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

Pull vfs changes from Al Viro.
 "A lot of misc stuff.  The obvious groups:
   * Miklos' atomic_open series; kills the damn abuse of
     ->d_revalidate() by NFS, which was the major stumbling block for
     all work in that area.
   * ripping security_file_mmap() and dealing with deadlocks in the
     area; sanitizing the neighborhood of vm_mmap()/vm_munmap() in
     general.
   * ->encode_fh() switched to saner API; insane fake dentry in
     mm/cleancache.c gone.
   * assorted annotations in fs (endianness, __user)
   * parts of Artem's ->s_dirty work (jff2 and reiserfs parts)
   * ->update_time() work from Josef.
   * other bits and pieces all over the place.

  Normally it would've been in two or three pull requests, but
  signal.git stuff had eaten a lot of time during this cycle ;-/"

Fix up trivial conflicts in Documentation/filesystems/vfs.txt (the
'truncate_range' inode method was removed by the VM changes, the VFS
update adds an 'update_time()' method), and in fs/btrfs/ulist.[ch] (due
to sparse fix added twice, with other changes nearby).

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (95 commits)
  nfs: don't open in ->d_revalidate
  vfs: retry last component if opening stale dentry
  vfs: nameidata_to_filp(): don't throw away file on error
  vfs: nameidata_to_filp(): inline __dentry_open()
  vfs: do_dentry_open(): don't put filp
  vfs: split __dentry_open()
  vfs: do_last() common post lookup
  vfs: do_last(): add audit_inode before open
  vfs: do_last(): only return EISDIR for O_CREAT
  vfs: do_last(): check LOOKUP_DIRECTORY
  vfs: do_last(): make ENOENT exit RCU safe
  vfs: make follow_link check RCU safe
  vfs: do_last(): use inode variable
  vfs: do_last(): inline walk_component()
  vfs: do_last(): make exit RCU safe
  vfs: split do_lookup()
  Btrfs: move over to use ->update_time
  fs: introduce inode operation ->update_time
  reiserfs: get rid of resierfs_sync_super
  reiserfs: mark the superblock as dirty a bit later
  ...

9 files changed, 58 insertions, 176 deletions

diff --git a/mm/cleancache.c b/mm/cleancache.c
index 5646c74..32e6f41 100644
--- a/mm/cleancache.c
+++ b/mm/cleancache.c
@@ -80,7 +80,7 @@ EXPORT_SYMBOL(__cleancache_init_shared_fs);
 static int cleancache_get_key(struct inode *inode,
 			      struct cleancache_filekey *key)
 {
-	int (*fhfn)(struct dentry *, __u32 *fh, int *, int);
+	int (*fhfn)(struct inode *, __u32 *fh, int *, struct inode *);
 	int len = 0, maxlen = CLEANCACHE_KEY_MAX;
 	struct super_block *sb = inode->i_sb;
 
@@ -88,9 +88,7 @@ static int cleancache_get_key(struct inode *inode,
 	if (sb->s_export_op != NULL) {
 		fhfn = sb->s_export_op->encode_fh;
 		if  (fhfn) {
-			struct dentry d;
-			d.d_inode = inode;
-			len = (*fhfn)(&d, &key->u.fh[0], &maxlen, 0);
+			len = (*fhfn)(inode, &key->u.fh[0], &maxlen, NULL);
 			if (len <= 0 || len == 255)
 				return -1;
 			if (maxlen > CLEANCACHE_KEY_MAX)
diff --git a/mm/filemap.c b/mm/filemap.c
index 64b48f9..a4a5260 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1899,71 +1899,6 @@ struct page *read_cache_page(struct address_space *mapping,
 }
 EXPORT_SYMBOL(read_cache_page);
 
