RFC patch, 21 parts[RFC] Parallel checkout

convert.c, convert.h

diff --git a/convert.c b/convert.c
index 572449825c..9710d770dc 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;
@@ -1300,18 +1289,10 @@ 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;
 
diff --git a/convert.h b/convert.h
index e29d1026a6..aeb4a1be9a 100644
--- a/convert.h
+++ b/convert.h
@@ -37,6 +37,27 @@ enum eol {
 #endif
 };
 
+enum 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 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 */
+};
+
 enum ce_delay_state {
 	CE_NO_DELAY = 0,
 	CE_CAN_DELAY = 1,
@@ -102,6 +123,9 @@ void convert_to_git_filter_fd(const struct index_state *istate,
 int would_convert_to_git_filter_fd(const struct index_state *istate,
 				   const char *path);
 
+void convert_attrs(const struct index_state *istate,
+		   struct conv_attrs *ca, const char *path);
+
 /*
  * Initialize the checkout metadata with the given values.  Any argument may be
  * NULL if it is not applicable.  The treeish should be a commit if that is

convert.c, convert.h

diff --git a/convert.c b/convert.c
index 9710d770dc..757dc2585c 100644
--- a/convert.c
+++ b/convert.c
@@ -1450,7 +1450,7 @@ 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,
+static int convert_to_working_tree_internal(const struct conv_attrs *ca,
 					    const char *path, const char *src,
 					    size_t len, struct strbuf *dst,
 					    int normalizing,
@@ -1458,11 +1458,8 @@ static int convert_to_working_tree_internal(const struct index_state *istate,
 					    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;
@@ -1472,24 +1469,24 @@ 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;
 }
@@ -1500,7 +1497,9 @@ int async_convert_to_working_tree(const struct index_state *istate,
 				  const struct checkout_metadata *meta,
 				  void *dco)
 {
-	return convert_to_working_tree_internal(istate, path, src, len, dst, 0, meta, dco);
+	struct conv_attrs ca;
+	convert_attrs(istate, &ca, path);
+	return convert_to_working_tree_internal(&ca, path, src, len, dst, 0, meta, dco);
 }
 
 int convert_to_working_tree(const struct index_state *istate,
@@ -1508,13 +1507,36 @@ int convert_to_working_tree(const struct index_state *istate,
 			    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);
+	struct conv_attrs ca;
+	convert_attrs(istate, &ca, path);
+	return convert_to_working_tree_internal(&ca, path, src, len, dst, 0, meta, NULL);
+}
+
+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(ca, path, src, len, dst, 0, meta, 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)
+{
+	return convert_to_working_tree_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_internal(&ca, path, src, len, dst, 1, NULL, NULL);
 	if (ret) {
 		src = dst->buf;
 		len = dst->len;
diff --git a/convert.h b/convert.h
index aeb4a1be9a..46d537d1ae 100644
--- a/convert.h
+++ b/convert.h
@@ -100,11 +100,20 @@ 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);
 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);
 int async_query_available_blobs(const char *cmd,
 				struct string_list *available_paths);
 int renormalize_buffer(const struct index_state *istate,

convert.c, convert.h

diff --git a/convert.c b/convert.c
index 757dc2585c..8e995b39c3 100644
--- a/convert.c
+++ b/convert.c
@@ -1963,34 +1963,31 @@ 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))
+	if (ca->drv && (ca->drv->process || ca->drv->smudge || ca->drv->clean))
 		return NULL;
 
-	if (ca.working_tree_encoding)
+	if (ca->working_tree_encoding)
 		return NULL;
 
-	if (ca.crlf_action == CRLF_AUTO || ca.crlf_action == CRLF_AUTO_CRLF)
+	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);
@@ -1998,6 +1995,15 @@ 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);
diff --git a/convert.h b/convert.h
index 46d537d1ae..262c1a1d46 100644
--- a/convert.h
+++ b/convert.h
@@ -169,6 +169,8 @@ 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 *);
 

convert.c, convert.h

diff --git a/convert.c b/convert.c
index 8e995b39c3..c037bb99eb 100644
--- a/convert.c
+++ b/convert.c
@@ -1975,13 +1975,7 @@ struct stream_filter *get_stream_filter_ca(const struct conv_attrs *ca,
 {
 	struct stream_filter *filter = NULL;
 
-	if (ca->drv && (ca->drv->process || ca->drv->smudge || ca->drv->clean))
-		return NULL;
-
-	if (ca->working_tree_encoding)
-		return NULL;
-
-	if (ca->crlf_action == CRLF_AUTO || ca->crlf_action == CRLF_AUTO_CRLF)
+	if (classify_conv_attrs(ca) != CA_CLASS_STREAMABLE)
 		return NULL;
 
 	if (ca->ident)
@@ -2037,3 +2031,21 @@ 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 262c1a1d46..523ba9b140 100644
--- a/convert.h
+++ b/convert.h
@@ -190,4 +190,37 @@ 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 */

apply.c, builtin/checkout-index.c, builtin/checkout.c, builtin/difftool.c, cache.h, entry.c, entry.h, unpack-trees.c

diff --git a/apply.c b/apply.c
index 8bff604dbe..1443c307a4 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 a854fd16e7..0f1ff73129 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 2837195491..3e09b29cfe 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 7ac432b881..dfa22b67eb 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/cache.h b/cache.h
index 0290849c19..e6963cf8fe 100644
--- a/cache.h
+++ b/cache.h
@@ -1695,30 +1695,6 @@ 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/entry.c b/entry.c
index 449bd32dee..f46c06e831 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)
@@ -429,14 +430,6 @@ 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)
 {
diff --git a/entry.h b/entry.h
new file mode 100644
index 0000000000..2d69185448
--- /dev/null
+++ b/entry.h
@@ -0,0 +1,41 @@
+#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.
+ */
+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);
+
+#endif /* ENTRY_H */
diff --git a/unpack-trees.c b/unpack-trees.c
index 323280dd48..a511fadd89 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

entry.c, entry.h

diff --git a/entry.c b/entry.c
index f46c06e831..cc27564473 100644
--- a/entry.c
+++ b/entry.c
@@ -84,7 +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);
@@ -109,7 +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() &&
@@ -132,7 +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)
@@ -346,7 +346,7 @@ 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)
diff --git a/entry.h b/entry.h
index 2d69185448..f860e60846 100644
--- a/entry.h
+++ b/entry.h
@@ -37,5 +37,7 @@ int finish_delayed_checkout(struct checkout *state, int *nr_checkouts);
  * 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);
 
 #endif /* ENTRY_H */

entry.c, entry.h

diff --git a/entry.c b/entry.c
index cc27564473..837629a804 100644
--- a/entry.c
+++ b/entry.c
@@ -251,6 +251,19 @@ int finish_delayed_checkout(struct checkout *state, int *nr_checkouts)
 	return errs;
 }
 
+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;
+	}
+}
+
+
 static int write_entry(struct cache_entry *ce,
 		       char *path, const struct checkout *state, int to_tempfile)
 {
@@ -371,15 +384,10 @@ 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;
diff --git a/entry.h b/entry.h
index f860e60846..664aed1576 100644
--- a/entry.h
+++ b/entry.h
@@ -39,5 +39,7 @@ int finish_delayed_checkout(struct checkout *state, int *nr_checkouts);
 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/entry.c b/entry.c
index 837629a804..59d5335ff1 100644
--- a/entry.c
+++ b/entry.c
@@ -263,9 +263,9 @@ void update_ce_after_write(const struct checkout *state, struct cache_entry *ce,
 	}
 }
 
-
-static int write_entry(struct cache_entry *ce,
-		       char *path, const struct checkout *state, int to_tempfile)
+/* 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;
@@ -282,8 +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,
@@ -330,14 +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);
@@ -443,6 +445,7 @@ int checkout_entry(struct cache_entry *ce, const struct checkout *state,
 {
 	static struct strbuf path = STRBUF_INIT;
 	struct stat st;
+	struct conv_attrs ca;
 
 	if (ce->ce_flags & CE_WT_REMOVE) {
 		if (topath)
@@ -455,8 +458,13 @@ 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)) {
+			convert_attrs(state->istate, &ca, ce->name);
+			return write_entry(ce, topath, &ca, state, 1);
+		}
+		return write_entry(ce, topath, NULL, state, 1);
+	}
 
 	strbuf_reset(&path);
 	strbuf_add(&path, state->base_dir, state->base_dir_len);
@@ -520,9 +528,16 @@ 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)) {
+		convert_attrs(state->istate, &ca, ce->name);
+		return write_entry(ce, path.buf, &ca, state, 0);
+	}
+
+	return write_entry(ce, path.buf, NULL, state, 0);
 }
 
 void unlink_entry(const struct cache_entry *ce)

entry.c, entry.h

diff --git a/entry.c b/entry.c
index 59d5335ff1..f9835afba3 100644
--- a/entry.c
+++ b/entry.c
@@ -440,12 +440,13 @@ static void mark_colliding_entries(const struct checkout *state,
 	}
 }
 
-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;
+	struct conv_attrs ca_buf;
 
 	if (ce->ce_flags & CE_WT_REMOVE) {
 		if (topath)
@@ -459,11 +460,11 @@ int checkout_entry(struct cache_entry *ce, const struct checkout *state,
 	}
 
 	if (topath) {
-		if (S_ISREG(ce->ce_mode)) {
-			convert_attrs(state->istate, &ca, ce->name);
-			return write_entry(ce, topath, &ca, state, 1);
+		if (S_ISREG(ce->ce_mode) && !ca) {
+			convert_attrs(state->istate, &ca_buf, ce->name);
+			ca = &ca_buf;
 		}
-		return write_entry(ce, topath, NULL, state, 1);
+		return write_entry(ce, topath, ca, state, 1);
 	}
 
 	strbuf_reset(&path);
@@ -532,12 +533,12 @@ int checkout_entry(struct cache_entry *ce, const struct checkout *state,
 	if (nr_checkouts)
 		(*nr_checkouts)++;
 
-	if (S_ISREG(ce->ce_mode)) {
-		convert_attrs(state->istate, &ca, ce->name);
-		return write_entry(ce, path.buf, &ca, 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, NULL, state, 0);
+	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
index 664aed1576..2081fbbbab 100644
--- a/entry.h
+++ b/entry.h
@@ -27,9 +27,18 @@ struct checkout {
  * 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(struct cache_entry *ce, const struct checkout *state,
-		   char *topath, int *nr_checkouts);
+#define checkout_entry(ce, state, topath, nr_checkouts) \
+		checkout_entry_ca(ce, NULL, state, topath, nr_checkouts)
+int checkout_entry_ca(struct cache_entry *ce, struct conv_attrs *ca,
+		      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);
 /*

Makefile, entry.c, parallel-checkout.c, parallel-checkout.h, unpack-trees.c

diff --git a/Makefile b/Makefile
index 65f8cfb236..caab8e6401 100644
--- a/Makefile
+++ b/Makefile
@@ -933,6 +933,7 @@ LIB_OBJS += pack-revindex.o
 LIB_OBJS += pack-write.o
 LIB_OBJS += packfile.o
 LIB_OBJS += pager.o
+LIB_OBJS += parallel-checkout.o
 LIB_OBJS += parse-options-cb.o
 LIB_OBJS += parse-options.o
 LIB_OBJS += patch-delta.o
diff --git a/entry.c b/entry.c
index f9835afba3..47c2c20d5a 100644
--- a/entry.c
+++ b/entry.c
@@ -7,6 +7,7 @@
 #include "progress.h"
 #include "fsmonitor.h"
 #include "entry.h"
+#include "parallel-checkout.h"
 
 static void create_directories(const char *path, int path_len,
 			       const struct checkout *state)
@@ -538,6 +539,9 @@ int checkout_entry_ca(struct cache_entry *ce, struct conv_attrs *ca,
 		ca = &ca_buf;
 	}
 
+	if (!enqueue_checkout(ce, ca))
+		return 0;
+
 	return write_entry(ce, path.buf, ca, state, 0);
 }
 
diff --git a/parallel-checkout.c b/parallel-checkout.c
new file mode 100644
index 0000000000..e3b44eeb34
--- /dev/null
+++ b/parallel-checkout.c
@@ -0,0 +1,340 @@
+#include "cache.h"
+#include "entry.h"
+#include "parallel-checkout.h"
+#include "streaming.h"
+
+enum ci_status {
+	CI_PENDING = 0,
+	CI_SUCCESS,
+	CI_RETRY,
+	CI_FAILED,
+};
+
+struct checkout_item {
+	/* pointer to a istate->cache[] entry. Not owned by us. */
+	struct cache_entry *ce;
+	struct conv_attrs ca;
+	struct stat st;
+	enum ci_status status;
+};
+
+struct parallel_checkout {
+	struct checkout_item *items;
+	size_t nr, alloc;
+};
+
+static struct parallel_checkout *parallel_checkout = NULL;
+
+enum pc_status {
+	PC_UNINITIALIZED = 0,
+	PC_ACCEPTING_ENTRIES,
+	PC_RUNNING,
+	PC_HANDLING_RESULTS,
+};
+
+static enum pc_status pc_status = PC_UNINITIALIZED;
+
+void init_parallel_checkout(void)
+{
+	if (parallel_checkout)
+		BUG("parallel checkout already initialized");
+
+	parallel_checkout = xcalloc(1, sizeof(*parallel_checkout));
+	pc_status = PC_ACCEPTING_ENTRIES;
+}
+
+static void finish_parallel_checkout(void)
+{
+	if (!parallel_checkout)
+		BUG("cannot finish parallel checkout: not initialized yet");
+
+	free(parallel_checkout->items);
+	FREE_AND_NULL(parallel_checkout);
+	pc_status = PC_UNINITIALIZED;
+}
+
+static int is_eligible_for_parallel_checkout(const struct cache_entry *ce,
+					     const struct conv_attrs *ca)
+{
+	enum conv_attrs_classification c;
+
+	if (!S_ISREG(ce->ce_mode))
+		return 0;
+
+	c = classify_conv_attrs(ca);
+	switch (c) {
+	case CA_CLASS_INCORE:
+		return 1;
+
+	case CA_CLASS_INCORE_FILTER:
+		/*
+		 * It would be safe to allow concurrent instances of
+		 * single-file smudge filters, like rot13, but we should not
+		 * assume that all filters are parallel-process safe. So we
+		 * don't allow this.
+		 */
+		return 0;
+
+	case CA_CLASS_INCORE_PROCESS:
+		/*
+		 * The parallel queue and the delayed queue are not compatible,
+		 * so they must be kept completely separated. And we can't tell
+		 * if a long-running process will delay its response without
+		 * actually asking it to perform the filtering. Therefore, this
+		 * type of filter is not allowed in parallel checkout.
+		 *
+		 * Furthermore, there should only be one instance of the
+		 * long-running process filter as we don't know how it is
+		 * managing its own concurrency. So, spreading the entries that
+		 * requisite such a filter among the parallel workers would
+		 * require a lot more inter-process communication. We would
+		 * probably have to designate a single process to interact with
+		 * the filter and send all the necessary data to it, for each
+		 * entry.
+		 */
+		return 0;
+
+	case CA_CLASS_STREAMABLE:
+		return 1;
+
+	default:
+		BUG("unsupported conv_attrs classification '%d'", c);
+	}
+}
+
+int enqueue_checkout(struct cache_entry *ce, struct conv_attrs *ca)
+{
+	struct checkout_item *ci;
+
+	if (!parallel_checkout || pc_status != PC_ACCEPTING_ENTRIES ||
+	    !is_eligible_for_parallel_checkout(ce, ca))
+		return -1;
+
+	ALLOC_GROW(parallel_checkout->items, parallel_checkout->nr + 1,
+		   parallel_checkout->alloc);
+
+	ci = &parallel_checkout->items[parallel_checkout->nr++];
+	ci->ce = ce;
+	memcpy(&ci->ca, ca, sizeof(ci->ca));
+
+	return 0;
+}
+
+static int handle_results(struct checkout *state)
+{
+	int ret = 0;
+	size_t i;
+
+	pc_status = PC_HANDLING_RESULTS;
+
+	for (i = 0; i < parallel_checkout->nr; ++i) {
+		struct checkout_item *ci = &parallel_checkout->items[i];
+		struct stat *st = &ci->st;
+
+		switch(ci->status) {
+		case CI_SUCCESS:
+			update_ce_after_write(state, ci->ce, st);
+			break;
+		case CI_RETRY:
+			/*
+			 * The fails for which we set CI_RETRY are the ones
+			 * that might have been caused by a path collision. So
+			 * we let checkout_entry_ca() retry writing, as it will
+			 * properly handle collisions and the creation of
+			 * leading dirs in the entry's path.
+			 */
+			ret |= checkout_entry_ca(ci->ce, &ci->ca, state, NULL, NULL);
+			break;
+		case CI_FAILED:
+			ret = -1;
+			break;
+		case CI_PENDING:
+			BUG("parallel checkout finished with pending entries");
+		default:
+			BUG("unknown checkout item status in parallel checkout");
+		}
+	}
+
+	return ret;
+}
+
+static int reset_fd(int fd, const char *path)
+{
+	if (lseek(fd, 0, SEEK_SET) != 0)
+		return error_errno("failed to rewind descriptor of %s", path);
+	if (ftruncate(fd, 0))
+		return error_errno("failed to truncate file %s", path);
+	return 0;
+}
+
+static int write_checkout_item_to_fd(int fd, struct checkout *state,
+				     struct checkout_item *ci, const char *path)
+{
+	int ret;
+	struct stream_filter *filter;
+	struct strbuf buf = STRBUF_INIT;
+	char *new_blob;
+	unsigned long size;
+	size_t newsize = 0;
+	ssize_t wrote;
+
+	/* Sanity check */
+	assert(is_eligible_for_parallel_checkout(ci->ce, &ci->ca));
+
+	filter = get_stream_filter_ca(&ci->ca, &ci->ce->oid);
+	if (filter) {
+		if (stream_blob_to_fd(fd, &ci->ce->oid, filter, 1)) {
+			/* On error, reset fd to try writing without streaming */
+			if (reset_fd(fd, path))
+				return -1;
+		} else {
+			return 0;
+		}
+	}
+
+	new_blob = read_blob_entry(ci->ce, &size);
+	if (!new_blob)
+		return error("unable to read sha1 file of %s (%s)", path,
+			     oid_to_hex(&ci->ce->oid));
+
+	/*
+	 * checkout metadata is used to give context for external process
+	 * filters. Files requiring such filters are not eligible for parallel
+	 * checkout, so pass NULL.
+	 */
+	ret = convert_to_working_tree_ca(&ci->ca, ci->ce->name, new_blob, size,
+					 &buf, NULL);
+
+	if (ret) {
+		free(new_blob);
+		new_blob = strbuf_detach(&buf, &newsize);
+		size = newsize;
+	}
+
+	wrote = write_in_full(fd, new_blob, size);
+	free(new_blob);
+	if (wrote < 0)
+		return error("unable to write file %s", path);
+
+	return 0;
+}
+
+static int close_and_clear(int *fd)
+{
+	int ret = 0;
+
+	if (*fd >= 0) {
+		ret = close(*fd);
+		*fd = -1;
+	}
+
+	return ret;
+}
+
+static int check_leading_dirs(const char *path, int len, int prefix_len)
+{
+	const char *slash = path + len;
+
+	while (slash > path && *slash != '/')
+		slash--;
+
+	return has_dirs_only_path(path, slash - path, prefix_len);
+}
+
+static void write_checkout_item(struct checkout *state, struct checkout_item *ci)
+{
+	unsigned int mode = (ci->ce->ce_mode & 0100) ? 0777 : 0666;
+	int fd = -1, fstat_done = 0;
+	struct strbuf path = STRBUF_INIT;
+
+	strbuf_add(&path, state->base_dir, state->base_dir_len);
+	strbuf_add(&path, ci->ce->name, ce_namelen(ci->ce));
+
+	/*
+	 * At this point, leading dirs should have already been created. But if
+	 * a symlink being checked out has collided with one of the dirs, due to
+	 * file system folding rules, it's possible that the dirs are no longer
+	 * present. So we have to check again, and report any path collisions.
+	 */
+	if (!check_leading_dirs(path.buf, path.len, state->base_dir_len)) {
+		ci->status = CI_RETRY;
+		goto out;
+	}
+
+	fd = open(path.buf, O_WRONLY | O_CREAT | O_EXCL, mode);
+
+	if (fd < 0) {
+		if (errno == EEXIST || errno == EISDIR) {
+			/*
+			 * Errors which probably represent a path collision.
+			 * Suppress the error message and mark the ci to be
+			 * retried later, sequentially. ENOTDIR and ENOENT are
+			 * also interesting, but check_leading_dirs() should
+			 * have already caught these cases.
+			 */
+			ci->status = CI_RETRY;
+		} else {
+			error_errno("failed to open file %s", path.buf);
+			ci->status = CI_FAILED;
+		}
+		goto out;
+	}
+
+	if (write_checkout_item_to_fd(fd, state, ci, path.buf)) {
+		/* Error was already reported. */
+		ci->status = CI_FAILED;
+		goto out;
+	}
+
+	fstat_done = fstat_checkout_output(fd, state, &ci->st);
+
+	if (close_and_clear(&fd)) {
+		error_errno("unable to close file %s", path.buf);
+		ci->status = CI_FAILED;
+		goto out;
+	}
+
+	if (state->refresh_cache && !fstat_done && lstat(path.buf, &ci->st) < 0) {
+		error_errno("unable to stat just-written file %s",  path.buf);
+		ci->status = CI_FAILED;
+		goto out;
+	}
+
+	ci->status = CI_SUCCESS;
+
+out:
+	/*
+	 * No need to check close() return. At this point, either fd is already
+	 * closed, or we are on an error path, that has already been reported.
+	 */
+	close_and_clear(&fd);
+	strbuf_release(&path);
+}
+
+static int run_checkout_sequentially(struct checkout *state)
+{
+	size_t i;
+
+	for (i = 0; i < parallel_checkout->nr; ++i) {
+		struct checkout_item *ci = &parallel_checkout->items[i];
+		write_checkout_item(state, ci);
+	}
+
+	return handle_results(state);
+}
+
+
+int run_parallel_checkout(struct checkout *state)
+{
+	int ret;
+
+	if (!parallel_checkout)
+		BUG("cannot run parallel checkout: not initialized yet");
+
+	pc_status = PC_RUNNING;
+
+	ret = run_checkout_sequentially(state);
+
+	finish_parallel_checkout();
+	return ret;
+}
diff --git a/parallel-checkout.h b/parallel-checkout.h
new file mode 100644
index 0000000000..8eef59ffcd
--- /dev/null
+++ b/parallel-checkout.h
@@ -0,0 +1,20 @@
+#ifndef PARALLEL_CHECKOUT_H
+#define PARALLEL_CHECKOUT_H
+
+struct cache_entry;
+struct checkout;
+struct conv_attrs;
+
+void init_parallel_checkout(void);
+
+/*
+ * Return -1 if parallel checkout is currently not enabled or if the entry is
+ * not eligible for parallel checkout. Otherwise, enqueue the entry for later
+ * write and return 0.
+ */
+int enqueue_checkout(struct cache_entry *ce, struct conv_attrs *ca);
+
+/* Write all the queued entries, returning 0 on success.*/
+int run_parallel_checkout(struct checkout *state);
+
+#endif /* PARALLEL_CHECKOUT_H */
diff --git a/unpack-trees.c b/unpack-trees.c
index a511fadd89..1b1da7485a 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -17,6 +17,7 @@
 #include "object-store.h"
 #include "promisor-remote.h"
 #include "entry.h"
+#include "parallel-checkout.h"
 
