register es_segment; + uint64_t rcx; + uint64_t rsi; + uint64_t rdi; +} hv_x64_io_port_intercept_message; + +union hv_x64_memory_access_info { + uint8_t as_uint8; + struct { + uint8_t gva_valid:1; + uint8_t gva_gpa_valid:1; + uint8_t hypercall_output_pending:1; + uint8_t tlb_locked_no_overlay:1; + uint8_t reserved:4; + }; +}; + +struct hv_x64_memory_intercept_message { + struct hv_x64_intercept_message_header header; + uint32_t cache_type; /* enum hv_cache_type */ + uint8_t instruction_byte_count; + union hv_x64_memory_access_info memory_access_info; + uint8_t tpr_priority; + uint8_t reserved1; + uint64_t guest_virtual_address; + uint64_t guest_physical_address; + uint8_t instruction_bytes[16]; +}; + +union hv_message_flags { + uint8_t asu8; + struct { + uint8_t msg_pending:1; + uint8_t reserved:7; + }; +}; + +struct hv_message_header { + uint32_t message_type; + uint8_t payload_size; + union hv_message_flags message_flags; + uint8_t reserved[2]; + union { + uint64_t sender; + union hv_port_id port; + }; +}; + +struct hv_message { + struct hv_message_header header; + union { + uint64_t payload[HV_MESSAGE_PAYLOAD_QWORD_COUNT]; + } u; +}; + +/* From github.com/rust-vmm/mshv-bindings/src/x86_64/regs.rs */ + +struct hv_cpuid_entry { + uint32_t function; + uint32_t index; + uint32_t flags; + uint32_t eax; + uint32_t ebx; + uint32_t ecx; + uint32_t edx; + uint32_t padding[3]; +}; + +struct hv_cpuid { + uint32_t nent; + uint32_t padding; + struct hv_cpuid_entry entries[0]; +}; + +#define IA32_MSR_TSC 0x00000010 +#define IA32_MSR_EFER 0xC0000080 +#define IA32_MSR_KERNEL_GS_BASE 0xC0000102 +#define IA32_MSR_APIC_BASE 0x0000001B +#define IA32_MSR_PAT 0x0277 +#define IA32_MSR_SYSENTER_CS 0x00000174 +#define IA32_MSR_SYSENTER_ESP 0x00000175 +#define IA32_MSR_SYSENTER_EIP 0x00000176 +#define IA32_MSR_STAR 0xC0000081 +#define IA32_MSR_LSTAR 0xC0000082 +#define IA32_MSR_CSTAR 0xC0000083 +#define IA32_MSR_SFMASK 0xC0000084 + +#define IA32_MSR_MTRR_CAP 0x00FE +#define IA32_MSR_MTRR_DEF_TYPE 0x02FF +#define IA32_MSR_MTRR_PHYSBASE0 0x0200 +#define IA32_MSR_MTRR_PHYSMASK0 0x0201 +#define IA32_MSR_MTRR_PHYSBASE1 0x0202 +#define IA32_MSR_MTRR_PHYSMASK1 0x0203 +#define IA32_MSR_MTRR_PHYSBASE2 0x0204 +#define IA32_MSR_MTRR_PHYSMASK2 0x0205 +#define IA32_MSR_MTRR_PHYSBASE3 0x0206 +#define IA32_MSR_MTRR_PHYSMASK3 0x0207 +#define IA32_MSR_MTRR_PHYSBASE4 0x0208 +#define IA32_MSR_MTRR_PHYSMASK4 0x0209 +#define IA32_MSR_MTRR_PHYSBASE5 0x020A +#define IA32_MSR_MTRR_PHYSMASK5 0x020B +#define IA32_MSR_MTRR_PHYSBASE6 0x020C +#define IA32_MSR_MTRR_PHYSMASK6 0x020D +#define IA32_MSR_MTRR_PHYSBASE7 0x020E +#define IA32_MSR_MTRR_PHYSMASK7 0x020F + +#define IA32_MSR_MTRR_FIX64K_00000 0x0250 +#define IA32_MSR_MTRR_FIX16K_80000 0x0258 +#define IA32_MSR_MTRR_FIX16K_A0000 0x0259 +#define IA32_MSR_MTRR_FIX4K_C0000 0x0268 +#define IA32_MSR_MTRR_FIX4K_C8000 0x0269 +#define IA32_MSR_MTRR_FIX4K_D0000 0x026A +#define IA32_MSR_MTRR_FIX4K_D8000 0x026B +#define IA32_MSR_MTRR_FIX4K_E0000 0x026C +#define IA32_MSR_MTRR_FIX4K_E8000 0x026D +#define IA32_MSR_MTRR_FIX4K_F0000 0x026E +#define IA32_MSR_MTRR_FIX4K_F8000 0x026F + +#define IA32_MSR_TSC_AUX 0xC0000103 +#define IA32_MSR_BNDCFGS 0x00000d90 +#define IA32_MSR_DEBUG_CTL 0x1D9 +#define IA32_MSR_SPEC_CTRL 0x00000048 +#define IA32_MSR_TSC_ADJUST 0x0000003b + +#define IA32_MSR_MISC_ENABLE 0x000001a0 + +#define HV_TRANSLATE_GVA_VALIDATE_READ (0x0001) +#define HV_TRANSLATE_GVA_VALIDATE_WRITE (0x0002) +#define HV_TRANSLATE_GVA_VALIDATE_EXECUTE (0x0004) + +#define HV_HYP_PAGE_SHIFT 12 +#define HV_HYP_PAGE_SIZE BIT(HV_HYP_PAGE_SHIFT) +#define HV_HYP_PAGE_MASK (~(HV_HYP_PAGE_SIZE - 1)) + +#define HVCALL_GET_PARTITION_PROPERTY 0x0044 +#define HVCALL_SET_PARTITION_PROPERTY 0x0045 +#define HVCALL_GET_VP_REGISTERS 0x0050 +#define HVCALL_SET_VP_REGISTERS 0x0051 +#define HVCALL_TRANSLATE_VIRTUAL_ADDRESS 0x0052 +#define HVCALL_REGISTER_INTERCEPT_RESULT 0x0091 +#define HVCALL_ASSERT_VIRTUAL_INTERRUPT 0x0094 + +#endif /* HW_HYPERV_HVGDK_MINI_H */ diff --git a/include/hw/hyperv/hvhdk.h b/include/hw/hyperv/hvhdk.h new file mode 100644 index 0000000..866c821 --- /dev/null +++ b/include/hw/hyperv/hvhdk.h @@ -0,0 +1,249 @@ +/* + * Type definitions for the mshv host. + * + * Copyright Microsoft, Corp. 2025 + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_HYPERV_HVHDK_H +#define HW_HYPERV_HVHDK_H + +#define HV_PARTITION_SYNTHETIC_PROCESSOR_FEATURES_BANKS 1 + +struct hv_input_set_partition_property { + uint64_t partition_id; + uint32_t property_code; /* enum hv_partition_property_code */ + uint32_t padding; + uint64_t property_value; +}; + +union hv_partition_synthetic_processor_features { + uint64_t as_uint64[HV_PARTITION_SYNTHETIC_PROCESSOR_FEATURES_BANKS]; + + struct { + /* + * Report a hypervisor is present. CPUID leaves + * 0x40000000 and 0x40000001 are supported. + */ + uint64_t hypervisor_present:1; + + /* + * Features associated with HV#1: + */ + + /* Report support for Hv1 (CPUID leaves 0x40000000 - 0x40000006). */ + uint64_t hv1:1; + + /* + * Access to HV_X64_MSR_VP_RUNTIME. + * Corresponds to access_vp_run_time_reg privilege. + */ + uint64_t access_vp_run_time_reg:1; + + /* + * Access to HV_X64_MSR_TIME_REF_COUNT. + * Corresponds to access_partition_reference_counter privilege. + */ + uint64_t access_partition_reference_counter:1; + + /* + * Access to SINT-related registers (HV_X64_MSR_SCONTROL through + * HV_X64_MSR_EOM and HV_X64_MSR_SINT0 through HV_X64_MSR_SINT15). + * Corresponds to access_synic_regs privilege. + */ + uint64_t access_synic_regs:1; + + /* + * Access to synthetic timers and associated MSRs + * (HV_X64_MSR_STIMER0_CONFIG through HV_X64_MSR_STIMER3_COUNT). + * Corresponds to access_synthetic_timer_regs privilege. + */ + uint64_t access_synthetic_timer_regs:1; + + /* + * Access to APIC MSRs (HV_X64_MSR_EOI, HV_X64_MSR_ICR and + * HV_X64_MSR_TPR) as well as the VP assist page. + * Corresponds to access_intr_ctrl_regs privilege. + */ + uint64_t access_intr_ctrl_regs:1; + + /* + * Access to registers associated with hypercalls + * (HV_X64_MSR_GUEST_OS_ID and HV_X64_MSR_HYPERCALL). + * Corresponds to access_hypercall_msrs privilege. + */ + uint64_t access_hypercall_regs:1; + + /* VP index can be queried. corresponds to access_vp_index privilege. */ + uint64_t access_vp_index:1; + + /* + * Access to the reference TSC. Corresponds to + * access_partition_reference_tsc privilege. + */ + uint64_t access_partition_reference_tsc:1; + + /* + * Partition has access to the guest idle reg. Corresponds to + * access_guest_idle_reg privilege. + */ + uint64_t access_guest_idle_reg:1; + + /* + * Partition has access to frequency regs. corresponds to + * access_frequency_regs privilege. + */ + uint64_t access_frequency_regs:1; + + uint64_t reserved_z12:1; /* Reserved for access_reenlightenment_controls */ + uint64_t reserved_z13:1; /* Reserved for access_root_scheduler_reg */ + uint64_t reserved_z14:1; /* Reserved for access_tsc_invariant_controls */ + + /* + * Extended GVA ranges for HvCallFlushVirtualAddressList hypercall. + * Corresponds to privilege. + */ + uint64_t enable_extended_gva_ranges_for_flush_virtual_address_list:1; + + uint64_t reserved_z16:1; /* Reserved for access_vsm. */ + uint64_t reserved_z17:1; /* Reserved for access_vp_registers. */ + + /* Use fast hypercall output. Corresponds to privilege. */ + uint64_t fast_hypercall_output:1; + + uint64_t reserved_z19:1; /* Reserved for enable_extended_hypercalls. */ + + /* + * HvStartVirtualProcessor can be used to start virtual processors. + * Corresponds to privilege. + */ + uint64_t start_virtual_processor:1; + + uint64_t reserved_z21:1; /* Reserved for Isolation. */ + + /* Synthetic timers in direct mode. */ + uint64_t direct_synthetic_timers:1; + + uint64_t reserved_z23:1; /* Reserved for synthetic time unhalted timer */ + + /* Use extended processor masks. */ + uint64_t extended_processor_masks:1; + + /* + * HvCallFlushVirtualAddressSpace / HvCallFlushVirtualAddressList are + * supported. + */ + uint64_t tb_flush_hypercalls:1; + + /* HvCallSendSyntheticClusterIpi is supported. */ + uint64_t synthetic_cluster_ipi:1; + + /* HvCallNotifyLongSpinWait is supported. */ + uint64_t notify_long_spin_wait:1; + + /* HvCallQueryNumaDistance is supported. */ + uint64_t query_numa_distance:1; + + /* HvCallSignalEvent is supported. Corresponds to privilege. */ + uint64_t signal_events:1; + + /* HvCallRetargetDeviceInterrupt is supported. */ + uint64_t retarget_device_interrupt:1; + + /* HvCallRestorePartitionTime is supported. */ + uint64_t restore_time:1; + + /* EnlightenedVmcs nested enlightenment is supported. */ + uint64_t enlightened_vmcs:1; + + uint64_t reserved:30; + }; +}; + +enum hv_translate_gva_result_code { + HV_TRANSLATE_GVA_SUCCESS = 0, + + /* Translation failures. */ + HV_TRANSLATE_GVA_PAGE_NOT_PRESENT = 1, + HV_TRANSLATE_GVA_PRIVILEGE_VIOLATION = 2, + HV_TRANSLATE_GVA_INVALIDE_PAGE_TABLE_FLAGS = 3, + + /* GPA access failures. */ + HV_TRANSLATE_GVA_GPA_UNMAPPED = 4, + HV_TRANSLATE_GVA_GPA_NO_READ_ACCESS = 5, + HV_TRANSLATE_GVA_GPA_NO_WRITE_ACCESS = 6, + HV_TRANSLATE_GVA_GPA_ILLEGAL_OVERLAY_ACCESS = 7, + + /* + * Intercept for memory access by either + * - a higher VTL + * - a nested hypervisor (due to a violation of the nested page table) + */ + HV_TRANSLATE_GVA_INTERCEPT = 8, + + HV_TRANSLATE_GVA_GPA_UNACCEPTED = 9, +}; + +union hv_translate_gva_result { + uint64_t as_uint64; + struct { + uint32_t result_code; /* enum hv_translate_hva_result_code */ + uint32_t cache_type:8; + uint32_t overlay_page:1; + uint32_t reserved:23; + }; +}; + +typedef struct hv_input_translate_virtual_address { + uint64_t partition_id; + uint32_t vp_index; + uint32_t padding; + uint64_t control_flags; + uint64_t gva_page; +} hv_input_translate_virtual_address; + +typedef struct hv_output_translate_virtual_address { + union hv_translate_gva_result translation_result; + uint64_t gpa_page; +} hv_output_translate_virtual_address; + +typedef struct hv_register_x64_cpuid_result_parameters { + struct { + uint32_t eax; + uint32_t ecx; + uint8_t subleaf_specific; + uint8_t always_override; + uint16_t padding; + } input; + struct { + uint32_t eax; + uint32_t eax_mask; + uint32_t ebx; + uint32_t ebx_mask; + uint32_t ecx; + uint32_t ecx_mask; + uint32_t edx; + uint32_t edx_mask; + } result; +} hv_register_x64_cpuid_result_parameters; + +typedef struct hv_register_x64_msr_result_parameters { + uint32_t msr_index; + uint32_t access_type; + uint32_t action; /* enum hv_unimplemented_msr_action */ +} hv_register_x64_msr_result_parameters; + +union hv_register_intercept_result_parameters { + struct hv_register_x64_cpuid_result_parameters cpuid; + struct hv_register_x64_msr_result_parameters msr; +}; + +typedef struct hv_input_register_intercept_result { + uint64_t partition_id; + uint32_t vp_index; + uint32_t intercept_type; /* enum hv_intercept_type */ + union hv_register_intercept_result_parameters parameters; +} hv_input_register_intercept_result; + +#endif /* HW_HYPERV_HVHDK_H */ diff --git a/include/hw/hyperv/hvhdk_mini.h b/include/hw/hyperv/hvhdk_mini.h new file mode 100644 index 0000000..9c2f3cf --- /dev/null +++ b/include/hw/hyperv/hvhdk_mini.h @@ -0,0 +1,102 @@ +/* + * Type definitions for the mshv host interface. + * + * Copyright Microsoft, Corp. 2025 + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_HYPERV_HVHDK_MINI_H +#define HW_HYPERV_HVHDK_MINI_H + +#define HVHVK_MINI_VERSION (25294) + +/* Each generic set contains 64 elements */ +#define HV_GENERIC_SET_SHIFT (6) +#define HV_GENERIC_SET_MASK (63) + +enum hv_generic_set_format { + HV_GENERIC_SET_SPARSE_4K, + HV_GENERIC_SET_ALL, +}; + +enum hv_partition_property_code { + /* Privilege properties */ + HV_PARTITION_PROPERTY_PRIVILEGE_FLAGS = 0x00010000, + HV_PARTITION_PROPERTY_SYNTHETIC_PROC_FEATURES = 0x00010001, + + /* Scheduling properties */ + HV_PARTITION_PROPERTY_SUSPEND = 0x00020000, + HV_PARTITION_PROPERTY_CPU_RESERVE = 0x00020001, + HV_PARTITION_PROPERTY_CPU_CAP = 0x00020002, + HV_PARTITION_PROPERTY_CPU_WEIGHT = 0x00020003, + HV_PARTITION_PROPERTY_CPU_GROUP_ID = 0x00020004, + + /* Time properties */ + HV_PARTITION_PROPERTY_TIME_FREEZE = 0x00030003, + HV_PARTITION_PROPERTY_REFERENCE_TIME = 0x00030005, + + /* Debugging properties */ + HV_PARTITION_PROPERTY_DEBUG_CHANNEL_ID = 0x00040000, + + /* Resource properties */ + HV_PARTITION_PROPERTY_VIRTUAL_TLB_PAGE_COUNT = 0x00050000, + HV_PARTITION_PROPERTY_VSM_CONFIG = 0x00050001, + HV_PARTITION_PROPERTY_ZERO_MEMORY_ON_RESET = 0x00050002, + HV_PARTITION_PROPERTY_PROCESSORS_PER_SOCKET = 0x00050003, + HV_PARTITION_PROPERTY_NESTED_TLB_SIZE = 0x00050004, + HV_PARTITION_PROPERTY_GPA_PAGE_ACCESS_TRACKING = 0x00050005, + HV_PARTITION_PROPERTY_VSM_PERMISSIONS_DIRTY_SINCE_LAST_QUERY = 0x00050006, + HV_PARTITION_PROPERTY_SGX_LAUNCH_CONTROL_CONFIG = 0x00050007, + HV_PARTITION_PROPERTY_DEFAULT_SGX_LAUNCH_CONTROL0 = 0x00050008, + HV_PARTITION_PROPERTY_DEFAULT_SGX_LAUNCH_CONTROL1 = 0x00050009, + HV_PARTITION_PROPERTY_DEFAULT_SGX_LAUNCH_CONTROL2 = 0x0005000a, + HV_PARTITION_PROPERTY_DEFAULT_SGX_LAUNCH_CONTROL3 = 0x0005000b, + HV_PARTITION_PROPERTY_ISOLATION_STATE = 0x0005000c, + HV_PARTITION_PROPERTY_ISOLATION_CONTROL = 0x0005000d, + HV_PARTITION_PROPERTY_ALLOCATION_ID = 0x0005000e, + HV_PARTITION_PROPERTY_MONITORING_ID = 0x0005000f, + HV_PARTITION_PROPERTY_IMPLEMENTED_PHYSICAL_ADDRESS_BITS = 0x00050010, + HV_PARTITION_PROPERTY_NON_ARCHITECTURAL_CORE_SHARING = 0x00050011, + HV_PARTITION_PROPERTY_HYPERCALL_DOORBELL_PAGE = 0x00050012, + HV_PARTITION_PROPERTY_ISOLATION_POLICY = 0x00050014, + HV_PARTITION_PROPERTY_UNIMPLEMENTED_MSR_ACTION = 0x00050017, + HV_PARTITION_PROPERTY_SEV_VMGEXIT_OFFLOADS = 0x00050022, + + /* Compatibility properties */ + HV_PARTITION_PROPERTY_PROCESSOR_VENDOR = 0x00060000, + HV_PARTITION_PROPERTY_PROCESSOR_FEATURES_DEPRECATED = 0x00060001, + HV_PARTITION_PROPERTY_PROCESSOR_XSAVE_FEATURES = 0x00060002, + HV_PARTITION_PROPERTY_PROCESSOR_CL_FLUSH_SIZE = 0x00060003, + HV_PARTITION_PROPERTY_ENLIGHTENMENT_MODIFICATIONS = 0x00060004, + HV_PARTITION_PROPERTY_COMPATIBILITY_VERSION = 0x00060005, + HV_PARTITION_PROPERTY_PHYSICAL_ADDRESS_WIDTH = 0x00060006, + HV_PARTITION_PROPERTY_XSAVE_STATES = 0x00060007, + HV_PARTITION_PROPERTY_MAX_XSAVE_DATA_SIZE = 0x00060008, + HV_PARTITION_PROPERTY_PROCESSOR_CLOCK_FREQUENCY = 0x00060009, + HV_PARTITION_PROPERTY_PROCESSOR_FEATURES0 = 0x0006000a, + HV_PARTITION_PROPERTY_PROCESSOR_FEATURES1 = 0x0006000b, + + /* Guest software properties */ + HV_PARTITION_PROPERTY_GUEST_OS_ID = 0x00070000, + + /* Nested virtualization properties */ + HV_PARTITION_PROPERTY_PROCESSOR_VIRTUALIZATION_FEATURES = 0x00080000, +}; + +/* HV Map GPA (Guest Physical Address) Flags */ +#define HV_MAP_GPA_PERMISSIONS_NONE 0x0 +#define HV_MAP_GPA_READABLE 0x1 +#define HV_MAP_GPA_WRITABLE 0x2 +#define HV_MAP_GPA_KERNEL_EXECUTABLE 0x4 +#define HV_MAP_GPA_USER_EXECUTABLE 0x8 +#define HV_MAP_GPA_EXECUTABLE 0xC +#define HV_MAP_GPA_PERMISSIONS_MASK 0xF +#define HV_MAP_GPA_ADJUSTABLE 0x8000 +#define HV_MAP_GPA_NO_ACCESS 0x10000 +#define HV_MAP_GPA_NOT_CACHED 0x200000 +#define HV_MAP_GPA_LARGE_PAGE 0x80000000 + +#define HV_PFN_RNG_PAGEBITS 24 /* HV_SPA_PAGE_RANGE_ADDITIONAL_PAGES_BITS */ + +#endif /* HW_HYPERV_HVHDK_MINI_H */ diff --git a/include/hw/hyperv/hyperv.h b/include/hw/hyperv/hyperv.h index d717b4e..63a8b65 100644 --- a/include/hw/hyperv/hyperv.h +++ b/include/hw/hyperv/hyperv.h @@ -10,7 +10,8 @@ #ifndef HW_HYPERV_HYPERV_H #define HW_HYPERV_HYPERV_H -#include "cpu-qom.h" +#include "exec/hwaddr.h" +#include "hw/core/cpu.h" #include "hw/hyperv/hyperv-proto.h" typedef struct HvSintRoute HvSintRoute; diff --git a/include/hw/i2c/aspeed_i2c.h b/include/hw/i2c/aspeed_i2c.h index 2c4c81b..2daacc1 100644 --- a/include/hw/i2c/aspeed_i2c.h +++ b/include/hw/i2c/aspeed_i2c.h @@ -14,8 +14,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + * with this program; if not, see <https://www.gnu.org/licenses/>. */ #ifndef ASPEED_I2C_H diff --git a/include/hw/i2c/npcm7xx_smbus.h b/include/hw/i2c/npcm7xx_smbus.h index dc45963..9c544c5 100644 --- a/include/hw/i2c/npcm7xx_smbus.h +++ b/include/hw/i2c/npcm7xx_smbus.h @@ -16,7 +16,7 @@ #ifndef NPCM7XX_SMBUS_H #define NPCM7XX_SMBUS_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/i2c/i2c.h" #include "hw/irq.h" #include "hw/sysbus.h" diff --git a/include/hw/i2c/pm_smbus.h b/include/hw/i2c/pm_smbus.h index 0d74207..dafe0df 100644 --- a/include/hw/i2c/pm_smbus.h +++ b/include/hw/i2c/pm_smbus.h @@ -1,7 +1,7 @@ #ifndef PM_SMBUS_H #define PM_SMBUS_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/i2c/smbus_master.h" #define PM_SMBUS_MAX_MSG_SIZE 32 diff --git a/include/hw/i386/apic.h b/include/hw/i386/apic.h index eb606d6..6a0933f 100644 --- a/include/hw/i386/apic.h +++ b/include/hw/i386/apic.h @@ -1,28 +1,29 @@ #ifndef APIC_H #define APIC_H +typedef struct APICCommonState APICCommonState; /* apic.c */ void apic_set_max_apic_id(uint32_t max_apic_id); -int apic_accept_pic_intr(DeviceState *s); -void apic_deliver_pic_intr(DeviceState *s, int level); -void apic_deliver_nmi(DeviceState *d); -int apic_get_interrupt(DeviceState *s); -int cpu_set_apic_base(DeviceState *s, uint64_t val); -uint64_t cpu_get_apic_base(DeviceState *s); -bool cpu_is_apic_enabled(DeviceState *s); -void cpu_set_apic_tpr(DeviceState *s, uint8_t val); -uint8_t cpu_get_apic_tpr(DeviceState *s); -void apic_init_reset(DeviceState *s); -void apic_sipi(DeviceState *s); -void apic_poll_irq(DeviceState *d); -void apic_designate_bsp(DeviceState *d, bool bsp); -int apic_get_highest_priority_irr(DeviceState *dev); -int apic_msr_read(int index, uint64_t *val); -int apic_msr_write(int index, uint64_t val); -bool is_x2apic_mode(DeviceState *d); +int apic_accept_pic_intr(APICCommonState *s); +void apic_deliver_pic_intr(APICCommonState *s, int level); +void apic_deliver_nmi(APICCommonState *s); +int apic_get_interrupt(APICCommonState *s); +int cpu_set_apic_base(APICCommonState *s, uint64_t val); +uint64_t cpu_get_apic_base(APICCommonState *s); +bool cpu_is_apic_enabled(APICCommonState *s); +void cpu_set_apic_tpr(APICCommonState *s, uint8_t val); +uint8_t cpu_get_apic_tpr(APICCommonState *s); +void apic_init_reset(APICCommonState *s); +void apic_sipi(APICCommonState *s); +void apic_poll_irq(APICCommonState *s); +void apic_designate_bsp(APICCommonState *s, bool bsp); +int apic_get_highest_priority_irr(APICCommonState *s); +int apic_msr_read(APICCommonState *s, int index, uint64_t *val); +int apic_msr_write(APICCommonState *s, int index, uint64_t val); +bool is_x2apic_mode(APICCommonState *s); /* pc.c */ -DeviceState *cpu_get_current_apic(void); +APICCommonState *cpu_get_current_apic(void); #endif diff --git a/include/hw/i386/apic_internal.h b/include/hw/i386/apic_internal.h index d6e8583..4a62fdc 100644 --- a/include/hw/i386/apic_internal.h +++ b/include/hw/i386/apic_internal.h @@ -22,7 +22,8 @@ #define QEMU_APIC_INTERNAL_H #include "cpu.h" -#include "exec/memory.h" +#include "hw/i386/apic.h" +#include "system/memory.h" #include "qemu/timer.h" #include "target/i386/cpu-qom.h" #include "qom/object.h" @@ -125,8 +126,6 @@ #define VAPIC_ENABLE_BIT 0 #define VAPIC_ENABLE_MASK (1 << VAPIC_ENABLE_BIT) -typedef struct APICCommonState APICCommonState; - #define TYPE_APIC_COMMON "apic-common" typedef struct APICCommonClass APICCommonClass; DECLARE_OBJ_CHECKERS(APICCommonState, APICCommonClass, @@ -203,8 +202,8 @@ typedef struct VAPICState { extern bool apic_report_tpr_access; bool apic_next_timer(APICCommonState *s, int64_t current_time); -void apic_enable_tpr_access_reporting(DeviceState *d, bool enable); -void apic_enable_vapic(DeviceState *d, hwaddr paddr); +void apic_enable_tpr_access_reporting(APICCommonState *s, bool enable); +void apic_enable_vapic(APICCommonState *s, hwaddr paddr); void vapic_report_tpr_access(DeviceState *dev, CPUState *cpu, target_ulong ip, TPRAccess access); diff --git a/include/hw/i386/intel_iommu.h b/include/hw/i386/intel_iommu.h index e95477e..ca7f7bb 100644 --- a/include/hw/i386/intel_iommu.h +++ b/include/hw/i386/intel_iommu.h @@ -95,6 +95,11 @@ struct VTDPASIDEntry { uint64_t val[8]; }; +typedef struct VTDPASIDCacheEntry { + struct VTDPASIDEntry pasid_entry; + bool valid; +} VTDPASIDCacheEntry; + struct VTDAddressSpace { PCIBus *bus; uint8_t devfn; @@ -107,9 +112,11 @@ struct VTDAddressSpace { MemoryRegion iommu_ir_fault; /* Interrupt region for catching fault */ IntelIOMMUState *iommu_state; VTDContextCacheEntry context_cache_entry; + VTDPASIDCacheEntry pasid_cache_entry; QLIST_ENTRY(VTDAddressSpace) next; /* Superset of notifier flags that this address space has */ IOMMUNotifierFlag notifier_flags; + IOMMUPRINotifier *pri_notifier; /* * @iova_tree traces mapped IOVA ranges. * @@ -306,7 +313,6 @@ struct IntelIOMMUState { bool buggy_eim; /* Force buggy EIM unless eim=off */ uint8_t aw_bits; /* Host/IOVA address width (in bits) */ bool dma_drain; /* Whether DMA r/w draining enabled */ - bool dma_translation; /* Whether DMA translation supported */ bool pasid; /* Whether to support PASID */ bool fs1gp; /* First Stage 1-GByte Page Support */ diff --git a/include/hw/i386/microvm.h b/include/hw/i386/microvm.h index b9ac34a..e73d1e6 100644 --- a/include/hw/i386/microvm.h +++ b/include/hw/i386/microvm.h @@ -102,8 +102,6 @@ struct MicrovmMachineState { Notifier powerdown_req; struct GPEXConfig gpex; - /* device tree */ - void *fdt; uint32_t ioapic_phandle[2]; }; diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h index 103b543..e83157a 100644 --- a/include/hw/i386/pc.h +++ b/include/hw/i386/pc.h @@ -107,7 +107,6 @@ struct PCMachineClass { /* RAM / address space compat: */ bool gigabyte_align; bool has_reserved_memory; - bool broken_reserved_end; bool enforce_amd_1tb_hole; bool isa_bios_alias; @@ -215,6 +214,12 @@ void pc_system_parse_ovmf_flash(uint8_t *flash_ptr, size_t flash_size); /* sgx.c */ void pc_machine_init_sgx_epc(PCMachineState *pcms); +extern GlobalProperty pc_compat_10_1[]; +extern const size_t pc_compat_10_1_len; + +extern GlobalProperty pc_compat_10_0[]; +extern const size_t pc_compat_10_0_len; + extern GlobalProperty pc_compat_9_2[]; extern const size_t pc_compat_9_2_len; @@ -296,14 +301,9 @@ extern const size_t pc_compat_2_7_len; extern GlobalProperty pc_compat_2_6[]; extern const size_t pc_compat_2_6_len; -extern GlobalProperty pc_compat_2_5[]; -extern const size_t pc_compat_2_5_len; - -extern GlobalProperty pc_compat_2_4[]; -extern const size_t pc_compat_2_4_len; - #define DEFINE_PC_MACHINE(suffix, namestr, initfn, optsfn) \ - static void pc_machine_##suffix##_class_init(ObjectClass *oc, void *data) \ + static void pc_machine_##suffix##_class_init(ObjectClass *oc, \ + const void *data) \ { \ MachineClass *mc = MACHINE_CLASS(oc); \ optsfn(mc); \ @@ -328,7 +328,7 @@ extern const size_t pc_compat_2_4_len; } \ static void MACHINE_VER_SYM(class_init, namesym, __VA_ARGS__)( \ ObjectClass *oc, \ - void *data) \ + const void *data) \ { \ MachineClass *mc = MACHINE_CLASS(oc); \ MACHINE_VER_SYM(options, namesym, __VA_ARGS__)(mc); \ diff --git a/include/hw/i386/tdvf.h b/include/hw/i386/tdvf.h new file mode 100644 index 0000000..e75c8d1 --- /dev/null +++ b/include/hw/i386/tdvf.h @@ -0,0 +1,45 @@ +/* + * Copyright (c) 2025 Intel Corporation + * Author: Isaku Yamahata <isaku.yamahata at gmail.com> + * <isaku.yamahata at intel.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_I386_TDVF_H +#define HW_I386_TDVF_H + +#include "qemu/osdep.h" + +#define TDVF_SECTION_TYPE_BFV 0 +#define TDVF_SECTION_TYPE_CFV 1 +#define TDVF_SECTION_TYPE_TD_HOB 2 +#define TDVF_SECTION_TYPE_TEMP_MEM 3 + +#define TDVF_SECTION_ATTRIBUTES_MR_EXTEND (1U << 0) +#define TDVF_SECTION_ATTRIBUTES_PAGE_AUG (1U << 1) + +typedef struct TdxFirmwareEntry { + uint32_t data_offset; + uint32_t data_len; + uint64_t address; + uint64_t size; + uint32_t type; + uint32_t attributes; + + void *mem_ptr; +} TdxFirmwareEntry; + +typedef struct TdxFirmware { + void *mem_ptr; + + uint32_t nr_entries; + TdxFirmwareEntry *entries; +} TdxFirmware; + +#define for_each_tdx_fw_entry(fw, e) \ + for (e = (fw)->entries; e != (fw)->entries + (fw)->nr_entries; e++) + +int tdvf_parse_metadata(TdxFirmware *fw, void *flash_ptr, int size); + +#endif /* HW_I386_TDVF_H */ diff --git a/include/hw/i386/x86-iommu.h b/include/hw/i386/x86-iommu.h index bfd2164..e89f55a 100644 --- a/include/hw/i386/x86-iommu.h +++ b/include/hw/i386/x86-iommu.h @@ -64,6 +64,7 @@ struct X86IOMMUState { OnOffAuto intr_supported; /* Whether vIOMMU supports IR */ bool dt_supported; /* Whether vIOMMU supports DT */ bool pt_supported; /* Whether vIOMMU supports pass-through */ + bool dma_translation; /* Whether vIOMMU supports DMA translation */ QLIST_HEAD(, IEC_Notifier) iec_notifiers; /* IEC notify list */ }; diff --git a/include/hw/i386/x86.h b/include/hw/i386/x86.h index d43cb39..8755cad 100644 --- a/include/hw/i386/x86.h +++ b/include/hw/i386/x86.h @@ -18,22 +18,18 @@ #define HW_I386_X86_H #include "exec/hwaddr.h" -#include "exec/memory.h" +#include "system/memory.h" #include "hw/boards.h" #include "hw/i386/topology.h" #include "hw/intc/ioapic.h" #include "hw/isa/isa.h" #include "qom/object.h" +#include "system/igvm-cfg.h" struct X86MachineClass { - /*< private >*/ MachineClass parent; - /*< public >*/ - - /* TSC rate migration: */ - bool save_tsc_khz; /* use DMA capable linuxboot option rom */ bool fwcfg_dma_enabled; /* CPU and apic information: */ @@ -97,6 +93,8 @@ struct X86MachineState { * which means no limitation on the guest's bus locks. */ uint64_t bus_lock_ratelimit; + + IgvmCfg *igvm; }; #define X86_MACHINE_SMM "smm" diff --git a/include/hw/i386/xen_arch_hvm.h b/include/hw/i386/xen_arch_hvm.h deleted file mode 100644 index 1000f8f..0000000 --- a/include/hw/i386/xen_arch_hvm.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef HW_XEN_ARCH_I386_HVM_H -#define HW_XEN_ARCH_I386_HVM_H - -#include <xen/hvm/ioreq.h> -#include "hw/xen/xen-hvm-common.h" - -void arch_handle_ioreq(XenIOState *state, ioreq_t *req); -void arch_xen_set_memory(XenIOState *state, - MemoryRegionSection *section, - bool add); -#endif diff --git a/include/hw/ide/ahci.h b/include/hw/ide/ahci.h index ac0292c..cd07b87 100644 --- a/include/hw/ide/ahci.h +++ b/include/hw/ide/ahci.h @@ -24,7 +24,7 @@ #ifndef HW_IDE_AHCI_H #define HW_IDE_AHCI_H -#include "exec/memory.h" +#include "system/memory.h" typedef struct AHCIDevice AHCIDevice; diff --git a/include/hw/ide/ide-bus.h b/include/hw/ide/ide-bus.h index 4841a7d..121b455 100644 --- a/include/hw/ide/ide-bus.h +++ b/include/hw/ide/ide-bus.h @@ -1,7 +1,7 @@ #ifndef HW_IDE_BUS_H #define HW_IDE_BUS_H -#include "exec/ioport.h" +#include "system/ioport.h" #include "hw/ide/ide-dev.h" #include "hw/ide/ide-dma.h" diff --git a/include/hw/input/lasips2.h b/include/hw/input/lasips2.h index 01911c5..fd74883 100644 --- a/include/hw/input/lasips2.h +++ b/include/hw/input/lasips2.h @@ -32,7 +32,8 @@ struct LASIPS2PortDeviceClass { DeviceRealize parent_realize; }; -typedef struct LASIPS2State LASIPS2State; +#define TYPE_LASIPS2 "lasips2" +OBJECT_DECLARE_SIMPLE_TYPE(LASIPS2State, LASIPS2) struct LASIPS2Port { DeviceState parent_obj; @@ -74,7 +75,4 @@ struct LASIPS2State { qemu_irq irq; }; -#define TYPE_LASIPS2 "lasips2" -OBJECT_DECLARE_SIMPLE_TYPE(LASIPS2State, LASIPS2) - #endif /* HW_INPUT_LASIPS2_H */ diff --git a/include/hw/intc/arm_gic.h b/include/hw/intc/arm_gic.h index 48f6a51..be923f7 100644 --- a/include/hw/intc/arm_gic.h +++ b/include/hw/intc/arm_gic.h @@ -27,6 +27,9 @@ * implement the security extensions * + QOM property "has-virtualization-extensions": set true if the GIC should * implement the virtualization extensions + * + QOM property "first-cpu-index": index of the first cpu attached to the + * GIC (default 0). The CPUs connected to the GIC are assumed to be + * first-cpu-index, first-cpu-index + 1, ... first-cpu-index + num-cpu - 1. * + unnamed GPIO inputs: (where P is number of SPIs, i.e. num-irq - 32) * [0..P-1] SPIs * [P..P+31] PPIs for CPU 0 diff --git a/include/hw/intc/arm_gic_common.h b/include/hw/intc/arm_gic_common.h index 97fea41..93a3cc2 100644 --- a/include/hw/intc/arm_gic_common.h +++ b/include/hw/intc/arm_gic_common.h @@ -129,6 +129,8 @@ struct GICState { uint32_t num_lrs; uint32_t num_cpu; + /* cpu_index of the first CPU, attached to this GIC. */ + uint32_t first_cpu_index; MemoryRegion iomem; /* Distributor */ /* This is just so we can have an opaque pointer which identifies diff --git a/include/hw/intc/arm_gicv3_common.h b/include/hw/intc/arm_gicv3_common.h index a3d6a0e..61d5191 100644 --- a/include/hw/intc/arm_gicv3_common.h +++ b/include/hw/intc/arm_gicv3_common.h @@ -27,6 +27,7 @@ #include "hw/sysbus.h" #include "hw/intc/arm_gic_common.h" #include "qom/object.h" +#include "qemu/notify.h" /* * Maximum number of possible interrupts, determined by the GIC architecture. @@ -165,6 +166,9 @@ struct GICv3CPUState { uint64_t icc_igrpen[3]; uint64_t icc_ctlr_el3; + /* For KVM, cached copy of the kernel reset value of ICC_CTLR_EL1 */ + uint64_t kvm_reset_icc_ctlr_el1; + /* Virtualization control interface */ uint64_t ich_apr[3][4]; /* ich_apr[GICV3_G1][x] never used */ uint64_t ich_hcr_el2; @@ -228,9 +232,11 @@ struct GICv3State { uint32_t *redist_region_count; /* redistributor count within each region */ uint32_t nb_redist_regions; /* number of redist regions */ + uint32_t first_cpu_idx; uint32_t num_cpu; uint32_t num_irq; uint32_t revision; + uint32_t maint_irq; bool lpi_enable; bool nmi_support; bool security_extn; @@ -270,6 +276,8 @@ struct GICv3State { GICv3CPUState *cpu; /* List of all ITSes connected to this GIC */ GPtrArray *itslist; + + NotifierWithReturn cpr_notifier; }; #define GICV3_BITMAP_ACCESSORS(BMP) \ diff --git a/include/hw/intc/arm_gicv3_its_common.h b/include/hw/intc/arm_gicv3_its_common.h index 7dc712b..3c7b543 100644 --- a/include/hw/intc/arm_gicv3_its_common.h +++ b/include/hw/intc/arm_gicv3_its_common.h @@ -128,7 +128,7 @@ struct GICv3ITSCommonClass { * Return the ITS class name to use depending on whether KVM acceleration * and KVM CAP_SIGNAL_MSI are supported * - * Returns: class name to use or NULL + * Returns: class name to use */ const char *its_class_name(void); diff --git a/include/hw/intc/armv7m_nvic.h b/include/hw/intc/armv7m_nvic.h index 89fe8ae..7b9964f 100644 --- a/include/hw/intc/armv7m_nvic.h +++ b/include/hw/intc/armv7m_nvic.h @@ -189,21 +189,7 @@ int armv7m_nvic_raw_execution_priority(NVICState *s); * @secure: the security state to test * This corresponds to the pseudocode IsReqExecPriNeg(). */ -#ifndef CONFIG_USER_ONLY bool armv7m_nvic_neg_prio_requested(NVICState *s, bool secure); -#else -static inline bool armv7m_nvic_neg_prio_requested(NVICState *s, bool secure) -{ - return false; -} -#endif -#ifndef CONFIG_USER_ONLY bool armv7m_nvic_can_take_pending_exception(NVICState *s); -#else -static inline bool armv7m_nvic_can_take_pending_exception(NVICState *s) -{ - return true; -} -#endif #endif diff --git a/include/hw/intc/aspeed_intc.h b/include/hw/intc/aspeed_intc.h index 3727ba2..5128838 100644 --- a/include/hw/intc/aspeed_intc.h +++ b/include/hw/intc/aspeed_intc.h @@ -15,6 +15,11 @@ #define TYPE_ASPEED_INTC "aspeed.intc" #define TYPE_ASPEED_2700_INTC TYPE_ASPEED_INTC "-ast2700" #define TYPE_ASPEED_2700_INTCIO TYPE_ASPEED_INTC "io-ast2700" +#define TYPE_ASPEED_2700SSP_INTC TYPE_ASPEED_INTC "-ast2700ssp" +#define TYPE_ASPEED_2700SSP_INTCIO TYPE_ASPEED_INTC "io-ast2700ssp" +#define TYPE_ASPEED_2700TSP_INTC TYPE_ASPEED_INTC "-ast2700tsp" +#define TYPE_ASPEED_2700TSP_INTCIO TYPE_ASPEED_INTC "io-ast2700tsp" + OBJECT_DECLARE_TYPE(AspeedINTCState, AspeedINTCClass, ASPEED_INTC) #define ASPEED_INTC_MAX_INPINS 10 diff --git a/include/hw/intc/loongarch_dintc.h b/include/hw/intc/loongarch_dintc.h new file mode 100644 index 0000000..01bb1e4 --- /dev/null +++ b/include/hw/intc/loongarch_dintc.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * LoongArch direct interrupt controller definitions + * + * Copyright (C) 2025 Loongson Technology Corporation Limited + */ + +#include "qom/object.h" +#include "hw/sysbus.h" +#include "hw/loongarch/virt.h" +#include "system/memory.h" + +#define NR_VECTORS 256 + +#define TYPE_LOONGARCH_DINTC "loongarch_dintc" +OBJECT_DECLARE_TYPE(LoongArchDINTCState, LoongArchDINTCClass, LOONGARCH_DINTC) + +typedef struct DINTCCore { + CPUState *cpu; + qemu_irq parent_irq; + uint64_t arch_id; +} DINTCCore; + +struct LoongArchDINTCState { + SysBusDevice parent_obj; + MemoryRegion dintc_mmio; + DINTCCore *cpu; + uint32_t num_cpu; +}; + +struct LoongArchDINTCClass { + SysBusDeviceClass parent_class; + + DeviceRealize parent_realize; + DeviceUnrealize parent_unrealize; +}; diff --git a/include/hw/intc/loongarch_extioi.h b/include/hw/intc/loongarch_extioi.h index 351f18a..4795bdc 100644 --- a/include/hw/intc/loongarch_extioi.h +++ b/include/hw/intc/loongarch_extioi.h @@ -15,13 +15,18 @@ OBJECT_DECLARE_TYPE(LoongArchExtIOIState, LoongArchExtIOIClass, LOONGARCH_EXTIOI struct LoongArchExtIOIState { LoongArchExtIOICommonState parent_obj; + int dev_fd; }; struct LoongArchExtIOIClass { LoongArchExtIOICommonClass parent_class; DeviceRealize parent_realize; - DeviceUnrealize parent_unrealize; + ResettablePhases parent_phases; }; +void kvm_extioi_realize(DeviceState *dev, Error **errp); +int kvm_extioi_get(void *opaque); +int kvm_extioi_put(void *opaque, int version_id); + #endif /* LOONGARCH_EXTIOI_H */ diff --git a/include/hw/intc/loongarch_extioi_common.h b/include/hw/intc/loongarch_extioi_common.h index 22d7880..1bd2bfa 100644 --- a/include/hw/intc/loongarch_extioi_common.h +++ b/include/hw/intc/loongarch_extioi_common.h @@ -10,6 +10,7 @@ #include "qom/object.h" #include "hw/sysbus.h" #include "hw/loongarch/virt.h" +#include "system/memory.h" #define LS3A_INTC_IP 8 #define EXTIOI_IRQS (256) @@ -35,7 +36,7 @@ #define EXTIOI_ISR_START (0x700 - APIC_OFFSET) #define EXTIOI_ISR_END (0x720 - APIC_OFFSET) #define EXTIOI_COREISR_START (0x800 - APIC_OFFSET) -#define EXTIOI_COREISR_END (0xB20 - APIC_OFFSET) +#define EXTIOI_COREISR_END (0x820 - APIC_OFFSET) #define EXTIOI_COREMAP_START (0xC00 - APIC_OFFSET) #define EXTIOI_COREMAP_END (0xD00 - APIC_OFFSET) #define EXTIOI_SIZE 0x800 @@ -94,6 +95,8 @@ struct LoongArchExtIOICommonClass { SysBusDeviceClass parent_class; DeviceRealize parent_realize; + DeviceUnrealize parent_unrealize; + ResettablePhases parent_phases; int (*pre_save)(void *s); int (*post_load)(void *s, int version_id); }; diff --git a/include/hw/intc/loongarch_ipi.h b/include/hw/intc/loongarch_ipi.h index 923bf21..5175a6b 100644 --- a/include/hw/intc/loongarch_ipi.h +++ b/include/hw/intc/loongarch_ipi.h @@ -16,11 +16,17 @@ OBJECT_DECLARE_TYPE(LoongarchIPIState, LoongarchIPIClass, LOONGARCH_IPI) struct LoongarchIPIState { LoongsonIPICommonState parent_obj; + int dev_fd; }; struct LoongarchIPIClass { LoongsonIPICommonClass parent_class; DeviceRealize parent_realize; + ResettablePhases parent_phases; }; +void kvm_ipi_realize(DeviceState *dev, Error **errp); +int kvm_ipi_get(void *opaque); +int kvm_ipi_put(void *opaque, int version_id); + #endif diff --git a/include/hw/intc/loongarch_pch_msi.h b/include/hw/intc/loongarch_pch_msi.h index b8586fb..ef4ec4f 100644 --- a/include/hw/intc/loongarch_pch_msi.h +++ b/include/hw/intc/loongarch_pch_msi.h @@ -6,6 +6,7 @@ */ #include "hw/sysbus.h" +#include "system/memory.h" #define TYPE_LOONGARCH_PCH_MSI "loongarch_pch_msi" OBJECT_DECLARE_SIMPLE_TYPE(LoongArchPCHMSI, LOONGARCH_PCH_MSI) diff --git a/include/hw/intc/loongarch_pch_pic.h b/include/hw/intc/loongarch_pch_pic.h index 481cc58..a46b6f8 100644 --- a/include/hw/intc/loongarch_pch_pic.h +++ b/include/hw/intc/loongarch_pch_pic.h @@ -16,12 +16,18 @@ OBJECT_DECLARE_TYPE(LoongarchPICState, LoongarchPICClass, LOONGARCH_PIC) struct LoongarchPICState { LoongArchPICCommonState parent_obj; + int dev_fd; }; struct LoongarchPICClass { LoongArchPICCommonClass parent_class; DeviceRealize parent_realize; + ResettablePhases parent_phases; }; +void kvm_pic_realize(DeviceState *dev, Error **errp); +int kvm_pic_get(void *opaque); +int kvm_pic_put(void *opaque, int version_id); + #endif /* HW_LOONGARCH_PCH_PIC_H */ diff --git a/include/hw/intc/loongarch_pic_common.h b/include/hw/intc/loongarch_pic_common.h index 43cce48..179361e 100644 --- a/include/hw/intc/loongarch_pic_common.h +++ b/include/hw/intc/loongarch_pic_common.h @@ -7,47 +7,48 @@ #ifndef HW_LOONGARCH_PIC_COMMON_H #define HW_LOONGARCH_PIC_COMMON_H -#include "hw/pci-host/ls7a.h" +#include "hw/loongarch/virt.h" #include "hw/sysbus.h" +#include "system/memory.h" -#define PCH_PIC_INT_ID_VAL 0x7000000UL -#define PCH_PIC_INT_ID_VER 0x1UL -#define PCH_PIC_INT_ID_LO 0x00 -#define PCH_PIC_INT_ID_HI 0x04 -#define PCH_PIC_INT_MASK_LO 0x20 -#define PCH_PIC_INT_MASK_HI 0x24 -#define PCH_PIC_HTMSI_EN_LO 0x40 -#define PCH_PIC_HTMSI_EN_HI 0x44 -#define PCH_PIC_INT_EDGE_LO 0x60 -#define PCH_PIC_INT_EDGE_HI 0x64 -#define PCH_PIC_INT_CLEAR_LO 0x80 -#define PCH_PIC_INT_CLEAR_HI 0x84 -#define PCH_PIC_AUTO_CTRL0_LO 0xc0 -#define PCH_PIC_AUTO_CTRL0_HI 0xc4 -#define PCH_PIC_AUTO_CTRL1_LO 0xe0 -#define PCH_PIC_AUTO_CTRL1_HI 0xe4 -#define PCH_PIC_ROUTE_ENTRY_OFFSET 0x100 +#define PCH_PIC_INT_ID 0x00 +#define PCH_PIC_INT_ID_VAL 0x7 +#define PCH_PIC_INT_ID_VER 0x1 +#define PCH_PIC_INT_MASK 0x20 +#define PCH_PIC_HTMSI_EN 0x40 +#define PCH_PIC_INT_EDGE 0x60 +#define PCH_PIC_INT_CLEAR 0x80 +#define PCH_PIC_AUTO_CTRL0 0xc0 +#define PCH_PIC_AUTO_CTRL1 0xe0 +#define PCH_PIC_ROUTE_ENTRY 0x100 #define PCH_PIC_ROUTE_ENTRY_END 0x13f -#define PCH_PIC_HTMSI_VEC_OFFSET 0x200 +#define PCH_PIC_HTMSI_VEC 0x200 #define PCH_PIC_HTMSI_VEC_END 0x23f -#define PCH_PIC_INT_STATUS_LO 0x3a0 -#define PCH_PIC_INT_STATUS_HI 0x3a4 -#define PCH_PIC_INT_POL_LO 0x3e0 -#define PCH_PIC_INT_POL_HI 0x3e4 - -#define STATUS_LO_START 0 -#define STATUS_HI_START 0x4 -#define POL_LO_START 0x40 -#define POL_HI_START 0x44 +#define PCH_PIC_INT_REQUEST 0x380 +#define PCH_PIC_INT_STATUS 0x3a0 +#define PCH_PIC_INT_POL 0x3e0 #define TYPE_LOONGARCH_PIC_COMMON "loongarch_pic_common" OBJECT_DECLARE_TYPE(LoongArchPICCommonState, LoongArchPICCommonClass, LOONGARCH_PIC_COMMON) +union LoongArchPIC_ID { + struct { + uint8_t _reserved_0[3]; + uint8_t id; + uint8_t version; + uint8_t _reserved_1; + uint8_t irq_num; + uint8_t _reserved_2; + } QEMU_PACKED desc; + uint64_t data; +}; + struct LoongArchPICCommonState { SysBusDevice parent_obj; qemu_irq parent_irq[64]; + union LoongArchPIC_ID id; /* 0x00 interrupt ID register */ uint64_t int_mask; /* 0x020 interrupt mask register */ uint64_t htmsi_en; /* 0x040 1=msi */ uint64_t intedge; /* 0x060 edge=1 level=0 */ @@ -66,9 +67,7 @@ struct LoongArchPICCommonState { uint8_t route_entry[64]; /* 0x100 - 0x138 */ uint8_t htmsi_vector[64]; /* 0x200 - 0x238 */ - MemoryRegion iomem32_low; - MemoryRegion iomem32_high; - MemoryRegion iomem8; + MemoryRegion iomem; unsigned int irq_num; }; @@ -76,6 +75,7 @@ struct LoongArchPICCommonClass { SysBusDeviceClass parent_class; DeviceRealize parent_realize; + ResettablePhases parent_phases; int (*pre_save)(LoongArchPICCommonState *s); int (*post_load)(LoongArchPICCommonState *s, int version_id); }; diff --git a/include/hw/intc/loongson_ipi_common.h b/include/hw/intc/loongson_ipi_common.h index b587f9c..4fa03bc 100644 --- a/include/hw/intc/loongson_ipi_common.h +++ b/include/hw/intc/loongson_ipi_common.h @@ -11,6 +11,7 @@ #include "qom/object.h" #include "hw/sysbus.h" #include "exec/memattrs.h" +#include "system/memory.h" #define IPI_MBX_NUM 4 @@ -48,6 +49,8 @@ struct LoongsonIPICommonClass { AddressSpace *(*get_iocsr_as)(CPUState *cpu); int (*cpu_by_arch_id)(LoongsonIPICommonState *lics, int64_t id, int *index, CPUState **pcs); + int (*pre_save)(void *opaque); + int (*post_load)(void *opaque, int version_id); }; MemTxResult loongson_ipi_core_readl(void *opaque, hwaddr addr, uint64_t *data, diff --git a/include/hw/intc/riscv_aclint.h b/include/hw/intc/riscv_aclint.h index 693415e..4b7406e 100644 --- a/include/hw/intc/riscv_aclint.h +++ b/include/hw/intc/riscv_aclint.h @@ -80,4 +80,8 @@ enum { RISCV_ACLINT_SWI_SIZE = 0x4000 }; +#define VMSTATE_TIMER_PTR_VARRAY(_f, _s, _f_n) \ +VMSTATE_VARRAY_OF_POINTER_UINT32(_f, _s, _f_n, 0, vmstate_info_timer, \ + QEMUTimer *) + #endif diff --git a/include/hw/ipmi/ipmi.h b/include/hw/ipmi/ipmi.h index 77a7213..cd581aa 100644 --- a/include/hw/ipmi/ipmi.h +++ b/include/hw/ipmi/ipmi.h @@ -25,7 +25,7 @@ #ifndef HW_IPMI_H #define HW_IPMI_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/qdev-core.h" #include "qom/object.h" @@ -41,6 +41,15 @@ enum ipmi_op { IPMI_SEND_NMI }; +/* Channel properties */ +#define IPMI_CHANNEL_IPMB 0x00 +#define IPMI_CHANNEL_SYSTEM 0x0f +#define IPMI_CHANNEL_MEDIUM_IPMB 0x01 +#define IPMI_CHANNEL_MEDIUM_SYSTEM 0x0c +#define IPMI_CHANNEL_PROTOCOL_IPMB 0x01 +#define IPMI_CHANNEL_PROTOCOL_KCS 0x05 +#define IPMI_CHANNEL_PROTOCOL_BT_15 0x08 + #define IPMI_CC_INVALID_CMD 0xc1 #define IPMI_CC_COMMAND_INVALID_FOR_LUN 0xc2 #define IPMI_CC_TIMEOUT 0xc3 @@ -76,6 +85,7 @@ typedef struct IPMIFwInfo { int interface_type; uint8_t ipmi_spec_major_revision; uint8_t ipmi_spec_minor_revision; + uint8_t ipmi_channel_protocol; uint8_t i2c_slave_address; uint32_t uuid; @@ -91,6 +101,11 @@ typedef struct IPMIFwInfo { int interrupt_number; enum { + IPMI_NO_IRQ = 0, + IPMI_ISA_IRQ, + IPMI_PCI_IRQ, + } irq_source; + enum { IPMI_LEVEL_IRQ, IPMI_EDGE_IRQ } irq_type; diff --git a/include/hw/irq.h b/include/hw/irq.h index b301223..291fdd6 100644 --- a/include/hw/irq.h +++ b/include/hw/irq.h @@ -36,12 +36,33 @@ static inline void qemu_irq_pulse(qemu_irq irq) /* * Init a single IRQ. The irq is assigned with a handler, an opaque data - * and the interrupt number. + * and the interrupt number. The caller must free this with qemu_free_irq(). + * If you are using this inside a device's init or realize method, then + * qemu_init_irq_child() is probably a better choice to avoid the need + * to manually clean up the IRQ. */ void qemu_init_irq(IRQState *irq, qemu_irq_handler handler, void *opaque, int n); /** + * qemu_init_irq_child: Initialize IRQ and make it a QOM child + * @parent: QOM object which owns this IRQ + * @propname: child property name + * @irq: pointer to IRQState to initialize + * @handler: handler function for incoming interrupts + * @opaque: opaque data to pass to @handler + * @n: interrupt number to pass to @handler + * + * Init a single IRQ and make the IRQ object a child of @parent with + * the child-property name @propname. The IRQ object will thus be + * automatically freed when @parent is destroyed. + */ +void qemu_init_irq_child(Object *parent, const char *propname, + IRQState *irq, qemu_irq_handler handler, + void *opaque, int n); + + +/** * qemu_init_irqs: Initialize an array of IRQs. * * @irq: Array of IRQs to initialize diff --git a/include/hw/isa/apm.h b/include/hw/isa/apm.h index b6e070c..0834539 100644 --- a/include/hw/isa/apm.h +++ b/include/hw/isa/apm.h @@ -1,7 +1,7 @@ #ifndef APM_H #define APM_H -#include "exec/memory.h" +#include "system/memory.h" #define APM_CNT_IOPORT 0xb2 #define ACPI_PORT_SMI_CMD APM_CNT_IOPORT diff --git a/include/hw/isa/isa.h b/include/hw/isa/isa.h index 40d6224..a82c5f1 100644 --- a/include/hw/isa/isa.h +++ b/include/hw/isa/isa.h @@ -3,8 +3,8 @@ /* ISA bus */ -#include "exec/memory.h" -#include "exec/ioport.h" +#include "system/memory.h" +#include "system/ioport.h" #include "hw/qdev-core.h" #include "qom/object.h" diff --git a/include/hw/isa/vt82c686.h b/include/hw/isa/vt82c686.h index da1722d..ace9e66 100644 --- a/include/hw/isa/vt82c686.h +++ b/include/hw/isa/vt82c686.h @@ -2,7 +2,7 @@ #define HW_VT82C686_H #include "hw/pci/pci_device.h" -#include "audio/audio.h" +#include "qemu/audio.h" #define TYPE_VT82C686B_ISA "vt82c686b-isa" #define TYPE_VT82C686B_USB_UHCI "vt82c686b-usb-uhci" @@ -24,7 +24,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(ViaAC97State, VIA_AC97); struct ViaAC97State { PCIDevice dev; - QEMUSoundCard card; + AudioBackend *audio_be; MemoryRegion sgd; MemoryRegion fm; MemoryRegion midi; diff --git a/include/hw/loader.h b/include/hw/loader.h index d280dc3..d035e72 100644 --- a/include/hw/loader.h +++ b/include/hw/loader.h @@ -1,6 +1,7 @@ #ifndef LOADER_H #define LOADER_H #include "hw/nvram/fw_cfg.h" +#include "qemu/typedefs.h" /* loader.c */ /** @@ -10,7 +11,7 @@ * Returns the size of the image file on success, -1 otherwise. * On error, errno is also set as appropriate. */ -int64_t get_image_size(const char *filename); +int64_t get_image_size(const char *filename, Error **errp); /** * load_image_size: load an image file into specified buffer * @filename: Path to the image file @@ -41,7 +42,8 @@ ssize_t load_image_size(const char *filename, void *addr, size_t size); * Returns the size of the loaded image on success, -1 otherwise. */ ssize_t load_image_targphys_as(const char *filename, - hwaddr addr, uint64_t max_sz, AddressSpace *as); + hwaddr addr, uint64_t max_sz, AddressSpace *as, + Error **errp); /**load_targphys_hex_as: * @filename: Path to the .hex file @@ -61,7 +63,7 @@ ssize_t load_targphys_hex_as(const char *filename, hwaddr *entry, * an AddressSpace. */ ssize_t load_image_targphys(const char *filename, hwaddr, - uint64_t max_sz); + uint64_t max_sz, Error **errp); /** * load_image_mr: load an image into a memory region @@ -270,8 +272,6 @@ int rom_add_elf_program(const char *name, GMappedFile *mapped_file, void *data, AddressSpace *as); int rom_check_and_register_reset(void); void rom_set_fw(FWCfgState *f); -void rom_set_order_override(int order); -void rom_reset_order_override(void); /** * rom_transaction_begin: diff --git a/include/hw/loongarch/boot.h b/include/hw/loongarch/boot.h index b3b870d..9819f7f 100644 --- a/include/hw/loongarch/boot.h +++ b/include/hw/loongarch/boot.h @@ -102,11 +102,10 @@ struct loongarch_boot_info { const char *kernel_cmdline; const char *initrd_filename; uint64_t a0, a1, a2; + uint64_t initrd_addr; + uint64_t initrd_size; }; -extern struct memmap_entry *memmap_table; -extern unsigned memmap_entries; - struct memmap_entry { uint64_t address; uint64_t length; diff --git a/include/hw/loongarch/virt.h b/include/hw/loongarch/virt.h index 2b7d199..27b1755 100644 --- a/include/hw/loongarch/virt.h +++ b/include/hw/loongarch/virt.h @@ -13,28 +13,84 @@ #include "hw/block/flash.h" #include "hw/loongarch/boot.h" +/* IOCSR region */ +#define VERSION_REG 0x0 +#define FEATURE_REG 0x8 +#define IOCSRF_TEMP 0 +#define IOCSRF_NODECNT 1 +#define IOCSRF_MSI 2 +#define IOCSRF_EXTIOI 3 +#define IOCSRF_CSRIPI 4 +#define IOCSRF_FREQCSR 5 +#define IOCSRF_FREQSCALE 6 +#define IOCSRF_DVFSV1 7 +#define IOCSRF_GMOD 9 +#define IOCSRF_VM 11 +#define IOCSRF_DMSI 15 +#define VENDOR_REG 0x10 +#define CPUNAME_REG 0x20 +#define MISC_FUNC_REG 0x420 +#define IOCSRM_EXTIOI_EN 48 +#define IOCSRM_EXTIOI_INT_ENCODE 49 +#define IOCSRM_DMSI_EN 51 + #define LOONGARCH_MAX_CPUS 256 -#define VIRT_FWCFG_BASE 0x1e020000UL +/* MMIO memory region */ +#define VIRT_PCH_REG_BASE 0x10000000UL +#define VIRT_PCH_REG_SIZE 0x400 +#define VIRT_RTC_REG_BASE 0x100d0100UL +#define VIRT_RTC_LEN 0x100 +#define VIRT_PLATFORM_BUS_BASEADDRESS 0x16000000UL +#define VIRT_PLATFORM_BUS_SIZE 0x02000000 +#define VIRT_PCI_IO_BASE 0x18004000UL +#define VIRT_PCI_IO_OFFSET 0x4000 +#define VIRT_PCI_IO_SIZE 0xC000 #define VIRT_BIOS_BASE 0x1c000000UL -#define VIRT_BIOS_SIZE (16 * MiB) +#define VIRT_BIOS_SIZE 0x01000000UL #define VIRT_FLASH_SECTOR_SIZE (256 * KiB) #define VIRT_FLASH0_BASE VIRT_BIOS_BASE #define VIRT_FLASH0_SIZE VIRT_BIOS_SIZE #define VIRT_FLASH1_BASE 0x1d000000UL -#define VIRT_FLASH1_SIZE (16 * MiB) +#define VIRT_FLASH1_SIZE 0x01000000UL +#define VIRT_FWCFG_BASE 0x1e020000UL +#define VIRT_UART_BASE 0x1fe001e0UL +#define VIRT_UART_SIZE 0x100 +#define VIRT_PCI_CFG_BASE 0x20000000UL +#define VIRT_PCI_CFG_SIZE 0x08000000UL +#define VIRT_DINTC_BASE 0x2FE00000UL +#define VIRT_DINTC_SIZE 0x00100000UL +#define VIRT_PCH_MSI_ADDR_LOW 0x2FF00000UL +#define VIRT_PCH_MSI_SIZE 0x8 +#define VIRT_PCI_MEM_BASE 0x40000000UL +#define VIRT_PCI_MEM_SIZE 0x40000000UL #define VIRT_LOWMEM_BASE 0 #define VIRT_LOWMEM_SIZE 0x10000000 +#define FDT_BASE 0x100000 #define VIRT_HIGHMEM_BASE 0x80000000 #define VIRT_GED_EVT_ADDR 0x100e0000 -#define VIRT_GED_MEM_ADDR (VIRT_GED_EVT_ADDR + ACPI_GED_EVT_SEL_LEN) -#define VIRT_GED_REG_ADDR (VIRT_GED_MEM_ADDR + MEMORY_HOTPLUG_IO_LEN) -#define VIRT_GED_CPUHP_ADDR (VIRT_GED_REG_ADDR + ACPI_GED_REG_COUNT) +#define VIRT_GED_MEM_ADDR QEMU_ALIGN_UP(VIRT_GED_EVT_ADDR + ACPI_GED_EVT_SEL_LEN, 4) +#define VIRT_GED_REG_ADDR QEMU_ALIGN_UP(VIRT_GED_MEM_ADDR + MEMORY_HOTPLUG_IO_LEN, 4) +#define VIRT_GED_CPUHP_ADDR QEMU_ALIGN_UP(VIRT_GED_REG_ADDR + ACPI_GED_REG_COUNT, 4) -#define COMMAND_LINE_SIZE 512 +/* + * GSI_BASE is hard-coded with 64 in linux kernel, else kernel fails to boot + * 0 - 15 GSI for ISA devices even if there is no ISA devices + * 16 - 63 GSI for CPU devices such as timers/perf monitor etc + * 64 - GSI for external devices + */ +#define VIRT_PCH_PIC_IRQ_NUM 32 +#define VIRT_GSI_BASE 64 +#define VIRT_DEVICE_IRQS 16 +#define VIRT_UART_IRQ (VIRT_GSI_BASE + 2) +#define VIRT_UART_COUNT 4 +#define VIRT_RTC_IRQ (VIRT_GSI_BASE + 6) +#define VIRT_SCI_IRQ (VIRT_GSI_BASE + 7) +#define VIRT_PLATFORM_BUS_IRQ (VIRT_GSI_BASE + 8) +#define VIRT_PLATFORM_BUS_NUM_IRQS 2 -#define FDT_BASE 0x100000 +#define COMMAND_LINE_SIZE 512 struct LoongArchVirtMachineState { /*< private >*/ @@ -50,6 +106,7 @@ struct LoongArchVirtMachineState { Notifier powerdown_notifier; OnOffAuto acpi; OnOffAuto veiointc; + OnOffAuto dmsi; char *oem_id; char *oem_table_id; DeviceState *acpi_ged; @@ -63,6 +120,11 @@ struct LoongArchVirtMachineState { struct loongarch_boot_info bootinfo; DeviceState *ipi; DeviceState *extioi; + struct memmap_entry *memmap_table; + unsigned int memmap_entries; + uint64_t misc_feature; + uint64_t misc_status; + DeviceState *dintc; }; #define TYPE_LOONGARCH_VIRT_MACHINE MACHINE_TYPE_NAME("virt") @@ -70,6 +132,15 @@ OBJECT_DECLARE_SIMPLE_TYPE(LoongArchVirtMachineState, LOONGARCH_VIRT_MACHINE) void virt_acpi_setup(LoongArchVirtMachineState *lvms); void virt_fdt_setup(LoongArchVirtMachineState *lvms); +static inline bool virt_has_dmsi(LoongArchVirtMachineState *lvms) +{ + if (!(lvms->misc_feature & BIT(IOCSRF_DMSI))) { + return false; + } + + return true; +} + static inline bool virt_is_veiointc_enabled(LoongArchVirtMachineState *lvms) { if (lvms->veiointc == ON_OFF_AUTO_OFF) { diff --git a/include/hw/m68k/q800.h b/include/hw/m68k/q800.h index 34365c9..9caaed9 100644 --- a/include/hw/m68k/q800.h +++ b/include/hw/m68k/q800.h @@ -26,7 +26,7 @@ #include "hw/boards.h" #include "qom/object.h" #include "target/m68k/cpu-qom.h" -#include "exec/memory.h" +#include "system/memory.h" #include "hw/m68k/q800-glue.h" #include "hw/misc/mac_via.h" #include "hw/net/dp8393x.h" diff --git a/include/hw/mem/npcm7xx_mc.h b/include/hw/mem/npcm7xx_mc.h index 7ed38be..568cc35 100644 --- a/include/hw/mem/npcm7xx_mc.h +++ b/include/hw/mem/npcm7xx_mc.h @@ -16,7 +16,7 @@ #ifndef NPCM7XX_MC_H #define NPCM7XX_MC_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/sysbus.h" /** diff --git a/include/hw/mem/pc-dimm.h b/include/hw/mem/pc-dimm.h index fe0f3ea..e0dbdd4 100644 --- a/include/hw/mem/pc-dimm.h +++ b/include/hw/mem/pc-dimm.h @@ -16,7 +16,7 @@ #ifndef QEMU_PC_DIMM_H #define QEMU_PC_DIMM_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/qdev-core.h" #include "qom/object.h" diff --git a/include/hw/mips/mips.h b/include/hw/mips/mips.h index 101799f..1f3672b 100644 --- a/include/hw/mips/mips.h +++ b/include/hw/mips/mips.h @@ -7,7 +7,7 @@ /* Kernels can be configured with 64KB pages */ #define INITRD_PAGE_SIZE (64 * KiB) -#include "exec/memory.h" +#include "system/memory.h" /* bonito.c */ PCIBus *bonito_init(qemu_irq *pic); diff --git a/include/hw/misc/aspeed_hace.h b/include/hw/misc/aspeed_hace.h index 5d4aa19..d5d07c6 100644 --- a/include/hw/misc/aspeed_hace.h +++ b/include/hw/misc/aspeed_hace.h @@ -22,7 +22,6 @@ OBJECT_DECLARE_TYPE(AspeedHACEState, AspeedHACEClass, ASPEED_HACE) -#define ASPEED_HACE_NR_REGS (0x64 >> 2) #define ASPEED_HACE_MAX_SG 256 /* max number of entries */ struct AspeedHACEState { @@ -31,10 +30,8 @@ struct AspeedHACEState { MemoryRegion iomem; qemu_irq irq; - struct iovec iov_cache[ASPEED_HACE_MAX_SG]; - uint32_t regs[ASPEED_HACE_NR_REGS]; + uint32_t *regs; uint32_t total_req_len; - uint32_t iov_count; MemoryRegion *dram_mr; AddressSpace dram_as; @@ -46,11 +43,17 @@ struct AspeedHACEState { struct AspeedHACEClass { SysBusDeviceClass parent_class; + const MemoryRegionOps *reg_ops; uint32_t src_mask; uint32_t dest_mask; uint32_t key_mask; uint32_t hash_mask; + uint64_t nr_regs; bool raise_crypt_interrupt_workaround; + uint32_t src_hi_mask; + uint32_t dest_hi_mask; + uint32_t key_hi_mask; + bool has_dma64; }; #endif /* ASPEED_HACE_H */ diff --git a/include/hw/misc/aspeed_sbc.h b/include/hw/misc/aspeed_sbc.h index 405e678..7d640a0 100644 --- a/include/hw/misc/aspeed_sbc.h +++ b/include/hw/misc/aspeed_sbc.h @@ -10,9 +10,11 @@ #define ASPEED_SBC_H #include "hw/sysbus.h" +#include "hw/nvram/aspeed_otp.h" #define TYPE_ASPEED_SBC "aspeed.sbc" #define TYPE_ASPEED_AST2600_SBC TYPE_ASPEED_SBC "-ast2600" +#define TYPE_ASPEED_AST10X0_SBC TYPE_ASPEED_SBC "-ast10x0" OBJECT_DECLARE_TYPE(AspeedSBCState, AspeedSBCClass, ASPEED_SBC) #define ASPEED_SBC_NR_REGS (0x93c >> 2) @@ -36,10 +38,14 @@ struct AspeedSBCState { MemoryRegion iomem; uint32_t regs[ASPEED_SBC_NR_REGS]; + + AspeedOTPState otp; }; struct AspeedSBCClass { SysBusDeviceClass parent_class; + + bool has_otp; }; #endif /* ASPEED_SBC_H */ diff --git a/include/hw/misc/auxbus.h b/include/hw/misc/auxbus.h index 03cacde..0051e03 100644 --- a/include/hw/misc/auxbus.h +++ b/include/hw/misc/auxbus.h @@ -25,17 +25,19 @@ #ifndef HW_MISC_AUXBUS_H #define HW_MISC_AUXBUS_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/qdev-core.h" #include "qom/object.h" -typedef struct AUXSlave AUXSlave; typedef enum AUXCommand AUXCommand; typedef enum AUXReply AUXReply; #define TYPE_AUXTOI2C "aux-to-i2c-bridge" OBJECT_DECLARE_SIMPLE_TYPE(AUXTOI2CState, AUXTOI2C) +#define TYPE_AUX_SLAVE "aux-slave" +OBJECT_DECLARE_SIMPLE_TYPE(AUXSlave, AUX_SLAVE) + enum AUXCommand { WRITE_I2C = 0, READ_I2C = 1, @@ -73,9 +75,6 @@ struct AUXBus { AddressSpace aux_addr_space; }; -#define TYPE_AUX_SLAVE "aux-slave" -OBJECT_DECLARE_SIMPLE_TYPE(AUXSlave, AUX_SLAVE) - struct AUXSlave { /* < private > */ DeviceState parent_obj; diff --git a/include/hw/misc/bcm2835_mphi.h b/include/hw/misc/bcm2835_mphi.h index 751363f..3f1997e 100644 --- a/include/hw/misc/bcm2835_mphi.h +++ b/include/hw/misc/bcm2835_mphi.h @@ -23,7 +23,8 @@ #define MPHI_MMIO_SIZE 0x1000 -typedef struct BCM2835MphiState BCM2835MphiState; +#define TYPE_BCM2835_MPHI "bcm2835-mphi" +OBJECT_DECLARE_SIMPLE_TYPE(BCM2835MphiState, BCM2835_MPHI) struct BCM2835MphiState { SysBusDevice parent_obj; @@ -37,8 +38,4 @@ struct BCM2835MphiState { uint32_t swirq; }; -#define TYPE_BCM2835_MPHI "bcm2835-mphi" - -OBJECT_DECLARE_SIMPLE_TYPE(BCM2835MphiState, BCM2835_MPHI) - #endif diff --git a/include/hw/misc/ivshmem-flat.h b/include/hw/misc/ivshmem-flat.h index 0c2b015..d656e57 100644 --- a/include/hw/misc/ivshmem-flat.h +++ b/include/hw/misc/ivshmem-flat.h @@ -14,7 +14,7 @@ #include "qemu/queue.h" #include "qemu/event_notifier.h" #include "chardev/char-fe.h" -#include "exec/memory.h" +#include "system/memory.h" #include "qom/object.h" #include "hw/sysbus.h" @@ -36,7 +36,7 @@ typedef struct IvshmemFTState IvshmemFTState; DECLARE_INSTANCE_CHECKER(IvshmemFTState, IVSHMEM_FLAT, TYPE_IVSHMEM_FLAT) -/* Ivshmem registers. See ./docs/specs/ivshmem-spec.txt for details. */ +/* Ivshmem registers. See docs/specs/ivshmem-spec.rst for details. */ enum ivshmem_registers { INTMASK = 0, INTSTATUS = 4, @@ -65,7 +65,7 @@ struct IvshmemFTState { QTAILQ_HEAD(, IvshmemPeer) peer; IvshmemPeer own; - CharBackend server_chr; + CharFrontend server_chr; /* IRQ */ qemu_irq irq; diff --git a/include/hw/misc/lasi.h b/include/hw/misc/lasi.h index f01c0f6..0e95be1 100644 --- a/include/hw/misc/lasi.h +++ b/include/hw/misc/lasi.h @@ -12,9 +12,9 @@ #ifndef LASI_H #define LASI_H -#include "exec/address-spaces.h" -#include "hw/pci/pci_host.h" +#include "system/address-spaces.h" #include "hw/boards.h" +#include "hw/sysbus.h" #define TYPE_LASI_CHIP "lasi-chip" OBJECT_DECLARE_SIMPLE_TYPE(LasiState, LASI_CHIP) @@ -28,7 +28,9 @@ OBJECT_DECLARE_SIMPLE_TYPE(LasiState, LASI_CHIP) #define LASI_LPT 0x02000 #define LASI_AUDIO 0x04000 #define LASI_UART 0x05000 +#define LASI_SCSI 0x06000 #define LASI_LAN 0x07000 +#define LASI_PS2 0x08000 #define LASI_RTC 0x09000 #define LASI_FDC 0x0A000 @@ -61,7 +63,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(LasiState, LASI_CHIP) #define LASI_IRQ_PS2MOU_HPA 26 struct LasiState { - PCIHostState parent_obj; + SysBusDevice parent_obj; uint32_t irr; uint32_t imr; diff --git a/include/hw/misc/mac_via.h b/include/hw/misc/mac_via.h index 63cdcf7..6a15228 100644 --- a/include/hw/misc/mac_via.h +++ b/include/hw/misc/mac_via.h @@ -9,7 +9,7 @@ #ifndef HW_MISC_MAC_VIA_H #define HW_MISC_MAC_VIA_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/sysbus.h" #include "hw/misc/mos6522.h" #include "hw/input/adb.h" diff --git a/include/hw/misc/max78000_aes.h b/include/hw/misc/max78000_aes.h new file mode 100644 index 0000000..407c45e --- /dev/null +++ b/include/hw/misc/max78000_aes.h @@ -0,0 +1,68 @@ +/* + * MAX78000 AES + * + * Copyright (c) 2025 Jackson Donaldson <jcksn@duck.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ +#ifndef HW_MAX78000_AES_H +#define HW_MAX78000_AES_H + +#include "hw/sysbus.h" +#include "crypto/aes.h" +#include "qom/object.h" + +#define TYPE_MAX78000_AES "max78000-aes" +OBJECT_DECLARE_SIMPLE_TYPE(Max78000AesState, MAX78000_AES) + +#define CTRL 0 +#define STATUS 4 +#define INTFL 8 +#define INTEN 0xc +#define FIFO 0x10 + +#define KEY_BASE 0x400 +#define KEY_END 0x420 + +/* CTRL */ +#define TYPE (1 << 9 | 1 << 8) +#define KEY_SIZE (1 << 7 | 1 << 6) +#define OUTPUT_FLUSH (1 << 5) +#define INPUT_FLUSH (1 << 4) +#define START (1 << 3) + +#define AES_EN (1 << 0) + +/* STATUS */ +#define OUTPUT_FULL (1 << 4) +#define OUTPUT_EMPTY (1 << 3) +#define INPUT_FULL (1 << 2) +#define INPUT_EMPTY (1 << 1) +#define BUSY (1 << 0) + +/* INTFL*/ +#define DONE (1 << 0) + +struct Max78000AesState { + SysBusDevice parent_obj; + + MemoryRegion mmio; + + uint32_t ctrl; + uint32_t status; + uint32_t intfl; + uint32_t inten; + uint32_t data_index; + uint8_t data[16]; + + uint8_t key[32]; + AES_KEY internal_key; + + uint32_t result_index; + uint8_t result[16]; + + + qemu_irq irq; +}; + +#endif diff --git a/include/hw/misc/max78000_gcr.h b/include/hw/misc/max78000_gcr.h new file mode 100644 index 0000000..d5858a4 --- /dev/null +++ b/include/hw/misc/max78000_gcr.h @@ -0,0 +1,131 @@ +/* + * MAX78000 Global Control Register + * + * Copyright (c) 2025 Jackson Donaldson <jcksn@duck.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ +#ifndef HW_MAX78000_GCR_H +#define HW_MAX78000_GCR_H + +#include "hw/sysbus.h" +#include "qom/object.h" + +#define TYPE_MAX78000_GCR "max78000-gcr" +OBJECT_DECLARE_SIMPLE_TYPE(Max78000GcrState, MAX78000_GCR) + +#define SYSCTRL 0x0 +#define RST0 0x4 +#define CLKCTRL 0x8 +#define PM 0xc +#define PCLKDIV 0x18 +#define PCLKDIS0 0x24 +#define MEMCTRL 0x28 +#define MEMZ 0x2c +#define SYSST 0x40 +#define RST1 0x44 +#define PCKDIS1 0x48 +#define EVENTEN 0x4c +#define REVISION 0x50 +#define SYSIE 0x54 +#define ECCERR 0x64 +#define ECCED 0x68 +#define ECCIE 0x6c +#define ECCADDR 0x70 + +/* RST0 */ +#define SYSTEM_RESET (1 << 31) +#define PERIPHERAL_RESET (1 << 30) +#define SOFT_RESET (1 << 29) +#define UART2_RESET (1 << 28) + +#define ADC_RESET (1 << 26) +#define CNN_RESET (1 << 25) +#define TRNG_RESET (1 << 24) + +#define RTC_RESET (1 << 17) +#define I2C0_RESET (1 << 16) + +#define SPI1_RESET (1 << 13) +#define UART1_RESET (1 << 12) +#define UART0_RESET (1 << 11) + +#define TMR3_RESET (1 << 8) +#define TMR2_RESET (1 << 7) +#define TMR1_RESET (1 << 6) +#define TMR0_RESET (1 << 5) + +#define GPIO1_RESET (1 << 3) +#define GPIO0_RESET (1 << 2) +#define WDT0_RESET (1 << 1) +#define DMA_RESET (1 << 0) + +/* CLKCTRL */ +#define SYSCLK_RDY (1 << 13) + +/* MEMZ */ +#define ram0 (1 << 0) +#define ram1 (1 << 1) +#define ram2 (1 << 2) +#define ram3 (1 << 3) + +/* RST1 */ +#define CPU1_RESET (1 << 31) + +#define SIMO_RESET (1 << 25) +#define DVS_RESET (1 << 24) + +#define I2C2_RESET (1 << 20) +#define I2S_RESET (1 << 19) + +#define SMPHR_RESET (1 << 16) + +#define SPI0_RESET (1 << 11) +#define AES_RESET (1 << 10) +#define CRC_RESET (1 << 9) + +#define PT_RESET (1 << 1) +#define I2C1_RESET (1 << 0) + + +#define SYSRAM0_START 0x20000000 +#define SYSRAM1_START 0x20008000 +#define SYSRAM2_START 0x20010000 +#define SYSRAM3_START 0x2001C000 + +struct Max78000GcrState { + SysBusDevice parent_obj; + + MemoryRegion mmio; + + uint32_t sysctrl; + uint32_t rst0; + uint32_t clkctrl; + uint32_t pm; + uint32_t pclkdiv; + uint32_t pclkdis0; + uint32_t memctrl; + uint32_t memz; + uint32_t sysst; + uint32_t rst1; + uint32_t pckdis1; + uint32_t eventen; + uint32_t revision; + uint32_t sysie; + uint32_t eccerr; + uint32_t ecced; + uint32_t eccie; + uint32_t eccaddr; + + MemoryRegion *sram; + AddressSpace sram_as; + + DeviceState *uart0; + DeviceState *uart1; + DeviceState *uart2; + DeviceState *trng; + DeviceState *aes; + +}; + +#endif diff --git a/include/hw/misc/max78000_icc.h b/include/hw/misc/max78000_icc.h new file mode 100644 index 0000000..6fe2bb7 --- /dev/null +++ b/include/hw/misc/max78000_icc.h @@ -0,0 +1,33 @@ +/* + * MAX78000 Instruction Cache + * + * Copyright (c) 2025 Jackson Donaldson <jcksn@duck.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_MAX78000_ICC_H +#define HW_MAX78000_ICC_H + +#include "hw/sysbus.h" +#include "qom/object.h" + +#define TYPE_MAX78000_ICC "max78000-icc" +OBJECT_DECLARE_SIMPLE_TYPE(Max78000IccState, MAX78000_ICC) + +#define ICC_INFO 0x0 +#define ICC_SZ 0x4 +#define ICC_CTRL 0x100 +#define ICC_INVALIDATE 0x700 + +struct Max78000IccState { + SysBusDevice parent_obj; + + MemoryRegion mmio; + + uint32_t info; + uint32_t sz; + uint32_t ctrl; +}; + +#endif diff --git a/include/hw/misc/max78000_trng.h b/include/hw/misc/max78000_trng.h new file mode 100644 index 0000000..c5a8129 --- /dev/null +++ b/include/hw/misc/max78000_trng.h @@ -0,0 +1,35 @@ +/* + * MAX78000 True Random Number Generator + * + * Copyright (c) 2025 Jackson Donaldson <jcksn@duck.