applied patches from i9305 jb sources, updated mali to r3p0

Change-Id: Iec4bc4e2fb59e2cf5b4d25568a644d4e3719565e

8 files changed, 1816 insertions, 10 deletions

diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index 5398ce8..e960312 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -178,4 +178,119 @@ config DMA_SHARED_BUFFER
 	  APIs extension; the file's descriptor can then be passed on to other
 	  driver.
 
+config SYNC
+	bool "Synchronization framework"
+	default n
+	select ANON_INODES
+	help
+	  This option enables the framework for synchronization between multiple
+	  drivers.  Sync implementations can take advantage of hardware
+	  synchronization built into devices like GPUs.
+
+config SW_SYNC
+	bool "Software synchronization objects"
+	default n
+	depends on SYNC
+	help
+	  A sync object driver that uses a 32bit counter to coordinate
+	  syncrhronization.  Useful when there is no hardware primitive backing
+	  the synchronization.
+
+config SW_SYNC_USER
+       bool "Userspace API for SW_SYNC"
+       default n
+       depends on SW_SYNC
+       help
+         Provides a user space API to the sw sync object.
+         *WARNING* improper use of this can result in deadlocking kernel
+	 drivers from userspace.
+
+config DMA_CMA
+	bool "Contiguous Memory Allocator (EXPERIMENTAL)"
+	default n
+	select MIGRATION
+	help
+	  This enables the Contiguous Memory Allocator which allows drivers
+	  to allocate big physically-contiguous blocks of memory for use with
+	  hardware components that do not support I/O map nor scatter-gather.
+
+	  For more information see <include/linux/dma-contiguous.h>.
+	  If unsure, say "n".
+
+if DMA_CMA
+
+config DMA_CMA_DEBUG
+	bool "NEW CMA debug messages (DEVELOPMENT)"
+	depends on DEBUG_KERNEL
+	help
+	  Turns on debug messages in CMA.  This produces KERN_DEBUG
+	  messages for every CMA call as well as various messages while
+	  processing calls such as dma_alloc_from_contiguous().
+	  This option does not affect warning and error messages.
+
+comment "Default contiguous memory area size:"
+
+config CMA_SIZE_MBYTES
+	int "Size in Mega Bytes"
+	depends on !CMA_SIZE_SEL_PERCENTAGE
+	default 16
+	help
+	  Defines the size (in MiB) of the default memory area for CMA.
+
+config CMA_SIZE_PERCENTAGE
+	int "Percentage of total memory"
+	depends on !CMA_SIZE_SEL_MBYTES
+	default 10
+	help
+	  Defines the size of the default memory area for Contiguous Memory
+	  Allocator as a percentage of the total memory in the system.
+
+choice
+	prompt "Selected region size"
+	default CMA_SIZE_SEL_ABSOLUTE
+
+config CMA_SIZE_SEL_MBYTES
+	bool "Use mega bytes value only"
+
+config CMA_SIZE_SEL_PERCENTAGE
+	bool "Use percentage value only"
+
+config CMA_SIZE_SEL_MIN
+	bool "Use lower value (minimum)"
+
+config CMA_SIZE_SEL_MAX
+	bool "Use higher value (maximum)"
+
+endchoice
+
+config CMA_ALIGNMENT
+	int "Maximum PAGE_SIZE order of alignment for contiguous buffers"
+	range 4 9
+	default 8
+	help
+	  DMA mapping framework by default aligns all buffers to the smallest
+	  PAGE_SIZE order which is greater than or equal to the requested buffer
+	  size. This works well for buffers up to a few hundreds kilobytes, but
+	  for larger buffers it just a memory waste. With this parameter you can
+	  specify the maximum PAGE_SIZE order for contiguous buffers. Larger
+	  buffers will be aligned only to this specified order. The order is
+	  expressed as a power of two multiplied by the PAGE_SIZE.
+
+	  For example, if your system defaults to 4KiB pages, the order value
+	  of 8 means that the buffers will be aligned up to 1MiB only.
+
+	  If unsure, leave the default value "8".
+
+config CMA_AREAS
+	int "Maximum count of the CMA device-private areas"
+	default 7
+	help
+	  CMA allows to create CMA areas for particular devices. This parameter
+	  sets the maximum number of such device private CMA areas in the
+	  system.
+
+	  If unsure, leave the default value "7".
+
+endif
+
 endmenu
diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index a749d9b..a60d7e2 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -5,6 +5,7 @@ obj-y			:= core.o sys.o bus.o dd.o syscore.o \
 			   cpu.o firmware.o init.o map.o devres.o \
 			   attribute_container.o transport_class.o
 obj-$(CONFIG_DEVTMPFS)	+= devtmpfs.o
+obj-$(CONFIG_DMA_CMA)	+= dma-contiguous.o
 obj-y			+= power/
 obj-$(CONFIG_HAS_DMA)	+= dma-mapping.o
 obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
@@ -20,5 +21,8 @@ obj-$(CONFIG_MODULES)	+= module.o
 endif
 obj-$(CONFIG_SYS_HYPERVISOR) += hypervisor.o
 
+obj-$(CONFIG_SYNC)	+= sync.o
+obj-$(CONFIG_SW_SYNC)	+= sw_sync.o
+
 ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG
 
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 835ed32..68bd89e 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -1743,10 +1743,12 @@ void device_shutdown(void)
 		 */
 		list_del_init(&dev->kobj.entry);
 		spin_unlock(&devices_kset->list_lock);
-		/* Disable all device's runtime power management */
-		pm_runtime_disable(dev);
 
-#if defined(CONFIG_MACH_Q1_BD) || defined(CONFIG_MACH_PX)
+		/* Don't allow any more runtime suspends */
+		pm_runtime_get_noresume(dev);
+		pm_runtime_barrier(dev);
+
+#if defined(CONFIG_MACH_Q1_BD) || defined(CONFIG_MACH_PX) || defined(CONFIG_MACH_MIDAS)
 		/* Temporary log to analyze a problem during shutdown */
 		if (dev->bus && dev->bus->shutdown) {
 			dev_info(dev, "shutdown +: %pF\n", dev->bus->shutdown);
diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c
new file mode 100644
index 0000000..c3a6e3b
--- /dev/null
+++ b/drivers/base/dma-contiguous.c
@@ -0,0 +1,504 @@
+/*
+ * Contiguous Memory Allocator for DMA mapping framework
+ * Copyright (c) 2010-2011 by Samsung Electronics.
+ * Written by:
+ *	Marek Szyprowski <m.szyprowski@samsung.com>
+ *	Michal Nazarewicz <mina86@mina86.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License or (at your optional) any later version of the license.
+ */
+
+#define pr_fmt(fmt) "cma: " fmt
+
+#ifdef CONFIG_DMA_CMA_DEBUG
+#ifndef DEBUG
+#  define DEBUG
+#endif
+#endif
+
+#include <asm/page.h>
+#include <asm/dma-contiguous.h>
+
+#include <linux/memblock.h>
+#include <linux/err.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/page-isolation.h>
+#include <linux/slab.h>
+#include <linux/swap.h>
+#include <linux/mm_types.h>
+#include <linux/dma-contiguous.h>
+
+#ifndef SZ_1M
+#define SZ_1M (1 << 20)
+#endif
+
+struct cma {
+	unsigned long	base_pfn;
+	unsigned long	count;
+	unsigned long	*bitmap;
+};
+
+struct cma *dma_contiguous_default_area;
+
+#ifdef CONFIG_CMA_SIZE_MBYTES
+#define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES
+#else
+#define CMA_SIZE_MBYTES 0
+#endif
+
+/*
+ * Default global CMA area size can be defined in kernel's .config.
