Add virtual file system settings and hook proc

On index load, clear/set the skip worktree bits based on the virtual
file system data. Use virtual file system data to update skip-worktree
bit in unpack-trees. Use virtual file system data to exclude files and
folders not explicitly requested.

Update 2022-04-05: disable the "present-despite-SKIP_WORKTREE" file removal
behavior when 'core.virtualfilesystem' is enabled.

Signed-off-by: Ben Peart <benpeart@microsoft.com>

Documentation/config/core.txt

@@ -111,6 +111,14 @@ Version 2 uses an opaque string so that the monitor can return
 something that can be used to determine what files have changed
 without race conditions.
 
+core.virtualFilesystem::
+	If set, the value of this variable is used as a command which
+	will identify all files and directories that are present in
+	the working directory.  Git will only track and update files
+	listed in the virtual file system.  Using the virtual file system
+	will supersede the sparse-checkout settings which will be ignored.
+	See the "virtual file system" section of linkgit:githooks[5].
+
 core.trustctime::
 	If false, the ctime differences between the index and the
 	working tree are ignored; useful when the inode change time

Documentation/githooks.txt

@@ -698,6 +698,26 @@ and "0" meaning they were not.
 Only one parameter should be set to "1" when the hook runs.  The hook
 running passing "1", "1" should not be possible.
 
+virtualFilesystem
+~~~~~~~~~~~~~~~~~~
+
+"Virtual File System" allows populating the working directory sparsely.
+The projection data is typically automatically generated by an external
+process.  Git will limit what files it checks for changes as well as which
+directories are checked for untracked files based on the path names given.
+Git will also only update those files listed in the projection.
+
+The hook is invoked when the configuration option core.virtualFilesystem
+is set.  It takes one argument, a version (currently 1).
+
+The hook should output to stdout the list of all files in the working
+directory that git should track.  The paths are relative to the root
+of the working directory and are separated by a single NUL.  Full paths
+('dir1/a.txt') as well as directories are supported (ie 'dir1/').
+
+The exit status determines whether git will use the data from the
+hook.  On error, git will abort the command with an error message.
+
 SEE ALSO
 --------
 linkgit:git-hook[1]

Makefile

@@ -1121,6 +1121,7 @@ LIB_OBJS += utf8.o
 LIB_OBJS += varint.o
 LIB_OBJS += version.o
 LIB_OBJS += versioncmp.o
+LIB_OBJS += virtualfilesystem.o
 LIB_OBJS += walker.o
 LIB_OBJS += wildmatch.o
 LIB_OBJS += worktree.o

cache.h

@@ -1074,6 +1074,7 @@ enum fsync_method {
 
 extern enum fsync_method fsync_method;
 extern int core_preload_index;
+extern const char *core_virtualfilesystem;
 extern int core_gvfs;
 extern int precomposed_unicode;
 extern int protect_hfs;

config.c

@@ -1736,7 +1736,11 @@ int git_default_core_config(const char *var, const char *value, void *cb)
 	}
 
 	if (!strcmp(var, "core.sparsecheckout")) {
-		core_apply_sparse_checkout = git_config_bool(var, value);
+		/* virtual file system relies on the sparse checkout logic so force it on */
+		if (core_virtualfilesystem)
+			core_apply_sparse_checkout = 1;
+		else
+			core_apply_sparse_checkout = git_config_bool(var, value);
 		return 0;
 	}
 
@@ -2800,6 +2804,30 @@ int git_config_get_max_percent_split_change(void)
 	return -1; /* default value */
 }
 
+int git_config_get_virtualfilesystem(void)
+{
+	/* Run only once. */
+	static int virtual_filesystem_result = -1;
+	if (virtual_filesystem_result >= 0)
+		return virtual_filesystem_result;
+
+	if (git_config_get_pathname("core.virtualfilesystem", &core_virtualfilesystem))
+		core_virtualfilesystem = getenv("GIT_VIRTUALFILESYSTEM_TEST");
+
+	if (core_virtualfilesystem && !*core_virtualfilesystem)
+		core_virtualfilesystem = NULL;
+
+	/* virtual file system relies on the sparse checkout logic so force it on */
+	if (core_virtualfilesystem) {
+		core_apply_sparse_checkout = 1;
+		virtual_filesystem_result = 1;
+		return 1;
+	}
+
+	virtual_filesystem_result = 0;
+	return 0;
+}
+
 int git_config_get_index_threads(int *dest)
 {
 	int is_bool, val;

config.h

@@ -614,6 +614,7 @@ int git_config_get_pathname(const char *key, const char **dest);
 int git_config_get_index_threads(int *dest);
 int git_config_get_split_index(void);
 int git_config_get_max_percent_split_change(void);
+int git_config_get_virtualfilesystem(void);
 
