Merge branch 'sp/stream-clean-filter'

When running a required clean filter, we do not have to mmap the
original before feeding the filter.  Instead, stream the file
contents directly to the filter and process its output.

* sp/stream-clean-filter:
  sha1_file: don't convert off_t to size_t too early to avoid potential die()
  convert: stream from fd to required clean filter to reduce used address space
  copy_fd(): do not close the input file descriptor
  mmap_limit: introduce GIT_MMAP_LIMIT to allow testing expected mmap size
  memory_limit: use git_env_ulong() to parse GIT_ALLOC_LIMIT
  config.c: add git_env_ulong() to parse environment variable
  convert: drop arguments other than 'path' from would_convert_to_git()

1 files changed, 53 insertions, 7 deletions

diff --git a/sha1_file.c b/sha1_file.c
index c08c0cbea8..6f18c22ab1 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -663,10 +663,26 @@ void release_pack_memory(size_t need)
 		; /* nothing */
 }
 
+static void mmap_limit_check(size_t length)
+{
+	static size_t limit = 0;
+	if (!limit) {
+		limit = git_env_ulong("GIT_MMAP_LIMIT", 0);
+		if (!limit)
+			limit = SIZE_MAX;
+	}
+	if (length > limit)
+		die("attempting to mmap %"PRIuMAX" over limit %"PRIuMAX,
+		    (uintmax_t)length, (uintmax_t)limit);
+}
+
 void *xmmap(void *start, size_t length,
 	int prot, int flags, int fd, off_t offset)
 {
-	void *ret = mmap(start, length, prot, flags, fd, offset);
+	void *ret;
+
+	mmap_limit_check(length);
+	ret = mmap(start, length, prot, flags, fd, offset);
 	if (ret == MAP_FAILED) {
 		if (!length)
 			return NULL;
@@ -3076,6 +3092,29 @@ static int index_mem(unsigned char *sha1, void *buf, size_t size,
 	return ret;
 }
 
+static int index_stream_convert_blob(unsigned char *sha1, int fd,
+				     const char *path, unsigned flags)
+{
+	int ret;
+	const int write_object = flags & HASH_WRITE_OBJECT;
+	struct strbuf sbuf = STRBUF_INIT;
+
+	assert(path);
+	assert(would_convert_to_git_filter_fd(path));
+
+	convert_to_git_filter_fd(path, fd, &sbuf,
+				 write_object ? safe_crlf : SAFE_CRLF_FALSE);
+
+	if (write_object)
+		ret = write_sha1_file(sbuf.buf, sbuf.len, typename(OBJ_BLOB),
+				      sha1);
+	else
+		ret = hash_sha1_file(sbuf.buf, sbuf.len, typename(OBJ_BLOB),
+				     sha1);
+	strbuf_release(&sbuf);
+	return ret;
+}
+
 static int index_pipe(unsigned char *sha1, int fd, enum object_type type,
 		      const char *path, unsigned flags)
 {
@@ -3141,15 +3180,22 @@ int index_fd(unsigned char *sha1, int fd, struct stat *st,
 	     enum object_type type, const char *path, unsigned flags)
 {
 	int ret;
-	size_t size = xsize_t(st->st_size);
 
-	if (!S_ISREG(st->st_mode))
+	/*
+	 * Call xsize_t() only when needed to avoid potentially unnecessary
+	 * die() for large files.
+	 */
+	if (type == OBJ_BLOB && path && would_convert_to_git_filter_fd(path))
+		ret = index_stream_convert_blob(sha1, fd, path, flags);
+	else if (!S_ISREG(st->st_mode))
 		ret = index_pipe(sha1, fd, type, path, flags);
-	else if (size <= big_file_threshold || type != OBJ_BLOB ||
-		 (path && would_convert_to_git(path, NULL, 0, 0)))
-		ret = index_core(sha1, fd, size, type, path, flags);
+	else if (st->st_size <= big_file_threshold || type != OBJ_BLOB ||
+		 (path && would_convert_to_git(path)))
+		ret = index_core(sha1, fd, xsize_t(st->st_size), type, path,
+				 flags);
 	else
-		ret = index_stream(sha1, fd, size, type, path, flags);
+		ret = index_stream(sha1, fd, xsize_t(st->st_size), type, path,
+				   flags);
 	close(fd);
 	return ret;
 }