13 files changed, 206 insertions, 10 deletions

diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index f5df23561b9..503c8a6b307 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -217,8 +217,24 @@ int cont_write_begin(struct file *, struct address_space *, loff_t,
 			get_block_t *, loff_t *);
 int generic_cont_expand_simple(struct inode *inode, loff_t size);
 int block_commit_write(struct page *page, unsigned from, unsigned to);
+int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
+				get_block_t get_block);
 int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 				get_block_t get_block);
+/* Convert errno to return value from ->page_mkwrite() call */
+static inline int block_page_mkwrite_return(int err)
+{
+	if (err == 0)
+		return VM_FAULT_LOCKED;
+	if (err == -EFAULT)
+		return VM_FAULT_NOPAGE;
+	if (err == -ENOMEM)
+		return VM_FAULT_OOM;
+	if (err == -EAGAIN)
+		return VM_FAULT_RETRY;
+	/* -ENOSPC, -EDQUOT, -EIO ... */
+	return VM_FAULT_SIGBUS;
+}
 sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *);
 int block_truncate_page(struct address_space *, loff_t, get_block_t *);
 int nobh_write_begin(struct address_space *, loff_t, unsigned, unsigned,
diff --git a/include/linux/cleancache.h b/include/linux/cleancache.h
new file mode 100644
index 00000000000..04ffb2e6c9d
--- /dev/null
+++ b/include/linux/cleancache.h
@@ -0,0 +1,122 @@
+#ifndef _LINUX_CLEANCACHE_H
+#define _LINUX_CLEANCACHE_H
+
+#include <linux/fs.h>
+#include <linux/exportfs.h>
+#include <linux/mm.h>
+
+#define CLEANCACHE_KEY_MAX 6
+
+/*
+ * cleancache requires every file with a page in cleancache to have a
+ * unique key unless/until the file is removed/truncated.  For some
+ * filesystems, the inode number is unique, but for "modern" filesystems
+ * an exportable filehandle is required (see exportfs.h)
+ */
+struct cleancache_filekey {
+	union {
+		ino_t ino;
+		__u32 fh[CLEANCACHE_KEY_MAX];
+		u32 key[CLEANCACHE_KEY_MAX];
+	} u;
+};
+
+struct cleancache_ops {
+	int (*init_fs)(size_t);
+	int (*init_shared_fs)(char *uuid, size_t);
+	int (*get_page)(int, struct cleancache_filekey,
+			pgoff_t, struct page *);
+	void (*put_page)(int, struct cleancache_filekey,
+			pgoff_t, struct page *);
+	void (*flush_page)(int, struct cleancache_filekey, pgoff_t);
+	void (*flush_inode)(int, struct cleancache_filekey);
+	void (*flush_fs)(int);
+};
+
+extern struct cleancache_ops
+	cleancache_register_ops(struct cleancache_ops *ops);
+extern void __cleancache_init_fs(struct super_block *);
+extern void __cleancache_init_shared_fs(char *, struct super_block *);
+extern int  __cleancache_get_page(struct page *);
+extern void __cleancache_put_page(struct page *);
+extern void __cleancache_flush_page(struct address_space *, struct page *);
+extern void __cleancache_flush_inode(struct address_space *);
+extern void __cleancache_flush_fs(struct super_block *);
+extern int cleancache_enabled;
+
+#ifdef CONFIG_CLEANCACHE
+static inline bool cleancache_fs_enabled(struct page *page)
+{
+	return page->mapping->host->i_sb->cleancache_poolid >= 0;
+}
+static inline bool cleancache_fs_enabled_mapping(struct address_space *mapping)
+{
+	return mapping->host->i_sb->cleancache_poolid >= 0;
+}
+#else
+#define cleancache_enabled (0)
+#define cleancache_fs_enabled(_page) (0)
+#define cleancache_fs_enabled_mapping(_page) (0)
+#endif
+
+/*
+ * The shim layer provided by these inline functions allows the compiler
+ * to reduce all cleancache hooks to nothingness if CONFIG_CLEANCACHE
+ * is disabled, to a single global variable check if CONFIG_CLEANCACHE
+ * is enabled but no cleancache "backend" has dynamically enabled it,
+ * and, for the most frequent cleancache ops, to a single global variable
+ * check plus a superblock element comparison if CONFIG_CLEANCACHE is enabled
+ * and a cleancache backend has dynamically enabled cleancache, but the
+ * filesystem referenced by that cleancache op has not enabled cleancache.
+ * As a result, CONFIG_CLEANCACHE can be enabled by default with essentially
+ * no measurable performance impact.
+ */
+
+static inline void cleancache_init_fs(struct super_block *sb)
+{
+	if (cleancache_enabled)
+		__cleancache_init_fs(sb);
+}
+
+static inline void cleancache_init_shared_fs(char *uuid, struct super_block *sb)
+{
+	if (cleancache_enabled)
+		__cleancache_init_shared_fs(uuid, sb);
+}
+
+static inline int cleancache_get_page(struct page *page)
+{
+	int ret = -1;
+
+	if (cleancache_enabled && cleancache_fs_enabled(page))
+		ret = __cleancache_get_page(page);
+	return ret;
+}
+
+static inline void cleancache_put_page(struct page *page)
+{
+	if (cleancache_enabled && cleancache_fs_enabled(page))
+		__cleancache_put_page(page);
+}
+
+static inline void cleancache_flush_page(struct address_space *mapping,
+					struct page *page)
+{
+	/* careful... page->mapping is NULL sometimes when this is called */
+	if (cleancache_enabled && cleancache_fs_enabled_mapping(mapping))
+		__cleancache_flush_page(mapping, page);
+}
+
+static inline void cleancache_flush_inode(struct address_space *mapping)
+{
+	if (cleancache_enabled && cleancache_fs_enabled_mapping(mapping))
+		__cleancache_flush_inode(mapping);
+}
+
+static inline void cleancache_flush_fs(struct super_block *sb)
+{
+	if (cleancache_enabled)
+		__cleancache_flush_fs(sb);
+}
+
+#endif /* _LINUX_CLEANCACHE_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3f9d3251790..241609346df 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1428,6 +1428,11 @@ struct super_block {
 	 */
 	char __rcu *s_options;
 	const struct dentry_operations *s_d_op; /* default d_op for dentries */
+
+	/*
+	 * Saved pool identifier for cleancache (-1 means none)
+	 */
+	int cleancache_poolid;
 };
 
