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

Pull vfs updates from Al Viro:
 "All kinds of stuff this time around; some more notable parts:

   - RCU'd vfsmounts handling
   - new primitives for coredump handling
   - files_lock is gone
   - Bruce's delegations handling series
   - exportfs fixes

  plus misc stuff all over the place"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (101 commits)
  ecryptfs: ->f_op is never NULL
  locks: break delegations on any attribute modification
  locks: break delegations on link
  locks: break delegations on rename
  locks: helper functions for delegation breaking
  locks: break delegations on unlink
  namei: minor vfs_unlink cleanup
  locks: implement delegations
  locks: introduce new FL_DELEG lock flag
  vfs: take i_mutex on renamed file
  vfs: rename I_MUTEX_QUOTA now that it's not used for quotas
  vfs: don't use PARENT/CHILD lock classes for non-directories
  vfs: pull ext4's double-i_mutex-locking into common code
  exportfs: fix quadratic behavior in filehandle lookup
  exportfs: better variable name
  exportfs: move most of reconnect_path to helper function
  exportfs: eliminate unused "noprogress" counter
  exportfs: stop retrying once we race with rename/remove
  exportfs: clear DISCONNECTED on all parents sooner
  exportfs: more detailed comment for path_reconnect
  ...

Documentation/filesystems/directory-locking

@@ -2,6 +2,10 @@
 kinds of locks - per-inode (->i_mutex) and per-filesystem
 (->s_vfs_rename_mutex).
 
+	When taking the i_mutex on multiple non-directory objects, we
+always acquire the locks in order by increasing address.  We'll call
+that "inode pointer" order in the following.
+
 	For our purposes all operations fall in 5 classes:
 
 1) read access.  Locking rules: caller locks directory we are accessing.
@@ -12,8 +16,9 @@ kinds of locks - per-inode (->i_mutex) and per-filesystem
 locks victim and calls the method.
 
 4) rename() that is _not_ cross-directory.  Locking rules: caller locks
-the parent, finds source and target, if target already exists - locks it
-and then calls the method.
+the parent and finds source and target.  If target already exists, lock
+it.  If source is a non-directory, lock it.  If that means we need to
+lock both, lock them in inode pointer order.
 
 5) link creation.  Locking rules:
 	* lock parent
@@ -30,7 +35,9 @@ rules:
 		fail with -ENOTEMPTY
 	* if new parent is equal to or is a descendent of source
 		fail with -ELOOP
-	* if target exists - lock it.
+	* If target exists, lock it.  If source is a non-directory, lock
+	  it.  In case that means we need to lock both source and target,
+	  do so in inode pointer order.
 	* call the method.
 
 
@@ -56,9 +63,11 @@ objects - A < B iff A is an ancestor of B.
     renames will be blocked on filesystem lock and we don't start changing
     the order until we had acquired all locks).
 
-(3) any operation holds at most one lock on non-directory object and
-    that lock is acquired after all other locks.  (Proof: see descriptions
-    of operations).
+(3) locks on non-directory objects are acquired only after locks on
+    directory objects, and are acquired in inode pointer order.
+    (Proof: all operations but renames take lock on at most one
+    non-directory object, except renames, which take locks on source and
+    target in inode pointer order in the case they are not directories.)
 
 	Now consider the minimal deadlock.  Each process is blocked on
 attempt to acquire some lock and already holds at least one lock.  Let's
@@ -66,9 +75,13 @@ consider the set of contended locks.  First of all, filesystem lock is
 not contended, since any process blocked on it is not holding any locks.
 Thus all processes are blocked on ->i_mutex.
 
-	Non-directory objects are not contended due to (3).  Thus link
-creation can't be a part of deadlock - it can't be blocked on source
-and it means that it doesn't hold any locks.
+	By (3), any process holding a non-directory lock can only be
+waiting on another non-directory lock with a larger address.  Therefore
+the process holding the "largest" such lock can always make progress, and
+non-directory objects are not included in the set of contended locks.
+
+	Thus link creation can't be a part of deadlock - it can't be
+blocked on source and it means that it doesn't hold any locks.
 
 	Any contended object is either held by cross-directory rename or
 has a child that is also contended.  Indeed, suppose that it is held by

Documentation/filesystems/porting

@@ -455,3 +455,11 @@ in your dentry operations instead.
 	vfs_follow_link has been removed.  Filesystems must use nd_set_link
 	from ->follow_link for normal symlinks, or nd_jump_link for magic
 	/proc/<pid> style links.
+--
+[mandatory]
+	iget5_locked()/ilookup5()/ilookup5_nowait() test() callback used to be
+	called with both ->i_lock and inode_hash_lock held; the former is *not*
+	taken anymore, so verify that your callbacks do not rely on it (none
+	of the in-tree instances did).  inode_hash_lock is still held,
+	of course, so they are still serialized wrt removal from inode hash,
+	as well as wrt set() callback of iget5_locked().

arch/arm64/kernel/signal32.c

@@ -122,7 +122,7 @@ static inline int get_sigset_t(sigset_t *set,
 	return 0;
 }
 
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
+int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 {
 	int err;
 

arch/ia64/kernel/elfcore.c

@@ -11,8 +11,7 @@ Elf64_Half elf_core_extra_phdrs(void)
 	return GATE_EHDR->e_phnum;
 }
 
-int elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size,
-			       unsigned long limit)
+int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
 {
 	const struct elf_phdr *const gate_phdrs =
 		(const struct elf_phdr *) (GATE_ADDR + GATE_EHDR->e_phoff);
@@ -35,15 +34,13 @@ int elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size,
 			phdr.p_offset += ofs;
 		}
 		phdr.p_paddr = 0; /* match other core phdrs */
-		*size += sizeof(phdr);
-		if (*size > limit || !dump_write(file, &phdr, sizeof(phdr)))
+		if (!dump_emit(cprm, &phdr, sizeof(phdr)))
 			return 0;
 	}
 	return 1;
 }
 
-int elf_core_write_extra_data(struct file *file, size_t *size,
-			      unsigned long limit)
+int elf_core_write_extra_data(struct coredump_params *cprm)
 {
 	const struct elf_phdr *const gate_phdrs =
 		(const struct elf_phdr *) (GATE_ADDR + GATE_EHDR->e_phoff);
@@ -54,8 +51,7 @@ int elf_core_write_extra_data(struct file *file, size_t *size,
 			void *addr = (void *)gate_phdrs[i].p_vaddr;
 			size_t memsz = PAGE_ALIGN(gate_phdrs[i].p_memsz);
 
-			*size += memsz;
-			if (*size > limit || !dump_write(file, addr, memsz))
+			if (!dump_emit(cprm, addr, memsz))
 				return 0;
 			break;
 		}

arch/ia64/kernel/signal.c

@@ -105,7 +105,7 @@ restore_sigcontext (struct sigcontext __user *sc, struct sigscratch *scr)
 }
 
 int
-copy_siginfo_to_user (siginfo_t __user *to, siginfo_t *from)
+copy_siginfo_to_user (siginfo_t __user *to, const siginfo_t *from)
 {
 	if (!access_ok(VERIFY_WRITE, to, sizeof(siginfo_t)))
 		return -EFAULT;

arch/mips/kernel/signal32.c

@@ -314,7 +314,7 @@ SYSCALL_DEFINE3(32_sigaction, long, sig, const struct compat_sigaction __user *,
 	return ret;
 }
 
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
+int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 {
 	int err;
 

arch/parisc/kernel/signal32.c

@@ -319,7 +319,7 @@ copy_siginfo_from_user32 (siginfo_t *to, compat_siginfo_t __user *from)
 }
 
 int
-copy_siginfo_to_user32 (compat_siginfo_t __user *to, siginfo_t *from)
+copy_siginfo_to_user32 (compat_siginfo_t __user *to, const siginfo_t *from)
 {
 	compat_uptr_t addr;
 	compat_int_t val;

arch/parisc/kernel/signal32.h

@@ -34,7 +34,7 @@ struct compat_ucontext {
 
 /* ELF32 signal handling */
 
-int copy_siginfo_to_user32 (compat_siginfo_t __user *to, siginfo_t *from);
+int copy_siginfo_to_user32 (compat_siginfo_t __user *to, const siginfo_t *from);
 int copy_siginfo_from_user32 (siginfo_t *to, compat_siginfo_t __user *from);
 
 /* In a deft move of uber-hackery, we decide to carry the top half of all

arch/powerpc/include/asm/spu.h

@@ -235,6 +235,7 @@ extern long spu_sys_callback(struct spu_syscall_block *s);
 
 /* syscalls implemented in spufs */
 struct file;
+struct coredump_params;
 struct spufs_calls {
 	long (*create_thread)(const char __user *name,
 					unsigned int flags, umode_t mode,
@@ -242,7 +243,7 @@ struct spufs_calls {
 	long (*spu_run)(struct file *filp, __u32 __user *unpc,
 						__u32 __user *ustatus);
 	int (*coredump_extra_notes_size)(void);
-	int (*coredump_extra_notes_write)(struct file *file, loff_t *foffset);
+	int (*coredump_extra_notes_write)(struct coredump_params *cprm);
 	void (*notify_spus_active)(void);
 	struct module *owner;
 };

arch/powerpc/kernel/signal_32.c

@@ -893,7 +893,7 @@ static long restore_tm_user_regs(struct pt_regs *regs,
 #endif
 
 #ifdef CONFIG_PPC64
-int copy_siginfo_to_user32(struct compat_siginfo __user *d, siginfo_t *s)
+int copy_siginfo_to_user32(struct compat_siginfo __user *d, const siginfo_t *s)
 {
 	int err;
 

arch/powerpc/platforms/cell/spu_syscalls.c

@@ -25,6 +25,7 @@
 #include <linux/module.h>
 #include <linux/syscalls.h>
 #include <linux/rcupdate.h>
+#include <linux/binfmts.h>
 
 #include <asm/spu.h>
 
@@ -126,7 +127,7 @@ int elf_coredump_extra_notes_size(void)
 	return ret;
 }
 
-int elf_coredump_extra_notes_write(struct file *file, loff_t *foffset)
+int elf_coredump_extra_notes_write(struct coredump_params *cprm)
 {
 	struct spufs_calls *calls;
 	int ret;
@@ -135,7 +136,7 @@ int elf_coredump_extra_notes_write(struct file *file, loff_t *foffset)
 	if (!calls)
 		return 0;
 
-	ret = calls->coredump_extra_notes_write(file, foffset);
+	ret = calls->coredump_extra_notes_write(cprm);
 
 	spufs_calls_put(calls);
 

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

@@ -27,6 +27,8 @@
 #include <linux/gfp.h>
 #include <linux/list.h>
 #include <linux/syscalls.h>
+#include <linux/coredump.h>
+#include <linux/binfmts.h>
 
 #include <asm/uaccess.h>
 
@@ -48,44 +50,6 @@ static ssize_t do_coredump_read(int num, struct spu_context *ctx, void *buffer,
 	return ++ret; /* count trailing NULL */
 }
 
-/*
- * These are the only things you should do on a core-file: use only these
- * functions to write out all the necessary info.
- */
-static int spufs_dump_write(struct file *file, const void *addr, int nr, loff_t *foffset)
-{
-	unsigned long limit = rlimit(RLIMIT_CORE);
-	ssize_t written;
-
-	if (*foffset + nr > limit)
-		return -EIO;
-
-	written = file->f_op->write(file, addr, nr, &file->f_pos);
-	*foffset += written;
-
-	if (written != nr)
-		return -EIO;
-
-	return 0;
-}
-
-static int spufs_dump_align(struct file *file, char *buf, loff_t new_off,
-			    loff_t *foffset)
-{
-	int rc, size;
-
-	size = min((loff_t)PAGE_SIZE, new_off - *foffset);
-	memset(buf, 0, size);
-
-	rc = 0;
-	while (rc == 0 && new_off > *foffset) {
-		size = min((loff_t)PAGE_SIZE, new_off - *foffset);
-		rc = spufs_dump_write(file, buf, size, foffset);
-	}
-
-	return rc;
-}
-
 static int spufs_ctx_note_size(struct spu_context *ctx, int dfd)
 {
 	int i, sz, total = 0;
@@ -165,10 +129,10 @@ int spufs_coredump_extra_notes_size(void)
 }
 
 static int spufs_arch_write_note(struct spu_context *ctx, int i,
-				  struct file *file, int dfd, loff_t *foffset)
+				  struct coredump_params *cprm, int dfd)
 {
 	loff_t pos = 0;
-	int sz, rc, nread, total = 0;
+	int sz, rc, total = 0;
 	const int bufsz = PAGE_SIZE;
 	char *name;
 	char fullname[80], *buf;
@@ -186,42 +150,39 @@ static int spufs_arch_write_note(struct spu_context *ctx, int i,
 	en.n_descsz = sz;
 	en.n_type = NT_SPU;
 
-	rc = spufs_dump_write(file, &en, sizeof(en), foffset);
-	if (rc)
-		goto out;
+	if (!dump_emit(cprm, &en, sizeof(en)))
+		goto Eio;
 
-	rc = spufs_dump_write(file, fullname, en.n_namesz, foffset);
-	if (rc)
-		goto out;
+	if (!dump_emit(cprm, fullname, en.n_namesz))
+		goto Eio;
 
-	rc = spufs_dump_align(file, buf, roundup(*foffset, 4), foffset);
-	if (rc)
-		goto out;
+	if (!dump_align(cprm, 4))
+		goto Eio;
 
 	do {
-		nread = do_coredump_read(i, ctx, buf, bufsz, &pos);
-		if (nread > 0) {
-			rc = spufs_dump_write(file, buf, nread, foffset);
-			if (rc)
-				goto out;
-			total += nread;
+		rc = do_coredump_read(i, ctx, buf, bufsz, &pos);
+		if (rc > 0) {
+			if (!dump_emit(cprm, buf, rc))
+				goto Eio;
+			total += rc;
 		}
-	} while (nread == bufsz && total < sz);
+	} while (rc == bufsz && total < sz);
 
-	if (nread < 0) {
-		rc = nread;
+	if (rc < 0)
 		goto out;
-	}
-
-	rc = spufs_dump_align(file, buf, roundup(*foffset - total + sz, 4),
-			      foffset);
 
+	if (!dump_skip(cprm,
+		       roundup(cprm->written - total + sz, 4) - cprm->written))
+		goto Eio;
 out:
 	free_page((unsigned long)buf);
 	return rc;
+Eio:
+	free_page((unsigned long)buf);
+	return -EIO;
 }
 
-int spufs_coredump_extra_notes_write(struct file *file, loff_t *foffset)
+int spufs_coredump_extra_notes_write(struct coredump_params *cprm)
 {
 	struct spu_context *ctx;
 	int fd, j, rc;
@@ -233,7 +194,7 @@ int spufs_coredump_extra_notes_write(struct file *file, loff_t *foffset)
 			return rc;
 
 		for (j = 0; spufs_coredump_read[j].name != NULL; j++) {
-			rc = spufs_arch_write_note(ctx, j, file, fd, foffset);
+			rc = spufs_arch_write_note(ctx, j, cprm, fd);
 			if (rc) {
 				spu_release_saved(ctx);
 				return rc;

arch/powerpc/platforms/cell/spufs/spufs.h

@@ -247,12 +247,13 @@ extern const struct spufs_tree_descr spufs_dir_debug_contents[];
 
 /* system call implementation */
 extern struct spufs_calls spufs_calls;
+struct coredump_params;
 long spufs_run_spu(struct spu_context *ctx, u32 *npc, u32 *status);
 long spufs_create(struct path *nd, struct dentry *dentry, unsigned int flags,
 			umode_t mode, struct file *filp);
 /* ELF coredump callbacks for writing SPU ELF notes */
 extern int spufs_coredump_extra_notes_size(void);
-extern int spufs_coredump_extra_notes_write(struct file *file, loff_t *foffset);
+extern int spufs_coredump_extra_notes_write(struct coredump_params *cprm);
 
 extern const struct file_operations spufs_context_fops;
 

arch/s390/kernel/compat_signal.c

@@ -49,7 +49,7 @@ typedef struct
 	__u32 gprs_high[NUM_GPRS];
 } rt_sigframe32;
 
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
+int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 {
 	int err;
 

arch/sparc/kernel/signal32.c

@@ -68,7 +68,7 @@ struct rt_signal_frame32 {
 	/* __siginfo_rwin_t * */u32 rwin_save;
 } __attribute__((aligned(8)));
 
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
+int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 {
 	int err;
 

arch/tile/kernel/compat_signal.c

@@ -49,7 +49,7 @@ struct compat_rt_sigframe {
 	struct compat_ucontext uc;
 };
 
-int copy_siginfo_to_user32(struct compat_siginfo __user *to, siginfo_t *from)
+int copy_siginfo_to_user32(struct compat_siginfo __user *to, const siginfo_t *from)
 {
 	int err;
 

arch/x86/ia32/ia32_aout.c

@@ -25,6 +25,7 @@
 #include <linux/personality.h>
 #include <linux/init.h>
 #include <linux/jiffies.h>
+#include <linux/perf_event.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgalloc.h>
@@ -33,14 +34,18 @@
 #include <asm/ia32.h>
 
 #undef WARN_OLD
-#undef CORE_DUMP /* definitely broken */
 
 static int load_aout_binary(struct linux_binprm *);
 static int load_aout_library(struct file *);
 
-#ifdef CORE_DUMP
-static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file,
-			  unsigned long limit);
+#ifdef CONFIG_COREDUMP
+static int aout_core_dump(struct coredump_params *);
+
+static unsigned long get_dr(int n)
+{
+	struct perf_event *bp = current->thread.ptrace_bps[n];
+	return bp ? bp->hw.info.address : 0;
+}
 
 /*
  * fill in the user structure for a core dump..
@@ -48,6 +53,7 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file,
 static void dump_thread32(struct pt_regs *regs, struct user32 *dump)
 {
 	u32 fs, gs;
+	memset(dump, 0, sizeof(*dump));
 
 /* changed the size calculations - should hopefully work better. lbt */
 	dump->magic = CMAGIC;
@@ -57,15 +63,12 @@ static void dump_thread32(struct pt_regs *regs, struct user32 *dump)
 	dump->u_dsize = ((unsigned long)
 			 (current->mm->brk + (PAGE_SIZE-1))) >> PAGE_SHIFT;
 	dump->u_dsize -= dump->u_tsize;
-	dump->u_ssize = 0;
-	dump->u_debugreg[0] = current->thread.debugreg0;
-	dump->u_debugreg[1] = current->thread.debugreg1;
-	dump->u_debugreg[2] = current->thread.debugreg2;
-	dump->u_debugreg[3] = current->thread.debugreg3;
-	dump->u_debugreg[4] = 0;
-	dump->u_debugreg[5] = 0;
+	dump->u_debugreg[0] = get_dr(0);
+	dump->u_debugreg[1] = get_dr(1);
+	dump->u_debugreg[2] = get_dr(2);
+	dump->u_debugreg[3] = get_dr(3);
 	dump->u_debugreg[6] = current->thread.debugreg6;
-	dump->u_debugreg[7] = current->thread.debugreg7;
+	dump->u_debugreg[7] = current->thread.ptrace_dr7;
 
 	if (dump->start_stack < 0xc0000000) {
 		unsigned long tmp;
@@ -74,24 +77,24 @@ static void dump_thread32(struct pt_regs *regs, struct user32 *dump)
 		dump->u_ssize = tmp >> PAGE_SHIFT;
 	}
 
-	dump->regs.bx = regs->bx;
-	dump->regs.cx = regs->cx;
-	dump->regs.dx = regs->dx;
-	dump->regs.si = regs->si;
-	dump->regs.di = regs->di;
-	dump->regs.bp = regs->bp;
-	dump->regs.ax = regs->ax;
+	dump->regs.ebx = regs->bx;
+	dump->regs.ecx = regs->cx;
+	dump->regs.edx = regs->dx;
+	dump->regs.esi = regs->si;
+	dump->regs.edi = regs->di;
+	dump->regs.ebp = regs->bp;
+	dump->regs.eax = regs->ax;
 	dump->regs.ds = current->thread.ds;
 	dump->regs.es = current->thread.es;
 	savesegment(fs, fs);
 	dump->regs.fs = fs;
 	savesegment(gs, gs);
 	dump->regs.gs = gs;
-	dump->regs.orig_ax = regs->orig_ax;
-	dump->regs.ip = regs->ip;
+	dump->regs.orig_eax = regs->orig_ax;
+	dump->regs.eip = regs->ip;
 	dump->regs.cs = regs->cs;
-	dump->regs.flags = regs->flags;
-	dump->regs.sp = regs->sp;
+	dump->regs.eflags = regs->flags;
+	dump->regs.esp = regs->sp;
 	dump->regs.ss = regs->ss;
 
 #if 1 /* FIXME */
@@ -107,7 +110,7 @@ static struct linux_binfmt aout_format = {
 	.module		= THIS_MODULE,
 	.load_binary	= load_aout_binary,
 	.load_shlib	= load_aout_library,
-#ifdef CORE_DUMP
+#ifdef CONFIG_COREDUMP
 	.core_dump	= aout_core_dump,
 #endif
 	.min_coredump	= PAGE_SIZE
@@ -122,7 +125,7 @@ static void set_brk(unsigned long start, unsigned long end)
 	vm_brk(start, end - start);
 }
 
-#ifdef CORE_DUMP
+#ifdef CONFIG_COREDUMP
 /*
  * These are the only things you should do on a core-file: use only these
  * macros to write out all the necessary info.
@@ -130,15 +133,7 @@ static void set_brk(unsigned long start, unsigned long end)
 
 #include <linux/coredump.h>
 
-#define DUMP_WRITE(addr, nr)			     \
-	if (!dump_write(file, (void *)(addr), (nr))) \
-		goto end_coredump;
-
-#define DUMP_SEEK(offset)		\
-	if (!dump_seek(file, offset))	\
-		goto end_coredump;
-
-#define START_DATA()	(u.u_tsize << PAGE_SHIFT)
+#define START_DATA(u)	(u.u_tsize << PAGE_SHIFT)
 #define START_STACK(u)	(u.start_stack)
 
 /*
@@ -151,8 +146,7 @@ static void set_brk(unsigned long start, unsigned long end)
  * dumping of the process results in another error..
  */
 
-static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file,
-			  unsigned long limit)
+static int aout_core_dump(struct coredump_params *cprm)
 {
 	mm_segment_t fs;
 	int has_dumped = 0;
@@ -164,19 +158,19 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file,
 	has_dumped = 1;
 	strncpy(dump.u_comm, current->comm, sizeof(current->comm));
 	dump.u_ar0 = offsetof(struct user32, regs);
-	dump.signal = signr;
-	dump_thread32(regs, &dump);
+	dump.signal = cprm->siginfo->si_signo;
+	dump_thread32(cprm->regs, &dump);
 
 	/*
 	 * If the size of the dump file exceeds the rlimit, then see
 	 * what would happen if we wrote the stack, but not the data
 	 * area.
 	 */
-	if ((dump.u_dsize + dump.u_ssize + 1) * PAGE_SIZE > limit)
+	if ((dump.u_dsize + dump.u_ssize + 1) * PAGE_SIZE > cprm->limit)
 		dump.u_dsize = 0;
 
 	/* Make sure we have enough room to write the stack and data areas. */
-	if ((dump.u_ssize + 1) * PAGE_SIZE > limit)
+	if ((dump.u_ssize + 1) * PAGE_SIZE > cprm->limit)
 		dump.u_ssize = 0;
 
 	/* make sure we actually have a data and stack area to dump */
@@ -190,22 +184,26 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file,
 
 	set_fs(KERNEL_DS);
 	/* struct user */
-	DUMP_WRITE(&dump, sizeof(dump));
+	if (!dump_emit(cprm, &dump, sizeof(dump)))
+		goto end_coredump;
 	/* Now dump all of the user data.  Include malloced stuff as well */
-	DUMP_SEEK(PAGE_SIZE - sizeof(dump));
+	if (!dump_skip(cprm, PAGE_SIZE - sizeof(dump)))
+		goto end_coredump;
 	/* now we start writing out the user space info */
 	set_fs(USER_DS);
 	/* Dump the data area */
 	if (dump.u_dsize != 0) {
 		dump_start = START_DATA(dump);
 		dump_size = dump.u_dsize << PAGE_SHIFT;
-		DUMP_WRITE(dump_start, dump_size);
+		if (!dump_emit(cprm, (void *)dump_start, dump_size))
+			goto end_coredump;
 	}
 	/* Now prepare to dump the stack area */
 	if (dump.u_ssize != 0) {
 		dump_start = START_STACK(dump);
 		dump_size = dump.u_ssize << PAGE_SHIFT;
-		DUMP_WRITE(dump_start, dump_size);
+		if (!dump_emit(cprm, (void *)dump_start, dump_size))
+			goto end_coredump;
 	}
 end_coredump:
 	set_fs(fs);

arch/x86/ia32/ia32_signal.c

@@ -34,7 +34,7 @@
 #include <asm/sys_ia32.h>
 #include <asm/smap.h>
 
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
+int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 {
 	int err = 0;
 	bool ia32 = test_thread_flag(TIF_IA32);

arch/x86/um/elfcore.c

@@ -11,8 +11,7 @@ Elf32_Half elf_core_extra_phdrs(void)
 	return vsyscall_ehdr ? (((struct elfhdr *)vsyscall_ehdr)->e_phnum) : 0;
 }
 
-int elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size,
-			       unsigned long limit)
+int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
 {
 	if ( vsyscall_ehdr ) {
 		const struct elfhdr *const ehdrp =
@@ -32,17 +31,14 @@ int elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size,
 				phdr.p_offset += ofs;
 			}
 			phdr.p_paddr = 0; /* match other core phdrs */
-			*size += sizeof(phdr);
-			if (*size > limit
-			    || !dump_write(file, &phdr, sizeof(phdr)))
+			if (!dump_emit(cprm, &phdr, sizeof(phdr)))
 				return 0;
 		}
 	}
 	return 1;
 }
 
-int elf_core_write_extra_data(struct file *file, size_t *size,
-			      unsigned long limit)
+int elf_core_write_extra_data(struct coredump_params *cprm)
 {
 	if ( vsyscall_ehdr ) {
 		const struct elfhdr *const ehdrp =
@@ -55,10 +51,7 @@ int elf_core_write_extra_data(struct file *file, size_t *size,
 			if (phdrp[i].p_type == PT_LOAD) {
 				void *addr = (void *) phdrp[i].p_vaddr;
 				size_t filesz = phdrp[i].p_filesz;
-
-				*size += filesz;
-				if (*size > limit
-				    || !dump_write(file, addr, filesz))
+				if (!dump_emit(cprm, addr, filesz))
 					return 0;
 			}
 		}

drivers/base/devtmpfs.c

@@ -216,7 +216,7 @@ static int handle_create(const char *nodename, umode_t mode, kuid_t uid,
 		newattrs.ia_gid = gid;
 		newattrs.ia_valid = ATTR_MODE|ATTR_UID|ATTR_GID;
 		mutex_lock(&dentry->d_inode->i_mutex);
-		notify_change(dentry, &newattrs);
+		notify_change(dentry, &newattrs, NULL);
 		mutex_unlock(&dentry->d_inode->i_mutex);
 
 		/* mark as kernel-created inode */
@@ -322,9 +322,9 @@ static int handle_remove(const char *nodename, struct device *dev)
 			newattrs.ia_valid =
 				ATTR_UID|ATTR_GID|ATTR_MODE;
 			mutex_lock(&dentry->d_inode->i_mutex);
-			notify_change(dentry, &newattrs);
+			notify_change(dentry, &newattrs, NULL);
 			mutex_unlock(&dentry->d_inode->i_mutex);
-			err = vfs_unlink(parent.dentry->d_inode, dentry);
+			err = vfs_unlink(parent.dentry->d_inode, dentry, NULL);
 			if (!err || err == -ENOENT)
 				deleted = 1;
 		}

drivers/char/misc.c

@@ -114,7 +114,7 @@ static int misc_open(struct inode * inode, struct file * file)
 	int minor = iminor(inode);
 	struct miscdevice *c;
 	int err = -ENODEV;
-	const struct file_operations *old_fops, *new_fops = NULL;
+	const struct file_operations *new_fops = NULL;
 
 	mutex_lock(&misc_mtx);
 	
@@ -141,17 +141,11 @@ static int misc_open(struct inode * inode, struct file * file)
 	}
 
 	err = 0;
-	old_fops = file->f_op;
-	file->f_op = new_fops;
+	replace_fops(file, new_fops);
 	if (file->f_op->open) {
 		file->private_data = c;
-		err=file->f_op->open(inode,file);
-		if (err) {
-			fops_put(file->f_op);
-			file->f_op = fops_get(old_fops);
-		}
+		err = file->f_op->open(inode,file);
 	}
-	fops_put(old_fops);
 fail:
 	mutex_unlock(&misc_mtx);
 	return err;

drivers/gpu/drm/drm_fops.c

@@ -148,7 +148,7 @@ int drm_stub_open(struct inode *inode, struct file *filp)
 	struct drm_minor *minor;
 	int minor_id = iminor(inode);
 	int err = -ENODEV;
-	const struct file_operations *old_fops;
+	const struct file_operations *new_fops;
 
 	DRM_DEBUG("\n");
 
@@ -163,18 +163,13 @@ int drm_stub_open(struct inode *inode, struct file *filp)
 	if (drm_device_is_unplugged(dev))
 		goto out;
 
-	old_fops = filp->f_op;
-	filp->f_op = fops_get(dev->driver->fops);
-	if (filp->f_op == NULL) {
-		filp->f_op = old_fops;
+	new_fops = fops_get(dev->driver->fops);
+	if (!new_fops)
 		goto out;
-	}
-	if (filp->f_op->open && (err = filp->f_op->open(inode, filp))) {
-		fops_put(filp->f_op);
-		filp->f_op = fops_get(old_fops);
-	}
-	fops_put(old_fops);
 
+	replace_fops(filp, new_fops);
+	if (filp->f_op->open)
+		err = filp->f_op->open(inode, filp);
 out:
 	mutex_unlock(&drm_global_mutex);
 	return err;

drivers/media/dvb-core/dmxdev.c

@@ -206,8 +206,6 @@ static int dvb_dvr_release(struct inode *inode, struct file *file)
 	/* TODO */
 	dvbdev->users--;
 	if (dvbdev->users == 1 && dmxdev->exit == 1) {
-		fops_put(file->f_op);
-		file->f_op = NULL;
 		mutex_unlock(&dmxdev->mutex);
 		wake_up(&dvbdev->wait_queue);
 	} else
@@ -1120,8 +1118,6 @@ static int dvb_demux_release(struct inode *inode, struct file *file)
 	mutex_lock(&dmxdev->mutex);
 	dmxdev->dvbdev->users--;
 	if(dmxdev->dvbdev->users==1 && dmxdev->exit==1) {
-		fops_put(file->f_op);
-		file->f_op = NULL;
 		mutex_unlock(&dmxdev->mutex);
 		wake_up(&dmxdev->dvbdev->wait_queue);
 	} else

drivers/media/dvb-core/dvbdev.c

@@ -74,22 +74,15 @@ static int dvb_device_open(struct inode *inode, struct file *file)
 
 	if (dvbdev && dvbdev->fops) {
 		int err = 0;
-		const struct file_operations *old_fops;
+		const struct file_operations *new_fops;
 
