37 files changed, 247 insertions, 67 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index c5f9ae5dbd1..2f88d8d9770 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 7829a4d0cb2..96514c134e5 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 7d8718468e0..90610c7030f 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 2ae842df455..5c44dcb0987 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 104ca40d8d1..aaa443b48c9 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 7b9c2ba396e..bce572a530e 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 8df5c1bdff9..bc2590d712d 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 eb6bbf86fb9..9b6ca734f1a 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 06073996a38..1b47319ca00 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 f09fff93217..b3d365dadef 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 de2ec6b8fea..188c82971eb 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 ca70e5fcc7a..020852d3bdd 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 3226077735b..1201191d7f1 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 d9335937959..be90b7d0e10 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 cf10f92856d..453a6e50db8 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 7ea2b31e319..c129542f6ae 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 3a528cf4366..fcf5a47f477 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 ee447404c85..588555a67d9 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/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 4e7d1182e8a..051204fc461 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/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 53b6dfa8334..54b73a28c20 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -386,6 +386,7 @@ extern unsigned long cpuidle_disable;
 enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF};
 
 extern int powersave_nap;       /* set if nap mode can be used in idle loop */
+extern void power7_nap(void);
 
 #ifdef CONFIG_PSERIES_IDLE
 extern void update_smt_snooze_delay(int snooze);
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 85b05c463fa..e8995727b1c 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -76,6 +76,7 @@ int main(void)
         DEFINE(SIGSEGV, SIGSEGV);
         DEFINE(NMI_MASK, NMI_MASK);
         DEFINE(THREAD_DSCR, offsetof(struct thread_struct, dscr));
+        DEFINE(THREAD_DSCR_INHERIT, offsetof(struct thread_struct, dscr_inherit));
 #else
         DEFINE(THREAD_INFO, offsetof(struct task_struct, stack));
 #endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index 5b25c8060fd..a892680668d 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -28,6 +28,8 @@ void doorbell_setup_this_cpu(void)
 
 void doorbell_cause_ipi(int cpu, unsigned long data)
 {
+        /* Order previous accesses vs. msgsnd, which is treated as a store */
+        mb();
         ppc_msgsnd(PPC_DBELL, 0, data);
 }
 
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 4b01a25e29e..b40e0b4815b 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -370,6 +370,12 @@ _GLOBAL(ret_from_fork)
         li      r3,0
         b       syscall_exit
 
+        .section        ".toc","aw"
+DSCR_DEFAULT:
+        .tc dscr_default[TC],dscr_default
+
+        .section        ".text"
+
 /*
  * This routine switches between two different tasks.  The process
  * state of one is saved on its kernel stack.  Then the state
@@ -509,9 +515,6 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
         mr      r1,r8           /* start using new stack pointer */
         std     r7,PACAKSAVE(r13)
 
-        ld      r6,_CCR(r1)
-        mtcrf   0xFF,r6
-
 #ifdef CONFIG_ALTIVEC
 BEGIN_FTR_SECTION
         ld      r0,THREAD_VRSAVE(r4)
@@ -520,14 +523,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif /* CONFIG_ALTIVEC */
 #ifdef CONFIG_PPC64
 BEGIN_FTR_SECTION
+        lwz     r6,THREAD_DSCR_INHERIT(r4)
+        ld      r7,DSCR_DEFAULT@toc(2)
         ld      r0,THREAD_DSCR(r4)
-        cmpd    r0,r25
-        beq     1f
+        cmpwi   r6,0
+        bne     1f
+        ld      r0,0(r7)
+1:      cmpd    r0,r25
+        beq     2f
         mtspr   SPRN_DSCR,r0
-1:      
+2:
 END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
 #endif
 
+        ld      r6,_CCR(r1)
+        mtcrf   0xFF,r6
+
         /* r3-r13 are destroyed -- Cort */
         REST_8GPRS(14, r1)
         REST_10GPRS(22, r1)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index e894515e77b..39aa97d3ff8 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -186,7 +186,7 @@ hardware_interrupt_hv:
         KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x800)
 
