v2.4.0.3 -> v2.4.0.4

  - ReiserFS merge
  - fix DRM R128/AGP dependency

Documentation/Configure.help

@@ -10745,6 +10745,46 @@ CONFIG_MINIX_FS
   called minix.o. Note that the file system of your root partition
   (the one containing the directory /) cannot be compiled as a module.
 
+Reiserfs support
+CONFIG_REISERFS_FS
+
+  Stores not just filenames but the files themselves in a balanced
+  tree.  Uses journaling.
+
+  Balanced trees are more efficient than traditional
+  filesystem architectural foundations.
+
+  You can use reiserfs in all cases where you use the ext2fs file
+  system, and you will gain in speed and disk space.  It has fewer
+  worst case performance situations than other file systems
+  because balanced trees are hardier creatures than other algorithms
+  are (if that is not technical enough, read www.namesys.com....:-) )
+
+  It is more easily extended to have features currently found in
+  database and keyword search systems than block allocation based
+  filesystems are.  The next version will be so extended, and will
+  support plugins consistent with our motto ``It takes more than a
+  license to make source code open.''
+
+  Read www.namesys.com to learn more about reiserfs.
+
+  Sponsored by Threshold Networks, Emusic.com, and Bigstorage.com.
+
+  If you like it, you can pay us to add new features to it that you
+  need, buy a support contract, or pay us to port it to another OS.
+
+Enable Reiserfs consistency checks
+CONFIG_REISERFS_CHECK
+  If you set this to yes, then ReiserFS will perform every check it
+  can possibly imagine of its internal consistency throughout its
+  operation.  It will also go substantially slower.  More than once we
+  have forgotten that this was on, and then gone despondent over the
+  latest benchmarks.:-) Use of this option allows our team to go all
+  out in checking for consistency when debugging without fear of its
+  effect on end users.  If you are on the verge of sending in a bug
+  report, say yes and you might get a useful error message.  Almost
+  everyone should say no.
+
 Second extended fs support
 CONFIG_EXT2_FS
   This is the de facto standard Linux file system (method to organize

Makefile

 VERSION = 2
 PATCHLEVEL = 4
 SUBLEVEL = 1
-EXTRAVERSION =-pre2
+EXTRAVERSION =-pre4
 
 KERNELRELEASE=$(VERSION).$(PATCHLEVEL).$(SUBLEVEL)$(EXTRAVERSION)
 

arch/i386/kernel/setup.c

@@ -2008,7 +2008,7 @@ void __init identify_cpu(struct cpuinfo_x86 *c)
 	 */
 
 	/* TSC disabled? */
-#ifdef CONFIG_TSC
+#ifndef CONFIG_X86_TSC
 	if ( tsc_disable )
 		clear_bit(X86_FEATURE_TSC, &c->x86_capability);
 #endif

arch/i386/mm/init.c

@@ -317,7 +317,7 @@ static void __init pagetable_init (void)
 	pgd_t *pgd, *pgd_base;
 	int i, j, k;
 	pmd_t *pmd;
-	pte_t *pte;
+	pte_t *pte, *pte_base;
 
 	/*
 	 * This can be zero as well - no problem, in that case we exit
@@ -366,11 +366,7 @@ static void __init pagetable_init (void)
 				continue;
 			}
 
-			pte = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE);
-			set_pmd(pmd, __pmd(_KERNPG_TABLE + __pa(pte)));
-
-			if (pte != pte_offset(pmd, 0))
-				BUG();
+			pte_base = pte = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE);
 
 			for (k = 0; k < PTRS_PER_PTE; pte++, k++) {
 				vaddr = i*PGDIR_SIZE + j*PMD_SIZE + k*PAGE_SIZE;
@@ -378,6 +374,10 @@ static void __init pagetable_init (void)
 					break;
 				*pte = mk_pte_phys(__pa(vaddr), PAGE_KERNEL);
 			}
+			set_pmd(pmd, __pmd(_KERNPG_TABLE + __pa(pte_base)));
+			if (pte_base != pte_offset(pmd, 0))
+				BUG();
+
 		}
 	}
 

drivers/char/drm/Config.in

@@ -9,7 +9,7 @@ bool 'Direct Rendering Manager (XFree86 DRI support)' CONFIG_DRM
 if [ "$CONFIG_DRM" != "n" ]; then
     tristate '  3dfx Banshee/Voodoo3+' CONFIG_DRM_TDFX
     tristate '  3dlabs GMX 2000' CONFIG_DRM_GAMMA
-    tristate '  ATI Rage 128' CONFIG_DRM_R128
+    dep_tristate '  ATI Rage 128' CONFIG_DRM_R128 $CONFIG_AGP
     dep_tristate '  Intel I810' CONFIG_DRM_I810 $CONFIG_AGP
     dep_tristate '  Matrox g200/g400' CONFIG_DRM_MGA $CONFIG_AGP
 fi

drivers/net/ppp_async.c

@@ -33,13 +33,6 @@
 #include <linux/init.h>
 #include <asm/uaccess.h>
 
-#ifndef spin_trylock_bh
-#define spin_trylock_bh(lock)	({ int __r; local_bh_disable();	\
-				   __r = spin_trylock(lock);	\
-				   if (!__r) local_bh_enable();	\
-				   __r; })
-#endif
-
 #define PPP_VERSION	"2.4.1"
 
 #define OBUFSIZE	256
@@ -76,6 +69,7 @@ struct asyncppp {
 /* Bit numbers in xmit_flags */
 #define XMIT_WAKEUP	0
 #define XMIT_FULL	1
+#define XMIT_BUSY	2
 
 /* State bits */
 #define SC_TOSS		0x20000000
@@ -181,18 +175,14 @@ ppp_asynctty_close(struct tty_struct *tty)
 }
 