+ * This is usefull mainly for distro maintainers to create a kernel
+ * that works correctly for most supported systems.
+ * The size can be set in bytes or as a percentage of the total memory
+ * in the system.
+ *
+ * Users, who want to set the size of global CMA area for their system
+ * should use cma= kernel parameter.
+ */
+static const unsigned long size_bytes = CMA_SIZE_MBYTES * SZ_1M;
+static long size_cmdline = -1;
+
+static int __init early_cma(char *p)
+{
+	pr_debug("%s(%s)\n", __func__, p);
+	size_cmdline = memparse(p, &p);
+	return 0;
+}
+early_param("cma", early_cma);
+
+#ifdef CONFIG_CMA_SIZE_PERCENTAGE
+
+static unsigned long __init __maybe_unused cma_early_percent_memory(void)
+{
+	struct memblock_region *reg;
+	unsigned long total_pages = 0;
+
+	/*
+	 * We cannot use memblock_phys_mem_size() here, because
+	 * memblock_analyze() has not been called yet.
+	 */
+	for_each_memblock(memory, reg)
+		total_pages += memblock_region_memory_end_pfn(reg) -
+			       memblock_region_memory_base_pfn(reg);
+
+	return (total_pages * CONFIG_CMA_SIZE_PERCENTAGE / 100) << PAGE_SHIFT;
+}
+
+#else
+
+static inline __maybe_unused unsigned long cma_early_percent_memory(void)
+{
+	return 0;
+}
+
+#endif
+
+/**
+ * dma_contiguous_reserve() - reserve area for contiguous memory handling
+ * @limit: End address of the reserved memory (optional, 0 for any).
+ *
+ * This function reserves memory from early allocator. It should be
+ * called by arch specific code once the early allocator (memblock or bootmem)
+ * has been activated and all other subsystems have already allocated/reserved
+ * memory.
+ */
+void __init dma_contiguous_reserve(phys_addr_t limit)
+{
+	unsigned long selected_size = 0;
+
+	pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit);
+
+	if (size_cmdline != -1) {
+		selected_size = size_cmdline;
+	} else {
+#ifdef CONFIG_CMA_SIZE_SEL_MBYTES
+		selected_size = size_bytes;
+#elif defined(CONFIG_CMA_SIZE_SEL_PERCENTAGE)
+		selected_size = cma_early_percent_memory();
+#elif defined(CONFIG_CMA_SIZE_SEL_MIN)
+		selected_size = min(size_bytes, cma_early_percent_memory());
+#elif defined(CONFIG_CMA_SIZE_SEL_MAX)
+		selected_size = max(size_bytes, cma_early_percent_memory());
+#endif
+	}
+
+	if (selected_size) {
+		pr_debug("%s: reserving %ld MiB for global area\n", __func__,
+			 selected_size / SZ_1M);
+
+		dma_declare_contiguous(NULL, selected_size, 0, limit);
+	}
+};
+
+static DEFINE_MUTEX(cma_mutex);
+
+static __init int cma_activate_area(unsigned long base_pfn, unsigned long count)
+{
+	unsigned long pfn = base_pfn;
+	unsigned i = count >> pageblock_order;
+	struct zone *zone;
+
+	WARN_ON_ONCE(!pfn_valid(pfn));
+	zone = page_zone(pfn_to_page(pfn));
+
+	do {
+		unsigned j;
+		base_pfn = pfn;
+		for (j = pageblock_nr_pages; j; --j, pfn++) {
+			WARN_ON_ONCE(!pfn_valid(pfn));
+			if (page_zone(pfn_to_page(pfn)) != zone)
+				return -EINVAL;
+		}
+		init_cma_reserved_pageblock(pfn_to_page(base_pfn));
+	} while (--i);
+	return 0;
+}
+
+static __init struct cma *cma_create_area(unsigned long base_pfn,
+				     unsigned long count)
+{
+	int bitmap_size = BITS_TO_LONGS(count) * sizeof(long);
+	struct cma *cma;
+	int ret = -ENOMEM;
+
+	pr_debug("%s(base %08lx, count %lx)\n", __func__, base_pfn, count);
+
+	cma = kmalloc(sizeof *cma, GFP_KERNEL);
+	if (!cma)
+		return ERR_PTR(-ENOMEM);
+
+	cma->base_pfn = base_pfn;
+	cma->count = count;
+	cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+
+	if (!cma->bitmap)
+		goto no_mem;
+
+	ret = cma_activate_area(base_pfn, count);
+	if (ret)
+		goto error;
+
+	pr_debug("%s: returned %p\n", __func__, (void *)cma);
+	return cma;
+
+error:
+	kfree(cma->bitmap);
+no_mem:
+	kfree(cma);
+	return ERR_PTR(ret);
+}
+
+static struct cma_reserved {
+	phys_addr_t start;
+	unsigned long size;
+	struct device *dev;
+} cma_reserved[MAX_CMA_AREAS] __initdata;
+static unsigned cma_reserved_count __initdata;
+
+static int __init cma_init_reserved_areas(void)
+{
+	struct cma_reserved *r = cma_reserved;
+	unsigned i = cma_reserved_count;
+
+	pr_debug("%s()\n", __func__);
+
+	for (; i; --i, ++r) {
+		struct cma *cma;
+		cma = cma_create_area(PFN_DOWN(r->start),
+					r->size >> PAGE_SHIFT);
+		if (!IS_ERR(cma))
+			dev_set_cma_area(r->dev, cma);
+		else
+			printk(KERN_ERR "%s() cma_create_area error for %ud\n",
+					__func__, i);
+	}
+	return 0;
+}
+core_initcall(cma_init_reserved_areas);
+
+/**
+ * dma_declare_contiguous() - reserve area for contiguous memory handling
+ *			      for particular device
+ * @dev:   Pointer to device structure.
+ * @size:  Size of the reserved memory.
+ * @base:  Start address of the reserved memory (optional, 0 for any).
+ * @limit: End address of the reserved memory (optional, 0 for any).
+ *
+ * This function reserves memory for specified device. It should be
+ * called by board specific code when early allocator (memblock or bootmem)
+ * is still activate.
+ */
+int __init dma_declare_contiguous(struct device *dev, unsigned long size,
+				  phys_addr_t base, phys_addr_t limit)
+{
+	struct cma_reserved *r = &cma_reserved[cma_reserved_count];
+	unsigned long alignment;
+
+	pr_debug("%s(size %lx, base %08lx, limit %08lx)\n", __func__,
+		 (unsigned long)size, (unsigned long)base,
+		 (unsigned long)limit);
+
+	/* Sanity checks */
+	if (cma_reserved_count == ARRAY_SIZE(cma_reserved)) {
+		pr_err("Not enough slots for CMA reserved regions!\n");
+		return -ENOSPC;
+	}
+
+	if (!size)
+		return -EINVAL;
+
+	/* Sanitise input arguments */
+	alignment = PAGE_SIZE << max(MAX_ORDER-1, pageblock_order);
+	base = ALIGN(base, alignment);
+	size = ALIGN(size, alignment);
+	limit &= ~(alignment - 1);
+
+	/* Reserve memory */
+	if (base) {
+		if (memblock_is_region_reserved(base, size) ||
+		    memblock_reserve(base, size) < 0) {
+			base = -EBUSY;
+			goto err;
+		}
+	} else {
+		/*
+		 * Use __memblock_alloc_base() since
+		 * memblock_alloc_base() panic()s.
