Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel…

…/git/viro/vfs

Pull vfs pile 1 from Al Viro:
 "This is _not_ all; in particular, Miklos' and Jan's stuff is not there
  yet."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (64 commits)
  ext4: initialization of ext4_li_mtx needs to be done earlier
  debugfs-related mode_t whack-a-mole
  hfsplus: add an ioctl to bless files
  hfsplus: change finder_info to u32
  hfsplus: initialise userflags
  qnx4: new helper - try_extent()
  qnx4: get rid of qnx4_bread/qnx4_getblk
  take removal of PF_FORKNOEXEC to flush_old_exec()
  trim includes in inode.c
  um: uml_dup_mmap() relies on ->mmap_sem being held, but activate_mm() doesn't hold it
  um: embed ->stub_pages[] into mmu_context
  gadgetfs: list_for_each_safe() misuse
  ocfs2: fix leaks on failure exits in module_init
  ecryptfs: make register_filesystem() the last potential failure exit
  ntfs: forgets to unregister sysctls on register_filesystem() failure
  logfs: missing cleanup on register_filesystem() failure
  jfs: mising cleanup on register_filesystem() failure
  make configfs_pin_fs() return root dentry on success
  configfs: configfs_create_dir() has parent dentry in dentry->d_parent
  configfs: sanitize configfs_create()
  ...

Documentation/filesystems/debugfs.txt

@@ -136,7 +136,7 @@ file.
 	void __iomem *base;
     };
 
-    struct dentry *debugfs_create_regset32(const char *name, mode_t mode,
+    struct dentry *debugfs_create_regset32(const char *name, umode_t mode,
 				     struct dentry *parent,
 				     struct debugfs_regset32 *regset);
 

Documentation/filesystems/porting

@@ -429,3 +429,9 @@ filemap_write_and_wait_range() so that all dirty pages are synced out properly.
 You must also keep in mind that ->fsync() is not called with i_mutex held
 anymore, so if you require i_mutex locking you must make sure to take it and
 release it yourself.
+
+--
+[mandatory]
+	d_alloc_root() is gone, along with a lot of bugs caused by code
+misusing it.  Replacement: d_make_root(inode).  The difference is,
+d_make_root() drops the reference to inode if dentry allocation fails.  

