Merge branch 'mt/parallel-checkout-part-1'

Preparatory API changes for parallel checkout.

* mt/parallel-checkout-part-1:
  entry: add checkout_entry_ca() taking preloaded conv_attrs
  entry: move conv_attrs lookup up to checkout_entry()
  entry: extract update_ce_after_write() from write_entry()
  entry: make fstat_output() and read_blob_entry() public
  entry: extract a header file for entry.c functions
  convert: add classification for conv_attrs struct
  convert: add get_stream_filter_ca() variant
  convert: add [async_]convert_to_working_tree_ca() variants
  convert: make convert_attrs() and convert structs public

11 files changed, 277 insertions, 137 deletions

diff --git a/apply.c b/apply.c
index 6695a931e9..466f880d73 100644
--- a/apply.c
+++ b/apply.c
@@ -21,6 +21,7 @@
 #include "quote.h"
 #include "rerere.h"
 #include "apply.h"
+#include "entry.h"
 
 struct gitdiff_data {
 	struct strbuf *root;
diff --git a/builtin/checkout-index.c b/builtin/checkout-index.c
index 023e49e271..c0bf4ac1b2 100644
--- a/builtin/checkout-index.c
+++ b/builtin/checkout-index.c
@@ -11,6 +11,7 @@
 #include "quote.h"
 #include "cache-tree.h"
 #include "parse-options.h"
+#include "entry.h"
 
 #define CHECKOUT_ALL 4
 static int nul_term_line;
diff --git a/builtin/checkout.c b/builtin/checkout.c
index 0e66390520..4c696ef480 100644
--- a/builtin/checkout.c
+++ b/builtin/checkout.c
@@ -26,6 +26,7 @@
 #include "unpack-trees.h"
 #include "wt-status.h"
 #include "xdiff-interface.h"
+#include "entry.h"
 
 static const char * const checkout_usage[] = {
 	N_("git checkout [<options>] <branch>"),
diff --git a/builtin/difftool.c b/builtin/difftool.c
index 6e18e623fd..ef25729d49 100644
--- a/builtin/difftool.c
+++ b/builtin/difftool.c
@@ -23,6 +23,7 @@
 #include "lockfile.h"
 #include "object-store.h"
 #include "dir.h"
+#include "entry.h"
 
 static int trust_exit_code;
 
diff --git a/builtin/stash.c b/builtin/stash.c
index 3477e940e3..c56fed3354 100644
--- a/builtin/stash.c
+++ b/builtin/stash.c
@@ -10,11 +10,13 @@
 #include "strvec.h"
 #include "run-command.h"
 #include "dir.h"
+#include "entry.h"
 #include "rerere.h"
 #include "revision.h"
 #include "log-tree.h"
 #include "diffcore.h"
 #include "exec-cmd.h"
+#include "entry.h"
 
 #define INCLUDE_ALL_FILES 2
 
diff --git a/cache.h b/cache.h
index 57f2285bba..148d9ab5f1 100644
--- a/cache.h
+++ b/cache.h
@@ -1621,30 +1621,6 @@ const char *show_ident_date(const struct ident_split *id,
  */
 int ident_cmp(const struct ident_split *, const struct ident_split *);
 
-struct checkout {
-	struct index_state *istate;
-	const char *base_dir;
-	int base_dir_len;
-	struct delayed_checkout *delayed_checkout;
-	struct checkout_metadata meta;
-	unsigned force:1,
-		 quiet:1,
-		 not_new:1,
-		 clone:1,
-		 refresh_cache:1;
-};
-#define CHECKOUT_INIT { NULL, "" }
-
-#define TEMPORARY_FILENAME_LENGTH 25
-int checkout_entry(struct cache_entry *ce, const struct checkout *state, char *topath, int *nr_checkouts);
-void enable_delayed_checkout(struct checkout *state);
-int finish_delayed_checkout(struct checkout *state, int *nr_checkouts);
-/*
- * Unlink the last component and schedule the leading directories for
- * removal, such that empty directories get removed.
- */
-void unlink_entry(const struct cache_entry *ce);
-
 struct cache_def {
 	struct strbuf path;
 	int flags;
diff --git a/convert.c b/convert.c
index 2d3a5a713c..3298e4acff 100644
--- a/convert.c
+++ b/convert.c
@@ -24,17 +24,6 @@
 #define CONVERT_STAT_BITS_TXT_CRLF  0x2
 #define CONVERT_STAT_BITS_BIN       0x4
 
