[FFmpeg-devel] [PATCH 2/2] lavu/riscv: add hwprobe() for CPU detection

[Rémi Denis-Courmont]

This adds the Linux-specific function call to detect CPU features. Unlike
the more portable auxillary vector, this supports extensions other than
single lettered ones. At this point, FFmpeg already needs this to detect
Zba and Zbb at run-time, and probably will need it for Zvbb in the near
future.

Support will be available in glibc 2.40 onward.
---
 configure             |  3 +++
 libavutil/riscv/cpu.c | 25 +++++++++++++++++++++++++
 2 files changed, 28 insertions(+)

diff --git a/configure b/configure
index ed74583a6f..bc8f40ed85 100755
--- a/configure
+++ b/configure
@@ -2298,6 +2298,7 @@ HEADERS_LIST="
     OpenGL_gl3_h
     poll_h
     pthread_np_h
+    sys_hwprobe_h
     sys_param_h
     sys_resource_h
     sys_select_h
@@ -5537,6 +5538,8 @@ elif enabled ppc; then
 
 elif enabled riscv; then
 
+    check_headers sys/hwprobe.h
+
     if test_cpp_condition stddef.h "__riscv_zbb"; then
         enable fast_clz
     fi
diff --git a/libavutil/riscv/cpu.c b/libavutil/riscv/cpu.c
index 984293aef0..c3683b06d0 100644
--- a/libavutil/riscv/cpu.c
+++ b/libavutil/riscv/cpu.c
@@ -18,8 +18,10 @@
  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  */
 
+#define _GNU_SOURCE
 #include "libavutil/cpu.h"
 #include "libavutil/cpu_internal.h"
+#include "libavutil/macros.h"
 #include "libavutil/log.h"
 #include "config.h"
 
@@ -27,10 +29,33 @@
 #include <sys/auxv.h>
 #define HWCAP_RV(letter) (1ul << ((letter) - 'A'))
 #endif
+#ifdef HAVE_SYS_HWPROBE_H
+#include <sys/hwprobe.h>
+#endif
 
 int ff_get_cpu_flags_riscv(void)
 {
     int ret = 0;
+#ifdef HAVE_SYS_HWPROBE_H
+    struct riscv_hwprobe pairs[] = {
+        { RISCV_HWPROBE_KEY_BASE_BEHAVIOR, 0 },
+        { RISCV_HWPROBE_KEY_IMA_EXT_0, 0 },
+    };
+
+    if (__riscv_hwprobe(pairs, FF_ARRAY_ELEMS(pairs), 0, NULL, 0) == 0) {
+        if (pairs[0].value & RISCV_HWPROBE_BASE_BEHAVIOR_IMA)
+            ret |= AV_CPU_FLAG_RVI;
+        if (pairs[1].value & RISCV_HWPROBE_IMA_FD)
+            ret |= AV_CPU_FLAG_RVF | AV_CPU_FLAG_RVD;
+        if (pairs[1].value & RISCV_HWPROBE_IMA_V)
+            ret |= AV_CPU_FLAG_RVV_I32 | AV_CPU_FLAG_RVV_I64
+                 | AV_CPU_FLAG_RVV_F32 | AV_CPU_FLAG_RVV_F64;
+        if (pairs[1].value & RISCV_HWPROBE_EXT_ZBA)
+            ret |= AV_CPU_FLAG_RVB_ADDR;
+        if (pairs[1].value & RISCV_HWPROBE_EXT_ZBB)
+            ret |= AV_CPU_FLAG_RVB_BASIC;
+    } else
+#endif
 #if HAVE_GETAUXVAL
     {
         const unsigned long hwcap = getauxval(AT_HWCAP);
-- 
2.43.0