| Message ID | 20180508151437.4232-5-richard.henderson@linaro.org |
|---|---|
| State | New |
| Headers | show |
| Series | target/arm: Implement v8.1-Atomics | expand |
On 8 May 2018 at 16:14, Richard Henderson <richard.henderson@linaro.org> wrote: > Given that this atomic operation will be used by both risc-v > and aarch64, let's not duplicate code across the two targets. > > Reviewed-by: Peter Maydell <peter.maydell@linaro.org> > Signed-off-by: Richard Henderson <richard.henderson@linaro.org> > --- > accel/tcg/atomic_template.h | 71 +++++++++++++++++++++++++++++++++++++ > accel/tcg/tcg-runtime.h | 8 +++++ > tcg/tcg-op.h | 34 ++++++++++++++++++ > tcg/tcg.h | 8 +++++ > tcg/tcg-op.c | 8 +++++ > 5 files changed, 129 insertions(+) > > diff --git a/accel/tcg/atomic_template.h b/accel/tcg/atomic_template.h > index e022df4571..2489dd3ec1 100644 > --- a/accel/tcg/atomic_template.h > +++ b/accel/tcg/atomic_template.h > @@ -25,18 +25,22 @@ > #elif DATA_SIZE == 8 > # define SUFFIX q > # define DATA_TYPE uint64_t > +# define SDATA_TYPE int64_t > # define BSWAP bswap64 > #elif DATA_SIZE == 4 > # define SUFFIX l > # define DATA_TYPE uint32_t > +# define SDATA_TYPE int32_t > # define BSWAP bswap32 > #elif DATA_SIZE == 2 > # define SUFFIX w > # define DATA_TYPE uint16_t > +# define SDATA_TYPE int16_t > # define BSWAP bswap16 > #elif DATA_SIZE == 1 > # define SUFFIX b > # define DATA_TYPE uint8_t > +# define SDATA_TYPE int8_t > # define BSWAP > #else > # error unsupported data size > @@ -118,6 +122,39 @@ GEN_ATOMIC_HELPER(or_fetch) > GEN_ATOMIC_HELPER(xor_fetch) > > #undef GEN_ATOMIC_HELPER > + > +/* These helpers are, as a whole, full barriers. Within the helper, > + * the leading barrier is explicit and the trailing barrier is within > + * cmpxchg primitive. > + */ > +#define GEN_ATOMIC_HELPER_FN(X, FN, XDATA_TYPE, RET) \ > +ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ > + ABI_TYPE xval EXTRA_ARGS) \ > +{ \ > + ATOMIC_MMU_DECLS; \ > + XDATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; \ > + XDATA_TYPE cmp, old, new, val = xval; \ > + smp_mb(); \ > + cmp = atomic_read__nocheck(haddr); \ > + do { \ > + old = cmp; new = FN(old, val); \ > + cmp = atomic_cmpxchg__nocheck(haddr, old, new); \ > + } while (cmp != old); \ > + ATOMIC_MMU_CLEANUP; \ > + return RET; \ > +} > + > +GEN_ATOMIC_HELPER_FN(fetch_smin, MIN, SDATA_TYPE, old) > +GEN_ATOMIC_HELPER_FN(fetch_umin, MIN, DATA_TYPE, old) > +GEN_ATOMIC_HELPER_FN(fetch_smax, MAX, SDATA_TYPE, old) > +GEN_ATOMIC_HELPER_FN(fetch_umax, MAX, DATA_TYPE, old) > + > +GEN_ATOMIC_HELPER_FN(smin_fetch, MIN, SDATA_TYPE, new) > +GEN_ATOMIC_HELPER_FN(umin_fetch, MIN, DATA_TYPE, new) > +GEN_ATOMIC_HELPER_FN(smax_fetch, MAX, SDATA_TYPE, new) > +GEN_ATOMIC_HELPER_FN(umax_fetch, MAX, DATA_TYPE, new) This fails to compile for me: In file included from /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/cputlb.c:1062:0: /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/atomic_template.h: In function ‘helper_atomic_fetch_sminb_mmu’: /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/atomic_template.h:147:1: error: value computed is not used [-Werror=unused-value] GEN_ATOMIC_HELPER_FN(fetch_smin, MIN, SDATA_TYPE, old) ^ In file included from /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/cputlb.c:1062:0: /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/atomic_template.h: In function ‘helper_atomic_fetch_smaxb_mmu’: /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/atomic_template.h:149:1: error: value computed is not used [-Werror=unused-value] GEN_ATOMIC_HELPER_FN(fetch_smax, MAX, SDATA_TYPE, old) ^ In file included from /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/cputlb.c:1062:0: /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/atomic_template.h: In function ‘helper_atomic_smin_fetchb_mmu’: /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/atomic_template.h:152:1: error: value computed is not used [-Werror=unused-value] GEN_ATOMIC_HELPER_FN(smin_fetch, MIN, SDATA_TYPE, new) ^ In file included from /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/cputlb.c:1062:0: /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/atomic_template.h: In function ‘helper_atomic_smax_fetchb_mmu’: /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/atomic_template.h:154:1: error: value computed is not used [-Werror=unused-value] GEN_ATOMIC_HELPER_FN(smax_fetch, MAX, SDATA_TYPE, new) ^ In file included from /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/cputlb.c:1090:0: /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/atomic_template.h: In function ‘helper_atomic_fetch_sminb’: /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/atomic_template.h:147:1: error: value computed is not used [-Werror=unused-value] GEN_ATOMIC_HELPER_FN(fetch_smin, MIN, SDATA_TYPE, old) ^ In file included from /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/cputlb.c:1090:0: /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/atomic_template.h: In function ‘helper_atomic_fetch_smaxb’: /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/atomic_template.h:149:1: error: value computed is not used [-Werror=unused-value] GEN_ATOMIC_HELPER_FN(fetch_smax, MAX, SDATA_TYPE, old) ^ In file included from /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/cputlb.c:1090:0: /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/atomic_template.h: In function ‘helper_atomic_smin_fetchb’: /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/atomic_template.h:152:1: error: value computed is not used [-Werror=unused-value] GEN_ATOMIC_HELPER_FN(smin_fetch, MIN, SDATA_TYPE, new) ^ In file included from /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/cputlb.c:1090:0: /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/atomic_template.h: In function ‘helper_atomic_smax_fetchb’: /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/atomic_template.h:154:1: error: value computed is not used [-Werror=unused-value] GEN_ATOMIC_HELPER_FN(smax_fetch, MAX, SDATA_TYPE, new) ^ gcc (Ubuntu 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 configure arguments exec '../../configure' '--target-list=arm-softmmu,aarch64-softmmu,arm-linux-user,aarch64-linux-user' '--enable-debug' '--cc=ccache gcc' '--audio-drv-list=pa' '--with-pkgversion=pm215' "$@" For some reason, only the signed versions get warnings... thanks -- PMM
On 8 May 2018 at 18:37, Peter Maydell <peter.maydell@linaro.org> wrote: > On 8 May 2018 at 16:14, Richard Henderson <richard.henderson@linaro.org> wrote: >> Given that this atomic operation will be used by both risc-v >> and aarch64, let's not duplicate code across the two targets. >> >> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> >> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> >> --- >> accel/tcg/atomic_template.h | 71 +++++++++++++++++++++++++++++++++++++ >> accel/tcg/tcg-runtime.h | 8 +++++ >> tcg/tcg-op.h | 34 ++++++++++++++++++ >> tcg/tcg.h | 8 +++++ >> tcg/tcg-op.c | 8 +++++ >> 5 files changed, 129 insertions(+) >> >> diff --git a/accel/tcg/atomic_template.h b/accel/tcg/atomic_template.h >> index e022df4571..2489dd3ec1 