diff options
Diffstat (limited to 'include')
-rw-r--r-- | include/exec/cpu_ldst.h | 67 | ||||
-rw-r--r-- | include/exec/exec-all.h | 3 | ||||
-rw-r--r-- | include/qemu/atomic128.h | 146 | ||||
-rw-r--r-- | include/tcg/debug-assert.h | 17 | ||||
-rw-r--r-- | include/tcg/tcg.h | 9 |
5 files changed, 49 insertions, 193 deletions
diff --git a/include/exec/cpu_ldst.h b/include/exec/cpu_ldst.h index 7c867c9..5939688 100644 --- a/include/exec/cpu_ldst.h +++ b/include/exec/cpu_ldst.h @@ -207,43 +207,21 @@ 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_be_mmu(CPUArchState *env, abi_ptr ptr, - MemOpIdx oi, uintptr_t ra); -uint32_t cpu_ldl_be_mmu(CPUArchState *env, abi_ptr ptr, - MemOpIdx oi, uintptr_t ra); -uint64_t cpu_ldq_be_mmu(CPUArchState *env, abi_ptr ptr, - MemOpIdx oi, uintptr_t ra); -uint16_t cpu_ldw_le_mmu(CPUArchState *env, abi_ptr ptr, - MemOpIdx oi, uintptr_t ra); -uint32_t cpu_ldl_le_mmu(CPUArchState *env, abi_ptr ptr, - MemOpIdx oi, uintptr_t ra); -uint64_t cpu_ldq_le_mmu(CPUArchState *env, abi_ptr ptr, - MemOpIdx oi, uintptr_t ra); - -Int128 cpu_ld16_be_mmu(CPUArchState *env, abi_ptr addr, - MemOpIdx oi, uintptr_t ra); -Int128 cpu_ld16_le_mmu(CPUArchState *env, abi_ptr addr, - 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_be_mmu(CPUArchState *env, abi_ptr ptr, uint16_t val, - MemOpIdx oi, uintptr_t ra); -void cpu_stl_be_mmu(CPUArchState *env, abi_ptr ptr, uint32_t val, - MemOpIdx oi, uintptr_t ra); -void cpu_stq_be_mmu(CPUArchState *env, abi_ptr ptr, uint64_t val, - MemOpIdx oi, uintptr_t ra); -void cpu_stw_le_mmu(CPUArchState *env, abi_ptr ptr, uint16_t val, - MemOpIdx oi, uintptr_t ra); -void cpu_stl_le_mmu(CPUArchState *env, abi_ptr ptr, uint32_t val, - MemOpIdx oi, uintptr_t ra); -void cpu_stq_le_mmu(CPUArchState *env, abi_ptr ptr, uint64_t val, - MemOpIdx oi, uintptr_t ra); - -void cpu_st16_be_mmu(CPUArchState *env, abi_ptr addr, Int128 val, - MemOpIdx oi, uintptr_t ra); -void cpu_st16_le_mmu(CPUArchState *env, abi_ptr addr, Int128 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, target_ulong addr, uint32_t cmpv, uint32_t newv, @@ -322,15 +300,6 @@ Int128 cpu_atomic_cmpxchgo_be_mmu(CPUArchState *env, target_ulong addr, Int128 cmpv, Int128 newv, MemOpIdx oi, uintptr_t retaddr); -Int128 cpu_atomic_ldo_le_mmu(CPUArchState *env, target_ulong addr, - MemOpIdx oi, uintptr_t retaddr); -Int128 cpu_atomic_ldo_be_mmu(CPUArchState *env, target_ulong addr, - MemOpIdx oi, uintptr_t retaddr); -void cpu_atomic_sto_le_mmu(CPUArchState *env, target_ulong addr, Int128 val, - MemOpIdx oi, uintptr_t retaddr); -void cpu_atomic_sto_be_mmu(CPUArchState *env, target_ulong addr, Int128 val, - MemOpIdx oi, uintptr_t retaddr); - #if defined(CONFIG_USER_ONLY) extern __thread uintptr_t helper_retaddr; @@ -416,9 +385,6 @@ static inline CPUTLBEntry *tlb_entry(CPUArchState *env, uintptr_t mmu_idx, # 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_ldw_mmu cpu_ldw_be_mmu -# define cpu_ldl_mmu cpu_ldl_be_mmu -# define cpu_ldq_mmu cpu_ldq_be_mmu # define cpu_stw_data cpu_stw_be_data # define cpu_stl_data cpu_stl_be_data # define cpu_stq_data cpu_stq_be_data @@ -428,9 +394,6 @@ static inline CPUTLBEntry *tlb_entry(CPUArchState *env, uintptr_t mmu_idx, # 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 -# define cpu_stw_mmu cpu_stw_be_mmu -# define cpu_stl_mmu cpu_stl_be_mmu -# define cpu_stq_mmu cpu_stq_be_mmu #else # define cpu_lduw_data cpu_lduw_le_data # define cpu_ldsw_data cpu_ldsw_le_data @@ -444,9 +407,6 @@ static inline CPUTLBEntry *tlb_entry(CPUArchState *env, uintptr_t mmu_idx, # 