Merge branch 'akpm-current/current'

Conflicts:
	mm/fremap.c

174 files changed, 2846 insertions, 846 deletions

diff --git a/Documentation/devicetree/bindings/i2c/trivial-devices.txt b/Documentation/devicetree/bindings/i2c/trivial-devices.txt
index 9f4e3824e71..4b95aca6e6d 100644
--- a/Documentation/devicetree/bindings/i2c/trivial-devices.txt
+++ b/Documentation/devicetree/bindings/i2c/trivial-devices.txt
@@ -58,7 +58,7 @@ fsl,sgtl5000		SGTL5000: Ultra Low-Power Audio Codec
 gmt,g751		G751: Digital Temperature Sensor and Thermal Watchdog with Two-Wire Interface
 infineon,slb9635tt	Infineon SLB9635 (Soft-) I2C TPM (old protocol, max 100khz)
 infineon,slb9645tt	Infineon SLB9645 I2C TPM (new protocol, max 400khz)
-isl,isl12057		Intersil ISL12057 I2C RTC Chip
+isl,isl12057		Intersil ISL12057 I2C RTC/Alarm Chip
 isil,isl29028           (deprecated, use isl)
 isl,isl29028            Intersil ISL29028 Ambient Light and Proximity Sensor
 maxim,ds1050		5 Bit Programmable, Pulse-Width Modulator
diff --git a/Documentation/filesystems/vfat.txt b/Documentation/filesystems/vfat.txt
index ce1126aceed..223c32171dc 100644
--- a/Documentation/filesystems/vfat.txt
+++ b/Documentation/filesystems/vfat.txt
@@ -180,6 +180,16 @@ dos1xfloppy  -- If set, use a fallback default BIOS Parameter Block
 
 <bool>: 0,1,yes,no,true,false
 
+LIMITATION
+---------------------------------------------------------------------
+* The fallocated region of file is discarded at umount/evict time
+  when using fallocate with FALLOC_FL_KEEP_SIZE.
+  So, User should assume that fallocated region can be discarded at
+  last close if there is memory pressure resulting in eviction of
+  the inode from the memory. As a result, for any dependency on
+  the fallocated region, user should make sure to recheck fallocate
+  after reopening the file.
+
 TODO
 ----------------------------------------------------------------------
 * Need to get rid of the raw scanning stuff.  Instead, always use
diff --git a/Documentation/leds/leds-class.txt b/Documentation/leds/leds-class.txt
index 79699c20076..62261c04060 100644
--- a/Documentation/leds/leds-class.txt
+++ b/Documentation/leds/leds-class.txt
@@ -2,9 +2,6 @@
 LED handling under Linux
 ========================
 
-If you're reading this and thinking about keyboard leds, these are
-handled by the input subsystem and the led class is *not* needed.
-
 In its simplest form, the LED class just allows control of LEDs from
 userspace. LEDs appear in /sys/class/leds/. The maximum brightness of the
 LED is defined in max_brightness file. The brightness file will set the brightness
diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt
index 5a615c14f75..8858db8f880 100644
--- a/Documentation/printk-formats.txt
+++ b/Documentation/printk-formats.txt
@@ -216,6 +216,12 @@ dentry names:
 	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.
 
+task_struct comm name:
+
+        %pT
+
+        For printing task_struct->comm.
+
 struct va_format:
 
 	%pV
diff --git a/Documentation/vm/remap_file_pages.txt b/Documentation/vm/remap_file_pages.txt
index 560e4363a55..f609142f406 100644
--- a/Documentation/vm/remap_file_pages.txt
+++ b/Documentation/vm/remap_file_pages.txt
@@ -18,10 +18,9 @@ on 32-bit systems to map files bigger than can linearly fit into 32-bit
 virtual address space. This use-case is not critical anymore since 64-bit
 systems are widely available.
 
-The plan is to deprecate the syscall and replace it with an emulation.
-The emulation will create new VMAs instead of nonlinear mappings. It's
-going to work slower for rare users of remap_file_pages() but ABI is
-preserved.
+The syscall is deprecated and replaced it with an emulation now. The
+emulation creates new VMAs instead of nonlinear mappings. It's going to
+work slower for rare users of remap_file_pages() but ABI is preserved.
 
 One side effect of emulation (apart from performance) is that user can hit
 vm.max_map_count limit more easily due to additional VMAs. See comment for
diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h
index 48bbea6898b..d5b98ab514b 100644
--- a/arch/alpha/include/asm/thread_info.h
+++ b/arch/alpha/include/asm/thread_info.h
@@ -27,8 +27,6 @@ struct thread_info {
 	int bpt_nsaved;
 	unsigned long bpt_addr[2];		/* breakpoint handling  */
 	unsigned int bpt_insn[2];
-
-	struct restart_block	restart_block;
 };
 
 /*
@@ -40,9 +38,6 @@ struct thread_info {
 	.exec_domain	= &default_exec_domain,	\
 	.addr_limit	= KERNEL_DS,		\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h
index 0086b472bc2..836fbd44f65 100644
--- a/arch/alpha/include/uapi/asm/mman.h
+++ b/arch/alpha/include/uapi/asm/mman.h
@@ -44,6 +44,7 @@
 #define MADV_WILLNEED	3		/* will need these pages */
 #define	MADV_SPACEAVAIL	5		/* ensure resources are available */
 #define MADV_DONTNEED	6		/* don't need these pages */
+#define MADV_FREE	7		/* free pages only if memory pressure */
 
 /* common/generic parameters */
 #define MADV_REMOVE	9		/* remove these pages & resources */
diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c
index 6cec2881acb..8dbfb15f174 100644
--- a/arch/alpha/kernel/signal.c
+++ b/arch/alpha/kernel/signal.c
@@ -150,7 +150,7 @@ restore_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs)
 	struct switch_stack *sw = (struct switch_stack *)regs - 1;
 	long i, err = __get_user(regs->pc, &sc->sc_pc);
 
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	sw->r26 = (unsigned long) ret_from_sys_call;
 
diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h
index 02bc5ec0fb2..1163a1838ac 100644
--- a/arch/arc/include/asm/thread_info.h
+++ b/arch/arc/include/asm/thread_info.h
@@ -46,7 +46,6 @@ struct thread_info {
 	struct exec_domain *exec_domain;/* execution domain */
 	__u32 cpu;			/* current CPU */
 	unsigned long thr_ptr;		/* TLS ptr */
-	struct restart_block restart_block;
 };
 
 /*
@@ -62,9 +61,6 @@ struct thread_info {
 	.cpu        = 0,			\
 	.preempt_count  = INIT_PREEMPT_COUNT,	\
 	.addr_limit = KERNEL_DS,		\
-	.restart_block  = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info    (init_thread_union.thread_info)
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index cb3142a2d40..114234e83ca 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -104,7 +104,7 @@ SYSCALL_DEFINE0(rt_sigreturn)
 	struct pt_regs *regs = current_pt_regs();
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/* Since we stacked the signal on a word boundary,
 	 * then 'sp' should be word aligned here.  If it's
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index a31ecdad4b5..54dc91486c1 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -249,6 +249,7 @@ PMD_BIT_FUNC(mkold,	&= ~PMD_SECT_AF);
 PMD_BIT_FUNC(mksplitting, |= L_PMD_SECT_SPLITTING);
 PMD_BIT_FUNC(mkwrite,   &= ~L_PMD_SECT_RDONLY);
 PMD_BIT_FUNC(mkdirty,   |= L_PMD_SECT_DIRTY);
+PMD_BIT_FUNC(mkclean,   &= ~L_PMD_SECT_DIRTY);
 PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
 
 #define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index d890e41f552..72812a1f3d1 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -68,7 +68,6 @@ struct thread_info {
 #ifdef CONFIG_ARM_THUMBEE
 	unsigned long		thumbee_state;	/* ThumbEE Handler Base register */
 #endif
-	struct restart_block	restart_block;
 };
 
 #define INIT_THREAD_INFO(tsk)						\
@@ -81,9 +80,6 @@ struct thread_info {
 	.cpu_domain	= domain_val(DOMAIN_USER, DOMAIN_MANAGER) |	\
 			  domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) |	\
 			  domain_val(DOMAIN_IO, DOMAIN_CLIENT),		\
-	.restart_block	= {						\
-		.fn	= do_no_restart_syscall,			\
-	},								\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 8aa6f1b87c9..023ac905e4c 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -191,7 +191,7 @@ asmlinkage int sys_sigreturn(struct pt_regs *regs)
 	struct sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Since we stacked the signal on a 64-bit boundary,
@@ -221,7 +221,7 @@ asmlinkage int sys_rt_sigreturn(struct pt_regs *regs)
 	struct rt_sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Since we stacked the signal on a 64-bit boundary,
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index df22314f57c..22e6157fe8d 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -281,10 +281,12 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
 
 #define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
+#define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
 #define pmd_mksplitting(pmd)	pte_pmd(pte_mkspecial(pmd_pte(pmd)))
 #define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
 #define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
+#define pmd_mkclean(pmd)	pte_pmd(pte_mkclean(pmd_pte(pmd)))
 #define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
 #define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
 #define pmd_mknotpresent(pmd)	(__pmd(pmd_val(pmd) & ~PMD_TYPE_MASK))
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 459bf8e5320..702e1e6a0d8 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -48,7 +48,6 @@ struct thread_info {
 	mm_segment_t		addr_limit;	/* address limit */
 	struct task_struct	*task;		/* main task structure */
 	struct exec_domain	*exec_domain;	/* execution domain */
-	struct restart_block	restart_block;
 	int			preempt_count;	/* 0 => preemptable, <0 => bug */
 	int			cpu;		/* cpu */
 };
@@ -60,9 +59,6 @@ struct thread_info {
 	.flags		= 0,						\
 	.preempt_count	= INIT_PREEMPT_COUNT,				\
 	.addr_limit	= KERNEL_DS,					\
-	.restart_block	= {						\
-		.fn	= do_no_restart_syscall,			\
-	},								\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 6fa792137ed..660ccf9f752 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -131,7 +131,7 @@ asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
 	struct rt_sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Since we stacked the signal on a 128-bit boundary, then 'sp' should
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 5a1ba6e80d4..64565c4ecbb 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -347,7 +347,7 @@ asmlinkage int compat_sys_sigreturn(struct pt_regs *regs)
 	struct compat_sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Since we stacked the signal on a 64-bit boundary,
@@ -381,7 +381,7 @@ asmlinkage int compat_sys_rt_sigreturn(struct pt_regs *regs)
 	struct compat_rt_sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Since we stacked the signal on a 64-bit boundary,
diff --git a/arch/avr32/include/asm/thread_info.h b/arch/avr32/include/asm/thread_info.h
index a978f3fe7c2..d56afa99a51 100644
--- a/arch/avr32/include/asm/thread_info.h
+++ b/arch/avr32/include/asm/thread_info.h
@@ -30,7 +30,6 @@ struct thread_info {
 						   saved by debug handler
 						   when setting up
 						   trampoline */
-	struct restart_block	restart_block;
 	__u8			supervisor_stack[0];
 };
 
@@ -41,9 +40,6 @@ struct thread_info {
 	.flags		= 0,						\
 	.cpu		= 0,						\
 	.preempt_count	= INIT_PREEMPT_COUNT,				\
-	.restart_block	= {						\
-		.fn	= do_no_restart_syscall				\
-	}								\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/avr32/kernel/asm-offsets.c b/arch/avr32/kernel/asm-offsets.c
index d6a8193a1d2..e41c84516e5 100644
--- a/arch/avr32/kernel/asm-offsets.c
+++ b/arch/avr32/kernel/asm-offsets.c
@@ -18,7 +18,6 @@ void foo(void)
 	OFFSET(TI_preempt_count, thread_info, preempt_count);
 	OFFSET(TI_rar_saved, thread_info, rar_saved);
 	OFFSET(TI_rsr_saved, thread_info, rsr_saved);
-	OFFSET(TI_restart_block, thread_info, restart_block);
 	BLANK();
 	OFFSET(TSK_active_mm, task_struct, active_mm);
 	BLANK();
diff --git a/arch/avr32/kernel/signal.c b/arch/avr32/kernel/signal.c
index d309fbcc3bd..8f1c63b9b98 100644
--- a/arch/avr32/kernel/signal.c
+++ b/arch/avr32/kernel/signal.c
@@ -69,7 +69,7 @@ asmlinkage int sys_rt_sigreturn(struct pt_regs *regs)
 	sigset_t set;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	frame = (struct rt_sigframe __user *)regs->sp;
 	pr_debug("SIG return: frame = %p\n", frame);
diff --git a/arch/blackfin/include/asm/thread_info.h b/arch/blackfin/include/asm/thread_info.h
index 55f473bdad3..57c3a8bd583 100644
--- a/arch/blackfin/include/asm/thread_info.h
+++ b/arch/blackfin/include/asm/thread_info.h
@@ -42,7 +42,6 @@ struct thread_info {
 	int cpu;		/* cpu we're on */
 	int preempt_count;	/* 0 => preemptable, <0 => BUG */
 	mm_segment_t addr_limit;	/* address limit */
-	struct restart_block restart_block;
 #ifndef CONFIG_SMP
 	struct l1_scratch_task_info l1_task_info;
 #endif
@@ -58,9 +57,6 @@ struct thread_info {
 	.flags		= 0,			\
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 #define init_thread_info	(init_thread_union.thread_info)
 #define init_stack		(init_thread_union.stack)
diff --git a/arch/blackfin/kernel/signal.c b/arch/blackfin/kernel/signal.c
index ef275571d88..f2a8b5493bd 100644
--- a/arch/blackfin/kernel/signal.c
+++ b/arch/blackfin/kernel/signal.c
@@ -44,7 +44,7 @@ rt_restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, int *p
 	int err = 0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 #define RESTORE(x) err |= __get_user(regs->x, &sc->sc_##x)
 
diff --git a/arch/c6x/include/asm/thread_info.h b/arch/c6x/include/asm/thread_info.h
index d4e9ef87076..584e253f321 100644
--- a/arch/c6x/include/asm/thread_info.h
+++ b/arch/c6x/include/asm/thread_info.h
@@ -45,7 +45,6 @@ struct thread_info {
 	int			cpu;		/* cpu we're on */
 	int			preempt_count;	/* 0 = preemptable, <0 = BUG */
 	mm_segment_t		addr_limit;	/* thread address space */
-	struct restart_block	restart_block;
 };
 
 /*
@@ -61,9 +60,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/c6x/kernel/signal.c b/arch/c6x/kernel/signal.c
index fe68226f6c4..3c4bb5a5c38 100644
--- a/arch/c6x/kernel/signal.c
+++ b/arch/c6x/kernel/signal.c
@@ -68,7 +68,7 @@ asmlinkage int do_rt_sigreturn(struct pt_regs *regs)
 	sigset_t set;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Since we stacked the signal on a dword boundary,
diff --git a/arch/cris/arch-v10/kernel/signal.c b/arch/cris/arch-v10/kernel/signal.c
index 9b32d338838..74d7ba35120 100644
--- a/arch/cris/arch-v10/kernel/signal.c
+++ b/arch/cris/arch-v10/kernel/signal.c
@@ -67,7 +67,7 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 	unsigned long old_usp;
 
         /* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/* restore the regs from &sc->regs (same as sc, since regs is first)
 	 * (sc is already checked for VERIFY_READ since the sigframe was
diff --git a/arch/cris/arch-v32/kernel/signal.c b/arch/cris/arch-v32/kernel/signal.c
index 78ce3b1c9bc..870e3e06931 100644
--- a/arch/cris/arch-v32/kernel/signal.c
+++ b/arch/cris/arch-v32/kernel/signal.c
@@ -59,7 +59,7 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 	unsigned long old_usp;
 
         /* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Restore the registers from &sc->regs. sc is already checked
diff --git a/arch/cris/include/asm/thread_info.h b/arch/cris/include/asm/thread_info.h
index 55dede18c03..7286db5ed90 100644
--- a/arch/cris/include/asm/thread_info.h
+++ b/arch/cris/include/asm/thread_info.h
@@ -38,7 +38,6 @@ struct thread_info {
 					 	   0-0xBFFFFFFF for user-thead
 						   0-0xFFFFFFFF for kernel-thread
 						*/
-	struct restart_block    restart_block;
 	__u8			supervisor_stack[0];
 };
 
@@ -56,9 +55,6 @@ struct thread_info {
 	.cpu		= 0,				\
 	.preempt_count	= INIT_PREEMPT_COUNT,		\
 	.addr_limit	= KERNEL_DS,			\
-	.restart_block = {				\
-		       .fn = do_no_restart_syscall,	\
-	},						\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/frv/include/asm/thread_info.h b/arch/frv/include/asm/thread_info.h
index af29e17c018..6b917f1c295 100644
--- a/arch/frv/include/asm/thread_info.h
+++ b/arch/frv/include/asm/thread_info.h
@@ -41,7 +41,6 @@ struct thread_info {
 						 * 0-0xBFFFFFFF for user-thead
 						 * 0-0xFFFFFFFF for kernel-thread
 						 */
-	struct restart_block    restart_block;
 
 	__u8			supervisor_stack[0];
 };
@@ -65,9 +64,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/frv/kernel/asm-offsets.c b/arch/frv/kernel/asm-offsets.c
index 9de96843a27..446e89d500c 100644
--- a/arch/frv/kernel/asm-offsets.c
+++ b/arch/frv/kernel/asm-offsets.c
@@ -40,7 +40,6 @@ void foo(void)
 	OFFSET(TI_CPU,			thread_info, cpu);
 	OFFSET(TI_PREEMPT_COUNT,	thread_info, preempt_count);
 	OFFSET(TI_ADDR_LIMIT,		thread_info, addr_limit);
-	OFFSET(TI_RESTART_BLOCK,	thread_info, restart_block);
 	BLANK();
 
 	/* offsets into register file storage */
diff --git a/arch/frv/kernel/signal.c b/arch/frv/kernel/signal.c
index dc3d59de087..336713ab474 100644
--- a/arch/frv/kernel/signal.c
+++ b/arch/frv/kernel/signal.c
@@ -62,7 +62,7 @@ static int restore_sigcontext(struct sigcontext __user *sc, int *_gr8)
 	unsigned long tbr, psr;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	tbr = user->i.tbr;
 	psr = user->i.psr;
diff --git a/arch/hexagon/include/asm/thread_info.h b/arch/hexagon/include/asm/thread_info.h
index a59dad3b369..bacd3d6030c 100644
--- a/arch/hexagon/include/asm/thread_info.h
+++ b/arch/hexagon/include/asm/thread_info.h
@@ -56,7 +56,6 @@ struct thread_info {
 	 * used for syscalls somehow;
 	 * seems to have a function pointer and four arguments
 	 */
-	struct restart_block    restart_block;
 	/* Points to the current pt_regs frame  */
 	struct pt_regs		*regs;
 	/*
@@ -83,9 +82,6 @@ struct thread_info {
 	.cpu            = 0,                    \
 	.preempt_count  = 1,                    \
 	.addr_limit     = KERNEL_DS,            \
-	.restart_block = {                      \
-		.fn = do_no_restart_syscall,    \
-	},                                      \
 	.sp = 0,				\
 	.regs = NULL,			\
 }
diff --git a/arch/hexagon/kernel/signal.c b/arch/hexagon/kernel/signal.c
index eadd70e47e7..b039a624c17 100644
--- a/arch/hexagon/kernel/signal.c
+++ b/arch/hexagon/kernel/signal.c
@@ -239,7 +239,7 @@ asmlinkage int sys_rt_sigreturn(void)
 	sigset_t blocked;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	frame = (struct rt_sigframe __user *)pt_psp(regs);
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h
index 5b17418b422..c16f21a068f 100644
--- a/arch/ia64/include/asm/thread_info.h
+++ b/arch/ia64/include/asm/thread_info.h
@@ -27,7 +27,6 @@ struct thread_info {
 	__u32 status;			/* Thread synchronous flags */
 	mm_segment_t addr_limit;	/* user-level address space limit */
 	int preempt_count;		/* 0=premptable, <0=BUG; will also serve as bh-counter */
-	struct restart_block restart_block;
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	__u64 ac_stamp;
 	__u64 ac_leave;
@@ -46,9 +45,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.addr_limit	= KERNEL_DS,		\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #ifndef ASM_OFFSETS_C
diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c
index 6d92170be45..b3a124da71e 100644
--- a/arch/ia64/kernel/signal.c
+++ b/arch/ia64/kernel/signal.c
@@ -46,7 +46,7 @@ restore_sigcontext (struct sigcontext __user *sc, struct sigscratch *scr)
 	long err;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/* restore scratch that always needs gets updated during signal delivery: */
 	err  = __get_user(flags, &sc->sc_flags);
diff --git a/arch/m32r/include/asm/thread_info.h b/arch/m32r/include/asm/thread_info.h
index 00171703402..32422d0211c 100644
--- a/arch/m32r/include/asm/thread_info.h
+++ b/arch/m32r/include/asm/thread_info.h
@@ -34,7 +34,6 @@ struct thread_info {
 					 	   0-0xBFFFFFFF for user-thread
 						   0-0xFFFFFFFF for kernel-thread
 						*/
-	struct restart_block    restart_block;
 
 	__u8			supervisor_stack[0];
 };
@@ -49,7 +48,6 @@ struct thread_info {
 #define TI_CPU		0x00000010
 #define TI_PRE_COUNT	0x00000014
 #define TI_ADDR_LIMIT	0x00000018
-#define TI_RESTART_BLOCK 0x000001C
 
 #endif
 
@@ -68,9 +66,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/m32r/kernel/signal.c b/arch/m32r/kernel/signal.c
index 95408b8f130..7736c6660a1 100644
--- a/arch/m32r/kernel/signal.c
+++ b/arch/m32r/kernel/signal.c
@@ -48,7 +48,7 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 	unsigned int err = 0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 #define COPY(x)		err |= __get_user(regs->x, &sc->sc_##x)
 	COPY(r4);
diff --git a/arch/m68k/include/asm/thread_info.h b/arch/m68k/include/asm/thread_info.h
index 21a4784ca5a..c54256e69e6 100644
--- a/arch/m68k/include/asm/thread_info.h
+++ b/arch/m68k/include/asm/thread_info.h
@@ -31,7 +31,6 @@ struct thread_info {
 	int			preempt_count;	/* 0 => preemptable, <0 => BUG */
 	__u32			cpu;		/* should always be 0 on m68k */
 	unsigned long		tp_value;	/* thread pointer */
-	struct restart_block    restart_block;
 };
 #endif /* __ASSEMBLY__ */
 
@@ -41,9 +40,6 @@ struct thread_info {
 	.exec_domain	= &default_exec_domain,	\
 	.addr_limit	= KERNEL_DS,		\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_stack		(init_thread_union.stack)
diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c
index 967a8b7e152..d7179281e74 100644
--- a/arch/m68k/kernel/signal.c
+++ b/arch/m68k/kernel/signal.c
@@ -655,7 +655,7 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *usc, void __u
 	int err = 0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/* get previous context */
 	if (copy_from_user(&context, usc, sizeof(context)))
@@ -693,7 +693,7 @@ rt_restore_ucontext(struct pt_regs *regs, struct switch_stack *sw,
 	int err;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	err = __get_user(temp, &uc->uc_mcontext.version);
 	if (temp != MCONTEXT_VERSION)
diff --git a/arch/metag/include/asm/thread_info.h b/arch/metag/include/asm/thread_info.h
index 47711336119..afb3ca4776d 100644
--- a/arch/metag/include/asm/thread_info.h
+++ b/arch/metag/include/asm/thread_info.h
@@ -35,9 +35,8 @@ struct thread_info {
 	int preempt_count;	/* 0 => preemptable, <0 => BUG */
 
 	mm_segment_t addr_limit;	/* thread address space */
-	struct restart_block restart_block;
 
-	u8 supervisor_stack[0];
+	u8 supervisor_stack[0] __aligned(8);
 };
 
 #else /* !__ASSEMBLY__ */
@@ -74,9 +73,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/metag/kernel/signal.c b/arch/metag/kernel/signal.c
index 0d100d5c140..ce49d429c74 100644
--- a/arch/metag/kernel/signal.c
+++ b/arch/metag/kernel/signal.c
@@ -48,7 +48,7 @@ static int restore_sigcontext(struct pt_regs *regs,
 	int err;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	err = metag_gp_regs_copyin(regs, 0, sizeof(struct user_gp_regs), NULL,
 				   &sc->regs);
diff --git a/arch/microblaze/include/asm/thread_info.h b/arch/microblaze/include/asm/thread_info.h
index 8c9d36591a0..b699fbd7de4 100644
--- a/arch/microblaze/include/asm/thread_info.h
+++ b/arch/microblaze/include/asm/thread_info.h
@@ -71,7 +71,6 @@ struct thread_info {
 	__u32			cpu; /* current CPU */
 	__s32			preempt_count; /* 0 => preemptable,< 0 => BUG*/
 	mm_segment_t		addr_limit; /* thread address space */
-	struct restart_block	restart_block;
 
 	struct cpu_context	cpu_context;
 };
@@ -87,9 +86,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/microblaze/kernel/signal.c b/arch/microblaze/kernel/signal.c
index 8955a3829cf..0245c27fa72 100644
--- a/arch/microblaze/kernel/signal.c
+++ b/arch/microblaze/kernel/signal.c
@@ -89,7 +89,7 @@ asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
 	int rval;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index 99eea59604e..75a8c55d3dc 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -34,7 +34,6 @@ struct thread_info {
 						 * 0x7fffffff for user-thead
 						 * 0xffffffff for kernel-thread
 						 */
-	struct restart_block	restart_block;
 	struct pt_regs		*regs;
 };
 
@@ -49,9 +48,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h
index cfcb876cae6..106e741aa7e 100644
--- a/arch/mips/include/uapi/asm/mman.h
+++ b/arch/mips/include/uapi/asm/mman.h
@@ -67,6 +67,7 @@
 #define MADV_SEQUENTIAL 2		/* expect sequential page references */
 #define MADV_WILLNEED	3		/* will need these pages */
 #define MADV_DONTNEED	4		/* don't need these pages */
+#define MADV_FREE	5		/* free pages only if memory pressure */
 
 /* common parameters: try to keep these consistent across architectures */
 #define MADV_REMOVE	9		/* remove these pages & resources */
diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c
index b1d84bd4efb..3b2dfdb4865 100644
--- a/arch/mips/kernel/asm-offsets.c
+++ b/arch/mips/kernel/asm-offsets.c
@@ -98,7 +98,6 @@ void output_thread_info_defines(void)
 	OFFSET(TI_CPU, thread_info, cpu);
 	OFFSET(TI_PRE_COUNT, thread_info, preempt_count);
 	OFFSET(TI_ADDR_LIMIT, thread_info, addr_limit);
-	OFFSET(TI_RESTART_BLOCK, thread_info, restart_block);
 	OFFSET(TI_REGS, thread_info, regs);
 	DEFINE(_THREAD_SIZE, THREAD_SIZE);
 	DEFINE(_THREAD_MASK, THREAD_MASK);
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index 545bf11bd2e..6a28c792d86 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -243,7 +243,7 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 	int i;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	err |= __get_user(regs->cp0_epc, &sc->sc_pc);
 
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index d69179c0d49..19a7705f2a0 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -220,7 +220,7 @@ static int restore_sigcontext32(struct pt_regs *regs,
 	int i;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	err |= __get_user(regs->cp0_epc, &sc->sc_pc);
 	err |= __get_user(regs->hi, &sc->sc_mdhi);
diff --git a/arch/mn10300/include/asm/thread_info.h b/arch/mn10300/include/asm/thread_info.h
index bf280eaccd3..c1c374f0ec1 100644
--- a/arch/mn10300/include/asm/thread_info.h
+++ b/arch/mn10300/include/asm/thread_info.h
@@ -50,7 +50,6 @@ struct thread_info {
 						   0-0xBFFFFFFF for user-thead
 						   0-0xFFFFFFFF for kernel-thread
 						*/
-	struct restart_block    restart_block;
 
 	__u8			supervisor_stack[0];
 };
@@ -80,9 +79,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/mn10300/kernel/asm-offsets.c b/arch/mn10300/kernel/asm-offsets.c
index 47b3bb0c04f..d780670cbaf 100644
--- a/arch/mn10300/kernel/asm-offsets.c
+++ b/arch/mn10300/kernel/asm-offsets.c
@@ -28,7 +28,6 @@ void foo(void)
 	OFFSET(TI_cpu,			thread_info, cpu);
 	OFFSET(TI_preempt_count,	thread_info, preempt_count);
 	OFFSET(TI_addr_limit,		thread_info, addr_limit);
-	OFFSET(TI_restart_block,	thread_info, restart_block);
 	BLANK();
 
 	OFFSET(REG_D0,			pt_regs, d0);
diff --git a/arch/mn10300/kernel/signal.c b/arch/mn10300/kernel/signal.c
index a6c0858592c..8609845f12c 100644
--- a/arch/mn10300/kernel/signal.c
+++ b/arch/mn10300/kernel/signal.c
@@ -40,7 +40,7 @@ static int restore_sigcontext(struct pt_regs *regs,
 	unsigned int err = 0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (is_using_fpu(current))
 		fpu_kill_state(current);
diff --git a/arch/openrisc/include/asm/thread_info.h b/arch/openrisc/include/asm/thread_info.h
index d797acc901e..875f0845a70 100644
--- a/arch/openrisc/include/asm/thread_info.h
+++ b/arch/openrisc/include/asm/thread_info.h
@@ -57,7 +57,6 @@ struct thread_info {
 					       0-0x7FFFFFFF for user-thead
 					       0-0xFFFFFFFF for kernel-thread
 					     */
-	struct restart_block    restart_block;
 	__u8			supervisor_stack[0];
 
 	/* saved context data */
@@ -79,9 +78,6 @@ struct thread_info {
 	.cpu		= 0,				\
 	.preempt_count	= 1,				\
 	.addr_limit	= KERNEL_DS,			\
-	.restart_block  = {				\
-			  .fn = do_no_restart_syscall,	\
-	},						\
 	.ksp            = 0,                            \
 }
 
diff --git a/arch/openrisc/kernel/signal.c b/arch/openrisc/kernel/signal.c
index 7d1b8235bf9..4112175bf80 100644
--- a/arch/openrisc/kernel/signal.c
+++ b/arch/openrisc/kernel/signal.c
@@ -46,7 +46,7 @@ static int restore_sigcontext(struct pt_regs *regs,
 	int err = 0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Restore the regs from &sc->regs.
diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h
index a8461183554..fb13e386556 100644
--- a/arch/parisc/include/asm/thread_info.h
+++ b/arch/parisc/include/asm/thread_info.h
@@ -14,7 +14,6 @@ struct thread_info {
 	mm_segment_t addr_limit;	/* user-level address space limit */
 	__u32 cpu;			/* current CPU */
 	int preempt_count;		/* 0=premptable, <0=BUG; will also serve as bh-counter */
-	struct restart_block restart_block;
 };
 