-/*
- * The logic we want is
- *
- *	if suid or (sgid and xgrp)
- *		remove privs
- */
-int should_remove_suid(struct dentry *dentry)
-{
-	umode_t mode = dentry->d_inode->i_mode;
-	int kill = 0;
-
-	/* suid always must be killed */
-	if (unlikely(mode & S_ISUID))
-		kill = ATTR_KILL_SUID;
-
-	/*
-	 * sgid without any exec bits is just a mandatory locking mark; leave
-	 * it alone.  If some exec bits are set, it's a real sgid; kill it.
-	 */
-	if (unlikely((mode & S_ISGID) && (mode & S_IXGRP)))
-		kill |= ATTR_KILL_SGID;
-
-	if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode)))
-		return kill;
-
-	return 0;
-}
-EXPORT_SYMBOL(should_remove_suid);
-
-static int __remove_suid(struct dentry *dentry, int kill)
-{
-	struct iattr newattrs;
-
-	newattrs.ia_valid = ATTR_FORCE | kill;
-	return notify_change(dentry, &newattrs);
-}
-
-int file_remove_suid(struct file *file)
-{
-	struct dentry *dentry = file->f_path.dentry;
-	struct inode *inode = dentry->d_inode;
-	int killsuid;
-	int killpriv;
-	int error = 0;
-
-	/* Fast path for nothing security related */
-	if (IS_NOSEC(inode))
-		return 0;
-
-	killsuid = should_remove_suid(dentry);
-	killpriv = security_inode_need_killpriv(dentry);
-
-	if (killpriv < 0)
-		return killpriv;
-	if (killpriv)
-		error = security_inode_killpriv(dentry);
-	if (!error && killsuid)
-		error = __remove_suid(dentry, killsuid);
-	if (!error && (inode->i_sb->s_flags & MS_NOSEC))
-		inode->i_flags |= S_NOSEC;
-
-	return error;
-}
-EXPORT_SYMBOL(file_remove_suid);
-
 static size_t __iovec_copy_from_user_inatomic(char *vaddr,
 			const struct iovec *iov, size_t base, size_t bytes)
 {
@@ -2489,7 +2424,9 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	if (err)
 		goto out;
 
-	file_update_time(file);
+	err = file_update_time(file);
+	if (err)
+		goto out;
 
 	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
 	if (unlikely(file->f_flags & O_DIRECT)) {
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index a4eb311..213ca1f 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -426,7 +426,9 @@ xip_file_write(struct file *filp, const char __user *buf, size_t len,
 	if (ret)
 		goto out_backing;
 
-	file_update_time(filp);
+	ret = file_update_time(filp);
+	if (ret)
+		goto out_backing;
 
 	ret = __xip_file_write (filp, buf, count, pos, ppos);
 
diff --git a/mm/internal.h b/mm/internal.h
index 4194ab9..5cbb781 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -350,3 +350,7 @@ extern u64 hwpoison_filter_flags_mask;
 extern u64 hwpoison_filter_flags_value;
 extern u64 hwpoison_filter_memcg;
 extern u32 hwpoison_filter_enable;
+
+extern unsigned long vm_mmap_pgoff(struct file *, unsigned long,
+        unsigned long, unsigned long,
+        unsigned long, unsigned long);
diff --git a/mm/mmap.c b/mm/mmap.c
index 4a9c2a3..3edfcdf 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -971,15 +971,13 @@ static inline unsigned long round_hint_to_min(unsigned long hint)
  * The caller must hold down_write(&current->mm->mmap_sem).
  */
 
-static unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
+unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 			unsigned long len, unsigned long prot,
 			unsigned long flags, unsigned long pgoff)
 {
 	struct mm_struct * mm = current->mm;
 	struct inode *inode;
 	vm_flags_t vm_flags;
-	int error;
-	unsigned long reqprot = prot;
 
 	/*
 	 * Does the application expect PROT_READ to imply PROT_EXEC?
@@ -1101,39 +1099,9 @@ static unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 		}
 	}
 
-	error = security_file_mmap(file, reqprot, prot, flags, addr, 0);
-	if (error)
-		return error;
-
 	return mmap_region(file, addr, len, flags, vm_flags, pgoff);
 }
 
-unsigned long do_mmap(struct file *file, unsigned long addr,
-	unsigned long len, unsigned long prot,
-	unsigned long flag, unsigned long offset)
-{
-	if (unlikely(offset + PAGE_ALIGN(len) < offset))
-		return -EINVAL;
-	if (unlikely(offset & ~PAGE_MASK))
-		return -EINVAL;
-	return do_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
-}
-EXPORT_SYMBOL(do_mmap);
-
-unsigned long vm_mmap(struct file *file, unsigned long addr,
-	unsigned long len, unsigned long prot,
-	unsigned long flag, unsigned long offset)
-{
-	unsigned long ret;
-	struct mm_struct *mm = current->mm;
-
-	down_write(&mm->mmap_sem);
-	ret = do_mmap(file, addr, len, prot, flag, offset);
-	up_write(&mm->mmap_sem);
-	return ret;
-}
-EXPORT_SYMBOL(vm_mmap);
-
 SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
 		unsigned long, prot, unsigned long, flags,
 		unsigned long, fd, unsigned long, pgoff)
@@ -1165,10 +1133,7 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
 
 	flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
 
-	down_write(&current->mm->mmap_sem);
-	retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
-	up_write(&current->mm->mmap_sem);
-
+	retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff);
 	if (file)
 		fput(file);
 out:
@@ -1629,7 +1594,9 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 	if (addr & ~PAGE_MASK)
 		return -EINVAL;
 
