diff options
63 files changed, 1609 insertions, 706 deletions
diff --git a/accel/tcg/atomic_common.c.inc b/accel/tcg/atomic_common.c.inc index 6c0339f610..1df1f243e9 100644 --- a/accel/tcg/atomic_common.c.inc +++ b/accel/tcg/atomic_common.c.inc @@ -13,56 +13,43 @@ * See the COPYING file in the top-level directory. */ -static uint16_t atomic_trace_rmw_pre(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi) +static void atomic_trace_rmw_pre(CPUArchState *env, target_ulong addr, + MemOpIdx oi) { CPUState *cpu = env_cpu(env); - uint16_t info = trace_mem_get_info(get_memop(oi), get_mmuidx(oi), false); - trace_guest_mem_before_exec(cpu, addr, info); - trace_guest_mem_before_exec(cpu, addr, info | TRACE_MEM_ST); - - return info; + trace_guest_rmw_before_exec(cpu, addr, oi); } static void atomic_trace_rmw_post(CPUArchState *env, target_ulong addr, - uint16_t info) + MemOpIdx oi) { - qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, info); - qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, info | TRACE_MEM_ST); + qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_RW); } #if HAVE_ATOMIC128 -static uint16_t atomic_trace_ld_pre(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi) +static void atomic_trace_ld_pre(CPUArchState *env, target_ulong addr, + MemOpIdx oi) { - uint16_t info = trace_mem_get_info(get_memop(oi), get_mmuidx(oi), false); - - trace_guest_mem_before_exec(env_cpu(env), addr, info); - - return info; + trace_guest_ld_before_exec(env_cpu(env), addr, oi); } static void atomic_trace_ld_post(CPUArchState *env, target_ulong addr, - uint16_t info) + MemOpIdx oi) { - qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, info); + qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R); } -static uint16_t atomic_trace_st_pre(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi) +static void atomic_trace_st_pre(CPUArchState *env, target_ulong addr, + MemOpIdx oi) { - uint16_t info = trace_mem_get_info(get_memop(oi), get_mmuidx(oi), true); - - trace_guest_mem_before_exec(env_cpu(env), addr, info); - - return info; + trace_guest_st_before_exec(env_cpu(env), addr, oi); } static void atomic_trace_st_post(CPUArchState *env, target_ulong addr, - uint16_t info) + MemOpIdx oi) { - qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, info); + qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W); } #endif diff --git a/accel/tcg/atomic_template.h b/accel/tcg/atomic_template.h index 8098a1be31..2d917b6b1f 100644 --- a/accel/tcg/atomic_template.h +++ b/accel/tcg/atomic_template.h @@ -19,7 +19,6 @@ */ #include "qemu/plugin.h" -#include "trace/mem.h" #if DATA_SIZE == 16 # define SUFFIX o @@ -72,77 +71,77 @@ ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr, ABI_TYPE cmpv, ABI_TYPE newv, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, PAGE_READ | PAGE_WRITE, retaddr); DATA_TYPE ret; - uint16_t info = atomic_trace_rmw_pre(env, addr, oi); + atomic_trace_rmw_pre(env, addr, oi); #if DATA_SIZE == 16 ret = atomic16_cmpxchg(haddr, cmpv, newv); #else ret = qatomic_cmpxchg__nocheck(haddr, cmpv, newv); #endif ATOMIC_MMU_CLEANUP; - atomic_trace_rmw_post(env, addr, info); + atomic_trace_rmw_post(env, addr, oi); return ret; } #if DATA_SIZE >= 16 #if HAVE_ATOMIC128 ABI_TYPE ATOMIC_NAME(ld)(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, PAGE_READ, retaddr); DATA_TYPE val; - uint16_t info = atomic_trace_ld_pre(env, addr, oi); + atomic_trace_ld_pre(env, addr, oi); val = atomic16_read(haddr); ATOMIC_MMU_CLEANUP; - atomic_trace_ld_post(env, addr, info); + atomic_trace_ld_post(env, addr, oi); return val; } void ATOMIC_NAME(st)(CPUArchState *env, target_ulong addr, ABI_TYPE val, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, PAGE_WRITE, retaddr); - uint16_t info = atomic_trace_st_pre(env, addr, oi); + atomic_trace_st_pre(env, addr, oi); atomic16_set(haddr, val); ATOMIC_MMU_CLEANUP; - atomic_trace_st_post(env, addr, info); + atomic_trace_st_post(env, addr, oi); } #endif #else ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, target_ulong addr, ABI_TYPE val, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, PAGE_READ | PAGE_WRITE, retaddr); DATA_TYPE ret; - uint16_t info = atomic_trace_rmw_pre(env, addr, oi); + atomic_trace_rmw_pre(env, addr, oi); ret = qatomic_xchg__nocheck(haddr, val); ATOMIC_MMU_CLEANUP; - atomic_trace_rmw_post(env, addr, info); + atomic_trace_rmw_post(env, addr, oi); return ret; } #define GEN_ATOMIC_HELPER(X) \ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ - ABI_TYPE val, TCGMemOpIdx oi, uintptr_t retaddr) \ + ABI_TYPE val, MemOpIdx oi, uintptr_t retaddr) \ { \ DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, \ PAGE_READ | PAGE_WRITE, retaddr); \ DATA_TYPE ret; \ - uint16_t info = atomic_trace_rmw_pre(env, addr, oi); \ + atomic_trace_rmw_pre(env, addr, oi); \ ret = qatomic_##X(haddr, val); \ ATOMIC_MMU_CLEANUP; \ - atomic_trace_rmw_post(env, addr, info); \ + atomic_trace_rmw_post(env, addr, oi); \ return ret; \ } @@ -167,12 +166,12 @@ GEN_ATOMIC_HELPER(xor_fetch) */ #define GEN_ATOMIC_HELPER_FN(X, FN, XDATA_TYPE, RET) \ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ - ABI_TYPE xval, TCGMemOpIdx oi, uintptr_t retaddr) \ + ABI_TYPE xval, MemOpIdx oi, uintptr_t retaddr) \ { \ XDATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, \ PAGE_READ | PAGE_WRITE, retaddr); \ XDATA_TYPE cmp, old, new, val = xval; \ - uint16_t info = atomic_trace_rmw_pre(env, addr, oi); \ + atomic_trace_rmw_pre(env, addr, oi); \ smp_mb(); \ cmp = qatomic_read__nocheck(haddr); \ do { \ @@ -180,7 +179,7 @@ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ cmp = qatomic_cmpxchg__nocheck(haddr, old, new); \ } while (cmp != old); \ ATOMIC_MMU_CLEANUP; \ - atomic_trace_rmw_post(env, addr, info); \ + atomic_trace_rmw_post(env, addr, oi); \ return RET; \ } @@ -211,78 +210,78 @@ GEN_ATOMIC_HELPER_FN(umax_fetch, MAX, DATA_TYPE, new) ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr, ABI_TYPE cmpv, ABI_TYPE newv, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, PAGE_READ | PAGE_WRITE, retaddr); DATA_TYPE ret; - uint16_t info = atomic_trace_rmw_pre(env, addr, oi); + atomic_trace_rmw_pre(env, addr, oi); #if DATA_SIZE == 16 ret = atomic16_cmpxchg(haddr, BSWAP(cmpv), BSWAP(newv)); #else ret = qatomic_cmpxchg__nocheck(haddr, BSWAP(cmpv), BSWAP(newv)); #endif ATOMIC_MMU_CLEANUP; - atomic_trace_rmw_post(env, addr, info); + atomic_trace_rmw_post(env, addr, oi); return BSWAP(ret); } #if DATA_SIZE >= 16 #if HAVE_ATOMIC128 ABI_TYPE ATOMIC_NAME(ld)(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, PAGE_READ, retaddr); DATA_TYPE val; - uint16_t info = atomic_trace_ld_pre(env, addr, oi); + atomic_trace_ld_pre(env, addr, oi); val = atomic16_read(haddr); ATOMIC_MMU_CLEANUP; - atomic_trace_ld_post(env, addr, info); + atomic_trace_ld_post(env, addr, oi); return BSWAP(val); } void ATOMIC_NAME(st)(CPUArchState *env, target_ulong addr, ABI_TYPE val, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, PAGE_WRITE, retaddr); - uint16_t info = atomic_trace_st_pre(env, addr, oi); + atomic_trace_st_pre(env, addr, oi); val = BSWAP(val); atomic16_set(haddr, val); ATOMIC_MMU_CLEANUP; - atomic_trace_st_post(env, addr, info); + atomic_trace_st_post(env, addr, oi); } #endif #else ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, target_ulong addr, ABI_TYPE val, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, PAGE_READ | PAGE_WRITE, retaddr); ABI_TYPE ret; - uint16_t info = atomic_trace_rmw_pre(env, addr, oi); + atomic_trace_rmw_pre(env, addr, oi); ret = qatomic_xchg__nocheck(haddr, BSWAP(val)); ATOMIC_MMU_CLEANUP; - atomic_trace_rmw_post(env, addr, info); + atomic_trace_rmw_post(env, addr, oi); return BSWAP(ret); } #define GEN_ATOMIC_HELPER(X) \ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ - ABI_TYPE val, TCGMemOpIdx oi, uintptr_t retaddr) \ + ABI_TYPE val, MemOpIdx oi, uintptr_t retaddr) \ { \ DATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, \ PAGE_READ | PAGE_WRITE, retaddr); \ DATA_TYPE ret; \ - uint16_t info = atomic_trace_rmw_pre(env, addr, oi); \ + atomic_trace_rmw_pre(env, addr, oi); \ ret = qatomic_##X(haddr, BSWAP(val)); \ ATOMIC_MMU_CLEANUP; \ - atomic_trace_rmw_post(env, addr, info); \ + atomic_trace_rmw_post(env, addr, oi); \ return BSWAP(ret); \ } @@ -304,12 +303,12 @@ GEN_ATOMIC_HELPER(xor_fetch) */ #define GEN_ATOMIC_HELPER_FN(X, FN, XDATA_TYPE, RET) \ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ - ABI_TYPE xval, TCGMemOpIdx oi, uintptr_t retaddr) \ + ABI_TYPE xval, MemOpIdx oi, uintptr_t retaddr) \ { \ XDATA_TYPE *haddr = atomic_mmu_lookup(env, addr, oi, DATA_SIZE, \ PAGE_READ | PAGE_WRITE, retaddr); \ XDATA_TYPE ldo, ldn, old, new, val = xval; \ - uint16_t info = atomic_trace_rmw_pre(env, addr, oi); \ + atomic_trace_rmw_pre(env, addr, oi); \ smp_mb(); \ ldn = qatomic_read__nocheck(haddr); \ do { \ @@ -317,7 +316,7 @@ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ ldn = qatomic_cmpxchg__nocheck(haddr, ldo, BSWAP(new)); \ } while (ldo != ldn); \ ATOMIC_MMU_CLEANUP; \ - atomic_trace_rmw_post(env, addr, info); \ + atomic_trace_rmw_post(env, addr, oi); \ return RET; \ } diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index b1e5471f94..46140ccff3 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -34,7 +34,6 @@ #include "qemu/atomic128.h" #include "exec/translate-all.h" #include "trace/trace-root.h" -#include "trace/mem.h" #include "tb-hash.h" #include "internal.h" #ifdef CONFIG_PLUGIN @@ -1749,7 +1748,7 @@ bool tlb_plugin_lookup(CPUState *cpu, target_ulong addr, int mmu_idx, * @prot may be PAGE_READ, PAGE_WRITE, or PAGE_READ|PAGE_WRITE. */ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, int size, int prot, + MemOpIdx oi, int size, int prot, uintptr_t retaddr) { size_t mmu_idx = get_mmuidx(oi); @@ -1850,7 +1849,7 @@ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr, */ typedef uint64_t FullLoadHelper(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); static inline uint64_t QEMU_ALWAYS_INLINE load_memop(const void *haddr, MemOp op) @@ -1876,7 +1875,7 @@ load_memop(const void *haddr, MemOp op) } static inline uint64_t QEMU_ALWAYS_INLINE -load_helper(CPUArchState *env, target_ulong addr, TCGMemOpIdx oi, +load_helper(CPUArchState *env, target_ulong addr, MemOpIdx oi, uintptr_t retaddr, MemOp op, bool code_read, FullLoadHelper *full_load) { @@ -1991,78 +1990,78 @@ load_helper(CPUArchState *env, target_ulong addr, TCGMemOpIdx oi, */ static uint64_t full_ldub_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { return load_helper(env, addr, oi, retaddr, MO_UB, false, full_ldub_mmu); } tcg_target_ulong helper_ret_ldub_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { return full_ldub_mmu(env, addr, oi, retaddr); } static uint64_t full_le_lduw_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { return load_helper(env, addr, oi, retaddr, MO_LEUW, false, full_le_lduw_mmu); } tcg_target_ulong helper_le_lduw_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { return full_le_lduw_mmu(env, addr, oi, retaddr); } static uint64_t full_be_lduw_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { return load_helper(env, addr, oi, retaddr, MO_BEUW, false, full_be_lduw_mmu); } tcg_target_ulong helper_be_lduw_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { return full_be_lduw_mmu(env, addr, oi, retaddr); } static uint64_t full_le_ldul_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { return load_helper(env, addr, oi, retaddr, MO_LEUL, false, full_le_ldul_mmu); } tcg_target_ulong helper_le_ldul_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { return full_le_ldul_mmu(env, addr, oi, retaddr); } static uint64_t full_be_ldul_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { return load_helper(env, addr, oi, retaddr, MO_BEUL, false, full_be_ldul_mmu); } tcg_target_ulong helper_be_ldul_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { return full_be_ldul_mmu(env, addr, oi, retaddr); } uint64_t helper_le_ldq_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { return load_helper(env, addr, oi, retaddr, MO_LEQ, false, helper_le_ldq_mmu); } uint64_t helper_be_ldq_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { return load_helper(env, addr, oi, retaddr, MO_BEQ, false, helper_be_ldq_mmu); @@ -2075,31 +2074,31 @@ uint64_t helper_be_ldq_mmu(CPUArchState *env, target_ulong addr, tcg_target_ulong helper_ret_ldsb_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { return (int8_t)helper_ret_ldub_mmu(env, addr, oi, retaddr); } tcg_target_ulong helper_le_ldsw_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { return (int16_t)helper_le_lduw_mmu(env, addr, oi, retaddr); } tcg_target_ulong helper_be_ldsw_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { return (int16_t)helper_be_lduw_mmu(env, addr, oi, retaddr); } tcg_target_ulong helper_le_ldsl_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { return (int32_t)helper_le_ldul_mmu(env, addr, oi, retaddr); } tcg_target_ulong helper_be_ldsl_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { return (int32_t)helper_be_ldul_mmu(env, addr, oi, retaddr); } @@ -2112,18 +2111,14 @@ static inline uint64_t cpu_load_helper(CPUArchState *env, abi_ptr addr, int mmu_idx, uintptr_t retaddr, MemOp op, FullLoadHelper *full_load) { - uint16_t meminfo; - TCGMemOpIdx oi; + MemOpIdx oi = make_memop_idx(op, mmu_idx); uint64_t ret; - meminfo = trace_mem_get_info(op, mmu_idx, false); - trace_guest_mem_before_exec(env_cpu(env), addr, meminfo); + trace_guest_ld_before_exec(env_cpu(env), addr, oi); - op &= ~MO_SIGN; - oi = make_memop_idx(op, mmu_idx); ret = full_load(env, addr, oi, retaddr); - qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, meminfo); + qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R); return ret; } @@ -2137,8 +2132,7 @@ uint32_t cpu_ldub_mmuidx_ra(CPUArchState *env, abi_ptr addr, int cpu_ldsb_mmuidx_ra(CPUArchState *env, abi_ptr addr, int mmu_idx, uintptr_t ra) { - return (int8_t)cpu_load_helper(env, addr, mmu_idx, ra, MO_SB, - full_ldub_mmu); + return (int8_t)cpu_ldub_mmuidx_ra(env, addr, mmu_idx, ra); } uint32_t cpu_lduw_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, @@ -2150,8 +2144,7 @@ uint32_t cpu_lduw_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, int cpu_ldsw_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, int mmu_idx, uintptr_t ra) { - return (int16_t)cpu_load_helper(env, addr, mmu_idx, ra, MO_BESW, - full_be_lduw_mmu); + return (int16_t)cpu_lduw_be_mmuidx_ra(env, addr, mmu_idx, ra); } uint32_t cpu_ldl_be_mmuidx_ra(CPUArchState *env, abi_ptr addr, @@ -2175,8 +2168,7 @@ uint32_t cpu_lduw_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, int cpu_ldsw_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, int mmu_idx, uintptr_t ra) { - return (int16_t)cpu_load_helper(env, addr, mmu_idx, ra, MO_LESW, - full_le_lduw_mmu); + return (int16_t)cpu_lduw_le_mmuidx_ra(env, addr, mmu_idx, ra); } uint32_t cpu_ldl_le_mmuidx_ra(CPUArchState *env, abi_ptr addr, @@ -2341,7 +2333,7 @@ store_helper_unaligned(CPUArchState *env, target_ulong addr, uint64_t val, uintptr_t index, index2; CPUTLBEntry *entry, *entry2; target_ulong page2, tlb_addr, tlb_addr2; - TCGMemOpIdx oi; + MemOpIdx oi; size_t size2; int i; @@ -2408,7 +2400,7 @@ store_helper_unaligned(CPUArchState *env, target_ulong addr, uint64_t val, static inline void QEMU_ALWAYS_INLINE store_helper(CPUArchState *env, target_ulong addr, uint64_t val, - TCGMemOpIdx oi, uintptr_t retaddr, MemOp op) + MemOpIdx oi, uintptr_t retaddr, MemOp op) { uintptr_t mmu_idx = get_mmuidx(oi); uintptr_t index = tlb_index(env, mmu_idx, addr); @@ -2506,43 +2498,43 @@ store_helper(CPUArchState *env, target_ulong addr, uint64_t val, void __attribute__((noinline)) helper_ret_stb_mmu(CPUArchState *env, target_ulong addr, uint8_t val, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { store_helper(env, addr, val, oi, retaddr, MO_UB); } void helper_le_stw_mmu(CPUArchState *env, target_ulong addr, uint16_t val, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { store_helper(env, addr, val, oi, retaddr, MO_LEUW); } void helper_be_stw_mmu(CPUArchState *env, target_ulong addr, uint16_t val, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { store_helper(env, addr, val, oi, retaddr, MO_BEUW); } void helper_le_stl_mmu(CPUArchState *env, target_ulong addr, uint32_t val, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { store_helper(env, addr, val, oi, retaddr, MO_LEUL); } void helper_be_stl_mmu(CPUArchState *env, target_ulong addr, uint32_t val, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { store_helper(env, addr, val, oi, retaddr, MO_BEUL); } void helper_le_stq_mmu(CPUArchState *env, target_ulong addr, uint64_t val, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { store_helper(env, addr, val, oi, retaddr, MO_LEQ); } void helper_be_stq_mmu(CPUArchState *env, target_ulong addr, uint64_t val, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { store_helper(env, addr, val, oi, retaddr, MO_BEQ); } @@ -2555,16 +2547,13 @@ static inline void QEMU_ALWAYS_INLINE cpu_store_helper(CPUArchState *env, target_ulong addr, uint64_t val, int mmu_idx, uintptr_t retaddr, MemOp op) { - TCGMemOpIdx oi; - uint16_t meminfo; + MemOpIdx oi = make_memop_idx(op, mmu_idx); - meminfo = trace_mem_get_info(op, mmu_idx, true); - trace_guest_mem_before_exec(env_cpu(env), addr, meminfo); + trace_guest_st_before_exec(env_cpu(env), addr, oi); - oi = make_memop_idx(op, mmu_idx); store_helper(env, addr, val, oi, retaddr, op); - qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, meminfo); + qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W); } void cpu_stb_mmuidx_ra(CPUArchState *env, target_ulong addr, uint32_t val, @@ -2721,49 +2710,49 @@ void cpu_stq_le_data(CPUArchState *env, target_ulong ptr, uint64_t val) /* Code access functions. */ static uint64_t full_ldub_code(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { return load_helper(env, addr, oi, retaddr, MO_8, true, full_ldub_code); } uint32_t cpu_ldub_code(CPUArchState *env, abi_ptr addr) { - TCGMemOpIdx oi = make_memop_idx(MO_UB, cpu_mmu_index(env, true)); + MemOpIdx oi = make_memop_idx(MO_UB, cpu_mmu_index(env, true)); return full_ldub_code(env, addr, oi, 0); } static uint64_t full_lduw_code(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { return load_helper(env, addr, oi, retaddr, MO_TEUW, true, full_lduw_code); } uint32_t cpu_lduw_code(CPUArchState *env, abi_ptr addr) { - TCGMemOpIdx oi = make_memop_idx(MO_TEUW, cpu_mmu_index(env, true)); + MemOpIdx oi = make_memop_idx(MO_TEUW, cpu_mmu_index(env, true)); return full_lduw_code(env, addr, oi, 0); } static uint64_t full_ldl_code(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { return load_helper(env, addr, oi, retaddr, MO_TEUL, true, full_ldl_code); } uint32_t cpu_ldl_code(CPUArchState *env, abi_ptr addr) { - TCGMemOpIdx oi = make_memop_idx(MO_TEUL, cpu_mmu_index(env, true)); + MemOpIdx oi = make_memop_idx(MO_TEUL, cpu_mmu_index(env, true)); return full_ldl_code(env, addr, oi, 0); } static uint64_t full_ldq_code(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr) + MemOpIdx oi, uintptr_t retaddr) { return load_helper(env, addr, oi, retaddr, MO_TEQ, true, full_ldq_code); } uint64_t cpu_ldq_code(CPUArchState *env, abi_ptr addr) { - TCGMemOpIdx oi = make_memop_idx(MO_TEQ, cpu_mmu_index(env, true)); + MemOpIdx oi = make_memop_idx(MO_TEQ, cpu_mmu_index(env, true)); return full_ldq_code(env, addr, oi, 0); } diff --git a/accel/tcg/plugin-gen.c b/accel/tcg/plugin-gen.c index 88e25c6df9..f5fd5f279c 100644 --- a/accel/tcg/plugin-gen.c +++ b/accel/tcg/plugin-gen.c @@ -45,7 +45,6 @@ #include "qemu/osdep.h" #include "tcg/tcg.h" #include "tcg/tcg-op.h" -#include "trace/mem.h" #include "exec/exec-all.h" #include "exec/plugin-gen.h" #include "exec/translator.h" @@ -211,9 +210,9 @@ static void gen_mem_wrapped(enum plugin_gen_cb type, const union mem_gen_fn *f, TCGv addr, uint32_t info, bool is_mem) { - int wr = !!