Merge tag 'tegra-for-3.7-dmaengine' of git://git.kernel.org/pub/scm/linux/kernel/git/swarren/linux-tegra into next/cleanup

ARM: tegra: switch to dmaengine

The Tegra code-base has contained both a legacy DMA and a dmaengine
driver since v3.6-rcX. This series flips Tegra's defconfig to enable
dmaengine rather than the legacy driver, and removes the legacy driver
and all client code.

* tag 'tegra-for-3.7-dmaengine' of git://git.kernel.org/pub/scm/linux/kernel/git/swarren/linux-tegra:
  ASoC: tegra: remove support of legacy DMA driver based access
  spi: tegra: remove support of legacy DMA driver based access
  ARM: tegra: apbio: remove support of legacy DMA driver based access
  ARM: tegra: dma: remove legacy APB DMA driver
  ARM: tegra: config: enable dmaengine based APB DMA driver
  + sync to 3.6-rc6

45 files changed, 357 insertions, 1306 deletions

diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index f15f82bf3a50..e968a52e4881 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -356,15 +356,15 @@ choice
 		  is nothing connected to read from the DCC.
 
 	config DEBUG_SEMIHOSTING
-		bool "Kernel low-level debug output via semihosting I"
+		bool "Kernel low-level debug output via semihosting I/O"
 		help
 		  Semihosting enables code running on an ARM target to use
 		  the I/O facilities on a host debugger/emulator through a
-		  simple SVC calls. The host debugger or emulator must have
+		  simple SVC call. The host debugger or emulator must have
 		  semihosting enabled for the special svc call to be trapped
 		  otherwise the kernel will crash.
 
-		  This is known to work with OpenOCD, as wellas
+		  This is known to work with OpenOCD, as well as
 		  ARM's Fast Models, or any other controlling environment
 		  that implements semihosting.
 
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 210c923025b1..74381a31ee42 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -283,10 +283,10 @@ zImage Image xipImage bootpImage uImage: vmlinux
 zinstall uinstall install: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $@
 
-%.dtb:
+%.dtb: scripts
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
 
-dtbs:
+dtbs: scripts
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
 
 # We use MRPROPER_FILES and CLEAN_FILES now
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index b8c64b80bafc..81769c1341fa 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -659,10 +659,14 @@ __armv7_mmu_cache_on:
 #ifdef CONFIG_CPU_ENDIAN_BE8
 		orr	r0, r0, #1 << 25	@ big-endian page tables
 #endif
+		mrcne   p15, 0, r6, c2, c0, 2   @ read ttb control reg
 		orrne	r0, r0, #1		@ MMU enabled
 		movne	r1, #0xfffffffd		@ domain 0 = client
+		bic     r6, r6, #1 << 31        @ 32-bit translation system
+		bic     r6, r6, #3 << 0         @ use only ttbr0
 		mcrne	p15, 0, r3, c2, c0, 0	@ load page table pointer
 		mcrne	p15, 0, r1, c3, c0, 0	@ load domain access control
+		mcrne   p15, 0, r6, c2, c0, 2   @ load ttb control
 #endif
 		mcr	p15, 0, r0, c7, c5, 4	@ ISB
 		mcr	p15, 0, r0, c1, c0, 0	@ load control register
diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig
index db2245353f0f..0d6bb738c6de 100644
--- a/arch/arm/configs/tegra_defconfig
+++ b/arch/arm/configs/tegra_defconfig
@@ -145,6 +145,8 @@ CONFIG_MMC_SDHCI_TEGRA=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_EM3027=y
 CONFIG_RTC_DRV_TEGRA=y
+CONFIG_DMADEVICES=y
+CONFIG_TEGRA20_APB_DMA=y
 CONFIG_STAGING=y
 CONFIG_SENSORS_ISL29018=y
 CONFIG_SENSORS_ISL29028=y
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 03fb93621d0d..5c8b3bf4d825 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -320,4 +320,12 @@
 	.size \name , . - \name
 	.endm
 
+	.macro check_uaccess, addr:req, size:req, limit:req, tmp:req, bad:req
+#ifndef CONFIG_CPU_USE_DOMAINS
+	adds	\tmp, \addr, #\size - 1
+	sbcccs	\tmp, \tmp, \limit
+	bcs	\bad
+#endif
+	.endm
+
 #endif /* __ASM_ASSEMBLER_H__ */
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index e965f1b560f1..5f6ddcc56452 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -187,6 +187,7 @@ static inline unsigned long __phys_to_virt(unsigned long x)
 #define __phys_to_virt(x)	((x) - PHYS_OFFSET + PAGE_OFFSET)
 #endif
 #endif
+#endif /* __ASSEMBLY__ */
 
 #ifndef PHYS_OFFSET
 #ifdef PLAT_PHYS_OFFSET
@@ -196,6 +197,8 @@ static inline unsigned long __phys_to_virt(unsigned long x)
 #endif
 #endif
 
+#ifndef __ASSEMBLY__
+
 /*
  * PFNs are used to describe any physical page; this means
  * PFN 0 == physical address 0.
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index 314d4664eae7..99a19512ee26 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -199,6 +199,9 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 {
 	pgtable_page_dtor(pte);
 
+#ifdef CONFIG_ARM_LPAE
+	tlb_add_flush(tlb, addr);
+#else
 	/*
 	 * With the classic ARM MMU, a pte page has two corresponding pmd
 	 * entries, each covering 1MB.
@@ -206,6 +209,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 	addr &= PMD_MASK;
 	tlb_add_flush(tlb, addr + SZ_1M - PAGE_SIZE);
 	tlb_add_flush(tlb, addr + SZ_1M);
+#endif
 
 	tlb_remove_page(tlb, pte);
 }
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 479a6352e0b5..77bd79f2ffdb 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -101,28 +101,39 @@ extern int __get_user_1(void *);
 extern int __get_user_2(void *);
 extern int __get_user_4(void *);
 
-#define __get_user_x(__r2,__p,__e,__s,__i...)				\
+#define __GUP_CLOBBER_1	"lr", "cc"
+#ifdef CONFIG_CPU_USE_DOMAINS
+#define __GUP_CLOBBER_2	"ip", "lr", "cc"
+#else
+#define __GUP_CLOBBER_2 "lr", "cc"
+#endif
+#define __GUP_CLOBBER_4	"lr", "cc"
+
+#define __get_user_x(__r2,__p,__e,__l,__s)				\
 	   __asm__ __volatile__ (					\
 		__asmeq("%0", "r0") __asmeq("%1", "r2")			\
+		__asmeq("%3", "r1")					\
 		"bl	__get_user_" #__s				\
 		: "=&r" (__e), "=r" (__r2)				\
-		: "0" (__p)						\
-		: __i, "cc")
+		: "0" (__p), "r" (__l)					\
+		: __GUP_CLOBBER_##__s)
 
-#define get_user(x,p)							\
+#define __get_user_check(x,p)							\
 	({								\
+		unsigned long __limit = current_thread_info()->addr_limit - 1; \
 		register const typeof(*(p)) __user *__p asm("r0") = (p);\
 		register unsigned long __r2 asm("r2");			\
+		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
 		switch (sizeof(*(__p))) {				\
 		case 1:							\
-			__get_user_x(__r2, __p, __e, 1, "lr");		\
-	       		break;						\
+			__get_user_x(__r2, __p, __e, __l, 1);		\
+			break;						\
 		case 2:							\
-			__get_user_x(__r2, __p, __e, 2, "r3", "lr");	\
+			__get_user_x(__r2, __p, __e, __l, 2);		\
 			break;						\
 		case 4:							\
-	       		__get_user_x(__r2, __p, __e, 4, "lr");		\
+			__get_user_x(__r2, __p, __e, __l, 4);		\
 			break;						\
 		default: __e = __get_user_bad(); break;			\
 		}							\
@@ -130,42 +141,57 @@ extern int __get_user_4(void *);
 		__e;							\
 	})
 
+#define get_user(x,p)							\
+	({								\
+		might_fault();						\
+		__get_user_check(x,p);					\
+	 })
+
 extern int __put_user_1(void *, unsigned int);
 extern int __put_user_2(void *, unsigned int);
 extern int __put_user_4(void *, unsigned int);
 extern int __put_user_8(void *, unsigned long long);
 
-#define __put_user_x(__r2,__p,__e,__s)					\
+#define __put_user_x(__r2,__p,__e,__l,__s)				\
 	   __asm__ __volatile__ (					\
 		__asmeq("%0", "r0") __asmeq("%2", "r2")			\
+		__asmeq("%3", "r1")					\
 		"bl	__put_user_" #__s				\
 		: "=&r" (__e)						\
-		: "0" (__p), "r" (__r2)					\
+		: "0" (__p), "r" (__r2), "r" (__l)			\
 		: "ip", "lr", "cc")
 
-#define put_user(x,p)							\
+#define __put_user_check(x,p)							\
 	({								\
+		unsigned long __limit = current_thread_info()->addr_limit - 1; \
 		register const typeof(*(p)) __r2 asm("r2") = (x);	\
 		register const typeof(*(p)) __user *__p asm("r0") = (p);\
+		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
 		switch (sizeof(*(__p))) {				\
 		case 1:							\
-			__put_user_x(__r2, __p, __e, 1);		\
+			__put_user_x(__r2, __p, __e, __l, 1);		\
 			break;						\
 		case 2:							\
-			__put_user_x(__r2, __p, __e, 2);		\
+			__put_user_x(__r2, __p, __e, __l, 2);		\
 			break;						\
 		case 4:							\
-			__put_user_x(__r2, __p, __e, 4);		\
+			__put_user_x(__r2, __p, __e, __l, 4);		\
 			break;						\
 		case 8:							\
-			__put_user_x(__r2, __p, __e, 8);		\
+			__put_user_x(__r2, __p, __e, __l, 8);		\
 			break;						\
 		default: __e = __put_user_bad(); break;			\
 		}							\
 		__e;							\
 	})
 
+#define put_user(x,p)							\
+	({								\
+		might_fault();						\
+		__put_user_check(x,p);					\
+	 })
+
 #else /* CONFIG_MMU */
 
 /*
@@ -219,6 +245,7 @@ do {									\
 	unsigned long __gu_addr = (unsigned long)(ptr);			\
 	unsigned long __gu_val;						\
 	__chk_user_ptr(ptr);						\
+	might_fault();							\
 	switch (sizeof(*(ptr))) {					\
 	case 1:	__get_user_asm_byte(__gu_val,__gu_addr,err);	break;	\
 	case 2:	__get_user_asm_half(__gu_val,__gu_addr,err);	break;	\
@@ -300,6 +327,7 @@ do {									\
 	unsigned long __pu_addr = (unsigned long)(ptr);			\
 	__typeof__(*(ptr)) __pu_val = (x);				\
 	__chk_user_ptr(ptr);						\
+	might_fault();							\
 	switch (sizeof(*(ptr))) {					\
 	case 1: __put_user_asm_byte(__pu_val,__pu_addr,err);	break;	\
 	case 2: __put_user_asm_half(__pu_val,__pu_addr,err);	break;	\
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index ba386bd94107..281bf3301241 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -159,6 +159,12 @@ static int debug_arch_supported(void)
 		arch >= ARM_DEBUG_ARCH_V7_1;
 }
 
+/* Can we determine the watchpoint access type from the fsr? */
+static int debug_exception_updates_fsr(void)
+{
+	return 0;
+}
+
 /* Determine number of WRP registers available. */
 static int get_num_wrp_resources(void)
 {
@@ -604,13 +610,14 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 		/* Aligned */
 		break;
 	case 1:
-		/* Allow single byte watchpoint. */
-		if (info->ctrl.len == ARM_BREAKPOINT_LEN_1)
-			break;
 	case 2:
 		/* Allow halfword watchpoints and breakpoints. */
 		if (info->ctrl.len == ARM_BREAKPOINT_LEN_2)
 			break;
+	case 3:
+		/* Allow single byte watchpoint. */
+		if (info->ctrl.len == ARM_BREAKPOINT_LEN_1)
+			break;
 	default:
 		ret = -EINVAL;
 		goto out;
@@ -619,18 +626,35 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	info->address &= ~alignment_mask;
 	info->ctrl.len <<= offset;
 
-	/*
-	 * Currently we rely on an overflow handler to take
-	 * care of single-stepping the breakpoint when it fires.
-	 * In the case of userspace breakpoints on a core with V7 debug,
-	 * we can use the mismatch feature as a poor-man's hardware
-	 * single-step, but this only works for per-task breakpoints.
-	 */
-	if (!bp->overflow_handler && (arch_check_bp_in_kernelspace(bp) ||
-	    !core_has_mismatch_brps() || !bp->hw.bp_target)) {
-		pr_warning("overflow handler required but none found\n");
-		ret = -EINVAL;
+	if (!bp->overflow_handler) {
+		/*
+		 * Mismatch breakpoints are required for single-stepping
+		 * breakpoints.
+		 */
+		if (!core_has_mismatch_brps())
+			return -EINVAL;
+
+		/* We don't allow mismatch breakpoints in kernel space. */
+		if (arch_check_bp_in_kernelspace(bp))
+			return -EPERM;
+
+		/*
+		 * Per-cpu breakpoints are not supported by our stepping
+		 * mechanism.
+		 */
+		if (!bp->hw.bp_target)
+			return -EINVAL;
+
+		/*
+		 * We only support specific access types if the fsr
+		 * reports them.
+		 */
+		if (!debug_exception_updates_fsr() &&
+		    (info->ctrl.type == ARM_BREAKPOINT_LOAD ||
+		     info->ctrl.type == ARM_BREAKPOINT_STORE))
+			return -EINVAL;
 	}
+
 out:
 	return ret;
 }
@@ -706,10 +730,12 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr,
 				goto unlock;
 