 #define INIT_THREAD_INFO(tsk)			\
@@ -25,9 +24,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.addr_limit	= KERNEL_DS,		\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
-  	.restart_block	= {			\
-		.fn = do_no_restart_syscall	\
-	}					\
 }
 
 #define init_thread_info        (init_thread_union.thread_info)
diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h
index 294d251ca7b..6cb8db76fd4 100644
--- a/arch/parisc/include/uapi/asm/mman.h
+++ b/arch/parisc/include/uapi/asm/mman.h
@@ -40,6 +40,7 @@
 #define MADV_SPACEAVAIL 5               /* insure that resources are reserved */
 #define MADV_VPS_PURGE  6               /* Purge pages from VM page cache */
 #define MADV_VPS_INHERIT 7              /* Inherit parents page size */
+#define MADV_FREE	8		/* free pages only if memory pressure */
 
 /* common/generic parameters */
 #define MADV_REMOVE	9		/* remove these pages & resources */
diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c
index 012d4fa63d9..9b910a0251b 100644
--- a/arch/parisc/kernel/signal.c
+++ b/arch/parisc/kernel/signal.c
@@ -99,7 +99,7 @@ sys_rt_sigreturn(struct pt_regs *regs, int in_syscall)
 		sigframe_size = PARISC_RT_SIGFRAME_SIZE32;
 #endif
 
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/* Unwind the user stack to get the rt_sigframe structure. */
 	frame = (struct rt_sigframe __user *)
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index b9dcc936e2d..ddf4e29fbd3 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -494,9 +494,11 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd)
 #define pmd_pfn(pmd)		pte_pfn(pmd_pte(pmd))
 #define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
+#define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
 #define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
 #define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
+#define pmd_mkclean(pmd)	pte_pmd(pte_mkclean(pmd_pte(pmd)))
 #define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
 #define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
 
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index ebc4f165690..06596aa4359 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -43,7 +43,6 @@ struct thread_info {
 	int		cpu;			/* cpu we're on */
 	int		preempt_count;		/* 0 => preemptable,
 						   <0 => BUG */
-	struct restart_block restart_block;
 	unsigned long	local_flags;		/* private flags for thread */
 
 	/* low level flags - has atomic operations done on it */
@@ -59,9 +58,6 @@ struct thread_info {
 	.exec_domain =	&default_exec_domain,	\
 	.cpu =		0,			\
 	.preempt_count = INIT_PREEMPT_COUNT,	\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 	.flags =	0,			\
 }
 
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index b171001698f..d3a831ac0f9 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -1231,7 +1231,7 @@ long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
 	int tm_restore = 0;
 #endif
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	rt_sf = (struct rt_sigframe __user *)
 		(regs->gpr[1] + __SIGNAL_FRAMESIZE + 16);
@@ -1504,7 +1504,7 @@ long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
 #endif
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	sf = (struct sigframe __user *)(regs->gpr[1] + __SIGNAL_FRAMESIZE);
 	sc = &sf->sctx;
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 2cb0c94cafa..c7c24d2e2bd 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -666,7 +666,7 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5,
 #endif
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (!access_ok(VERIFY_READ, uc, sizeof(*uc)))
 		goto badframe;
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 4d62fd5b56e..ef1df718642 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -39,7 +39,6 @@ struct thread_info {
 	unsigned long		sys_call_table;	/* System call table address */
 	unsigned int		cpu;		/* current CPU */
 	int			preempt_count;	/* 0 => preemptable, <0 => BUG */
-	struct restart_block	restart_block;
 	unsigned int		system_call;
 	__u64			user_timer;
 	__u64			system_timer;
@@ -56,9 +55,6 @@ struct thread_info {
 	.flags		= 0,			\
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index 34d5fa7b01b..bc1df12dd4f 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -209,7 +209,7 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs)
 	int i;
 
 	/* Alwys make any pending restarted system call return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (__copy_from_user(&user_sregs, &sregs->regs, sizeof(user_sregs)))
 		return -EFAULT;
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index 6a2ac257d98..b3ae6f70c6d 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -162,7 +162,7 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 	_sigregs user_sregs;
 
 	/* Alwys make any pending restarted system call return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (__copy_from_user(&user_sregs, sregs, sizeof(user_sregs)))
 		return -EFAULT;
diff --git a/arch/score/include/asm/thread_info.h b/arch/score/include/asm/thread_info.h
index 656b7ada932..33864fa2a8d 100644
--- a/arch/score/include/asm/thread_info.h
+++ b/arch/score/include/asm/thread_info.h
@@ -42,7 +42,6 @@ struct thread_info {
 	 * 0-0xFFFFFFFF for kernel-thread
 	 */
 	mm_segment_t		addr_limit;
-	struct restart_block	restart_block;
 	struct pt_regs		*regs;
 };
 
@@ -58,9 +57,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= 1,			\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/score/kernel/asm-offsets.c b/arch/score/kernel/asm-offsets.c
index 57788f44c6f..b4d5214a7a7 100644
--- a/arch/score/kernel/asm-offsets.c
+++ b/arch/score/kernel/asm-offsets.c
@@ -106,7 +106,6 @@ void output_thread_info_defines(void)
 	OFFSET(TI_CPU, thread_info, cpu);
 	OFFSET(TI_PRE_COUNT, thread_info, preempt_count);
 	OFFSET(TI_ADDR_LIMIT, thread_info, addr_limit);
-	OFFSET(TI_RESTART_BLOCK, thread_info, restart_block);
 	OFFSET(TI_REGS, thread_info, regs);
 	DEFINE(KERNEL_STACK_SIZE, THREAD_SIZE);
 	DEFINE(KERNEL_STACK_MASK, THREAD_MASK);
diff --git a/arch/score/kernel/signal.c b/arch/score/kernel/signal.c
index 1651807774a..e381c8c4ff6 100644
--- a/arch/score/kernel/signal.c
+++ b/arch/score/kernel/signal.c
@@ -141,7 +141,7 @@ score_rt_sigreturn(struct pt_regs *regs)
 	int sig;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	frame = (struct rt_sigframe __user *) regs->regs[0];
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
diff --git a/arch/sh/include/asm/thread_info.h b/arch/sh/include/asm/thread_info.h
index ad27ffa65e2..657c0391962 100644
--- a/arch/sh/include/asm/thread_info.h
+++ b/arch/sh/include/asm/thread_info.h
@@ -33,7 +33,6 @@ struct thread_info {
 	__u32			cpu;
 	int			preempt_count; /* 0 => preemptable, <0 => BUG */
 	mm_segment_t		addr_limit;	/* thread address space */
-	struct restart_block	restart_block;
 	unsigned long		previous_sp;	/* sp of previous stack in case
 						   of nested IRQ stacks */
 	__u8			supervisor_stack[0];
@@ -63,9 +62,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/sh/kernel/asm-offsets.c b/arch/sh/kernel/asm-offsets.c
index 08a2be775b6..542225fedb1 100644
--- a/arch/sh/kernel/asm-offsets.c
+++ b/arch/sh/kernel/asm-offsets.c
@@ -25,7 +25,6 @@ int main(void)
 	DEFINE(TI_FLAGS,	offsetof(struct thread_info, flags));
 	DEFINE(TI_CPU,		offsetof(struct thread_info, cpu));
 	DEFINE(TI_PRE_COUNT,	offsetof(struct thread_info, preempt_count));
-	DEFINE(TI_RESTART_BLOCK,offsetof(struct thread_info, restart_block));
 	DEFINE(TI_SIZE,		sizeof(struct thread_info));
 
 #ifdef CONFIG_HIBERNATION
diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c
index 2f002b24fb9..0b34f2a704f 100644
--- a/arch/sh/kernel/signal_32.c
+++ b/arch/sh/kernel/signal_32.c
@@ -156,7 +156,7 @@ asmlinkage int sys_sigreturn(void)
 	int r0;
 
         /* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
@@ -186,7 +186,7 @@ asmlinkage int sys_rt_sigreturn(void)
 	int r0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
diff --git a/arch/sh/kernel/signal_64.c b/arch/sh/kernel/signal_64.c
index 897abe7b871..71993c6a7d9 100644
--- a/arch/sh/kernel/signal_64.c
+++ b/arch/sh/kernel/signal_64.c
@@ -260,7 +260,7 @@ asmlinkage int sys_sigreturn(unsigned long r2, unsigned long r3,
 	long long ret;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
@@ -294,7 +294,7 @@ asmlinkage int sys_rt_sigreturn(unsigned long r2, unsigned long r3,
 	long long ret;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 1ff9e786416..e890921d5a7 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -731,6 +731,15 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd)
 	return __pmd(pte_val(pte));
 }
 
+static inline pmd_t pmd_mkclean(pmd_t pmd)
+{
+	pte_t pte = __pte(pmd_val(pmd));
+
+	pte = pte_mkclean(pte);
+
+	return __pmd(pte_val(pte));
+}
+
 static inline pmd_t pmd_mkyoung(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
diff --git a/arch/sparc/include/asm/thread_info_32.h b/arch/sparc/include/asm/thread_info_32.h
index 025c98446b1..fd7bd0a440c 100644
--- a/arch/sparc/include/asm/thread_info_32.h
+++ b/arch/sparc/include/asm/thread_info_32.h
@@ -47,8 +47,6 @@ struct thread_info {
 	struct reg_window32	reg_window[NSWINS];	/* align for ldd! */
 	unsigned long		rwbuf_stkptrs[NSWINS];
 	unsigned long		w_saved;
-
-	struct restart_block	restart_block;
 };
 
 /*
@@ -62,9 +60,6 @@ struct thread_info {
 	.flags		=	0,			\
 	.cpu		=	0,			\
 	.preempt_count	=	INIT_PREEMPT_COUNT,	\
-	.restart_block	= {				\
-		.fn	=	do_no_restart_syscall,	\
-	},						\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
@@ -103,7 +98,6 @@ register struct thread_info *current_thread_info_reg asm("g6");
 #define TI_REG_WINDOW	0x30
 #define TI_RWIN_SPTRS	0x230
 #define TI_W_SAVED	0x250
-/* #define TI_RESTART_BLOCK 0x25n */ /* Nobody cares */
 
 /*
  * thread information flag bit numbers
diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index 798f0279a4b..ff455164732 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -58,8 +58,6 @@ struct thread_info {
 	unsigned long		gsr[7];
 	unsigned long		xfsr[7];
 
-	struct restart_block	restart_block;
-
 	struct pt_regs		*kern_una_regs;
 	unsigned int		kern_una_insn;
 
@@ -92,10 +90,9 @@ struct thread_info {
 #define TI_RWIN_SPTRS	0x000003c8
 #define TI_GSR		0x00000400
 #define TI_XFSR		0x00000438
-#define TI_RESTART_BLOCK 0x00000470
-#define TI_KUNA_REGS	0x000004a0
-#define TI_KUNA_INSN	0x000004a8
-#define TI_FPREGS	0x000004c0
+#define TI_KUNA_REGS	0x00000470
+#define TI_KUNA_INSN	0x00000478
+#define TI_FPREGS	0x00000480
 
 /* We embed this in the uppermost byte of thread_info->flags */
 #define FAULT_CODE_WRITE	0x01	/* Write access, implies D-TLB	   */
@@ -124,9 +121,6 @@ struct thread_info {
 	.current_ds	=	ASI_P,			\
 	.exec_domain	=	&default_exec_domain,	\
 	.preempt_count	=	INIT_PREEMPT_COUNT,	\
-	.restart_block	= {				\
-		.fn	=	do_no_restart_syscall,	\
-	},						\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index 62deba7be1a..4eed773a773 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -150,7 +150,7 @@ void do_sigreturn32(struct pt_regs *regs)
 	int err, i;
 	
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	synchronize_user_stack();
 
@@ -235,7 +235,7 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
 	int err, i;
 	
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	synchronize_user_stack();
 	regs->u_regs[UREG_FP] &= 0x00000000ffffffffUL;
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index 9ee72fc8e0e..52aa5e4ce5e 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -70,7 +70,7 @@ asmlinkage void do_sigreturn(struct pt_regs *regs)
 	int err;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	synchronize_user_stack();
 
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index 1a699986803..d88beff47ba 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -254,7 +254,7 @@ void do_rt_sigreturn(struct pt_regs *regs)
 	int err;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	synchronize_user_stack ();
 	sf = (struct rt_signal_frame __user *)
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 981a769b955..a27651e866e 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -2730,8 +2730,6 @@ void __init trap_init(void)
 		     TI_NEW_CHILD != offsetof(struct thread_info, new_child) ||
 		     TI_CURRENT_DS != offsetof(struct thread_info,
 						current_ds) ||
-		     TI_RESTART_BLOCK != offsetof(struct thread_info,
-						  restart_block) ||
 		     TI_KUNA_REGS != offsetof(struct thread_info,
 					      kern_una_regs) ||
 		     TI_KUNA_INSN != offsetof(struct thread_info,
diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h
index 48e4fd0f38e..96c14c1430d 100644
--- a/arch/tile/include/asm/thread_info.h
+++ b/arch/tile/include/asm/thread_info.h
@@ -36,7 +36,6 @@ struct thread_info {
 
 	mm_segment_t		addr_limit;	/* thread address space
 						   (KERNEL_DS or USER_DS) */
-	struct restart_block	restart_block;
 	struct single_step_state *step_state;	/* single step state
 						   (if non-zero) */
 	int			align_ctl;	/* controls unaligned access */
@@ -57,9 +56,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 	.step_state	= NULL,			\
 	.align_ctl	= 0,			\
 }
diff --git a/arch/tile/kernel/signal.c b/arch/tile/kernel/signal.c
index bb0a9ce7ae2..8a524e332c1 100644
--- a/arch/tile/kernel/signal.c
+++ b/arch/tile/kernel/signal.c
@@ -48,7 +48,7 @@ int restore_sigcontext(struct pt_regs *regs,
 	int err;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Enforce that sigcontext is like pt_regs, and doesn't mess
diff --git a/arch/um/include/asm/thread_info.h b/arch/um/include/asm/thread_info.h
index 1c5b2a83046..e04114c4fcd 100644
--- a/arch/um/include/asm/thread_info.h
+++ b/arch/um/include/asm/thread_info.h
@@ -22,7 +22,6 @@ struct thread_info {
 	mm_segment_t		addr_limit;	/* thread address space:
 					 	   0-0xBFFFFFFF for user
 						   0-0xFFFFFFFF for kernel */
-	struct restart_block    restart_block;
 	struct thread_info	*real_thread;    /* Points to non-IRQ stack */
 };
 
@@ -34,9 +33,6 @@ struct thread_info {
 	.cpu =		0,			\
 	.preempt_count = INIT_PREEMPT_COUNT,	\
 	.addr_limit =	KERNEL_DS,		\
-	.restart_block =  {			\
-		.fn =  do_no_restart_syscall,	\
-	},					\
 	.real_thread = NULL,			\
 }
 
diff --git a/arch/unicore32/include/asm/thread_info.h b/arch/unicore32/include/asm/thread_info.h
index af36d8eabdf..63e2839dfeb 100644
--- a/arch/unicore32/include/asm/thread_info.h
+++ b/arch/unicore32/include/asm/thread_info.h
@@ -79,7 +79,6 @@ struct thread_info {
 #ifdef CONFIG_UNICORE_FPU_F64
 	struct fp_state		fpstate __attribute__((aligned(8)));
 #endif
-	struct restart_block	restart_block;
 };
 
 #define INIT_THREAD_INFO(tsk)						\
@@ -89,9 +88,6 @@ struct thread_info {
 	.flags		= 0,						\
 	.preempt_count	= INIT_PREEMPT_COUNT,				\
 	.addr_limit	= KERNEL_DS,					\
-	.restart_block	= {						\
-		.fn	= do_no_restart_syscall,			\
-	},								\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/unicore32/kernel/signal.c b/arch/unicore32/kernel/signal.c
index 7c8fb7018dc..d329f85766c 100644
--- a/arch/unicore32/kernel/signal.c
+++ b/arch/unicore32/kernel/signal.c
@@ -105,7 +105,7 @@ asmlinkage int __sys_rt_sigreturn(struct pt_regs *regs)
 	struct rt_sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	/*
 	 * Since we stacked the signal on a 64-bit boundary,
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index f9e181aaba9..d0165c9a293 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -169,7 +169,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 	u32 tmp;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	get_user_try {
 		/*
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index e8a5454acc9..5e105ca5de5 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -278,6 +278,11 @@ static inline pmd_t pmd_mkold(pmd_t pmd)
 	return pmd_clear_flags(pmd, _PAGE_ACCESSED);
 }
 
+static inline pmd_t pmd_mkclean(pmd_t pmd)
+{
+	return pmd_clear_flags(pmd, _PAGE_DIRTY);
+}
+
 static inline pmd_t pmd_wrprotect(pmd_t pmd)
 {
 	return pmd_clear_flags(pmd, _PAGE_RW);
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 547e344a6dc..8550f2427d5 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -31,7 +31,6 @@ struct thread_info {
 	__u32			cpu;		/* current CPU */
 	int			saved_preempt_count;
 	mm_segment_t		addr_limit;
-	struct restart_block    restart_block;
 	void __user		*sysenter_return;
 	unsigned int		sig_on_uaccess_error:1;
 	unsigned int		uaccess_err:1;	/* uaccess failed */
@@ -45,9 +44,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.saved_preempt_count = INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 485981059a4..47cc835cec5 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -334,6 +334,7 @@ void arch_crash_save_vmcoreinfo(void)
 #endif
 	vmcoreinfo_append_str("KERNELOFFSET=%lx\n",
 			      (unsigned long)&_text - __START_KERNEL);
+	VMCOREINFO_PHYS_BASE(phys_base);
 }
 
 /* arch-dependent functionality related to kexec file-based syscall */
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index ed37a768d0f..0a62df4abcf 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -69,7 +69,7 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 	unsigned int err = 0;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	get_user_try {
 
diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c
index 79d824551c1..0c8c32bfd79 100644
--- a/arch/x86/um/signal.c
+++ b/arch/x86/um/signal.c
@@ -157,7 +157,7 @@ static int copy_sc_from_user(struct pt_regs *regs,
 	int err, pid;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	err = copy_from_user(&sc, from, sizeof(sc));
 	if (err)
diff --git a/arch/xtensa/include/asm/thread_info.h b/arch/xtensa/include/asm/thread_info.h
index 470153e8547..a9b5d3ba196 100644
--- a/arch/xtensa/include/asm/thread_info.h
+++ b/arch/xtensa/include/asm/thread_info.h
@@ -51,7 +51,6 @@ struct thread_info {
 	__s32			preempt_count;	/* 0 => preemptable,< 0 => BUG*/
 
 	mm_segment_t		addr_limit;	/* thread address space */
-	struct restart_block    restart_block;
 
 	unsigned long		cpenable;
 
@@ -72,7 +71,6 @@ struct thread_info {
 #define TI_CPU		 0x00000010
 #define TI_PRE_COUNT	 0x00000014
 #define TI_ADDR_LIMIT	 0x00000018
-#define TI_RESTART_BLOCK 0x000001C
 
 #endif
 
@@ -90,9 +88,6 @@ struct thread_info {
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h
index 201aec0e044..1b19f25bc56 100644
--- a/arch/xtensa/include/uapi/asm/mman.h
+++ b/arch/xtensa/include/uapi/asm/mman.h
@@ -80,6 +80,7 @@
 #define MADV_SEQUENTIAL	2		/* expect sequential page references */
 #define MADV_WILLNEED	3		/* will need these pages */
 #define MADV_DONTNEED	4		/* don't need these pages */
+#define MADV_FREE	5		/* free pages only if memory pressure */
 
 /* common parameters: try to keep these consistent across architectures */
 #define MADV_REMOVE	9		/* remove these pages & resources */
diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c
index 4612321c73c..3d733ba16f2 100644
--- a/arch/xtensa/kernel/signal.c
+++ b/arch/xtensa/kernel/signal.c
@@ -245,7 +245,7 @@ asmlinkage long xtensa_rt_sigreturn(long a0, long a1, long a2, long a3,
 	int ret;
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (regs->depc > 64)
 		panic("rt_sigreturn in double exception!\n");
diff --git a/block/genhd.c b/block/genhd.c
index 0a536dc05f3..64600e911aa 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -850,7 +850,7 @@ static int show_partition(struct seq_file *seqf, void *v)
 	char buf[BDEVNAME_SIZE];
 
 	/* Don't show non-partitionable removeable devices or empty devices */
-	if (!get_capacity(sgp) || (!disk_max_parts(sgp) &&
+	if (!get_capacity(sgp) || (!(disk_max_parts(sgp) > 1) &&
 				   (sgp->flags & GENHD_FL_REMOVABLE)))
 		return 0;
 	if (sgp->flags & GENHD_FL_SUPPRESS_PARTITION_INFO)
diff --git a/drivers/input/Kconfig b/drivers/input/Kconfig
index a11ff74a512..9eac8de9e8b 100644
--- a/drivers/input/Kconfig
+++ b/drivers/input/Kconfig
@@ -178,6 +178,15 @@ comment "Input Device Drivers"
 
 source "drivers/input/keyboard/Kconfig"
 
+config INPUT_LEDS
+	bool "LED Support"
+	depends on LEDS_CLASS = INPUT || LEDS_CLASS = y
+	select LEDS_TRIGGERS
+	default y
+	help
+	  This option enables support for LEDs on keyboards managed
+	  by the input layer.
+
 source "drivers/input/mouse/Kconfig"
 
 source "drivers/input/joystick/Kconfig"
diff --git a/drivers/input/Makefile b/drivers/input/Makefile
index 5ca3f631497..2ab5f3336da 100644
--- a/drivers/input/Makefile
+++ b/drivers/input/Makefile
@@ -6,6 +6,9 @@
 
 obj-$(CONFIG_INPUT)		+= input-core.o
 input-core-y := input.o input-compat.o input-mt.o ff-core.o
+ifeq ($(CONFIG_INPUT_LEDS),y)
+input-core-y += leds.o
+endif
 
 obj-$(CONFIG_INPUT_FF_MEMLESS)	+= ff-memless.o
 obj-$(CONFIG_INPUT_POLLDEV)	+= input-polldev.o
diff --git a/drivers/input/input.c b/drivers/input/input.c
index 213e3a1903e..a1e609a6522 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -711,6 +711,9 @@ static void input_disconnect_device(struct input_dev *dev)
 		handle->open = 0;
 
 	spin_unlock_irq(&dev->event_lock);
+
+	if (is_event_supported(EV_LED, dev->evbit, EV_MAX))
+		input_led_disconnect(dev);
 }
 
 /**
@@ -2141,6 +2144,9 @@ int input_register_device(struct input_dev *dev)
 
 	list_add_tail(&dev->node, &input_dev_list);
 
+	if (is_event_supported(EV_LED, dev->evbit, EV_MAX))
+		input_led_connect(dev);
+
 	list_for_each_entry(handler, &input_handler_list, node)
 		input_attach_handler(dev, handler);
 
@@ -2426,6 +2432,8 @@ static int __init input_init(void)
 		goto fail2;
 	}
 
+	input_led_init();
+
 	return 0;
 
  fail2:	input_proc_exit();
@@ -2435,6 +2443,7 @@ static int __init input_init(void)
 
 static void __exit input_exit(void)
 {
+	input_led_exit();
 	input_proc_exit();
 	unregister_chrdev_region(MKDEV(INPUT_MAJOR, 0),
 				 INPUT_MAX_CHAR_DEVICES);
diff --git a/drivers/input/leds.c b/drivers/input/leds.c
new file mode 100644
index 00000000000..193ee2425db
--- /dev/null
+++ b/drivers/input/leds.c
@@ -0,0 +1,272 @@
+/*
+ * LED support for the input layer
+ *
+ * Copyright 2010-2014 Samuel Thibault <samuel.thibault@ens-lyon.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/leds.h>
+#include <linux/input.h>
+
+/*
+ * Keyboard LEDs are propagated by default like the following example:
+ *
+ * VT keyboard numlock trigger
+ * -> vt::numl VT LED
+ * -> vt-numl VT trigger
+ * -> per-device inputX::numl LED
+ *
+ * Userland can however choose the trigger for the vt::numl LED, or
+ * independently choose the trigger for any inputx::numl LED.
+ *
+ *
+ * VT LED classes and triggers are registered on-demand according to
+ * existing LED devices
+ */
+
+/* Handler for VT LEDs, just triggers the corresponding VT trigger. */
+static void vt_led_set(struct led_classdev *cdev,
+			  enum led_brightness brightness);
+static struct led_classdev vt_leds[LED_CNT] = {
+#define DEFINE_INPUT_LED(vt_led, nam, deftrig) \
+	[vt_led] = { \
+		.name = "vt::"nam, \
+		.max_brightness = 1, \
+		.brightness_set = vt_led_set, \
+		.default_trigger = deftrig, \
+	}
+/* Default triggers for the VT LEDs just correspond to the legacy
+ * usage. */
+	DEFINE_INPUT_LED(LED_NUML, "numl", "kbd-numlock"),
+	DEFINE_INPUT_LED(LED_CAPSL, "capsl", "kbd-capslock"),
+	DEFINE_INPUT_LED(LED_SCROLLL, "scrolll", "kbd-scrollock"),
+	DEFINE_INPUT_LED(LED_COMPOSE, "compose", NULL),
+	DEFINE_INPUT_LED(LED_KANA, "kana", "kbd-kanalock"),
+	DEFINE_INPUT_LED(LED_SLEEP, "sleep", NULL),
+	DEFINE_INPUT_LED(LED_SUSPEND, "suspend", NULL),
+	DEFINE_INPUT_LED(LED_MUTE, "mute", NULL),
+	DEFINE_INPUT_LED(LED_MISC, "misc", NULL),
+	DEFINE_INPUT_LED(LED_MAIL, "mail", NULL),
+	DEFINE_INPUT_LED(LED_CHARGING, "charging", NULL),
+};
+static const char *const vt_led_names[LED_CNT] = {
+	[LED_NUML] = "numl",
+	[LED_CAPSL] = "capsl",
+	[LED_SCROLLL] = "scrolll",
+	[LED_COMPOSE] = "compose",
+	[LED_KANA] = "kana",
+	[LED_SLEEP] = "sleep",
+	[LED_SUSPEND] = "suspend",
+	[LED_MUTE] = "mute",
+	[LED_MISC] = "misc",
+	[LED_MAIL] = "mail",
+	[LED_CHARGING] = "charging",
+};
+/* Handler for hotplug initialization */
+static void vt_led_trigger_activate(struct led_classdev *cdev);
+/* VT triggers */
+static struct led_trigger vt_led_triggers[LED_CNT] = {
+#define DEFINE_INPUT_LED_TRIGGER(vt_led, nam) \
+	[vt_led] = { \
+		.name = "vt-"nam, \
+		.activate = vt_led_trigger_activate, \
+	}
+	DEFINE_INPUT_LED_TRIGGER(LED_NUML, "numl"),
+	DEFINE_INPUT_LED_TRIGGER(LED_CAPSL, "capsl"),
+	DEFINE_INPUT_LED_TRIGGER(LED_SCROLLL, "scrolll"),
+	DEFINE_INPUT_LED_TRIGGER(LED_COMPOSE, "compose"),
+	DEFINE_INPUT_LED_TRIGGER(LED_KANA, "kana"),
+	DEFINE_INPUT_LED_TRIGGER(LED_SLEEP, "sleep"),
+	DEFINE_INPUT_LED_TRIGGER(LED_SUSPEND, "suspend"),
+	DEFINE_INPUT_LED_TRIGGER(LED_MUTE, "mute"),
+	DEFINE_INPUT_LED_TRIGGER(LED_MISC, "misc"),
+	DEFINE_INPUT_LED_TRIGGER(LED_MAIL, "mail"),
+	DEFINE_INPUT_LED_TRIGGER(LED_CHARGING, "charging"),
+};
+
+/* Lock for registration coherency */
+static DEFINE_MUTEX(vt_led_registered_lock);
+
+/* Which VT LED classes and triggers are registered */
+static unsigned long vt_led_registered[BITS_TO_LONGS(LED_CNT)];
+
+/* Number of input devices having each LED */
+static int vt_led_references[LED_CNT];
+
+static int vt_led_state[LED_CNT];
+static struct work_struct vt_led_work[LED_CNT];
+
+static void vt_led_cb(struct work_struct *work)
+{
+	int led = work - vt_led_work;
+
+	led_trigger_event(&vt_led_triggers[led], vt_led_state[led]);
+}
+
+/* VT LED state change, tell the VT trigger.  */
+static void vt_led_set(struct led_classdev *cdev,
+			  enum led_brightness brightness)
+{
+	int led = cdev - vt_leds;
+
+	vt_led_state[led] = !!brightness;
+	schedule_work(&vt_led_work[led]);
+}
+
+/* LED state change for some keyboard, notify that keyboard.  */
+static void perdevice_input_led_set(struct led_classdev *cdev,
+			  enum led_brightness brightness)
+{
+	struct input_dev *dev;
+	struct led_classdev *leds;
+	int led;
+
+	dev = cdev->dev->platform_data;
+	if (!dev)
+		/* Still initializing */
+		return;
+	leds = dev->leds;
+	led = cdev - leds;
+
+	input_event(dev, EV_LED, led, !!brightness);
+	input_event(dev, EV_SYN, SYN_REPORT, 0);
+}
+
+/* Keyboard hotplug, initialize its LED status */
+static void vt_led_trigger_activate(struct led_classdev *cdev)
+{
+	struct led_trigger *trigger = cdev->trigger;
+	int led = trigger - vt_led_triggers;
+
+	if (cdev->brightness_set)
+		cdev->brightness_set(cdev, vt_leds[led].brightness);
+}
+
+/* Free led stuff from input device, used at abortion and disconnection.  */
+static void input_led_delete(struct input_dev *dev)
+{
+	if (dev) {
+		struct led_classdev *leds = dev->leds;
+		if (leds) {
+			int i;
+			for (i = 0; i < LED_CNT; i++)
+				kfree(leds[i].name);
+			kfree(leds);
+			dev->leds = NULL;
+		}
+	}
+}
+
+/* A new input device with potential LEDs to connect.  */
+int input_led_connect(struct input_dev *dev)
+{
+	int i, error = 0;
+	struct led_classdev *leds;
+
+	dev->leds = leds = kcalloc(LED_CNT, sizeof(*leds), GFP_KERNEL);
+	if (!dev->leds)
+		return -ENOMEM;
+
+	/* lazily register missing VT LEDs */
+	mutex_lock(&vt_led_registered_lock);
+	for (i = 0; i < LED_CNT; i++)
+		if (vt_leds[i].name && test_bit(i, dev->ledbit)) {
+			if (!vt_led_references[i]) {
+				led_trigger_register(&vt_led_triggers[i]);
+				/* This keyboard is first to have led i,
+				 * try to register it */
+				if (!led_classdev_register(NULL, &vt_leds[i]))
+					vt_led_references[i] = 1;
+				else
+					led_trigger_unregister(&vt_led_triggers[i]);
+			} else
+				vt_led_references[i]++;
+		}
+	mutex_unlock(&vt_led_registered_lock);
+
+	/* and register this device's LEDs */
+	for (i = 0; i < LED_CNT; i++)
+		if (vt_leds[i].name && test_bit(i, dev->ledbit)) {
+			leds[i].name = kasprintf(GFP_KERNEL, "%s::%s",
+						dev_name(&dev->dev),
+						vt_led_names[i]);
+			if (!leds[i].name) {
+				error = -ENOMEM;
+				goto err;
+			}
+			leds[i].max_brightness = 1;
+			leds[i].brightness_set = perdevice_input_led_set;
+			leds[i].default_trigger = vt_led_triggers[i].name;
+		}
+
+	/* No issue so far, we can register for real.  */
+	for (i = 0; i < LED_CNT; i++)
+		if (leds[i].name) {
+			led_classdev_register(&dev->dev, &leds[i]);
+			leds[i].dev->platform_data = dev;
+			perdevice_input_led_set(&leds[i],
+					vt_leds[i].brightness);
+		}
+
+	return 0;
+
+err:
+	input_led_delete(dev);
+	return error;
+}
+
+/*
+ * Disconnected input device. Clean it, and deregister now-useless VT LEDs
+ * and triggers.
+ */
+void input_led_disconnect(struct input_dev *dev)
+{
+	int i;
+	struct led_classdev *leds = dev->leds;
+
+	for (i = 0; i < LED_CNT; i++)
+		if (leds[i].name)
+			led_classdev_unregister(&leds[i]);
+
+	input_led_delete(dev);
+
+	mutex_lock(&vt_led_registered_lock);
+	for (i = 0; i < LED_CNT; i++) {
+		if (!vt_leds[i].name || !test_bit(i, dev->ledbit))
+			continue;
+
+		vt_led_references[i]--;
+		if (vt_led_references[i]) {
+			/* Still some devices needing it */
+			continue;
+		}
+
+		led_classdev_unregister(&vt_leds[i]);
+		led_trigger_unregister(&vt_led_triggers[i]);
+		clear_bit(i, vt_led_registered);
+	}
+	mutex_unlock(&vt_led_registered_lock);
+}
+
+void __init input_led_init(void)
+{
+	unsigned i;
+
+	for (i = 0; i < LED_CNT; i++)
+		INIT_WORK(&vt_led_work[i], vt_led_cb);
+}
+
+void __exit input_led_exit(void)
+{
+	unsigned i;
+
+	for (i = 0; i < LED_CNT; i++)
+		cancel_work_sync(&vt_led_work[i]);
+}
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index a6c3d2f153f..59f4228cc9c 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -11,9 +11,6 @@ menuconfig NEW_LEDS
 	  Say Y to enable Linux LED support.  This allows control of supported
 	  LEDs from both userspace and optionally, by kernel events (triggers).
 
