Merge tag 's3c24xx-dma' of git://git.kernel.org/pub/scm/linux/kernel/git/kgene/linux-samsung into next/drivers

From Kukjin Kim, this branch adds device-tree support to the DMA controller
on the older Samsung SoCs. It also adds support for one of the missing SoCs
in the family (2410).

The driver has been Ack:ed by Vinod Koul, but is merged through here due
to dependencies with platform code.

* tag 's3c24xx-dma' of git://git.kernel.org/pub/scm/linux/kernel/git/kgene/linux-samsung:
  ARM: S3C24XX: add dma pdata for s3c2410, s3c2440 and s3c2442
  dmaengine: s3c24xx-dma: add support for the s3c2410 type of controller
  ARM: S3C24XX: Fix possible dma selection warning
  ARM: SAMSUNG: set s3c24xx_dma_filter for s3c64xx-spi0 device
  ARM: S3C24XX: add platform-devices for new dma driver for s3c2412 and s3c2443
  dmaengine: add driver for Samsung s3c24xx SoCs
  ARM: S3C24XX: number the dma clocks
  + Linux 3.12-rc3

Signed-off-by: Olof Johansson <olof@lixom.net>

48 files changed, 494 insertions, 211 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index 1feb169274fe..af2cc6eabcc7 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -286,9 +286,6 @@ config HAVE_PERF_USER_STACK_DUMP
 config HAVE_ARCH_JUMP_LABEL
 	bool
 
-config HAVE_ARCH_MUTEX_CPU_RELAX
-	bool
-
 config HAVE_RCU_TABLE_FREE
 	bool
 
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index ad3767095422..0d5c94a623f6 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -2216,8 +2216,7 @@ config NEON
 
 config KERNEL_MODE_NEON
 	bool "Support for NEON in kernel mode"
-	default n
-	depends on NEON
+	depends on NEON && AEABI
 	help
 	  Say Y to include support for NEON in kernel mode.
 
diff --git a/arch/arm/crypto/aes-armv4.S b/arch/arm/crypto/aes-armv4.S
index 19d6cd6f29f9..3a14ea8fe97e 100644
--- a/arch/arm/crypto/aes-armv4.S
+++ b/arch/arm/crypto/aes-armv4.S
@@ -148,7 +148,7 @@ AES_Te:
 @ 		 const AES_KEY *key) {
 .align	5
 ENTRY(AES_encrypt)
-	sub	r3,pc,#8		@ AES_encrypt
+	adr	r3,AES_encrypt
 	stmdb   sp!,{r1,r4-r12,lr}
 	mov	r12,r0		@ inp
 	mov	r11,r2
@@ -381,7 +381,7 @@ _armv4_AES_encrypt:
 .align	5
 ENTRY(private_AES_set_encrypt_key)
 _armv4_AES_set_encrypt_key:
-	sub	r3,pc,#8		@ AES_set_encrypt_key
+	adr	r3,_armv4_AES_set_encrypt_key
 	teq	r0,#0
 	moveq	r0,#-1
 	beq	.Labrt
@@ -843,7 +843,7 @@ AES_Td:
 @ 		 const AES_KEY *key) {
 .align	5
 ENTRY(AES_decrypt)
-	sub	r3,pc,#8		@ AES_decrypt
+	adr	r3,AES_decrypt
 	stmdb   sp!,{r1,r4-r12,lr}
 	mov	r12,r0		@ inp
 	mov	r11,r2
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 7e1f76027f66..72abdc541f38 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -19,6 +19,13 @@
 #include <asm/unified.h>
 #include <asm/compiler.h>
 
+#if __LINUX_ARM_ARCH__ < 6
+#include <asm-generic/uaccess-unaligned.h>
+#else
+#define __get_user_unaligned __get_user
+#define __put_user_unaligned __put_user
+#endif
+
 #define VERIFY_READ 0
 #define VERIFY_WRITE 1
 
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 74ad15d1a065..bc6bd9683ba4 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -442,10 +442,10 @@ local_restart:
 	ldrcc	pc, [tbl, scno, lsl #2]		@ call sys_* routine
 
 	add	r1, sp, #S_OFF
-	cmp	scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE)
+2:	cmp	scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE)
 	eor	r0, scno, #__NR_SYSCALL_BASE	@ put OS number back
 	bcs	arm_syscall
-2:	mov	why, #0				@ no longer a real syscall
+	mov	why, #0				@ no longer a real syscall
 	b	sys_ni_syscall			@ not private func
 
 #if defined(CONFIG_OABI_COMPAT) || !defined(CONFIG_AEABI)
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index de23a9beed13..39f89fbd5111 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -329,10 +329,10 @@
 #ifdef CONFIG_CONTEXT_TRACKING
 	.if	\save
 	stmdb   sp!, {r0-r3, ip, lr}
-	bl	user_exit
+	bl	context_tracking_user_exit
 	ldmia	sp!, {r0-r3, ip, lr}
 	.else
-	bl	user_exit
+	bl	context_tracking_user_exit
 	.endif
 #endif
 	.endm
@@ -341,10 +341,10 @@
 #ifdef CONFIG_CONTEXT_TRACKING
 	.if	\save
 	stmdb   sp!, {r0-r3, ip, lr}
-	bl	user_enter
+	bl	context_tracking_user_enter
 	ldmia	sp!, {r0-r3, ip, lr}
 	.else
-	bl	user_enter
+	bl	context_tracking_user_enter
 	.endif
 #endif
 	.endm
diff --git a/arch/arm/mach-s3c24xx/Kconfig b/arch/arm/mach-s3c24xx/Kconfig
index dba2173e70f3..8f1d327e0cd1 100644
--- a/arch/arm/mach-s3c24xx/Kconfig
+++ b/arch/arm/mach-s3c24xx/Kconfig
@@ -28,6 +28,7 @@ config CPU_S3C2410
 	select CPU_ARM920T
 	select CPU_LLSERIAL_S3C2410
 	select S3C2410_CLOCK
+	select S3C2410_DMA if S3C24XX_DMA
 	select ARM_S3C2410_CPUFREQ if ARM_S3C24XX_CPUFREQ
 	select S3C2410_PM if PM
 	select SAMSUNG_WDT_RESET
@@ -70,6 +71,7 @@ config CPU_S3C2442
 	select CPU_ARM920T
 	select CPU_LLSERIAL_S3C2440
 	select S3C2410_CLOCK
+	select S3C2410_DMA if S3C24XX_DMA
 	select S3C2410_PM if PM
 	help
 	  Support for S3C2442 Samsung Mobile CPU based systems.
@@ -148,7 +150,6 @@ config S3C2410_DMA_DEBUG
 config S3C2410_DMA
 	bool
 	depends on S3C24XX_DMA && (CPU_S3C2410 || CPU_S3C2442)
-	default y if CPU_S3C2410 || CPU_S3C2442
 	help
 	  DMA device selection for S3C2410 and compatible CPUs
 
diff --git a/arch/arm/mach-s3c24xx/clock-s3c2412.c b/arch/arm/mach-s3c24xx/clock-s3c2412.c
index d8f253f2b486..11b3b28457bb 100644
--- a/arch/arm/mach-s3c24xx/clock-s3c2412.c
+++ b/arch/arm/mach-s3c24xx/clock-s3c2412.c
@@ -484,22 +484,22 @@ static struct clk init_clocks_disable[] = {
 