+		 */
+		phys_addr_t addr = __memblock_alloc_base(size, alignment,
+									limit);
+		if (!addr) {
+			base = -ENOMEM;
+			goto err;
+		} else if (addr + size > ~(unsigned long)0) {
+			memblock_free(addr, size);
+			base = -EINVAL;
+			goto err;
+		} else {
+			base = addr;
+		}
+	}
+
+	/*
+	 * Each reserved area must be initialised later, when more kernel
+	 * subsystems (like slab allocator) are available.
+	 */
+	r->start = base;
+	r->size = size;
+	r->dev = dev;
+	cma_reserved_count++;
+	pr_info("CMA: reserved %ld MiB at %08lx\n", size / SZ_1M,
+		(unsigned long)base);
+
+	/* Architecture specific contiguous memory fixup. */
+	dma_contiguous_early_fixup(base, size);
+	return 0;
+err:
+	pr_err("CMA: failed to reserve %ld MiB\n", size / SZ_1M);
+	return base;
+}
+
+static struct page *__dma_alloc_from_contiguous(struct device *dev, int count,
+				       unsigned int align)
+{
+	unsigned long mask, pfn, pageno, start = 0;
+	struct cma *cma = dev_get_cma_area(dev);
+	int ret;
+
+	if (!cma || !cma->count)
+		return NULL;
+
+	if (align > CONFIG_CMA_ALIGNMENT)
+		align = CONFIG_CMA_ALIGNMENT;
+
+	pr_debug("%s(cma %p, count %d, align %d)\n", __func__, (void *)cma,
+		 count, align);
+
+	if (!count)
+		return NULL;
+
+	mask = (1 << align) - 1;
+
+	mutex_lock(&cma_mutex);
+
+	for (;;) {
+		pageno = bitmap_find_next_zero_area(cma->bitmap, cma->count,
+						    start, count, mask);
+		if (pageno >= cma->count) {
+			printk(KERN_ERR "%s : cma->count is %lu, "
+					"pageno is %lu\n", __func__,
+					cma->count, pageno);
+			ret = -ENOMEM;
+			goto error;
+		}
+
+		pfn = cma->base_pfn + pageno;
+		ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA);
+		if (ret == 0) {
+			bitmap_set(cma->bitmap, pageno, count);
+			break;
+		} else if (ret != -EBUSY && ret != -EAGAIN) {
+			goto error;
+		}
+		pr_debug("%s(): memory range at %p is busy, retrying\n",
+			 __func__, pfn_to_page(pfn));
+		/* try again with a bit different memory target */
+		start = pageno + mask + 1;
+	}
+
+	mutex_unlock(&cma_mutex);
+
+	pr_debug("%s(): returned %p\n", __func__, pfn_to_page(pfn));
+	return pfn_to_page(pfn);
+error:
+	pr_err("%s(): returned error (%d)\n", __func__, ret);
+	mutex_unlock(&cma_mutex);
+	return NULL;
+}
+
+struct dma_prepare_alloc_ctx {
+	struct device *dev;
+	int count;
+	unsigned int align;
+	struct work_struct work;
+	struct list_head node;
+	struct page *result;
+};
+
+/* list of asynchronous allocations */
+static LIST_HEAD(dma_prepare_alloc_head);
+/* protects dma_prepare_alloc_head */
+static DEFINE_SPINLOCK(dma_prepare_alloc_lock);
+
+static void do_dma_prepare_alloc(struct work_struct *work)
+{
+	struct dma_prepare_alloc_ctx *ctx = container_of(
+			work, struct dma_prepare_alloc_ctx, work);
+
+	ctx->result = __dma_alloc_from_contiguous(ctx->dev, ctx->count,
+			ctx->align);
+	printk(KERN_INFO "%s[%d]: alloc %d pages for dev %s %s\n",
+		__func__, __LINE__, ctx->count, dev_name(ctx->dev),
+		ctx->result ? "succeeded" : "failed");
+}
+
+/**
+ * dma_prepare_alloc_from_contiguous() - prepare allocation of pages in
+ * an asynchronous thread
+ * @dev:   Pointer to device for which the allocation is performed.
+ * @count: Requested number of pages.
+ * @align: Requested alignment of pages (in PAGE_SIZE order).
+ *
+ * This function prepares an allocation by scheduling it in a separate work
+ * thread. Once dma_alloc_from_contiguous is called then it searches
+ * the dma_prepare_alloc_head list in the first place.
+ */
+int dma_prepare_alloc_from_contiguous(struct device *dev, int count,
+				unsigned int align)
+{
+	struct dma_prepare_alloc_ctx *ctx;
+	unsigned long flags;
+
+	ctx = kzalloc(sizeof *ctx, GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->dev = dev;
+	ctx->count = count;
+	ctx->align = align;
+	INIT_WORK(&ctx->work, do_dma_prepare_alloc);
+
+	spin_lock_irqsave(&dma_prepare_alloc_lock, flags);
+	list_add_tail(&ctx->node, &dma_prepare_alloc_head);
+	spin_unlock_irqrestore(&dma_prepare_alloc_lock, flags);
+
+	queue_work(system_long_wq, &ctx->work);
+	return 0;
+}
+
+/**
+ * dma_alloc_from_contiguous() - allocate pages from contiguous area
+ * @dev:   Pointer to device for which the allocation is performed.
+ * @count: Requested number of pages.
+ * @align: Requested alignment of pages (in PAGE_SIZE order).
+ *
+ * This function allocates memory buffer for specified device. It uses
+ * device specific contiguous memory area if available or the default
+ * global one. Requires architecture specific get_dev_cma_area() helper
+ * function.
+ */
+struct page *dma_alloc_from_contiguous(struct device *dev, int count,
+				unsigned int align)
+{
+	unsigned long flags;
+	struct list_head *i, *n;
+	struct dma_prepare_alloc_ctx *ctx = NULL;
+	struct page *result = NULL;
+
+	/* search for a cached allocation */
+	spin_lock_irqsave(&dma_prepare_alloc_lock, flags);
+	list_for_each_safe(i, n, &dma_prepare_alloc_head) {
+		ctx = list_entry(i, struct dma_prepare_alloc_ctx, node);
+		if (ctx->dev == dev && ctx->count == count &&
+		    ctx->align == align) {
+			list_del(i);
+			break;
+		}
+		ctx = NULL;
+	}
+	spin_unlock_irqrestore(&dma_prepare_alloc_lock, flags);
+
+	/* If a cached allocation is found then use its result */
+	if (ctx) {
+		flush_work(&ctx->work);
+		result = ctx->result;
+		kfree(ctx);
+	}
+	/* fallback to sync allocation */
+	if (!result)
+		result = __dma_alloc_from_contiguous(dev, count, align);
+	return result;
+}
+
+/**
+ * dma_release_from_contiguous() - release allocated pages
+ * @dev:   Pointer to device for which the pages were allocated.
+ * @pages: Allocated pages.
+ * @count: Number of allocated pages.
+ *
+ * This function releases memory allocated by dma_alloc_from_contiguous().
+ * It returns false when provided pages do not belong to contiguous area and
+ * true otherwise.