 			/* Check that the access type matches. */
-			access = (fsr & ARM_FSR_ACCESS_MASK) ? HW_BREAKPOINT_W :
-				 HW_BREAKPOINT_R;
-			if (!(access & hw_breakpoint_type(wp)))
-				goto unlock;
+			if (debug_exception_updates_fsr()) {
+				access = (fsr & ARM_FSR_ACCESS_MASK) ?
+					  HW_BREAKPOINT_W : HW_BREAKPOINT_R;
+				if (!(access & hw_breakpoint_type(wp)))
+					goto unlock;
+			}
 
 			/* We have a winner. */
 			info->trigger = addr;
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index f7945218b8c6..b0179b89a04c 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -420,20 +420,23 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 #endif
 			instr = *(u32 *) pc;
 	} else if (thumb_mode(regs)) {
-		get_user(instr, (u16 __user *)pc);
+		if (get_user(instr, (u16 __user *)pc))
+			goto die_sig;
 		if (is_wide_instruction(instr)) {
 			unsigned int instr2;
-			get_user(instr2, (u16 __user *)pc+1);
+			if (get_user(instr2, (u16 __user *)pc+1))
+				goto die_sig;
 			instr <<= 16;
 			instr |= instr2;
 		}
-	} else {
-		get_user(instr, (u32 __user *)pc);
+	} else if (get_user(instr, (u32 __user *)pc)) {
+		goto die_sig;
 	}
 
 	if (call_undef_hook(regs, instr) == 0)
 		return;
 
+die_sig:
 #ifdef CONFIG_DEBUG_USER
 	if (user_debug & UDBG_UNDEFINED) {
 		printk(KERN_INFO "%s (%d): undefined instruction: pc=%p\n",
diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c
index d6dacc69254e..395d5fbb8fa2 100644
--- a/arch/arm/lib/delay.c
+++ b/arch/arm/lib/delay.c
@@ -59,6 +59,7 @@ void __init init_current_timer_delay(unsigned long freq)
 {
 	pr_info("Switching to timer-based delay loop\n");
 	lpj_fine			= freq / HZ;
+	loops_per_jiffy			= lpj_fine;
 	arm_delay_ops.delay		= __timer_delay;
 	arm_delay_ops.const_udelay	= __timer_const_udelay;
 	arm_delay_ops.udelay		= __timer_udelay;
diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S
index 11093a7c3e32..9b06bb41fca6 100644
--- a/arch/arm/lib/getuser.S
+++ b/arch/arm/lib/getuser.S
@@ -16,8 +16,9 @@
  * __get_user_X
  *
  * Inputs:	r0 contains the address
+ *		r1 contains the address limit, which must be preserved
  * Outputs:	r0 is the error code
- *		r2, r3 contains the zero-extended value
+ *		r2 contains the zero-extended value
  *		lr corrupted
  *
  * No other registers must be altered.  (see <asm/uaccess.h>
@@ -27,33 +28,39 @@
  * Note also that it is intended that __get_user_bad is not global.
  */
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 #include <asm/errno.h>
 #include <asm/domain.h>
 
 ENTRY(__get_user_1)
+	check_uaccess r0, 1, r1, r2, __get_user_bad
 1: TUSER(ldrb)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__get_user_1)
 
 ENTRY(__get_user_2)
-#ifdef CONFIG_THUMB2_KERNEL
-2: TUSER(ldrb)	r2, [r0]
-3: TUSER(ldrb)	r3, [r0, #1]
+	check_uaccess r0, 2, r1, r2, __get_user_bad
+#ifdef CONFIG_CPU_USE_DOMAINS
+rb	.req	ip
+2:	ldrbt	r2, [r0], #1
+3:	ldrbt	rb, [r0], #0
 #else
-2: TUSER(ldrb)	r2, [r0], #1
-3: TUSER(ldrb)	r3, [r0]
+rb	.req	r0
+2:	ldrb	r2, [r0]
+3:	ldrb	rb, [r0, #1]
 #endif
 #ifndef __ARMEB__
-	orr	r2, r2, r3, lsl #8
+	orr	r2, r2, rb, lsl #8
 #else
-	orr	r2, r3, r2, lsl #8
+	orr	r2, rb, r2, lsl #8
 #endif
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__get_user_2)
 
 ENTRY(__get_user_4)
+	check_uaccess r0, 4, r1, r2, __get_user_bad
 4: TUSER(ldr)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
diff --git a/arch/arm/lib/putuser.S b/arch/arm/lib/putuser.S
index 7db25990c589..3d73dcb959b0 100644
--- a/arch/arm/lib/putuser.S
+++ b/arch/arm/lib/putuser.S
@@ -16,6 +16,7 @@
  * __put_user_X
  *
  * Inputs:	r0 contains the address
+ *		r1 contains the address limit, which must be preserved
  *		r2, r3 contains the value
  * Outputs:	r0 is the error code
  *		lr corrupted
@@ -27,16 +28,19 @@
  * Note also that it is intended that __put_user_bad is not global.
  */
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 #include <asm/errno.h>
 #include <asm/domain.h>
 
 ENTRY(__put_user_1)
+	check_uaccess r0, 1, r1, ip, __put_user_bad
 1: TUSER(strb)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__put_user_1)
 
 ENTRY(__put_user_2)
+	check_uaccess r0, 2, r1, ip, __put_user_bad
 	mov	ip, r2, lsr #8
 #ifdef CONFIG_THUMB2_KERNEL
 #ifndef __ARMEB__
@@ -60,12 +64,14 @@ ENTRY(__put_user_2)
 ENDPROC(__put_user_2)
 
 ENTRY(__put_user_4)
+	check_uaccess r0, 4, r1, ip, __put_user_bad
 4: TUSER(str)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__put_user_4)
 
 ENTRY(__put_user_8)
+	check_uaccess r0, 8, r1, ip, __put_user_bad
 #ifdef CONFIG_THUMB2_KERNEL
 5: TUSER(str)	r2, [r0]
 6: TUSER(str)	r3, [r0, #4]
diff --git a/arch/arm/mach-imx/clk-imx25.c b/arch/arm/mach-imx/clk-imx25.c
index fdd8cc87c9fe..4431a62fff5b 100644
--- a/arch/arm/mach-imx/clk-imx25.c
+++ b/arch/arm/mach-imx/clk-imx25.c
@@ -222,10 +222,8 @@ int __init mx25_clocks_init(void)
 	clk_register_clkdev(clk[lcdc_ipg], "ipg", "imx-fb.0");
 	clk_register_clkdev(clk[lcdc_ahb], "ahb", "imx-fb.0");
 	clk_register_clkdev(clk[wdt_ipg], NULL, "imx2-wdt.0");
-	clk_register_clkdev(clk[ssi1_ipg_per], "per", "imx-ssi.0");
-	clk_register_clkdev(clk[ssi1_ipg], "ipg", "imx-ssi.0");
-	clk_register_clkdev(clk[ssi2_ipg_per], "per", "imx-ssi.1");
-	clk_register_clkdev(clk[ssi2_ipg], "ipg", "imx-ssi.1");
+	clk_register_clkdev(clk[ssi1_ipg], NULL, "imx-ssi.0");
+	clk_register_clkdev(clk[ssi2_ipg], NULL, "imx-ssi.1");
 	clk_register_clkdev(clk[esdhc1_ipg_per], "per", "sdhci-esdhc-imx25.0");
 	clk_register_clkdev(clk[esdhc1_ipg], "ipg", "sdhci-esdhc-imx25.0");
 	clk_register_clkdev(clk[esdhc1_ahb], "ahb", "sdhci-esdhc-imx25.0");
diff --git a/arch/arm/mach-imx/clk-imx35.c b/arch/arm/mach-imx/clk-imx35.c
index c6422fb10bae..65fb8bcd86cb 100644
--- a/arch/arm/mach-imx/clk-imx35.c
+++ b/arch/arm/mach-imx/clk-imx35.c
@@ -230,10 +230,8 @@ int __init mx35_clocks_init()
 	clk_register_clkdev(clk[ipu_gate], NULL, "mx3_sdc_fb");
 	clk_register_clkdev(clk[owire_gate], NULL, "mxc_w1");
 	clk_register_clkdev(clk[sdma_gate], NULL, "imx35-sdma");
-	clk_register_clkdev(clk[ipg], "ipg", "imx-ssi.0");
-	clk_register_clkdev(clk[ssi1_div_post], "per", "imx-ssi.0");
-	clk_register_clkdev(clk[ipg], "ipg", "imx-ssi.1");
-	clk_register_clkdev(clk[ssi2_div_post], "per", "imx-ssi.1");
+	clk_register_clkdev(clk[ssi1_gate], NULL, "imx-ssi.0");
+	clk_register_clkdev(clk[ssi2_gate], NULL, "imx-ssi.1");
 	/* i.mx35 has the i.mx21 type uart */
 	clk_register_clkdev(clk[uart1_gate], "per", "imx21-uart.0");
 	clk_register_clkdev(clk[ipg], "ipg", "imx21-uart.0");
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index fcd4e85c4ddc..346fd26f3aa6 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -232,10 +232,11 @@ config MACH_OMAP3_PANDORA
 	select OMAP_PACKAGE_CBB
 	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 
-config MACH_OMAP3_TOUCHBOOK
+config MACH_TOUCHBOOK
 	bool "OMAP3 Touch Book"
 	depends on ARCH_OMAP3
 	default y
+	select OMAP_PACKAGE_CBB
 
 config MACH_OMAP_3430SDP
 	bool "OMAP 3430 SDP board"
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index eb203ec193d0..7706fdfd0252 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -235,7 +235,7 @@ obj-$(CONFIG_MACH_OMAP_3630SDP)		+= board-zoom-display.o
 obj-$(CONFIG_MACH_CM_T35)		+= board-cm-t35.o
 obj-$(CONFIG_MACH_CM_T3517)		+= board-cm-t3517.o
 obj-$(CONFIG_MACH_IGEP0020)		+= board-igep0020.o
-obj-$(CONFIG_MACH_OMAP3_TOUCHBOOK)	+= board-omap3touchbook.o
+obj-$(CONFIG_MACH_TOUCHBOOK)		+= board-omap3touchbook.o
 obj-$(CONFIG_MACH_OMAP_4430SDP)		+= board-4430sdp.o
 obj-$(CONFIG_MACH_OMAP4_PANDA)		+= board-omap4panda.o
 
diff --git a/arch/arm/mach-omap2/clock33xx_data.c b/arch/arm/mach-omap2/clock33xx_data.c
index 7aa5ecaee5a2..8e06de665b14 100644
--- a/arch/arm/mach-omap2/clock33xx_data.c
+++ b/arch/arm/mach-omap2/clock33xx_data.c
@@ -1036,13 +1036,13 @@ static struct omap_clk am33xx_clks[] = {
 	CLK(NULL,	"mmu_fck",		&mmu_fck,	CK_AM33XX),
 	CLK(NULL,	"smartreflex0_fck",	&smartreflex0_fck,	CK_AM33XX),
 	CLK(NULL,	"smartreflex1_fck",	&smartreflex1_fck,	CK_AM33XX),
-	CLK(NULL,	"gpt1_fck",		&timer1_fck,	CK_AM33XX),
-	CLK(NULL,	"gpt2_fck",		&timer2_fck,	CK_AM33XX),
-	CLK(NULL,	"gpt3_fck",		&timer3_fck,	CK_AM33XX),
-	CLK(NULL,	"gpt4_fck",		&timer4_fck,	CK_AM33XX),
-	CLK(NULL,	"gpt5_fck",		&timer5_fck,	CK_AM33XX),
-	CLK(NULL,	"gpt6_fck",		&timer6_fck,	CK_AM33XX),
-	CLK(NULL,	"gpt7_fck",		&timer7_fck,	CK_AM33XX),
+	CLK(NULL,	"timer1_fck",		&timer1_fck,	CK_AM33XX),
+	CLK(NULL,	"timer2_fck",		&timer2_fck,	CK_AM33XX),
+	CLK(NULL,	"timer3_fck",		&timer3_fck,	CK_AM33XX),
+	CLK(NULL,	"timer4_fck",		&timer4_fck,	CK_AM33XX),
+	CLK(NULL,	"timer5_fck",		&timer5_fck,	CK_AM33XX),
+	CLK(NULL,	"timer6_fck",		&timer6_fck,	CK_AM33XX),
+	CLK(NULL,	"timer7_fck",		&timer7_fck,	CK_AM33XX),
 	CLK(NULL,	"usbotg_fck",		&usbotg_fck,	CK_AM33XX),
 	CLK(NULL,	"ieee5000_fck",		&ieee5000_fck,	CK_AM33XX),
 	CLK(NULL,	"wdt1_fck",		&wdt1_fck,	CK_AM33XX),
diff --git a/arch/arm/mach-omap2/clockdomain2xxx_3xxx.c b/arch/arm/mach-omap2/clockdomain2xxx_3xxx.c
index a0d68dbecfa3..f99e65cfb862 100644
--- a/arch/arm/mach-omap2/clockdomain2xxx_3xxx.c
+++ b/arch/arm/mach-omap2/clockdomain2xxx_3xxx.c
@@ -241,6 +241,52 @@ static void omap3_clkdm_deny_idle(struct clockdomain *clkdm)
 		_clkdm_del_autodeps(clkdm);
 }
 