 /*
  * Error messages expected by scripts out of plumbing commands such as
@@ -438,7 +439,6 @@ static int check_updates(struct unpack_trees_options *o,
 	if (should_update_submodules())
 		load_gitmodules_file(index, &state);
 
-	enable_delayed_checkout(&state);
 	if (has_promisor_remote()) {
 		/*
 		 * Prefetch the objects that are to be checked out in the loop
@@ -461,6 +461,9 @@ static int check_updates(struct unpack_trees_options *o,
 					   to_fetch.oid, to_fetch.nr);
 		oid_array_clear(&to_fetch);
 	}
+
+	enable_delayed_checkout(&state);
+	init_parallel_checkout();
 	for (i = 0; i < index->cache_nr; i++) {
 		struct cache_entry *ce = index->cache[i];
 
@@ -474,6 +477,7 @@ static int check_updates(struct unpack_trees_options *o,
 		}
 	}
 	stop_progress(&progress);
+	errs |= run_parallel_checkout(&state);
 	errs |= finish_delayed_checkout(&state, NULL);
 	git_attr_set_direction(GIT_ATTR_CHECKIN);
 

.gitignore, Makefile, builtin.h, builtin/checkout--helper.c, entry.c, git.c, parallel-checkout.c, parallel-checkout.h

diff --git a/.gitignore b/.gitignore
index ee509a2ad2..6c01f0a58c 100644
--- a/.gitignore
+++ b/.gitignore
@@ -33,6 +33,7 @@
 /git-check-mailmap
 /git-check-ref-format
 /git-checkout
+/git-checkout--helper
 /git-checkout-index
 /git-cherry
 /git-cherry-pick
diff --git a/Makefile b/Makefile
index caab8e6401..926473d484 100644
--- a/Makefile
+++ b/Makefile
@@ -1049,6 +1049,7 @@ BUILTIN_OBJS += builtin/check-attr.o
 BUILTIN_OBJS += builtin/check-ignore.o
 BUILTIN_OBJS += builtin/check-mailmap.o
 BUILTIN_OBJS += builtin/check-ref-format.o
+BUILTIN_OBJS += builtin/checkout--helper.o
 BUILTIN_OBJS += builtin/checkout-index.o
 BUILTIN_OBJS += builtin/checkout.o
 BUILTIN_OBJS += builtin/clean.o
diff --git a/builtin.h b/builtin.h
index a5ae15bfe5..5790c68750 100644
--- a/builtin.h
+++ b/builtin.h
@@ -122,6 +122,7 @@ int cmd_branch(int argc, const char **argv, const char *prefix);
 int cmd_bundle(int argc, const char **argv, const char *prefix);
 int cmd_cat_file(int argc, const char **argv, const char *prefix);
 int cmd_checkout(int argc, const char **argv, const char *prefix);
+int cmd_checkout__helper(int argc, const char **argv, const char *prefix);
 int cmd_checkout_index(int argc, const char **argv, const char *prefix);
 int cmd_check_attr(int argc, const char **argv, const char *prefix);
 int cmd_check_ignore(int argc, const char **argv, const char *prefix);
diff --git a/builtin/checkout--helper.c b/builtin/checkout--helper.c
new file mode 100644
index 0000000000..269cf02feb
--- /dev/null
+++ b/builtin/checkout--helper.c
@@ -0,0 +1,135 @@
+#include "builtin.h"
+#include "config.h"
+#include "entry.h"
+#include "parallel-checkout.h"
+#include "parse-options.h"
+#include "pkt-line.h"
+
+static void packet_to_ci(char *line, int len, struct checkout_item *ci)
+{
+	struct ci_fixed_portion *fixed_portion;
+	char *encoding, *variant;
+
+	if (len < sizeof(struct ci_fixed_portion))
+		BUG("checkout worker received too short item (got %d, exp %d)",
+		    len, (int)sizeof(struct ci_fixed_portion));
+
+	fixed_portion = (struct ci_fixed_portion *)line;
+
+	if (len - sizeof(struct ci_fixed_portion) !=
+		fixed_portion->name_len + fixed_portion->working_tree_encoding_len)
+		BUG("checkout worker received corrupted item");
+
+	variant = line + sizeof(struct ci_fixed_portion);
+	if (fixed_portion->working_tree_encoding_len) {
+		encoding = xmemdupz(variant,
+				    fixed_portion->working_tree_encoding_len);
+		variant += fixed_portion->working_tree_encoding_len;
+	} else {
+		encoding = NULL;
+	}
+
+	memset(ci, 0, sizeof(*ci));
+	ci->ce = make_empty_transient_cache_entry(fixed_portion->name_len);
+	ci->ce->ce_namelen = fixed_portion->name_len;
+	ci->ce->ce_mode = fixed_portion->ce_mode;
+	memcpy(ci->ce->name, variant, ci->ce->ce_namelen);
+	oidcpy(&ci->ce->oid, &fixed_portion->oid);
+
+	ci->id = fixed_portion->id;
+	ci->ca.attr_action = fixed_portion->attr_action;
+	ci->ca.crlf_action = fixed_portion->crlf_action;
+	ci->ca.ident = fixed_portion->ident;
+	ci->ca.working_tree_encoding = encoding;
+}
+
+static void report_result(struct checkout_item *ci)
+{
+	struct ci_result res = { 0 };
+	size_t size;
+
+	res.id = ci->id;
+	res.status = ci->status;
+
+	if (ci->status == CI_SUCCESS) {
+		res.st = ci->st;
+		size = sizeof(res);
+	} else {
+		size = ci_result_base_size();
+	}
+
+	packet_write(1, (const char *)&res, size);
+}
+
+/* Free the worker-side malloced data, but not the ci itself. */
+static void release_checkout_item_data(struct checkout_item *ci)
+{
+	free((char *)ci->ca.working_tree_encoding);
+	discard_cache_entry(ci->ce);
+}
+
+static void worker_loop(struct checkout *state)
+{
+	struct checkout_item *items = NULL;
+	size_t i, nr = 0, alloc = 0;
+
+	while (1) {
+		int len;
+		char *line = packet_read_line(0, &len);
+
+		if (!line)
+			break;
+
+		ALLOC_GROW(items, nr + 1, alloc);
+		packet_to_ci(line, len, &items[nr++]);
+	}
+
+	for (i = 0; i < nr; ++i) {
+		struct checkout_item *ci = &items[i];
+		write_checkout_item(state, ci);
+		report_result(ci);
+		release_checkout_item_data(ci);
+	}
+
+	packet_flush(1);
+
+	free(items);
+}
+
+static const char * const checkout_helper_usage[] = {
+	N_("git checkout--helper [<options>]"),
+	NULL
+};
+
+int cmd_checkout__helper(int argc, const char **argv, const char *prefix)
+{
+	struct checkout state = CHECKOUT_INIT;
+	struct option checkout_helper_options[] = {
+		OPT_STRING(0, "prefix", &state.base_dir, N_("string"),
+			N_("when creating files, prepend <string>")),
+		OPT_END()
+	};
+
+	if (argc == 2 && !strcmp(argv[1], "-h"))
+		usage_with_options(checkout_helper_usage,
+				   checkout_helper_options);
+
+	git_config(git_default_config, NULL);
+	argc = parse_options(argc, argv, prefix, checkout_helper_options,
+			     checkout_helper_usage, 0);
+	if (argc > 0)
+		usage_with_options(checkout_helper_usage, checkout_helper_options);
+
+	if (state.base_dir)
+		state.base_dir_len = strlen(state.base_dir);
+
+	/*
+	 * Setting this on worker won't actually update the index. We just need
+	 * to pretend so to induce the checkout machinery to stat() the written
+	 * entries.
+	 */
+	state.refresh_cache = 1;
+
+	worker_loop(&state);
+	return 0;
+}
diff --git a/entry.c b/entry.c
index 47c2c20d5a..b6c808dffa 100644
--- a/entry.c
+++ b/entry.c
@@ -427,8 +427,17 @@ static void mark_colliding_entries(const struct checkout *state,
 	for (i = 0; i < state->istate->cache_nr; i++) {
 		struct cache_entry *dup = state->istate->cache[i];
 
-		if (dup == ce)
-			break;
+		if (dup == ce) {
+			/*
+			 * Parallel checkout creates the files in a racy order.
+			 * So the other side of the collision may appear after
+			 * the given cache_entry in the array.
+			 */
+			if (parallel_checkout_status() == PC_HANDLING_RESULTS)
+				continue;
+			else
+				break;
+		}
 
 		if (dup->ce_flags & (CE_MATCHED | CE_VALID | CE_SKIP_WORKTREE))
 			continue;
diff --git a/git.c b/git.c
index 8bd1d7551d..78c7bd412c 100644
--- a/git.c
+++ b/git.c
@@ -486,6 +486,8 @@ static struct cmd_struct commands[] = {
 	{ "check-mailmap", cmd_check_mailmap, RUN_SETUP },
 	{ "check-ref-format", cmd_check_ref_format, NO_PARSEOPT  },
 	{ "checkout", cmd_checkout, RUN_SETUP | NEED_WORK_TREE },
+	{ "checkout--helper", cmd_checkout__helper,
+		RUN_SETUP | NEED_WORK_TREE | SUPPORT_SUPER_PREFIX },
 	{ "checkout-index", cmd_checkout_index,
 		RUN_SETUP | NEED_WORK_TREE},
 	{ "cherry", cmd_cherry, RUN_SETUP },
diff --git a/parallel-checkout.c b/parallel-checkout.c
index e3b44eeb34..ec42342bc8 100644
--- a/parallel-checkout.c
+++ b/parallel-checkout.c
@@ -1,39 +1,23 @@
 #include "cache.h"
 #include "entry.h"
 #include "parallel-checkout.h"
+#include "pkt-line.h"
+#include "run-command.h"
 #include "streaming.h"
 
-enum ci_status {
-	CI_PENDING = 0,
-	CI_SUCCESS,
-	CI_RETRY,
-	CI_FAILED,
-};
-
-struct checkout_item {
-	/* pointer to a istate->cache[] entry. Not owned by us. */
-	struct cache_entry *ce;
-	struct conv_attrs ca;
-	struct stat st;
-	enum ci_status status;
-};
-
 struct parallel_checkout {
 	struct checkout_item *items;
 	size_t nr, alloc;
 };
 
 static struct parallel_checkout *parallel_checkout = NULL;
-
-enum pc_status {
-	PC_UNINITIALIZED = 0,
-	PC_ACCEPTING_ENTRIES,
-	PC_RUNNING,
-	PC_HANDLING_RESULTS,
-};
-
 static enum pc_status pc_status = PC_UNINITIALIZED;
 
+enum pc_status parallel_checkout_status(void)
+{
+	return pc_status;
+}
+
 void init_parallel_checkout(void)
 {
 	if (parallel_checkout)
@@ -113,9 +97,11 @@ int enqueue_checkout(struct cache_entry *ce, struct conv_attrs *ca)
 	ALLOC_GROW(parallel_checkout->items, parallel_checkout->nr + 1,
 		   parallel_checkout->alloc);
 
-	ci = &parallel_checkout->items[parallel_checkout->nr++];
+	ci = &parallel_checkout->items[parallel_checkout->nr];
 	ci->ce = ce;
 	memcpy(&ci->ca, ca, sizeof(ci->ca));
+	ci->id = parallel_checkout->nr;
+	parallel_checkout->nr++;
 
 	return 0;
 }
@@ -200,7 +186,8 @@ static int write_checkout_item_to_fd(int fd, struct checkout *state,
 	/*
 	 * checkout metadata is used to give context for external process
 	 * filters. Files requiring such filters are not eligible for parallel
-	 * checkout, so pass NULL.
+	 * checkout, so pass NULL. Note: if that changes, the metadata must also
+	 * be passed from the main process to the workers.
 	 */
 	ret = convert_to_working_tree_ca(&ci->ca, ci->ce->name, new_blob, size,
 					 &buf, NULL);
@@ -241,14 +228,14 @@ static int check_leading_dirs(const char *path, int len, int prefix_len)
 	return has_dirs_only_path(path, slash - path, prefix_len);
 }
 
-static void write_checkout_item(struct checkout *state, struct checkout_item *ci)
+void write_checkout_item(struct checkout *state, struct checkout_item *ci)
 {
 	unsigned int mode = (ci->ce->ce_mode & 0100) ? 0777 : 0666;
 	int fd = -1, fstat_done = 0;
 	struct strbuf path = STRBUF_INIT;
 
 	strbuf_add(&path, state->base_dir, state->base_dir_len);
-	strbuf_add(&path, ci->ce->name, ce_namelen(ci->ce));
+	strbuf_add(&path, ci->ce->name, ci->ce->ce_namelen);
 
 	/*
 	 * At this point, leading dirs should have already been created. But if
@@ -311,30 +298,214 @@ static void write_checkout_item(struct checkout *state, struct checkout_item *ci
 	strbuf_release(&path);
 }
 
-static int run_checkout_sequentially(struct checkout *state)
+static void send_one_item(int fd, struct checkout_item *ci)
+{
+	size_t len_data;
+	char *data, *variant;
+	struct ci_fixed_portion *fixed_portion;
+	const char *working_tree_encoding = ci->ca.working_tree_encoding;
+	size_t name_len = ci->ce->ce_namelen;
+	size_t working_tree_encoding_len = working_tree_encoding ?
+					   strlen(working_tree_encoding) : 0;
+
+	len_data = sizeof(struct ci_fixed_portion) + name_len +
+		   working_tree_encoding_len;
+
+	data = xcalloc(1, len_data);
+
+	fixed_portion = (struct ci_fixed_portion *)data;
+	fixed_portion->id = ci->id;
+	oidcpy(&fixed_portion->oid, &ci->ce->oid);
+	fixed_portion->ce_mode = ci->ce->ce_mode;
+	fixed_portion->attr_action = ci->ca.attr_action;
+	fixed_portion->crlf_action = ci->ca.crlf_action;
+	fixed_portion->ident = ci->ca.ident;
+	fixed_portion->name_len = name_len;
+	fixed_portion->working_tree_encoding_len = working_tree_encoding_len;
+
+	variant = data + sizeof(*fixed_portion);
+	if (working_tree_encoding_len) {
+		memcpy(variant, working_tree_encoding, working_tree_encoding_len);
+		variant += working_tree_encoding_len;
+	}
+	memcpy(variant, ci->ce->name, name_len);
+
+	packet_write(fd, data, len_data);
+
+	free(data);
+}
+
+static void send_batch(int fd, size_t start, size_t nr)
 {
 	size_t i;
+	for (i = 0; i < nr; ++i)
+		send_one_item(fd, &parallel_checkout->items[start + i]);
+	packet_flush(fd);
+}
 
-	for (i = 0; i < parallel_checkout->nr; ++i) {
-		struct checkout_item *ci = &parallel_checkout->items[i];
-		write_checkout_item(state, ci);
+static struct child_process *setup_workers(struct checkout *state, int num_workers)
+{
+	struct child_process *workers;
+	int i, workers_with_one_extra_item;
+	size_t base_batch_size, next_to_assign = 0;
+
+	base_batch_size = parallel_checkout->nr / num_workers;
+	workers_with_one_extra_item = parallel_checkout->nr % num_workers;
+	ALLOC_ARRAY(workers, num_workers);
+
+	for (i = 0; i < num_workers; ++i) {
+		struct child_process *cp = &workers[i];
+		size_t batch_size = base_batch_size;
+
+		child_process_init(cp);
+		cp->git_cmd = 1;
+		cp->in = -1;
+		cp->out = -1;
+		strvec_push(&cp->args, "checkout--helper");
+		if (state->base_dir_len)
+			strvec_pushf(&cp->args, "--prefix=%s", state->base_dir);
+		if (start_command(cp))
+			die(_("failed to spawn checkout worker"));
+
+		/* distribute the extra work evenly */
+		if (i < workers_with_one_extra_item)
+			batch_size++;
+
+		send_batch(cp->in, next_to_assign, batch_size);
+		next_to_assign += batch_size;
 	}
 
+	return workers;
+}
+
+static void finish_workers(struct child_process *workers, int num_workers)
+{
+	int i;
+	for (i = 0; i < num_workers; ++i) {
+		struct child_process *w = &workers[i];
+		if (w->in >= 0)
+			close(w->in);
+		if (w->out >= 0)
+			close(w->out);
+		if (finish_command(w))
+			die(_("checkout worker finished with error"));
+	}
+	free(workers);
+}
+
+static void parse_and_save_result(const char *line, int len)
+{
+	struct ci_result *res;
+	struct checkout_item *ci;
+
+	/*
+	 * Worker should send either the full result struct or just the base
+	 * (i.e. no stat data).
+	 */
+	if (len != ci_result_base_size() && len != sizeof(struct ci_result))
+		BUG("received corrupted item from checkout worker");
+
+	res = (struct ci_result *)line;
+
+	if (res->id > parallel_checkout->nr)
+		BUG("checkout worker sent unknown item id");
+
+	ci = &parallel_checkout->items[res->id];
+	ci->status = res->status;
+
+	/*
+	 * Worker only sends stat data on success. Otherwise, we *cannot* access
+	 * res->st as that will be an invalid address.
+	 */
+	if (res->status == CI_SUCCESS)
+		ci->st = res->st;
+}
+
+static void gather_results_from_workers(struct child_process *workers,
+					int num_workers)
+{
+	int i, active_workers = num_workers;
+	struct pollfd *pfds;
+
+	CALLOC_ARRAY(pfds, num_workers);
+	for (i = 0; i < num_workers; ++i) {
+		pfds[i].fd = workers[i].out;
+		pfds[i].events = POLLIN;
+	}
+
+	while (active_workers) {
+		int nr = poll(pfds, num_workers, -1);
+
+		if (nr < 0) {
+			if (errno == EINTR)
+				continue;
+			die_errno("failed to poll checkout workers");
+		}
+
+		for (i = 0; i < num_workers && nr > 0; ++i) {
+			struct pollfd *pfd = &pfds[i];
+
+			if (!pfd->revents)
+				continue;
+
+			if (pfd->revents & POLLIN) {
+				int len;
+				const char *line = packet_read_line(pfd->fd, &len);
+
+				if (!line) {
+					pfd->fd = -1;
+					active_workers--;
+				} else {
+					parse_and_save_result(line, len);
+				}
+			} else if (pfd->revents & POLLHUP) {
+				pfd->fd = -1;
+				active_workers--;
+			} else if (pfd->revents & (POLLNVAL | POLLERR)) {
+				die(_("error polling from checkout worker"));
+			}
+
+			nr--;
+		}
+	}
+
+	free(pfds);
+}
+
+static int run_checkout_sequentially(struct checkout *state)
+{
+	size_t i;
+	for (i = 0; i < parallel_checkout->nr; ++i)
+		write_checkout_item(state, &parallel_checkout->items[i]);
 	return handle_results(state);
 }
 
+static const int workers_threshold = 0;
 
 int run_parallel_checkout(struct checkout *state)
 {
-	int ret;
+	int num_workers = online_cpus();
+	int ret = 0;
+	struct child_process *workers;
 
 	if (!parallel_checkout)
 		BUG("cannot run parallel checkout: not initialized yet");
 
 	pc_status = PC_RUNNING;
 
-	ret = run_checkout_sequentially(state);
+	if (parallel_checkout->nr == 0) {
+		goto done;
+	} else if (parallel_checkout->nr < workers_threshold || num_workers == 1) {
+		ret = run_checkout_sequentially(state);
+		goto done;
+	}
+
+	workers = setup_workers(state, num_workers);
+	gather_results_from_workers(workers, num_workers);
+	finish_workers(workers, num_workers);
+	ret = handle_results(state);
 
+done:
 	finish_parallel_checkout();
 	return ret;
 }
diff --git a/parallel-checkout.h b/parallel-checkout.h
index 8eef59ffcd..f25f2874ae 100644
--- a/parallel-checkout.h
+++ b/parallel-checkout.h
@@ -1,10 +1,21 @@
 #ifndef PARALLEL_CHECKOUT_H
 #define PARALLEL_CHECKOUT_H
 
-struct cache_entry;
-struct checkout;
-struct conv_attrs;
+#include "entry.h"
+#include "convert.h"
 
+/****************************************************************
+ * Users of parallel checkout
+ ****************************************************************/
+
+enum pc_status {
+	PC_UNINITIALIZED = 0,
+	PC_ACCEPTING_ENTRIES,
+	PC_RUNNING,
+	PC_HANDLING_RESULTS,
+};
+
+enum pc_status parallel_checkout_status(void);
 void init_parallel_checkout(void);
 
 /*
@@ -14,7 +25,62 @@ void init_parallel_checkout(void);
  */
 int enqueue_checkout(struct cache_entry *ce, struct conv_attrs *ca);
 
-/* Write all the queued entries, returning 0 on success.*/
+/* Write all the queued entries, returning 0 on success. */
 int run_parallel_checkout(struct checkout *state);
 
+/****************************************************************
+ * Interface with checkout--helper
+ ****************************************************************/
+
+enum ci_status {
+	CI_PENDING = 0,
+	CI_SUCCESS,
+	CI_RETRY,
+	CI_FAILED,
+};
+
+struct checkout_item {
+	/*
+	 * In main process ce points to a istate->cache[] entry. Thus, it's not
+	 * owned by us. In workers they own the memory, which *must be* released.
+	 */
+	struct cache_entry *ce;
+	struct conv_attrs ca;
+	size_t id; /* position in parallel_checkout->items[] of main process */
+
+	/* Output fields, sent from workers. */
+	enum ci_status status;
+	struct stat st;
+};
+
+/*
+ * The fixed-size portion of `struct checkout_item` that is sent to the workers.
+ * Following this will be 2 strings: ca.working_tree_encoding and ce.name; These
+ * are NOT null terminated, since we have the size in the fixed portion.
+ */
+struct ci_fixed_portion {
+	size_t id;
+	struct object_id oid;
+	unsigned int ce_mode;
+	enum crlf_action attr_action;
+	enum crlf_action crlf_action;
+	int ident;
+	size_t working_tree_encoding_len;
+	size_t name_len;
+};
+
+/*
+ * The `struct checkout_item` fields returned by the workers. The order is
+ * important here, specially stat being the last one, as it is omitted on error.
+ */
+struct ci_result {
+	size_t id;
+	enum ci_status status;
+	struct stat st;
+};
+
+#define ci_result_base_size() offsetof(struct ci_result, st)
+
+void write_checkout_item(struct checkout *state, struct checkout_item *ci);
+
 #endif /* PARALLEL_CHECKOUT_H */