+ */
+bool dma_release_from_contiguous(struct device *dev, struct page *pages,
+				 int count)
+{
+	struct cma *cma = dev_get_cma_area(dev);
+	unsigned long pfn;
+
+	if (!cma || !pages)
+		return false;
+
+	pr_debug("%s(page %p)\n", __func__, (void *)pages);
+
+	pfn = page_to_pfn(pages);
+
+	if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count) {
+		pr_info("%s : return false\n", __func__);
+		return false;
+	}
+
+	VM_BUG_ON(pfn + count > cma->base_pfn + cma->count);
+
+	mutex_lock(&cma_mutex);
+	bitmap_clear(cma->bitmap, pfn - cma->base_pfn, count);
+	free_contig_range(pfn, count);
+	mutex_unlock(&cma_mutex);
+
+	return true;
+}
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 06ed6b4..3719c94 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -226,13 +226,13 @@ static ssize_t firmware_loading_store(struct device *dev,
 	int loading = simple_strtol(buf, NULL, 10);
 	int i;
 
+	mutex_lock(&fw_lock);
+
+	if (!fw_priv->fw)
+		goto out;
+
 	switch (loading) {
 	case 1:
-		mutex_lock(&fw_lock);
-		if (!fw_priv->fw) {
-			mutex_unlock(&fw_lock);
-			break;
-		}
 		firmware_free_data(fw_priv->fw);
 		memset(fw_priv->fw, 0, sizeof(struct firmware));
 		/* If the pages are not owned by 'struct firmware' */
@@ -243,7 +243,6 @@ static ssize_t firmware_loading_store(struct device *dev,
 		fw_priv->page_array_size = 0;
 		fw_priv->nr_pages = 0;
 		set_bit(FW_STATUS_LOADING, &fw_priv->status);
-		mutex_unlock(&fw_lock);
 		break;
 	case 0:
 		if (test_bit(FW_STATUS_LOADING, &fw_priv->status)) {
@@ -274,7 +273,8 @@ static ssize_t firmware_loading_store(struct device *dev,
 		fw_load_abort(fw_priv);
 		break;
 	}
-
+out:
+	mutex_unlock(&fw_lock);
 	return count;
 }
 
diff --git a/drivers/base/iommu.c b/drivers/base/iommu.c
new file mode 100644
index 0000000..6e6b6a1
--- /dev/null
+++ b/drivers/base/iommu.c
@@ -0,0 +1,124 @@
+/*
+ * Copyright (C) 2007-2008 Advanced Micro Devices, Inc.
+ * Author: Joerg Roedel <joerg.roedel@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#include <linux/bug.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/iommu.h>
+
+static struct iommu_ops *iommu_ops;
+
+void register_iommu(struct iommu_ops *ops)
+{
+	if (iommu_ops)
+		BUG();
+
+	iommu_ops = ops;
+}
+
+bool iommu_found(void)
+{
+	return iommu_ops != NULL;
+}
+EXPORT_SYMBOL_GPL(iommu_found);
+
+struct iommu_domain *iommu_domain_alloc(void)
+{
+	struct iommu_domain *domain;
+	int ret;
+
+	domain = kmalloc(sizeof(*domain), GFP_KERNEL);
+	if (!domain)
+		return NULL;
+
+	ret = iommu_ops->domain_init(domain);
+	if (ret)
+		goto out_free;
+
+	return domain;
+
+out_free:
+	kfree(domain);
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(iommu_domain_alloc);
+
+void iommu_domain_free(struct iommu_domain *domain)
+{
+	iommu_ops->domain_destroy(domain);
+	kfree(domain);
+}
+EXPORT_SYMBOL_GPL(iommu_domain_free);
+
+int iommu_attach_device(struct iommu_domain *domain, struct device *dev)
+{
+	return iommu_ops->attach_dev(domain, dev);
+}
+EXPORT_SYMBOL_GPL(iommu_attach_device);
+
+void iommu_detach_device(struct iommu_domain *domain, struct device *dev)
+{
+	iommu_ops->detach_dev(domain, dev);
+}
+EXPORT_SYMBOL_GPL(iommu_detach_device);
+
+phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain,
+			       unsigned long iova)
+{
+	return iommu_ops->iova_to_phys(domain, iova);
+}
+EXPORT_SYMBOL_GPL(iommu_iova_to_phys);
+
+int iommu_domain_has_cap(struct iommu_domain *domain,
+			 unsigned long cap)
+{
+	return iommu_ops->domain_has_cap(domain, cap);
+}
+EXPORT_SYMBOL_GPL(iommu_domain_has_cap);
+
+int iommu_map(struct iommu_domain *domain, unsigned long iova,
+	      phys_addr_t paddr, int gfp_order, int prot)
+{
+	unsigned long invalid_mask;
+	size_t size;
+
+	size         = 0x1000UL << gfp_order;
+	invalid_mask = size - 1;
+
+	BUG_ON((iova | paddr) & invalid_mask);
+
+	return iommu_ops->map(domain, iova, paddr, gfp_order, prot);
+}
+EXPORT_SYMBOL_GPL(iommu_map);
+
+int iommu_unmap(struct iommu_domain *domain, unsigned long iova, int gfp_order)
+{
+	unsigned long invalid_mask;
+	size_t size;
+
+	size         = 0x1000UL << gfp_order;
+	invalid_mask = size - 1;
+
+	BUG_ON(iova & invalid_mask);
+
+	return iommu_ops->unmap(domain, iova, gfp_order);
+}
+EXPORT_SYMBOL_GPL(iommu_unmap);
diff --git a/drivers/base/sw_sync.c b/drivers/base/sw_sync.c
new file mode 100644
index 0000000..21ddf4f
--- /dev/null
+++ b/drivers/base/sw_sync.c
@@ -0,0 +1,256 @@
+/*
+ * drivers/base/sw_sync.c
+ *
+ * Copyright (C) 2012 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/sw_sync.h>
+#include <linux/syscalls.h>
+#include <linux/uaccess.h>
+
+static int sw_sync_cmp(u32 a, u32 b)
+{
+	if (a == b)
+		return 0;
+
+	return ((s32)a - (s32)b) < 0 ? -1 : 1;
+}
+
+struct sync_pt *sw_sync_pt_create(struct sw_sync_timeline *obj, u32 value)
+{
+	struct sw_sync_pt *pt;
+
+	pt = (struct sw_sync_pt *)
+		sync_pt_create(&obj->obj, sizeof(struct sw_sync_pt));
+
+	pt->value = value;
+
+	return (struct sync_pt *)pt;
+}
+
+static struct sync_pt *sw_sync_pt_dup(struct sync_pt *sync_pt)
+{
+	struct sw_sync_pt *pt = (struct sw_sync_pt *) sync_pt;
+	struct sw_sync_timeline *obj =
+		(struct sw_sync_timeline *)sync_pt->parent;
+
+	return (struct sync_pt *) sw_sync_pt_create(obj, pt->value);
+}
+
+static int sw_sync_pt_has_signaled(struct sync_pt *sync_pt)
+{
+	struct sw_sync_pt *pt = (struct sw_sync_pt *)sync_pt;
+	struct sw_sync_timeline *obj =
+		(struct sw_sync_timeline *)sync_pt->parent;
+
+	return sw_sync_cmp(obj->value, pt->value) >= 0;
+}
+
+static int sw_sync_pt_compare(struct sync_pt *a, struct sync_pt *b)
+{