Documentation/filesystems/qnx6.txt

@@ -0,0 +1,174 @@
+The QNX6 Filesystem
+===================
+
+The qnx6fs is used by newer QNX operating system versions. (e.g. Neutrino)
+It got introduced in QNX 6.4.0 and is used default since 6.4.1.
+
+Option
+======
+
+mmi_fs		Mount filesystem as used for example by Audi MMI 3G system
+
+Specification
+=============
+
+qnx6fs shares many properties with traditional Unix filesystems. It has the
+concepts of blocks, inodes and directories.
+On QNX it is possible to create little endian and big endian qnx6 filesystems.
+This feature makes it possible to create and use a different endianness fs
+for the target (QNX is used on quite a range of embedded systems) plattform
+running on a different endianess.
+The Linux driver handles endianness transparently. (LE and BE)
+
+Blocks
+------
+
+The space in the device or file is split up into blocks. These are a fixed
+size of 512, 1024, 2048 or 4096, which is decided when the filesystem is
+created.
+Blockpointers are 32bit, so the maximum space that can be adressed is
+2^32 * 4096 bytes or 16TB
+
+The superblocks
+---------------
+
+The superblock contains all global information about the filesystem.
+Each qnx6fs got two superblocks, each one having a 64bit serial number.
+That serial number is used to identify the "active" superblock.
+In write mode with reach new snapshot (after each synchronous write), the
+serial of the new master superblock is increased (old superblock serial + 1)
+
+So basically the snapshot functionality is realized by an atomic final
+update of the serial number. Before updating that serial, all modifications
+are done by copying all modified blocks during that specific write request
+(or period) and building up a new (stable) filesystem structure under the
+inactive superblock.
+
+Each superblock holds a set of root inodes for the different filesystem
+parts. (Inode, Bitmap and Longfilenames)
+Each of these root nodes holds information like total size of the stored
+data and the adressing levels in that specific tree.
+If the level value is 0, up to 16 direct blocks can be adressed by each
+node.
+Level 1 adds an additional indirect adressing level where each indirect
+adressing block holds up to blocksize / 4 bytes pointers to data blocks.
+Level 2 adds an additional indirect adressig block level (so, already up
+to 16 * 256 * 256 = 1048576 blocks that can be adressed by such a tree)a
+
+Unused block pointers are always set to ~0 - regardless of root node,
+indirect adressing blocks or inodes.
+Data leaves are always on the lowest level. So no data is stored on upper
+tree levels.
+
+The first Superblock is located at 0x2000. (0x2000 is the bootblock size)
+The Audi MMI 3G first superblock directly starts at byte 0.
+Second superblock position can either be calculated from the superblock
+information (total number of filesystem blocks) or by taking the highest
+device address, zeroing the last 3 bytes and then substracting 0x1000 from
+that address.
+
+0x1000 is the size reserved for each superblock - regardless of the
+blocksize of the filesystem.
+
+Inodes
+------
+
+Each object in the filesystem is represented by an inode. (index node)
+The inode structure contains pointers to the filesystem blocks which contain
+the data held in the object and all of the metadata about an object except
+its longname. (filenames longer than 27 characters)
+The metadata about an object includes the permissions, owner, group, flags,
+size, number of blocks used, access time, change time and modification time.
+
+Object mode field is POSIX format. (which makes things easier)
+
+There are also pointers to the first 16 blocks, if the object data can be
+adressed with 16 direct blocks.
+For more than 16 blocks an indirect adressing in form of another tree is
+used. (scheme is the same as the one used for the superblock root nodes)
+
+The filesize is stored 64bit. Inode counting starts with 1. (whilst long
+filename inodes start with 0)
+
+Directories
+-----------
+
+A directory is a filesystem object and has an inode just like a file.
+It is a specially formatted file containing records which associate each
+name with an inode number.
+'.' inode number points to the directory inode
+'..' inode number points to the parent directory inode
+Eeach filename record additionally got a filename length field.
+
+One special case are long filenames or subdirectory names.
+These got set a filename length field of 0xff in the corresponding directory
+record plus the longfile inode number also stored in that record.
+With that longfilename inode number, the longfilename tree can be walked
+starting with the superblock longfilename root node pointers.
+
+Special files
+-------------
+
+Symbolic links are also filesystem objects with inodes. They got a specific
+bit in the inode mode field identifying them as symbolic link.
+The directory entry file inode pointer points to the target file inode.
+
+Hard links got an inode, a directory entry, but a specific mode bit set,
+no block pointers and the directory file record pointing to the target file
+inode.
+
+Character and block special devices do not exist in QNX as those files
+are handled by the QNX kernel/drivers and created in /dev independant of the
+underlaying filesystem.
+
+Long filenames
+--------------
+
+Long filenames are stored in a seperate adressing tree. The staring point
+is the longfilename root node in the active superblock.
+Each data block (tree leaves) holds one long filename. That filename is
+limited to 510 bytes. The first two starting bytes are used as length field
+for the actual filename.
+If that structure shall fit for all allowed blocksizes, it is clear why there
+is a limit of 510 bytes for the actual filename stored.
+
+Bitmap
+------
+
+The qnx6fs filesystem allocation bitmap is stored in a tree under bitmap
+root node in the superblock and each bit in the bitmap represents one
+filesystem block.
+The first block is block 0, which starts 0x1000 after superblock start.
+So for a normal qnx6fs 0x3000 (bootblock + superblock) is the physical
+address at which block 0 is located.
+
+Bits at the end of the last bitmap block are set to 1, if the device is
+smaller than addressing space in the bitmap.
+
+Bitmap system area
+------------------
+
+The bitmap itself is devided into three parts.
+First the system area, that is split into two halfs.
+Then userspace.
+
+The requirement for a static, fixed preallocated system area comes from how
+qnx6fs deals with writes.
+Each superblock got it's own half of the system area. So superblock #1
+always uses blocks from the lower half whilst superblock #2 just writes to
+blocks represented by the upper half bitmap system area bits.
+
+Bitmap blocks, Inode blocks and indirect addressing blocks for those two
+tree structures are treated as system blocks.
+
+The rational behind that is that a write request can work on a new snapshot
+(system area of the inactive - resp. lower serial numbered superblock) while
+at the same time there is still a complete stable filesystem structer in the
+other half of the system area.
+
+When finished with writing (a sync write is completed, the maximum sync leap
+time or a filesystem sync is requested), serial of the previously inactive
+superblock atomically is increased and the fs switches over to that - then
+stable declared - superblock.
+
+For all data outside the system area, blocks are just copied while writing.

