migration/xbzrle: Use i386 host/cpuinfo.h

Perform the function selection once, and only if CONFIG_AVX512_OPT is enabled. Centralize the selection to xbzrle.c, instead of spreading the init across 3 files. Remove xbzrle-bench.c. The benefit of being able to benchmark the different implementations is less important than not peeking into the internals of the implementation. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Juan Quintela <quintela@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
qemu · May 23, 2023 · 7ba7db9 · 7ba7db9
1 parent 1b48d0a
commit 7ba7db9
Show file tree

Hide file tree

Showing 6 changed files with 39 additions and 550 deletions.
diff --git a/migration/ram.c b/migration/ram.c
@@ -90,34 +90,6 @@
 #define RAM_SAVE_FLAG_MULTIFD_FLUSH    0x200
 /* We can't use any flag that is bigger than 0x200 */
 
-int (*xbzrle_encode_buffer_func)(uint8_t *, uint8_t *, int,
-     uint8_t *, int) = xbzrle_encode_buffer;
-#if defined(CONFIG_AVX512BW_OPT)
-#include "qemu/cpuid.h"
-static void __attribute__((constructor)) init_cpu_flag(void)
-{
-    unsigned max = __get_cpuid_max(0, NULL);
-    int a, b, c, d;
-    if (max >= 1) {
-        __cpuid(1, a, b, c, d);
-         /* We must check that AVX is not just available, but usable.  */
-        if ((c & bit_OSXSAVE) && (c & bit_AVX) && max >= 7) {
-            int bv;
-            __asm("xgetbv" : "=a"(bv), "=d"(d) : "c"(0));
-            __cpuid_count(7, 0, a, b, c, d);
-           /* 0xe6:
-            *  XCR0[7:5] = 111b (OPMASK state, upper 256-bit of ZMM0-ZMM15
-            *                    and ZMM16-ZMM31 state are enabled by OS)
-            *  XCR0[2:1] = 11b (XMM state and YMM state are enabled by OS)
-            */
-            if ((bv & 0xe6) == 0xe6 && (b & bit_AVX512BW)) {
-                xbzrle_encode_buffer_func = xbzrle_encode_buffer_avx512;
-            }
-        }
-    }
-}
-#endif
-
 XBZRLECacheStats xbzrle_counters;
 
 /* used by the search for pages to send */
@@ -660,9 +632,9 @@ static int save_xbzrle_page(RAMState *rs, PageSearchStatus *pss,
     memcpy(XBZRLE.current_buf, *current_data, TARGET_PAGE_SIZE);
 
     /* XBZRLE encoding (if there is no overflow) */
-    encoded_len = xbzrle_encode_buffer_func(prev_cached_page, XBZRLE.current_buf,
-                                            TARGET_PAGE_SIZE, XBZRLE.encoded_buf,
-                                            TARGET_PAGE_SIZE);
+    encoded_len = xbzrle_encode_buffer(prev_cached_page, XBZRLE.current_buf,
+                                       TARGET_PAGE_SIZE, XBZRLE.encoded_buf,
+                                       TARGET_PAGE_SIZE);
 
     /*
      * Update the cache contents, so that it corresponds to the data

diff --git a/migration/xbzrle.c b/migration/xbzrle.c
@@ -17,8 +17,9 @@
 
 #if defined(CONFIG_AVX512BW_OPT)
 #include <immintrin.h>
+#include "host/cpuinfo.h"
 
-int __attribute__((target("avx512bw")))
+static int __attribute__((target("avx512bw")))
 xbzrle_encode_buffer_avx512(uint8_t *old_buf, uint8_t *new_buf, int slen,
                             uint8_t *dst, int dlen)
 {
@@ -135,6 +136,29 @@ xbzrle_encode_buffer_avx512(uint8_t *old_buf, uint8_t *new_buf, int slen,
     }
     return d;
 }
+
+static int xbzrle_encode_buffer_int(uint8_t *old_buf, uint8_t *new_buf,
+                                    int slen, uint8_t *dst, int dlen);
+
+static int (*accel_func)(uint8_t *, uint8_t *, int, uint8_t *, int);
+
+static void __attribute__((constructor)) init_accel(void)
+{
+    unsigned info = cpuinfo_init();
+    if (info & CPUINFO_AVX512BW) {
+        accel_func = xbzrle_encode_buffer_avx512;
+    } else {
+        accel_func = xbzrle_encode_buffer_int;
+    }
+}
+
+int xbzrle_encode_buffer(uint8_t *old_buf, uint8_t *new_buf, int slen,
+                         uint8_t *dst, int dlen)
+{
+    return accel_func(old_buf, new_buf, slen, dst, dlen);
+}
+
+#define xbzrle_encode_buffer xbzrle_encode_buffer_int
 #endif
 
 /*

diff --git a/migration/xbzrle.h b/migration/xbzrle.h
@@ -18,8 +18,5 @@ int xbzrle_encode_buffer(uint8_t *old_buf, uint8_t *new_buf, int slen,
                          uint8_t *dst, int dlen);
 
 int xbzrle_decode_buffer(uint8_t *src, int slen, uint8_t *dst, int dlen);
-#if defined(CONFIG_AVX512BW_OPT)
-int xbzrle_encode_buffer_avx512(uint8_t *old_buf, uint8_t *new_buf, int slen,
-                                uint8_t *dst, int dlen);
-#endif
+
 #endif
diff --git a/tests/bench/meson.build b/tests/bench/meson.build
@@ -3,12 +3,6 @@ qht_bench = executable('qht-bench',
                        sources: 'qht-bench.c',
                        dependencies: [qemuutil])
 
-if have_system
-xbzrle_bench = executable('xbzrle-bench',
-                       sources: 'xbzrle-bench.c',
-                       dependencies: [qemuutil,migration])
-endif
-
 qtree_bench = executable('qtree-bench',
                          sources: 'qtree-bench.c',
                          dependencies: [qemuutil])