+static int omap3xxx_clkdm_clk_enable(struct clockdomain *clkdm)
+{
+	bool hwsup = false;
+
+	if (!clkdm->clktrctrl_mask)
+		return 0;
+
+	hwsup = omap2_cm_is_clkdm_in_hwsup(clkdm->pwrdm.ptr->prcm_offs,
+				clkdm->clktrctrl_mask);
+
+	if (hwsup) {
+		/* Disable HW transitions when we are changing deps */
+		_disable_hwsup(clkdm);
+		_clkdm_add_autodeps(clkdm);
+		_enable_hwsup(clkdm);
+	} else {
+		if (clkdm->flags & CLKDM_CAN_FORCE_WAKEUP)
+			omap3_clkdm_wakeup(clkdm);
+	}
+
+	return 0;
+}
+
+static int omap3xxx_clkdm_clk_disable(struct clockdomain *clkdm)
+{
+	bool hwsup = false;
+
+	if (!clkdm->clktrctrl_mask)
+		return 0;
+
+	hwsup = omap2_cm_is_clkdm_in_hwsup(clkdm->pwrdm.ptr->prcm_offs,
+				clkdm->clktrctrl_mask);
+
+	if (hwsup) {
+		/* Disable HW transitions when we are changing deps */
+		_disable_hwsup(clkdm);
+		_clkdm_del_autodeps(clkdm);
+		_enable_hwsup(clkdm);
+	} else {
+		if (clkdm->flags & CLKDM_CAN_FORCE_SLEEP)
+			omap3_clkdm_sleep(clkdm);
+	}
+
+	return 0;
+}
+
 struct clkdm_ops omap2_clkdm_operations = {
 	.clkdm_add_wkdep	= omap2_clkdm_add_wkdep,
 	.clkdm_del_wkdep	= omap2_clkdm_del_wkdep,
@@ -267,6 +313,6 @@ struct clkdm_ops omap3_clkdm_operations = {
 	.clkdm_wakeup		= omap3_clkdm_wakeup,
 	.clkdm_allow_idle	= omap3_clkdm_allow_idle,
 	.clkdm_deny_idle	= omap3_clkdm_deny_idle,
-	.clkdm_clk_enable	= omap2_clkdm_clk_enable,
-	.clkdm_clk_disable	= omap2_clkdm_clk_disable,
+	.clkdm_clk_enable	= omap3xxx_clkdm_clk_enable,
+	.clkdm_clk_disable	= omap3xxx_clkdm_clk_disable,
 };
diff --git a/arch/arm/mach-omap2/cm-regbits-34xx.h b/arch/arm/mach-omap2/cm-regbits-34xx.h
index 766338fe4d34..975f6bda0e0b 100644
--- a/arch/arm/mach-omap2/cm-regbits-34xx.h
+++ b/arch/arm/mach-omap2/cm-regbits-34xx.h
@@ -67,6 +67,7 @@
 #define OMAP3430_EN_IVA2_DPLL_MASK			(0x7 << 0)
 
 /* CM_IDLEST_IVA2 */
+#define OMAP3430_ST_IVA2_SHIFT				0
 #define OMAP3430_ST_IVA2_MASK				(1 << 0)
 
 /* CM_IDLEST_PLL_IVA2 */
diff --git a/arch/arm/mach-omap2/omap-wakeupgen.c b/arch/arm/mach-omap2/omap-wakeupgen.c
index b54427dec2a3..ecaad7d371ee 100644
--- a/arch/arm/mach-omap2/omap-wakeupgen.c
+++ b/arch/arm/mach-omap2/omap-wakeupgen.c
@@ -47,7 +47,7 @@
 static void __iomem *wakeupgen_base;
 static void __iomem *sar_base;
 static DEFINE_SPINLOCK(wakeupgen_lock);
-static unsigned int irq_target_cpu[NR_IRQS];
+static unsigned int irq_target_cpu[MAX_IRQS];
 static unsigned int irq_banks = MAX_NR_REG_BANKS;
 static unsigned int max_irqs = MAX_IRQS;
 static unsigned int omap_secure_apis;
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 80b7359500f1..3615e0d9ee3c 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -1889,6 +1889,7 @@ static int _enable(struct omap_hwmod *oh)
 			_enable_sysc(oh);
 		}
 	} else {
+		_omap4_disable_module(oh);
 		_disable_clocks(oh);
 		pr_debug("omap_hwmod: %s: _wait_target_ready: %d\n",
 			 oh->name, r);
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index a1df9d4690f7..b1675e6214d3 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -100,9 +100,9 @@ static struct omap_hwmod omap3xxx_mpu_hwmod = {
 
 /* IVA2 (IVA2) */
 static struct omap_hwmod_rst_info omap3xxx_iva_resets[] = {
-	{ .name = "logic", .rst_shift = 0 },
-	{ .name = "seq0", .rst_shift = 1 },
-	{ .name = "seq1", .rst_shift = 2 },
+	{ .name = "logic", .rst_shift = 0, .st_shift = 8 },
+	{ .name = "seq0", .rst_shift = 1, .st_shift = 9 },
+	{ .name = "seq1", .rst_shift = 2, .st_shift = 10 },
 };
 
 static struct omap_hwmod omap3xxx_iva_hwmod = {
@@ -112,6 +112,15 @@ static struct omap_hwmod omap3xxx_iva_hwmod = {
 	.rst_lines	= omap3xxx_iva_resets,
 	.rst_lines_cnt	= ARRAY_SIZE(omap3xxx_iva_resets),
 	.main_clk	= "iva2_ck",
+	.prcm = {
+		.omap2 = {
+			.module_offs = OMAP3430_IVA2_MOD,
+			.prcm_reg_id = 1,
+			.module_bit = OMAP3430_CM_FCLKEN_IVA2_EN_IVA2_SHIFT,
+			.idlest_reg_id = 1,
+			.idlest_idle_bit = OMAP3430_ST_IVA2_SHIFT,
+		}
+	},
 };
 
 /* timer class */
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index f033f950a232..f9bcb24cd515 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -4209,7 +4209,7 @@ static struct omap_hwmod_ocp_if omap44xx_dsp__iva = {
 };
 
 /* dsp -> sl2if */
-static struct omap_hwmod_ocp_if omap44xx_dsp__sl2if = {
+static struct omap_hwmod_ocp_if __maybe_unused omap44xx_dsp__sl2if = {
 	.master		= &omap44xx_dsp_hwmod,
 	.slave		= &omap44xx_sl2if_hwmod,
 	.clk		= "dpll_iva_m5x2_ck",
@@ -4827,7 +4827,7 @@ static struct omap_hwmod_ocp_if omap44xx_l3_main_2__iss = {
 };
 
 /* iva -> sl2if */
-static struct omap_hwmod_ocp_if omap44xx_iva__sl2if = {
+static struct omap_hwmod_ocp_if __maybe_unused omap44xx_iva__sl2if = {
 	.master		= &omap44xx_iva_hwmod,
 	.slave		= &omap44xx_sl2if_hwmod,
 	.clk		= "dpll_iva_m5x2_ck",
@@ -5361,7 +5361,7 @@ static struct omap_hwmod_ocp_if omap44xx_l4_wkup__scrm = {
 };
 
 /* l3_main_2 -> sl2if */
-static struct omap_hwmod_ocp_if omap44xx_l3_main_2__sl2if = {
+static struct omap_hwmod_ocp_if __maybe_unused omap44xx_l3_main_2__sl2if = {
 	.master		= &omap44xx_l3_main_2_hwmod,
 	.slave		= &omap44xx_sl2if_hwmod,
 	.clk		= "l3_div_ck",
@@ -6031,7 +6031,7 @@ static struct omap_hwmod_ocp_if *omap44xx_hwmod_ocp_ifs[] __initdata = {
 	&omap44xx_l4_abe__dmic,
 	&omap44xx_l4_abe__dmic_dma,
 	&omap44xx_dsp__iva,
-	&omap44xx_dsp__sl2if,
+	/* &omap44xx_dsp__sl2if, */
 	&omap44xx_l4_cfg__dsp,
 	&omap44xx_l3_main_2__dss,
 	&omap44xx_l4_per__dss,
@@ -6067,7 +6067,7 @@ static struct omap_hwmod_ocp_if *omap44xx_hwmod_ocp_ifs[] __initdata = {
 	&omap44xx_l4_per__i2c4,
 	&omap44xx_l3_main_2__ipu,
 	&omap44xx_l3_main_2__iss,
-	&omap44xx_iva__sl2if,
+	/* &omap44xx_iva__sl2if, */
 	&omap44xx_l3_main_2__iva,
 	&omap44xx_l4_wkup__kbd,
 	&omap44xx_l4_cfg__mailbox,
@@ -6098,7 +6098,7 @@ static struct omap_hwmod_ocp_if *omap44xx_hwmod_ocp_ifs[] __initdata = {
 	&omap44xx_l4_cfg__cm_core,
 	&omap44xx_l4_wkup__prm,
 	&omap44xx_l4_wkup__scrm,
-	&omap44xx_l3_main_2__sl2if,
+	/* &omap44xx_l3_main_2__sl2if, */
 	&omap44xx_l4_abe__slimbus1,
 	&omap44xx_l4_abe__slimbus1_dma,
 	&omap44xx_l4_per__slimbus2,
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index e17cf974d16c..5214d5bfba27 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -262,6 +262,7 @@ static u32 notrace dmtimer_read_sched_clock(void)
 	return 0;
 }
 
+#ifdef CONFIG_OMAP_32K_TIMER
 /* Setup free-running counter for clocksource */
 static int __init omap2_sync32k_clocksource_init(void)
 {
@@ -301,6 +302,12 @@ static int __init omap2_sync32k_clocksource_init(void)
 
 	return ret;
 }
+#else
+static inline int omap2_sync32k_clocksource_init(void)
+{
+	return -ENODEV;
+}
+#endif
 
 static void __init omap2_gptimer_clocksource_init(int gptimer_id,
 						const char *fck_source)
diff --git a/arch/arm/mach-tegra/Kconfig b/arch/arm/mach-tegra/Kconfig
index b3226f80c985..5f3c03b61f8e 100644
--- a/arch/arm/mach-tegra/Kconfig
+++ b/arch/arm/mach-tegra/Kconfig
@@ -110,13 +110,6 @@ config TEGRA_DEBUG_UART_AUTO_SCRATCH
 
 endchoice
 
-config TEGRA_SYSTEM_DMA
-	bool "Enable system DMA driver for NVIDIA Tegra SoCs"
-	default y
-	help
-	  Adds system DMA functionality for NVIDIA Tegra SoCs, used by
-	  several Tegra device drivers
-
 config TEGRA_EMC_SCALING_ENABLE
 	bool "Enable scaling the memory frequency"
 
diff --git a/arch/arm/mach-tegra/Makefile b/arch/arm/mach-tegra/Makefile
index 56065acbd816..0974ace45558 100644
--- a/arch/arm/mach-tegra/Makefile
+++ b/arch/arm/mach-tegra/Makefile
@@ -18,7 +18,6 @@ obj-$(CONFIG_ARCH_TEGRA_3x_SOC)		+= tegra30_clocks.o
 obj-$(CONFIG_SMP)			+= platsmp.o headsmp.o
 obj-$(CONFIG_SMP)                       += reset.o
 obj-$(CONFIG_HOTPLUG_CPU)               += hotplug.o
-obj-$(CONFIG_TEGRA_SYSTEM_DMA)		+= dma.o
 obj-$(CONFIG_CPU_FREQ)                  += cpu-tegra.o
 obj-$(CONFIG_TEGRA_PCI)			+= pcie.o
 obj-$(CONFIG_USB_SUPPORT)		+= usb_phy.o
diff --git a/arch/arm/mach-tegra/apbio.c b/arch/arm/mach-tegra/apbio.c
index 643a37809a15..b5015d0f1912 100644
--- a/arch/arm/mach-tegra/apbio.c
+++ b/arch/arm/mach-tegra/apbio.c
@@ -28,7 +28,7 @@
 
 #include "apbio.h"
 
