feat(parity): wire-stats protocol 2.25.0 + out-format %b/%c/%C

Bump PROTOCOL_VERSION to 2.25.0 and append a report_stats bool to the
config frame, add a STATUS_STATS status, and add process-wide wire byte
counters (protocol_bytes_written/read) for the client.

Render the rsync 3.4.1 --out-format %b (wire bytes sent) and %c (wire
bytes read back) tokens from per-file counter deltas, and %C (whole-file
xxh128 checksum, seed 0) via a new streaming checksum_digest_file().

src/shared/checksum.c

@@ -1,10 +1,14 @@
 #include "checksum.h"
+#include <fcntl.h>
 #include <openssl/evp.h>
 #include <string.h>
 #include <strings.h>
+#include <unistd.h>
 
 /* delta.c owns the single XXH_IMPLEMENTATION that provides the xxHash symbols
- * for the whole binary; this TU only needs the declarations. */
+ * for the whole binary; this TU only needs the declarations.  The streaming
+ * state structs and XXH3_update are exposed only with XXH_STATIC_LINKING_ONLY. */
+#define XXH_STATIC_LINKING_ONLY
 #include <xxhash.h>
 
 bool checksum_digest(ChecksumAlgo algo, uint64_t seed, const void* data, size_t size, uint8_t* out,
@@ -54,6 +58,99 @@ bool checksum_digest(ChecksumAlgo algo, uint64_t seed, const void* data, size_t
   return false;
 }
 
+bool checksum_digest_file(ChecksumAlgo algo, uint64_t seed, const char* path, uint8_t* out,
+                          size_t out_capacity, size_t* out_len) {
+  if (!path || !out || !out_len || out_capacity < CHECKSUM_MAX_DIGEST_LEN)
+    return false;
+
+  int fd = open(path, O_RDONLY | O_CLOEXEC);
+  if (fd < 0)
+    return false;
+
+  uint8_t buffer[64 * 1024];
+  bool ok = false;
+
+  if (algo == CHECKSUM_ALGO_MD5) {
+    EVP_MD_CTX* ctx = EVP_MD_CTX_new();
+    if (!ctx) {
+      close(fd);
+      return false;
+    }
+    unsigned int digest_len = 0;
+    if (EVP_DigestInit_ex(ctx, EVP_md5(), NULL) == 1) {
+      ok = true;
+      ssize_t got;
+      while ((got = read(fd, buffer, sizeof(buffer))) > 0) {
+        if (EVP_DigestUpdate(ctx, buffer, (size_t)got) != 1) {
+          ok = false;
+          break;
+        }
+      }
+      if (got < 0)
+        ok = false;
+      if (ok && EVP_DigestFinal_ex(ctx, out, &digest_len) == 1 && digest_len <= out_capacity)
+        *out_len = digest_len;
+      else
+        ok = false;
+    }
+    EVP_MD_CTX_free(ctx);
+    close(fd);
+    return ok;
+  }
+
+  XXH64_state_t xxh64;
+  XXH3_state_t* xxh3 = NULL;
+  if (algo == CHECKSUM_ALGO_XXH64) {
+    XXH64_reset(&xxh64, seed);
+  } else if (algo == CHECKSUM_ALGO_XXH3 || algo == CHECKSUM_ALGO_XXH128) {
+    xxh3 = XXH3_createState();
+    if (!xxh3) {
+      close(fd);
+      return false;
+    }
+    if (algo == CHECKSUM_ALGO_XXH3)
+      XXH3_64bits_reset_withSeed(xxh3, seed);
+    else
+      XXH3_128bits_reset_withSeed(xxh3, seed);
+  } else {
+    close(fd);
+    return false;
+  }
+
+  ok = true;
+  ssize_t got;
+  while ((got = read(fd, buffer, sizeof(buffer))) > 0) {
+    if (algo == CHECKSUM_ALGO_XXH64)
+      XXH64_update(&xxh64, buffer, (size_t)got);
+    else if (XXH3_64bits_update(xxh3, buffer, (size_t)got) == XXH_ERROR) {
+      ok = false;
+      break;
+    }
+  }
+  if (got < 0)
+    ok = false;
+
+  if (ok) {
+    if (algo == CHECKSUM_ALGO_XXH64) {
+      uint64_t digest = XXH64_digest(&xxh64);
+      memcpy(out, &digest, sizeof(digest));
+      *out_len = sizeof(digest);
+    } else if (algo == CHECKSUM_ALGO_XXH3) {
+      uint64_t digest = XXH3_64bits_digest(xxh3);
+      memcpy(out, &digest, sizeof(digest));
+      *out_len = sizeof(digest);
+    } else {
+      XXH128_hash_t digest = XXH3_128bits_digest(xxh3);
+      memcpy(out, &digest, sizeof(digest));
+      *out_len = sizeof(digest);
+    }
+  }
+  if (xxh3)
+    XXH3_freeState(xxh3);
+  close(fd);
+  return ok;
+}
+
 int checksum_algo_from_name(const char* name) {
   if (!name)
     return -1;

