powerpc: Add HWCAP3/HWCAP4 data to TCB for Power Architecture.

This patch adds a new feature for powerpc.  In order to get faster
access to the HWCAP3/HWCAP4 masks, similar to HWCAP/HWCAP2 (i.e. for
implementing __builtin_cpu_supports() in GCC) without the overhead of
reading them from the auxiliary vector, we now reserve space for them
in the TCB.

Suggested-by: Peter Bergner <bergner@linux.ibm.com>
Reviewed-by: Peter Bergner <bergner@linux.ibm.com>
(cherry picked from commit 3ab9b88e2ac91062b6d493fe32bd101a55006c6a)

9 files changed, 66 insertions, 19 deletions

diff --git a/sysdeps/generic/ldsodefs.h b/sysdeps/generic/ldsodefs.h
index 117c901ccc..50f58a60e3 100644
--- a/sysdeps/generic/ldsodefs.h
+++ b/sysdeps/generic/ldsodefs.h
@@ -646,6 +646,8 @@ struct rtld_global_ro
   /* Mask for more hardware capabilities that are available on some
      platforms.  */
   EXTERN uint64_t _dl_hwcap2;
+  EXTERN uint64_t _dl_hwcap3;
+  EXTERN uint64_t _dl_hwcap4;
 
   EXTERN enum dso_sort_algorithm _dl_dso_sort_algo;
 
diff --git a/sysdeps/powerpc/dl-procinfo.c b/sysdeps/powerpc/dl-procinfo.c
index a76bb6e5b0..8cf00aa7e3 100644
--- a/sysdeps/powerpc/dl-procinfo.c
+++ b/sysdeps/powerpc/dl-procinfo.c
@@ -38,6 +38,10 @@
        needed.
   */
 
+/* The total number of available bits (including those prior to
+   _DL_HWCAP_FIRST).  Some of these bits might not be used.  */
+#define _DL_HWCAP_COUNT         128
+
 #ifndef PROCINFO_CLASS
 # define PROCINFO_CLASS
 #endif
@@ -61,7 +65,7 @@ PROCINFO_CLASS struct cpu_features _dl_powerpc_cpu_features
 #if !defined PROCINFO_DECL && defined SHARED
   ._dl_powerpc_cap_flags
 #else
-PROCINFO_CLASS const char _dl_powerpc_cap_flags[64][15]
+PROCINFO_CLASS const char _dl_powerpc_cap_flags[_DL_HWCAP_COUNT][15]
 #endif
 #ifndef PROCINFO_DECL
 = {
diff --git a/sysdeps/powerpc/dl-procinfo.h b/sysdeps/powerpc/dl-procinfo.h
index 68f4241095..f8cb343877 100644
--- a/sysdeps/powerpc/dl-procinfo.h
+++ b/sysdeps/powerpc/dl-procinfo.h
@@ -22,16 +22,17 @@
 #include <ldsodefs.h>
 #include <sysdep.h>	/* This defines the PPC_FEATURE[2]_* macros.  */
 
-/* The total number of available bits (including those prior to
-   _DL_HWCAP_FIRST).  Some of these bits might not be used.  */
-#define _DL_HWCAP_COUNT		64
+/* Feature masks are all 32-bits in size.  */
+#define _DL_HWCAP_SIZE		32
 
-/* Features started at bit 31 and decremented as new features were added.  */
-#define _DL_HWCAP_LAST		31
+/* AT_HWCAP2 feature strings follow the AT_HWCAP feature strings.  */
+#define _DL_HWCAP2_OFFSET	_DL_HWCAP_SIZE
 
-/* AT_HWCAP2 features started at bit 31 and decremented as new features were
-   added.  HWCAP2 feature bits start at bit 0.  */
-#define _DL_HWCAP2_LAST		31
+/* AT_HWCAP3 feature strings follow the AT_HWCAP2 feature strings.  */
+#define _DL_HWCAP3_OFFSET	(_DL_HWCAP2_OFFSET + _DL_HWCAP_SIZE)
+
+/* AT_HWCAP4 feature strings follow the AT_HWCAP3 feature strings.  */
+#define _DL_HWCAP4_OFFSET	(_DL_HWCAP3_OFFSET + _DL_HWCAP_SIZE)
 
 /* These bits influence library search.  */
 #define HWCAP_IMPORTANT		(PPC_FEATURE_HAS_ALTIVEC \
@@ -187,21 +188,42 @@ _dl_procinfo (unsigned int type, unsigned long int word)
     case AT_HWCAP:
       _dl_printf ("AT_HWCAP:            ");
 