(info & TRACE_MEM_ST); + enum qemu_plugin_mem_rw rw = get_plugin_meminfo_rw(info); - gen_plugin_cb_start(PLUGIN_GEN_FROM_MEM, type, wr); + gen_plugin_cb_start(PLUGIN_GEN_FROM_MEM, type, rw); if (is_mem) { f->mem_fn(addr, info); } else { diff --git a/accel/tcg/user-exec.c b/accel/tcg/user-exec.c index 8fed542622..65d3c9b286 100644 --- a/accel/tcg/user-exec.c +++ b/accel/tcg/user-exec.c @@ -27,7 +27,7 @@ #include "exec/helper-proto.h" #include "qemu/atomic128.h" #include "trace/trace-root.h" -#include "trace/mem.h" +#include "internal.h" #undef EAX #undef ECX @@ -888,111 +888,93 @@ int cpu_signal_handler(int host_signum, void *pinfo, uint32_t cpu_ldub_data(CPUArchState *env, abi_ptr ptr) { + MemOpIdx oi = make_memop_idx(MO_UB, MMU_USER_IDX); uint32_t ret; - uint16_t meminfo = trace_mem_get_info(MO_UB, MMU_USER_IDX, false); - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + trace_guest_ld_before_exec(env_cpu(env), ptr, oi); ret = ldub_p(g2h(env_cpu(env), ptr)); - qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, oi, QEMU_PLUGIN_MEM_R); return ret; } int cpu_ldsb_data(CPUArchState *env, abi_ptr ptr) { - int ret; - uint16_t meminfo = trace_mem_get_info(MO_SB, MMU_USER_IDX, false); - - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); - ret = ldsb_p(g2h(env_cpu(env), ptr)); - qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); - return ret; + return (int8_t)cpu_ldub_data(env, ptr); } uint32_t cpu_lduw_be_data(CPUArchState *env, abi_ptr ptr) { + MemOpIdx oi = make_memop_idx(MO_BEUW, MMU_USER_IDX); uint32_t ret; - uint16_t meminfo = trace_mem_get_info(MO_BEUW, MMU_USER_IDX, false); - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + trace_guest_ld_before_exec(env_cpu(env), ptr, oi); ret = lduw_be_p(g2h(env_cpu(env), ptr)); - qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, oi, QEMU_PLUGIN_MEM_R); return ret; } int cpu_ldsw_be_data(CPUArchState *env, abi_ptr ptr) { - int ret; - uint16_t meminfo = trace_mem_get_info(MO_BESW, MMU_USER_IDX, false); - - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); - ret = ldsw_be_p(g2h(env_cpu(env), ptr)); - qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); - return ret; + return (int16_t)cpu_lduw_be_data(env, ptr); } uint32_t cpu_ldl_be_data(CPUArchState *env, abi_ptr ptr) { + MemOpIdx oi = make_memop_idx(MO_BEUL, MMU_USER_IDX); uint32_t ret; - uint16_t meminfo = trace_mem_get_info(MO_BEUL, MMU_USER_IDX, false); - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + trace_guest_ld_before_exec(env_cpu(env), ptr, oi); ret = ldl_be_p(g2h(env_cpu(env), ptr)); - qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, oi, QEMU_PLUGIN_MEM_R); return ret; } uint64_t cpu_ldq_be_data(CPUArchState *env, abi_ptr ptr) { + MemOpIdx oi = make_memop_idx(MO_BEQ, MMU_USER_IDX); uint64_t ret; - uint16_t meminfo = trace_mem_get_info(MO_BEQ, MMU_USER_IDX, false); - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + trace_guest_ld_before_exec(env_cpu(env), ptr, oi); ret = ldq_be_p(g2h(env_cpu(env), ptr)); - qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, oi, QEMU_PLUGIN_MEM_R); return ret; } uint32_t cpu_lduw_le_data(CPUArchState *env, abi_ptr ptr) { + MemOpIdx oi = make_memop_idx(MO_LEUW, MMU_USER_IDX); uint32_t ret; - uint16_t meminfo = trace_mem_get_info(MO_LEUW, MMU_USER_IDX, false); - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + trace_guest_ld_before_exec(env_cpu(env), ptr, oi); ret = lduw_le_p(g2h(env_cpu(env), ptr)); - qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, oi, QEMU_PLUGIN_MEM_R); return ret; } int cpu_ldsw_le_data(CPUArchState *env, abi_ptr ptr) { - int ret; - uint16_t meminfo = trace_mem_get_info(MO_LESW, MMU_USER_IDX, false); - - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); - ret = ldsw_le_p(g2h(env_cpu(env), ptr)); - qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); - return ret; + return (int16_t)cpu_lduw_le_data(env, ptr); } uint32_t cpu_ldl_le_data(CPUArchState *env, abi_ptr ptr) { + MemOpIdx oi = make_memop_idx(MO_LEUL, MMU_USER_IDX); uint32_t ret; - uint16_t meminfo = trace_mem_get_info(MO_LEUL, MMU_USER_IDX, false); - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + trace_guest_ld_before_exec(env_cpu(env), ptr, oi); ret = ldl_le_p(g2h(env_cpu(env), ptr)); - qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, oi, QEMU_PLUGIN_MEM_R); return ret; } uint64_t cpu_ldq_le_data(CPUArchState *env, abi_ptr ptr) { + MemOpIdx oi = make_memop_idx(MO_LEQ, MMU_USER_IDX); uint64_t ret; - uint16_t meminfo = trace_mem_get_info(MO_LEQ, MMU_USER_IDX, false); - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + trace_guest_ld_before_exec(env_cpu(env), ptr, oi); ret = ldq_le_p(g2h(env_cpu(env), ptr)); - qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, oi, QEMU_PLUGIN_MEM_R); return ret; } @@ -1008,12 +990,7 @@ uint32_t cpu_ldub_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr) int cpu_ldsb_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr) { - int ret; - - set_helper_retaddr(retaddr); - ret = cpu_ldsb_data(env, ptr); - clear_helper_retaddr(); - return ret; + return (int8_t)cpu_ldub_data_ra(env, ptr, retaddr); } uint32_t cpu_lduw_be_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr) @@ -1028,12 +1005,7 @@ uint32_t cpu_lduw_be_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr) int cpu_ldsw_be_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr) { - int ret; - - set_helper_retaddr(retaddr); - ret = cpu_ldsw_be_data(env, ptr); - clear_helper_retaddr(); - return ret; + return (int16_t)cpu_lduw_be_data_ra(env, ptr, retaddr); } uint32_t cpu_ldl_be_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr) @@ -1068,12 +1040,7 @@ uint32_t cpu_lduw_le_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr) int cpu_ldsw_le_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr) { - int ret; - - set_helper_retaddr(retaddr); - ret = cpu_ldsw_le_data(env, ptr); - clear_helper_retaddr(); - return ret; + return (int16_t)cpu_lduw_le_data_ra(env, ptr, retaddr); } uint32_t cpu_ldl_le_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr) @@ -1098,65 +1065,65 @@ uint64_t cpu_ldq_le_data_ra(CPUArchState *env, abi_ptr ptr, uintptr_t retaddr) void cpu_stb_data(CPUArchState *env, abi_ptr ptr, uint32_t val) { - uint16_t meminfo = trace_mem_get_info(MO_UB, MMU_USER_IDX, true); + MemOpIdx oi = make_memop_idx(MO_UB, MMU_USER_IDX); - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + trace_guest_st_before_exec(env_cpu(env), ptr, oi); stb_p(g2h(env_cpu(env), ptr), val); - qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, oi, QEMU_PLUGIN_MEM_W); } void cpu_stw_be_data(CPUArchState *env, abi_ptr ptr, uint32_t val) { - uint16_t meminfo = trace_mem_get_info(MO_BEUW, MMU_USER_IDX, true); + MemOpIdx oi = make_memop_idx(MO_BEUW, MMU_USER_IDX); - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + trace_guest_st_before_exec(env_cpu(env), ptr, oi); stw_be_p(g2h(env_cpu(env), ptr), val); - qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, oi, QEMU_PLUGIN_MEM_W); } void cpu_stl_be_data(CPUArchState *env, abi_ptr ptr, uint32_t val) { - uint16_t meminfo = trace_mem_get_info(MO_BEUL, MMU_USER_IDX, true); + MemOpIdx oi = make_memop_idx(MO_BEUL, MMU_USER_IDX); - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + trace_guest_st_before_exec(env_cpu(env), ptr, oi); stl_be_p(g2h(env_cpu(env), ptr), val); - qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, oi, QEMU_PLUGIN_MEM_W); } void cpu_stq_be_data(CPUArchState *env, abi_ptr ptr, uint64_t val) { - uint16_t meminfo = trace_mem_get_info(MO_BEQ, MMU_USER_IDX, true); + MemOpIdx oi = make_memop_idx(MO_BEQ, MMU_USER_IDX); - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + trace_guest_st_before_exec(env_cpu(env), ptr, oi); stq_be_p(g2h(env_cpu(env), ptr), val); - qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, oi, QEMU_PLUGIN_MEM_W); } void cpu_stw_le_data(CPUArchState *env, abi_ptr ptr, uint32_t val) { - uint16_t meminfo = trace_mem_get_info(MO_LEUW, MMU_USER_IDX, true); + MemOpIdx oi = make_memop_idx(MO_LEUW, MMU_USER_IDX); - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + trace_guest_st_before_exec(env_cpu(env), ptr, oi); stw_le_p(g2h(env_cpu(env), ptr), val); - qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, oi, QEMU_PLUGIN_MEM_W); } void cpu_stl_le_data(CPUArchState *env, abi_ptr ptr, uint32_t val) { - uint16_t meminfo = trace_mem_get_info(MO_LEUL, MMU_USER_IDX, true); + MemOpIdx oi = make_memop_idx(MO_LEUL, MMU_USER_IDX); - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + trace_guest_st_before_exec(env_cpu(env), ptr, oi); stl_le_p(g2h(env_cpu(env), ptr), val); - qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, oi, QEMU_PLUGIN_MEM_W); } void cpu_stq_le_data(CPUArchState *env, abi_ptr ptr, uint64_t val) { - uint16_t meminfo = trace_mem_get_info(MO_LEQ, MMU_USER_IDX, true); + MemOpIdx oi = make_memop_idx(MO_LEQ, MMU_USER_IDX); - trace_guest_mem_before_exec(env_cpu(env), ptr, meminfo); + trace_guest_st_before_exec(env_cpu(env), ptr, oi); stq_le_p(g2h(env_cpu(env), ptr), val); - qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, meminfo); + qemu_plugin_vcpu_mem_cb(env_cpu(env), ptr, oi, QEMU_PLUGIN_MEM_W); } void cpu_stb_data_ra(CPUArchState *env, abi_ptr ptr, @@ -1261,7 +1228,7 @@ uint64_t cpu_ldq_code(CPUArchState *env, abi_ptr ptr) * @prot may be PAGE_READ, PAGE_WRITE, or PAGE_READ|PAGE_WRITE. */ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, int size, int prot, + MemOpIdx oi, int size, int prot, uintptr_t retaddr) { /* Enforce qemu required alignment. */ diff --git a/block.c b/block.c index 5ce08a79fd..45f653a88b 100644 --- a/block.c +++ b/block.c @@ -1604,16 +1604,26 @@ open_failed: return ret; } -BlockDriverState *bdrv_new_open_driver(BlockDriver *drv, const char *node_name, - int flags, Error **errp) +/* + * Create and open a block node. + * + * @options is a QDict of options to pass to the block drivers, or NULL for an + * empty set of options. The reference to the QDict belongs to the block layer + * after the call (even on failure), so if the caller intends to reuse the + * dictionary, it needs to use qobject_ref() before calling bdrv_open. + */ +BlockDriverState *bdrv_new_open_driver_opts(BlockDriver *drv, + const char *node_name, + QDict *options, int flags, + Error **errp) { BlockDriverState *bs; int ret; bs = bdrv_new(); bs->open_flags = flags; - bs->explicit_options = qdict_new(); - bs->options = qdict_new(); + bs->options = options ?: qdict_new(); + bs->explicit_options = qdict_clone_shallow(bs->options); bs->opaque = NULL; update_options_from_flags(bs->options, flags); @@ -1631,6 +1641,13 @@ BlockDriverState *bdrv_new_open_driver(BlockDriver *drv, const char *node_name, return bs; } +/* Create and open a block node. */ +BlockDriverState *bdrv_new_open_driver(BlockDriver *drv, const char *node_name, + int flags, Error **errp) +{ + return bdrv_new_open_driver_opts(drv, node_name, NULL, flags, errp); +} + QemuOptsList bdrv_runtime_opts = { .name = "bdrv_common", .head = QTAILQ_HEAD_INITIALIZER(bdrv_runtime_opts.head), @@ -5102,29 +5119,61 @@ static void bdrv_delete(BlockDriverState *bs) g_free(bs); } -BlockDriverState *bdrv_insert_node(BlockDriverState *bs, QDict *node_options, + +/* + * Replace @bs by newly created block node. + * + * @options is a QDict of options to pass to the block drivers, or NULL for an + * empty set of options. The reference to the QDict belongs to the block layer + * after the call (even on failure), so if the caller intends to reuse the + * dictionary, it needs to use qobject_ref() before calling bdrv_open. + */ +BlockDriverState *bdrv_insert_node(BlockDriverState *bs, QDict *options, int flags, Error **errp) { - BlockDriverState *new_node_bs; - Error *local_err = NULL; + ERRP_GUARD(); + int ret; + BlockDriverState *new_node_bs = NULL; + const char *drvname, *node_name; + BlockDriver *drv; + + drvname = qdict_get_try_str(options, "driver"); + if (!drvname) { + error_setg(errp, "driver is not specified"); + goto fail; + } + + drv = bdrv_find_format(drvname); + if (!drv) { + error_setg(errp, "Unknown driver: '%s'", drvname); + goto fail; + } + + node_name = qdict_get_try_str(options, "node-name"); - new_node_bs = bdrv_open(NULL, NULL, node_options, flags, errp); - if (new_node_bs == NULL) { + new_node_bs = bdrv_new_open_driver_opts(drv, node_name, options, flags, + errp); + options = NULL; /* bdrv_new_open_driver() eats options */ + if (!new_node_bs) { error_prepend(errp, "Could not create node: "); - return NULL; + goto fail; } bdrv_drained_begin(bs); - bdrv_replace_node(bs, new_node_bs, &local_err); + ret = bdrv_replace_node(bs, new_node_bs, errp); bdrv_drained_end(bs); - if (local_err) { - bdrv_unref(new_node_bs); - error_propagate(errp, local_err); - return NULL; + if (ret < 0) { + error_prepend(errp, "Could not replace node: "); + goto fail; } return new_node_bs; + +fail: + qobject_unref(options); + bdrv_unref(new_node_bs); + return NULL; } /* diff --git a/block/block-backend.c b/block/block-backend.c index 6140d133e2..ba2b5ebb10 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -1986,6 +1986,12 @@ uint32_t blk_get_max_transfer(BlockBackend *blk) return ROUND_DOWN(max, blk_get_request_alignment(blk)); } +int blk_get_max_hw_iov(BlockBackend *blk) +{ + return MIN_NON_ZERO(blk->root->bs->bl.max_hw_iov, + blk->root->bs->bl.max_iov); +} + int blk_get_max_iov(BlockBackend *blk) { return blk->root->bs->bl.max_iov; diff --git a/block/file-posix.c b/block/file-posix.c index c62e42743d..53be0bdc1b 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -1273,7 +1273,7 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp) ret = hdev_get_max_segments(s->fd, &st); if (ret > 0) { - bs->bl.max_iov = ret; + bs->bl.max_hw_iov = ret; } } } diff --git a/block/io.c b/block/io.c index 18d345a87a..bb0a254def 100644 --- a/block/io.c +++ b/block/io.c @@ -136,6 +136,7 @@ static void bdrv_merge_limits(BlockLimits *dst, const BlockLimits *src) dst->min_mem_alignment = MAX(dst->min_mem_alignment, src->min_mem_alignment); dst->max_iov = MIN_NON_ZERO(dst->max_iov, src->max_iov); + dst->max_hw_iov = MIN_NON_ZERO(dst->max_hw_iov, src->max_hw_iov); } typedef struct BdrvRefreshLimitsState { diff --git a/hw/scsi/scsi-generic.c b/hw/scsi/scsi-generic.c index 665baf900e..0306ccc7b1 100644 --- a/hw/scsi/scsi-generic.c +++ b/hw/scsi/scsi-generic.c @@ -180,7 +180,7 @@ static int scsi_handle_inquiry_reply(SCSIGenericReq *r, SCSIDevice *s, int len) page = r->req.cmd.buf[2]; if (page == 0xb0) { uint64_t max_transfer = blk_get_max_hw_transfer(s->conf.blk); - uint32_t max_iov = blk_get_max_iov(s->conf.blk); + uint32_t max_iov = blk_get_max_hw_iov(s->conf.blk); assert(max_transfer); max_transfer = MIN_NON_ZERO(max_transfer, max_iov * qemu_real_host_page_size) diff --git a/include/block/block.h b/include/block/block.h index 740038a892..e5dd22b034 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -383,6 +383,10 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options, const char *bdref_key, Error **errp); BlockDriverState *bdrv_open(const char *filename, const char *reference, QDict *options, int flags, Error **errp); +BlockDriverState *bdrv_new_open_driver_opts(BlockDriver *drv, + const char *node_name, + QDict *options, int flags, + Error **errp); BlockDriverState *bdrv_new_open_driver(BlockDriver *drv, const char *node_name, int flags, Error **errp); BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue, @@ -751,9 +755,7 @@ bool bdrv_drain_poll(BlockDriverState *bs, bool recursive, * bdrv_drained_begin: * * Begin a quiesced section for exclusive access to the BDS, by disabling - * external request sources including NBD server and device model. Note that - * this doesn't block timers or coroutines from submitting more requests, which - * means block_job_pause is still necessary. + * external request sources including NBD server, block jobs, and device model. * * This function can be recursive. */ diff --git a/include/block/block_int.h b/include/block/block_int.h index ffe86068d4..f4c75e8ba9 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -718,6 +718,13 @@ typedef struct BlockLimits { */ uint64_t max_hw_transfer; + /* Maximal 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 */ size_t min_mem_alignment; diff --git a/include/exec/memop.h b/include/exec/memop.h index 529d07b02d..04264ffd6b 100644 --- a/include/exec/memop.h +++ b/include/exec/memop.h @@ -19,11 +19,15 @@ typedef enum MemOp { MO_16 = 1, MO_32 = 2, MO_64 = 3, - MO_SIZE = 3, /* Mask for the above. */ + MO_128 = 4, + MO_256 = 5, + MO_512 = 6, + MO_1024 = 7, + MO_SIZE = 0x07, /* Mask for the above. */ - MO_SIGN = 4, /* Sign-extended, otherwise zero-extended. */ + MO_SIGN = 0x08, /* Sign-extended, otherwise zero-extended. */ - MO_BSWAP = 8, /* Host reverse endian. */ + MO_BSWAP = 0x10, /* Host reverse endian. */ #ifdef HOST_WORDS_BIGENDIAN MO_LE = MO_BSWAP, MO_BE = 0, @@ -59,8 +63,8 @@ typedef enum MemOp { * - an alignment to a specified size, which may be more or less than * the access size (MO_ALIGN_x where 'x' is a size in bytes); */ - MO_ASHIFT = 4, - MO_AMASK = 7 << MO_ASHIFT, + MO_ASHIFT = 5, + MO_AMASK = 0x7 << MO_ASHIFT, #ifdef NEED_CPU_H #ifdef TARGET_ALIGNED_ONLY MO_ALIGN = 0, diff --git a/include/exec/memopidx.h b/include/exec/memopidx.h new file mode 100644 index 0000000000..83bce97874 --- /dev/null +++ b/include/exec/memopidx.h @@ -0,0 +1,55 @@ +/* + * Combine the MemOp and mmu_idx parameters into a single value. + * + * Authors: + * Richard Henderson <rth@twiddle.net> + * + * 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 EXEC_MEMOPIDX_H +#define EXEC_MEMOPIDX_H 1 + +#include "exec/memop.h" + +typedef uint32_t MemOpIdx; + +/** + * make_memop_idx + * @op: memory operation + * @idx: mmu index + * + * Encode these values into a single parameter. + */ +static inline MemOpIdx make_memop_idx(MemOp op, unsigned idx) +{ +#ifdef CONFIG_DEBUG_TCG + assert(idx <= 15); +#endif + return (op << 4) | idx; +} + +/** + * get_memop + * @oi: combined op/idx parameter + * + * Extract the memory operation from the combined value. + */ +static