diff --git a/Documentation/devicetree/bindings/mfd/tc3589x.txt b/Documentation/devicetree/bindings/mfd/tc3589x.txt
new file mode 100644
index 0000000..6fcedba
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/tc3589x.txt
@@ -0,0 +1,107 @@
+* Toshiba TC3589x multi-purpose expander
+
+The Toshiba TC3589x series are I2C-based MFD devices which may expose the
+following built-in devices: gpio, keypad, rotator (vibrator), PWM (for
+e.g. LEDs or vibrators) The included models are:
+
+- TC35890
+- TC35892
+- TC35893
+- TC35894
+- TC35895
+- TC35896
+
+Required properties:
+ - compatible : must be "toshiba,tc35890", "toshiba,tc35892", "toshiba,tc35893",
+   "toshiba,tc35894", "toshiba,tc35895" or "toshiba,tc35896"
+ - reg : I2C address of the device
+ - interrupt-parent : specifies which IRQ controller we're connected to
+ - interrupts : the interrupt on the parent the controller is connected to
+ - interrupt-controller : marks the device node as an interrupt controller
+ - #interrupt-cells : should be <1>, the first cell is the IRQ offset on this
+   TC3589x interrupt controller.
+
+Optional nodes:
+
+- GPIO
+  This GPIO module inside the TC3589x has 24 (TC35890, TC35892) or 20
+  (other models) GPIO lines.
+ - compatible : must be "toshiba,tc3589x-gpio"
+ - interrupts : interrupt on the parent, which must be the tc3589x MFD device
+ - interrupt-controller : marks the device node as an interrupt controller
+ - #interrupt-cells : should be <2>, the first cell is the IRQ offset on this
+   TC3589x GPIO interrupt controller, the second cell is the interrupt flags
+   in accordance with <dt-bindings/interrupt-controller/irq.h>. The following
+   flags are valid:
+   - IRQ_TYPE_LEVEL_LOW
+   - IRQ_TYPE_LEVEL_HIGH
+   - IRQ_TYPE_EDGE_RISING
+   - IRQ_TYPE_EDGE_FALLING
+   - IRQ_TYPE_EDGE_BOTH
+ - gpio-controller : marks the device node as a GPIO controller
+ - #gpio-cells : should be <2>, the first cell is the GPIO offset on this
+   GPIO controller, the second cell is the flags.
+
+- Keypad
+  This keypad is the same on all variants, supporting up to 96 different
+  keys. The linux-specific properties are modeled on those already existing
+  in other input drivers.
+ - compatible : must be "toshiba,tc3589x-keypad"
+ - debounce-delay-ms : debounce interval in milliseconds
+ - keypad,num-rows : number of rows in the matrix, see
+   bindings/input/matrix-keymap.txt
+ - keypad,num-columns : number of columns in the matrix, see
+   bindings/input/matrix-keymap.txt
+ - linux,keymap: the definition can be found in
+   bindings/input/matrix-keymap.txt
+ - linux,no-autorepeat: do no enable autorepeat feature.
+ - linux,wakeup: use any event on keypad as wakeup event.
+
+Example:
+
+tc35893@44 {
+	compatible = "toshiba,tc35893";
+	reg = <0x44>;
+	interrupt-parent = <&gpio6>;
+	interrupts = <26 IRQ_TYPE_EDGE_RISING>;
+
+	interrupt-controller;
+	#interrupt-cells = <1>;
+
+	tc3589x_gpio {
+		compatible = "toshiba,tc3589x-gpio";
+		interrupts = <0>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
+	tc3589x_keypad {
+		compatible = "toshiba,tc3589x-keypad";
+		interrupts = <6>;
+		debounce-delay-ms = <4>;
+		keypad,num-columns = <8>;
+		keypad,num-rows = <8>;
+		linux,no-autorepeat;
+		linux,wakeup;
+		linux,keymap = <0x0301006b
+				0x04010066
+				0x06040072
+				0x040200d7
+				0x0303006a
+				0x0205000e
+				0x0607008b
+				0x0500001c
+				0x0403000b
+				0x03040034
+				0x05020067
+				0x0305006c
+				0x040500e7
+				0x0005009e
+				0x06020073
+				0x01030039
+				0x07060069
+				0x050500d9>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,apq8064-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,apq8064-pinctrl.txt
index 0211c6d..92fae82 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,apq8064-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,apq8064-pinctrl.txt
@@ -62,7 +62,7 @@
 		#gpio-cells = <2>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
-		interrupts = <0 32 0x4>;
+		interrupts = <0 16 0x4>;
 
 		pinctrl-names = "default";
 		pinctrl-0 = <&gsbi5_uart_default>;
diff --git a/Documentation/dma-buf-sharing.txt b/Documentation/dma-buf-sharing.txt
index 67a4087..bb9753b 100644
--- a/Documentation/dma-buf-sharing.txt
+++ b/Documentation/dma-buf-sharing.txt
@@ -56,10 +56,10 @@
 				     size_t size, int flags,
 				     const char *exp_name)
 
-   If this succeeds, dma_buf_export allocates a dma_buf structure, and returns a
-   pointer to the same. It also associates an anonymous file with this buffer,
-   so it can be exported. On failure to allocate the dma_buf object, it returns
-   NULL.
+   If this succeeds, dma_buf_export_named allocates a dma_buf structure, and
+   returns a pointer to the same. It also associates an anonymous file with this
+   buffer, so it can be exported. On failure to allocate the dma_buf object,
+   it returns NULL.
 
    'exp_name' is the name of exporter - to facilitate information while
    debugging.
@@ -76,7 +76,7 @@
    drivers and/or processes.
 
    Interface:
-      int dma_buf_fd(struct dma_buf *dmabuf)
+      int dma_buf_fd(struct dma_buf *dmabuf, int flags)
 
    This API installs an fd for the anonymous file associated with this buffer;
    returns either 'fd', or error.
@@ -157,7 +157,9 @@
    "dma_buf->ops->" indirection from the users of this interface.
 
    In struct dma_buf_ops, unmap_dma_buf is defined as
-      void (*unmap_dma_buf)(struct dma_buf_attachment *, struct sg_table *);
+      void (*unmap_dma_buf)(struct dma_buf_attachment *,
+                            struct sg_table *,
+                            enum dma_data_direction);
 
    unmap_dma_buf signifies the end-of-DMA for the attachment provided. Like
    map_dma_buf, this API also must be implemented by the exporter.
diff --git a/Documentation/this_cpu_ops.txt b/Documentation/this_cpu_ops.txt
index 1a4ce7e..0ec9957 100644
--- a/Documentation/this_cpu_ops.txt
+++ b/Documentation/this_cpu_ops.txt
@@ -2,26 +2,26 @@
 -------------------
 
 this_cpu operations are a way of optimizing access to per cpu
-variables associated with the *currently* executing processor through
-the use of segment registers (or a dedicated register where the cpu
-permanently stored the beginning of the per cpu area for a specific
-processor).
+variables associated with the *currently* executing processor. This is
+done through the use of segment registers (or a dedicated register where
+the cpu permanently stored the beginning of the per cpu	area for a
+specific processor).
 
-The this_cpu operations add a per cpu variable offset to the processor
-specific percpu base and encode that operation in the instruction
+this_cpu operations add a per cpu variable offset to the processor
+specific per cpu base and encode that operation in the instruction
 operating on the per cpu variable.
 
-This means there are no atomicity issues between the calculation of
+This means that there are no atomicity issues between the calculation of
 the offset and the operation on the data. Therefore it is not
-necessary to disable preempt or interrupts to ensure that the
+necessary to disable preemption or interrupts to ensure that the
 processor is not changed between the calculation of the address and
 the operation on the data.
 
 Read-modify-write operations are of particular interest. Frequently
 processors have special lower latency instructions that can operate
-without the typical synchronization overhead but still provide some
-sort of relaxed atomicity guarantee. The x86 for example can execute
-RMV (Read Modify Write) instructions like inc/dec/cmpxchg without the
+without the typical synchronization overhead, but still provide some
+sort of relaxed atomicity guarantees. The x86, for example, can execute
+RMW (Read Modify Write) instructions like inc/dec/cmpxchg without the
 lock prefix and the associated latency penalty.
 
 Access to the variable without the lock prefix is not synchronized but
@@ -30,6 +30,38 @@
 processor should be accessing that variable and therefore there are no
 concurrency issues with other processors in the system.
 
+Please note that accesses by remote processors to a per cpu area are
+exceptional situations and may impact performance and/or correctness
+(remote write operations) of local RMW operations via this_cpu_*.
+
+The main use of the this_cpu operations has been to optimize counter
+operations.
+
+The following this_cpu() operations with implied preemption protection
+are defined. These operations can be used without worrying about
+preemption and interrupts.
+
+	this_cpu_add()
+	this_cpu_read(pcp)
+	this_cpu_write(pcp, val)
+	this_cpu_add(pcp, val)
+	this_cpu_and(pcp, val)
+	this_cpu_or(pcp, val)
+	this_cpu_add_return(pcp, val)
+	this_cpu_xchg(pcp, nval)
+	this_cpu_cmpxchg(pcp, oval, nval)
+	this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+	this_cpu_sub(pcp, val)
+	this_cpu_inc(pcp)
+	this_cpu_dec(pcp)
+	this_cpu_sub_return(pcp, val)
+	this_cpu_inc_return(pcp)
+	this_cpu_dec_return(pcp)
+
+
+Inner working of this_cpu operations
+------------------------------------
+
 On x86 the fs: or the gs: segment registers contain the base of the
 per cpu area. It is then possible to simply use the segment override
 to relocate a per cpu relative address to the proper per cpu area for
@@ -48,22 +80,21 @@
 	mov ax, gs:[x]
 
 instead of a sequence of calculation of the address and then a fetch
-from that address which occurs with the percpu operations. Before
+from that address which occurs with the per cpu operations. Before
 this_cpu_ops such sequence also required preempt disable/enable to
 prevent the kernel from moving the thread to a different processor
 while the calculation is performed.
 
-The main use of the this_cpu operations has been to optimize counter
-operations.
+Consider the following this_cpu operation:
 
 	this_cpu_inc(x)
 
-results in the following single instruction (no lock prefix!)
+The above results in the following single instruction (no lock prefix!)
 
 	inc gs:[x]
 
 instead of the following operations required if there is no segment
-register.
+register:
 
 	int *y;
 	int cpu;
@@ -73,10 +104,10 @@
 	(*y)++;
 	put_cpu();
 
-Note that these operations can only be used on percpu data that is
+Note that these operations can only be used on per cpu data that is
 reserved for a specific processor. Without disabling preemption in the
 surrounding code this_cpu_inc() will only guarantee that one of the
-percpu counters is correctly incremented. However, there is no
+per cpu counters is correctly incremented. However, there is no
 guarantee that the OS will not move the process directly before or
 after the this_cpu instruction is executed. In general this means that
 the value of the individual counters for each processor are
@@ -86,9 +117,9 @@
 Per cpu variables are used for performance reasons. Bouncing cache
 lines can be avoided if multiple processors concurrently go through
 the same code paths.  Since each processor has its own per cpu
-variables no concurrent cacheline updates take place. The price that
+variables no concurrent cache line updates take place. The price that
 has to be paid for this optimization is the need to add up the per cpu
-counters when the value of the counter is needed.
+counters when the value of a counter is needed.
 
 
 Special operations:
@@ -100,33 +131,39 @@
 of the per cpu variable that belongs to the currently executing
 processor.  this_cpu_ptr avoids multiple steps that the common
 get_cpu/put_cpu sequence requires. No processor number is
-available. Instead the offset of the local per cpu area is simply
-added to the percpu offset.
+available. Instead, the offset of the local per cpu area is simply
+added to the per cpu offset.
 
+Note that this operation is usually used in a code segment when
+preemption has been disabled. The pointer is then used to
+access local per cpu data in a critical section. When preemption
+is re-enabled this pointer is usually no longer useful since it may
+no longer point to per cpu data of the current processor.
 
 
 Per cpu variables and offsets
 -----------------------------
 
-Per cpu variables have *offsets* to the beginning of the percpu
+Per cpu variables have *offsets* to the beginning of the per cpu
 area. They do not have addresses although they look like that in the
 code. Offsets cannot be directly dereferenced. The offset must be
-added to a base pointer of a percpu area of a processor in order to
+added to a base pointer of a per cpu area of a processor in order to
 form a valid address.
 
 Therefore the use of x or &x outside of the context of per cpu
 operations is invalid and will generally be treated like a NULL
 pointer dereference.
 
-In the context of per cpu operations
+	DEFINE_PER_CPU(int, x);
 
-	x is a per cpu variable. Most this_cpu operations take a cpu
-	variable.
+In the context of per cpu operations the above implies that x is a per
+cpu variable. Most this_cpu operations take a cpu variable.
 
-	&x is the *offset* a per cpu variable. this_cpu_ptr() takes
-	the offset of a per cpu variable which makes this look a bit
-	strange.
+	int __percpu *p = &x;
 
+&x and hence p is the *offset* of a per cpu variable. this_cpu_ptr()
+takes the offset of a per cpu variable which makes this look a bit
+strange.
 
 
 Operations on a field of a per cpu structure
@@ -152,7 +189,7 @@
 
 	struct s __percpu *ps = &p;
 
-	z = this_cpu_dec(ps->m);
+	this_cpu_dec(ps->m);
 
 	z = this_cpu_inc_return(ps->n);
 
@@ -172,29 +209,52 @@
 Variants of this_cpu ops
 -------------------------
 
-this_cpu ops are interrupt safe. Some architecture do not support
+this_cpu ops are interrupt safe. Some architectures do not support
 these per cpu local operations. In that case the operation must be
 replaced by code that disables interrupts, then does the operations
-that are guaranteed to be atomic and then reenable interrupts. Doing
+that are guaranteed to be atomic and then re-enable interrupts. Doing
 so is expensive. If there are other reasons why the scheduler cannot
 change the processor we are executing on then there is no reason to
-disable interrupts. For that purpose the __this_cpu operations are
-provided. For example.
+disable interrupts. For that purpose the following __this_cpu operations
+are provided.
 
-	__this_cpu_inc(x);
+These operations have no guarantee against concurrent interrupts or
+preemption. If a per cpu variable is not used in an interrupt context
+and the scheduler cannot preempt, then they are safe. If any interrupts
+still occur while an operation is in progress and if the interrupt too
+modifies the variable, then RMW actions can not be guaranteed to be
+safe.
 
-Will increment x and will not fallback to code that disables
+	__this_cpu_add()
+	__this_cpu_read(pcp)
+	__this_cpu_write(pcp, val)
+	__this_cpu_add(pcp, val)
+	__this_cpu_and(pcp, val)
+	__this_cpu_or(pcp, val)
+	__this_cpu_add_return(pcp, val)
+	__this_cpu_xchg(pcp, nval)
+	__this_cpu_cmpxchg(pcp, oval, nval)
+	__this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+	__this_cpu_sub(pcp, val)
+	__this_cpu_inc(pcp)
+	__this_cpu_dec(pcp)
+	__this_cpu_sub_return(pcp, val)
+	__this_cpu_inc_return(pcp)
+	__this_cpu_dec_return(pcp)
+
+
+Will increment x and will not fall-back to code that disables
 interrupts on platforms that cannot accomplish atomicity through
 address relocation and a Read-Modify-Write operation in the same
 instruction.
 
 
-
 &this_cpu_ptr(pp)->n vs this_cpu_ptr(&pp->n)
 --------------------------------------------
 
 The first operation takes the offset and forms an address and then
-adds the offset of the n field.
+adds the offset of the n field. This may result in two add
+instructions emitted by the compiler.
 
 The second one first adds the two offsets and then does the
 relocation.  IMHO the second form looks cleaner and has an easier time
@@ -202,4 +262,73 @@
 this_cpu_read() and friends are used.
 
 
-Christoph Lameter, April 3rd, 2013
+Remote access to per cpu data
+------------------------------
+
+Per cpu data structures are designed to be used by one cpu exclusively.
+If you use the variables as intended, this_cpu_ops() are guaranteed to
+be "atomic" as no other CPU has access to these data structures.
+
+There are special cases where you might need to access per cpu data
+structures remotely. It is usually safe to do a remote read access
+and that is frequently done to summarize counters. Remote write access
+something which could be problematic because this_cpu ops do not
+have lock semantics. A remote write may interfere with a this_cpu
+RMW operation.
+
+Remote write accesses to percpu data structures are highly discouraged
+unless absolutely necessary. Please consider using an IPI to wake up
+the remote CPU and perform the update to its per cpu area.
+
+To access per-cpu data structure remotely, typically the per_cpu_ptr()
+function is used:
+
+
+	DEFINE_PER_CPU(struct data, datap);
+
+	struct data *p = per_cpu_ptr(&datap, cpu);
+
+This makes it explicit that we are getting ready to access a percpu
+area remotely.
+
+You can also do the following to convert the datap offset to an address
+
+	struct data *p = this_cpu_ptr(&datap);
+
+but, passing of pointers calculated via this_cpu_ptr to other cpus is
+unusual and should be avoided.
+
+Remote access are typically only for reading the status of another cpus
+per cpu data. Write accesses can cause unique problems due to the
+relaxed synchronization requirements for this_cpu operations.
+
+One example that illustrates some concerns with write operations is
+the following scenario that occurs because two per cpu variables
+share a cache-line but the relaxed synchronization is applied to
+only one process updating the cache-line.
+
+Consider the following example
+
+
+	struct test {
+		atomic_t a;
+		int b;
+	};
+
+	DEFINE_PER_CPU(struct test, onecacheline);
+
+There is some concern about what would happen if the field 'a' is updated
+remotely from one processor and the local processor would use this_cpu ops
+to update field b. Care should be taken that such simultaneous accesses to
+data within the same cache line are avoided. Also costly synchronization
+may be necessary. IPIs are generally recommended in such scenarios instead
+of a remote write to the per cpu area of another processor.
+
+Even in cases where the remote writes are rare, please bear in
+mind that a remote write will evict the cache line from the processor
+that most likely will access it. If the processor wakes up and finds a
+missing local cache line of a per cpu area, its performance and hence
+the wake up times will be affected.
+
+Christoph Lameter, August 4th, 2014
+Pranith Kumar, Aug 2nd, 2014
diff --git a/arch/alpha/include/asm/io.h b/arch/alpha/include/asm/io.h
index 5ebab58..f05bdb4 100644
--- a/arch/alpha/include/asm/io.h
+++ b/arch/alpha/include/asm/io.h
@@ -500,10 +500,14 @@
 #define outb_p		outb
 #define outw_p		outw
 #define outl_p		outl
-#define readb_relaxed(addr) __raw_readb(addr)
-#define readw_relaxed(addr) __raw_readw(addr)
-#define readl_relaxed(addr) __raw_readl(addr)
-#define readq_relaxed(addr) __raw_readq(addr)
+#define readb_relaxed(addr)	__raw_readb(addr)
+#define readw_relaxed(addr)	__raw_readw(addr)
+#define readl_relaxed(addr)	__raw_readl(addr)
+#define readq_relaxed(addr)	__raw_readq(addr)
+#define writeb_relaxed(b, addr)	__raw_writeb(b, addr)
+#define writew_relaxed(b, addr)	__raw_writew(b, addr)
+#define writel_relaxed(b, addr)	__raw_writel(b, addr)
+#define writeq_relaxed(b, addr)	__raw_writeq(b, addr)
 
 #define mmiowb()
 
diff --git a/arch/alpha/include/asm/unistd.h b/arch/alpha/include/asm/unistd.h
index f2c9440..c509d30 100644
--- a/arch/alpha/include/asm/unistd.h
+++ b/arch/alpha/include/asm/unistd.h
@@ -3,7 +3,7 @@
 
 #include <uapi/asm/unistd.h>
 
-#define NR_SYSCALLS			508
+#define NR_SYSCALLS			511
 
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_STAT64
diff --git a/arch/alpha/include/uapi/asm/unistd.h b/arch/alpha/include/uapi/asm/unistd.h
index 53ae7bb..d214a035 100644
--- a/arch/alpha/include/uapi/asm/unistd.h
+++ b/arch/alpha/include/uapi/asm/unistd.h
@@ -469,5 +469,8 @@
 #define __NR_process_vm_writev		505
 #define __NR_kcmp			506
 #define __NR_finit_module		507
+#define __NR_sched_setattr		508
+#define __NR_sched_getattr		509
+#define __NR_renameat2			510
 
