Merge remote-tracking branch 'pci/pci/gavin-window-alignment' into next

Merge Gavin patches from the PCI tree as subsequent powerpc
patches are going to depend on them

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

28 files changed, 254 insertions, 75 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index c5f9ae5..2f88d8d 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -6,7 +6,7 @@ config ARM
 	select HAVE_DMA_API_DEBUG
 	select HAVE_IDE if PCI || ISA || PCMCIA
 	select HAVE_DMA_ATTRS
-	select HAVE_DMA_CONTIGUOUS if (CPU_V6 || CPU_V6K || CPU_V7)
+	select HAVE_DMA_CONTIGUOUS if MMU
 	select HAVE_MEMBLOCK
 	select RTC_LIB
 	select SYS_SUPPORTS_APM_EMULATION
diff --git a/arch/arm/boot/dts/at91sam9g25ek.dts b/arch/arm/boot/dts/at91sam9g25ek.dts
index 7829a4d..96514c1 100644
--- a/arch/arm/boot/dts/at91sam9g25ek.dts
+++ b/arch/arm/boot/dts/at91sam9g25ek.dts
@@ -15,7 +15,7 @@
 	compatible = "atmel,at91sam9g25ek", "atmel,at91sam9x5ek", "atmel,at91sam9x5", "atmel,at91sam9";
 
 	chosen {
-		bootargs = "128M console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=ubifs ubi.mtd=1 root=ubi0:rootfs";
+		bootargs = "console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=ubifs ubi.mtd=1 root=ubi0:rootfs";
 	};
 
 	ahb {
diff --git a/arch/arm/configs/armadillo800eva_defconfig b/arch/arm/configs/armadillo800eva_defconfig
index 7d87184..90610c7 100644
--- a/arch/arm/configs/armadillo800eva_defconfig
+++ b/arch/arm/configs/armadillo800eva_defconfig
@@ -33,7 +33,7 @@ CONFIG_AEABI=y
 CONFIG_FORCE_MAX_ZONEORDER=13
 CONFIG_ZBOOT_ROM_TEXT=0x0
 CONFIG_ZBOOT_ROM_BSS=0x0
-CONFIG_CMDLINE="console=tty0 console=ttySC1,115200 earlyprintk=sh-sci.1,115200 ignore_loglevel root=/dev/nfs ip=dhcp nfsroot=,rsize=4096,wsize=4096"
+CONFIG_CMDLINE="console=tty0 console=ttySC1,115200 earlyprintk=sh-sci.1,115200 ignore_loglevel root=/dev/nfs ip=dhcp nfsroot=,rsize=4096,wsize=4096 rw"
 CONFIG_CMDLINE_FORCE=y
 CONFIG_KEXEC=y
 CONFIG_VFP=y
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index 2ae842d..5c44dcb 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -203,6 +203,13 @@ static inline void dma_free_writecombine(struct device *dev, size_t size,
 }
 
 /*
+ * This can be called during early boot to increase the size of the atomic
+ * coherent DMA pool above the default value of 256KiB. It must be called
+ * before postcore_initcall.
+ */
+extern void __init init_dma_coherent_pool_size(unsigned long size);
+
+/*
  * This can be called during boot to increase the size of the consistent
  * DMA region above it's default value of 2MB. It must be called before the
  * memory allocator is initialised, i.e. before any core_initcall.
diff --git a/arch/arm/mach-at91/at91rm9200_time.c b/arch/arm/mach-at91/at91rm9200_time.c
index 104ca40..aaa443b 100644
--- a/arch/arm/mach-at91/at91rm9200_time.c
+++ b/arch/arm/mach-at91/at91rm9200_time.c
@@ -197,7 +197,7 @@ void __init at91rm9200_timer_init(void)
 	at91_st_read(AT91_ST_SR);
 
 	/* Make IRQs happen for the system timer */
-	setup_irq(AT91_ID_SYS, &at91rm9200_timer_irq);
+	setup_irq(NR_IRQS_LEGACY + AT91_ID_SYS, &at91rm9200_timer_irq);
 
 	/* The 32KiHz "Slow Clock" (tick every 30517.58 nanoseconds) is used
 	 * directly for the clocksource and all clockevents, after adjusting
diff --git a/arch/arm/mach-at91/at91sam9260_devices.c b/arch/arm/mach-at91/at91sam9260_devices.c
index 7b9c2ba..bce572a 100644
--- a/arch/arm/mach-at91/at91sam9260_devices.c
+++ b/arch/arm/mach-at91/at91sam9260_devices.c
@@ -726,6 +726,8 @@ static struct resource rtt_resources[] = {
 		.flags	= IORESOURCE_MEM,
 	}, {
 		.flags	= IORESOURCE_MEM,
+	}, {
+		.flags  = IORESOURCE_IRQ,
 	},
 };
 
