vfs: names up to 255 bytes and paths up to 4096, like Linux
Every path component was copied into a DIRSIZ buffer and every path into a MAXPATH one, so names were cut at 29 bytes and paths at 127 without an error. Two names sharing their first 29 bytes opened the same file, on SchFS and FAT alike, though both hold 255. VFS_NAME_MAX (255) and VFS_PATH_MAX (4096) are the limits now, and anything longer is ENAMETOOLONG. namex_from() takes its path buffers from kalloc(), a page each, rather than putting two of them on an 8 KB kernel stack. The v1 format still stores DIRSIZ bytes, and refuses a longer name instead of matching on its first 30. Checked: 255-byte names on SchFS and FAT (fsck.fat clean, and the FAT name answers to its uppercase form), 256 refused, a 200-byte path and a link to it, and no pages lost over 700 lookups through links. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01S1giNvrHTrPMPw7V6x1kQ4
This commit is contained in:
Nexoniarz
parent
b213ab5778
commit
67db42b460
7 changed files with 121 additions and 38 deletions
|
|
@ -92,9 +92,6 @@ directory ends at the first entry whose first byte is zero.
|
|||
|
||||
## What it does not do
|
||||
|
||||
- **Names longer than 29 bytes.** FAT allows 255 UTF-16 units, but the VFS's
|
||||
`DIRSIZ` caps a path component, so a longer name is cut short on the way in.
|
||||
Lifting that is a VFS change.
|
||||
- **Permissions and owners.** Every file shows as `0755 root:root`, like Linux
|
||||
vfat with its defaults. The read-only attribute is kept but not enforced.
|
||||
- **exFAT.** Large SD cards (SDXC, over 32 GB) ship with it. It is a different
|
||||
|
|
|
|||
|
|
@ -288,6 +288,20 @@ held alive by an `nlink` bump.
|
|||
Renaming a *directory* is still refused with `EISDIR`, and so is replacing one:
|
||||
both need the `..` fixup and the ancestor-loop check that are not written.
|
||||
|
||||
## Names and paths
|
||||
|
||||
A name is at most 255 bytes and a path 4096 including its NUL, Linux's
|
||||
`NAME_MAX` and `PATH_MAX` (`VFS_NAME_MAX` and `VFS_PATH_MAX` in
|
||||
`include/file.h`). Longer is `ENAMETOOLONG`. A filesystem may hold less: the v1
|
||||
format stores `DIRSIZ` bytes and refuses longer names rather than matching on
|
||||
their first 30.
|
||||
|
||||
Both limits used to be the copy buffers: every component went through a
|
||||
`DIRSIZ` array and every path through a `MAXPATH` one, so a name was cut at 29
|
||||
bytes and a path at 127, silently. Two files sharing their first 29 bytes were
|
||||
one file. The path buffers are a page each now, from `kalloc()`, since two of
|
||||
them would be most of a kernel stack.
|
||||
|
||||
## Symlinks
|
||||
|
||||
Followed the way Linux follows them, in `namex_from()`. A link in the middle of
|
||||
|
|
|
|||
|
|
@ -176,7 +176,9 @@ mount. It is set where it is because the page-pointer vector lives inside
|
|||
|
||||
These are VFS and driver limits rather than SchFS ones:
|
||||
|
||||
- `MAXPATH` caps a path at **128 bytes**.
|
||||
- A path is at most **4096 bytes** and a name **255**, Linux's `PATH_MAX` and
|
||||
`NAME_MAX` (`VFS_PATH_MAX`, `VFS_NAME_MAX`). Longer is `ENAMETOOLONG`. Both
|
||||
used to be cut short without a word, at 128 and 29.
|
||||
- `NMOUNT` allows **8** mounts.
|
||||
- The IDE driver handles the primary channel only: **2** ATA devices.
|
||||
- The IDE driver uses LBA48 past 128 GiB, so the disk is not the limit there.