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ +#ifndef HW_MAX78000_TRNG_H +#define HW_MAX78000_TRNG_H + +#include "hw/sysbus.h" +#include "qom/object.h" + +#define TYPE_MAX78000_TRNG "max78000-trng" +OBJECT_DECLARE_SIMPLE_TYPE(Max78000TrngState, MAX78000_TRNG) + +#define CTRL 0 +#define STATUS 4 +#define DATA 8 + +#define RND_IE (1 << 1) + +struct Max78000TrngState { + SysBusDevice parent_obj; + + MemoryRegion mmio; + + uint32_t ctrl; + uint32_t status; + uint32_t data; + + qemu_irq irq; +}; + +#endif diff --git a/include/hw/misc/npcm7xx_mft.h b/include/hw/misc/npcm7xx_mft.h index d638438..e4b997a 100644 --- a/include/hw/misc/npcm7xx_mft.h +++ b/include/hw/misc/npcm7xx_mft.h @@ -16,7 +16,7 @@ #ifndef NPCM7XX_MFT_H #define NPCM7XX_MFT_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/clock.h" #include "hw/irq.h" #include "hw/sysbus.h" diff --git a/include/hw/misc/npcm7xx_pwm.h b/include/hw/misc/npcm7xx_pwm.h index bf95344..df92726 100644 --- a/include/hw/misc/npcm7xx_pwm.h +++ b/include/hw/misc/npcm7xx_pwm.h @@ -35,8 +35,8 @@ * value of 100,000 the duty cycle for that PWM is 10%. */ #define NPCM7XX_PWM_MAX_DUTY 1000000 - -typedef struct NPCM7xxPWMState NPCM7xxPWMState; +#define TYPE_NPCM7XX_PWM "npcm7xx-pwm" +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxPWMState, NPCM7XX_PWM) /** * struct NPCM7xxPWM - The state of a single PWM channel. @@ -100,7 +100,4 @@ struct NPCM7xxPWMState { uint32_t piir; }; -#define TYPE_NPCM7XX_PWM "npcm7xx-pwm" -OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxPWMState, NPCM7XX_PWM) - #endif /* NPCM7XX_PWM_H */ diff --git a/include/hw/misc/npcm_clk.h b/include/hw/misc/npcm_clk.h index 8fa1e14..52e972f 100644 --- a/include/hw/misc/npcm_clk.h +++ b/include/hw/misc/npcm_clk.h @@ -16,7 +16,7 @@ #ifndef NPCM_CLK_H #define NPCM_CLK_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/clock.h" #include "hw/sysbus.h" diff --git a/include/hw/misc/npcm_gcr.h b/include/hw/misc/npcm_gcr.h index d81bb9a..702e7fd 100644 --- a/include/hw/misc/npcm_gcr.h +++ b/include/hw/misc/npcm_gcr.h @@ -16,7 +16,7 @@ #ifndef NPCM_GCR_H #define NPCM_GCR_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/sysbus.h" #include "qom/object.h" diff --git a/include/hw/misc/pvpanic.h b/include/hw/misc/pvpanic.h index 049a94c..5098693 100644 --- a/include/hw/misc/pvpanic.h +++ b/include/hw/misc/pvpanic.h @@ -15,7 +15,7 @@ #ifndef HW_MISC_PVPANIC_H #define HW_MISC_PVPANIC_H -#include "exec/memory.h" +#include "system/memory.h" #include "qom/object.h" #include "standard-headers/misc/pvpanic.h" diff --git a/include/hw/misc/xlnx-versal-crl.h b/include/hw/misc/xlnx-versal-crl.h index dba6d35..49ed500 100644 --- a/include/hw/misc/xlnx-versal-crl.h +++ b/include/hw/misc/xlnx-versal-crl.h @@ -2,6 +2,7 @@ * QEMU model of the Clock-Reset-LPD (CRL). * * Copyright (c) 2022 Xilinx Inc. + * Copyright (c) 2025 Advanced Micro Devices, Inc. * SPDX-License-Identifier: GPL-2.0-or-later * * Written by Edgar E. Iglesias <edgar.iglesias@xilinx.com> @@ -12,9 +13,16 @@ #include "hw/sysbus.h" #include "hw/register.h" #include "target/arm/cpu-qom.h" +#include "hw/arm/xlnx-versal-version.h" +#define TYPE_XLNX_VERSAL_CRL_BASE "xlnx-versal-crl-base" #define TYPE_XLNX_VERSAL_CRL "xlnx-versal-crl" +#define TYPE_XLNX_VERSAL2_CRL "xlnx-versal2-crl" + +OBJECT_DECLARE_TYPE(XlnxVersalCRLBase, XlnxVersalCRLBaseClass, + XLNX_VERSAL_CRL_BASE) OBJECT_DECLARE_SIMPLE_TYPE(XlnxVersalCRL, XLNX_VERSAL_CRL) +OBJECT_DECLARE_SIMPLE_TYPE(XlnxVersal2CRL, XLNX_VERSAL2_CRL) REG32(ERR_CTRL, 0x0) FIELD(ERR_CTRL, SLVERR_ENABLE, 0, 1) @@ -214,22 +222,369 @@ REG32(PSM_RST_MODE, 0x370) #define CRL_R_MAX (R_PSM_RST_MODE + 1) -#define RPU_MAX_CPU 2 +REG32(VERSAL2_ERR_CTRL, 0x0) +REG32(VERSAL2_WPROT, 0x1c) + FIELD(VERSAL2_WPROT, ACTIVE, 0, 1) +REG32(VERSAL2_RPLL_CTRL, 0x40) + FIELD(VERSAL2_RPLL_CTRL, POST_SRC, 24, 3) + FIELD(VERSAL2_RPLL_CTRL, PRE_SRC, 20, 3) + FIELD(VERSAL2_RPLL_CTRL, CLKOUTDIV, 16, 2) + FIELD(VERSAL2_RPLL_CTRL, FBDIV, 8, 8) + FIELD(VERSAL2_RPLL_CTRL, BYPASS, 3, 1) + FIELD(VERSAL2_RPLL_CTRL, RESET, 0, 1) +REG32(VERSAL2_RPLL_CFG, 0x44) + FIELD(VERSAL2_RPLL_CFG, LOCK_DLY, 25, 7) + FIELD(VERSAL2_RPLL_CFG, LOCK_CNT, 13, 10) + FIELD(VERSAL2_RPLL_CFG, LFHF, 10, 2) + FIELD(VERSAL2_RPLL_CFG, CP, 5, 4) + FIELD(VERSAL2_RPLL_CFG, RES, 0, 4) +REG32(VERSAL2_FLXPLL_CTRL, 0x50) + FIELD(VERSAL2_FLXPLL_CTRL, POST_SRC, 24, 3) + FIELD(VERSAL2_FLXPLL_CTRL, PRE_SRC, 20, 3) + FIELD(VERSAL2_FLXPLL_CTRL, CLKOUTDIV, 16, 2) + FIELD(VERSAL2_FLXPLL_CTRL, FBDIV, 8, 8) + FIELD(VERSAL2_FLXPLL_CTRL, BYPASS, 3, 1) + FIELD(VERSAL2_FLXPLL_CTRL, RESET, 0, 1) +REG32(VERSAL2_FLXPLL_CFG, 0x54) + FIELD(VERSAL2_FLXPLL_CFG, LOCK_DLY, 25, 7) + FIELD(VERSAL2_FLXPLL_CFG, LOCK_CNT, 13, 10) + FIELD(VERSAL2_FLXPLL_CFG, LFHF, 10, 2) + FIELD(VERSAL2_FLXPLL_CFG, CP, 5, 4) + FIELD(VERSAL2_FLXPLL_CFG, RES, 0, 4) +REG32(VERSAL2_PLL_STATUS, 0x60) + FIELD(VERSAL2_PLL_STATUS, FLXPLL_STABLE, 3, 1) + FIELD(VERSAL2_PLL_STATUS, RPLL_STABLE, 2, 1) + FIELD(VERSAL2_PLL_STATUS, FLXPLL_LOCK, 1, 1) + FIELD(VERSAL2_PLL_STATUS, RPLL_LOCK, 0, 1) +REG32(VERSAL2_RPLL_TO_XPD_CTRL, 0x100) + FIELD(VERSAL2_RPLL_TO_XPD_CTRL, DIVISOR0, 8, 10) +REG32(VERSAL2_LPX_TOP_SWITCH_CTRL, 0x104) + FIELD(VERSAL2_LPX_TOP_SWITCH_CTRL, CLKACT_ADMA, 26, 1) + FIELD(VERSAL2_LPX_TOP_SWITCH_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_LPX_TOP_SWITCH_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_LPX_TOP_SWITCH_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_LPX_LSBUS_CLK_CTRL, 0x108) + FIELD(VERSAL2_LPX_LSBUS_CLK_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_LPX_LSBUS_CLK_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_LPX_LSBUS_CLK_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_RPU_CLK_CTRL, 0x10c) + FIELD(VERSAL2_RPU_CLK_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_RPU_CLK_CTRL, CLKACT_CLUSTERE, 24, 1) + FIELD(VERSAL2_RPU_CLK_CTRL, CLKACT_CLUSTERD, 23, 1) + FIELD(VERSAL2_RPU_CLK_CTRL, CLKACT_CLUSTERC, 22, 1) + FIELD(VERSAL2_RPU_CLK_CTRL, CLKACT_CLUSTERB, 21, 1) + FIELD(VERSAL2_RPU_CLK_CTRL, CLKACT_CLUSTERA, 20, 1) + FIELD(VERSAL2_RPU_CLK_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_RPU_CLK_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_OCM_CLK_CTRL, 0x120) + FIELD(VERSAL2_OCM_CLK_CTRL, CLKACT_OCM3, 24, 1) + FIELD(VERSAL2_OCM_CLK_CTRL, CLKACT_OCM2, 23, 1) + FIELD(VERSAL2_OCM_CLK_CTRL, CLKACT_OCM1, 22, 1) + FIELD(VERSAL2_OCM_CLK_CTRL, CLKACT_OCM0, 21, 1) +REG32(VERSAL2_IOU_SWITCH_CLK_CTRL, 0x124) + FIELD(VERSAL2_IOU_SWITCH_CLK_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_IOU_SWITCH_CLK_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_IOU_SWITCH_CLK_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_GEM0_REF_CTRL, 0x128) + FIELD(VERSAL2_GEM0_REF_CTRL, CLKACT_RX, 27, 1) + FIELD(VERSAL2_GEM0_REF_CTRL, CLKACT_TX, 26, 1) + FIELD(VERSAL2_GEM0_REF_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_GEM0_REF_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_GEM0_REF_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_GEM1_REF_CTRL, 0x12c) + FIELD(VERSAL2_GEM1_REF_CTRL, CLKACT_RX, 27, 1) + FIELD(VERSAL2_GEM1_REF_CTRL, CLKACT_TX, 26, 1) + FIELD(VERSAL2_GEM1_REF_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_GEM1_REF_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_GEM1_REF_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_GEM_TSU_REF_CLK_CTRL, 0x130) + FIELD(VERSAL2_GEM_TSU_REF_CLK_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_GEM_TSU_REF_CLK_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_GEM_TSU_REF_CLK_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_USB0_BUS_REF_CLK_CTRL, 0x134) + FIELD(VERSAL2_USB0_BUS_REF_CLK_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_USB0_BUS_REF_CLK_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_USB0_BUS_REF_CLK_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_USB1_BUS_REF_CLK_CTRL, 0x138) + FIELD(VERSAL2_USB1_BUS_REF_CLK_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_USB1_BUS_REF_CLK_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_USB1_BUS_REF_CLK_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_UART0_REF_CLK_CTRL, 0x13c) + FIELD(VERSAL2_UART0_REF_CLK_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_UART0_REF_CLK_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_UART0_REF_CLK_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_UART1_REF_CLK_CTRL, 0x140) + FIELD(VERSAL2_UART1_REF_CLK_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_UART1_REF_CLK_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_UART1_REF_CLK_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_SPI0_REF_CLK_CTRL, 0x144) + FIELD(VERSAL2_SPI0_REF_CLK_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_SPI0_REF_CLK_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_SPI0_REF_CLK_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_SPI1_REF_CLK_CTRL, 0x148) + FIELD(VERSAL2_SPI1_REF_CLK_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_SPI1_REF_CLK_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_SPI1_REF_CLK_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_CAN0_REF_2X_CTRL, 0x14c) + FIELD(VERSAL2_CAN0_REF_2X_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_CAN0_REF_2X_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_CAN0_REF_2X_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_CAN1_REF_2X_CTRL, 0x150) + FIELD(VERSAL2_CAN1_REF_2X_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_CAN1_REF_2X_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_CAN1_REF_2X_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_CAN2_REF_2X_CTRL, 0x154) + FIELD(VERSAL2_CAN2_REF_2X_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_CAN2_REF_2X_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_CAN2_REF_2X_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_CAN3_REF_2X_CTRL, 0x158) + FIELD(VERSAL2_CAN3_REF_2X_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_CAN3_REF_2X_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_CAN3_REF_2X_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_I3C0_REF_CTRL, 0x15c) + FIELD(VERSAL2_I3C0_REF_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_I3C0_REF_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_I3C0_REF_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_I3C1_REF_CTRL, 0x160) + FIELD(VERSAL2_I3C1_REF_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_I3C1_REF_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_I3C1_REF_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_I3C2_REF_CTRL, 0x164) + FIELD(VERSAL2_I3C2_REF_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_I3C2_REF_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_I3C2_REF_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_I3C3_REF_CTRL, 0x168) + FIELD(VERSAL2_I3C3_REF_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_I3C3_REF_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_I3C3_REF_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_I3C4_REF_CTRL, 0x16c) + FIELD(VERSAL2_I3C4_REF_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_I3C4_REF_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_I3C4_REF_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_I3C5_REF_CTRL, 0x170) + FIELD(VERSAL2_I3C5_REF_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_I3C5_REF_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_I3C5_REF_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_I3C6_REF_CTRL, 0x174) + FIELD(VERSAL2_I3C6_REF_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_I3C6_REF_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_I3C6_REF_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_I3C7_REF_CTRL, 0x178) + FIELD(VERSAL2_I3C7_REF_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_I3C7_REF_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_I3C7_REF_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_DBG_LPX_CTRL, 0x17c) + FIELD(VERSAL2_DBG_LPX_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_DBG_LPX_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_DBG_LPX_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_TIMESTAMP_REF_CTRL, 0x180) + FIELD(VERSAL2_TIMESTAMP_REF_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_TIMESTAMP_REF_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_TIMESTAMP_REF_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_SAFETY_CHK, 0x184) +REG32(VERSAL2_ASU_CLK_CTRL, 0x188) + FIELD(VERSAL2_ASU_CLK_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_ASU_CLK_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_DBG_TSTMP_CLK_CTRL, 0x18c) + FIELD(VERSAL2_DBG_TSTMP_CLK_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_DBG_TSTMP_CLK_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_DBG_TSTMP_CLK_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_MMI_TOPSW_CLK_CTRL, 0x190) + FIELD(VERSAL2_MMI_TOPSW_CLK_CTRL, CLKACT, 25, 1) + FIELD(VERSAL2_MMI_TOPSW_CLK_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_MMI_TOPSW_CLK_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_WWDT_PLL_CLK_CTRL, 0x194) + FIELD(VERSAL2_WWDT_PLL_CLK_CTRL, DIVISOR0, 8, 10) + FIELD(VERSAL2_WWDT_PLL_CLK_CTRL, SRCSEL, 0, 3) +REG32(VERSAL2_RCLK_CTRL, 0x1a0) + FIELD(VERSAL2_RCLK_CTRL, CLKACT, 8, 6) + FIELD(VERSAL2_RCLK_CTRL, SELECT, 0, 6) +REG32(VERSAL2_RST_RPU_A, 0x310) + FIELD(VERSAL2_RST_RPU_A, TOPRESET, 16, 1) + FIELD(VERSAL2_RST_RPU_A, CORE1_POR, 9, 1) + FIELD(VERSAL2_RST_RPU_A, CORE0_POR, 8, 1) + FIELD(VERSAL2_RST_RPU_A, CORE1_RESET, 1, 1) + FIELD(VERSAL2_RST_RPU_A, CORE0_RESET, 0, 1) +REG32(VERSAL2_RST_RPU_B, 0x314) + FIELD(VERSAL2_RST_RPU_B, TOPRESET, 16, 1) + FIELD(VERSAL2_RST_RPU_B, CORE1_POR, 9, 1) + FIELD(VERSAL2_RST_RPU_B, CORE0_POR, 8, 1) + FIELD(VERSAL2_RST_RPU_B, CORE1_RESET, 1, 1) + FIELD(VERSAL2_RST_RPU_B, CORE0_RESET, 0, 1) +REG32(VERSAL2_RST_RPU_C, 0x318) + FIELD(VERSAL2_RST_RPU_C, TOPRESET, 16, 1) + FIELD(VERSAL2_RST_RPU_C, CORE1_POR, 9, 1) + FIELD(VERSAL2_RST_RPU_C, CORE0_POR, 8, 1) + FIELD(VERSAL2_RST_RPU_C, CORE1_RESET, 1, 1) + FIELD(VERSAL2_RST_RPU_C, CORE0_RESET, 0, 1) +REG32(VERSAL2_RST_RPU_D, 0x31c) + FIELD(VERSAL2_RST_RPU_D, TOPRESET, 16, 1) + FIELD(VERSAL2_RST_RPU_D, CORE1_POR, 9, 1) + FIELD(VERSAL2_RST_RPU_D, CORE0_POR, 8, 1) + FIELD(VERSAL2_RST_RPU_D, CORE1_RESET, 1, 1) + FIELD(VERSAL2_RST_RPU_D, CORE0_RESET, 0, 1) +REG32(VERSAL2_RST_RPU_E, 0x320) + FIELD(VERSAL2_RST_RPU_E, TOPRESET, 16, 1) + FIELD(VERSAL2_RST_RPU_E, CORE1_POR, 9, 1) + FIELD(VERSAL2_RST_RPU_E, CORE0_POR, 8, 1) + FIELD(VERSAL2_RST_RPU_E, CORE1_RESET, 1, 1) + FIELD(VERSAL2_RST_RPU_E, CORE0_RESET, 0, 1) +REG32(VERSAL2_RST_RPU_GD_0, 0x324) + FIELD(VERSAL2_RST_RPU_GD_0, RESET, 1, 1) + FIELD(VERSAL2_RST_RPU_GD_0, TOP_RESET, 0, 1) +REG32(VERSAL2_RST_RPU_GD_1, 0x328) + FIELD(VERSAL2_RST_RPU_GD_1, RESET, 1, 1) + FIELD(VERSAL2_RST_RPU_GD_1, TOP_RESET, 0, 1) +REG32(VERSAL2_RST_ASU_GD, 0x32c) + FIELD(VERSAL2_RST_ASU_GD, RESET, 1, 1) + FIELD(VERSAL2_RST_ASU_GD, TOP_RESET, 0, 1) +REG32(VERSAL2_RST_ADMA, 0x334) + FIELD(VERSAL2_RST_ADMA, RESET, 0, 1) +REG32(VERSAL2_RST_SDMA, 0x338) + FIELD(VERSAL2_RST_SDMA, RESET, 0, 1) +REG32(VERSAL2_RST_GEM0, 0x33c) + FIELD(VERSAL2_RST_GEM0, RESET, 0, 1) +REG32(VERSAL2_RST_GEM1, 0x340) + FIELD(VERSAL2_RST_GEM1, RESET, 0, 1) +REG32(VERSAL2_RST_USB0, 0x348) + FIELD(VERSAL2_RST_USB0, RESET, 0, 1) +REG32(VERSAL2_RST_USB1, 0x34c) + FIELD(VERSAL2_RST_USB1, RESET, 0, 1) +REG32(VERSAL2_RST_UART0, 0x350) + FIELD(VERSAL2_RST_UART0, RESET, 0, 1) +REG32(VERSAL2_RST_UART1, 0x354) + FIELD(VERSAL2_RST_UART1, RESET, 0, 1) +REG32(VERSAL2_RST_SPI0, 0x358) + FIELD(VERSAL2_RST_SPI0, RESET, 0, 1) +REG32(VERSAL2_RST_SPI1, 0x35c) + FIELD(VERSAL2_RST_SPI1, RESET, 0, 1) +REG32(VERSAL2_RST_CAN0, 0x360) + FIELD(VERSAL2_RST_CAN0, RESET, 0, 1) +REG32(VERSAL2_RST_CAN1, 0x364) + FIELD(VERSAL2_RST_CAN1, RESET, 0, 1) +REG32(VERSAL2_RST_CAN2, 0x368) + FIELD(VERSAL2_RST_CAN2, RESET, 0, 1) +REG32(VERSAL2_RST_CAN3, 0x36c) + FIELD(VERSAL2_RST_CAN3, RESET, 0, 1) +REG32(VERSAL2_RST_I3C0, 0x374) + FIELD(VERSAL2_RST_I3C0, RESET, 0, 1) +REG32(VERSAL2_RST_I3C1, 0x378) + FIELD(VERSAL2_RST_I3C1, RESET, 0, 1) +REG32(VERSAL2_RST_I3C2, 0x37c) + FIELD(VERSAL2_RST_I3C2, RESET, 0, 1) +REG32(VERSAL2_RST_I3C3, 0x380) + FIELD(VERSAL2_RST_I3C3, RESET, 0, 1) +REG32(VERSAL2_RST_I3C4, 0x384) + FIELD(VERSAL2_RST_I3C4, RESET, 0, 1) +REG32(VERSAL2_RST_I3C5, 0x388) + FIELD(VERSAL2_RST_I3C5, RESET, 0, 1) +REG32(VERSAL2_RST_I3C6, 0x38c) + FIELD(VERSAL2_RST_I3C6, RESET, 0, 1) +REG32(VERSAL2_RST_I3C7, 0x390) + FIELD(VERSAL2_RST_I3C7, RESET, 0, 1) +REG32(VERSAL2_RST_DBG_LPX, 0x398) + FIELD(VERSAL2_RST_DBG_LPX, RESET_HSDP, 1, 1) + FIELD(VERSAL2_RST_DBG_LPX, RESET, 0, 1) +REG32(VERSAL2_RST_GPIO, 0x39c) + FIELD(VERSAL2_RST_GPIO, RESET, 0, 1) +REG32(VERSAL2_RST_TTC, 0x3a0) + FIELD(VERSAL2_RST_TTC, TTC7_RESET, 7, 1) + FIELD(VERSAL2_RST_TTC, TTC6_RESET, 6, 1) + FIELD(VERSAL2_RST_TTC, TTC5_RESET, 5, 1) + FIELD(VERSAL2_RST_TTC, TTC4_RESET, 4, 1) + FIELD(VERSAL2_RST_TTC, TTC3_RESET, 3, 1) + FIELD(VERSAL2_RST_TTC, TTC2_RESET, 2, 1) + FIELD(VERSAL2_RST_TTC, TTC1_RESET, 1, 1) + FIELD(VERSAL2_RST_TTC, TTC0_RESET, 0, 1) +REG32(VERSAL2_RST_TIMESTAMP, 0x3a4) + FIELD(VERSAL2_RST_TIMESTAMP, RESET, 0, 1) +REG32(VERSAL2_RST_SWDT0, 0x3a8) + FIELD(VERSAL2_RST_SWDT0, RESET, 0, 1) +REG32(VERSAL2_RST_SWDT1, 0x3ac) + FIELD(VERSAL2_RST_SWDT1, RESET, 0, 1) +REG32(VERSAL2_RST_SWDT2, 0x3b0) + FIELD(VERSAL2_RST_SWDT2, RESET, 0, 1) +REG32(VERSAL2_RST_SWDT3, 0x3b4) + FIELD(VERSAL2_RST_SWDT3, RESET, 0, 1) +REG32(VERSAL2_RST_SWDT4, 0x3b8) + FIELD(VERSAL2_RST_SWDT4, RESET, 0, 1) +REG32(VERSAL2_RST_IPI, 0x3bc) + FIELD(VERSAL2_RST_IPI, RESET, 0, 1) +REG32(VERSAL2_RST_SYSMON, 0x3c0) + FIELD(VERSAL2_RST_SYSMON, CFG_RST, 0, 1) +REG32(VERSAL2_ASU_MB_RST_MODE, 0x3c4) + FIELD(VERSAL2_ASU_MB_RST_MODE, WAKEUP, 2, 1) + FIELD(VERSAL2_ASU_MB_RST_MODE, RST_MODE, 0, 2) +REG32(VERSAL2_FPX_TOPSW_MUX_CTRL, 0x3c8) + FIELD(VERSAL2_FPX_TOPSW_MUX_CTRL, SELECT, 0, 1) +REG32(VERSAL2_RST_FPX, 0x3d0) + FIELD(VERSAL2_RST_FPX, SRST, 1, 1) + FIELD(VERSAL2_RST_FPX, POR, 0, 1) +REG32(VERSAL2_RST_MMI, 0x3d4) + FIELD(VERSAL2_RST_MMI, POR, 0, 1) +REG32(VERSAL2_RST_OCM, 0x3d8) + FIELD(VERSAL2_RST_OCM, RESET_OCM3, 3, 1) + FIELD(VERSAL2_RST_OCM, RESET_OCM2, 2, 1) + FIELD(VERSAL2_RST_OCM, RESET_OCM1, 1, 1) + FIELD(VERSAL2_RST_OCM, RESET_OCM0, 0, 1) -struct XlnxVersalCRL { +#define VERSAL2_CRL_R_MAX (R_VERSAL2_RST_OCM + 1) + +struct XlnxVersalCRLBase { SysBusDevice parent_obj; + + uint32_t *regs; +}; + +struct XlnxVersalCRLBaseClass { + SysBusDeviceClass parent_class; + + DeviceState ** (*decode_periph_rst)(XlnxVersalCRLBase *s, hwaddr, size_t *); +}; + +struct XlnxVersalCRL { + XlnxVersalCRLBase parent_obj; qemu_irq irq; struct { - ARMCPU *cpu_r5[RPU_MAX_CPU]; + DeviceState *rpu[2]; DeviceState *adma[8]; DeviceState *uart[2]; DeviceState *gem[2]; - DeviceState *usb; + DeviceState *usb[1]; } cfg; - RegisterInfoArray *reg_array; uint32_t regs[CRL_R_MAX]; RegisterInfo regs_info[CRL_R_MAX]; }; + +struct XlnxVersal2CRL { + XlnxVersalCRLBase parent_obj; + + struct { + DeviceState *rpu[10]; + DeviceState *adma[8]; + DeviceState *sdma[8]; + DeviceState *uart[2]; + DeviceState *gem[2]; + DeviceState *usb[2]; + DeviceState *can[4]; + } cfg; + + RegisterInfo regs_info[VERSAL2_CRL_R_MAX]; + uint32_t regs[VERSAL2_CRL_R_MAX]; +}; + +static inline const char *xlnx_versal_crl_class_name(VersalVersion ver) +{ + switch (ver) { + case VERSAL_VER_VERSAL: + return TYPE_XLNX_VERSAL_CRL; + case VERSAL_VER_VERSAL2: + return TYPE_XLNX_VERSAL2_CRL; + default: + g_assert_not_reached(); + } +} + #endif diff --git a/include/hw/misc/xlnx-versal-xramc.h b/include/hw/misc/xlnx-versal-xramc.h index d3d1862..35e4e8b 100644 --- a/include/hw/misc/xlnx-versal-xramc.h +++ b/include/hw/misc/xlnx-versal-xramc.h @@ -90,7 +90,6 @@ typedef struct XlnxXramCtrl { unsigned int encoded_size; } cfg; - RegisterInfoArray *reg_array; uint32_t regs[XRAM_CTRL_R_MAX]; RegisterInfo regs_info[XRAM_CTRL_R_MAX]; } XlnxXramCtrl; diff --git a/include/hw/misc/xlnx-zynqmp-apu-ctrl.h b/include/hw/misc/xlnx-zynqmp-apu-ctrl.h index c3bf3c1..fbfe34a 100644 --- a/include/hw/misc/xlnx-zynqmp-apu-ctrl.h +++ b/include/hw/misc/xlnx-zynqmp-apu-ctrl.h @@ -85,7 +85,6 @@ struct XlnxZynqMPAPUCtrl { uint8_t cpu_pwrdwn_req; uint8_t cpu_in_wfi; - RegisterInfoArray *reg_array; uint32_t regs[APU_R_MAX]; RegisterInfo regs_info[APU_R_MAX]; }; diff --git a/include/hw/misc/xlnx-zynqmp-crf.h b/include/hw/misc/xlnx-zynqmp-crf.h index 02ef0bd..c746ae1 100644 --- a/include/hw/misc/xlnx-zynqmp-crf.h +++ b/include/hw/misc/xlnx-zynqmp-crf.h @@ -203,7 +203,6 @@ struct XlnxZynqMPCRF { MemoryRegion iomem; qemu_irq irq_ir; - RegisterInfoArray *reg_array; uint32_t regs[CRF_R_MAX]; RegisterInfo regs_info[CRF_R_MAX]; }; diff --git a/include/hw/net/cadence_gem.h b/include/hw/net/cadence_gem.h index 91ebb5c..e63941f 100644 --- a/include/hw/net/cadence_gem.h +++ b/include/hw/net/cadence_gem.h @@ -62,6 +62,7 @@ struct CadenceGEMState { uint8_t num_type2_screeners; uint32_t revision; uint16_t jumbo_max_len; + bool pcs_enabled; /* GEM registers backing store */ uint32_t regs[CADENCE_GEM_MAXREG]; @@ -81,6 +82,9 @@ struct CadenceGEMState { uint8_t phy_loop; /* Are we in phy loopback? */ + bool phy_connected; /* true if connected */ + struct CadenceGEMState *phy_consumer; + /* The current DMA descriptor pointers */ uint32_t rx_desc_addr[MAX_PRIORITY_QUEUES]; uint32_t tx_desc_addr[MAX_PRIORITY_QUEUES]; diff --git a/include/hw/net/dp8393x.h b/include/hw/net/dp8393x.h index 4a3f747..24273dc 100644 --- a/include/hw/net/dp8393x.h +++ b/include/hw/net/dp8393x.h @@ -22,7 +22,7 @@ #include "hw/sysbus.h" #include "net/net.h" -#include "exec/memory.h" +#include "system/memory.h" #define SONIC_REG_COUNT 0x40 diff --git a/include/hw/net/lasi_82596.h b/include/hw/net/lasi_82596.h index 439356e..c46a4a1 100644 --- a/include/hw/net/lasi_82596.h +++ b/include/hw/net/lasi_82596.h @@ -25,7 +25,4 @@ struct SysBusI82596State { int val_index:1; }; -SysBusI82596State *lasi_82596_init(MemoryRegion *addr_space, hwaddr hpa, - qemu_irq irq, gboolean match_default); - #endif diff --git a/include/hw/net/msf2-emac.h b/include/hw/net/msf2-emac.h index 846ba6e..b5d9127 100644 --- a/include/hw/net/msf2-emac.h +++ b/include/hw/net/msf2-emac.h @@ -23,7 +23,7 @@ */ #include "hw/sysbus.h" -#include "exec/memory.h" +#include "system/memory.h" #include "net/net.h" #include "net/eth.h" #include "qom/object.h" diff --git a/include/hw/net/xlnx-versal-canfd.h b/include/hw/net/xlnx-versal-canfd.h index ad3104d..396f90d 100644 --- a/include/hw/net/xlnx-versal-canfd.h +++ b/include/hw/net/xlnx-versal-canfd.h @@ -54,14 +54,6 @@ typedef struct XlnxVersalCANFDState { qemu_irq irq_addr_err; RegisterInfo reg_info[XLNX_VERSAL_CANFD_R_MAX]; - RegisterAccessInfo *tx_regs; - RegisterAccessInfo *rx0_regs; - RegisterAccessInfo *rx1_regs; - RegisterAccessInfo *af_regs; - RegisterAccessInfo *txe_regs; - RegisterAccessInfo *rx_mailbox_regs; - RegisterAccessInfo *af_mask_regs_mailbox; - uint32_t regs[XLNX_VERSAL_CANFD_R_MAX]; ptimer_state *canfd_timer; diff --git a/include/hw/nubus/nubus.h b/include/hw/nubus/nubus.h index fee79b7..7825840 100644 --- a/include/hw/nubus/nubus.h +++ b/include/hw/nubus/nubus.h @@ -11,7 +11,7 @@ #include "hw/qdev-properties.h" #include "hw/sysbus.h" -#include "exec/address-spaces.h" +#include "system/address-spaces.h" #include "qom/object.h" #include "qemu/units.h" diff --git a/include/hw/nvram/aspeed_otp.h b/include/hw/nvram/aspeed_otp.h new file mode 100644 index 0000000..3752353 --- /dev/null +++ b/include/hw/nvram/aspeed_otp.h @@ -0,0 +1,33 @@ +/* + * ASPEED OTP (One-Time Programmable) memory + * + * Copyright (C) 2025 Aspeed + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef ASPEED_OTP_H +#define ASPEED_OTP_H + +#include "system/memory.h" +#include "hw/block/block.h" +#include "system/address-spaces.h" + +#define TYPE_ASPEED_OTP "aspeed-otp" +OBJECT_DECLARE_SIMPLE_TYPE(AspeedOTPState, ASPEED_OTP) + +typedef struct AspeedOTPState { + DeviceState parent_obj; + + BlockBackend *blk; + + uint64_t size; + + AddressSpace as; + + MemoryRegion mmio; + + uint8_t *storage; +} AspeedOTPState; + +#endif /* ASPEED_OTP_H */ diff --git a/include/hw/nvram/fw_cfg.h b/include/hw/nvram/fw_cfg.h index 47578cc..d41b932 100644 --- a/include/hw/nvram/fw_cfg.h +++ b/include/hw/nvram/fw_cfg.h @@ -42,14 +42,6 @@ struct FWCfgDataGeneratorClass { typedef struct fw_cfg_file FWCfgFile; -#define FW_CFG_ORDER_OVERRIDE_VGA 70 -#define FW_CFG_ORDER_OVERRIDE_NIC 80 -#define FW_CFG_ORDER_OVERRIDE_USER 100 -#define FW_CFG_ORDER_OVERRIDE_DEVICE 110 - -void fw_cfg_set_order_override(FWCfgState *fw_cfg, int order); -void fw_cfg_reset_order_override(FWCfgState *fw_cfg); - typedef struct FWCfgFiles { uint32_t count; FWCfgFile f[]; @@ -75,8 +67,6 @@ struct FWCfgState { uint32_t cur_offset; Notifier machine_ready; - int fw_cfg_order_override; - bool dma_enabled; dma_addr_t dma_addr; AddressSpace *dma_as; diff --git a/include/hw/nvram/mac_nvram.h b/include/hw/nvram/mac_nvram.h index 0c4dfae..e9d8398 100644 --- a/include/hw/nvram/mac_nvram.h +++ b/include/hw/nvram/mac_nvram.h @@ -26,7 +26,7 @@ #ifndef MAC_NVRAM_H #define MAC_NVRAM_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/sysbus.h" #define MACIO_NVRAM_SIZE 0x2000 diff --git a/include/hw/nvram/npcm7xx_otp.h b/include/hw/nvram/npcm7xx_otp.h index ea4b5d0..77b05f8 100644 --- a/include/hw/nvram/npcm7xx_otp.h +++ b/include/hw/nvram/npcm7xx_otp.h @@ -16,7 +16,7 @@ #ifndef NPCM7XX_OTP_H #define NPCM7XX_OTP_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/sysbus.h" /* Each OTP module holds 8192 bits of one-time programmable storage */ diff --git a/include/hw/nvram/xlnx-bbram.h b/include/hw/nvram/xlnx-bbram.h index 58acbe9..af90900 100644 --- a/include/hw/nvram/xlnx-bbram.h +++ b/include/hw/nvram/xlnx-bbram.h @@ -47,7 +47,6 @@ struct XlnxBBRam { bool bbram8_wo; bool blk_ro; - RegisterInfoArray *reg_array; uint32_t regs[RMAX_XLNX_BBRAM]; RegisterInfo regs_info[RMAX_XLNX_BBRAM]; }; diff --git a/include/hw/pci-host/aspeed_pcie.h b/include/hw/pci-host/aspeed_pcie.h new file mode 100644 index 0000000..be53ea96 --- /dev/null +++ b/include/hw/pci-host/aspeed_pcie.h @@ -0,0 +1,137 @@ +/* + * ASPEED PCIe Host Controller + * + * Copyright (C) 2025 ASPEED Technology Inc. + * Copyright (c) 2022 Cédric Le Goater <clg@kaod.org> + * + * Authors: + * Cédric Le Goater <clg@kaod.org> + * Jamin Lin <jamin_lin@aspeedtech.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + * + * Based on previous work from Cédric Le Goater. + * Modifications extend support for the ASPEED AST2600 and AST2700 platforms. + */ + +#ifndef ASPEED_PCIE_H +#define ASPEED_PCIE_H + +#include "hw/sysbus.h" +#include "hw/pci/pci_bridge.h" +#include "hw/pci/pcie_host.h" +#include "hw/pci/pcie_port.h" +#include "qom/object.h" + +typedef struct AspeedPCIECfgTxDesc { + uint32_t desc0; + uint32_t desc1; + uint32_t desc2; + uint32_t desc3; + uint32_t wdata; + uint32_t rdata_reg; +} AspeedPCIECfgTxDesc; + +typedef struct AspeedPCIERcRegs { + uint32_t int_en_reg; + uint32_t int_sts_reg; + uint32_t msi_sts0_reg; + uint32_t msi_sts1_reg; +} AspeedPCIERcRegs; + +typedef struct AspeedPCIERegMap { + AspeedPCIERcRegs rc; +} AspeedPCIERegMap; + +#define TYPE_ASPEED_PCIE_ROOT_PORT "aspeed.pcie-root-port" +OBJECT_DECLARE_SIMPLE_TYPE(AspeedPCIERootPortState, ASPEED_PCIE_ROOT_PORT) + +typedef struct AspeedPCIERootPortState { + PCIESlot parent_obj; +} AspeedPCIERootPortState; + +#define TYPE_ASPEED_PCIE_ROOT_DEVICE "aspeed.pcie-root-device" +OBJECT_DECLARE_SIMPLE_TYPE(AspeedPCIERootDeviceState, ASPEED_PCIE_ROOT_DEVICE); + +struct AspeedPCIERootDeviceState { + PCIBridge parent_obj; +}; + +#define TYPE_ASPEED_PCIE_RC "aspeed.pcie-rc" +OBJECT_DECLARE_SIMPLE_TYPE(AspeedPCIERcState, ASPEED_PCIE_RC); + +struct AspeedPCIERcState { + PCIExpressHost parent_obj; + + MemoryRegion iommu_root; + AddressSpace iommu_as; + MemoryRegion dram_alias; + MemoryRegion *dram_mr; + MemoryRegion mmio_window; + MemoryRegion msi_window; + MemoryRegion io_window; + MemoryRegion mmio; + MemoryRegion io; + + uint64_t dram_base; + uint32_t msi_addr; + uint32_t rp_addr; + uint32_t bus_nr; + char name[16]; + bool has_rd; + qemu_irq irq; + + AspeedPCIERootDeviceState root_device; + AspeedPCIERootPortState root_port; +}; + +/* Bridge between AHB bus and PCIe RC. */ +#define TYPE_ASPEED_PCIE_CFG "aspeed.pcie-cfg" +#define TYPE_ASPEED_2700_PCIE_CFG TYPE_ASPEED_PCIE_CFG "-ast2700" +OBJECT_DECLARE_TYPE(AspeedPCIECfgState, AspeedPCIECfgClass, ASPEED_PCIE_CFG); + +struct AspeedPCIECfgState { + SysBusDevice parent_obj; + + MemoryRegion mmio; + uint32_t *regs; + uint32_t id; + + const AspeedPCIERcRegs *rc_regs; + AspeedPCIERcState rc; + uint32_t tlpn_fifo[3]; + uint32_t tlpn_idx; +}; + +struct AspeedPCIECfgClass { + SysBusDeviceClass parent_class; + + const AspeedPCIERegMap *reg_map; + const MemoryRegionOps *reg_ops; + + uint32_t rc_msi_addr; + uint32_t rc_rp_addr; + uint64_t rc_bus_nr; + uint64_t nr_regs; + bool rc_has_rd; +}; + +#define TYPE_ASPEED_PCIE_PHY "aspeed.pcie-phy" +#define TYPE_ASPEED_2700_PCIE_PHY TYPE_ASPEED_PCIE_PHY "-ast2700" +OBJECT_DECLARE_TYPE(AspeedPCIEPhyState, AspeedPCIEPhyClass, ASPEED_PCIE_PHY); + +struct AspeedPCIEPhyState { + SysBusDevice parent_obj; + + MemoryRegion mmio; + uint32_t *regs; + uint32_t id; +}; + +struct AspeedPCIEPhyClass { + SysBusDeviceClass parent_class; + + uint64_t nr_regs; +}; + +#endif /* ASPEED_PCIE_H */ diff --git a/include/hw/pci-host/dino.h b/include/hw/pci-host/dino.h index fd7975c..5dc8cdf 100644 --- a/include/hw/pci-host/dino.h +++ b/include/hw/pci-host/dino.h @@ -109,10 +109,6 @@ static const uint32_t reg800_keep_bits[DINO800_REGS] = { struct DinoState { PCIHostState parent_obj; - /* - * PCI_CONFIG_ADDR is parent_obj.config_reg, via pci_host_conf_be_ops, - * so that we can map PCI_CONFIG_DATA to pci_host_data_be_ops. - */ uint32_t config_reg_dino; /* keep original copy, including 2 lowest bits */ uint32_t iar0; diff --git a/include/hw/pci-host/fsl_imx8m_phy.h b/include/hw/pci-host/fsl_imx8m_phy.h index 4f4875b..5f1b212 100644 --- a/include/hw/pci-host/fsl_imx8m_phy.h +++ b/include/hw/pci-host/fsl_imx8m_phy.h @@ -11,7 +11,7 @@ #include "hw/sysbus.h" #include "qom/object.h" -#include "exec/memory.h" +#include "system/memory.h" #define TYPE_FSL_IMX8M_PCIE_PHY "fsl-imx8m-pcie-phy" OBJECT_DECLARE_SIMPLE_TYPE(FslImx8mPciePhyState, FSL_IMX8M_PCIE_PHY) diff --git a/include/hw/pci-host/gpex.h b/include/hw/pci-host/gpex.h index 8447153..feaf827 100644 --- a/include/hw/pci-host/gpex.h +++ b/include/hw/pci-host/gpex.h @@ -45,6 +45,7 @@ struct GPEXConfig { MemMapEntry pio; int irq; PCIBus *bus; + bool pci_native_hotplug; }; typedef struct GPEXIrq GPEXIrq; diff --git a/include/hw/pci-host/ls7a.h b/include/hw/pci-host/ls7a.h index 79d4ea8..33e7942 100644 --- a/include/hw/pci-host/ls7a.h +++ b/include/hw/pci-host/ls7a.h @@ -13,41 +13,4 @@ #include "qemu/range.h" #include "qom/object.h" -#define VIRT_PCI_MEM_BASE 0x40000000UL -#define VIRT_PCI_MEM_SIZE 0x40000000UL -#define VIRT_PCI_IO_OFFSET 0x4000 -#define VIRT_PCI_CFG_BASE 0x20000000 -#define VIRT_PCI_CFG_SIZE 0x08000000 -#define VIRT_PCI_IO_BASE 0x18004000UL -#define VIRT_PCI_IO_SIZE 0xC000 - -#define VIRT_PCH_REG_BASE 0x10000000UL -#define VIRT_IOAPIC_REG_BASE (VIRT_PCH_REG_BASE) -#define VIRT_PCH_MSI_ADDR_LOW 0x2FF00000UL -#define VIRT_PCH_REG_SIZE 0x400 -#define VIRT_PCH_MSI_SIZE 0x8 - -/* - * GSI_BASE is hard-coded with 64 in linux kernel, else kernel fails to boot - * 0 - 15 GSI for ISA devices even if there is no ISA devices - * 16 - 63 GSI for CPU devices such as timers/perf monitor etc - * 64 - GSI for external devices - */ -#define VIRT_PCH_PIC_IRQ_NUM 32 -#define VIRT_GSI_BASE 64 -#define VIRT_DEVICE_IRQS 16 -#define VIRT_UART_COUNT 4 -#define VIRT_UART_IRQ (VIRT_GSI_BASE + 2) -#define VIRT_UART_BASE 0x1fe001e0 -#define VIRT_UART_SIZE 0x100 -#define VIRT_RTC_IRQ (VIRT_GSI_BASE + 6) -#define VIRT_MISC_REG_BASE (VIRT_PCH_REG_BASE + 0x00080000) -#define VIRT_RTC_REG_BASE (VIRT_MISC_REG_BASE + 0x00050100) -#define VIRT_RTC_LEN 0x100 -#define VIRT_SCI_IRQ (VIRT_GSI_BASE + 7) - -#define VIRT_PLATFORM_BUS_BASEADDRESS 0x16000000 -#define VIRT_PLATFORM_BUS_SIZE 0x2000000 -#define VIRT_PLATFORM_BUS_NUM_IRQS 2 -#define VIRT_PLATFORM_BUS_IRQ (VIRT_GSI_BASE + 8) #endif diff --git a/include/hw/pci-host/pam.h b/include/hw/pci-host/pam.h index 005916f..44f3908 100644 --- a/include/hw/pci-host/pam.h +++ b/include/hw/pci-host/pam.h @@ -50,7 +50,7 @@ * 0xf0000 - 0xfffff System BIOS Area Memory Segments */ -#include "exec/memory.h" +#include "system/memory.h" #define SMRAM_C_BASE 0xa0000 #define SMRAM_C_END 0xc0000 diff --git a/include/hw/pci-host/pnv_phb3.h b/include/hw/pci-host/pnv_phb3.h index 24ca3dd..682f62a 100644 --- a/include/hw/pci-host/pnv_phb3.h +++ b/include/hw/pci-host/pnv_phb3.h @@ -14,7 +14,8 @@ #include "qom/object.h" #include "hw/pci-host/pnv_phb.h" -typedef struct PnvPHB3 PnvPHB3; +#define TYPE_PNV_PHB3 "pnv-phb3" +OBJECT_DECLARE_SIMPLE_TYPE(PnvPHB3, PNV_PHB3) /* * PHB3 XICS Source for MSIs @@ -115,9 +116,6 @@ OBJECT_DECLARE_SIMPLE_TYPE(PnvPHB3RootBus, PNV_PHB3_ROOT_BUS) /* * PHB3 PCIe Host Bridge for PowerNV machines (POWER8) */ -#define TYPE_PNV_PHB3 "pnv-phb3" -OBJECT_DECLARE_SIMPLE_TYPE(PnvPHB3, PNV_PHB3) - #define PNV_PHB3_NUM_M64 16 #define PNV_PHB3_NUM_REGS (0x1000 >> 3) #define PNV_PHB3_NUM_LSI 8 diff --git a/include/hw/pci-host/pnv_phb4.h b/include/hw/pci-host/pnv_phb4.h index 8a80c0c..de996e7 100644 --- a/include/hw/pci-host/pnv_phb4.h +++ b/include/hw/pci-host/pnv_phb4.h @@ -17,8 +17,11 @@ #include "hw/ppc/xive.h" #include "qom/object.h" + +#define TYPE_PNV_PHB4 "pnv-phb4" +OBJECT_DECLARE_SIMPLE_TYPE(PnvPHB4, PNV_PHB4) + typedef struct PnvPhb4PecStack PnvPhb4PecStack; -typedef struct PnvPHB4 PnvPHB4; /* * We have one such address space wrapper per possible device under @@ -59,9 +62,6 @@ OBJECT_DECLARE_SIMPLE_TYPE(PnvPHB4RootBus, PNV_PHB4_ROOT_BUS) /* * PHB4 PCIe Host Bridge for PowerNV machines (POWER9) */ -#define TYPE_PNV_PHB4 "pnv-phb4" -OBJECT_DECLARE_SIMPLE_TYPE(PnvPHB4, PNV_PHB4) - #define PNV_PHB4_MAX_LSIs 8 #define PNV_PHB4_MAX_INTs 4096 #define PNV_PHB4_MAX_MIST (PNV_PHB4_MAX_INTs >> 2) diff --git a/include/hw/pci-host/remote.h b/include/hw/pci-host/remote.h index 690a01f..5264c35 100644 --- a/include/hw/pci-host/remote.h +++ b/include/hw/pci-host/remote.h @@ -11,7 +11,7 @@ #ifndef PCI_HOST_REMOTE_H #define PCI_HOST_REMOTE_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/pci/pcie_host.h" #define TYPE_REMOTE_PCIHOST "remote-pcihost" diff --git a/include/hw/pci/msix.h b/include/hw/pci/msix.h index 0e6f257..551a2bc 100644 --- a/include/hw/pci/msix.h +++ b/include/hw/pci/msix.h @@ -7,12 +7,12 @@ void msix_set_message(PCIDevice *dev, int vector, MSIMessage msg); MSIMessage msix_get_message(PCIDevice *dev, unsigned int vector); -int msix_init(PCIDevice *dev, unsigned short nentries, +int msix_init(PCIDevice *dev, uint32_t nentries, MemoryRegion *table_bar, uint8_t table_bar_nr, unsigned table_offset, MemoryRegion *pba_bar, uint8_t pba_bar_nr, unsigned pba_offset, uint8_t cap_pos, Error **errp); -int msix_init_exclusive_bar(PCIDevice *dev, unsigned short nentries, +int msix_init_exclusive_bar(PCIDevice *dev, uint32_t nentries, uint8_t bar_nr, Error **errp); void msix_write_config(PCIDevice *dev, uint32_t address, uint32_t val, int len); @@ -32,6 +32,7 @@ int msix_present(PCIDevice *dev); bool msix_is_masked(PCIDevice *dev, unsigned vector); void msix_set_pending(PCIDevice *dev, unsigned vector); void msix_clr_pending(PCIDevice *dev, int vector); +int msix_is_pending(PCIDevice *dev, unsigned vector); void msix_vector_use(PCIDevice *dev, unsigned vector); void msix_vector_unuse(PCIDevice *dev, unsigned vector); diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h index 822fbac..b72e484 100644 --- a/include/hw/pci/pci.h +++ b/include/hw/pci/pci.h @@ -1,7 +1,7 @@ #ifndef QEMU_PCI_H #define QEMU_PCI_H -#include "exec/memory.h" +#include "system/memory.h" #include "system/dma.h" #include "system/host_iommu_device.h" @@ -134,6 +134,15 @@ struct PCIHostDeviceAddress { unsigned int function; }; +/* + * Represents the Address Type (AT) field in a PCI request, + * see MemTxAttrs.address_type + */ +typedef enum PCIAddressType { + PCI_AT_UNTRANSLATED = 0, /* Default when no attribute is set */ + PCI_AT_TRANSLATED = 1, +} PCIAddressType; + typedef void PCIConfigWriteFunc(PCIDevice *pci_dev, uint32_t address, uint32_t data, int len); typedef uint32_t PCIConfigReadFunc(PCIDevice *pci_dev, @@ -222,6 +231,8 @@ enum { QEMU_PCIE_EXT_TAG = (1 << QEMU_PCIE_EXT_TAG_BITNR), #define QEMU_PCI_CAP_PM_BITNR 14 QEMU_PCI_CAP_PM = (1 << QEMU_PCI_CAP_PM_BITNR), +#define QEMU_PCI_SKIP_RESET_ON_CPR_BITNR 15 + QEMU_PCI_SKIP_RESET_ON_CPR = (1 << QEMU_PCI_SKIP_RESET_ON_CPR_BITNR), }; typedef struct PCIINTxRoute { @@ -375,6 +386,28 @@ void pci_bus_get_w64_range(PCIBus *bus, Range *range); void pci_device_deassert_intx(PCIDevice *dev); +/* Page Request Interface */ +typedef enum { + IOMMU_PRI_RESP_SUCCESS, + IOMMU_PRI_RESP_INVALID_REQUEST, + IOMMU_PRI_RESP_FAILURE, +} IOMMUPRIResponseCode; + +typedef struct IOMMUPRIResponse { + IOMMUPRIResponseCode response_code; + uint16_t prgi; +} IOMMUPRIResponse; + +struct IOMMUPRINotifier; + +typedef void (*IOMMUPRINotify)(struct IOMMUPRINotifier *notifier, + IOMMUPRIResponse *response); + +typedef struct IOMMUPRINotifier { + IOMMUPRINotify notify; +} IOMMUPRINotifier; + +#define PCI_PRI_PRGI_MASK 0x1ffU /** * struct PCIIOMMUOps: callbacks structure for specific IOMMU handlers @@ -429,6 +462,179 @@ typedef struct PCIIOMMUOps { * @devfn: device and function number of the PCI device. */ void (*unset_iommu_device)(PCIBus *bus, void *opaque, int devfn); + /** + * @get_iotlb_info: get properties required to initialize a device IOTLB. + * + * Callback required if devices are allowed to cache translations. + * + * @opaque: the data passed to pci_setup_iommu(). + * + * @addr_width: the address width of the IOMMU (output parameter). + * + * @min_page_size: the page size of the IOMMU (output parameter). + */ + void (*get_iotlb_info)(void *opaque, uint8_t *addr_width, + uint32_t *min_page_size); + /** + * @init_iotlb_notifier: initialize an IOMMU notifier. + * + * Optional callback. + * + * @bus: the #PCIBus of the PCI device. + * + * @opaque: the data passed to pci_setup_iommu(). + * + * @devfn: device and function number of the PCI device. + * + * @n: the notifier to be initialized. + * + * @fn: the callback to be installed. + * + * @user_opaque: a user pointer that can be used to track a state. + */ + void (*init_iotlb_notifier)(PCIBus *bus, void *opaque, int devfn, + IOMMUNotifier *n, IOMMUNotify fn, + void *user_opaque); + /** + * @register_iotlb_notifier: setup an IOTLB invalidation notifier. + * + * Callback required if devices are allowed to cache translations. + * + * @bus: the #PCIBus of the PCI device. + * + * @opaque: the data passed to pci_setup_iommu(). + * + * @devfn: device and function number of the PCI device. + * + * @pasid: the pasid of the address space to watch. + * + * @n: the notifier to register. + */ + void (*register_iotlb_notifier)(PCIBus *bus, void *opaque, int devfn, + uint32_t pasid, IOMMUNotifier *n); + /** + * @unregister_iotlb_notifier: remove an IOTLB invalidation notifier. + * + * Callback required if devices are allowed to cache translations. + * + * @bus: the #PCIBus of the PCI device. + * + * @opaque: the data passed to pci_setup_iommu(). + * + * @devfn: device and function number of the PCI device. + * + * @pasid: the pasid of the address space to stop watching. + * + * @n: the notifier to unregister. + */ + void (*unregister_iotlb_notifier)(PCIBus *bus, void *opaque, int devfn, + uint32_t pasid, IOMMUNotifier *n); + /** + * @ats_request_translation: issue an ATS request. + * + * Callback required if devices are allowed to use the address + * translation service. + * + * @bus: the #PCIBus of the PCI device. + * + * @opaque: the data passed to pci_setup_iommu(). + * + * @devfn: device and function number of the PCI device. + * + * @pasid: the pasid of the address space to use for the request. + * + * @priv_req: privileged mode bit (PASID TLP). + * + * @exec_req: execute request bit (PASID TLP). + * + * @addr: start address of the memory range to be translated. + * + * @length: length of the memory range in bytes. + * + * @no_write: request a read-only translation (if supported). + * + * @result: buffer in which the TLB entries will be stored. + * + * @result_length: result buffer length. + * + * @err_count: number of untranslated subregions. + * + * Returns: the number of translations stored in the result buffer, or + * -ENOMEM if the buffer is not large enough. + */ + ssize_t (*ats_request_translation)(PCIBus *bus, void *opaque, int devfn, + uint32_t pasid, bool priv_req, + bool exec_req, hwaddr addr, + size_t length, bool no_write, + IOMMUTLBEntry *result, + size_t result_length, + uint32_t *err_count); + /** + * @pri_register_notifier: setup the PRI completion callback. + * + * Callback required if devices are allowed to use the page request + * interface. + * + * @bus: the #PCIBus of the PCI device. + * + * @opaque: the data passed to pci_setup_iommu(). + * + * @devfn: device and function number of the PCI device. + * + * @pasid: the pasid of the address space to track. + * + * @notifier: the notifier to register. + */ + void (*pri_register_notifier)(PCIBus *bus, void *opaque, int devfn, + uint32_t pasid, IOMMUPRINotifier *notifier); + /** + * @pri_unregister_notifier: remove the PRI completion callback. + * + * Callback required if devices are allowed to use the page request + * interface. + * + * @bus: the #PCIBus of the PCI device. + * + * @opaque: the data passed to pci_setup_iommu(). + * + * @devfn: device and function number of the PCI device. + * + * @pasid: the pasid of the address space to stop tracking. + */ + void (*pri_unregister_notifier)(PCIBus *bus, void *opaque, int devfn, + uint32_t pasid); + /** + * @pri_request_page: issue a PRI request. + * + * Callback required if devices are allowed to use the page request + * interface. + * + * @bus: the #PCIBus of the PCI device. + * + * @opaque: the data passed to pci_setup_iommu(). + * + * @devfn: device and function number of the PCI device. + * + * @pasid: the pasid of the address space to use for the request. + * + * @priv_req: privileged mode bit (PASID TLP). + * + * @exec_req: execute request bit (PASID TLP). + * + * @addr: untranslated address of the requested page. + * + * @lpig: last page in group. + * + * @prgi: page request group index. + * + * @is_read: request read access. + * + * @is_write: request write access. + */ + int (*pri_request_page)(PCIBus *bus, void *opaque, int devfn, + uint32_t pasid, bool priv_req, bool exec_req, + hwaddr addr, bool lpig, uint16_t prgi, bool is_read, + bool is_write); } PCIIOMMUOps; AddressSpace *pci_device_iommu_address_space(PCIDevice *dev); @@ -437,6 +643,126 @@ bool pci_device_set_iommu_device(PCIDevice *dev, HostIOMMUDevice *hiod, void pci_device_unset_iommu_device(PCIDevice *dev); /** + * pci_iommu_get_iotlb_info: get properties required to initialize a + * device IOTLB. + * + * Returns 0 on success, or a negative errno otherwise. + * + * @dev: the device that wants to get the information. + * @addr_width: the address width of the IOMMU (output parameter). + * @min_page_size: the page size of the IOMMU (output parameter). + */ +int pci_iommu_get_iotlb_info(PCIDevice *dev, uint8_t *addr_width, + uint32_t *min_page_size); + +/** + * pci_iommu_init_iotlb_notifier: initialize an IOMMU notifier. + * + * This function is used by devices before registering an IOTLB notifier. + * + * @dev: the device. + * @n: the notifier to be initialized. + * @fn: the callback to be installed. + * @opaque: a user pointer that can be used to track a state. + */ +int pci_iommu_init_iotlb_notifier(PCIDevice *dev, IOMMUNotifier *n, + IOMMUNotify fn, void *opaque); + +/** + * pci_ats_request_translation: perform an ATS request. + * + * Returns the number of translations stored in @result in case of success, + * a negative error code otherwise. + * -ENOMEM is returned when the result buffer is not large enough to store + * all the translations. + * + * @dev: the ATS-capable PCI device. + * @pasid: the pasid of the address space in which the translation will be done. + * @priv_req: privileged mode bit (PASID TLP). + * @exec_req: execute request bit (PASID TLP). + * @addr: start address of the memory range to be translated. + * @length: length of the memory range in bytes. + * @no_write: request a read-only translation (if supported). + * @result: buffer in which the TLB entries will be stored. + * @result_length: result buffer length. + * @err_count: number of untranslated subregions. + */ +ssize_t pci_ats_request_translation(PCIDevice *dev, uint32_t pasid, + bool priv_req, bool exec_req, + hwaddr addr, size_t length, + bool no_write, IOMMUTLBEntry *result, + size_t result_length, + uint32_t *err_count); + +/** + * pci_pri_request_page: perform a PRI request. + * + * Returns 0 if the PRI request has been sent to the guest OS, + * an error code otherwise. + * + * @dev: the PRI-capable PCI device. + * @pasid: the pasid of the address space in which the translation will be done. + * @priv_req: privileged mode bit (PASID TLP). + * @exec_req: execute request bit (PASID TLP). + * @addr: untranslated address of the requested page. + * @lpig: last page in group. + * @prgi: page request group index. + * @is_read: request read access. + * @is_write: request write access. + */ +int pci_pri_request_page(PCIDevice *dev, uint32_t pasid, bool priv_req, + bool exec_req, hwaddr addr, bool lpig, + uint16_t prgi, bool is_read, bool is_write); + +/** + * pci_pri_register_notifier: register the PRI callback for a given address + * space. + * + * Returns 0 on success, an error code otherwise. + * + * @dev: the PRI-capable PCI device. + * @pasid: the pasid of the address space to track. + * @notifier: the notifier to register. + */ +int pci_pri_register_notifier(PCIDevice *dev, uint32_t pasid, + IOMMUPRINotifier *notifier); + +/** + * pci_pri_unregister_notifier: remove the PRI callback from a given address + * space. + * + * @dev: the PRI-capable PCI device. + * @pasid: the pasid of the address space to stop tracking. + */ +void pci_pri_unregister_notifier(PCIDevice *dev, uint32_t pasid); + +/** + * pci_iommu_register_iotlb_notifier: register a notifier for changes to + * IOMMU translation entries in a specific address space. + * + * Returns 0 on success, or a negative errno otherwise. + * + * @dev: the device that wants to get notified. + * @pasid: the pasid of the address space to track. + * @n: the notifier to register. + */ +int pci_iommu_register_iotlb_notifier(PCIDevice *dev, uint32_t pasid, + IOMMUNotifier *n); + +/** + * pci_iommu_unregister_iotlb_notifier: unregister a notifier that has been + * registered with pci_iommu_register_iotlb_notifier. + * + * Returns 0 on success, or a negative errno otherwise. + * + * @dev: the device that wants to stop notifications. + * @pasid: the pasid of the address space to stop tracking. + * @n: the notifier to unregister. + */ +int pci_iommu_unregister_iotlb_notifier(PCIDevice *dev, uint32_t pasid, + IOMMUNotifier *n); + +/** * pci_setup_iommu: Initialize specific IOMMU handlers for a PCIBus * * Let PCI host bridges define specific operations. @@ -447,6 +773,8 @@ void pci_device_unset_iommu_device(PCIDevice *dev); */ void pci_setup_iommu(PCIBus *bus, const PCIIOMMUOps *ops, void *opaque); +void pci_setup_iommu_per_bus(PCIBus *bus, const PCIIOMMUOps *ops, void *opaque); + pcibus_t pci_bar_address(PCIDevice *d, int reg, uint8_t type, pcibus_t size); @@ -668,6 +996,7 @@ void lsi53c8xx_handle_legacy_cmdline(DeviceState *lsi_dev); qemu_irq pci_allocate_irq(PCIDevice *pci_dev); void pci_set_irq(PCIDevice *pci_dev, int level); +int pci_irq_disabled(PCIDevice *d); static inline void pci_irq_assert(PCIDevice *pci_dev) { diff --git a/include/hw/pci/pci_bridge.h b/include/hw/pci/pci_bridge.h index b0f5204..a055fd8 100644 --- a/include/hw/pci/pci_bridge.h +++ b/include/hw/pci/pci_bridge.h @@ -14,8 +14,8 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * along with this program; if not, see + * <https://www.gnu.org/licenses/>. * * split out pci bus specific stuff from pci.[hc] to pci_bridge.[hc] * Copyright (c) 2009 Isaku Yamahata <yamahata at valinux co jp> @@ -104,6 +104,7 @@ typedef struct PXBPCIEDev { PXBDev parent_obj; } PXBPCIEDev; +#define TYPE_PXB_PCIE_BUS "pxb-pcie-bus" #define TYPE_PXB_CXL_BUS "pxb-cxl-bus" #define TYPE_PXB_DEV "pxb" OBJECT_DECLARE_SIMPLE_TYPE(PXBDev, PXB_DEV) diff --git a/include/hw/pci/pci_bus.h b/include/hw/pci/pci_bus.h index 2261312..c738446 100644 --- a/include/hw/pci/pci_bus.h +++ b/include/hw/pci/pci_bus.h @@ -35,6 +35,7 @@ struct PCIBus { enum PCIBusFlags flags; const PCIIOMMUOps *iommu_ops; void *iommu_opaque; + bool iommu_per_bus; uint8_t devfn_min; uint32_t slot_reserved_mask; pci_set_irq_fn set_irq; diff --git a/include/hw/pci/pci_device.h b/include/hw/pci/pci_device.h index 345b12e..88ccea5 100644 --- a/include/hw/pci/pci_device.h +++ b/include/hw/pci/pci_device.h @@ -4,6 +4,7 @@ #include "hw/pci/pci.h" #include "hw/pci/pcie.h" #include "hw/pci/pcie_doe.h" +#include "system/spdm-socket.h" #define TYPE_PCI_DEVICE "pci-device" typedef struct PCIDeviceClass PCIDeviceClass; @@ -38,6 +39,8 @@ struct PCIDeviceClass { uint16_t subsystem_id; /* only for header type = 0 */ const char *romfile; /* rom bar */ + + bool sriov_vf_user_creatable; }; enum PCIReqIDType { @@ -88,6 +91,7 @@ struct PCIDevice { char name[64]; PCIIORegion io_regions[PCI_NUM_REGIONS]; AddressSpace bus_master_as; + bool is_master; MemoryRegion bus_master_container_region; MemoryRegion bus_master_enable_region; @@ -163,6 +167,7 @@ struct PCIDevice { /* SPDM */ uint16_t spdm_port; + SpdmTransportType spdm_trans; /* DOE */ DOECap doe_spdm; @@ -177,6 +182,8 @@ struct PCIDevice { * realizing the device. */ uint32_t max_bounce_buffer_size; + + char *sriov_pf; }; static inline int pci_intx(PCIDevice *pci_dev) @@ -209,7 +216,7 @@ static inline int pci_is_express_downstream_port(const PCIDevice *d) static inline int pci_is_vf(const PCIDevice *d) { - return d->exp.sriov_vf.pf != NULL; + return d->sriov_pf || d->exp.sriov_vf.pf != NULL; } static inline uint32_t pci_config_size(const PCIDevice *d) diff --git a/include/hw/pci/pci_host.h b/include/hw/pci/pci_host.h index e52d8ec..954dd44 100644 --- a/include/hw/pci/pci_host.h +++ b/include/hw/pci/pci_host.h @@ -68,6 +68,5 @@ uint32_t pci_data_read(PCIBus *s, uint32_t addr, unsigned len); extern const MemoryRegionOps pci_host_conf_le_ops; extern const MemoryRegionOps pci_host_conf_be_ops; extern const MemoryRegionOps pci_host_data_le_ops; -extern const MemoryRegionOps pci_host_data_be_ops; #endif /* PCI_HOST_H */ diff --git a/include/hw/pci/pci_ids.h b/include/hw/pci/pci_ids.h index 33e2898..16034aa 100644 --- a/include/hw/pci/pci_ids.h +++ b/include/hw/pci/pci_ids.h @@ -291,4 +291,6 @@ #define PCI_VENDOR_ID_NVIDIA 0x10de +#define PCI_VENDOR_ID_ASPEED 0x1A03 + #endif diff --git a/include/hw/pci/pcie.h b/include/hw/pci/pcie.h index 70a5de0..42cebcd 100644 --- a/include/hw/pci/pcie.h +++ b/include/hw/pci/pcie.h @@ -70,8 +70,10 @@ struct PCIExpressDevice { uint16_t aer_cap; PCIEAERLog aer_log; - /* Offset of ATS capability in config space */ + /* Offset of ATS, PRI and PASID capabilities in config space */ uint16_t ats_cap; + uint16_t pasid_cap; + uint16_t pri_cap; /* ACS */ uint16_t acs_cap; @@ -150,4 +152,14 @@ void pcie_cap_slot_unplug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp); void pcie_cap_slot_unplug_request_cb(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp); + +void pcie_pasid_init(PCIDevice *dev, uint16_t offset, uint8_t pasid_width, + bool exec_perm, bool priv_mod); +void pcie_pri_init(PCIDevice *dev, uint16_t offset, uint32_t outstanding_pr_cap, + bool prg_response_pasid_req); + +uint32_t pcie_pri_get_req_alloc(const PCIDevice *dev); +bool pcie_pri_enabled(const PCIDevice *dev); +bool pcie_pasid_enabled(const PCIDevice *dev); +bool pcie_ats_enabled(const PCIDevice *dev); #endif /* QEMU_PCIE_H */ diff --git a/include/hw/pci/pcie_host.h b/include/hw/pci/pcie_host.h index 82d9217..f09de76 100644 --- a/include/hw/pci/pcie_host.h +++ b/include/hw/pci/pcie_host.h @@ -22,7 +22,7 @@ #define PCIE_HOST_H #include "hw/pci/pci_host.h" -#include "exec/memory.h" +#include "system/memory.h" #include "qom/object.h" #define TYPE_PCIE_HOST_BRIDGE "pcie-host-bridge" diff --git a/include/hw/pci/pcie_regs.h b/include/hw/pci/pcie_regs.h index 9d3b686..33a2222 100644 --- a/include/hw/pci/pcie_regs.h +++ b/include/hw/pci/pcie_regs.h @@ -86,6 +86,14 @@ typedef enum PCIExpLinkWidth { #define PCI_ARI_VER 1 #define PCI_ARI_SIZEOF 8 +/* PASID */ +#define PCI_PASID_VER 1 +#define PCI_EXT_CAP_PASID_MAX_WIDTH 20 +#define PCI_PASID_CAP_WIDTH_SHIFT 8 + +/* PRI */ +#define PCI_PRI_VER 1 + /* AER */ #define PCI_ERR_VER 2 #define PCI_ERR_SIZEOF 0x48 diff --git a/include/hw/pci/pcie_sriov.h b/include/hw/pci/pcie_sriov.h index c5d2d31..b0ea6a6 100644 --- a/include/hw/pci/pcie_sriov.h +++ b/include/hw/pci/pcie_sriov.h @@ -18,6 +18,7 @@ typedef struct PCIESriovPF { uint8_t vf_bar_type[PCI_NUM_REGIONS]; /* Store type for each VF bar */ PCIDevice **vf; /* Pointer to an array of num_vfs VF devices */ + bool vf_user_created; /* If VFs are created by user */ } PCIESriovPF; typedef struct PCIESriovVF { @@ -36,9 +37,25 @@ void pcie_sriov_pf_exit(PCIDevice *dev); void pcie_sriov_pf_init_vf_bar(PCIDevice *dev, int region_num, uint8_t type, dma_addr_t size); -/* Instantiate a bar for a VF */ -void pcie_sriov_vf_register_bar(PCIDevice *dev, int region_num, - MemoryRegion *memory); +/** + * pcie_sriov_pf_init_from_user_created_vfs() - Initialize PF with user-created + * VFs, adding ARI to PF + * @dev: A PCIe device being realized. + * @offset: The offset of the SR-IOV capability. + * @errp: pointer to Error*, to store an error if it happens. + * + * Initializes a PF with user-created VFs, adding the ARI extended capability to + * the PF. The VFs should call pcie_ari_init() to form an ARI device. + * + * Return: The size of added capabilities. 0 if the user did not create VFs. + * -1 if failed. + */ +int16_t pcie_sriov_pf_init_from_user_created_vfs(PCIDevice *dev, + uint16_t offset, + Error **errp); + +bool pcie_sriov_register_device(PCIDevice *dev, Error **errp); +void pcie_sriov_unregister_device(PCIDevice *dev); /* * Default (minimal) page size support values diff --git a/include/hw/pci/shpc.h b/include/hw/pci/shpc.h index a0789df..ad10895 100644 --- a/include/hw/pci/shpc.h +++ b/include/hw/pci/shpc.h @@ -1,7 +1,7 @@ #ifndef SHPC_H #define SHPC_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/hotplug.h" #include "hw/pci/pci_device.h" #include "migration/vmstate.h" diff --git a/include/hw/ppc/mac_dbdma.h b/include/hw/ppc/mac_dbdma.h index 672c2be..7676488 100644 --- a/include/hw/ppc/mac_dbdma.h +++ b/include/hw/ppc/mac_dbdma.h @@ -23,7 +23,7 @@ #ifndef HW_MAC_DBDMA_H #define HW_MAC_DBDMA_H -#include "exec/memory.h" +#include "system/memory.h" #include "qemu/iov.h" #include "system/dma.h" #include "hw/sysbus.h" @@ -164,7 +164,9 @@ struct DBDMAState { DBDMA_channel channels[DBDMA_CHANNELS]; QEMUBH *bh; }; -typedef struct DBDMAState DBDMAState; + +#define TYPE_MAC_DBDMA "mac-dbdma" +OBJECT_DECLARE_SIMPLE_TYPE(DBDMAState, MAC_DBDMA) /* Externally callable functions */ @@ -173,7 +175,4 @@ void DBDMA_register_channel(void *dbdma, int nchan, qemu_irq irq, void *opaque); void DBDMA_kick(DBDMAState *dbdma); -#define TYPE_MAC_DBDMA "mac-dbdma" -OBJECT_DECLARE_SIMPLE_TYPE(DBDMAState, MAC_DBDMA) - #endif diff --git a/include/hw/ppc/pnv.h b/include/hw/ppc/pnv.h index d8fca07..cbdddfc 100644 --- a/include/hw/ppc/pnv.h +++ b/include/hw/ppc/pnv.h @@ -33,6 +33,7 @@ typedef struct PnvChip PnvChip; typedef struct Pnv8Chip Pnv8Chip; typedef struct Pnv9Chip Pnv9Chip; typedef struct Pnv10Chip Pnv10Chip; +typedef struct Pnv10Chip Pnv11Chip; #define PNV_CHIP_TYPE_SUFFIX "-" TYPE_PNV_CHIP #define PNV_CHIP_TYPE_NAME(cpu_model) cpu_model PNV_CHIP_TYPE_SUFFIX @@ -57,6 +58,10 @@ DECLARE_INSTANCE_CHECKER(PnvChip, PNV_CHIP_POWER9, DECLARE_INSTANCE_CHECKER(PnvChip, PNV_CHIP_POWER10, TYPE_PNV_CHIP_POWER10) +#define TYPE_PNV_CHIP_POWER11 PNV_CHIP_TYPE_NAME("power11_v2.0") +DECLARE_INSTANCE_CHECKER(PnvChip, PNV_CHIP_POWER11, + TYPE_PNV_CHIP_POWER11) + PnvCore *pnv_chip_find_core(PnvChip *chip, uint32_t core_id); PowerPCCPU *pnv_chip_find_cpu(PnvChip *chip, uint32_t pir); @@ -252,4 +257,37 @@ void pnv_bmc_set_pnor(IPMIBmc *bmc, PnvPnor *pnor); #define PNV10_HOMER_BASE(chip) \ (0x300ffd800000ll + ((uint64_t)(chip)->chip_id) * PNV_HOMER_SIZE) +/* Power11 */ +#define PNV11_XSCOM_SIZE PNV10_XSCOM_SIZE +#define PNV11_XSCOM_BASE(chip) PNV10_XSCOM_BASE(chip) + +#define PNV11_LPCM_SIZE PNV10_LPCM_SIZE +#define PNV11_LPCM_BASE(chip) PNV10_LPCM_BASE(chip) + +#define PNV11_PSIHB_ESB_SIZE PNV10_PSIHB_ESB_SIZE +#define PNV11_PSIHB_ESB_BASE(chip) PNV10_PSIHB_ESB_BASE(chip) + +#define PNV11_PSIHB_SIZE PNV10_PSIHB_SIZE +#define PNV11_PSIHB_BASE(chip) PNV10_PSIHB_BASE(chip) + +#define PNV11_XIVE2_IC_SIZE PNV10_XIVE2_IC_SIZE +#define PNV11_XIVE2_IC_BASE(chip) PNV10_XIVE2_IC_BASE(chip) + +#define PNV11_XIVE2_TM_SIZE PNV10_XIVE2_TM_SIZE +#define PNV11_XIVE2_TM_BASE(chip) PNV10_XIVE2_TM_BASE(chip) + +#define PNV11_XIVE2_NVC_SIZE PNV10_XIVE2_NVC_SIZE +#define PNV11_XIVE2_NVC_BASE(chip) PNV10_XIVE2_NVC_BASE(chip) + +#define PNV11_XIVE2_NVPG_SIZE PNV10_XIVE2_NVPG_SIZE +#define PNV11_XIVE2_NVPG_BASE(chip) PNV10_XIVE2_NVPG_BASE(chip) + +#define PNV11_XIVE2_ESB_SIZE PNV10_XIVE2_ESB_SIZE +#define PNV11_XIVE2_ESB_BASE(chip) PNV10_XIVE2_ESB_BASE(chip) + +#define PNV11_XIVE2_END_SIZE PNV10_XIVE2_END_SIZE +#define PNV11_XIVE2_END_BASE(chip) PNV10_XIVE2_END_BASE(chip) + +#define PNV11_OCC_SENSOR_BASE(chip) PNV10_OCC_SENSOR_BASE(chip) + #endif /* PPC_PNV_H */ diff --git a/include/hw/ppc/pnv_chip.h b/include/hw/ppc/pnv_chip.h index 24ce37a..a5b8c49 100644 --- a/include/hw/ppc/pnv_chip.h +++ b/include/hw/ppc/pnv_chip.h @@ -141,6 +141,13 @@ struct Pnv10Chip { #define PNV10_PIR2CHIP(pir) (((pir) >> 8) & 0x7f) #define PNV10_PIR2THREAD(pir) (((pir) & 0x7f)) +#define TYPE_PNV11_CHIP "pnv11-chip" +DECLARE_INSTANCE_CHECKER(Pnv11Chip, PNV11_CHIP, + TYPE_PNV11_CHIP) + +/* Power11 core is same as Power10 */ +typedef struct Pnv10Chip Pnv11Chip; + struct PnvChipClass { /*< private >*/ SysBusDeviceClass parent_class; @@ -163,6 +170,7 @@ struct PnvChipClass { void (*intc_reset)(PnvChip *chip, PowerPCCPU *cpu); void (*intc_destroy)(PnvChip *chip, PowerPCCPU *cpu); void (*intc_print_info)(PnvChip *chip, PowerPCCPU *cpu, GString *buf); + void* (*intc_get)(PnvChip *chip); ISABus *(*isa_create)(PnvChip *chip, Error **errp); void (*dt_populate)(PnvChip *chip, void *fdt); void (*pic_print_info)(PnvChip *chip, GString *buf); diff --git a/include/hw/ppc/pnv_chiptod.h b/include/hw/ppc/pnv_chiptod.h index fde569b..466b065 100644 --- a/include/hw/ppc/pnv_chiptod.h +++ b/include/hw/ppc/pnv_chiptod.h @@ -17,6 +17,8 @@ OBJECT_DECLARE_TYPE(PnvChipTOD, PnvChipTODClass, PNV_CHIPTOD) DECLARE_INSTANCE_CHECKER(PnvChipTOD, PNV9_CHIPTOD, TYPE_PNV9_CHIPTOD) #define TYPE_PNV10_CHIPTOD TYPE_PNV_CHIPTOD "-POWER10" DECLARE_INSTANCE_CHECKER(PnvChipTOD, PNV10_CHIPTOD, TYPE_PNV10_CHIPTOD) +#define TYPE_PNV11_CHIPTOD TYPE_PNV_CHIPTOD "-POWER11" +DECLARE_INSTANCE_CHECKER(PnvChipTOD, PNV11_CHIPTOD, TYPE_PNV11_CHIPTOD) enum tod_state { tod_error = 0, diff --git a/include/hw/ppc/pnv_lpc.h b/include/hw/ppc/pnv_lpc.h index 174add4..266d562 100644 --- a/include/hw/ppc/pnv_lpc.h +++ b/include/hw/ppc/pnv_lpc.h @@ -20,7 +20,7 @@ #ifndef PPC_PNV_LPC_H #define PPC_PNV_LPC_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/ppc/pnv.h" #include "hw/qdev-core.h" #include "hw/isa/isa.h" /* For ISA_NUM_IRQS */ diff --git a/include/hw/ppc/pnv_occ.h b/include/hw/ppc/pnv_occ.h index 3ec42de..013ea2e 100644 --- a/include/hw/ppc/pnv_occ.h +++ b/include/hw/ppc/pnv_occ.h @@ -20,7 +20,7 @@ #ifndef PPC_PNV_OCC_H #define PPC_PNV_OCC_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/qdev-core.h" #define TYPE_PNV_OCC "pnv-occ" diff --git a/include/hw/ppc/pnv_sbe.h b/include/hw/ppc/pnv_sbe.h index b6b378a..48a8b86 100644 --- a/include/hw/ppc/pnv_sbe.h +++ b/include/hw/ppc/pnv_sbe.h @@ -20,7 +20,7 @@ #ifndef PPC_PNV_SBE_H #define PPC_PNV_SBE_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/qdev-core.h" #define TYPE_PNV_SBE "pnv-sbe" diff --git a/include/hw/ppc/pnv_xscom.h b/include/hw/ppc/pnv_xscom.h index a927aea..610b075 100644 --- a/include/hw/ppc/pnv_xscom.h +++ b/include/hw/ppc/pnv_xscom.h @@ -20,7 +20,7 @@ #ifndef PPC_PNV_XSCOM_H #define PPC_PNV_XSCOM_H -#include "exec/memory.h" +#include "system/memory.h" typedef struct PnvXScomInterface PnvXScomInterface; typedef struct PnvChip PnvChip; @@ -207,6 +207,55 @@ struct PnvXScomInterfaceClass { #define PNV10_XSCOM_PIB_SPIC_BASE 0xc0000 #define PNV10_XSCOM_PIB_SPIC_SIZE 0x20 +/* + * Power11 core is same as Power10 + */ +#define PNV11_XSCOM_EC_BASE(core) PNV10_XSCOM_EC_BASE(core) + +#define PNV11_XSCOM_ADU_BASE PNV10_XSCOM_ADU_BASE +#define PNV11_XSCOM_ADU_SIZE PNV10_XSCOM_ADU_SIZE + +#define PNV11_XSCOM_QME_BASE(core) PNV10_XSCOM_QME_BASE(core) + +#define PNV11_XSCOM_EQ_BASE(core) PNV10_XSCOM_EQ_BASE(core) + +#define PNV11_XSCOM_PSIHB_BASE PNV10_XSCOM_PSIHB_BASE +#define PNV11_XSCOM_PSIHB_SIZE PNV10_XSCOM_PSIHB_SIZE + +#define PNV11_XSCOM_I2CM_BASE PNV10_XSCOM_I2CM_BASE +#define PNV11_XSCOM_I2CM_SIZE PNV10_XSCOM_I2CM_SIZE + +#define PNV11_XSCOM_CHIPTOD_BASE PNV10_XSCOM_CHIPTOD_BASE +#define PNV11_XSCOM_CHIPTOD_SIZE PNV10_XSCOM_CHIPTOD_SIZE + +#define PNV11_XSCOM_OCC_BASE PNV10_XSCOM_OCC_BASE +#define PNV11_XSCOM_OCC_SIZE PNV10_XSCOM_OCC_SIZE + +#define PNV11_XSCOM_SBE_CTRL_BASE PNV10_XSCOM_SBE_CTRL_BASE +#define PNV11_XSCOM_SBE_CTRL_SIZE PNV10_XSCOM_SBE_CTRL_SIZE + +#define PNV11_XSCOM_SBE_MBOX_BASE PNV10_XSCOM_SBE_MBOX_BASE +#define PNV11_XSCOM_SBE_MBOX_SIZE PNV10_XSCOM_SBE_MBOX_SIZE + +#define PNV11_XSCOM_PBA_BASE PNV10_XSCOM_PBA_BASE +#define PNV11_XSCOM_PBA_SIZE PNV10_XSCOM_PBA_SIZE + +#define PNV11_XSCOM_XIVE2_BASE PNV10_XSCOM_XIVE2_BASE +#define PNV11_XSCOM_XIVE2_SIZE PNV10_XSCOM_XIVE2_SIZE + +#define PNV11_XSCOM_N1_CHIPLET_CTRL_REGS_BASE \ + PNV10_XSCOM_N1_CHIPLET_CTRL_REGS_BASE +#define PNV11_XSCOM_CHIPLET_CTRL_REGS_SIZE PNV10_XSCOM_CHIPLET_CTRL_REGS_SIZE + +#define PNV11_XSCOM_N1_PB_SCOM_EQ_BASE PNV10_XSCOM_N1_PB_SCOM_EQ_BASE +#define PNV11_XSCOM_N1_PB_SCOM_EQ_SIZE PNV10_XSCOM_N1_PB_SCOM_EQ_SIZE + +#define PNV11_XSCOM_N1_PB_SCOM_ES_BASE PNV10_XSCOM_N1_PB_SCOM_ES_BASE +#define PNV11_XSCOM_N1_PB_SCOM_ES_SIZE PNV10_XSCOM_N1_PB_SCOM_ES_SIZE + +#define PNV11_XSCOM_PIB_SPIC_BASE PNV10_XSCOM_PIB_SPIC_BASE +#define PNV11_XSCOM_PIB_SPIC_SIZE PNV10_XSCOM_PIB_SPIC_SIZE + void pnv_xscom_init(PnvChip *chip, uint64_t size, hwaddr addr); int pnv_dt_xscom(PnvChip *chip, void *fdt, int root_offset, uint64_t xscom_base, uint64_t xscom_size, diff --git a/include/hw/ppc/ppc.h b/include/hw/ppc/ppc.h index 8a14d62..cb51d70 100644 --- a/include/hw/ppc/ppc.h +++ b/include/hw/ppc/ppc.h @@ -52,6 +52,7 @@ struct ppc_tb_t { #define PPC_DECR_UNDERFLOW_LEVEL (1 << 4) /* Decr interrupt active when * the most significant bit is 1. */ +#define PPC_TIMER_PPE (1 << 5) /* Enable PPE support */ uint64_t cpu_ppc_get_tb(ppc_tb_t *tb_env, uint64_t vmclk, int64_t tb_offset); void cpu_ppc_tb_init(CPUPPCState *env, uint32_t freq); diff --git a/include/hw/ppc/ppc4xx.h b/include/hw/ppc/ppc4xx.h index 1bd9b88..2e94b00 100644 --- a/include/hw/ppc/ppc4xx.h +++ b/include/hw/ppc/ppc4xx.h @@ -26,7 +26,7 @@ #define PPC4XX_H #include "hw/ppc/ppc.h" -#include "exec/memory.h" +#include "system/memory.h" #include "hw/sysbus.h" /* diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h index 39bd5bd..28cf272 100644 --- a/include/hw/ppc/spapr.h +++ b/include/hw/ppc/spapr.h @@ -13,6 +13,7 @@ #include "hw/ppc/xics.h" /* For ICSState */ #include "hw/ppc/spapr_tpm_proxy.h" #include "hw/ppc/spapr_nested.h" /* For SpaprMachineStateNested */ +#include "hw/ppc/spapr_fadump.h" /* For FadumpMemStruct */ struct SpaprVioBus; struct SpaprPhbState; @@ -139,27 +140,11 @@ struct SpaprCapabilities { * SpaprMachineClass: */ struct SpaprMachineClass { - /*< private >*/ MachineClass parent_class; - /*< public >*/ - bool dr_phb_enabled; /* enable dynamic-reconfig/hotplug of PHBs */ - bool update_dt_enabled; /* enable KVMPPC_H_UPDATE_DT */ - bool legacy_irq_allocation; - uint32_t nr_xirqs; - bool broken_host_serial_model; /* present real host info to the guest */ - bool pre_4_1_migration; /* don't migrate hpt-max-page-size */ - bool linux_pci_probe; - bool smp_threads_vsmt; /* set VSMT to smp_threads by default */ - hwaddr rma_limit; /* clamp the RMA to this size */ bool pre_5_1_assoc_refpoints; bool pre_5_2_numa_associativity; bool pre_6_2_numa_affinity; - - bool (*phb_placement)(SpaprMachineState *spapr, uint32_t index, - uint64_t *buid, hwaddr *pio, - hwaddr *mmio32, hwaddr *mmio64, - unsigned n_dma, uint32_t *liobns, Error **errp); SpaprResizeHpt resize_hpt_default; SpaprCapabilities default_caps; SpaprIrq *irq; @@ -283,6 +268,11 @@ struct SpaprMachineState { Error *fwnmi_migration_blocker; SpaprWatchdog wds[WDT_MAX_WATCHDOGS]; + + /* Fadump State */ + bool fadump_registered; + bool fadump_dump_active; + FadumpMemStruct registered_fdm; }; #define