inline MemOp get_memop(MemOpIdx oi) +{ + return oi >> 4; +} + +/** + * get_mmuidx + * @oi: combined op/idx parameter + * + * Extract the mmu index from the combined value. + */ +static inline unsigned get_mmuidx(MemOpIdx oi) +{ + return oi & 15; +} + +#endif diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h index bc864564ce..b7d5bc1200 100644 --- a/include/hw/core/cpu.h +++ b/include/hw/core/cpu.h @@ -131,7 +131,6 @@ struct CPUClass { ObjectClass *(*class_by_name)(const char *cpu_model); void (*parse_features)(const char *typename, char *str, Error **errp); - int reset_dump_flags; bool (*has_work)(CPUState *cpu); int (*memory_rw_debug)(CPUState *cpu, vaddr addr, uint8_t *buf, int len, bool is_write); @@ -149,9 +148,6 @@ struct CPUClass { void (*disas_set_info)(CPUState *cpu, disassemble_info *info); const char *deprecation_note; - /* Keep non-pointer data at the end to minimize holes. */ - int gdb_num_core_regs; - bool gdb_stop_before_watchpoint; struct AccelCPUClass *accel_cpu; /* when system emulation is not available, this pointer is NULL */ @@ -165,6 +161,13 @@ struct CPUClass { * class data that depends on the accelerator, see accel/accel-common.c. */ void (*init_accel_cpu)(struct AccelCPUClass *accel_cpu, CPUClass *cc); + + /* + * Keep non-pointer data at the end to minimize holes. + */ + int reset_dump_flags; + int gdb_num_core_regs; + bool gdb_stop_before_watchpoint; }; /* diff --git a/include/qemu/plugin.h b/include/qemu/plugin.h index 9a8438f683..b3172b147f 100644 --- a/include/qemu/plugin.h +++ b/include/qemu/plugin.h @@ -12,6 +12,7 @@ #include "qemu/error-report.h" #include "qemu/queue.h" #include "qemu/option.h" +#include "exec/memopidx.h" /* * Events that plugins can subscribe to. @@ -36,6 +37,25 @@ enum qemu_plugin_event { struct qemu_plugin_desc; typedef QTAILQ_HEAD(, qemu_plugin_desc) QemuPluginList; +/* + * Construct a qemu_plugin_meminfo_t. + */ +static inline qemu_plugin_meminfo_t +make_plugin_meminfo(MemOpIdx oi, enum qemu_plugin_mem_rw rw) +{ + return oi | (rw << 16); +} + +/* + * Extract the memory operation direction from a qemu_plugin_meminfo_t. + * Other portions may be extracted via get_memop and get_mmuidx. + */ +static inline enum qemu_plugin_mem_rw +get_plugin_meminfo_rw(qemu_plugin_meminfo_t i) +{ + return i >> 16; +} + #ifdef CONFIG_PLUGIN extern QemuOptsList qemu_plugin_opts; @@ -180,7 +200,8 @@ qemu_plugin_vcpu_syscall(CPUState *cpu, int64_t num, uint64_t a1, uint64_t a6, uint64_t a7, uint64_t a8); void qemu_plugin_vcpu_syscall_ret(CPUState *cpu, int64_t num, int64_t ret); -void qemu_plugin_vcpu_mem_cb(CPUState *cpu, uint64_t vaddr, uint32_t meminfo); +void qemu_plugin_vcpu_mem_cb(CPUState *cpu, uint64_t vaddr, + MemOpIdx oi, enum qemu_plugin_mem_rw rw); void qemu_plugin_flush_cb(void); @@ -244,7 +265,8 @@ void qemu_plugin_vcpu_syscall_ret(CPUState *cpu, int64_t num, int64_t ret) { } static inline void qemu_plugin_vcpu_mem_cb(CPUState *cpu, uint64_t vaddr, - uint32_t meminfo) + MemOpIdx oi, + enum qemu_plugin_mem_rw rw) { } static inline void qemu_plugin_flush_cb(void) diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h index 29d4fdbf63..82bae55161 100644 --- a/include/sysemu/block-backend.h +++ b/include/sysemu/block-backend.h @@ -211,6 +211,7 @@ uint32_t blk_get_request_alignment(BlockBackend *blk); uint32_t blk_get_max_transfer(BlockBackend *blk); uint64_t blk_get_max_hw_transfer(BlockBackend *blk); int blk_get_max_iov(BlockBackend *blk); +int blk_get_max_hw_iov(BlockBackend *blk); void blk_set_guest_block_size(BlockBackend *blk, int align); void *blk_try_blockalign(BlockBackend *blk, size_t size); void *blk_blockalign(BlockBackend *blk, size_t size); diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h index 44ccd86f3e..ba13ab1151 100644 --- a/include/tcg/tcg.h +++ b/include/tcg/tcg.h @@ -27,6 +27,7 @@ #include "cpu.h" #include "exec/memop.h" +#include "exec/memopidx.h" #include "qemu/bitops.h" #include "qemu/plugin.h" #include "qemu/queue.h" @@ -1147,44 +1148,6 @@ static inline size_t tcg_current_code_size(TCGContext *s) return tcg_ptr_byte_diff(s->code_ptr, s->code_buf); } -/* Combine the MemOp and mmu_idx parameters into a single value. */ -typedef uint32_t TCGMemOpIdx; - -/** - * make_memop_idx - * @op: memory operation - * @idx: mmu index - * - * Encode these values into a single parameter. - */ -static inline TCGMemOpIdx make_memop_idx(MemOp op, unsigned idx) -{ - tcg_debug_assert(idx <= 15); - return (op << 4) | idx; -} - -/** - * get_memop - * @oi: combined op/idx parameter - * - * Extract the memory operation from the combined value. - */ -static inline MemOp get_memop(TCGMemOpIdx oi) -{ - return oi >> 4; -} - -/** - * get_mmuidx - * @oi: combined op/idx parameter - * - * Extract the mmu index from the combined value. - */ -static inline unsigned get_mmuidx(TCGMemOpIdx oi) -{ - return oi & 15; -} - /** * tcg_qemu_tb_exec: * @env: pointer to CPUArchState for the CPU @@ -1272,52 +1235,64 @@ uint64_t dup_const(unsigned vece, uint64_t c); : (qemu_build_not_reached_always(), 0)) \ : dup_const(VECE, C)) +#if TARGET_LONG_BITS == 64 +# define dup_const_tl dup_const +#else +# define dup_const_tl(VECE, C) \ + (__builtin_constant_p(VECE) \ + ? ( (VECE) == MO_8 ? 0x01010101ul * (uint8_t)(C) \ + : (VECE) == MO_16 ? 0x00010001ul * (uint16_t)(C) \ + : (VECE) == MO_32 ? 0x00000001ul * (uint32_t)(C) \ + : (qemu_build_not_reached_always(), 0)) \ + : (target_long)dup_const(VECE, C)) +#endif + /* * Memory helpers that will be used by TCG generated code. */ #ifdef CONFIG_SOFTMMU /* Value zero-extended to tcg register size. */ tcg_target_ulong helper_ret_ldub_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); tcg_target_ulong helper_le_lduw_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); tcg_target_ulong helper_le_ldul_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); uint64_t helper_le_ldq_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); tcg_target_ulong helper_be_lduw_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); tcg_target_ulong helper_be_ldul_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); uint64_t helper_be_ldq_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); /* Value sign-extended to tcg register size. */ tcg_target_ulong helper_ret_ldsb_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); tcg_target_ulong helper_le_ldsw_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); tcg_target_ulong helper_le_ldsl_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); tcg_target_ulong helper_be_ldsw_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); tcg_target_ulong helper_be_ldsl_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); void helper_ret_stb_mmu(CPUArchState *env, target_ulong addr, uint8_t val, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); void helper_le_stw_mmu(CPUArchState *env, target_ulong addr, uint16_t val, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); void helper_le_stl_mmu(CPUArchState *env, target_ulong addr, uint32_t val, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); void helper_le_stq_mmu(CPUArchState *env, target_ulong addr, uint64_t val, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); void helper_be_stw_mmu(CPUArchState *env, target_ulong addr, uint16_t val, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); void helper_be_stl_mmu(CPUArchState *env, target_ulong addr, uint32_t val, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); void helper_be_stq_mmu(CPUArchState *env, target_ulong addr, uint64_t val, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); /* Temporary aliases until backends are converted. */ #ifdef TARGET_WORDS_BIGENDIAN @@ -1345,30 +1320,30 @@ void helper_be_stq_mmu(CPUArchState *env, target_ulong addr, uint64_t val, uint32_t cpu_atomic_cmpxchgb_mmu(CPUArchState *env, target_ulong addr, uint32_t cmpv, uint32_t newv, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); uint32_t cpu_atomic_cmpxchgw_le_mmu(CPUArchState *env, target_ulong addr, uint32_t cmpv, uint32_t newv, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); uint32_t cpu_atomic_cmpxchgl_le_mmu(CPUArchState *env, target_ulong addr, uint32_t cmpv, uint32_t newv, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); uint64_t cpu_atomic_cmpxchgq_le_mmu(CPUArchState *env, target_ulong addr, uint64_t cmpv, uint64_t newv, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); uint32_t cpu_atomic_cmpxchgw_be_mmu(CPUArchState *env, target_ulong addr, uint32_t cmpv, uint32_t newv, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); uint32_t cpu_atomic_cmpxchgl_be_mmu(CPUArchState *env, target_ulong addr, uint32_t cmpv, uint32_t newv, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); uint64_t cpu_atomic_cmpxchgq_be_mmu(CPUArchState *env, target_ulong addr, uint64_t cmpv, uint64_t newv, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); #define GEN_ATOMIC_HELPER(NAME, TYPE, SUFFIX) \ TYPE cpu_atomic_ ## NAME ## SUFFIX ## _mmu \ (CPUArchState *env, target_ulong addr, TYPE val, \ - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); #ifdef CONFIG_ATOMIC64 #define GEN_ATOMIC_HELPER_ALL(NAME) \ @@ -1415,19 +1390,19 @@ GEN_ATOMIC_HELPER_ALL(xchg) Int128 cpu_atomic_cmpxchgo_le_mmu(CPUArchState *env, target_ulong addr, Int128 cmpv, Int128 newv, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); Int128 cpu_atomic_cmpxchgo_be_mmu(CPUArchState *env, target_ulong addr, Int128 cmpv, Int128 newv, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); Int128 cpu_atomic_ldo_le_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); Int128 cpu_atomic_ldo_be_mmu(CPUArchState *env, target_ulong addr, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); void cpu_atomic_sto_le_mmu(CPUArchState *env, target_ulong addr, Int128 val, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); void cpu_atomic_sto_be_mmu(CPUArchState *env, target_ulong addr, Int128 val, - TCGMemOpIdx oi, uintptr_t retaddr); + MemOpIdx oi, uintptr_t retaddr); #ifdef CONFIG_DEBUG_TCG void tcg_assert_listed_vecop(TCGOpcode); diff --git a/meson.build b/meson.build index 7b596fdcd9..99a0a3e689 100644 --- a/meson.build +++ b/meson.build @@ -268,8 +268,6 @@ if not get_option('tcg').disabled() tcg_arch = 'tci' elif config_host['ARCH'] == 'sparc64' tcg_arch = 'sparc' - elif config_host['ARCH'] == 's390x' - tcg_arch = 's390' elif config_host['ARCH'] in ['x86_64', 'x32'] tcg_arch = 'i386' elif config_host['ARCH'] == 'ppc64' diff --git a/plugins/api.c b/plugins/api.c index acff9ce8ac..b143b09ce9 100644 --- a/plugins/api.c +++ b/plugins/api.c @@ -45,7 +45,6 @@ #include "qemu/plugin-memory.h" #include "hw/boards.h" #endif -#include "trace/mem.h" /* Uninstall and Reset handlers */ @@ -246,22 +245,25 @@ const char *qemu_plugin_insn_symbol(const struct qemu_plugin_insn *insn) unsigned qemu_plugin_mem_size_shift(qemu_plugin_meminfo_t info) { - return info & TRACE_MEM_SZ_SHIFT_MASK; + MemOp op = get_memop(info); + return op & MO_SIZE; } bool qemu_plugin_mem_is_sign_extended(qemu_plugin_meminfo_t info) { - return !!(info & TRACE_MEM_SE); + MemOp op = get_memop(info); + return op & MO_SIGN; } bool qemu_plugin_mem_is_big_endian(qemu_plugin_meminfo_t info) { - return !!(info & TRACE_MEM_BE); + MemOp op = get_memop(info); + return (op & MO_BSWAP) == MO_BE; } bool qemu_plugin_mem_is_store(qemu_plugin_meminfo_t info) { - return !!(info & TRACE_MEM_ST); + return get_plugin_meminfo_rw(info) & QEMU_PLUGIN_MEM_W; } /* @@ -277,11 +279,12 @@ struct qemu_plugin_hwaddr *qemu_plugin_get_hwaddr(qemu_plugin_meminfo_t info, { #ifdef CONFIG_SOFTMMU CPUState *cpu = current_cpu; - unsigned int mmu_idx = info >> TRACE_MEM_MMU_SHIFT; - hwaddr_info.is_store = info & TRACE_MEM_ST; + unsigned int mmu_idx = get_mmuidx(info); + enum qemu_plugin_mem_rw rw = get_plugin_meminfo_rw(info); + hwaddr_info.is_store = (rw & QEMU_PLUGIN_MEM_W) != 0; if (!tlb_plugin_lookup(cpu, vaddr, mmu_idx, - info & TRACE_MEM_ST, &hwaddr_info)) { + hwaddr_info.is_store, &hwaddr_info)) { error_report("invalid use of qemu_plugin_get_hwaddr"); return NULL; } diff --git a/plugins/core.c b/plugins/core.c index 6b2490f973..792262da08 100644 --- a/plugins/core.c +++ b/plugins/core.c @@ -27,7 +27,6 @@ #include "exec/helper-proto.h" #include "tcg/tcg.h" #include "tcg/tcg-op.h" -#include "trace/mem.h" /* mem_info macros */ #include "plugin.h" #include "qemu/compiler.h" @@ -446,7 +445,8 @@ void exec_inline_op(struct qemu_plugin_dyn_cb *cb) } } -void qemu_plugin_vcpu_mem_cb(CPUState *cpu, uint64_t vaddr, uint32_t info) +void qemu_plugin_vcpu_mem_cb(CPUState *cpu, uint64_t vaddr, + MemOpIdx oi, enum qemu_plugin_mem_rw rw) { GArray *arr = cpu->plugin_mem_cbs; size_t i; @@ -457,14 +457,14 @@ void qemu_plugin_vcpu_mem_cb(CPUState *cpu, uint64_t vaddr, uint32_t info) for (i = 0; i < arr->len; i++) { struct qemu_plugin_dyn_cb *cb = &g_array_index(arr, struct qemu_plugin_dyn_cb, i); - int w = !!(info & TRACE_MEM_ST) + 1; - if (!(w & cb->rw)) { + if (!(rw & cb->rw)) { break; } switch (cb->type) { case PLUGIN_CB_REGULAR: - cb->f.vcpu_mem(cpu->cpu_index, info, vaddr, cb->userp); + cb->f.vcpu_mem(cpu->cpu_index, make_plugin_meminfo(oi, rw), + vaddr, cb->userp); break; case PLUGIN_CB_INLINE: exec_inline_op(cb); diff --git a/storage-daemon/qemu-storage-daemon.c b/storage-daemon/qemu-storage-daemon.c index fc8b150629..10a1a33761 100644 --- a/storage-daemon/qemu-storage-daemon.c +++ b/storage-daemon/qemu-storage-daemon.c @@ -98,10 +98,12 @@ static void help(void) " export the specified block node over NBD\n" " (requires --nbd-server)\n" "\n" +#ifdef CONFIG_FUSE " --export [type=]fuse,id=<id>,node-name=<node-name>,mountpoint=<file>\n" " [,growable=on|off][,writable=on|off]\n" " export the specified block node over FUSE\n" "\n" +#endif /* CONFIG_FUSE */ " --monitor [chardev=]name[,mode=control][,pretty[=on|off]]\n" " configure a QMP monitor\n" "\n" diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index 19445b3c94..c5af779006 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -531,8 +531,8 @@ uint64_t HELPER(paired_cmpxchg64_le)(CPUARMState *env, uint64_t addr, clear_helper_retaddr(); #else int mem_idx = cpu_mmu_index(env, false); - TCGMemOpIdx oi0 = make_memop_idx(MO_LEQ | MO_ALIGN_16, mem_idx); - TCGMemOpIdx oi1 = make_memop_idx(MO_LEQ, mem_idx); + MemOpIdx oi0 = make_memop_idx(MO_LEQ | MO_ALIGN_16, mem_idx); + MemOpIdx oi1 = make_memop_idx(MO_LEQ, mem_idx); o0 = helper_le_ldq_mmu(env, addr + 0, oi0, ra); o1 = helper_le_ldq_mmu(env, addr + 8, oi1, ra); @@ -555,7 +555,7 @@ uint64_t HELPER(paired_cmpxchg64_le_parallel)(CPUARMState *env, uint64_t addr, uintptr_t ra = GETPC(); bool success; int mem_idx; - TCGMemOpIdx oi; + MemOpIdx oi; assert(HAVE_CMPXCHG128); @@ -601,8 +601,8 @@ uint64_t HELPER(paired_cmpxchg64_be)(CPUARMState *env, uint64_t addr, clear_helper_retaddr(); #else int mem_idx = cpu_mmu_index(env, false); - TCGMemOpIdx oi0 = make_memop_idx(MO_BEQ | MO_ALIGN_16, mem_idx); - TCGMemOpIdx oi1 = make_memop_idx(MO_BEQ, mem_idx); + MemOpIdx oi0 = make_memop_idx(MO_BEQ | MO_ALIGN_16, mem_idx); + MemOpIdx oi1 = make_memop_idx(MO_BEQ, mem_idx); o1 = helper_be_ldq_mmu(env, addr + 0, oi0, ra); o0 = helper_be_ldq_mmu(env, addr + 8, oi1, ra); @@ -625,7 +625,7 @@ uint64_t HELPER(paired_cmpxchg64_be_parallel)(CPUARMState *env, uint64_t addr, uintptr_t ra = GETPC(); bool success; int mem_idx; - TCGMemOpIdx oi; + MemOpIdx oi; assert(HAVE_CMPXCHG128); @@ -651,7 +651,7 @@ void HELPER(casp_le_parallel)(CPUARMState *env, uint32_t rs, uint64_t addr, Int128 oldv, cmpv, newv; uintptr_t ra = GETPC(); int mem_idx; - TCGMemOpIdx oi; + MemOpIdx oi; assert(HAVE_CMPXCHG128); @@ -672,7 +672,7 @@ void HELPER(casp_be_parallel)(CPUARMState *env, uint32_t rs, uint64_t addr, Int128 oldv, cmpv, newv; uintptr_t ra = GETPC(); int mem_idx; - TCGMemOpIdx oi; + MemOpIdx oi; assert(HAVE_CMPXCHG128); diff --git a/target/arm/m_helper.c b/target/arm/m_helper.c index 47903b3dc3..62aa12c9d8 100644 --- a/target/arm/m_helper.c +++ b/target/arm/m_helper.c @@ -1930,7 +1930,7 @@ static bool do_v7m_function_return(ARMCPU *cpu) { bool threadmode, spsel; - TCGMemOpIdx oi; + MemOpIdx oi; ARMMMUIdx mmu_idx; uint32_t *frame_sp_p; uint32_t frameptr; diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index ab6b346e35..717afd481c 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -1045,7 +1045,7 @@ static void read_vec_element(DisasContext *s, TCGv_i64 tcg_dest, int srcidx, int element, MemOp memop) { int vect_off = vec_reg_offset(s, srcidx, element, memop & MO_SIZE); - switch (memop) { + switch ((unsigned)memop) { case MO_8: tcg_gen_ld8u_i64(tcg_dest, cpu_env, vect_off); break; diff --git a/target/i386/tcg/mem_helper.c b/target/i386/tcg/mem_helper.c index 2da3cd14b6..0fd696f9c1 100644 --- a/target/i386/tcg/mem_helper.c +++ b/target/i386/tcg/mem_helper.c @@ -67,7 +67,7 @@ void helper_cmpxchg8b(CPUX86State *env, target_ulong a0) { uintptr_t ra = GETPC(); int mem_idx = cpu_mmu_index(env, false); - TCGMemOpIdx oi = make_memop_idx(MO_TEQ, mem_idx); + MemOpIdx oi = make_memop_idx(MO_TEQ, mem_idx); oldv = cpu_atomic_cmpxchgq_le_mmu(env, a0, cmpv, newv, oi, ra); } @@ -136,7 +136,7 @@ void helper_cmpxchg16b(CPUX86State *env, target_ulong a0) Int128 newv = int128_make128(env->regs[R_EBX], env->regs[R_ECX]); int mem_idx = cpu_mmu_index(env, false); - TCGMemOpIdx oi = make_memop_idx(MO_TEQ | MO_ALIGN_16, mem_idx); + MemOpIdx oi = make_memop_idx(MO_TEQ | MO_ALIGN_16, mem_idx); Int128 oldv = cpu_atomic_cmpxchgo_le_mmu(env, a0, cmpv, newv, oi, ra); if (int128_eq(oldv, cmpv)) { diff --git a/target/m68k/op_helper.c b/target/m68k/op_helper.c index 5d624838ae..c1bf73b6f9 100644 --- a/target/m68k/op_helper.c +++ b/target/m68k/op_helper.c @@ -775,7 +775,7 @@ static void do_cas2l(CPUM68KState *env, uint32_t regs, uint32_t a1, uint32_t a2, uintptr_t ra = GETPC(); #if defined(CONFIG_ATOMIC64) int mmu_idx = cpu_mmu_index(env, 0); - TCGMemOpIdx oi = make_memop_idx(MO_BEQ, mmu_idx); + MemOpIdx oi = make_memop_idx(MO_BEQ, mmu_idx); #endif if (parallel) { diff --git a/target/mips/tcg/msa_helper.c b/target/mips/tcg/msa_helper.c index 04af54f66d..167d9a591c 100644 --- a/target/mips/tcg/msa_helper.c +++ b/target/mips/tcg/msa_helper.c @@ -8211,9 +8211,9 @@ void helper_msa_ffint_u_df(CPUMIPSState *env, uint32_t df, uint32_t wd, #define DF_ELEMENTS(df) (MSA_WRLEN / DF_BITS(df)) #if !defined(CONFIG_USER_ONLY) -#define MEMOP_IDX(DF) \ - TCGMemOpIdx oi = make_memop_idx(MO_TE | DF | MO_UNALN, \ - cpu_mmu_index(env, false)); +#define MEMOP_IDX(DF) \ + MemOpIdx oi = make_memop_idx(MO_TE | DF | MO_UNALN, \ + cpu_mmu_index(env, false)); #else #define MEMOP_IDX(DF) #endif diff --git a/target/s390x/tcg/mem_helper.c b/target/s390x/tcg/mem_helper.c index 0bf775a37d..75f6735545 100644 --- a/target/s390x/tcg/mem_helper.c +++ b/target/s390x/tcg/mem_helper.c @@ -239,7 +239,7 @@ static void do_access_memset(CPUS390XState *env, vaddr vaddr, char *haddr, g_assert(haddr); memset(haddr, byte, size); #else - TCGMemOpIdx oi = make_memop_idx(MO_UB, mmu_idx); + MemOpIdx oi = make_memop_idx(MO_UB, mmu_idx); int