-#if defined(CONFIG_TEGRA_SYSTEM_DMA) || defined(CONFIG_TEGRA20_APB_DMA)
+#if defined(CONFIG_TEGRA20_APB_DMA)
 static DEFINE_MUTEX(tegra_apb_dma_lock);
 static u32 *tegra_apb_bb;
 static dma_addr_t tegra_apb_bb_phys;
@@ -37,121 +37,6 @@ static DECLARE_COMPLETION(tegra_apb_wait);
 static u32 tegra_apb_readl_direct(unsigned long offset);
 static void tegra_apb_writel_direct(u32 value, unsigned long offset);
 
-#if defined(CONFIG_TEGRA_SYSTEM_DMA)
-static struct tegra_dma_channel *tegra_apb_dma;
-
-bool tegra_apb_init(void)
-{
-	struct tegra_dma_channel *ch;
-
-	mutex_lock(&tegra_apb_dma_lock);
-
-	/* Check to see if we raced to setup */
-	if (tegra_apb_dma)
-		goto out;
-
-	ch = tegra_dma_allocate_channel(TEGRA_DMA_MODE_ONESHOT |
-		TEGRA_DMA_SHARED);
-
-	if (!ch)
-		goto out_fail;
-
-	tegra_apb_bb = dma_alloc_coherent(NULL, sizeof(u32),
-		&tegra_apb_bb_phys, GFP_KERNEL);
-	if (!tegra_apb_bb) {
-		pr_err("%s: can not allocate bounce buffer\n", __func__);
-		tegra_dma_free_channel(ch);
-		goto out_fail;
-	}
-
-	tegra_apb_dma = ch;
-out:
-	mutex_unlock(&tegra_apb_dma_lock);
-	return true;
-
-out_fail:
-	mutex_unlock(&tegra_apb_dma_lock);
-	return false;
-}
-
-static void apb_dma_complete(struct tegra_dma_req *req)
-{
-	complete(&tegra_apb_wait);
-}
-
-static u32 tegra_apb_readl_using_dma(unsigned long offset)
-{
-	struct tegra_dma_req req;
-	int ret;
-
-	if (!tegra_apb_dma && !tegra_apb_init())
-		return tegra_apb_readl_direct(offset);
-
-	mutex_lock(&tegra_apb_dma_lock);
-	req.complete = apb_dma_complete;
-	req.to_memory = 1;
-	req.dest_addr = tegra_apb_bb_phys;
-	req.dest_bus_width = 32;
-	req.dest_wrap = 1;
-	req.source_addr = offset;
-	req.source_bus_width = 32;
-	req.source_wrap = 4;
-	req.req_sel = TEGRA_DMA_REQ_SEL_CNTR;
-	req.size = 4;
-
-	INIT_COMPLETION(tegra_apb_wait);
-
-	tegra_dma_enqueue_req(tegra_apb_dma, &req);
-
-	ret = wait_for_completion_timeout(&tegra_apb_wait,
-		msecs_to_jiffies(50));
-
-	if (WARN(ret == 0, "apb read dma timed out")) {
-		tegra_dma_dequeue_req(tegra_apb_dma, &req);
-		*(u32 *)tegra_apb_bb = 0;
-	}
-
-	mutex_unlock(&tegra_apb_dma_lock);
-	return *((u32 *)tegra_apb_bb);
-}
-
-static void tegra_apb_writel_using_dma(u32 value, unsigned long offset)
-{
-	struct tegra_dma_req req;
-	int ret;
-
-	if (!tegra_apb_dma && !tegra_apb_init()) {
-		tegra_apb_writel_direct(value, offset);
-		return;
-	}
-
-	mutex_lock(&tegra_apb_dma_lock);
-	*((u32 *)tegra_apb_bb) = value;
-	req.complete = apb_dma_complete;
-	req.to_memory = 0;
-	req.dest_addr = offset;
-	req.dest_wrap = 4;
-	req.dest_bus_width = 32;
-	req.source_addr = tegra_apb_bb_phys;
-	req.source_bus_width = 32;
-	req.source_wrap = 1;
-	req.req_sel = TEGRA_DMA_REQ_SEL_CNTR;
-	req.size = 4;
-
-	INIT_COMPLETION(tegra_apb_wait);
-
-	tegra_dma_enqueue_req(tegra_apb_dma, &req);
-
-	ret = wait_for_completion_timeout(&tegra_apb_wait,
-		msecs_to_jiffies(50));
-
-	if (WARN(ret == 0, "apb write dma timed out"))
-		tegra_dma_dequeue_req(tegra_apb_dma, &req);
-
-	mutex_unlock(&tegra_apb_dma_lock);
-}
-
-#else
 static struct dma_chan *tegra_apb_dma_chan;
 static struct dma_slave_config dma_sconfig;
 
