[PATCH 08/30] Update AVX512 support for xbzrle_encode_buffer

[Juan Quintela <quintela@redhat.com>]

From: ling xu <ling1.xu@intel.com>

This commit updates code of avx512 support for xbzrle_encode_buffer
function to accelerate xbzrle encoding speed. Runtime check of avx512
support and benchmark for this feature are added. Compared with C
version of xbzrle_encode_buffer function, avx512 version can achieve
50%-70% performance improvement on benchmarking. In addition, if dirty
data is randomly located in 4K page, the avx512 version can achieve
almost 140% performance gain.

Signed-off-by: ling xu <ling1.xu@intel.com>
Co-authored-by: Zhou Zhao <zhou.zhao@intel.com>
Co-authored-by: Jun Jin <jun.i.jin@intel.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
---
 meson.build                   |  16 +++++
 migration/xbzrle.h            |   4 ++
 migration/ram.c               |  34 +++++++++-
 migration/xbzrle.c            | 124 ++++++++++++++++++++++++++++++++++
 meson_options.txt             |   2 +
 scripts/meson-buildoptions.sh |  14 ++--
 6 files changed, 186 insertions(+), 8 deletions(-)

diff --git a/meson.build b/meson.build
index cf3e517e56..d0d28f5c9e 100644
--- a/meson.build
+++ b/meson.build
@@ -2344,6 +2344,22 @@ config_host_data.set('CONFIG_AVX512F_OPT', get_option('avx512f') \
     int main(int argc, char *argv[]) { return bar(argv[argc - 1]); }
   '''), error_message: 'AVX512F not available').allowed())
 
+config_host_data.set('CONFIG_AVX512BW_OPT', get_option('avx512bw') \
+  .require(have_cpuid_h, error_message: 'cpuid.h not available, cannot enable AVX512BW') \
+  .require(cc.links('''
+    #pragma GCC push_options
+    #pragma GCC target("avx512bw")
+    #include <cpuid.h>
+    #include <immintrin.h>
+    static int bar(void *a) {
+
+      __m512i *x = a;
+      __m512i res= _mm512_abs_epi8(*x);
+      return res[1];
+    }
+    int main(int argc, char *argv[]) { return bar(argv[0]); }
+  '''), error_message: 'AVX512BW not available').allowed())
+
 have_pvrdma = get_option('pvrdma') \
   .require(rdma.found(), error_message: 'PVRDMA requires OpenFabrics libraries') \
   .require(cc.compiles(gnu_source_prefix + '''
diff --git a/migration/xbzrle.h b/migration/xbzrle.h
index a0db507b9c..6feb49160a 100644
--- a/migration/xbzrle.h
+++ b/migration/xbzrle.h
@@ -18,4 +18,8 @@ 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/migration/ram.c b/migration/ram.c
index 67e41dd2c0..bb4f08bfed 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -83,6 +83,34 @@
 /* 0x80 is reserved in migration.h start with 0x100 next */
 #define RAM_SAVE_FLAG_COMPRESS_PAGE    0x100
 
+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;
 
 /* struct contains XBZRLE cache and a static page
@@ -802,9 +830,9 @@ static int save_xbzrle_page(RAMState *rs, uint8_t **current_data,
     memcpy(XBZRLE.current_buf, *current_data, TARGET_PAGE_SIZE);
 
     /* XBZRLE encoding (if there is no overflow) */
-    encoded_len = xbzrle_encode_buffer(prev_cached_page, XBZRLE.current_buf,
-                                       TARGET_PAGE_SIZE, XBZRLE.encoded_buf,
-                                       TARGET_PAGE_SIZE);
+    encoded_len = xbzrle_encode_buffer_func(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
index 1ba482ded9..05366e86c0 100644
--- a/migration/xbzrle.c
+++ b/migration/xbzrle.c
@@ -174,3 +174,127 @@ int xbzrle_decode_buffer(uint8_t *src, int slen, uint8_t *dst, int dlen)
 
