--- lum-pristine/include/linux/lustre_version.h Wed Dec 31 19:00:00 1969 +++ lum/include/linux/lustre_version.h Tue Nov 26 07:02:14 2002 @@ -0,0 +1,1 @@ +#define LUSTRE_KERNEL_VERSION 5 --- lum-pristine/arch/ia64/mm/init.c Fri Nov 9 17:26:17 2001 +++ lum/arch/ia64/mm/init.c Thu Aug 1 18:07:35 2002 @@ -37,6 +37,12 @@ static unsigned long totalram_pages; +struct page *check_get_page(unsigned long kaddr) +{ +#warning FIXME: Lustre team, is this solid? + return virt_to_page(kaddr); +} + int do_check_pgt_cache (int low, int high) { --- lum-pristine/arch/i386/mm/init.c Fri Dec 21 12:41:53 2001 +++ lum/arch/i386/mm/init.c Thu Aug 1 18:07:35 2002 @@ -43,6 +43,12 @@ static unsigned long totalram_pages; static unsigned long totalhigh_pages; +struct page *check_get_page(unsigned long kaddr) +{ +#warning FIXME: Lustre team, is this solid? + return virt_to_page(kaddr); +} + int do_check_pgt_cache(int low, int high) { int freed = 0; --- lum-pristine/drivers/block/blkpg.c Mon Feb 25 14:37:57 2002 +++ lum/drivers/block/blkpg.c Thu Aug 1 18:07:35 2002 @@ -294,3 +294,38 @@ } EXPORT_SYMBOL(blk_ioctl); + +#define NUM_DEV_NO_WRITE 16 +static int dev_no_write[NUM_DEV_NO_WRITE]; + +/* + * Debug code for turning block devices "read-only" (will discard writes + * silently). This is for filesystem crash/recovery testing. + */ +void dev_set_rdonly(kdev_t dev, int no_write) +{ + if (dev) { + printk(KERN_WARNING "Turning device %s read-only\n", + bdevname(dev)); + dev_no_write[no_write] = 0xdead0000 + dev; + } +} + +int dev_check_rdonly(kdev_t dev) { + int i; + + for (i = 0; i < NUM_DEV_NO_WRITE; i++) { + if ((dev_no_write[i] & 0xffff0000) == 0xdead0000 && + dev == (dev_no_write[i] & 0xffff)) + return 1; + } + return 0; +} + +void dev_clear_rdonly(int no_write) { + dev_no_write[no_write] = 0; +} + +EXPORT_SYMBOL(dev_set_rdonly); +EXPORT_SYMBOL(dev_check_rdonly); +EXPORT_SYMBOL(dev_clear_rdonly); --- lum-pristine/drivers/block/loop.c Fri Dec 21 12:41:53 2001 +++ lum/drivers/block/loop.c Thu Aug 1 18:07:35 2002 @@ -471,6 +471,11 @@ spin_unlock_irq(&lo->lo_lock); if (rw == WRITE) { +#ifdef CONFIG_DEV_RDONLY + if (dev_check_rdonly(rbh->b_rdev)) + goto err; +#endif + if (lo->lo_flags & LO_FLAGS_READ_ONLY) goto err; } else if (rw == READA) { --- lum-pristine/drivers/ide/ide-disk.c Fri Dec 21 12:41:54 2001 +++ lum/drivers/ide/ide-disk.c Thu Aug 1 18:07:35 2002 @@ -367,6 +367,12 @@ */ static ide_startstop_t do_rw_disk (ide_drive_t *drive, struct request *rq, unsigned long block) { +#ifdef CONFIG_DEV_RDONLY + if (rq->cmd == WRITE && dev_check_rdonly(rq->rq_dev)) { + ide_end_request(1, HWGROUP(drive)); + return ide_stopped; + } +#endif if (IDE_CONTROL_REG) OUT_BYTE(drive->ctl,IDE_CONTROL_REG); OUT_BYTE(0x00, IDE_FEATURE_REG); --- lum-pristine/fs/ext3/Makefile Fri Dec 21 12:41:55 2001 +++ lum/fs/ext3/Makefile Thu Aug 1 18:07:35 2002 @@ -9,6 +9,8 @@ O_TARGET := ext3.o +export-objs := super.o + obj-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o \ ioctl.o namei.o super.o symlink.o obj-m := $(O_TARGET) --- lum-pristine/fs/ext3/super.c Mon Feb 25 14:38:08 2002 +++ lum/fs/ext3/super.c Thu Aug 1 18:07:35 2002 @@ -1744,7 +1744,7 @@ unregister_filesystem(&ext3_fs_type); } -EXPORT_NO_SYMBOLS; +EXPORT_SYMBOL(ext3_bread); MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others"); MODULE_DESCRIPTION("Second Extended Filesystem with journaling extensions"); --- lum-pristine/fs/jbd/commit.c Mon Feb 25 14:38:08 2002 +++ lum/fs/jbd/commit.c Thu Aug 1 18:07:35 2002 @@ -475,7 +475,7 @@ transaction's t_log_list queue, and metadata buffers are on the t_iobuf_list queue. - Wait for the transactions in reverse order. That way we are + Wait for the buffers in reverse order. That way we are less likely to be woken up until all IOs have completed, and so we incur less scheduling load. */ @@ -566,8 +566,10 @@ jbd_debug(3, "JBD: commit phase 6\n"); - if (is_journal_aborted(journal)) + if (is_journal_aborted(journal)) { + unlock_journal(journal); goto skip_commit; + } /* Done it all: now write the commit record. We should have * cleaned up our previous buffers by now, so if we are in abort @@ -577,6 +579,7 @@ descriptor = journal_get_descriptor_buffer(journal); if (!descriptor) { __journal_abort_hard(journal); + unlock_journal(journal); goto skip_commit; } @@ -600,7 +603,6 @@ put_bh(bh); /* One for getblk() */ journal_unlock_journal_head(descriptor); } - lock_journal(journal); /* End of a transaction! Finally, we can do checkpoint processing: any buffers committed as a result of this @@ -609,6 +611,25 @@ skip_commit: + /* Call any callbacks that had been registered for handles in this + * transaction. It is up to the callback to free any allocated + * memory. + */ + if (!list_empty(&commit_transaction->t_jcb)) { + struct list_head *p, *n; + int error = is_journal_aborted(journal); + + list_for_each_safe(p, n, &commit_transaction->t_jcb) { + struct journal_callback *jcb; + + jcb = list_entry(p, struct journal_callback, jcb_list); + list_del(p); + jcb->jcb_func(jcb, error); + } + } + + lock_journal(journal); + jbd_debug(3, "JBD: commit phase 7\n"); J_ASSERT(commit_transaction->t_sync_datalist == NULL); --- lum-pristine/fs/jbd/journal.c Mon Feb 25 14:38:08 2002 +++ lum/fs/jbd/journal.c Thu Aug 1 18:07:35 2002 @@ -58,6 +58,7 @@ #endif EXPORT_SYMBOL(journal_flush); EXPORT_SYMBOL(journal_revoke); +EXPORT_SYMBOL(journal_callback_set); EXPORT_SYMBOL(journal_init_dev); EXPORT_SYMBOL(journal_init_inode); --- lum-pristine/fs/jbd/transaction.c Mon Feb 25 14:38:08 2002 +++ lum/fs/jbd/transaction.c Thu Aug 1 18:07:35 2002 @@ -57,6 +57,7 @@ transaction->t_state = T_RUNNING; transaction->t_tid = journal->j_transaction_sequence++; transaction->t_expires = jiffies + journal->j_commit_interval; + INIT_LIST_HEAD(&transaction->t_jcb); /* Set up the commit timer for the new transaction. */ J_ASSERT (!journal->j_commit_timer_active); @@ -201,6 +202,20 @@ return 0; } +/* Allocate a new handle. This should probably be in a slab... */ +static handle_t *new_handle(int nblocks) +{ + handle_t *handle = jbd_kmalloc(sizeof (handle_t), GFP_NOFS); + if (!handle) + return NULL; + memset(handle, 0, sizeof (handle_t)); + handle->h_buffer_credits = nblocks; + handle->h_ref = 1; + INIT_LIST_HEAD(&handle->h_jcb); + + return handle; +} + /* * Obtain a new handle. * @@ -227,14 +242,11 @@ handle->h_ref++; return handle; } - - handle = jbd_kmalloc(sizeof (handle_t), GFP_NOFS); + + handle = new_handle(nblocks); if (!handle) return ERR_PTR(-ENOMEM); - memset (handle, 0, sizeof (handle_t)); - handle->h_buffer_credits = nblocks; - handle->h_ref = 1; current->journal_info = handle; err = start_this_handle(journal, handle); @@ -333,14 +345,11 @@ if (is_journal_aborted(journal)) return ERR_PTR(-EIO); - - handle = jbd_kmalloc(sizeof (handle_t), GFP_NOFS); + + handle = new_handle(nblocks); if (!handle) return ERR_PTR(-ENOMEM); - memset (handle, 0, sizeof (handle_t)); - handle->h_buffer_credits = nblocks; - handle->h_ref = 1; current->journal_info = handle; err = try_start_this_handle(journal, handle); @@ -1328,6 +1337,28 @@ #endif /* + * Register a callback function for this handle. The function will be + * called when the transaction that this handle is part of has been + * committed to disk with the original callback data struct and the + * error status of the journal as parameters. There is no guarantee of + * ordering between handles within a single transaction, nor between + * callbacks registered on the same handle. + * + * The caller is responsible for allocating the journal_callback struct. + * This is to allow the caller to add as much extra data to the callback + * as needed, but reduce the overhead of multiple allocations. The caller + * allocated struct must start with a struct journal_callback at offset 0, + * and has the caller-specific data afterwards. + */ +void journal_callback_set(handle_t *handle, + void (*func)(struct journal_callback *jcb, int error), + struct journal_callback *jcb) +{ + list_add(&jcb->jcb_list, &handle->h_jcb); + jcb->jcb_func = func; +} + +/* * All done for a particular handle. * * There is not much action needed here. We just return any remaining @@ -1383,7 +1415,10 @@ wake_up(&journal->j_wait_transaction_locked); } - /* + /* Move callbacks from the handle to the transaction. */ + list_splice(&handle->h_jcb, &transaction->t_jcb); + + /* * If the handle is marked SYNC, we need to set another commit * going! We also want to force a commit if the current * transaction is occupying too much of the log, or if the --- lum-pristine/include/linux/blkdev.h Mon Nov 26 08:29:17 2001 +++ lum/include/linux/blkdev.h Mon Aug 12 11:48:39 2002 @@ -228,4 +228,8 @@ return retval; } +#define CONFIG_DEV_RDONLY +void dev_set_rdonly(kdev_t, int); +int dev_check_rdonly(kdev_t); +void dev_clear_rdonly(int); #endif --- lum-pristine/include/linux/slab.h Fri Dec 21 12:42:04 2001 +++ lum/include/linux/slab.h Mon Aug 12 11:48:38 2002 @@ -57,6 +57,7 @@ extern int kmem_cache_shrink(kmem_cache_t *); extern void *kmem_cache_alloc(kmem_cache_t *, int); extern void kmem_cache_free(kmem_cache_t *, void *); +extern int kmem_cache_validate(kmem_cache_t *cachep, void *objp); extern void *kmalloc(size_t, int); extern void kfree(const void *); --- lum-pristine/include/linux/jbd.h Mon Feb 25 14:38:13 2002 +++ lum/include/linux/jbd.h Mon Aug 12 11:50:09 2002 @@ -249,6 +249,13 @@ return bh->b_private; } +#define HAVE_JOURNAL_CALLBACK_STATUS +struct journal_callback { + struct list_head jcb_list; + void (*jcb_func)(struct journal_callback *jcb, int error); + /* user data goes here */ +}; + struct jbd_revoke_table_s; /* The handle_t type represents a single atomic update being performed @@ -279,6 +286,12 @@ operations */ int h_err; + /* List of application registered callbacks for this handle. + * The function(s) will be called after the transaction that + * this handle is part of has been committed to disk. + */ + struct list_head h_jcb; + /* Flags */ unsigned int h_sync: 1; /* sync-on-close */ unsigned int h_jdata: 1; /* force data journaling */ @@ -398,6 +411,10 @@ /* How many handles used this transaction? */ int t_handle_count; + + /* List of registered callback functions for this transaction. + * Called when the transaction is committed. */ + struct list_head t_jcb; }; @@ -646,6 +663,9 @@ extern int journal_try_to_free_buffers(journal_t *, struct page *, int); extern int journal_stop(handle_t *); extern int journal_flush (journal_t *); +extern void journal_callback_set(handle_t *handle, + void (*fn)(struct journal_callback *,int), + struct journal_callback *jcb); extern void journal_lock_updates (journal_t *); extern void journal_unlock_updates (journal_t *); --- lum-pristine/kernel/ksyms.c Mon Feb 25 14:38:13 2002 +++ lum/kernel/ksyms.c Thu Aug 1 18:07:35 2002 @@ -260,6 +260,7 @@ EXPORT_SYMBOL(set_page_dirty); EXPORT_SYMBOL(vfs_readlink); EXPORT_SYMBOL(vfs_follow_link); +EXPORT_SYMBOL(vfs_follow_link_it); EXPORT_SYMBOL(page_readlink); EXPORT_SYMBOL(page_follow_link); EXPORT_SYMBOL(page_symlink_inode_operations); @@ -271,6 +272,12 @@ EXPORT_SYMBOL(lock_may_write); EXPORT_SYMBOL(dcache_readdir); +/* lustre */ +EXPORT_SYMBOL(panic_notifier_list); +EXPORT_SYMBOL(pagecache_lock); +EXPORT_SYMBOL(do_kern_mount); +EXPORT_SYMBOL(kmem_cache_validate); + /* for stackable file systems (lofs, wrapfs, cryptfs, etc.) */ EXPORT_SYMBOL(default_llseek); EXPORT_SYMBOL(dentry_open); --- lum-pristine/include/linux/dcache.h Thu Nov 22 14:46:18 2001 +++ lum/include/linux/dcache.h Mon Aug 12 00:02:29 2002 @@ -6,6 +6,34 @@ #include #include +#define IT_OPEN (1) +#define IT_CREAT (1<<1) +#define IT_MKDIR (1<<2) +#define IT_LINK (1<<3) +#define IT_LINK2 (1<<4) +#define IT_SYMLINK (1<<5) +#define IT_UNLINK (1<<6) +#define IT_RMDIR (1<<7) +#define IT_RENAME (1<<8) +#define IT_RENAME2 (1<<9) +#define IT_READDIR (1<<10) +#define IT_GETATTR (1<<11) +#define IT_SETATTR (1<<12) +#define IT_READLINK (1<<13) +#define IT_MKNOD (1<<14) +#define IT_LOOKUP (1<<15) + +struct lookup_intent { + int it_op; + int it_mode; + int it_disposition; + int it_status; + struct iattr *it_iattr; + __u64 it_lock_handle[2]; + int it_lock_mode; + void *it_data; +}; + /* * linux/include/linux/dcache.h * @@ -78,6 +106,7 @@ unsigned long d_time; /* used by d_revalidate */ struct dentry_operations *d_op; struct super_block * d_sb; /* The root of the dentry tree */ + struct lookup_intent *d_it; unsigned long d_vfs_flags; void * d_fsdata; /* fs-specific data */ unsigned char d_iname[DNAME_INLINE_LEN]; /* small names */ @@ -91,6 +119,8 @@ int (*d_delete)(struct dentry *); void (*d_release)(struct dentry *); void (*d_iput)(struct dentry *, struct inode *); + int (*d_revalidate2)(struct dentry *, int, struct lookup_intent *); + void (*d_intent_release)(struct dentry *, struct lookup_intent *); }; /* the dentry parameter passed to d_hash and d_compare is the parent --- lum-pristine/include/linux/fs.h Mon Aug 12 11:02:53 2002 +++ lum/include/linux/fs.h Mon Aug 12 11:48:38 2002 @@ -536,6 +536,7 @@ /* needed for tty driver, and maybe others */ void *private_data; + struct lookup_intent *f_intent; /* preallocated helper kiobuf to speedup O_DIRECT */ struct kiobuf *f_iobuf; @@ -779,7 +780,9 @@ extern int vfs_link(struct dentry *, struct inode *, struct dentry *); extern int vfs_rmdir(struct inode *, struct dentry *); extern int vfs_unlink(struct inode *, struct dentry *); -extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *); +int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + struct lookup_intent *it); /* * File types @@ -840,6 +843,7 @@ struct inode_operations { int (*create) (struct inode *,struct dentry *,int); struct dentry * (*lookup) (struct inode *,struct dentry *); + struct dentry * (*lookup2) (struct inode *,struct dentry *, struct lookup_intent *); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct inode *,struct dentry *,const char *); @@ -850,6 +854,8 @@ struct inode *, struct dentry *); int (*readlink) (struct dentry *, char *,int); int (*follow_link) (struct dentry *, struct nameidata *); + int (*follow_link2) (struct dentry *, struct nameidata *, + struct lookup_intent *it); void (*truncate) (struct inode *); int (*permission) (struct inode *, int); int (*revalidate) (struct dentry *); @@ -986,7 +990,7 @@ extern struct vfsmount *kern_mount(struct file_system_type *); extern int may_umount(struct vfsmount *); extern long do_mount(char *, char *, char *, unsigned long, void *); - +struct vfsmount *do_kern_mount(char *type, int flags, char *name, void *data); #define kern_umount mntput extern int vfs_statfs(struct super_block *, struct statfs *); @@ -1307,6 +1311,7 @@ extern loff_t default_llseek(struct file *file, loff_t offset, int origin); extern int FASTCALL(__user_walk(const char *, unsigned, struct nameidata *)); +extern int FASTCALL(__user_walk_it(const char *, unsigned, struct nameidata *, struct lookup_intent *it)); extern int FASTCALL(path_init(const char *, unsigned, struct nameidata *)); extern int FASTCALL(path_walk(const char *, struct nameidata *)); extern int FASTCALL(link_path_walk(const char *, struct nameidata *)); @@ -1317,6 +1322,8 @@ extern struct dentry * lookup_hash(struct qstr *, struct dentry *); #define user_path_walk(name,nd) __user_walk(name, LOOKUP_FOLLOW|LOOKUP_POSITIVE, nd) #define user_path_walk_link(name,nd) __user_walk(name, LOOKUP_POSITIVE, nd) +#define user_path_walk_it(name,nd,it) __user_walk_it(name, LOOKUP_FOLLOW|LOOKUP_POSITIVE, nd, it) +#define user_path_walk_link_it(name,nd,it) __user_walk_it(name, LOOKUP_POSITIVE, nd, it) extern void iput(struct inode *); extern void force_delete(struct inode *); @@ -1422,6 +1428,8 @@ extern int vfs_readlink(struct dentry *, char *, int, const char *); extern int vfs_follow_link(struct nameidata *, const char *); +extern int vfs_follow_link_it(struct nameidata *, const char *, + struct lookup_intent *it); extern int page_readlink(struct dentry *, char *, int); extern int page_follow_link(struct dentry *, struct nameidata *); extern struct inode_operations page_symlink_inode_operations; --- lum-pristine/fs/dcache.c Mon Feb 25 14:38:08 2002 +++ lum/fs/dcache.c Thu Aug 1 18:07:35 2002 @@ -617,6 +617,7 @@ dentry->d_op = NULL; dentry->d_fsdata = NULL; dentry->d_mounted = 0; + dentry->d_it = NULL; INIT_LIST_HEAD(&dentry->d_hash); INIT_LIST_HEAD(&dentry->d_lru); INIT_LIST_HEAD(&dentry->d_subdirs); --- lum-pristine/fs/nfsd/vfs.c Fri Dec 21 12:41:55 2001 +++ lum/fs/nfsd/vfs.c Thu Aug 1 18:07:35 2002 @@ -1285,7 +1285,7 @@ err = nfserr_perm; } else #endif - err = vfs_rename(fdir, odentry, tdir, ndentry); + err = vfs_rename(fdir, odentry, tdir, ndentry, NULL); if (!err && EX_ISSYNC(tfhp->fh_export)) { nfsd_sync_dir(tdentry); nfsd_sync_dir(fdentry); --- lum-pristine/fs/namei.c Mon Feb 25 14:38:09 2002 +++ lum/fs/namei.c Mon Aug 12 