-		file->private_data = dvbdev;
-		old_fops = file->f_op;
-		file->f_op = fops_get(dvbdev->fops);
-		if (file->f_op == NULL) {
-			file->f_op = old_fops;
+		new_fops = fops_get(dvbdev->fops);
+		if (!new_fops)
 			goto fail;
-		}
-		if(file->f_op->open)
+		file->private_data = dvbdev;
+		replace_fops(file, new_fops);
+		if (file->f_op->open)
 			err = file->f_op->open(inode,file);
-		if (err) {
-			fops_put(file->f_op);
-			file->f_op = fops_get(old_fops);
-		}
-		fops_put(old_fops);
 		up_read(&minor_rwsem);
 		mutex_unlock(&dvbdev_mutex);
 		return err;

drivers/mtd/nand/nandsim.c

@@ -575,7 +575,7 @@ static int alloc_device(struct nandsim *ns)
 		cfile = filp_open(cache_file, O_CREAT | O_RDWR | O_LARGEFILE, 0600);
 		if (IS_ERR(cfile))
 			return PTR_ERR(cfile);
-		if (!cfile->f_op || (!cfile->f_op->read && !cfile->f_op->aio_read)) {
+		if (!cfile->f_op->read && !cfile->f_op->aio_read) {
 			NS_ERR("alloc_device: cache file not readable\n");
 			err = -EINVAL;
 			goto err_close;

drivers/staging/comedi/comedi_compat32.c

@@ -86,9 +86,6 @@ struct comedi32_insnlist_struct {
 static int translated_ioctl(struct file *file, unsigned int cmd,
 			    unsigned long arg)
 {
-	if (!file->f_op)
-		return -ENOTTY;
-
 	if (file->f_op->unlocked_ioctl)
 		return file->f_op->unlocked_ioctl(file, cmd, arg);
 

drivers/staging/lustre/lustre/include/linux/lustre_compat25.h

@@ -105,8 +105,8 @@ static inline void ll_set_fs_pwd(struct fs_struct *fs, struct vfsmount *mnt,
 #define ll_vfs_unlink(inode,entry,mnt)	  vfs_unlink(inode,entry)
 #define ll_vfs_mknod(dir,entry,mnt,mode,dev)    vfs_mknod(dir,entry,mode,dev)
 #define ll_security_inode_unlink(dir,entry,mnt) security_inode_unlink(dir,entry)
-#define ll_vfs_rename(old,old_dir,mnt,new,new_dir,mnt1) \
-		vfs_rename(old,old_dir,new,new_dir)
+#define ll_vfs_rename(old,old_dir,mnt,new,new_dir,mnt1,delegated_inode) \
+		vfs_rename(old,old_dir,new,new_dir,delegated_inode)
 
 #define cfs_bio_io_error(a,b)   bio_io_error((a))
 #define cfs_bio_endio(a,b,c)    bio_endio((a),(c))

drivers/staging/lustre/lustre/llite/namei.c

@@ -83,7 +83,7 @@ int ll_unlock(__u32 mode, struct lustre_handle *lockh)
 }
 
 
-/* called from iget5_locked->find_inode() under inode_lock spinlock */
+/* called from iget5_locked->find_inode() under inode_hash_lock spinlock */
 static int ll_test_inode(struct inode *inode, void *opaque)
 {
 	struct ll_inode_info *lli = ll_i2info(inode);

drivers/staging/lustre/lustre/lvfs/lvfs_linux.c

@@ -224,7 +224,7 @@ int lustre_rename(struct dentry *dir, struct vfsmount *mnt,
 		GOTO(put_old, err = PTR_ERR(dchild_new));
 
 	err = ll_vfs_rename(dir->d_inode, dchild_old, mnt,
-			    dir->d_inode, dchild_new, mnt);
+			    dir->d_inode, dchild_new, mnt, NULL);
 
 	dput(dchild_new);
 put_old:

drivers/staging/rtl8188eu/include/osdep_service.h

@@ -430,11 +430,6 @@ int ATOMIC_SUB_RETURN(ATOMIC_T *v, int i);
 int ATOMIC_INC_RETURN(ATOMIC_T *v);
 int ATOMIC_DEC_RETURN(ATOMIC_T *v);
 
-/* File operation APIs, just for linux now */
-int rtw_is_file_readable(char *path);
-int rtw_retrive_from_file(char *path, u8 __user *buf, u32 sz);
-int rtw_store_to_file(char *path, u8 __user *buf, u32 sz);
-
 struct rtw_netdev_priv_indicator {
 	void *priv;
 	u32 sizeof_priv;

drivers/staging/rtl8188eu/os_dep/osdep_service.c

@@ -356,214 +356,6 @@ inline int ATOMIC_DEC_RETURN(ATOMIC_T *v)
 	return atomic_dec_return(v);
 }
 
-/* Open a file with the specific @param path, @param flag, @param mode
- * @param fpp the pointer of struct file pointer to get struct file pointer while file opening is success
- * @param path the path of the file to open
- * @param flag file operation flags, please refer to linux document
- * @param mode please refer to linux document
- * @return Linux specific error code
- */
-static int openfile(struct file **fpp, char *path, int flag, int mode)
-{
-	struct file *fp;
-
-	fp = filp_open(path, flag, mode);
-	if (IS_ERR(fp)) {
-		*fpp = NULL;
-		return PTR_ERR(fp);
-	} else {
-		*fpp = fp;
-		return 0;
-	}
-}
-
-/* Close the file with the specific @param fp
- * @param fp the pointer of struct file to close
- * @return always 0
- */
-static int closefile(struct file *fp)
-{
-	filp_close(fp, NULL);
-	return 0;
-}
-
-static int readfile(struct file *fp, char __user *buf, int len)
-{
-	int rlen = 0, sum = 0;
-
-	if (!fp->f_op || !fp->f_op->read)
-		return -EPERM;
-
-	while (sum < len) {
-		rlen = fp->f_op->read(fp, buf+sum, len-sum, &fp->f_pos);
-		if (rlen > 0)
-			sum += rlen;
-		else if (0 != rlen)
-			return rlen;
-		else
-			break;
-	}
-	return  sum;
-}
-
-static int writefile(struct file *fp, char __user *buf, int len)
-{
-	int wlen = 0, sum = 0;
-
-	if (!fp->f_op || !fp->f_op->write)
-		return -EPERM;
-
-	while (sum < len) {
-		wlen = fp->f_op->write(fp, buf+sum, len-sum, &fp->f_pos);
-		if (wlen > 0)
-			sum += wlen;
-		else if (0 != wlen)
-			return wlen;
-		else
-			break;
-	}
-	return sum;
-}
-
-/* Test if the specifi @param path is a file and readable
- * @param path the path of the file to test
- * @return Linux specific error code
- */
-static int isfilereadable(char *path)
-{
-	struct file *fp;
-	int ret = 0;
-	mm_segment_t oldfs;
-	char __user buf;
-
-	fp = filp_open(path, O_RDONLY, 0);
-	if (IS_ERR(fp)) {
-		ret = PTR_ERR(fp);
-	} else {
-		oldfs = get_fs(); set_fs(get_ds());
-
-		if (1 != readfile(fp, &buf, 1))
-			ret = PTR_ERR(fp);
-
-		set_fs(oldfs);
-		filp_close(fp, NULL);
-	}
-	return ret;
-}
-
-/* Open the file with @param path and retrive the file content into
- * memory starting from @param buf for @param sz at most
- * @param path the path of the file to open and read
- * @param buf the starting address of the buffer to store file content
- * @param sz how many bytes to read at most
- * @return the byte we've read, or Linux specific error code
- */
-static int retrievefromfile(char *path, u8 __user *buf, u32 sz)
-{
-	int ret = -1;
-	mm_segment_t oldfs;
-	struct file *fp;
-
-	if (path && buf) {
-		ret = openfile(&fp, path, O_RDONLY, 0);
-		if (0 == ret) {
-			DBG_88E("%s openfile path:%s fp =%p\n", __func__,
-				path, fp);
-
-			oldfs = get_fs(); set_fs(get_ds());
-			ret = readfile(fp, buf, sz);
-			set_fs(oldfs);
-			closefile(fp);
-
-			DBG_88E("%s readfile, ret:%d\n", __func__, ret);
-
-		} else {
-			DBG_88E("%s openfile path:%s Fail, ret:%d\n", __func__,
-				path, ret);
-		}
-	} else {
-		DBG_88E("%s NULL pointer\n", __func__);
-		ret =  -EINVAL;
-	}
-	return ret;
-}
-
-/*
-* Open the file with @param path and wirte @param sz byte of data starting from @param buf into the file
-* @param path the path of the file to open and write
-* @param buf the starting address of the data to write into file
-* @param sz how many bytes to write at most
-* @return the byte we've written, or Linux specific error code
-*/
-static int storetofile(char *path, u8 __user *buf, u32 sz)
-{
-	int ret = 0;
-	mm_segment_t oldfs;
-	struct file *fp;
-
-	if (path && buf) {
-		ret = openfile(&fp, path, O_CREAT|O_WRONLY, 0666);
-		if (0 == ret) {
-			DBG_88E("%s openfile path:%s fp =%p\n", __func__, path, fp);
-
-			oldfs = get_fs(); set_fs(get_ds());
-			ret = writefile(fp, buf, sz);
-			set_fs(oldfs);
-			closefile(fp);
-
-			DBG_88E("%s writefile, ret:%d\n", __func__, ret);
-
-		} else {
-			DBG_88E("%s openfile path:%s Fail, ret:%d\n", __func__, path, ret);
-		}
-	} else {
-		DBG_88E("%s NULL pointer\n", __func__);
-		ret =  -EINVAL;
-	}
-	return ret;
-}
-
-/*
-* Test if the specifi @param path is a file and readable
-* @param path the path of the file to test
-* @return true or false
-*/
-int rtw_is_file_readable(char *path)
-{
-	if (isfilereadable(path) == 0)
-		return true;
-	else
-		return false;
-}
-
-/*
-* Open the file with @param path and retrive the file content into memory starting from @param buf for @param sz at most
-* @param path the path of the file to open and read
-* @param buf the starting address of the buffer to store file content
-* @param sz how many bytes to read at most
-* @return the byte we've read
-*/
-int rtw_retrive_from_file(char *path, u8 __user *buf, u32 sz)
-{
-	int ret = retrievefromfile(path, buf, sz);
-
-	return ret >= 0 ? ret : 0;
-}
-
-/*
- * Open the file with @param path and wirte @param sz byte of data
- * starting from @param buf into the file
- * @param path the path of the file to open and write
- * @param buf the starting address of the data to write into file
- * @param sz how many bytes to write at most
- * @return the byte we've written
- */
-int rtw_store_to_file(char *path, u8 __user *buf, u32 sz)
-{
-	int ret = storetofile(path, buf, sz);
-	return ret >= 0 ? ret : 0;
-}
-
 struct net_device *rtw_alloc_etherdev_with_old_priv(int sizeof_priv,
 						    void *old_priv)
 {

drivers/usb/core/file.c

@@ -29,27 +29,19 @@ static DECLARE_RWSEM(minor_rwsem);
 
 static int usb_open(struct inode *inode, struct file *file)
 {
-	int minor = iminor(inode);
-	const struct file_operations *c;
 	int err = -ENODEV;
-	const struct file_operations *old_fops, *new_fops = NULL;
+	const struct file_operations *new_fops;
 
 	down_read(&minor_rwsem);
-	c = usb_minors[minor];
+	new_fops = fops_get(usb_minors[iminor(inode)]);
 
-	if (!c || !(new_fops = fops_get(c)))
+	if (!new_fops)
 		goto done;
 
-	old_fops = file->f_op;
-	file->f_op = new_fops;
+	replace_fops(file, new_fops);
 	/* Curiouser and curiouser... NULL ->open() as "no device" ? */
 	if (file->f_op->open)
 		err = file->f_op->open(inode, file);
-	if (err) {
-		fops_put(file->f_op);
-		file->f_op = fops_get(old_fops);
-	}
-	fops_put(old_fops);
  done:
 	up_read(&minor_rwsem);
 	return err;

fs/9p/cache.h

@@ -101,6 +101,18 @@ static inline void v9fs_fscache_wait_on_page_write(struct inode *inode,
 
 #else /* CONFIG_9P_FSCACHE */
 
+static inline void v9fs_cache_inode_get_cookie(struct inode *inode)
+{
+}
+
+static inline void v9fs_cache_inode_put_cookie(struct inode *inode)
+{
+}
+
+static inline void v9fs_cache_inode_set_cookie(struct inode *inode, struct file *file)
+{
+}
+
 static inline int v9fs_fscache_release_page(struct page *page,
 					    gfp_t gfp) {
 	return 1;

fs/9p/vfs_file.c

@@ -105,10 +105,8 @@ int v9fs_file_open(struct inode *inode, struct file *file)
 		v9inode->writeback_fid = (void *) fid;
 	}
 	mutex_unlock(&v9inode->v_mutex);
-#ifdef CONFIG_9P_FSCACHE
 	if (v9ses->cache)
 		v9fs_cache_inode_set_cookie(inode, file);
-#endif
 	return 0;
 out_error:
 	p9_client_clunk(file->private_data);

fs/9p/vfs_inode.c

@@ -448,9 +448,7 @@ void v9fs_evict_inode(struct inode *inode)
 	clear_inode(inode);
 	filemap_fdatawrite(inode->i_mapping);
 
-#ifdef CONFIG_9P_FSCACHE
 	v9fs_cache_inode_put_cookie(inode);
-#endif
 	/* clunk the fid stashed in writeback_fid */
 	if (v9inode->writeback_fid) {
 		p9_client_clunk(v9inode->writeback_fid);
@@ -531,9 +529,7 @@ static struct inode *v9fs_qid_iget(struct super_block *sb,
 		goto error;
 
 	v9fs_stat2inode(st, inode, sb);
-#ifdef CONFIG_9P_FSCACHE
 	v9fs_cache_inode_get_cookie(inode);
-#endif
 	unlock_new_inode(inode);
 	return inode;
 error:
@@ -905,10 +901,8 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
 		goto error;
 
 	file->private_data = fid;
-#ifdef CONFIG_9P_FSCACHE
 	if (v9ses->cache)
 		v9fs_cache_inode_set_cookie(dentry->d_inode, file);
-#endif
 
 	*opened |= FILE_CREATED;
 out:

fs/9p/vfs_inode_dotl.c

@@ -141,9 +141,7 @@ static struct inode *v9fs_qid_iget_dotl(struct super_block *sb,
 		goto error;
 
 	v9fs_stat2inode_dotl(st, inode);
-#ifdef CONFIG_9P_FSCACHE
 	v9fs_cache_inode_get_cookie(inode);
-#endif
 	retval = v9fs_get_acl(inode, fid);
 	if (retval)
 		goto error;
@@ -355,10 +353,8 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
 	if (err)
 		goto err_clunk_old_fid;
 	file->private_data = ofid;
-#ifdef CONFIG_9P_FSCACHE
 	if (v9ses->cache)
 		v9fs_cache_inode_set_cookie(inode, file);
-#endif
 	*opened |= FILE_CREATED;
 out:
 	v9fs_put_acl(dacl, pacl);

fs/adfs/adfs.h

@@ -43,9 +43,12 @@ struct adfs_dir_ops;
  * ADFS file system superblock data in memory
  */
 struct adfs_sb_info {
-	struct adfs_discmap *s_map;	/* bh list containing map		 */
-	struct adfs_dir_ops *s_dir;	/* directory operations			 */
-
+	union { struct {
+		struct adfs_discmap *s_map;	/* bh list containing map	 */
+		struct adfs_dir_ops *s_dir;	/* directory operations		 */
+		};
+		struct rcu_head rcu;		/* used only at shutdown time	 */
+	};
 	kuid_t		s_uid;		/* owner uid				 */
 	kgid_t		s_gid;		/* owner gid				 */
 	umode_t		s_owner_mask;	/* ADFS owner perm -> unix perm		 */

fs/adfs/super.c

@@ -123,8 +123,7 @@ static void adfs_put_super(struct super_block *sb)
 	for (i = 0; i < asb->s_map_size; i++)
 		brelse(asb->s_map[i].dm_bh);
 	kfree(asb->s_map);
-	kfree(asb);
-	sb->s_fs_info = NULL;
+	kfree_rcu(asb, rcu);
 }
 
 static int adfs_show_options(struct seq_file *seq, struct dentry *root)

fs/aio.c

@@ -36,10 +36,10 @@
 #include <linux/eventfd.h>
 #include <linux/blkdev.h>
 #include <linux/compat.h>
-#include <linux/anon_inodes.h>
 #include <linux/migrate.h>
 #include <linux/ramfs.h>
 #include <linux/percpu-refcount.h>
+#include <linux/mount.h>
 
 #include <asm/kmap_types.h>
 #include <asm/uaccess.h>
@@ -152,12 +152,67 @@ unsigned long aio_max_nr = 0x10000; /* system wide maximum number of aio request
 static struct kmem_cache	*kiocb_cachep;
 static struct kmem_cache	*kioctx_cachep;
 
+static struct vfsmount *aio_mnt;
+
+static const struct file_operations aio_ring_fops;
+static const struct address_space_operations aio_ctx_aops;
+
+static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
+{
+	struct qstr this = QSTR_INIT("[aio]", 5);
+	struct file *file;
+	struct path path;
+	struct inode *inode = alloc_anon_inode(aio_mnt->mnt_sb);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+
+	inode->i_mapping->a_ops = &aio_ctx_aops;
+	inode->i_mapping->private_data = ctx;
+	inode->i_size = PAGE_SIZE * nr_pages;
+
+	path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this);
+	if (!path.dentry) {
+		iput(inode);
+		return ERR_PTR(-ENOMEM);
+	}
+	path.mnt = mntget(aio_mnt);
+
+	d_instantiate(path.dentry, inode);
+	file = alloc_file(&path, FMODE_READ | FMODE_WRITE, &aio_ring_fops);
+	if (IS_ERR(file)) {
+		path_put(&path);
+		return file;
+	}
+
+	file->f_flags = O_RDWR;
+	file->private_data = ctx;
+	return file;
+}
+
+static struct dentry *aio_mount(struct file_system_type *fs_type,
+				int flags, const char *dev_name, void *data)
+{
+	static const struct dentry_operations ops = {
+		.d_dname	= simple_dname,
+	};
+	return mount_pseudo(fs_type, "aio:", NULL, &ops, 0xa10a10a1);
+}
+
 /* aio_setup
  *	Creates the slab caches used by the aio routines, panic on
  *	failure as this is done early during the boot sequence.
  */
 static int __init aio_setup(void)
 {
+	static struct file_system_type aio_fs = {
+		.name		= "aio",
+		.mount		= aio_mount,
+		.kill_sb	= kill_anon_super,
+	};
+	aio_mnt = kern_mount(&aio_fs);
+	if (IS_ERR(aio_mnt))
+		panic("Failed to create aio fs mount.");
+
 	kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 	kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 
@@ -283,16 +338,12 @@ static int aio_setup_ring(struct kioctx *ctx)
 	if (nr_pages < 0)
 		return -EINVAL;
 
-	file = anon_inode_getfile_private("[aio]", &aio_ring_fops, ctx, O_RDWR);
+	file = aio_private_file(ctx, nr_pages);
 	if (IS_ERR(file)) {
 		ctx->aio_ring_file = NULL;
 		return -EAGAIN;
 	}
 
-	file->f_inode->i_mapping->a_ops = &aio_ctx_aops;
-	file->f_inode->i_mapping->private_data = ctx;
-	file->f_inode->i_size = PAGE_SIZE * (loff_t)nr_pages;
-
 	for (i = 0; i < nr_pages; i++) {
 		struct page *page;
 		page = find_or_create_page(file->f_inode->i_mapping,

fs/anon_inodes.c

@@ -24,7 +24,6 @@
 
 static struct vfsmount *anon_inode_mnt __read_mostly;
 static struct inode *anon_inode_inode;
-static const struct file_operations anon_inode_fops;
 
 /*
  * anon_inodefs_dname() is called from d_path().
@@ -39,51 +38,6 @@ static const struct dentry_operations anon_inodefs_dentry_operations = {
 	.d_dname	= anon_inodefs_dname,
 };
 
-/*
- * nop .set_page_dirty method so that people can use .page_mkwrite on
- * anon inodes.
- */
-static int anon_set_page_dirty(struct page *page)
-{
-	return 0;
-};
-
-static const struct address_space_operations anon_aops = {
-	.set_page_dirty = anon_set_page_dirty,
-};
-
-/*
- * A single inode exists for all anon_inode files. Contrary to pipes,
- * anon_inode inodes have no associated per-instance data, so we need
- * only allocate one of them.
- */
-static struct inode *anon_inode_mkinode(struct super_block *s)
-{
-	struct inode *inode = new_inode_pseudo(s);
-
-	if (!inode)
-		return ERR_PTR(-ENOMEM);
-
-	inode->i_ino = get_next_ino();
-	inode->i_fop = &anon_inode_fops;
-
-	inode->i_mapping->a_ops = &anon_aops;
-
-	/*
-	 * Mark the inode dirty from the very beginning,
-	 * that way it will never be moved to the dirty
-	 * list because mark_inode_dirty() will think
-	 * that it already _is_ on the dirty list.
-	 */
-	inode->i_state = I_DIRTY;
-	inode->i_mode = S_IRUSR | S_IWUSR;
-	inode->i_uid = current_fsuid();
-	inode->i_gid = current_fsgid();
-	inode->i_flags |= S_PRIVATE;
-	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-	return inode;
-}
-
 static struct dentry *anon_inodefs_mount(struct file_system_type *fs_type,
 				int flags, const char *dev_name, void *data)
 {
@@ -92,7 +46,7 @@ static struct dentry *anon_inodefs_mount(struct file_system_type *fs_type,
 			&anon_inodefs_dentry_operations, ANON_INODE_FS_MAGIC);
 	if (!IS_ERR(root)) {
 		struct super_block *s = root->d_sb;
-		anon_inode_inode = anon_inode_mkinode(s);
+		anon_inode_inode = alloc_anon_inode(s);
 		if (IS_ERR(anon_inode_inode)) {
 			dput(root);
 			deactivate_locked_super(s);
@@ -108,72 +62,6 @@ static struct file_system_type anon_inode_fs_type = {
 	.kill_sb	= kill_anon_super,
 };
 
-/**
- * anon_inode_getfile_private - creates a new file instance by hooking it up to an
- *                      anonymous inode, and a dentry that describe the "class"
- *                      of the file
- *
- * @name:    [in]    name of the "class" of the new file
- * @fops:    [in]    file operations for the new file
- * @priv:    [in]    private data for the new file (will be file's private_data)
- * @flags:   [in]    flags
- *
- *
- * Similar to anon_inode_getfile, but each file holds a single inode.
- *
- */
-struct file *anon_inode_getfile_private(const char *name,
-					const struct file_operations *fops,
-					void *priv, int flags)
-{
-	struct qstr this;
-	struct path path;
-	struct file *file;
-	struct inode *inode;
-
-	if (fops->owner && !try_module_get(fops->owner))
-		return ERR_PTR(-ENOENT);
-
-	inode = anon_inode_mkinode(anon_inode_mnt->mnt_sb);
-	if (IS_ERR(inode)) {
-		file = ERR_PTR(-ENOMEM);
-		goto err_module;
-	}
-
-	/*
-	 * Link the inode to a directory entry by creating a unique name
-	 * using the inode sequence number.
-	 */
-	file = ERR_PTR(-ENOMEM);
-	this.name = name;
-	this.len = strlen(name);
-	this.hash = 0;
-	path.dentry = d_alloc_pseudo(anon_inode_mnt->mnt_sb, &this);
-	if (!path.dentry)
-		goto err_module;
-
-	path.mnt = mntget(anon_inode_mnt);
-
-	d_instantiate(path.dentry, inode);
-
-	file = alloc_file(&path, OPEN_FMODE(flags), fops);
-	if (IS_ERR(file))
-		goto err_dput;
-
-	file->f_mapping = inode->i_mapping;
-	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
-	file->private_data = priv;
-
-	return file;
-
-err_dput:
-	path_put(&path);
-err_module:
-	module_put(fops->owner);
-	return file;
-}
-EXPORT_SYMBOL_GPL(anon_inode_getfile_private);
-
 /**
  * anon_inode_getfile - creates a new file instance by hooking it up to an
  *                      anonymous inode, and a dentry that describe the "class"

fs/attr.c

@@ -167,7 +167,27 @@ void setattr_copy(struct inode *inode, const struct iattr *attr)
 }
 EXPORT_SYMBOL(setattr_copy);
 
-int notify_change(struct dentry * dentry, struct iattr * attr)
+/**
+ * notify_change - modify attributes of a filesytem object
+ * @dentry:	object affected
+ * @iattr:	new attributes
+ * @delegated_inode: returns inode, if the inode is delegated
+ *
+ * The caller must hold the i_mutex on the affected object.
+ *
+ * If notify_change discovers a delegation in need of breaking,
+ * it will return -EWOULDBLOCK and return a reference to the inode in
+ * delegated_inode.  The caller should then break the delegation and
+ * retry.  Because breaking a delegation may take a long time, the
+ * caller should drop the i_mutex before doing so.
+ *
+ * Alternatively, a caller may pass NULL for delegated_inode.  This may
+ * be appropriate for callers that expect the underlying filesystem not
+ * to be NFS exported.  Also, passing NULL is fine for callers holding
+ * the file open for write, as there can be no conflicting delegation in
+ * that case.
+ */
+int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **delegated_inode)
 {
 	struct inode *inode = dentry->d_inode;
 	umode_t mode = inode->i_mode;
@@ -241,6 +261,9 @@ int notify_change(struct dentry * dentry, struct iattr * attr)
 		return 0;
 
 	error = security_inode_setattr(dentry, attr);
+	if (error)
+		return error;
+	error = try_break_deleg(inode, delegated_inode);
 	if (error)
 		return error;
 

fs/autofs4/autofs_i.h

@@ -122,6 +122,7 @@ struct autofs_sb_info {
 	spinlock_t lookup_lock;
 	struct list_head active_list;
 	struct list_head expiring_list;
+	struct rcu_head rcu;
 };
 
 static inline struct autofs_sb_info *autofs4_sbi(struct super_block *sb)
@@ -271,7 +272,7 @@ void autofs4_clean_ino(struct autofs_info *);
 
 static inline int autofs_prepare_pipe(struct file *pipe)
 {
-	if (!pipe->f_op || !pipe->f_op->write)
+	if (!pipe->f_op->write)
 		return -EINVAL;
 	if (!S_ISFIFO(file_inode(pipe)->i_mode))
 		return -EINVAL;

fs/autofs4/dev-ioctl.c

@@ -658,12 +658,6 @@ static int _autofs_dev_ioctl(unsigned int command, struct autofs_dev_ioctl __use
 			goto out;
 		}
 
-		if (!fp->f_op) {
-			err = -ENOTTY;
-			fput(fp);
-			goto out;
-		}
-
 		sbi = autofs_dev_ioctl_sbi(fp);
 		if (!sbi || sbi->magic != AUTOFS_SBI_MAGIC) {
 			err = -EINVAL;

fs/autofs4/inode.c

@@ -56,18 +56,13 @@ void autofs4_kill_sb(struct super_block *sb)
 	 * just call kill_anon_super when we are called from
 	 * deactivate_super.
 	 */
-	if (!sbi)
-		goto out_kill_sb;
-
-	/* Free wait queues, close pipe */
-	autofs4_catatonic_mode(sbi);
-
-	sb->s_fs_info = NULL;
-	kfree(sbi);
+	if (sbi) /* Free wait queues, close pipe */
+		autofs4_catatonic_mode(sbi);
 
-out_kill_sb:
 	DPRINTK("shutting down");
 	kill_litter_super(sb);
+	if (sbi)
+		kfree_rcu(sbi, rcu);
 }
 
 static int autofs4_show_options(struct seq_file *m, struct dentry *root)

fs/befs/linuxvfs.c

@@ -42,7 +42,7 @@ static void befs_destroy_inode(struct inode *inode);
 static int befs_init_inodecache(void);
 static void befs_destroy_inodecache(void);
 static void *befs_follow_link(struct dentry *, struct nameidata *);
-static void befs_put_link(struct dentry *, struct nameidata *, void *);
+static void *befs_fast_follow_link(struct dentry *, struct nameidata *);
 static int befs_utf2nls(struct super_block *sb, const char *in, int in_len,
 			char **out, int *out_len);
 static int befs_nls2utf(struct super_block *sb, const char *in, int in_len,
@@ -79,10 +79,15 @@ static const struct address_space_operations befs_aops = {
 	.bmap		= befs_bmap,
 };
 
+static const struct inode_operations befs_fast_symlink_inode_operations = {
+	.readlink	= generic_readlink,
+	.follow_link	= befs_fast_follow_link,
+};
+
 static const struct inode_operations befs_symlink_inode_operations = {
 	.readlink	= generic_readlink,
 	.follow_link	= befs_follow_link,
-	.put_link	= befs_put_link,
+	.put_link	= kfree_put_link,
 };
 
 /* 
@@ -411,7 +416,10 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
 		inode->i_op = &befs_dir_inode_operations;
 		inode->i_fop = &befs_dir_operations;
 	} else if (S_ISLNK(inode->i_mode)) {
-		inode->i_op = &befs_symlink_inode_operations;
+		if (befs_ino->i_flags & BEFS_LONG_SYMLINK)
+			inode->i_op = &befs_symlink_inode_operations;
+		else
+			inode->i_op = &befs_fast_symlink_inode_operations;
 	} else {
 		befs_error(sb, "Inode %lu is not a regular file, "
 			   "directory or symlink. THAT IS WRONG! BeFS has no "
@@ -477,47 +485,40 @@ befs_destroy_inodecache(void)
 static void *
 befs_follow_link(struct dentry *dentry, struct nameidata *nd)
 {
+	struct super_block *sb = dentry->d_sb;
 	befs_inode_info *befs_ino = BEFS_I(dentry->d_inode);
+	befs_data_stream *data = &befs_ino->i_data.ds;
+	befs_off_t len = data->size;
 	char *link;
 
-	if (befs_ino->i_flags & BEFS_LONG_SYMLINK) {
-		struct super_block *sb = dentry->d_sb;
-		befs_data_stream *data = &befs_ino->i_data.ds;
-		befs_off_t len = data->size;
+	if (len == 0) {
+		befs_error(sb, "Long symlink with illegal length");
+		link = ERR_PTR(-EIO);
+	} else {
+		befs_debug(sb, "Follow long symlink");
 
-		if (len == 0) {
-			befs_error(sb, "Long symlink with illegal length");
+		link = kmalloc(len, GFP_NOFS);
+		if (!link) {
+			link = ERR_PTR(-ENOMEM);
+		} else if (befs_read_lsymlink(sb, data, link, len) != len) {
+			kfree(link);
+			befs_error(sb, "Failed to read entire long symlink");
 			link = ERR_PTR(-EIO);
 		} else {
-			befs_debug(sb, "Follow long symlink");
-
-			link = kmalloc(len, GFP_NOFS);
-			if (!link) {
-				link = ERR_PTR(-ENOMEM);
-			} else if (befs_read_lsymlink(sb, data, link, len) != len) {
-				kfree(link);
-				befs_error(sb, "Failed to read entire long symlink");
-				link = ERR_PTR(-EIO);
-			} else {
-				link[len - 1] = '\0';
-			}
+			link[len - 1] = '\0';
 		}
-	} else {
-		link = befs_ino->i_data.symlink;
 	}
-
 	nd_set_link(nd, link);
 	return NULL;
 }
 
-static void befs_put_link(struct dentry *dentry, struct nameidata *nd, void *p)
+
+static void *
+befs_fast_follow_link(struct dentry *dentry, struct nameidata *nd)
 {
 	befs_inode_info *befs_ino = BEFS_I(dentry->d_inode);
-	if (befs_ino->i_flags & BEFS_LONG_SYMLINK) {
-		char *link = nd_get_link(nd);
-		if (!IS_ERR(link))
-			kfree(link);
-	}
+	nd_set_link(nd, befs_ino->i_data.symlink);
+	return NULL;
 }
 