-      for (int i = 0; i <= _DL_HWCAP_LAST; ++i)
+      for (int i = 0; i < _DL_HWCAP_SIZE; ++i)
        if (word & (1 << i))
          _dl_printf (" %s", _dl_hwcap_string (i));
       break;
     case AT_HWCAP2:
       {
-       unsigned int offset = _DL_HWCAP_LAST + 1;
 
        _dl_printf ("AT_HWCAP2:           ");
 
-        /* We have to go through them all because the kernel added the
-          AT_HWCAP2 features starting with the high bits.  */
-       for (int i = 0; i <= _DL_HWCAP2_LAST; ++i)
-         if (word & (1 << i))
-           _dl_printf (" %s", _dl_hwcap_string (offset + i));
+       /* We have to go through them all because the kernel added the
+	  AT_HWCAP2 features starting with the high bits.  */
+       for (int i = 0; i < _DL_HWCAP_SIZE; ++i)
+	 if (word & (1 << i))
+	   _dl_printf (" %s", _dl_hwcap_string (_DL_HWCAP2_OFFSET + i));
+       break;
+      }
+    case AT_HWCAP3:
+      {
+       _dl_printf ("AT_HWCAP3:           ");
+
+       /* We have to go through them all because the kernel added the
+	  AT_HWCAP3 features starting with the high bits.  */
+       for (int i = 0; i < _DL_HWCAP_SIZE; ++i)
+	 if (word & (1 << i))
+	   _dl_printf (" %s", _dl_hwcap_string (_DL_HWCAP3_OFFSET + i));
+       break;
+      }
+    case AT_HWCAP4:
+      {
+       _dl_printf ("AT_HWCAP4:           ");
+
+       /* We have to go through them all because the kernel added the
+	  AT_HWCAP4 features starting with the high bits.  */
+       for (int i = 0; i <= _DL_HWCAP_SIZE; ++i)
+	 if (word & (1 << i))
+	   _dl_printf (" %s", _dl_hwcap_string (_DL_HWCAP4_OFFSET + i));
        break;
       }
     case AT_L1I_CACHEGEOMETRY:
diff --git a/sysdeps/powerpc/hwcapinfo.c b/sysdeps/powerpc/hwcapinfo.c
index 76344f285a..f6fede15a7 100644
--- a/sysdeps/powerpc/hwcapinfo.c
+++ b/sysdeps/powerpc/hwcapinfo.c
@@ -31,7 +31,7 @@ void
 __tcb_parse_hwcap_and_convert_at_platform (void)
 {
 
-  uint64_t h1, h2;
+  uint64_t h1, h2, h3, h4;
 
   /* Read AT_PLATFORM string from auxv and convert it to a number.  */
   __tcb.at_platform = _dl_string_platform (GLRO (dl_platform));
@@ -39,6 +39,8 @@ __tcb_parse_hwcap_and_convert_at_platform (void)
   /* Read HWCAP and HWCAP2 from auxv.  */
   h1 = GLRO (dl_hwcap);
   h2 = GLRO (dl_hwcap2);
+  h3 = GLRO (dl_hwcap3);
+  h4 = GLRO (dl_hwcap4);
 
   /* hwcap contains only the latest supported ISA, the code checks which is
      and fills the previous supported ones.  */
@@ -64,13 +66,16 @@ __tcb_parse_hwcap_and_convert_at_platform (void)
   else if (h1 & PPC_FEATURE_POWER5)
     h1 |= PPC_FEATURE_POWER4;
 
-  uint64_t array_hwcaps[] = { h1, h2 };
+  uint64_t array_hwcaps[] = { h1, h2, h3, h4 };
   init_cpu_features (&GLRO(dl_powerpc_cpu_features), array_hwcaps);
 
   /* Consolidate both HWCAP and HWCAP2 into a single doubleword so that
      we can read both in a single load later.  */
   __tcb.hwcap = (h1 << 32) | (h2 & 0xffffffff);
-  __tcb.hwcap_extn = 0x0;
+
+  /* Consolidate both HWCAP3 and HWCAP4 into a single doubleword so that
+     we can read both in a single load later.  */
+  __tcb.hwcap_extn = (h3 << 32) | (h4 & 0xffffffff);
 