 static struct clk init_clocks[] = {
 	{
-		.name		= "dma",
+		.name		= "dma.0",
 		.parent		= &clk_h,
 		.enable		= s3c2412_clkcon_enable,
 		.ctrlbit	= S3C2412_CLKCON_DMA0,
 	}, {
-		.name		= "dma",
+		.name		= "dma.1",
 		.parent		= &clk_h,
 		.enable		= s3c2412_clkcon_enable,
 		.ctrlbit	= S3C2412_CLKCON_DMA1,
 	}, {
-		.name		= "dma",
+		.name		= "dma.2",
 		.parent		= &clk_h,
 		.enable		= s3c2412_clkcon_enable,
 		.ctrlbit	= S3C2412_CLKCON_DMA2,
 	}, {
-		.name		= "dma",
+		.name		= "dma.3",
 		.parent		= &clk_h,
 		.enable		= s3c2412_clkcon_enable,
 		.ctrlbit	= S3C2412_CLKCON_DMA3,
diff --git a/arch/arm/mach-s3c24xx/common-s3c2443.c b/arch/arm/mach-s3c24xx/common-s3c2443.c
index f6b9f2ef01bd..65d3eef73090 100644
--- a/arch/arm/mach-s3c24xx/common-s3c2443.c
+++ b/arch/arm/mach-s3c24xx/common-s3c2443.c
@@ -438,32 +438,32 @@ static struct clk init_clocks_off[] = {
 
 static struct clk init_clocks[] = {
 	{
-		.name		= "dma",
+		.name		= "dma.0",
 		.parent		= &clk_h,
 		.enable		= s3c2443_clkcon_enable_h,
 		.ctrlbit	= S3C2443_HCLKCON_DMA0,
 	}, {
-		.name		= "dma",
+		.name		= "dma.1",
 		.parent		= &clk_h,
 		.enable		= s3c2443_clkcon_enable_h,
 		.ctrlbit	= S3C2443_HCLKCON_DMA1,
 	}, {
-		.name		= "dma",
+		.name		= "dma.2",
 		.parent		= &clk_h,
 		.enable		= s3c2443_clkcon_enable_h,
 		.ctrlbit	= S3C2443_HCLKCON_DMA2,
 	}, {
-		.name		= "dma",
+		.name		= "dma.3",
 		.parent		= &clk_h,
 		.enable		= s3c2443_clkcon_enable_h,
 		.ctrlbit	= S3C2443_HCLKCON_DMA3,
 	}, {
-		.name		= "dma",
+		.name		= "dma.4",
 		.parent		= &clk_h,
 		.enable		= s3c2443_clkcon_enable_h,
 		.ctrlbit	= S3C2443_HCLKCON_DMA4,
 	}, {
-		.name		= "dma",
+		.name		= "dma.5",
 		.parent		= &clk_h,
 		.enable		= s3c2443_clkcon_enable_h,
 		.ctrlbit	= S3C2443_HCLKCON_DMA5,
diff --git a/arch/arm/mach-s3c24xx/common.c b/arch/arm/mach-s3c24xx/common.c
index 457261c98433..4adaa4b43ffe 100644
--- a/arch/arm/mach-s3c24xx/common.c
+++ b/arch/arm/mach-s3c24xx/common.c
@@ -31,6 +31,7 @@
 #include <linux/platform_device.h>
 #include <linux/delay.h>
 #include <linux/io.h>
+#include <linux/platform_data/dma-s3c24xx.h>
 
 #include <mach/hardware.h>
 #include <mach/regs-clock.h>
@@ -44,6 +45,7 @@
 
 #include <mach/regs-gpio.h>
 #include <plat/regs-serial.h>
+#include <mach/dma.h>
 