 /*

fs/binfmt_aout.c

@@ -45,7 +45,6 @@ static int load_aout_library(struct file*);
  */
 static int aout_core_dump(struct coredump_params *cprm)
 {
-	struct file *file = cprm->file;
 	mm_segment_t fs;
 	int has_dumped = 0;
 	void __user *dump_start;
@@ -85,10 +84,10 @@ static int aout_core_dump(struct coredump_params *cprm)
 
 	set_fs(KERNEL_DS);
 /* struct user */
-	if (!dump_write(file, &dump, sizeof(dump)))
+	if (!dump_emit(cprm, &dump, sizeof(dump)))
 		goto end_coredump;
 /* Now dump all of the user data.  Include malloced stuff as well */
-	if (!dump_seek(cprm->file, PAGE_SIZE - sizeof(dump)))
+	if (!dump_skip(cprm, PAGE_SIZE - sizeof(dump)))
 		goto end_coredump;
 /* now we start writing out the user space info */
 	set_fs(USER_DS);
@@ -96,14 +95,14 @@ static int aout_core_dump(struct coredump_params *cprm)
 	if (dump.u_dsize != 0) {
 		dump_start = START_DATA(dump);
 		dump_size = dump.u_dsize << PAGE_SHIFT;
-		if (!dump_write(file, dump_start, dump_size))
+		if (!dump_emit(cprm, dump_start, dump_size))
 			goto end_coredump;
 	}
 /* Now prepare to dump the stack area */
 	if (dump.u_ssize != 0) {
 		dump_start = START_STACK(dump);
 		dump_size = dump.u_ssize << PAGE_SHIFT;
-		if (!dump_write(file, dump_start, dump_size))
+		if (!dump_emit(cprm, dump_start, dump_size))
 			goto end_coredump;
 	}
 end_coredump:
@@ -221,7 +220,7 @@ static int load_aout_binary(struct linux_binprm * bprm)
 	 * Requires a mmap handler. This prevents people from using a.out
 	 * as part of an exploit attack against /proc-related vulnerabilities.
 	 */
-	if (!bprm->file->f_op || !bprm->file->f_op->mmap)
+	if (!bprm->file->f_op->mmap)
 		return -ENOEXEC;
 
 	fd_offset = N_TXTOFF(ex);
@@ -374,7 +373,7 @@ static int load_aout_library(struct file *file)
 	 * Requires a mmap handler. This prevents people from using a.out
 	 * as part of an exploit attack against /proc-related vulnerabilities.
 	 */
-	if (!file->f_op || !file->f_op->mmap)
+	if (!file->f_op->mmap)
 		goto out;
 
 	if (N_FLAGS(ex))

fs/binfmt_elf.c

@@ -406,7 +406,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
 		goto out;
 	if (!elf_check_arch(interp_elf_ex))
 		goto out;
-	if (!interpreter->f_op || !interpreter->f_op->mmap)
+	if (!interpreter->f_op->mmap)
 		goto out;
 
 	/*
@@ -607,7 +607,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
 		goto out;
 	if (!elf_check_arch(&loc->elf_ex))
 		goto out;
-	if (!bprm->file->f_op || !bprm->file->f_op->mmap)
+	if (!bprm->file->f_op->mmap)
 		goto out;
 
 	/* Now read in all of the header information */
@@ -1028,7 +1028,7 @@ static int load_elf_library(struct file *file)
 
 	/* First of all, some simple consistency checks */
 	if (elf_ex.e_type != ET_EXEC || elf_ex.e_phnum > 2 ||
-	    !elf_check_arch(&elf_ex) || !file->f_op || !file->f_op->mmap)
+	    !elf_check_arch(&elf_ex) || !file->f_op->mmap)
 		goto out;
 
 	/* Now read in all of the header information */
@@ -1225,35 +1225,17 @@ static int notesize(struct memelfnote *en)
 	return sz;
 }
 
-#define DUMP_WRITE(addr, nr, foffset)	\
-	do { if (!dump_write(file, (addr), (nr))) return 0; *foffset += (nr); } while(0)
-
-static int alignfile(struct file *file, loff_t *foffset)
-{
-	static const char buf[4] = { 0, };
-	DUMP_WRITE(buf, roundup(*foffset, 4) - *foffset, foffset);
-	return 1;
-}
-
-static int writenote(struct memelfnote *men, struct file *file,
-			loff_t *foffset)
+static int writenote(struct memelfnote *men, struct coredump_params *cprm)
 {
 	struct elf_note en;
 	en.n_namesz = strlen(men->name) + 1;
 	en.n_descsz = men->datasz;
 	en.n_type = men->type;
 
-	DUMP_WRITE(&en, sizeof(en), foffset);
-	DUMP_WRITE(men->name, en.n_namesz, foffset);
-	if (!alignfile(file, foffset))
-		return 0;
-	DUMP_WRITE(men->data, men->datasz, foffset);
-	if (!alignfile(file, foffset))
-		return 0;
-
-	return 1;
+	return dump_emit(cprm, &en, sizeof(en)) &&
+	    dump_emit(cprm, men->name, en.n_namesz) && dump_align(cprm, 4) &&
+	    dump_emit(cprm, men->data, men->datasz) && dump_align(cprm, 4);
 }
-#undef DUMP_WRITE
 
 static void fill_elf_header(struct elfhdr *elf, int segs,
 			    u16 machine, u32 flags)
@@ -1392,7 +1374,7 @@ static void fill_auxv_note(struct memelfnote *note, struct mm_struct *mm)
 }
 
 static void fill_siginfo_note(struct memelfnote *note, user_siginfo_t *csigdata,
-		siginfo_t *siginfo)
+		const siginfo_t *siginfo)
 {
 	mm_segment_t old_fs = get_fs();
 	set_fs(KERNEL_DS);
@@ -1599,7 +1581,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 
 static int fill_note_info(struct elfhdr *elf, int phdrs,
 			  struct elf_note_info *info,
-			  siginfo_t *siginfo, struct pt_regs *regs)
+			  const siginfo_t *siginfo, struct pt_regs *regs)
 {
 	struct task_struct *dump_task = current;
 	const struct user_regset_view *view = task_user_regset_view(dump_task);
@@ -1702,7 +1684,7 @@ static size_t get_note_info_size(struct elf_note_info *info)
  * process-wide notes are interleaved after the first thread-specific note.
  */
 static int write_note_info(struct elf_note_info *info,
-			   struct file *file, loff_t *foffset)
+			   struct coredump_params *cprm)
 {
 	bool first = 1;
 	struct elf_thread_core_info *t = info->thread;
@@ -1710,22 +1692,22 @@ static int write_note_info(struct elf_note_info *info,
 	do {
 		int i;
 
-		if (!writenote(&t->notes[0], file, foffset))
+		if (!writenote(&t->notes[0], cprm))
 			return 0;
 
-		if (first && !writenote(&info->psinfo, file, foffset))
+		if (first && !writenote(&info->psinfo, cprm))
 			return 0;
-		if (first && !writenote(&info->signote, file, foffset))
+		if (first && !writenote(&info->signote, cprm))
 			return 0;
-		if (first && !writenote(&info->auxv, file, foffset))
+		if (first && !writenote(&info->auxv, cprm))
 			return 0;
 		if (first && info->files.data &&
-				!writenote(&info->files, file, foffset))
+				!writenote(&info->files, cprm))
 			return 0;
 
 		for (i = 1; i < info->thread_notes; ++i)
 			if (t->notes[i].data &&
-			    !writenote(&t->notes[i], file, foffset))
+			    !writenote(&t->notes[i], cprm))
 				return 0;
 
 		first = 0;
@@ -1848,34 +1830,31 @@ static int elf_note_info_init(struct elf_note_info *info)
 
 static int fill_note_info(struct elfhdr *elf, int phdrs,
 			  struct elf_note_info *info,
-			  siginfo_t *siginfo, struct pt_regs *regs)
+			  const siginfo_t *siginfo, struct pt_regs *regs)
 {
 	struct list_head *t;
+	struct core_thread *ct;
+	struct elf_thread_status *ets;
 
 	if (!elf_note_info_init(info))
 		return 0;
 
-	if (siginfo->si_signo) {
-		struct core_thread *ct;
-		struct elf_thread_status *ets;
-
-		for (ct = current->mm->core_state->dumper.next;
-						ct; ct = ct->next) {
-			ets = kzalloc(sizeof(*ets), GFP_KERNEL);
-			if (!ets)
-				return 0;
+	for (ct = current->mm->core_state->dumper.next;
+					ct; ct = ct->next) {
+		ets = kzalloc(sizeof(*ets), GFP_KERNEL);
+		if (!ets)
+			return 0;
 
-			ets->thread = ct->task;
-			list_add(&ets->list, &info->thread_list);
-		}
+		ets->thread = ct->task;
+		list_add(&ets->list, &info->thread_list);
+	}
 
-		list_for_each(t, &info->thread_list) {
-			int sz;
+	list_for_each(t, &info->thread_list) {
+		int sz;
 
-			ets = list_entry(t, struct elf_thread_status, list);
-			sz = elf_dump_thread_status(siginfo->si_signo, ets);
-			info->thread_status_size += sz;
-		}
+		ets = list_entry(t, struct elf_thread_status, list);
+		sz = elf_dump_thread_status(siginfo->si_signo, ets);
+		info->thread_status_size += sz;
 	}
 	/* now collect the dump for the current */
 	memset(info->prstatus, 0, sizeof(*info->prstatus));
@@ -1935,13 +1914,13 @@ static size_t get_note_info_size(struct elf_note_info *info)
 }
 
 static int write_note_info(struct elf_note_info *info,
-			   struct file *file, loff_t *foffset)
+			   struct coredump_params *cprm)
 {
 	int i;
 	struct list_head *t;
 
 	for (i = 0; i < info->numnote; i++)
-		if (!writenote(info->notes + i, file, foffset))
+		if (!writenote(info->notes + i, cprm))
 			return 0;
 
 	/* write out the thread status notes section */
@@ -1950,7 +1929,7 @@ static int write_note_info(struct elf_note_info *info,
 				list_entry(t, struct elf_thread_status, list);
 
 		for (i = 0; i < tmp->num_notes; i++)
-			if (!writenote(&tmp->notes[i], file, foffset))
+			if (!writenote(&tmp->notes[i], cprm))
 				return 0;
 	}
 
@@ -2046,10 +2025,9 @@ static int elf_core_dump(struct coredump_params *cprm)
 	int has_dumped = 0;
 	mm_segment_t fs;
 	int segs;
-	size_t size = 0;
 	struct vm_area_struct *vma, *gate_vma;
 	struct elfhdr *elf = NULL;
-	loff_t offset = 0, dataoff, foffset;
+	loff_t offset = 0, dataoff;
 	struct elf_note_info info = { };
 	struct elf_phdr *phdr4note = NULL;
 	struct elf_shdr *shdr4extnum = NULL;
@@ -2105,7 +2083,6 @@ static int elf_core_dump(struct coredump_params *cprm)
 
 	offset += sizeof(*elf);				/* Elf header */
 	offset += segs * sizeof(struct elf_phdr);	/* Program headers */
-	foffset = offset;
 
 	/* Write notes phdr entry */
 	{
@@ -2136,13 +2113,10 @@ static int elf_core_dump(struct coredump_params *cprm)
 
 	offset = dataoff;
 
-	size += sizeof(*elf);
-	if (size > cprm->limit || !dump_write(cprm->file, elf, sizeof(*elf)))
+	if (!dump_emit(cprm, elf, sizeof(*elf)))
 		goto end_coredump;
 
-	size += sizeof(*phdr4note);
-	if (size > cprm->limit
-	    || !dump_write(cprm->file, phdr4note, sizeof(*phdr4note)))
+	if (!dump_emit(cprm, phdr4note, sizeof(*phdr4note)))
 		goto end_coredump;
 
 	/* Write program headers for segments dump */
@@ -2164,24 +2138,22 @@ static int elf_core_dump(struct coredump_params *cprm)
 			phdr.p_flags |= PF_X;
 		phdr.p_align = ELF_EXEC_PAGESIZE;
 
-		size += sizeof(phdr);
-		if (size > cprm->limit
-		    || !dump_write(cprm->file, &phdr, sizeof(phdr)))
+		if (!dump_emit(cprm, &phdr, sizeof(phdr)))
 			goto end_coredump;
 	}
 
-	if (!elf_core_write_extra_phdrs(cprm->file, offset, &size, cprm->limit))
+	if (!elf_core_write_extra_phdrs(cprm, offset))
 		goto end_coredump;
 
  	/* write out the notes section */
-	if (!write_note_info(&info, cprm->file, &foffset))
+	if (!write_note_info(&info, cprm))
 		goto end_coredump;
 
-	if (elf_coredump_extra_notes_write(cprm->file, &foffset))
+	if (elf_coredump_extra_notes_write(cprm))
 		goto end_coredump;
 
 	/* Align to page */
-	if (!dump_seek(cprm->file, dataoff - foffset))
+	if (!dump_skip(cprm, dataoff - cprm->written))
 		goto end_coredump;
 
 	for (vma = first_vma(current, gate_vma); vma != NULL;
@@ -2198,26 +2170,21 @@ static int elf_core_dump(struct coredump_params *cprm)
 			page = get_dump_page(addr);
 			if (page) {
 				void *kaddr = kmap(page);
-				stop = ((size += PAGE_SIZE) > cprm->limit) ||
-					!dump_write(cprm->file, kaddr,
-						    PAGE_SIZE);
+				stop = !dump_emit(cprm, kaddr, PAGE_SIZE);
 				kunmap(page);
 				page_cache_release(page);
 			} else
-				stop = !dump_seek(cprm->file, PAGE_SIZE);
+				stop = !dump_skip(cprm, PAGE_SIZE);
 			if (stop)
 				goto end_coredump;
 		}
 	}
 
-	if (!elf_core_write_extra_data(cprm->file, &size, cprm->limit))
+	if (!elf_core_write_extra_data(cprm))
 		goto end_coredump;
 
 	if (e_phnum == PN_XNUM) {
-		size += sizeof(*shdr4extnum);
-		if (size > cprm->limit
-		    || !dump_write(cprm->file, shdr4extnum,
-				   sizeof(*shdr4extnum)))
+		if (!dump_emit(cprm, shdr4extnum, sizeof(*shdr4extnum)))
 			goto end_coredump;
 	}
 

fs/binfmt_elf_fdpic.c

@@ -111,7 +111,7 @@ static int is_elf_fdpic(struct elfhdr *hdr, struct file *file)
 		return 0;
 	if (!elf_check_arch(hdr) || !elf_check_fdpic(hdr))
 		return 0;
-	if (!file->f_op || !file->f_op->mmap)
+	if (!file->f_op->mmap)
 		return 0;
 	return 1;
 }
@@ -1267,35 +1267,17 @@ static int notesize(struct memelfnote *en)
 
 /* #define DEBUG */
 
-#define DUMP_WRITE(addr, nr, foffset)	\
-	do { if (!dump_write(file, (addr), (nr))) return 0; *foffset += (nr); } while(0)
-
-static int alignfile(struct file *file, loff_t *foffset)
-{
-	static const char buf[4] = { 0, };
-	DUMP_WRITE(buf, roundup(*foffset, 4) - *foffset, foffset);
-	return 1;
-}
-
-static int writenote(struct memelfnote *men, struct file *file,
-			loff_t *foffset)
+static int writenote(struct memelfnote *men, struct coredump_params *cprm)
 {
 	struct elf_note en;
 	en.n_namesz = strlen(men->name) + 1;
 	en.n_descsz = men->datasz;
 	en.n_type = men->type;
 
-	DUMP_WRITE(&en, sizeof(en), foffset);
-	DUMP_WRITE(men->name, en.n_namesz, foffset);
-	if (!alignfile(file, foffset))
-		return 0;
-	DUMP_WRITE(men->data, men->datasz, foffset);
-	if (!alignfile(file, foffset))
-		return 0;
-
-	return 1;
+	return dump_emit(cprm, &en, sizeof(en)) &&
+		dump_emit(cprm, men->name, en.n_namesz) && dump_align(cprm, 4) &&
+		dump_emit(cprm, men->data, men->datasz) && dump_align(cprm, 4);
 }
-#undef DUMP_WRITE
 
 static inline void fill_elf_fdpic_header(struct elfhdr *elf, int segs)
 {
@@ -1500,66 +1482,40 @@ static void fill_extnum_info(struct elfhdr *elf, struct elf_shdr *shdr4extnum,
 /*
  * dump the segments for an MMU process
  */
-#ifdef CONFIG_MMU
-static int elf_fdpic_dump_segments(struct file *file, size_t *size,
-			   unsigned long *limit, unsigned long mm_flags)
+static bool elf_fdpic_dump_segments(struct coredump_params *cprm)
 {
 	struct vm_area_struct *vma;
-	int err = 0;
 
 	for (vma = current->mm->mmap; vma; vma = vma->vm_next) {
 		unsigned long addr;
 
-		if (!maydump(vma, mm_flags))
+		if (!maydump(vma, cprm->mm_flags))
 			continue;
 
+#ifdef CONFIG_MMU
 		for (addr = vma->vm_start; addr < vma->vm_end;
 							addr += PAGE_SIZE) {
+			bool res;
 			struct page *page = get_dump_page(addr);
 			if (page) {
 				void *kaddr = kmap(page);
-				*size += PAGE_SIZE;
-				if (*size > *limit)
-					err = -EFBIG;
-				else if (!dump_write(file, kaddr, PAGE_SIZE))
-					err = -EIO;
+				res = dump_emit(cprm, kaddr, PAGE_SIZE);
 				kunmap(page);
 				page_cache_release(page);
-			} else if (!dump_seek(file, PAGE_SIZE))
-				err = -EFBIG;
-			if (err)
-				goto out;
+			} else {
+				res = dump_skip(cprm, PAGE_SIZE);
+			}
+			if (!res)
+				return false;
 		}
-	}
-out:
-	return err;
-}
-#endif
-
-/*
- * dump the segments for a NOMMU process
- */
-#ifndef CONFIG_MMU
-static int elf_fdpic_dump_segments(struct file *file, size_t *size,
-			   unsigned long *limit, unsigned long mm_flags)
-{
-	struct vm_area_struct *vma;
-
-	for (vma = current->mm->mmap; vma; vma = vma->vm_next) {
-		if (!maydump(vma, mm_flags))
-			continue;
-
-		if ((*size += PAGE_SIZE) > *limit)
-			return -EFBIG;
-
-		if (!dump_write(file, (void *) vma->vm_start,
+#else
+		if (!dump_emit(cprm, (void *) vma->vm_start,
 				vma->vm_end - vma->vm_start))
-			return -EIO;
+			return false;
+#endif
 	}
-
-	return 0;
+	return true;
 }
-#endif
 
 static size_t elf_core_vma_data_size(unsigned long mm_flags)
 {
@@ -1585,11 +1541,10 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	int has_dumped = 0;
 	mm_segment_t fs;
 	int segs;
-	size_t size = 0;
 	int i;
 	struct vm_area_struct *vma;
 	struct elfhdr *elf = NULL;
-	loff_t offset = 0, dataoff, foffset;
+	loff_t offset = 0, dataoff;
 	int numnote;
 	struct memelfnote *notes = NULL;
 	struct elf_prstatus *prstatus = NULL;	/* NT_PRSTATUS */
@@ -1606,6 +1561,8 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	struct elf_shdr *shdr4extnum = NULL;
 	Elf_Half e_phnum;
 	elf_addr_t e_shoff;
+	struct core_thread *ct;
+	struct elf_thread_status *tmp;
 
 	/*
 	 * We no longer stop all VM operations.
@@ -1641,28 +1598,23 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 		goto cleanup;
 #endif
 
-	if (cprm->siginfo->si_signo) {
-		struct core_thread *ct;
-		struct elf_thread_status *tmp;
-
-		for (ct = current->mm->core_state->dumper.next;
-						ct; ct = ct->next) {
-			tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
-			if (!tmp)
-				goto cleanup;
+	for (ct = current->mm->core_state->dumper.next;
+					ct; ct = ct->next) {
+		tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
+		if (!tmp)
+			goto cleanup;
 
-			tmp->thread = ct->task;
-			list_add(&tmp->list, &thread_list);
-		}
+		tmp->thread = ct->task;
+		list_add(&tmp->list, &thread_list);
+	}
 
-		list_for_each(t, &thread_list) {
-			struct elf_thread_status *tmp;
-			int sz;
+	list_for_each(t, &thread_list) {
+		struct elf_thread_status *tmp;
+		int sz;
 
-			tmp = list_entry(t, struct elf_thread_status, list);
-			sz = elf_dump_thread_status(cprm->siginfo->si_signo, tmp);
-			thread_status_size += sz;
-		}
+		tmp = list_entry(t, struct elf_thread_status, list);
+		sz = elf_dump_thread_status(cprm->siginfo->si_signo, tmp);
+		thread_status_size += sz;
 	}
 
 	/* now collect the dump for the current */
@@ -1720,7 +1672,6 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 
 	offset += sizeof(*elf);				/* Elf header */
 	offset += segs * sizeof(struct elf_phdr);	/* Program headers */
-	foffset = offset;
 
 	/* Write notes phdr entry */
 	{
@@ -1755,13 +1706,10 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 
 	offset = dataoff;
 
-	size += sizeof(*elf);
-	if (size > cprm->limit || !dump_write(cprm->file, elf, sizeof(*elf)))
+	if (!dump_emit(cprm, elf, sizeof(*elf)))
 		goto end_coredump;
 
-	size += sizeof(*phdr4note);
-	if (size > cprm->limit
-	    || !dump_write(cprm->file, phdr4note, sizeof(*phdr4note)))
+	if (!dump_emit(cprm, phdr4note, sizeof(*phdr4note)))
 		goto end_coredump;
 
 	/* write program headers for segments dump */
@@ -1785,18 +1733,16 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 			phdr.p_flags |= PF_X;
 		phdr.p_align = ELF_EXEC_PAGESIZE;
 
-		size += sizeof(phdr);
-		if (size > cprm->limit
-		    || !dump_write(cprm->file, &phdr, sizeof(phdr)))
+		if (!dump_emit(cprm, &phdr, sizeof(phdr)))
 			goto end_coredump;
 	}
 
-	if (!elf_core_write_extra_phdrs(cprm->file, offset, &size, cprm->limit))
+	if (!elf_core_write_extra_phdrs(cprm, offset))
 		goto end_coredump;
 
  	/* write out the notes section */
 	for (i = 0; i < numnote; i++)
-		if (!writenote(notes + i, cprm->file, &foffset))
+		if (!writenote(notes + i, cprm))
 			goto end_coredump;
 
 	/* write out the thread status notes section */
@@ -1805,25 +1751,21 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 				list_entry(t, struct elf_thread_status, list);
 
 		for (i = 0; i < tmp->num_notes; i++)
-			if (!writenote(&tmp->notes[i], cprm->file, &foffset))
+			if (!writenote(&tmp->notes[i], cprm))
 				goto end_coredump;
 	}
 
-	if (!dump_seek(cprm->file, dataoff - foffset))
+	if (!dump_skip(cprm, dataoff - cprm->written))
 		goto end_coredump;
 
-	if (elf_fdpic_dump_segments(cprm->file, &size, &cprm->limit,
-				    cprm->mm_flags) < 0)
+	if (!elf_fdpic_dump_segments(cprm))
 		goto end_coredump;
 
-	if (!elf_core_write_extra_data(cprm->file, &size, cprm->limit))
+	if (!elf_core_write_extra_data(cprm))
 		goto end_coredump;
 
 	if (e_phnum == PN_XNUM) {
-		size += sizeof(*shdr4extnum);
-		if (size > cprm->limit
-		    || !dump_write(cprm->file, shdr4extnum,
-				   sizeof(*shdr4extnum)))
+		if (!dump_emit(cprm, shdr4extnum, sizeof(*shdr4extnum)))
 			goto end_coredump;
 	}
 

fs/binfmt_em86.c

@@ -38,7 +38,7 @@ static int load_em86(struct linux_binprm *bprm)
 	/* First of all, some simple consistency checks */
 	if ((elf_ex.e_type != ET_EXEC && elf_ex.e_type != ET_DYN) ||
 		(!((elf_ex.e_machine == EM_386) || (elf_ex.e_machine == EM_486))) ||
-		(!bprm->file->f_op || !bprm->file->f_op->mmap)) {
+		!bprm->file->f_op->mmap) {
 			return -ENOEXEC;
 	}
 

fs/cachefiles/interface.c

@@ -449,14 +449,14 @@ static int cachefiles_attr_changed(struct fscache_object *_object)
 		_debug("discard tail %llx", oi_size);
 		newattrs.ia_valid = ATTR_SIZE;
 		newattrs.ia_size = oi_size & PAGE_MASK;
-		ret = notify_change(object->backer, &newattrs);
+		ret = notify_change(object->backer, &newattrs, NULL);
 		if (ret < 0)
 			goto truncate_failed;
 	}
 
 	newattrs.ia_valid = ATTR_SIZE;
 	newattrs.ia_size = ni_size;
-	ret = notify_change(object->backer, &newattrs);
+	ret = notify_change(object->backer, &newattrs, NULL);
 
 truncate_failed:
 	mutex_unlock(&object->backer->d_inode->i_mutex);

fs/cachefiles/namei.c

@@ -294,7 +294,7 @@ static int cachefiles_bury_object(struct cachefiles_cache *cache,
 		if (ret < 0) {
 			cachefiles_io_error(cache, "Unlink security error");
 		} else {
-			ret = vfs_unlink(dir->d_inode, rep);
+			ret = vfs_unlink(dir->d_inode, rep, NULL);
 
 			if (preemptive)
 				cachefiles_mark_object_buried(cache, rep);
@@ -396,7 +396,7 @@ try_again:
 		cachefiles_io_error(cache, "Rename security error %d", ret);
 	} else {
 		ret = vfs_rename(dir->d_inode, rep,
-				 cache->graveyard->d_inode, grave);
+				 cache->graveyard->d_inode, grave, NULL);
 		if (ret != 0 && ret != -ENOMEM)
 			cachefiles_io_error(cache,
 					    "Rename failed with error %d", ret);

fs/char_dev.c

@@ -368,6 +368,7 @@ void cdev_put(struct cdev *p)
  */
 static int chrdev_open(struct inode *inode, struct file *filp)
 {
+	const struct file_operations *fops;
 	struct cdev *p;
 	struct cdev *new = NULL;
 	int ret = 0;
@@ -400,10 +401,11 @@ static int chrdev_open(struct inode *inode, struct file *filp)
 		return ret;
 
 	ret = -ENXIO;
-	filp->f_op = fops_get(p->ops);
-	if (!filp->f_op)
+	fops = fops_get(p->ops);
+	if (!fops)
 		goto out_cdev_put;
 
+	replace_fops(filp, fops);
 	if (filp->f_op->open) {
 		ret = filp->f_op->open(inode, filp);
 		if (ret)

fs/cifs/cifs_fs_sb.h

@@ -65,5 +65,6 @@ struct cifs_sb_info {
 	char   *mountdata; /* options received at mount time or via DFS refs */
 	struct backing_dev_info bdi;
 	struct delayed_work prune_tlinks;
+	struct rcu_head rcu;
 };
 #endif				/* _CIFS_FS_SB_H */

fs/cifs/cifsfs.c

@@ -862,7 +862,7 @@ const struct inode_operations cifs_file_inode_ops = {
 const struct inode_operations cifs_symlink_inode_ops = {
 	.readlink = generic_readlink,
 	.follow_link = cifs_follow_link,
-	.put_link = cifs_put_link,
+	.put_link = kfree_put_link,
 	.permission = cifs_permission,
 	/* BB add the following two eventually */
 	/* revalidate: cifs_revalidate,

fs/cifs/cifsfs.h

@@ -115,8 +115,6 @@ extern struct vfsmount *cifs_dfs_d_automount(struct path *path);
 
 /* Functions related to symlinks */
 extern void *cifs_follow_link(struct dentry *direntry, struct nameidata *nd);
-extern void cifs_put_link(struct dentry *direntry,
-			  struct nameidata *nd, void *);
 extern int cifs_readlink(struct dentry *direntry, char __user *buffer,
 			 int buflen);
 extern int cifs_symlink(struct inode *inode, struct dentry *direntry,

fs/cifs/connect.c

@@ -3770,6 +3770,13 @@ CIFSTCon(const unsigned int xid, struct cifs_ses *ses,
 	return rc;
 }
 
+static void delayed_free(struct rcu_head *p)
+{
+	struct cifs_sb_info *sbi = container_of(p, struct cifs_sb_info, rcu);
+	unload_nls(sbi->local_nls);
+	kfree(sbi);
+}
+
 void
 cifs_umount(struct cifs_sb_info *cifs_sb)
 {
@@ -3794,8 +3801,7 @@ cifs_umount(struct cifs_sb_info *cifs_sb)
 
 	bdi_destroy(&cifs_sb->bdi);
 	kfree(cifs_sb->mountdata);
-	unload_nls(cifs_sb->local_nls);
-	kfree(cifs_sb);
+	call_rcu(&cifs_sb->rcu, delayed_free);
 }
 
 int

fs/cifs/link.c

@@ -621,10 +621,3 @@ symlink_exit:
 	free_xid(xid);
 	return rc;
 }
-
-void cifs_put_link(struct dentry *direntry, struct nameidata *nd, void *cookie)
-{
-	char *p = nd_get_link(nd);
-	if (!IS_ERR(p))
-		kfree(p);
-}

fs/coda/coda_linux.h

@@ -40,7 +40,7 @@ extern const struct file_operations coda_ioctl_operations;
 int coda_open(struct inode *i, struct file *f);
 int coda_release(struct inode *i, struct file *f);
 int coda_permission(struct inode *inode, int mask);
-int coda_revalidate_inode(struct dentry *);
+int coda_revalidate_inode(struct inode *);
 int coda_getattr(struct vfsmount *, struct dentry *, struct kstat *);
 int coda_setattr(struct dentry *, struct iattr *);
 

fs/coda/dir.c

@@ -387,9 +387,6 @@ static int coda_readdir(struct file *coda_file, struct dir_context *ctx)
 	BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
 	host_file = cfi->cfi_container;
 
-	if (!host_file->f_op)
-		return -ENOTDIR;
-
 	if (host_file->f_op->iterate) {
 		struct inode *host_inode = file_inode(host_file);
 		mutex_lock(&host_inode->i_mutex);
@@ -566,13 +563,12 @@ static int coda_dentry_delete(const struct dentry * dentry)
  * cache manager Venus issues a downcall to the kernel when this 
  * happens 
  */
-int coda_revalidate_inode(struct dentry *dentry)
+int coda_revalidate_inode(struct inode *inode)
 {
 	struct coda_vattr attr;
 	int error;
 	int old_mode;
 	ino_t old_ino;
-	struct inode *inode = dentry->d_inode;
 	struct coda_inode_info *cii = ITOC(inode);
 
 	if (!cii->c_flags)

fs/coda/file.c

@@ -36,7 +36,7 @@ coda_file_read(struct file *coda_file, char __user *buf, size_t count, loff_t *p
 	BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
 	host_file = cfi->cfi_container;
 
-	if (!host_file->f_op || !host_file->f_op->read)
+	if (!host_file->f_op->read)
 		return -EINVAL;
 
 	return host_file->f_op->read(host_file, buf, count, ppos);
@@ -75,7 +75,7 @@ coda_file_write(struct file *coda_file, const char __user *buf, size_t count, lo
 	BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
 	host_file = cfi->cfi_container;
 
-	if (!host_file->f_op || !host_file->f_op->write)
+	if (!host_file->f_op->write)
 		return -EINVAL;
 
 	host_inode = file_inode(host_file);
@@ -105,7 +105,7 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma)
 	BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
 	host_file = cfi->cfi_container;
 
-	if (!host_file->f_op || !host_file->f_op->mmap)
+	if (!host_file->f_op->mmap)
 		return -ENODEV;
 
 	coda_inode = file_inode(coda_file);

fs/coda/inode.c

@@ -257,7 +257,7 @@ static void coda_evict_inode(struct inode *inode)
 
 int coda_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 {
-	int err = coda_revalidate_inode(dentry);
+	int err = coda_revalidate_inode(dentry->d_inode);
 	if (!err)
 		generic_fillattr(dentry->d_inode, stat);
 	return err;

fs/compat_ioctl.c

@@ -1583,13 +1583,13 @@ asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd,
 		/*FALL THROUGH*/
 
 	default:
-		if (f.file->f_op && f.file->f_op->compat_ioctl) {
+		if (f.file->f_op->compat_ioctl) {
 			error = f.file->f_op->compat_ioctl(f.file, cmd, arg);
 			if (error != -ENOIOCTLCMD)
 				goto out_fput;
 		}
 
-		if (!f.file->f_op || !f.file->f_op->unlocked_ioctl)
+		if (!f.file->f_op->unlocked_ioctl)
 			goto do_ioctl;
 		break;
 	}

fs/coredump.c

@@ -485,7 +485,7 @@ static int umh_pipe_setup(struct subprocess_info *info, struct cred *new)
 	return err;
 }
 