H_SUCCESS 0 @@ -708,6 +698,8 @@ void push_sregs_to_kvm_pr(SpaprMachineState *spapr); #define RTAS_OUT_PARAM_ERROR -3 #define RTAS_OUT_NOT_SUPPORTED -3 #define RTAS_OUT_NO_SUCH_INDICATOR -3 +#define RTAS_OUT_DUMP_ALREADY_REGISTERED -9 +#define RTAS_OUT_DUMP_ACTIVE -10 #define RTAS_OUT_NOT_AUTHORIZED -9002 #define RTAS_OUT_SYSPARM_PARAM_ERROR -9999 @@ -770,8 +762,9 @@ void push_sregs_to_kvm_pr(SpaprMachineState *spapr); #define RTAS_IBM_SUSPEND_ME (RTAS_TOKEN_BASE + 0x2A) #define RTAS_IBM_NMI_REGISTER (RTAS_TOKEN_BASE + 0x2B) #define RTAS_IBM_NMI_INTERLOCK (RTAS_TOKEN_BASE + 0x2C) +#define RTAS_CONFIGURE_KERNEL_DUMP (RTAS_TOKEN_BASE + 0x2D) -#define RTAS_TOKEN_MAX (RTAS_TOKEN_BASE + 0x2D) +#define RTAS_TOKEN_MAX (RTAS_TOKEN_BASE + 0x2E) /* RTAS ibm,get-system-parameter token values */ #define RTAS_SYSPARM_SPLPAR_CHARACTERISTICS 20 diff --git a/include/hw/ppc/spapr_fadump.h b/include/hw/ppc/spapr_fadump.h new file mode 100644 index 0000000..fde2830 --- /dev/null +++ b/include/hw/ppc/spapr_fadump.h @@ -0,0 +1,124 @@ +/* + * Firmware Assisted Dump in PSeries + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ +#ifndef PPC_SPAPR_FADUMP_H +#define PPC_SPAPR_FADUMP_H + +#include "qemu/osdep.h" +#include "cpu.h" + +/* Fadump commands */ +#define FADUMP_CMD_REGISTER 1 +#define FADUMP_CMD_UNREGISTER 2 +#define FADUMP_CMD_INVALIDATE 3 + +#define FADUMP_VERSION 1 + +/* Firmware provided dump sections */ +#define FADUMP_CPU_STATE_DATA 0x0001 +#define FADUMP_HPTE_REGION 0x0002 +#define FADUMP_REAL_MODE_REGION 0x0011 + +/* OS defined sections */ +#define FADUMP_PARAM_AREA 0x0100 + +/* Dump request flag */ +#define FADUMP_REQUEST_FLAG 0x00000001 + +/* Dump status flags */ +#define FADUMP_STATUS_DUMP_PERFORMED 0x8000 +#define FADUMP_STATUS_DUMP_TRIGGERED 0x4000 +#define FADUMP_STATUS_DUMP_ERROR 0x2000 + +/* Region dump error flags */ +#define FADUMP_ERROR_INVALID_DATA_TYPE 0x8000 +#define FADUMP_ERROR_INVALID_SOURCE_ADDR 0x4000 +#define FADUMP_ERROR_LENGTH_EXCEEDS_SOURCE 0x2000 +#define FADUMP_ERROR_INVALID_DEST_ADDR 0x1000 +#define FAUDMP_ERROR_DEST_TOO_SMALL 0x0800 + +/* + * The Firmware Assisted Dump Memory structure supports a maximum of 10 sections + * in the dump memory structure. Presently, three sections are used for + * CPU state data, HPTE & Parameters area, while the remaining seven sections + * can be used for boot memory regions. + */ +#define FADUMP_MAX_SECTIONS 10 + +/* Number of register entries stored per cpu */ +#define FADUMP_PER_CPU_REG_ENTRIES (32 /*GPR*/ + 45 /*others*/ + 2 /*STRT & END*/) + +/* Mask of CPU ID in CPUSTRT and CPUEND entries */ +#define FADUMP_CPU_ID_MASK ((1ULL << 32) - 1) + +typedef struct FadumpSection FadumpSection; +typedef struct FadumpSectionHeader FadumpSectionHeader; +typedef struct FadumpMemStruct FadumpMemStruct; +typedef struct FadumpRegSaveAreaHeader FadumpRegSaveAreaHeader; +typedef struct FadumpRegEntry FadumpRegEntry; + +struct SpaprMachineState; + +/* Kernel Dump section info */ +/* All fields are in big-endian */ +struct FadumpSection { + uint32_t request_flag; + uint16_t source_data_type; + uint16_t error_flags; + uint64_t source_address; + uint64_t source_len; + uint64_t bytes_dumped; + uint64_t destination_address; +}; + +/* ibm,configure-kernel-dump header. */ +struct FadumpSectionHeader { + uint32_t dump_format_version; + uint16_t dump_num_sections; + uint16_t dump_status_flag; + uint32_t offset_first_dump_section; + + /* Fields for disk dump option. */ + uint32_t dd_block_size; + uint64_t dd_block_offset; + uint64_t dd_num_blocks; + uint32_t dd_offset_disk_path; + + /* Maximum time allowed to prevent an automatic dump-reboot. */ + uint32_t max_time_auto; +}; + +/* Note: All the data in these structures is in big-endian */ +struct FadumpMemStruct { + FadumpSectionHeader header; + FadumpSection rgn[FADUMP_MAX_SECTIONS]; +}; + +/* + * The firmware-assisted dump format. + * + * The register save area is an area in the partition's memory used to preserve + * the register contents (CPU state data) for the active CPUs during a firmware + * assisted dump. The dump format contains register save area header followed + * by register entries. Each list of registers for a CPU starts with "CPUSTRT" + * and ends with "CPUEND". + */ + +/* Register save area header. */ +struct FadumpRegSaveAreaHeader { + uint64_t magic_number; + uint32_t version; + uint32_t num_cpu_offset; +}; + +/* Register entry. */ +struct FadumpRegEntry { + uint64_t reg_id; + uint64_t reg_value; +}; + +uint32_t do_fadump_register(struct SpaprMachineState *, target_ulong); +void trigger_fadump_boot(struct SpaprMachineState *, target_ulong); +#endif /* PPC_SPAPR_FADUMP_H */ diff --git a/include/hw/ppc/spapr_irq.h b/include/hw/ppc/spapr_irq.h index cb9a85f..265d43e 100644 --- a/include/hw/ppc/spapr_irq.h +++ b/include/hw/ppc/spapr_irq.h @@ -40,6 +40,7 @@ #define SPAPR_IRQ_MSI (SPAPR_XIRQ_BASE + 0x0300) #define SPAPR_NR_XIRQS 0x1000 +#define SPAPR_IRQ_NR_MSIS (SPAPR_XIRQ_BASE + SPAPR_NR_XIRQS - SPAPR_IRQ_MSI) struct SpaprMachineState; @@ -89,7 +90,6 @@ void spapr_irq_print_info(struct SpaprMachineState *spapr, GString *buf); void spapr_irq_dt(struct SpaprMachineState *spapr, uint32_t nr_servers, void *fdt, uint32_t phandle); -uint32_t spapr_irq_nr_msis(struct SpaprMachineState *spapr); int spapr_irq_msi_alloc(struct SpaprMachineState *spapr, uint32_t num, bool align, Error **errp); void spapr_irq_msi_free(struct SpaprMachineState *spapr, int irq, uint32_t num); @@ -100,7 +100,6 @@ typedef struct SpaprIrq { } SpaprIrq; extern SpaprIrq spapr_irq_xics; -extern SpaprIrq spapr_irq_xics_legacy; extern SpaprIrq spapr_irq_xive; extern SpaprIrq spapr_irq_dual; diff --git a/include/hw/ppc/vof.h b/include/hw/ppc/vof.h index d3f293d..3a0fbff 100644 --- a/include/hw/ppc/vof.h +++ b/include/hw/ppc/vof.h @@ -7,8 +7,8 @@ #define HW_VOF_H #include "qom/object.h" -#include "exec/address-spaces.h" -#include "exec/memory.h" +#include "system/address-spaces.h" +#include "system/memory.h" #include "exec/cpu-defs.h" typedef struct Vof { diff --git a/include/hw/ppc/xics.h b/include/hw/ppc/xics.h index e94d534..097fcdf 100644 --- a/include/hw/ppc/xics.h +++ b/include/hw/ppc/xics.h @@ -28,7 +28,7 @@ #ifndef XICS_H #define XICS_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/qdev-core.h" #include "qom/object.h" diff --git a/include/hw/ppc/xive.h b/include/hw/ppc/xive.h index 538f438..b7ca854 100644 --- a/include/hw/ppc/xive.h +++ b/include/hw/ppc/xive.h @@ -365,6 +365,11 @@ static inline uint32_t xive_tctx_word2(uint8_t *ring) return *((uint32_t *) &ring[TM_WORD2]); } +bool xive_ring_valid(XiveTCTX *tctx, uint8_t ring); +bool xive_nsr_indicates_exception(uint8_t ring, uint8_t nsr); +bool xive_nsr_indicates_group_exception(uint8_t ring, uint8_t nsr); +uint8_t xive_nsr_exception_ring(uint8_t ring, uint8_t nsr); + /* * XIVE Router */ @@ -421,6 +426,7 @@ void xive_router_end_notify(XiveRouter *xrtr, XiveEAS *eas); typedef struct XiveTCTXMatch { XiveTCTX *tctx; + int count; uint8_t ring; bool precluded; } XiveTCTXMatch; @@ -436,10 +442,10 @@ DECLARE_CLASS_CHECKERS(XivePresenterClass, XIVE_PRESENTER, struct XivePresenterClass { InterfaceClass parent; - int (*match_nvt)(XivePresenter *xptr, uint8_t format, - uint8_t nvt_blk, uint32_t nvt_idx, - bool crowd, bool cam_ignore, uint8_t priority, - uint32_t logic_serv, XiveTCTXMatch *match); + bool (*match_nvt)(XivePresenter *xptr, uint8_t format, + uint8_t nvt_blk, uint32_t nvt_idx, + bool crowd, bool cam_ignore, uint8_t priority, + uint32_t logic_serv, XiveTCTXMatch *match); bool (*in_kernel)(const XivePresenter *xptr); uint32_t (*get_config)(XivePresenter *xptr); int (*broadcast)(XivePresenter *xptr, @@ -451,12 +457,14 @@ int xive_presenter_tctx_match(XivePresenter *xptr, XiveTCTX *tctx, uint8_t format, uint8_t nvt_blk, uint32_t nvt_idx, bool cam_ignore, uint32_t logic_serv); -bool xive_presenter_notify(XiveFabric *xfb, uint8_t format, - uint8_t nvt_blk, uint32_t nvt_idx, - bool crowd, bool cam_ignore, uint8_t priority, - uint32_t logic_serv, bool *precluded); +bool xive_presenter_match(XiveFabric *xfb, uint8_t format, + uint8_t nvt_blk, uint32_t nvt_idx, + bool crowd, bool cam_ignore, uint8_t priority, + uint32_t logic_serv, XiveTCTXMatch *match); uint32_t xive_get_vpgroup_size(uint32_t nvp_index); +uint8_t xive_get_group_level(bool crowd, bool ignore, + uint32_t nvp_blk, uint32_t nvp_index); /* * XIVE Fabric (Interface between Interrupt Controller and Machine) @@ -471,10 +479,10 @@ DECLARE_CLASS_CHECKERS(XiveFabricClass, XIVE_FABRIC, struct XiveFabricClass { InterfaceClass parent; - int (*match_nvt)(XiveFabric *xfb, uint8_t format, - uint8_t nvt_blk, uint32_t nvt_idx, - bool crowd, bool cam_ignore, uint8_t priority, - uint32_t logic_serv, XiveTCTXMatch *match); + bool (*match_nvt)(XiveFabric *xfb, uint8_t format, + uint8_t nvt_blk, uint32_t nvt_idx, + bool crowd, bool cam_ignore, uint8_t priority, + uint32_t logic_serv, XiveTCTXMatch *match); int (*broadcast)(XiveFabric *xfb, uint8_t nvt_blk, uint32_t nvt_idx, bool crowd, bool cam_ignore, uint8_t priority); }; @@ -532,7 +540,7 @@ static inline uint8_t xive_ipb_to_pipr(uint8_t ibp) } /* - * XIVE Thread Interrupt Management Aera (TIMA) + * XIVE Thread Interrupt Management Area (TIMA) * * This region gives access to the registers of the thread interrupt * management context. It is four page wide, each page providing a @@ -544,6 +552,30 @@ static inline uint8_t xive_ipb_to_pipr(uint8_t ibp) #define XIVE_TM_OS_PAGE 0x2 #define XIVE_TM_USER_PAGE 0x3 +/* + * The TCTX (TIMA) has 4 rings (phys, pool, os, user), but only signals + * (raises an interrupt on) the CPU from 3 of them. Phys and pool both + * cause a hypervisor privileged interrupt so interrupts presented on + * those rings signal using the phys ring. This helper returns the signal + * regs from the given ring. + */ +static inline uint8_t *xive_tctx_signal_regs(XiveTCTX *tctx, uint8_t ring) +{ + /* + * This is a good point to add invariants to ensure nothing has tried to + * signal using the POOL ring. + */ + g_assert(tctx->regs[TM_QW2_HV_POOL + TM_NSR] == 0); + g_assert(tctx->regs[TM_QW2_HV_POOL + TM_PIPR] == 0); + g_assert(tctx->regs[TM_QW2_HV_POOL + TM_CPPR] == 0); + + if (ring == TM_QW2_HV_POOL) { + /* POOL and PHYS rings share the signal regs (PIPR, NSR, CPPR) */ + ring = TM_QW3_HV_PHYS; + } + return &tctx->regs[ring]; +} + void xive_tctx_tm_write(XivePresenter *xptr, XiveTCTX *tctx, hwaddr offset, uint64_t value, unsigned size); uint64_t xive_tctx_tm_read(XivePresenter *xptr, XiveTCTX *tctx, hwaddr offset, @@ -553,10 +585,12 @@ void xive_tctx_pic_print_info(XiveTCTX *tctx, GString *buf); Object *xive_tctx_create(Object *cpu, XivePresenter *xptr, Error **errp); void xive_tctx_reset(XiveTCTX *tctx); void xive_tctx_destroy(XiveTCTX *tctx); -void xive_tctx_pipr_update(XiveTCTX *tctx, uint8_t ring, uint8_t priority, - uint8_t group_level); +void xive_tctx_pipr_set(XiveTCTX *tctx, uint8_t ring, uint8_t priority, + uint8_t group_level); +void xive_tctx_pipr_present(XiveTCTX *tctx, uint8_t ring, uint8_t priority, + uint8_t group_level); void xive_tctx_reset_signal(XiveTCTX *tctx, uint8_t ring); -void xive_tctx_notify(XiveTCTX *tctx, uint8_t ring, uint8_t group_level); +uint64_t xive_tctx_accept(XiveTCTX *tctx, uint8_t ring); /* * KVM XIVE device helpers diff --git a/include/hw/ppc/xive2.h b/include/hw/ppc/xive2.h index 8cdf819..f4437e2 100644 --- a/include/hw/ppc/xive2.h +++ b/include/hw/ppc/xive2.h @@ -29,9 +29,11 @@ OBJECT_DECLARE_TYPE(Xive2Router, Xive2RouterClass, XIVE2_ROUTER); * Configuration flags */ -#define XIVE2_GEN1_TIMA_OS 0x00000001 -#define XIVE2_VP_SAVE_RESTORE 0x00000002 -#define XIVE2_THREADID_8BITS 0x00000004 +#define XIVE2_GEN1_TIMA_OS 0x00000001 +#define XIVE2_VP_SAVE_RESTORE 0x00000002 +#define XIVE2_THREADID_8BITS 0x00000004 +#define XIVE2_EN_VP_GRP_PRIORITY 0x00000008 +#define XIVE2_VP_INT_PRIO 0x00000030 typedef struct Xive2RouterClass { SysBusDeviceClass parent; @@ -80,6 +82,7 @@ int xive2_router_write_nvgc(Xive2Router *xrtr, bool crowd, uint32_t xive2_router_get_config(Xive2Router *xrtr); void xive2_router_notify(XiveNotifier *xn, uint32_t lisn, bool pq_checked); +void xive2_notify(Xive2Router *xrtr, uint32_t lisn, bool pq_checked); /* * XIVE2 Presenter (POWER10) @@ -127,6 +130,8 @@ void xive2_tm_set_hv_cppr(XivePresenter *xptr, XiveTCTX *tctx, hwaddr offset, uint64_t value, unsigned size); void xive2_tm_set_os_cppr(XivePresenter *xptr, XiveTCTX *tctx, hwaddr offset, uint64_t value, unsigned size); +void xive2_tm_set_os_pending(XivePresenter *xptr, XiveTCTX *tctx, + hwaddr offset, uint64_t value, unsigned size); void xive2_tm_push_os_ctx(XivePresenter *xptr, XiveTCTX *tctx, hwaddr offset, uint64_t value, unsigned size); uint64_t xive2_tm_pull_os_ctx(XivePresenter *xptr, XiveTCTX *tctx, @@ -137,7 +142,16 @@ bool xive2_tm_irq_precluded(XiveTCTX *tctx, int ring, uint8_t priority); void xive2_tm_set_lsmfb(XiveTCTX *tctx, int ring, uint8_t priority); void xive2_tm_set_hv_target(XivePresenter *xptr, XiveTCTX *tctx, hwaddr offset, uint64_t value, unsigned size); +void xive2_tm_push_pool_ctx(XivePresenter *xptr, XiveTCTX *tctx, + hwaddr offset, uint64_t value, unsigned size); +uint64_t xive2_tm_pull_pool_ctx(XivePresenter *xptr, XiveTCTX *tctx, + hwaddr offset, unsigned size); +void xive2_tm_push_phys_ctx(XivePresenter *xptr, XiveTCTX *tctx, + hwaddr offset, uint64_t value, unsigned size); +uint64_t xive2_tm_pull_phys_ctx(XivePresenter *xptr, XiveTCTX *tctx, + hwaddr offset, unsigned size); void xive2_tm_pull_phys_ctx_ol(XivePresenter *xptr, XiveTCTX *tctx, hwaddr offset, uint64_t value, unsigned size); - +void xive2_tm_ack_os_el(XivePresenter *xptr, XiveTCTX *tctx, + hwaddr offset, uint64_t value, unsigned size); #endif /* PPC_XIVE2_H */ diff --git a/include/hw/ppc/xive2_regs.h b/include/hw/ppc/xive2_regs.h index b11395c..2a3e60a 100644 --- a/include/hw/ppc/xive2_regs.h +++ b/include/hw/ppc/xive2_regs.h @@ -39,15 +39,18 @@ typedef struct Xive2Eas { uint64_t w; -#define EAS2_VALID PPC_BIT(0) -#define EAS2_END_BLOCK PPC_BITMASK(4, 7) /* Destination EQ block# */ -#define EAS2_END_INDEX PPC_BITMASK(8, 31) /* Destination EQ index */ -#define EAS2_MASKED PPC_BIT(32) /* Masked */ -#define EAS2_END_DATA PPC_BITMASK(33, 63) /* written to the EQ */ +#define EAS2_VALID PPC_BIT(0) +#define EAS2_QOS PPC_BIT(1, 2) /* Quality of Service(unimp) */ +#define EAS2_RESUME PPC_BIT(3) /* END Resume(unimp) */ +#define EAS2_END_BLOCK PPC_BITMASK(4, 7) /* Destination EQ block# */ +#define EAS2_END_INDEX PPC_BITMASK(8, 31) /* Destination EQ index */ +#define EAS2_MASKED PPC_BIT(32) /* Masked */ +#define EAS2_END_DATA PPC_BITMASK(33, 63) /* written to the EQ */ } Xive2Eas; #define xive2_eas_is_valid(eas) (be64_to_cpu((eas)->w) & EAS2_VALID) #define xive2_eas_is_masked(eas) (be64_to_cpu((eas)->w) & EAS2_MASKED) +#define xive2_eas_is_resume(eas) (be64_to_cpu((eas)->w) & EAS2_RESUME) void xive2_eas_pic_print_info(Xive2Eas *eas, uint32_t lisn, GString *buf); @@ -87,6 +90,7 @@ typedef struct Xive2End { #define END2_W2_EQ_ADDR_HI PPC_BITMASK32(8, 31) uint32_t w3; #define END2_W3_EQ_ADDR_LO PPC_BITMASK32(0, 24) +#define END2_W3_CL PPC_BIT32(27) #define END2_W3_QSIZE PPC_BITMASK32(28, 31) uint32_t w4; #define END2_W4_END_BLOCK PPC_BITMASK32(4, 7) @@ -154,6 +158,7 @@ typedef struct Xive2Nvp { #define NVP2_W0_L PPC_BIT32(8) #define NVP2_W0_G PPC_BIT32(9) #define NVP2_W0_T PPC_BIT32(10) +#define NVP2_W0_P PPC_BIT32(11) #define NVP2_W0_ESC_END PPC_BIT32(25) /* 'N' bit 0:ESB 1:END */ #define NVP2_W0_PGOFIRST PPC_BITMASK32(26, 31) uint32_t w1; @@ -205,9 +210,9 @@ static inline uint32_t xive2_nvp_idx(uint32_t cam_line) return cam_line & ((1 << XIVE2_NVP_SHIFT) - 1); } -static inline uint32_t xive2_nvp_blk(uint32_t cam_line) +static inline uint8_t xive2_nvp_blk(uint32_t cam_line) { - return (cam_line >> XIVE2_NVP_SHIFT) & 0xf; + return (uint8_t)((cam_line >> XIVE2_NVP_SHIFT) & 0xf); } void xive2_nvp_pic_print_info(Xive2Nvp *nvp, uint32_t nvp_idx, GString *buf); @@ -220,6 +225,9 @@ typedef struct Xive2Nvgc { #define NVGC2_W0_VALID PPC_BIT32(0) #define NVGC2_W0_PGONEXT PPC_BITMASK32(26, 31) uint32_t w1; +#define NVGC2_W1_PSIZE PPC_BITMASK32(0, 1) +#define NVGC2_W1_END_BLK PPC_BITMASK32(4, 7) +#define NVGC2_W1_END_IDX PPC_BITMASK32(8, 31) uint32_t w2; uint32_t w3; uint32_t w4; diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h index 530f3da..2caa0cb 100644 --- a/include/hw/qdev-core.h +++ b/include/hw/qdev-core.h @@ -725,7 +725,8 @@ void qdev_connect_gpio_out_named(DeviceState *dev, const char *name, int n, * * Return: qemu_irq associated with GPIO or NULL if un-wired. */ -qemu_irq qdev_get_gpio_out_connector(DeviceState *dev, const char *name, int n); +qemu_irq qdev_get_gpio_out_connector(const DeviceState *dev, + const char *name, int n); /** * qdev_intercept_gpio_out: Intercept an existing GPIO connection @@ -1064,6 +1065,7 @@ bool qdev_set_parent_bus(DeviceState *dev, BusState *bus, Error **errp); extern bool qdev_hot_removed; char *qdev_get_dev_path(DeviceState *dev); +const char *qdev_get_printable_name(DeviceState *dev); void qbus_set_hotplug_handler(BusState *bus, Object *handler); void qbus_set_bus_hotplug_handler(BusState *bus); diff --git a/include/hw/qdev-properties-system.h b/include/hw/qdev-properties-system.h index b921392..45687be 100644 --- a/include/hw/qdev-properties-system.h +++ b/include/hw/qdev-properties-system.h @@ -32,12 +32,13 @@ extern const PropertyInfo qdev_prop_cpus390entitlement; extern const PropertyInfo qdev_prop_iothread_vq_mapping_list; extern const PropertyInfo qdev_prop_endian_mode; extern const PropertyInfo qdev_prop_vmapple_virtio_blk_variant; +extern const PropertyInfo qdev_prop_virtio_gpu_output_list; #define DEFINE_PROP_PCI_DEVFN(_n, _s, _f, _d) \ DEFINE_PROP_SIGNED(_n, _s, _f, _d, qdev_prop_pci_devfn, int32_t) #define DEFINE_PROP_CHR(_n, _s, _f) \ - DEFINE_PROP(_n, _s, _f, qdev_prop_chr, CharBackend) + DEFINE_PROP(_n, _s, _f, qdev_prop_chr, CharFrontend) #define DEFINE_PROP_NETDEV(_n, _s, _f) \ DEFINE_PROP(_n, _s, _f, qdev_prop_netdev, NICPeers) #define DEFINE_PROP_DRIVE(_n, _s, _f) \ @@ -86,7 +87,7 @@ extern const PropertyInfo qdev_prop_vmapple_virtio_blk_variant; .set_default = true) #define DEFINE_PROP_AUDIODEV(_n, _s, _f) \ - DEFINE_PROP(_n, _s, _f, qdev_prop_audiodev, QEMUSoundCard) + DEFINE_PROP(_n, _s, _f, qdev_prop_audiodev, AudioBackend *) #define DEFINE_PROP_UUID_NODEFAULT(_name, _state, _field) \ DEFINE_PROP(_name, _state, _field, qdev_prop_uuid, QemuUUID) @@ -110,4 +111,8 @@ extern const PropertyInfo qdev_prop_vmapple_virtio_blk_variant; qdev_prop_vmapple_virtio_blk_variant, \ VMAppleVirtioBlkVariant) +#define DEFINE_PROP_VIRTIO_GPU_OUTPUT_LIST(_name, _state, _field) \ + DEFINE_PROP(_name, _state, _field, qdev_prop_virtio_gpu_output_list, \ + VirtIOGPUOutputList *) + #endif diff --git a/include/hw/qdev-properties.h b/include/hw/qdev-properties.h index 2c99856..60b8133 100644 --- a/include/hw/qdev-properties.h +++ b/include/hw/qdev-properties.h @@ -34,7 +34,7 @@ struct PropertyInfo { const char *description; const QEnumLookup *enum_table; bool realized_set_allowed; /* allow setting property on realized device */ - int (*print)(Object *obj, const Property *prop, char *dest, size_t len); + char *(*print)(Object *obj, const Property *prop); void (*set_default_value)(ObjectProperty *op, const Property *prop); ObjectProperty *(*create)(ObjectClass *oc, const char *name, const Property *prop); @@ -43,11 +43,22 @@ struct PropertyInfo { ObjectPropertyRelease *release; }; +/** + * struct OnOffAutoBit64 - OnOffAuto storage with 64 elements. + * @on_bits: Bitmap of elements with "on". + * @auto_bits: Bitmap of elements with "auto". + */ +typedef struct OnOffAutoBit64 { + uint64_t on_bits; + uint64_t auto_bits; +} OnOffAutoBit64; + /*** qdev-properties.c ***/ extern const PropertyInfo qdev_prop_bit; extern const PropertyInfo qdev_prop_bit64; +extern const PropertyInfo qdev_prop_on_off_auto_bit64; extern const PropertyInfo qdev_prop_bool; extern const PropertyInfo qdev_prop_uint8; extern const PropertyInfo qdev_prop_uint16; @@ -100,6 +111,13 @@ extern const PropertyInfo qdev_prop_link; .set_default = true, \ .defval.u = (bool)_defval) +#define DEFINE_PROP_ON_OFF_AUTO_BIT64(_name, _state, _field, _bit, _defval) \ + DEFINE_PROP(_name, _state, _field, qdev_prop_on_off_auto_bit64, \ + OnOffAutoBit64, \ + .bitnr = (_bit), \ + .set_default = true, \ + .defval.i = (OnOffAuto)_defval) + #define DEFINE_PROP_BOOL(_name, _state, _field, _defval) \ DEFINE_PROP(_name, _state, _field, qdev_prop_bool, bool, \ .set_default = true, \ diff --git a/include/hw/register.h b/include/hw/register.h index 6a076cf..7b0f4c8 100644 --- a/include/hw/register.h +++ b/include/hw/register.h @@ -12,7 +12,7 @@ #define REGISTER_H #include "hw/qdev-core.h" -#include "exec/memory.h" +#include "system/memory.h" #include "hw/registerfields.h" #include "qom/object.h" @@ -75,10 +75,6 @@ struct RegisterAccessInfo { */ struct RegisterInfo { - /* <private> */ - DeviceState parent_obj; - - /* <public> */ void *data; int data_size; @@ -87,9 +83,8 @@ struct RegisterInfo { void *opaque; }; -#define TYPE_REGISTER "qemu-register" -DECLARE_INSTANCE_CHECKER(RegisterInfo, REGISTER, - TYPE_REGISTER) +#define TYPE_REGISTER_ARRAY "qemu-register-array" +OBJECT_DECLARE_SIMPLE_TYPE(RegisterInfoArray, REGISTER_ARRAY) /** * This structure is used to group all of the individual registers which are @@ -103,6 +98,8 @@ DECLARE_INSTANCE_CHECKER(RegisterInfo, REGISTER, */ struct RegisterInfoArray { + Object parent_obj; + MemoryRegion mem; int num_elements; @@ -212,18 +209,4 @@ RegisterInfoArray *register_init_block64(DeviceState *owner, bool debug_enabled, uint64_t memory_size); -/** - * This function should be called to cleanup the registers that were initialized - * when calling register_init_block32(). This function should only be called - * from the device's instance_finalize function. - * - * Any memory operations that the device performed that require cleanup (such - * as creating subregions) need to be called before calling this function. - * - * @r_array: A structure containing all of the registers, as returned by - * register_init_block32() - */ - -void register_finalize_block(RegisterInfoArray *r_array); - #endif diff --git a/include/hw/remote/proxy-memory-listener.h b/include/hw/remote/proxy-memory-listener.h index c4f3efb..ec516d8 100644 --- a/include/hw/remote/proxy-memory-listener.h +++ b/include/hw/remote/proxy-memory-listener.h @@ -9,7 +9,7 @@ #ifndef PROXY_MEMORY_LISTENER_H #define PROXY_MEMORY_LISTENER_H -#include "exec/memory.h" +#include "system/memory.h" #include "io/channel.h" typedef struct ProxyMemoryListener { diff --git a/include/hw/riscv/boot.h b/include/hw/riscv/boot.h index 7d59b2e..51b0e13 100644 --- a/include/hw/riscv/boot.h +++ b/include/hw/riscv/boot.h @@ -43,18 +43,18 @@ bool riscv_is_32bit(RISCVHartArrayState *harts); char *riscv_plic_hart_config_string(int hart_count); void riscv_boot_info_init(RISCVBootInfo *info, RISCVHartArrayState *harts); -target_ulong riscv_calc_kernel_start_addr(RISCVBootInfo *info, - target_ulong firmware_end_addr); -target_ulong riscv_find_and_load_firmware(MachineState *machine, - const char *default_machine_firmware, - hwaddr *firmware_load_addr, - symbol_fn_t sym_cb); +hwaddr riscv_calc_kernel_start_addr(RISCVBootInfo *info, + hwaddr firmware_end_addr); +hwaddr riscv_find_and_load_firmware(MachineState *machine, + const char *default_machine_firmware, + hwaddr *firmware_load_addr, + symbol_fn_t sym_cb); const char *riscv_default_firmware_name(RISCVHartArrayState *harts); char *riscv_find_firmware(const char *firmware_filename, const char *default_machine_firmware); -target_ulong riscv_load_firmware(const char *firmware_filename, - hwaddr *firmware_load_addr, - symbol_fn_t sym_cb); +hwaddr riscv_load_firmware(const char *firmware_filename, + hwaddr *firmware_load_addr, + symbol_fn_t sym_cb); void riscv_load_kernel(MachineState *machine, RISCVBootInfo *info, target_ulong kernel_start_addr, diff --git a/include/hw/riscv/boot_opensbi.h b/include/hw/riscv/boot_opensbi.h index 18664a1..ab9999b 100644 --- a/include/hw/riscv/boot_opensbi.h +++ b/include/hw/riscv/boot_opensbi.h @@ -29,17 +29,17 @@ enum sbi_scratch_options { }; /** Representation dynamic info passed by previous booting stage */ -struct fw_dynamic_info { +struct fw_dynamic_info64 { /** Info magic */ - target_long magic; + int64_t magic; /** Info version */ - target_long version; + int64_t version; /** Next booting stage address */ - target_long next_addr; + int64_t next_addr; /** Next booting stage mode */ - target_long next_mode; + int64_t next_mode; /** Options for OpenSBI library */ - target_long options; + int64_t options; /** * Preferred boot HART id * @@ -55,7 +55,7 @@ struct fw_dynamic_info { * stage can set it to -1UL which will force the FW_DYNAMIC firmware * to use the relocation lottery mechanism. */ - target_long boot_hart; + int64_t boot_hart; }; /** Representation dynamic info passed by previous booting stage */ diff --git a/include/hw/riscv/iommu.h b/include/hw/riscv/iommu.h index b03339d..25f1a8b 100644 --- a/include/hw/riscv/iommu.h +++ b/include/hw/riscv/iommu.h @@ -24,20 +24,15 @@ #define TYPE_RISCV_IOMMU "riscv-iommu" OBJECT_DECLARE_SIMPLE_TYPE(RISCVIOMMUState, RISCV_IOMMU) -typedef struct RISCVIOMMUState RISCVIOMMUState; #define TYPE_RISCV_IOMMU_MEMORY_REGION "riscv-iommu-mr" typedef struct RISCVIOMMUSpace RISCVIOMMUSpace; #define TYPE_RISCV_IOMMU_PCI "riscv-iommu-pci" -OBJECT_DECLARE_TYPE(RISCVIOMMUStatePci, RISCVIOMMUPciClass, RISCV_IOMMU_PCI) -typedef struct RISCVIOMMUStatePci RISCVIOMMUStatePci; -typedef struct RISCVIOMMUPciClass RISCVIOMMUPciClass; +OBJECT_DECLARE_SIMPLE_TYPE(RISCVIOMMUStatePci, RISCV_IOMMU_PCI) #define TYPE_RISCV_IOMMU_SYS "riscv-iommu-device" -OBJECT_DECLARE_TYPE(RISCVIOMMUStateSys, RISCVIOMMUSysClass, RISCV_IOMMU_SYS) -typedef struct RISCVIOMMUStateSys RISCVIOMMUStateSys; -typedef struct RISCVIOMMUSysClass RISCVIOMMUSysClass; +OBJECT_DECLARE_SIMPLE_TYPE(RISCVIOMMUStateSys, RISCV_IOMMU_SYS) #define FDT_IRQ_TYPE_EDGE_LOW 1 diff --git a/include/hw/riscv/microchip_pfsoc.h b/include/hw/riscv/microchip_pfsoc.h index daef086..7ca9b97 100644 --- a/include/hw/riscv/microchip_pfsoc.h +++ b/include/hw/riscv/microchip_pfsoc.h @@ -67,6 +67,7 @@ typedef struct MicrochipIcicleKitState { MachineState parent_obj; /*< public >*/ + uint32_t clint_timebase_freq; MicrochipPFSoCState soc; } MicrochipIcicleKitState; diff --git a/include/hw/riscv/virt.h b/include/hw/riscv/virt.h index 48a14be..7b4c2c8 100644 --- a/include/hw/riscv/virt.h +++ b/include/hw/riscv/virt.h @@ -63,6 +63,7 @@ struct RISCVVirtState { const MemMapEntry *memmap; struct GPEXHost *gpex_host; OnOffAuto iommu_sys; + uint16_t pci_iommu_bdf; }; enum { diff --git a/include/hw/riscv/xiangshan_kmh.h b/include/hw/riscv/xiangshan_kmh.h new file mode 100644 index 0000000..c5dc6b1 --- /dev/null +++ b/include/hw/riscv/xiangshan_kmh.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: BSD-2-Clause */ +/* + * QEMU RISC-V Board Compatible with the Xiangshan Kunminghu + * FPGA prototype platform + * + * Copyright (c) 2025 Beijing Institute of Open Source Chip (BOSC) + * + */ + +#ifndef HW_XIANGSHAN_KMH_H +#define HW_XIANGSHAN_KMH_H + +#include "hw/boards.h" +#include "hw/riscv/riscv_hart.h" + +#define XIANGSHAN_KMH_MAX_CPUS 16 + +typedef struct XiangshanKmhSoCState { + /*< private >*/ + DeviceState parent_obj; + + /*< public >*/ + RISCVHartArrayState cpus; + DeviceState *irqchip; + MemoryRegion rom; +} XiangshanKmhSoCState; + +#define TYPE_XIANGSHAN_KMH_SOC "xiangshan.kunminghu.soc" +DECLARE_INSTANCE_CHECKER(XiangshanKmhSoCState, XIANGSHAN_KMH_SOC, + TYPE_XIANGSHAN_KMH_SOC) + +typedef struct XiangshanKmhState { + /*< private >*/ + MachineState parent_obj; + + /*< public >*/ + XiangshanKmhSoCState soc; +} XiangshanKmhState; + +#define TYPE_XIANGSHAN_KMH_MACHINE MACHINE_TYPE_NAME("xiangshan-kunminghu") +DECLARE_INSTANCE_CHECKER(XiangshanKmhState, XIANGSHAN_KMH_MACHINE, + TYPE_XIANGSHAN_KMH_MACHINE) + +enum { + XIANGSHAN_KMH_ROM, + XIANGSHAN_KMH_UART0, + XIANGSHAN_KMH_CLINT, + XIANGSHAN_KMH_APLIC_M, + XIANGSHAN_KMH_APLIC_S, + XIANGSHAN_KMH_IMSIC_M, + XIANGSHAN_KMH_IMSIC_S, + XIANGSHAN_KMH_DRAM, +}; + +enum { + XIANGSHAN_KMH_UART0_IRQ = 10, +}; + +/* Indicating Timebase-freq (1MHZ) */ +#define XIANGSHAN_KMH_CLINT_TIMEBASE_FREQ 1000000 + +#define XIANGSHAN_KMH_IMSIC_NUM_IDS 255 +#define XIANGSHAN_KMH_IMSIC_NUM_GUESTS 7 +#define XIANGSHAN_KMH_IMSIC_GUEST_BITS 3 + +#define XIANGSHAN_KMH_APLIC_NUM_SOURCES 96 + +#endif diff --git a/include/hw/s390x/ap-bridge.h b/include/hw/s390x/ap-bridge.h index 470e439..7efc529 100644 --- a/include/hw/s390x/ap-bridge.h +++ b/include/hw/s390x/ap-bridge.h @@ -16,4 +16,43 @@ void s390_init_ap(void); +typedef struct ChscSeiNt0Res { + uint16_t length; + uint16_t code; + uint8_t reserved1; + uint16_t reserved2; + uint8_t nt; +#define PENDING_EVENT_INFO_BITMASK 0x80; + uint8_t flags; + uint8_t reserved3; + uint8_t rs; + uint8_t cc; +} QEMU_PACKED ChscSeiNt0Res; + +#define NT0_RES_RESPONSE_CODE 1 +#define NT0_RES_NT_DEFAULT 0 +#define NT0_RES_RS_AP_CHANGE 5 +#define NT0_RES_CC_AP_CHANGE 3 + +#define EVENT_INFORMATION_NOT_STORED 1 +#define EVENT_INFORMATION_STORED 0 + +/** + * ap_chsc_sei_nt0_get_event - Retrieve the next pending AP config + * change event + * @res: Pointer to a ChscSeiNt0Res struct to be filled with event + * data + * + * This function checks for any pending AP config change events and, + * if present, populates the provided response structure with the + * appropriate SEI NT0 fields. + * + * Return: + * EVENT_INFORMATION_STORED - An event was available and written to @res + * EVENT_INFORMATION_NOT_STORED - No event was available + */ +int ap_chsc_sei_nt0_get_event(void *res); + +bool ap_chsc_sei_nt0_have_event(void); + #endif diff --git a/include/hw/s390x/cpu-topology.h b/include/hw/s390x/cpu-topology.h index 9283c94..d5e9aa4 100644 --- a/include/hw/s390x/cpu-topology.h +++ b/include/hw/s390x/cpu-topology.h @@ -13,7 +13,7 @@ #include "qemu/queue.h" #include "hw/boards.h" -#include "qapi/qapi-types-machine-target.h" +#include "qapi/qapi-types-machine-s390x.h" #define S390_TOPOLOGY_CPU_IFL 0x03 diff --git a/include/hw/s390x/css.h b/include/hw/s390x/css.h index cd97e2b..0b0400a 100644 --- a/include/hw/s390x/css.h +++ b/include/hw/s390x/css.h @@ -238,7 +238,6 @@ uint32_t css_get_adapter_id(CssIoAdapterType type, uint8_t isc); void css_register_io_adapters(CssIoAdapterType type, bool swap, bool maskable, uint8_t flags, Error **errp); -#ifndef CONFIG_USER_ONLY SubchDev *css_find_subch(uint8_t m, uint8_t cssid, uint8_t ssid, uint16_t schid); bool css_subch_visible(SubchDev *sch); @@ -262,7 +261,6 @@ int css_enable_mss(void); IOInstEnding css_do_rsch(SubchDev *sch); int css_do_rchp(uint8_t cssid, uint8_t chpid); bool css_present(uint8_t cssid); -#endif extern const PropertyInfo css_devid_ro_propinfo; @@ -333,10 +331,4 @@ static inline int ccw_dstream_read_buf(CcwDataStream *cds, void *buff, int len) #define ccw_dstream_read(cds, v) ccw_dstream_read_buf((cds), &(v), sizeof(v)) #define ccw_dstream_write(cds, v) ccw_dstream_write_buf((cds), &(v), sizeof(v)) -/** - * true if (vmstate based) migration of the channel subsystem - * is enabled, false if it is disabled. - */ -extern bool css_migration_enabled; - #endif diff --git a/include/hw/s390x/event-facility.h b/include/hw/s390x/event-facility.h index ff874e7..eac7a51 100644 --- a/include/hw/s390x/event-facility.h +++ b/include/hw/s390x/event-facility.h @@ -25,6 +25,7 @@ #define SCLP_EVENT_MESSAGE 0x02 #define SCLP_EVENT_CONFIG_MGT_DATA 0x04 #define SCLP_EVENT_PMSGCMD 0x09 +#define SCLP_EVENT_CTRL_PGM_ID 0x0b #define SCLP_EVENT_ASCII_CONSOLE_DATA 0x1a #define SCLP_EVENT_SIGNAL_QUIESCE 0x1d @@ -35,6 +36,7 @@ #define SCLP_EVENT_MASK_MSG SCLP_EVMASK(SCLP_EVENT_MESSAGE) #define SCLP_EVENT_MASK_CONFIG_MGT_DATA SCLP_EVMASK(SCLP_EVENT_CONFIG_MGT_DATA) #define SCLP_EVENT_MASK_PMSGCMD SCLP_EVMASK(SCLP_EVENT_PMSGCMD) +#define SCLP_EVENT_MASK_CTRL_PGM_ID SCLP_EVMASK(SCLP_EVENT_CTRL_PGM_ID) #define SCLP_EVENT_MASK_MSG_ASCII SCLP_EVMASK(SCLP_EVENT_ASCII_CONSOLE_DATA) #define SCLP_EVENT_MASK_SIGNAL_QUIESCE SCLP_EVMASK(SCLP_EVENT_SIGNAL_QUIESCE) @@ -191,6 +193,21 @@ struct SCLPEventClass { bool (*can_handle_event)(uint8_t type); }; +#define TYPE_SCLP_EVENT_CPI "sclpcpi" +typedef struct SCLPEventCPIClass SCLPEventCPIClass; +typedef struct SCLPEventCPI SCLPEventCPI; +OBJECT_DECLARE_TYPE(SCLPEventCPI, SCLPEventCPIClass, + SCLP_EVENT_CPI) + +struct SCLPEventCPI { + SCLPEvent event; + uint8_t system_type[8]; + uint8_t system_name[8]; + uint64_t system_level; + uint8_t sysplex_name[8]; + uint64_t timestamp; +}; + #define TYPE_SCLP_EVENT_FACILITY "s390-sclp-event-facility" typedef struct SCLPEventFacility SCLPEventFacility; typedef struct SCLPEventFacilityClass SCLPEventFacilityClass; diff --git a/include/hw/s390x/s390-pci-kvm.h b/include/hw/s390x/s390-pci-kvm.h index 933814a..c33f283 100644 --- a/include/hw/s390x/s390-pci-kvm.h +++ b/include/hw/s390x/s390-pci-kvm.h @@ -14,12 +14,19 @@ #include "hw/s390x/s390-pci-bus.h" #include "hw/s390x/s390-pci-inst.h" +#include "system/kvm.h" #ifdef CONFIG_KVM +static inline void s390_pcihost_kvm_realize(void) +{ + kvm_msi_via_irqfd_allowed = kvm_irqfds_enabled(); +} + bool s390_pci_kvm_interp_allowed(void); int s390_pci_kvm_aif_enable(S390PCIBusDevice *pbdev, ZpciFib *fib, bool assist); int s390_pci_kvm_aif_disable(S390PCIBusDevice *pbdev); #else +static inline void s390_pcihost_kvm_realize(void) {} static inline bool s390_pci_kvm_interp_allowed(void) { return false; diff --git a/include/hw/s390x/s390-virtio-ccw.h b/include/hw/s390x/s390-virtio-ccw.h index 686d949..526078a 100644 --- a/include/hw/s390x/s390-virtio-ccw.h +++ b/include/hw/s390x/s390-virtio-ccw.h @@ -53,11 +53,8 @@ struct S390CcwMachineClass { MachineClass parent_class; /*< public >*/ - bool hpage_1m_allowed; int max_threads; + bool use_cpi; }; -/* 1M huge page mappings allowed by the machine */ -bool hpage_1m_allowed(void); - #endif diff --git a/include/hw/s390x/s390_flic.h b/include/hw/s390x/s390_flic.h index 85016d5..91edaac 100644 --- a/include/hw/s390x/s390_flic.h +++ b/include/hw/s390x/s390_flic.h @@ -42,7 +42,6 @@ OBJECT_DECLARE_TYPE(S390FLICState, S390FLICStateClass, struct S390FLICState { SysBusDevice parent_obj; bool ais_supported; - bool migration_enabled; }; diff --git a/include/hw/s390x/sclp.h b/include/hw/s390x/sclp.h index d32f618..33f01f8 100644 --- a/include/hw/s390x/sclp.h +++ b/include/hw/s390x/sclp.h @@ -197,12 +197,9 @@ OBJECT_DECLARE_TYPE(SCLPDevice, SCLPDeviceClass, struct SCLPEventFacility; struct SCLPDevice { - /* private */ DeviceState parent_obj; - struct SCLPEventFacility *event_facility; - int increment_size; - /* public */ + struct SCLPEventFacility *event_facility; }; struct SCLPDeviceClass { diff --git a/include/hw/s390x/storage-attributes.h b/include/hw/s390x/storage-attributes.h index 8921a04..b5c6d8f 100644 --- a/include/hw/s390x/storage-attributes.h +++ b/include/hw/s390x/storage-attributes.h @@ -25,7 +25,6 @@ OBJECT_DECLARE_TYPE(S390StAttribState, S390StAttribClass, S390_STATTRIB) struct S390StAttribState { DeviceState parent_obj; uint64_t migration_cur_gfn; - bool migration_enabled; }; diff --git a/include/hw/s390x/storage-keys.h b/include/hw/s390x/storage-keys.h index 408d281..ac30300 100644 --- a/include/hw/s390x/storage-keys.h +++ b/include/hw/s390x/storage-keys.h @@ -122,7 +122,23 @@ int s390_skeys_set(S390SKeysState *ks, uint64_t start_gfn, S390SKeysState *s390_get_skeys_device(void); +void s390_qmp_dump_skeys(const char *filename, Error **errp); void hmp_dump_skeys(Monitor *mon, const QDict *qdict); void hmp_info_skeys(Monitor *mon, const QDict *qdict); +#define TYPE_DUMP_SKEYS_INTERFACE "dump-skeys-interface" + +typedef struct DumpSKeysInterface DumpSKeysInterface; +DECLARE_CLASS_CHECKERS(DumpSKeysInterface, DUMP_SKEYS_INTERFACE, + TYPE_DUMP_SKEYS_INTERFACE) + +struct DumpSKeysInterface { + InterfaceClass parent_class; + + /** + * @qmp_dump_skeys: Callback to dump guest's storage keys to @filename. + */ + void (*qmp_dump_skeys)(const char *filename, Error **errp); +}; + #endif /* S390_STORAGE_KEYS_H */ diff --git a/include/hw/s390x/vfio-ccw.h b/include/hw/s390x/vfio-ccw.h index 4209d27..1e0922d 100644 --- a/include/hw/s390x/vfio-ccw.h +++ b/include/hw/s390x/vfio-ccw.h @@ -14,7 +14,7 @@ #ifndef HW_VFIO_CCW_H #define HW_VFIO_CCW_H -#include "hw/vfio/vfio-common.h" +#include "hw/vfio/vfio-device.h" #include "hw/s390x/s390-ccw.h" #include "hw/s390x/ccw-device.h" #include "qom/object.h" diff --git a/include/hw/scsi/esp.h b/include/hw/scsi/esp.h index 533d856..3526bad 100644 --- a/include/hw/scsi/esp.h +++ b/include/hw/scsi/esp.h @@ -14,7 +14,11 @@ typedef void (*ESPDMAMemoryReadWriteFunc)(void *opaque, uint8_t *buf, int len); #define ESP_FIFO_SZ 16 #define ESP_CMDFIFO_SZ 32 -typedef struct ESPState ESPState; +enum ESPASCMode { + ESP_ASC_MODE_DIS = 0, /* Disconnected */ + ESP_ASC_MODE_INI = 1, /* Initiator */ + ESP_ASC_MODE_TGT = 2 /* Target */ +}; #define TYPE_ESP "esp" OBJECT_DECLARE_SIMPLE_TYPE(ESPState, ESP) @@ -40,6 +44,7 @@ struct ESPState { uint8_t cmdfifo_cdb_offset; uint8_t lun; uint32_t do_cmd; + uint8_t asc_mode; bool data_ready; int dma_enabled; @@ -106,6 +111,13 @@ struct SysBusESPState { #define CMD_DMA 0x80 #define CMD_CMD 0x7f +#define CMD_GRP_MASK 0x70 + +#define CMD_GRP_MISC 0x00 +#define CMD_GRP_INIT 0x01 +#define CMD_GRP_TRGT 0x02 +#define CMD_GRP_DISC 0x04 + #define CMD_NOP 0x00 #define CMD_FLUSH 0x01 #define CMD_RESET 0x02 @@ -140,6 +152,7 @@ struct SysBusESPState { #define INTR_FC 0x08 #define INTR_BS 0x10 #define INTR_DC 0x20 +#define INTR_IL 0x40 #define INTR_RST 0x80 #define SEQ_0 0x0 diff --git a/include/hw/scsi/scsi.h b/include/hw/scsi/scsi.h index 90ee192..044bd04 100644 --- a/include/hw/scsi/scsi.h +++ b/include/hw/scsi/scsi.h @@ -10,7 +10,9 @@ #define MAX_SCSI_DEVS 255 -typedef struct SCSIBus SCSIBus; +#define TYPE_SCSI_BUS "SCSI" +OBJECT_DECLARE_SIMPLE_TYPE(SCSIBus, SCSI_BUS) + typedef struct SCSIBusInfo SCSIBusInfo; typedef struct SCSIDevice SCSIDevice; typedef struct SCSIRequest SCSIRequest; @@ -151,9 +153,6 @@ struct SCSIBusInfo { void (*drained_end)(SCSIBus *bus); }; -#define TYPE_SCSI_BUS "SCSI" -OBJECT_DECLARE_SIMPLE_TYPE(SCSIBus, SCSI_BUS) - struct SCSIBus { BusState qbus; int busnr; diff --git a/include/hw/sd/sd.h b/include/hw/sd/sd.h index d6bad17..91b5c40 100644 --- a/include/hw/sd/sd.h +++ b/include/hw/sd/sd.h @@ -56,7 +56,6 @@ #define AKE_SEQ_ERROR (1 << 3) enum SDPhySpecificationVersion { - SD_PHY_SPECv1_10_VERS = 1, SD_PHY_SPECv2_00_VERS = 2, SD_PHY_SPECv3_01_VERS = 3, }; @@ -96,7 +95,17 @@ struct SDCardClass { DeviceClass parent_class; /*< public >*/ - int (*do_command)(SDState *sd, SDRequest *req, uint8_t *response); + /** + * Process a SD command request. + * @sd: card + * @req: command request + * @resp: buffer to receive the command response + * @respsz: size of @resp buffer + * + * Return: size of the response + */ + size_t (*do_command)(SDState *sd, SDRequest *req, + uint8_t *resp, size_t respsz); /** * Write a byte to a SD card. * @sd: card @@ -153,7 +162,16 @@ struct SDBusClass { void sdbus_set_voltage(SDBus *sdbus, uint16_t millivolts); uint8_t sdbus_get_dat_lines(SDBus *sdbus); bool sdbus_get_cmd_line(SDBus *sdbus); -int sdbus_do_command(SDBus *sd, SDRequest *req, uint8_t *response); +/** + * sdbus_do_command: Process a SD command request + * @sd: card + * @req: command request + * @resp: buffer to receive the command response + * @respsz: size of @resp buffer + * + * Return: size of the response + */ +size_t sdbus_do_command(SDBus *sd, SDRequest *req, uint8_t *resp, size_t respsz); /** * Write a byte to a SD bus. * @sd: bus diff --git a/include/hw/sh4/sh_intc.h b/include/hw/sh4/sh_intc.h index f62d5c5..94f1831 100644 --- a/include/hw/sh4/sh_intc.h +++ b/include/hw/sh4/sh_intc.h @@ -1,7 +1,7 @@ #ifndef SH_INTC_H #define SH_INTC_H -#include "exec/memory.h" +#include "system/memory.h" typedef unsigned char intc_enum; diff --git a/include/hw/southbridge/ich9.h b/include/hw/southbridge/ich9.h index 6c60017..2c35dd0 100644 --- a/include/hw/southbridge/ich9.h +++ b/include/hw/southbridge/ich9.h @@ -7,7 +7,7 @@ #include "hw/pci/pci.h" #include "hw/pci/pci_device.h" #include "hw/rtc/mc146818rtc.h" -#include "exec/memory.h" +#include "system/memory.h" #include "qemu/notify.h" #include "qom/object.h" @@ -95,7 +95,7 @@ struct ICH9LPCState { #define ICH9_CC_OIC 0x31FF #define ICH9_CC_OIC_AEN 0x1 #define ICH9_CC_GCS 0x3410 -#define ICH9_CC_GCS_DEFAULT 0x00000020 +#define ICH9_CC_GCS_DEFAULT 0x00000000 #define ICH9_CC_GCS_NO_REBOOT (1 << 5) /* D28:F[0-5] */ diff --git a/include/hw/ssi/ssi.h b/include/hw/ssi/ssi.h index 3cdcbd5..2ad8033 100644 --- a/include/hw/ssi/ssi.h +++ b/include/hw/ssi/ssi.h @@ -38,6 +38,7 @@ struct SSIPeripheralClass { /* if you have standard or no CS behaviour, just override transfer. * This is called when the device cs is active (true by default). + * See ssi_transfer(). */ uint32_t (*transfer)(SSIPeripheral *dev, uint32_t val); /* called when the CS line changes. Optional, devices only need to implement @@ -52,6 +53,7 @@ struct SSIPeripheralClass { * of the CS behaviour at the device level. transfer, set_cs, and * cs_polarity are unused if this is overwritten. Transfer_raw will * always be called for the device for every txrx access to the parent bus + * See ssi_transfer(). */ uint32_t (*transfer_raw)(SSIPeripheral *dev, uint32_t val); }; @@ -110,6 +112,18 @@ bool ssi_realize_and_unref(DeviceState *dev, SSIBus *bus, Error **errp); /* Master interface. */ SSIBus *ssi_create_bus(DeviceState *parent, const char *name); +/** + * Transfer a word on a SSI bus + * @bus: SSI bus + * @val: word to transmit + * + * At the same time, read a word and write the @val one on the SSI bus. + * + * SSI words might vary between 8 and 32 bits. The same number of bits + * written is received. + * + * Return: word value received + */ uint32_t ssi_transfer(SSIBus *bus, uint32_t val); DeviceState *ssi_get_cs(SSIBus *bus, uint8_t cs_index); diff --git a/include/hw/sysbus.h b/include/hw/sysbus.h index 81bbda1..69eb62e 100644 --- a/include/hw/sysbus.h +++ b/include/hw/sysbus.h @@ -4,7 +4,7 @@ /* Devices attached directly to the main system bus. */ #include "hw/qdev-core.h" -#include "exec/memory.h" +#include "system/memory.h" #include "qom/object.h" #define QDEV_MAX_MMIO 32 @@ -70,18 +70,19 @@ struct SysBusDevice { typedef void FindSysbusDeviceFunc(SysBusDevice *sbdev, void *opaque); void sysbus_init_mmio(SysBusDevice *dev, MemoryRegion *memory); -MemoryRegion *sysbus_mmio_get_region(SysBusDevice *dev, int n); +MemoryRegion *sysbus_mmio_get_region(const SysBusDevice *dev, int n); void sysbus_init_irq(SysBusDevice *dev, qemu_irq *p); void sysbus_pass_irq(SysBusDevice *dev, SysBusDevice *target); void sysbus_init_ioports(SysBusDevice *dev, uint32_t ioport, uint32_t size); -bool sysbus_has_irq(SysBusDevice *dev, int n); -bool sysbus_has_mmio(SysBusDevice *dev, unsigned int n); +bool sysbus_has_irq(const SysBusDevice *dev, int n); +bool sysbus_has_mmio(const SysBusDevice *dev, unsigned int n); void sysbus_connect_irq(SysBusDevice *dev, int n, qemu_irq irq); -bool sysbus_is_irq_connected(SysBusDevice *dev, int n); -qemu_irq sysbus_get_connected_irq(SysBusDevice *dev, int n); +bool sysbus_is_irq_connected(const SysBusDevice *dev, int n); +qemu_irq sysbus_get_connected_irq(const SysBusDevice *dev, int n); void sysbus_mmio_map(SysBusDevice *dev, int n, hwaddr addr); +int sysbus_mmio_map_name(SysBusDevice *dev, const char*name, hwaddr addr); void sysbus_mmio_map_overlap(SysBusDevice *dev, int n, hwaddr addr, int priority); diff --git a/include/hw/timer/aspeed_timer.h b/include/hw/timer/aspeed_timer.h index 767cae4..a850625 100644 --- a/include/hw/timer/aspeed_timer.h +++ b/include/hw/timer/aspeed_timer.h @@ -16,8 +16,7 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + * with this program; if not, see <https://www.gnu.org/licenses/>. */ #ifndef ASPEED_TIMER_H #define ASPEED_TIMER_H diff --git a/include/hw/timer/i8254.h b/include/hw/timer/i8254.h index 8402caa..f7148d9 100644 --- a/include/hw/timer/i8254.h +++ b/include/hw/timer/i8254.h @@ -75,7 +75,7 @@ static inline ISADevice *kvm_pit_init(ISABus *bus, int base) return d; } -void pit_set_gate(ISADevice *dev, int channel, int val); -void pit_get_channel_info(ISADevice *dev, int channel, PITChannelInfo *info); +void pit_set_gate(PITCommonState *pit, int channel, int val); +void pit_get_channel_info(PITCommonState *pit, int channel, PITChannelInfo *info); #endif /* HW_I8254_H */ diff --git a/include/hw/timer/npcm7xx_timer.h b/include/hw/timer/npcm7xx_timer.h index d45c051..e287375 100644 --- a/include/hw/timer/npcm7xx_timer.h +++ b/include/hw/timer/npcm7xx_timer.h @@ -16,7 +16,7 @@ #ifndef NPCM7XX_TIMER_H #define NPCM7XX_TIMER_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/sysbus.h" #include "qemu/timer.h" diff --git a/include/hw/tricore/triboard.h b/include/hw/tricore/triboard.h index 8250470..ca49a0c 100644 --- a/include/hw/tricore/triboard.h +++ b/include/hw/tricore/triboard.h @@ -21,7 +21,7 @@ #include "qapi/error.h" #include "hw/boards.h" #include "system/system.h" -#include "exec/address-spaces.h" +#include "system/address-spaces.h" #include "qom/object.h" #include "hw/tricore/tc27x_soc.h" diff --git a/include/hw/tricore/tricore.h b/include/hw/tricore/tricore.h index c19ed3f..4ffc0fe 100644 --- a/include/hw/tricore/tricore.h +++ b/include/hw/tricore/tricore.h @@ -1,7 +1,7 @@ #ifndef HW_TRICORE_H #define HW_TRICORE_H -#include "exec/memory.h" +#include "system/memory.h" struct tricore_boot_info { uint64_t ram_size; diff --git a/include/hw/uefi/var-service.h b/include/hw/uefi/var-service.h index f7ceac4..91fb4a2 100644 --- a/include/hw/uefi/var-service.h +++ b/include/hw/uefi/var-service.h @@ -9,6 +9,7 @@ #include "qemu/uuid.h" #include "qemu/queue.h" +#include "system/memory.h" #include "hw/uefi/var-service-edk2.h" #define MAX_BUFFER_SIZE (64 * 1024) diff --git a/include/hw/usb.h b/include/hw/usb.h index e410693..26a9f3e 100644 --- a/include/hw/usb.h +++ b/include/hw/usb.h @@ -25,7 +25,7 @@ * THE SOFTWARE. */ -#include "exec/memory.h" +#include "system/memory.h" #include "hw/qdev-core.h" #include "qemu/iov.h" #include "qemu/queue.h" diff --git a/include/hw/vfio/vfio-amd-xgbe.h b/include/hw/vfio/vfio-amd-xgbe.h deleted file mode 100644 index a894546..0000000 --- a/include/hw/vfio/vfio-amd-xgbe.h +++ /dev/null @@ -1,46 +0,0 @@ -/* - * VFIO AMD XGBE device - * - * Copyright Linaro Limited, 2015 - * - * Authors: - * Eric Auger <eric.auger@linaro.org> - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. - * - */ - -#ifndef HW_VFIO_VFIO_AMD_XGBE_H -#define HW_VFIO_VFIO_AMD_XGBE_H - -#include "hw/vfio/vfio-platform.h" -#include "qom/object.h" - -#define TYPE_VFIO_AMD_XGBE "vfio-amd-xgbe" - -/** - * This device exposes: - * - 5 MMIO regions: MAC, PCS, SerDes Rx/Tx regs, - SerDes Integration Registers 1/2 & 2/2 - * - 2 level sensitive IRQs and optional DMA channel IRQs - */ -struct VFIOAmdXgbeDevice { - VFIOPlatformDevice vdev; -}; - -typedef struct VFIOAmdXgbeDevice VFIOAmdXgbeDevice; - -struct VFIOAmdXgbeDeviceClass { - /*< private >*/ - VFIOPlatformDeviceClass parent_class; - /*< public >*/ - DeviceRealize parent_realize; -}; - -typedef struct VFIOAmdXgbeDeviceClass VFIOAmdXgbeDeviceClass; - -DECLARE_OBJ_CHECKERS(VFIOAmdXgbeDevice, VFIOAmdXgbeDeviceClass, - VFIO_AMD_XGBE_DEVICE, TYPE_VFIO_AMD_XGBE) - -#endif diff --git a/include/hw/vfio/vfio-calxeda-xgmac.h b/include/hw/vfio/vfio-calxeda-xgmac.h deleted file mode 100644 index 8482f15..0000000 --- a/include/hw/vfio/vfio-calxeda-xgmac.h +++ /dev/null @@ -1,43 +0,0 @@ -/* - * VFIO calxeda xgmac device - * - * Copyright Linaro Limited, 2014 - * - * Authors: - * Eric Auger <eric.auger@linaro.org> - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. - * - */ - -#ifndef HW_VFIO_VFIO_CALXEDA_XGMAC_H -#define HW_VFIO_VFIO_CALXEDA_XGMAC_H - -#include "hw/vfio/vfio-platform.h" -#include "qom/object.h" - -#define TYPE_VFIO_CALXEDA_XGMAC "vfio-calxeda-xgmac" - -/** - * This device exposes: - * - a single MMIO region corresponding to its register space - * - 3 IRQS (main and 2 power related IRQs) - */ -struct VFIOCalxedaXgmacDevice { - VFIOPlatformDevice vdev; -}; -typedef struct VFIOCalxedaXgmacDevice VFIOCalxedaXgmacDevice; - -struct VFIOCalxedaXgmacDeviceClass { - /*< private >*/ - VFIOPlatformDeviceClass parent_class; - /*< public >*/ - DeviceRealize parent_realize; -}; -typedef struct VFIOCalxedaXgmacDeviceClass VFIOCalxedaXgmacDeviceClass; - -DECLARE_OBJ_CHECKERS(VFIOCalxedaXgmacDevice, VFIOCalxedaXgmacDeviceClass, - VFIO_CALXEDA_XGMAC_DEVICE, TYPE_VFIO_CALXEDA_XGMAC) - -#endif diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h deleted file mode 100644 index 04b123a..0000000 --- a/include/hw/vfio/vfio-common.h +++ /dev/null @@ -1,346 +0,0 @@ -/* - * common header for vfio based device assignment support - * - * Copyright Red Hat, Inc. 2012 - * - * Authors: - * Alex Williamson <alex.williamson@redhat.com> - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. - * - * Based on qemu-kvm device-assignment: - * Adapted for KVM by Qumranet. - * Copyright (c) 2007, Neocleus, Alex Novik (alex@neocleus.com) - * Copyright (c) 2007, Neocleus, Guy Zana (guy@neocleus.com) - * Copyright (C) 2008, Qumranet, Amit Shah (amit.shah@qumranet.com) - * Copyright (C) 2008, Red Hat, Amit Shah (amit.shah@redhat.com) - * Copyright (C) 2008, IBM, Muli Ben-Yehuda (muli@il.ibm.com) - */ - -#ifndef HW_VFIO_VFIO_COMMON_H -#define HW_VFIO_VFIO_COMMON_H - -#include "exec/memory.h" -#include "qemu/queue.h" -#include "qemu/notify.h" -#include "ui/console.h" -#include "hw/display/ramfb.h" -#ifdef CONFIG_LINUX -#include <linux/vfio.h> -#endif -#include "system/system.h" -#include "hw/vfio/vfio-container-base.h" -#include "system/host_iommu_device.h" -#include "system/iommufd.h" - -#define VFIO_MSG_PREFIX "vfio %s: " - -/* - * Flags to be used as unique delimiters for VFIO devices in the migration - * stream. These flags are composed as: - * 0xffffffff => MSB 32-bit all 1s - * 0xef10 => Magic ID, represents emulated (virtual) function IO - * 0x0000 => 16-bits reserved for flags - * - * The beginning of state information is marked by _DEV_CONFIG_STATE, - * _DEV_SETUP_STATE, or _DEV_DATA_STATE, respectively. The end of a - * certain state information is marked by _END_OF_STATE. - */ -#define VFIO_MIG_FLAG_END_OF_STATE (0xffffffffef100001ULL) -#define VFIO_MIG_FLAG_DEV_CONFIG_STATE (0xffffffffef100002ULL) -#define VFIO_MIG_FLAG_DEV_SETUP_STATE (0xffffffffef100003ULL) -#define VFIO_MIG_FLAG_DEV_DATA_STATE (0xffffffffef100004ULL) -#define VFIO_MIG_FLAG_DEV_INIT_DATA_SENT (0xffffffffef100005ULL) - -enum { - VFIO_DEVICE_TYPE_PCI = 0, - VFIO_DEVICE_TYPE_PLATFORM = 1, - VFIO_DEVICE_TYPE_CCW = 2, - VFIO_DEVICE_TYPE_AP = 3, -}; - -typedef struct VFIOMmap { - MemoryRegion mem; - void *mmap; - off_t offset; - size_t size; -} VFIOMmap; - -typedef struct VFIORegion { - struct VFIODevice *vbasedev; - off_t fd_offset; /* offset of region within device fd */ - MemoryRegion *mem; /* slow, read/write access */ - size_t size; - uint32_t flags; /* VFIO region flags (rd/wr/mmap) */ - uint32_t nr_mmaps; - VFIOMmap *mmaps; - uint8_t nr; /* cache the region number for debug */ -} VFIORegion; - -typedef struct VFIOMultifd VFIOMultifd; - -typedef struct VFIOMigration { - struct VFIODevice *vbasedev; - VMChangeStateEntry *vm_state; - NotifierWithReturn migration_state; - uint32_t device_state; - int data_fd; - void *data_buffer; - size_t data_buffer_size; - uint64_t mig_flags; - uint64_t precopy_init_size; - uint64_t precopy_dirty_size; - bool multifd_transfer; - VFIOMultifd *multifd; - bool initial_data_sent; - - bool event_save_iterate_started; - bool event_precopy_empty_hit; -} VFIOMigration; - -struct VFIOGroup; - -typedef struct VFIOContainer { - VFIOContainerBase bcontainer; - int fd; /* /dev/vfio/vfio, empowered by the attached groups */ - unsigned iommu_type; - QLIST_HEAD(, VFIOGroup) group_list; -} VFIOContainer; - -OBJECT_DECLARE_SIMPLE_TYPE(VFIOContainer, VFIO_IOMMU_LEGACY); - -typedef struct VFIOHostDMAWindow { - hwaddr min_iova; - hwaddr max_iova; - uint64_t iova_pgsizes; - QLIST_ENTRY(VFIOHostDMAWindow) hostwin_next; -} VFIOHostDMAWindow; - -typedef struct IOMMUFDBackend IOMMUFDBackend; - -typedef struct VFIOIOASHwpt { - uint32_t hwpt_id; - uint32_t hwpt_flags; - QLIST_HEAD(, VFIODevice) device_list; - QLIST_ENTRY(VFIOIOASHwpt) next; -} VFIOIOASHwpt; - -typedef struct VFIOIOMMUFDContainer { - VFIOContainerBase bcontainer; - IOMMUFDBackend *be; - uint32_t ioas_id; - QLIST_HEAD(, VFIOIOASHwpt) hwpt_list; -} VFIOIOMMUFDContainer; - -OBJECT_DECLARE_SIMPLE_TYPE(VFIOIOMMUFDContainer, VFIO_IOMMU_IOMMUFD); - -typedef struct VFIODeviceOps VFIODeviceOps; - -typedef struct VFIODevice { - QLIST_ENTRY(VFIODevice) next; - QLIST_ENTRY(VFIODevice) container_next; - QLIST_ENTRY(VFIODevice) global_next; - struct VFIOGroup *group; - VFIOContainerBase *bcontainer; - char *sysfsdev; - char *name; - DeviceState *dev; - int fd; - int type; - bool mdev; - bool reset_works; - bool needs_reset; - bool no_mmap; - bool ram_block_discard_allowed; - OnOffAuto enable_migration; - OnOffAuto migration_multifd_transfer; - bool migration_events; - VFIODeviceOps *ops; - unsigned int num_irqs; - unsigned int num_regions; - unsigned int flags; - VFIOMigration *migration; - Error *migration_blocker; - OnOffAuto pre_copy_dirty_page_tracking; - OnOffAuto device_dirty_page_tracking; - bool dirty_pages_supported; - bool dirty_tracking; /* Protected by BQL */ - bool iommu_dirty_tracking; - HostIOMMUDevice *hiod; - int devid; - IOMMUFDBackend *iommufd; - VFIOIOASHwpt *hwpt; - QLIST_ENTRY(VFIODevice) hwpt_next; -} VFIODevice; - -struct VFIODeviceOps { - void (*vfio_compute_needs_reset)(VFIODevice *vdev); - int (*vfio_hot_reset_multi)(VFIODevice *vdev); - void (*vfio_eoi)(VFIODevice *vdev); - Object *(*vfio_get_object)(VFIODevice *vdev); - - /** - * @vfio_save_config - * - * Save device config state - * - * @vdev: #VFIODevice for which to save the config - * @f: #QEMUFile where to send the data - * @errp: pointer to Error*, to store an error if it happens. - * - * Returns zero to indicate success and negative for error - */ - int (*vfio_save_config)(VFIODevice *vdev, QEMUFile *f, Error **errp); - - /** - * @vfio_load_config - * - * Load device config state - * - * @vdev: #VFIODevice for which to load the config - * @f: #QEMUFile where to get the data - * - * Returns zero to indicate success and negative for error - */ - int (*vfio_load_config)(VFIODevice *vdev, QEMUFile *f); -}; - -typedef struct VFIOGroup { - int fd; - int groupid; - VFIOContainer *container; - QLIST_HEAD(, VFIODevice) device_list; - QLIST_ENTRY(VFIOGroup) next; - QLIST_ENTRY(VFIOGroup) container_next; - bool ram_block_discard_allowed; -} VFIOGroup; - -#define TYPE_HOST_IOMMU_DEVICE_LEGACY_VFIO TYPE_HOST_IOMMU_DEVICE "-legacy-vfio" -#define TYPE_HOST_IOMMU_DEVICE_IOMMUFD_VFIO \ - TYPE_HOST_IOMMU_DEVICE_IOMMUFD "-vfio" - -typedef struct VFIODMABuf { - QemuDmaBuf *buf; - uint32_t pos_x, pos_y, pos_updates; - uint32_t hot_x, hot_y, hot_updates; - int dmabuf_id; - QTAILQ_ENTRY(VFIODMABuf) next; -} VFIODMABuf; - -typedef struct VFIODisplay { - QemuConsole *con; - RAMFBState *ramfb; - struct vfio_region_info *edid_info; - struct vfio_region_gfx_edid *edid_regs; - uint8_t *edid_blob; - QEMUTimer *edid_link_timer; - struct { - VFIORegion buffer; - DisplaySurface *surface; - } region; - struct { - QTAILQ_HEAD(, VFIODMABuf) bufs; - VFIODMABuf *primary; - VFIODMABuf *cursor; - } dmabuf; -} VFIODisplay; - -VFIOAddressSpace *vfio_get_address_space(AddressSpace *as); -void vfio_put_address_space(VFIOAddressSpace *space); -void vfio_address_space_insert(VFIOAddressSpace *space, - VFIOContainerBase *bcontainer); - -void vfio_disable_irqindex(VFIODevice *vbasedev, int index); -void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index); -void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index); -bool vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex, - int action, int fd, Error **errp); -void vfio_region_write(void *opaque, hwaddr addr, - uint64_t data, unsigned size); -uint64_t vfio_region_read(void *opaque, - hwaddr addr, unsigned size); -int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region, - int index, const char *name); -int vfio_region_mmap(VFIORegion *region); -void vfio_region_mmaps_set_enabled(VFIORegion *region, bool enabled); -void vfio_region_unmap(VFIORegion *region); -void vfio_region_exit(VFIORegion *region); -void vfio_region_finalize(VFIORegion *region); -void vfio_reset_handler(void *opaque); -struct vfio_device_info *vfio_get_device_info(int fd); -bool vfio_device_is_mdev(VFIODevice *vbasedev); -bool vfio_device_hiod_realize(VFIODevice *vbasedev, Error **errp); -bool vfio_attach_device(char *name, VFIODevice *vbasedev, - AddressSpace *as, Error **errp); -void vfio_detach_device(VFIODevice *vbasedev); -VFIODevice *vfio_get_vfio_device(Object *obj); - -int vfio_kvm_device_add_fd(int fd, Error **errp); -int vfio_kvm_device_del_fd(int fd, Error **errp); - -bool vfio_cpr_register_container(VFIOContainerBase *bcontainer, Error **errp); -void vfio_cpr_unregister_container(VFIOContainerBase *bcontainer); - -extern const MemoryRegionOps vfio_region_ops; -typedef QLIST_HEAD(VFIOGroupList, VFIOGroup) VFIOGroupList; -typedef QLIST_HEAD(VFIODeviceList, VFIODevice) VFIODeviceList; -extern VFIOGroupList vfio_group_list; -extern VFIODeviceList vfio_device_list; -extern const MemoryListener vfio_memory_listener; -extern int vfio_kvm_device_fd; - -bool vfio_mig_active(void); -int vfio_block_multiple_devices_migration(VFIODevice *vbasedev, Error **errp); -void vfio_unblock_multiple_devices_migration(void); -bool vfio_viommu_preset(VFIODevice *vbasedev); -int64_t vfio_mig_bytes_transferred(void); -void vfio_reset_bytes_transferred(void); -void vfio_mig_add_bytes_transferred(unsigned long val); -bool vfio_device_state_is_running(VFIODevice *vbasedev); -bool vfio_device_state_is_precopy(VFIODevice *vbasedev); - -int vfio_save_device_config_state(QEMUFile *f, void *opaque, Error **errp); -int vfio_load_device_config_state(QEMUFile *f, void *opaque); - -#ifdef CONFIG_LINUX -int vfio_get_region_info(VFIODevice *vbasedev, int index, - struct vfio_region_info **info); -int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type, - uint32_t subtype, struct vfio_region_info **info); -bool vfio_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type); -struct vfio_info_cap_header * -vfio_get_region_info_cap(struct vfio_region_info *info, uint16_t id); -bool vfio_get_info_dma_avail(struct vfio_iommu_type1_info *info, - unsigned int *avail); -struct vfio_info_cap_header * -vfio_get_device_info_cap(struct vfio_device_info *info, uint16_t id); -struct vfio_info_cap_header * -vfio_get_cap(void *ptr, uint32_t cap_offset, uint16_t id); - -int vfio_migration_set_state(VFIODevice *vbasedev, - enum vfio_device_mig_state new_state, - enum vfio_device_mig_state recover_state, - Error **errp); -#endif - -bool vfio_migration_realize(VFIODevice *vbasedev, Error **errp); -void vfio_migration_exit(VFIODevice *vbasedev); - -int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size); -bool vfio_devices_all_dirty_tracking_started( - const VFIOContainerBase *bcontainer); -bool -vfio_devices_all_device_dirty_tracking(const VFIOContainerBase *bcontainer); -int vfio_devices_query_dirty_bitmap(const VFIOContainerBase *bcontainer, - VFIOBitmap *vbmap, hwaddr iova, hwaddr size, Error **errp); -int vfio_get_dirty_bitmap(const VFIOContainerBase *bcontainer, uint64_t iova, - uint64_t size, ram_addr_t ram_addr, Error **errp); - -/* Returns 0 on success, or a negative errno. */ -bool vfio_device_get_name(VFIODevice *vbasedev, Error **errp); -void vfio_device_set_fd(VFIODevice *vbasedev, const char *str, Error **errp); -void vfio_device_init(VFIODevice *vbasedev, int type, VFIODeviceOps *ops, - DeviceState *dev, bool ram_discard); -int vfio_device_get_aw_bits(VFIODevice *vdev); -#endif /* HW_VFIO_VFIO_COMMON_H */ diff --git a/include/hw/vfio/vfio-container-base.h b/include/hw/vfio/vfio-container-base.h deleted file mode 100644 index 4cff994..0000000 --- a/include/hw/vfio/vfio-container-base.h +++ /dev/null @@ -1,166 +0,0 @@ -/* - * VFIO BASE CONTAINER - * - * Copyright (C) 2023 Intel Corporation. - * Copyright Red Hat, Inc. 2023 - * - * Authors: Yi Liu <yi.l.liu@intel.com> - * Eric Auger <eric.auger@redhat.com> - * - * SPDX-License-Identifier: GPL-2.0-or-later - */ - -#ifndef HW_VFIO_VFIO_CONTAINER_BASE_H -#define HW_VFIO_VFIO_CONTAINER_BASE_H - -#include "exec/memory.h" - -typedef struct VFIODevice VFIODevice; -typedef struct VFIOIOMMUClass VFIOIOMMUClass; - -typedef struct { - unsigned long *bitmap; - hwaddr size; - hwaddr pages; -} VFIOBitmap; - -typedef struct VFIOAddressSpace { - AddressSpace *as; - QLIST_HEAD(, VFIOContainerBase) containers; - QLIST_ENTRY(VFIOAddressSpace) list; -} VFIOAddressSpace; - -/* - * This is the base object for vfio container backends - */ -typedef struct VFIOContainerBase { - Object parent; - VFIOAddressSpace *space; - MemoryListener listener; - Error *error; - bool initialized; - uint64_t dirty_pgsizes; - uint64_t max_dirty_bitmap_size; - unsigned long pgsizes; - unsigned int dma_max_mappings; - bool dirty_pages_supported; - bool dirty_pages_started; /* Protected by BQL */ - QLIST_HEAD(, VFIOGuestIOMMU) giommu_list; - QLIST_HEAD(, VFIORamDiscardListener) vrdl_list; - QLIST_ENTRY(VFIOContainerBase) next; - QLIST_HEAD(, VFIODevice) device_list; - GList *iova_ranges; - NotifierWithReturn cpr_reboot_notifier; -} VFIOContainerBase; - -typedef struct VFIOGuestIOMMU { - VFIOContainerBase *bcontainer; - IOMMUMemoryRegion *iommu_mr; - hwaddr iommu_offset; - IOMMUNotifier n; - QLIST_ENTRY(VFIOGuestIOMMU) giommu_next; -} VFIOGuestIOMMU; - -typedef struct VFIORamDiscardListener { - VFIOContainerBase *bcontainer; - MemoryRegion *mr; - hwaddr offset_within_address_space; - hwaddr size; - uint64_t granularity; - RamDiscardListener listener; - QLIST_ENTRY(VFIORamDiscardListener) next; -} VFIORamDiscardListener; - -int vfio_container_dma_map(VFIOContainerBase *bcontainer, - hwaddr iova, ram_addr_t size, - void *vaddr, bool readonly); -int vfio_container_dma_unmap(VFIOContainerBase *bcontainer, - hwaddr iova, ram_addr_t size, - IOMMUTLBEntry *iotlb); -bool vfio_container_add_section_window(VFIOContainerBase *bcontainer, - MemoryRegionSection *section, - Error **errp); -void vfio_container_del_section_window(VFIOContainerBase *bcontainer, - MemoryRegionSection *section); -int vfio_container_set_dirty_page_tracking(VFIOContainerBase *bcontainer, - bool start, Error **errp); -int vfio_container_query_dirty_bitmap(const VFIOContainerBase *bcontainer, - VFIOBitmap *vbmap, hwaddr iova, hwaddr size, Error **errp); - -GList *vfio_container_get_iova_ranges(const VFIOContainerBase *bcontainer); - -static inline uint64_t -vfio_container_get_page_size_mask(const VFIOContainerBase *bcontainer) -{ - assert(bcontainer); - return bcontainer->pgsizes; -} - -#define TYPE_VFIO_IOMMU "vfio-iommu" -#define TYPE_VFIO_IOMMU_LEGACY TYPE_VFIO_IOMMU "-legacy" -#define TYPE_VFIO_IOMMU_SPAPR TYPE_VFIO_IOMMU "-spapr" -#define TYPE_VFIO_IOMMU_IOMMUFD TYPE_VFIO_IOMMU "-iommufd" - -OBJECT_DECLARE_TYPE(VFIOContainerBase, VFIOIOMMUClass, VFIO_IOMMU) - -struct VFIOIOMMUClass { - ObjectClass parent_class; - - /* Properties */ - const char *hiod_typename; - - /* basic feature */ - bool (*setup)(VFIOContainerBase *bcontainer, Error **errp); - int (*dma_map)(const VFIOContainerBase *bcontainer, - hwaddr iova, ram_addr_t size, - void *vaddr, bool readonly); - int (*dma_unmap)(const VFIOContainerBase *bcontainer, - hwaddr iova, ram_addr_t size, - IOMMUTLBEntry *iotlb); - bool (*attach_device)(const char *name, VFIODevice *vbasedev, - AddressSpace *as, Error **errp); - void (*detach_device)(VFIODevice *vbasedev); - - /* migration feature */ - - /** - * @set_dirty_page_tracking - * - * Start or stop dirty pages tracking on VFIO container - * - * @bcontainer: #VFIOContainerBase on which to de/activate dirty - * page tracking - * @start: indicates whether to start or stop dirty pages tracking - * @errp: pointer to Error*, to store an error if it happens. - * - * Returns zero to indicate success and negative for error - */ - int (*set_dirty_page_tracking)(const VFIOContainerBase *bcontainer, - bool start, Error **errp); - /** - * @query_dirty_bitmap - * - * Get bitmap of dirty pages from container - * - * @bcontainer: #VFIOContainerBase from which to get dirty pages - * @vbmap: #VFIOBitmap internal bitmap structure - * @iova: iova base address - * @size: size of iova range - * @errp: pointer to Error*, to store an error if it happens. - * - * Returns zero to indicate success and negative for error - */ - int (*query_dirty_bitmap)(const VFIOContainerBase *bcontainer, - VFIOBitmap *vbmap, hwaddr iova, hwaddr size, Error **errp); - /* PCI specific */ - int (*pci_hot_reset)(VFIODevice *vbasedev, bool single); - - /* SPAPR specific */ - bool (*add_window)(VFIOContainerBase *bcontainer, - MemoryRegionSection *section, - Error **errp); - void (*del_window)(VFIOContainerBase *bcontainer, - MemoryRegionSection *section); - void (*release)(VFIOContainerBase *bcontainer); -}; -#endif /* HW_VFIO_VFIO_CONTAINER_BASE_H */ diff --git a/include/hw/vfio/vfio-container-legacy.h b/include/hw/vfio/vfio-container-legacy.h new file mode 100644 index 0000000..fe82212 --- /dev/null +++ b/include/hw/vfio/vfio-container-legacy.h @@ -0,0 +1,39 @@ +/* + * VFIO container + * + * Copyright Red Hat, Inc. 2025 + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_VFIO_CONTAINER_LEGACY_H +#define HW_VFIO_CONTAINER_LEGACY_H + +#include "hw/vfio/vfio-container.h" +#include "hw/vfio/vfio-cpr.h" + +OBJECT_DECLARE_SIMPLE_TYPE(VFIOLegacyContainer, VFIO_IOMMU_LEGACY); + +typedef struct VFIODevice VFIODevice; + +typedef struct VFIOGroup { + int fd; + int groupid; + VFIOLegacyContainer *container; + QLIST_HEAD(, VFIODevice) device_list; + QLIST_ENTRY(VFIOGroup) next; + QLIST_ENTRY(VFIOGroup) container_next; + bool ram_block_discard_allowed; +} VFIOGroup; + +struct VFIOLegacyContainer { + VFIOContainer parent_obj; + + int fd; /* /dev/vfio/vfio, empowered by the attached groups */ + unsigned iommu_type; + bool unmap_all_supported; + QLIST_HEAD(, VFIOGroup) group_list; + VFIOContainerCPR cpr; +}; + +#endif /* HW_VFIO_CONTAINER_LEGACY_H */ diff --git a/include/hw/vfio/vfio-container.h b/include/hw/vfio/vfio-container.h new file mode 100644 index 0000000..c4b58d6 --- /dev/null +++ b/include/hw/vfio/vfio-container.h @@ -0,0 +1,280 @@ +/* + * VFIO BASE CONTAINER + * + * Copyright (C) 2023 Intel Corporation. + * Copyright Red Hat, Inc. 2023 + * + * Authors: Yi Liu <yi.l.liu@intel.com> + * Eric Auger <eric.auger@redhat.