 extern struct timespec current_fs_time(struct super_block *sb);
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 943c76b3d4b..59225ef27d1 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -1,6 +1,7 @@
 #ifndef _LINUX_HUGETLB_H
 #define _LINUX_HUGETLB_H
 
+#include <linux/mm_types.h>
 #include <linux/fs.h>
 #include <linux/hugetlb_inline.h>
 
@@ -41,7 +42,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, unsigned int flags);
 int hugetlb_reserve_pages(struct inode *inode, long from, long to,
 						struct vm_area_struct *vma,
-						int acctflags);
+						vm_flags_t vm_flags);
 void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed);
 int dequeue_hwpoisoned_huge_page(struct page *page);
 void copy_huge_page(struct page *dst, struct page *src);
@@ -168,7 +169,7 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb)
 
 extern const struct file_operations hugetlbfs_file_operations;
 extern const struct vm_operations_struct hugetlb_vm_ops;
-struct file *hugetlb_file_setup(const char *name, size_t size, int acct,
+struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct,
 				struct user_struct **user, int creat_flags);
 int hugetlb_get_quota(struct address_space *mapping, long delta);
 void hugetlb_put_quota(struct address_space *mapping, long delta);
@@ -192,7 +193,7 @@ static inline void set_file_hugepages(struct file *file)
 #define is_file_hugepages(file)			0
 #define set_file_hugepages(file)		BUG()
 static inline struct file *hugetlb_file_setup(const char *name, size_t size,
-		int acctflag, struct user_struct **user, int creat_flags)
+		vm_flags_t acctflag, struct user_struct **user, int creat_flags)
 {
 	return ERR_PTR(-ENOSYS);
 }
diff --git a/include/linux/hugetlb_inline.h b/include/linux/hugetlb_inline.h
index 6931489a5c1..2bb681fbeb3 100644
--- a/include/linux/hugetlb_inline.h
+++ b/include/linux/hugetlb_inline.h
@@ -7,7 +7,7 @@
 
 static inline int is_vm_hugetlb_page(struct vm_area_struct *vma)
 {
-	return vma->vm_flags & VM_HUGETLB;
+	return !!(vma->vm_flags & VM_HUGETLB);
 }
 