 /* This dies if the configured or default date is in the future */
 int git_config_get_expiry(const char *key, const char **output);

dir.c

@@ -6,6 +6,7 @@
  *		 Junio Hamano, 2005-2006
  */
 #include "cache.h"
+#include "virtualfilesystem.h"
 #include "config.h"
 #include "dir.h"
 #include "object-store.h"
@@ -1414,6 +1415,17 @@ enum pattern_match_result path_matches_pattern_list(
 	int result = NOT_MATCHED;
 	size_t slash_pos;
 
+	/*
+	 * The virtual file system data is used to prevent git from traversing
+	 * any part of the tree that is not in the virtual file system.  Return
+	 * 1 to exclude the entry if it is not found in the virtual file system,
+	 * else fall through to the regular excludes logic as it may further exclude.
+	 */
+	if (*dtype == DT_UNKNOWN)
+		*dtype = resolve_dtype(DT_UNKNOWN, istate, pathname, pathlen);
+	if (is_excluded_from_virtualfilesystem(pathname, pathlen, *dtype) > 0)
+		return 1;
+
 	if (!pl->use_cone_patterns) {
 		pattern = last_matching_pattern_from_list(pathname, pathlen, basename,
 							dtype, pl, istate);
@@ -1757,8 +1769,20 @@ struct path_pattern *last_matching_pattern(struct dir_struct *dir,
 int is_excluded(struct dir_struct *dir, struct index_state *istate,
 		const char *pathname, int *dtype_p)
 {
-	struct path_pattern *pattern =
+	struct path_pattern *pattern;
-		last_matching_pattern(dir, istate, pathname, dtype_p);
+
+	/*
+	 * The virtual file system data is used to prevent git from traversing
+	 * any part of the tree that is not in the virtual file system.  Return
+	 * 1 to exclude the entry if it is not found in the virtual file system,
+	 * else fall through to the regular excludes logic as it may further exclude.
+	 */
+	if (*dtype_p == DT_UNKNOWN)
+		*dtype_p = resolve_dtype(DT_UNKNOWN, istate, pathname, strlen(pathname));
+	if (is_excluded_from_virtualfilesystem(pathname, strlen(pathname), *dtype_p) > 0)
+		return 1;
+
+	pattern = last_matching_pattern(dir, istate, pathname, dtype_p);
 	if (pattern)
 		return pattern->flags & PATTERN_FLAG_NEGATIVE ? 0 : 1;
 	return 0;
@@ -2344,6 +2368,8 @@ static enum path_treatment treat_path(struct dir_struct *dir,
 						ignore_case);
 	if (dtype != DT_DIR && has_path_in_index)
 		return path_none;
+	if (is_excluded_from_virtualfilesystem(path->buf, path->len, dtype) > 0)
+		return path_excluded;
 
 	/*
 	 * When we are looking at a directory P in the working tree,
@@ -2548,6 +2574,8 @@ static void add_path_to_appropriate_result_list(struct dir_struct *dir,
 	/* add the path to the appropriate result list */
 	switch (state) {
 	case path_excluded:
+		if (is_excluded_from_virtualfilesystem(path->buf, path->len, DT_DIR) > 0)
+			break;
 		if (dir->flags & DIR_SHOW_IGNORED)
 			dir_add_name(dir, istate, path->buf, path->len);
 		else if ((dir->flags & DIR_SHOW_IGNORED_TOO) ||

environment.c

@@ -73,6 +73,7 @@ int core_apply_sparse_checkout;
 int core_sparse_checkout_cone;
 int sparse_expect_files_outside_of_patterns;
 int core_gvfs;
+const char *core_virtualfilesystem;
 int merge_log_config = -1;
 int precomposed_unicode = -1; /* see probe_utf8_pathname_composition() */
 unsigned long pack_size_limit_cfg;