 #endif /* _UAPI_ALPHA_UNISTD_H */
diff --git a/arch/alpha/kernel/systbls.S b/arch/alpha/kernel/systbls.S
index dca9b3f..24789713 100644
--- a/arch/alpha/kernel/systbls.S
+++ b/arch/alpha/kernel/systbls.S
@@ -526,6 +526,9 @@
 	.quad sys_process_vm_writev		/* 505 */
 	.quad sys_kcmp
 	.quad sys_finit_module
+	.quad sys_sched_setattr
+	.quad sys_sched_getattr
+	.quad sys_renameat2			/* 510 */
 
 	.size sys_call_table, . - sys_call_table
 	.type sys_call_table, @object
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index b15f1a7..1fe45d1 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -353,7 +353,7 @@
 	};
 
 	twl_power: power {
-		compatible = "ti,twl4030-power-n900";
+		compatible = "ti,twl4030-power-n900", "ti,twl4030-power-idle-osc-off";
 		ti,use_poweroff;
 	};
 };
diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h
index 3802d2d..940ac49 100644
--- a/arch/s390/include/uapi/asm/unistd.h
+++ b/arch/s390/include/uapi/asm/unistd.h
@@ -283,7 +283,10 @@
 #define __NR_sched_setattr	345
 #define __NR_sched_getattr	346
 #define __NR_renameat2		347
-#define NR_syscalls 348
+#define __NR_seccomp		348
+#define __NR_getrandom		349
+#define __NR_memfd_create	350
+#define NR_syscalls 351
 
 /* 
  * There are some system calls that are not present on 64 bit, some
diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c
index 45cdb37..faf6caa 100644
--- a/arch/s390/kernel/compat_wrapper.c
+++ b/arch/s390/kernel/compat_wrapper.c
@@ -214,3 +214,6 @@
 COMPAT_SYSCALL_WRAP3(sched_setattr, pid_t, pid, struct sched_attr __user *, attr, unsigned int, flags);
 COMPAT_SYSCALL_WRAP4(sched_getattr, pid_t, pid, struct sched_attr __user *, attr, unsigned int, size, unsigned int, flags);
 COMPAT_SYSCALL_WRAP5(renameat2, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, unsigned int, flags);
+COMPAT_SYSCALL_WRAP3(seccomp, unsigned int, op, unsigned int, flags, const char __user *, uargs)
+COMPAT_SYSCALL_WRAP3(getrandom, char __user *, buf, size_t, count, unsigned int, flags)
+COMPAT_SYSCALL_WRAP2(memfd_create, const char __user *, uname, unsigned int, flags)
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 633ca75..22aac58 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -2060,6 +2060,13 @@
 	S390_lowcore.program_new_psw.addr =
 		PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler;
 
+	/*
+	 * Clear subchannel ID and number to signal new kernel that no CCW or
+	 * SCSI IPL has been done (for kexec and kdump)
+	 */
+	S390_lowcore.subchannel_id = 0;
+	S390_lowcore.subchannel_nr = 0;
+
 	/* Store status at absolute zero */
 	store_status();
 
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index ae1d5be..82bc113 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -24,6 +24,7 @@
 #include <linux/stddef.h>
 #include <linux/unistd.h>
 #include <linux/ptrace.h>
+#include <linux/random.h>
 #include <linux/user.h>
 #include <linux/tty.h>
 #include <linux/ioport.h>
@@ -61,6 +62,7 @@
 #include <asm/diag.h>
 #include <asm/os_info.h>
 #include <asm/sclp.h>
+#include <asm/sysinfo.h>
 #include "entry.h"
 
 /*
@@ -766,6 +768,7 @@
 #endif
 
 	get_cpu_id(&cpu_id);
+	add_device_randomness(&cpu_id, sizeof(cpu_id));
 	switch (cpu_id.machine) {
 	case 0x9672:
 #if !defined(CONFIG_64BIT)
@@ -804,6 +807,19 @@
 }
 
 /*
+ * Add system information as device randomness
+ */
+static void __init setup_randomness(void)
+{
+	struct sysinfo_3_2_2 *vmms;
+
+	vmms = (struct sysinfo_3_2_2 *) alloc_page(GFP_KERNEL);
+	if (vmms && stsi(vmms, 3, 2, 2) == 0 && vmms->count)
+		add_device_randomness(&vmms, vmms->count);
+	free_page((unsigned long) vmms);
+}
+
+/*
  * Setup function called from init/main.c just after the banner
  * was printed.
  */
@@ -901,6 +917,9 @@
 
 	/* Setup zfcpdump support */
 	setup_zfcpdump();
+
+	/* Add system specific data to the random pool */
+	setup_randomness();
 }
 
 #ifdef CONFIG_32BIT
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
index fe5cdf2..6fe886a 100644
--- a/arch/s390/kernel/syscalls.S
+++ b/arch/s390/kernel/syscalls.S
@@ -356,3 +356,6 @@
 SYSCALL(sys_sched_setattr,sys_sched_setattr,compat_sys_sched_setattr) /* 345 */
 SYSCALL(sys_sched_getattr,sys_sched_getattr,compat_sys_sched_getattr)
 SYSCALL(sys_renameat2,sys_renameat2,compat_sys_renameat2)
+SYSCALL(sys_seccomp,sys_seccomp,compat_sys_seccomp)
+SYSCALL(sys_getrandom,sys_getrandom,compat_sys_getrandom)
+SYSCALL(sys_memfd_create,sys_memfd_create,compat_sys_memfd_create) /* 350 */
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index bc423f7b..f14b4ab 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -520,7 +520,7 @@
 	 */
 	if (error) {
 		bio->bi_end_io = bip->bip_end_io;
-		bio_endio(bio, error);
+		bio_endio_nodec(bio, error);
 
 		return;
 	}
diff --git a/block/blk-core.c b/block/blk-core.c
index c359d72..bf930f4 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1252,7 +1252,6 @@
 	rq->__sector = (sector_t) -1;
 	rq->bio = rq->biotail = NULL;
 	memset(rq->__cmd, 0, sizeof(rq->__cmd));
-	rq->cmd = rq->__cmd;
 }
 EXPORT_SYMBOL(blk_rq_set_block_pc);
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 5189cb1..4aac826 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -112,18 +112,22 @@
  */
 void blk_mq_freeze_queue(struct request_queue *q)
 {
+	bool freeze;
+
 	spin_lock_irq(q->queue_lock);
-	q->mq_freeze_depth++;
+	freeze = !q->mq_freeze_depth++;
 	spin_unlock_irq(q->queue_lock);
 
-	percpu_ref_kill(&q->mq_usage_counter);
-	blk_mq_run_queues(q, false);
+	if (freeze) {
+		percpu_ref_kill(&q->mq_usage_counter);
+		blk_mq_run_queues(q, false);
+	}
 	wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->mq_usage_counter));
 }
 
 static void blk_mq_unfreeze_queue(struct request_queue *q)
 {
-	bool wake = false;
+	bool wake;
 
 	spin_lock_irq(q->queue_lock);
 	wake = !--q->mq_freeze_depth;
@@ -172,6 +176,8 @@
 	/* tag was already set */
 	rq->errors = 0;
 
+	rq->cmd = rq->__cmd;
+
 	rq->extra_len = 0;
 	rq->sense_len = 0;
 	rq->resid_len = 0;
@@ -1068,13 +1074,17 @@
 		blk_account_io_start(rq, 1);
 }
 
+static inline bool hctx_allow_merges(struct blk_mq_hw_ctx *hctx)
+{
+	return (hctx->flags & BLK_MQ_F_SHOULD_MERGE) &&
+		!blk_queue_nomerges(hctx->queue);
+}
+
 static inline bool blk_mq_merge_queue_io(struct blk_mq_hw_ctx *hctx,
 					 struct blk_mq_ctx *ctx,
 					 struct request *rq, struct bio *bio)
 {
-	struct request_queue *q = hctx->queue;
-
-	if (!(hctx->flags & BLK_MQ_F_SHOULD_MERGE)) {
+	if (!hctx_allow_merges(hctx)) {
 		blk_mq_bio_to_request(rq, bio);
 		spin_lock(&ctx->lock);
 insert_rq:
@@ -1082,6 +1092,8 @@
 		spin_unlock(&ctx->lock);
 		return false;
 	} else {
+		struct request_queue *q = hctx->queue;
+
 		spin_lock(&ctx->lock);
 		if (!blk_mq_attempt_merge(q, ctx, bio)) {
 			blk_mq_bio_to_request(rq, bio);
@@ -1574,7 +1586,7 @@
 		hctx->tags = set->tags[i];
 
 		/*
-		 * Allocate space for all possible cpus to avoid allocation in
+		 * Allocate space for all possible cpus to avoid allocation at
 		 * runtime
 		 */
 		hctx->ctxs = kmalloc_node(nr_cpu_ids * sizeof(void *),
@@ -1662,8 +1674,8 @@
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		/*
-		 * If not software queues are mapped to this hardware queue,
-		 * disable it and free the request entries
+		 * If no software queues are mapped to this hardware queue,
+		 * disable it and free the request entries.
 		 */
 		if (!hctx->nr_ctx) {
 			struct blk_mq_tag_set *set = q->tag_set;
@@ -1713,14 +1725,10 @@
 {
 	struct blk_mq_tag_set *set = q->tag_set;
 
-	blk_mq_freeze_queue(q);
-
 	mutex_lock(&set->tag_list_lock);
 	list_del_init(&q->tag_set_list);
 	blk_mq_update_tag_set_depth(set);
 	mutex_unlock(&set->tag_list_lock);
-
-	blk_mq_unfreeze_queue(q);
 }
 
 static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index cadc378..3f31cf9 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1272,15 +1272,22 @@
 	rb_insert_color(&cfqg->rb_node, &st->rb);
 }
 
+/*
+ * This has to be called only on activation of cfqg
+ */
 static void
 cfq_update_group_weight(struct cfq_group *cfqg)
 {
-	BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));
-
 	if (cfqg->new_weight) {
 		cfqg->weight = cfqg->new_weight;
 		cfqg->new_weight = 0;
 	}
+}
+
+static void
+cfq_update_group_leaf_weight(struct cfq_group *cfqg)
+{
+	BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));
 
 	if (cfqg->new_leaf_weight) {
 		cfqg->leaf_weight = cfqg->new_leaf_weight;
@@ -1299,7 +1306,12 @@
 	/* add to the service tree */
 	BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));
 
-	cfq_update_group_weight(cfqg);
+	/*
+	 * Update leaf_weight.  We cannot update weight at this point
+	 * because cfqg might already have been activated and is
+	 * contributing its current weight to the parent's child_weight.
+	 */
+	cfq_update_group_leaf_weight(cfqg);
 	__cfq_group_service_tree_add(st, cfqg);
 
 	/*
@@ -1323,6 +1335,7 @@
 	 */
 	while ((parent = cfqg_parent(pos))) {
 		if (propagate) {
+			cfq_update_group_weight(pos);
 			propagate = !parent->nr_active++;
 			parent->children_weight += pos->weight;
 		}
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 51bf515..9b8eaec 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -279,7 +279,6 @@
 	r = blk_rq_unmap_user(bio);
 	if (!ret)
 		ret = r;
-	blk_put_request(rq);
 
 	return ret;
 }
@@ -297,8 +296,6 @@
 
 	if (hdr->interface_id != 'S')
 		return -EINVAL;
-	if (hdr->cmd_len > BLK_MAX_CDB)
-		return -EINVAL;
 
 	if (hdr->dxfer_len > (queue_max_hw_sectors(q) << 9))
 		return -EIO;
@@ -317,16 +314,23 @@
 	if (hdr->flags & SG_FLAG_Q_AT_HEAD)
 		at_head = 1;
 
+	ret = -ENOMEM;
 	rq = blk_get_request(q, writing ? WRITE : READ, GFP_KERNEL);
 	if (!rq)
-		return -ENOMEM;
+		goto out;
 	blk_rq_set_block_pc(rq);
 
-	if (blk_fill_sghdr_rq(q, rq, hdr, mode)) {
-		blk_put_request(rq);
-		return -EFAULT;
+	if (hdr->cmd_len > BLK_MAX_CDB) {
+		rq->cmd = kzalloc(hdr->cmd_len, GFP_KERNEL);
+		if (!rq->cmd)
+			goto out_put_request;
 	}
 
+	ret = -EFAULT;
+	if (blk_fill_sghdr_rq(q, rq, hdr, mode))
+		goto out_free_cdb;
+
+	ret = 0;
 	if (hdr->iovec_count) {
 		size_t iov_data_len;
 		struct iovec *iov = NULL;
@@ -335,7 +339,7 @@
 					    0, NULL, &iov);
 		if (ret < 0) {
 			kfree(iov);
-			goto out;
+			goto out_free_cdb;
 		}
 
 		iov_data_len = ret;
@@ -358,7 +362,7 @@
 				      GFP_KERNEL);
 
 	if (ret)
-		goto out;
+		goto out_free_cdb;
 
 	bio = rq->bio;
 	memset(sense, 0, sizeof(sense));
@@ -376,9 +380,14 @@
 
 	hdr->duration = jiffies_to_msecs(jiffies - start_time);
 
-	return blk_complete_sghdr_rq(rq, hdr, bio);
-out:
+	ret = blk_complete_sghdr_rq(rq, hdr, bio);
+
+out_free_cdb:
+	if (rq->cmd != rq->__cmd)
+		kfree(rq->cmd);
+out_put_request:
 	blk_put_request(rq);
+out:
 	return ret;
 }
 
@@ -448,6 +457,11 @@
 	}
 
 	rq = blk_get_request(q, in_len ? WRITE : READ, __GFP_WAIT);
+	if (!rq) {
+		err = -ENOMEM;
+		goto error;
+	}
+	blk_rq_set_block_pc(rq);
 
 	cmdlen = COMMAND_SIZE(opcode);
 
@@ -501,7 +515,6 @@
 	memset(sense, 0, sizeof(sense));
 	rq->sense = sense;
 	rq->sense_len = 0;
-	blk_rq_set_block_pc(rq);
 
 	blk_execute_rq(q, disk, rq, 0);
 
@@ -521,7 +534,8 @@
 	
 error:
 	kfree(buffer);
-	blk_put_request(rq);
+	if (rq)
+		blk_put_request(rq);
 	return err;
 }
 EXPORT_SYMBOL_GPL(sg_scsi_ioctl);
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index c7d138e..3598110 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -442,12 +442,15 @@
 int rd_size = CONFIG_BLK_DEV_RAM_SIZE;
 static int max_part;
 static int part_shift;
+static int part_show = 0;
 module_param(rd_nr, int, S_IRUGO);
 MODULE_PARM_DESC(rd_nr, "Maximum number of brd devices");
 module_param(rd_size, int, S_IRUGO);
 MODULE_PARM_DESC(rd_size, "Size of each RAM disk in kbytes.");
 module_param(max_part, int, S_IRUGO);
 MODULE_PARM_DESC(max_part, "Maximum number of partitions per RAM disk");
+module_param(part_show, int, S_IRUGO);
+MODULE_PARM_DESC(part_show, "Control RAM disk visibility in /proc/partitions");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_BLOCKDEV_MAJOR(RAMDISK_MAJOR);
 MODULE_ALIAS("rd");
@@ -501,7 +504,8 @@
 	disk->fops		= &brd_fops;
 	disk->private_data	= brd;
 	disk->queue		= brd->brd_queue;
-	disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO;
+	if (!part_show)
+		disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO;
 	sprintf(disk->disk_name, "ram%d", i);
 	set_capacity(disk, rd_size * 2);
 
diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c
index ab3ea62..c4328d9 100644
--- a/drivers/block/xsysace.c
+++ b/drivers/block/xsysace.c
@@ -1203,7 +1203,6 @@
 	.probe = ace_probe,
 	.remove = ace_remove,
 	.driver = {
-		.owner = THIS_MODULE,
 		.name = "xsysace",
 		.of_match_table = ace_of_match,
 	},
diff --git a/drivers/dma-buf/fence.c b/drivers/dma-buf/fence.c
index 4222cb2..7bb9d65 100644
--- a/drivers/dma-buf/fence.c
+++ b/drivers/dma-buf/fence.c
@@ -29,7 +29,7 @@
 EXPORT_TRACEPOINT_SYMBOL(fence_annotate_wait_on);
 EXPORT_TRACEPOINT_SYMBOL(fence_emit);
 
-/**
+/*
  * fence context counter: each execution context should have its own
  * fence context, this allows checking if fences belong to the same
  * context or not. One device can have multiple separate contexts,
diff --git a/drivers/gpu/drm/ast/ast_tables.h b/drivers/gpu/drm/ast/ast_tables.h
index 4c761dc..05c01ea 100644
--- a/drivers/gpu/drm/ast/ast_tables.h
+++ b/drivers/gpu/drm/ast/ast_tables.h
@@ -99,6 +99,7 @@
 	{0x25, 0x65, 0x80},					/* 16: VCLK88.75    */
 	{0x77, 0x58, 0x80},					/* 17: VCLK119      */
 	{0x32, 0x67, 0x80},				    /* 18: VCLK85_5     */
+	{0x6a, 0x6d, 0x80},					/* 19: VCLK97_75	*/
 };
 
 static struct ast_vbios_stdtable vbios_stdtable[] = {
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index fa2be24..90e7730 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -4696,8 +4696,9 @@
 		return -EINVAL;
 
 	/* overflow checks for 32bit size calculations */
+	/* NOTE: DIV_ROUND_UP() can overflow */
 	cpp = DIV_ROUND_UP(args->bpp, 8);
-	if (cpp > 0xffffffffU / args->width)
+	if (!cpp || cpp > 0xffffffffU / args->width)
 		return -EINVAL;
 	stride = cpp * args->width;
 	if (args->height > 0xffffffffU / stride)
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c
index 74cebb5..c6c80ea2 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c
@@ -397,6 +397,7 @@
 	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
 	DBG("%s", mdp4_crtc->name);
 	/* make sure we hold a ref to mdp clks while setting up mode: */
+	drm_crtc_vblank_get(crtc);
 	mdp4_enable(get_kms(crtc));
 	mdp4_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
 }
@@ -407,6 +408,7 @@
 	crtc_flush(crtc);
 	/* drop the ref to mdp clk's that we got in prepare: */
 	mdp4_disable(get_kms(crtc));
+	drm_crtc_vblank_put(crtc);
 }
 
 static int mdp4_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y,
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index b447c01..26ee80d 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -974,12 +974,11 @@
 
 	for (i = 0; i < ARRAY_SIZE(devnames); i++) {
 		struct device *dev;
-		int ret;
 
 		dev = bus_find_device_by_name(&platform_bus_type,
 				NULL, devnames[i]);
 		if (!dev) {
-			dev_info(master, "still waiting for %s\n", devnames[i]);
+			dev_info(&pdev->dev, "still waiting for %s\n", devnames[i]);
 			return -EPROBE_DEFER;
 		}
 
diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c
index 9c5221c..ab5bfd2 100644
--- a/drivers/gpu/drm/msm/msm_fbdev.c
+++ b/drivers/gpu/drm/msm/msm_fbdev.c
@@ -143,7 +143,7 @@
 	ret = msm_gem_get_iova_locked(fbdev->bo, 0, &paddr);
 	if (ret) {
 		dev_err(dev->dev, "failed to get buffer obj iova: %d\n", ret);
-		goto fail;
+		goto fail_unlock;
 	}
 
 	fbi = framebuffer_alloc(0, dev->dev);
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index 099af48..7acdaa5 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -27,8 +27,8 @@
 static int msm_fault_handler(struct iommu_domain *iommu, struct device *dev,
 		unsigned long iova, int flags, void *arg)
 {
-	DBG("*** fault: iova=%08lx, flags=%d", iova, flags);
-	return -ENOSYS;
+	pr_warn_ratelimited("*** fault: iova=%08lx, flags=%d\n", iova, flags);
+	return 0;
 }
 
 static int msm_iommu_attach(struct msm_mmu *mmu, const char **names, int cnt)
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 79a5a55..fa95659 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -5749,20 +5749,17 @@
 	WREG32(0x15D8, 0);
 	WREG32(0x15DC, 0);
 
-	/* empty context1-15 */
-	/* FIXME start with 4G, once using 2 level pt switch to full
-	 * vm size space
-	 */
+	/* restore context1-15 */
 	/* set vm size, must be a multiple of 4 */
 	WREG32(VM_CONTEXT1_PAGE_TABLE_START_ADDR, 0);
 	WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn);
 	for (i = 1; i < 16; i++) {
 		if (i < 8)
 			WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (i << 2),
-			       rdev->gart.table_addr >> 12);
+			       rdev->vm_manager.saved_table_addr[i]);
 		else
 			WREG32(VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((i - 8) << 2),
-			       rdev->gart.table_addr >> 12);
+			       rdev->vm_manager.saved_table_addr[i]);
 	}
 