 /*
- * Read does nothing.
+ * Read does nothing - no data is ever available this way.
+ * Pppd reads and writes packets via /dev/ppp instead.
  */
 static ssize_t
 ppp_asynctty_read(struct tty_struct *tty, struct file *file,
 		  unsigned char *buf, size_t count)
 {
-	/* For now, do the same as the old 2.3.x code useta */
-	struct asyncppp *ap = tty->disc_data;
-
-	if (ap == 0)
-		return -ENXIO;
-	return ppp_channel_read(&ap->chan, file, buf, count);
+	return -EAGAIN;
 }
 
 /*
@@ -203,12 +193,7 @@ static ssize_t
 ppp_asynctty_write(struct tty_struct *tty, struct file *file,
 		   const unsigned char *buf, size_t count)
 {
-	/* For now, do the same as the old 2.3.x code useta */
-	struct asyncppp *ap = tty->disc_data;
-
-	if (ap == 0)
-		return -ENXIO;
-	return ppp_channel_write(&ap->chan, buf, count);
+	return -EAGAIN;
 }
 
 static int
@@ -259,25 +244,6 @@ ppp_asynctty_ioctl(struct tty_struct *tty, struct file *file,
 		err = 0;
 		break;
 
-/*
- * For now, do the same as the old 2.3 driver useta
- */
-	case PPPIOCGFLAGS:
-	case PPPIOCSFLAGS:
-	case PPPIOCGASYNCMAP:
-	case PPPIOCSASYNCMAP:
-	case PPPIOCGRASYNCMAP:
-	case PPPIOCSRASYNCMAP:
-	case PPPIOCGXASYNCMAP:
-	case PPPIOCSXASYNCMAP:
-	case PPPIOCGMRU:
-	case PPPIOCSMRU:
-		err = -EPERM;
-		if (!capable(CAP_NET_ADMIN))
-			break;
-		err = ppp_async_ioctl(&ap->chan, cmd, arg);
-		break;
-
 	case PPPIOCATTACH:
 	case PPPIOCDETACH:
 		err = ppp_channel_ioctl(&ap->chan, cmd, arg);
@@ -294,18 +260,7 @@ ppp_asynctty_ioctl(struct tty_struct *tty, struct file *file,
 static unsigned int
 ppp_asynctty_poll(struct tty_struct *tty, struct file *file, poll_table *wait)
 {
-	unsigned int mask;
-	struct asyncppp *ap = tty->disc_data;
-
-	mask = POLLOUT | POLLWRNORM;
-/*
- * For now, do the same as the old 2.3 driver useta
- */
-	if (ap != 0)
-		mask |= ppp_channel_poll(&ap->chan, file, wait);
-	if (test_bit(TTY_OTHER_CLOSED, &tty->flags) || tty_hung_up_p(file))
-		mask |= POLLHUP;
-	return mask;
+	return 0;
 }
 
 static int
@@ -637,8 +592,18 @@ ppp_async_push(struct asyncppp *ap)
 	int tty_stuffed = 0;
 
 	set_bit(XMIT_WAKEUP, &ap->xmit_flags);
-	if (!spin_trylock_bh(&ap->xmit_lock))
+	/*
+	 * We can get called recursively here if the tty write
+	 * function calls our wakeup function.  This can happen
+	 * for example on a pty with both the master and slave
+	 * set to PPP line discipline.
+	 * We use the XMIT_BUSY bit to detect this and get out,
+	 * leaving the XMIT_WAKEUP bit set to tell the other
+	 * instance that it may now be able to write more now.
+	 */
+	if (test_and_set_bit(XMIT_BUSY, &ap->xmit_flags))
 		return 0;
+	spin_lock_bh(&ap->xmit_lock);
 	for (;;) {
 		if (test_and_clear_bit(XMIT_WAKEUP, &ap->xmit_flags))
 			tty_stuffed = 0;
@@ -653,7 +618,7 @@ ppp_async_push(struct asyncppp *ap)
 				tty_stuffed = 1;
 			continue;
 		}
-		if (ap->optr == ap->olim && ap->tpkt != 0) {
+		if (ap->optr >= ap->olim && ap->tpkt != 0) {
 			if (ppp_async_encode(ap)) {
 				/* finished processing ap->tpkt */
 				clear_bit(XMIT_FULL, &ap->xmit_flags);
@@ -661,17 +626,29 @@ ppp_async_push(struct asyncppp *ap)
 			}
 			continue;
 		}
-		/* haven't made any progress */
-		spin_unlock_bh(&ap->xmit_lock);
+		/*
+		 * We haven't made any progress this time around.
+		 * Clear XMIT_BUSY to let other callers in, but
+		 * after doing so we have to check if anyone set
+		 * XMIT_WAKEUP since we last checked it.  If they
+		 * did, we should try again to set XMIT_BUSY and go
+		 * around again in case XMIT_BUSY was still set when
+		 * the other caller tried.
+		 */
+		clear_bit(XMIT_BUSY, &ap->xmit_flags);
+		/* any more work to do? if not, exit the loop */
 		if (!(test_bit(XMIT_WAKEUP, &ap->xmit_flags)
 		      || (!tty_stuffed && ap->tpkt != 0)))
 			break;
-		if (!spin_trylock_bh(&ap->xmit_lock))
+		/* more work to do, see if we can do it now */
+		if (test_and_set_bit(XMIT_BUSY, &ap->xmit_flags))
 			break;
 	}
+	spin_unlock_bh(&ap->xmit_lock);
 	return done;
 
 flush:
+	clear_bit(XMIT_BUSY, &ap->xmit_flags);
 	if (ap->tpkt != 0) {
 		kfree_skb(ap->tpkt);
 		ap->tpkt = 0;

fs/Config.in

@@ -8,6 +8,8 @@ bool 'Quota support' CONFIG_QUOTA
 tristate 'Kernel automounter support' CONFIG_AUTOFS_FS
 tristate 'Kernel automounter version 4 support (also supports v3)' CONFIG_AUTOFS4_FS
 
