Merge branch 'for-linus' of git://git.linaro.org/people/rmk/linux-arm

Pull ARM updates (part one) from Russell King:

 - MMC patches from Ulf Hansson and Pawel Moll.  These add support for
   DDR mode and the latest variant found on ARM Versatile Express, as
   well as a number of cleanups.

 - A fix for to improve the behaviour of ARMs sched_clock()

 - Changes to the ARM ioremap() code.  I'm not convinced with the
   primary arguments for this, but it's been around for a while, and
   people seem happy with it - and the "other" justification for this is
   at

      http://lkml.org/lkml/2012/12/6/184

 - Add SCHED_HRTICK to ARMs Kconfig

 - Making the ARM SHA/AES code Thumb-2 compatible

 - A collection of other small updates.

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (26 commits)
  ARM: add SCHED_HRTICK config option
  ARM: 7650/1: mm: replace direct access to mm->context.id with new macro
  ARM: 7649/1: mm: mm->context.id fix for big-endian
  ARM: 7648/1: pci: Allow passing per-controller private data
  ARM: 7647/1: pci: Keep pci_common_init() around after init
  ARM: fix warnings introduced by previous patch
  ARM: 7646/1: mm: use static_vm for managing static mapped areas
  ARM: 7645/1: ioremap: introduce an infrastructure for static mapped area
  ARM: 7644/1: vmregion: remove vmregion code entirely
  MAINTAINERS: Re-assert MMCI driver maintainer status
  MAINTAINERS: add additional file for MMCI driver
  MAINTAINERS: add maintainer entry for AMBA serial drivers
  ARM: 7637/1: memory: use SZ_ constants for defining the virtual memory layout
  ARM: 7643/1: sched: correct update_sched_clock()
  ARM: 7635/1: versatile: fix the PCI IRQ regression
  ARM: 7639/1: cache-l2x0: add missed dummy outer_resume entry
  ARM: 7630/1: mmc: mmci: Fixup and cleanup code for DMA handling
  ARM: 7632/1: spinlock: avoid exclusive accesses on unlock() path
  ARM: 7631/1: mmc: mmci: Add new VE MMCI variant
  ARM: 7623/1: mmc: mmci: Fixup clock gating when freq is 0 for ST-variants
  ...

MAINTAINERS

@@ -670,8 +670,16 @@ F:	drivers/input/serio/ambakmi.*
 F:	include/linux/amba/kmi.h
 
 ARM PRIMECELL MMCI PL180/1 DRIVER
-S:	Orphan
+M:	Russell King <linux@arm.linux.org.uk>
+S:	Maintained
 F:	drivers/mmc/host/mmci.*
+F:	include/linux/amba/mmci.h
+
+ARM PRIMECELL UART PL010 AND PL011 DRIVERS
+M:	Russell King <linux@arm.linux.org.uk>
+S:	Maintained
+F:	drivers/tty/serial/amba-pl01*.c
+F:	include/linux/amba/serial.h
 
 ARM PRIMECELL BUS SUPPORT
 M:	Russell King <linux@arm.linux.org.uk>

arch/arm/Kconfig

@@ -1654,6 +1654,9 @@ config HZ
 	default SHMOBILE_TIMER_HZ if ARCH_SHMOBILE
 	default 100
 
+config SCHED_HRTICK
+	def_bool HIGH_RES_TIMERS
+
 config THUMB2_KERNEL
 	bool "Compile the kernel in Thumb-2 mode"
 	depends on CPU_V7 && !CPU_V6 && !CPU_V6K

arch/arm/crypto/aes-armv4.S

@@ -34,8 +34,9 @@
 @ A little glue here to select the correct code below for the ARM CPU
 @ that is being targetted.
 
+#include <linux/linkage.h>
+
 .text
-.code	32
 
 .type	AES_Te,%object
 .align	5
@@ -145,10 +146,8 @@ AES_Te:
 
 @ void AES_encrypt(const unsigned char *in, unsigned char *out,
 @ 		 const AES_KEY *key) {
-.global AES_encrypt
-.type   AES_encrypt,%function
 .align	5
-AES_encrypt:
+ENTRY(AES_encrypt)
 	sub	r3,pc,#8		@ AES_encrypt
 	stmdb   sp!,{r1,r4-r12,lr}
 	mov	r12,r0		@ inp
@@ -239,15 +238,8 @@ AES_encrypt:
 	strb	r6,[r12,#14]
 	strb	r3,[r12,#15]
 #endif
-#if __ARM_ARCH__>=5
 	ldmia	sp!,{r4-r12,pc}
-#else
-	ldmia   sp!,{r4-r12,lr}
-	tst	lr,#1
-	moveq	pc,lr			@ be binary compatible with V4, yet
-	.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
-#endif
-.size	AES_encrypt,.-AES_encrypt
+ENDPROC(AES_encrypt)
 
 .type   _armv4_AES_encrypt,%function
 .align	2
@@ -386,10 +378,8 @@ _armv4_AES_encrypt:
 	ldr	pc,[sp],#4		@ pop and return
 .size	_armv4_AES_encrypt,.-_armv4_AES_encrypt
 
-.global private_AES_set_encrypt_key
-.type   private_AES_set_encrypt_key,%function
 .align	5
-private_AES_set_encrypt_key:
+ENTRY(private_AES_set_encrypt_key)
 _armv4_AES_set_encrypt_key:
 	sub	r3,pc,#8		@ AES_set_encrypt_key
 	teq	r0,#0
@@ -658,15 +648,11 @@ _armv4_AES_set_encrypt_key:
 
 .Ldone:	mov	r0,#0
 	ldmia   sp!,{r4-r12,lr}
-.Labrt:	tst	lr,#1
-	moveq	pc,lr			@ be binary compatible with V4, yet
-	.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
-.size	private_AES_set_encrypt_key,.-private_AES_set_encrypt_key
+.Labrt:	mov	pc,lr
+ENDPROC(private_AES_set_encrypt_key)
 
-.global private_AES_set_decrypt_key
-.type   private_AES_set_decrypt_key,%function
 .align	5
-private_AES_set_decrypt_key:
+ENTRY(private_AES_set_decrypt_key)
 	str	lr,[sp,#-4]!            @ push lr
 #if 0
 	@ kernel does both of these in setkey so optimise this bit out by
@@ -748,15 +734,8 @@ private_AES_set_decrypt_key:
 	bne	.Lmix
 
 	mov	r0,#0
-#if __ARM_ARCH__>=5
 	ldmia	sp!,{r4-r12,pc}
-#else
-	ldmia   sp!,{r4-r12,lr}
-	tst	lr,#1
-	moveq	pc,lr			@ be binary compatible with V4, yet
-	.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
-#endif
-.size	private_AES_set_decrypt_key,.-private_AES_set_decrypt_key
+ENDPROC(private_AES_set_decrypt_key)
 
 .type	AES_Td,%object
 .align	5
@@ -862,10 +841,8 @@ AES_Td:
 
 @ void AES_decrypt(const unsigned char *in, unsigned char *out,
 @ 		 const AES_KEY *key) {
-.global AES_decrypt
-.type   AES_decrypt,%function
 .align	5
-AES_decrypt:
+ENTRY(AES_decrypt)
 	sub	r3,pc,#8		@ AES_decrypt
 	stmdb   sp!,{r1,r4-r12,lr}
 	mov	r12,r0		@ inp
@@ -956,15 +933,8 @@ AES_decrypt:
 	strb	r6,[r12,#14]
 	strb	r3,[r12,#15]
 #endif
-#if __ARM_ARCH__>=5
 	ldmia	sp!,{r4-r12,pc}
-#else
-	ldmia   sp!,{r4-r12,lr}
-	tst	lr,#1
-	moveq	pc,lr			@ be binary compatible with V4, yet
-	.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
-#endif
-.size	AES_decrypt,.-AES_decrypt
+ENDPROC(AES_decrypt)
 
 .type   _armv4_AES_decrypt,%function
 .align	2
@@ -1064,7 +1034,9 @@ _armv4_AES_decrypt:
 	and	r9,lr,r1,lsr#8
 
 	ldrb	r7,[r10,r7]		@ Td4[s1>>0]
-	ldrb	r1,[r10,r1,lsr#24]	@ Td4[s1>>24]
+ ARM(	ldrb	r1,[r10,r1,lsr#24]  )	@ Td4[s1>>24]
+ THUMB(	add	r1,r10,r1,lsr#24    ) 	@ Td4[s1>>24]
+ THUMB(	ldrb	r1,[r1]		    )
 	ldrb	r8,[r10,r8]		@ Td4[s1>>16]
 	eor	r0,r7,r0,lsl#24
 	ldrb	r9,[r10,r9]		@ Td4[s1>>8]
@@ -1077,7 +1049,9 @@ _armv4_AES_decrypt:
 	ldrb	r8,[r10,r8]		@ Td4[s2>>0]
 	and	r9,lr,r2,lsr#16
 