@@ -744,10 +746,12 @@ static void __init at91_add_device_rtt_rtc(void)
 	 * The second resource is needed:
 	 * GPBR will serve as the storage for RTC time offset
 	 */
-	at91sam9260_rtt_device.num_resources = 2;
+	at91sam9260_rtt_device.num_resources = 3;
 	rtt_resources[1].start = AT91SAM9260_BASE_GPBR +
 				 4 * CONFIG_RTC_DRV_AT91SAM9_GPBR;
 	rtt_resources[1].end = rtt_resources[1].start + 3;
+	rtt_resources[2].start = NR_IRQS_LEGACY + AT91_ID_SYS;
+	rtt_resources[2].end = NR_IRQS_LEGACY + AT91_ID_SYS;
 }
 #else
 static void __init at91_add_device_rtt_rtc(void)
diff --git a/arch/arm/mach-at91/at91sam9261_devices.c b/arch/arm/mach-at91/at91sam9261_devices.c
index 8df5c1bd..bc2590d 100644
--- a/arch/arm/mach-at91/at91sam9261_devices.c
+++ b/arch/arm/mach-at91/at91sam9261_devices.c
@@ -609,6 +609,8 @@ static struct resource rtt_resources[] = {
 		.flags	= IORESOURCE_MEM,
 	}, {
 		.flags	= IORESOURCE_MEM,
+	}, {
+		.flags  = IORESOURCE_IRQ,
 	}
 };
 
@@ -626,10 +628,12 @@ static void __init at91_add_device_rtt_rtc(void)
 	 * The second resource is needed:
 	 * GPBR will serve as the storage for RTC time offset
 	 */
-	at91sam9261_rtt_device.num_resources = 2;
+	at91sam9261_rtt_device.num_resources = 3;
 	rtt_resources[1].start = AT91SAM9261_BASE_GPBR +
 				 4 * CONFIG_RTC_DRV_AT91SAM9_GPBR;
 	rtt_resources[1].end = rtt_resources[1].start + 3;
+	rtt_resources[2].start = NR_IRQS_LEGACY + AT91_ID_SYS;
+	rtt_resources[2].end = NR_IRQS_LEGACY + AT91_ID_SYS;
 }
 #else
 static void __init at91_add_device_rtt_rtc(void)
diff --git a/arch/arm/mach-at91/at91sam9263_devices.c b/arch/arm/mach-at91/at91sam9263_devices.c
index eb6bbf8..9b6ca73 100644
--- a/arch/arm/mach-at91/at91sam9263_devices.c
+++ b/arch/arm/mach-at91/at91sam9263_devices.c
@@ -990,6 +990,8 @@ static struct resource rtt0_resources[] = {
 		.flags	= IORESOURCE_MEM,
 	}, {
 		.flags	= IORESOURCE_MEM,
+	}, {
+		.flags  = IORESOURCE_IRQ,
 	}
 };
 
@@ -1006,6 +1008,8 @@ static struct resource rtt1_resources[] = {
 		.flags	= IORESOURCE_MEM,
 	}, {
 		.flags	= IORESOURCE_MEM,
+	}, {
+		.flags  = IORESOURCE_IRQ,
 	}
 };
 
@@ -1027,14 +1031,14 @@ static void __init at91_add_device_rtt_rtc(void)
 		 * The second resource is needed only for the chosen RTT:
 		 * GPBR will serve as the storage for RTC time offset
 		 */
-		at91sam9263_rtt0_device.num_resources = 2;
+		at91sam9263_rtt0_device.num_resources = 3;
 		at91sam9263_rtt1_device.num_resources = 1;
 		pdev = &at91sam9263_rtt0_device;
 		r = rtt0_resources;
 		break;
 	case 1:
 		at91sam9263_rtt0_device.num_resources = 1;
-		at91sam9263_rtt1_device.num_resources = 2;
+		at91sam9263_rtt1_device.num_resources = 3;
 		pdev = &at91sam9263_rtt1_device;
 		r = rtt1_resources;
 		break;
@@ -1047,6 +1051,8 @@ static void __init at91_add_device_rtt_rtc(void)
 	pdev->name = "rtc-at91sam9";
 	r[1].start = AT91SAM9263_BASE_GPBR + 4 * CONFIG_RTC_DRV_AT91SAM9_GPBR;
 	r[1].end = r[1].start + 3;
+	r[2].start = NR_IRQS_LEGACY + AT91_ID_SYS;
+	r[2].end = NR_IRQS_LEGACY + AT91_ID_SYS;
 }
 #else
 static void __init at91_add_device_rtt_rtc(void)
diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c
index 0607399..1b47319 100644
--- a/arch/arm/mach-at91/at91sam9g45_devices.c
+++ b/arch/arm/mach-at91/at91sam9g45_devices.c
@@ -1293,6 +1293,8 @@ static struct resource rtt_resources[] = {
 		.flags	= IORESOURCE_MEM,
 	}, {
 		.flags	= IORESOURCE_MEM,
+	}, {
+		.flags  = IORESOURCE_IRQ,
 	}
 };
 