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_VFIO_VFIO_CONTAINER_H +#define HW_VFIO_VFIO_CONTAINER_H + +#include "system/memory.h" + +typedef struct VFIODevice VFIODevice; +typedef struct VFIOIOMMUClass VFIOIOMMUClass; + +typedef struct { + unsigned long *bitmap; + hwaddr size; + hwaddr pages; +} VFIOBitmap; + +typedef struct VFIOAddressSpace { + AddressSpace *as; + QLIST_HEAD(, VFIOContainer) containers; + QLIST_ENTRY(VFIOAddressSpace) list; +} VFIOAddressSpace; + +/* + * This is the base object for vfio container backends + */ +struct VFIOContainer { + Object parent_obj; + + VFIOAddressSpace *space; + MemoryListener listener; + Error *error; + bool initialized; + uint64_t dirty_pgsizes; + uint64_t max_dirty_bitmap_size; + unsigned long pgsizes; + unsigned int dma_max_mappings; + bool dirty_pages_supported; + bool dirty_pages_started; /* Protected by BQL */ + QLIST_HEAD(, VFIOGuestIOMMU) giommu_list; + QLIST_HEAD(, VFIORamDiscardListener) vrdl_list; + QLIST_ENTRY(VFIOContainer) next; + QLIST_HEAD(, VFIODevice) device_list; + GList *iova_ranges; + NotifierWithReturn cpr_reboot_notifier; +}; + +#define TYPE_VFIO_IOMMU "vfio-iommu" +OBJECT_DECLARE_TYPE(VFIOContainer, VFIOIOMMUClass, VFIO_IOMMU) + +typedef struct VFIOGuestIOMMU { + VFIOContainer *bcontainer; + IOMMUMemoryRegion *iommu_mr; + hwaddr iommu_offset; + IOMMUNotifier n; + QLIST_ENTRY(VFIOGuestIOMMU) giommu_next; +} VFIOGuestIOMMU; + +typedef struct VFIORamDiscardListener { + VFIOContainer *bcontainer; + MemoryRegion *mr; + hwaddr offset_within_address_space; + hwaddr size; + uint64_t granularity; + RamDiscardListener listener; + QLIST_ENTRY(VFIORamDiscardListener) next; +} VFIORamDiscardListener; + +VFIOAddressSpace *vfio_address_space_get(AddressSpace *as); +void vfio_address_space_put(VFIOAddressSpace *space); +void vfio_address_space_insert(VFIOAddressSpace *space, + VFIOContainer *bcontainer); + +int vfio_container_dma_map(VFIOContainer *bcontainer, + hwaddr iova, uint64_t size, + void *vaddr, bool readonly, MemoryRegion *mr); +int vfio_container_dma_unmap(VFIOContainer *bcontainer, + hwaddr iova, uint64_t size, + IOMMUTLBEntry *iotlb, bool unmap_all); +bool vfio_container_add_section_window(VFIOContainer *bcontainer, + MemoryRegionSection *section, + Error **errp); +void vfio_container_del_section_window(VFIOContainer *bcontainer, + MemoryRegionSection *section); +int vfio_container_set_dirty_page_tracking(VFIOContainer *bcontainer, + bool start, Error **errp); +bool vfio_container_dirty_tracking_is_started( + const VFIOContainer *bcontainer); +bool vfio_container_devices_dirty_tracking_is_supported( + const VFIOContainer *bcontainer); +int vfio_container_query_dirty_bitmap(const VFIOContainer *bcontainer, + uint64_t iova, uint64_t size, + hwaddr translated_addr, Error **errp); + +GList *vfio_container_get_iova_ranges(const VFIOContainer *bcontainer); + +static inline uint64_t +vfio_container_get_page_size_mask(const VFIOContainer *bcontainer) +{ + assert(bcontainer); + return bcontainer->pgsizes; +} + +#define TYPE_VFIO_IOMMU_LEGACY TYPE_VFIO_IOMMU "-legacy" +#define TYPE_VFIO_IOMMU_SPAPR TYPE_VFIO_IOMMU "-spapr" +#define TYPE_VFIO_IOMMU_IOMMUFD TYPE_VFIO_IOMMU "-iommufd" +#define TYPE_VFIO_IOMMU_USER TYPE_VFIO_IOMMU "-user" + +struct VFIOIOMMUClass { + ObjectClass parent_class; + + /** + * @setup + * + * Perform basic setup of the container, including configuring IOMMU + * capabilities, IOVA ranges, supported page sizes, etc. + * + * @bcontainer: #VFIOContainer + * @errp: pointer to Error*, to store an error if it happens. + * + * Returns true to indicate success and false for error. + */ + bool (*setup)(VFIOContainer *bcontainer, Error **errp); + + /** + * @listener_begin + * + * Called at the beginning of an address space update transaction. + * See #MemoryListener. + * + * @bcontainer: #VFIOContainer + */ + void (*listener_begin)(VFIOContainer *bcontainer); + + /** + * @listener_commit + * + * Called at the end of an address space update transaction, + * See #MemoryListener. + * + * @bcontainer: #VFIOContainer + */ + void (*listener_commit)(VFIOContainer *bcontainer); + + /** + * @dma_map + * + * Map an address range into the container. Note that the memory region is + * referenced within an RCU read lock region across this call. + * + * @bcontainer: #VFIOContainer to use + * @iova: start address to map + * @size: size of the range to map + * @vaddr: process virtual address of mapping + * @readonly: true if mapping should be readonly + * @mr: the memory region for this mapping + * + * Returns 0 to indicate success and -errno otherwise. + */ + int (*dma_map)(const VFIOContainer *bcontainer, + hwaddr iova, uint64_t size, + void *vaddr, bool readonly, MemoryRegion *mr); + /** + * @dma_map_file + * + * Map a file range for the container. + * + * @bcontainer: #VFIOContainer to use for map + * @iova: start address to map + * @size: size of the range to map + * @fd: descriptor of the file to map + * @start: starting file offset of the range to map + * @readonly: map read only if true + */ + int (*dma_map_file)(const VFIOContainer *bcontainer, + hwaddr iova, uint64_t size, + int fd, unsigned long start, bool readonly); + /** + * @dma_unmap + * + * Unmap an address range from the container. + * + * @bcontainer: #VFIOContainer to use for unmap + * @iova: start address to unmap + * @size: size of the range to unmap + * @iotlb: The IOMMU TLB mapping entry (or NULL) + * @unmap_all: if set, unmap the entire address space + * + * Returns 0 to indicate success and -errno otherwise. + */ + int (*dma_unmap)(const VFIOContainer *bcontainer, + hwaddr iova, uint64_t size, + IOMMUTLBEntry *iotlb, bool unmap_all); + + + /** + * @attach_device + * + * Associate the given device with a container and do some related + * initialization of the device context. + * + * @name: name of the device + * @vbasedev: the device + * @as: address space to use + * @errp: pointer to Error*, to store an error if it happens. + * + * Returns true to indicate success and false for error. + */ + bool (*attach_device)(const char *name, VFIODevice *vbasedev, + AddressSpace *as, Error **errp); + + /* + * @detach_device + * + * Detach the given device from its container and clean up any necessary + * state. + * + * @vbasedev: the device to disassociate + */ + void (*detach_device)(VFIODevice *vbasedev); + + /* migration feature */ + + /** + * @set_dirty_page_tracking + * + * Start or stop dirty pages tracking on VFIO container + * + * @bcontainer: #VFIOContainer on which to de/activate dirty + * page tracking + * @start: indicates whether to start or stop dirty pages tracking + * @errp: pointer to Error*, to store an error if it happens. + * + * Returns zero to indicate success and negative for error. + */ + int (*set_dirty_page_tracking)(const VFIOContainer *bcontainer, + bool start, Error **errp); + /** + * @query_dirty_bitmap + * + * Get bitmap of dirty pages from container + * + * @bcontainer: #VFIOContainer from which to get dirty pages + * @vbmap: #VFIOBitmap internal bitmap structure + * @iova: iova base address + * @size: size of iova range + * @errp: pointer to Error*, to store an error if it happens. + * + * Returns zero to indicate success and negative for error. + */ + int (*query_dirty_bitmap)(const VFIOContainer *bcontainer, + VFIOBitmap *vbmap, hwaddr iova, hwaddr size, Error **errp); + /* PCI specific */ + int (*pci_hot_reset)(VFIODevice *vbasedev, bool single); + + /* SPAPR specific */ + bool (*add_window)(VFIOContainer *bcontainer, + MemoryRegionSection *section, + Error **errp); + void (*del_window)(VFIOContainer *bcontainer, + MemoryRegionSection *section); + void (*release)(VFIOContainer *bcontainer); +}; + +VFIORamDiscardListener *vfio_find_ram_discard_listener( + VFIOContainer *bcontainer, MemoryRegionSection *section); + +void vfio_container_region_add(VFIOContainer *bcontainer, + MemoryRegionSection *section, bool cpr_remap); + +#endif /* HW_VFIO_VFIO_CONTAINER_H */ diff --git a/include/hw/vfio/vfio-cpr.h b/include/hw/vfio/vfio-cpr.h new file mode 100644 index 0000000..4606da5 --- /dev/null +++ b/include/hw/vfio/vfio-cpr.h @@ -0,0 +1,88 @@ +/* + * VFIO CPR + * + * Copyright (c) 2025 Oracle and/or its affiliates. + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_VFIO_VFIO_CPR_H +#define HW_VFIO_VFIO_CPR_H + +#include "migration/misc.h" +#include "system/memory.h" + +struct VFIOLegacyContainer; +struct VFIOContainer; +struct VFIOGroup; +struct VFIODevice; +struct VFIOPCIDevice; +struct VFIOIOMMUFDContainer; +struct IOMMUFDBackend; + +typedef int (*dma_map_fn)(const struct VFIOContainer *bcontainer, + hwaddr iova, uint64_t size, void *vaddr, + bool readonly, MemoryRegion *mr); + +typedef struct VFIOContainerCPR { + Error *blocker; + bool vaddr_unmapped; + NotifierWithReturn transfer_notifier; + MemoryListener remap_listener; +} VFIOContainerCPR; + +typedef struct VFIODeviceCPR { + Error *mdev_blocker; + Error *id_blocker; + uint32_t hwpt_id; + uint32_t ioas_id; +} VFIODeviceCPR; + +typedef struct VFIOPCICPR { + NotifierWithReturn transfer_notifier; +} VFIOPCICPR; + +bool vfio_legacy_cpr_register_container(struct VFIOLegacyContainer *container, + Error **errp); +void vfio_legacy_cpr_unregister_container( + struct VFIOLegacyContainer *container); + +int vfio_cpr_reboot_notifier(NotifierWithReturn *notifier, MigrationEvent *e, + Error **errp); + +bool vfio_iommufd_cpr_register_container(struct VFIOIOMMUFDContainer *container, + Error **errp); +void vfio_iommufd_cpr_unregister_container( + struct VFIOIOMMUFDContainer *container); +bool vfio_iommufd_cpr_register_iommufd(struct IOMMUFDBackend *be, Error **errp); +void vfio_iommufd_cpr_unregister_iommufd(struct IOMMUFDBackend *be); +void vfio_iommufd_cpr_register_device(struct VFIODevice *vbasedev); +void vfio_iommufd_cpr_unregister_device(struct VFIODevice *vbasedev); +void vfio_cpr_load_device(struct VFIODevice *vbasedev); + +int vfio_cpr_group_get_device_fd(int d, const char *name); + +bool vfio_cpr_container_match(struct VFIOLegacyContainer *container, + struct VFIOGroup *group, int fd); + +void vfio_cpr_giommu_remap(struct VFIOContainer *bcontainer, + MemoryRegionSection *section); + +bool vfio_cpr_ram_discard_replay_populated( + struct VFIOContainer *bcontainer, MemoryRegionSection *section); + +void vfio_cpr_save_vector_fd(struct VFIOPCIDevice *vdev, const char *name, + int nr, int fd); +int vfio_cpr_load_vector_fd(struct VFIOPCIDevice *vdev, const char *name, + int nr); +void vfio_cpr_delete_vector_fd(struct VFIOPCIDevice *vdev, const char *name, + int nr); + +extern const VMStateDescription vfio_cpr_pci_vmstate; +extern const VMStateDescription vmstate_cpr_vfio_devices; + +void vfio_cpr_add_kvm_notifier(void); +void vfio_cpr_pci_register_device(struct VFIOPCIDevice *vdev); +void vfio_cpr_pci_unregister_device(struct VFIOPCIDevice *vdev); + +#endif /* HW_VFIO_VFIO_CPR_H */ diff --git a/include/hw/vfio/vfio-device.h b/include/hw/vfio/vfio-device.h new file mode 100644 index 0000000..0fe6c60 --- /dev/null +++ b/include/hw/vfio/vfio-device.h @@ -0,0 +1,291 @@ +/* + * VFIO Device interface + * + * Copyright Red Hat, Inc. 2012 + * + * Authors: + * Alex Williamson <alex.williamson@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Based on qemu-kvm device-assignment: + * Adapted for KVM by Qumranet. + * Copyright (c) 2007, Neocleus, Alex Novik (alex@neocleus.com) + * Copyright (c) 2007, Neocleus, Guy Zana (guy@neocleus.com) + * Copyright (C) 2008, Qumranet, Amit Shah (amit.shah@qumranet.com) + * Copyright (C) 2008, Red Hat, Amit Shah (amit.shah@redhat.com) + * Copyright (C) 2008, IBM, Muli Ben-Yehuda (muli@il.ibm.com) + */ + +#ifndef HW_VFIO_VFIO_DEVICE_H +#define HW_VFIO_VFIO_DEVICE_H + +#include "system/memory.h" +#include "qemu/queue.h" +#ifdef CONFIG_LINUX +#include <linux/vfio.h> +#endif +#include "system/system.h" +#include "hw/vfio/vfio-container.h" +#include "hw/vfio/vfio-cpr.h" +#include "system/host_iommu_device.h" +#include "system/iommufd.h" + +#define VFIO_MSG_PREFIX "vfio %s: " + +enum { + VFIO_DEVICE_TYPE_PCI = 0, + VFIO_DEVICE_TYPE_UNUSED = 1, + VFIO_DEVICE_TYPE_CCW = 2, + VFIO_DEVICE_TYPE_AP = 3, +}; + +typedef struct VFIODeviceOps VFIODeviceOps; +typedef struct VFIODeviceIOOps VFIODeviceIOOps; +typedef struct VFIOMigration VFIOMigration; + +typedef struct IOMMUFDBackend IOMMUFDBackend; +typedef struct VFIOIOASHwpt VFIOIOASHwpt; +typedef struct VFIOUserProxy VFIOUserProxy; + +typedef struct VFIODevice { + QLIST_ENTRY(VFIODevice) next; + QLIST_ENTRY(VFIODevice) container_next; + QLIST_ENTRY(VFIODevice) global_next; + struct VFIOGroup *group; + VFIOContainer *bcontainer; + char *sysfsdev; + char *name; + DeviceState *dev; + int fd; + int type; + bool mdev; + bool reset_works; + bool needs_reset; + bool no_mmap; + bool ram_block_discard_allowed; + OnOffAuto enable_migration; + OnOffAuto migration_multifd_transfer; + OnOffAuto migration_load_config_after_iter; + uint64_t migration_max_queued_buffers_size; + bool migration_events; + bool use_region_fds; + VFIODeviceOps *ops; + VFIODeviceIOOps *io_ops; + unsigned int num_irqs; + unsigned int num_initial_regions; + unsigned int flags; + VFIOMigration *migration; + Error *migration_blocker; + OnOffAuto pre_copy_dirty_page_tracking; + OnOffAuto device_dirty_page_tracking; + bool dirty_pages_supported; + bool dirty_tracking; /* Protected by BQL */ + bool iommu_dirty_tracking; + HostIOMMUDevice *hiod; + int devid; + IOMMUFDBackend *iommufd; + VFIOIOASHwpt *hwpt; + QLIST_ENTRY(VFIODevice) hwpt_next; + struct vfio_region_info **reginfo; + int *region_fds; + VFIODeviceCPR cpr; + VFIOUserProxy *proxy; +} VFIODevice; + +struct VFIODeviceOps { + void (*vfio_compute_needs_reset)(VFIODevice *vdev); + int (*vfio_hot_reset_multi)(VFIODevice *vdev); + void (*vfio_eoi)(VFIODevice *vdev); + Object *(*vfio_get_object)(VFIODevice *vdev); + + /** + * @vfio_save_config + * + * Save device config state + * + * @vdev: #VFIODevice for which to save the config + * @f: #QEMUFile where to send the data + * @errp: pointer to Error*, to store an error if it happens. + * + * Returns zero to indicate success and negative for error + */ + int (*vfio_save_config)(VFIODevice *vdev, QEMUFile *f, Error **errp); + + /** + * @vfio_load_config + * + * Load device config state + * + * @vdev: #VFIODevice for which to load the config + * @f: #QEMUFile where to get the data + * + * Returns zero to indicate success and negative for error + */ + int (*vfio_load_config)(VFIODevice *vdev, QEMUFile *f); +}; + +/* + * Given a return value of either a short number of bytes read or -errno, + * construct a meaningful error message. + */ +#define strreaderror(ret) \ + (ret < 0 ? strerror(-ret) : "short read") + +/* + * Given a return value of either a short number of bytes written or -errno, + * construct a meaningful error message. + */ +#define strwriteerror(ret) \ + (ret < 0 ? strerror(-ret) : "short write") + +void vfio_device_irq_disable(VFIODevice *vbasedev, int index); +void vfio_device_irq_unmask(VFIODevice *vbasedev, int index); +void vfio_device_irq_mask(VFIODevice *vbasedev, int index); +bool vfio_device_irq_set_signaling(VFIODevice *vbasedev, int index, int subindex, + int action, int fd, Error **errp); + +void vfio_device_reset_handler(void *opaque); +bool vfio_device_is_mdev(VFIODevice *vbasedev); +bool vfio_device_hiod_create_and_realize(VFIODevice *vbasedev, + const char *typename, Error **errp); +bool vfio_device_attach(char *name, VFIODevice *vbasedev, + AddressSpace *as, Error **errp); +bool vfio_device_attach_by_iommu_type(const char *iommu_type, char *name, + VFIODevice *vbasedev, AddressSpace *as, + Error **errp); +void vfio_device_detach(VFIODevice *vbasedev); +VFIODevice *vfio_get_vfio_device(Object *obj); + +typedef QLIST_HEAD(VFIODeviceList, VFIODevice) VFIODeviceList; +extern VFIODeviceList vfio_device_list; + +#ifdef CONFIG_LINUX +/* + * How devices communicate with the server. The default option is through + * ioctl() to the kernel VFIO driver, but vfio-user can use a socket to a remote + * process. + */ +struct VFIODeviceIOOps { + /** + * @device_feature + * + * Fill in feature info for the given device. + * + * @vdev: #VFIODevice to use + * @feat: feature information to fill in + * + * Returns 0 on success or -errno. + */ + int (*device_feature)(VFIODevice *vdev, struct vfio_device_feature *feat); + + /** + * @get_region_info + * + * Get the information for a given region on the device. + * + * @vdev: #VFIODevice to use + * @info: set @info->index to the region index to look up; the rest of the + * struct will be filled in on success + * @fd: pointer to the fd for the region; will be -1 if not found + * + * Returns 0 on success or -errno. + */ + int (*get_region_info)(VFIODevice *vdev, + struct vfio_region_info *info, int *fd); + + /** + * @get_irq_info + * + * @vdev: #VFIODevice to use + * @irq: set @irq->index to the IRQ index to look up; the rest of the struct + * will be filled in on success + * + * Returns 0 on success or -errno. + */ + int (*get_irq_info)(VFIODevice *vdev, struct vfio_irq_info *irq); + + /** + * @set_irqs + * + * Configure IRQs. + * + * @vdev: #VFIODevice to use + * @irqs: IRQ configuration as defined by VFIO docs. + * + * Returns 0 on success or -errno. + */ + int (*set_irqs)(VFIODevice *vdev, struct vfio_irq_set *irqs); + + /** + * @region_read + * + * Read part of a region. + * + * @vdev: #VFIODevice to use + * @nr: region index + * @off: offset within the region + * @size: size in bytes to read + * @data: buffer to read into + * + * Returns number of bytes read on success or -errno. + */ + int (*region_read)(VFIODevice *vdev, uint8_t nr, off_t off, uint32_t size, + void *data); + + /** + * @region_write + * + * Write part of a region. + * + * @vdev: #VFIODevice to use + * @nr: region index + * @off: offset within the region + * @size: size in bytes to write + * @data: buffer to write from + * @post: true if this is a posted write + * + * Returns number of bytes write on success or -errno. + */ + int (*region_write)(VFIODevice *vdev, uint8_t nr, off_t off, uint32_t size, + void *data, bool post); +}; + +void vfio_device_prepare(VFIODevice *vbasedev, VFIOContainer *bcontainer, + struct vfio_device_info *info); + +void vfio_device_unprepare(VFIODevice *vbasedev); + +int vfio_device_get_region_info(VFIODevice *vbasedev, int index, + struct vfio_region_info **info); +int vfio_device_get_region_info_type(VFIODevice *vbasedev, uint32_t type, + uint32_t subtype, struct vfio_region_info **info); + +/** + * Return the fd for mapping this region. This is either the device's fd (for + * e.g. kernel vfio), or a per-region fd (for vfio-user). + * + * @vbasedev: #VFIODevice to use + * @index: region index + * + * Returns the fd. + */ +int vfio_device_get_region_fd(VFIODevice *vbasedev, int index); + +bool vfio_device_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type); + +int vfio_device_get_irq_info(VFIODevice *vbasedev, int index, + struct vfio_irq_info *info); +#endif + +/* Returns 0 on success, or a negative errno. */ +bool vfio_device_get_name(VFIODevice *vbasedev, Error **errp); +void vfio_device_free_name(VFIODevice *vbasedev); +void vfio_device_set_fd(VFIODevice *vbasedev, const char *str, Error **errp); +void vfio_device_init(VFIODevice *vbasedev, int type, VFIODeviceOps *ops, + DeviceState *dev, bool ram_discard); +int vfio_device_get_aw_bits(VFIODevice *vdev); + +void vfio_kvm_device_close(void); +#endif /* HW_VFIO_VFIO_DEVICE_H */ diff --git a/include/hw/vfio/vfio-migration.h b/include/hw/vfio/vfio-migration.h new file mode 100644 index 0000000..0d4ecd3 --- /dev/null +++ b/include/hw/vfio/vfio-migration.h @@ -0,0 +1,16 @@ +/* + * VFIO migration interface + * + * Copyright Red Hat, Inc. 2025 + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_VFIO_VFIO_MIGRATION_H +#define HW_VFIO_VFIO_MIGRATION_H + +bool vfio_migration_active(void); +int64_t vfio_migration_bytes_transferred(void); +void vfio_migration_reset_bytes_transferred(void); + +#endif /* HW_VFIO_VFIO_MIGRATION_H */ diff --git a/include/hw/vfio/vfio-platform.h b/include/hw/vfio/vfio-platform.h deleted file mode 100644 index c414c3d..0000000 --- a/include/hw/vfio/vfio-platform.h +++ /dev/null @@ -1,76 +0,0 @@ -/* - * vfio based device assignment support - platform devices - * - * Copyright Linaro Limited, 2014 - * - * Authors: - * Kim Phillips <kim.phillips@linaro.org> - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. - * - * Based on vfio based PCI device assignment support: - * Copyright Red Hat, Inc. 2012 - */ - -#ifndef HW_VFIO_VFIO_PLATFORM_H -#define HW_VFIO_VFIO_PLATFORM_H - -#include "hw/sysbus.h" -#include "hw/vfio/vfio-common.h" -#include "qemu/event_notifier.h" -#include "qemu/queue.h" -#include "qom/object.h" - -#define TYPE_VFIO_PLATFORM "vfio-platform" - -enum { - VFIO_IRQ_INACTIVE = 0, - VFIO_IRQ_PENDING = 1, - VFIO_IRQ_ACTIVE = 2, - /* VFIO_IRQ_ACTIVE_AND_PENDING cannot happen with VFIO */ -}; - -typedef struct VFIOINTp { - QLIST_ENTRY(VFIOINTp) next; /* entry for IRQ list */ - QSIMPLEQ_ENTRY(VFIOINTp) pqnext; /* entry for pending IRQ queue */ - EventNotifier *interrupt; /* eventfd triggered on interrupt */ - EventNotifier *unmask; /* eventfd for unmask on QEMU bypass */ - qemu_irq qemuirq; - struct VFIOPlatformDevice *vdev; /* back pointer to device */ - int state; /* inactive, pending, active */ - uint8_t pin; /* index */ - uint32_t flags; /* IRQ info flags */ - bool kvm_accel; /* set when QEMU bypass through KVM enabled */ -} VFIOINTp; - -/* function type for user side eventfd handler */ -typedef void (*eventfd_user_side_handler_t)(VFIOINTp *intp); - -struct VFIOPlatformDevice { - SysBusDevice sbdev; - VFIODevice vbasedev; /* not a QOM object */ - VFIORegion **regions; - QLIST_HEAD(, VFIOINTp) intp_list; /* list of IRQs */ - /* queue of pending IRQs */ - QSIMPLEQ_HEAD(, VFIOINTp) pending_intp_queue; - char *compat; /* DT compatible values, separated by NUL */ - unsigned int num_compat; /* number of compatible values */ - uint32_t mmap_timeout; /* delay to re-enable mmaps after interrupt */ - QEMUTimer *mmap_timer; /* allows fast-path resume after IRQ hit */ - QemuMutex intp_mutex; /* protect the intp_list IRQ state */ - bool irqfd_allowed; /* debug option to force irqfd on/off */ -}; -typedef struct VFIOPlatformDevice VFIOPlatformDevice; - -struct VFIOPlatformDeviceClass { - /*< private >*/ - SysBusDeviceClass parent_class; - /*< public >*/ -}; -typedef struct VFIOPlatformDeviceClass VFIOPlatformDeviceClass; - -DECLARE_OBJ_CHECKERS(VFIOPlatformDevice, VFIOPlatformDeviceClass, - VFIO_PLATFORM_DEVICE, TYPE_VFIO_PLATFORM) - -#endif /* HW_VFIO_VFIO_PLATFORM_H */ diff --git a/include/hw/virtio/vhost-backend.h b/include/hw/virtio/vhost-backend.h index 70c2e8f..ff94fa1 100644 --- a/include/hw/virtio/vhost-backend.h +++ b/include/hw/virtio/vhost-backend.h @@ -11,7 +11,7 @@ #ifndef VHOST_BACKEND_H #define VHOST_BACKEND_H -#include "exec/memory.h" +#include "system/memory.h" typedef enum VhostBackendType { VHOST_BACKEND_TYPE_NONE = 0, @@ -95,6 +95,10 @@ typedef int (*vhost_new_worker_op)(struct vhost_dev *dev, struct vhost_worker_state *worker); typedef int (*vhost_free_worker_op)(struct vhost_dev *dev, struct vhost_worker_state *worker); +typedef int (*vhost_set_features_ex_op)(struct vhost_dev *dev, + const uint64_t *features); +typedef int (*vhost_get_features_ex_op)(struct vhost_dev *dev, + uint64_t *features); typedef int (*vhost_set_features_op)(struct vhost_dev *dev, uint64_t features); typedef int (*vhost_get_features_op)(struct vhost_dev *dev, @@ -186,6 +190,8 @@ typedef struct VhostOps { vhost_free_worker_op vhost_free_worker; vhost_get_vring_worker_op vhost_get_vring_worker; vhost_attach_vring_worker_op vhost_attach_vring_worker; + vhost_set_features_ex_op vhost_set_features_ex; + vhost_get_features_ex_op vhost_get_features_ex; vhost_set_features_op vhost_set_features; vhost_get_features_op vhost_get_features; vhost_set_backend_cap_op vhost_set_backend_cap; diff --git a/include/hw/virtio/vhost-scsi-common.h b/include/hw/virtio/vhost-scsi-common.h index c5d2c09..d54d9c9 100644 --- a/include/hw/virtio/vhost-scsi-common.h +++ b/include/hw/virtio/vhost-scsi-common.h @@ -40,7 +40,7 @@ struct VHostSCSICommon { }; int vhost_scsi_common_start(VHostSCSICommon *vsc, Error **errp); -void vhost_scsi_common_stop(VHostSCSICommon *vsc); +int vhost_scsi_common_stop(VHostSCSICommon *vsc); char *vhost_scsi_common_get_fw_dev_path(FWPathProvider *p, BusState *bus, DeviceState *dev); void vhost_scsi_common_set_config(VirtIODevice *vdev, const uint8_t *config); diff --git a/include/hw/virtio/vhost-user-base.h b/include/hw/virtio/vhost-user-base.h index 51d0968..d5d2f08 100644 --- a/include/hw/virtio/vhost-user-base.h +++ b/include/hw/virtio/vhost-user-base.h @@ -20,7 +20,7 @@ struct VHostUserBase { VirtIODevice parent_obj; /* Properties */ - CharBackend chardev; + CharFrontend chardev; uint16_t virtio_id; uint32_t num_vqs; uint32_t vq_size; /* can't exceed VIRTIO_QUEUE_MAX */ @@ -44,6 +44,6 @@ struct VHostUserBaseClass { }; -#define TYPE_VHOST_USER_DEVICE "vhost-user-device" +#define TYPE_VHOST_USER_TEST_DEVICE "vhost-user-test-device" #endif /* QEMU_VHOST_USER_BASE_H */ diff --git a/include/hw/virtio/vhost-user-blk.h b/include/hw/virtio/vhost-user-blk.h index ea085ee..8158d46 100644 --- a/include/hw/virtio/vhost-user-blk.h +++ b/include/hw/virtio/vhost-user-blk.h @@ -29,7 +29,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(VHostUserBlk, VHOST_USER_BLK) struct VHostUserBlk { VirtIODevice parent_obj; - CharBackend chardev; + CharFrontend chardev; int32_t bootindex; struct virtio_blk_config blkcfg; uint16_t num_queues; @@ -50,6 +50,8 @@ struct VHostUserBlk { bool connected; /* vhost_user_blk_start/vhost_user_blk_stop */ bool started_vu; + + bool skip_get_vring_base_on_force_shutdown; }; #endif diff --git a/include/hw/virtio/vhost-user-fs.h b/include/hw/virtio/vhost-user-fs.h index 94c3aaa..5699ea0 100644 --- a/include/hw/virtio/vhost-user-fs.h +++ b/include/hw/virtio/vhost-user-fs.h @@ -24,7 +24,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(VHostUserFS, VHOST_USER_FS) typedef struct { - CharBackend chardev; + CharFrontend chardev; char *tag; uint16_t num_request_queues; uint16_t queue_size; diff --git a/include/hw/virtio/vhost-user-scmi.h b/include/hw/virtio/vhost-user-scmi.h index c90db77..30ab0d7 100644 --- a/include/hw/virtio/vhost-user-scmi.h +++ b/include/hw/virtio/vhost-user-scmi.h @@ -18,7 +18,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(VHostUserSCMI, VHOST_USER_SCMI); struct VHostUserSCMI { VirtIODevice parent; - CharBackend chardev; + CharFrontend chardev; struct vhost_virtqueue *vhost_vqs; struct vhost_dev vhost_dev; VhostUserState vhost_user; diff --git a/include/hw/virtio/vhost-user-vsock.h b/include/hw/virtio/vhost-user-vsock.h index 67aa46c..5db6938 100644 --- a/include/hw/virtio/vhost-user-vsock.h +++ b/include/hw/virtio/vhost-user-vsock.h @@ -20,7 +20,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(VHostUserVSock, VHOST_USER_VSOCK) typedef struct { - CharBackend chardev; + CharFrontend chardev; } VHostUserVSockConf; struct VHostUserVSock { diff --git a/include/hw/virtio/vhost-user.h b/include/hw/virtio/vhost-user.h index 9a3f238..55d5725 100644 --- a/include/hw/virtio/vhost-user.h +++ b/include/hw/virtio/vhost-user.h @@ -64,7 +64,7 @@ typedef struct VhostUserHostNotifier { * @memory_slots: */ typedef struct VhostUserState { - CharBackend *chr; + CharFrontend *chr; GPtrArray *notifiers; int memory_slots; bool supports_config; @@ -82,7 +82,7 @@ typedef struct VhostUserState { * * Return: true on success, false on error while setting errp. */ -bool vhost_user_init(VhostUserState *user, CharBackend *chr, Error **errp); +bool vhost_user_init(VhostUserState *user, CharFrontend *chr, Error **errp); /** * vhost_user_cleanup() - cleanup state @@ -96,7 +96,7 @@ void vhost_user_cleanup(VhostUserState *user); /** * vhost_user_async_close() - cleanup vhost-user post connection drop * @d: DeviceState for the associated device (passed to callback) - * @chardev: the CharBackend associated with the connection + * @chardev: the CharFrontend associated with the connection * @vhost: the common vhost device * @cb: the user callback function to complete the clean-up * @@ -108,7 +108,7 @@ void vhost_user_cleanup(VhostUserState *user); typedef void (*vu_async_close_fn)(DeviceState *cb); void vhost_user_async_close(DeviceState *d, - CharBackend *chardev, struct vhost_dev *vhost, + CharFrontend *chardev, struct vhost_dev *vhost, vu_async_close_fn cb); #endif diff --git a/include/hw/virtio/vhost-vdpa.h b/include/hw/virtio/vhost-vdpa.h index 0a9575b..449bf5c 100644 --- a/include/hw/virtio/vhost-vdpa.h +++ b/include/hw/virtio/vhost-vdpa.h @@ -43,7 +43,21 @@ typedef struct vhost_vdpa_shared { struct vhost_vdpa_iova_range iova_range; QLIST_HEAD(, vdpa_iommu) iommu_list; - /* IOVA mapping used by the Shadow Virtqueue */ + /* + * IOVA mapping used by the Shadow Virtqueue + * + * It is shared among all ASID for simplicity, whether CVQ shares ASID with + * guest or not: + * - Memory listener need access to guest's memory addresses allocated in + * the IOVA tree. + * - There should be plenty of IOVA address space for both ASID not to + * worry about collisions between them. Guest's translations are still + * validated with virtio virtqueue_pop so there is no risk for the guest + * to access memory that it shouldn't. + * + * To allocate a iova tree per ASID is doable but it complicates the code + * and it is not worth it for the moment. + */ VhostIOVATree *iova_tree; /* Copy of backend features */ @@ -51,6 +65,12 @@ typedef struct vhost_vdpa_shared { bool iotlb_batch_begin_sent; + /* + * The memory listener has been registered, so DMA maps have been sent to + * the device. + */ + bool listener_registered; + /* Vdpa must send shadow addresses as IOTLB key for data queues, not GPA */ bool shadow_data; diff --git a/include/hw/virtio/vhost-vsock-common.h b/include/hw/virtio/vhost-vsock-common.h index 75a74e8..01bf606 100644 --- a/include/hw/virtio/vhost-vsock-common.h +++ b/include/hw/virtio/vhost-vsock-common.h @@ -42,7 +42,7 @@ struct VHostVSockCommon { }; int vhost_vsock_common_start(VirtIODevice *vdev); -void vhost_vsock_common_stop(VirtIODevice *vdev); +int vhost_vsock_common_stop(VirtIODevice *vdev); int vhost_vsock_common_pre_save(void *opaque); int vhost_vsock_common_post_load(void *opaque, int version_id); void vhost_vsock_common_realize(VirtIODevice *vdev); diff --git a/include/hw/virtio/vhost.h b/include/hw/virtio/vhost.h index a9469d5..08bbb4d 100644 --- a/include/hw/virtio/vhost.h +++ b/include/hw/virtio/vhost.h @@ -1,9 +1,10 @@ #ifndef VHOST_H #define VHOST_H +#include "net/vhost_net.h" #include "hw/virtio/vhost-backend.h" #include "hw/virtio/virtio.h" -#include "exec/memory.h" +#include "system/memory.h" #define VHOST_F_DEVICE_IOTLB 63 #define VHOST_USER_F_PROTOCOL_FEATURES 30 @@ -106,9 +107,9 @@ struct vhost_dev { * future use should be discouraged and the variable retired as * its easy to confuse with the VirtIO backend_features. */ - uint64_t features; - uint64_t acked_features; - uint64_t backend_features; + VIRTIO_DECLARE_FEATURES(features); + VIRTIO_DECLARE_FEATURES(acked_features); + VIRTIO_DECLARE_FEATURES(backend_features); /** * @protocol_features: is the vhost-user only feature set by @@ -143,6 +144,10 @@ struct vhost_net { struct vhost_dev dev; struct vhost_virtqueue vqs[2]; int backend; + const int *feature_bits; + int max_tx_queue_size; + SaveAcketFeatures *save_acked_features; + bool is_vhost_user; NetClientState *nc; }; @@ -232,8 +237,25 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev, bool vrings); * Stop the vhost device. After the device is stopped the notifiers * can be disabled (@vhost_dev_disable_notifiers) and the device can * be torn down (@vhost_dev_cleanup). + * + * Return: 0 on success, != 0 on error when stopping dev. + */ +int vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev, bool vrings); + +/** + * vhost_dev_force_stop() - force stop the vhost device + * @hdev: common vhost_dev structure + * @vdev: the VirtIODevice structure + * @vrings: true to have vrings disabled in this call + * + * Force stop the vhost device. After the device is stopped the notifiers + * can be disabled (@vhost_dev_disable_notifiers) and the device can + * be torn down (@vhost_dev_cleanup). Unlike @vhost_dev_stop, this doesn't + * attempt to flush in-flight backend requests by skipping GET_VRING_BASE + * entirely. */ -void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev, bool vrings); +int vhost_dev_force_stop(struct vhost_dev *hdev, VirtIODevice *vdev, + bool vrings); /** * DOC: vhost device configuration handling @@ -299,6 +321,20 @@ void vhost_virtqueue_mask(struct vhost_dev *hdev, VirtIODevice *vdev, int n, bool mask); /** + * vhost_get_features_ex() - sanitize the extended features set + * @hdev: common vhost_dev structure + * @feature_bits: pointer to terminated table of feature bits + * @features: original features set, filtered out on return + * + * This is the extended variant of vhost_get_features(), supporting the + * the extended features set. Filter it with the intersection of what is + * supported by the vhost backend (hdev->features) and the supported + * feature_bits. + */ +void vhost_get_features_ex(struct vhost_dev *hdev, + const int *feature_bits, + uint64_t *features); +/** * vhost_get_features() - return a sanitised set of feature bits * @hdev: common vhost_dev structure * @feature_bits: pointer to terminated table of feature bits @@ -308,8 +344,28 @@ void vhost_virtqueue_mask(struct vhost_dev *hdev, VirtIODevice *vdev, int n, * is supported by the vhost backend (hdev->features), the supported * feature_bits and the requested feature set. */ -uint64_t vhost_get_features(struct vhost_dev *hdev, const int *feature_bits, - uint64_t features); +static inline uint64_t vhost_get_features(struct vhost_dev *hdev, + const int *feature_bits, + uint64_t features) +{ + uint64_t features_ex[VIRTIO_FEATURES_NU64S]; + + virtio_features_from_u64(features_ex, features); + vhost_get_features_ex(hdev, feature_bits, features_ex); + return features_ex[0]; +} + +/** + * vhost_ack_features_ex() - set vhost full set of acked_features + * @hdev: common vhost_dev structure + * @feature_bits: pointer to terminated table of feature bits + * @features: requested feature set + * + * This sets the internal hdev->acked_features to the intersection of + * the backends advertised features and the supported feature_bits. + */ +void vhost_ack_features_ex(struct vhost_dev *hdev, const int *feature_bits, + const uint64_t *features); /** * vhost_ack_features() - set vhost acked_features @@ -320,8 +376,16 @@ uint64_t vhost_get_features(struct vhost_dev *hdev, const int *feature_bits, * This sets the internal hdev->acked_features to the intersection of * the backends advertised features and the supported feature_bits. */ -void vhost_ack_features(struct vhost_dev *hdev, const int *feature_bits, - uint64_t features); +static inline void vhost_ack_features(struct vhost_dev *hdev, + const int *feature_bits, + uint64_t features) +{ + uint64_t features_ex[VIRTIO_FEATURES_NU64S]; + + virtio_features_from_u64(features_ex, features); + vhost_ack_features_ex(hdev, feature_bits, features_ex); +} + unsigned int vhost_get_max_memslots(void); unsigned int vhost_get_free_memslots(void); @@ -333,8 +397,8 @@ int vhost_device_iotlb_miss(struct vhost_dev *dev, uint64_t iova, int write); int vhost_virtqueue_start(struct vhost_dev *dev, struct VirtIODevice *vdev, struct vhost_virtqueue *vq, unsigned idx); -void vhost_virtqueue_stop(struct vhost_dev *dev, struct VirtIODevice *vdev, - struct vhost_virtqueue *vq, unsigned idx); +int vhost_virtqueue_stop(struct vhost_dev *dev, struct VirtIODevice *vdev, + struct vhost_virtqueue *vq, unsigned idx); void vhost_dev_reset_inflight(struct vhost_inflight *inflight); void vhost_dev_free_inflight(struct vhost_inflight *inflight); diff --git a/include/hw/virtio/virtio-features.h b/include/hw/virtio/virtio-features.h new file mode 100644 index 0000000..e29b7fe --- /dev/null +++ b/include/hw/virtio/virtio-features.h @@ -0,0 +1,126 @@ +/* + * Virtio features helpers + * + * Copyright 2025 Red Hat, Inc. + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef QEMU_VIRTIO_FEATURES_H +#define QEMU_VIRTIO_FEATURES_H + +#include "qemu/bitops.h" + +#define VIRTIO_FEATURES_FMT "%016"PRIx64"%016"PRIx64 +#define VIRTIO_FEATURES_PR(f) (f)[1], (f)[0] + +#define VIRTIO_FEATURES_MAX 128 +#define VIRTIO_FEATURES_BIT(b) BIT_ULL((b) % 64) +#define VIRTIO_FEATURES_U64(b) ((b) / 64) +#define VIRTIO_FEATURES_NU32S (VIRTIO_FEATURES_MAX / 32) +#define VIRTIO_FEATURES_NU64S (VIRTIO_FEATURES_MAX / 64) + +#define VIRTIO_DECLARE_FEATURES(name) \ + union { \ + uint64_t name; \ + uint64_t name##_ex[VIRTIO_FEATURES_NU64S]; \ + } + +#define VIRTIO_DEFINE_PROP_FEATURE(_name, _state, _field, _bit, _defval) \ + DEFINE_PROP_BIT64(_name, _state, _field[VIRTIO_FEATURES_U64(_bit)], \ + (_bit) % 64, _defval) + +static inline void virtio_features_clear(uint64_t *features) +{ + memset(features, 0, sizeof(features[0]) * VIRTIO_FEATURES_NU64S); +} + +static inline void virtio_features_from_u64(uint64_t *features, uint64_t from) +{ + virtio_features_clear(features); + features[0] = from; +} + +static inline bool virtio_has_feature_ex(const uint64_t *features, + unsigned int fbit) +{ + assert(fbit < VIRTIO_FEATURES_MAX); + return features[VIRTIO_FEATURES_U64(fbit)] & VIRTIO_FEATURES_BIT(fbit); +} + +static inline void virtio_add_feature_ex(uint64_t *features, + unsigned int fbit) +{ + assert(fbit < VIRTIO_FEATURES_MAX); + features[VIRTIO_FEATURES_U64(fbit)] |= VIRTIO_FEATURES_BIT(fbit); +} + +static inline void virtio_clear_feature_ex(uint64_t *features, + unsigned int fbit) +{ + assert(fbit < VIRTIO_FEATURES_MAX); + features[VIRTIO_FEATURES_U64(fbit)] &= ~VIRTIO_FEATURES_BIT(fbit); +} + +static inline bool virtio_features_equal(const uint64_t *f1, + const uint64_t *f2) +{ + return !memcmp(f1, f2, sizeof(uint64_t) * VIRTIO_FEATURES_NU64S); +} + +static inline bool virtio_features_use_ex(const uint64_t *features) +{ + int i; + + for (i = 1; i < VIRTIO_FEATURES_NU64S; ++i) { + if (features[i]) { + return true; + } + } + return false; +} + +static inline bool virtio_features_empty(const uint64_t *features) +{ + return !virtio_features_use_ex(features) && !features[0]; +} + +static inline void virtio_features_copy(uint64_t *to, const uint64_t *from) +{ + memcpy(to, from, sizeof(to[0]) * VIRTIO_FEATURES_NU64S); +} + +static inline bool virtio_features_andnot(uint64_t *to, const uint64_t *f1, + const uint64_t *f2) +{ + uint64_t diff = 0; + int i; + + for (i = 0; i < VIRTIO_FEATURES_NU64S; i++) { + to[i] = f1[i] & ~f2[i]; + diff |= to[i]; + } + return diff; +} + +static inline void virtio_features_and(uint64_t *to, const uint64_t *f1, + const uint64_t *f2) +{ + int i; + + for (i = 0; i < VIRTIO_FEATURES_NU64S; i++) { + to[i] = f1[i] & f2[i]; + } +} + +static inline void virtio_features_or(uint64_t *to, const uint64_t *f1, + const uint64_t *f2) +{ + int i; + + for (i = 0; i < VIRTIO_FEATURES_NU64S; i++) { + to[i] = f1[i] | f2[i]; + } +} + +#endif diff --git a/include/hw/virtio/virtio-gpu.h b/include/hw/virtio/virtio-gpu.h index a42957c..58e0f91 100644 --- a/include/hw/virtio/virtio-gpu.h +++ b/include/hw/virtio/virtio-gpu.h @@ -20,6 +20,7 @@ #include "hw/virtio/virtio.h" #include "qemu/log.h" #include "system/vhost-user-backend.h" +#include "qapi/qapi-types-virtio.h" #include "standard-headers/linux/virtio_gpu.h" #include "standard-headers/linux/virtio_ids.h" @@ -128,6 +129,7 @@ struct virtio_gpu_base_conf { uint32_t xres; uint32_t yres; uint64_t hostmem; + VirtIOGPUOutputList *outputs; }; struct virtio_gpu_ctrl_command { @@ -167,6 +169,7 @@ struct VirtIOGPUBaseClass { #define VIRTIO_GPU_BASE_PROPERTIES(_state, _conf) \ DEFINE_PROP_UINT32("max_outputs", _state, _conf.max_outputs, 1), \ + DEFINE_PROP_VIRTIO_GPU_OUTPUT_LIST("outputs", _state, _conf.outputs), \ DEFINE_PROP_BIT("edid", _state, _conf.flags, \ VIRTIO_GPU_FLAG_EDID_ENABLED, true), \ DEFINE_PROP_UINT32("xres", _state, _conf.xres, 1280), \ @@ -254,7 +257,7 @@ struct VhostUserGPU { VhostUserBackend *vhost; int vhost_gpu_fd; /* closed by the chardev */ - CharBackend vhost_chr; + CharFrontend vhost_chr; QemuDmaBuf *dmabuf[VIRTIO_GPU_MAX_SCANOUTS]; bool backend_blocked; }; diff --git a/include/hw/virtio/virtio-mem.h b/include/hw/virtio/virtio-mem.h index bc4f787..e0ab31b 100644 --- a/include/hw/virtio/virtio-mem.h +++ b/include/hw/virtio/virtio-mem.h @@ -134,7 +134,7 @@ struct VirtioMemSystemReset { struct VirtIOMEMClass { /* private */ - VirtIODevice parent; + VirtioDeviceClass parent_class; /* public */ void (*fill_device_info)(const VirtIOMEM *vmen, VirtioMEMDeviceInfo *vi); diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h index b9ea9e8..5b8ab7b 100644 --- a/include/hw/virtio/virtio-net.h +++ b/include/hw/virtio/virtio-net.h @@ -144,7 +144,11 @@ typedef struct VirtioNetRssData { bool enabled_software_rss; bool redirect; bool populate_hash; - uint32_t hash_types; + bool peer_hash_available; + uint32_t runtime_hash_types; + uint32_t supported_hash_types; + uint32_t peer_hash_types; + OnOffAutoBit64 specified_hash_types; uint8_t key[VIRTIO_NET_RSS_MAX_KEY_SIZE]; uint16_t indirections_len; uint16_t *indirections_table; @@ -178,7 +182,7 @@ struct VirtIONet { uint32_t has_vnet_hdr; size_t host_hdr_len; size_t guest_hdr_len; - uint64_t host_features; + VIRTIO_DECLARE_FEATURES(host_features); uint32_t rsc_timeout; uint8_t rsc4_enabled; uint8_t rsc6_enabled; diff --git a/include/hw/virtio/virtio-pci.h b/include/hw/virtio/virtio-pci.h index 971c5fa..6397529 100644 --- a/include/hw/virtio/virtio-pci.h +++ b/include/hw/virtio/virtio-pci.h @@ -32,9 +32,7 @@ DECLARE_OBJ_CHECKERS(VirtioPCIBusState, VirtioPCIBusClass, enum { VIRTIO_PCI_FLAG_BUS_MASTER_BUG_MIGRATION_BIT, VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT, - VIRTIO_PCI_FLAG_MIGRATE_EXTRA_BIT, VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY_BIT, - VIRTIO_PCI_FLAG_DISABLE_PCIE_BIT, VIRTIO_PCI_FLAG_PAGE_PER_VQ_BIT, VIRTIO_PCI_FLAG_ATS_BIT, VIRTIO_PCI_FLAG_INIT_DEVERR_BIT, @@ -54,12 +52,6 @@ enum { * vcpu thread using ioeventfd for some devices. */ #define VIRTIO_PCI_FLAG_USE_IOEVENTFD (1 << VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT) -/* virtio version flags */ -#define VIRTIO_PCI_FLAG_DISABLE_PCIE (1 << VIRTIO_PCI_FLAG_DISABLE_PCIE_BIT) - -/* migrate extra state */ -#define VIRTIO_PCI_FLAG_MIGRATE_EXTRA (1 << VIRTIO_PCI_FLAG_MIGRATE_EXTRA_BIT) - /* have pio notification for modern device ? */ #define VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY \ (1 << VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY_BIT) @@ -155,6 +147,7 @@ struct VirtIOPCIProxy { uint32_t modern_io_bar_idx; uint32_t modern_mem_bar_idx; int config_cap; + uint16_t last_pcie_cap_offset; uint32_t flags; bool disable_modern; bool ignore_backend_features; @@ -165,7 +158,7 @@ struct VirtIOPCIProxy { uint32_t nvectors; uint32_t dfselect; uint32_t gfselect; - uint32_t guest_features[2]; + uint32_t guest_features[VIRTIO_FEATURES_NU32S]; VirtIOPCIQueue vqs[VIRTIO_QUEUE_MAX]; VirtIOIRQFD *vector_irqfd; @@ -255,8 +248,8 @@ typedef struct VirtioPCIDeviceTypeInfo { size_t class_size; void (*instance_init)(Object *obj); void (*instance_finalize)(Object *obj); - void (*class_init)(ObjectClass *klass, void *data); - InterfaceInfo *interfaces; + void (*class_init)(ObjectClass *klass, const void *data); + const InterfaceInfo *interfaces; } VirtioPCIDeviceTypeInfo; /* Register virtio-pci type(s). @t must be static. */ diff --git a/include/hw/virtio/virtio-pmem.h b/include/hw/virtio/virtio-pmem.h index fc4fd1f..9cce600 100644 --- a/include/hw/virtio/virtio-pmem.h +++ b/include/hw/virtio/virtio-pmem.h @@ -36,7 +36,7 @@ struct VirtIOPMEM { struct VirtIOPMEMClass { /* private */ - VirtIODevice parent; + VirtioDeviceClass parent_class; /* public */ void (*fill_device_info)(const VirtIOPMEM *pmem, VirtioPMEMDeviceInfo *vi); diff --git a/include/hw/virtio/virtio-scsi.h b/include/hw/virtio/virtio-scsi.h index 31e852e..b6028bb 100644 --- a/include/hw/virtio/virtio-scsi.h +++ b/include/hw/virtio/virtio-scsi.h @@ -58,7 +58,7 @@ struct VirtIOSCSIConf { uint32_t cmd_per_lun; char *vhostfd; char *wwpn; - CharBackend chardev; + CharFrontend chardev; uint32_t boot_tpgt; IOThread *iothread; IOThreadVirtQueueMappingList *iothread_vq_mapping_list; diff --git a/include/hw/virtio/virtio-serial.h b/include/hw/virtio/virtio-serial.h index d87c62e..6064186 100644 --- a/include/hw/virtio/virtio-serial.h +++ b/include/hw/virtio/virtio-serial.h @@ -29,7 +29,8 @@ struct virtio_serial_conf { OBJECT_DECLARE_TYPE(VirtIOSerialPort, VirtIOSerialPortClass, VIRTIO_SERIAL_PORT) -typedef struct VirtIOSerial VirtIOSerial; +#define TYPE_VIRTIO_SERIAL "virtio-serial-device" +OBJECT_DECLARE_SIMPLE_TYPE(VirtIOSerial, VIRTIO_SERIAL) #define TYPE_VIRTIO_SERIAL_BUS "virtio-serial-bus" OBJECT_DECLARE_SIMPLE_TYPE(VirtIOSerialBus, VIRTIO_SERIAL_BUS) @@ -221,7 +222,5 @@ size_t virtio_serial_guest_ready(VirtIOSerialPort *port); */ void virtio_serial_throttle_port(VirtIOSerialPort *port, bool throttle); -#define TYPE_VIRTIO_SERIAL "virtio-serial-device" -OBJECT_DECLARE_SIMPLE_TYPE(VirtIOSerial, VIRTIO_SERIAL) #endif diff --git a/include/hw/virtio/virtio.h b/include/hw/virtio/virtio.h index 6386910..d97529c 100644 --- a/include/hw/virtio/virtio.h +++ b/include/hw/virtio/virtio.h @@ -14,8 +14,9 @@ #ifndef QEMU_VIRTIO_H #define QEMU_VIRTIO_H -#include "exec/memory.h" +#include "system/memory.h" #include "hw/qdev-core.h" +#include "hw/virtio/virtio-features.h" #include "net/net.h" #include "migration/vmstate.h" #include "qemu/event_notifier.h" @@ -121,9 +122,9 @@ struct VirtIODevice * backend (e.g. vhost) and could potentially be a subset of the * total feature set offered by QEMU. */ - uint64_t host_features; - uint64_t guest_features; - uint64_t backend_features; + VIRTIO_DECLARE_FEATURES(host_features); + VIRTIO_DECLARE_FEATURES(guest_features); + VIRTIO_DECLARE_FEATURES(backend_features); size_t config_len; void *config; @@ -177,6 +178,9 @@ struct VirtioDeviceClass { /* This is what a VirtioDevice must implement */ DeviceRealize realize; DeviceUnrealize unrealize; + void (*get_features_ex)(VirtIODevice *vdev, uint64_t *requested_features, + Error **errp); + void (*set_features_ex)(VirtIODevice *vdev, const uint64_t *val); uint64_t (*get_features)(VirtIODevice *vdev, uint64_t requested_features, Error **errp); @@ -186,7 +190,7 @@ struct VirtioDeviceClass { void (*get_config)(VirtIODevice *vdev, uint8_t *config); void (*set_config)(VirtIODevice *vdev, const uint8_t *config); void (*reset)(VirtIODevice *vdev); - void (*set_status)(VirtIODevice *vdev, uint8_t val); + int (*set_status)(VirtIODevice *vdev, uint8_t val); /* Device must validate queue_index. */ void (*queue_reset)(VirtIODevice *vdev, uint32_t queue_index); /* Device must validate queue_index. */ @@ -210,8 +214,14 @@ struct VirtioDeviceClass { void (*guest_notifier_mask)(VirtIODevice *vdev, int n, bool mask); int (*start_ioeventfd)(VirtIODevice *vdev); void (*stop_ioeventfd)(VirtIODevice *vdev); - /* Called before loading queues. Useful to add queues before loading. */ - int (*pre_load_queues)(VirtIODevice *vdev); + /* + * Called before loading queues. + * If the number of queues change at runtime, use @n to know the + * number and add or remove queues accordingly. + * Note that this function is called in the middle of loading vmsd; + * no assumption should be made on states being loaded from vmsd. + */ + int (*pre_load_queues)(VirtIODevice *vdev, uint32_t n); /* Saving and loading of a device; trying to deprecate save/load * use vmsd for new devices. */ @@ -284,7 +294,6 @@ int virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes, unsigned int *out_bytes, unsigned max_in_bytes, unsigned max_out_bytes); -void virtio_notify_irqfd(VirtIODevice *vdev, VirtQueue *vq); void virtio_notify(VirtIODevice *vdev, VirtQueue *vq); int virtio_save(VirtIODevice *vdev, QEMUFile *f); @@ -366,6 +375,7 @@ void virtio_queue_reset(VirtIODevice *vdev, uint32_t queue_index); void virtio_queue_enable(VirtIODevice *vdev, uint32_t queue_index); void virtio_update_irq(VirtIODevice *vdev); int virtio_set_features(VirtIODevice *vdev, uint64_t val); +int virtio_set_features_ex(VirtIODevice *vdev, const uint64_t *val); /* Base devices. */ typedef struct VirtIOBlkConf VirtIOBlkConf; diff --git a/include/hw/xen/arch_hvm.h b/include/hw/xen/arch_hvm.h index df39c81..8bacaa4 100644 --- a/include/hw/xen/arch_hvm.h +++ b/include/hw/xen/arch_hvm.h @@ -1,5 +1,11 @@ -#if defined(TARGET_I386) || defined(TARGET_X86_64) -#include "hw/i386/xen_arch_hvm.h" -#elif defined(TARGET_ARM) || defined(TARGET_AARCH64) -#include "hw/arm/xen_arch_hvm.h" +#ifndef HW_XEN_ARCH_HVM_H +#define HW_XEN_ARCH_HVM_H + +#include <xen/hvm/ioreq.h> +#include "hw/xen/xen-hvm-common.h" + +void arch_handle_ioreq(XenIOState *state, ioreq_t *req); +void arch_xen_set_memory(XenIOState *state, + MemoryRegionSection *section, + bool add); #endif diff --git a/include/hw/xen/interface/hvm/params.h b/include/hw/xen/interface/hvm/params.h index a22b4ed..99c40b4 100644 --- a/include/hw/xen/interface/hvm/params.h +++ b/include/hw/xen/interface/hvm/params.h @@ -246,16 +246,11 @@ #define HVM_PARAM_VM_GENERATION_ID_ADDR 34 /* - * Set mode for altp2m: - * disabled: don't activate altp2m (default) + * Get mode for altp2m: + * disabled: altp2m not active (default) * mixed: allow access to all altp2m ops for both in-guest and external tools * external: allow access to external privileged tools only * limited: guest only has limited access (ie. control VMFUNC and #VE) - * - * Note that 'mixed' mode has not been evaluated for safety from a - * security perspective. Before using this mode in a - * security-critical environment, each subop should be evaluated for - * safety, with unsafe subops blacklisted in XSM. */ #define HVM_PARAM_ALTP2M 35 #define XEN_ALTP2M_disabled 0 diff --git a/include/hw/xen/interface/io/blkif.h b/include/hw/xen/interface/io/blkif.h index 22f1eef..c552799 100644 --- a/include/hw/xen/interface/io/blkif.h +++ b/include/hw/xen/interface/io/blkif.h @@ -324,7 +324,7 @@ * access (even when it should be read-only). If the frontend hits the * maximum number of allowed persistently mapped grants, it can fallback * to non persistent mode. This will cause a performance degradation, - * since the the backend driver will still try to map those grants + * since the backend driver will still try to map those grants * persistently. Since the persistent grants protocol is compatible with * the previous protocol, a frontend driver can choose to work in * persistent mode even when the backend doesn't support it. diff --git a/include/hw/xen/xen-pvh-common.h b/include/hw/xen/xen-pvh-common.h index 17c5a58..5db83d8 100644 --- a/include/hw/xen/xen-pvh-common.h +++ b/include/hw/xen/xen-pvh-common.h @@ -9,7 +9,7 @@ #ifndef XEN_PVH_COMMON_H__ #define XEN_PVH_COMMON_H__ -#include "exec/memory.h" +#include "system/memory.h" #include "qom/object.h" #include "hw/boards.h" #include "hw/pci-host/gpex.h" diff --git a/include/hw/xtensa/mx_pic.h b/include/hw/xtensa/mx_pic.h index 500424c..cd316d8 100644 --- a/include/hw/xtensa/mx_pic.h +++ b/include/hw/xtensa/mx_pic.h @@ -28,7 +28,7 @@ #ifndef XTENSA_MX_PIC_H #define XTENSA_MX_PIC_H -#include "exec/memory.h" +#include "system/memory.h" struct XtensaMxPic; typedef struct XtensaMxPic XtensaMxPic; diff --git a/include/io/channel-socket.h b/include/io/channel-socket.h index ab15577..a1ef313 100644 --- a/include/io/channel-socket.h +++ b/include/io/channel-socket.h @@ -49,6 +49,12 @@ struct QIOChannelSocket { socklen_t remoteAddrLen; ssize_t zero_copy_queued; ssize_t zero_copy_sent; + bool blocking; + /** + * This flag indicates whether any new data was successfully sent with + * zerocopy since the last qio_channel_socket_flush() call. + */ + bool new_zero_copy_sent_success; }; @@ -222,7 +228,7 @@ void qio_channel_socket_dgram_async(QIOChannelSocket *ioc, * release with a call qapi_free_SocketAddress() when no * longer required. * - * Returns: 0 on success, -1 on error + * Returns: the socket address struct, or NULL on error */ SocketAddress * qio_channel_socket_get_local_address(QIOChannelSocket *ioc, @@ -261,5 +267,18 @@ QIOChannelSocket * qio_channel_socket_accept(QIOChannelSocket *ioc, Error **errp); +/** + * qio_channel_socket_set_send_buffer: + * @ioc: the socket channel object + * @size: buffer size + * @errp: pointer to a NULL-initialized error object + * + * Set the underlying socket send buffer size. + * + * Retruns: 0 on success, or -1 on error. + */ +int qio_channel_socket_set_send_buffer(QIOChannelSocket *ioc, + size_t size, + Error **errp); #endif /* QIO_CHANNEL_SOCKET_H */ diff --git a/include/io/channel-websock.h b/include/io/channel-websock.h index e180827..6700cf8 100644 --- a/include/io/channel-websock.h +++ b/include/io/channel-websock.h @@ -61,7 +61,8 @@ struct QIOChannelWebsock { size_t payload_remain; size_t pong_remain; QIOChannelWebsockMask mask; - guint io_tag; + guint hs_io_tag; /* tracking handshake task */ + guint io_tag; /* tracking watch task */ Error *io_err; gboolean io_eof; uint8_t opcode; diff --git a/include/io/channel.h b/include/io/channel.h index 62b6571..f42be76 100644 --- a/include/io/channel.h +++ b/include/io/channel.h @@ -36,6 +36,7 @@ OBJECT_DECLARE_TYPE(QIOChannel, QIOChannelClass, #define QIO_CHANNEL_READ_FLAG_MSG_PEEK 0x1 #define QIO_CHANNEL_READ_FLAG_RELAXED_EOF 0x2 +#define QIO_CHANNEL_READ_FLAG_FD_PRESERVE_BLOCKING 0x4 typedef enum QIOChannelFeature QIOChannelFeature; @@ -46,6 +47,7 @@ enum QIOChannelFeature { QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY, QIO_CHANNEL_FEATURE_READ_MSG_PEEK, QIO_CHANNEL_FEATURE_SEEKABLE, + QIO_CHANNEL_FEATURE_CONCURRENT_IO, }; @@ -116,6 +118,15 @@ struct QIOChannelClass { size_t nfds, int flags, Error **errp); + + /* + * The io_readv handler must guarantee that all + * incoming fds are set BLOCKING (unless + * QIO_CHANNEL_READ_FLAG_FD_PRESERVE_BLOCKING flag is set) and + * CLOEXEC (if available). + * @fds and @nfds are set only on success path. Still, setting + * @fds and @nfds to zero is acceptable on failure path. + */ ssize_t (*io_readv)(QIOChannel *ioc, const struct iovec *iov, size_t niov, @@ -123,6 +134,7 @@ struct QIOChannelClass { size_t *nfds, int flags, Error **errp); + int (*io_close)(QIOChannel *ioc, Error **errp); GSource * (*io_create_watch)(QIOChannel *ioc, @@ -233,6 +245,13 @@ void qio_channel_set_name(QIOChannel *ioc, * was allocated. It is the callers responsibility * to call close() on each file descriptor and to * call g_free() on the array pointer in @fds. + * @fds allocated and set (and @nfds is set too) + * _only_ on success path. Still, @fds and @nfds + * may be set to zero on failure path. + * qio_channel_readv_full() guarantees that all + * incoming fds are set BLOCKING (unless + * QIO_CHANNEL_READ_FLAG_FD_PRESERVE_BLOCKING flag + * is set) and CLOEXEC (if available). * * It is an error to pass a non-NULL @fds parameter * unless qio_channel_has_feature() returns a true @@ -418,7 +437,7 @@ ssize_t qio_channel_writev(QIOChannel *ioc, * a single memory region. */ ssize_t qio_channel_read(QIOChannel *ioc, - char *buf, + void *buf, size_t buflen, Error **errp); @@ -434,7 +453,7 @@ ssize_t qio_channel_read(QIOChannel *ioc, * single memory region. */ ssize_t qio_channel_write(QIOChannel *ioc, - const char *buf, + const void *buf, size_t buflen, Error **errp); @@ -456,7 +475,7 @@ ssize_t qio_channel_write(QIOChannel *ioc, * without data, or -1 on error */ int coroutine_mixed_fn qio_channel_read_all_eof(QIOChannel *ioc, - char *buf, + void *buf, size_t buflen, Error **errp); @@ -476,7 +495,7 @@ int coroutine_mixed_fn qio_channel_read_all_eof(QIOChannel *ioc, * Returns: 0 if all bytes were read, or -1 on error */ int coroutine_mixed_fn qio_channel_read_all(QIOChannel *ioc, - char *buf, + void *buf, size_t buflen, Error **errp); @@ -495,7 +514,7 @@ int coroutine_mixed_fn qio_channel_read_all(QIOChannel *ioc, * Returns: 0 if all bytes were written, or -1 on error */ int coroutine_mixed_fn qio_channel_write_all(QIOChannel *ioc, - const char *buf, + const void *buf, size_t buflen, Error **errp); @@ -512,9 +531,9 @@ int coroutine_mixed_fn qio_channel_write_all(QIOChannel *ioc, * return QIO_CHANNEL_ERR_BLOCK if they would otherwise * block on I/O */ -int qio_channel_set_blocking(QIOChannel *ioc, - bool enabled, - Error **errp); +bool qio_channel_set_blocking(QIOChannel *ioc, + bool enabled, + Error **errp); /** * qio_channel_set_follow_coroutine_ctx: @@ -576,7 +595,7 @@ ssize_t qio_channel_pwritev(QIOChannel *ioc, const struct iovec *iov, * flag QIO_CHANNEL_FEATURE_SEEKABLE prior to calling this method. * */ -ssize_t qio_channel_pwrite(QIOChannel *ioc, char *buf, size_t buflen, +ssize_t qio_channel_pwrite(QIOChannel *ioc, void *buf, size_t buflen, off_t offset, Error **errp); /** @@ -612,7 +631,7 @@ ssize_t qio_channel_preadv(QIOChannel *ioc, const struct iovec *iov, * flag QIO_CHANNEL_FEATURE_SEEKABLE prior to calling this method. * */ -ssize_t qio_channel_pread(QIOChannel *ioc, char *buf, size_t buflen, +ssize_t qio_channel_pread(QIOChannel *ioc, void *buf, size_t buflen, off_t offset, Error **errp); /** @@ -853,6 +872,21 @@ void qio_channel_wait(QIOChannel *ioc, GIOCondition condition); /** + * qio_channel_wait_cond: + * @ioc: the channel object + * @condition: the I/O condition to wait for + * + * Block execution from the current thread until + * the condition indicated by @condition becomes + * available. + * + * This will work with/without a coroutine context, by automatically select + * the proper API to wait. + */ +void qio_channel_wait_cond(QIOChannel *ioc, + GIOCondition condition); + +/** * qio_channel_set_aio_fd_handler: * @ioc: the channel object * @read_ctx: the AioContext to set the read handler on or NULL diff --git a/include/io/net-listener.h b/include/io/net-listener.h index ab9f291..fdc5f1c 100644 --- a/include/io/net-listener.h +++ b/include/io/net-listener.h @@ -28,6 +28,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(QIONetListener, QIO_NET_LISTENER) +typedef struct QIONetListenerSource QIONetListenerSource; typedef void (*QIONetListenerClientFunc)(QIONetListener *listener, QIOChannelSocket *sioc, @@ -47,12 +48,15 @@ struct QIONetListener { Object parent; char *name; - QIOChannelSocket **sioc; - GSource **io_source; + QIONetListenerSource **source; size_t nsioc; + /* At most one of context or aio_context will be set */ + GMainContext *context; + AioContext *aio_context; bool connected; + QemuMutex lock; /* Protects remaining fields */ QIONetListenerClientFunc io_func; gpointer io_data; GDestroyNotify io_notify; @@ -149,6 +153,27 @@ void qio_net_listener_set_client_func(QIONetListener *listener, GDestroyNotify notify); /** + * qio_net_listener_set_client_aio_func: + * @listener: the network listener object + * @func: the callback function + * @data: opaque data to pass to @func + * @context: AioContext that @func will be bound to; if NULL, this will + * will use qemu_get_aio_context(). + * + * Similar to qio_net_listener_set_client_func_full(), except that the polling + * will be done by an AioContext rather than a GMainContext. + * + * Because AioContext does not (yet) support a clean way to deregister + * a callback from one thread while another thread might be in that + * callback, this function is only safe to call from the thread + * currently associated with @context. + */ +void qio_net_listener_set_client_aio_func(QIONetListener *listener, + QIONetListenerClientFunc func, + void *data, + AioContext *context); + +/** * qio_net_listener_wait_client: * @listener: the network listener object * @@ -183,4 +208,46 @@ void qio_net_listener_disconnect(QIONetListener *listener); */ bool qio_net_listener_is_connected(QIONetListener *listener); + +/** + * qio_net_listener_nsioc: + * @listener: the network listener object + * + * Determine the number of listener channels currently owned by the + * given listener. + * + * Returns: number of channels, or 0 if not listening + */ +size_t qio_net_listener_nsioc(QIONetListener *listener); + + +/** + * qio_net_listener_sioc: + * @listener: the network listener object + * @n: index of the sioc to grab + * + * Accessor for the nth sioc owned by the listener. + * + * Returns: the requested listener, or NULL if not in bounds + */ +QIOChannelSocket *qio_net_listener_sioc(QIONetListener *listener, size_t n); + +/** + * qio_net_listener_get_local_address: + * @listener: the network listener object + * @n: index of the sioc to grab + * @errp: pointer to a NULL-initialized error object + * + * Get the string representation