|
||||
|
|
|
|||
|
|
@ -171,6 +171,16 @@ struct inode {
|
|||
|
||||
// Mounted FAT volumes, FAT_DEV onward. See include/fat.h.
|
||||
|
||||
// Linux's limits, for every filesystem behind the VFS. A path component can be
|
||||
// NAME_MAX bytes and a whole path PATH_MAX including its NUL. Each filesystem
|
||||
// may refuse less: SchFS and FAT take 255, the v1 format DIRSIZ.
|
||||
//
|
||||
// The VFS used to copy every component into a DIRSIZ buffer and every path
|
||||
// into a MAXPATH one, which cut names at 29 bytes and paths at 127 without a
|
||||
// word -- so a longer name opened whichever file shared its first 29 bytes.
|
||||
#define VFS_NAME_MAX 255
|
||||
#define VFS_PATH_MAX 4096 // one page: namex_from() kalloc()s it
|
||||
|
||||
// 1 if some inode on dev with this number is referenced. In fs.c.
|
||||
int iheld(uint dev, uint64 inum);
|
||||
// 1 if any inode on dev but `except` is referenced (0: no exception). In fs.c.
|
||||
|
|
|
|||
|
|
@ -667,7 +667,7 @@ static int
|
|||
vfs_name(const char *name, uint16 *out)
|
||||
{
|
||||
int n = 0;
|
||||
while (n < DIRSIZ && name[n])
|
||||
while (n < VFS_NAME_MAX && name[n])
|
||||
n++;
|
||||
int len = utf8_to_16(name, n, out);
|
||||
if (len < 0)
|
||||
|
|
|
|||
|
|
@ -1345,6 +1345,10 @@ v1_dirlookup(struct inode *dp, char *name, uint *poff)
|
|||
return 0;
|
||||
}
|
||||
|
||||
// The format stores DIRSIZ bytes of a name. A longer one cannot be here,
|
||||
// and comparing only its first DIRSIZ would find a different file.
|
||||
if (strlen(name) > DIRSIZ)
|
||||
return 0;
|
||||
tree_search(dp, name, poff, &de, 0);
|
||||
if (de.inum)
|
||||
return iget(dp->dev, de.inum);
|
||||
|
|
@ -1358,6 +1362,8 @@ v1_dirlink(struct inode *dp, char *name, uint64 inum)
|
|||
struct dirent de;
|
||||
struct inode *ip;
|
||||
|
||||
if (strlen(name) > DIRSIZ)
|
||||
return -1; // see v1_dirlookup
|
||||
if ((ip = dirlookup(dp, name, 0)) != 0) {
|
||||
iput(ip);
|
||||
return -1; // already exists
|
||||
|
|
@ -1537,8 +1543,11 @@ build_dir_tree(struct inode *dp, uint64 pinum)
|
|||
// Path lookup
|
||||
// ===========================================================================
|
||||
|
||||
// Copy the next component of `path` into `name` (VFS_NAME_MAX + 1 bytes) and
|
||||
// return what follows it, or 0 at the end. A component longer than
|
||||
// VFS_NAME_MAX sets *toolong and ends the walk.
|
||||
static char *
|
||||
skipelem(char *path, char *name)
|
||||
skipelem(char *path, char *name, int *toolong)
|
||||
{
|
||||
char *s;
|
||||
int len;
|
||||
|
|
@ -1551,12 +1560,12 @@ skipelem(char *path, char *name)
|
|||
while (*path != '/' && *path != 0)
|
||||
path++;
|
||||
len = path - s;
|
||||
if (len >= DIRSIZ)
|
||||
memmove(name, s, DIRSIZ);
|
||||
else {
|
||||
memmove(name, s, len);
|
||||
name[len] = 0;
|
||||
if (len > VFS_NAME_MAX) {
|
||||
*toolong = 1;
|
||||
return 0;
|
||||
}
|
||||
memmove(name, s, len);
|
||||
name[len] = 0;
|
||||
while (*path == '/')
|
||||
path++;
|
||||
return path;
|
||||
|
|
@ -1764,14 +1773,27 @@ namex_from(struct inode *start, char *path, int nameiparent, char *name,
|
|||
int follow, int *err)
|
||||
{
|
||||
struct inode *ip, *next;
|
||||
int links = 0;
|
||||
int links = 0, toolong = 0;
|
||||
|
||||
// A private copy, because following a link rewrites what is left of it.