 }
 #if IS_IN (rtld)
diff --git a/sysdeps/unix/sysv/linux/dl-parse_auxv.h b/sysdeps/unix/sysv/linux/dl-parse_auxv.h
index e3d758b163..ea2a58ecb1 100644
--- a/sysdeps/unix/sysv/linux/dl-parse_auxv.h
+++ b/sysdeps/unix/sysv/linux/dl-parse_auxv.h
@@ -47,6 +47,8 @@ void _dl_parse_auxv (ElfW(auxv_t) *av, dl_parse_auxv_t auxv_values)
   GLRO(dl_platform) = (void *) auxv_values[AT_PLATFORM];
   GLRO(dl_hwcap) = auxv_values[AT_HWCAP];
   GLRO(dl_hwcap2) = auxv_values[AT_HWCAP2];
+  GLRO(dl_hwcap3) = auxv_values[AT_HWCAP3];
+  GLRO(dl_hwcap4) = auxv_values[AT_HWCAP4];
   GLRO(dl_clktck) = auxv_values[AT_CLKTCK];
   GLRO(dl_fpu_control) = auxv_values[AT_FPUCW];
   _dl_random = (void *) auxv_values[AT_RANDOM];
diff --git a/sysdeps/unix/sysv/linux/dl-sysdep.c b/sysdeps/unix/sysv/linux/dl-sysdep.c
index ad3692d738..e1b14e9eb3 100644
--- a/sysdeps/unix/sysv/linux/dl-sysdep.c
+++ b/sysdeps/unix/sysv/linux/dl-sysdep.c
@@ -197,6 +197,8 @@ _dl_show_auxv (void)
 	  [AT_SYSINFO_EHDR - 2] =	{ "SYSINFO_EHDR:      0x", hex },
 	  [AT_RANDOM - 2] =		{ "RANDOM:            0x", hex },
 	  [AT_HWCAP2 - 2] =		{ "HWCAP2:            0x", hex },
+	  [AT_HWCAP3 - 2] =		{ "HWCAP3:            0x", hex },
+	  [AT_HWCAP4 - 2] =		{ "HWCAP4:            0x", hex },
 	  [AT_MINSIGSTKSZ - 2] =	{ "MINSIGSTKSZ:       ", dec },
 	  [AT_L1I_CACHESIZE - 2] =	{ "L1I_CACHESIZE:     ", dec },
 	  [AT_L1I_CACHEGEOMETRY - 2] =	{ "L1I_CACHEGEOMETRY: 0x", hex },
diff --git a/sysdeps/unix/sysv/linux/powerpc/cpu-features.c b/sysdeps/unix/sysv/linux/powerpc/cpu-features.c
index 8e8a5ec2ea..a947d62db6 100644
--- a/sysdeps/unix/sysv/linux/powerpc/cpu-features.c
+++ b/sysdeps/unix/sysv/linux/powerpc/cpu-features.c
@@ -94,6 +94,8 @@ init_cpu_features (struct cpu_features *cpu_features, uint64_t hwcaps[])
      which are set by __tcb_parse_hwcap_and_convert_at_platform.  */
   cpu_features->hwcap = hwcaps[0];
   cpu_features->hwcap2 = hwcaps[1];
+  cpu_features->hwcap3 = hwcaps[2];
+  cpu_features->hwcap4 = hwcaps[3];
   /* Default is to use aligned memory access on optimized function unless
      tunables is enable, since for this case user can explicit disable
      unaligned optimizations.  */
diff --git a/sysdeps/unix/sysv/linux/powerpc/cpu-features.h b/sysdeps/unix/sysv/linux/powerpc/cpu-features.h
index 1294f0b601..e9eb6a13c8 100644
--- a/sysdeps/unix/sysv/linux/powerpc/cpu-features.h
+++ b/sysdeps/unix/sysv/linux/powerpc/cpu-features.h
@@ -26,6 +26,8 @@ struct cpu_features
   bool use_cached_memopt;
   unsigned long int hwcap;
   unsigned long int hwcap2;
+  unsigned long int hwcap3;
+  unsigned long int hwcap4;
 };
 
 static const char hwcap_names[] = {
diff --git a/sysdeps/unix/sysv/linux/powerpc/libc-start.c b/sysdeps/unix/sysv/linux/powerpc/libc-start.c
index a4705daf1c..6a00cd88cd 100644
--- a/sysdeps/unix/sysv/linux/powerpc/libc-start.c
+++ b/sysdeps/unix/sysv/linux/powerpc/libc-start.c
@@ -87,6 +87,12 @@ __libc_start_main_impl (int argc, char **argv,
       case AT_HWCAP2:
 	_dl_hwcap2 = (unsigned long int) av->a_un.a_val;
 	break;
+      case AT_HWCAP3:
+	_dl_hwcap3 = (unsigned long int) av->a_un.a_val;
+	break;
+      case AT_HWCAP4:
+	_dl_hwcap4 = (unsigned long int) av->a_un.a_val;
+	break;
       case AT_PLATFORM:
 	_dl_platform = (void *) av->a_un.a_val;
 	break;