+dep_tristate 'Reiserfs support' CONFIG_REISERFS_FS $CONFIG_EXPERIMENTAL
+dep_mbool '  Have reiserfs do extra internal checking' CONFIG_REISERFS_CHECK $CONFIG_REISERFS_FS $CONFIG_EXPERIMENTAL
 
 dep_tristate 'ADFS file system support' CONFIG_ADFS_FS $CONFIG_EXPERIMENTAL
 dep_mbool '  ADFS write support (DANGEROUS)' CONFIG_ADFS_FS_RW $CONFIG_ADFS_FS $CONFIG_EXPERIMENTAL

fs/Makefile

@@ -58,6 +58,7 @@ subdir-$(CONFIG_UDF_FS)		+= udf
 subdir-$(CONFIG_AUTOFS_FS)	+= autofs
 subdir-$(CONFIG_AUTOFS4_FS)	+= autofs4
 subdir-$(CONFIG_ADFS_FS)	+= adfs
+subdir-$(CONFIG_REISERFS_FS)	+= reiserfs
 subdir-$(CONFIG_DEVPTS_FS)	+= devpts
 subdir-$(CONFIG_SUN_OPENPROMFS)	+= openpromfs
 

fs/buffer.c

@@ -834,6 +834,10 @@ static void end_buffer_io_async(struct buffer_head * bh, int uptodate)
 	return;
 }
 
+void set_buffer_async_io(struct buffer_head *bh) {
+    bh->b_end_io = end_buffer_io_async ;
+}
+
 /*
  * Synchronise all the inode's dirty buffers to the disk.
  *
@@ -2411,6 +2415,7 @@ int try_to_free_buffers(struct page * page, int wait)
 			loop = 1;
 			goto cleaned_buffers_try_again;
 		}
+		wakeup_bdflush(0);
 	}
 	return 0;
 }

fs/inode.c

@@ -134,8 +134,12 @@ static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags)
 void __mark_inode_dirty(struct inode *inode, int flags)
 {
 	struct super_block * sb = inode->i_sb;
-
 	if (sb) {
+		/* Don't do this for I_DIRTY_PAGES - that doesn't actually dirty the inode itself */
+		if (flags & (I_DIRTY | I_DIRTY_SYNC)) {
+			if (sb->s_op && sb->s_op->dirty_inode)
+				sb->s_op->dirty_inode(inode);
+		}
 		spin_lock(&inode_lock);
 		if ((inode->i_state & flags) != flags) {
 			inode->i_state |= flags;
@@ -676,7 +680,17 @@ static struct inode * get_new_inode(struct super_block *sb, unsigned long ino, s
 			spin_unlock(&inode_lock);
 
 			clean_inode(inode);
-			sb->s_op->read_inode(inode);
+
+			/* reiserfs specific hack right here.  We don't
+			** want this to last, and are looking for VFS changes
+			** that will allow us to get rid of it.
+			** -- mason@suse.com 
+			*/
+			if (sb->s_op->read_inode2) {
+				sb->s_op->read_inode2(inode, opaque) ;
+			} else {
+				sb->s_op->read_inode(inode);
+			}
 
 			/*
 			 * This is special!  We do not need the spinlock

fs/reiserfs/Makefile

+#
+# Makefile for the linux reiser-filesystem routines.
+#
+# Note! Dependencies are done automagically by 'make dep', which also
+# removes any old dependencies. DON'T put your own dependencies here
+# unless it's something special (ie not a .c file).
+#
+# Note 2! The CFLAGS definitions are now in the main makefile...
+
+O_TARGET := reiserfs.o
+obj-y   := bitmap.o do_balan.o namei.o inode.o file.o dir.o fix_node.o super.o prints.o objectid.o \
+lbalance.o ibalance.o stree.o hashes.o buffer2.o tail_conversion.o journal.o resize.o tail_conversion.o version.o item_ops.o ioctl.o
+
+obj-m   := $(O_TARGET)
+
+include $(TOPDIR)/Rules.make
+
+TAGS:
+	etags *.c
+

