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

Pull vfs pile 1 from Al Viro:
 "Unfortunately, this merge window it'll have a be a lot of small piles -
  my fault, actually, for not keeping #for-next in anything that would
  resemble a sane shape ;-/

  This pile: assorted fixes (the first 3 are -stable fodder, IMO) and
  cleanups + %pd/%pD formats (dentry/file pathname, up to 4 last
  components) + several long-standing patches from various folks.

  There definitely will be a lot more (starting with Miklos'
  check_submount_and_drop() series)"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (26 commits)
  direct-io: Handle O_(D)SYNC AIO
  direct-io: Implement generic deferred AIO completions
  add formats for dentry/file pathnames
  kvm eventfd: switch to fdget
  powerpc kvm: use fdget
  switch fchmod() to fdget
  switch epoll_ctl() to fdget
  switch copy_module_from_fd() to fdget
  git simplify nilfs check for busy subtree
  ibmasmfs: don't bother passing superblock when not needed
  don't pass superblock to hypfs_{mkdir,create*}
  don't pass superblock to hypfs_diag_create_files
  don't pass superblock to hypfs_vm_create_files()
  oprofile: get rid of pointless forward declarations of struct super_block
  oprofilefs_create_...() do not need superblock argument
  oprofilefs_mkdir() doesn't need superblock argument
  don't bother with passing superblock to oprofile_create_stats_files()
  oprofile: don't bother with passing superblock to ->create_files()
  don't bother passing sb to oprofile_create_files()
  coh901318: don't open-code simple_read_from_buffer()
  ...

Documentation/printk-formats.txt

@@ -168,6 +168,15 @@ UUID/GUID addresses:
 	Where no additional specifiers are used the default little endian
 	order with lower case hex characters will be printed.
 
+dentry names:
+	%pd{,2,3,4}
+	%pD{,2,3,4}
+
+	For printing dentry name; if we race with d_move(), the name might be
+	a mix of old and new ones, but it won't oops.  %pd dentry is a safer
+	equivalent of %s dentry->d_name.name we used to use, %pd<n> prints
+	n last components.  %pD does the same thing for struct file.
+
 struct va_format:
 
 	%pV

arch/alpha/oprofile/common.c

@@ -106,7 +106,7 @@ op_axp_stop(void)
 }
 
 static int
-op_axp_create_files(struct super_block *sb, struct dentry *root)
+op_axp_create_files(struct dentry *root)
 {
 	int i;
 
@@ -115,23 +115,23 @@ op_axp_create_files(struct super_block *sb, struct dentry *root)
 		char buf[4];
 
 		snprintf(buf, sizeof buf, "%d", i);
-		dir = oprofilefs_mkdir(sb, root, buf);
+		dir = oprofilefs_mkdir(root, buf);
 
-		oprofilefs_create_ulong(sb, dir, "enabled", &ctr[i].enabled);
+		oprofilefs_create_ulong(dir, "enabled", &ctr[i].enabled);
-                oprofilefs_create_ulong(sb, dir, "event", &ctr[i].event);
+                oprofilefs_create_ulong(dir, "event", &ctr[i].event);
-		oprofilefs_create_ulong(sb, dir, "count", &ctr[i].count);
+		oprofilefs_create_ulong(dir, "count", &ctr[i].count);
 		/* Dummies.  */
-		oprofilefs_create_ulong(sb, dir, "kernel", &ctr[i].kernel);
+		oprofilefs_create_ulong(dir, "kernel", &ctr[i].kernel);
-		oprofilefs_create_ulong(sb, dir, "user", &ctr[i].user);
+		oprofilefs_create_ulong(dir, "user", &ctr[i].user);
-		oprofilefs_create_ulong(sb, dir, "unit_mask", &ctr[i].unit_mask);
+		oprofilefs_create_ulong(dir, "unit_mask", &ctr[i].unit_mask);
 	}
 
 	if (model->can_set_proc_mode) {
-		oprofilefs_create_ulong(sb, root, "enable_pal",
+		oprofilefs_create_ulong(root, "enable_pal",
 					&sys.enable_pal);
-		oprofilefs_create_ulong(sb, root, "enable_kernel",
+		oprofilefs_create_ulong(root, "enable_kernel",
 					&sys.enable_kernel);
-		oprofilefs_create_ulong(sb, root, "enable_user",
+		oprofilefs_create_ulong(root, "enable_user",
 					&sys.enable_user);
 	}
 

arch/avr32/oprofile/op_model_avr32.c

@@ -97,8 +97,7 @@ static irqreturn_t avr32_perf_counter_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static int avr32_perf_counter_create_files(struct super_block *sb,
+static int avr32_perf_counter_create_files(struct dentry *root)
-		struct dentry *root)
 {
 	struct dentry *dir;
 	unsigned int i;
@@ -106,21 +105,21 @@ static int avr32_perf_counter_create_files(struct super_block *sb,
 
 	for (i = 0; i < NR_counter; i++) {
 		snprintf(filename, sizeof(filename), "%u", i);
-		dir = oprofilefs_mkdir(sb, root, filename);
+		dir = oprofilefs_mkdir(root, filename);
 
-		oprofilefs_create_ulong(sb, dir, "enabled",
+		oprofilefs_create_ulong(dir, "enabled",
 				&counter[i].enabled);
-		oprofilefs_create_ulong(sb, dir, "event",
+		oprofilefs_create_ulong(dir, "event",
 				&counter[i].event);
-		oprofilefs_create_ulong(sb, dir, "count",
+		oprofilefs_create_ulong(dir, "count",
 				&counter[i].count);
 
 		/* Dummy entries */
-		oprofilefs_create_ulong(sb, dir, "kernel",
+		oprofilefs_create_ulong(dir, "kernel",
 				&counter[i].kernel);
-		oprofilefs_create_ulong(sb, dir, "user",
+		oprofilefs_create_ulong(dir, "user",
 				&counter[i].user);
-		oprofilefs_create_ulong(sb, dir, "unit_mask",
+		oprofilefs_create_ulong(dir, "unit_mask",
 				&counter[i].unit_mask);
 	}
 

arch/mips/oprofile/common.c

@@ -33,7 +33,7 @@ static int op_mips_setup(void)
 	return 0;
 }
 
-static int op_mips_create_files(struct super_block *sb, struct dentry *root)
+static int op_mips_create_files(struct dentry *root)
 {
 	int i;
 
@@ -42,16 +42,16 @@ static int op_mips_create_files(struct super_block *sb, struct dentry *root)
 		char buf[4];
 
 		snprintf(buf, sizeof buf, "%d", i);
-		dir = oprofilefs_mkdir(sb, root, buf);
+		dir = oprofilefs_mkdir(root, buf);
 
-		oprofilefs_create_ulong(sb, dir, "enabled", &ctr[i].enabled);
+		oprofilefs_create_ulong(dir, "enabled", &ctr[i].enabled);
-		oprofilefs_create_ulong(sb, dir, "event", &ctr[i].event);
+		oprofilefs_create_ulong(dir, "event", &ctr[i].event);
-		oprofilefs_create_ulong(sb, dir, "count", &ctr[i].count);
+		oprofilefs_create_ulong(dir, "count", &ctr[i].count);
-		oprofilefs_create_ulong(sb, dir, "kernel", &ctr[i].kernel);
+		oprofilefs_create_ulong(dir, "kernel", &ctr[i].kernel);
-		oprofilefs_create_ulong(sb, dir, "user", &ctr[i].user);
+		oprofilefs_create_ulong(dir, "user", &ctr[i].user);
-		oprofilefs_create_ulong(sb, dir, "exl", &ctr[i].exl);
+		oprofilefs_create_ulong(dir, "exl", &ctr[i].exl);
 		/* Dummy.  */
-		oprofilefs_create_ulong(sb, dir, "unit_mask", &ctr[i].unit_mask);
+		oprofilefs_create_ulong(dir, "unit_mask", &ctr[i].unit_mask);
 	}
 
 	return 0;

arch/powerpc/kvm/powerpc.c

@@ -825,39 +825,39 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 #endif
 #ifdef CONFIG_KVM_MPIC
 	case KVM_CAP_IRQ_MPIC: {
-		struct file *filp;
+		struct fd f;
 		struct kvm_device *dev;
 
 		r = -EBADF;
-		filp = fget(cap->args[0]);
+		f = fdget(cap->args[0]);
-		if (!filp)
+		if (!f.file)
 			break;
 
 		r = -EPERM;
-		dev = kvm_device_from_filp(filp);
+		dev = kvm_device_from_filp(f.file);
 		if (dev)
 			r = kvmppc_mpic_connect_vcpu(dev, vcpu, cap->args[1]);
 
-		fput(filp);
+		fdput(f);
 		break;
 	}
 #endif
 #ifdef CONFIG_KVM_XICS
 	case KVM_CAP_IRQ_XICS: {
-		struct file *filp;
+		struct fd f;
 		struct kvm_device *dev;
 
 		r = -EBADF;
-		filp = fget(cap->args[0]);
+		f = fdget(cap->args[0]);
-		if (!filp)
+		if (!f.file)
 			break;
 
 		r = -EPERM;
-		dev = kvm_device_from_filp(filp);
+		dev = kvm_device_from_filp(f.file);
 		if (dev)
 			r = kvmppc_xics_connect_vcpu(dev, vcpu, cap->args[1]);
 
-		fput(filp);
+		fdput(f);
 		break;
 	}
 #endif /* CONFIG_KVM_XICS */

arch/powerpc/oprofile/common.c

@@ -119,7 +119,7 @@ static void op_powerpc_stop(void)
                 model->global_stop();
 }
 
-static int op_powerpc_create_files(struct super_block *sb, struct dentry *root)
+static int op_powerpc_create_files(struct dentry *root)
 {
 	int i;
 
@@ -128,9 +128,9 @@ static int op_powerpc_create_files(struct super_block *sb, struct dentry *root)
 	 * There is one mmcr0, mmcr1 and mmcra for setting the events for
 	 * all of the counters.
 	 */
-	oprofilefs_create_ulong(sb, root, "mmcr0", &sys.mmcr0);
+	oprofilefs_create_ulong(root, "mmcr0", &sys.mmcr0);
-	oprofilefs_create_ulong(sb, root, "mmcr1", &sys.mmcr1);
+	oprofilefs_create_ulong(root, "mmcr1", &sys.mmcr1);
-	oprofilefs_create_ulong(sb, root, "mmcra", &sys.mmcra);
+	oprofilefs_create_ulong(root, "mmcra", &sys.mmcra);
 #ifdef CONFIG_OPROFILE_CELL
 	/* create a file the user tool can check to see what level of profiling
 	 * support exits with this kernel. Initialize bit mask to indicate
@@ -142,7 +142,7 @@ static int op_powerpc_create_files(struct super_block *sb, struct dentry *root)
 	 * If the file does not exist, then the kernel only supports SPU
 	 * cycle profiling, PPU event and cycle profiling.
 	 */
-	oprofilefs_create_ulong(sb, root, "cell_support", &sys.cell_support);
+	oprofilefs_create_ulong(root, "cell_support", &sys.cell_support);
 	sys.cell_support = 0x1; /* Note, the user OProfile tool must check
 				 * that this bit is set before attempting to
 				 * user SPU event profiling.  Older kernels
@@ -160,11 +160,11 @@ static int op_powerpc_create_files(struct super_block *sb, struct dentry *root)
 		char buf[4];
 
 		snprintf(buf, sizeof buf, "%d", i);
-		dir = oprofilefs_mkdir(sb, root, buf);
+		dir = oprofilefs_mkdir(root, buf);
 
-		oprofilefs_create_ulong(sb, dir, "enabled", &ctr[i].enabled);
+		oprofilefs_create_ulong(dir, "enabled", &ctr[i].enabled);
-		oprofilefs_create_ulong(sb, dir, "event", &ctr[i].event);
+		oprofilefs_create_ulong(dir, "event", &ctr[i].event);
-		oprofilefs_create_ulong(sb, dir, "count", &ctr[i].count);
+		oprofilefs_create_ulong(dir, "count", &ctr[i].count);
 
 		/*
 		 * Classic PowerPC doesn't support per-counter
@@ -173,14 +173,14 @@ static int op_powerpc_create_files(struct super_block *sb, struct dentry *root)
 		 * Book-E style performance monitors, we do
 		 * support them.
 		 */
-		oprofilefs_create_ulong(sb, dir, "kernel", &ctr[i].kernel);
+		oprofilefs_create_ulong(dir, "kernel", &ctr[i].kernel);
-		oprofilefs_create_ulong(sb, dir, "user", &ctr[i].user);
+		oprofilefs_create_ulong(dir, "user", &ctr[i].user);
 
-		oprofilefs_create_ulong(sb, dir, "unit_mask", &ctr[i].unit_mask);
+		oprofilefs_create_ulong(dir, "unit_mask", &ctr[i].unit_mask);
 	}
 
-	oprofilefs_create_ulong(sb, root, "enable_kernel", &sys.enable_kernel);
+	oprofilefs_create_ulong(root, "enable_kernel", &sys.enable_kernel);
-	oprofilefs_create_ulong(sb, root, "enable_user", &sys.enable_user);
+	oprofilefs_create_ulong(root, "enable_user", &sys.enable_user);
 
 	/* Default to tracing both kernel and user */
 	sys.enable_kernel = 1;

arch/s390/hypfs/hypfs.h

@@ -18,26 +18,23 @@
 #define UPDATE_FILE_MODE 0220
 #define DIR_MODE         0550
 
-extern struct dentry *hypfs_mkdir(struct super_block *sb, struct dentry *parent,
+extern struct dentry *hypfs_mkdir(struct dentry *parent, const char *name);
-				  const char *name);
 
-extern struct dentry *hypfs_create_u64(struct super_block *sb,
+extern struct dentry *hypfs_create_u64(struct dentry *dir, const char *name,
-				       struct dentry *dir, const char *name,
 				       __u64 value);
 
-extern struct dentry *hypfs_create_str(struct super_block *sb,
+extern struct dentry *hypfs_create_str(struct dentry *dir, const char *name,
-				       struct dentry *dir, const char *name,
 				       char *string);
 
 /* LPAR Hypervisor */
 extern int hypfs_diag_init(void);
 extern void hypfs_diag_exit(void);
-extern int hypfs_diag_create_files(struct super_block *sb, struct dentry *root);
+extern int hypfs_diag_create_files(struct dentry *root);
 
 /* VM Hypervisor */
 extern int hypfs_vm_init(void);
 extern void hypfs_vm_exit(void);
-extern int hypfs_vm_create_files(struct super_block *sb, struct dentry *root);
+extern int hypfs_vm_create_files(struct dentry *root);
 