11:47:56 2002 @@ -94,6 +94,12 @@ * XEmacs seems to be relying on it... */ +void intent_release(struct dentry *de, struct lookup_intent *it) +{ + if (it && de->d_op && de->d_op->d_intent_release) + de->d_op->d_intent_release(de, it); +} + /* In order to reduce some races, while at the same time doing additional * checking and hopefully speeding things up, we copy filenames to the * kernel data space before using them.. @@ -260,10 +268,19 @@ * Internal lookup() using the new generic dcache. * SMP-safe */ -static struct dentry * cached_lookup(struct dentry * parent, struct qstr * name, int flags) +static struct dentry *cached_lookup(struct dentry *parent, struct qstr *name, + int flags, struct lookup_intent *it) { struct dentry * dentry = d_lookup(parent, name); + if (dentry && dentry->d_op && dentry->d_op->d_revalidate2) { + if (!dentry->d_op->d_revalidate2(dentry, flags, it) && + !d_invalidate(dentry)) { + dput(dentry); + dentry = NULL; + } + return dentry; + } else if (dentry && dentry->d_op && dentry->d_op->d_revalidate) { if (!dentry->d_op->d_revalidate(dentry, flags) && !d_invalidate(dentry)) { dput(dentry); @@ -281,7 +298,8 @@ * make sure that nobody added the entry to the dcache in the meantime.. * SMP-safe */ -static struct dentry * real_lookup(struct dentry * parent, struct qstr * name, int flags) +static struct dentry *real_lookup(struct dentry *parent, struct qstr *name, + int flags, struct lookup_intent *it) { struct dentry * result; struct inode *dir = parent->d_inode; @@ -300,6 +318,9 @@ result = ERR_PTR(-ENOMEM); if (dentry) { lock_kernel(); + if (dir->i_op->lookup2) + result = dir->i_op->lookup2(dir, dentry, it); + else result = dir->i_op->lookup(dir, dentry); unlock_kernel(); if (result) @@ -321,6 +342,12 @@ dput(result); result = ERR_PTR(-ENOENT); } + } else if (result->d_op && result->d_op->d_revalidate2) { + if (!result->d_op->d_revalidate2(result, flags, it) && + !d_invalidate(result)) { + dput(result); + result = ERR_PTR(-ENOENT); + } } return result; } @@ -334,7 +361,8 @@ * Without that kind of total limit, nasty chains of consecutive * symlinks can cause almost arbitrarily long lookups. */ -static inline int do_follow_link(struct dentry *dentry, struct nameidata *nd) +static inline int do_follow_link(struct dentry *dentry, struct nameidata *nd, + struct lookup_intent *it) { int err; if (current->link_count >= max_recursive_link) @@ -348,10 +376,14 @@ current->link_count++; current->total_link_count++; UPDATE_ATIME(dentry->d_inode); - err = dentry->d_inode->i_op->follow_link(dentry, nd); + if (dentry->d_inode->i_op->follow_link2) + err = dentry->d_inode->i_op->follow_link2(dentry, nd, it); + else + err = dentry->d_inode->i_op->follow_link(dentry, nd); current->link_count--; return err; loop: + intent_release(dentry, it); path_release(nd); return -ELOOP; } @@ -445,7 +472,8 @@ * * We expect 'base' to be positive and a directory. */ -int link_path_walk(const char * name, struct nameidata *nd) +int link_path_walk_it(const char *name, struct nameidata *nd, + struct lookup_intent *it) { struct dentry *dentry; struct inode *inode; @@ -518,9 +546,9 @@ break; } /* This does the actual lookups.. */ - dentry = cached_lookup(nd->dentry, &this, LOOKUP_CONTINUE); + dentry = cached_lookup(nd->dentry, &this, LOOKUP_CONTINUE, NULL); if (!dentry) { - dentry = real_lookup(nd->dentry, &this, LOOKUP_CONTINUE); + dentry = real_lookup(nd->dentry, &this, LOOKUP_CONTINUE, NULL); err = PTR_ERR(dentry); if (IS_ERR(dentry)) break; @@ -537,8 +570,8 @@ if (!inode->i_op) goto out_dput; - if (inode->i_op->follow_link) { - err = do_follow_link(dentry, nd); + if (inode->i_op->follow_link || inode->i_op->follow_link2) { + err = do_follow_link(dentry, nd, NULL); dput(dentry); if (err) goto return_err; @@ -554,7 +582,7 @@ nd->dentry = dentry; } err = -ENOTDIR; - if (!inode->i_op->lookup) + if (!inode->i_op->lookup && !inode->i_op->lookup2) break; continue; /* here ends the main loop */ @@ -581,9 +609,9 @@ if (err < 0) break; } - dentry = cached_lookup(nd->dentry, &this, 0); + dentry = cached_lookup(nd->dentry, &this, 0, it); if (!dentry) { - dentry = real_lookup(nd->dentry, &this, 0); + dentry = real_lookup(nd->dentry, &this, 0, it); err = PTR_ERR(dentry); if (IS_ERR(dentry)) break; @@ -591,9 +625,9 @@ while (d_mountpoint(dentry) && __follow_down(&nd->mnt, &dentry)) ; inode = dentry->d_inode; - if ((lookup_flags & LOOKUP_FOLLOW) - && inode && inode->i_op && inode->i_op->follow_link) { - err = do_follow_link(dentry, nd); + if ((lookup_flags & LOOKUP_FOLLOW) && inode && inode->i_op && + (inode->i_op->follow_link || inode->i_op->follow_link2)) { + err = do_follow_link(dentry, nd, it); dput(dentry); if (err) goto return_err; @@ -607,7 +635,8 @@ goto no_inode; if (lookup_flags & LOOKUP_DIRECTORY) { err = -ENOTDIR; - if (!inode->i_op || !inode->i_op->lookup) + if (!inode->i_op || + (!inode->i_op->lookup && !inode->i_op->lookup2)) break; } goto return_base; @@ -630,12 +660,23 @@ return err; } +int link_path_walk(const char * name, struct nameidata *nd) +{ + return link_path_walk_it(name, nd, NULL); +} + +int path_walk_it(const char * name, struct nameidata *nd, struct lookup_intent *it) +{ + current->total_link_count = 0; + return link_path_walk_it(name, nd, it); +} + int path_walk(const char * name, struct nameidata *nd) { current->total_link_count = 0; - return link_path_walk(name, nd); + return link_path_walk_it(name, nd, NULL); } /* SMP-safe */ /* returns 1 if everything is done */ static int __emul_lookup_dentry(const char *name, struct nameidata *nd) @@ -742,7 +786,8 @@ * needs parent already locked. Doesn't