-enum crlf_action {
-	CRLF_UNDEFINED,
-	CRLF_BINARY,
-	CRLF_TEXT,
-	CRLF_TEXT_INPUT,
-	CRLF_TEXT_CRLF,
-	CRLF_AUTO,
-	CRLF_AUTO_INPUT,
-	CRLF_AUTO_CRLF
-};
-
 struct text_stat {
 	/* NUL, CR, LF and CRLF counts */
 	unsigned nul, lonecr, lonelf, crlf;
@@ -172,7 +161,7 @@ static int text_eol_is_crlf(void)
 	return 0;
 }
 
-static enum eol output_eol(enum crlf_action crlf_action)
+static enum eol output_eol(enum convert_crlf_action crlf_action)
 {
 	switch (crlf_action) {
 	case CRLF_BINARY:
@@ -246,7 +235,7 @@ static int has_crlf_in_index(const struct index_state *istate, const char *path)
 }
 
 static int will_convert_lf_to_crlf(struct text_stat *stats,
-				   enum crlf_action crlf_action)
+				   enum convert_crlf_action crlf_action)
 {
 	if (output_eol(crlf_action) != EOL_CRLF)
 		return 0;
@@ -499,7 +488,7 @@ static int encode_to_worktree(const char *path, const char *src, size_t src_len,
 static int crlf_to_git(const struct index_state *istate,
 		       const char *path, const char *src, size_t len,
 		       struct strbuf *buf,
-		       enum crlf_action crlf_action, int conv_flags)
+		       enum convert_crlf_action crlf_action, int conv_flags)
 {
 	struct text_stat stats;
 	char *dst;
@@ -585,8 +574,8 @@ static int crlf_to_git(const struct index_state *istate,
 	return 1;
 }
 
-static int crlf_to_worktree(const char *src, size_t len,
-			    struct strbuf *buf, enum crlf_action crlf_action)
+static int crlf_to_worktree(const char *src, size_t len, struct strbuf *buf,
+			    enum convert_crlf_action crlf_action)
 {
 	char *to_free = NULL;
 	struct text_stat stats;
@@ -1247,7 +1236,7 @@ static const char *git_path_check_encoding(struct attr_check_item *check)
 	return value;
 }
 
-static enum crlf_action git_path_check_crlf(struct attr_check_item *check)
+static enum convert_crlf_action git_path_check_crlf(struct attr_check_item *check)
 {
 	const char *value = check->value;
 
@@ -1297,18 +1286,10 @@ static int git_path_check_ident(struct attr_check_item *check)
 	return !!ATTR_TRUE(value);
 }
 
-struct conv_attrs {
-	struct convert_driver *drv;
-	enum crlf_action attr_action; /* What attr says */
-	enum crlf_action crlf_action; /* When no attr is set, use core.autocrlf */
-	int ident;
-	const char *working_tree_encoding; /* Supported encoding or default encoding if NULL */
-};
-
 static struct attr_check *check;
 
-static void convert_attrs(const struct index_state *istate,
-			  struct conv_attrs *ca, const char *path)
+void convert_attrs(const struct index_state *istate,
+		   struct conv_attrs *ca, const char *path)
 {
 	struct attr_check_item *ccheck = NULL;
 
@@ -1465,19 +1446,16 @@ void convert_to_git_filter_fd(const struct index_state *istate,
 	ident_to_git(dst->buf, dst->len, dst, ca.ident);
 }
 
-static int convert_to_working_tree_internal(const struct index_state *istate,
-					    const char *path, const char *src,
-					    size_t len, struct strbuf *dst,
-					    int normalizing,
-					    const struct checkout_metadata *meta,
-					    struct delayed_checkout *dco)
+static int convert_to_working_tree_ca_internal(const struct conv_attrs *ca,
+					       const char *path, const char *src,
+					       size_t len, struct strbuf *dst,
+					       int normalizing,
+					       const struct checkout_metadata *meta,
+					       struct delayed_checkout *dco)
 {
 	int ret = 0, ret_filter = 0;
-	struct conv_attrs ca;
-
-	convert_attrs(istate, &ca, path);
 