-	ldrb	r2,[r10,r2,lsr#24]	@ Td4[s2>>24]
+ ARM(	ldrb	r2,[r10,r2,lsr#24]  )	@ Td4[s2>>24]
+ THUMB(	add	r2,r10,r2,lsr#24    )	@ Td4[s2>>24]
+ THUMB(	ldrb	r2,[r2]		    )
 	eor	r0,r0,r7,lsl#8
 	ldrb	r9,[r10,r9]		@ Td4[s2>>16]
 	eor	r1,r8,r1,lsl#16
@@ -1090,7 +1064,9 @@ _armv4_AES_decrypt:
 	and	r9,lr,r3		@ i2
 
 	ldrb	r9,[r10,r9]		@ Td4[s3>>0]
-	ldrb	r3,[r10,r3,lsr#24]	@ Td4[s3>>24]
+ ARM(	ldrb	r3,[r10,r3,lsr#24]  )	@ Td4[s3>>24]
+ THUMB(	add	r3,r10,r3,lsr#24    )	@ Td4[s3>>24]
+ THUMB(	ldrb	r3,[r3]		    )
 	eor	r0,r0,r7,lsl#16
 	ldr	r7,[r11,#0]
 	eor	r1,r1,r8,lsl#8

arch/arm/crypto/sha1-armv4-large.S

@@ -51,13 +51,12 @@
 @ Profiler-assisted and platform-specific optimization resulted in 10%
 @ improvement on Cortex A8 core and 12.2 cycles per byte.
 
-.text
+#include <linux/linkage.h>
 
-.global	sha1_block_data_order
-.type	sha1_block_data_order,%function
+.text
 
 .align	2
-sha1_block_data_order:
+ENTRY(sha1_block_data_order)
 	stmdb	sp!,{r4-r12,lr}
 	add	r2,r1,r2,lsl#6	@ r2 to point at the end of r1
 	ldmia	r0,{r3,r4,r5,r6,r7}
@@ -194,7 +193,7 @@ sha1_block_data_order:
 	eor	r10,r10,r7,ror#2		@ F_00_19(B,C,D)
 	str	r9,[r14,#-4]!
 	add	r3,r3,r10			@ E+=F_00_19(B,C,D)
-	teq	r14,sp
+	cmp	r14,sp
 	bne	.L_00_15		@ [((11+4)*5+2)*3]
 #if __ARM_ARCH__<7
 	ldrb	r10,[r1,#2]
@@ -374,7 +373,9 @@ sha1_block_data_order:
 						@ F_xx_xx
 	add	r3,r3,r9			@ E+=X[i]
 	add	r3,r3,r10			@ E+=F_20_39(B,C,D)
-	teq	r14,sp			@ preserve carry
+ ARM(	teq	r14,sp		)	@ preserve carry
+ THUMB(	mov	r11,sp		)
+ THUMB(	teq	r14,r11		)	@ preserve carry
 	bne	.L_20_39_or_60_79	@ [+((12+3)*5+2)*4]
 	bcs	.L_done			@ [+((12+3)*5+2)*4], spare 300 bytes
 
@@ -466,7 +467,7 @@ sha1_block_data_order:
 	add	r3,r3,r9			@ E+=X[i]
 	add	r3,r3,r10			@ E+=F_40_59(B,C,D)
 	add	r3,r3,r11,ror#2
-	teq	r14,sp
+	cmp	r14,sp
 	bne	.L_40_59		@ [+((12+5)*5+2)*4]
 
 	ldr	r8,.LK_60_79
@@ -485,19 +486,12 @@ sha1_block_data_order:
 	teq	r1,r2
 	bne	.Lloop			@ [+18], total 1307
 
-#if __ARM_ARCH__>=5
 	ldmia	sp!,{r4-r12,pc}
-#else
-	ldmia	sp!,{r4-r12,lr}
-	tst	lr,#1
-	moveq	pc,lr			@ be binary compatible with V4, yet
-	.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
-#endif
 .align	2
 .LK_00_19:	.word	0x5a827999
 .LK_20_39:	.word	0x6ed9eba1
 .LK_40_59:	.word	0x8f1bbcdc
 .LK_60_79:	.word	0xca62c1d6
-.size	sha1_block_data_order,.-sha1_block_data_order
+ENDPROC(sha1_block_data_order)
 .asciz	"SHA1 block transform for ARMv4, CRYPTOGAMS by <appro@openssl.org>"
 .align	2

arch/arm/include/asm/mach/pci.h

@@ -23,6 +23,7 @@ struct hw_pci {
 #endif
 	struct pci_ops	*ops;
 	int		nr_controllers;
+	void		**private_data;
 	int		(*setup)(int nr, struct pci_sys_data *);
 	struct pci_bus *(*scan)(int nr, struct pci_sys_data *);
 	void		(*preinit)(void);

arch/arm/include/asm/memory.h

@@ -36,23 +36,23 @@
  * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area
  */
 #define PAGE_OFFSET		UL(CONFIG_PAGE_OFFSET)
-#define TASK_SIZE		(UL(CONFIG_PAGE_OFFSET) - UL(0x01000000))
+#define TASK_SIZE		(UL(CONFIG_PAGE_OFFSET) - UL(SZ_16M))
 #define TASK_UNMAPPED_BASE	ALIGN(TASK_SIZE / 3, SZ_16M)
 
 /*
  * The maximum size of a 26-bit user space task.
  */
-#define TASK_SIZE_26		UL(0x04000000)
+#define TASK_SIZE_26		(UL(1) << 26)
 
 /*
  * The module space lives between the addresses given by TASK_SIZE
  * and PAGE_OFFSET - it must be within 32MB of the kernel text.
  */
 #ifndef CONFIG_THUMB2_KERNEL
-#define MODULES_VADDR		(PAGE_OFFSET - 16*1024*1024)
+#define MODULES_VADDR		(PAGE_OFFSET - SZ_16M)
 #else
 /* smaller range for Thumb-2 symbols relocation (2^24)*/
-#define MODULES_VADDR		(PAGE_OFFSET - 8*1024*1024)
+#define MODULES_VADDR		(PAGE_OFFSET - SZ_8M)
 #endif
 
 #if TASK_SIZE > MODULES_VADDR

arch/arm/include/asm/outercache.h

@@ -92,6 +92,7 @@ static inline void outer_flush_range(phys_addr_t start, phys_addr_t end)
 static inline void outer_flush_all(void) { }
 static inline void outer_inv_all(void) { }
 static inline void outer_disable(void) { }
+static inline void outer_resume(void) { }
 
 #endif
 

arch/arm/include/asm/spinlock.h

@@ -119,22 +119,8 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
-	unsigned long tmp;
-	u32 slock;
-
 	smp_mb();
-
-	__asm__ __volatile__(
-"	mov	%1, #1\n"
-"1:	ldrex	%0, [%2]\n"
-"	uadd16	%0, %0, %1\n"
-"	strex	%1, %0, [%2]\n"
-"	teq	%1, #0\n"
-"	bne	1b"
-	: "=&r" (slock), "=&r" (tmp)
-	: "r" (&lock->slock)
-	: "cc");
-
+	lock->tickets.owner++;
 	dsb_sev();
 }
 

arch/arm/kernel/bios32.c

@@ -413,7 +413,7 @@ static int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	return irq;
 }
 
-static int __init pcibios_init_resources(int busnr, struct pci_sys_data *sys)
+static int pcibios_init_resources(int busnr, struct pci_sys_data *sys)
 {
 	int ret;
 	struct pci_host_bridge_window *window;
@@ -445,7 +445,7 @@ static int __init pcibios_init_resources(int busnr, struct pci_sys_data *sys)
 	return 0;
 }
 
-static void __init pcibios_init_hw(struct hw_pci *hw, struct list_head *head)
+static void pcibios_init_hw(struct hw_pci *hw, struct list_head *head)
 {
 	struct pci_sys_data *sys = NULL;
 	int ret;
@@ -464,6 +464,9 @@ static void __init pcibios_init_hw(struct hw_pci *hw, struct list_head *head)
 		sys->map_irq = hw->map_irq;
 		INIT_LIST_HEAD(&sys->resources);
 