Documentation/config/checkout.txt, parallel-checkout.c, parallel-checkout.h, unpack-trees.c

diff --git a/Documentation/config/checkout.txt b/Documentation/config/checkout.txt
index 6b646813ab..9dabdf9231 100644
--- a/Documentation/config/checkout.txt
+++ b/Documentation/config/checkout.txt
@@ -16,3 +16,19 @@ will checkout the '<something>' branch on another remote,
 and by linkgit:git-worktree[1] when 'git worktree add' refers to a
 remote branch. This setting might be used for other checkout-like
 commands or functionality in the future.
+
+checkout.workers::
+	The number of worker processes to use when updating the working tree.
+	If unset (or set to a value less than one), Git will use as many
+	workers as the number of logical cores available. One means sequential
+	execution. This and the checkout.workersThreshold settings affect all
+	commands which perform checkout. E.g. checkout, switch, clone,
+	sparse-checkout, read-tree, etc.
+
+checkout.workersThreshold::
+	If set to a positive number, parallel checkout will not be attempted
+	when the number of files to be updated is less than the defined limit.
+	When set to a negative number or unset, defaults to 0. The reasoning
+	behind this config is that, when modifying a small number of files, a
+	sequential execution might be faster, as it avoids the cost of spawning
+	subprocesses and inter-process communication.
diff --git a/parallel-checkout.c b/parallel-checkout.c
index ec42342bc8..e0fca4d380 100644
--- a/parallel-checkout.c
+++ b/parallel-checkout.c
@@ -4,6 +4,8 @@
 #include "pkt-line.h"
 #include "run-command.h"
 #include "streaming.h"
+#include "thread-utils.h"
+#include "config.h"
 
 struct parallel_checkout {
 	struct checkout_item *items;
@@ -18,6 +20,19 @@ enum pc_status parallel_checkout_status(void)
 	return pc_status;
 }
 
+#define DEFAULT_WORKERS_THRESHOLD 0
+
+void get_parallel_checkout_configs(int *num_workers, int *threshold)
+{
+	if (git_config_get_int("checkout.workers", num_workers) ||
+	    *num_workers < 1)
+		*num_workers = online_cpus();
+
+	if (git_config_get_int("checkout.workersThreshold", threshold) ||
+	    *threshold < 0)
+		*threshold = DEFAULT_WORKERS_THRESHOLD;
+}
+
 void init_parallel_checkout(void)
 {
 	if (parallel_checkout)
@@ -480,22 +495,23 @@ static int run_checkout_sequentially(struct checkout *state)
 	return handle_results(state);
 }
 
-static const int workers_threshold = 0;
-
-int run_parallel_checkout(struct checkout *state)
+int run_parallel_checkout(struct checkout *state, int num_workers, int threshold)
 {
-	int num_workers = online_cpus();
 	int ret = 0;
 	struct child_process *workers;
 
 	if (!parallel_checkout)
 		BUG("cannot run parallel checkout: not initialized yet");
 
+	if (num_workers < 1)
+		BUG("invalid number of workers for run_parallel_checkout: %d",
+		    num_workers);
+
 	pc_status = PC_RUNNING;
 
 	if (parallel_checkout->nr == 0) {
 		goto done;
-	} else if (parallel_checkout->nr < workers_threshold || num_workers == 1) {
+	} else if (parallel_checkout->nr < threshold || num_workers == 1) {
 		ret = run_checkout_sequentially(state);
 		goto done;
 	}
diff --git a/parallel-checkout.h b/parallel-checkout.h
index f25f2874ae..b4d412c8b5 100644
--- a/parallel-checkout.h
+++ b/parallel-checkout.h
@@ -18,6 +18,9 @@ enum pc_status {
 enum pc_status parallel_checkout_status(void);
 void init_parallel_checkout(void);
 
+/* Reads the checkout.workers and checkout.workersThreshold settings. */
+void get_parallel_checkout_configs(int *num_workers, int *threshold);
+
 /*
  * Return -1 if parallel checkout is currently not enabled or if the entry is
  * not eligible for parallel checkout. Otherwise, enqueue the entry for later
@@ -25,8 +28,12 @@ void init_parallel_checkout(void);
  */
 int enqueue_checkout(struct cache_entry *ce, struct conv_attrs *ca);
 
-/* Write all the queued entries, returning 0 on success. */
-int run_parallel_checkout(struct checkout *state);
+/*
+ * Write all the queued entries, returning 0 on success. If the number of
+ * entries is below the specified threshold, the operation is performed
+ * sequentially.
+ */
+int run_parallel_checkout(struct checkout *state, int num_workers, int threshold);
 
 /****************************************************************
  * Interface with checkout--helper
diff --git a/unpack-trees.c b/unpack-trees.c
index 1b1da7485a..117ed42370 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -399,7 +399,7 @@ static int check_updates(struct unpack_trees_options *o,
 	int errs = 0;
 	struct progress *progress;
 	struct checkout state = CHECKOUT_INIT;
-	int i;
+	int i, pc_workers, pc_threshold;
 
 	trace_performance_enter();
 	state.force = 1;
@@ -462,8 +462,11 @@ static int check_updates(struct unpack_trees_options *o,
 		oid_array_clear(&to_fetch);
 	}
 
+	get_parallel_checkout_configs(&pc_workers, &pc_threshold);
+
 	enable_delayed_checkout(&state);
-	init_parallel_checkout();
+	if (pc_workers > 1)
+		init_parallel_checkout();
 	for (i = 0; i < index->cache_nr; i++) {
 		struct cache_entry *ce = index->cache[i];
 
@@ -477,7 +480,8 @@ static int check_updates(struct unpack_trees_options *o,
 		}
 	}
 	stop_progress(&progress);
-	errs |= run_parallel_checkout(&state);
+	if (pc_workers > 1)
+		errs |= run_parallel_checkout(&state, pc_workers, pc_threshold);
 	errs |= finish_delayed_checkout(&state, NULL);
 	git_attr_set_direction(GIT_ATTR_CHECKIN);
 

parallel-checkout.c, parallel-checkout.h, unpack-trees.c

diff --git a/parallel-checkout.c b/parallel-checkout.c
index e0fca4d380..78bf2de5ea 100644
--- a/parallel-checkout.c
+++ b/parallel-checkout.c
@@ -2,6 +2,7 @@
 #include "entry.h"
 #include "parallel-checkout.h"
 #include "pkt-line.h"
+#include "progress.h"
 #include "run-command.h"
 #include "streaming.h"
 #include "thread-utils.h"
@@ -10,6 +11,8 @@
 struct parallel_checkout {
 	struct checkout_item *items;
 	size_t nr, alloc;
+	struct progress *progress;
+	unsigned int *progress_cnt;
 };
 
 static struct parallel_checkout *parallel_checkout = NULL;
@@ -121,6 +124,22 @@ int enqueue_checkout(struct cache_entry *ce, struct conv_attrs *ca)
 	return 0;
 }
 
+size_t pc_queue_size(void)
+{
+	if (!parallel_checkout)
+		return 0;
+	return parallel_checkout->nr;
+}
+
+static void advance_progress_meter(void)
+{
+	if (parallel_checkout && parallel_checkout->progress) {
+		(*parallel_checkout->progress_cnt)++;
+		display_progress(parallel_checkout->progress,
+				 *parallel_checkout->progress_cnt);
+	}
+}
+
 static int handle_results(struct checkout *state)
 {
 	int ret = 0;
@@ -132,6 +151,10 @@ static int handle_results(struct checkout *state)
 		struct checkout_item *ci = &parallel_checkout->items[i];
 		struct stat *st = &ci->st;
 
+		/*
+		 * Note: progress meter was already incremented for CI_SUCCESS
+		 * and CI_FAILED.
+		 */
 		switch(ci->status) {
 		case CI_SUCCESS:
 			update_ce_after_write(state, ci->ce, st);
@@ -145,6 +168,7 @@ static int handle_results(struct checkout *state)
 			 * leading dirs in the entry's path.
 			 */
 			ret |= checkout_entry_ca(ci->ce, &ci->ca, state, NULL, NULL);
+			advance_progress_meter();
 			break;
 		case CI_FAILED:
 			ret = -1;
@@ -434,6 +458,9 @@ static void parse_and_save_result(const char *line, int len)
 	 */
 	if (res->status == CI_SUCCESS)
 		ci->st = res->st;
+
+	if (res->status != CI_RETRY)
+		advance_progress_meter();
 }
 
 static void gather_results_from_workers(struct child_process *workers,
@@ -490,12 +517,17 @@ static void gather_results_from_workers(struct child_process *workers,
 static int run_checkout_sequentially(struct checkout *state)
 {
 	size_t i;
-	for (i = 0; i < parallel_checkout->nr; ++i)
-		write_checkout_item(state, &parallel_checkout->items[i]);
+	for (i = 0; i < parallel_checkout->nr; ++i) {
+		struct checkout_item *ci = &parallel_checkout->items[i];
+		write_checkout_item(state, ci);
+		if (ci->status != CI_RETRY)
+			advance_progress_meter();
+	}
 	return handle_results(state);
 }
 
-int run_parallel_checkout(struct checkout *state, int num_workers, int threshold)
+int run_parallel_checkout(struct checkout *state, int num_workers, int threshold,
+			  struct progress *progress, unsigned int *progress_cnt)
 {
 	int ret = 0;
 	struct child_process *workers;
@@ -508,6 +540,8 @@ int run_parallel_checkout(struct checkout *state, int num_workers, int threshold
 		    num_workers);
 
 	pc_status = PC_RUNNING;
+	parallel_checkout->progress = progress;
+	parallel_checkout->progress_cnt = progress_cnt;
 
 	if (parallel_checkout->nr == 0) {
 		goto done;
diff --git a/parallel-checkout.h b/parallel-checkout.h
index b4d412c8b5..2b81a5db6c 100644
--- a/parallel-checkout.h
+++ b/parallel-checkout.h
@@ -27,13 +27,15 @@ void get_parallel_checkout_configs(int *num_workers, int *threshold);
  * write and return 0.
  */
 int enqueue_checkout(struct cache_entry *ce, struct conv_attrs *ca);
+size_t pc_queue_size(void);
 
 /*
  * Write all the queued entries, returning 0 on success. If the number of
  * entries is below the specified threshold, the operation is performed
  * sequentially.
  */
-int run_parallel_checkout(struct checkout *state, int num_workers, int threshold);
+int run_parallel_checkout(struct checkout *state, int num_workers, int threshold,
+			  struct progress *progress, unsigned int *progress_cnt);
 
 /****************************************************************
  * Interface with checkout--helper
diff --git a/unpack-trees.c b/unpack-trees.c
index 117ed42370..e05e6ceff2 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -471,17 +471,22 @@ static int check_updates(struct unpack_trees_options *o,
 		struct cache_entry *ce = index->cache[i];
 
 		if (ce->ce_flags & CE_UPDATE) {
+			size_t last_pc_queue_size = pc_queue_size();
+
 			if (ce->ce_flags & CE_WT_REMOVE)
 				BUG("both update and delete flags are set on %s",
 				    ce->name);
-			display_progress(progress, ++cnt);
 			ce->ce_flags &= ~CE_UPDATE;
 			errs |= checkout_entry(ce, &state, NULL, NULL);
+
+			if (last_pc_queue_size == pc_queue_size())
+				display_progress(progress, ++cnt);
 		}
 	}
-	stop_progress(&progress);
 	if (pc_workers > 1)
-		errs |= run_parallel_checkout(&state, pc_workers, pc_threshold);
+		errs |= run_parallel_checkout(&state, pc_workers, pc_threshold,
+					      progress, &cnt);
+	stop_progress(&progress);
 	errs |= finish_delayed_checkout(&state, NULL);
 	git_attr_set_direction(GIT_ATTR_CHECKIN);
 

builtin/checkout--helper.c, builtin/checkout.c, builtin/difftool.c, cache.h, read-cache.c, unpack-trees.c

diff --git a/builtin/checkout--helper.c b/builtin/checkout--helper.c
index 269cf02feb..d2ab40cb4c 100644
--- a/builtin/checkout--helper.c
+++ b/builtin/checkout--helper.c
@@ -30,7 +30,7 @@ static void packet_to_ci(char *line, int len, struct checkout_item *ci)
 	}
 
 	memset(ci, 0, sizeof(*ci));
-	ci->ce = make_empty_transient_cache_entry(fixed_portion->name_len);
+	ci->ce = make_empty_transient_cache_entry(fixed_portion->name_len, NULL);
 	ci->ce->ce_namelen = fixed_portion->name_len;
 	ci->ce->ce_mode = fixed_portion->ce_mode;
 	memcpy(ci->ce->name, variant, ci->ce->ce_namelen);
diff --git a/builtin/checkout.c b/builtin/checkout.c
index 3e09b29cfe..8e4a3c1df0 100644
--- a/builtin/checkout.c
+++ b/builtin/checkout.c
@@ -291,7 +291,7 @@ static int checkout_merged(int pos, const struct checkout *state, int *nr_checko
 	if (write_object_file(result_buf.ptr, result_buf.size, blob_type, &oid))
 		die(_("Unable to add merge result for '%s'"), path);
 	free(result_buf.ptr);
-	ce = make_transient_cache_entry(mode, &oid, path, 2);
+	ce = make_transient_cache_entry(mode, &oid, path, 2, NULL);
 	if (!ce)
 		die(_("make_cache_entry failed for path '%s'"), path);
 	status = checkout_entry(ce, state, NULL, nr_checkouts);
diff --git a/builtin/difftool.c b/builtin/difftool.c
index dfa22b67eb..5e7a57c8c2 100644
--- a/builtin/difftool.c
+++ b/builtin/difftool.c
@@ -323,7 +323,7 @@ static int checkout_path(unsigned mode, struct object_id *oid,
 	struct cache_entry *ce;
 	int ret;
 
-	ce = make_transient_cache_entry(mode, oid, path, 0);
+	ce = make_transient_cache_entry(mode, oid, path, 0, NULL);
 	ret = checkout_entry(ce, state, NULL, NULL);
 
 	discard_cache_entry(ce);
diff --git a/cache.h b/cache.h
index e6963cf8fe..e2b41c5f8b 100644
--- a/cache.h
+++ b/cache.h
@@ -355,16 +355,16 @@ struct cache_entry *make_empty_cache_entry(struct index_state *istate,
 					   size_t name_len);
 
 /*
- * Create a cache_entry that is not intended to be added to an index.
- * Caller is responsible for discarding the cache_entry
- * with `discard_cache_entry`.
+ * Create a cache_entry that is not intended to be added to an index. If mp is
+ * not NULL, the entry is allocated within the given memory pool. Caller is
+ * responsible for discarding the cache_entry with `discard_cache_entry`.
  */
 struct cache_entry *make_transient_cache_entry(unsigned int mode,
 					       const struct object_id *oid,
 					       const char *path,
-					       int stage);
+					       int stage, struct mem_pool *mp);
 
-struct cache_entry *make_empty_transient_cache_entry(size_t name_len);
+struct cache_entry *make_empty_transient_cache_entry(size_t len, struct mem_pool *mp);
 
 /*
  * Discard cache entry.
diff --git a/read-cache.c b/read-cache.c
index 8ed1c29b54..eeb122cca4 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -811,8 +811,10 @@ struct cache_entry *make_empty_cache_entry(struct index_state *istate, size_t le
 	return mem_pool__ce_calloc(find_mem_pool(istate), len);
 }
 
-struct cache_entry *make_empty_transient_cache_entry(size_t len)
+struct cache_entry *make_empty_transient_cache_entry(size_t len, struct mem_pool *mp)
 {
+	if (mp)
+		return mem_pool__ce_calloc(mp, len);
 	return xcalloc(1, cache_entry_size(len));
 }
 
@@ -846,8 +848,10 @@ struct cache_entry *make_cache_entry(struct index_state *istate,
 	return ret;
 }
 
-struct cache_entry *make_transient_cache_entry(unsigned int mode, const struct object_id *oid,
-					       const char *path, int stage)
+struct cache_entry *make_transient_cache_entry(unsigned int mode,
+					       const struct object_id *oid,
+					       const char *path, int stage,
+					       struct mem_pool *mp)
 {
 	struct cache_entry *ce;
 	int len;
@@ -858,7 +862,7 @@ struct cache_entry *make_transient_cache_entry(unsigned int mode, const struct o
 	}
 
 	len = strlen(path);
-	ce = make_empty_transient_cache_entry(len);
+	ce = make_empty_transient_cache_entry(len, mp);
 
 	oidcpy(&ce->oid, oid);
 	memcpy(ce->name, path, len);
diff --git a/unpack-trees.c b/unpack-trees.c
index e05e6ceff2..dcb40dc8fa 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -1031,7 +1031,7 @@ static struct cache_entry *create_ce_entry(const struct traverse_info *info,
 	size_t len = traverse_path_len(info, tree_entry_len(n));
 	struct cache_entry *ce =
 		is_transient ?
-		make_empty_transient_cache_entry(len) :
+		make_empty_transient_cache_entry(len, NULL) :
 		make_empty_cache_entry(istate, len);
 
 	ce->ce_mode = create_ce_mode(n->mode);

diff --git a/builtin/checkout.c b/builtin/checkout.c
index 8e4a3c1df0..b9230d5009 100644
--- a/builtin/checkout.c
+++ b/builtin/checkout.c
@@ -27,6 +27,7 @@
 #include "wt-status.h"
 #include "xdiff-interface.h"
 #include "entry.h"
+#include "parallel-checkout.h"
 
 static const char * const checkout_usage[] = {
 	N_("git checkout [<options>] <branch>"),
@@ -230,7 +231,8 @@ static int checkout_stage(int stage, const struct cache_entry *ce, int pos,
 		return error(_("path '%s' does not have their version"), ce->name);
 }
 
-static int checkout_merged(int pos, const struct checkout *state, int *nr_checkouts)
+static int checkout_merged(int pos, const struct checkout *state,
+			   int *nr_checkouts, struct mem_pool *ce_mem_pool)
 {
 	struct cache_entry *ce = active_cache[pos];
 	const char *path = ce->name;
@@ -291,11 +293,10 @@ static int checkout_merged(int pos, const struct checkout *state, int *nr_checko
 	if (write_object_file(result_buf.ptr, result_buf.size, blob_type, &oid))
 		die(_("Unable to add merge result for '%s'"), path);
 	free(result_buf.ptr);
-	ce = make_transient_cache_entry(mode, &oid, path, 2, NULL);
+	ce = make_transient_cache_entry(mode, &oid, path, 2, ce_mem_pool);
 	if (!ce)
 		die(_("make_cache_entry failed for path '%s'"), path);
 	status = checkout_entry(ce, state, NULL, nr_checkouts);
-	discard_cache_entry(ce);
 	return status;
 }
 
@@ -359,16 +360,22 @@ static int checkout_worktree(const struct checkout_opts *opts,
 	int nr_checkouts = 0, nr_unmerged = 0;
 	int errs = 0;
 	int pos;
+	int pc_workers, pc_threshold;
+	struct mem_pool *ce_mem_pool = NULL;
 
 	state.force = 1;
 	state.refresh_cache = 1;
 	state.istate = &the_index;
 
+	mem_pool_init(&ce_mem_pool, 0);
+	get_parallel_checkout_configs(&pc_workers, &pc_threshold);
 	init_checkout_metadata(&state.meta, info->refname,
 			       info->commit ? &info->commit->object.oid : &info->oid,
 			       NULL);
 
 	enable_delayed_checkout(&state);
+	if (pc_workers > 1)
+		init_parallel_checkout();
 	for (pos = 0; pos < active_nr; pos++) {
 		struct cache_entry *ce = active_cache[pos];
 		if (ce->ce_flags & CE_MATCHED) {
@@ -384,10 +391,15 @@ static int checkout_worktree(const struct checkout_opts *opts,
 						       &nr_checkouts, opts->overlay_mode);
 			else if (opts->merge)
 				errs |= checkout_merged(pos, &state,
-							&nr_unmerged);
+							&nr_unmerged,
+							ce_mem_pool);
 			pos = skip_same_name(ce, pos) - 1;
 		}
 	}
+	if (pc_workers > 1)
+		errs |= run_parallel_checkout(&state, pc_workers, pc_threshold,
+					      NULL, NULL);
+	mem_pool_discard(ce_mem_pool, should_validate_cache_entries());
 	remove_marked_cache_entries(&the_index, 1);
 	remove_scheduled_dirs();
 	errs |= finish_delayed_checkout(&state, &nr_checkouts);

diff --git a/builtin/checkout-index.c b/builtin/checkout-index.c
index 0f1ff73129..33fb933c30 100644
--- a/builtin/checkout-index.c
+++ b/builtin/checkout-index.c
@@ -12,6 +12,7 @@
 #include "cache-tree.h"
 #include "parse-options.h"
 #include "entry.h"
+#include "parallel-checkout.h"
 
 #define CHECKOUT_ALL 4
 static int nul_term_line;
@@ -160,6 +161,7 @@ int cmd_checkout_index(int argc, const char **argv, const char *prefix)
 	int prefix_length;
 	int force = 0, quiet = 0, not_new = 0;
 	int index_opt = 0;
+	int pc_workers, pc_threshold;
 	struct option builtin_checkout_index_options[] = {
 		OPT_BOOL('a', "all", &all,
 			N_("check out all files in the index")),
@@ -214,6 +216,14 @@ int cmd_checkout_index(int argc, const char **argv, const char *prefix)
 		hold_locked_index(&lock_file, LOCK_DIE_ON_ERROR);
 	}
 
+	if (!to_tempfile)
+		get_parallel_checkout_configs(&pc_workers, &pc_threshold);
+	else
+		pc_workers = 1;
+
+	if (pc_workers > 1)
+		init_parallel_checkout();
+
 	/* Check out named files first */
 	for (i = 0; i < argc; i++) {
 		const char *arg = argv[i];
@@ -256,6 +266,12 @@ int cmd_checkout_index(int argc, const char **argv, const char *prefix)
 	if (all)
 		checkout_all(prefix, prefix_length);
 
+	if (pc_workers > 1) {
+		/* Errors were already reported */
+		run_parallel_checkout(&state, pc_workers, pc_threshold,
+				      NULL, NULL);
+	}
+
 	if (is_lock_file_locked(&lock_file) &&
 	    write_locked_index(&the_index, &lock_file, COMMIT_LOCK))
 		die("Unable to write new index file");

entry.c, parallel-checkout.c, parallel-checkout.h, unpack-trees.c

diff --git a/entry.c b/entry.c
index b6c808dffa..6208df23df 100644
--- a/entry.c
+++ b/entry.c
@@ -477,6 +477,16 @@ int checkout_entry_ca(struct cache_entry *ce, struct conv_attrs *ca,
 		return write_entry(ce, topath, ca, state, 1);
 	}
 
