LoongArch: Add glibc.cpu.hwcap support.

Key Points:
1. On lasx & lsx platforms, We must use _dl_runtime_{profile, resolve}_{lsx, lasx}
   to save vector registers.
2. Via "tunables", users can choose str/mem_{lasx,lsx,unaligned} functions with
   `export GLIBC_TUNABLES=glibc.cpu.hwcaps=LASX,...`.
   Note: glibc.cpu.hwcaps doesn't affect _dl_runtime_{profile, resolve}_{lsx, lasx}
   selection.

Usage Notes:
1. Only valid inputs: LASX, LSX, UAL. Case-sensitive, comma-separated, no spaces.
2. Example: `export GLIBC_TUNABLES=glibc.cpu.hwcaps=LASX,UAL` turns on LASX & UAL.
   Unmentioned features turn off. With default ifunc: lasx > lsx > unaligned >
   aligned > generic, effect is: lasx > unaligned > aligned > generic; lsx off.
3. Incorrect GLIBC_TUNABLES settings will show error messages.
   For example: On lsx platforms, you cannot enable lasx features. If you do
   that, you will get error messages.
4. Valid input examples:
   - GLIBC_TUNABLES=glibc.cpu.hwcaps=LASX: lasx > aligned > generic.
   - GLIBC_TUNABLES=glibc.cpu.hwcaps=LSX,UAL: lsx > unaligned > aligned > generic.
   - GLIBC_TUNABLES=glibc.cpu.hwcaps=LASX,UAL,LASX,UAL,LSX,LASX,UAL: Repetitions
     allowed but not recommended. Results in: lasx > lsx > unaligned > aligned >
     generic.

1 files changed, 23 insertions, 4 deletions

diff --git a/sysdeps/loongarch/dl-machine.h b/sysdeps/loongarch/dl-machine.h
index 57913cefaa..b395a9283e 100644
--- a/sysdeps/loongarch/dl-machine.h
+++ b/sysdeps/loongarch/dl-machine.h
@@ -29,6 +29,8 @@
 #include <dl-static-tls.h>
 #include <dl-machine-rel.h>
 
+#include <cpu-features.c>
+
 #ifndef _RTLD_PROLOGUE
 # define _RTLD_PROLOGUE(entry)					\
 	".globl\t" __STRING (entry) "\n\t"			\
@@ -53,6 +55,23 @@
 #define ELF_MACHINE_NO_REL 1
 #define ELF_MACHINE_NO_RELA 0
 
+#define DL_PLATFORM_INIT dl_platform_init ()
+
+static inline void __attribute__ ((unused))
+dl_platform_init (void)
+{
+  if (GLRO(dl_platform) != NULL && *GLRO(dl_platform) == '\0')
+    /* Avoid an empty string which would disturb us.  */
+    GLRO(dl_platform) = NULL;
+
+#ifdef SHARED
+  /* init_cpu_features has been called early from __libc_start_main in
+     static executable.  */
+  init_cpu_features (&GLRO(dl_larch_cpu_features));
+#endif
+}
+
+
 /* Return nonzero iff ELF header is compatible with the running host.  */
 static inline int
 elf_machine_matches_host (const ElfW (Ehdr) *ehdr)
@@ -290,9 +309,9 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
       if (profile != 0)
 	{
 #if !defined __loongarch_soft_float
-	  if (SUPPORT_LASX)
+	  if (RTLD_SUPPORT_LASX)
 	    gotplt[0] = (ElfW(Addr)) &_dl_runtime_profile_lasx;
-	  else if (SUPPORT_LSX)
+	  else if (RTLD_SUPPORT_LSX)
 	    gotplt[0] = (ElfW(Addr)) &_dl_runtime_profile_lsx;
 	  else
 #endif
@@ -310,9 +329,9 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	     indicated by the offset on the stack, and then jump to
 	     the resolved address.  */
 #if !defined __loongarch_soft_float
-	  if (SUPPORT_LASX)
+	  if (RTLD_SUPPORT_LASX)
 	    gotplt[0] = (ElfW(Addr)) &_dl_runtime_resolve_lasx;
-	  else if (SUPPORT_LSX)
+	  else if (RTLD_SUPPORT_LSX)
 	    gotplt[0] = (ElfW(Addr)) &_dl_runtime_resolve_lsx;
 	  else
 #endif