From e4fe830b50b56561dae5b5c79c6eb63cc2e94a3d Mon Sep 17 00:00:00 2001 From: Peter Maydell Date: Sat, 4 Jan 2014 22:15:45 +0000 Subject: target-arm: Widen thread-local register state fields to 64 bits The common pattern for system registers in a 64-bit capable ARM CPU is that when in AArch32 the cp15 register is a view of the bottom 32 bits of the 64-bit AArch64 system register; writes in AArch32 leave the top half unchanged. The most natural way to model this is to have the state field in the CPU struct be a 64 bit value, and simply have the AArch32 TCG code operate on a pointer to its lower half. For aarch64-linux-user the only registers we need to share like this are the thread-local-storage ones. Widen their fields to 64 bits and provide the 64 bit reginfo struct to make them visible in AArch64 state. Note that minor cleanup of the AArch64 system register encoding space means We can share the TPIDR_EL1 reginfo but need split encodings for TPIDR_EL0 and TPIDRRO_EL0. Since we're touching almost every line in QEMU that uses the c13_tls* fields in this patch anyway, we take the opportunity to rename them in line with the standard ARM architectural names for these registers. Signed-off-by: Peter Maydell Reviewed-by: Richard Henderson --- linux-user/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'linux-user/main.c') diff --git a/linux-user/main.c b/linux-user/main.c index 54f71fe8f6..c0df8b5cd4 100644 --- a/linux-user/main.c +++ b/linux-user/main.c @@ -566,7 +566,7 @@ do_kernel_trap(CPUARMState *env) end_exclusive(); break; case 0xffff0fe0: /* __kernel_get_tls */ - env->regs[0] = env->cp15.c13_tls2; + env->regs[0] = env->cp15.tpidrro_el0; break; case 0xffff0f60: /* __kernel_cmpxchg64 */ arm_kernel_cmpxchg64_helper(env); -- cgit v1.2.3-55-g7522 From 03d05e2d0765512fb960192b6e9f9a41c47282bd Mon Sep 17 00:00:00 2001 From: Peter Maydell Date: Sat, 4 Jan 2014 22:15:47 +0000 Subject: target-arm: Widen exclusive-access support struct fields to 64 bits In preparation for adding support for A64 load/store exclusive instructions, widen the fields in the CPU state struct that deal with address and data values for exclusives from 32 to 64 bits. Although in practice AArch64 and AArch32 exclusive accesses will be generally separate there are some odd theoretical corner cases (eg you should be able to do the exclusive load in AArch32, take an exception to AArch64 and successfully do the store exclusive there), and it's also easier to reason about. The changes in semantics for the variables are: exclusive_addr -> extended to 64 bits; -1ULL for "monitor lost", otherwise always < 2^32 for AArch32 exclusive_val -> extended to 64 bits. 64 bit exclusives in AArch32 now use the high half of exclusive_val instead of a separate exclusive_high exclusive_high -> is no longer used in AArch32; extended to 64 bits as it will be needed for AArch64's pair-of-64-bit-values exclusives. exclusive_test -> extended to 64 bits, as it is an address. Since this is a linux-user-only field, in arm-linux-user it will always have the top 32 bits zero. exclusive_info -> stays 32 bits, as it is neither data nor address, but simply holds register indexes etc. AArch64 will be able to fit all its information into 32 bits as