+	/*
+	 * If a regular file x/f is queued for parallel checkout and a symlink
+	 * X is created now, the worker could wrongly create the file at X/f
+	 * due to path collision. Thus, symlinks are only created after
+	 * parallel-eligible entries.
+	 */
+	if (parallel_checkout_status() == PC_ACCEPTING_ENTRIES &&
+	    S_ISLNK(ce->ce_mode))
+		enqueue_symlink_checkout(ce, nr_checkouts);
+
 	strbuf_reset(&path);
 	strbuf_add(&path, state->base_dir, state->base_dir_len);
 	strbuf_add(&path, ce->name, ce_namelen(ce));
diff --git a/parallel-checkout.c b/parallel-checkout.c
index 78bf2de5ea..fee93460c1 100644
--- a/parallel-checkout.c
+++ b/parallel-checkout.c
@@ -140,6 +140,44 @@ static void advance_progress_meter(void)
 	}
 }
 
+struct symlink_checkout_item {
+	struct cache_entry *ce;
+	int *nr_checkouts;
+};
+
+static struct symlink_checkout_item *symlink_queue = NULL;
+static size_t symlink_queue_nr = 0, symlink_queue_alloc = 0;
+
+void enqueue_symlink_checkout(struct cache_entry *ce, int *nr_checkouts)
+{
+	assert(S_ISLNK(ce->ce_mode));
+	ALLOC_GROW(symlink_queue, symlink_queue_nr + 1, symlink_queue_alloc);
+	symlink_queue[symlink_queue_nr].ce = ce;
+	symlink_queue[symlink_queue_nr].nr_checkouts = nr_checkouts;
+	symlink_queue_nr++;
+}
+
+size_t symlink_queue_size(void)
+{
+	return symlink_queue_nr;
+}
+
+static int checkout_symlink_queue(struct checkout *state)
+{
+	size_t i;
+	int ret = 0;
+
+	for (i = 0; i < symlink_queue_nr; ++i) {
+		struct symlink_checkout_item *sci = &symlink_queue[i];
+		ret |= checkout_entry(sci->ce, state, NULL, sci->nr_checkouts);
+		advance_progress_meter();
+	}
+
+	FREE_AND_NULL(symlink_queue);
+	symlink_queue_nr = symlink_queue_alloc = 0;
+	return ret;
+}
+
 static int handle_results(struct checkout *state)
 {
 	int ret = 0;
@@ -257,16 +295,6 @@ static int close_and_clear(int *fd)
 	return ret;
 }
 
-static int check_leading_dirs(const char *path, int len, int prefix_len)
-{
-	const char *slash = path + len;
-
-	while (slash > path && *slash != '/')
-		slash--;
-
-	return has_dirs_only_path(path, slash - path, prefix_len);
-}
-
 void write_checkout_item(struct checkout *state, struct checkout_item *ci)
 {
 	unsigned int mode = (ci->ce->ce_mode & 0100) ? 0777 : 0666;
@@ -276,27 +304,15 @@ void write_checkout_item(struct checkout *state, struct checkout_item *ci)
 	strbuf_add(&path, state->base_dir, state->base_dir_len);
 	strbuf_add(&path, ci->ce->name, ci->ce->ce_namelen);
 
-	/*
-	 * At this point, leading dirs should have already been created. But if
-	 * a symlink being checked out has collided with one of the dirs, due to
-	 * file system folding rules, it's possible that the dirs are no longer
-	 * present. So we have to check again, and report any path collisions.
-	 */
-	if (!check_leading_dirs(path.buf, path.len, state->base_dir_len)) {
-		ci->status = CI_RETRY;
-		goto out;
-	}
-
 	fd = open(path.buf, O_WRONLY | O_CREAT | O_EXCL, mode);
 
 	if (fd < 0) {
-		if (errno == EEXIST || errno == EISDIR) {
+		if (errno == EEXIST || errno == EISDIR || errno == ENOENT ||
+		    errno == ENOTDIR) {
 			/*
 			 * Errors which probably represent a path collision.
 			 * Suppress the error message and mark the ci to be
-			 * retried later, sequentially. ENOTDIR and ENOENT are
-			 * also interesting, but check_leading_dirs() should
-			 * have already caught these cases.
+			 * retried later, sequentially.
 			 */
 			ci->status = CI_RETRY;
 		} else {
@@ -523,7 +539,7 @@ static int run_checkout_sequentially(struct checkout *state)
 		if (ci->status != CI_RETRY)
 			advance_progress_meter();
 	}
-	return handle_results(state);
+	return handle_results(state) | checkout_symlink_queue(state);
 }
 
 int run_parallel_checkout(struct checkout *state, int num_workers, int threshold,
@@ -553,7 +569,8 @@ int run_parallel_checkout(struct checkout *state, int num_workers, int threshold
 	workers = setup_workers(state, num_workers);
 	gather_results_from_workers(workers, num_workers);
 	finish_workers(workers, num_workers);
-	ret = handle_results(state);
+	ret |= handle_results(state);
+	ret |= checkout_symlink_queue(state);
 
 done:
 	finish_parallel_checkout();
diff --git a/parallel-checkout.h b/parallel-checkout.h
index 2b81a5db6c..a4f7e5b7bd 100644
--- a/parallel-checkout.h
+++ b/parallel-checkout.h
@@ -29,6 +29,14 @@ void get_parallel_checkout_configs(int *num_workers, int *threshold);
 int enqueue_checkout(struct cache_entry *ce, struct conv_attrs *ca);
 size_t pc_queue_size(void);
 
+/*
+ * Enqueues a symlink to be checked out *sequentially* after the parallel
+ * checkout finishes. This is done to avoid path collisions with leading dirs,
+ * which could make parallel workers write a file to the wrong place.
+ */
+void enqueue_symlink_checkout(struct cache_entry *ce, int *nr_checkouts);
+size_t symlink_queue_size(void);
+
 /*
  * Write all the queued entries, returning 0 on success. If the number of
  * entries is below the specified threshold, the operation is performed
diff --git a/unpack-trees.c b/unpack-trees.c
index dcb40dc8fa..01928d3d65 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -472,6 +472,7 @@ static int check_updates(struct unpack_trees_options *o,
 
 		if (ce->ce_flags & CE_UPDATE) {
 			size_t last_pc_queue_size = pc_queue_size();
+			size_t last_symlink_queue_size = symlink_queue_size();
 
 			if (ce->ce_flags & CE_WT_REMOVE)
 				BUG("both update and delete flags are set on %s",
@@ -479,7 +480,8 @@ static int check_updates(struct unpack_trees_options *o,
 			ce->ce_flags &= ~CE_UPDATE;
 			errs |= checkout_entry(ce, &state, NULL, NULL);
 
-			if (last_pc_queue_size == pc_queue_size())
+			if (last_pc_queue_size == pc_queue_size() &&
+			    last_symlink_queue_size == symlink_queue_size())
 				display_progress(progress, ++cnt);
 		}
 	}

diff --git a/entry.c b/entry.c
index 6208df23df..19f2c1d132 100644
--- a/entry.c
+++ b/entry.c
@@ -19,7 +19,7 @@ static void create_directories(const char *path, int path_len,
 		do {
 			buf[len] = path[len];
 			len++;
-		} while (len < path_len && path[len] != '/');
+		} while (len < path_len && !is_dir_sep(path[len]));
 		if (len >= path_len)
 			break;
 		buf[len] = 0;
@@ -404,7 +404,7 @@ static int check_path(const char *path, int len, struct stat *st, int skiplen)
 {
 	const char *slash = path + len;
 
-	while (path < slash && *slash != '/')
+	while (path < slash && !is_dir_sep(*slash))
 		slash--;
 	if (!has_dirs_only_path(path, slash - path, skiplen)) {
 		errno = ENOENT;

cache.h, entry.c, parallel-checkout.c, symlinks.c

diff --git a/cache.h b/cache.h
index e2b41c5f8b..7a08cd6f0e 100644
--- a/cache.h
+++ b/cache.h
@@ -1711,6 +1711,7 @@ int has_symlink_leading_path(const char *name, int len);
 int threaded_has_symlink_leading_path(struct cache_def *, const char *, int);
 int check_leading_path(const char *name, int len);
 int has_dirs_only_path(const char *name, int len, int prefix_len);
+void reset_default_lstat_cache(void);
 void schedule_dir_for_removal(const char *name, int len);
 void remove_scheduled_dirs(void);
 
diff --git a/entry.c b/entry.c
index 19f2c1d132..e876adff19 100644
--- a/entry.c
+++ b/entry.c
@@ -14,6 +14,7 @@ static void create_directories(const char *path, int path_len,
 {
 	char *buf = xmallocz(path_len);
 	int len = 0;
+	int reset_cache = 0;
 
 	while (len < path_len) {
 		do {
@@ -31,7 +32,7 @@ static void create_directories(const char *path, int path_len,
 		 * we test the path components of the prefix with the
 		 * stat() function instead of the lstat() function.
 		 */
-		if (has_dirs_only_path(buf, len, state->base_dir_len))
+		if (has_dirs_only_path(buf, len, state->base_dir_len) > 0)
 			continue; /* ok, it is already a directory. */
 
 		/*
@@ -45,8 +46,14 @@ static void create_directories(const char *path, int path_len,
 			    !unlink_or_warn(buf) && !mkdir(buf, 0777))
 				continue;
 			die_errno("cannot create directory at '%s'", buf);
+		} else {
+			/* The cache had FL_NOENT, but we now created a dir */
+			reset_cache = 1;
 		}
 	}
+
+	if (reset_cache)
+		reset_default_lstat_cache();
 	free(buf);
 }
 
@@ -406,7 +413,7 @@ static int check_path(const char *path, int len, struct stat *st, int skiplen)
 
 	while (path < slash && !is_dir_sep(*slash))
 		slash--;
-	if (!has_dirs_only_path(path, slash - path, skiplen)) {
+	if (has_dirs_only_path(path, slash - path, skiplen) <= 0) {
 		errno = ENOENT;
 		return -1;
 	}
diff --git a/parallel-checkout.c b/parallel-checkout.c
index fee93460c1..4d72540256 100644
--- a/parallel-checkout.c
+++ b/parallel-checkout.c
@@ -185,6 +185,9 @@ static int handle_results(struct checkout *state)
 
 	pc_status = PC_HANDLING_RESULTS;
 
+	/* Workers might have created dirs, so the cache must be invalidated */
+	reset_default_lstat_cache();
+
 	for (i = 0; i < parallel_checkout->nr; ++i) {
 		struct checkout_item *ci = &parallel_checkout->items[i];
 		struct stat *st = &ci->st;
diff --git a/symlinks.c b/symlinks.c
index 69d458a24d..3adf6ef8a1 100644
--- a/symlinks.c
+++ b/symlinks.c
@@ -47,6 +47,11 @@ static inline void reset_lstat_cache(struct cache_def *cache)
 	 */
 }
 
+void reset_default_lstat_cache(void)
+{
+	reset_lstat_cache(&default_cache);
+}
+
 #define FL_DIR      (1 << 0)
 #define FL_NOENT    (1 << 1)
 #define FL_SYMLINK  (1 << 2)
@@ -210,15 +215,6 @@ int has_symlink_leading_path(const char *name, int len)
 	return threaded_has_symlink_leading_path(&default_cache, name, len);
 }
 
-/*
- * Return zero if path 'name' has a leading symlink component or
- * if some leading path component does not exists.
- *
- * Return -1 if leading path exists and is a directory.
- *
- * Return path length if leading path exists and is neither a
- * directory nor a symlink.
- */
 int check_leading_path(const char *name, int len)
 {
 	return threaded_check_leading_path(&default_cache, name, len);
@@ -246,30 +242,28 @@ static int threaded_check_leading_path(struct cache_def *cache, const char *name
 		return match_len;
 }
 
-/*
- * Return non-zero if all path components of 'name' exists as a
- * directory.  If prefix_len > 0, we will test with the stat()
- * function instead of the lstat() function for a prefix length of
- * 'prefix_len', thus we then allow for symlinks in the prefix part as
- * long as those points to real existing directories.
- */
 int has_dirs_only_path(const char *name, int len, int prefix_len)
 {
 	return threaded_has_dirs_only_path(&default_cache, name, len, prefix_len);
 }
 
 /*
- * Return non-zero if all path components of 'name' exists as a
- * directory.  If prefix_len > 0, we will test with the stat()
- * function instead of the lstat() function for a prefix length of
- * 'prefix_len', thus we then allow for symlinks in the prefix part as
- * long as those points to real existing directories.
+ * Return a positive number if all path components of 'name' exist as
+ * directories, a negative number if a component does not exist, and 0 otherwise
+ * (e.g. a component exists but as another file type). If prefix_len > 0, we
+ * will test with the stat() function instead of the lstat() function for a
+ * prefix length of 'prefix_len', thus we return +1 for symlinks in the prefix
+ * part as long as those points to real existing directories.
  */
 static int threaded_has_dirs_only_path(struct cache_def *cache, const char *name, int len, int prefix_len)
 {
-	return lstat_cache(cache, name, len,
-			   FL_DIR|FL_FULLPATH, prefix_len) &
-		FL_DIR;
+	int flags = lstat_cache(cache, name, len,
+				FL_NOENT|FL_DIR|FL_FULLPATH, prefix_len);
+	if (flags & FL_DIR)
+		return 1;
+	if (flags & FL_NOENT)
+		return -1;
+	return 0;
 }
 
 static struct strbuf removal = STRBUF_INIT;

entry.c, parallel-checkout.c

diff --git a/entry.c b/entry.c
index e876adff19..5dfd4d150d 100644
--- a/entry.c
+++ b/entry.c
@@ -57,6 +57,43 @@ static void create_directories(const char *path, int path_len,
 	free(buf);
 }
 
+static void remove_non_dirs(const char *path, int path_len,
+			    const struct checkout *state)
+{
+	char *buf = xmallocz(path_len);
+	int len = 0;
+
+	while (len < path_len) {
+		int ret;
+
+		do {
+			buf[len] = path[len];
+			len++;
+		} while (len < path_len && !is_dir_sep(path[len]));
+		if (len >= path_len)
+			break;
+		buf[len] = 0;
+
+		ret = has_dirs_only_path(buf, len, state->base_dir_len);
+
+		if (ret > 0)
+			continue; /* Is directory. */
+		if (ret < 0)
+			break; /* No entry */
+
+		/* ret == 0: not a directory, let's unlink it. */
+
+		if (!state->force)
+			die("'%s' already exists, and it's not a directory", buf);
+
+		if (unlink(buf))
+			die_errno("cannot unlink '%s'", buf);
+		else
+			break;
+	}
+	free(buf);
+}
+
 static void remove_subtree(struct strbuf *path)
 {
 	DIR *dir = opendir(path->buf);
@@ -555,8 +592,6 @@ int checkout_entry_ca(struct cache_entry *ce, struct conv_attrs *ca,
 	} else if (state->not_new)
 		return 0;
 
-	create_directories(path.buf, path.len, state);
-
 	if (nr_checkouts)
 		(*nr_checkouts)++;
 
@@ -565,9 +600,13 @@ int checkout_entry_ca(struct cache_entry *ce, struct conv_attrs *ca,
 		ca = &ca_buf;
 	}
 
-	if (!enqueue_checkout(ce, ca))
+	if (!enqueue_checkout(ce, ca)) {
+		/* "clean" path so that workers can create leading dirs */
+		remove_non_dirs(path.buf, path.len, state);
 		return 0;
+	}
 
+	create_directories(path.buf, path.len, state);
 	return write_entry(ce, path.buf, ca, state, 0);
 }
 
diff --git a/parallel-checkout.c b/parallel-checkout.c
index 4d72540256..5b73d8fa4b 100644
--- a/parallel-checkout.c
+++ b/parallel-checkout.c
@@ -298,20 +298,48 @@ static int close_and_clear(int *fd)
 	return ret;
 }
 
+struct ci_open_data {
+	int fd;
+	unsigned int mode;
+};
+
+static int ci_open(const char *path, void *cb)
+{
+	struct ci_open_data *data = cb;
+	data->fd = open(path, O_WRONLY | O_CREAT | O_EXCL, data->mode);
+
+	if (data->fd < 0) {
+		/*
+		 * EISDIR can only indicate path collisions among the entries
+		 * being checked out. We don't need raceproof_create_file() to
+		 * try removing empty dirs. Instead, just let the caller known
+		 * that the path already exists, so that the collision can be
+		 * properly handled later.
+		 */
+		if (errno == EISDIR)
+			errno = EEXIST;
+		return 1;
+	}
+
+	return 0;
+}
+
 void write_checkout_item(struct checkout *state, struct checkout_item *ci)
 {
-	unsigned int mode = (ci->ce->ce_mode & 0100) ? 0777 : 0666;
+	struct ci_open_data open_data;
 	int fd = -1, fstat_done = 0;
 	struct strbuf path = STRBUF_INIT;
 
+	open_data.mode = (ci->ce->ce_mode & 0100) ? 0777 : 0666;
 	strbuf_add(&path, state->base_dir, state->base_dir_len);
 	strbuf_add(&path, ci->ce->name, ci->ce->ce_namelen);
 
-	fd = open(path.buf, O_WRONLY | O_CREAT | O_EXCL, mode);
-
-	if (fd < 0) {
-		if (errno == EEXIST || errno == EISDIR || errno == ENOENT ||
-		    errno == ENOTDIR) {
+	/*
+	 * The main process already removed any non-directory file that was in
+	 * the way. So if we find one, it's a path collision.
+	 */
+	if (raceproof_create_file(path.buf, ci_open, &open_data)) {
+		if (errno == EEXIST || errno == ENOTDIR || errno == ENOENT) {
 			/*
 			 * Errors which probably represent a path collision.
 			 * Suppress the error message and mark the ci to be
@@ -325,6 +353,8 @@ void write_checkout_item(struct checkout *state, struct checkout_item *ci)
 		goto out;
 	}
 
+	fd = open_data.fd;
+
 	if (write_checkout_item_to_fd(fd, state, ci, path.buf)) {
 		/* Error was already reported. */
 		ci->status = CI_FAILED;

diff --git a/entry.c b/entry.c
index 5dfd4d150d..8c03e23811 100644
--- a/entry.c
+++ b/entry.c
@@ -513,12 +513,24 @@ int checkout_entry_ca(struct cache_entry *ce, struct conv_attrs *ca,
 		return 0;
 	}
 
-	if (topath) {
+	if (topath || state->clone) {
 		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);
+		if (topath)
+			return write_entry(ce, topath, ca, state, 1);
+		/*
+		 * Since we are cloning, there should be no previous files in
+		 * the working tree. So we can skip calling remove_non_dirs()
+		 * and check_path(). (parallel-checkout.c will take care of path
+		 * collision.)
+		 */
+		if (!enqueue_checkout(ce, ca)) {
+			if (nr_checkouts)
+				(*nr_checkouts)++;
+			return 0;
+		}
 	}
 
 	/*

convert.c, convert.h

diff --git a/convert.c b/convert.c
index 8e6c292421..941a845692 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;
@@ -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;
 
diff --git a/convert.h b/convert.h
index e29d1026a6..aeb4a1be9a 100644
--- a/convert.h
+++ b/convert.h
@@ -37,6 +37,27 @@ enum eol {
 #endif
 };
 
+enum 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 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 */
+};
+
 enum ce_delay_state {
 	CE_NO_DELAY = 0,
 	CE_CAN_DELAY = 1,
@@ -102,6 +123,9 @@ void convert_to_git_filter_fd(const struct index_state *istate,
 int would_convert_to_git_filter_fd(const struct index_state *istate,
 				   const char *path);
 
+void convert_attrs(const struct index_state *istate,
+		   struct conv_attrs *ca, const char *path);
+
 /*
  * Initialize the checkout metadata with the given values.  Any argument may be
  * NULL if it is not applicable.  The treeish should be a commit if that is

convert.c, convert.h

diff --git a/convert.c b/convert.c
index 55bcce891c..c112ea23cb 100644
--- a/convert.c
+++ b/convert.c
@@ -1960,34 +1960,31 @@ 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))
+	if (ca->drv && (ca->drv->process || ca->drv->smudge || ca->drv->clean))
 		return NULL;
 
-	if (ca.working_tree_encoding)
+	if (ca->working_tree_encoding)
 		return NULL;
 
-	if (ca.crlf_action == CRLF_AUTO || ca.crlf_action == CRLF_AUTO_CRLF)
+	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);
@@ -1995,6 +1992,15 @@ 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);
diff --git a/convert.h b/convert.h
index 46d537d1ae..262c1a1d46 100644
--- a/convert.h
+++ b/convert.h
@@ -169,6 +169,8 @@ 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 *);
 

convert.c, convert.h

diff --git a/convert.c b/convert.c
index 941a845692..55bcce891c 100644
--- a/convert.c
+++ b/convert.c
@@ -1447,7 +1447,7 @@ 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,
+static int convert_to_working_tree_internal(const struct conv_attrs *ca,
 					    const char *path, const char *src,
 					    size_t len, struct strbuf *dst,
 					    int normalizing,
@@ -1455,11 +1455,8 @@ static int convert_to_working_tree_internal(const struct index_state *istate,
 					    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;
@@ -1469,24 +1466,24 @@ 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;
 }
@@ -1497,7 +1494,9 @@ int async_convert_to_working_tree(const struct index_state *istate,
 				  const struct checkout_metadata *meta,
 				  void *dco)
 {
-	return convert_to_working_tree_internal(istate, path, src, len, dst, 0, meta, dco);
+	struct conv_attrs ca;
+	convert_attrs(istate, &ca, path);
+	return convert_to_working_tree_internal(&ca, path, src, len, dst, 0, meta, dco);
 }
 
 int convert_to_working_tree(const struct index_state *istate,
@@ -1505,13 +1504,36 @@ int convert_to_working_tree(const struct index_state *istate,
 			    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);
+	struct conv_attrs ca;
+	convert_attrs(istate, &ca, path);
+	return convert_to_working_tree_internal(&ca, path, src, len, dst, 0, meta, NULL);
+}
+
+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(ca, path, src, len, dst, 0, meta, 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)
+{
+	return convert_to_working_tree_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_internal(&ca, path, src, len, dst, 1, NULL, NULL);
 	if (ret) {
 		src = dst->buf;
 		len = dst->len;
diff --git a/convert.h b/convert.h
index aeb4a1be9a..46d537d1ae 100644
--- a/convert.h
+++ b/convert.h
@@ -100,11 +100,20 @@ 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);
 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);
 int async_query_available_blobs(const char *cmd,
 				struct string_list *available_paths);
 int renormalize_buffer(const struct index_state *istate,

convert.c, convert.h

diff --git a/convert.c b/convert.c
index c112ea23cb..633ad6976a 100644
--- a/convert.c
+++ b/convert.c
@@ -1972,13 +1972,7 @@ struct stream_filter *get_stream_filter_ca(const struct conv_attrs *ca,
 {
 	struct stream_filter *filter = NULL;
 