 #include <plat/cpu.h>
 #include <plat/devs.h>
@@ -329,3 +331,207 @@ void __init_or_cpufreq s3c24xx_setup_clocks(unsigned long fclk,
 	clk_p.rate = pclk;
 	clk_f.rate = fclk;
 }
+
+#if defined(CONFIG_CPU_S3C2410) || defined(CONFIG_CPU_S3C2412) || \
+	defined(CONFIG_CPU_S3C2440) || defined(CONFIG_CPU_S3C2442)
+static struct resource s3c2410_dma_resource[] = {
+	[0] = DEFINE_RES_MEM(S3C24XX_PA_DMA, S3C24XX_SZ_DMA),
+	[1] = DEFINE_RES_IRQ(IRQ_DMA0),
+	[2] = DEFINE_RES_IRQ(IRQ_DMA1),
+	[3] = DEFINE_RES_IRQ(IRQ_DMA2),
+	[4] = DEFINE_RES_IRQ(IRQ_DMA3),
+};
+#endif
+
+#if defined(CONFIG_CPU_S3C2410) || defined(CONFIG_CPU_S3C2442)
+static struct s3c24xx_dma_channel s3c2410_dma_channels[DMACH_MAX] = {
+	[DMACH_XD0] = { S3C24XX_DMA_AHB, true, S3C24XX_DMA_CHANREQ(0, 0), },
+	[DMACH_XD1] = { S3C24XX_DMA_AHB, true, S3C24XX_DMA_CHANREQ(0, 1), },
+	[DMACH_SDI] = { S3C24XX_DMA_APB, false, S3C24XX_DMA_CHANREQ(2, 0) |
+						S3C24XX_DMA_CHANREQ(2, 2) |
+						S3C24XX_DMA_CHANREQ(1, 3),
+	},
+	[DMACH_SPI0] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(3, 1), },
+	[DMACH_SPI1] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(2, 3), },
+	[DMACH_UART0] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(1, 0), },
+	[DMACH_UART1] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(1, 1), },
+	[DMACH_UART2] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(0, 3), },
+	[DMACH_TIMER] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(3, 0) |
+						 S3C24XX_DMA_CHANREQ(3, 2) |
+						 S3C24XX_DMA_CHANREQ(3, 3),
+	},
+	[DMACH_I2S_IN] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(2, 1) |
+						  S3C24XX_DMA_CHANREQ(1, 2),
+	},
+	[DMACH_I2S_OUT] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(0, 2), },
+	[DMACH_USB_EP1] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(4, 0), },
+	[DMACH_USB_EP2] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(4, 1), },
+	[DMACH_USB_EP3] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(4, 2), },
+	[DMACH_USB_EP4] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(4, 3), },
+};
+
+static struct s3c24xx_dma_platdata s3c2410_dma_platdata = {
+	.num_phy_channels = 4,
+	.channels = s3c2410_dma_channels,
+	.num_channels = DMACH_MAX,
+};
+
+struct platform_device s3c2410_device_dma = {
+	.name		= "s3c2410-dma",
+	.id		= 0,
+	.num_resources	= ARRAY_SIZE(s3c2410_dma_resource),
+	.resource	= s3c2410_dma_resource,
+	.dev	= {
+		.platform_data	= &s3c2410_dma_platdata,
+	},
+};
+#endif
+
+#ifdef CONFIG_CPU_S3C2412
+static struct s3c24xx_dma_channel s3c2412_dma_channels[DMACH_MAX] = {
+	[DMACH_XD0] = { S3C24XX_DMA_AHB, true, 17 },
+	[DMACH_XD1] = { S3C24XX_DMA_AHB, true, 18 },
+	[DMACH_SDI] = { S3C24XX_DMA_APB, false, 10 },
+	[DMACH_SPI0_RX] = { S3C24XX_DMA_APB, true, 1 },
+	[DMACH_SPI0_TX] = { S3C24XX_DMA_APB, true, 0 },
+	[DMACH_SPI1_RX] = { S3C24XX_DMA_APB, true, 3 },
+	[DMACH_SPI1_TX] = { S3C24XX_DMA_APB, true, 2 },
+	[DMACH_UART0] = { S3C24XX_DMA_APB, true, 19 },
+	[DMACH_UART1] = { S3C24XX_DMA_APB, true, 21 },
+	[DMACH_UART2] = { S3C24XX_DMA_APB, true, 23 },
+	[DMACH_UART0_SRC2] = { S3C24XX_DMA_APB, true, 20 },
+	[DMACH_UART1_SRC2] = { S3C24XX_DMA_APB, true, 22 },
+	[DMACH_UART2_SRC2] = { S3C24XX_DMA_APB, true, 24 },
+	[DMACH_TIMER] = { S3C24XX_DMA_APB, true, 9 },
+	[DMACH_I2S_IN] = { S3C24XX_DMA_APB, true, 5 },
+	[DMACH_I2S_OUT] = { S3C24XX_DMA_APB, true, 4 },
+	[DMACH_USB_EP1] = { S3C24XX_DMA_APB, true, 13 },
+	[DMACH_USB_EP2] = { S3C24XX_DMA_APB, true, 14 },
+	[DMACH_USB_EP3] = { S3C24XX_DMA_APB, true, 15 },
+	[DMACH_USB_EP4] = { S3C24XX_DMA_APB, true, 16 },
+};
+
+static struct s3c24xx_dma_platdata s3c2412_dma_platdata = {
+	.num_phy_channels = 4,
+	.channels = s3c2412_dma_channels,
+	.num_channels = DMACH_MAX,
+};
+
+struct platform_device s3c2412_device_dma = {
+	.name		= "s3c2412-dma",
+	.id		= 0,
+	.num_resources	= ARRAY_SIZE(s3c2410_dma_resource),
+	.resource	= s3c2410_dma_resource,
+	.dev	= {
+		.platform_data	= &s3c2412_dma_platdata,
+	},
+};
+#endif
+
+#if defined(CONFIG_CPU_S3C2440)
+static struct s3c24xx_dma_channel s3c2440_dma_channels[DMACH_MAX] = {
+	[DMACH_XD0] = { S3C24XX_DMA_AHB, true, S3C24XX_DMA_CHANREQ(0, 0), },
+	[DMACH_XD1] = { S3C24XX_DMA_AHB, true, S3C24XX_DMA_CHANREQ(0, 1), },
+	[DMACH_SDI] = { S3C24XX_DMA_APB, false, S3C24XX_DMA_CHANREQ(2, 0) |
+						S3C24XX_DMA_CHANREQ(6, 1) |
+						S3C24XX_DMA_CHANREQ(2, 2) |
+						S3C24XX_DMA_CHANREQ(1, 3),
+	},
+	[DMACH_SPI0] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(3, 1), },
+	[DMACH_SPI1] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(2, 3), },
+	[DMACH_UART0] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(1, 0), },
+	[DMACH_UART1] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(1, 1), },
+	[DMACH_UART2] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(0, 3), },
+	[DMACH_TIMER] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(3, 0) |
+						 S3C24XX_DMA_CHANREQ(3, 2) |
+						 S3C24XX_DMA_CHANREQ(3, 3),
+	},
+	[DMACH_I2S_IN] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(2, 1) |
+						  S3C24XX_DMA_CHANREQ(1, 2),
+	},
+	[DMACH_I2S_OUT] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(5, 0) |
+						   S3C24XX_DMA_CHANREQ(0, 2),
+	},
+	[DMACH_PCM_IN] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(6, 0) |
+						  S3C24XX_DMA_CHANREQ(5, 2),
+	},
+	[DMACH_PCM_OUT] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(5, 1) |
+						  S3C24XX_DMA_CHANREQ(6, 3),
+	},
+	[DMACH_MIC_IN] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(6, 2) |
+						  S3C24XX_DMA_CHANREQ(5, 3),
+	},
+	[DMACH_USB_EP1] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(4, 0), },
+	[DMACH_USB_EP2] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(4, 1), },
+	[DMACH_USB_EP3] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(4, 2), },
+	[DMACH_USB_EP4] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(4, 3), },
+};
+
+static struct s3c24xx_dma_platdata s3c2440_dma_platdata = {
+	.num_phy_channels = 4,
+	.channels = s3c2440_dma_channels,
+	.num_channels = DMACH_MAX,
+};
+
+struct platform_device s3c2440_device_dma = {
+	.name		= "s3c2410-dma",
+	.id		= 0,
+	.num_resources	= ARRAY_SIZE(s3c2410_dma_resource),
+	.resource	= s3c2410_dma_resource,
+	.dev	= {
+		.platform_data	= &s3c2440_dma_platdata,
+	},
+};
+#endif
+
+#if defined(CONFIG_CPUS_3C2443) || defined(CONFIG_CPU_S3C2416)
+static struct resource s3c2443_dma_resource[] = {
+	[0] = DEFINE_RES_MEM(S3C24XX_PA_DMA, S3C24XX_SZ_DMA),
+	[1] = DEFINE_RES_IRQ(IRQ_S3C2443_DMA0),
+	[2] = DEFINE_RES_IRQ(IRQ_S3C2443_DMA1),
+	[3] = DEFINE_RES_IRQ(IRQ_S3C2443_DMA2),
+	[4] = DEFINE_RES_IRQ(IRQ_S3C2443_DMA3),
+	[5] = DEFINE_RES_IRQ(IRQ_S3C2443_DMA4),
+	[6] = DEFINE_RES_IRQ(IRQ_S3C2443_DMA5),
+};
+
+static struct s3c24xx_dma_channel s3c2443_dma_channels[DMACH_MAX] = {
+	[DMACH_XD0] = { S3C24XX_DMA_AHB, true, 17 },
+	[DMACH_XD1] = { S3C24XX_DMA_AHB, true, 18 },
+	[DMACH_SDI] = { S3C24XX_DMA_APB, false, 10 },
+	[DMACH_SPI0_RX] = { S3C24XX_DMA_APB, true, 1 },
+	[DMACH_SPI0_TX] = { S3C24XX_DMA_APB, true, 0 },
+	[DMACH_SPI1_RX] = { S3C24XX_DMA_APB, true, 3 },
+	[DMACH_SPI1_TX] = { S3C24XX_DMA_APB, true, 2 },
+	[DMACH_UART0] = { S3C24XX_DMA_APB, true, 19 },
+	[DMACH_UART1] = { S3C24XX_DMA_APB, true, 21 },
+	[DMACH_UART2] = { S3C24XX_DMA_APB, true, 23 },
+	[DMACH_UART3] = { S3C24XX_DMA_APB, true, 25 },
+	[DMACH_UART0_SRC2] = { S3C24XX_DMA_APB, true, 20 },
+	[DMACH_UART1_SRC2] = { S3C24XX_DMA_APB, true, 22 },
+	[DMACH_UART2_SRC2] = { S3C24XX_DMA_APB, true, 24 },
+	[DMACH_UART3_SRC2] = { S3C24XX_DMA_APB, true, 26 },
+	[DMACH_TIMER] = { S3C24XX_DMA_APB, true, 9 },
+	[DMACH_I2S_IN] = { S3C24XX_DMA_APB, true, 5 },
+	[DMACH_I2S_OUT] = { S3C24XX_DMA_APB, true, 4 },
+	[DMACH_PCM_IN] = { S3C24XX_DMA_APB, true, 28 },
+	[DMACH_PCM_OUT] = { S3C24XX_DMA_APB, true, 27 },
+	[DMACH_MIC_IN] = { S3C24XX_DMA_APB, true, 29 },
+};
+
+static struct s3c24xx_dma_platdata s3c2443_dma_platdata = {
+	.num_phy_channels = 6,
+	.channels = s3c2443_dma_channels,
+	.num_channels = DMACH_MAX,
+};
+
+struct platform_device s3c2443_device_dma = {
+	.name		= "s3c2443-dma",
+	.id		= 0,
+	.num_resources	= ARRAY_SIZE(s3c2443_dma_resource),
+	.resource	= s3c2443_dma_resource,
+	.dev	= {
+		.platform_data	= &s3c2443_dma_platdata,
+	},
+};
+#endif
diff --git a/arch/arm/mach-s3c24xx/common.h b/arch/arm/mach-s3c24xx/common.h
index 84b280654f4c..e46c10417216 100644
--- a/arch/arm/mach-s3c24xx/common.h
+++ b/arch/arm/mach-s3c24xx/common.h
@@ -109,4 +109,9 @@ extern void s3c2443_init_irq(void);
 
 extern struct syscore_ops s3c24xx_irq_syscore_ops;
 