100644 >> --- a/accel/tcg/atomic_template.h >> +++ b/accel/tcg/atomic_template.h >> @@ -25,18 +25,22 @@ >> #elif DATA_SIZE == 8 >> # define SUFFIX q >> # define DATA_TYPE uint64_t >> +# define SDATA_TYPE int64_t >> # define BSWAP bswap64 >> #elif DATA_SIZE == 4 >> # define SUFFIX l >> # define DATA_TYPE uint32_t >> +# define SDATA_TYPE int32_t >> # define BSWAP bswap32 >> #elif DATA_SIZE == 2 >> # define SUFFIX w >> # define DATA_TYPE uint16_t >> +# define SDATA_TYPE int16_t >> # define BSWAP bswap16 >> #elif DATA_SIZE == 1 >> # define SUFFIX b >> # define DATA_TYPE uint8_t >> +# define SDATA_TYPE int8_t >> # define BSWAP >> #else >> # error unsupported data size >> @@ -118,6 +122,39 @@ GEN_ATOMIC_HELPER(or_fetch) >> GEN_ATOMIC_HELPER(xor_fetch) >> >> #undef GEN_ATOMIC_HELPER >> + >> +/* These helpers are, as a whole, full barriers. Within the helper, >> + * the leading barrier is explicit and the trailing barrier is within >> + * cmpxchg primitive. >> + */ >> +#define GEN_ATOMIC_HELPER_FN(X, FN, XDATA_TYPE, RET) \ >> +ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ >> + ABI_TYPE xval EXTRA_ARGS) \ >> +{ \ >> + ATOMIC_MMU_DECLS; \ >> + XDATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; \ >> + XDATA_TYPE cmp, old, new, val = xval; \ >> + smp_mb(); \ >> + cmp = atomic_read__nocheck(haddr); \ >> + do { \ >> + old = cmp; new = FN(old, val); \ >> + cmp = atomic_cmpxchg__nocheck(haddr, old, new); \ >> + } while (cmp != old); \ >> + ATOMIC_MMU_CLEANUP; \ >> + return RET; \ >> +} >> + >> +GEN_ATOMIC_HELPER_FN(fetch_smin, MIN, SDATA_TYPE, old) >> +GEN_ATOMIC_HELPER_FN(fetch_umin, MIN, DATA_TYPE, old) >> +GEN_ATOMIC_HELPER_FN(fetch_smax, MAX, SDATA_TYPE, old) >> +GEN_ATOMIC_HELPER_FN(fetch_umax, MAX, DATA_TYPE, old) >> + >> +GEN_ATOMIC_HELPER_FN(smin_fetch, MIN, SDATA_TYPE, new) >> +GEN_ATOMIC_HELPER_FN(umin_fetch, MIN, DATA_TYPE, new) >> +GEN_ATOMIC_HELPER_FN(smax_fetch, MAX, SDATA_TYPE, new) >> +GEN_ATOMIC_HELPER_FN(umax_fetch, MAX, DATA_TYPE, new) > > This fails to compile for me: Running it not via ccache gave me some more detail (??): In file included from /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/cputlb.c:22:0: /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/atomic_template.h: In function ‘helper_atomic_fetch_sminb_mmu’: /home/petmay01/linaro/qemu-from-laptop/qemu/target/arm/cpu.h:36:29: error: value computed is not used [-Werror=unused-value] #define CPUArchState struct CPUARMState ^ /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/atomic_template.h:131:25: note: in expansion of macro ‘CPUArchState’ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ ^ /home/petmay01/linaro/qemu-from-laptop/qemu/accel/tcg/atomic_template.h:147:1: note: in expansion of macro ‘GEN_ATOMIC_HELPER_FN’ GEN_ATOMIC_HELPER_FN(fetch_smin, MIN, SDATA_TYPE, old) ^ though that doesn't make much sense either. I'll see if I can get gcc to show me the macros-expanded code. thanks -- PMM
On 8 May 2018 at 18:49, Peter Maydell <peter.maydell@linaro.org> wrote:
> [weird compiler errors]
This fixes them:
--- a/include/qemu/atomic.h
+++ b/include/qemu/atomic.h
@@ -187,7 +187,7 @@
/* Returns the eventual value, failed or not */
#define atomic_cmpxchg__nocheck(ptr, old, new) ({ \
typeof_strip_qual(*ptr) _old = (old); \
- __atomic_compare_exchange_n(ptr, &_old, new, false, \
+ (void)__atomic_compare_exchange_n(ptr, &_old, new, false, \
__ATOMIC_SEQ_CST, __ATOMIC_SEQ_CST); \
_old; \
})
Seems pretty clearly a compiler bug -- rth says newer gcc don't
do this, so presumably fixed upstream somewhere between gcc 5 and 6.