read-cache.c

@@ -5,6 +5,7 @@
  */
 #include "cache.h"
 #include "gvfs.h"
+#include "virtualfilesystem.h"
 #include "config.h"
 #include "diff.h"
 #include "diffcore.h"
@@ -2047,6 +2048,7 @@ static void post_read_index_from(struct index_state *istate)
 	tweak_untracked_cache(istate);
 	tweak_split_index(istate);
 	tweak_fsmonitor(istate);
+	apply_virtualfilesystem(istate);
 }
 
 static size_t estimate_cache_size_from_compressed(unsigned int entries)

sparse-index.c

@@ -495,6 +495,7 @@ void clear_skip_worktree_from_present_files(struct index_state *istate)
 	int i;
 
 	if (!core_apply_sparse_checkout ||
+	    core_virtualfilesystem ||
 	    sparse_expect_files_outside_of_patterns)
 		return;
 

t/t1090-sparse-checkout-scope.sh

@@ -107,9 +107,9 @@ test_expect_success 'in partial clone, sparse checkout only fetches needed blobs
 '
 
 test_expect_success 'checkout does not delete items outside the sparse checkout file' '
-	# The "sparse.expectfilesoutsideofpatterns" config will prevent the
+	# The "core.virtualfilesystem" config will prevent the
 	# SKIP_WORKTREE flag from being dropped on files present on-disk.
-	test_config sparse.expectfilesoutsideofpatterns true &&
+	test_config core.virtualfilesystem true &&
 