|
||||
char safe[MAXPATH];
|
||||
safestrcpy(safe, path, MAXPATH);
|
||||
char *spath = safe;
|
||||
if (err)
|
||||
*err = ENOENT;
|
||||
if (strnlen(path, VFS_PATH_MAX) >= VFS_PATH_MAX) {
|
||||
if (err)
|
||||
*err = ENAMETOOLONG;
|
||||
return 0;
|
||||
}
|
||||
|
||||
// A private copy, because following a link rewrites what is left of it.
|
||||
// A page each rather than on the stack: PATH_MAX twice over is the whole of
|
||||
// a kernel stack's slack, and a page is exactly PATH_MAX.
|
||||
char *safe = kalloc(), *tgt = 0;
|
||||
if (!safe) {
|
||||
if (err)
|
||||
*err = ENOMEM;
|
||||
return 0;
|
||||
}
|
||||
safestrcpy(safe, path, VFS_PATH_MAX);
|
||||
char *spath = safe;
|
||||
|
||||
// Root is a SchFS object, not a v1 inode. ops_for(SCHFS_DEV) then routes
|
||||
// every operation on it through schfs_ops, which is the whole point: the v1
|
||||
|
|
@ -1780,7 +1802,7 @@ namex_from(struct inode *start, char *path, int nameiparent, char *name,
|
|||
// The root itself can be a mount point, and a relative walk can start on one.
|
||||
ip = mount_cross(ip);
|
||||
|
||||
while ((spath = skipelem(spath, name)) != 0) {
|
||||
while ((spath = skipelem(spath, name, &toolong)) != 0) {
|
||||
// ".." out of a mounted filesystem's root leaves it. The filesystem down
|
||||
// there does not know it is mounted anywhere and would answer with its own
|
||||
// root, which turns the mount into a subtree you can enter and never
|
||||
|
|
@ -1800,15 +1822,15 @@ namex_from(struct inode *start, char *path, int nameiparent, char *name,
|
|||
iunlockput(ip);
|
||||
if (err)
|
||||
*err = ENOTDIR;
|
||||
return 0;
|
||||
goto fail;
|
||||
}
|
||||
if (nameiparent && *spath == '\0') {
|
||||
iunlock(ip);
|
||||
return ip;
|
||||
goto out;
|
||||
}
|
||||
if ((next = dirlookup(ip, name, 0)) == 0) {
|
||||
iunlockput(ip);
|
||||
return 0;
|
||||
goto fail;
|
||||
}
|
||||
iunlock(ip);
|
||||
next = mount_cross(next);
|
||||
|
|
@ -1823,16 +1845,22 @@ namex_from(struct inode *start, char *path, int nameiparent, char *name,
|
|||
|
||||
// A link: put its target in front of what is left of the path and carry
|
||||
// on from the directory it was found in, or from root.