follow mounts. * SMP-safe. */ -struct dentry * lookup_hash(struct qstr *name, struct dentry * base) +struct dentry * lookup_hash_it(struct qstr *name, struct dentry * base, + struct lookup_intent *it) { struct dentry * dentry; struct inode *inode; @@ -765,13 +810,16 @@ goto out; } - dentry = cached_lookup(base, name, 0); + dentry = cached_lookup(base, name, 0, it); if (!dentry) { struct dentry *new = d_alloc(base, name); dentry = ERR_PTR(-ENOMEM); if (!new) goto out; lock_kernel(); + if (inode->i_op->lookup2) + dentry = inode->i_op->lookup2(inode, new, it); + else dentry = inode->i_op->lookup(inode, new); unlock_kernel(); if (!dentry) @@ -783,6 +831,12 @@ return dentry; } +struct dentry * lookup_hash(struct qstr *name, struct dentry * base) +{ + return lookup_hash_it(name, base, NULL); +} + + /* SMP-safe */ struct dentry * lookup_one_len(const char * name, struct dentry * base, int len) { @@ -804,7 +858,7 @@ } this.hash = end_name_hash(hash); - return lookup_hash(&this, base); + return lookup_hash_it(&this, base, NULL); access: return ERR_PTR(-EACCES); } @@ -836,6 +890,23 @@ return err; } +int __user_walk_it(const char *name, unsigned flags, struct nameidata *nd, + struct lookup_intent *it) +{ + char *tmp; + int err; + + tmp = getname(name); + err = PTR_ERR(tmp); + if (!IS_ERR(tmp)) { + err = 0; + if (path_init(tmp, flags, nd)) + err = path_walk_it(tmp, nd, it); + putname(tmp); + } + return err; +} + /* * It's inline, so penalty for filesystems that don't use sticky bit is * minimal. @@ -970,7 +1041,8 @@ * for symlinks (where the permissions are checked later). * SMP-safe */ -int open_namei(const char * pathname, int flag, int mode, struct nameidata *nd) +int open_namei_it(const char *pathname, int flag, int mode, + struct nameidata *nd, struct lookup_intent *it) { int acc_mode, error = 0; struct inode *inode; @@ -985,7 +1057,7 @@ */ if (!(flag & O_CREAT)) { if (path_init(pathname, lookup_flags(flag), nd)) - error = path_walk(pathname, nd); + error = path_walk_it(pathname, nd, it); if (error) return error; dentry = nd->dentry; @@ -994,6 +1067,10 @@ /* * Create - we need to know the parent. */ + if (it) { + it->it_mode = mode; + it->it_op |= IT_CREAT; + } if (path_init(pathname, LOOKUP_PARENT, nd)) error = path_walk(pathname, nd); if (error) @@ -1011,7 +1089,7 @@ dir = nd->dentry; down(&dir->d_inode->i_sem); - dentry = lookup_hash(&nd->last, nd->dentry); + dentry = lookup_hash_it(&nd->last, nd->dentry, it); do_last: error = PTR_ERR(dentry); @@ -1020,6 +1098,7 @@ goto exit; } + it->it_mode = mode; /* Negative dentry, just create the file */ if (!dentry->d_inode) { error = vfs_create(dir->d_inode, dentry, @@ -1053,7 +1134,8 @@ error = -ENOENT; if (!dentry->d_inode) goto exit_dput; - if (dentry->d_inode->i_op && dentry->d_inode->i_op->follow_link) + if (dentry->d_inode->i_op && (dentry->d_inode->i_op->follow_link || + dentry->d_inode->i_op->follow_link2)) goto do_link; dput(nd->dentry); @@ -1139,8 +1219,10 @@ return 0; exit_dput: + intent_release(dentry, it); dput(dentry); exit: + intent_release(nd->dentry, it); path_release(nd); return error; @@ -1160,7 +1242,12 @@ * are done. Procfs-like symlinks just set LAST_BIND. */ UPDATE_ATIME(dentry->d_inode); - error = dentry->d_inode->i_op->follow_link(dentry, nd); + if (dentry->d_inode->i_op->follow_link2) + error = dentry->d_inode->i_op->follow_link2(dentry, nd, it); + else + error = dentry->d_inode->i_op->follow_link(dentry, nd); + if (error) + intent_release(dentry, it); dput(dentry); if (error) return error; @@ -1181,13 +1265,20 @@ } dir = nd->dentry; down(&dir->d_inode->i_sem); - dentry = lookup_hash(&nd->last, nd->dentry); + dentry = lookup_hash_it(&nd->last, nd->dentry, it); putname(nd->last.name); goto do_last; } +int open_namei(const char *pathname, int flag, int mode, struct nameidata *nd) +{ + return open_namei_it(pathname, flag, mode, nd, NULL); +} + + /* SMP-safe */ -static struct dentry *lookup_create(struct nameidata *nd, int is_dir) +static struct dentry *lookup_create(struct nameidata *nd, int is_dir, + struct lookup_intent *it) { struct dentry *dentry; @@ -1195,7 +1286,7 @@ dentry = ERR_PTR(-EEXIST); if (nd->last_type != LAST_NORM) goto fail; - dentry = lookup_hash(&nd->last, nd->dentry); + dentry = lookup_hash_it(&nd->last, nd->dentry, it); if (IS_ERR(dentry)) goto fail; if (!is_dir && nd->last.name[nd->last.len] && !dentry->d_inode) @@ -1241,6 +1332,7 @@ char * tmp; struct dentry * dentry; struct nameidata nd; + struct lookup_intent it = { .it_op = IT_MKNOD, .it_mode = mode }; if (S_ISDIR(mode)) return -EPERM; @@ -1252,7 +1344,7 @@ error = path_walk(tmp, &nd); if (error) goto out; - dentry = lookup_create(&nd, 0); + dentry = lookup_create(&nd, 0, &it); error = PTR_ERR(dentry); mode &= ~current->fs->umask; @@ -1270,6 +1363,7 @@ default: error = -EINVAL; } + intent_release(dentry, &it); dput(dentry); } up(&nd.dentry->d_inode->i_sem); @@ -1310,6 +1404,7 @@ { int error = 0; char * tmp; + struct lookup_intent it = { .it_op = IT_MKDIR, .it_mode = mode }; tmp = getname(pathname); error = PTR_ERR(tmp); @@ -1321,11 +1416,12 @@ error = path_walk(tmp, &nd); if (error) goto out; - dentry = lookup_create(&nd, 1); + dentry = lookup_create(&nd, 1, &it); error = PTR_ERR(dentry); if (!IS_ERR(dentry)) { error = vfs_mkdir(nd.dentry->d_inode, dentry, mode & ~current->fs->umask); + intent_release(dentry, &it); dput(dentry); } up(&nd.dentry->d_inode->i_sem); @@ -1407,6 +1504,7 @@ char * name; struct dentry *dentry; struct nameidata nd; + struct lookup_intent it = { .it_op = IT_RMDIR }; name = getname(pathname); if(IS_ERR(name)) @@ -1429,10 +1527,11 @@ goto exit1; } down(&nd.dentry->d_inode->i_sem); - dentry = lookup_hash(&nd.last, nd.dentry); + dentry = lookup_hash_it(&nd.last, nd.dentry, &it); error = PTR_ERR(dentry); if (!IS_ERR(dentry)) { error = vfs_rmdir(nd.dentry->d_inode, dentry); + intent_release(dentry, &it); dput(dentry); } up(&nd.dentry->d_inode->i_sem); @@ -1476,6 +1576,7 @@ char * name; struct dentry *dentry; struct nameidata nd; + struct lookup_intent it = { .it_op = IT_UNLINK }; name = getname(pathname); if(IS_ERR(name)) @@ -1489,14 +1590,15 @@ if (nd.last_type != LAST_NORM) goto exit1; down(&nd.dentry->d_inode->i_sem); - dentry = lookup_hash(&nd.last, nd.dentry); + dentry = lookup_hash_it(&nd.last, nd.dentry, &it); error = PTR_ERR(dentry); if (!IS_ERR(dentry)) { /* Why not before? Because we want correct error value */ if (nd.last.name[nd.last.len]) goto slashes; error = vfs_unlink(nd.dentry->d_inode, dentry); exit2: + intent_release(dentry, &it); dput(dentry); } up(&nd.dentry->d_inode->i_sem); @@ -1543,6 +1646,7 @@ int error = 0; char * from; char * to; + struct lookup_intent it = { .it_op = IT_SYMLINK }; from = getname(oldname); if(IS_ERR(from)) @@ -1557,10 +1661,12 @@ error = path_walk(to, &nd); if (error) goto out; - dentry = lookup_create(&nd, 0); + it.it_data = from; + dentry = lookup_create(&nd, 0, &it); error = PTR_ERR(dentry); if (!IS_ERR(dentry)) { error = vfs_symlink(nd.dentry->d_inode, dentry, from); + intent_release(dentry, &it); dput(dentry); } up(&nd.dentry->d_inode->i_sem); @@ -1626,6 +1732,7 @@ int error; char * from; char * to; + struct lookup_intent it = { .it_op = IT_LINK }; from = getname(oldname); if(IS_ERR(from)) @@ -1639,7 +1745,7 @@ error = 0; if (path_init(from, LOOKUP_POSITIVE, &old_nd)) - error = path_walk(from, &old_nd); + error = path_walk_it(from, &old_nd, &it); if (error) goto exit; if (path_init(to, LOOKUP_PARENT, &nd)) @@ -1648,10 +1755,12 @@ error = -EXDEV; if (old_nd.mnt != nd.mnt) goto out_release; - new_dentry = lookup_create(&nd, 0); + it.it_op = IT_LINK2; + new_dentry = lookup_create(&nd, 0, &it); error = PTR_ERR(new_dentry); if (!IS_ERR(new_dentry)) { error = vfs_link(old_nd.dentry, nd.dentry->d_inode, new_dentry); + intent_release(new_dentry, &it); dput(new_dentry); } up(&nd.dentry->d_inode->i_sem); @@ -1694,7 +1803,8 @@ * locking]. */ int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry) + struct inode *new_dir, struct dentry *new_dentry, + struct lookup_intent *it) { int error; struct inode *target; @@ -1754,6 +1864,7 @@ error = -EBUSY; else error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry); + intent_release(new_dentry, it); if (target) { if (!error) target->i_flags |= S_DEAD; @@ -1775,7 +1887,8 @@ } int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry) + struct inode *new_dir, struct dentry *new_dentry, + struct lookup_intent *it) { int error; @@ -1806,6 +1919,7 @@ error = -EBUSY; else error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry); + intent_release(new_dentry, it); double_up(&old_dir->i_zombie, &new_dir->i_zombie); if (error) return error; @@ -1817,13 +1932,14 @@ } int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry) + struct inode *new_dir, struct dentry *new_dentry, + struct lookup_intent *it) { int error; if (S_ISDIR(old_dentry->d_inode->i_mode)) - error = vfs_rename_dir(old_dir,old_dentry,new_dir,new_dentry); + error = vfs_rename_dir(old_dir,old_dentry,new_dir,new_dentry,it); else - error = vfs_rename_other(old_dir,old_dentry,new_dir,new_dentry); + error = vfs_rename_other(old_dir,old_dentry,new_dir,new_dentry,it); if (!error) { if (old_dir == new_dir) inode_dir_notify(old_dir, DN_RENAME); @@ -1840,6 +1956,7 @@ int error = 0; struct dentry * old_dir, * new_dir; struct dentry * old_dentry, *new_dentry; + struct lookup_intent it = { .it_op = IT_RENAME }; struct nameidata oldnd, newnd; if (path_init(oldname, LOOKUP_PARENT, &oldnd)) @@ -1868,7 +1985,7 @@ double_lock(new_dir, old_dir); - old_dentry = lookup_hash(&oldnd.last, old_dir); + old_dentry = lookup_hash_it(&oldnd.last, old_dir, &it); error = PTR_ERR(old_dentry); if (IS_ERR(old_dentry)) goto exit3; @@ -1884,18 +2003,21 @@ if (newnd.last.name[newnd.last.len]) goto exit4; } - new_dentry = lookup_hash(&newnd.last, new_dir); + it.it_op = IT_RENAME2; + new_dentry = lookup_hash_it(&newnd.last, new_dir, &it); error = PTR_ERR(new_dentry); if (IS_ERR(new_dentry)) goto exit4; lock_kernel(); error = vfs_rename(old_dir->d_inode, old_dentry, - new_dir->d_inode, new_dentry); + new_dir->d_inode, new_dentry, &it); unlock_kernel(); + intent_release(new_dentry, &it); dput(new_dentry); exit4: + intent_release(old_dentry, &it); dput(old_dentry); exit3: double_up(&new_dir->d_inode->i_sem, &old_dir->d_inode->i_sem); @@ -1965,7 +2094,8 @@ } static inline int -__vfs_follow_link(struct nameidata *nd, const char *link) +__vfs_follow_link(struct nameidata *nd, const char *link, + struct lookup_intent *it) { int res = 0; char *name; @@ -1978,7 +2108,7 @@ /* weird __emul_prefix() stuff did it */ goto out; } - res = link_path_walk(link, nd); + res = link_path_walk_it(link, nd, it); out: if (current->link_count || res || nd->last_type!