+		if (hw->private_data)
+			sys->private_data = hw->private_data[nr];
+
 		ret = hw->setup(nr, sys);
 
 		if (ret > 0) {
@@ -493,7 +496,7 @@ static void __init pcibios_init_hw(struct hw_pci *hw, struct list_head *head)
 	}
 }
 
-void __init pci_common_init(struct hw_pci *hw)
+void pci_common_init(struct hw_pci *hw)
 {
 	struct pci_sys_data *sys;
 	LIST_HEAD(head);

arch/arm/kernel/sched_clock.c

@@ -93,11 +93,11 @@ static void notrace update_sched_clock(void)
 	 * detectable in cyc_to_fixed_sched_clock().
 	 */
 	raw_local_irq_save(flags);
-	cd.epoch_cyc = cyc;
+	cd.epoch_cyc_copy = cyc;
 	smp_wmb();
 	cd.epoch_ns = ns;
 	smp_wmb();
-	cd.epoch_cyc_copy = cyc;
+	cd.epoch_cyc = cyc;
 	raw_local_irq_restore(flags);
 }
 

arch/arm/kernel/smp.c

@@ -125,18 +125,6 @@ void __init smp_init_cpus(void)
 		smp_ops.smp_init_cpus();
 }
 
-static void __init platform_smp_prepare_cpus(unsigned int max_cpus)
-{
-	if (smp_ops.smp_prepare_cpus)
-		smp_ops.smp_prepare_cpus(max_cpus);
-}
-
-static void __cpuinit platform_secondary_init(unsigned int cpu)
-{
-	if (smp_ops.smp_secondary_init)
-		smp_ops.smp_secondary_init(cpu);
-}
-
 int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
 	if (smp_ops.smp_boot_secondary)
@@ -154,12 +142,6 @@ static int platform_cpu_kill(unsigned int cpu)
 	return 1;
 }
 
-static void platform_cpu_die(unsigned int cpu)
-{
-	if (smp_ops.cpu_die)
-		smp_ops.cpu_die(cpu);
-}
-
 static int platform_cpu_disable(unsigned int cpu)
 {
 	if (smp_ops.cpu_disable)
@@ -257,7 +239,8 @@ void __ref cpu_die(void)
 	 * actual CPU shutdown procedure is at least platform (if not
 	 * CPU) specific.
 	 */
-	platform_cpu_die(cpu);
+	if (smp_ops.cpu_die)
+		smp_ops.cpu_die(cpu);
 
 	/*
 	 * Do not return to the idle loop - jump back to the secondary
@@ -324,7 +307,8 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	/*
 	 * Give the platform a chance to do its own initialisation.
 	 */
-	platform_secondary_init(cpu);
+	if (smp_ops.smp_secondary_init)
+		smp_ops.smp_secondary_init(cpu);
 
 	notify_cpu_starting(cpu);
 
@@ -399,8 +383,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 		/*
 		 * Initialise the present map, which describes the set of CPUs
 		 * actually populated at the present time. A platform should
-		 * re-initialize the map in platform_smp_prepare_cpus() if
-		 * present != possible (e.g. physical hotplug).
+		 * re-initialize the map in the platforms smp_prepare_cpus()
+		 * if present != possible (e.g. physical hotplug).
 		 */
 		init_cpu_present(cpu_possible_mask);
 
@@ -408,7 +392,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 		 * Initialise the SCU if there are more than one CPU
 		 * and let them know where to start.
 		 */
-		platform_smp_prepare_cpus(max_cpus);
+		if (smp_ops.smp_prepare_cpus)
+			smp_ops.smp_prepare_cpus(max_cpus);
 	}
 }
 

arch/arm/mach-versatile/core.c

@@ -36,6 +36,7 @@
 #include <linux/gfp.h>
 #include <linux/clkdev.h>
 #include <linux/mtd/physmap.h>
+#include <linux/bitops.h>
 
 #include <asm/irq.h>
 #include <asm/hardware/arm_timer.h>
@@ -65,16 +66,28 @@
 #define VA_VIC_BASE		__io_address(VERSATILE_VIC_BASE)
 #define VA_SIC_BASE		__io_address(VERSATILE_SIC_BASE)
 
+/* These PIC IRQs are valid in each configuration */
+#define PIC_VALID_ALL	BIT(SIC_INT_KMI0) | BIT(SIC_INT_KMI1) | \
+			BIT(SIC_INT_SCI3) | BIT(SIC_INT_UART3) | \
+			BIT(SIC_INT_CLCD) | BIT(SIC_INT_TOUCH) | \
+			BIT(SIC_INT_KEYPAD) | BIT(SIC_INT_DoC) | \
+			BIT(SIC_INT_USB) | BIT(SIC_INT_PCI0) | \
+			BIT(SIC_INT_PCI1) | BIT(SIC_INT_PCI2) | \
+			BIT(SIC_INT_PCI3)
 #if 1
 #define IRQ_MMCI0A	IRQ_VICSOURCE22
 #define IRQ_AACI	IRQ_VICSOURCE24
 #define IRQ_ETH		IRQ_VICSOURCE25
 #define PIC_MASK	0xFFD00000
+#define PIC_VALID	PIC_VALID_ALL
 #else
 #define IRQ_MMCI0A	IRQ_SIC_MMCI0A
 #define IRQ_AACI	IRQ_SIC_AACI
 #define IRQ_ETH		IRQ_SIC_ETH
 #define PIC_MASK	0
+#define PIC_VALID	PIC_VALID_ALL | BIT(SIC_INT_MMCI0A) | \
+			BIT(SIC_INT_MMCI1A) | BIT(SIC_INT_AACI) | \
+			BIT(SIC_INT_ETH)
 #endif
 
 /* Lookup table for finding a DT node that represents the vic instance */
@@ -102,7 +115,7 @@ void __init versatile_init_irq(void)
 					      VERSATILE_SIC_BASE);
 
 	fpga_irq_init(VA_SIC_BASE, "SIC", IRQ_SIC_START,
-		IRQ_VICSOURCE31, ~PIC_MASK, np);
+		IRQ_VICSOURCE31, PIC_VALID, np);
 
 	/*
 	 * Interrupts on secondary controller from 0 to 8 are routed to

arch/arm/mach-versatile/pci.c

@@ -23,6 +23,7 @@
 #include <linux/io.h>
 
 #include <mach/hardware.h>
+#include <mach/irqs.h>
 #include <asm/irq.h>
 #include <asm/mach/pci.h>
 
@@ -327,12 +328,12 @@ static int __init versatile_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	int irq;
 
 	/* slot,  pin,	irq
-	 *  24     1     27
-	 *  25     1     28
-	 *  26     1     29
-	 *  27     1     30
+	 *  24     1     IRQ_SIC_PCI0
+	 *  25     1     IRQ_SIC_PCI1
+	 *  26     1     IRQ_SIC_PCI2
+	 *  27     1     IRQ_SIC_PCI3
 	 */
-	irq = 27 + ((slot - 24 + pin - 1) & 3);
+	irq = IRQ_SIC_PCI0 + ((slot - 24 + pin - 1) & 3);
 
 	return irq;
 }

arch/arm/mm/Makefile

@@ -6,7 +6,7 @@ obj-y				:= dma-mapping.o extable.o fault.o init.o \
 				   iomap.o
 
 obj-$(CONFIG_MMU)		+= fault-armv.o flush.o idmap.o ioremap.o \
-				   mmap.o pgd.o mmu.o vmregion.o
+				   mmap.o pgd.o mmu.o
 
 ifneq ($(CONFIG_MMU),y)
 obj-y				+= nommu.o

arch/arm/mm/context.c

@@ -34,6 +34,9 @@
  * The ASID is used to tag entries in the CPU caches and TLBs.
  * The context ID is used by debuggers and trace logic, and
  * should be unique within all running processes.
+ *
+ * In big endian operation, the two 32 bit words are swapped if accesed by
+ * non 64-bit operations.
  */
 #define ASID_FIRST_VERSION	(1ULL << ASID_BITS)
 #define NUM_USER_ASIDS		(ASID_FIRST_VERSION - 1)

arch/arm/mm/ioremap.c

@@ -39,6 +39,70 @@
 #include <asm/mach/pci.h>
 #include "mm.h"
 