+extern struct platform_device s3c2410_device_dma;
+extern struct platform_device s3c2412_device_dma;
+extern struct platform_device s3c2440_device_dma;
+extern struct platform_device s3c2443_device_dma;
+
 #endif /* __ARCH_ARM_MACH_S3C24XX_COMMON_H */
diff --git a/arch/arm/mach-s3c24xx/mach-jive.c b/arch/arm/mach-s3c24xx/mach-jive.c
index a45fcd8ccf79..43c23e220f5b 100644
--- a/arch/arm/mach-s3c24xx/mach-jive.c
+++ b/arch/arm/mach-s3c24xx/mach-jive.c
@@ -466,6 +466,7 @@ static struct platform_device *jive_devices[] __initdata = {
 	&jive_device_wm8750,
 	&s3c_device_nand,
 	&s3c_device_usbgadget,
+	&s3c2412_device_dma,
 };
 
 static struct s3c2410_udc_mach_info jive_udc_cfg __initdata = {
diff --git a/arch/arm/mach-s3c24xx/mach-smdk2413.c b/arch/arm/mach-s3c24xx/mach-smdk2413.c
index 8146e920f10d..c9d31ef28dd1 100644
--- a/arch/arm/mach-s3c24xx/mach-smdk2413.c
+++ b/arch/arm/mach-s3c24xx/mach-smdk2413.c
@@ -89,6 +89,7 @@ static struct platform_device *smdk2413_devices[] __initdata = {
 	&s3c_device_i2c0,
 	&s3c_device_iis,
 	&s3c_device_usbgadget,
+	&s3c2412_device_dma,
 };
 
 static void __init smdk2413_fixup(struct tag *tags, char **cmdline,
diff --git a/arch/arm/mach-s3c24xx/mach-smdk2416.c b/arch/arm/mach-s3c24xx/mach-smdk2416.c
index cb46847c66b4..f88e672ad1e4 100644
--- a/arch/arm/mach-s3c24xx/mach-smdk2416.c
+++ b/arch/arm/mach-s3c24xx/mach-smdk2416.c
@@ -215,6 +215,7 @@ static struct platform_device *smdk2416_devices[] __initdata = {
 	&s3c_device_hsmmc0,
 	&s3c_device_hsmmc1,
 	&s3c_device_usb_hsudc,
+	&s3c2443_device_dma,
 };
 
 static void __init smdk2416_map_io(void)
diff --git a/arch/arm/mach-s3c24xx/mach-smdk2443.c b/arch/arm/mach-s3c24xx/mach-smdk2443.c
index 9435c3bef18a..d9933fcc6cc8 100644
--- a/arch/arm/mach-s3c24xx/mach-smdk2443.c
+++ b/arch/arm/mach-s3c24xx/mach-smdk2443.c
@@ -115,6 +115,7 @@ static struct platform_device *smdk2443_devices[] __initdata = {
 #ifdef CONFIG_SND_SOC_SMDK2443_WM9710
 	&s3c_device_ac97,
 #endif
+	&s3c2443_device_dma,
 };
 
 static void __init smdk2443_map_io(void)
diff --git a/arch/arm/mach-s3c24xx/mach-vstms.c b/arch/arm/mach-s3c24xx/mach-vstms.c
index b66588428ec9..f7ec9c550787 100644
--- a/arch/arm/mach-s3c24xx/mach-vstms.c
+++ b/arch/arm/mach-s3c24xx/mach-vstms.c
@@ -126,6 +126,7 @@ static struct platform_device *vstms_devices[] __initdata = {
 	&s3c_device_iis,
 	&s3c_device_rtc,
 	&s3c_device_nand,
+	&s3c2412_device_dma,
 };
 
 static void __init vstms_fixup(struct tag *tags, char **cmdline,
diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c
index 8ce0ac007eb9..a7b9b9e81c36 100644
--- a/arch/arm/plat-samsung/devs.c
+++ b/arch/arm/plat-samsung/devs.c
@@ -32,6 +32,7 @@
 #include <linux/ioport.h>
 #include <linux/platform_data/s3c-hsudc.h>
 #include <linux/platform_data/s3c-hsotg.h>
+#include <linux/platform_data/dma-s3c24xx.h>
 
 #include <media/s5p_hdmi.h>
 
@@ -1499,8 +1500,10 @@ void __init s3c64xx_spi0_set_platdata(int (*cfg_gpio)(void), int src_clk_nr,
 	pd.num_cs = num_cs;
 	pd.src_clk_nr = src_clk_nr;
 	pd.cfg_gpio = (cfg_gpio) ? cfg_gpio : s3c64xx_spi0_cfg_gpio;
-#ifdef CONFIG_PL330_DMA
+#if defined(CONFIG_PL330_DMA)
 	pd.filter = pl330_filter;
+#elif defined(CONFIG_S3C24XX_DMAC)
+	pd.filter = s3c24xx_dma_filter;
 #endif
 
 	s3c_set_platdata(&pd, sizeof(pd), &s3c64xx_device_spi0);
diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index 51680d15ca8e..d445d060e346 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -187,7 +187,7 @@
 
 /*
  * MIPS32, MIPS64, VR5500, IDT32332, IDT32334 and maybe a few other
- * pre-MIPS32/MIPS53 processors have CLO, CLZ.	The IDT RC64574 is 64-bit and
+ * pre-MIPS32/MIPS64 processors have CLO, CLZ.	The IDT RC64574 is 64-bit and
  * has CLO and CLZ but not DCLO nor DCLZ.  For 64-bit kernels
  * cpu_has_clo_clz also indicates the availability of DCLO and DCLZ.
  */
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index f25a7e9f8cbc..5f8b95512580 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -308,12 +308,10 @@ static void mips_dma_sync_sg_for_cpu(struct device *dev,
 {
 	int i;
 
-	/* Make sure that gcc doesn't leave the empty loop body.  */
-	for (i = 0; i < nelems; i++, sg++) {
-		if (cpu_needs_post_dma_flush(dev))
+	if (cpu_needs_post_dma_flush(dev))
+		for (i = 0; i < nelems; i++, sg++)
 			__dma_sync(sg_page(sg), sg->offset, sg->length,
 				   direction);
-	}
 }
 
 static void mips_dma_sync_sg_for_device(struct device *dev,
@@ -321,12 +319,10 @@ static void mips_dma_sync_sg_for_device(struct device *dev,
 {
 	int i;
 
-	/* Make sure that gcc doesn't leave the empty loop body.  */
-	for (i = 0; i < nelems; i++, sg++) {
-		if (!plat_device_is_coherent(dev))
+	if (!plat_device_is_coherent(dev))
+		for (i = 0; i < nelems; i++, sg++)
 			__dma_sync(sg_page(sg), sg->offset, sg->length,
 				   direction);
-	}
 }
 
 int mips_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
diff --git a/arch/openrisc/include/asm/prom.h b/arch/openrisc/include/asm/prom.h
index eb59bfe23e85..93c9980e1b6b 100644
--- a/arch/openrisc/include/asm/prom.h
+++ b/arch/openrisc/include/asm/prom.h
@@ -14,53 +14,9 @@
  * the Free Software Foundation; either version 2 of the License, or
  * (at your option) any later version.
  */
-
-#include <linux/of.h>	/* linux/of.h gets to determine #include ordering */
-
 #ifndef _ASM_OPENRISC_PROM_H
 #define _ASM_OPENRISC_PROM_H
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
 
-#include <linux/types.h>
-#include <asm/irq.h>
-#include <linux/irqdomain.h>
-#include <linux/atomic.h>
-#include <linux/of_irq.h>
-#include <linux/of_fdt.h>
-#include <linux/of_address.h>
-#include <linux/proc_fs.h>
-#include <linux/platform_device.h>
 #define HAVE_ARCH_DEVTREE_FIXUPS
 