=LAST_NORM) return res; @@ -2000,7 +2130,13 @@ int vfs_follow_link(struct nameidata *nd, const char *link) { - return __vfs_follow_link(nd, link); + return __vfs_follow_link(nd, link, NULL); +} + +int vfs_follow_link_it(struct nameidata *nd, const char *link, + struct lookup_intent *it) +{ + return __vfs_follow_link(nd, link, it); } /* get the link contents into pagecache */ @@ -2042,7 +2178,7 @@ { struct page *page = NULL; char *s = page_getlink(dentry, &page); - int res = __vfs_follow_link(nd, s); + int res = __vfs_follow_link(nd, s, NULL); if (page) { kunmap(page); page_cache_release(page); --- lum-pristine/fs/open.c Fri Oct 12 16:48:42 2001 +++ lum/fs/open.c Sun Aug 11 15:26:29 2002 @@ -19,6 +19,9 @@ #include #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m)) +extern int path_walk_it(const char *name, struct nameidata *nd, + struct lookup_intent *it); +extern void intent_release(struct dentry *de, struct lookup_intent *it); int vfs_statfs(struct super_block *sb, struct statfs *buf) { @@ -94,12 +97,13 @@ struct nameidata nd; struct inode * inode; int error; + struct lookup_intent it = { .it_op = IT_SETATTR }; error = -EINVAL; if (length < 0) /* sorry, but loff_t says... */ goto out; - error = user_path_walk(path, &nd); + error = user_path_walk_it(path, &nd, &it); if (error) goto out; inode = nd.dentry->d_inode; @@ -144,6 +149,7 @@ put_write_access(inode); dput_and_out: + intent_release(nd.dentry, &it); path_release(&nd); out: return error; @@ -235,8 +241,9 @@ struct nameidata nd; struct inode * inode; struct iattr newattrs; + struct lookup_intent it = { .it_op = IT_SETATTR }; - error = user_path_walk(filename, &nd); + error = user_path_walk_it(filename, &nd, &it); if (error) goto out; inode = nd.dentry->d_inode; @@ -262,6 +270,7 @@ } error = notify_change(nd.dentry, &newattrs); dput_and_out: + intent_release(nd.dentry, &it); path_release(&nd); out: return error; @@ -279,8 +288,9 @@ struct nameidata nd; struct inode * inode; struct iattr newattrs; + struct lookup_intent it = { .it_op = IT_SETATTR }; - error = user_path_walk(filename, &nd); + error = user_path_walk_it(filename, &nd, &it); if (error) goto out; @@ -306,6 +317,7 @@ } error = notify_change(nd.dentry, &newattrs); dput_and_out: + intent_release(nd.dentry, &it); path_release(&nd); out: return error; @@ -322,6 +334,7 @@ int old_fsuid, old_fsgid; kernel_cap_t old_cap; int res; + struct lookup_intent it = { .it_op = IT_GETATTR }; if (mode & ~S_IRWXO) /* where's F_OK, X_OK, W_OK, R_OK? */ return -EINVAL; @@ -339,13 +352,14 @@ else current->cap_effective = current->cap_permitted; - res = user_path_walk(filename, &nd); + res = user_path_walk_it(filename, &nd, &it); if (!res) { res = permission(nd.dentry->d_inode, mode); /* SuS v2 requires we report a read only fs too */ if(!res && (mode & S_IWOTH) && IS_RDONLY(nd.dentry->d_inode) && !special_file(nd.dentry->d_inode->i_mode)) res = -EROFS; + intent_release(nd.dentry, &it); path_release(&nd); } @@ -361,6 +375,7 @@ int error; struct nameidata nd; char *name; + struct lookup_intent it = { .it_op = IT_GETATTR }; name = getname(filename); error = PTR_ERR(name); @@ -369,7 +384,7 @@ error = 0; if (path_init(name,LOOKUP_POSITIVE|LOOKUP_FOLLOW|LOOKUP_DIRECTORY,&nd)) - error = path_walk(name, &nd); + error = path_walk_it(name, &nd, &it); putname(name); if (error) goto out; @@ -381,6 +397,7 @@ set_fs_pwd(current->fs, nd.mnt, nd.dentry); dput_and_out: + intent_release(nd.dentry, &it); path_release(&nd); out: return error; @@ -421,6 +438,7 @@ int error; struct nameidata nd; char *name; + struct lookup_intent it = { .it_op = IT_GETATTR }; name = getname(filename); error = PTR_ERR(name); @@ -429,7 +447,7 @@ path_init(name, LOOKUP_POSITIVE | LOOKUP_FOLLOW | LOOKUP_DIRECTORY | LOOKUP_NOALT, &nd); - error = path_walk(name, &nd); + error = path_walk_it(name, &nd, &it); putname(name); if (error) goto out; @@ -446,6 +465,7 @@ set_fs_altroot(); error = 0; dput_and_out: + intent_release(nd.dentry, &it); path_release(&nd); out: return error; @@ -490,8 +510,9 @@ struct inode * inode; int error; struct iattr newattrs; + struct lookup_intent it = { .it_op = IT_SETATTR }; - error = user_path_walk(filename, &nd); + error = user_path_walk_it(filename, &nd, &it); if (error) goto out; inode = nd.dentry->d_inode; @@ -511,6 +532,7 @@ error = notify_change(nd.dentry, &newattrs); dput_and_out: + intent_release(nd.dentry, &it); path_release(&nd); out: return error; @@ -580,10 +602,12 @@ { struct nameidata nd; int error; + struct lookup_intent it = { .it_op = IT_SETATTR }; - error = user_path_walk(filename, &nd); + error = user_path_walk_it(filename, &nd, &it); if (!error) { error = chown_common(nd.dentry, user, group); + intent_release(nd.dentry, &it); path_release(&nd); } return error; @@ -593,10 +618,12 @@ { struct nameidata nd; int error; + struct lookup_intent it = { .it_op = IT_SETATTR }; - error = user_path_walk_link(filename, &nd); + error = user_path_walk_link_it(filename, &nd, &it); if (!error) { error = chown_common(nd.dentry, user, group); + intent_release(nd.dentry, &it); path_release(&nd); } return error; @@ -630,10 +658,16 @@ * for the internal routines (ie open_namei()/follow_link() etc). 00 is * used by symlinks. */ +extern int open_namei_it(const char *filename, int namei_flags, int mode, + struct nameidata *nd, struct lookup_intent *it); +struct file *dentry_open_it(struct dentry *dentry, struct vfsmount *mnt, + int flags, struct lookup_intent *it); + struct file *filp_open(const char * filename, int flags, int mode) { int namei_flags, error; struct nameidata nd; + struct lookup_intent it = { .it_op = IT_OPEN }; namei_flags = flags; if ((namei_flags+1) & O_ACCMODE) @@ -641,14 +675,15 @@ if (namei_flags & O_TRUNC) namei_flags |= 2; - error = open_namei(filename, namei_flags, mode, &nd); - if (!error) - return dentry_open(nd.dentry, nd.mnt, flags); + error = open_namei_it(filename, namei_flags, mode, &nd, &it); + if (error) + return ERR_PTR(error); - return ERR_PTR(error); + return dentry_open_it(nd.dentry, nd.mnt, flags, &it); } -struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags) +struct