Merge branches 'work.mount', 'work.misc' and 'work.iov_iter' into for-next

.clang-format

@@ -259,7 +259,6 @@ ForEachMacros:
   - 'idr_for_each_entry_ul'
   - 'inet_bind_bucket_for_each'
   - 'inet_lhash2_for_each_icsk_rcu'
-  - 'iov_for_each'
   - 'key_for_each'
   - 'key_for_each_safe'
   - 'klp_for_each_func'

arch/x86/kernel/cpu/resctrl/internal.h

@@ -4,6 +4,7 @@
 
 #include <linux/sched.h>
 #include <linux/kernfs.h>
+#include <linux/fs_context.h>
 #include <linux/jump_label.h>
 
 #define MSR_IA32_L3_QOS_CFG		0xc81
@@ -40,6 +41,21 @@
 #define RMID_VAL_ERROR			BIT_ULL(63)
 #define RMID_VAL_UNAVAIL		BIT_ULL(62)
 
+
+struct rdt_fs_context {
+	struct kernfs_fs_context	kfc;
+	bool				enable_cdpl2;
+	bool				enable_cdpl3;
+	bool				enable_mba_mbps;
+};
+
+static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc)
+{
+	struct kernfs_fs_context *kfc = fc->fs_private;
+
+	return container_of(kfc, struct rdt_fs_context, kfc);
+}
+
 DECLARE_STATIC_KEY_FALSE(rdt_enable_key);
 
 /**

arch/x86/kernel/cpu/resctrl/rdtgroup.c

@@ -24,6 +24,7 @@
 #include <linux/cpu.h>
 #include <linux/debugfs.h>
 #include <linux/fs.h>
+#include <linux/fs_parser.h>
 #include <linux/sysfs.h>
 #include <linux/kernfs.h>
 #include <linux/seq_buf.h>
@@ -32,6 +33,7 @@
 #include <linux/sched/task.h>
 #include <linux/slab.h>
 #include <linux/task_work.h>
+#include <linux/user_namespace.h>
 
 #include <uapi/linux/magic.h>
 
@@ -1858,46 +1860,6 @@ static void cdp_disable_all(void)
 		cdpl2_disable();
 }
 
-static int parse_rdtgroupfs_options(char *data)
-{
-	char *token, *o = data;
-	int ret = 0;
-
-	while ((token = strsep(&o, ",")) != NULL) {
-		if (!*token) {
-			ret = -EINVAL;
-			goto out;
-		}
-
-		if (!strcmp(token, "cdp")) {
-			ret = cdpl3_enable();
-			if (ret)
-				goto out;
-		} else if (!strcmp(token, "cdpl2")) {
-			ret = cdpl2_enable();
-			if (ret)
-				goto out;
-		} else if (!strcmp(token, "mba_MBps")) {
-			if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
-				ret = set_mba_sc(true);
-			else
-				ret = -EINVAL;
-			if (ret)
-				goto out;
-		} else {
-			ret = -EINVAL;
-			goto out;
-		}
-	}
-
-	return 0;
-
-out:
-	pr_err("Invalid mount option \"%s\"\n", token);
-
-	return ret;
-}
-
 /*
  * We don't allow rdtgroup directories to be created anywhere
  * except the root directory. Thus when looking for the rdtgroup
@@ -1969,13 +1931,27 @@ static int mkdir_mondata_all(struct kernfs_node *parent_kn,
 			     struct rdtgroup *prgrp,
 			     struct kernfs_node **mon_data_kn);
 
-static struct dentry *rdt_mount(struct file_system_type *fs_type,
-				int flags, const char *unused_dev_name,
-				void *data)
+static int rdt_enable_ctx(struct rdt_fs_context *ctx)
 {
+	int ret = 0;
+
+	if (ctx->enable_cdpl2)
+		ret = cdpl2_enable();
+
+	if (!ret && ctx->enable_cdpl3)
+		ret = cdpl3_enable();
+
+	if (!ret && ctx->enable_mba_mbps)
+		ret = set_mba_sc(true);
+
+	return ret;
+}
+
+static int rdt_get_tree(struct fs_context *fc)
+{
+	struct rdt_fs_context *ctx = rdt_fc2context(fc);
 	struct rdt_domain *dom;
 	struct rdt_resource *r;
-	struct dentry *dentry;
 	int ret;
 
 	cpus_read_lock();
@@ -1984,53 +1960,42 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type,
 	 * resctrl file system can only be mounted once.
 	 */
 	if (static_branch_unlikely(&rdt_enable_key)) {
-		dentry = ERR_PTR(-EBUSY);
+		ret = -EBUSY;
 		goto out;
 	}
 
-	ret = parse_rdtgroupfs_options(data);
-	if (ret) {
-		dentry = ERR_PTR(ret);
+	ret = rdt_enable_ctx(ctx);
+	if (ret < 0)
 		goto out_cdp;
-	}
 
 	closid_init();
 
 	ret = rdtgroup_create_info_dir(rdtgroup_default.kn);
-	if (ret) {
-		dentry = ERR_PTR(ret);
-		goto out_cdp;
-	}
+	if (ret < 0)
+		goto out_mba;
 
 	if (rdt_mon_capable) {
 		ret = mongroup_create_dir(rdtgroup_default.kn,
 					  NULL, "mon_groups",
 					  &kn_mongrp);
-		if (ret) {
-			dentry = ERR_PTR(ret);
+		if (ret < 0)
 			goto out_info;
-		}
 		kernfs_get(kn_mongrp);
 
 		ret = mkdir_mondata_all(rdtgroup_default.kn,
 					&rdtgroup_default, &kn_mondata);
-		if (ret) {
-			dentry = ERR_PTR(ret);
+		if (ret < 0)
 			goto out_mongrp;
-		}
 		kernfs_get(kn_mondata);
 		rdtgroup_default.mon.mon_data_kn = kn_mondata;
 	}
 
 	ret = rdt_pseudo_lock_init();
-	if (ret) {
-		dentry = ERR_PTR(ret);
+	if (ret)
 		goto out_mondata;
-	}
 
-	dentry = kernfs_mount(fs_type, flags, rdt_root,
-			      RDTGROUP_SUPER_MAGIC, NULL);
-	if (IS_ERR(dentry))
+	ret = kernfs_get_tree(fc);
+	if (ret < 0)
 		goto out_psl;
 
 	if (rdt_alloc_capable)
@@ -2059,14 +2024,95 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type,
 		kernfs_remove(kn_mongrp);
 out_info:
 	kernfs_remove(kn_info);
+out_mba:
+	if (ctx->enable_mba_mbps)
+		set_mba_sc(false);
 out_cdp:
 	cdp_disable_all();
 out:
 	rdt_last_cmd_clear();
 	mutex_unlock(&rdtgroup_mutex);
 	cpus_read_unlock();
+	return ret;
+}
+
+enum rdt_param {
+	Opt_cdp,
+	Opt_cdpl2,
+	Opt_mba_mpbs,
+	nr__rdt_params
+};
+
+static const struct fs_parameter_spec rdt_param_specs[] = {
+	fsparam_flag("cdp",		Opt_cdp),
+	fsparam_flag("cdpl2",		Opt_cdpl2),
+	fsparam_flag("mba_mpbs",	Opt_mba_mpbs),
+	{}
+};
+
+static const struct fs_parameter_description rdt_fs_parameters = {
+	.name		= "rdt",
+	.specs		= rdt_param_specs,
+};
 