-void do_coredump(siginfo_t *siginfo)
+void do_coredump(const siginfo_t *siginfo)
 {
 	struct core_state core_state;
 	struct core_name cn;
@@ -645,7 +645,7 @@ void do_coredump(siginfo_t *siginfo)
 		 */
 		if (!uid_eq(inode->i_uid, current_fsuid()))
 			goto close_fail;
-		if (!cprm.file->f_op || !cprm.file->f_op->write)
+		if (!cprm.file->f_op->write)
 			goto close_fail;
 		if (do_truncate(cprm.file->f_path.dentry, 0, 0, cprm.file))
 			goto close_fail;
@@ -685,40 +685,55 @@ fail:
  * do on a core-file: use only these functions to write out all the
  * necessary info.
  */
-int dump_write(struct file *file, const void *addr, int nr)
+int dump_emit(struct coredump_params *cprm, const void *addr, int nr)
 {
-	return !dump_interrupted() &&
-		access_ok(VERIFY_READ, addr, nr) &&
-		file->f_op->write(file, addr, nr, &file->f_pos) == nr;
+	struct file *file = cprm->file;
+	loff_t pos = file->f_pos;
+	ssize_t n;
+	if (cprm->written + nr > cprm->limit)
+		return 0;
+	while (nr) {
+		if (dump_interrupted())
+			return 0;
+		n = vfs_write(file, addr, nr, &pos);
+		if (n <= 0)
+			return 0;
+		file->f_pos = pos;
+		cprm->written += n;
+		nr -= n;
+	}
+	return 1;
 }
-EXPORT_SYMBOL(dump_write);
+EXPORT_SYMBOL(dump_emit);
 
-int dump_seek(struct file *file, loff_t off)
+int dump_skip(struct coredump_params *cprm, size_t nr)
 {
-	int ret = 1;
-
+	static char zeroes[PAGE_SIZE];
+	struct file *file = cprm->file;
 	if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
+		if (cprm->written + nr > cprm->limit)
+			return 0;
 		if (dump_interrupted() ||
-		    file->f_op->llseek(file, off, SEEK_CUR) < 0)
+		    file->f_op->llseek(file, nr, SEEK_CUR) < 0)
 			return 0;
+		cprm->written += nr;
+		return 1;
 	} else {
-		char *buf = (char *)get_zeroed_page(GFP_KERNEL);
-
-		if (!buf)
-			return 0;
-		while (off > 0) {
-			unsigned long n = off;
-
-			if (n > PAGE_SIZE)
-				n = PAGE_SIZE;
-			if (!dump_write(file, buf, n)) {
-				ret = 0;
-				break;
-			}
-			off -= n;
+		while (nr > PAGE_SIZE) {
+			if (!dump_emit(cprm, zeroes, PAGE_SIZE))
+				return 0;
+			nr -= PAGE_SIZE;
 		}
-		free_page((unsigned long)buf);
+		return dump_emit(cprm, zeroes, nr);
 	}
-	return ret;
 }
-EXPORT_SYMBOL(dump_seek);
+EXPORT_SYMBOL(dump_skip);
+
+int dump_align(struct coredump_params *cprm, int align)
+{
+	unsigned mod = cprm->written & (align - 1);
+	if (align & (align - 1))
+		return -EINVAL;
+	return mod ? dump_skip(cprm, align - mod) : 0;
+}
+EXPORT_SYMBOL(dump_align);

fs/dcache.c

@@ -343,6 +343,7 @@ static void dentry_unlink_inode(struct dentry * dentry)
 	__releases(dentry->d_inode->i_lock)
 {
 	struct inode *inode = dentry->d_inode;
+	__d_clear_type(dentry);
 	dentry->d_inode = NULL;
 	hlist_del_init(&dentry->d_alias);
 	dentry_rcuwalk_barrier(dentry);
@@ -483,27 +484,6 @@ static struct dentry *d_kill(struct dentry *dentry, struct dentry *parent)
 	return parent;
 }
 
-/*
- * Unhash a dentry without inserting an RCU walk barrier or checking that
- * dentry->d_lock is locked.  The caller must take care of that, if
- * appropriate.
- */
-static void __d_shrink(struct dentry *dentry)
-{
-	if (!d_unhashed(dentry)) {
-		struct hlist_bl_head *b;
-		if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED))
-			b = &dentry->d_sb->s_anon;
-		else
-			b = d_hash(dentry->d_parent, dentry->d_name.hash);
-
-		hlist_bl_lock(b);
-		__hlist_bl_del(&dentry->d_hash);
-		dentry->d_hash.pprev = NULL;
-		hlist_bl_unlock(b);
-	}
-}
-
 /**
  * d_drop - drop a dentry
  * @dentry: dentry to drop
@@ -522,7 +502,21 @@ static void __d_shrink(struct dentry *dentry)
 void __d_drop(struct dentry *dentry)
 {
 	if (!d_unhashed(dentry)) {
-		__d_shrink(dentry);
+		struct hlist_bl_head *b;
+		/*
+		 * Hashed dentries are normally on the dentry hashtable,
+		 * with the exception of those newly allocated by
+		 * d_obtain_alias, which are always IS_ROOT:
+		 */
+		if (unlikely(IS_ROOT(dentry)))
+			b = &dentry->d_sb->s_anon;
+		else
+			b = d_hash(dentry->d_parent, dentry->d_name.hash);
+
+		hlist_bl_lock(b);
+		__hlist_bl_del(&dentry->d_hash);
+		dentry->d_hash.pprev = NULL;
+		hlist_bl_unlock(b);
 		dentry_rcuwalk_barrier(dentry);
 	}
 }
@@ -1075,116 +1069,6 @@ void shrink_dcache_sb(struct super_block *sb)
 }
 EXPORT_SYMBOL(shrink_dcache_sb);
 
-/*
- * destroy a single subtree of dentries for unmount
- * - see the comments on shrink_dcache_for_umount() for a description of the
- *   locking
- */
-static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
-{
-	struct dentry *parent;
-
-	BUG_ON(!IS_ROOT(dentry));
-
-	for (;;) {
-		/* descend to the first leaf in the current subtree */
-		while (!list_empty(&dentry->d_subdirs))
-			dentry = list_entry(dentry->d_subdirs.next,
-					    struct dentry, d_u.d_child);
-
-		/* consume the dentries from this leaf up through its parents
-		 * until we find one with children or run out altogether */
-		do {
-			struct inode *inode;
-
-			/*
-			 * inform the fs that this dentry is about to be
-			 * unhashed and destroyed.
-			 */
-			if ((dentry->d_flags & DCACHE_OP_PRUNE) &&
-			    !d_unhashed(dentry))
-				dentry->d_op->d_prune(dentry);
-
-			dentry_lru_del(dentry);
-			__d_shrink(dentry);
-
-			if (dentry->d_lockref.count != 0) {
-				printk(KERN_ERR
-				       "BUG: Dentry %p{i=%lx,n=%s}"
-				       " still in use (%d)"
-				       " [unmount of %s %s]\n",
-				       dentry,
-				       dentry->d_inode ?
-				       dentry->d_inode->i_ino : 0UL,
-				       dentry->d_name.name,
-				       dentry->d_lockref.count,
-				       dentry->d_sb->s_type->name,
-				       dentry->d_sb->s_id);
-				BUG();
-			}
-
-			if (IS_ROOT(dentry)) {
-				parent = NULL;
-				list_del(&dentry->d_u.d_child);
-			} else {
-				parent = dentry->d_parent;
-				parent->d_lockref.count--;
-				list_del(&dentry->d_u.d_child);
-			}
-
-			inode = dentry->d_inode;
-			if (inode) {
-				dentry->d_inode = NULL;
-				hlist_del_init(&dentry->d_alias);
-				if (dentry->d_op && dentry->d_op->d_iput)
-					dentry->d_op->d_iput(dentry, inode);
-				else
-					iput(inode);
-			}
-
-			d_free(dentry);
-
-			/* finished when we fall off the top of the tree,
-			 * otherwise we ascend to the parent and move to the
-			 * next sibling if there is one */
-			if (!parent)
-				return;
-			dentry = parent;
-		} while (list_empty(&dentry->d_subdirs));
-
-		dentry = list_entry(dentry->d_subdirs.next,
-				    struct dentry, d_u.d_child);
-	}
-}
-
-/*
- * destroy the dentries attached to a superblock on unmounting
- * - we don't need to use dentry->d_lock because:
- *   - the superblock is detached from all mountings and open files, so the
- *     dentry trees will not be rearranged by the VFS
- *   - s_umount is write-locked, so the memory pressure shrinker will ignore
- *     any dentries belonging to this superblock that it comes across
- *   - the filesystem itself is no longer permitted to rearrange the dentries
- *     in this superblock
- */
-void shrink_dcache_for_umount(struct super_block *sb)
-{
-	struct dentry *dentry;
-
-	if (down_read_trylock(&sb->s_umount))
-		BUG();
-
-	dentry = sb->s_root;
-	sb->s_root = NULL;
-	dentry->d_lockref.count--;
-	shrink_dcache_for_umount_subtree(dentry);
-
-	while (!hlist_bl_empty(&sb->s_anon)) {
-		dentry = hlist_bl_entry(hlist_bl_first(&sb->s_anon), struct dentry, d_hash);
-		shrink_dcache_for_umount_subtree(dentry);
-	}
-}
-
 /*
  * This tries to ascend one level of parenthood, but
  * we can race with renaming, so we need to re-check
@@ -1478,6 +1362,91 @@ void shrink_dcache_parent(struct dentry *parent)
 }
 EXPORT_SYMBOL(shrink_dcache_parent);
 
+static enum d_walk_ret umount_collect(void *_data, struct dentry *dentry)
+{
+	struct select_data *data = _data;
+	enum d_walk_ret ret = D_WALK_CONTINUE;
+
+	if (dentry->d_lockref.count) {
+		dentry_lru_del(dentry);
+		if (likely(!list_empty(&dentry->d_subdirs)))
+			goto out;
+		if (dentry == data->start && dentry->d_lockref.count == 1)
+			goto out;
+		printk(KERN_ERR
+		       "BUG: Dentry %p{i=%lx,n=%s}"
+		       " still in use (%d)"
+		       " [unmount of %s %s]\n",
+		       dentry,
+		       dentry->d_inode ?
+		       dentry->d_inode->i_ino : 0UL,
+		       dentry->d_name.name,
+		       dentry->d_lockref.count,
+		       dentry->d_sb->s_type->name,
+		       dentry->d_sb->s_id);
+		BUG();
+	} else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) {
+		/*
+		 * We can't use d_lru_shrink_move() because we
+		 * need to get the global LRU lock and do the
+		 * LRU accounting.
+		 */
+		if (dentry->d_flags & DCACHE_LRU_LIST)
+			d_lru_del(dentry);
+		d_shrink_add(dentry, &data->dispose);
+		data->found++;
+		ret = D_WALK_NORETRY;
+	}
+out:
+	if (data->found && need_resched())
+		ret = D_WALK_QUIT;
+	return ret;
+}
+
+/*
+ * destroy the dentries attached to a superblock on unmounting
+ */
+void shrink_dcache_for_umount(struct super_block *sb)
+{
+	struct dentry *dentry;
+
+	if (down_read_trylock(&sb->s_umount))
+		BUG();
+
+	dentry = sb->s_root;
+	sb->s_root = NULL;
+	for (;;) {
+		struct select_data data;
+
+		INIT_LIST_HEAD(&data.dispose);
+		data.start = dentry;
+		data.found = 0;
+
+		d_walk(dentry, &data, umount_collect, NULL);
+		if (!data.found)
+			break;
+
+		shrink_dentry_list(&data.dispose);
+		cond_resched();
+	}
+	d_drop(dentry);
+	dput(dentry);
+
+	while (!hlist_bl_empty(&sb->s_anon)) {
+		struct select_data data;
+		dentry = hlist_bl_entry(hlist_bl_first(&sb->s_anon), struct dentry, d_hash);
+
+		INIT_LIST_HEAD(&data.dispose);
+		data.start = NULL;
+		data.found = 0;
+
+		d_walk(dentry, &data, umount_collect, NULL);
+		if (data.found)
+			shrink_dentry_list(&data.dispose);
+		cond_resched();
+	}
+}
+
 static enum d_walk_ret check_and_collect(void *_data, struct dentry *dentry)
 {
 	struct select_data *data = _data;
@@ -1638,12 +1607,17 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
 }
 EXPORT_SYMBOL(d_alloc);
 
+/**
+ * d_alloc_pseudo - allocate a dentry (for lookup-less filesystems)
+ * @sb: the superblock
+ * @name: qstr of the name
+ *
+ * For a filesystem that just pins its dentries in memory and never
+ * performs lookups at all, return an unhashed IS_ROOT dentry.
+ */
 struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name)
 {
-	struct dentry *dentry = __d_alloc(sb, name);
-	if (dentry)
-		dentry->d_flags |= DCACHE_DISCONNECTED;
-	return dentry;
+	return __d_alloc(sb, name);
 }
 EXPORT_SYMBOL(d_alloc_pseudo);
 
@@ -1685,14 +1659,42 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
 }
 EXPORT_SYMBOL(d_set_d_op);
 
+static unsigned d_flags_for_inode(struct inode *inode)
+{
+	unsigned add_flags = DCACHE_FILE_TYPE;
+
+	if (!inode)
+		return DCACHE_MISS_TYPE;
+
+	if (S_ISDIR(inode->i_mode)) {
+		add_flags = DCACHE_DIRECTORY_TYPE;
+		if (unlikely(!(inode->i_opflags & IOP_LOOKUP))) {
+			if (unlikely(!inode->i_op->lookup))
+				add_flags = DCACHE_AUTODIR_TYPE;
+			else
+				inode->i_opflags |= IOP_LOOKUP;
+		}
+	} else if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) {
+		if (unlikely(inode->i_op->follow_link))
+			add_flags = DCACHE_SYMLINK_TYPE;
+		else
+			inode->i_opflags |= IOP_NOFOLLOW;
+	}
+
+	if (unlikely(IS_AUTOMOUNT(inode)))
+		add_flags |= DCACHE_NEED_AUTOMOUNT;
+	return add_flags;
+}
+
 static void __d_instantiate(struct dentry *dentry, struct inode *inode)
 {
+	unsigned add_flags = d_flags_for_inode(inode);
+
 	spin_lock(&dentry->d_lock);
-	if (inode) {
-		if (unlikely(IS_AUTOMOUNT(inode)))
-			dentry->d_flags |= DCACHE_NEED_AUTOMOUNT;
+	dentry->d_flags &= ~DCACHE_ENTRY_TYPE;
+	dentry->d_flags |= add_flags;
+	if (inode)
 		hlist_add_head(&dentry->d_alias, &inode->i_dentry);
-	}
 	dentry->d_inode = inode;
 	dentry_rcuwalk_barrier(dentry);
 	spin_unlock(&dentry->d_lock);
@@ -1801,6 +1803,33 @@ struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode)
 
 EXPORT_SYMBOL(d_instantiate_unique);
 
+/**
+ * d_instantiate_no_diralias - instantiate a non-aliased dentry
+ * @entry: dentry to complete
+ * @inode: inode to attach to this dentry
+ *
+ * Fill in inode information in the entry.  If a directory alias is found, then
+ * return an error (and drop inode).  Together with d_materialise_unique() this
+ * guarantees that a directory inode may never have more than one alias.
+ */
+int d_instantiate_no_diralias(struct dentry *entry, struct inode *inode)
+{
+	BUG_ON(!hlist_unhashed(&entry->d_alias));
+
+	spin_lock(&inode->i_lock);
+	if (S_ISDIR(inode->i_mode) && !hlist_empty(&inode->i_dentry)) {
+		spin_unlock(&inode->i_lock);
+		iput(inode);
+		return -EBUSY;
+	}
+	__d_instantiate(entry, inode);
+	spin_unlock(&inode->i_lock);
+	security_d_instantiate(entry, inode);
+
+	return 0;
+}
+EXPORT_SYMBOL(d_instantiate_no_diralias);
+
 struct dentry *d_make_root(struct inode *root_inode)
 {
 	struct dentry *res = NULL;
@@ -1870,6 +1899,7 @@ struct dentry *d_obtain_alias(struct inode *inode)
 	static const struct qstr anonstring = QSTR_INIT("/", 1);
 	struct dentry *tmp;
 	struct dentry *res;
+	unsigned add_flags;
 
 	if (!inode)
 		return ERR_PTR(-ESTALE);
@@ -1895,9 +1925,11 @@ struct dentry *d_obtain_alias(struct inode *inode)
 	}
 
 	/* attach a disconnected dentry */
+	add_flags = d_flags_for_inode(inode) | DCACHE_DISCONNECTED;
+
 	spin_lock(&tmp->d_lock);
 	tmp->d_inode = inode;
-	tmp->d_flags |= DCACHE_DISCONNECTED;
+	tmp->d_flags |= add_flags;
 	hlist_add_head(&tmp->d_alias, &inode->i_dentry);
 	hlist_bl_lock(&tmp->d_sb->s_anon);
 	hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_anon);
@@ -2725,7 +2757,6 @@ static void __d_materialise_dentry(struct dentry *dentry, struct dentry *anon)
 	spin_unlock(&dentry->d_lock);
 
 	/* anon->d_lock still locked, returns locked */
-	anon->d_flags &= ~DCACHE_DISCONNECTED;
 }
 
 /**
@@ -2885,23 +2916,28 @@ static int prepend_path(const struct path *path,
 	struct vfsmount *vfsmnt = path->mnt;
 	struct mount *mnt = real_mount(vfsmnt);
 	int error = 0;
-	unsigned seq = 0;
+	unsigned seq, m_seq = 0;
 	char *bptr;
 	int blen;
 
 	rcu_read_lock();
+restart_mnt:
+	read_seqbegin_or_lock(&mount_lock, &m_seq);
+	seq = 0;
 restart:
 	bptr = *buffer;
 	blen = *buflen;
+	error = 0;
 	read_seqbegin_or_lock(&rename_lock, &seq);
 	while (dentry != root->dentry || vfsmnt != root->mnt) {
 		struct dentry * parent;
 
 		if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) {
+			struct mount *parent = ACCESS_ONCE(mnt->mnt_parent);
 			/* Global root? */
-			if (mnt_has_parent(mnt)) {
-				dentry = mnt->mnt_mountpoint;
-				mnt = mnt->mnt_parent;
+			if (mnt != parent) {
+				dentry = ACCESS_ONCE(mnt->mnt_mountpoint);
+				mnt = parent;
 				vfsmnt = &mnt->mnt;
 				continue;
 			}
@@ -2935,6 +2971,11 @@ restart:
 		goto restart;
 	}
 	done_seqretry(&rename_lock, seq);
+	if (need_seqretry(&mount_lock, m_seq)) {
+		m_seq = 1;
+		goto restart_mnt;
+	}
+	done_seqretry(&mount_lock, m_seq);
 
 	if (error >= 0 && bptr == *buffer) {
 		if (--blen < 0)
@@ -2971,9 +3012,7 @@ char *__d_path(const struct path *path,
 	int error;
 
 	prepend(&res, &buflen, "\0", 1);
-	br_read_lock(&vfsmount_lock);
 	error = prepend_path(path, root, &res, &buflen);
-	br_read_unlock(&vfsmount_lock);
 
 	if (error < 0)
 		return ERR_PTR(error);
@@ -2990,9 +3029,7 @@ char *d_absolute_path(const struct path *path,
 	int error;
 
 	prepend(&res, &buflen, "\0", 1);
-	br_read_lock(&vfsmount_lock);
 	error = prepend_path(path, &root, &res, &buflen);
-	br_read_unlock(&vfsmount_lock);
 
 	if (error > 1)
 		error = -EINVAL;
@@ -3067,9 +3104,7 @@ char *d_path(const struct path *path, char *buf, int buflen)
 
 	rcu_read_lock();
 	get_fs_root_rcu(current->fs, &root);
-	br_read_lock(&vfsmount_lock);
 	error = path_with_deleted(path, &root, &res, &buflen);
-	br_read_unlock(&vfsmount_lock);
 	rcu_read_unlock();
 
 	if (error < 0)
@@ -3224,7 +3259,6 @@ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size)
 	get_fs_root_and_pwd_rcu(current->fs, &root, &pwd);
 
 	error = -ENOENT;
-	br_read_lock(&vfsmount_lock);
 	if (!d_unlinked(pwd.dentry)) {
 		unsigned long len;
 		char *cwd = page + PATH_MAX;
@@ -3232,7 +3266,6 @@ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size)
 
 		prepend(&cwd, &buflen, "\0", 1);
 		error = prepend_path(&pwd, &root, &cwd, &buflen);
-		br_read_unlock(&vfsmount_lock);
 		rcu_read_unlock();
 
 		if (error < 0)
@@ -3253,7 +3286,6 @@ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size)
 				error = -EFAULT;
 		}
 	} else {
-		br_read_unlock(&vfsmount_lock);
 		rcu_read_unlock();
 	}
 

fs/ecryptfs/dentry.c

@@ -44,15 +44,15 @@
  */
 static int ecryptfs_d_revalidate(struct dentry *dentry, unsigned int flags)
 {
-	struct dentry *lower_dentry;
-	int rc = 1;
+	struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
+	int rc;
+
+	if (!(lower_dentry->d_flags & DCACHE_OP_REVALIDATE))
+		return 1;
 
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
-	lower_dentry = ecryptfs_dentry_to_lower(dentry);
-	if (!lower_dentry->d_op || !lower_dentry->d_op->d_revalidate)
-		goto out;
 	rc = lower_dentry->d_op->d_revalidate(lower_dentry, flags);
 	if (dentry->d_inode) {
 		struct inode *lower_inode =
@@ -60,12 +60,17 @@ static int ecryptfs_d_revalidate(struct dentry *dentry, unsigned int flags)
 
 		fsstack_copy_attr_all(dentry->d_inode, lower_inode);
 	}
-out:
 	return rc;
 }
 
 struct kmem_cache *ecryptfs_dentry_info_cache;
 
+static void ecryptfs_dentry_free_rcu(struct rcu_head *head)
+{
+	kmem_cache_free(ecryptfs_dentry_info_cache,
+		container_of(head, struct ecryptfs_dentry_info, rcu));
+}
+
 /**
  * ecryptfs_d_release
  * @dentry: The ecryptfs dentry
@@ -74,15 +79,11 @@ struct kmem_cache *ecryptfs_dentry_info_cache;
  */
 static void ecryptfs_d_release(struct dentry *dentry)
 {
-	if (ecryptfs_dentry_to_private(dentry)) {
-		if (ecryptfs_dentry_to_lower(dentry)) {
-			dput(ecryptfs_dentry_to_lower(dentry));
-			mntput(ecryptfs_dentry_to_lower_mnt(dentry));
-		}
-		kmem_cache_free(ecryptfs_dentry_info_cache,
-				ecryptfs_dentry_to_private(dentry));
+	struct ecryptfs_dentry_info *p = dentry->d_fsdata;
+	if (p) {
+		path_put(&p->lower_path);
+		call_rcu(&p->rcu, ecryptfs_dentry_free_rcu);
 	}
-	return;
 }
 
 const struct dentry_operations ecryptfs_dops = {

fs/ecryptfs/ecryptfs_kernel.h

@@ -261,7 +261,10 @@ struct ecryptfs_inode_info {
  * vfsmount too. */
 struct ecryptfs_dentry_info {
 	struct path lower_path;
-	struct ecryptfs_crypt_stat *crypt_stat;
+	union {
+		struct ecryptfs_crypt_stat *crypt_stat;
+		struct rcu_head rcu;
+	};
 };
 
 /**
@@ -512,13 +515,6 @@ ecryptfs_dentry_to_lower(struct dentry *dentry)
 	return ((struct ecryptfs_dentry_info *)dentry->d_fsdata)->lower_path.dentry;
 }
 
-static inline void
-ecryptfs_set_dentry_lower(struct dentry *dentry, struct dentry *lower_dentry)
-{
-	((struct ecryptfs_dentry_info *)dentry->d_fsdata)->lower_path.dentry =
-		lower_dentry;
-}
-
 static inline struct vfsmount *
 ecryptfs_dentry_to_lower_mnt(struct dentry *dentry)
 {
@@ -531,13 +527,6 @@ ecryptfs_dentry_to_lower_path(struct dentry *dentry)
 	return &((struct ecryptfs_dentry_info *)dentry->d_fsdata)->lower_path;
 }
 
-static inline void
-ecryptfs_set_dentry_lower_mnt(struct dentry *dentry, struct vfsmount *lower_mnt)
-{
-	((struct ecryptfs_dentry_info *)dentry->d_fsdata)->lower_path.mnt =
-		lower_mnt;
-}
-
 #define ecryptfs_printk(type, fmt, arg...) \
         __ecryptfs_printk(type "%s: " fmt, __func__, ## arg);
 __printf(1, 2)

fs/ecryptfs/file.c

@@ -271,7 +271,7 @@ static int ecryptfs_flush(struct file *file, fl_owner_t td)
 {
 	struct file *lower_file = ecryptfs_file_to_lower(file);
 
-	if (lower_file->f_op && lower_file->f_op->flush) {
+	if (lower_file->f_op->flush) {
 		filemap_write_and_wait(file->f_mapping);
 		return lower_file->f_op->flush(lower_file, td);
 	}
@@ -305,7 +305,7 @@ static int ecryptfs_fasync(int fd, struct file *file, int flag)
 	struct file *lower_file = NULL;
 
 	lower_file = ecryptfs_file_to_lower(file);
-	if (lower_file->f_op && lower_file->f_op->fasync)
+	if (lower_file->f_op->fasync)
 		rc = lower_file->f_op->fasync(fd, lower_file, flag);
 	return rc;
 }
@@ -318,7 +318,7 @@ ecryptfs_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 	if (ecryptfs_file_to_private(file))
 		lower_file = ecryptfs_file_to_lower(file);
-	if (lower_file && lower_file->f_op && lower_file->f_op->unlocked_ioctl)
+	if (lower_file->f_op->unlocked_ioctl)
 		rc = lower_file->f_op->unlocked_ioctl(lower_file, cmd, arg);
 	return rc;
 }
@@ -332,7 +332,7 @@ ecryptfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 	if (ecryptfs_file_to_private(file))
 		lower_file = ecryptfs_file_to_lower(file);
-	if (lower_file && lower_file->f_op && lower_file->f_op->compat_ioctl)
+	if (lower_file->f_op && lower_file->f_op->compat_ioctl)
 		rc = lower_file->f_op->compat_ioctl(lower_file, cmd, arg);
 	return rc;
 }

fs/ecryptfs/inode.c

@@ -153,7 +153,7 @@ static int ecryptfs_do_unlink(struct inode *dir, struct dentry *dentry,
 
 	dget(lower_dentry);
 	lower_dir_dentry = lock_parent(lower_dentry);
-	rc = vfs_unlink(lower_dir_inode, lower_dentry);
+	rc = vfs_unlink(lower_dir_inode, lower_dentry, NULL);
 	if (rc) {
 		printk(KERN_ERR "Error in vfs_unlink; rc = [%d]\n", rc);
 		goto out_unlock;
@@ -208,7 +208,7 @@ ecryptfs_do_create(struct inode *directory_inode,
 	inode = __ecryptfs_get_inode(lower_dentry->d_inode,
 				     directory_inode->i_sb);
 	if (IS_ERR(inode)) {
-		vfs_unlink(lower_dir_dentry->d_inode, lower_dentry);
+		vfs_unlink(lower_dir_dentry->d_inode, lower_dentry, NULL);
 		goto out_lock;
 	}
 	fsstack_copy_attr_times(directory_inode, lower_dir_dentry->d_inode);
@@ -361,8 +361,8 @@ static int ecryptfs_lookup_interpose(struct dentry *dentry,
 	BUG_ON(!d_count(lower_dentry));
 
 	ecryptfs_set_dentry_private(dentry, dentry_info);
-	ecryptfs_set_dentry_lower(dentry, lower_dentry);
-	ecryptfs_set_dentry_lower_mnt(dentry, lower_mnt);
+	dentry_info->lower_path.mnt = lower_mnt;
+	dentry_info->lower_path.dentry = lower_dentry;
 
 	if (!lower_dentry->d_inode) {
 		/* We want to add because we couldn't find in lower */
@@ -475,7 +475,7 @@ static int ecryptfs_link(struct dentry *old_dentry, struct inode *dir,
 	dget(lower_new_dentry);
 	lower_dir_dentry = lock_parent(lower_new_dentry);
 	rc = vfs_link(lower_old_dentry, lower_dir_dentry->d_inode,
-		      lower_new_dentry);
+		      lower_new_dentry, NULL);
 	if (rc || !lower_new_dentry->d_inode)
 		goto out_lock;
 	rc = ecryptfs_interpose(lower_new_dentry, new_dentry, dir->i_sb);
@@ -640,7 +640,8 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		goto out_lock;
 	}
 	rc = vfs_rename(lower_old_dir_dentry->d_inode, lower_old_dentry,
-			lower_new_dir_dentry->d_inode, lower_new_dentry);
+			lower_new_dir_dentry->d_inode, lower_new_dentry,
+			NULL);
 	if (rc)
 		goto out_lock;
 	if (target_inode)
@@ -703,16 +704,6 @@ out:
 	return NULL;
 }
 
-static void
-ecryptfs_put_link(struct dentry *dentry, struct nameidata *nd, void *ptr)
-{
-	char *buf = nd_get_link(nd);
-	if (!IS_ERR(buf)) {
-		/* Free the char* */
-		kfree(buf);
-	}
-}
-
 /**
  * upper_size_to_lower_size
  * @crypt_stat: Crypt_stat associated with file
@@ -891,7 +882,7 @@ int ecryptfs_truncate(struct dentry *dentry, loff_t new_length)
 		struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
 
 		mutex_lock(&lower_dentry->d_inode->i_mutex);
-		rc = notify_change(lower_dentry, &lower_ia);
+		rc = notify_change(lower_dentry, &lower_ia, NULL);
 		mutex_unlock(&lower_dentry->d_inode->i_mutex);
 	}
 	return rc;
@@ -992,7 +983,7 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia)
 		lower_ia.ia_valid &= ~ATTR_MODE;
 
 	mutex_lock(&lower_dentry->d_inode->i_mutex);
-	rc = notify_change(lower_dentry, &lower_ia);
+	rc = notify_change(lower_dentry, &lower_ia, NULL);
 	mutex_unlock(&lower_dentry->d_inode->i_mutex);
 out:
 	fsstack_copy_attr_all(inode, lower_inode);
@@ -1121,7 +1112,7 @@ out:
 const struct inode_operations ecryptfs_symlink_iops = {
 	.readlink = generic_readlink,
 	.follow_link = ecryptfs_follow_link,
-	.put_link = ecryptfs_put_link,
+	.put_link = kfree_put_link,
 	.permission = ecryptfs_permission,
 	.setattr = ecryptfs_setattr,
 	.getattr = ecryptfs_getattr_link,

fs/ecryptfs/main.c

@@ -585,8 +585,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 
 	/* ->kill_sb() will take care of root_info */
 	ecryptfs_set_dentry_private(s->s_root, root_info);
-	ecryptfs_set_dentry_lower(s->s_root, path.dentry);
-	ecryptfs_set_dentry_lower_mnt(s->s_root, path.mnt);
+	root_info->lower_path = path;
 
 	s->s_flags |= MS_ACTIVE;
 	return dget(s->s_root);

fs/eventpoll.c

@@ -1814,7 +1814,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 
 	/* The target file descriptor must support poll */
 	error = -EPERM;
-	if (!tf.file->f_op || !tf.file->f_op->poll)
+	if (!tf.file->f_op->poll)
 		goto error_tgt_fput;
 
 	/* Check if EPOLLWAKEUP is allowed */

fs/exec.c

@@ -106,6 +106,7 @@ static inline void put_binfmt(struct linux_binfmt * fmt)
  */
 SYSCALL_DEFINE1(uselib, const char __user *, library)
 {
+	struct linux_binfmt *fmt;
 	struct file *file;
 	struct filename *tmp = getname(library);
 	int error = PTR_ERR(tmp);
@@ -136,24 +137,21 @@ SYSCALL_DEFINE1(uselib, const char __user *, library)
 	fsnotify_open(file);
 
 	error = -ENOEXEC;
-	if(file->f_op) {
-		struct linux_binfmt * fmt;
 