fs/reiserfs/README

+[LICENSING] 
+
+ReiserFS is hereby licensed under the GNU General
+Public License version 2.
+
+Source code files that contain the phrase "licensing governed by
+reiserfs/README" are "governed files" throughout this file.  Governed
+files are licensed under the GPL.  The portions of them owned by Hans
+Reiser, or authorized to be licensed by him, have been in the past,
+and likely will be in the future, licensed to other parties under
+other licenses.  If you add your code to governed files, and don't
+want it to be owned by Hans Reiser, put your copyright label on that
+code so the poor blight and his customers can keep things straight.
+All portions of governed files not labeled otherwise are owned by Hans
+Reiser, and by adding your code to it, widely distributing it to
+others or sending us a patch, and leaving the sentence in stating that
+licensing is governed by the statement in this file, you accept this.
+It will be a kindness if you identify whether Hans Reiser is allowed
+to license code labeled as owned by you on your behalf other than
+under the GPL, because he wants to know if it is okay to do so and put
+a check in the mail to you (for non-trivial improvements) when he
+makes his next sale.  He makes no guarantees as to the amount if any,
+though he feels motivated to motivate contributors, and you can surely
+discuss this with him before or after contributing.  You have the
+right to decline to allow him to license your code contribution other
+than under the GPL.
+
+Further licensing options are available for commercial and/or other
+interests directly from Hans Reiser: hans@reiser.to.  If you interpret
+the GPL as not allowing those additional licensing options, you read
+it wrongly, and Richard Stallman agrees with me, when carefully read
+you can see that those restrictions on additional terms do not apply
+to the owner of the copyright, and my interpretation of this shall
+govern for this license.  
+
+Finally, nothing in this license shall be interpreted to allow you to
+fail to fairly credit me, or to remove my credits, without my
+permission, unless you are an end user not redistributing to others.
+If you have doubts about how to properly do that, or about what is
+fair, ask.  (Last I spoke with him Richard was contemplating how best
+to address the fair crediting issue in the next GPL version.)
+
+[END LICENSING]
+
+Reiserfs is a file system based on balanced tree algorithms, which is
+described at http://devlinux.com/namesys.
+
+Stop reading here.  Go there, then return.
+
+Send bug reports to yura@namesys.botik.ru.
+
+mkreiserfs and other utilities are in reiserfs/utils, or wherever your
+Linux provider put them.  There is some disagreement about how useful
+it is for users to get their fsck and mkreiserfs out of sync with the
+version of reiserfs that is in their kernel, with many important
+distributors wanting them out of sync.:-) Please try to remember to
+recompile and reinstall fsck and mkreiserfs with every update of
+reiserfs, this is a common source of confusion.  Note that some of the
+utilities cannot be compiled without accessing the balancing code
+which is in the kernel code, and relocating the utilities may require
+you to specify where that code can be found.
+
+Yes, if you update your reiserfs kernel module you do have to
+recompile your kernel, most of the time.  The errors you get will be
+quite cryptic if your forget to do so.
+
+Real users, as opposed to folks who want to hack and then understand
+what went wrong, will want REISERFS_CHECK off.
+
+Hideous Commercial Pitch: Spread your development costs across other OS
+vendors.  Select from the best in the world, not the best in your
+building, by buying from third party OS component suppliers.  Leverage
+the software component development power of the internet.  Be the most
+aggressive in taking advantage of the commercial possibilities of
+decentralized internet development, and add value through your branded
+integration that you sell as an operating system.  Let your competitors
+be the ones to compete against the entire internet by themselves.  Be
+hip, get with the new economic trend, before your competitors do.  Send
+email to hans@reiser.to.
+
+To understand the code, after reading the website, start reading the
+code by reading reiserfs_fs.h first.
+
+Hans Reiser was the project initiator, primary architect, source of all
+funding for the first 5.5 years, and one of the programmers.  He owns
+the copyright.
+
+Vladimir Saveljev was one of the programmers, and he worked long hours
+writing the cleanest code.  He always made the effort to be the best he
+could be, and to make his code the best that it could be.  What resulted
+was quite remarkable. I don't think that money can ever motivate someone
+to work the way he did, he is one of the most selfless men I know.
+
+Yura helps with benchmarking, coding hashes, and block pre-allocation
+code.
+
+Anatoly Pinchuk is a former member of our team who worked closely with
+Vladimir throughout the project's development.  He wrote a quite
+substantial portion of the total code.  He realized that there was a
+space problem with packing tails of files for files larger than a node
+that start on a node aligned boundary (there are reasons to want to node
+align files), and he invented and implemented indirect items and
+unformatted nodes as the solution.
+
+Konstantin Shvachko, with the help of the Russian version of a VC,
+tried to put me in a position where I was forced into giving control
+of the project to him.  (Fortunately, as the person paying the money
+for all salaries from my dayjob I owned all copyrights, and you can't
+really force takeovers of sole proprietorships.)  This was something
+curious, because he never really understood the value of our project,
+why we should do what we do, or why innovation was possible in
+general, but he was sure that he ought to be controlling it.  Every
+innovation had to be forced past him while he was with us.  He added
+two years to the time required to complete reiserfs, and was a net
+loss for me.  Mikhail Gilula was a brilliant innovator who also left
+in a destructive way that erased the value of his contributions, and
+that he was shown much generosity just makes it more painful.
+
+Grigory Zaigralin was an extremely effective system administrator for
+our group.
+
+Igor Krasheninnikov was wonderful at hardware procurement, repair, and
+network installation.
+
+Jeremy Fitzhardinge wrote the teahash.c code, and he gives credit to a
+textbook he got the algorithm from in the code.  Note that his analysis
+of how we could use the hashing code in making 32 bit NFS cookies work
+was probably more important than the actual algorithm.  Colin Plumb also
+contributed to it.
+
+Chris Mason dived right into our code, and in just a few months produced
+the journaling code that dramatically increased the value of ReiserFS.
+He is just an amazing programmer.
+
+Igor Zagorovsky is writing much of the new item handler and extent code
+for our next major release.
+
+Alexander Zarochentcev (sometimes known as zam, or sasha), wrote the
+resizer, and is hard at work on implementing allocate on flush.  SGI
+implemented allocate on flush before us for XFS, and generously took
+the time to convince me we should do it also.  They are great people,
+and a great company.
+
+Yuri Shevchuk and Nikita Danilov are doing squid cache optimization.
+
+Vitaly Fertman is doing fsck.
+
+SuSE, IntegratedLinux.com, Ecila, MP3.com, bigstorage.com, and the
+Alpha PC Company made it possible for me to not have a day job
+anymore, and to dramatically increase our staffing.  Ecila funded
+hypertext feature development, MP3.com funded journaling, SuSE funded
+core development, IntegratedLinux.com funded squid web cache
+appliances, bigstorage.com funded HSM, and the alpha PC company funded
+the alpha port.  Many of these tasks were helped by sponsors other
+than the ones just named.  SuSE has helped in much more than just
+funding....
+