-/* Other Prototypes */
-extern int early_uartlite_console(void);
-
-/* Parse the ibm,dma-window property of an OF node into the busno, phys and
- * size parameters.
- */
-void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
-		unsigned long *busno, unsigned long *phys, unsigned long *size);
-
-extern void kdump_move_device_tree(void);
-
-/* Get the MAC address */
-extern const void *of_get_mac_address(struct device_node *np);
-
-/**
- * of_irq_map_pci - Resolve the interrupt for a PCI device
- * @pdev:	the device whose interrupt is to be resolved
- * @out_irq:	structure of_irq filled by this function
- *
- * This function resolves the PCI interrupt for a given PCI device. If a
- * device-node exists for a given pci_dev, it will use normal OF tree
- * walking. If not, it will implement standard swizzling and walk up the
- * PCI tree until an device-node is found, at which point it will finish
- * resolving using the OF tree walking.
- */
-struct pci_dev;
-extern int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq);
-
-#endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
 #endif /* _ASM_OPENRISC_PROM_H */
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 6a15c968d214..15ca2255f438 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -74,7 +74,7 @@ src-wlib-$(CONFIG_8xx) += mpc8xx.c planetcore.c
 src-wlib-$(CONFIG_PPC_82xx) += pq2.c fsl-soc.c planetcore.c
 src-wlib-$(CONFIG_EMBEDDED6xx) += mv64x60.c mv64x60_i2c.c ugecon.c
 
-src-plat-y := of.c
+src-plat-y := of.c epapr.c
 src-plat-$(CONFIG_40x) += fixed-head.S ep405.c cuboot-hotfoot.c \
 				treeboot-walnut.c cuboot-acadia.c \
 				cuboot-kilauea.c simpleboot.c \
@@ -97,7 +97,7 @@ src-plat-$(CONFIG_EMBEDDED6xx) += cuboot-pq2.c cuboot-mpc7448hpc2.c \
 					prpmc2800.c
 src-plat-$(CONFIG_AMIGAONE) += cuboot-amigaone.c
 src-plat-$(CONFIG_PPC_PS3) += ps3-head.S ps3-hvcall.S ps3.c
-src-plat-$(CONFIG_EPAPR_BOOT) += epapr.c
+src-plat-$(CONFIG_EPAPR_BOOT) += epapr.c epapr-wrapper.c
 
 src-wlib := $(sort $(src-wlib-y))
 src-plat := $(sort $(src-plat-y))
diff --git a/arch/powerpc/boot/epapr-wrapper.c b/arch/powerpc/boot/epapr-wrapper.c
new file mode 100644
index 000000000000..c10191006673
--- /dev/null
+++ b/arch/powerpc/boot/epapr-wrapper.c
@@ -0,0 +1,9 @@
+extern void epapr_platform_init(unsigned long r3, unsigned long r4,
+				unsigned long r5, unsigned long r6,
+				unsigned long r7);
+
+void platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
+		   unsigned long r6, unsigned long r7)
+{
+	epapr_platform_init(r3, r4, r5, r6, r7);
+}
diff --git a/arch/powerpc/boot/epapr.c b/arch/powerpc/boot/epapr.c
index 06c1961bd124..02e91aa2194a 100644
--- a/arch/powerpc/boot/epapr.c
+++ b/arch/powerpc/boot/epapr.c
@@ -48,8 +48,8 @@ static void platform_fixups(void)
 		       fdt_addr, fdt_totalsize((void *)fdt_addr), ima_size);
 }
 
-void platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
-		   unsigned long r6, unsigned long r7)
+void epapr_platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
+			 unsigned long r6, unsigned long r7)
 {
 	epapr_magic = r6;
 	ima_size = r7;
diff --git a/arch/powerpc/boot/of.c b/arch/powerpc/boot/of.c
index 61d9899aa0d0..62e2f43ec1df 100644
--- a/arch/powerpc/boot/of.c
+++ b/arch/powerpc/boot/of.c
@@ -26,6 +26,9 @@
 
 static unsigned long claim_base;
 
+void epapr_platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
+			 unsigned long r6, unsigned long r7);
+
 static void *of_try_claim(unsigned long size)
 {
 	unsigned long addr = 0;
@@ -61,7 +64,7 @@ static void of_image_hdr(const void *hdr)
 	}
 }
 
-void platform_init(unsigned long a1, unsigned long a2, void *promptr)
+static void of_platform_init(unsigned long a1, unsigned long a2, void *promptr)
 {
 	platform_ops.image_hdr = of_image_hdr;
 	platform_ops.malloc = of_try_claim;
@@ -81,3 +84,14 @@ void platform_init(unsigned long a1, unsigned long a2, void *promptr)
 		loader_info.initrd_size = a2;
 	}
 }
+
+void platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
+		   unsigned long r6, unsigned long r7)
+{
+	/* Detect OF vs. ePAPR boot */
+	if (r5)
+		of_platform_init(r3, r4, (void *)r5);
+	else
+		epapr_platform_init(r3, r4, r5, r6, r7);
+}
+
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index 6761c746048d..cd7af841ba05 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -148,18 +148,18 @@ make_space=y
 
 case "$platform" in
 pseries)
-    platformo=$object/of.o
+    platformo="$object/of.o $object/epapr.o"
     link_address='0x4000000'
     ;;
 maple)
-    platformo=$object/of.o
+    platformo="$object/of.o $object/epapr.o"
     link_address='0x400000'
     ;;
 pmac|chrp)
-    platformo=$object/of.o
+    platformo="$object/of.o $object/epapr.o"
     ;;
 coff)
-    platformo="$object/crt0.o $object/of.o"
+    platformo="$object/crt0.o $object/of.o $object/epapr.o"
     lds=$object/zImage.coff.lds
     link_address='0x500000'
     pie=
@@ -253,6 +253,7 @@ treeboot-iss4xx-mpic)
     platformo="$object/treeboot-iss4xx.o"
     ;;
 epapr)
+    platformo="$object/epapr.o $object/epapr-wrapper.o"
     link_address='0x20000000'
     pie=-pie
     ;;
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index 0e40843a1c6e..41f13cec8a8f 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -69,9 +69,9 @@ extern struct thread_info *softirq_ctx[NR_CPUS];
 
 extern void irq_ctx_init(void);
 extern void call_do_softirq(struct thread_info *tp);
-extern int call_handle_irq(int irq, void *p1,
-			   struct thread_info *tp, void *func);
+extern void call_do_irq(struct pt_regs *regs, struct thread_info *tp);
 extern void do_IRQ(struct pt_regs *regs);
+extern void __do_irq(struct pt_regs *regs);
 
 int irq_choose_cpu(const struct cpumask *mask);
 
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index e378cccfca55..ce4de5aed7b5 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -149,8 +149,6 @@ typedef struct {
 
 struct thread_struct {
 	unsigned long	ksp;		/* Kernel stack pointer */
-	unsigned long	ksp_limit;	/* if ksp <= ksp_limit stack overflow */
-
 #ifdef CONFIG_PPC64
 	unsigned long	ksp_vsid;
 #endif
@@ -162,6 +160,7 @@ struct thread_struct {
 #endif
 #ifdef CONFIG_PPC32
 	void		*pgdir;		/* root of page-table tree */
+	unsigned long	ksp_limit;	/* if ksp <= ksp_limit stack overflow */
 #endif
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
 	/*
@@ -321,7 +320,6 @@ struct thread_struct {
 #else
 #define INIT_THREAD  { \
 	.ksp = INIT_SP, \
-	.ksp_limit = INIT_SP_LIMIT, \
 	.regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \
 	.fs = KERNEL_DS, \
 	.fpr = {{0}}, \
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index d8958be5f31a..502c7a4e73f7 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -80,10 +80,11 @@ int main(void)
 	DEFINE(TASKTHREADPPR, offsetof(struct task_struct, thread.ppr));
 #else
 	DEFINE(THREAD_INFO, offsetof(struct task_struct, stack));
+	DEFINE(THREAD_INFO_GAP, _ALIGN_UP(sizeof(struct thread_info), 16));
+	DEFINE(KSP_LIMIT, offsetof(struct thread_struct, ksp_limit));
 #endif /* CONFIG_PPC64 */
 
 	DEFINE(KSP, offsetof(struct thread_struct, ksp));
-	DEFINE(KSP_LIMIT, offsetof(struct thread_struct, ksp_limit));
 	DEFINE(PT_REGS, offsetof(struct thread_struct, regs));
 #ifdef CONFIG_BOOKE
 	DEFINE(THREAD_NORMSAVES, offsetof(struct thread_struct, normsave[0]));
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index c69440cef7af..57d286a78f86 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -441,50 +441,6 @@ void migrate_irqs(void)
 }
 #endif
 