well. Note that the refactoring of gen_store_exclusive() coincidentally fixes a minor bug where ldrexd would incorrectly update the first CPU register even if the load for the second register faulted. Signed-off-by: Peter Maydell Reviewed-by: Richard Henderson --- linux-user/main.c | 25 +++++++++++-------- target-arm/cpu.h | 8 +++---- target-arm/machine.c | 12 +++++----- target-arm/translate.c | 65 ++++++++++++++++++++++++++++++-------------------- 4 files changed, 64 insertions(+), 46 deletions(-) (limited to 'linux-user/main.c') diff --git a/linux-user/main.c b/linux-user/main.c index c0df8b5cd4..20f9832d38 100644 --- a/linux-user/main.c +++ b/linux-user/main.c @@ -589,16 +589,21 @@ do_kernel_trap(CPUARMState *env) static int do_strex(CPUARMState *env) { - uint32_t val; + uint64_t val; int size; int rc = 1; int segv = 0; uint32_t addr; start_exclusive(); - addr = env->exclusive_addr; - if (addr != env->exclusive_test) { + if (env->exclusive_addr != env->exclusive_test) { goto fail; } + /* We know we're always AArch32 so the address is in uint32_t range + * unless it was the -1 exclusive-monitor-lost value (which won't + * match exclusive_test above). + */ + assert(extract64(env->exclusive_addr, 32, 32) == 0); + addr = env->exclusive_addr; size = env->exclusive_info & 0xf; switch (size) { case 0: @@ -618,19 +623,19 @@ static int do_strex(CPUARMState *env) env->cp15.c6_data = addr; goto done; } - if (val != env->exclusive_val) { - goto fail; - } if (size == 3) { - segv = get_user_u32(val, addr + 4); + uint32_t valhi; + segv = get_user_u32(valhi, addr + 4); if (segv) { env->cp15.c6_data = addr + 4; goto done; } - if (val != env->exclusive_high) { - goto fail; - } + val = deposit64(val, 32, 32, valhi); + } + if (val != env->exclusive_val) { + goto fail; } + val = env->regs[(env->exclusive_info >> 8) & 0xf]; switch (size) { case 0: diff --git a/target-arm/cpu.h b/target-arm/cpu.h index 983aa31bef..6fbbab2c7f 100644 --- a/target-arm/cpu.h +++ b/target-arm/cpu.h @@ -278,11 +278,11 @@ typedef struct CPUARMState { float_status fp_status; float_status standard_fp_status; } vfp; - uint32_t exclusive_addr; - uint32_t exclusive_val; - uint32_t exclusive_high; + uint64_t exclusive_addr; + uint64_t exclusive_val; + uint64_t exclusive_high; #if defined(CONFIG_USER_ONLY) - uint32_t exclusive_test; + uint64_t exclusive_test; uint32_t exclusive_info; #endif diff --git a/target-arm/machine.c b/target-arm/machine.c index 74f010f637..8f9e7d4d28 100644 --- a/target-arm/machine.c +++ b/target-arm/machine.c @@ -222,9 +222,9 @@ static int cpu_post_load(void *opaque, int version_id) const VMStateDescription vmstate_arm_cpu = { .name = "cpu", - .version_id = 13, - .minimum_version_id = 13, - .minimum_version_id_old = 13, + .version_id = 14, + .minimum_version_id = 14, + .minimum_version_id_old = 14, .pre_save = cpu_pre_save, .post_load = cpu_post_load, .fields = (VMStateField[]) { @@ -253,9 +253,9 @@ const VMStateDescription vmstate_arm_cpu = { VMSTATE_VARRAY_INT32(cpreg_vmstate_values, ARMCPU, cpreg_vmstate_array_len, 