 /* debugfs interface */
 struct hypfs_dbfs_file;

arch/s390/hypfs/hypfs_diag.c

@@ -623,8 +623,7 @@ void hypfs_diag_exit(void)
  * *******************************************
  */
 
-static int hypfs_create_cpu_files(struct super_block *sb,
+static int hypfs_create_cpu_files(struct dentry *cpus_dir, void *cpu_info)
-				  struct dentry *cpus_dir, void *cpu_info)
 {
 	struct dentry *cpu_dir;
 	char buffer[TMP_SIZE];
@@ -632,30 +631,29 @@ static int hypfs_create_cpu_files(struct super_block *sb,
 
 	snprintf(buffer, TMP_SIZE, "%d", cpu_info__cpu_addr(diag204_info_type,
 							    cpu_info));
-	cpu_dir = hypfs_mkdir(sb, cpus_dir, buffer);
+	cpu_dir = hypfs_mkdir(cpus_dir, buffer);
-	rc = hypfs_create_u64(sb, cpu_dir, "mgmtime",
+	rc = hypfs_create_u64(cpu_dir, "mgmtime",
 			      cpu_info__acc_time(diag204_info_type, cpu_info) -
 			      cpu_info__lp_time(diag204_info_type, cpu_info));
 	if (IS_ERR(rc))
 		return PTR_ERR(rc);
-	rc = hypfs_create_u64(sb, cpu_dir, "cputime",
+	rc = hypfs_create_u64(cpu_dir, "cputime",
 			      cpu_info__lp_time(diag204_info_type, cpu_info));
 	if (IS_ERR(rc))
 		return PTR_ERR(rc);
 	if (diag204_info_type == INFO_EXT) {
-		rc = hypfs_create_u64(sb, cpu_dir, "onlinetime",
+		rc = hypfs_create_u64(cpu_dir, "onlinetime",
 				      cpu_info__online_time(diag204_info_type,
 							    cpu_info));
 		if (IS_ERR(rc))
 			return PTR_ERR(rc);
 	}
 	diag224_idx2name(cpu_info__ctidx(diag204_info_type, cpu_info), buffer);
-	rc = hypfs_create_str(sb, cpu_dir, "type", buffer);
+	rc = hypfs_create_str(cpu_dir, "type", buffer);
 	return PTR_RET(rc);
 }
 
-static void *hypfs_create_lpar_files(struct super_block *sb,
+static void *hypfs_create_lpar_files(struct dentry *systems_dir, void *part_hdr)
-				     struct dentry *systems_dir, void *part_hdr)
 {
 	struct dentry *cpus_dir;
 	struct dentry *lpar_dir;
@@ -665,16 +663,16 @@ static void *hypfs_create_lpar_files(struct super_block *sb,
 
 	part_hdr__part_name(diag204_info_type, part_hdr, lpar_name);
 	lpar_name[LPAR_NAME_LEN] = 0;
-	lpar_dir = hypfs_mkdir(sb, systems_dir, lpar_name);
+	lpar_dir = hypfs_mkdir(systems_dir, lpar_name);
 	if (IS_ERR(lpar_dir))
 		return lpar_dir;
-	cpus_dir = hypfs_mkdir(sb, lpar_dir, "cpus");
+	cpus_dir = hypfs_mkdir(lpar_dir, "cpus");
 	if (IS_ERR(cpus_dir))
 		return cpus_dir;
 	cpu_info = part_hdr + part_hdr__size(diag204_info_type);
 	for (i = 0; i < part_hdr__rcpus(diag204_info_type, part_hdr); i++) {
 		int rc;
-		rc = hypfs_create_cpu_files(sb, cpus_dir, cpu_info);
+		rc = hypfs_create_cpu_files(cpus_dir, cpu_info);
 		if (rc)
 			return ERR_PTR(rc);
 		cpu_info += cpu_info__size(diag204_info_type);
@@ -682,8 +680,7 @@ static void *hypfs_create_lpar_files(struct super_block *sb,
 	return cpu_info;
 }
 
-static int hypfs_create_phys_cpu_files(struct super_block *sb,
+static int hypfs_create_phys_cpu_files(struct dentry *cpus_dir, void *cpu_info)
-				       struct dentry *cpus_dir, void *cpu_info)
 {
 	struct dentry *cpu_dir;
 	char buffer[TMP_SIZE];
@@ -691,32 +688,31 @@ static int hypfs_create_phys_cpu_files(struct super_block *sb,
 
 	snprintf(buffer, TMP_SIZE, "%i", phys_cpu__cpu_addr(diag204_info_type,
 							    cpu_info));
-	cpu_dir = hypfs_mkdir(sb, cpus_dir, buffer);
+	cpu_dir = hypfs_mkdir(cpus_dir, buffer);
 	if (IS_ERR(cpu_dir))
 		return PTR_ERR(cpu_dir);
-	rc = hypfs_create_u64(sb, cpu_dir, "mgmtime",
+	rc = hypfs_create_u64(cpu_dir, "mgmtime",
 			      phys_cpu__mgm_time(diag204_info_type, cpu_info));
 	if (IS_ERR(rc))
 		return PTR_ERR(rc);
 	diag224_idx2name(phys_cpu__ctidx(diag204_info_type, cpu_info), buffer);
-	rc = hypfs_create_str(sb, cpu_dir, "type", buffer);
+	rc = hypfs_create_str(cpu_dir, "type", buffer);
 	return PTR_RET(rc);
 }
 
-static void *hypfs_create_phys_files(struct super_block *sb,
+static void *hypfs_create_phys_files(struct dentry *parent_dir, void *phys_hdr)
-				     struct dentry *parent_dir, void *phys_hdr)
 {
 	int i;
 	void *cpu_info;
 	struct dentry *cpus_dir;
 
-	cpus_dir = hypfs_mkdir(sb, parent_dir, "cpus");
+	cpus_dir = hypfs_mkdir(parent_dir, "cpus");
 	if (IS_ERR(cpus_dir))
 		return cpus_dir;
 	cpu_info = phys_hdr + phys_hdr__size(diag204_info_type);
 	for (i = 0; i < phys_hdr__cpus(diag204_info_type, phys_hdr); i++) {
 		int rc;
-		rc = hypfs_create_phys_cpu_files(sb, cpus_dir, cpu_info);
+		rc = hypfs_create_phys_cpu_files(cpus_dir, cpu_info);
 		if (rc)
 			return ERR_PTR(rc);
 		cpu_info += phys_cpu__size(diag204_info_type);
@@ -724,7 +720,7 @@ static void *hypfs_create_phys_files(struct super_block *sb,
 	return cpu_info;
 }
 
-int hypfs_diag_create_files(struct super_block *sb, struct dentry *root)
+int hypfs_diag_create_files(struct dentry *root)
 {
 	struct dentry *systems_dir, *hyp_dir;
 	void *time_hdr, *part_hdr;
@@ -735,7 +731,7 @@ int hypfs_diag_create_files(struct super_block *sb, struct dentry *root)
 	if (IS_ERR(buffer))
 		return PTR_ERR(buffer);
 
-	systems_dir = hypfs_mkdir(sb, root, "systems");
+	systems_dir = hypfs_mkdir(root, "systems");
 	if (IS_ERR(systems_dir)) {
 		rc = PTR_ERR(systems_dir);
 		goto err_out;
@@ -743,25 +739,25 @@ int hypfs_diag_create_files(struct super_block *sb, struct dentry *root)
 	time_hdr = (struct x_info_blk_hdr *)buffer;
 	part_hdr = time_hdr + info_blk_hdr__size(diag204_info_type);
 	for (i = 0; i < info_blk_hdr__npar(diag204_info_type, time_hdr); i++) {
-		part_hdr = hypfs_create_lpar_files(sb, systems_dir, part_hdr);
+		part_hdr = hypfs_create_lpar_files(systems_dir, part_hdr);
 		if (IS_ERR(part_hdr)) {
 			rc = PTR_ERR(part_hdr);
 			goto err_out;
 		}
 	}
 	if (info_blk_hdr__flags(diag204_info_type, time_hdr) & LPAR_PHYS_FLG) {
-		ptr = hypfs_create_phys_files(sb, root, part_hdr);
+		ptr = hypfs_create_phys_files(root, part_hdr);
 		if (IS_ERR(ptr)) {
 			rc = PTR_ERR(ptr);
 			goto err_out;
 		}
 	}
-	hyp_dir = hypfs_mkdir(sb, root, "hyp");
+	hyp_dir = hypfs_mkdir(root, "hyp");
 	if (IS_ERR(hyp_dir)) {
 		rc = PTR_ERR(hyp_dir);
 		goto err_out;
 	}
-	ptr = hypfs_create_str(sb, hyp_dir, "type", "LPAR Hypervisor");
+	ptr = hypfs_create_str(hyp_dir, "type", "LPAR Hypervisor");
 	if (IS_ERR(ptr)) {
 		rc = PTR_ERR(ptr);
 		goto err_out;

arch/s390/hypfs/hypfs_vm.c

@@ -107,16 +107,15 @@ static void diag2fc_free(const void *data)
 	vfree(data);
 }
 
-#define ATTRIBUTE(sb, dir, name, member) \
+#define ATTRIBUTE(dir, name, member) \
 do { \
 	void *rc; \
-	rc = hypfs_create_u64(sb, dir, name, member); \
+	rc = hypfs_create_u64(dir, name, member); \
 	if (IS_ERR(rc)) \
 		return PTR_ERR(rc); \
 } while(0)
 
-static int hpyfs_vm_create_guest(struct super_block *sb,
+static int hpyfs_vm_create_guest(struct dentry *systems_dir,
-				 struct dentry *systems_dir,
 				 struct diag2fc_data *data)
 {
 	char guest_name[NAME_LEN + 1] = {};
@@ -130,46 +129,46 @@ static int hpyfs_vm_create_guest(struct super_block *sb,
 	memcpy(guest_name, data->guest_name, NAME_LEN);
 	EBCASC(guest_name, NAME_LEN);
 	strim(guest_name);
-	guest_dir = hypfs_mkdir(sb, systems_dir, guest_name);
+	guest_dir = hypfs_mkdir(systems_dir, guest_name);
 	if (IS_ERR(guest_dir))
 		return PTR_ERR(guest_dir);
-	ATTRIBUTE(sb, guest_dir, "onlinetime_us", data->el_time);
+	ATTRIBUTE(guest_dir, "onlinetime_us", data->el_time);
 
 	/* logical cpu information */
-	cpus_dir = hypfs_mkdir(sb, guest_dir, "cpus");
+	cpus_dir = hypfs_mkdir(guest_dir, "cpus");
 	if (IS_ERR(cpus_dir))
 		return PTR_ERR(cpus_dir);
-	ATTRIBUTE(sb, cpus_dir, "cputime_us", data->used_cpu);
+	ATTRIBUTE(cpus_dir, "cputime_us", data->used_cpu);
-	ATTRIBUTE(sb, cpus_dir, "capped", capped_value);
+	ATTRIBUTE(cpus_dir, "capped", capped_value);
-	ATTRIBUTE(sb, cpus_dir, "dedicated", dedicated_flag);
+	ATTRIBUTE(cpus_dir, "dedicated", dedicated_flag);
-	ATTRIBUTE(sb, cpus_dir, "count", data->vcpus);
+	ATTRIBUTE(cpus_dir, "count", data->vcpus);
-	ATTRIBUTE(sb, cpus_dir, "weight_min", data->cpu_min);
+	ATTRIBUTE(cpus_dir, "weight_min", data->cpu_min);
-	ATTRIBUTE(sb, cpus_dir, "weight_max", data->cpu_max);
+	ATTRIBUTE(cpus_dir, "weight_max", data->cpu_max);
-	ATTRIBUTE(sb, cpus_dir, "weight_cur", data->cpu_shares);
+	ATTRIBUTE(cpus_dir, "weight_cur", data->cpu_shares);
 
 	/* memory information */
-	mem_dir = hypfs_mkdir(sb, guest_dir, "mem");
+	mem_dir = hypfs_mkdir(guest_dir, "mem");
 	if (IS_ERR(mem_dir))
 		return PTR_ERR(mem_dir);
-	ATTRIBUTE(sb, mem_dir, "min_KiB", data->mem_min_kb);
+	ATTRIBUTE(mem_dir, "min_KiB", data->mem_min_kb);
-	ATTRIBUTE(sb, mem_dir, "max_KiB", data->mem_max_kb);
+	ATTRIBUTE(mem_dir, "max_KiB", data->mem_max_kb);
-	ATTRIBUTE(sb, mem_dir, "used_KiB", data->mem_used_kb);
+	ATTRIBUTE(mem_dir, "used_KiB", data->mem_used_kb);
-	ATTRIBUTE(sb, mem_dir, "share_KiB", data->mem_share_kb);
+	ATTRIBUTE(mem_dir, "share_KiB", data->mem_share_kb);
 
 	/* samples */
-	samples_dir = hypfs_mkdir(sb, guest_dir, "samples");
+	samples_dir = hypfs_mkdir(guest_dir, "samples");
 	if (IS_ERR(samples_dir))
 		return PTR_ERR(samples_dir);
-	ATTRIBUTE(sb, samples_dir, "cpu_using", data->cpu_use_samp);
+	ATTRIBUTE(samples_dir, "cpu_using", data->cpu_use_samp);
-	ATTRIBUTE(sb, samples_dir, "cpu_delay", data->cpu_delay_samp);
+	ATTRIBUTE(samples_dir, "cpu_delay", data->cpu_delay_samp);
-	ATTRIBUTE(sb, samples_dir, "mem_delay", data->page_wait_samp);
+	ATTRIBUTE(samples_dir, "mem_delay", data->page_wait_samp);
-	ATTRIBUTE(sb, samples_dir, "idle", data->idle_samp);
+	ATTRIBUTE(samples_dir, "idle", data->idle_samp);
-	ATTRIBUTE(sb, samples_dir, "other", data->other_samp);
+	ATTRIBUTE(samples_dir, "other", data->other_samp);
-	ATTRIBUTE(sb, samples_dir, "total", data->total_samp);
+	ATTRIBUTE(samples_dir, "total", data->total_samp);
 	return 0;
 }
 
-int hypfs_vm_create_files(struct super_block *sb, struct dentry *root)
+int hypfs_vm_create_files(struct dentry *root)
 {
 	struct dentry *dir, *file;
 	struct diag2fc_data *data;
@@ -181,38 +180,38 @@ int hypfs_vm_create_files(struct super_block *sb, struct dentry *root)
 		return PTR_ERR(data);
 