-	ret |= ident_to_worktree(src, len, dst, ca.ident);
+	ret |= ident_to_worktree(src, len, dst, ca->ident);
 	if (ret) {
 		src = dst->buf;
 		len = dst->len;
@@ -1487,49 +1465,56 @@ static int convert_to_working_tree_internal(const struct index_state *istate,
 	 * is a smudge or process filter (even if the process filter doesn't
 	 * support smudge).  The filters might expect CRLFs.
 	 */
-	if ((ca.drv && (ca.drv->smudge || ca.drv->process)) || !normalizing) {
-		ret |= crlf_to_worktree(src, len, dst, ca.crlf_action);
+	if ((ca->drv && (ca->drv->smudge || ca->drv->process)) || !normalizing) {
+		ret |= crlf_to_worktree(src, len, dst, ca->crlf_action);
 		if (ret) {
 			src = dst->buf;
 			len = dst->len;
 		}
 	}
 
-	ret |= encode_to_worktree(path, src, len, dst, ca.working_tree_encoding);
+	ret |= encode_to_worktree(path, src, len, dst, ca->working_tree_encoding);
 	if (ret) {
 		src = dst->buf;
 		len = dst->len;
 	}
 
 	ret_filter = apply_filter(
-		path, src, len, -1, dst, ca.drv, CAP_SMUDGE, meta, dco);
-	if (!ret_filter && ca.drv && ca.drv->required)
-		die(_("%s: smudge filter %s failed"), path, ca.drv->name);
+		path, src, len, -1, dst, ca->drv, CAP_SMUDGE, meta, dco);
+	if (!ret_filter && ca->drv && ca->drv->required)
+		die(_("%s: smudge filter %s failed"), path, ca->drv->name);
 
 	return ret | ret_filter;
 }
 
-int async_convert_to_working_tree(const struct index_state *istate,
-				  const char *path, const char *src,
-				  size_t len, struct strbuf *dst,
-				  const struct checkout_metadata *meta,
-				  void *dco)
+int async_convert_to_working_tree_ca(const struct conv_attrs *ca,
+				     const char *path, const char *src,
+				     size_t len, struct strbuf *dst,
+				     const struct checkout_metadata *meta,
+				     void *dco)
 {
-	return convert_to_working_tree_internal(istate, path, src, len, dst, 0, meta, dco);
+	return convert_to_working_tree_ca_internal(ca, path, src, len, dst, 0,
+						   meta, dco);
 }
 
-int convert_to_working_tree(const struct index_state *istate,
-			    const char *path, const char *src,
-			    size_t len, struct strbuf *dst,
-			    const struct checkout_metadata *meta)
+int convert_to_working_tree_ca(const struct conv_attrs *ca,
+			       const char *path, const char *src,
+			       size_t len, struct strbuf *dst,
+			       const struct checkout_metadata *meta)
 {
-	return convert_to_working_tree_internal(istate, path, src, len, dst, 0, meta, NULL);
+	return convert_to_working_tree_ca_internal(ca, path, src, len, dst, 0,
+						   meta, NULL);
 }
 
 int renormalize_buffer(const struct index_state *istate, const char *path,
 		       const char *src, size_t len, struct strbuf *dst)
 {
-	int ret = convert_to_working_tree_internal(istate, path, src, len, dst, 1, NULL, NULL);
+	struct conv_attrs ca;
+	int ret;
+
+	convert_attrs(istate, &ca, path);
+	ret = convert_to_working_tree_ca_internal(&ca, path, src, len, dst, 1,
+						  NULL, NULL);
 	if (ret) {
 		src = dst->buf;
 		len = dst->len;
@@ -1956,34 +1941,25 @@ static struct stream_filter *ident_filter(const struct object_id *oid)
 }
 
 /*
- * Return an appropriately constructed filter for the path, or NULL if
+ * Return an appropriately constructed filter for the given ca, or NULL if
  * the contents cannot be filtered without reading the whole thing
  * in-core.
  *
  * Note that you would be crazy to set CRLF, smudge/clean or ident to a
  * large binary blob you would want us not to slurp into the memory!
  */
-struct stream_filter *get_stream_filter(const struct index_state *istate,
-					const char *path,
-					const struct object_id *oid)
+struct stream_filter *get_stream_filter_ca(const struct conv_attrs *ca,
+					   const struct object_id *oid)
 {
-	struct conv_attrs ca;
 	struct stream_filter *filter = NULL;
 