@@ -279,7 +164,6 @@ static void tegra_apb_writel_using_dma(u32 value, unsigned long offset)
 		pr_err("error in writing offset 0x%08lx using dma\n", offset);
 	mutex_unlock(&tegra_apb_dma_lock);
 }
-#endif
 #else
 #define tegra_apb_readl_using_dma tegra_apb_readl_direct
 #define tegra_apb_writel_using_dma tegra_apb_writel_direct
diff --git a/arch/arm/mach-tegra/dma.c b/arch/arm/mach-tegra/dma.c
deleted file mode 100644
index 29c5114d607c..000000000000
--- a/arch/arm/mach-tegra/dma.c
+++ /dev/null
@@ -1,823 +0,0 @@
-/*
- * arch/arm/mach-tegra/dma.c
- *
- * System DMA driver for NVIDIA Tegra SoCs
- *
- * Copyright (c) 2008-2009, NVIDIA Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
- */
-
-#include <linux/io.h>
-#include <linux/interrupt.h>
-#include <linux/module.h>
-#include <linux/spinlock.h>
-#include <linux/err.h>
-#include <linux/irq.h>
-#include <linux/delay.h>
-#include <linux/clk.h>
-#include <mach/dma.h>
-#include <mach/irqs.h>
-#include <mach/iomap.h>
-#include <mach/suspend.h>
-
-#include "apbio.h"
-
-#define APB_DMA_GEN				0x000
-#define GEN_ENABLE				(1<<31)
-
-#define APB_DMA_CNTRL				0x010
-
-#define APB_DMA_IRQ_MASK			0x01c
-
-#define APB_DMA_IRQ_MASK_SET			0x020
-
-#define APB_DMA_CHAN_CSR			0x000
-#define CSR_ENB					(1<<31)
-#define CSR_IE_EOC				(1<<30)
-#define CSR_HOLD				(1<<29)
-#define CSR_DIR					(1<<28)
-#define CSR_ONCE				(1<<27)
-#define CSR_FLOW				(1<<21)
-#define CSR_REQ_SEL_SHIFT			16
-#define CSR_WCOUNT_SHIFT			2
-#define CSR_WCOUNT_MASK				0xFFFC
-
-#define APB_DMA_CHAN_STA				0x004
-#define STA_BUSY				(1<<31)
-#define STA_ISE_EOC				(1<<30)
-#define STA_HALT				(1<<29)
-#define STA_PING_PONG				(1<<28)
-#define STA_COUNT_SHIFT				2
-#define STA_COUNT_MASK				0xFFFC
-
-#define APB_DMA_CHAN_AHB_PTR				0x010
-
-#define APB_DMA_CHAN_AHB_SEQ				0x014
-#define AHB_SEQ_INTR_ENB			(1<<31)
-#define AHB_SEQ_BUS_WIDTH_SHIFT			28
-#define AHB_SEQ_BUS_WIDTH_MASK			(0x7<<AHB_SEQ_BUS_WIDTH_SHIFT)
-#define AHB_SEQ_BUS_WIDTH_8			(0<<AHB_SEQ_BUS_WIDTH_SHIFT)
-#define AHB_SEQ_BUS_WIDTH_16			(1<<AHB_SEQ_BUS_WIDTH_SHIFT)
-#define AHB_SEQ_BUS_WIDTH_32			(2<<AHB_SEQ_BUS_WIDTH_SHIFT)
-#define AHB_SEQ_BUS_WIDTH_64			(3<<AHB_SEQ_BUS_WIDTH_SHIFT)
-#define AHB_SEQ_BUS_WIDTH_128			(4<<AHB_SEQ_BUS_WIDTH_SHIFT)
-#define AHB_SEQ_DATA_SWAP			(1<<27)
-#define AHB_SEQ_BURST_MASK			(0x7<<24)
-#define AHB_SEQ_BURST_1				(4<<24)
-#define AHB_SEQ_BURST_4				(5<<24)
-#define AHB_SEQ_BURST_8				(6<<24)
-#define AHB_SEQ_DBL_BUF				(1<<19)
-#define AHB_SEQ_WRAP_SHIFT			16
-#define AHB_SEQ_WRAP_MASK			(0x7<<AHB_SEQ_WRAP_SHIFT)
-
-#define APB_DMA_CHAN_APB_PTR				0x018
-
-#define APB_DMA_CHAN_APB_SEQ				0x01c
-#define APB_SEQ_BUS_WIDTH_SHIFT			28
-#define APB_SEQ_BUS_WIDTH_MASK			(0x7<<APB_SEQ_BUS_WIDTH_SHIFT)
-#define APB_SEQ_BUS_WIDTH_8			(0<<APB_SEQ_BUS_WIDTH_SHIFT)
-#define APB_SEQ_BUS_WIDTH_16			(1<<APB_SEQ_BUS_WIDTH_SHIFT)
-#define APB_SEQ_BUS_WIDTH_32			(2<<APB_SEQ_BUS_WIDTH_SHIFT)
-#define APB_SEQ_BUS_WIDTH_64			(3<<APB_SEQ_BUS_WIDTH_SHIFT)
-#define APB_SEQ_BUS_WIDTH_128			(4<<APB_SEQ_BUS_WIDTH_SHIFT)
-#define APB_SEQ_DATA_SWAP			(1<<27)
-#define APB_SEQ_WRAP_SHIFT			16
-#define APB_SEQ_WRAP_MASK			(0x7<<APB_SEQ_WRAP_SHIFT)
-
-#define TEGRA_SYSTEM_DMA_CH_NR			16
-#define TEGRA_SYSTEM_DMA_AVP_CH_NUM		4
-#define TEGRA_SYSTEM_DMA_CH_MIN			0
-#define TEGRA_SYSTEM_DMA_CH_MAX	\
-	(TEGRA_SYSTEM_DMA_CH_NR - TEGRA_SYSTEM_DMA_AVP_CH_NUM - 1)
-
-#define NV_DMA_MAX_TRASFER_SIZE 0x10000
-
-static const unsigned int ahb_addr_wrap_table[8] = {
-	0, 32, 64, 128, 256, 512, 1024, 2048
-};
-
-static const unsigned int apb_addr_wrap_table[8] = {
-	0, 1, 2, 4, 8, 16, 32, 64
-};
-
-static const unsigned int bus_width_table[5] = {
-	8, 16, 32, 64, 128
-};
-
-#define TEGRA_DMA_NAME_SIZE 16
-struct tegra_dma_channel {
-	struct list_head	list;
-	int			id;
-	spinlock_t		lock;
-	char			name[TEGRA_DMA_NAME_SIZE];
-	void  __iomem		*addr;
-	int			mode;
-	int			irq;
-	int			req_transfer_count;
-};
-
-#define  NV_DMA_MAX_CHANNELS  32
-
-static bool tegra_dma_initialized;
-static DEFINE_MUTEX(tegra_dma_lock);
-static DEFINE_SPINLOCK(enable_lock);
-
-static DECLARE_BITMAP(channel_usage, NV_DMA_MAX_CHANNELS);
-static struct tegra_dma_channel dma_channels[NV_DMA_MAX_CHANNELS];
-
-static void tegra_dma_update_hw(struct tegra_dma_channel *ch,
-	struct tegra_dma_req *req);
-static void tegra_dma_update_hw_partial(struct tegra_dma_channel *ch,
-	struct tegra_dma_req *req);
-static void tegra_dma_stop(struct tegra_dma_channel *ch);
-
-void tegra_dma_flush(struct tegra_dma_channel *ch)
-{
-}
-EXPORT_SYMBOL(tegra_dma_flush);
-
-void tegra_dma_dequeue(struct tegra_dma_channel *ch)
-{
-	struct tegra_dma_req *req;
-
-	if (tegra_dma_is_empty(ch))
-		return;
-
-	req = list_entry(ch->list.next, typeof(*req), node);
-
-	tegra_dma_dequeue_req(ch, req);
-	return;
-}
-
-static void tegra_dma_stop(struct tegra_dma_channel *ch)
-{
-	u32 csr;
-	u32 status;
-
-	csr = readl(ch->addr + APB_DMA_CHAN_CSR);
-	csr &= ~CSR_IE_EOC;
-	writel(csr, ch->addr + APB_DMA_CHAN_CSR);
-
-	csr &= ~CSR_ENB;
-	writel(csr, ch->addr + APB_DMA_CHAN_CSR);
-
-	status = readl(ch->addr + APB_DMA_CHAN_STA);
-	if (status & STA_ISE_EOC)
-		writel(status, ch->addr + APB_DMA_CHAN_STA);
-}
-
-static int tegra_dma_cancel(struct tegra_dma_channel *ch)
-{
-	unsigned long irq_flags;
-
-	spin_lock_irqsave(&ch->lock, irq_flags);
-	while (!list_empty(&ch->list))
-		list_del(ch->list.next);
-
-	tegra_dma_stop(ch);
-
-	spin_unlock_irqrestore(&ch->lock, irq_flags);
-	return 0;
-}
-
-static unsigned int get_channel_status(struct tegra_dma_channel *ch,
-			struct tegra_dma_req *req, bool is_stop_dma)
-{
-	void __iomem *addr = IO_ADDRESS(TEGRA_APB_DMA_BASE);
-	unsigned int status;
-
-	if (is_stop_dma) {
-		/*
-		 * STOP the DMA and get the transfer count.
-		 * Getting the transfer count is tricky.
-		 *  - Globally disable DMA on all channels
-		 *  - Read the channel's status register to know the number
-		 *    of pending bytes to be transfered.
-		 *  - Stop the dma channel
-		 *  - Globally re-enable DMA to resume other transfers
-		 */
-		spin_lock(&enable_lock);
-		writel(0, addr + APB_DMA_GEN);
-		udelay(20);
-		status = readl(ch->addr + APB_DMA_CHAN_STA);
-		tegra_dma_stop(ch);
-		writel(GEN_ENABLE, addr + APB_DMA_GEN);
-		spin_unlock(&enable_lock);
-		if (status & STA_ISE_EOC) {
-			pr_err("Got Dma Int here clearing");
-			writel(status, ch->addr + APB_DMA_CHAN_STA);
-		}
-		req->status = TEGRA_DMA_REQ_ERROR_ABORTED;
-	} else {
-		status = readl(ch->addr + APB_DMA_CHAN_STA);
-	}
-	return status;
-}
-
-/* should be called with the channel lock held */
-static unsigned int dma_active_count(struct tegra_dma_channel *ch,
-	struct tegra_dma_req *req, unsigned int status)
-{
-	unsigned int to_transfer;
-	unsigned int req_transfer_count;
-	unsigned int bytes_transferred;
-
-	to_transfer = ((status & STA_COUNT_MASK) >> STA_COUNT_SHIFT) + 1;
-	req_transfer_count = ch->req_transfer_count + 1;
-	bytes_transferred = req_transfer_count;
-	if (status & STA_BUSY)
-		bytes_transferred -= to_transfer;
-	/*
-	 * In continuous transfer mode, DMA only tracks the count of the
-	 * half DMA buffer. So, if the DMA already finished half the DMA
-	 * then add the half buffer to the completed count.
-	 */
-	if (ch->mode & TEGRA_DMA_MODE_CONTINOUS) {
-		if (req->buffer_status == TEGRA_DMA_REQ_BUF_STATUS_HALF_FULL)
-			bytes_transferred += req_transfer_count;
-		if (status & STA_ISE_EOC)
-			bytes_transferred += req_transfer_count;
-	}
-	bytes_transferred *= 4;
-	return bytes_transferred;
-}
-
-int tegra_dma_dequeue_req(struct tegra_dma_channel *ch,
-	struct tegra_dma_req *_req)
-{
-	unsigned int status;
-	struct tegra_dma_req *req = NULL;
-	int found = 0;
-	unsigned long irq_flags;
-	int stop = 0;
-
-	spin_lock_irqsave(&ch->lock, irq_flags);
-
-	if (list_entry(ch->list.next, struct tegra_dma_req, node) == _req)
-		stop = 1;
-
-	list_for_each_entry(req, &ch->list, node) {
-		if (req == _req) {
-			list_del(&req->node);
-			found = 1;
-			break;
-		}
-	}
-	if (!found) {
-		spin_unlock_irqrestore(&ch->lock, irq_flags);
-		return 0;
-	}
-
-	if (!stop)
-		goto skip_stop_dma;
-
-	status = get_channel_status(ch, req, true);
-	req->bytes_transferred = dma_active_count(ch, req, status);
-
-	if (!list_empty(&ch->list)) {
-		/* if the list is not empty, queue the next request */
-		struct tegra_dma_req *next_req;
-		next_req = list_entry(ch->list.next,
-			typeof(*next_req), node);
-		tegra_dma_update_hw(ch, next_req);
-	}
-
-skip_stop_dma:
-	req->status = -TEGRA_DMA_REQ_ERROR_ABORTED;
-
-	spin_unlock_irqrestore(&ch->lock, irq_flags);
-
-	/* Callback should be called without any lock */
-	req->complete(req);
-	return 0;
-}
-EXPORT_SYMBOL(tegra_dma_dequeue_req);
-
-bool tegra_dma_is_empty(struct tegra_dma_channel *ch)
-{
-	unsigned long irq_flags;
-	bool is_empty;
-
-	spin_lock_irqsave(&ch->lock, irq_flags);
-	if (list_empty(&ch->list))
-		is_empty = true;
-	else
-		is_empty = false;
-	spin_unlock_irqrestore(&ch->lock, irq_flags);
-	return is_empty;
-}
-EXPORT_SYMBOL(tegra_dma_is_empty);
-
-bool tegra_dma_is_req_inflight(struct tegra_dma_channel *ch,
-	struct tegra_dma_req *_req)
-{
-	unsigned long irq_flags;
-	struct tegra_dma_req *req;
-
-	spin_lock_irqsave(&ch->lock, irq_flags);
-	list_for_each_entry(req, &ch->list, node) {
-		if (req == _req) {
-			spin_unlock_irqrestore(&ch->lock, irq_flags);
-			return true;
-		}
-	}
-	spin_unlock_irqrestore(&ch->lock, irq_flags);
-	return false;
-}
-EXPORT_SYMBOL(tegra_dma_is_req_inflight);
-
-int tegra_dma_enqueue_req(struct tegra_dma_channel *ch,
-	struct tegra_dma_req *req)
-{
-	unsigned long irq_flags;
-	struct tegra_dma_req *_req;
-	int start_dma = 0;
-
-	if (req->size > NV_DMA_MAX_TRASFER_SIZE ||
-		req->source_addr & 0x3 || req->dest_addr & 0x3) {
-		pr_err("Invalid DMA request for channel %d\n", ch->id);
-		return -EINVAL;
-	}
-
-	spin_lock_irqsave(&ch->lock, irq_flags);
-
-	list_for_each_entry(_req, &ch->list, node) {
-		if (req == _req) {
-		    spin_unlock_irqrestore(&ch->lock, irq_flags);
-		    return -EEXIST;
-		}
-	}
-
-	req->bytes_transferred = 0;
-	req->status = 0;
-	req->buffer_status = 0;
-	if (list_empty(&ch->list))
-		start_dma = 1;
-
-	list_add_tail(&req->node, &ch->list);
-
-	if (start_dma)
-		tegra_dma_update_hw(ch, req);
-
-	spin_unlock_irqrestore(&ch->lock, irq_flags);
-
-	return 0;
-}
-EXPORT_SYMBOL(tegra_dma_enqueue_req);
-
-struct tegra_dma_channel *tegra_dma_allocate_channel(int mode)
-{
-	int channel;
-	struct tegra_dma_channel *ch = NULL;
-
-	if (!tegra_dma_initialized)
-		return NULL;
-
-	mutex_lock(&tegra_dma_lock);
-
-	/* first channel is the shared channel */
-	if (mode & TEGRA_DMA_SHARED) {
-		channel = TEGRA_SYSTEM_DMA_CH_MIN;
-	} else {
-		channel = find_first_zero_bit(channel_usage,
-			ARRAY_SIZE(dma_channels));
-		if (channel >= ARRAY_SIZE(dma_channels))
-			goto out;
-	}
-	__set_bit(channel, channel_usage);
-	ch = &dma_channels[channel];
-	ch->mode = mode;
-
-out:
-	mutex_unlock(&tegra_dma_lock);
-	return ch;
-}
-EXPORT_SYMBOL(tegra_dma_allocate_channel);
-
-void tegra_dma_free_channel(struct tegra_dma_channel *ch)
-{
-	if (ch->mode & TEGRA_DMA_SHARED)
-		return;
-	tegra_dma_cancel(ch);
-	mutex_lock(&tegra_dma_lock);
-	__clear_bit(ch->id, channel_usage);
-	mutex_unlock(&tegra_dma_lock);
-}
-EXPORT_SYMBOL(tegra_dma_free_channel);
-
-static void tegra_dma_update_hw_partial(struct tegra_dma_channel *ch,
-	struct tegra_dma_req *req)
-{
-	u32 apb_ptr;
-	u32 ahb_ptr;
-
-	if (req->to_memory) {
-		apb_ptr = req->source_addr;
-		ahb_ptr = req->dest_addr;
-	} else {
-		apb_ptr = req->dest_addr;
-		ahb_ptr = req->source_addr;
-	}
-	writel(apb_ptr, ch->addr + APB_DMA_CHAN_APB_PTR);
-	writel(ahb_ptr, ch->addr + APB_DMA_CHAN_AHB_PTR);
-
-	req->status = TEGRA_DMA_REQ_INFLIGHT;
-	return;
-}
-
-static void tegra_dma_update_hw(struct tegra_dma_channel *ch,
-	struct tegra_dma_req *req)
-{
-	int ahb_addr_wrap;
-	int apb_addr_wrap;
-	int ahb_bus_width;
-	int apb_bus_width;
-	int index;
-
-	u32 ahb_seq;
-	u32 apb_seq;
-	u32 ahb_ptr;
-	u32 apb_ptr;
-	u32 csr;
-
-	csr = CSR_IE_EOC | CSR_FLOW;
-	ahb_seq = AHB_SEQ_INTR_ENB | AHB_SEQ_BURST_1;
-	apb_seq = 0;
-
-	csr |= req->req_sel << CSR_REQ_SEL_SHIFT;
-
-	/* One shot mode is always single buffered,
-	 * continuous mode is always double buffered
-	 * */
-	if (ch->mode & TEGRA_DMA_MODE_ONESHOT) {
-		csr |= CSR_ONCE;
-		ch->req_transfer_count = (req->size >> 2) - 1;
-	} else {
-		ahb_seq |= AHB_SEQ_DBL_BUF;
-
-		/* In double buffered mode, we set the size to half the
-		 * requested size and interrupt when half the buffer
-		 * is full */
-		ch->req_transfer_count = (req->size >> 3) - 1;
-	}
-
-	csr |= ch->req_transfer_count << CSR_WCOUNT_SHIFT;
-
-	if (req->to_memory) {
-		apb_ptr = req->source_addr;
-		ahb_ptr = req->dest_addr;
-
-		apb_addr_wrap = req->source_wrap;
-		ahb_addr_wrap = req->dest_wrap;
-		apb_bus_width = req->source_bus_width;
-		ahb_bus_width = req->dest_bus_width;
-
-	} else {
-		csr |= CSR_DIR;
-		apb_ptr = req->dest_addr;
-		ahb_ptr = req->source_addr;
-
-		apb_addr_wrap = req->dest_wrap;
-		ahb_addr_wrap = req->source_wrap;
-		apb_bus_width = req->dest_bus_width;
-		ahb_bus_width = req->source_bus_width;
-	}
-
-	apb_addr_wrap >>= 2;
-	ahb_addr_wrap >>= 2;
-
-	/* set address wrap for APB size */
-	index = 0;
-	do  {
-		if (apb_addr_wrap_table[index] == apb_addr_wrap)
-			break;
-		index++;
-	} while (index < ARRAY_SIZE(apb_addr_wrap_table));
-	BUG_ON(index == ARRAY_SIZE(apb_addr_wrap_table));
-	apb_seq |= index << APB_SEQ_WRAP_SHIFT;
-
-	/* set address wrap for AHB size */
-	index = 0;
-	do  {
-		if (ahb_addr_wrap_table[index] == ahb_addr_wrap)
-			break;
-		index++;
-	} while (index < ARRAY_SIZE(ahb_addr_wrap_table));
-	BUG_ON(index == ARRAY_SIZE(ahb_addr_wrap_table));
-	ahb_seq |= index << AHB_SEQ_WRAP_SHIFT;
-
-	for (index = 0; index < ARRAY_SIZE(bus_width_table); index++) {
-		if (bus_width_table[index] == ahb_bus_width)
-			break;
-	}
-	BUG_ON(index == ARRAY_SIZE(bus_width_table));
-	ahb_seq |= index << AHB_SEQ_BUS_WIDTH_SHIFT;
-
-	for (index = 0; index < ARRAY_SIZE(bus_width_table); index++) {
-		if (bus_width_table[index] == apb_bus_width)
-			break;
-	}
-	BUG_ON(index == ARRAY_SIZE(bus_width_table));
-	apb_seq |= index << APB_SEQ_BUS_WIDTH_SHIFT;
-
-	writel(csr, ch->addr + APB_DMA_CHAN_CSR);
-	writel(apb_seq, ch->addr + APB_DMA_CHAN_APB_SEQ);
-	writel(apb_ptr, ch->addr + APB_DMA_CHAN_APB_PTR);
-	writel(ahb_seq, ch->addr + APB_DMA_CHAN_AHB_SEQ);
-	writel(ahb_ptr, ch->addr + APB_DMA_CHAN_AHB_PTR);
-
-	csr |= CSR_ENB;
-	writel(csr, ch->addr + APB_DMA_CHAN_CSR);
-
-	req->status = TEGRA_DMA_REQ_INFLIGHT;
-}
-
-static void handle_oneshot_dma(struct tegra_dma_channel *ch)
-{
-	struct tegra_dma_req *req;
-	unsigned long irq_flags;
-
-	spin_lock_irqsave(&ch->lock, irq_flags);
-	if (list_empty(&ch->list)) {
-		spin_unlock_irqrestore(&ch->lock, irq_flags);
-		return;
-	}
-
-	req = list_entry(ch->list.next, typeof(*req), node);
-	if (req) {
-		int bytes_transferred;
-
-		bytes_transferred = ch->req_transfer_count;
-		bytes_transferred += 1;
-		bytes_transferred <<= 2;
-
-		list_del(&req->node);
-		req->bytes_transferred = bytes_transferred;
-		req->status = TEGRA_DMA_REQ_SUCCESS;
-
-		spin_unlock_irqrestore(&ch->lock, irq_flags);
-		/* Callback should be called without any lock */
-		pr_debug("%s: transferred %d bytes\n", __func__,
-			req->bytes_transferred);
-		req->complete(req);
-		spin_lock_irqsave(&ch->lock, irq_flags);
-	}
-
-	if (!list_empty(&ch->list)) {
-		req = list_entry(ch->list.next, typeof(*req), node);
-		/* the complete function we just called may have enqueued
-		   another req, in which case dma has already started */
-		if (req->status != TEGRA_DMA_REQ_INFLIGHT)
-			tegra_dma_update_hw(ch, req);
-	}
-	spin_unlock_irqrestore(&ch->lock, irq_flags);
-}
-
-static void handle_continuous_dma(struct tegra_dma_channel *ch)
-{
-	struct tegra_dma_req *req;
-	unsigned long irq_flags;
-
-	spin_lock_irqsave(&ch->lock, irq_flags);
-	if (list_empty(&ch->list)) {
-		spin_unlock_irqrestore(&ch->lock, irq_flags);
-		return;
-	}
-
-	req = list_entry(ch->list.next, typeof(*req), node);
-	if (req) {
-		if (req->buffer_status == TEGRA_DMA_REQ_BUF_STATUS_EMPTY) {
-			bool is_dma_ping_complete;
-			is_dma_ping_complete = (readl(ch->addr + APB_DMA_CHAN_STA)
-						& STA_PING_PONG) ? true : false;
-			if (req->to_memory)
-				is_dma_ping_complete = !is_dma_ping_complete;
-			/* Out of sync - Release current buffer */
-			if (!is_dma_ping_complete) {
-				int bytes_transferred;
-
-				bytes_transferred = ch->req_transfer_count;
-				bytes_transferred += 1;
-				bytes_transferred <<= 3;
-				req->buffer_status = TEGRA_DMA_REQ_BUF_STATUS_FULL;
-				req->bytes_transferred = bytes_transferred;
-				req->status = TEGRA_DMA_REQ_SUCCESS;
-				tegra_dma_stop(ch);
-
-				if (!list_is_last(&req->node, &ch->list)) {
-					struct tegra_dma_req *next_req;
-
-					next_req = list_entry(req->node.next,
-						typeof(*next_req), node);
-					tegra_dma_update_hw(ch, next_req);
-				}
-
-				list_del(&req->node);
-
-				/* DMA lock is NOT held when callbak is called */
-				spin_unlock_irqrestore(&ch->lock, irq_flags);
-				req->complete(req);
-				return;
-			}
-			/* Load the next request into the hardware, if available
-			 * */
-			if (!list_is_last(&req->node, &ch->list)) {
-				struct tegra_dma_req *next_req;
-
-				next_req = list_entry(req->node.next,
-					typeof(*next_req), node);
-				tegra_dma_update_hw_partial(ch, next_req);
-			}
-			req->buffer_status = TEGRA_DMA_REQ_BUF_STATUS_HALF_FULL;
-			req->status = TEGRA_DMA_REQ_SUCCESS;
-			/* DMA lock is NOT held when callback is called */
-			spin_unlock_irqrestore(&ch->lock, irq_flags);
-			if (likely(req->threshold))
-				req->threshold(req);
-			return;
-
-		} else if (req->buffer_status ==
-			TEGRA_DMA_REQ_BUF_STATUS_HALF_FULL) {
-			/* Callback when the buffer is completely full (i.e on
-			 * the second  interrupt */
-			int bytes_transferred;
-
-			bytes_transferred = ch->req_transfer_count;
-			bytes_transferred += 1;
-			bytes_transferred <<= 3;
-
-			req->buffer_status = TEGRA_DMA_REQ_BUF_STATUS_FULL;
-			req->bytes_transferred = bytes_transferred;
-			req->status = TEGRA_DMA_REQ_SUCCESS;
-			list_del(&req->node);
-
-			/* DMA lock is NOT held when callbak is called */
-			spin_unlock_irqrestore(&ch->lock, irq_flags);
-			req->complete(req);
-			return;
-
-		} else {
-			BUG();
-		}
-	}
-	spin_unlock_irqrestore(&ch->lock, irq_flags);
-}
-
-static irqreturn_t dma_isr(int irq, void *data)
-{
-	struct tegra_dma_channel *ch = data;
-	unsigned long status;
-
-	status = readl(ch->addr + APB_DMA_CHAN_STA);
-	if (status & STA_ISE_EOC)
-		writel(status, ch->addr + APB_DMA_CHAN_STA);
-	else {
-		pr_warning("Got a spurious ISR for DMA channel %d\n", ch->id);
-		return IRQ_HANDLED;
-	}
-	return IRQ_WAKE_THREAD;
-}
-
-static irqreturn_t dma_thread_fn(int irq, void *data)
-{
-	struct tegra_dma_channel *ch = data;
-
-	if (ch->mode & TEGRA_DMA_MODE_ONESHOT)
-		handle_oneshot_dma(ch);
-	else
-		handle_continuous_dma(ch);
-
-
-	return IRQ_HANDLED;
-}
-
-int __init tegra_dma_init(void)
-{
-	int ret = 0;
-	int i;
-	unsigned int irq;
-	void __iomem *addr;
-	struct clk *c;
-
-	bitmap_fill(channel_usage, NV_DMA_MAX_CHANNELS);
-
-	c = clk_get_sys("tegra-apbdma", NULL);
-	if (IS_ERR(c)) {
-		pr_err("Unable to get clock for APB DMA\n");
-		ret = PTR_ERR(c);
-		goto fail;
-	}
-	ret = clk_prepare_enable(c);
-	if (ret != 0) {
-		pr_err("Unable to enable clock for APB DMA\n");
-		goto fail;
-	}
-
-	addr = IO_ADDRESS(TEGRA_APB_DMA_BASE);
-	writel(GEN_ENABLE, addr + APB_DMA_GEN);
-	writel(0, addr + APB_DMA_CNTRL);
-	writel(0xFFFFFFFFul >> (31 - TEGRA_SYSTEM_DMA_CH_MAX),
-	       addr + APB_DMA_IRQ_MASK_SET);
-
-	for (i = TEGRA_SYSTEM_DMA_CH_MIN; i <= TEGRA_SYSTEM_DMA_CH_MAX; i++) {
-		struct tegra_dma_channel *ch = &dma_channels[i];
-
-		ch->id = i;
-		snprintf(ch->name, TEGRA_DMA_NAME_SIZE, "dma_channel_%d", i);
-
-		ch->addr = IO_ADDRESS(TEGRA_APB_DMA_CH0_BASE +
-			TEGRA_APB_DMA_CH0_SIZE * i);
-
-		spin_lock_init(&ch->lock);
-		INIT_LIST_HEAD(&ch->list);
-
-		irq = INT_APB_DMA_CH0 + i;
-		ret = request_threaded_irq(irq, dma_isr, dma_thread_fn, 0,
-			dma_channels[i].name, ch);
-		if (ret) {
-			pr_err("Failed to register IRQ %d for DMA %d\n",
-				irq, i);
-			goto fail;
-		}
-		ch->irq = irq;
-
-		__clear_bit(i, channel_usage);
-	}
-	/* mark the shared channel allocated */
-	__set_bit(TEGRA_SYSTEM_DMA_CH_MIN, channel_usage);
-
-	tegra_dma_initialized = true;
-
-	return 0;
-fail:
-	writel(0, addr + APB_DMA_GEN);
-	for (i = TEGRA_SYSTEM_DMA_CH_MIN; i <= TEGRA_SYSTEM_DMA_CH_MAX; i++) {
-		struct tegra_dma_channel *ch = &dma_channels[i];
-		if (ch->irq)
-			free_irq(ch->irq, ch);
-	}
-	return ret;
-}
-postcore_initcall(tegra_dma_init);
-
-#ifdef CONFIG_PM
-static u32 apb_dma[5*TEGRA_SYSTEM_DMA_CH_NR + 3];
-
-void tegra_dma_suspend(void)
-{
-	void __iomem *addr = IO_ADDRESS(TEGRA_APB_DMA_BASE);
-	u32 *ctx = apb_dma;
-	int i;
-
-	*ctx++ = readl(addr + APB_DMA_GEN);
-	*ctx++ = readl(addr + APB_DMA_CNTRL);
-	*ctx++ = readl(addr + APB_DMA_IRQ_MASK);
-
-	for (i = 0; i < TEGRA_SYSTEM_DMA_CH_NR; i++) {
-		addr = IO_ADDRESS(TEGRA_APB_DMA_CH0_BASE +
-				  TEGRA_APB_DMA_CH0_SIZE * i);
-
-		*ctx++ = readl(addr + APB_DMA_CHAN_CSR);
-		*ctx++ = readl(addr + APB_DMA_CHAN_AHB_PTR);
-		*ctx++ = readl(addr + APB_DMA_CHAN_AHB_SEQ);
-		*ctx++ = readl(addr + APB_DMA_CHAN_APB_PTR);
-		*ctx++ = readl(addr + APB_DMA_CHAN_APB_SEQ);
-	}
-}
-
-void tegra_dma_resume(void)
-{
-	void __iomem *addr = IO_ADDRESS(TEGRA_APB_DMA_BASE);
-	u32 *ctx = apb_dma;
-	int i;
-
-	writel(*ctx++, addr + APB_DMA_GEN);
-	writel(*ctx++, addr + APB_DMA_CNTRL);
-	writel(*ctx++, addr + APB_DMA_IRQ_MASK);
-
-	for (i = 0; i < TEGRA_SYSTEM_DMA_CH_NR; i++) {
-		addr = IO_ADDRESS(TEGRA_APB_DMA_CH0_BASE +
-				  TEGRA_APB_DMA_CH0_SIZE * i);
-
-		writel(*ctx++, addr + APB_DMA_CHAN_CSR);
-		writel(*ctx++, addr + APB_DMA_CHAN_AHB_PTR);
-		writel(*ctx++, addr + APB_DMA_CHAN_AHB_SEQ);
-		writel(*ctx++, addr + APB_DMA_CHAN_APB_PTR);
-		writel(*ctx++, addr + APB_DMA_CHAN_APB_SEQ);
-	}
-}
-
-#endif
diff --git a/arch/arm/mach-tegra/include/mach/dma.h b/arch/arm/mach-tegra/include/mach/dma.h
index 9077092812c0..3081cc6dda3b 100644
--- a/arch/arm/mach-tegra/include/mach/dma.h
+++ b/arch/arm/mach-tegra/include/mach/dma.h
@@ -51,101 +51,4 @@
 #define TEGRA_DMA_REQ_SEL_OWR			25
 #define TEGRA_DMA_REQ_SEL_INVALID		31
 