fs/reiserfs/dir.c

+/*
+ * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
+ */
+
+#ifdef __KERNEL__
+
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/reiserfs_fs.h>
+#include <linux/stat.h>
+#include <linux/smp_lock.h>
+#include <asm/uaccess.h>
+
+#else
+
+#include "nokernel.h"
+
+#endif
+
+extern struct key  MIN_KEY;
+
+static int reiserfs_readdir (struct file *, void *, filldir_t);
+int reiserfs_dir_fsync(struct file *filp, struct dentry *dentry, int datasync) ;
+
+struct file_operations reiserfs_dir_operations = {
+    read:	generic_read_dir,
+    readdir:	reiserfs_readdir,
+    fsync:	reiserfs_dir_fsync,
+};
+
+/*
+ * directories can handle most operations...
+ */
+struct inode_operations reiserfs_dir_inode_operations = {
+  //&reiserfs_dir_operations,	/* default_file_ops */
+    create:	reiserfs_create,
+    lookup:	reiserfs_lookup,
+    link:	reiserfs_link,
+    unlink:	reiserfs_unlink,
+    symlink:	reiserfs_symlink,
+    mkdir:	reiserfs_mkdir,
+    rmdir:	reiserfs_rmdir,
+    mknod:	reiserfs_mknod,
+    rename:	reiserfs_rename,
+};
+
+int reiserfs_dir_fsync(struct file *filp, struct dentry *dentry, int datasync) {
+  int ret = 0 ;
+  int windex ;
+  struct reiserfs_transaction_handle th ;
+
+  journal_begin(&th, dentry->d_inode->i_sb, 1) ;
+  windex = push_journal_writer("dir_fsync") ;
+  reiserfs_prepare_for_journal(th.t_super, SB_BUFFER_WITH_SB(th.t_super), 1) ;
+  journal_mark_dirty(&th, dentry->d_inode->i_sb, SB_BUFFER_WITH_SB (dentry->d_inode->i_sb)) ;
+  pop_journal_writer(windex) ;
+  journal_end_sync(&th, dentry->d_inode->i_sb, 1) ;
+
+  return ret ;
+}
+
+
+#define store_ih(where,what) copy_item_head (where, what)
+
+//
+static int reiserfs_readdir (struct file * filp, void * dirent, filldir_t filldir)
+{
+    struct inode *inode = filp->f_dentry->d_inode;
+    struct cpu_key pos_key;	/* key of current position in the directory (key of directory entry) */
+    INITIALIZE_PATH (path_to_entry);
+    struct buffer_head * bh;
+    int item_num, entry_num;
+    struct key * rkey;
+    struct item_head * ih, tmp_ih;
+    int search_res;
+    char * local_buf;
+    loff_t next_pos;
+    char small_buf[32] ; /* avoid kmalloc if we can */
+    struct reiserfs_dir_entry de;
+
+
+    reiserfs_check_lock_depth("readdir") ;
+
+    /* form key for search the next directory entry using f_pos field of
+       file structure */
+    make_cpu_key (&pos_key, inode, (filp->f_pos) ? (filp->f_pos) : DOT_OFFSET,
+		  TYPE_DIRENTRY, 3);
+    next_pos = cpu_key_k_offset (&pos_key);
+
+    /*  reiserfs_warning ("reiserfs_readdir 1: f_pos = %Ld\n", filp->f_pos);*/
+
+    while (1) {
+    research:
+	/* search the directory item, containing entry with specified key */
+	search_res = search_by_entry_key (inode->i_sb, &pos_key, &path_to_entry, &de);
+	if (search_res == IO_ERROR) {
+	    // FIXME: we could just skip part of directory which could
+	    // not be read
+	    return -EIO;
+	}
+	entry_num = de.de_entry_num;
+	bh = de.de_bh;
+	item_num = de.de_item_num;
+	ih = de.de_ih;
+	store_ih (&tmp_ih, ih);
+		
+#ifdef CONFIG_REISERFS_CHECK
+	/* we must have found item, that is item of this directory, */
+	if (COMP_SHORT_KEYS (&(ih->ih_key), &pos_key))
+	    reiserfs_panic (inode->i_sb, "vs-9000: reiserfs_readdir: "
+			    "found item %h does not match to dir we readdir %k",
+			    ih, &pos_key);
+      
+	if (item_num > B_NR_ITEMS (bh) - 1)
+	    reiserfs_panic (inode->i_sb, "vs-9005: reiserfs_readdir: "
+			    "item_num == %d, item amount == %d",
+			    item_num, B_NR_ITEMS (bh));
+      
+	/* and entry must be not more than number of entries in the item */
+	if (I_ENTRY_COUNT (ih) < entry_num)
+	    reiserfs_panic (inode->i_sb, "vs-9010: reiserfs_readdir: "
+			    "entry number is too big %d (%d)",
+			    entry_num, I_ENTRY_COUNT (ih));
+#endif	/* CONFIG_REISERFS_CHECK */
+
+	if (search_res == POSITION_FOUND || entry_num < I_ENTRY_COUNT (ih)) {
+	    /* go through all entries in the directory item beginning from the entry, that has been found */
+	    struct reiserfs_de_head * deh = B_I_DEH (bh, ih) + entry_num;
+
+	    for (; entry_num < I_ENTRY_COUNT (ih); entry_num ++, deh ++) {
+		int d_reclen;
+		char * d_name;
+		off_t d_off;
+		ino_t d_ino;
+
+		if (!de_visible (deh))
+		    /* it is hidden entry */
+		    continue;
+		d_reclen = entry_length (bh, ih, entry_num);
+		d_name = B_I_DEH_ENTRY_FILE_NAME (bh, ih, deh);
+		if (!d_name[d_reclen - 1])
+		    d_reclen = strlen (d_name);
+	
+		d_off = deh_offset (deh);
+		filp->f_pos = d_off ;
+		d_ino = deh_objectid (deh);
+		if (d_reclen <= 32) {
+		  local_buf = small_buf ;
+		} else {
+		    local_buf = kmalloc(d_reclen, GFP_BUFFER) ;
+		    if (!local_buf) {
+			pathrelse (&path_to_entry);
+			return -ENOMEM ;
+		    }
+		    if (item_moved (&tmp_ih, &path_to_entry)) {
+			kfree(local_buf) ;
+			goto research;
+		    }
+		}
+		// Note, that we copy name to user space via temporary
+		// buffer (local_buf) because filldir will block if
+		// user space buffer is swapped out. At that time
+		// entry can move to somewhere else
+		memcpy (local_buf, d_name, d_reclen);
+		if (filldir (dirent, d_name, d_reclen, d_off, d_ino, 
+		             DT_UNKNOWN) < 0) {
+		    if (local_buf != small_buf) {
+			kfree(local_buf) ;
+		    }
+		    goto end;
+		}
+		if (local_buf != small_buf) {
+		    kfree(local_buf) ;
+		}
+
+		// next entry should be looked for with such offset
+		next_pos = deh_offset (deh) + 1;
+
+		if (item_moved (&tmp_ih, &path_to_entry)) {
+		    reiserfs_warning ("vs-9020: reiserfs_readdir "
+				      "things are moving under hands. Researching..\n");
+		    goto research;
+		}
+	    } /* for */
+	}
+
+	if (item_num != B_NR_ITEMS (bh) - 1)
+	    // end of directory has been reached
+	    goto end;
+
+	/* item we went through is last item of node. Using right
+	   delimiting key check is it directory end */
+	rkey = get_rkey (&path_to_entry, inode->i_sb);
+	if (! comp_le_keys (rkey, &MIN_KEY)) {
+#ifdef CONFIG_REISERFS_CHECK
+	    reiserfs_warning ("vs-9025: reiserfs_readdir:"
+			      "get_rkey failed. Researching..\n");
+#endif
+	    /* set pos_key to key, that is the smallest and greater
+	       that key of the last entry in the item */
+	    set_cpu_key_k_offset (&pos_key, next_pos);
+	    continue;
+	}
+
+	if ( COMP_SHORT_KEYS (rkey, &pos_key)) {
+	    // end of directory has been reached
+	    goto end;
+	}
+	
+	/* directory continues in the right neighboring block */
+	set_cpu_key_k_offset (&pos_key, le_key_k_offset (ITEM_VERSION_1, rkey));
+
+    } /* while */
+
+
+ end:
+    // FIXME: ext2_readdir does not reset f_pos
+    filp->f_pos = next_pos;
+    pathrelse (&path_to_entry);
+    reiserfs_check_path(&path_to_entry) ;
+    return 0;
+}
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