     return d;
 }
+
+#if defined(CONFIG_AVX512BW_OPT)
+#pragma GCC push_options
+#pragma GCC target("avx512bw")
+#include <immintrin.h>
+int xbzrle_encode_buffer_avx512(uint8_t *old_buf, uint8_t *new_buf, int slen,
+                             uint8_t *dst, int dlen)
+{
+    uint32_t zrun_len = 0, nzrun_len = 0;
+    int d = 0, i = 0, num = 0;
+    uint8_t *nzrun_start = NULL;
+    /* add 1 to include residual part in main loop */
+    uint32_t count512s = (slen >> 6) + 1;
+    /* countResidual is tail of data, i.e., countResidual = slen % 64 */
+    uint32_t count_residual = slen & 0b111111;
+    bool never_same = true;
+    uint64_t mask_residual = 1;
+    mask_residual <<= count_residual;
+    mask_residual -= 1;
+    __m512i r = _mm512_set1_epi32(0);
+
+    while (count512s) {
+        if (d + 2 > dlen) {
+            return -1;
+        }
+
+        int bytes_to_check = 64;
+        uint64_t mask = 0xffffffffffffffff;
+        if (count512s == 1) {
+            bytes_to_check = count_residual;
+            mask = mask_residual;
+        }
+        __m512i old_data = _mm512_mask_loadu_epi8(r,
+                                                  mask, old_buf + i);
+        __m512i new_data = _mm512_mask_loadu_epi8(r,
+                                                  mask, new_buf + i);
+        uint64_t comp = _mm512_cmpeq_epi8_mask(old_data, new_data);
+        count512s--;
+
+        bool is_same = (comp & 0x1);
+        while (bytes_to_check) {
+            if (is_same) {
+                if (nzrun_len) {
+                    d += uleb128_encode_small(dst + d, nzrun_len);
+                    if (d + nzrun_len > dlen) {
+                        return -1;
+                    }
+                    nzrun_start = new_buf + i - nzrun_len;
+                    memcpy(dst + d, nzrun_start, nzrun_len);
+                    d += nzrun_len;
+                    nzrun_len = 0;
+                }
+                /* 64 data at a time for speed */
+                if (count512s && (comp == 0xffffffffffffffff)) {
+                    i += 64;
+                    zrun_len += 64;
+                    break;
+                }
+                never_same = false;
+                num = __builtin_ctzll(~comp);
+                num = (num < bytes_to_check) ? num : bytes_to_check;
+                zrun_len += num;
+                bytes_to_check -= num;
+                comp >>= num;
+                i += num;
+                if (bytes_to_check) {
+                    /* still has different data after same data */
+                    d += uleb128_encode_small(dst + d, zrun_len);
+                    zrun_len = 0;
+                } else {
+                    break;
+                }
+            }
+            if (never_same || zrun_len) {
+                /*
+                 * never_same only acts if
+                 * data begins with diff in first count512s
+                 */
+                d += uleb128_encode_small(dst + d, zrun_len);
+                zrun_len = 0;
+                never_same = false;
+            }
+            /* has diff, 64 data at a time for speed */
+            if ((bytes_to_check == 64) && (comp == 0x0)) {
+                i += 64;
+                nzrun_len += 64;
+                break;
+            }
+            num = __builtin_ctzll(comp);
+            num = (num < bytes_to_check) ? num : bytes_to_check;
+            nzrun_len += num;
+            bytes_to_check -= num;
+            comp >>= num;
+            i += num;
+            if (bytes_to_check) {
+                /* mask like 111000 */
+                d += uleb128_encode_small(dst + d, nzrun_len);
+                /* overflow */
+                if (d + nzrun_len > dlen) {
+                    return -1;
+                }
+                nzrun_start = new_buf + i - nzrun_len;
+                memcpy(dst + d, nzrun_start, nzrun_len);
+                d += nzrun_len;
+                nzrun_len = 0;
+                is_same = true;
+            }
+        }
+    }
+
+    if (nzrun_len != 0) {
+        d += uleb128_encode_small(dst + d, nzrun_len);
+        /* overflow */
+        if (d + nzrun_len > dlen) {
+            return -1;
+        }
+        nzrun_start = new_buf + i - nzrun_len;
+        memcpy(dst + d, nzrun_start, nzrun_len);
+        d += nzrun_len;
+    }
+    return d;
+}
+#pragma GCC pop_options
+#endif
diff --git a/meson_options.txt b/meson_options.txt
index 66128178bf..96814dd211 100644
--- a/meson_options.txt
+++ b/meson_options.txt
@@ -104,6 +104,8 @@ option('avx2', type: 'feature', value: 'auto',
        description: 'AVX2 optimizations')
 option('avx512f', type: 'feature', value: 'disabled',
        description: 'AVX512F optimizations')
+option('avx512bw', type: 'feature', value: 'auto',
+       description: 'AVX512BW optimizations')
 option('keyring', type: 'feature', value: 'auto',
        description: 'Linux keyring support')
 