         MASKABLE_EXCEPTION_PSERIES(0x900, 0x900, decrementer)
-        MASKABLE_EXCEPTION_HV(0x980, 0x982, decrementer)
+        STD_EXCEPTION_HV(0x980, 0x982, hdecrementer)
 
         STD_EXCEPTION_PSERIES(0xa00, 0xa00, trap_0a)
         KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xa00)
@@ -486,6 +486,7 @@ machine_check_common:
 
         STD_EXCEPTION_COMMON_ASYNC(0x500, hardware_interrupt, do_IRQ)
         STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, .timer_interrupt)
+        STD_EXCEPTION_COMMON(0x980, hdecrementer, .hdec_interrupt)
         STD_EXCEPTION_COMMON(0xa00, trap_0a, .unknown_exception)
         STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception)
         STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception)
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index 7140d838339..e11863f4e59 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -28,7 +28,9 @@ _GLOBAL(power7_idle)
         lwz     r4,ADDROFF(powersave_nap)(r3)
         cmpwi   0,r4,0
         beqlr
+        /* fall through */
 
+_GLOBAL(power7_nap)
         /* NAP is a state loss, we create a regs frame on the
          * stack, fill it up with the state we care about and
          * stick a pointer to it in PACAR1. We really only
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 710f400476d..1a1f2ddfb58 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -802,16 +802,8 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 #endif /* CONFIG_PPC_STD_MMU_64 */
 #ifdef CONFIG_PPC64 
         if (cpu_has_feature(CPU_FTR_DSCR)) {
-                if (current->thread.dscr_inherit) {
-                        p->thread.dscr_inherit = 1;
-                        p->thread.dscr = current->thread.dscr;
-                } else if (0 != dscr_default) {
-                        p->thread.dscr_inherit = 1;
-                        p->thread.dscr = dscr_default;
-                } else {
-                        p->thread.dscr_inherit = 0;
-                        p->thread.dscr = 0;
-                }
+                p->thread.dscr_inherit = current->thread.dscr_inherit;
+                p->thread.dscr = current->thread.dscr;
         }
 #endif
 
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 0321007086f..8d4214afc21 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -198,8 +198,15 @@ void smp_muxed_ipi_message_pass(int cpu, int msg)
         struct cpu_messages *info = &per_cpu(ipi_message, cpu);
         char *message = (char *)&info->messages;
 
+        /*
+         * Order previous accesses before accesses in the IPI handler.
+         */
+        smp_mb();
         message[msg] = 1;
-        mb();
+        /*
+         * cause_ipi functions are required to include a full barrier
+         * before doing whatever causes the IPI.
+         */
         smp_ops->cause_ipi(cpu, info->data);
 }
 
@@ -211,7 +218,7 @@ irqreturn_t smp_ipi_demux(void)
         mb();   /* order any irq clear */
 
         do {
-                all = xchg_local(&info->messages, 0);
+                all = xchg(&info->messages, 0);
 
 #ifdef __BIG_ENDIAN
                 if (all & (1 << (24 - 8 * PPC_MSG_CALL_FUNCTION)))
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 3529446c2ab..8302af64921 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -194,6 +194,14 @@ static ssize_t show_dscr_default(struct device *dev,
         return sprintf(buf, "%lx\n", dscr_default);
 }
 
+static void update_dscr(void *dummy)
+{
+        if (!current->thread.dscr_inherit) {
+                current->thread.dscr = dscr_default;
+                mtspr(SPRN_DSCR, dscr_default);
+        }
+}
+
 static ssize_t __used store_dscr_default(struct device *dev,
                 struct device_attribute *attr, const char *buf,
                 size_t count)
@@ -206,6 +214,8 @@ static ssize_t __used store_dscr_default(struct device *dev,
                 return -EINVAL;
         dscr_default = val;
 
+        on_each_cpu(update_dscr, NULL, 1);
+
         return count;
 }
 
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index be171ee73bf..e49e93191b6 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -535,6 +535,15 @@ void timer_interrupt(struct pt_regs * regs)
         trace_timer_interrupt_exit(regs);
 }
 