-	return dentry;
+static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct rdt_fs_context *ctx = rdt_fc2context(fc);
+	struct fs_parse_result result;
+	int opt;
+
+	opt = fs_parse(fc, &rdt_fs_parameters, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_cdp:
+		ctx->enable_cdpl3 = true;
+		return 0;
+	case Opt_cdpl2:
+		ctx->enable_cdpl2 = true;
+		return 0;
+	case Opt_mba_mpbs:
+		if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+			return -EINVAL;
+		ctx->enable_mba_mbps = true;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static void rdt_fs_context_free(struct fs_context *fc)
+{
+	struct rdt_fs_context *ctx = rdt_fc2context(fc);
+
+	kernfs_free_fs_context(fc);
+	kfree(ctx);
+}
+
+static const struct fs_context_operations rdt_fs_context_ops = {
+	.free		= rdt_fs_context_free,
+	.parse_param	= rdt_parse_param,
+	.get_tree	= rdt_get_tree,
+};
+
+static int rdt_init_fs_context(struct fs_context *fc)
+{
+	struct rdt_fs_context *ctx;
+
+	ctx = kzalloc(sizeof(struct rdt_fs_context), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->kfc.root = rdt_root;
+	ctx->kfc.magic = RDTGROUP_SUPER_MAGIC;
+	fc->fs_private = &ctx->kfc;
+	fc->ops = &rdt_fs_context_ops;
+	if (fc->user_ns)
+		put_user_ns(fc->user_ns);
+	fc->user_ns = get_user_ns(&init_user_ns);
+	fc->global = true;
+	return 0;
 }
 
 static int reset_all_ctrls(struct rdt_resource *r)
@@ -2240,7 +2286,8 @@ static void rdt_kill_sb(struct super_block *sb)
 
 static struct file_system_type rdt_fs_type = {
 	.name			= "resctrl",
-	.mount   = rdt_mount,
+	.init_fs_context	= rdt_init_fs_context,
+	.parameters		= &rdt_fs_parameters,
 	.kill_sb		= rdt_kill_sb,
 };
 

fs/Kconfig

@@ -8,6 +8,13 @@ menu "File systems"
 config DCACHE_WORD_ACCESS
        bool
 
+config VALIDATE_FS_PARSER
+	bool "Validate filesystem parameter description"
+	default y
+	help
+	  Enable this to perform validation of the parameter description for a
+	  filesystem when it is registered.
+
 if BLOCK
 
 config FS_IOMAP

fs/Makefile

@@ -12,7 +12,8 @@ obj-y :=	open.o read_write.o file_table.o super.o \
 		attr.o bad_inode.o file.o filesystems.o namespace.o \
 		seq_file.o xattr.o libfs.o fs-writeback.o \
 		pnode.o splice.o sync.o utimes.o d_path.o \
-		stack.o fs_struct.o statfs.o fs_pin.o nsfs.o
+		stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \
+		fs_context.o fs_parser.o
 
 ifeq ($(CONFIG_BLOCK),y)
 obj-y +=	buffer.o block_dev.o direct-io.o mpage.o

fs/afs/internal.h

@@ -36,15 +36,14 @@
 struct pagevec;
 struct afs_call;
 
-struct afs_mount_params {
-	bool			rwpath;		/* T if the parent should be considered R/W */
+struct afs_fs_context {
 	bool			force;		/* T to force cell type */
 	bool			autocell;	/* T if set auto mount operation */
 	bool			dyn_root;	/* T if dynamic root */
+	bool			no_cell;	/* T if the source is "none" (for dynroot) */
 	afs_voltype_t		type;		/* type of volume requested */
-	int			volnamesz;	/* size of volume name */
+	unsigned int		volnamesz;	/* size of volume name */
 	const char		*volname;	/* name of volume to mount */
-	struct net		*net_ns;	/* Network namespace in effect */
 	struct afs_net		*net;		/* the AFS net namespace stuff */
 	struct afs_cell		*cell;		/* cell in which to find volume */
 	struct afs_volume	*volume;	/* volume record */
@@ -1274,7 +1273,7 @@ static inline struct afs_volume *__afs_get_volume(struct afs_volume *volume)
 	return volume;
 }
 
-extern struct afs_volume *afs_create_volume(struct afs_mount_params *);
+extern struct afs_volume *afs_create_volume(struct afs_fs_context *);
 extern void afs_activate_volume(struct afs_volume *);
 extern void afs_deactivate_volume(struct afs_volume *);
 extern void afs_put_volume(struct afs_cell *, struct afs_volume *);

fs/afs/mntpt.c

@@ -17,6 +17,7 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/gfp.h>
+#include <linux/fs_context.h>
 #include "internal.h"
 
 
@@ -47,6 +48,8 @@ static DECLARE_DELAYED_WORK(afs_mntpt_expiry_timer, afs_mntpt_expiry_timed_out);
 
 static unsigned long afs_mntpt_expiry_timeout = 10 * 60;
 
+static const char afs_root_volume[] = "root.cell";
+
 /*
  * no valid lookup procedure on this sort of dir
  */
@@ -68,108 +71,112 @@ static int afs_mntpt_open(struct inode *inode, struct file *file)
 }
 
 /*
- * create a vfsmount to be automounted
+ * Set the parameters for the proposed superblock.
  */
-static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
+static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt)
 {
-	struct afs_super_info *as;
-	struct vfsmount *mnt;
-	struct afs_vnode *vnode;
-	struct page *page;
-	char *devname, *options;
-	bool rwpath = false;
+	struct afs_fs_context *ctx = fc->fs_private;
+	struct afs_super_info *src_as = AFS_FS_S(mntpt->d_sb);
+	struct afs_vnode *vnode = AFS_FS_I(d_inode(mntpt));
+	struct afs_cell *cell;
+	const char *p;
 	int ret;
 
-	_enter("{%pd}", mntpt);
-
-	BUG_ON(!d_inode(mntpt));
-
-	ret = -ENOMEM;
-	devname = (char *) get_zeroed_page(GFP_KERNEL);
-	if (!devname)
-		goto error_no_devname;
-
-	options = (char *) get_zeroed_page(GFP_KERNEL);
-	if (!options)
-		goto error_no_options;
+	if (fc->net_ns != src_as->net_ns) {
+		put_net(fc->net_ns);
+		fc->net_ns = get_net(src_as->net_ns);
+	}
 
-	vnode = AFS_FS_I(d_inode(mntpt));
+	if (src_as->volume && src_as->volume->type == AFSVL_RWVOL) {
+		ctx->type = AFSVL_RWVOL;
+		ctx->force = true;
+	}
+	if (ctx->cell) {
+		afs_put_cell(ctx->net, ctx->cell);
+		ctx->cell = NULL;
+	}
 	if (test_bit(AFS_VNODE_PSEUDODIR, &vnode->flags)) {
 		/* if the directory is a pseudo directory, use the d_name */
-		static const char afs_root_cell[] = ":root.cell.";
 		unsigned size = mntpt->d_name.len;
 