 	/* enable context1-15 */
@@ -5827,6 +5824,17 @@
  */
 static void cik_pcie_gart_disable(struct radeon_device *rdev)
 {
+	unsigned i;
+
+	for (i = 1; i < 16; ++i) {
+		uint32_t reg;
+		if (i < 8)
+			reg = VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (i << 2);
+		else
+			reg = VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((i - 8) << 2);
+		rdev->vm_manager.saved_table_addr[i] = RREG32(reg);
+	}
+
 	/* Disable all tables */
 	WREG32(VM_CONTEXT0_CNTL, 0);
 	WREG32(VM_CONTEXT1_CNTL, 0);
@@ -9555,6 +9563,9 @@
 	int ret, i;
 	u16 tmp16;
 
+	if (pci_is_root_bus(rdev->pdev->bus))
+		return;
+
 	if (radeon_pcie_gen2 == 0)
 		return;
 
@@ -9781,7 +9792,8 @@
 			if (orig != data)
 				WREG32_PCIE_PORT(PCIE_LC_LINK_WIDTH_CNTL, data);
 
-			if (!disable_clkreq) {
+			if (!disable_clkreq &&
+			    !pci_is_root_bus(rdev->pdev->bus)) {
 				struct pci_dev *root = rdev->pdev->bus->self;
 				u32 lnkcap;
 
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index ba89375..3faee58 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1271,7 +1271,7 @@
 		WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR + (i << 2), 0);
 		WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR + (i << 2), rdev->vm_manager.max_pfn);
 		WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (i << 2),
-			rdev->gart.table_addr >> 12);
+		       rdev->vm_manager.saved_table_addr[i]);
 	}
 
 	/* enable context1-7 */
@@ -1303,6 +1303,13 @@
 
 static void cayman_pcie_gart_disable(struct radeon_device *rdev)
 {
+	unsigned i;
+
+	for (i = 1; i < 8; ++i) {
+		rdev->vm_manager.saved_table_addr[i] = RREG32(
+			VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (i << 2));
+	}
+
 	/* Disable all tables */
 	WREG32(VM_CONTEXT0_CNTL, 0);
 	WREG32(VM_CONTEXT1_CNTL, 0);
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index e8bf0ea..e616eb5 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -1812,7 +1812,6 @@
 {
 	u32 tiling_config;
 	u32 ramcfg;
-	u32 cc_rb_backend_disable;
 	u32 cc_gc_shader_pipe_config;
 	u32 tmp;
 	int i, j;
@@ -1939,29 +1938,20 @@
 	}
 	tiling_config |= BANK_SWAPS(1);
 
-	cc_rb_backend_disable = RREG32(CC_RB_BACKEND_DISABLE) & 0x00ff0000;
-	tmp = R6XX_MAX_BACKENDS -
-		r600_count_pipe_bits((cc_rb_backend_disable >> 16) & R6XX_MAX_BACKENDS_MASK);
-	if (tmp < rdev->config.r600.max_backends) {
-		rdev->config.r600.max_backends = tmp;
-	}
-
 	cc_gc_shader_pipe_config = RREG32(CC_GC_SHADER_PIPE_CONFIG) & 0x00ffff00;
-	tmp = R6XX_MAX_PIPES -
-		r600_count_pipe_bits((cc_gc_shader_pipe_config >> 8) & R6XX_MAX_PIPES_MASK);
-	if (tmp < rdev->config.r600.max_pipes) {
-		rdev->config.r600.max_pipes = tmp;
-	}
-	tmp = R6XX_MAX_SIMDS -
-		r600_count_pipe_bits((cc_gc_shader_pipe_config >> 16) & R6XX_MAX_SIMDS_MASK);
-	if (tmp < rdev->config.r600.max_simds) {
-		rdev->config.r600.max_simds = tmp;
-	}
 	tmp = rdev->config.r600.max_simds -
 		r600_count_pipe_bits((cc_gc_shader_pipe_config >> 16) & R6XX_MAX_SIMDS_MASK);
 	rdev->config.r600.active_simds = tmp;
 
 	disabled_rb_mask = (RREG32(CC_RB_BACKEND_DISABLE) >> 16) & R6XX_MAX_BACKENDS_MASK;
+	tmp = 0;
+	for (i = 0; i < rdev->config.r600.max_backends; i++)
+		tmp |= (1 << i);
+	/* if all the backends are disabled, fix it up here */
+	if ((disabled_rb_mask & tmp) == tmp) {
+		for (i = 0; i < rdev->config.r600.max_backends; i++)
+			disabled_rb_mask &= ~(1 << i);
+	}
 	tmp = (tiling_config & PIPE_TILING__MASK) >> PIPE_TILING__SHIFT;
 	tmp = r6xx_remap_render_backend(rdev, tmp, rdev->config.r600.max_backends,
 					R6XX_MAX_BACKENDS, disabled_rb_mask);
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index b281886..5f05b4c 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -915,6 +915,8 @@
 	u64				vram_base_offset;
 	/* is vm enabled? */
 	bool				enabled;
+	/* for hw to save the PD addr on suspend/resume */
+	uint32_t			saved_table_addr[RADEON_NUM_VM];
 };
 
 /*
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index 2983f17..d9f5ce7 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -1177,7 +1177,6 @@
 	u32 hdp_host_path_cntl;
 	u32 sq_dyn_gpr_size_simd_ab_0;
 	u32 gb_tiling_config = 0;
-	u32 cc_rb_backend_disable = 0;
 	u32 cc_gc_shader_pipe_config = 0;
 	u32 mc_arb_ramcfg;
 	u32 db_debug4, tmp;
@@ -1311,21 +1310,7 @@
 		WREG32(SPI_CONFIG_CNTL, 0);
 	}
 
-	cc_rb_backend_disable = RREG32(CC_RB_BACKEND_DISABLE) & 0x00ff0000;
-	tmp = R7XX_MAX_BACKENDS - r600_count_pipe_bits(cc_rb_backend_disable >> 16);
-	if (tmp < rdev->config.rv770.max_backends) {
-		rdev->config.rv770.max_backends = tmp;
-	}
-
 	cc_gc_shader_pipe_config = RREG32(CC_GC_SHADER_PIPE_CONFIG) & 0xffffff00;
-	tmp = R7XX_MAX_PIPES - r600_count_pipe_bits((cc_gc_shader_pipe_config >> 8) & R7XX_MAX_PIPES_MASK);
-	if (tmp < rdev->config.rv770.max_pipes) {
-		rdev->config.rv770.max_pipes = tmp;
-	}
-	tmp = R7XX_MAX_SIMDS - r600_count_pipe_bits((cc_gc_shader_pipe_config >> 16) & R7XX_MAX_SIMDS_MASK);
-	if (tmp < rdev->config.rv770.max_simds) {
-		rdev->config.rv770.max_simds = tmp;
-	}
 	tmp = rdev->config.rv770.max_simds -
 		r600_count_pipe_bits((cc_gc_shader_pipe_config >> 16) & R7XX_MAX_SIMDS_MASK);
 	rdev->config.rv770.active_simds = tmp;
@@ -1348,6 +1333,14 @@
 	rdev->config.rv770.tiling_npipes = rdev->config.rv770.max_tile_pipes;
 
 	disabled_rb_mask = (RREG32(CC_RB_BACKEND_DISABLE) >> 16) & R7XX_MAX_BACKENDS_MASK;
+	tmp = 0;
+	for (i = 0; i < rdev->config.rv770.max_backends; i++)
+		tmp |= (1 << i);
+	/* if all the backends are disabled, fix it up here */
+	if ((disabled_rb_mask & tmp) == tmp) {
+		for (i = 0; i < rdev->config.rv770.max_backends; i++)
+			disabled_rb_mask &= ~(1 << i);
+	}
 	tmp = (gb_tiling_config & PIPE_TILING__MASK) >> PIPE_TILING__SHIFT;
 	tmp = r6xx_remap_render_backend(rdev, tmp, rdev->config.rv770.max_backends,
 					R7XX_MAX_BACKENDS, disabled_rb_mask);
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index a1274a3..6bce408 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -4290,10 +4290,10 @@
 	for (i = 1; i < 16; i++) {
 		if (i < 8)
 			WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (i << 2),
-			       rdev->gart.table_addr >> 12);
+			       rdev->vm_manager.saved_table_addr[i]);
 		else
 			WREG32(VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((i - 8) << 2),
-			       rdev->gart.table_addr >> 12);
+			       rdev->vm_manager.saved_table_addr[i]);
 	}
 
 	/* enable context1-15 */
@@ -4325,6 +4325,17 @@
 
 static void si_pcie_gart_disable(struct radeon_device *rdev)
 {
+	unsigned i;
+
+	for (i = 1; i < 16; ++i) {
+		uint32_t reg;
+		if (i < 8)
+			reg = VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (i << 2);
+		else
+			reg = VM_CONTEXT8_PAGE_TABLE_BASE_ADDR + ((i - 8) << 2);
+		rdev->vm_manager.saved_table_addr[i] = RREG32(reg);
+	}
+
 	/* Disable all tables */
 	WREG32(VM_CONTEXT0_CNTL, 0);
 	WREG32(VM_CONTEXT1_CNTL, 0);
@@ -7177,6 +7188,9 @@
 	int ret, i;
 	u16 tmp16;
 
+	if (pci_is_root_bus(rdev->pdev->bus))
+		return;
+
 	if (radeon_pcie_gen2 == 0)
 		return;
 
@@ -7454,7 +7468,8 @@
 			if (orig != data)
 				WREG32_PIF_PHY1(PB1_PIF_CNTL, data);
 
-			if (!disable_clkreq) {
+			if (!disable_clkreq &&
+			    !pci_is_root_bus(rdev->pdev->bus)) {
 				struct pci_dev *root = rdev->pdev->bus->self;
 				u32 lnkcap;
 
diff --git a/drivers/gpu/drm/sti/Kconfig b/drivers/gpu/drm/sti/Kconfig
index 2d9d425..ae8850f 100644
--- a/drivers/gpu/drm/sti/Kconfig
+++ b/drivers/gpu/drm/sti/Kconfig
@@ -1,6 +1,7 @@
 config DRM_STI
 	tristate "DRM Support for STMicroelectronics SoC stiH41x Series"
 	depends on DRM && (SOC_STIH415 || SOC_STIH416 || ARCH_MULTIPLATFORM)
+	select RESET_CONTROLLER
 	select DRM_KMS_HELPER
 	select DRM_GEM_CMA_HELPER
 	select DRM_KMS_CMA_HELPER
diff --git a/drivers/gpu/drm/sti/sti_drm_drv.c b/drivers/gpu/drm/sti/sti_drm_drv.c
index a7cc249..223d93c 100644
--- a/drivers/gpu/drm/sti/sti_drm_drv.c
+++ b/drivers/gpu/drm/sti/sti_drm_drv.c
@@ -201,8 +201,8 @@
 	master = platform_device_register_resndata(dev,
 			DRIVER_NAME "__master", -1,
 			NULL, 0, NULL, 0);
-	if (!master)
-		return -EINVAL;
+	if (IS_ERR(master))
+               return PTR_ERR(master);
 
 	platform_set_drvdata(pdev, master);
 	return 0;
diff --git a/drivers/gpu/drm/sti/sti_hda.c b/drivers/gpu/drm/sti/sti_hda.c
index 72d957f..2ae9a9b 100644
--- a/drivers/gpu/drm/sti/sti_hda.c
+++ b/drivers/gpu/drm/sti/sti_hda.c
@@ -730,16 +730,16 @@
 		return -ENOMEM;
 	}
 	hda->regs = devm_ioremap_nocache(dev, res->start, resource_size(res));
-	if (IS_ERR(hda->regs))
-		return PTR_ERR(hda->regs);
+	if (!hda->regs)
+		return -ENOMEM;
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
 			"video-dacs-ctrl");
 	if (res) {
 		hda->video_dacs_ctrl = devm_ioremap_nocache(dev, res->start,
 				resource_size(res));
-		if (IS_ERR(hda->video_dacs_ctrl))
-			return PTR_ERR(hda->video_dacs_ctrl);
+		if (!hda->video_dacs_ctrl)
+			return -ENOMEM;
 	} else {
 		/* If no existing video-dacs-ctrl resource continue the probe */
 		DRM_DEBUG_DRIVER("No video-dacs-ctrl resource\n");
@@ -770,7 +770,7 @@
 	return 0;
 }
 
-static struct of_device_id hda_of_match[] = {
+static const struct of_device_id hda_of_match[] = {
 	{ .compatible = "st,stih416-hda", },
 	{ .compatible = "st,stih407-hda", },
 	{ /* end node */ }
diff --git a/drivers/gpu/drm/sti/sti_hdmi.c b/drivers/gpu/drm/sti/sti_hdmi.c
index 284e541..ef93156 100644
--- a/drivers/gpu/drm/sti/sti_hdmi.c
+++ b/drivers/gpu/drm/sti/sti_hdmi.c
@@ -677,7 +677,7 @@
 	.unbind = sti_hdmi_unbind,
 };
 
-static struct of_device_id hdmi_of_match[] = {
+static const struct of_device_id hdmi_of_match[] = {
 	{
 		.compatible = "st,stih416-hdmi",
 		.data = &tx3g0c55phy_ops,
@@ -713,8 +713,8 @@
 		return -ENOMEM;
 	}
 	hdmi->regs = devm_ioremap_nocache(dev, res->start, resource_size(res));
-	if (IS_ERR(hdmi->regs))
-		return PTR_ERR(hdmi->regs);
+	if (!hdmi->regs)
+		return -ENOMEM;
 
 	if (of_device_is_compatible(np, "st,stih416-hdmi")) {
 		res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
@@ -725,8 +725,8 @@
 		}
 		hdmi->syscfg = devm_ioremap_nocache(dev, res->start,
 						    resource_size(res));
-		if (IS_ERR(hdmi->syscfg))
-			return PTR_ERR(hdmi->syscfg);
+		if (!hdmi->syscfg)
+			return -ENOMEM;
 
 	}
 
diff --git a/drivers/gpu/drm/sti/sti_tvout.c b/drivers/gpu/drm/sti/sti_tvout.c
index b69e26f..b8afe49 100644
--- a/drivers/gpu/drm/sti/sti_tvout.c
+++ b/drivers/gpu/drm/sti/sti_tvout.c
@@ -591,8 +591,8 @@
 		return -ENOMEM;
 	}
 	tvout->regs = devm_ioremap_nocache(dev, res->start, resource_size(res));
-	if (IS_ERR(tvout->regs))
-		return PTR_ERR(tvout->regs);
+	if (!tvout->regs)
+		return -ENOMEM;
 
 	/* get reset resources */
 	tvout->reset = devm_reset_control_get(dev, "tvout");
@@ -624,7 +624,7 @@
 	return 0;
 }
 
-static struct of_device_id tvout_of_match[] = {
+static const struct of_device_id tvout_of_match[] = {
 	{ .compatible = "st,stih416-tvout", },
 	{ .compatible = "st,stih407-tvout", },
 	{ /* end node */ }
diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c
index b7ba829..9bf8637 100644
--- a/drivers/hid/hid-logitech-dj.c
+++ b/drivers/hid/hid-logitech-dj.c
@@ -656,7 +656,6 @@
 	struct dj_receiver_dev *djrcv_dev = hid_get_drvdata(hdev);
 	struct dj_report *dj_report = (struct dj_report *) data;
 	unsigned long flags;
-	bool report_processed = false;
 
 	dbg_hid("%s, size:%d\n", __func__, size);
 
@@ -683,34 +682,42 @@
 	 * device (via hid_input_report() ) and return 1 so hid-core does not do
 	 * anything else with it.
 	 */
+
+	/* case 1) */
+	if (data[0] != REPORT_ID_DJ_SHORT)
+		return false;
+
 	if ((dj_report->device_index < DJ_DEVICE_INDEX_MIN) ||
 	    (dj_report->device_index > DJ_DEVICE_INDEX_MAX)) {
-		dev_err(&hdev->dev, "%s: invalid device index:%d\n",
+		/*
+		 * Device index is wrong, bail out.
+		 * This driver can ignore safely the receiver notifications,
+		 * so ignore those reports too.
+		 */
+		if (dj_report->device_index != DJ_RECEIVER_INDEX)
+			dev_err(&hdev->dev, "%s: invalid device index:%d\n",
 				__func__, dj_report->device_index);
 		return false;
 	}
 
 	spin_lock_irqsave(&djrcv_dev->lock, flags);
-	if (dj_report->report_id == REPORT_ID_DJ_SHORT) {
-		switch (dj_report->report_type) {
-		case REPORT_TYPE_NOTIF_DEVICE_PAIRED:
-		case REPORT_TYPE_NOTIF_DEVICE_UNPAIRED:
-			logi_dj_recv_queue_notification(djrcv_dev, dj_report);
-			break;
-		case REPORT_TYPE_NOTIF_CONNECTION_STATUS:
-			if (dj_report->report_params[CONNECTION_STATUS_PARAM_STATUS] ==
-			    STATUS_LINKLOSS) {
-				logi_dj_recv_forward_null_report(djrcv_dev, dj_report);
-			}
-			break;
-		default:
-			logi_dj_recv_forward_report(djrcv_dev, dj_report);
+	switch (dj_report->report_type) {
+	case REPORT_TYPE_NOTIF_DEVICE_PAIRED:
+	case REPORT_TYPE_NOTIF_DEVICE_UNPAIRED:
+		logi_dj_recv_queue_notification(djrcv_dev, dj_report);
+		break;
+	case REPORT_TYPE_NOTIF_CONNECTION_STATUS:
+		if (dj_report->report_params[CONNECTION_STATUS_PARAM_STATUS] ==
+		    STATUS_LINKLOSS) {
+			logi_dj_recv_forward_null_report(djrcv_dev, dj_report);
 		}
-		report_processed = true;
+		break;
+	default:
+		logi_dj_recv_forward_report(djrcv_dev, dj_report);
 	}
 	spin_unlock_irqrestore(&djrcv_dev->lock, flags);
 
-	return report_processed;
+	return true;
 }
 
 static int logi_dj_probe(struct hid_device *hdev,
diff --git a/drivers/hid/hid-logitech-dj.h b/drivers/hid/hid-logitech-dj.h
index 4a40003..daeb0aa 100644
--- a/drivers/hid/hid-logitech-dj.h
+++ b/drivers/hid/hid-logitech-dj.h
@@ -27,6 +27,7 @@
 
 #define DJ_MAX_PAIRED_DEVICES			6
 #define DJ_MAX_NUMBER_NOTIFICATIONS		8
+#define DJ_RECEIVER_INDEX			0
 #define DJ_DEVICE_INDEX_MIN 			1
 #define DJ_DEVICE_INDEX_MAX 			6
 
diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c
index ecc2cbf..29a74c1 100644
--- a/drivers/hid/hid-magicmouse.c
+++ b/drivers/hid/hid-magicmouse.c
@@ -290,6 +290,11 @@
 		if (size < 4 || ((size - 4) % 9) != 0)
 			return 0;
 		npoints = (size - 4) / 9;
+		if (npoints > 15) {
+			hid_warn(hdev, "invalid size value (%d) for TRACKPAD_REPORT_ID\n",
+					size);
+			return 0;
+		}
 		msc->ntouches = 0;
 		for (ii = 0; ii < npoints; ii++)
 			magicmouse_emit_touch(msc, ii, data + ii * 9 + 4);
@@ -307,6 +312,11 @@
 		if (size < 6 || ((size - 6) % 8) != 0)
 			return 0;
 		npoints = (size - 6) / 8;
+		if (npoints > 15) {
+			hid_warn(hdev, "invalid size value (%d) for MOUSE_REPORT_ID\n",
+					size);
+			return 0;
+		}
 		msc->ntouches = 0;
 		for (ii = 0; ii < npoints; ii++)
 			magicmouse_emit_touch(msc, ii, data + ii * 8 + 6);
diff --git a/drivers/hid/hid-picolcd_core.c b/drivers/hid/hid-picolcd_core.c
index acbb0210..020df3c 100644
--- a/drivers/hid/hid-picolcd_core.c
+++ b/drivers/hid/hid-picolcd_core.c
@@ -350,6 +350,12 @@
 	if (!data)
 		return 1;
 