-	if (ca->drv && (ca->drv->process || ca->drv->smudge || ca->drv->clean))
-		return NULL;
-
-	if (ca->working_tree_encoding)
-		return NULL;
-
-	if (ca->crlf_action == CRLF_AUTO || ca->crlf_action == CRLF_AUTO_CRLF)
+	if (classify_conv_attrs(ca) != CA_CLASS_STREAMABLE)
 		return NULL;
 
 	if (ca->ident)
@@ -2034,3 +2028,21 @@ 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 262c1a1d46..523ba9b140 100644
--- a/convert.h
+++ b/convert.h
@@ -190,4 +190,37 @@ 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 */

apply.c, builtin/checkout-index.c, builtin/checkout.c, builtin/difftool.c, cache.h, entry.c, entry.h, unpack-trees.c

diff --git a/apply.c b/apply.c
index 76dba93c97..ddec80b4b0 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 a854fd16e7..0f1ff73129 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 0951f8fee5..b18b9d6f3c 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 7ac432b881..dfa22b67eb 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/cache.h b/cache.h
index cee8aa5dc3..17350cafa2 100644
--- a/cache.h
+++ b/cache.h
@@ -1706,30 +1706,6 @@ 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/entry.c b/entry.c
index a0532f1f00..b0b8099699 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)
@@ -429,14 +430,6 @@ 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)
 {
diff --git a/entry.h b/entry.h
new file mode 100644
index 0000000000..2d69185448
--- /dev/null
+++ b/entry.h
@@ -0,0 +1,41 @@
+#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.
+ */
+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);
+
+#endif /* ENTRY_H */
diff --git a/unpack-trees.c b/unpack-trees.c
index 323280dd48..a511fadd89 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

entry.c, entry.h

diff --git a/entry.c b/entry.c
index b0b8099699..b36071a610 100644
--- a/entry.c
+++ b/entry.c
@@ -84,7 +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);
@@ -109,7 +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() &&
@@ -132,7 +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)
@@ -346,7 +346,7 @@ 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)
diff --git a/entry.h b/entry.h
index 2d69185448..f860e60846 100644
--- a/entry.h
+++ b/entry.h
@@ -37,5 +37,7 @@ int finish_delayed_checkout(struct checkout *state, int *nr_checkouts);
  * 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);
 
 #endif /* ENTRY_H */

entry.c, entry.h

diff --git a/entry.c b/entry.c
index b36071a610..1d2df188e5 100644
--- a/entry.c
+++ b/entry.c
@@ -251,6 +251,18 @@ int finish_delayed_checkout(struct checkout *state, int *nr_checkouts)
 	return errs;
 }
 
+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;
+	}
+}
+
 static int write_entry(struct cache_entry *ce,
 		       char *path, const struct checkout *state, int to_tempfile)
 {
@@ -371,15 +383,10 @@ 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;
diff --git a/entry.h b/entry.h
index f860e60846..664aed1576 100644
--- a/entry.h
+++ b/entry.h
@@ -39,5 +39,7 @@ int finish_delayed_checkout(struct checkout *state, int *nr_checkouts);
 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/entry.c b/entry.c
index 1d2df188e5..8237859b12 100644
--- a/entry.c
+++ b/entry.c
@@ -263,8 +263,9 @@ void update_ce_after_write(const struct checkout *state, struct cache_entry *ce,
 	}
 }
 
-static int write_entry(struct cache_entry *ce,
-		       char *path, const struct checkout *state, int to_tempfile)
+/* 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;
@@ -281,8 +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,
@@ -329,14 +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);
@@ -442,6 +445,7 @@ int checkout_entry(struct cache_entry *ce, const struct checkout *state,
 {
 	static struct strbuf path = STRBUF_INIT;
 	struct stat st;
+	struct conv_attrs ca;
 
 	if (ce->ce_flags & CE_WT_REMOVE) {
 		if (topath)
@@ -454,8 +458,13 @@ 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)) {
+			convert_attrs(state->istate, &ca, ce->name);
+			return write_entry(ce, topath, &ca, state, 1);
+		}
+		return write_entry(ce, topath, NULL, state, 1);
+	}
 
 	strbuf_reset(&path);
 	strbuf_add(&path, state->base_dir, state->base_dir_len);
@@ -517,9 +526,16 @@ 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)) {
+		convert_attrs(state->istate, &ca, ce->name);
+		return write_entry(ce, path.buf, &ca, state, 0);
+	}
+
+	return write_entry(ce, path.buf, NULL, state, 0);
 }
 
 void unlink_entry(const struct cache_entry *ce)

entry.c, entry.h

diff --git a/entry.c b/entry.c
index 8237859b12..9d79a5671f 100644
--- a/entry.c
+++ b/entry.c
@@ -440,12 +440,13 @@ static void mark_colliding_entries(const struct checkout *state,
 	}
 }
 
-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;
+	struct conv_attrs ca_buf;
 
 	if (ce->ce_flags & CE_WT_REMOVE) {
 		if (topath)
@@ -459,11 +460,11 @@ int checkout_entry(struct cache_entry *ce, const struct checkout *state,
 	}
 
 	if (topath) {
-		if (S_ISREG(ce->ce_mode)) {
-			convert_attrs(state->istate, &ca, ce->name);
-			return write_entry(ce, topath, &ca, state, 1);
+		if (S_ISREG(ce->ce_mode) && !ca) {
+			convert_attrs(state->istate, &ca_buf, ce->name);
+			ca = &ca_buf;
 		}
-		return write_entry(ce, topath, NULL, state, 1);
+		return write_entry(ce, topath, ca, state, 1);
 	}
 
 	strbuf_reset(&path);
@@ -530,12 +531,12 @@ int checkout_entry(struct cache_entry *ce, const struct checkout *state,
 	if (nr_checkouts)
 		(*nr_checkouts)++;
 
-	if (S_ISREG(ce->ce_mode)) {
-		convert_attrs(state->istate, &ca, ce->name);
-		return write_entry(ce, path.buf, &ca, 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, NULL, state, 0);
+	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
index 664aed1576..2081fbbbab 100644
--- a/entry.h
+++ b/entry.h
@@ -27,9 +27,18 @@ struct checkout {
  * 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(struct cache_entry *ce, const struct checkout *state,
-		   char *topath, int *nr_checkouts);
+#define checkout_entry(ce, state, topath, nr_checkouts) \
+		checkout_entry_ca(ce, NULL, state, topath, nr_checkouts)
+int checkout_entry_ca(struct cache_entry *ce, struct conv_attrs *ca,
+		      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);
 /*

Makefile, entry.c, parallel-checkout.c, parallel-checkout.h, unpack-trees.c

diff --git a/Makefile b/Makefile
index f1b1bc8aa0..3edcdc534c 100644
--- a/Makefile
+++ b/Makefile
@@ -932,6 +932,7 @@ LIB_OBJS += pack-revindex.o
 LIB_OBJS += pack-write.o
 LIB_OBJS += packfile.o
 LIB_OBJS += pager.o
+LIB_OBJS += parallel-checkout.o
 LIB_OBJS += parse-options-cb.o
 LIB_OBJS += parse-options.o
 LIB_OBJS += patch-delta.o
diff --git a/entry.c b/entry.c
index 9d79a5671f..6676954431 100644
--- a/entry.c
+++ b/entry.c
@@ -7,6 +7,7 @@
 #include "progress.h"
 #include "fsmonitor.h"
 #include "entry.h"
+#include "parallel-checkout.h"
 
 static void create_directories(const char *path, int path_len,
 			       const struct checkout *state)
@@ -426,8 +427,17 @@ static void mark_colliding_entries(const struct checkout *state,
 	for (i = 0; i < state->istate->cache_nr; i++) {
 		struct cache_entry *dup = state->istate->cache[i];
 
-		if (dup == ce)
-			break;
+		if (dup == ce) {
+			/*
+			 * Parallel checkout creates the files in no particular
+			 * order. So the other side of the collision may appear
+			 * after the given cache_entry in the array.
+			 */
+			if (parallel_checkout_status() == PC_RUNNING)
+				continue;
+			else
+				break;
+		}
 
 		if (dup->ce_flags & (CE_MATCHED | CE_VALID | CE_SKIP_WORKTREE))
 			continue;
@@ -536,6 +546,9 @@ int checkout_entry_ca(struct cache_entry *ce, struct conv_attrs *ca,
 		ca = &ca_buf;
 	}
 
+	if (!enqueue_checkout(ce, ca))
+		return 0;
+
 	return write_entry(ce, path.buf, ca, state, 0);
 }
 
diff --git a/parallel-checkout.c b/parallel-checkout.c
new file mode 100644
index 0000000000..7dc8ab2a67
--- /dev/null
+++ b/parallel-checkout.c
@@ -0,0 +1,368 @@
+#include "cache.h"
+#include "entry.h"
+#include "parallel-checkout.h"
+#include "streaming.h"
+
+enum pc_item_status {
+	PC_ITEM_PENDING = 0,
+	PC_ITEM_WRITTEN,
+	/*
+	 * The entry could not be written because there was another file
+	 * already present in its path or leading directories. Since
+	 * checkout_entry_ca() removes such files from the working tree before
+	 * enqueueing the entry for parallel checkout, it means that there was
+	 * a path collision among the entries being written.
+	 */
+	PC_ITEM_COLLIDED,
+	PC_ITEM_FAILED,
+};
+
+struct parallel_checkout_item {
+	/* pointer to a istate->cache[] entry. Not owned by us. */
+	struct cache_entry *ce;
+	struct conv_attrs ca;
+	struct stat st;
+	enum pc_item_status status;
+};
+
+struct parallel_checkout {
+	enum pc_status status;
+	struct parallel_checkout_item *items;
+	size_t nr, alloc;
+};
+
+static struct parallel_checkout parallel_checkout = { 0 };
+
+enum pc_status parallel_checkout_status(void)
+{
+	return parallel_checkout.status;
+}
+
+void init_parallel_checkout(void)
+{
+	if (parallel_checkout.status != PC_UNINITIALIZED)
+		BUG("parallel checkout already initialized");
+
+	parallel_checkout.status = PC_ACCEPTING_ENTRIES;
+}
+
+static void finish_parallel_checkout(void)
+{
+	if (parallel_checkout.status == PC_UNINITIALIZED)
+		BUG("cannot finish parallel checkout: not initialized yet");
+
+	free(parallel_checkout.items);
+	memset(&parallel_checkout, 0, sizeof(parallel_checkout));
+}
+
+static int is_eligible_for_parallel_checkout(const struct cache_entry *ce,
+					     const struct conv_attrs *ca)
+{
+	enum conv_attrs_classification c;
+
+	if (!S_ISREG(ce->ce_mode))
+		return 0;
+
+	c = classify_conv_attrs(ca);
+	switch (c) {
+	case CA_CLASS_INCORE:
+		return 1;
+
+	case CA_CLASS_INCORE_FILTER:
+		/*
+		 * It would be safe to allow concurrent instances of
+		 * single-file smudge filters, like rot13, but we should not
+		 * assume that all filters are parallel-process safe. So we
+		 * don't allow this.
+		 */
+		return 0;
+
+	case CA_CLASS_INCORE_PROCESS:
+		/*
+		 * The parallel queue and the delayed queue are not compatible,
+		 * so they must be kept completely separated. And we can't tell
+		 * if a long-running process will delay its response without
+		 * actually asking it to perform the filtering. Therefore, this
+		 * type of filter is not allowed in parallel checkout.
+		 *
+		 * Furthermore, there should only be one instance of the
+		 * long-running process filter as we don't know how it is
+		 * managing its own concurrency. So, spreading the entries that
+		 * requisite such a filter among the parallel workers would
+		 * require a lot more inter-process communication. We would
+		 * probably have to designate a single process to interact with
+		 * the filter and send all the necessary data to it, for each
+		 * entry.
+		 */
+		return 0;
+
+	case CA_CLASS_STREAMABLE:
+		return 1;
+
+	default:
+		BUG("unsupported conv_attrs classification '%d'", c);
+	}
+}
+
+int enqueue_checkout(struct cache_entry *ce, struct conv_attrs *ca)
+{
+	struct parallel_checkout_item *pc_item;
+
+	if (parallel_checkout.status != PC_ACCEPTING_ENTRIES ||
+	    !is_eligible_for_parallel_checkout(ce, ca))
+		return -1;
+
+	ALLOC_GROW(parallel_checkout.items, parallel_checkout.nr + 1,
+		   parallel_checkout.alloc);
+
+	pc_item = &parallel_checkout.items[parallel_checkout.nr++];
+	pc_item->ce = ce;
+	memcpy(&pc_item->ca, ca, sizeof(pc_item->ca));
+	pc_item->status = PC_ITEM_PENDING;
+
+	return 0;
+}
+
+static int handle_results(struct checkout *state)
+{
+	int ret = 0;
+	size_t i;
+	int have_pending = 0;
+
+	/*
+	 * We first update the successfully written entries with the collected
+	 * stat() data, so that they can be found by mark_colliding_entries(),
+	 * in the next loop, when necessary.
+	 */
+	for (i = 0; i < parallel_checkout.nr; ++i) {
+		struct parallel_checkout_item *pc_item = &parallel_checkout.items[i];
+		if (pc_item->status == PC_ITEM_WRITTEN)
+			update_ce_after_write(state, pc_item->ce, &pc_item->st);
+	}
+
+	for (i = 0; i < parallel_checkout.nr; ++i) {
+		struct parallel_checkout_item *pc_item = &parallel_checkout.items[i];
+
+		switch(pc_item->status) {
+		case PC_ITEM_WRITTEN:
+			/* Already handled */
+			break;
+		case PC_ITEM_COLLIDED:
+			/*
+			 * The entry could not be checked out due to a path
+			 * collision with another entry. Since there can only
+			 * be one entry of each colliding group on the disk, we
+			 * could skip trying to check out this one and move on.
+			 * However, this would leave the unwritten entries with
+			 * null stat() fields on the index, which could
+			 * potentially slow down subsequent operations that
+			 * require refreshing it: git would not be able to
+			 * trust st_size and would have to go to the filesystem
+			 * to see if the contents match (see ie_modified()).
+			 *
+			 * Instead, let's pay the overhead only once, now, and
+			 * call checkout_entry_ca() again for this file, to
+			 * have it's stat() data stored in the index. This also
+			 * has the benefit of adding this entry and its
+			 * colliding pair to the collision report message.
+			 * Additionally, this overwriting behavior is consistent
+			 * with what the sequential checkout does, so it doesn't
+			 * add any extra overhead.
+			 */
+			ret |= checkout_entry_ca(pc_item->ce, &pc_item->ca,
+						 state, NULL, NULL);
+			break;
+		case PC_ITEM_PENDING:
+			have_pending = 1;
+			/* fall through */
+		case PC_ITEM_FAILED:
+			ret = -1;
+			break;
+		default:
+			BUG("unknown checkout item status in parallel checkout");
+		}
+	}
+
+	if (have_pending)
+		error(_("parallel checkout finished with pending entries"));
+
+	return ret;
+}
+
+static int reset_fd(int fd, const char *path)
+{
+	if (lseek(fd, 0, SEEK_SET) != 0)
+		return error_errno("failed to rewind descriptor of %s", path);
+	if (ftruncate(fd, 0))
+		return error_errno("failed to truncate file %s", path);
+	return 0;
+}
+
+static int write_pc_item_to_fd(struct parallel_checkout_item *pc_item, int fd,
+			       const char *path, struct checkout *state)
+{
+	int ret;
+	struct stream_filter *filter;
+	struct strbuf buf = STRBUF_INIT;
+	char *new_blob;
+	unsigned long size;
+	size_t newsize = 0;
+	ssize_t wrote;
+
+	/* Sanity check */
+	assert(is_eligible_for_parallel_checkout(pc_item->ce, &pc_item->ca));
+
+	filter = get_stream_filter_ca(&pc_item->ca, &pc_item->ce->oid);
+	if (filter) {
+		if (stream_blob_to_fd(fd, &pc_item->ce->oid, filter, 1)) {
+			/* On error, reset fd to try writing without streaming */
+			if (reset_fd(fd, path))
+				return -1;
+		} else {
+			return 0;
+		}
+	}
+
+	new_blob = read_blob_entry(pc_item->ce, &size);
+	if (!new_blob)
+		return error("unable to read sha1 file of %s (%s)", path,
+			     oid_to_hex(&pc_item->ce->oid));
+
+	/*
+	 * checkout metadata is used to give context for external process
+	 * filters. Files requiring such filters are not eligible for parallel
+	 * checkout, so pass NULL.
+	 */
+	ret = convert_to_working_tree_ca(&pc_item->ca, pc_item->ce->name,
+					 new_blob, size, &buf, NULL);
+
+	if (ret) {
+		free(new_blob);
+		new_blob = strbuf_detach(&buf, &newsize);
+		size = newsize;
+	}
+
+	wrote = write_in_full(fd, new_blob, size);
+	free(new_blob);
+	if (wrote < 0)
+		return error("unable to write file %s", path);
+
+	return 0;
+}
+
+static int close_and_clear(int *fd)
+{
+	int ret = 0;
+
+	if (*fd >= 0) {
+		ret = close(*fd);
+		*fd = -1;
+	}
+
+	return ret;
+}
+
+static int check_leading_dirs(const char *path, int len, int prefix_len)
+{
+	const char *slash = path + len;
+
+	while (slash > path && *slash != '/')
+		slash--;
+
+	return has_dirs_only_path(path, slash - path, prefix_len);
+}
+
+static void write_pc_item(struct parallel_checkout_item *pc_item,
+			  struct checkout *state)
+{
+	unsigned int mode = (pc_item->ce->ce_mode & 0100) ? 0777 : 0666;
+	int fd = -1, fstat_done = 0;
+	struct strbuf path = STRBUF_INIT;
+
+	strbuf_add(&path, state->base_dir, state->base_dir_len);
+	strbuf_add(&path, pc_item->ce->name, pc_item->ce->ce_namelen);
+
+	/*
+	 * At this point, leading dirs should have already been created. But if
+	 * a symlink being checked out has collided with one of the dirs, due to
+	 * file system folding rules, it's possible that the dirs are no longer
+	 * present. So we have to check again, and report any path collisions.
+	 */
+	if (!check_leading_dirs(path.buf, path.len, state->base_dir_len)) {
+		pc_item->status = PC_ITEM_COLLIDED;
+		goto out;
+	}
+
+	fd = open(path.buf, O_WRONLY | O_CREAT | O_EXCL, mode);
+
+	if (fd < 0) {
+		if (errno == EEXIST || errno == EISDIR) {
+			/*
+			 * Errors which probably represent a path collision.
+			 * Suppress the error message and mark the item to be
+			 * retried later, sequentially. ENOTDIR and ENOENT are
+			 * also interesting, but check_leading_dirs() should
+			 * have already caught these cases.
+			 */
+			pc_item->status = PC_ITEM_COLLIDED;
+		} else {
+			error_errno("failed to open file %s", path.buf);
+			pc_item->status = PC_ITEM_FAILED;
+		}
+		goto out;
+	}
+
+	if (write_pc_item_to_fd(pc_item, fd, path.buf, state)) {
+		/* Error was already reported. */
+		pc_item->status = PC_ITEM_FAILED;
+		goto out;
+	}
+
+	fstat_done = fstat_checkout_output(fd, state, &pc_item->st);
+
+	if (close_and_clear(&fd)) {
+		error_errno("unable to close file %s", path.buf);
+		pc_item->status = PC_ITEM_FAILED;
+		goto out;
+	}
+
+	if (state->refresh_cache && !fstat_done && lstat(path.buf, &pc_item->st) < 0) {
+		error_errno("unable to stat just-written file %s",  path.buf);
+		pc_item->status = PC_ITEM_FAILED;
+		goto out;
+	}
+
+	pc_item->status = PC_ITEM_WRITTEN;
+
+out:
+	/*
+	 * No need to check close() return. At this point, either fd is already
+	 * closed, or we are on an error path, that has already been reported.
+	 */
+	close_and_clear(&fd);
+	strbuf_release(&path);
+}
+
+static void write_items_sequentially(struct checkout *state)
+{
+	size_t i;
+
+	for (i = 0; i < parallel_checkout.nr; ++i)
+		write_pc_item(&parallel_checkout.items[i], state);
+}
+
+int run_parallel_checkout(struct checkout *state)
+{
+	int ret;
+
+	if (parallel_checkout.status != PC_ACCEPTING_ENTRIES)
+		BUG("cannot run parallel checkout: uninitialized or already running");
+
+	parallel_checkout.status = PC_RUNNING;
+
+	write_items_sequentially(state);
+	ret = handle_results(state);
+
+	finish_parallel_checkout();
+	return ret;
+}
diff --git a/parallel-checkout.h b/parallel-checkout.h
new file mode 100644
index 0000000000..e6d6fc01ea
--- /dev/null
+++ b/parallel-checkout.h
@@ -0,0 +1,27 @@
+#ifndef PARALLEL_CHECKOUT_H
+#define PARALLEL_CHECKOUT_H
+
+struct cache_entry;
+struct checkout;
+struct conv_attrs;
+
+enum pc_status {
+	PC_UNINITIALIZED = 0,
+	PC_ACCEPTING_ENTRIES,
+	PC_RUNNING,
+};
+
+enum pc_status parallel_checkout_status(void);
+void init_parallel_checkout(void);
+
+/*
+ * Return -1 if parallel checkout is currently not enabled or if the entry is
+ * not eligible for parallel checkout. Otherwise, enqueue the entry for later
+ * write and return 0.
+ */
+int enqueue_checkout(struct cache_entry *ce, struct conv_attrs *ca);
+
+/* Write all the queued entries, returning 0 on success.*/
+int run_parallel_checkout(struct checkout *state);
+
+#endif /* PARALLEL_CHECKOUT_H */
diff --git a/unpack-trees.c b/unpack-trees.c
index a511fadd89..1b1da7485a 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -17,6 +17,7 @@
 #include "object-store.h"
 #include "promisor-remote.h"
 #include "entry.h"
+#include "parallel-checkout.h"
 
 /*
  * Error messages expected by scripts out of plumbing commands such as
@@ -438,7 +439,6 @@ static int check_updates(struct unpack_trees_options *o,
 	if (should_update_submodules())
 		load_gitmodules_file(index, &state);
 
-	enable_delayed_checkout(&state);
 	if (has_promisor_remote()) {
 		/*
 		 * Prefetch the objects that are to be checked out in the loop
@@ -461,6 +461,9 @@ static int check_updates(struct unpack_trees_options *o,
 					   to_fetch.oid, to_fetch.nr);
 		oid_array_clear(&to_fetch);
 	}
+
+	enable_delayed_checkout(&state);
+	init_parallel_checkout();
 	for (i = 0; i < index->cache_nr; i++) {
 		struct cache_entry *ce = index->cache[i];
 
@@ -474,6 +477,7 @@ static int check_updates(struct unpack_trees_options *o,
 		}
 	}
 	stop_progress(&progress);
+	errs |= run_parallel_checkout(&state);
 	errs |= finish_delayed_checkout(&state, NULL);
 	git_attr_set_direction(GIT_ATTR_CHECKIN);
 

diff --git a/parallel-checkout.c b/parallel-checkout.c
index 94b44d2a48..d077618719 100644
--- a/parallel-checkout.c
+++ b/parallel-checkout.c
@@ -233,7 +233,7 @@ static int reset_fd(int fd, const char *path)
 }
 
 static int write_pc_item_to_fd(struct parallel_checkout_item *pc_item, int fd,
-			       const char *path, struct checkout *state)
+			       const char *path)
 {
 	int ret;
 	struct stream_filter *filter;
@@ -347,7 +347,7 @@ void write_pc_item(struct parallel_checkout_item *pc_item,
 		goto out;
 	}
 