-		ret = -ENOENT;
-		if (size < 2 || size > AFS_MAXCELLNAME)
-			goto error_no_page;
+		if (size < 2)
+			return -ENOENT;
 
+		p = mntpt->d_name.name;
 		if (mntpt->d_name.name[0] == '.') {
-			devname[0] = '%';
-			memcpy(devname + 1, mntpt->d_name.name + 1, size - 1);
-			memcpy(devname + size, afs_root_cell,
-			       sizeof(afs_root_cell));
-			rwpath = true;
-		} else {
-			devname[0] = '#';
-			memcpy(devname + 1, mntpt->d_name.name, size);
-			memcpy(devname + size + 1, afs_root_cell,
-			       sizeof(afs_root_cell));
+			size--;
+			p++;
+			ctx->type = AFSVL_RWVOL;
+			ctx->force = true;
 		}
+		if (size > AFS_MAXCELLNAME)
+			return -ENAMETOOLONG;
+
+		cell = afs_lookup_cell(ctx->net, p, size, NULL, false);
+		if (IS_ERR(cell)) {
+			pr_err("kAFS: unable to lookup cell '%pd'\n", mntpt);
+			return PTR_ERR(cell);
+		}
+		ctx->cell = cell;
+
+		ctx->volname = afs_root_volume;
+		ctx->volnamesz = sizeof(afs_root_volume) - 1;
 	} else {
 		/* read the contents of the AFS special symlink */
+		struct page *page;
 		loff_t size = i_size_read(d_inode(mntpt));
 		char *buf;
 
-		ret = -EINVAL;
+		if (src_as->cell)
+			ctx->cell = afs_get_cell(src_as->cell);
+
 		if (size > PAGE_SIZE - 1)
-			goto error_no_page;
+			return -EINVAL;
 
 		page = read_mapping_page(d_inode(mntpt)->i_mapping, 0, NULL);
-		if (IS_ERR(page)) {
-			ret = PTR_ERR(page);
-			goto error_no_page;
-		}
+		if (IS_ERR(page))
+			return PTR_ERR(page);
 
 		if (PageError(page)) {
 			ret = afs_bad(AFS_FS_I(d_inode(mntpt)), afs_file_error_mntpt);
-			goto error;
+			put_page(page);
+			return ret;
 		}
 
-		buf = kmap_atomic(page);
-		memcpy(devname, buf, size);
-		kunmap_atomic(buf);
+		buf = kmap(page);
+		ret = vfs_parse_fs_string(fc, "source", buf, size);
+		kunmap(page);
 		put_page(page);
-		page = NULL;
+		if (ret < 0)
+			return ret;
 	}
 
-	/* work out what options we want */
-	as = AFS_FS_S(mntpt->d_sb);
-	if (as->cell) {
-		memcpy(options, "cell=", 5);
-		strcpy(options + 5, as->cell->name);
-		if ((as->volume && as->volume->type == AFSVL_RWVOL) || rwpath)
-			strcat(options, ",rwpath");
-	}
+	return 0;
+}
 
-	/* try and do the mount */
-	_debug("--- attempting mount %s -o %s ---", devname, options);
-	mnt = vfs_submount(mntpt, &afs_fs_type, devname, options);
-	_debug("--- mount result %p ---", mnt);
+/*
+ * create a vfsmount to be automounted
+ */
+static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
+{
+	struct fs_context *fc;
+	struct vfsmount *mnt;
+	int ret;
 
-	free_page((unsigned long) devname);
-	free_page((unsigned long) options);
-	_leave(" = %p", mnt);
-	return mnt;
+	BUG_ON(!d_inode(mntpt));
 
-error:
-	put_page(page);
-error_no_page:
-	free_page((unsigned long) options);
-error_no_options:
-	free_page((unsigned long) devname);
-error_no_devname:
-	_leave(" = %d", ret);
-	return ERR_PTR(ret);
+	fc = fs_context_for_submount(&afs_fs_type, mntpt);
+	if (IS_ERR(fc))
+		return ERR_CAST(fc);
+
+	ret = afs_mntpt_set_params(fc, mntpt);
+	if (!ret)
+		mnt = fc_mount(fc);
+	else
+		mnt = ERR_PTR(ret);
+
+	put_fs_context(fc);
+	return mnt;
 }
 
 /*

fs/afs/volume.c

@@ -21,7 +21,7 @@ static const char *const afs_voltypes[] = { "R/W", "R/O", "BAK" };
 /*
  * Allocate a volume record and load it up from a vldb record.
  */
-static struct afs_volume *afs_alloc_volume(struct afs_mount_params *params,
+static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params,
 					   struct afs_vldb_entry *vldb,
 					   unsigned long type_mask)
 {
@@ -113,7 +113,7 @@ static struct afs_vldb_entry *afs_vl_lookup_vldb(struct afs_cell *cell,
  * - Rule 3: If parent volume is R/W, then only mount R/W volume unless
  *           explicitly told otherwise
  */
-struct afs_volume *afs_create_volume(struct afs_mount_params *params)
+struct afs_volume *afs_create_volume(struct afs_fs_context *params)
 {
 	struct afs_vldb_entry *vldb;
 	struct afs_volume *volume;

fs/devpts/inode.c

@@ -455,6 +455,7 @@ devpts_fill_super(struct super_block *s, void *data, int silent)
 	s->s_blocksize_bits = 10;
 	s->s_magic = DEVPTS_SUPER_MAGIC;
 	s->s_op = &devpts_sops;
+	s->s_d_op = &simple_dentry_operations;
 	s->s_time_gran = 1;
 
 	error = -ENOMEM;

fs/filesystems.c

@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <linux/fs_parser.h>
 
 /*
  * Handling of filesystem drivers list.
@@ -73,6 +74,9 @@ int register_filesystem(struct file_system_type * fs)
 	int res = 0;
 	struct file_system_type ** p;
 
+	if (fs->parameters && !fs_validate_description(fs->parameters))
+		return -EINVAL;
+
 	BUG_ON(strchr(fs->name, '.'));
 	if (fs->next)
 		return -EBUSY;

fs/internal.h

@@ -17,6 +17,7 @@ struct linux_binprm;
 struct path;
 struct mount;
 struct shrink_control;
+struct fs_context;
 
 /*
  * block_dev.c
@@ -51,9 +52,17 @@ int __generic_write_end(struct inode *inode, loff_t pos, unsigned copied,
  */
 extern void __init chrdev_init(void);
 
+/*
+ * fs_context.c
+ */
+extern int parse_monolithic_mount_data(struct fs_context *, void *);
+extern void fc_drop_locked(struct fs_context *);
+
 /*
  * namei.c
  */
+extern int filename_lookup(int dfd, struct filename *name, unsigned flags,
+			   struct path *path, struct path *root);
 extern int user_path_mountpoint_at(int, const char __user *, unsigned int, struct path *);
 extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
 			   const char *, unsigned int, struct path *);
@@ -99,10 +108,8 @@ extern struct file *alloc_empty_file_noaccount(int, const struct cred *);
 /*
  * super.c
  */
-extern int do_remount_sb(struct super_block *, int, void *, int);
+extern int reconfigure_super(struct fs_context *);
 extern bool trylock_super(struct super_block *sb);
-extern struct dentry *mount_fs(struct file_system_type *,
-			       int, const char *, void *);
 extern struct super_block *user_get_super(dev_t);
 
