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

[Rémi Denis-Courmont]

This adds the Linux-specific system call to detect CPU features. Unlike
the auxillary vector, this supports extension other than single lettered
ones. (The API is kind of a mess though.)

At the moment, we need this to detect Zba and Zbb at run-time.
---
 configure             |  5 +++++
 libavutil/riscv/cpu.c | 43 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 48 insertions(+)

diff --git a/configure b/configure
index 6be849fc08..a6039c1476 100755
--- a/configure
+++ b/configure
@@ -2202,6 +2202,7 @@ HAVE_LIST_PUB="
 
 HEADERS_LIST="
     arpa_inet_h
+    asm_hwprobe_h
     asm_types_h
     cdio_paranoia_h
     cdio_paranoia_paranoia_h
@@ -2227,6 +2228,7 @@ HEADERS_LIST="
     opencv2_core_core_c_h
     OpenGL_gl3_h
     poll_h
+    sys_hwprobe_h
     sys_param_h
     sys_resource_h
     sys_select_h
@@ -5410,6 +5412,9 @@ elif enabled ppc; then
 
 elif enabled riscv; then
 
+    check_headers asm/hwprobe.h
+    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..23e49767c2 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 +29,51 @@
 #include <sys/auxv.h>
 #define HWCAP_RV(letter) (1ul << ((letter) - 'A'))
 #endif
+#if defined (HAVE_SYS_HWPROBE_H)
+#include <sys/hwprobe.h>
+#elif defined (HAVE_ASM_HWPROBE_H)
+#include <asm/hwprobe.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+static int __riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
+                           size_t cpu_count, unsigned long *cpus,
+                           unsigned int flags)
+{
+        return syscall(__NR_riscv_hwprobe, pairs, pair_count, cpu_count, cpus,
+                       flags);
+}
+#endif
 
 int ff_get_cpu_flags_riscv(void)
 {
     int ret = 0;
+#if defined (HAVE_SYS_HWPROBE_H) || defined (HAVE_ASM_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;
+# ifdef RISCV_HWPROBE_IMA_V
+        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;
+# endif
+# ifdef RISCV_HWPROBE_EXT_ZBA
+        if (pairs[1].value & RISCV_HWPROBE_EXT_ZBA)
+            ret |= AV_CPU_FLAG_RVB_ADDR;
+# endif
+# ifdef RISCV_HWPROBE_EXT_ZBB
+        if (pairs[1].value & RISCV_HWPROBE_EXT_ZBB)
+            ret |= AV_CPU_FLAG_RVB_BASIC;
+# endif
+    } else
+#endif
 #if HAVE_GETAUXVAL
     {
         const unsigned long hwcap = getauxval(AT_HWCAP);
-- 
2.42.0