+	if (size > 64) {
+		hid_warn(hdev, "invalid size value (%d) for picolcd raw event\n",
+				size);
+		return 0;
+	}
+
 	if (report->id == REPORT_KEY_STATE) {
 		if (data->input_keys)
 			ret = picolcd_raw_keypad(data, report, raw_data+1, size-1);
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 2785007..cd15e08 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1688,6 +1688,7 @@
 	unsigned int key_size, opt_params;
 	unsigned long long tmpll;
 	int ret;
+	size_t iv_size_padding;
 	struct dm_arg_set as;
 	const char *opt_string;
 	char dummy;
@@ -1724,20 +1725,32 @@
 
 	cc->dmreq_start = sizeof(struct ablkcipher_request);
 	cc->dmreq_start += crypto_ablkcipher_reqsize(any_tfm(cc));
-	cc->dmreq_start = ALIGN(cc->dmreq_start, crypto_tfm_ctx_alignment());
-	cc->dmreq_start += crypto_ablkcipher_alignmask(any_tfm(cc)) &
-			   ~(crypto_tfm_ctx_alignment() - 1);
+	cc->dmreq_start = ALIGN(cc->dmreq_start, __alignof__(struct dm_crypt_request));
+
+	if (crypto_ablkcipher_alignmask(any_tfm(cc)) < CRYPTO_MINALIGN) {
+		/* Allocate the padding exactly */
+		iv_size_padding = -(cc->dmreq_start + sizeof(struct dm_crypt_request))
+				& crypto_ablkcipher_alignmask(any_tfm(cc));
+	} else {
+		/*
+		 * If the cipher requires greater alignment than kmalloc
+		 * alignment, we don't know the exact position of the
+		 * initialization vector. We must assume worst case.
+		 */
+		iv_size_padding = crypto_ablkcipher_alignmask(any_tfm(cc));
+	}
 
 	cc->req_pool = mempool_create_kmalloc_pool(MIN_IOS, cc->dmreq_start +
-			sizeof(struct dm_crypt_request) + cc->iv_size);
+			sizeof(struct dm_crypt_request) + iv_size_padding + cc->iv_size);
 	if (!cc->req_pool) {
 		ti->error = "Cannot allocate crypt request mempool";
 		goto bad;
 	}
 
 	cc->per_bio_data_size = ti->per_bio_data_size =
-				sizeof(struct dm_crypt_io) + cc->dmreq_start +
-				sizeof(struct dm_crypt_request) + cc->iv_size;
+		ALIGN(sizeof(struct dm_crypt_io) + cc->dmreq_start +
+		      sizeof(struct dm_crypt_request) + iv_size_padding + cc->iv_size,
+		      ARCH_KMALLOC_MINALIGN);
 
 	cc->page_pool = mempool_create_page_pool(MIN_POOL_PAGES, 0);
 	if (!cc->page_pool) {
diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c
index ce48aa7..bde2fc0 100644
--- a/drivers/mfd/ab8500-core.c
+++ b/drivers/mfd/ab8500-core.c
@@ -1754,7 +1754,7 @@
 	if (ret)
 		return ret;
 
-#if CONFIG_DEBUG_FS
+#ifdef CONFIG_DEBUG_FS
 	/* Pass to debugfs */
 	ab8500_debug_resources[0].start = ab8500->irq;
 	ab8500_debug_resources[0].end = ab8500->irq;
diff --git a/drivers/mfd/htc-i2cpld.c b/drivers/mfd/htc-i2cpld.c
index b44f020..6bdb78c 100644
--- a/drivers/mfd/htc-i2cpld.c
+++ b/drivers/mfd/htc-i2cpld.c
@@ -404,7 +404,7 @@
 	}
 
 	i2c_set_clientdata(client, chip);
-	snprintf(client->name, I2C_NAME_SIZE, "Chip_0x%d", client->addr);
+	snprintf(client->name, I2C_NAME_SIZE, "Chip_0x%x", client->addr);
 	chip->client = client;
 
 	/* Reset the chip */
diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c
index 33a9234..83dab2f 100644
--- a/drivers/mfd/omap-usb-host.c
+++ b/drivers/mfd/omap-usb-host.c
@@ -647,7 +647,7 @@
 		default:
 			omap->nports = OMAP3_HS_USB_PORTS;
 			dev_dbg(dev,
-			 "USB HOST Rev:0x%d not recognized, assuming %d ports\n",
+			 "USB HOST Rev:0x%x not recognized, assuming %d ports\n",
 			 omap->usbhs_rev, omap->nports);
 			break;
 		}
diff --git a/drivers/mfd/twl4030-power.c b/drivers/mfd/twl4030-power.c
index 3bc969a..4d3ff37 100644
--- a/drivers/mfd/twl4030-power.c
+++ b/drivers/mfd/twl4030-power.c
@@ -724,24 +724,24 @@
  * above.
  */
 static struct twl4030_resconfig omap3_idle_rconfig[] = {
-	TWL_REMAP_SLEEP(RES_VAUX1, DEV_GRP_NULL, 0, 0),
-	TWL_REMAP_SLEEP(RES_VAUX2, DEV_GRP_NULL, 0, 0),
-	TWL_REMAP_SLEEP(RES_VAUX3, DEV_GRP_NULL, 0, 0),
-	TWL_REMAP_SLEEP(RES_VAUX4, DEV_GRP_NULL, 0, 0),
-	TWL_REMAP_SLEEP(RES_VMMC1, DEV_GRP_NULL, 0, 0),
-	TWL_REMAP_SLEEP(RES_VMMC2, DEV_GRP_NULL, 0, 0),
+	TWL_REMAP_SLEEP(RES_VAUX1, TWL4030_RESCONFIG_UNDEF, 0, 0),
+	TWL_REMAP_SLEEP(RES_VAUX2, TWL4030_RESCONFIG_UNDEF, 0, 0),
+	TWL_REMAP_SLEEP(RES_VAUX3, TWL4030_RESCONFIG_UNDEF, 0, 0),
+	TWL_REMAP_SLEEP(RES_VAUX4, TWL4030_RESCONFIG_UNDEF, 0, 0),
+	TWL_REMAP_SLEEP(RES_VMMC1, TWL4030_RESCONFIG_UNDEF, 0, 0),
+	TWL_REMAP_SLEEP(RES_VMMC2, TWL4030_RESCONFIG_UNDEF, 0, 0),
 	TWL_REMAP_OFF(RES_VPLL1, DEV_GRP_P1, 3, 1),
 	TWL_REMAP_SLEEP(RES_VPLL2, DEV_GRP_P1, 0, 0),
-	TWL_REMAP_SLEEP(RES_VSIM, DEV_GRP_NULL, 0, 0),
-	TWL_REMAP_SLEEP(RES_VDAC, DEV_GRP_NULL, 0, 0),
+	TWL_REMAP_SLEEP(RES_VSIM, TWL4030_RESCONFIG_UNDEF, 0, 0),
+	TWL_REMAP_SLEEP(RES_VDAC, TWL4030_RESCONFIG_UNDEF, 0, 0),
 	TWL_REMAP_SLEEP(RES_VINTANA1, TWL_DEV_GRP_P123, 1, 2),
 	TWL_REMAP_SLEEP(RES_VINTANA2, TWL_DEV_GRP_P123, 0, 2),
 	TWL_REMAP_SLEEP(RES_VINTDIG, TWL_DEV_GRP_P123, 1, 2),
 	TWL_REMAP_SLEEP(RES_VIO, TWL_DEV_GRP_P123, 2, 2),
 	TWL_REMAP_OFF(RES_VDD1, DEV_GRP_P1, 4, 1),
 	TWL_REMAP_OFF(RES_VDD2, DEV_GRP_P1, 3, 1),
-	TWL_REMAP_SLEEP(RES_VUSB_1V5, DEV_GRP_NULL, 0, 0),
-	TWL_REMAP_SLEEP(RES_VUSB_1V8, DEV_GRP_NULL, 0, 0),
+	TWL_REMAP_SLEEP(RES_VUSB_1V5, TWL4030_RESCONFIG_UNDEF, 0, 0),
+	TWL_REMAP_SLEEP(RES_VUSB_1V8, TWL4030_RESCONFIG_UNDEF, 0, 0),
 	TWL_REMAP_SLEEP(RES_VUSB_3V1, TWL_DEV_GRP_P123, 0, 0),
 	/* Resource #20 USB charge pump skipped */
 	TWL_REMAP_SLEEP(RES_REGEN, TWL_DEV_GRP_P123, 2, 1),
diff --git a/drivers/pinctrl/nomadik/pinctrl-abx500.c b/drivers/pinctrl/nomadik/pinctrl-abx500.c
index a53a689..8c6fd8d 100644
--- a/drivers/pinctrl/nomadik/pinctrl-abx500.c
+++ b/drivers/pinctrl/nomadik/pinctrl-abx500.c
@@ -620,8 +620,7 @@
 	} else
 		seq_printf(s, " %-9s", chip->get(chip, offset) ? "hi" : "lo");
 
-	if (pctldev)
-		mode = abx500_get_mode(pctldev, chip, offset);
+	mode = abx500_get_mode(pctldev, chip, offset);
 
 	seq_printf(s, " %s", (mode < 0) ? "unknown" : modes[mode]);
 
diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c
index af1ba4f..60464a2 100644
--- a/drivers/pinctrl/pinctrl-at91.c
+++ b/drivers/pinctrl/pinctrl-at91.c
@@ -497,10 +497,10 @@
 static void at91_pin_dbg(const struct device *dev, const struct at91_pmx_pin *pin)
 {
 	if (pin->mux) {
-		dev_dbg(dev, "pio%c%d configured as periph%c with conf = 0x%lu\n",
+		dev_dbg(dev, "pio%c%d configured as periph%c with conf = 0x%lx\n",
 			pin->bank + 'A', pin->pin, pin->mux - 1 + 'A', pin->conf);
 	} else {
-		dev_dbg(dev, "pio%c%d configured as gpio with conf = 0x%lu\n",
+		dev_dbg(dev, "pio%c%d configured as gpio with conf = 0x%lx\n",
 			pin->bank + 'A', pin->pin, pin->conf);
 	}
 }
diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c
index 5e8b2e0..0c372a3 100644
--- a/drivers/pinctrl/pinctrl-rockchip.c
+++ b/drivers/pinctrl/pinctrl-rockchip.c
@@ -438,7 +438,7 @@
 	int reg, ret, mask;
 	unsigned long flags;
 	u8 bit;
-	u32 data;
+	u32 data, rmask;
 
 	if (iomux_num > 3)
 		return -EINVAL;
@@ -478,8 +478,9 @@
 	spin_lock_irqsave(&bank->slock, flags);
 
 	data = (mask << (bit + 16));
+	rmask = data | (data >> 16);
 	data |= (mux & mask) << bit;
-	ret = regmap_write(regmap, reg, data);
+	ret = regmap_update_bits(regmap, reg, rmask, data);
 
 	spin_unlock_irqrestore(&bank->slock, flags);
 
@@ -634,7 +635,7 @@
 	struct regmap *regmap;
 	unsigned long flags;
 	int reg, ret, i;
-	u32 data;
+	u32 data, rmask;
 	u8 bit;
 
 	rk3288_calc_drv_reg_and_bit(bank, pin_num, &regmap, &reg, &bit);
@@ -657,9 +658,10 @@
 
 	/* enable the write to the equivalent lower bits */
 	data = ((1 << RK3288_DRV_BITS_PER_PIN) - 1) << (bit + 16);
+	rmask = data | (data >> 16);
 	data |= (ret << bit);
 
-	ret = regmap_write(regmap, reg, data);
+	ret = regmap_update_bits(regmap, reg, rmask, data);
 	spin_unlock_irqrestore(&bank->slock, flags);
 
 	return ret;
@@ -722,7 +724,7 @@
 	int reg, ret;
 	unsigned long flags;
 	u8 bit;
-	u32 data;
+	u32 data, rmask;
 
 	dev_dbg(info->dev, "setting pull of GPIO%d-%d to %d\n",
 		 bank->bank_num, pin_num, pull);
@@ -750,6 +752,7 @@
 
 		/* enable the write to the equivalent lower bits */
 		data = ((1 << RK3188_PULL_BITS_PER_PIN) - 1) << (bit + 16);
+		rmask = data | (data >> 16);
 
 		switch (pull) {
 		case PIN_CONFIG_BIAS_DISABLE:
@@ -770,7 +773,7 @@
 			return -EINVAL;
 		}
 
-		ret = regmap_write(regmap, reg, data);
+		ret = regmap_update_bits(regmap, reg, rmask, data);
 
 		spin_unlock_irqrestore(&bank->slock, flags);
 		break;
diff --git a/drivers/pinctrl/pinctrl-tegra-xusb.c b/drivers/pinctrl/pinctrl-tegra-xusb.c
index a066204..e641b42 100644
--- a/drivers/pinctrl/pinctrl-tegra-xusb.c
+++ b/drivers/pinctrl/pinctrl-tegra-xusb.c
@@ -680,7 +680,7 @@
 	if (args->args_count <= 0)
 		return ERR_PTR(-EINVAL);
 
-	if (index > ARRAY_SIZE(padctl->phys))
+	if (index >= ARRAY_SIZE(padctl->phys))
 		return ERR_PTR(-EINVAL);
 
 	return padctl->phys[index];
@@ -930,7 +930,8 @@
 
 	padctl->provider = devm_of_phy_provider_register(&pdev->dev,
 							 tegra_xusb_padctl_xlate);
-	if (err < 0) {
+	if (IS_ERR(padctl->provider)) {
+		err = PTR_ERR(padctl->provider);
 		dev_err(&pdev->dev, "failed to register PHYs: %d\n", err);
 		goto unregister;
 	}
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c
index 003bfd8..d7154ed 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.c
@@ -127,14 +127,10 @@
 	struct irq_chip *chip = irq_data_get_irq_chip(irqd);
 	struct exynos_irq_chip *our_chip = to_exynos_irq_chip(chip);
 	struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd);
-	struct samsung_pin_bank_type *bank_type = bank->type;
 	struct samsung_pinctrl_drv_data *d = bank->drvdata;
-	unsigned int pin = irqd->hwirq;
-	unsigned int shift = EXYNOS_EINT_CON_LEN * pin;
+	unsigned int shift = EXYNOS_EINT_CON_LEN * irqd->hwirq;
 	unsigned int con, trig_type;
 	unsigned long reg_con = our_chip->eint_con + bank->eint_offset;
-	unsigned long flags;
-	unsigned int mask;
 
 	switch (type) {
 	case IRQ_TYPE_EDGE_RISING:
@@ -167,8 +163,32 @@
 	con |= trig_type << shift;
 	writel(con, d->virt_base + reg_con);
 
+	return 0;
+}
+
+static int exynos_irq_request_resources(struct irq_data *irqd)
+{
+	struct irq_chip *chip = irq_data_get_irq_chip(irqd);
+	struct exynos_irq_chip *our_chip = to_exynos_irq_chip(chip);
+	struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd);
+	struct samsung_pin_bank_type *bank_type = bank->type;
+	struct samsung_pinctrl_drv_data *d = bank->drvdata;
+	unsigned int shift = EXYNOS_EINT_CON_LEN * irqd->hwirq;
+	unsigned long reg_con = our_chip->eint_con + bank->eint_offset;
+	unsigned long flags;
+	unsigned int mask;
+	unsigned int con;
+	int ret;
+
+	ret = gpio_lock_as_irq(&bank->gpio_chip, irqd->hwirq);
+	if (ret) {
+		dev_err(bank->gpio_chip.dev, "unable to lock pin %s-%lu IRQ\n",
+			bank->name, irqd->hwirq);
+		return ret;
+	}
+
 	reg_con = bank->pctl_offset + bank_type->reg_offset[PINCFG_TYPE_FUNC];
-	shift = pin * bank_type->fld_width[PINCFG_TYPE_FUNC];
+	shift = irqd->hwirq * bank_type->fld_width[PINCFG_TYPE_FUNC];
 	mask = (1 << bank_type->fld_width[PINCFG_TYPE_FUNC]) - 1;
 
 	spin_lock_irqsave(&bank->slock, flags);
@@ -180,9 +200,42 @@
 
 	spin_unlock_irqrestore(&bank->slock, flags);
 
+	exynos_irq_unmask(irqd);
+
 	return 0;
 }
 
+static void exynos_irq_release_resources(struct irq_data *irqd)
+{
+	struct irq_chip *chip = irq_data_get_irq_chip(irqd);
+	struct exynos_irq_chip *our_chip = to_exynos_irq_chip(chip);
+	struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd);
+	struct samsung_pin_bank_type *bank_type = bank->type;
+	struct samsung_pinctrl_drv_data *d = bank->drvdata;
+	unsigned int shift = EXYNOS_EINT_CON_LEN * irqd->hwirq;
+	unsigned long reg_con = our_chip->eint_con + bank->eint_offset;
+	unsigned long flags;
+	unsigned int mask;
+	unsigned int con;
+
+	reg_con = bank->pctl_offset + bank_type->reg_offset[PINCFG_TYPE_FUNC];
+	shift = irqd->hwirq * bank_type->fld_width[PINCFG_TYPE_FUNC];
+	mask = (1 << bank_type->fld_width[PINCFG_TYPE_FUNC]) - 1;
+
+	exynos_irq_mask(irqd);
+
+	spin_lock_irqsave(&bank->slock, flags);
+
+	con = readl(d->virt_base + reg_con);
+	con &= ~(mask << shift);
+	con |= FUNC_INPUT << shift;
+	writel(con, d->virt_base + reg_con);
+
+	spin_unlock_irqrestore(&bank->slock, flags);
+
+	gpio_unlock_as_irq(&bank->gpio_chip, irqd->hwirq);
+}
+
 /*
  * irq_chip for gpio interrupts.
  */
@@ -193,6 +246,8 @@
 		.irq_mask = exynos_irq_mask,
 		.irq_ack = exynos_irq_ack,
 		.irq_set_type = exynos_irq_set_type,
+		.irq_request_resources = exynos_irq_request_resources,
+		.irq_release_resources = exynos_irq_release_resources,
 	},
 	.eint_con = EXYNOS_GPIO_ECON_OFFSET,
 	.eint_mask = EXYNOS_GPIO_EMASK_OFFSET,
@@ -336,6 +391,8 @@
 		.irq_ack = exynos_irq_ack,
 		.irq_set_type = exynos_irq_set_type,
 		.irq_set_wake = exynos_wkup_irq_set_wake,
+		.irq_request_resources = exynos_irq_request_resources,
+		.irq_release_resources = exynos_irq_release_resources,
 	},
 	.eint_con = EXYNOS_WKUP_ECON_OFFSET,
 	.eint_mask = EXYNOS_WKUP_EMASK_OFFSET,
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.h b/drivers/pinctrl/samsung/pinctrl-samsung.h
index 2b88232..5cedc9d 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.h
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.h
@@ -26,6 +26,7 @@
 #include <linux/gpio.h>
 
 /* pinmux function number for pin as gpio output line */
+#define FUNC_INPUT	0x0
 #define FUNC_OUTPUT	0x1
 
 /**
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
index 576d41b..c6e5deb 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
@@ -4509,24 +4509,24 @@
 };
 
 static const char * const can0_groups[] = {
-	"can0_data_a",
+	"can0_data",
 	"can0_data_b",
 	"can0_data_c",
 	"can0_data_d",
 	"can0_data_e",
 	"can0_data_f",
-	"can_clk_a",
+	"can_clk",
 	"can_clk_b",
 	"can_clk_c",
 	"can_clk_d",
 };
 
 static const char * const can1_groups[] = {
-	"can1_data_a",
+	"can1_data",
 	"can1_data_b",
 	"can1_data_c",
 	"can1_data_d",
-	"can_clk_a",
+	"can_clk",
 	"can_clk_b",
 	"can_clk_c",
 	"can_clk_d",
diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c
index a6d47e5..c43aca6 100644
--- a/drivers/s390/char/con3215.c
+++ b/drivers/s390/char/con3215.c
@@ -1035,12 +1035,26 @@
 			 const unsigned char *buf, int count)
 {
 	struct raw3215_info *raw;
+	int i, written;
 
 	if (!tty)
 		return 0;
 	raw = (struct raw3215_info *) tty->driver_data;
-	raw3215_write(raw, buf, count);
-	return count;
+	written = count;
+	while (count > 0) {
+		for (i = 0; i < count; i++)
+			if (buf[i] == '\t' || buf[i] == '\n')
+				break;
+		raw3215_write(raw, buf, i);
+		count -= i;
+		buf += i;
+		if (count > 0) {
+			raw3215_putchar(raw, *buf);
+			count--;
+			buf++;
+		}
+	}
+	return written;
 }
 