-		read_lock(&binfmt_lock);
-		list_for_each_entry(fmt, &formats, lh) {
-			if (!fmt->load_shlib)
-				continue;
-			if (!try_module_get(fmt->module))
-				continue;
-			read_unlock(&binfmt_lock);
-			error = fmt->load_shlib(file);
-			read_lock(&binfmt_lock);
-			put_binfmt(fmt);
-			if (error != -ENOEXEC)
-				break;
-		}
+	read_lock(&binfmt_lock);
+	list_for_each_entry(fmt, &formats, lh) {
+		if (!fmt->load_shlib)
+			continue;
+		if (!try_module_get(fmt->module))
+			continue;
 		read_unlock(&binfmt_lock);
+		error = fmt->load_shlib(file);
+		read_lock(&binfmt_lock);
+		put_binfmt(fmt);
+		if (error != -ENOEXEC)
+			break;
 	}
+	read_unlock(&binfmt_lock);
 exit:
 	fput(file);
 out:
@@ -1277,13 +1275,10 @@ static int check_unsafe_exec(struct linux_binprm *bprm)
  */
 int prepare_binprm(struct linux_binprm *bprm)
 {
-	umode_t mode;
-	struct inode * inode = file_inode(bprm->file);
+	struct inode *inode = file_inode(bprm->file);
+	umode_t mode = inode->i_mode;
 	int retval;
 
-	mode = inode->i_mode;
-	if (bprm->file->f_op == NULL)
-		return -EACCES;
 
 	/* clear any previous set[ug]id data from a previous binary */
 	bprm->cred->euid = current_euid();

fs/exportfs/expfs.c

@@ -69,145 +69,162 @@ find_acceptable_alias(struct dentry *result,
 	return NULL;
 }
 
-/*
- * Find root of a disconnected subtree and return a reference to it.
- */
-static struct dentry *
-find_disconnected_root(struct dentry *dentry)
+static bool dentry_connected(struct dentry *dentry)
 {
 	dget(dentry);
-	while (!IS_ROOT(dentry)) {
+	while (dentry->d_flags & DCACHE_DISCONNECTED) {
 		struct dentry *parent = dget_parent(dentry);
 
-		if (!(parent->d_flags & DCACHE_DISCONNECTED)) {
+		dput(dentry);
+		if (IS_ROOT(dentry)) {
 			dput(parent);
-			break;
+			return false;
 		}
+		dentry = parent;
+	}
+	dput(dentry);
+	return true;
+}
+
+static void clear_disconnected(struct dentry *dentry)
+{
+	dget(dentry);
+	while (dentry->d_flags & DCACHE_DISCONNECTED) {
+		struct dentry *parent = dget_parent(dentry);
+
+		WARN_ON_ONCE(IS_ROOT(dentry));
+
+		spin_lock(&dentry->d_lock);
+		dentry->d_flags &= ~DCACHE_DISCONNECTED;
+		spin_unlock(&dentry->d_lock);
 
 		dput(dentry);
 		dentry = parent;
 	}
-	return dentry;
+	dput(dentry);
+}
+
+/*
+ * Reconnect a directory dentry with its parent.
+ *
+ * This can return a dentry, or NULL, or an error.
+ *
+ * In the first case the returned dentry is the parent of the given
+ * dentry, and may itself need to be reconnected to its parent.
+ *
+ * In the NULL case, a concurrent VFS operation has either renamed or
+ * removed this directory.  The concurrent operation has reconnected our
+ * dentry, so we no longer need to.
+ */
+static struct dentry *reconnect_one(struct vfsmount *mnt,
+		struct dentry *dentry, char *nbuf)
+{
+	struct dentry *parent;
+	struct dentry *tmp;
+	int err;
+
+	parent = ERR_PTR(-EACCES);
+	mutex_lock(&dentry->d_inode->i_mutex);
+	if (mnt->mnt_sb->s_export_op->get_parent)
+		parent = mnt->mnt_sb->s_export_op->get_parent(dentry);
+	mutex_unlock(&dentry->d_inode->i_mutex);
+
+	if (IS_ERR(parent)) {
+		dprintk("%s: get_parent of %ld failed, err %d\n",
+			__func__, dentry->d_inode->i_ino, PTR_ERR(parent));
+		return parent;
+	}
+
+	dprintk("%s: find name of %lu in %lu\n", __func__,
+		dentry->d_inode->i_ino, parent->d_inode->i_ino);
+	err = exportfs_get_name(mnt, parent, nbuf, dentry);
+	if (err == -ENOENT)
+		goto out_reconnected;
+	if (err)
+		goto out_err;
+	dprintk("%s: found name: %s\n", __func__, nbuf);
+	mutex_lock(&parent->d_inode->i_mutex);
+	tmp = lookup_one_len(nbuf, parent, strlen(nbuf));
+	mutex_unlock(&parent->d_inode->i_mutex);
+	if (IS_ERR(tmp)) {
+		dprintk("%s: lookup failed: %d\n", __func__, PTR_ERR(tmp));
+		goto out_err;
+	}
+	if (tmp != dentry) {
+		dput(tmp);
+		goto out_reconnected;
+	}
+	dput(tmp);
+	if (IS_ROOT(dentry)) {
+		err = -ESTALE;
+		goto out_err;
+	}
+	return parent;
+
+out_err:
+	dput(parent);
+	return ERR_PTR(err);
+out_reconnected:
+	dput(parent);
+	/*
+	 * Someone must have renamed our entry into another parent, in
+	 * which case it has been reconnected by the rename.
+	 *
+	 * Or someone removed it entirely, in which case filehandle
+	 * lookup will succeed but the directory is now IS_DEAD and
+	 * subsequent operations on it will fail.
+	 *
+	 * Alternatively, maybe there was no race at all, and the
+	 * filesystem is just corrupt and gave us a parent that doesn't
+	 * actually contain any entry pointing to this inode.  So,
+	 * double check that this worked and return -ESTALE if not:
+	 */
+	if (!dentry_connected(dentry))
+		return ERR_PTR(-ESTALE);
+	return NULL;
 }
 
 /*
  * Make sure target_dir is fully connected to the dentry tree.
  *
- * It may already be, as the flag isn't always updated when connection happens.
+ * On successful return, DCACHE_DISCONNECTED will be cleared on
+ * target_dir, and target_dir->d_parent->...->d_parent will reach the
+ * root of the filesystem.
+ *
+ * Whenever DCACHE_DISCONNECTED is unset, target_dir is fully connected.
+ * But the converse is not true: target_dir may have DCACHE_DISCONNECTED
+ * set but already be connected.  In that case we'll verify the
+ * connection to root and then clear the flag.
+ *
+ * Note that target_dir could be removed by a concurrent operation.  In
+ * that case reconnect_path may still succeed with target_dir fully
+ * connected, but further operations using the filehandle will fail when
+ * necessary (due to S_DEAD being set on the directory).
  */
 static int
 reconnect_path(struct vfsmount *mnt, struct dentry *target_dir, char *nbuf)
 {
-	int noprogress = 0;
-	int err = -ESTALE;
+	struct dentry *dentry, *parent;
 
-	/*
-	 * It is possible that a confused file system might not let us complete
-	 * the path to the root.  For example, if get_parent returns a directory
-	 * in which we cannot find a name for the child.  While this implies a
-	 * very sick filesystem we don't want it to cause knfsd to spin.  Hence
-	 * the noprogress counter.  If we go through the loop 10 times (2 is
-	 * probably enough) without getting anywhere, we just give up
-	 */
-	while (target_dir->d_flags & DCACHE_DISCONNECTED && noprogress++ < 10) {
-		struct dentry *pd = find_disconnected_root(target_dir);
-
-		if (!IS_ROOT(pd)) {
-			/* must have found a connected parent - great */
-			spin_lock(&pd->d_lock);
-			pd->d_flags &= ~DCACHE_DISCONNECTED;
-			spin_unlock(&pd->d_lock);
-			noprogress = 0;
-		} else if (pd == mnt->mnt_sb->s_root) {
-			printk(KERN_ERR "export: Eeek filesystem root is not connected, impossible\n");
-			spin_lock(&pd->d_lock);
-			pd->d_flags &= ~DCACHE_DISCONNECTED;
-			spin_unlock(&pd->d_lock);
-			noprogress = 0;
-		} else {
-			/*
-			 * We have hit the top of a disconnected path, try to
-			 * find parent and connect.
-			 *
-			 * Racing with some other process renaming a directory
-			 * isn't much of a problem here.  If someone renames
-			 * the directory, it will end up properly connected,
-			 * which is what we want
-			 *
-			 * Getting the parent can't be supported generically,
-			 * the locking is too icky.
-			 *
-			 * Instead we just return EACCES.  If server reboots
-			 * or inodes get flushed, you lose
-			 */
-			struct dentry *ppd = ERR_PTR(-EACCES);
-			struct dentry *npd;
-
-			mutex_lock(&pd->d_inode->i_mutex);
-			if (mnt->mnt_sb->s_export_op->get_parent)
-				ppd = mnt->mnt_sb->s_export_op->get_parent(pd);
-			mutex_unlock(&pd->d_inode->i_mutex);
-
-			if (IS_ERR(ppd)) {
-				err = PTR_ERR(ppd);
-				dprintk("%s: get_parent of %ld failed, err %d\n",
-					__func__, pd->d_inode->i_ino, err);
-				dput(pd);
-				break;
-			}
+	dentry = dget(target_dir);
 
-			dprintk("%s: find name of %lu in %lu\n", __func__,
-				pd->d_inode->i_ino, ppd->d_inode->i_ino);
-			err = exportfs_get_name(mnt, ppd, nbuf, pd);
-			if (err) {
-				dput(ppd);
-				dput(pd);
-				if (err == -ENOENT)
-					/* some race between get_parent and
-					 * get_name?  just try again
-					 */
-					continue;
-				break;
-			}
-			dprintk("%s: found name: %s\n", __func__, nbuf);
-			mutex_lock(&ppd->d_inode->i_mutex);
-			npd = lookup_one_len(nbuf, ppd, strlen(nbuf));
-			mutex_unlock(&ppd->d_inode->i_mutex);
-			if (IS_ERR(npd)) {
-				err = PTR_ERR(npd);
-				dprintk("%s: lookup failed: %d\n",
-					__func__, err);
-				dput(ppd);
-				dput(pd);
-				break;
-			}
-			/* we didn't really want npd, we really wanted
-			 * a side-effect of the lookup.
-			 * hopefully, npd == pd, though it isn't really
-			 * a problem if it isn't
-			 */
-			if (npd == pd)
-				noprogress = 0;
-			else
-				printk("%s: npd != pd\n", __func__);
-			dput(npd);
-			dput(ppd);
-			if (IS_ROOT(pd)) {
-				/* something went wrong, we have to give up */
-				dput(pd);
-				break;
-			}
-		}
-		dput(pd);
-	}
+	while (dentry->d_flags & DCACHE_DISCONNECTED) {
+		BUG_ON(dentry == mnt->mnt_sb->s_root);
 
-	if (target_dir->d_flags & DCACHE_DISCONNECTED) {
-		/* something went wrong - oh-well */
-		if (!err)
-			err = -ESTALE;
-		return err;
-	}
+		if (IS_ROOT(dentry))
+			parent = reconnect_one(mnt, dentry, nbuf);
+		else
+			parent = dget_parent(dentry);
 
+		if (!parent)
+			break;
+		dput(dentry);
+		if (IS_ERR(parent))
+			return PTR_ERR(parent);
+		dentry = parent;
+	}
+	dput(dentry);
+	clear_disconnected(target_dir);
 	return 0;
 }
 
@@ -215,7 +232,7 @@ struct getdents_callback {
 	struct dir_context ctx;
 	char *name;		/* name that was found. It already points to a
 				   buffer NAME_MAX+1 is size */
-	unsigned long ino;	/* the inum we are looking for */
+	u64 ino;		/* the inum we are looking for */
 	int found;		/* inode matched? */
 	int sequence;		/* sequence counter */
 };
@@ -255,10 +272,14 @@ static int get_name(const struct path *path, char *name, struct dentry *child)
 	struct inode *dir = path->dentry->d_inode;
 	int error;
 	struct file *file;
+	struct kstat stat;
+	struct path child_path = {
+		.mnt = path->mnt,
+		.dentry = child,
+	};
 	struct getdents_callback buffer = {
 		.ctx.actor = filldir_one,
 		.name = name,
-		.ino = child->d_inode->i_ino
 	};
 
 	error = -ENOTDIR;
@@ -267,6 +288,16 @@ static int get_name(const struct path *path, char *name, struct dentry *child)
 	error = -EINVAL;
 	if (!dir->i_fop)
 		goto out;
+	/*
+	 * inode->i_ino is unsigned long, kstat->ino is u64, so the
+	 * former would be insufficient on 32-bit hosts when the
+	 * filesystem supports 64-bit inode numbers.  So we need to
+	 * actually call ->getattr, not just read i_ino:
+	 */
+	error = vfs_getattr_nosec(&child_path, &stat);
+	if (error)
+		return error;
+	buffer.ino = stat.ino;
 	/*
 	 * Open the directory ...
 	 */

fs/ext4/ext4.h

@@ -2734,8 +2734,6 @@ extern void ext4_double_down_write_data_sem(struct inode *first,
 					    struct inode *second);
 extern void ext4_double_up_write_data_sem(struct inode *orig_inode,
 					  struct inode *donor_inode);
-void ext4_inode_double_lock(struct inode *inode1, struct inode *inode2);
-void ext4_inode_double_unlock(struct inode *inode1, struct inode *inode2);
 extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
 			     __u64 start_orig, __u64 start_donor,
 			     __u64 len, __u64 *moved_len);

fs/ext4/ioctl.c

@@ -130,7 +130,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 
 	/* Protect orig inodes against a truncate and make sure,
 	 * that only 1 swap_inode_boot_loader is running. */
-	ext4_inode_double_lock(inode, inode_bl);
+	lock_two_nondirectories(inode, inode_bl);
 
 	truncate_inode_pages(&inode->i_data, 0);
 	truncate_inode_pages(&inode_bl->i_data, 0);
@@ -205,7 +205,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 	ext4_inode_resume_unlocked_dio(inode);
 	ext4_inode_resume_unlocked_dio(inode_bl);
 
-	ext4_inode_double_unlock(inode, inode_bl);
+	unlock_two_nondirectories(inode, inode_bl);
 
 	iput(inode_bl);
 

fs/ext4/move_extent.c

@@ -1202,42 +1202,6 @@ mext_check_arguments(struct inode *orig_inode,
 	return 0;
 }
 
-/**
- * ext4_inode_double_lock - Lock i_mutex on both @inode1 and @inode2
- *
- * @inode1:	the inode structure
- * @inode2:	the inode structure
- *
- * Lock two inodes' i_mutex
- */
-void
-ext4_inode_double_lock(struct inode *inode1, struct inode *inode2)
-{
-	BUG_ON(inode1 == inode2);
-	if (inode1 < inode2) {
-		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
-		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
-	} else {
-		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT);
-		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD);
-	}
-}
-
-/**
- * ext4_inode_double_unlock - Release i_mutex on both @inode1 and @inode2
- *
- * @inode1:     the inode that is released first
- * @inode2:     the inode that is released second
- *
- */
-
-void
-ext4_inode_double_unlock(struct inode *inode1, struct inode *inode2)
-{
-	mutex_unlock(&inode1->i_mutex);
-	mutex_unlock(&inode2->i_mutex);
-}
-
 /**
  * ext4_move_extents - Exchange the specified range of a file
  *
@@ -1327,7 +1291,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
 		return -EINVAL;
 	}
 	/* Protect orig and donor inodes against a truncate */
-	ext4_inode_double_lock(orig_inode, donor_inode);
+	lock_two_nondirectories(orig_inode, donor_inode);
 
 	/* Wait for all existing dio workers */
 	ext4_inode_block_unlocked_dio(orig_inode);
@@ -1535,7 +1499,7 @@ out:
 	ext4_double_up_write_data_sem(orig_inode, donor_inode);
 	ext4_inode_resume_unlocked_dio(orig_inode);
 	ext4_inode_resume_unlocked_dio(donor_inode);
-	ext4_inode_double_unlock(orig_inode, donor_inode);
+	unlock_two_nondirectories(orig_inode, donor_inode);
 
 	return ret;
 }

fs/fat/fat.h

@@ -102,6 +102,7 @@ struct msdos_sb_info {
 	struct hlist_head dir_hashtable[FAT_HASH_SIZE];
 
 	unsigned int dirty;           /* fs state before mount */
+	struct rcu_head rcu;
 };
 
 #define FAT_CACHE_VALID	0	/* special case for valid cache */

fs/fat/inode.c

@@ -548,6 +548,16 @@ static void fat_set_state(struct super_block *sb,
 	brelse(bh);
 }
 
+static void delayed_free(struct rcu_head *p)
+{
+	struct msdos_sb_info *sbi = container_of(p, struct msdos_sb_info, rcu);
+	unload_nls(sbi->nls_disk);
+	unload_nls(sbi->nls_io);
+	if (sbi->options.iocharset != fat_default_iocharset)
+		kfree(sbi->options.iocharset);
+	kfree(sbi);
+}
+
 static void fat_put_super(struct super_block *sb)
 {
 	struct msdos_sb_info *sbi = MSDOS_SB(sb);
@@ -557,14 +567,7 @@ static void fat_put_super(struct super_block *sb)
 	iput(sbi->fsinfo_inode);
 	iput(sbi->fat_inode);
 
-	unload_nls(sbi->nls_disk);
-	unload_nls(sbi->nls_io);
-
-	if (sbi->options.iocharset != fat_default_iocharset)
-		kfree(sbi->options.iocharset);
-
-	sb->s_fs_info = NULL;
-	kfree(sbi);
+	call_rcu(&sbi->rcu, delayed_free);
 }
 
 static struct kmem_cache *fat_inode_cachep;

fs/fcntl.c

@@ -56,7 +56,7 @@ static int setfl(int fd, struct file * filp, unsigned long arg)
 				return -EINVAL;
 	}
 
-	if (filp->f_op && filp->f_op->check_flags)
+	if (filp->f_op->check_flags)
 		error = filp->f_op->check_flags(arg);
 	if (error)
 		return error;
@@ -64,8 +64,7 @@ static int setfl(int fd, struct file * filp, unsigned long arg)
 	/*
 	 * ->fasync() is responsible for setting the FASYNC bit.
 	 */
-	if (((arg ^ filp->f_flags) & FASYNC) && filp->f_op &&
-			filp->f_op->fasync) {
+	if (((arg ^ filp->f_flags) & FASYNC) && filp->f_op->fasync) {
 		error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0);
 		if (error < 0)
 			goto out;

fs/file_table.c

@@ -36,8 +36,6 @@ struct files_stat_struct files_stat = {
 	.max_files = NR_FILE
 };
 
-DEFINE_STATIC_LGLOCK(files_lglock);
-
 /* SLAB cache for file structures */
 static struct kmem_cache *filp_cachep __read_mostly;
 
@@ -134,7 +132,6 @@ struct file *get_empty_filp(void)
 		return ERR_PTR(error);
 	}
 
-	INIT_LIST_HEAD(&f->f_u.fu_list);
 	atomic_long_set(&f->f_count, 1);
 	rwlock_init(&f->f_owner.lock);
 	spin_lock_init(&f->f_lock);
@@ -240,11 +237,11 @@ static void __fput(struct file *file)
 	locks_remove_flock(file);
 
 	if (unlikely(file->f_flags & FASYNC)) {
-		if (file->f_op && file->f_op->fasync)
+		if (file->f_op->fasync)
 			file->f_op->fasync(-1, file, 0);
 	}
 	ima_file_free(file);
-	if (file->f_op && file->f_op->release)
+	if (file->f_op->release)
 		file->f_op->release(inode, file);
 	security_file_free(file);
 	if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL &&
@@ -304,7 +301,6 @@ void fput(struct file *file)
 	if (atomic_long_dec_and_test(&file->f_count)) {
 		struct task_struct *task = current;
 
-		file_sb_list_del(file);
 		if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
 			init_task_work(&file->f_u.fu_rcuhead, ____fput);
 			if (!task_work_add(task, &file->f_u.fu_rcuhead, true))
@@ -333,7 +329,6 @@ void __fput_sync(struct file *file)
 {
 	if (atomic_long_dec_and_test(&file->f_count)) {
 		struct task_struct *task = current;
-		file_sb_list_del(file);
 		BUG_ON(!(task->flags & PF_KTHREAD));
 		__fput(file);
 	}
@@ -345,129 +340,10 @@ void put_filp(struct file *file)
 {
 	if (atomic_long_dec_and_test(&file->f_count)) {
 		security_file_free(file);
-		file_sb_list_del(file);
 		file_free(file);
 	}
 }
 
-static inline int file_list_cpu(struct file *file)
-{
-#ifdef CONFIG_SMP
-	return file->f_sb_list_cpu;
-#else
-	return smp_processor_id();
-#endif
-}
-
-/* helper for file_sb_list_add to reduce ifdefs */
-static inline void __file_sb_list_add(struct file *file, struct super_block *sb)
-{
-	struct list_head *list;
-#ifdef CONFIG_SMP
-	int cpu;
-	cpu = smp_processor_id();
-	file->f_sb_list_cpu = cpu;
-	list = per_cpu_ptr(sb->s_files, cpu);
-#else
-	list = &sb->s_files;
-#endif
-	list_add(&file->f_u.fu_list, list);
-}
-
-/**
- * file_sb_list_add - add a file to the sb's file list
- * @file: file to add
- * @sb: sb to add it to
- *
- * Use this function to associate a file with the superblock of the inode it
- * refers to.
- */
-void file_sb_list_add(struct file *file, struct super_block *sb)
-{
-	if (likely(!(file->f_mode & FMODE_WRITE)))
-		return;
-	if (!S_ISREG(file_inode(file)->i_mode))
-		return;
-	lg_local_lock(&files_lglock);
-	__file_sb_list_add(file, sb);
-	lg_local_unlock(&files_lglock);
-}
-
-/**
- * file_sb_list_del - remove a file from the sb's file list
- * @file: file to remove
- * @sb: sb to remove it from
- *
- * Use this function to remove a file from its superblock.
- */
-void file_sb_list_del(struct file *file)
-{
-	if (!list_empty(&file->f_u.fu_list)) {
-		lg_local_lock_cpu(&files_lglock, file_list_cpu(file));
-		list_del_init(&file->f_u.fu_list);
-		lg_local_unlock_cpu(&files_lglock, file_list_cpu(file));
-	}
-}
-
-#ifdef CONFIG_SMP
-
-/*
- * These macros iterate all files on all CPUs for a given superblock.
- * files_lglock must be held globally.
- */
-#define do_file_list_for_each_entry(__sb, __file)		\
-{								\
-	int i;							\
-	for_each_possible_cpu(i) {				\
-		struct list_head *list;				\
-		list = per_cpu_ptr((__sb)->s_files, i);		\
-		list_for_each_entry((__file), list, f_u.fu_list)
-
-#define while_file_list_for_each_entry				\
-	}							\
-}
-
-#else
-
-#define do_file_list_for_each_entry(__sb, __file)		\
-{								\
-	struct list_head *list;					\
-	list = &(sb)->s_files;					\
-	list_for_each_entry((__file), list, f_u.fu_list)
-
-#define while_file_list_for_each_entry				\
-}
-
-#endif
-
-/**
- *	mark_files_ro - mark all files read-only
- *	@sb: superblock in question
- *
- *	All files are marked read-only.  We don't care about pending
- *	delete files so this should be used in 'force' mode only.
- */
-void mark_files_ro(struct super_block *sb)
-{
-	struct file *f;
-
-	lg_global_lock(&files_lglock);
-	do_file_list_for_each_entry(sb, f) {
-		if (!file_count(f))
-			continue;
-		if (!(f->f_mode & FMODE_WRITE))
-			continue;
-		spin_lock(&f->f_lock);
-		f->f_mode &= ~FMODE_WRITE;
-		spin_unlock(&f->f_lock);
-		if (file_check_writeable(f) != 0)
-			continue;
-		__mnt_drop_write(f->f_path.mnt);
-		file_release_write(f);
-	} while_file_list_for_each_entry;
-	lg_global_unlock(&files_lglock);
-}
-
 void __init files_init(unsigned long mempages)
 { 
 	unsigned long n;
@@ -483,6 +359,5 @@ void __init files_init(unsigned long mempages)
 	n = (mempages * (PAGE_SIZE / 1024)) / 10;
 	files_stat.max_files = max_t(unsigned long, n, NR_FILE);
 	files_defer_init();
-	lg_lock_init(&files_lglock, "files_lglock");
 	percpu_counter_init(&nr_files, 0);
 } 

fs/fs-writeback.c

@@ -26,6 +26,7 @@
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
 #include <linux/tracepoint.h>
+#include <linux/device.h>
 #include "internal.h"
 
 /*

fs/fuse/cuse.c

@@ -473,7 +473,7 @@ err:
 static void cuse_fc_release(struct fuse_conn *fc)
 {
 	struct cuse_conn *cc = fc_to_cc(fc);
-	kfree(cc);
+	kfree_rcu(cc, fc.rcu);
 }
 
 /**

fs/fuse/dir.c

@@ -342,24 +342,6 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, struct qstr *name,
 	return err;
 }
 
-static struct dentry *fuse_materialise_dentry(struct dentry *dentry,
-					      struct inode *inode)
-{
-	struct dentry *newent;
-
-	if (inode && S_ISDIR(inode->i_mode)) {
-		struct fuse_conn *fc = get_fuse_conn(inode);
-
-		mutex_lock(&fc->inst_mutex);
-		newent = d_materialise_unique(dentry, inode);
-		mutex_unlock(&fc->inst_mutex);
-	} else {
-		newent = d_materialise_unique(dentry, inode);
-	}
-
-	return newent;
-}
-
 static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
 				  unsigned int flags)
 {
@@ -382,7 +364,7 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
 	if (inode && get_node_id(inode) == FUSE_ROOT_ID)
 		goto out_iput;
 
-	newent = fuse_materialise_dentry(entry, inode);
+	newent = d_materialise_unique(entry, inode);
 	err = PTR_ERR(newent);
 	if (IS_ERR(newent))
 		goto out_err;
@@ -601,21 +583,9 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_req *req,
 	}
 	kfree(forget);
 
-	if (S_ISDIR(inode->i_mode)) {
-		struct dentry *alias;
-		mutex_lock(&fc->inst_mutex);
-		alias = d_find_alias(inode);
-		if (alias) {
-			/* New directory must have moved since mkdir */
-			mutex_unlock(&fc->inst_mutex);
-			dput(alias);
-			iput(inode);
-			return -EBUSY;
-		}
-		d_instantiate(entry, inode);
-		mutex_unlock(&fc->inst_mutex);
-	} else
-		d_instantiate(entry, inode);
+	err = d_instantiate_no_diralias(entry, inode);
+	if (err)
+		return err;
 
 	fuse_change_entry_timeout(entry, &outarg);
 	fuse_invalidate_attr(dir);
@@ -1284,7 +1254,7 @@ static int fuse_direntplus_link(struct file *file,
 	if (!inode)
 		goto out;
 
-	alias = fuse_materialise_dentry(dentry, inode);
+	alias = d_materialise_unique(dentry, inode);
 	err = PTR_ERR(alias);
 	if (IS_ERR(alias))
 		goto out;

fs/fuse/fuse_i.h

@@ -375,12 +375,11 @@ struct fuse_conn {
 	/** Lock protecting accessess to  members of this structure */
 	spinlock_t lock;
 
-	/** Mutex protecting against directory alias creation */
-	struct mutex inst_mutex;
-
 	/** Refcount */
 	atomic_t count;
 
+	struct rcu_head rcu;
+
 	/** The user id for this mount */
 	kuid_t user_id;
 

fs/fuse/inode.c

@@ -565,7 +565,6 @@ void fuse_conn_init(struct fuse_conn *fc)
 {
 	memset(fc, 0, sizeof(*fc));
 	spin_lock_init(&fc->lock);
-	mutex_init(&fc->inst_mutex);
 	init_rwsem(&fc->killsb);
 	atomic_set(&fc->count, 1);
 	init_waitqueue_head(&fc->waitq);
@@ -596,7 +595,6 @@ void fuse_conn_put(struct fuse_conn *fc)
 	if (atomic_dec_and_test(&fc->count)) {
 		if (fc->destroy_req)
 			fuse_request_free(fc->destroy_req);
-		mutex_destroy(&fc->inst_mutex);
 		fc->release(fc);
 	}
 }
@@ -920,7 +918,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
 
 static void fuse_free_conn(struct fuse_conn *fc)
 {
-	kfree(fc);
+	kfree_rcu(fc, rcu);
 }
 
 static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb)

fs/gfs2/inode.c

@@ -1514,13 +1514,6 @@ out:
 	return NULL;
 }
 
-static void gfs2_put_link(struct dentry *dentry, struct nameidata *nd, void *p)
-{
-	char *s = nd_get_link(nd);
-	if (!IS_ERR(s))
-		kfree(s);
-}
-
 /**
  * gfs2_permission -
  * @inode: The inode
@@ -1872,7 +1865,7 @@ const struct inode_operations gfs2_dir_iops = {
 const struct inode_operations gfs2_symlink_iops = {
 	.readlink = generic_readlink,
 	.follow_link = gfs2_follow_link,
-	.put_link = gfs2_put_link,
+	.put_link = kfree_put_link,
 	.permission = gfs2_permission,
 	.setattr = gfs2_setattr,
 	.getattr = gfs2_getattr,

fs/hpfs/hpfs_fn.h

@@ -80,6 +80,7 @@ struct hpfs_sb_info {
 	unsigned sb_c_bitmap;		/* current bitmap */
 	unsigned sb_max_fwd_alloc;	/* max forwad allocation */
 	int sb_timeshift;
+	struct rcu_head rcu;
 };
 
 /* Four 512-byte buffers and the 2k block obtained by concatenating them */

fs/hpfs/namei.c

@@ -407,7 +407,7 @@ again:
 			/*printk("HPFS: truncating file before delete.\n");*/
 			newattrs.ia_size = 0;
 			newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME;
-			err = notify_change(dentry, &newattrs);
+			err = notify_change(dentry, &newattrs, NULL);
 			put_write_access(inode);
 			if (!err)
 				goto again;

fs/hpfs/super.c

@@ -101,18 +101,24 @@ int hpfs_stop_cycles(struct super_block *s, int key, int *c1, int *c2,
 	return 0;
 }
 
-static void hpfs_put_super(struct super_block *s)
+static void free_sbi(struct hpfs_sb_info *sbi)
 {
-	struct hpfs_sb_info *sbi = hpfs_sb(s);
+	kfree(sbi->sb_cp_table);
+	kfree(sbi->sb_bmp_dir);
+	kfree(sbi);
+}
 
+static void lazy_free_sbi(struct rcu_head *rcu)
+{
+	free_sbi(container_of(rcu, struct hpfs_sb_info, rcu));
+}
+
+static void hpfs_put_super(struct super_block *s)
+{
 	hpfs_lock(s);
 	unmark_dirty(s);
 	hpfs_unlock(s);
-
-	kfree(sbi->sb_cp_table);
-	kfree(sbi->sb_bmp_dir);
-	s->s_fs_info = NULL;
-	kfree(sbi);
+	call_rcu(&hpfs_sb(s)->rcu, lazy_free_sbi);
 }
 
 unsigned hpfs_count_one_bitmap(struct super_block *s, secno secno)
@@ -485,9 +491,6 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent)
 	}
 	s->s_fs_info = sbi;
 
-	sbi->sb_bmp_dir = NULL;
-	sbi->sb_cp_table = NULL;
-
 	mutex_init(&sbi->hpfs_mutex);
 	hpfs_lock(s);
 
