Merge tag 'omap-fixes-against-v3.17-rc3' of...

Merge tag 'omap-fixes-against-v3.17-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap into fixes

Merge "omap fixes against v3.17-rc3" from Tony Lindgren:

Few fixes for omaps mostly for various devices to get them working
properly on the new am437x and dra7 hardware for several devices
such as I2C, NAND, DDR3 and USB. There's also a clock fix for omap3.

And also included are two minor cosmetic fixes that are not
stictly fixes for the new hardware support added recently to
downgrade a GPMC warning into a debug statement, and fix the
confusing comments for dra7-evm spi1 mux.

Note that these are all .dts changes except for a GPMC change.

* tag 'omap-fixes-against-v3.17-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap

: (255 commits)
  ARM: dts: dra7-evm: Add vtt regulator support
  ARM: dts: dra7-evm: Fix spi1 mux documentation
  ARM: dts: am43x-epos-evm: Disable QSPI to prevent conflict with GPMC-NAND
  ARM: OMAP2+: gpmc: Don't complain if wait pin is used without r/w monitoring
  ARM: dts: am43xx-epos-evm: Don't use read/write wait monitoring
  ARM: dts: am437x-gp-evm: Don't use read/write wait monitoring
  ARM: dts: am437x-gp-evm: Use BCH16 ECC scheme instead of BCH8
  ARM: dts: am43x-epos-evm: Use BCH16 ECC scheme instead of BCH8
  ARM: dts: am4372: fix USB regs size
  ARM: dts: am437x-gp: switch i2c0 to 100KHz
  ARM: dts: dra7-evm: Fix 8th NAND partition's name
  ARM: dts: dra7-evm: Fix i2c3 pinmux and frequency
  Linux 3.17-rc3
  ...
Signed-off-by: Kevin Hilman <khilman@linaro.org>

Documentation/devicetree/bindings/mfd/tc3589x.txt

+* 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>;
+	};
+};

Documentation/devicetree/bindings/pinctrl/qcom,apq8064-pinctrl.txt

@@ -62,7 +62,7 @@ Example:
 		#gpio-cells = <2>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
-		interrupts = <0 32 0x4>;
+		interrupts = <0 16 0x4>;
 
 		pinctrl-names = "default";
 		pinctrl-0 = <&gsbi5_uart_default>;

Documentation/dma-buf-sharing.txt

@@ -56,10 +56,10 @@ The dma_buf buffer sharing API usage contains the following steps:
 				     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 @@ The dma_buf buffer sharing API usage contains the following steps:
    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 @@ to request use of buffer for allocation.
    "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.

Documentation/kdump/kdump.txt

@@ -18,7 +18,7 @@ memory image to a dump file on the local disk, or across the network to
 a remote system.
 
 Kdump and kexec are currently supported on the x86, x86_64, ppc64, ia64,
-and s390x architectures.
+s390x and arm architectures.
 
 When the system kernel boots, it reserves a small section of memory for
 the dump-capture kernel. This ensures that ongoing Direct Memory Access
@@ -112,7 +112,7 @@ There are two possible methods of using Kdump.
 2) Or use the system kernel binary itself as dump-capture kernel and there is
    no need to build a separate dump-capture kernel. This is possible
    only with the architectures which support a relocatable kernel. As
-   of today, i386, x86_64, ppc64 and ia64 architectures support relocatable
+   of today, i386, x86_64, ppc64, ia64 and arm architectures support relocatable
    kernel.
 
 Building a relocatable kernel is advantageous from the point of view that
@@ -241,6 +241,13 @@ Dump-capture kernel config options (Arch Dependent, ia64)
   kernel will be aligned to 64Mb, so if the start address is not then
   any space below the alignment point will be wasted.
 
+Dump-capture kernel config options (Arch Dependent, arm)
+----------------------------------------------------------
+
+-   To use a relocatable kernel,
+    Enable "AUTO_ZRELADDR" support under "Boot" options:
+
+    AUTO_ZRELADDR=y
 
 Extended crashkernel syntax
 ===========================
@@ -256,6 +263,10 @@ The syntax is:
     crashkernel=<range1>:<size1>[,<range2>:<size2>,...][@offset]
     range=start-[end]
 
+Please note, on arm, the offset is required.
+    crashkernel=<range1>:<size1>[,<range2>:<size2>,...]@offset
+    range=start-[end]
+
     'start' is inclusive and 'end' is exclusive.
 
 For example:
@@ -296,6 +307,12 @@ Boot into System Kernel
    on the memory consumption of the kdump system. In general this is not
    dependent on the memory size of the production system.
 