i; if (likely(haddr)) { @@ -282,7 +282,7 @@ static uint8_t do_access_get_byte(CPUS390XState *env, vaddr vaddr, char **haddr, #ifdef CONFIG_USER_ONLY return ldub_p(*haddr + offset); #else - TCGMemOpIdx oi = make_memop_idx(MO_UB, mmu_idx); + MemOpIdx oi = make_memop_idx(MO_UB, mmu_idx); uint8_t byte; if (likely(*haddr)) { @@ -316,7 +316,7 @@ static void do_access_set_byte(CPUS390XState *env, vaddr vaddr, char **haddr, #ifdef CONFIG_USER_ONLY stb_p(*haddr + offset, byte); #else - TCGMemOpIdx oi = make_memop_idx(MO_UB, mmu_idx); + MemOpIdx oi = make_memop_idx(MO_UB, mmu_idx); if (likely(*haddr)) { stb_p(*haddr + offset, byte); @@ -1804,7 +1804,7 @@ void HELPER(cdsg_parallel)(CPUS390XState *env, uint64_t addr, Int128 cmpv = int128_make128(env->regs[r1 + 1], env->regs[r1]); Int128 newv = int128_make128(env->regs[r3 + 1], env->regs[r3]); int mem_idx; - TCGMemOpIdx oi; + MemOpIdx oi; Int128 oldv; bool fail; @@ -1884,7 +1884,7 @@ static uint32_t do_csst(CPUS390XState *env, uint32_t r3, uint64_t a1, uint32_t *haddr = g2h(env_cpu(env), a1); ov = qatomic_cmpxchg__nocheck(haddr, cv, nv); #else - TCGMemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mem_idx); + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mem_idx); ov = cpu_atomic_cmpxchgl_be_mmu(env, a1, cv, nv, oi, ra); #endif } else { @@ -1904,7 +1904,7 @@ static uint32_t do_csst(CPUS390XState *env, uint32_t r3, uint64_t a1, if (parallel) { #ifdef CONFIG_ATOMIC64 - TCGMemOpIdx oi = make_memop_idx(MO_TEQ | MO_ALIGN, mem_idx); + MemOpIdx oi = make_memop_idx(MO_TEQ | MO_ALIGN, mem_idx); ov = cpu_atomic_cmpxchgq_be_mmu(env, a1, cv, nv, oi, ra); #else /* Note that we asserted !parallel above. */ @@ -1940,7 +1940,7 @@ static uint32_t do_csst(CPUS390XState *env, uint32_t r3, uint64_t a1, cpu_stq_data_ra(env, a1 + 0, int128_gethi(nv), ra); cpu_stq_data_ra(env, a1 + 8, int128_getlo(nv), ra); } else if (HAVE_CMPXCHG128) { - TCGMemOpIdx oi = make_memop_idx(MO_TEQ | MO_ALIGN_16, mem_idx); + MemOpIdx oi = make_memop_idx(MO_TEQ | MO_ALIGN_16, mem_idx); ov = cpu_atomic_cmpxchgo_be_mmu(env, a1, cv, nv, oi, ra); cc = !int128_eq(ov, cv); } else { @@ -1979,7 +1979,7 @@ static uint32_t do_csst(CPUS390XState *env, uint32_t r3, uint64_t a1, cpu_stq_data_ra(env, a2 + 0, svh, ra); cpu_stq_data_ra(env, a2 + 8, svl, ra); } else if (HAVE_ATOMIC128) { - TCGMemOpIdx oi = make_memop_idx(MO_TEQ | MO_ALIGN_16, mem_idx); + MemOpIdx oi = make_memop_idx(MO_TEQ | MO_ALIGN_16, mem_idx); Int128 sv = int128_make128(svl, svh); cpu_atomic_sto_be_mmu(env, a2, sv, oi, ra); } else { @@ -2497,7 +2497,7 @@ uint64_t HELPER(lpq_parallel)(CPUS390XState *env, uint64_t addr) uintptr_t ra = GETPC(); uint64_t hi, lo; int mem_idx; - TCGMemOpIdx oi; + MemOpIdx oi; Int128 v; assert(HAVE_ATOMIC128); @@ -2528,7 +2528,7 @@ void HELPER(stpq_parallel)(CPUS390XState *env, uint64_t addr, { uintptr_t ra = GETPC(); int mem_idx; - TCGMemOpIdx oi; + MemOpIdx oi; Int128 v; assert(HAVE_ATOMIC128); diff --git a/target/s390x/tcg/translate_vx.c.inc b/target/s390x/tcg/translate_vx.c.inc index 0afa46e463..28bf5a23b6 100644 --- a/target/s390x/tcg/translate_vx.c.inc +++ b/target/s390x/tcg/translate_vx.c.inc @@ -67,7 +67,7 @@ static void read_vec_element_i64(TCGv_i64 dst, uint8_t reg, uint8_t enr, { const int offs = vec_reg_offset(reg, enr, memop & MO_SIZE); - switch (memop) { + switch ((unsigned)memop) { case ES_8: tcg_gen_ld8u_i64(dst, cpu_env, offs); break; diff --git a/target/sparc/ldst_helper.c b/target/sparc/ldst_helper.c index 22327d7d72..abe2889d27 100644 --- a/target/sparc/ldst_helper.c +++ b/target/sparc/ldst_helper.c @@ -1318,7 +1318,7 @@ uint64_t helper_ld_asi(CPUSPARCState *env, target_ulong addr, case ASI_SNF: case ASI_SNFL: { - TCGMemOpIdx oi; + MemOpIdx oi; int idx = (env->pstate & PS_PRIV ? (asi & 1 ? MMU_KERNEL_SECONDARY_IDX : MMU_KERNEL_IDX) : (asi & 1 ? MMU_USER_SECONDARY_IDX : MMU_USER_IDX)); diff --git a/tcg/aarch64/tcg-target.c.inc b/tcg/aarch64/tcg-target.c.inc index 5924977b42..5edca8d44d 100644 --- a/tcg/aarch64/tcg-target.c.inc +++ b/tcg/aarch64/tcg-target.c.inc @@ -1545,9 +1545,9 @@ static void tcg_out_cltz(TCGContext *s, TCGType ext, TCGReg d, #include "../tcg-ldst.c.inc" /* helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr, - * TCGMemOpIdx oi, uintptr_t ra) + * MemOpIdx oi, uintptr_t ra) */ -static void * const qemu_ld_helpers[4] = { +static void * const qemu_ld_helpers[MO_SIZE + 1] = { [MO_8] = helper_ret_ldub_mmu, #ifdef HOST_WORDS_BIGENDIAN [MO_16] = helper_be_lduw_mmu, @@ -1561,10 +1561,10 @@ static void * const qemu_ld_helpers[4] = { }; /* helper signature: helper_ret_st_mmu(CPUState *env, target_ulong addr, - * uintxx_t val, TCGMemOpIdx oi, + * uintxx_t val, MemOpIdx oi, * uintptr_t ra) */ -static void * const qemu_st_helpers[4] = { +static void * const qemu_st_helpers[MO_SIZE + 1] = { [MO_8] = helper_ret_stb_mmu, #ifdef HOST_WORDS_BIGENDIAN [MO_16] = helper_be_stw_mmu, @@ -1586,7 +1586,7 @@ static inline void tcg_out_adr(TCGContext *s, TCGReg rd, const void *target) static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) { - TCGMemOpIdx oi = lb->oi; + MemOpIdx oi = lb->oi; MemOp opc = get_memop(oi); MemOp size = opc & MO_SIZE; @@ -1611,7 +1611,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) { - TCGMemOpIdx oi = lb->oi; + MemOpIdx oi = lb->oi; MemOp opc = get_memop(oi); MemOp size = opc & MO_SIZE; @@ -1629,7 +1629,7 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) return true; } -static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi, +static void add_qemu_ldst_label(TCGContext *s, bool is_ld, MemOpIdx oi, TCGType ext, TCGReg data_reg, TCGReg addr_reg, tcg_insn_unit *raddr, tcg_insn_unit *label_ptr) { @@ -1778,7 +1778,7 @@ static void tcg_out_qemu_st_direct(TCGContext *s, MemOp memop, } static void tcg_out_qemu_ld(TCGContext *s, TCGReg data_reg, TCGReg addr_reg, - TCGMemOpIdx oi, TCGType ext) + MemOpIdx oi, TCGType ext) { MemOp memop = get_memop(oi); const TCGType otype = TARGET_LONG_BITS == 64 ? TCG_TYPE_I64 : TCG_TYPE_I32; @@ -1803,7 +1803,7 @@ static void tcg_out_qemu_ld(TCGContext *s, TCGReg data_reg, TCGReg addr_reg, } static void tcg_out_qemu_st(TCGContext *s, TCGReg data_reg, TCGReg addr_reg, - TCGMemOpIdx oi) + MemOpIdx oi) { MemOp memop = get_memop(oi); const TCGType otype = TARGET_LONG_BITS == 64 ? TCG_TYPE_I64 : TCG_TYPE_I32; diff --git a/tcg/arm/tcg-target.c.inc b/tcg/arm/tcg-target.c.inc index d25e68b36b..633b8a37ba 100644 --- a/tcg/arm/tcg-target.c.inc +++ b/tcg/arm/tcg-target.c.inc @@ -1437,7 +1437,7 @@ static void tcg_out_vldst(TCGContext *s, ARMInsn insn, /* helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr, * int mmu_idx, uintptr_t ra) */ -static void * const qemu_ld_helpers[8] = { +static void * const qemu_ld_helpers[MO_SSIZE + 1] = { [MO_UB] = helper_ret_ldub_mmu, [MO_SB] = helper_ret_ldsb_mmu, #ifdef HOST_WORDS_BIGENDIAN @@ -1458,7 +1458,7 @@ static void * const qemu_ld_helpers[8] = { /* helper signature: helper_ret_st_mmu(CPUState *env, target_ulong addr, * uintxx_t val, int mmu_idx, uintptr_t ra) */ -static void * const qemu_st_helpers[4] = { +static void * const qemu_st_helpers[MO_SIZE + 1] = { [MO_8] = helper_ret_stb_mmu, #ifdef HOST_WORDS_BIGENDIAN [MO_16] = helper_be_stw_mmu, @@ -1632,7 +1632,7 @@ static TCGReg tcg_out_tlb_read(TCGContext *s, TCGReg addrlo, TCGReg addrhi, /* Record the context of a call to the out of line helper code for the slow path for a load or store, so that we can later generate the correct helper code. */ -static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi, +static void add_qemu_ldst_label(TCGContext *s, bool is_ld, MemOpIdx oi, TCGReg datalo, TCGReg datahi, TCGReg addrlo, TCGReg addrhi, tcg_insn_unit *raddr, tcg_insn_unit *label_ptr) @@ -1652,7 +1652,7 @@ static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi, static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) { TCGReg argreg, datalo, datahi; - TCGMemOpIdx oi = lb->oi; + MemOpIdx oi = lb->oi; MemOp opc = get_memop(oi); void *func; @@ -1716,7 +1716,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) { TCGReg argreg, datalo, datahi; - TCGMemOpIdx oi = lb->oi; + MemOpIdx oi = lb->oi; MemOp opc = get_memop(oi); if (!reloc_pc24(lb->label_ptr[0], tcg_splitwx_to_rx(s->code_ptr))) { @@ -1846,7 +1846,7 @@ static void tcg_out_qemu_ld_direct(TCGContext *s, MemOp opc, TCGReg datalo, static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is64) { TCGReg addrlo, datalo, datahi, addrhi __attribute__((unused)); - TCGMemOpIdx oi; + MemOpIdx oi; MemOp opc; #ifdef CONFIG_SOFTMMU int mem_index; @@ -1952,7 +1952,7 @@ static void tcg_out_qemu_st_direct(TCGContext *s, MemOp opc, TCGReg datalo, static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is64) { TCGReg addrlo, datalo, datahi, addrhi __attribute__((unused)); - TCGMemOpIdx oi; + MemOpIdx oi; MemOp opc; #ifdef CONFIG_SOFTMMU int mem_index; diff --git a/tcg/i386/tcg-target.c.inc b/tcg/i386/tcg-target.c.inc index 997510109d..84b109bb84 100644 --- a/tcg/i386/tcg-target.c.inc +++ b/tcg/i386/tcg-target.c.inc @@ -1611,7 +1611,7 @@ static void tcg_out_nopn(TCGContext *s, int n) /* helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr, * int mmu_idx, uintptr_t ra) */ -static void * const qemu_ld_helpers[16] = { +static void * const qemu_ld_helpers[(MO_SIZE | MO_BSWAP) + 1] = { [MO_UB] = helper_ret_ldub_mmu, [MO_LEUW] = helper_le_lduw_mmu, [MO_LEUL] = helper_le_ldul_mmu, @@ -1624,7 +1624,7 @@ static void * const qemu_ld_helpers[16] = { /* helper signature: helper_ret_st_mmu(CPUState *env, target_ulong addr, * uintxx_t val, int mmu_idx, uintptr_t ra) */ -static void * const qemu_st_helpers[16] = { +static void * const qemu_st_helpers[(MO_SIZE | MO_BSWAP) + 1] = { [MO_UB] = helper_ret_stb_mmu, [MO_LEUW] = helper_le_stw_mmu, [MO_LEUL] = helper_le_stl_mmu, @@ -1741,7 +1741,7 @@ static inline void tcg_out_tlb_load(TCGContext *s, TCGReg addrlo, TCGReg addrhi, * for a load or store, so that we can later generate the correct helper code */ static void add_qemu_ldst_label(TCGContext *s, bool is_ld, bool is_64, - TCGMemOpIdx oi, + MemOpIdx oi, TCGReg datalo, TCGReg datahi, TCGReg addrlo, TCGReg addrhi, tcg_insn_unit *raddr, @@ -1768,7 +1768,7 @@ static void add_qemu_ldst_label(TCGContext *s, bool is_ld, bool is_64, */ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l) { - TCGMemOpIdx oi = l->oi; + MemOpIdx oi = l->oi; MemOp opc = get_memop(oi); TCGReg data_reg; tcg_insn_unit **label_ptr = &l->label_ptr[0]; @@ -1853,7 +1853,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l) */ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l) { - TCGMemOpIdx oi = l->oi; + MemOpIdx oi = l->oi; MemOp opc = get_memop(oi); MemOp s_bits = opc & MO_SIZE; tcg_insn_unit **label_ptr = &l->label_ptr[0]; @@ -2054,7 +2054,7 @@ static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is64) { TCGReg datalo, datahi, addrlo; TCGReg addrhi __attribute__((unused)); - TCGMemOpIdx oi; + MemOpIdx oi; MemOp opc; #if defined(CONFIG_SOFTMMU) int mem_index; @@ -2143,7 +2143,7 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is64) { TCGReg datalo, datahi, addrlo; TCGReg addrhi __attribute__((unused)); - TCGMemOpIdx oi; + MemOpIdx oi; MemOp opc; #if defined(CONFIG_SOFTMMU) int mem_index; diff --git a/tcg/mips/tcg-target.c.inc b/tcg/mips/tcg-target.c.inc index 41ffa28394..d8f6914f03 100644 --- a/tcg/mips/tcg-target.c.inc +++ b/tcg/mips/tcg-target.c.inc @@ -1017,7 +1017,7 @@ static void tcg_out_call(TCGContext *s, const tcg_insn_unit *arg) #if defined(CONFIG_SOFTMMU) #include "../tcg-ldst.c.inc" -static void * const qemu_ld_helpers[16] = { +static void * const qemu_ld_helpers[(MO_SSIZE | MO_BSWAP) + 1] = { [MO_UB] = helper_ret_ldub_mmu, [MO_SB] = helper_ret_ldsb_mmu, [MO_LEUW] = helper_le_lduw_mmu, @@ -1034,7 +1034,7 @@ static void * const qemu_ld_helpers[16] = { #endif }; -static void * const qemu_st_helpers[16] = { +static void * const qemu_st_helpers[(MO_SIZE | MO_BSWAP) + 1] = { [MO_UB] = helper_ret_stb_mmu, [MO_LEUW] = helper_le_stw_mmu, [MO_LEUL] = helper_le_stl_mmu, @@ -1120,7 +1120,7 @@ QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) < -32768); * Clobbers TMP0, TMP1, TMP2, TMP3. */ static void tcg_out_tlb_load(TCGContext *s, TCGReg base, TCGReg addrl, - TCGReg addrh, TCGMemOpIdx oi, + TCGReg addrh, MemOpIdx oi, tcg_insn_unit *label_ptr[2], bool is_load) { MemOp opc = get_memop(oi); @@ -1196,7 +1196,7 @@ static void tcg_out_tlb_load(TCGContext *s, TCGReg base, TCGReg addrl, tcg_out_opc_reg(s, ALIAS_PADD, base, TCG_TMP2, addrl); } -static void add_qemu_ldst_label(TCGContext *s, int is_ld, TCGMemOpIdx oi, +static void add_qemu_ldst_label(TCGContext *s, int is_ld, MemOpIdx oi, TCGType ext, TCGReg datalo, TCGReg datahi, TCGReg addrlo, TCGReg addrhi, @@ -1221,7 +1221,7 @@ static void add_qemu_ldst_label(TCGContext *s, int is_ld, TCGMemOpIdx oi, static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l) { const tcg_insn_unit *tgt_rx = tcg_splitwx_to_rx(s->code_ptr); - TCGMemOpIdx oi = l->oi; + MemOpIdx oi = l->oi; MemOp opc = get_memop(oi); TCGReg v0; int i; @@ -1275,7 +1275,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l) static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l) { const tcg_insn_unit *tgt_rx = tcg_splitwx_to_rx(s->code_ptr); - TCGMemOpIdx oi = l->oi; + MemOpIdx oi = l->oi; MemOp opc = get_memop(oi); MemOp s_bits = opc & MO_SIZE; int i; @@ -1434,7 +1434,7 @@ static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is_64) { TCGReg addr_regl, addr_regh __attribute__((unused)); TCGReg data_regl, data_regh; - TCGMemOpIdx oi; + MemOpIdx oi; MemOp opc; #if defined(CONFIG_SOFTMMU) tcg_insn_unit *label_ptr[2]; @@ -1536,7 +1536,7 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is_64) { TCGReg addr_regl, addr_regh __attribute__((unused)); TCGReg data_regl, data_regh; - TCGMemOpIdx oi; + MemOpIdx oi; MemOp opc; #if defined(CONFIG_SOFTMMU) tcg_insn_unit *label_ptr[2]; diff --git a/tcg/optimize.c b/tcg/optimize.c index 9876ac52a8..c239c3bd07 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -1023,7 +1023,7 @@ void tcg_optimize(TCGContext *s) CASE_OP_32_64(qemu_ld): { - TCGMemOpIdx oi = op->args[nb_oargs + nb_iargs]; + MemOpIdx oi = op->args[nb_oargs + nb_iargs]; MemOp mop = get_memop(oi); if (!(mop & MO_SIGN)) { mask = (2ULL << ((8 << (mop & MO_SIZE)) - 1)) - 1; diff --git a/tcg/ppc/tcg-target.c.inc b/tcg/ppc/tcg-target.c.inc index 5e1fac914a..3e4ca2be88 100644 --- a/tcg/ppc/tcg-target.c.inc +++ b/tcg/ppc/tcg-target.c.inc @@ -1931,7 +1931,7 @@ static void tcg_out_call(TCGContext *s, const tcg_insn_unit *target) #endif } -static const uint32_t qemu_ldx_opc[16] = { +static const uint32_t qemu_ldx_opc[(MO_SSIZE + MO_BSWAP) + 1] = { [MO_UB] = LBZX, [MO_UW] = LHZX, [MO_UL] = LWZX, @@ -1944,7 +1944,7 @@ static const uint32_t qemu_ldx_opc[16] = { [MO_BSWAP | MO_Q] = LDBRX, }; -static const uint32_t qemu_stx_opc[16] = { +static const uint32_t qemu_stx_opc[(MO_SIZE + MO_BSWAP) + 1] = { [MO_UB] = STBX, [MO_UW] = STHX, [MO_UL] = STWX, @@ -1965,7 +1965,7 @@ static const uint32_t qemu_exts_opc[4] = { /* helper signature: helper_ld_mmu(CPUState *env, target_ulong addr, * int mmu_idx, uintptr_t ra) */ -static void * const qemu_ld_helpers[16] = { +static void * const qemu_ld_helpers[(MO_SIZE | MO_BSWAP) + 1] = { [MO_UB] = helper_ret_ldub_mmu, [MO_LEUW] = helper_le_lduw_mmu, [MO_LEUL] = helper_le_ldul_mmu, @@ -1978,7 +1978,7 @@ static void * const qemu_ld_helpers[16] = { /* helper signature: helper_st_mmu(CPUState *env, target_ulong addr, * uintxx_t val, int mmu_idx, uintptr_t ra) */ -static void * const qemu_st_helpers[16] = { +static void * const qemu_st_helpers[(MO_SIZE | MO_BSWAP) + 1] = { [MO_UB] = helper_ret_stb_mmu, [MO_LEUW] = helper_le_stw_mmu, [MO_LEUL] = helper_le_stl_mmu, @@ -2103,7 +2103,7 @@ static TCGReg tcg_out_tlb_read(TCGContext *s, MemOp opc, /* Record the context of a call to the out of line helper code for the slow path for a load or store, so that we can later generate the correct helper code. */ -static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi, +static void add_qemu_ldst_label(TCGContext *s, bool is_ld, MemOpIdx oi, TCGReg datalo_reg, TCGReg datahi_reg, TCGReg addrlo_reg, TCGReg addrhi_reg, tcg_insn_unit *raddr, tcg_insn_unit *lptr) @@ -2122,7 +2122,7 @@ static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi, static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) { - TCGMemOpIdx oi = lb->oi; + MemOpIdx oi = lb->oi; MemOp opc = get_memop(oi); TCGReg hi, lo, arg = TCG_REG_R3; @@ -2169,7 +2169,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) { - TCGMemOpIdx oi = lb->oi; + MemOpIdx oi = lb->oi; MemOp opc = get_memop(oi); MemOp s_bits = opc & MO_SIZE; TCGReg hi, lo, arg = TCG_REG_R3; @@ -2233,7 +2233,7 @@ static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is_64) { TCGReg datalo, datahi, addrlo, rbase; TCGReg addrhi __attribute__((unused)); - TCGMemOpIdx oi; + MemOpIdx oi; MemOp opc, s_bits; #ifdef CONFIG_SOFTMMU int mem_index; @@ -2308,7 +2308,7 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is_64) { TCGReg datalo, datahi, addrlo, rbase; TCGReg addrhi __attribute__((unused)); - TCGMemOpIdx oi; + MemOpIdx oi; MemOp opc, s_bits; #ifdef CONFIG_SOFTMMU int mem_index; diff --git a/tcg/riscv/tcg-target.c.inc b/tcg/riscv/tcg-target.c.inc index dc8d8f1de2..9b13a46fb4 100644 --- a/tcg/riscv/tcg-target.c.inc +++ b/tcg/riscv/tcg-target.c.inc @@ -850,9 +850,9 @@ static void tcg_out_mb(TCGContext *s, TCGArg a0) #include "../tcg-ldst.c.inc" /* helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr, - * TCGMemOpIdx oi, uintptr_t ra) + * MemOpIdx oi, uintptr_t ra) */ -static void * const qemu_ld_helpers[8] = { +static void * const qemu_ld_helpers[MO_SSIZE + 1] = { [MO_UB] = helper_ret_ldub_mmu, [MO_SB] = helper_ret_ldsb_mmu, #ifdef HOST_WORDS_BIGENDIAN @@ -875,10 +875,10 @@ static void * const qemu_ld_helpers[8] = { }; /* helper signature: helper_ret_st_mmu(CPUState *env, target_ulong addr, - * uintxx_t val, TCGMemOpIdx oi, + * uintxx_t val, MemOpIdx oi, * uintptr_t ra) */ -static void * const qemu_st_helpers[4] = { +static void * const qemu_st_helpers[MO_SIZE + 1] = { [MO_8] = helper_ret_stb_mmu, #ifdef HOST_WORDS_BIGENDIAN [MO_16] = helper_be_stw_mmu, @@ -906,7 +906,7 @@ static void tcg_out_goto(TCGContext *s, const tcg_insn_unit *target) } static void tcg_out_tlb_load(TCGContext *s, TCGReg addrl, - TCGReg addrh, TCGMemOpIdx oi, + TCGReg addrh, MemOpIdx oi, tcg_insn_unit **label_ptr, bool is_load) { MemOp opc = get_memop(oi); @@ -959,7 +959,7 @@ static void tcg_out_tlb_load(TCGContext *s, TCGReg addrl, tcg_out_opc_reg(s, OPC_ADD, TCG_REG_TMP0, TCG_REG_TMP2, addrl); } -static void add_qemu_ldst_label(TCGContext *s, int is_ld, TCGMemOpIdx oi, +static void add_qemu_ldst_label(TCGContext *s, int is_ld, MemOpIdx oi, TCGType ext, TCGReg datalo, TCGReg datahi, TCGReg addrlo, TCGReg addrhi, @@ -980,7 +980,7 @@ static void add_qemu_ldst_label(TCGContext *s, int is_ld, TCGMemOpIdx oi, static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l) { - TCGMemOpIdx oi = l->oi; + MemOpIdx oi = l->oi; MemOp opc = get_memop(oi); TCGReg a0 = tcg_target_call_iarg_regs[0]; TCGReg a1 = tcg_target_call_iarg_regs[1]; @@ -1012,7 +1012,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l) static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l) { - TCGMemOpIdx oi = l->oi; + MemOpIdx oi = l->oi; MemOp opc = get_memop(oi); MemOp s_bits = opc & MO_SIZE; TCGReg a0 = tcg_target_call_iarg_regs[0]; @@ -1104,7 +1104,7 @@ static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is_64) { TCGReg addr_regl, addr_regh __attribute__((unused)); TCGReg data_regl, data_regh; - TCGMemOpIdx oi; + MemOpIdx oi; MemOp opc; #if defined(CONFIG_SOFTMMU) tcg_insn_unit *label_ptr[1]; @@ -1170,7 +1170,7 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is_64) { TCGReg addr_regl, addr_regh __attribute__((unused)); TCGReg data_regl, data_regh; - TCGMemOpIdx oi; + MemOpIdx oi; MemOp opc; #if defined(CONFIG_SOFTMMU) tcg_insn_unit *label_ptr[1]; diff --git a/tcg/s390/tcg-target-con-set.h b/tcg/s390x/tcg-target-con-set.h index 31985e4903..426dd92e51 100644 --- a/tcg/s390/tcg-target-con-set.h +++ b/tcg/s390x/tcg-target-con-set.h @@ -13,13 +13,20 @@ C_O0_I1(r) C_O0_I2(L, L) C_O0_I2(r, r) C_O0_I2(r, ri) +C_O0_I2(v, r) C_O1_I1(r, L) C_O1_I1(r, r) +C_O1_I1(v, r) +C_O1_I1(v, v) +C_O1_I1(v, vr) C_O1_I2(r, 0, ri) C_O1_I2(r, 0, rI) C_O1_I2(r, 0, rJ) C_O1_I2(r, r, ri) C_O1_I2(r, rZ, r) +C_O1_I2(v, v, r) +C_O1_I2(v, v, v) +C_O1_I3(v, v, v, v) C_O1_I4(r, r, ri, r, 0) C_O1_I4(r, r, ri, rI, 0) C_O2_I2(b, a, 0, r) diff --git a/tcg/s390/tcg-target-con-str.h b/tcg/s390x/tcg-target-con-str.h index 892d8f8c06..8bb0358ae5 100644 --- a/tcg/s390/tcg-target-con-str.h +++ b/tcg/s390x/tcg-target-con-str.h @@ -10,6 +10,7 @@ */ REGS('r', ALL_GENERAL_REGS) REGS('L', ALL_GENERAL_REGS & ~SOFTMMU_RESERVE_REGS) +REGS('v', ALL_VECTOR_REGS) /* * A (single) even/odd pair for division. * TODO: Add something to the register allocator to allow diff --git a/tcg/s390/tcg-target.c.inc b/tcg/s390x/tcg-target.c.inc index b82cf19f09..8938c446c8 100644 --- a/tcg/s390/tcg-target.c.inc +++ b/tcg/s390x/tcg-target.c.inc @@ -43,6 +43,8 @@ #define TCG_CT_CONST_ZERO 0x800 #define ALL_GENERAL_REGS MAKE_64BIT_MASK(0, 16) +#define ALL_VECTOR_REGS MAKE_64BIT_MASK(32, 32) + /* * For softmmu, we need to avoid conflicts with the first 3 * argument registers to perform the tlb lookup, and to call @@ -66,7 +68,7 @@ We don't need this when we have pc-relative loads with the general instructions extension facility. */ #define TCG_REG_TB TCG_REG_R12 -#define USE_REG_TB (!