https://gcc.gnu.org/g:1af4a8451d4149ecbddfe9963e7f7ea3d273cc2d
commit r15-1204-g1af4a8451d4149ecbddfe9963e7f7ea3d273cc2d
Author: Victor Do Nascimento <victor.donascime...@arm.com>
Date: Thu Feb 1 13:27:50 2024 +0000
Libatomic: Make ifunc selector behavior contingent on importing file
By querying previously-defined file-identifier macros, `host-config.h'
is able to get information about its environment and, based on this
information, select more appropriate function-specific ifunc
selectors. This reduces the number of unnecessary feature tests that
need to be carried out in order to find the best atomic implementation
for a function at run-time.
An immediate benefit of this is that we can further fine-tune the
architectural requirements for each atomic function without risk of
incurring the maintenance and runtime-performance penalties of having
to maintain an ifunc selector with a huge number of alternatives, most
of which are irrelevant for any particular function. Consequently,
for AArch64 targets, we relax the architectural requirements of
`compare_exchange_16', which now requires only LSE as opposed to the
newer LSE2.
The new flexibility provided by this approach also means that certain
functions can now be called directly, doing away with ifunc selectors
altogether when only a single implementation is available for it on a
given target. As per the macro expansion framework laid out in
`libatomic_i.h', such functions should have their names prefixed with
`__atomic_' as opposed to `libat_'. This is the same prefix applied
to function names when Libatomic is configured with
`--disable-gnu-indirect-function'.
To achieve this, these functions unconditionally apply the aliasing
rule that at present is conditionally applied only when libatomic is
built without ifunc support, which ensures that the default
`libat_##NAME' is accessible via the equivalent `__atomic_##NAME' too.
This is ensured by using the new `ENTRY_ALIASED' macro.
Finally, this means we are able to do away with a whole set of
function aliases that were needed until now, thus considerably
cleaning up the implementation.
libatomic/ChangeLog:
* config/linux/aarch64/atomic_16.S: Remove unnecessary
aliasing.
(LSE): New.
(ENTRY_ALIASED): Likewise.
* config/linux/aarch64/host-config.h (LSE_ATOP): New.
(LSE2_ATOP): Likewise.
(LSE128_ATOP): Likewise.
(IFUNC_COND_1): Make its definition conditional on above 3
macros.
(IFUNC_NCOND): Likewise.
Diff:
---
libatomic/config/linux/aarch64/atomic_16.S | 64 ++++++++--------------------
libatomic/config/linux/aarch64/host-config.h | 35 ++++++++++++---
2 files changed, 45 insertions(+), 54 deletions(-)
diff --git a/libatomic/config/linux/aarch64/atomic_16.S
b/libatomic/config/linux/aarch64/atomic_16.S