+
+LIST_HEAD(static_vmlist);
+
+static struct static_vm *find_static_vm_paddr(phys_addr_t paddr,
+			size_t size, unsigned int mtype)
+{
+	struct static_vm *svm;
+	struct vm_struct *vm;
+
+	list_for_each_entry(svm, &static_vmlist, list) {
+		vm = &svm->vm;
+		if (!(vm->flags & VM_ARM_STATIC_MAPPING))
+			continue;
+		if ((vm->flags & VM_ARM_MTYPE_MASK) != VM_ARM_MTYPE(mtype))
+			continue;
+
+		if (vm->phys_addr > paddr ||
+			paddr + size - 1 > vm->phys_addr + vm->size - 1)
+			continue;
+
+		return svm;
+	}
+
+	return NULL;
+}
+
+struct static_vm *find_static_vm_vaddr(void *vaddr)
+{
+	struct static_vm *svm;
+	struct vm_struct *vm;
+
+	list_for_each_entry(svm, &static_vmlist, list) {
+		vm = &svm->vm;
+
+		/* static_vmlist is ascending order */
+		if (vm->addr > vaddr)
+			break;
+
+		if (vm->addr <= vaddr && vm->addr + vm->size > vaddr)
+			return svm;
+	}
+
+	return NULL;
+}
+
+void __init add_static_vm_early(struct static_vm *svm)
+{
+	struct static_vm *curr_svm;
+	struct vm_struct *vm;
+	void *vaddr;
+
+	vm = &svm->vm;
+	vm_area_add_early(vm);
+	vaddr = vm->addr;
+
+	list_for_each_entry(curr_svm, &static_vmlist, list) {
+		vm = &curr_svm->vm;
+
+		if (vm->addr > vaddr)
+			break;
+	}
+	list_add_tail(&svm->list, &curr_svm->list);
+}
+
 int ioremap_page(unsigned long virt, unsigned long phys,
 		 const struct mem_type *mtype)
 {
@@ -197,13 +261,14 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 	const struct mem_type *type;
 	int err;
 	unsigned long addr;
- 	struct vm_struct * area;
+	struct vm_struct *area;
+	phys_addr_t paddr = __pfn_to_phys(pfn);
 
 #ifndef CONFIG_ARM_LPAE
 	/*
 	 * High mappings must be supersection aligned
 	 */
-	if (pfn >= 0x100000 && (__pfn_to_phys(pfn) & ~SUPERSECTION_MASK))
+	if (pfn >= 0x100000 && (paddr & ~SUPERSECTION_MASK))
 		return NULL;
 #endif
 
@@ -219,24 +284,16 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 	/*
 	 * Try to reuse one of the static mapping whenever possible.
 	 */
-	read_lock(&vmlist_lock);
-	for (area = vmlist; area; area = area->next) {
-		if (!size || (sizeof(phys_addr_t) == 4 && pfn >= 0x100000))
-			break;
-		if (!(area->flags & VM_ARM_STATIC_MAPPING))
-			continue;
-		if ((area->flags & VM_ARM_MTYPE_MASK) != VM_ARM_MTYPE(mtype))
-			continue;
-		if (__phys_to_pfn(area->phys_addr) > pfn ||
-		    __pfn_to_phys(pfn) + size-1 > area->phys_addr + area->size-1)
-			continue;
-		/* we can drop the lock here as we know *area is static */
-		read_unlock(&vmlist_lock);
-		addr = (unsigned long)area->addr;
-		addr += __pfn_to_phys(pfn) - area->phys_addr;
-		return (void __iomem *) (offset + addr);
+	if (size && !(sizeof(phys_addr_t) == 4 && pfn >= 0x100000)) {
+		struct static_vm *svm;
+
+		svm = find_static_vm_paddr(paddr, size, mtype);
+		if (svm) {
+			addr = (unsigned long)svm->vm.addr;
+			addr += paddr - svm->vm.phys_addr;
+			return (void __iomem *) (offset + addr);
+		}
 	}
-	read_unlock(&vmlist_lock);
 
 	/*
 	 * Don't allow RAM to be mapped - this causes problems with ARMv6+
@@ -248,21 +305,21 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
  	if (!area)
  		return NULL;
  	addr = (unsigned long)area->addr;
-	area->phys_addr = __pfn_to_phys(pfn);
+	area->phys_addr = paddr;
 
 #if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
 	if (DOMAIN_IO == 0 &&
 	    (((cpu_architecture() >= CPU_ARCH_ARMv6) && (get_cr() & CR_XP)) ||
 	       cpu_is_xsc3()) && pfn >= 0x100000 &&
-	       !((__pfn_to_phys(pfn) | size | addr) & ~SUPERSECTION_MASK)) {
+	       !((paddr | size | addr) & ~SUPERSECTION_MASK)) {
 		area->flags |= VM_ARM_SECTION_MAPPING;
 		err = remap_area_supersections(addr, pfn, size, type);
-	} else if (!((__pfn_to_phys(pfn) | size | addr) & ~PMD_MASK)) {
+	} else if (!((paddr | size | addr) & ~PMD_MASK)) {
 		area->flags |= VM_ARM_SECTION_MAPPING;
 		err = remap_area_sections(addr, pfn, size, type);
 	} else
 #endif
-		err = ioremap_page_range(addr, addr + size, __pfn_to_phys(pfn),
+		err = ioremap_page_range(addr, addr + size, paddr,
 					 __pgprot(type->prot_pte));
 
 	if (err) {
@@ -346,34 +403,28 @@ __arm_ioremap_exec(unsigned long phys_addr, size_t size, bool cached)
 void __iounmap(volatile void __iomem *io_addr)
 {
 	void *addr = (void *)(PAGE_MASK & (unsigned long)io_addr);
-	struct vm_struct *vm;
+	struct static_vm *svm;
+
+	/* If this is a static mapping, we must leave it alone */
+	svm = find_static_vm_vaddr(addr);
+	if (svm)
+		return;
 
-	read_lock(&vmlist_lock);
-	for (vm = vmlist; vm; vm = vm->next) {
-		if (vm->addr > addr)
-			break;
-		if (!(vm->flags & VM_IOREMAP))
-			continue;
-		/* If this is a static mapping we must leave it alone */
-		if ((vm->flags & VM_ARM_STATIC_MAPPING) &&
-		    (vm->addr <= addr) && (vm->addr + vm->size > addr)) {
-			read_unlock(&vmlist_lock);
-			return;
-		}
 #if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
+	{
+		struct vm_struct *vm;
+
+		vm = find_vm_area(addr);
+
 		/*
 		 * If this is a section based mapping we need to handle it
 		 * specially as the VM subsystem does not know how to handle
 		 * such a beast.
 		 */
-		if ((vm->addr == addr) &&
-		    (vm->flags & VM_ARM_SECTION_MAPPING)) {
+		if (vm && (vm->flags & VM_ARM_SECTION_MAPPING))
 			unmap_area_sections((unsigned long)vm->addr, vm->size);
-			break;
-		}
-#endif
 	}
-	read_unlock(&vmlist_lock);
+#endif
 
 	vunmap(addr);
 }

arch/arm/mm/mm.h

 #ifdef CONFIG_MMU
+#include <linux/list.h>
+#include <linux/vmalloc.h>
 
 /* the upper-most page table pointer */
 extern pmd_t *top_pmd;
@@ -65,6 +67,16 @@ extern void __flush_dcache_page(struct address_space *mapping, struct page *page
 /* consistent regions used by dma_alloc_attrs() */
 #define VM_ARM_DMA_CONSISTENT	0x20000000
 
+
+struct static_vm {
+	struct vm_struct vm;
+	struct list_head list;
+};
+
+extern struct list_head static_vmlist;
+extern struct static_vm *find_static_vm_vaddr(void *vaddr);
+extern __init void add_static_vm_early(struct static_vm *svm);
+
 #endif
 
 #ifdef CONFIG_ZONE_DMA

arch/arm/mm/mmu.c

@@ -757,21 +757,24 @@ void __init iotable_init(struct map_desc *io_desc, int nr)
 {
 	struct map_desc *md;
 	struct vm_struct *vm;
+	struct static_vm *svm;
 
 	if (!nr)
 		return;
 
-	vm = early_alloc_aligned(sizeof(*vm) * nr, __alignof__(*vm));
+	svm = early_alloc_aligned(sizeof(*svm) * nr, __alignof__(*svm));
 
 	for (md = io_desc; nr; md++, nr--) {
 		create_mapping(md);
+
+		vm = &svm->vm;
 		vm->addr = (void *)(md->virtual & PAGE_MASK);
 		vm->size = PAGE_ALIGN(md->length + (md->virtual & ~PAGE_MASK));
 		vm->phys_addr = __pfn_to_phys(md->pfn);
 		vm->flags = VM_IOREMAP | VM_ARM_STATIC_MAPPING;
 		vm->flags |= VM_ARM_MTYPE(md->type);
 		vm->caller = iotable_init;
-		vm_area_add_early(vm++);
+		add_static_vm_early(svm++);
 	}
 }
 