-	return arch_rebalance_pgtables(addr, len);
+	addr = arch_rebalance_pgtables(addr, len);
+	error = security_mmap_addr(addr);
+	return error ? error : addr;
 }
 
 EXPORT_SYMBOL(get_unmapped_area);
@@ -1819,7 +1786,7 @@ int expand_downwards(struct vm_area_struct *vma,
 		return -ENOMEM;
 
 	address &= PAGE_MASK;
-	error = security_file_mmap(NULL, 0, 0, 0, address, 1);
+	error = security_mmap_addr(address);
 	if (error)
 		return error;
 
@@ -2159,7 +2126,6 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 
 	return 0;
 }
-EXPORT_SYMBOL(do_munmap);
 
 int vm_munmap(unsigned long start, size_t len)
 {
@@ -2207,10 +2173,6 @@ static unsigned long do_brk(unsigned long addr, unsigned long len)
 	if (!len)
 		return addr;
 
-	error = security_file_mmap(NULL, 0, 0, 0, addr, 1);
-	if (error)
-		return error;
-
 	flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
 
 	error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED);
@@ -2563,10 +2525,6 @@ int install_special_mapping(struct mm_struct *mm,
 	vma->vm_ops = &special_mapping_vmops;
 	vma->vm_private_data = pages;
 
-	ret = security_file_mmap(NULL, 0, 0, 0, vma->vm_start, 1);
-	if (ret)
-		goto out;
-
 	ret = insert_vm_struct(mm, vma);
 	if (ret)
 		goto out;
diff --git a/mm/mremap.c b/mm/mremap.c
index db8d983..21fed20 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -371,10 +371,6 @@ static unsigned long mremap_to(unsigned long addr,
 	if ((addr <= new_addr) && (addr+old_len) > new_addr)
 		goto out;
 
-	ret = security_file_mmap(NULL, 0, 0, 0, new_addr, 1);
-	if (ret)
-		goto out;
-
 	ret = do_munmap(mm, new_addr, new_len);
 	if (ret)
 		goto out;
@@ -432,15 +428,17 @@ static int vma_expandable(struct vm_area_struct *vma, unsigned long delta)
  * MREMAP_FIXED option added 5-Dec-1999 by Benjamin LaHaise
  * This option implies MREMAP_MAYMOVE.
  */
-unsigned long do_mremap(unsigned long addr,
-	unsigned long old_len, unsigned long new_len,
-	unsigned long flags, unsigned long new_addr)
+SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
+		unsigned long, new_len, unsigned long, flags,
+		unsigned long, new_addr)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	unsigned long ret = -EINVAL;
 	unsigned long charged = 0;
 
+	down_write(&current->mm->mmap_sem);
+
 	if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
 		goto out;
 
@@ -530,25 +528,11 @@ unsigned long do_mremap(unsigned long addr,
 			goto out;
 		}
 
-		ret = security_file_mmap(NULL, 0, 0, 0, new_addr, 1);
-		if (ret)
-			goto out;
 		ret = move_vma(vma, addr, old_len, new_len, new_addr);
 	}
 out:
 	if (ret & ~PAGE_MASK)
 		vm_unacct_memory(charged);
-	return ret;
-}
-
-SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
-		unsigned long, new_len, unsigned long, flags,
-		unsigned long, new_addr)
-{
-	unsigned long ret;
-
-	down_write(&current->mm->mmap_sem);
-	ret = do_mremap(addr, old_len, new_len, flags, new_addr);
 	up_write(&current->mm->mmap_sem);
 	return ret;
 }
diff --git a/mm/nommu.c b/mm/nommu.c
index bb8f4f0..c4acfbc 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -889,7 +889,6 @@ static int validate_mmap_request(struct file *file,
 				 unsigned long *_capabilities)
 {
 	unsigned long capabilities, rlen;
-	unsigned long reqprot = prot;
 	int ret;
 