 	test_config core.gvfs 8 &&
 	git checkout -b outside &&

t/t1093-virtualfilesystem.sh

@@ -0,0 +1,350 @@
+#!/bin/sh
+
+test_description='virtual file system tests'
+
+. ./test-lib.sh
+
+clean_repo () {
+	rm .git/index &&
+	git -c core.virtualfilesystem= reset --hard HEAD &&
+	git -c core.virtualfilesystem= clean -fd &&
+	touch untracked.txt &&
+	touch dir1/untracked.txt &&
+	touch dir2/untracked.txt
+}
+
+test_expect_success 'setup' '
+	git branch -M main &&
+	mkdir -p .git/hooks/ &&
+	cat > .gitignore <<-\EOF &&
+		.gitignore
+		expect*
+		actual*
+	EOF
+	mkdir -p dir1 &&
+	touch dir1/file1.txt &&
+	touch dir1/file2.txt &&
+	mkdir -p dir2 &&
+	touch dir2/file1.txt &&
+	touch dir2/file2.txt &&
+	git add . &&
+	git commit -m "initial" &&
+	git config --local core.virtualfilesystem .git/hooks/virtualfilesystem
+'
+
+test_expect_success 'test hook parameters and version' '
+	clean_repo &&
+	write_script .git/hooks/virtualfilesystem <<-\EOF &&
+		if test "$#" -ne 1
+		then
+			echo "$0: Exactly 1 argument expected" >&2
+			exit 2
+		fi
+
+		if test "$1" != 1
+		then
+			echo "$0: Unsupported hook version." >&2
+			exit 1
+		fi
+	EOF
+	git status &&
+	write_script .git/hooks/virtualfilesystem <<-\EOF &&
+		exit 3
+	EOF
+	test_must_fail git status
+'
+
+test_expect_success 'verify status is clean' '
+	clean_repo &&
+	write_script .git/hooks/virtualfilesystem <<-\EOF &&
+		printf "dir2/file1.txt\0"
+	EOF
+	rm -f .git/index &&
+	git checkout -f &&
+	write_script .git/hooks/virtualfilesystem <<-\EOF &&
+		printf "dir2/file1.txt\0"
+		printf "dir1/file1.txt\0"
+		printf "dir1/file2.txt\0"
+	EOF
+	git status > actual &&
+	cat > expected <<-\EOF &&
+		On branch main
+		nothing to commit, working tree clean
+	EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'verify skip-worktree bit is set for absolute path' '
+	clean_repo &&
+	write_script .git/hooks/virtualfilesystem <<-\EOF &&
+		printf "dir1/file1.txt\0"
+	EOF
+	git ls-files -v > actual &&
+	cat > expected <<-\EOF &&
+		H dir1/file1.txt
+		S dir1/file2.txt
+		S dir2/file1.txt
+		S dir2/file2.txt
+	EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'verify skip-worktree bit is cleared for absolute path' '
+	clean_repo &&
+	write_script .git/hooks/virtualfilesystem <<-\EOF &&
+		printf "dir1/file2.txt\0"
+	EOF
+	git ls-files -v > actual &&
+	cat > expected <<-\EOF &&
+		S dir1/file1.txt
+		H dir1/file2.txt
+		S dir2/file1.txt
+		S dir2/file2.txt
+	EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'verify folder wild cards' '
+	clean_repo &&
+	write_script .git/hooks/virtualfilesystem <<-\EOF &&
+		printf "dir1/\0"
+	EOF
+	git ls-files -v > actual &&
+	cat > expected <<-\EOF &&
+		H dir1/file1.txt
+		H dir1/file2.txt
+		S dir2/file1.txt
+		S dir2/file2.txt
+	EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'verify folders not included are ignored' '
+	clean_repo &&
+	write_script .git/hooks/virtualfilesystem <<-\EOF &&
+		printf "dir1/file1.txt\0"
+		printf "dir1/file2.txt\0"
+	EOF
+	mkdir -p dir1/dir2 &&
+	touch dir1/a &&
+	touch dir1/b &&
+	touch dir1/dir2/a &&
+	touch dir1/dir2/b &&
+	git add . &&
+	git ls-files -v > actual &&
+	cat > expected <<-\EOF &&
+		H dir1/file1.txt
+		H dir1/file2.txt
+		S dir2/file1.txt
+		S dir2/file2.txt
+	EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'verify including one file doesnt include the rest' '
+	clean_repo &&
+	write_script .git/hooks/virtualfilesystem <<-\EOF &&
+		printf "dir1/file1.txt\0"
+		printf "dir1/file2.txt\0"
+		printf "dir1/dir2/a\0"
+	EOF
+	mkdir -p dir1/dir2 &&
+	touch dir1/a &&
+	touch dir1/b &&
+	touch dir1/dir2/a &&
+	touch dir1/dir2/b &&
+	git add . &&
+	git ls-files -v > actual &&
+	cat > expected <<-\EOF &&
+		H dir1/dir2/a
+		H dir1/file1.txt
+		H dir1/file2.txt
+		S dir2/file1.txt
+		S dir2/file2.txt
+	EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'verify files not listed are ignored by git clean -f -x' '
+	clean_repo &&
+	write_script .git/hooks/virtualfilesystem <<-\EOF &&
+		printf "untracked.txt\0"
+		printf "dir1/\0"
+	EOF
+	mkdir -p dir3 &&