@@ -679,10 +682,7 @@ bail2:	brelse(bh0);
 bail1:
 bail0:
 	hpfs_unlock(s);
-	kfree(sbi->sb_bmp_dir);
-	kfree(sbi->sb_cp_table);
-	s->s_fs_info = NULL;
-	kfree(sbi);
+	free_sbi(sbi);
 	return -EINVAL;
 }
 

fs/inode.c

@@ -773,15 +773,11 @@ static struct inode *find_inode(struct super_block *sb,
 
 repeat:
 	hlist_for_each_entry(inode, head, i_hash) {
-		spin_lock(&inode->i_lock);
-		if (inode->i_sb != sb) {
-			spin_unlock(&inode->i_lock);
+		if (inode->i_sb != sb)
 			continue;
-		}
-		if (!test(inode, data)) {
-			spin_unlock(&inode->i_lock);
+		if (!test(inode, data))
 			continue;
-		}
+		spin_lock(&inode->i_lock);
 		if (inode->i_state & (I_FREEING|I_WILL_FREE)) {
 			__wait_on_freeing_inode(inode);
 			goto repeat;
@@ -804,15 +800,11 @@ static struct inode *find_inode_fast(struct super_block *sb,
 
 repeat:
 	hlist_for_each_entry(inode, head, i_hash) {
-		spin_lock(&inode->i_lock);
-		if (inode->i_ino != ino) {
-			spin_unlock(&inode->i_lock);
+		if (inode->i_ino != ino)
 			continue;
-		}
-		if (inode->i_sb != sb) {
-			spin_unlock(&inode->i_lock);
+		if (inode->i_sb != sb)
 			continue;
-		}
+		spin_lock(&inode->i_lock);
 		if (inode->i_state & (I_FREEING|I_WILL_FREE)) {
 			__wait_on_freeing_inode(inode);
 			goto repeat;
@@ -950,6 +942,42 @@ void unlock_new_inode(struct inode *inode)
 }
 EXPORT_SYMBOL(unlock_new_inode);
 
+/**
+ * lock_two_nondirectories - take two i_mutexes on non-directory objects
+ * @inode1: first inode to lock
+ * @inode2: second inode to lock
+ */
+void lock_two_nondirectories(struct inode *inode1, struct inode *inode2)
+{
+	WARN_ON_ONCE(S_ISDIR(inode1->i_mode));
+	if (inode1 == inode2 || !inode2) {
+		mutex_lock(&inode1->i_mutex);
+		return;
+	}
+	WARN_ON_ONCE(S_ISDIR(inode2->i_mode));
+	if (inode1 < inode2) {
+		mutex_lock(&inode1->i_mutex);
+		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_NONDIR2);
+	} else {
+		mutex_lock(&inode2->i_mutex);
+		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_NONDIR2);
+	}
+}
+EXPORT_SYMBOL(lock_two_nondirectories);
+
+/**
+ * unlock_two_nondirectories - release locks from lock_two_nondirectories()
+ * @inode1: first inode to unlock
+ * @inode2: second inode to unlock
+ */
+void unlock_two_nondirectories(struct inode *inode1, struct inode *inode2)
+{
+	mutex_unlock(&inode1->i_mutex);
+	if (inode2 && inode2 != inode1)
+		mutex_unlock(&inode2->i_mutex);
+}
+EXPORT_SYMBOL(unlock_two_nondirectories);
+
 /**
  * iget5_locked - obtain an inode from a mounted file system
  * @sb:		super block of file system
@@ -1575,7 +1603,11 @@ static int __remove_suid(struct dentry *dentry, int kill)
 	struct iattr newattrs;
 
 	newattrs.ia_valid = ATTR_FORCE | kill;
-	return notify_change(dentry, &newattrs);
+	/*
+	 * Note we call this on write, so notify_change will not
+	 * encounter any conflicting delegations:
+	 */
+	return notify_change(dentry, &newattrs, NULL);
 }
 
 int file_remove_suid(struct file *file)

fs/internal.h

@@ -9,8 +9,6 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-#include <linux/lglock.h>
-
 struct super_block;
 struct file_system_type;
 struct linux_binprm;
@@ -62,8 +60,6 @@ extern int sb_prepare_remount_readonly(struct super_block *);
 
 extern void __init mnt_init(void);
 
-extern struct lglock vfsmount_lock;
-
 extern int __mnt_want_write(struct vfsmount *);
 extern int __mnt_want_write_file(struct file *);
 extern void __mnt_drop_write(struct vfsmount *);
@@ -77,9 +73,6 @@ extern void chroot_fs_refs(const struct path *, const struct path *);
 /*
  * file_table.c
  */
-extern void file_sb_list_add(struct file *f, struct super_block *sb);
-extern void file_sb_list_del(struct file *f);
-extern void mark_files_ro(struct super_block *);
 extern struct file *get_empty_filp(void);
 
 /*

fs/ioctl.c

@@ -37,7 +37,7 @@ static long vfs_ioctl(struct file *filp, unsigned int cmd,
 {
 	int error = -ENOTTY;
 
-	if (!filp->f_op || !filp->f_op->unlocked_ioctl)
+	if (!filp->f_op->unlocked_ioctl)
 		goto out;
 
 	error = filp->f_op->unlocked_ioctl(filp, cmd, arg);
@@ -501,7 +501,7 @@ static int ioctl_fioasync(unsigned int fd, struct file *filp,
 
 	/* Did FASYNC state change ? */
 	if ((flag ^ filp->f_flags) & FASYNC) {
-		if (filp->f_op && filp->f_op->fasync)
+		if (filp->f_op->fasync)
 			/* fasync() adjusts filp->f_flags */
 			error = filp->f_op->fasync(fd, filp, on);
 		else

fs/isofs/inode.c

@@ -181,7 +181,7 @@ struct iso9660_options{
  * Compute the hash for the isofs name corresponding to the dentry.
  */
 static int
-isofs_hash_common(const struct dentry *dentry, struct qstr *qstr, int ms)
+isofs_hash_common(struct qstr *qstr, int ms)
 {
 	const char *name;
 	int len;
@@ -202,7 +202,7 @@ isofs_hash_common(const struct dentry *dentry, struct qstr *qstr, int ms)
  * Compute the hash for the isofs name corresponding to the dentry.
  */
 static int
-isofs_hashi_common(const struct dentry *dentry, struct qstr *qstr, int ms)
+isofs_hashi_common(struct qstr *qstr, int ms)
 {
 	const char *name;
 	int len;
@@ -259,13 +259,13 @@ static int isofs_dentry_cmp_common(
 static int
 isofs_hash(const struct dentry *dentry, struct qstr *qstr)
 {
-	return isofs_hash_common(dentry, qstr, 0);
+	return isofs_hash_common(qstr, 0);
 }
 
 static int
 isofs_hashi(const struct dentry *dentry, struct qstr *qstr)
 {
-	return isofs_hashi_common(dentry, qstr, 0);
+	return isofs_hashi_common(qstr, 0);
 }
 
 static int
@@ -286,13 +286,13 @@ isofs_dentry_cmpi(const struct dentry *parent, const struct dentry *dentry,
 static int
 isofs_hash_ms(const struct dentry *dentry, struct qstr *qstr)
 {
-	return isofs_hash_common(dentry, qstr, 1);
+	return isofs_hash_common(qstr, 1);
 }
 
 static int
 isofs_hashi_ms(const struct dentry *dentry, struct qstr *qstr)
 {
-	return isofs_hashi_common(dentry, qstr, 1);
+	return isofs_hashi_common(qstr, 1);
 }
 
 static int

fs/libfs.c

@@ -10,6 +10,7 @@
 #include <linux/vfs.h>
 #include <linux/quotaops.h>
 #include <linux/mutex.h>
+#include <linux/namei.h>
 #include <linux/exportfs.h>
 #include <linux/writeback.h>
 #include <linux/buffer_head.h> /* sync_mapping_buffers */
@@ -31,6 +32,7 @@ int simple_getattr(struct vfsmount *mnt, struct dentry *dentry,
 	stat->blocks = inode->i_mapping->nrpages << (PAGE_CACHE_SHIFT - 9);
 	return 0;
 }
+EXPORT_SYMBOL(simple_getattr);
 
 int simple_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
@@ -39,6 +41,7 @@ int simple_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_namelen = NAME_MAX;
 	return 0;
 }
+EXPORT_SYMBOL(simple_statfs);
 
 /*
  * Retaining negative dentries for an in-memory filesystem just wastes
@@ -66,6 +69,7 @@ struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, unsigned
 	d_add(dentry, NULL);
 	return NULL;
 }
+EXPORT_SYMBOL(simple_lookup);
 
 int dcache_dir_open(struct inode *inode, struct file *file)
 {
@@ -75,12 +79,14 @@ int dcache_dir_open(struct inode *inode, struct file *file)
 
 	return file->private_data ? 0 : -ENOMEM;
 }
+EXPORT_SYMBOL(dcache_dir_open);
 
 int dcache_dir_close(struct inode *inode, struct file *file)
 {
 	dput(file->private_data);
 	return 0;
 }
+EXPORT_SYMBOL(dcache_dir_close);
 
 loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
 {
@@ -123,6 +129,7 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
 	mutex_unlock(&dentry->d_inode->i_mutex);
 	return offset;
 }
+EXPORT_SYMBOL(dcache_dir_lseek);
 
 /* Relationship between i_mode and the DT_xxx types */
 static inline unsigned char dt_type(struct inode *inode)
@@ -172,11 +179,13 @@ int dcache_readdir(struct file *file, struct dir_context *ctx)
 	spin_unlock(&dentry->d_lock);
 	return 0;
 }
+EXPORT_SYMBOL(dcache_readdir);
 
 ssize_t generic_read_dir(struct file *filp, char __user *buf, size_t siz, loff_t *ppos)
 {
 	return -EISDIR;
 }
+EXPORT_SYMBOL(generic_read_dir);
 
 const struct file_operations simple_dir_operations = {
 	.open		= dcache_dir_open,
@@ -186,10 +195,12 @@ const struct file_operations simple_dir_operations = {
 	.iterate	= dcache_readdir,
 	.fsync		= noop_fsync,
 };
+EXPORT_SYMBOL(simple_dir_operations);
 
 const struct inode_operations simple_dir_inode_operations = {
 	.lookup		= simple_lookup,
 };
+EXPORT_SYMBOL(simple_dir_inode_operations);
 
 static const struct super_operations simple_super_operations = {
 	.statfs		= simple_statfs,
@@ -244,6 +255,7 @@ Enomem:
 	deactivate_locked_super(s);
 	return ERR_PTR(-ENOMEM);
 }
+EXPORT_SYMBOL(mount_pseudo);
 
 int simple_open(struct inode *inode, struct file *file)
 {
@@ -251,6 +263,7 @@ int simple_open(struct inode *inode, struct file *file)
 		file->private_data = inode->i_private;
 	return 0;
 }
+EXPORT_SYMBOL(simple_open);
 
 int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
 {
@@ -263,6 +276,7 @@ int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *den
 	d_instantiate(dentry, inode);
 	return 0;
 }
+EXPORT_SYMBOL(simple_link);
 
 int simple_empty(struct dentry *dentry)
 {
@@ -283,6 +297,7 @@ out:
 	spin_unlock(&dentry->d_lock);
 	return ret;
 }
+EXPORT_SYMBOL(simple_empty);
 
 int simple_unlink(struct inode *dir, struct dentry *dentry)
 {
@@ -293,6 +308,7 @@ int simple_unlink(struct inode *dir, struct dentry *dentry)
 	dput(dentry);
 	return 0;
 }
+EXPORT_SYMBOL(simple_unlink);
 
 int simple_rmdir(struct inode *dir, struct dentry *dentry)
 {
@@ -304,6 +320,7 @@ int simple_rmdir(struct inode *dir, struct dentry *dentry)
 	drop_nlink(dir);
 	return 0;
 }
+EXPORT_SYMBOL(simple_rmdir);
 
 int simple_rename(struct inode *old_dir, struct dentry *old_dentry,
 		struct inode *new_dir, struct dentry *new_dentry)
@@ -330,6 +347,7 @@ int simple_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	return 0;
 }
+EXPORT_SYMBOL(simple_rename);
 
 /**
  * simple_setattr - setattr for simple filesystem
@@ -370,6 +388,7 @@ int simple_readpage(struct file *file, struct page *page)
 	unlock_page(page);
 	return 0;
 }
+EXPORT_SYMBOL(simple_readpage);
 
 int simple_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned flags,
@@ -393,6 +412,7 @@ int simple_write_begin(struct file *file, struct address_space *mapping,
 	}
 	return 0;
 }
+EXPORT_SYMBOL(simple_write_begin);
 
 /**
  * simple_write_end - .write_end helper for non-block-device FSes
@@ -444,6 +464,7 @@ int simple_write_end(struct file *file, struct address_space *mapping,
 
 	return copied;
 }
+EXPORT_SYMBOL(simple_write_end);
 
 /*
  * the inodes created here are not hashed. If you use iunique to generate
@@ -512,6 +533,7 @@ out:
 	dput(root);
 	return -ENOMEM;
 }
+EXPORT_SYMBOL(simple_fill_super);
 
 static DEFINE_SPINLOCK(pin_fs_lock);
 
@@ -534,6 +556,7 @@ int simple_pin_fs(struct file_system_type *type, struct vfsmount **mount, int *c
 	mntput(mnt);
 	return 0;
 }
+EXPORT_SYMBOL(simple_pin_fs);
 
 void simple_release_fs(struct vfsmount **mount, int *count)
 {
@@ -545,6 +568,7 @@ void simple_release_fs(struct vfsmount **mount, int *count)
 	spin_unlock(&pin_fs_lock);
 	mntput(mnt);
 }
+EXPORT_SYMBOL(simple_release_fs);
 
 /**
  * simple_read_from_buffer - copy data from the buffer to user space
@@ -579,6 +603,7 @@ ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos,
 	*ppos = pos + count;
 	return count;
 }
+EXPORT_SYMBOL(simple_read_from_buffer);
 
 /**
  * simple_write_to_buffer - copy data from user space to the buffer
@@ -613,6 +638,7 @@ ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos,
 	*ppos = pos + count;
 	return count;
 }
+EXPORT_SYMBOL(simple_write_to_buffer);
 
 /**
  * memory_read_from_buffer - copy data from the buffer
@@ -644,6 +670,7 @@ ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos,
 
 	return count;
 }
+EXPORT_SYMBOL(memory_read_from_buffer);
 
 /*
  * Transaction based IO.
@@ -665,6 +692,7 @@ void simple_transaction_set(struct file *file, size_t n)
 	smp_mb();
 	ar->size = n;
 }
+EXPORT_SYMBOL(simple_transaction_set);
 
 char *simple_transaction_get(struct file *file, const char __user *buf, size_t size)
 {
@@ -696,6 +724,7 @@ char *simple_transaction_get(struct file *file, const char __user *buf, size_t s
 
 	return ar->data;
 }
+EXPORT_SYMBOL(simple_transaction_get);
 
 ssize_t simple_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos)
 {
@@ -705,12 +734,14 @@ ssize_t simple_transaction_read(struct file *file, char __user *buf, size_t size
 		return 0;
 	return simple_read_from_buffer(buf, size, pos, ar->data, ar->size);
 }
+EXPORT_SYMBOL(simple_transaction_read);
 
 int simple_transaction_release(struct inode *inode, struct file *file)
 {
 	free_page((unsigned long)file->private_data);
 	return 0;
 }
+EXPORT_SYMBOL(simple_transaction_release);
 
 /* Simple attribute files */
 
@@ -746,12 +777,14 @@ int simple_attr_open(struct inode *inode, struct file *file,
 
 	return nonseekable_open(inode, file);
 }
+EXPORT_SYMBOL_GPL(simple_attr_open);
 
 int simple_attr_release(struct inode *inode, struct file *file)
 {
 	kfree(file->private_data);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(simple_attr_release);	/* GPL-only?  This?  Really? */
 
 /* read from the buffer that is filled with the get function */
 ssize_t simple_attr_read(struct file *file, char __user *buf,
@@ -787,6 +820,7 @@ out:
 	mutex_unlock(&attr->mutex);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(simple_attr_read);
 
 /* interpret the buffer as a number to call the set function with */
 ssize_t simple_attr_write(struct file *file, const char __user *buf,
@@ -819,6 +853,7 @@ out:
 	mutex_unlock(&attr->mutex);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(simple_attr_write);
 
 /**
  * generic_fh_to_dentry - generic helper for the fh_to_dentry export operation
@@ -957,39 +992,56 @@ int noop_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	return 0;
 }
-
-EXPORT_SYMBOL(dcache_dir_close);
-EXPORT_SYMBOL(dcache_dir_lseek);
-EXPORT_SYMBOL(dcache_dir_open);
-EXPORT_SYMBOL(dcache_readdir);
-EXPORT_SYMBOL(generic_read_dir);
-EXPORT_SYMBOL(mount_pseudo);
-EXPORT_SYMBOL(simple_write_begin);
-EXPORT_SYMBOL(simple_write_end);
-EXPORT_SYMBOL(simple_dir_inode_operations);
-EXPORT_SYMBOL(simple_dir_operations);
-EXPORT_SYMBOL(simple_empty);
-EXPORT_SYMBOL(simple_fill_super);
-EXPORT_SYMBOL(simple_getattr);
-EXPORT_SYMBOL(simple_open);
-EXPORT_SYMBOL(simple_link);
-EXPORT_SYMBOL(simple_lookup);
-EXPORT_SYMBOL(simple_pin_fs);
-EXPORT_SYMBOL(simple_readpage);
-EXPORT_SYMBOL(simple_release_fs);
-EXPORT_SYMBOL(simple_rename);
-EXPORT_SYMBOL(simple_rmdir);
-EXPORT_SYMBOL(simple_statfs);
 EXPORT_SYMBOL(noop_fsync);
-EXPORT_SYMBOL(simple_unlink);
-EXPORT_SYMBOL(simple_read_from_buffer);
-EXPORT_SYMBOL(simple_write_to_buffer);
-EXPORT_SYMBOL(memory_read_from_buffer);
-EXPORT_SYMBOL(simple_transaction_set);
-EXPORT_SYMBOL(simple_transaction_get);
-EXPORT_SYMBOL(simple_transaction_read);
-EXPORT_SYMBOL(simple_transaction_release);
-EXPORT_SYMBOL_GPL(simple_attr_open);
-EXPORT_SYMBOL_GPL(simple_attr_release);
-EXPORT_SYMBOL_GPL(simple_attr_read);
-EXPORT_SYMBOL_GPL(simple_attr_write);
+
+void kfree_put_link(struct dentry *dentry, struct nameidata *nd,
+				void *cookie)
+{
+	char *s = nd_get_link(nd);
+	if (!IS_ERR(s))
+		kfree(s);
+}
+EXPORT_SYMBOL(kfree_put_link);
+
+/*
+ * nop .set_page_dirty method so that people can use .page_mkwrite on
+ * anon inodes.
+ */
+static int anon_set_page_dirty(struct page *page)
+{
+	return 0;
+};
+
+/*
+ * A single inode exists for all anon_inode files. Contrary to pipes,
+ * anon_inode inodes have no associated per-instance data, so we need
+ * only allocate one of them.
+ */
+struct inode *alloc_anon_inode(struct super_block *s)
+{
+	static const struct address_space_operations anon_aops = {
+		.set_page_dirty = anon_set_page_dirty,
+	};
+	struct inode *inode = new_inode_pseudo(s);
+
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+
+	inode->i_ino = get_next_ino();
+	inode->i_mapping->a_ops = &anon_aops;
+
+	/*
+	 * Mark the inode dirty from the very beginning,
+	 * that way it will never be moved to the dirty
+	 * list because mark_inode_dirty() will think
+	 * that it already _is_ on the dirty list.
+	 */
+	inode->i_state = I_DIRTY;
+	inode->i_mode = S_IRUSR | S_IWUSR;
+	inode->i_uid = current_fsuid();
+	inode->i_gid = current_fsgid();
+	inode->i_flags |= S_PRIVATE;
+	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	return inode;
+}
+EXPORT_SYMBOL(alloc_anon_inode);

fs/locks.c

@@ -134,7 +134,7 @@
 
 #define IS_POSIX(fl)	(fl->fl_flags & FL_POSIX)
 #define IS_FLOCK(fl)	(fl->fl_flags & FL_FLOCK)
-#define IS_LEASE(fl)	(fl->fl_flags & FL_LEASE)
+#define IS_LEASE(fl)	(fl->fl_flags & (FL_LEASE|FL_DELEG))
 
 static bool lease_breaking(struct file_lock *fl)
 {
@@ -1292,28 +1292,40 @@ static void time_out_leases(struct inode *inode)
 	}
 }
 
+static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker)
+{
+	if ((breaker->fl_flags & FL_DELEG) && (lease->fl_flags & FL_LEASE))
+		return false;
+	return locks_conflict(breaker, lease);
+}
+
 /**
  *	__break_lease	-	revoke all outstanding leases on file
  *	@inode: the inode of the file to return
- *	@mode: the open mode (read or write)
+ *	@mode: O_RDONLY: break only write leases; O_WRONLY or O_RDWR:
+ *	    break all leases
+ *	@type: FL_LEASE: break leases and delegations; FL_DELEG: break
+ *	    only delegations
  *
  *	break_lease (inlined for speed) has checked there already is at least
  *	some kind of lock (maybe a lease) on this file.  Leases are broken on
  *	a call to open() or truncate().  This function can sleep unless you
  *	specified %O_NONBLOCK to your open().
  */
-int __break_lease(struct inode *inode, unsigned int mode)
+int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 {
 	int error = 0;
 	struct file_lock *new_fl, *flock;
 	struct file_lock *fl;
 	unsigned long break_time;
 	int i_have_this_lease = 0;
+	bool lease_conflict = false;
 	int want_write = (mode & O_ACCMODE) != O_RDONLY;
 
 	new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK);
 	if (IS_ERR(new_fl))
 		return PTR_ERR(new_fl);
+	new_fl->fl_flags = type;
 
 	spin_lock(&inode->i_lock);
 
@@ -1323,13 +1335,16 @@ int __break_lease(struct inode *inode, unsigned int mode)
 	if ((flock == NULL) || !IS_LEASE(flock))
 		goto out;
 
-	if (!locks_conflict(flock, new_fl))
+	for (fl = flock; fl && IS_LEASE(fl); fl = fl->fl_next) {
+		if (leases_conflict(fl, new_fl)) {
+			lease_conflict = true;
+			if (fl->fl_owner == current->files)
+				i_have_this_lease = 1;
+		}
+	}
+	if (!lease_conflict)
 		goto out;
 
-	for (fl = flock; fl && IS_LEASE(fl); fl = fl->fl_next)
-		if (fl->fl_owner == current->files)
-			i_have_this_lease = 1;
-
 	break_time = 0;
 	if (lease_break_time > 0) {
 		break_time = jiffies + lease_break_time * HZ;
@@ -1338,6 +1353,8 @@ int __break_lease(struct inode *inode, unsigned int mode)
 	}
 
 	for (fl = flock; fl && IS_LEASE(fl); fl = fl->fl_next) {
+		if (!leases_conflict(fl, new_fl))
+			continue;
 		if (want_write) {
 			if (fl->fl_flags & FL_UNLOCK_PENDING)
 				continue;
@@ -1379,7 +1396,7 @@ restart:
 		 */
 		for (flock = inode->i_flock; flock && IS_LEASE(flock);
 				flock = flock->fl_next) {
-			if (locks_conflict(new_fl, flock))
+			if (leases_conflict(new_fl, flock))
 				goto restart;
 		}
 		error = 0;
@@ -1460,9 +1477,26 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp
 	struct file_lock *fl, **before, **my_before = NULL, *lease;
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
+	bool is_deleg = (*flp)->fl_flags & FL_DELEG;
 	int error;
 
 	lease = *flp;
+	/*
+	 * In the delegation case we need mutual exclusion with
+	 * a number of operations that take the i_mutex.  We trylock
+	 * because delegations are an optional optimization, and if
+	 * there's some chance of a conflict--we'd rather not
+	 * bother, maybe that's a sign this just isn't a good file to
+	 * hand out a delegation on.
+	 */
+	if (is_deleg && !mutex_trylock(&inode->i_mutex))
+		return -EAGAIN;
+
+	if (is_deleg && arg == F_WRLCK) {
+		/* Write delegations are not currently supported: */
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
 
 	error = -EAGAIN;
 	if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0))
@@ -1514,9 +1548,10 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp
 		goto out;
 
 	locks_insert_lock(before, lease);
-	return 0;
-
+	error = 0;
 out:
+	if (is_deleg)
+		mutex_unlock(&inode->i_mutex);
 	return error;
 }
 
@@ -1579,7 +1614,7 @@ EXPORT_SYMBOL(generic_setlease);
 
 static int __vfs_setlease(struct file *filp, long arg, struct file_lock **lease)
 {
-	if (filp->f_op && filp->f_op->setlease)
+	if (filp->f_op->setlease)
 		return filp->f_op->setlease(filp, arg, lease);
 	else
 		return generic_setlease(filp, arg, lease);
@@ -1771,7 +1806,7 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd)
 	if (error)
 		goto out_free;
 
-	if (f.file->f_op && f.file->f_op->flock)
+	if (f.file->f_op->flock)
 		error = f.file->f_op->flock(f.file,
 					  (can_sleep) ? F_SETLKW : F_SETLK,
 					  lock);
@@ -1797,7 +1832,7 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd)
  */
 int vfs_test_lock(struct file *filp, struct file_lock *fl)
 {
-	if (filp->f_op && filp->f_op->lock)
+	if (filp->f_op->lock)
 		return filp->f_op->lock(filp, F_GETLK, fl);
 	posix_test_lock(filp, fl);
 	return 0;
@@ -1909,7 +1944,7 @@ out:
  */
 int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf)
 {
-	if (filp->f_op && filp->f_op->lock)
+	if (filp->f_op->lock)
 		return filp->f_op->lock(filp, cmd, fl);
 	else
 		return posix_lock_file(filp, fl, conf);
@@ -2182,7 +2217,7 @@ void locks_remove_flock(struct file *filp)
 	if (!inode->i_flock)
 		return;
 
-	if (filp->f_op && filp->f_op->flock) {
+	if (filp->f_op->flock) {
 		struct file_lock fl = {
 			.fl_pid = current->tgid,
 			.fl_file = filp,
@@ -2246,7 +2281,7 @@ EXPORT_SYMBOL(posix_unblock_lock);
  */
 int vfs_cancel_lock(struct file *filp, struct file_lock *fl)
 {
-	if (filp->f_op && filp->f_op->lock)
+	if (filp->f_op->lock)
 		return filp->f_op->lock(filp, F_CANCELLK, fl);
 	return 0;
 }

fs/mount.h

@@ -29,6 +29,7 @@ struct mount {
 	struct mount *mnt_parent;
 	struct dentry *mnt_mountpoint;
 	struct vfsmount mnt;
+	struct rcu_head mnt_rcu;
 #ifdef CONFIG_SMP
 	struct mnt_pcp __percpu *mnt_pcp;
 #else
@@ -55,7 +56,7 @@ struct mount {
 	int mnt_group_id;		/* peer group identifier */
 	int mnt_expiry_mark;		/* true if marked for expiry */
 	int mnt_pinned;
-	int mnt_ghosts;
+	struct path mnt_ex_mountpoint;
 };
 
 #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */
@@ -76,13 +77,28 @@ static inline int is_mounted(struct vfsmount *mnt)
 	return !IS_ERR_OR_NULL(real_mount(mnt));
 }
 
-extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *, int);
+extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *);
+extern struct mount *__lookup_mnt_last(struct vfsmount *, struct dentry *);
+
+extern bool legitimize_mnt(struct vfsmount *, unsigned);
 
 static inline void get_mnt_ns(struct mnt_namespace *ns)
 {
 	atomic_inc(&ns->count);
 }
 
+extern seqlock_t mount_lock;
+
+static inline void lock_mount_hash(void)
+{
+	write_seqlock(&mount_lock);
+}
+
+static inline void unlock_mount_hash(void)
+{
+	write_sequnlock(&mount_lock);
+}
+
 struct proc_mounts {
 	struct seq_file m;
 	struct mnt_namespace *ns;

fs/namei.c

@@ -482,18 +482,6 @@ EXPORT_SYMBOL(path_put);
  * to restart the path walk from the beginning in ref-walk mode.
  */
 
-static inline void lock_rcu_walk(void)
-{
-	br_read_lock(&vfsmount_lock);
-	rcu_read_lock();
-}
-
-static inline void unlock_rcu_walk(void)
-{
-	rcu_read_unlock();
-	br_read_unlock(&vfsmount_lock);
-}
-
 /**
  * unlazy_walk - try to switch to ref-walk mode.
  * @nd: nameidata pathwalk data
@@ -512,26 +500,23 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry)
 	BUG_ON(!(nd->flags & LOOKUP_RCU));
 
 	/*
-	 * Get a reference to the parent first: we're
-	 * going to make "path_put(nd->path)" valid in
-	 * non-RCU context for "terminate_walk()".
-	 *
-	 * If this doesn't work, return immediately with
-	 * RCU walking still active (and then we will do
-	 * the RCU walk cleanup in terminate_walk()).
+	 * After legitimizing the bastards, terminate_walk()
+	 * will do the right thing for non-RCU mode, and all our
+	 * subsequent exit cases should rcu_read_unlock()
+	 * before returning.  Do vfsmount first; if dentry
+	 * can't be legitimized, just set nd->path.dentry to NULL
+	 * and rely on dput(NULL) being a no-op.
 	 */
-	if (!lockref_get_not_dead(&parent->d_lockref))
+	if (!legitimize_mnt(nd->path.mnt, nd->m_seq))
 		return -ECHILD;
-
-	/*
-	 * After the mntget(), we terminate_walk() will do
-	 * the right thing for non-RCU mode, and all our
-	 * subsequent exit cases should unlock_rcu_walk()
-	 * before returning.
-	 */
-	mntget(nd->path.mnt);
 	nd->flags &= ~LOOKUP_RCU;
 
+	if (!lockref_get_not_dead(&parent->d_lockref)) {
+		nd->path.dentry = NULL;	
+		rcu_read_unlock();
+		return -ECHILD;
+	}
+
 	/*
 	 * For a negative lookup, the lookup sequence point is the parents
 	 * sequence point, and it only needs to revalidate the parent dentry.
@@ -566,17 +551,17 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry)
 		spin_unlock(&fs->lock);
 	}
 
-	unlock_rcu_walk();
+	rcu_read_unlock();
 	return 0;
 
 unlock_and_drop_dentry:
 	spin_unlock(&fs->lock);
 drop_dentry:
-	unlock_rcu_walk();
+	rcu_read_unlock();
 	dput(dentry);
 	goto drop_root_mnt;
 out:
-	unlock_rcu_walk();
+	rcu_read_unlock();
 drop_root_mnt:
 	if (!(nd->flags & LOOKUP_ROOT))
 		nd->root.mnt = NULL;
@@ -608,17 +593,22 @@ static int complete_walk(struct nameidata *nd)
 		if (!(nd->flags & LOOKUP_ROOT))
 			nd->root.mnt = NULL;
 
+		if (!legitimize_mnt(nd->path.mnt, nd->m_seq)) {
+			rcu_read_unlock();
+			return -ECHILD;
+		}
 		if (unlikely(!lockref_get_not_dead(&dentry->d_lockref))) {
-			unlock_rcu_walk();
+			rcu_read_unlock();
+			mntput(nd->path.mnt);
 			return -ECHILD;
 		}
 		if (read_seqcount_retry(&dentry->d_seq, nd->seq)) {
-			unlock_rcu_walk();
+			rcu_read_unlock();
 			dput(dentry);
+			mntput(nd->path.mnt);
 			return -ECHILD;
 		}
-		mntget(nd->path.mnt);
-		unlock_rcu_walk();
+		rcu_read_unlock();
 	}
 
 	if (likely(!(nd->flags & LOOKUP_JUMPED)))
@@ -909,15 +899,15 @@ int follow_up(struct path *path)
 	struct mount *parent;
 	struct dentry *mountpoint;
 
-	br_read_lock(&vfsmount_lock);
+	read_seqlock_excl(&mount_lock);
 	parent = mnt->mnt_parent;
 	if (parent == mnt) {
-		br_read_unlock(&vfsmount_lock);
+		read_sequnlock_excl(&mount_lock);
 		return 0;
 	}
 	mntget(&parent->mnt);
 	mountpoint = dget(mnt->mnt_mountpoint);
-	br_read_unlock(&vfsmount_lock);
+	read_sequnlock_excl(&mount_lock);
 	dput(path->dentry);
 	path->dentry = mountpoint;
 	mntput(path->mnt);
@@ -1048,8 +1038,8 @@ static int follow_managed(struct path *path, unsigned flags)
 