 	/* Hpervisor Info */
-	dir = hypfs_mkdir(sb, root, "hyp");
+	dir = hypfs_mkdir(root, "hyp");
 	if (IS_ERR(dir)) {
 		rc = PTR_ERR(dir);
 		goto failed;
 	}
-	file = hypfs_create_str(sb, dir, "type", "z/VM Hypervisor");
+	file = hypfs_create_str(dir, "type", "z/VM Hypervisor");
 	if (IS_ERR(file)) {
 		rc = PTR_ERR(file);
 		goto failed;
 	}
 
 	/* physical cpus */
-	dir = hypfs_mkdir(sb, root, "cpus");
+	dir = hypfs_mkdir(root, "cpus");
 	if (IS_ERR(dir)) {
 		rc = PTR_ERR(dir);
 		goto failed;
 	}
-	file = hypfs_create_u64(sb, dir, "count", data->lcpus);
+	file = hypfs_create_u64(dir, "count", data->lcpus);
 	if (IS_ERR(file)) {
 		rc = PTR_ERR(file);
 		goto failed;
 	}
 
 	/* guests */
-	dir = hypfs_mkdir(sb, root, "systems");
+	dir = hypfs_mkdir(root, "systems");
 	if (IS_ERR(dir)) {
 		rc = PTR_ERR(dir);
 		goto failed;
 	}
 
 	for (i = 0; i < count; i++) {
-		rc = hpyfs_vm_create_guest(sb, dir, &(data[i]));
+		rc = hpyfs_vm_create_guest(dir, &(data[i]));
 		if (rc)
 			goto failed;
 	}

arch/s390/hypfs/inode.c

@@ -28,8 +28,7 @@
 #define HYPFS_MAGIC 0x687970	/* ASCII 'hyp' */
 #define TMP_SIZE 64		/* size of temporary buffers */
 
-static struct dentry *hypfs_create_update_file(struct super_block *sb,
+static struct dentry *hypfs_create_update_file(struct dentry *dir);
-					       struct dentry *dir);
 
 struct hypfs_sb_info {
 	kuid_t uid;			/* uid used for files and dirs */
@@ -193,9 +192,9 @@ static ssize_t hypfs_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	}
 	hypfs_delete_tree(sb->s_root);
 	if (MACHINE_IS_VM)
-		rc = hypfs_vm_create_files(sb, sb->s_root);
+		rc = hypfs_vm_create_files(sb->s_root);
 	else
-		rc = hypfs_diag_create_files(sb, sb->s_root);
+		rc = hypfs_diag_create_files(sb->s_root);
 	if (rc) {
 		pr_err("Updating the hypfs tree failed\n");
 		hypfs_delete_tree(sb->s_root);
@@ -302,12 +301,12 @@ static int hypfs_fill_super(struct super_block *sb, void *data, int silent)
 	if (!root_dentry)
 		return -ENOMEM;
 	if (MACHINE_IS_VM)
-		rc = hypfs_vm_create_files(sb, root_dentry);
+		rc = hypfs_vm_create_files(root_dentry);
 	else
-		rc = hypfs_diag_create_files(sb, root_dentry);
+		rc = hypfs_diag_create_files(root_dentry);
 	if (rc)
 		return rc;
-	sbi->update_file = hypfs_create_update_file(sb, root_dentry);
+	sbi->update_file = hypfs_create_update_file(root_dentry);
 	if (IS_ERR(sbi->update_file))
 		return PTR_ERR(sbi->update_file);
 	hypfs_update_update(sb);
@@ -334,8 +333,7 @@ static void hypfs_kill_super(struct super_block *sb)
 	kill_litter_super(sb);
 }
 
-static struct dentry *hypfs_create_file(struct super_block *sb,
+static struct dentry *hypfs_create_file(struct dentry *parent, const char *name,
-					struct dentry *parent, const char *name,
 					char *data, umode_t mode)
 {
 	struct dentry *dentry;
@@ -347,7 +345,7 @@ static struct dentry *hypfs_create_file(struct super_block *sb,
 		dentry = ERR_PTR(-ENOMEM);
 		goto fail;
 	}
-	inode = hypfs_make_inode(sb, mode);
+	inode = hypfs_make_inode(parent->d_sb, mode);
 	if (!inode) {
 		dput(dentry);
 		dentry = ERR_PTR(-ENOMEM);
@@ -373,24 +371,22 @@ fail:
 	return dentry;
 }
 
-struct dentry *hypfs_mkdir(struct super_block *sb, struct dentry *parent,
+struct dentry *hypfs_mkdir(struct dentry *parent, const char *name)
-			   const char *name)
 {
 	struct dentry *dentry;
 
-	dentry = hypfs_create_file(sb, parent, name, NULL, S_IFDIR | DIR_MODE);
+	dentry = hypfs_create_file(parent, name, NULL, S_IFDIR | DIR_MODE);
 	if (IS_ERR(dentry))
 		return dentry;
 	hypfs_add_dentry(dentry);
 	return dentry;
 }
 
-static struct dentry *hypfs_create_update_file(struct super_block *sb,
+static struct dentry *hypfs_create_update_file(struct dentry *dir)
-					       struct dentry *dir)
 {
 	struct dentry *dentry;
 
-	dentry = hypfs_create_file(sb, dir, "update", NULL,
+	dentry = hypfs_create_file(dir, "update", NULL,
 				   S_IFREG | UPDATE_FILE_MODE);
 	/*
 	 * We do not put the update file on the 'delete' list with
@@ -400,7 +396,7 @@ static struct dentry *hypfs_create_update_file(struct super_block *sb,
 	return dentry;
 }
 
-struct dentry *hypfs_create_u64(struct super_block *sb, struct dentry *dir,
+struct dentry *hypfs_create_u64(struct dentry *dir,
 				const char *name, __u64 value)
 {
 	char *buffer;
@@ -412,7 +408,7 @@ struct dentry *hypfs_create_u64(struct super_block *sb, struct dentry *dir,
 	if (!buffer)
 		return ERR_PTR(-ENOMEM);
 	dentry =
-	    hypfs_create_file(sb, dir, name, buffer, S_IFREG | REG_FILE_MODE);
+	    hypfs_create_file(dir, name, buffer, S_IFREG | REG_FILE_MODE);
 	if (IS_ERR(dentry)) {
 		kfree(buffer);
 		return ERR_PTR(-ENOMEM);
@@ -421,7 +417,7 @@ struct dentry *hypfs_create_u64(struct super_block *sb, struct dentry *dir,
 	return dentry;
 }
 
-struct dentry *hypfs_create_str(struct super_block *sb, struct dentry *dir,
+struct dentry *hypfs_create_str(struct dentry *dir,
 				const char *name, char *string)
 {
 	char *buffer;
@@ -432,7 +428,7 @@ struct dentry *hypfs_create_str(struct super_block *sb, struct dentry *dir,
 		return ERR_PTR(-ENOMEM);
 	sprintf(buffer, "%s\n", string);
 	dentry =
-	    hypfs_create_file(sb, dir, name, buffer, S_IFREG | REG_FILE_MODE);
+	    hypfs_create_file(dir, name, buffer, S_IFREG | REG_FILE_MODE);
 	if (IS_ERR(dentry)) {
 		kfree(buffer);
 		return ERR_PTR(-ENOMEM);

arch/s390/oprofile/init.c

@@ -346,16 +346,15 @@ static const struct file_operations timer_enabled_fops = {
 };
 
 
-static int oprofile_create_hwsampling_files(struct super_block *sb,
+static int oprofile_create_hwsampling_files(struct dentry *root)
-					    struct dentry *root)
 {
 	struct dentry *dir;
 
-	dir = oprofilefs_mkdir(sb, root, "timer");
+	dir = oprofilefs_mkdir(root, "timer");
 	if (!dir)
 		return -EINVAL;
 
-	oprofilefs_create_file(sb, dir, "enabled", &timer_enabled_fops);
+	oprofilefs_create_file(dir, "enabled", &timer_enabled_fops);
 
 	if (!hwsampler_available)
 		return 0;
@@ -376,17 +375,17 @@ static int oprofile_create_hwsampling_files(struct super_block *sb,
 		 * and can only be set to 0.
 		 */
 
-		dir = oprofilefs_mkdir(sb, root, "0");
+		dir = oprofilefs_mkdir(root, "0");
 		if (!dir)
 			return -EINVAL;
 
-		oprofilefs_create_file(sb, dir, "enabled", &hwsampler_fops);
+		oprofilefs_create_file(dir, "enabled", &hwsampler_fops);
-		oprofilefs_create_file(sb, dir, "event", &zero_fops);
+		oprofilefs_create_file(dir, "event", &zero_fops);
-		oprofilefs_create_file(sb, dir, "count", &hw_interval_fops);
+		oprofilefs_create_file(dir, "count", &hw_interval_fops);
-		oprofilefs_create_file(sb, dir, "unit_mask", &zero_fops);
+		oprofilefs_create_file(dir, "unit_mask", &zero_fops);
-		oprofilefs_create_file(sb, dir, "kernel", &kernel_fops);
+		oprofilefs_create_file(dir, "kernel", &kernel_fops);
-		oprofilefs_create_file(sb, dir, "user", &user_fops);
+		oprofilefs_create_file(dir, "user", &user_fops);
-		oprofilefs_create_ulong(sb, dir, "hw_sdbt_blocks",
+		oprofilefs_create_ulong(dir, "hw_sdbt_blocks",
 					&oprofile_sdbt_blocks);
 
 	} else {
@@ -396,19 +395,19 @@ static int oprofile_create_hwsampling_files(struct super_block *sb,
 		 * space tools.  The /dev/oprofile/hwsampling fs is
 		 * provided in that case.
 		 */
-		dir = oprofilefs_mkdir(sb, root, "hwsampling");
+		dir = oprofilefs_mkdir(root, "hwsampling");
 		if (!dir)
 			return -EINVAL;
 
-		oprofilefs_create_file(sb, dir, "hwsampler",
+		oprofilefs_create_file(dir, "hwsampler",
 				       &hwsampler_fops);
-		oprofilefs_create_file(sb, dir, "hw_interval",
+		oprofilefs_create_file(dir, "hw_interval",
 				       &hw_interval_fops);
-		oprofilefs_create_ro_ulong(sb, dir, "hw_min_interval",
+		oprofilefs_create_ro_ulong(dir, "hw_min_interval",
 					   &oprofile_min_interval);
-		oprofilefs_create_ro_ulong(sb, dir, "hw_max_interval",
+		oprofilefs_create_ro_ulong(dir, "hw_max_interval",
 					   &oprofile_max_interval);
-		oprofilefs_create_ulong(sb, dir, "hw_sdbt_blocks",
+		oprofilefs_create_ulong(dir, "hw_sdbt_blocks",
 					&oprofile_sdbt_blocks);
 	}
 	return 0;

arch/x86/oprofile/nmi_int.c

@@ -403,7 +403,7 @@ static void nmi_cpu_down(void *dummy)
 		nmi_cpu_shutdown(dummy);
 }
 
-static int nmi_create_files(struct super_block *sb, struct dentry *root)
+static int nmi_create_files(struct dentry *root)
 {
 	unsigned int i;
 
@@ -420,14 +420,14 @@ static int nmi_create_files(struct super_block *sb, struct dentry *root)
 			continue;
 
 		snprintf(buf,  sizeof(buf), "%d", i);
-		dir = oprofilefs_mkdir(sb, root, buf);
+		dir = oprofilefs_mkdir(root, buf);
-		oprofilefs_create_ulong(sb, dir, "enabled", &counter_config[i].enabled);
+		oprofilefs_create_ulong(dir, "enabled", &counter_config[i].enabled);
-		oprofilefs_create_ulong(sb, dir, "event", &counter_config[i].event);
+		oprofilefs_create_ulong(dir, "event", &counter_config[i].event);
-		oprofilefs_create_ulong(sb, dir, "count", &counter_config[i].count);
+		oprofilefs_create_ulong(dir, "count", &counter_config[i].count);
-		oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask);
+		oprofilefs_create_ulong(dir, "unit_mask", &counter_config[i].unit_mask);
-		oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel);
+		oprofilefs_create_ulong(dir, "kernel", &counter_config[i].kernel);
-		oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user);
+		oprofilefs_create_ulong(dir, "user", &counter_config[i].user);
-		oprofilefs_create_ulong(sb, dir, "extra", &counter_config[i].extra);
+		oprofilefs_create_ulong(dir, "extra", &counter_config[i].extra);
 	}
 
 	return 0;

arch/x86/oprofile/op_model_amd.c

@@ -454,16 +454,16 @@ static void init_ibs(void)
 	printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps);
 }
 
-static int (*create_arch_files)(struct super_block *sb, struct dentry *root);
+static int (*create_arch_files)(struct dentry *root);
 
-static int setup_ibs_files(struct super_block *sb, struct dentry *root)
+static int setup_ibs_files(struct dentry *root)
 {
 	struct dentry *dir;
 	int ret = 0;
 
 	/* architecture specific files */
 	if (create_arch_files)
-		ret = create_arch_files(sb, root);
+		ret = create_arch_files(root);
 
 	if (ret)
 		return ret;
@@ -479,26 +479,26 @@ static int setup_ibs_files(struct super_block *sb, struct dentry *root)
 	ibs_config.max_cnt_op = 250000;
 
 	if (ibs_caps & IBS_CAPS_FETCHSAM) {
-		dir = oprofilefs_mkdir(sb, root, "ibs_fetch");
+		dir = oprofilefs_mkdir(root, "ibs_fetch");
-		oprofilefs_create_ulong(sb, dir, "enable",
+		oprofilefs_create_ulong(dir, "enable",
 					&ibs_config.fetch_enabled);
-		oprofilefs_create_ulong(sb, dir, "max_count",
+		oprofilefs_create_ulong(dir, "max_count",
 					&ibs_config.max_cnt_fetch);
-		oprofilefs_create_ulong(sb, dir, "rand_enable",
+		oprofilefs_create_ulong(dir, "rand_enable",
 					&ibs_config.rand_en);
 	}
 
 	if (ibs_caps & IBS_CAPS_OPSAM) {
-		dir = oprofilefs_mkdir(sb, root, "ibs_op");
+		dir = oprofilefs_mkdir(root, "ibs_op");
-		oprofilefs_create_ulong(sb, dir, "enable",
+		oprofilefs_create_ulong(dir, "enable",
 					&ibs_config.op_enabled);
-		oprofilefs_create_ulong(sb, dir, "max_count",
+		oprofilefs_create_ulong(dir, "max_count",
 					&ibs_config.max_cnt_op);
 		if (ibs_caps & IBS_CAPS_OPCNT)
-			oprofilefs_create_ulong(sb, dir, "dispatched_ops",
+			oprofilefs_create_ulong(dir, "dispatched_ops",
 						&ibs_config.dispatched_ops);
 		if (ibs_caps & IBS_CAPS_BRNTRGT)
-			oprofilefs_create_ulong(sb, dir, "branch_target",
+			oprofilefs_create_ulong(dir, "branch_target",
 						&ibs_config.branch_target);
 	}
 

drivers/dma/coh901318.c

@@ -1339,15 +1339,14 @@ static int coh901318_debugfs_read(struct file *file, char __user *buf,
 {
 	u64 started_channels = debugfs_dma_base->pm.started_channels;
 	int pool_count = debugfs_dma_base->pool.debugfs_pool_counter;
-	int i;
-	int ret = 0;
 	char *dev_buf;
 	char *tmp;
-	int dev_size;
+	int ret;
+	int i;
 
 	dev_buf = kmalloc(4*1024, GFP_KERNEL);
 	if (dev_buf == NULL)
-		goto err_kmalloc;
+		return -ENOMEM;
 	tmp = dev_buf;
 
 	tmp += sprintf(tmp, "DMA -- enabled dma channels\n");
@@ -1357,26 +1356,11 @@ static int coh901318_debugfs_read(struct file *file, char __user *buf,
 			tmp += sprintf(tmp, "channel %d\n", i);
 
 	tmp += sprintf(tmp, "Pool alloc nbr %d\n", pool_count);
-	dev_size = tmp  - dev_buf;
 
