feat: receiver-side basis matching with link/copy materialization

The receiver's per-file incremental check now consults the ordered basis-dir
list whenever the destination is not already up to date.  An exact basis match
requires equal size, equal mtime (unless --size-only; --ignore-times disables
basis matching like rsync), and an equal content xxHash64 -- the sender sends
its xxHash for every file whenever basis dirs are configured (not only under
--checksum), so a hard link or local copy is only ever made from byte-identical
content.

On a match:
  - compare-dest: reply STATUS_OK and skip data only when the destination does
    not already hold the file (sparse, rsync parity).  A destination that holds
    a DIFFERENT version falls back to a normal transfer instead of rsync's
    delete, keeping the mirror complete.
  - copy-dest: reply STATUS_OK and hand a synthetic File (bytes read from the
    basis file, basis metadata) to the normal store sink, so the file is
    installed as a real local copy through the existing atomic temp+rename
    engine and honors --existing/--ignore-existing/--update/--backup/
    --delay-updates/--partial-dir unchanged.
  - link-dest: same, but File.basis_link records the basis path and the store
    engine calls the new file_to_disk_secure_link(): an atomic temp hard link +
    rename.  Cross-filesystem/refused links fall back to a byte-identical local
    copy (never a corrupt or partial file); the copy fallback applies metadata,
    while a successful link keeps the basis inode's own attributes so the basis
    file is never mutated.

Basis-materialized files carry File.skip so they are not acknowledged to a
--remove-source-files sender (the sender already saw STATUS_OK and keeps the
source).  The no-match path is byte-for-byte identical to the existing delta /
full-data transfer.

src/client/client_send.c

@@ -613,7 +613,10 @@ static int incremental_check(Client* client, File* file, const Config* config,
     return -1;
   if (!send_n_data(client->file_descriptor, &mtime_nsec, sizeof(mtime_nsec)))
     return -1;
-  if (config->checksum) {
+  /* With alternate basis directories the receiver must be able to verify the
+   * content of every candidate basis file, so the sender supplies its xxHash64
+   * for every file even when --checksum was not requested. */
+  if (config->checksum || config_has_basis(config)) {
     uint64_t checksum;
     if (!file_checksum(file, &checksum) ||
         !send_n_data(client->file_descriptor, &checksum, sizeof(checksum)))

src/server/receiver.c

@@ -214,7 +214,7 @@ static bool receiver_save_file(File* file, void* context_pointer) {
     result = file_save_to_disk_full(context->config->receive_root_directory, file, context->config);
   }
   if (result != FILE_SAVE_ERROR && context->config->remove_source_files && !file->is_dir &&
-      !receiver_outcomes_append(&context->outcomes, (unsigned char)result)) {
+      !file->skip && !receiver_outcomes_append(&context->outcomes, (unsigned char)result)) {
     file_destroy(file);
     return false;
   }

src/shared/file.c

@@ -83,6 +83,7 @@ File* file_create(const char* path) {
   file->metadata = NULL;
   file->skip = false;
   file->is_dir = false;
+  file->basis_link = NULL;
   return file;
 }
 
@@ -98,6 +99,8 @@ void file_destroy(void* item) {
   file->path = NULL;
   free(file->send_path);
   file->send_path = NULL;
+  free(file->basis_link);
+  file->basis_link = NULL;
   free(file);
 }
 
@@ -630,6 +633,106 @@ bool file_to_disk_secure_no_replace(const char* path, const void* data,
                                   preserve_executability, false, true, false, temp_dir);
 }
 