@@ -779,13 +782,16 @@ void __init vm_reserve_area_early(unsigned long addr, unsigned long size,
 				  void *caller)
 {
 	struct vm_struct *vm;
+	struct static_vm *svm;
+
+	svm = early_alloc_aligned(sizeof(*svm), __alignof__(*svm));
 
-	vm = early_alloc_aligned(sizeof(*vm), __alignof__(*vm));
+	vm = &svm->vm;
 	vm->addr = (void *)addr;
 	vm->size = size;
 	vm->flags = VM_IOREMAP | VM_ARM_EMPTY_MAPPING;
 	vm->caller = caller;
-	vm_area_add_early(vm);
+	add_static_vm_early(svm);
 }
 
 #ifndef CONFIG_ARM_LPAE
@@ -810,14 +816,13 @@ static void __init pmd_empty_section_gap(unsigned long addr)
 
 static void __init fill_pmd_gaps(void)
 {
+	struct static_vm *svm;
 	struct vm_struct *vm;
 	unsigned long addr, next = 0;
 	pmd_t *pmd;
 
-	/* we're still single threaded hence no lock needed here */
-	for (vm = vmlist; vm; vm = vm->next) {
-		if (!(vm->flags & (VM_ARM_STATIC_MAPPING | VM_ARM_EMPTY_MAPPING)))
-			continue;
+	list_for_each_entry(svm, &static_vmlist, list) {
+		vm = &svm->vm;
 		addr = (unsigned long)vm->addr;
 		if (addr < next)
 			continue;
@@ -857,19 +862,12 @@ static void __init fill_pmd_gaps(void)
 #if defined(CONFIG_PCI) && !defined(CONFIG_NEED_MACH_IO_H)
 static void __init pci_reserve_io(void)
 {
-	struct vm_struct *vm;
-	unsigned long addr;
+	struct static_vm *svm;
 
-	/* we're still single threaded hence no lock needed here */
-	for (vm = vmlist; vm; vm = vm->next) {
-		if (!(vm->flags & VM_ARM_STATIC_MAPPING))
-			continue;
-		addr = (unsigned long)vm->addr;
-		addr &= ~(SZ_2M - 1);
-		if (addr == PCI_IO_VIRT_BASE)
-			return;
+	svm = find_static_vm_vaddr((void *)PCI_IO_VIRT_BASE);
+	if (svm)
+		return;
 
-	}
 	vm_reserve_area_early(PCI_IO_VIRT_BASE, SZ_2M, pci_reserve_io);
 }
 #else

arch/arm/mm/proc-macros.S

@@ -38,9 +38,14 @@
 
 /*
  * mmid - get context id from mm pointer (mm->context.id)
+ * note, this field is 64bit, so in big-endian the two words are swapped too.
  */
 	.macro	mmid, rd, rn
+#ifdef __ARMEB__
+	ldr	\rd, [\rn, #MM_CONTEXT_ID + 4 ]
+#else
 	ldr	\rd, [\rn, #MM_CONTEXT_ID]
+#endif
 	.endm
 
 /*

arch/arm/mm/proc-v6.S

@@ -101,7 +101,7 @@ ENTRY(cpu_v6_dcache_clean_area)
 ENTRY(cpu_v6_switch_mm)
 #ifdef CONFIG_MMU
 	mov	r2, #0
-	ldr	r1, [r1, #MM_CONTEXT_ID]	@ get mm->context.id
+	mmid	r1, r1				@ get mm->context.id
 	ALT_SMP(orr	r0, r0, #TTB_FLAGS_SMP)
 	ALT_UP(orr	r0, r0, #TTB_FLAGS_UP)
 	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB

arch/arm/mm/proc-v7-2level.S

@@ -40,7 +40,7 @@
 ENTRY(cpu_v7_switch_mm)
 #ifdef CONFIG_MMU
 	mov	r2, #0
-	ldr	r1, [r1, #MM_CONTEXT_ID]	@ get mm->context.id
+	mmid	r1, r1				@ get mm->context.id
 	ALT_SMP(orr	r0, r0, #TTB_FLAGS_SMP)
 	ALT_UP(orr	r0, r0, #TTB_FLAGS_UP)
 #ifdef CONFIG_ARM_ERRATA_430973

arch/arm/mm/proc-v7-3level.S

@@ -47,7 +47,7 @@
  */
 ENTRY(cpu_v7_switch_mm)
 #ifdef CONFIG_MMU
-	ldr	r1, [r1, #MM_CONTEXT_ID]	@ get mm->context.id
+	mmid	r1, r1				@ get mm->context.id
 	and	r3, r1, #0xff
 	mov	r3, r3, lsl #(48 - 32)		@ ASID
 	mcrr	p15, 0, r0, r3, c2		@ set TTB 0

arch/arm/mm/vmregion.c

-#include <linux/fs.h>
-#include <linux/spinlock.h>
-#include <linux/list.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/slab.h>
-
-#include "vmregion.h"
-
-/*
- * VM region handling support.
- *
- * This should become something generic, handling VM region allocations for
- * vmalloc and similar (ioremap, module space, etc).
- *
- * I envisage vmalloc()'s supporting vm_struct becoming:
- *
- *  struct vm_struct {
- *    struct vmregion	region;
- *    unsigned long	flags;
- *    struct page	**pages;
- *    unsigned int	nr_pages;
- *    unsigned long	phys_addr;
- *  };
- *
- * get_vm_area() would then call vmregion_alloc with an appropriate
- * struct vmregion head (eg):
- *
- *  struct vmregion vmalloc_head = {
- *	.vm_list	= LIST_HEAD_INIT(vmalloc_head.vm_list),
- *	.vm_start	= VMALLOC_START,
- *	.vm_end		= VMALLOC_END,
- *  };
- *
- * However, vmalloc_head.vm_start is variable (typically, it is dependent on
- * the amount of RAM found at boot time.)  I would imagine that get_vm_area()
- * would have to initialise this each time prior to calling vmregion_alloc().
- */
-
-struct arm_vmregion *
-arm_vmregion_alloc(struct arm_vmregion_head *head, size_t align,
-		   size_t size, gfp_t gfp, const void *caller)
-{
-	unsigned long start = head->vm_start, addr = head->vm_end;
-	unsigned long flags;
-	struct arm_vmregion *c, *new;
-
-	if (head->vm_end - head->vm_start < size) {
-		printk(KERN_WARNING "%s: allocation too big (requested %#x)\n",
-			__func__, size);
-		goto out;
-	}
-
-	new = kmalloc(sizeof(struct arm_vmregion), gfp);
-	if (!new)
-		goto out;
-
-	new->caller = caller;
-
-	spin_lock_irqsave(&head->vm_lock, flags);
-
-	addr = rounddown(addr - size, align);
-	list_for_each_entry_reverse(c, &head->vm_list, vm_list) {
-		if (addr >= c->vm_end)
-			goto found;
-		addr = rounddown(c->vm_start - size, align);
-		if (addr < start)
-			goto nospc;
-	}
-
- found:
-	/*
-	 * Insert this entry after the one we found.
-	 */
-	list_add(&new->vm_list, &c->vm_list);
-	new->vm_start = addr;
-	new->vm_end = addr + size;
-	new->vm_active = 1;
-
-	spin_unlock_irqrestore(&head->vm_lock, flags);
-	return new;
-
- nospc:
-	spin_unlock_irqrestore(&head->vm_lock, flags);
-	kfree(new);
- out:
-	return NULL;
-}
-
-static struct arm_vmregion *__arm_vmregion_find(struct arm_vmregion_head *head, unsigned long addr)
-{
-	struct arm_vmregion *c;
-
-	list_for_each_entry(c, &head->vm_list, vm_list) {
-		if (c->vm_active && c->vm_start == addr)
-			goto out;
-	}
-	c = NULL;
- out:
-	return c;
-}
-
-struct arm_vmregion *arm_vmregion_find(struct arm_vmregion_head *head, unsigned long addr)
-{
-	struct arm_vmregion *c;
-	unsigned long flags;
-
-	spin_lock_irqsave(&head->vm_lock, flags);
-	c = __arm_vmregion_find(head, addr);
-	spin_unlock_irqrestore(&head->vm_lock, flags);
-	return c;
-}
-
-struct arm_vmregion *arm_vmregion_find_remove(struct arm_vmregion_head *head, unsigned long addr)
-{
-	struct arm_vmregion *c;
-	unsigned long flags;
-
-	spin_lock_irqsave(&head->vm_lock, flags);
-	c = __arm_vmregion_find(head, addr);
-	if (c)
-		c->vm_active = 0;
-	spin_unlock_irqrestore(&head->vm_lock, flags);
-	return c;
-}
-
-void arm_vmregion_free(struct arm_vmregion_head *head, struct arm_vmregion *c)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&head->vm_lock, flags);
-	list_del(&c->vm_list);
-	spin_unlock_irqrestore(&head->vm_lock, flags);
-
-	kfree(c);
-}
-
-#ifdef CONFIG_PROC_FS
-static int arm_vmregion_show(struct seq_file *m, void *p)
-{
-	struct arm_vmregion *c = list_entry(p, struct arm_vmregion, vm_list);
-
-	seq_printf(m, "0x%08lx-0x%08lx %7lu", c->vm_start, c->vm_end,
-		c->vm_end - c->vm_start);
-	if (c->caller)
-		seq_printf(m, " %pS", (void *)c->caller);
-	seq_putc(m, '\n');
-	return 0;
-}
-
-static void *arm_vmregion_start(struct seq_file *m, loff_t *pos)
-{
-	struct arm_vmregion_head *h = m->private;
-	spin_lock_irq(&h->vm_lock);
-	return seq_list_start(&h->vm_list, *pos);
-}
-
-static void *arm_vmregion_next(struct seq_file *m, void *p, loff_t *pos)
-{
-	struct arm_vmregion_head *h = m->private;
-	return seq_list_next(p, &h->vm_list, pos);
-}
-
-static void arm_vmregion_stop(struct seq_file *m, void *p)
-{
-	struct arm_vmregion_head *h = m->private;
-	spin_unlock_irq(&h->vm_lock);
-}
-
-static const struct seq_operations arm_vmregion_ops = {
-	.start	= arm_vmregion_start,
-	.stop	= arm_vmregion_stop,
-	.next	= arm_vmregion_next,
-	.show	= arm_vmregion_show,
-};
-
-static int arm_vmregion_open(struct inode *inode, struct file *file)
-{
-	struct arm_vmregion_head *h = PDE(inode)->data;
-	int ret = seq_open(file, &arm_vmregion_ops);
-	if (!ret) {
-		struct seq_file *m = file->private_data;
-		m->private = h;
-	}
-	return ret;
-}
-
-static const struct file_operations arm_vmregion_fops = {
-	.open	= arm_vmregion_open,
-	.read	= seq_read,
-	.llseek	= seq_lseek,
-	.release = seq_release,
-};
-
-int arm_vmregion_create_proc(const char *path, struct arm_vmregion_head *h)
-{
-	proc_create_data(path, S_IRUSR, NULL, &arm_vmregion_fops, h);
-	return 0;
-}
-#else
-int arm_vmregion_create_proc(const char *path, struct arm_vmregion_head *h)
-{
-	return 0;
-}
-#endif