 /*
@@ -1188,7 +1202,7 @@
 	driver->subtype = SYSTEM_TYPE_TTY;
 	driver->init_termios = tty_std_termios;
 	driver->init_termios.c_iflag = IGNBRK | IGNPAR;
-	driver->init_termios.c_oflag = ONLCR | XTABS;
+	driver->init_termios.c_oflag = ONLCR;
 	driver->init_termios.c_lflag = ISIG;
 	driver->flags = TTY_DRIVER_REAL_RAW;
 	tty_set_operations(driver, &tty3215_ops);
diff --git a/drivers/s390/char/sclp_tty.c b/drivers/s390/char/sclp_tty.c
index 7ed7a59..0036632 100644
--- a/drivers/s390/char/sclp_tty.c
+++ b/drivers/s390/char/sclp_tty.c
@@ -559,7 +559,7 @@
 	driver->subtype = SYSTEM_TYPE_TTY;
 	driver->init_termios = tty_std_termios;
 	driver->init_termios.c_iflag = IGNBRK | IGNPAR;
-	driver->init_termios.c_oflag = ONLCR | XTABS;
+	driver->init_termios.c_oflag = ONLCR;
 	driver->init_termios.c_lflag = ISIG | ECHO;
 	driver->flags = TTY_DRIVER_REAL_RAW;
 	tty_set_operations(driver, &sclp_ops);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index ce62e87..d837dc1 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1808,7 +1808,6 @@
 
 	cmd->tag = req->tag;
 
-	req->cmd = req->__cmd;
 	cmd->cmnd = req->cmd;
 	cmd->prot_op = SCSI_PROT_NORMAL;
 
diff --git a/drivers/video/backlight/pwm_bl.c b/drivers/video/backlight/pwm_bl.c
index d7a3d13..b85983e 100644
--- a/drivers/video/backlight/pwm_bl.c
+++ b/drivers/video/backlight/pwm_bl.c
@@ -173,6 +173,7 @@
 		data->max_brightness--;
 	}
 
+	data->enable_gpio = -EINVAL;
 	return 0;
 }
 
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 5a201d8..fbd76de 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -22,7 +22,6 @@
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/freezer.h>
-#include <linux/workqueue.h>
 #include "async-thread.h"
 #include "ctree.h"
 
@@ -55,8 +54,39 @@
 	struct __btrfs_workqueue *high;
 };
 
-static inline struct __btrfs_workqueue
-*__btrfs_alloc_workqueue(const char *name, int flags, int max_active,
+static void normal_work_helper(struct btrfs_work *work);
+
+#define BTRFS_WORK_HELPER(name)					\
+void btrfs_##name(struct work_struct *arg)				\
+{									\
+	struct btrfs_work *work = container_of(arg, struct btrfs_work,	\
+					       normal_work);		\
+	normal_work_helper(work);					\
+}
+
+BTRFS_WORK_HELPER(worker_helper);
+BTRFS_WORK_HELPER(delalloc_helper);
+BTRFS_WORK_HELPER(flush_delalloc_helper);
+BTRFS_WORK_HELPER(cache_helper);
+BTRFS_WORK_HELPER(submit_helper);
+BTRFS_WORK_HELPER(fixup_helper);
+BTRFS_WORK_HELPER(endio_helper);
+BTRFS_WORK_HELPER(endio_meta_helper);
+BTRFS_WORK_HELPER(endio_meta_write_helper);
+BTRFS_WORK_HELPER(endio_raid56_helper);
+BTRFS_WORK_HELPER(rmw_helper);
+BTRFS_WORK_HELPER(endio_write_helper);
+BTRFS_WORK_HELPER(freespace_write_helper);
+BTRFS_WORK_HELPER(delayed_meta_helper);
+BTRFS_WORK_HELPER(readahead_helper);
+BTRFS_WORK_HELPER(qgroup_rescan_helper);
+BTRFS_WORK_HELPER(extent_refs_helper);
+BTRFS_WORK_HELPER(scrub_helper);
+BTRFS_WORK_HELPER(scrubwrc_helper);
+BTRFS_WORK_HELPER(scrubnc_helper);
+
+static struct __btrfs_workqueue *
+__btrfs_alloc_workqueue(const char *name, int flags, int max_active,
 			 int thresh)
 {
 	struct __btrfs_workqueue *ret = kzalloc(sizeof(*ret), GFP_NOFS);
@@ -232,13 +262,11 @@
 	spin_unlock_irqrestore(lock, flags);
 }
 
-static void normal_work_helper(struct work_struct *arg)
+static void normal_work_helper(struct btrfs_work *work)
 {
-	struct btrfs_work *work;
 	struct __btrfs_workqueue *wq;
 	int need_order = 0;
 
-	work = container_of(arg, struct btrfs_work, normal_work);
 	/*
 	 * We should not touch things inside work in the following cases:
 	 * 1) after work->func() if it has no ordered_free
@@ -262,7 +290,7 @@
 		trace_btrfs_all_work_done(work);
 }
 
-void btrfs_init_work(struct btrfs_work *work,
+void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t uniq_func,
 		     btrfs_func_t func,
 		     btrfs_func_t ordered_func,
 		     btrfs_func_t ordered_free)
@@ -270,7 +298,7 @@
 	work->func = func;
 	work->ordered_func = ordered_func;
 	work->ordered_free = ordered_free;
-	INIT_WORK(&work->normal_work, normal_work_helper);
+	INIT_WORK(&work->normal_work, uniq_func);
 	INIT_LIST_HEAD(&work->ordered_list);
 	work->flags = 0;
 }
diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
index 9c6b66d1..e9e31c9 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -19,12 +19,14 @@
 
 #ifndef __BTRFS_ASYNC_THREAD_
 #define __BTRFS_ASYNC_THREAD_
+#include <linux/workqueue.h>
 
 struct btrfs_workqueue;
 /* Internal use only */
 struct __btrfs_workqueue;
 struct btrfs_work;
 typedef void (*btrfs_func_t)(struct btrfs_work *arg);
+typedef void (*btrfs_work_func_t)(struct work_struct *arg);
 
 struct btrfs_work {
 	btrfs_func_t func;
@@ -38,11 +40,35 @@
 	unsigned long flags;
 };
 
+#define BTRFS_WORK_HELPER_PROTO(name)					\
+void btrfs_##name(struct work_struct *arg)
+
+BTRFS_WORK_HELPER_PROTO(worker_helper);
+BTRFS_WORK_HELPER_PROTO(delalloc_helper);
+BTRFS_WORK_HELPER_PROTO(flush_delalloc_helper);
+BTRFS_WORK_HELPER_PROTO(cache_helper);
+BTRFS_WORK_HELPER_PROTO(submit_helper);
+BTRFS_WORK_HELPER_PROTO(fixup_helper);
+BTRFS_WORK_HELPER_PROTO(endio_helper);
+BTRFS_WORK_HELPER_PROTO(endio_meta_helper);
+BTRFS_WORK_HELPER_PROTO(endio_meta_write_helper);
+BTRFS_WORK_HELPER_PROTO(endio_raid56_helper);
+BTRFS_WORK_HELPER_PROTO(rmw_helper);
+BTRFS_WORK_HELPER_PROTO(endio_write_helper);
+BTRFS_WORK_HELPER_PROTO(freespace_write_helper);
+BTRFS_WORK_HELPER_PROTO(delayed_meta_helper);
+BTRFS_WORK_HELPER_PROTO(readahead_helper);
+BTRFS_WORK_HELPER_PROTO(qgroup_rescan_helper);
+BTRFS_WORK_HELPER_PROTO(extent_refs_helper);
+BTRFS_WORK_HELPER_PROTO(scrub_helper);
+BTRFS_WORK_HELPER_PROTO(scrubwrc_helper);
+BTRFS_WORK_HELPER_PROTO(scrubnc_helper);
+
 struct btrfs_workqueue *btrfs_alloc_workqueue(const char *name,
 					      int flags,
 					      int max_active,
 					      int thresh);
-void btrfs_init_work(struct btrfs_work *work,
+void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t helper,
 		     btrfs_func_t func,
 		     btrfs_func_t ordered_func,
 		     btrfs_func_t ordered_free);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index da775bf..a2e90f8 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1395,8 +1395,8 @@
 		return -ENOMEM;
 
 	async_work->delayed_root = delayed_root;
-	btrfs_init_work(&async_work->work, btrfs_async_run_delayed_root,
-			NULL, NULL);
+	btrfs_init_work(&async_work->work, btrfs_delayed_meta_helper,
+			btrfs_async_run_delayed_root, NULL, NULL);
 	async_work->nr = nr;
 
 	btrfs_queue_work(root->fs_info->delayed_workers, &async_work->work);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index d0ed9e6..a1d36e6 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -39,7 +39,6 @@
 #include "btrfs_inode.h"
 #include "volumes.h"
 #include "print-tree.h"
-#include "async-thread.h"
 #include "locking.h"
 #include "tree-log.h"
 #include "free-space-cache.h"
@@ -693,35 +692,41 @@
 {
 	struct end_io_wq *end_io_wq = bio->bi_private;
 	struct btrfs_fs_info *fs_info;
+	struct btrfs_workqueue *wq;
+	btrfs_work_func_t func;
 
 	fs_info = end_io_wq->info;
 	end_io_wq->error = err;
-	btrfs_init_work(&end_io_wq->work, end_workqueue_fn, NULL, NULL);
 
 	if (bio->bi_rw & REQ_WRITE) {
-		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA)
-			btrfs_queue_work(fs_info->endio_meta_write_workers,
-					 &end_io_wq->work);
-		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE)
-			btrfs_queue_work(fs_info->endio_freespace_worker,
-					 &end_io_wq->work);
-		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
-			btrfs_queue_work(fs_info->endio_raid56_workers,
-					 &end_io_wq->work);
-		else
-			btrfs_queue_work(fs_info->endio_write_workers,
-					 &end_io_wq->work);
+		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) {
+			wq = fs_info->endio_meta_write_workers;
+			func = btrfs_endio_meta_write_helper;
+		} else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE) {
+			wq = fs_info->endio_freespace_worker;
+			func = btrfs_freespace_write_helper;
+		} else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
+			wq = fs_info->endio_raid56_workers;
+			func = btrfs_endio_raid56_helper;
+		} else {
+			wq = fs_info->endio_write_workers;
+			func = btrfs_endio_write_helper;
+		}
 	} else {
-		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
-			btrfs_queue_work(fs_info->endio_raid56_workers,
-					 &end_io_wq->work);
-		else if (end_io_wq->metadata)
-			btrfs_queue_work(fs_info->endio_meta_workers,
-					 &end_io_wq->work);
-		else
-			btrfs_queue_work(fs_info->endio_workers,
-					 &end_io_wq->work);
+		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
+			wq = fs_info->endio_raid56_workers;
+			func = btrfs_endio_raid56_helper;
+		} else if (end_io_wq->metadata) {
+			wq = fs_info->endio_meta_workers;
+			func = btrfs_endio_meta_helper;
+		} else {
+			wq = fs_info->endio_workers;
+			func = btrfs_endio_helper;
+		}
 	}
+
+	btrfs_init_work(&end_io_wq->work, func, end_workqueue_fn, NULL, NULL);
+	btrfs_queue_work(wq, &end_io_wq->work);
 }
 
 /*
@@ -828,7 +833,7 @@
 	async->submit_bio_start = submit_bio_start;
 	async->submit_bio_done = submit_bio_done;
 
-	btrfs_init_work(&async->work, run_one_async_start,
+	btrfs_init_work(&async->work, btrfs_worker_helper, run_one_async_start,
 			run_one_async_done, run_one_async_free);
 
 	async->bio_flags = bio_flags;
@@ -3450,7 +3455,8 @@
 		btrfs_set_stack_device_generation(dev_item, 0);
 		btrfs_set_stack_device_type(dev_item, dev->type);
 		btrfs_set_stack_device_id(dev_item, dev->devid);
-		btrfs_set_stack_device_total_bytes(dev_item, dev->total_bytes);
+		btrfs_set_stack_device_total_bytes(dev_item,
+						   dev->disk_total_bytes);
 		btrfs_set_stack_device_bytes_used(dev_item, dev->bytes_used);
 		btrfs_set_stack_device_io_align(dev_item, dev->io_align);
 		btrfs_set_stack_device_io_width(dev_item, dev->io_width);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 102ed31..3efe1c3 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -552,7 +552,8 @@
 	caching_ctl->block_group = cache;
 	caching_ctl->progress = cache->key.objectid;
 	atomic_set(&caching_ctl->count, 1);
-	btrfs_init_work(&caching_ctl->work, caching_thread, NULL, NULL);
+	btrfs_init_work(&caching_ctl->work, btrfs_cache_helper,
+			caching_thread, NULL, NULL);
 
 	spin_lock(&cache->lock);
 	/*
@@ -2749,8 +2750,8 @@
 		async->sync = 0;
 	init_completion(&async->wait);
 
-	btrfs_init_work(&async->work, delayed_ref_async_start,
-			NULL, NULL);
+	btrfs_init_work(&async->work, btrfs_extent_refs_helper,
+			delayed_ref_async_start, NULL, NULL);
 
 	btrfs_queue_work(root->fs_info->extent_workers, &async->work);
 
@@ -3586,13 +3587,7 @@
  */
 static u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags)
 {
-	/*
-	 * we add in the count of missing devices because we want
-	 * to make sure that any RAID levels on a degraded FS
-	 * continue to be honored.
-	 */
-	u64 num_devices = root->fs_info->fs_devices->rw_devices +
-		root->fs_info->fs_devices->missing_devices;
+	u64 num_devices = root->fs_info->fs_devices->rw_devices;
 	u64 target;
 	u64 tmp;
 
@@ -8440,13 +8435,7 @@
 	if (stripped)
 		return extended_to_chunk(stripped);
 
-	/*
-	 * we add in the count of missing devices because we want
-	 * to make sure that any RAID levels on a degraded FS
-	 * continue to be honored.
-	 */
-	num_devices = root->fs_info->fs_devices->rw_devices +
-		root->fs_info->fs_devices->missing_devices;
+	num_devices = root->fs_info->fs_devices->rw_devices;
 
 	stripped = BTRFS_BLOCK_GROUP_RAID0 |
 		BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6 |
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 3e11aab..af0359d 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2532,6 +2532,7 @@
 					test_bit(BIO_UPTODATE, &bio->bi_flags);
 				if (err)
 					uptodate = 0;
+				offset += len;
 				continue;
 			}
 		}
@@ -4207,8 +4208,8 @@
 		return -ENOMEM;
 	path->leave_spinning = 1;
 
-	start = ALIGN(start, BTRFS_I(inode)->root->sectorsize);
-	len = ALIGN(len, BTRFS_I(inode)->root->sectorsize);
+	start = round_down(start, BTRFS_I(inode)->root->sectorsize);
+	len = round_up(max, BTRFS_I(inode)->root->sectorsize) - start;
 
 	/*
 	 * lookup the last file extent.  We're not using i_size here
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index d3afac2..36861b7 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1840,7 +1840,15 @@
 {
 	if (filp->private_data)
 		btrfs_ioctl_trans_end(filp);
-	filemap_flush(inode->i_mapping);
+	/*
+	 * ordered_data_close is set by settattr when we are about to truncate
+	 * a file from a non-zero size to a zero size.  This tries to
+	 * flush down new bytes that may have been written if the
+	 * application were using truncate to replace a file in place.
+	 */
+	if (test_and_clear_bit(BTRFS_INODE_ORDERED_DATA_CLOSE,
+			       &BTRFS_I(inode)->runtime_flags))
+			filemap_flush(inode->i_mapping);
 	return 0;
 }
 
@@ -2088,10 +2096,9 @@
 		goto out;
 	}
 
-	if (hole_mergeable(inode, leaf, path->slots[0]+1, offset, end)) {
+	if (hole_mergeable(inode, leaf, path->slots[0], offset, end)) {
 		u64 num_bytes;
 
-		path->slots[0]++;
 		key.offset = offset;
 		btrfs_set_item_key_safe(root, path, &key);
 		fi = btrfs_item_ptr(leaf, path->slots[0],
@@ -2216,7 +2223,7 @@
 		goto out_only_mutex;
 	}
 
-	lockstart = round_up(offset , BTRFS_I(inode)->root->sectorsize);
+	lockstart = round_up(offset, BTRFS_I(inode)->root->sectorsize);
 	lockend = round_down(offset + len,
 			     BTRFS_I(inode)->root->sectorsize) - 1;
 	same_page = ((offset >> PAGE_CACHE_SHIFT) ==
@@ -2277,7 +2284,7 @@
 						tail_start + tail_len, 0, 1);
 				if (ret)
 					goto out_only_mutex;
-				}
+			}
 		}
 	}
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 03708ef..9c194bd 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1096,8 +1096,10 @@
 		async_cow->end = cur_end;
 		INIT_LIST_HEAD(&async_cow->extents);
 
-		btrfs_init_work(&async_cow->work, async_cow_start,
-				async_cow_submit, async_cow_free);
+		btrfs_init_work(&async_cow->work,
+				btrfs_delalloc_helper,
+				async_cow_start, async_cow_submit,
+				async_cow_free);
 
 		nr_pages = (cur_end - start + PAGE_CACHE_SIZE) >>
 			PAGE_CACHE_SHIFT;
@@ -1881,7 +1883,8 @@
 
 	SetPageChecked(page);
 	page_cache_get(page);
-	btrfs_init_work(&fixup->work, btrfs_writepage_fixup_worker, NULL, NULL);
+	btrfs_init_work(&fixup->work, btrfs_fixup_helper,
+			btrfs_writepage_fixup_worker, NULL, NULL);
 	fixup->page = page;
 	btrfs_queue_work(root->fs_info->fixup_workers, &fixup->work);
 	return -EBUSY;
@@ -2822,7 +2825,8 @@
 	struct inode *inode = page->mapping->host;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_ordered_extent *ordered_extent = NULL;
-	struct btrfs_workqueue *workers;
+	struct btrfs_workqueue *wq;
+	btrfs_work_func_t func;
 
 	trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);
 
@@ -2831,13 +2835,17 @@
 					    end - start + 1, uptodate))
 		return 0;
 
-	btrfs_init_work(&ordered_extent->work, finish_ordered_fn, NULL, NULL);
+	if (btrfs_is_free_space_inode(inode)) {
+		wq = root->fs_info->endio_freespace_worker;
+		func = btrfs_freespace_write_helper;
+	} else {
+		wq = root->fs_info->endio_write_workers;
+		func = btrfs_endio_write_helper;
+	}
 
-	if (btrfs_is_free_space_inode(inode))
-		workers = root->fs_info->endio_freespace_worker;
-	else
-		workers = root->fs_info->endio_write_workers;
-	btrfs_queue_work(workers, &ordered_extent->work);
+	btrfs_init_work(&ordered_extent->work, func, finish_ordered_fn, NULL,
+			NULL);
+	btrfs_queue_work(wq, &ordered_extent->work);
 
 	return 0;
 }
@@ -4674,6 +4682,11 @@
 		clear_bit(EXTENT_FLAG_LOGGING, &em->flags);
 		remove_extent_mapping(map_tree, em);
 		free_extent_map(em);
+		if (need_resched()) {
+			write_unlock(&map_tree->lock);
+			cond_resched();
+			write_lock(&map_tree->lock);
+		}
 	}
 	write_unlock(&map_tree->lock);
 
@@ -4696,6 +4709,7 @@
 				 &cached_state, GFP_NOFS);
 		free_extent_state(state);
 
+		cond_resched();
 		spin_lock(&io_tree->lock);
 	}
 	spin_unlock(&io_tree->lock);
@@ -5181,6 +5195,42 @@
 			iput(inode);
 			inode = ERR_PTR(ret);
 		}
+		/*
+		 * If orphan cleanup did remove any orphans, it means the tree
+		 * was modified and therefore the commit root is not the same as
+		 * the current root anymore. This is a problem, because send
+		 * uses the commit root and therefore can see inode items that
+		 * don't exist in the current root anymore, and for example make
+		 * calls to btrfs_iget, which will do tree lookups based on the
+		 * current root and not on the commit root. Those lookups will
+		 * fail, returning a -ESTALE error, and making send fail with
+		 * that error. So make sure a send does not see any orphans we
+		 * have just removed, and that it will see the same inodes
+		 * regardless of whether a transaction commit happened before
+		 * it started (meaning that the commit root will be the same as
+		 * the current root) or not.
+		 */
+		if (sub_root->node != sub_root->commit_root) {
+			u64 sub_flags = btrfs_root_flags(&sub_root->root_item);
+
+			if (sub_flags & BTRFS_ROOT_SUBVOL_RDONLY) {
+				struct extent_buffer *eb;
+
+				/*
+				 * Assert we can't have races between dentry
+				 * lookup called through the snapshot creation
+				 * ioctl and the VFS.
+				 */
+				ASSERT(mutex_is_locked(&dir->i_mutex));
+
+				down_write(&root->fs_info->commit_root_sem);
+				eb = sub_root->commit_root;
+				sub_root->commit_root =
+					btrfs_root_node(sub_root);
+				up_write(&root->fs_info->commit_root_sem);
+				free_extent_buffer(eb);
+			}
+		}
 	}
 
 	return inode;
@@ -5606,6 +5656,13 @@
 	}
 
 	/*
+	 * O_TMPFILE, set link count to 0, so that after this point,
+	 * we fill in an inode item with the correct link count.
+	 */
+	if (!name)
+		set_nlink(inode, 0);
+
+	/*
 	 * we have to initialize this early, so we can reclaim the inode
 	 * number if we fail afterwards in this function.
 	 */
@@ -6097,14 +6154,14 @@
 static int merge_extent_mapping(struct extent_map_tree *em_tree,
 				struct extent_map *existing,
 				struct extent_map *em,
-				u64 map_start, u64 map_len)
+				u64 map_start)
 {
 	u64 start_diff;
 