thanks
-- PMM
On 8 May 2018 at 19:27, Peter Maydell <peter.maydell@linaro.org> wrote: > On 8 May 2018 at 18:49, Peter Maydell <peter.maydell@linaro.org> wrote: >> [weird compiler errors] > > This fixes them: > > --- a/include/qemu/atomic.h > +++ b/include/qemu/atomic.h > @@ -187,7 +187,7 @@ > /* Returns the eventual value, failed or not */ > #define atomic_cmpxchg__nocheck(ptr, old, new) ({ \ > typeof_strip_qual(*ptr) _old = (old); \ > - __atomic_compare_exchange_n(ptr, &_old, new, false, \ > + (void)__atomic_compare_exchange_n(ptr, &_old, new, false, \ > __ATOMIC_SEQ_CST, __ATOMIC_SEQ_CST); \ > _old; \ > }) > > Seems pretty clearly a compiler bug -- rth says newer gcc don't > do this, so presumably fixed upstream somewhere between gcc 5 and 6. Standalone testcase, fwiw: ===begin=== /* * Weirdly, this compiler will complain about FOO(int8_t) but not * the others: * $ gcc -g -Wall -Wunused-value -o zz9.o -c zz9.c * zz9.c: In function ‘foo_int8_t’: * zz9.c:12:5: warning: value computed is not used [-Wunused-value] * __atomic_compare_exchange_n(p, exp, des, 0, __ATOMIC_SEQ_CST, __ATOMIC_SEQ_CST); \ * ^ * /tmp/zz9.c:17:1: note: in expansion of macro ‘FOO’ * FOO(int8_t) * ^ * * This is gcc (Ubuntu 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 */ typedef unsigned char uint8_t; typedef signed char int8_t; #define FOO(TYPE) \ void foo_##TYPE(TYPE *p, TYPE *exp, TYPE *des) { \ __atomic_compare_exchange_n(p, exp, des, 0, __ATOMIC_SEQ_CST, __ATOMIC_SEQ_CST); \ } FOO(int) FOO(uint8_t) FOO(int8_t) ===endit=== thanks -- PMM
diff --git a/accel/tcg/atomic_template.h b/accel/tcg/atomic_template.h index e022df4571..2489dd3ec1 100644 --- a/accel/tcg/atomic_template.h +++ b/accel/tcg/atomic_template.h @@ -25,18 +25,22 @@ #elif DATA_SIZE == 8 # define SUFFIX q # define DATA_TYPE uint64_t +# define SDATA_TYPE int64_t # define BSWAP bswap64 #elif DATA_SIZE == 4 # define SUFFIX l # define DATA_TYPE uint32_t +# define SDATA_TYPE int32_t # define BSWAP bswap32 #elif DATA_SIZE == 2 # define SUFFIX w # define DATA_TYPE uint16_t +# define SDATA_TYPE int16_t # define BSWAP bswap16 #elif DATA_SIZE == 1 # define SUFFIX b # define DATA_TYPE uint8_t +# define SDATA_TYPE int8_t # define BSWAP #else # error unsupported data size @@ -118,6 +122,39 @@ GEN_ATOMIC_HELPER(or_fetch) GEN_ATOMIC_HELPER(xor_fetch) #undef GEN_ATOMIC_HELPER + +/* These helpers are, as a whole, full barriers. Within the helper, + * the leading barrier is explicit and the trailing barrier is within + * cmpxchg