+	touch dir3/untracked.txt &&
+	git clean -f -x &&
+	test ! -f untracked.txt &&
+	test -d dir1 &&
+	test -f dir1/file1.txt &&
+	test -f dir1/file2.txt &&
+	test ! -f dir1/untracked.txt &&
+	test -f dir2/file1.txt &&
+	test -f dir2/file2.txt &&
+	test -f dir2/untracked.txt &&
+	test -d dir3 &&
+	test -f dir3/untracked.txt
+'
+
+test_expect_success 'verify files not listed are ignored by git clean -f -d -x' '
+	clean_repo &&
+	write_script .git/hooks/virtualfilesystem <<-\EOF &&
+		printf "untracked.txt\0"
+		printf "dir1/\0"
+		printf "dir3/\0"
+	EOF
+	mkdir -p dir3 &&
+	touch dir3/untracked.txt &&
+	git clean -f -d -x &&
+	test ! -f untracked.txt &&
+	test -d dir1 &&
+	test -f dir1/file1.txt &&
+	test -f dir1/file2.txt &&
+	test ! -f dir1/untracked.txt &&
+	test -f dir2/file1.txt &&
+	test -f dir2/file2.txt &&
+	test -f dir2/untracked.txt &&
+	test ! -d dir3 &&
+	test ! -f dir3/untracked.txt
+'
+
+test_expect_success 'verify folder entries include all files' '
+	clean_repo &&
+	write_script .git/hooks/virtualfilesystem <<-\EOF &&
+		printf "dir1/\0"
+	EOF
+	mkdir -p dir1/dir2 &&
+	touch dir1/a &&
+	touch dir1/b &&
+	touch dir1/dir2/a &&
+	touch dir1/dir2/b &&
+	git status -su > actual &&
+	cat > expected <<-\EOF &&
+		?? dir1/a
+		?? dir1/b
+		?? dir1/untracked.txt
+	EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'verify case insensitivity of virtual file system entries' '
+	clean_repo &&
+	write_script .git/hooks/virtualfilesystem <<-\EOF &&
+		printf "dir1/a\0"
+		printf "Dir1/Dir2/a\0"
+		printf "DIR2/\0"
+	EOF
+	mkdir -p dir1/dir2 &&
+	touch dir1/a &&
+	touch dir1/b &&
+	touch dir1/dir2/a &&
+	touch dir1/dir2/b &&
+	git -c core.ignorecase=false status -su > actual &&
+	cat > expected <<-\EOF &&
+		?? dir1/a
+	EOF
+	test_cmp expected actual &&
+	git -c core.ignorecase=true status -su > actual &&
+	cat > expected <<-\EOF &&
+		?? dir1/a
+		?? dir1/dir2/a
+		?? dir2/untracked.txt
+	EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'on file created' '
+	clean_repo &&
+	write_script .git/hooks/virtualfilesystem <<-\EOF &&
+		printf "dir1/file3.txt\0"
+	EOF
+	touch dir1/file3.txt &&
+	git add . &&
+	git ls-files -v > actual &&
+	cat > expected <<-\EOF &&
+		S dir1/file1.txt
+		S dir1/file2.txt
+		H dir1/file3.txt
+		S dir2/file1.txt
+		S dir2/file2.txt
+	EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'on file renamed' '
+	clean_repo &&
+	write_script .git/hooks/virtualfilesystem <<-\EOF &&
+		printf "dir1/file1.txt\0"
+		printf "dir1/file3.txt\0"
+	EOF
+	mv dir1/file1.txt dir1/file3.txt &&
+	git status -su > actual &&
+	cat > expected <<-\EOF &&
+		 D dir1/file1.txt
+		?? dir1/file3.txt
+	EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'on file deleted' '
+	clean_repo &&
+	write_script .git/hooks/virtualfilesystem <<-\EOF &&
+		printf "dir1/file1.txt\0"
+	EOF
+	rm dir1/file1.txt &&
+	git status -su > actual &&
+	cat > expected <<-\EOF &&
+		 D dir1/file1.txt
+	EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'on file overwritten' '
+	clean_repo &&
+	write_script .git/hooks/virtualfilesystem <<-\EOF &&
+		printf "dir1/file1.txt\0"
+	EOF
+	echo "overwritten" > dir1/file1.txt &&
+	git status -su > actual &&
+	cat > expected <<-\EOF &&
+		 M dir1/file1.txt
+	EOF
+	test_cmp expected actual
+'
+
+test_expect_success 'on folder created' '
+	clean_repo &&
+	write_script .git/hooks/virtualfilesystem <<-\EOF &&
+		printf "dir1/dir1/\0"
+	EOF
+	mkdir -p dir1/dir1 &&
+	git status -su > actual &&
+	cat > expected <<-\EOF &&
+	EOF
+	test_cmp expected actual &&
+	git clean -fd &&
+	test ! -d "/dir1/dir1"
+'
+
+test_expect_success 'on folder renamed' '
+	clean_repo &&
+	write_script .git/hooks/virtualfilesystem <<-\EOF &&
+		printf "dir3/\0"
+		printf "dir1/file1.txt\0"
+		printf "dir1/file2.txt\0"
+		printf "dir3/file1.txt\0"
+		printf "dir3/file2.txt\0"
+	EOF
+	mv dir1 dir3 &&
+	git status -su > actual &&
+	cat > expected <<-\EOF &&
+		 D dir1/file1.txt
+		 D dir1/file2.txt
+		?? dir3/file1.txt
+		?? dir3/file2.txt
+		?? dir3/untracked.txt
+	EOF
+	test_cmp expected actual
+'
+
+test_done