0, vmstate_info_uint64, uint64_t), - VMSTATE_UINT32(env.exclusive_addr, ARMCPU), - VMSTATE_UINT32(env.exclusive_val, ARMCPU), - VMSTATE_UINT32(env.exclusive_high, ARMCPU), + VMSTATE_UINT64(env.exclusive_addr, ARMCPU), + VMSTATE_UINT64(env.exclusive_val, ARMCPU), + VMSTATE_UINT64(env.exclusive_high, ARMCPU), VMSTATE_UINT64(env.features, ARMCPU), VMSTATE_TIMER(gt_timer[GTIMER_PHYS], ARMCPU), VMSTATE_TIMER(gt_timer[GTIMER_VIRT], ARMCPU), diff --git a/target-arm/translate.c b/target-arm/translate.c index 8bfe95007e..4387547a9c 100644 --- a/target-arm/translate.c +++ b/target-arm/translate.c @@ -61,11 +61,10 @@ TCGv_ptr cpu_env; static TCGv_i64 cpu_V0, cpu_V1, cpu_M0; static TCGv_i32 cpu_R[16]; static TCGv_i32 cpu_CF, cpu_NF, cpu_VF, cpu_ZF; -static TCGv_i32 cpu_exclusive_addr; -static TCGv_i32 cpu_exclusive_val; -static TCGv_i32 cpu_exclusive_high; +static TCGv_i64 cpu_exclusive_addr; +static TCGv_i64 cpu_exclusive_val; #ifdef CONFIG_USER_ONLY -static TCGv_i32 cpu_exclusive_test; +static TCGv_i64 cpu_exclusive_test; static TCGv_i32 cpu_exclusive_info; #endif @@ -96,14 +95,12 @@ void arm_translate_init(void) cpu_VF = tcg_global_mem_new_i32(TCG_AREG0, offsetof(CPUARMState, VF), "VF"); cpu_ZF = tcg_global_mem_new_i32(TCG_AREG0, offsetof(CPUARMState, ZF), "ZF"); - cpu_exclusive_addr = tcg_global_mem_new_i32(TCG_AREG0, + cpu_exclusive_addr = tcg_global_mem_new_i64(TCG_AREG0, offsetof(CPUARMState, exclusive_addr), "exclusive_addr"); - cpu_exclusive_val = tcg_global_mem_new_i32(TCG_AREG0, + cpu_exclusive_val = tcg_global_mem_new_i64(TCG_AREG0, offsetof(CPUARMState, exclusive_val), "exclusive_val"); - cpu_exclusive_high = tcg_global_mem_new_i32(TCG_AREG0, - offsetof(CPUARMState, exclusive_high), "exclusive_high"); #ifdef CONFIG_USER_ONLY - cpu_exclusive_test = tcg_global_mem_new_i32(TCG_AREG0, + cpu_exclusive_test = tcg_global_mem_new_i64(TCG_AREG0, offsetof(CPUARMState, exclusive_test), "exclusive_test"); cpu_exclusive_info = tcg_global_mem_new_i32(TCG_AREG0, offsetof(CPUARMState, exclusive_info), "exclusive_info"); @@ -6758,30 +6755,34 @@ static void gen_load_exclusive(DisasContext *s, int rt, int rt2, default: abort(); } - tcg_gen_mov_i32(cpu_exclusive_val, tmp); - store_reg(s, rt, tmp); + if (size == 3) { TCGv_i32 tmp2 = tcg_temp_new_i32(); + TCGv_i32 tmp3 = tcg_temp_new_i32(); + tcg_gen_addi_i32(tmp2, addr, 4); - tmp = tcg_temp_new_i32(); - gen_aa32_ld32u(tmp, tmp2, IS_USER(s)); + gen_aa32_ld32u(tmp3, tmp2, IS_USER(s)); tcg_temp_free_i32(tmp2); - tcg_gen_mov_i32(cpu_exclusive_high, tmp); - store_reg(s, rt2, tmp); + tcg_gen_concat_i32_i64(cpu_exclusive_val, tmp, tmp3); + store_reg(s, rt2, tmp3); + } else { + tcg_gen_extu_i32_i64(cpu_exclusive_val, tmp); } - tcg_gen_mov_i32(cpu_exclusive_addr, addr); + + store_reg(s, rt, tmp); + tcg_gen_extu_i32_i64(cpu_exclusive_addr, addr); } static void gen_clrex(DisasContext *s) { - tcg_gen_movi_i32(cpu_exclusive_addr, -1); + tcg_gen_movi_i64(cpu_exclusive_addr, -1); } #ifdef CONFIG_USER_ONLY static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2, TCGv_i32 addr, int size) { - tcg_gen_mov_i32(cpu_exclusive_test, addr); + tcg_gen_extu_i32_i64(cpu_exclusive_test, addr); tcg_gen_movi_i32(cpu_exclusive_info, size | (rd << 4) | (rt << 8) | (rt2 << 12)); gen_exception_insn(s, 4, EXCP_STREX); @@ -6791,6 +6792,7 @@ static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2, TCGv_i32 addr, int size) { TCGv_i32 tmp; + TCGv_i64 val64, extaddr; int