 			/* Something is mounted on this dentry in another
 			 * namespace and/or whatever was mounted there in this
-			 * namespace got unmounted before we managed to get the
-			 * vfsmount_lock */
+			 * namespace got unmounted before lookup_mnt() could
+			 * get it */
 		}
 
 		/* Handle an automount point */
@@ -1111,7 +1101,7 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 		if (!d_mountpoint(path->dentry))
 			break;
 
-		mounted = __lookup_mnt(path->mnt, path->dentry, 1);
+		mounted = __lookup_mnt(path->mnt, path->dentry);
 		if (!mounted)
 			break;
 		path->mnt = &mounted->mnt;
@@ -1132,7 +1122,7 @@ static void follow_mount_rcu(struct nameidata *nd)
 {
 	while (d_mountpoint(nd->path.dentry)) {
 		struct mount *mounted;
-		mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry, 1);
+		mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry);
 		if (!mounted)
 			break;
 		nd->path.mnt = &mounted->mnt;
@@ -1174,7 +1164,7 @@ failed:
 	nd->flags &= ~LOOKUP_RCU;
 	if (!(nd->flags & LOOKUP_ROOT))
 		nd->root.mnt = NULL;
-	unlock_rcu_walk();
+	rcu_read_unlock();
 	return -ECHILD;
 }
 
@@ -1308,8 +1298,8 @@ static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir,
 }
 
 /*
- * Call i_op->lookup on the dentry.  The dentry must be negative but may be
- * hashed if it was pouplated with DCACHE_NEED_LOOKUP.
+ * Call i_op->lookup on the dentry.  The dentry must be negative and
+ * unhashed.
  *
  * dir->d_inode->i_mutex must be held
  */
@@ -1501,7 +1491,7 @@ static void terminate_walk(struct nameidata *nd)
 		nd->flags &= ~LOOKUP_RCU;
 		if (!(nd->flags & LOOKUP_ROOT))
 			nd->root.mnt = NULL;
-		unlock_rcu_walk();
+		rcu_read_unlock();
 	}
 }
 
@@ -1511,18 +1501,9 @@ static void terminate_walk(struct nameidata *nd)
  * so we keep a cache of "no, this doesn't need follow_link"
  * for the common case.
  */
-static inline int should_follow_link(struct inode *inode, int follow)
+static inline int should_follow_link(struct dentry *dentry, int follow)
 {
-	if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) {
-		if (likely(inode->i_op->follow_link))
-			return follow;
-
-		/* This gets set once for the inode lifetime */
-		spin_lock(&inode->i_lock);
-		inode->i_opflags |= IOP_NOFOLLOW;
-		spin_unlock(&inode->i_lock);
-	}
-	return 0;
+	return unlikely(d_is_symlink(dentry)) ? follow : 0;
 }
 
 static inline int walk_component(struct nameidata *nd, struct path *path,
@@ -1552,7 +1533,7 @@ static inline int walk_component(struct nameidata *nd, struct path *path,
 	if (!inode)
 		goto out_path_put;
 
-	if (should_follow_link(inode, follow)) {
+	if (should_follow_link(path->dentry, follow)) {
 		if (nd->flags & LOOKUP_RCU) {
 			if (unlikely(unlazy_walk(nd, path->dentry))) {
 				err = -ECHILD;
@@ -1610,26 +1591,6 @@ static inline int nested_symlink(struct path *path, struct nameidata *nd)
 	return res;
 }
 
-/*
- * We really don't want to look at inode->i_op->lookup
- * when we don't have to. So we keep a cache bit in
- * the inode ->i_opflags field that says "yes, we can
- * do lookup on this inode".
- */
-static inline int can_lookup(struct inode *inode)
-{
-	if (likely(inode->i_opflags & IOP_LOOKUP))
-		return 1;
-	if (likely(!inode->i_op->lookup))
-		return 0;
-
-	/* We do this once for the lifetime of the inode */
-	spin_lock(&inode->i_lock);
-	inode->i_opflags |= IOP_LOOKUP;
-	spin_unlock(&inode->i_lock);
-	return 1;
-}
-
 /*
  * We can do the critical dentry name comparison and hashing
  * operations one word at a time, but we are limited to:
@@ -1833,7 +1794,7 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 			if (err)
 				return err;
 		}
-		if (!can_lookup(nd->inode)) {
+		if (!d_is_directory(nd->path.dentry)) {
 			err = -ENOTDIR; 
 			break;
 		}
@@ -1851,9 +1812,10 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 	nd->flags = flags | LOOKUP_JUMPED;
 	nd->depth = 0;
 	if (flags & LOOKUP_ROOT) {
-		struct inode *inode = nd->root.dentry->d_inode;
+		struct dentry *root = nd->root.dentry;
+		struct inode *inode = root->d_inode;
 		if (*name) {
-			if (!can_lookup(inode))
+			if (!d_is_directory(root))
 				return -ENOTDIR;
 			retval = inode_permission(inode, MAY_EXEC);
 			if (retval)
@@ -1862,8 +1824,9 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 		nd->path = nd->root;
 		nd->inode = inode;
 		if (flags & LOOKUP_RCU) {
-			lock_rcu_walk();
+			rcu_read_lock();
 			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
+			nd->m_seq = read_seqbegin(&mount_lock);
 		} else {
 			path_get(&nd->path);
 		}
@@ -1872,9 +1835,10 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 
 	nd->root.mnt = NULL;
 
+	nd->m_seq = read_seqbegin(&mount_lock);
 	if (*name=='/') {
 		if (flags & LOOKUP_RCU) {
-			lock_rcu_walk();
+			rcu_read_lock();
 			set_root_rcu(nd);
 		} else {
 			set_root(nd);
@@ -1886,7 +1850,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 			struct fs_struct *fs = current->fs;
 			unsigned seq;
 
-			lock_rcu_walk();
+			rcu_read_lock();
 
 			do {
 				seq = read_seqcount_begin(&fs->seq);
@@ -1907,7 +1871,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 		dentry = f.file->f_path.dentry;
 
 		if (*name) {
-			if (!can_lookup(dentry->d_inode)) {
+			if (!d_is_directory(dentry)) {
 				fdput(f);
 				return -ENOTDIR;
 			}
@@ -1918,7 +1882,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 			if (f.need_put)
 				*fp = f.file;
 			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
-			lock_rcu_walk();
+			rcu_read_lock();
 		} else {
 			path_get(&nd->path);
 			fdput(f);
@@ -1989,7 +1953,7 @@ static int path_lookupat(int dfd, const char *name,
 		err = complete_walk(nd);
 
 	if (!err && nd->flags & LOOKUP_DIRECTORY) {
-		if (!can_lookup(nd->inode)) {
+		if (!d_is_directory(nd->path.dentry)) {
 			path_put(&nd->path);
 			err = -ENOTDIR;
 		}
@@ -2281,7 +2245,7 @@ done:
 	}
 	path->dentry = dentry;
 	path->mnt = mntget(nd->path.mnt);
-	if (should_follow_link(dentry->d_inode, nd->flags & LOOKUP_FOLLOW))
+	if (should_follow_link(dentry, nd->flags & LOOKUP_FOLLOW))
 		return 1;
 	follow_mount(path);
 	error = 0;
@@ -2426,12 +2390,14 @@ static inline int check_sticky(struct inode *dir, struct inode *inode)
  * 10. We don't allow removal of NFS sillyrenamed files; it's handled by
  *     nfs_async_unlink().
  */
-static int may_delete(struct inode *dir,struct dentry *victim,int isdir)
+static int may_delete(struct inode *dir, struct dentry *victim, bool isdir)
 {
+	struct inode *inode = victim->d_inode;
 	int error;
 
-	if (!victim->d_inode)
+	if (d_is_negative(victim))
 		return -ENOENT;
+	BUG_ON(!inode);
 
 	BUG_ON(victim->d_parent->d_inode != dir);
 	audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
@@ -2441,15 +2407,16 @@ static int may_delete(struct inode *dir,struct dentry *victim,int isdir)
 		return error;
 	if (IS_APPEND(dir))
 		return -EPERM;
-	if (check_sticky(dir, victim->d_inode)||IS_APPEND(victim->d_inode)||
-	    IS_IMMUTABLE(victim->d_inode) || IS_SWAPFILE(victim->d_inode))
+
+	if (check_sticky(dir, inode) || IS_APPEND(inode) ||
+	    IS_IMMUTABLE(inode) || IS_SWAPFILE(inode))
 		return -EPERM;
 	if (isdir) {
-		if (!S_ISDIR(victim->d_inode->i_mode))
+		if (!d_is_directory(victim) && !d_is_autodir(victim))
 			return -ENOTDIR;
 		if (IS_ROOT(victim))
 			return -EBUSY;
-	} else if (S_ISDIR(victim->d_inode->i_mode))
+	} else if (d_is_directory(victim) || d_is_autodir(victim))
 		return -EISDIR;
 	if (IS_DEADDIR(dir))
 		return -ENOENT;
@@ -2983,7 +2950,7 @@ retry_lookup:
 	/*
 	 * create/update audit record if it already exists.
 	 */
-	if (path->dentry->d_inode)
+	if (d_is_positive(path->dentry))
 		audit_inode(name, path->dentry, 0);
 
 	/*
@@ -3012,12 +2979,12 @@ retry_lookup:
 finish_lookup:
 	/* we _can_ be in RCU mode here */
 	error = -ENOENT;
-	if (!inode) {
+	if (d_is_negative(path->dentry)) {
 		path_to_nameidata(path, nd);
 		goto out;
 	}
 
-	if (should_follow_link(inode, !symlink_ok)) {
+	if (should_follow_link(path->dentry, !symlink_ok)) {
 		if (nd->flags & LOOKUP_RCU) {
 			if (unlikely(unlazy_walk(nd, path->dentry))) {
 				error = -ECHILD;
@@ -3046,10 +3013,11 @@ finish_open:
 	}
 	audit_inode(name, nd->path.dentry, 0);
 	error = -EISDIR;
-	if ((open_flag & O_CREAT) && S_ISDIR(nd->inode->i_mode))
+	if ((open_flag & O_CREAT) &&
+	    (d_is_directory(nd->path.dentry) || d_is_autodir(nd->path.dentry)))
 		goto out;
 	error = -ENOTDIR;
-	if ((nd->flags & LOOKUP_DIRECTORY) && !can_lookup(nd->inode))
+	if ((nd->flags & LOOKUP_DIRECTORY) && !d_is_directory(nd->path.dentry))
 		goto out;
 	if (!S_ISREG(nd->inode->i_mode))
 		will_truncate = false;
@@ -3275,7 +3243,7 @@ struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt,
 	nd.root.mnt = mnt;
 	nd.root.dentry = dentry;
 
-	if (dentry->d_inode->i_op->follow_link && op->intent & LOOKUP_OPEN)
+	if (d_is_symlink(dentry) && op->intent & LOOKUP_OPEN)
 		return ERR_PTR(-ELOOP);
 
 	file = path_openat(-1, &filename, &nd, op, flags | LOOKUP_RCU);
@@ -3325,8 +3293,9 @@ struct dentry *kern_path_create(int dfd, const char *pathname,
 		goto unlock;
 
 	error = -EEXIST;
-	if (dentry->d_inode)
+	if (d_is_positive(dentry))
 		goto fail;
+
 	/*
 	 * Special case - lookup gave negative, but... we had foo/bar/
 	 * From the vfs_mknod() POV we just have a negative dentry -
@@ -3647,8 +3616,27 @@ SYSCALL_DEFINE1(rmdir, const char __user *, pathname)
 	return do_rmdir(AT_FDCWD, pathname);
 }
 
-int vfs_unlink(struct inode *dir, struct dentry *dentry)
+/**
+ * vfs_unlink - unlink a filesystem object
+ * @dir:	parent directory
+ * @dentry:	victim
+ * @delegated_inode: returns victim inode, if the inode is delegated.
+ *
+ * The caller must hold dir->i_mutex.
+ *
+ * If vfs_unlink discovers a delegation, it will return -EWOULDBLOCK and
+ * return a reference to the inode in delegated_inode.  The caller
+ * should then break the delegation on that inode and retry.  Because
+ * breaking a delegation may take a long time, the caller should drop
+ * dir->i_mutex before doing so.
+ *
+ * Alternatively, a caller may pass NULL for delegated_inode.  This may
+ * be appropriate for callers that expect the underlying filesystem not
+ * to be NFS exported.
+ */
+int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode)
 {
+	struct inode *target = dentry->d_inode;
 	int error = may_delete(dir, dentry, 0);
 
 	if (error)
@@ -3657,22 +3645,26 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry)
 	if (!dir->i_op->unlink)
 		return -EPERM;
 
-	mutex_lock(&dentry->d_inode->i_mutex);
+	mutex_lock(&target->i_mutex);
 	if (d_mountpoint(dentry))
 		error = -EBUSY;
 	else {
 		error = security_inode_unlink(dir, dentry);
 		if (!error) {
+			error = try_break_deleg(target, delegated_inode);
+			if (error)
+				goto out;
 			error = dir->i_op->unlink(dir, dentry);
 			if (!error)
 				dont_mount(dentry);
 		}
 	}
-	mutex_unlock(&dentry->d_inode->i_mutex);
+out:
+	mutex_unlock(&target->i_mutex);
 
 	/* We don't d_delete() NFS sillyrenamed files--they still exist. */
 	if (!error && !(dentry->d_flags & DCACHE_NFSFS_RENAMED)) {
-		fsnotify_link_count(dentry->d_inode);
+		fsnotify_link_count(target);
 		d_delete(dentry);
 	}
 
@@ -3692,6 +3684,7 @@ static long do_unlinkat(int dfd, const char __user *pathname)
 	struct dentry *dentry;
 	struct nameidata nd;
 	struct inode *inode = NULL;
+	struct inode *delegated_inode = NULL;
 	unsigned int lookup_flags = 0;
 retry:
 	name = user_path_parent(dfd, pathname, &nd, lookup_flags);
@@ -3706,7 +3699,7 @@ retry:
 	error = mnt_want_write(nd.path.mnt);
 	if (error)
 		goto exit1;
-
+retry_deleg:
 	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
 	dentry = lookup_hash(&nd);
 	error = PTR_ERR(dentry);
@@ -3715,19 +3708,25 @@ retry:
 		if (nd.last.name[nd.last.len])
 			goto slashes;
 		inode = dentry->d_inode;
-		if (!inode)
+		if (d_is_negative(dentry))
 			goto slashes;
 		ihold(inode);
 		error = security_path_unlink(&nd.path, dentry);
 		if (error)
 			goto exit2;
-		error = vfs_unlink(nd.path.dentry->d_inode, dentry);
+		error = vfs_unlink(nd.path.dentry->d_inode, dentry, &delegated_inode);
 exit2:
 		dput(dentry);
 	}
 	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
 	if (inode)
 		iput(inode);	/* truncate the inode here */
+	inode = NULL;
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
 	mnt_drop_write(nd.path.mnt);
 exit1:
 	path_put(&nd.path);
@@ -3740,8 +3739,12 @@ exit1:
 	return error;
 
 slashes:
-	error = !dentry->d_inode ? -ENOENT :
-		S_ISDIR(dentry->d_inode->i_mode) ? -EISDIR : -ENOTDIR;
+	if (d_is_negative(dentry))
+		error = -ENOENT;
+	else if (d_is_directory(dentry) || d_is_autodir(dentry))
+		error = -EISDIR;
+	else
+		error = -ENOTDIR;
 	goto exit2;
 }
 
@@ -3817,7 +3820,26 @@ SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newn
 	return sys_symlinkat(oldname, AT_FDCWD, newname);
 }
 
-int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry)
+/**
+ * vfs_link - create a new link
+ * @old_dentry:	object to be linked
+ * @dir:	new parent
+ * @new_dentry:	where to create the new link
+ * @delegated_inode: returns inode needing a delegation break
+ *
+ * The caller must hold dir->i_mutex
+ *
+ * If vfs_link discovers a delegation on the to-be-linked file in need
+ * of breaking, it will return -EWOULDBLOCK and return a reference to the
+ * inode in delegated_inode.  The caller should then break the delegation
+ * and retry.  Because breaking a delegation may take a long time, the
+ * caller should drop the i_mutex before doing so.
+ *
+ * Alternatively, a caller may pass NULL for delegated_inode.  This may
+ * be appropriate for callers that expect the underlying filesystem not
+ * to be NFS exported.
+ */
+int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode)
 {
 	struct inode *inode = old_dentry->d_inode;
 	unsigned max_links = dir->i_sb->s_max_links;
@@ -3853,8 +3875,11 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de
 		error =  -ENOENT;
 	else if (max_links && inode->i_nlink >= max_links)
 		error = -EMLINK;
-	else
-		error = dir->i_op->link(old_dentry, dir, new_dentry);
+	else {
+		error = try_break_deleg(inode, delegated_inode);
+		if (!error)
+			error = dir->i_op->link(old_dentry, dir, new_dentry);
+	}
 
 	if (!error && (inode->i_state & I_LINKABLE)) {
 		spin_lock(&inode->i_lock);
@@ -3881,6 +3906,7 @@ SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname,
 {
 	struct dentry *new_dentry;
 	struct path old_path, new_path;
+	struct inode *delegated_inode = NULL;
 	int how = 0;
 	int error;
 
@@ -3919,9 +3945,14 @@ retry:
 	error = security_path_link(old_path.dentry, &new_path, new_dentry);
 	if (error)
 		goto out_dput;
-	error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry);
+	error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode);
 out_dput:
 	done_path_create(&new_path, new_dentry);
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry;
+	}
 	if (retry_estale(error, how)) {
 		how |= LOOKUP_REVAL;
 		goto retry;
@@ -3946,7 +3977,8 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname
  *	   That's where 4.4 screws up. Current fix: serialization on
  *	   sb->s_vfs_rename_mutex. We might be more accurate, but that's another
  *	   story.
- *	c) we have to lock _three_ objects - parents and victim (if it exists).
+ *	c) we have to lock _four_ objects - parents and victim (if it exists),
+ *	   and source (if it is not a directory).
  *	   And that - after we got ->i_mutex on parents (until then we don't know
  *	   whether the target exists).  Solution: try to be smart with locking
  *	   order for inodes.  We rely on the fact that tree topology may change
@@ -4019,9 +4051,11 @@ out:
 }
 
 static 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 inode **delegated_inode)
 {
 	struct inode *target = new_dentry->d_inode;
+	struct inode *source = old_dentry->d_inode;
 	int error;
 
 	error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry);
@@ -4029,13 +4063,20 @@ static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry,
 		return error;
 
 	dget(new_dentry);
-	if (target)
-		mutex_lock(&target->i_mutex);
+	lock_two_nondirectories(source, target);
 
 	error = -EBUSY;
 	if (d_mountpoint(old_dentry)||d_mountpoint(new_dentry))
 		goto out;
 
+	error = try_break_deleg(source, delegated_inode);
+	if (error)
+		goto out;
+	if (target) {
+		error = try_break_deleg(target, delegated_inode);
+		if (error)
+			goto out;
+	}
 	error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
 	if (error)
 		goto out;
@@ -4045,17 +4086,38 @@ static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry,
 	if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE))
 		d_move(old_dentry, new_dentry);
 out:
-	if (target)
-		mutex_unlock(&target->i_mutex);
+	unlock_two_nondirectories(source, target);
 	dput(new_dentry);
 	return error;
 }
 
+/**
+ * vfs_rename - rename a filesystem object
+ * @old_dir:	parent of source
+ * @old_dentry:	source
+ * @new_dir:	parent of destination
+ * @new_dentry:	destination
+ * @delegated_inode: returns an inode needing a delegation break
+ *
+ * The caller must hold multiple mutexes--see lock_rename()).
+ *
+ * If vfs_rename discovers a delegation in need of breaking at either
+ * the source or destination, it will return -EWOULDBLOCK and return a
+ * reference to the inode in delegated_inode.  The caller should then
+ * break the delegation and retry.  Because breaking a delegation may
+ * take a long time, the caller should drop all locks before doing
+ * so.
+ *
+ * Alternatively, a caller may pass NULL for delegated_inode.  This may
+ * be appropriate for callers that expect the underlying filesystem not
+ * to be NFS exported.
+ */
 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 inode **delegated_inode)
 {
 	int error;
-	int is_dir = S_ISDIR(old_dentry->d_inode->i_mode);
+	int is_dir = d_is_directory(old_dentry) || d_is_autodir(old_dentry);
 	const unsigned char *old_name;
 
 	if (old_dentry->d_inode == new_dentry->d_inode)
@@ -4080,7 +4142,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (is_dir)
 		error = vfs_rename_dir(old_dir,old_dentry,new_dir,new_dentry);
 	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,delegated_inode);
 	if (!error)
 		fsnotify_move(old_dir, new_dir, old_name, is_dir,
 			      new_dentry->d_inode, old_dentry);
@@ -4096,6 +4158,7 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
 	struct dentry *old_dentry, *new_dentry;
 	struct dentry *trap;
 	struct nameidata oldnd, newnd;
+	struct inode *delegated_inode = NULL;
 	struct filename *from;
 	struct filename *to;
 	unsigned int lookup_flags = 0;
@@ -4135,6 +4198,7 @@ retry:
 	newnd.flags &= ~LOOKUP_PARENT;
 	newnd.flags |= LOOKUP_RENAME_TARGET;
 
+retry_deleg:
 	trap = lock_rename(new_dir, old_dir);
 
 	old_dentry = lookup_hash(&oldnd);
@@ -4143,10 +4207,10 @@ retry:
 		goto exit3;
 	/* source must exist */
 	error = -ENOENT;
-	if (!old_dentry->d_inode)
+	if (d_is_negative(old_dentry))
 		goto exit4;
 	/* unless the source is a directory trailing slashes give -ENOTDIR */
-	if (!S_ISDIR(old_dentry->d_inode->i_mode)) {
+	if (!d_is_directory(old_dentry) && !d_is_autodir(old_dentry)) {
 		error = -ENOTDIR;
 		if (oldnd.last.name[oldnd.last.len])
 			goto exit4;
@@ -4171,13 +4235,19 @@ retry:
 	if (error)
 		goto exit5;
 	error = vfs_rename(old_dir->d_inode, old_dentry,
-				   new_dir->d_inode, new_dentry);
+				   new_dir->d_inode, new_dentry,
+				   &delegated_inode);
 exit5:
 	dput(new_dentry);
 exit4:
 	dput(old_dentry);
 exit3:
 	unlock_rename(new_dir, old_dir);
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
 	mnt_drop_write(oldnd.path.mnt);
 exit2:
 	if (retry_estale(error, lookup_flags))

fs/namespace.c

@@ -39,7 +39,7 @@ static int mnt_group_start = 1;
 static struct list_head *mount_hashtable __read_mostly;
 static struct list_head *mountpoint_hashtable __read_mostly;
 static struct kmem_cache *mnt_cache __read_mostly;
-static struct rw_semaphore namespace_sem;
+static DECLARE_RWSEM(namespace_sem);
 
 /* /sys/fs */
 struct kobject *fs_kobj;
@@ -53,7 +53,7 @@ EXPORT_SYMBOL_GPL(fs_kobj);
  * It should be taken for write in all cases where the vfsmount
  * tree or hash is modified or when a vfsmount structure is modified.
  */
-DEFINE_BRLOCK(vfsmount_lock);
+__cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock);
 
 static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry)
 {
@@ -63,8 +63,6 @@ static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry)
 	return tmp & (HASH_SIZE - 1);
 }
 
-#define MNT_WRITER_UNDERFLOW_LIMIT -(1<<16)
-
 /*
  * allocation is serialized by namespace_sem, but we need the spinlock to
  * serialize with freeing.
@@ -458,7 +456,7 @@ static int mnt_make_readonly(struct mount *mnt)
 {
 	int ret = 0;
 
-	br_write_lock(&vfsmount_lock);
+	lock_mount_hash();
 	mnt->mnt.mnt_flags |= MNT_WRITE_HOLD;
 	/*
 	 * After storing MNT_WRITE_HOLD, we'll read the counters. This store
@@ -492,15 +490,15 @@ static int mnt_make_readonly(struct mount *mnt)
 	 */
 	smp_wmb();
 	mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD;
-	br_write_unlock(&vfsmount_lock);
+	unlock_mount_hash();
 	return ret;
 }
 
 static void __mnt_unmake_readonly(struct mount *mnt)
 {
-	br_write_lock(&vfsmount_lock);
+	lock_mount_hash();
 	mnt->mnt.mnt_flags &= ~MNT_READONLY;
-	br_write_unlock(&vfsmount_lock);
+	unlock_mount_hash();
 }
 
 int sb_prepare_remount_readonly(struct super_block *sb)
@@ -512,7 +510,7 @@ int sb_prepare_remount_readonly(struct super_block *sb)
 	if (atomic_long_read(&sb->s_remove_count))
 		return -EBUSY;
 
-	br_write_lock(&vfsmount_lock);
+	lock_mount_hash();
 	list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) {
 		if (!(mnt->mnt.mnt_flags & MNT_READONLY)) {
 			mnt->mnt.mnt_flags |= MNT_WRITE_HOLD;
@@ -534,7 +532,7 @@ int sb_prepare_remount_readonly(struct super_block *sb)
 		if (mnt->mnt.mnt_flags & MNT_WRITE_HOLD)
 			mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD;
 	}
-	br_write_unlock(&vfsmount_lock);
+	unlock_mount_hash();
 
 	return err;
 }
@@ -549,30 +547,56 @@ static void free_vfsmnt(struct mount *mnt)
 	kmem_cache_free(mnt_cache, mnt);
 }
 
+/* call under rcu_read_lock */
+bool legitimize_mnt(struct vfsmount *bastard, unsigned seq)
+{
+	struct mount *mnt;
+	if (read_seqretry(&mount_lock, seq))
+		return false;
+	if (bastard == NULL)
+		return true;
+	mnt = real_mount(bastard);
+	mnt_add_count(mnt, 1);
+	if (likely(!read_seqretry(&mount_lock, seq)))
+		return true;
+	if (bastard->mnt_flags & MNT_SYNC_UMOUNT) {
+		mnt_add_count(mnt, -1);
+		return false;
+	}
+	rcu_read_unlock();
+	mntput(bastard);
+	rcu_read_lock();
+	return false;
+}
+
 /*
- * find the first or last mount at @dentry on vfsmount @mnt depending on
- * @dir. If @dir is set return the first mount else return the last mount.
- * vfsmount_lock must be held for read or write.
+ * find the first mount at @dentry on vfsmount @mnt.
+ * call under rcu_read_lock()
  */
-struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry,
-			      int dir)
+struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
 {
 	struct list_head *head = mount_hashtable + hash(mnt, dentry);
-	struct list_head *tmp = head;
-	struct mount *p, *found = NULL;
+	struct mount *p;
 
-	for (;;) {
-		tmp = dir ? tmp->next : tmp->prev;
-		p = NULL;
-		if (tmp == head)
-			break;
-		p = list_entry(tmp, struct mount, mnt_hash);
-		if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry) {
-			found = p;
-			break;
-		}
-	}
-	return found;
+	list_for_each_entry_rcu(p, head, mnt_hash)
+		if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry)
+			return p;
+	return NULL;
+}
+
+/*
+ * find the last mount at @dentry on vfsmount @mnt.
+ * mount_lock must be held.
+ */
+struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry)
+{
+	struct list_head *head = mount_hashtable + hash(mnt, dentry);
+	struct mount *p;
+
+	list_for_each_entry_reverse(p, head, mnt_hash)
+		if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry)
+			return p;
+	return NULL;
 }
 
 /*
@@ -594,17 +618,17 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry,
 struct vfsmount *lookup_mnt(struct path *path)
 {
 	struct mount *child_mnt;
+	struct vfsmount *m;
+	unsigned seq;
 
-	br_read_lock(&vfsmount_lock);
-	child_mnt = __lookup_mnt(path->mnt, path->dentry, 1);
-	if (child_mnt) {
-		mnt_add_count(child_mnt, 1);
-		br_read_unlock(&vfsmount_lock);
-		return &child_mnt->mnt;
-	} else {
-		br_read_unlock(&vfsmount_lock);
-		return NULL;
-	}
+	rcu_read_lock();
+	do {
+		seq = read_seqbegin(&mount_lock);
+		child_mnt = __lookup_mnt(path->mnt, path->dentry);
+		m = child_mnt ? &child_mnt->mnt : NULL;
+	} while (!legitimize_mnt(m, seq));
+	rcu_read_unlock();
+	return m;
 }
 
 static struct mountpoint *new_mountpoint(struct dentry *dentry)
@@ -796,9 +820,9 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void
 	mnt->mnt.mnt_sb = root->d_sb;
 	mnt->mnt_mountpoint = mnt->mnt.mnt_root;
 	mnt->mnt_parent = mnt;
-	br_write_lock(&vfsmount_lock);
+	lock_mount_hash();
 	list_add_tail(&mnt->mnt_instance, &root->d_sb->s_mounts);
-	br_write_unlock(&vfsmount_lock);
+	unlock_mount_hash();
 	return &mnt->mnt;
 }
 EXPORT_SYMBOL_GPL(vfs_kern_mount);
@@ -839,9 +863,9 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 	mnt->mnt.mnt_root = dget(root);
 	mnt->mnt_mountpoint = mnt->mnt.mnt_root;
 	mnt->mnt_parent = mnt;
-	br_write_lock(&vfsmount_lock);
+	lock_mount_hash();
 	list_add_tail(&mnt->mnt_instance, &sb->s_mounts);
-	br_write_unlock(&vfsmount_lock);
+	unlock_mount_hash();
 
 	if ((flag & CL_SLAVE) ||
 	    ((flag & CL_SHARED_TO_SLAVE) && IS_MNT_SHARED(old))) {
@@ -872,64 +896,66 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 	return ERR_PTR(err);
 }
 