unpack-trees.c

@@ -1,5 +1,6 @@
 #include "cache.h"
 #include "gvfs.h"
+#include "virtualfilesystem.h"
 #include "strvec.h"
 #include "repository.h"
 #include "config.h"
@@ -1682,6 +1683,14 @@ static int clear_ce_flags_1(struct index_state *istate,
 			continue;
 		}
 
+		/* if it's not in the virtual file system, exit early */
+		if (core_virtualfilesystem) {
+			if (is_included_in_virtualfilesystem(ce->name, ce->ce_namelen) > 0)
+				ce->ce_flags &= ~clear_mask;
+			cache++;
+			continue;
+		}
+
 		if (prefix->len && strncmp(ce->name, prefix->buf, prefix->len))
 			break;
 
@@ -1903,7 +1912,10 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options
 	if (!o->skip_sparse_checkout && !o->pl) {
 		memset(&pl, 0, sizeof(pl));
 		free_pattern_list = 1;
-		populate_from_existing_patterns(o, &pl);
+		if (core_virtualfilesystem)
+			o->pl = &pl;
+		else
+			populate_from_existing_patterns(o, &pl);
 	}
 
 	memset(&o->result, 0, sizeof(o->result));

virtualfilesystem.c

@@ -0,0 +1,308 @@
+#include "cache.h"
+#include "config.h"
+#include "dir.h"
+#include "hashmap.h"
+#include "run-command.h"
+#include "virtualfilesystem.h"
+
+#define HOOK_INTERFACE_VERSION	(1)
+
+static struct strbuf virtual_filesystem_data = STRBUF_INIT;
+static struct hashmap virtual_filesystem_hashmap;
+static struct hashmap parent_directory_hashmap;
+
+struct virtualfilesystem {
+	struct hashmap_entry ent; /* must be the first member! */
+	const char *pattern;
+	int patternlen;
+};
+
+static unsigned int(*vfshash)(const void *buf, size_t len);
+static int(*vfscmp)(const char *a, const char *b, size_t len);
+
+static int vfs_hashmap_cmp(const void *unused_cmp_data,
+			   const struct hashmap_entry *he1,
+			   const struct hashmap_entry *he2,
+			   const void *key)
+{
+	const struct virtualfilesystem *vfs1 =
+		container_of(he1, const struct virtualfilesystem, ent);
+	const struct virtualfilesystem *vfs2 =
+		container_of(he2, const struct virtualfilesystem, ent);
+
+	return vfscmp(vfs1->pattern, vfs2->pattern, vfs1->patternlen);
+}
+
+static void get_virtual_filesystem_data(struct strbuf *vfs_data)
+{
+	struct child_process cp = CHILD_PROCESS_INIT;
+	int err;
+
+	strbuf_init(vfs_data, 0);
+
+	strvec_push(&cp.args, core_virtualfilesystem);
+	strvec_pushf(&cp.args, "%d", HOOK_INTERFACE_VERSION);
+	cp.use_shell = 1;
+	cp.dir = get_git_work_tree();
+
+	err = capture_command(&cp, vfs_data, 1024);
+	if (err)
+		die("unable to load virtual file system");
+}
+
+static int check_includes_hashmap(struct hashmap *map, const char *pattern, int patternlen)
+{
+	struct strbuf sb = STRBUF_INIT;
+	struct virtualfilesystem vfs;
+	char *slash;
+
+	/* Check straight mapping */
+	strbuf_reset(&sb);
+	strbuf_add(&sb, pattern, patternlen);
+	vfs.pattern = sb.buf;
+	vfs.patternlen = sb.len;
+	hashmap_entry_init(&vfs.ent, vfshash(vfs.pattern, vfs.patternlen));
+	if (hashmap_get_entry(map, &vfs, ent, NULL)) {
+		strbuf_release(&sb);
+		return 1;
+	}
+
+	/*
+	 * Check to see if it matches a directory or any path
+	 * underneath it.  In other words, 'a/b/foo.txt' will match
+	 * '/', 'a/', and 'a/b/'.
+	 */
+	slash = strchr(sb.buf, '/');
+	while (slash) {
+		vfs.pattern = sb.buf;
+		vfs.patternlen = slash - sb.buf + 1;
+		hashmap_entry_init(&vfs.ent, vfshash(vfs.pattern, vfs.patternlen));
+		if (hashmap_get_entry(map, &vfs, ent, NULL)) {
+			strbuf_release(&sb);
+			return 1;
+		}
+		slash = strchr(slash + 1, '/');
+	}
+
+	strbuf_release(&sb);
+	return 0;
+}
+
+static void includes_hashmap_add(struct hashmap *map, const char *pattern, const int patternlen)
+{
+	struct virtualfilesystem *vfs;
+
+	vfs = xmalloc(sizeof(struct virtualfilesystem));
+	vfs->pattern = pattern;
+	vfs->patternlen = patternlen;
+	hashmap_entry_init(&vfs->ent, vfshash(vfs->pattern, vfs->patternlen));
+	hashmap_add(map, &vfs->ent);
+}
+
+static void initialize_includes_hashmap(struct hashmap *map, struct strbuf *vfs_data)
+{
+	char *buf, *entry;
+	size_t len;
+	int i;
+
+	/*
+	 * Build a hashmap of the virtual file system data we can use to look
+	 * for cache entry matches quickly
+	 */
+	vfshash = ignore_case ? memihash : memhash;
+	vfscmp = ignore_case ? strncasecmp : strncmp;
+	hashmap_init(map, vfs_hashmap_cmp, NULL, 0);
+
+	entry = buf = vfs_data->buf;
+	len = vfs_data->len;
+	for (i = 0; i < len; i++) {
+		if (buf[i] == '\0') {
+			includes_hashmap_add(map, entry, buf + i - entry);
+			entry = buf + i + 1;
+		}
+	}
+}
+
+/*
+ * Return 1 if the requested item is found in the virtual file system,
+ * 0 for not found and -1 for undecided.
+ */
+int is_included_in_virtualfilesystem(const char *pathname, int pathlen)
+{
+	if (!core_virtualfilesystem)
+		return -1;
+
+	if (!virtual_filesystem_hashmap.tablesize && virtual_filesystem_data.len)
+		initialize_includes_hashmap(&virtual_filesystem_hashmap, &virtual_filesystem_data);