@@ -1310,10 +1312,12 @@ static void __init at91_add_device_rtt_rtc(void)
 	 * The second resource is needed:
 	 * GPBR will serve as the storage for RTC time offset
 	 */
-	at91sam9g45_rtt_device.num_resources = 2;
+	at91sam9g45_rtt_device.num_resources = 3;
 	rtt_resources[1].start = AT91SAM9G45_BASE_GPBR +
 				 4 * CONFIG_RTC_DRV_AT91SAM9_GPBR;
 	rtt_resources[1].end = rtt_resources[1].start + 3;
+	rtt_resources[2].start = NR_IRQS_LEGACY + AT91_ID_SYS;
+	rtt_resources[2].end = NR_IRQS_LEGACY + AT91_ID_SYS;
 }
 #else
 static void __init at91_add_device_rtt_rtc(void)
diff --git a/arch/arm/mach-at91/at91sam9rl_devices.c b/arch/arm/mach-at91/at91sam9rl_devices.c
index f09fff9..b3d365d 100644
--- a/arch/arm/mach-at91/at91sam9rl_devices.c
+++ b/arch/arm/mach-at91/at91sam9rl_devices.c
@@ -688,6 +688,8 @@ static struct resource rtt_resources[] = {
 		.flags	= IORESOURCE_MEM,
 	}, {
 		.flags	= IORESOURCE_MEM,
+	}, {
+		.flags  = IORESOURCE_IRQ,
 	}
 };
 
@@ -705,10 +707,12 @@ static void __init at91_add_device_rtt_rtc(void)
 	 * The second resource is needed:
 	 * GPBR will serve as the storage for RTC time offset
 	 */
-	at91sam9rl_rtt_device.num_resources = 2;
+	at91sam9rl_rtt_device.num_resources = 3;
 	rtt_resources[1].start = AT91SAM9RL_BASE_GPBR +
 				 4 * CONFIG_RTC_DRV_AT91SAM9_GPBR;
 	rtt_resources[1].end = rtt_resources[1].start + 3;
+	rtt_resources[2].start = NR_IRQS_LEGACY + AT91_ID_SYS;
+	rtt_resources[2].end = NR_IRQS_LEGACY + AT91_ID_SYS;
 }
 #else
 static void __init at91_add_device_rtt_rtc(void)
diff --git a/arch/arm/mach-at91/clock.c b/arch/arm/mach-at91/clock.c
index de2ec6b..188c829 100644
--- a/arch/arm/mach-at91/clock.c
+++ b/arch/arm/mach-at91/clock.c
@@ -63,6 +63,12 @@ EXPORT_SYMBOL_GPL(at91_pmc_base);
 
 #define cpu_has_300M_plla()	(cpu_is_at91sam9g10())
 
+#define cpu_has_240M_plla()	(cpu_is_at91sam9261() \
+				|| cpu_is_at91sam9263() \
+				|| cpu_is_at91sam9rl())
+
+#define cpu_has_210M_plla()	(cpu_is_at91sam9260())
+
 #define cpu_has_pllb()		(!(cpu_is_at91sam9rl() \
 				|| cpu_is_at91sam9g45() \
 				|| cpu_is_at91sam9x5() \
@@ -706,6 +712,12 @@ static int __init at91_pmc_init(unsigned long main_clock)
 	} else if (cpu_has_800M_plla()) {
 		if (plla.rate_hz > 800000000)
 			pll_overclock = true;
+	} else if (cpu_has_240M_plla()) {
+		if (plla.rate_hz > 240000000)
+			pll_overclock = true;
+	} else if (cpu_has_210M_plla()) {
+		if (plla.rate_hz > 210000000)
+			pll_overclock = true;
 	} else {
 		if (plla.rate_hz > 209000000)
 			pll_overclock = true;
diff --git a/arch/arm/mach-gemini/irq.c b/arch/arm/mach-gemini/irq.c
index ca70e5f..020852d 100644
--- a/arch/arm/mach-gemini/irq.c
+++ b/arch/arm/mach-gemini/irq.c
@@ -17,6 +17,7 @@
 #include <linux/sched.h>
 #include <asm/irq.h>
 #include <asm/mach/irq.h>
+#include <asm/system_misc.h>
 #include <mach/hardware.h>
 