+   On arm, use "crashkernel=Y@X". Note that the start address of the kernel
+   will be aligned to 128MiB (0x08000000), so if the start address is not then
+   any space below the alignment point may be overwritten by the dump-capture kernel,
+   which means it is possible that the vmcore is not that precise as expected.
+
+
 Load the Dump-capture Kernel
 ============================
 
@@ -315,7 +332,8 @@ For ia64:
 	- Use vmlinux or vmlinuz.gz
 For s390x:
 	- Use image or bzImage
-
+For arm:
+	- Use zImage
 
 If you are using a uncompressed vmlinux image then use following command
 to load dump-capture kernel.
@@ -331,6 +349,15 @@ to load dump-capture kernel.
    --initrd=<initrd-for-dump-capture-kernel> \
    --append="root=<root-dev> <arch-specific-options>"
 
+If you are using a compressed zImage, then use following command
+to load dump-capture kernel.
+
+   kexec --type zImage -p <dump-capture-kernel-bzImage> \
+   --initrd=<initrd-for-dump-capture-kernel> \
+   --dtb=<dtb-for-dump-capture-kernel> \
+   --append="root=<root-dev> <arch-specific-options>"
+
+
 Please note, that --args-linux does not need to be specified for ia64.
 It is planned to make this a no-op on that architecture, but for now
 it should be omitted
@@ -347,6 +374,9 @@ For ppc64:
 For s390x:
 	"1 maxcpus=1 cgroup_disable=memory"
 
+For arm:
+	"1 maxcpus=1 reset_devices"
+
 Notes on loading the dump-capture kernel:
 
 * By default, the ELF headers are stored in ELF64 format to support

Documentation/this_cpu_ops.txt

@@ -2,26 +2,26 @@ this_cpu operations
 -------------------
 
 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 @@ data specific to the currently executing processor. Only the current
 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 @@ results in a single instruction
 	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 @@ register.
 	(*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 @@ that is of interest.
 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 @@ Takes the offset of a per cpu variable (&x !) and returns the address
 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 @@ If we have an offset to struct s:
 
 	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 @@ if we do not make use of this_cpu ops later to manipulate fields:
 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.
-
-	__this_cpu_inc(x);
-
-Will increment x and will not fallback to code that disables
+disable interrupts. For that purpose the following __this_cpu operations
+are provided.
+
+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.
+
+	__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 @@ with (). The second form also is consistent with the way
 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

MAINTAINERS

@@ -9562,6 +9562,14 @@ S:	Maintained
 F:	Documentation/usb/ohci.txt
 F:	drivers/usb/host/ohci*
 
+USB OVER IP DRIVER
+M:	Valentina Manea <valentina.manea.m@gmail.com>
+M:	Shuah Khan <shuah.kh@samsung.com>
+L:	linux-usb@vger.kernel.org
+S:	Maintained
+F:	drivers/usb/usbip/
+F:	tools/usb/usbip/
+
 USB PEGASUS DRIVER
 M:	Petko Manolov <petkan@nucleusys.com>
 L:	linux-usb@vger.kernel.org

Makefile

 VERSION = 3
 PATCHLEVEL = 17
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
 NAME = Shuffling Zombie Juror
 
 # *DOCUMENTATION*

arch/alpha/include/asm/io.h

@@ -500,10 +500,14 @@ extern inline void writeq(u64 b, volatile void __iomem *addr)
 #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()
 

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

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 */

arch/alpha/kernel/systbls.S

@@ -526,6 +526,9 @@ sys_call_table:
 	.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

arch/arc/mm/cache_arc700.c

@@ -581,6 +581,7 @@ void flush_icache_range(unsigned long kstart, unsigned long kend)
 		tot_sz -= sz;
 	}
 }
+EXPORT_SYMBOL(flush_icache_range);
 
 /*
  * General purpose helper to make I and D cache lines consistent.

arch/arm/Kconfig

@@ -1983,8 +1983,6 @@ config XIP_PHYS_ADDR
 config KEXEC
 	bool "Kexec system call (EXPERIMENTAL)"
 	depends on (!SMP || PM_SLEEP_SMP)
-	select CRYPTO
-	select CRYPTO_SHA256
 	help
 	  kexec is a system call that implements the ability to shutdown your
 	  current kernel, and to start another kernel.  It is like a reboot

arch/arm/boot/dts/am4372.dtsi

@@ -804,7 +804,7 @@ dwc3_1: omap_dwc3@48380000 {
 
 			usb1: usb@48390000 {
 				compatible = "synopsys,dwc3";
-				reg = <0x48390000 0x17000>;
+				reg = <0x48390000 0x10000>;
 				interrupts = <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>;
 				phys = <&usb2_phy1>;
 				phy-names = "usb2-phy";
@@ -826,7 +826,7 @@ dwc3_2: omap_dwc3@483c0000 {
 