 #else
diff --git a/include/linux/if_link.h b/include/linux/if_link.h
index f4a2e6b1b86..0ee969a5593 100644
--- a/include/linux/if_link.h
+++ b/include/linux/if_link.h
@@ -136,6 +136,7 @@ enum {
 	IFLA_PORT_SELF,
 	IFLA_AF_SPEC,
 	IFLA_GROUP,		/* Group the device belongs to */
+	IFLA_NET_NS_FD,
 	__IFLA_MAX
 };
 
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index a32dcaec04e..4ecb7b16b27 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -529,9 +529,10 @@ struct transaction_s
 	enum {
 		T_RUNNING,
 		T_LOCKED,
-		T_RUNDOWN,
 		T_FLUSH,
 		T_COMMIT,
+		T_COMMIT_DFLUSH,
+		T_COMMIT_JFLUSH,
 		T_FINISHED
 	}			t_state;
 
@@ -658,7 +659,9 @@ struct transaction_s
 	 * waiting for it to finish.
 	 */
 	unsigned int t_synchronous_commit:1;
-	unsigned int t_flushed_data_blocks:1;
+
+	/* Disk flush needs to be sent to fs partition [no locking] */
+	int			t_need_data_flush;
 
 	/*
 	 * For use by the filesystem to store fs-specific data
@@ -1228,6 +1231,7 @@ int jbd2_journal_start_commit(journal_t *journal, tid_t *tid);
 int jbd2_journal_force_commit_nested(journal_t *journal);
 int jbd2_log_wait_commit(journal_t *journal, tid_t tid);
 int jbd2_log_do_checkpoint(journal_t *journal);
+int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid);
 
 void __jbd2_log_wait_for_space(journal_t *journal);
 extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8eb969ebf90..fb8e814f78d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -165,12 +165,12 @@ extern pgprot_t protection_map[16];
  */
 static inline int is_linear_pfn_mapping(struct vm_area_struct *vma)
 {
-	return (vma->vm_flags & VM_PFN_AT_MMAP);
+	return !!(vma->vm_flags & VM_PFN_AT_MMAP);
 }
 
 static inline int is_pfn_mapping(struct vm_area_struct *vma)
 {
-	return (vma->vm_flags & VM_PFNMAP);
+	return !!(vma->vm_flags & VM_PFNMAP);
 }
 
 /*
@@ -1432,7 +1432,7 @@ extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 	unsigned long flag, unsigned long pgoff);
 extern unsigned long mmap_region(struct file *file, unsigned long addr,
 	unsigned long len, unsigned long flags,
-	unsigned int vm_flags, unsigned long pgoff);
+	vm_flags_t vm_flags, unsigned long pgoff);
 
 static inline unsigned long do_mmap(struct file *file, unsigned long addr,
 	unsigned long len, unsigned long prot,
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 071d459e866..6fe96c19f85 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -102,6 +102,8 @@ struct page {
 #endif
 };
 
+typedef unsigned long __nocast vm_flags_t;
+
 /*
  * A region containing a mapping of a non-memory backed file under NOMMU
  * conditions.  These are held in a global tree and are pinned by the VMAs that
@@ -109,7 +111,7 @@ struct page {
  */
 struct vm_region {
 	struct rb_node	vm_rb;		/* link in global region tree */
-	unsigned long	vm_flags;	/* VMA vm_flags */
+	vm_flags_t	vm_flags;	/* VMA vm_flags */
 	unsigned long	vm_start;	/* start address of region */
 	unsigned long	vm_end;		/* region initialised to here */
 	unsigned long	vm_top;		/* region allocated to here */
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 3686cd6c9ac..648c9c58add 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -179,6 +179,8 @@ extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);
 extern struct file *get_mm_exe_file(struct mm_struct *mm);
 extern void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm);
 
