X-Git-Url: https://repo.jachan.dev/qemu.git/blobdiff_plain/f3e8275f491ca3dd082e1238c62ca2a0ec740d69..bdd4df332a1bdb20b7fa39ea741f7830e41e1187:/exec-all.h diff --git a/exec-all.h b/exec-all.h index 51d01f260b..94ed613e37 100644 --- a/exec-all.h +++ b/exec-all.h @@ -51,7 +51,7 @@ typedef struct TranslationBlock TranslationBlock; #else #define MAX_OPC_PARAM_PER_ARG 1 #endif -#define MAX_OPC_PARAM_IARGS 4 +#define MAX_OPC_PARAM_IARGS 5 #define MAX_OPC_PARAM_OARGS 1 #define MAX_OPC_PARAM_ARGS (MAX_OPC_PARAM_IARGS + MAX_OPC_PARAM_OARGS) @@ -76,32 +76,44 @@ extern uint16_t gen_opc_icount[OPC_BUF_SIZE]; #include "qemu-log.h" -void gen_intermediate_code(CPUState *env, struct TranslationBlock *tb); -void gen_intermediate_code_pc(CPUState *env, struct TranslationBlock *tb); -void restore_state_to_opc(CPUState *env, struct TranslationBlock *tb, +void gen_intermediate_code(CPUArchState *env, struct TranslationBlock *tb); +void gen_intermediate_code_pc(CPUArchState *env, struct TranslationBlock *tb); +void restore_state_to_opc(CPUArchState *env, struct TranslationBlock *tb, int pc_pos); void cpu_gen_init(void); -int cpu_gen_code(CPUState *env, struct TranslationBlock *tb, +int cpu_gen_code(CPUArchState *env, struct TranslationBlock *tb, int *gen_code_size_ptr); int cpu_restore_state(struct TranslationBlock *tb, - CPUState *env, unsigned long searched_pc); -void cpu_resume_from_signal(CPUState *env1, void *puc); -void cpu_io_recompile(CPUState *env, void *retaddr); -TranslationBlock *tb_gen_code(CPUState *env, + CPUArchState *env, uintptr_t searched_pc); +void QEMU_NORETURN cpu_resume_from_signal(CPUArchState *env1, void *puc); +void QEMU_NORETURN cpu_io_recompile(CPUArchState *env, uintptr_t retaddr); +TranslationBlock *tb_gen_code(CPUArchState *env, target_ulong pc, target_ulong cs_base, int flags, int cflags); -void cpu_exec_init(CPUState *env); -void QEMU_NORETURN cpu_loop_exit(CPUState *env1); -int page_unprotect(target_ulong address, unsigned long pc, void *puc); +void cpu_exec_init(CPUArchState *env); +void QEMU_NORETURN cpu_loop_exit(CPUArchState *env1); +int page_unprotect(target_ulong address, uintptr_t pc, void *puc); void tb_invalidate_phys_page_range(tb_page_addr_t start, tb_page_addr_t end, int is_cpu_write_access); -void tlb_flush_page(CPUState *env, target_ulong addr); -void tlb_flush(CPUState *env, int flush_global); +void tb_invalidate_phys_range(tb_page_addr_t start, tb_page_addr_t end, + int is_cpu_write_access); #if !defined(CONFIG_USER_ONLY) -void tlb_set_page(CPUState *env, target_ulong vaddr, - target_phys_addr_t paddr, int prot, +/* cputlb.c */ +void tlb_flush_page(CPUArchState *env, target_ulong addr); +void tlb_flush(CPUArchState *env, int flush_global); +void tlb_set_page(CPUArchState *env, target_ulong vaddr, + hwaddr paddr, int prot, int mmu_idx, target_ulong size); +void tb_invalidate_phys_addr(hwaddr addr); +#else +static inline void tlb_flush_page(CPUArchState *env, target_ulong addr) +{ +} + +static inline void tlb_flush(CPUArchState *env, int flush_global) +{ +} #endif #define CODE_GEN_ALIGN 16 /* must be >= of the size of a icache line */ @@ -109,8 +121,6 @@ void tlb_set_page(CPUState *env, target_ulong vaddr, #define CODE_GEN_PHYS_HASH_BITS 15 #define CODE_GEN_PHYS_HASH_SIZE (1 << CODE_GEN_PHYS_HASH_BITS) -#define MIN_CODE_GEN_BUFFER_SIZE (1024 * 1024) - /* estimated block size for TB allocation */ /* XXX: use a per code average code fragment size and modulate it according to the host CPU */ @@ -120,9 +130,10 @@ void tlb_set_page(CPUState *env, target_ulong vaddr, #define CODE_GEN_AVG_BLOCK_SIZE 64 #endif -#if defined(_ARCH_PPC) || defined(__x86_64__) || defined(__arm__) || defined(__i386__) -#define USE_DIRECT_JUMP -#elif defined(CONFIG_TCG_INTERPRETER) +#if defined(__arm__) || defined(_ARCH_PPC) \ + || defined(__x86_64__) || defined(__i386__) \ + || defined(__sparc__) \ + || defined(CONFIG_TCG_INTERPRETER) #define USE_DIRECT_JUMP #endif @@ -150,7 +161,7 @@ struct TranslationBlock { #ifdef USE_DIRECT_JUMP uint16_t tb_jmp_offset[2]; /* offset of jump instruction */ #else - unsigned long tb_next[2]; /* address of jump generated code */ + uintptr_t tb_next[2]; /* address of jump generated code */ #endif /* list of TBs jumping to this one. This is a circular list using the two least significant bits of the pointers to tell what is @@ -182,9 +193,7 @@ static inline unsigned int tb_phys_hash_func(tb_page_addr_t pc) } void tb_free(TranslationBlock *tb); -void tb_flush(CPUState *env); -void tb_link_page(TranslationBlock *tb, - tb_page_addr_t phys_pc, tb_page_addr_t phys_page2); +void tb_flush(CPUArchState *env); void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr); extern TranslationBlock *tb_phys_hash[CODE_GEN_PHYS_HASH_SIZE]; @@ -202,14 +211,14 @@ static inline void tb_set_jmp_target1(uintptr_t jmp_addr, uintptr_t addr) void ppc_tb_set_jmp_target(unsigned long jmp_addr, unsigned long addr); #define tb_set_jmp_target1 ppc_tb_set_jmp_target #elif defined(__i386__) || defined(__x86_64__) -static inline void tb_set_jmp_target1(unsigned long jmp_addr, unsigned long addr) +static inline void tb_set_jmp_target1(uintptr_t jmp_addr, uintptr_t addr) { /* patch the branch destination */ *(uint32_t *)jmp_addr = addr - (jmp_addr + 4); /* no need to flush icache explicitly */ } #elif defined(__arm__) -static inline void tb_set_jmp_target1(unsigned long jmp_addr, unsigned long addr) +static inline void tb_set_jmp_target1(uintptr_t jmp_addr, uintptr_t addr) { #if !QEMU_GNUC_PREREQ(4, 1) register unsigned long _beg __asm ("a1"); @@ -232,24 +241,24 @@ static inline void tb_set_jmp_target1(unsigned long jmp_addr, unsigned long addr __asm __volatile__ ("swi 0x9f0002" : : "r" (_beg), "r" (_end), "r" (_flg)); #endif } +#elif defined(__sparc__) +void tb_set_jmp_target1(uintptr_t jmp_addr, uintptr_t addr); #else #error tb_set_jmp_target1 is missing #endif static inline void tb_set_jmp_target(TranslationBlock *tb, - int n, unsigned long addr) + int n, uintptr_t addr) { - unsigned long offset; - - offset = tb->tb_jmp_offset[n]; - tb_set_jmp_target1((unsigned long)(tb->tc_ptr + offset), addr); + uint16_t offset = tb->tb_jmp_offset[n]; + tb_set_jmp_target1((uintptr_t)(tb->tc_ptr + offset), addr); } #else /* set the jump target */ static inline void tb_set_jmp_target(TranslationBlock *tb, - int n, unsigned long addr) + int n, uintptr_t addr) { tb->tb_next[n] = addr; } @@ -262,15 +271,15 @@ static inline void tb_add_jump(TranslationBlock *tb, int n, /* NOTE: this test is only needed for thread safety */ if (!tb->jmp_next[n]) { /* patch the native jump address */ - tb_set_jmp_target(tb, n, (unsigned long)tb_next->tc_ptr); + tb_set_jmp_target(tb, n, (uintptr_t)tb_next->tc_ptr); /* add in TB jmp circular list */ tb->jmp_next[n] = tb_next->jmp_first; - tb_next->jmp_first = (TranslationBlock *)((long)(tb) | (n)); + tb_next->jmp_first = (TranslationBlock *)((uintptr_t)(tb) | (n)); } } -TranslationBlock *tb_find_pc(unsigned long pc_ptr); +TranslationBlock *tb_find_pc(uintptr_t pc_ptr); #include "qemu-lock.h" @@ -283,35 +292,76 @@ extern int tb_invalidated_flag; #if defined(CONFIG_TCG_INTERPRETER) /* Alpha and SH4 user mode emulations and Softmmu call GETPC(). For all others, GETPC remains undefined (which makes TCI a little faster. */ -# if defined(CONFIG_SOFTMMU) || defined(TARGET_ALPHA) || defined(TARGET_SH4) -extern void *tci_tb_ptr; +# if defined(CONFIG_SOFTMMU) || defined(TARGET_ALPHA) || defined(TARGET_SH4) \ + || defined(TARGET_SPARC) +extern uintptr_t tci_tb_ptr; # define GETPC() tci_tb_ptr # endif #elif defined(__s390__) && !defined(__s390x__) -# define GETPC() ((void*)(((unsigned long)__builtin_return_address(0) & 0x7fffffffUL) - 1)) +# define GETPC() \ + (((uintptr_t)__builtin_return_address(0) & 0x7fffffffUL) - 1) #elif defined(__arm__) /* Thumb return addresses have the low bit set, so we need