file *dentry_open_it(struct dentry *dentry, struct vfsmount *mnt, + int flags, struct lookup_intent *it) { struct file * f; struct inode *inode; @@ -691,6 +726,7 @@ } f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC); + intent_release(dentry, it); return f; cleanup_all: @@ -705,11 +741,17 @@ cleanup_file: put_filp(f); cleanup_dentry: + intent_release(dentry, it); dput(dentry); mntput(mnt); return ERR_PTR(error); } +struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags) +{ + return dentry_open_it(dentry, mnt, flags, NULL); +} + /* * Find an empty file descriptor entry, and mark it busy. */ --- lum-pristine/fs/stat.c Thu Sep 13 19:04:43 2001 +++ lum/fs/stat.c Mon Aug 12 00:04:39 2002 @@ -13,6 +13,7 @@ #include +extern void intent_release(struct dentry *de, struct lookup_intent *it); /* * Revalidate the inode. This is required for proper NFS attribute caching. */ @@ -135,13 +135,15 @@ asmlinkage long sys_stat(char * filename, struct __old_kernel_stat * statbuf) { struct nameidata nd; + struct lookup_intent it = { .it_op = IT_GETATTR }; int error; - error = user_path_walk(filename, &nd); + error = user_path_walk_it(filename, &nd, &it); if (!error) { error = do_revalidate(nd.dentry); if (!error) error = cp_old_stat(nd.dentry->d_inode, statbuf); + intent_release(nd.dentry, &it); path_release(&nd); } return error; @@ -151,13 +153,15 @@ asmlinkage long sys_newstat(char * filename, struct stat * statbuf) { struct nameidata nd; + struct lookup_intent it = { .it_op = IT_GETATTR }; int error; - error = user_path_walk(filename, &nd); + error = user_path_walk_it(filename, &nd, &it); if (!error) { error = do_revalidate(nd.dentry); if (!error) error = cp_new_stat(nd.dentry->d_inode, statbuf); + intent_release(nd.dentry, &it); path_release(&nd); } return error; @@ -172,13 +176,15 @@ asmlinkage long sys_lstat(char * filename, struct __old_kernel_stat * statbuf) { struct nameidata nd; + struct lookup_intent it = { .it_op = IT_GETATTR }; int error; - error = user_path_walk_link(filename, &nd); + error = user_path_walk_link_it(filename, &nd, &it); if (!error) { error = do_revalidate(nd.dentry); if (!error) error = cp_old_stat(nd.dentry->d_inode, statbuf); + intent_release(nd.dentry, &it); path_release(&nd); } return error; @@ -189,13 +195,15 @@ asmlinkage long sys_newlstat(char * filename, struct stat * statbuf) { struct nameidata nd; + struct lookup_intent it = { .it_op = IT_GETATTR }; int error; - error = user_path_walk_link(filename, &nd); + error = user_path_walk_link_it(filename, &nd, &it); if (!error) { error = do_revalidate(nd.dentry); if (!error) error = cp_new_stat(nd.dentry->d_inode, statbuf); + intent_release(nd.dentry, &it); path_release(&nd); } return error; @@ -247,20 +255,21 @@ { struct nameidata nd; int error; + struct lookup_intent it = { .it_op = IT_READLINK }; if (bufsiz <= 0) return -EINVAL; - error = user_path_walk_link(path, &nd); + error = user_path_walk_link_it(path, &nd, &it); if (!error) { struct inode * inode = nd.dentry->d_inode; - error = -EINVAL; if (inode->i_op && inode->i_op->readlink && !(error = do_revalidate(nd.dentry))) { UPDATE_ATIME(inode); error = inode->i_op->readlink(nd.dentry, buf, bufsiz); } + intent_release(nd.dentry, &it); path_release(&nd); } return error; @@ -333,12 +342,14 @@ { struct nameidata nd; int error; + struct lookup_intent it = { .it_op = IT_GETATTR }; - error = user_path_walk(filename, &nd); + error = user_path_walk_it(filename, &nd, &it); if (!error) { error = do_revalidate(nd.dentry); if (!error) error = cp_new_stat64(nd.dentry->d_inode, statbuf); + intent_release(nd.dentry, &it); path_release(&nd); } return error; @@ -348,12 +359,14 @@ { struct nameidata nd; int error; + struct lookup_intent it = { .it_op = IT_GETATTR }; - error = user_path_walk_link(filename, &nd); + error = user_path_walk_link_it(filename, &nd, &it); if (!error) { error = do_revalidate(nd.dentry); if (!error) error = cp_new_stat64(nd.dentry->d_inode, statbuf); + intent_release(nd.dentry, &it); path_release(&nd); } return error; --- lum-pristine/mm/slab.c Fri Dec 21 12:42:05 2001 +++ lum/mm/slab.c Thu Aug 1 18:07:35 2002 @@ -1187,6 +1187,59 @@ * Called with the cache-lock held. */ +extern struct page *check_get_page(unsigned long kaddr); +struct page *page_mem_map(struct page *page); +static int kmem_check_cache_obj (kmem_cache_t * cachep, + slab_t *slabp, void * objp) +{ + int i; + unsigned int objnr; + +#if DEBUG + if (cachep->flags & SLAB_RED_ZONE) { + objp -= BYTES_PER_WORD; + if ( *(unsigned long *)objp != RED_MAGIC2) + /* Either write before start, or a double free. */ + return 0; + if (*(unsigned long *)(objp+cachep->objsize - + BYTES_PER_WORD) != RED_MAGIC2) + /* Either write past end, or a double free. */ + return 0; + } +#endif + + objnr = (objp-slabp->s_mem)/cachep->objsize; + if (objnr >= cachep->num) + return 0; + if (objp != slabp->s_mem + objnr*cachep->objsize) + return 0; + + /* Check slab's freelist to see if this obj is there. */ + for (i = slabp->free; i != BUFCTL_END; i = slab_bufctl(slabp)[i]) { + if (i == objnr) + return 0; + } + return 1; +} + + +int kmem_cache_validate(kmem_cache_t *cachep, void *objp) +{ + struct page *page = check_get_page((unsigned long)objp); + + if (!VALID_PAGE(page)) + return 0; + + if (!PageSlab(page)) + return 0; + + /* XXX check for freed slab objects ? */ + if (!kmem_check_cache_obj(cachep, GET_PAGE_SLAB(page), objp)) + return 0; + + return (cachep == GET_PAGE_CACHE(page)); +} + #if DEBUG static int kmem_extra_free_checks (kmem_cache_t * cachep, slab_t *slabp, void * objp)