+	struct sw_sync_pt *pt_a = (struct sw_sync_pt *)a;
+	struct sw_sync_pt *pt_b = (struct sw_sync_pt *)b;
+
+	return sw_sync_cmp(pt_a->value, pt_b->value);
+}
+
+static void sw_sync_print_obj(struct seq_file *s,
+			      struct sync_timeline *sync_timeline)
+{
+	struct sw_sync_timeline *obj = (struct sw_sync_timeline *)sync_timeline;
+
+	seq_printf(s, "%d", obj->value);
+}
+
+static void sw_sync_print_pt(struct seq_file *s, struct sync_pt *sync_pt)
+{
+	struct sw_sync_pt *pt = (struct sw_sync_pt *)sync_pt;
+	struct sw_sync_timeline *obj =
+		(struct sw_sync_timeline *)sync_pt->parent;
+
+	seq_printf(s, "%d / %d", pt->value, obj->value);
+}
+
+static int sw_sync_fill_driver_data(struct sync_pt *sync_pt,
+				    void *data, int size)
+{
+	struct sw_sync_pt *pt = (struct sw_sync_pt *)sync_pt;
+
+	if (size < sizeof(pt->value))
+		return -ENOMEM;
+
+	memcpy(data, &pt->value, sizeof(pt->value));
+
+	return sizeof(pt->value);
+}
+
+struct sync_timeline_ops sw_sync_timeline_ops = {
+	.driver_name = "sw_sync",
+	.dup = sw_sync_pt_dup,
+	.has_signaled = sw_sync_pt_has_signaled,
+	.compare = sw_sync_pt_compare,
+	.print_obj = sw_sync_print_obj,
+	.print_pt = sw_sync_print_pt,
+	.fill_driver_data = sw_sync_fill_driver_data,
+};
+
+
+struct sw_sync_timeline *sw_sync_timeline_create(const char *name)
+{
+	struct sw_sync_timeline *obj = (struct sw_sync_timeline *)
+		sync_timeline_create(&sw_sync_timeline_ops,
+				     sizeof(struct sw_sync_timeline),
+				     name);
+
+	return obj;
+}
+
+void sw_sync_timeline_inc(struct sw_sync_timeline *obj, u32 inc)
+{
+	obj->value += inc;
+
+	sync_timeline_signal(&obj->obj);
+}
+
+
+#ifdef CONFIG_SW_SYNC_USER
+/* *WARNING*
+ *
+ * improper use of this can result in deadlocking kernel drivers from userspace.
+ */
+
+/* opening sw_sync create a new sync obj */
+int sw_sync_open(struct inode *inode, struct file *file)
+{
+	struct sw_sync_timeline *obj;
+	char task_comm[TASK_COMM_LEN];
+
+	get_task_comm(task_comm, current);
+
+	obj = sw_sync_timeline_create(task_comm);
+	if (obj == NULL)
+		return -ENOMEM;
+
+	file->private_data = obj;
+
+	return 0;
+}
+
+int sw_sync_release(struct inode *inode, struct file *file)
+{
+	struct sw_sync_timeline *obj = file->private_data;
+	sync_timeline_destroy(&obj->obj);
+	return 0;
+}
+
+long sw_sync_ioctl_create_fence(struct sw_sync_timeline *obj, unsigned long arg)
+{
+	int fd = get_unused_fd();
+	int err;
+	struct sync_pt *pt;
+	struct sync_fence *fence;
+	struct sw_sync_create_fence_data data;
+
+	if (copy_from_user(&data, (void __user *)arg, sizeof(data)))
+		return -EFAULT;
+
+	pt = sw_sync_pt_create(obj, data.value);
+	if (pt == NULL) {
+		err = -ENOMEM;
+		goto err;
+	}
+
+	data.name[sizeof(data.name) - 1] = '\0';
+	fence = sync_fence_create(data.name, pt);
+	if (fence == NULL) {
+		sync_pt_free(pt);
+		err = -ENOMEM;
+		goto err;
+	}
+
+	data.fence = fd;
+	if (copy_to_user((void __user *)arg, &data, sizeof(data))) {
+		sync_fence_put(fence);
+		err = -EFAULT;
+		goto err;
+	}
+
+	sync_fence_install(fence, fd);
+
+	return 0;
+
+err:
+	put_unused_fd(fd);
+	return err;
+}
+
+long sw_sync_ioctl_inc(struct sw_sync_timeline *obj, unsigned long arg)
+{
+	u32 value;
+
+	if (copy_from_user(&value, (void __user *)arg, sizeof(value)))
+		return -EFAULT;
+
+	sw_sync_timeline_inc(obj, value);
+
+	return 0;
+}
+
+long sw_sync_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct sw_sync_timeline *obj = file->private_data;
+
+	switch (cmd) {
+	case SW_SYNC_IOC_CREATE_FENCE:
+		return sw_sync_ioctl_create_fence(obj, arg);
+
+	case SW_SYNC_IOC_INC:
+		return sw_sync_ioctl_inc(obj, arg);
+
+	default:
+		return -ENOTTY;
+	}
+}
+
+static const struct file_operations sw_sync_fops = {
+	.owner = THIS_MODULE,
+	.open = sw_sync_open,
+	.release = sw_sync_release,
+	.unlocked_ioctl = sw_sync_ioctl,
+};
+
+static struct miscdevice sw_sync_dev = {
+	.minor	= MISC_DYNAMIC_MINOR,
+	.name	= "sw_sync",
+	.fops	= &sw_sync_fops,
+};
+
+int __init sw_sync_device_init(void)
+{
+	return misc_register(&sw_sync_dev);
+}
+
+void __exit sw_sync_device_remove(void)
+{
+	misc_deregister(&sw_sync_dev);
+}
+
+module_init(sw_sync_device_init);
+module_exit(sw_sync_device_remove);
+
+#endif /* CONFIG_SW_SYNC_USER */
diff --git a/drivers/base/sync.c b/drivers/base/sync.c
new file mode 100644
index 0000000..d6913f8
--- /dev/null
+++ b/drivers/base/sync.c
@@ -0,0 +1,801 @@
+/*
+ * drivers/base/sync.c
+ *
+ * Copyright (C) 2012 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/debugfs.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/kernel.h>
+#include <linux/poll.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/sync.h>
+#include <linux/uaccess.h>
+
+#include <linux/anon_inodes.h>
+
+static void sync_fence_signal_pt(struct sync_pt *pt);
+static int _sync_pt_has_signaled(struct sync_pt *pt);
+
+static LIST_HEAD(sync_timeline_list_head);
+static DEFINE_SPINLOCK(sync_timeline_list_lock);
+
+static LIST_HEAD(sync_fence_list_head);
+static DEFINE_SPINLOCK(sync_fence_list_lock);
+
+struct sync_timeline *sync_timeline_create(const struct sync_timeline_ops *ops,
+					   int size, const char *name)
+{
+	struct sync_timeline *obj;
+	unsigned long flags;
+
+	if (size < sizeof(struct sync_timeline))
+		return NULL;
+
+	obj = kzalloc(size, GFP_KERNEL);
+	if (obj == NULL)
+		return NULL;
+
+	obj->ops = ops;
+	strlcpy(obj->name, name, sizeof(obj->name));
+
+	INIT_LIST_HEAD(&obj->child_list_head);
+	spin_lock_init(&obj->child_list_lock);
+
+	INIT_LIST_HEAD(&obj->active_list_head);
+	spin_lock_init(&obj->active_list_lock);
+