-static inline void handle_one_irq(unsigned int irq)
-{
-	struct thread_info *curtp, *irqtp;
-	unsigned long saved_sp_limit;
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	if (!desc)
-		return;
-
-	/* Switch to the irq stack to handle this */
-	curtp = current_thread_info();
-	irqtp = hardirq_ctx[smp_processor_id()];
-
-	if (curtp == irqtp) {
-		/* We're already on the irq stack, just handle it */
-		desc->handle_irq(irq, desc);
-		return;
-	}
-
-	saved_sp_limit = current->thread.ksp_limit;
-
-	irqtp->task = curtp->task;
-	irqtp->flags = 0;
-
-	/* Copy the softirq bits in preempt_count so that the
-	 * softirq checks work in the hardirq context. */
-	irqtp->preempt_count = (irqtp->preempt_count & ~SOFTIRQ_MASK) |
-			       (curtp->preempt_count & SOFTIRQ_MASK);
-
-	current->thread.ksp_limit = (unsigned long)irqtp +
-		_ALIGN_UP(sizeof(struct thread_info), 16);
-
-	call_handle_irq(irq, desc, irqtp, desc->handle_irq);
-	current->thread.ksp_limit = saved_sp_limit;
-	irqtp->task = NULL;
-
-	/* Set any flag that may have been set on the
-	 * alternate stack
-	 */
-	if (irqtp->flags)
-		set_bits(irqtp->flags, &curtp->flags);
-}
-
 static inline void check_stack_overflow(void)
 {
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
@@ -501,9 +457,9 @@ static inline void check_stack_overflow(void)
 #endif
 }
 
-void do_IRQ(struct pt_regs *regs)
+void __do_irq(struct pt_regs *regs)
 {
-	struct pt_regs *old_regs = set_irq_regs(regs);
+	struct irq_desc *desc;
 	unsigned int irq;
 
 	irq_enter();
@@ -519,18 +475,56 @@ void do_IRQ(struct pt_regs *regs)
 	 */
 	irq = ppc_md.get_irq();
 
-	/* We can hard enable interrupts now */
+	/* We can hard enable interrupts now to allow perf interrupts */
 	may_hard_irq_enable();
 
 	/* And finally process it */
-	if (irq != NO_IRQ)
-		handle_one_irq(irq);
-	else
+	if (unlikely(irq == NO_IRQ))
 		__get_cpu_var(irq_stat).spurious_irqs++;
+	else {
+		desc = irq_to_desc(irq);
+		if (likely(desc))
+			desc->handle_irq(irq, desc);
+	}
 
 	trace_irq_exit(regs);
 
 	irq_exit();
+}
+
+void do_IRQ(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+	struct thread_info *curtp, *irqtp;
+
+	/* Switch to the irq stack to handle this */
+	curtp = current_thread_info();
+	irqtp = hardirq_ctx[raw_smp_processor_id()];
+
+	/* Already there ? */
+	if (unlikely(curtp == irqtp)) {
+		__do_irq(regs);
+		set_irq_regs(old_regs);
+		return;
+	}
+
+	/* Prepare the thread_info in the irq stack */
+	irqtp->task = curtp->task;
+	irqtp->flags = 0;
+
+	/* Copy the preempt_count so that the [soft]irq checks work. */
+	irqtp->preempt_count = curtp->preempt_count;
+
+	/* Switch stack and call */
+	call_do_irq(regs, irqtp);
+
+	/* Restore stack limit */
+	irqtp->task = NULL;
+
+	/* Copy back updates to the thread_info */
+	if (irqtp->flags)
+		set_bits(irqtp->flags, &curtp->flags);
+
 	set_irq_regs(old_regs);
 }
 
@@ -592,28 +586,22 @@ void irq_ctx_init(void)
 		memset((void *)softirq_ctx[i], 0, THREAD_SIZE);
 		tp = softirq_ctx[i];
 		tp->cpu = i;
-		tp->preempt_count = 0;
 
 		memset((void *)hardirq_ctx[i], 0, THREAD_SIZE);
 		tp = hardirq_ctx[i];
 		tp->cpu = i;
-		tp->preempt_count = HARDIRQ_OFFSET;
 	}
 }
 
 static inline void do_softirq_onstack(void)
 {
 	struct thread_info *curtp, *irqtp;
-	unsigned long saved_sp_limit = current->thread.ksp_limit;
 
 	curtp = current_thread_info();
 	irqtp = softirq_ctx[smp_processor_id()];
 	irqtp->task = curtp->task;
 	irqtp->flags = 0;
-	current->thread.ksp_limit = (unsigned long)irqtp +
-				    _ALIGN_UP(sizeof(struct thread_info), 16);
 	call_do_softirq(irqtp);
-	current->thread.ksp_limit = saved_sp_limit;
 	irqtp->task = NULL;
 
 	/* Set any flag that may have been set on the
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 777d999f563b..2b0ad9845363 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -36,26 +36,41 @@
 
 	.text
 
+/*
+ * We store the saved ksp_limit in the unused part
+ * of the STACK_FRAME_OVERHEAD
+ */
 _GLOBAL(call_do_softirq)
 	mflr	r0
 	stw	r0,4(r1)
+	lwz	r10,THREAD+KSP_LIMIT(r2)
+	addi	r11,r3,THREAD_INFO_GAP
 	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3)
 	mr	r1,r3
+	stw	r10,8(r1)
+	stw	r11,THREAD+KSP_LIMIT(r2)
 	bl	__do_softirq
+	lwz	r10,8(r1)
 	lwz	r1,0(r1)
 	lwz	r0,4(r1)
+	stw	r10,THREAD+KSP_LIMIT(r2)
 	mtlr	r0
 	blr
 
-_GLOBAL(call_handle_irq)
+_GLOBAL(call_do_irq)
 	mflr	r0
 	stw	r0,4(r1)
-	mtctr	r6
-	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r5)
-	mr	r1,r5
-	bctrl
+	lwz	r10,THREAD+KSP_LIMIT(r2)
+	addi	r11,r3,THREAD_INFO_GAP
+	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
+	mr	r1,r4
+	stw	r10,8(r1)
+	stw	r11,THREAD+KSP_LIMIT(r2)
+	bl	__do_irq
+	lwz	r10,8(r1)
 	lwz	r1,0(r1)
 	lwz	r0,4(r1)
+	stw	r10,THREAD+KSP_LIMIT(r2)
 	mtlr	r0
 	blr
 
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 971d7e78aff2..e59caf874d05 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -40,14 +40,12 @@ _GLOBAL(call_do_softirq)
 	mtlr	r0
 	blr
 
-_GLOBAL(call_handle_irq)
-	ld	r8,0(r6)
+_GLOBAL(call_do_irq)
 	mflr	r0
 	std	r0,16(r1)
-	mtctr	r8
-	stdu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r5)
-	mr	r1,r5
-	bctrl
+	stdu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
+	mr	r1,r4
+	bl	.__do_irq
 	ld	r1,0(r1)
 	ld	r0,16(r1)
 	mtlr	r0
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 6f428da53e20..96d2fdf3aa9e 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1000,9 +1000,10 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	kregs = (struct pt_regs *) sp;
 	sp -= STACK_FRAME_OVERHEAD;
 	p->thread.ksp = sp;
+#ifdef CONFIG_PPC32
 	p->thread.ksp_limit = (unsigned long)task_stack_page(p) +
 				_ALIGN_UP(sizeof(struct thread_info), 16);
-
+#endif
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	p->thread.ptrace_bps[0] = NULL;
 #endif
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 12e656ffe60e..5fe2842e8bab 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -196,6 +196,8 @@ static int __initdata mem_reserve_cnt;
 
 static cell_t __initdata regbuf[1024];
 
+static bool rtas_has_query_cpu_stopped;
+
 
 /*
  * Error results ... some OF calls will return "-1" on error, some
@@ -1574,6 +1576,11 @@ static void __init prom_instantiate_rtas(void)
 	prom_setprop(rtas_node, "/rtas", "linux,rtas-entry",
 		     &val, sizeof(val));
 