fs/reiserfs/file.c

+/*
+ * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
+ */
+
+
+#ifdef __KERNEL__
+
+#include <linux/sched.h>
+#include <linux/reiserfs_fs.h>
+#include <linux/smp_lock.h>
+
+#else
+
+#include "nokernel.h"
+
+#endif
+
+/*
+** We pack the tails of files on file close, not at the time they are written.
+** This implies an unnecessary copy of the tail and an unnecessary indirect item
+** insertion/balancing, for files that are written in one write.
+** It avoids unnecessary tail packings (balances) for files that are written in
+** multiple writes and are small enough to have tails.
+** 
+** file_release is called by the VFS layer when the file is closed.  If
+** this is the last open file descriptor, and the file
+** small enough to have a tail, and the tail is currently in an
+** unformatted node, the tail is converted back into a direct item.
+** 
+** We use reiserfs_truncate_file to pack the tail, since it already has
+** all the conditions coded.  
+*/
+static int reiserfs_file_release (struct inode * inode, struct file * filp)
+{
+
+    struct reiserfs_transaction_handle th ;
+    int windex ;
+
+    if (!S_ISREG (inode->i_mode))
+	BUG ();
+
+    /* fast out for when nothing needs to be done */
+    if ((atomic_read(&inode->i_count) > 1 ||
+         !inode->u.reiserfs_i.i_pack_on_close || 
+         !tail_has_to_be_packed(inode))       && 
+	inode->u.reiserfs_i.i_prealloc_count <= 0) {
+	return 0;
+    }    
+    
+    lock_kernel() ;
+    down (&inode->i_sem); 
+    journal_begin(&th, inode->i_sb, JOURNAL_PER_BALANCE_CNT * 3) ;
+
+#ifdef REISERFS_PREALLOCATE
+    reiserfs_discard_prealloc (&th, inode);
+#endif
+    journal_end(&th, inode->i_sb, JOURNAL_PER_BALANCE_CNT * 3) ;
+
+    if (atomic_read(&inode->i_count) <= 1 &&
+	inode->u.reiserfs_i.i_pack_on_close &&
+        tail_has_to_be_packed (inode)) {
+	/* if regular file is released by last holder and it has been
+	   appended (we append by unformatted node only) or its direct
+	   item(s) had to be converted, then it may have to be
+	   indirect2direct converted */
+	windex = push_journal_writer("file_release") ;
+	reiserfs_truncate_file(inode) ;
+	pop_journal_writer(windex) ;
+    }
+    up (&inode->i_sem); 
+    unlock_kernel() ;
+    return 0;
+}
+
+
+/* Sync a reiserfs file. */
+static int reiserfs_sync_file(
+			      struct file   * p_s_filp,
+			      struct dentry * p_s_dentry,
+			      int datasync
+			      ) {
+  struct inode * p_s_inode = p_s_dentry->d_inode;
+  struct reiserfs_transaction_handle th ;
+  int n_err = 0;
+  int windex ;
+  int jbegin_count = 1 ;
+
+  lock_kernel() ;
+
+  if (!S_ISREG(p_s_inode->i_mode))
+      BUG ();
+
+  n_err = fsync_inode_buffers(p_s_inode) ;
+  /* commit the current transaction to flush any metadata
+  ** changes.  sys_fsync takes care of flushing the dirty pages for us
+  */
+  journal_begin(&th, p_s_inode->i_sb, jbegin_count) ;
+  windex = push_journal_writer("sync_file") ;
+  reiserfs_update_sd(&th, p_s_inode);
+  pop_journal_writer(windex) ;
+  journal_end_sync(&th, p_s_inode->i_sb,jbegin_count) ;
+  unlock_kernel() ;
+  return ( n_err < 0 ) ? -EIO : 0;
+}
+
+
+struct file_operations reiserfs_file_operations = {
+    read:	generic_file_read,
+    write:	generic_file_write,
+    ioctl:	reiserfs_ioctl,
+    mmap:	generic_file_mmap,
+    release:	reiserfs_file_release,
+    fsync:	reiserfs_sync_file,
+};
+
+
+struct  inode_operations reiserfs_file_inode_operations = {
+    truncate:	reiserfs_truncate_file,
+};
+
+