-	convert_attrs(istate, &ca, path);
-	if (ca.drv && (ca.drv->process || ca.drv->smudge || ca.drv->clean))
-		return NULL;
-
-	if (ca.working_tree_encoding)
+	if (classify_conv_attrs(ca) != CA_CLASS_STREAMABLE)
 		return NULL;
 
-	if (ca.crlf_action == CRLF_AUTO || ca.crlf_action == CRLF_AUTO_CRLF)
-		return NULL;
-
-	if (ca.ident)
+	if (ca->ident)
 		filter = ident_filter(oid);
 
-	if (output_eol(ca.crlf_action) == EOL_CRLF)
+	if (output_eol(ca->crlf_action) == EOL_CRLF)
 		filter = cascade_filter(filter, lf_to_crlf_filter());
 	else
 		filter = cascade_filter(filter, &null_filter_singleton);
@@ -1991,6 +1967,15 @@ struct stream_filter *get_stream_filter(const struct index_state *istate,
 	return filter;
 }
 
+struct stream_filter *get_stream_filter(const struct index_state *istate,
+					const char *path,
+					const struct object_id *oid)
+{
+	struct conv_attrs ca;
+	convert_attrs(istate, &ca, path);
+	return get_stream_filter_ca(&ca, oid);
+}
+
 void free_stream_filter(struct stream_filter *filter)
 {
 	filter->vtbl->free(filter);
@@ -2024,3 +2009,21 @@ void clone_checkout_metadata(struct checkout_metadata *dst,
 	if (blob)
 		oidcpy(&dst->blob, blob);
 }
+
+enum conv_attrs_classification classify_conv_attrs(const struct conv_attrs *ca)
+{
+	if (ca->drv) {
+		if (ca->drv->process)
+			return CA_CLASS_INCORE_PROCESS;
+		if (ca->drv->smudge || ca->drv->clean)
+			return CA_CLASS_INCORE_FILTER;
+	}
+
+	if (ca->working_tree_encoding)
+		return CA_CLASS_INCORE;
+
+	if (ca->crlf_action == CRLF_AUTO || ca->crlf_action == CRLF_AUTO_CRLF)
+		return CA_CLASS_INCORE;
+
+	return CA_CLASS_STREAMABLE;
+}
diff --git a/convert.h b/convert.h
index e29d1026a6..43e567a59b 100644
--- a/convert.h
+++ b/convert.h
@@ -63,6 +63,30 @@ struct checkout_metadata {
 	struct object_id blob;
 };
 
+enum convert_crlf_action {
+	CRLF_UNDEFINED,
+	CRLF_BINARY,
+	CRLF_TEXT,
+	CRLF_TEXT_INPUT,
+	CRLF_TEXT_CRLF,
+	CRLF_AUTO,
+	CRLF_AUTO_INPUT,
+	CRLF_AUTO_CRLF
+};
+
+struct convert_driver;
+
+struct conv_attrs {
+	struct convert_driver *drv;
+	enum convert_crlf_action attr_action; /* What attr says */
+	enum convert_crlf_action crlf_action; /* When no attr is set, use core.autocrlf */
+	int ident;
+	const char *working_tree_encoding; /* Supported encoding or default encoding if NULL */
+};
+
+void convert_attrs(const struct index_state *istate,
+		   struct conv_attrs *ca, const char *path);
+
 extern enum eol core_eol;
 extern char *check_roundtrip_encoding;
 const char *get_cached_convert_stats_ascii(const struct index_state *istate,
@@ -75,15 +99,34 @@ const char *get_convert_attr_ascii(const struct index_state *istate,
 int convert_to_git(const struct index_state *istate,
 		   const char *path, const char *src, size_t len,
 		   struct strbuf *dst, int conv_flags);
-int convert_to_working_tree(const struct index_state *istate,
-			    const char *path, const char *src,
-			    size_t len, struct strbuf *dst,
-			    const struct checkout_metadata *meta);
-int async_convert_to_working_tree(const struct index_state *istate,
-				  const char *path, const char *src,
-				  size_t len, struct strbuf *dst,
-				  const struct checkout_metadata *meta,
-				  void *dco);
+int convert_to_working_tree_ca(const struct conv_attrs *ca,
+			       const char *path, const char *src,
+			       size_t len, struct strbuf *dst,
+			       const struct checkout_metadata *meta);
+int async_convert_to_working_tree_ca(const struct conv_attrs *ca,
+				     const char *path, const char *src,
+				     size_t len, struct strbuf *dst,
+				     const struct checkout_metadata *meta,
+				     void *dco);
+static inline int convert_to_working_tree(const struct index_state *istate,
+					  const char *path, const char *src,
+					  size_t len, struct strbuf *dst,
+					  const struct checkout_metadata *meta)
+{
+	struct conv_attrs ca;
+	convert_attrs(istate, &ca, path);
+	return convert_to_working_tree_ca(&ca, path, src, len, dst, meta);
+}
+static inline int async_convert_to_working_tree(const struct index_state *istate,
+						const char *path, const char *src,
+						size_t len, struct strbuf *dst,
+						const struct checkout_metadata *meta,
+						void *dco)
+{
+	struct conv_attrs ca;
+	convert_attrs(istate, &ca, path);
+	return async_convert_to_working_tree_ca(&ca, path, src, len, dst, meta, dco);
+}
 int async_query_available_blobs(const char *cmd,
 				struct string_list *available_paths);
 int renormalize_buffer(const struct index_state *istate,
@@ -136,6 +179,8 @@ struct stream_filter; /* opaque */
 struct stream_filter *get_stream_filter(const struct index_state *istate,
 					const char *path,
 					const struct object_id *);
+struct stream_filter *get_stream_filter_ca(const struct conv_attrs *ca,
+					   const struct object_id *oid);
 void free_stream_filter(struct stream_filter *);
 int is_null_stream_filter(struct stream_filter *);
 