Documentation/ioctl/ioctl-number.txt

@@ -218,6 +218,7 @@ Code  Seq#(hex)	Include File		Comments
 'h'	00-7F				conflict! Charon filesystem
 					<mailto:[email protected]>
 'h'	00-1F	linux/hpet.h		conflict!
+'h'	80-8F	fs/hfsplus/ioctl.c
 'i'	00-3F	linux/i2o-dev.h		conflict!
 'i'	0B-1F	linux/ipmi.h		conflict!
 'i'	80-8F	linux/i8k.h

arch/alpha/kernel/binfmt_loader.c

@@ -46,6 +46,7 @@ static struct linux_binfmt loader_format = {
 
 static int __init init_loader_binfmt(void)
 {
-	return insert_binfmt(&loader_format);
+	insert_binfmt(&loader_format);
+	return 0;
 }
 arch_initcall(init_loader_binfmt);

arch/powerpc/platforms/cell/spufs/inode.c

@@ -757,9 +757,9 @@ spufs_create_root(struct super_block *sb, void *data)
 		goto out_iput;
 
 	ret = -ENOMEM;
-	sb->s_root = d_alloc_root(inode);
+	sb->s_root = d_make_root(inode);
 	if (!sb->s_root)
-		goto out_iput;
+		goto out;
 
 	return 0;
 out_iput:
@@ -828,19 +828,19 @@ static int __init spufs_init(void)
 	ret = spu_sched_init();
 	if (ret)
 		goto out_cache;
-	ret = register_filesystem(&spufs_type);
+	ret = register_spu_syscalls(&spufs_calls);
 	if (ret)
 		goto out_sched;
-	ret = register_spu_syscalls(&spufs_calls);
+	ret = register_filesystem(&spufs_type);
 	if (ret)
-		goto out_fs;
+		goto out_syscalls;
 
 	spufs_init_isolated_loader();
 
 	return 0;
 
-out_fs:
-	unregister_filesystem(&spufs_type);
+out_syscalls:
+	unregister_spu_syscalls(&spufs_calls);
 out_sched:
 	spu_sched_exit();
 out_cache:

arch/s390/hypfs/inode.c

@@ -293,11 +293,9 @@ static int hypfs_fill_super(struct super_block *sb, void *data, int silent)
 		return -ENOMEM;
 	root_inode->i_op = &simple_dir_inode_operations;
 	root_inode->i_fop = &simple_dir_operations;
-	sb->s_root = root_dentry = d_alloc_root(root_inode);
-	if (!root_dentry) {
-		iput(root_inode);
+	sb->s_root = root_dentry = d_make_root(root_inode);
+	if (!root_dentry)
 		return -ENOMEM;
-	}
 	if (MACHINE_IS_VM)
 		rc = hypfs_vm_create_files(sb, root_dentry);
 	else

arch/um/include/asm/mmu.h

@@ -12,7 +12,7 @@
 typedef struct mm_context {
 	struct mm_id id;
 	struct uml_arch_mm_context arch;
-	struct page **stub_pages;
+	struct page *stub_pages[2];
 } mm_context_t;
 
 extern void __switch_mm(struct mm_id * mm_idp);

arch/um/include/asm/mmu_context.h

@@ -9,7 +9,7 @@
 #include <linux/sched.h>
 #include <asm/mmu.h>
 
-extern void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm);
+extern void uml_setup_stubs(struct mm_struct *mm);
 extern void arch_exit_mmap(struct mm_struct *mm);
 