 	/* do the simple checks first */
@@ -1047,7 +1046,7 @@ static int validate_mmap_request(struct file *file,
 	}
 
 	/* allow the security API to have its say */
-	ret = security_file_mmap(file, reqprot, prot, flags, addr, 0);
+	ret = security_mmap_addr(addr);
 	if (ret < 0)
 		return ret;
 
@@ -1233,7 +1232,7 @@ enomem:
 /*
  * handle mapping creation for uClinux
  */
-static unsigned long do_mmap_pgoff(struct file *file,
+unsigned long do_mmap_pgoff(struct file *file,
 			    unsigned long addr,
 			    unsigned long len,
 			    unsigned long prot,
@@ -1471,32 +1470,6 @@ error_getting_region:
 	return -ENOMEM;
 }
 
-unsigned long do_mmap(struct file *file, unsigned long addr,
-	unsigned long len, unsigned long prot,
-	unsigned long flag, unsigned long offset)
-{
-	if (unlikely(offset + PAGE_ALIGN(len) < offset))
-		return -EINVAL;
-	if (unlikely(offset & ~PAGE_MASK))
-		return -EINVAL;
-	return do_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
-}
-EXPORT_SYMBOL(do_mmap);
-
-unsigned long vm_mmap(struct file *file, unsigned long addr,
-	unsigned long len, unsigned long prot,
-	unsigned long flag, unsigned long offset)
-{
-	unsigned long ret;
-	struct mm_struct *mm = current->mm;
-
-	down_write(&mm->mmap_sem);
-	ret = do_mmap(file, addr, len, prot, flag, offset);
-	up_write(&mm->mmap_sem);
-	return ret;
-}
-EXPORT_SYMBOL(vm_mmap);
-
 SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
 		unsigned long, prot, unsigned long, flags,
 		unsigned long, fd, unsigned long, pgoff)
@@ -1513,9 +1486,7 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
 
 	flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
 
-	down_write(&current->mm->mmap_sem);
-	retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
-	up_write(&current->mm->mmap_sem);
+	ret = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff);
 
 	if (file)
 		fput(file);
diff --git a/mm/shmem.c b/mm/shmem.c
index d576b84..585bd220 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2439,11 +2439,9 @@ static struct dentry *shmem_fh_to_dentry(struct super_block *sb,
 	return dentry;
 }
 
-static int shmem_encode_fh(struct dentry *dentry, __u32 *fh, int *len,
-				int connectable)
+static int shmem_encode_fh(struct inode *inode, __u32 *fh, int *len,
+				struct inode *parent)
 {
-	struct inode *inode = dentry->d_inode;
-
 	if (*len < 3) {
 		*len = 3;
 		return 255;
diff --git a/mm/util.c b/mm/util.c
index ae962b3..8c7265a 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -4,6 +4,7 @@
 #include <linux/export.h>
 #include <linux/err.h>
 #include <linux/sched.h>
+#include <linux/security.h>
 #include <asm/uaccess.h>
 
 #include "internal.h"
@@ -341,6 +342,35 @@ int __attribute__((weak)) get_user_pages_fast(unsigned long start,
 }
 EXPORT_SYMBOL_GPL(get_user_pages_fast);
 
+unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
+	unsigned long len, unsigned long prot,
+	unsigned long flag, unsigned long pgoff)
+{
+	unsigned long ret;
+	struct mm_struct *mm = current->mm;
+
+	ret = security_mmap_file(file, prot, flag);
+	if (!ret) {
+		down_write(&mm->mmap_sem);
+		ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff);
+		up_write(&mm->mmap_sem);
+	}
+	return ret;
+}
+
+unsigned long vm_mmap(struct file *file, unsigned long addr,
+	unsigned long len, unsigned long prot,
+	unsigned long flag, unsigned long offset)
+{
+	if (unlikely(offset + PAGE_ALIGN(len) < offset))
+		return -EINVAL;
+	if (unlikely(offset & ~PAGE_MASK))
+		return -EINVAL;
+
+	return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
+}
+EXPORT_SYMBOL(vm_mmap);
+
 /* Tracepoints definitions. */
 EXPORT_TRACEPOINT_SYMBOL(kmalloc);
 EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);