primitive. + */ +#define GEN_ATOMIC_HELPER_FN(X, FN, XDATA_TYPE, RET) \ +ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ + ABI_TYPE xval EXTRA_ARGS) \ +{ \ + ATOMIC_MMU_DECLS; \ + XDATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; \ + XDATA_TYPE cmp, old, new, val = xval; \ + smp_mb(); \ + cmp = atomic_read__nocheck(haddr); \ + do { \ + old = cmp; new = FN(old, val); \ + cmp = atomic_cmpxchg__nocheck(haddr, old, new); \ + } while (cmp != old); \ + ATOMIC_MMU_CLEANUP; \ + return RET; \ +} + +GEN_ATOMIC_HELPER_FN(fetch_smin, MIN, SDATA_TYPE, old) +GEN_ATOMIC_HELPER_FN(fetch_umin, MIN, DATA_TYPE, old) +GEN_ATOMIC_HELPER_FN(fetch_smax, MAX, SDATA_TYPE, old) +GEN_ATOMIC_HELPER_FN(fetch_umax, MAX, DATA_TYPE, old) + +GEN_ATOMIC_HELPER_FN(smin_fetch, MIN, SDATA_TYPE, new) +GEN_ATOMIC_HELPER_FN(umin_fetch, MIN, DATA_TYPE, new) +GEN_ATOMIC_HELPER_FN(smax_fetch, MAX, SDATA_TYPE, new) +GEN_ATOMIC_HELPER_FN(umax_fetch, MAX, DATA_TYPE, new) + +#undef GEN_ATOMIC_HELPER_FN #endif /* DATA SIZE >= 16 */ #undef END @@ -233,6 +270,39 @@ ABI_TYPE ATOMIC_NAME(add_fetch)(CPUArchState *env, target_ulong addr, ldo = ldn; } } + +/* These helpers are, as a whole, full barriers. Within the helper, + * the leading barrier is explicit and the trailing barrier is within + * cmpxchg primitive. + */ +#define GEN_ATOMIC_HELPER_FN(X, FN, XDATA_TYPE, RET) \ +ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr, \ + ABI_TYPE xval EXTRA_ARGS) \ +{ \ + ATOMIC_MMU_DECLS; \ + XDATA_TYPE *haddr = ATOMIC_MMU_LOOKUP; \ + XDATA_TYPE ldo, ldn, old, new, val = xval; \ + smp_mb(); \ + ldn = atomic_read__nocheck(haddr); \ + do { \ + ldo = ldn; old = BSWAP(ldo); new = FN(old, val); \ + ldn = atomic_cmpxchg__nocheck(haddr, ldo, BSWAP(new)); \ + } while (ldo != ldn); \ + ATOMIC_MMU_CLEANUP; \ + return RET; \ +} + +GEN_ATOMIC_HELPER_FN(fetch_smin, MIN, SDATA_TYPE, old) +GEN_ATOMIC_HELPER_FN(fetch_umin, MIN, DATA_TYPE, old) +GEN_ATOMIC_HELPER_FN(fetch_smax, MAX, SDATA_TYPE, old) +GEN_ATOMIC_HELPER_FN(fetch_umax, MAX, DATA_TYPE, old) + +GEN_ATOMIC_HELPER_FN(smin_fetch, MIN, SDATA_TYPE, new) +GEN_ATOMIC_HELPER_FN(umin_fetch, MIN, DATA_TYPE, new) +GEN_ATOMIC_HELPER_FN(smax_fetch, MAX, SDATA_TYPE, new) +GEN_ATOMIC_HELPER_FN(umax_fetch, MAX, DATA_TYPE, new) + +#undef GEN_ATOMIC_HELPER_FN #endif /* DATA_SIZE >= 16 */ #undef END @@ -241,5 +311,6 @@ ABI_TYPE ATOMIC_NAME(add_fetch)(CPUArchState *env, target_ulong addr, #undef BSWAP #undef ABI_TYPE #undef DATA_TYPE +#undef SDATA_TYPE #undef SUFFIX #undef