+	spin_lock_irqsave(&sync_timeline_list_lock, flags);
+	list_add_tail(&obj->sync_timeline_list, &sync_timeline_list_head);
+	spin_unlock_irqrestore(&sync_timeline_list_lock, flags);
+
+	return obj;
+}
+
+static void sync_timeline_free(struct sync_timeline *obj)
+{
+	unsigned long flags;
+
+	if (obj->ops->release_obj)
+		obj->ops->release_obj(obj);
+
+	spin_lock_irqsave(&sync_timeline_list_lock, flags);
+	list_del(&obj->sync_timeline_list);
+	spin_unlock_irqrestore(&sync_timeline_list_lock, flags);
+
+	kfree(obj);
+}
+
+void sync_timeline_destroy(struct sync_timeline *obj)
+{
+	unsigned long flags;
+	bool needs_freeing;
+
+	spin_lock_irqsave(&obj->child_list_lock, flags);
+	obj->destroyed = true;
+	needs_freeing = list_empty(&obj->child_list_head);
+	spin_unlock_irqrestore(&obj->child_list_lock, flags);
+
+	if (needs_freeing)
+		sync_timeline_free(obj);
+	else
+		sync_timeline_signal(obj);
+}
+
+static void sync_timeline_add_pt(struct sync_timeline *obj, struct sync_pt *pt)
+{
+	unsigned long flags;
+
+	pt->parent = obj;
+
+	spin_lock_irqsave(&obj->child_list_lock, flags);
+	list_add_tail(&pt->child_list, &obj->child_list_head);
+	spin_unlock_irqrestore(&obj->child_list_lock, flags);
+}
+
+static void sync_timeline_remove_pt(struct sync_pt *pt)
+{
+	struct sync_timeline *obj = pt->parent;
+	unsigned long flags;
+	bool needs_freeing;
+
+	spin_lock_irqsave(&obj->active_list_lock, flags);
+	if (!list_empty(&pt->active_list))
+		list_del_init(&pt->active_list);
+	spin_unlock_irqrestore(&obj->active_list_lock, flags);
+
+	spin_lock_irqsave(&obj->child_list_lock, flags);
+	list_del(&pt->child_list);
+	needs_freeing = obj->destroyed && list_empty(&obj->child_list_head);
+	spin_unlock_irqrestore(&obj->child_list_lock, flags);
+
+	if (needs_freeing)
+		sync_timeline_free(obj);
+}
+
+void sync_timeline_signal(struct sync_timeline *obj)
+{
+	unsigned long flags;
+	LIST_HEAD(signaled_pts);
+	struct list_head *pos, *n;
+
+	spin_lock_irqsave(&obj->active_list_lock, flags);
+
+	list_for_each_safe(pos, n, &obj->active_list_head) {
+		struct sync_pt *pt =
+			container_of(pos, struct sync_pt, active_list);
+
+		if (_sync_pt_has_signaled(pt))
+			list_move(pos, &signaled_pts);
+	}
+
+	spin_unlock_irqrestore(&obj->active_list_lock, flags);
+
+	list_for_each_safe(pos, n, &signaled_pts) {
+		struct sync_pt *pt =
+			container_of(pos, struct sync_pt, active_list);
+
+		list_del_init(pos);
+		sync_fence_signal_pt(pt);
+	}
+}
+
+struct sync_pt *sync_pt_create(struct sync_timeline *parent, int size)
+{
+	struct sync_pt *pt;
+
+	if (size < sizeof(struct sync_pt))
+		return NULL;
+
+	pt = kzalloc(size, GFP_KERNEL);
+	if (pt == NULL)
+		return NULL;
+
+	INIT_LIST_HEAD(&pt->active_list);
+	sync_timeline_add_pt(parent, pt);
+
+	return pt;
+}
+
+void sync_pt_free(struct sync_pt *pt)
+{
+	if (pt->parent->ops->free_pt)
+		pt->parent->ops->free_pt(pt);
+
+	sync_timeline_remove_pt(pt);
+
+	kfree(pt);
+}
+
+/* call with pt->parent->active_list_lock held */
+static int _sync_pt_has_signaled(struct sync_pt *pt)
+{
+	int old_status = pt->status;
+
+	if (!pt->status)
+		pt->status = pt->parent->ops->has_signaled(pt);
+
+	if (!pt->status && pt->parent->destroyed)
+		pt->status = -ENOENT;
+
+	if (pt->status != old_status)
+		pt->timestamp = ktime_get();
+
+	return pt->status;
+}
+
+static struct sync_pt *sync_pt_dup(struct sync_pt *pt)
+{
+	return pt->parent->ops->dup(pt);
+}
+
+/* Adds a sync pt to the active queue.  Called when added to a fence */
+static void sync_pt_activate(struct sync_pt *pt)
+{
+	struct sync_timeline *obj = pt->parent;
+	unsigned long flags;
+	int err;
+
+	spin_lock_irqsave(&obj->active_list_lock, flags);
+
+	err = _sync_pt_has_signaled(pt);
+	if (err != 0)
+		goto out;
+
+	list_add_tail(&pt->active_list, &obj->active_list_head);
+
+out:
+	spin_unlock_irqrestore(&obj->active_list_lock, flags);
+}
+
+static int sync_fence_release(struct inode *inode, struct file *file);
+static unsigned int sync_fence_poll(struct file *file, poll_table *wait);
+static long sync_fence_ioctl(struct file *file, unsigned int cmd,
+			     unsigned long arg);
+
+
+static const struct file_operations sync_fence_fops = {
+	.release = sync_fence_release,
+	.poll = sync_fence_poll,
+	.unlocked_ioctl = sync_fence_ioctl,
+};
+
+static struct sync_fence *sync_fence_alloc(const char *name)
+{
+	struct sync_fence *fence;
+	unsigned long flags;
+
+	fence = kzalloc(sizeof(struct sync_fence), GFP_KERNEL);
+	if (fence == NULL)
+		return NULL;
+
+	fence->file = anon_inode_getfile("sync_fence", &sync_fence_fops,
+					 fence, 0);
+	if (fence->file == NULL)
+		goto err;
+
+	strlcpy(fence->name, name, sizeof(fence->name));
+
+	INIT_LIST_HEAD(&fence->pt_list_head);
+	INIT_LIST_HEAD(&fence->waiter_list_head);
+	spin_lock_init(&fence->waiter_list_lock);
+
+	init_waitqueue_head(&fence->wq);
+
+	spin_lock_irqsave(&sync_fence_list_lock, flags);
+	list_add_tail(&fence->sync_fence_list, &sync_fence_list_head);
+	spin_unlock_irqrestore(&sync_fence_list_lock, flags);
+
+	return fence;
+
+err:
+	kfree(fence);
+	return NULL;
+}
+
+/* TODO: implement a create which takes more that one sync_pt */
+struct sync_fence *sync_fence_create(const char *name, struct sync_pt *pt)
+{
+	struct sync_fence *fence;
+
+	if (pt->fence)
+		return NULL;
+
+	fence = sync_fence_alloc(name);
+	if (fence == NULL)
+		return NULL;
+
+	pt->fence = fence;
+	list_add(&pt->pt_list, &fence->pt_list_head);
+	sync_pt_activate(pt);
+
+	return fence;
+}
+
+static int sync_fence_copy_pts(struct sync_fence *dst, struct sync_fence *src)
+{
+	struct list_head *pos;
+
+	list_for_each(pos, &src->pt_list_head) {