@@ -155,4 +200,37 @@ int stream_filter(struct stream_filter *,
 		  const char *input, size_t *isize_p,
 		  char *output, size_t *osize_p);
 
+enum conv_attrs_classification {
+	/*
+	 * The blob must be loaded into a buffer before it can be
+	 * smudged. All smudging is done in-proc.
+	 */
+	CA_CLASS_INCORE,
+
+	/*
+	 * The blob must be loaded into a buffer, but uses a
+	 * single-file driver filter, such as rot13.
+	 */
+	CA_CLASS_INCORE_FILTER,
+
+	/*
+	 * The blob must be loaded into a buffer, but uses a
+	 * long-running driver process, such as LFS. This might or
+	 * might not use delayed operations. (The important thing is
+	 * that there is a single subordinate long-running process
+	 * handling all associated blobs and in case of delayed
+	 * operations, may hold per-blob state.)
+	 */
+	CA_CLASS_INCORE_PROCESS,
+
+	/*
+	 * The blob can be streamed and smudged without needing to
+	 * completely read it into a buffer.
+	 */
+	CA_CLASS_STREAMABLE,
+};
+
+enum conv_attrs_classification classify_conv_attrs(
+	const struct conv_attrs *ca);
+
 #endif /* CONVERT_H */
diff --git a/entry.c b/entry.c
index 33ce80ca91..2dc94ba5cc 100644
--- a/entry.c
+++ b/entry.c
@@ -6,6 +6,7 @@
 #include "submodule.h"
 #include "progress.h"
 #include "fsmonitor.h"
+#include "entry.h"
 
 static void create_directories(const char *path, int path_len,
 			       const struct checkout *state)
@@ -83,7 +84,7 @@ static int create_file(const char *path, unsigned int mode)
 	return open(path, O_WRONLY | O_CREAT | O_EXCL, mode);
 }
 
-static void *read_blob_entry(const struct cache_entry *ce, unsigned long *size)
+void *read_blob_entry(const struct cache_entry *ce, unsigned long *size)
 {
 	enum object_type type;
 	void *blob_data = read_object_file(&ce->oid, &type, size);
@@ -108,7 +109,7 @@ static int open_output_fd(char *path, const struct cache_entry *ce, int to_tempf
 	}
 }
 
-static int fstat_output(int fd, const struct checkout *state, struct stat *st)
+int fstat_checkout_output(int fd, const struct checkout *state, struct stat *st)
 {
 	/* use fstat() only when path == ce->name */
 	if (fstat_is_reliable() &&
@@ -131,7 +132,7 @@ static int streaming_write_entry(const struct cache_entry *ce, char *path,
 		return -1;
 
 	result |= stream_blob_to_fd(fd, &ce->oid, filter, 1);
-	*fstat_done = fstat_output(fd, state, statbuf);
+	*fstat_done = fstat_checkout_output(fd, state, statbuf);
 	result |= close(fd);
 
 	if (result)
@@ -250,8 +251,21 @@ int finish_delayed_checkout(struct checkout *state, int *nr_checkouts)
 	return errs;
 }
 