 #define IRQ_SOURCE(base_addr)	(base_addr + 0x00)
diff --git a/arch/arm/mach-kirkwood/common.c b/arch/arm/mach-kirkwood/common.c
index 3226077..1201191 100644
--- a/arch/arm/mach-kirkwood/common.c
+++ b/arch/arm/mach-kirkwood/common.c
@@ -517,6 +517,13 @@ void __init kirkwood_wdt_init(void)
 void __init kirkwood_init_early(void)
 {
 	orion_time_set_base(TIMER_VIRT_BASE);
+
+	/*
+	 * Some Kirkwood devices allocate their coherent buffers from atomic
+	 * context. Increase size of atomic coherent pool to make sure such
+	 * the allocations won't fail.
+	 */
+	init_dma_coherent_pool_size(SZ_1M);
 }
 
 int kirkwood_tclk;
diff --git a/arch/arm/mach-kirkwood/db88f6281-bp-setup.c b/arch/arm/mach-kirkwood/db88f6281-bp-setup.c
index d933593..be90b7d 100644
--- a/arch/arm/mach-kirkwood/db88f6281-bp-setup.c
+++ b/arch/arm/mach-kirkwood/db88f6281-bp-setup.c
@@ -10,6 +10,7 @@
 
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/sizes.h>
 #include <linux/platform_device.h>
 #include <linux/mtd/partitions.h>
 #include <linux/ata_platform.h>
diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c
index cf10f92..453a6e5 100644
--- a/arch/arm/mach-shmobile/board-armadillo800eva.c
+++ b/arch/arm/mach-shmobile/board-armadillo800eva.c
@@ -520,13 +520,14 @@ static struct platform_device hdmi_lcdc_device = {
 };
 
 /* GPIO KEY */
-#define GPIO_KEY(c, g, d) { .code = c, .gpio = g, .desc = d, .active_low = 1 }
+#define GPIO_KEY(c, g, d, ...) \
+	{ .code = c, .gpio = g, .desc = d, .active_low = 1, __VA_ARGS__ }
 
 static struct gpio_keys_button gpio_buttons[] = {
-	GPIO_KEY(KEY_POWER,	GPIO_PORT99,	"SW1"),
-	GPIO_KEY(KEY_BACK,	GPIO_PORT100,	"SW2"),
-	GPIO_KEY(KEY_MENU,	GPIO_PORT97,	"SW3"),
-	GPIO_KEY(KEY_HOME,	GPIO_PORT98,	"SW4"),
+	GPIO_KEY(KEY_POWER,	GPIO_PORT99,	"SW3", .wakeup = 1),
+	GPIO_KEY(KEY_BACK,	GPIO_PORT100,	"SW4"),
+	GPIO_KEY(KEY_MENU,	GPIO_PORT97,	"SW5"),
+	GPIO_KEY(KEY_HOME,	GPIO_PORT98,	"SW6"),
 };
 
 static struct gpio_keys_platform_data gpio_key_info = {
@@ -901,8 +902,8 @@ static struct platform_device *eva_devices[] __initdata = {
 	&camera_device,
 	&ceu0_device,
 	&fsi_device,
-	&fsi_hdmi_device,
 	&fsi_wm8978_device,
+	&fsi_hdmi_device,
 };
 
 static void __init eva_clock_init(void)
diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c
index 7ea2b31..c129542 100644
--- a/arch/arm/mach-shmobile/board-mackerel.c
+++ b/arch/arm/mach-shmobile/board-mackerel.c
@@ -695,6 +695,7 @@ static struct platform_device usbhs0_device = {
  *  - J30 "open"
  *  - modify usbhs1_get_id() USBHS_HOST -> USBHS_GADGET
  *  - add .get_vbus = usbhs_get_vbus in usbhs1_private
+ *  - check usbhs0_device(pio)/usbhs1_device(irq) order in mackerel_devices.
  */
 #define IRQ8 evt2irq(0x0300)
 #define USB_PHY_MODE		(1 << 4)
@@ -1325,8 +1326,8 @@ static struct platform_device *mackerel_devices[] __initdata = {
 	&nor_flash_device,
 	&smc911x_device,
 	&lcdc_device,
-	&usbhs1_device,
 	&usbhs0_device,
+	&usbhs1_device,
 	&leds_device,
 	&fsi_device,
 	&fsi_ak4643_device,
diff --git a/arch/arm/mach-shmobile/board-marzen.c b/arch/arm/mach-shmobile/board-marzen.c
index 3a528cf..fcf5a47 100644
--- a/arch/arm/mach-shmobile/board-marzen.c
+++ b/arch/arm/mach-shmobile/board-marzen.c
@@ -67,7 +67,7 @@ static struct smsc911x_platform_config smsc911x_platdata = {
 