-	if (write_pc_item_to_fd(pc_item, fd, path.buf, state)) {
+	if (write_pc_item_to_fd(pc_item, fd, path.buf)) {
 		/* Error was already reported. */
 		pc_item->status = PC_ITEM_FAILED;
 		goto out;

.gitignore, Documentation/config/checkout.txt, Makefile, builtin.h, builtin/checkout--helper.c, git.c, parallel-checkout.c, parallel-checkout.h, unpack-trees.c

diff --git a/.gitignore b/.gitignore
index d0f692a355..6427739814 100644
--- a/.gitignore
+++ b/.gitignore
@@ -33,6 +33,7 @@
 /git-check-mailmap
 /git-check-ref-format
 /git-checkout
+/git-checkout--helper
 /git-checkout-index
 /git-cherry
 /git-cherry-pick
diff --git a/Documentation/config/checkout.txt b/Documentation/config/checkout.txt
index 6b646813ab..44eb58bcd3 100644
--- a/Documentation/config/checkout.txt
+++ b/Documentation/config/checkout.txt
@@ -16,3 +16,24 @@ will checkout the '<something>' branch on another remote,
 and by linkgit:git-worktree[1] when 'git worktree add' refers to a
 remote branch. This setting might be used for other checkout-like
 commands or functionality in the future.
+
+checkout.workers::
+	The number of parallel workers to use when updating the working tree.
+	The default is one, i.e. sequential execution. If set to a value less
+	than one, Git will use as many workers as the number of logical cores
+	available. This setting and checkout.thresholdForParallelism affect all
+	commands that perform checkout. E.g. checkout, switch, clone, reset,
+	sparse-checkout, read-tree, etc.
++
+Note: parallel checkout usually delivers better performance for repositories
+located on SSDs or over NFS. For repositories on spinning disks and/or machines
+with a small number of cores, the default sequential checkout often performs
+better. The size and compression level of a repository might also influence how
+well the parallel version performs.
+
+checkout.thresholdForParallelism::
+	When running parallel checkout with a small number of files, the cost
+	of subprocess spawning and inter-process communication might outweigh
+	the parallelization gains. This setting allows to define the minimum
+	number of files for which parallel checkout should be attempted. The
+	default is 100.
diff --git a/Makefile b/Makefile
index 3edcdc534c..e9c6616180 100644
--- a/Makefile
+++ b/Makefile
@@ -1049,6 +1049,7 @@ BUILTIN_OBJS += builtin/check-attr.o
 BUILTIN_OBJS += builtin/check-ignore.o
 BUILTIN_OBJS += builtin/check-mailmap.o
 BUILTIN_OBJS += builtin/check-ref-format.o
+BUILTIN_OBJS += builtin/checkout--helper.o
 BUILTIN_OBJS += builtin/checkout-index.o
 BUILTIN_OBJS += builtin/checkout.o
 BUILTIN_OBJS += builtin/clean.o
diff --git a/builtin.h b/builtin.h
index ba954e180c..b52243848d 100644
--- a/builtin.h
+++ b/builtin.h
@@ -123,6 +123,7 @@ int cmd_bugreport(int argc, const char **argv, const char *prefix);
 int cmd_bundle(int argc, const char **argv, const char *prefix);
 int cmd_cat_file(int argc, const char **argv, const char *prefix);
 int cmd_checkout(int argc, const char **argv, const char *prefix);
+int cmd_checkout__helper(int argc, const char **argv, const char *prefix);
 int cmd_checkout_index(int argc, const char **argv, const char *prefix);
 int cmd_check_attr(int argc, const char **argv, const char *prefix);
 int cmd_check_ignore(int argc, const char **argv, const char *prefix);
diff --git a/builtin/checkout--helper.c b/builtin/checkout--helper.c
new file mode 100644
index 0000000000..67fe37cf11
--- /dev/null
+++ b/builtin/checkout--helper.c
@@ -0,0 +1,142 @@
+#include "builtin.h"
+#include "config.h"
+#include "entry.h"
+#include "parallel-checkout.h"
+#include "parse-options.h"
+#include "pkt-line.h"
+
+static void packet_to_pc_item(char *line, int len,
+			      struct parallel_checkout_item *pc_item)
+{
+	struct pc_item_fixed_portion *fixed_portion;
+	char *encoding, *variant;
+
+	if (len < sizeof(struct pc_item_fixed_portion))
+		BUG("checkout worker received too short item (got %dB, exp %dB)",
+		    len, (int)sizeof(struct pc_item_fixed_portion));
+
+	fixed_portion = (struct pc_item_fixed_portion *)line;
+
+	if (len - sizeof(struct pc_item_fixed_portion) !=
+		fixed_portion->name_len + fixed_portion->working_tree_encoding_len)
+		BUG("checkout worker received corrupted item");
+
+	variant = line + sizeof(struct pc_item_fixed_portion);
+
+	/*
+	 * Note: the main process uses zero length to communicate that the
+	 * encoding is NULL. There is no use case in actually sending an empty
+	 * string since it's considered as NULL when ca.working_tree_encoding
+	 * is set at git_path_check_encoding().
+	 */
+	if (fixed_portion->working_tree_encoding_len) {
+		encoding = xmemdupz(variant,
+				    fixed_portion->working_tree_encoding_len);
+		variant += fixed_portion->working_tree_encoding_len;
+	} else {
+		encoding = NULL;
+	}
+
+	memset(pc_item, 0, sizeof(*pc_item));
+	pc_item->ce = make_empty_transient_cache_entry(fixed_portion->name_len);
+	pc_item->ce->ce_namelen = fixed_portion->name_len;
+	pc_item->ce->ce_mode = fixed_portion->ce_mode;
+	memcpy(pc_item->ce->name, variant, pc_item->ce->ce_namelen);
+	oidcpy(&pc_item->ce->oid, &fixed_portion->oid);
+
+	pc_item->id = fixed_portion->id;
+	pc_item->ca.crlf_action = fixed_portion->crlf_action;
+	pc_item->ca.ident = fixed_portion->ident;
+	pc_item->ca.working_tree_encoding = encoding;
+}
+
+static void report_result(struct parallel_checkout_item *pc_item)
+{
+	struct pc_item_result res = { 0 };
+	size_t size;
+
+	res.id = pc_item->id;
+	res.status = pc_item->status;
+
+	if (pc_item->status == PC_ITEM_WRITTEN) {
+		res.st = pc_item->st;
+		size = sizeof(res);
+	} else {
+		size = PC_ITEM_RESULT_BASE_SIZE;
+	}
+
+	packet_write(1, (const char *)&res, size);
+}
+
+/* Free the worker-side malloced data, but not pc_item itself. */
+static void release_pc_item_data(struct parallel_checkout_item *pc_item)
+{
+	free((char *)pc_item->ca.working_tree_encoding);
+	discard_cache_entry(pc_item->ce);
+}
+
+static void worker_loop(struct checkout *state)
+{
+	struct parallel_checkout_item *items = NULL;
+	size_t i, nr = 0, alloc = 0;
+
+	while (1) {
+		int len;
+		char *line = packet_read_line(0, &len);
+
+		if (!line)
+			break;
+
+		ALLOC_GROW(items, nr + 1, alloc);
+		packet_to_pc_item(line, len, &items[nr++]);
+	}
+
+	for (i = 0; i < nr; ++i) {
+		struct parallel_checkout_item *pc_item = &items[i];
+		write_pc_item(pc_item, state);
+		report_result(pc_item);
+		release_pc_item_data(pc_item);
+	}
+
+	packet_flush(1);
+
+	free(items);
+}
+
+static const char * const checkout_helper_usage[] = {
+	N_("git checkout--helper [<options>]"),
+	NULL
+};
+
+int cmd_checkout__helper(int argc, const char **argv, const char *prefix)
+{
+	struct checkout state = CHECKOUT_INIT;
+	struct option checkout_helper_options[] = {
+		OPT_STRING(0, "prefix", &state.base_dir, N_("string"),
+			N_("when creating files, prepend <string>")),
+		OPT_END()
+	};
+
+	if (argc == 2 && !strcmp(argv[1], "-h"))
+		usage_with_options(checkout_helper_usage,
+				   checkout_helper_options);
+
+	git_config(git_default_config, NULL);
+	argc = parse_options(argc, argv, prefix, checkout_helper_options,
+			     checkout_helper_usage, 0);
+	if (argc > 0)
+		usage_with_options(checkout_helper_usage, checkout_helper_options);
+
+	if (state.base_dir)
+		state.base_dir_len = strlen(state.base_dir);
+
+	/*
+	 * Setting this on worker won't actually update the index. We just need
+	 * to pretend so to induce the checkout machinery to stat() the written
+	 * entries.
+	 */
+	state.refresh_cache = 1;
+
+	worker_loop(&state);
+	return 0;
+}
diff --git a/git.c b/git.c
index 01c456edce..a09357fc56 100644
--- a/git.c
+++ b/git.c
@@ -487,6 +487,8 @@ static struct cmd_struct commands[] = {
 	{ "check-mailmap", cmd_check_mailmap, RUN_SETUP },
 	{ "check-ref-format", cmd_check_ref_format, NO_PARSEOPT  },
 	{ "checkout", cmd_checkout, RUN_SETUP | NEED_WORK_TREE },
+	{ "checkout--helper", cmd_checkout__helper,
+		RUN_SETUP | NEED_WORK_TREE | SUPPORT_SUPER_PREFIX },
 	{ "checkout-index", cmd_checkout_index,
 		RUN_SETUP | NEED_WORK_TREE},
 	{ "cherry", cmd_cherry, RUN_SETUP },
diff --git a/parallel-checkout.c b/parallel-checkout.c
index 7dc8ab2a67..7ea0faa526 100644
--- a/parallel-checkout.c
+++ b/parallel-checkout.c
@@ -1,28 +1,15 @@
 #include "cache.h"
 #include "entry.h"
 #include "parallel-checkout.h"
+#include "pkt-line.h"
+#include "run-command.h"
 #include "streaming.h"
+#include "thread-utils.h"
+#include "config.h"
 
-enum pc_item_status {
-	PC_ITEM_PENDING = 0,
-	PC_ITEM_WRITTEN,
-	/*
-	 * The entry could not be written because there was another file
-	 * already present in its path or leading directories. Since
-	 * checkout_entry_ca() removes such files from the working tree before
-	 * enqueueing the entry for parallel checkout, it means that there was
-	 * a path collision among the entries being written.
-	 */
-	PC_ITEM_COLLIDED,
-	PC_ITEM_FAILED,
-};
-
-struct parallel_checkout_item {
-	/* pointer to a istate->cache[] entry. Not owned by us. */
-	struct cache_entry *ce;
-	struct conv_attrs ca;
-	struct stat st;
-	enum pc_item_status status;
+struct pc_worker {
+	struct child_process cp;
+	size_t next_to_complete, nr_to_complete;
 };
 
 struct parallel_checkout {
@@ -38,6 +25,19 @@ enum pc_status parallel_checkout_status(void)
 	return parallel_checkout.status;
 }
 
+#define DEFAULT_THRESHOLD_FOR_PARALLELISM 100
+
+void get_parallel_checkout_configs(int *num_workers, int *threshold)
+{
+	if (git_config_get_int("checkout.workers", num_workers))
+		*num_workers = 1;
+	else if (*num_workers < 1)
+		*num_workers = online_cpus();
+
+	if (git_config_get_int("checkout.thresholdForParallelism", threshold))
+		*threshold = DEFAULT_THRESHOLD_FOR_PARALLELISM;
+}
+
 void init_parallel_checkout(void)
 {
 	if (parallel_checkout.status != PC_UNINITIALIZED)
@@ -115,10 +115,12 @@ int enqueue_checkout(struct cache_entry *ce, struct conv_attrs *ca)
 	ALLOC_GROW(parallel_checkout.items, parallel_checkout.nr + 1,
 		   parallel_checkout.alloc);
 
-	pc_item = &parallel_checkout.items[parallel_checkout.nr++];
+	pc_item = &parallel_checkout.items[parallel_checkout.nr];
 	pc_item->ce = ce;
 	memcpy(&pc_item->ca, ca, sizeof(pc_item->ca));
 	pc_item->status = PC_ITEM_PENDING;
+	pc_item->id = parallel_checkout.nr;
+	parallel_checkout.nr++;
 
 	return 0;
 }
@@ -231,7 +233,8 @@ static int write_pc_item_to_fd(struct parallel_checkout_item *pc_item, int fd,
 	/*
 	 * checkout metadata is used to give context for external process
 	 * filters. Files requiring such filters are not eligible for parallel
-	 * checkout, so pass NULL.
+	 * checkout, so pass NULL. Note: if that changes, the metadata must also
+	 * be passed from the main process to the workers.
 	 */
 	ret = convert_to_working_tree_ca(&pc_item->ca, pc_item->ce->name,
 					 new_blob, size, &buf, NULL);
@@ -272,8 +275,8 @@ static int check_leading_dirs(const char *path, int len, int prefix_len)
 	return has_dirs_only_path(path, slash - path, prefix_len);
 }
 
-static void write_pc_item(struct parallel_checkout_item *pc_item,
-			  struct checkout *state)
+void write_pc_item(struct parallel_checkout_item *pc_item,
+		   struct checkout *state)
 {
 	unsigned int mode = (pc_item->ce->ce_mode & 0100) ? 0777 : 0666;
 	int fd = -1, fstat_done = 0;
@@ -343,6 +346,214 @@ static void write_pc_item(struct parallel_checkout_item *pc_item,
 	strbuf_release(&path);
 }
 
+static void send_one_item(int fd, struct parallel_checkout_item *pc_item)
+{
+	size_t len_data;
+	char *data, *variant;
+	struct pc_item_fixed_portion *fixed_portion;
+	const char *working_tree_encoding = pc_item->ca.working_tree_encoding;
+	size_t name_len = pc_item->ce->ce_namelen;
+	size_t working_tree_encoding_len = working_tree_encoding ?
+					   strlen(working_tree_encoding) : 0;
+
+	len_data = sizeof(struct pc_item_fixed_portion) + name_len +
+		   working_tree_encoding_len;
+
+	data = xcalloc(1, len_data);
+
+	fixed_portion = (struct pc_item_fixed_portion *)data;
+	fixed_portion->id = pc_item->id;
+	oidcpy(&fixed_portion->oid, &pc_item->ce->oid);
+	fixed_portion->ce_mode = pc_item->ce->ce_mode;
+	fixed_portion->crlf_action = pc_item->ca.crlf_action;
+	fixed_portion->ident = pc_item->ca.ident;
+	fixed_portion->name_len = name_len;
+	fixed_portion->working_tree_encoding_len = working_tree_encoding_len;
+
+	variant = data + sizeof(*fixed_portion);
+	if (working_tree_encoding_len) {
+		memcpy(variant, working_tree_encoding, working_tree_encoding_len);
+		variant += working_tree_encoding_len;
+	}
+	memcpy(variant, pc_item->ce->name, name_len);
+
+	packet_write(fd, data, len_data);
+
+	free(data);
+}
+
+static void send_batch(int fd, size_t start, size_t nr)
+{
+	size_t i;
+	for (i = 0; i < nr; ++i)
+		send_one_item(fd, &parallel_checkout.items[start + i]);
+	packet_flush(fd);
+}
+
+static struct pc_worker *setup_workers(struct checkout *state, int num_workers)
+{
+	struct pc_worker *workers;
+	int i, workers_with_one_extra_item;
+	size_t base_batch_size, next_to_assign = 0;
+
+	ALLOC_ARRAY(workers, num_workers);
+
+	for (i = 0; i < num_workers; ++i) {
+		struct child_process *cp = &workers[i].cp;
+
+		child_process_init(cp);
+		cp->git_cmd = 1;
+		cp->in = -1;
+		cp->out = -1;
+		cp->clean_on_exit = 1;
+		strvec_push(&cp->args, "checkout--helper");
+		if (state->base_dir_len)
+			strvec_pushf(&cp->args, "--prefix=%s", state->base_dir);
+		if (start_command(cp))
+			die(_("failed to spawn checkout worker"));
+	}
+
+	base_batch_size = parallel_checkout.nr / num_workers;
+	workers_with_one_extra_item = parallel_checkout.nr % num_workers;
+
+	for (i = 0; i < num_workers; ++i) {
+		struct pc_worker *worker = &workers[i];
+		size_t batch_size = base_batch_size;
+
+		/* distribute the extra work evenly */
+		if (i < workers_with_one_extra_item)
+			batch_size++;
+
+		send_batch(worker->cp.in, next_to_assign, batch_size);
+		worker->next_to_complete = next_to_assign;
+		worker->nr_to_complete = batch_size;
+
+		next_to_assign += batch_size;
+	}
+
+	return workers;
+}
+
+static void finish_workers(struct pc_worker *workers, int num_workers)
+{
+	int i;
+
+	/*
+	 * Close pipes before calling finish_command() to let the workers
+	 * exit asynchronously and avoid spending extra time on wait().
+	 */
+	for (i = 0; i < num_workers; ++i) {
+		struct child_process *cp = &workers[i].cp;
+		if (cp->in >= 0)
+			close(cp->in);
+		if (cp->out >= 0)
+			close(cp->out);
+	}
+
+	for (i = 0; i < num_workers; ++i) {
+		if (finish_command(&workers[i].cp))
+			error(_("checkout worker %d finished with error"), i);
+	}
+
+	free(workers);
+}
+
+#define ASSERT_PC_ITEM_RESULT_SIZE(got, exp) \
+{ \
+	if (got != exp) \
+		BUG("corrupted result from checkout worker (got %dB, exp %dB)", \
+		    got, exp); \
+} while(0)
+
+static void parse_and_save_result(const char *line, int len,
+				  struct pc_worker *worker)
+{
+	struct pc_item_result *res;
+	struct parallel_checkout_item *pc_item;
+	struct stat *st = NULL;
+
+	if (len < PC_ITEM_RESULT_BASE_SIZE)
+		BUG("too short result from checkout worker (got %dB, exp %dB)",
+		    len, (int)PC_ITEM_RESULT_BASE_SIZE);
+
+	res = (struct pc_item_result *)line;
+
+	/*
+	 * Worker should send either the full result struct on success, or
+	 * just the base (i.e. no stat data), otherwise.
+	 */
+	if (res->status == PC_ITEM_WRITTEN) {
+		ASSERT_PC_ITEM_RESULT_SIZE(len, (int)sizeof(struct pc_item_result));
+		st = &res->st;
+	} else {
+		ASSERT_PC_ITEM_RESULT_SIZE(len, (int)PC_ITEM_RESULT_BASE_SIZE);
+	}
+
+	if (!worker->nr_to_complete || res->id != worker->next_to_complete)
+		BUG("checkout worker sent unexpected item id");
+
+	worker->next_to_complete++;
+	worker->nr_to_complete--;
+
+	pc_item = &parallel_checkout.items[res->id];
+	pc_item->status = res->status;
+	if (st)
+		pc_item->st = *st;
+}
+
+
+static void gather_results_from_workers(struct pc_worker *workers,
+					int num_workers)
+{
+	int i, active_workers = num_workers;
+	struct pollfd *pfds;
+
+	CALLOC_ARRAY(pfds, num_workers);
+	for (i = 0; i < num_workers; ++i) {
+		pfds[i].fd = workers[i].cp.out;
+		pfds[i].events = POLLIN;
+	}
+
+	while (active_workers) {
+		int nr = poll(pfds, num_workers, -1);
+
+		if (nr < 0) {
+			if (errno == EINTR)
+				continue;
+			die_errno("failed to poll checkout workers");
+		}
+
+		for (i = 0; i < num_workers && nr > 0; ++i) {
+			struct pc_worker *worker = &workers[i];
+			struct pollfd *pfd = &pfds[i];
+
+			if (!pfd->revents)
+				continue;
+
+			if (pfd->revents & POLLIN) {
+				int len;
+				const char *line = packet_read_line(pfd->fd, &len);
+
+				if (!line) {
+					pfd->fd = -1;
+					active_workers--;
+				} else {
+					parse_and_save_result(line, len, worker);
+				}
+			} else if (pfd->revents & POLLHUP) {
+				pfd->fd = -1;
+				active_workers--;
+			} else if (pfd->revents & (POLLNVAL | POLLERR)) {
+				die(_("error polling from checkout worker"));
+			}
+
+			nr--;
+		}
+	}
+
+	free(pfds);
+}
+
 static void write_items_sequentially(struct checkout *state)
 {
 	size_t i;
@@ -351,7 +562,7 @@ static void write_items_sequentially(struct checkout *state)
 		write_pc_item(&parallel_checkout.items[i], state);
 }
 
-int run_parallel_checkout(struct checkout *state)
+int run_parallel_checkout(struct checkout *state, int num_workers, int threshold)
 {
 	int ret;
 
@@ -360,7 +571,17 @@ int run_parallel_checkout(struct checkout *state)
 
 	parallel_checkout.status = PC_RUNNING;
 
-	write_items_sequentially(state);
+	if (parallel_checkout.nr < num_workers)
+		num_workers = parallel_checkout.nr;
+
+	if (num_workers <= 1 || parallel_checkout.nr < threshold) {
+		write_items_sequentially(state);
+	} else {
+		struct pc_worker *workers = setup_workers(state, num_workers);
+		gather_results_from_workers(workers, num_workers);
+		finish_workers(workers, num_workers);
+	}
+
 	ret = handle_results(state);
 
 	finish_parallel_checkout();
diff --git a/parallel-checkout.h b/parallel-checkout.h
index e6d6fc01ea..0c9984584e 100644
--- a/parallel-checkout.h
+++ b/parallel-checkout.h
@@ -1,9 +1,12 @@
 #ifndef PARALLEL_CHECKOUT_H
 #define PARALLEL_CHECKOUT_H
 
-struct cache_entry;
-struct checkout;
-struct conv_attrs;
+#include "entry.h"
+#include "convert.h"
+
+/****************************************************************
+ * Users of parallel checkout
+ ****************************************************************/
 
 enum pc_status {
 	PC_UNINITIALIZED = 0,
@@ -12,6 +15,7 @@ enum pc_status {
 };
 
 enum pc_status parallel_checkout_status(void);
+void get_parallel_checkout_configs(int *num_workers, int *threshold);
 void init_parallel_checkout(void);
 
 /*
@@ -21,7 +25,77 @@ void init_parallel_checkout(void);
  */
 int enqueue_checkout(struct cache_entry *ce, struct conv_attrs *ca);
 