 #define deactivate_mm(tsk,mm)	do { } while (0)
@@ -23,7 +23,9 @@ static inline void activate_mm(struct mm_struct *old, struct mm_struct *new)
 	 * when the new ->mm is used for the first time.
 	 */
 	__switch_mm(&new->context.id);
-	arch_dup_mmap(old, new);
+	down_write(&new->mmap_sem);
+	uml_setup_stubs(new);
+	up_write(&new->mmap_sem);
 }
 
 static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, 
@@ -39,6 +41,11 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	}
 }
 
+static inline void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
+{
+	uml_setup_stubs(mm);
+}
+
 static inline void enter_lazy_tlb(struct mm_struct *mm, 
 				  struct task_struct *tsk)
 {

arch/um/kernel/skas/mmu.c

@@ -92,8 +92,6 @@ int init_new_context(struct task_struct *task, struct mm_struct *mm)
 		goto out_free;
 	}
 
-	to_mm->stub_pages = NULL;
-
 	return 0;
 
  out_free:
@@ -103,7 +101,7 @@ int init_new_context(struct task_struct *task, struct mm_struct *mm)
 	return ret;
 }
 
-void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
+void uml_setup_stubs(struct mm_struct *mm)
 {
 	struct page **pages;
 	int err, ret;
@@ -120,29 +118,20 @@ void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
 	if (ret)
 		goto out;
 
-	pages = kmalloc(2 * sizeof(struct page *), GFP_KERNEL);
-	if (pages == NULL) {
-		printk(KERN_ERR "arch_dup_mmap failed to allocate 2 page "
-		       "pointers\n");
-		goto out;
-	}
-
-	pages[0] = virt_to_page(&__syscall_stub_start);
-	pages[1] = virt_to_page(mm->context.id.stack);
-	mm->context.stub_pages = pages;
+	mm->context.stub_pages[0] = virt_to_page(&__syscall_stub_start);
+	mm->context.stub_pages[1] = virt_to_page(mm->context.id.stack);
 
 	/* dup_mmap already holds mmap_sem */
 	err = install_special_mapping(mm, STUB_START, STUB_END - STUB_START,
 				      VM_READ | VM_MAYREAD | VM_EXEC |
-				      VM_MAYEXEC | VM_DONTCOPY, pages);
+				      VM_MAYEXEC | VM_DONTCOPY,
+				      mm->context.stub_pages);
 	if (err) {
 		printk(KERN_ERR "install_special_mapping returned %d\n", err);
-		goto out_free;
+		goto out;
 	}
 	return;
 
-out_free:
-	kfree(pages);
 out:
 	force_sigsegv(SIGSEGV, current);
 }
@@ -151,8 +140,6 @@ void arch_exit_mmap(struct mm_struct *mm)
 {
 	pte_t *pte;
 
-	if (mm->context.stub_pages != NULL)
-		kfree(mm->context.stub_pages);
 	pte = virt_to_pte(mm, STUB_CODE);
 	if (pte != NULL)
 		pte_clear(mm, STUB_CODE, pte);

arch/x86/ia32/ia32_aout.c

@@ -323,7 +323,6 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 	}
 
 	install_exec_creds(bprm);
-	current->flags &= ~PF_FORKNOEXEC;
 
 	if (N_MAGIC(ex) == OMAGIC) {
 		unsigned long text_addr, map_size;
@@ -519,7 +518,8 @@ static int load_aout_library(struct file *file)
 
 static int __init init_aout_binfmt(void)
 {
-	return register_binfmt(&aout_format);
+	register_binfmt(&aout_format);
+	return 0;
 }
 
 static void __exit exit_aout_binfmt(void)