+	/* Check if it supports "query-cpu-stopped-state" */
+	if (prom_getprop(rtas_node, "query-cpu-stopped-state",
+			 &val, sizeof(val)) != PROM_ERROR)
+		rtas_has_query_cpu_stopped = true;
+
 #if defined(CONFIG_PPC_POWERNV) && defined(__BIG_ENDIAN__)
 	/* PowerVN takeover hack */
 	prom_rtas_data = base;
@@ -1815,6 +1822,18 @@ static void __init prom_hold_cpus(void)
 		= (void *) LOW_ADDR(__secondary_hold_acknowledge);
 	unsigned long secondary_hold = LOW_ADDR(__secondary_hold);
 
+	/*
+	 * On pseries, if RTAS supports "query-cpu-stopped-state",
+	 * we skip this stage, the CPUs will be started by the
+	 * kernel using RTAS.
+	 */
+	if ((of_platform == PLATFORM_PSERIES ||
+	     of_platform == PLATFORM_PSERIES_LPAR) &&
+	    rtas_has_query_cpu_stopped) {
+		prom_printf("prom_hold_cpus: skipped\n");
+		return;
+	}
+
 	prom_debug("prom_hold_cpus: start...\n");
 	prom_debug("    1) spinloop       = 0x%x\n", (unsigned long)spinloop);
 	prom_debug("    1) *spinloop      = 0x%x\n", *spinloop);
@@ -3011,6 +3030,8 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	 * On non-powermacs, put all CPUs in spin-loops.
 	 *
 	 * PowerMacs use a different mechanism to spin CPUs
+	 *
+	 * (This must be done after instanciating RTAS)
 	 */
 	if (of_platform != PLATFORM_POWERMAC &&
 	    of_platform != PLATFORM_OPAL)
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index a7ee978fb860..b1faa1593c90 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -1505,6 +1505,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		 */
 		if ((ra == 1) && !(regs->msr & MSR_PR) \
 			&& (val3 >= (regs->gpr[1] - STACK_INT_FRAME_SIZE))) {
+#ifdef CONFIG_PPC32
 			/*
 			 * Check if we will touch kernel sack overflow
 			 */
@@ -1513,7 +1514,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 				err = -EINVAL;
 				break;
 			}
-
+#endif /* CONFIG_PPC32 */
 			/*
 			 * Check if we already set since that means we'll
 			 * lose the previous value.
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index 1c1771a40250..24f58cb0a543 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -233,18 +233,24 @@ static void __init smp_init_pseries(void)
 
 	alloc_bootmem_cpumask_var(&of_spin_mask);
 
-	/* Mark threads which are still spinning in hold loops. */
-	if (cpu_has_feature(CPU_FTR_SMT)) {
-		for_each_present_cpu(i) { 
-			if (cpu_thread_in_core(i) == 0)
-				cpumask_set_cpu(i, of_spin_mask);
-		}
-	} else {
-		cpumask_copy(of_spin_mask, cpu_present_mask);
+	/*
+	 * Mark threads which are still spinning in hold loops
+	 *
+	 * We know prom_init will not have started them if RTAS supports
+	 * query-cpu-stopped-state.
+	 */
+	if (rtas_token("query-cpu-stopped-state") == RTAS_UNKNOWN_SERVICE) {
+		if (cpu_has_feature(CPU_FTR_SMT)) {
+			for_each_present_cpu(i) {
+				if (cpu_thread_in_core(i) == 0)
+					cpumask_set_cpu(i, of_spin_mask);
+			}
+		} else
+			cpumask_copy(of_spin_mask, cpu_present_mask);
+
+		cpumask_clear_cpu(boot_cpuid, of_spin_mask);
 	}
 
-	cpumask_clear_cpu(boot_cpuid, of_spin_mask);
-
 	/* Non-lpar has additional take/give timebase */
 	if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) {
 		smp_ops->give_timebase = rtas_give_timebase;
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index dcc6ac2d8026..7143793859fa 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -93,6 +93,7 @@ config S390
 	select ARCH_INLINE_WRITE_UNLOCK_IRQ
 	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
 	select ARCH_SAVE_PAGE_KEYS if HIBERNATION
+	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS2
@@ -102,7 +103,6 @@ config S390
 	select GENERIC_TIME_VSYSCALL_OLD
 	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
 	select HAVE_ARCH_JUMP_LABEL if !MARCH_G5
-	select HAVE_ARCH_MUTEX_CPU_RELAX
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT
diff --git a/arch/s390/include/asm/mutex.h b/arch/s390/include/asm/mutex.h
index 688271f5f2e4..458c1f7fbc18 100644
--- a/arch/s390/include/asm/mutex.h
+++ b/arch/s390/include/asm/mutex.h
@@ -7,5 +7,3 @@
  */
 
 #include <asm-generic/mutex-dec.h>
-
-#define arch_mutex_cpu_relax()	barrier()
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 0eb37505cab1..ca7821f07260 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -198,6 +198,8 @@ static inline void cpu_relax(void)
 	barrier();
 }
 
+#define arch_mutex_cpu_relax()  barrier()
+
 static inline void psw_set_key(unsigned int key)
 {
 	asm volatile("spka 0(%0)" : : "d" (key));
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index 701fe8c59e1f..83e5d216105e 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/arch/s390/include/asm/spinlock.h
@@ -44,6 +44,11 @@ extern void arch_spin_lock_wait_flags(arch_spinlock_t *, unsigned long flags);
 extern int arch_spin_trylock_retry(arch_spinlock_t *);
 extern void arch_spin_relax(arch_spinlock_t *lock);
 
+static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
+{
+	return lock.owner_cpu == 0;
+}
+
 static inline void arch_spin_lock(arch_spinlock_t *lp)
 {
 	int old;
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 6aef9fbc09b7..b913915e8e63 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -79,30 +79,38 @@ static inline int phys_to_machine_mapping_valid(unsigned long pfn)
 	return get_phys_to_machine(pfn) != INVALID_P2M_ENTRY;
 }
 
-static inline unsigned long mfn_to_pfn(unsigned long mfn)
+static inline unsigned long mfn_to_pfn_no_overrides(unsigned long mfn)
 {
 	unsigned long pfn;
-	int ret = 0;
+	int ret;
 
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return mfn;
 
-	if (unlikely(mfn >= machine_to_phys_nr)) {
-		pfn = ~0;
-		goto try_override;
-	}
-	pfn = 0;
+	if (unlikely(mfn >= machine_to_phys_nr))
+		return ~0;
+
 	/*
 	 * The array access can fail (e.g., device space beyond end of RAM).
 	 * In such cases it doesn't matter what we return (we return garbage),
 	 * but we must handle the fault without crashing!
 	 */
 	ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
-try_override:
-	/* ret might be < 0 if there are no entries in the m2p for mfn */
 	if (ret < 0)
-		pfn = ~0;
-	else if (get_phys_to_machine(pfn) != mfn)
+		return ~0;
+
+	return pfn;
+}
+
+static inline unsigned long mfn_to_pfn(unsigned long mfn)
+{
+	unsigned long pfn;
+
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return mfn;
+
+	pfn = mfn_to_pfn_no_overrides(mfn);
+	if (get_phys_to_machine(pfn) != mfn) {
 		/*
 		 * If this appears to be a foreign mfn (because the pfn
 		 * doesn't map back to the mfn), then check the local override
@@ -111,6 +119,7 @@ try_override:
 		 * m2p_find_override_pfn returns ~0 if it doesn't find anything.
 		 */
 		pfn = m2p_find_override_pfn(mfn, ~0);
+	}
 