-/* Write all the queued entries, returning 0 on success.*/
-int run_parallel_checkout(struct checkout *state);
+/*
+ * Write all the queued entries, returning 0 on success. If the number of
+ * entries is smaller than the specified threshold, the operation is performed
+ * sequentially.
+ */
+int run_parallel_checkout(struct checkout *state, int num_workers, int threshold);
+
+/****************************************************************
+ * Interface with checkout--helper
+ ****************************************************************/
+
+enum pc_item_status {
+	PC_ITEM_PENDING = 0,
+	PC_ITEM_WRITTEN,
+	/*
+	 * The entry could not be written because there was another file
+	 * already present in its path or leading directories. Since
+	 * checkout_entry_ca() removes such files from the working tree before
+	 * enqueueing the entry for parallel checkout, it means that there was
+	 * a path collision among the entries being written.
+	 */
+	PC_ITEM_COLLIDED,
+	PC_ITEM_FAILED,
+};
+
+struct parallel_checkout_item {
+	/*
+	 * In main process ce points to a istate->cache[] entry. Thus, it's not
+	 * owned by us. In workers they own the memory, which *must be* released.
+	 */
+	struct cache_entry *ce;
+	struct conv_attrs ca;
+	size_t id; /* position in parallel_checkout.items[] of main process */
+
+	/* Output fields, sent from workers. */
+	enum pc_item_status status;
+	struct stat st;
+};
+
+/*
+ * The fixed-size portion of `struct parallel_checkout_item` that is sent to the
+ * workers. Following this will be 2 strings: ca.working_tree_encoding and
+ * ce.name; These are NOT null terminated, since we have the size in the fixed
+ * portion.
+ *
+ * Note that not all fields of conv_attrs and cache_entry are passed, only the
+ * ones that will be required by the workers to smudge and write the entry.
+ */
+struct pc_item_fixed_portion {
+	size_t id;
+	struct object_id oid;
+	unsigned int ce_mode;
+	enum crlf_action crlf_action;
+	int ident;
+	size_t working_tree_encoding_len;
+	size_t name_len;
+};
+
+/*
+ * The fields of `struct parallel_checkout_item` that are returned by the
+ * workers. Note: `st` must be the last one, as it is omitted on error.
+ */
+struct pc_item_result {
+	size_t id;
+	enum pc_item_status status;
+	struct stat st;
+};
+
+#define PC_ITEM_RESULT_BASE_SIZE offsetof(struct pc_item_result, st)
+
+void write_pc_item(struct parallel_checkout_item *pc_item,
+		   struct checkout *state);
 
 #endif /* PARALLEL_CHECKOUT_H */
diff --git a/unpack-trees.c b/unpack-trees.c
index 1b1da7485a..117ed42370 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -399,7 +399,7 @@ static int check_updates(struct unpack_trees_options *o,
 	int errs = 0;
 	struct progress *progress;
 	struct checkout state = CHECKOUT_INIT;
-	int i;
+	int i, pc_workers, pc_threshold;
 
 	trace_performance_enter();
 	state.force = 1;
@@ -462,8 +462,11 @@ static int check_updates(struct unpack_trees_options *o,
 		oid_array_clear(&to_fetch);
 	}
 
+	get_parallel_checkout_configs(&pc_workers, &pc_threshold);
+
 	enable_delayed_checkout(&state);
-	init_parallel_checkout();
+	if (pc_workers > 1)
+		init_parallel_checkout();
 	for (i = 0; i < index->cache_nr; i++) {
 		struct cache_entry *ce = index->cache[i];
 
@@ -477,7 +480,8 @@ static int check_updates(struct unpack_trees_options *o,
 		}
 	}
 	stop_progress(&progress);
-	errs |= run_parallel_checkout(&state);
+	if (pc_workers > 1)
+		errs |= run_parallel_checkout(&state, pc_workers, pc_threshold);
 	errs |= finish_delayed_checkout(&state, NULL);
 	git_attr_set_direction(GIT_ATTR_CHECKIN);
 

parallel-checkout.c, parallel-checkout.h, unpack-trees.c

diff --git a/parallel-checkout.c b/parallel-checkout.c
index 7ea0faa526..5156b14c53 100644
--- a/parallel-checkout.c
+++ b/parallel-checkout.c
@@ -2,6 +2,7 @@
 #include "entry.h"
 #include "parallel-checkout.h"
 #include "pkt-line.h"
+#include "progress.h"
 #include "run-command.h"
 #include "streaming.h"
 #include "thread-utils.h"
@@ -16,6 +17,8 @@ struct parallel_checkout {
 	enum pc_status status;
 	struct parallel_checkout_item *items;
 	size_t nr, alloc;
+	struct progress *progress;
+	unsigned int *progress_cnt;
 };
 
 static struct parallel_checkout parallel_checkout = { 0 };
@@ -125,6 +128,20 @@ int enqueue_checkout(struct cache_entry *ce, struct conv_attrs *ca)
 	return 0;
 }
 
+size_t pc_queue_size(void)
+{
+	return parallel_checkout.nr;
+}
+
+static void advance_progress_meter(void)
+{
+	if (parallel_checkout.progress) {
+		(*parallel_checkout.progress_cnt)++;
+		display_progress(parallel_checkout.progress,
+				 *parallel_checkout.progress_cnt);
+	}
+}
+
 static int handle_results(struct checkout *state)
 {
 	int ret = 0;
@@ -173,6 +190,7 @@ static int handle_results(struct checkout *state)
 			 */
 			ret |= checkout_entry_ca(pc_item->ce, &pc_item->ca,
 						 state, NULL, NULL);
+			advance_progress_meter();
 			break;
 		case PC_ITEM_PENDING:
 			have_pending = 1;
@@ -499,6 +517,9 @@ static void parse_and_save_result(const char *line, int len,
 	pc_item->status = res->status;
 	if (st)
 		pc_item->st = *st;
+
+	if (res->status != PC_ITEM_COLLIDED)
+		advance_progress_meter();
 }
 
 
@@ -558,11 +579,16 @@ static void write_items_sequentially(struct checkout *state)
 {
 	size_t i;
 
-	for (i = 0; i < parallel_checkout.nr; ++i)
-		write_pc_item(&parallel_checkout.items[i], state);
+	for (i = 0; i < parallel_checkout.nr; ++i) {
+		struct parallel_checkout_item *pc_item = &parallel_checkout.items[i];
+		write_pc_item(pc_item, state);
+		if (pc_item->status != PC_ITEM_COLLIDED)
+			advance_progress_meter();
+	}
 }
 
-int run_parallel_checkout(struct checkout *state, int num_workers, int threshold)
+int run_parallel_checkout(struct checkout *state, int num_workers, int threshold,
+			  struct progress *progress, unsigned int *progress_cnt)
 {
 	int ret;
 
@@ -570,6 +596,8 @@ int run_parallel_checkout(struct checkout *state, int num_workers, int threshold
 		BUG("cannot run parallel checkout: uninitialized or already running");
 
 	parallel_checkout.status = PC_RUNNING;
+	parallel_checkout.progress = progress;
+	parallel_checkout.progress_cnt = progress_cnt;
 
 	if (parallel_checkout.nr < num_workers)
 		num_workers = parallel_checkout.nr;
diff --git a/parallel-checkout.h b/parallel-checkout.h
index 0c9984584e..6c3a016c0b 100644
--- a/parallel-checkout.h
+++ b/parallel-checkout.h
@@ -24,13 +24,15 @@ void init_parallel_checkout(void);
  * write and return 0.
  */
 int enqueue_checkout(struct cache_entry *ce, struct conv_attrs *ca);
+size_t pc_queue_size(void);
 
 /*
  * Write all the queued entries, returning 0 on success. If the number of
  * entries is smaller than the specified threshold, the operation is performed
  * sequentially.
  */
-int run_parallel_checkout(struct checkout *state, int num_workers, int threshold);
+int run_parallel_checkout(struct checkout *state, int num_workers, int threshold,
+			  struct progress *progress, unsigned int *progress_cnt);
 
 /****************************************************************
  * Interface with checkout--helper
diff --git a/unpack-trees.c b/unpack-trees.c
index 117ed42370..e05e6ceff2 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -471,17 +471,22 @@ static int check_updates(struct unpack_trees_options *o,
 		struct cache_entry *ce = index->cache[i];
 
 		if (ce->ce_flags & CE_UPDATE) {
+			size_t last_pc_queue_size = pc_queue_size();
+
 			if (ce->ce_flags & CE_WT_REMOVE)
 				BUG("both update and delete flags are set on %s",
 				    ce->name);
-			display_progress(progress, ++cnt);
 			ce->ce_flags &= ~CE_UPDATE;
 			errs |= checkout_entry(ce, &state, NULL, NULL);
+
+			if (last_pc_queue_size == pc_queue_size())
+				display_progress(progress, ++cnt);
 		}
 	}
-	stop_progress(&progress);
 	if (pc_workers > 1)
-		errs |= run_parallel_checkout(&state, pc_workers, pc_threshold);
+		errs |= run_parallel_checkout(&state, pc_workers, pc_threshold,
+					      progress, &cnt);
+	stop_progress(&progress);
 	errs |= finish_delayed_checkout(&state, NULL);
 	git_attr_set_direction(GIT_ATTR_CHECKIN);
 

builtin/checkout--helper.c, builtin/checkout.c, builtin/difftool.c, cache.h, read-cache.c, unpack-trees.c

diff --git a/builtin/checkout--helper.c b/builtin/checkout--helper.c
index 67fe37cf11..9646ed9eeb 100644
--- a/builtin/checkout--helper.c
+++ b/builtin/checkout--helper.c
@@ -38,7 +38,7 @@ static void packet_to_pc_item(char *line, int len,
 	}
 
 	memset(pc_item, 0, sizeof(*pc_item));
-	pc_item->ce = make_empty_transient_cache_entry(fixed_portion->name_len);
+	pc_item->ce = make_empty_transient_cache_entry(fixed_portion->name_len, NULL);
 	pc_item->ce->ce_namelen = fixed_portion->name_len;
 	pc_item->ce->ce_mode = fixed_portion->ce_mode;
 	memcpy(pc_item->ce->name, variant, pc_item->ce->ce_namelen);
diff --git a/builtin/checkout.c b/builtin/checkout.c
index b18b9d6f3c..c0bf5e6711 100644
--- a/builtin/checkout.c
+++ b/builtin/checkout.c
@@ -291,7 +291,7 @@ static int checkout_merged(int pos, const struct checkout *state, int *nr_checko
 	if (write_object_file(result_buf.ptr, result_buf.size, blob_type, &oid))
 		die(_("Unable to add merge result for '%s'"), path);
 	free(result_buf.ptr);
-	ce = make_transient_cache_entry(mode, &oid, path, 2);
+	ce = make_transient_cache_entry(mode, &oid, path, 2, NULL);
 	if (!ce)
 		die(_("make_cache_entry failed for path '%s'"), path);
 	status = checkout_entry(ce, state, NULL, nr_checkouts);
diff --git a/builtin/difftool.c b/builtin/difftool.c
index dfa22b67eb..5e7a57c8c2 100644
--- a/builtin/difftool.c
+++ b/builtin/difftool.c
@@ -323,7 +323,7 @@ static int checkout_path(unsigned mode, struct object_id *oid,
 	struct cache_entry *ce;
 	int ret;
 
-	ce = make_transient_cache_entry(mode, oid, path, 0);
+	ce = make_transient_cache_entry(mode, oid, path, 0, NULL);
 	ret = checkout_entry(ce, state, NULL, NULL);
 
 	discard_cache_entry(ce);
diff --git a/cache.h b/cache.h
index 17350cafa2..a394263f0e 100644
--- a/cache.h
+++ b/cache.h
@@ -355,16 +355,16 @@ struct cache_entry *make_empty_cache_entry(struct index_state *istate,
 					   size_t name_len);
 
 /*
- * Create a cache_entry that is not intended to be added to an index.
- * Caller is responsible for discarding the cache_entry
- * with `discard_cache_entry`.
+ * Create a cache_entry that is not intended to be added to an index. If mp is
+ * not NULL, the entry is allocated within the given memory pool. Caller is
+ * responsible for discarding the cache_entry with `discard_cache_entry`.
  */
 struct cache_entry *make_transient_cache_entry(unsigned int mode,
 					       const struct object_id *oid,
 					       const char *path,
-					       int stage);
+					       int stage, struct mem_pool *mp);
 
-struct cache_entry *make_empty_transient_cache_entry(size_t name_len);
+struct cache_entry *make_empty_transient_cache_entry(size_t len, struct mem_pool *mp);
 
 /*
  * Discard cache entry.
diff --git a/read-cache.c b/read-cache.c
index ecf6f68994..f9bac760af 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -813,8 +813,10 @@ struct cache_entry *make_empty_cache_entry(struct index_state *istate, size_t le
 	return mem_pool__ce_calloc(find_mem_pool(istate), len);
 }
 
-struct cache_entry *make_empty_transient_cache_entry(size_t len)
+struct cache_entry *make_empty_transient_cache_entry(size_t len, struct mem_pool *mp)
 {
+	if (mp)
+		return mem_pool__ce_calloc(mp, len);
 	return xcalloc(1, cache_entry_size(len));
 }
 
@@ -848,8 +850,10 @@ struct cache_entry *make_cache_entry(struct index_state *istate,
 	return ret;
 }
 
-struct cache_entry *make_transient_cache_entry(unsigned int mode, const struct object_id *oid,
-					       const char *path, int stage)
+struct cache_entry *make_transient_cache_entry(unsigned int mode,
+					       const struct object_id *oid,
+					       const char *path, int stage,
+					       struct mem_pool *mp)
 {
 	struct cache_entry *ce;
 	int len;
@@ -860,7 +864,7 @@ struct cache_entry *make_transient_cache_entry(unsigned int mode, const struct o
 	}
 
 	len = strlen(path);
-	ce = make_empty_transient_cache_entry(len);
+	ce = make_empty_transient_cache_entry(len, mp);
 
 	oidcpy(&ce->oid, oid);
 	memcpy(ce->name, path, len);
diff --git a/unpack-trees.c b/unpack-trees.c
index e05e6ceff2..dcb40dc8fa 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -1031,7 +1031,7 @@ static struct cache_entry *create_ce_entry(const struct traverse_info *info,
 	size_t len = traverse_path_len(info, tree_entry_len(n));
 	struct cache_entry *ce =
 		is_transient ?
-		make_empty_transient_cache_entry(len) :
+		make_empty_transient_cache_entry(len, NULL) :
 		make_empty_cache_entry(istate, len);
 
 	ce->ce_mode = create_ce_mode(n->mode);

diff --git a/builtin/checkout.c b/builtin/checkout.c
index c0bf5e6711..ddc4079b85 100644
--- a/builtin/checkout.c
+++ b/builtin/checkout.c
@@ -27,6 +27,7 @@
 #include "wt-status.h"
 #include "xdiff-interface.h"
 #include "entry.h"
+#include "parallel-checkout.h"
 
 static const char * const checkout_usage[] = {
 	N_("git checkout [<options>] <branch>"),
@@ -230,7 +231,8 @@ static int checkout_stage(int stage, const struct cache_entry *ce, int pos,
 		return error(_("path '%s' does not have their version"), ce->name);
 }
 
-static int checkout_merged(int pos, const struct checkout *state, int *nr_checkouts)
+static int checkout_merged(int pos, const struct checkout *state,
+			   int *nr_checkouts, struct mem_pool *ce_mem_pool)
 {
 	struct cache_entry *ce = active_cache[pos];
 	const char *path = ce->name;
@@ -291,11 +293,10 @@ static int checkout_merged(int pos, const struct checkout *state, int *nr_checko
 	if (write_object_file(result_buf.ptr, result_buf.size, blob_type, &oid))
 		die(_("Unable to add merge result for '%s'"), path);
 	free(result_buf.ptr);
-	ce = make_transient_cache_entry(mode, &oid, path, 2, NULL);
+	ce = make_transient_cache_entry(mode, &oid, path, 2, ce_mem_pool);
 	if (!ce)
 		die(_("make_cache_entry failed for path '%s'"), path);
 	status = checkout_entry(ce, state, NULL, nr_checkouts);
-	discard_cache_entry(ce);
 	return status;
 }
 
@@ -359,16 +360,22 @@ static int checkout_worktree(const struct checkout_opts *opts,
 	int nr_checkouts = 0, nr_unmerged = 0;
 	int errs = 0;
 	int pos;
+	int pc_workers, pc_threshold;
+	struct mem_pool ce_mem_pool;
 
 	state.force = 1;
 	state.refresh_cache = 1;
 	state.istate = &the_index;
 
+	mem_pool_init(&ce_mem_pool, 0);
+	get_parallel_checkout_configs(&pc_workers, &pc_threshold);
 	init_checkout_metadata(&state.meta, info->refname,
 			       info->commit ? &info->commit->object.oid : &info->oid,
 			       NULL);
 
 	enable_delayed_checkout(&state);
+	if (pc_workers > 1)
+		init_parallel_checkout();
 	for (pos = 0; pos < active_nr; pos++) {
 		struct cache_entry *ce = active_cache[pos];
 		if (ce->ce_flags & CE_MATCHED) {
@@ -384,10 +391,15 @@ static int checkout_worktree(const struct checkout_opts *opts,
 						       &nr_checkouts, opts->overlay_mode);
 			else if (opts->merge)
 				errs |= checkout_merged(pos, &state,
-							&nr_unmerged);
+							&nr_unmerged,
+							&ce_mem_pool);
 			pos = skip_same_name(ce, pos) - 1;
 		}
 	}
+	if (pc_workers > 1)
+		errs |= run_parallel_checkout(&state, pc_workers, pc_threshold,
+					      NULL, NULL);
+	mem_pool_discard(&ce_mem_pool, should_validate_cache_entries());
 	remove_marked_cache_entries(&the_index, 1);
 	remove_scheduled_dirs();
 	errs |= finish_delayed_checkout(&state, &nr_checkouts);

diff --git a/builtin/checkout-index.c b/builtin/checkout-index.c
index 0f1ff73129..33fb933c30 100644
--- a/builtin/checkout-index.c
+++ b/builtin/checkout-index.c
@@ -12,6 +12,7 @@
 #include "cache-tree.h"
 #include "parse-options.h"
 #include "entry.h"
+#include "parallel-checkout.h"
 
 #define CHECKOUT_ALL 4
 static int nul_term_line;
@@ -160,6 +161,7 @@ int cmd_checkout_index(int argc, const char **argv, const char *prefix)
 	int prefix_length;
 	int force = 0, quiet = 0, not_new = 0;
 	int index_opt = 0;
+	int pc_workers, pc_threshold;
 	struct option builtin_checkout_index_options[] = {
 		OPT_BOOL('a', "all", &all,
 			N_("check out all files in the index")),
@@ -214,6 +216,14 @@ int cmd_checkout_index(int argc, const char **argv, const char *prefix)
 		hold_locked_index(&lock_file, LOCK_DIE_ON_ERROR);
 	}
 
+	if (!to_tempfile)
+		get_parallel_checkout_configs(&pc_workers, &pc_threshold);
+	else
+		pc_workers = 1;
+
+	if (pc_workers > 1)
+		init_parallel_checkout();
+
 	/* Check out named files first */
 	for (i = 0; i < argc; i++) {
 		const char *arg = argv[i];
@@ -256,6 +266,12 @@ int cmd_checkout_index(int argc, const char **argv, const char *prefix)
 	if (all)
 		checkout_all(prefix, prefix_length);
 
+	if (pc_workers > 1) {
+		/* Errors were already reported */
+		run_parallel_checkout(&state, pc_workers, pc_threshold,
+				      NULL, NULL);
+	}
+
 	if (is_lock_file_locked(&lock_file) &&
 	    write_locked_index(&the_index, &lock_file, COMMIT_LOCK))
 		die("Unable to write new index file");