+/*
+ * Hypervisor decrementer interrupts shouldn't occur but are sometimes
+ * left pending on exit from a KVM guest.  We don't need to do anything
+ * to clear them, as they are edge-triggered.
+ */
+void hdec_interrupt(struct pt_regs *regs)
+{
+}
+
 #ifdef CONFIG_SUSPEND
 static void generic_suspend_disable_irqs(void)
 {
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 158972341a2..ae0843fa7a6 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -972,8 +972,9 @@ static int emulate_instruction(struct pt_regs *regs)
                         cpu_has_feature(CPU_FTR_DSCR)) {
                 PPC_WARN_EMULATED(mtdscr, regs);
                 rd = (instword >> 21) & 0x1f;
-                mtspr(SPRN_DSCR, regs->gpr[rd]);
+                current->thread.dscr = regs->gpr[rd];
                 current->thread.dscr_inherit = 1;
+                mtspr(SPRN_DSCR, current->thread.dscr);
                 return 0;
         }
 #endif
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index dd223b3eb33..17e5b236431 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -20,7 +20,7 @@ int patch_instruction(unsigned int *addr, unsigned int instr)
 {
         int err;
 
-        err = __put_user(instr, addr);
+        __put_user_size(instr, addr, 4, err);
         if (err)
                 return err;
         asm ("dcbst 0, %0; sync; icbi 0,%0; sync; isync" : : "r" (addr));
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 39b159751c3..59213cfaeca 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1436,11 +1436,11 @@ static long vphn_get_associativity(unsigned long cpu,
 
 /*
  * Update the node maps and sysfs entries for each cpu whose home node
- * has changed.
+ * has changed. Returns 1 when the topology has changed, and 0 otherwise.
  */
 int arch_update_cpu_topology(void)
 {
-        int cpu, nid, old_nid;
+        int cpu, nid, old_nid, changed = 0;
         unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
         struct device *dev;
 
@@ -1466,9 +1466,10 @@ int arch_update_cpu_topology(void)
                 dev = get_cpu_device(cpu);
                 if (dev)
                         kobject_uevent(&dev->kobj, KOBJ_CHANGE);
+                changed = 1;
         }
 
-        return 1;
+        return changed;
 }
 
 static void topology_work_fn(struct work_struct *work)
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 3ef46254c35..7698b6e13c5 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -106,14 +106,6 @@ static void pnv_smp_cpu_kill_self(void)
 {
         unsigned int cpu;
 
-        /* If powersave_nap is enabled, use NAP mode, else just
-         * spin aimlessly
-         */
-        if (!powersave_nap) {
-                generic_mach_cpu_die();
-                return;
-        }
-
         /* Standard hot unplug procedure */
         local_irq_disable();
         idle_task_exit();
@@ -128,7 +120,7 @@ static void pnv_smp_cpu_kill_self(void)
          */
         mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1);
         while (!generic_check_cpu_restart(cpu)) {
-                power7_idle();
+                power7_nap();
                 if (!generic_check_cpu_restart(cpu)) {
                         DBG("CPU%d Unexpected exit while offline !\n", cpu);
                         /* We may be getting an IPI, so we re-enable
diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c
index 14469cf9df6..df0fc582146 100644
--- a/arch/powerpc/sysdev/xics/icp-hv.c
+++ b/arch/powerpc/sysdev/xics/icp-hv.c
@@ -65,7 +65,11 @@ static inline void icp_hv_set_xirr(unsigned int value)
 static inline void icp_hv_set_qirr(int n_cpu , u8 value)
 {
         int hw_cpu = get_hard_smp_processor_id(n_cpu);
-        long rc = plpar_hcall_norets(H_IPI, hw_cpu, value);
+        long rc;
+
+        /* Make sure all previous accesses are ordered before IPI sending */
+        mb();
+        rc = plpar_hcall_norets(H_IPI, hw_cpu, value);
         if (rc != H_SUCCESS) {
                 pr_err("%s: bad return code qirr cpu=%d hw_cpu=%d mfrr=0x%x "
                         "returned %ld\n", __func__, n_cpu, hw_cpu, value, rc);
diff --git a/arch/um/os-Linux/time.c b/arch/um/os-Linux/time.c
index f60238559af..0748fe0c8a7 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 b65a76133f4..5141d808e75 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 d4b25546325..76ba0e97e53 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])