 	BUG_ON(map_start < em->start || map_start >= extent_map_end(em));
 	start_diff = map_start - em->start;
 	em->start = map_start;
-	em->len = map_len;
+	em->len = existing->start - em->start;
 	if (em->block_start < EXTENT_MAP_LAST_BYTE &&
 	    !test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
 		em->block_start += start_diff;
@@ -6275,6 +6332,8 @@
 			goto not_found;
 		if (start + len <= found_key.offset)
 			goto not_found;
+		if (start > found_key.offset)
+			goto next;
 		em->start = start;
 		em->orig_start = start;
 		em->len = found_key.offset - start;
@@ -6390,8 +6449,7 @@
 							 em->len);
 			if (existing) {
 				err = merge_extent_mapping(em_tree, existing,
-							   em, start,
-							   root->sectorsize);
+							   em, start);
 				free_extent_map(existing);
 				if (err) {
 					free_extent_map(em);
@@ -7158,7 +7216,8 @@
 	if (!ret)
 		goto out_test;
 
-	btrfs_init_work(&ordered->work, finish_ordered_fn, NULL, NULL);
+	btrfs_init_work(&ordered->work, btrfs_endio_write_helper,
+			finish_ordered_fn, NULL, NULL);
 	btrfs_queue_work(root->fs_info->endio_write_workers,
 			 &ordered->work);
 out_test:
@@ -7306,10 +7365,8 @@
 	map_length = orig_bio->bi_iter.bi_size;
 	ret = btrfs_map_block(root->fs_info, rw, start_sector << 9,
 			      &map_length, NULL, 0);
-	if (ret) {
-		bio_put(orig_bio);
+	if (ret)
 		return -EIO;
-	}
 
 	if (map_length >= orig_bio->bi_iter.bi_size) {
 		bio = orig_bio;
@@ -7326,6 +7383,7 @@
 	bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, start_sector, GFP_NOFS);
 	if (!bio)
 		return -ENOMEM;
+
 	bio->bi_private = dip;
 	bio->bi_end_io = btrfs_end_dio_bio;
 	atomic_inc(&dip->pending_bios);
@@ -7534,7 +7592,8 @@
 	count = iov_iter_count(iter);
 	if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
 		     &BTRFS_I(inode)->runtime_flags))
-		filemap_fdatawrite_range(inode->i_mapping, offset, count);
+		filemap_fdatawrite_range(inode->i_mapping, offset,
+					 offset + count - 1);
 
 	if (rw & WRITE) {
 		/*
@@ -8495,7 +8554,9 @@
 	work->inode = inode;
 	work->wait = wait;
 	work->delay_iput = delay_iput;
-	btrfs_init_work(&work->work, btrfs_run_delalloc_work, NULL, NULL);
+	WARN_ON_ONCE(!inode);
+	btrfs_init_work(&work->work, btrfs_flush_delalloc_helper,
+			btrfs_run_delalloc_work, NULL, NULL);
 
 	return work;
 }
@@ -8979,6 +9040,14 @@
 	if (ret)
 		goto out;
 
+	/*
+	 * We set number of links to 0 in btrfs_new_inode(), and here we set
+	 * it to 1 because d_tmpfile() will issue a warning if the count is 0,
+	 * through:
+	 *
+	 *    d_tmpfile() -> inode_dec_link_count() -> drop_nlink()
+	 */
+	set_nlink(inode, 1);
 	d_tmpfile(dentry, inode);
 	mark_inode_dirty(inode);
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 47aceb4..fce6fd0e 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -711,39 +711,6 @@
 	if (ret)
 		goto fail;
 
-	ret = btrfs_orphan_cleanup(pending_snapshot->snap);
-	if (ret)
-		goto fail;
-
-	/*
-	 * If orphan cleanup did remove any orphans, it means the tree was
-	 * modified and therefore the commit root is not the same as the
-	 * current root anymore. This is a problem, because send uses the
-	 * commit root and therefore can see inode items that don't exist
-	 * in the current root anymore, and for example make calls to
-	 * btrfs_iget, which will do tree lookups based on the current root
-	 * and not on the commit root. Those lookups will fail, returning a
-	 * -ESTALE error, and making send fail with that error. So make sure
-	 * a send does not see any orphans we have just removed, and that it
-	 * will see the same inodes regardless of whether a transaction
-	 * commit happened before it started (meaning that the commit root
-	 * will be the same as the current root) or not.
-	 */
-	if (readonly && pending_snapshot->snap->node !=
-	    pending_snapshot->snap->commit_root) {
-		trans = btrfs_join_transaction(pending_snapshot->snap);
-		if (IS_ERR(trans) && PTR_ERR(trans) != -ENOENT) {
-			ret = PTR_ERR(trans);
-			goto fail;
-		}
-		if (!IS_ERR(trans)) {
-			ret = btrfs_commit_transaction(trans,
-						       pending_snapshot->snap);
-			if (ret)
-				goto fail;
-		}
-	}
-
 	inode = btrfs_lookup_dentry(dentry->d_parent->d_inode, dentry);
 	if (IS_ERR(inode)) {
 		ret = PTR_ERR(inode);
@@ -3527,7 +3494,8 @@
 			btrfs_mark_buffer_dirty(leaf);
 			btrfs_release_path(path);
 
-			last_dest_end = new_key.offset + datal;
+			last_dest_end = ALIGN(new_key.offset + datal,
+					      root->sectorsize);
 			ret = clone_finish_inode_update(trans, inode,
 							last_dest_end,
 							destoff, olen);
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 963895c..ac734ec 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -615,6 +615,7 @@
 		spin_unlock(&root->ordered_extent_lock);
 
 		btrfs_init_work(&ordered->flush_work,
+				btrfs_flush_delalloc_helper,
 				btrfs_run_ordered_extent_work, NULL, NULL);
 		list_add_tail(&ordered->work_list, &works);
 		btrfs_queue_work(root->fs_info->flush_workers,
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index b497498..ded5c60 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1973,7 +1973,7 @@
 				   elem.seq, &roots);
 	btrfs_put_tree_mod_seq(fs_info, &elem);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	if (roots->nnodes != 1)
 		goto out;
@@ -2720,6 +2720,7 @@
 	memset(&fs_info->qgroup_rescan_work, 0,
 	       sizeof(fs_info->qgroup_rescan_work));
 	btrfs_init_work(&fs_info->qgroup_rescan_work,
+			btrfs_qgroup_rescan_helper,
 			btrfs_qgroup_rescan_worker, NULL, NULL);
 
 	if (ret) {
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 4a88f07..0a6b6e4 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1416,7 +1416,8 @@
 
 static void async_rmw_stripe(struct btrfs_raid_bio *rbio)
 {
-	btrfs_init_work(&rbio->work, rmw_work, NULL, NULL);
+	btrfs_init_work(&rbio->work, btrfs_rmw_helper,
+			rmw_work, NULL, NULL);
 
 	btrfs_queue_work(rbio->fs_info->rmw_workers,
 			 &rbio->work);
@@ -1424,7 +1425,8 @@
 
 static void async_read_rebuild(struct btrfs_raid_bio *rbio)
 {
-	btrfs_init_work(&rbio->work, read_rebuild_work, NULL, NULL);
+	btrfs_init_work(&rbio->work, btrfs_rmw_helper,
+			read_rebuild_work, NULL, NULL);
 
 	btrfs_queue_work(rbio->fs_info->rmw_workers,
 			 &rbio->work);
@@ -1665,7 +1667,8 @@
 	plug = container_of(cb, struct btrfs_plug_cb, cb);
 
 	if (from_schedule) {
-		btrfs_init_work(&plug->work, unplug_work, NULL, NULL);
+		btrfs_init_work(&plug->work, btrfs_rmw_helper,
+				unplug_work, NULL, NULL);
 		btrfs_queue_work(plug->info->rmw_workers,
 				 &plug->work);
 		return;
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 09230cf..20408c6 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -798,7 +798,8 @@
 		/* FIXME we cannot handle this properly right now */
 		BUG();
 	}
-	btrfs_init_work(&rmw->work, reada_start_machine_worker, NULL, NULL);
+	btrfs_init_work(&rmw->work, btrfs_readahead_helper,
+			reada_start_machine_worker, NULL, NULL);
 	rmw->fs_info = fs_info;
 
 	btrfs_queue_work(fs_info->readahead_workers, &rmw->work);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index b6d198f..f4a41f3 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -428,8 +428,8 @@
 		sbio->index = i;
 		sbio->sctx = sctx;
 		sbio->page_count = 0;
-		btrfs_init_work(&sbio->work, scrub_bio_end_io_worker,
-				NULL, NULL);
+		btrfs_init_work(&sbio->work, btrfs_scrub_helper,
+				scrub_bio_end_io_worker, NULL, NULL);
 
 		if (i != SCRUB_BIOS_PER_SCTX - 1)
 			sctx->bios[i]->next_free = i + 1;
@@ -999,8 +999,8 @@
 		fixup_nodatasum->root = fs_info->extent_root;
 		fixup_nodatasum->mirror_num = failed_mirror_index + 1;
 		scrub_pending_trans_workers_inc(sctx);
-		btrfs_init_work(&fixup_nodatasum->work, scrub_fixup_nodatasum,
-				NULL, NULL);
+		btrfs_init_work(&fixup_nodatasum->work, btrfs_scrub_helper,
+				scrub_fixup_nodatasum, NULL, NULL);
 		btrfs_queue_work(fs_info->scrub_workers,
 				 &fixup_nodatasum->work);
 		goto out;
@@ -1616,7 +1616,8 @@
 	sbio->err = err;
 	sbio->bio = bio;
 
-	btrfs_init_work(&sbio->work, scrub_wr_bio_end_io_worker, NULL, NULL);
+	btrfs_init_work(&sbio->work, btrfs_scrubwrc_helper,
+			 scrub_wr_bio_end_io_worker, NULL, NULL);
 	btrfs_queue_work(fs_info->scrub_wr_completion_workers, &sbio->work);
 }
 
@@ -2904,6 +2905,7 @@
 	struct scrub_ctx *sctx;
 	int ret;
 	struct btrfs_device *dev;
+	struct rcu_string *name;
 
 	if (btrfs_fs_closing(fs_info))
 		return -EINVAL;
@@ -2965,6 +2967,16 @@
 		return -ENODEV;
 	}
 
+	if (!is_dev_replace && !readonly && !dev->writeable) {
+		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+		rcu_read_lock();
+		name = rcu_dereference(dev->name);
+		btrfs_err(fs_info, "scrub: device %s is not writable",
+			  name->str);
+		rcu_read_unlock();
+		return -EROFS;
+	}
+
 	mutex_lock(&fs_info->scrub_lock);
 	if (!dev->in_fs_metadata || dev->is_tgtdev_for_dev_replace) {
 		mutex_unlock(&fs_info->scrub_lock);
@@ -3203,7 +3215,8 @@
 	nocow_ctx->len = len;
 	nocow_ctx->mirror_num = mirror_num;
 	nocow_ctx->physical_for_dev_replace = physical_for_dev_replace;
-	btrfs_init_work(&nocow_ctx->work, copy_nocow_pages_worker, NULL, NULL);
+	btrfs_init_work(&nocow_ctx->work, btrfs_scrubnc_helper,
+			copy_nocow_pages_worker, NULL, NULL);
 	INIT_LIST_HEAD(&nocow_ctx->inodes);
 	btrfs_queue_work(fs_info->scrub_nocow_workers,
 			 &nocow_ctx->work);
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 7869936..12e5355 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -614,7 +614,7 @@
 	if (!fs_info->device_dir_kobj)
 		return -EINVAL;
 
-	if (one_device) {
+	if (one_device && one_device->bdev) {
 		disk = one_device->bdev->bd_part;
 		disk_kobj = &part_to_dev(disk)->kobj;
 
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 9e1f2cd..7e0e6e3 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3298,7 +3298,7 @@
 	struct list_head ordered_sums;
 	int skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
 	bool has_extents = false;
-	bool need_find_last_extent = (*last_extent == 0);
+	bool need_find_last_extent = true;
 	bool done = false;
 
 	INIT_LIST_HEAD(&ordered_sums);
@@ -3352,8 +3352,7 @@
 		 */
 		if (ins_keys[i].type == BTRFS_EXTENT_DATA_KEY) {
 			has_extents = true;
-			if (need_find_last_extent &&
-			    first_key.objectid == (u64)-1)
+			if (first_key.objectid == (u64)-1)
 				first_key = ins_keys[i];
 		} else {
 			need_find_last_extent = false;
@@ -3427,6 +3426,16 @@
 	if (!has_extents)
 		return ret;
 
+	if (need_find_last_extent && *last_extent == first_key.offset) {
+		/*
+		 * We don't have any leafs between our current one and the one
+		 * we processed before that can have file extent items for our
+		 * inode (and have a generation number smaller than our current
+		 * transaction id).
+		 */
+		need_find_last_extent = false;
+	}
+
 	/*
 	 * Because we use btrfs_search_forward we could skip leaves that were
 	 * not modified and then assume *last_extent is valid when it really
@@ -3537,7 +3546,7 @@
 					       0, 0);
 		if (ret)
 			break;
-		*last_extent = offset + len;
+		*last_extent = extent_end;
 	}
 	/*
 	 * Need to let the callers know we dropped the path so they should
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 6cb82f6..340a92d 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -508,6 +508,44 @@
 		ret = 1;
 		device->fs_devices = fs_devices;
 	} else if (!device->name || strcmp(device->name->str, path)) {
+		/*
+		 * When FS is already mounted.
+		 * 1. If you are here and if the device->name is NULL that
+		 *    means this device was missing at time of FS mount.
+		 * 2. If you are here and if the device->name is different
+		 *    from 'path' that means either
+		 *      a. The same device disappeared and reappeared with
+		 *         different name. or
+		 *      b. The missing-disk-which-was-replaced, has
+		 *         reappeared now.
+		 *
+		 * We must allow 1 and 2a above. But 2b would be a spurious
+		 * and unintentional.
+		 *
+		 * Further in case of 1 and 2a above, the disk at 'path'
+		 * would have missed some transaction when it was away and
+		 * in case of 2a the stale bdev has to be updated as well.
+		 * 2b must not be allowed at all time.
+		 */
+
+		/*
+		 * As of now don't allow update to btrfs_fs_device through
+		 * the btrfs dev scan cli, after FS has been mounted.
+		 */
+		if (fs_devices->opened) {
+			return -EBUSY;
+		} else {
+			/*
+			 * That is if the FS is _not_ mounted and if you
+			 * are here, that means there is more than one
+			 * disk with same uuid and devid.We keep the one
+			 * with larger generation number or the last-in if
+			 * generation are equal.
+			 */
+			if (found_transid < device->generation)
+				return -EEXIST;
+		}
+
 		name = rcu_string_strdup(path, GFP_NOFS);
 		if (!name)
 			return -ENOMEM;
@@ -519,6 +557,15 @@
 		}
 	}
 
+	/*
+	 * Unmount does not free the btrfs_device struct but would zero
+	 * generation along with most of the other members. So just update
+	 * it back. We need it to pick the disk with largest generation
+	 * (as above).
+	 */
+	if (!fs_devices->opened)
+		device->generation = found_transid;
+
 	if (found_transid > fs_devices->latest_trans) {
 		fs_devices->latest_devid = devid;
 		fs_devices->latest_trans = found_transid;
@@ -1436,7 +1483,7 @@
 	btrfs_set_device_io_align(leaf, dev_item, device->io_align);
 	btrfs_set_device_io_width(leaf, dev_item, device->io_width);
 	btrfs_set_device_sector_size(leaf, dev_item, device->sector_size);
-	btrfs_set_device_total_bytes(leaf, dev_item, device->total_bytes);
+	btrfs_set_device_total_bytes(leaf, dev_item, device->disk_total_bytes);
 	btrfs_set_device_bytes_used(leaf, dev_item, device->bytes_used);
 	btrfs_set_device_group(leaf, dev_item, 0);
 	btrfs_set_device_seek_speed(leaf, dev_item, 0);
@@ -1671,7 +1718,7 @@
 	device->fs_devices->total_devices--;
 
 	if (device->missing)
-		root->fs_info->fs_devices->missing_devices--;
+		device->fs_devices->missing_devices--;
 
 	next_device = list_entry(root->fs_info->fs_devices->devices.next,
 				 struct btrfs_device, dev_list);
@@ -1801,8 +1848,12 @@
 	if (srcdev->bdev) {
 		fs_info->fs_devices->open_devices--;
 
-		/* zero out the old super */
-		btrfs_scratch_superblock(srcdev);
+		/*
+		 * zero out the old super if it is not writable
+		 * (e.g. seed device)
+		 */
+		if (srcdev->writeable)
+			btrfs_scratch_superblock(srcdev);
 	}
 
 	call_rcu(&srcdev->rcu, free_device);
@@ -1941,6 +1992,9 @@
 	fs_devices->seeding = 0;
 	fs_devices->num_devices = 0;
 	fs_devices->open_devices = 0;
+	fs_devices->missing_devices = 0;
+	fs_devices->num_can_discard = 0;
+	fs_devices->rotating = 0;
 	fs_devices->seed = seed_devices;
 
 	generate_random_uuid(fs_devices->fsid);
@@ -5800,7 +5854,8 @@
 	else
 		generate_random_uuid(dev->uuid);
 
-	btrfs_init_work(&dev->work, pending_bios_fn, NULL, NULL);
+	btrfs_init_work(&dev->work, btrfs_submit_helper,
+			pending_bios_fn, NULL, NULL);
 
 	return dev;
 }
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 5b19760..b0c225c 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1825,7 +1825,7 @@
 /*
  * Special error return code only used by dx_probe() and its callers.
  */
-#define ERR_BAD_DX_DIR	-75000
+#define ERR_BAD_DX_DIR	(-(MAX_ERRNO - 1))
 
 /*
  * Timeout and state flag for lazy initialization inode thread.
@@ -2454,6 +2454,22 @@
 	up_write(&EXT4_I(inode)->i_data_sem);
 }
 