+	if (!virtual_filesystem_hashmap.tablesize)
+		return -1;
+
+	return check_includes_hashmap(&virtual_filesystem_hashmap, pathname, pathlen);
+}
+
+static void parent_directory_hashmap_add(struct hashmap *map, const char *pattern, const int patternlen)
+{
+	char *slash;
+	struct virtualfilesystem *vfs;
+
+	/*
+	 * Add any directories leading up to the file as the excludes logic
+	 * needs to match directories leading up to the files as well. Detect
+	 * and prevent unnecessary duplicate entries which will be common.
+	 */
+	if (patternlen > 1) {
+		slash = strchr(pattern + 1, '/');
+		while (slash) {
+			vfs = xmalloc(sizeof(struct virtualfilesystem));
+			vfs->pattern = pattern;
+			vfs->patternlen = slash - pattern + 1;
+			hashmap_entry_init(&vfs->ent, vfshash(vfs->pattern, vfs->patternlen));
+			if (hashmap_get_entry(map, vfs, ent, NULL))
+				free(vfs);
+			else
+				hashmap_add(map, &vfs->ent);
+			slash = strchr(slash + 1, '/');
+		}
+	}
+}
+
+static void initialize_parent_directory_hashmap(struct hashmap *map, struct strbuf *vfs_data)
+{
+	char *buf, *entry;
+	size_t len;
+	int i;
+
+	/*
+	 * Build a hashmap of the parent directories contained in the virtual
+	 * file system data we can use to look for matches quickly
+	 */
+	vfshash = ignore_case ? memihash : memhash;
+	vfscmp = ignore_case ? strncasecmp : strncmp;
+	hashmap_init(map, vfs_hashmap_cmp, NULL, 0);
+
+	entry = buf = vfs_data->buf;
+	len = vfs_data->len;
+	for (i = 0; i < len; i++) {
+		if (buf[i] == '\0') {
+			parent_directory_hashmap_add(map, entry, buf + i - entry);
+			entry = buf + i + 1;
+		}
+	}
+}
+
+static int check_directory_hashmap(struct hashmap *map, const char *pathname, int pathlen)
+{
+	struct strbuf sb = STRBUF_INIT;
+	struct virtualfilesystem vfs;
+
+	/* Check for directory */
+	strbuf_reset(&sb);
+	strbuf_add(&sb, pathname, pathlen);
+	strbuf_addch(&sb, '/');
+	vfs.pattern = sb.buf;
+	vfs.patternlen = sb.len;
+	hashmap_entry_init(&vfs.ent, vfshash(vfs.pattern, vfs.patternlen));
+	if (hashmap_get_entry(map, &vfs, ent, NULL)) {
+		strbuf_release(&sb);
+		return 0;
+	}
+
+	strbuf_release(&sb);
+	return 1;
+}
+
+/*
+ * Return 1 for exclude, 0 for include and -1 for undecided.
+ */
+int is_excluded_from_virtualfilesystem(const char *pathname, int pathlen, int dtype)
+{
+	if (!core_virtualfilesystem)
+		return -1;
+
+	if (dtype != DT_REG && dtype != DT_DIR && dtype != DT_LNK)
+		die(_("is_excluded_from_virtualfilesystem passed unhandled dtype"));
+
+	if (dtype == DT_REG) {
+		int ret = is_included_in_virtualfilesystem(pathname, pathlen);
+		if (ret > 0)
+			return 0;
+		if (ret == 0)
+			return 1;
+		return ret;
+	}
+
+	if (dtype == DT_DIR || dtype == DT_LNK) {
+		if (!parent_directory_hashmap.tablesize && virtual_filesystem_data.len)
+			initialize_parent_directory_hashmap(&parent_directory_hashmap, &virtual_filesystem_data);
+		if (!parent_directory_hashmap.tablesize)
+			return -1;
+
+		return check_directory_hashmap(&parent_directory_hashmap, pathname, pathlen);
+	}
+
+	return -1;
+}
+
+/*
+ * Update the CE_SKIP_WORKTREE bits based on the virtual file system.
+ */
+void apply_virtualfilesystem(struct index_state *istate)
+{
+	char *buf, *entry;
+	int i;
+
+	if (!git_config_get_virtualfilesystem())
+		return;
+
+	if (!virtual_filesystem_data.len)
+		get_virtual_filesystem_data(&virtual_filesystem_data);
+
+	/* set CE_SKIP_WORKTREE bit on all entries */
+	for (i = 0; i < istate->cache_nr; i++)
+		istate->cache[i]->ce_flags |= CE_SKIP_WORKTREE;
+
+	/* clear CE_SKIP_WORKTREE bit for everything in the virtual file system */
+	entry = buf = virtual_filesystem_data.buf;
+	for (i = 0; i < virtual_filesystem_data.len; i++) {
+		if (buf[i] == '\0') {
+			int pos, len;
+
+			len = buf + i - entry;
+
+			/* look for a directory wild card (ie "dir1/") */
+			if (buf[i - 1] == '/') {
+				if (ignore_case)
+					adjust_dirname_case(istate, entry);
+				pos = index_name_pos(istate, entry, len - 1);
+				if (pos < 0) {
+					pos = -pos - 1;
+					while (pos < istate->cache_nr && !fspathncmp(istate->cache[pos]->name, entry, len)) {
+						istate->cache[pos]->ce_flags &= ~CE_SKIP_WORKTREE;
+						pos++;
+					}
+				}
+			} else {
+				if (ignore_case) {
+					struct cache_entry *ce = index_file_exists(istate, entry, len, ignore_case);
+					if (ce)
+						ce->ce_flags &= ~CE_SKIP_WORKTREE;
+				} else {
+					int pos = index_name_pos(istate, entry, len);
+					if (pos >= 0)
+						istate->cache[pos]->ce_flags &= ~CE_SKIP_WORKTREE;
+				}
+			}
+
+			entry += len + 1;
+		}
+	}
+}
+
+/*
+ * Free the virtual file system data structures.
+ */
+void free_virtualfilesystem(void) {
+	hashmap_clear_and_free(&virtual_filesystem_hashmap, struct virtualfilesystem, ent);
+	hashmap_clear_and_free(&parent_directory_hashmap, struct virtualfilesystem, ent);
+	strbuf_release(&virtual_filesystem_data);
+}