index d6e71ba6e167..11a296dacc3a 100644
--- a/libatomic/config/linux/aarch64/atomic_16.S
+++ b/libatomic/config/linux/aarch64/atomic_16.S
@@ -45,17 +45,20 @@
.arch armv8-a+lse
#define LSE128(NAME) libat_##NAME##_i1
-#define LSE2(NAME) libat_##NAME##_i2
+#define LSE(NAME) libat_##NAME##_i1
+#define LSE2(NAME) libat_##NAME##_i1
#define CORE(NAME) libat_##NAME
#define ATOMIC(NAME) __atomic_##NAME
+/* Emit __atomic_* entrypoints if no ifuncs. */
+#define ENTRY_ALIASED(NAME) ENTRY2 (CORE (NAME), ALIAS (NAME, ATOMIC, CORE))
+
#if HAVE_IFUNC
# define ENTRY(NAME) ENTRY2 (CORE (NAME), )
# define ENTRY_FEAT(NAME, FEAT) ENTRY2 (FEAT (NAME), )
# define END_FEAT(NAME, FEAT) END2 (FEAT (NAME))
#else
-/* Emit __atomic_* entrypoints if no ifuncs. */
-# define ENTRY(NAME) ENTRY2 (CORE (NAME), ALIAS (NAME, ATOMIC, CORE))
+# define ENTRY(NAME) ENTRY_ALIASED (NAME)
#endif
#define END(NAME) END2 (CORE (NAME))
@@ -291,7 +294,7 @@ END (compare_exchange_16)
#if HAVE_FEAT_LSE2
-ENTRY_FEAT (compare_exchange_16, LSE2)
+ENTRY_FEAT (compare_exchange_16, LSE)
ldp exp0, exp1, [x1]
mov tmp0, exp0
mov tmp1, exp1
@@ -324,11 +327,11 @@ ENTRY_FEAT (compare_exchange_16, LSE2)
/* ACQ_REL/SEQ_CST. */
4: caspal exp0, exp1, in0, in1, [x0]
b 0b
-END_FEAT (compare_exchange_16, LSE2)
+END_FEAT (compare_exchange_16, LSE)
#endif
-ENTRY (fetch_add_16)
+ENTRY_ALIASED (fetch_add_16)
mov x5, x0
cbnz w4, 2f
@@ -350,7 +353,7 @@ ENTRY (fetch_add_16)
END (fetch_add_16)
-ENTRY (add_fetch_16)
+ENTRY_ALIASED (add_fetch_16)
mov x5, x0
cbnz w4, 2f
@@ -372,7 +375,7 @@ ENTRY (add_fetch_16)
END (add_fetch_16)
-ENTRY (fetch_sub_16)
+ENTRY_ALIASED (fetch_sub_16)
mov x5, x0
cbnz w4, 2f
@@ -394,7 +397,7 @@ ENTRY (fetch_sub_16)
END (fetch_sub_16)
-ENTRY (sub_fetch_16)
+ENTRY_ALIASED (sub_fetch_16)
mov x5, x0
cbnz w4, 2f
@@ -620,7 +623,7 @@ ENTRY_FEAT (and_fetch_16, LSE128)
END_FEAT (and_fetch_16, LSE128)
-ENTRY (fetch_xor_16)
+ENTRY_ALIASED (fetch_xor_16)
mov x5, x0
cbnz w4, 2f
@@ -642,7 +645,7 @@ ENTRY (fetch_xor_16)
END (fetch_xor_16)
-ENTRY (xor_fetch_16)
+ENTRY_ALIASED (xor_fetch_16)
mov x5, x0
cbnz w4, 2f
@@ -664,7 +667,7 @@ ENTRY (xor_fetch_16)
END (xor_fetch_16)
-ENTRY (fetch_nand_16)
+ENTRY_ALIASED (fetch_nand_16)
mov x5, x0
mvn in0, in0
mvn in1, in1
@@ -688,7 +691,7 @@ ENTRY (fetch_nand_16)
END (fetch_nand_16)
-ENTRY (nand_fetch_16)
+ENTRY_ALIASED (nand_fetch_16)
mov x5, x0
mvn in0, in0
mvn in1, in1
@@ -714,7 +717,7 @@ END (nand_fetch_16)
/* __atomic_test_and_set is always inlined, so this entry is unused and
only required for completeness. */
-ENTRY (test_and_set_16)
+ENTRY_ALIASED (test_and_set_16)
/* RELAXED/ACQUIRE/CONSUME/RELEASE/ACQ_REL/SEQ_CST. */
mov x5, x0
@@ -725,39 +728,6 @@ ENTRY (test_and_set_16)
END (test_and_set_16)
-#if HAVE_IFUNC
-
