aarch64: Add Linux runtime cpu feature detection using HWCAP_CPUID

Based partially on code by Janne Grunau.

Signed-off-by: Martin Storsjö <martin@martin.st>

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

libavutil/aarch64/cpu.c

@@ -20,6 +20,56 @@
 #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;
+
+    hwcap = getauxval(AT_HWCAP);
+
+#if defined(HWCAP_CPUID)
+    // We can check for DOTPROD and I8MM using HWCAP_ASIMDDP and
+    // HWCAP2_I8MM too, avoiding to read the CPUID registers (which triggers
+    // a trap, handled by the kernel). However the HWCAP_* defines for these
+    // extensions are added much later than HWCAP_CPUID, so the userland
+    // headers might lack support for them even if the binary later is run
+    // on hardware that does support it (and where the kernel might support
+    // HWCAP_CPUID).
+    // 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;
+    }
+#else
+    (void)hwcap;
+#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 +83,8 @@ int ff_get_cpu_flags_aarch64(void)
     flags |= AV_CPU_FLAG_I8MM;
 #endif
 
+    flags |= detect_flags();
+
     return flags;
 }