fs/reiserfs/hashes.c

+
+/*
+ * Keyed 32-bit hash function using TEA in a Davis-Meyer function
+ *   H0 = Key
+ *   Hi = E Mi(Hi-1) + Hi-1
+ *
+ * (see Applied Cryptography, 2nd edition, p448).
+ *
+ * Jeremy Fitzhardinge <jeremy@zip.com.au> 1998
+ * 
+ * Jeremy has agreed to the contents of reiserfs/README. -Hans
+ * Yura's function is added (04/07/2000)
+ */
+
+//
+// keyed_hash
+// yura_hash
+// r5_hash
+//
+
+#include <asm/types.h>
+
+
+
+#define DELTA 0x9E3779B9
+#define FULLROUNDS 10		/* 32 is overkill, 16 is strong crypto */
+#define PARTROUNDS 6		/* 6 gets complete mixing */
+
+#ifndef __KERNEL__
+typedef __u32 u32;
+#endif
+
+/* a, b, c, d - data; h0, h1 - accumulated hash */
+#define TEACORE(rounds)							\
+	do {								\
+		u32 sum = 0;						\
+		int n = rounds;						\
+		u32 b0, b1;						\
+									\
+		b0 = h0;						\
+		b1 = h1;						\
+									\
+		do							\
+		{							\
+			sum += DELTA;					\
+			b0 += ((b1 << 4)+a) ^ (b1+sum) ^ ((b1 >> 5)+b);	\
+			b1 += ((b0 << 4)+c) ^ (b0+sum) ^ ((b0 >> 5)+d);	\
+		} while(--n);						\
+									\
+		h0 += b0;						\
+		h1 += b1;						\
+	} while(0)
+
+
+u32 keyed_hash(const char *msg, int len)
+{
+	u32 k[] = { 0x9464a485, 0x542e1a94, 0x3e846bff, 0xb75bcfc3}; 
+
+	u32 h0 = k[0], h1 = k[1];
+	u32 a, b, c, d;
+	u32 pad;
+	int i;
+ 
+
+	//	assert(len >= 0 && len < 256);
+
+	pad = (u32)len | ((u32)len << 8);
+	pad |= pad << 16;
+
+	while(len >= 16)
+	{
+		a = (u32)msg[ 0]      |
+		    (u32)msg[ 1] << 8 |
+		    (u32)msg[ 2] << 16|
+		    (u32)msg[ 3] << 24;
+		b = (u32)msg[ 4]      |
+		    (u32)msg[ 5] << 8 |
+		    (u32)msg[ 6] << 16|
+		    (u32)msg[ 7] << 24;
+		c = (u32)msg[ 8]      |
+		    (u32)msg[ 9] << 8 |
+		    (u32)msg[10] << 16|
+		    (u32)msg[11] << 24;
+		d = (u32)msg[12]      |
+		    (u32)msg[13] << 8 |
+		    (u32)msg[14] << 16|
+		    (u32)msg[15] << 24;
+		
+		TEACORE(PARTROUNDS);
+
+		len -= 16;
+		msg += 16;
+	}
+
+	if (len >= 12)
+	{
+	    	//assert(len < 16);
+		if (len >= 16)
+		    *(int *)0 = 0;
+
+		a = (u32)msg[ 0]      |
+		    (u32)msg[ 1] << 8 |
+		    (u32)msg[ 2] << 16|
+		    (u32)msg[ 3] << 24;
+		b = (u32)msg[ 4]      |
+		    (u32)msg[ 5] << 8 |
+		    (u32)msg[ 6] << 16|
+		    (u32)msg[ 7] << 24;
+		c = (u32)msg[ 8]      |
+		    (u32)msg[ 9] << 8 |
+		    (u32)msg[10] << 16|
+		    (u32)msg[11] << 24;
+
+		d = pad;
+		for(i = 12; i < len; i++)
+		{
+			d <<= 8;
+			d |= msg[i];
+		}
+	}
+	else if (len >= 8)
+	{
+	    	//assert(len < 12);
+		if (len >= 12)
+		    *(int *)0 = 0;
+		a = (u32)msg[ 0]      |
+		    (u32)msg[ 1] << 8 |
+		    (u32)msg[ 2] << 16|
+		    (u32)msg[ 3] << 24;
+		b = (u32)msg[ 4]      |
+		    (u32)msg[ 5] << 8 |
+		    (u32)msg[ 6] << 16|
+		    (u32)msg[ 7] << 24;
+
+		c = d = pad;
+		for(i = 8; i < len; i++)
+		{
+			c <<= 8;
+			c |= msg[i];
+		}
+	}
+	else if (len >= 4)
+	{
+	    	//assert(len < 8);
+		if (len >= 8)
+		    *(int *)0 = 0;
+		a = (u32)msg[ 0]      |
+		    (u32)msg[ 1] << 8 |
+		    (u32)msg[ 2] << 16|
+		    (u32)msg[ 3] << 24;
+
+		b = c = d = pad;
+		for(i = 4; i < len; i++)
+		{
+			b <<= 8;
+			b |= msg[i];
+		}
+	}
+	else
+	{
+	    	//assert(len < 4);
+		if (len >= 4)
+		    *(int *)0 = 0;
+		a = b = c = d = pad;
+		for(i = 0; i < len; i++)
+		{
+			a <<= 8;
+			a |= msg[i];
+		}
+	}
+
+	TEACORE(FULLROUNDS);
+
+/*	return 0;*/
+	return h0^h1;
+}
+
+/* What follows in this file is copyright 2000 by Hans Reiser, and the
+ * licensing of what follows is governed by reiserfs/README */
+
+u32 yura_hash (const char *msg, int len)
+{
+    int j, pow;
+    u32 a, c;
+    int i;
+    
+    for (pow=1,i=1; i < len; i++) pow = pow * 10; 
+    
+    if (len == 1) 
+	a = msg[0]-48;
+    else
+	a = (msg[0] - 48) * pow;
+    
+    for (i=1; i < len; i++) {
+	c = msg[i] - 48; 
+	for (pow=1,j=i; j < len-1; j++) pow = pow * 10; 
+	a = a + c * pow;
+    }
+    
+    for (; i < 40; i++) {
+	c = '0' - 48; 
+	for (pow=1,j=i; j < len-1; j++) pow = pow * 10; 
+	a = a + c * pow;
+    }
+    
+    for (; i < 256; i++) {
+	c = i; 
+	for (pow=1,j=i; j < len-1; j++) pow = pow * 10; 
+	a = a + c * pow;
+    }
+    
+    a = a << 7;
+    return a;
+}
+
+u32 r5_hash (const char *msg, int len)
+{
+  u32 a=0;
+  while(*msg) { 
+    a += *msg << 4;
+    a += *msg >> 4;
+    a *= 11;
+    msg++;
+   } 
+  return a;
+}

