[FFmpeg-devel] [PATCH 3/4] aarch64: Add linux runtime cpu feature detection using getauxval(AT_HWCAP)

[Martin Storsjö]

Based on code by Janne Grunau.

Using HWCAP_CPUID for user space access to the CPU feature registers. See
https://www.kernel.org/doc/html/latest/arm64/cpu-feature-registers.html.
---
 configure               |  2 ++
 libavutil/aarch64/cpu.c | 38 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 40 insertions(+)

diff --git a/configure b/configure
index 3c7473efb2..b5357b8d27 100755
--- a/configure
+++ b/configure
@@ -2207,6 +2207,7 @@ HAVE_LIST_PUB="
 
 HEADERS_LIST="
     arpa_inet_h
+    asm_hwcap_h
     asm_types_h
     cdio_paranoia_h
     cdio_paranoia_paranoia_h
@@ -6422,6 +6423,7 @@ check_headers io.h
 enabled libdrm &&
     check_headers linux/dma-buf.h
 
+check_headers asm/hwcap.h
 check_headers linux/perf_event.h
 check_headers libcrystalhd/libcrystalhd_if.h
 check_headers malloc.h
diff --git a/libavutil/aarch64/cpu.c b/libavutil/aarch64/cpu.c
index 42b33e4a2d..34c838c2f5 100644
--- a/libavutil/aarch64/cpu.c
+++ b/libavutil/aarch64/cpu.c
@@ -20,6 +20,42 @@
 #include "libavutil/cpu_internal.h"
 #include "config.h"
 
+#if (defined(__linux__) || defined(__ANDROID__)) && HAVE_GETAUXVAL && HAVE_ASM_HWCAP_H
+#include <stdint.h>
+#include <asm/hwcap.h>
+#include <sys/auxv.h>
+
+#define get_cpu_feature_reg(reg, val) \
+        __asm__("mrs %0, " #reg : "=r" (val))
+
+static int detect_flags(void)
+{
+    unsigned long ret = getauxval(AT_HWCAP);
+    int flags = 0;
+#if defined(HWCAP_CPUID)
+    uint64_t tmp;
+    if (!(ret & HWCAP_CPUID))
+        return flags;
+    get_cpu_feature_reg(ID_AA64ISAR0_EL1, tmp);
+    if (((tmp >> 44) & 0xf) == 0x1)
+        flags |= AV_CPU_FLAG_DOTPROD;
+    get_cpu_feature_reg(ID_AA64ISAR1_EL1, tmp);
+    if (((tmp >> 52) & 0xf) == 0x1)
+        flags |= AV_CPU_FLAG_I8MM;
+#endif
+
+    return flags;
+}
+
+#else
+
+static int detect_flags(void)
+{
+    return 0;
+}
+
+#endif
+
 int ff_get_cpu_flags_aarch64(void)
 {
     int flags = AV_CPU_FLAG_ARMV8 * HAVE_ARMV8 |
@@ -33,6 +69,8 @@ int ff_get_cpu_flags_aarch64(void)
     flags |= AV_CPU_FLAG_I8MM;
 #endif
 
+    flags |= detect_flags();
+
     return flags;
 }
 
-- 
2.37.1 (Apple Git-137.1)