Re: [PATCH v2 1/2] libatomic: atomic_16.S: Improve ENTRY, END and ALIAS macro interface

Wed, 29 Nov 2023 05:44:18 -0800 



On 13/11/2023 11:37, Victor Do Nascimento wrote:

The introduction of further architectural-feature dependent ifuncs
for AArch64 makes hard-coding ifunc `_i<n>' suffixes to functions
cumbersome to work with.  It is awkward to remember which ifunc maps
onto which arch feature and makes the code harder to maintain when new
ifuncs are added and their suffixes possibly altered.

This patch uses pre-processor `#define' statements to map each suffix to
a descriptive feature name macro, for example:

   #define LSE2 _i1

and reconstructs function names with the pre-processor's token
concatenation feature, such that for `MACRO(name)', we would now have
`MACRO(name, feature)' and in the macro definition body we replace
`name` with `name##feature`.

libatomic/ChangeLog:
        * config/linux/aarch64/atomic_16.S (CORE): New macro.
        (LSE2): Likewise.
        (ENTRY): Modify macro to take in `arch' argument.
        (END): Likewise.
        (ALIAS): Likewise.
        (ENTRY1): New macro.
        (END1): Likewise.
        (ALIAS): Likewise.
---
  libatomic/config/linux/aarch64/atomic_16.S | 147 +++++++++++----------
  1 file changed, 79 insertions(+), 68 deletions(-)

diff --git a/libatomic/config/linux/aarch64/atomic_16.S 
b/libatomic/config/linux/aarch64/atomic_16.S
index 0485c284117..3f6225830e6 100644
--- a/libatomic/config/linux/aarch64/atomic_16.S
+++ b/libatomic/config/linux/aarch64/atomic_16.S
@@ -39,22 +39,34 @@

  
  	.arch	armv8-a+lse
  
-#define ENTRY(name)		\

-       .global name;           \
-       .hidden name;           \
-       .type name,%function;   \
-       .p2align 4;             \
-name:                          \
-       .cfi_startproc;         \
+#define ENTRY(name, feat)              \
+       ENTRY1(name, feat)



I'd be much more inclined to keep the 'API' of ENTRY and the related 
functions the same and then define a new macro ENTRY_FEAT that took the 
second parameter; then you could define ENTRY as


#define ENTRY(name) ENTRY_FEAT (name, CORE)

and save the need to modify all the base functionality.


+
+#define ENTRY1(name, feat)             \
+       .global name##feat;             \
+       .hidden name##feat;             \
+       .type name##feat,%function;     \
+       .p2align 4;                     \
+name##feat:                            \
+       .cfi_startproc;                 \
        hint    34      // bti c

  
-#define END(name)		\

-       .cfi_endproc;           \
-       .size name, .-name;
+#define END(name, feat)                        \
+       END1(name, feat)

  
-#define ALIAS(alias,name)	\

-       .global alias;          \
-       .set alias, name;
+#define END1(name, feat)               \
+       .cfi_endproc;                   \
+       .size name##feat, .-name##feat;
+
+#define ALIAS(alias, from, to)         \
+       ALIAS1(alias,from,to)
+
+#define ALIAS1(alias, from, to)                \
+       .global alias##from;            \
+       .set alias##from, alias##to > +
+#define CORE
+#define LSE2   _i1

  
  #define res0 x0

  #define res1 x1
@@ -89,7 +101,7 @@ name:                                \
  #define SEQ_CST 5

  
  
-ENTRY (libat_load_16)

+ENTRY (libat_load_16, CORE)
        mov     x5, x0
        cbnz    w1, 2f

  
@@ -104,10 +116,10 @@ ENTRY (libat_load_16)

        stxp    w4, res0, res1, [x5]
        cbnz    w4, 2b
        ret
-END (libat_load_16)
+END (libat_load_16, CORE)

  
  
-ENTRY (libat_load_16_i1)

+ENTRY (libat_load_16, LSE2)
        cbnz    w1, 1f

  
  	/* RELAXED.  */

@@ -127,10 +139,10 @@ ENTRY (libat_load_16_i1)
        ldp     res0, res1, [x0]
        dmb     ishld
        ret
-END (libat_load_16_i1)
+END (libat_load_16, LSE2)

  
  
-ENTRY (libat_store_16)

+ENTRY (libat_store_16, CORE)
        cbnz    w4, 2f

  
  	/* RELAXED.  */

@@ -144,10 +156,10 @@ ENTRY (libat_store_16)
        stlxp   w4, in0, in1, [x0]
        cbnz    w4, 2b
        ret
-END (libat_store_16)
+END (libat_store_16, CORE)

  
  
-ENTRY (libat_store_16_i1)

+ENTRY (libat_store_16, LSE2)
        cbnz    w4, 1f

  
  	/* RELAXED.  */

@@ -159,10 +171,10 @@ ENTRY (libat_store_16_i1)
        stlxp   w4, in0, in1, [x0]
        cbnz    w4, 1b
        ret
-END (libat_store_16_i1)
+END (libat_store_16, LSE2)