+/* Atomic --link-dest install.  The destination is replaced (via a temporary
+ * name and a final rename) with a hard link to `basis_path`.  When a hard
+ * link cannot be created (the basis lives on a different filesystem, the
+ * filesystem refuses hard links, ...) the install falls back to writing a
+ * local copy from `data`/`data_size`, which the caller has already verified is
+ * byte-identical to the basis file.  `metadata` is only applied on that copy
+ * fallback; a successful hard link keeps the basis inode's own attributes
+ * (applying metadata through the shared inode would mutate the basis file).
+ * Returns false only when both the link and the copy fallback fail. */
+bool file_to_disk_secure_link(const char* path, const char* basis_path, const void* data,
+                              unsigned long long data_size, const FileMetadata* metadata,
+                              bool preserve_executability, bool use_fsync, const char* temp_dir) {
+  if (!path || !basis_path)
+    return false;
+  char* leaf = NULL;
+  int dirfd = file_open_secure_parent(path, &leaf, true);
+  if (dirfd < 0)
+    return false;
+
+  int scratch_dirfd = -1;
+  if (temp_dir) {
+    scratch_dirfd = file_open_private_dir(temp_dir);
+    if (scratch_dirfd < 0) {
+      int saved_errno = errno;
+      log_message(LOG_LEVEL_ERROR, "could not open --temp-dir scratch directory '%s': %s", temp_dir,
+                  strerror(saved_errno));
+      close(dirfd);
+      free(leaf);
+      return false;
+    }
+  }
+
+  char* basis_leaf = NULL;
+  int basis_dirfd = file_open_secure_parent(basis_path, &basis_leaf, false);
+  bool linked = false;
+  if (basis_dirfd >= 0 && basis_leaf != NULL) {
+    int tmp_size = snprintf(NULL, 0, ".%s.tmp.%ld.%llu", leaf, (long)getpid(), ~0ULL);
+    char* tmp = NULL;
+    if (tmp_size >= 0)
+      tmp = malloc((size_t)tmp_size + 1);
+    if (!tmp) {
+      log_message(LOG_LEVEL_ERROR, "memory allocation failed while hard-linking basis file");
+    } else {
+      for (unsigned int i = 0; i < 100 && !linked; ++i) {
+        if (scratch_dirfd >= 0)
+          snprintf(tmp, (size_t)tmp_size + 1, ".%s.tmp.%ld.%llu", leaf, (long)getpid(),
+                   next_temp_sequence());
+        else
+          snprintf(tmp, (size_t)tmp_size + 1, ".%s.tmp.%ld.%u", leaf, (long)getpid(), i);
+        if (linkat(basis_dirfd, basis_leaf, scratch_dirfd >= 0 ? scratch_dirfd : dirfd, tmp, 0) ==
+            0) {
+          linked = true;
+          break;
+        }
+        if (errno != EEXIST)
+          break; /* EXDEV / EPERM / ...: give up and fall back to a copy */
+      }
+      if (linked) {
+        int target_dirfd = scratch_dirfd >= 0 ? scratch_dirfd : dirfd;
+        if (use_fsync) {
+          int tfd = openat(target_dirfd, tmp, O_RDONLY | O_NOFOLLOW | O_CLOEXEC);
+          if (tfd < 0 || fsync(tfd) != 0) {
+            linked = false;
+            if (tfd >= 0)
+              close(tfd);
+          } else {
+            close(tfd);
+          }
+        }
+        if (linked && renameat(target_dirfd, tmp, dirfd, leaf) != 0)
+          linked = false;
+        if (!linked)
+          unlinkat(target_dirfd, tmp, 0);
+      }
+      free(tmp);
+    }
+  }
+  if (basis_dirfd >= 0)
+    close(basis_dirfd);
+  free(basis_leaf);
+  basis_leaf = NULL;
+
+  if (!linked) {
+    if (scratch_dirfd >= 0)
+      close(scratch_dirfd);
+    close(dirfd);
+    free(leaf);
+    /* The basis file could not be linked in (missing, cross-device, refused
+       by the filesystem).  Write a byte-identical local copy instead. */
+    return file_to_disk_secure_with_fsync(path, data, data_size, false, false, metadata,
+                                          preserve_executability, use_fsync, temp_dir);
+  }
+
+  if (scratch_dirfd >= 0)
+    close(scratch_dirfd);
+  close(dirfd);
+  free(leaf);
+  return true;
+}
+
 bool file_write_to_disk(const char* path, const void* data, unsigned long long data_size,
                         bool inplace, bool sparse) {
   if (!path || (!data && data_size != 0) || has_path_traversal(path))