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_ldw_mmu cpu_ldw_le_mmu -# define cpu_ldl_mmu cpu_ldl_le_mmu -# define cpu_ldq_mmu cpu_ldq_le_mmu # define cpu_stw_data cpu_stw_le_data # define cpu_stl_data cpu_stl_le_data # define cpu_stq_data cpu_stq_le_data @@ -456,9 +416,6 @@ static inline CPUTLBEntry *tlb_entry(CPUArchState *env, uintptr_t mmu_idx, # 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 -# define cpu_stw_mmu cpu_stw_le_mmu -# define cpu_stl_mmu cpu_stl_le_mmu -# define cpu_stq_mmu cpu_stq_le_mmu #endif uint8_t cpu_ldb_code_mmu(CPUArchState *env, abi_ptr addr, diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index ecded1f..4d2b151 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -27,9 +27,6 @@ #include "qemu/interval-tree.h" #include "qemu/clang-tsa.h" -/* allow to see translation results - the slowdown should be negligible, so we leave it */ -#define DEBUG_DISAS - /* Page tracking code uses ram addresses in system mode, and virtual addresses in userspace mode. Define tb_page_addr_t to be an appropriate type. */ diff --git a/include/qemu/atomic128.h b/include/qemu/atomic128.h index d0ba0b9..34554bf 100644 --- a/include/qemu/atomic128.h +++ b/include/qemu/atomic128.h @@ -16,6 +16,23 @@ #include "qemu/int128.h" /* + * If __alignof(unsigned __int128) < 16, GCC may refuse to inline atomics + * that are supported by the host, e.g. s390x. We can force the pointer to + * have our known alignment with __builtin_assume_aligned, however prior to + * GCC 13 that was only reliable with optimization enabled. See + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107389 + */ +#if defined(CONFIG_ATOMIC128_OPT) +# if !defined(__OPTIMIZE__) +# define ATTRIBUTE_ATOMIC128_OPT __attribute__((optimize("O1"))) +# endif +# define CONFIG_ATOMIC128 +#endif +#ifndef ATTRIBUTE_ATOMIC128_OPT +# define ATTRIBUTE_ATOMIC128_OPT +#endif + +/* * GCC is a house divided about supporting large atomic operations. * * For hosts that only have large compare-and-swap, a legalistic reading @@ -41,132 +58,7 @@ * Therefore, special case each platform. */ -#if defined(CONFIG_ATOMIC128) -static inline Int128 atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new) -{ - Int128Alias r, c, n; - - c.s = cmp; - n.s = new; - r.i = qatomic_cmpxchg__nocheck((__int128_t *)ptr, c.i, n.i); - return r.s; -} -# define HAVE_CMPXCHG128 1 -#elif defined(CONFIG_CMPXCHG128) -static inline Int128 atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new) -{ - Int128Alias r, c, n; - - c.s = cmp; - n.s = new; - r.i = __sync_val_compare_and_swap_16((__int128_t *)ptr, c.i, n.i); - return r.s; -} -# define HAVE_CMPXCHG128 1 -#elif defined(__aarch64__) -/* Through gcc 8, aarch64 has no support for 128-bit at all. */ -static inline Int128 atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new) -{ - uint64_t cmpl = int128_getlo(cmp), cmph = int128_gethi(cmp); - uint64_t newl = int128_getlo(new), newh = int128_gethi(new); - uint64_t oldl, oldh; - uint32_t tmp; - - asm("0: ldaxp %[oldl], %[oldh], %[mem]\n\t" - "cmp %[oldl], %[cmpl]\n\t" - "ccmp %[oldh], %[cmph], #0, eq\n\t" - "b.ne 1f\n\t" - "stlxp %w[tmp], %[newl], %[newh], %[mem]\n\t" - "cbnz %w[tmp], 0b\n" - "1:" - : [mem] "+m"(*ptr), [tmp] "=&r"(tmp), - [oldl] "=&r"(oldl), [oldh] "=&r"(oldh) - : [cmpl] "r"(cmpl), [cmph] "r"(cmph), - [newl] "r"(newl), [newh] "r"(newh) - : "memory", "cc"); - - return int128_make128(oldl, oldh); -} -# define HAVE_CMPXCHG128 1 -#else -/* Fallback definition that must be optimized away, or error. */ -Int128 QEMU_ERROR("unsupported