 			usb2: usb@483d0000 {
 				compatible = "synopsys,dwc3";
-				reg = <0x483d0000 0x17000>;
+				reg = <0x483d0000 0x10000>;
 				interrupts = <GIC_SPI 174 IRQ_TYPE_LEVEL_HIGH>;
 				phys = <&usb2_phy2>;
 				phy-names = "usb2-phy";

arch/arm/boot/dts/am437x-gp-evm.dts

@@ -260,7 +260,7 @@ &i2c0 {
 	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&i2c0_pins>;
-	clock-frequency = <400000>;
+	clock-frequency = <100000>;
 
 	tps65218: tps65218@24 {
 		reg = <0x24>;
@@ -424,7 +424,7 @@ &gpmc {
 	ranges = <0 0 0 0x01000000>;	/* minimum GPMC partition = 16MB */
 	nand@0,0 {
 		reg = <0 0 4>;		/* device IO registers */
-		ti,nand-ecc-opt = "bch8";
+		ti,nand-ecc-opt = "bch16";
 		ti,elm-id = <&elm>;
 		nand-bus-width = <8>;
 		gpmc,device-width = <1>;
@@ -443,8 +443,6 @@ nand@0,0 {
 		gpmc,rd-cycle-ns = <40>;
 		gpmc,wr-cycle-ns = <40>;
 		gpmc,wait-pin = <0>;
-		gpmc,wait-on-read;
-		gpmc,wait-on-write;
 		gpmc,bus-turnaround-ns = <0>;
 		gpmc,cycle2cycle-delay-ns = <0>;
 		gpmc,clk-activation-ns = <0>;

arch/arm/boot/dts/am43x-epos-evm.dts

@@ -435,13 +435,13 @@ &elm {
 };
 
 &gpmc {
-	status = "okay";
+	status = "okay";	/* Disable QSPI when enabling GPMC (NAND) */
 	pinctrl-names = "default";
 	pinctrl-0 = <&nand_flash_x8>;
 	ranges = <0 0 0x08000000 0x10000000>;	/* CS0: NAND */
 	nand@0,0 {
 		reg = <0 0 0>; /* CS0, offset 0 */
-		ti,nand-ecc-opt = "bch8";
+		ti,nand-ecc-opt = "bch16";
 		ti,elm-id = <&elm>;
 		nand-bus-width = <8>;
 		gpmc,device-width = <1>;
@@ -459,8 +459,7 @@ nand@0,0 {
 		gpmc,access-ns = <30>; /* tCEA + 4*/
 		gpmc,rd-cycle-ns = <40>;
 		gpmc,wr-cycle-ns = <40>;
-		gpmc,wait-on-read = "true";
-		gpmc,wait-on-write = "true";
+		gpmc,wait-pin = <0>;
 		gpmc,bus-turnaround-ns = <0>;
 		gpmc,cycle2cycle-delay-ns = <0>;
 		gpmc,clk-activation-ns = <0>;
@@ -557,7 +556,7 @@ &usb2 {
 };
 
 &qspi {
-	status = "okay";
+	status = "disabled";	/* Disable GPMC (NAND) when enabling QSPI */
 	pinctrl-names = "default";
 	pinctrl-0 = <&qspi1_default>;
 

arch/arm/boot/dts/dra7-evm.dts

@@ -8,6 +8,7 @@
 /dts-v1/;
 
 #include "dra74x.dtsi"
+#include <dt-bindings/gpio/gpio.h>
 
 / {
 	model = "TI DRA742";
@@ -24,9 +25,29 @@ mmc2_3v3: fixedregulator-mmc2 {
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
 	};
+
+	vtt_fixed: fixedregulator-vtt {
+		compatible = "regulator-fixed";
+		regulator-name = "vtt_fixed";
+		regulator-min-microvolt = <1350000>;
+		regulator-max-microvolt = <1350000>;
+		regulator-always-on;
+		regulator-boot-on;
+		enable-active-high;
+		gpio = <&gpio7 11 GPIO_ACTIVE_HIGH>;
+	};
 };
 