-	/* No more to read if offset != 0 */
+	ret = simple_read_from_buffer(buf, count, f_pos, dev_buf, 
-	if (*f_pos > dev_size)
+					tmp - dev_buf);
-		goto out;
-
-	if (count > dev_size - *f_pos)
-		count = dev_size - *f_pos;
-
-	if (copy_to_user(buf, dev_buf + *f_pos, count))
-		ret = -EINVAL;
-	ret = count;
-	*f_pos += count;
-
- out:
 	kfree(dev_buf);
 	return ret;
-
- err_kmalloc:
-	return 0;
 }
 
 static const struct file_operations coh901318_debugfs_status_operations = {

drivers/misc/ibmasm/ibmasmfs.c

@@ -149,8 +149,7 @@ static struct inode *ibmasmfs_make_inode(struct super_block *sb, int mode)
 	return ret;
 }
 
-static struct dentry *ibmasmfs_create_file (struct super_block *sb,
+static struct dentry *ibmasmfs_create_file(struct dentry *parent,
-			struct dentry *parent,
 			const char *name,
 			const struct file_operations *fops,
 			void *data,
@@ -163,7 +162,7 @@ static struct dentry *ibmasmfs_create_file (struct super_block *sb,
 	if (!dentry)
 		return NULL;
 
-	inode = ibmasmfs_make_inode(sb, S_IFREG | mode);
+	inode = ibmasmfs_make_inode(parent->d_sb, S_IFREG | mode);
 	if (!inode) {
 		dput(dentry);
 		return NULL;
@@ -176,8 +175,7 @@ static struct dentry *ibmasmfs_create_file (struct super_block *sb,
 	return dentry;
 }
 
-static struct dentry *ibmasmfs_create_dir (struct super_block *sb,
+static struct dentry *ibmasmfs_create_dir(struct dentry *parent,
-				struct dentry *parent,
 				const char *name)
 {
 	struct dentry *dentry;
@@ -187,7 +185,7 @@ static struct dentry *ibmasmfs_create_dir (struct super_block *sb,
 	if (!dentry)
 		return NULL;
 
-	inode = ibmasmfs_make_inode(sb, S_IFDIR | 0500);
+	inode = ibmasmfs_make_inode(parent->d_sb, S_IFDIR | 0500);
 	if (!inode) {
 		dput(dentry);
 		return NULL;
@@ -612,20 +610,20 @@ static void ibmasmfs_create_files (struct super_block *sb)
 		struct dentry *dir;
 		struct dentry *remote_dir;
 		sp = list_entry(entry, struct service_processor, node);
-		dir = ibmasmfs_create_dir(sb, sb->s_root, sp->dirname);
+		dir = ibmasmfs_create_dir(sb->s_root, sp->dirname);
 		if (!dir)
 			continue;
 
-		ibmasmfs_create_file(sb, dir, "command", &command_fops, sp, S_IRUSR|S_IWUSR);
+		ibmasmfs_create_file(dir, "command", &command_fops, sp, S_IRUSR|S_IWUSR);
-		ibmasmfs_create_file(sb, dir, "event", &event_fops, sp, S_IRUSR|S_IWUSR);
+		ibmasmfs_create_file(dir, "event", &event_fops, sp, S_IRUSR|S_IWUSR);
-		ibmasmfs_create_file(sb, dir, "reverse_heartbeat", &r_heartbeat_fops, sp, S_IRUSR|S_IWUSR);
+		ibmasmfs_create_file(dir, "reverse_heartbeat", &r_heartbeat_fops, sp, S_IRUSR|S_IWUSR);
 
-		remote_dir = ibmasmfs_create_dir(sb, dir, "remote_video");
+		remote_dir = ibmasmfs_create_dir(dir, "remote_video");
 		if (!remote_dir)
 			continue;
 
-		ibmasmfs_create_file(sb, remote_dir, "width", &remote_settings_fops, (void *)display_width(sp), S_IRUSR|S_IWUSR);
+		ibmasmfs_create_file(remote_dir, "width", &remote_settings_fops, (void *)display_width(sp), S_IRUSR|S_IWUSR);
-		ibmasmfs_create_file(sb, remote_dir, "height", &remote_settings_fops, (void *)display_height(sp), S_IRUSR|S_IWUSR);
+		ibmasmfs_create_file(remote_dir, "height", &remote_settings_fops, (void *)display_height(sp), S_IRUSR|S_IWUSR);
-		ibmasmfs_create_file(sb, remote_dir, "depth", &remote_settings_fops, (void *)display_depth(sp), S_IRUSR|S_IWUSR);
+		ibmasmfs_create_file(remote_dir, "depth", &remote_settings_fops, (void *)display_depth(sp), S_IRUSR|S_IWUSR);
 	}
 }

drivers/oprofile/oprof.h

@@ -30,10 +30,9 @@ extern struct oprofile_operations oprofile_ops;
 extern unsigned long oprofile_started;
 extern unsigned long oprofile_backtrace_depth;
 
-struct super_block;
 struct dentry;
 
-void oprofile_create_files(struct super_block *sb, struct dentry *root);
+void oprofile_create_files(struct dentry *root);
 int oprofile_timer_init(struct oprofile_operations *ops);
 #ifdef CONFIG_OPROFILE_NMI_TIMER
 int op_nmi_timer_init(struct oprofile_operations *ops);

drivers/oprofile/oprofile_files.c

@@ -175,7 +175,7 @@ static const struct file_operations dump_fops = {
 	.llseek		= noop_llseek,
 };
 
-void oprofile_create_files(struct super_block *sb, struct dentry *root)
+void oprofile_create_files(struct dentry *root)
 {
 	/* reinitialize default values */
 	oprofile_buffer_size =		BUFFER_SIZE_DEFAULT;
@@ -183,19 +183,19 @@ void oprofile_create_files(struct super_block *sb, struct dentry *root)
 	oprofile_buffer_watershed =	BUFFER_WATERSHED_DEFAULT;
 	oprofile_time_slice =		msecs_to_jiffies(TIME_SLICE_DEFAULT);
 
-	oprofilefs_create_file(sb, root, "enable", &enable_fops);
+	oprofilefs_create_file(root, "enable", &enable_fops);
-	oprofilefs_create_file_perm(sb, root, "dump", &dump_fops, 0666);
+	oprofilefs_create_file_perm(root, "dump", &dump_fops, 0666);
-	oprofilefs_create_file(sb, root, "buffer", &event_buffer_fops);
+	oprofilefs_create_file(root, "buffer", &event_buffer_fops);
-	oprofilefs_create_ulong(sb, root, "buffer_size", &oprofile_buffer_size);
+	oprofilefs_create_ulong(root, "buffer_size", &oprofile_buffer_size);
-	oprofilefs_create_ulong(sb, root, "buffer_watershed", &oprofile_buffer_watershed);
+	oprofilefs_create_ulong(root, "buffer_watershed", &oprofile_buffer_watershed);
-	oprofilefs_create_ulong(sb, root, "cpu_buffer_size", &oprofile_cpu_buffer_size);
+	oprofilefs_create_ulong(root, "cpu_buffer_size", &oprofile_cpu_buffer_size);
-	oprofilefs_create_file(sb, root, "cpu_type", &cpu_type_fops);
+	oprofilefs_create_file(root, "cpu_type", &cpu_type_fops);
-	oprofilefs_create_file(sb, root, "backtrace_depth", &depth_fops);
+	oprofilefs_create_file(root, "backtrace_depth", &depth_fops);
-	oprofilefs_create_file(sb, root, "pointer_size", &pointer_size_fops);
+	oprofilefs_create_file(root, "pointer_size", &pointer_size_fops);
 #ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
-	oprofilefs_create_file(sb, root, "time_slice", &timeout_fops);
+	oprofilefs_create_file(root, "time_slice", &timeout_fops);
 #endif
-	oprofile_create_stats_files(sb, root);
+	oprofile_create_stats_files(root);
 	if (oprofile_ops.create_files)
-		oprofile_ops.create_files(sb, root);
+		oprofile_ops.create_files(root);
 }

drivers/oprofile/oprofile_perf.c

@@ -138,7 +138,7 @@ static void op_perf_stop(void)
 			op_destroy_counter(cpu, event);
 }
 
-static int oprofile_perf_create_files(struct super_block *sb, struct dentry *root)
+static int oprofile_perf_create_files(struct dentry *root)
 {
 	unsigned int i;
 
@@ -147,13 +147,13 @@ static int oprofile_perf_create_files(struct super_block *sb, struct dentry *roo
 		char buf[4];
 
 		snprintf(buf, sizeof buf, "%d", i);
-		dir = oprofilefs_mkdir(sb, root, buf);
+		dir = oprofilefs_mkdir(root, buf);
-		oprofilefs_create_ulong(sb, dir, "enabled", &counter_config[i].enabled);
+		oprofilefs_create_ulong(dir, "enabled", &counter_config[i].enabled);
-		oprofilefs_create_ulong(sb, dir, "event", &counter_config[i].event);
+		oprofilefs_create_ulong(dir, "event", &counter_config[i].event);
-		oprofilefs_create_ulong(sb, dir, "count", &counter_config[i].count);
+		oprofilefs_create_ulong(dir, "count", &counter_config[i].count);
-		oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask);
+		oprofilefs_create_ulong(dir, "unit_mask", &counter_config[i].unit_mask);
-		oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel);
+		oprofilefs_create_ulong(dir, "kernel", &counter_config[i].kernel);
-		oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user);
+		oprofilefs_create_ulong(dir, "user", &counter_config[i].user);
 	}
 
 	return 0;

drivers/oprofile/oprofile_stats.c

@@ -38,7 +38,7 @@ void oprofile_reset_stats(void)
 }
 
 
-void oprofile_create_stats_files(struct super_block *sb, struct dentry *root)
+void oprofile_create_stats_files(struct dentry *root)
 {
 	struct oprofile_cpu_buffer *cpu_buf;
 	struct dentry *cpudir;
@@ -46,39 +46,39 @@ void oprofile_create_stats_files(struct super_block *sb, struct dentry *root)
 	char buf[10];
 	int i;
 
-	dir = oprofilefs_mkdir(sb, root, "stats");
+	dir = oprofilefs_mkdir(root, "stats");
 	if (!dir)
 		return;
 
 	for_each_possible_cpu(i) {
 		cpu_buf = &per_cpu(op_cpu_buffer, i);
 		snprintf(buf, 10, "cpu%d", i);
-		cpudir = oprofilefs_mkdir(sb, dir, buf);
+		cpudir = oprofilefs_mkdir(dir, buf);
 
 		/* Strictly speaking access to these ulongs is racy,
 		 * but we can't simply lock them, and they are
 		 * informational only.
 		 */
-		oprofilefs_create_ro_ulong(sb, cpudir, "sample_received",
+		oprofilefs_create_ro_ulong(cpudir, "sample_received",
 			&cpu_buf->sample_received);
-		oprofilefs_create_ro_ulong(sb, cpudir, "sample_lost_overflow",
+		oprofilefs_create_ro_ulong(cpudir, "sample_lost_overflow",
 			&cpu_buf->sample_lost_overflow);
-		oprofilefs_create_ro_ulong(sb, cpudir, "backtrace_aborted",
+		oprofilefs_create_ro_ulong(cpudir, "backtrace_aborted",
 			&cpu_buf->backtrace_aborted);
-		oprofilefs_create_ro_ulong(sb, cpudir, "sample_invalid_eip",
+		oprofilefs_create_ro_ulong(cpudir, "sample_invalid_eip",
 			&cpu_buf->sample_invalid_eip);
 	}
 
-	oprofilefs_create_ro_atomic(sb, dir, "sample_lost_no_mm",
+	oprofilefs_create_ro_atomic(dir, "sample_lost_no_mm",
 		&oprofile_stats.sample_lost_no_mm);
-	oprofilefs_create_ro_atomic(sb, dir, "sample_lost_no_mapping",
+	oprofilefs_create_ro_atomic(dir, "sample_lost_no_mapping",
 		&oprofile_stats.sample_lost_no_mapping);
-	oprofilefs_create_ro_atomic(sb, dir, "event_lost_overflow",
+	oprofilefs_create_ro_atomic(dir, "event_lost_overflow",
 		&oprofile_stats.event_lost_overflow);
-	oprofilefs_create_ro_atomic(sb, dir, "bt_lost_no_mapping",
+	oprofilefs_create_ro_atomic(dir, "bt_lost_no_mapping",
 		&oprofile_stats.bt_lost_no_mapping);
 #ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
-	oprofilefs_create_ro_atomic(sb, dir, "multiplex_counter",
+	oprofilefs_create_ro_atomic(dir, "multiplex_counter",
 		&oprofile_stats.multiplex_counter);
 #endif
 }

drivers/oprofile/oprofile_stats.h

@@ -25,10 +25,9 @@ extern struct oprofile_stat_struct oprofile_stats;
 /* reset all stats to zero */
 void oprofile_reset_stats(void);
 
-struct super_block;
 struct dentry;
 
 /* create the stats/ dir */
-void oprofile_create_stats_files(struct super_block *sb, struct dentry *root);
+void oprofile_create_stats_files(struct dentry *root);
 
 #endif /* OPROFILE_STATS_H */

drivers/oprofile/oprofilefs.c

@@ -132,9 +132,8 @@ static const struct file_operations ulong_ro_fops = {
 };
 
