From: "Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>
To: git@vger.kernel.org
Cc: "Junio C Hamano" <gitster@pobox.com>,
"Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>
Subject: [PATCH v2 05/11] copy.c: convert copy_file() to copy_dir_recursively()
Date: Mon, 28 Nov 2016 16:43:13 +0700 [thread overview]
Message-ID: <20161128094319.16176-6-pclouds@gmail.com> (raw)
In-Reply-To: <20161128094319.16176-1-pclouds@gmail.com>
This finally enables busybox's copy_file() code under a new name
(because "copy_file" is already taken in Git code base). Because this
comes from busybox, POSIXy (or even Linuxy) behavior is expected. More
changes may be needed for Windows support.
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
cache.h | 1 +
copy.c | 216 ++++++++++++++++++++++++++++++++++++++++++++++++++++------------
2 files changed, 179 insertions(+), 38 deletions(-)
diff --git a/cache.h b/cache.h
index a50a61a..a9a72f8 100644
--- a/cache.h
+++ b/cache.h
@@ -1857,6 +1857,7 @@ extern void fprintf_or_die(FILE *, const char *fmt, ...);
extern int copy_fd(int ifd, int ofd);
extern int copy_file(const char *dst, const char *src, int mode);
extern int copy_file_with_time(const char *dst, const char *src, int mode);
+extern int copy_dir_recursively(const char *source, const char *dest);
extern void write_or_die(int fd, const void *buf, size_t count);
extern void fsync_or_die(int fd, const char *);
diff --git a/copy.c b/copy.c
index 60c7d8a..8ef4b23 100644
--- a/copy.c
+++ b/copy.c
@@ -1,4 +1,6 @@
#include "cache.h"
+#include "dir.h"
+#include "hashmap.h"
int copy_fd(int ifd, int ofd)
{
@@ -66,21 +68,126 @@ int copy_file_with_time(const char *dst, const char *src, int mode)
return status;
}
-#if 0
-/* Return:
- * -1 error, copy not made
- * 0 copy is made or user answered "no" in interactive mode
- * (failures to preserve mode/owner/times are not reported in exit code)
+struct inode_key {
+ struct hashmap_entry entry;
+ ino_t ino;
+ dev_t dev;
+ /*
+ * Reportedly, on cramfs a file and a dir can have same ino.
+ * Need to also remember "file/dir" bit:
+ */
+ char isdir; /* bool */
+};
+
+struct inode_value {
+ struct inode_key key;
+ char name[FLEX_ARRAY];
+};
+
+#define HASH_SIZE 311u /* Should be prime */
+static inline unsigned hash_inode(ino_t i)
+{
+ return i % HASH_SIZE;
+}
+
+static int inode_cmp(const void *entry, const void *entry_or_key,
+ const void *keydata)
+{
+ const struct inode_value *inode = entry;
+ const struct inode_key *key = entry_or_key;
+
+ return !(inode->key.ino == key->ino &&
+ inode->key.dev == key->dev &&
+ inode->key.isdir == key->isdir);
+}
+
+static const char *is_in_ino_dev_hashtable(const struct hashmap *map,
+ const struct stat *st)
+{
+ struct inode_key key;
+ struct inode_value *value;
+
+ key.entry.hash = hash_inode(st->st_ino);
+ key.ino = st->st_ino;
+ key.dev = st->st_dev;
+ key.isdir = !!S_ISDIR(st->st_mode);
+ value = hashmap_get(map, &key, NULL);
+ return value ? value->name : NULL;
+}
+
+static void add_to_ino_dev_hashtable(struct hashmap *map,
+ const struct stat *st,
+ const char *path)
+{
+ struct inode_value *v;
+ int len = strlen(path);
+
+ v = xmalloc(offsetof(struct inode_value, name) + len + 1);
+ v->key.entry.hash = hash_inode(st->st_ino);
+ v->key.ino = st->st_ino;
+ v->key.dev = st->st_dev;
+ v->key.isdir = !!S_ISDIR(st->st_mode);
+ memcpy(v->name, path, len + 1);
+ hashmap_add(map, v);
+}
+
+/*
+ * Find out if the last character of a string matches the one given.
+ * Don't underrun the buffer if the string length is 0.