-	  This is not related to standard keyboard LEDs which are controlled
-	  via the input system.
-
 if NEW_LEDS
 
 config LEDS_CLASS
diff --git a/drivers/misc/ti-st/st_core.c b/drivers/misc/ti-st/st_core.c
index 54be83d3efd..374480cb69b 100644
--- a/drivers/misc/ti-st/st_core.c
+++ b/drivers/misc/ti-st/st_core.c
@@ -343,7 +343,7 @@ void st_int_recv(void *disc_data,
 			/* Unknow packet? */
 		default:
 			type = *ptr;
-			if (st_gdata->list[type] == NULL) {
+			if (type >= ST_MAX_CHANNELS || st_gdata->list[type] == NULL) {
 				pr_err("chip/interface misbehavior dropping"
 					" frame starting with 0x%02x", type);
 				goto done;
diff --git a/drivers/rtc/rtc-isl12057.c b/drivers/rtc/rtc-isl12057.c
index 6e1fcfb5d7e..b94b6225576 100644
--- a/drivers/rtc/rtc-isl12057.c
+++ b/drivers/rtc/rtc-isl12057.c
@@ -1,5 +1,5 @@
 /*
- * rtc-isl12057 - Driver for Intersil ISL12057 I2C Real Time Clock
+ * rtc-isl12057 - Driver for Intersil ISL12057 I2C Real Time Clock / Alarm
  *
  * Copyright (C) 2013, Arnaud EBALARD <arno@natisbad.org>
  *
@@ -79,8 +79,10 @@
 #define ISL12057_MEM_MAP_LEN	0x10
 
 struct isl12057_rtc_data {
+	struct rtc_device *rtc;
 	struct regmap *regmap;
 	struct mutex lock;
+	int irq;
 };
 
 static void isl12057_rtc_regs_to_tm(struct rtc_time *tm, u8 *regs)
@@ -160,14 +162,47 @@ static int isl12057_i2c_validate_chip(struct regmap *regmap)
 	return 0;
 }
 
-static int isl12057_rtc_read_time(struct device *dev, struct rtc_time *tm)
+static int _isl12057_rtc_clear_alarm(struct device *dev)
+{
+	struct isl12057_rtc_data *data = dev_get_drvdata(dev);
+	int ret;
+
+	ret = regmap_update_bits(data->regmap, ISL12057_REG_SR,
+				 ISL12057_REG_SR_A1F, 0);
+	if (ret)
+		dev_err(dev, "%s: clearing alarm failed (%d)\n", __func__, ret);
+
+	return ret;
+}
+
+static int _isl12057_rtc_update_alarm(struct device *dev, int enable)
+{
+	struct isl12057_rtc_data *data = dev_get_drvdata(dev);
+	int ret;
+
+	ret = regmap_update_bits(data->regmap, ISL12057_REG_INT,
+				 ISL12057_REG_INT_A1IE,
+				 enable ? ISL12057_REG_INT_A1IE : 0);
+	if (ret)
+		dev_err(dev, "%s: changing alarm interrupt flag failed (%d)\n",
+			__func__, ret);
+
+	return ret;
+}
+
+/*
+ * Note: as we only read from device and do not perform any update, there is
+ * no need for an equivalent function which would try and get driver's main
+ * lock. Here, it is safe for everyone if we just use regmap internal lock
+ * on the device when reading.
+ */
+static int _isl12057_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
 	struct isl12057_rtc_data *data = dev_get_drvdata(dev);
 	u8 regs[ISL12057_RTC_SEC_LEN];
 	unsigned int sr;
 	int ret;
 
-	mutex_lock(&data->lock);
 	ret = regmap_read(data->regmap, ISL12057_REG_SR, &sr);
 	if (ret) {
 		dev_err(dev, "%s: unable to read oscillator status flag (%d)\n",
@@ -187,8 +222,6 @@ static int isl12057_rtc_read_time(struct device *dev, struct rtc_time *tm)
 			__func__, ret);
 
 out:
-	mutex_unlock(&data->lock);
-
 	if (ret)
 		return ret;
 
@@ -197,6 +230,168 @@ out:
 	return rtc_valid_tm(tm);
 }
 
+static int isl12057_rtc_update_alarm(struct device *dev, int enable)
+{
+	struct isl12057_rtc_data *data = dev_get_drvdata(dev);
+	int ret;
+
+	mutex_lock(&data->lock);
+	ret = _isl12057_rtc_update_alarm(dev, enable);
+	mutex_unlock(&data->lock);
+
+	return ret;
+}
+
+static int isl12057_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm)
+{
+	struct isl12057_rtc_data *data = dev_get_drvdata(dev);
+	struct rtc_time rtc_tm, *alarm_tm = &alarm->time;
+	unsigned long rtc_secs, alarm_secs;
+	u8 regs[ISL12057_A1_SEC_LEN];
+	unsigned int ir;
+	int ret;
+
+	mutex_lock(&data->lock);
+	ret = regmap_bulk_read(data->regmap, ISL12057_REG_A1_SC, regs,
+			       ISL12057_A1_SEC_LEN);
+	if (ret) {
+		dev_err(dev, "%s: reading alarm section failed (%d)\n",
+			__func__, ret);
+		goto err_unlock;
+	}
+
+	alarm_tm->tm_sec  = bcd2bin(regs[0] & 0x7f);
+	alarm_tm->tm_min  = bcd2bin(regs[1] & 0x7f);
+	alarm_tm->tm_hour = bcd2bin(regs[2] & 0x3f);
+	alarm_tm->tm_mday = bcd2bin(regs[3] & 0x3f);
+	alarm_tm->tm_wday = -1;
+
+	/*
+	 * The alarm section does not store year/month. We use the ones in rtc
+	 * section as a basis and increment month and then year if needed to get
+	 * alarm after current time.
+	 */
+	ret = _isl12057_rtc_read_time(dev, &rtc_tm);
+	if (ret)
+		goto err_unlock;
+
+	alarm_tm->tm_year = rtc_tm.tm_year;
+	alarm_tm->tm_mon = rtc_tm.tm_mon;
+
+	ret = rtc_tm_to_time(&rtc_tm, &rtc_secs);
+	if (ret)
+		goto err_unlock;
+
+	ret = rtc_tm_to_time(alarm_tm, &alarm_secs);
+	if (ret)
+		goto err_unlock;
+
+	if (alarm_secs < rtc_secs) {
+		if (alarm_tm->tm_mon == 11) {
+			alarm_tm->tm_mon = 0;
+			alarm_tm->tm_year += 1;
+		} else {
+			alarm_tm->tm_mon += 1;
+		}
+	}
+
+	ret = regmap_read(data->regmap, ISL12057_REG_INT, &ir);
+	if (ret) {
+		dev_err(dev, "%s: reading alarm interrupt flag failed (%d)\n",
+			__func__, ret);
+		goto err_unlock;
+	}
+
+	alarm->enabled = !!(ir & ISL12057_REG_INT_A1IE);
+
+err_unlock:
+	mutex_unlock(&data->lock);
+
+	return ret;
+}
+
+static int isl12057_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm)
+{
+	struct isl12057_rtc_data *data = dev_get_drvdata(dev);
+	struct rtc_time *alarm_tm = &alarm->time;
+	unsigned long rtc_secs, alarm_secs;
+	u8 regs[ISL12057_A1_SEC_LEN];
+	struct rtc_time rtc_tm;
+	int ret, enable = 1;
+
+	mutex_lock(&data->lock);
+	ret = _isl12057_rtc_read_time(dev, &rtc_tm);
+	if (ret)
+		goto err_unlock;
+
+	ret = rtc_tm_to_time(&rtc_tm, &rtc_secs);
+	if (ret)
+		goto err_unlock;
+
+	ret = rtc_tm_to_time(alarm_tm, &alarm_secs);
+	if (ret)
+		goto err_unlock;
+
+	/* If alarm time is before current time, disable the alarm */
+	if (!alarm->enabled || alarm_secs <= rtc_secs) {
+		enable = 0;
+	} else {
+		/*
+		 * Chip only support alarms up to one month in the future. Let's
+		 * return an error if we get something after that limit.
+		 * Comparison is done by incrementing rtc_tm month field by one
+		 * and checking alarm value is still below.
+		 */
+		if (rtc_tm.tm_mon == 11) { /* handle year wrapping */
+			rtc_tm.tm_mon = 0;
+			rtc_tm.tm_year += 1;
+		} else {
+			rtc_tm.tm_mon += 1;
+		}
+
+		ret = rtc_tm_to_time(&rtc_tm, &rtc_secs);
+		if (ret)
+			goto err_unlock;
+
+		if (alarm_secs > rtc_secs) {
+			dev_err(dev, "%s: max for alarm is one month (%d)\n",
+				__func__, ret);
+			ret = -EINVAL;
+			goto err_unlock;
+		}
+	}
+
+	/* Disable the alarm before modifying it */
+	ret = _isl12057_rtc_update_alarm(dev, 0);
+	if (ret < 0) {
+		dev_err(dev, "%s: unable to disable the alarm (%d)\n",
+			__func__, ret);
+		goto err_unlock;
+	}
+
+	/* Program alarm registers */
+	regs[0] = bin2bcd(alarm_tm->tm_sec) & 0x7f;
+	regs[1] = bin2bcd(alarm_tm->tm_min) & 0x7f;
+	regs[2] = bin2bcd(alarm_tm->tm_hour) & 0x3f;
+	regs[3] = bin2bcd(alarm_tm->tm_mday) & 0x3f;
+
+	ret = regmap_bulk_write(data->regmap, ISL12057_REG_A1_SC, regs,
+				ISL12057_A1_SEC_LEN);
+	if (ret < 0) {
+		dev_err(dev, "%s: writing alarm section failed (%d)\n",
+			__func__, ret);
+		goto err_unlock;
+	}
+
+	/* Enable or disable alarm */
+	ret = _isl12057_rtc_update_alarm(dev, enable);
+
+err_unlock:
+	mutex_unlock(&data->lock);
+
+	return ret;
+}
+
 static int isl12057_rtc_set_time(struct device *dev, struct rtc_time *tm)
 {
 	struct isl12057_rtc_data *data = dev_get_drvdata(dev);
@@ -262,9 +457,48 @@ static int isl12057_check_rtc_status(struct device *dev, struct regmap *regmap)
 	return 0;
 }
 
+static int isl12057_rtc_alarm_irq_enable(struct device *dev,
+					 unsigned int enable)
+{
+	struct isl12057_rtc_data *rtc_data = dev_get_drvdata(dev);
+	int ret = -ENOTTY;
+
+	if (rtc_data->irq)
+		ret = isl12057_rtc_update_alarm(dev, enable);
+
+	return ret;
+}
+
+static irqreturn_t isl12057_rtc_interrupt(int irq, void *data)
+{
+	struct i2c_client *client = data;
+	struct isl12057_rtc_data *rtc_data = dev_get_drvdata(&client->dev);
+	struct rtc_device *rtc = rtc_data->rtc;
+	int ret, handled = IRQ_NONE;
+	unsigned int sr;
+
+	ret = regmap_read(rtc_data->regmap, ISL12057_REG_SR, &sr);
+	if (!ret && (sr & ISL12057_REG_SR_A1F)) {
+		dev_dbg(&client->dev, "RTC alarm!\n");
+
+		rtc_update_irq(rtc, 1, RTC_IRQF | RTC_AF);
+
+		/* Acknowledge and disable the alarm */
+		_isl12057_rtc_clear_alarm(&client->dev);
+		_isl12057_rtc_update_alarm(&client->dev, 0);
+
+		handled = IRQ_HANDLED;
+	}
+
+	return handled;
+}
+
 static const struct rtc_class_ops rtc_ops = {
-	.read_time = isl12057_rtc_read_time,
+	.read_time = _isl12057_rtc_read_time,
 	.set_time = isl12057_rtc_set_time,
+	.read_alarm = isl12057_rtc_read_alarm,
+	.set_alarm = isl12057_rtc_set_alarm,
+	.alarm_irq_enable = isl12057_rtc_alarm_irq_enable,
 };
 
 static struct regmap_config isl12057_rtc_regmap_config = {
@@ -277,7 +511,6 @@ static int isl12057_probe(struct i2c_client *client,
 {
 	struct device *dev = &client->dev;
 	struct isl12057_rtc_data *data;
-	struct rtc_device *rtc;
 	struct regmap *regmap;
 	int ret;
 
@@ -310,10 +543,79 @@ static int isl12057_probe(struct i2c_client *client,
 	data->regmap = regmap;
 	dev_set_drvdata(dev, data);
 
-	rtc = devm_rtc_device_register(dev, DRV_NAME, &rtc_ops, THIS_MODULE);
-	return PTR_ERR_OR_ZERO(rtc);
+	if (client->irq > 0) {
+		ret = devm_request_threaded_irq(dev, client->irq, NULL,
+						isl12057_rtc_interrupt,
+						IRQF_SHARED|IRQF_ONESHOT,
+						DRV_NAME, client);
+		if (!ret)
+			data->irq = client->irq;
+		else
+			dev_err(dev, "%s: irq %d unavailable (%d)\n", __func__,
+				client->irq, ret);
+	}
+
+	/*
+	 * This is needed to have 'wakealarm' sysfs entry available. One
+	 * would expect the device to be marked as a wakeup source only
+	 * when an IRQ pin of the RTC is routed to an interrupt line of the
+	 * CPU. In practice, such an IRQ pin can be connected to a PMIC and
+	 * this allows the device to be powered up when RTC alarm rings.
+	 */
+	device_init_wakeup(dev, true);
+
+	data->rtc = devm_rtc_device_register(dev, DRV_NAME, &rtc_ops,
+					     THIS_MODULE);
+	ret = PTR_ERR_OR_ZERO(data->rtc);
+	if (ret) {
+		dev_err(dev, "%s: unable to register RTC device (%d)\n",
+			__func__, ret);
+		goto err;
+	}
+
+	/* We cannot support UIE mode if we do not have an IRQ line */
+	if (!data->irq)
+		data->rtc->uie_unsupported = 1;
+
+err:
+	return ret;
 }
 
+static int isl12057_remove(struct i2c_client *client)
+{
+	struct isl12057_rtc_data *rtc_data = dev_get_drvdata(&client->dev);
+
+	if (rtc_data->irq > 0)
+		device_init_wakeup(&client->dev, false);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int isl12057_rtc_suspend(struct device *dev)
+{
+	struct isl12057_rtc_data *rtc_data = dev_get_drvdata(dev);
+
+	if (device_may_wakeup(dev))
+		return enable_irq_wake(rtc_data->irq);
+
+	return 0;
+}
+
+static int isl12057_rtc_resume(struct device *dev)
+{
+	struct isl12057_rtc_data *rtc_data = dev_get_drvdata(dev);
+
+	if (device_may_wakeup(dev))
+		return disable_irq_wake(rtc_data->irq);
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(isl12057_rtc_pm_ops, isl12057_rtc_suspend,
+			 isl12057_rtc_resume);
+
 #ifdef CONFIG_OF
 static const struct of_device_id isl12057_dt_match[] = {
 	{ .compatible = "isl,isl12057" },
@@ -331,13 +633,15 @@ static struct i2c_driver isl12057_driver = {
 	.driver = {
 		.name = DRV_NAME,
 		.owner = THIS_MODULE,
+		.pm = &isl12057_rtc_pm_ops,
 		.of_match_table = of_match_ptr(isl12057_dt_match),
 	},
 	.probe	  = isl12057_probe,
+	.remove	  = isl12057_remove,
 	.id_table = isl12057_id,
 };
 module_i2c_driver(isl12057_driver);
 
 MODULE_AUTHOR("Arnaud EBALARD <arno@natisbad.org>");
-MODULE_DESCRIPTION("Intersil ISL12057 RTC driver");
+MODULE_DESCRIPTION("Intersil ISL12057 RTC/Alarm driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/tty/Kconfig b/drivers/tty/Kconfig
index b24aa010f68..65cd80bf9ae 100644
--- a/drivers/tty/Kconfig
+++ b/drivers/tty/Kconfig
@@ -13,6 +13,10 @@ config VT
 	bool "Virtual terminal" if EXPERT
 	depends on !S390 && !UML
 	select INPUT
+	select NEW_LEDS
+	select LEDS_CLASS
+	select LEDS_TRIGGERS
+	select INPUT_LEDS
 	default y
 	---help---
 	  If you say Y here, you will get support for terminal devices with
diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index 8a89f6e7715..acfb4c00e48 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -33,6 +33,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/leds.h>
 
 #include <linux/kbd_kern.h>
 #include <linux/kbd_diacr.h>
@@ -130,6 +131,7 @@ static char rep;					/* flag telling character repeat */
 static int shift_state = 0;
 
 static unsigned char ledstate = 0xff;			/* undefined */
+static unsigned char lockstate = 0xff;			/* undefined */
 static unsigned char ledioctl;
 
 /*
@@ -961,6 +963,41 @@ static void k_brl(struct vc_data *vc, unsigned char value, char up_flag)
 	}
 }
 
+/* We route VT keyboard "leds" through triggers */
+static void kbd_ledstate_trigger_activate(struct led_classdev *cdev);
+
+static struct led_trigger ledtrig_ledstate[] = {
+#define DEFINE_LEDSTATE_TRIGGER(kbd_led, nam) \
+	[kbd_led] = { \
+		.name = nam, \
+		.activate = kbd_ledstate_trigger_activate, \
+	}
+	DEFINE_LEDSTATE_TRIGGER(VC_SCROLLOCK, "kbd-scrollock"),
+	DEFINE_LEDSTATE_TRIGGER(VC_NUMLOCK,   "kbd-numlock"),
+	DEFINE_LEDSTATE_TRIGGER(VC_CAPSLOCK,  "kbd-capslock"),
+	DEFINE_LEDSTATE_TRIGGER(VC_KANALOCK,  "kbd-kanalock"),
+#undef DEFINE_LEDSTATE_TRIGGER
+};
+
+static void kbd_lockstate_trigger_activate(struct led_classdev *cdev);
+
+static struct led_trigger ledtrig_lockstate[] = {
+#define DEFINE_LOCKSTATE_TRIGGER(kbd_led, nam) \
+	[kbd_led] = { \
+		.name = nam, \
+		.activate = kbd_lockstate_trigger_activate, \
+	}
+	DEFINE_LOCKSTATE_TRIGGER(VC_SHIFTLOCK,  "kbd-shiftlock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_ALTGRLOCK,  "kbd-altgrlock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_CTRLLOCK,   "kbd-ctrllock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_ALTLOCK,    "kbd-altlock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_SHIFTLLOCK, "kbd-shiftllock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_SHIFTRLOCK, "kbd-shiftrlock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_CTRLLLOCK,  "kbd-ctrlllock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_CTRLRLOCK,  "kbd-ctrlrlock"),
+#undef DEFINE_LOCKSTATE_TRIGGER
+};
+
 /*
  * The leds display either (i) the status of NumLock, CapsLock, ScrollLock,
  * or (ii) whatever pattern of lights people want to show using KDSETLED,
@@ -995,18 +1032,25 @@ static inline unsigned char getleds(void)
 	return kb->ledflagstate;
 }
 
-static int kbd_update_leds_helper(struct input_handle *handle, void *data)
+/* Called on trigger connection, to set initial state */
+static void kbd_ledstate_trigger_activate(struct led_classdev *cdev)
 {
-	unsigned char leds = *(unsigned char *)data;
+	struct led_trigger *trigger = cdev->trigger;
+	int led = trigger - ledtrig_ledstate;
 
-	if (test_bit(EV_LED, handle->dev->evbit)) {
-		input_inject_event(handle, EV_LED, LED_SCROLLL, !!(leds & 0x01));
-		input_inject_event(handle, EV_LED, LED_NUML,    !!(leds & 0x02));
-		input_inject_event(handle, EV_LED, LED_CAPSL,   !!(leds & 0x04));
-		input_inject_event(handle, EV_SYN, SYN_REPORT, 0);
-	}
+	tasklet_disable(&keyboard_tasklet);
+	led_trigger_event(trigger, ledstate & (1 << led) ? LED_FULL : LED_OFF);
+	tasklet_enable(&keyboard_tasklet);
+}
 
-	return 0;
+static void kbd_lockstate_trigger_activate(struct led_classdev *cdev)
+{
+	struct led_trigger *trigger = cdev->trigger;
+	int led = trigger - ledtrig_lockstate;
+
+	tasklet_disable(&keyboard_tasklet);
+	led_trigger_event(trigger, lockstate & (1 << led) ? LED_FULL : LED_OFF);
+	tasklet_enable(&keyboard_tasklet);
 }
 
 /**
@@ -1095,16 +1139,29 @@ static void kbd_bh(unsigned long dummy)
 {
 	unsigned char leds;
 	unsigned long flags;
-	
+	int i;
+
 	spin_lock_irqsave(&led_lock, flags);
 	leds = getleds();
 	spin_unlock_irqrestore(&led_lock, flags);
 
 	if (leds != ledstate) {
-		input_handler_for_each_handle(&kbd_handler, &leds,
-					      kbd_update_leds_helper);
+		for (i = 0; i < ARRAY_SIZE(ledtrig_ledstate); i++)
+			if ((leds ^ ledstate) & (1 << i))
+				led_trigger_event(&ledtrig_ledstate[i],
+						leds & (1 << i)
+						? LED_FULL : LED_OFF);
 		ledstate = leds;
 	}
+
+	if (kbd->lockstate != lockstate) {
+		for (i = 0; i < ARRAY_SIZE(ledtrig_lockstate); i++)
+			if ((kbd->lockstate ^ lockstate) & (1 << i))
+				led_trigger_event(&ledtrig_lockstate[i],
+						kbd->lockstate & (1 << i)
+						? LED_FULL : LED_OFF);
+		lockstate = kbd->lockstate;
+	}
 }
 
 DECLARE_TASKLET_DISABLED(keyboard_tasklet, kbd_bh, 0);
@@ -1442,20 +1499,6 @@ static void kbd_disconnect(struct input_handle *handle)
 	kfree(handle);
 }
 
-/*
- * Start keyboard handler on the new keyboard by refreshing LED state to
- * match the rest of the system.
- */
-static void kbd_start(struct input_handle *handle)
-{
-	tasklet_disable(&keyboard_tasklet);
-
-	if (ledstate != 0xff)
-		kbd_update_leds_helper(handle, &ledstate);
-
-	tasklet_enable(&keyboard_tasklet);
-}
-
 static const struct input_device_id kbd_ids[] = {
 	{
 		.flags = INPUT_DEVICE_ID_MATCH_EVBIT,
@@ -1477,7 +1520,6 @@ static struct input_handler kbd_handler = {
 	.match		= kbd_match,
 	.connect	= kbd_connect,
 	.disconnect	= kbd_disconnect,
-	.start		= kbd_start,
 	.name		= "kbd",
 	.id_table	= kbd_ids,
 };
@@ -1501,6 +1543,20 @@ int __init kbd_init(void)
 	if (error)
 		return error;
 
+	for (i = 0; i < ARRAY_SIZE(ledtrig_ledstate); i++) {
+		error = led_trigger_register(&ledtrig_ledstate[i]);
+		if (error)
+			pr_err("error %d while registering trigger %s\n",
+					error, ledtrig_ledstate[i].name);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(ledtrig_lockstate); i++) {
+		error = led_trigger_register(&ledtrig_lockstate[i]);
+		if (error)
+			pr_err("error %d while registering trigger %s\n",
+					error, ledtrig_lockstate[i].name);
+	}
+
 	tasklet_enable(&keyboard_tasklet);
 	tasklet_schedule(&keyboard_tasklet);
 
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index a8bc47f75fa..5b6e9f24623 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -107,7 +107,10 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	}
 
 	if (!journal) {
-		ret = generic_file_fsync(file, start, end, datasync);
+		if (test_opt(inode->i_sb, BARRIER))
+			ret = generic_file_fsync(file, start, end, datasync);
+		else
+			ret = __generic_file_fsync(file, start, end, datasync);
 		if (!ret && !hlist_empty(&inode->i_dentry))
 			ret = ext4_sync_parent(inode);
 		goto out;
diff --git a/fs/fat/cache.c b/fs/fat/cache.c
index 91ad9e1c944..d3dd5baccdf 100644
--- a/fs/fat/cache.c
+++ b/fs/fat/cache.c
@@ -303,6 +303,29 @@ static int fat_bmap_cluster(struct inode *inode, int cluster)
 	return dclus;
 }
 
+int fat_get_mapped_cluster(struct inode *inode, sector_t sector,
+			   sector_t last_block,
+			   unsigned long *mapped_blocks, sector_t *bmap)
+{
+	struct super_block *sb = inode->i_sb;
+	struct msdos_sb_info *sbi = MSDOS_SB(sb);
+	int cluster, offset;
+
+	cluster = sector >> (sbi->cluster_bits - sb->s_blocksize_bits);
+	offset  = sector & (sbi->sec_per_clus - 1);
+	cluster = fat_bmap_cluster(inode, cluster);
+	if (cluster < 0)
+		return cluster;
+	else if (cluster) {
+		*bmap = fat_clus_to_blknr(sbi, cluster) + offset;
+		*mapped_blocks = sbi->sec_per_clus - offset;
+		if (*mapped_blocks > last_block - sector)
+			*mapped_blocks = last_block - sector;
+	}
+
+	return 0;
+}
+
 int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
 	     unsigned long *mapped_blocks, int create)
 {
@@ -311,7 +334,6 @@ int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
 	const unsigned long blocksize = sb->s_blocksize;
 	const unsigned char blocksize_bits = sb->s_blocksize_bits;
 	sector_t last_block;
-	int cluster, offset;
 
 	*phys = 0;
 	*mapped_blocks = 0;
@@ -338,16 +360,6 @@ int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
 			return 0;
 	}
 
-	cluster = sector >> (sbi->cluster_bits - sb->s_blocksize_bits);
-	offset  = sector & (sbi->sec_per_clus - 1);
-	cluster = fat_bmap_cluster(inode, cluster);
-	if (cluster < 0)
-		return cluster;
-	else if (cluster) {
-		*phys = fat_clus_to_blknr(sbi, cluster) + offset;
-		*mapped_blocks = sbi->sec_per_clus - offset;
-		if (*mapped_blocks > last_block - sector)
-			*mapped_blocks = last_block - sector;
-	}
-	return 0;
+	return fat_get_mapped_cluster(inode, sector, last_block, mapped_blocks,
+				      phys);
 }
diff --git a/fs/fat/fat.h b/fs/fat/fat.h
index 64e295e8ff3..e59eb6ece9a 100644
--- a/fs/fat/fat.h
+++ b/fs/fat/fat.h
@@ -288,6 +288,9 @@ static inline void fatwchar_to16(__u8 *dst, const wchar_t *src, size_t len)
 extern void fat_cache_inval_inode(struct inode *inode);
 extern int fat_get_cluster(struct inode *inode, int cluster,
 			   int *fclus, int *dclus);
+extern int fat_get_mapped_cluster(struct inode *inode, sector_t sector,
+				  sector_t last_block,
+				  unsigned long *mapped_blocks, sector_t *bmap);
 extern int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
 		    unsigned long *mapped_blocks, int create);
 