(s390_facilities & FACILITY_GEN_INST_EXT)) +#define USE_REG_TB (!HAVE_FACILITY(GEN_INST_EXT)) #ifndef CONFIG_SOFTMMU #define TCG_GUEST_BASE_REG TCG_REG_R13 @@ -263,13 +265,66 @@ typedef enum S390Opcode { RX_STC = 0x42, RX_STH = 0x40, + VRIa_VGBM = 0xe744, + VRIa_VREPI = 0xe745, + VRIb_VGM = 0xe746, + VRIc_VREP = 0xe74d, + + VRRa_VLC = 0xe7de, + VRRa_VLP = 0xe7df, + VRRa_VLR = 0xe756, + VRRc_VA = 0xe7f3, + VRRc_VCEQ = 0xe7f8, /* we leave the m5 cs field 0 */ + VRRc_VCH = 0xe7fb, /* " */ + VRRc_VCHL = 0xe7f9, /* " */ + VRRc_VERLLV = 0xe773, + VRRc_VESLV = 0xe770, + VRRc_VESRAV = 0xe77a, + VRRc_VESRLV = 0xe778, + VRRc_VML = 0xe7a2, + VRRc_VMN = 0xe7fe, + VRRc_VMNL = 0xe7fc, + VRRc_VMX = 0xe7ff, + VRRc_VMXL = 0xe7fd, + VRRc_VN = 0xe768, + VRRc_VNC = 0xe769, + VRRc_VNO = 0xe76b, + VRRc_VO = 0xe76a, + VRRc_VOC = 0xe76f, + VRRc_VPKS = 0xe797, /* we leave the m5 cs field 0 */ + VRRc_VS = 0xe7f7, + VRRa_VUPH = 0xe7d7, + VRRa_VUPL = 0xe7d6, + VRRc_VX = 0xe76d, + VRRe_VSEL = 0xe78d, + VRRf_VLVGP = 0xe762, + + VRSa_VERLL = 0xe733, + VRSa_VESL = 0xe730, + VRSa_VESRA = 0xe73a, + VRSa_VESRL = 0xe738, + VRSb_VLVG = 0xe722, + VRSc_VLGV = 0xe721, + + VRX_VL = 0xe706, + VRX_VLLEZ = 0xe704, + VRX_VLREP = 0xe705, + VRX_VST = 0xe70e, + VRX_VSTEF = 0xe70b, + VRX_VSTEG = 0xe70a, + NOP = 0x0707, } S390Opcode; #ifdef CONFIG_DEBUG_TCG static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = { - "%r0", "%r1", "%r2", "%r3", "%r4", "%r5", "%r6", "%r7", - "%r8", "%r9", "%r10" "%r11" "%r12" "%r13" "%r14" "%r15" + "%r0", "%r1", "%r2", "%r3", "%r4", "%r5", "%r6", "%r7", + "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15", + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + "%v0", "%v1", "%v2", "%v3", "%v4", "%v5", "%v6", "%v7", + "%v8", "%v9", "%v10", "%v11", "%v12", "%v13", "%v14", "%v15", + "%v16", "%v17", "%v18", "%v19", "%v20", "%v21", "%v22", "%v23", + "%v24", "%v25", "%v26", "%v27", "%v28", "%v29", "%v30", "%v31", }; #endif @@ -295,6 +350,32 @@ static const int tcg_target_reg_alloc_order[] = { TCG_REG_R4, TCG_REG_R3, TCG_REG_R2, + + /* V8-V15 are call saved, and omitted. */ + TCG_REG_V0, + TCG_REG_V1, + TCG_REG_V2, + TCG_REG_V3, + TCG_REG_V4, + TCG_REG_V5, + TCG_REG_V6, + TCG_REG_V7, + TCG_REG_V16, + TCG_REG_V17, + TCG_REG_V18, + TCG_REG_V19, + TCG_REG_V20, + TCG_REG_V21, + TCG_REG_V22, + TCG_REG_V23, + TCG_REG_V24, + TCG_REG_V25, + TCG_REG_V26, + TCG_REG_V27, + TCG_REG_V28, + TCG_REG_V29, + TCG_REG_V30, + TCG_REG_V31, }; static const int tcg_target_call_iarg_regs[] = { @@ -350,7 +431,7 @@ static const uint8_t tcg_cond_to_ltr_cond[] = { }; #ifdef CONFIG_SOFTMMU -static void * const qemu_ld_helpers[16] = { +static void * const qemu_ld_helpers[(MO_SSIZE | MO_BSWAP) + 1] = { [MO_UB] = helper_ret_ldub_mmu, [MO_SB] = helper_ret_ldsb_mmu, [MO_LEUW] = helper_le_lduw_mmu, @@ -365,7 +446,7 @@ static void * const qemu_ld_helpers[16] = { [MO_BEQ] = helper_be_ldq_mmu, }; -static void * const qemu_st_helpers[16] = { +static void * const qemu_st_helpers[(MO_SIZE | MO_BSWAP) + 1] = { [MO_UB] = helper_ret_stb_mmu, [MO_LEUW] = helper_le_stw_mmu, [MO_LEUL] = helper_le_stl_mmu, @@ -377,7 +458,17 @@ static void * const qemu_st_helpers[16] = { #endif static const tcg_insn_unit *tb_ret_addr; -uint64_t s390_facilities; +uint64_t s390_facilities[3]; + +static inline bool is_general_reg(TCGReg r) +{ + return r <= TCG_REG_R15; +} + +static inline bool is_vector_reg(TCGReg r) +{ + return r >= TCG_REG_V0 && r <= TCG_REG_V31; +} static bool patch_reloc(tcg_insn_unit *src_rw, int type, intptr_t value, intptr_t addend) @@ -496,6 +587,138 @@ static void tcg_out_insn_RSY(TCGContext *s, S390Opcode op, TCGReg r1, #define tcg_out_insn_RX tcg_out_insn_RS #define tcg_out_insn_RXY tcg_out_insn_RSY +static int RXB(TCGReg v1, TCGReg v2, TCGReg v3, TCGReg v4) +{ + /* + * Shift bit 4 of each regno to its corresponding bit of RXB. + * RXB itself begins at bit 8 of the instruction so 8 - 4 = 4 + * is the left-shift of the 4th operand. + */ + return ((v1 & 0x10) << (4 + 3)) + | ((v2 & 0x10) << (4 + 2)) + | ((v3 & 0x10) << (4 + 1)) + | ((v4 & 0x10) << (4 + 0)); +} + +static void tcg_out_insn_VRIa(TCGContext *s, S390Opcode op, + TCGReg v1, uint16_t i2, int m3) +{ + tcg_debug_assert(is_vector_reg(v1)); + tcg_out16(s, (op & 0xff00) | ((v1 & 0xf) << 4)); + tcg_out16(s, i2); + tcg_out16(s, (op & 0x00ff) | RXB(v1, 0, 0, 0) | (m3 << 12)); +} + +static void tcg_out_insn_VRIb(TCGContext *s, S390Opcode op, + TCGReg v1, uint8_t i2, uint8_t i3, int m4) +{ + tcg_debug_assert(is_vector_reg(v1)); + tcg_out16(s, (op & 0xff00) | ((v1 & 0xf) << 4)); + tcg_out16(s, (i2 << 8) | (i3 & 0xff)); + tcg_out16(s, (op & 0x00ff) | RXB(v1, 0, 0, 0) | (m4 << 12)); +} + +static void tcg_out_insn_VRIc(TCGContext *s, S390Opcode op, + TCGReg v1, uint16_t i2, TCGReg v3, int m4) +{ + tcg_debug_assert(is_vector_reg(v1)); + tcg_debug_assert(is_vector_reg(v3)); + tcg_out16(s, (op & 0xff00) | ((v1 & 0xf) << 4) | (v3 & 0xf)); + tcg_out16(s, i2); + tcg_out16(s, (op & 0x00ff) | RXB(v1, 0, v3, 0) | (m4 << 12)); +} + +static void tcg_out_insn_VRRa(TCGContext *s, S390Opcode op, + TCGReg v1, TCGReg v2, int m3) +{ + tcg_debug_assert(is_vector_reg(v1)); + tcg_debug_assert(is_vector_reg(v2)); + tcg_out16(s, (op & 0xff00) | ((v1 & 0xf) << 4) | (v2 & 0xf)); + tcg_out32(s, (op & 0x00ff) | RXB(v1, v2, 0, 0) | (m3 << 12)); +} + +static void tcg_out_insn_VRRc(TCGContext *s, S390Opcode op, + TCGReg v1, TCGReg v2, TCGReg v3, int m4) +{ + tcg_debug_assert(is_vector_reg(v1)); + tcg_debug_assert(is_vector_reg(v2)); + tcg_debug_assert(is_vector_reg(v3)); + tcg_out16(s, (op & 0xff00) | ((v1 & 0xf) << 4) | (v2 & 0xf)); + tcg_out16(s, v3 << 12); + tcg_out16(s, (op & 0x00ff) | RXB(v1, v2, v3, 0) | (m4 << 12)); +} + +static void tcg_out_insn_VRRe(TCGContext *s, S390Opcode op, + TCGReg v1, TCGReg v2, TCGReg v3, TCGReg v4) +{ + tcg_debug_assert(is_vector_reg(v1)); + tcg_debug_assert(is_vector_reg(v2)); + tcg_debug_assert(is_vector_reg(v3)); + tcg_debug_assert(is_vector_reg(v4)); + tcg_out16(s, (op & 0xff00) | ((v1 & 0xf) << 4) | (v2 & 0xf)); + tcg_out16(s, v3 << 12); + tcg_out16(s, (op & 0x00ff) | RXB(v1, v2, v3, v4) | (v4 << 12)); +} + +static void tcg_out_insn_VRRf(TCGContext *s, S390Opcode op, + TCGReg v1, TCGReg r2, TCGReg r3) +{ + tcg_debug_assert(is_vector_reg(v1)); + tcg_debug_assert(is_general_reg(r2)); + tcg_debug_assert(is_general_reg(r3)); + tcg_out16(s, (op & 0xff00) | ((v1 & 0xf) << 4) | r2); + tcg_out16(s, r3 << 12); + tcg_out16(s, (op & 0x00ff) | RXB(v1, 0, 0, 0)); +} + +static void tcg_out_insn_VRSa(TCGContext *s, S390Opcode op, TCGReg v1, + intptr_t d2, TCGReg b2, TCGReg v3, int m4) +{ + tcg_debug_assert(is_vector_reg(v1)); + tcg_debug_assert(d2 >= 0 && d2 <= 0xfff); + tcg_debug_assert(is_general_reg(b2)); + tcg_debug_assert(is_vector_reg(v3)); + tcg_out16(s, (op & 0xff00) | ((v1 & 0xf) << 4) | (v3 & 0xf)); + tcg_out16(s, b2 << 12 | d2); + tcg_out16(s, (op & 0x00ff) | RXB(v1, 0, v3, 0) | (m4 << 12)); +} + +static void tcg_out_insn_VRSb(TCGContext *s, S390Opcode op, TCGReg v1, + intptr_t d2, TCGReg b2, TCGReg r3, int m4) +{ + tcg_debug_assert(is_vector_reg(v1)); + tcg_debug_assert(d2 >= 0 && d2 <= 0xfff); + tcg_debug_assert(is_general_reg(b2)); + tcg_debug_assert(is_general_reg(r3)); + tcg_out16(s, (op & 0xff00) | ((v1 & 0xf) << 4) | r3); + tcg_out16(s, b2 << 12 | d2); + tcg_out16(s, (op & 0x00ff) | RXB(v1, 0, 0, 0) | (m4 << 12)); +} + +static void tcg_out_insn_VRSc(TCGContext *s, S390Opcode op, TCGReg r1, + intptr_t d2, TCGReg b2, TCGReg v3, int m4) +{ + tcg_debug_assert(is_general_reg(r1)); + tcg_debug_assert(d2 >= 0 && d2 <= 0xfff); + tcg_debug_assert(is_general_reg(b2)); + tcg_debug_assert(is_vector_reg(v3)); + tcg_out16(s, (op & 0xff00) | (r1 << 4) | (v3 & 0xf)); + tcg_out16(s, b2 << 12 | d2); + tcg_out16(s, (op & 0x00ff) | RXB(0, 0, v3, 0) | (m4 << 12)); +} + +static void tcg_out_insn_VRX(TCGContext *s, S390Opcode op, TCGReg v1, + TCGReg b2, TCGReg x2, intptr_t d2, int m3) +{ + tcg_debug_assert(is_vector_reg(v1)); + tcg_debug_assert(d2 >= 0 && d2 <= 0xfff); + tcg_debug_assert(is_general_reg(x2)); + tcg_debug_assert(is_general_reg(b2)); + tcg_out16(s, (op & 0xff00) | ((v1 & 0xf) << 4) | x2); + tcg_out16(s, (b2 << 12) | d2); + tcg_out16(s, (op & 0x00ff) | RXB(v1, 0, 0, 0) | (m3 << 12)); +} + /* Emit an opcode with "type-checking" of the format. */ #define tcg_out_insn(S, FMT, OP, ...) \ glue(tcg_out_insn_,FMT)(S, glue(glue(FMT,_),OP), ## __VA_ARGS__) @@ -517,12 +740,38 @@ static void tcg_out_sh32(TCGContext* s, S390Opcode op, TCGReg dest, static bool tcg_out_mov(TCGContext *s, TCGType type, TCGReg dst, TCGReg src) { - if (src != dst) { - if (type == TCG_TYPE_I32) { + if (src == dst) { + return true; + } + switch (type) { + case TCG_TYPE_I32: + if (likely(is_general_reg(dst) && is_general_reg(src))) { tcg_out_insn(s, RR, LR, dst, src); - } else { - tcg_out_insn(s, RRE, LGR, dst, src); + break; } + /* fallthru */ + + case TCG_TYPE_I64: + if (likely(is_general_reg(dst))) { + if (likely(is_general_reg(src))) { + tcg_out_insn(s, RRE, LGR, dst, src); + } else { + tcg_out_insn(s, VRSc, VLGV, dst, 0, 0, src, 3); + } + break; + } else if (is_general_reg(src)) { + tcg_out_insn(s, VRSb, VLVG, dst, 0, 0, src, 3); + break; + } + /* fallthru */ + + case TCG_TYPE_V64: + case TCG_TYPE_V128: + tcg_out_insn(s, VRRa, VLR, dst, src, 0); + break; + + default: + g_assert_not_reached(); } return true; } @@ -577,7 +826,7 @@ static void tcg_out_movi_int(TCGContext *s, TCGType type, TCGReg ret, } /* Try all 48-bit insns that can load it in one go. */ - if (s390_facilities & FACILITY_EXT_IMM) { + if (HAVE_FACILITY(EXT_IMM)) { if (sval == (int32_t)sval) { tcg_out_insn(s, RIL, LGFI, ret, sval); return; @@ -620,7 +869,7 @@ static void tcg_out_movi_int(TCGContext *s, TCGType type, TCGReg ret, } /* Otherwise, stuff it in the constant pool. */ - if (s390_facilities & FACILITY_GEN_INST_EXT) { + if (HAVE_FACILITY(GEN_INST_EXT)) { tcg_out_insn(s, RIL, LGRL, ret, 0); new_pool_label(s, sval, R_390_PC32DBL, s->code_ptr - 2, 2); } else if (USE_REG_TB && !in_prologue) { @@ -672,25 +921,92 @@ static void tcg_out_mem(TCGContext *s, S390Opcode opc_rx, S390Opcode opc_rxy, } } +static void tcg_out_vrx_mem(TCGContext *s, S390Opcode opc_vrx, + TCGReg data, TCGReg base, TCGReg index, + tcg_target_long ofs, int m3) +{ + if (ofs < 0 || ofs >= 0x1000) { + if (ofs >= -0x80000 && ofs < 0x80000) { + tcg_out_insn(s, RXY, LAY, TCG_TMP0, base, index, ofs); + base = TCG_TMP0; + index = TCG_REG_NONE; + ofs = 0; + } else { + tcg_out_movi(s, TCG_TYPE_PTR, TCG_TMP0, ofs); + if (index != TCG_REG_NONE) { + tcg_out_insn(s, RRE, AGR, TCG_TMP0, index); + } + index = TCG_TMP0; + ofs = 0; + } + } + tcg_out_insn_VRX(s, opc_vrx, data, base, index, ofs, m3); +} /* load data without address translation or endianness conversion */ -static inline void tcg_out_ld(TCGContext *s, TCGType type, TCGReg data, - TCGReg base, intptr_t ofs) +static void tcg_out_ld(TCGContext *s, TCGType type, TCGReg data, + TCGReg base, intptr_t ofs) { - if (type == TCG_TYPE_I32) { - tcg_out_mem(s, RX_L, RXY_LY, data, base, TCG_REG_NONE, ofs); - } else { - tcg_out_mem(s, 0, RXY_LG, data, base, TCG_REG_NONE, ofs); + switch (type) { + case TCG_TYPE_I32: + if (likely(is_general_reg(data))) { + tcg_out_mem(s, RX_L, RXY_LY, data, base, TCG_REG_NONE, ofs); + break; + } + tcg_out_vrx_mem(s, VRX_VLLEZ, data, base, TCG_REG_NONE, ofs, MO_32); + break; + + case TCG_TYPE_I64: + if (likely(is_general_reg(data))) { + tcg_out_mem(s, 0, RXY_LG, data, base, TCG_REG_NONE, ofs); + break; + } + /* fallthru */ + + case TCG_TYPE_V64: + tcg_out_vrx_mem(s, VRX_VLLEZ, data, base, TCG_REG_NONE, ofs, MO_64); + break; + + case TCG_TYPE_V128: + /* Hint quadword aligned. */ + tcg_out_vrx_mem(s, VRX_VL, data, base, TCG_REG_NONE, ofs, 4); + break; + + default: + g_assert_not_reached(); } } -static inline void tcg_out_st(TCGContext *s, TCGType type, TCGReg data, - TCGReg base, intptr_t ofs) +static void tcg_out_st(TCGContext *s, TCGType type, TCGReg data, + TCGReg base, intptr_t ofs) { - if (type == TCG_TYPE_I32) { - tcg_out_mem(s, RX_ST, RXY_STY, data, base, TCG_REG_NONE, ofs); - } else { - tcg_out_mem(s, 0, RXY_STG, data, base, TCG_REG_NONE, ofs); + switch (type) { + case TCG_TYPE_I32: + if (likely(is_general_reg(data))) { + tcg_out_mem(s, RX_ST, RXY_STY, data, base, TCG_REG_NONE, ofs); + } else { + tcg_out_vrx_mem(s, VRX_VSTEF, data, base, TCG_REG_NONE, ofs, 1); + } + break; + + case TCG_TYPE_I64: + if (likely(is_general_reg(data))) { + tcg_out_mem(s, 0, RXY_STG, data, base, TCG_REG_NONE, ofs); + break; + } + /* fallthru */ + + case TCG_TYPE_V64: + tcg_out_vrx_mem(s, VRX_VSTEG, data, base, TCG_REG_NONE, ofs, 0); + break; + + case TCG_TYPE_V128: + /* Hint quadword aligned. */ + tcg_out_vrx_mem(s, VRX_VST, data, base, TCG_REG_NONE, ofs, 4); + break; + + default: + g_assert_not_reached(); } } @@ -706,7 +1022,7 @@ static void tcg_out_ld_abs(TCGContext *s, TCGType type, { intptr_t addr = (intptr_t)abs; - if ((s390_facilities & FACILITY_GEN_INST_EXT) && !(addr & 1)) { + if (HAVE_FACILITY(GEN_INST_EXT) && !(addr & 1)) { ptrdiff_t disp = tcg_pcrel_diff(s, abs) >> 1; if (disp == (int32_t)disp) { if (type == TCG_TYPE_I32) { @@ -740,7 +1056,7 @@ static inline void tcg_out_risbg(TCGContext *s, TCGReg dest, TCGReg src, static void tgen_ext8s(TCGContext *s, TCGType type, TCGReg dest, TCGReg src) { - if (s390_facilities & FACILITY_EXT_IMM) { + if (HAVE_FACILITY(EXT_IMM)) { tcg_out_insn(s, RRE, LGBR, dest, src); return; } @@ -760,7 +1076,7 @@ static void tgen_ext8s(TCGContext *s, TCGType type, TCGReg dest, TCGReg src) static void tgen_ext8u(TCGContext *s, TCGType type, TCGReg dest, TCGReg src) { - if (s390_facilities & FACILITY_EXT_IMM) { + if (HAVE_FACILITY(EXT_IMM)) { tcg_out_insn(s, RRE, LLGCR, dest, src); return; } @@ -780,7 +1096,7 @@ static void tgen_ext8u(TCGContext *s, TCGType type, TCGReg dest, TCGReg src) static void tgen_ext16s(TCGContext *s, TCGType type, TCGReg dest, TCGReg src) { - if (s390_facilities & FACILITY_EXT_IMM) { + if (HAVE_FACILITY(EXT_IMM)) { tcg_out_insn(s, RRE, LGHR, dest, src); return; } @@ -800,7 +1116,7 @@ static void tgen_ext16s(TCGContext *s, TCGType type, TCGReg dest, TCGReg src) static void tgen_ext16u(TCGContext *s, TCGType type, TCGReg dest, TCGReg src) { - if (s390_facilities & FACILITY_EXT_IMM) { + if (HAVE_FACILITY(EXT_IMM)) { tcg_out_insn(s, RRE, LLGHR, dest, src); return; } @@ -888,7 +1204,7 @@ static void tgen_andi(TCGContext *s, TCGType type, TCGReg dest, uint64_t val) tgen_ext32u(s, dest, dest); return; } - if (s390_facilities & FACILITY_EXT_IMM) { + if (HAVE_FACILITY(EXT_IMM)) { if ((val & valid) == 0xff) { tgen_ext8u(s, TCG_TYPE_I64, dest, dest); return; @@ -909,7 +1225,7 @@ static void tgen_andi(TCGContext *s, TCGType type, TCGReg dest, uint64_t val) } /* Try all 48-bit insns that can perform it in one go. */ - if (s390_facilities & FACILITY_EXT_IMM) { + if (HAVE_FACILITY(EXT_IMM)) { for (i = 0; i < 2; i++) { tcg_target_ulong mask = ~(0xffffffffull << i*32); if (((val | ~valid) & mask) == mask) { @@ -918,7 +1234,7 @@ static void tgen_andi(TCGContext *s, TCGType type, TCGReg dest, uint64_t val) } } } - if ((s390_facilities & FACILITY_GEN_INST_EXT) && risbg_mask(val)) { + if (HAVE_FACILITY(GEN_INST_EXT) && risbg_mask(val)) { tgen_andi_risbg(s, dest, dest, val); return; } @@ -967,7 +1283,7 @@ static void tgen_ori(TCGContext *s, TCGType type, TCGReg dest, uint64_t val) } /* Try all 48-bit insns that can perform it in one go. */ - if (s390_facilities & FACILITY_EXT_IMM) { + if (HAVE_FACILITY(EXT_IMM)) { for (i = 0; i < 2; i++) { tcg_target_ulong mask = (0xffffffffull << i*32); if ((val & mask) != 0 && (val & ~mask) == 0) { @@ -992,7 +1308,7 @@ static void tgen_ori(TCGContext *s, TCGType type, TCGReg dest, uint64_t val) /* Perform the OR via sequential modifications to the high and low parts. Do this via recursion to handle 16-bit vs 32-bit masks in each half. */ - tcg_debug_assert(s390_facilities & FACILITY_EXT_IMM); + tcg_debug_assert(HAVE_FACILITY(EXT_IMM)); tgen_ori(s, type, dest, val & 0x00000000ffffffffull); tgen_ori(s, type, dest, val & 0xffffffff00000000ull); } @@ -1001,7 +1317,7 @@ static void tgen_ori(TCGContext *s, TCGType type, TCGReg dest, uint64_t val) static void tgen_xori(TCGContext *s, TCGType type, TCGReg dest, uint64_t val) { /* Try all 48-bit insns that can perform it in one go. */ - if (s390_facilities & FACILITY_EXT_IMM) { + if (HAVE_FACILITY(EXT_IMM)) { if ((val & 0xffffffff00000000ull) == 0) { tcg_out_insn(s, RIL, XILF, dest, val); return; @@ -1025,7 +1341,7 @@ static void tgen_xori(TCGContext *s, TCGType type, TCGReg dest, uint64_t val) tcg_tbrel_diff(s, NULL)); } else { /* Perform the xor by parts. */ - tcg_debug_assert(s390_facilities & FACILITY_EXT_IMM); + tcg_debug_assert(HAVE_FACILITY(EXT_IMM)); if (val & 0xffffffff) { tcg_out_insn(s, RIL, XILF, dest, val); } @@ -1059,7 +1375,7 @@ static int tgen_cmp(TCGContext *s, TCGType type, TCGCond c, TCGReg r1, goto exit; } - if (s390_facilities & FACILITY_EXT_IMM) { + if (HAVE_FACILITY(EXT_IMM)) { if (type == TCG_TYPE_I32) { op = (is_unsigned ? RIL_CLFI : RIL_CFI); tcg_out_insn_RIL(s, op, r1, c2); @@ -1122,7 +1438,7 @@ static void tgen_setcond(TCGContext *s, TCGType type, TCGCond cond, bool have_loc; /* With LOC2, we can always emit the minimum 3 insns. */ - if (s390_facilities & FACILITY_LOAD_ON_COND2) { + if (HAVE_FACILITY(LOAD_ON_COND2)) { /* Emit: d = 0, d = (cc ? 