-struct tegra_dma_req;
-struct tegra_dma_channel;
-
-enum tegra_dma_mode {
-	TEGRA_DMA_SHARED = 1,
-	TEGRA_DMA_MODE_CONTINOUS = 2,
-	TEGRA_DMA_MODE_ONESHOT = 4,
-};
-
-enum tegra_dma_req_error {
-	TEGRA_DMA_REQ_SUCCESS = 0,
-	TEGRA_DMA_REQ_ERROR_ABORTED,
-	TEGRA_DMA_REQ_INFLIGHT,
-};
-
-enum tegra_dma_req_buff_status {
-	TEGRA_DMA_REQ_BUF_STATUS_EMPTY = 0,
-	TEGRA_DMA_REQ_BUF_STATUS_HALF_FULL,
-	TEGRA_DMA_REQ_BUF_STATUS_FULL,
-};
-
-struct tegra_dma_req {
-	struct list_head node;
-	unsigned int modid;
-	int instance;
-
-	/* Called when the req is complete and from the DMA ISR context.
-	 * When this is called the req structure is no longer queued by
-	 * the DMA channel.
-	 *
-	 * State of the DMA depends on the number of req it has. If there are
-	 * no DMA requests queued up, then it will STOP the DMA. It there are
-	 * more requests in the DMA, then it will queue the next request.
-	 */
-	void (*complete)(struct tegra_dma_req *req);
-
-	/*  This is a called from the DMA ISR context when the DMA is still in
-	 *  progress and is actively filling same buffer.
-	 *
-	 *  In case of continuous mode receive, this threshold is 1/2 the buffer
-	 *  size. In other cases, this will not even be called as there is no
-	 *  hardware support for it.
-	 *
-	 * In the case of continuous mode receive, if there is next req already
-	 * queued, DMA programs the HW to use that req when this req is
-	 * completed. If there is no "next req" queued, then DMA ISR doesn't do
-	 * anything before calling this callback.
-	 *
-	 *	This is mainly used by the cases, where the clients has queued
-	 *	only one req and want to get some sort of DMA threshold
-	 *	callback to program the next buffer.
-	 *
-	 */
-	void (*threshold)(struct tegra_dma_req *req);
-
-	/* 1 to copy to memory.
-	 * 0 to copy from the memory to device FIFO */
-	int to_memory;
-
-	void *virt_addr;
-
-	unsigned long source_addr;
-	unsigned long dest_addr;
-	unsigned long dest_wrap;
-	unsigned long source_wrap;
-	unsigned long source_bus_width;
-	unsigned long dest_bus_width;
-	unsigned long req_sel;
-	unsigned int size;
-
-	/* Updated by the DMA driver on the conpletion of the request. */
-	int bytes_transferred;
-	int status;
-
-	/* DMA completion tracking information */
-	int buffer_status;
-
-	/* Client specific data */
-	void *dev;
-};
-
-int tegra_dma_enqueue_req(struct tegra_dma_channel *ch,
-	struct tegra_dma_req *req);
-int tegra_dma_dequeue_req(struct tegra_dma_channel *ch,
-	struct tegra_dma_req *req);
-void tegra_dma_dequeue(struct tegra_dma_channel *ch);
-void tegra_dma_flush(struct tegra_dma_channel *ch);
-
-bool tegra_dma_is_req_inflight(struct tegra_dma_channel *ch,
-	struct tegra_dma_req *req);
-bool tegra_dma_is_empty(struct tegra_dma_channel *ch);
-
-struct tegra_dma_channel *tegra_dma_allocate_channel(int mode);
-void tegra_dma_free_channel(struct tegra_dma_channel *ch);
-
-int __init tegra_dma_init(void);
-
 #endif
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 119bc52ab93e..4e07eec1270d 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -63,10 +63,11 @@ static int contextidr_notifier(struct notifier_block *unused, unsigned long cmd,
 	pid = task_pid_nr(thread->task) << ASID_BITS;
 	asm volatile(
 	"	mrc	p15, 0, %0, c13, c0, 1\n"
-	"	bfi	%1, %0, #0, %2\n"
-	"	mcr	p15, 0, %1, c13, c0, 1\n"
+	"	and	%0, %0, %2\n"
+	"	orr	%0, %0, %1\n"
+	"	mcr	p15, 0, %0, c13, c0, 1\n"
 	: "=r" (contextidr), "+r" (pid)
-	: "I" (ASID_BITS));
+	: "I" (~ASID_MASK));
 	isb();
 