@@ -387,6 +390,7 @@ static inline unsigned long fat_dir_hash(int logstart)
 {
 	return hash_32(logstart, FAT_HASH_BITS);
 }
+extern int fat_add_cluster(struct inode *inode);
 
 /* fat/misc.c */
 extern __printf(3, 4) __cold
diff --git a/fs/fat/file.c b/fs/fat/file.c
index 8429c68e305..eac05ebd7c7 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -17,8 +17,12 @@
 #include <linux/blkdev.h>
 #include <linux/fsnotify.h>
 #include <linux/security.h>
+#include <linux/falloc.h>
 #include "fat.h"
 
+static long fat_fallocate(struct file *file, int mode,
+			  loff_t offset, loff_t len);
+
 static int fat_ioctl_get_attributes(struct inode *inode, u32 __user *user_attr)
 {
 	u32 attr;
@@ -182,6 +186,7 @@ const struct file_operations fat_file_operations = {
 #endif
 	.fsync		= fat_file_fsync,
 	.splice_read	= generic_file_splice_read,
+	.fallocate	= fat_fallocate,
 };
 
 static int fat_cont_expand(struct inode *inode, loff_t size)
@@ -220,6 +225,63 @@ out:
 	return err;
 }
 
+/*
+ * Preallocate space for a file. This implements fat's fallocate file
+ * operation, which gets called from sys_fallocate system call. User
+ * space requests len bytes at offset. If FALLOC_FL_KEEP_SIZE is set
+ * we just allocate clusters without zeroing them out. Otherwise we
+ * allocate and zero out clusters via an expanding truncate.
+ */
+static long fat_fallocate(struct file *file, int mode,
+			  loff_t offset, loff_t len)
+{
+	int nr_cluster; /* Number of clusters to be allocated */
+	loff_t mm_bytes; /* Number of bytes to be allocated for file */
+	loff_t ondisksize; /* block aligned on-disk size in bytes*/
+	struct inode *inode = file->f_mapping->host;
+	struct super_block *sb = inode->i_sb;
+	struct msdos_sb_info *sbi = MSDOS_SB(sb);
+	int err = 0;
+
+	/* No support for hole punch or other fallocate flags. */
+	if (mode & ~FALLOC_FL_KEEP_SIZE)
+		return -EOPNOTSUPP;
+
+	/* No support for dir */
+	if (!S_ISREG(inode->i_mode))
+		return -EOPNOTSUPP;
+
+	mutex_lock(&inode->i_mutex);
+	if (mode & FALLOC_FL_KEEP_SIZE) {
+		ondisksize = inode->i_blocks << 9;
+		if ((offset + len) <= ondisksize)
+			goto error;
+
+		/* First compute the number of clusters to be allocated */
+		mm_bytes = offset + len - ondisksize;
+		nr_cluster = (mm_bytes + (sbi->cluster_size - 1)) >>
+			sbi->cluster_bits;
+
+		/* Start the allocation.We are not zeroing out the clusters */
+		while (nr_cluster-- > 0) {
+			err = fat_add_cluster(inode);
+			if (err)
+				goto error;
+		}
+	} else {
+		err = inode_newsize_ok(inode, (offset + len));
+		if (err)
+			goto error;
+
+		/* This is just an expanding truncate */
+		err = fat_cont_expand(inode, (offset + len));
+	}
+
+error:
+	mutex_unlock(&inode->i_mutex);
+	return err;
+}
+
 /* Free all clusters after the skip'th cluster. */
 static int fat_free(struct inode *inode, int skip)
 {
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 7b41a2dcdd7..1956dae03c7 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -101,7 +101,7 @@ static struct fat_floppy_defaults {
 },
 };
 
-static int fat_add_cluster(struct inode *inode)
+int fat_add_cluster(struct inode *inode)
 {
 	int err, cluster;
 
@@ -123,7 +123,7 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock,
 	struct super_block *sb = inode->i_sb;
 	struct msdos_sb_info *sbi = MSDOS_SB(sb);
 	unsigned long mapped_blocks;
-	sector_t phys;
+	sector_t phys, last_block;
 	int err, offset;
 
 	err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create);
@@ -143,8 +143,14 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock,
 		return -EIO;
 	}
 
+	last_block = inode->i_blocks >> (sb->s_blocksize_bits - 9);
 	offset = (unsigned long)iblock & (sbi->sec_per_clus - 1);
-	if (!offset) {
+	/*
+	 * allocate a cluster according to the following.
+	 * 1) no more available blocks
+	 * 2) not part of fallocate region
+	 */
+	if (!offset && !(iblock < last_block)) {
 		/* TODO: multiple cluster allocation would be desirable. */
 		err = fat_add_cluster(inode);
 		if (err)
@@ -282,13 +288,44 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb,
 	return ret;
 }
 
+static int fat_get_block_bmap(struct inode *inode, sector_t iblock,
+		struct buffer_head *bh_result, int create)
+{
+	struct super_block *sb = inode->i_sb;
+	unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
+	int err;
+	sector_t bmap, last_block;
+	unsigned long mapped_blocks;
+
+	BUG_ON(create != 0);
+
+	last_block = inode->i_blocks >> (sb->s_blocksize_bits - 9);
+
+	if (iblock >= last_block)
+		return 0;
+
+	err = fat_get_mapped_cluster(inode, iblock, last_block, &mapped_blocks,
+		&bmap);
+	if (err)
+		return err;
+
+	if (bmap) {
+		map_bh(bh_result, sb, bmap);
+		max_blocks = min(mapped_blocks, max_blocks);
+	}
+
+	bh_result->b_size = max_blocks << sb->s_blocksize_bits;
+
+	return 0;
+}
+
 static sector_t _fat_bmap(struct address_space *mapping, sector_t block)
 {
 	sector_t blocknr;
 
 	/* fat_get_cluster() assumes the requested blocknr isn't truncated. */
 	down_read(&MSDOS_I(mapping->host)->truncate_lock);
-	blocknr = generic_block_bmap(mapping, block, fat_get_block);
+	blocknr = generic_block_bmap(mapping, block, fat_get_block_bmap);
 	up_read(&MSDOS_I(mapping->host)->truncate_lock);
 
 	return blocknr;
@@ -562,12 +599,35 @@ out:
 
 EXPORT_SYMBOL_GPL(fat_build_inode);
 
+static int __fat_write_inode(struct inode *inode, int wait);
 static void fat_evict_inode(struct inode *inode)
 {
 	truncate_inode_pages_final(&inode->i_data);
 	if (!inode->i_nlink) {
 		inode->i_size = 0;
 		fat_truncate_blocks(inode, 0);
+	} else {
+		/* Release unwritten fallocated blocks on inode eviction. */
+		if ((inode->i_blocks << 9) >
+		    round_up(MSDOS_I(inode)->mmu_private,
+				inode->i_sb->s_blocksize)) {
+			int err;
+
+			fat_truncate_blocks(inode, MSDOS_I(inode)->mmu_private);
+			/* Fallocate results in updating the i_start/iogstart
+			 * for the zero byte file. So, make it return to
+			 * original state during evict and commit it to avoid
+			 * any corruption on the next access to the cluster
+			 * chain for the file.
+			 */
+			err = __fat_write_inode(inode, inode_needs_sync(inode));
+			if (err) {
+				fat_msg(inode->i_sb, KERN_WARNING, "Failed to "
+				"update on disk inode for unused fallocated "
+				"blocks, inode could be corrupted. Please run "
+				"fsck");
+			}
+		}
 	}
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c
index 32602c667b4..7892e6fddb6 100644
--- a/fs/hfsplus/catalog.c
+++ b/fs/hfsplus/catalog.c
@@ -38,21 +38,30 @@ int hfsplus_cat_bin_cmp_key(const hfsplus_btree_key *k1,
 	return hfsplus_strcmp(&k1->cat.name, &k2->cat.name);
 }
 
-void hfsplus_cat_build_key(struct super_block *sb, hfsplus_btree_key *key,
-			   u32 parent, struct qstr *str)
+/* Generates key for catalog file/folders record. */
+int hfsplus_cat_build_key(struct super_block *sb,
+		hfsplus_btree_key *key, u32 parent, struct qstr *str)
 {
-	int len;
+	int len, err;
 
 	key->cat.parent = cpu_to_be32(parent);
-	if (str) {
-		hfsplus_asc2uni(sb, &key->cat.name, HFSPLUS_MAX_STRLEN,
-					str->name, str->len);
-		len = be16_to_cpu(key->cat.name.length);
-	} else {
-		key->cat.name.length = 0;
-		len = 0;
-	}
+	err = hfsplus_asc2uni(sb, &key->cat.name, HFSPLUS_MAX_STRLEN,
+			str->name, str->len);
+	if (unlikely(err < 0))
+		return err;
+
+	len = be16_to_cpu(key->cat.name.length);
 	key->key_len = cpu_to_be16(6 + 2 * len);
+	return 0;
+}
+
+/* Generates key for catalog thread record. */
+void hfsplus_cat_build_key_with_cnid(struct super_block *sb,
+			hfsplus_btree_key *key, u32 parent)
+{
+	key->cat.parent = cpu_to_be32(parent);
+	key->cat.name.length = 0;
+	key->key_len = cpu_to_be16(6);
 }
 
 static void hfsplus_cat_build_key_uni(hfsplus_btree_key *key, u32 parent,
@@ -167,11 +176,16 @@ static int hfsplus_fill_cat_thread(struct super_block *sb,
 				   hfsplus_cat_entry *entry, int type,
 				   u32 parentid, struct qstr *str)
 {
+	int err;
+
 	entry->type = cpu_to_be16(type);
 	entry->thread.reserved = 0;
 	entry->thread.parentID = cpu_to_be32(parentid);
-	hfsplus_asc2uni(sb, &entry->thread.nodeName, HFSPLUS_MAX_STRLEN,
+	err = hfsplus_asc2uni(sb, &entry->thread.nodeName, HFSPLUS_MAX_STRLEN,
 				str->name, str->len);
+	if (unlikely(err < 0))
+		return err;
+
 	return 10 + be16_to_cpu(entry->thread.nodeName.length) * 2;
 }
 
@@ -183,7 +197,7 @@ int hfsplus_find_cat(struct super_block *sb, u32 cnid,
 	int err;
 	u16 type;
 
-	hfsplus_cat_build_key(sb, fd->search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, fd->search_key, cnid);
 	err = hfs_brec_read(fd, &tmp, sizeof(hfsplus_cat_entry));
 	if (err)
 		return err;
@@ -250,11 +264,16 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir,
 	if (err)
 		return err;
 
-	hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid);
 	entry_size = hfsplus_fill_cat_thread(sb, &entry,
 		S_ISDIR(inode->i_mode) ?
 			HFSPLUS_FOLDER_THREAD : HFSPLUS_FILE_THREAD,
 		dir->i_ino, str);
+	if (unlikely(entry_size < 0)) {
+		err = entry_size;
+		goto err2;
+	}
+
 	err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 	if (err != -ENOENT) {
 		if (!err)
@@ -265,7 +284,10 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir,
 	if (err)
 		goto err2;
 
-	hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str);
+	err = hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str);
+	if (unlikely(err))
+		goto err1;
+
 	entry_size = hfsplus_cat_build_record(&entry, cnid, inode);
 	err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 	if (err != -ENOENT) {
@@ -288,7 +310,7 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir,
 	return 0;
 
 err1:
-	hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid);
 	if (!hfs_brec_find(&fd, hfs_find_rec_by_key))
 		hfs_brec_remove(&fd);
 err2:
@@ -313,7 +335,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
 	if (!str) {
 		int len;
 
-		hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
+		hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid);
 		err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 		if (err)
 			goto out;
@@ -329,7 +351,9 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
 			off + 2, len);
 		fd.search_key->key_len = cpu_to_be16(6 + len);
 	} else
-		hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str);
+		err = hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str);
+		if (unlikely(err))
+			goto out;
 
 	err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 	if (err)
@@ -360,7 +384,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
 	if (err)
 		goto out;
 
-	hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid);
 	err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 	if (err)
 		goto out;
@@ -405,7 +429,11 @@ int hfsplus_rename_cat(u32 cnid,
 	dst_fd = src_fd;
 
 	/* find the old dir entry and read the data */
-	hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name);
+	err = hfsplus_cat_build_key(sb, src_fd.search_key,
+			src_dir->i_ino, src_name);
+	if (unlikely(err))
+		goto out;
+
 	err = hfs_brec_find(&src_fd, hfs_find_rec_by_key);
 	if (err)
 		goto out;
@@ -419,7 +447,11 @@ int hfsplus_rename_cat(u32 cnid,
 	type = be16_to_cpu(entry.type);
 
 	/* create new dir entry with the data from the old entry */
-	hfsplus_cat_build_key(sb, dst_fd.search_key, dst_dir->i_ino, dst_name);
+	err = hfsplus_cat_build_key(sb, dst_fd.search_key,
+			dst_dir->i_ino, dst_name);
+	if (unlikely(err))
+		goto out;
+
 	err = hfs_brec_find(&dst_fd, hfs_find_rec_by_key);
 	if (err != -ENOENT) {
 		if (!err)
@@ -436,7 +468,11 @@ int hfsplus_rename_cat(u32 cnid,
 	dst_dir->i_mtime = dst_dir->i_ctime = CURRENT_TIME_SEC;
 
 	/* finally remove the old entry */
-	hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name);
+	err = hfsplus_cat_build_key(sb, src_fd.search_key,
+			src_dir->i_ino, src_name);
+	if (unlikely(err))
+		goto out;
+
 	err = hfs_brec_find(&src_fd, hfs_find_rec_by_key);
 	if (err)
 		goto out;
@@ -449,7 +485,7 @@ int hfsplus_rename_cat(u32 cnid,
 	src_dir->i_mtime = src_dir->i_ctime = CURRENT_TIME_SEC;
 
 	/* remove old thread entry */
-	hfsplus_cat_build_key(sb, src_fd.search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, src_fd.search_key, cnid);
 	err = hfs_brec_find(&src_fd, hfs_find_rec_by_key);
 	if (err)
 		goto out;
@@ -459,9 +495,14 @@ int hfsplus_rename_cat(u32 cnid,
 		goto out;
 
 	/* create new thread entry */
-	hfsplus_cat_build_key(sb, dst_fd.search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, dst_fd.search_key, cnid);
 	entry_size = hfsplus_fill_cat_thread(sb, &entry, type,
 		dst_dir->i_ino, dst_name);
+	if (unlikely(entry_size < 0)) {
+		err = entry_size;
+		goto out;
+	}
+
 	err = hfs_brec_find(&dst_fd, hfs_find_rec_by_key);
 	if (err != -ENOENT) {
 		if (!err)
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index 610a3260bef..435bea231cc 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -44,7 +44,10 @@ static struct dentry *hfsplus_lookup(struct inode *dir, struct dentry *dentry,
 	err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
 	if (err)
 		return ERR_PTR(err);
-	hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, &dentry->d_name);
+	err = hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino,
+			&dentry->d_name);
+	if (unlikely(err < 0))
+		goto fail;
 again:
 	err = hfs_brec_read(&fd, &entry, sizeof(entry));
 	if (err) {
@@ -97,9 +100,11 @@ again:
 					be32_to_cpu(entry.file.permissions.dev);
 				str.len = sprintf(name, "iNode%d", linkid);
 				str.name = name;
-				hfsplus_cat_build_key(sb, fd.search_key,
+				err = hfsplus_cat_build_key(sb, fd.search_key,
 					HFSPLUS_SB(sb)->hidden_dir->i_ino,
 					&str);
+				if (unlikely(err < 0))
+					goto fail;
 				goto again;
 			}
 		} else if (!dentry->d_fsdata)
@@ -145,7 +150,7 @@ static int hfsplus_readdir(struct file *file, struct dir_context *ctx)
 		err = -ENOMEM;
 		goto out;
 	}
-	hfsplus_cat_build_key(sb, fd.search_key, inode->i_ino, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, fd.search_key, inode->i_ino);
 	err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 	if (err)
 		goto out;
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index eb5e059f481..b0441d65fa5 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -443,8 +443,10 @@ int hfsplus_cat_case_cmp_key(const hfsplus_btree_key *k1,
 			     const hfsplus_btree_key *k2);
 int hfsplus_cat_bin_cmp_key(const hfsplus_btree_key *k1,
 			    const hfsplus_btree_key *k2);
-void hfsplus_cat_build_key(struct super_block *sb, hfsplus_btree_key *key,
+int hfsplus_cat_build_key(struct super_block *sb, hfsplus_btree_key *key,
 			   u32 parent, struct qstr *str);
+void hfsplus_cat_build_key_with_cnid(struct super_block *sb,
+				     hfsplus_btree_key *key, u32 parent);
 void hfsplus_cat_set_perms(struct inode *inode, struct hfsplus_perm *perms);
 int hfsplus_find_cat(struct super_block *sb, u32 cnid,
 		     struct hfs_find_data *fd);
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 4cf2024b87d..593af2fdcc2 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -515,7 +515,9 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 	err = hfs_find_init(sbi->cat_tree, &fd);
 	if (err)
 		goto out_put_root;
-	hfsplus_cat_build_key(sb, fd.search_key, HFSPLUS_ROOT_CNID, &str);
+	err = hfsplus_cat_build_key(sb, fd.search_key, HFSPLUS_ROOT_CNID, &str);
+	if (unlikely(err < 0))
+		goto out_put_root;
 	if (!hfs_brec_read(&fd, &entry, sizeof(entry))) {
 		hfs_find_exit(&fd);
 		if (entry.type != cpu_to_be16(HFSPLUS_FOLDER))
diff --git a/fs/mpage.c b/fs/mpage.c
index 3e79220baba..587c7ed4185 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -482,6 +482,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
 	struct buffer_head map_bh;
 	loff_t i_size = i_size_read(inode);
 	int ret = 0;
+	int wr = (wbc->sync_mode == WB_SYNC_ALL ?  WRITE_SYNC : WRITE);
 
 	if (page_has_buffers(page)) {
 		struct buffer_head *head = page_buffers(page);
@@ -590,7 +591,7 @@ page_is_mapped:
 	 * This page will go to BIO.  Do we need to send this BIO off first?
 	 */
 	if (bio && mpd->last_block_in_bio != blocks[0] - 1)
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 
 alloc_new:
 	if (bio == NULL) {
@@ -614,7 +615,7 @@ alloc_new:
 	 */
 	length = first_unmapped << blkbits;
 	if (bio_add_page(bio, page, length, 0) < length) {
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 		goto alloc_new;
 	}
 
@@ -624,7 +625,7 @@ alloc_new:
 	set_page_writeback(page);
 	unlock_page(page);
 	if (boundary || (first_unmapped != blocks_per_page)) {
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 		if (boundary_block) {
 			write_boundary_block(boundary_bdev,
 					boundary_block, 1 << blkbits);
@@ -636,7 +637,7 @@ alloc_new:
 
 confused:
 	if (bio)
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 
 	if (mpd->use_writepage) {
 		ret = mapping->a_ops->writepage(page, wbc);
@@ -692,8 +693,11 @@ mpage_writepages(struct address_space *mapping,
 		};
 
 		ret = write_cache_pages(mapping, wbc, __mpage_writepage, &mpd);
-		if (mpd.bio)
-			mpage_bio_submit(WRITE, mpd.bio);
+		if (mpd.bio) {
+			int wr = (wbc->sync_mode == WB_SYNC_ALL ?
+				  WRITE_SYNC : WRITE);
+			mpage_bio_submit(wr, mpd.bio);
+		}
 	}
 	blk_finish_plug(&plug);
 	return ret;
@@ -710,8 +714,11 @@ int mpage_writepage(struct page *page, get_block_t get_block,
 		.use_writepage = 0,
 	};
 	int ret = __mpage_writepage(page, wbc, &mpd);
-	if (mpd.bio)
-		mpage_bio_submit(WRITE, mpd.bio);
+	if (mpd.bio) {
+		int wr = (wbc->sync_mode == WB_SYNC_ALL ?
+			  WRITE_SYNC : WRITE);
+		mpage_bio_submit(wr, mpd.bio);
+	}
 	return ret;
 }
 EXPORT_SYMBOL(mpage_writepage);
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index a93bf989225..fcae9ef1a32 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -5662,7 +5662,7 @@ int ocfs2_remove_btree_range(struct inode *inode,
 			     struct ocfs2_extent_tree *et,
 			     u32 cpos, u32 phys_cpos, u32 len, int flags,
 			     struct ocfs2_cached_dealloc_ctxt *dealloc,
-			     u64 refcount_loc)
+			     u64 refcount_loc, bool refcount_tree_locked)
 {
 	int ret, credits = 0, extra_blocks = 0;
 	u64 phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos);
@@ -5676,11 +5676,13 @@ int ocfs2_remove_btree_range(struct inode *inode,
 		BUG_ON(!(OCFS2_I(inode)->ip_dyn_features &
 			 OCFS2_HAS_REFCOUNT_FL));
 
-		ret = ocfs2_lock_refcount_tree(osb, refcount_loc, 1,
-					       &ref_tree, NULL);
-		if (ret) {
-			mlog_errno(ret);
-			goto bail;
+		if (!refcount_tree_locked) {
+			ret = ocfs2_lock_refcount_tree(osb, refcount_loc, 1,
+						       &ref_tree, NULL);
+			if (ret) {
+				mlog_errno(ret);
+				goto bail;
+			}
 		}
 
 		ret = ocfs2_prepare_refcount_change_for_del(inode,
@@ -7021,6 +7023,7 @@ int ocfs2_commit_truncate(struct ocfs2_super *osb,
 	u64 refcount_loc = le64_to_cpu(di->i_refcount_loc);
 	struct ocfs2_extent_tree et;
 	struct ocfs2_cached_dealloc_ctxt dealloc;
+	struct ocfs2_refcount_tree *ref_tree = NULL;
 
 	ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), di_bh);
 	ocfs2_init_dealloc_ctxt(&dealloc);
@@ -7130,9 +7133,18 @@ start:
 
 	phys_cpos = ocfs2_blocks_to_clusters(inode->i_sb, blkno);
 
+	if ((flags & OCFS2_EXT_REFCOUNTED) && trunc_len && !ref_tree) {
+		status = ocfs2_lock_refcount_tree(osb, refcount_loc, 1,
+				&ref_tree, NULL);
+		if (status) {
+			mlog_errno(status);
+			goto bail;
+		}
+	}
+
 	status = ocfs2_remove_btree_range(inode, &et, trunc_cpos,
 					  phys_cpos, trunc_len, flags, &dealloc,
-					  refcount_loc);
+					  refcount_loc, true);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
@@ -7147,6 +7159,8 @@ start:
 	goto start;
 
 bail:
+	if (ref_tree)
+		ocfs2_unlock_refcount_tree(osb, ref_tree, 1);
 
 	ocfs2_schedule_truncate_log_flush(osb, 1);
 
diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h
index ca381c58412..fb09b97db16 100644
--- a/fs/ocfs2/alloc.h
+++ b/fs/ocfs2/alloc.h
@@ -142,7 +142,7 @@ int ocfs2_remove_btree_range(struct inode *inode,
 			     struct ocfs2_extent_tree *et,
 			     u32 cpos, u32 phys_cpos, u32 len, int flags,
 			     struct ocfs2_cached_dealloc_ctxt *dealloc,
-			     u64 refcount_loc);
+			     u64 refcount_loc, bool refcount_tree_locked);
 
 int ocfs2_num_free_extents(struct ocfs2_super *osb,
 			   struct ocfs2_extent_tree *et);
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index d9f222987f2..0aca748e0a7 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -28,6 +28,7 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/mpage.h>
 #include <linux/quotaops.h>
+#include <linux/blkdev.h>
 
 #include <cluster/masklog.h>
 
@@ -47,6 +48,9 @@
 #include "ocfs2_trace.h"
 
 #include "buffer_head_io.h"
+#include "dir.h"
+#include "namei.h"
+#include "sysfile.h"
 
 static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
 				   struct buffer_head *bh_result, int create)
@@ -506,18 +510,21 @@ bail:
  *
  * called like this: dio->get_blocks(dio->inode, fs_startblk,
  * 					fs_count, map_bh, dio->rw == WRITE);
- *
- * Note that we never bother to allocate blocks here, and thus ignore the
- * create argument.
  */
 static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 				     struct buffer_head *bh_result, int create)
 {
 	int ret;
+	u32 cpos = 0;
+	int alloc_locked = 0;
 	u64 p_blkno, inode_blocks, contig_blocks;
 	unsigned int ext_flags;
 	unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits;
 	unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
+	unsigned long len = bh_result->b_size;
+	unsigned int clusters_to_alloc = 0;
+
+	cpos = ocfs2_blocks_to_clusters(inode->i_sb, iblock);
 
 	/* This function won't even be called if the request isn't all
 	 * nicely aligned and of the right size, so there's no need
@@ -539,6 +546,40 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 	/* We should already CoW the refcounted extent in case of create. */
 	BUG_ON(create && (ext_flags & OCFS2_EXT_REFCOUNTED));
 
+	/* allocate blocks if no p_blkno is found, and create == 1 */
+	if (!p_blkno && create) {
+		ret = ocfs2_inode_lock(inode, NULL, 1);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto bail;
+		}
+
+		alloc_locked = 1;
+
+		/* fill hole, allocate blocks can't be larger than the size
+		 * of the hole */
+		clusters_to_alloc = ocfs2_clusters_for_bytes(inode->i_sb, len);
+		if (clusters_to_alloc > contig_blocks)
+			clusters_to_alloc = contig_blocks;
+
+		/* allocate extent and insert them into the extent tree */
+		ret = ocfs2_extend_allocation(inode, cpos,
+				clusters_to_alloc, 0);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto bail;
+		}
+
+		ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
+				&contig_blocks, &ext_flags);
+		if (ret < 0) {
+			mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
+					(unsigned long long)iblock);
+			ret = -EIO;
+			goto bail;
+		}
+	}
+
 	/*
 	 * get_more_blocks() expects us to describe a hole by clearing
 	 * the mapped bit on bh_result().
@@ -556,6 +597,8 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 		contig_blocks = max_blocks;
 	bh_result->b_size = contig_blocks << blocksize_bits;
 bail:
+	if (alloc_locked)
+		ocfs2_inode_unlock(inode, 1);
 	return ret;
 }
 
@@ -597,6 +640,180 @@ static int ocfs2_releasepage(struct page *page, gfp_t wait)
 	return try_to_free_buffers(page);
 }
 
+static int ocfs2_is_overwrite(struct ocfs2_super *osb,
+		struct inode *inode , loff_t offset)
+{
+	int ret = 0;
+	u32 v_cpos = 0;
+	u32 p_cpos = 0;
+	unsigned int num_clusters = 0;
+	unsigned int ext_flags = 0;
+
+	v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset);
+	ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos,
+			&num_clusters, &ext_flags);
+	if (ret < 0) {
+		mlog_errno(ret);
+		return ret;
+	}
+
+	if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN))
+		return 1;
+
+	return 0;
+}
+
+static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
+		struct iov_iter *iter,
+		loff_t offset)
+{
+	ssize_t ret = 0;
+	ssize_t written = 0;
+	bool orphaned = false;
+	int is_overwrite = 0;
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file)->i_mapping->host;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct buffer_head *di_bh = NULL;
+	size_t count = iter->count;
+	journal_t *journal = osb->journal->j_journal;
+	u32 zero_len;
+	int cluster_align;
+	loff_t final_size = offset + count;
+	int append_write = offset >= i_size_read(inode) ? 1 : 0;
+	unsigned int num_clusters = 0;
+	unsigned int ext_flags = 0;
+
+	{
+		u64 o = offset;
+
+		zero_len = do_div(o, 1 << osb->s_clustersize_bits);
+		cluster_align = !!zero_len;
+	}
+
+	/*
+	 * when final_size > inode->i_size, inode->i_size will be
+	 * updated after direct write, so add the inode to orphan
+	 * dir first.
+	 */
+	if (final_size > i_size_read(inode)) {
+		ret = ocfs2_add_inode_to_orphan(osb, inode);
+		if (ret < 0)
+			goto out;
+		orphaned = true;
+	}
+
+	if (append_write) {
+		ret = ocfs2_inode_lock(inode, &di_bh, 1);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto clean_orphan;
+		}
+
+		if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
+			ret = ocfs2_zero_extend(inode, di_bh, offset);
+		else
+			ret = ocfs2_extend_no_holes(inode, di_bh, offset, offset);
+		if (ret < 0) {
+			mlog_errno(ret);
+			ocfs2_inode_unlock(inode, 1);
+			brelse(di_bh);
+			goto clean_orphan;
+		}
+
+		is_overwrite = ocfs2_is_overwrite(osb, inode, offset);
+		if (is_overwrite < 0) {
+			mlog_errno(is_overwrite);
+			ocfs2_inode_unlock(inode, 1);
+			brelse(di_bh);
+			goto clean_orphan;
+		}
+
+		ocfs2_inode_unlock(inode, 1);
+		brelse(di_bh);
+		di_bh = NULL;
+	}
+
+	written = __blockdev_direct_IO(WRITE, iocb, inode, inode->i_sb->s_bdev,
+			iter, offset,
+			ocfs2_direct_IO_get_blocks,
+			ocfs2_dio_end_io, NULL, 0);
+	if (unlikely(written < 0)) {
+		loff_t i_size = i_size_read(inode);
+
+		if (offset + count > i_size) {
+			ret = ocfs2_inode_lock(inode, &di_bh, 1);
+			if (ret < 0) {
+				mlog_errno(ret);
+				goto clean_orphan;
+			}
+
+			if (i_size == i_size_read(inode)) {
+				ret = ocfs2_truncate_file(inode, di_bh,
+						i_size);
+				if (ret < 0) {
+					if (ret != -ENOSPC)
+						mlog_errno(ret);
+
+					ocfs2_inode_unlock(inode, 1);
+					brelse(di_bh);
+					goto clean_orphan;
+				}
+			}
+
+			ocfs2_inode_unlock(inode, 1);
+			brelse(di_bh);
+
+			ret = jbd2_journal_force_commit(journal);
+			if (ret < 0)
+				mlog_errno(ret);
+		}
+	} else if (append_write && !is_overwrite && !cluster_align) {
+		u32 p_cpos = 0;
+		u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset);
+
+		ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos,
+				&num_clusters, &ext_flags);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto clean_orphan;
+		}
+
+		BUG_ON(!p_cpos || (ext_flags & OCFS2_EXT_UNWRITTEN));
+
+		ret = blkdev_issue_zeroout(osb->sb->s_bdev,
+				p_cpos << (osb->s_clustersize_bits - 9),
+				zero_len >> 9,
+				GFP_KERNEL);
+		if (ret < 0)
+			mlog_errno(ret);
+	}
+
+clean_orphan:
+	if (orphaned) {
+		int tmp_ret;
+		int update_isize = written > 0 ? 1 : 0;
+		loff_t end = update_isize ? offset + written : 0;
+		tmp_ret = ocfs2_del_inode_from_orphan(osb, inode,
+				update_isize, end);
+		if (tmp_ret < 0) {
+			ret = tmp_ret;
+			goto out;
+		}
+
+		tmp_ret = jbd2_journal_force_commit(journal);
+		if (tmp_ret < 0) {
+			ret = tmp_ret;
+			mlog_errno(tmp_ret);
+		}
+	}
+
+out:
+	if (ret >= 0)
+		ret = written;
+	return ret;
+}
+
 static ssize_t ocfs2_direct_IO(int rw,
 			       struct kiocb *iocb,
 			       struct iov_iter *iter,
@@ -604,6 +821,9 @@ static ssize_t ocfs2_direct_IO(int rw,
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file)->i_mapping->host;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	int full_coherency = !(osb->s_mount_opt &
+			OCFS2_MOUNT_COHERENCY_BUFFERED);
 