 static struct platform_device eth_device = {
 	.name		= "smsc911x",
-	.id		= 0,
+	.id		= -1,
 	.dev  = {
 		.platform_data = &smsc911x_platdata,
 	},
diff --git a/arch/arm/mach-shmobile/intc-sh73a0.c b/arch/arm/mach-shmobile/intc-sh73a0.c
index ee44740..588555a 100644
--- a/arch/arm/mach-shmobile/intc-sh73a0.c
+++ b/arch/arm/mach-shmobile/intc-sh73a0.c
@@ -259,9 +259,9 @@ static int sh73a0_set_wake(struct irq_data *data, unsigned int on)
 	return 0; /* always allow wakeup */
 }
 
-#define RELOC_BASE 0x1000
+#define RELOC_BASE 0x1200
 
-/* INTCA IRQ pins at INTCS + 0x1000 to make space for GIC+INTC handling */
+/* INTCA IRQ pins at INTCS + RELOC_BASE to make space for GIC+INTC handling */
 #define INTCS_VECT_RELOC(n, vect) INTCS_VECT((n), (vect) + RELOC_BASE)
 
 INTC_IRQ_PINS_32(intca_irq_pins, 0xe6900000,
diff --git a/arch/arm/mach-tegra/pcie.c b/arch/arm/mach-tegra/pcie.c
index d3ad515..c25a2a4 100644
--- a/arch/arm/mach-tegra/pcie.c
+++ b/arch/arm/mach-tegra/pcie.c
@@ -367,17 +367,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0bf1, tegra_pcie_fixup_class);
 /* Tegra PCIE requires relaxed ordering */
 static void __devinit tegra_pcie_relax_enable(struct pci_dev *dev)
 {
-	u16 val16;
-	int pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
-
-	if (pos <= 0) {
-		dev_err(&dev->dev, "skipping relaxed ordering fixup\n");
-		return;
-	}
-
-	pci_read_config_word(dev, pos + PCI_EXP_DEVCTL, &val16);
-	val16 |= PCI_EXP_DEVCTL_RELAX_EN;
-	pci_write_config_word(dev, pos + PCI_EXP_DEVCTL, val16);
+	pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_RELAX_EN);
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_ANY_ID, PCI_ANY_ID, tegra_pcie_relax_enable);
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 4e7d118..051204f 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -267,17 +267,19 @@ static void __dma_free_remap(void *cpu_addr, size_t size)
 	vunmap(cpu_addr);
 }
 
+#define DEFAULT_DMA_COHERENT_POOL_SIZE	SZ_256K
+
 struct dma_pool {
 	size_t size;
 	spinlock_t lock;
 	unsigned long *bitmap;
 	unsigned long nr_pages;
 	void *vaddr;
-	struct page *page;
+	struct page **pages;
 };
 
 static struct dma_pool atomic_pool = {
-	.size = SZ_256K,
+	.size = DEFAULT_DMA_COHERENT_POOL_SIZE,
 };
 
 static int __init early_coherent_pool(char *p)
@@ -287,6 +289,21 @@ static int __init early_coherent_pool(char *p)
 }
 early_param("coherent_pool", early_coherent_pool);
 
+void __init init_dma_coherent_pool_size(unsigned long size)
+{
+	/*
+	 * Catch any attempt to set the pool size too late.
+	 */
+	BUG_ON(atomic_pool.vaddr);
+
+	/*
+	 * Set architecture specific coherent pool size only if
+	 * it has not been changed by kernel command line parameter.
+	 */
+	if (atomic_pool.size == DEFAULT_DMA_COHERENT_POOL_SIZE)
+		atomic_pool.size = size;
+}
+
 /*
  * Initialise the coherent pool for atomic allocations.
  */
@@ -297,6 +314,7 @@ static int __init atomic_pool_init(void)
 	unsigned long nr_pages = pool->size >> PAGE_SHIFT;
 	unsigned long *bitmap;
 	struct page *page;
+	struct page **pages;
 	void *ptr;
 	int bitmap_size = BITS_TO_LONGS(nr_pages) * sizeof(long);
 
@@ -304,21 +322,31 @@ static int __init atomic_pool_init(void)
 	if (!bitmap)
 		goto no_bitmap;
 