 	return NOTIFY_OK;
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 051204fc4617..e59c4ab71bcb 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -489,7 +489,7 @@ static bool __in_atomic_pool(void *start, size_t size)
 	void *pool_start = pool->vaddr;
 	void *pool_end = pool->vaddr + pool->size;
 
-	if (start < pool_start || start > pool_end)
+	if (start < pool_start || start >= pool_end)
 		return false;
 
 	if (end <= pool_end)
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index a7a9e41fa2c2..18144e6a3115 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -990,8 +990,8 @@ void __init sanity_check_meminfo(void)
 		 * Check whether this memory bank would partially overlap
 		 * the vmalloc area.
 		 */
-		if (__va(bank->start + bank->size) > vmalloc_min ||
-		    __va(bank->start + bank->size) < __va(bank->start)) {
+		if (__va(bank->start + bank->size - 1) >= vmalloc_min ||
+		    __va(bank->start + bank->size - 1) <= __va(bank->start)) {
 			unsigned long newsize = vmalloc_min - __va(bank->start);
 			printk(KERN_NOTICE "Truncating RAM at %.8llx-%.8llx "
 			       "to -%.8llx (vmalloc region overlap).\n",
diff --git a/arch/arm/plat-omap/sram.c b/arch/arm/plat-omap/sram.c
index d861aa73299d..28acb383e7df 100644
--- a/arch/arm/plat-omap/sram.c
+++ b/arch/arm/plat-omap/sram.c
@@ -67,6 +67,7 @@
 
 static unsigned long omap_sram_start;
 static void __iomem *omap_sram_base;
+static unsigned long omap_sram_skip;
 static unsigned long omap_sram_size;
 static void __iomem *omap_sram_ceil;
 
@@ -105,6 +106,7 @@ static int is_sram_locked(void)
  */
 static void __init omap_detect_sram(void)
 {
+	omap_sram_skip = SRAM_BOOTLOADER_SZ;
 	if (cpu_class_is_omap2()) {
 		if (is_sram_locked()) {
 			if (cpu_is_omap34xx()) {
@@ -112,6 +114,7 @@ static void __init omap_detect_sram(void)
 				if ((omap_type() == OMAP2_DEVICE_TYPE_EMU) ||
 				    (omap_type() == OMAP2_DEVICE_TYPE_SEC)) {
 					omap_sram_size = 0x7000; /* 28K */
+					omap_sram_skip += SZ_16K;
 				} else {
 					omap_sram_size = 0x8000; /* 32K */
 				}
@@ -174,8 +177,10 @@ static void __init omap_map_sram(void)
 		return;
 
 #ifdef CONFIG_OMAP4_ERRATA_I688
+	if (cpu_is_omap44xx()) {
 		omap_sram_start += PAGE_SIZE;
 		omap_sram_size -= SZ_16K;
+	}
 #endif
 	if (cpu_is_omap34xx()) {
 		/*
@@ -202,8 +207,8 @@ static void __init omap_map_sram(void)
 	 * Looks like we need to preserve some bootloader code at the
 	 * beginning of SRAM for jumping to flash for reboot to work...
 	 */
-	memset_io(omap_sram_base + SRAM_BOOTLOADER_SZ, 0,
-		  omap_sram_size - SRAM_BOOTLOADER_SZ);
+	memset_io(omap_sram_base + omap_sram_skip, 0,
+		  omap_sram_size - omap_sram_skip);
 }
 
 /*
@@ -217,7 +222,7 @@ void *omap_sram_push_address(unsigned long size)
 {
 	unsigned long available, new_ceil = (unsigned long)omap_sram_ceil;
 
-	available = omap_sram_ceil - (omap_sram_base + SRAM_BOOTLOADER_SZ);
+	available = omap_sram_ceil - (omap_sram_base + omap_sram_skip);
 
 	if (size > available) {
 		pr_err("Not enough space in SRAM\n");
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index f34861920634..c7092e6057c5 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -38,6 +38,7 @@ config BLACKFIN
 	select GENERIC_ATOMIC64
 	select GENERIC_IRQ_PROBE
 	select IRQ_PER_CPU if SMP
+	select USE_GENERIC_SMP_HELPERS if SMP
 	select HAVE_NMI_WATCHDOG if NMI_WATCHDOG
 	select GENERIC_SMP_IDLE_THREAD
 	select ARCH_USES_GETTIMEOFFSET if !GENERIC_CLOCKEVENTS
diff --git a/arch/blackfin/Makefile b/arch/blackfin/Makefile
index d3d7e64ca96d..66cf00095b84 100644
--- a/arch/blackfin/Makefile
+++ b/arch/blackfin/Makefile
@@ -20,7 +20,6 @@ endif
 KBUILD_AFLAGS           += $(call cc-option,-mno-fdpic)
 KBUILD_CFLAGS_MODULE    += -mlong-calls
 LDFLAGS                 += -m elf32bfin
-KALLSYMS         += --symbol-prefix=_
 
 KBUILD_DEFCONFIG := BF537-STAMP_defconfig
 
diff --git a/arch/blackfin/include/asm/smp.h b/arch/blackfin/include/asm/smp.h
index dc3d144b4bb5..9631598dcc5d 100644
--- a/arch/blackfin/include/asm/smp.h
+++ b/arch/blackfin/include/asm/smp.h
@@ -18,6 +18,8 @@
 #define raw_smp_processor_id()  blackfin_core_id()
 
 extern void bfin_relocate_coreb_l1_mem(void);
+extern void arch_send_call_function_single_ipi(int cpu);
+extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
 #if defined(CONFIG_SMP) && defined(CONFIG_ICACHE_FLUSH_L1)
 asmlinkage void blackfin_icache_flush_range_l1(unsigned long *ptr);
diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c
index 00bbe672b3b3..a40151306b77 100644
--- a/arch/blackfin/mach-common/smp.c
+++ b/arch/blackfin/mach-common/smp.c
@@ -48,10 +48,13 @@ unsigned long blackfin_iflush_l1_entry[NR_CPUS];
 
 struct blackfin_initial_pda __cpuinitdata initial_pda_coreb;
 
-#define BFIN_IPI_TIMER	      0
-#define BFIN_IPI_RESCHEDULE   1
-#define BFIN_IPI_CALL_FUNC    2
-#define BFIN_IPI_CPU_STOP     3
+enum ipi_message_type {
+	BFIN_IPI_TIMER,
+	BFIN_IPI_RESCHEDULE,
+	BFIN_IPI_CALL_FUNC,
+	BFIN_IPI_CALL_FUNC_SINGLE,
+	BFIN_IPI_CPU_STOP,
+};
 
 struct blackfin_flush_data {
 	unsigned long start;
@@ -60,35 +63,20 @@ struct blackfin_flush_data {
 
 void *secondary_stack;
 
-
-struct smp_call_struct {
-	void (*func)(void *info);
-	void *info;
-	int wait;
-	cpumask_t *waitmask;
-};
-
 static struct blackfin_flush_data smp_flush_data;
 
 static DEFINE_SPINLOCK(stop_lock);
 
-struct ipi_message {
-	unsigned long type;
-	struct smp_call_struct call_struct;
-};
-
 /* A magic number - stress test shows this is safe for common cases */
 #define BFIN_IPI_MSGQ_LEN 5
 
 /* Simple FIFO buffer, overflow leads to panic */
-struct ipi_message_queue {
-	spinlock_t lock;
+struct ipi_data {
 	unsigned long count;
-	unsigned long head; /* head of the queue */
-	struct ipi_message ipi_message[BFIN_IPI_MSGQ_LEN];
+	unsigned long bits;
 };
 
-static DEFINE_PER_CPU(struct ipi_message_queue, ipi_msg_queue);
+static DEFINE_PER_CPU(struct ipi_data, bfin_ipi);
 
 static void ipi_cpu_stop(unsigned int cpu)
 {
@@ -129,28 +117,6 @@ static void ipi_flush_icache(void *info)
 	blackfin_icache_flush_range(fdata->start, fdata->end);
 }
 
-static void ipi_call_function(unsigned int cpu, struct ipi_message *msg)
-{
-	int wait;
-	void (*func)(void *info);
-	void *info;
-	func = msg->call_struct.func;
-	info = msg->call_struct.info;
-	wait = msg->call_struct.wait;
-	func(info);
-	if (wait) {
-#ifdef __ARCH_SYNC_CORE_DCACHE
-		/*
-		 * 'wait' usually means synchronization between CPUs.
-		 * Invalidate D cache in case shared data was changed
-		 * by func() to ensure cache coherence.
-		 */
-		resync_core_dcache();
-#endif
-		cpumask_clear_cpu(cpu, msg->call_struct.waitmask);
-	}
-}
-
 /* Use IRQ_SUPPLE_0 to request reschedule.
  * When returning from interrupt to user space,
  * there is chance to reschedule */
@@ -172,152 +138,95 @@ void ipi_timer(void)
 
 static irqreturn_t ipi_handler_int1(int irq, void *dev_instance)
 {
-	struct ipi_message *msg;
-	struct ipi_message_queue *msg_queue;
+	struct ipi_data *bfin_ipi_data;
 	unsigned int cpu = smp_processor_id();
-	unsigned long flags;
+	unsigned long pending;
+	unsigned long msg;
 
 	platform_clear_ipi(cpu, IRQ_SUPPLE_1);
 