done_label; int fail_label; @@ -6802,7 +6804,11 @@ static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2, } */ fail_label = gen_new_label(); done_label = gen_new_label(); - tcg_gen_brcond_i32(TCG_COND_NE, addr, cpu_exclusive_addr, fail_label); + extaddr = tcg_temp_new_i64(); + tcg_gen_extu_i32_i64(extaddr, addr); + tcg_gen_brcond_i64(TCG_COND_NE, extaddr, cpu_exclusive_addr, fail_label); + tcg_temp_free_i64(extaddr); + tmp = tcg_temp_new_i32(); switch (size) { case 0: @@ -6818,17 +6824,24 @@ static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2, default: abort(); } - tcg_gen_brcond_i32(TCG_COND_NE, tmp, cpu_exclusive_val, fail_label); - tcg_temp_free_i32(tmp); + + val64 = tcg_temp_new_i64(); if (size == 3) { TCGv_i32 tmp2 = tcg_temp_new_i32(); + TCGv_i32 tmp3 = tcg_temp_new_i32(); tcg_gen_addi_i32(tmp2, addr, 4); - tmp = tcg_temp_new_i32(); - gen_aa32_ld32u(tmp, tmp2, IS_USER(s)); + gen_aa32_ld32u(tmp3, tmp2, IS_USER(s)); tcg_temp_free_i32(tmp2); - tcg_gen_brcond_i32(TCG_COND_NE, tmp, cpu_exclusive_high, fail_label); - tcg_temp_free_i32(tmp); + tcg_gen_concat_i32_i64(val64, tmp, tmp3); + tcg_temp_free_i32(tmp3); + } else { + tcg_gen_extu_i32_i64(val64, tmp); } + tcg_temp_free_i32(tmp); + + tcg_gen_brcond_i64(TCG_COND_NE, val64, cpu_exclusive_val, fail_label); + tcg_temp_free_i64(val64); + tmp = load_reg(s, rt); switch (size) { case 0: @@ -6856,7 +6869,7 @@ static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2, gen_set_label(fail_label); tcg_gen_movi_i32(cpu_R[rd], 1); gen_set_label(done_label); - tcg_gen_movi_i32(cpu_exclusive_addr, -1); + tcg_gen_movi_i64(cpu_exclusive_addr, -1); } #endif -- cgit v1.2.3-55-g7522 From fa2ef212dff8556ea92c4aef54b57efec69ca6fe Mon Sep 17 00:00:00 2001 From: Michael Matz Date: Sat, 4 Jan 2014 22:15:47 +0000 Subject: target-arm: A64: support for ld/st/cl exclusive This implement exclusive loads/stores for aarch64 along the lines of arm32 and ppc implementations. The exclusive load remembers the address and loaded value. The exclusive store throws an an exception which uses those values to check for equality in a proper exclusive region. This is not actually the architecture mandated semantics (for either AArch32 or AArch64) but it is close enough for typical guest code sequences to work correctly, and saves us from having to monitor all guest stores. It's fairly easy to come up with test cases where we don't behave like hardware - we don't for example model cache line behaviour. However in the common patterns this works, and the existing 32 bit ARM exclusive access implementation has the same limitations. AArch64 also implements new acquire/release loads/stores (which may be either exclusive or non-exclusive). These imposes extra ordering constraints on memory operations (ie they act as if they have an implicit barrier built into them). As TCG is single-threaded all our barriers are no-ops, so these just behave like normal loads and stores. Signed-off-by: Michael Matz Signed-off-by: Alex Bennée Signed-off-by: Peter Maydell Reviewed-by: Richard Henderson --- linux-user/main.c | 127 +++++++++++++++++++++++++++++++++++- target-arm/translate-a64.c | 156 ++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 277 insertions(+), 6 deletions(-) (limited