arch/arm/mm/vmregion.h

-#ifndef VMREGION_H
-#define VMREGION_H
-
-#include <linux/spinlock.h>
-#include <linux/list.h>
-
-struct page;
-
-struct arm_vmregion_head {
-	spinlock_t		vm_lock;
-	struct list_head	vm_list;
-	unsigned long		vm_start;
-	unsigned long		vm_end;
-};
-
-struct arm_vmregion {
-	struct list_head	vm_list;
-	unsigned long		vm_start;
-	unsigned long		vm_end;
-	int			vm_active;
-	const void		*caller;
-};
-
-struct arm_vmregion *arm_vmregion_alloc(struct arm_vmregion_head *, size_t, size_t, gfp_t, const void *);
-struct arm_vmregion *arm_vmregion_find(struct arm_vmregion_head *, unsigned long);
-struct arm_vmregion *arm_vmregion_find_remove(struct arm_vmregion_head *, unsigned long);
-void arm_vmregion_free(struct arm_vmregion_head *, struct arm_vmregion *);
-
-int arm_vmregion_create_proc(const char *, struct arm_vmregion_head *);
-
-#endif

drivers/mmc/host/mmci.c

@@ -20,6 +20,7 @@
 #include <linux/err.h>
 #include <linux/highmem.h>
 #include <linux/log2.h>
+#include <linux/mmc/pm.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/card.h>
 #include <linux/amba/bus.h>
@@ -59,6 +60,7 @@ static unsigned int fmax = 515633;
  * @blksz_datactrl16: true if Block size is at b16..b30 position in datactrl register
  * @pwrreg_powerup: power up value for MMCIPOWER register
  * @signal_direction: input/out direction of bus signals can be indicated
+ * @pwrreg_clkgate: MMCIPOWER register must be used to gate the clock
  */
 struct variant_data {
 	unsigned int		clkreg;
@@ -71,6 +73,7 @@ struct variant_data {
 	bool			blksz_datactrl16;
 	u32			pwrreg_powerup;
 	bool			signal_direction;
+	bool			pwrreg_clkgate;
 };
 
 static struct variant_data variant_arm = {
@@ -87,6 +90,14 @@ static struct variant_data variant_arm_extended_fifo = {
 	.pwrreg_powerup		= MCI_PWR_UP,
 };
 
+static struct variant_data variant_arm_extended_fifo_hwfc = {
+	.fifosize		= 128 * 4,
+	.fifohalfsize		= 64 * 4,
+	.clkreg_enable		= MCI_ARM_HWFCEN,
+	.datalength_bits	= 16,
+	.pwrreg_powerup		= MCI_PWR_UP,
+};
+
 static struct variant_data variant_u300 = {
 	.fifosize		= 16 * 4,
 	.fifohalfsize		= 8 * 4,
@@ -95,6 +106,7 @@ static struct variant_data variant_u300 = {
 	.sdio			= true,
 	.pwrreg_powerup		= MCI_PWR_ON,
 	.signal_direction	= true,
+	.pwrreg_clkgate		= true,
 };
 
 static struct variant_data variant_nomadik = {
@@ -106,6 +118,7 @@ static struct variant_data variant_nomadik = {
 	.st_clkdiv		= true,
 	.pwrreg_powerup		= MCI_PWR_ON,
 	.signal_direction	= true,
+	.pwrreg_clkgate		= true,
 };
 
 static struct variant_data variant_ux500 = {
@@ -118,6 +131,7 @@ static struct variant_data variant_ux500 = {
 	.st_clkdiv		= true,
 	.pwrreg_powerup		= MCI_PWR_ON,
 	.signal_direction	= true,
+	.pwrreg_clkgate		= true,
 };
 
 static struct variant_data variant_ux500v2 = {
@@ -131,8 +145,27 @@ static struct variant_data variant_ux500v2 = {
 	.blksz_datactrl16	= true,
 	.pwrreg_powerup		= MCI_PWR_ON,
 	.signal_direction	= true,
+	.pwrreg_clkgate		= true,
 };
 
+/*
+ * Validate mmc prerequisites
+ */
+static int mmci_validate_data(struct mmci_host *host,
+			      struct mmc_data *data)
+{
+	if (!data)
+		return 0;
+
+	if (!is_power_of_2(data->blksz)) {
+		dev_err(mmc_dev(host->mmc),
+			"unsupported block size (%d bytes)\n", data->blksz);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /*
  * This must be called with host->lock held
  */
@@ -202,6 +235,9 @@ static void mmci_set_clkreg(struct mmci_host *host, unsigned int desired)
 	if (host->mmc->ios.bus_width == MMC_BUS_WIDTH_8)
 		clk |= MCI_ST_8BIT_BUS;
 
+	if (host->mmc->ios.timing == MMC_TIMING_UHS_DDR50)
+		clk |= MCI_ST_UX500_NEG_EDGE;
+
 	mmci_write_clkreg(host, clk);
 }
 
@@ -352,10 +388,33 @@ static inline void mmci_dma_release(struct mmci_host *host)
 	host->dma_rx_channel = host->dma_tx_channel = NULL;
 }
 
+static void mmci_dma_data_error(struct mmci_host *host)
+{
+	dev_err(mmc_dev(host->mmc), "error during DMA transfer!\n");
+	dmaengine_terminate_all(host->dma_current);
+	host->dma_current = NULL;
+	host->dma_desc_current = NULL;
+	host->data->host_cookie = 0;
+}
+
 static void mmci_dma_unmap(struct mmci_host *host, struct mmc_data *data)
 {
-	struct dma_chan *chan = host->dma_current;
+	struct dma_chan *chan;
 	enum dma_data_direction dir;
+
+	if (data->flags & MMC_DATA_READ) {
+		dir = DMA_FROM_DEVICE;
+		chan = host->dma_rx_channel;
+	} else {
+		dir = DMA_TO_DEVICE;
+		chan = host->dma_tx_channel;
+	}
+
+	dma_unmap_sg(chan->device->dev, data->sg, data->sg_len, dir);
+}
+
+static void mmci_dma_finalize(struct mmci_host *host, struct mmc_data *data)
+{
 	u32 status;
 	int i;
 