DATA_SIZE diff --git a/accel/tcg/tcg-runtime.h b/accel/tcg/tcg-runtime.h index 2536959a18..1bd39d136d 100644 --- a/accel/tcg/tcg-runtime.h +++ b/accel/tcg/tcg-runtime.h @@ -125,11 +125,19 @@ GEN_ATOMIC_HELPERS(fetch_add) GEN_ATOMIC_HELPERS(fetch_and) GEN_ATOMIC_HELPERS(fetch_or) GEN_ATOMIC_HELPERS(fetch_xor) +GEN_ATOMIC_HELPERS(fetch_smin) +GEN_ATOMIC_HELPERS(fetch_umin) +GEN_ATOMIC_HELPERS(fetch_smax) +GEN_ATOMIC_HELPERS(fetch_umax) GEN_ATOMIC_HELPERS(add_fetch) GEN_ATOMIC_HELPERS(and_fetch) GEN_ATOMIC_HELPERS(or_fetch) GEN_ATOMIC_HELPERS(xor_fetch) +GEN_ATOMIC_HELPERS(smin_fetch) +GEN_ATOMIC_HELPERS(umin_fetch) +GEN_ATOMIC_HELPERS(smax_fetch) +GEN_ATOMIC_HELPERS(umax_fetch) GEN_ATOMIC_HELPERS(xchg) diff --git a/tcg/tcg-op.h b/tcg/tcg-op.h index 0451e2752e..04eb3e9e17 100644 --- a/tcg/tcg-op.h +++ b/tcg/tcg-op.h @@ -898,6 +898,7 @@ void tcg_gen_atomic_cmpxchg_i64(TCGv_i64, TCGv, TCGv_i64, TCGv_i64, void tcg_gen_atomic_xchg_i32(TCGv_i32, TCGv, TCGv_i32, TCGArg, TCGMemOp); void tcg_gen_atomic_xchg_i64(TCGv_i64, TCGv, TCGv_i64, TCGArg, TCGMemOp); + void tcg_gen_atomic_fetch_add_i32(TCGv_i32, TCGv, TCGv_i32, TCGArg, TCGMemOp); void tcg_gen_atomic_fetch_add_i64(TCGv_i64, TCGv, TCGv_i64, TCGArg, TCGMemOp); void tcg_gen_atomic_fetch_and_i32(TCGv_i32, TCGv, TCGv_i32, TCGArg, TCGMemOp); @@ -906,6 +907,15 @@ void tcg_gen_atomic_fetch_or_i32(TCGv_i32, TCGv, TCGv_i32, TCGArg, TCGMemOp); void tcg_gen_atomic_fetch_or_i64(TCGv_i64, TCGv, TCGv_i64, TCGArg, TCGMemOp); void tcg_gen_atomic_fetch_xor_i32(TCGv_i32, TCGv, TCGv_i32, TCGArg, TCGMemOp); void tcg_gen_atomic_fetch_xor_i64(TCGv_i64, TCGv, TCGv_i64, TCGArg, TCGMemOp); +void tcg_gen_atomic_fetch_smin_i32(TCGv_i32, TCGv, TCGv_i32, TCGArg, TCGMemOp); +void tcg_gen_atomic_fetch_smin_i64(TCGv_i64, TCGv, TCGv_i64, TCGArg, TCGMemOp); +void tcg_gen_atomic_fetch_umin_i32(TCGv_i32, TCGv, TCGv_i32, TCGArg, TCGMemOp); +void tcg_gen_atomic_fetch_umin_i64(TCGv_i64, TCGv, TCGv_i64, TCGArg, TCGMemOp); +void tcg_gen_atomic_fetch_smax_i32(TCGv_i32, TCGv, TCGv_i32, TCGArg, TCGMemOp); +void tcg_gen_atomic_fetch_smax_i64(TCGv_i64, TCGv, TCGv_i64, TCGArg, TCGMemOp); +void tcg_gen_atomic_fetch_umax_i32(TCGv_i32, TCGv, TCGv_i32, TCGArg, TCGMemOp); +void tcg_gen_atomic_fetch_umax_i64(TCGv_i64, TCGv, TCGv_i64, TCGArg, TCGMemOp); + void tcg_gen_atomic_add_fetch_i32(TCGv_i32, TCGv, TCGv_i32, TCGArg, TCGMemOp); void tcg_gen_atomic_add_fetch_i64(TCGv_i64, TCGv, TCGv_i64, TCGArg, TCGMemOp); void tcg_gen_atomic_and_fetch_i32(TCGv_i32, TCGv, TCGv_i32, TCGArg, TCGMemOp); @@ -914,6 +924,14 @@ void tcg_gen_atomic_or_fetch_i32(TCGv_i32, TCGv, TCGv_i32, TCGArg, TCGMemOp); void tcg_gen_atomic_or_fetch_i64(TCGv_i64, TCGv, TCGv_i64, TCGArg, TCGMemOp); void tcg_gen_atomic_xor_fetch_i32(TCGv_i32, TCGv, TCGv_i32, TCGArg, TCGMemOp); void tcg_gen_atomic_xor_fetch_i64(TCGv_i64, TCGv, TCGv_i64, TCGArg, TCGMemOp); +void tcg_gen_atomic_smin_fetch_i32(TCGv_i32, TCGv, TCGv_i32, TCGArg, TCGMemOp); +void tcg_gen_atomic_smin_fetch_i64(TCGv_i64, TCGv, TCGv_i64, TCGArg, TCGMemOp); +void tcg_gen_atomic_umin_fetch_i32(TCGv_i32, TCGv, TCGv_i32, TCGArg, TCGMemOp); +void tcg_gen_atomic_umin_fetch_i64(TCGv_i64, TCGv, TCGv_i64, TCGArg, TCGMemOp); +void tcg_gen_atomic_smax_fetch_i32(TCGv_i32, TCGv, TCGv_i32, TCGArg, TCGMemOp); +void tcg_gen_atomic_smax_fetch_i64(TCGv_i64, TCGv, TCGv_i64, TCGArg, TCGMemOp); +void tcg_gen_atomic_umax_fetch_i32(TCGv_i32, TCGv, TCGv_i32, TCGArg, TCGMemOp); +void tcg_gen_atomic_umax_fetch_i64(TCGv_i64, TCGv, TCGv_i64, TCGArg, TCGMemOp); void tcg_gen_mov_vec(TCGv_vec, TCGv_vec); void tcg_gen_dup_i32_vec(unsigned vece, TCGv_vec, TCGv_i32); @@ -1043,10 +1061,18 @@ void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset, TCGType t); #define tcg_gen_atomic_fetch_and_tl tcg_gen_atomic_fetch_and_i64 #define tcg_gen_atomic_fetch_or_tl tcg_gen_atomic_fetch_or_i64 #define tcg_gen_atomic_fetch_xor_tl tcg_gen_atomic_fetch_xor_i64 +#define tcg_gen_atomic_fetch_smin_tl tcg_gen_atomic_fetch_smin_i64 +#define tcg_gen_atomic_fetch_umin_tl tcg_gen_atomic_fetch_umin_i64 +#define tcg_gen_atomic_fetch_smax_tl tcg_gen_atomic_fetch_smax_i64 +#define tcg_gen_atomic_fetch_umax_tl tcg_gen_atomic_fetch_umax_i64 #define tcg_gen_atomic_add_fetch_tl tcg_gen_atomic_add_fetch_i64 #define tcg_gen_atomic_and_fetch_tl tcg_gen_atomic_and_fetch_i64 #define tcg_gen_atomic_or_fetch_tl tcg_gen_atomic_or_fetch_i64 #define tcg_gen_atomic_xor_fetch_tl tcg_gen_atomic_xor_fetch_i64 +#define tcg_gen_atomic_smin_fetch_tl tcg_gen_atomic_smin_fetch_i64 +#define tcg_gen_atomic_umin_fetch_tl tcg_gen_atomic_umin_fetch_i64 +#define tcg_gen_atomic_smax_fetch_tl tcg_gen_atomic_smax_fetch_i64 +#define tcg_gen_atomic_umax_fetch_tl tcg_gen_atomic_umax_fetch_i64 #define tcg_gen_dup_tl_vec tcg_gen_dup_i64_vec #else #define tcg_gen_movi_tl tcg_gen_movi_i32 @@ -1145,10 +1171,18 @@ void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset, TCGType t); #define tcg_gen_atomic_fetch_and_tl tcg_gen_atomic_fetch_and_i32 #define tcg_gen_atomic_fetch_or_tl