|
||||
char tgt[MAXPATH];
|
||||
int len = (++links > MAXSYMLINKS) ? -1
|
||||
: readi(next, 0, (uint64)tgt, 0, MAXPATH - 1);
|
||||
if (!tgt && !(tgt = kalloc())) {
|
||||
iunlockput(next);
|
||||
iput(ip);
|
||||
if (err)
|
||||
*err = ENOMEM;
|
||||
goto fail;
|
||||
}
|
||||
int len = (++links > MAXSYMLINKS) ? -1
|
||||
: readi(next, 0, (uint64)tgt, 0, VFS_PATH_MAX - 1);
|
||||
iunlockput(next);
|
||||
int rest = strlen(spath);
|
||||
if (len <= 0 || len + 1 + rest >= MAXPATH) {
|
||||
if (len <= 0 || len + 1 + rest >= VFS_PATH_MAX) {
|
||||
iput(ip);
|
||||
if (err)
|
||||
*err = len < 0 ? ELOOP : len == 0 ? ENOENT : ENAMETOOLONG;
|
||||
return 0;
|
||||
goto fail;
|
||||
}
|
||||
tgt[len] = '\0';
|
||||
if (rest) {
|
||||
|
|
@ -1847,11 +1875,26 @@ namex_from(struct inode *start, char *path, int nameiparent, char *name,
|
|||
}
|
||||
}
|
||||
|
||||
if (toolong) {
|
||||
iput(ip);
|
||||
if (err)
|
||||
*err = ENAMETOOLONG;
|
||||
goto fail;
|
||||
}
|
||||
if (nameiparent) {
|
||||
iput(ip);
|
||||
return 0;
|
||||
goto fail;
|
||||
}
|
||||
out:
|
||||
kfree(safe);
|
||||
if (tgt)
|
||||
kfree(tgt);
|
||||
return ip;
|
||||
fail:
|
||||
kfree(safe);
|
||||
if (tgt)
|
||||
kfree(tgt);
|
||||
return 0;
|
||||
}
|
||||
|
||||
static struct inode *
|
||||
|
|
@ -1863,7 +1906,7 @@ namex(char *path, int nameiparent, char *name)
|
|||
struct inode *
|
||||
namei(char *path)
|
||||
{
|
||||
char name[DIRSIZ];
|
||||
char name[VFS_NAME_MAX + 1];
|
||||
return namex(path, 0, name);
|
||||
}
|
||||
|
||||
|
|
@ -1878,7 +1921,7 @@ nameiparent(char *path, char *name)
|
|||
struct inode *
|
||||
nameifrom(struct inode *start, char *path)
|
||||
{
|
||||
char name[DIRSIZ];
|
||||
char name[VFS_NAME_MAX + 1];
|
||||
return namex_from(start, path, 0, name, 0, 0);
|
||||
}
|
||||
|
||||
|
|
@ -1894,7 +1937,7 @@ nameiparentfrom(struct inode *start, char *path, char *name)
|
|||
struct inode *
|
||||
nameifollow(struct inode *start, char *path, int *err)
|
||||
{
|
||||
char name[DIRSIZ];
|
||||
char name[VFS_NAME_MAX + 1];
|
||||
return namex_from(start ? start : myproc()->cwd, path, 0, name, 1, err);
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -186,14 +186,31 @@ at_nameiparent(int dirfd, char *path, char *name)
|
|||
return nameiparentfrom(start, path, name);
|
||||
}
|
||||
|
||||
// 1 if some component of `path` is longer than NAME_MAX, which is why a
|
||||
// lookup through nameiparent() failed when it did. It reports no reason.
|
||||
static int
|
||||
path_toolong(const char *path)
|
||||
{
|
||||
int n = 0;
|
||||
if (strnlen(path, VFS_PATH_MAX) >= VFS_PATH_MAX) return 1;
|
||||
for (; *path; path++) {
|
||||
n = (*path == '/') ? 0 : n + 1;
|
||||
if (n > VFS_NAME_MAX) return 1;
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
static struct inode*
|
||||
createat_x(int dirfd, char *path, short type, short major, short minor,
|
||||
int *err)
|
||||
{
|
||||
struct inode *ip, *dp;
|
||||
char name[DIRSIZ];
|
||||
char name[VFS_NAME_MAX + 1];
|
||||
uint off;
|
||||
if (!(dp = at_nameiparent(dirfd, path, name))) return 0;
|
||||
if (!(dp = at_nameiparent(dirfd, path, name))) {
|
||||
if (err && path && path_toolong(path)) *err = ENAMETOOLONG;
|
||||
return 0;
|
||||
}
|
||||
ilock(dp);
|
||||
// `err` lets the caller report why. Returning 0 alone made a refused
|
||||
// write say "No such file or directory", which is what a shell prints for
|
||||
|
|
@ -884,7 +901,7 @@ addr_t sys_mknod(void)
|
|||
// renameat() is corrected alongside rename() because musl's rename() calls it.