 /*

fs/kernfs/kernfs-internal.h

@@ -17,6 +17,7 @@
 #include <linux/xattr.h>
 
 #include <linux/kernfs.h>
+#include <linux/fs_context.h>
 
 struct kernfs_iattrs {
 	struct iattr		ia_iattr;

fs/kernfs/mount.c

@@ -22,16 +22,6 @@
 
 struct kmem_cache *kernfs_node_cache;
 
-static int kernfs_sop_remount_fs(struct super_block *sb, int *flags, char *data)
-{
-	struct kernfs_root *root = kernfs_info(sb)->root;
-	struct kernfs_syscall_ops *scops = root->syscall_ops;
-
-	if (scops && scops->remount_fs)
-		return scops->remount_fs(root, flags, data);
-	return 0;
-}
-
 static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry)
 {
 	struct kernfs_root *root = kernfs_root(kernfs_dentry_node(dentry));
@@ -60,7 +50,6 @@ const struct super_operations kernfs_sops = {
 	.drop_inode	= generic_delete_inode,
 	.evict_inode	= kernfs_evict_inode,
 
-	.remount_fs	= kernfs_sop_remount_fs,
 	.show_options	= kernfs_sop_show_options,
 	.show_path	= kernfs_sop_show_path,
 };
@@ -222,7 +211,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
 	} while (true);
 }
 
-static int kernfs_fill_super(struct super_block *sb, unsigned long magic)
+static int kernfs_fill_super(struct super_block *sb, struct kernfs_fs_context *kfc)
 {
 	struct kernfs_super_info *info = kernfs_info(sb);
 	struct inode *inode;
@@ -233,7 +222,7 @@ static int kernfs_fill_super(struct super_block *sb, unsigned long magic)
 	sb->s_iflags |= SB_I_NOEXEC | SB_I_NODEV;
 	sb->s_blocksize = PAGE_SIZE;
 	sb->s_blocksize_bits = PAGE_SHIFT;
-	sb->s_magic = magic;
+	sb->s_magic = kfc->magic;
 	sb->s_op = &kernfs_sops;
 	sb->s_xattr = kernfs_xattr_handlers;
 	if (info->root->flags & KERNFS_ROOT_SUPPORT_EXPORTOP)
@@ -263,21 +252,20 @@ static int kernfs_fill_super(struct super_block *sb, unsigned long magic)
 	return 0;
 }
 
-static int kernfs_test_super(struct super_block *sb, void *data)
+static int kernfs_test_super(struct super_block *sb, struct fs_context *fc)
 {
 	struct kernfs_super_info *sb_info = kernfs_info(sb);
-	struct kernfs_super_info *info = data;
+	struct kernfs_super_info *info = fc->s_fs_info;
 
 	return sb_info->root == info->root && sb_info->ns == info->ns;
 }
 
-static int kernfs_set_super(struct super_block *sb, void *data)
+static int kernfs_set_super(struct super_block *sb, struct fs_context *fc)
 {
-	int error;
-	error = set_anon_super(sb, data);
-	if (!error)
-		sb->s_fs_info = data;
-	return error;
+	struct kernfs_fs_context *kfc = fc->fs_private;
+
+	kfc->ns_tag = NULL;
+	return set_anon_super_fc(sb, fc);
 }
 
 /**
@@ -294,63 +282,60 @@ const void *kernfs_super_ns(struct super_block *sb)
 }
 
 /**
- * kernfs_mount_ns - kernfs mount helper
- * @fs_type: file_system_type of the fs being mounted
- * @flags: mount flags specified for the mount
- * @root: kernfs_root of the hierarchy being mounted
- * @magic: file system specific magic number
- * @new_sb_created: tell the caller if we allocated a new superblock
- * @ns: optional namespace tag of the mount
- *
- * This is to be called from each kernfs user's file_system_type->mount()
- * implementation, which should pass through the specified @fs_type and
- * @flags, and specify the hierarchy and namespace tag to mount via @root
- * and @ns, respectively.
+ * kernfs_get_tree - kernfs filesystem access/retrieval helper
+ * @fc: The filesystem context.
  *
- * The return value can be passed to the vfs layer verbatim.
+ * This is to be called from each kernfs user's fs_context->ops->get_tree()
+ * implementation, which should set the specified ->@fs_type and ->@flags, and
+ * specify the hierarchy and namespace tag to mount via ->@root and ->@ns,
+ * respectively.
  */
-struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
-				struct kernfs_root *root, unsigned long magic,
-				bool *new_sb_created, const void *ns)
+int kernfs_get_tree(struct fs_context *fc)
 {
+	struct kernfs_fs_context *kfc = fc->fs_private;
 	struct super_block *sb;
 	struct kernfs_super_info *info;
 	int error;
 
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
-	info->root = root;
-	info->ns = ns;
+	info->root = kfc->root;
+	info->ns = kfc->ns_tag;
 	INIT_LIST_HEAD(&info->node);
 
-	sb = sget_userns(fs_type, kernfs_test_super, kernfs_set_super, flags,
-			 &init_user_ns, info);
-	if (IS_ERR(sb) || sb->s_fs_info != info)
-		kfree(info);
+	fc->s_fs_info = info;
+	sb = sget_fc(fc, kernfs_test_super, kernfs_set_super);
 	if (IS_ERR(sb))
-		return ERR_CAST(sb);
-
-	if (new_sb_created)
-		*new_sb_created = !sb->s_root;
+		return PTR_ERR(sb);
 
 	if (!sb->s_root) {
 		struct kernfs_super_info *info = kernfs_info(sb);
 
-		error = kernfs_fill_super(sb, magic);
+		kfc->new_sb_created = true;
+
+		error = kernfs_fill_super(sb, kfc);
 		if (error) {
 			deactivate_locked_super(sb);
-			return ERR_PTR(error);
+			return error;
 		}
 		sb->s_flags |= SB_ACTIVE;
 
 		mutex_lock(&kernfs_mutex);
-		list_add(&info->node, &root->supers);
+		list_add(&info->node, &info->root->supers);
 		mutex_unlock(&kernfs_mutex);
 	}
 
-	return dget(sb->s_root);
+	fc->root = dget(sb->s_root);
+	return 0;
+}
+
+void kernfs_free_fs_context(struct fs_context *fc)
+{
+	/* Note that we don't deal with kfc->ns_tag here. */
+	kfree(fc->s_fs_info);
+	fc->s_fs_info = NULL;
 }
 
 /**
@@ -377,36 +362,6 @@ void kernfs_kill_sb(struct super_block *sb)
 	kfree(info);
 }
 