+		struct sync_pt *orig_pt =
+			container_of(pos, struct sync_pt, pt_list);
+		struct sync_pt *new_pt = sync_pt_dup(orig_pt);
+
+		if (new_pt == NULL)
+			return -ENOMEM;
+
+		new_pt->fence = dst;
+		list_add(&new_pt->pt_list, &dst->pt_list_head);
+		sync_pt_activate(new_pt);
+	}
+
+	return 0;
+}
+
+static void sync_fence_free_pts(struct sync_fence *fence)
+{
+	struct list_head *pos, *n;
+
+	list_for_each_safe(pos, n, &fence->pt_list_head) {
+		struct sync_pt *pt = container_of(pos, struct sync_pt, pt_list);
+		sync_pt_free(pt);
+	}
+}
+
+struct sync_fence *sync_fence_fdget(int fd)
+{
+	struct file *file = fget(fd);
+
+	if (file == NULL)
+		return NULL;
+
+	if (file->f_op != &sync_fence_fops)
+		goto err;
+
+	return file->private_data;
+
+err:
+	fput(file);
+	return NULL;
+}
+
+void sync_fence_put(struct sync_fence *fence)
+{
+	fput(fence->file);
+}
+
+void sync_fence_install(struct sync_fence *fence, int fd)
+{
+	fd_install(fd, fence->file);
+}
+
+static int sync_fence_get_status(struct sync_fence *fence)
+{
+	struct list_head *pos;
+	int status = 1;
+
+	list_for_each(pos, &fence->pt_list_head) {
+		struct sync_pt *pt = container_of(pos, struct sync_pt, pt_list);
+		int pt_status = pt->status;
+
+		if (pt_status < 0) {
+			status = pt_status;
+			break;
+		} else if (status == 1) {
+			status = pt_status;
+		}
+	}
+
+	return status;
+}
+
+struct sync_fence *sync_fence_merge(const char *name,
+				    struct sync_fence *a, struct sync_fence *b)
+{
+	struct sync_fence *fence;
+	int err;
+
+	fence = sync_fence_alloc(name);
+	if (fence == NULL)
+		return NULL;
+
+	err = sync_fence_copy_pts(fence, a);
+	if (err < 0)
+		goto err;
+
+	err = sync_fence_copy_pts(fence, b);
+	if (err < 0)
+		goto err;
+
+	fence->status = sync_fence_get_status(fence);
+
+	return fence;
+err:
+	sync_fence_free_pts(fence);
+	kfree(fence);
+	return NULL;
+}
+
+static void sync_fence_signal_pt(struct sync_pt *pt)
+{
+	LIST_HEAD(signaled_waiters);
+	struct sync_fence *fence = pt->fence;
+	struct list_head *pos;
+	struct list_head *n;
+	unsigned long flags;
+	int status;
+
+	status = sync_fence_get_status(fence);
+
+	spin_lock_irqsave(&fence->waiter_list_lock, flags);
+	/*
+	 * this should protect against two threads racing on the signaled
+	 * false -> true transition
+	 */
+	if (status && !fence->status) {
+		list_for_each_safe(pos, n, &fence->waiter_list_head)
+			list_move(pos, &signaled_waiters);
+
+		fence->status = status;
+	} else {
+		status = 0;
+	}
+	spin_unlock_irqrestore(&fence->waiter_list_lock, flags);
+
+	if (status) {
+		list_for_each_safe(pos, n, &signaled_waiters) {
+			struct sync_fence_waiter *waiter =
+				container_of(pos, struct sync_fence_waiter,
+					     waiter_list);
+
+			waiter->callback(fence, waiter->callback_data);
+			list_del(pos);
+			kfree(waiter);
+		}
+		wake_up(&fence->wq);
+	}
+}
+
+int sync_fence_wait_async(struct sync_fence *fence,
+			  void (*callback)(struct sync_fence *, void *data),
+			  void *callback_data)
+{
+	struct sync_fence_waiter *waiter;
+	unsigned long flags;
+	int err = 0;
+
+	waiter = kzalloc(sizeof(struct sync_fence_waiter), GFP_KERNEL);
+	if (waiter == NULL)
+		return -ENOMEM;
+
+	waiter->callback = callback;
+	waiter->callback_data = callback_data;
+
+	spin_lock_irqsave(&fence->waiter_list_lock, flags);
+
+	if (fence->status) {
+		kfree(waiter);
+		err = fence->status;
+		goto out;
+	}
+
+	list_add_tail(&waiter->waiter_list, &fence->waiter_list_head);
+out:
+	spin_unlock_irqrestore(&fence->waiter_list_lock, flags);
+
+	return err;
+}
+
+int sync_fence_wait(struct sync_fence *fence, long timeout)
+{
+	int err;
+
+	if (timeout) {
+		timeout = msecs_to_jiffies(timeout);
+		err = wait_event_interruptible_timeout(fence->wq,
+						       fence->status != 0,
+						       timeout);
+	} else {
+		err = wait_event_interruptible(fence->wq, fence->status != 0);
+	}
+
+	if (err < 0)
+		return err;
+
+	if (fence->status < 0)
+		return fence->status;
+
+	if (fence->status == 0)
+		return -ETIME;
+
+	return 0;
+}
+
+static int sync_fence_release(struct inode *inode, struct file *file)
+{
+	struct sync_fence *fence = file->private_data;
+	unsigned long flags;
+
+	sync_fence_free_pts(fence);
+
+	spin_lock_irqsave(&sync_fence_list_lock, flags);
+	list_del(&fence->sync_fence_list);
+	spin_unlock_irqrestore(&sync_fence_list_lock, flags);
+
+	kfree(fence);
+
+	return 0;
+}
+
+static unsigned int sync_fence_poll(struct file *file, poll_table *wait)
+{
+	struct sync_fence *fence = file->private_data;
+
+	poll_wait(file, &fence->wq, wait);
+
+	if (fence->status == 1)
+		return POLLIN;
+	else if (fence->status < 0)
+		return POLLERR;
+	else
+		return 0;
+}
+
+static long sync_fence_ioctl_wait(struct sync_fence *fence, unsigned long arg)
+{
+	__u32 value;
+
+	if (copy_from_user(&value, (void __user *)arg, sizeof(value)))
+		return -EFAULT;
+
+	return sync_fence_wait(fence, value);
+}
+
+static long sync_fence_ioctl_merge(struct sync_fence *fence, unsigned long arg)
+{
+	int fd = get_unused_fd();
+	int err;
+	struct sync_fence *fence2, *fence3;
+	struct sync_merge_data data;
+
+	if (copy_from_user(&data, (void __user *)arg, sizeof(data)))
+		return -EFAULT;
+
+	fence2 = sync_fence_fdget(data.fd2);
+	if (fence2 == NULL) {
+		err = -ENOENT;
+		goto err_put_fd;
+	}
+
+	data.name[sizeof(data.name) - 1] = '\0';
+	fence3 = sync_fence_merge(data.name, fence, fence2);
+	if (fence3 == NULL) {
+		err = -ENOMEM;
+		goto err_put_fence2;
+	}
+
+	data.fence = fd;
+	if (copy_to_user((void __user *)arg, &data, sizeof(data))) {
+		err = -EFAULT;
+		goto err_put_fence3;