to 'linux-user/main.c') diff --git a/linux-user/main.c b/linux-user/main.c index 20f9832d38..cabc9e1a0e 100644 --- a/linux-user/main.c +++ b/linux-user/main.c @@ -585,8 +585,8 @@ do_kernel_trap(CPUARMState *env) return 0; } -#endif +/* Store exclusive handling for AArch32 */ static int do_strex(CPUARMState *env) { uint64_t val; @@ -670,7 +670,6 @@ done: return segv; } -#ifdef TARGET_ABI32 void cpu_loop(CPUARMState *env) { CPUState *cs = CPU(arm_env_get_cpu(env)); @@ -885,6 +884,122 @@ void cpu_loop(CPUARMState *env) #else +/* + * Handle AArch64 store-release exclusive + * + * rs = gets the status result of store exclusive + * rt = is the register that is stored + * rt2 = is the second register store (in STP) + * + */ +static int do_strex_a64(CPUARMState *env) +{ + uint64_t val; + int size; + bool is_pair; + int rc = 1; + int segv = 0; + uint64_t addr; + int rs, rt, rt2; + + start_exclusive(); + /* size | is_pair << 2 | (rs << 4) | (rt << 9) | (rt2 << 14)); */ + size = extract32(env->exclusive_info, 0, 2); + is_pair = extract32(env->exclusive_info, 2, 1); + rs = extract32(env->exclusive_info, 4, 5); + rt = extract32(env->exclusive_info, 9, 5); + rt2 = extract32(env->exclusive_info, 14, 5); + + addr = env->exclusive_addr; + + if (addr != env->exclusive_test) { + goto finish; + } + + switch (size) { + case 0: + segv = get_user_u8(val, addr); + break; + case 1: + segv = get_user_u16(val, addr); + break; + case 2: + segv = get_user_u32(val, addr); + break; + case 3: + segv = get_user_u64(val, addr); + break; + default: + abort(); + } + if (segv) { + env->cp15.c6_data = addr; + goto error; + } + if (val != env->exclusive_val) { + goto finish; + } + if (is_pair) { + if (size == 2) { + segv = get_user_u32(val, addr + 4); + } else { + segv = get_user_u64(val, addr + 8); + } + if (segv) { + env->cp15.c6_data = addr + (size == 2 ? 4 : 8); + goto error; + } + if (val != env->exclusive_high) { + goto finish; + } + } + val = env->xregs[rt]; + switch (size) { + case 0: + segv = put_user_u8(val, addr); + break; + case 1: + segv = put_user_u16(val, addr); + break; + case 2: + segv = put_user_u32(val, addr); + break; + case 3: + segv = put_user_u64(val, addr); + break; + } + if (segv) { + goto error; + } + if (is_pair) { + val = env->xregs[rt2]; + if (size == 2) { + segv = put_user_u32(val, addr + 4); + } else { + segv = put_user_u64(val, addr + 8); + } + if (segv) { + env->cp15.c6_data = addr + (size == 2 ? 4 : 8); + goto error; + } + } + rc = 0; +finish: + env->pc += 4; + /* rs == 31 encodes a write to the ZR, thus throwing away + * the status return. This is rather silly but valid. + */ + if (rs < 31) { + env->xregs[rs] = rc; + } +error: + /* instruction faulted, PC does not advance */ + /* either way a strex releases any exclusive lock we have */ + env->exclusive_addr = -1; + end_exclusive(); + return segv; +} + /* AArch64 main loop */ void cpu_loop(CPUARMState *env) { @@ -944,7 +1059,7 @@ void cpu_loop(CPUARMState *env) } break; case EXCP_STREX: - if (do_strex(env)) { + if (do_strex_a64(env)) { addr = env->cp15.c6_data; goto do_segv; } @@ -956,6 +1071,12 @@ void cpu_loop(CPUARMState *env) abort(); } process_pending_signals(env); + /* Exception return on AArch64 always clears the exclusive