1 : d). */ cc = tgen_cmp(s, type, cond, c1, c2, c2const, false); tcg_out_movi(s, TCG_TYPE_I64, dest, 0); @@ -1130,7 +1446,7 @@ static void tgen_setcond(TCGContext *s, TCGType type, TCGCond cond, return; } - have_loc = (s390_facilities & FACILITY_LOAD_ON_COND) != 0; + have_loc = HAVE_FACILITY(LOAD_ON_COND); /* For HAVE_LOC, only the paths through GTU/GT/LEU/LE are smaller. */ restart: @@ -1216,7 +1532,7 @@ static void tgen_movcond(TCGContext *s, TCGType type, TCGCond c, TCGReg dest, TCGArg v3, int v3const) { int cc; - if (s390_facilities & FACILITY_LOAD_ON_COND) { + if (HAVE_FACILITY(LOAD_ON_COND)) { cc = tgen_cmp(s, type, c, c1, c2, c2const, false); if (v3const) { tcg_out_insn(s, RIE, LOCGHI, dest, v3, cc); @@ -1249,7 +1565,7 @@ static void tgen_clz(TCGContext *s, TCGReg dest, TCGReg a1, } else { tcg_out_mov(s, TCG_TYPE_I64, dest, a2); } - if (s390_facilities & FACILITY_LOAD_ON_COND) { + if (HAVE_FACILITY(LOAD_ON_COND)) { /* Emit: if (one bit found) dest = r0. */ tcg_out_insn(s, RRF, LOCGR, dest, TCG_REG_R0, 2); } else { @@ -1325,7 +1641,7 @@ static void tgen_brcond(TCGContext *s, TCGType type, TCGCond c, { int cc; - if (s390_facilities & FACILITY_GEN_INST_EXT) { + if (HAVE_FACILITY(GEN_INST_EXT)) { bool is_unsigned = is_unsigned_cond(c); bool in_range; S390Opcode opc; @@ -1519,7 +1835,7 @@ static TCGReg tcg_out_tlb_read(TCGContext *s, TCGReg addr_reg, MemOp opc, cross pages using the address of the last byte of the access. */ a_off = (a_bits >= s_bits ? 0 : s_mask - a_mask); tlb_mask = (uint64_t)TARGET_PAGE_MASK | a_mask; - if ((s390_facilities & FACILITY_GEN_INST_EXT) && a_off == 0) { + if (HAVE_FACILITY(GEN_INST_EXT) && a_off == 0) { tgen_andi_risbg(s, TCG_REG_R3, addr_reg, tlb_mask); } else { tcg_out_insn(s, RX, LA, TCG_REG_R3, addr_reg, TCG_REG_NONE, a_off); @@ -1547,7 +1863,7 @@ static TCGReg tcg_out_tlb_read(TCGContext *s, TCGReg addr_reg, MemOp opc, return addr_reg; } -static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi, +static void add_qemu_ldst_label(TCGContext *s, bool is_ld, MemOpIdx oi, TCGReg data, TCGReg addr, tcg_insn_unit *raddr, tcg_insn_unit *label_ptr) { @@ -1565,7 +1881,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) { TCGReg addr_reg = lb->addrlo_reg; TCGReg data_reg = lb->datalo_reg; - TCGMemOpIdx oi = lb->oi; + MemOpIdx oi = lb->oi; MemOp opc = get_memop(oi); if (!patch_reloc(lb->label_ptr[0], R_390_PC16DBL, @@ -1590,7 +1906,7 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb) { TCGReg addr_reg = lb->addrlo_reg; TCGReg data_reg = lb->datalo_reg; - TCGMemOpIdx oi = lb->oi; + MemOpIdx oi = lb->oi; MemOp opc = get_memop(oi); if (!patch_reloc(lb->label_ptr[0], R_390_PC16DBL, @@ -1644,7 +1960,7 @@ static void tcg_prepare_user_ldst(TCGContext *s, TCGReg *addr_reg, #endif /* CONFIG_SOFTMMU */ static void tcg_out_qemu_ld(TCGContext* s, TCGReg data_reg, TCGReg addr_reg, - TCGMemOpIdx oi) + MemOpIdx oi) { MemOp opc = get_memop(oi); #ifdef CONFIG_SOFTMMU @@ -1671,7 +1987,7 @@ static void tcg_out_qemu_ld(TCGContext* s, TCGReg data_reg, TCGReg addr_reg, } static void tcg_out_qemu_st(TCGContext* s, TCGReg data_reg, TCGReg addr_reg, - TCGMemOpIdx oi) + MemOpIdx oi) { MemOp opc = get_memop(oi); #ifdef CONFIG_SOFTMMU @@ -1810,7 +2126,7 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, tcg_out_insn(s, RI, AHI, a0, a2); break; } - if (s390_facilities & FACILITY_EXT_IMM) { + if (HAVE_FACILITY(EXT_IMM)) { tcg_out_insn(s, RIL, AFI, a0, a2); break; } @@ -2056,7 +2372,7 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, tcg_out_insn(s, RI, AGHI, a0, a2); break; } - if (s390_facilities & FACILITY_EXT_IMM) { + if (HAVE_FACILITY(EXT_IMM)) { if (a2 == (int32_t)a2) { tcg_out_insn(s, RIL, AGFI, a0, a2); break; @@ -2281,8 +2597,7 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, /* The host memory model is quite strong, we simply need to serialize the instruction stream. */ if (args[0] & TCG_MO_ST_LD) { - tcg_out_insn(s, RR, BCR, - s390_facilities & FACILITY_FAST_BCR_SER ? 14 : 15, 0); + tcg_out_insn(s, RR, BCR, HAVE_FACILITY(FAST_BCR_SER) ? 14 : 15, 0); } break; @@ -2294,6 +2609,423 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, } } +static bool tcg_out_dup_vec(TCGContext *s, TCGType type, unsigned vece, + TCGReg dst, TCGReg src) +{ + if (is_general_reg(src)) { + /* Replicate general register into two MO_64. */ + tcg_out_insn(s, VRRf, VLVGP, dst, src, src); + if (vece == MO_64) { + return true; + } + } + + /* + * Recall that the "standard" integer, within a vector, is the + * rightmost element of the leftmost doubleword, a-la VLLEZ. + */ + tcg_out_insn(s, VRIc, VREP, dst, (8 >> vece) - 1, src, vece); + return true; +} + +static bool tcg_out_dupm_vec(TCGContext *s, TCGType type, unsigned vece, + TCGReg dst, TCGReg base, intptr_t offset) +{ + tcg_out_vrx_mem(s, VRX_VLREP, dst, base, TCG_REG_NONE, offset, vece); + return true; +} + +static void tcg_out_dupi_vec(TCGContext *s, TCGType type, unsigned vece, + TCGReg dst, int64_t val) +{ + int i, mask, msb, lsb; + + /* Look for int16_t elements. */ + if (vece <= MO_16 || + (vece == MO_32 ? (int32_t)val : val) == (int16_t)val) { + tcg_out_insn(s, VRIa, VREPI, dst, val, vece); + return; + } + + /* Look for bit masks. */ + if (vece == MO_32) { + if (risbg_mask((int32_t)val)) { + /* Handle wraparound by swapping msb and lsb. */ + if ((val & 0x80000001u) == 0x80000001u) { + msb = 32 - ctz32(~val); + lsb = clz32(~val) - 1; + } else { + msb = clz32(val); + lsb = 31 - ctz32(val); + } + tcg_out_insn(s, VRIb, VGM, dst, lsb, msb, MO_32); + return; + } + } else { + if (risbg_mask(val)) { + /* Handle wraparound by swapping msb and lsb. */ + if ((val & 0x8000000000000001ull) == 0x8000000000000001ull) { + /* Handle wraparound by swapping msb and lsb. */ + msb = 64 - ctz64(~val); + lsb = clz64(~val) - 1; + } else { + msb = clz64(val); + lsb = 63 - ctz64(val); + } + tcg_out_insn(s, VRIb, VGM, dst, lsb, msb, MO_64); + return; + } + } + + /* Look for all bytes 0x00 or 0xff. */ + for (i = mask = 0; i < 8; i++) { + uint8_t byte = val >> (i * 8); + if (byte == 0xff) { + mask |= 1 << i; + } else if (byte != 0) { + break; + } + } + if (i == 8) { + tcg_out_insn(s, VRIa, VGBM, dst, mask * 0x0101, 0); + return; + } + + /* Otherwise, stuff it in the constant pool. */ + tcg_out_insn(s, RIL, LARL, TCG_TMP0, 0); + new_pool_label(s, val, R_390_PC32DBL, s->code_ptr - 2, 2); + tcg_out_insn(s, VRX, VLREP, dst, TCG_TMP0, TCG_REG_NONE, 0, MO_64); +} + +static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc, + unsigned vecl, unsigned vece, + const TCGArg *args, const int *const_args) +{ + TCGType type = vecl + TCG_TYPE_V64; + TCGArg a0 = args[0], a1 = args[1], a2 = args[2]; + + switch (opc) { + case INDEX_op_ld_vec: + tcg_out_ld(s, type, a0, a1, a2); + break; + case INDEX_op_st_vec: + tcg_out_st(s, type, a0, a1, a2); + break; + case INDEX_op_dupm_vec: + tcg_out_dupm_vec(s, type, vece, a0, a1, a2); + break; + + case INDEX_op_abs_vec: + tcg_out_insn(s, VRRa, VLP, a0, a1, vece); + break; + case INDEX_op_neg_vec: + tcg_out_insn(s, VRRa, VLC, a0, a1, vece); + break; + case INDEX_op_not_vec: + tcg_out_insn(s, VRRc, VNO, a0, a1, a1, 0); + break; + + case INDEX_op_add_vec: + tcg_out_insn(s, VRRc, VA, a0, a1, a2, vece); + break; + case INDEX_op_sub_vec: + tcg_out_insn(s, VRRc, VS, a0, a1, a2, vece); + break; + case INDEX_op_and_vec: + tcg_out_insn(s, VRRc, VN, a0, a1, a2, 0); + break; + case INDEX_op_andc_vec: + tcg_out_insn(s, VRRc, VNC, a0, a1, a2, 0); + break; + case INDEX_op_mul_vec: + tcg_out_insn(s, VRRc, VML, a0, a1, a2, vece); + break; + case INDEX_op_or_vec: + tcg_out_insn(s, VRRc, VO, a0, a1, a2, 0); + break; + case INDEX_op_orc_vec: + tcg_out_insn(s, VRRc, VOC, a0, a1, a2, 0); + break; + case INDEX_op_xor_vec: + tcg_out_insn(s, VRRc, VX, a0, a1, a2, 0); + break; + + case INDEX_op_shli_vec: + tcg_out_insn(s, VRSa, VESL, a0, a2, TCG_REG_NONE, a1, vece); + break; + case INDEX_op_shri_vec: + tcg_out_insn(s, VRSa, VESRL, a0, a2, TCG_REG_NONE, a1, vece); + break; + case INDEX_op_sari_vec: + tcg_out_insn(s, VRSa, VESRA, a0, a2, TCG_REG_NONE, a1, vece); + break; + case INDEX_op_rotli_vec: + tcg_out_insn(s, VRSa, VERLL, a0, a2, TCG_REG_NONE, a1, vece); + break; + case INDEX_op_shls_vec: + tcg_out_insn(s, VRSa, VESL, a0, 0, a2, a1, vece); + break; + case INDEX_op_shrs_vec: + tcg_out_insn(s, VRSa, VESRL, a0, 0, a2, a1, vece); + break; + case INDEX_op_sars_vec: + tcg_out_insn(s, VRSa, VESRA, a0, 0, a2, a1, vece); + break; + case INDEX_op_rotls_vec: + tcg_out_insn(s, VRSa, VERLL, a0, 0, a2, a1, vece); + break; + case INDEX_op_shlv_vec: + tcg_out_insn(s, VRRc, VESLV, a0, a1, a2, vece); + break; + case INDEX_op_shrv_vec: + tcg_out_insn(s, VRRc, VESRLV, a0, a1, a2, vece); + break; + case INDEX_op_sarv_vec: + tcg_out_insn(s, VRRc, VESRAV, a0, a1, a2, vece); + break; + case INDEX_op_rotlv_vec: + tcg_out_insn(s, VRRc, VERLLV, a0, a1, a2, vece); + break; + + case INDEX_op_smin_vec: + tcg_out_insn(s, VRRc, VMN, a0, a1, a2, vece); + break; + case INDEX_op_smax_vec: + tcg_out_insn(s, VRRc, VMX, a0, a1, a2, vece); + break; + case INDEX_op_umin_vec: + tcg_out_insn(s, VRRc, VMNL, a0, a1, a2, vece); + break; + case INDEX_op_umax_vec: + tcg_out_insn(s, VRRc, VMXL, a0, a1, a2, vece); + break; + + case INDEX_op_bitsel_vec: + tcg_out_insn(s, VRRe, VSEL, a0, a1, a2, args[3]); + break; + + case INDEX_op_cmp_vec: + switch ((TCGCond)args[3]) { + case TCG_COND_EQ: + tcg_out_insn(s, VRRc, VCEQ, a0, a1, a2, vece); + break; + case TCG_COND_GT: + tcg_out_insn(s, VRRc, VCH, a0, a1, a2, vece); + break; + case TCG_COND_GTU: + tcg_out_insn(s, VRRc, VCHL, a0, a1, a2, vece); + break; + default: + g_assert_not_reached(); + } + break; + + case INDEX_op_s390_vuph_vec: + tcg_out_insn(s, VRRa, VUPH, a0, a1, vece); + break; + case INDEX_op_s390_vupl_vec: + tcg_out_insn(s, VRRa, VUPL, a0, a1, vece); + break; + case INDEX_op_s390_vpks_vec: + tcg_out_insn(s, VRRc, VPKS, a0, a1, a2, vece); + break; + + case INDEX_op_mov_vec: /* Always emitted via tcg_out_mov. */ + case INDEX_op_dup_vec: /* Always emitted via tcg_out_dup_vec. */ + default: + g_assert_not_reached(); + } +} + +int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece) +{ + switch (opc) { + case INDEX_op_abs_vec: + case INDEX_op_add_vec: + case INDEX_op_and_vec: + case INDEX_op_andc_vec: + case INDEX_op_bitsel_vec: + case INDEX_op_neg_vec: + case INDEX_op_not_vec: + case INDEX_op_or_vec: + case INDEX_op_orc_vec: + case INDEX_op_rotli_vec: + case INDEX_op_rotls_vec: + case INDEX_op_rotlv_vec: + case INDEX_op_sari_vec: + case INDEX_op_sars_vec: + case INDEX_op_sarv_vec: + case INDEX_op_shli_vec: + case INDEX_op_shls_vec: + case INDEX_op_shlv_vec: + case INDEX_op_shri_vec: + case INDEX_op_shrs_vec: + case INDEX_op_shrv_vec: + case INDEX_op_smax_vec: + case INDEX_op_smin_vec: + case INDEX_op_sub_vec: + case INDEX_op_umax_vec: + case INDEX_op_umin_vec: + case INDEX_op_xor_vec: + return 1; + case INDEX_op_cmp_vec: + case INDEX_op_cmpsel_vec: + case INDEX_op_rotrv_vec: + return -1; + case INDEX_op_mul_vec: + return vece < MO_64; + case INDEX_op_ssadd_vec: + case INDEX_op_sssub_vec: + return vece < MO_64 ? -1 : 0; + default: + return 0; + } +} + +static bool expand_vec_cmp_noinv(TCGType type, unsigned vece, TCGv_vec v0, + TCGv_vec v1, TCGv_vec v2, TCGCond cond) +{ + bool need_swap = false, need_inv = false; + + switch (cond) { + case TCG_COND_EQ: + case TCG_COND_GT: + case TCG_COND_GTU: + break; + case TCG_COND_NE: + case TCG_COND_LE: + case TCG_COND_LEU: + need_inv = true; + break; + case TCG_COND_LT: + case TCG_COND_LTU: + need_swap = true; + break; + case TCG_COND_GE: + case TCG_COND_GEU: + need_swap = need_inv = true; + break; + default: + g_assert_not_reached(); + } + + if (need_inv) { + cond = tcg_invert_cond(cond); + } + if (need_swap) { + TCGv_vec t1; + t1 = v1, v1 = v2, v2 = t1; + cond = tcg_swap_cond(cond); + } + + vec_gen_4(INDEX_op_cmp_vec, type, vece, tcgv_vec_arg(v0), + tcgv_vec_arg(v1), tcgv_vec_arg(v2), cond); + + return need_inv; +} + +static void expand_vec_cmp(TCGType type, unsigned vece, TCGv_vec v0, + TCGv_vec v1, TCGv_vec v2, TCGCond cond) +{ + if (expand_vec_cmp_noinv(type, vece, v0, v1, v2, cond)) { + tcg_gen_not_vec(vece, v0, v0); + } +} + +static void expand_vec_cmpsel(TCGType type, unsigned vece, TCGv_vec v0, + TCGv_vec c1, TCGv_vec c2, + TCGv_vec v3, TCGv_vec v4, TCGCond cond) +{ + TCGv_vec t = tcg_temp_new_vec(type); + + if (expand_vec_cmp_noinv(type, vece, t, c1, c2, cond)) { + /* Invert the sense of the compare by swapping arguments. */ + tcg_gen_bitsel_vec(vece, v0, t, v4, v3); + } else { + tcg_gen_bitsel_vec(vece, v0, t, v3, v4); + } + tcg_temp_free_vec(t); +} + +static void expand_vec_sat(TCGType type, unsigned vece, TCGv_vec v0, + TCGv_vec v1, TCGv_vec v2, TCGOpcode add_sub_opc) +{ + TCGv_vec h1 = tcg_temp_new_vec(type); + TCGv_vec h2 = tcg_temp_new_vec(type); + TCGv_vec l1 = tcg_temp_new_vec(type); + TCGv_vec l2 = tcg_temp_new_vec(type); + + tcg_debug_assert (vece < MO_64); + + /* Unpack with sign-extension. */ + vec_gen_2(INDEX_op_s390_vuph_vec, type, vece, + tcgv_vec_arg(h1), tcgv_vec_arg(v1)); + vec_gen_2(INDEX_op_s390_vuph_vec, type, vece, + tcgv_vec_arg(h2), tcgv_vec_arg(v2)); + + vec_gen_2(INDEX_op_s390_vupl_vec, type, vece, + tcgv_vec_arg(l1), tcgv_vec_arg(v1)); + vec_gen_2(INDEX_op_s390_vupl_vec, type, vece, + tcgv_vec_arg(l2), tcgv_vec_arg(v2)); + + /* Arithmetic on a wider element size. */ + vec_gen_3(add_sub_opc, type, vece + 1, tcgv_vec_arg(h1), + tcgv_vec_arg(h1), tcgv_vec_arg(h2)); + vec_gen_3(add_sub_opc, type, vece + 1, tcgv_vec_arg(l1), + tcgv_vec_arg(l1), tcgv_vec_arg(l2)); + + /* Pack with saturation. */ + vec_gen_3(INDEX_op_s390_vpks_vec, type, vece + 1, + tcgv_vec_arg(v0), tcgv_vec_arg(h1), tcgv_vec_arg(l1)); + + tcg_temp_free_vec(h1); + tcg_temp_free_vec(h2); + tcg_temp_free_vec(l1); + tcg_temp_free_vec(l2); +} + +void tcg_expand_vec_op(TCGOpcode opc, TCGType type, unsigned vece, + TCGArg a0, ...) +{ + va_list va; + TCGv_vec v0, v1, v2, v3, v4, t0; + + va_start(va, a0); + v0 = temp_tcgv_vec(arg_temp(a0)); + v1 = temp_tcgv_vec(arg_temp(va_arg(va, TCGArg))); + v2 = temp_tcgv_vec(arg_temp(va_arg(va, TCGArg))); + + switch (opc) { + case INDEX_op_cmp_vec: + expand_vec_cmp(type, vece, v0, v1, v2, va_arg(va, TCGArg)); + break; + + case INDEX_op_cmpsel_vec: + v3 = temp_tcgv_vec(arg_temp(va_arg(va, TCGArg))); + v4 = temp_tcgv_vec(arg_temp(va_arg(va, TCGArg))); + expand_vec_cmpsel(type, vece, v0, v1, v2, v3, v4, va_arg(va, TCGArg)); + break; + + case INDEX_op_rotrv_vec: + t0 = tcg_temp_new_vec(type); + tcg_gen_neg_vec(vece, t0, v2); + tcg_gen_rotlv_vec(vece, v0, v1, t0); + tcg_temp_free_vec(t0); + break; + + case INDEX_op_ssadd_vec: + expand_vec_sat(type, vece, v0, v1, v2, INDEX_op_add_vec); + break; + case INDEX_op_sssub_vec: + expand_vec_sat(type, vece, v0, v1, v2, INDEX_op_sub_vec); + break; + + default: + g_assert_not_reached(); + } + va_end(va); +} + static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op) { switch (op) { @@ -2345,7 +3077,7 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op) case INDEX_op_or_i64: case INDEX_op_xor_i32: case INDEX_op_xor_i64: - return (s390_facilities & FACILITY_DISTINCT_OPS + return (HAVE_FACILITY(DISTINCT_OPS) ? C_O1_I2(r, r, ri) : C_O1_I2(r, 0, ri)); @@ -2353,19 +3085,19 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op) /* If we have the general-instruction-extensions, then we have MULTIPLY SINGLE IMMEDIATE with a signed 32-bit, otherwise we have only MULTIPLY HALFWORD IMMEDIATE, with a signed 16-bit. */ - return (s390_facilities & FACILITY_GEN_INST_EXT + return (HAVE_FACILITY(GEN_INST_EXT) ? C_O1_I2(r, 0, ri) : C_O1_I2(r, 0, rI)); case INDEX_op_mul_i64: - return (s390_facilities & FACILITY_GEN_INST_EXT + return (HAVE_FACILITY(GEN_INST_EXT) ? C_O1_I2(r, 0, rJ) : C_O1_I2(r, 0, rI)); case INDEX_op_shl_i32: case INDEX_op_shr_i32: case INDEX_op_sar_i32: - return (s390_facilities & FACILITY_DISTINCT_OPS + return (HAVE_FACILITY(DISTINCT_OPS) ? C_O1_I2(r, r, ri) : C_O1_I2(r, 0, ri)); @@ -2409,7 +3141,7 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op) case INDEX_op_movcond_i32: case INDEX_op_movcond_i64: - return (s390_facilities & FACILITY_LOAD_ON_COND2 + return (HAVE_FACILITY(LOAD_ON_COND2) ? C_O1_I4(r, r, ri, rI, 0) : C_O1_I4(r, r, ri, r, 0)); @@ -2424,21 +3156,74 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op) case INDEX_op_add2_i32: case INDEX_op_sub2_i32: - return (s390_facilities & FACILITY_EXT_IMM + return (HAVE_FACILITY(EXT_IMM) ? C_O2_I4(r, r, 0, 1, ri, r) : C_O2_I4(r, r, 0, 1, r, r)); case INDEX_op_add2_i64: case INDEX_op_sub2_i64: - return (s390_facilities & FACILITY_EXT_IMM + return (HAVE_FACILITY(EXT_IMM) ? C_O2_I4(r, r, 0, 1, rA, r) : C_O2_I4(r, r, 0, 1, r, r)); + case INDEX_op_st_vec: + return C_O0_I2(v, r); + case INDEX_op_ld_vec: + case INDEX_op_dupm_vec: + return C_O1_I1(v, r); + case INDEX_op_dup_vec: + return C_O1_I1(v, vr); + case INDEX_op_abs_vec: + case INDEX_op_neg_vec: + case INDEX_op_not_vec: + case INDEX_op_rotli_vec: + case INDEX_op_sari_vec: + case INDEX_op_shli_vec: + case INDEX_op_shri_vec: + case INDEX_op_s390_vuph_vec: + case INDEX_op_s390_vupl_vec: + return C_O1_I1(v, v); + case INDEX_op_add_vec: + case INDEX_op_sub_vec: + case INDEX_op_and_vec: + case INDEX_op_andc_vec: + case INDEX_op_or_vec: + case INDEX_op_orc_vec: + case INDEX_op_xor_vec: + case INDEX_op_cmp_vec: + case INDEX_op_mul_vec: + case INDEX_op_rotlv_vec: + case INDEX_op_rotrv_vec: + case INDEX_op_shlv_vec: + case INDEX_op_shrv_vec: + case INDEX_op_sarv_vec: + case INDEX_op_smax_vec: + case INDEX_op_smin_vec: + case INDEX_op_umax_vec: + case INDEX_op_umin_vec: + case INDEX_op_s390_vpks_vec: + return C_O1_I2(v, v, v); + case INDEX_op_rotls_vec: + case INDEX_op_shls_vec: + case INDEX_op_shrs_vec: + case INDEX_op_sars_vec: + return C_O1_I2(v, v, r); + case INDEX_op_bitsel_vec: + return C_O1_I3(v, v, v, v); + default: g_assert_not_reached(); } } +/* + * Mainline glibc added HWCAP_S390_VX before it was kernel abi. + * Some distros have fixed this up locally, others have not. + */ +#ifndef HWCAP_S390_VXRS +#define HWCAP_S390_VXRS 2048 +#endif + static void query_s390_facilities(void) { unsigned long hwcap = qemu_getauxval(AT_HWCAP); @@ -2446,13 +3231,22 @@ static void query_s390_facilities(void) /* Is STORE FACILITY LIST EXTENDED available? Honestly, I believe this is present on all 64-bit systems, but let's check for it anyway. */ if (hwcap & HWCAP_S390_STFLE) { - register int r0 __asm__("0"); - register void *r1 __asm__("1"); + register int r0 __asm__("0") = ARRAY_SIZE(s390_facilities) - 1; + register void *r1 __asm__("1") = s390_facilities; /* stfle 0(%r1) */ - r1 = &s390_facilities; asm volatile(".word 0xb2b0,0x1000" - : "=r"(r0) : "0"(0), "r"(r1) : "memory", "cc"); + : "=r"(r0) : "r"(r0), "r"(r1) : "memory", "cc"); + } + + /* + * Use of vector registers requires os support beyond the facility bit. + * If the kernel does not advertise support, disable the facility bits. + * There is nothing else we currently care about in the 3rd word, so + * disable VECTOR with one store. + */ + if (!