virtualfilesystem.h

@@ -0,0 +1,25 @@
+#ifndef VIRTUALFILESYSTEM_H
+#define VIRTUALFILESYSTEM_H
+
+/*
+ * Update the CE_SKIP_WORKTREE bits based on the virtual file system.
+ */
+void apply_virtualfilesystem(struct index_state *istate);
+
+/*
+ * Return 1 if the requested item is found in the virtual file system,
+ * 0 for not found and -1 for undecided.
+ */
+int is_included_in_virtualfilesystem(const char *pathname, int pathlen);
+
+/*
+ * Return 1 for exclude, 0 for include and -1 for undecided.
+ */
+int is_excluded_from_virtualfilesystem(const char *pathname, int pathlen, int dtype);
+
+/*
+ * Free the virtual file system data structures.
+ */
+void free_virtualfilesystem(void);
+
+#endif

wt-status.c

@@ -1572,6 +1572,8 @@ static void show_sparse_checkout_in_use(struct wt_status *s,
 {
 	if (s->state.sparse_checkout_percentage == SPARSE_CHECKOUT_DISABLED)
 		return;
+	if (core_virtualfilesystem)
+		return;
 
 	if (s->state.sparse_checkout_percentage == SPARSE_CHECKOUT_SPARSE_INDEX)
 		status_printf_ln(s, color, _("You are in a sparse checkout."));