of the local socket + * address. A pointer to the allocated address information + * struct will be returned, which the caller is required to + * release with a call qapi_free_SocketAddress() when no + * longer required. + * + * Returns: the socket address struct, or NULL on error + */ +SocketAddress * +qio_net_listener_get_local_address(QIONetListener *listener, size_t n, + Error **errp); + #endif /* QIO_NET_LISTENER_H */ diff --git a/include/libdecnumber/dconfig.h b/include/libdecnumber/dconfig.h index 2bc0ba7f..e67ecc1 100644 --- a/include/libdecnumber/dconfig.h +++ b/include/libdecnumber/dconfig.h @@ -23,9 +23,8 @@ for more details. You should have received a copy of the GNU General Public License - along with GCC; see the file COPYING. If not, write to the Free - Software Foundation, 51 Franklin Street, Fifth Floor, Boston, MA - 02110-1301, USA. */ + along with GCC; see the file COPYING. If not, see + <https://www.gnu.org/licenses/>. */ #if HOST_BIG_ENDIAN diff --git a/include/libdecnumber/decContext.h b/include/libdecnumber/decContext.h index cea6e42..5bb64e1 100644 --- a/include/libdecnumber/decContext.h +++ b/include/libdecnumber/decContext.h @@ -24,9 +24,8 @@ for more details. You should have received a copy of the GNU General Public License - along with GCC; see the file COPYING. If not, write to the Free - Software Foundation, 51 Franklin Street, Fifth Floor, Boston, MA - 02110-1301, USA. */ + along with GCC; see the file COPYING. If not, see + <https://www.gnu.org/licenses/>. */ /* ------------------------------------------------------------------ */ /* Decimal Context module header */ diff --git a/include/libdecnumber/decDPD.h b/include/libdecnumber/decDPD.h index 26a21ec..8eb4552 100644 --- a/include/libdecnumber/decDPD.h +++ b/include/libdecnumber/decDPD.h @@ -24,9 +24,8 @@ for more details. You should have received a copy of the GNU General Public License - along with GCC; see the file COPYING. If not, write to the Free - Software Foundation, 51 Franklin Street, Fifth Floor, Boston, MA - 02110-1301, USA. */ + along with GCC; see the file COPYING. If not, see + <https://www.gnu.org/licenses/>. */ /* ------------------------------------------------------------------------ */ /* Binary Coded Decimal and Densely Packed Decimal conversion lookup tables */ diff --git a/include/libdecnumber/decNumber.h b/include/libdecnumber/decNumber.h index 41bc2a0..bf37af8 100644 --- a/include/libdecnumber/decNumber.h +++ b/include/libdecnumber/decNumber.h @@ -24,9 +24,8 @@ for more details. You should have received a copy of the GNU General Public License - along with GCC; see the file COPYING. If not, write to the Free - Software Foundation, 51 Franklin Street, Fifth Floor, Boston, MA - 02110-1301, USA. */ + along with GCC; see the file COPYING. If not, see + <https://www.gnu.org/licenses/>. */ /* ------------------------------------------------------------------ */ /* Decimal Number arithmetic module header */ diff --git a/include/libdecnumber/decNumberLocal.h b/include/libdecnumber/decNumberLocal.h index 6198ca8..0959f66 100644 --- a/include/libdecnumber/decNumberLocal.h +++ b/include/libdecnumber/decNumberLocal.h @@ -24,9 +24,8 @@ for more details. You should have received a copy of the GNU General Public License - along with GCC; see the file COPYING. If not, write to the Free - Software Foundation, 51 Franklin Street, Fifth Floor, Boston, MA - 02110-1301, USA. */ + along with GCC; see the file COPYING. If not, see + <https://www.gnu.org/licenses/>. */ /* ------------------------------------------------------------------ */ /* decNumber package local type, tuning, and macro definitions */ diff --git a/include/libdecnumber/dpd/decimal128.h b/include/libdecnumber/dpd/decimal128.h index aff261e..c57180b 100644 --- a/include/libdecnumber/dpd/decimal128.h +++ b/include/libdecnumber/dpd/decimal128.h @@ -24,9 +24,8 @@ for more details. You should have received a copy of the GNU General Public License - along with GCC; see the file COPYING. If not, write to the Free - Software Foundation, 51 Franklin Street, Fifth Floor, Boston, MA - 02110-1301, USA. */ + along with GCC; see the file COPYING. If not, see + <https://www.gnu.org/licenses/>. */ /* ------------------------------------------------------------------ */ /* Decimal 128-bit format module header */ diff --git a/include/libdecnumber/dpd/decimal128Local.h b/include/libdecnumber/dpd/decimal128Local.h index 9765427..2948ab2 100644 --- a/include/libdecnumber/dpd/decimal128Local.h +++ b/include/libdecnumber/dpd/decimal128Local.h @@ -23,9 +23,8 @@ for more details. You should have received a copy of the GNU General Public License - along with GCC; see the file COPYING. If not, write to the Free - Software Foundation, 51 Franklin Street, Fifth Floor, Boston, MA - 02110-1301, USA. */ + along with GCC; see the file COPYING. If not, see + <https://www.gnu.org/licenses/>. */ #if !defined(DECIMAL128LOCAL) diff --git a/include/libdecnumber/dpd/decimal32.h b/include/libdecnumber/dpd/decimal32.h index 6cb9e43..9a17933 100644 --- a/include/libdecnumber/dpd/decimal32.h +++ b/include/libdecnumber/dpd/decimal32.h @@ -24,9 +24,8 @@ for more details. You should have received a copy of the GNU General Public License - along with GCC; see the file COPYING. If not, write to the Free - Software Foundation, 51 Franklin Street, Fifth Floor, Boston, MA - 02110-1301, USA. */ + along with GCC; see the file COPYING. If not, see + <https://www.gnu.org/licenses/>. */ /* ------------------------------------------------------------------ */ /* Decimal 32-bit format module header */ diff --git a/include/libdecnumber/dpd/decimal64.h b/include/libdecnumber/dpd/decimal64.h index f29e570..5c3d0bb 100644 --- a/include/libdecnumber/dpd/decimal64.h +++ b/include/libdecnumber/dpd/decimal64.h @@ -24,9 +24,8 @@ for more details. You should have received a copy of the GNU General Public License - along with GCC; see the file COPYING. If not, write to the Free - Software Foundation, 51 Franklin Street, Fifth Floor, Boston, MA - 02110-1301, USA. */ + along with GCC; see the file COPYING. If not, see + <https://www.gnu.org/licenses/>. */ /* ------------------------------------------------------------------ */ /* Decimal 64-bit format module header */ diff --git a/include/migration/blocker.h b/include/migration/blocker.h index a687ac0..80b75ad 100644 --- a/include/migration/blocker.h +++ b/include/migration/blocker.h @@ -16,8 +16,6 @@ #include "qapi/qapi-types-migration.h" -#define MIG_MODE_ALL MIG_MODE__MAX - /** * @migrate_add_blocker - prevent all modes of migration from proceeding * @@ -82,16 +80,15 @@ int migrate_add_blocker_normal(Error **reasonp, Error **errp); * * @reasonp - address of an error to be returned whenever migration is attempted * - * @errp - [out] The reason (if any) we cannot block migration right now. + * @modes - the migration modes to be blocked, a bit set of MigMode * - * @mode - one or more migration modes to be blocked. The list is terminated - * by -1 or MIG_MODE_ALL. For the latter, all modes are blocked. + * @errp - [out] The reason (if any) we cannot block migration right now. * * @returns - 0 on success, -EBUSY/-EACCES on failure, with errp set. * * *@reasonp is freed and set to NULL if failure is returned. * On success, the caller must not free *@reasonp before the blocker is removed. */ -int migrate_add_blocker_modes(Error **reasonp, Error **errp, MigMode mode, ...); +int migrate_add_blocker_modes(Error **reasonp, unsigned modes, Error **errp); #endif diff --git a/include/migration/colo.h b/include/migration/colo.h index 43222ef..d4fe422 100644 --- a/include/migration/colo.h +++ b/include/migration/colo.h @@ -25,7 +25,7 @@ void migrate_start_colo_process(MigrationState *s); bool migration_in_colo_state(void); /* loadvm */ -int migration_incoming_enable_colo(void); +int migration_incoming_enable_colo(Error **errp); void migration_incoming_disable_colo(void); bool migration_incoming_colo_enabled(void); bool migration_incoming_in_colo_state(void); diff --git a/include/migration/cpr.h b/include/migration/cpr.h index 7561fc7..027cb98 100644 --- a/include/migration/cpr.h +++ b/include/migration/cpr.h @@ -9,26 +9,55 @@ #define MIGRATION_CPR_H #include "qapi/qapi-types-migration.h" +#include "qemu/queue.h" #define MIG_MODE_NONE -1 #define QEMU_CPR_FILE_MAGIC 0x51435052 #define QEMU_CPR_FILE_VERSION 0x00000001 +#define CPR_STATE "CprState" + +typedef QLIST_HEAD(CprFdList, CprFd) CprFdList; +typedef QLIST_HEAD(CprVFIODeviceList, CprVFIODevice) CprVFIODeviceList; + +typedef struct CprState { + CprFdList fds; + CprVFIODeviceList vfio_devices; +} CprState; + +extern CprState cpr_state; void cpr_save_fd(const char *name, int id, int fd); void cpr_delete_fd(const char *name, int id); int cpr_find_fd(const char *name, int id); +void cpr_resave_fd(const char *name, int id, int fd); +int cpr_open_fd(const char *path, int flags, const char *name, int id, + Error **errp); + +typedef bool (*cpr_walk_fd_cb)(int fd); +bool cpr_walk_fd(cpr_walk_fd_cb cb); MigMode cpr_get_incoming_mode(void); void cpr_set_incoming_mode(MigMode mode); bool cpr_is_incoming(void); -int cpr_state_save(MigrationChannel *channel, Error **errp); +bool cpr_state_save(MigrationChannel *channel, Error **errp); int cpr_state_load(MigrationChannel *channel, Error **errp); void cpr_state_close(void); struct QIOChannel *cpr_state_ioc(void); +bool cpr_incoming_needed(void *opaque); +int cpr_get_fd_param(const char *name, const char *fdname, int index, + Error **errp); + QEMUFile *cpr_transfer_output(MigrationChannel *channel, Error **errp); QEMUFile *cpr_transfer_input(MigrationChannel *channel, Error **errp); +void cpr_exec_init(void); +QEMUFile *cpr_exec_output(Error **errp); +QEMUFile *cpr_exec_input(Error **errp); +bool cpr_exec_persist_state(QEMUFile *f, Error **errp); +bool cpr_exec_has_state(void); +void cpr_exec_unpersist_state(void); +void cpr_exec_unpreserve_fds(void); #endif diff --git a/include/migration/cpu.h b/include/migration/cpu.h index 65abe3c..ca7cc04 100644 --- a/include/migration/cpu.h +++ b/include/migration/cpu.h @@ -19,8 +19,6 @@ #define VMSTATE_UINTTL_V(_f, _s, _v) \ VMSTATE_UINT64_V(_f, _s, _v) -#define VMSTATE_UINTTL_EQUAL_V(_f, _s, _v) \ - VMSTATE_UINT64_EQUAL_V(_f, _s, _v) #define VMSTATE_UINTTL_ARRAY_V(_f, _s, _n, _v) \ VMSTATE_UINT64_ARRAY_V(_f, _s, _n, _v) #define VMSTATE_UINTTL_2DARRAY_V(_f, _s, _n1, _n2, _v) \ @@ -40,8 +38,6 @@ #define VMSTATE_UINTTL_V(_f, _s, _v) \ VMSTATE_UINT32_V(_f, _s, _v) -#define VMSTATE_UINTTL_EQUAL_V(_f, _s, _v) \ - VMSTATE_UINT32_EQUAL_V(_f, _s, _v) #define VMSTATE_UINTTL_ARRAY_V(_f, _s, _n, _v) \ VMSTATE_UINT32_ARRAY_V(_f, _s, _n, _v) #define VMSTATE_UINTTL_2DARRAY_V(_f, _s, _n1, _n2, _v) \ @@ -53,8 +49,6 @@ #define VMSTATE_UINTTL(_f, _s) \ VMSTATE_UINTTL_V(_f, _s, 0) -#define VMSTATE_UINTTL_EQUAL(_f, _s) \ - VMSTATE_UINTTL_EQUAL_V(_f, _s, 0) #define VMSTATE_UINTTL_ARRAY(_f, _s, _n) \ VMSTATE_UINTTL_ARRAY_V(_f, _s, _n, 0) #define VMSTATE_UINTTL_2DARRAY(_f, _s, _n1, _n2) \ diff --git a/include/migration/misc.h b/include/migration/misc.h index 8fd36eb..e26d418 100644 --- a/include/migration/misc.h +++ b/include/migration/misc.h @@ -90,12 +90,24 @@ void migration_add_notifier(NotifierWithReturn *notify, MigrationNotifyFunc func); /* - * Same as migration_add_notifier, but applies to be specified @mode. + * Same as migration_add_notifier, but applies to the specified @mode + * instead of MIG_MODE_NORMAL. */ void migration_add_notifier_mode(NotifierWithReturn *notify, MigrationNotifyFunc func, MigMode mode); +/* + * Same as migration_add_notifier, but applies to the specified @modes + * (a bitset of MigMode). + */ +void migration_add_notifier_modes(NotifierWithReturn *notify, + MigrationNotifyFunc func, unsigned modes); + +/* + * Remove a notifier from all modes. + */ void migration_remove_notifier(NotifierWithReturn *notify); + void migration_file_set_error(int ret, Error *err); /* True if incoming migration entered POSTCOPY_INCOMING_DISCARD */ @@ -119,19 +131,19 @@ bool migrate_uri_parse(const char *uri, MigrationChannel **channel, Error **errp); /* migration/multifd-device-state.c */ -typedef struct SaveLiveCompletePrecopyThreadData { - SaveLiveCompletePrecopyThreadHandler hdlr; +typedef struct SaveCompletePrecopyThreadData { + SaveCompletePrecopyThreadHandler hdlr; char *idstr; uint32_t instance_id; void *handler_opaque; -} SaveLiveCompletePrecopyThreadData; +} SaveCompletePrecopyThreadData; bool multifd_queue_device_state(char *idstr, uint32_t instance_id, char *data, size_t len); bool multifd_device_state_supported(void); void -multifd_spawn_device_state_save_thread(SaveLiveCompletePrecopyThreadHandler hdlr, +multifd_spawn_device_state_save_thread(SaveCompletePrecopyThreadHandler hdlr, char *idstr, uint32_t instance_id, void *opaque); diff --git a/include/migration/register.h b/include/migration/register.h index c041ce3..ae79794 100644 --- a/include/migration/register.h +++ b/include/migration/register.h @@ -78,51 +78,43 @@ typedef struct SaveVMHandlers { void (*save_cleanup)(void *opaque); /** - * @save_live_complete_postcopy + * @save_complete * - * Called at the end of postcopy for all postcopyable devices. + * Transmits the last section for the device containing any + * remaining data at the end phase of migration. * - * @f: QEMUFile where to send the data - * @opaque: data pointer passed to register_savevm_live() + * For precopy, this will be invoked _during_ the switchover phase + * after source VM is stopped. * - * Returns zero to indicate success and negative for error - */ - int (*save_live_complete_postcopy)(QEMUFile *f, void *opaque); - - /** - * @save_live_complete_precopy - * - * Transmits the last section for the device containing any - * remaining data at the end of a precopy phase. When postcopy is - * enabled, devices that support postcopy will skip this step, - * where the final data will be flushed at the end of postcopy via - * @save_live_complete_postcopy instead. + * For postcopy, this will be invoked _after_ the switchover phase + * (except some very unusual cases, like PMEM ramblocks), while + * destination VM can be running. * * @f: QEMUFile where to send the data * @opaque: data pointer passed to register_savevm_live() * * Returns zero to indicate success and negative for error */ - int (*save_live_complete_precopy)(QEMUFile *f, void *opaque); + int (*save_complete)(QEMUFile *f, void *opaque); /** - * @save_live_complete_precopy_thread (invoked in a separate thread) + * @save_complete_precopy_thread (invoked in a separate thread) * * Called at the end of a precopy phase from a separate worker thread * in configurations where multifd device state transfer is supported * in order to perform asynchronous transmission of the remaining data in - * parallel with @save_live_complete_precopy handlers. + * parallel with @save_complete handlers. * When postcopy is enabled, devices that support postcopy will skip this * step. * - * @d: a #SaveLiveCompletePrecopyThreadData containing parameters that the + * @d: a #SaveCompletePrecopyThreadData containing parameters that the * handler may need, including this device section idstr and instance_id, * and opaque data pointer passed to register_savevm_live(). * @errp: pointer to Error*, to store an error if it happens. * * Returns true to indicate success and false for errors. */ - SaveLiveCompletePrecopyThreadHandler save_live_complete_precopy_thread; + SaveCompletePrecopyThreadHandler save_complete_precopy_thread; /* This runs both outside and inside the BQL. */ @@ -190,6 +182,21 @@ typedef struct SaveVMHandlers { /* This runs outside the BQL! */ /** + * @save_postcopy_prepare + * + * This hook will be invoked on the source side right before switching + * to postcopy (before VM stopped). + * + * @f: QEMUFile where to send the data + * @opaque: Data pointer passed to register_savevm_live() + * @errp: Error** used to report error message + * + * Returns: true if succeeded, false if error occured. When false is + * returned, @errp must be set. + */ + bool (*save_postcopy_prepare)(QEMUFile *f, void *opaque, Error **errp); + + /** * @state_pending_estimate * * This estimates the remaining data to transfer diff --git a/include/migration/vmstate.h b/include/migration/vmstate.h index a1dfab4..a87a5ef 100644 --- a/include/migration/vmstate.h +++ b/include/migration/vmstate.h @@ -155,10 +155,15 @@ enum VMStateFlags { }; typedef enum { - MIG_PRI_DEFAULT = 0, + MIG_PRI_UNINITIALIZED = 0, /* An uninitialized priority field maps to */ + /* MIG_PRI_DEFAULT in save_state_priority */ + + MIG_PRI_LOW, /* Must happen after default */ + MIG_PRI_DEFAULT, MIG_PRI_IOMMU, /* Must happen before PCI devices */ MIG_PRI_PCI_BUS, /* Must happen before IOMMU */ MIG_PRI_VIRTIO_MEM, /* Must happen before IOMMU */ + MIG_PRI_APIC, /* Must happen before PCI devices */ MIG_PRI_GICV3_ITS, /* Must happen before PCI devices */ MIG_PRI_GICV3, /* Must happen before the ITS */ MIG_PRI_MAX, @@ -196,14 +201,28 @@ struct VMStateDescription { * exclusive. For this reason, also early_setup VMSDs are migrated in a * QEMU_VM_SECTION_FULL section, while save_setup() data is migrated in * a QEMU_VM_SECTION_START section. + * + * There are duplicate impls of the post/pre save/load hooks. + * New impls should preferentally use 'errp' variants of these + * methods and existing impls incrementally converted. + * The variants without 'errp' are intended to be removed + * once all usage is converted. + * + * For the errp variants, + * Returns: 0 on success, + * <0 on error where -value is an error number from errno.h */ + bool early_setup; int version_id; int minimum_version_id; MigrationPriority priority; int (*pre_load)(void *opaque); + bool (*pre_load_errp)(void *opaque, Error **errp); int (*post_load)(void *opaque, int version_id); + bool (*post_load_errp)(void *opaque, int version_id, Error **errp); int (*pre_save)(void *opaque); + bool (*pre_save_errp)(void *opaque, Error **errp); int (*post_save)(void *opaque); bool (*needed)(void *opaque); bool (*dev_unplug_pending)(void *opaque); @@ -518,6 +537,16 @@ extern const VMStateInfo vmstate_info_qlist; .offset = vmstate_offset_array(_s, _f, _type*, _n), \ } +#define VMSTATE_VARRAY_OF_POINTER_UINT32(_field, _state, _field_num, _version, _info, _type) { \ + .name = (stringify(_field)), \ + .version_id = (_version), \ + .num_offset = vmstate_offset_value(_state, _field_num, uint32_t), \ + .info = &(_info), \ + .size = sizeof(_type), \ + .flags = VMS_VARRAY_UINT32 | VMS_ARRAY_OF_POINTER | VMS_POINTER, \ + .offset = vmstate_offset_pointer(_state, _field, _type), \ +} + #define VMSTATE_STRUCT_SUB_ARRAY(_field, _state, _start, _num, _version, _vmsd, _type) { \ .name = (stringify(_field)), \ .version_id = (_version), \ @@ -703,7 +732,7 @@ extern const VMStateInfo vmstate_info_qlist; .version_id = (_version), \ .size = (_size), \ .info = &vmstate_info_buffer, \ - .flags = VMS_BUFFER|VMS_POINTER, \ + .flags = VMS_BUFFER | VMS_POINTER, \ .offset = offsetof(_state, _field), \ } @@ -1192,10 +1221,8 @@ extern const VMStateInfo vmstate_info_qlist; } int vmstate_load_state(QEMUFile *f, const VMStateDescription *vmsd, - void *opaque, int version_id); + void *opaque, int version_id, Error **errp); int vmstate_save_state(QEMUFile *f, const VMStateDescription *vmsd, - void *opaque, JSONWriter *vmdesc); -int vmstate_save_state_with_err(QEMUFile *f, const VMStateDescription *vmsd, void *opaque, JSONWriter *vmdesc, Error **errp); int vmstate_save_state_v(QEMUFile *f, const VMStateDescription *vmsd, void *opaque, JSONWriter *vmdesc, diff --git a/include/monitor/hmp.h b/include/monitor/hmp.h index ae116d9..83721b5 100644 --- a/include/monitor/hmp.h +++ b/include/monitor/hmp.h @@ -24,6 +24,7 @@ strList *hmp_split_at_comma(const char *str); void hmp_info_name(Monitor *mon, const QDict *qdict); void hmp_info_version(Monitor *mon, const QDict *qdict); void hmp_info_kvm(Monitor *mon, const QDict *qdict); +void hmp_info_accelerators(Monitor *mon, const QDict *qdict); void hmp_info_status(Monitor *mon, const QDict *qdict); void hmp_info_uuid(Monitor *mon, const QDict *qdict); void hmp_info_chardev(Monitor *mon, const QDict *qdict); @@ -178,5 +179,6 @@ void hmp_boot_set(Monitor *mon, const QDict *qdict); void hmp_info_mtree(Monitor *mon, const QDict *qdict); void hmp_info_cryptodev(Monitor *mon, const QDict *qdict); void hmp_dumpdtb(Monitor *mon, const QDict *qdict); +void hmp_info_firmware_log(Monitor *mon, const QDict *qdict); #endif diff --git a/include/monitor/qdev.h b/include/monitor/qdev.h index 1d57bf6..de33637 100644 --- a/include/monitor/qdev.h +++ b/include/monitor/qdev.h @@ -1,6 +1,8 @@ #ifndef MONITOR_QDEV_H #define MONITOR_QDEV_H +#include "hw/qdev-core.h" + /*** monitor commands ***/ void hmp_info_qtree(Monitor *mon, const QDict *qdict); @@ -11,6 +13,7 @@ int qdev_device_help(QemuOpts *opts); DeviceState *qdev_device_add(QemuOpts *opts, Error **errp); DeviceState *qdev_device_add_from_qdict(const QDict *opts, bool from_json, Error **errp); +BusState *qdev_find_default_bus(DeviceClass *dc, Error **errp); /** * qdev_set_id: parent the device and set its id if provided. diff --git a/include/net/can_emu.h b/include/net/can_emu.h index 6f9b206..777281b 100644 --- a/include/net/can_emu.h +++ b/include/net/can_emu.h @@ -85,7 +85,9 @@ typedef struct qemu_can_filter { #define QEMU_CAN_INV_FILTER 0x20000000U typedef struct CanBusClientState CanBusClientState; -typedef struct CanBusState CanBusState; + +#define TYPE_CAN_BUS "can-bus" +OBJECT_DECLARE_SIMPLE_TYPE(CanBusState, CAN_BUS) typedef struct CanBusClientInfo { bool (*can_receive)(CanBusClientState *); @@ -105,9 +107,6 @@ struct CanBusClientState { bool fd_mode; }; -#define TYPE_CAN_BUS "can-bus" -OBJECT_DECLARE_SIMPLE_TYPE(CanBusState, CAN_BUS) - int can_bus_filter_match(struct qemu_can_filter *filter, qemu_canid_t can_id); int can_bus_insert_client(CanBusState *bus, CanBusClientState *client); diff --git a/include/net/net.h b/include/net/net.h index cdd5b10..72b476e 100644 --- a/include/net/net.h +++ b/include/net/net.h @@ -35,6 +35,18 @@ typedef struct NICConf { int32_t bootindex; } NICConf; +typedef struct NetOffloads { + bool csum; + bool tso4; + bool tso6; + bool ecn; + bool ufo; + bool uso4; + bool uso6; + bool tnl; + bool tnl_csum; +} NetOffloads; + #define DEFINE_NIC_PROPERTIES(_state, _conf) \ DEFINE_PROP_MACADDR("mac", _state, _conf.macaddr), \ DEFINE_PROP_NETDEV("netdev", _state, _conf.peers) @@ -55,11 +67,13 @@ typedef void (NetClientDestructor)(NetClientState *); typedef RxFilterInfo *(QueryRxFilter)(NetClientState *); typedef bool (HasUfo)(NetClientState *); typedef bool (HasUso)(NetClientState *); +typedef bool (HasTunnel)(NetClientState *); typedef bool (HasVnetHdr)(NetClientState *); typedef bool (HasVnetHdrLen)(NetClientState *, int); -typedef void (SetOffload)(NetClientState *, int, int, int, int, int, int, int); +typedef void (SetOffload)(NetClientState *, const NetOffloads *); typedef int (GetVnetHdrLen)(NetClientState *); typedef void (SetVnetHdrLen)(NetClientState *, int); +typedef bool (GetVnetHashSupportedTypes)(NetClientState *, uint32_t *); typedef int (SetVnetLE)(NetClientState *, bool); typedef int (SetVnetBE)(NetClientState *, bool); typedef struct SocketReadState SocketReadState; @@ -67,6 +81,7 @@ typedef void (SocketReadStateFinalize)(SocketReadState *rs); typedef void (NetAnnounce)(NetClientState *); typedef bool (SetSteeringEBPF)(NetClientState *, int); typedef bool (NetCheckPeerType)(NetClientState *, ObjectClass *, Error **); +typedef struct vhost_net *(GetVHostNet)(NetClientState *nc); typedef struct NetClientInfo { NetClientDriver type; @@ -83,15 +98,18 @@ typedef struct NetClientInfo { NetPoll *poll; HasUfo *has_ufo; HasUso *has_uso; + HasTunnel *has_tunnel; HasVnetHdr *has_vnet_hdr; HasVnetHdrLen *has_vnet_hdr_len; SetOffload *set_offload; SetVnetHdrLen *set_vnet_hdr_len; SetVnetLE *set_vnet_le; SetVnetBE *set_vnet_be; + GetVnetHashSupportedTypes *get_vnet_hash_supported_types; NetAnnounce *announce; SetSteeringEBPF *set_steering_ebpf; NetCheckPeerType *check_peer_type; + GetVHostNet *get_vhost_net; } NetClientInfo; struct NetClientState { @@ -183,12 +201,13 @@ void qemu_set_info_str(NetClientState *nc, void qemu_format_nic_info_str(NetClientState *nc, uint8_t macaddr[6]); bool qemu_has_ufo(NetClientState *nc); bool qemu_has_uso(NetClientState *nc); +bool qemu_has_tunnel(NetClientState *nc); bool qemu_has_vnet_hdr(NetClientState *nc); bool qemu_has_vnet_hdr_len(NetClientState *nc, int len); -void qemu_set_offload(NetClientState *nc, int csum, int tso4, int tso6, - int ecn, int ufo, int uso4, int uso6); +void qemu_set_offload(NetClientState *nc, const NetOffloads *ol); int qemu_get_vnet_hdr_len(NetClientState *nc); void qemu_set_vnet_hdr_len(NetClientState *nc, int len); +bool qemu_get_vnet_hash_supported_types(NetClientState *nc, uint32_t *types); int qemu_set_vnet_le(NetClientState *nc, bool is_le); int qemu_set_vnet_be(NetClientState *nc, bool is_be); void qemu_macaddr_default_if_unset(MACAddr *macaddr); @@ -298,6 +317,7 @@ void net_client_parse(QemuOptsList *opts_list, const char *optstr); void show_netdevs(void); void net_init_clients(void); void net_check_clients(void); +void net_client_set_link(NetClientState **ncs, int queues, bool up); void net_cleanup(void); void hmp_host_net_add(Monitor *mon, const QDict *qdict); void hmp_host_net_remove(Monitor *mon, const QDict *qdict); diff --git a/include/net/tap.h b/include/net/tap.h index 5d58551..6f34f13 100644 --- a/include/net/tap.h +++ b/include/net/tap.h @@ -33,7 +33,4 @@ int tap_disable(NetClientState *nc); int tap_get_fd(NetClientState *nc); -struct vhost_net; -struct vhost_net *tap_get_vhost_net(NetClientState *nc); - #endif /* QEMU_NET_TAP_H */ diff --git a/include/net/vhost-user.h b/include/net/vhost-user.h deleted file mode 100644 index 35bf619..0000000 --- a/include/net/vhost-user.h +++ /dev/null @@ -1,19 +0,0 @@ -/* - * vhost-user.h - * - * Copyright (c) 2013 Virtual Open Systems Sarl. - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#ifndef VHOST_USER_H -#define VHOST_USER_H - -struct vhost_net; -struct vhost_net *vhost_user_get_vhost_net(NetClientState *nc); -uint64_t vhost_user_get_acked_features(NetClientState *nc); -void vhost_user_save_acked_features(NetClientState *nc); - -#endif /* VHOST_USER_H */ diff --git a/include/net/vhost-vdpa.h b/include/net/vhost-vdpa.h index b81f9a6..f8d7d6c 100644 --- a/include/net/vhost-vdpa.h +++ b/include/net/vhost-vdpa.h @@ -14,8 +14,4 @@ #define TYPE_VHOST_VDPA "vhost-vdpa" -struct vhost_net *vhost_vdpa_get_vhost_net(NetClientState *nc); - -extern const int vdpa_feature_bits[]; - #endif /* VHOST_VDPA_H */ diff --git a/include/net/vhost_net.h b/include/net/vhost_net.h index c6a5361..0225207 100644 --- a/include/net/vhost_net.h +++ b/include/net/vhost_net.h @@ -2,16 +2,25 @@ #define VHOST_NET_H #include "net/net.h" +#include "hw/virtio/virtio-features.h" #include "hw/virtio/vhost-backend.h" struct vhost_net; typedef struct vhost_net VHostNetState; +typedef uint64_t (GetAckedFeatures)(NetClientState *nc); +typedef void (SaveAcketFeatures)(NetClientState *nc); + typedef struct VhostNetOptions { VhostBackendType backend_type; NetClientState *net_backend; uint32_t busyloop_timeout; unsigned int nvqs; + const int *feature_bits; + int max_tx_queue_size; + bool is_vhost_user; + GetAckedFeatures *get_acked_features; + SaveAcketFeatures *save_acked_features; void *opaque; } VhostNetOptions; @@ -25,8 +34,26 @@ void vhost_net_stop(VirtIODevice *dev, NetClientState *ncs, void vhost_net_cleanup(VHostNetState *net); -uint64_t vhost_net_get_features(VHostNetState *net, uint64_t features); -void vhost_net_ack_features(VHostNetState *net, uint64_t features); +void vhost_net_get_features_ex(VHostNetState *net, uint64_t *features); +static inline uint64_t vhost_net_get_features(VHostNetState *net, + uint64_t features) +{ + uint64_t features_array[VIRTIO_FEATURES_NU64S]; + + virtio_features_from_u64(features_array, features); + vhost_net_get_features_ex(net, features_array); + return features_array[0]; +} + +void vhost_net_ack_features_ex(VHostNetState *net, const uint64_t *features); +static inline void vhost_net_ack_features(VHostNetState *net, + uint64_t features) +{ + uint64_t features_array[VIRTIO_FEATURES_NU64S]; + + virtio_features_from_u64(features_array, features); + vhost_net_ack_features_ex(net, features_array); +} int vhost_net_get_config(struct vhost_net *net, uint8_t *config, uint32_t config_len); @@ -41,9 +68,17 @@ void vhost_net_config_mask(VHostNetState *net, VirtIODevice *dev, bool mask); int vhost_net_notify_migration_done(VHostNetState *net, char* mac_addr); VHostNetState *get_vhost_net(NetClientState *nc); -int vhost_set_vring_enable(NetClientState * nc, int enable); +int vhost_net_set_vring_enable(NetClientState *nc, int enable); + +void vhost_net_get_acked_features_ex(VHostNetState *net, uint64_t *features); +static inline uint64_t vhost_net_get_acked_features(VHostNetState *net) +{ + uint64_t features[VIRTIO_FEATURES_NU64S]; -uint64_t vhost_net_get_acked_features(VHostNetState *net); + vhost_net_get_acked_features_ex(net, features); + assert(!virtio_features_use_ex(features)); + return features[0]; +} int vhost_net_set_mtu(struct vhost_net *net, uint16_t mtu); diff --git a/include/qapi/error-internal.h b/include/qapi/error-internal.h new file mode 100644 index 0000000..ff18a20 --- /dev/null +++ b/include/qapi/error-internal.h @@ -0,0 +1,35 @@ +/* + * QEMU Error Objects - struct definition + * + * Copyright IBM, Corp. 2011 + * Copyright (C) 2011-2015 Red Hat, Inc. + * + * Authors: + * Anthony Liguori <aliguori@us.ibm.com> + * Markus Armbruster <armbru@redhat.com>, + * + * This work is licensed under the terms of the GNU LGPL, version 2. See + * the COPYING.LIB file in the top-level directory. + */ + +#ifndef QAPI_ERROR_INTERNAL_H + +struct Error +{ + char *msg; + ErrorClass err_class; + + /* Used for error_abort only, may be NULL. */ + const char *func; + + /* + * src might be NUL-terminated or not. If it is, src_len is negative. + * If it is not, src_len is the length. + */ + const char *src; + int src_len; + int line; + GString *hint; +}; + +#endif diff --git a/include/qapi/error.h b/include/qapi/error.h index 41e3816..b16c630 100644 --- a/include/qapi/error.h +++ b/include/qapi/error.h @@ -534,12 +534,6 @@ static inline void error_propagator_cleanup(ErrorPropagator *prop) G_DEFINE_AUTO_CLEANUP_CLEAR_FUNC(ErrorPropagator, error_propagator_cleanup); /* - * Special error destination to warn on error. - * See error_setg() and error_propagate() for details. - */ -extern Error *error_warn; - -/* * Special error destination to abort on error. * See error_setg() and error_propagate() for details. */ diff --git a/include/qemu/accel.h b/include/qemu/accel.h index 972a849..d3638c7 100644 --- a/include/qemu/accel.h +++ b/include/qemu/accel.h @@ -26,39 +26,8 @@ #include "qom/object.h" #include "exec/hwaddr.h" -struct AccelState { - /*< private >*/ - Object parent_obj; -}; - -typedef struct AccelClass { - /*< private >*/ - ObjectClass parent_class; - /*< public >*/ - - const char *name; - int (*init_machine)(MachineState *ms); -#ifndef CONFIG_USER_ONLY - void (*setup_post)(MachineState *ms, AccelState *accel); - bool (*has_memory)(MachineState *ms, AddressSpace *as, - hwaddr start_addr, hwaddr size); -#endif - bool (*cpu_common_realize)(CPUState *cpu, Error **errp); - void (*cpu_common_unrealize)(CPUState *cpu); - - /* gdbstub related hooks */ - int (*gdbstub_supported_sstep_flags)(void); - - bool *allowed; - /* - * Array of global properties that would be applied when specific - * accelerator is chosen. It works like MachineClass.compat_props - * but it's for accelerators not machines. Accelerator-provided - * global properties may be overridden by machine-type - * compat_props or user-provided global properties. - */ - GPtrArray *compat_props; -} AccelClass; +typedef struct AccelState AccelState; +typedef struct AccelClass AccelClass; #define TYPE_ACCEL "accel" @@ -78,12 +47,12 @@ const char *current_accel_name(void); void accel_init_interfaces(AccelClass *ac); -#ifndef CONFIG_USER_ONLY int accel_init_machine(AccelState *accel, MachineState *ms); /* Called just before os_setup_post (ie just before drop OS privs) */ void accel_setup_post(MachineState *ms); -#endif /* !CONFIG_USER_ONLY */ + +void accel_pre_resume(MachineState *ms, bool step_pending); /** * accel_cpu_instance_init: diff --git a/include/qemu/audio-capture.h b/include/qemu/audio-capture.h new file mode 100644 index 0000000..a07412d --- /dev/null +++ b/include/qemu/audio-capture.h @@ -0,0 +1,43 @@ +/* + * QEMU Audio subsystem + * + * SPDX-License-Identifier: MIT + */ +#ifndef QEMU_AUDIO_CAPTURE_H +#define QEMU_AUDIO_CAPTURE_H + +#include "audio.h" + +typedef struct CaptureVoiceOut CaptureVoiceOut; + +typedef enum { + AUD_CNOTIFY_ENABLE, + AUD_CNOTIFY_DISABLE +} audcnotification_e; + +struct audio_capture_ops { + void (*notify) (void *opaque, audcnotification_e cmd); + void (*capture) (void *opaque, const void *buf, int size); + void (*destroy) (void *opaque); +}; + +struct capture_ops { + void (*info) (void *opaque); + void (*destroy) (void *opaque); +}; + +typedef struct CaptureState { + void *opaque; + struct capture_ops ops; + QLIST_ENTRY(CaptureState) entries; +} CaptureState; + +CaptureVoiceOut *AUD_add_capture( + AudioBackend *be, + struct audsettings *as, + struct audio_capture_ops *ops, + void *opaque + ); +void AUD_del_capture (CaptureVoiceOut *cap, void *cb_opaque); + +#endif /* QEMU_AUDIO_CAPTURE_H */ diff --git a/include/qemu/audio.h b/include/qemu/audio.h new file mode 100644 index 0000000..c56af89 --- /dev/null +++ b/include/qemu/audio.h @@ -0,0 +1,150 @@ +/* + * QEMU Audio subsystem header + * + * Copyright (c) 2003-2005 Vassili Karpov (malc) + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#ifndef QEMU_AUDIO_H +#define QEMU_AUDIO_H + +#include "qemu/queue.h" +#include "qapi/qapi-types-audio.h" +#include "hw/qdev-properties-system.h" +#ifdef CONFIG_GIO +#include "gio/gio.h" +#endif + +typedef void (*audio_callback_fn) (void *opaque, int avail); + +typedef struct audsettings { + int freq; + int nchannels; + AudioFormat fmt; + int endianness; +} audsettings; + +typedef struct SWVoiceOut SWVoiceOut; +typedef struct SWVoiceIn SWVoiceIn; + +struct AudioBackendClass { + ObjectClass parent_class; +}; + +typedef struct AudioBackend AudioBackend; + +typedef struct QEMUAudioTimeStamp { + uint64_t old_ts; +} QEMUAudioTimeStamp; + +bool AUD_backend_check(AudioBackend **be, Error **errp); + +SWVoiceOut *AUD_open_out ( + AudioBackend *be, + SWVoiceOut *sw, + const char *name, + void *callback_opaque, + audio_callback_fn callback_fn, + struct audsettings *settings + ); + +void AUD_close_out (AudioBackend *be, SWVoiceOut *sw); +size_t AUD_write (SWVoiceOut *sw, void *pcm_buf, size_t size); +int AUD_get_buffer_size_out (SWVoiceOut *sw); +void AUD_set_active_out(SWVoiceOut *sw, bool on); +bool AUD_is_active_out(SWVoiceOut *sw); + +void AUD_init_time_stamp_out (SWVoiceOut *sw, QEMUAudioTimeStamp *ts); +uint64_t AUD_get_elapsed_usec_out (SWVoiceOut *sw, QEMUAudioTimeStamp *ts); + +#define AUDIO_MAX_CHANNELS 16 +typedef struct Volume { + bool mute; + int channels; + uint8_t vol[AUDIO_MAX_CHANNELS]; +} Volume; + +void AUD_set_volume_out(SWVoiceOut *sw, Volume *vol); +void AUD_set_volume_in(SWVoiceIn *sw, Volume *vol); + +static inline void +AUD_set_volume_out_lr(SWVoiceOut *sw, bool mut, uint8_t lvol, uint8_t rvol) { + AUD_set_volume_out(sw, &(Volume) { + .mute = mut, .channels = 2, .vol = { lvol, rvol } + }); +} + +static inline void +AUD_set_volume_in_lr(SWVoiceIn *sw, bool mut, uint8_t lvol, uint8_t rvol) { + AUD_set_volume_in(sw, &(Volume) { + .mute = mut, .channels = 2, .vol = { lvol, rvol } + }); +} + +SWVoiceIn *AUD_open_in( + AudioBackend *be, + SWVoiceIn *sw, + const char *name, + void *callback_opaque, + audio_callback_fn callback_fn, + struct audsettings *settings + ); + +void AUD_close_in(AudioBackend *be, SWVoiceIn *sw); +size_t AUD_read (SWVoiceIn *sw, void *pcm_buf, size_t size); +void AUD_set_active_in(SWVoiceIn *sw, bool on); +bool AUD_is_active_in(SWVoiceIn *sw); + +void AUD_init_time_stamp_in (SWVoiceIn *sw, QEMUAudioTimeStamp *ts); +uint64_t AUD_get_elapsed_usec_in (SWVoiceIn *sw, QEMUAudioTimeStamp *ts); + +void audio_cleanup(void); + +typedef struct st_sample st_sample; + +void audio_sample_to_uint64(const st_sample *sample, int pos, + uint64_t *left, uint64_t *right); +void audio_sample_from_uint64(st_sample *sample, int pos, + uint64_t left, uint64_t right); + +void audio_add_audiodev(Audiodev *audio); +void audio_add_default_audiodev(Audiodev *dev, Error **errp); +void audio_parse_option(const char *opt); +void audio_create_default_audiodevs(void); +void audio_init_audiodevs(void); +void audio_help(void); + +AudioBackend *audio_be_by_name(const char *name, Error **errp); +AudioBackend *audio_get_default_audio_be(Error **errp); +const char *audio_be_get_id(AudioBackend *be); +#ifdef CONFIG_GIO +bool audio_be_set_dbus_server(AudioBackend *be, + GDBusObjectManagerServer *server, + bool p2p, + Error **errp); +#endif + +#define DEFINE_AUDIO_PROPERTIES(_s, _f) \ + DEFINE_PROP_AUDIODEV("audiodev", _s, _f) + +#define TYPE_AUDIO_BACKEND "audio-backend" +OBJECT_DECLARE_TYPE(AudioBackend, AudioBackendClass, AUDIO_BACKEND) + +#endif /* QEMU_AUDIO_H */ diff --git a/include/qemu/bswap.h b/include/qemu/bswap.h index b915835..39ba640 100644 --- a/include/qemu/bswap.h +++ b/include/qemu/bswap.h @@ -1,6 +1,8 @@ #ifndef BSWAP_H #define BSWAP_H +#include "qemu/target-info.h" + #undef bswap16 #define bswap16(_x) __builtin_bswap16(_x) #undef bswap32 @@ -205,9 +207,6 @@ CPU_CONVERT(le, 64, uint64_t) * te : target endian * (except for byte accesses, which have no endian infix). * - * The target endian accessors are obviously only available to source - * files which are built per-target; they are defined in cpu-all.h. - * * In all cases these functions take a host pointer. * For accessors that take a guest address rather than a * host address, see the cpu_{ld,st}_* accessors defined in @@ -435,4 +434,75 @@ DO_STN_LDN_P(be) #undef le_bswaps #undef be_bswaps + +/* Return ld{word}_{le,be}_p following target endianness. */ +#define LOAD_IMPL(word, args...) \ +do { \ + if (target_big_endian()) { \ + return glue(glue(ld, word), _be_p)(args); \ + } else { \ + return glue(glue(ld, word), _le_p)(args); \ + } \ +} while (0) + +static inline int lduw_p(const void *ptr) +{ + LOAD_IMPL(uw, ptr); +} + +static inline int ldsw_p(const void *ptr) +{ + LOAD_IMPL(sw, ptr); +} + +static inline int ldl_p(const void *ptr) +{ + LOAD_IMPL(l, ptr); +} + +static inline uint64_t ldq_p(const void *ptr) +{ + LOAD_IMPL(q, ptr); +} + +static inline uint64_t ldn_p(const void *ptr, int sz) +{ + LOAD_IMPL(n, ptr, sz); +} + +#undef LOAD_IMPL + +/* Call st{word}_{le,be}_p following target endianness. */ +#define STORE_IMPL(word, args...) \ +do { \ + if (target_big_endian()) { \ + glue(glue(st, word), _be_p)(args); \ + } else { \ + glue(glue(st, word), _le_p)(args); \ + } \ +} while (0) + + +static inline void stw_p(void *ptr, uint16_t v) +{ + STORE_IMPL(w, ptr, v); +} + +static inline void stl_p(void *ptr, uint32_t v) +{ + STORE_IMPL(l, ptr, v); +} + +static inline void stq_p(void *ptr, uint64_t v) +{ + STORE_IMPL(q, ptr, v); +} + +static inline void stn_p(void *ptr, int sz, uint64_t v) +{ + STORE_IMPL(n, ptr, sz, v); +} + +#undef STORE_IMPL + #endif /* BSWAP_H */ diff --git a/include/qemu/cacheflush.h b/include/qemu/cacheflush.h index ae20bcd..76eb55d 100644 --- a/include/qemu/cacheflush.h +++ b/include/qemu/cacheflush.h @@ -26,6 +26,13 @@ static inline void flush_idcache_range(uintptr_t rx, uintptr_t rw, size_t len) /* icache is coherent and does not require flushing. */ } +#elif defined(EMSCRIPTEN) + +static inline void flush_idcache_range(uintptr_t rx, uintptr_t rw, size_t len) +{ + /* Wasm doesn't have executable region of memory. */ +} + #else void flush_idcache_range(uintptr_t rx, uintptr_t rw, size_t len); diff --git a/include/qemu/compiler.h b/include/qemu/compiler.h index 496dac5..1c2b673 100644 --- a/include/qemu/compiler.h +++ b/include/qemu/compiler.h @@ -182,19 +182,6 @@ #define QEMU_DISABLE_CFI #endif -/* - * Apple clang version 14 has a bug in its __builtin_subcll(); define - * BUILTIN_SUBCLL_BROKEN for the offending versions so we can avoid it. - * When a version of Apple clang which has this bug fixed is released - * we can add an upper bound to this check. - * See https://gitlab.com/qemu-project/qemu/-/issues/1631 - * and https://gitlab.com/qemu-project/qemu/-/issues/1659 for details. - * The bug never made it into any upstream LLVM releases, only Apple ones. - */ -#if defined(__apple_build_version__) && __clang_major__ >= 14 -#define BUILTIN_SUBCLL_BROKEN -#endif - #if __has_attribute(annotate) #define QEMU_ANNOTATE(x) __attribute__((annotate(x))) #else @@ -208,6 +195,26 @@ #endif /* + * Disable -ftrivial-auto-var-init on a local variable. + * + * Use this in cases where there a method in the device I/O path (or other + * important hot paths), that has large variables on the stack. A rule of + * thumb is that "large" means a method with 4kb data in the local stack + * frame. Any variables which are KB in size, should be annotated with this + * attribute, to pre-emptively eliminate any potential overhead from the + * compiler's implicit zero'ing of memory. + * + * Given that this turns off a security hardening feature, when using this + * to flag variables, it is important that the code is double-checked to + * ensure there is no possible use of uninitialized data in the method. + */ +#if __has_attribute(uninitialized) +# define QEMU_UNINITIALIZED __attribute__((uninitialized)) +#else +# define QEMU_UNINITIALIZED +#endif + +/* * http://clang.llvm.org/docs/ThreadSafetyAnalysis.html * * TSA is available since clang 3.6-ish. diff --git a/include/qemu/cpuid.h b/include/qemu/cpuid.h index b111615..de7a9005 100644 --- a/include/qemu/cpuid.h +++ b/include/qemu/cpuid.h @@ -68,6 +68,9 @@ #ifndef bit_AVX512VBMI2 #define bit_AVX512VBMI2 (1 << 6) #endif +#ifndef bit_GFNI +#define bit_GFNI (1 << 8) +#endif /* Leaf 0x80000001, %ecx */ #ifndef bit_LZCNT diff --git a/include/qemu/datadir.h b/include/qemu/datadir.h index 21f9097..cca32af 100644 --- a/include/qemu/datadir.h +++ b/include/qemu/datadir.h @@ -1,11 +1,16 @@ #ifndef QEMU_DATADIR_H #define QEMU_DATADIR_H -#define QEMU_FILE_TYPE_BIOS 0 -#define QEMU_FILE_TYPE_KEYMAP 1 +typedef enum { + QEMU_FILE_TYPE_BIOS, + QEMU_FILE_TYPE_DTB, + QEMU_FILE_TYPE_KEYMAP, +} QemuFileType; + /** * qemu_find_file: * @type: QEMU_FILE_TYPE_BIOS (for BIOS, VGA BIOS) + * QEMU_FILE_TYPE_DTB (for device tree blobs) * or QEMU_FILE_TYPE_KEYMAP (for keymaps). * @name: Relative or absolute file name * @@ -20,7 +25,7 @@ * * Returns: a path that can access @name, or NULL if no matching file exists. */ -char *qemu_find_file(int type, const char *name); +char *qemu_find_file(QemuFileType type, const char *name); void qemu_add_default_firmwarepath(void); void qemu_add_data_dir(char *path); void qemu_list_data_dirs(void); diff --git a/include/qemu/exit-with-parent.h b/include/qemu/exit-with-parent.h new file mode 100644 index 0000000..c00b863 --- /dev/null +++ b/include/qemu/exit-with-parent.h @@ -0,0 +1,57 @@ +/* + * SPDX-License-Identifier: BSD-3-Clause + * Originally derived from nbdkit common/utils/exit-with-parent.h + * Copyright Red Hat + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are + * met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * + * * Neither the name of Red Hat nor the names of its contributors may be + * used to endorse or promote products derived from this software without + * specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY RED HAT AND CONTRIBUTORS ''AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, + * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A + * PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL RED HAT OR + * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF + * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, + * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT + * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#ifndef NBDKIT_EXIT_WITH_PARENT_H +#define NBDKIT_EXIT_WITH_PARENT_H + +/* Test if the feature is available on the platform. */ +static inline bool can_exit_with_parent(void) +{ +#if defined(__linux__) || defined(__FreeBSD__) || defined(__APPLE__) + return true; +#else + return false; +#endif +} + +/* + * --exit-with-parent: kill the current process if the parent exits. + * This may return -1 on error. + * + * Note this will abort on platforms where can_exit_with_parent() + * returned false. + */ +extern int set_exit_with_parent(void); + +#endif /* NBDKIT_EXIT_WITH_PARENT_H */ diff --git a/include/qemu/futex.h b/include/qemu/futex.h index 91ae889..607613e 100644 --- a/include/qemu/futex.h +++ b/include/qemu/futex.h @@ -1,5 +1,5 @@ /* - * Wrappers around Linux futex syscall + * Wrappers around Linux futex syscall and similar * * Copyright Red Hat, Inc. 2017 * @@ -11,17 +11,35 @@ * */ +/* + * Note that a wake-up can also be caused by common futex usage patterns in + * unrelated code that happened to have previously used the futex word's + * memory location (e.g., typical futex-based implementations of Pthreads + * mutexes can cause this under some conditions). Therefore, qemu_futex_wait() + * callers should always conservatively assume that it is a spurious wake-up, + * and use the futex word's value (i.e., the user-space synchronization scheme) + * to decide whether to continue to block or not. + */ + #ifndef QEMU_FUTEX_H #define QEMU_FUTEX_H +#define HAVE_FUTEX + +#ifdef CONFIG_LINUX #include <sys/syscall.h> #include <linux/futex.h> #define qemu_futex(...) syscall(__NR_futex, __VA_ARGS__) -static inline void qemu_futex_wake(void *f, int n) +static inline void qemu_futex_wake_all(void *f) { - qemu_futex(f, FUTEX_WAKE, n, NULL, NULL, 0); + qemu_futex(f, FUTEX_WAKE, INT_MAX, NULL, NULL, 0); +} + +static inline void qemu_futex_wake_single(void *f) +{ + qemu_futex(f, FUTEX_WAKE, 1, NULL, NULL, 0); } static inline void qemu_futex_wait(void *f, unsigned val) @@ -37,5 +55,25 @@ static inline void qemu_futex_wait(void *f, unsigned val) } } } +#elif defined(CONFIG_WIN32) +#include <synchapi.h> + +static inline void qemu_futex_wake_all(void *f) +{ + WakeByAddressAll(f); +} + +static inline void qemu_futex_wake_single(void *f) +{ + WakeByAddressSingle(f); +} + +static inline void qemu_futex_wait(void *f, unsigned val) +{ + WaitOnAddress(f, &val, sizeof(val), INFINITE); +} +#else +#undef HAVE_FUTEX +#endif #endif /* QEMU_FUTEX_H */ diff --git a/include/qemu/host-pci-mmio.h b/include/qemu/host-pci-mmio.h new file mode 100644 index 0000000..a8ed993 --- /dev/null +++ b/include/qemu/host-pci-mmio.h @@ -0,0 +1,136 @@ +/* + * API for host PCI MMIO accesses (e.g. Linux VFIO BARs) + * + * Copyright 2025 IBM Corp. + * Author(s): Farhan Ali <alifm@linux.ibm.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HOST_PCI_MMIO_H +#define HOST_PCI_MMIO_H + +#include "qemu/bswap.h" +#include "qemu/s390x_pci_mmio.h" + +static inline uint8_t host_pci_ldub_p(const void *ioaddr) +{ + uint8_t ret = 0; +#ifdef __s390x__ + ret = s390x_pci_mmio_read_8(ioaddr); +#else + ret = ldub_p(ioaddr); +#endif + + return ret; +} + +static inline uint16_t host_pci_lduw_le_p(const void *ioaddr) +{ + uint16_t ret = 0; +#ifdef __s390x__ + ret = le16_to_cpu(s390x_pci_mmio_read_16(ioaddr)); +#else + ret = lduw_le_p(ioaddr); +#endif + + return ret; +} + +static inline uint32_t host_pci_ldl_le_p(const void *ioaddr) +{ + uint32_t ret = 0; +#ifdef __s390x__ + ret = le32_to_cpu(s390x_pci_mmio_read_32(ioaddr)); +#else + ret = ldl_le_p(ioaddr); +#endif + + return ret; +} + +static inline uint64_t host_pci_ldq_le_p(const void *ioaddr) +{ + uint64_t ret = 0; +#ifdef __s390x__ + ret = le64_to_cpu(s390x_pci_mmio_read_64(ioaddr)); +#else + ret = ldq_le_p(ioaddr); +#endif + + return ret; +} + +static inline void host_pci_stb_p(void *ioaddr, uint8_t val) +{ +#ifdef __s390x__ + s390x_pci_mmio_write_8(ioaddr, val); +#else + stb_p(ioaddr, val); +#endif +} + +static inline void host_pci_stw_le_p(void *ioaddr, uint16_t val) +{ +#ifdef __s390x__ + s390x_pci_mmio_write_16(ioaddr, cpu_to_le16(val)); +#else + stw_le_p(ioaddr, val); +#endif +} + +static inline void host_pci_stl_le_p(void *ioaddr, uint32_t val) +{ +#ifdef __s390x__ + s390x_pci_mmio_write_32(ioaddr, cpu_to_le32(val)); +#else + stl_le_p(ioaddr, val); +#endif +} + +static inline void host_pci_stq_le_p(void *ioaddr, uint64_t val) +{ +#ifdef __s390x__ + s390x_pci_mmio_write_64(ioaddr, cpu_to_le64(val)); +#else + stq_le_p(ioaddr, val); +#endif +} + +static inline uint64_t host_pci_ldn_le_p(const void *ioaddr, int sz) +{ + switch (sz) { + case 1: + return host_pci_ldub_p(ioaddr); + case 2: + return host_pci_lduw_le_p(ioaddr); + case 4: + return host_pci_ldl_le_p(ioaddr); + case 8: + return host_pci_ldq_le_p(ioaddr); + default: + g_assert_not_reached(); + } +} + +static inline void host_pci_stn_le_p(void *ioaddr, int sz, uint64_t v) +{ + switch (sz) { + case 1: + host_pci_stb_p(ioaddr, v); + break; + case 2: + host_pci_stw_le_p(ioaddr, v); + break; + case 4: + host_pci_stl_le_p(ioaddr, v); + break; + case 8: + host_pci_stq_le_p(ioaddr, v); + break; + default: + g_assert_not_reached(); + } +} + +#endif diff --git a/include/qemu/host-utils.h b/include/qemu/host-utils.h index 4d28fa2..dd55858 100644 --- a/include/qemu/host-utils.h +++ b/include/qemu/host-utils.h @@ -677,7 +677,7 @@ static inline uint64_t uadd64_carry(uint64_t x, uint64_t y, bool *pcarry) */ static inline uint64_t usub64_borrow(uint64_t x, uint64_t y, bool *pborrow) { -#if __has_builtin(__builtin_subcll) && !defined(BUILTIN_SUBCLL_BROKEN) +#if __has_builtin(__builtin_subcll) unsigned long long b = *pborrow; x = __builtin_subcll(x, y, b, &b); *pborrow = b & 1; diff --git a/include/qemu/iova-tree.h b/include/qemu/iova-tree.h index 16d354a..14e82a2 100644 --- a/include/qemu/iova-tree.h +++ b/include/qemu/iova-tree.h @@ -23,7 +23,7 @@ * for the thread safety issue. */ -#include "exec/memory.h" +#include "system/memory.h" #include "exec/hwaddr.h" #define IOVA_OK (0) diff --git a/include/qemu/job.h b/include/qemu/job.h index a5a0415..ead3157 100644 --- a/include/qemu/job.h +++ b/include/qemu/job.h @@ -263,7 +263,7 @@ struct JobDriver { * This callback will not be invoked if the job has already failed. * If it fails, abort and then clean will be called. */ - int (*prepare)(Job *job); + int GRAPH_UNLOCKED_PTR (*prepare)(Job *job); /** * If the callback is not NULL, it will be invoked when all the jobs @@ -283,7 +283,7 @@ struct JobDriver { * All jobs will complete with a call to either .commit() or .abort() but * never both. */ - void (*abort)(Job *job); + void GRAPH_UNLOCKED_PTR (*abort)(Job *job); /** * If the callback is not NULL, it will be invoked after a call to either diff --git a/include/qemu/lockcnt.h b/include/qemu/lockcnt.h index f4b62a3..5a2800e 100644 --- a/include/qemu/lockcnt.h +++ b/include/qemu/lockcnt.h @@ -17,7 +17,7 @@ typedef struct QemuLockCnt QemuLockCnt; struct QemuLockCnt { -#ifndef CONFIG_LINUX +#ifndef HAVE_FUTEX QemuMutex mutex; #endif unsigned count; diff --git a/include/qemu/log-for-trace.h b/include/qemu/log-for-trace.h index d47c9cd..f3a8791 100644 --- a/include/qemu/log-for-trace.h +++ b/include/qemu/log-for-trace.h @@ -19,9 +19,9 @@ #define QEMU_LOG_FOR_TRACE_H /* Private global variable, don't use */ -extern int qemu_loglevel; +extern unsigned qemu_loglevel; -#define LOG_TRACE (1 << 15) +#define LOG_TRACE (1u << 15) /* Returns true if a bit is set in the current loglevel mask */ static inline bool qemu_loglevel_mask(int mask) diff --git a/include/qemu/log.h b/include/qemu/log.h index 60da703..7effba4 100644 --- a/include/qemu/log.h +++ b/include/qemu/log.h @@ -14,30 +14,30 @@ bool qemu_log_enabled(void); /* Returns true if qemu_log() will write somewhere other than stderr. */ bool qemu_log_separate(void); -#define CPU_LOG_TB_OUT_ASM (1 << 0) -#define CPU_LOG_TB_IN_ASM (1 << 1) -#define CPU_LOG_TB_OP (1 << 2) -#define CPU_LOG_TB_OP_OPT (1 << 3) -#define CPU_LOG_INT (1 << 4) -#define CPU_LOG_EXEC (1 << 5) -#define CPU_LOG_PCALL (1 << 6) -#define CPU_LOG_TB_CPU (1 << 8) -#define CPU_LOG_RESET (1 << 9) -#define LOG_UNIMP (1 << 10) -#define LOG_GUEST_ERROR (1 << 11) -#define CPU_LOG_MMU (1 << 12) -#define CPU_LOG_TB_NOCHAIN (1 << 13) -#define CPU_LOG_PAGE (1 << 14) +#define CPU_LOG_TB_OUT_ASM (1u << 0) +#define CPU_LOG_TB_IN_ASM (1u << 1) +#define CPU_LOG_TB_OP (1u << 2) +#define CPU_LOG_TB_OP_OPT (1u << 3) +#define CPU_LOG_INT (1u << 4) +#define CPU_LOG_EXEC (1u << 5) +#define CPU_LOG_PCALL (1u << 6) +#define CPU_LOG_TB_CPU (1u << 8) +#define CPU_LOG_RESET (1u << 9) +#define LOG_UNIMP (1u << 10) +#define LOG_GUEST_ERROR (1u << 11) +#define CPU_LOG_MMU (1u << 12) +#define CPU_LOG_TB_NOCHAIN (1u << 13) +#define CPU_LOG_PAGE (1u << 14) /* LOG_TRACE (1 << 15) is defined in log-for-trace.h */ -#define CPU_LOG_TB_OP_IND (1 << 16) -#define CPU_LOG_TB_FPU (1 << 17) -#define CPU_LOG_PLUGIN (1 << 18) +#define CPU_LOG_TB_OP_IND (1u << 16) +#define CPU_LOG_TB_FPU (1u << 17) +#define CPU_LOG_PLUGIN (1u << 18) /* LOG_STRACE is used for user-mode strace logging. */ -#define LOG_STRACE (1 << 19) -#define LOG_PER_THREAD (1 << 20) -#define CPU_LOG_TB_VPU (1 << 21) -#define LOG_TB_OP_PLUGIN (1 << 22) -#define LOG_INVALID_MEM (1 << 23) +#define LOG_STRACE (1u << 19) +#define LOG_PER_THREAD (1u << 20) +#define CPU_LOG_TB_VPU (1u << 21) +#define LOG_TB_OP_PLUGIN (1u << 22) +#define LOG_INVALID_MEM (1u << 23) /* Lock/unlock output. */ @@ -84,6 +84,8 @@ typedef struct QEMULogItem { extern const QEMULogItem qemu_log_items[]; +ssize_t rust_fwrite(const void *ptr, size_t size, size_t nmemb, FILE *stream); + bool qemu_set_log(int log_flags, Error **errp); bool qemu_set_log_filename(const char *filename, Error **errp); bool qemu_set_log_filename_flags(const char *name, int flags, Error **errp); diff --git a/include/qemu/main-loop.h b/include/qemu/main-loop.h index 4e2436b..0d55c63 100644 --- a/include/qemu/main-loop.h +++ b/include/qemu/main-loop.h @@ -271,6 +271,24 @@ void rust_bql_mock_lock(void); bool bql_locked(void); /** + * mutex_is_bql: + * + * @mutex: the mutex pointer + * + * Returns whether the mutex is the BQL. + */ +bool mutex_is_bql(QemuMutex *mutex); + +/** + * bql_update_status: + * + * @locked: update status on whether the BQL is locked + * + * NOTE: this should normally only be invoked when the status changed. + */ +void bql_update_status(bool locked); + +/** * bql_block: Allow/deny releasing the BQL * * The Big QEMU Lock (BQL) is used to provide interior mutability to diff --git a/include/qemu/osdep.h b/include/qemu/osdep.h index 4397a90..3cb45a1 100644 --- a/include/qemu/osdep.h +++ b/include/qemu/osdep.h @@ -8,7 +8,7 @@ * To avoid getting into possible circular include dependencies, this * file should not include any other QEMU headers, with the exceptions * of config-host.h, config-target.h, qemu/compiler.h, - * system/os-posix.h, system/os-win32.h, glib-compat.h and + * system/os-posix.h, system/os-win32.h, system/os-wasm.h, glib-compat.h and * qemu/typedefs.h, all of which are doing a similar job to this file * and are under similar constraints. * @@ -133,6 +133,20 @@ QEMU_EXTERN_C int daemon(int, int); #include <setjmp.h> #include <signal.h> +/* + * Avoid conflict with linux/arch/powerpc/include/uapi/asm/elf.h, included + * from <asm/sigcontext.h>, but we might as well do this unconditionally. + */ +#undef ELF_CLASS +#undef ELF_DATA +#undef ELF_ARCH + +/* + * Avoid conflict with Solaris FSCALE definition from <sys/param.h> header, + * but we might as well do this unconditionally. + */ +#undef FSCALE + #ifdef CONFIG_IOVEC #include <sys/uio.h> #endif @@ -164,10 +178,14 @@ QEMU_EXTERN_C int daemon(int, int); #include "system/os-win32.h" #endif -#ifdef CONFIG_POSIX +#if defined(CONFIG_POSIX) && !defined(EMSCRIPTEN) #include "system/os-posix.h" #endif +#if defined(EMSCRIPTEN) +#include "system/os-wasm.h" +#endif + #ifdef __cplusplus extern "C" { #endif @@ -549,7 +567,7 @@ int madvise(char *, size_t, int); #if defined(__linux__) && \ (defined(__x86_64__) || defined(__arm__) || defined(__aarch64__) \ - || defined(__powerpc64__)) + || defined(__powerpc64__) || defined(__riscv)) /* Use 2 MiB alignment so transparent hugepages can be used by KVM. Valgrind does not support alignments larger than 1 MiB, therefore we need special code which handles running on Valgrind. */ @@ -675,6 +693,16 @@ ssize_t qemu_write_full(int fd, const void *buf, size_t count) G_GNUC_WARN_UNUSED_RESULT; void qemu_set_cloexec(int fd); +bool qemu_set_blocking(int fd, bool block, Error **errp); + +/* + * Clear FD_CLOEXEC for a descriptor. + * + * The caller must guarantee that no other fork+exec's occur before the + * exec that is intended to inherit this descriptor, eg by suspending CPUs + * and blocking monitor commands. + */ +void qemu_clear_cloexec(int fd); /* Return a dynamically allocated directory path that is appropriate for storing * local state. diff --git a/include/qemu/plugin-event.h b/include/qemu/plugin-event.h index 7056d84..1100dae 100644 --- a/include/qemu/plugin-event.h +++ b/include/qemu/plugin-event.h @@ -20,6 +20,9 @@ enum qemu_plugin_event { QEMU_PLUGIN_EV_VCPU_SYSCALL_RET, QEMU_PLUGIN_EV_FLUSH, QEMU_PLUGIN_EV_ATEXIT, + QEMU_PLUGIN_EV_VCPU_INTERRUPT, + QEMU_PLUGIN_EV_VCPU_EXCEPTION, + QEMU_PLUGIN_EV_VCPU_HOSTCALL, QEMU_PLUGIN_EV_MAX, /* total number of plugin events we support */ }; diff --git a/include/qemu/plugin.h b/include/qemu/plugin.h index 9726a9e..cea0a68 100644 --- a/include/qemu/plugin.h +++ b/include/qemu/plugin.h @@ -59,6 +59,7 @@ union qemu_plugin_cb_sig { qemu_plugin_udata_cb_t udata; qemu_plugin_vcpu_simple_cb_t vcpu_simple; qemu_plugin_vcpu_udata_cb_t vcpu_udata; + qemu_plugin_vcpu_discon_cb_t vcpu_discon; qemu_plugin_vcpu_tb_trans_cb_t vcpu_tb_trans; qemu_plugin_vcpu_mem_cb_t vcpu_mem; qemu_plugin_vcpu_syscall_cb_t vcpu_syscall; @@ -160,6 +161,9 @@ void qemu_plugin_vcpu_exit_hook(CPUState *cpu); void qemu_plugin_tb_trans_cb(CPUState *cpu, struct qemu_plugin_tb *tb); void qemu_plugin_vcpu_idle_cb(CPUState *cpu); void qemu_plugin_vcpu_resume_cb(CPUState *cpu); +void qemu_plugin_vcpu_interrupt_cb(CPUState *cpu, uint64_t from); +void qemu_plugin_vcpu_exception_cb(CPUState *cpu, uint64_t from); +void qemu_plugin_vcpu_hostcall_cb(CPUState *cpu, uint64_t from); void qemu_plugin_vcpu_syscall(CPUState *cpu, int64_t num, uint64_t a1, uint64_t a2, uint64_t a3, uint64_t a4, uint64_t a5, @@ -209,6 +213,21 @@ void qemu_plugin_user_prefork_lock(void); */ void qemu_plugin_user_postfork(bool is_child); +enum qemu_plugin_cb_flags tcg_call_to_qemu_plugin_cb_flags(int flags); + +static inline void qemu_plugin_set_cb_flags(CPUState *cpu, + enum qemu_plugin_cb_flags flags) +{ + assert(cpu); + cpu->neg.plugin_cb_flags = flags; +} + +static inline enum qemu_plugin_cb_flags qemu_plugin_get_cb_flags(void) +{ + assert(current_cpu); + return current_cpu->neg.plugin_cb_flags; +} + #else /* !CONFIG_PLUGIN */ static inline void qemu_plugin_add_opts(void) @@ -242,6 +261,15 @@ static inline void qemu_plugin_vcpu_idle_cb(CPUState *cpu) static inline void qemu_plugin_vcpu_resume_cb(CPUState *cpu) { } +static inline void qemu_plugin_vcpu_interrupt_cb(CPUState *cpu, uint64_t from) +{ } + +static inline void qemu_plugin_vcpu_exception_cb(CPUState *cpu, uint64_t from) +{ } + +static inline void qemu_plugin_vcpu_hostcall_cb(CPUState *cpu, uint64_t from) +{ } + static inline void qemu_plugin_vcpu_syscall(CPUState *cpu, int64_t num, uint64_t a1, uint64_t a2, uint64_t a3, uint64_t a4, uint64_t a5, uint64_t a6, diff --git a/include/qemu/qemu-plugin.h b/include/qemu/qemu-plugin.h index 3a850aa..60de4fd 100644 --- a/include/qemu/qemu-plugin.h +++ b/include/qemu/qemu-plugin.h @@ -65,11 +65,18 @@ typedef uint64_t qemu_plugin_id_t; * * version 4: * - added qemu_plugin_read_memory_vaddr + * + * version 5: + * - added qemu_plugin_write_memory_vaddr + * - added qemu_plugin_read_memory_hwaddr + * - added qemu_plugin_write_memory_hwaddr + * - added qemu_plugin_write_register + * - added qemu_plugin_translate_vaddr */ extern QEMU_PLUGIN_EXPORT int qemu_plugin_version; -#define QEMU_PLUGIN_VERSION 4 +#define QEMU_PLUGIN_VERSION 5 /** * struct qemu_info_t - system information for plugins @@ -154,6 +161,50 @@ typedef void (*qemu_plugin_vcpu_simple_cb_t)(qemu_plugin_id_t id, typedef void (*qemu_plugin_vcpu_udata_cb_t)(unsigned int vcpu_index, void *userdata); + +/** + * enum qemu_plugin_discon_type - type of a (potential) PC discontinuity + * + * @QEMU_PLUGIN_DISCON_INTERRUPT: an interrupt, defined across all architectures + * as an asynchronous event, usually originating + * from outside the CPU + * @QEMU_PLUGIN_DISCON_EXCEPTION: an exception, defined across all architectures + * as a synchronous event in response to a + * specific instruction being executed + * @QEMU_PLUGIN_DISCON_HOSTCALL: a host call, functionally a special kind of + * exception that is not handled by code run by + * the vCPU but machinery outside the vCPU + * @QEMU_PLUGIN_DISCON_ALL: all types of disconinuity events currently covered + */ +enum qemu_plugin_discon_type { + QEMU_PLUGIN_DISCON_INTERRUPT = 1 << 0, + QEMU_PLUGIN_DISCON_EXCEPTION = 1 << 1, + QEMU_PLUGIN_DISCON_HOSTCALL = 1 << 2, + QEMU_PLUGIN_DISCON_ALL = -1 +}; + +/** + * typedef qemu_plugin_vcpu_discon_cb_t - vcpu discontinuity callback + * @id: plugin ID + * @vcpu_index: the current vcpu context + * @type: the type of discontinuity + * @from_pc: the source of the discontinuity, e.g. the PC before the + * transition + * @to_pc: the PC pointing to the next instruction to be executed + * + * The exact semantics of @from_pc depends on the @type of discontinuity. For + * interrupts, @from_pc will point to the next instruction which would have + * been executed. For exceptions and host calls, @from_pc will point to the + * instruction that caused the exception or issued the host call. Note that + * in the case of exceptions, the instruction may not be retired and thus not + * observable via general instruction exec callbacks. The same may be the case + * for some host calls such as hypervisor call "exceptions". + */ +typedef void (*qemu_plugin_vcpu_discon_cb_t)(qemu_plugin_id_t id, + unsigned int vcpu_index, + enum qemu_plugin_discon_type type, + uint64_t from_pc, uint64_t to_pc); + /** * qemu_plugin_uninstall() - Uninstall a plugin * @id: this plugin's opaque ID @@ -230,6 +281,22 @@ QEMU_PLUGIN_API void qemu_plugin_register_vcpu_resume_cb(qemu_plugin_id_t id, qemu_plugin_vcpu_simple_cb_t cb); +/** + * qemu_plugin_register_vcpu_discon_cb() - register a discontinuity callback + * @id: plugin ID + * @type: types of discontinuities for which to call the callback + * @cb: callback function + * + * The @cb function is called every time a vCPU receives a discontinuity event + * of the specified type(s), after the vCPU was prepared to handle the event. + * Preparation entails updating the PC, usually to some interrupt handler or + * trap vector entry. + */ +QEMU_PLUGIN_API +void qemu_plugin_register_vcpu_discon_cb(qemu_plugin_id_t id, + enum qemu_plugin_discon_type type, + qemu_plugin_vcpu_discon_cb_t cb); + /** struct qemu_plugin_tb - Opaque handle for a translation block */ struct qemu_plugin_tb; /** struct qemu_plugin_insn - Opaque handle for a translated instruction */ @@ -254,9 +321,6 @@ typedef struct { * @QEMU_PLUGIN_CB_NO_REGS: callback does not access the CPU's regs * @QEMU_PLUGIN_CB_R_REGS: callback reads the CPU's regs * @QEMU_PLUGIN_CB_RW_REGS: callback reads and writes the CPU's regs - * - * Note: currently QEMU_PLUGIN_CB_RW_REGS is unused, plugins cannot change - * system register