 	/*
 	 * Fallback to buffered I/O if we see an inode without
@@ -612,14 +832,19 @@ static ssize_t ocfs2_direct_IO(int rw,
 	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
 		return 0;
 
-	/* Fallback to buffered I/O if we are appending. */
-	if (i_size_read(inode) <= offset)
+	/* Fallback to buffered I/O if we are appending and
+	 * concurrent O_DIRECT writes are allowed.
+	 */
+	if (i_size_read(inode) <= offset && !full_coherency)
 		return 0;
 
-	return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev,
+	if (rw == READ)
+		return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev,
 				    iter, offset,
 				    ocfs2_direct_IO_get_blocks,
 				    ocfs2_dio_end_io, NULL, 0);
+	else
+		return ocfs2_direct_IO_write(iocb, iter, offset);
 }
 
 static void ocfs2_figure_cluster_boundaries(struct ocfs2_super *osb,
@@ -894,7 +1119,7 @@ void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages)
 	}
 }
 
-static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
+static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc)
 {
 	int i;
 
@@ -915,7 +1140,11 @@ static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
 		page_cache_release(wc->w_target_page);
 	}
 	ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages);
+}
 
+static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
+{
+	ocfs2_unlock_pages(wc);
 	brelse(wc->w_di_bh);
 	kfree(wc);
 }
@@ -1818,16 +2047,6 @@ try_again:
 		if (ret)
 			goto out_commit;
 	}
-	/*
-	 * We don't want this to fail in ocfs2_write_end(), so do it
-	 * here.
-	 */
-	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
-				      OCFS2_JOURNAL_ACCESS_WRITE);
-	if (ret) {
-		mlog_errno(ret);
-		goto out_quota;
-	}
 
 	/*
 	 * Fill our page array first. That way we've grabbed enough so
@@ -1978,7 +2197,7 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 			   loff_t pos, unsigned len, unsigned copied,
 			   struct page *page, void *fsdata)
 {
-	int i;
+	int i, ret;
 	unsigned from, to, start = pos & (PAGE_CACHE_SIZE - 1);
 	struct inode *inode = mapping->host;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
@@ -2028,6 +2247,14 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 		}
 	}
 
+	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		copied = ret;
+		mlog_errno(ret);
+		goto out;
+	}
+
 out_write_size:
 	pos += copied;
 	if (pos > i_size_read(inode)) {
@@ -2042,11 +2269,20 @@ out_write_size:
 	ocfs2_update_inode_fsync_trans(handle, inode, 1);
 	ocfs2_journal_dirty(handle, wc->w_di_bh);
 
+out:
+	/* unlock pages before dealloc since it needs acquiring j_trans_barrier
+	 * lock, or it will cause a deadlock since journal commit threads holds
+	 * this lock and will ask for the page lock when flushing the data.
+	 * put it here to preserve the unlock order.
+	 */
+	ocfs2_unlock_pages(wc);
+
 	ocfs2_commit_trans(osb, handle);
 
 	ocfs2_run_deallocs(osb, &wc->w_dealloc);
 
-	ocfs2_free_write_ctxt(wc);
+	brelse(wc->w_di_bh);
+	kfree(wc);
 
 	return copied;
 }
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index 79d56dc981b..319e786175a 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -4479,7 +4479,7 @@ int ocfs2_dx_dir_truncate(struct inode *dir, struct buffer_head *di_bh)
 		p_cpos = ocfs2_blocks_to_clusters(dir->i_sb, blkno);
 
 		ret = ocfs2_remove_btree_range(dir, &et, cpos, p_cpos, clen, 0,
-					       &dealloc, 0);
+					       &dealloc, 0, false);
 		if (ret) {
 			mlog_errno(ret);
 			goto out;
diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c
index b46278f9ae4..fd6bbbbd7d7 100644
--- a/fs/ocfs2/dlm/dlmast.c
+++ b/fs/ocfs2/dlm/dlmast.c
@@ -385,8 +385,12 @@ int dlm_proxy_ast_handler(struct o2net_msg *msg, u32 len, void *data,
 		head = &res->granted;
 
 	list_for_each_entry(lock, head, list) {
-		if (lock->ml.cookie == cookie)
+		/* if lock is found but unlock is pending ignore the bast */
+		if (lock->ml.cookie == cookie) {
+			if (lock->unlock_pending)
+				break;
 			goto do_ast;
+		}
 	}
 
 	mlog(0, "Got %sast for unknown lock! cookie=%u:%llu, name=%.*s, "
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 3689b359204..b26b476e1f0 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -498,16 +498,6 @@ static void dlm_lockres_release(struct kref *kref)
 	mlog(0, "destroying lockres %.*s\n", res->lockname.len,
 	     res->lockname.name);
 
-	spin_lock(&dlm->track_lock);
-	if (!list_empty(&res->tracking))
-		list_del_init(&res->tracking);
-	else {
-		mlog(ML_ERROR, "Resource %.*s not on the Tracking list\n",
-		     res->lockname.len, res->lockname.name);
-		dlm_print_one_lock_resource(res);
-	}
-	spin_unlock(&dlm->track_lock);
-
 	atomic_dec(&dlm->res_cur_count);
 
 	if (!hlist_unhashed(&res->hash_node) ||
@@ -695,14 +685,6 @@ void __dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm,
 			res->inflight_assert_workers);
 }
 
-static void dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm,
-		struct dlm_lock_resource *res)
-{
-	spin_lock(&res->spinlock);
-	__dlm_lockres_grab_inflight_worker(dlm, res);
-	spin_unlock(&res->spinlock);
-}
-
 static void __dlm_lockres_drop_inflight_worker(struct dlm_ctxt *dlm,
 		struct dlm_lock_resource *res)
 {
@@ -1646,6 +1628,7 @@ send_response:
 		}
 		mlog(0, "%u is the owner of %.*s, cleaning everyone else\n",
 			     dlm->node_num, res->lockname.len, res->lockname.name);
+		spin_lock(&res->spinlock);
 		ret = dlm_dispatch_assert_master(dlm, res, 0, request->node_idx,
 						 DLM_ASSERT_MASTER_MLE_CLEANUP);
 		if (ret < 0) {
@@ -1653,7 +1636,8 @@ send_response:
 			response = DLM_MASTER_RESP_ERROR;
 			dlm_lockres_put(res);
 		} else
-			dlm_lockres_grab_inflight_worker(dlm, res);
+			__dlm_lockres_grab_inflight_worker(dlm, res);
+		spin_unlock(&res->spinlock);
 	} else {
 		if (res)
 			dlm_lockres_put(res);
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index 69aac6f088a..2e5e6d5fffe 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -211,6 +211,16 @@ static void dlm_purge_lockres(struct dlm_ctxt *dlm,
 
 	__dlm_unhash_lockres(dlm, res);
 
+	spin_lock(&dlm->track_lock);
+	if (!list_empty(&res->tracking))
+		list_del_init(&res->tracking);
+	else {
+		mlog(ML_ERROR, "Resource %.*s not on the Tracking list\n",
+				res->lockname.len, res->lockname.name);
+		__dlm_print_one_lock_resource(res);
+	}
+	spin_unlock(&dlm->track_lock);
+
 	/* lockres is not in the hash now.  drop the flag and wake up
 	 * any processes waiting in dlm_get_lock_resource. */
 	if (!master) {
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 69fb9f75b08..38f3a562d77 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -295,7 +295,7 @@ out:
 	return ret;
 }
 
-static int ocfs2_set_inode_size(handle_t *handle,
+int ocfs2_set_inode_size(handle_t *handle,
 				struct inode *inode,
 				struct buffer_head *fe_bh,
 				u64 new_i_size)
@@ -441,7 +441,7 @@ out:
 	return status;
 }
 
-static int ocfs2_truncate_file(struct inode *inode,
+int ocfs2_truncate_file(struct inode *inode,
 			       struct buffer_head *di_bh,
 			       u64 new_i_size)
 {
@@ -709,6 +709,13 @@ leave:
 	return status;
 }
 
+int ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
+		u32 clusters_to_add, int mark_unwritten)
+{
+	return __ocfs2_extend_allocation(inode, logical_start,
+			clusters_to_add, mark_unwritten);
+}
+
 /*
  * While a write will already be ordering the data, a truncate will not.
  * Thus, we need to explicitly order the zeroed pages.
@@ -1352,44 +1359,6 @@ out:
 	return ret;
 }
 
-/*
- * Will look for holes and unwritten extents in the range starting at
- * pos for count bytes (inclusive).
- */
-static int ocfs2_check_range_for_holes(struct inode *inode, loff_t pos,
-				       size_t count)
-{
-	int ret = 0;
-	unsigned int extent_flags;
-	u32 cpos, clusters, extent_len, phys_cpos;
-	struct super_block *sb = inode->i_sb;
-
-	cpos = pos >> OCFS2_SB(sb)->s_clustersize_bits;
-	clusters = ocfs2_clusters_for_bytes(sb, pos + count) - cpos;
-
-	while (clusters) {
-		ret = ocfs2_get_clusters(inode, cpos, &phys_cpos, &extent_len,
-					 &extent_flags);
-		if (ret < 0) {
-			mlog_errno(ret);
-			goto out;
-		}
-
-		if (phys_cpos == 0 || (extent_flags & OCFS2_EXT_UNWRITTEN)) {
-			ret = 1;
-			break;
-		}
-
-		if (extent_len > clusters)
-			extent_len = clusters;
-
-		clusters -= extent_len;
-		cpos += extent_len;
-	}
-out:
-	return ret;
-}
-
 static int ocfs2_write_remove_suid(struct inode *inode)
 {
 	int ret;
@@ -1803,7 +1772,7 @@ static int ocfs2_remove_inode_range(struct inode *inode,
 
 		ret = ocfs2_remove_btree_range(inode, &et, trunc_cpos,
 					       phys_cpos, trunc_len, flags,
-					       &dealloc, refcount_loc);
+					       &dealloc, refcount_loc, false);
 		if (ret < 0) {
 			mlog_errno(ret);
 			goto out;
@@ -2109,6 +2078,9 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
 	loff_t saved_pos = 0, end;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	int full_coherency = !(osb->s_mount_opt &
+		OCFS2_MOUNT_COHERENCY_BUFFERED);
 
 	/*
 	 * We start with a read level meta lock and only jump to an ex
@@ -2197,23 +2169,11 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 		 * one node could wind up truncating another
 		 * nodes writes.
 		 */
-		if (end > i_size_read(inode)) {
+		if (end > i_size_read(inode) && !full_coherency) {
 			*direct_io = 0;
 			break;
 		}
 
-		/*
-		 * We don't fill holes during direct io, so
-		 * check for them here. If any are found, the
-		 * caller will have to retake some cluster
-		 * locks and initiate the io as buffered.
-		 */
-		ret = ocfs2_check_range_for_holes(inode, saved_pos, count);
-		if (ret == 1) {
-			*direct_io = 0;
-			ret = 0;
-		} else if (ret < 0)
-			mlog_errno(ret);
 		break;
 	}
 
@@ -2243,6 +2203,7 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 	u32 old_clusters;
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
+	struct address_space *mapping = file->f_mapping;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	int full_coherency = !(osb->s_mount_opt &
 			       OCFS2_MOUNT_COHERENCY_BUFFERED);
@@ -2357,11 +2318,50 @@ relock:
 
 	iov_iter_truncate(from, count);
 	if (direct_io) {
+		loff_t endbyte;
+		ssize_t written_buffered;
 		written = generic_file_direct_write(iocb, from, *ppos);
-		if (written < 0) {
+		if (written < 0 || written == count) {
 			ret = written;
 			goto out_dio;
 		}
+
+		/*
+		 * direct-io write to a hole: fall through to buffered I/O
+		 * for completing the rest of the request.
+		 */
+		count -= written;
+		written_buffered = generic_perform_write(file, from, *ppos);
+		/*
+		 * If generic_file_buffered_write() returned a synchronous error
+		 * then we want to return the number of bytes which were
+		 * direct-written, or the error code if that was zero. Note
+		 * that this differs from normal direct-io semantics, which
+		 * will return -EFOO even if some bytes were written.
+		 */
+		if (written_buffered < 0) {
+			ret = written_buffered;
+			goto out;
+		}
+
+		/* We need to ensure that the page cache pages are written to
+		 * disk and invalidated to preserve the expected O_DIRECT
+		 * semantics.
+		 */
+		endbyte = *ppos + written_buffered - written - 1;
+		ret = filemap_write_and_wait_range(file->f_mapping, *ppos,
+				endbyte);
+		if (ret == 0) {
+			written = written_buffered;
+			invalidate_mapping_pages(mapping,
+					*ppos >> PAGE_CACHE_SHIFT,
+					endbyte >> PAGE_CACHE_SHIFT);
+		} else {
+			/*
+			 * We don't know how much we wrote, so just return
+			 * the number of bytes which were direct-written
+			 */
+		}
 	} else {
 		current->backing_dev_info = file->f_mapping->backing_dev_info;
 		written = generic_perform_write(file, from, *ppos);
diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h
index 97bf761c9e7..e8c62f22215 100644
--- a/fs/ocfs2/file.h
+++ b/fs/ocfs2/file.h
@@ -51,13 +51,22 @@ int ocfs2_add_inode_data(struct ocfs2_super *osb,
 			 struct ocfs2_alloc_context *data_ac,
 			 struct ocfs2_alloc_context *meta_ac,
 			 enum ocfs2_alloc_restarted *reason_ret);
+int ocfs2_set_inode_size(handle_t *handle,
+		struct inode *inode,
+		struct buffer_head *fe_bh,
+		u64 new_i_size);
 int ocfs2_simple_size_update(struct inode *inode,
 			     struct buffer_head *di_bh,
 			     u64 new_i_size);
+int ocfs2_truncate_file(struct inode *inode,
+		struct buffer_head *di_bh,
+		u64 new_i_size);
 int ocfs2_extend_no_holes(struct inode *inode, struct buffer_head *di_bh,
 			  u64 new_i_size, u64 zero_to);
 int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh,
 		      loff_t zero_to);
+int ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
+		u32 clusters_to_add, int mark_unwritten);
 int ocfs2_setattr(struct dentry *dentry, struct iattr *attr);
 int ocfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		  struct kstat *stat);
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index c8b25de9efb..ae1a5e9f8f1 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -1191,17 +1191,9 @@ void ocfs2_evict_inode(struct inode *inode)
 int ocfs2_drop_inode(struct inode *inode)
 {
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
-	int res;
-
 	trace_ocfs2_drop_inode((unsigned long long)oi->ip_blkno,
 				inode->i_nlink, oi->ip_flags);
-
-	if (oi->ip_flags & OCFS2_INODE_MAYBE_ORPHANED)
-		res = 1;
-	else
-		res = generic_drop_inode(inode);
-
-	return res;
+	return 1;
 }
 
 /*
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index ca3431ee7f2..5e86b247c82 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -81,6 +81,8 @@ struct ocfs2_inode_info
 	tid_t i_sync_tid;
 	tid_t i_datasync_tid;
 
+	wait_queue_head_t append_dio_wq;
+
 	struct dquot *i_dquot[MAXQUOTAS];
 };
 
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 4f502382180..e238bbc27a3 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -50,6 +50,8 @@
 #include "sysfile.h"
 #include "uptodate.h"
 #include "quota.h"
+#include "file.h"
+#include "namei.h"
 
 #include "buffer_head_io.h"
 #include "ocfs2_trace.h"
@@ -69,13 +71,15 @@ static int ocfs2_journal_toggle_dirty(struct ocfs2_super *osb,
 static int ocfs2_trylock_journal(struct ocfs2_super *osb,
 				 int slot_num);
 static int ocfs2_recover_orphans(struct ocfs2_super *osb,
-				 int slot);
+				 int slot,
+				 enum ocfs2_orphan_reco_type orphan_reco_type);
 static int ocfs2_commit_thread(void *arg);
 static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
 					    int slot_num,
 					    struct ocfs2_dinode *la_dinode,
 					    struct ocfs2_dinode *tl_dinode,
-					    struct ocfs2_quota_recovery *qrec);
+					    struct ocfs2_quota_recovery *qrec,
+					    enum ocfs2_orphan_reco_type orphan_reco_type);
 
 static inline int ocfs2_wait_on_mount(struct ocfs2_super *osb)
 {
@@ -149,7 +153,8 @@ int ocfs2_compute_replay_slots(struct ocfs2_super *osb)
 	return 0;
 }
 
-void ocfs2_queue_replay_slots(struct ocfs2_super *osb)
+void ocfs2_queue_replay_slots(struct ocfs2_super *osb,
+		enum ocfs2_orphan_reco_type orphan_reco_type)
 {
 	struct ocfs2_replay_map *replay_map = osb->replay_map;
 	int i;
@@ -163,7 +168,8 @@ void ocfs2_queue_replay_slots(struct ocfs2_super *osb)
 	for (i = 0; i < replay_map->rm_slots; i++)
 		if (replay_map->rm_replay_slots[i])
 			ocfs2_queue_recovery_completion(osb->journal, i, NULL,
-							NULL, NULL);
+							NULL, NULL,
+							orphan_reco_type);
 	replay_map->rm_state = REPLAY_DONE;
 }
 
@@ -1174,6 +1180,7 @@ struct ocfs2_la_recovery_item {
 	struct ocfs2_dinode	*lri_la_dinode;
 	struct ocfs2_dinode	*lri_tl_dinode;
 	struct ocfs2_quota_recovery *lri_qrec;
+	enum ocfs2_orphan_reco_type  lri_orphan_reco_type;
 };
 
 /* Does the second half of the recovery process. By this point, the
@@ -1195,6 +1202,7 @@ void ocfs2_complete_recovery(struct work_struct *work)
 	struct ocfs2_dinode *la_dinode, *tl_dinode;
 	struct ocfs2_la_recovery_item *item, *n;
 	struct ocfs2_quota_recovery *qrec;
+	enum ocfs2_orphan_reco_type orphan_reco_type;
 	LIST_HEAD(tmp_la_list);
 
 	trace_ocfs2_complete_recovery(
@@ -1212,6 +1220,7 @@ void ocfs2_complete_recovery(struct work_struct *work)
 		la_dinode = item->lri_la_dinode;
 		tl_dinode = item->lri_tl_dinode;
 		qrec = item->lri_qrec;
+		orphan_reco_type = item->lri_orphan_reco_type;
 
 		trace_ocfs2_complete_recovery_slot(item->lri_slot,
 			la_dinode ? le64_to_cpu(la_dinode->i_blkno) : 0,
@@ -1236,7 +1245,8 @@ void ocfs2_complete_recovery(struct work_struct *work)
 			kfree(tl_dinode);
 		}
 
-		ret = ocfs2_recover_orphans(osb, item->lri_slot);
+		ret = ocfs2_recover_orphans(osb, item->lri_slot,
+				orphan_reco_type);
 		if (ret < 0)
 			mlog_errno(ret);
 
@@ -1261,7 +1271,8 @@ static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
 					    int slot_num,
 					    struct ocfs2_dinode *la_dinode,
 					    struct ocfs2_dinode *tl_dinode,
-					    struct ocfs2_quota_recovery *qrec)
+					    struct ocfs2_quota_recovery *qrec,
+					    enum ocfs2_orphan_reco_type orphan_reco_type)
 {
 	struct ocfs2_la_recovery_item *item;
 
@@ -1285,6 +1296,7 @@ static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
 	item->lri_slot = slot_num;
 	item->lri_tl_dinode = tl_dinode;
 	item->lri_qrec = qrec;
+	item->lri_orphan_reco_type = orphan_reco_type;
 
 	spin_lock(&journal->j_lock);
 	list_add_tail(&item->lri_list, &journal->j_la_cleanups);
@@ -1304,7 +1316,8 @@ void ocfs2_complete_mount_recovery(struct ocfs2_super *osb)
 	/* No need to queue up our truncate_log as regular cleanup will catch
 	 * that */
 	ocfs2_queue_recovery_completion(journal, osb->slot_num,
-					osb->local_alloc_copy, NULL, NULL);
+					osb->local_alloc_copy, NULL, NULL,
+					ORPHAN_NEED_TRUNCATE);
 	ocfs2_schedule_truncate_log_flush(osb, 0);
 
 	osb->local_alloc_copy = NULL;
@@ -1312,7 +1325,7 @@ void ocfs2_complete_mount_recovery(struct ocfs2_super *osb)
 
 	/* queue to recover orphan slots for all offline slots */
 	ocfs2_replay_map_set_state(osb, REPLAY_NEEDED);
-	ocfs2_queue_replay_slots(osb);
+	ocfs2_queue_replay_slots(osb, ORPHAN_NEED_TRUNCATE);
 	ocfs2_free_replay_slots(osb);
 }
 
@@ -1323,7 +1336,8 @@ void ocfs2_complete_quota_recovery(struct ocfs2_super *osb)
 						osb->slot_num,
 						NULL,
 						NULL,
-						osb->quota_rec);
+						osb->quota_rec,
+						ORPHAN_NEED_TRUNCATE);
 		osb->quota_rec = NULL;
 	}
 }
@@ -1360,7 +1374,7 @@ restart:
 
 	/* queue recovery for our own slot */
 	ocfs2_queue_recovery_completion(osb->journal, osb->slot_num, NULL,
-					NULL, NULL);
+					NULL, NULL, ORPHAN_NO_NEED_TRUNCATE);
 
 	spin_lock(&osb->osb_lock);
 	while (rm->rm_used) {
@@ -1419,13 +1433,14 @@ skip_recovery:
 			continue;
 		}
 		ocfs2_queue_recovery_completion(osb->journal, rm_quota[i],
-						NULL, NULL, qrec);
+						NULL, NULL, qrec,
+						ORPHAN_NEED_TRUNCATE);
 	}
 
 	ocfs2_super_unlock(osb, 1);
 
 	/* queue recovery for offline slots */
-	ocfs2_queue_replay_slots(osb);
+	ocfs2_queue_replay_slots(osb, ORPHAN_NEED_TRUNCATE);
 
 bail:
 	mutex_lock(&osb->recovery_lock);
@@ -1712,7 +1727,7 @@ static int ocfs2_recover_node(struct ocfs2_super *osb,
 
 	/* This will kfree the memory pointed to by la_copy and tl_copy */
 	ocfs2_queue_recovery_completion(osb->journal, slot_num, la_copy,
-					tl_copy, NULL);
+					tl_copy, NULL, ORPHAN_NEED_TRUNCATE);
 
 	status = 0;
 done:
@@ -1902,7 +1917,7 @@ void ocfs2_queue_orphan_scan(struct ocfs2_super *osb)
 
 	for (i = 0; i < osb->max_slots; i++)
 		ocfs2_queue_recovery_completion(osb->journal, i, NULL, NULL,
-						NULL);
+						NULL, ORPHAN_NO_NEED_TRUNCATE);
 	/*
 	 * We queued a recovery on orphan slots, increment the sequence
 	 * number and update LVB so other node will skip the scan for a while
@@ -2090,6 +2105,39 @@ static void ocfs2_clear_recovering_orphan_dir(struct ocfs2_super *osb,
 	ocfs2_node_map_clear_bit(osb, &osb->osb_recovering_orphan_dirs, slot);
 }
 
+static int ocfs2_truncate_file_locked(struct inode *inode)
+{
+	struct buffer_head *di_bh = NULL;
+	int ret;
+
+	ret = ocfs2_rw_lock(inode, 1);
+	if (ret < 0) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (ret < 0) {
+		ocfs2_rw_unlock(inode, 1);
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_truncate_file(inode, di_bh, i_size_read(inode));
+	if (ret < 0) {
+		if (ret != -ENOSPC)
+			mlog_errno(ret);
+		ret = -ENOSPC;
+	}
+
+	ocfs2_inode_unlock(inode, 1);
+	ocfs2_rw_unlock(inode, 1);
+	brelse(di_bh);
+
+out:
+	return ret;
+}
+
 /*
  * Orphan recovery. Each mounted node has it's own orphan dir which we
  * must run during recovery. Our strategy here is to build a list of
@@ -2109,7 +2157,8 @@ static void ocfs2_clear_recovering_orphan_dir(struct ocfs2_super *osb,
  *   advertising our state to ocfs2_delete_inode().
  */
 static int ocfs2_recover_orphans(struct ocfs2_super *osb,
-				 int slot)
+				 int slot,
+				 enum ocfs2_orphan_reco_type orphan_reco_type)
 {
 	int ret = 0;
 	struct inode *inode = NULL;
@@ -2134,12 +2183,38 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
 
 		iter = oi->ip_next_orphan;
 
-		spin_lock(&oi->ip_lock);
-		/* Set the proper information to get us going into
-		 * ocfs2_delete_inode. */
-		oi->ip_flags |= OCFS2_INODE_MAYBE_ORPHANED;
-		spin_unlock(&oi->ip_lock);
+		/*
+		 * We need to take and drop the inode lock to
+		 * force read inode from disk.
+		 */
+		ret = ocfs2_inode_lock(inode, NULL, 0);
+		if (ret) {
+			mlog_errno(ret);
+			goto next;
+		}
+		ocfs2_inode_unlock(inode, 0);
+
+		if (inode->i_nlink == 0) {
+			spin_lock(&oi->ip_lock);
+			/* Set the proper information to get us going into
+			 * ocfs2_delete_inode. */
+			oi->ip_flags |= OCFS2_INODE_MAYBE_ORPHANED;
+			spin_unlock(&oi->ip_lock);
+		} else if (orphan_reco_type == ORPHAN_NEED_TRUNCATE) {
+			ret = ocfs2_truncate_file_locked(inode);
+			if (ret) {
+				mlog_errno(ret);
+				goto next;
+			}
+
+			ret = ocfs2_del_inode_from_orphan(osb, inode, 0, 0);
+			if (ret)
+				mlog_errno(ret);
+
+			wake_up(&OCFS2_I(inode)->append_dio_wq);
+		} /* else if ORPHAN_NO_NEED_TRUNCATE, do nothing */
 
+next:
 		iput(inode);
 
 		inode = iter;
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 7f8cde94abf..f4cd3c3e9fb 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -472,6 +472,11 @@ static inline int ocfs2_unlink_credits(struct super_block *sb)
  * orphan dir index leaf */
 #define OCFS2_DELETE_INODE_CREDITS (3 * OCFS2_INODE_UPDATE_CREDITS + 4)
 
+/* dinode + orphan dir dinode + extent tree leaf block + orphan dir entry +
+ * orphan dir index root + orphan dir index leaf */
+#define OCFS2_INODE_ADD_TO_ORPHAN_CREDITS  (2 * OCFS2_INODE_UPDATE_CREDITS + 4)
+#define OCFS2_INODE_DEL_FROM_ORPHAN_CREDITS  OCFS2_INODE_ADD_TO_ORPHAN_CREDITS
+
 /* dinode update, old dir dinode update, new dir dinode update, old
  * dir dir entry, new dir dir entry, dir entry update for renaming
  * directory + target unlink + 3 x dir index leaves */
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index b931e04e338..f15b560e1bb 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -81,6 +81,12 @@ static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb,
 				    char *name,
 				    struct ocfs2_dir_lookup_result *lookup);
 
+static int ocfs2_dio_prepare_orphan_dir(struct ocfs2_super *osb,
+		struct inode **ret_orphan_dir,
+		u64 blkno,
+		char *name,
+		struct ocfs2_dir_lookup_result *lookup);
+
 static int ocfs2_orphan_add(struct ocfs2_super *osb,
 			    handle_t *handle,
 			    struct inode *inode,
@@ -89,6 +95,15 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb,
 			    struct ocfs2_dir_lookup_result *lookup,
 			    struct inode *orphan_dir_inode);
 
+static int ocfs2_dio_orphan_add(struct ocfs2_super *osb,
+		handle_t *handle,
+		struct inode *inode,
+		struct buffer_head *fe_bh,
+		char *name,
+		struct ocfs2_dir_lookup_result *lookup,
+		struct inode *orphan_dir_inode,
+		bool orphaned);
+
 static int ocfs2_create_symlink_data(struct ocfs2_super *osb,
 				     handle_t *handle,
 				     struct inode *inode,
@@ -2137,6 +2152,51 @@ out:
 	return ret;
 }
 