atomic") - atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new); -# define HAVE_CMPXCHG128 0 -#endif /* Some definition for HAVE_CMPXCHG128 */ - - -#if defined(CONFIG_ATOMIC128) -static inline Int128 atomic16_read(Int128 *ptr) -{ - Int128Alias r; - - r.i = qatomic_read__nocheck((__int128_t *)ptr); - return r.s; -} - -static inline void atomic16_set(Int128 *ptr, Int128 val) -{ - Int128Alias v; - - v.s = val; - qatomic_set__nocheck((__int128_t *)ptr, v.i); -} - -# define HAVE_ATOMIC128 1 -#elif !defined(CONFIG_USER_ONLY) && defined(__aarch64__) -/* We can do better than cmpxchg for AArch64. */ -static inline Int128 atomic16_read(Int128 *ptr) -{ - uint64_t l, h; - uint32_t tmp; - - /* The load must be paired with the store to guarantee not tearing. */ - asm("0: ldxp %[l], %[h], %[mem]\n\t" - "stxp %w[tmp], %[l], %[h], %[mem]\n\t" - "cbnz %w[tmp], 0b" - : [mem] "+m"(*ptr), [tmp] "=r"(tmp), [l] "=r"(l), [h] "=r"(h)); - - return int128_make128(l, h); -} - -static inline void atomic16_set(Int128 *ptr, Int128 val) -{ - uint64_t l = int128_getlo(val), h = int128_gethi(val); - uint64_t t1, t2; - - /* Load into temporaries to acquire the exclusive access lock. */ - asm("0: ldxp %[t1], %[t2], %[mem]\n\t" - "stxp %w[t1], %[l], %[h], %[mem]\n\t" - "cbnz %w[t1], 0b" - : [mem] "+m"(*ptr), [t1] "=&r"(t1), [t2] "=&r"(t2) - : [l] "r"(l), [h] "r"(h)); -} - -# define HAVE_ATOMIC128 1 -#elif !defined(CONFIG_USER_ONLY) && HAVE_CMPXCHG128 -static inline Int128 atomic16_read(Int128 *ptr) -{ - /* Maybe replace 0 with 0, returning the old value. */ - Int128 z = int128_make64(0); - return atomic16_cmpxchg(ptr, z, z); -} - -static inline void atomic16_set(Int128 *ptr, Int128 val) -{ - Int128 old = *ptr, cmp; - do { - cmp = old; - old = atomic16_cmpxchg(ptr, cmp, val); - } while (int128_ne(old, cmp)); -} - -# define HAVE_ATOMIC128 1 -#else -/* Fallback definitions that must be optimized away, or error. */ -Int128 QEMU_ERROR("unsupported atomic") atomic16_read(Int128 *ptr); -void QEMU_ERROR("unsupported atomic") atomic16_set(Int128 *ptr, Int128 val); -# define HAVE_ATOMIC128 0 -#endif /* Some definition for HAVE_ATOMIC128 */ +#include "host/atomic128-cas.h" +#include "host/atomic128-ldst.h" #endif /* QEMU_ATOMIC128_H */ diff --git a/include/tcg/debug-assert.h b/include/tcg/debug-assert.h new file mode 100644 index 0000000..596765a --- /dev/null +++ b/include/tcg/debug-assert.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Define tcg_debug_assert + * Copyright (c) 2008 Fabrice Bellard + */ + +#ifndef TCG_DEBUG_ASSERT_H +#define TCG_DEBUG_ASSERT_H + +#if defined CONFIG_DEBUG_TCG || defined QEMU_STATIC_ANALYSIS +# define tcg_debug_assert(X) do { assert(X); } while (0) +#else +# define tcg_debug_assert(X) \ + do { if (!(X)) { __builtin_unreachable(); } } while (0) +#endif + +#endif diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h index cd6327b..072c35f 100644 --- a/include/tcg/tcg.h +++ b/include/tcg/tcg.h @@ -34,6 +34,7 @@ #include "tcg/tcg-mo.h" #include "tcg-target.h" #include "tcg/tcg-cond.h" +#include "tcg/debug-assert.h" /* XXX: make safe guess about sizes */ #define MAX_OP_PER_INSTR 266 @@ -222,14 +223,6 @@ typedef uint64_t tcg_insn_unit; /* The port better have done this. */ #endif - -#if defined CONFIG_DEBUG_TCG || defined QEMU_STATIC_ANALYSIS -# define tcg_debug_assert(X) do { assert(X); } while (0) -#else -# define tcg_debug_assert(X) \ - do { if (!(X)) { __builtin_unreachable(); } } while (0) -#endif - typedef struct TCGRelocation TCGRelocation; struct TCGRelocation { QSIMPLEQ_ENTRY(TCGRelocation) next; |