monitor, + * so any return to running guest code implies this. + * A strex (successful or otherwise) also clears the monitor, so + * we don't need to specialcase EXCP_STREX. + */ + env->exclusive_addr = -1; } } #endif /* ndef TARGET_ABI32 */ diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c index 61974419cd..40c6fc4a9b 100644 --- a/target-arm/translate-a64.c +++ b/target-arm/translate-a64.c @@ -38,6 +38,15 @@ static TCGv_i64 cpu_X[32]; static TCGv_i64 cpu_pc; static TCGv_i32 cpu_NF, cpu_ZF, cpu_CF, cpu_VF; +/* Load/store exclusive handling */ +static TCGv_i64 cpu_exclusive_addr; +static TCGv_i64 cpu_exclusive_val; +static TCGv_i64 cpu_exclusive_high; +#ifdef CONFIG_USER_ONLY +static TCGv_i64 cpu_exclusive_test; +static TCGv_i32 cpu_exclusive_info; +#endif + static const char *regnames[] = { "x0", "x1", "x2", "x3", "x4", "x5", "x6", "x7", "x8", "x9", "x10", "x11", "x12", "x13", "x14", "x15", @@ -70,6 +79,19 @@ void a64_translate_init(void) cpu_ZF = tcg_global_mem_new_i32(TCG_AREG0, offsetof(CPUARMState, ZF), "ZF"); cpu_CF = tcg_global_mem_new_i32(TCG_AREG0, offsetof(CPUARMState, CF), "CF"); cpu_VF = tcg_global_mem_new_i32(TCG_AREG0, offsetof(CPUARMState, VF), "VF"); + + cpu_exclusive_addr = tcg_global_mem_new_i64(TCG_AREG0, + offsetof(CPUARMState, exclusive_addr), "exclusive_addr"); + cpu_exclusive_val = tcg_global_mem_new_i64(TCG_AREG0, + offsetof(CPUARMState, exclusive_val), "exclusive_val"); + cpu_exclusive_high = tcg_global_mem_new_i64(TCG_AREG0, + offsetof(CPUARMState, exclusive_high), "exclusive_high"); +#ifdef CONFIG_USER_ONLY + cpu_exclusive_test = tcg_global_mem_new_i64(TCG_AREG0, + offsetof(CPUARMState, exclusive_test), "exclusive_test"); + cpu_exclusive_info = tcg_global_mem_new_i32(TCG_AREG0, + offsetof(CPUARMState, exclusive_info), "exclusive_info"); +#endif } void aarch64_cpu_dump_state(CPUState *cs, FILE *f, @@ -767,6 +789,11 @@ static void handle_hint(DisasContext *s, uint32_t insn, } } +static void gen_clrex(DisasContext *s, uint32_t insn) +{ + tcg_gen_movi_i64(cpu_exclusive_addr, -1); +} + /* CLREX, DSB, DMB, ISB */ static void handle_sync(DisasContext *s, uint32_t insn, unsigned int op1, unsigned int op2, unsigned int crm) @@ -778,7 +805,7 @@ static void handle_sync(DisasContext *s, uint32_t insn, switch (op2) { case 2: /* CLREX */ - unsupported_encoding(s, insn); + gen_clrex(s, insn); return; case 4: /* DSB */ case 5: /* DMB */ @@ -1106,10 +1133,133 @@ static void disas_b_exc_sys(DisasContext *s, uint32_t insn) } } -/* Load/store exclusive */ +/* + * Load/Store exclusive instructions are implemented by remembering + * the value/address loaded, and seeing if these are the same + * when the store is performed. This is not actually the architecturally + * mandated semantics, but it works for typical guest code sequences + * and avoids having to monitor regular stores. + * + * In system emulation mode only one CPU will be running at once, so + * this sequence is effectively atomic. In user emulation mode we + * throw an exception and handle the atomic operation elsewhere. + */ +static void gen_load_exclusive(DisasContext *s, int rt, int rt2, + TCGv_i64 addr, int size, bool is_pair) +{ + TCGv_i64 tmp = tcg_temp_new_i64(); + TCGMemOp memop = MO_TE + size; + + g_assert(size <= 3); + tcg_gen_qemu_ld_i64(tmp, addr, get_mem_index(s), memop); + + if (is_pair) { + TCGv_i64 addr2 = tcg_temp_new_i64(); + TCGv_i64 hitmp = tcg_temp_new_i64(); + + g_assert(size >= 2); + tcg_gen_addi_i64(addr2, addr, 1 << size); + tcg_gen_qemu_ld_i64(hitmp, addr2, get_mem_index(s), memop); + tcg_temp_free_i64(addr2); + tcg_gen_mov_i64(cpu_exclusive_high, hitmp); + tcg_gen_mov_i64(cpu_reg(s, rt2), hitmp); + tcg_temp_free_i64(hitmp); + } + + tcg_gen_mov_i64(cpu_exclusive_val, tmp); + tcg_gen_mov_i64(cpu_reg(s, rt), tmp); + + tcg_temp_free_i64(tmp); + tcg_gen_mov_i64(cpu_exclusive_addr, addr); +} + +#ifdef CONFIG_USER_ONLY +static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2, + TCGv_i64 addr, int size, int is_pair) +{ + tcg_gen_mov_i64(cpu_exclusive_test, addr); + tcg_gen_movi_i32(cpu_exclusive_info, + size | is_pair << 2 | (rd << 4) | (rt << 9) | (rt2 << 14)); + gen_exception_insn(s, 4, EXCP_STREX); +} +#else +static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2, + TCGv_i64 addr, int size, int is_pair) +{ + qemu_log_mask(LOG_UNIMP, + "%s:%d: system mode store_exclusive unsupported " + "at pc=%016" PRIx64 "\n", + __FILE__, __LINE__, s->pc - 4); +} +#endif + +/* C3.3.6 Load/store exclusive + * + * 31 30 29 24 23 22 21 20 16 15 14 10 9 5 4 0 + * +-----+-------------+----+---+----+------+----+-------+------+------+ + * | sz | 0 0 1 0 0 0 | o2 | L | o1 | Rs | o0 | Rt2 | Rn | Rt | + * +-----+-------------+----+---+----+------+----+-------+------+------+ + * + * sz: 00 -> 8 bit, 01 -> 16 bit, 10 -> 32 bit, 11 -> 64 bit + * L: 0 -> store, 1 -> load + * o2: 0 -> exclusive, 1 -> not + * o1: 0 -> single register, 1 -> register pair + * o0: 1 -> load-acquire/store-release, 0 -> not + * + * o0 == 0 AND o2 == 1 is un-allocated + * o1 == 1 is un-allocated except for 32 and 64 bit sizes + */ static void disas_ldst_excl(DisasContext *s, uint32_t insn) { - unsupported_encoding(s, insn); + int rt = extract32(insn, 0, 5); + int rn = extract32(insn, 5, 5); + int rt2 = extract32(insn, 10, 5); + int is_lasr = extract32(insn, 15, 1); + int rs = extract32(insn, 16, 5); + int is_pair = extract32(insn, 21, 1); + int is_store = !extract32(insn, 22, 1); + int is_excl = !extract32(insn, 23, 1); + int size = extract32(insn, 30, 2); + TCGv_i64 tcg_addr; + + if ((!is_excl && !is_lasr) || + (is_pair && size < 2)) { + unallocated_encoding(s); + return; + } + + if (rn == 31) { + gen_check_sp_alignment(s); + } + tcg_addr = read_cpu_reg_sp(s, rn, 1); + + /* Note that since TCG is single threaded load-acquire/store-release + * semantics require no extra if (is_lasr) { ... } handling. + */ + + if (is_excl) { + if (!is_store) { + gen_load_exclusive(s, rt, rt2, tcg_addr, size, is_pair); + } else { + gen_store_exclusive(s, rs, rt, rt2, tcg_addr, size, is_pair); + } + } else { + TCGv_i64 tcg_rt = cpu_reg(s, rt); + if (is_store) { + do_gpr_st(s, tcg_rt, tcg_addr, size); + } else { + do_gpr_ld(s, tcg_rt, tcg_addr, size, false, false); + } + if (is_pair) { + TCGv_i64 tcg_rt2 = cpu_reg(s, rt); + tcg_gen_addi_i64(tcg_addr, tcg_addr, 1 << size); + if (is_store) { + do_gpr_st(s, tcg_rt2, tcg_addr, size); + } else { + do_gpr_ld(s, tcg_rt2, tcg_addr, size, false, false); + } + } + } } /* -- cgit v1.2.3-55-g7522