state. */ enum qemu_plugin_cb_flags { QEMU_PLUGIN_CB_NO_REGS, @@ -871,7 +935,8 @@ struct qemu_plugin_register; /** * typedef qemu_plugin_reg_descriptor - register descriptions * - * @handle: opaque handle for retrieving value with qemu_plugin_read_register + * @handle: opaque handle for retrieving value with qemu_plugin_read_register or + * writing value with qemu_plugin_write_register * @name: register name * @feature: optional feature descriptor, can be NULL */ @@ -894,6 +959,51 @@ QEMU_PLUGIN_API GArray *qemu_plugin_get_registers(void); /** + * qemu_plugin_read_register() - read register for current vCPU + * + * @handle: a @qemu_plugin_reg_handle handle + * @buf: A GByteArray for the data owned by the plugin + * + * This function is only available in a context that register read access is + * explicitly requested via the QEMU_PLUGIN_CB_R_REGS flag, if called inside a + * callback that can be registered with a qemu_plugin_cb_flags argument. This + * function can also be used in any callback context that does not use a flags + * argument, such as in a callback registered with + * qemu_plugin_register_vcpu_init_cb(), except for callbacks registered with + * qemu_plugin_register_atexit_cb() and qemu_plugin_register_flush_cb(). + * + * Returns the size of the read register. The content of @buf is in target byte + * order. On failure returns -1. + */ +QEMU_PLUGIN_API +int qemu_plugin_read_register(struct qemu_plugin_register *handle, + GByteArray *buf); + +/** + * qemu_plugin_write_register() - write register for current vCPU + * + * @handle: a @qemu_plugin_reg_handle handle + * @buf: A GByteArray for the data owned by the plugin + * + * This function is only available in a context that register read access is + * explicitly requested via the QEMU_PLUGIN_CB_RW_REGS flag, if called inside a + * callback that can be registered with a qemu_plugin_cb_flags argument. This + * function can also be used in any callback context that does not use a flags + * argument, such as in a callback registered with + * qemu_plugin_register_vcpu_init_cb(), except for callbacks registered with + * qemu_plugin_register_atexit_cb() and qemu_plugin_register_flush_cb(). + * + * The size of @buf must be at least the size of the requested register. + * Attempting to write a register with @buf smaller than the register size + * will result in a crash or other undesired behavior. + * + * Returns the number of bytes written. On failure returns 0. + */ +QEMU_PLUGIN_API +int qemu_plugin_write_register(struct qemu_plugin_register *handle, + GByteArray *buf); + +/** * qemu_plugin_read_memory_vaddr() - read from memory using a virtual address * * @addr: A virtual address to read from @@ -916,20 +1026,118 @@ bool qemu_plugin_read_memory_vaddr(uint64_t addr, GByteArray *data, size_t len); /** - * qemu_plugin_read_register() - read register for current vCPU + * qemu_plugin_write_memory_vaddr() - write to memory using a virtual address * - * @handle: a @qemu_plugin_reg_handle handle - * @buf: A GByteArray for the data owned by the plugin + * @addr: A virtual address to write to + * @data: A byte array containing the data to write * - * This function is only available in a context that register read access is - * explicitly requested via the QEMU_PLUGIN_CB_R_REGS flag. + * The contents of @data will be written to memory starting at the virtual + * address @addr. * - * Returns the size of the read register. The content of @buf is in target byte - * order. On failure returns -1. + * This function does not guarantee consistency of writes, nor does it ensure + * that pending writes are flushed either before or after the write takes place, + * so callers should take care to only call this function in vCPU context (i.e. + * in callbacks) and avoid depending on the existence of data written using this + * function which may be overwritten afterward. + * + * Returns true on success and false on failure. */ QEMU_PLUGIN_API -int qemu_plugin_read_register(struct qemu_plugin_register *handle, - GByteArray *buf); +bool qemu_plugin_write_memory_vaddr(uint64_t addr, + GByteArray *data); + +/** + * enum qemu_plugin_hwaddr_operation_result - result of a memory operation + * + * @QEMU_PLUGIN_HWADDR_OPERATION_OK: hwaddr operation succeeded + * @QEMU_PLUGIN_HWADDR_OPERATION_ERROR: unexpected error occurred + * @QEMU_PLUGIN_HWADDR_OPERATION_DEVICE_ERROR: error in memory device + * @QEMU_PLUGIN_HWADDR_OPERATION_ACCESS_DENIED: permission error + * @QEMU_PLUGIN_HWADDR_OPERATION_INVALID_ADDRESS: address was invalid + * @QEMU_PLUGIN_HWADDR_OPERATION_INVALID_ADDRESS_SPACE: invalid address space + */ +enum qemu_plugin_hwaddr_operation_result { + QEMU_PLUGIN_HWADDR_OPERATION_OK, + QEMU_PLUGIN_HWADDR_OPERATION_ERROR, + QEMU_PLUGIN_HWADDR_OPERATION_DEVICE_ERROR, + QEMU_PLUGIN_HWADDR_OPERATION_ACCESS_DENIED, + QEMU_PLUGIN_HWADDR_OPERATION_INVALID_ADDRESS, + QEMU_PLUGIN_HWADDR_OPERATION_INVALID_ADDRESS_SPACE, +}; + +/** + * qemu_plugin_read_memory_hwaddr() - read from memory using a hardware address + * + * @addr: The physical address to read from + * @data: A byte array to store data into + * @len: The number of bytes to read, starting from @addr + * + * @len bytes of data is read from the current memory space for the current + * vCPU starting at @addr and stored into @data. If @data is not large enough to + * hold @len bytes, it will be expanded to the necessary size, reallocating if + * necessary. @len must be greater than 0. + * + * This function does not ensure writes are flushed prior to reading, so + * callers should take care when calling this function in plugin callbacks to + * avoid attempting to read data which may not yet be written and should use + * the memory callback API instead. + * + * This function is only valid for softmmu targets. + * + * Returns a qemu_plugin_hwaddr_operation_result indicating the result of the + * operation. + */ +QEMU_PLUGIN_API +enum qemu_plugin_hwaddr_operation_result +qemu_plugin_read_memory_hwaddr(uint64_t addr, GByteArray *data, size_t len); + +/** + * qemu_plugin_write_memory_hwaddr() - write to memory using a hardware address + * + * @addr: A physical address to write to + * @data: A byte array containing the data to write + * + * The contents of @data will be written to memory starting at the hardware + * address @addr in the current address space for the current vCPU. + * + * This function does not guarantee consistency of writes, nor does it ensure + * that pending writes are flushed either before or after the write takes place, + * so callers should take care when calling this function in plugin callbacks to + * avoid depending on the existence of data written using this function which + * may be overwritten afterward. In addition, this function requires that the + * pages containing the address are not locked. Practically, this means that you + * should not write instruction memory in a current translation block inside a + * callback registered with qemu_plugin_register_vcpu_tb_trans_cb. + * + * You can, for example, write instruction memory in a current translation block + * in a callback registered with qemu_plugin_register_vcpu_tb_exec_cb, although + * be aware that the write will not be flushed until after the translation block + * has finished executing. In general, this function should be used to write + * data memory or to patch code at a known address, not in a current translation + * block. + * + * This function is only valid for softmmu targets. + * + * Returns a qemu_plugin_hwaddr_operation_result indicating the result of the + * operation. + */ +QEMU_PLUGIN_API +enum qemu_plugin_hwaddr_operation_result +qemu_plugin_write_memory_hwaddr(uint64_t addr, GByteArray *data); + +/** + * qemu_plugin_translate_vaddr() - translate virtual address for current vCPU + * + * @vaddr: virtual address to translate + * @hwaddr: pointer to store the physical address + * + * This function is only valid in vCPU context (i.e. in callbacks) and is only + * valid for softmmu targets. + * + * Returns true on success and false on failure. + */ +QEMU_PLUGIN_API +bool qemu_plugin_translate_vaddr(uint64_t vaddr, uint64_t *hwaddr); /** * qemu_plugin_scoreboard_new() - alloc a new scoreboard diff --git a/include/qemu/rcu.h b/include/qemu/rcu.h index fea058a..020dbe4 100644 --- a/include/qemu/rcu.h +++ b/include/qemu/rcu.h @@ -17,8 +17,8 @@ * Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + * License along with this library; if not, see + * <https://www.gnu.org/licenses/>. * * IBM's contributions to this file may be relicensed under LGPLv2 or later. */ diff --git a/include/qemu/rcu_queue.h b/include/qemu/rcu_queue.h index 4e6298d..bfd5900 100644 --- a/include/qemu/rcu_queue.h +++ b/include/qemu/rcu_queue.h @@ -17,8 +17,8 @@ * Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + * License along with this library; if not, see + * <https://www.gnu.org/licenses/>. * * Copyright (c) 2013 Mike D. Day, IBM Corporation. * diff --git a/include/qemu/reserved-region.h b/include/qemu/reserved-region.h index 8e6f0a9..9026cf0 100644 --- a/include/qemu/reserved-region.h +++ b/include/qemu/reserved-region.h @@ -20,7 +20,7 @@ #ifndef QEMU_RESERVED_REGION_H #define QEMU_RESERVED_REGION_H -#include "exec/memory.h" +#include "system/memory.h" /* * Insert a new region into a sorted list of reserved regions. In case diff --git a/include/qemu/s390x_pci_mmio.h b/include/qemu/s390x_pci_mmio.h new file mode 100644 index 0000000..c5f63ec --- /dev/null +++ b/include/qemu/s390x_pci_mmio.h @@ -0,0 +1,24 @@ +/* + * s390x PCI MMIO definitions + * + * Copyright 2025 IBM Corp. + * Author(s): Farhan Ali <alifm@linux.ibm.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ +#ifndef S390X_PCI_MMIO_H +#define S390X_PCI_MMIO_H + +#ifdef __s390x__ +uint8_t s390x_pci_mmio_read_8(const void *ioaddr); +uint16_t s390x_pci_mmio_read_16(const void *ioaddr); +uint32_t s390x_pci_mmio_read_32(const void *ioaddr); +uint64_t s390x_pci_mmio_read_64(const void *ioaddr); + +void s390x_pci_mmio_write_8(void *ioaddr, uint8_t val); +void s390x_pci_mmio_write_16(void *ioaddr, uint16_t val); +void s390x_pci_mmio_write_32(void *ioaddr, uint32_t val); +void s390x_pci_mmio_write_64(void *ioaddr, uint64_t val); +#endif /* __s390x__ */ + +#endif /* S390X_PCI_MMIO_H */ diff --git a/include/qemu/sockets.h b/include/qemu/sockets.h index c562690..be351d8 100644 --- a/include/qemu/sockets.h +++ b/include/qemu/sockets.h @@ -46,9 +46,6 @@ ssize_t qemu_send_full(int s, const void *buf, size_t count) G_GNUC_WARN_UNUSED_RESULT; int socket_set_cork(int fd, int v); int socket_set_nodelay(int fd); -void qemu_socket_set_block(int fd); -int qemu_socket_try_set_nonblock(int fd); -void qemu_socket_set_nonblock(int fd); int socket_set_fast_reuse(int fd); #ifdef WIN32 diff --git a/include/qemu/target-info-impl.h b/include/qemu/target-info-impl.h new file mode 100644 index 0000000..e446585 --- /dev/null +++ b/include/qemu/target-info-impl.h @@ -0,0 +1,37 @@ +/* + * QEMU TargetInfo structure definition + * + * Copyright (c) Linaro + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef QEMU_TARGET_INFO_IMPL_H +#define QEMU_TARGET_INFO_IMPL_H + +#include "qapi/qapi-types-common.h" +#include "qapi/qapi-types-machine.h" + +typedef struct TargetInfo { + /* runtime equivalent of TARGET_NAME definition */ + const char *target_name; + /* related to TARGET_ARCH definition */ + SysEmuTarget target_arch; + /* runtime equivalent of TARGET_LONG_BITS definition */ + unsigned long_bits; + /* runtime equivalent of CPU_RESOLVING_TYPE definition */ + const char *cpu_type; + /* QOM typename machines for this binary must implement */ + const char *machine_typename; + /* related to TARGET_BIG_ENDIAN definition */ + EndianMode endianness; +} TargetInfo; + +/** + * target_info: + * + * Returns: The TargetInfo structure definition for this target binary. + */ +const TargetInfo *target_info(void); + +#endif diff --git a/include/qemu/target-info-qapi.h b/include/qemu/target-info-qapi.h new file mode 100644 index 0000000..d5ce052 --- /dev/null +++ b/include/qemu/target-info-qapi.h @@ -0,0 +1,29 @@ +/* + * QEMU target info API (returning QAPI types) + * + * Copyright (c) Linaro + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef QEMU_TARGET_INFO_EXTRA_H +#define QEMU_TARGET_INFO_EXTRA_H + +#include "qapi/qapi-types-common.h" +#include "qapi/qapi-types-machine.h" + +/** + * target_arch: + * + * Returns: QAPI SysEmuTarget enum (e.g. SYS_EMU_TARGET_X86_64). + */ +SysEmuTarget target_arch(void); + +/** + * target_endian_mode: + * + * Returns: QAPI EndianMode enum (e.g. ENDIAN_MODE_LITTLE). + */ +EndianMode target_endian_mode(void); + +#endif diff --git a/include/qemu/target-info.h b/include/qemu/target-info.h new file mode 100644 index 0000000..6235962 --- /dev/null +++ b/include/qemu/target-info.h @@ -0,0 +1,74 @@ +/* + * QEMU target info API (returning native types) + * + * Copyright (c) Linaro + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef QEMU_TARGET_INFO_H +#define QEMU_TARGET_INFO_H + +/** + * target_name: + * + * Returns: Canonical target name (i.e. "i386"). + */ +const char *target_name(void); + +/** + * target_long_bits: + * + * Returns: number of bits in a long type for this target (i.e. 64). + */ +unsigned target_long_bits(void); + +/** + * target_machine_typename: + * + * Returns: Name of the QOM interface implemented by machines + * usable on this target binary. + */ +const char *target_machine_typename(void); + +/** + * target_cpu_type: + * + * Returns: target CPU base QOM type name (i.e. TYPE_X86_CPU). + */ +const char *target_cpu_type(void); + +/** + * target_big_endian: + * + * Returns: %true if the (default) endianness of the target is big endian, + * %false otherwise. + * + * Common code should normally never need to know about the endianness of + * the target, so please do *not* use this function unless you know very + * well what you are doing! + */ +bool target_big_endian(void); + +/** + * target_base_arm: + * + * Returns whether the target architecture is ARM or Aarch64. + */ +bool target_base_arm(void); + +/** + * target_arm: + * + * Returns whether the target architecture is ARM (32-bit, not Aarch64). + */ +bool target_arm(void); + +/** + * target_aarch64: + * + * Returns whether the target architecture is Aarch64. + */ +bool target_aarch64(void); + +#endif diff --git a/include/qemu/thread-posix.h b/include/qemu/thread-posix.h index 5f2f3d1..758808b 100644 --- a/include/qemu/thread-posix.h +++ b/include/qemu/thread-posix.h @@ -32,15 +32,6 @@ struct QemuSemaphore { unsigned int count; }; -struct QemuEvent { -#ifndef __linux__ - pthread_mutex_t lock; - pthread_cond_t cond; -#endif - unsigned value; - bool initialized; -}; - struct QemuThread { pthread_t thread; }; diff --git a/include/qemu/thread-win32.h b/include/qemu/thread-win32.h index d95af44..da9e732 100644 --- a/include/qemu/thread-win32.h +++ b/include/qemu/thread-win32.h @@ -28,12 +28,6 @@ struct QemuSemaphore { bool initialized; }; -struct QemuEvent { - int value; - HANDLE event; - bool initialized; -}; - typedef struct QemuThreadData QemuThreadData; struct QemuThread { QemuThreadData *data; diff --git a/include/qemu/thread.h b/include/qemu/thread.h index 6f800aa..f0302ed 100644 --- a/include/qemu/thread.h +++ b/include/qemu/thread.h @@ -3,13 +3,32 @@ #include "qemu/processor.h" #include "qemu/atomic.h" +#include "qemu/futex.h" typedef struct QemuCond QemuCond; typedef struct QemuSemaphore QemuSemaphore; -typedef struct QemuEvent QemuEvent; typedef struct QemuLockCnt QemuLockCnt; typedef struct QemuThread QemuThread; +/* + * QemuEvent + * ========= + * + * QemuEvent is an implementation of Win32 manual-reset event object. + * For details, refer to: + * https://learn.microsoft.com/en-us/windows/win32/sync/using-event-objects + * + * QemuEvent is more lightweight than QemuSemaphore when HAVE_FUTEX is defined. + */ +typedef struct QemuEvent { +#ifndef HAVE_FUTEX + pthread_mutex_t lock; + pthread_cond_t cond; +#endif + unsigned value; + bool initialized; +} QemuEvent; + #ifdef _WIN32 #include "qemu/thread-win32.h" #else diff --git a/include/qemu/timer.h b/include/qemu/timer.h index abd2204..8b561cd 100644 --- a/include/qemu/timer.h +++ b/include/qemu/timer.h @@ -699,7 +699,7 @@ void timer_mod_anticipate(QEMUTimer *ts, int64_t expire_time); * * Returns: true if the timer is pending */ -bool timer_pending(QEMUTimer *ts); +bool timer_pending(const QEMUTimer *ts); /** * timer_expired: @@ -710,7 +710,7 @@ bool timer_pending(QEMUTimer *ts); * * Returns: true if the timer has expired */ -bool timer_expired(QEMUTimer *timer_head, int64_t current_time); +bool timer_expired(const QEMUTimer *timer_head, int64_t current_time); /** * timer_expire_time_ns: @@ -720,7 +720,7 @@ bool timer_expired(QEMUTimer *timer_head, int64_t current_time); * * Returns: the expiry time in nanoseconds */ -uint64_t timer_expire_time_ns(QEMUTimer *ts); +uint64_t timer_expire_time_ns(const QEMUTimer *ts); /** * timer_get: @@ -786,11 +786,12 @@ static inline int64_t qemu_soonest_timeout(int64_t timeout1, int64_t timeout2) } /** - * initclocks: + * qemu_init_clocks: + * @notify_cb: optional call-back for timer expiry * * Initialise the clock & timer infrastructure */ -void init_clocks(QEMUTimerListNotifyCB *notify_cb); +void qemu_init_clocks(QEMUTimerListNotifyCB *notify_cb); static inline int64_t get_max_clock_jump(void) { @@ -850,12 +851,11 @@ static inline int64_t get_clock(void) /*******************************************/ /* host CPU ticks (if available) */ -#if defined(_ARCH_PPC) +#if defined(_ARCH_PPC64) static inline int64_t cpu_get_host_ticks(void) { int64_t retval; -#ifdef _ARCH_PPC64 /* This reads timebase in one 64bit go and includes Cell workaround from: http://ozlabs.org/pipermail/linuxppc-dev/2006-October/027052.html */ @@ -863,16 +863,6 @@ static inline int64_t cpu_get_host_ticks(void) "cmpwi %0,0\n\t" "beq- $-8" : "=r" (retval)); -#else - /* http://ozlabs.org/pipermail/linuxppc-dev/1999-October/003889.html */ - unsigned long junk; - __asm__ __volatile__ ("mfspr %1,269\n\t" /* mftbu */ - "mfspr %L0,268\n\t" /* mftb */ - "mfspr %0,269\n\t" /* mftbu */ - "cmpw %0,%1\n\t" - "bne $-16" - : "=r" (retval), "=r" (junk)); -#endif return retval; } diff --git a/include/qemu/typedefs.h b/include/qemu/typedefs.h index 507f081..4a94af9 100644 --- a/include/qemu/typedefs.h +++ b/include/qemu/typedefs.h @@ -109,7 +109,7 @@ typedef struct QString QString; typedef struct RAMBlock RAMBlock; typedef struct Range Range; typedef struct ReservedRegion ReservedRegion; -typedef struct SaveLiveCompletePrecopyThreadData SaveLiveCompletePrecopyThreadData; +typedef struct SaveCompletePrecopyThreadData SaveCompletePrecopyThreadData; typedef struct SHPCDevice SHPCDevice; typedef struct SSIBus SSIBus; typedef struct TCGCPUOps TCGCPUOps; @@ -135,7 +135,7 @@ typedef struct IRQState *qemu_irq; typedef void (*qemu_irq_handler)(void *opaque, int n, int level); typedef bool (*MigrationLoadThread)(void *opaque, bool *should_quit, Error **errp); -typedef bool (*SaveLiveCompletePrecopyThreadHandler)(SaveLiveCompletePrecopyThreadData *d, - Error **errp); +typedef bool (*SaveCompletePrecopyThreadHandler)(SaveCompletePrecopyThreadData *d, + Error **errp); #endif /* QEMU_TYPEDEFS_H */ diff --git a/include/qemu/xattr.h b/include/qemu/xattr.h index b08a934..224ba12 100644 --- a/include/qemu/xattr.h +++ b/include/qemu/xattr.h @@ -26,7 +26,11 @@ # define ENOATTR ENODATA # endif # ifndef CONFIG_WIN32 -# include <sys/xattr.h> +# ifdef CONFIG_FREEBSD +# include <sys/extattr.h> +# else +# include <sys/xattr.h> +# endif # endif #endif diff --git a/include/qobject/qdict.h b/include/qobject/qdict.h index 903e6e5..861996f 100644 --- a/include/qobject/qdict.h +++ b/include/qobject/qdict.h @@ -57,6 +57,7 @@ void qdict_put_str(QDict *qdict, const char *key, const char *value); double qdict_get_double(const QDict *qdict, const char *key); int64_t qdict_get_int(const QDict *qdict, const char *key); +uint64_t qdict_get_uint(const QDict *qdict, const char *key); bool qdict_get_bool(const QDict *qdict, const char *key); QList *qdict_get_qlist(const QDict *qdict, const char *key); QDict *qdict_get_qdict(const QDict *qdict, const char *key); diff --git a/include/qobject/qobject.h b/include/qobject/qobject.h index a6244d0..02f4c6a 100644 --- a/include/qobject/qobject.h +++ b/include/qobject/qobject.h @@ -32,6 +32,7 @@ #ifndef QOBJECT_H #define QOBJECT_H +#include "qemu/atomic.h" #include "qapi/qapi-builtin-types.h" /* Not for use outside include/qobject/ */ @@ -73,7 +74,7 @@ QEMU_BUILD_BUG_MSG(QTYPE__MAX != 7, static inline void qobject_ref_impl(QObject *obj) { if (obj) { - obj->base.refcnt++; + qatomic_inc(&obj->base.refcnt); } } @@ -95,7 +96,7 @@ void qobject_destroy(QObject *obj); static inline void qobject_unref_impl(QObject *obj) { assert(!obj || obj->base.refcnt); - if (obj && --obj->base.refcnt == 0) { + if (obj && qatomic_fetch_dec(&obj->base.refcnt) == 1) { qobject_destroy(obj); } } diff --git a/include/qom/object.h b/include/qom/object.h index 9192265..26df613 100644 --- a/include/qom/object.h +++ b/include/qom/object.h @@ -280,7 +280,7 @@ struct Object static void \ module_obj_name##_finalize(Object *obj); \ static void \ - module_obj_name##_class_init(ObjectClass *oc, void *data); \ + module_obj_name##_class_init(ObjectClass *oc, const void *data); \ static void \ module_obj_name##_init(Object *obj); \ \ @@ -294,7 +294,7 @@ struct Object .class_size = CLASS_SIZE, \ .class_init = module_obj_name##_class_init, \ .abstract = ABSTRACT, \ - .interfaces = (InterfaceInfo[]) { __VA_ARGS__ } , \ + .interfaces = (const InterfaceInfo[]) { __VA_ARGS__ } , \ }; \ \ static void \ @@ -445,7 +445,8 @@ struct Object * class will have already been initialized so the type is only responsible * for initializing its own members. * @instance_post_init: This function is called to finish initialization of - * an object, after all @instance_init functions were called. + * an object, after all @instance_init functions were called, as well as + * @instance_post_init functions for the parent classes. * @instance_finalize: This function is called during object destruction. This * is called before the parent @instance_finalize function has been called. * An object should only free the members that are unique to its type in this @@ -486,11 +487,11 @@ struct TypeInfo bool abstract; size_t class_size; - void (*class_init)(ObjectClass *klass, void *data); - void (*class_base_init)(ObjectClass *klass, void *data); - void *class_data; + void (*class_init)(ObjectClass *klass, const void *data); + void (*class_base_init)(ObjectClass *klass, const void *data); + const void *class_data; - InterfaceInfo *interfaces; + const InterfaceInfo *interfaces; }; /** diff --git a/include/semihosting/common-semi.h b/include/semihosting/common-semi.h index 0a91db7..aa511a4 100644 --- a/include/semihosting/common-semi.h +++ b/include/semihosting/common-semi.h @@ -35,5 +35,11 @@ #define COMMON_SEMI_H void do_common_semihosting(CPUState *cs); +uint64_t common_semi_arg(CPUState *cs, int argno); +void common_semi_set_ret(CPUState *cs, uint64_t ret); +bool is_64bit_semihosting(CPUArchState *env); +bool common_semi_sys_exit_is_extended(CPUState *cs); +uint64_t common_semi_stack_bottom(CPUState *cs); +bool common_semi_has_synccache(CPUArchState *env); #endif /* COMMON_SEMI_H */ diff --git a/include/semihosting/guestfd.h b/include/semihosting/guestfd.h index 3d426fe..a7ea104 100644 --- a/include/semihosting/guestfd.h +++ b/include/semihosting/guestfd.h @@ -35,13 +35,6 @@ typedef struct GuestFD { }; } GuestFD; -/* - * For ARM semihosting, we have a separate structure for routing - * data for the console which is outside the guest fd address space. - */ -extern GuestFD console_in_gf; -extern GuestFD console_out_gf; - /** * alloc_guestfd: * diff --git a/include/semihosting/semihost.h b/include/semihosting/semihost.h index 97d2a2b..231dc89 100644 --- a/include/semihosting/semihost.h +++ b/include/semihosting/semihost.h @@ -26,32 +26,6 @@ typedef enum SemihostingTarget { SEMIHOSTING_TARGET_GDB } SemihostingTarget; -#ifdef CONFIG_USER_ONLY -static inline bool semihosting_enabled(bool is_user) -{ - return true; -} - -static inline SemihostingTarget semihosting_get_target(void) -{ - return SEMIHOSTING_TARGET_AUTO; -} - -static inline const char *semihosting_get_arg(int i) -{ - return NULL; -} - -static inline int semihosting_get_argc(void) -{ - return 0; -} - -static inline const char *semihosting_get_cmdline(void) -{ - return NULL; -} -#else /* !CONFIG_USER_ONLY */ /** * semihosting_enabled: * @is_user: true if guest code is in usermode (i.e. not privileged) @@ -59,17 +33,20 @@ static inline const char *semihosting_get_cmdline(void) * Return true if guest code is allowed to make semihosting calls. */ bool semihosting_enabled(bool is_user); +bool semihosting_arm_compatible(void); +void semihosting_arm_compatible_init(void); + SemihostingTarget semihosting_get_target(void); const char *semihosting_get_arg(int i); int semihosting_get_argc(void); const char *semihosting_get_cmdline(void); void semihosting_arg_fallback(const char *file, const char *cmd); + /* for vl.c hooks */ void qemu_semihosting_enable(void); int qemu_semihosting_config_options(const char *optstr); void qemu_semihosting_chardev_init(void); void qemu_semihosting_console_init(Chardev *); -#endif /* CONFIG_USER_ONLY */ void qemu_semihosting_guestfd_init(void); #endif /* SEMIHOST_H */ diff --git a/include/semihosting/syscalls.h b/include/semihosting/syscalls.h index 6627c45..03aa45b 100644 --- a/include/semihosting/syscalls.h +++ b/include/semihosting/syscalls.h @@ -9,7 +9,7 @@ #ifndef SEMIHOSTING_SYSCALLS_H #define SEMIHOSTING_SYSCALLS_H -#include "exec/cpu-defs.h" +#include "exec/vaddr.h" #include "gdbstub/syscalls.h" /* @@ -24,23 +24,23 @@ typedef struct GuestFD GuestFD; void semihost_sys_open(CPUState *cs, gdb_syscall_complete_cb complete, - target_ulong fname, target_ulong fname_len, + vaddr fname, uint64_t fname_len, int gdb_flags, int mode); void semihost_sys_close(CPUState *cs, gdb_syscall_complete_cb complete, int fd); void semihost_sys_read(CPUState *cs, gdb_syscall_complete_cb complete, - int fd, target_ulong buf, target_ulong len); + int fd, vaddr buf, uint64_t len); void semihost_sys_read_gf(CPUState *cs, gdb_syscall_complete_cb complete, - GuestFD *gf, target_ulong buf, target_ulong len); + GuestFD *gf, vaddr buf, uint64_t len); void semihost_sys_write(CPUState *cs, gdb_syscall_complete_cb complete, - int fd, target_ulong buf, target_ulong len); + int fd, vaddr buf, uint64_t len); void semihost_sys_write_gf(CPUState *cs, gdb_syscall_complete_cb complete, - GuestFD *gf, target_ulong buf, target_ulong len); + GuestFD *gf, vaddr buf, uint64_t len); void semihost_sys_lseek(CPUState *cs, gdb_syscall_complete_cb complete, int fd, int64_t off, int gdb_whence); @@ -50,27 +50,27 @@ void semihost_sys_isatty(CPUState *cs, gdb_syscall_complete_cb complete, void semihost_sys_flen(CPUState *cs, gdb_syscall_complete_cb fstat_cb, gdb_syscall_complete_cb flen_cb, - int fd, target_ulong fstat_addr); + int fd, vaddr fstat_addr); void semihost_sys_fstat(CPUState *cs, gdb_syscall_complete_cb complete, - int fd, target_ulong addr); + int fd, vaddr addr); void semihost_sys_stat(CPUState *cs, gdb_syscall_complete_cb complete, - target_ulong fname, target_ulong fname_len, - target_ulong addr); + vaddr fname, uint64_t fname_len, + vaddr addr); void semihost_sys_remove(CPUState *cs, gdb_syscall_complete_cb complete, - target_ulong fname, target_ulong fname_len); + vaddr fname, uint64_t fname_len); void semihost_sys_rename(CPUState *cs, gdb_syscall_complete_cb complete, - target_ulong oname, target_ulong oname_len, - target_ulong nname, target_ulong nname_len); + vaddr oname, uint64_t oname_len, + vaddr nname, uint64_t nname_len); void semihost_sys_system(CPUState *cs, gdb_syscall_complete_cb complete, - target_ulong cmd, target_ulong cmd_len); + vaddr cmd, uint64_t cmd_len); void semihost_sys_gettimeofday(CPUState *cs, gdb_syscall_complete_cb complete, - target_ulong tv_addr, target_ulong tz_addr); + vaddr tv_addr, vaddr tz_addr); void semihost_sys_poll_one(CPUState *cs, gdb_syscall_complete_cb complete, int fd, GIOCondition cond, int timeout); diff --git a/include/semihosting/uaccess.h b/include/semihosting/uaccess.h index 6bc90b1..2093a49 100644 --- a/include/semihosting/uaccess.h +++ b/include/semihosting/uaccess.h @@ -15,9 +15,9 @@ #endif #include "exec/cpu-common.h" -#include "exec/cpu-defs.h" #include "exec/tswap.h" #include "exec/page-protection.h" +#include "exec/vaddr.h" /** * get_user_u64: @@ -89,8 +89,8 @@ * * The returned pointer should be freed using uaccess_unlock_user(). */ -void *uaccess_lock_user(CPUArchState *env, target_ulong addr, - target_ulong len, bool copy); +void *uaccess_lock_user(CPUArchState *env, vaddr addr, + size_t len, bool copy); /** * lock_user: * @@ -103,7 +103,7 @@ void *uaccess_lock_user(CPUArchState *env, target_ulong addr, * * The returned string should be freed using uaccess_unlock_user(). */ -char *uaccess_lock_user_string(CPUArchState *env, target_ulong addr); +char *uaccess_lock_user_string(CPUArchState *env, vaddr addr); /** * uaccess_lock_user_string: * @@ -112,10 +112,10 @@ char *uaccess_lock_user_string(CPUArchState *env, target_ulong addr); #define lock_user_string(p) uaccess_lock_user_string(env, p) void uaccess_unlock_user(CPUArchState *env, void *p, - target_ulong addr, target_ulong len); + vaddr addr, size_t len); #define unlock_user(s, args, len) uaccess_unlock_user(env, s, args, len) -ssize_t uaccess_strlen_user(CPUArchState *env, target_ulong addr); +ssize_t uaccess_strlen_user(CPUArchState *env, vaddr addr); #define target_strlen(p) uaccess_strlen_user(env, p) #endif /* SEMIHOSTING_SOFTMMU_UACCESS_H */ diff --git a/include/standard-headers/asm-x86/setup_data.h b/include/standard-headers/asm-x86/setup_data.h index 09355f5..2e446c1d 100644 --- a/include/standard-headers/asm-x86/setup_data.h +++ b/include/standard-headers/asm-x86/setup_data.h @@ -13,12 +13,13 @@ #define SETUP_CC_BLOB 7 #define SETUP_IMA 8 #define SETUP_RNG_SEED 9 -#define SETUP_ENUM_MAX SETUP_RNG_SEED +#define SETUP_KEXEC_KHO 10 +#define SETUP_ENUM_MAX SETUP_KEXEC_KHO #define SETUP_INDIRECT (1<<31) #define SETUP_TYPE_MAX (SETUP_ENUM_MAX | SETUP_INDIRECT) -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include "standard-headers/linux/types.h" @@ -78,6 +79,16 @@ struct ima_setup_data { uint64_t size; } QEMU_PACKED; -#endif /* __ASSEMBLY__ */ +/* + * Locations of kexec handover metadata + */ +struct kho_data { + uint64_t fdt_addr; + uint64_t fdt_size; + uint64_t scratch_addr; + uint64_t scratch_size; +} QEMU_PACKED; + +#endif /* __ASSEMBLER__ */ #endif /* _ASM_X86_SETUP_DATA_H */ diff --git a/include/standard-headers/drm/drm_fourcc.h b/include/standard-headers/drm/drm_fourcc.h index 7086477..cef077d 100644 --- a/include/standard-headers/drm/drm_fourcc.h +++ b/include/standard-headers/drm/drm_fourcc.h @@ -209,6 +209,10 @@ extern "C" { #define DRM_FORMAT_RGBA1010102 fourcc_code('R', 'A', '3', '0') /* [31:0] R:G:B:A 10:10:10:2 little endian */ #define DRM_FORMAT_BGRA1010102 fourcc_code('B', 'A', '3', '0') /* [31:0] B:G:R:A 10:10:10:2 little endian */ +/* 48 bpp RGB */ +#define DRM_FORMAT_RGB161616 fourcc_code('R', 'G', '4', '8') /* [47:0] R:G:B 16:16:16 little endian */ +#define DRM_FORMAT_BGR161616 fourcc_code('B', 'G', '4', '8') /* [47:0] B:G:R 16:16:16 little endian */ + /* 64 bpp RGB */ #define DRM_FORMAT_XRGB16161616 fourcc_code('X', 'R', '4', '8') /* [63:0] x:R:G:B 16:16:16:16 little endian */ #define DRM_FORMAT_XBGR16161616 fourcc_code('X', 'B', '4', '8') /* [63:0] x:B:G:R 16:16:16:16 little endian */ @@ -217,7 +221,7 @@ extern "C" { #define DRM_FORMAT_ABGR16161616 fourcc_code('A', 'B', '4', '8') /* [63:0] A:B:G:R 16:16:16:16 little endian */ /* - * Floating point 64bpp RGB + * Half-Floating point - 16b/component * IEEE 754-2008 binary16 half-precision float * [15:0] sign:exponent:mantissa 1:5:10 */ @@ -227,6 +231,20 @@ extern "C" { #define DRM_FORMAT_ARGB16161616F fourcc_code('A', 'R', '4', 'H') /* [63:0] A:R:G:B 16:16:16:16 little endian */ #define DRM_FORMAT_ABGR16161616F fourcc_code('A', 'B', '4', 'H') /* [63:0] A:B:G:R 16:16:16:16 little endian */ +#define DRM_FORMAT_R16F fourcc_code('R', ' ', ' ', 'H') /* [15:0] R 16 little endian */ +#define DRM_FORMAT_GR1616F fourcc_code('G', 'R', ' ', 'H') /* [31:0] G:R 16:16 little endian */ +#define DRM_FORMAT_BGR161616F fourcc_code('B', 'G', 'R', 'H') /* [47:0] B:G:R 16:16:16 little endian */ + +/* + * Floating point - 32b/component + * IEEE 754-2008 binary32 float + * [31:0] sign:exponent:mantissa 1:8:23 + */ +#define DRM_FORMAT_R32F fourcc_code('R', ' ', ' ', 'F') /* [31:0] R 32 little endian */ +#define DRM_FORMAT_GR3232F fourcc_code('G', 'R', ' ', 'F') /* [63:0] R:G 32:32 little endian */ +#define DRM_FORMAT_BGR323232F fourcc_code('B', 'G', 'R', 'F') /* [95:0] R:G:B 32:32:32 little endian */ +#define DRM_FORMAT_ABGR32323232F fourcc_code('A', 'B', '8', 'F') /* [127:0] R:G:B:A 32:32:32:32 little endian */ + /* * RGBA format with 10-bit components packed in 64-bit per pixel, with 6 bits * of unused padding per component: @@ -377,6 +395,42 @@ extern "C" { #define DRM_FORMAT_Q401 fourcc_code('Q', '4', '0', '1') /* + * 3 plane YCbCr LSB aligned + * In order to use these formats in a similar fashion to MSB aligned ones + * implementation can multiply the values by 2^6=64. For that reason the padding + * must only contain zeros. + * index 0 = Y plane, [15:0] z:Y [6:10] little endian + * index 1 = Cr plane, [15:0] z:Cr [6:10] little endian + * index 2 = Cb plane, [15:0] z:Cb [6:10] little endian + */ +#define DRM_FORMAT_S010 fourcc_code('S', '0', '1', '0') /* 2x2 subsampled Cb (1) and Cr (2) planes 10 bits per channel */ +#define DRM_FORMAT_S210 fourcc_code('S', '2', '1', '0') /* 2x1 subsampled Cb (1) and Cr (2) planes 10 bits per channel */ +#define DRM_FORMAT_S410 fourcc_code('S', '4', '1', '0') /* non-subsampled Cb (1) and Cr (2) planes 10 bits per channel */ + +/* + * 3 plane YCbCr LSB aligned + * In order to use these formats in a similar fashion to MSB aligned ones + * implementation can multiply the values by 2^4=16. For that reason the padding + * must only contain zeros. + * index 0 = Y plane, [15:0] z:Y [4:12] little endian + * index 1 = Cr plane, [15:0] z:Cr [4:12] little endian + * index 2 = Cb plane, [15:0] z:Cb [4:12] little endian + */ +#define DRM_FORMAT_S012 fourcc_code('S', '0', '1', '2') /* 2x2 subsampled Cb (1) and Cr (2) planes 12 bits per channel */ +#define DRM_FORMAT_S212 fourcc_code('S', '2', '1', '2') /* 2x1 subsampled Cb (1) and Cr (2) planes 12 bits per channel */ +#define DRM_FORMAT_S412 fourcc_code('S', '4', '1', '2') /* non-subsampled Cb (1) and Cr (2) planes 12 bits per channel */ + +/* + * 3 plane YCbCr + * index 0 = Y plane, [15:0] Y little endian + * index 1 = Cr plane, [15:0] Cr little endian + * index 2 = Cb plane, [15:0] Cb little endian + */ +#define DRM_FORMAT_S016 fourcc_code('S', '0', '1', '6') /* 2x2 subsampled Cb (1) and Cr (2) planes 16 bits per channel */ +#define DRM_FORMAT_S216 fourcc_code('S', '2', '1', '6') /* 2x1 subsampled Cb (1) and Cr (2) planes 16 bits per channel */ +#define DRM_FORMAT_S416 fourcc_code('S', '4', '1', '6') /* non-subsampled Cb (1) and Cr (2) planes 16 bits per channel */ + +/* * 3 plane YCbCr * index 0: Y plane, [7:0] Y * index 1: Cb plane, [7:0] Cb @@ -420,6 +474,8 @@ extern "C" { #define DRM_FORMAT_MOD_VENDOR_ARM 0x08 #define DRM_FORMAT_MOD_VENDOR_ALLWINNER 0x09 #define DRM_FORMAT_MOD_VENDOR_AMLOGIC 0x0a +#define DRM_FORMAT_MOD_VENDOR_MTK 0x0b +#define DRM_FORMAT_MOD_VENDOR_APPLE 0x0c /* add more to the end as needed */ @@ -1452,6 +1508,90 @@ drm_fourcc_canonicalize_nvidia_format_mod(uint64_t modifier) */ #define AMLOGIC_FBC_OPTION_MEM_SAVING (1ULL << 0) +/* MediaTek modifiers + * Bits Parameter Notes + * ----- ------------------------ --------------------------------------------- + * 7: 0 TILE LAYOUT Values are MTK_FMT_MOD_TILE_* + * 15: 8 COMPRESSION Values are MTK_FMT_MOD_COMPRESS_* + * 23:16 10 BIT LAYOUT Values are MTK_FMT_MOD_10BIT_LAYOUT_* + * + */ + +#define DRM_FORMAT_MOD_MTK(__flags) fourcc_mod_code(MTK, __flags) + +/* + * MediaTek Tiled Modifier + * The lowest 8 bits of the modifier is used to specify the tiling + * layout. Only the 16L_32S tiling is used for now, but we define an + * "untiled" version and leave room for future expansion. + */ +#define MTK_FMT_MOD_TILE_MASK 0xf +#define MTK_FMT_MOD_TILE_NONE 0x0 +#define MTK_FMT_MOD_TILE_16L32S 0x1 + +/* + * Bits 8-15 specify compression options + */ +#define MTK_FMT_MOD_COMPRESS_MASK (0xf << 8) +#define MTK_FMT_MOD_COMPRESS_NONE (0x0 << 8) +#define MTK_FMT_MOD_COMPRESS_V1 (0x1 << 8) + +/* + * Bits 16-23 specify how the bits of 10 bit formats are + * stored out in memory + */ +#define MTK_FMT_MOD_10BIT_LAYOUT_MASK (0xf << 16) +#define MTK_FMT_MOD_10BIT_LAYOUT_PACKED (0x0 << 16) +#define MTK_FMT_MOD_10BIT_LAYOUT_LSBTILED (0x1 << 16) +#define MTK_FMT_MOD_10BIT_LAYOUT_LSBRASTER (0x2 << 16) + +/* alias for the most common tiling format */ +#define DRM_FORMAT_MOD_MTK_16L_32S_TILE DRM_FORMAT_MOD_MTK(MTK_FMT_MOD_TILE_16L32S) + +/* + * Apple GPU-tiled layouts. + * + * Apple GPUs support nonlinear tilings with optional lossless compression. + * + * GPU-tiled images are divided into 16KiB tiles: + * + * Bytes per pixel Tile size + * --------------- --------- + * 1 128x128 + * 2 128x64 + * 4 64x64 + * 8 64x32 + * 16 32x32 + * + * Tiles are raster-order. Pixels within a tile are interleaved (Morton order). + * + * Compressed images pad the body to 128-bytes and are immediately followed by a + * metadata section. The metadata section rounds the image dimensions to + * powers-of-two and contains 8 bytes for each 16x16 compression subtile. + * Subtiles are interleaved (Morton order). + * + * All images are 128-byte aligned. + * + * These layouts fundamentally do not have meaningful strides. No matter how we + * specify strides for these layouts, userspace unaware of Apple image layouts + * will be unable to use correctly the specified stride for any purpose. + * Userspace aware of the image layouts do not use strides. The most "correct" + * convention would be setting the image stride to 0. Unfortunately, some + * software assumes the stride is at least (width * bytes per pixel). We + * therefore require that stride equals (width * bytes per pixel). Since the + * stride is arbitrary here, we pick the simplest convention. + * + * Although containing two sections, compressed image layouts are treated in + * software as a single plane. This is modelled after AFBC, a similar + * scheme. Attempting to separate the sections to be "explicit" in DRM would + * only generate more confusion, as software does not treat the image this way. + * + * For detailed information on the hardware image layouts, see + * https://docs.mesa3d.org/drivers/asahi.html#image-layouts + */ +#define DRM_FORMAT_MOD_APPLE_GPU_TILED fourcc_mod_code(APPLE, 1) +#define DRM_FORMAT_MOD_APPLE_GPU_TILED_COMPRESSED fourcc_mod_code(APPLE, 2) + /* * AMD modifiers * diff --git a/include/standard-headers/linux/const.h b/include/standard-headers/linux/const.h index 2122610..95ede23 100644 --- a/include/standard-headers/linux/const.h +++ b/include/standard-headers/linux/const.h @@ -33,7 +33,7 @@ * Missing __asm__ support * * __BIT128() would not work in the __asm__ code, as it shifts an - * 'unsigned __init128' data type as direct representation of + * 'unsigned __int128' data type as direct representation of * 128 bit constants is not supported in the gcc compiler, as * they get silently truncated. * diff --git a/include/standard-headers/linux/ethtool.h b/include/standard-headers/linux/ethtool.h index e833825..dc24512 100644 --- a/include/standard-headers/linux/ethtool.h +++ b/include/standard-headers/linux/ethtool.h @@ -2059,6 +2059,24 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_10baseT1S_Half_BIT = 100, ETHTOOL_LINK_MODE_10baseT1S_P2MP_Half_BIT = 101, ETHTOOL_LINK_MODE_10baseT1BRR_Full_BIT = 102, + ETHTOOL_LINK_MODE_200000baseCR_Full_BIT = 103, + ETHTOOL_LINK_MODE_200000baseKR_Full_BIT = 104, + ETHTOOL_LINK_MODE_200000baseDR_Full_BIT = 105, + ETHTOOL_LINK_MODE_200000baseDR_2_Full_BIT = 106, + ETHTOOL_LINK_MODE_200000baseSR_Full_BIT = 107, + ETHTOOL_LINK_MODE_200000baseVR_Full_BIT = 108, + ETHTOOL_LINK_MODE_400000baseCR2_Full_BIT = 109, + ETHTOOL_LINK_MODE_400000baseKR2_Full_BIT = 110, + ETHTOOL_LINK_MODE_400000baseDR2_Full_BIT = 111, + ETHTOOL_LINK_MODE_400000baseDR2_2_Full_BIT = 112, + ETHTOOL_LINK_MODE_400000baseSR2_Full_BIT = 113, + ETHTOOL_LINK_MODE_400000baseVR2_Full_BIT = 114, + ETHTOOL_LINK_MODE_800000baseCR4_Full_BIT = 115, + ETHTOOL_LINK_MODE_800000baseKR4_Full_BIT = 116, + ETHTOOL_LINK_MODE_800000baseDR4_Full_BIT = 117, + ETHTOOL_LINK_MODE_800000baseDR4_2_Full_BIT = 118, + ETHTOOL_LINK_MODE_800000baseSR4_Full_BIT = 119, + ETHTOOL_LINK_MODE_800000baseVR4_Full_BIT = 120, /* must be last entry */ __ETHTOOL_LINK_MODE_MASK_NBITS @@ -2271,73 +2289,81 @@ static inline int ethtool_validate_duplex(uint8_t duplex) * be exploited to reduce the RSS queue spread. */ #define RXH_XFRM_SYM_XOR (1 << 0) +/* Similar to SYM_XOR, except that one copy of the XOR'ed fields is replaced by + * an OR of the same fields + */ +#define RXH_XFRM_SYM_OR_XOR (1 << 1) #define RXH_XFRM_NO_CHANGE 0xff -/* L2-L4 network traffic flow types */ -#define TCP_V4_FLOW 0x01 /* hash or spec (tcp_ip4_spec) */ -#define UDP_V4_FLOW 0x02 /* hash or spec (udp_ip4_spec) */ -#define SCTP_V4_FLOW 0x03 /* hash or spec (sctp_ip4_spec) */ -#define AH_ESP_V4_FLOW 0x04 /* hash only */ -#define TCP_V6_FLOW 0x05 /* hash or spec (tcp_ip6_spec; nfc only) */ -#define UDP_V6_FLOW 0x06 /* hash or spec (udp_ip6_spec; nfc only) */ -#define SCTP_V6_FLOW 0x07 /* hash or spec (sctp_ip6_spec; nfc only) */ -#define AH_ESP_V6_FLOW 0x08 /* hash only */ -#define AH_V4_FLOW 0x09 /* hash or spec (ah_ip4_spec) */ -#define ESP_V4_FLOW 0x0a /* hash or spec (esp_ip4_spec) */ -#define AH_V6_FLOW 0x0b /* hash or spec (ah_ip6_spec; nfc only) */ -#define ESP_V6_FLOW 0x0c /* hash or spec (esp_ip6_spec; nfc only) */ -#define IPV4_USER_FLOW 0x0d /* spec only (usr_ip4_spec) */ -#define IP_USER_FLOW IPV4_USER_FLOW -#define IPV6_USER_FLOW 0x0e /* spec only (usr_ip6_spec; nfc only) */ -#define IPV4_FLOW 0x10 /* hash only */ -#define IPV6_FLOW 0x11 /* hash only */ -#define ETHER_FLOW 0x12 /* spec only (ether_spec) */ - -/* Used for GTP-U IPv4 and IPv6. - * The format of GTP packets only includes - * elements such as TEID and GTP version. - * It is primarily intended for data communication of the UE. - */ -#define GTPU_V4_FLOW 0x13 /* hash only */ -#define GTPU_V6_FLOW 0x14 /* hash only */ - -/* Use for GTP-C IPv4 and v6. - * The format of these GTP packets does not include TEID. - * Primarily expected to be used for communication - * to create sessions for UE data communication, - * commonly referred to as CSR (Create Session Request). - */ -#define GTPC_V4_FLOW 0x15 /* hash only */ -#define GTPC_V6_FLOW 0x16 /* hash only */ - -/* Use for GTP-C IPv4 and v6. - * Unlike GTPC_V4_FLOW, the format of these GTP packets includes TEID. - * After session creation, it becomes this packet. - * This is mainly used for requests to realize UE handover. - */ -#define GTPC_TEID_V4_FLOW 0x17 /* hash only */ -#define GTPC_TEID_V6_FLOW 0x18 /* hash only */ - -/* Use for GTP-U and extended headers for the PSC (PDU Session Container). - * The format of these GTP packets includes TEID and QFI. - * In 5G communication using UPF (User Plane Function), - * data communication with this extended header is performed. - */ -#define GTPU_EH_V4_FLOW 0x19 /* hash only */ -#define GTPU_EH_V6_FLOW 0x1a /* hash only */ - -/* Use for GTP-U IPv4 and v6 PSC (PDU Session Container) extended headers. - * This differs from GTPU_EH_V(4|6)_FLOW in that it is distinguished by - * UL/DL included in the PSC. - * There are differences in the data included based on Downlink/Uplink, - * and can be used to distinguish packets. - * The functions described so far are useful when you want to - * handle communication from the mobile network in UPF, PGW, etc. - */ -#define GTPU_UL_V4_FLOW 0x1b /* hash only */ -#define GTPU_UL_V6_FLOW 0x1c /* hash only */ -#define GTPU_DL_V4_FLOW 0x1d /* hash only */ -#define GTPU_DL_V6_FLOW 0x1e /* hash only */ +enum { + /* L2-L4 network traffic flow types */ + TCP_V4_FLOW = 0x01, /* hash or spec (tcp_ip4_spec) */ + UDP_V4_FLOW = 0x02, /* hash or spec (udp_ip4_spec) */ + SCTP_V4_FLOW = 0x03, /* hash or spec (sctp_ip4_spec) */ + AH_ESP_V4_FLOW = 0x04, /* hash only */ + TCP_V6_FLOW = 0x05, /* hash or spec (tcp_ip6_spec; nfc only) */ + UDP_V6_FLOW = 0x06, /* hash or spec (udp_ip6_spec; nfc only) */ + SCTP_V6_FLOW = 0x07, /* hash or spec (sctp_ip6_spec; nfc only) */ + AH_ESP_V6_FLOW = 0x08, /* hash only */ + AH_V4_FLOW = 0x09, /* hash or spec (ah_ip4_spec) */ + ESP_V4_FLOW = 0x0a, /* hash or spec (esp_ip4_spec) */ + AH_V6_FLOW = 0x0b, /* hash or spec (ah_ip6_spec; nfc only) */ + ESP_V6_FLOW = 0x0c, /* hash or spec (esp_ip6_spec; nfc only) */ + IPV4_USER_FLOW = 0x0d, /* spec only (usr_ip4_spec) */ + IP_USER_FLOW = IPV4_USER_FLOW, + IPV6_USER_FLOW = 0x0e, /* spec only (usr_ip6_spec; nfc only) */ + IPV4_FLOW = 0x10, /* hash only */ + IPV6_FLOW = 0x11, /* hash only */ + ETHER_FLOW = 0x12, /* hash or spec (ether_spec) */ + + /* Used for GTP-U IPv4 and IPv6. + * The format of GTP packets only includes + * elements such as TEID and GTP version. + * It is primarily intended for data communication of the UE. + */ + GTPU_V4_FLOW = 0x13, /* hash only */ + GTPU_V6_FLOW = 0x14, /* hash only */ + + /* Use for GTP-C IPv4 and v6. + * The format of these GTP packets does not include TEID. + * Primarily expected to be used for communication + * to create sessions for UE data communication, + * commonly referred to as CSR (Create Session Request). + */ + GTPC_V4_FLOW = 0x15, /* hash only */ + GTPC_V6_FLOW = 0x16, /* hash only */ + + /* Use for GTP-C IPv4 and v6. + * Unlike GTPC_V4_FLOW, the format of these GTP packets includes TEID. + * After session creation, it becomes this packet. + * This is mainly used for requests to realize UE handover. + */ + GTPC_TEID_V4_FLOW = 0x17, /* hash only */ + GTPC_TEID_V6_FLOW = 0x18, /* hash only */ + + /* Use for GTP-U and extended headers for the PSC (PDU Session Container). + * The format of these GTP packets includes TEID and QFI. + * In 5G communication using UPF (User Plane Function), + * data communication with this extended header is performed. + */ + GTPU_EH_V4_FLOW = 0x19, /* hash only */ + GTPU_EH_V6_FLOW = 0x1a, /* hash only */ + + /* Use for GTP-U IPv4 and v6 PSC (PDU Session Container) extended headers. + * This differs from GTPU_EH_V(4|6)_FLOW in that it is distinguished by + * UL/DL included in the PSC. + * There are differences in the data included based on Downlink/Uplink, + * and can be used to distinguish packets. + * The functions described so far are useful when you want to + * handle communication from the mobile network in UPF, PGW, etc. + */ + GTPU_UL_V4_FLOW = 0x1b, /* hash only */ + GTPU_UL_V6_FLOW = 0x1c, /* hash only */ + GTPU_DL_V4_FLOW = 0x1d, /* hash only */ + GTPU_DL_V6_FLOW = 0x1e, /* hash only */ + + __FLOW_TYPE_COUNT, +}; /* Flag to enable additional fields in struct ethtool_rx_flow_spec */ #define FLOW_EXT 0x80000000 @@ -2345,7 +2371,7 @@ static inline int ethtool_validate_duplex(uint8_t duplex) /* Flag to enable RSS spreading of traffic matching rule (nfc only) */ #define FLOW_RSS 0x20000000 -/* L3-L4 network traffic flow hash options */ +/* L2-L4 network traffic flow hash options */ #define RXH_L2DA (1 << 1) #define RXH_VLAN (1 << 2) #define RXH_L3_PROTO (1 << 3) @@ -2354,6 +2380,7 @@ static inline int ethtool_validate_duplex(uint8_t duplex) #define RXH_L4_B_0_1 (1 << 6) /* src port in case of TCP/UDP/SCTP */ #define RXH_L4_B_2_3 (1 << 7) /* dst port in case of TCP/UDP/SCTP */ #define RXH_GTP_TEID (1 << 8) /* teid in case of GTP */ +#define RXH_IP6_FL (1 << 9) /* IPv6 flow label */ #define RXH_DISCARD (1 << 31) #define RX_CLS_FLOW_DISC 0xffffffffffffffffULL diff --git a/include/standard-headers/linux/fuse.h b/include/standard-headers/linux/fuse.h index d303eff..abf3a78 100644 --- a/include/standard-headers/linux/fuse.h +++ b/include/standard-headers/linux/fuse.h @@ -229,6 +229,17 @@ * - FUSE_URING_IN_OUT_HEADER_SZ * - FUSE_URING_OP_IN_OUT_SZ * - enum fuse_uring_cmd + * + * 7.43 + * - add FUSE_REQUEST_TIMEOUT + * + * 7.44 + * - add FUSE_NOTIFY_INC_EPOCH + * + * 7.45 + * - add FUSE_COPY_FILE_RANGE_64 + * - add struct fuse_copy_file_range_out + * - add FUSE_NOTIFY_PRUNE */ #ifndef _LINUX_FUSE_H @@ -260,7 +271,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 42 +#define FUSE_KERNEL_MINOR_VERSION 45 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -431,6 +442,8 @@ struct fuse_file_lock { * of the request ID indicates resend requests * FUSE_ALLOW_IDMAP: allow creation of idmapped mounts * FUSE_OVER_IO_URING: Indicate that client supports io-uring + * FUSE_REQUEST_TIMEOUT: kernel supports timing out requests. + * init_out.request_timeout contains the timeout (in secs) */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -473,11 +486,11 @@ struct fuse_file_lock { #define FUSE_PASSTHROUGH (1ULL << 37) #define FUSE_NO_EXPORT_SUPPORT (1ULL << 38) #define FUSE_HAS_RESEND (1ULL << 39) - /* Obsolete alias for FUSE_DIRECT_IO_ALLOW_MMAP */ #define FUSE_DIRECT_IO_RELAX FUSE_DIRECT_IO_ALLOW_MMAP #define FUSE_ALLOW_IDMAP (1ULL << 40) #define FUSE_OVER_IO_URING (1ULL << 41) +#define FUSE_REQUEST_TIMEOUT (1ULL << 42) /** * CUSE INIT request/reply flags @@ -645,6 +658,7 @@ enum fuse_opcode { FUSE_SYNCFS = 50, FUSE_TMPFILE = 51, FUSE_STATX = 52, + FUSE_COPY_FILE_RANGE_64 = 53, /* CUSE specific operations */ CUSE_INIT = 4096, @@ -662,7 +676,8 @@ enum fuse_notify_code { FUSE_NOTIFY_RETRIEVE = 5, FUSE_NOTIFY_DELETE = 6, FUSE_NOTIFY_RESEND = 7, - FUSE_NOTIFY_CODE_MAX, + FUSE_NOTIFY_INC_EPOCH = 8, + FUSE_NOTIFY_PRUNE = 9, }; /* The read buffer is required to be at least 8k, but may be much larger */ @@ -905,7 +920,8 @@ struct fuse_init_out { uint16_t map_alignment; uint32_t flags2; uint32_t max_stack_depth; - uint32_t unused[6]; + uint16_t request_timeout; + uint16_t unused[11]; }; #define CUSE_INIT_INFO_MAX 4096 @@ -1100,6 +1116,12 @@ struct fuse_notify_retrieve_in { uint64_t dummy4; }; +struct fuse_notify_prune_out { + uint32_t count; + uint32_t padding; + uint64_t spare; +}; + struct fuse_backing_map { int32_t fd; uint32_t flags; @@ -1112,6 +1134,7 @@ struct fuse_backing_map { #define FUSE_DEV_IOC_BACKING_OPEN _IOW(FUSE_DEV_IOC_MAGIC, 1, \ struct fuse_backing_map) #define FUSE_DEV_IOC_BACKING_CLOSE _IOW(FUSE_DEV_IOC_MAGIC, 2, uint32_t) +#define FUSE_DEV_IOC_SYNC_INIT _IO(FUSE_DEV_IOC_MAGIC, 3) struct fuse_lseek_in { uint64_t fh; @@ -1134,6 +1157,11 @@ struct fuse_copy_file_range_in { uint64_t flags; }; +/* For FUSE_COPY_FILE_RANGE_64 */ +struct fuse_copy_file_range_out { + uint64_t bytes_copied; +}; + #define FUSE_SETUPMAPPING_FLAG_WRITE (1ull << 0) #define FUSE_SETUPMAPPING_FLAG_READ (1ull << 1) struct fuse_setupmapping_in { diff --git a/include/standard-headers/linux/input-event-codes.h b/include/standard-headers/linux/input-event-codes.h index 09ba0ad..c914ccd 100644 --- a/include/standard-headers/linux/input-event-codes.h +++ b/include/standard-headers/linux/input-event-codes.h @@ -27,6 +27,7 @@ #define INPUT_PROP_TOPBUTTONPAD 0x04 /* softbuttons at top of pad */ #define INPUT_PROP_POINTING_STICK 0x05 /* is a pointing stick */ #define INPUT_PROP_ACCELEROMETER 0x06 /* has accelerometer */ +#define INPUT_PROP_HAPTIC_TOUCHPAD 0x07 /* is a haptic touchpad */ #define INPUT_PROP_MAX 0x1f #define INPUT_PROP_CNT (INPUT_PROP_MAX + 1) @@ -601,6 +602,11 @@ #define BTN_DPAD_LEFT 0x222 #define BTN_DPAD_RIGHT 0x223 +#define BTN_GRIPL 0x224 +#define BTN_GRIPR 0x225 +#define BTN_GRIPL2 0x226 +#define BTN_GRIPR2 0x227 + #define KEY_ALS_TOGGLE 0x230 /* Ambient light sensor */ #define KEY_ROTATE_LOCK_TOGGLE 0x231 /* Display rotation lock */ #define KEY_REFRESH_RATE_TOGGLE 0x232 /* Display refresh rate toggle */ @@ -765,6 +771,9 @@ #define KEY_KBD_LCD_MENU4 0x2bb #define KEY_KBD_LCD_MENU5 0x2bc +/* Performance Boost key (Alienware)/G-Mode key (Dell) */ +#define KEY_PERFORMANCE 0x2bd + #define BTN_TRIGGER_HAPPY 0x2c0 #define BTN_TRIGGER_HAPPY1 0x2c0 #define BTN_TRIGGER_HAPPY2 0x2c1 @@ -925,7 +934,8 @@ #define SW_MUTE_DEVICE 0x0e /* set = device disabled */ #define SW_PEN_INSERTED 0x0f /* set = pen inserted */ #define SW_MACHINE_COVER 0x10 /* set = cover closed */ -#define SW_MAX_ 0x10 +#define SW_USB_INSERT 0x11 /* set = USB audio device connected */ +#define SW_MAX_ 0x11 #define SW_CNT (SW_MAX_+1) /* diff --git a/include/standard-headers/linux/input.h b/include/standard-headers/linux/input.h index 942ea6a..9aff211 100644 --- a/include/standard-headers/linux/input.h +++ b/include/standard-headers/linux/input.h @@ -272,6 +272,7 @@ struct input_mask { #define BUS_CEC 0x1E #define BUS_INTEL_ISHTP 0x1F #define BUS_AMD_SFH 0x20 +#define BUS_SDW 0x21 /* * MT_TOOL types @@ -426,6 +427,24 @@ struct ff_rumble_effect { }; /** + * struct ff_haptic_effect + * @hid_usage: hid_usage according to Haptics page (WAVEFORM_CLICK, etc.) + * @vendor_id: the waveform vendor ID if hid_usage is in the vendor-defined range + * @vendor_waveform_page: the vendor waveform page if hid_usage is in the vendor-defined range + * @intensity: strength of the effect as percentage + * @repeat_count: number of times to retrigger effect + * @retrigger_period: time before effect is retriggered (in ms) + */ +struct ff_haptic_effect { + uint16_t hid_usage; + uint16_t vendor_id; + uint8_t vendor_waveform_page; + uint16_t intensity; + uint16_t repeat_count; + uint16_t retrigger_period; +}; + +/** * struct ff_effect - defines force feedback effect * @type: type of the effect (FF_CONSTANT, FF_PERIODIC, FF_RAMP, FF_SPRING, * FF_FRICTION, FF_DAMPER, FF_RUMBLE, FF_INERTIA, or FF_CUSTOM) @@ -461,6 +480,7 @@ struct ff_effect { struct ff_periodic_effect periodic; struct ff_condition_effect condition[2]; /* One for each axis */ struct ff_rumble_effect rumble; + struct ff_haptic_effect haptic; } u; }; @@ -468,6 +488,7 @@ struct ff_effect { * Force feedback effect types */ +#define FF_HAPTIC 0x4f #define FF_RUMBLE 0x50 #define FF_PERIODIC 0x51 #define FF_CONSTANT 0x52 @@ -477,7 +498,7 @@ struct ff_effect { #define FF_INERTIA 0x56 #define FF_RAMP 0x57 -#define FF_EFFECT_MIN FF_RUMBLE +#define FF_EFFECT_MIN FF_HAPTIC #define FF_EFFECT_MAX FF_RAMP /* diff --git a/include/standard-headers/linux/pci_regs.h b/include/standard-headers/linux/pci_regs.h index 3445c49..07e06aa 100644 --- a/include/standard-headers/linux/pci_regs.h +++ b/include/standard-headers/linux/pci_regs.h @@ -207,6 +207,9 @@ /* Capability lists */ +#define PCI_CAP_ID_MASK 0x00ff /* Capability ID mask */ +#define PCI_CAP_LIST_NEXT_MASK 0xff00 /* Next Capability Pointer mask */ + #define PCI_CAP_LIST_ID 0 /* Capability ID */ #define PCI_CAP_ID_PM 0x01 /* Power Management */ #define PCI_CAP_ID_AGP 0x02 /* Accelerated Graphics Port */ @@ -486,6 +489,7 @@ #define PCI_EXP_TYPE_RC_EC 0xa /* Root Complex Event Collector */ #define PCI_EXP_FLAGS_SLOT 0x0100 /* Slot implemented */ #define PCI_EXP_FLAGS_IRQ 0x3e00 /* Interrupt message number */ +#define PCI_EXP_FLAGS_FLIT 0x8000 /* Flit Mode Supported */ #define PCI_EXP_DEVCAP 0x04 /* Device capabilities */ #define PCI_EXP_DEVCAP_PAYLOAD 0x00000007 /* Max_Payload_Size */ #define PCI_EXP_DEVCAP_PHANTOM 0x00000018 /* Phantom functions */ @@ -744,12 +748,14 @@ #define PCI_EXT_CAP_ID_L1SS 0x1E /* L1 PM Substates */ #define PCI_EXT_CAP_ID_PTM 0x1F /* Precision Time Measurement */ #define PCI_EXT_CAP_ID_DVSEC 0x23 /* Designated Vendor-Specific */ +#define PCI_EXT_CAP_ID_VF_REBAR 0x24 /* VF Resizable BAR */ #define PCI_EXT_CAP_ID_DLF 0x25 /* Data Link Feature */ #define PCI_EXT_CAP_ID_PL_16GT 0x26 /* Physical Layer 16.0 GT/s */ #define PCI_EXT_CAP_ID_NPEM 0x29 /* Native PCIe Enclosure Management */ #define PCI_EXT_CAP_ID_PL_32GT 0x2A /* Physical Layer 32.0 GT/s */ #define PCI_EXT_CAP_ID_DOE 0x2E /* Data Object Exchange */ -#define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_DOE +#define PCI_EXT_CAP_ID_PL_64GT 0x31 /* Physical Layer 64.0 GT/s */ +#define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_PL_64GT #define PCI_EXT_CAP_DSN_SIZEOF 12 #define PCI_EXT_CAP_MCAST_ENDPOINT_SIZEOF 40 @@ -773,6 +779,12 @@ #define PCI_ERR_UNC_MCBTLP 0x00800000 /* MC blocked TLP */ #define PCI_ERR_UNC_ATOMEG 0x01000000 /* Atomic egress blocked */ #define PCI_ERR_UNC_TLPPRE 0x02000000 /* TLP prefix blocked */ +#define PCI_ERR_UNC_POISON_BLK 0x04000000 /* Poisoned TLP Egress Blocked */ +#define PCI_ERR_UNC_DMWR_BLK 0x08000000 /* DMWr Request Egress Blocked */ +#define PCI_ERR_UNC_IDE_CHECK 0x10000000 /* IDE Check Failed */ +#define PCI_ERR_UNC_MISR_IDE 0x20000000 /* Misrouted IDE TLP */ +#define PCI_ERR_UNC_PCRC_CHECK 0x40000000 /* PCRC Check Failed */ +#define PCI_ERR_UNC_XLAT_BLK 0x80000000 /* TLP Translation Egress Blocked */ #define PCI_ERR_UNCOR_MASK 0x08 /* Uncorrectable Error Mask */ /* Same bits as above */ #define PCI_ERR_UNCOR_SEVER 0x0c /* Uncorrectable Error Severity */ @@ -795,6 +807,9 @@ #define PCI_ERR_CAP_ECRC_CHKC 0x00000080 /* ECRC Check Capable */ #define PCI_ERR_CAP_ECRC_CHKE 0x00000100 /* ECRC Check Enable */ #define PCI_ERR_CAP_PREFIX_LOG_PRESENT 0x00000800 /* TLP Prefix Log Present */ +#define PCI_ERR_CAP_COMP_TIME_LOG 0x00001000 /* Completion Timeout Prefix/Header Log Capable */ +#define PCI_ERR_CAP_TLP_LOG_FLIT 0x00040000 /* TLP was logged in Flit Mode */ +#define PCI_ERR_CAP_TLP_LOG_SIZE 0x00f80000 /* Logged TLP Size (only in Flit mode) */ #define PCI_ERR_HEADER_LOG 0x1c /* Header Log Register (16 bytes) */ #define PCI_ERR_ROOT_COMMAND 0x2c /* Root Error Command */ #define PCI_ERR_ROOT_CMD_COR_EN 0x00000001 /* Correctable Err Reporting Enable */ @@ -1013,7 +1028,7 @@ /* Resizable BARs */ #define PCI_REBAR_CAP 4 /* capability register */ -#define PCI_REBAR_CAP_SIZES 0x00FFFFF0 /* supported BAR sizes */ +#define PCI_REBAR_CAP_SIZES 0xFFFFFFF0 /* supported BAR sizes */ #define PCI_REBAR_CTRL 8 /* control register */ #define PCI_REBAR_CTRL_BAR_IDX 0x00000007 /* BAR index */ #define PCI_REBAR_CTRL_NBAR_MASK 0x000000E0 /* # of resizable BARs */ @@ -1061,8 +1076,9 @@ #define PCI_EXP_DPC_CAP_RP_EXT 0x0020 /* Root Port Extensions */ #define PCI_EXP_DPC_CAP_POISONED_TLP 0x0040 /* Poisoned TLP Egress Blocking Supported */ #define PCI_EXP_DPC_CAP_SW_TRIGGER 0x0080 /* Software Triggering Supported */ -#define PCI_EXP_DPC_RP_PIO_LOG_SIZE 0x0F00 /* RP PIO Log Size */ +#define PCI_EXP_DPC_RP_PIO_LOG_SIZE 0x0F00 /* RP PIO Log Size [3:0] */ #define PCI_EXP_DPC_CAP_DL_ACTIVE 0x1000 /* ERR_COR signal on DL_Active supported */ +#define PCI_EXP_DPC_RP_PIO_LOG_SIZE4 0x2000 /* RP PIO Log Size [4] */ #define PCI_EXP_DPC_CTL 0x06 /* DPC control */ #define PCI_EXP_DPC_CTL_EN_FATAL 0x0001 /* Enable trigger on ERR_FATAL message */ @@ -1136,16 +1152,33 @@ #define PCI_DVSEC_HEADER2 0x8 /* Designated Vendor-Specific Header2 */ #define PCI_DVSEC_HEADER2_ID(x) ((x) & 0xffff) +/* VF Resizable BARs, same layout as PCI_REBAR */ +#define PCI_VF_REBAR_CAP PCI_REBAR_CAP +#define PCI_VF_REBAR_CAP_SIZES PCI_REBAR_CAP_SIZES +#define PCI_VF_REBAR_CTRL PCI_REBAR_CTRL +#define PCI_VF_REBAR_CTRL_BAR_IDX PCI_REBAR_CTRL_BAR_IDX +#define PCI_VF_REBAR_CTRL_NBAR_MASK PCI_REBAR_CTRL_NBAR_MASK +#define PCI_VF_REBAR_CTRL_BAR_SIZE PCI_REBAR_CTRL_BAR_SIZE + /* Data Link Feature */ #define PCI_DLF_CAP 0x04 /* Capabilities Register */ #define PCI_DLF_EXCHANGE_ENABLE 0x80000000 /* Data Link Feature Exchange Enable */ +/* Secondary PCIe Capability 8.0 GT/s */ +#define PCI_SECPCI_LE_CTRL 0x0c /* Lane Equalization Control Register */ + /* Physical Layer 16.0 GT/s */ #define PCI_PL_16GT_LE_CTRL 0x20 /* Lane Equalization Control Register */ #define PCI_PL_16GT_LE_CTRL_DSP_TX_PRESET_MASK 0x0000000F #define PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_MASK 0x000000F0 #define PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_SHIFT 4 +/* Physical Layer 32.0 GT/s */ +#define PCI_PL_32GT_LE_CTRL 0x20 /* Lane Equalization Control Register */ + +/* Physical Layer 64.0 GT/s */ +#define PCI_PL_64GT_LE_CTRL 0x20 /* Lane Equalization Control Register */ + /* Native PCIe Enclosure Management */ #define PCI_NPEM_CAP 0x04 /* NPEM capability register */ #define PCI_NPEM_CAP_CAPABLE 0x00000001 /* NPEM Capable */ @@ -1205,9 +1238,12 @@ #define PCI_DOE_DATA_OBJECT_DISC_REQ_3_INDEX 0x000000ff #define PCI_DOE_DATA_OBJECT_DISC_REQ_3_VER 0x0000ff00 #define PCI_DOE_DATA_OBJECT_DISC_RSP_3_VID 0x0000ffff -#define PCI_DOE_DATA_OBJECT_DISC_RSP_3_PROTOCOL 0x00ff0000 +#define PCI_DOE_DATA_OBJECT_DISC_RSP_3_TYPE 0x00ff0000 #define PCI_DOE_DATA_OBJECT_DISC_RSP_3_NEXT_INDEX 0xff000000 +/* Deprecated old name, replaced with PCI_DOE_DATA_OBJECT_DISC_RSP_3_TYPE */ +#define PCI_DOE_DATA_OBJECT_DISC_RSP_3_PROTOCOL PCI_DOE_DATA_OBJECT_DISC_RSP_3_TYPE + /* Compute Express Link (CXL r3.1, sec 8.1.5) */ #define PCI_DVSEC_CXL_PORT 3 #define PCI_DVSEC_CXL_PORT_CTL 0x0c diff --git a/include/standard-headers/linux/vhost_types.h b/include/standard-headers/linux/vhost_types.h index fd54044..79b53a9 100644 --- a/include/standard-headers/linux/vhost_types.h +++ b/include/standard-headers/linux/vhost_types.h @@ -110,6 +110,11 @@ struct vhost_msg_v2 { }; }; +struct vhost_features_array { + uint64_t count; /* number of entries present in features array */ + uint64_t features[] ; +}; + struct vhost_memory_region { uint64_t guest_phys_addr; uint64_t memory_size; /* bytes */ diff --git a/include/standard-headers/linux/virtio_gpu.h b/include/standard-headers/linux/virtio_gpu.h index 6459fdb..00cd3f0 100644 --- a/include/standard-headers/linux/virtio_gpu.h +++ b/include/standard-headers/linux/virtio_gpu.h @@ -309,8 +309,9 @@ struct virtio_gpu_cmd_submit { #define VIRTIO_GPU_CAPSET_VIRGL 1 #define VIRTIO_GPU_CAPSET_VIRGL2 2 -/* 3 is reserved for gfxstream */ +#define VIRTIO_GPU_CAPSET_GFXSTREAM_VULKAN 3 #define VIRTIO_GPU_CAPSET_VENUS 4 +#define VIRTIO_GPU_CAPSET_CROSS_DOMAIN 5 #define VIRTIO_GPU_CAPSET_DRM 6 /* VIRTIO_GPU_CMD_GET_CAPSET_INFO */ diff --git a/include/standard-headers/linux/virtio_ids.h b/include/standard-headers/linux/virtio_ids.h index 7aa2eb7..6c12db1 100644 --- a/include/standard-headers/linux/virtio_ids.h +++ b/include/standard-headers/linux/virtio_ids.h @@ -68,6 +68,7 @@ #define VIRTIO_ID_AUDIO_POLICY 39 /* virtio audio policy */ #define VIRTIO_ID_BT 40 /* virtio bluetooth */ #define VIRTIO_ID_GPIO 41 /* virtio gpio */ +#define VIRTIO_ID_SPI 45 /* virtio spi */ /* * Virtio Transitional IDs diff --git a/include/standard-headers/linux/virtio_net.h b/include/standard-headers/linux/virtio_net.h index fc594fe..93abaae 100644 --- a/include/standard-headers/linux/virtio_net.h +++ b/include/standard-headers/linux/virtio_net.h @@ -70,6 +70,28 @@ * with the same MAC. */ #define VIRTIO_NET_F_SPEED_DUPLEX 63 /* Device set linkspeed and duplex */ +#define VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO 65 /* Driver can receive + * GSO-over-UDP-tunnel packets + */ +#define VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM 66 /* Driver handles + * GSO-over-UDP-tunnel + * packets with partial csum + * for the outer header + */ +#define VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO 67 /* Device can receive + * GSO-over-UDP-tunnel packets + */ +#define VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO_CSUM 68 /* Device handles + * GSO-over-UDP-tunnel + * packets with partial csum + * for the outer header + */ + +/* Offloads bits corresponding to VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO{,_CSUM} + * features + */ +#define VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_MAPPED 46 +#define VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM_MAPPED 47 #ifndef VIRTIO_NET_NO_LEGACY #define VIRTIO_NET_F_GSO 6 /* Host handles pkts w/ any GSO type */ @@ -131,12 +153,17 @@ struct virtio_net_hdr_v1 { #define VIRTIO_NET_HDR_F_NEEDS_CSUM 1 /* Use csum_start, csum_offset */ #define VIRTIO_NET_HDR_F_DATA_VALID 2 /* Csum is valid */ #define VIRTIO_NET_HDR_F_RSC_INFO 4 /* rsc info in csum_ fields */ +#define VIRTIO_NET_HDR_F_UDP_TUNNEL_CSUM 8 /* UDP tunnel csum offload */ uint8_t flags; #define VIRTIO_NET_HDR_GSO_NONE 0 /* Not a GSO frame */ #define VIRTIO_NET_HDR_GSO_TCPV4 1 /* GSO frame, IPv4 TCP (TSO) */ #define VIRTIO_NET_HDR_GSO_UDP 3 /* GSO frame, IPv4 UDP (UFO) */ #define VIRTIO_NET_HDR_GSO_TCPV6 4 /* GSO frame, IPv6 TCP */ #define VIRTIO_NET_HDR_GSO_UDP_L4 5 /* GSO frame, IPv4& IPv6 UDP (USO) */ +#define VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV4 0x20 /* UDPv4 tunnel present */ +#define VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6 0x40 /* UDPv6 tunnel present */ +#define VIRTIO_NET_HDR_GSO_UDP_TUNNEL (VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV4 | \ + VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6) #define VIRTIO_NET_HDR_GSO_ECN 0x80 /* TCP has ECN set */ uint8_t gso_type; __virtio16 hdr_len; /* Ethernet + IP + tcp/udp hdrs */ @@ -181,6 +208,12 @@ struct virtio_net_hdr_v1_hash { uint16_t padding; }; +struct virtio_net_hdr_v1_hash_tunnel { + struct virtio_net_hdr_v1_hash hash_hdr; + uint16_t outer_th_offset; + uint16_t inner_nh_offset; +}; + #ifndef VIRTIO_NET_NO_LEGACY /* This header comes first in the scatter-gather list. * For legacy virtio, if VIRTIO_F_ANY_LAYOUT is not negotiated, it must @@ -327,6 +360,19 @@ struct virtio_net_rss_config { uint8_t hash_key_data[/* hash_key_length */]; }; +struct virtio_net_rss_config_hdr { + uint32_t hash_types; + uint16_t indirection_table_mask; + uint16_t unclassified_queue; + uint16_t indirection_table[/* 1 + indirection_table_mask */]; +}; + +struct virtio_net_rss_config_trailer { + uint16_t max_tx_vq; + uint8_t hash_key_length; + uint8_t hash_key_data[/* hash_key_length */]; +}; + #define VIRTIO_NET_CTRL_MQ_RSS_CONFIG 1 /* diff --git a/include/standard-headers/linux/virtio_pci.h b/include/standard-headers/linux/virtio_pci.h index 91fec6f..09e964e 100644 --- a/include/standard-headers/linux/virtio_pci.h +++ b/include/standard-headers/linux/virtio_pci.h @@ -246,6 +246,7 @@ struct virtio_pci_cfg_cap { #define VIRTIO_ADMIN_CMD_LIST_USE 0x1 /* Admin command group type. */ +#define VIRTIO_ADMIN_GROUP_TYPE_SELF 0x0 #define VIRTIO_ADMIN_GROUP_TYPE_SRIOV 0x1 /* Transitional device admin command. */ diff --git a/include/standard-headers/linux/virtio_snd.h b/include/standard-headers/linux/virtio_snd.h index 860f12e..160d578 100644 --- a/include/standard-headers/linux/virtio_snd.h +++ b/include/standard-headers/linux/virtio_snd.h @@ -25,7 +25,7 @@ struct virtio_snd_config { uint32_t streams; /* # of available channel maps */ uint32_t chmaps; - /* # of available control elements */ + /* # of available control elements (if VIRTIO_SND_F_CTLS) */ uint32_t controls; }; diff --git a/include/standard-headers/uefi/uefi.h b/include/standard-headers/uefi/uefi.h new file mode 100644 index 0000000..5256349 --- /dev/null +++ b/include/standard-headers/uefi/uefi.h @@ -0,0 +1,187 @@ +/* + * Copyright (C) 2025 Intel Corporation + * + * Author: Isaku Yamahata <isaku.yamahata at gmail.com> + * <isaku.yamahata at intel.com> + * Xiaoyao Li <xiaoyao.li@intel.