to subtract two. This is still safe in ARM mode because instructions are 4 bytes. */ -# define GETPC() ((void *)((unsigned long)__builtin_return_address(0) - 2)) +# define GETPC() ((uintptr_t)__builtin_return_address(0) - 2) +#else +# define GETPC() ((uintptr_t)__builtin_return_address(0) - 1) +#endif + +#if defined(CONFIG_QEMU_LDST_OPTIMIZATION) && defined(CONFIG_SOFTMMU) +/* qemu_ld/st optimization split code generation to fast and slow path, thus, + it needs special handling for an MMU helper which is called from the slow + path, to get the fast path's pc without any additional argument. + It uses a tricky solution which embeds the fast path pc into the slow path. + + Code flow in slow path: + (1) pre-process + (2) call MMU helper + (3) jump to (5) + (4) fast path information (implementation specific) + (5) post-process (e.g. stack adjust) + (6) jump to corresponding code of the next of fast path + */ +# if defined(__i386__) || defined(__x86_64__) +/* To avoid broken disassembling, long jmp is used for embedding fast path pc, + so that the destination is the next code of fast path, though this jmp is + never executed. + + call MMU helper + jmp POST_PROC (2byte) <- GETRA() + jmp NEXT_CODE (5byte) + POST_PROCESS ... <- GETRA() + 7 + */ +# define GETRA() ((uintptr_t)__builtin_return_address(0)) +# define GETPC_LDST() ((uintptr_t)(GETRA() + 7 + \ + *(int32_t *)((void *)GETRA() + 3) - 1)) +# elif defined (_ARCH_PPC) && !defined (_ARCH_PPC64) +# define GETRA() ((uintptr_t)__builtin_return_address(0)) +# define GETPC_LDST() ((uintptr_t) ((*(int32_t *)(GETRA() + 4)) - 1)) +# else +# error "CONFIG_QEMU_LDST_OPTIMIZATION needs GETPC_LDST() implementation!" +# endif +bool is_tcg_gen_code(uintptr_t pc_ptr); +# define GETPC_EXT() (is_tcg_gen_code(GETRA()) ? GETPC_LDST() : GETPC()) #else -# define GETPC() ((void *)((unsigned long)__builtin_return_address(0) - 1)) +# define GETPC_EXT() GETPC() #endif #if !defined(CONFIG_USER_ONLY) -uint64_t io_mem_read(int index, target_phys_addr_t addr, unsigned size); -void io_mem_write(int index, target_phys_addr_t addr, uint64_t value, - unsigned size); -extern struct MemoryRegion *io_mem_region[IO_MEM_NB_ENTRIES]; +struct MemoryRegion *iotlb_to_region(hwaddr index); +uint64_t io_mem_read(struct MemoryRegion *mr, hwaddr addr, + unsigned size); +void io_mem_write(struct MemoryRegion *mr, hwaddr addr, + uint64_t value, unsigned size); -void tlb_fill(CPUState *env1, target_ulong addr, int is_write, int mmu_idx, - void *retaddr); +void tlb_fill(CPUArchState *env1, target_ulong addr, int is_write, int mmu_idx, + uintptr_t retaddr); #include "softmmu_defs.h" #define ACCESS_TYPE (NB_MMU_MODES + 1) #define MEMSUFFIX _code -#define env cpu_single_env #define DATA_SIZE 1 #include "softmmu_header.h" @@ -327,22 +377,22 @@ void tlb_fill(CPUState *env1, target_ulong addr, int is_write, int mmu_idx, #undef ACCESS_TYPE #undef MEMSUFFIX -#undef env #endif #if defined(CONFIG_USER_ONLY) -static inline tb_page_addr_t get_page_addr_code(CPUState *env1, target_ulong addr) +static inline tb_page_addr_t get_page_addr_code(CPUArchState *env1, target_ulong addr) { return addr; } #else -tb_page_addr_t get_page_addr_code(CPUState *env1, target_ulong addr); +/* cputlb.c */ +tb_page_addr_t get_page_addr_code(CPUArchState *env1, target_ulong addr); #endif -typedef void (CPUDebugExcpHandler)(CPUState *env); +typedef void (CPUDebugExcpHandler)(CPUArchState *env); -CPUDebugExcpHandler *cpu_set_debug_excp_handler(CPUDebugExcpHandler *handler); +void cpu_set_debug_excp_handler(CPUDebugExcpHandler *handler); /* vl.c */ extern int singlestep; @@ -352,7 +402,7 @@ extern volatile sig_atomic_t exit_request; /* Deterministic execution requires that IO only be performed on the last instruction of a TB so that interrupts take effect immediately. */ -static inline int can_do_io(CPUState *env) +static inline int can_do_io(CPUArchState *env) { if (!use_icount) { return 1;