+/* Update i_size, i_disksize. Requires i_mutex to avoid races with truncate */
+static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize)
+{
+	int changed = 0;
+
+	if (newsize > inode->i_size) {
+		i_size_write(inode, newsize);
+		changed = 1;
+	}
+	if (newsize > EXT4_I(inode)->i_disksize) {
+		ext4_update_i_disksize(inode, newsize);
+		changed |= 2;
+	}
+	return changed;
+}
+
 struct ext4_group_info {
 	unsigned long   bb_state;
 	struct rb_root  bb_free_root;
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 76c2df3..74292a7 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4665,7 +4665,8 @@
 }
 
 static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
-				  ext4_lblk_t len, int flags, int mode)
+				  ext4_lblk_t len, loff_t new_size,
+				  int flags, int mode)
 {
 	struct inode *inode = file_inode(file);
 	handle_t *handle;
@@ -4674,8 +4675,10 @@
 	int retries = 0;
 	struct ext4_map_blocks map;
 	unsigned int credits;
+	loff_t epos;
 
 	map.m_lblk = offset;
+	map.m_len = len;
 	/*
 	 * Don't normalize the request if it can fit in one extent so
 	 * that it doesn't get unnecessarily split into multiple
@@ -4690,9 +4693,7 @@
 	credits = ext4_chunk_trans_blocks(inode, len);
 
 retry:
-	while (ret >= 0 && ret < len) {
-		map.m_lblk = map.m_lblk + ret;
-		map.m_len = len = len - ret;
+	while (ret >= 0 && len) {
 		handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
 					    credits);
 		if (IS_ERR(handle)) {
@@ -4709,6 +4710,21 @@
 			ret2 = ext4_journal_stop(handle);
 			break;
 		}
+		map.m_lblk += ret;
+		map.m_len = len = len - ret;
+		epos = (loff_t)map.m_lblk << inode->i_blkbits;
+		inode->i_ctime = ext4_current_time(inode);
+		if (new_size) {
+			if (epos > new_size)
+				epos = new_size;
+			if (ext4_update_inode_size(inode, epos) & 0x1)
+				inode->i_mtime = inode->i_ctime;
+		} else {
+			if (epos > inode->i_size)
+				ext4_set_inode_flag(inode,
+						    EXT4_INODE_EOFBLOCKS);
+		}
+		ext4_mark_inode_dirty(handle, inode);
 		ret2 = ext4_journal_stop(handle);
 		if (ret2)
 			break;
@@ -4731,7 +4747,8 @@
 	loff_t new_size = 0;
 	int ret = 0;
 	int flags;
-	int partial;
+	int credits;
+	int partial_begin, partial_end;
 	loff_t start, end;
 	ext4_lblk_t lblk;
 	struct address_space *mapping = inode->i_mapping;
@@ -4771,7 +4788,8 @@
 
 	if (start < offset || end > offset + len)
 		return -EINVAL;
-	partial = (offset + len) & ((1 << blkbits) - 1);
+	partial_begin = offset & ((1 << blkbits) - 1);
+	partial_end = (offset + len) & ((1 << blkbits) - 1);
 
 	lblk = start >> blkbits;
 	max_blocks = (end >> blkbits);
@@ -4805,7 +4823,7 @@
 		 * If we have a partial block after EOF we have to allocate
 		 * the entire block.
 		 */
-		if (partial)
+		if (partial_end)
 			max_blocks += 1;
 	}
 
@@ -4813,6 +4831,7 @@
 
 		/* Now release the pages and zero block aligned part of pages*/
 		truncate_pagecache_range(inode, start, end - 1);
+		inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
 
 		/* Wait all existing dio workers, newcomers will block on i_mutex */
 		ext4_inode_block_unlocked_dio(inode);
@@ -4825,13 +4844,22 @@
 		if (ret)
 			goto out_dio;
 
-		ret = ext4_alloc_file_blocks(file, lblk, max_blocks, flags,
-					     mode);
+		ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
+					     flags, mode);
 		if (ret)
 			goto out_dio;
 	}
+	if (!partial_begin && !partial_end)
+		goto out_dio;
 
-	handle = ext4_journal_start(inode, EXT4_HT_MISC, 4);
+	/*
+	 * In worst case we have to writeout two nonadjacent unwritten
+	 * blocks and update the inode
+	 */
+	credits = (2 * ext4_ext_index_trans_blocks(inode, 2)) + 1;
+	if (ext4_should_journal_data(inode))
+		credits += 2;
+	handle = ext4_journal_start(inode, EXT4_HT_MISC, credits);
 	if (IS_ERR(handle)) {
 		ret = PTR_ERR(handle);
 		ext4_std_error(inode->i_sb, ret);
@@ -4839,12 +4867,8 @@
 	}
 
 	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
-
 	if (new_size) {
-		if (new_size > i_size_read(inode))
-			i_size_write(inode, new_size);
-		if (new_size > EXT4_I(inode)->i_disksize)
-			ext4_update_i_disksize(inode, new_size);
+		ext4_update_inode_size(inode, new_size);
 	} else {
 		/*
 		* Mark that we allocate beyond EOF so the subsequent truncate
@@ -4853,7 +4877,6 @@
 		if ((offset + len) > i_size_read(inode))
 			ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
 	}
-
 	ext4_mark_inode_dirty(handle, inode);
 
 	/* Zero out partial block at the edges of the range */
@@ -4880,13 +4903,11 @@
 long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 {
 	struct inode *inode = file_inode(file);
-	handle_t *handle;
 	loff_t new_size = 0;
 	unsigned int max_blocks;
 	int ret = 0;
 	int flags;
 	ext4_lblk_t lblk;
-	struct timespec tv;
 	unsigned int blkbits = inode->i_blkbits;
 
 	/* Return error if mode is not supported */
@@ -4937,36 +4958,15 @@
 			goto out;
 	}
 
-	ret = ext4_alloc_file_blocks(file, lblk, max_blocks, flags, mode);
+	ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
+				     flags, mode);
 	if (ret)
 		goto out;
 
-	handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
-	if (IS_ERR(handle))
-		goto out;
-
-	tv = inode->i_ctime = ext4_current_time(inode);
-
-	if (new_size) {
-		if (new_size > i_size_read(inode)) {
-			i_size_write(inode, new_size);
-			inode->i_mtime = tv;
-		}
-		if (new_size > EXT4_I(inode)->i_disksize)
-			ext4_update_i_disksize(inode, new_size);
-	} else {
-		/*
-		* Mark that we allocate beyond EOF so the subsequent truncate
-		* can proceed even if the new size is the same as i_size.
-		*/
-		if ((offset + len) > i_size_read(inode))
-			ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
+	if (file->f_flags & O_SYNC && EXT4_SB(inode->i_sb)->s_journal) {
+		ret = jbd2_complete_transaction(EXT4_SB(inode->i_sb)->s_journal,
+						EXT4_I(inode)->i_sync_tid);
 	}
-	ext4_mark_inode_dirty(handle, inode);
-	if (file->f_flags & O_SYNC)
-		ext4_handle_sync(handle);
-
-	ext4_journal_stop(handle);
 out:
 	mutex_unlock(&inode->i_mutex);
 	trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 367a60c..3aa26e9 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1055,27 +1055,11 @@
 	} else
 		copied = block_write_end(file, mapping, pos,
 					 len, copied, page, fsdata);
-
 	/*
-	 * No need to use i_size_read() here, the i_size
-	 * cannot change under us because we hole i_mutex.
-	 *
-	 * But it's important to update i_size while still holding page lock:
+	 * it's important to update i_size while still holding page lock:
 	 * page writeout could otherwise come in and zero beyond i_size.
 	 */
-	if (pos + copied > inode->i_size) {
-		i_size_write(inode, pos + copied);
-		i_size_changed = 1;
-	}
-
-	if (pos + copied > EXT4_I(inode)->i_disksize) {
-		/* We need to mark inode dirty even if
-		 * new_i_size is less that inode->i_size
-		 * but greater than i_disksize. (hint delalloc)
-		 */
-		ext4_update_i_disksize(inode, (pos + copied));
-		i_size_changed = 1;
-	}
+	i_size_changed = ext4_update_inode_size(inode, pos + copied);
 	unlock_page(page);
 	page_cache_release(page);
 
@@ -1123,7 +1107,7 @@
 	int ret = 0, ret2;
 	int partial = 0;
 	unsigned from, to;
-	loff_t new_i_size;
+	int size_changed = 0;
 
 	trace_ext4_journalled_write_end(inode, pos, len, copied);
 	from = pos & (PAGE_CACHE_SIZE - 1);
@@ -1146,20 +1130,18 @@
 		if (!partial)
 			SetPageUptodate(page);
 	}
-	new_i_size = pos + copied;
-	if (new_i_size > inode->i_size)
-		i_size_write(inode, pos+copied);
+	size_changed = ext4_update_inode_size(inode, pos + copied);
 	ext4_set_inode_state(inode, EXT4_STATE_JDATA);
 	EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
-	if (new_i_size > EXT4_I(inode)->i_disksize) {
-		ext4_update_i_disksize(inode, new_i_size);
+	unlock_page(page);
+	page_cache_release(page);
+
+	if (size_changed) {
 		ret2 = ext4_mark_inode_dirty(handle, inode);
 		if (!ret)
 			ret = ret2;
 	}
 
-	unlock_page(page);
-	page_cache_release(page);
 	if (pos + len > inode->i_size && ext4_can_truncate(inode))
 		/* if we have allocated more blocks and copied
 		 * less. We will have blocks allocated outside
@@ -2095,6 +2077,7 @@
 	struct ext4_map_blocks *map = &mpd->map;
 	int err;
 	loff_t disksize;
+	int progress = 0;
 
 	mpd->io_submit.io_end->offset =
 				((loff_t)map->m_lblk) << inode->i_blkbits;
@@ -2111,8 +2094,11 @@
 			 * is non-zero, a commit should free up blocks.
 			 */
 			if ((err == -ENOMEM) ||
-			    (err == -ENOSPC && ext4_count_free_clusters(sb)))
+			    (err == -ENOSPC && ext4_count_free_clusters(sb))) {
+				if (progress)
+					goto update_disksize;
 				return err;
+			}
 			ext4_msg(sb, KERN_CRIT,
 				 "Delayed block allocation failed for "
 				 "inode %lu at logical offset %llu with"
@@ -2129,15 +2115,17 @@
 			*give_up_on_write = true;
 			return err;
 		}
+		progress = 1;
 		/*
 		 * Update buffer state, submit mapped pages, and get us new
 		 * extent to map
 		 */
 		err = mpage_map_and_submit_buffers(mpd);
 		if (err < 0)
-			return err;
+			goto update_disksize;
 	} while (map->m_len);
 
+update_disksize:
 	/*
 	 * Update on-disk size after IO is submitted.  Races with
 	 * truncate are avoided by checking i_size under i_data_sem.
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 9560277..8b0f9ef 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1412,6 +1412,8 @@
 	int last = first + count - 1;
 	struct super_block *sb = e4b->bd_sb;
 
+	if (WARN_ON(count == 0))
+		return;
 	BUG_ON(last >= (sb->s_blocksize << 3));
 	assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group));
 	/* Don't bother if the block group is corrupt. */
@@ -3221,6 +3223,8 @@
 	int err;
 
 	if (pa == NULL) {
+		if (ac->ac_f_ex.fe_len == 0)
+			return;
 		err = ext4_mb_load_buddy(ac->ac_sb, ac->ac_f_ex.fe_group, &e4b);
 		if (err) {
 			/*
@@ -3235,6 +3239,7 @@
 		mb_free_blocks(ac->ac_inode, &e4b, ac->ac_f_ex.fe_start,
 			       ac->ac_f_ex.fe_len);
 		ext4_unlock_group(ac->ac_sb, ac->ac_f_ex.fe_group);
+		ext4_mb_unload_buddy(&e4b);
 		return;
 	}
 	if (pa->pa_type == MB_INODE_PA)
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index b147a67..90a3cdc 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1227,7 +1227,7 @@
 				   buffer */
 	int num = 0;
 	ext4_lblk_t  nblocks;
-	int i, err;
+	int i, err = 0;
 	int namelen;
 
 	*res_dir = NULL;
@@ -1264,7 +1264,11 @@
 		 * return.  Otherwise, fall back to doing a search the
 		 * old fashioned way.
 		 */
-		if (bh || (err != ERR_BAD_DX_DIR))
+		if (err == -ENOENT)
+			return NULL;
+		if (err && err != ERR_BAD_DX_DIR)
+			return ERR_PTR(err);
+		if (bh)
 			return bh;
 		dxtrace(printk(KERN_DEBUG "ext4_find_entry: dx failed, "
 			       "falling back\n"));
@@ -1295,6 +1299,11 @@
 				}
 				num++;
 				bh = ext4_getblk(NULL, dir, b++, 0, &err);
+				if (unlikely(err)) {
+					if (ra_max == 0)
+						return ERR_PTR(err);
+					break;
+				}
 				bh_use[ra_max] = bh;
 				if (bh)
 					ll_rw_block(READ | REQ_META | REQ_PRIO,
@@ -1417,6 +1426,8 @@
 		return ERR_PTR(-ENAMETOOLONG);
 
 	bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL);
+	if (IS_ERR(bh))
+		return (struct dentry *) bh;
 	inode = NULL;
 	if (bh) {
 		__u32 ino = le32_to_cpu(de->inode);
@@ -1450,6 +1461,8 @@
 	struct buffer_head *bh;
 
 	bh = ext4_find_entry(child->d_inode, &dotdot, &de, NULL);
+	if (IS_ERR(bh))
+		return (struct dentry *) bh;
 	if (!bh)
 		return ERR_PTR(-ENOENT);
 	ino = le32_to_cpu(de->inode);
@@ -2727,6 +2740,8 @@
 
 	retval = -ENOENT;
 	bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL);
+	if (IS_ERR(bh))
+		return PTR_ERR(bh);
 	if (!bh)
 		goto end_rmdir;
 
@@ -2794,6 +2809,8 @@
 
 	retval = -ENOENT;
 	bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL);
+	if (IS_ERR(bh))
+		return PTR_ERR(bh);
 	if (!bh)
 		goto end_unlink;
 
@@ -3121,6 +3138,8 @@
 	struct ext4_dir_entry_2 *de;
 
 	bh = ext4_find_entry(dir, d_name, &de, NULL);
+	if (IS_ERR(bh))
+		return PTR_ERR(bh);
 	if (bh) {
 		retval = ext4_delete_entry(handle, dir, de, bh);
 		brelse(bh);
@@ -3128,7 +3147,8 @@
 	return retval;
 }
 
-static void ext4_rename_delete(handle_t *handle, struct ext4_renament *ent)
+static void ext4_rename_delete(handle_t *handle, struct ext4_renament *ent,
+			       int force_reread)
 {
 	int retval;
 	/*
@@ -3140,7 +3160,8 @@
 	if (le32_to_cpu(ent->de->inode) != ent->inode->i_ino ||
 	    ent->de->name_len != ent->dentry->d_name.len ||
 	    strncmp(ent->de->name, ent->dentry->d_name.name,
-		    ent->de->name_len)) {
+		    ent->de->name_len) ||
+	    force_reread) {
 		retval = ext4_find_delete_entry(handle, ent->dir,
 						&ent->dentry->d_name);
 	} else {
@@ -3191,6 +3212,7 @@
 		.dentry = new_dentry,
 		.inode = new_dentry->d_inode,
 	};
+	int force_reread;
 	int retval;
 
 	dquot_initialize(old.dir);
@@ -3202,6 +3224,8 @@
 		dquot_initialize(new.inode);
 
 	old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL);
+	if (IS_ERR(old.bh))
+		return PTR_ERR(old.bh);
 	/*
 	 *  Check for inode number is _not_ due to possible IO errors.
 	 *  We might rmdir the source, keep it as pwd of some process
@@ -3214,6 +3238,10 @@
 
 	new.bh = ext4_find_entry(new.dir, &new.dentry->d_name,
 				 &new.de, &new.inlined);
+	if (IS_ERR(new.bh)) {
+		retval = PTR_ERR(new.bh);
+		goto end_rename;
+	}
 	if (new.bh) {
 		if (!new.inode) {
 			brelse(new.bh);
@@ -3246,6 +3274,15 @@
 		if (retval)
 			goto end_rename;
 	}
+	/*
+	 * If we're renaming a file within an inline_data dir and adding or
+	 * setting the new dirent causes a conversion from inline_data to
+	 * extents/blockmap, we need to force the dirent delete code to
+	 * re-read the directory, or else we end up trying to delete a dirent
+	 * from what is now the extent tree root (or a block map).
+	 */
+	force_reread = (new.dir->i_ino == old.dir->i_ino &&
+			ext4_test_inode_flag(new.dir, EXT4_INODE_INLINE_DATA));
 	if (!new.bh) {
 		retval = ext4_add_entry(handle, new.dentry, old.inode);
 		if (retval)
@@ -3256,6 +3293,9 @@
 		if (retval)
 			goto end_rename;
 	}
+	if (force_reread)
+		force_reread = !ext4_test_inode_flag(new.dir,
+						     EXT4_INODE_INLINE_DATA);
 
 	/*
 	 * Like most other Unix systems, set the ctime for inodes on a
@@ -3267,7 +3307,7 @@
 	/*
 	 * ok, that's it
 	 */
-	ext4_rename_delete(handle, &old);
+	ext4_rename_delete(handle, &old, force_reread);
 
 	if (new.inode) {
 		ext4_dec_count(handle, new.inode);
@@ -3330,6 +3370,8 @@
 
 	old.bh = ext4_find_entry(old.dir, &old.dentry->d_name,
 				 &old.de, &old.inlined);
+	if (IS_ERR(old.bh))
+		return PTR_ERR(old.bh);
 	/*
 	 *  Check for inode number is _not_ due to possible IO errors.
 	 *  We might rmdir the source, keep it as pwd of some process
@@ -3342,6 +3384,10 @@
 
 	new.bh = ext4_find_entry(new.dir, &new.dentry->d_name,
 				 &new.de, &new.inlined);
+	if (IS_ERR(new.bh)) {
+		retval = PTR_ERR(new.bh);
+		goto end_rename;
+	}
 
 	/* RENAME_EXCHANGE case: old *and* new must both exist */
 	if (!new.bh || le32_to_cpu(new.de->inode) != new.inode->i_ino)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 32b43ad..0b28b36 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3181,9 +3181,9 @@
 
 	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
 				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
-		/* journal checksum v2 */
+		/* journal checksum v3 */
 		compat = 0;
-		incompat = JBD2_FEATURE_INCOMPAT_CSUM_V2;
+		incompat = JBD2_FEATURE_INCOMPAT_CSUM_V3;
 	} else {
 		/* journal checksum v1 */
 		compat = JBD2_FEATURE_COMPAT_CHECKSUM;
@@ -3205,6 +3205,7 @@
 		jbd2_journal_clear_features(sbi->s_journal,
 				JBD2_FEATURE_COMPAT_CHECKSUM, 0,
 				JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT |
+				JBD2_FEATURE_INCOMPAT_CSUM_V3 |
 				JBD2_FEATURE_INCOMPAT_CSUM_V2);
 	}
 
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 6fac743..b73e021 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -97,7 +97,7 @@
 	struct commit_header *h;
 	__u32 csum;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	h = (struct commit_header *)(bh->b_data);
@@ -313,11 +313,11 @@
 	return checksum;
 }
 
-static void write_tag_block(int tag_bytes, journal_block_tag_t *tag,
+static void write_tag_block(journal_t *j, journal_block_tag_t *tag,
 				   unsigned long long block)
 {
 	tag->t_blocknr = cpu_to_be32(block & (u32)~0);
-	if (tag_bytes > JBD2_TAG_SIZE32)
+	if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_64BIT))
 		tag->t_blocknr_high = cpu_to_be32((block >> 31) >> 1);
 }
 
@@ -327,7 +327,7 @@
 	struct jbd2_journal_block_tail *tail;
 	__u32 csum;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	tail = (struct jbd2_journal_block_tail *)(bh->b_data + j->j_blocksize -
@@ -340,12 +340,13 @@
 static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag,
 				    struct buffer_head *bh, __u32 sequence)
 {
+	journal_block_tag3_t *tag3 = (journal_block_tag3_t *)tag;
 	struct page *page = bh->b_page;
 	__u8 *addr;
 	__u32 csum32;
 	__be32 seq;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	seq = cpu_to_be32(sequence);
@@ -355,8 +356,10 @@
 			     bh->b_size);
 	kunmap_atomic(addr);
 
-	/* We only have space to store the lower 16 bits of the crc32c. */
-	tag->t_checksum = cpu_to_be16(csum32);
+	if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+		tag3->t_checksum = cpu_to_be32(csum32);
+	else
+		tag->t_checksum = cpu_to_be16(csum32);
 }
 /*
  * jbd2_journal_commit_transaction
@@ -396,7 +399,7 @@
 	LIST_HEAD(io_bufs);
 	LIST_HEAD(log_bufs);
 
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (jbd2_journal_has_csum_v2or3(journal))
 		csum_size = sizeof(struct jbd2_journal_block_tail);
 
 	/*
@@ -690,7 +693,7 @@
 			tag_flag |= JBD2_FLAG_SAME_UUID;
 
 		tag = (journal_block_tag_t *) tagp;
-		write_tag_block(tag_bytes, tag, jh2bh(jh)->b_blocknr);
+		write_tag_block(journal, tag, jh2bh(jh)->b_blocknr);
 		tag->t_flags = cpu_to_be16(tag_flag);
 		jbd2_block_tag_csum_set(journal, tag, wbuf[bufs],
 					commit_transaction->t_tid);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 67b8e30..19d74d8 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -124,7 +124,7 @@
 /* Checksumming functions */
 static int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb)
 {
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	return sb->s_checksum_type == JBD2_CRC32C_CHKSUM;
@@ -145,7 +145,7 @@
 
 static int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb)
 {
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	return sb->s_checksum == jbd2_superblock_csum(j, sb);
@@ -153,7 +153,7 @@
 
 static void jbd2_superblock_csum_set(journal_t *j, journal_superblock_t *sb)
 {
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	sb->s_checksum = jbd2_superblock_csum(j, sb);
@@ -1522,21 +1522,29 @@
 		goto out;
 	}
 