*/
-int FAST_FUNC copy_file(const char *source, const char *dest, int flags)
+static inline char *last_char_is(const char *s, int c)
+{
+ if (s && *s) {
+ size_t sz = strlen(s) - 1;
+ s += sz;
+ if ((unsigned char)*s == c)
+ return (char *)s;
+ }
+ return NULL;
+}
+
+static inline char *concat_path_file(const char *path, const char *filename)
+{
+ struct strbuf sb = STRBUF_INIT;
+ char *lc;
+
+ if (!path)
+ path = "";
+ lc = last_char_is(path, '/');
+ while (*filename == '/')
+ filename++;
+ strbuf_addf(&sb, "%s%s%s", path, !lc ? "/" : "", filename);
+ return strbuf_detach(&sb, NULL);
+}
+
+static char *concat_subpath_file(const char *path, const char *f)
+{
+ if (f && is_dot_or_dotdot(f))
+ return NULL;
+ return concat_path_file(path, f);
+}
+
+static int do_unlink(const char *dest)
+{
+ int e = errno;
+
+ if (unlink(dest) < 0) {
+ errno = e; /* do not use errno from unlink */
+ return error_errno(_("can't create '%s'"), dest);
+ }
+ return 0;
+}
+
+static int copy_dir_1(struct hashmap *inode_map,
+ const char *source,
+ const char *dest)
{
/* This is a recursive function, try to minimize stack usage */
- /* NB: each struct stat is ~100 bytes */
struct stat source_stat;
struct stat dest_stat;
- smallint retval = 0;
- smallint dest_exists = 0;
- smallint ovr;
+ int retval = 0;
+ int dest_exists = 0;
+ int ovr;
if (lstat(source, &source_stat) < 0)
return error_errno(_("can't stat '%s'"), source);
@@ -102,7 +209,7 @@ int FAST_FUNC copy_file(const char *source, const char *dest, int flags)
mode_t saved_umask = 0;
/* Did we ever create source ourself before? */
- tp = is_in_ino_dev_hashtable(&source_stat);
+ tp = is_in_ino_dev_hashtable(inode_map, &source_stat);
if (tp)
/* We did! it's a recursion! man the lifeboats... */
return error(_("recursion detected, omitting directory '%s'"),
@@ -132,11 +239,12 @@ int FAST_FUNC copy_file(const char *source, const char *dest, int flags)
if (lstat(dest, &dest_stat) < 0)
return error_errno(_("can't stat '%s'"), dest);
}
+
/*
* remember (dev,inode) of each created dir. name is
* not remembered
*/
- add_to_ino_dev_hashtable(&dest_stat, NULL);
+ add_to_ino_dev_hashtable(inode_map, &dest_stat, "");
/* Recursively copy files in SOURCE */
dp = opendir(source);
@@ -152,7 +260,7 @@ int FAST_FUNC copy_file(const char *source, const char *dest, int flags)
if (!new_source)
continue;
new_dest = concat_path_file(dest, d->d_name);
- if (copy_file(new_source, new_dest, flags & ~FILEUTILS_DEREFERENCE_L0) < 0)
+ if (copy_dir_1(inode_map, new_source, new_dest) < 0)
retval = -1;
free(new_source);
free(new_dest);
@@ -177,53 +285,57 @@ int FAST_FUNC copy_file(const char *source, const char *dest, int flags)
goto dont_cat;
}
- if (ENABLE_FEATURE_PRESERVE_HARDLINKS) {
+ if (1 /*ENABLE_FEATURE_PRESERVE_HARDLINKS*/) {
const char *link_target;
- link_target = is_in_ino_dev_hashtable(&source_stat);
+ link_target = is_in_ino_dev_hashtable(inode_map, &source_stat);
if (link_target) {
if (link(link_target, dest) < 0) {
- ovr = ask_and_unlink(dest, flags);
- if (ovr <= 0)
+ ovr = do_unlink(dest);
+ if (ovr < 0)
return ovr;