-/**
- * kernfs_pin_sb: try to pin the superblock associated with a kernfs_root
- * @kernfs_root: the kernfs_root in question
- * @ns: the namespace tag
- *
- * Pin the superblock so the superblock won't be destroyed in subsequent
- * operations.  This can be used to block ->kill_sb() which may be useful
- * for kernfs users which dynamically manage superblocks.
- *
- * Returns NULL if there's no superblock associated to this kernfs_root, or
- * -EINVAL if the superblock is being freed.
- */
-struct super_block *kernfs_pin_sb(struct kernfs_root *root, const void *ns)
-{
-	struct kernfs_super_info *info;
-	struct super_block *sb = NULL;
-
-	mutex_lock(&kernfs_mutex);
-	list_for_each_entry(info, &root->supers, node) {
-		if (info->ns == ns) {
-			sb = info->sb;
-			if (!atomic_inc_not_zero(&info->sb->s_active))
-				sb = ERR_PTR(-EINVAL);
-			break;
-		}
-	}
-	mutex_unlock(&kernfs_mutex);
-	return sb;
-}
-
 void __init kernfs_init(void)
 {
 

fs/mount.h

@@ -146,3 +146,8 @@ static inline bool is_local_mountpoint(struct dentry *dentry)
 
 	return __is_local_mountpoint(dentry);
 }
+
+static inline bool is_anon_ns(struct mnt_namespace *ns)
+{
+	return ns->seq == 0;
+}

fs/namei.c

@@ -2333,7 +2333,7 @@ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path
 	return err;
 }
 
-static int filename_lookup(int dfd, struct filename *name, unsigned flags,
+int filename_lookup(int dfd, struct filename *name, unsigned flags,
 		    struct path *path, struct path *root)
 {
 	int retval;

fs/orangefs/inode.c

@@ -261,11 +261,8 @@ int orangefs_getattr(const struct path *path, struct kstat *stat,
 		generic_fillattr(inode, stat);
 
 		/* override block size reported to stat */
-		if (request_mask & STATX_SIZE)
-			stat->result_mask = STATX_BASIC_STATS;
-		else
-			stat->result_mask = STATX_BASIC_STATS &
-			    ~STATX_SIZE;
+		if (!(request_mask & STATX_SIZE))
+			stat->result_mask &= ~STATX_SIZE;
 
 		stat->attributes_mask = STATX_ATTR_IMMUTABLE |
 		    STATX_ATTR_APPEND;

fs/pipe.c

@@ -226,8 +226,15 @@ void generic_pipe_buf_release(struct pipe_inode_info *pipe,
 }
 EXPORT_SYMBOL(generic_pipe_buf_release);
 
+/* New data written to a pipe may be appended to a buffer with this type. */
 static const struct pipe_buf_operations anon_pipe_buf_ops = {
-	.can_merge = 1,
+	.confirm = generic_pipe_buf_confirm,
+	.release = anon_pipe_buf_release,
+	.steal = anon_pipe_buf_steal,
+	.get = generic_pipe_buf_get,
+};
+
+static const struct pipe_buf_operations anon_pipe_buf_nomerge_ops = {
 	.confirm = generic_pipe_buf_confirm,
 	.release = anon_pipe_buf_release,
 	.steal = anon_pipe_buf_steal,
@@ -235,13 +242,32 @@ static const struct pipe_buf_operations anon_pipe_buf_ops = {
 };
 
 static const struct pipe_buf_operations packet_pipe_buf_ops = {
-	.can_merge = 0,
 	.confirm = generic_pipe_buf_confirm,
 	.release = anon_pipe_buf_release,
 	.steal = anon_pipe_buf_steal,
 	.get = generic_pipe_buf_get,
 };
 
+/**
+ * pipe_buf_mark_unmergeable - mark a &struct pipe_buffer as unmergeable
+ * @buf:	the buffer to mark
+ *
+ * Description:
+ *	This function ensures that no future writes will be merged into the
+ *	given &struct pipe_buffer. This is necessary when multiple pipe buffers
+ *	share the same backing page.
+ */
+void pipe_buf_mark_unmergeable(struct pipe_buffer *buf)
+{
+	if (buf->ops == &anon_pipe_buf_ops)
+		buf->ops = &anon_pipe_buf_nomerge_ops;
+}
+
+static bool pipe_buf_can_merge(struct pipe_buffer *buf)
+{
+	return buf->ops == &anon_pipe_buf_ops;
+}
+
 static ssize_t
 pipe_read(struct kiocb *iocb, struct iov_iter *to)
 {
@@ -379,7 +405,7 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
 		struct pipe_buffer *buf = pipe->bufs + lastbuf;
 		int offset = buf->offset + buf->len;
 
-		if (buf->ops->can_merge && offset + chars <= PAGE_SIZE) {
+		if (pipe_buf_can_merge(buf) && offset + chars <= PAGE_SIZE) {
 			ret = pipe_buf_confirm(pipe, buf);
 			if (ret)
 				goto out;

fs/pnode.c

@@ -214,7 +214,6 @@ static struct mount *next_group(struct mount *m, struct mount *origin)
 }
 
 /* all accesses are serialized by namespace_sem */
-static struct user_namespace *user_ns;
 static struct mount *last_dest, *first_source, *last_source, *dest_master;
 static struct mountpoint *mp;
 static struct hlist_head *list;
@@ -260,9 +259,6 @@ static int propagate_one(struct mount *m)
 			type |= CL_MAKE_SHARED;
 	}
 		
-	/* Notice when we are propagating across user namespaces */
-	if (m->mnt_ns->user_ns != user_ns)
-		type |= CL_UNPRIVILEGED;
 	child = copy_tree(last_source, last_source->mnt.mnt_root, type);
 	if (IS_ERR(child))
 		return PTR_ERR(child);
@@ -303,7 +299,6 @@ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp,
 	 * propagate_one(); everything is serialized by namespace_sem,
 	 * so globals will do just fine.
 	 */
-	user_ns = current->nsproxy->mnt_ns->user_ns;
 	last_dest = dest_mnt;
 	first_source = source_mnt;
 	last_source = source_mnt;

fs/pnode.h

@@ -27,8 +27,7 @@
 #define CL_MAKE_SHARED 		0x08
 #define CL_PRIVATE 		0x10
 #define CL_SHARED_TO_SLAVE	0x20
-#define CL_UNPRIVILEGED		0x40
-#define CL_COPY_MNT_NS_FILE	0x80
+#define CL_COPY_MNT_NS_FILE	0x40
 
 #define CL_COPY_ALL		(CL_COPY_UNBINDABLE | CL_COPY_MNT_NS_FILE)
 

fs/proc/inode.c

@@ -24,7 +24,6 @@
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/mount.h>
-#include <linux/magic.h>
 
 #include <linux/uaccess.h>
 
@@ -122,13 +121,12 @@ static int proc_show_options(struct seq_file *seq, struct dentry *root)
 	return 0;
 }
 
-static const struct super_operations proc_sops = {
+const struct super_operations proc_sops = {
 	.alloc_inode	= proc_alloc_inode,
 	.destroy_inode	= proc_destroy_inode,
 	.drop_inode	= generic_delete_inode,
 	.evict_inode	= proc_evict_inode,
 	.statfs		= simple_statfs,
-	.remount_fs	= proc_remount,
 	.show_options	= proc_show_options,
 };
 
