Hello!
On Wed, Sep 04, 2002 at 10:36:51PM -0700, David S. Miller wrote:
> > Our disk format has link counts > 32k
> Does the internal reiserfs nlink value translate directly
> to what stat() puts in st_nlink?
> It really doesn't matter. Even if you have some huge value that can't
> be represented in st_nlink, you can report to the user that st_nlink
> is NLINK_MAX.
Ok, since I really like this approach, below is the patch (for 2.4) that
demonstrates my solution.
Also it correctly calculates maximal number given type may hold ( does not work
with unsigned long long, though) with my own way ;)
FS compatibility is still intact and older kernel will work.
If nobody will object against this code, then I'll implement something
similar for 2.5 too and we will fix reiserfsck to understand this correct
nlink accounting.
The only downside of this patch is that v3.5 filesystems won't allow to
create more than 64k-2 subdirs in a dir, like old code did, but this is
not an issue I think. (already existent dirs should still work)
Bye,
Oleg
===== fs/reiserfs/inode.c 1.35 vs edited =====
--- 1.35/fs/reiserfs/inode.c Fri Aug 9 19:22:33 2002
+++ edited/fs/reiserfs/inode.c Thu Sep 5 13:43:26 2002
@@ -891,7 +891,8 @@
set_inode_item_key_version (inode, KEY_FORMAT_3_5);
set_inode_sd_version (inode, STAT_DATA_V1);
inode->i_mode = sd_v1_mode(sd);
- inode->i_nlink = sd_v1_nlink(sd);
+ inode->i_nlink = ( sd_v1_nlink(sd) > REISERFS_LINK_MAX ) ? REISERFS_LINK_MAX:sd_v1_nlink(sd);
+ inode->u.reiserfs_i.i_nlink_real = sd_v1_nlink(sd);
inode->i_uid = sd_v1_uid(sd);
inode->i_gid = sd_v1_gid(sd);
inode->i_size = sd_v1_size(sd);
@@ -923,7 +924,8 @@
struct stat_data * sd = (struct stat_data *)B_I_PITEM (bh, ih);
inode->i_mode = sd_v2_mode(sd);
- inode->i_nlink = sd_v2_nlink(sd);
+ inode->i_nlink = (sd_v2_nlink(sd)>REISERFS_LINK_MAX)?REISERFS_LINK_MAX:sd_v2_nlink(sd);
+ inode->u.reiserfs_i.i_nlink_real = sd_v2_nlink(sd);
inode->i_uid = sd_v2_uid(sd);
inode->i_size = sd_v2_size(sd);
inode->i_gid = sd_v2_gid(sd);
@@ -975,7 +977,7 @@
__u16 flags;
set_sd_v2_mode(sd_v2, inode->i_mode );
- set_sd_v2_nlink(sd_v2, inode->i_nlink );
+ set_sd_v2_nlink(sd_v2, inode->u.reiserfs_i.i_nlink_real );
set_sd_v2_uid(sd_v2, inode->i_uid );
set_sd_v2_size(sd_v2, inode->i_size );
set_sd_v2_gid(sd_v2, inode->i_gid );
@@ -1001,7 +1003,7 @@
set_sd_v1_mode(sd_v1, inode->i_mode );
set_sd_v1_uid(sd_v1, inode->i_uid );
set_sd_v1_gid(sd_v1, inode->i_gid );
- set_sd_v1_nlink(sd_v1, inode->i_nlink );
+ set_sd_v1_nlink(sd_v1, inode->u.reiserfs_i.i_nlink_real );
set_sd_v1_size(sd_v1, inode->i_size );
set_sd_v1_atime(sd_v1, inode->i_atime );
set_sd_v1_ctime(sd_v1, inode->i_ctime );
@@ -1537,7 +1539,7 @@
/* fill stat data */
inode->i_mode = mode;
- inode->i_nlink = (S_ISDIR (mode) ? 2 : 1);
+ inode->u.reiserfs_i.i_nlink_real = inode->i_nlink = (S_ISDIR (mode) ? 2 : 1);