src/shared/file.h

@@ -63,5 +63,12 @@ bool file_to_disk_secure_no_replace(const char* path, const void* data,
                                     unsigned long long data_size, bool sparse,
                                     const FileMetadata* metadata, bool preserve_executability,
                                     const char* temp_dir);
+/* Atomic --link-dest install: replace `path` with a hard link to `basis_path`
+   (via a temp name + rename); fall back to a byte-identical local copy from
+   `data` when the link is impossible (EXDEV/EPERM/unsupported filesystem).
+   `metadata` is applied only on the copy fallback. */
+bool file_to_disk_secure_link(const char* path, const char* basis_path, const void* data,
+                              unsigned long long data_size, const FileMetadata* metadata,
+                              bool preserve_executability, bool use_fsync, const char* temp_dir);
 
 #endif

src/shared/file_receive.c

@@ -75,10 +75,17 @@ static FileSaveResult file_stage_delayed_update(const char* root_directory,
   /* The staged location is brand new (stale leftovers from a prior crash were
      wiped by prepare), so the plain atomic temp+rename engine installs the
      complete file there.  --temp-dir scratch is deliberately not layered on
-     top of the delay-updates staging tree. */
+     top of the delay-updates staging tree.  A --link-dest basis file is hard
-  bool ok =
+     linked into the staging tree (so publication's rename keeps the link). */
-      file_to_disk_secure_with_fsync(staged_path, file->data->data, file->data->size, false, sparse,
+  bool ok;
-                                     metadata, preserve_executability, config->use_fsync, NULL);
+  if (file->basis_link) {
+    ok = file_to_disk_secure_link(staged_path, file->basis_link, file->data->data, file->data->size,
+                                  metadata, preserve_executability, config->use_fsync, NULL);
+  } else {
+    ok = file_to_disk_secure_with_fsync(staged_path, file->data->data, file->data->size, false,
+                                        sparse, metadata, preserve_executability, config->use_fsync,
+                                        NULL);
+  }
   if (!ok) {
     free(staged_path);
     return FILE_SAVE_ERROR;
@@ -272,16 +279,27 @@ FileSaveResult file_save_to_disk_full(const char* root_directory, const File* fi
     while (temp_len > 1 && confined_temp[temp_len - 1] == '/')
       confined_temp[--temp_len] = '\0';
   }
-  bool ok =
+  /* A --link-dest basis hit installs an atomic hard link (with a byte-copy
-      config && config->ignore_existing
+     fallback); --inplace and the update/no-replace write variants do not
-          ? file_to_disk_secure_no_replace(disk_path, file->data->data, file->data->size, sparse,
+     apply to a fresh hard link, whose inode attributes already match.  The
-                                           metadata, preserve_executability, confined_temp)
+     existing/ignore-existing/update/backup preamble above has already made the
-      : config && config->update
+     policy decision. */
-          ? file_to_disk_secure_update(disk_path, file->data->data, file->data->size, inplace,
+  bool ok;
-                                       sparse, metadata, preserve_executability, confined_temp)
+  if (config && file->basis_link) {
-          : file_to_disk_secure_with_fsync(disk_path, file->data->data, file->data->size, inplace,
+    ok = file_to_disk_secure_link(disk_path, file->basis_link, file->data->data, file->data->size,
-                                           sparse, metadata, preserve_executability,
+                                  metadata, preserve_executability, config->use_fsync,
-                                           config && config->use_fsync, confined_temp);
+                                  confined_temp);
+  } else {
+    ok = config && config->ignore_existing
+             ? file_to_disk_secure_no_replace(disk_path, file->data->data, file->data->size, sparse,
+                                              metadata, preserve_executability, confined_temp)
+         : config && config->update
+             ? file_to_disk_secure_update(disk_path, file->data->data, file->data->size, inplace,
+                                          sparse, metadata, preserve_executability, confined_temp)
+             : file_to_disk_secure_with_fsync(disk_path, file->data->data, file->data->size,
+                                              inplace, sparse, metadata, preserve_executability,
+                                              config && config->use_fsync, confined_temp);
+  }
   free(confined_temp);
   confined_temp = NULL;
   if (!ok)
@@ -505,6 +523,143 @@ static File* receive_delta_file(int fd, const Config* config, const char* check_
   return NULL;
 }
 