 
-static int __oprofilefs_create_file(struct super_block *sb,
+static int __oprofilefs_create_file(struct dentry *root, char const *name,
-	struct dentry *root, char const *name, const struct file_operations *fops,
+	const struct file_operations *fops, int perm, void *priv)
-	int perm, void *priv)
 {
 	struct dentry *dentry;
 	struct inode *inode;
@@ -145,7 +144,7 @@ static int __oprofilefs_create_file(struct super_block *sb,
 		mutex_unlock(&root->d_inode->i_mutex);
 		return -ENOMEM;
 	}
-	inode = oprofilefs_get_inode(sb, S_IFREG | perm);
+	inode = oprofilefs_get_inode(root->d_sb, S_IFREG | perm);
 	if (!inode) {
 		dput(dentry);
 		mutex_unlock(&root->d_inode->i_mutex);
@@ -159,18 +158,18 @@ static int __oprofilefs_create_file(struct super_block *sb,
 }
 
 
-int oprofilefs_create_ulong(struct super_block *sb, struct dentry *root,
+int oprofilefs_create_ulong(struct dentry *root,
 	char const *name, unsigned long *val)
 {
-	return __oprofilefs_create_file(sb, root, name,
+	return __oprofilefs_create_file(root, name,
 					&ulong_fops, 0644, val);
 }
 
 
-int oprofilefs_create_ro_ulong(struct super_block *sb, struct dentry *root,
+int oprofilefs_create_ro_ulong(struct dentry *root,
 	char const *name, unsigned long *val)
 {
-	return __oprofilefs_create_file(sb, root, name,
+	return __oprofilefs_create_file(root, name,
 					&ulong_ro_fops, 0444, val);
 }
 
@@ -189,50 +188,49 @@ static const struct file_operations atomic_ro_fops = {
 };
 
 
-int oprofilefs_create_ro_atomic(struct super_block *sb, struct dentry *root,
+int oprofilefs_create_ro_atomic(struct dentry *root,
 	char const *name, atomic_t *val)
 {
-	return __oprofilefs_create_file(sb, root, name,
+	return __oprofilefs_create_file(root, name,
 					&atomic_ro_fops, 0444, val);
 }
 
 
-int oprofilefs_create_file(struct super_block *sb, struct dentry *root,
+int oprofilefs_create_file(struct dentry *root,
 	char const *name, const struct file_operations *fops)
 {
-	return __oprofilefs_create_file(sb, root, name, fops, 0644, NULL);
+	return __oprofilefs_create_file(root, name, fops, 0644, NULL);
 }
 
 
-int oprofilefs_create_file_perm(struct super_block *sb, struct dentry *root,
+int oprofilefs_create_file_perm(struct dentry *root,
 	char const *name, const struct file_operations *fops, int perm)
 {
-	return __oprofilefs_create_file(sb, root, name, fops, perm, NULL);
+	return __oprofilefs_create_file(root, name, fops, perm, NULL);
 }
 
 
-struct dentry *oprofilefs_mkdir(struct super_block *sb,
+struct dentry *oprofilefs_mkdir(struct dentry *parent, char const *name)
-	struct dentry *root, char const *name)
 {
 	struct dentry *dentry;
 	struct inode *inode;
 
-	mutex_lock(&root->d_inode->i_mutex);
+	mutex_lock(&parent->d_inode->i_mutex);
-	dentry = d_alloc_name(root, name);
+	dentry = d_alloc_name(parent, name);
 	if (!dentry) {
-		mutex_unlock(&root->d_inode->i_mutex);
+		mutex_unlock(&parent->d_inode->i_mutex);
 		return NULL;
 	}
-	inode = oprofilefs_get_inode(sb, S_IFDIR | 0755);
+	inode = oprofilefs_get_inode(parent->d_sb, S_IFDIR | 0755);
 	if (!inode) {
 		dput(dentry);
-		mutex_unlock(&root->d_inode->i_mutex);
+		mutex_unlock(&parent->d_inode->i_mutex);
 		return NULL;
 	}
 	inode->i_op = &simple_dir_inode_operations;
 	inode->i_fop = &simple_dir_operations;
 	d_add(dentry, inode);
-	mutex_unlock(&root->d_inode->i_mutex);
+	mutex_unlock(&parent->d_inode->i_mutex);
 	return dentry;
 }
 
@@ -256,7 +254,7 @@ static int oprofilefs_fill_super(struct super_block *sb, void *data, int silent)
 	if (!sb->s_root)
 		return -ENOMEM;
 
-	oprofile_create_files(sb, sb->s_root);
+	oprofile_create_files(sb->s_root);
 
 	// FIXME: verify kill_litter_super removes our dentries
 	return 0;

fs/block_dev.c

@@ -1519,7 +1519,7 @@ ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
 
 	blk_start_plug(&plug);
 	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
-	if (ret > 0 || ret == -EIOCBQUEUED) {
+	if (ret > 0) {
 		ssize_t err;
 
 		err = generic_write_sync(file, pos, ret);

fs/btrfs/file.c

@@ -1727,7 +1727,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 	 */
 	BTRFS_I(inode)->last_trans = root->fs_info->generation + 1;
 	BTRFS_I(inode)->last_sub_trans = root->log_transid;
-	if (num_written > 0 || num_written == -EIOCBQUEUED) {
+	if (num_written > 0) {
 		err = generic_write_sync(file, pos, num_written);
 		if (err < 0 && num_written > 0)
 			num_written = err;

fs/cifs/file.c

@@ -2553,7 +2553,7 @@ cifs_writev(struct kiocb *iocb, const struct iovec *iov,
 		mutex_unlock(&inode->i_mutex);
 	}
 
-	if (rc > 0 || rc == -EIOCBQUEUED) {
+	if (rc > 0) {
 		ssize_t err;
 
 		err = generic_write_sync(file, pos, rc);

fs/dcache.c

@@ -472,7 +472,7 @@ relock:
 	 * inform the fs via d_prune that this dentry is about to be
 	 * unhashed and destroyed.
 	 */
-	if (dentry->d_flags & DCACHE_OP_PRUNE)
+	if ((dentry->d_flags & DCACHE_OP_PRUNE) && !d_unhashed(dentry))
 		dentry->d_op->d_prune(dentry);
 
 	dentry_lru_del(dentry);
@@ -727,6 +727,14 @@ restart:
 	hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
 		spin_lock(&dentry->d_lock);
 		if (!dentry->d_lockref.count) {
+			/*
+			 * inform the fs via d_prune 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);
+
 			__dget_dlock(dentry);
 			__d_drop(dentry);
 			spin_unlock(&dentry->d_lock);
@@ -911,7 +919,8 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
 			 * inform the fs that this dentry is about to be
 			 * unhashed and destroyed.
 			 */
-			if (dentry->d_flags & DCACHE_OP_PRUNE)
+			if ((dentry->d_flags & DCACHE_OP_PRUNE) &&
+			    !d_unhashed(dentry))
 				dentry->d_op->d_prune(dentry);
 
 			dentry_lru_del(dentry);

fs/direct-io.c

@@ -127,6 +127,7 @@ struct dio {
 	spinlock_t bio_lock;		/* protects BIO fields below */
 	int page_errors;		/* errno from get_user_pages() */
 	int is_async;			/* is IO async ? */
+	bool defer_completion;		/* defer AIO completion to workqueue? */
 	int io_error;			/* IO error in completion path */
 	unsigned long refcount;		/* direct_io_worker() and bios */
 	struct bio *bio_list;		/* singly linked via bi_private */
@@ -141,7 +142,10 @@ struct dio {
 	 * allocation time.  Don't add new fields after pages[] unless you
 	 * wish that they not be zeroed.
 	 */
-	struct page *pages[DIO_PAGES];	/* page buffer */
+	union {
+		struct page *pages[DIO_PAGES];	/* page buffer */
+		struct work_struct complete_work;/* deferred AIO completion */
+	};
 } ____cacheline_aligned_in_smp;
 
 static struct kmem_cache *dio_cache __read_mostly;
@@ -221,16 +225,16 @@ static inline struct page *dio_get_page(struct dio *dio,
  * dio_complete() - called when all DIO BIO I/O has been completed
  * @offset: the byte offset in the file of the completed operation
  *
- * This releases locks as dictated by the locking type, lets interested parties
+ * This drops i_dio_count, lets interested parties know that a DIO operation
- * know that a DIO operation has completed, and calculates the resulting return
+ * has completed, and calculates the resulting return code for the operation.
- * code for the operation.
  *
  * It lets the filesystem know if it registered an interest earlier via
  * get_block.  Pass the private field of the map buffer_head so that
  * filesystems can use it to hold additional state between get_block calls and
  * dio_complete.
  */
-static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, bool is_async)
+static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret,
+		bool is_async)
 {
 	ssize_t transferred = 0;
 
@@ -258,19 +262,36 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, bool is
 	if (ret == 0)
 		ret = transferred;
 
-	if (dio->end_io && dio->result) {
+	if (dio->end_io && dio->result)
-		dio->end_io(dio->iocb, offset, transferred,
+		dio->end_io(dio->iocb, offset, transferred, dio->private);
-			    dio->private, ret, is_async);
+
-	} else {
+	inode_dio_done(dio->inode);
-		inode_dio_done(dio->inode);
+	if (is_async) {
-		if (is_async)
+		if (dio->rw & WRITE) {
-			aio_complete(dio->iocb, ret, 0);
+			int err;
+
+			err = generic_write_sync(dio->iocb->ki_filp, offset,
+						 transferred);
+			if (err < 0 && ret > 0)
+				ret = err;
+		}
+
+		aio_complete(dio->iocb, ret, 0);
 	}
 
+	kmem_cache_free(dio_cache, dio);
 	return ret;
 }
 
+static void dio_aio_complete_work(struct work_struct *work)
+{
+	struct dio *dio = container_of(work, struct dio, complete_work);
+
+	dio_complete(dio, dio->iocb->ki_pos, 0, true);
+}
+
 static int dio_bio_complete(struct dio *dio, struct bio *bio);
+
 /*
  * Asynchronous IO callback. 
  */
@@ -290,8 +311,13 @@ static void dio_bio_end_aio(struct bio *bio, int error)
 	spin_unlock_irqrestore(&dio->bio_lock, flags);
 
 	if (remaining == 0) {
-		dio_complete(dio, dio->iocb->ki_pos, 0, true);
+		if (dio->result && dio->defer_completion) {
-		kmem_cache_free(dio_cache, dio);
+			INIT_WORK(&dio->complete_work, dio_aio_complete_work);
+			queue_work(dio->inode->i_sb->s_dio_done_wq,
+				   &dio->complete_work);
+		} else {
+			dio_complete(dio, dio->iocb->ki_pos, 0, true);
+		}
 	}
 }
 
@@ -510,6 +536,41 @@ static inline int dio_bio_reap(struct dio *dio, struct dio_submit *sdio)
 	return ret;
 }
 
+/*
+ * Create workqueue for deferred direct IO completions. We allocate the
+ * workqueue when it's first needed. This avoids creating workqueue for
+ * filesystems that don't need it and also allows us to create the workqueue
+ * late enough so the we can include s_id in the name of the workqueue.
+ */
+static int sb_init_dio_done_wq(struct super_block *sb)
+{
+	struct workqueue_struct *wq = alloc_workqueue("dio/%s",
+						      WQ_MEM_RECLAIM, 0,
+						      sb->s_id);
+	if (!wq)
+		return -ENOMEM;
+	/*
+	 * This has to be atomic as more DIOs can race to create the workqueue
+	 */
+	cmpxchg(&sb->s_dio_done_wq, NULL, wq);
+	/* Someone created workqueue before us? Free ours... */
+	if (wq != sb->s_dio_done_wq)
+		destroy_workqueue(wq);
+	return 0;
+}
+
+static int dio_set_defer_completion(struct dio *dio)
+{
+	struct super_block *sb = dio->inode->i_sb;
+
+	if (dio->defer_completion)
+		return 0;
+	dio->defer_completion = true;
+	if (!sb->s_dio_done_wq)
+		return sb_init_dio_done_wq(sb);
+	return 0;
+}
+
 /*
  * Call into the fs to map some more disk blocks.  We record the current number
  * of available blocks at sdio->blocks_available.  These are in units of the
@@ -581,6 +642,9 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio,
 
 		/* Store for completion */
 		dio->private = map_bh->b_private;
+
+		if (ret == 0 && buffer_defer_completion(map_bh))
+			ret = dio_set_defer_completion(dio);
 	}
 	return ret;
 }
@@ -1128,11 +1192,6 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 		}
 	}
 
-	/*
-	 * Will be decremented at I/O completion time.
-	 */
-	atomic_inc(&inode->i_dio_count);
-
 	/*
 	 * For file extending writes updating i_size before data
 	 * writeouts complete can expose uninitialized blocks. So
@@ -1141,11 +1200,33 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	 */
 	dio->is_async = !is_sync_kiocb(iocb) && !((rw & WRITE) &&
 		(end > i_size_read(inode)));
-
-	retval = 0;
-
 	dio->inode = inode;
 	dio->rw = rw;
+
+	/*
+	 * For AIO O_(D)SYNC writes we need to defer completions to a workqueue
+	 * so that we can call ->fsync.
+	 */
+	if (dio->is_async && (rw & WRITE) &&
+	    ((iocb->ki_filp->f_flags & O_DSYNC) ||
+	     IS_SYNC(iocb->ki_filp->f_mapping->host))) {
+		retval = dio_set_defer_completion(dio);
+		if (retval) {
+			/*
+			 * We grab i_mutex only for reads so we don't have
+			 * to release it here
+			 */
+			kmem_cache_free(dio_cache, dio);
+			goto out;
+		}
+	}
+
+	/*
+	 * Will be decremented at I/O completion time.
+	 */
+	atomic_inc(&inode->i_dio_count);
+
+	retval = 0;
 	sdio.blkbits = blkbits;
 	sdio.blkfactor = i_blkbits - blkbits;
 	sdio.block_in_file = offset >> blkbits;
@@ -1269,7 +1350,6 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 
 	if (drop_refcount(dio) == 0) {
 		retval = dio_complete(dio, offset, retval, false);
-		kmem_cache_free(dio_cache, dio);
 	} else
 		BUG_ON(retval != -EIOCBQUEUED);
 

fs/eventpoll.c

@@ -1792,7 +1792,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 {
 	int error;
 	int did_lock_epmutex = 0;
-	struct file *file, *tfile;
+	struct fd f, tf;
 	struct eventpoll *ep;
 	struct epitem *epi;
 	struct epoll_event epds;
@@ -1802,20 +1802,19 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	    copy_from_user(&epds, event, sizeof(struct epoll_event)))
 		goto error_return;
 
-	/* Get the "struct file *" for the eventpoll file */
 	error = -EBADF;
-	file = fget(epfd);
+	f = fdget(epfd);
-	if (!file)
+	if (!f.file)
 		goto error_return;
 