t/lib-parallel-checkout.sh, t/t2080-parallel-checkout-basics.sh

diff --git a/t/lib-parallel-checkout.sh b/t/lib-parallel-checkout.sh
new file mode 100644
index 0000000000..c95ca27711
--- /dev/null
+++ b/t/lib-parallel-checkout.sh
@@ -0,0 +1,39 @@
+# Helpers for t208* tests
+
+# Runs `git -c checkout.workers=$1 -c checkout.thesholdForParallelism=$2 ${@:4}`
+# and checks that the number of workers spawned is equal to $3.
+git_pc()
+{
+	if test $# -lt 4
+	then
+		BUG "too few arguments to git_pc()"
+	fi
+
+	workers=$1 threshold=$2 expected_workers=$3 &&
+	shift && shift && shift &&
+
+	rm -f trace &&
+	GIT_TRACE2="$(pwd)/trace" git \
+		-c checkout.workers=$workers \
+		-c checkout.thresholdForParallelism=$threshold \
+		-c advice.detachedHead=0 \
+		$@ &&
+
+	# Check that the expected number of workers has been used. Note that it
+	# can be different than the requested number in two cases: when the
+	# quantity of entries to be checked out is less than the number of
+	# workers; and when the threshold has not been reached.
+	#
+	local workers_in_trace=$(grep "child_start\[.\+\] git checkout--helper" trace | wc -l) &&
+	test $workers_in_trace -eq $expected_workers &&
+	rm -f trace
+}
+
+# Verify that both the working tree and the index were created correctly
+verify_checkout()
+{
+	git -C $1 diff-index --quiet HEAD -- &&
+	git -C $1 diff-index --quiet --cached HEAD -- &&
+	git -C $1 status --porcelain >$1.status &&
+	test_must_be_empty $1.status
+}
diff --git a/t/t2080-parallel-checkout-basics.sh b/t/t2080-parallel-checkout-basics.sh
new file mode 100755
index 0000000000..c088a06ecc
--- /dev/null
+++ b/t/t2080-parallel-checkout-basics.sh
@@ -0,0 +1,197 @@
+#!/bin/sh
+
+test_description='parallel-checkout basics
+
+Ensure that parallel-checkout basically works on clone and checkout, spawning
+the required number of workers and correctly populating both the index and
+working tree.
+'
+
+TEST_NO_CREATE_REPO=1
+. ./test-lib.sh
+. "$TEST_DIRECTORY/lib-parallel-checkout.sh"
+
+# NEEDSWORK: cloning a SHA1 repo with GIT_TEST_DEFAULT_HASH set to "sha256"
+# currently produces a wrong result (See
+# https://lore.kernel.org/git/20200911151717.43475-1-matheus.bernardino@usp.br/).
+# So we skip the "parallel-checkout during clone" tests when this test flag is
+# set to "sha256". Remove this when the bug is fixed.
+#
+if test "$GIT_TEST_DEFAULT_HASH" = "sha256"
+then
+	skip_all="t2080 currently don't work with GIT_TEST_DEFAULT_HASH=sha256"
+	test_done
+fi
+
+R_BASE=$GIT_BUILD_DIR
+
+test_expect_success 'sequential clone' '
+	git_pc 1 0 0 clone --quiet -- $R_BASE r_sequential &&
+	verify_checkout r_sequential
+'
+
+test_expect_success 'parallel clone' '
+	git_pc 2 0 2 clone --quiet -- $R_BASE r_parallel &&
+	verify_checkout r_parallel
+'
+
+test_expect_success 'fallback to sequential clone (threshold)' '
+	git -C $R_BASE ls-files >files &&
+	nr_files=$(wc -l <files) &&
+	threshold=$(($nr_files + 1)) &&
+
+	git_pc 2 $threshold 0 clone --quiet -- $R_BASE r_sequential_fallback &&
+	verify_checkout r_sequential_fallback
+'
+
+# Just to be paranoid, actually compare the contents of the worktrees directly.
+test_expect_success 'compare working trees from clones' '
+	rm -rf r_sequential/.git &&
+	rm -rf r_parallel/.git &&
+	rm -rf r_sequential_fallback/.git &&
+	diff -qr r_sequential r_parallel &&
+	diff -qr r_sequential r_sequential_fallback
+'
+
+# Test parallel-checkout with different operations (creation, deletion,
+# modification) and entry types. A branch switch from B1 to B2 will contain:
+#
+# - a (file):      modified
+# - e/x (file):    deleted
+# - b (symlink):   deleted
+# - b/f (file):    created
+# - e (symlink):   created
+# - d (submodule): created
+#
+test_expect_success SYMLINKS 'setup repo for checkout with various operations' '
+	git init various &&
+	(
+		cd various &&
+		git checkout -b B1 &&
+		echo a>a &&
+		mkdir e &&
+		echo e/x >e/x &&
+		ln -s e b &&
+		git add -A &&
+		git commit -m B1 &&
+
+		git checkout -b B2 &&
+		echo modified >a &&
+		rm -rf e &&
+		rm b &&
+		mkdir b &&
+		echo b/f >b/f &&
+		ln -s b e &&
+		git init d &&
+		test_commit -C d f &&
+		git submodule add ./d &&
+		git add -A &&
+		git commit -m B2 &&
+
+		git checkout --recurse-submodules B1
+	)
+'
+
+test_expect_success SYMLINKS 'sequential checkout' '
+	cp -R various various_sequential &&
+	git_pc 1 0 0 -C various_sequential checkout --recurse-submodules B2 &&
+	verify_checkout various_sequential
+'
+
+test_expect_success SYMLINKS 'parallel checkout' '
+	cp -R various various_parallel &&
+	git_pc 2 0 2 -C various_parallel checkout --recurse-submodules B2 &&
+	verify_checkout various_parallel
+'
+
+test_expect_success SYMLINKS 'fallback to sequential checkout (threshold)' '
+	cp -R various various_sequential_fallback &&
+	git_pc 2 100 0 -C various_sequential_fallback checkout --recurse-submodules B2 &&
+	verify_checkout various_sequential_fallback
+'
+
+test_expect_success SYMLINKS 'compare working trees from checkouts' '
+	rm -rf various_sequential/.git &&
+	rm -rf various_parallel/.git &&
+	rm -rf various_sequential_fallback/.git &&
+	diff -qr various_sequential various_parallel &&
+	diff -qr various_sequential various_sequential_fallback
+'
+
+test_cmp_str()
+{
+	echo "$1" >tmp &&
+	test_cmp tmp "$2"
+}
+
+test_expect_success 'parallel checkout respects --[no]-force' '
+	git init dirty &&
+	(
+		cd dirty &&
+		mkdir D &&
+		test_commit D/F &&
+		test_commit F &&
+
+		echo changed >F.t &&
+		rm -rf D &&
+		echo changed >D &&
+
+		# We expect 0 workers because there is nothing to be updated
+		git_pc 2 0 0 checkout HEAD &&
+		test_path_is_file D &&
+		test_cmp_str changed D &&
+		test_cmp_str changed F.t &&
+
+		git_pc 2 0 2 checkout --force HEAD &&
+		test_path_is_dir D &&
+		test_cmp_str D/F D/F.t &&
+		test_cmp_str F F.t
+	)
+'
+
+test_expect_success SYMLINKS 'parallel checkout checks for symlinks in leading dirs' '
+	git init symlinks &&
+	(
+		cd symlinks &&
+		mkdir D E &&
+
+		# Create two entries in D to have enough work for 2 parallel
+		# workers
+		test_commit D/A &&
+		test_commit D/B &&
+		test_commit E/C &&
+		rm -rf D &&
+		ln -s E D &&
+
+		git_pc 2 0 2 checkout --force HEAD &&
+		! test -L D &&
+		test_cmp_str D/A D/A.t &&
+		test_cmp_str D/B D/B.t
+	)
+'
+
+test_expect_success SYMLINKS,CASE_INSENSITIVE_FS 'symlink colliding with leading dir' '
+	git init colliding-symlink &&
+	(
+		cd colliding-symlink &&
+		file_hex=$(git hash-object -w --stdin </dev/null) &&
+		file_oct=$(echo $file_hex | hex2oct) &&
+
+		sym_hex=$(echo "./D" | git hash-object -w --stdin) &&
+		sym_oct=$(echo $sym_hex | hex2oct) &&
+
+		printf "100644 D/A\0${file_oct}" >tree &&
+		printf "100644 E/B\0${file_oct}" >>tree &&
+		printf "120000 e\0${sym_oct}" >>tree &&
+
+		tree_hex=$(git hash-object -w -t tree --stdin <tree) &&
+		commit_hex=$(git commit-tree -m collisions $tree_hex) &&
+		git update-ref refs/heads/colliding-symlink $commit_hex &&
+
+		git_pc 2 0 2 checkout colliding-symlink &&
+		test_path_is_dir D &&
+		test_path_is_missing D/B
+	)
+'
+
+test_done

diff --git a/t/t2081-parallel-checkout-collisions.sh b/t/t2081-parallel-checkout-collisions.sh
new file mode 100755
index 0000000000..3ce195b892
--- /dev/null
+++ b/t/t2081-parallel-checkout-collisions.sh
@@ -0,0 +1,115 @@
+#!/bin/sh
+
+test_description='parallel-checkout collisions'
+
+. ./test-lib.sh
+
+# When there are pathname collisions during a clone, Git should report a warning
+# listing all of the colliding entries. The sequential code detects a collision
+# by calling lstat() before trying to open(O_CREAT) the file. Then, to find the
+# colliding pair of an item k, it searches cache_entry[0, k-1].
+#
+# This is not sufficient in parallel-checkout mode since colliding files may be
+# created in a racy order. The tests in this file make sure the collision
+# detection code is extended for parallel-checkout. This is done in two parts:
+#
+# - First, two parallel workers create four colliding files racily.
+# - Then this exercise is repeated but forcing the colliding pair to appear in
+#   the second half of the cache_entry's array.
+#
+# The second item uses the fact that files with clean/smudge filters are not
+# parallel-eligible; and that they are processed sequentially *before* any
+# worker is spawned. We set a filter attribute to the last entry in the
+# cache_entry[] array, making it non-eligible, so that it is populated first.
+# This way, we can test if the collision detection code is correctly looking
+# for collision pairs in the second half of the array.
+
+test_expect_success CASE_INSENSITIVE_FS 'setup' '
+	file_hex=$(git hash-object -w --stdin </dev/null) &&
+	file_oct=$(echo $file_hex | hex2oct) &&
+
+	attr_hex=$(echo "file_x filter=logger" | git hash-object -w --stdin) &&
+	attr_oct=$(echo $attr_hex | hex2oct) &&
+
+	printf "100644 FILE_X\0${file_oct}" >tree &&
+	printf "100644 FILE_x\0${file_oct}" >>tree &&
+	printf "100644 file_X\0${file_oct}" >>tree &&
+	printf "100644 file_x\0${file_oct}" >>tree &&
+	printf "100644 .gitattributes\0${attr_oct}" >>tree &&
+
+	tree_hex=$(git hash-object -w -t tree --stdin <tree) &&
+	commit_hex=$(git commit-tree -m collisions $tree_hex) &&
+	git update-ref refs/heads/collisions $commit_hex &&
+
+	write_script logger_script <<-\EOF
+	echo "$@" >>filter.log
+	EOF
+'
+
+clone_and_check_collision()
+{
+	id=$1 workers=$2 threshold=$3 expected_workers=$4 filter=$5 &&
+
+	filter_opts=
+	if test "$filter" -eq "use_filter"
+	then
+		# We use `core.ignoreCase=0` so that only `file_x`
+		# matches the pattern in .gitattributes.
+		#
+		filter_opts='-c filter.logger.smudge="../logger_script %f" -c core.ignoreCase=0'
+	fi &&
+
+	test_path_is_missing $id.trace &&
+	GIT_TRACE2="$(pwd)/$id.trace" git \
+		-c checkout.workers=$workers \
+		-c checkout.thresholdForParallelism=$threshold \
+		$filter_opts clone --branch=collisions -- . r_$id 2>$id.warning &&
+
+	# Check that checkout spawned the right number of workers
+	workers_in_trace=$(grep "child_start\[.\] git checkout--helper" $id.trace | wc -l) &&
+	test $workers_in_trace -eq $expected_workers &&
+
+	if test $filter -eq "use_filter"
+	then
+		#  Make sure only 'file_x' was filtered
+		test_path_is_file r_$id/filter.log &&
+		echo file_x >expected.filter.log &&
+		test_cmp r_$id/filter.log expected.filter.log
+	else
+		test_path_is_missing r_$id/filter.log
+	fi &&
+
+	grep FILE_X $id.warning &&
+	grep FILE_x $id.warning &&
+	grep file_X $id.warning &&
+	grep file_x $id.warning &&
+	test_i18ngrep "the following paths have collided" $id.warning
+}
+
+test_expect_success CASE_INSENSITIVE_FS 'collision detection on parallel clone' '
+	clone_and_check_collision parallel 2 0 2
+'
+
+test_expect_success CASE_INSENSITIVE_FS 'collision detection on fallback to sequential clone' '
+	git ls-tree --name-only -r collisions >files &&
+	nr_files=$(wc -l <files) &&
+	threshold=$(($nr_files + 1)) &&
+	clone_and_check_collision sequential 2 $threshold 0
+'
+
+# The next two tests don't work on Windows because, on this system, collision
+# detection uses strcmp() (when core.ignoreCase=0) to find the colliding pair.
+# But they work on OSX, where collision detection uses inode.
+
+test_expect_success CASE_INSENSITIVE_FS,!MINGW,!CYGWIN 'collision detection on parallel clone w/ filter' '
+	clone_and_check_collision parallel-with-filter 2 0 2 use_filter
+'
+
+test_expect_success CASE_INSENSITIVE_FS,!MINGW,!CYGWIN 'collision detection on fallback to sequential clone w/ filter' '
+	git ls-tree --name-only -r collisions >files &&
+	nr_files=$(wc -l <files) &&
+	threshold=$(($nr_files + 1)) &&
+	clone_and_check_collision sequential-with-filter 2 $threshold 0 use_filter
+'
+
+test_done

t/lib-encoding.sh, t/t0028-working-tree-encoding.sh, t/t2082-parallel-checkout-attributes.sh

diff --git a/t/lib-encoding.sh b/t/lib-encoding.sh
new file mode 100644
index 0000000000..c52ffbbed5
--- /dev/null
+++ b/t/lib-encoding.sh
@@ -0,0 +1,25 @@
+# Encoding helpers used by t0028 and t2082
+
+test_lazy_prereq NO_UTF16_BOM '
+	test $(printf abc | iconv -f UTF-8 -t UTF-16 | wc -c) = 6
+'
+
+test_lazy_prereq NO_UTF32_BOM '
+	test $(printf abc | iconv -f UTF-8 -t UTF-32 | wc -c) = 12
+'
+
+write_utf16 () {
+	if test_have_prereq NO_UTF16_BOM
+	then
+		printf '\376\377'
+	fi &&
+	iconv -f UTF-8 -t UTF-16
+}
+
+write_utf32 () {
+	if test_have_prereq NO_UTF32_BOM
+	then
+		printf '\0\0\376\377'
+	fi &&
+	iconv -f UTF-8 -t UTF-32
+}
diff --git a/t/t0028-working-tree-encoding.sh b/t/t0028-working-tree-encoding.sh
index bfc4fb9af5..4fffc3a639 100755
--- a/t/t0028-working-tree-encoding.sh
+++ b/t/t0028-working-tree-encoding.sh
@@ -3,33 +3,10 @@
 test_description='working-tree-encoding conversion via gitattributes'
 
 . ./test-lib.sh
+. "$TEST_DIRECTORY/lib-encoding.sh"
 
 GIT_TRACE_WORKING_TREE_ENCODING=1 && export GIT_TRACE_WORKING_TREE_ENCODING
 
-test_lazy_prereq NO_UTF16_BOM '
-	test $(printf abc | iconv -f UTF-8 -t UTF-16 | wc -c) = 6
-'
-
-test_lazy_prereq NO_UTF32_BOM '
-	test $(printf abc | iconv -f UTF-8 -t UTF-32 | wc -c) = 12
-'
-
-write_utf16 () {
-	if test_have_prereq NO_UTF16_BOM
-	then
-		printf '\376\377'
-	fi &&
-	iconv -f UTF-8 -t UTF-16
-}
-
-write_utf32 () {
-	if test_have_prereq NO_UTF32_BOM
-	then
-		printf '\0\0\376\377'
-	fi &&
-	iconv -f UTF-8 -t UTF-32
-}
-
 test_expect_success 'setup test files' '
 	git config core.eol lf &&
 
diff --git a/t/t2082-parallel-checkout-attributes.sh b/t/t2082-parallel-checkout-attributes.sh
new file mode 100755
index 0000000000..6800574588
--- /dev/null
+++ b/t/t2082-parallel-checkout-attributes.sh
@@ -0,0 +1,174 @@
+#!/bin/sh
+
+test_description='parallel-checkout: attributes
+
+Verify that parallel-checkout correctly creates files that require
+conversions, as specified in .gitattributes. The main point here is
+to check that the conv_attr data is correctly sent to the workers
+and that it contains sufficient information to smudge files
+properly (without access to the index or attribute stack).
+'
+
+TEST_NO_CREATE_REPO=1
+. ./test-lib.sh
+. "$TEST_DIRECTORY/lib-parallel-checkout.sh"
+. "$TEST_DIRECTORY/lib-encoding.sh"
+
+test_expect_success 'parallel-checkout with ident' '
+	git init ident &&
+	(
+		cd ident &&
+		echo "A ident" >.gitattributes &&
+		echo "\$Id\$" >A &&
+		echo "\$Id\$" >B &&
+		git add -A &&
+		git commit -m id &&
+
+		rm A B &&
+		git_pc 2 0 2 reset --hard &&
+		hexsz=$(test_oid hexsz) &&
+		grep -E "\\\$Id: [0-9a-f]{$hexsz} \\\$" A &&
+		grep "\\\$Id\\\$" B
+	)
+'
+
+test_expect_success 'parallel-checkout with re-encoding' '
+	git init encoding &&
+	(
+		cd encoding &&
+		echo text >utf8-text &&
+		cat utf8-text | write_utf16 >utf16-text &&
+
+		echo "A working-tree-encoding=UTF-16" >.gitattributes &&
+		cp utf16-text A &&
+		cp utf16-text B &&
+		git add A B .gitattributes &&
+		git commit -m encoding &&
+
+		# Check that A (and only A) is stored in UTF-8
+		git cat-file -p :A >A.internal &&
+		test_cmp_bin utf8-text A.internal &&
+		git cat-file -p :B >B.internal &&
+		test_cmp_bin utf16-text B.internal &&
+
+		# Check that A is re-encoded during checkout
+		rm A B &&
+		git_pc 2 0 2 checkout A B &&
+		test_cmp_bin utf16-text A
+	)
+'
+
+test_expect_success 'parallel-checkout with eol conversions' '
+	git init eol &&
+	(
+		cd eol &&
+		git config core.autocrlf false &&
+		printf "multi\r\nline\r\ntext" >crlf-text &&
+		printf "multi\nline\ntext" >lf-text &&
+
+		echo "A text eol=crlf" >.gitattributes &&
+		echo "B -text" >>.gitattributes &&
+		cp crlf-text A &&
+		cp crlf-text B &&
+		git add A B .gitattributes &&
+		git commit -m eol &&
+
+		# Check that A (and only A) is stored with LF format
+		git cat-file -p :A >A.internal &&
+		test_cmp_bin lf-text A.internal &&
+		git cat-file -p :B >B.internal &&
+		test_cmp_bin crlf-text B.internal &&
+
+		# Check that A is converted to CRLF during checkout
+		rm A B &&
+		git_pc 2 0 2 checkout A B &&
+		test_cmp_bin crlf-text A
+	)
+'
+
+test_cmp_str()
+{
+	echo "$1" >tmp &&
+	test_cmp tmp "$2"
+}
+
+# Entries that require an external filter are not eligible for parallel
+# checkout. Check that both the parallel-eligible and non-eligible entries are
+# properly writen in a single checkout process.
+#
+test_expect_success 'parallel-checkout and external filter' '
+	git init filter &&
+	(
+		cd filter &&
+		git config filter.x2y.clean "tr x y" &&
+		git config filter.x2y.smudge "tr y x" &&
+		git config filter.x2y.required true &&
+
+		echo "A filter=x2y" >.gitattributes &&
+		echo x >A &&
+		echo x >B &&
+		echo x >C &&
+		git add -A &&
+		git commit -m filter &&
+
+		# Check that A (and only A) was cleaned
+		git cat-file -p :A >A.internal &&
+		test_cmp_str y A.internal &&
+		git cat-file -p :B >B.internal &&
+		test_cmp_str x B.internal &&
+		git cat-file -p :C >C.internal &&
+		test_cmp_str x C.internal &&
+
+		rm A B C *.internal &&
+		git_pc 2 0 2 checkout A B C &&
+		test_cmp_str x A &&
+		test_cmp_str x B &&
+		test_cmp_str x C
+	)
+'
+
+# The delayed queue is independent from the parallel queue, and they should be
+# able to work together in the same checkout process.
+#
+test_expect_success PERL 'parallel-checkout and delayed checkout' '
+	write_script rot13-filter.pl "$PERL_PATH" \
+		<"$TEST_DIRECTORY"/t0021/rot13-filter.pl &&
+	test_config_global filter.delay.process \
+		"\"$(pwd)/rot13-filter.pl\" \"$(pwd)/delayed.log\" clean smudge delay" &&
+	test_config_global filter.delay.required true &&
+
+	echo "a b c" >delay-content &&
+	echo "n o p" >delay-rot13-content &&
+
+	git init delayed &&
+	(
+		cd delayed &&
+		echo "*.a filter=delay" >.gitattributes &&
+		cp ../delay-content test-delay10.a &&
+		cp ../delay-content test-delay11.a &&
+		echo parallel >parallel1.b &&
+		echo parallel >parallel2.b &&
+		git add -A &&
+		git commit -m delayed &&
+
+		# Check that the stored data was cleaned
+		git cat-file -p :test-delay10.a > delay10.internal &&
+		test_cmp delay10.internal ../delay-rot13-content &&
+		git cat-file -p :test-delay11.a > delay11.internal &&
+		test_cmp delay11.internal ../delay-rot13-content &&
+		rm *.internal &&
+
+		rm *.a *.b
+	) &&
+
+	git_pc 2 0 2 -C delayed checkout -f &&
+	verify_checkout delayed &&
+
+	# Check that the *.a files got to the delay queue and were filtered
+	grep "smudge test-delay10.a .* \[DELAYED\]" delayed.log &&
+	grep "smudge test-delay11.a .* \[DELAYED\]" delayed.log &&
+	test_cmp delayed/test-delay10.a delay-content &&
+	test_cmp delayed/test-delay11.a delay-content
+'
+
+test_done

ci/run-build-and-tests.sh, parallel-checkout.c, t/README, t/lib-parallel-checkout.sh, t/t2081-parallel-checkout-collisions.sh

diff --git a/ci/run-build-and-tests.sh b/ci/run-build-and-tests.sh
index 6c27b886b8..aa32ddc361 100755
--- a/ci/run-build-and-tests.sh
+++ b/ci/run-build-and-tests.sh
@@ -22,6 +22,7 @@ linux-gcc)
 	export GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS=1
 	export GIT_TEST_MULTI_PACK_INDEX=1
 	export GIT_TEST_ADD_I_USE_BUILTIN=1
+	export GIT_TEST_CHECKOUT_WORKERS=2
 	make test
 	;;
 linux-clang)
diff --git a/parallel-checkout.c b/parallel-checkout.c
index 5156b14c53..94b44d2a48 100644
--- a/parallel-checkout.c
+++ b/parallel-checkout.c
@@ -32,6 +32,20 @@ enum pc_status parallel_checkout_status(void)
 
 void get_parallel_checkout_configs(int *num_workers, int *threshold)
 {
+	char *env_workers = getenv("GIT_TEST_CHECKOUT_WORKERS");
+
+	if (env_workers && *env_workers) {
+		if (strtol_i(env_workers, 10, num_workers)) {
+			die("invalid value for GIT_TEST_CHECKOUT_WORKERS: '%s'",
+			    env_workers);
+		}
+		if (*num_workers < 1)
+			*num_workers = online_cpus();
+
+		*threshold = 0;
+		return;
+	}
+
 	if (git_config_get_int("checkout.workers", num_workers))
 		*num_workers = 1;
 	else if (*num_workers < 1)
diff --git a/t/README b/t/README
index 2adaf7c2d2..cd1b15c55a 100644
--- a/t/README
+++ b/t/README
@@ -425,6 +425,10 @@ GIT_TEST_DEFAULT_HASH=<hash-algo> specifies which hash algorithm to
 use in the test scripts. Recognized values for <hash-algo> are "sha1"
 and "sha256".
 
+GIT_TEST_CHECKOUT_WORKERS=<n> overrides the 'checkout.workers' setting
+to <n> and 'checkout.thresholdForParallelism' to 0, forcing the
+execution of the parallel-checkout code.
+
 Naming Tests
 ------------
 
diff --git a/t/lib-parallel-checkout.sh b/t/lib-parallel-checkout.sh
index c95ca27711..80bb0a0900 100644
--- a/t/lib-parallel-checkout.sh
+++ b/t/lib-parallel-checkout.sh
@@ -1,5 +1,11 @@
 # Helpers for t208* tests
 
+if ! test -z "$GIT_TEST_CHECKOUT_WORKERS"
+then
+	skip_all="skipping test, GIT_TEST_CHECKOUT_WORKERS is set"
+	test_done
+fi
+
 # Runs `git -c checkout.workers=$1 -c checkout.thesholdForParallelism=$2 ${@:4}`
 # and checks that the number of workers spawned is equal to $3.
 git_pc()
diff --git a/t/t2081-parallel-checkout-collisions.sh b/t/t2081-parallel-checkout-collisions.sh
index 3ce195b892..5dbff54bfb 100755
--- a/t/t2081-parallel-checkout-collisions.sh
+++ b/t/t2081-parallel-checkout-collisions.sh
@@ -3,6 +3,7 @@
 test_description='parallel-checkout collisions'
 
 . ./test-lib.sh
+. "$TEST_DIRECTORY/lib-parallel-checkout.sh"
 
 # When there are pathname collisions during a clone, Git should report a warning
 # listing all of the colliding entries. The sequential code detects a collision