@@ -488,51 +486,3 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
 	       pde_put(de);
 	return inode;
 }
-
-int proc_fill_super(struct super_block *s, void *data, int silent)
-{
-	struct pid_namespace *ns = get_pid_ns(s->s_fs_info);
-	struct inode *root_inode;
-	int ret;
-
-	if (!proc_parse_options(data, ns))
-		return -EINVAL;
-
-	/* User space would break if executables or devices appear on proc */
-	s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NOEXEC | SB_I_NODEV;
-	s->s_flags |= SB_NODIRATIME | SB_NOSUID | SB_NOEXEC;
-	s->s_blocksize = 1024;
-	s->s_blocksize_bits = 10;
-	s->s_magic = PROC_SUPER_MAGIC;
-	s->s_op = &proc_sops;
-	s->s_time_gran = 1;
-
-	/*
-	 * procfs isn't actually a stacking filesystem; however, there is
-	 * too much magic going on inside it to permit stacking things on
-	 * top of it
-	 */
-	s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;
-	
-	/* procfs dentries and inodes don't require IO to create */
-	s->s_shrink.seeks = 0;
-
-	pde_get(&proc_root);
-	root_inode = proc_get_inode(s, &proc_root);
-	if (!root_inode) {
-		pr_err("proc_fill_super: get root inode failed\n");
-		return -ENOMEM;
-	}
-
-	s->s_root = d_make_root(root_inode);
-	if (!s->s_root) {
-		pr_err("proc_fill_super: allocate dentry failed\n");
-		return -ENOMEM;
-	}
-
-	ret = proc_setup_self(s);
-	if (ret) {
-		return ret;
-	}
-	return proc_setup_thread_self(s);
-}

fs/proc/internal.h

@@ -205,13 +205,12 @@ struct pde_opener {
 	struct completion *c;
 } __randomize_layout;
 extern const struct inode_operations proc_link_inode_operations;
-
 extern const struct inode_operations proc_pid_link_inode_operations;
+extern const struct super_operations proc_sops;
 
 void proc_init_kmemcache(void);
 void set_proc_pid_nlink(void);
 extern struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *);
-extern int proc_fill_super(struct super_block *, void *data, int flags);
 extern void proc_entry_rundown(struct proc_dir_entry *);
 
 /*
@@ -269,10 +268,8 @@ static inline void proc_tty_init(void) {}
  * root.c
  */
 extern struct proc_dir_entry proc_root;
-extern int proc_parse_options(char *options, struct pid_namespace *pid);
 
 extern void proc_self_init(void);
-extern int proc_remount(struct super_block *, int *, char *);
 
 /*
  * task_[no]mmu.c

fs/proc/root.c

@@ -19,86 +19,178 @@
 #include <linux/module.h>
 #include <linux/bitops.h>
 #include <linux/user_namespace.h>
+#include <linux/fs_context.h>
 #include <linux/mount.h>
 #include <linux/pid_namespace.h>
-#include <linux/parser.h>
+#include <linux/fs_parser.h>
 #include <linux/cred.h>
+#include <linux/magic.h>
+#include <linux/slab.h>
 
 #include "internal.h"
 
-enum {
-	Opt_gid, Opt_hidepid, Opt_err,
+struct proc_fs_context {
+	struct pid_namespace	*pid_ns;
+	unsigned int		mask;
+	int			hidepid;
+	int			gid;
 };
 
-static const match_table_t tokens = {
-	{Opt_hidepid, "hidepid=%u"},
-	{Opt_gid, "gid=%u"},
-	{Opt_err, NULL},
+enum proc_param {
+	Opt_gid,
+	Opt_hidepid,
 };
 
-int proc_parse_options(char *options, struct pid_namespace *pid)
-{
-	char *p;
-	substring_t args[MAX_OPT_ARGS];
-	int option;
+static const struct fs_parameter_spec proc_param_specs[] = {
+	fsparam_u32("gid",	Opt_gid),
+	fsparam_u32("hidepid",	Opt_hidepid),
+	{}
+};
+
+static const struct fs_parameter_description proc_fs_parameters = {
+	.name		= "proc",
+	.specs		= proc_param_specs,
+};
 
-	if (!options)
-		return 1;
+static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct proc_fs_context *ctx = fc->fs_private;
+	struct fs_parse_result result;
+	int opt;
 
-	while ((p = strsep(&options, ",")) != NULL) {
-		int token;
-		if (!*p)
-			continue;
+	opt = fs_parse(fc, &proc_fs_parameters, param, &result);
+	if (opt < 0)
+		return opt;
 
-		args[0].to = args[0].from = NULL;
-		token = match_token(p, tokens, args);
-		switch (token) {
+	switch (opt) {
 	case Opt_gid:
-			if (match_int(&args[0], &option))
-				return 0;
-			pid->pid_gid = make_kgid(current_user_ns(), option);
+		ctx->gid = result.uint_32;
 		break;
+
 	case Opt_hidepid:
-			if (match_int(&args[0], &option))
-				return 0;
-			if (option < HIDEPID_OFF ||
-			    option > HIDEPID_INVISIBLE) {
-				pr_err("proc: hidepid value must be between 0 and 2.\n");
-				return 0;
-			}
-			pid->hide_pid = option;
+		ctx->hidepid = result.uint_32;
+		if (ctx->hidepid < HIDEPID_OFF ||
+		    ctx->hidepid > HIDEPID_INVISIBLE)
+			return invalf(fc, "proc: hidepid value must be between 0 and 2.\n");
 		break;
+
 	default:
-			pr_err("proc: unrecognized mount option \"%s\" "
-			       "or missing value\n", p);
+		return -EINVAL;
+	}
+
+	ctx->mask |= 1 << opt;
 	return 0;
+}
+
+static void proc_apply_options(struct super_block *s,
+			       struct fs_context *fc,
+			       struct pid_namespace *pid_ns,
+			       struct user_namespace *user_ns)
+{
+	struct proc_fs_context *ctx = fc->fs_private;
+
+	if (ctx->mask & (1 << Opt_gid))
+		pid_ns->pid_gid = make_kgid(user_ns, ctx->gid);
+	if (ctx->mask & (1 << Opt_hidepid))
+		pid_ns->hide_pid = ctx->hidepid;
+}
+
+static int proc_fill_super(struct super_block *s, struct fs_context *fc)
+{
+	struct pid_namespace *pid_ns = get_pid_ns(s->s_fs_info);
+	struct inode *root_inode;
+	int ret;
+
+	proc_apply_options(s, fc, pid_ns, current_user_ns());
+
+	/* User space would break if executables or devices appear on proc */
+	s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NOEXEC | SB_I_NODEV;
+	s->s_flags |= SB_NODIRATIME | SB_NOSUID | SB_NOEXEC;
+	s->s_blocksize = 1024;
+	s->s_blocksize_bits = 10;
+	s->s_magic = PROC_SUPER_MAGIC;
+	s->s_op = &proc_sops;
+	s->s_time_gran = 1;
+
+	/*
+	 * procfs isn't actually a stacking filesystem; however, there is
+	 * too much magic going on inside it to permit stacking things on
+	 * top of it
+	 */
+	s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;
+	
+	/* procfs dentries and inodes don't require IO to create */
+	s->s_shrink.seeks = 0;
+
+	pde_get(&proc_root);
+	root_inode = proc_get_inode(s, &proc_root);
+	if (!root_inode) {
+		pr_err("proc_fill_super: get root inode failed\n");
+		return -ENOMEM;
 	}
+
+	s->s_root = d_make_root(root_inode);
+	if (!s->s_root) {
+		pr_err("proc_fill_super: allocate dentry failed\n");
+		return -ENOMEM;
 	}
 