 	/* Get the "struct file *" for the target file */
-	tfile = fget(fd);
+	tf = fdget(fd);
-	if (!tfile)
+	if (!tf.file)
 		goto error_fput;
 
 	/* The target file descriptor must support poll */
 	error = -EPERM;
-	if (!tfile->f_op || !tfile->f_op->poll)
+	if (!tf.file->f_op || !tf.file->f_op->poll)
 		goto error_tgt_fput;
 
 	/* Check if EPOLLWAKEUP is allowed */
@@ -1828,14 +1827,14 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	 * adding an epoll file descriptor inside itself.
 	 */
 	error = -EINVAL;
-	if (file == tfile || !is_file_epoll(file))
+	if (f.file == tf.file || !is_file_epoll(f.file))
 		goto error_tgt_fput;
 
 	/*
 	 * At this point it is safe to assume that the "private_data" contains
 	 * our own data structure.
 	 */
-	ep = file->private_data;
+	ep = f.file->private_data;
 
 	/*
 	 * When we insert an epoll file descriptor, inside another epoll file
@@ -1854,14 +1853,14 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 		did_lock_epmutex = 1;
 	}
 	if (op == EPOLL_CTL_ADD) {
-		if (is_file_epoll(tfile)) {
+		if (is_file_epoll(tf.file)) {
 			error = -ELOOP;
-			if (ep_loop_check(ep, tfile) != 0) {
+			if (ep_loop_check(ep, tf.file) != 0) {
 				clear_tfile_check_list();
 				goto error_tgt_fput;
 			}
 		} else
-			list_add(&tfile->f_tfile_llink, &tfile_check_list);
+			list_add(&tf.file->f_tfile_llink, &tfile_check_list);
 	}
 
 	mutex_lock_nested(&ep->mtx, 0);
@@ -1871,14 +1870,14 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	 * above, we can be sure to be able to use the item looked up by
 	 * ep_find() till we release the mutex.
 	 */
-	epi = ep_find(ep, tfile, fd);
+	epi = ep_find(ep, tf.file, fd);
 
 	error = -EINVAL;
 	switch (op) {
 	case EPOLL_CTL_ADD:
 		if (!epi) {
 			epds.events |= POLLERR | POLLHUP;
-			error = ep_insert(ep, &epds, tfile, fd);
+			error = ep_insert(ep, &epds, tf.file, fd);
 		} else
 			error = -EEXIST;
 		clear_tfile_check_list();
@@ -1903,9 +1902,9 @@ error_tgt_fput:
 	if (did_lock_epmutex)
 		mutex_unlock(&epmutex);
 
-	fput(tfile);
+	fdput(tf);
 error_fput:
-	fput(file);
+	fdput(f);
 error_return:
 
 	return error;

fs/ext4/ext4.h

@@ -180,7 +180,6 @@ struct ext4_map_blocks {
  * Flags for ext4_io_end->flags
  */
 #define	EXT4_IO_END_UNWRITTEN	0x0001
-#define EXT4_IO_END_DIRECT	0x0002
 
 /*
  * For converting uninitialized extents on a work queue. 'handle' is used for
@@ -196,8 +195,6 @@ typedef struct ext4_io_end {
 	unsigned int		flag;		/* unwritten or not */
 	loff_t			offset;		/* offset in the file */
 	ssize_t			size;		/* size of the extent */
-	struct kiocb		*iocb;		/* iocb struct for AIO */
-	int			result;		/* error value for AIO */
 	atomic_t		count;		/* reference counter */
 } ext4_io_end_t;
 
@@ -914,11 +911,9 @@ struct ext4_inode_info {
 	 * Completed IOs that need unwritten extents handling and don't have
 	 * transaction reserved
 	 */
-	struct list_head i_unrsv_conversion_list;
 	atomic_t i_ioend_count;	/* Number of outstanding io_end structs */
 	atomic_t i_unwritten; /* Nr. of inflight conversions pending */
 	struct work_struct i_rsv_conversion_work;
-	struct work_struct i_unrsv_conversion_work;
 
 	spinlock_t i_block_reservation_lock;
 
@@ -1290,8 +1285,6 @@ struct ext4_sb_info {
 	struct flex_groups *s_flex_groups;
 	ext4_group_t s_flex_groups_allocated;
 
-	/* workqueue for unreserved extent convertions (dio) */
-	struct workqueue_struct *unrsv_conversion_wq;
 	/* workqueue for reserved extent conversions (buffered io) */
 	struct workqueue_struct *rsv_conversion_wq;
 
@@ -1354,9 +1347,6 @@ static inline void ext4_set_io_unwritten_flag(struct inode *inode,
 					      struct ext4_io_end *io_end)
 {
 	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
-		/* Writeback has to have coversion transaction reserved */
-		WARN_ON(EXT4_SB(inode->i_sb)->s_journal && !io_end->handle &&
-			!(io_end->flag & EXT4_IO_END_DIRECT));
 		io_end->flag |= EXT4_IO_END_UNWRITTEN;
 		atomic_inc(&EXT4_I(inode)->i_unwritten);
 	}
@@ -2760,7 +2750,6 @@ extern void ext4_put_io_end_defer(ext4_io_end_t *io_end);
 extern void ext4_io_submit_init(struct ext4_io_submit *io,
 				struct writeback_control *wbc);
 extern void ext4_end_io_rsv_work(struct work_struct *work);
-extern void ext4_end_io_unrsv_work(struct work_struct *work);
 extern void ext4_io_submit(struct ext4_io_submit *io);
 extern int ext4_bio_write_page(struct ext4_io_submit *io,
 			       struct page *page,

fs/ext4/file.c

@@ -149,7 +149,7 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
 	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
 	mutex_unlock(&inode->i_mutex);
 
-	if (ret > 0 || ret == -EIOCBQUEUED) {
+	if (ret > 0) {
 		ssize_t err;
 
 		err = generic_write_sync(file, pos, ret);

fs/ext4/inode.c

@@ -727,8 +727,12 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
 
 	ret = ext4_map_blocks(handle, inode, &map, flags);
 	if (ret > 0) {
+		ext4_io_end_t *io_end = ext4_inode_aio(inode);
+
 		map_bh(bh, inode->i_sb, map.m_pblk);
 		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+		if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN)
+			set_buffer_defer_completion(bh);
 		bh->b_size = inode->i_sb->s_blocksize * map.m_len;
 		ret = 0;
 	}
@@ -3024,19 +3028,13 @@ static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock,
 }
 
 static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
-			    ssize_t size, void *private, int ret,
+			    ssize_t size, void *private)
-			    bool is_async)
 {
-	struct inode *inode = file_inode(iocb->ki_filp);
         ext4_io_end_t *io_end = iocb->private;
 
 	/* if not async direct IO just return */
-	if (!io_end) {
+	if (!io_end)
-		inode_dio_done(inode);
-		if (is_async)
-			aio_complete(iocb, ret, 0);
 		return;
-	}
 
 	ext_debug("ext4_end_io_dio(): io_end 0x%p "
 		  "for inode %lu, iocb 0x%p, offset %llu, size %zd\n",
@@ -3046,11 +3044,7 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
 	iocb->private = NULL;
 	io_end->offset = offset;
 	io_end->size = size;
-	if (is_async) {
+	ext4_put_io_end(io_end);
-		io_end->iocb = iocb;
-		io_end->result = ret;
-	}
-	ext4_put_io_end_defer(io_end);
 }
 
 /*
@@ -3135,7 +3129,6 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 			ret = -ENOMEM;
 			goto retake_lock;
 		}
-		io_end->flag |= EXT4_IO_END_DIRECT;
 		/*
 		 * Grab reference for DIO. Will be dropped in ext4_end_io_dio()
 		 */
@@ -3180,13 +3173,6 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 		if (ret <= 0 && ret != -EIOCBQUEUED && iocb->private) {
 			WARN_ON(iocb->private != io_end);
 			WARN_ON(io_end->flag & EXT4_IO_END_UNWRITTEN);
-			WARN_ON(io_end->iocb);
-			/*
-			 * Generic code already did inode_dio_done() so we
-			 * have to clear EXT4_IO_END_DIRECT to not do it for
-			 * the second time.
-			 */
-			io_end->flag = 0;
 			ext4_put_io_end(io_end);
 			iocb->private = NULL;
 		}

fs/ext4/page-io.c

@@ -123,10 +123,6 @@ static void ext4_release_io_end(ext4_io_end_t *io_end)
 		ext4_finish_bio(bio);
 		bio_put(bio);
 	}
-	if (io_end->flag & EXT4_IO_END_DIRECT)
-		inode_dio_done(io_end->inode);
-	if (io_end->iocb)
-		aio_complete(io_end->iocb, io_end->result, 0);
 	kmem_cache_free(io_end_cachep, io_end);
 }
 
@@ -204,19 +200,14 @@ static void ext4_add_complete_io(ext4_io_end_t *io_end)
 	struct workqueue_struct *wq;
 	unsigned long flags;
 
-	BUG_ON(!(io_end->flag & EXT4_IO_END_UNWRITTEN));
+	/* Only reserved conversions from writeback should enter here */
+	WARN_ON(!(io_end->flag & EXT4_IO_END_UNWRITTEN));
+	WARN_ON(!io_end->handle);
 	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
-	if (io_end->handle) {
+	wq = EXT4_SB(io_end->inode->i_sb)->rsv_conversion_wq;
-		wq = EXT4_SB(io_end->inode->i_sb)->rsv_conversion_wq;
+	if (list_empty(&ei->i_rsv_conversion_list))
-		if (list_empty(&ei->i_rsv_conversion_list))
+		queue_work(wq, &ei->i_rsv_conversion_work);
-			queue_work(wq, &ei->i_rsv_conversion_work);
+	list_add_tail(&io_end->list, &ei->i_rsv_conversion_list);
-		list_add_tail(&io_end->list, &ei->i_rsv_conversion_list);
-	} else {
-		wq = EXT4_SB(io_end->inode->i_sb)->unrsv_conversion_wq;
-		if (list_empty(&ei->i_unrsv_conversion_list))
-			queue_work(wq, &ei->i_unrsv_conversion_work);
-		list_add_tail(&io_end->list, &ei->i_unrsv_conversion_list);
-	}
 	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
 }
 
@@ -256,13 +247,6 @@ void ext4_end_io_rsv_work(struct work_struct *work)
 	ext4_do_flush_completed_IO(&ei->vfs_inode, &ei->i_rsv_conversion_list);
 }
 
-void ext4_end_io_unrsv_work(struct work_struct *work)
-{
-	struct ext4_inode_info *ei = container_of(work, struct ext4_inode_info,
-						  i_unrsv_conversion_work);
-	ext4_do_flush_completed_IO(&ei->vfs_inode, &ei->i_unrsv_conversion_list);
-}
-
 ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags)
 {
 	ext4_io_end_t *io = kmem_cache_zalloc(io_end_cachep, flags);

fs/ext4/super.c

@@ -762,9 +762,7 @@ static void ext4_put_super(struct super_block *sb)
 	ext4_unregister_li_request(sb);
 	dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
 
-	flush_workqueue(sbi->unrsv_conversion_wq);
 	flush_workqueue(sbi->rsv_conversion_wq);
-	destroy_workqueue(sbi->unrsv_conversion_wq);
 	destroy_workqueue(sbi->rsv_conversion_wq);
 
 	if (sbi->s_journal) {
@@ -875,14 +873,12 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 #endif
 	ei->jinode = NULL;
 	INIT_LIST_HEAD(&ei->i_rsv_conversion_list);
-	INIT_LIST_HEAD(&ei->i_unrsv_conversion_list);
 	spin_lock_init(&ei->i_completed_io_lock);
 	ei->i_sync_tid = 0;
 	ei->i_datasync_tid = 0;
 	atomic_set(&ei->i_ioend_count, 0);
 	atomic_set(&ei->i_unwritten, 0);
 	INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work);
-	INIT_WORK(&ei->i_unrsv_conversion_work, ext4_end_io_unrsv_work);
 
 	return &ei->vfs_inode;
 }
@@ -3995,14 +3991,6 @@ no_journal:
 		goto failed_mount4;
 	}
 
-	EXT4_SB(sb)->unrsv_conversion_wq =
-		alloc_workqueue("ext4-unrsv-conversion", WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
-	if (!EXT4_SB(sb)->unrsv_conversion_wq) {
-		printk(KERN_ERR "EXT4-fs: failed to create workqueue\n");
-		ret = -ENOMEM;
-		goto failed_mount4;
-	}
-
 	/*
 	 * The jbd2_journal_load will have done any necessary log recovery,
 	 * so we can safely mount the rest of the filesystem now.
@@ -4156,8 +4144,6 @@ failed_mount4:
 	ext4_msg(sb, KERN_ERR, "mount failed");
 	if (EXT4_SB(sb)->rsv_conversion_wq)
 		destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq);
-	if (EXT4_SB(sb)->unrsv_conversion_wq)
-		destroy_workqueue(EXT4_SB(sb)->unrsv_conversion_wq);
 failed_mount_wq:
 	if (sbi->s_journal) {
 		jbd2_journal_destroy(sbi->s_journal);
@@ -4605,7 +4591,6 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
 
 	trace_ext4_sync_fs(sb, wait);
 	flush_workqueue(sbi->rsv_conversion_wq);
-	flush_workqueue(sbi->unrsv_conversion_wq);
 	/*
 	 * Writeback quota in non-journalled quota case - journalled quota has
 	 * no dirty dquots
@@ -4641,7 +4626,6 @@ static int ext4_sync_fs_nojournal(struct super_block *sb, int wait)
 
 	trace_ext4_sync_fs(sb, wait);
 	flush_workqueue(EXT4_SB(sb)->rsv_conversion_wq);
-	flush_workqueue(EXT4_SB(sb)->unrsv_conversion_wq);
 	dquot_writeback_dquots(sb, -1);
 	if (wait && test_opt(sb, BARRIER))
 		ret = blkdev_issue_flush(sb->s_bdev, GFP_KERNEL, NULL);

fs/file_table.c

@@ -385,6 +385,10 @@ static inline void __file_sb_list_add(struct file *file, struct super_block *sb)
  */
 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);
@@ -450,8 +454,6 @@ void mark_files_ro(struct super_block *sb)
 
 	lg_global_lock(&files_lglock);
 	do_file_list_for_each_entry(sb, f) {
-		if (!S_ISREG(file_inode(f)->i_mode))
-		       continue;
 		if (!file_count(f))
 			continue;
 		if (!(f->f_mode & FMODE_WRITE))

fs/inode.c

@@ -1525,7 +1525,7 @@ static int update_time(struct inode *inode, struct timespec *time, int flags)
  *	This function automatically handles read only file systems and media,
  *	as well as the "noatime" flag and inode specific "noatime" markers.
  */
-void touch_atime(struct path *path)
+void touch_atime(const struct path *path)
 {
 	struct vfsmount *mnt = path->mnt;
 	struct inode *inode = path->dentry->d_inode;

fs/namei.c

@@ -2222,6 +2222,188 @@ user_path_parent(int dfd, const char __user *path, struct nameidata *nd,
 	return s;
 }
 