inode->i_uid = current->fsuid;
if (dir->i_mode & S_ISGID) {
inode->i_gid = dir->i_gid;
===== fs/reiserfs/namei.c 1.24 vs edited =====
--- 1.24/fs/reiserfs/namei.c Fri Aug 9 19:22:33 2002
+++ edited/fs/reiserfs/namei.c Thu Sep 5 13:34:43 2002
@@ -8,8 +8,16 @@
#include <linux/reiserfs_fs.h>
#include <linux/smp_lock.h>
-#define INC_DIR_INODE_NLINK(i) if (i->i_nlink != 1) { i->i_nlink++; if (i->i_nlink >= REISERFS_LINK_MAX) i->i_nlink=1; }
-#define DEC_DIR_INODE_NLINK(i) if (i->i_nlink != 1) i->i_nlink--;
+#define INC_INODE_NLINK(i) { if (i->i_nlink < REISERFS_LINK_MAX) i->i_nlink++; i->u.reiserfs_i.i_nlink_real++; }
+#define DEC_INODE_NLINK(i) {if ( --i->u.reiserfs_i.i_nlink_real < REISERFS_LINK_MAX) i->i_nlink--;}
+
+// v3.5 files have 16bit nlink_t, v3.6 files have 32bit nlink_t.
+#define CAN_INCREASE_NLINK(i) ( i->u.reiserfs_i.i_nlink_real < ((get_inode_item_key_version (inode) != KEY_FORMAT_3_5)?MAX_UL_INT:MAX_US_INT))
+
+// Compatibility stuff with old trick that allowed to have lots of subdirs in
+// one dir. Such dirs had 1 as their nlink count.
+#define INC_DIR_INODE_NLINK(i) { if (i->i_nlink != 1) INC_INODE_NLINK(i);}
+#define DEC_DIR_INODE_NLINK(i) { if (i->i_nlink != 1) DEC_INODE_NLINK(i);}
// directory item contains array of entry headers. This performs
// binary search through that array
@@ -518,7 +526,7 @@
retval = reiserfs_add_entry (&th, dir, dentry->d_name.name, dentry->d_name.len,
inode, 1/*visible*/);
if (retval) {
- inode->i_nlink--;
+ DEC_INODE_NLINK(inode);
reiserfs_update_sd (&th, inode);
pop_journal_writer(windex) ;
// FIXME: should we put iput here and have stat data deleted
@@ -569,7 +577,7 @@
retval = reiserfs_add_entry (&th, dir, dentry->d_name.name, dentry->d_name.len,
inode, 1/*visible*/);
if (retval) {
- inode->i_nlink--;
+ DEC_INODE_NLINK(inode);
reiserfs_update_sd (&th, inode);
pop_journal_writer(windex) ;
journal_end(&th, dir->i_sb, jbegin_count) ;
@@ -613,7 +621,7 @@
dentry, inode, &retval);
if (!inode) {
pop_journal_writer(windex) ;
- dir->i_nlink-- ;
+ DEC_DIR_INODE_NLINK(dir);
journal_end(&th, dir->i_sb, jbegin_count) ;
return retval;
}
@@ -627,7 +635,7 @@
retval = reiserfs_add_entry (&th, dir, dentry->d_name.name, dentry->d_name.len,
inode, 1/*visible*/);
if (retval) {
- inode->i_nlink = 0;
+ inode->u.reiserfs_i.i_nlink_real = inode->i_nlink = 0;
DEC_DIR_INODE_NLINK(dir);
reiserfs_update_sd (&th, inode);
pop_journal_writer(windex) ;
@@ -711,7 +719,7 @@
if ( inode->i_nlink != 2 && inode->i_nlink != 1 )
printk ("reiserfs_rmdir: empty directory has nlink != 2 (%d)\n", inode->i_nlink);
- inode->i_nlink = 0;
+ inode->u.reiserfs_i.i_nlink_real = inode->i_nlink = 0;
inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
reiserfs_update_sd (&th, inode);
@@ -780,14 +788,14 @@
if (!inode->i_nlink) {