  
  
-ENTRY (libat_exchange_16)

+ENTRY (libat_exchange_16, CORE)
        mov     x5, x0
        cbnz    w4, 2f

  
@@ -186,10 +198,10 @@ ENTRY (libat_exchange_16)

        stlxp   w4, in0, in1, [x5]
        cbnz    w4, 4b
        ret
-END (libat_exchange_16)
+END (libat_exchange_16, CORE)

  
  
-ENTRY (libat_compare_exchange_16)

+ENTRY (libat_compare_exchange_16, CORE)
        ldp     exp0, exp1, [x1]
        cbz     w4, 3f
        cmp     w4, RELEASE
@@ -228,10 +240,10 @@ ENTRY (libat_compare_exchange_16)
        cbnz    w4, 4b
        mov     x0, 1
        ret
-END (libat_compare_exchange_16)
+END (libat_compare_exchange_16, CORE)

  
  
-ENTRY (libat_compare_exchange_16_i1)

+ENTRY (libat_compare_exchange_16, LSE2)
        ldp     exp0, exp1, [x1]
        mov     tmp0, exp0
        mov     tmp1, exp1
@@ -264,10 +276,10 @@ ENTRY (libat_compare_exchange_16_i1)
        /* ACQ_REL/SEQ_CST.  */
  4:    caspal  exp0, exp1, in0, in1, [x0]
        b       0b
-END (libat_compare_exchange_16_i1)
+END (libat_compare_exchange_16, LSE2)

  
  
-ENTRY (libat_fetch_add_16)

+ENTRY (libat_fetch_add_16, CORE)
        mov     x5, x0
        cbnz    w4, 2f

  
@@ -286,10 +298,10 @@ ENTRY (libat_fetch_add_16)

        stlxp   w4, tmp0, tmp1, [x5]
        cbnz    w4, 2b
        ret
-END (libat_fetch_add_16)
+END (libat_fetch_add_16, CORE)

  
  
-ENTRY (libat_add_fetch_16)

+ENTRY (libat_add_fetch_16, CORE)
        mov     x5, x0
        cbnz    w4, 2f

  
@@ -308,10 +320,10 @@ ENTRY (libat_add_fetch_16)

        stlxp   w4, res0, res1, [x5]
        cbnz    w4, 2b
        ret
-END (libat_add_fetch_16)
+END (libat_add_fetch_16, CORE)

  
  
-ENTRY (libat_fetch_sub_16)

+ENTRY (libat_fetch_sub_16, CORE)
        mov     x5, x0
        cbnz    w4, 2f

  
@@ -330,10 +342,10 @@ ENTRY (libat_fetch_sub_16)

        stlxp   w4, tmp0, tmp1, [x5]
        cbnz    w4, 2b
        ret
-END (libat_fetch_sub_16)
+END (libat_fetch_sub_16, CORE)

  
  
-ENTRY (libat_sub_fetch_16)

+ENTRY (libat_sub_fetch_16, CORE)
        mov     x5, x0
        cbnz    w4, 2f

  
@@ -352,10 +364,10 @@ ENTRY (libat_sub_fetch_16)

        stlxp   w4, res0, res1, [x5]
        cbnz    w4, 2b
        ret
-END (libat_sub_fetch_16)
+END (libat_sub_fetch_16, CORE)

  
  
-ENTRY (libat_fetch_or_16)

+ENTRY (libat_fetch_or_16, CORE)
        mov     x5, x0
        cbnz    w4, 2f

  
@@ -374,10 +386,10 @@ ENTRY (libat_fetch_or_16)

        stlxp   w4, tmp0, tmp1, [x5]
        cbnz    w4, 2b
        ret
-END (libat_fetch_or_16)
+END (libat_fetch_or_16, CORE)

  
  
-ENTRY (libat_or_fetch_16)

+ENTRY (libat_or_fetch_16, CORE)
        mov     x5, x0
        cbnz    w4, 2f

  
@@ -396,10 +408,10 @@ ENTRY (libat_or_fetch_16)

        stlxp   w4, res0, res1, [x5]
        cbnz    w4, 2b
        ret
-END (libat_or_fetch_16)
+END (libat_or_fetch_16, CORE)

  
  
-ENTRY (libat_fetch_and_16)

+ENTRY (libat_fetch_and_16, CORE)
        mov     x5, x0
        cbnz    w4, 2f

  
@@ -418,10 +430,10 @@ ENTRY (libat_fetch_and_16)

        stlxp   w4, tmp0, tmp1, [x5]
        cbnz    w4, 2b
        ret
-END (libat_fetch_and_16)
+END (libat_fetch_and_16, CORE)

  
  
-ENTRY (libat_and_fetch_16)

+ENTRY (libat_and_fetch_16, CORE)
        mov     x5, x0
        cbnz    w4, 2f

  
@@ -440,10 +452,10 @@ ENTRY (libat_and_fetch_16)

        stlxp   w4, res0, res1, [x5]
        cbnz    w4, 2b
        ret
-END (libat_and_fetch_16)
+END (libat_and_fetch_16, CORE)