src/shared/checksum.h

@@ -35,8 +35,13 @@ typedef enum {
 bool checksum_digest(ChecksumAlgo algo, uint64_t seed, const void* data, size_t size, uint8_t* out,
                      size_t out_capacity, size_t* out_len);
 
-/* Resolve a --checksum-choice string (case-insensitive) to an algorithm id.
- * Accepts "xxh64"/"xxhash", "xxh3", "xxh128" and "md5".  "auto", rsync's
+/* Streaming whole-file digest: hash the contents of `path` without holding the
+ * whole file in memory.  Same digest/capacity contract as checksum_digest.
+ * Returns false on open/read failure or an undersized buffer. */
+bool checksum_digest_file(ChecksumAlgo algo, uint64_t seed, const char* path, uint8_t* out,
+                          size_t out_capacity, size_t* out_len);
+
+/* Resolve a --checksum-choice string (case-insensitive) to an algorithm id. * Accepts "xxh64"/"xxhash", "xxh3", "xxh128" and "md5".  "auto", rsync's
  * default automatic choice, is resolved to the default by the caller (it is not
  * a distinct algorithm here).  Returns -1 for any name FastSync does not
  * implement (md4/sha1/none included). */

src/shared/config.h

@@ -250,8 +250,17 @@ typedef enum SuperMode { SUPER_MODE_AUTO = 0, SUPER_MODE_ON = 1, SUPER_MODE_OFF
  * answer every per-file STATUS_CHECK with a STATUS_DEST_INFO snapshot of the
  * pre-transfer destination entry (see protocol.h).  It is set by the client
  * only when -i/--itemize-changes or --out-format asks for per-file change
- * output; the transfer decision itself is unchanged. */
-#define CONFIG_WIRE_OUTPUT_FIELDS(X) X(report_dest_info, bool, false, BOOL)
+ * output; the transfer decision itself is unchanged.
+ *
+ * Wire-stats wave (protocol 2.25.0).  report_stats tells the receiver to send a
+ * STATUS_STATS frame immediately before its terminal success status carrying
+ * the receiver-only counters (matched data, deleted/created file counts) and,
+ * for -n/--dry-run --delete, the destination-relative paths it WOULD have
+ * deleted.  It is set by the client only when --stats, --progress/-P, an
+ * --out-format token needs a wire counter (%b/%c), or a dry-run carries
+ * --delete; the transfer decision itself is unchanged. */
+#define CONFIG_WIRE_OUTPUT_FIELDS(X)                                                               \
+  X(report_dest_info, bool, false, BOOL) X(report_stats, bool, false, BOOL)
 
 /* All serialized fields, in exact wire order.  Concatenating the per-segment
  * lists here is what keeps the declaration order = the wire order. */
@@ -911,8 +920,17 @@ typedef struct Config {
  * snapshot of the old entry) before its ordinary verdict when the config frame
  * carries the new report_dest_info bool appended after the --copy-as block.
  * This is both a config-frame layout change (one trailing bool) and a frame
- * sequence change (the new status). */
-#define PROTOCOL_VERSION "2.23.0"
+ * sequence change (the new status).
+ *
+ * (4) Wire-stats parity (protocol 2.25.0): --stats, --progress/-P and the
+ * --out-format %b/%c tokens need receiver-only and wire counters that the push
+ * sender cannot observe, and -n/--dry-run --delete must report the extras it
+ * would have removed without deleting anything.  The config frame gains one
+ * trailing report_stats bool and the receiver emits a new STATUS_STATS frame
+ * (carrying matched data, created/deleted counts and the would-delete path
+ * list) immediately before its terminal success status.  Both a config-frame
+ * layout change and a frame-sequence change, hence the bump. */
+#define PROTOCOL_VERSION "2.25.0"
 #define DEFAULT_CHUNK_SIZE (10 * 1024 * 1024)
 /* Upper bound on total basis-dir entries (rsync caps --link-dest at 20). */
 #define MAX_BASIS_DIRS 64