+extern struct file *proc_ns_fget(int fd);
+
 #else
 
 #define proc_net_fops_create(net, name, mode, fops)  ({ (void)(mode), NULL; })
@@ -241,6 +243,11 @@ static inline void dup_mm_exe_file(struct mm_struct *oldmm,
 	       			   struct mm_struct *newmm)
 {}
 
+static inline struct file *proc_ns_fget(int fd)
+{
+	return ERR_PTR(-EINVAL);
+}
+
 #endif /* CONFIG_PROC_FS */
 
 #if !defined(CONFIG_PROC_KCORE)
@@ -252,6 +259,18 @@ kclist_add(struct kcore_list *new, void *addr, size_t size, int type)
 extern void kclist_add(struct kcore_list *, void *, size_t, int type);
 #endif
 
+struct nsproxy;
+struct proc_ns_operations {
+	const char *name;
+	int type;
+	void *(*get)(struct task_struct *task);
+	void (*put)(void *ns);
+	int (*install)(struct nsproxy *nsproxy, void *ns);
+};
+extern const struct proc_ns_operations netns_operations;
+extern const struct proc_ns_operations utsns_operations;
+extern const struct proc_ns_operations ipcns_operations;
+
 union proc_op {
 	int (*proc_get_link)(struct inode *, struct path *);
 	int (*proc_read)(struct task_struct *task, char *page);
@@ -270,6 +289,8 @@ struct proc_inode {
 	struct proc_dir_entry *pde;
 	struct ctl_table_header *sysctl;
 	struct ctl_table *sysctl_entry;
+	void *ns;
+	const struct proc_ns_operations *ns_ops;
 	struct inode vfs_inode;
 };
 
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index ab71447d0c5..8c03b98df5f 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -846,4 +846,5 @@ asmlinkage long sys_name_to_handle_at(int dfd, const char __user *name,
 asmlinkage long sys_open_by_handle_at(int mountdirfd,
 				      struct file_handle __user *handle,
 				      int flags);
+asmlinkage long sys_setns(int fd, int nstype);
 #endif
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 3ae491932bc..dcc8f5749d3 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -119,6 +119,7 @@ static inline struct net *copy_net_ns(unsigned long flags, struct net *net_ns)
 extern struct list_head net_namespace_list;
 
 extern struct net *get_net_ns_by_pid(pid_t pid);
+extern struct net *get_net_ns_by_fd(int pid);
 
 #ifdef CONFIG_NET_NS
 extern void __put_net(struct net *net);
diff --git a/include/xen/interface/xen.h b/include/xen/interface/xen.h
index b33257bc7e8..70213b4515e 100644
--- a/include/xen/interface/xen.h
+++ b/include/xen/interface/xen.h
@@ -58,6 +58,7 @@
 #define __HYPERVISOR_event_channel_op     32
 #define __HYPERVISOR_physdev_op           33
 #define __HYPERVISOR_hvm_op               34
+#define __HYPERVISOR_tmem_op              38
 
 /* Architecture-specific hypercall definitions. */
 #define __HYPERVISOR_arch_0               48
@@ -461,6 +462,27 @@ typedef uint8_t xen_domain_handle_t[16];
 #define __mk_unsigned_long(x) x ## UL
 #define mk_unsigned_long(x) __mk_unsigned_long(x)
 
+#define TMEM_SPEC_VERSION 1
+
+struct tmem_op {
+	uint32_t cmd;
+	int32_t pool_id;
+	union {
+		struct {  /* for cmd == TMEM_NEW_POOL */
+			uint64_t uuid[2];
+			uint32_t flags;
+		} new;
+		struct {
+			uint64_t oid[3];
+			uint32_t index;
+			uint32_t tmem_offset;
+			uint32_t pfn_offset;
+			uint32_t len;
+			GUEST_HANDLE(void) gmfn; /* guest machine page frame */
+		} gen;
+	} u;
+};
+
 #else /* __ASSEMBLY__ */
 
 /* In assembly code we cannot use C numeric constant suffixes. */