 &dra7_pmx_core {
+	pinctrl-names = "default";
+	pinctrl-0 = <&vtt_pin>;
+
+	vtt_pin: pinmux_vtt_pin {
+		pinctrl-single,pins = <
+			0x3b4 (PIN_OUTPUT | MUX_MODE14) /* spi1_cs1.gpio7_11 */
+		>;
+	};
+
 	i2c1_pins: pinmux_i2c1_pins {
 		pinctrl-single,pins = <
 			0x400 (PIN_INPUT | MUX_MODE0) /* i2c1_sda */
@@ -43,20 +64,19 @@ i2c2_pins: pinmux_i2c2_pins {
 
 	i2c3_pins: pinmux_i2c3_pins {
 		pinctrl-single,pins = <
-			0x410 (PIN_INPUT | MUX_MODE0) /* i2c3_sda */
-			0x414 (PIN_INPUT | MUX_MODE0) /* i2c3_scl */
+			0x288 (PIN_INPUT | MUX_MODE9) /* gpio6_14.i2c3_sda */
+			0x28c (PIN_INPUT | MUX_MODE9) /* gpio6_15.i2c3_scl */
 		>;
 	};
 
 	mcspi1_pins: pinmux_mcspi1_pins {
 		pinctrl-single,pins = <
-			0x3a4 (PIN_INPUT | MUX_MODE0) /* spi2_clk */
-			0x3a8 (PIN_INPUT | MUX_MODE0) /* spi2_d1 */
-			0x3ac (PIN_INPUT | MUX_MODE0) /* spi2_d0 */
-			0x3b0 (PIN_INPUT_SLEW | MUX_MODE0) /* spi2_cs0 */
-			0x3b4 (PIN_INPUT_SLEW | MUX_MODE0) /* spi2_cs1 */
-			0x3b8 (PIN_INPUT_SLEW | MUX_MODE6) /* spi2_cs2 */
-			0x3bc (PIN_INPUT_SLEW | MUX_MODE6) /* spi2_cs3 */
+			0x3a4 (PIN_INPUT | MUX_MODE0) /* spi1_sclk */
+			0x3a8 (PIN_INPUT | MUX_MODE0) /* spi1_d1 */
+			0x3ac (PIN_INPUT | MUX_MODE0) /* spi1_d0 */
+			0x3b0 (PIN_INPUT_SLEW | MUX_MODE0) /* spi1_cs0 */
+			0x3b8 (PIN_INPUT_SLEW | MUX_MODE6) /* spi1_cs2.hdmi1_hpd */
+			0x3bc (PIN_INPUT_SLEW | MUX_MODE6) /* spi1_cs3.hdmi1_cec */
 		>;
 	};
 
@@ -284,7 +304,7 @@ &i2c3 {
 	status = "okay";
 	pinctrl-names = "default";
 	pinctrl-0 = <&i2c3_pins>;
-	clock-frequency = <3400000>;
+	clock-frequency = <400000>;
 };
 
 &mcspi1 {
@@ -483,7 +503,7 @@ partition@6 {
 			reg = <0x001c0000 0x00020000>;
 		};
 		partition@7 {
-			label = "NAND.u-boot-env";
+			label = "NAND.u-boot-env.backup1";
 			reg = <0x001e0000 0x00020000>;
 		};
 		partition@8 {
@@ -504,3 +524,8 @@ &usb2_phy1 {
 &usb2_phy2 {
 	phy-supply = <&ldousb_reg>;
 };
+
+&gpio7 {
+	ti,no-reset-on-init;
+	ti,no-idle-on-init;
+};

arch/arm/boot/dts/omap3-n900.dts

@@ -353,7 +353,7 @@ twl_audio: audio {
 	};
 
 	twl_power: power {
-		compatible = "ti,twl4030-power-n900";
+		compatible = "ti,twl4030-power-n900", "ti,twl4030-power-idle-osc-off";
 		ti,use_poweroff;
 	};
 };

arch/arm/boot/dts/omap3xxx-clocks.dtsi

@@ -467,6 +467,7 @@ dpll4_m5x2_ck: dpll4_m5x2_ck {
 		ti,bit-shift = <0x1e>;
 		reg = <0x0d00>;
 		ti,set-bit-to-disable;
+		ti,set-rate-parent;
 	};
 
 	dpll4_m6_ck: dpll4_m6_ck {

arch/arm/include/asm/cacheflush.h

@@ -472,7 +472,6 @@ static inline void __sync_cache_range_r(volatile void *p, size_t size)
 	"mcr	p15, 0, r0, c1, c0, 0	@ set SCTLR \n\t" \
 	"isb	\n\t" \
 	"bl	v7_flush_dcache_"__stringify(level)" \n\t" \
-	"clrex	\n\t" \
 	"mrc	p15, 0, r0, c1, c0, 1	@ get ACTLR \n\t" \
 	"bic	r0, r0, #(1 << 6)	@ disable local coherency \n\t" \
 	"mcr	p15, 0, r0, c1, c0, 1	@ set ACTLR \n\t" \