@@ -374,19 +433,13 @@ static void mmci_dma_unmap(struct mmci_host *host, struct mmc_data *data)
 	 * contiguous buffers.  On TX, we'll get a FIFO underrun error.
 	 */
 	if (status & MCI_RXDATAAVLBLMASK) {
-		dmaengine_terminate_all(chan);
+		mmci_dma_data_error(host);
 		if (!data->error)
 			data->error = -EIO;
 	}
 
-	if (data->flags & MMC_DATA_WRITE) {
-		dir = DMA_TO_DEVICE;
-	} else {
-		dir = DMA_FROM_DEVICE;
-	}
-
 	if (!data->host_cookie)
-		dma_unmap_sg(chan->device->dev, data->sg, data->sg_len, dir);
+		mmci_dma_unmap(host, data);
 
 	/*
 	 * Use of DMA with scatter-gather is impossible.
@@ -396,16 +449,15 @@ static void mmci_dma_unmap(struct mmci_host *host, struct mmc_data *data)
 		dev_err(mmc_dev(host->mmc), "buggy DMA detected. Taking evasive action.\n");
 		mmci_dma_release(host);
 	}
-}
 
-static void mmci_dma_data_error(struct mmci_host *host)
-{
-	dev_err(mmc_dev(host->mmc), "error during DMA transfer!\n");
-	dmaengine_terminate_all(host->dma_current);
+	host->dma_current = NULL;
+	host->dma_desc_current = NULL;
 }
 
-static int mmci_dma_prep_data(struct mmci_host *host, struct mmc_data *data,
-			      struct mmci_host_next *next)
+/* prepares DMA channel and DMA descriptor, returns non-zero on failure */
+static int __mmci_dma_prep_data(struct mmci_host *host, struct mmc_data *data,
+				struct dma_chan **dma_chan,
+				struct dma_async_tx_descriptor **dma_desc)
 {
 	struct variant_data *variant = host->variant;
 	struct dma_slave_config conf = {
@@ -423,16 +475,6 @@ static int mmci_dma_prep_data(struct mmci_host *host, struct mmc_data *data,
 	enum dma_data_direction buffer_dirn;
 	int nr_sg;
 
-	/* Check if next job is already prepared */
-	if (data->host_cookie && !next &&
-	    host->dma_current && host->dma_desc_current)
-		return 0;
-
-	if (!next) {
-		host->dma_current = NULL;
-		host->dma_desc_current = NULL;
-	}
-
 	if (data->flags & MMC_DATA_READ) {
 		conf.direction = DMA_DEV_TO_MEM;
 		buffer_dirn = DMA_FROM_DEVICE;
@@ -462,29 +504,41 @@ static int mmci_dma_prep_data(struct mmci_host *host, struct mmc_data *data,
 	if (!desc)
 		goto unmap_exit;
 
-	if (next) {
-		next->dma_chan = chan;
-		next->dma_desc = desc;
-	} else {
-		host->dma_current = chan;
-		host->dma_desc_current = desc;
-	}
+	*dma_chan = chan;
+	*dma_desc = desc;
 
 	return 0;
 
  unmap_exit:
-	if (!next)
-		dmaengine_terminate_all(chan);
 	dma_unmap_sg(device->dev, data->sg, data->sg_len, buffer_dirn);
 	return -ENOMEM;
 }
 
+static inline int mmci_dma_prep_data(struct mmci_host *host,
+				     struct mmc_data *data)
+{
+	/* Check if next job is already prepared. */
+	if (host->dma_current && host->dma_desc_current)
+		return 0;
+
+	/* No job were prepared thus do it now. */
+	return __mmci_dma_prep_data(host, data, &host->dma_current,
+				    &host->dma_desc_current);
+}
+
+static inline int mmci_dma_prep_next(struct mmci_host *host,
+				     struct mmc_data *data)
+{
+	struct mmci_host_next *nd = &host->next_data;
+	return __mmci_dma_prep_data(host, data, &nd->dma_chan, &nd->dma_desc);
+}
+
 static int mmci_dma_start_data(struct mmci_host *host, unsigned int datactrl)
 {
 	int ret;
 	struct mmc_data *data = host->data;
 
-	ret = mmci_dma_prep_data(host, host->data, NULL);
+	ret = mmci_dma_prep_data(host, host->data);
 	if (ret)
 		return ret;
 
@@ -514,19 +568,11 @@ static void mmci_get_next_data(struct mmci_host *host, struct mmc_data *data)
 {
 	struct mmci_host_next *next = &host->next_data;
 
-	if (data->host_cookie && data->host_cookie != next->cookie) {
-		pr_warning("[%s] invalid cookie: data->host_cookie %d"
-		       " host->next_data.cookie %d\n",
-		       __func__, data->host_cookie, host->next_data.cookie);
-		data->host_cookie = 0;
-	}
-
-	if (!data->host_cookie)
-		return;
+	WARN_ON(data->host_cookie && data->host_cookie != next->cookie);
+	WARN_ON(!data->host_cookie && (next->dma_desc || next->dma_chan));
 
 	host->dma_desc_current = next->dma_desc;
 	host->dma_current = next->dma_chan;
-
 	next->dma_desc = NULL;
 	next->dma_chan = NULL;
 }
@@ -541,19 +587,13 @@ static void mmci_pre_request(struct mmc_host *mmc, struct mmc_request *mrq,
 	if (!data)
 		return;
 
-	if (data->host_cookie) {
-		data->host_cookie = 0;
+	BUG_ON(data->host_cookie);
+
+	if (mmci_validate_data(host, data))
 		return;
-	}
 
-	/* if config for dma */
-	if (((data->flags & MMC_DATA_WRITE) && host->dma_tx_channel) ||
-	    ((data->flags & MMC_DATA_READ) && host->dma_rx_channel)) {
-		if (mmci_dma_prep_data(host, data, nd))
-			data->host_cookie = 0;
-		else
-			data->host_cookie = ++nd->cookie < 0 ? 1 : nd->cookie;
-	}
+	if (!mmci_dma_prep_next(host, data))
+		data->host_cookie = ++nd->cookie < 0 ? 1 : nd->cookie;
 }
 
 static void mmci_post_request(struct mmc_host *mmc, struct mmc_request *mrq,
@@ -561,29 +601,23 @@ static void mmci_post_request(struct mmc_host *mmc, struct mmc_request *mrq,
 {
 	struct mmci_host *host = mmc_priv(mmc);
 	struct mmc_data *data = mrq->data;
-	struct dma_chan *chan;
-	enum dma_data_direction dir;
 
-	if (!data)
+	if (!data || !data->host_cookie)
 		return;
 
-	if (data->flags & MMC_DATA_READ) {
-		dir = DMA_FROM_DEVICE;
-		chan = host->dma_rx_channel;
-	} else {
-		dir = DMA_TO_DEVICE;
-		chan = host->dma_tx_channel;
-	}
+	mmci_dma_unmap(host, data);
 
+	if (err) {
+		struct mmci_host_next *next = &host->next_data;
+		struct dma_chan *chan;
+		if (data->flags & MMC_DATA_READ)
+			chan = host->dma_rx_channel;
+		else
+			chan = host->dma_tx_channel;
+		dmaengine_terminate_all(chan);
 
-	/* if config for dma */
-	if (chan) {
-		if (err)
-			dmaengine_terminate_all(chan);
-		if (data->host_cookie)
-			dma_unmap_sg(mmc_dev(host->mmc), data->sg,
-				     data->sg_len, dir);
-		mrq->data->host_cookie = 0;
+		next->dma_desc = NULL;
+		next->dma_chan = NULL;
 	}
 }
 
@@ -604,6 +638,11 @@ static inline void mmci_dma_unmap(struct mmci_host *host, struct mmc_data *data)
 {
 }
 
+static inline void mmci_dma_finalize(struct mmci_host *host,
+				     struct mmc_data *data)
+{
+}
+
 static inline void mmci_dma_data_error(struct mmci_host *host)
 {
 }
@@ -680,6 +719,9 @@ static void mmci_start_data(struct mmci_host *host, struct mmc_data *data)
 			mmci_write_clkreg(host, clk);
 		}
 