(hwcap & HWCAP_S390_VXRS)) { + s390_facilities[2] = 0; } } @@ -2462,6 +3256,10 @@ static void tcg_target_init(TCGContext *s) tcg_target_available_regs[TCG_TYPE_I32] = 0xffff; tcg_target_available_regs[TCG_TYPE_I64] = 0xffff; + if (HAVE_FACILITY(VECTOR)) { + tcg_target_available_regs[TCG_TYPE_V64] = 0xffffffff00000000ull; + tcg_target_available_regs[TCG_TYPE_V128] = 0xffffffff00000000ull; + } tcg_target_call_clobber_regs = 0; tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R0); @@ -2476,6 +3274,31 @@ static void tcg_target_init(TCGContext *s) /* The return register can be considered call-clobbered. */ tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R14); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V0); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V1); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V2); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V3); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V4); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V5); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V6); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V7); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V16); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V17); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V18); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V19); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V20); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V21); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V22); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V23); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V24); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V25); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V26); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V27); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V28); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V29); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V30); + tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_V31); + s->reserved_regs = 0; tcg_regset_set_reg(s->reserved_regs, TCG_TMP0); /* XXX many insns can't be used with R0, so we better avoid it for now */ diff --git a/tcg/s390/tcg-target.h b/tcg/s390x/tcg-target.h index 2e4ede2ea2..527ada0f63 100644 --- a/tcg/s390/tcg-target.h +++ b/tcg/s390x/tcg-target.h @@ -32,39 +32,44 @@ #define MAX_CODE_GEN_BUFFER_SIZE (3 * GiB) typedef enum TCGReg { - TCG_REG_R0 = 0, - TCG_REG_R1, - TCG_REG_R2, - TCG_REG_R3, - TCG_REG_R4, - TCG_REG_R5, - TCG_REG_R6, - TCG_REG_R7, - TCG_REG_R8, - TCG_REG_R9, - TCG_REG_R10, - TCG_REG_R11, - TCG_REG_R12, - TCG_REG_R13, - TCG_REG_R14, - TCG_REG_R15 + TCG_REG_R0, TCG_REG_R1, TCG_REG_R2, TCG_REG_R3, + TCG_REG_R4, TCG_REG_R5, TCG_REG_R6, TCG_REG_R7, + TCG_REG_R8, TCG_REG_R9, TCG_REG_R10, TCG_REG_R11, + TCG_REG_R12, TCG_REG_R13, TCG_REG_R14, TCG_REG_R15, + + TCG_REG_V0 = 32, TCG_REG_V1, TCG_REG_V2, TCG_REG_V3, + TCG_REG_V4, TCG_REG_V5, TCG_REG_V6, TCG_REG_V7, + TCG_REG_V8, TCG_REG_V9, TCG_REG_V10, TCG_REG_V11, + TCG_REG_V12, TCG_REG_V13, TCG_REG_V14, TCG_REG_V15, + TCG_REG_V16, TCG_REG_V17, TCG_REG_V18, TCG_REG_V19, + TCG_REG_V20, TCG_REG_V21, TCG_REG_V22, TCG_REG_V23, + TCG_REG_V24, TCG_REG_V25, TCG_REG_V26, TCG_REG_V27, + TCG_REG_V28, TCG_REG_V29, TCG_REG_V30, TCG_REG_V31, + + TCG_AREG0 = TCG_REG_R10, + TCG_REG_CALL_STACK = TCG_REG_R15 } TCGReg; -#define TCG_TARGET_NB_REGS 16 +#define TCG_TARGET_NB_REGS 64 /* A list of relevant facilities used by this translator. Some of these are required for proper operation, and these are checked at startup. */ -#define FACILITY_ZARCH_ACTIVE (1ULL << (63 - 2)) -#define FACILITY_LONG_DISP (1ULL << (63 - 18)) -#define FACILITY_EXT_IMM (1ULL << (63 - 21)) -#define FACILITY_GEN_INST_EXT (1ULL << (63 - 34)) -#define FACILITY_LOAD_ON_COND (1ULL << (63 - 45)) +#define FACILITY_ZARCH_ACTIVE 2 +#define FACILITY_LONG_DISP 18 +#define FACILITY_EXT_IMM 21 +#define FACILITY_GEN_INST_EXT 34 +#define FACILITY_LOAD_ON_COND 45 #define FACILITY_FAST_BCR_SER FACILITY_LOAD_ON_COND #define FACILITY_DISTINCT_OPS FACILITY_LOAD_ON_COND -#define FACILITY_LOAD_ON_COND2 (1ULL << (63 - 53)) +#define FACILITY_LOAD_ON_COND2 53 +#define FACILITY_VECTOR 129 +#define FACILITY_VECTOR_ENH1 135 + +extern uint64_t s390_facilities[3]; -extern uint64_t s390_facilities; +#define HAVE_FACILITY(X) \ + ((s390_facilities[FACILITY_##X / 64] >> (63 - FACILITY_##X % 64)) & 1) /* optional instructions */ #define TCG_TARGET_HAS_div2_i32 1 @@ -85,8 +90,8 @@ extern uint64_t s390_facilities; #define TCG_TARGET_HAS_clz_i32 0 #define TCG_TARGET_HAS_ctz_i32 0 #define TCG_TARGET_HAS_ctpop_i32 0 -#define TCG_TARGET_HAS_deposit_i32 (s390_facilities & FACILITY_GEN_INST_EXT) -#define TCG_TARGET_HAS_extract_i32 (s390_facilities & FACILITY_GEN_INST_EXT) +#define TCG_TARGET_HAS_deposit_i32 HAVE_FACILITY(GEN_INST_EXT) +#define TCG_TARGET_HAS_extract_i32 HAVE_FACILITY(GEN_INST_EXT) #define TCG_TARGET_HAS_sextract_i32 0 #define TCG_TARGET_HAS_extract2_i32 0 #define TCG_TARGET_HAS_movcond_i32 1 @@ -98,7 +103,7 @@ extern uint64_t s390_facilities; #define TCG_TARGET_HAS_mulsh_i32 0 #define TCG_TARGET_HAS_extrl_i64_i32 0 #define TCG_TARGET_HAS_extrh_i64_i32 0 -#define TCG_TARGET_HAS_direct_jump (s390_facilities & FACILITY_GEN_INST_EXT) +#define TCG_TARGET_HAS_direct_jump HAVE_FACILITY(GEN_INST_EXT) #define TCG_TARGET_HAS_qemu_st8_i32 0 #define TCG_TARGET_HAS_div2_i64 1 @@ -119,11 +124,11 @@ extern uint64_t s390_facilities; #define TCG_TARGET_HAS_eqv_i64 0 #define TCG_TARGET_HAS_nand_i64 0 #define TCG_TARGET_HAS_nor_i64 0 -#define TCG_TARGET_HAS_clz_i64 (s390_facilities & FACILITY_EXT_IMM) +#define TCG_TARGET_HAS_clz_i64 HAVE_FACILITY(EXT_IMM) #define TCG_TARGET_HAS_ctz_i64 0 #define TCG_TARGET_HAS_ctpop_i64 0 -#define TCG_TARGET_HAS_deposit_i64 (s390_facilities & FACILITY_GEN_INST_EXT) -#define TCG_TARGET_HAS_extract_i64 (s390_facilities & FACILITY_GEN_INST_EXT) +#define TCG_TARGET_HAS_deposit_i64 HAVE_FACILITY(GEN_INST_EXT) +#define TCG_TARGET_HAS_extract_i64 HAVE_FACILITY(GEN_INST_EXT) #define TCG_TARGET_HAS_sextract_i64 0 #define TCG_TARGET_HAS_extract2_i64 0 #define TCG_TARGET_HAS_movcond_i64 1 @@ -134,8 +139,28 @@ extern uint64_t s390_facilities; #define TCG_TARGET_HAS_muluh_i64 0 #define TCG_TARGET_HAS_mulsh_i64 0 +#define TCG_TARGET_HAS_v64 HAVE_FACILITY(VECTOR) +#define TCG_TARGET_HAS_v128 HAVE_FACILITY(VECTOR) +#define TCG_TARGET_HAS_v256 0 + +#define TCG_TARGET_HAS_andc_vec 1 +#define TCG_TARGET_HAS_orc_vec HAVE_FACILITY(VECTOR_ENH1) +#define TCG_TARGET_HAS_not_vec 1 +#define TCG_TARGET_HAS_neg_vec 1 +#define TCG_TARGET_HAS_abs_vec 1 +#define TCG_TARGET_HAS_roti_vec 1 +#define TCG_TARGET_HAS_rots_vec 1 +#define TCG_TARGET_HAS_rotv_vec 1 +#define TCG_TARGET_HAS_shi_vec 1 +#define TCG_TARGET_HAS_shs_vec 1 +#define TCG_TARGET_HAS_shv_vec 1 +#define TCG_TARGET_HAS_mul_vec 1 +#define TCG_TARGET_HAS_sat_vec 0 +#define TCG_TARGET_HAS_minmax_vec 1 +#define TCG_TARGET_HAS_bitsel_vec 1 +#define TCG_TARGET_HAS_cmpsel_vec 0 + /* used for function call generation */ -#define TCG_REG_CALL_STACK TCG_REG_R15 #define TCG_TARGET_STACK_ALIGN 8 #define TCG_TARGET_CALL_STACK_OFFSET 160 @@ -144,10 +169,6 @@ extern uint64_t s390_facilities; #define TCG_TARGET_DEFAULT_MO (TCG_MO_ALL & ~TCG_MO_ST_LD) -enum { - TCG_AREG0 = TCG_REG_R10, -}; - static inline void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_rx, uintptr_t jmp_rw, uintptr_t addr) { diff --git a/tcg/s390x/tcg-target.opc.h b/tcg/s390x/tcg-target.opc.h new file mode 100644 index 0000000000..0eb2350fb3 --- /dev/null +++ b/tcg/s390x/tcg-target.opc.h @@ -0,0 +1,15 @@ +/* + * Copyright (c) 2021 Linaro + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * (at your option) any later version. + * + * See the COPYING file in the top-level directory for details. + * + * Target-specific opcodes for host vector expansion. These will be + * emitted by tcg_expand_vec_op. For those familiar with GCC internals, + * consider these to be UNSPEC with names. + */ +DEF(s390_vuph_vec, 1, 1, 0, IMPLVEC) +DEF(s390_vupl_vec, 1, 1, 0, IMPLVEC) +DEF(s390_vpks_vec, 1, 2, 0, IMPLVEC) diff --git a/tcg/sparc/tcg-target.c.inc b/tcg/sparc/tcg-target.c.inc index 9720d76abd..9dd32ef95e 100644 --- a/tcg/sparc/tcg-target.c.inc +++ b/tcg/sparc/tcg-target.c.inc @@ -855,8 +855,8 @@ static void tcg_out_mb(TCGContext *s, TCGArg a0) } #ifdef CONFIG_SOFTMMU -static const tcg_insn_unit *qemu_ld_trampoline[16]; -static const tcg_insn_unit *qemu_st_trampoline[16]; +static const tcg_insn_unit *qemu_ld_trampoline[(MO_SSIZE | MO_BSWAP) + 1]; +static const tcg_insn_unit *qemu_st_trampoline[(MO_SIZE | MO_BSWAP) + 1]; static void emit_extend(TCGContext *s, TCGReg r, int op) { @@ -883,7 +883,7 @@ static void emit_extend(TCGContext *s, TCGReg r, int op) static void build_trampolines(TCGContext *s) { - static void * const qemu_ld_helpers[16] = { + static void * const qemu_ld_helpers[] = { [MO_UB] = helper_ret_ldub_mmu, [MO_SB] = helper_ret_ldsb_mmu, [MO_LEUW] = helper_le_lduw_mmu, @@ -895,7 +895,7 @@ static void build_trampolines(TCGContext *s) [MO_BEUL] = helper_be_ldul_mmu, [MO_BEQ] = helper_be_ldq_mmu, }; - static void * const qemu_st_helpers[16] = { + static void * const qemu_st_helpers[] = { [MO_UB] = helper_ret_stb_mmu, [MO_LEUW] = helper_le_stw_mmu, [MO_LEUL] = helper_le_stl_mmu, @@ -908,7 +908,7 @@ static void build_trampolines(TCGContext *s) int i; TCGReg ra; - for (i = 0; i < 16; ++i) { + for (i = 0; i < ARRAY_SIZE(qemu_ld_helpers); ++i) { if (qemu_ld_helpers[i] == NULL) { continue; } @@ -936,7 +936,7 @@ static void build_trampolines(TCGContext *s) tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_O7, ra); } - for (i = 0; i < 16; ++i) { + for (i = 0; i < ARRAY_SIZE(qemu_st_helpers); ++i) { if (qemu_st_helpers[i] == NULL) { continue; } @@ -1118,7 +1118,7 @@ static TCGReg tcg_out_tlb_load(TCGContext *s, TCGReg addr, int mem_index, } #endif /* CONFIG_SOFTMMU */ -static const int qemu_ld_opc[16] = { +static const int qemu_ld_opc[(MO_SSIZE | MO_BSWAP) + 1] = { [MO_UB] = LDUB, [MO_SB] = LDSB, @@ -1135,7 +1135,7 @@ static const int qemu_ld_opc[16] = { [MO_LEQ] = LDX_LE, }; -static const int qemu_st_opc[16] = { +static const int qemu_st_opc[(MO_SIZE | MO_BSWAP) + 1] = { [MO_UB] = STB, [MO_BEUW] = STH, @@ -1148,7 +1148,7 @@ static const int qemu_st_opc[16] = { }; static void tcg_out_qemu_ld(TCGContext *s, TCGReg data, TCGReg addr, - TCGMemOpIdx oi, bool is_64) + MemOpIdx oi, bool is_64) { MemOp memop = get_memop(oi); #ifdef CONFIG_SOFTMMU @@ -1230,7 +1230,7 @@ static void tcg_out_qemu_ld(TCGContext *s, TCGReg data, TCGReg addr, } static void tcg_out_qemu_st(TCGContext *s, TCGReg data, TCGReg addr, - TCGMemOpIdx oi) + MemOpIdx oi) { MemOp memop = get_memop(oi); #ifdef CONFIG_SOFTMMU diff --git a/tcg/tcg-ldst.c.inc b/tcg/tcg-ldst.c.inc index c3ce88e69d..6c6848d034 100644 --- a/tcg/tcg-ldst.c.inc +++ b/tcg/tcg-ldst.c.inc @@ -22,7 +22,7 @@ typedef struct TCGLabelQemuLdst { bool is_ld; /* qemu_ld: true, qemu_st: false */ - TCGMemOpIdx oi; + MemOpIdx oi; TCGType type; /* result type of a load */ TCGReg addrlo_reg; /* reg index for low word of guest virtual addr */ TCGReg addrhi_reg; /* reg index for high word of guest virtual addr */ diff --git a/tcg/tcg-op-vec.c b/tcg/tcg-op-vec.c index 15e026ae49..faf30f9cdd 100644 --- a/tcg/tcg-op-vec.c +++ b/tcg/tcg-op-vec.c @@ -119,6 +119,18 @@ bool tcg_can_emit_vecop_list(const TCGOpcode *list, continue; } break; + case INDEX_op_usadd_vec: + if (tcg_can_emit_vec_op(INDEX_op_umin_vec, type, vece) || + tcg_can_emit_vec_op(INDEX_op_cmp_vec, type, vece)) { + continue; + } + break; + case INDEX_op_ussub_vec: + if (tcg_can_emit_vec_op(INDEX_op_umax_vec, type, vece) || + tcg_can_emit_vec_op(INDEX_op_cmp_vec, type, vece)) { + continue; + } + break; case INDEX_op_cmpsel_vec: case INDEX_op_smin_vec: case INDEX_op_smax_vec: @@ -603,7 +615,18 @@ void tcg_gen_ssadd_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b) void tcg_gen_usadd_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b) { - do_op3_nofail(vece, r, a, b, INDEX_op_usadd_vec); + if (!do_op3(vece, r, a, b, INDEX_op_usadd_vec)) { + const TCGOpcode *hold_list = tcg_swap_vecop_list(NULL); + TCGv_vec t = tcg_temp_new_vec_matching(r); + + /* usadd(a, b) = min(a, ~b) + b */ + tcg_gen_not_vec(vece, t, b); + tcg_gen_umin_vec(vece, t, t, a); + tcg_gen_add_vec(vece, r, t, b); + + tcg_temp_free_vec(t); + tcg_swap_vecop_list(hold_list); + } } void tcg_gen_sssub_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b) @@ -613,7 +636,17 @@ void tcg_gen_sssub_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b) void tcg_gen_ussub_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b) { - do_op3_nofail(vece, r, a, b, INDEX_op_ussub_vec); + if (!do_op3(vece, r, a, b, INDEX_op_ussub_vec)) { + const TCGOpcode *hold_list = tcg_swap_vecop_list(NULL); + TCGv_vec t = tcg_temp_new_vec_matching(r); + + /* ussub(a, b) = max(a, b) - b */ + tcg_gen_umax_vec(vece, t, a, b); + tcg_gen_sub_vec(vece, r, t, b); + + tcg_temp_free_vec(t); + tcg_swap_vecop_list(hold_list); + } } static void do_minmax(unsigned vece, TCGv_vec r, TCGv_vec a, diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c index c754396575..b1cfd36f29 100644 --- a/tcg/tcg-op.c +++ b/tcg/tcg-op.c @@ -28,7 +28,6 @@ #include "tcg/tcg-op.h" #include "tcg/tcg-mo.h" #include "trace-tcg.h" -#include "trace/mem.h" #include "exec/plugin-gen.h" /* Reduce the number of ifdefs below. This assumes that all uses of @@ -2780,10 +2779,13 @@ static inline MemOp tcg_canonicalize_memop(MemOp op, bool is64, bool st) } break; case MO_64: - if (!is64) { - tcg_abort(); + if (is64) { + op &= ~MO_SIGN; + break; } - break; + /* fall through */ + default: + g_assert_not_reached(); } if (st) { op &= ~MO_SIGN; @@ -2794,7 +2796,7 @@ static inline MemOp tcg_canonicalize_memop(MemOp op, bool is64, bool st) static void gen_ldst_i32(TCGOpcode opc, TCGv_i32 val, TCGv addr, MemOp memop, TCGArg idx) { - TCGMemOpIdx oi = make_memop_idx(memop, idx); + MemOpIdx oi = make_memop_idx(memop, idx); #if TARGET_LONG_BITS == 32 tcg_gen_op3i_i32(opc, val, addr, oi); #else @@ -2809,7 +2811,7 @@ static void gen_ldst_i32(TCGOpcode opc, TCGv_i32 val, TCGv addr, static void gen_ldst_i64(TCGOpcode opc, TCGv_i64 val, TCGv addr, MemOp memop, TCGArg idx) { - TCGMemOpIdx oi = make_memop_idx(memop, idx); + MemOpIdx oi = make_memop_idx(memop, idx); #if TARGET_LONG_BITS == 32 if (TCG_TARGET_REG_BITS == 32) { tcg_gen_op4i_i32(opc, TCGV_LOW(val), TCGV_HIGH(val), addr, oi); @@ -2850,10 +2852,12 @@ static inline TCGv plugin_prep_mem_callbacks(TCGv vaddr) return vaddr; } -static inline void plugin_gen_mem_callbacks(TCGv vaddr, uint16_t info) +static void plugin_gen_mem_callbacks(TCGv vaddr, MemOpIdx oi, + enum qemu_plugin_mem_rw rw) { #ifdef CONFIG_PLUGIN if (tcg_ctx->plugin_insn != NULL) { + qemu_plugin_meminfo_t info = make_plugin_meminfo(oi, rw); plugin_gen_empty_mem_callback(vaddr, info); tcg_temp_free(vaddr); } @@ -2863,11 +2867,12 @@ static inline void plugin_gen_mem_callbacks(TCGv vaddr, uint16_t info) void tcg_gen_qemu_ld_i32(TCGv_i32 val, TCGv addr, TCGArg idx, MemOp memop) { MemOp orig_memop; - uint16_t info = trace_mem_get_info(memop, idx, 0); + MemOpIdx oi; tcg_gen_req_mo(TCG_MO_LD_LD | TCG_MO_ST_LD); memop = tcg_canonicalize_memop(memop, 0, 0); - trace_guest_mem_before_tcg(tcg_ctx->cpu, cpu_env, addr, info); + oi = make_memop_idx(memop, idx); + trace_guest_ld_before_tcg(tcg_ctx->cpu, cpu_env, addr, oi); orig_memop = memop; if (!TCG_TARGET_HAS_MEMORY_BSWAP && (memop & MO_BSWAP)) { @@ -2880,7 +2885,7 @@ void tcg_gen_qemu_ld_i32(TCGv_i32 val, TCGv addr, TCGArg idx, MemOp memop) addr = plugin_prep_mem_callbacks(addr); gen_ldst_i32(INDEX_op_qemu_ld_i32, val, addr, memop, idx); - plugin_gen_mem_callbacks(addr, info); + plugin_gen_mem_callbacks(addr, oi, QEMU_PLUGIN_MEM_R); if ((orig_memop ^ memop) & MO_BSWAP) { switch (orig_memop & MO_SIZE) { @@ -2901,11 +2906,12 @@ void tcg_gen_qemu_ld_i32(TCGv_i32 val, TCGv addr, TCGArg idx, MemOp memop) void tcg_gen_qemu_st_i32(TCGv_i32 val, TCGv addr, TCGArg idx, MemOp memop) { TCGv_i32 swap = NULL; - uint16_t info = trace_mem_get_info(memop, idx, 1); + MemOpIdx oi; tcg_gen_req_mo(TCG_MO_LD_ST | TCG_MO_ST_ST); memop = tcg_canonicalize_memop(memop, 0, 1); - trace_guest_mem_before_tcg(tcg_ctx->cpu, cpu_env, addr, info); + oi = make_memop_idx(memop, idx); + trace_guest_st_before_tcg(tcg_ctx->cpu, cpu_env, addr, oi); if (!TCG_TARGET_HAS_MEMORY_BSWAP && (memop & MO_BSWAP)) { swap = tcg_temp_new_i32(); @@ -2929,7 +2935,7 @@ void tcg_gen_qemu_st_i32(TCGv_i32 val, TCGv addr, TCGArg idx, MemOp memop) } else { gen_ldst_i32(INDEX_op_qemu_st_i32, val, addr, memop, idx); } - plugin_gen_mem_callbacks(addr, info); + plugin_gen_mem_callbacks(addr, oi, QEMU_PLUGIN_MEM_W); if (swap) { tcg_temp_free_i32(swap); @@ -2939,7 +2945,7 @@ void tcg_gen_qemu_st_i32(TCGv_i32 val, TCGv addr, TCGArg idx, MemOp memop) void tcg_gen_qemu_ld_i64(TCGv_i64 val, TCGv addr, TCGArg idx, MemOp memop) { MemOp orig_memop; - uint16_t info; + MemOpIdx oi; if (TCG_TARGET_REG_BITS == 32 && (memop & MO_SIZE) < MO_64) { tcg_gen_qemu_ld_i32(TCGV_LOW(val), addr, idx, memop); @@ -2953,8 +2959,8 @@ void tcg_gen_qemu_ld_i64(TCGv_i64 val, TCGv addr, TCGArg idx, MemOp memop) tcg_gen_req_mo(TCG_MO_LD_LD | TCG_MO_ST_LD); memop = tcg_canonicalize_memop(memop, 1, 0); - info = trace_mem_get_info(memop, idx, 0); - trace_guest_mem_before_tcg(tcg_ctx->cpu, cpu_env, addr, info); + oi = make_memop_idx(memop, idx); + trace_guest_ld_before_tcg(tcg_ctx->cpu, cpu_env, addr, oi); orig_memop = memop; if (!TCG_TARGET_HAS_MEMORY_BSWAP && (memop & MO_BSWAP)) { @@ -2967,7 +2973,7 @@ void tcg_gen_qemu_ld_i64(TCGv_i64 val, TCGv addr, TCGArg idx, MemOp memop) addr = plugin_prep_mem_callbacks(addr); gen_ldst_i64(INDEX_op_qemu_ld_i64, val, addr, memop, idx); - plugin_gen_mem_callbacks(addr, info); + plugin_gen_mem_callbacks(addr, oi, QEMU_PLUGIN_MEM_R); if ((orig_memop ^ memop) & MO_BSWAP) { int flags = (orig_memop & MO_SIGN @@ -2992,7 +2998,7 @@ void tcg_gen_qemu_ld_i64(TCGv_i64 val, TCGv addr, TCGArg idx, MemOp memop) void tcg_gen_qemu_st_i64(TCGv_i64 