|
||||
addr_t sys_link(void)
|
||||
{
|
||||
char name[DIRSIZ], *new, *old;
|
||||
char name[VFS_NAME_MAX + 1], *new, *old;
|
||||
struct inode *dp, *ip;
|
||||
int err = EPERM;
|
||||
if (argstr(0, &old) < 0 || argstr(1, &new) < 0) return -EFAULT;
|
||||
|
|
@ -936,7 +953,7 @@ int
|
|||
unlink_path(char *path)
|
||||
{
|
||||
struct inode *ip, *dp;
|
||||
char name[DIRSIZ];
|
||||
char name[VFS_NAME_MAX + 1];
|
||||
uint off;
|
||||
int err = EPERM;
|
||||
|
||||
|
|
@ -1067,7 +1084,7 @@ addr_t sys_rename(void)
|
|||
{
|
||||
char *oldpath, *newpath;
|
||||
struct inode *ip, *dp_old, *dp_new, *ip_src, *ip_dst;
|
||||
char oldname[DIRSIZ], newname[DIRSIZ];
|
||||
char oldname[VFS_NAME_MAX + 1], newname[VFS_NAME_MAX + 1];
|
||||
uint off, dstoff;
|
||||
int err = EPERM;
|
||||
if (argstr(0, &oldpath) < 0 || argstr(1, &newpath) < 0) return -EFAULT;
|
||||
|
|
@ -1244,7 +1261,7 @@ sys_getdents64(void)
|
|||
addr_t sys_delete(void)
|
||||
{
|
||||
struct inode *ip, *dp, *ip2;
|
||||
char name[DIRSIZ], *path;
|
||||
char name[VFS_NAME_MAX + 1], *path;
|
||||
uint off;
|
||||
if (argstr(0, &path) < 0) return -1;
|
||||
begin_op();
|
||||
|
|
@ -1897,7 +1914,7 @@ addr_t sys_unlinkat(void)
|
|||
int dirfd, flags;
|
||||
char *path;
|
||||
struct inode *ip, *dp;
|
||||
char name[DIRSIZ];
|
||||
char name[VFS_NAME_MAX + 1];
|
||||
uint off;
|
||||
argint(0, &dirfd);
|
||||
if (argstr(1, &path) < 0) return -1;
|
||||
|
|
@ -1937,7 +1954,7 @@ addr_t sys_renameat(void)
|
|||
// Delegate to sys_rename internals — fake the args for rename.
|
||||
// Easiest: place path pointers in registers and call rename logic directly.
|
||||
struct inode *ip, *dp_old, *dp_new, *ip_src;
|
||||
char oldname[DIRSIZ], newname[DIRSIZ];
|
||||
char oldname[VFS_NAME_MAX + 1], newname[VFS_NAME_MAX + 1];
|
||||
uint off;
|
||||
struct dirent de;
|
||||
begin_op();
|
||||
|
|
@ -1981,7 +1998,7 @@ addr_t sys_linkat(void)
|
|||
int olddirfd, newdirfd;
|
||||
char *old, *new;
|
||||
struct inode *dp, *ip;
|
||||
char name[DIRSIZ];
|
||||
char name[VFS_NAME_MAX + 1];
|
||||
argint(0, &olddirfd); argstr(1, &old);
|
||||
argint(2, &newdirfd); argstr(3, &new);
|
||||
argint(4, &(int){0}); // flags
|
||||
|
|
|
|||
Loading…
Reference in a new issue