+/* ---- Alternate basis directories (--compare-dest / --copy-dest / --link-dest) ----
+ * The receiver consults the ordered basis-dir list only when the destination
+ * entry is NOT already up to date.  An "exact match" requires an equal size,
+ * an equal mtime (unless --size-only), and an equal content xxHash64, so a
+ * hard link / local copy is only ever made from byte-identical content. */
+
+typedef struct BasisMatch {
+  bool hit;
+  BasisDestType type;
+  char* basis_path; /* owned absolute path of the matched basis file */
+  struct stat st;   /* fstat() of the matched basis file */
+  Data* content;    /* owned basis bytes (or empty Data), NULL when not loaded */
+} BasisMatch;
+
+static void basis_match_free(BasisMatch* match) {
+  if (!match)
+    return;
+  free(match->basis_path);
+  match->basis_path = NULL;
+  data_destroy(match->content);
+  match->content = NULL;
+  match->hit = false;
+  match->type = BASIS_DEST_NONE;
+}
+
+/* Open `path` (via the secure, root-confined primitives) and require it to be
+   a regular file of exactly `expected_size` bytes.  Returns an open read-only
+   descriptor and its fstat on success. */
+static bool basis_open_regular(const char* path, unsigned long long expected_size, int* out_fd,
+                               struct stat* out_st) {
+  char* leaf = NULL;
+  int parent_fd = file_open_secure_parent(path, &leaf, false);
+  if (parent_fd < 0)
+    return false;
+  int fd = openat(parent_fd, leaf, O_RDONLY | O_CLOEXEC | O_NOFOLLOW);
+  free(leaf);
+  close(parent_fd);
+  if (fd < 0)
+    return false;
+  struct stat st;
+  if (fstat(fd, &st) != 0 || !S_ISREG(st.st_mode) ||
+      (unsigned long long)st.st_size != expected_size) {
+    close(fd);
+    return false;
+  }
+  *out_fd = fd;
+  *out_st = st;
+  return true;
+}
+
+/* Read the whole remaining content of an open descriptor.  A zero-length file
+   yields an empty Data (data pointer NULL). */
+static Data* basis_read_content(int fd, unsigned long long size) {
+  if (size == 0)
+    return data_create_reserve(0);
+  if (size > MAX_RECEIVE_WHOLE_FILE_SIZE || size > SIZE_MAX)
+    return NULL;
+  void* buf = protocol_alloc((size_t)size);
+  if (!buf)
+    return NULL;
+  size_t got = 0;
+  while (got < (size_t)size) {
+    ssize_t n = read(fd, (char*)buf + got, (size_t)size - got);
+    if (n <= 0) {
+      free(buf);
+      return NULL;
+    }
+    got += (size_t)n;
+  }
+  return data_create(buf, (size_t)size);
+}
+
+/* --ignore-times forces every file to be updated, so no basis hit is ever
+   declared (matching rsync, where -I prevents link-dest from linking). */
+static bool basis_quick_matches(const Config* config, const struct stat* st, time_t check_mtime,
+                                long check_mtime_nsec) {
+  if (config->size_only)
+    return true;
+  long mtime_nsec = 0;
+#ifdef __linux__
+  mtime_nsec = st->st_mtim.tv_nsec;
