[FFmpeg-devel] [PATCH v2 3/5] aarch64: Add Linux runtime cpu feature detection using getauxval(AT_HWCAP)

[Martin Storsjö]

Based partially on code by Janne Grunau.

---
Updated to use both the direct HWCAP* macros and HWCAP_CPUID. A
not unreasonably old distribution like Ubuntu 20.04 does have
HWCAP_CPUID but not HWCAP2_I8MM in the distribution provided headers.

Alternatively I guess we could carry our own fallback hardcoded values
for the HWCAP* values we use and skip HWCAP_CPUID.
---
 configure               |  2 ++
 libavutil/aarch64/cpu.c | 63 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 65 insertions(+)

diff --git a/configure b/configure
index 50eb27ba0e..b39de74de5 100755
--- a/configure
+++ b/configure
@@ -2209,6 +2209,7 @@ HAVE_LIST_PUB="
 
 HEADERS_LIST="
     arpa_inet_h
+    asm_hwcap_h
     asm_types_h
     cdio_paranoia_h
     cdio_paranoia_paranoia_h
@@ -6432,6 +6433,7 @@ 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 0c76f5ad15..4563959ffd 100644
--- a/libavutil/aarch64/cpu.c
+++ b/libavutil/aarch64/cpu.c
@@ -20,6 +20,67 @@
 #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)
+{
+    int flags = 0;
+    unsigned long hwcap, hwcap2;
+
+    // Check for support using direct individual HWCAPs
+    hwcap = getauxval(AT_HWCAP);
+#ifdef HWCAP_ASIMDDP
+    if (hwcap & HWCAP_ASIMDDP)
+        flags |= AV_CPU_FLAG_DOTPROD;
+#endif
+
+#ifdef AT_HWCAP2
+    hwcap2 = getauxval(AT_HWCAP2);
+#ifdef HWCAP2_I8MM
+    if (hwcap2 & HWCAP2_I8MM)
+        flags |= AV_CPU_FLAG_I8MM;
+#endif
+#endif
+
+    // Silence warnings if none of the hwcaps to check are known.
+    (void)hwcap;
+    (void)hwcap2;
+
+#if defined(HWCAP_CPUID)
+    // The HWCAP_* defines for individual extensions may become available late, as
+    // they require updates to userland headers. As a fallback, see if we can access
+    // the CPUID registers (trapped via the kernel).
+    // See https://www.kernel.org/doc/html/latest/arm64/cpu-feature-registers.html
+    if (hwcap & HWCAP_CPUID) {
+        uint64_t tmp;
+
+        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 +94,8 @@ 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)