 	/* 
 	 * pfn is ~0 if there are no entries in the m2p for mfn or if the
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 8355c84b9729..897783b3302a 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1506,7 +1506,7 @@ static int __init init_hw_perf_events(void)
 		err = amd_pmu_init();
 		break;
 	default:
-		return 0;
+		err = -ENOTSUPP;
 	}
 	if (err != 0) {
 		pr_cont("no PMU driver, software events only.\n");
@@ -1883,9 +1883,9 @@ static struct pmu pmu = {
 
 void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 {
-	userpg->cap_usr_time = 0;
-	userpg->cap_usr_time_zero = 0;
-	userpg->cap_usr_rdpmc = x86_pmu.attr_rdpmc;
+	userpg->cap_user_time = 0;
+	userpg->cap_user_time_zero = 0;
+	userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc;
 	userpg->pmc_width = x86_pmu.cntval_bits;
 
 	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
@@ -1894,13 +1894,13 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 	if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
 		return;
 
-	userpg->cap_usr_time = 1;
+	userpg->cap_user_time = 1;
 	userpg->time_mult = this_cpu_read(cyc2ns);
 	userpg->time_shift = CYC2NS_SCALE_FACTOR;
 	userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
 
 	if (sched_clock_stable && !check_tsc_disabled()) {
-		userpg->cap_usr_time_zero = 1;
+		userpg->cap_user_time_zero = 1;
 		userpg->time_zero = this_cpu_read(cyc2ns_offset);
 	}
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 9db76c31b3c3..f31a1655d1ff 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2325,6 +2325,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case 55: /* Atom 22nm "Silvermont" */
+	case 77: /* Avoton "Silvermont" */
 		memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
 			sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 8ed44589b0e4..4118f9f68315 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -2706,14 +2706,14 @@ static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box)
 	box->hrtimer.function = uncore_pmu_hrtimer;
 }
 
-struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cpu)
+static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int node)
 {
 	struct intel_uncore_box *box;
 	int i, size;
 
 	size = sizeof(*box) + type->num_shared_regs * sizeof(struct intel_uncore_extra_reg);
 
-	box = kzalloc_node(size, GFP_KERNEL, cpu_to_node(cpu));
+	box = kzalloc_node(size, GFP_KERNEL, node);
 	if (!box)
 		return NULL;
 
@@ -3031,7 +3031,7 @@ static int uncore_validate_group(struct intel_uncore_pmu *pmu,
 	struct intel_uncore_box *fake_box;
 	int ret = -EINVAL, n;
 
-	fake_box = uncore_alloc_box(pmu->type, smp_processor_id());
+	fake_box = uncore_alloc_box(pmu->type, NUMA_NO_NODE);
 	if (!fake_box)
 		return -ENOMEM;
 
@@ -3294,7 +3294,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	}
 
 	type = pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)];
-	box = uncore_alloc_box(type, 0);
+	box = uncore_alloc_box(type, NUMA_NO_NODE);
 	if (!box)
 		return -ENOMEM;
 
@@ -3499,7 +3499,7 @@ static int uncore_cpu_prepare(int cpu, int phys_id)
 			if (pmu->func_id < 0)
 				pmu->func_id = j;
 
-			box = uncore_alloc_box(type, cpu);
+			box = uncore_alloc_box(type, cpu_to_node(cpu));
 			if (!box)
 				return -ENOMEM;
 
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 7123b5df479d..af99f71aeb7f 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -216,6 +216,7 @@ int apply_microcode_amd(int cpu)
 	/* need to apply patch? */
 	if (rev >= mc_amd->hdr.patch_id) {
 		c->microcode = rev;
+		uci->cpu_sig.rev = rev;
 		return 0;
 	}
 
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 563ed91e6faa..e643e744e4d8 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -352,12 +352,28 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 	},
 	{	/* Handle problems with rebooting on the Precision M6600. */
 		.callback = set_pci_reboot,
-		.ident = "Dell OptiPlex 990",
+		.ident = "Dell Precision M6600",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"),
 		},
 	},
+	{	/* Handle problems with rebooting on the Dell PowerEdge C6100. */
+		.callback = set_pci_reboot,
+		.ident = "Dell PowerEdge C6100",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "C6100"),
+		},
+	},
+	{	/* Some C6100 machines were shipped with vendor being 'Dell'. */
+		.callback = set_pci_reboot,
+		.ident = "Dell PowerEdge C6100",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "C6100"),
+		},
+	},
 	{ }
 };
 
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 90f6ed127096..c7e22ab29a5a 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -912,10 +912,13 @@ void __init efi_enter_virtual_mode(void)
 
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		md = p;
-		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
-		    md->type != EFI_BOOT_SERVICES_CODE &&
-		    md->type != EFI_BOOT_SERVICES_DATA)
-			continue;
+		if (!(md->attribute & EFI_MEMORY_RUNTIME)) {
+#ifdef CONFIG_X86_64
+			if (md->type != EFI_BOOT_SERVICES_CODE &&
+			    md->type != EFI_BOOT_SERVICES_DATA)
+#endif
+				continue;
+		}
 
 		size = md->num_pages << EFI_PAGE_SHIFT;
 		end = md->phys_addr + size;
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 8b901e8d782d..a61c7d5811be 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -879,7 +879,6 @@ int m2p_add_override(unsigned long mfn, struct page *page,
 	unsigned long uninitialized_var(address);
 	unsigned level;
 	pte_t *ptep = NULL;
-	int ret = 0;
 
 	pfn = page_to_pfn(page);
 	if (!PageHighMem(page)) {
@@ -926,8 +925,8 @@ int m2p_add_override(unsigned long mfn, struct page *page,
 	 * frontend pages while they are being shared with the backend,
 	 * because mfn_to_pfn (that ends up being called by GUPF) will
 	 * return the backend pfn rather than the frontend pfn. */
-	ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
-	if (ret == 0 && get_phys_to_machine(pfn) == mfn)
+	pfn = mfn_to_pfn_no_overrides(mfn);
+	if (get_phys_to_machine(pfn) == mfn)
 		set_phys_to_machine(pfn, FOREIGN_FRAME(mfn));
 
 	return 0;
@@ -942,7 +941,6 @@ int m2p_remove_override(struct page *page,
 	unsigned long uninitialized_var(address);
 	unsigned level;
 	pte_t *ptep = NULL;
-	int ret = 0;
 
 	pfn = page_to_pfn(page);
 	mfn = get_phys_to_machine(pfn);
@@ -1029,8 +1027,8 @@ int m2p_remove_override(struct page *page,
 	 * the original pfn causes mfn_to_pfn(mfn) to return the frontend
 	 * pfn again. */
 	mfn &= ~FOREIGN_FRAME_BIT;
-	ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
-	if (ret == 0 && get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) &&
+	pfn = mfn_to_pfn_no_overrides(mfn);
+	if (get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) &&
 			m2p_find_override(mfn) == NULL)
 		set_phys_to_machine(pfn, mfn);
 
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 253f63fceea1..be6b86078957 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -259,6 +259,14 @@ void xen_uninit_lock_cpu(int cpu)
 }
 
 
+/*
+ * Our init of PV spinlocks is split in two init functions due to us
+ * using paravirt patching and jump labels patching and having to do
+ * all of this before SMP code is invoked.
+ *
+ * The paravirt patching needs to be done _before_ the alternative asm code
+ * is started, otherwise we would not patch the core kernel code.
+ */
 void __init xen_init_spinlocks(void)
 {
 
@@ -267,12 +275,26 @@ void __init xen_init_spinlocks(void)
 		return;
 	}
 
-	static_key_slow_inc(&paravirt_ticketlocks_enabled);
-
 	pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
 	pv_lock_ops.unlock_kick = xen_unlock_kick;
 }
 
+/*
+ * While the jump_label init code needs to happend _after_ the jump labels are
+ * enabled and before SMP is started. Hence we use pre-SMP initcall level
+ * init. We cannot do it in xen_init_spinlocks as that is done before
+ * jump labels are activated.
+ */
+static __init int xen_init_spinlocks_jump(void)
+{
+	if (!xen_pvspin)
+		return 0;
+
+	static_key_slow_inc(&paravirt_ticketlocks_enabled);
+	return 0;
+}
+early_initcall(xen_init_spinlocks_jump);
+
 static __init int xen_parse_nopvspin(char *arg)
 {
 	xen_pvspin = false;