if (link(link_target, dest) < 0)
return error_errno(_("can't create link '%s'"), dest);
}
return 0;
}
- add_to_ino_dev_hashtable(&source_stat, dest);
+ add_to_ino_dev_hashtable(inode_map, &source_stat, dest);
}
- src_fd = open_or_warn(source, O_RDONLY);
+ src_fd = open(source, O_RDONLY);
if (src_fd < 0)
- return -1;
+ return error_errno(_("can't open '%s'"), source);
/* Do not try to open with weird mode fields */
new_mode = source_stat.st_mode;
if (!S_ISREG(source_stat.st_mode))
new_mode = 0666;
- /* POSIX way is a security problem versus (sym)link attacks */
- if (!ENABLE_FEATURE_NON_POSIX_CP) {
- dst_fd = open(dest, O_WRONLY|O_CREAT|O_TRUNC, new_mode);
- } else { /* safe way: */
- dst_fd = open(dest, O_WRONLY|O_CREAT|O_EXCL, new_mode);
- }
+ dst_fd = open(dest, O_WRONLY|O_CREAT|O_EXCL, new_mode);
if (dst_fd == -1) {
- ovr = ask_and_unlink(dest, flags);
- if (ovr <= 0) {
+ ovr = do_unlink(dest);
+ if (ovr < 0) {
close(src_fd);
return ovr;
}
/* It shouldn't exist. If it exists, do not open (symlink attack?) */
- dst_fd = open3_or_warn(dest, O_WRONLY|O_CREAT|O_EXCL, new_mode);
+ dst_fd = open(dest, O_WRONLY|O_CREAT|O_EXCL, new_mode);
if (dst_fd < 0) {
close(src_fd);
- return -1;
+ return error_errno(_("can't open '%s'"), dest);
}
}
- if (bb_copyfd_eof(src_fd, dst_fd) == -1)
+ switch (copy_fd(src_fd, dst_fd)) {
+ case COPY_READ_ERROR:
+ error(_("copy-fd: read returned %s"), strerror(errno));
retval = -1;
+ break;
+ case COPY_WRITE_ERROR:
+ error(_("copy-fd: write returned %s"), strerror(errno));
+ retval = -1;
+ break;
+ }
+
/* Careful with writing... */
if (close(dst_fd) < 0)
retval = error_errno(_("error writing to '%s'"), dest);
@@ -243,19 +355,28 @@ int FAST_FUNC copy_file(const char *source, const char *dest, int flags)
/* We are lazy here, a bit lax with races... */
if (dest_exists) {
errno = EEXIST;
- ovr = ask_and_unlink(dest, flags);
- if (ovr <= 0)
+ ovr = do_unlink(dest);
+ if (ovr < 0)
return ovr;
}
if (S_ISLNK(source_stat.st_mode)) {
- char *lpath = xmalloc_readlink_or_warn(source);
- if (lpath) {
- int r = symlink(lpath, dest);
- free(lpath);
+ struct strbuf lpath = STRBUF_INIT;
+ if (!strbuf_readlink(&lpath, source, 0)) {
+ int r = symlink(lpath.buf, dest);
+ strbuf_release(&lpath);
if (r < 0)
return error_errno(_("can't create symlink '%s'"), dest);
if (lchown(dest, source_stat.st_uid, source_stat.st_gid) < 0)
error_errno(_("can't preserve %s of '%s'"), "ownership", dest);
+ } else {
+ /* EINVAL => "file: Invalid argument" => puzzled user */
+ const char *errmsg = _("not a symlink");
+ int err = errno;
+
+ if (err != EINVAL)
+ errmsg = strerror(err);
+ error(_("%s: cannot read link: %s"), source, errmsg);
+ strbuf_release(&lpath);
}
/*
* _Not_ jumping to preserve_mode_ugid_time: symlinks
@@ -293,4 +414,23 @@ int FAST_FUNC copy_file(const char *source, const char *dest, int flags)
return retval;
}
-#endif
+
+/*
+ * Return:
+ * -1 error, copy not made
+ * 0 copy is made
+ *
+ * Failures to preserve mode/owner/times are not reported in exit
+ * code. No support for preserving SELinux security context. Symlinks
+ * and hardlinks are preserved.