-/* Alias entry points which are the same in LSE2 and LSE128. */
-ALIAS (load_16, LSE128, LSE2)
-ALIAS (store_16, LSE128, LSE2)
-ALIAS (compare_exchange_16, LSE128, LSE2)
-ALIAS (fetch_add_16, LSE128, LSE2)
-ALIAS (add_fetch_16, LSE128, LSE2)
-ALIAS (fetch_sub_16, LSE128, LSE2)
-ALIAS (sub_fetch_16, LSE128, LSE2)
-ALIAS (fetch_xor_16, LSE128, LSE2)
-ALIAS (xor_fetch_16, LSE128, LSE2)
-ALIAS (fetch_nand_16, LSE128, LSE2)
-ALIAS (nand_fetch_16, LSE128, LSE2)
-ALIAS (test_and_set_16, LSE128, LSE2)
-
-/* Alias entry points which are the same in baseline and LSE2. */
-ALIAS (exchange_16, LSE2, CORE)
-ALIAS (fetch_add_16, LSE2, CORE)
-ALIAS (add_fetch_16, LSE2, CORE)
-ALIAS (fetch_sub_16, LSE2, CORE)
-ALIAS (sub_fetch_16, LSE2, CORE)
-ALIAS (fetch_or_16, LSE2, CORE)
-ALIAS (or_fetch_16, LSE2, CORE)
-ALIAS (fetch_and_16, LSE2, CORE)
-ALIAS (and_fetch_16, LSE2, CORE)
-ALIAS (fetch_xor_16, LSE2, CORE)
-ALIAS (xor_fetch_16, LSE2, CORE)
-ALIAS (fetch_nand_16, LSE2, CORE)
-ALIAS (nand_fetch_16, LSE2, CORE)
-ALIAS (test_and_set_16, LSE2, CORE)
-#endif
-
/* GNU_PROPERTY_AARCH64_* macros from elf.h for use in asm code. */
#define FEATURE_1_AND 0xc0000000
#define FEATURE_1_BTI 1
diff --git a/libatomic/config/linux/aarch64/host-config.h
b/libatomic/config/linux/aarch64/host-config.h
index e1a699948f48..d05e9eb628f5 100644
--- a/libatomic/config/linux/aarch64/host-config.h
+++ b/libatomic/config/linux/aarch64/host-config.h
@@ -48,15 +48,36 @@ typedef struct __ifunc_arg_t {
# define _IFUNC_ARG_HWCAP (1ULL << 62)
#endif
-#if N == 16
-# define IFUNC_COND_1 (has_lse128 (hwcap, features))
-# define IFUNC_COND_2 (has_lse2 (hwcap, features))
-# define IFUNC_NCOND(N) 2
-#else
-# define IFUNC_COND_1 (hwcap & HWCAP_ATOMICS)
-# define IFUNC_NCOND(N) 1
+/* From the file which imported `host-config.h' we can ascertain which
+ architectural extension provides relevant atomic support. From this,
+ we can proceed to tweak the ifunc selector behavior. */
+#if defined (LAT_CAS_N)
+# define LSE_ATOP
+#elif defined (LAT_LOAD_N) || defined (LAT_STORE_N)
+# define LSE2_ATOP
+#elif defined (LAT_EXCH_N) || defined (LAT_FIOR_N) || defined (LAT_FAND_N)
+# define LSE128_ATOP
#endif
+# if N == 16
+# if defined (LSE_ATOP)
+# define IFUNC_NCOND(N) 1
+# define IFUNC_COND_1 (hwcap & HWCAP_ATOMICS)
+# elif defined (LSE2_ATOP)
+# define IFUNC_NCOND(N) 1
+# define IFUNC_COND_1 (has_lse2 (hwcap, features))
+# elif defined (LSE128_ATOP)
+# define IFUNC_NCOND(N) 1
+# define IFUNC_COND_1 (has_lse128 (hwcap, features))
+# else
+# define IFUNC_NCOND(N) 0
+# define IFUNC_ALT 1
+# endif
+# else
+# define IFUNC_COND_1 (hwcap & HWCAP_ATOMICS)
+# define IFUNC_NCOND(N) 1
+# endif
+
#define MIDR_IMPLEMENTOR(midr) (((midr) >> 24) & 255)
#define MIDR_PARTNUM(midr) (((midr) >> 4) & 0xfff)