src/shared/file_send.c

@@ -182,6 +182,7 @@ bool file_send_sendfile_with_skip(File* file, int file_descriptor, bool use_meta
       close(fd);
       return false;
     }
+    protocol_note_bytes_written((unsigned long long)sent);
   }
 
   close(fd);

src/shared/protocol.c

@@ -29,6 +29,13 @@ static unsigned long long io_bwlimit = 0;
 static mtx_t bw_mutex;
 static once_flag bw_mutex_once = ONCE_FLAG_INIT;
 
+/* Process-wide wire byte counters, used by the client to render rsync's
+ * --stats/--progress totals and the --out-format %b/%c tokens.  The zero-copy
+ * sendfile path bypasses protocol_send_n_data, so it reports its bytes through
+ * protocol_note_bytes_written. */
+static atomic_ullong io_bytes_written = 0;
+static atomic_ullong io_bytes_read = 0;
+
 static unsigned long long global_bwlimit(void);
 
 static bool protocol_reserve_memory(ProtocolSession* session, size_t charge) {
@@ -242,6 +249,18 @@ SSL* io_get_ssl(void) {
   return io_ssl;
 }
 
+unsigned long long protocol_bytes_written(void) {
+  return atomic_load(&io_bytes_written);
+}
+
+unsigned long long protocol_bytes_read(void) {
+  return atomic_load(&io_bytes_read);
+}
+
+void protocol_note_bytes_written(unsigned long long bytes) {
+  atomic_fetch_add(&io_bytes_written, bytes);
+}
+
 static ProtocolSession* legacy_session(int read_fd, int write_fd) {
   if (bound_session)
     return bound_session;
@@ -343,6 +362,7 @@ bool protocol_send_n_data(ProtocolSession* session, const void* data, size_t dat
       wait_events = POLLOUT;
   }
   log_debug_message(LOG_DEBUG_IO, "    Send n Data: %zu", total_bytes_send);
+  atomic_fetch_add(&io_bytes_written, (unsigned long long)total_bytes_send);
   return true;
 }
 
@@ -430,6 +450,7 @@ static bool protocol_receive_n_data_until(ProtocolSession* session, void* data,
       wait_events = POLLIN;
   }
   log_debug_message(LOG_DEBUG_IO, "    Received n Data: %zu", total_bytes_received);
+  atomic_fetch_add(&io_bytes_read, (unsigned long long)total_bytes_received);
   return true;
 }
 

src/shared/protocol.h

@@ -181,7 +181,14 @@ enum NET_STATUS {
    * (new vs modified, and which of size/time/perms/owner/group differ) without
    * changing the transfer decision itself.  Appended after
    * STATUS_DELETE_LIMIT so no existing status is renumbered. */
-  STATUS_DEST_INFO
+  STATUS_DEST_INFO,
+  /* End-of-transfer receiver counter report (protocol 2.25.0).  When the wire
+   * config carries report_stats=true, the receiver sends this status once,
+   * immediately before its terminal success status, followed by a fixed stats
+   * record (see format_stats_send/receive in format.h) and, when the run is a
+   * --dry-run with --delete, the would-delete path list.  Appended after
+   * STATUS_DEST_INFO so no existing status is renumbered. */
+  STATUS_STATS
 };
 
 void io_set_fds(int read_fd, int write_fd);
@@ -189,6 +196,14 @@ void io_set_bwlimit(unsigned long long bytes_per_sec);
 void io_set_ssl(SSL* ssl);
 SSL* io_get_ssl(void);
 
+/* Process-wide wire byte counters.  protocol_send_n_data/protocol_receive_n_data
+ * update them; the zero-copy sendfile path reports through
+ * protocol_note_bytes_written.  Used by the client to render rsync's
+ * --stats/--progress totals and the --out-format %b/%c tokens. */
+unsigned long long protocol_bytes_written(void);
+unsigned long long protocol_bytes_read(void);
+void protocol_note_bytes_written(unsigned long long bytes);
+
 void protocol_session_init(ProtocolSession* session, int read_fd, int write_fd);
 /* Transitional bridge for helpers whose signatures still carry only an fd. */
 void protocol_session_bind(ProtocolSession* session);