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_I386_UEFI_H +#define HW_I386_UEFI_H + +/***************************************************************************/ +/* + * basic EFI definitions + * supplemented with UEFI Specification Version 2.8 (Errata A) + * released February 2020 + */ +/* UEFI integer is little endian */ + +typedef struct { + uint32_t Data1; + uint16_t Data2; + uint16_t Data3; + uint8_t Data4[8]; +} EFI_GUID; + +typedef enum { + EfiReservedMemoryType, + EfiLoaderCode, + EfiLoaderData, + EfiBootServicesCode, + EfiBootServicesData, + EfiRuntimeServicesCode, + EfiRuntimeServicesData, + EfiConventionalMemory, + EfiUnusableMemory, + EfiACPIReclaimMemory, + EfiACPIMemoryNVS, + EfiMemoryMappedIO, + EfiMemoryMappedIOPortSpace, + EfiPalCode, + EfiPersistentMemory, + EfiUnacceptedMemoryType, + EfiMaxMemoryType +} EFI_MEMORY_TYPE; + +#define EFI_HOB_HANDOFF_TABLE_VERSION 0x0009 + +#define EFI_HOB_TYPE_HANDOFF 0x0001 +#define EFI_HOB_TYPE_MEMORY_ALLOCATION 0x0002 +#define EFI_HOB_TYPE_RESOURCE_DESCRIPTOR 0x0003 +#define EFI_HOB_TYPE_GUID_EXTENSION 0x0004 +#define EFI_HOB_TYPE_FV 0x0005 +#define EFI_HOB_TYPE_CPU 0x0006 +#define EFI_HOB_TYPE_MEMORY_POOL 0x0007 +#define EFI_HOB_TYPE_FV2 0x0009 +#define EFI_HOB_TYPE_LOAD_PEIM_UNUSED 0x000A +#define EFI_HOB_TYPE_UEFI_CAPSULE 0x000B +#define EFI_HOB_TYPE_FV3 0x000C +#define EFI_HOB_TYPE_UNUSED 0xFFFE +#define EFI_HOB_TYPE_END_OF_HOB_LIST 0xFFFF + +typedef struct { + uint16_t HobType; + uint16_t HobLength; + uint32_t Reserved; +} EFI_HOB_GENERIC_HEADER; + +typedef uint64_t EFI_PHYSICAL_ADDRESS; +typedef uint32_t EFI_BOOT_MODE; + +typedef struct { + EFI_HOB_GENERIC_HEADER Header; + uint32_t Version; + EFI_BOOT_MODE BootMode; + EFI_PHYSICAL_ADDRESS EfiMemoryTop; + EFI_PHYSICAL_ADDRESS EfiMemoryBottom; + EFI_PHYSICAL_ADDRESS EfiFreeMemoryTop; + EFI_PHYSICAL_ADDRESS EfiFreeMemoryBottom; + EFI_PHYSICAL_ADDRESS EfiEndOfHobList; +} EFI_HOB_HANDOFF_INFO_TABLE; + +#define EFI_RESOURCE_SYSTEM_MEMORY 0x00000000 +#define EFI_RESOURCE_MEMORY_MAPPED_IO 0x00000001 +#define EFI_RESOURCE_IO 0x00000002 +#define EFI_RESOURCE_FIRMWARE_DEVICE 0x00000003 +#define EFI_RESOURCE_MEMORY_MAPPED_IO_PORT 0x00000004 +#define EFI_RESOURCE_MEMORY_RESERVED 0x00000005 +#define EFI_RESOURCE_IO_RESERVED 0x00000006 +#define EFI_RESOURCE_MEMORY_UNACCEPTED 0x00000007 +#define EFI_RESOURCE_MAX_MEMORY_TYPE 0x00000008 + +#define EFI_RESOURCE_ATTRIBUTE_PRESENT 0x00000001 +#define EFI_RESOURCE_ATTRIBUTE_INITIALIZED 0x00000002 +#define EFI_RESOURCE_ATTRIBUTE_TESTED 0x00000004 +#define EFI_RESOURCE_ATTRIBUTE_SINGLE_BIT_ECC 0x00000008 +#define EFI_RESOURCE_ATTRIBUTE_MULTIPLE_BIT_ECC 0x00000010 +#define EFI_RESOURCE_ATTRIBUTE_ECC_RESERVED_1 0x00000020 +#define EFI_RESOURCE_ATTRIBUTE_ECC_RESERVED_2 0x00000040 +#define EFI_RESOURCE_ATTRIBUTE_READ_PROTECTED 0x00000080 +#define EFI_RESOURCE_ATTRIBUTE_WRITE_PROTECTED 0x00000100 +#define EFI_RESOURCE_ATTRIBUTE_EXECUTION_PROTECTED 0x00000200 +#define EFI_RESOURCE_ATTRIBUTE_UNCACHEABLE 0x00000400 +#define EFI_RESOURCE_ATTRIBUTE_WRITE_COMBINEABLE 0x00000800 +#define EFI_RESOURCE_ATTRIBUTE_WRITE_THROUGH_CACHEABLE 0x00001000 +#define EFI_RESOURCE_ATTRIBUTE_WRITE_BACK_CACHEABLE 0x00002000 +#define EFI_RESOURCE_ATTRIBUTE_16_BIT_IO 0x00004000 +#define EFI_RESOURCE_ATTRIBUTE_32_BIT_IO 0x00008000 +#define EFI_RESOURCE_ATTRIBUTE_64_BIT_IO 0x00010000 +#define EFI_RESOURCE_ATTRIBUTE_UNCACHED_EXPORTED 0x00020000 +#define EFI_RESOURCE_ATTRIBUTE_READ_ONLY_PROTECTED 0x00040000 +#define EFI_RESOURCE_ATTRIBUTE_READ_ONLY_PROTECTABLE 0x00080000 +#define EFI_RESOURCE_ATTRIBUTE_READ_PROTECTABLE 0x00100000 +#define EFI_RESOURCE_ATTRIBUTE_WRITE_PROTECTABLE 0x00200000 +#define EFI_RESOURCE_ATTRIBUTE_EXECUTION_PROTECTABLE 0x00400000 +#define EFI_RESOURCE_ATTRIBUTE_PERSISTENT 0x00800000 +#define EFI_RESOURCE_ATTRIBUTE_PERSISTABLE 0x01000000 +#define EFI_RESOURCE_ATTRIBUTE_MORE_RELIABLE 0x02000000 + +typedef uint32_t EFI_RESOURCE_TYPE; +typedef uint32_t EFI_RESOURCE_ATTRIBUTE_TYPE; + +typedef struct { + EFI_HOB_GENERIC_HEADER Header; + EFI_GUID Owner; + EFI_RESOURCE_TYPE ResourceType; + EFI_RESOURCE_ATTRIBUTE_TYPE ResourceAttribute; + EFI_PHYSICAL_ADDRESS PhysicalStart; + uint64_t ResourceLength; +} EFI_HOB_RESOURCE_DESCRIPTOR; + +typedef struct { + EFI_HOB_GENERIC_HEADER Header; + EFI_GUID Name; + + /* guid specific data follows */ +} EFI_HOB_GUID_TYPE; + +typedef struct { + EFI_HOB_GENERIC_HEADER Header; + EFI_PHYSICAL_ADDRESS BaseAddress; + uint64_t Length; +} EFI_HOB_FIRMWARE_VOLUME; + +typedef struct { + EFI_HOB_GENERIC_HEADER Header; + EFI_PHYSICAL_ADDRESS BaseAddress; + uint64_t Length; + EFI_GUID FvName; + EFI_GUID FileName; +} EFI_HOB_FIRMWARE_VOLUME2; + +typedef struct { + EFI_HOB_GENERIC_HEADER Header; + EFI_PHYSICAL_ADDRESS BaseAddress; + uint64_t Length; + uint32_t AuthenticationStatus; + bool ExtractedFv; + EFI_GUID FvName; + EFI_GUID FileName; +} EFI_HOB_FIRMWARE_VOLUME3; + +typedef struct { + EFI_HOB_GENERIC_HEADER Header; + uint8_t SizeOfMemorySpace; + uint8_t SizeOfIoSpace; + uint8_t Reserved[6]; +} EFI_HOB_CPU; + +typedef struct { + EFI_HOB_GENERIC_HEADER Header; +} EFI_HOB_MEMORY_POOL; + +typedef struct { + EFI_HOB_GENERIC_HEADER Header; + + EFI_PHYSICAL_ADDRESS BaseAddress; + uint64_t Length; +} EFI_HOB_UEFI_CAPSULE; + +#define EFI_HOB_OWNER_ZERO \ + ((EFI_GUID){ 0x00000000, 0x0000, 0x0000, \ + { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 } }) + +#endif diff --git a/include/system/accel-irq.h b/include/system/accel-irq.h new file mode 100644 index 0000000..671fb7d --- /dev/null +++ b/include/system/accel-irq.h @@ -0,0 +1,37 @@ +/* + * Accelerated irqchip abstraction + * + * Copyright Microsoft, Corp. 2025 + * + * Authors: Ziqiao Zhou <ziqiaozhou@microsoft.com> + * Magnus Kulke <magnuskulke@microsoft.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef SYSTEM_ACCEL_IRQ_H +#define SYSTEM_ACCEL_IRQ_H +#include "hw/pci/msi.h" +#include "qemu/osdep.h" +#include "system/kvm.h" +#include "system/mshv.h" + +static inline bool accel_msi_via_irqfd_enabled(void) +{ + return mshv_msi_via_irqfd_enabled() || kvm_msi_via_irqfd_enabled(); +} + +static inline bool accel_irqchip_is_split(void) +{ + return mshv_msi_via_irqfd_enabled() || kvm_irqchip_is_split(); +} + +int accel_irqchip_add_msi_route(KVMRouteChange *c, int vector, PCIDevice *dev); +int accel_irqchip_update_msi_route(int vector, MSIMessage msg, PCIDevice *dev); +void accel_irqchip_commit_route_changes(KVMRouteChange *c); +void accel_irqchip_commit_routes(void); +void accel_irqchip_release_virq(int virq); +int accel_irqchip_add_irqfd_notifier_gsi(EventNotifier *n, EventNotifier *rn, + int virq); +int accel_irqchip_remove_irqfd_notifier_gsi(EventNotifier *n, int virq); +#endif diff --git a/include/exec/address-spaces.h b/include/system/address-spaces.h index 0d0aa61..72d17af 100644 --- a/include/exec/address-spaces.h +++ b/include/system/address-spaces.h @@ -11,16 +11,14 @@ * */ -#ifndef EXEC_ADDRESS_SPACES_H -#define EXEC_ADDRESS_SPACES_H +#ifndef SYSTEM_ADDRESS_SPACES_H +#define SYSTEM_ADDRESS_SPACES_H /* * Internal interfaces between memory.c/exec.c/vl.c. Do not #include unless * you're one of them. */ -#ifndef CONFIG_USER_ONLY - /* Get the root memory region. This interface should only be used temporarily * until a proper bus interface is available. */ @@ -35,5 +33,3 @@ extern AddressSpace address_space_memory; extern AddressSpace address_space_io; #endif - -#endif diff --git a/include/system/block-backend-global-state.h b/include/system/block-backend-global-state.h index 35b5e83..c384964 100644 --- a/include/system/block-backend-global-state.h +++ b/include/system/block-backend-global-state.h @@ -55,7 +55,7 @@ void monitor_remove_blk(BlockBackend *blk); BlockBackendPublic *blk_get_public(BlockBackend *blk); -void blk_remove_bs(BlockBackend *blk); +void GRAPH_UNLOCKED blk_remove_bs(BlockBackend *blk); int blk_insert_bs(BlockBackend *blk, BlockDriverState *bs, Error **errp); int blk_replace_bs(BlockBackend *blk, BlockDriverState *new_bs, Error **errp); bool GRAPH_RDLOCK bdrv_has_blk(BlockDriverState *bs); @@ -78,8 +78,8 @@ int blk_make_zero(BlockBackend *blk, BdrvRequestFlags flags); void blk_aio_cancel(BlockAIOCB *acb); int blk_commit_all(void); bool blk_in_drain(BlockBackend *blk); -void blk_drain(BlockBackend *blk); -void blk_drain_all(void); +void GRAPH_UNLOCKED blk_drain(BlockBackend *blk); +void GRAPH_UNLOCKED blk_drain_all(void); void blk_set_on_error(BlockBackend *blk, BlockdevOnError on_read_error, BlockdevOnError on_write_error); bool blk_supports_write_perm(BlockBackend *blk); @@ -109,7 +109,7 @@ int blk_probe_blocksizes(BlockBackend *blk, BlockSizes *bsz); int blk_probe_geometry(BlockBackend *blk, HDGeometry *geo); void blk_set_io_limits(BlockBackend *blk, ThrottleConfig *cfg); -void blk_io_limits_disable(BlockBackend *blk); +void GRAPH_UNLOCKED blk_io_limits_disable(BlockBackend *blk); void blk_io_limits_enable(BlockBackend *blk, const char *group); void blk_io_limits_update_group(BlockBackend *blk, const char *group); void blk_set_force_allow_inactivate(BlockBackend *blk); diff --git a/include/system/block-backend-io.h b/include/system/block-backend-io.h index ba8dfcc..6d5ac47 100644 --- a/include/system/block-backend-io.h +++ b/include/system/block-backend-io.h @@ -116,6 +116,7 @@ BlockAIOCB *blk_abort_aio_request(BlockBackend *blk, void *opaque, int ret); uint32_t blk_get_request_alignment(BlockBackend *blk); +uint32_t blk_get_pwrite_zeroes_alignment(BlockBackend *blk); uint32_t blk_get_max_transfer(BlockBackend *blk); uint64_t blk_get_max_hw_transfer(BlockBackend *blk); diff --git a/include/system/confidential-guest-support.h b/include/system/confidential-guest-support.h index b68c4be..0cc8b26 100644 --- a/include/system/confidential-guest-support.h +++ b/include/system/confidential-guest-support.h @@ -18,11 +18,8 @@ #ifndef QEMU_CONFIDENTIAL_GUEST_SUPPORT_H #define QEMU_CONFIDENTIAL_GUEST_SUPPORT_H -#ifdef CONFIG_USER_ONLY -#error Cannot include system/confidential-guest-support.h from user emulation -#endif - #include "qom/object.h" +#include "exec/hwaddr.h" #define TYPE_CONFIDENTIAL_GUEST_SUPPORT "confidential-guest-support" OBJECT_DECLARE_TYPE(ConfidentialGuestSupport, @@ -30,6 +27,40 @@ OBJECT_DECLARE_TYPE(ConfidentialGuestSupport, CONFIDENTIAL_GUEST_SUPPORT) +typedef enum ConfidentialGuestPlatformType { + CGS_PLATFORM_SEV, + CGS_PLATFORM_SEV_ES, + CGS_PLATFORM_SEV_SNP, +} ConfidentialGuestPlatformType; + +typedef enum ConfidentialGuestMemoryType { + CGS_MEM_RAM, + CGS_MEM_RESERVED, + CGS_MEM_ACPI, + CGS_MEM_NVS, + CGS_MEM_UNUSABLE, +} ConfidentialGuestMemoryType; + +typedef struct ConfidentialGuestMemoryMapEntry { + uint64_t gpa; + uint64_t size; + ConfidentialGuestMemoryType type; +} ConfidentialGuestMemoryMapEntry; + +typedef enum ConfidentialGuestPageType { + CGS_PAGE_TYPE_NORMAL, + CGS_PAGE_TYPE_VMSA, + CGS_PAGE_TYPE_ZERO, + CGS_PAGE_TYPE_UNMEASURED, + CGS_PAGE_TYPE_SECRETS, + CGS_PAGE_TYPE_CPUID, + CGS_PAGE_TYPE_REQUIRED_MEMORY, +} ConfidentialGuestPageType; + +typedef enum ConfidentialGuestPolicyType { + GUEST_POLICY_SEV, +} ConfidentialGuestPolicyType; + struct ConfidentialGuestSupport { Object parent; @@ -68,6 +99,59 @@ typedef struct ConfidentialGuestSupportClass { int (*kvm_init)(ConfidentialGuestSupport *cgs, Error **errp); int (*kvm_reset)(ConfidentialGuestSupport *cgs, Error **errp); + + /* + * Check to see if this confidential guest supports a particular + * platform or configuration. + * + * Return true if supported or false if not supported. + */ + bool (*check_support)(ConfidentialGuestPlatformType platform, + uint16_t platform_version, uint8_t highest_vtl, + uint64_t shared_gpa_boundary); + + /* + * Configure part of the state of a guest for a particular set of data, page + * type and gpa. This can be used for example to pre-populate and measure + * guest memory contents, define private ranges or set the initial CPU state + * for one or more CPUs. + * + * If memory_type is CGS_PAGE_TYPE_VMSA then ptr points to the initial CPU + * context for a virtual CPU. The format of the data depends on the type of + * confidential virtual machine. For example, for SEV-ES ptr will point to a + * vmcb_save_area structure that should be copied into guest memory at the + * address specified in gpa. The cpu_index parameter contains the index of + * the CPU the VMSA applies to. + */ + int (*set_guest_state)(hwaddr gpa, uint8_t *ptr, uint64_t len, + ConfidentialGuestPageType memory_type, + uint16_t cpu_index, Error **errp); + + /* + * Set the guest policy. The policy can be used to configure the + * confidential platform, such as if debug is enabled or not and can contain + * information about expected launch measurements, signed verification of + * guest configuration and other platform data. + * + * The format of the policy data is specific to each platform. For example, + * SEV-SNP uses a policy bitfield in the 'policy' argument and provides an + * ID block and ID authentication in the 'policy_data' parameters. The type + * of policy data is identified by the 'policy_type' argument. + */ + int (*set_guest_policy)(ConfidentialGuestPolicyType policy_type, + uint64_t policy, + void *policy_data1, uint32_t policy_data1_size, + void *policy_data2, uint32_t policy_data2_size, + Error **errp); + + /* + * Iterate the system memory map, getting the entry with the given index + * that can be populated into guest memory. + * + * Returns 0 for ok, 1 if the index is out of range and -1 on error. + */ + int (*get_mem_map_entry)(int index, ConfidentialGuestMemoryMapEntry *entry, + Error **errp); } ConfidentialGuestSupportClass; static inline int confidential_guest_kvm_init(ConfidentialGuestSupport *cgs, diff --git a/include/system/cpu-timers.h b/include/system/cpu-timers.h index 64ae54f..a1abed0 100644 --- a/include/system/cpu-timers.h +++ b/include/system/cpu-timers.h @@ -15,64 +15,6 @@ /* init the whole cpu timers API, including icount, ticks, and cpu_throttle */ void cpu_timers_init(void); -/* icount - Instruction Counter API */ - -/** - * ICountMode: icount enablement state: - * - * @ICOUNT_DISABLED: Disabled - Do not count executed instructions. - * @ICOUNT_PRECISE: Enabled - Fixed conversion of insn to ns via "shift" option - * @ICOUNT_ADAPTATIVE: Enabled - Runtime adaptive algorithm to compute shift - */ -typedef enum { - ICOUNT_DISABLED = 0, - ICOUNT_PRECISE, - ICOUNT_ADAPTATIVE, -} ICountMode; - -#if defined(CONFIG_TCG) && !defined(CONFIG_USER_ONLY) -extern ICountMode use_icount; -#define icount_enabled() (use_icount) -#else -#define icount_enabled() ICOUNT_DISABLED -#endif - -/* - * Update the icount with the executed instructions. Called by - * cpus-tcg vCPU thread so the main-loop can see time has moved forward. - */ -void icount_update(CPUState *cpu); - -/* get raw icount value */ -int64_t icount_get_raw(void); - -/* return the virtual CPU time in ns, based on the instruction counter. */ -int64_t icount_get(void); -/* - * convert an instruction counter value to ns, based on the icount shift. - * This shift is set as a fixed value with the icount "shift" option - * (precise mode), or it is constantly approximated and corrected at - * runtime in adaptive mode. - */ -int64_t icount_to_ns(int64_t icount); - -/** - * icount_configure: configure the icount options, including "shift" - * @opts: Options to parse - * @errp: pointer to a NULL-initialized error object - * - * Return: true on success, else false setting @errp with error - */ -bool icount_configure(QemuOpts *opts, Error **errp); - -/* used by tcg vcpu thread to calc icount budget */ -int64_t icount_round(int64_t count); - -/* if the CPUs are idle, start accounting real time to virtual clock. */ -void icount_start_warp_timer(void); -void icount_account_warp_timer(void); -void icount_notify_exit(void); - /* * CPU Ticks and Clock */ diff --git a/include/system/cpus.h b/include/system/cpus.h index 3226c76..508444c 100644 --- a/include/system/cpus.h +++ b/include/system/cpus.h @@ -7,11 +7,6 @@ void cpus_register_accel(const AccelOpsClass *i); /* return registers ops */ const AccelOpsClass *cpus_get_accel(void); -/* accel/dummy-cpus.c */ - -/* Create a dummy vcpu for AccelOpsClass->create_vcpu_thread */ -void dummy_start_vcpu_thread(CPUState *); - /* interface available for cpus accelerator threads */ /* For temporary buffers for forming a name */ @@ -22,8 +17,7 @@ bool cpu_work_list_empty(CPUState *cpu); bool cpu_thread_is_idle(CPUState *cpu); bool all_cpu_threads_idle(void); bool cpu_can_run(CPUState *cpu); -void qemu_wait_io_event_common(CPUState *cpu); -void qemu_wait_io_event(CPUState *cpu); +void qemu_process_cpu_events_common(CPUState *cpu); void cpu_thread_signal_created(CPUState *cpu); void cpu_thread_signal_destroyed(CPUState *cpu); void cpu_handle_guest_debug(CPUState *cpu); diff --git a/include/system/dma.h b/include/system/dma.h index e142f7e..82e7ad5 100644 --- a/include/system/dma.h +++ b/include/system/dma.h @@ -10,8 +10,8 @@ #ifndef DMA_H #define DMA_H -#include "exec/memory.h" -#include "exec/address-spaces.h" +#include "system/memory.h" +#include "system/address-spaces.h" #include "block/block.h" #include "block/accounting.h" diff --git a/include/system/host_iommu_device.h b/include/system/host_iommu_device.h index 809cced..ab849a4 100644 --- a/include/system/host_iommu_device.h +++ b/include/system/host_iommu_device.h @@ -14,6 +14,13 @@ #include "qom/object.h" #include "qapi/error.h" +#ifdef CONFIG_LINUX +#include "linux/iommufd.h" + +typedef union VendorCaps { + struct iommu_hw_info_vtd vtd; + struct iommu_hw_info_arm_smmuv3 smmuv3; +} VendorCaps; /** * struct HostIOMMUDeviceCaps - Define host IOMMU device capabilities. @@ -22,11 +29,17 @@ * * @hw_caps: host platform IOMMU capabilities (e.g. on IOMMUFD this represents * the @out_capabilities value returned from IOMMU_GET_HW_INFO ioctl) + * + * @vendor_caps: host platform IOMMU vendor specific capabilities (e.g. on + * IOMMUFD this represents a user-space buffer filled by kernel + * with host IOMMU @type specific hardware information data) */ typedef struct HostIOMMUDeviceCaps { uint32_t type; uint64_t hw_caps; + VendorCaps vendor_caps; } HostIOMMUDeviceCaps; +#endif #define TYPE_HOST_IOMMU_DEVICE "host-iommu-device" OBJECT_DECLARE_TYPE(HostIOMMUDevice, HostIOMMUDeviceClass, HOST_IOMMU_DEVICE) @@ -38,7 +51,9 @@ struct HostIOMMUDevice { void *agent; /* pointer to agent device, ie. VFIO or VDPA device */ PCIBus *aliased_bus; int aliased_devfn; +#ifdef CONFIG_LINUX HostIOMMUDeviceCaps caps; +#endif }; /** diff --git a/include/system/hostmem.h b/include/system/hostmem.h index 62642e6..88fa791 100644 --- a/include/system/hostmem.h +++ b/include/system/hostmem.h @@ -16,7 +16,7 @@ #include "system/numa.h" #include "qapi/qapi-types-machine.h" #include "qom/object.h" -#include "exec/memory.h" +#include "system/memory.h" #include "qemu/bitmap.h" #include "qemu/thread-context.h" diff --git a/include/system/hvf.h b/include/system/hvf.h index 730f927..d3dcf08 100644 --- a/include/system/hvf.h +++ b/include/system/hvf.h @@ -14,19 +14,21 @@ #define HVF_H #include "qemu/accel.h" -#include "qom/object.h" #ifdef COMPILING_PER_TARGET -#include "cpu.h" +# ifdef CONFIG_HVF +# define CONFIG_HVF_IS_POSSIBLE +# endif /* !CONFIG_HVF */ +#else +# define CONFIG_HVF_IS_POSSIBLE +#endif /* COMPILING_PER_TARGET */ -#ifdef CONFIG_HVF +#ifdef CONFIG_HVF_IS_POSSIBLE extern bool hvf_allowed; #define hvf_enabled() (hvf_allowed) -#else /* !CONFIG_HVF */ +#else /* !CONFIG_HVF_IS_POSSIBLE */ #define hvf_enabled() 0 -#endif /* !CONFIG_HVF */ - -#endif /* COMPILING_PER_TARGET */ +#endif /* !CONFIG_HVF_IS_POSSIBLE */ #define TYPE_HVF_ACCEL ACCEL_CLASS_NAME("hvf") @@ -34,38 +36,4 @@ typedef struct HVFState HVFState; DECLARE_INSTANCE_CHECKER(HVFState, HVF_STATE, TYPE_HVF_ACCEL) -#ifdef COMPILING_PER_TARGET -struct hvf_sw_breakpoint { - vaddr pc; - vaddr saved_insn; - int use_count; - QTAILQ_ENTRY(hvf_sw_breakpoint) entry; -}; - -struct hvf_sw_breakpoint *hvf_find_sw_breakpoint(CPUState *cpu, - vaddr pc); -int hvf_sw_breakpoints_active(CPUState *cpu); - -int hvf_arch_insert_sw_breakpoint(CPUState *cpu, struct hvf_sw_breakpoint *bp); -int hvf_arch_remove_sw_breakpoint(CPUState *cpu, struct hvf_sw_breakpoint *bp); -int hvf_arch_insert_hw_breakpoint(vaddr addr, vaddr len, int type); -int hvf_arch_remove_hw_breakpoint(vaddr addr, vaddr len, int type); -void hvf_arch_remove_all_hw_breakpoints(void); - -/* - * hvf_update_guest_debug: - * @cs: CPUState for the CPU to update - * - * Update guest to enable or disable debugging. Per-arch specifics will be - * handled by calling down to hvf_arch_update_guest_debug. - */ -int hvf_update_guest_debug(CPUState *cpu); -void hvf_arch_update_guest_debug(CPUState *cpu); - -/* - * Return whether the guest supports debugging. - */ -bool hvf_arch_supports_guest_debug(void); -#endif /* COMPILING_PER_TARGET */ - #endif diff --git a/include/system/hvf_int.h b/include/system/hvf_int.h index 42ae184..3d2be40 100644 --- a/include/system/hvf_int.h +++ b/include/system/hvf_int.h @@ -11,6 +11,11 @@ #ifndef HVF_INT_H #define HVF_INT_H +#include "qemu/queue.h" +#include "exec/vaddr.h" +#include "qom/object.h" +#include "accel/accel-ops.h" + #ifdef __aarch64__ #include <Hypervisor/Hypervisor.h> typedef hv_vcpu_t hvf_vcpuid; @@ -41,7 +46,8 @@ typedef struct hvf_vcpu_caps { } hvf_vcpu_caps; struct HVFState { - AccelState parent; + AccelState parent_obj; + hvf_slot slots[32]; int num_slots; @@ -53,11 +59,12 @@ extern HVFState *hvf_state; struct AccelCPUState { hvf_vcpuid fd; - void *exit; +#ifdef __aarch64__ + hv_vcpu_exit_t *exit; bool vtimer_masked; sigset_t unblock_ipi_mask; bool guest_debug_enabled; - bool dirty; +#endif }; void assert_hvf_ok_impl(hv_return_t ret, const char *file, unsigned int line, @@ -66,12 +73,51 @@ void assert_hvf_ok_impl(hv_return_t ret, const char *file, unsigned int line, const char *hvf_return_string(hv_return_t ret); int hvf_arch_init(void); hv_return_t hvf_arch_vm_create(MachineState *ms, uint32_t pa_range); -int hvf_arch_init_vcpu(CPUState *cpu); -void hvf_arch_vcpu_destroy(CPUState *cpu); -int hvf_vcpu_exec(CPUState *); hvf_slot *hvf_find_overlap_slot(uint64_t, uint64_t); -int hvf_put_registers(CPUState *); -int hvf_get_registers(CPUState *); void hvf_kick_vcpu_thread(CPUState *cpu); +/* Must be called by the owning thread */ +int hvf_arch_init_vcpu(CPUState *cpu); +/* Must be called by the owning thread */ +void hvf_arch_vcpu_destroy(CPUState *cpu); +/* Must be called by the owning thread */ +int hvf_arch_vcpu_exec(CPUState *); +/* Must be called by the owning thread */ +int hvf_arch_put_registers(CPUState *); +/* Must be called by the owning thread */ +int hvf_arch_get_registers(CPUState *); +/* Must be called by the owning thread */ +void hvf_arch_update_guest_debug(CPUState *cpu); + +struct hvf_sw_breakpoint { + vaddr pc; + vaddr saved_insn; + int use_count; + QTAILQ_ENTRY(hvf_sw_breakpoint) entry; +}; + +struct hvf_sw_breakpoint *hvf_find_sw_breakpoint(CPUState *cpu, + vaddr pc); +int hvf_sw_breakpoints_active(CPUState *cpu); + +int hvf_arch_insert_sw_breakpoint(CPUState *cpu, struct hvf_sw_breakpoint *bp); +int hvf_arch_remove_sw_breakpoint(CPUState *cpu, struct hvf_sw_breakpoint *bp); +int hvf_arch_insert_hw_breakpoint(vaddr addr, vaddr len, int type); +int hvf_arch_remove_hw_breakpoint(vaddr addr, vaddr len, int type); +void hvf_arch_remove_all_hw_breakpoints(void); + +/* + * hvf_update_guest_debug: + * @cs: CPUState for the CPU to update + * + * Update guest to enable or disable debugging. Per-arch specifics will be + * handled by calling down to hvf_arch_update_guest_debug. + */ +int hvf_update_guest_debug(CPUState *cpu); + +/* + * Return whether the guest supports debugging. + */ +bool hvf_arch_supports_guest_debug(void); + #endif diff --git a/include/system/hw_accel.h b/include/system/hw_accel.h index 380e9e6..55497ed 100644 --- a/include/system/hw_accel.h +++ b/include/system/hw_accel.h @@ -14,12 +14,30 @@ #include "hw/core/cpu.h" #include "system/kvm.h" #include "system/hvf.h" +#include "system/mshv.h" #include "system/whpx.h" #include "system/nvmm.h" +/** + * cpu_synchronize_state: + * cpu_synchronize_pre_loadvm: + * @cpu: The vCPU to synchronize. + * + * Request to synchronize QEMU vCPU registers from the hardware accelerator + * (the hardware accelerator is the reference). + */ void cpu_synchronize_state(CPUState *cpu); +void cpu_synchronize_pre_loadvm(CPUState *cpu); + +/** + * cpu_synchronize_post_reset: + * cpu_synchronize_post_init: + * @cpu: The vCPU to synchronize. + * + * Request to synchronize QEMU vCPU registers to the hardware accelerator + * (QEMU is the reference). + */ void cpu_synchronize_post_reset(CPUState *cpu); void cpu_synchronize_post_init(CPUState *cpu); -void cpu_synchronize_pre_loadvm(CPUState *cpu); #endif /* QEMU_HW_ACCEL_H */ diff --git a/include/system/igvm-cfg.h b/include/system/igvm-cfg.h new file mode 100644 index 0000000..944f23a --- /dev/null +++ b/include/system/igvm-cfg.h @@ -0,0 +1,49 @@ +/* + * QEMU IGVM interface + * + * Copyright (C) 2024 SUSE + * + * Authors: + * Roy Hopkins <roy.hopkins@randomman.co.uk> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef QEMU_IGVM_CFG_H +#define QEMU_IGVM_CFG_H + +#include "qom/object.h" + +typedef struct IgvmCfg { + ObjectClass parent_class; + + /* + * filename: Filename that specifies a file that contains the configuration + * of the guest in Independent Guest Virtual Machine (IGVM) + * format. + */ + char *filename; +} IgvmCfg; + +typedef struct IgvmCfgClass { + ObjectClass parent_class; + + /* + * If an IGVM filename has been specified then process the IGVM file. + * Performs a no-op if no filename has been specified. + * If onlyVpContext is true then only the IGVM_VHT_VP_CONTEXT entries + * in the IGVM file will be processed, allowing information about the + * CPU state to be determined before processing the entire file. + * + * Returns 0 for ok and -1 on error. + */ + int (*process)(IgvmCfg *cfg, ConfidentialGuestSupport *cgs, + bool onlyVpContext, Error **errp); + +} IgvmCfgClass; + +#define TYPE_IGVM_CFG "igvm-cfg" + +OBJECT_DECLARE_TYPE(IgvmCfg, IgvmCfgClass, IGVM_CFG) + +#endif diff --git a/include/system/igvm.h b/include/system/igvm.h new file mode 100644 index 0000000..48ce206 --- /dev/null +++ b/include/system/igvm.h @@ -0,0 +1,29 @@ +/* + * QEMU IGVM configuration backend for Confidential Guests + * + * Copyright (C) 2023-2024 SUSE + * + * Authors: + * Roy Hopkins <roy.hopkins@randomman.co.uk> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef BACKENDS_IGVM_H +#define BACKENDS_IGVM_H + +#include "system/confidential-guest-support.h" +#include "system/igvm-cfg.h" +#include "qapi/error.h" + +int qigvm_process_file(IgvmCfg *igvm, ConfidentialGuestSupport *cgs, + bool onlyVpContext, Error **errp); + +/* x86 native */ +int qigvm_x86_get_mem_map_entry(int index, + ConfidentialGuestMemoryMapEntry *entry, + Error **errp); +int qigvm_x86_set_vp_context(void *data, int index, + Error **errp); + +#endif diff --git a/include/system/iommufd.h b/include/system/iommufd.h index cbab75b..a659f36 100644 --- a/include/system/iommufd.h +++ b/include/system/iommufd.h @@ -32,6 +32,7 @@ struct IOMMUFDBackend { /*< protected >*/ int fd; /* /dev/iommu file descriptor */ bool owned; /* is the /dev/iommu opened internally */ + Error *cpr_blocker;/* set if be does not support CPR */ uint32_t users; /*< public >*/ @@ -43,10 +44,13 @@ void iommufd_backend_disconnect(IOMMUFDBackend *be); bool iommufd_backend_alloc_ioas(IOMMUFDBackend *be, uint32_t *ioas_id, Error **errp); void iommufd_backend_free_id(IOMMUFDBackend *be, uint32_t id); +int iommufd_backend_map_file_dma(IOMMUFDBackend *be, uint32_t ioas_id, + hwaddr iova, uint64_t size, int fd, + unsigned long start, bool readonly); int iommufd_backend_map_dma(IOMMUFDBackend *be, uint32_t ioas_id, hwaddr iova, - ram_addr_t size, void *vaddr, bool readonly); + uint64_t size, void *vaddr, bool readonly); int iommufd_backend_unmap_dma(IOMMUFDBackend *be, uint32_t ioas_id, - hwaddr iova, ram_addr_t size); + hwaddr iova, uint64_t size); bool iommufd_backend_get_device_info(IOMMUFDBackend *be, uint32_t devid, uint32_t *type, void *data, uint32_t len, uint64_t *caps, Error **errp); @@ -61,6 +65,63 @@ bool iommufd_backend_get_dirty_bitmap(IOMMUFDBackend *be, uint32_t hwpt_id, uint64_t iova, ram_addr_t size, uint64_t page_size, uint64_t *data, Error **errp); +bool iommufd_backend_invalidate_cache(IOMMUFDBackend *be, uint32_t id, + uint32_t data_type, uint32_t entry_len, + uint32_t *entry_num, void *data, + Error **errp); + +bool iommufd_change_process_capable(IOMMUFDBackend *be); +bool iommufd_change_process(IOMMUFDBackend *be, Error **errp); #define TYPE_HOST_IOMMU_DEVICE_IOMMUFD TYPE_HOST_IOMMU_DEVICE "-iommufd" +OBJECT_DECLARE_TYPE(HostIOMMUDeviceIOMMUFD, HostIOMMUDeviceIOMMUFDClass, + HOST_IOMMU_DEVICE_IOMMUFD) + +/* Overload of the host IOMMU device for the iommufd backend */ +struct HostIOMMUDeviceIOMMUFD { + HostIOMMUDevice parent_obj; + + IOMMUFDBackend *iommufd; + uint32_t devid; + uint32_t hwpt_id; +}; + +struct HostIOMMUDeviceIOMMUFDClass { + HostIOMMUDeviceClass parent_class; + + /** + * @attach_hwpt: attach host IOMMU device to IOMMUFD hardware page table. + * VFIO and VDPA device can have different implementation. + * + * Mandatory callback. + * + * @idev: host IOMMU device backed by IOMMUFD backend. + * + * @hwpt_id: ID of IOMMUFD hardware page table. + * + * @errp: pass an Error out when attachment fails. + * + * Returns: true on success, false on failure. + */ + bool (*attach_hwpt)(HostIOMMUDeviceIOMMUFD *idev, uint32_t hwpt_id, + Error **errp); + /** + * @detach_hwpt: detach host IOMMU device from IOMMUFD hardware page table. + * VFIO and VDPA device can have different implementation. + * + * Mandatory callback. + * + * @idev: host IOMMU device backed by IOMMUFD backend. + * + * @errp: pass an Error out when attachment fails. + * + * Returns: true on success, false on failure. + */ + bool (*detach_hwpt)(HostIOMMUDeviceIOMMUFD *idev, Error **errp); +}; + +bool host_iommu_device_iommufd_attach_hwpt(HostIOMMUDeviceIOMMUFD *idev, + uint32_t hwpt_id, Error **errp); +bool host_iommu_device_iommufd_detach_hwpt(HostIOMMUDeviceIOMMUFD *idev, + Error **errp); #endif diff --git a/include/exec/ioport.h b/include/system/ioport.h index 4397f12..780ea5a 100644 --- a/include/exec/ioport.h +++ b/include/system/ioport.h @@ -21,10 +21,10 @@ * IO ports API */ -#ifndef IOPORT_H -#define IOPORT_H +#ifndef SYSTEM_IOPORT_H +#define SYSTEM_IOPORT_H -#include "exec/memory.h" +#include "system/memory.h" #define MAX_IOPORTS (64 * 1024) #define IOPORTS_MASK (MAX_IOPORTS - 1) @@ -39,9 +39,7 @@ typedef struct MemoryRegionPortio { #define PORTIO_END_OF_LIST() { } -#ifndef CONFIG_USER_ONLY extern const MemoryRegionOps unassigned_io_ops; -#endif void cpu_outb(uint32_t addr, uint8_t val); void cpu_outw(uint32_t addr, uint16_t val); diff --git a/include/system/kvm.h b/include/system/kvm.h index ab17c09..8f9eecf 100644 --- a/include/system/kvm.h +++ b/include/system/kvm.h @@ -42,6 +42,7 @@ extern bool kvm_gsi_routing_allowed; extern bool kvm_gsi_direct_mapping; extern bool kvm_readonly_mem_allowed; extern bool kvm_msi_use_devid; +extern bool kvm_pre_fault_memory_supported; #define kvm_enabled() (kvm_allowed) /** @@ -194,6 +195,7 @@ bool kvm_has_sync_mmu(void); int kvm_has_vcpu_events(void); int kvm_max_nested_state_length(void); int kvm_has_gsi_routing(void); +void kvm_close(void); /** * kvm_arm_supports_user_irq @@ -210,11 +212,15 @@ bool kvm_arm_supports_user_irq(void); int kvm_on_sigbus_vcpu(CPUState *cpu, int code, void *addr); int kvm_on_sigbus(int code, void *addr); -#ifdef COMPILING_PER_TARGET -#include "cpu.h" +int kvm_check_extension(KVMState *s, unsigned int extension); + +int kvm_vm_ioctl(KVMState *s, unsigned long type, ...); void kvm_flush_coalesced_mmio_buffer(void); +#ifdef COMPILING_PER_TARGET +#include "cpu.h" + /** * kvm_update_guest_debug(): ensure KVM debug structures updated * @cs: the CPUState for this cpu @@ -237,8 +243,6 @@ static inline int kvm_update_guest_debug(CPUState *cpu, unsigned long reinject_t int kvm_ioctl(KVMState *s, unsigned long type, ...); -int kvm_vm_ioctl(KVMState *s, unsigned long type, ...); - int kvm_vcpu_ioctl(CPUState *cpu, unsigned long type, ...); /** @@ -314,31 +318,6 @@ int kvm_create_device(KVMState *s, uint64_t type, bool test); bool kvm_device_supported(int vmfd, uint64_t type); /** - * kvm_create_vcpu - Gets a parked KVM vCPU or creates a KVM vCPU - * @cpu: QOM CPUState object for which KVM vCPU has to be fetched/created. - * - * @returns: 0 when success, errno (<0) when failed. - */ -int kvm_create_vcpu(CPUState *cpu); - -/** - * kvm_park_vcpu - Park QEMU KVM vCPU context - * @cpu: QOM CPUState object for which QEMU KVM vCPU context has to be parked. - * - * @returns: none - */ -void kvm_park_vcpu(CPUState *cpu); - -/** - * kvm_unpark_vcpu - unpark QEMU KVM vCPU context - * @s: KVM State - * @vcpu_id: Architecture vCPU ID of the parked vCPU - * - * @returns: KVM fd - */ -int kvm_unpark_vcpu(KVMState *s, unsigned long vcpu_id); - -/** * kvm_create_and_park_vcpu - Create and park a KVM vCPU * @cpu: QOM CPUState object for which KVM vCPU has to be created and parked. * @@ -361,19 +340,22 @@ int kvm_arch_process_async_events(CPUState *cpu); int kvm_arch_get_registers(CPUState *cpu, Error **errp); -/* state subset only touched by the VCPU itself during runtime */ -#define KVM_PUT_RUNTIME_STATE 1 -/* state subset modified during VCPU reset */ -#define KVM_PUT_RESET_STATE 2 -/* full state set, modified during initialization or on vmload */ -#define KVM_PUT_FULL_STATE 3 +typedef enum kvm_put_state { + /* state subset only touched by the VCPU itself during runtime */ + KVM_PUT_RUNTIME_STATE = 1, + /* state subset modified during VCPU reset */ + KVM_PUT_RESET_STATE = 2, + /* full state set, modified during initialization or on vmload */ + KVM_PUT_FULL_STATE = 3, +} KvmPutState; -int kvm_arch_put_registers(CPUState *cpu, int level, Error **errp); +int kvm_arch_put_registers(CPUState *cpu, KvmPutState level, Error **errp); int kvm_arch_get_default_type(MachineState *ms); int kvm_arch_init(MachineState *ms, KVMState *s); +int kvm_arch_pre_create_vcpu(CPUState *cpu, Error **errp); int kvm_arch_init_vcpu(CPUState *cpu); int kvm_arch_destroy_vcpu(CPUState *cpu); @@ -390,9 +372,7 @@ bool kvm_vcpu_id_is_valid(int vcpu_id); /* Returns VCPU ID to be used on KVM_CREATE_VCPU ioctl() */ unsigned long kvm_arch_vcpu_id(CPUState *cpu); -#ifdef KVM_HAVE_MCE_INJECTION void kvm_arch_on_sigbus_vcpu(CPUState *cpu, int code, void *addr); -#endif void kvm_arch_init_irq_routing(KVMState *s); @@ -443,8 +423,6 @@ void kvm_arch_update_guest_debug(CPUState *cpu, struct kvm_guest_debug *dbg); bool kvm_arch_stop_on_emulation_error(CPUState *cpu); -int kvm_check_extension(KVMState *s, unsigned int extension); - int kvm_vm_check_extension(KVMState *s, unsigned int extension); #define kvm_vm_enable_cap(s, capability, cap_flags, ...) \ diff --git a/include/system/kvm_int.h b/include/system/kvm_int.h index 4de6106..9247493 100644 --- a/include/system/kvm_int.h +++ b/include/system/kvm_int.h @@ -9,11 +9,12 @@ #ifndef QEMU_KVM_INT_H #define QEMU_KVM_INT_H -#include "exec/memory.h" +#include "system/memory.h" #include "qapi/qapi-types-common.h" #include "qemu/accel.h" #include "qemu/queue.h" #include "system/kvm.h" +#include "accel/accel-ops.h" #include "hw/boards.h" #include "hw/i386/topology.h" #include "io/channel-socket.h" diff --git a/include/exec/memory.h b/include/system/memory.h index d09af58..3bd5ffa 100644 --- a/include/exec/memory.h +++ b/include/system/memory.h @@ -11,10 +11,8 @@ * */ -#ifndef MEMORY_H -#define MEMORY_H - -#ifndef CONFIG_USER_ONLY +#ifndef SYSTEM_MEMORY_H +#define SYSTEM_MEMORY_H #include "exec/cpu-common.h" #include "exec/hwaddr.h" @@ -110,15 +108,34 @@ struct MemoryRegionSection { typedef struct IOMMUTLBEntry IOMMUTLBEntry; -/* See address_space_translate: bit 0 is read, bit 1 is write. */ +/* + * See address_space_translate: + * - bit 0 : read + * - bit 1 : write + * - bit 2 : exec + * - bit 3 : priv + * - bit 4 : global + * - bit 5 : untranslated only + */ typedef enum { IOMMU_NONE = 0, IOMMU_RO = 1, IOMMU_WO = 2, IOMMU_RW = 3, + IOMMU_EXEC = 4, + IOMMU_PRIV = 8, + IOMMU_GLOBAL = 16, + IOMMU_UNTRANSLATED_ONLY = 32, } IOMMUAccessFlags; -#define IOMMU_ACCESS_FLAG(r, w) (((r) ? IOMMU_RO : 0) | ((w) ? IOMMU_WO : 0)) +#define IOMMU_ACCESS_FLAG(r, w) (((r) ? IOMMU_RO : 0) | \ + ((w) ? IOMMU_WO : 0)) +#define IOMMU_ACCESS_FLAG_FULL(r, w, x, p, g, uo) \ + (IOMMU_ACCESS_FLAG(r, w) | \ + ((x) ? IOMMU_EXEC : 0) | \ + ((p) ? IOMMU_PRIV : 0) | \ + ((g) ? IOMMU_GLOBAL : 0) | \ + ((uo) ? IOMMU_UNTRANSLATED_ONLY : 0)) struct IOMMUTLBEntry { AddressSpace *target_as; @@ -126,6 +143,7 @@ struct IOMMUTLBEntry { hwaddr translated_addr; hwaddr addr_mask; /* 0xfff = 4k translation */ IOMMUAccessFlags perm; + uint32_t pasid; }; /* @@ -184,6 +202,7 @@ struct IOMMUNotifier { hwaddr start; hwaddr end; int iommu_idx; + void *opaque; QLIST_ENTRY(IOMMUNotifier) node; }; typedef struct IOMMUNotifier IOMMUNotifier; @@ -576,8 +595,20 @@ static inline void ram_discard_listener_init(RamDiscardListener *rdl, rdl->double_discard_supported = double_discard_supported; } -typedef int (*ReplayRamPopulate)(MemoryRegionSection *section, void *opaque); -typedef void (*ReplayRamDiscard)(MemoryRegionSection *section, void *opaque); +/** + * typedef ReplayRamDiscardState: + * + * The callback handler for #RamDiscardManagerClass.replay_populated/ + * #RamDiscardManagerClass.replay_discarded to invoke on populated/discarded + * parts. + * + * @section: the #MemoryRegionSection of populated/discarded part + * @opaque: pointer to forward to the callback + * + * Returns 0 on success, or a negative error if failed. + */ +typedef int (*ReplayRamDiscardState)(MemoryRegionSection *section, + void *opaque); /* * RamDiscardManagerClass: @@ -651,36 +682,38 @@ struct RamDiscardManagerClass { /** * @replay_populated: * - * Call the #ReplayRamPopulate callback for all populated parts within the - * #MemoryRegionSection via the #RamDiscardManager. + * Call the #ReplayRamDiscardState callback for all populated parts within + * the #MemoryRegionSection via the #RamDiscardManager. * * In case any call fails, no further calls are made. * * @rdm: the #RamDiscardManager * @section: the #MemoryRegionSection - * @replay_fn: the #ReplayRamPopulate callback + * @replay_fn: the #ReplayRamDiscardState callback * @opaque: pointer to forward to the callback * * Returns 0 on success, or a negative error if any notification failed. */ int (*replay_populated)(const RamDiscardManager *rdm, MemoryRegionSection *section, - ReplayRamPopulate replay_fn, void *opaque); + ReplayRamDiscardState replay_fn, void *opaque); /** * @replay_discarded: * - * Call the #ReplayRamDiscard callback for all discarded parts within the - * #MemoryRegionSection via the #RamDiscardManager. + * Call the #ReplayRamDiscardState callback for all discarded parts within + * the #MemoryRegionSection via the #RamDiscardManager. * * @rdm: the #RamDiscardManager * @section: the #MemoryRegionSection - * @replay_fn: the #ReplayRamDiscard callback + * @replay_fn: the #ReplayRamDiscardState callback * @opaque: pointer to forward to the callback + * + * Returns 0 on success, or a negative error if any notification failed. */ - void (*replay_discarded)(const RamDiscardManager *rdm, - MemoryRegionSection *section, - ReplayRamDiscard replay_fn, void *opaque); + int (*replay_discarded)(const RamDiscardManager *rdm, + MemoryRegionSection *section, + ReplayRamDiscardState replay_fn, void *opaque); /** * @register_listener: @@ -721,15 +754,41 @@ uint64_t ram_discard_manager_get_min_granularity(const RamDiscardManager *rdm, bool ram_discard_manager_is_populated(const RamDiscardManager *rdm, const MemoryRegionSection *section); +/** + * ram_discard_manager_replay_populated: + * + * A wrapper to call the #RamDiscardManagerClass.replay_populated callback + * of the #RamDiscardManager. + * + * @rdm: the #RamDiscardManager + * @section: the #MemoryRegionSection + * @replay_fn: the #ReplayRamDiscardState callback + * @opaque: pointer to forward to the callback + * + * Returns 0 on success, or a negative error if any notification failed. + */ int ram_discard_manager_replay_populated(const RamDiscardManager *rdm, MemoryRegionSection *section, - ReplayRamPopulate replay_fn, + ReplayRamDiscardState replay_fn, void *opaque); -void ram_discard_manager_replay_discarded(const RamDiscardManager *rdm, - MemoryRegionSection *section, - ReplayRamDiscard replay_fn, - void *opaque); +/** + * ram_discard_manager_replay_discarded: + * + * A wrapper to call the #RamDiscardManagerClass.replay_discarded callback + * of the #RamDiscardManager. + * + * @rdm: the #RamDiscardManager + * @section: the #MemoryRegionSection + * @replay_fn: the #ReplayRamDiscardState callback + * @opaque: pointer to forward to the callback + * + * Returns 0 on success, or a negative error if any notification failed. + */ +int ram_discard_manager_replay_discarded(const RamDiscardManager *rdm, + MemoryRegionSection *section, + ReplayRamDiscardState replay_fn, + void *opaque); void ram_discard_manager_register_listener(RamDiscardManager *rdm, RamDiscardListener *rdl, @@ -739,21 +798,20 @@ void ram_discard_manager_unregister_listener(RamDiscardManager *rdm, RamDiscardListener *rdl); /** - * memory_get_xlat_addr: Extract addresses from a TLB entry + * memory_translate_iotlb: Extract addresses from a TLB entry. + * Called with rcu_read_lock held. * * @iotlb: pointer to an #IOMMUTLBEntry - * @vaddr: virtual address - * @ram_addr: RAM address - * @read_only: indicates if writes are allowed - * @mr_has_discard_manager: indicates memory is controlled by a - * RamDiscardManager + * @xlat_p: return the offset of the entry from the start of the returned + * MemoryRegion. * @errp: pointer to Error*, to store an error if it happens. * - * Return: true on success, else false setting @errp with error. + * Return: On success, return the MemoryRegion containing the @iotlb translated + * addr. The MemoryRegion must not be accessed after rcu_read_unlock. + * On failure, return NULL, setting @errp with error. */ -bool memory_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr, - ram_addr_t *ram_addr, bool *read_only, - bool *mr_has_discard_manager, Error **errp); +MemoryRegion *memory_translate_iotlb(IOMMUTLBEntry *iotlb, hwaddr *xlat_p, + Error **errp); typedef struct CoalescedMemoryRange CoalescedMemoryRange; typedef struct MemoryRegionIoeventfd MemoryRegionIoeventfd; @@ -775,6 +833,7 @@ struct MemoryRegion { bool nonvolatile; bool rom_device; bool flush_coalesced_mmio; + bool lockless_io; bool unmergeable; uint8_t dirty_log_mask; bool is_iommu; @@ -1213,6 +1272,36 @@ MemoryRegionSection *memory_region_section_new_copy(MemoryRegionSection *s); void memory_region_section_free_copy(MemoryRegionSection *s); /** + * memory_region_section_intersect_range: Adjust the memory section to cover + * the intersection with the given range. + * + * @s: the #MemoryRegionSection to be adjusted + * @offset: the offset of the given range in the memory region + * @size: the size of the given range + * + * Returns false if the intersection is empty, otherwise returns true. + */ +static inline bool memory_region_section_intersect_range(MemoryRegionSection *s, + uint64_t offset, + uint64_t size) +{ + uint64_t start = MAX(s->offset_within_region, offset); + Int128 end = int128_min(int128_add(int128_make64(s->offset_within_region), + s->size), + int128_add(int128_make64(offset), + int128_make64(size))); + + if (int128_le(end, int128_make64(start))) { + return false; + } + + s->offset_within_address_space += start - s->offset_within_region; + s->offset_within_region = start; + s->size = int128_sub(end, int128_make64(start)); + return true; +} + +/** * memory_region_init: Initialize a memory region * * The region typically acts as a container for other memory regions. Use @@ -2162,7 +2251,7 @@ void memory_region_flush_rom_device(MemoryRegion *mr, hwaddr addr, hwaddr size); * only useful on RAM regions. * * @mr: the region being updated. - * @readonly: whether rhe region is to be ROM or RAM. + * @readonly: whether the region is to be ROM or RAM. */ void memory_region_set_readonly(MemoryRegion *mr, bool readonly); @@ -2173,7 +2262,7 @@ void memory_region_set_readonly(MemoryRegion *mr, bool readonly); * only useful on RAM regions. * * @mr: the region being updated. - * @nonvolatile: whether rhe region is to be non-volatile. + * @nonvolatile: whether the region is to be non-volatile. */ void memory_region_set_nonvolatile(MemoryRegion *mr, bool nonvolatile); @@ -2254,6 +2343,17 @@ void memory_region_set_flush_coalesced(MemoryRegion *mr); void memory_region_clear_flush_coalesced(MemoryRegion *mr); /** + * memory_region_enable_lockless_io: Enable lockless (BQL free) acceess. + * + * Enable BQL-free access for devices that are well prepared to handle + * locking during I/O themselves: either by doing fine grained locking or + * by providing lock-free I/O schemes. + * + * @mr: the memory region to be updated. + */ +void memory_region_enable_lockless_io(MemoryRegion *mr); + +/** * memory_region_add_eventfd: Request an eventfd to be triggered when a word * is written to a location. * @@ -2470,13 +2570,13 @@ static inline bool memory_region_has_ram_discard_manager(MemoryRegion *mr) * * This function must not be called for a mapped #MemoryRegion, a #MemoryRegion * that does not cover RAM, or a #MemoryRegion that already has a - * #RamDiscardManager assigned. + * #RamDiscardManager assigned. Return 0 if the rdm is set successfully. * * @mr: the #MemoryRegion * @rdm: #RamDiscardManager to set */ -void memory_region_set_ram_discard_manager(MemoryRegion *mr, - RamDiscardManager *rdm); +int memory_region_set_ram_discard_manager(MemoryRegion *mr, + RamDiscardManager *rdm); /** * memory_region_find: translate an address/size relative to a @@ -2627,15 +2727,33 @@ void address_space_init(AddressSpace *as, MemoryRegion *root, const char *name); /** * address_space_destroy: destroy an address space * - * Releases all resources associated with an address space. After an address space - * is destroyed, its root memory region (given by address_space_init()) may be destroyed - * as well. + * Releases all resources associated with an address space. After an + * address space is destroyed, the reference the AddressSpace had to + * its root memory region is dropped, which may result in the + * destruction of that memory region as well. + * + * Note that destruction of the AddressSpace is done via RCU; + * it is therefore not valid to free the memory the AddressSpace + * struct is in until after that RCU callback has completed. + * If you want to g_free() the AddressSpace after destruction you + * can do that with address_space_destroy_free(). * * @as: address space to be destroyed */ void address_space_destroy(AddressSpace *as); /** + * address_space_destroy_free: destroy an address space and free it + * + * This does the same thing as address_space_destroy(), and then also + * frees (via g_free()) the AddressSpace itself once the destruction + * is complete. + * + * @as: address space to be destroyed + */ +void address_space_destroy_free(AddressSpace *as); + +/** * address_space_remove_listeners: unregister all listeners of an address space * * Removes all callbacks previously registered with memory_listener_register() @@ -2732,6 +2850,12 @@ MemTxResult address_space_write_rom(AddressSpace *as, hwaddr addr, #define ARG1_DECL AddressSpace *as #include "exec/memory_ldst.h.inc" +static inline void stl_phys_notdirty(AddressSpace *as, hwaddr addr, uint32_t val) +{ + address_space_stl_notdirty(as, addr, val, + MEMTXATTRS_UNSPECIFIED, NULL); +} + #define SUFFIX #define ARG1 as #define ARG1_DECL AddressSpace *as @@ -2798,6 +2922,9 @@ static inline void address_space_stb_cached(MemoryRegionCache *cache, } } +#define ENDIANNESS +#include "exec/memory_ldst_cached.h.inc" + #define ENDIANNESS _le #include "exec/memory_ldst_cached.h.inc" @@ -2868,6 +2995,8 @@ void address_space_cache_invalidate(MemoryRegionCache *cache, */ void address_space_cache_destroy(MemoryRegionCache *cache); +void address_space_flush_icache_range(AddressSpace *as, hwaddr addr, hwaddr len); + /* address_space_get_iotlb_entry: translate an address into an IOTLB * entry. Should be called from an RCU critical section. */ @@ -2920,6 +3049,15 @@ static inline MemoryRegion *address_space_translate(AddressSpace *as, bool address_space_access_valid(AddressSpace *as, hwaddr addr, hwaddr len, bool is_write, MemTxAttrs attrs); +/** + * address_space_is_io: check whether an guest physical addresses + * whithin an address space is I/O memory. + * + * @as: #AddressSpace to be accessed + * @addr: address within that address space + */ +bool address_space_is_io(AddressSpace *as, hwaddr addr); + /* address_space_map: map a physical memory region into a host virtual address * * May map a subset of the requested range, given by and returned in @plen. @@ -3128,26 +3266,6 @@ address_space_write_cached(MemoryRegionCache *cache, hwaddr addr, MemTxResult address_space_set(AddressSpace *as, hwaddr addr, uint8_t c, hwaddr len, MemTxAttrs attrs); -#ifdef COMPILING_PER_TARGET -/* enum device_endian to MemOp. */ -static inline MemOp devend_memop(enum device_endian end) -{ - QEMU_BUILD_BUG_ON(DEVICE_HOST_ENDIAN != DEVICE_LITTLE_ENDIAN && - DEVICE_HOST_ENDIAN != DEVICE_BIG_ENDIAN); - -#if HOST_BIG_ENDIAN != TARGET_BIG_ENDIAN - /* Swap if non-host endianness or native (target) endianness */ - return (end == DEVICE_HOST_ENDIAN) ? 0 : MO_BSWAP; -#else - const int non_host_endianness = - DEVICE_LITTLE_ENDIAN ^ DEVICE_BIG_ENDIAN ^ DEVICE_HOST_ENDIAN; - - /* In this case, native (target) endianness needs no swap. */ - return (end == non_host_endianness) ? MO_BSWAP : 0; -#endif -} -#endif /* COMPILING_PER_TARGET */ - /* * Inhibit technologies that require discarding of pages in RAM blocks, e.g., * to manage the actual amount of memory consumed by the VM (then, the memory @@ -3207,5 +3325,3 @@ void ram_block_add_cpr_blocker(RAMBlock *rb, Error **errp); void ram_block_del_cpr_blocker(RAMBlock *rb); #endif - -#endif diff --git a/include/system/mshv.h b/include/system/mshv.h new file mode 100644 index 0000000..8b1fc20 --- /dev/null +++ b/include/system/mshv.h @@ -0,0 +1,64 @@ +/* + * QEMU MSHV support + * + * Copyright Microsoft, Corp. 2025 + * + * Authors: Ziqiao Zhou <ziqiaozhou@microsoft.com> + * Magnus Kulke <magnuskulke@microsoft.com> + * Jinank Jain <jinankjain@microsoft.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + * + */ + +#ifndef QEMU_MSHV_H +#define QEMU_MSHV_H + +#include "qemu/osdep.h" +#include "qemu/accel.h" +#include "hw/hyperv/hyperv-proto.h" +#include "hw/hyperv/hvhdk.h" +#include "hw/hyperv/hvgdk_mini.h" +#include "qapi/qapi-types-common.h" +#include "system/memory.h" +#include "accel/accel-ops.h" + +#ifdef COMPILING_PER_TARGET +#ifdef CONFIG_MSHV +#include <linux/mshv.h> +#define CONFIG_MSHV_IS_POSSIBLE +#endif +#else +#define CONFIG_MSHV_IS_POSSIBLE +#endif + +#define MSHV_MAX_MSI_ROUTES 4096 + +#define MSHV_PAGE_SHIFT 12 + +#ifdef CONFIG_MSHV_IS_POSSIBLE +extern bool mshv_allowed; +#define mshv_enabled() (mshv_allowed) +#define mshv_msi_via_irqfd_enabled() mshv_enabled() +#else /* CONFIG_MSHV_IS_POSSIBLE */ +#define mshv_enabled() false +#define mshv_msi_via_irqfd_enabled() mshv_enabled() +#endif + +typedef struct MshvState MshvState; +extern MshvState *mshv_state; + +/* interrupt */ +int mshv_request_interrupt(MshvState *mshv_state, uint32_t interrupt_type, uint32_t vector, + uint32_t vp_index, bool logical_destination_mode, + bool level_triggered); + +int mshv_irqchip_add_msi_route(int vector, PCIDevice *dev); +int mshv_irqchip_update_msi_route(int virq, MSIMessage msg, PCIDevice *dev); +void mshv_irqchip_commit_routes(void); +void mshv_irqchip_release_virq(int virq); +int mshv_irqchip_add_irqfd_notifier_gsi(const EventNotifier *n, + const EventNotifier *rn, int virq); +int mshv_irqchip_remove_irqfd_notifier_gsi(const EventNotifier *n, int virq); + +#endif diff --git a/include/system/mshv_int.h b/include/system/mshv_int.h new file mode 100644 index 0000000..490563c --- /dev/null +++ b/include/system/mshv_int.h @@ -0,0 +1,155 @@ +/* + * QEMU MSHV support + * + * Copyright Microsoft, Corp. 2025 + * + * Authors: Ziqiao Zhou <ziqiaozhou@microsoft.com> + * Magnus Kulke <magnuskulke@microsoft.com> + * Jinank Jain <jinankjain@microsoft.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + * + */ + +#ifndef QEMU_MSHV_INT_H +#define QEMU_MSHV_INT_H + +#define MSHV_MSR_ENTRIES_COUNT 64 + +#define MSHV_MAX_MEM_SLOTS 32 + +typedef struct hyperv_message hv_message; + +typedef struct MshvHvCallArgs { + void *base; + void *input_page; + void *output_page; +} MshvHvCallArgs; + +struct AccelCPUState { + int cpufd; + bool dirty; + MshvHvCallArgs hvcall_args; +}; + +typedef struct MshvMemoryListener { + MemoryListener listener; + int as_id; +} MshvMemoryListener; + +typedef struct MshvAddressSpace { + MshvMemoryListener *ml; + AddressSpace *as; +} MshvAddressSpace; + +typedef struct MshvMemorySlotManager { + size_t n_slots; + GList *slots; + QemuMutex mutex; +} MshvMemorySlotManager; + +struct MshvState { + AccelState parent_obj; + int vm; + MshvMemoryListener memory_listener; + /* number of listeners */ + int nr_as; + MshvAddressSpace *as; + int fd; + MshvMemorySlotManager msm; +}; + +typedef struct MshvMsiControl { + bool updated; + GHashTable *gsi_routes; +} MshvMsiControl; + +#define mshv_vcpufd(cpu) (cpu->accel->cpufd) + +/* cpu */ +typedef struct MshvFPU { + uint8_t fpr[8][16]; + uint16_t fcw; + uint16_t fsw; + uint8_t ftwx; + uint8_t pad1; + uint16_t last_opcode; + uint64_t last_ip; + uint64_t last_dp; + uint8_t xmm[16][16]; + uint32_t mxcsr; + uint32_t pad2; +} MshvFPU; + +typedef enum MshvVmExit { + MshvVmExitIgnore = 0, + MshvVmExitShutdown = 1, + MshvVmExitSpecial = 2, +} MshvVmExit; + +typedef enum MshvRemapResult { + MshvRemapOk = 0, + MshvRemapNoMapping = 1, + MshvRemapNoOverlap = 2, +} MshvRemapResult; + +void mshv_init_mmio_emu(void); +int mshv_create_vcpu(int vm_fd, uint8_t vp_index, int *cpu_fd); +void mshv_remove_vcpu(int vm_fd, int cpu_fd); +int mshv_configure_vcpu(const CPUState *cpu, const MshvFPU *fpu, uint64_t xcr0); +int mshv_get_standard_regs(CPUState *cpu); +int mshv_get_special_regs(CPUState *cpu); +int mshv_run_vcpu(int vm_fd, CPUState *cpu, hv_message *msg, MshvVmExit *exit); +int mshv_load_regs(CPUState *cpu); +int mshv_store_regs(CPUState *cpu); +int mshv_set_generic_regs(const CPUState *cpu, const hv_register_assoc *assocs, + size_t n_regs); +int mshv_arch_put_registers(const CPUState *cpu); +void mshv_arch_init_vcpu(CPUState *cpu); +void mshv_arch_destroy_vcpu(CPUState *cpu); +void mshv_arch_amend_proc_features( + union hv_partition_synthetic_processor_features *features); +int mshv_arch_post_init_vm(int vm_fd); + +#if defined COMPILING_PER_TARGET && defined CONFIG_MSHV_IS_POSSIBLE +int mshv_hvcall(int fd, const struct mshv_root_hvcall *args); +#endif + +/* memory */ +typedef struct MshvMemorySlot { + uint64_t guest_phys_addr; + uint64_t memory_size; + uint64_t userspace_addr; + bool readonly; + bool mapped; +} MshvMemorySlot; + +MshvRemapResult mshv_remap_overlap_region(int vm_fd, uint64_t gpa); +int mshv_guest_mem_read(uint64_t gpa, uint8_t *data, uintptr_t size, + bool is_secure_mode, bool instruction_fetch); +int mshv_guest_mem_write(uint64_t gpa, const uint8_t *data, uintptr_t size, + bool is_secure_mode); +void mshv_set_phys_mem(MshvMemoryListener *mml, MemoryRegionSection *section, + bool add); +void mshv_init_memory_slot_manager(MshvState *mshv_state); + +/* msr */ +typedef struct MshvMsrEntry { + uint32_t index; + uint32_t reserved; + uint64_t data; +} MshvMsrEntry; + +typedef struct MshvMsrEntries { + MshvMsrEntry entries[MSHV_MSR_ENTRIES_COUNT]; + uint32_t nmsrs; +} MshvMsrEntries; + +int mshv_configure_msr(const CPUState *cpu, const MshvMsrEntry *msrs, + size_t n_msrs); + +/* interrupt */ +void mshv_init_msicontrol(void); +int mshv_reserve_ioapic_msi_routes(int vm_fd); + +#endif diff --git a/include/system/nvmm.h b/include/system/nvmm.h index 6971ddb..7390def 100644 --- a/include/system/nvmm.h +++ b/include/system/nvmm.h @@ -13,17 +13,18 @@ #define QEMU_NVMM_H #ifdef COMPILING_PER_TARGET - -#ifdef CONFIG_NVMM - -int nvmm_enabled(void); - -#else /* CONFIG_NVMM */ - -#define nvmm_enabled() (0) - -#endif /* CONFIG_NVMM */ - +# ifdef CONFIG_NVMM +# define CONFIG_NVMM_IS_POSSIBLE +# endif /* !CONFIG_NVMM */ +#else +# define CONFIG_NVMM_IS_POSSIBLE #endif /* COMPILING_PER_TARGET */ +#ifdef CONFIG_NVMM_IS_POSSIBLE +extern bool nvmm_allowed; +#define nvmm_enabled() (nvmm_allowed) +#else /* !CONFIG_NVMM_IS_POSSIBLE */ +#define nvmm_enabled() 0 +#endif /* !CONFIG_NVMM_IS_POSSIBLE */ + #endif /* QEMU_NVMM_H */ diff --git a/include/system/os-wasm.h b/include/system/os-wasm.h new file mode 100644 index 0000000..3abb3aa --- /dev/null +++ b/include/system/os-wasm.h @@ -0,0 +1,104 @@ +/* SPDX-License-Identifier: MIT */ +/* + * posix specific declarations forked from os-posix.h, removing functions not + * working on Emscripten + * + * Copyright (c) 2003-2008 Fabrice Bellard + * Copyright (c) 2010 Jes Sorensen <Jes.Sorensen@redhat.