+	pages = kzalloc(nr_pages * sizeof(struct page *), GFP_KERNEL);
+	if (!pages)
+		goto no_pages;
+
 	if (IS_ENABLED(CONFIG_CMA))
 		ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page);
 	else
 		ptr = __alloc_remap_buffer(NULL, pool->size, GFP_KERNEL, prot,
 					   &page, NULL);
 	if (ptr) {
+		int i;
+
+		for (i = 0; i < nr_pages; i++)
+			pages[i] = page + i;
+
 		spin_lock_init(&pool->lock);
 		pool->vaddr = ptr;
-		pool->page = page;
+		pool->pages = pages;
 		pool->bitmap = bitmap;
 		pool->nr_pages = nr_pages;
 		pr_info("DMA: preallocated %u KiB pool for atomic coherent allocations\n",
 		       (unsigned)pool->size / 1024);
 		return 0;
 	}
+no_pages:
 	kfree(bitmap);
 no_bitmap:
 	pr_err("DMA: failed to allocate %u KiB pool for atomic coherent allocation\n",
@@ -443,27 +471,45 @@ static void *__alloc_from_pool(size_t size, struct page **ret_page)
 	if (pageno < pool->nr_pages) {
 		bitmap_set(pool->bitmap, pageno, count);
 		ptr = pool->vaddr + PAGE_SIZE * pageno;
-		*ret_page = pool->page + pageno;
+		*ret_page = pool->pages[pageno];
+	} else {
+		pr_err_once("ERROR: %u KiB atomic DMA coherent pool is too small!\n"
+			    "Please increase it with coherent_pool= kernel parameter!\n",
+			    (unsigned)pool->size / 1024);
 	}
 	spin_unlock_irqrestore(&pool->lock, flags);
 
 	return ptr;
 }
 
+static bool __in_atomic_pool(void *start, size_t size)
+{
+	struct dma_pool *pool = &atomic_pool;
+	void *end = start + size;
+	void *pool_start = pool->vaddr;
+	void *pool_end = pool->vaddr + pool->size;
+
+	if (start < pool_start || start > pool_end)
+		return false;
+
+	if (end <= pool_end)
+		return true;
+
+	WARN(1, "Wrong coherent size(%p-%p) from atomic pool(%p-%p)\n",
+	     start, end - 1, pool_start, pool_end - 1);
+
+	return false;
+}
+
 static int __free_from_pool(void *start, size_t size)
 {
 	struct dma_pool *pool = &atomic_pool;
 	unsigned long pageno, count;
 	unsigned long flags;
 
-	if (start < pool->vaddr || start > pool->vaddr + pool->size)
+	if (!__in_atomic_pool(start, size))
 		return 0;
 
-	if (start + size > pool->vaddr + pool->size) {
-		WARN(1, "freeing wrong coherent size from pool\n");
-		return 0;
-	}
-
 	pageno = (start - pool->vaddr) >> PAGE_SHIFT;
 	count = size >> PAGE_SHIFT;
 
@@ -1090,10 +1136,22 @@ static int __iommu_remove_mapping(struct device *dev, dma_addr_t iova, size_t si
 	return 0;
 }
 
+static struct page **__atomic_get_pages(void *addr)
+{
+	struct dma_pool *pool = &atomic_pool;
+	struct page **pages = pool->pages;
+	int offs = (addr - pool->vaddr) >> PAGE_SHIFT;
+
+	return pages + offs;
+}
+
 static struct page **__iommu_get_pages(void *cpu_addr, struct dma_attrs *attrs)
 {
 	struct vm_struct *area;
 
+	if (__in_atomic_pool(cpu_addr, PAGE_SIZE))
+		return __atomic_get_pages(cpu_addr);
+
 	if (dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs))
 		return cpu_addr;
 
@@ -1103,6 +1161,34 @@ static struct page **__iommu_get_pages(void *cpu_addr, struct dma_attrs *attrs)
 	return NULL;
 }
 
+static void *__iommu_alloc_atomic(struct device *dev, size_t size,
+				  dma_addr_t *handle)
+{
+	struct page *page;
+	void *addr;
+
+	addr = __alloc_from_pool(size, &page);
+	if (!addr)
+		return NULL;
+
+	*handle = __iommu_create_mapping(dev, &page, size);
+	if (*handle == DMA_ERROR_CODE)
+		goto err_mapping;
+
+	return addr;
+
+err_mapping:
+	__free_from_pool(addr, size);
+	return NULL;
+}
+
+static void __iommu_free_atomic(struct device *dev, struct page **pages,
+				dma_addr_t handle, size_t size)
+{
+	__iommu_remove_mapping(dev, handle, size);
+	__free_from_pool(page_address(pages[0]), size);
+}
+
 static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	    dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
 {
@@ -1113,6 +1199,9 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	*handle = DMA_ERROR_CODE;
 	size = PAGE_ALIGN(size);
 
+	if (gfp & GFP_ATOMIC)
+		return __iommu_alloc_atomic(dev, size, handle);
+
 	pages = __iommu_alloc_buffer(dev, size, gfp);
 	if (!pages)
 		return NULL;
@@ -1179,6 +1268,11 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 		return;
 	}
 