-	return 1;
+	ret = proc_setup_self(s);
+	if (ret) {
+		return ret;
+	}
+	return proc_setup_thread_self(s);
 }
 
-int proc_remount(struct super_block *sb, int *flags, char *data)
+static int proc_reconfigure(struct fs_context *fc)
 {
+	struct super_block *sb = fc->root->d_sb;
 	struct pid_namespace *pid = sb->s_fs_info;
 
 	sync_filesystem(sb);
-	return !proc_parse_options(data, pid);
+
+	proc_apply_options(sb, fc, pid, current_user_ns());
+	return 0;
 }
 
-static struct dentry *proc_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
+static int proc_get_tree(struct fs_context *fc)
 {
-	struct pid_namespace *ns;
+	struct proc_fs_context *ctx = fc->fs_private;
 
-	if (flags & SB_KERNMOUNT) {
-		ns = data;
-		data = NULL;
-	} else {
-		ns = task_active_pid_ns(current);
-	}
+	put_user_ns(fc->user_ns);
+	fc->user_ns = get_user_ns(ctx->pid_ns->user_ns);
+	fc->s_fs_info = ctx->pid_ns;
+	return vfs_get_super(fc, vfs_get_keyed_super, proc_fill_super);
+}
+
+static void proc_fs_context_free(struct fs_context *fc)
+{
+	struct proc_fs_context *ctx = fc->fs_private;
 
-	return mount_ns(fs_type, flags, data, ns, ns->user_ns, proc_fill_super);
+	if (ctx->pid_ns)
+		put_pid_ns(ctx->pid_ns);
+	kfree(ctx);
+}
+
+static const struct fs_context_operations proc_fs_context_ops = {
+	.free		= proc_fs_context_free,
+	.parse_param	= proc_parse_param,
+	.get_tree	= proc_get_tree,
+	.reconfigure	= proc_reconfigure,
+};
+
+static int proc_init_fs_context(struct fs_context *fc)
+{
+	struct proc_fs_context *ctx;
+
+	ctx = kzalloc(sizeof(struct proc_fs_context), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->pid_ns = get_pid_ns(task_active_pid_ns(current));
+	fc->fs_private = ctx;
+	fc->ops = &proc_fs_context_ops;
+	return 0;
 }
 
 static void proc_kill_sb(struct super_block *sb)
@@ -116,7 +208,8 @@ static void proc_kill_sb(struct super_block *sb)
 
 static struct file_system_type proc_fs_type = {
 	.name			= "proc",
-	.mount		= proc_mount,
+	.init_fs_context	= proc_init_fs_context,
+	.parameters		= &proc_fs_parameters,
 	.kill_sb		= proc_kill_sb,
 	.fs_flags		= FS_USERNS_MOUNT,
 };
@@ -209,9 +302,28 @@ struct proc_dir_entry proc_root = {
 
 int pid_ns_prepare_proc(struct pid_namespace *ns)
 {
+	struct proc_fs_context *ctx;
+	struct fs_context *fc;
 	struct vfsmount *mnt;
 
-	mnt = kern_mount_data(&proc_fs_type, ns);
+	fc = fs_context_for_mount(&proc_fs_type, SB_KERNMOUNT);
+	if (IS_ERR(fc))
+		return PTR_ERR(fc);
+
+	if (fc->user_ns != ns->user_ns) {
+		put_user_ns(fc->user_ns);
+		fc->user_ns = get_user_ns(ns->user_ns);
+	}
+
+	ctx = fc->fs_private;
+	if (ctx->pid_ns != ns) {
+		put_pid_ns(ctx->pid_ns);
+		get_pid_ns(ns);
+		ctx->pid_ns = ns;
+	}
+
+	mnt = fc_mount(fc);
+	put_fs_context(fc);
 	if (IS_ERR(mnt))
 		return PTR_ERR(mnt);
 

fs/read_write.c

@@ -478,8 +478,8 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t
 	return ret;
 }
 
-ssize_t __vfs_write(struct file *file, const char __user *p, size_t count,
-		    loff_t *pos)
+static ssize_t __vfs_write(struct file *file, const char __user *p,
+			   size_t count, loff_t *pos)
 {
 	if (file->f_op->write)
 		return file->f_op->write(file, p, count, pos);
@@ -1238,6 +1238,9 @@ COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd,
 		const struct compat_iovec __user *,vec,
 		unsigned long, vlen, loff_t, pos, rwf_t, flags)
 {
+	if (pos == -1)
+		return do_compat_readv(fd, vec, vlen, flags);
+
 	return do_compat_preadv64(fd, vec, vlen, pos, flags);
 }
 #endif
@@ -1344,6 +1347,9 @@ COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd,
 		const struct compat_iovec __user *,vec,
 		unsigned long, vlen, loff_t, pos, rwf_t, flags)
 {
+	if (pos == -1)
+		return do_compat_writev(fd, vec, vlen, flags);
+
 	return do_compat_pwritev64(fd, vec, vlen, pos, flags);
 }
 #endif

fs/splice.c

@@ -138,7 +138,6 @@ static int page_cache_pipe_buf_confirm(struct pipe_inode_info *pipe,
 }
 
 const struct pipe_buf_operations page_cache_pipe_buf_ops = {
-	.can_merge = 0,
 	.confirm = page_cache_pipe_buf_confirm,
 	.release = page_cache_pipe_buf_release,
 	.steal = page_cache_pipe_buf_steal,
@@ -156,7 +155,6 @@ static int user_page_pipe_buf_steal(struct pipe_inode_info *pipe,
 }
 
 static const struct pipe_buf_operations user_page_pipe_buf_ops = {
-	.can_merge = 0,
 	.confirm = generic_pipe_buf_confirm,
 	.release = page_cache_pipe_buf_release,
 	.steal = user_page_pipe_buf_steal,
@@ -326,7 +324,6 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
 EXPORT_SYMBOL(generic_file_splice_read);
 
 const struct pipe_buf_operations default_pipe_buf_ops = {
-	.can_merge = 0,
 	.confirm = generic_pipe_buf_confirm,
 	.release = generic_pipe_buf_release,
 	.steal = generic_pipe_buf_steal,
@@ -341,7 +338,6 @@ static int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe,
 
 /* Pipe buffer operations for a socket and similar. */
 const struct pipe_buf_operations nosteal_pipe_buf_ops = {
-	.can_merge = 0,
 	.confirm = generic_pipe_buf_confirm,
 	.release = generic_pipe_buf_release,
 	.steal = generic_pipe_buf_nosteal,
@@ -1597,6 +1593,8 @@ static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
 			 */
 			obuf->flags &= ~PIPE_BUF_FLAG_GIFT;
 
+			pipe_buf_mark_unmergeable(obuf);
+
 			obuf->len = len;
 			opipe->nrbufs++;
 			ibuf->offset += obuf->len;
@@ -1671,6 +1669,8 @@ static int link_pipe(struct pipe_inode_info *ipipe,
 		 */
 		obuf->flags &= ~PIPE_BUF_FLAG_GIFT;
 