-static int write_entry(struct cache_entry *ce,
-		       char *path, const struct checkout *state, int to_tempfile)
+void update_ce_after_write(const struct checkout *state, struct cache_entry *ce,
+			   struct stat *st)
+{
+	if (state->refresh_cache) {
+		assert(state->istate);
+		fill_stat_cache_info(state->istate, ce, st);
+		ce->ce_flags |= CE_UPDATE_IN_BASE;
+		mark_fsmonitor_invalid(state->istate, ce);
+		state->istate->cache_changed |= CE_ENTRY_CHANGED;
+	}
+}
+
+/* Note: ca is used (and required) iff the entry refers to a regular file. */
+static int write_entry(struct cache_entry *ce, char *path, struct conv_attrs *ca,
+		       const struct checkout *state, int to_tempfile)
 {
 	unsigned int ce_mode_s_ifmt = ce->ce_mode & S_IFMT;
 	struct delayed_checkout *dco = state->delayed_checkout;
@@ -268,8 +282,7 @@ static int write_entry(struct cache_entry *ce,
 	clone_checkout_metadata(&meta, &state->meta, &ce->oid);
 
 	if (ce_mode_s_ifmt == S_IFREG) {
-		struct stream_filter *filter = get_stream_filter(state->istate, ce->name,
-								 &ce->oid);
+		struct stream_filter *filter = get_stream_filter_ca(ca, &ce->oid);
 		if (filter &&
 		    !streaming_write_entry(ce, path, filter,
 					   state, to_tempfile,
@@ -316,14 +329,17 @@ static int write_entry(struct cache_entry *ce,
 		 * Convert from git internal format to working tree format
 		 */
 		if (dco && dco->state != CE_NO_DELAY) {
-			ret = async_convert_to_working_tree(state->istate, ce->name, new_blob,
-							    size, &buf, &meta, dco);
+			ret = async_convert_to_working_tree_ca(ca, ce->name,
+							       new_blob, size,
+							       &buf, &meta, dco);
 			if (ret && string_list_has_string(&dco->paths, ce->name)) {
 				free(new_blob);
 				goto delayed;
 			}
-		} else
-			ret = convert_to_working_tree(state->istate, ce->name, new_blob, size, &buf, &meta);
+		} else {
+			ret = convert_to_working_tree_ca(ca, ce->name, new_blob,
+							 size, &buf, &meta);
+		}
 
 		if (ret) {
 			free(new_blob);
@@ -345,7 +361,7 @@ static int write_entry(struct cache_entry *ce,
 
 		wrote = write_in_full(fd, new_blob, size);
 		if (!to_tempfile)
-			fstat_done = fstat_output(fd, state, &st);
+			fstat_done = fstat_checkout_output(fd, state, &st);
 		close(fd);
 		free(new_blob);
 		if (wrote < 0)
@@ -370,15 +386,10 @@ static int write_entry(struct cache_entry *ce,
 
 finish:
 	if (state->refresh_cache) {
-		assert(state->istate);
-		if (!fstat_done)
-			if (lstat(ce->name, &st) < 0)
-				return error_errno("unable to stat just-written file %s",
-						   ce->name);
-		fill_stat_cache_info(state->istate, ce, &st);
-		ce->ce_flags |= CE_UPDATE_IN_BASE;
-		mark_fsmonitor_invalid(state->istate, ce);
-		state->istate->cache_changed |= CE_ENTRY_CHANGED;
+		if (!fstat_done && lstat(ce->name, &st) < 0)
+			return error_errno("unable to stat just-written file %s",
+					   ce->name);
+		update_ce_after_write(state, ce , &st);
 	}
 delayed:
 	return 0;
@@ -429,19 +440,13 @@ static void mark_colliding_entries(const struct checkout *state,
 	}
 }
 