+	if (host->mmc->ios.timing == MMC_TIMING_UHS_DDR50)
+		datactrl |= MCI_ST_DPSM_DDRMODE;
+
 	/*
 	 * Attempt to use DMA operation mode, if this
 	 * should fail, fall back to PIO mode
@@ -751,8 +793,10 @@ mmci_data_irq(struct mmci_host *host, struct mmc_data *data,
 		u32 remain, success;
 
 		/* Terminate the DMA transfer */
-		if (dma_inprogress(host))
+		if (dma_inprogress(host)) {
 			mmci_dma_data_error(host);
+			mmci_dma_unmap(host, data);
+		}
 
 		/*
 		 * Calculate how far we are into the transfer.  Note that
@@ -791,7 +835,7 @@ mmci_data_irq(struct mmci_host *host, struct mmc_data *data,
 
 	if (status & MCI_DATAEND || data->error) {
 		if (dma_inprogress(host))
-			mmci_dma_unmap(host, data);
+			mmci_dma_finalize(host, data);
 		mmci_stop_data(host);
 
 		if (!data->error)
@@ -828,8 +872,10 @@ mmci_cmd_irq(struct mmci_host *host, struct mmc_command *cmd,
 	if (!cmd->data || cmd->error) {
 		if (host->data) {
 			/* Terminate the DMA transfer */
-			if (dma_inprogress(host))
+			if (dma_inprogress(host)) {
 				mmci_dma_data_error(host);
+				mmci_dma_unmap(host, host->data);
+			}
 			mmci_stop_data(host);
 		}
 		mmci_request_end(host, cmd->mrq);
@@ -1055,10 +1101,8 @@ static void mmci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 
 	WARN_ON(host->mrq != NULL);
 
-	if (mrq->data && !is_power_of_2(mrq->data->blksz)) {
-		dev_err(mmc_dev(mmc), "unsupported block size (%d bytes)\n",
-			mrq->data->blksz);
-		mrq->cmd->error = -EINVAL;
+	mrq->cmd->error = mmci_validate_data(host, mrq->data);
+	if (mrq->cmd->error) {
 		mmc_request_done(mmc, mrq);
 		return;
 	}
@@ -1086,7 +1130,6 @@ static void mmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	struct variant_data *variant = host->variant;
 	u32 pwr = 0;
 	unsigned long flags;
-	int ret;
 
 	pm_runtime_get_sync(mmc_dev(mmc));
 
@@ -1096,23 +1139,13 @@ static void mmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 
 	switch (ios->power_mode) {
 	case MMC_POWER_OFF:
-		if (host->vcc)
-			ret = mmc_regulator_set_ocr(mmc, host->vcc, 0);
+		if (!IS_ERR(mmc->supply.vmmc))
+			mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, 0);
 		break;
 	case MMC_POWER_UP:
-		if (host->vcc) {
-			ret = mmc_regulator_set_ocr(mmc, host->vcc, ios->vdd);
-			if (ret) {
-				dev_err(mmc_dev(mmc), "unable to set OCR\n");
-				/*
-				 * The .set_ios() function in the mmc_host_ops
-				 * struct return void, and failing to set the
-				 * power should be rare so we print an error
-				 * and return here.
-				 */
-				goto out;
-			}
-		}
+		if (!IS_ERR(mmc->supply.vmmc))
+			mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, ios->vdd);
+
 		/*
 		 * The ST Micro variant doesn't have the PL180s MCI_PWR_UP
 		 * and instead uses MCI_PWR_ON so apply whatever value is
@@ -1154,6 +1187,13 @@ static void mmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		}
 	}
 
+	/*
+	 * If clock = 0 and the variant requires the MMCIPOWER to be used for
+	 * gating the clock, the MCI_PWR_ON bit is cleared.
+	 */
+	if (!ios->clock && variant->pwrreg_clkgate)
+		pwr &= ~MCI_PWR_ON;
+
 	spin_lock_irqsave(&host->lock, flags);
 
 	mmci_set_clkreg(host, ios->clock);
@@ -1161,7 +1201,6 @@ static void mmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 
 	spin_unlock_irqrestore(&host->lock, flags);
 
- out:
 	pm_runtime_mark_last_busy(mmc_dev(mmc));
 	pm_runtime_put_autosuspend(mmc_dev(mmc));
 }
@@ -1384,32 +1423,19 @@ static int mmci_probe(struct amba_device *dev,
 	} else
 		dev_warn(&dev->dev, "could not get default pinstate\n");
 
-#ifdef CONFIG_REGULATOR
-	/* If we're using the regulator framework, try to fetch a regulator */
-	host->vcc = regulator_get(&dev->dev, "vmmc");
-	if (IS_ERR(host->vcc))
-		host->vcc = NULL;
-	else {
-		int mask = mmc_regulator_get_ocrmask(host->vcc);
-
-		if (mask < 0)
-			dev_err(&dev->dev, "error getting OCR mask (%d)\n",
-				mask);
-		else {
-			host->mmc->ocr_avail = (u32) mask;
-			if (plat->ocr_mask)
-				dev_warn(&dev->dev,
-				 "Provided ocr_mask/setpower will not be used "
-				 "(using regulator instead)\n");
-		}
-	}
-#endif
-	/* Fall back to platform data if no regulator is found */
-	if (host->vcc == NULL)
+	/* Get regulators and the supported OCR mask */
+	mmc_regulator_get_supply(mmc);
+	if (!mmc->ocr_avail)
 		mmc->ocr_avail = plat->ocr_mask;
+	else if (plat->ocr_mask)
+		dev_warn(mmc_dev(mmc), "Platform OCR mask is ignored\n");
+
 	mmc->caps = plat->capabilities;
 	mmc->caps2 = plat->capabilities2;
 
+	/* We support these PM capabilities. */
+	mmc->pm_caps = MMC_PM_KEEP_POWER;
+
 	/*
 	 * We can do SGIO
 	 */
@@ -1585,10 +1611,6 @@ static int mmci_remove(struct amba_device *dev)
 		clk_disable_unprepare(host->clk);
 		clk_put(host->clk);
 
-		if (host->vcc)
-			mmc_regulator_set_ocr(mmc, host->vcc, 0);
-		regulator_put(host->vcc);
-
 		mmc_free_host(mmc);
 
 		amba_release_regions(dev);
@@ -1636,8 +1658,37 @@ static int mmci_resume(struct device *dev)
 }
 #endif
 
+#ifdef CONFIG_PM_RUNTIME
+static int mmci_runtime_suspend(struct device *dev)
+{
+	struct amba_device *adev = to_amba_device(dev);
+	struct mmc_host *mmc = amba_get_drvdata(adev);
+
+	if (mmc) {
+		struct mmci_host *host = mmc_priv(mmc);
+		clk_disable_unprepare(host->clk);
+	}
+
+	return 0;
+}
+
+static int mmci_runtime_resume(struct device *dev)
+{
+	struct amba_device *adev = to_amba_device(dev);
+	struct mmc_host *mmc = amba_get_drvdata(adev);
+
+	if (mmc) {
+		struct mmci_host *host = mmc_priv(mmc);
+		clk_prepare_enable(host->clk);
+	}
+
+	return 0;
+}
+#endif
+
 static const struct dev_pm_ops mmci_dev_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(mmci_suspend, mmci_resume)
+	SET_RUNTIME_PM_OPS(mmci_runtime_suspend, mmci_runtime_resume, NULL)
 };
 
 static struct amba_id mmci_ids[] = {
@@ -1651,6 +1702,11 @@ static struct amba_id mmci_ids[] = {
 		.mask	= 0xff0fffff,
 		.data	= &variant_arm_extended_fifo,
 	},
+	{
+		.id	= 0x02041180,
+		.mask	= 0xff0fffff,
+		.data	= &variant_arm_extended_fifo_hwfc,
+	},
 	{
 		.id	= 0x00041181,
 		.mask	= 0x000fffff,

drivers/mmc/host/mmci.h

@@ -28,6 +28,8 @@
 #define MCI_ST_UX500_NEG_EDGE	(1 << 13)
 #define MCI_ST_UX500_HWFCEN	(1 << 14)
 #define MCI_ST_UX500_CLK_INV	(1 << 15)
+/* Modified PL180 on Versatile Express platform */
+#define MCI_ARM_HWFCEN		(1 << 12)
 
 #define MMCIARGUMENT		0x008
 #define MMCICOMMAND		0x00c
@@ -193,7 +195,6 @@ struct mmci_host {
 	/* pio stuff */
 	struct sg_mapping_iter	sg_miter;
 	unsigned int		size;
-	struct regulator	*vcc;
 
 	/* pinctrl handles */
 	struct pinctrl		*pinctrl;