+	if (__in_atomic_pool(cpu_addr, size)) {
+		__iommu_free_atomic(dev, pages, handle, size);
+		return;
+	}
+
 	if (!dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) {
 		unmap_kernel_range((unsigned long)cpu_addr, size);
 		vunmap(cpu_addr);
diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c
index 52a1ba7..c5dfb2c 100644
--- a/arch/mips/pci/pci-octeon.c
+++ b/arch/mips/pci/pci-octeon.c
@@ -117,16 +117,11 @@ int pcibios_plat_dev_init(struct pci_dev *dev)
 	}
 
 	/* Enable the PCIe normal error reporting */
-	pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
-	if (pos) {
-		/* Update Device Control */
-		pci_read_config_word(dev, pos + PCI_EXP_DEVCTL, &config);
-		config |= PCI_EXP_DEVCTL_CERE; /* Correctable Error Reporting */
-		config |= PCI_EXP_DEVCTL_NFERE; /* Non-Fatal Error Reporting */
-		config |= PCI_EXP_DEVCTL_FERE;  /* Fatal Error Reporting */
-		config |= PCI_EXP_DEVCTL_URRE;  /* Unsupported Request */
-		pci_write_config_word(dev, pos + PCI_EXP_DEVCTL, config);
-	}
+	config = PCI_EXP_DEVCTL_CERE; /* Correctable Error Reporting */
+	config |= PCI_EXP_DEVCTL_NFERE; /* Non-Fatal Error Reporting */
+	config |= PCI_EXP_DEVCTL_FERE;  /* Fatal Error Reporting */
+	config |= PCI_EXP_DEVCTL_URRE;  /* Unsupported Request */
+	pcie_capability_set_word(dev, PCI_EXP_DEVCTL, config);
 
 	/* Find the Advanced Error Reporting capability */
 	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 236b477..8111e1b 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -215,6 +215,9 @@ struct machdep_calls {
 	/* Called after scan and before resource survey */
 	void (*pcibios_fixup_phb)(struct pci_controller *hose);
 
+	/* Called during PCI resource reassignment */
+	resource_size_t (*pcibios_window_alignment)(struct pci_bus *, unsigned long type);
+
 	/* Called to shutdown machine specific hardware not already controlled
 	 * by other drivers.
 	 */
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 4cb7147..7f94f76 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -99,6 +99,26 @@ void pcibios_free_controller(struct pci_controller *phb)
 		kfree(phb);
 }
 
+/*
+ * The function is used to return the minimal alignment
+ * for memory or I/O windows of the associated P2P bridge.
+ * By default, 4KiB alignment for I/O windows and 1MiB for
+ * memory windows.
+ */
+resource_size_t pcibios_window_alignment(struct pci_bus *bus,
+					 unsigned long type)
+{
+	if (ppc_md.pcibios_window_alignment)
+		return ppc_md.pcibios_window_alignment(bus, type);
+
+	/*
+	 * PCI core will figure out the default
+	 * alignment: 4KiB for I/O and 1MiB for
+	 * memory window.
+	 */
+	return 1;
+}
+
 static resource_size_t pcibios_io_size(const struct pci_controller *hose)
 {
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 5e75dcf..cae7281 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -854,7 +854,7 @@ static void __devinit pnv_ioda_setup_PEs(struct pci_bus *bus)
 		if (pe == NULL)
 			continue;
 		/* Leaving the PCIe domain ... single PE# */
-		if (dev->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE)
+		if (pci_pcie_type(dev) == PCI_EXP_TYPE_PCI_BRIDGE)
 			pnv_ioda_setup_bus_PE(dev, pe);
 		else if (dev->subordinate)
 			pnv_ioda_setup_PEs(dev->subordinate);
@@ -1138,6 +1138,44 @@ static void __devinit pnv_pci_ioda_fixup_phb(struct pci_controller *hose)
 	}
 }
 