+/**
+ * Copy from ocfs2_prepare_orphan_dir(). The difference:
+ * It will still lock orphan dir if entry exists.
+ * Caller must take care of -EEXIST and responsible for unlock.
+*/
+static int ocfs2_dio_prepare_orphan_dir(struct ocfs2_super *osb,
+				    struct inode **ret_orphan_dir,
+				    u64 blkno,
+				    char *name,
+				    struct ocfs2_dir_lookup_result *lookup)
+{
+	struct inode *orphan_dir_inode = NULL;
+	struct buffer_head *orphan_dir_bh = NULL;
+	int ret = 0;
+
+	ret = ocfs2_lookup_lock_orphan_dir(osb, &orphan_dir_inode,
+					   &orphan_dir_bh);
+	if (ret < 0) {
+		mlog_errno(ret);
+		return ret;
+	}
+
+	ret = __ocfs2_prepare_orphan_dir(orphan_dir_inode, orphan_dir_bh,
+					 blkno, name, lookup);
+	if (ret < 0 && ret != -EEXIST) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	*ret_orphan_dir = orphan_dir_inode;
+
+out:
+	brelse(orphan_dir_bh);
+
+	if (ret && ret != -EEXIST) {
+		ocfs2_inode_unlock(orphan_dir_inode, 1);
+		mutex_unlock(&orphan_dir_inode->i_mutex);
+		iput(orphan_dir_inode);
+	}
+
+	if (ret && ret != -EEXIST)
+		mlog_errno(ret);
+	return ret;
+}
+
 static int ocfs2_orphan_add(struct ocfs2_super *osb,
 			    handle_t *handle,
 			    struct inode *inode,
@@ -2226,6 +2286,100 @@ leave:
 	return status;
 }
 
+/**
+ * Copy from ocfs2_orphan_add, the difference:
+ * 1. Do not add entry if already added.
+ * 2. Update di flags OCFS2_DIO_ORPHANED_FL and record the
+ * orphan slot.
+*/
+static int ocfs2_dio_orphan_add(struct ocfs2_super *osb,
+			    handle_t *handle,
+			    struct inode *inode,
+			    struct buffer_head *fe_bh,
+			    char *name,
+			    struct ocfs2_dir_lookup_result *lookup,
+			    struct inode *orphan_dir_inode,
+			    bool orphaned)
+{
+	struct buffer_head *orphan_dir_bh = NULL;
+	int status = 0;
+	struct ocfs2_dinode *orphan_fe;
+	struct ocfs2_dinode *fe = (struct ocfs2_dinode *) fe_bh->b_data;
+
+	trace_ocfs2_dio_orphan_add_begin(
+				(unsigned long long)OCFS2_I(inode)->ip_blkno);
+
+	status = ocfs2_read_inode_block(orphan_dir_inode, &orphan_dir_bh);
+	if (status < 0) {
+		mlog_errno(status);
+		goto leave;
+	}
+
+	status = ocfs2_journal_access_di(handle,
+					 INODE_CACHE(orphan_dir_inode),
+					 orphan_dir_bh,
+					 OCFS2_JOURNAL_ACCESS_WRITE);
+	if (status < 0) {
+		mlog_errno(status);
+		goto leave;
+	}
+
+	/*
+	 * We're going to journal the change of i_flags and i_dio_orphaned_slot.
+	 * It's safe anyway, though some callers may duplicate the journaling.
+	 * Journaling within the func just make the logic look more
+	 * straightforward.
+	 */
+	status = ocfs2_journal_access_di(handle,
+					 INODE_CACHE(inode),
+					 fe_bh,
+					 OCFS2_JOURNAL_ACCESS_WRITE);
+	if (status < 0) {
+		mlog_errno(status);
+		goto leave;
+	}
+
+	/* we're a cluster, and nlink can change on disk from
+	 * underneath us... */
+	orphan_fe = (struct ocfs2_dinode *) orphan_dir_bh->b_data;
+	if (S_ISDIR(inode->i_mode))
+		ocfs2_add_links_count(orphan_fe, 1);
+	set_nlink(orphan_dir_inode, ocfs2_read_links_count(orphan_fe));
+	ocfs2_journal_dirty(handle, orphan_dir_bh);
+
+	/* It may already be orphaned by ocfs2_unlink/ocfs2_rename */
+	if (!orphaned) {
+		status = __ocfs2_add_entry(handle, orphan_dir_inode, name,
+				   OCFS2_ORPHAN_NAMELEN, inode,
+				   OCFS2_I(inode)->ip_blkno,
+				   orphan_dir_bh, lookup);
+		if (status < 0) {
+			mlog_errno(status);
+			goto rollback;
+		}
+	}
+
+	/* Update flag OCFS2_DIO_ORPHANED_FL and record the orphan slot */
+	fe->i_flags |= cpu_to_le32(OCFS2_DIO_ORPHANED_FL);
+	fe->i_dio_orphaned_slot = cpu_to_le16(osb->slot_num);
+
+	ocfs2_journal_dirty(handle, fe_bh);
+
+	trace_ocfs2_dio_orphan_add_end((unsigned long long)OCFS2_I(inode)->ip_blkno,
+				   osb->slot_num);
+
+rollback:
+	if (status < 0) {
+		if (S_ISDIR(inode->i_mode))
+			ocfs2_add_links_count(orphan_fe, -1);
+		set_nlink(orphan_dir_inode, ocfs2_read_links_count(orphan_fe));
+	}
+
+leave:
+	brelse(orphan_dir_bh);
+
+	return status;
+}
 /* unlike orphan_add, we expect the orphan dir to already be locked here. */
 int ocfs2_orphan_del(struct ocfs2_super *osb,
 		     handle_t *handle,
@@ -2500,6 +2654,200 @@ leave:
 	return status;
 }
 
+static int ocfs2_dio_orphan_recovered(struct inode *inode)
+{
+	int ret;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_dinode *di = NULL;
+
+	ret = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (ret < 0) {
+		mlog_errno(ret);
+		return 0;
+	}
+
+	di = (struct ocfs2_dinode *) di_bh->b_data;
+	ret = !(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL));
+	ocfs2_inode_unlock(inode, 1);
+	brelse(di_bh);
+
+	return ret;
+}
+
+int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
+	struct inode *inode)
+{
+	char orphan_name[OCFS2_ORPHAN_NAMELEN + 1];
+	struct inode *orphan_dir_inode = NULL;
+	struct ocfs2_dir_lookup_result orphan_insert = { NULL, };
+	struct buffer_head *di_bh = NULL;
+	int status = 0;
+	handle_t *handle = NULL;
+	struct ocfs2_dinode *di = NULL;
+	bool orphaned = false;
+
+restart:
+	status = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail;
+	}
+
+	di = (struct ocfs2_dinode *) di_bh->b_data;
+	/*
+	 * Another append dio crashed?
+	 * If so, wait for recovery first.
+	 */
+	if (unlikely(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL))) {
+		ocfs2_inode_unlock(inode, 1);
+		brelse(di_bh);
+		wait_event_interruptible(OCFS2_I(inode)->append_dio_wq,
+				ocfs2_dio_orphan_recovered(inode));
+		goto restart;
+	}
+
+	status = ocfs2_dio_prepare_orphan_dir(osb, &orphan_dir_inode,
+			OCFS2_I(inode)->ip_blkno,
+			orphan_name,
+			&orphan_insert);
+	if (status < 0 && status != -EEXIST) {
+		mlog_errno(status);
+		goto bail_unlock_inode;
+	} else if (status == -EEXIST) {
+		mlog(ML_NOTICE, "inode %llu already added to "
+				"orphan dir %llu.\n",
+				OCFS2_I(inode)->ip_blkno,
+				OCFS2_I(orphan_dir_inode)->ip_blkno);
+		if (!(di->i_flags & cpu_to_le32(OCFS2_ORPHANED_FL))) {
+			mlog_errno(status);
+			goto bail_unlock_orphan;
+		}
+		orphaned = true;
+	}
+
+	handle = ocfs2_start_trans(osb,
+			OCFS2_INODE_ADD_TO_ORPHAN_CREDITS);
+	if (IS_ERR(handle)) {
+		status = PTR_ERR(handle);
+		goto bail_unlock_orphan;
+	}
+
+	status = ocfs2_dio_orphan_add(osb, handle, inode, di_bh, orphan_name,
+			&orphan_insert, orphan_dir_inode, orphaned);
+	if (status)
+		mlog_errno(status);
+
+	ocfs2_commit_trans(osb, handle);
+
+bail_unlock_orphan:
+	ocfs2_inode_unlock(orphan_dir_inode, 1);
+	mutex_unlock(&orphan_dir_inode->i_mutex);
+	iput(orphan_dir_inode);
+
+	ocfs2_free_dir_lookup_result(&orphan_insert);
+
+bail_unlock_inode:
+	ocfs2_inode_unlock(inode, 1);
+	brelse(di_bh);
+
+bail:
+	return status;
+}
+
+int ocfs2_del_inode_from_orphan(struct ocfs2_super *osb,
+		struct inode *inode, int update_isize,
+		loff_t end)
+{
+	struct inode *orphan_dir_inode = NULL;
+	struct buffer_head *orphan_dir_bh = NULL;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_dinode *di = NULL;
+	handle_t *handle = NULL;
+	int status = 0;
+
+	status = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail;
+	}
+	di = (struct ocfs2_dinode *) di_bh->b_data;
+
+	orphan_dir_inode = ocfs2_get_system_file_inode(osb,
+			ORPHAN_DIR_SYSTEM_INODE,
+			le16_to_cpu(di->i_dio_orphaned_slot));
+	if (!orphan_dir_inode) {
+		status = -EEXIST;
+		mlog_errno(status);
+		goto bail_unlock_inode;
+	}
+
+	mutex_lock(&orphan_dir_inode->i_mutex);
+	status = ocfs2_inode_lock(orphan_dir_inode, &orphan_dir_bh, 1);
+	if (status < 0) {
+		mutex_unlock(&orphan_dir_inode->i_mutex);
+		iput(orphan_dir_inode);
+		mlog_errno(status);
+		goto bail_unlock_inode;
+	}
+
+	handle = ocfs2_start_trans(osb,
+			OCFS2_INODE_DEL_FROM_ORPHAN_CREDITS);
+	if (IS_ERR(handle)) {
+		status = PTR_ERR(handle);
+		goto bail_unlock_orphan;
+	}
+
+	BUG_ON(!(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL)));
+
+	/* Only delete entry if OCFS2_ORPHANED_FL not set, or
+	 * there are two entries added */
+	if (!(di->i_flags & cpu_to_le32(OCFS2_ORPHANED_FL)) ||
+			(di->i_flags & cpu_to_le32(OCFS2_ORPHANED_FL) &&
+			(di->i_orphaned_slot != di->i_dio_orphaned_slot))) {
+		status = ocfs2_orphan_del(osb, handle, orphan_dir_inode,
+				inode, orphan_dir_bh);
+		if (status < 0) {
+			mlog_errno(status);
+			goto bail_commit;
+		}
+	}
+
+	status = ocfs2_journal_access_di(handle,
+			INODE_CACHE(inode),
+			di_bh,
+			OCFS2_JOURNAL_ACCESS_WRITE);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail_commit;
+	}
+
+	di->i_flags &= ~cpu_to_le32(OCFS2_DIO_ORPHANED_FL);
+	di->i_dio_orphaned_slot = 0;
+
+	if (update_isize) {
+		status = ocfs2_set_inode_size(handle, inode, di_bh, end);
+		if (status)
+			mlog_errno(status);
+	} else
+		ocfs2_journal_dirty(handle, di_bh);
+
+bail_commit:
+	ocfs2_commit_trans(osb, handle);
+
+bail_unlock_orphan:
+	ocfs2_inode_unlock(orphan_dir_inode, 1);
+	mutex_unlock(&orphan_dir_inode->i_mutex);
+	brelse(orphan_dir_bh);
+	iput(orphan_dir_inode);
+
+bail_unlock_inode:
+	ocfs2_inode_unlock(inode, 1);
+	brelse(di_bh);
+
+bail:
+	return status;
+}
+
 int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
 				   struct inode *inode,
 				   struct dentry *dentry)
diff --git a/fs/ocfs2/namei.h b/fs/ocfs2/namei.h
index e5d059d4f11..562554026a6 100644
--- a/fs/ocfs2/namei.h
+++ b/fs/ocfs2/namei.h
@@ -38,6 +38,11 @@ int ocfs2_orphan_del(struct ocfs2_super *osb,
 int ocfs2_create_inode_in_orphan(struct inode *dir,
 				 int mode,
 				 struct inode **new_inode);
+int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
+		struct inode *inode);
+int ocfs2_del_inode_from_orphan(struct ocfs2_super *osb,
+		struct inode *inode, int update_isize,
+		loff_t end);
 int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
 				   struct inode *new_inode,
 				   struct dentry *new_dentry);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 7d6b7d09045..131cc1cd856 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -209,6 +209,11 @@ struct ocfs2_lock_res {
 #endif
 };
 
+enum ocfs2_orphan_reco_type {
+	ORPHAN_NO_NEED_TRUNCATE = 0,
+	ORPHAN_NEED_TRUNCATE,
+};
+
 enum ocfs2_orphan_scan_state {
 	ORPHAN_SCAN_ACTIVE,
 	ORPHAN_SCAN_INACTIVE
@@ -724,6 +729,16 @@ static inline unsigned int ocfs2_clusters_for_bytes(struct super_block *sb,
 	return clusters;
 }
 
+static inline unsigned int ocfs2_bytes_to_clusters(struct super_block *sb,
+		u64 bytes)
+{
+	int cl_bits = OCFS2_SB(sb)->s_clustersize_bits;
+	unsigned int clusters;
+
+	clusters = (unsigned int)(bytes >> cl_bits);
+	return clusters;
+}
+
 static inline u64 ocfs2_blocks_for_bytes(struct super_block *sb,
 					 u64 bytes)
 {
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 938387a10d5..e933ea2e976 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -229,6 +229,7 @@
 #define OCFS2_CHAIN_FL		(0x00000400)	/* Chain allocator */
 #define OCFS2_DEALLOC_FL	(0x00000800)	/* Truncate log */
 #define OCFS2_QUOTA_FL		(0x00001000)	/* Quota file */
+#define OCFS2_DIO_ORPHANED_FL	(0X00002000)	/* On the orphan list especially for dio */
 
 /*
  * Flags on ocfs2_dinode.i_dyn_features
@@ -729,7 +730,9 @@ struct ocfs2_dinode {
 					   inode belongs to.  Only valid
 					   if allocated from a
 					   discontiguous block group */
-/*A0*/	__le64 i_reserved2[3];
+/*A0*/	__le16 i_dio_orphaned_slot;	/* only used for append dio write */
+	__le16 i_reserved1[3];
+	__le64 i_reserved2[2];
 /*B8*/	union {
 		__le64 i_pad1;		/* Generic way to refer to this
 					   64bit union */
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index 6cb019b7c6a..2d471cc879c 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -2373,6 +2373,9 @@ DEFINE_OCFS2_ULL_EVENT(ocfs2_orphan_add_begin);
 
 DEFINE_OCFS2_ULL_UINT_EVENT(ocfs2_orphan_add_end);
 
+DEFINE_OCFS2_ULL_EVENT(ocfs2_dio_orphan_add_begin);
+DEFINE_OCFS2_ULL_UINT_EVENT(ocfs2_dio_orphan_add_end);
+
 TRACE_EVENT(ocfs2_orphan_del,
 	TP_PROTO(unsigned long long dir, const char *name, int namelen),
 	TP_ARGS(dir, name, namelen),
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 83723179e1e..04ee6d16cb3 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1768,6 +1768,8 @@ static void ocfs2_inode_init_once(void *data)
 	ocfs2_lock_res_init_once(&oi->ip_inode_lockres);
 	ocfs2_lock_res_init_once(&oi->ip_open_lockres);
 
+	init_waitqueue_head(&oi->append_dio_wq);
+
 	ocfs2_metadata_cache_init(INODE_CACHE(&oi->vfs_inode),
 				  &ocfs2_inode_caching_ops);
 
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index aa1eee06420..d3ebf2e6185 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -12,6 +12,9 @@
 #include <linux/vmstat.h>
 #include <linux/atomic.h>
 #include <linux/vmalloc.h>
+#ifdef CONFIG_CMA
+#include <linux/cma.h>
+#endif
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include "internal.h"
@@ -138,6 +141,10 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 		"AnonHugePages:  %8lu kB\n"
 #endif
+#ifdef CONFIG_CMA
+		"CmaTotal:       %8lu kB\n"
+		"CmaFree:        %8lu kB\n"
+#endif
 		,
 		K(i.totalram),
 		K(i.freeram),
@@ -187,12 +194,16 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		vmi.used >> 10,
 		vmi.largest_chunk >> 10
 #ifdef CONFIG_MEMORY_FAILURE
-		,atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10)
+		, atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10)
 #endif
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		,K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) *
+		, K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) *
 		   HPAGE_PMD_NR)
 #endif
+#ifdef CONFIG_CMA
+		, K(totalcma_pages)
+		, K(global_page_state(NR_FREE_CMA_PAGES))
+#endif
 		);
 
 	hugetlb_report_meminfo(m);
diff --git a/fs/select.c b/fs/select.c
index 467bb1cb3ea..f684c750e08 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -971,7 +971,7 @@ SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds,
 	if (ret == -EINTR) {
 		struct restart_block *restart_block;
 
-		restart_block = &current_thread_info()->restart_block;
+		restart_block = &current->restart_block;
 		restart_block->fn = do_restart_poll;
 		restart_block->poll.ufds = ufds;
 		restart_block->poll.nfds = nfds;
diff --git a/include/linux/cma.h b/include/linux/cma.h
index a93438beb33..9384ba66e97 100644
--- a/include/linux/cma.h
+++ b/include/linux/cma.h
@@ -15,6 +15,7 @@
 
 struct cma;
 
+extern unsigned long totalcma_pages;
 extern phys_addr_t cma_get_base(struct cma *cma);
 extern unsigned long cma_get_size(struct cma *cma);
 
diff --git a/include/linux/crc64_ecma.h b/include/linux/crc64_ecma.h
new file mode 100644
index 00000000000..bba7a4d692b
--- /dev/null
+++ b/include/linux/crc64_ecma.h
@@ -0,0 +1,56 @@
+/*
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __CRC64_ECMA_H_
+#define __CRC64_ECMA_H_
+
+#include <linux/types.h>
+
+
+#define CRC64_DEFAULT_INITVAL           0xFFFFFFFFFFFFFFFFULL
+
+
+/*
+ * crc64_ecma_seed - Initializes the CRC64 ECMA seed.
+ */
+u64 crc64_ecma_seed(void);
+
+/*
+ * crc64_ecma - Computes the 64 bit ECMA CRC.
+ *
+ * @pdata:	pointer to the data to compute checksum for.
+ * @nbytes:	number of bytes in data buffer.
+ * @seed:	CRC seed.
+ */
+u64 crc64_ecma(u8 const *pdata, u32 nbytes, u64 seed);
+
+#endif /* __CRC64_ECMA_H_ */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f90c0282c11..86397708b7a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2481,8 +2481,12 @@ extern int sb_min_blocksize(struct super_block *, int);
 
 extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
-extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr,
-		unsigned long size, pgoff_t pgoff);
+static inline int generic_file_remap_pages(struct vm_area_struct *vma,
+		unsigned long addr, unsigned long size, pgoff_t pgoff)
+{
+	BUG();
+	return 0;
+}
 int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
 extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index ad9051bab26..07f736b18ff 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -19,6 +19,9 @@ extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 					  unsigned long addr,
 					  pmd_t *pmd,
 					  unsigned int flags);
+extern int madvise_free_huge_pmd(struct mmu_gather *tlb,
+			struct vm_area_struct *vma,
+			pmd_t *pmd, unsigned long addr);
 extern int zap_huge_pmd(struct mmu_gather *tlb,
 			struct vm_area_struct *vma,
 			pmd_t *pmd, unsigned long addr);
@@ -56,6 +59,7 @@ extern pmd_t *page_check_address_pmd(struct page *page,
 				     unsigned long address,
 				     enum page_check_address_pmd_flag flag,
 				     spinlock_t **ptl);
+extern int pmd_freeable(pmd_t pmd);
 
 #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
 #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 3037fc085e8..d3d43ecf148 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -193,6 +193,9 @@ extern struct task_group root_task_group;
 	.nr_cpus_allowed= NR_CPUS,					\
 	.mm		= NULL,						\
 	.active_mm	= &init_mm,					\
+	.restart_block = {						\
+		.fn = do_no_restart_syscall,				\
+	},								\
 	.se		= {						\
 		.group_node 	= LIST_HEAD_INIT(tsk.se.group_node),	\
 	},								\
diff --git a/include/linux/input.h b/include/linux/input.h
index 82ce323b998..3b4c32f7312 100644
--- a/include/linux/input.h
+++ b/include/linux/input.h
@@ -79,6 +79,7 @@ struct input_value {
  * @led: reflects current state of device's LEDs
  * @snd: reflects current state of sound effects
  * @sw: reflects current state of device's switches
+ * @leds: leds objects for the device's LEDs
  * @open: this method is called when the very first user calls
  *	input_open_device(). The driver must prepare the device
  *	to start generating events (start polling thread,
@@ -164,6 +165,8 @@ struct input_dev {
 	unsigned long snd[BITS_TO_LONGS(SND_CNT)];
 	unsigned long sw[BITS_TO_LONGS(SW_CNT)];
 
+	struct led_classdev *leds;
+
 	int (*open)(struct input_dev *dev);
 	void (*close)(struct input_dev *dev);
 	int (*flush)(struct input_dev *dev, struct file *file);
@@ -531,4 +534,29 @@ int input_ff_erase(struct input_dev *dev, int effect_id, struct file *file);
 int input_ff_create_memless(struct input_dev *dev, void *data,
 		int (*play_effect)(struct input_dev *, void *, struct ff_effect *));
 
+#ifdef CONFIG_INPUT_LEDS
+
+void input_led_init(void);
+void input_led_exit(void);
+
+int input_led_connect(struct input_dev *dev);
+void input_led_disconnect(struct input_dev *dev);
+
+#else
+
+static inline void input_led_init(void) { }
+
+static inline void input_led_exit(void) { }
+
+static inline int input_led_connect(struct input_dev *dev)
+{
+	return 0;
+}
+
+static inline void input_led_disconnect(struct input_dev *dev)
+{
+}
+
+#endif
+
 #endif
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 9d957b7ae09..bee3c5b097d 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -258,6 +258,8 @@ unsigned long paddr_vmcoreinfo_note(void);
 	vmcoreinfo_append_str("NUMBER(%s)=%ld\n", #name, (long)name)
 #define VMCOREINFO_CONFIG(name) \
 	vmcoreinfo_append_str("CONFIG_%s=y\n", #name)
+#define VMCOREINFO_PHYS_BASE(value) \
+	vmcoreinfo_append_str("PHYS_BASE=%lx\n", (unsigned long)value)
 
 extern struct kimage *kexec_image;
 extern struct kimage *kexec_crash_image;
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 853698c721f..76200984d1e 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -85,11 +85,6 @@ static inline void oom_killer_enable(void)
 	oom_killer_disabled = false;
 }
 
-static inline bool oom_gfp_allowed(gfp_t gfp_mask)
-{
-	return (gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY);
-}
-
 extern struct task_struct *find_lock_task_mm(struct task_struct *p);
 
 static inline bool task_will_free_mem(struct task_struct *task)
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index c0c2bce6b0b..94d5bcacc83 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -75,6 +75,7 @@ enum ttu_flags {
 	TTU_UNMAP = 1,			/* unmap mode */
 	TTU_MIGRATION = 2,		/* migration mode */
 	TTU_MUNLOCK = 4,		/* munlock mode */
+	TTU_FREE = 8,			/* free mode */
 
 	TTU_IGNORE_MLOCK = (1 << 8),	/* ignore mlock */
 	TTU_IGNORE_ACCESS = (1 << 9),	/* don't age */
@@ -181,7 +182,8 @@ static inline void page_dup_rmap(struct page *page)
  * Called from mm/vmscan.c to handle paging out
  */
 int page_referenced(struct page *, int is_locked,
-			struct mem_cgroup *memcg, unsigned long *vm_flags);
+			struct mem_cgroup *memcg, unsigned long *vm_flags,
+			int *is_pte_dirty);
 
 #define TTU_ACTION(x) ((x) & TTU_ACTION_MASK)
 
@@ -260,9 +262,12 @@ int rmap_walk(struct page *page, struct rmap_walk_control *rwc);
 
 static inline int page_referenced(struct page *page, int is_locked,
 				  struct mem_cgroup *memcg,
-				  unsigned long *vm_flags)
+				  unsigned long *vm_flags,
+				  int *is_pte_dirty)
 {
 	*vm_flags = 0;
+	if (is_pte_dirty)
+		*is_pte_dirty = 0;
 	return 0;
 }
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8db31ef98d2..22ee0d5d7f8 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1370,6 +1370,8 @@ struct task_struct {
 
 	unsigned long atomic_flags; /* Flags needing atomic access. */
 
+	struct restart_block restart_block;
+
 	pid_t pid;
 	pid_t tgid;
 
diff --git a/include/linux/string.h b/include/linux/string.h
index 2e22a2e58f3..a0c6fd5fb5c 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -117,6 +117,7 @@ void *memchr_inv(const void *s, int c, size_t n);
 
 extern char *kstrdup(const char *s, gfp_t gfp);
 extern char *kstrndup(const char *s, size_t len, gfp_t gfp);
+extern char *kstrimdup(const char *s, gfp_t gfp);
 extern void *kmemdup(const void *src, size_t len, gfp_t gfp);
 
 extern char **argv_split(gfp_t gfp, const char *str, int *argcp);
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 9246d32dc97..2b1cef88b82 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -25,6 +25,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		FOR_ALL_ZONES(PGALLOC),
 		PGFREE, PGACTIVATE, PGDEACTIVATE,
 		PGFAULT, PGMAJFAULT,
+		PGLAZYFREED,
 		FOR_ALL_ZONES(PGREFILL),
 		FOR_ALL_ZONES(PGSTEAL_KSWAPD),
 		FOR_ALL_ZONES(PGSTEAL_DIRECT),
diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h
index ddc3b36f104..7a94102b7a0 100644
--- a/include/uapi/asm-generic/mman-common.h
+++ b/include/uapi/asm-generic/mman-common.h
@@ -34,6 +34,7 @@
 #define MADV_SEQUENTIAL	2		/* expect sequential page references */
 #define MADV_WILLNEED	3		/* will need these pages */
 #define MADV_DONTNEED	4		/* don't need these pages */
+#define MADV_FREE	5		/* free pages only if memory pressure */
 
 /* common parameters: try to keep these consistent across architectures */
 #define MADV_REMOVE	9		/* remove these pages & resources */
diff --git a/init/Kconfig b/init/Kconfig
index 0c90b97d1fa..d68d8b0780b 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1280,22 +1280,6 @@ source "usr/Kconfig"
 
 endif
 
-config INIT_FALLBACK
-	bool "Fall back to defaults if init= parameter is bad"
-	default y
-	help
-	  If enabled, the kernel will try the default init binaries if an
-	  explicit request from the init= parameter fails.
-
-	  This can have unexpected effects.  For example, booting
-	  with init=/sbin/kiosk_app will run /sbin/init or even /bin/sh
-	  if /sbin/kiosk_app cannot be executed.
-
-	  The default value of Y is consistent with historical behavior.
-	  Selecting N is likely to be more appropriate for most uses,
-	  especially on kiosks and on kernels that are intended to be
-	  run under the control of a script.
-
 config CC_OPTIMIZE_FOR_SIZE
 	bool "Optimize for size"
 	help
diff --git a/init/main.c b/init/main.c
index 61b993767db..cf954286596 100644
--- a/init/main.c
+++ b/init/main.c
@@ -966,13 +966,8 @@ static int __ref kernel_init(void *unused)
 		ret = run_init_process(execute_command);
 		if (!ret)
 			return 0;
-#ifndef CONFIG_INIT_FALLBACK
 		panic("Requested init %s failed (error %d).",
 		      execute_command, ret);
-#else
-		pr_err("Failed to execute %s (error %d).  Attempting defaults...\n",
-		       execute_command, ret);
-#endif
 	}
 	if (!try_to_run_init_process("/sbin/init") ||
 	    !try_to_run_init_process("/etc/init") ||
diff --git a/kernel/compat.c b/kernel/compat.c
index ebb3c369d03..24f00610c57 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -276,8 +276,7 @@ COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp,
 	 * core implementation decides to return random nonsense.
 	 */
 	if (ret == -ERESTART_RESTARTBLOCK) {
-		struct restart_block *restart
-			= &current_thread_info()->restart_block;
+		struct restart_block *restart = &current->restart_block;
 
 		restart->fn = compat_nanosleep_restart;
 		restart->nanosleep.compat_rmtp = rmtp;
@@ -860,7 +859,7 @@ COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags,
 		return -EFAULT;
 
 	if (err == -ERESTART_RESTARTBLOCK) {
-		restart = &current_thread_info()->restart_block;
+		restart = &current->restart_block;
 		restart->fn = compat_clock_nanosleep_restart;
 		restart->nanosleep.compat_rmtp = rmtp;
 	}
diff --git a/kernel/exit.c b/kernel/exit.c
index 1ea4369890a..6806c55475e 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1287,9 +1287,15 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
 static int wait_consider_task(struct wait_opts *wo, int ptrace,
 				struct task_struct *p)
 {
+	/*
+	 * We can race with wait_task_zombie() from another thread.
+	 * Ensure that EXIT_ZOMBIE -> EXIT_DEAD/EXIT_TRACE transition
+	 * can't confuse the checks below.
+	 */
+	int exit_state = ACCESS_ONCE(p->exit_state);
 	int ret;
 
-	if (unlikely(p->exit_state == EXIT_DEAD))
+	if (unlikely(exit_state == EXIT_DEAD))
 		return 0;
 
 	ret = eligible_child(wo, p);
@@ -1310,7 +1316,7 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
 		return 0;
 	}
 
-	if (unlikely(p->exit_state == EXIT_TRACE)) {
+	if (unlikely(exit_state == EXIT_TRACE)) {
 		/*
 		 * ptrace == 0 means we are the natural parent. In this case
 		 * we should clear notask_error, debugger will notify us.
@@ -1337,7 +1343,7 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
 	}
 
 	/* slay zombie? */
-	if (p->exit_state == EXIT_ZOMBIE) {
+	if (exit_state == EXIT_ZOMBIE) {
 		/* we don't reap group leaders with subthreads */
 		if (!delay_group_leader(p)) {
 			/*
diff --git a/kernel/futex.c b/kernel/futex.c
index 63678b573d6..f4d8a85641e 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2217,7 +2217,7 @@ retry:
 	if (!abs_time)
 		goto out;
 
-	restart = &current_thread_info()->restart_block;
+	restart = &current->restart_block;
 	restart->fn = futex_wait_restart;
 	restart->futex.uaddr = uaddr;
 	restart->futex.val = val;
diff --git a/kernel/signal.c b/kernel/signal.c
index 16a30529525..33a52759cc0 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2501,7 +2501,7 @@ EXPORT_SYMBOL(unblock_all_signals);
  */
 SYSCALL_DEFINE0(restart_syscall)
 {
-	struct restart_block *restart = &current_thread_info()->restart_block;
+	struct restart_block *restart = &current->restart_block;
 	return restart->fn(restart);
 }
 
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index a7077d3ae52..1b001ed1edb 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -788,7 +788,7 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
 			goto out;
 	}
 
-	restart = &current_thread_info()->restart_block;
+	restart = &current->restart_block;
 	restart->fn = alarm_timer_nsleep_restart;
 	restart->nanosleep.clockid = type;
 	restart->nanosleep.expires = exp.tv64;
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 37e50aadd47..dbcec65d08c 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1591,7 +1591,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
 			goto out;
 	}
 
-	restart = &current_thread_info()->restart_block;
+	restart = &current->restart_block;
 	restart->fn = hrtimer_nanosleep_restart;
 	restart->nanosleep.clockid = t.timer.base->clockid;
 	restart->nanosleep.rmtp = rmtp;
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index a16b67859e2..0075da74abf 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -1334,8 +1334,7 @@ static long posix_cpu_nsleep_restart(struct restart_block *restart_block);
 static int posix_cpu_nsleep(const clockid_t which_clock, int flags,
 			    struct timespec *rqtp, struct timespec __user *rmtp)
 {
-	struct restart_block *restart_block =
-		&current_thread_info()->restart_block;
+	struct restart_block *restart_block = &current->restart_block;
 	struct itimerspec it;
 	int error;
 
diff --git a/lib/Kconfig b/lib/Kconfig
index 54cf309a92a..2faf7b2de5b 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -180,6 +180,13 @@ config CRC8
 	  when they need to do cyclic redundancy check according CRC8
 	  algorithm. Module will be called crc8.
 