+/**
+ * umount_lookup_last - look up last component for umount
+ * @nd:   pathwalk nameidata - currently pointing at parent directory of "last"
+ * @path: pointer to container for result
+ *
+ * This is a special lookup_last function just for umount. In this case, we
+ * need to resolve the path without doing any revalidation.
+ *
+ * The nameidata should be the result of doing a LOOKUP_PARENT pathwalk. Since
+ * mountpoints are always pinned in the dcache, their ancestors are too. Thus,
+ * in almost all cases, this lookup will be served out of the dcache. The only
+ * cases where it won't are if nd->last refers to a symlink or the path is
+ * bogus and it doesn't exist.
+ *
+ * Returns:
+ * -error: if there was an error during lookup. This includes -ENOENT if the
+ *         lookup found a negative dentry. The nd->path reference will also be
+ *         put in this case.
+ *
+ * 0:      if we successfully resolved nd->path and found it to not to be a
+ *         symlink that needs to be followed. "path" will also be populated.
+ *         The nd->path reference will also be put.
+ *
+ * 1:      if we successfully resolved nd->last and found it to be a symlink
+ *         that needs to be followed. "path" will be populated with the path
+ *         to the link, and nd->path will *not* be put.
+ */
+static int
+umount_lookup_last(struct nameidata *nd, struct path *path)
+{
+	int error = 0;
+	struct dentry *dentry;
+	struct dentry *dir = nd->path.dentry;
+
+	if (unlikely(nd->flags & LOOKUP_RCU)) {
+		WARN_ON_ONCE(1);
+		error = -ECHILD;
+		goto error_check;
+	}
+
+	nd->flags &= ~LOOKUP_PARENT;
+
+	if (unlikely(nd->last_type != LAST_NORM)) {
+		error = handle_dots(nd, nd->last_type);
+		if (!error)
+			dentry = dget(nd->path.dentry);
+		goto error_check;
+	}
+
+	mutex_lock(&dir->d_inode->i_mutex);
+	dentry = d_lookup(dir, &nd->last);
+	if (!dentry) {
+		/*
+		 * No cached dentry. Mounted dentries are pinned in the cache,
+		 * so that means that this dentry is probably a symlink or the
+		 * path doesn't actually point to a mounted dentry.
+		 */
+		dentry = d_alloc(dir, &nd->last);
+		if (!dentry) {
+			error = -ENOMEM;
+		} else {
+			dentry = lookup_real(dir->d_inode, dentry, nd->flags);
+			if (IS_ERR(dentry))
+				error = PTR_ERR(dentry);
+		}
+	}
+	mutex_unlock(&dir->d_inode->i_mutex);
+
+error_check:
+	if (!error) {
+		if (!dentry->d_inode) {
+			error = -ENOENT;
+			dput(dentry);
+		} else {
+			path->dentry = dentry;
+			path->mnt = mntget(nd->path.mnt);
+			if (should_follow_link(dentry->d_inode,
+						nd->flags & LOOKUP_FOLLOW))
+				return 1;
+			follow_mount(path);
+		}
+	}
+	terminate_walk(nd);
+	return error;
+}
+
+/**
+ * path_umountat - look up a path to be umounted
+ * @dfd:	directory file descriptor to start walk from
+ * @name:	full pathname to walk
+ * @flags:	lookup flags
+ * @nd:		pathwalk nameidata
+ *
+ * Look up the given name, but don't attempt to revalidate the last component.
+ * Returns 0 and "path" will be valid on success; Retuns error otherwise.
+ */
+static int
+path_umountat(int dfd, const char *name, struct path *path, unsigned int flags)
+{
+	struct file *base = NULL;
+	struct nameidata nd;
+	int err;
+
+	err = path_init(dfd, name, flags | LOOKUP_PARENT, &nd, &base);
+	if (unlikely(err))
+		return err;
+
+	current->total_link_count = 0;
+	err = link_path_walk(name, &nd);
+	if (err)
+		goto out;
+
+	/* If we're in rcuwalk, drop out of it to handle last component */
+	if (nd.flags & LOOKUP_RCU) {
+		err = unlazy_walk(&nd, NULL);
+		if (err) {
+			terminate_walk(&nd);
+			goto out;
+		}
+	}
+
+	err = umount_lookup_last(&nd, path);
+	while (err > 0) {
+		void *cookie;
+		struct path link = *path;
+		err = may_follow_link(&link, &nd);
+		if (unlikely(err))
+			break;
+		nd.flags |= LOOKUP_PARENT;
+		err = follow_link(&link, &nd, &cookie);
+		if (err)
+			break;
+		err = umount_lookup_last(&nd, path);
+		put_link(&nd, &link, cookie);
+	}
+out:
+	if (base)
+		fput(base);
+
+	if (nd.root.mnt && !(nd.flags & LOOKUP_ROOT))
+		path_put(&nd.root);
+
+	return err;
+}
+
+/**
+ * user_path_umountat - lookup a path from userland in order to umount it
+ * @dfd:	directory file descriptor
+ * @name:	pathname from userland
+ * @flags:	lookup flags
+ * @path:	pointer to container to hold result
+ *
+ * A umount is a special case for path walking. We're not actually interested
+ * in the inode in this situation, and ESTALE errors can be a problem. We
+ * simply want track down the dentry and vfsmount attached at the mountpoint
+ * and avoid revalidating the last component.
+ *
+ * Returns 0 and populates "path" on success.
+ */
+int
+user_path_umountat(int dfd, const char __user *name, unsigned int flags,
+			struct path *path)
+{
+	struct filename *s = getname(name);
+	int error;
+
+	if (IS_ERR(s))
+		return PTR_ERR(s);
+
+	error = path_umountat(dfd, s->name, path, flags | LOOKUP_RCU);
+	if (unlikely(error == -ECHILD))
+		error = path_umountat(dfd, s->name, path, flags);
+	if (unlikely(error == -ESTALE))
+		error = path_umountat(dfd, s->name, path, flags | LOOKUP_REVAL);
+
+	if (likely(!error))
+		audit_inode(s, path->dentry, 0);
+
+	putname(s);
+	return error;
+}
+
 /*
  * It's inline, so penalty for filesystems that don't use sticky bit is
  * minimal.

fs/namespace.c

@@ -1318,7 +1318,7 @@ SYSCALL_DEFINE2(umount, char __user *, name, int, flags)
 	if (!(flags & UMOUNT_NOFOLLOW))
 		lookup_flags |= LOOKUP_FOLLOW;
 
-	retval = user_path_at(AT_FDCWD, name, lookup_flags, &path);
+	retval = user_path_umountat(AT_FDCWD, name, lookup_flags, &path);
 	if (retval)
 		goto out;
 	mnt = real_mount(path.mnt);

fs/nfsd/nfs4xdr.c

@@ -1816,10 +1816,7 @@ static __be32 nfsd4_encode_fs_location4(struct nfsd4_fs_location *location,
 static __be32 nfsd4_encode_path(const struct path *root,
 		const struct path *path, __be32 **pp, int *buflen)
 {
-	struct path cur = {
+	struct path cur = *path;
-		.mnt = path->mnt,
-		.dentry = path->dentry,
-	};
 	__be32 *p = *pp;
 	struct dentry **components = NULL;
 	unsigned int ncomponents = 0;
@@ -1859,14 +1856,19 @@ static __be32 nfsd4_encode_path(const struct path *root,
 
 	while (ncomponents) {
 		struct dentry *dentry = components[ncomponents - 1];
-		unsigned int len = dentry->d_name.len;
+		unsigned int len;
 
+		spin_lock(&dentry->d_lock);
+		len = dentry->d_name.len;
 		*buflen -= 4 + (XDR_QUADLEN(len) << 2);
-		if (*buflen < 0)
+		if (*buflen < 0) {
+			spin_unlock(&dentry->d_lock);
 			goto out_free;
+		}
 		WRITE32(len);
 		WRITEMEM(dentry->d_name.name, len);
 		dprintk("/%s", dentry->d_name.name);
+		spin_unlock(&dentry->d_lock);
 		dput(dentry);
 		ncomponents--;
 	}

fs/nilfs2/super.c

@@ -994,23 +994,16 @@ static int nilfs_attach_snapshot(struct super_block *s, __u64 cno,
 	return ret;
 }
 
-static int nilfs_tree_was_touched(struct dentry *root_dentry)
-{
-	return d_count(root_dentry) > 1;
-}
-
 /**
- * nilfs_try_to_shrink_tree() - try to shrink dentries of a checkpoint
+ * nilfs_tree_is_busy() - try to shrink dentries of a checkpoint
  * @root_dentry: root dentry of the tree to be shrunk
  *
  * This function returns true if the tree was in-use.
  */
-static int nilfs_try_to_shrink_tree(struct dentry *root_dentry)
+static bool nilfs_tree_is_busy(struct dentry *root_dentry)
 {
-	if (have_submounts(root_dentry))
-		return true;
 	shrink_dcache_parent(root_dentry);
-	return nilfs_tree_was_touched(root_dentry);
+	return d_count(root_dentry) > 1;
 }
 
 int nilfs_checkpoint_is_mounted(struct super_block *sb, __u64 cno)
@@ -1034,8 +1027,7 @@ int nilfs_checkpoint_is_mounted(struct super_block *sb, __u64 cno)
 		if (inode) {
 			dentry = d_find_alias(inode);
 			if (dentry) {
-				if (nilfs_tree_was_touched(dentry))
+				ret = nilfs_tree_is_busy(dentry);
-					ret = nilfs_try_to_shrink_tree(dentry);
 				dput(dentry);
 			}
 			iput(inode);
@@ -1331,11 +1323,8 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
 
 		s->s_flags |= MS_ACTIVE;
 	} else if (!sd.cno) {
-		int busy = false;
+		if (nilfs_tree_is_busy(s->s_root)) {
-
+			if ((flags ^ s->s_flags) & MS_RDONLY) {
-		if (nilfs_tree_was_touched(s->s_root)) {
-			busy = nilfs_try_to_shrink_tree(s->s_root);
-			if (busy && (flags ^ s->s_flags) & MS_RDONLY) {
 				printk(KERN_ERR "NILFS: the device already "
 				       "has a %s mount.\n",
 				       (s->s_flags & MS_RDONLY) ?
@@ -1343,8 +1332,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
 				err = -EBUSY;
 				goto failed_super;
 			}
-		}
+		} else {
-		if (!busy) {
 			/*
 			 * Try remount to setup mount states if the current
 			 * tree is not mounted and only snapshots use this sb.

fs/ocfs2/aops.c

@@ -565,9 +565,7 @@ bail:
 static void ocfs2_dio_end_io(struct kiocb *iocb,
 			     loff_t offset,
 			     ssize_t bytes,
-			     void *private,
+			     void *private)
-			     int ret,
-			     bool is_async)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
 	int level;
@@ -592,10 +590,6 @@ static void ocfs2_dio_end_io(struct kiocb *iocb,
 
 	level = ocfs2_iocb_rw_locked_level(iocb);
 	ocfs2_rw_unlock(inode, level);
-
-	inode_dio_done(inode);
-	if (is_async)
-		aio_complete(iocb, ret, 0);
 }
 
 /*

fs/open.c

@@ -485,14 +485,13 @@ out_unlock:
 
 SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode)
 {
-	struct file * file;
+	struct fd f = fdget(fd);
 	int err = -EBADF;
 
-	file = fget(fd);
+	if (f.file) {
-	if (file) {
+		audit_inode(NULL, f.file->f_path.dentry, 0);
-		audit_inode(NULL, file->f_path.dentry, 0);
+		err = chmod_common(&f.file->f_path, mode);
-		err = chmod_common(&file->f_path, mode);
+		fdput(f);
-		fput(file);
 	}
 	return err;
 }

fs/super.c

@@ -152,15 +152,9 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 	static const struct super_operations default_op;
 
 	if (s) {
-		if (security_sb_alloc(s)) {
+		if (security_sb_alloc(s))
-			/*
+			goto out_free_sb;
-			 * We cannot call security_sb_free() without
+
-			 * security_sb_alloc() succeeding. So bail out manually
-			 */
-			kfree(s);
-			s = NULL;
-			goto out;
-		}
 #ifdef CONFIG_SMP
 		s->s_files = alloc_percpu(struct list_head);
 		if (!s->s_files)
@@ -228,6 +222,7 @@ err_out:
 		free_percpu(s->s_files);
 #endif
 	destroy_sb_writers(s);
+out_free_sb:
 	kfree(s);
 	s = NULL;
 	goto out;
@@ -414,6 +409,11 @@ void generic_shutdown_super(struct super_block *sb)
 
 		evict_inodes(sb);
 
+		if (sb->s_dio_done_wq) {
+			destroy_workqueue(sb->s_dio_done_wq);
+			sb->s_dio_done_wq = NULL;
+		}
+
 		if (sop->put_super)
 			sop->put_super(sb);
 

fs/xfs/xfs_aops.c

@@ -86,14 +86,6 @@ xfs_destroy_ioend(
 		bh->b_end_io(bh, !ioend->io_error);
 	}
 
-	if (ioend->io_iocb) {
-		inode_dio_done(ioend->io_inode);
-		if (ioend->io_isasync) {
-			aio_complete(ioend->io_iocb, ioend->io_error ?
-					ioend->io_error : ioend->io_result, 0);
-		}
-	}
-
 	mempool_free(ioend, xfs_ioend_pool);
 }
 
@@ -281,7 +273,6 @@ xfs_alloc_ioend(
 	 * all the I/O from calling the completion routine too early.
 	 */
 	atomic_set(&ioend->io_remaining, 1);
-	ioend->io_isasync = 0;
 	ioend->io_isdirect = 0;
 	ioend->io_error = 0;
 	ioend->io_list = NULL;
@@ -291,8 +282,6 @@ xfs_alloc_ioend(
 	ioend->io_buffer_tail = NULL;
 	ioend->io_offset = 0;
 	ioend->io_size = 0;
-	ioend->io_iocb = NULL;
-	ioend->io_result = 0;
 	ioend->io_append_trans = NULL;
 