diff --git a/scripts/meson-buildoptions.sh b/scripts/meson-buildoptions.sh
index 2cb0de5601..bcb5d854a5 100644
--- a/scripts/meson-buildoptions.sh
+++ b/scripts/meson-buildoptions.sh
@@ -40,7 +40,8 @@ meson_options_help() {
   printf "%s\n" '  --enable-trace-backends=CHOICES'
   printf "%s\n" '                           Set available tracing backends [log] (choices:'
   printf "%s\n" '                           dtrace/ftrace/log/nop/simple/syslog/ust)'
-  printf "%s\n" '  --firmwarepath=VALUES    search PATH for firmware files [share/qemu-firmware]'
+  printf "%s\n" '  --firmwarepath=VALUES    search PATH for firmware files [share/qemu-'
+  printf "%s\n" '                           firmware]'
   printf "%s\n" '  --iasl=VALUE             Path to ACPI disassembler'
   printf "%s\n" '  --includedir=VALUE       Header file directory [include]'
   printf "%s\n" '  --interp-prefix=VALUE    where to find shared libraries etc., use %M for'
@@ -66,6 +67,7 @@ meson_options_help() {
   printf "%s\n" '  attr            attr/xattr support'
   printf "%s\n" '  auth-pam        PAM access control'
   printf "%s\n" '  avx2            AVX2 optimizations'
+  printf "%s\n" '  avx512bw        AVX512BW optimizations'
   printf "%s\n" '  avx512f         AVX512F optimizations'
   printf "%s\n" '  blkio           libblkio block device driver'
   printf "%s\n" '  bochs           bochs image format support'
@@ -155,6 +157,8 @@ meson_options_help() {
   printf "%s\n" '  usb-redir       libusbredir support'
   printf "%s\n" '  vde             vde network backend support'
   printf "%s\n" '  vdi             vdi image format support'
+  printf "%s\n" '  vduse-blk-export'
+  printf "%s\n" '                  VDUSE block export support'
   printf "%s\n" '  vfio-user-server'
   printf "%s\n" '                  vfio-user server support'
   printf "%s\n" '  vhost-crypto    vhost-user crypto backend support'
@@ -163,8 +167,6 @@ meson_options_help() {
   printf "%s\n" '  vhost-user      vhost-user backend support'
   printf "%s\n" '  vhost-user-blk-server'
   printf "%s\n" '                  build vhost-user-blk server'
-  printf "%s\n" '  vduse-blk-export'
-  printf "%s\n" '                  VDUSE block export support'
   printf "%s\n" '  vhost-vdpa      vhost-vdpa kernel backend support'
   printf "%s\n" '  virglrenderer   virgl rendering support'
   printf "%s\n" '  virtfs          virtio-9p support'
@@ -193,6 +195,8 @@ _meson_option_parse() {
     --disable-auth-pam) printf "%s" -Dauth_pam=disabled ;;
     --enable-avx2) printf "%s" -Davx2=enabled ;;
     --disable-avx2) printf "%s" -Davx2=disabled ;;
+    --enable-avx512bw) printf "%s" -Davx512bw=enabled ;;
+    --disable-avx512bw) printf "%s" -Davx512bw=disabled ;;
     --enable-avx512f) printf "%s" -Davx512f=enabled ;;
     --disable-avx512f) printf "%s" -Davx512f=disabled ;;
     --enable-gcov) printf "%s" -Db_coverage=true ;;
@@ -426,6 +430,8 @@ _meson_option_parse() {
     --disable-vde) printf "%s" -Dvde=disabled ;;
     --enable-vdi) printf "%s" -Dvdi=enabled ;;
     --disable-vdi) printf "%s" -Dvdi=disabled ;;
+    --enable-vduse-blk-export) printf "%s" -Dvduse_blk_export=enabled ;;
+    --disable-vduse-blk-export) printf "%s" -Dvduse_blk_export=disabled ;;
     --enable-vfio-user-server) printf "%s" -Dvfio_user_server=enabled ;;
     --disable-vfio-user-server) printf "%s" -Dvfio_user_server=disabled ;;
     --enable-vhost-crypto) printf "%s" -Dvhost_crypto=enabled ;;
@@ -438,8 +444,6 @@ _meson_option_parse() {
     --disable-vhost-user) printf "%s" -Dvhost_user=disabled ;;
     --enable-vhost-user-blk-server) printf "%s" -Dvhost_user_blk_server=enabled ;;
     --disable-vhost-user-blk-server) printf "%s" -Dvhost_user_blk_server=disabled ;;
-    --enable-vduse-blk-export) printf "%s" -Dvduse_blk_export=enabled ;;
-    --disable-vduse-blk-export) printf "%s" -Dvduse_blk_export=disabled ;;
     --enable-vhost-vdpa) printf "%s" -Dvhost_vdpa=enabled ;;
     --disable-vhost-vdpa) printf "%s" -Dvhost_vdpa=disabled ;;
     --enable-virglrenderer) printf "%s" -Dvirglrenderer=enabled ;;
-- 
2.38.1