printk("reiserfs_unlink: deleting nonexistent file (%s:%lu), %d\n",
kdevname(inode->i_dev), inode->i_ino, inode->i_nlink);
- inode->i_nlink = 1;
+ inode->u.reiserfs_i.i_nlink_real = inode->i_nlink = 1;
}
retval = reiserfs_cut_from_item (&th, &path, &(de.de_entry_key), dir, NULL, 0);
if (retval < 0)
goto end_unlink;
- inode->i_nlink--;
+ DEC_INODE_NLINK(inode);
inode->i_ctime = CURRENT_TIME;
reiserfs_update_sd (&th, inode);
@@ -868,7 +876,7 @@
retval = reiserfs_add_entry (&th, parent_dir, dentry->d_name.name, dentry->d_name.len,
inode, 1/*visible*/);
if (retval) {
- inode->i_nlink--;
+ DEC_INODE_NLINK(inode);
reiserfs_update_sd (&th, inode);
pop_journal_writer(windex) ;
journal_end(&th, parent_dir->i_sb, jbegin_count) ;
@@ -896,7 +904,7 @@
if (S_ISDIR(inode->i_mode))
return -EPERM;
- if (inode->i_nlink >= REISERFS_LINK_MAX) {
+ if (CAN_INCREASE_NLINK(inode)) {
//FIXME: sd_nlink is 32 bit for new files
return -EMLINK;
}
@@ -917,7 +925,7 @@
return retval;
}
- inode->i_nlink++;
+ INC_INODE_NLINK(inode);
ctime = CURRENT_TIME;
inode->i_ctime = ctime;
reiserfs_update_sd (&th, inode);
@@ -1157,9 +1165,9 @@
if (new_dentry_inode) {
// adjust link number of the victim
if (S_ISDIR(new_dentry_inode->i_mode)) {
- new_dentry_inode->i_nlink = 0;
+ new_dentry_inode->u.reiserfs_i.i_nlink_real = new_dentry_inode->i_nlink = 0;
} else {
- new_dentry_inode->i_nlink--;
+ DEC_INODE_NLINK(new_dentry_inode);
}
ctime = CURRENT_TIME;
new_dentry_inode->i_ctime = ctime;
===== include/linux/reiserfs_fs.h 1.22 vs edited =====
--- 1.22/include/linux/reiserfs_fs.h Tue Aug 20 13:40:53 2002
+++ edited/include/linux/reiserfs_fs.h Thu Sep 5 13:42:08 2002
@@ -1163,7 +1163,6 @@
#define INODE_PKEY(inode) ((struct key *)((inode)->u.reiserfs_i.i_key))
#define MAX_UL_INT 0xffffffff
-#define MAX_INT 0x7ffffff
#define MAX_US_INT 0xffff
// reiserfs version 2 has max offset 60 bits. Version 1 - 32 bit offset
@@ -1186,8 +1185,9 @@
#define MAX_FC_NUM MAX_US_INT
-/* the purpose is to detect overflow of an unsigned short */
-#define REISERFS_LINK_MAX (MAX_US_INT - 1000)
+/* Find maximal number, that nlink_t can hold. GCC is able to calculate this
+ value at compile time, so do not worry about extra CPU overhead. */
+#define REISERFS_LINK_MAX ((((nlink_t) -1) > 0)?~0:((1u<<(sizeof(nlink_t)*8-1))-1))
/* The following defines are used in reiserfs_insert_item and reiserfs_append_item */
===== include/linux/reiserfs_fs_i.h 1.8 vs edited =====
--- 1.8/include/linux/reiserfs_fs_i.h Fri Aug 9 19:22:34 2002
+++ edited/include/linux/reiserfs_fs_i.h Thu Sep 5 13:41:01 2002
@@ -53,6 +53,8 @@
** flushed */
unsigned long i_trans_id ;
unsigned long i_trans_index ;
+ unsigned int i_nlink_real; /* We store real nlink number since field in
+ struct inode is too short for us */
};
#endif
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Sat Sep 07 2002 - 22:00:24 EST