+#endif
+  return metadata_mtime_matches(st->st_mtime, mtime_nsec, check_mtime, check_mtime_nsec,
+                                config->modify_window);
+}
+
+/* Search the basis-dir list in command-line order and return the first exact
+   match.  When load_content is true the matched bytes are kept in out->content
+   so the caller can materialize the file without re-reading it. */
+static bool basis_match_find(const Config* config, const char* check_path,
+                             unsigned long long check_size, time_t check_mtime,
+                             long check_mtime_nsec, uint64_t check_checksum, bool load_content,
+                             BasisMatch* out) {
+  memset(out, 0, sizeof(*out));
+  if (!config || !config_has_basis(config) || config->ignore_times)
+    return false;
+  for (int i = 0; i < config->basis_count; i++) {
+    const BasisDest* entry = &config->basis_dirs[i];
+    char* basis_dir = path_cat(config->receive_root_directory, entry->path);
+    if (!basis_dir)
+      continue;
+    char* candidate = path_cat(basis_dir, check_path);
+    free(basis_dir);
+    if (!candidate)
+      continue;
+
+    int fd;
+    struct stat st;
+    if (basis_open_regular(candidate, check_size, &fd, &st)) {
+      if (basis_quick_matches(config, &st, check_mtime, check_mtime_nsec)) {
+        Data* content = basis_read_content(fd, check_size);
+        if (content) {
+          uint64_t basis_hash = check_size == 0 ? delta_xxhash64("", 0)
+                                : content->data ? delta_xxhash64(content->data, content->size)
+                                                : 0;
+          if (basis_hash == check_checksum) {
+            out->hit = true;
+            out->type = entry->type;
+            out->basis_path = candidate;
+            candidate = NULL; /* ownership transferred to out */
+            out->st = st;
+            out->content = load_content ? content : NULL;
+            if (!load_content)
+              data_destroy(content);
+            close(fd);
+            return true;
+          }
+        }
+        data_destroy(content);
+      }
+      close(fd);
+    }
+    free(candidate);
+  }
+  return false;
+}
+
 File* receive_incremental_check(int fd, const Config* config, bool* skipped) {
   if (!config || !skipped) {
     send_status(fd, STATUS_ERROR);
@@ -531,7 +686,8 @@ File* receive_incremental_check(int fd, const Config* config, bool* skipped) {
     send_status(fd, STATUS_ERROR);
     return NULL;
   }
-  if (config->checksum && !receive_n_data(fd, &check_checksum, sizeof(check_checksum))) {
+  if ((config->checksum || config_has_basis(config)) &&
+      !receive_n_data(fd, &check_checksum, sizeof(check_checksum))) {
     free(check_path);
     return NULL;
   }
@@ -642,6 +798,76 @@ File* receive_incremental_check(int fd, const Config* config, bool* skipped) {
     return NULL;
   }
 