+ */
+int copy_dir_recursively(const char *source, const char *dest)
+{
+ int ret;
+ struct hashmap inode_map;
+
+ hashmap_init(&inode_map, inode_cmp, 1024);
+ ret = copy_dir_1(&inode_map, source, dest);
+ hashmap_free(&inode_map, 1);
+ return ret;
+}
--
2.8.2.524.g6ff3d78
next prev parent reply other threads:[~2016-11-28 9:44 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-11-12 2:23 [PATCH 00/11] git worktree (re)move Nguyễn Thái Ngọc Duy
2016-11-12 2:23 ` [PATCH 01/11] copy.c: import copy_file() from busybox Nguyễn Thái Ngọc Duy
2016-11-12 2:23 ` [PATCH 02/11] copy.c: delete unused code in copy_file() Nguyễn Thái Ngọc Duy
2016-11-12 2:23 ` [PATCH 03/11] copy.c: convert bb_(p)error_msg to error(_errno) Nguyễn Thái Ngọc Duy
2016-11-12 2:23 ` [PATCH 04/11] copy.c: style fix Nguyễn Thái Ngọc Duy
2016-11-12 2:23 ` [PATCH 05/11] copy.c: convert copy_file() to copy_dir_recursively() Nguyễn Thái Ngọc Duy
2016-11-12 2:23 ` [PATCH 06/11] worktree.c: add validate_worktree() Nguyễn Thái Ngọc Duy
2016-11-12 2:23 ` [PATCH 07/11] worktree.c: add update_worktree_location() Nguyễn Thái Ngọc Duy
2016-11-12 2:23 ` [PATCH 08/11] worktree move: new command Nguyễn Thái Ngọc Duy
2016-11-12 2:23 ` [PATCH 09/11] worktree move: accept destination as directory Nguyễn Thái Ngọc Duy
2016-11-12 2:23 ` [PATCH 10/11] worktree move: refuse to move worktrees with submodules Nguyễn Thái Ngọc Duy
2016-11-12 2:23 ` [PATCH 11/11] worktree remove: new command Nguyễn Thái Ngọc Duy
[not found] ` <xmqqeg2gyv1v.fsf@gitster.mtv.corp.google.com>
[not found] ` <xmqqa8d4yts7.fsf@gitster.mtv.corp.google.com>
2016-11-16 13:05 ` [PATCH 00/11] git worktree (re)move Duy Nguyen
2016-11-16 13:11 ` Duy Nguyen
2016-11-16 18:11 ` Junio C Hamano
2016-11-16 18:39 ` Junio C Hamano
2016-11-28 9:43 ` [PATCH v2 " Nguyễn Thái Ngọc Duy
2016-11-28 9:43 ` [PATCH v2 01/11] copy.c: import copy_file() from busybox Nguyễn Thái Ngọc Duy
2016-11-28 9:43 ` [PATCH v2 02/11] copy.c: delete unused code in copy_file() Nguyễn Thái Ngọc Duy
2016-11-28 9:43 ` [PATCH v2 03/11] copy.c: convert bb_(p)error_msg to error(_errno) Nguyễn Thái Ngọc Duy
2016-11-28 9:43 ` [PATCH v2 04/11] copy.c: style fix Nguyễn Thái Ngọc Duy
2016-11-28 9:43 ` Nguyễn Thái Ngọc Duy [this message]
2016-11-28 9:43 ` [PATCH v2 06/11] worktree.c: add validate_worktree() Nguyễn Thái Ngọc Duy
2016-11-28 9:43 ` [PATCH v2 07/11] worktree.c: add update_worktree_location() Nguyễn Thái Ngọc Duy
2016-11-28 9:43 ` [PATCH v2 08/11] worktree move: new command Nguyễn Thái Ngọc Duy
2016-11-28 9:43 ` [PATCH v2 09/11] worktree move: accept destination as directory Nguyễn Thái Ngọc Duy
2016-11-28 9:43 ` [PATCH v2 10/11] worktree move: refuse to move worktrees with submodules Nguyễn Thái Ngọc Duy
2016-12-19 20:57 ` Stefan Beller
2016-11-28 9:43 ` [PATCH v2 11/11] worktree remove: new command Nguyễn Thái Ngọc Duy
2016-11-28 19:48 ` [PATCH v2 00/11] git worktree (re)move Junio C Hamano
2016-11-28 20:20 ` Junio C Hamano
2016-11-28 21:25 ` Johannes Sixt
2016-11-29 12:17 ` Duy Nguyen
2016-11-29 12:08 ` Duy Nguyen
2016-11-29 13:56 ` Duy Nguyen
2016-11-29 19:28 ` Junio C Hamano
2016-11-30 0:18 ` Stefan Beller
2016-11-29 21:14 ` Johannes Sixt
2016-11-30 0:09 ` Duy Nguyen
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: http://vger.kernel.org/majordomo-info.html
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20161128094319.16176-6-pclouds@gmail.com \
--to=pclouds@gmail.com \
--cc=git@vger.kernel.org \
--cc=gitster@pobox.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
Code repositories for project(s) associated with this public inbox
https://80x24.org/mirrors/git.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).