+		pipe_buf_mark_unmergeable(obuf);
+
 		if (obuf->len > len)
 			obuf->len = len;
 

fs/stat.c

@@ -45,11 +45,6 @@ void generic_fillattr(struct inode *inode, struct kstat *stat)
 	stat->ctime = inode->i_ctime;
 	stat->blksize = i_blocksize(inode);
 	stat->blocks = inode->i_blocks;
-
-	if (IS_NOATIME(inode))
-		stat->result_mask &= ~STATX_ATIME;
-	if (IS_AUTOMOUNT(inode))
-		stat->attributes |= STATX_ATTR_AUTOMOUNT;
 }
 EXPORT_SYMBOL(generic_fillattr);
 
@@ -75,6 +70,13 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat,
 	stat->result_mask |= STATX_BASIC_STATS;
 	request_mask &= STATX_ALL;
 	query_flags &= KSTAT_QUERY_FLAGS;
+
+	/* allow the fs to override these if it really wants to */
+	if (IS_NOATIME(inode))
+		stat->result_mask &= ~STATX_ATIME;
+	if (IS_AUTOMOUNT(inode))
+		stat->attributes |= STATX_ATTR_AUTOMOUNT;
+
 	if (inode->i_op->getattr)
 		return inode->i_op->getattr(path, stat, request_mask,
 					    query_flags);

fs/sysfs/mount.c

@@ -13,34 +13,69 @@
 #include <linux/magic.h>
 #include <linux/mount.h>
 #include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/user_namespace.h>
+#include <linux/fs_context.h>
+#include <net/net_namespace.h>
 
 #include "sysfs.h"
 
 static struct kernfs_root *sysfs_root;
 struct kernfs_node *sysfs_root_kn;
 
-static struct dentry *sysfs_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
+static int sysfs_get_tree(struct fs_context *fc)
 {
-	struct dentry *root;
-	void *ns;
-	bool new_sb = false;
+	struct kernfs_fs_context *kfc = fc->fs_private;
+	int ret;
 
-	if (!(flags & SB_KERNMOUNT)) {
+	ret = kernfs_get_tree(fc);
+	if (ret)
+		return ret;
+
+	if (kfc->new_sb_created)
+		fc->root->d_sb->s_iflags |= SB_I_USERNS_VISIBLE;
+	return 0;
+}
+
+static void sysfs_fs_context_free(struct fs_context *fc)
+{
+	struct kernfs_fs_context *kfc = fc->fs_private;
+
+	if (kfc->ns_tag)
+		kobj_ns_drop(KOBJ_NS_TYPE_NET, kfc->ns_tag);
+	kernfs_free_fs_context(fc);
+	kfree(kfc);
+}
+
+static const struct fs_context_operations sysfs_fs_context_ops = {
+	.free		= sysfs_fs_context_free,
+	.get_tree	= sysfs_get_tree,
+};
+
+static int sysfs_init_fs_context(struct fs_context *fc)
+{
+	struct kernfs_fs_context *kfc;
+	struct net *netns;
+
+	if (!(fc->sb_flags & SB_KERNMOUNT)) {
 		if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET))
-			return ERR_PTR(-EPERM);
+			return -EPERM;
 	}
 
-	ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET);
-	root = kernfs_mount_ns(fs_type, flags, sysfs_root,
-				SYSFS_MAGIC, &new_sb, ns);
-	if (!new_sb)
-		kobj_ns_drop(KOBJ_NS_TYPE_NET, ns);
-	else if (!IS_ERR(root))
-		root->d_sb->s_iflags |= SB_I_USERNS_VISIBLE;
+	kfc = kzalloc(sizeof(struct kernfs_fs_context), GFP_KERNEL);
+	if (!kfc)
+		return -ENOMEM;
 
-	return root;
+	kfc->ns_tag = netns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET);
+	kfc->root = sysfs_root;
+	kfc->magic = SYSFS_MAGIC;
+	fc->fs_private = kfc;
+	fc->ops = &sysfs_fs_context_ops;
+	if (fc->user_ns)
+		put_user_ns(fc->user_ns);
+	fc->user_ns = get_user_ns(netns->user_ns);
+	fc->global = true;
+	return 0;
 }
 
 static void sysfs_kill_sb(struct super_block *sb)
@@ -53,7 +88,7 @@ static void sysfs_kill_sb(struct super_block *sb)
 
 static struct file_system_type sysfs_fs_type = {
 	.name			= "sysfs",
-	.mount		= sysfs_mount,
+	.init_fs_context	= sysfs_init_fs_context,
 	.kill_sb		= sysfs_kill_sb,
 	.fs_flags		= FS_USERNS_MOUNT,
 };

include/linux/errno.h

@@ -18,6 +18,7 @@
 #define ERESTART_RESTARTBLOCK 516 /* restart by calling sys_restart_syscall */
 #define EPROBE_DEFER	517	/* Driver requests probe retry */
 #define EOPENSTALE	518	/* open found a stale dentry */
+#define ENOPARAM	519	/* Parameter not supported */
 
 /* Defined for the NFSv3 protocol */
 #define EBADHANDLE	521	/* Illegal NFS file handle */

include/linux/lsm_hooks.h

@@ -76,6 +76,22 @@
  *	changes on the process such as clearing out non-inheritable signal
  *	state.  This is called immediately after commit_creds().
  *
+ * Security hooks for mount using fs_context.
+ *	[See also Documentation/filesystems/mounting.txt]
+ *
+ * @fs_context_dup:
+ *	Allocate and attach a security structure to sc->security.  This pointer
+ *	is initialised to NULL by the caller.
+ *	@fc indicates the new filesystem context.
+ *	@src_fc indicates the original filesystem context.
+ * @fs_context_parse_param:
+ *	Userspace provided a parameter to configure a superblock.  The LSM may
+ *	reject it with an error and may use it for itself, in which case it
+ *	should return 0; otherwise it should return -ENOPARAM to pass it on to
+ *	the filesystem.
+ *	@fc indicates the filesystem context.
+ *	@param The parameter
+ *
  * Security hooks for filesystem operations.
  *
  * @sb_alloc_security:
@@ -1459,6 +1475,9 @@ union security_list_options {
 	void (*bprm_committing_creds)(struct linux_binprm *bprm);
 	void (*bprm_committed_creds)(struct linux_binprm *bprm);
 
+	int (*fs_context_dup)(struct fs_context *fc, struct fs_context *src_sc);
+	int (*fs_context_parse_param)(struct fs_context *fc, struct fs_parameter *param);
+
 	int (*sb_alloc_security)(struct super_block *sb);
 	void (*sb_free_security)(struct super_block *sb);
 	void (*sb_free_mnt_opts)(void *mnt_opts);
@@ -1800,6 +1819,8 @@ struct security_hook_heads {
 	struct hlist_head bprm_check_security;
 	struct hlist_head bprm_committing_creds;
 	struct hlist_head bprm_committed_creds;
+	struct hlist_head fs_context_dup;
+	struct hlist_head fs_context_parse_param;
 	struct hlist_head sb_alloc_security;
 	struct hlist_head sb_free_security;
 	struct hlist_head sb_free_mnt_opts;

ipc/namespace.c

@@ -42,7 +42,7 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
 		goto fail;
 
 	err = -ENOMEM;
-	ns = kmalloc(sizeof(struct ipc_namespace), GFP_KERNEL);
+	ns = kzalloc(sizeof(struct ipc_namespace), GFP_KERNEL);
 	if (ns == NULL)
 		goto fail_dec;