-	if (JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM) &&
-	    JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
+	if (jbd2_journal_has_csum_v2or3(journal) &&
+	    JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM)) {
 		/* Can't have checksum v1 and v2 on at the same time! */
 		printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2 "
 		       "at the same time!\n");
 		goto out;
 	}
 
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2) &&
+	    JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
+		/* Can't have checksum v2 and v3 at the same time! */
+		printk(KERN_ERR "JBD2: Can't enable checksumming v2 and v3 "
+		       "at the same time!\n");
+		goto out;
+	}
+
 	if (!jbd2_verify_csum_type(journal, sb)) {
 		printk(KERN_ERR "JBD2: Unknown checksum type\n");
 		goto out;
 	}
 
 	/* Load the checksum driver */
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
+	if (jbd2_journal_has_csum_v2or3(journal)) {
 		journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0);
 		if (IS_ERR(journal->j_chksum_driver)) {
 			printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n");
@@ -1553,7 +1561,7 @@
 	}
 
 	/* Precompute checksum seed for all metadata */
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (jbd2_journal_has_csum_v2or3(journal))
 		journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid,
 						   sizeof(sb->s_uuid));
 
@@ -1813,8 +1821,14 @@
 	if (!jbd2_journal_check_available_features(journal, compat, ro, incompat))
 		return 0;
 
-	/* Asking for checksumming v2 and v1?  Only give them v2. */
-	if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2 &&
+	/* If enabling v2 checksums, turn on v3 instead */
+	if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2) {
+		incompat &= ~JBD2_FEATURE_INCOMPAT_CSUM_V2;
+		incompat |= JBD2_FEATURE_INCOMPAT_CSUM_V3;
+	}
+
+	/* Asking for checksumming v3 and v1?  Only give them v3. */
+	if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V3 &&
 	    compat & JBD2_FEATURE_COMPAT_CHECKSUM)
 		compat &= ~JBD2_FEATURE_COMPAT_CHECKSUM;
 
@@ -1823,8 +1837,8 @@
 
 	sb = journal->j_superblock;
 
-	/* If enabling v2 checksums, update superblock */
-	if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
+	/* If enabling v3 checksums, update superblock */
+	if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
 		sb->s_checksum_type = JBD2_CRC32C_CHKSUM;
 		sb->s_feature_compat &=
 			~cpu_to_be32(JBD2_FEATURE_COMPAT_CHECKSUM);
@@ -1842,8 +1856,7 @@
 		}
 
 		/* Precompute checksum seed for all metadata */
-		if (JBD2_HAS_INCOMPAT_FEATURE(journal,
-					      JBD2_FEATURE_INCOMPAT_CSUM_V2))
+		if (jbd2_journal_has_csum_v2or3(journal))
 			journal->j_csum_seed = jbd2_chksum(journal, ~0,
 							   sb->s_uuid,
 							   sizeof(sb->s_uuid));
@@ -1852,7 +1865,8 @@
 	/* If enabling v1 checksums, downgrade superblock */
 	if (COMPAT_FEATURE_ON(JBD2_FEATURE_COMPAT_CHECKSUM))
 		sb->s_feature_incompat &=
-			~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2);
+			~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2 |
+				     JBD2_FEATURE_INCOMPAT_CSUM_V3);
 
 	sb->s_feature_compat    |= cpu_to_be32(compat);
 	sb->s_feature_ro_compat |= cpu_to_be32(ro);
@@ -2165,16 +2179,20 @@
  */
 size_t journal_tag_bytes(journal_t *journal)
 {
-	journal_block_tag_t tag;
-	size_t x = 0;
+	size_t sz;
+
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+		return sizeof(journal_block_tag3_t);
+
+	sz = sizeof(journal_block_tag_t);
 
 	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
-		x += sizeof(tag.t_checksum);
+		sz += sizeof(__u16);
 
 	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
-		return x + JBD2_TAG_SIZE64;
+		return sz;
 	else
-		return x + JBD2_TAG_SIZE32;
+		return sz - sizeof(__u32);
 }
 
 /*
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 3b6bb19..9b329b5 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -181,7 +181,7 @@
 	__be32 provided;
 	__u32 calculated;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	tail = (struct jbd2_journal_block_tail *)(buf + j->j_blocksize -
@@ -205,7 +205,7 @@
 	int			nr = 0, size = journal->j_blocksize;
 	int			tag_bytes = journal_tag_bytes(journal);
 
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (jbd2_journal_has_csum_v2or3(journal))
 		size -= sizeof(struct jbd2_journal_block_tail);
 
 	tagp = &bh->b_data[sizeof(journal_header_t)];
@@ -338,10 +338,11 @@
 	return err;
 }
 
-static inline unsigned long long read_tag_block(int tag_bytes, journal_block_tag_t *tag)
+static inline unsigned long long read_tag_block(journal_t *journal,
+						journal_block_tag_t *tag)
 {
 	unsigned long long block = be32_to_cpu(tag->t_blocknr);
-	if (tag_bytes > JBD2_TAG_SIZE32)
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
 		block |= (u64)be32_to_cpu(tag->t_blocknr_high) << 32;
 	return block;
 }
@@ -384,7 +385,7 @@
 	__be32 provided;
 	__u32 calculated;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	h = buf;
@@ -399,17 +400,21 @@
 static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag,
 				      void *buf, __u32 sequence)
 {
+	journal_block_tag3_t *tag3 = (journal_block_tag3_t *)tag;
 	__u32 csum32;
 	__be32 seq;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	seq = cpu_to_be32(sequence);
 	csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&seq, sizeof(seq));
 	csum32 = jbd2_chksum(j, csum32, buf, j->j_blocksize);
 
-	return tag->t_checksum == cpu_to_be16(csum32);
+	if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+		return tag3->t_checksum == cpu_to_be32(csum32);
+	else
+		return tag->t_checksum == cpu_to_be16(csum32);
 }
 
 static int do_one_pass(journal_t *journal,
@@ -426,6 +431,7 @@
 	int			tag_bytes = journal_tag_bytes(journal);
 	__u32			crc32_sum = ~0; /* Transactional Checksums */
 	int			descr_csum_size = 0;
+	int			block_error = 0;
 
 	/*
 	 * First thing is to establish what we expect to find in the log
@@ -512,8 +518,7 @@
 		switch(blocktype) {
 		case JBD2_DESCRIPTOR_BLOCK:
 			/* Verify checksum first */
-			if (JBD2_HAS_INCOMPAT_FEATURE(journal,
-					JBD2_FEATURE_INCOMPAT_CSUM_V2))
+			if (jbd2_journal_has_csum_v2or3(journal))
 				descr_csum_size =
 					sizeof(struct jbd2_journal_block_tail);
 			if (descr_csum_size > 0 &&
@@ -574,7 +579,7 @@
 					unsigned long long blocknr;
 
 					J_ASSERT(obh != NULL);
-					blocknr = read_tag_block(tag_bytes,
+					blocknr = read_tag_block(journal,
 								 tag);
 
 					/* If the block has been
@@ -598,7 +603,8 @@
 						       "checksum recovering "
 						       "block %llu in log\n",
 						       blocknr);
-						continue;
+						block_error = 1;
+						goto skip_write;
 					}
 
 					/* Find a buffer for the new
@@ -797,7 +803,8 @@
 				success = -EIO;
 		}
 	}
-
+	if (block_error && success == 0)
+		success = -EIO;
 	return success;
 
  failed:
@@ -811,7 +818,7 @@
 	__be32 provided;
 	__u32 calculated;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	tail = (struct jbd2_journal_revoke_tail *)(buf + j->j_blocksize -
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index 198c9c1..d5e95a1 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -91,8 +91,8 @@
 #include <linux/list.h>
 #include <linux/init.h>
 #include <linux/bio.h>
-#endif
 #include <linux/log2.h>
+#endif
 
 static struct kmem_cache *jbd2_revoke_record_cache;
 static struct kmem_cache *jbd2_revoke_table_cache;
@@ -597,7 +597,7 @@
 	offset = *offsetp;
 
 	/* Do we need to leave space at the end for a checksum? */
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (jbd2_journal_has_csum_v2or3(journal))
 		csum_size = sizeof(struct jbd2_journal_revoke_tail);
 
 	/* Make sure we have a descriptor with space left for the record */
@@ -644,7 +644,7 @@
 	struct jbd2_journal_revoke_tail *tail;
 	__u32 csum;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	tail = (struct jbd2_journal_revoke_tail *)(bh->b_data + j->j_blocksize -
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index eb726b9..a1e31f2 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -127,10 +127,9 @@
 	BLK_MQ_RQ_QUEUE_ERROR	= 2,	/* end IO with error */
 
 	BLK_MQ_F_SHOULD_MERGE	= 1 << 0,
-	BLK_MQ_F_SHOULD_SORT	= 1 << 1,
-	BLK_MQ_F_TAG_SHARED	= 1 << 2,
-	BLK_MQ_F_SG_MERGE	= 1 << 3,
-	BLK_MQ_F_SYSFS_UP	= 1 << 4,
+	BLK_MQ_F_TAG_SHARED	= 1 << 1,
+	BLK_MQ_F_SG_MERGE	= 1 << 2,
+	BLK_MQ_F_SYSFS_UP	= 1 << 3,
 
 	BLK_MQ_S_STOPPED	= 0,
 	BLK_MQ_S_TAG_ACTIVE	= 1,
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index d5b50a1..0dae71e 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -159,7 +159,11 @@
  * journal_block_tag (in the descriptor).  The other h_chksum* fields are
  * not used.
  *
- * Checksum v1 and v2 are mutually exclusive features.
+ * If FEATURE_INCOMPAT_CSUM_V3 is set, the descriptor block uses
+ * journal_block_tag3_t to store a full 32-bit checksum.  Everything else
+ * is the same as v2.
+ *
+ * Checksum v1, v2, and v3 are mutually exclusive features.
  */
 struct commit_header {
 	__be32		h_magic;
@@ -179,6 +183,14 @@
  * raw struct shouldn't be used for pointer math or sizeof() - use
  * journal_tag_bytes(journal) instead to compute this.
  */
+typedef struct journal_block_tag3_s
+{
+	__be32		t_blocknr;	/* The on-disk block number */
+	__be32		t_flags;	/* See below */
+	__be32		t_blocknr_high; /* most-significant high 32bits. */
+	__be32		t_checksum;	/* crc32c(uuid+seq+block) */
+} journal_block_tag3_t;
+
 typedef struct journal_block_tag_s
 {
 	__be32		t_blocknr;	/* The on-disk block number */
@@ -187,9 +199,6 @@
 	__be32		t_blocknr_high; /* most-significant high 32bits. */
 } journal_block_tag_t;
 
-#define JBD2_TAG_SIZE32 (offsetof(journal_block_tag_t, t_blocknr_high))
-#define JBD2_TAG_SIZE64 (sizeof(journal_block_tag_t))
-
 /* Tail of descriptor block, for checksumming */
 struct jbd2_journal_block_tail {
 	__be32		t_checksum;	/* crc32c(uuid+descr_block) */
@@ -284,6 +293,7 @@
 #define JBD2_FEATURE_INCOMPAT_64BIT		0x00000002
 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT	0x00000004
 #define JBD2_FEATURE_INCOMPAT_CSUM_V2		0x00000008
+#define JBD2_FEATURE_INCOMPAT_CSUM_V3		0x00000010
 
 /* Features known to this kernel version: */
 #define JBD2_KNOWN_COMPAT_FEATURES	JBD2_FEATURE_COMPAT_CHECKSUM
@@ -291,7 +301,8 @@
 #define JBD2_KNOWN_INCOMPAT_FEATURES	(JBD2_FEATURE_INCOMPAT_REVOKE | \
 					JBD2_FEATURE_INCOMPAT_64BIT | \
 					JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \
-					JBD2_FEATURE_INCOMPAT_CSUM_V2)
+					JBD2_FEATURE_INCOMPAT_CSUM_V2 | \
+					JBD2_FEATURE_INCOMPAT_CSUM_V3)
 
 #ifdef __KERNEL__
 
@@ -1296,6 +1307,15 @@
 extern int jbd2_journal_blocks_per_page(struct inode *inode);
 extern size_t journal_tag_bytes(journal_t *journal);
 
+static inline int jbd2_journal_has_csum_v2or3(journal_t *journal)
+{
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2) ||
+	    JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+		return 1;
+
+	return 0;
+}
+
 /*
  * We reserve t_outstanding_credits >> JBD2_CONTROL_BLOCKS_SHIFT for
  * transaction control blocks.
diff --git a/include/linux/seqno-fence.h b/include/linux/seqno-fence.h
index 3d6003d..a1ba6a5 100644
--- a/include/linux/seqno-fence.h
+++ b/include/linux/seqno-fence.h
@@ -62,6 +62,7 @@
  * @context: the execution context this fence is a part of
  * @seqno_ofs: the offset within @sync_buf
  * @seqno: the sequence # to signal on
+ * @cond: fence wait condition
  * @ops: the fence_ops for operations on this seqno fence
  *
  * This function initializes a struct seqno_fence with passed parameters,
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index afb04b9..b38fb2b 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -626,8 +626,22 @@
 		work = &cpu_buffer->irq_work;
 	}
 
-	work->waiters_pending = true;
 	poll_wait(filp, &work->waiters, poll_table);
+	work->waiters_pending = true;
+	/*
+	 * There's a tight race between setting the waiters_pending and
+	 * checking if the ring buffer is empty.  Once the waiters_pending bit
+	 * is set, the next event will wake the task up, but we can get stuck
+	 * if there's only a single event in.
+	 *
+	 * FIXME: Ideally, we need a memory barrier on the writer side as well,
+	 * but adding a memory barrier to all events will cause too much of a
+	 * performance hit in the fast path.  We only need a memory barrier when
+	 * the buffer goes from empty to having content.  But as this race is
+	 * extremely small, and it's not a problem if another event comes in, we
+	 * will fix it later.
+	 */
+	smp_mb();
 
 	if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
 	    (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 07c2832..1b233fc 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -892,6 +892,10 @@
 	 the full mutex checks enabled with (CONFIG_PROVE_LOCKING) this
 	 will test all possible w/w mutex interface abuse with the
 	 exception of simply not acquiring all the required locks.
+	 Note that this feature can introduce significant overhead, so
+	 it really should not be enabled in a production or distro kernel,
+	 even a debug kernel.  If you are a driver writer, enable it.  If
+	 you are a distro, do not.
 
 config DEBUG_LOCK_ALLOC
 	bool "Lock debugging: detect incorrect freeing of live locks"
diff --git a/scripts/kernel-doc b/scripts/kernel-doc
index 16a07cf..70bea94 100755
--- a/scripts/kernel-doc
+++ b/scripts/kernel-doc
@@ -2085,6 +2085,7 @@
     $prototype =~ s/^noinline +//;
     $prototype =~ s/__init +//;
     $prototype =~ s/__init_or_module +//;
+    $prototype =~ s/__meminit +//;
     $prototype =~ s/__must_check +//;
     $prototype =~ s/__weak +//;
     my $define = $prototype =~ s/^#\s*define\s+//; #ak added
diff --git a/security/tomoyo/realpath.c b/security/tomoyo/realpath.c
index a3386d1..bed745c 100644
--- a/security/tomoyo/realpath.c
+++ b/security/tomoyo/realpath.c
@@ -173,7 +173,7 @@
 		 * Use filesystem name if filesystem does not support rename()
 		 * operation.
 		 */
-		if (!inode->i_op->rename)
+		if (!inode->i_op->rename && !inode->i_op->rename2)
 			goto prepend_filesystem_name;
 	}
 	/* Prepend device name. */
@@ -282,7 +282,8 @@
 		 * Get local name for filesystems without rename() operation
 		 * or dentry without vfsmount.
 		 */
-		if (!path->mnt || !inode->i_op->rename)
+		if (!path->mnt ||
+		    (!inode->i_op->rename && !inode->i_op->rename2))
 			pos = tomoyo_get_local_path(path->dentry, buf,
 						    buf_len - 1);
 		/* Get absolute name for the rest. */
diff --git a/sound/core/info.c b/sound/core/info.c
index 051d55b..9f404e9 100644
--- a/sound/core/info.c
+++ b/sound/core/info.c
@@ -684,7 +684,7 @@
  * snd_info_get_line - read one line from the procfs buffer
  * @buffer: the procfs buffer
  * @line: the buffer to store
- * @len: the max. buffer size - 1
+ * @len: the max. buffer size
  *
  * Reads one line from the buffer and stores the string.
  *
@@ -704,7 +704,7 @@
 			buffer->stop = 1;
 		if (c == '\n')
 			break;
-		if (len) {
+		if (len > 1) {
 			len--;
 			*line++ = c;
 		}
diff --git a/sound/core/pcm_misc.c b/sound/core/pcm_misc.c
index 4560ca0..2c6fd80 100644
--- a/sound/core/pcm_misc.c
+++ b/sound/core/pcm_misc.c
@@ -142,11 +142,11 @@
 	},
 	[SNDRV_PCM_FORMAT_DSD_U8] = {
 		.width = 8, .phys = 8, .le = 1, .signd = 0,
-		.silence = {},
+		.silence = { 0x69 },
 	},
 	[SNDRV_PCM_FORMAT_DSD_U16_LE] = {
 		.width = 16, .phys = 16, .le = 1, .signd = 0,
-		.silence = {},
+		.silence = { 0x69, 0x69 },
 	},
 	/* FIXME: the following three formats are not defined properly yet */
 	[SNDRV_PCM_FORMAT_MPEG] = {
diff --git a/sound/pci/ctxfi/ct20k1reg.h b/sound/pci/ctxfi/ct20k1reg.h
index f2e34e3..5851249 100644
--- a/sound/pci/ctxfi/ct20k1reg.h
+++ b/sound/pci/ctxfi/ct20k1reg.h
@@ -7,7 +7,7 @@
  */
 
 #ifndef CT20K1REG_H
-#define CT20k1REG_H
+#define CT20K1REG_H
 
 /* 20k1 registers */
 #define 	DSPXRAM_START 			0x000000
@@ -632,5 +632,3 @@
 #define I2SD_R    0x19L
 
 #endif /* CT20K1REG_H */
-
-
diff --git a/sound/pci/hda/ca0132_regs.h b/sound/pci/hda/ca0132_regs.h
index 07e7609..8371274 100644
--- a/sound/pci/hda/ca0132_regs.h
+++ b/sound/pci/hda/ca0132_regs.h
@@ -20,7 +20,7 @@
  */
 
 #ifndef __CA0132_REGS_H
-#define __CA0312_REGS_H
+#define __CA0132_REGS_H
 
 #define DSP_CHIP_OFFSET                0x100000
 #define DSP_DBGCNTL_MODULE_OFFSET      0xE30
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index d71270a..d446ac3 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4408,6 +4408,7 @@
 	ALC292_FIXUP_TPT440_DOCK,
 	ALC283_FIXUP_BXBT2807_MIC,
 	ALC255_FIXUP_DELL_WMI_MIC_MUTE_LED,
+	ALC282_FIXUP_ASPIRE_V5_PINS,
 };
 
 static const struct hda_fixup alc269_fixups[] = {
@@ -4855,6 +4856,22 @@
 		.chained_before = true,
 		.chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE
 	},
+	[ALC282_FIXUP_ASPIRE_V5_PINS] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x12, 0x90a60130 },
+			{ 0x14, 0x90170110 },
+			{ 0x17, 0x40000008 },
+			{ 0x18, 0x411111f0 },
+			{ 0x19, 0x411111f0 },
+			{ 0x1a, 0x411111f0 },
+			{ 0x1b, 0x411111f0 },
+			{ 0x1d, 0x40f89b2d },
+			{ 0x1e, 0x411111f0 },
+			{ 0x21, 0x0321101f },
+			{ },
+		},
+	},
 
 };
 
@@ -4866,6 +4883,7 @@
 	SND_PCI_QUIRK(0x1025, 0x0740, "Acer AO725", ALC271_FIXUP_HP_GATE_MIC_JACK),
 	SND_PCI_QUIRK(0x1025, 0x0742, "Acer AO756", ALC271_FIXUP_HP_GATE_MIC_JACK),
 	SND_PCI_QUIRK(0x1025, 0x0775, "Acer Aspire E1-572", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572),
+	SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS),
 	SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z),
 	SND_PCI_QUIRK(0x1028, 0x05bd, "Dell", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x05be, "Dell", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),