-/*
- * Write the contents from ce out to the working tree.
- *
- * When topath[] is not NULL, instead of writing to the working tree
- * file named by ce, a temporary file is created by this function and
- * its name is returned in topath[], which must be able to hold at
- * least TEMPORARY_FILENAME_LENGTH bytes long.
- */
-int checkout_entry(struct cache_entry *ce, const struct checkout *state,
-		   char *topath, int *nr_checkouts)
+int checkout_entry_ca(struct cache_entry *ce, struct conv_attrs *ca,
+		      const struct checkout *state, char *topath,
+		      int *nr_checkouts)
 {
 	static struct strbuf path = STRBUF_INIT;
 	struct stat st;
+	struct conv_attrs ca_buf;
 
 	if (ce->ce_flags & CE_WT_REMOVE) {
 		if (topath)
@@ -454,8 +459,13 @@ int checkout_entry(struct cache_entry *ce, const struct checkout *state,
 		return 0;
 	}
 
-	if (topath)
-		return write_entry(ce, topath, state, 1);
+	if (topath) {
+		if (S_ISREG(ce->ce_mode) && !ca) {
+			convert_attrs(state->istate, &ca_buf, ce->name);
+			ca = &ca_buf;
+		}
+		return write_entry(ce, topath, ca, state, 1);
+	}
 
 	strbuf_reset(&path);
 	strbuf_add(&path, state->base_dir, state->base_dir_len);
@@ -517,9 +527,16 @@ int checkout_entry(struct cache_entry *ce, const struct checkout *state,
 		return 0;
 
 	create_directories(path.buf, path.len, state);
+
 	if (nr_checkouts)
 		(*nr_checkouts)++;
-	return write_entry(ce, path.buf, state, 0);
+
+	if (S_ISREG(ce->ce_mode) && !ca) {
+		convert_attrs(state->istate, &ca_buf, ce->name);
+		ca = &ca_buf;
+	}
+
+	return write_entry(ce, path.buf, ca, state, 0);
 }
 
 void unlink_entry(const struct cache_entry *ce)
diff --git a/entry.h b/entry.h
new file mode 100644
index 0000000000..b8c0e170dc
--- /dev/null
+++ b/entry.h
@@ -0,0 +1,59 @@
+#ifndef ENTRY_H
+#define ENTRY_H
+
+#include "cache.h"
+#include "convert.h"
+
+struct checkout {
+	struct index_state *istate;
+	const char *base_dir;
+	int base_dir_len;
+	struct delayed_checkout *delayed_checkout;
+	struct checkout_metadata meta;
+	unsigned force:1,
+		 quiet:1,
+		 not_new:1,
+		 clone:1,
+		 refresh_cache:1;
+};
+#define CHECKOUT_INIT { NULL, "" }
+
+#define TEMPORARY_FILENAME_LENGTH 25
+/*
+ * Write the contents from ce out to the working tree.
+ *
+ * When topath[] is not NULL, instead of writing to the working tree
+ * file named by ce, a temporary file is created by this function and
+ * its name is returned in topath[], which must be able to hold at
+ * least TEMPORARY_FILENAME_LENGTH bytes long.
+ *
+ * With checkout_entry_ca(), callers can optionally pass a preloaded
+ * conv_attrs struct (to avoid reloading it), when ce refers to a
+ * regular file. If ca is NULL, the attributes will be loaded
+ * internally when (and if) needed.
+ */
+int checkout_entry_ca(struct cache_entry *ce, struct conv_attrs *ca,
+		      const struct checkout *state, char *topath,
+		      int *nr_checkouts);
+static inline int checkout_entry(struct cache_entry *ce,
+				 const struct checkout *state, char *topath,
+				 int *nr_checkouts)
+{
+	return checkout_entry_ca(ce, NULL, state, topath, nr_checkouts);
+}
+
+void enable_delayed_checkout(struct checkout *state);
+int finish_delayed_checkout(struct checkout *state, int *nr_checkouts);
+
+/*
+ * Unlink the last component and schedule the leading directories for
+ * removal, such that empty directories get removed.
+ */
+void unlink_entry(const struct cache_entry *ce);
+
+void *read_blob_entry(const struct cache_entry *ce, unsigned long *size);
+int fstat_checkout_output(int fd, const struct checkout *state, struct stat *st);
+void update_ce_after_write(const struct checkout *state, struct cache_entry *ce,
+			   struct stat *st);
+
+#endif /* ENTRY_H */
diff --git a/unpack-trees.c b/unpack-trees.c
index 29029f34ed..8a1afbc1e4 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -16,6 +16,7 @@
 #include "fsmonitor.h"
 #include "object-store.h"
 #include "promisor-remote.h"
+#include "entry.h"
 
 /*
  * Error messages expected by scripts out of plumbing commands such as