+config CRC64_ECMA
+	tristate "CRC64 ECMA function"
+	help
+	  This option provides CRC64 ECMA function. Drivers may select this
+	  when they need to do cyclic redundancy check according to the CRC64
+	  ECMA algorithm.
+
 config AUDIT_GENERIC
 	bool
 	depends on AUDIT && !AUDIT_ARCH
diff --git a/lib/Makefile b/lib/Makefile
index 3c3b30b9e02..f42838ac6f3 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -72,6 +72,7 @@ obj-$(CONFIG_CRC32)	+= crc32.o
 obj-$(CONFIG_CRC7)	+= crc7.o
 obj-$(CONFIG_LIBCRC32C)	+= libcrc32c.o
 obj-$(CONFIG_CRC8)	+= crc8.o
+obj-$(CONFIG_CRC64_ECMA)	+= crc64_ecma.o
 obj-$(CONFIG_GENERIC_ALLOCATOR) += genalloc.o
 
 obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate/
diff --git a/lib/crc64_ecma.c b/lib/crc64_ecma.c
new file mode 100644
index 00000000000..41629ea5a60
--- /dev/null
+++ b/lib/crc64_ecma.c
@@ -0,0 +1,341 @@
+/*
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/module.h>
+#include <linux/crc64_ecma.h>
+
+
+#define CRC64_BYTE_MASK			0xFF
+#define CRC64_TABLE_SIZE		256
+
+
+struct crc64_table {
+	u64 seed;
+	u64 table[CRC64_TABLE_SIZE];
+};
+
+
+static struct crc64_table CRC64_ECMA_182 = {
+	CRC64_DEFAULT_INITVAL,
+	{
+		0x0000000000000000ULL,
+		0xb32e4cbe03a75f6fULL,
+		0xf4843657a840a05bULL,
+		0x47aa7ae9abe7ff34ULL,
+		0x7bd0c384ff8f5e33ULL,
+		0xc8fe8f3afc28015cULL,
+		0x8f54f5d357cffe68ULL,
+		0x3c7ab96d5468a107ULL,
+		0xf7a18709ff1ebc66ULL,
+		0x448fcbb7fcb9e309ULL,
+		0x0325b15e575e1c3dULL,
+		0xb00bfde054f94352ULL,
+		0x8c71448d0091e255ULL,
+		0x3f5f08330336bd3aULL,
+		0x78f572daa8d1420eULL,
+		0xcbdb3e64ab761d61ULL,
+		0x7d9ba13851336649ULL,
+		0xceb5ed8652943926ULL,
+		0x891f976ff973c612ULL,
+		0x3a31dbd1fad4997dULL,
+		0x064b62bcaebc387aULL,
+		0xb5652e02ad1b6715ULL,
+		0xf2cf54eb06fc9821ULL,
+		0x41e11855055bc74eULL,
+		0x8a3a2631ae2dda2fULL,
+		0x39146a8fad8a8540ULL,
+		0x7ebe1066066d7a74ULL,
+		0xcd905cd805ca251bULL,
+		0xf1eae5b551a2841cULL,
+		0x42c4a90b5205db73ULL,
+		0x056ed3e2f9e22447ULL,
+		0xb6409f5cfa457b28ULL,
+		0xfb374270a266cc92ULL,
+		0x48190ecea1c193fdULL,
+		0x0fb374270a266cc9ULL,
+		0xbc9d3899098133a6ULL,
+		0x80e781f45de992a1ULL,
+		0x33c9cd4a5e4ecdceULL,
+		0x7463b7a3f5a932faULL,
+		0xc74dfb1df60e6d95ULL,
+		0x0c96c5795d7870f4ULL,
+		0xbfb889c75edf2f9bULL,
+		0xf812f32ef538d0afULL,
+		0x4b3cbf90f69f8fc0ULL,
+		0x774606fda2f72ec7ULL,
+		0xc4684a43a15071a8ULL,
+		0x83c230aa0ab78e9cULL,
+		0x30ec7c140910d1f3ULL,
+		0x86ace348f355aadbULL,
+		0x3582aff6f0f2f5b4ULL,
+		0x7228d51f5b150a80ULL,
+		0xc10699a158b255efULL,
+		0xfd7c20cc0cdaf4e8ULL,
+		0x4e526c720f7dab87ULL,
+		0x09f8169ba49a54b3ULL,
+		0xbad65a25a73d0bdcULL,
+		0x710d64410c4b16bdULL,
+		0xc22328ff0fec49d2ULL,
+		0x85895216a40bb6e6ULL,
+		0x36a71ea8a7ace989ULL,
+		0x0adda7c5f3c4488eULL,
+		0xb9f3eb7bf06317e1ULL,
+		0xfe5991925b84e8d5ULL,
+		0x4d77dd2c5823b7baULL,
+		0x64b62bcaebc387a1ULL,
+		0xd7986774e864d8ceULL,
+		0x90321d9d438327faULL,
+		0x231c512340247895ULL,
+		0x1f66e84e144cd992ULL,
+		0xac48a4f017eb86fdULL,
+		0xebe2de19bc0c79c9ULL,
+		0x58cc92a7bfab26a6ULL,
+		0x9317acc314dd3bc7ULL,
+		0x2039e07d177a64a8ULL,
+		0x67939a94bc9d9b9cULL,
+		0xd4bdd62abf3ac4f3ULL,
+		0xe8c76f47eb5265f4ULL,
+		0x5be923f9e8f53a9bULL,
+		0x1c4359104312c5afULL,
+		0xaf6d15ae40b59ac0ULL,
+		0x192d8af2baf0e1e8ULL,
+		0xaa03c64cb957be87ULL,
+		0xeda9bca512b041b3ULL,
+		0x5e87f01b11171edcULL,
+		0x62fd4976457fbfdbULL,
+		0xd1d305c846d8e0b4ULL,
+		0x96797f21ed3f1f80ULL,
+		0x2557339fee9840efULL,
+		0xee8c0dfb45ee5d8eULL,
+		0x5da24145464902e1ULL,
+		0x1a083bacedaefdd5ULL,
+		0xa9267712ee09a2baULL,
+		0x955cce7fba6103bdULL,
+		0x267282c1b9c65cd2ULL,
+		0x61d8f8281221a3e6ULL,
+		0xd2f6b4961186fc89ULL,
+		0x9f8169ba49a54b33ULL,
+		0x2caf25044a02145cULL,
+		0x6b055fede1e5eb68ULL,
+		0xd82b1353e242b407ULL,
+		0xe451aa3eb62a1500ULL,
+		0x577fe680b58d4a6fULL,
+		0x10d59c691e6ab55bULL,
+		0xa3fbd0d71dcdea34ULL,
+		0x6820eeb3b6bbf755ULL,
+		0xdb0ea20db51ca83aULL,
+		0x9ca4d8e41efb570eULL,
+		0x2f8a945a1d5c0861ULL,
+		0x13f02d374934a966ULL,
+		0xa0de61894a93f609ULL,
+		0xe7741b60e174093dULL,
+		0x545a57dee2d35652ULL,
+		0xe21ac88218962d7aULL,
+		0x5134843c1b317215ULL,
+		0x169efed5b0d68d21ULL,
+		0xa5b0b26bb371d24eULL,
+		0x99ca0b06e7197349ULL,
+		0x2ae447b8e4be2c26ULL,
+		0x6d4e3d514f59d312ULL,
+		0xde6071ef4cfe8c7dULL,
+		0x15bb4f8be788911cULL,
+		0xa6950335e42fce73ULL,
+		0xe13f79dc4fc83147ULL,
+		0x521135624c6f6e28ULL,
+		0x6e6b8c0f1807cf2fULL,
+		0xdd45c0b11ba09040ULL,
+		0x9aefba58b0476f74ULL,
+		0x29c1f6e6b3e0301bULL,
+		0xc96c5795d7870f42ULL,
+		0x7a421b2bd420502dULL,
+		0x3de861c27fc7af19ULL,
+		0x8ec62d7c7c60f076ULL,
+		0xb2bc941128085171ULL,
+		0x0192d8af2baf0e1eULL,
+		0x4638a2468048f12aULL,
+		0xf516eef883efae45ULL,
+		0x3ecdd09c2899b324ULL,
+		0x8de39c222b3eec4bULL,
+		0xca49e6cb80d9137fULL,
+		0x7967aa75837e4c10ULL,
+		0x451d1318d716ed17ULL,
+		0xf6335fa6d4b1b278ULL,
+		0xb199254f7f564d4cULL,
+		0x02b769f17cf11223ULL,
+		0xb4f7f6ad86b4690bULL,
+		0x07d9ba1385133664ULL,
+		0x4073c0fa2ef4c950ULL,
+		0xf35d8c442d53963fULL,
+		0xcf273529793b3738ULL,
+		0x7c0979977a9c6857ULL,
+		0x3ba3037ed17b9763ULL,
+		0x888d4fc0d2dcc80cULL,
+		0x435671a479aad56dULL,
+		0xf0783d1a7a0d8a02ULL,
+		0xb7d247f3d1ea7536ULL,
+		0x04fc0b4dd24d2a59ULL,
+		0x3886b22086258b5eULL,
+		0x8ba8fe9e8582d431ULL,
+		0xcc0284772e652b05ULL,
+		0x7f2cc8c92dc2746aULL,
+		0x325b15e575e1c3d0ULL,
+		0x8175595b76469cbfULL,
+		0xc6df23b2dda1638bULL,
+		0x75f16f0cde063ce4ULL,
+		0x498bd6618a6e9de3ULL,
+		0xfaa59adf89c9c28cULL,
+		0xbd0fe036222e3db8ULL,
+		0x0e21ac88218962d7ULL,
+		0xc5fa92ec8aff7fb6ULL,
+		0x76d4de52895820d9ULL,
+		0x317ea4bb22bfdfedULL,
+		0x8250e80521188082ULL,
+		0xbe2a516875702185ULL,
+		0x0d041dd676d77eeaULL,
+		0x4aae673fdd3081deULL,
+		0xf9802b81de97deb1ULL,
+		0x4fc0b4dd24d2a599ULL,
+		0xfceef8632775faf6ULL,
+		0xbb44828a8c9205c2ULL,
+		0x086ace348f355aadULL,
+		0x34107759db5dfbaaULL,
+		0x873e3be7d8faa4c5ULL,
+		0xc094410e731d5bf1ULL,
+		0x73ba0db070ba049eULL,
+		0xb86133d4dbcc19ffULL,
+		0x0b4f7f6ad86b4690ULL,
+		0x4ce50583738cb9a4ULL,
+		0xffcb493d702be6cbULL,
+		0xc3b1f050244347ccULL,
+		0x709fbcee27e418a3ULL,
+		0x3735c6078c03e797ULL,
+		0x841b8ab98fa4b8f8ULL,
+		0xadda7c5f3c4488e3ULL,
+		0x1ef430e13fe3d78cULL,
+		0x595e4a08940428b8ULL,
+		0xea7006b697a377d7ULL,
+		0xd60abfdbc3cbd6d0ULL,
+		0x6524f365c06c89bfULL,
+		0x228e898c6b8b768bULL,
+		0x91a0c532682c29e4ULL,
+		0x5a7bfb56c35a3485ULL,
+		0xe955b7e8c0fd6beaULL,
+		0xaeffcd016b1a94deULL,
+		0x1dd181bf68bdcbb1ULL,
+		0x21ab38d23cd56ab6ULL,
+		0x9285746c3f7235d9ULL,
+		0xd52f0e859495caedULL,
+		0x6601423b97329582ULL,
+		0xd041dd676d77eeaaULL,
+		0x636f91d96ed0b1c5ULL,
+		0x24c5eb30c5374ef1ULL,
+		0x97eba78ec690119eULL,
+		0xab911ee392f8b099ULL,
+		0x18bf525d915feff6ULL,
+		0x5f1528b43ab810c2ULL,
+		0xec3b640a391f4fadULL,
+		0x27e05a6e926952ccULL,
+		0x94ce16d091ce0da3ULL,
+		0xd3646c393a29f297ULL,
+		0x604a2087398eadf8ULL,
+		0x5c3099ea6de60cffULL,
+		0xef1ed5546e415390ULL,
+		0xa8b4afbdc5a6aca4ULL,
+		0x1b9ae303c601f3cbULL,
+		0x56ed3e2f9e224471ULL,
+		0xe5c372919d851b1eULL,
+		0xa26908783662e42aULL,
+		0x114744c635c5bb45ULL,
+		0x2d3dfdab61ad1a42ULL,
+		0x9e13b115620a452dULL,
+		0xd9b9cbfcc9edba19ULL,
+		0x6a978742ca4ae576ULL,
+		0xa14cb926613cf817ULL,
+		0x1262f598629ba778ULL,
+		0x55c88f71c97c584cULL,
+		0xe6e6c3cfcadb0723ULL,
+		0xda9c7aa29eb3a624ULL,
+		0x69b2361c9d14f94bULL,
+		0x2e184cf536f3067fULL,
+		0x9d36004b35545910ULL,
+		0x2b769f17cf112238ULL,
+		0x9858d3a9ccb67d57ULL,
+		0xdff2a94067518263ULL,
+		0x6cdce5fe64f6dd0cULL,
+		0x50a65c93309e7c0bULL,
+		0xe388102d33392364ULL,
+		0xa4226ac498dedc50ULL,
+		0x170c267a9b79833fULL,
+		0xdcd7181e300f9e5eULL,
+		0x6ff954a033a8c131ULL,
+		0x28532e49984f3e05ULL,
+		0x9b7d62f79be8616aULL,
+		0xa707db9acf80c06dULL,
+		0x14299724cc279f02ULL,
+		0x5383edcd67c06036ULL,
+		0xe0ada17364673f59ULL
+	}
+};
+
+
+/*
+ * crc64_ecma_seed - Initializes the CRC64 ECMA seed.
+ */
+u64 crc64_ecma_seed(void)
+{
+	return CRC64_ECMA_182.seed;
+}
+EXPORT_SYMBOL(crc64_ecma_seed);
+
+/*
+ * crc64_ecma - Computes the 64 bit ECMA CRC.
+ *
+ * pdata: pointer to the data to compute checksum for.
+ * nbytes: number of bytes in data buffer.
+ * seed: CRC seed.
+ */
+u64 crc64_ecma(u8 const *pdata, u32 nbytes, u64 seed)
+{
+	unsigned int i;
+	u64 crc = seed;
+
+	for (i = 0; i < nbytes; i++)
+		crc = CRC64_ECMA_182.table[(crc ^ pdata[i]) & CRC64_BYTE_MASK] ^
+			(crc >> 8);
+
+	return crc;
+}
+EXPORT_SYMBOL(crc64_ecma);
+
+MODULE_DESCRIPTION("CRC64 ECMA function");
+MODULE_AUTHOR("Freescale Semiconductor Inc.");
+MODULE_LICENSE("GPL");
diff --git a/lib/show_mem.c b/lib/show_mem.c
index 5e256271b47..7de89f4a36c 100644
--- a/lib/show_mem.c
+++ b/lib/show_mem.c
@@ -8,6 +8,7 @@
 #include <linux/mm.h>
 #include <linux/nmi.h>
 #include <linux/quicklist.h>
+#include <linux/cma.h>
 
 void show_mem(unsigned int filter)
 {
@@ -38,7 +39,12 @@ void show_mem(unsigned int filter)
 
 	printk("%lu pages RAM\n", total);
 	printk("%lu pages HighMem/MovableOnly\n", highmem);
+#ifdef CONFIG_CMA
+	printk("%lu pages reserved\n", (reserved - totalcma_pages));
+	printk("%lu pages cma reserved\n", totalcma_pages);
+#else
 	printk("%lu pages reserved\n", reserved);
+#endif
 #ifdef CONFIG_QUICKLIST
 	printk("%lu pages in pagetable cache\n",
 		quicklist_total_size());
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index ec337f64f52..d57551c031f 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -1240,6 +1240,21 @@ char *address_val(char *buf, char *end, const void *addr,
 	return number(buf, end, num, spec);
 }
 
+static noinline_for_stack
+char *comm_name(char *buf, char *end, struct task_struct *tsk,
+		struct printf_spec spec, const char *fmt)
+{
+	char name[TASK_COMM_LEN];
+
+	/* Caller can pass NULL instead of current. */
+	if (!tsk)
+		tsk = current;
+	/* Not using get_task_comm() in case I'm in IRQ context. */
+	memcpy(name, tsk->comm, TASK_COMM_LEN);
+	name[sizeof(name) - 1] = '\0';
+	return string(buf, end, name, spec);
+}
+
 int kptr_restrict __read_mostly;
 
 /*
@@ -1318,6 +1333,7 @@ int kptr_restrict __read_mostly;
  *           (default assumed to be phys_addr_t, passed by reference)
  * - 'd[234]' For a dentry name (optionally 2-4 last components)
  * - 'D[234]' Same as 'd' but for a struct file
+ * - 'T' task_struct->comm
  *
  * Note: The difference between 'S' and 'F' is that on ia64 and ppc64
  * function pointers are really function descriptors, which contain a
@@ -1329,7 +1345,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 {
 	int default_width = 2 * sizeof(void *) + (spec.flags & SPECIAL ? 2 : 0);
 
-	if (!ptr && *fmt != 'K') {
+	if (!ptr && *fmt != 'K' && *fmt != 'T') {
 		/*
 		 * Print (null) with the same width as a pointer so it makes
 		 * tabular output look nice.
@@ -1459,6 +1475,8 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 		return dentry_name(buf, end,
 				   ((const struct file *)ptr)->f_path.dentry,
 				   spec, fmt);
+	case 'T':
+		return comm_name(buf, end, ptr, spec, fmt);
 	}
 	spec.flags |= SMALL;
 	if (spec.field_width == -1) {
diff --git a/mm/Makefile b/mm/Makefile
index 4bf586e6637..3548460ab7b 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -3,7 +3,7 @@
 #
 
 mmu-y			:= nommu.o
-mmu-$(CONFIG_MMU)	:= fremap.o gup.o highmem.o memory.o mincore.o \
+mmu-$(CONFIG_MMU)	:= gup.o highmem.o memory.o mincore.o \
 			   mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \
 			   vmalloc.o pagewalk.o pgtable-generic.o
 
diff --git a/mm/cma.c b/mm/cma.c
index f8917629cbd..a85ae28709a 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -337,6 +337,7 @@ int __init cma_declare_contiguous(phys_addr_t base,
 	if (ret)
 		goto err;
 
+	totalcma_pages += (size / PAGE_SIZE);
 	pr_info("Reserved %ld MiB at %pa\n", (unsigned long)size / SZ_1M,
 		&base);
 	return 0;
diff --git a/mm/fremap.c b/mm/fremap.c
deleted file mode 100644
index 2805d71cf47..00000000000
--- a/mm/fremap.c
+++ /dev/null
@@ -1,283 +0,0 @@
-/*
- *   linux/mm/fremap.c
- * 
- * Explicit pagetable population and nonlinear (random) mappings support.
- *
- * started by Ingo Molnar, Copyright (C) 2002, 2003
- */
-#include <linux/export.h>
-#include <linux/backing-dev.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/file.h>
-#include <linux/mman.h>
-#include <linux/pagemap.h>
-#include <linux/swapops.h>
-#include <linux/rmap.h>
-#include <linux/syscalls.h>
-#include <linux/mmu_notifier.h>
-
-#include <asm/mmu_context.h>
-#include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
-
-#include "internal.h"
-
-static int mm_counter(struct page *page)
-{
-	return PageAnon(page) ? MM_ANONPAGES : MM_FILEPAGES;
-}
-
-static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
-			unsigned long addr, pte_t *ptep)
-{
-	pte_t pte = *ptep;
-	struct page *page;
-	swp_entry_t entry;
-
-	if (pte_present(pte)) {
-		flush_cache_page(vma, addr, pte_pfn(pte));
-		pte = ptep_clear_flush_notify(vma, addr, ptep);
-		page = vm_normal_page(vma, addr, pte);
-		if (page) {
-			if (pte_dirty(pte))
-				set_page_dirty(page);
-			update_hiwater_rss(mm);
-			dec_mm_counter(mm, mm_counter(page));
-			page_remove_rmap(page);
-			page_cache_release(page);
-		}
-	} else {	/* zap_pte() is not called when pte_none() */
-		if (!pte_file(pte)) {
-			update_hiwater_rss(mm);
-			entry = pte_to_swp_entry(pte);
-			if (non_swap_entry(entry)) {
-				if (is_migration_entry(entry)) {
-					page = migration_entry_to_page(entry);
-					dec_mm_counter(mm, mm_counter(page));
-				}
-			} else {
-				free_swap_and_cache(entry);
-				dec_mm_counter(mm, MM_SWAPENTS);
-			}
-		}
-		pte_clear_not_present_full(mm, addr, ptep, 0);
-	}
-}
-
-/*
- * Install a file pte to a given virtual memory address, release any
- * previously existing mapping.
- */
-static int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma,
-		unsigned long addr, unsigned long pgoff, pgprot_t prot)
-{
-	int err = -ENOMEM;
-	pte_t *pte, ptfile;
-	spinlock_t *ptl;
-
-	pte = get_locked_pte(mm, addr, &ptl);
-	if (!pte)
-		goto out;
-
-	ptfile = pgoff_to_pte(pgoff);
-
-	if (!pte_none(*pte))
-		zap_pte(mm, vma, addr, pte);
-
-	set_pte_at(mm, addr, pte, pte_file_mksoft_dirty(ptfile));
-	/*
-	 * We don't need to run update_mmu_cache() here because the "file pte"
-	 * being installed by install_file_pte() is not a real pte - it's a
-	 * non-present entry (like a swap entry), noting what file offset should
-	 * be mapped there when there's a fault (in a non-linear vma where
-	 * that's not obvious).
-	 */
-	pte_unmap_unlock(pte, ptl);
-	err = 0;
-out:
-	return err;
-}
-
-int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr,
-			     unsigned long size, pgoff_t pgoff)
-{
-	struct mm_struct *mm = vma->vm_mm;
-	int err;
-
-	do {
-		err = install_file_pte(mm, vma, addr, pgoff, vma->vm_page_prot);
-		if (err)
-			return err;
-
-		size -= PAGE_SIZE;
-		addr += PAGE_SIZE;
-		pgoff++;
-	} while (size);
-
-	return 0;
-}
-EXPORT_SYMBOL(generic_file_remap_pages);
-
-/**
- * sys_remap_file_pages - remap arbitrary pages of an existing VM_SHARED vma
- * @start: start of the remapped virtual memory range
- * @size: size of the remapped virtual memory range
- * @prot: new protection bits of the range (see NOTE)
- * @pgoff: to-be-mapped page of the backing store file
- * @flags: 0 or MAP_NONBLOCKED - the later will cause no IO.
- *
- * sys_remap_file_pages remaps arbitrary pages of an existing VM_SHARED vma
- * (shared backing store file).
- *
- * This syscall works purely via pagetables, so it's the most efficient
- * way to map the same (large) file into a given virtual window. Unlike
- * mmap()/mremap() it does not create any new vmas. The new mappings are
- * also safe across swapout.
- *
- * NOTE: the @prot parameter right now is ignored (but must be zero),
- * and the vma's default protection is used. Arbitrary protections
- * might be implemented in the future.
- */
-SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
-		unsigned long, prot, unsigned long, pgoff, unsigned long, flags)
-{
-	struct mm_struct *mm = current->mm;
-	struct address_space *mapping;
-	struct vm_area_struct *vma;
-	int err = -EINVAL;
-	int has_write_lock = 0;
-	vm_flags_t vm_flags = 0;
-
-	pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. "
-			"See Documentation/vm/remap_file_pages.txt.\n",
-			current->comm, current->pid);
-
-	if (prot)
-		return err;
-	/*
-	 * Sanitize the syscall parameters:
-	 */
-	start = start & PAGE_MASK;
-	size = size & PAGE_MASK;
-
-	/* Does the address range wrap, or is the span zero-sized? */
-	if (start + size <= start)
-		return err;
-
-	/* Does pgoff wrap? */
-	if (pgoff + (size >> PAGE_SHIFT) < pgoff)
-		return err;
-
-	/* Can we represent this offset inside this architecture's pte's? */
-#if PTE_FILE_MAX_BITS < BITS_PER_LONG
-	if (pgoff + (size >> PAGE_SHIFT) >= (1UL << PTE_FILE_MAX_BITS))
-		return err;
-#endif
-
-	/* We need down_write() to change vma->vm_flags. */
-	down_read(&mm->mmap_sem);
- retry:
-	vma = find_vma(mm, start);
-
-	/*
-	 * Make sure the vma is shared, that it supports prefaulting,
-	 * and that the remapped range is valid and fully within
-	 * the single existing vma.
-	 */
-	if (!vma || !(vma->vm_flags & VM_SHARED))
-		goto out;
-
-	if (!vma->vm_ops || !vma->vm_ops->remap_pages)
-		goto out;
-
-	if (start < vma->vm_start || start + size > vma->vm_end)
-		goto out;
-
-	/* Must set VM_NONLINEAR before any pages are populated. */
-	if (!(vma->vm_flags & VM_NONLINEAR)) {
-		/*
-		 * vm_private_data is used as a swapout cursor
-		 * in a VM_NONLINEAR vma.
-		 */
-		if (vma->vm_private_data)
-			goto out;
-
-		/* Don't need a nonlinear mapping, exit success */
-		if (pgoff == linear_page_index(vma, start)) {
-			err = 0;
-			goto out;
-		}
-
-		if (!has_write_lock) {
-get_write_lock:
-			up_read(&mm->mmap_sem);
-			down_write(&mm->mmap_sem);
-			has_write_lock = 1;
-			goto retry;
-		}
-		mapping = vma->vm_file->f_mapping;
-		/*
-		 * page_mkclean doesn't work on nonlinear vmas, so if
-		 * dirty pages need to be accounted, emulate with linear
-		 * vmas.
-		 */
-		if (mapping_cap_account_dirty(mapping)) {
-			unsigned long addr;
-			struct file *file = get_file(vma->vm_file);
-			/* mmap_region may free vma; grab the info now */
-			vm_flags = vma->vm_flags;
-
-			addr = mmap_region(file, start, size, vm_flags, pgoff);
-			fput(file);
-			if (IS_ERR_VALUE(addr)) {
-				err = addr;
-			} else {
-				BUG_ON(addr != start);
-				err = 0;
-			}
-			goto out_freed;
-		}
-		i_mmap_lock_write(mapping);
-		flush_dcache_mmap_lock(mapping);
-		vma->vm_flags |= VM_NONLINEAR;
-		vma_interval_tree_remove(vma, &mapping->i_mmap);
-		vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear);
-		flush_dcache_mmap_unlock(mapping);
-		i_mmap_unlock_write(mapping);
-	}
-
-	if (vma->vm_flags & VM_LOCKED) {
-		/*
-		 * drop PG_Mlocked flag for over-mapped range
-		 */
-		if (!has_write_lock)
-			goto get_write_lock;
-		vm_flags = vma->vm_flags;
-		munlock_vma_pages_range(vma, start, start + size);
-		vma->vm_flags = vm_flags;
-	}
-
-	mmu_notifier_invalidate_range_start(mm, start, start + size);
-	err = vma->vm_ops->remap_pages(vma, start, size, pgoff);
-	mmu_notifier_invalidate_range_end(mm, start, start + size);
-
-	/*
-	 * We can't clear VM_NONLINEAR because we'd have to do
-	 * it after ->populate completes, and that would prevent
-	 * downgrading the lock.  (Locks can't be upgraded).
-	 */
-
-out:
-	if (vma)
-		vm_flags = vma->vm_flags;
-out_freed:
-	if (likely(!has_write_lock))
-		up_read(&mm->mmap_sem);
-	else
-		up_write(&mm->mmap_sem);
-	if (!err && ((vm_flags & VM_LOCKED) || !(flags & MAP_NONBLOCK)))
-		mm_populate(start, size);
-
-	return err;
-}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 817a875f2b8..cf3b67bdf86 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1383,6 +1383,36 @@ out:
 	return 0;
 }
 
+int madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
+		 pmd_t *pmd, unsigned long addr)
+
+{
+	spinlock_t *ptl;
+	struct mm_struct *mm = tlb->mm;
+	int ret = 1;
+
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+		struct page *page;
+		pmd_t orig_pmd;
+
+		orig_pmd = pmdp_get_and_clear(mm, addr, pmd);
+
+		/* No hugepage in swapcache */
+		page = pmd_page(orig_pmd);
+		VM_BUG_ON_PAGE(PageSwapCache(page), page);
+
+		orig_pmd = pmd_mkold(orig_pmd);
+		orig_pmd = pmd_mkclean(orig_pmd);
+
+		set_pmd_at(mm, addr, pmd, orig_pmd);
+		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
+		spin_unlock(ptl);
+		ret = 0;
+	}
+
+	return ret;
+}
+
 int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		 pmd_t *pmd, unsigned long addr)
 {
@@ -1620,6 +1650,11 @@ unlock:
 	return NULL;
 }
 