fs/reiserfs/ioctl.c

+/*
+ * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
+ */
+
+#ifdef __KERNEL__
+
+#include <linux/fs.h>
+#include <linux/reiserfs_fs.h>
+#include <linux/sched.h>
+#include <asm/uaccess.h>
+#include <linux/smp_lock.h>
+#include <linux/locks.h>
+
+#else
+
+#include "nokernel.h"
+
+#endif
+
+/*
+** reiserfs_ioctl - handler for ioctl for inode
+** supported commands:
+**  1) REISERFS_IOC_UNPACK - try to unpack tail from direct item into indirect
+**                           and prevent packing file (argument arg has to be non-zero)
+**  2) That's all for a while ...
+*/
+int reiserfs_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
+		unsigned long arg)
+{
+	switch (cmd) {
+	    case REISERFS_IOC_UNPACK:
+		if (arg)
+		    return reiserfs_unpack (inode, filp);
+			
+	    default:
+		return -ENOTTY;
+	}
+}
+
+/*
+** reiserfs_unpack
+** Function try to convert tail from direct item into indirect.
+** It set up nopack attribute in the inode.u.reiserfs_i.nopack
+*/
+int reiserfs_unpack (struct inode * inode, struct file * filp)
+{
+    int retval = 0;
+    int index ;
+    struct page *page ;
+    unsigned long write_from ;
+    unsigned long blocksize = inode->i_sb->s_blocksize ;
+    	
+    if (inode->i_size == 0) {
+        return -EINVAL ;
+    }
+    /* ioctl already done */
+    if (inode->u.reiserfs_i.nopack) {
+        return 0 ;
+    }
+    lock_kernel();
+
+    /* we need to make sure nobody is changing the file size beneath
+    ** us
+    */
+    down(&inode->i_sem) ;
+
+    write_from = inode->i_size & (blocksize - 1) ;
+    /* if we are on a block boundary, we are already unpacked.  */
+    if ( write_from == 0) {
+	inode->u.reiserfs_i.nopack = 1;
+	goto out ;
+    }
+
+    /* we unpack by finding the page with the tail, and calling
+    ** reiserfs_prepare_write on that page.  This will force a 
+    ** reiserfs_get_block to unpack the tail for us.
+    */
+    index = inode->i_size >> PAGE_CACHE_SHIFT ;
+    page = grab_cache_page(inode->i_mapping, index) ;
+    retval = PTR_ERR(page) ;
+    if (IS_ERR(page)) {
+        goto out ;
+    }
+    retval = reiserfs_prepare_write(NULL, page, write_from, blocksize) ;
+    if (retval)
+        goto out_unlock ;
+
+    /* conversion can change page contents, must flush */
+    flush_dcache_page(page) ;
+    inode->u.reiserfs_i.nopack = 1;
+    kunmap(page) ; /* mapped by prepare_write */
+
+out_unlock:
+    UnlockPage(page) ;
+    page_cache_release(page) ;
+
+out:
+    up(&inode->i_sem) ;
+    unlock_kernel();    
+    return retval;
+}

fs/reiserfs/version.c

+/*
+ * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
+ */
+
+char *reiserfs_get_version_string(void) {
+  return "ReiserFS version 3.6.25" ;
+}

include/asm-alpha/errno.h

@@ -139,4 +139,6 @@
 #define ENOMEDIUM	129	/* No medium found */
 #define EMEDIUMTYPE	130	/* Wrong medium type */
 
+#define EHASHCOLLISION  131     /* Number of hash collisons exceeds maximum generation counter value.  */
+
 #endif