tcg_gen_atomic_fetch_or_i32 #define tcg_gen_atomic_fetch_xor_tl tcg_gen_atomic_fetch_xor_i32 +#define tcg_gen_atomic_fetch_smin_tl tcg_gen_atomic_fetch_smin_i32 +#define tcg_gen_atomic_fetch_umin_tl tcg_gen_atomic_fetch_umin_i32 +#define tcg_gen_atomic_fetch_smax_tl tcg_gen_atomic_fetch_smax_i32 +#define tcg_gen_atomic_fetch_umax_tl tcg_gen_atomic_fetch_umax_i32 #define tcg_gen_atomic_add_fetch_tl tcg_gen_atomic_add_fetch_i32 #define tcg_gen_atomic_and_fetch_tl tcg_gen_atomic_and_fetch_i32 #define tcg_gen_atomic_or_fetch_tl tcg_gen_atomic_or_fetch_i32 #define tcg_gen_atomic_xor_fetch_tl tcg_gen_atomic_xor_fetch_i32 +#define tcg_gen_atomic_smin_fetch_tl tcg_gen_atomic_smin_fetch_i32 +#define tcg_gen_atomic_umin_fetch_tl tcg_gen_atomic_umin_fetch_i32 +#define tcg_gen_atomic_smax_fetch_tl tcg_gen_atomic_smax_fetch_i32 +#define tcg_gen_atomic_umax_fetch_tl tcg_gen_atomic_umax_fetch_i32 #define tcg_gen_dup_tl_vec tcg_gen_dup_i32_vec #endif diff --git a/tcg/tcg.h b/tcg/tcg.h index 75fbad128b..1ca985479b 100644 --- a/tcg/tcg.h +++ b/tcg/tcg.h @@ -1415,12 +1415,20 @@ GEN_ATOMIC_HELPER_ALL(fetch_sub) GEN_ATOMIC_HELPER_ALL(fetch_and) GEN_ATOMIC_HELPER_ALL(fetch_or) GEN_ATOMIC_HELPER_ALL(fetch_xor) +GEN_ATOMIC_HELPER_ALL(fetch_smin) +GEN_ATOMIC_HELPER_ALL(fetch_umin) +GEN_ATOMIC_HELPER_ALL(fetch_smax) +GEN_ATOMIC_HELPER_ALL(fetch_umax) GEN_ATOMIC_HELPER_ALL(add_fetch) GEN_ATOMIC_HELPER_ALL(sub_fetch) GEN_ATOMIC_HELPER_ALL(and_fetch) GEN_ATOMIC_HELPER_ALL(or_fetch) GEN_ATOMIC_HELPER_ALL(xor_fetch) +GEN_ATOMIC_HELPER_ALL(smin_fetch) +GEN_ATOMIC_HELPER_ALL(umin_fetch) +GEN_ATOMIC_HELPER_ALL(smax_fetch) +GEN_ATOMIC_HELPER_ALL(umax_fetch) GEN_ATOMIC_HELPER_ALL(xchg) diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c index 5b82c3be8d..6a914654f5 100644 --- a/tcg/tcg-op.c +++ b/tcg/tcg-op.c @@ -3051,11 +3051,19 @@ GEN_ATOMIC_HELPER(fetch_add, add, 0) GEN_ATOMIC_HELPER(fetch_and, and, 0) GEN_ATOMIC_HELPER(fetch_or, or, 0) GEN_ATOMIC_HELPER(fetch_xor, xor, 0) +GEN_ATOMIC_HELPER(fetch_smin, smin, 0) +GEN_ATOMIC_HELPER(fetch_umin, umin, 0) +GEN_ATOMIC_HELPER(fetch_smax, smax, 0) +GEN_ATOMIC_HELPER(fetch_umax, umax, 0) GEN_ATOMIC_HELPER(add_fetch, add, 1) GEN_ATOMIC_HELPER(and_fetch, and, 1) GEN_ATOMIC_HELPER(or_fetch, or, 1) GEN_ATOMIC_HELPER(xor_fetch, xor, 1) +GEN_ATOMIC_HELPER(smin_fetch, smin, 1) +GEN_ATOMIC_HELPER(umin_fetch, umin, 1) +GEN_ATOMIC_HELPER(smax_fetch, smax, 1) +GEN_ATOMIC_HELPER(umax_fetch, umax, 1) static void tcg_gen_mov2_i32(TCGv_i32 r, TCGv_i32 a, TCGv_i32 b) {