-	msg_queue = &__get_cpu_var(ipi_msg_queue);
-
-	spin_lock_irqsave(&msg_queue->lock, flags);
-
-	while (msg_queue->count) {
-		msg = &msg_queue->ipi_message[msg_queue->head];
-		switch (msg->type) {
-		case BFIN_IPI_TIMER:
-			ipi_timer();
-			break;
-		case BFIN_IPI_RESCHEDULE:
-			scheduler_ipi();
-			break;
-		case BFIN_IPI_CALL_FUNC:
-			ipi_call_function(cpu, msg);
-			break;
-		case BFIN_IPI_CPU_STOP:
-			ipi_cpu_stop(cpu);
-			break;
-		default:
-			printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%lx\n",
-			       cpu, msg->type);
-			break;
-		}
-		msg_queue->head++;
-		msg_queue->head %= BFIN_IPI_MSGQ_LEN;
-		msg_queue->count--;
+	bfin_ipi_data = &__get_cpu_var(bfin_ipi);
+
+	while ((pending = xchg(&bfin_ipi_data->bits, 0)) != 0) {
+		msg = 0;
+		do {
+			msg = find_next_bit(&pending, BITS_PER_LONG, msg + 1);
+			switch (msg) {
+			case BFIN_IPI_TIMER:
+				ipi_timer();
+				break;
+			case BFIN_IPI_RESCHEDULE:
+				scheduler_ipi();
+				break;
+			case BFIN_IPI_CALL_FUNC:
+				generic_smp_call_function_interrupt();
+				break;
+
+			case BFIN_IPI_CALL_FUNC_SINGLE:
+				generic_smp_call_function_single_interrupt();
+				break;
+
+			case BFIN_IPI_CPU_STOP:
+				ipi_cpu_stop(cpu);
+				break;
+			}
+		} while (msg < BITS_PER_LONG);
+
+		smp_mb();
 	}
-	spin_unlock_irqrestore(&msg_queue->lock, flags);
 	return IRQ_HANDLED;
 }
 
-static void ipi_queue_init(void)
+static void bfin_ipi_init(void)
 {
 	unsigned int cpu;
-	struct ipi_message_queue *msg_queue;
+	struct ipi_data *bfin_ipi_data;
 	for_each_possible_cpu(cpu) {
-		msg_queue = &per_cpu(ipi_msg_queue, cpu);
-		spin_lock_init(&msg_queue->lock);
-		msg_queue->count = 0;
-		msg_queue->head = 0;
+		bfin_ipi_data = &per_cpu(bfin_ipi, cpu);
+		bfin_ipi_data->bits = 0;
+		bfin_ipi_data->count = 0;
 	}
 }
 
-static inline void smp_send_message(cpumask_t callmap, unsigned long type,
-					void (*func) (void *info), void *info, int wait)
+void send_ipi(const struct cpumask *cpumask, enum ipi_message_type msg)
 {
 	unsigned int cpu;
-	struct ipi_message_queue *msg_queue;
-	struct ipi_message *msg;
-	unsigned long flags, next_msg;
-	cpumask_t waitmask; /* waitmask is shared by all cpus */
-
-	cpumask_copy(&waitmask, &callmap);
-	for_each_cpu(cpu, &callmap) {
-		msg_queue = &per_cpu(ipi_msg_queue, cpu);
-		spin_lock_irqsave(&msg_queue->lock, flags);
-		if (msg_queue->count < BFIN_IPI_MSGQ_LEN) {
-			next_msg = (msg_queue->head + msg_queue->count)
-					% BFIN_IPI_MSGQ_LEN;
-			msg = &msg_queue->ipi_message[next_msg];
-			msg->type = type;
-			if (type == BFIN_IPI_CALL_FUNC) {
-				msg->call_struct.func = func;
-				msg->call_struct.info = info;
-				msg->call_struct.wait = wait;
-				msg->call_struct.waitmask = &waitmask;
-			}
-			msg_queue->count++;
-		} else
-			panic("IPI message queue overflow\n");
-		spin_unlock_irqrestore(&msg_queue->lock, flags);
+	struct ipi_data *bfin_ipi_data;
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	for_each_cpu(cpu, cpumask) {
+		bfin_ipi_data = &per_cpu(bfin_ipi, cpu);
+		smp_mb();
+		set_bit(msg, &bfin_ipi_data->bits);
+		bfin_ipi_data->count++;
 		platform_send_ipi_cpu(cpu, IRQ_SUPPLE_1);
 	}
 
-	if (wait) {
-		while (!cpumask_empty(&waitmask))
-			blackfin_dcache_invalidate_range(
-				(unsigned long)(&waitmask),
-				(unsigned long)(&waitmask));
-#ifdef __ARCH_SYNC_CORE_DCACHE
-		/*
-		 * Invalidate D cache in case shared data was changed by
-		 * other processors to ensure cache coherence.
-		 */
-		resync_core_dcache();
-#endif
-	}
+	local_irq_restore(flags);
 }
 
-int smp_call_function(void (*func)(void *info), void *info, int wait)
+void arch_send_call_function_single_ipi(int cpu)
 {
-	cpumask_t callmap;
-
-	preempt_disable();
-	cpumask_copy(&callmap, cpu_online_mask);
-	cpumask_clear_cpu(smp_processor_id(), &callmap);
-	if (!cpumask_empty(&callmap))
-		smp_send_message(callmap, BFIN_IPI_CALL_FUNC, func, info, wait);
-
-	preempt_enable();
-
-	return 0;
+	send_ipi(cpumask_of(cpu), BFIN_IPI_CALL_FUNC_SINGLE);
 }
-EXPORT_SYMBOL_GPL(smp_call_function);
 
-int smp_call_function_single(int cpuid, void (*func) (void *info), void *info,
-				int wait)
+void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
-	unsigned int cpu = cpuid;
-	cpumask_t callmap;
-
-	if (cpu_is_offline(cpu))
-		return 0;
-	cpumask_clear(&callmap);
-	cpumask_set_cpu(cpu, &callmap);
-
-	smp_send_message(callmap, BFIN_IPI_CALL_FUNC, func, info, wait);
-
-	return 0;
+	send_ipi(mask, BFIN_IPI_CALL_FUNC);
 }
-EXPORT_SYMBOL_GPL(smp_call_function_single);
 
 void smp_send_reschedule(int cpu)
 {
-	cpumask_t callmap;
-	/* simply trigger an ipi */
-
-	cpumask_clear(&callmap);
-	cpumask_set_cpu(cpu, &callmap);
-
-	smp_send_message(callmap, BFIN_IPI_RESCHEDULE, NULL, NULL, 0);
+	send_ipi(cpumask_of(cpu), BFIN_IPI_RESCHEDULE);
 
 	return;
 }
 
 void smp_send_msg(const struct cpumask *mask, unsigned long type)
 {
-	smp_send_message(*mask, type, NULL, NULL, 0);
+	send_ipi(mask, type);
 }
 
 void smp_timer_broadcast(const struct cpumask *mask)
@@ -333,7 +242,7 @@ void smp_send_stop(void)
 	cpumask_copy(&callmap, cpu_online_mask);
 	cpumask_clear_cpu(smp_processor_id(), &callmap);
 	if (!cpumask_empty(&callmap))
-		smp_send_message(callmap, BFIN_IPI_CPU_STOP, NULL, NULL, 0);
+		send_ipi(&callmap, BFIN_IPI_CPU_STOP);
 
 	preempt_enable();
 
@@ -436,7 +345,7 @@ void __init smp_prepare_boot_cpu(void)
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	platform_prepare_cpus(max_cpus);
-	ipi_queue_init();
+	bfin_ipi_init();
 	platform_request_ipi(IRQ_SUPPLE_0, ipi_handler_int0);
 	platform_request_ipi(IRQ_SUPPLE_1, ipi_handler_int1);
 }
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index a1e9d69a9c90..584b93674ea4 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -169,7 +169,7 @@ static ssize_t hw_interval_write(struct file *file, char const __user *buf,
 	if (*offset)
 		return -EINVAL;
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval)
+	if (retval <= 0)
 		return retval;
 	if (val < oprofile_min_interval)
 		oprofile_hw_interval = oprofile_min_interval;
@@ -212,7 +212,7 @@ static ssize_t hwsampler_zero_write(struct file *file, char const __user *buf,
 		return -EINVAL;
 
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval)
+	if (retval <= 0)
 		return retval;
 	if (val != 0)
 		return -EINVAL;
@@ -243,7 +243,7 @@ static ssize_t hwsampler_kernel_write(struct file *file, char const __user *buf,
 		return -EINVAL;
 
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval)
+	if (retval <= 0)
 		return retval;
 
 	if (val != 0 && val != 1)
@@ -278,7 +278,7 @@ static ssize_t hwsampler_user_write(struct file *file, char const __user *buf,
 		return -EINVAL;
 
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval)
+	if (retval <= 0)
 		return retval;
 
 	if (val != 0 && val != 1)
@@ -317,7 +317,7 @@ static ssize_t timer_enabled_write(struct file *file, char const __user *buf,
 		return -EINVAL;
 
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval)
+	if (retval <= 0)
 		return retval;
 
 	if (val != 0 && val != 1)
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 7f2739e03e79..0d3d63afa76a 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2008,6 +2008,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case 28: /* Atom */
+	case 54: /* Cedariew */
 		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 520b4265fcd2..da02e9cc3754 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -686,7 +686,8 @@ void intel_pmu_lbr_init_atom(void)
 	 * to have an operational LBR which can freeze
 	 * on PMU interrupt
 	 */
-	if (boot_cpu_data.x86_mask < 10) {
+	if (boot_cpu_data.x86_model == 28
+	    && boot_cpu_data.x86_mask < 10) {
 		pr_cont("LBR disabled due to erratum");
 		return;
 	}
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 4873e62db6a1..9e5bcf1e2376 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -225,6 +225,9 @@ static ssize_t microcode_write(struct file *file, const char __user *buf,
 	if (do_microcode_update(buf, len) == 0)
 		ret = (ssize_t)len;
 
+	if (ret > 0)
+		perf_check_microcode();
+
 	mutex_unlock(&microcode_mutex);
 	put_online_cpus();
 
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index e498b18f010c..9fc9aa7ac703 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -318,7 +318,7 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val)
 		if (val & 0x10) {
 			u8 edge_irr = s->irr & ~s->elcr;
 			int i;
-			bool found;
+			bool found = false;
 			struct kvm_vcpu *vcpu;
 
 			s->init4 = val & 1;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c00f03de1b79..b1eb202ee76a 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3619,6 +3619,7 @@ static void seg_setup(int seg)
 
 static int alloc_apic_access_page(struct kvm *kvm)
 {
+	struct page *page;
 	struct kvm_userspace_memory_region kvm_userspace_mem;
 	int r = 0;
 
@@ -3633,7 +3634,13 @@ static int alloc_apic_access_page(struct kvm *kvm)
 	if (r)
 		goto out;
 
-	kvm->arch.apic_access_page = gfn_to_page(kvm, 0xfee00);
+	page = gfn_to_page(kvm, 0xfee00);
+	if (is_error_page(page)) {
+		r = -EFAULT;
+		goto out;
+	}
+
+	kvm->arch.apic_access_page = page;
 out:
 	mutex_unlock(&kvm->slots_lock);
 	return r;
@@ -3641,6 +3648,7 @@ out:
 
 static int alloc_identity_pagetable(struct kvm *kvm)
 {
+	struct page *page;
 	struct kvm_userspace_memory_region kvm_userspace_mem;
 	int r = 0;
 
@@ -3656,8 +3664,13 @@ static int alloc_identity_pagetable(struct kvm *kvm)
 	if (r)
 		goto out;
 
-	kvm->arch.ept_identity_pagetable = gfn_to_page(kvm,
-			kvm->arch.ept_identity_map_addr >> PAGE_SHIFT);
+	page = gfn_to_page(kvm, kvm->arch.ept_identity_map_addr >> PAGE_SHIFT);
+	if (is_error_page(page)) {
+		r = -EFAULT;
+		goto out;
+	}
+
+	kvm->arch.ept_identity_pagetable = page;
 out:
 	mutex_unlock(&kvm->slots_lock);
 	return r;
@@ -6575,7 +6588,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 	/* Exposing INVPCID only when PCID is exposed */
 	best = kvm_find_cpuid_entry(vcpu, 0x7, 0);
 	if (vmx_invpcid_supported() &&
-	    best && (best->ecx & bit(X86_FEATURE_INVPCID)) &&
+	    best && (best->ebx & bit(X86_FEATURE_INVPCID)) &&
 	    guest_cpuid_has_pcid(vcpu)) {
 		exec_control |= SECONDARY_EXEC_ENABLE_INVPCID;
 		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
@@ -6585,7 +6598,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
 			     exec_control);
 		if (best)
-			best->ecx &= ~bit(X86_FEATURE_INVPCID);
+			best->ebx &= ~bit(X86_FEATURE_INVPCID);
 	}
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 148ed666e311..2966c847d489 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5113,17 +5113,20 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
 			!kvm_event_needs_reinjection(vcpu);
 }
 
-static void vapic_enter(struct kvm_vcpu *vcpu)
+static int vapic_enter(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	struct page *page;
 
 	if (!apic || !apic->vapic_addr)
-		return;
+		return 0;
 
 	page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
+	if (is_error_page(page))
+		return -EFAULT;
 
 	vcpu->arch.apic->vapic_page = page;
+	return 0;
 }
 
 static void vapic_exit(struct kvm_vcpu *vcpu)
@@ -5430,7 +5433,11 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 	}
 
 	vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
-	vapic_enter(vcpu);
+	r = vapic_enter(vcpu);
+	if (r) {
+		srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
+		return r;
+	}
 
 	r = 1;
 	while (r > 0) {