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#ifndef QEMU_OS_WASM_H +#define QEMU_OS_WASM_H + +#include <sys/mman.h> +#include <sys/socket.h> +#include <netinet/in.h> +#include <netinet/tcp.h> +#include <arpa/inet.h> +#include <netdb.h> +#include <sys/un.h> + +#ifdef CONFIG_SYSMACROS +#include <sys/sysmacros.h> +#endif + +#ifdef __cplusplus +extern "C" { +#endif + +void os_set_line_buffering(void); +void os_setup_early_signal_handling(void); +void os_set_proc_name(const char *s); +void os_setup_signal_handling(void); +void os_setup_limits(void); +void os_setup_post(void); +int os_mlock(bool on_fault); +static inline int os_set_daemonize(bool d) +{ + return -1; +}; +bool is_daemonized(void); +static inline void os_daemonize(void) {} + +/** + * qemu_alloc_stack: + * @sz: pointer to a size_t holding the requested usable stack size + * + * Allocate memory that can be used as a stack, for instance for + * coroutines. If the memory cannot be allocated, this function + * will abort (like g_malloc()). This function also inserts an + * additional guard page to catch a potential stack overflow. + * Note that the memory required for the guard page and alignment + * and minimal stack size restrictions will increase the value of sz. + * + * The allocated stack must be freed with qemu_free_stack(). + * + * Returns: pointer to (the lowest address of) the stack memory. + */ +void *qemu_alloc_stack(size_t *sz); + +/** + * qemu_free_stack: + * @stack: stack to free + * @sz: size of stack in bytes + * + * Free a stack allocated via qemu_alloc_stack(). Note that sz must + * be exactly the adjusted stack size returned by qemu_alloc_stack. + */ +void qemu_free_stack(void *stack, size_t sz); + +/* POSIX and Mingw32 differ in the name of the stdio lock functions. */ + +static inline void qemu_flockfile(FILE *f) +{ + flockfile(f); +} + +static inline void qemu_funlockfile(FILE *f) +{ + funlockfile(f); +} + +#ifdef __cplusplus +} +#endif + +#endif diff --git a/include/system/os-win32.h b/include/system/os-win32.h index bc62306..22d72ba 100644 --- a/include/system/os-win32.h +++ b/include/system/os-win32.h @@ -130,7 +130,6 @@ static inline int os_mlock(bool on_fault G_GNUC_UNUSED) static inline void os_setup_limits(void) { - return; } #define fsync _commit @@ -169,11 +168,14 @@ static inline void qemu_funlockfile(FILE *f) #endif } -/* Helper for WSAEventSelect, to report errors */ +/* Helpers for WSAEventSelect() */ bool qemu_socket_select(int sockfd, WSAEVENT hEventObject, long lNetworkEvents, Error **errp); +void qemu_socket_select_nofail(int sockfd, WSAEVENT hEventObject, + long lNetworkEvents); bool qemu_socket_unselect(int sockfd, Error **errp); +void qemu_socket_unselect_nofail(int sockfd); /* We wrap all the sockets functions so that we can set errno based on * WSAGetLastError(), and use file-descriptors instead of SOCKET. diff --git a/include/system/physmem.h b/include/system/physmem.h new file mode 100644 index 0000000..879f6ea --- /dev/null +++ b/include/system/physmem.h @@ -0,0 +1,54 @@ +/* + * QEMU physical memory interfaces (target independent). + * + * Copyright (c) 2003 Fabrice Bellard + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ +#ifndef QEMU_SYSTEM_PHYSMEM_H +#define QEMU_SYSTEM_PHYSMEM_H + +#include "exec/hwaddr.h" +#include "exec/ramlist.h" + +#define DIRTY_CLIENTS_ALL ((1 << DIRTY_MEMORY_NUM) - 1) +#define DIRTY_CLIENTS_NOCODE (DIRTY_CLIENTS_ALL & ~(1 << DIRTY_MEMORY_CODE)) + +bool physical_memory_get_dirty_flag(ram_addr_t addr, unsigned client); + +bool physical_memory_is_clean(ram_addr_t addr); + +uint8_t physical_memory_range_includes_clean(ram_addr_t start, + ram_addr_t length, + uint8_t mask); + +void physical_memory_set_dirty_flag(ram_addr_t addr, unsigned client); + +void physical_memory_set_dirty_range(ram_addr_t start, ram_addr_t length, + uint8_t mask); + +/* + * Contrary to physical_memory_sync_dirty_bitmap() this function returns + * the number of dirty pages in @bitmap passed as argument. On the other hand, + * physical_memory_sync_dirty_bitmap() returns newly dirtied pages that + * weren't set in the global migration bitmap. + */ +uint64_t physical_memory_set_dirty_lebitmap(unsigned long *bitmap, + ram_addr_t start, + ram_addr_t pages); + +void physical_memory_dirty_bits_cleared(ram_addr_t start, ram_addr_t length); + +bool physical_memory_test_and_clear_dirty(ram_addr_t start, + ram_addr_t length, + unsigned client); + +DirtyBitmapSnapshot * +physical_memory_snapshot_and_clear_dirty(MemoryRegion *mr, hwaddr offset, + hwaddr length, unsigned client); + +bool physical_memory_snapshot_get_dirty(DirtyBitmapSnapshot *snap, + ram_addr_t start, + ram_addr_t length); + +#endif diff --git a/include/system/qtest.h b/include/system/qtest.h index 6ddddc5..7f6dc01 100644 --- a/include/system/qtest.h +++ b/include/system/qtest.h @@ -23,9 +23,8 @@ static inline bool qtest_enabled(void) return qtest_allowed; } -#ifndef CONFIG_USER_ONLY -void G_GNUC_PRINTF(2, 3) qtest_sendf(CharBackend *chr, const char *fmt, ...); -void qtest_set_command_cb(bool (*pc_cb)(CharBackend *chr, gchar **words)); +void G_GNUC_PRINTF(2, 3) qtest_sendf(CharFrontend *chr, const char *fmt, ...); +void qtest_set_command_cb(bool (*pc_cb)(CharFrontend *chr, gchar **words)); bool qtest_driver(void); void qtest_server_init(const char *qtest_chrdev, const char *qtest_log, Error **errp); @@ -33,6 +32,5 @@ void qtest_server_init(const char *qtest_chrdev, const char *qtest_log, Error ** void qtest_server_set_send_handler(void (*send)(void *, const char *), void *opaque); void qtest_server_inproc_recv(void *opaque, const char *buf); -#endif #endif diff --git a/include/system/ram_addr.h b/include/system/ram_addr.h new file mode 100644 index 0000000..6834859 --- /dev/null +++ b/include/system/ram_addr.h @@ -0,0 +1,135 @@ +/* + * Declarations for cpu physical memory functions + * + * Copyright 2011 Red Hat, Inc. and/or its affiliates + * + * Authors: + * Avi Kivity <avi@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * later. See the COPYING file in the top-level directory. + * + */ + +/* + * This header is for use by exec.c and memory.c ONLY. Do not include it. + * The functions declared here will be removed soon. + */ + +#ifndef SYSTEM_RAM_ADDR_H +#define SYSTEM_RAM_ADDR_H + +#include "system/ramblock.h" +#include "exec/target_page.h" +#include "exec/hwaddr.h" + +extern uint64_t total_dirty_pages; + +/** + * clear_bmap_size: calculate clear bitmap size + * + * @pages: number of guest pages + * @shift: guest page number shift + * + * Returns: number of bits for the clear bitmap + */ +static inline long clear_bmap_size(uint64_t pages, uint8_t shift) +{ + return DIV_ROUND_UP(pages, 1UL << shift); +} + +/** + * clear_bmap_set: set clear bitmap for the page range. Must be with + * bitmap_mutex held. + * + * @rb: the ramblock to operate on + * @start: the start page number + * @size: number of pages to set in the bitmap + * + * Returns: None + */ +static inline void clear_bmap_set(RAMBlock *rb, uint64_t start, + uint64_t npages) +{ + uint8_t shift = rb->clear_bmap_shift; + + bitmap_set(rb->clear_bmap, start >> shift, clear_bmap_size(npages, shift)); +} + +/** + * clear_bmap_test_and_clear: test clear bitmap for the page, clear if set. + * Must be with bitmap_mutex held. + * + * @rb: the ramblock to operate on + * @page: the page number to check + * + * Returns: true if the bit was set, false otherwise + */ +static inline bool clear_bmap_test_and_clear(RAMBlock *rb, uint64_t page) +{ + uint8_t shift = rb->clear_bmap_shift; + + return bitmap_test_and_clear(rb->clear_bmap, page >> shift, 1); +} + +static inline unsigned long int ramblock_recv_bitmap_offset(void *host_addr, + RAMBlock *rb) +{ + uint64_t host_addr_offset = + (uint64_t)(uintptr_t)(host_addr - (void *)rb->host); + return host_addr_offset >> TARGET_PAGE_BITS; +} + +/** + * qemu_ram_alloc_from_file, + * qemu_ram_alloc_from_fd: Allocate a ram block from the specified backing + * file or device + * + * Parameters: + * @size: the size in bytes of the ram block + * @max_size: the maximum size of the block after resizing + * @mr: the memory region where the ram block is + * @resized: callback after calls to qemu_ram_resize + * @ram_flags: RamBlock flags. Supported flags: RAM_SHARED, RAM_PMEM, + * RAM_NORESERVE, RAM_PROTECTED, RAM_NAMED_FILE, RAM_READONLY, + * RAM_READONLY_FD, RAM_GUEST_MEMFD + * @mem_path or @fd: specify the backing file or device + * @offset: Offset into target file + * @grow: extend file if necessary (but an empty file is always extended). + * @errp: pointer to Error*, to store an error if it happens + * + * Return: + * On success, return a pointer to the ram block. + * On failure, return NULL. + */ +typedef void (*qemu_ram_resize_cb)(const char *, uint64_t length, void *host); + +RAMBlock *qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr, + uint32_t ram_flags, const char *mem_path, + off_t offset, Error **errp); +RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, ram_addr_t max_size, + qemu_ram_resize_cb resized, MemoryRegion *mr, + uint32_t ram_flags, int fd, off_t offset, + bool grow, + Error **errp); + +RAMBlock *qemu_ram_alloc_from_ptr(ram_addr_t size, void *host, + MemoryRegion *mr, Error **errp); +RAMBlock *qemu_ram_alloc(ram_addr_t size, uint32_t ram_flags, MemoryRegion *mr, + Error **errp); +RAMBlock *qemu_ram_alloc_resizeable(ram_addr_t size, ram_addr_t max_size, + qemu_ram_resize_cb resized, + MemoryRegion *mr, Error **errp); +void qemu_ram_free(RAMBlock *block); + +int qemu_ram_resize(RAMBlock *block, ram_addr_t newsize, Error **errp); + +void qemu_ram_msync(RAMBlock *block, ram_addr_t start, ram_addr_t length); + +/* Clear whole block of mem */ +static inline void qemu_ram_block_writeback(RAMBlock *block) +{ + qemu_ram_msync(block, 0, block->used_length); +} + +#endif diff --git a/include/exec/ramblock.h b/include/system/ramblock.h index 64484cd..76694fe 100644 --- a/include/exec/ramblock.h +++ b/include/system/ramblock.h @@ -11,18 +11,16 @@ * */ -/* - * This header is for use by exec.c and memory.c ONLY. Do not include it. - * The functions declared here will be removed soon. - */ - -#ifndef QEMU_EXEC_RAMBLOCK_H -#define QEMU_EXEC_RAMBLOCK_H +#ifndef SYSTEM_RAMBLOCK_H +#define SYSTEM_RAMBLOCK_H -#ifndef CONFIG_USER_ONLY -#include "cpu-common.h" +#include "exec/cpu-common.h" #include "qemu/rcu.h" #include "exec/ramlist.h" +#include "system/hostmem.h" + +#define TYPE_RAM_BLOCK_ATTRIBUTES "ram-block-attributes" +OBJECT_DECLARE_SIMPLE_TYPE(RamBlockAttributes, RAM_BLOCK_ATTRIBUTES) struct RAMBlock { struct rcu_head rcu; @@ -43,6 +41,7 @@ struct RAMBlock { int fd; uint64_t fd_offset; int guest_memfd; + RamBlockAttributes *attributes; size_t page_size; /* dirty bitmap used during migration */ unsigned long *bmap; @@ -91,5 +90,44 @@ struct RAMBlock { */ ram_addr_t postcopy_length; }; -#endif + +struct RamBlockAttributes { + Object parent; + + RAMBlock *ram_block; + + /* 1-setting of the bitmap represents ram is populated (shared) */ + unsigned bitmap_size; + unsigned long *bitmap; + + QLIST_HEAD(, RamDiscardListener) rdl_list; +}; + +/* @offset: the offset within the RAMBlock */ +int ram_block_discard_range(RAMBlock *rb, uint64_t offset, size_t length); +/* @offset: the offset within the RAMBlock */ +int ram_block_discard_guest_memfd_range(RAMBlock *rb, uint64_t offset, + size_t length); + +RamBlockAttributes *ram_block_attributes_create(RAMBlock *ram_block); +void ram_block_attributes_destroy(RamBlockAttributes *attr); +int ram_block_attributes_state_change(RamBlockAttributes *attr, uint64_t offset, + uint64_t size, bool to_discard); + +/** + * ram_block_is_pmem: Whether the RAM block is of persistent memory + */ +bool ram_block_is_pmem(RAMBlock *rb); + +static inline bool offset_in_ramblock(RAMBlock *b, ram_addr_t offset) +{ + return b && b->host && (offset < b->used_length); +} + +static inline void *ramblock_ptr(RAMBlock *block, ram_addr_t offset) +{ + assert(offset_in_ramblock(block, offset)); + return (char *)block->host + offset; +} + #endif diff --git a/include/system/replay.h b/include/system/replay.h index 8926d8c..68f91bd 100644 --- a/include/system/replay.h +++ b/include/system/replay.h @@ -11,15 +11,12 @@ #ifndef SYSTEM_REPLAY_H #define SYSTEM_REPLAY_H -#ifdef CONFIG_USER_ONLY -#error Cannot include this header from user emulation -#endif - #include "exec/replay-core.h" #include "qapi/qapi-types-misc.h" #include "qapi/qapi-types-run-state.h" #include "qapi/qapi-types-ui.h" #include "block/aio.h" +#include "qemu/audio.h" /* replay clock kinds */ enum ReplayClockKind { @@ -169,7 +166,7 @@ void replay_net_packet_event(ReplayNetState *rns, unsigned flags, /*! Saves/restores number of played samples of audio out operation. */ void replay_audio_out(size_t *played); /*! Saves/restores recorded samples of audio in operation. */ -void replay_audio_in(size_t *recorded, void *samples, size_t *wpos, size_t size); +void replay_audio_in(size_t *recorded, st_sample *samples, size_t *wpos, size_t size); /* VM state operations */ diff --git a/include/system/runstate.h b/include/system/runstate.h index bffc371..929379a 100644 --- a/include/system/runstate.h +++ b/include/system/runstate.h @@ -12,29 +12,76 @@ bool runstate_needs_reset(void); void runstate_replay_enable(void); typedef void VMChangeStateHandler(void *opaque, bool running, RunState state); +typedef int VMChangeStateHandlerWithRet(void *opaque, bool running, RunState state); +/** + * qemu_add_vm_change_state_handler: + * @cb: the callback to invoke + * @opaque: user data passed to the callback + * + * Register a callback function that is invoked when the vm starts or stops + * running. + * + * Returns: an entry to be freed using qemu_del_vm_change_state_handler() + */ VMChangeStateEntry *qemu_add_vm_change_state_handler(VMChangeStateHandler *cb, void *opaque); +/** + * qemu_add_vm_change_state_handler_prio: + * @cb: the callback to invoke + * @opaque: user data passed to the callback + * @priority: low priorities execute first when the vm runs and the reverse is + * true when the vm stops + * + * Register a callback function that is invoked when the vm starts or stops + * running. + * + * Returns: an entry to be freed using qemu_del_vm_change_state_handler() + */ VMChangeStateEntry *qemu_add_vm_change_state_handler_prio( VMChangeStateHandler *cb, void *opaque, int priority); VMChangeStateEntry * +/** + * qemu_add_vm_change_state_handler_prio_full: + * @cb: the main callback to invoke + * @prepare_cb: a callback to invoke before the main callback + * @cb_ret: the main callback to invoke with return value + * @opaque: user data passed to the callbacks + * @priority: low priorities execute first when the vm runs and the reverse is + * true when the vm stops + * + * Register a main callback function and an optional prepare callback function + * that are invoked when the vm starts or stops running. The main callback and + * the prepare callback are called in two separate phases: First all prepare + * callbacks are called and only then all main callbacks are called. As its + * name suggests, the prepare callback can be used to do some preparatory work + * before invoking the main callback. + * + * Returns: an entry to be freed using qemu_del_vm_change_state_handler() + */ qemu_add_vm_change_state_handler_prio_full(VMChangeStateHandler *cb, VMChangeStateHandler *prepare_cb, + VMChangeStateHandlerWithRet *cb_ret, void *opaque, int priority); VMChangeStateEntry *qdev_add_vm_change_state_handler(DeviceState *dev, VMChangeStateHandler *cb, + VMChangeStateHandlerWithRet *cb_ret, void *opaque); VMChangeStateEntry *qdev_add_vm_change_state_handler_full( - DeviceState *dev, VMChangeStateHandler *cb, - VMChangeStateHandler *prepare_cb, void *opaque); + DeviceState *dev, VMChangeStateHandler *cb, VMChangeStateHandler *prepare_cb, + VMChangeStateHandlerWithRet *cb_ret, void *opaque); void qemu_del_vm_change_state_handler(VMChangeStateEntry *e); /** * vm_state_notify: Notify the state of the VM * * @running: whether the VM is running or not. * @state: the #RunState of the VM. + * + * Return the result of the callback which has return value. + * If no callback has return value, still return 0 and the + * upper layer should not do additional processing. */ -void vm_state_notify(bool running, RunState state); +int vm_state_notify(bool running, RunState state); static inline bool shutdown_caused_by_guest(ShutdownCause cause) { @@ -100,6 +147,7 @@ void qemu_system_vmstop_request(RunState reason); void qemu_system_vmstop_request_prepare(void); bool qemu_vmstop_requested(RunState *r); ShutdownCause qemu_shutdown_requested_get(void); +bool qemu_force_shutdown_requested(void); ShutdownCause qemu_reset_requested_get(void); void qemu_system_killed(int signal, pid_t pid); void qemu_system_reset(ShutdownCause reason); diff --git a/include/system/spdm-socket.h b/include/system/spdm-socket.h index 5d8bd9a..00cb0e9 100644 --- a/include/system/spdm-socket.h +++ b/include/system/spdm-socket.h @@ -51,6 +51,35 @@ uint32_t spdm_socket_rsp(const int socket, uint32_t transport_type, void *rsp, uint32_t rsp_len); /** + * spdm_socket_rsp: Receive a message from an SPDM server + * @socket: socket returned from spdm_socket_connect() + * @transport_type: SPDM_SOCKET_TRANSPORT_TYPE_* macro + * @rsp: response buffer + * @rsp_len: response buffer length + * + * Receives a message from the SPDM server and returns the number of bytes + * received or 0 on failure. This can be used to receive a message from the SPDM + * server without sending anything first. + */ +uint32_t spdm_socket_receive(const int socket, uint32_t transport_type, + void *rsp, uint32_t rsp_len); + +/** + * spdm_socket_rsp: Sends a message to an SPDM server + * @socket: socket returned from spdm_socket_connect() + * @socket_cmd: socket command type (normal/if_recv/if_send etc...) + * @transport_type: SPDM_SOCKET_TRANSPORT_TYPE_* macro + * @req: request buffer + * @req_len: request buffer length + * + * Sends platform data to a SPDM server on socket, returns true on success. + * The response from the server must then be fetched by using + * spdm_socket_receive(). + */ +bool spdm_socket_send(const int socket, uint32_t socket_cmd, + uint32_t transport_type, void *req, uint32_t req_len); + +/** * spdm_socket_close: send a shutdown command to the server * @socket: socket returned from spdm_socket_connect() * @transport_type: SPDM_SOCKET_TRANSPORT_TYPE_* macro @@ -59,16 +88,46 @@ uint32_t spdm_socket_rsp(const int socket, uint32_t transport_type, */ void spdm_socket_close(const int socket, uint32_t transport_type); +/* + * Defines the transport encoding for SPDM, this information shall be passed + * down to the SPDM server, when conforming to the SPDM over Storage standard + * as defined by DSP0286. + */ +typedef struct { + uint8_t security_protocol; /* Must be 0xE8 for SPDM Commands + as per SCSI Primary Commands 5 */ + uint16_t security_protocol_specific; /* Bit[7:2] SPDM Operation + Bit[0:1] Connection ID + per DSP0286 1.0: Section 7.2 */ + uint32_t length; /* Length of the SPDM Message*/ +} QEMU_PACKED StorageSpdmTransportHeader; + #define SPDM_SOCKET_COMMAND_NORMAL 0x0001 +#define SPDM_SOCKET_STORAGE_CMD_IF_SEND 0x0002 +#define SPDM_SOCKET_STORAGE_CMD_IF_RECV 0x0003 +#define SOCKET_SPDM_STORAGE_ACK_STATUS 0x0004 #define SPDM_SOCKET_COMMAND_OOB_ENCAP_KEY_UPDATE 0x8001 #define SPDM_SOCKET_COMMAND_CONTINUE 0xFFFD #define SPDM_SOCKET_COMMAND_SHUTDOWN 0xFFFE #define SPDM_SOCKET_COMMAND_UNKOWN 0xFFFF #define SPDM_SOCKET_COMMAND_TEST 0xDEAD -#define SPDM_SOCKET_TRANSPORT_TYPE_MCTP 0x01 -#define SPDM_SOCKET_TRANSPORT_TYPE_PCI_DOE 0x02 - #define SPDM_SOCKET_MAX_MESSAGE_BUFFER_SIZE 0x1200 +#define SPDM_SOCKET_MAX_MSG_STATUS_LEN 0x02 + +typedef enum SpdmTransportType { + SPDM_SOCKET_TRANSPORT_TYPE_UNSPEC = 0, + SPDM_SOCKET_TRANSPORT_TYPE_MCTP, + SPDM_SOCKET_TRANSPORT_TYPE_PCI_DOE, + SPDM_SOCKET_TRANSPORT_TYPE_SCSI, + SPDM_SOCKET_TRANSPORT_TYPE_NVME, + SPDM_SOCKET_TRANSPORT_TYPE_MAX +} SpdmTransportType; + +extern const PropertyInfo qdev_prop_spdm_trans; + +#define DEFINE_PROP_SPDM_TRANS(_name, _state, _field, _default) \ + DEFINE_PROP_UNSIGNED(_name, _state, _field, _default, \ + qdev_prop_spdm_trans, SpdmTransportType) #endif diff --git a/include/system/system.h b/include/system/system.h index a7effe7..03a2d0e 100644 --- a/include/system/system.h +++ b/include/system/system.h @@ -42,7 +42,6 @@ extern int graphic_height; extern int graphic_depth; extern int display_opengl; extern const char *keyboard_layout; -extern int old_param; extern uint8_t *boot_splash_filedata; extern bool enable_cpu_pm; extern QEMUClockType rtc_clock; diff --git a/include/system/tcg.h b/include/system/tcg.h index 7322964..7622dce 100644 --- a/include/system/tcg.h +++ b/include/system/tcg.h @@ -17,4 +17,12 @@ extern bool tcg_allowed; #define tcg_enabled() 0 #endif +/** + * qemu_tcg_mttcg_enabled: + * Check whether we are running MultiThread TCG or not. + * + * Returns: %true if we are in MTTCG mode %false otherwise. + */ +bool qemu_tcg_mttcg_enabled(void); + #endif diff --git a/include/system/vhost-user-backend.h b/include/system/vhost-user-backend.h index 327b0b8..3184c8e 100644 --- a/include/system/vhost-user-backend.h +++ b/include/system/vhost-user-backend.h @@ -13,7 +13,7 @@ #define QEMU_VHOST_USER_BACKEND_H #include "qom/object.h" -#include "exec/memory.h" +#include "system/memory.h" #include "qemu/option.h" #include "qemu/bitmap.h" #include "hw/virtio/vhost.h" @@ -32,7 +32,7 @@ struct VhostUserBackend { Object parent; char *chr_name; - CharBackend chr; + CharFrontend chr; VhostUserState vhost_user; struct vhost_dev dev; VirtIODevice *vdev; @@ -43,6 +43,6 @@ struct VhostUserBackend { int vhost_user_backend_dev_init(VhostUserBackend *b, VirtIODevice *vdev, unsigned nvqs, Error **errp); void vhost_user_backend_start(VhostUserBackend *b); -void vhost_user_backend_stop(VhostUserBackend *b); +int vhost_user_backend_stop(VhostUserBackend *b); #endif diff --git a/include/system/whpx.h b/include/system/whpx.h index 00ff409..00f6a3e 100644 --- a/include/system/whpx.h +++ b/include/system/whpx.h @@ -16,19 +16,20 @@ #define QEMU_WHPX_H #ifdef COMPILING_PER_TARGET +# ifdef CONFIG_WHPX +# define CONFIG_WHPX_IS_POSSIBLE +# endif /* !CONFIG_WHPX */ +#else +# define CONFIG_WHPX_IS_POSSIBLE +#endif /* COMPILING_PER_TARGET */ -#ifdef CONFIG_WHPX - -int whpx_enabled(void); +#ifdef CONFIG_WHPX_IS_POSSIBLE +extern bool whpx_allowed; +#define whpx_enabled() (whpx_allowed) bool whpx_apic_in_platform(void); - -#else /* CONFIG_WHPX */ - -#define whpx_enabled() (0) +#else /* !CONFIG_WHPX_IS_POSSIBLE */ +#define whpx_enabled() 0 #define whpx_apic_in_platform() (0) - -#endif /* CONFIG_WHPX */ - -#endif /* COMPILING_PER_TARGET */ +#endif /* !CONFIG_WHPX_IS_POSSIBLE */ #endif /* QEMU_WHPX_H */ diff --git a/include/system/xen-mapcache.h b/include/system/xen-mapcache.h index b68f196..bb454a7 100644 --- a/include/system/xen-mapcache.h +++ b/include/system/xen-mapcache.h @@ -14,8 +14,6 @@ typedef hwaddr (*phys_offset_to_gaddr_t)(hwaddr phys_offset, ram_addr_t size); -#ifdef CONFIG_XEN_IS_POSSIBLE - void xen_map_cache_init(phys_offset_to_gaddr_t f, void *opaque); uint8_t *xen_map_cache(MemoryRegion *mr, hwaddr phys_addr, hwaddr size, @@ -28,44 +26,5 @@ void xen_invalidate_map_cache(void); uint8_t *xen_replace_cache_entry(hwaddr old_phys_addr, hwaddr new_phys_addr, hwaddr size); -#else - -static inline void xen_map_cache_init(phys_offset_to_gaddr_t f, - void *opaque) -{ -} - -static inline uint8_t *xen_map_cache(MemoryRegion *mr, - hwaddr phys_addr, - hwaddr size, - ram_addr_t ram_addr_offset, - uint8_t lock, - bool dma, - bool is_write) -{ - abort(); -} - -static inline ram_addr_t xen_ram_addr_from_mapcache(void *ptr) -{ - abort(); -} - -static inline void xen_invalidate_map_cache_entry(uint8_t *buffer) -{ -} - -static inline void xen_invalidate_map_cache(void) -{ -} - -static inline uint8_t *xen_replace_cache_entry(hwaddr old_phys_addr, - hwaddr new_phys_addr, - hwaddr size) -{ - abort(); -} - -#endif #endif /* XEN_MAPCACHE_H */ diff --git a/include/system/xen.h b/include/system/xen.h index 990c19a..c2f283d 100644 --- a/include/system/xen.h +++ b/include/system/xen.h @@ -10,10 +10,6 @@ #ifndef SYSTEM_XEN_H #define SYSTEM_XEN_H -#ifdef CONFIG_USER_ONLY -#error Cannot include system/xen.h from user emulation -#endif - #include "exec/cpu-common.h" #ifdef COMPILING_PER_TARGET @@ -25,30 +21,15 @@ #endif /* COMPILING_PER_TARGET */ #ifdef CONFIG_XEN_IS_POSSIBLE - extern bool xen_allowed; - #define xen_enabled() (xen_allowed) - -void xen_hvm_modified_memory(ram_addr_t start, ram_addr_t length); -void xen_ram_alloc(ram_addr_t ram_addr, ram_addr_t size, - struct MemoryRegion *mr, Error **errp); - #else /* !CONFIG_XEN_IS_POSSIBLE */ - #define xen_enabled() 0 -static inline void xen_hvm_modified_memory(ram_addr_t start, ram_addr_t length) -{ - /* nothing */ -} -static inline void xen_ram_alloc(ram_addr_t ram_addr, ram_addr_t size, - MemoryRegion *mr, Error **errp) -{ - g_assert_not_reached(); -} - #endif /* CONFIG_XEN_IS_POSSIBLE */ +void xen_hvm_modified_memory(ram_addr_t start, ram_addr_t length); +void xen_ram_alloc(ram_addr_t ram_addr, ram_addr_t size, + struct MemoryRegion *mr, Error **errp); bool xen_mr_is_memory(MemoryRegion *mr); bool xen_mr_is_grants(MemoryRegion *mr); #endif diff --git a/include/tcg/helper-info.h b/include/tcg/helper-info.h index 909fe73..49a27e4 100644 --- a/include/tcg/helper-info.h +++ b/include/tcg/helper-info.h @@ -10,7 +10,19 @@ #define TCG_HELPER_INFO_H #ifdef CONFIG_TCG_INTERPRETER +/* + * MacOSX 15 uses an old version of libffi which contains + * #if FFI_GO_CLOSURES + * but does not define that in <ffitarget.h>, included from <ffi.h>. + * This was fixed upstream with + * https://github.com/libffi/libffi/commit/c23e9a1c + * We don't care about go closures one way or the other; + * just suppress the warning. + */ +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wundef" #include <ffi.h> +#pragma GCC diagnostic pop #endif #include "tcg-target-reg-bits.h" diff --git a/include/tcg/insn-start-words.h b/include/tcg/insn-start-words.h index 50c18bd..c52aec5 100644 --- a/include/tcg/insn-start-words.h +++ b/include/tcg/insn-start-words.h @@ -1,17 +1,12 @@ /* SPDX-License-Identifier: MIT */ /* - * Define TARGET_INSN_START_WORDS + * Define INSN_START_WORDS * Copyright (c) 2008 Fabrice Bellard */ -#ifndef TARGET_INSN_START_WORDS +#ifndef TCG_INSN_START_WORDS +#define TCG_INSN_START_WORDS -#include "cpu.h" +#define INSN_START_WORDS 3 -#ifndef TARGET_INSN_START_EXTRA_WORDS -# define TARGET_INSN_START_WORDS 1 -#else -# define TARGET_INSN_START_WORDS (1 + TARGET_INSN_START_EXTRA_WORDS) -#endif - -#endif /* TARGET_INSN_START_WORDS */ +#endif /* TCG_INSN_START_WORDS */ diff --git a/include/tcg/startup.h b/include/tcg/startup.h index f713057..95f574a 100644 --- a/include/tcg/startup.h +++ b/include/tcg/startup.h @@ -29,12 +29,12 @@ * tcg_init: Initialize the TCG runtime * @tb_size: translation buffer size * @splitwx: use separate rw and rx mappings - * @max_cpus: number of vcpus in system mode + * @max_threads: number of vcpu threads in system mode * * Allocate and initialize TCG resources, especially the JIT buffer. - * In user-only mode, @max_cpus is unused. + * In user-only mode, @max_threads is unused. */ -void tcg_init(size_t tb_size, int splitwx, unsigned max_cpus); +void tcg_init(size_t tb_size, int splitwx, unsigned max_threads); /** * tcg_register_thread: Register this thread with the TCG runtime diff --git a/include/tcg/tcg-op-common.h b/include/tcg/tcg-op-common.h index 009e277..f752ef4 100644 --- a/include/tcg/tcg-op-common.h +++ b/include/tcg/tcg-op-common.h @@ -14,6 +14,7 @@ TCGv_i32 tcg_constant_i32(int32_t val); TCGv_i64 tcg_constant_i64(int64_t val); +TCGv_vaddr tcg_constant_vaddr(uintptr_t val); TCGv_vec tcg_constant_vec(TCGType type, unsigned vece, int64_t val); TCGv_vec tcg_constant_vec_matching(TCGv_vec match, unsigned vece, int64_t val); @@ -135,6 +136,8 @@ void tcg_gen_add2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 al, TCGv_i32 ah, TCGv_i32 bl, TCGv_i32 bh); void tcg_gen_sub2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 al, TCGv_i32 ah, TCGv_i32 bl, TCGv_i32 bh); +void tcg_gen_addcio_i32(TCGv_i32 r, TCGv_i32 co, + TCGv_i32 a, TCGv_i32 b, TCGv_i32 ci); void tcg_gen_mulu2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 arg1, TCGv_i32 arg2); void tcg_gen_muls2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 arg1, TCGv_i32 arg2); void tcg_gen_mulsu2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 arg1, TCGv_i32 arg2); @@ -238,6 +241,8 @@ void tcg_gen_add2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 al, TCGv_i64 ah, TCGv_i64 bl, TCGv_i64 bh); void tcg_gen_sub2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 al, TCGv_i64 ah, TCGv_i64 bl, TCGv_i64 bh); +void tcg_gen_addcio_i64(TCGv_i64 r, TCGv_i64 co, + TCGv_i64 a, TCGv_i64 b, TCGv_i64 ci); void tcg_gen_mulu2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 arg1, TCGv_i64 arg2); void tcg_gen_muls2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 arg1, TCGv_i64 arg2); void tcg_gen_mulsu2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 arg1, TCGv_i64 arg2); @@ -339,6 +344,8 @@ void tcg_gen_atomic_xchg_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, TCGArg, MemOp, TCGType); void tcg_gen_atomic_xchg_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, TCGArg, MemOp, TCGType); +void tcg_gen_atomic_xchg_i128_chk(TCGv_i128, TCGTemp *, TCGv_i128, + TCGArg, MemOp, TCGType); void tcg_gen_atomic_fetch_add_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, TCGArg, MemOp, TCGType); @@ -406,6 +413,11 @@ void tcg_gen_atomic_umax_fetch_i32_chk(TCGv_i32, TCGTemp *, TCGv_i32, void tcg_gen_atomic_umax_fetch_i64_chk(TCGv_i64, TCGTemp *, TCGv_i64, TCGArg, MemOp, TCGType); +void tcg_gen_atomic_fetch_and_i128_chk(TCGv_i128, TCGTemp *, TCGv_i128, + TCGArg, MemOp, TCGType); +void tcg_gen_atomic_fetch_or_i128_chk(TCGv_i128, TCGTemp *, TCGv_i128, + TCGArg, MemOp, TCGType); + /* Vector ops */ void tcg_gen_mov_vec(TCGv_vec, TCGv_vec); diff --git a/include/tcg/tcg-op-gvec-common.h b/include/tcg/tcg-op-gvec-common.h index 65553f5..ea0c87f 100644 --- a/include/tcg/tcg-op-gvec-common.h +++ b/include/tcg/tcg-op-gvec-common.h @@ -227,25 +227,66 @@ typedef struct { bool prefer_i64; } GVecGen4i; +/* Expand (dbase+dofs) = op(abase+aofs), length @oprsz, clearing to @maxsz. */ +void tcg_gen_gvec_2_var(TCGv_ptr dbase, uint32_t dofs, + TCGv_ptr abase, uint32_t aofs, + uint32_t oprsz, uint32_t maxsz, const GVecGen2 *op); +/* Similarly, expand (env+dofs) = op(env+aofs). */ void tcg_gen_gvec_2(uint32_t dofs, uint32_t aofs, - uint32_t oprsz, uint32_t maxsz, const GVecGen2 *); + uint32_t oprsz, uint32_t maxsz, const GVecGen2 *op); +/* Similarly, expand (env+dofs) = op(env+aofs, c). */ void tcg_gen_gvec_2i(uint32_t dofs, uint32_t aofs, uint32_t oprsz, - uint32_t maxsz, int64_t c, const GVecGen2i *); + uint32_t maxsz, int64_t c, const GVecGen2i *op); +/* Similarly, expand (env+dofs) = op(env+aofs, s). */ void tcg_gen_gvec_2s(uint32_t dofs, uint32_t aofs, uint32_t oprsz, - uint32_t maxsz, TCGv_i64 c, const GVecGen2s *); + uint32_t maxsz, TCGv_i64 c, const GVecGen2s *op); + +/* + * Expand (dbase+dofs) = op(abase+aofs, bbase+bofs), + * length @oprsz, clearing to @maxsz. + */ +void tcg_gen_gvec_3_var(TCGv_ptr dbase, uint32_t dofs, + TCGv_ptr abase, uint32_t aofs, + TCGv_ptr bbase, uint32_t bofs, + uint32_t oprsz, uint32_t maxsz, const GVecGen3 *op); +/* Similarly, expand (env+dofs) = op(env+aofs, env+bofs). */ void tcg_gen_gvec_3(uint32_t dofs, uint32_t aofs, uint32_t bofs, - uint32_t oprsz, uint32_t maxsz, const GVecGen3 *); + uint32_t oprsz, uint32_t maxsz, const GVecGen3 *op); + +/* + * Depending on op->load_dest and op->write_aofs, expand + * (env+dofs) = op(env+aofs, env+bofs, c) + * or + * (env+dofs) = op(env+dofs, env+aofs, env+bofs, c) + * or + * (env+dofs), (env+aofs) = op(env+aofs, env+bofs, c) + * or + * (env+dofs), (env+aofs) = op(env+dofs, env+aofs, env+bofs, c) + */ void tcg_gen_gvec_3i(uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t oprsz, uint32_t maxsz, int64_t c, - const GVecGen3i *); + const GVecGen3i *op); + +/* + * Depending on op->write_aofs, expand + * (env+dofs) = op(env+aofs, env+bofs, env+cofs) + * or + * (env+dofs), (env+aofs) = op(env+aofs, env+bofs, env+cofs) + */ void tcg_gen_gvec_4(uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t cofs, uint32_t oprsz, uint32_t maxsz, const GVecGen4 *); + +/* Expand (env+dofs) = op(env+aofs, env+bofs, env+cofs, c). */ void tcg_gen_gvec_4i(uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t cofs, uint32_t oprsz, uint32_t maxsz, int64_t c, const GVecGen4i *); /* Expand a specific vector operation. */ +void tcg_gen_gvec_mov_var(unsigned vece, TCGv_ptr dbase, uint32_t dofs, + TCGv_ptr abase, uint32_t aofs, + uint32_t oprsz, uint32_t maxsz); + void tcg_gen_gvec_mov(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t oprsz, uint32_t maxsz); void tcg_gen_gvec_not(unsigned vece, uint32_t dofs, uint32_t aofs, @@ -255,6 +296,15 @@ void tcg_gen_gvec_neg(unsigned vece, uint32_t dofs, uint32_t aofs, void tcg_gen_gvec_abs(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_add_var(unsigned vece, TCGv_ptr dbase, uint32_t dofs, + TCGv_ptr abase, uint32_t aofs, + TCGv_ptr bbase, uint32_t bofs, + uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_sub_var(unsigned vece, TCGv_ptr dbase, uint32_t dofs, + TCGv_ptr abase, uint32_t aofs, + TCGv_ptr bbase, uint32_t bofs, + uint32_t oprsz, uint32_t maxsz); + void tcg_gen_gvec_add(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t oprsz, uint32_t maxsz); void tcg_gen_gvec_sub(unsigned vece, uint32_t dofs, uint32_t aofs, @@ -336,6 +386,9 @@ void tcg_gen_gvec_dup_i32(unsigned vece, uint32_t dofs, uint32_t s, void tcg_gen_gvec_dup_i64(unsigned vece, uint32_t dofs, uint32_t s, uint32_t m, TCGv_i64); +void tcg_gen_gvec_dup_imm_var(unsigned vece, TCGv_ptr dbase, uint32_t dofs, + uint32_t oprsz, uint32_t maxsz, uint64_t imm); + void tcg_gen_gvec_shli(unsigned vece, uint32_t dofs, uint32_t aofs, int64_t shift, uint32_t oprsz, uint32_t maxsz); void tcg_gen_gvec_shri(unsigned vece, uint32_t dofs, uint32_t aofs, diff --git a/include/tcg/tcg-op.h b/include/tcg/tcg-op.h index a028505..232733c 100644 --- a/include/tcg/tcg-op.h +++ b/include/tcg/tcg-op.h @@ -9,6 +9,8 @@ #define TCG_TCG_OP_H #include "tcg/tcg-op-common.h" +#include "tcg/insn-start-words.h" +#include "exec/target_long.h" #ifndef TARGET_LONG_BITS #error must include QEMU headers @@ -22,24 +24,34 @@ # error #endif -#ifndef TARGET_INSN_START_EXTRA_WORDS +#if INSN_START_WORDS != 3 +# error Mismatch with insn-start-words.h +#endif + +#if TARGET_INSN_START_EXTRA_WORDS == 0 static inline void tcg_gen_insn_start(target_ulong pc) { - TCGOp *op = tcg_emit_op(INDEX_op_insn_start, 64 / TCG_TARGET_REG_BITS); + TCGOp *op = tcg_emit_op(INDEX_op_insn_start, + INSN_START_WORDS * 64 / TCG_TARGET_REG_BITS); tcg_set_insn_start_param(op, 0, pc); + tcg_set_insn_start_param(op, 1, 0); + tcg_set_insn_start_param(op, 2, 0); } #elif TARGET_INSN_START_EXTRA_WORDS == 1 static inline void tcg_gen_insn_start(target_ulong pc, target_ulong a1) { - TCGOp *op = tcg_emit_op(INDEX_op_insn_start, 2 * 64 / TCG_TARGET_REG_BITS); + TCGOp *op = tcg_emit_op(INDEX_op_insn_start, + INSN_START_WORDS * 64 / TCG_TARGET_REG_BITS); tcg_set_insn_start_param(op, 0, pc); tcg_set_insn_start_param(op, 1, a1); + tcg_set_insn_start_param(op, 2, 0); } #elif TARGET_INSN_START_EXTRA_WORDS == 2 static inline void tcg_gen_insn_start(target_ulong pc, target_ulong a1, target_ulong a2) { - TCGOp *op = tcg_emit_op(INDEX_op_insn_start, 3 * 64 / TCG_TARGET_REG_BITS); + TCGOp *op = tcg_emit_op(INDEX_op_insn_start, + INSN_START_WORDS * 64 / TCG_TARGET_REG_BITS); tcg_set_insn_start_param(op, 0, pc); tcg_set_insn_start_param(op, 1, a1); tcg_set_insn_start_param(op, 2, a2); @@ -122,13 +134,16 @@ DEF_ATOMIC3(tcg_gen_nonatomic_cmpxchg, i128) DEF_ATOMIC2(tcg_gen_atomic_xchg, i32) DEF_ATOMIC2(tcg_gen_atomic_xchg, i64) +DEF_ATOMIC2(tcg_gen_atomic_xchg, i128) DEF_ATOMIC2(tcg_gen_atomic_fetch_add, i32) DEF_ATOMIC2(tcg_gen_atomic_fetch_add, i64) DEF_ATOMIC2(tcg_gen_atomic_fetch_and, i32) DEF_ATOMIC2(tcg_gen_atomic_fetch_and, i64) +DEF_ATOMIC2(tcg_gen_atomic_fetch_and, i128) DEF_ATOMIC2(tcg_gen_atomic_fetch_or, i32) DEF_ATOMIC2(tcg_gen_atomic_fetch_or, i64) +DEF_ATOMIC2(tcg_gen_atomic_fetch_or, i128) DEF_ATOMIC2(tcg_gen_atomic_fetch_xor, i32) DEF_ATOMIC2(tcg_gen_atomic_fetch_xor, i64) DEF_ATOMIC2(tcg_gen_atomic_fetch_smin, i32) @@ -252,6 +267,7 @@ DEF_ATOMIC2(tcg_gen_atomic_umax_fetch, i64) #define tcg_gen_movcond_tl tcg_gen_movcond_i64 #define tcg_gen_add2_tl tcg_gen_add2_i64 #define tcg_gen_sub2_tl tcg_gen_sub2_i64 +#define tcg_gen_addcio_tl tcg_gen_addcio_i64 #define tcg_gen_mulu2_tl tcg_gen_mulu2_i64 #define tcg_gen_muls2_tl tcg_gen_muls2_i64 #define tcg_gen_mulsu2_tl tcg_gen_mulsu2_i64 @@ -370,6 +386,7 @@ DEF_ATOMIC2(tcg_gen_atomic_umax_fetch, i64) #define tcg_gen_movcond_tl tcg_gen_movcond_i32 #define tcg_gen_add2_tl tcg_gen_add2_i32 #define tcg_gen_sub2_tl tcg_gen_sub2_i32 +#define tcg_gen_addcio_tl tcg_gen_addcio_i32 #define tcg_gen_mulu2_tl tcg_gen_mulu2_i32 #define tcg_gen_muls2_tl tcg_gen_muls2_i32 #define tcg_gen_mulsu2_tl tcg_gen_mulsu2_i32 diff --git a/include/tcg/tcg-opc.h b/include/tcg/tcg-opc.h index 5bf78b0..e988edd 100644 --- a/include/tcg/tcg-opc.h +++ b/include/tcg/tcg-opc.h @@ -34,152 +34,87 @@ DEF(set_label, 0, 0, 1, TCG_OPF_BB_END | TCG_OPF_NOT_PRESENT) DEF(call, 0, 0, 3, TCG_OPF_CALL_CLOBBER | TCG_OPF_NOT_PRESENT) DEF(br, 0, 0, 1, TCG_OPF_BB_END | TCG_OPF_NOT_PRESENT) +DEF(brcond, 0, 2, 2, TCG_OPF_BB_END | TCG_OPF_COND_BRANCH | TCG_OPF_INT) DEF(mb, 0, 0, 1, TCG_OPF_NOT_PRESENT) -DEF(mov_i32, 1, 1, 0, TCG_OPF_NOT_PRESENT) -DEF(setcond_i32, 1, 2, 1, 0) -DEF(negsetcond_i32, 1, 2, 1, 0) -DEF(movcond_i32, 1, 4, 1, 0) -/* load/store */ -DEF(ld8u_i32, 1, 1, 1, 0) -DEF(ld8s_i32, 1, 1, 1, 0) -DEF(ld16u_i32, 1, 1, 1, 0) -DEF(ld16s_i32, 1, 1, 1, 0) -DEF(ld_i32, 1, 1, 1, 0) -DEF(st8_i32, 0, 2, 1, 0) -DEF(st16_i32, 0, 2, 1, 0) -DEF(st_i32, 0, 2, 1, 0) -/* arith */ -DEF(add_i32, 1, 2, 0, 0) -DEF(sub_i32, 1, 2, 0, 0) -DEF(mul_i32, 1, 2, 0, 0) -DEF(div_i32, 1, 2, 0, 0) -DEF(divu_i32, 1, 2, 0, 0) -DEF(rem_i32, 1, 2, 0, 0) -DEF(remu_i32, 1, 2, 0, 0) -DEF(div2_i32, 2, 3, 0, 0) -DEF(divu2_i32, 2, 3, 0, 0) -DEF(and_i32, 1, 2, 0, 0) -DEF(or_i32, 1, 2, 0, 0) -DEF(xor_i32, 1, 2, 0, 0) -/* shifts/rotates */ -DEF(shl_i32, 1, 2, 0, 0) -DEF(shr_i32, 1, 2, 0, 0) -DEF(sar_i32, 1, 2, 0, 0) -DEF(rotl_i32, 1, 2, 0, 0) -DEF(rotr_i32, 1, 2, 0, 0) -DEF(deposit_i32, 1, 2, 2, 0) -DEF(extract_i32, 1, 1, 2, 0) -DEF(sextract_i32, 1, 1, 2, 0) -DEF(extract2_i32, 1, 2, 1, 0) +DEF(mov, 1, 1, 0, TCG_OPF_INT | TCG_OPF_NOT_PRESENT) + +DEF(add, 1, 2, 0, TCG_OPF_INT) +DEF(and, 1, 2, 0, TCG_OPF_INT) +DEF(andc, 1, 2, 0, TCG_OPF_INT) +DEF(bswap16, 1, 1, 1, TCG_OPF_INT) +DEF(bswap32, 1, 1, 1, TCG_OPF_INT) +DEF(bswap64, 1, 1, 1, TCG_OPF_INT) +DEF(clz, 1, 2, 0, TCG_OPF_INT) +DEF(ctpop, 1, 1, 0, TCG_OPF_INT) +DEF(ctz, 1, 2, 0, TCG_OPF_INT) +DEF(deposit, 1, 2, 2, TCG_OPF_INT) +DEF(divs, 1, 2, 0, TCG_OPF_INT) +DEF(divs2, 2, 3, 0, TCG_OPF_INT) +DEF(divu, 1, 2, 0, TCG_OPF_INT) +DEF(divu2, 2, 3, 0, TCG_OPF_INT) +DEF(eqv, 1, 2, 0, TCG_OPF_INT) +DEF(extract, 1, 1, 2, TCG_OPF_INT) +DEF(extract2, 1, 2, 1, TCG_OPF_INT) +DEF(ld8u, 1, 1, 1, TCG_OPF_INT) +DEF(ld8s, 1, 1, 1, TCG_OPF_INT) +DEF(ld16u, 1, 1, 1, TCG_OPF_INT) +DEF(ld16s, 1, 1, 1, TCG_OPF_INT) +DEF(ld32u, 1, 1, 1, TCG_OPF_INT) +DEF(ld32s, 1, 1, 1, TCG_OPF_INT) +DEF(ld, 1, 1, 1, TCG_OPF_INT) +DEF(movcond, 1, 4, 1, TCG_OPF_INT) +DEF(mul, 1, 2, 0, TCG_OPF_INT) +DEF(muls2, 2, 2, 0, TCG_OPF_INT) +DEF(mulsh, 1, 2, 0, TCG_OPF_INT) +DEF(mulu2, 2, 2, 0, TCG_OPF_INT) +DEF(muluh, 1, 2, 0, TCG_OPF_INT) +DEF(nand, 1, 2, 0, TCG_OPF_INT) +DEF(neg, 1, 1, 0, TCG_OPF_INT) +DEF(negsetcond, 1, 2, 1, TCG_OPF_INT) +DEF(nor, 1, 2, 0, TCG_OPF_INT) +DEF(not, 1, 1, 0, TCG_OPF_INT) +DEF(or, 1, 2, 0, TCG_OPF_INT) +DEF(orc, 1, 2, 0, TCG_OPF_INT) +DEF(rems, 1, 2, 0, TCG_OPF_INT) +DEF(remu, 1, 2, 0, TCG_OPF_INT) +DEF(rotl, 1, 2, 0, TCG_OPF_INT) +DEF(rotr, 1, 2, 0, TCG_OPF_INT) +DEF(sar, 1, 2, 0, TCG_OPF_INT) +DEF(setcond, 1, 2, 1, TCG_OPF_INT) +DEF(sextract, 1, 1, 2, TCG_OPF_INT) +DEF(shl, 1, 2, 0, TCG_OPF_INT) +DEF(shr, 1, 2, 0, TCG_OPF_INT) +DEF(st8, 0, 2, 1, TCG_OPF_INT) +DEF(st16, 0, 2, 1, TCG_OPF_INT) +DEF(st32, 0, 2, 1, TCG_OPF_INT) +DEF(st, 0, 2, 1, TCG_OPF_INT) +DEF(sub, 1, 2, 0, TCG_OPF_INT) +DEF(xor, 1, 2, 0, TCG_OPF_INT) + +DEF(addco, 1, 2, 0, TCG_OPF_INT | TCG_OPF_CARRY_OUT) +DEF(addc1o, 1, 2, 0, TCG_OPF_INT | TCG_OPF_CARRY_OUT) +DEF(addci, 1, 2, 0, TCG_OPF_INT | TCG_OPF_CARRY_IN) +DEF(addcio, 1, 2, 0, TCG_OPF_INT | TCG_OPF_CARRY_IN | TCG_OPF_CARRY_OUT) + +DEF(subbo, 1, 2, 0, TCG_OPF_INT | TCG_OPF_CARRY_OUT) +DEF(subb1o, 1, 2, 0, TCG_OPF_INT | TCG_OPF_CARRY_OUT) +DEF(subbi, 1, 2, 0, TCG_OPF_INT | TCG_OPF_CARRY_IN) +DEF(subbio, 1, 2, 0, TCG_OPF_INT | TCG_OPF_CARRY_IN | TCG_OPF_CARRY_OUT) -DEF(brcond_i32, 0, 2, 2, TCG_OPF_BB_END | TCG_OPF_COND_BRANCH) - -DEF(add2_i32, 2, 4, 0, 0) -DEF(sub2_i32, 2, 4, 0, 0) -DEF(mulu2_i32, 2, 2, 0, 0) -DEF(muls2_i32, 2, 2, 0, 0) -DEF(muluh_i32, 1, 2, 0, 0) -DEF(mulsh_i32, 1, 2, 0, 0) DEF(brcond2_i32, 0, 4, 2, TCG_OPF_BB_END | TCG_OPF_COND_BRANCH) DEF(setcond2_i32, 1, 4, 1, 0) -DEF(ext8s_i32, 1, 1, 0, 0) -DEF(ext16s_i32, 1, 1, 0, 0) -DEF(ext8u_i32, 1, 1, 0, 0) -DEF(ext16u_i32, 1, 1, 0, 0) -DEF(bswap16_i32, 1, 1, 1, 0) -DEF(bswap32_i32, 1, 1, 1, 0) -DEF(not_i32, 1, 1, 0, 0) -DEF(neg_i32, 1, 1, 0, 0) -DEF(andc_i32, 1, 2, 0, 0) -DEF(orc_i32, 1, 2, 0, 0) -DEF(eqv_i32, 1, 2, 0, 0) -DEF(nand_i32, 1, 2, 0, 0) -DEF(nor_i32, 1, 2, 0, 0) -DEF(clz_i32, 1, 2, 0, 0) -DEF(ctz_i32, 1, 2, 0, 0) -DEF(ctpop_i32, 1, 1, 0, 0) - -DEF(mov_i64, 1, 1, 0, TCG_OPF_NOT_PRESENT) -DEF(setcond_i64, 1, 2, 1, 0) -DEF(negsetcond_i64, 1, 2, 1, 0) -DEF(movcond_i64, 1, 4, 1, 0) -/* load/store */ -DEF(ld8u_i64, 1, 1, 1, 0) -DEF(ld8s_i64, 1, 1, 1, 0) -DEF(ld16u_i64, 1, 1, 1, 0) -DEF(ld16s_i64, 1, 1, 1, 0) -DEF(ld32u_i64, 1, 1, 1, 0) -DEF(ld32s_i64, 1, 1, 1, 0) -DEF(ld_i64, 1, 1, 1, 0) -DEF(st8_i64, 0, 2, 1, 0) -DEF(st16_i64, 0, 2, 1, 0) -DEF(st32_i64, 0, 2, 1, 0) -DEF(st_i64, 0, 2, 1, 0) -/* arith */ -DEF(add_i64, 1, 2, 0, 0) -DEF(sub_i64, 1, 2, 0, 0) -DEF(mul_i64, 1, 2, 0, 0) -DEF(div_i64, 1, 2, 0, 0) -DEF(divu_i64, 1, 2, 0, 0) -DEF(rem_i64, 1, 2, 0, 0) -DEF(remu_i64, 1, 2, 0, 0) -DEF(div2_i64, 2, 3, 0, 0) -DEF(divu2_i64, 2, 3, 0, 0) -DEF(and_i64, 1, 2, 0, 0) -DEF(or_i64, 1, 2, 0, 0) -DEF(xor_i64, 1, 2, 0, 0) -/* shifts/rotates */ -DEF(shl_i64, 1, 2, 0, 0) -DEF(shr_i64, 1, 2, 0, 0) -DEF(sar_i64, 1, 2, 0, 0) -DEF(rotl_i64, 1, 2, 0, 0) -DEF(rotr_i64, 1, 2, 0, 0) -DEF(deposit_i64, 1, 2, 2, 0) -DEF(extract_i64, 1, 1, 2, 0) -DEF(sextract_i64, 1, 1, 2, 0) -DEF(extract2_i64, 1, 2, 1, 0) - /* size changing ops */ DEF(ext_i32_i64, 1, 1, 0, 0) DEF(extu_i32_i64, 1, 1, 0, 0) DEF(extrl_i64_i32, 1, 1, 0, 0) DEF(extrh_i64_i32, 1, 1, 0, 0) -DEF(brcond_i64, 0, 2, 2, TCG_OPF_BB_END | TCG_OPF_COND_BRANCH) -DEF(ext8s_i64, 1, 1, 0, 0) -DEF(ext16s_i64, 1, 1, 0, 0) -DEF(ext32s_i64, 1, 1, 0, 0) -DEF(ext8u_i64, 1, 1, 0, 0) -DEF(ext16u_i64, 1, 1, 0, 0) -DEF(ext32u_i64, 1, 1, 0, 0) -DEF(bswap16_i64, 1, 1, 1, 0) -DEF(bswap32_i64, 1, 1, 1, 0) -DEF(bswap64_i64, 1, 1, 1, 0) -DEF(not_i64, 1, 1, 0, 0) -DEF(neg_i64, 1, 1, 0, 0) -DEF(andc_i64, 1, 2, 0, 0) -DEF(orc_i64, 1, 2, 0, 0) -DEF(eqv_i64, 1, 2, 0, 0) -DEF(nand_i64, 1, 2, 0, 0) -DEF(nor_i64, 1, 2, 0, 0) -DEF(clz_i64, 1, 2, 0, 0) -DEF(ctz_i64, 1, 2, 0, 0) -DEF(ctpop_i64, 1, 1, 0, 0) - -DEF(add2_i64, 2, 4, 0, 0) -DEF(sub2_i64, 2, 4, 0, 0) -DEF(mulu2_i64, 2, 2, 0, 0) -DEF(muls2_i64, 2, 2, 0, 0) -DEF(muluh_i64, 1, 2, 0, 0) -DEF(mulsh_i64, 1, 2, 0, 0) - #define DATA64_ARGS (TCG_TARGET_REG_BITS == 64 ? 1 : 2) -/* There are tcg_ctx->insn_start_words here, not just one. */ -DEF(insn_start, 0, 0, DATA64_ARGS, TCG_OPF_NOT_PRESENT) +DEF(insn_start, 0, 0, DATA64_ARGS * INSN_START_WORDS, TCG_OPF_NOT_PRESENT) DEF(exit_tb, 0, 0, 1, TCG_OPF_BB_EXIT | TCG_OPF_BB_END | TCG_OPF_NOT_PRESENT) DEF(goto_tb, 0, 0, 1, TCG_OPF_BB_EXIT | TCG_OPF_BB_END | TCG_OPF_NOT_PRESENT) @@ -188,22 +123,10 @@ DEF(goto_ptr, 0, 1, 0, TCG_OPF_BB_EXIT | TCG_OPF_BB_END) DEF(plugin_cb, 0, 0, 1, TCG_OPF_NOT_PRESENT) DEF(plugin_mem_cb, 0, 1, 1, TCG_OPF_NOT_PRESENT) -DEF(qemu_ld_i32, 1, 1, 1, - TCG_OPF_CALL_CLOBBER | TCG_OPF_SIDE_EFFECTS) -DEF(qemu_st_i32, 0, 1 + 1, 1, - TCG_OPF_CALL_CLOBBER | TCG_OPF_SIDE_EFFECTS) -DEF(qemu_ld_i64, DATA64_ARGS, 1, 1, - TCG_OPF_CALL_CLOBBER | TCG_OPF_SIDE_EFFECTS) -DEF(qemu_st_i64, 0, DATA64_ARGS + 1, 1, - TCG_OPF_CALL_CLOBBER | TCG_OPF_SIDE_EFFECTS) - -/* Only used by i386 to cope with stupid register constraints. */ -DEF(qemu_st8_i32, 0, 1 + 1, 1, - TCG_OPF_CALL_CLOBBER | TCG_OPF_SIDE_EFFECTS) - -/* Only for 64-bit hosts at the moment. */ -DEF(qemu_ld_i128, 2, 1, 1, TCG_OPF_CALL_CLOBBER | TCG_OPF_SIDE_EFFECTS) -DEF(qemu_st_i128, 0, 3, 1, TCG_OPF_CALL_CLOBBER | TCG_OPF_SIDE_EFFECTS) +DEF(qemu_ld, 1, 1, 1, TCG_OPF_CALL_CLOBBER | TCG_OPF_SIDE_EFFECTS | TCG_OPF_INT) +DEF(qemu_st, 0, 2, 1, TCG_OPF_CALL_CLOBBER | TCG_OPF_SIDE_EFFECTS | TCG_OPF_INT) +DEF(qemu_ld2, 2, 1, 1, TCG_OPF_CALL_CLOBBER | TCG_OPF_SIDE_EFFECTS | TCG_OPF_INT) +DEF(qemu_st2, 0, 3, 1, TCG_OPF_CALL_CLOBBER | TCG_OPF_SIDE_EFFECTS | TCG_OPF_INT) /* Host vector support. */ diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h index 84d9950..a6d9aa5 100644 --- a/include/tcg/tcg.h +++ b/include/tcg/tcg.h @@ -34,6 +34,7 @@ #include "tcg-target-reg-bits.h" #include "tcg-target.h" #include "tcg/tcg-cond.h" +#include "tcg/insn-start-words.h" #include "tcg/debug-assert.h" /* XXX: make safe guess about sizes */ @@ -188,6 +189,7 @@ typedef tcg_target_ulong TCGArg; * TCGv_i64 : 64 bit integer type * TCGv_i128 : 128 bit integer type * TCGv_ptr : a host pointer type + * TCGv_vaddr: an integer type wide enough to hold a target pointer type * TCGv_vec : a host vector type; the exact size is not exposed to the CPU front-end code. * TCGv : an integer type the same size as target_ulong @@ -216,6 +218,14 @@ typedef struct TCGv_ptr_d *TCGv_ptr; typedef struct TCGv_vec_d *TCGv_vec; typedef TCGv_ptr TCGv_env; +#if __SIZEOF_POINTER__ == 4 +typedef TCGv_i32 TCGv_vaddr; +#elif __SIZEOF_POINTER__ == 8 +typedef TCGv_i64 TCGv_vaddr; +#else +# error "sizeof pointer is different from {4,8}" +#endif /* __SIZEOF_POINTER__ */ + /* call flags */ /* Helper does not read globals (either directly or through an exception). It implies TCG_CALL_NO_WRITE_GLOBALS. */ @@ -347,7 +357,7 @@ static inline TCGRegSet output_pref(const TCGOp *op, unsigned i) } struct TCGContext { - uint8_t *pool_cur, *pool_end; + uintptr_t pool_cur, pool_end; TCGPool *pool_first, *pool_current, *pool_first_large; int nb_labels; int nb_globals; @@ -355,11 +365,6 @@ struct TCGContext { int nb_indirects; int nb_ops; TCGType addr_type; /* TCG_TYPE_I32 or TCG_TYPE_I64 */ - - int page_mask; - uint8_t page_bits; - uint8_t tlb_dyn_max_bits; - uint8_t insn_start_words; TCGBar guest_mo; TCGRegSet reserved_regs; @@ -418,6 +423,11 @@ struct TCGContext { MemOp riscv_cur_vsew; TCGType riscv_cur_type; #endif + /* + * During the tcg_reg_alloc_op loop, we are within a sequence of + * carry-using opcodes like addco+addci. + */ + bool carry_live; GHashTable *const_table[TCG_TYPE_COUNT]; TCGTempSet free_temps[TCG_TYPE_COUNT]; @@ -572,23 +582,29 @@ static inline TCGv_ptr temp_tcgv_ptr(TCGTemp *t) return (TCGv_ptr)temp_tcgv_i32(t); } +static inline TCGv_vaddr temp_tcgv_vaddr(TCGTemp *t) +{ + return (TCGv_vaddr)temp_tcgv_i32(t); +} + static inline TCGv_vec temp_tcgv_vec(TCGTemp *t) { return (TCGv_vec)temp_tcgv_i32(t); } -static inline TCGArg tcg_get_insn_param(TCGOp *op, int arg) +static inline TCGArg tcg_get_insn_param(TCGOp *op, unsigned arg) { return op->args[arg]; } -static inline void tcg_set_insn_param(TCGOp *op, int arg, TCGArg v) +static inline void tcg_set_insn_param(TCGOp *op, unsigned arg, TCGArg v) { op->args[arg] = v; } -static inline uint64_t tcg_get_insn_start_param(TCGOp *op, int arg) +static inline uint64_t tcg_get_insn_start_param(TCGOp *op, unsigned arg) { + tcg_debug_assert(arg < INSN_START_WORDS); if (TCG_TARGET_REG_BITS == 64) { return tcg_get_insn_param(op, arg); } else { @@ -597,8 +613,9 @@ static inline uint64_t tcg_get_insn_start_param(TCGOp *op, int arg) } } -static inline void tcg_set_insn_start_param(TCGOp *op, int arg, uint64_t v) +static inline void tcg_set_insn_start_param(TCGOp *op, unsigned arg, uint64_t v) { + tcg_debug_assert(arg < INSN_START_WORDS); if (TCG_TARGET_REG_BITS == 64) { tcg_set_insn_param(op, arg, v); } else { @@ -689,7 +706,7 @@ size_t tcg_nb_tbs(void); static inline void *tcg_malloc(int size) { TCGContext *s = tcg_ctx; - uint8_t *ptr, *ptr_end; + uintptr_t ptr, ptr_end; /* ??? This is a weak placeholder for minimum malloc alignment. */ size = QEMU_ALIGN_UP(size, 8); @@ -700,7 +717,7 @@ static inline void *tcg_malloc(int size) return tcg_malloc_internal(tcg_ctx, size); } else { s->pool_cur = ptr_end; - return ptr; + return (void *)ptr; } } @@ -741,19 +758,25 @@ enum { /* Instruction has side effects: it cannot be removed if its outputs are not used, and might trigger exceptions. */ TCG_OPF_SIDE_EFFECTS = 0x08, + /* Instruction operands may be I32 or I64 */ + TCG_OPF_INT = 0x10, /* Instruction is optional and not implemented by the host, or insn is generic and should not be implemented by the host. */ TCG_OPF_NOT_PRESENT = 0x20, /* Instruction operands are vectors. */ TCG_OPF_VECTOR = 0x40, /* Instruction is a conditional branch. */ - TCG_OPF_COND_BRANCH = 0x80 + TCG_OPF_COND_BRANCH = 0x80, + /* Instruction produces carry out. */ + TCG_OPF_CARRY_OUT = 0x100, + /* Instruction consumes carry in. */ + TCG_OPF_CARRY_IN = 0x200, }; typedef struct TCGOpDef { const char *name; uint8_t nb_oargs, nb_iargs, nb_cargs, nb_args; - uint8_t flags; + uint16_t flags; } TCGOpDef; extern const TCGOpDef tcg_op_defs[]; @@ -982,5 +1005,7 @@ static inline const TCGOpcode *tcg_swap_vecop_list(const TCGOpcode *n) bool tcg_can_emit_vecop_list(const TCGOpcode *, TCGType, unsigned); void tcg_dump_ops(TCGContext *s, FILE *f, bool have_prefs); +/* tcg_dump_stats: Append TCG statistics to @buf */ +void tcg_dump_stats(GString *buf); #endif /* TCG_H */ diff --git a/include/ui/clipboard.h b/include/ui/clipboard.h index ab6acdb..62a96ce 100644 --- a/include/ui/clipboard.h +++ b/include/ui/clipboard.h @@ -2,6 +2,7 @@ #define QEMU_CLIPBOARD_H #include "qemu/notify.h" +#include "migration/vmstate.h" /** * DOC: Introduction @@ -25,6 +26,9 @@ typedef enum QemuClipboardSelection QemuClipboardSelection; typedef struct QemuClipboardPeer QemuClipboardPeer; typedef struct QemuClipboardNotify QemuClipboardNotify; typedef struct QemuClipboardInfo QemuClipboardInfo; +typedef struct QemuClipboardContent QemuClipboardContent; + +extern const VMStateDescription vmstate_cbinfo; /** * enum QemuClipboardType @@ -97,6 +101,24 @@ struct QemuClipboardNotify { }; }; + +/** + * struct QemuClipboardContent + * + * @available: whether the data is available + * @requested: whether the data was requested + * @size: the size of the @data + * @data: the clipboard data + * + * Clipboard content. + */ +struct QemuClipboardContent { + bool available; + bool requested; + uint32_t size; + void *data; +}; + /** * struct QemuClipboardInfo * @@ -112,15 +134,10 @@ struct QemuClipboardNotify { struct QemuClipboardInfo { uint32_t refcount; QemuClipboardPeer *owner; - QemuClipboardSelection selection; + int selection; /* QemuClipboardSelection */ bool has_serial; uint32_t serial; - struct { - bool available; - bool requested; - size_t size; - void *data; - } types[QEMU_CLIPBOARD_TYPE__COUNT]; + QemuClipboardContent types[QEMU_CLIPBOARD_TYPE__COUNT]; }; /** diff --git a/include/ui/console.h b/include/ui/console.h index 46b3128..98feaa5 100644 --- a/include/ui/console.h +++ b/include/ui/console.h @@ -422,6 +422,9 @@ bool console_gl_check_format(DisplayChangeListener *dcl, pixman_format_code_t format); void surface_gl_create_texture(QemuGLShader *gls, DisplaySurface *surface); +bool surface_gl_create_texture_from_fd(DisplaySurface *surface, + int fd, GLuint *texture, + GLuint *mem_obj); void surface_gl_update_texture(QemuGLShader *gls, DisplaySurface *surface, int x, int y, int w, int h); diff --git a/include/ui/dmabuf.h b/include/ui/dmabuf.h index dc74ba8..3decdca 100644 --- a/include/ui/dmabuf.h +++ b/include/ui/dmabuf.h @@ -10,24 +10,29 @@ #ifndef DMABUF_H #define DMABUF_H +#define DMABUF_MAX_PLANES 4 + typedef struct QemuDmaBuf QemuDmaBuf; QemuDmaBuf *qemu_dmabuf_new(uint32_t width, uint32_t height, - uint32_t stride, uint32_t x, - uint32_t y, uint32_t backing_width, - uint32_t backing_height, uint32_t fourcc, - uint64_t modifier, int dmabuf_fd, + const uint32_t *offset, const uint32_t *stride, + uint32_t x, uint32_t y, + uint32_t backing_width, uint32_t backing_height, + uint32_t fourcc, uint64_t modifier, + const int32_t *dmabuf_fd, uint32_t num_planes, bool allow_fences, bool y0_top); void qemu_dmabuf_free(QemuDmaBuf *dmabuf); G_DEFINE_AUTOPTR_CLEANUP_FUNC(QemuDmaBuf, qemu_dmabuf_free); -int qemu_dmabuf_get_fd(QemuDmaBuf *dmabuf); -int qemu_dmabuf_dup_fd(QemuDmaBuf *dmabuf); +const int *qemu_dmabuf_get_fds(QemuDmaBuf *dmabuf, int *nfds); +void qemu_dmabuf_dup_fds(QemuDmaBuf *dmabuf, int *fds, int nfds); void qemu_dmabuf_close(QemuDmaBuf *dmabuf); uint32_t qemu_dmabuf_get_width(QemuDmaBuf *dmabuf); uint32_t qemu_dmabuf_get_height(QemuDmaBuf *dmabuf); -uint32_t qemu_dmabuf_get_stride(QemuDmaBuf *dmabuf); +const uint32_t *qemu_dmabuf_get_offsets(QemuDmaBuf *dmabuf, int *noffsets); +const uint32_t *qemu_dmabuf_get_strides(QemuDmaBuf *dmabuf, int *nstrides); +uint32_t qemu_dmabuf_get_num_planes(QemuDmaBuf *dmabuf); uint32_t qemu_dmabuf_get_fourcc(QemuDmaBuf *dmabuf); uint64_t qemu_dmabuf_get_modifier(QemuDmaBuf *dmabuf); uint32_t qemu_dmabuf_get_texture(QemuDmaBuf *dmabuf); @@ -44,6 +49,5 @@ void qemu_dmabuf_set_texture(QemuDmaBuf *dmabuf, uint32_t texture); void qemu_dmabuf_set_fence_fd(QemuDmaBuf *dmabuf, int32_t fence_fd); void qemu_dmabuf_set_sync(QemuDmaBuf *dmabuf, void *sync); void qemu_dmabuf_set_draw_submitted(QemuDmaBuf *dmabuf, bool draw_submitted); -void qemu_dmabuf_set_fd(QemuDmaBuf *dmabuf, int32_t fd); #endif diff --git a/include/ui/egl-helpers.h b/include/ui/egl-helpers.h index 4b8c0d2..acf993f 100644 --- a/include/ui/egl-helpers.h +++ b/include/ui/egl-helpers.h @@ -17,6 +17,8 @@ extern bool qemu_egl_angle_d3d; typedef struct egl_fb { int width; int height; + int x; + int y; GLuint texture; GLuint framebuffer; bool delete_texture; @@ -26,7 +28,7 @@ typedef struct egl_fb { #define EGL_FB_INIT { 0, } void egl_fb_destroy(egl_fb *fb); -void egl_fb_setup_default(egl_fb *fb, int width, int height); +void egl_fb_setup_default(egl_fb *fb, int width, int height, int x, int y); void egl_fb_setup_for_tex(egl_fb *fb, int width, int height, GLuint texture, bool delete); void egl_fb_setup_new_tex(egl_fb *fb, int width, int height); @@ -46,8 +48,9 @@ extern int qemu_egl_rn_fd; extern struct gbm_device *qemu_egl_rn_gbm_dev; int egl_rendernode_init(const char *rendernode, DisplayGLMode mode); -int egl_get_fd_for_texture(uint32_t tex_id, EGLint *stride, EGLint *fourcc, - EGLuint64KHR *modifier); +bool egl_dmabuf_export_texture(uint32_t tex_id, int *fd, EGLint *offset, + EGLint *stride, EGLint *fourcc, int *num_planes, + EGLuint64KHR *modifier); void egl_dmabuf_import_texture(QemuDmaBuf *dmabuf); void egl_dmabuf_release_texture(QemuDmaBuf *dmabuf); diff --git a/include/ui/gtk.h b/include/ui/gtk.h index aa3d637..3e6ce3c 100644 --- a/include/ui/gtk.h +++ b/include/ui/gtk.h @@ -41,6 +41,7 @@ typedef struct VirtualGfxConsole { DisplaySurface *ds; pixman_image_t *convert; cairo_surface_t *surface; + double preferred_scale; double scale_x; double scale_y; #if defined(CONFIG_OPENGL) @@ -140,6 +141,7 @@ struct GtkDisplayState { GdkCursor *null_cursor; Notifier mouse_mode_notifier; gboolean free_scale; + gboolean keep_aspect_ratio; bool external_pause_update; @@ -224,4 +226,6 @@ int gd_gl_area_make_current(DisplayGLCtx *dgc, /* gtk-clipboard.c */ void gd_clipboard_init(GtkDisplayState *gd); +void gd_update_scale(VirtualConsole *vc, int ww, int wh, int fbw, int fbh); + #endif /* UI_GTK_H */ diff --git a/include/ui/qemu-pixman.h b/include/ui/qemu-pixman.h index 193bc04..2ca0ed7 100644 --- a/include/ui/qemu-pixman.h +++ b/include/ui/qemu-pixman.h @@ -75,12 +75,12 @@ PixelFormat qemu_pixelformat_from_pixman(pixman_format_code_t format); pixman_format_code_t qemu_default_pixman_format(int bpp, bool native_endian); pixman_format_code_t qemu_drm_format_to_pixman(uint32_t drm_format); uint32_t qemu_pixman_to_drm_format(pixman_format_code_t pixman); -int qemu_pixman_get_type(int rshift, int gshift, int bshift); +int qemu_pixman_get_type(int rshift, int gshift, int bshift, int endian); bool qemu_pixman_check_format(DisplayChangeListener *dcl, pixman_format_code_t format); #ifdef CONFIG_PIXMAN -pixman_format_code_t qemu_pixman_get_format(PixelFormat *pf); +pixman_format_code_t qemu_pixman_get_format(PixelFormat *pf, int endian); pixman_image_t *qemu_pixman_linebuf_create(pixman_format_code_t format, int width); void qemu_pixman_linebuf_fill(pixman_image_t *linebuf, pixman_image_t *fb, diff --git a/include/ui/spice-display.h b/include/ui/spice-display.h index e1a9b36..690ece7 100644 --- a/include/ui/spice-display.h +++ b/include/ui/spice-display.h @@ -132,6 +132,9 @@ struct SimpleSpiceDisplay { egl_fb guest_fb; egl_fb blit_fb; egl_fb cursor_fb; + bool backing_y_0_top; + bool blit_scanout_texture; + bool new_scanout_texture; bool have_hot; #endif }; @@ -151,6 +154,8 @@ struct SimpleSpiceCursor { }; extern bool spice_opengl; +extern bool spice_remote_client; +extern int spice_max_refresh_rate; int qemu_spice_rect_is_empty(const QXLRect* r); void qemu_spice_rect_union(QXLRect *dest, const QXLRect *r); diff --git a/include/ui/surface.h b/include/ui/surface.h index f16f7be..006b198 100644 --- a/include/ui/surface.h +++ b/include/ui/surface.h @@ -22,6 +22,7 @@ typedef struct DisplaySurface { GLenum glformat; GLenum gltype; GLuint texture; + GLuint mem_obj; #endif qemu_pixman_shareable share_handle; uint32_t share_handle_offset; diff --git a/include/user/abitypes.h b/include/user/abitypes.h index 7528124..be7a876 100644 --- a/include/user/abitypes.h +++ b/include/user/abitypes.h @@ -6,7 +6,6 @@ #endif #include "exec/cpu-defs.h" -#include "exec/tswap.h" #include "user/tswap-target.h" #ifdef TARGET_ABI32 diff --git a/include/user/cpu_loop.h b/include/user/cpu_loop.h index 589c665..346e37e 100644 --- a/include/user/cpu_loop.h +++ b/include/user/cpu_loop.h @@ -20,11 +20,9 @@ #ifndef USER_CPU_LOOP_H #define USER_CPU_LOOP_H -#include "exec/abi_ptr.h" +#include "exec/vaddr.h" #include "exec/mmu-access-type.h" -#include "exec/log.h" -#include "exec/target_long.h" -#include "special-errno.h" + /** * adjust_signal_pc: @@ -46,7 +44,7 @@ MMUAccessType adjust_signal_pc(uintptr_t *pc, bool is_write); * Return true if the write fault has been handled, and should be re-tried. */ bool handle_sigsegv_accerr_write(CPUState *cpu, sigset_t *old_set, - uintptr_t host_pc, abi_ptr guest_addr); + uintptr_t host_pc, vaddr guest_addr); /** * cpu_loop_exit_sigsegv: @@ -59,7 +57,7 @@ bool handle_sigsegv_accerr_write(CPUState *cpu, sigset_t *old_set, * Use the TCGCPUOps hook to record cpu state, do guest operating system * specific things to raise SIGSEGV, and jump to the main cpu loop. */ -G_NORETURN void cpu_loop_exit_sigsegv(CPUState *cpu, target_ulong addr, +G_NORETURN void cpu_loop_exit_sigsegv(CPUState *cpu, vaddr addr, MMUAccessType access_type, bool maperr, uintptr_t ra); @@ -73,7 +71,7 @@ G_NORETURN void cpu_loop_exit_sigsegv(CPUState *cpu, target_ulong addr, * Use the TCGCPUOps hook to record cpu state, do guest operating system * specific things to raise SIGBUS, and jump to the main cpu loop. */ -G_NORETURN void cpu_loop_exit_sigbus(CPUState *cpu, target_ulong addr, +G_NORETURN void cpu_loop_exit_sigbus(CPUState *cpu, vaddr addr, MMUAccessType access_type, uintptr_t ra); @@ -83,8 +81,4 @@ void target_exception_dump(CPUArchState *env, const char *fmt, int code); #define EXCP_DUMP(env, fmt, code) \ target_exception_dump(env, fmt, code) -typedef struct target_pt_regs target_pt_regs; - -void target_cpu_copy_regs(CPUArchState *env, target_pt_regs *regs); - #endif diff --git a/include/user/guest-host.h b/include/user/guest-host.h index 8d2079b..8f7ef75 100644 --- a/include/user/guest-host.h +++ b/include/user/guest-host.h @@ -8,9 +8,9 @@ #ifndef USER_GUEST_HOST_H #define USER_GUEST_HOST_H -#include "user/abitypes.h" +#include "exec/vaddr.h" #include "user/guest-base.h" -#include "cpu.h" +#include "accel/tcg/cpu-ops.h" /* * If non-zero, the guest virtual address space is a contiguous subset @@ -23,59 +23,48 @@ extern unsigned long reserved_va; /* - * Limit the guest addresses as best we can. - * - * When not using -R reserved_va, we cannot really limit the guest - * to less address space than the host. For 32-bit guests, this - * acts as a sanity check that we're not giving the guest an address - * that it cannot even represent. For 64-bit guests... the address - * might not be what the real kernel would give, but it is at least - * representable in the guest. - * - * TODO: Improve address allocation to avoid this problem, and to - * avoid setting bits at the top of guest addresses that might need - * to be used for tags. + * The last byte of the guest address space. + * If reserved_va is non-zero, guest_addr_max matches. + * If reserved_va is zero, guest_addr_max equals the full guest space. */ -#define GUEST_ADDR_MAX_ \ - ((MIN_CONST(TARGET_VIRT_ADDR_SPACE_BITS, TARGET_ABI_BITS) <= 32) ? \ - UINT32_MAX : ~0ul) -#define GUEST_ADDR_MAX (reserved_va ? : GUEST_ADDR_MAX_) +extern unsigned long guest_addr_max; -#ifndef TARGET_TAGGED_ADDRESSES -static inline abi_ptr cpu_untagged_addr(CPUState *cs, abi_ptr x) +static inline vaddr cpu_untagged_addr(CPUState *cs, vaddr x) { + const TCGCPUOps *tcg_ops = cs->cc->tcg_ops; + if (tcg_ops->untagged_addr) { + return tcg_ops->untagged_addr(cs, x); + } return x; } -#endif /* All direct uses of g2h and h2g need to go away for usermode softmmu. */ -static inline void *g2h_untagged(abi_ptr x) +static inline void *g2h_untagged(vaddr x) { return (void *)((uintptr_t)(x) + guest_base); } -static inline void *g2h(CPUState *cs, abi_ptr x) +static inline void *g2h(CPUState *cs, vaddr x) { return g2h_untagged(cpu_untagged_addr(cs, x)); } -static inline bool guest_addr_valid_untagged(abi_ulong x) +static inline bool guest_addr_valid_untagged(vaddr x) { - return x <= GUEST_ADDR_MAX; + return x <= guest_addr_max; } -static inline bool guest_range_valid_untagged(abi_ulong start, abi_ulong len) +static inline bool guest_range_valid_untagged(vaddr start, vaddr len) { - return len - 1 <= GUEST_ADDR_MAX && start <= GUEST_ADDR_MAX - len + 1; + return len - 1 <= guest_addr_max && start <= guest_addr_max - len + 1; } #define h2g_valid(x) \ - (HOST_LONG_BITS <= TARGET_VIRT_ADDR_SPACE_BITS || \ - (uintptr_t)(x) - guest_base <= GUEST_ADDR_MAX) + ((uintptr_t)(x) - guest_base <= guest_addr_max) #define h2g_nocheck(x) ({ \ uintptr_t __ret = (uintptr_t)(x) - guest_base; \ - (abi_ptr)__ret; \ + (vaddr)__ret; \ }) #define h2g(x) ({ \ diff --git a/include/user/page-protection.h b/include/user/page-protection.h index 51daa18..41b23e7 100644 --- a/include/user/page-protection.h +++ b/include/user/page-protection.h @@ -12,29 +12,32 @@ #error Cannot include this header from system emulation #endif -#include "cpu-param.h" -#include "exec/target_long.h" +#include "exec/vaddr.h" #include "exec/translation-block.h" -void page_protect(tb_page_addr_t page_addr); -int page_unprotect(tb_page_addr_t address, uintptr_t pc); +int page_unprotect(CPUState *cpu, tb_page_addr_t address, uintptr_t pc); -int page_get_flags(target_ulong address); +int page_get_flags(vaddr address); /** * page_set_flags: * @start: first byte of range * @last: last byte of range - * @flags: flags to set + * @set_flags: flags to set + * @clr_flags: flags to clear * Context: holding mmap lock * * Modify the flags of a page and invalidate the code if necessary. * The flag PAGE_WRITE_ORG is positioned automatically depending * on PAGE_WRITE. The mmap_lock should already be held. + * + * For each page, flags = (flags & ~clr_flags) | set_flags. + * If clr_flags includes PAGE_VALID, this indicates a new mapping + * and page_reset_target_data will be called as well. */ -void page_set_flags(target_ulong start, target_ulong last, int flags); +void page_set_flags(vaddr start, vaddr last, int set_flags, int clr_flags); -void page_reset_target_data(target_ulong start, target_ulong last); +void page_reset_target_data(vaddr start, vaddr last); /** * page_check_range @@ -46,7 +49,7 @@ void page_reset_target_data(target_ulong start, target_ulong last); * Return false if any page is unmapped. Thus testing flags == 0 is * equivalent to testing for flags == PAGE_VALID. */ -bool page_check_range(target_ulong start, target_ulong last, int flags); +bool page_check_range(vaddr start, vaddr last, int flags); /** * page_check_range_empty: @@ -58,7 +61,7 @@ bool page_check_range(target_ulong start, target_ulong last, int flags); * The memory lock must be held so that the caller will can ensure * the result stays true until a new mapping can be installed. */ -bool page_check_range_empty(target_ulong start, target_ulong last); +bool page_check_range_empty(vaddr start, vaddr last); /** * page_find_range_empty @@ -72,26 +75,25 @@ bool page_check_range_empty(target_ulong start, target_ulong last); * The memory lock must be held, as the caller will want to ensure * the returned range stays empty until a new mapping can be installed. */ -target_ulong page_find_range_empty(target_ulong min, target_ulong max, - target_ulong len, target_ulong align); +vaddr page_find_range_empty(vaddr min, vaddr max, vaddr len, vaddr align); /** - * page_get_target_data(address) + * page_get_target_data * @address: guest virtual address + * @size: per-page size * - * Return TARGET_PAGE_DATA_SIZE bytes of out-of-band data to associate + * Return @size bytes of out-of-band data to associate * with the guest page at @address, allocating it if necessary. The * caller should already have verified that the address is valid. + * The value of @size must be the same for every call. * * The memory will be freed when the guest page is deallocated, * e.g. with the munmap system call. */ __attribute__((returns_nonnull)) -void *page_get_target_data(target_ulong address); - -typedef int (*walk_memory_regions_fn)(void *, target_ulong, - target_ulong, unsigned long); +void *page_get_target_data(vaddr address, size_t size); +typedef int (*walk_memory_regions_fn)(void *, vaddr, vaddr, int); int walk_memory_regions(void *, walk_memory_regions_fn); void page_dump(FILE *f); |