 	INIT_WORK(&ioend->io_work, xfs_end_io);
@@ -1292,8 +1281,10 @@ __xfs_get_blocks(
 		if (create || !ISUNWRITTEN(&imap))
 			xfs_map_buffer(inode, bh_result, &imap, offset);
 		if (create && ISUNWRITTEN(&imap)) {
-			if (direct)
+			if (direct) {
 				bh_result->b_private = inode;
+				set_buffer_defer_completion(bh_result);
+			}
 			set_buffer_unwritten(bh_result);
 		}
 	}
@@ -1390,9 +1381,7 @@ xfs_end_io_direct_write(
 	struct kiocb		*iocb,
 	loff_t			offset,
 	ssize_t			size,
-	void			*private,
+	void			*private)
-	int			ret,
-	bool			is_async)
 {
 	struct xfs_ioend	*ioend = iocb->private;
 
@@ -1414,17 +1403,10 @@ xfs_end_io_direct_write(
 
 	ioend->io_offset = offset;
 	ioend->io_size = size;
-	ioend->io_iocb = iocb;
-	ioend->io_result = ret;
 	if (private && size > 0)
 		ioend->io_type = XFS_IO_UNWRITTEN;
 
-	if (is_async) {
+	xfs_finish_ioend_sync(ioend);
-		ioend->io_isasync = 1;
-		xfs_finish_ioend(ioend);
-	} else {
-		xfs_finish_ioend_sync(ioend);
-	}
 }
 
 STATIC ssize_t

fs/xfs/xfs_aops.h

@@ -45,7 +45,6 @@ typedef struct xfs_ioend {
 	unsigned int		io_type;	/* delalloc / unwritten */
 	int			io_error;	/* I/O error code */
 	atomic_t		io_remaining;	/* hold count */
-	unsigned int		io_isasync : 1;	/* needs aio_complete */
 	unsigned int		io_isdirect : 1;/* direct I/O */
 	struct inode		*io_inode;	/* file being written to */
 	struct buffer_head	*io_buffer_head;/* buffer linked list head */
@@ -54,8 +53,6 @@ typedef struct xfs_ioend {
 	xfs_off_t		io_offset;	/* offset in the file */
 	struct work_struct	io_work;	/* xfsdatad work queue */
 	struct xfs_trans	*io_append_trans;/* xact. for size update */
-	struct kiocb		*io_iocb;
-	int			io_result;
 } xfs_ioend_t;
 
 extern const struct address_space_operations xfs_address_space_operations;

include/linux/buffer_head.h

@@ -36,6 +36,7 @@ enum bh_state_bits {
 	BH_Quiet,	/* Buffer Error Prinks to be quiet */
 	BH_Meta,	/* Buffer contains metadata */
 	BH_Prio,	/* Buffer should be submitted with REQ_PRIO */
+	BH_Defer_Completion, /* Defer AIO completion to workqueue */
 
 	BH_PrivateStart,/* not a state bit, but the first bit available
 			 * for private allocation by other entities
@@ -128,6 +129,7 @@ BUFFER_FNS(Write_EIO, write_io_error)
 BUFFER_FNS(Unwritten, unwritten)
 BUFFER_FNS(Meta, meta)
 BUFFER_FNS(Prio, prio)
+BUFFER_FNS(Defer_Completion, defer_completion)
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
 

include/linux/fs.h

@@ -46,6 +46,7 @@ struct vfsmount;
 struct cred;
 struct swap_info_struct;
 struct seq_file;
+struct workqueue_struct;
 
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);
@@ -63,8 +64,7 @@ struct buffer_head;
 typedef int (get_block_t)(struct inode *inode, sector_t iblock,
 			struct buffer_head *bh_result, int create);
 typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
-			ssize_t bytes, void *private, int ret,
+			ssize_t bytes, void *private);
-			bool is_async);
 
 #define MAY_EXEC		0x00000001
 #define MAY_WRITE		0x00000002
@@ -1328,6 +1328,9 @@ struct super_block {
 
 	/* Being remounted read-only */
 	int s_readonly_remount;
+
+	/* AIO completions deferred from interrupt context */
+	struct workqueue_struct *s_dio_done_wq;
 };
 
 /* superblock cache pruning functions */
@@ -1804,7 +1807,7 @@ enum file_time_flags {
 	S_VERSION = 8,
 };
 
-extern void touch_atime(struct path *);
+extern void touch_atime(const struct path *);
 static inline void file_accessed(struct file *file)
 {
 	if (!(file->f_flags & O_NOATIME))

include/linux/namei.h

@@ -58,6 +58,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
 
 extern int user_path_at(int, const char __user *, unsigned, struct path *);
 extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty);
+extern int user_path_umountat(int, const char __user *, unsigned int, struct path *);
 
 #define user_path(name, path) user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW, path)
 #define user_lpath(name, path) user_path_at(AT_FDCWD, name, 0, path)

include/linux/oprofile.h

@@ -42,7 +42,6 @@
 #define IBS_FETCH_CODE			13
 #define IBS_OP_CODE			14
 
-struct super_block;
 struct dentry;
 struct file_operations;
 struct pt_regs;
@@ -51,7 +50,7 @@ struct pt_regs;
 struct oprofile_operations {
 	/* create any necessary configuration files in the oprofile fs.
 	 * Optional. */
-	int (*create_files)(struct super_block * sb, struct dentry * root);
+	int (*create_files)(struct dentry * root);
 	/* Do any necessary interrupt setup. Optional. */
 	int (*setup)(void);
 	/* Do any necessary interrupt shutdown. Optional. */
@@ -125,27 +124,26 @@ void oprofile_add_trace(unsigned long eip);
  * Create a file of the given name as a child of the given root, with
  * the specified file operations.
  */
-int oprofilefs_create_file(struct super_block * sb, struct dentry * root,
+int oprofilefs_create_file(struct dentry * root,
 	char const * name, const struct file_operations * fops);
 
-int oprofilefs_create_file_perm(struct super_block * sb, struct dentry * root,
+int oprofilefs_create_file_perm(struct dentry * root,
 	char const * name, const struct file_operations * fops, int perm);
  
 /** Create a file for read/write access to an unsigned long. */
-int oprofilefs_create_ulong(struct super_block * sb, struct dentry * root,
+int oprofilefs_create_ulong(struct dentry * root,
 	char const * name, ulong * val);
  
 /** Create a file for read-only access to an unsigned long. */
-int oprofilefs_create_ro_ulong(struct super_block * sb, struct dentry * root,
+int oprofilefs_create_ro_ulong(struct dentry * root,
 	char const * name, ulong * val);
  
 /** Create a file for read-only access to an atomic_t. */
-int oprofilefs_create_ro_atomic(struct super_block * sb, struct dentry * root,
+int oprofilefs_create_ro_atomic(struct dentry * root,
 	char const * name, atomic_t * val);
  
 /** create a directory */
-struct dentry * oprofilefs_mkdir(struct super_block * sb, struct dentry * root,
+struct dentry *oprofilefs_mkdir(struct dentry *parent, char const *name);
-	char const * name);
 
 /**
  * Write the given asciz string to the given user buffer @buf, updating *offset

kernel/module.c

@@ -2549,21 +2549,20 @@ static int copy_module_from_user(const void __user *umod, unsigned long len,
 /* Sets info->hdr and info->len. */
 static int copy_module_from_fd(int fd, struct load_info *info)
 {
-	struct file *file;
+	struct fd f = fdget(fd);
 	int err;
 	struct kstat stat;
 	loff_t pos;
 	ssize_t bytes = 0;
 
-	file = fget(fd);
+	if (!f.file)
-	if (!file)
 		return -ENOEXEC;
 
-	err = security_kernel_module_from_file(file);
+	err = security_kernel_module_from_file(f.file);
 	if (err)
 		goto out;
 
-	err = vfs_getattr(&file->f_path, &stat);
+	err = vfs_getattr(&f.file->f_path, &stat);
 	if (err)
 		goto out;
 
@@ -2586,7 +2585,7 @@ static int copy_module_from_fd(int fd, struct load_info *info)
 
 	pos = 0;
 	while (pos < stat.size) {
-		bytes = kernel_read(file, pos, (char *)(info->hdr) + pos,
+		bytes = kernel_read(f.file, pos, (char *)(info->hdr) + pos,
 				    stat.size - pos);
 		if (bytes < 0) {
 			vfree(info->hdr);
@@ -2600,7 +2599,7 @@ static int copy_module_from_fd(int fd, struct load_info *info)
 	info->len = pos;
 
 out:
-	fput(file);
+	fdput(f);
 	return err;
 }
 

lib/vsprintf.c

@@ -26,6 +26,7 @@
 #include <linux/math64.h>
 #include <linux/uaccess.h>
 #include <linux/ioport.h>
+#include <linux/dcache.h>
 #include <net/addrconf.h>
 
 #include <asm/page.h>		/* for PAGE_SIZE */
@@ -532,6 +533,81 @@ char *string(char *buf, char *end, const char *s, struct printf_spec spec)
 	return buf;
 }
 
+static void widen(char *buf, char *end, unsigned len, unsigned spaces)
+{
+	size_t size;
+	if (buf >= end)	/* nowhere to put anything */
+		return;
+	size = end - buf;
+	if (size <= spaces) {
+		memset(buf, ' ', size);
+		return;
+	}
+	if (len) {
+		if (len > size - spaces)
+			len = size - spaces;
+		memmove(buf + spaces, buf, len);
+	}
+	memset(buf, ' ', spaces);
+}
+
+static noinline_for_stack
+char *dentry_name(char *buf, char *end, const struct dentry *d, struct printf_spec spec,
+		  const char *fmt)
+{
+	const char *array[4], *s;
+	const struct dentry *p;
+	int depth;
+	int i, n;
+
+	switch (fmt[1]) {
+		case '2': case '3': case '4':
+			depth = fmt[1] - '0';
+			break;
+		default:
+			depth = 1;
+	}
+
+	rcu_read_lock();
+	for (i = 0; i < depth; i++, d = p) {
+		p = ACCESS_ONCE(d->d_parent);
+		array[i] = ACCESS_ONCE(d->d_name.name);
+		if (p == d) {
+			if (i)
+				array[i] = "";
+			i++;
+			break;
+		}
+	}
+	s = array[--i];
+	for (n = 0; n != spec.precision; n++, buf++) {
+		char c = *s++;
+		if (!c) {
+			if (!i)
+				break;
+			c = '/';
+			s = array[--i];
+		}
+		if (buf < end)
+			*buf = c;
+	}
+	rcu_read_unlock();
+	if (n < spec.field_width) {
+		/* we want to pad the sucker */
+		unsigned spaces = spec.field_width - n;
+		if (!(spec.flags & LEFT)) {
+			widen(buf - n, end, n, spaces);
+			return buf + spaces;
+		}
+		while (spaces--) {
+			if (buf < end)
+				*buf = ' ';
+			++buf;
+		}
+	}
+	return buf;
+}
+
 static noinline_for_stack
 char *symbol_string(char *buf, char *end, void *ptr,
 		    struct printf_spec spec, const char *fmt)
@@ -1253,6 +1329,12 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 		spec.base = 16;
 		return number(buf, end,
 			      (unsigned long long) *((phys_addr_t *)ptr), spec);
+	case 'd':
+		return dentry_name(buf, end, ptr, spec, fmt);
+	case 'D':
+		return dentry_name(buf, end,
+				   ((const struct file *)ptr)->f_path.dentry,
+				   spec, fmt);
 	}
 	spec.flags |= SMALL;
 	if (spec.field_width == -1) {

mm/filemap.c

@@ -2550,7 +2550,7 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
 	mutex_unlock(&inode->i_mutex);
 
-	if (ret > 0 || ret == -EIOCBQUEUED) {
+	if (ret > 0) {
 		ssize_t err;
 
 		err = generic_write_sync(file, pos, ret);

mm/shmem.c

@@ -2615,13 +2615,15 @@ int shmem_fill_super(struct super_block *sb, void *data, int silent)
 	 * tmpfs instance, limiting inodes to one per page of lowmem;
 	 * but the internal instance is left unlimited.
 	 */
-	if (!(sb->s_flags & MS_NOUSER)) {
+	if (!(sb->s_flags & MS_KERNMOUNT)) {
 		sbinfo->max_blocks = shmem_default_max_blocks();
 		sbinfo->max_inodes = shmem_default_max_inodes();
 		if (shmem_parse_options(data, sbinfo, false)) {
 			err = -EINVAL;
 			goto failed;
 		}
+	} else {
+		sb->s_flags |= MS_NOUSER;
 	}
 	sb->s_export_op = &shmem_export_ops;
 	sb->s_flags |= MS_NOSEC;
@@ -2831,8 +2833,7 @@ int __init shmem_init(void)
 		goto out2;
 	}
 
-	shm_mnt = vfs_kern_mount(&shmem_fs_type, MS_NOUSER,
+	shm_mnt = kern_mount(&shmem_fs_type);
-				 shmem_fs_type.name, NULL);
 	if (IS_ERR(shm_mnt)) {
 		error = PTR_ERR(shm_mnt);
 		printk(KERN_ERR "Could not kern_mount tmpfs\n");

virt/kvm/eventfd.c

@@ -291,7 +291,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 {
 	struct kvm_irq_routing_table *irq_rt;
 	struct _irqfd *irqfd, *tmp;
-	struct file *file = NULL;
+	struct fd f;
 	struct eventfd_ctx *eventfd = NULL, *resamplefd = NULL;
 	int ret;
 	unsigned int events;
@@ -306,13 +306,13 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 	INIT_WORK(&irqfd->inject, irqfd_inject);
 	INIT_WORK(&irqfd->shutdown, irqfd_shutdown);
 
-	file = eventfd_fget(args->fd);
+	f = fdget(args->fd);
-	if (IS_ERR(file)) {
+	if (!f.file) {
-		ret = PTR_ERR(file);
+		ret = -EBADF;
-		goto fail;
+		goto out;
 	}
 
-	eventfd = eventfd_ctx_fileget(file);
+	eventfd = eventfd_ctx_fileget(f.file);
 	if (IS_ERR(eventfd)) {
 		ret = PTR_ERR(eventfd);
 		goto fail;
@@ -391,7 +391,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 					   lockdep_is_held(&kvm->irqfds.lock));
 	irqfd_update(kvm, irqfd, irq_rt);
 
-	events = file->f_op->poll(file, &irqfd->pt);
+	events = f.file->f_op->poll(f.file, &irqfd->pt);
 
 	list_add_tail(&irqfd->list, &kvm->irqfds.items);
 
@@ -408,7 +408,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 	 * do not drop the file until the irqfd is fully initialized, otherwise
 	 * we might race against the POLLHUP
 	 */
-	fput(file);
+	fdput(f);
 
 	return 0;
 
@@ -422,9 +422,9 @@ fail:
 	if (eventfd && !IS_ERR(eventfd))
 		eventfd_ctx_put(eventfd);
 
-	if (!IS_ERR(file))
+	fdput(f);
-		fput(file);
 
+out:
 	kfree(irqfd);
 	return ret;
 }