val, TCGv addr, TCGArg idx, MemOp memop) { TCGv_i64 swap = NULL; - uint16_t info; + MemOpIdx oi; if (TCG_TARGET_REG_BITS == 32 && (memop & MO_SIZE) < MO_64) { tcg_gen_qemu_st_i32(TCGV_LOW(val), addr, idx, memop); @@ -3001,8 +3007,8 @@ void tcg_gen_qemu_st_i64(TCGv_i64 val, TCGv addr, TCGArg idx, MemOp memop) tcg_gen_req_mo(TCG_MO_LD_ST | TCG_MO_ST_ST); memop = tcg_canonicalize_memop(memop, 1, 1); - info = trace_mem_get_info(memop, idx, 1); - trace_guest_mem_before_tcg(tcg_ctx->cpu, cpu_env, addr, info); + oi = make_memop_idx(memop, idx); + trace_guest_st_before_tcg(tcg_ctx->cpu, cpu_env, addr, oi); if (!TCG_TARGET_HAS_MEMORY_BSWAP && (memop & MO_BSWAP)) { swap = tcg_temp_new_i64(); @@ -3025,7 +3031,7 @@ void tcg_gen_qemu_st_i64(TCGv_i64 val, TCGv addr, TCGArg idx, MemOp memop) addr = plugin_prep_mem_callbacks(addr); gen_ldst_i64(INDEX_op_qemu_st_i64, val, addr, memop, idx); - plugin_gen_mem_callbacks(addr, info); + plugin_gen_mem_callbacks(addr, oi, QEMU_PLUGIN_MEM_W); if (swap) { tcg_temp_free_i64(swap); @@ -3095,7 +3101,7 @@ typedef void (*gen_atomic_op_i64)(TCGv_i64, TCGv_env, TCGv, # define WITH_ATOMIC64(X) #endif -static void * const table_cmpxchg[16] = { +static void * const table_cmpxchg[(MO_SIZE | MO_BSWAP) + 1] = { [MO_8] = gen_helper_atomic_cmpxchgb, [MO_16 | MO_LE] = gen_helper_atomic_cmpxchgw_le, [MO_16 | MO_BE] = gen_helper_atomic_cmpxchgw_be, @@ -3129,7 +3135,7 @@ void tcg_gen_atomic_cmpxchg_i32(TCGv_i32 retv, TCGv addr, TCGv_i32 cmpv, tcg_temp_free_i32(t1); } else { gen_atomic_cx_i32 gen; - TCGMemOpIdx oi; + MemOpIdx oi; gen = table_cmpxchg[memop & (MO_SIZE | MO_BSWAP)]; tcg_debug_assert(gen != NULL); @@ -3168,7 +3174,7 @@ void tcg_gen_atomic_cmpxchg_i64(TCGv_i64 retv, TCGv addr, TCGv_i64 cmpv, } else if ((memop & MO_SIZE) == MO_64) { #ifdef CONFIG_ATOMIC64 gen_atomic_cx_i64 gen; - TCGMemOpIdx oi; + MemOpIdx oi; gen = table_cmpxchg[memop & (MO_SIZE | MO_BSWAP)]; tcg_debug_assert(gen != NULL); @@ -3224,7 +3230,7 @@ static void do_atomic_op_i32(TCGv_i32 ret, TCGv addr, TCGv_i32 val, TCGArg idx, MemOp memop, void * const table[]) { gen_atomic_op_i32 gen; - TCGMemOpIdx oi; + MemOpIdx oi; memop = tcg_canonicalize_memop(memop, 0, 0); @@ -3266,7 +3272,7 @@ static void do_atomic_op_i64(TCGv_i64 ret, TCGv addr, TCGv_i64 val, if ((memop & MO_SIZE) == MO_64) { #ifdef CONFIG_ATOMIC64 gen_atomic_op_i64 gen; - TCGMemOpIdx oi; + MemOpIdx oi; gen = table[memop & (MO_SIZE | MO_BSWAP)]; tcg_debug_assert(gen != NULL); @@ -3297,7 +3303,7 @@ static void do_atomic_op_i64(TCGv_i64 ret, TCGv addr, TCGv_i64 val, } #define GEN_ATOMIC_HELPER(NAME, OP, NEW) \ -static void * const table_##NAME[16] = { \ +static void * const table_##NAME[(MO_SIZE | MO_BSWAP) + 1] = { \ [MO_8] = gen_helper_atomic_##NAME##b, \ [MO_16 | MO_LE] = gen_helper_atomic_##NAME##w_le, \ [MO_16 | MO_BE] = gen_helper_atomic_##NAME##w_be, \ diff --git a/tcg/tcg.c b/tcg/tcg.c index 4142d42d77..658be0c6b6 100644 --- a/tcg/tcg.c +++ b/tcg/tcg.c @@ -1910,7 +1910,7 @@ static void tcg_dump_ops(TCGContext *s, bool have_prefs) case INDEX_op_qemu_ld_i64: case INDEX_op_qemu_st_i64: { - TCGMemOpIdx oi = op->args[k++]; + MemOpIdx oi = op->args[k++]; MemOp op = get_memop(oi); unsigned ix = get_mmuidx(oi); diff --git a/tcg/tci.c b/tcg/tci.c index b672c7cae5..5c08dc0a9a 100644 --- a/tcg/tci.c +++ b/tcg/tci.c @@ -61,7 +61,7 @@ static uint64_t tci_uint64(uint32_t high, uint32_t low) * i = immediate (uint32_t) * I = immediate (tcg_target_ulong) * l = label or pointer - * m = immediate (TCGMemOpIdx) + * m = immediate (MemOpIdx) * n = immediate (call return length) * r = register * s = signed ldst offset @@ -105,7 +105,7 @@ static void tci_args_ri(uint32_t insn, TCGReg *r0, tcg_target_ulong *i1) } static void tci_args_rrm(uint32_t insn, TCGReg *r0, - TCGReg *r1, TCGMemOpIdx *m2) + TCGReg *r1, MemOpIdx *m2) { *r0 = extract32(insn, 8, 4); *r1 = extract32(insn, 12, 4); @@ -145,7 +145,7 @@ static void tci_args_rrrc(uint32_t insn, } static void tci_args_rrrm(uint32_t insn, - TCGReg *r0, TCGReg *r1, TCGReg *r2, TCGMemOpIdx *m3) + TCGReg *r0, TCGReg *r1, TCGReg *r2, MemOpIdx *m3) { *r0 = extract32(insn, 8, 4); *r1 = extract32(insn, 12, 4); @@ -289,7 +289,7 @@ static bool tci_compare64(uint64_t u0, uint64_t u1, TCGCond condition) } static uint64_t tci_qemu_ld(CPUArchState *env, target_ulong taddr, - TCGMemOpIdx oi, const void *tb_ptr) + MemOpIdx oi, const void *tb_ptr) { MemOp mop = get_memop(oi) & (MO_BSWAP | MO_SSIZE); uintptr_t ra = (uintptr_t)tb_ptr; @@ -374,7 +374,7 @@ static uint64_t tci_qemu_ld(CPUArchState *env, target_ulong taddr, } static void tci_qemu_st(CPUArchState *env, target_ulong taddr, uint64_t val, - TCGMemOpIdx oi, const void *tb_ptr) + MemOpIdx oi, const void *tb_ptr) { MemOp mop = get_memop(oi) & (MO_BSWAP | MO_SSIZE); uintptr_t ra = (uintptr_t)tb_ptr; @@ -482,7 +482,7 @@ uintptr_t QEMU_DISABLE_CFI tcg_qemu_tb_exec(CPUArchState *env, uint32_t tmp32; uint64_t tmp64; uint64_t T1, T2; - TCGMemOpIdx oi; + MemOpIdx oi; int32_t ofs; void *ptr; @@ -1148,7 +1148,7 @@ int print_insn_tci(bfd_vma addr, disassemble_info *info) tcg_target_ulong i1; int32_t s2; TCGCond c; - TCGMemOpIdx oi; + MemOpIdx oi; uint8_t pos, len; void *ptr; diff --git a/tests/docker/Makefile.include b/tests/docker/Makefile.include index ff5d732889..0806c6f726 100644 --- a/tests/docker/Makefile.include +++ b/tests/docker/Makefile.include @@ -184,7 +184,7 @@ DOCKER_PARTIAL_IMAGES += debian-riscv64-cross DOCKER_PARTIAL_IMAGES += debian-sh4-cross debian-sparc64-cross DOCKER_PARTIAL_IMAGES += debian-tricore-cross DOCKER_PARTIAL_IMAGES += debian-xtensa-cross -DOCKER_PARTIAL_IMAGES += fedora-i386-cross fedora-cris-cross +DOCKER_PARTIAL_IMAGES += fedora-cris-cross # Rules for building linux-user powered images # diff --git a/tests/docker/dockerfiles/fedora-i386-cross.docker b/tests/docker/dockerfiles/fedora-i386-cross.docker index 84f2697b6c..f62a71ce22 100644 --- a/tests/docker/dockerfiles/fedora-i386-cross.docker +++ b/tests/docker/dockerfiles/fedora-i386-cross.docker @@ -18,13 +18,14 @@ ENV PACKAGES \ glibc-static.i686 \ gnutls-devel.i686 \ nettle-devel.i686 \ + pcre-devel.i686 \ perl-Test-Harness \ pixman-devel.i686 \ sysprof-capture-devel.i686 \ zlib-devel.i686 -ENV QEMU_CONFIGURE_OPTS --extra-cflags=-m32 --disable-vhost-user -ENV PKG_CONFIG_PATH /usr/lib/pkgconfig +ENV QEMU_CONFIGURE_OPTS --cpu=i386 --disable-vhost-user +ENV PKG_CONFIG_LIBDIR /usr/lib/pkgconfig RUN dnf update -y && dnf install -y $PACKAGES RUN rpm -q $PACKAGES | sort > /packages.txt diff --git a/tests/qemu-iotests/235 b/tests/qemu-iotests/235 index 8aed45f9a7..4de920c380 100755 --- a/tests/qemu-iotests/235 +++ b/tests/qemu-iotests/235 @@ -24,8 +24,6 @@ import os import iotests from iotests import qemu_img_create, qemu_io, file_path, log -sys.path.append(os.path.join(os.path.dirname(__file__), '..', '..', 'python')) - from qemu.machine import QEMUMachine iotests.script_initialize(supported_fmts=['qcow2']) diff --git a/tests/qemu-iotests/297 b/tests/qemu-iotests/297 index b04cba5366..91ec34d952 100755 --- a/tests/qemu-iotests/297 +++ b/tests/qemu-iotests/297 @@ -68,44 +68,34 @@ def run_linters(): # Todo notes are fine, but fixme's or xxx's should probably just be # fixed (in tests, at least) env = os.environ.copy() - qemu_module_path = os.path.join(os.path.dirname(__file__), - '..', '..', 'python') - try: - env['PYTHONPATH'] += os.pathsep + qemu_module_path - except KeyError: - env['PYTHONPATH'] = qemu_module_path subprocess.run(('pylint-3', '--score=n', '--notes=FIXME,XXX', *files), env=env, check=False) print('=== mypy ===') sys.stdout.flush() - # We have to call mypy separately for each file. Otherwise, it - # will interpret all given files as belonging together (i.e., they - # may not both define the same classes, etc.; most notably, they - # must not both define the __main__ module). env['MYPYPATH'] = env['PYTHONPATH'] - for filename in files: - p = subprocess.run(('mypy', - '--warn-unused-configs', - '--disallow-subclassing-any', - '--disallow-any-generics', - '--disallow-incomplete-defs', - '--disallow-untyped-decorators', - '--no-implicit-optional', - '--warn-redundant-casts', - '--warn-unused-ignores', - '--no-implicit-reexport', - '--namespace-packages', - filename), - env=env, - check=False, - stdout=subprocess.PIPE, - stderr=subprocess.STDOUT, - universal_newlines=True) - - if p.returncode != 0: - print(p.stdout) + p = subprocess.run(('mypy', + '--warn-unused-configs', + '--disallow-subclassing-any', + '--disallow-any-generics', + '--disallow-incomplete-defs', + '--disallow-untyped-decorators', + '--no-implicit-optional', + '--warn-redundant-casts', + '--warn-unused-ignores', + '--no-implicit-reexport', + '--namespace-packages', + '--scripts-are-modules', + *files), + env=env, + check=False, + stdout=subprocess.PIPE, + stderr=subprocess.STDOUT, + universal_newlines=True) + + if p.returncode != 0: + print(p.stdout) for linter in ('pylint-3', 'mypy'): diff --git a/tests/qemu-iotests/300 b/tests/qemu-iotests/300 index fe94de84ed..10f9f2a8da 100755 --- a/tests/qemu-iotests/300 +++ b/tests/qemu-iotests/300 @@ -24,11 +24,10 @@ import random import re from typing import Dict, List, Optional +from qemu.machine import machine + import iotests -# Import qemu after iotests.py has amended sys.path -# pylint: disable=wrong-import-order -from qemu.machine import machine BlockBitmapMapping = List[Dict[str, object]] diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py index ce06cf5630..b06ad76e0c 100644 --- a/tests/qemu-iotests/iotests.py +++ b/tests/qemu-iotests/iotests.py @@ -36,8 +36,6 @@ import unittest from contextlib import contextmanager -# pylint: disable=import-error, wrong-import-position -sys.path.append(os.path.join(os.path.dirname(__file__), '..', '..', 'python')) from qemu.machine import qtest from qemu.qmp import QMPMessage diff --git a/tests/qemu-iotests/pylintrc b/tests/qemu-iotests/pylintrc index f2c0b522ac..8cb4e1d6a6 100644 --- a/tests/qemu-iotests/pylintrc +++ b/tests/qemu-iotests/pylintrc @@ -19,13 +19,17 @@ disable=invalid-name, too-many-public-methods, # pylint warns about Optional[] etc. as unsubscriptable in 3.9 unsubscriptable-object, + # pylint's static analysis causes false positivies for file_path(); + # If we really care to make it statically knowable, we'll use mypy. + unbalanced-tuple-unpacking, # Sometimes we need to disable a newly introduced pylint warning. # Doing so should not produce a warning in older versions of pylint. bad-option-value, # These are temporary, and should be removed: missing-docstring, too-many-return-statements, - too-many-statements + too-many-statements, + consider-using-f-string, [FORMAT] diff --git a/tests/qemu-iotests/testenv.py b/tests/qemu-iotests/testenv.py index 70da0d60c8..99a57a69f3 100644 --- a/tests/qemu-iotests/testenv.py +++ b/tests/qemu-iotests/testenv.py @@ -108,12 +108,15 @@ class TestEnv(ContextManager['TestEnv']): SAMPLE_IMG_DIR OUTPUT_DIR """ - self.pythonpath = os.getenv('PYTHONPATH') - if self.pythonpath: - self.pythonpath = self.source_iotests + os.pathsep + \ - self.pythonpath - else: - self.pythonpath = self.source_iotests + + # Path where qemu goodies live in this source tree. + qemu_srctree_path = Path(__file__, '../../../python').resolve() + + self.pythonpath = os.pathsep.join(filter(None, ( + self.source_iotests, + str(qemu_srctree_path), + os.getenv('PYTHONPATH'), + ))) self.test_dir = os.getenv('TEST_DIR', os.path.join(os.getcwd(), 'scratch')) diff --git a/tests/qemu-iotests/testrunner.py b/tests/qemu-iotests/testrunner.py index 4a6ec421ed..a56b6da396 100644 --- a/tests/qemu-iotests/testrunner.py +++ b/tests/qemu-iotests/testrunner.py @@ -266,12 +266,13 @@ class TestRunner(ContextManager['TestRunner']): diff=file_diff(str(f_reference), str(f_bad))) if f_notrun.exists(): - return TestResult(status='not run', - description=f_notrun.read_text().strip()) + return TestResult( + status='not run', + description=f_notrun.read_text(encoding='utf-8').strip()) casenotrun = '' if f_casenotrun.exists(): - casenotrun = f_casenotrun.read_text() + casenotrun = f_casenotrun.read_text(encoding='utf-8') diff = file_diff(str(f_reference), str(f_bad)) if diff: diff --git a/tests/qemu-iotests/tests/image-fleecing b/tests/qemu-iotests/tests/image-fleecing index f6318492c6..35164e9036 100755 --- a/tests/qemu-iotests/tests/image-fleecing +++ b/tests/qemu-iotests/tests/image-fleecing @@ -28,6 +28,7 @@ from iotests import log, qemu_img, qemu_io, qemu_io_silent iotests.script_initialize( supported_fmts=['qcow2', 'qcow', 'qed', 'vmdk', 'vhdx', 'raw'], supported_platforms=['linux'], + required_fmts=['copy-before-write'], ) patterns = [('0x5d', '0', '64k'), diff --git a/tests/qemu-iotests/tests/migrate-bitmaps-test b/tests/qemu-iotests/tests/migrate-bitmaps-test index dc431c35b3..c23df3d75c 100755 --- a/tests/qemu-iotests/tests/migrate-bitmaps-test +++ b/tests/qemu-iotests/tests/migrate-bitmaps-test @@ -19,10 +19,11 @@ # along with this program. If not, see <http://www.gnu.org/licenses/>. # -import os import itertools import operator +import os import re + import iotests from iotests import qemu_img, qemu_img_create, Timeout @@ -224,25 +225,6 @@ def inject_test_case(klass, suffix, method, *args, **kwargs): setattr(klass, 'test_' + method + suffix, lambda self: mc(self)) -for cmb in list(itertools.product((True, False), repeat=5)): - name = ('_' if cmb[0] else '_not_') + 'persistent_' - name += ('_' if cmb[1] else '_not_') + 'migbitmap_' - name += '_online' if cmb[2] else '_offline' - name += '_shared' if cmb[3] else '_nonshared' - if cmb[4]: - name += '__pre_shutdown' - - inject_test_case(TestDirtyBitmapMigration, name, 'do_test_migration', - *list(cmb)) - -for cmb in list(itertools.product((True, False), repeat=2)): - name = ('_' if cmb[0] else '_not_') + 'persistent_' - name += ('_' if cmb[1] else '_not_') + 'migbitmap' - - inject_test_case(TestDirtyBitmapMigration, name, - 'do_test_migration_resume_source', *list(cmb)) - - class TestDirtyBitmapBackingMigration(iotests.QMPTestCase): def setUp(self): qemu_img_create('-f', iotests.imgfmt, base_a, size) @@ -304,6 +286,30 @@ class TestDirtyBitmapBackingMigration(iotests.QMPTestCase): self.assert_qmp(result, 'return', {}) +def main() -> None: + for cmb in list(itertools.product((True, False), repeat=5)): + name = ('_' if cmb[0] else '_not_') + 'persistent_' + name += ('_' if cmb[1] else '_not_') + 'migbitmap_' + name += '_online' if cmb[2] else '_offline' + name += '_shared' if cmb[3] else '_nonshared' + if cmb[4]: + name += '__pre_shutdown' + + inject_test_case(TestDirtyBitmapMigration, name, 'do_test_migration', + *list(cmb)) + + for cmb in list(itertools.product((True, False), repeat=2)): + name = ('_' if cmb[0] else '_not_') + 'persistent_' + name += ('_' if cmb[1] else '_not_') + 'migbitmap' + + inject_test_case(TestDirtyBitmapMigration, name, + 'do_test_migration_resume_source', *list(cmb)) + + iotests.main( + supported_fmts=['qcow2'], + supported_protocols=['file'] + ) + + if __name__ == '__main__': - iotests.main(supported_fmts=['qcow2'], - supported_protocols=['file']) + main() diff --git a/tests/qemu-iotests/tests/mirror-top-perms b/tests/qemu-iotests/tests/mirror-top-perms index 2fc8dd66e0..3d475aa3a5 100755 --- a/tests/qemu-iotests/tests/mirror-top-perms +++ b/tests/qemu-iotests/tests/mirror-top-perms @@ -20,13 +20,13 @@ # import os + +from qemu import qmp +from qemu.machine import machine + import iotests from iotests import qemu_img -# Import qemu after iotests.py has amended sys.path -# pylint: disable=wrong-import-order -import qemu - image_size = 1 * 1024 * 1024 source = os.path.join(iotests.test_dir, 'source.img') @@ -47,7 +47,7 @@ class TestMirrorTopPerms(iotests.QMPTestCase): def tearDown(self): try: self.vm.shutdown() - except qemu.machine.machine.AbnormalShutdown: + except machine.AbnormalShutdown: pass if self.vm_b is not None: @@ -102,7 +102,7 @@ class TestMirrorTopPerms(iotests.QMPTestCase): self.vm_b.launch() print('ERROR: VM B launched successfully, this should not have ' 'happened') - except qemu.qmp.QMPConnectError: + except qmp.QMPConnectError: assert 'Is another process using the image' in self.vm_b.get_log() result = self.vm.qmp('block-job-cancel', diff --git a/trace-events b/trace-events index c4cca29939..a637a61eba 100644 --- a/trace-events +++ b/trace-events @@ -120,26 +120,16 @@ vcpu guest_cpu_reset(void) # tcg/tcg-op.c # @vaddr: Access' virtual address. -# @info : Access' information (see below). +# @memopidx: Access' information (see below). # # Start virtual memory access (before any potential access violation). -# # Does not include memory accesses performed by devices. # -# Access information can be parsed as: -# -# struct mem_info { -# uint8_t size_shift : 4; /* interpreted as "1 << size_shift" bytes */ -# bool sign_extend: 1; /* sign-extended */ -# uint8_t endianness : 1; /* 0: little, 1: big */ -# bool store : 1; /* whether it is a store operation */ -# pad : 1; -# uint8_t mmuidx : 4; /* mmuidx (softmmu only) */ -# }; -# # Mode: user, softmmu # Targets: TCG(all) -vcpu tcg guest_mem_before(TCGv vaddr, uint16_t info) "info=%d", "vaddr=0x%016"PRIx64" info=%d" +vcpu tcg guest_ld_before(TCGv vaddr, uint32_t memopidx) "info=%d", "vaddr=0x%016"PRIx64" memopidx=0x%x" +vcpu tcg guest_st_before(TCGv vaddr, uint32_t memopidx) "info=%d", "vaddr=0x%016"PRIx64" memopidx=0x%x" +vcpu tcg guest_rmw_before(TCGv vaddr, uint32_t memopidx) "info=%d", "vaddr=0x%016"PRIx64" memopidx=0x%x" # include/user/syscall-trace.h diff --git a/trace/mem.h b/trace/mem.h deleted file mode 100644 index 2f27e7bdf0..0000000000 --- a/trace/mem.h +++ /dev/null @@ -1,63 +0,0 @@ -/* - * Helper functions for guest memory tracing - * - * Copyright (C) 2016 Lluís Vilanova <vilanova@ac.upc.edu> - * - * 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 TRACE__MEM_H -#define TRACE__MEM_H - -#include "tcg/tcg.h" - -#define TRACE_MEM_SZ_SHIFT_MASK 0xf /* size shift mask */ -#define TRACE_MEM_SE (1ULL << 4) /* sign extended (y/n) */ -#define TRACE_MEM_BE (1ULL << 5) /* big endian (y/n) */ -#define TRACE_MEM_ST (1ULL << 6) /* store (y/n) */ -#define TRACE_MEM_MMU_SHIFT 8 /* mmu idx */ - -/** - * trace_mem_build_info: - * - * Return a value for the 'info' argument in guest memory access traces. - */ -static inline uint16_t trace_mem_build_info(int size_shift, bool sign_extend, - MemOp endianness, bool store, - unsigned int mmu_idx) -{ - uint16_t res; - - res = size_shift & TRACE_MEM_SZ_SHIFT_MASK; - if (sign_extend) { - res |= TRACE_MEM_SE; - } - if (endianness == MO_BE) { - res |= TRACE_MEM_BE; - } - if (store) { - res |= TRACE_MEM_ST; - } -#ifdef CONFIG_SOFTMMU - res |= mmu_idx << TRACE_MEM_MMU_SHIFT; -#endif - return res; -} - - -/** - * trace_mem_get_info: - * - * Return a value for the 'info' argument in guest memory access traces. - */ -static inline uint16_t trace_mem_get_info(MemOp op, - unsigned int mmu_idx, - bool store) -{ - return trace_mem_build_info(op & MO_SIZE, !!(op & MO_SIGN), - op & MO_BSWAP, store, - mmu_idx); -} - -#endif /* TRACE__MEM_H */ |