  
  
-ENTRY (libat_fetch_xor_16)

+ENTRY (libat_fetch_xor_16, CORE)
        mov     x5, x0
        cbnz    w4, 2f

  
@@ -462,10 +474,10 @@ ENTRY (libat_fetch_xor_16)

        stlxp   w4, tmp0, tmp1, [x5]
        cbnz    w4, 2b
        ret
-END (libat_fetch_xor_16)
+END (libat_fetch_xor_16, CORE)

  
  
-ENTRY (libat_xor_fetch_16)

+ENTRY (libat_xor_fetch_16, CORE)
        mov     x5, x0
        cbnz    w4, 2f

  
@@ -484,10 +496,10 @@ ENTRY (libat_xor_fetch_16)

        stlxp   w4, res0, res1, [x5]
        cbnz    w4, 2b
        ret
-END (libat_xor_fetch_16)
+END (libat_xor_fetch_16, CORE)

  
  
-ENTRY (libat_fetch_nand_16)

+ENTRY (libat_fetch_nand_16, CORE)
        mov     x5, x0
        mvn     in0, in0
        mvn     in1, in1
@@ -508,10 +520,10 @@ ENTRY (libat_fetch_nand_16)
        stlxp   w4, tmp0, tmp1, [x5]
        cbnz    w4, 2b
        ret
-END (libat_fetch_nand_16)
+END (libat_fetch_nand_16, CORE)

  
  
-ENTRY (libat_nand_fetch_16)

+ENTRY (libat_nand_fetch_16, CORE)
        mov     x5, x0
        mvn     in0, in0
        mvn     in1, in1
@@ -532,12 +544,12 @@ ENTRY (libat_nand_fetch_16)
        stlxp   w4, res0, res1, [x5]
        cbnz    w4, 2b
        ret
-END (libat_nand_fetch_16)
+END (libat_nand_fetch_16, CORE)

  
  
  /* __atomic_test_and_set is always inlined, so this entry is unused and

     only required for completeness.  */
-ENTRY (libat_test_and_set_16)
+ENTRY (libat_test_and_set_16, CORE)

  
  	/* RELAXED/ACQUIRE/CONSUME/RELEASE/ACQ_REL/SEQ_CST.  */

        mov     x5, x0
@@ -545,26 +557,25 @@ ENTRY (libat_test_and_set_16)
        stlxrb  w4, w2, [x5]
        cbnz    w4, 1b
        ret
-END (libat_test_and_set_16)
+END (libat_test_and_set_16, CORE)

  
  
  /* Alias entry points which are the same in baseline and LSE2.  */
  
-ALIAS (libat_exchange_16_i1, libat_exchange_16)

-ALIAS (libat_fetch_add_16_i1, libat_fetch_add_16)
-ALIAS (libat_add_fetch_16_i1, libat_add_fetch_16)
-ALIAS (libat_fetch_sub_16_i1, libat_fetch_sub_16)
-ALIAS (libat_sub_fetch_16_i1, libat_sub_fetch_16)
-ALIAS (libat_fetch_or_16_i1, libat_fetch_or_16)
-ALIAS (libat_or_fetch_16_i1, libat_or_fetch_16)
-ALIAS (libat_fetch_and_16_i1, libat_fetch_and_16)
-ALIAS (libat_and_fetch_16_i1, libat_and_fetch_16)
-ALIAS (libat_fetch_xor_16_i1, libat_fetch_xor_16)
-ALIAS (libat_xor_fetch_16_i1, libat_xor_fetch_16)
-ALIAS (libat_fetch_nand_16_i1, libat_fetch_nand_16)
-ALIAS (libat_nand_fetch_16_i1, libat_nand_fetch_16)
-ALIAS (libat_test_and_set_16_i1, libat_test_and_set_16)
-
+ALIAS (libat_exchange_16, LSE2, CORE)
+ALIAS (libat_fetch_add_16, LSE2, CORE)
+ALIAS (libat_add_fetch_16, LSE2, CORE)
+ALIAS (libat_fetch_sub_16, LSE2, CORE)
+ALIAS (libat_sub_fetch_16, LSE2, CORE)
+ALIAS (libat_fetch_or_16, LSE2, CORE)
+ALIAS (libat_or_fetch_16, LSE2, CORE)
+ALIAS (libat_fetch_and_16, LSE2, CORE)
+ALIAS (libat_and_fetch_16, LSE2, CORE)
+ALIAS (libat_fetch_xor_16, LSE2, CORE)
+ALIAS (libat_xor_fetch_16, LSE2, CORE)
+ALIAS (libat_fetch_nand_16, LSE2, CORE)
+ALIAS (libat_nand_fetch_16, LSE2, CORE)
+ALIAS (libat_test_and_set_16, LSE2, CORE)

  
  /* GNU_PROPERTY_AARCH64_* macros from elf.h for use in asm code.  */

  #define FEATURE_1_AND 0xc0000000


Other than that, this is OK.

R.






















					Reply via email to