+/*
+ * Returns the alignment for I/O or memory windows for P2P
+ * bridges. That actually depends on how PEs are segmented.
+ * For now, we return I/O or M32 segment size for PE sensitive
+ * P2P bridges. Otherwise, the default values (4KiB for I/O,
+ * 1MiB for memory) will be returned.
+ *
+ * The current PCI bus might be put into one PE, which was
+ * create against the parent PCI bridge. For that case, we
+ * needn't enlarge the alignment so that we can save some
+ * resources.
+ */
+static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus,
+						unsigned long type)
+{
+	struct pci_dev *bridge;
+	struct pci_controller *hose = pci_bus_to_host(bus);
+	struct pnv_phb *phb = hose->private_data;
+	int num_pci_bridges = 0;
+
+	bridge = bus->self;
+	while (bridge) {
+		if (pci_pcie_type(bridge) == PCI_EXP_TYPE_PCI_BRIDGE) {
+			num_pci_bridges++;
+			if (num_pci_bridges >= 2)
+				return 1;
+		}
+
+		bridge = bridge->bus->self;
+	}
+
+	/* We need support prefetchable memory window later */
+	if (type & IORESOURCE_MEM)
+		return phb->ioda.m32_segsize;
+
+	return phb->ioda.io_segsize;
+}
+
 /* Prevent enabling devices for which we couldn't properly
  * assign a PE
  */
@@ -1305,6 +1343,7 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np)
 	 */
 	ppc_md.pcibios_fixup_phb = pnv_pci_ioda_fixup_phb;
 	ppc_md.pcibios_enable_device_hook = pnv_pci_enable_device_hook;
+	ppc_md.pcibios_window_alignment = pnv_pci_window_alignment;
 	pci_add_flags(PCI_PROBE_ONLY | PCI_REASSIGN_ALL_RSRC);
 
 	/* Reset IODA tables to a clean state */
diff --git a/arch/tile/kernel/pci.c b/arch/tile/kernel/pci.c
index 33c1086..d2292be 100644
--- a/arch/tile/kernel/pci.c
+++ b/arch/tile/kernel/pci.c
@@ -246,16 +246,13 @@ static void __devinit fixup_read_and_payload_sizes(void)
 
 	/* Scan for the smallest maximum payload size. */
 	while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
-		int pcie_caps_offset;
 		u32 devcap;
 		int max_payload;
 
-		pcie_caps_offset = pci_find_capability(dev, PCI_CAP_ID_EXP);
-		if (pcie_caps_offset == 0)
+		if (!pci_is_pcie(dev))
 			continue;
 
-		pci_read_config_dword(dev, pcie_caps_offset + PCI_EXP_DEVCAP,
-				      &devcap);
+		pcie_capability_read_dword(dev, PCI_EXP_DEVCAP, &devcap);
 		max_payload = devcap & PCI_EXP_DEVCAP_PAYLOAD;
 		if (max_payload < smallest_max_payload)
 			smallest_max_payload = max_payload;
@@ -263,21 +260,10 @@ static void __devinit fixup_read_and_payload_sizes(void)
 
 	/* Now, set the max_payload_size for all devices to that value. */
 	new_values = (max_read_size << 12) | (smallest_max_payload << 5);
-	while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
-		int pcie_caps_offset;
-		u16 devctl;
-
-		pcie_caps_offset = pci_find_capability(dev, PCI_CAP_ID_EXP);
-		if (pcie_caps_offset == 0)
-			continue;
-
-		pci_read_config_word(dev, pcie_caps_offset + PCI_EXP_DEVCTL,
-				     &devctl);
-		devctl &= ~(PCI_EXP_DEVCTL_PAYLOAD | PCI_EXP_DEVCTL_READRQ);
-		devctl |= new_values;
-		pci_write_config_word(dev, pcie_caps_offset + PCI_EXP_DEVCTL,
-				      devctl);
-	}
+	while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL)
+		pcie_capability_clear_and_set_word(dev, PCI_EXP_DEVCTL,
+				PCI_EXP_DEVCTL_PAYLOAD | PCI_EXP_DEVCTL_READRQ,
+				new_values);
 }
 
 
diff --git a/arch/um/os-Linux/time.c b/arch/um/os-Linux/time.c
index f602385..0748fe0 100644
--- a/arch/um/os-Linux/time.c
+++ b/arch/um/os-Linux/time.c
@@ -114,7 +114,7 @@ static void deliver_alarm(void)
 	skew += this_tick - last_tick;
 
 	while (skew >= one_tick) {
-		alarm_handler(SIGVTALRM, NULL);
+		alarm_handler(SIGVTALRM, NULL, NULL);
 		skew -= one_tick;
 	}
 
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index b65a761..5141d80 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1283,7 +1283,7 @@ static void xen_flush_tlb_others(const struct cpumask *cpus,
 	cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask));
 
 	args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
-	if (start != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) {
+	if (end != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) {
 		args->op.cmd = MMUEXT_INVLPG_MULTI;
 		args->op.arg1.linear_addr = start;
 	}
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index d4b2554..76ba0e9 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -599,7 +599,7 @@ bool __init early_can_reuse_p2m_middle(unsigned long set_pfn, unsigned long set_
 	if (p2m_index(set_pfn))
 		return false;
 
-	for (pfn = 0; pfn <= MAX_DOMAIN_PAGES; pfn += P2M_PER_PAGE) {
+	for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_PER_PAGE) {
 		topidx = p2m_top_index(pfn);
 
 		if (!p2m_top[topidx])