+  /* ---- Alternate basis directories ---- */
+  if (config_has_basis(config)) {
+    BasisMatch basis;
+    basis_match_find(config, check_path, check_size, (time_t)check_mtime, (long)check_mtime_nsec,
+                     check_checksum, true, &basis);
+    if (basis.hit) {
+      if (basis.type == BASIS_DEST_COMPARE) {
+        /* compare-dest never copies: an exact match only suppresses the data
+           for a file the destination does not already hold (sparse backup).
+           When the destination holds a DIFFERENT version FastSync falls back to
+           a normal transfer rather than deleting the stale entry the way rsync
+           does (see RSYNC_COMPAT.md). */
+        basis_match_free(&basis);
+        if (!has_old_file) {
+          if (!send_status(fd, STATUS_OK)) {
+            close(old_fd);
+            free(full_path);
+            free(check_path);
+            return NULL;
+          }
+          free(old_data);
+          close(old_fd);
+          free(full_path);
+          free(check_path);
+          *skipped = true;
+          return NULL;
+        }
+      } else {
+        /* copy-dest / link-dest: materialize the unchanged file locally so the
+           sender can skip the data.  The store engine re-applies the normal
+           existing/ignore-existing/update/backup/delay-updates policy. */
+        File* materialized = file_create(check_path);
+        if (materialized && basis.content) {
+          materialized->data = basis.content;
+          basis.content = NULL;
+          materialized->metadata = file_metadata_create(&basis.st);
+          materialized->skip = true; /* receiver must not ack this as a data file */
+          if (basis.type == BASIS_DEST_LINK) {
+            materialized->basis_link = basis.basis_path;
+            basis.basis_path = NULL;
+          }
+          if (!materialized->metadata) {
+            file_destroy(materialized);
+            materialized = NULL;
+          }
+        } else {
+          file_destroy(materialized);
+          materialized = NULL;
+        }
+        if (materialized) {
+          if (!send_status(fd, STATUS_OK)) {
+            file_destroy(materialized);
+            close(old_fd);
+            free(full_path);
+            free(check_path);
+            return NULL;
+          }
+          free(old_data);
+          close(old_fd);
+          free(full_path);
+          free(check_path);
+          *skipped = false;
+          return materialized;
+        }
+        /* Materialization setup failed: fall through to the normal transfer. */
+      }
+    }
+    basis_match_free(&basis);
+  }
+
   if (try_delta && old_data != NULL) {
     bool delta_failed = false;
     File* delta_file =
@@ -843,10 +1069,29 @@ int receive_manifest(int fd, const Config* config, int* next_status) {
   /* With --delay-updates the staged (not yet published) files live directly
      under the receive root in the staging directory; the delete walker must
      not treat them as extras or it would remove every staged file before it
-     can be published. */
+     can be published.  Alternate basis directories (--compare-dest /
-  const char* skip_staging = config->delay_updates ? DELAY_UPDATES_STAGING_DIR : NULL;
+     --copy-dest / --link-dest) are also excluded: they are extra comparison
-  bool deletion_ok = delete_extras_limited(config->receive_root_directory, manifest,
+     snapshots the user pointed at, not destination content, and deleting them
-                                           MAX_SERVER_DELETE_COUNT, skip_staging);
+     would destroy the very files a --link-dest run just linked into place. */
+  int skip_count = (config->delay_updates ? 1 : 0) + config->basis_count;
+  const char** skip_prefixes = NULL;
+  bool deletion_ok = false;
+  if (skip_count > 0) {
+    skip_prefixes = calloc((size_t)skip_count, sizeof(char*));
+    if (!skip_prefixes) {
+      array_list_delete(manifest);
+      send_status(fd, STATUS_ERROR);
+      return -1;
+    }
+    int idx = 0;
+    if (config->delay_updates)
+      skip_prefixes[idx++] = DELAY_UPDATES_STAGING_DIR;
+    for (int i = 0; i < config->basis_count; i++)
+      skip_prefixes[idx++] = config->basis_dirs[i].path;
+  }
+  deletion_ok = delete_extras_limited(config->receive_root_directory, manifest,
+                                      MAX_SERVER_DELETE_COUNT, skip_prefixes, skip_count);
+  free(skip_prefixes);
   array_list_delete(manifest);
   if (!deletion_ok)
     send_status(fd, STATUS_ERROR);

src/shared/file_types.h

@@ -29,6 +29,12 @@ typedef struct {
   /* True when this entry is an explicit directory entry (--dirs mode): the
    * receiver creates the directory instead of writing a regular file. */
   bool is_dir;
+  /* Receiver-only, --link-dest: when set, install the destination entry as a
+   * hard link to this absolute (root-confined) path instead of writing
+   * `data`.  The matching code has already verified the link target's content
+   * equals the incoming file, and `data` is kept as the cross-filesystem
+   * fallback (a local copy) if the hard link cannot be created. */
+  char* basis_link;
 } File;
 
 /* The path that should be sent on the wire and used for the receiver-side

src/shared/multiprocessing.c

@@ -297,7 +297,7 @@ int write_thread(void* pipeline_context) {
     /* Record the per-file outcome so a --remove-source-files sender learns
        which sources were actually written versus skipped on the receiver.
        Explicit directory entries have no source and are never acknowledged. */
-    if (context->config->remove_source_files && !file->is_dir &&
+    if (context->config->remove_source_files && !file->is_dir && !file->skip &&
         !receiver_outcomes_append(&context->outcomes, (unsigned char)result)) {
       file_destroy(file);
       pipeline_context_receiver_note_bytes_released(context, file_bytes);