-static inline void mntfree(struct mount *mnt)
+static void delayed_free(struct rcu_head *head)
 {
-	struct vfsmount *m = &mnt->mnt;
-	struct super_block *sb = m->mnt_sb;
-
-	/*
-	 * This probably indicates that somebody messed
-	 * up a mnt_want/drop_write() pair.  If this
-	 * happens, the filesystem was probably unable
-	 * to make r/w->r/o transitions.
-	 */
-	/*
-	 * The locking used to deal with mnt_count decrement provides barriers,
-	 * so mnt_get_writers() below is safe.
-	 */
-	WARN_ON(mnt_get_writers(mnt));
-	fsnotify_vfsmount_delete(m);
-	dput(m->mnt_root);
-	free_vfsmnt(mnt);
-	deactivate_super(sb);
+	struct mount *mnt = container_of(head, struct mount, mnt_rcu);
+	kfree(mnt->mnt_devname);
+#ifdef CONFIG_SMP
+	free_percpu(mnt->mnt_pcp);
+#endif
+	kmem_cache_free(mnt_cache, mnt);
 }
 
 static void mntput_no_expire(struct mount *mnt)
 {
 put_again:
-#ifdef CONFIG_SMP
-	br_read_lock(&vfsmount_lock);
-	if (likely(mnt->mnt_ns)) {
-		/* shouldn't be the last one */
-		mnt_add_count(mnt, -1);
-		br_read_unlock(&vfsmount_lock);
+	rcu_read_lock();
+	mnt_add_count(mnt, -1);
+	if (likely(mnt->mnt_ns)) { /* shouldn't be the last one */
+		rcu_read_unlock();
 		return;
 	}
-	br_read_unlock(&vfsmount_lock);
-
-	br_write_lock(&vfsmount_lock);
-	mnt_add_count(mnt, -1);
+	lock_mount_hash();
 	if (mnt_get_count(mnt)) {
-		br_write_unlock(&vfsmount_lock);
+		rcu_read_unlock();
+		unlock_mount_hash();
 		return;
 	}
-#else
-	mnt_add_count(mnt, -1);
-	if (likely(mnt_get_count(mnt)))
-		return;
-	br_write_lock(&vfsmount_lock);
-#endif
 	if (unlikely(mnt->mnt_pinned)) {
 		mnt_add_count(mnt, mnt->mnt_pinned + 1);
 		mnt->mnt_pinned = 0;
-		br_write_unlock(&vfsmount_lock);
+		rcu_read_unlock();
+		unlock_mount_hash();
 		acct_auto_close_mnt(&mnt->mnt);
 		goto put_again;
 	}
+	if (unlikely(mnt->mnt.mnt_flags & MNT_DOOMED)) {
+		rcu_read_unlock();
+		unlock_mount_hash();
+		return;
+	}
+	mnt->mnt.mnt_flags |= MNT_DOOMED;
+	rcu_read_unlock();
 
 	list_del(&mnt->mnt_instance);
-	br_write_unlock(&vfsmount_lock);
-	mntfree(mnt);
+	unlock_mount_hash();
+
+	/*
+	 * This probably indicates that somebody messed
+	 * up a mnt_want/drop_write() pair.  If this
+	 * happens, the filesystem was probably unable
+	 * to make r/w->r/o transitions.
+	 */
+	/*
+	 * The locking used to deal with mnt_count decrement provides barriers,
+	 * so mnt_get_writers() below is safe.
+	 */
+	WARN_ON(mnt_get_writers(mnt));
+	fsnotify_vfsmount_delete(&mnt->mnt);
+	dput(mnt->mnt.mnt_root);
+	deactivate_super(mnt->mnt.mnt_sb);
+	mnt_free_id(mnt);
+	call_rcu(&mnt->mnt_rcu, delayed_free);
 }
 
 void mntput(struct vfsmount *mnt)
@@ -954,21 +980,21 @@ EXPORT_SYMBOL(mntget);
 
 void mnt_pin(struct vfsmount *mnt)
 {
-	br_write_lock(&vfsmount_lock);
+	lock_mount_hash();
 	real_mount(mnt)->mnt_pinned++;
-	br_write_unlock(&vfsmount_lock);
+	unlock_mount_hash();
 }
 EXPORT_SYMBOL(mnt_pin);
 
 void mnt_unpin(struct vfsmount *m)
 {
 	struct mount *mnt = real_mount(m);
-	br_write_lock(&vfsmount_lock);
+	lock_mount_hash();
 	if (mnt->mnt_pinned) {
 		mnt_add_count(mnt, 1);
 		mnt->mnt_pinned--;
 	}
-	br_write_unlock(&vfsmount_lock);
+	unlock_mount_hash();
 }
 EXPORT_SYMBOL(mnt_unpin);
 
@@ -1085,12 +1111,12 @@ int may_umount_tree(struct vfsmount *m)
 	BUG_ON(!m);
 
 	/* write lock needed for mnt_get_count */
-	br_write_lock(&vfsmount_lock);
+	lock_mount_hash();
 	for (p = mnt; p; p = next_mnt(p, mnt)) {
 		actual_refs += mnt_get_count(p);
 		minimum_refs += 2;
 	}
-	br_write_unlock(&vfsmount_lock);
+	unlock_mount_hash();
 
 	if (actual_refs > minimum_refs)
 		return 0;
@@ -1117,10 +1143,10 @@ int may_umount(struct vfsmount *mnt)
 {
 	int ret = 1;
 	down_read(&namespace_sem);
-	br_write_lock(&vfsmount_lock);
+	lock_mount_hash();
 	if (propagate_mount_busy(real_mount(mnt), 2))
 		ret = 0;
-	br_write_unlock(&vfsmount_lock);
+	unlock_mount_hash();
 	up_read(&namespace_sem);
 	return ret;
 }
@@ -1142,23 +1168,13 @@ static void namespace_unlock(void)
 	list_splice_init(&unmounted, &head);
 	up_write(&namespace_sem);
 
+	synchronize_rcu();
+
 	while (!list_empty(&head)) {
 		mnt = list_first_entry(&head, struct mount, mnt_hash);
 		list_del_init(&mnt->mnt_hash);
-		if (mnt_has_parent(mnt)) {
-			struct dentry *dentry;
-			struct mount *m;
-
-			br_write_lock(&vfsmount_lock);
-			dentry = mnt->mnt_mountpoint;
-			m = mnt->mnt_parent;
-			mnt->mnt_mountpoint = mnt->mnt.mnt_root;
-			mnt->mnt_parent = mnt;
-			m->mnt_ghosts--;
-			br_write_unlock(&vfsmount_lock);
-			dput(dentry);
-			mntput(&m->mnt);
-		}
+		if (mnt->mnt_ex_mountpoint.mnt)
+			path_put(&mnt->mnt_ex_mountpoint);
 		mntput(&mnt->mnt);
 	}
 }
@@ -1169,10 +1185,13 @@ static inline void namespace_lock(void)
 }
 
 /*
- * vfsmount lock must be held for write
+ * mount_lock must be held
  * namespace_sem must be held for write
+ * how = 0 => just this tree, don't propagate
+ * how = 1 => propagate; we know that nobody else has reference to any victims
+ * how = 2 => lazy umount
  */
-void umount_tree(struct mount *mnt, int propagate)
+void umount_tree(struct mount *mnt, int how)
 {
 	LIST_HEAD(tmp_list);
 	struct mount *p;
@@ -1180,7 +1199,7 @@ void umount_tree(struct mount *mnt, int propagate)
 	for (p = mnt; p; p = next_mnt(p, mnt))
 		list_move(&p->mnt_hash, &tmp_list);
 
-	if (propagate)
+	if (how)
 		propagate_umount(&tmp_list);
 
 	list_for_each_entry(p, &tmp_list, mnt_hash) {
@@ -1188,10 +1207,16 @@ void umount_tree(struct mount *mnt, int propagate)
 		list_del_init(&p->mnt_list);
 		__touch_mnt_namespace(p->mnt_ns);
 		p->mnt_ns = NULL;
+		if (how < 2)
+			p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
 		list_del_init(&p->mnt_child);
 		if (mnt_has_parent(p)) {
-			p->mnt_parent->mnt_ghosts++;
 			put_mountpoint(p->mnt_mp);
+			/* move the reference to mountpoint into ->mnt_ex_mountpoint */
+			p->mnt_ex_mountpoint.dentry = p->mnt_mountpoint;
+			p->mnt_ex_mountpoint.mnt = &p->mnt_parent->mnt;
+			p->mnt_mountpoint = p->mnt.mnt_root;
+			p->mnt_parent = p;
 			p->mnt_mp = NULL;
 		}
 		change_mnt_propagation(p, MS_PRIVATE);
@@ -1225,12 +1250,12 @@ static int do_umount(struct mount *mnt, int flags)
 		 * probably don't strictly need the lock here if we examined
 		 * all race cases, but it's a slowpath.
 		 */
-		br_write_lock(&vfsmount_lock);
+		lock_mount_hash();
 		if (mnt_get_count(mnt) != 2) {
-			br_write_unlock(&vfsmount_lock);
+			unlock_mount_hash();
 			return -EBUSY;
 		}
-		br_write_unlock(&vfsmount_lock);
+		unlock_mount_hash();
 
 		if (!xchg(&mnt->mnt_expiry_mark, 1))
 			return -EAGAIN;
@@ -1272,19 +1297,23 @@ static int do_umount(struct mount *mnt, int flags)
 	}
 
 	namespace_lock();
-	br_write_lock(&vfsmount_lock);
+	lock_mount_hash();
 	event++;
 
-	if (!(flags & MNT_DETACH))
-		shrink_submounts(mnt);
-
-	retval = -EBUSY;
-	if (flags & MNT_DETACH || !propagate_mount_busy(mnt, 2)) {
+	if (flags & MNT_DETACH) {
 		if (!list_empty(&mnt->mnt_list))
-			umount_tree(mnt, 1);
+			umount_tree(mnt, 2);
 		retval = 0;
+	} else {
+		shrink_submounts(mnt);
+		retval = -EBUSY;
+		if (!propagate_mount_busy(mnt, 2)) {
+			if (!list_empty(&mnt->mnt_list))
+				umount_tree(mnt, 1);
+			retval = 0;
+		}
 	}
-	br_write_unlock(&vfsmount_lock);
+	unlock_mount_hash();
 	namespace_unlock();
 	return retval;
 }
@@ -1427,18 +1456,18 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 			q = clone_mnt(p, p->mnt.mnt_root, flag);
 			if (IS_ERR(q))
 				goto out;
-			br_write_lock(&vfsmount_lock);
+			lock_mount_hash();
 			list_add_tail(&q->mnt_list, &res->mnt_list);
 			attach_mnt(q, parent, p->mnt_mp);
-			br_write_unlock(&vfsmount_lock);
+			unlock_mount_hash();
 		}
 	}
 	return res;
 out:
 	if (res) {
-		br_write_lock(&vfsmount_lock);
+		lock_mount_hash();
 		umount_tree(res, 0);
-		br_write_unlock(&vfsmount_lock);
+		unlock_mount_hash();
 	}
 	return q;
 }
@@ -1460,9 +1489,9 @@ struct vfsmount *collect_mounts(struct path *path)
 void drop_collected_mounts(struct vfsmount *mnt)
 {
 	namespace_lock();
-	br_write_lock(&vfsmount_lock);
+	lock_mount_hash();
 	umount_tree(real_mount(mnt), 0);
-	br_write_unlock(&vfsmount_lock);
+	unlock_mount_hash();
 	namespace_unlock();
 }
 
@@ -1589,7 +1618,7 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 	if (err)
 		goto out_cleanup_ids;
 
-	br_write_lock(&vfsmount_lock);
+	lock_mount_hash();
 
 	if (IS_MNT_SHARED(dest_mnt)) {
 		for (p = source_mnt; p; p = next_mnt(p, source_mnt))
@@ -1608,7 +1637,7 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 		list_del_init(&child->mnt_hash);
 		commit_tree(child);
 	}
-	br_write_unlock(&vfsmount_lock);
+	unlock_mount_hash();
 
 	return 0;
 
@@ -1710,10 +1739,10 @@ static int do_change_type(struct path *path, int flag)
 			goto out_unlock;
 	}
 
-	br_write_lock(&vfsmount_lock);
+	lock_mount_hash();
 	for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL))
 		change_mnt_propagation(m, type);
-	br_write_unlock(&vfsmount_lock);
+	unlock_mount_hash();
 
  out_unlock:
 	namespace_unlock();
@@ -1785,9 +1814,9 @@ static int do_loopback(struct path *path, const char *old_name,
 
 	err = graft_tree(mnt, parent, mp);
 	if (err) {
-		br_write_lock(&vfsmount_lock);
+		lock_mount_hash();
 		umount_tree(mnt, 0);
-		br_write_unlock(&vfsmount_lock);
+		unlock_mount_hash();
 	}
 out2:
 	unlock_mount(mp);
@@ -1846,17 +1875,13 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
 	else
 		err = do_remount_sb(sb, flags, data, 0);
 	if (!err) {
-		br_write_lock(&vfsmount_lock);
+		lock_mount_hash();
 		mnt_flags |= mnt->mnt.mnt_flags & MNT_PROPAGATION_MASK;
 		mnt->mnt.mnt_flags = mnt_flags;
-		br_write_unlock(&vfsmount_lock);
-	}
-	up_write(&sb->s_umount);
-	if (!err) {
-		br_write_lock(&vfsmount_lock);
 		touch_mnt_namespace(mnt->mnt_ns);
-		br_write_unlock(&vfsmount_lock);
+		unlock_mount_hash();
 	}
+	up_write(&sb->s_umount);
 	return err;
 }
 
@@ -1972,7 +1997,7 @@ static int do_add_mount(struct mount *newmnt, struct path *path, int mnt_flags)
 	struct mount *parent;
 	int err;
 
-	mnt_flags &= ~(MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL);
+	mnt_flags &= ~(MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | MNT_DOOMED | MNT_SYNC_UMOUNT);
 
 	mp = lock_mount(path);
 	if (IS_ERR(mp))
@@ -2077,9 +2102,7 @@ fail:
 	/* remove m from any expiration list it may be on */
 	if (!list_empty(&mnt->mnt_expire)) {
 		namespace_lock();
-		br_write_lock(&vfsmount_lock);
 		list_del_init(&mnt->mnt_expire);
-		br_write_unlock(&vfsmount_lock);
 		namespace_unlock();
 	}
 	mntput(m);
@@ -2095,11 +2118,9 @@ fail:
 void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list)
 {
 	namespace_lock();
-	br_write_lock(&vfsmount_lock);
 
 	list_add_tail(&real_mount(mnt)->mnt_expire, expiry_list);
 
-	br_write_unlock(&vfsmount_lock);
 	namespace_unlock();
 }
 EXPORT_SYMBOL(mnt_set_expiry);
@@ -2118,7 +2139,7 @@ void mark_mounts_for_expiry(struct list_head *mounts)
 		return;
 
 	namespace_lock();
-	br_write_lock(&vfsmount_lock);
+	lock_mount_hash();
 
 	/* extract from the expiration list every vfsmount that matches the
 	 * following criteria:
@@ -2137,7 +2158,7 @@ void mark_mounts_for_expiry(struct list_head *mounts)
 		touch_mnt_namespace(mnt->mnt_ns);
 		umount_tree(mnt, 1);
 	}
-	br_write_unlock(&vfsmount_lock);
+	unlock_mount_hash();
 	namespace_unlock();
 }
 
@@ -2193,7 +2214,7 @@ resume:
  * process a list of expirable mountpoints with the intent of discarding any
  * submounts of a specific parent mountpoint
  *
- * vfsmount_lock must be held for write
+ * mount_lock must be held for write
  */
 static void shrink_submounts(struct mount *mnt)
 {
@@ -2414,20 +2435,25 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns)
 	return new_ns;
 }
 
-/*
- * Allocate a new namespace structure and populate it with contents
- * copied from the namespace of the passed in task structure.
- */
-static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
-		struct user_namespace *user_ns, struct fs_struct *fs)
+struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
+		struct user_namespace *user_ns, struct fs_struct *new_fs)
 {
 	struct mnt_namespace *new_ns;
 	struct vfsmount *rootmnt = NULL, *pwdmnt = NULL;
 	struct mount *p, *q;
-	struct mount *old = mnt_ns->root;
+	struct mount *old;
 	struct mount *new;
 	int copy_flags;
 
+	BUG_ON(!ns);
+
+	if (likely(!(flags & CLONE_NEWNS))) {
+		get_mnt_ns(ns);
+		return ns;
+	}
+
+	old = ns->root;
+
 	new_ns = alloc_mnt_ns(user_ns);
 	if (IS_ERR(new_ns))
 		return new_ns;
@@ -2435,7 +2461,7 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
 	namespace_lock();
 	/* First pass: copy the tree topology */
 	copy_flags = CL_COPY_UNBINDABLE | CL_EXPIRE;
-	if (user_ns != mnt_ns->user_ns)
+	if (user_ns != ns->user_ns)
 		copy_flags |= CL_SHARED_TO_SLAVE | CL_UNPRIVILEGED;
 	new = copy_tree(old, old->mnt.mnt_root, copy_flags);
 	if (IS_ERR(new)) {
@@ -2444,9 +2470,7 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
 		return ERR_CAST(new);
 	}
 	new_ns->root = new;
-	br_write_lock(&vfsmount_lock);
 	list_add_tail(&new_ns->list, &new->mnt_list);
-	br_write_unlock(&vfsmount_lock);
 
 	/*
 	 * Second pass: switch the tsk->fs->* elements and mark new vfsmounts
@@ -2457,13 +2481,13 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
 	q = new;
 	while (p) {
 		q->mnt_ns = new_ns;
-		if (fs) {
-			if (&p->mnt == fs->root.mnt) {
-				fs->root.mnt = mntget(&q->mnt);
+		if (new_fs) {
+			if (&p->mnt == new_fs->root.mnt) {
+				new_fs->root.mnt = mntget(&q->mnt);
 				rootmnt = &p->mnt;
 			}
-			if (&p->mnt == fs->pwd.mnt) {
-				fs->pwd.mnt = mntget(&q->mnt);
+			if (&p->mnt == new_fs->pwd.mnt) {
+				new_fs->pwd.mnt = mntget(&q->mnt);
 				pwdmnt = &p->mnt;
 			}
 		}
@@ -2484,23 +2508,6 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
 	return new_ns;
 }
 
-struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
-		struct user_namespace *user_ns, struct fs_struct *new_fs)
-{
-	struct mnt_namespace *new_ns;
-
-	BUG_ON(!ns);
-	get_mnt_ns(ns);
-
-	if (!(flags & CLONE_NEWNS))
-		return ns;
-
-	new_ns = dup_mnt_ns(ns, user_ns, new_fs);
-
-	put_mnt_ns(ns);
-	return new_ns;
-}
-
 /**
  * create_mnt_ns - creates a private namespace and adds a root filesystem
  * @mnt: pointer to the new root filesystem mountpoint
@@ -2593,7 +2600,7 @@ out_type:
 /*
  * Return true if path is reachable from root
  *
- * namespace_sem or vfsmount_lock is held
+ * namespace_sem or mount_lock is held
  */
 bool is_path_reachable(struct mount *mnt, struct dentry *dentry,
 			 const struct path *root)
@@ -2608,9 +2615,9 @@ bool is_path_reachable(struct mount *mnt, struct dentry *dentry,
 int path_is_under(struct path *path1, struct path *path2)
 {
 	int res;
-	br_read_lock(&vfsmount_lock);
+	read_seqlock_excl(&mount_lock);
 	res = is_path_reachable(real_mount(path1->mnt), path1->dentry, path2);
-	br_read_unlock(&vfsmount_lock);
+	read_sequnlock_excl(&mount_lock);
 	return res;
 }
 EXPORT_SYMBOL(path_is_under);
@@ -2701,7 +2708,7 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 	if (!is_path_reachable(old_mnt, old.dentry, &new))
 		goto out4;
 	root_mp->m_count++; /* pin it so it won't go away */
-	br_write_lock(&vfsmount_lock);
+	lock_mount_hash();
 	detach_mnt(new_mnt, &parent_path);
 	detach_mnt(root_mnt, &root_parent);
 	if (root_mnt->mnt.mnt_flags & MNT_LOCKED) {
@@ -2713,7 +2720,7 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 	/* mount new_root on / */
 	attach_mnt(new_mnt, real_mount(root_parent.mnt), root_mp);
 	touch_mnt_namespace(current->nsproxy->mnt_ns);
-	br_write_unlock(&vfsmount_lock);
+	unlock_mount_hash();
 	chroot_fs_refs(&root, &new);
 	put_mountpoint(root_mp);
 	error = 0;
@@ -2767,8 +2774,6 @@ void __init mnt_init(void)
 	unsigned u;
 	int err;
 
-	init_rwsem(&namespace_sem);
-
 	mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount),
 			0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
 
@@ -2785,8 +2790,6 @@ void __init mnt_init(void)
 	for (u = 0; u < HASH_SIZE; u++)
 		INIT_LIST_HEAD(&mountpoint_hashtable[u]);
 
-	br_lock_init(&vfsmount_lock);
-
 	err = sysfs_init();
 	if (err)
 		printk(KERN_WARNING "%s: sysfs_init error: %d\n",
@@ -2802,11 +2805,7 @@ void put_mnt_ns(struct mnt_namespace *ns)
 {
 	if (!atomic_dec_and_test(&ns->count))
 		return;
-	namespace_lock();
-	br_write_lock(&vfsmount_lock);
-	umount_tree(ns->root, 0);
-	br_write_unlock(&vfsmount_lock);
-	namespace_unlock();
+	drop_collected_mounts(&ns->root->mnt);
 	free_mnt_ns(ns);
 }
 
@@ -2829,9 +2828,8 @@ void kern_unmount(struct vfsmount *mnt)
 {
 	/* release long term mount so mount point can be released */
 	if (!IS_ERR_OR_NULL(mnt)) {
-		br_write_lock(&vfsmount_lock);
 		real_mount(mnt)->mnt_ns = NULL;
-		br_write_unlock(&vfsmount_lock);
+		synchronize_rcu();	/* yecchhh... */
 		mntput(mnt);
 	}
 }
@@ -2875,7 +2873,7 @@ bool fs_fully_visible(struct file_system_type *type)
 	if (unlikely(!ns))
 		return false;
 
-	namespace_lock();
+	down_read(&namespace_sem);
 	list_for_each_entry(mnt, &ns->list, mnt_list) {
 		struct mount *child;
 		if (mnt->mnt.mnt_sb->s_type != type)
@@ -2896,7 +2894,7 @@ bool fs_fully_visible(struct file_system_type *type)
 	next:	;
 	}
 found:
-	namespace_unlock();
+	up_read(&namespace_sem);
 	return visible;
 }
 

fs/ncpfs/dir.c

@@ -339,9 +339,8 @@ ncp_lookup_validate(struct dentry *dentry, unsigned int flags)
 	if (val)
 		goto finished;
 
-	DDPRINTK("ncp_lookup_validate: %s/%s not valid, age=%ld, server lookup\n",
-		dentry->d_parent->d_name.name, dentry->d_name.name,
-		NCP_GET_AGE(dentry));
+	DDPRINTK("ncp_lookup_validate: %pd2 not valid, age=%ld, server lookup\n",
+		dentry, NCP_GET_AGE(dentry));
 
 	len = sizeof(__name);
 	if (ncp_is_server_root(dir)) {
@@ -359,8 +358,8 @@ ncp_lookup_validate(struct dentry *dentry, unsigned int flags)
 			res = ncp_obtain_info(server, dir, __name, &(finfo.i));
 	}
 	finfo.volume = finfo.i.volNumber;
-	DDPRINTK("ncp_lookup_validate: looked for %s/%s, res=%d\n",
-		dentry->d_parent->d_name.name, __name, res);
+	DDPRINTK("ncp_lookup_validate: looked for %pd/%s, res=%d\n",
+		dentry->d_parent, __name, res);
 	/*
 	 * If we didn't find it, or if it has a different dirEntNum to
 	 * what we remember, it's not valid any more.
@@ -454,8 +453,7 @@ static int ncp_readdir(struct file *file, struct dir_context *ctx)
 	ctl.page  = NULL;
 	ctl.cache = NULL;
 
-	DDPRINTK("ncp_readdir: reading %s/%s, pos=%d\n",
-		dentry->d_parent->d_name.name, dentry->d_name.name,
+	DDPRINTK("ncp_readdir: reading %pD2, pos=%d\n", file,
 		(int) ctx->pos);
 
 	result = -EIO;
@@ -740,12 +738,10 @@ ncp_do_readdir(struct file *file, struct dir_context *ctx,
 	int more;
 	size_t bufsize;
 
-	DPRINTK("ncp_do_readdir: %s/%s, fpos=%ld\n",
-		dentry->d_parent->d_name.name, dentry->d_name.name,
+	DPRINTK("ncp_do_readdir: %pD2, fpos=%ld\n", file,
 		(unsigned long) ctx->pos);
-	PPRINTK("ncp_do_readdir: init %s, volnum=%d, dirent=%u\n",
-		dentry->d_name.name, NCP_FINFO(dir)->volNumber,
-		NCP_FINFO(dir)->dirEntNum);
+	PPRINTK("ncp_do_readdir: init %pD, volnum=%d, dirent=%u\n",
+		file, NCP_FINFO(dir)->volNumber, NCP_FINFO(dir)->dirEntNum);
 
 	err = ncp_initialize_search(server, dir, &seq);
 	if (err) {
@@ -850,8 +846,7 @@ static struct dentry *ncp_lookup(struct inode *dir, struct dentry *dentry, unsig
 	if (!ncp_conn_valid(server))
 		goto finished;
 
-	PPRINTK("ncp_lookup: server lookup for %s/%s\n",
-		dentry->d_parent->d_name.name, dentry->d_name.name);
+	PPRINTK("ncp_lookup: server lookup for %pd2\n", dentry);
 
 	len = sizeof(__name);
 	if (ncp_is_server_root(dir)) {
@@ -867,8 +862,7 @@ static struct dentry *ncp_lookup(struct inode *dir, struct dentry *dentry, unsig
 		if (!res)
 			res = ncp_obtain_info(server, dir, __name, &(finfo.i));
 	}
-	PPRINTK("ncp_lookup: looked for %s/%s, res=%d\n",
-		dentry->d_parent->d_name.name, __name, res);
+	PPRINTK("ncp_lookup: looked for %pd2, res=%d\n", dentry, res);
 	/*
 	 * If we didn't find an entry, make a negative dentry.
 	 */
@@ -915,8 +909,7 @@ out:
 	return error;
 
 out_close:
-	PPRINTK("ncp_instantiate: %s/%s failed, closing file\n",
-		dentry->d_parent->d_name.name, dentry->d_name.name);
+	PPRINTK("ncp_instantiate: %pd2 failed, closing file\n", dentry);
 	ncp_close_file(NCP_SERVER(dir), finfo->file_handle);
 	goto out;
 }
@@ -930,8 +923,7 @@ int ncp_create_new(struct inode *dir, struct dentry *dentry, umode_t mode,
 	int opmode;
 	__u8 __name[NCP_MAXPATHLEN + 1];
 	
-	PPRINTK("ncp_create_new: creating %s/%s, mode=%hx\n",
-		dentry->d_parent->d_name.name, dentry->d_name.name, mode);
+	PPRINTK("ncp_create_new: creating %pd2, mode=%hx\n", dentry, mode);
 
 	ncp_age_dentry(server, dentry);
 	len = sizeof(__name);
@@ -960,8 +952,7 @@ int ncp_create_new(struct inode *dir, struct dentry *dentry, umode_t mode,
 				error = -ENAMETOOLONG;
 			else if (result < 0)
 				error = result;
-			DPRINTK("ncp_create: %s/%s failed\n",
-				dentry->d_parent->d_name.name, dentry->d_name.name);
+			DPRINTK("ncp_create: %pd2 failed\n", dentry);
 			goto out;
 		}
 		opmode = O_WRONLY;
@@ -994,8 +985,7 @@ static int ncp_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	int error, len;
 	__u8 __name[NCP_MAXPATHLEN + 1];
 
-	DPRINTK("ncp_mkdir: making %s/%s\n",
-		dentry->d_parent->d_name.name, dentry->d_name.name);
+	DPRINTK("ncp_mkdir: making %pd2\n", dentry);
 
 	ncp_age_dentry(server, dentry);
 	len = sizeof(__name);
@@ -1032,8 +1022,7 @@ static int ncp_rmdir(struct inode *dir, struct dentry *dentry)
 	int error, result, len;
 	__u8 __name[NCP_MAXPATHLEN + 1];
 
-	DPRINTK("ncp_rmdir: removing %s/%s\n",
-		dentry->d_parent->d_name.name, dentry->d_name.name);
+	DPRINTK("ncp_rmdir: removing %pd2\n", dentry);
 
 	len = sizeof(__name);
 	error = ncp_io2vol(server, __name, &len, dentry->d_name.name,
@@ -1078,8 +1067,7 @@ static int ncp_unlink(struct inode *dir, struct dentry *dentry)
 	int error;
 
 	server = NCP_SERVER(dir);
-	DPRINTK("ncp_unlink: unlinking %s/%s\n",
-		dentry->d_parent->d_name.name, dentry->d_name.name);
+	DPRINTK("ncp_unlink: unlinking %pd2\n", dentry);
 	
 	/*
 	 * Check whether to close the file ...
@@ -1099,8 +1087,7 @@ static int ncp_unlink(struct inode *dir, struct dentry *dentry)
 #endif
 	switch (error) {
 		case 0x00:
-			DPRINTK("ncp: removed %s/%s\n",
-				dentry->d_parent->d_name.name, dentry->d_name.name);
+			DPRINTK("ncp: removed %pd2\n", dentry);
 			break;
 		case 0x85:
 		case 0x8A:
@@ -1133,9 +1120,7 @@ static int ncp_rename(struct inode *old_dir, struct dentry *old_dentry,
 	int old_len, new_len;
 	__u8 __old_name[NCP_MAXPATHLEN + 1], __new_name[NCP_MAXPATHLEN + 1];
 
-	DPRINTK("ncp_rename: %s/%s to %s/%s\n",
-		old_dentry->d_parent->d_name.name, old_dentry->d_name.name,
-		new_dentry->d_parent->d_name.name, new_dentry->d_name.name);
+	DPRINTK("ncp_rename: %pd2 to %pd2\n", old_dentry, new_dentry);
 
 	ncp_age_dentry(server, old_dentry);
 	ncp_age_dentry(server, new_dentry);
@@ -1165,8 +1150,8 @@ static int ncp_rename(struct inode *old_dir, struct dentry *old_dentry,
 #endif
 	switch (error) {
 		case 0x00:
-               	        DPRINTK("ncp renamed %s -> %s.\n",
-                                old_dentry->d_name.name,new_dentry->d_name.name);
+               	        DPRINTK("ncp renamed %pd -> %pd.\n",
+                                old_dentry, new_dentry);
 			break;
 		case 0x9E:
 			error = -ENAMETOOLONG;

fs/ncpfs/file.c

@@ -107,8 +107,7 @@ ncp_file_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 	void* freepage;
 	size_t freelen;
 
-	DPRINTK("ncp_file_read: enter %s/%s\n",
-		dentry->d_parent->d_name.name, dentry->d_name.name);
+	DPRINTK("ncp_file_read: enter %pd2\n", dentry);
 
 	pos = *ppos;
 
@@ -166,8 +165,7 @@ ncp_file_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 
 	file_accessed(file);
 
-	DPRINTK("ncp_file_read: exit %s/%s\n",
-		dentry->d_parent->d_name.name, dentry->d_name.name);
+	DPRINTK("ncp_file_read: exit %pd2\n", dentry);
 outrel:
 	ncp_inode_close(inode);		
 	return already_read ? already_read : error;
@@ -184,8 +182,7 @@ ncp_file_write(struct file *file, const char __user *buf, size_t count, loff_t *
 	int errno;
 	void* bouncebuffer;
 
-	DPRINTK("ncp_file_write: enter %s/%s\n",
-		dentry->d_parent->d_name.name, dentry->d_name.name);
+	DPRINTK("ncp_file_write: enter %pd2\n", dentry);
 	if ((ssize_t) count < 0)
 		return -EINVAL;
 	pos = *ppos;
@@ -264,8 +261,7 @@ ncp_file_write(struct file *file, const char __user *buf, size_t count, loff_t *
 			i_size_write(inode, pos);
 		mutex_unlock(&inode->i_mutex);
 	}
-	DPRINTK("ncp_file_write: exit %s/%s\n",
-		dentry->d_parent->d_name.name, dentry->d_name.name);
+	DPRINTK("ncp_file_write: exit %pd2\n", dentry);
 outrel:
 	ncp_inode_close(inode);		
 	return already_written ? already_written : errno;

fs/ncpfs/inode.c

@@ -782,6 +782,17 @@ out:
 	return error;
 }
 
+static void delayed_free(struct rcu_head *p)
+{
+	struct ncp_server *server = container_of(p, struct ncp_server, rcu);
+#ifdef CONFIG_NCPFS_NLS
+	/* unload the NLS charsets */
+	unload_nls(server->nls_vol);
+	unload_nls(server->nls_io);
+#endif /* CONFIG_NCPFS_NLS */
+	kfree(server);
+}
+
 static void ncp_put_super(struct super_block *sb)
 {
 	struct ncp_server *server = NCP_SBP(sb);
@@ -792,11 +803,6 @@ static void ncp_put_super(struct super_block *sb)
 
 	ncp_stop_tasks(server);
 
-#ifdef CONFIG_NCPFS_NLS
-	/* unload the NLS charsets */
-	unload_nls(server->nls_vol);
-	unload_nls(server->nls_io);
-#endif /* CONFIG_NCPFS_NLS */
 	mutex_destroy(&server->rcv.creq_mutex);
 	mutex_destroy(&server->root_setup_lock);
 	mutex_destroy(&server->mutex);
@@ -813,8 +819,7 @@ static void ncp_put_super(struct super_block *sb)
 	vfree(server->rxbuf);
 	vfree(server->txbuf);
 	vfree(server->packet);
-	sb->s_fs_info = NULL;
-	kfree(server);
+	call_rcu(&server->rcu, delayed_free);
 }
 
 static int ncp_statfs(struct dentry *dentry, struct kstatfs *buf)