+int pmd_freeable(pmd_t pmd)
+{
+	return !pmd_dirty(pmd);
+}
+
 static int __split_huge_page_splitting(struct page *page,
 				       struct vm_area_struct *vma,
 				       unsigned long address)
diff --git a/mm/madvise.c b/mm/madvise.c
index a271adc9328..6fc9b8298da 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -19,6 +19,14 @@
 #include <linux/blkdev.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/mmu_notifier.h>
+
+#include <asm/tlb.h>
+
+struct madvise_free_private {
+	struct vm_area_struct *vma;
+	struct mmu_gather *tlb;
+};
 
 /*
  * Any behaviour which results in changes to the vma->vm_flags needs to
@@ -31,6 +39,7 @@ static int madvise_need_mmap_write(int behavior)
 	case MADV_REMOVE:
 	case MADV_WILLNEED:
 	case MADV_DONTNEED:
+	case MADV_FREE:
 		return 0;
 	default:
 		/* be safe, default to 1. list exceptions explicitly */
@@ -251,6 +260,138 @@ static long madvise_willneed(struct vm_area_struct *vma,
 	return 0;
 }
 
+static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
+				unsigned long end, struct mm_walk *walk)
+
+{
+	struct madvise_free_private *fp = walk->private;
+	struct mmu_gather *tlb = fp->tlb;
+	struct mm_struct *mm = tlb->mm;
+	struct vm_area_struct *vma = fp->vma;
+	spinlock_t *ptl;
+	pte_t *pte, ptent;
+	struct page *page;
+	unsigned long next;
+
+	next = pmd_addr_end(addr, end);
+	if (pmd_trans_huge(*pmd)) {
+		if (next - addr != HPAGE_PMD_SIZE)
+			split_huge_page_pmd(vma, addr, pmd);
+		else if (!madvise_free_huge_pmd(tlb, vma, pmd, addr))
+			goto next;
+		/* fall through */
+	}
+
+	if (pmd_trans_unstable(pmd))
+		return 0;
+
+	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+	arch_enter_lazy_mmu_mode();
+	for (; addr != end; pte++, addr += PAGE_SIZE) {
+		ptent = *pte;
+
+		if (!pte_present(ptent))
+			continue;
+
+		page = vm_normal_page(vma, addr, ptent);
+		if (!page)
+			continue;
+
+		if (PageSwapCache(page)) {
+			if (!trylock_page(page))
+				continue;
+
+			if (!try_to_free_swap(page)) {
+				unlock_page(page);
+				continue;
+			}
+
+			ClearPageDirty(page);
+			unlock_page(page);
+		}
+
+		/*
+		 * Some of architecture(ex, PPC) don't update TLB
+		 * with set_pte_at and tlb_remove_tlb_entry so for
+		 * the portability, remap the pte with old|clean
+		 * after pte clearing.
+		 */
+		ptent = ptep_get_and_clear_full(mm, addr, pte,
+						tlb->fullmm);
+		ptent = pte_mkold(ptent);
+		ptent = pte_mkclean(ptent);
+		set_pte_at(mm, addr, pte, ptent);
+		tlb_remove_tlb_entry(tlb, pte, addr);
+	}
+	arch_leave_lazy_mmu_mode();
+	pte_unmap_unlock(pte - 1, ptl);
+next:
+	cond_resched();
+	return 0;
+}
+
+static void madvise_free_page_range(struct mmu_gather *tlb,
+			     struct vm_area_struct *vma,
+			     unsigned long addr, unsigned long end)
+{
+	struct madvise_free_private fp = {
+		.vma = vma,
+		.tlb = tlb,
+	};
+
+	struct mm_walk free_walk = {
+		.pmd_entry = madvise_free_pte_range,
+		.mm = vma->vm_mm,
+		.private = &fp,
+	};
+
+	BUG_ON(addr >= end);
+	tlb_start_vma(tlb, vma);
+	walk_page_range(addr, end, &free_walk);
+	tlb_end_vma(tlb, vma);
+}
+
+static int madvise_free_single_vma(struct vm_area_struct *vma,
+			unsigned long start_addr, unsigned long end_addr)
+{
+	unsigned long start, end;
+	struct mm_struct *mm = vma->vm_mm;
+	struct mmu_gather tlb;
+
+	if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP))
+		return -EINVAL;
+
+	/* MADV_FREE works for only anon vma at the moment */
+	if (vma->vm_file)
+		return -EINVAL;
+
+	start = max(vma->vm_start, start_addr);
+	if (start >= vma->vm_end)
+		return -EINVAL;
+	end = min(vma->vm_end, end_addr);
+	if (end <= vma->vm_start)
+		return -EINVAL;
+
+	lru_add_drain();
+	tlb_gather_mmu(&tlb, mm, start, end);
+	update_hiwater_rss(mm);
+
+	mmu_notifier_invalidate_range_start(mm, start, end);
+	madvise_free_page_range(&tlb, vma, start, end);
+	mmu_notifier_invalidate_range_end(mm, start, end);
+	tlb_finish_mmu(&tlb, start, end);
+
+	return 0;
+}
+
+static long madvise_free(struct vm_area_struct *vma,
+			     struct vm_area_struct **prev,
+			     unsigned long start, unsigned long end)
+{
+	*prev = vma;
+	return madvise_free_single_vma(vma, start, end);
+}
+
 /*
  * Application no longer needs these pages.  If the pages are dirty,
  * it's OK to just throw them away.  The app will be more careful about
@@ -381,6 +522,14 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
 		return madvise_remove(vma, prev, start, end);
 	case MADV_WILLNEED:
 		return madvise_willneed(vma, prev, start, end);
+	case MADV_FREE:
+		/*
+		 * XXX: In this implementation, MADV_FREE works like
+		 * MADV_DONTNEED on swapless system or full swap.
+		 */
+		if (get_nr_swap_pages() > 0)
+			return madvise_free(vma, prev, start, end);
+		/* passthrough */
 	case MADV_DONTNEED:
 		return madvise_dontneed(vma, prev, start, end);
 	default:
@@ -400,6 +549,7 @@ madvise_behavior_valid(int behavior)
 	case MADV_REMOVE:
 	case MADV_WILLNEED:
 	case MADV_DONTNEED:
+	case MADV_FREE:
 #ifdef CONFIG_KSM
 	case MADV_MERGEABLE:
 	case MADV_UNMERGEABLE:
diff --git a/mm/memory.c b/mm/memory.c
index ee5cfc18e22..33f7370cc09 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2966,6 +2966,8 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	int dirtied = 0;
 	int ret, tmp;
 
+	WARN_ON_ONCE(!rwsem_is_locked(&mm->mmap_sem));
+
 	ret = __do_fault(vma, address, pgoff, flags, &fault_page);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
 		return ret;
@@ -2996,6 +2998,12 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	if (set_page_dirty(fault_page))
 		dirtied = 1;
+	/*
+	 * Take a local copy of the address_space - page.mapping may be zeroed
+	 * by truncate after unlock_page().   The address_space itself remains
+	 * pinned by vma->vm_file's reference.  We rely on unlock_page()'s
+	 * release semantics to prevent the compiler from undoing this copying.
+	 */
 	mapping = fault_page->mapping;
 	unlock_page(fault_page);
 	if ((dirtied || vma->vm_ops->page_mkwrite) && mapping) {
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 9fab10795be..b82b61e94bb 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1331,7 +1331,7 @@ int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
 }
 
 /*
- * Confirm all pages in a range [start, end) is belongs to the same zone.
+ * Confirm all pages in a range [start, end) belong to the same zone.
  */
 int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
 {
@@ -1342,10 +1342,11 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
 	for (pfn = start_pfn;
 	     pfn < end_pfn;
 	     pfn += MAX_ORDER_NR_PAGES) {
-		i = 0;
-		/* This is just a CONFIG_HOLES_IN_ZONE check.*/
-		while ((i < MAX_ORDER_NR_PAGES) && !pfn_valid_within(pfn + i))
-			i++;
+		/* Find the first valid pfn in this pageblock */
+		for (i = 0; i < MAX_ORDER_NR_PAGES; i++) {
+			if (pfn_valid(pfn + i))
+				break;
+		}
 		if (i == MAX_ORDER_NR_PAGES)
 			continue;
 		page = pfn_to_page(pfn + i);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index c1b273f1837..0e0961b8c39 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -162,12 +162,6 @@ static const struct mempolicy_operations {
 			enum mpol_rebind_step step);
 } mpol_ops[MPOL_MAX];
 
-/* Check that the nodemask contains at least one populated zone */
-static int is_valid_nodemask(const nodemask_t *nodemask)
-{
-	return nodes_intersects(*nodemask, node_states[N_MEMORY]);
-}
-
 static inline int mpol_store_user_nodemask(const struct mempolicy *pol)
 {
 	return pol->flags & MPOL_MODE_FLAGS;
@@ -202,7 +196,7 @@ static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes)
 
 static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes)
 {
-	if (!is_valid_nodemask(nodes))
+	if (nodes_empty(*nodes))
 		return -EINVAL;
 	pol->v.nodes = *nodes;
 	return 0;
@@ -234,7 +228,7 @@ static int mpol_set_nodemask(struct mempolicy *pol,
 		nodes = NULL;	/* explicit local allocation */
 	else {
 		if (pol->flags & MPOL_F_RELATIVE_NODES)
-			mpol_relative_nodemask(&nsc->mask2, nodes,&nsc->mask1);
+			mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1);
 		else
 			nodes_and(nsc->mask2, *nodes, nsc->mask1);
 
diff --git a/mm/mmap.c b/mm/mmap.c
index 7b36aa7cc89..e996cfd802b 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2629,6 +2629,75 @@ SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
 	return vm_munmap(addr, len);
 }
 
+
+/*
+ * Emulation of deprecated remap_file_pages() syscall.
+ */
+SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
+		unsigned long, prot, unsigned long, pgoff, unsigned long, flags)
+{
+
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	unsigned long populate = 0;
+	unsigned long ret = -EINVAL;
+	struct file *file;
+
+	pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. "
+			"See Documentation/vm/remap_file_pages.txt.\n",
+			current->comm, current->pid);
+
+	if (prot)
+		return ret;
+	start = start & PAGE_MASK;
+	size = size & PAGE_MASK;
+
+	if (start + size <= start)
+		return ret;
+
+	/* Does pgoff wrap? */
+	if (pgoff + (size >> PAGE_SHIFT) < pgoff)
+		return ret;
+
+	down_write(&mm->mmap_sem);
+	vma = find_vma(mm, start);
+
+	if (!vma || !(vma->vm_flags & VM_SHARED))
+		goto out;
+
+	if (start < vma->vm_start || start + size > vma->vm_end)
+		goto out;
+
+	if (pgoff == linear_page_index(vma, start)) {
+		ret = 0;
+		goto out;
+	}
+
+	prot |= vma->vm_flags & VM_READ ? PROT_READ : 0;
+	prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0;
+	prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0;
+
+	flags &= MAP_NONBLOCK;
+	flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE;
+	if (vma->vm_flags & VM_LOCKED) {
+		flags |= MAP_LOCKED;
+		/* drop PG_Mlocked flag for over-mapped range */
+		munlock_vma_pages_range(vma, start, start + size);
+	}
+
+	file = get_file(vma->vm_file);
+	ret = do_mmap_pgoff(vma->vm_file, start, size,
+			prot, flags, pgoff, &populate);
+	fput(file);
+out:
+	up_write(&mm->mmap_sem);
+	if (populate)
+		mm_populate(ret, populate);
+	if (!IS_ERR_VALUE(ret))
+		ret = 0;
+	return ret;
+}
+
 static inline void verify_mm_writelocked(struct mm_struct *mm)
 {
 #ifdef CONFIG_DEBUG_VM
diff --git a/mm/nommu.c b/mm/nommu.c
index b51eadf6d95..099cc72aa39 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1983,14 +1983,6 @@ void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf)
 }
 EXPORT_SYMBOL(filemap_map_pages);
 
-int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr,
-			     unsigned long size, pgoff_t pgoff)
-{
-	BUG();
-	return 0;
-}
-EXPORT_SYMBOL(generic_file_remap_pages);
-
 static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
 		unsigned long addr, void *buf, int len, int write)
 {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fa974d87f60..1bb65e6f48d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -111,6 +111,7 @@ static DEFINE_SPINLOCK(managed_page_count_lock);
 
 unsigned long totalram_pages __read_mostly;
 unsigned long totalreserve_pages __read_mostly;
+unsigned long totalcma_pages __read_mostly;
 /*
  * When calculating the number of globally allowed dirty pages, there
  * is a certain number of per-zone reserves that should not be
@@ -2331,12 +2332,21 @@ static inline struct page *
 __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, struct zone *preferred_zone,
-	int classzone_idx, int migratetype)
+	int classzone_idx, int migratetype, unsigned long *did_some_progress)
 {
 	struct page *page;
 
-	/* Acquire the per-zone oom lock for each zone */
+	*did_some_progress = 0;
+
+	if (oom_killer_disabled)
+		return NULL;
+
+	/*
+	 * Acquire the per-zone oom lock for each zone.  If that
+	 * fails, somebody else is making progress for us.
+	 */
 	if (!oom_zonelist_trylock(zonelist, gfp_mask)) {
+		*did_some_progress = 1;
 		schedule_timeout_uninterruptible(1);
 		return NULL;
 	}
@@ -2362,12 +2372,18 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 		goto out;
 
 	if (!(gfp_mask & __GFP_NOFAIL)) {
+		/* Coredumps can quickly deplete all memory reserves */
+		if (current->flags & PF_DUMPCORE)
+			goto out;
 		/* The OOM killer will not help higher order allocs */
 		if (order > PAGE_ALLOC_COSTLY_ORDER)
 			goto out;
 		/* The OOM killer does not needlessly kill tasks for lowmem */
 		if (high_zoneidx < ZONE_NORMAL)
 			goto out;
+		/* The OOM killer does not compensate for light reclaim */
+		if (!(gfp_mask & __GFP_FS))
+			goto out;
 		/*
 		 * GFP_THISNODE contains __GFP_NORETRY and we never hit this.
 		 * Sanity check for bare calls of __GFP_THISNODE, not real OOM.
@@ -2380,7 +2396,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	}
 	/* Exhausted what can be done so it's blamo time */
 	out_of_memory(zonelist, gfp_mask, order, nodemask, false);
-
+	*did_some_progress = 1;
 out:
 	oom_zonelist_unlock(zonelist, gfp_mask);
 	return page;
@@ -2657,7 +2673,6 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	    (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
 		goto nopage;
 
-restart:
 	if (!(gfp_mask & __GFP_NO_KSWAPD))
 		wake_all_kswapds(order, zonelist, high_zoneidx,
 				preferred_zone, nodemask);
@@ -2787,51 +2802,27 @@ rebalance:
 	if (page)
 		goto got_pg;
 
-	/*
-	 * If we failed to make any progress reclaiming, then we are
-	 * running out of options and have to consider going OOM
-	 */
-	if (!did_some_progress) {
-		if (oom_gfp_allowed(gfp_mask)) {
-			if (oom_killer_disabled)
-				goto nopage;
-			/* Coredumps can quickly deplete all memory reserves */
-			if ((current->flags & PF_DUMPCORE) &&
-			    !(gfp_mask & __GFP_NOFAIL))
-				goto nopage;
-			page = __alloc_pages_may_oom(gfp_mask, order,
-					zonelist, high_zoneidx,
-					nodemask, preferred_zone,
-					classzone_idx, migratetype);
-			if (page)
-				goto got_pg;
-
-			if (!(gfp_mask & __GFP_NOFAIL)) {
-				/*
-				 * The oom killer is not called for high-order
-				 * allocations that may fail, so if no progress
-				 * is being made, there are no other options and
-				 * retrying is unlikely to help.
-				 */
-				if (order > PAGE_ALLOC_COSTLY_ORDER)
-					goto nopage;
-				/*
-				 * The oom killer is not called for lowmem
-				 * allocations to prevent needlessly killing
-				 * innocent tasks.
-				 */
-				if (high_zoneidx < ZONE_NORMAL)
-					goto nopage;
-			}
-
-			goto restart;
-		}
-	}
-
 	/* Check if we should retry the allocation */
 	pages_reclaimed += did_some_progress;
 	if (should_alloc_retry(gfp_mask, order, did_some_progress,
 						pages_reclaimed)) {
+		/*
+		 * If we fail to make progress by freeing individual
+		 * pages, but the allocation wants us to keep going,
+		 * start OOM killing tasks.
+		 */
+		if (!did_some_progress) {
+			page = __alloc_pages_may_oom(gfp_mask, order, zonelist,
+						high_zoneidx, nodemask,
+						preferred_zone, classzone_idx,
+						migratetype,&did_some_progress);
+			if (page)
+				goto got_pg;
+			if (!did_some_progress) {
+				BUG_ON(gfp_mask & __GFP_NOFAIL);
+				goto nopage;
+			}
+		}
 		/* Wait for some write requests to complete then retry */
 		wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50);
 		goto rebalance;
@@ -2876,6 +2867,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	unsigned int cpuset_mems_cookie;
 	int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_FAIR;
 	int classzone_idx;
+	gfp_t mask;
 
 	gfp_mask &= gfp_allowed_mask;
 
@@ -2909,22 +2901,24 @@ retry_cpuset:
 	classzone_idx = zonelist_zone_idx(preferred_zoneref);
 
 	/* First allocation attempt */
-	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
-			zonelist, high_zoneidx, alloc_flags,
-			preferred_zone, classzone_idx, migratetype);
+	mask = gfp_mask|__GFP_HARDWALL;
+	page = get_page_from_freelist(mask, nodemask, order, zonelist,
+			high_zoneidx, alloc_flags, preferred_zone,
+			classzone_idx, migratetype);
 	if (unlikely(!page)) {
 		/*
 		 * Runtime PM, block IO and its error handling path
 		 * can deadlock because I/O on the device might not
 		 * complete.
 		 */
-		gfp_mask = memalloc_noio_flags(gfp_mask);
-		page = __alloc_pages_slowpath(gfp_mask, order,
+		mask = memalloc_noio_flags(gfp_mask);
+
+		page = __alloc_pages_slowpath(mask, order,
 				zonelist, high_zoneidx, nodemask,
 				preferred_zone, classzone_idx, migratetype);
 	}
 
-	trace_mm_page_alloc(page, order, gfp_mask, migratetype);
+	trace_mm_page_alloc(page, order, mask, migratetype);
 
 out:
 	/*
@@ -5586,7 +5580,7 @@ void __init mem_init_print_info(const char *str)
 
 	pr_info("Memory: %luK/%luK available "
 	       "(%luK kernel code, %luK rwdata, %luK rodata, "
-	       "%luK init, %luK bss, %luK reserved"
+	       "%luK init, %luK bss, %luK reserved, %luK cma-reserved"
 #ifdef	CONFIG_HIGHMEM
 	       ", %luK highmem"
 #endif
@@ -5594,7 +5588,8 @@ void __init mem_init_print_info(const char *str)
 	       nr_free_pages() << (PAGE_SHIFT-10), physpages << (PAGE_SHIFT-10),
 	       codesize >> 10, datasize >> 10, rosize >> 10,
 	       (init_data_size + init_code_size) >> 10, bss_size >> 10,
-	       (physpages - totalram_pages) << (PAGE_SHIFT-10),
+	       (physpages - totalram_pages - totalcma_pages) << (PAGE_SHIFT-10),
+	       totalcma_pages << (PAGE_SHIFT-10),
 #ifdef	CONFIG_HIGHMEM
 	       totalhigh_pages << (PAGE_SHIFT-10),
 #endif
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 72f5ac381ab..e5d9c527796 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -176,8 +176,11 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 undo:
 	for (pfn = start_pfn;
 	     pfn < undo_pfn;
-	     pfn += pageblock_nr_pages)
-		unset_migratetype_isolate(pfn_to_page(pfn), migratetype);
+	     pfn += pageblock_nr_pages) {
+		page = __first_valid_page(pfn, pageblock_nr_pages);
+		if (page)
+			unset_migratetype_isolate(page, migratetype);
+	}
 
 	return -EBUSY;
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index c5bc241127b..b4047838da0 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -666,6 +666,7 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
 }
 
 struct page_referenced_arg {
+	int dirtied;
 	int mapcount;
 	int referenced;
 	unsigned long vm_flags;
@@ -680,6 +681,7 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 	struct mm_struct *mm = vma->vm_mm;
 	spinlock_t *ptl;
 	int referenced = 0;
+	int dirty = 0;
 	struct page_referenced_arg *pra = arg;
 
 	if (unlikely(PageTransHuge(page))) {
@@ -703,6 +705,15 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 		/* go ahead even if the pmd is pmd_trans_splitting() */
 		if (pmdp_clear_flush_young_notify(vma, address, pmd))
 			referenced++;
+
+		/*
+		 * Use pmd_freeable instead of raw pmd_dirty because in some
+		 * of architecture, pmd_dirty is not defined unless
+		 * CONFIG_TRANSPARENT_HUGEPAGE is enabled
+		 */
+		if (!pmd_freeable(*pmd))
+			dirty++;
+
 		spin_unlock(ptl);
 	} else {
 		pte_t *pte;
@@ -732,6 +743,10 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 			if (likely(!(vma->vm_flags & VM_SEQ_READ)))
 				referenced++;
 		}
+
+		if (pte_dirty(*pte))
+			dirty++;
+
 		pte_unmap_unlock(pte, ptl);
 	}
 
@@ -740,6 +755,9 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 		pra->vm_flags |= vma->vm_flags;
 	}
 
+	if (dirty)
+		pra->dirtied++;
+
 	pra->mapcount--;
 	if (!pra->mapcount)
 		return SWAP_SUCCESS; /* To break the loop */
@@ -764,6 +782,7 @@ static bool invalid_page_referenced_vma(struct vm_area_struct *vma, void *arg)
  * @is_locked: caller holds lock on the page
  * @memcg: target memory cgroup
  * @vm_flags: collect encountered vma->vm_flags who actually referenced the page
+ * @is_pte_dirty: ptes which have marked dirty bit - used for lazyfree page
  *
  * Quick test_and_clear_referenced for all mappings to a page,
  * returns the number of ptes which referenced the page.
@@ -771,7 +790,8 @@ static bool invalid_page_referenced_vma(struct vm_area_struct *vma, void *arg)
 int page_referenced(struct page *page,
 		    int is_locked,
 		    struct mem_cgroup *memcg,
-		    unsigned long *vm_flags)
+		    unsigned long *vm_flags,
+		    int *is_pte_dirty)
 {
 	int ret;
 	int we_locked = 0;
@@ -786,6 +806,9 @@ int page_referenced(struct page *page,
 	};
 
 	*vm_flags = 0;
+	if (is_pte_dirty)
+		*is_pte_dirty = 0;
+
 	if (!page_mapped(page))
 		return 0;
 
@@ -813,6 +836,9 @@ int page_referenced(struct page *page,
 	if (we_locked)
 		unlock_page(page);
 
+	if (is_pte_dirty)
+		*is_pte_dirty = pra.dirtied;
+
 	return pra.referenced;
 }
 
@@ -1145,6 +1171,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	spinlock_t *ptl;
 	int ret = SWAP_AGAIN;
 	enum ttu_flags flags = (enum ttu_flags)arg;
+	int dirty = 0;
 
 	pte = page_check_address(page, mm, address, &ptl, 0);
 	if (!pte)
@@ -1174,7 +1201,8 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	pteval = ptep_clear_flush(vma, address, pte);
 
 	/* Move the dirty bit to the physical page now the pte is gone. */
-	if (pte_dirty(pteval))
+	dirty = pte_dirty(pteval);
+	if (dirty)
 		set_page_dirty(page);
 
 	/* Update high watermark before we lower rss */
@@ -1203,6 +1231,19 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 		swp_entry_t entry = { .val = page_private(page) };
 		pte_t swp_pte;
 
+		if (flags & TTU_FREE) {
+			VM_BUG_ON_PAGE(PageSwapCache(page), page);
+			if (!dirty && !PageDirty(page)) {
+				/* It's a freeable page by MADV_FREE */
+				dec_mm_counter(mm, MM_ANONPAGES);
+				goto discard;
+			} else {
+				set_pte_at(mm, address, pte, pteval);
+				ret = SWAP_FAIL;
+				goto out_unmap;
+			}
+		}
+
 		if (PageSwapCache(page)) {
 			/*
 			 * Store the swap location in the pte.
@@ -1244,6 +1285,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	} else
 		dec_mm_counter(mm, MM_FILEPAGES);
 
+discard:
 	page_remove_rmap(page);
 	page_cache_release(page);
 
diff --git a/mm/util.c b/mm/util.c
index fec39d4509a..d25558ba661 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -3,6 +3,7 @@
 #include <linux/string.h>
 #include <linux/compiler.h>
 #include <linux/export.h>
+#include <linux/ctype.h>
 #include <linux/err.h>
 #include <linux/sched.h>
 #include <linux/security.h>
@@ -62,6 +63,35 @@ char *kstrndup(const char *s, size_t max, gfp_t gfp)
 EXPORT_SYMBOL(kstrndup);
 
 /**
+ * kstrimdup - Trim and copy a %NUL terminated string.
+ * @s: the string to trim and duplicate
+ * @gfp: the GFP mask used in the kmalloc() call when allocating memory
+ *
+ * Returns an address, which the caller must kfree, containing
+ * a duplicate of the passed string with leading and/or trailing
+ * whitespace (as defined by isspace) removed.
+ */
+char *kstrimdup(const char *s, gfp_t gfp)
+{
+	char *buf;
+	char *begin = skip_spaces(s);
+	size_t len = strlen(begin);
+
+	while (len && isspace(begin[len - 1]))
+		len--;
+
+	buf = kmalloc_track_caller(len + 1, gfp);
+	if (!buf)
+		return NULL;
+
+	memcpy(buf, begin, len);
+	buf[len] = '\0';
+
+	return buf;
+}
+EXPORT_SYMBOL(kstrimdup);
+
+/**
  * kmemdup - duplicate region of memory
  *
  * @src: memory region to duplicate
diff --git a/mm/vmscan.c b/mm/vmscan.c
index bd9a72bc4a1..5e8772b2b9e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -713,13 +713,17 @@ enum page_references {
 };
 
 static enum page_references page_check_references(struct page *page,
-						  struct scan_control *sc)
+						  struct scan_control *sc,
+						  bool *freeable)
 {
 	int referenced_ptes, referenced_page;
 	unsigned long vm_flags;
+	int pte_dirty;
+
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
 
 	referenced_ptes = page_referenced(page, 1, sc->target_mem_cgroup,
-					  &vm_flags);
+					  &vm_flags, &pte_dirty);
 	referenced_page = TestClearPageReferenced(page);
 
 	/*
@@ -760,6 +764,10 @@ static enum page_references page_check_references(struct page *page,
 		return PAGEREF_KEEP;
 	}
 
+	if (PageAnon(page) && !pte_dirty && !PageSwapCache(page) &&
+			!PageDirty(page))
+		*freeable = true;
+
 	/* Reclaim if clean, defer dirty pages to writeback */
 	if (referenced_page && !PageSwapBacked(page))
 		return PAGEREF_RECLAIM_CLEAN;
@@ -828,6 +836,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		int may_enter_fs;
 		enum page_references references = PAGEREF_RECLAIM_CLEAN;
 		bool dirty, writeback;
+		bool freeable = false;
 
 		cond_resched();
 
@@ -951,7 +960,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		}
 
 		if (!force_reclaim)
-			references = page_check_references(page, sc);
+			references = page_check_references(page, sc,
+							&freeable);
 
 		switch (references) {
 		case PAGEREF_ACTIVATE:
@@ -968,22 +978,31 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * Try to allocate it some swap space here.
 		 */
 		if (PageAnon(page) && !PageSwapCache(page)) {
-			if (!(sc->gfp_mask & __GFP_IO))
-				goto keep_locked;
-			if (!add_to_swap(page, page_list))
-				goto activate_locked;
-			may_enter_fs = 1;
-
-			/* Adding to swap updated mapping */
-			mapping = page_mapping(page);
+			if (!freeable) {
+				if (!(sc->gfp_mask & __GFP_IO))
+					goto keep_locked;
+				if (!add_to_swap(page, page_list))
+					goto activate_locked;
+				may_enter_fs = 1;
+				/* Adding to swap updated mapping */
+				mapping = page_mapping(page);
+			} else {
+				if (likely(!PageTransHuge(page)))
+					goto unmap;
+				/* try_to_unmap isn't aware of THP page */
+				if (unlikely(split_huge_page_to_list(page,
+								page_list)))
+					goto keep_locked;
+			}
 		}
-
+unmap:
 		/*
 		 * The page is mapped into the page tables of one or more
 		 * processes. Try to unmap it here.
 		 */
-		if (page_mapped(page) && mapping) {
-			switch (try_to_unmap(page, ttu_flags)) {
+		if (page_mapped(page) && (mapping || freeable)) {
+			switch (try_to_unmap(page,
+				freeable ? TTU_FREE : ttu_flags)) {
 			case SWAP_FAIL:
 				goto activate_locked;
 			case SWAP_AGAIN:
@@ -991,7 +1010,20 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			case SWAP_MLOCK:
 				goto cull_mlocked;
 			case SWAP_SUCCESS:
-				; /* try to free the page below */
+				/* try to free the page below */
+				if (!freeable)
+					break;
+				/*
+				 * Freeable anon page doesn't have mapping
+				 * due to skipping of swapcache so we free
+				 * page in here rather than __remove_mapping.
+				 */
+				VM_BUG_ON_PAGE(PageSwapCache(page), page);
+				if (!page_freeze_refs(page, 1))
+					goto keep_locked;
+				__clear_page_locked(page);
+				count_vm_event(PGLAZYFREED);
+				goto free_it;
 			}
 		}
 
@@ -1731,7 +1763,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 		}
 
 		if (page_referenced(page, 0, sc->target_mem_cgroup,
-				    &vm_flags)) {
+				    &vm_flags, NULL)) {
 			nr_rotated += hpage_nr_pages(page);
 			/*
 			 * Identify referenced, file-backed active pages and
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 1284f89fca0..5fba97d122a 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -816,6 +816,7 @@ const char * const vmstat_text[] = {
 
 	"pgfault",
 	"pgmajfault",
+	"pglazyfreed",
 
 	TEXTS_FOR_ZONES("pgrefill")
 	TEXTS_FOR_ZONES("pgsteal_kswapd")