+	}
+
+	sync_fence_install(fence3, fd);
+	sync_fence_put(fence2);
+	return 0;
+
+err_put_fence3:
+	sync_fence_put(fence3);
+
+err_put_fence2:
+	sync_fence_put(fence2);
+
+err_put_fd:
+	put_unused_fd(fd);
+	return err;
+}
+
+int sync_fill_pt_info(struct sync_pt *pt, void *data, int size)
+{
+	struct sync_pt_info *info = data;
+	int ret;
+
+	if (size < sizeof(struct sync_pt_info))
+		return -ENOMEM;
+
+	info->len = sizeof(struct sync_pt_info);
+
+	if (pt->parent->ops->fill_driver_data) {
+		ret = pt->parent->ops->fill_driver_data(pt, info->driver_data,
+							size - sizeof(*info));
+		if (ret < 0)
+			return ret;
+
+		info->len += ret;
+	}
+
+	strlcpy(info->obj_name, pt->parent->name, sizeof(info->obj_name));
+	strlcpy(info->driver_name, pt->parent->ops->driver_name,
+		sizeof(info->driver_name));
+	info->status = pt->status;
+	info->timestamp_ns = ktime_to_ns(pt->timestamp);
+
+	return info->len;
+}
+
+
+static long sync_fence_ioctl_fence_info(struct sync_fence *fence,
+					unsigned long arg)
+{
+	struct sync_fence_info_data *data;
+	struct list_head *pos;
+	__u32 size;
+	__u32 len = 0;
+	int ret;
+
+	if (copy_from_user(&size, (void __user *)arg, sizeof(size)))
+		return -EFAULT;
+
+	if (size < sizeof(struct sync_fence_info_data))
+		return -EINVAL;
+
+	if (size > 4096)
+		size = 4096;
+
+	data = kzalloc(size, GFP_KERNEL);
+	if (data == NULL)
+		return -ENOMEM;
+
+	strlcpy(data->name, fence->name, sizeof(data->name));
+	data->status = fence->status;
+	len = sizeof(struct sync_fence_info_data);
+
+	list_for_each(pos, &fence->pt_list_head) {
+		struct sync_pt *pt =
+			container_of(pos, struct sync_pt, pt_list);
+
+		ret = sync_fill_pt_info(pt, (u8 *)data + len, size - len);
+
+		if (ret < 0)
+			goto out;
+
+		len += ret;
+	}
+
+	data->len = len;
+
+	if (copy_to_user((void __user *)arg, data, len))
+		ret = -EFAULT;
+	else
+		ret = 0;
+
+out:
+	kfree(data);
+
+	return ret;
+}
+
+static long sync_fence_ioctl(struct file *file, unsigned int cmd,
+			     unsigned long arg)
+{
+	struct sync_fence *fence = file->private_data;
+	switch (cmd) {
+	case SYNC_IOC_WAIT:
+		return sync_fence_ioctl_wait(fence, arg);
+
+	case SYNC_IOC_MERGE:
+		return sync_fence_ioctl_merge(fence, arg);
+
+	case SYNC_IOC_FENCE_INFO:
+		return sync_fence_ioctl_fence_info(fence, arg);
+
+	default:
+		return -ENOTTY;
+	}
+}
+
+#ifdef CONFIG_DEBUG_FS
+static const char *sync_status_str(int status)
+{
+	if (status > 0)
+		return "signaled";
+	else if (status == 0)
+		return "active";
+	else
+		return "error";
+}
+
+static void sync_print_pt(struct seq_file *s, struct sync_pt *pt, bool fence)
+{
+	int status = pt->status;
+	seq_printf(s, "  %s%spt %s",
+		   fence ? pt->parent->name : "",
+		   fence ? "_" : "",
+		   sync_status_str(status));
+	if (pt->status) {
+		struct timeval tv = ktime_to_timeval(pt->timestamp);
+		seq_printf(s, "@%ld.%06ld", tv.tv_sec, tv.tv_usec);
+	}
+
+	if (pt->parent->ops->print_pt) {
+		seq_printf(s, ": ");
+		pt->parent->ops->print_pt(s, pt);
+	}
+
+	seq_printf(s, "\n");
+}
+
+static void sync_print_obj(struct seq_file *s, struct sync_timeline *obj)
+{
+	struct list_head *pos;
+	unsigned long flags;
+
+	seq_printf(s, "%s %s", obj->name, obj->ops->driver_name);
+
+	if (obj->ops->print_obj) {
+		seq_printf(s, ": ");
+		obj->ops->print_obj(s, obj);
+	}
+
+	seq_printf(s, "\n");
+
+	spin_lock_irqsave(&obj->child_list_lock, flags);
+	list_for_each(pos, &obj->child_list_head) {
+		struct sync_pt *pt =
+			container_of(pos, struct sync_pt, child_list);
+		sync_print_pt(s, pt, false);
+	}
+	spin_unlock_irqrestore(&obj->child_list_lock, flags);
+}
+
+static void sync_print_fence(struct seq_file *s, struct sync_fence *fence)
+{
+	struct list_head *pos;
+	unsigned long flags;
+
+	seq_printf(s, "%s: %s\n", fence->name, sync_status_str(fence->status));
+
+	list_for_each(pos, &fence->pt_list_head) {
+		struct sync_pt *pt =
+			container_of(pos, struct sync_pt, pt_list);
+		sync_print_pt(s, pt, true);
+	}
+
+	spin_lock_irqsave(&fence->waiter_list_lock, flags);
+	list_for_each(pos, &fence->waiter_list_head) {
+		struct sync_fence_waiter *waiter =
+			container_of(pos, struct sync_fence_waiter,
+				     waiter_list);
+
+		seq_printf(s, "waiter %pF %p\n", waiter->callback,
+			   waiter->callback_data);
+	}
+	spin_unlock_irqrestore(&fence->waiter_list_lock, flags);
+}
+
+static int sync_debugfs_show(struct seq_file *s, void *unused)
+{
+	unsigned long flags;
+	struct list_head *pos;
+
+	seq_printf(s, "objs:\n--------------\n");
+
+	spin_lock_irqsave(&sync_timeline_list_lock, flags);
+	list_for_each(pos, &sync_timeline_list_head) {
+		struct sync_timeline *obj =
+			container_of(pos, struct sync_timeline,
+				     sync_timeline_list);
+
+		sync_print_obj(s, obj);
+		seq_printf(s, "\n");
+	}
+	spin_unlock_irqrestore(&sync_timeline_list_lock, flags);
+
+	seq_printf(s, "fences:\n--------------\n");
+
+	spin_lock_irqsave(&sync_fence_list_lock, flags);
+	list_for_each(pos, &sync_fence_list_head) {
+		struct sync_fence *fence =
+			container_of(pos, struct sync_fence, sync_fence_list);
+
+		sync_print_fence(s, fence);
+		seq_printf(s, "\n");
+	}
+	spin_unlock_irqrestore(&sync_fence_list_lock, flags);
+	return 0;
+}
+
+static int sync_debugfs_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, sync_debugfs_show, inode->i_private);
+}
+
+static const struct file_operations sync_debugfs_fops = {
+	.open           = sync_debugfs_open,
+	.read           = seq_read,
+	.llseek         = seq_lseek,
+	.release        = single_release,
+};
+
+static __init int sync_debugfs_init(void)
+{
+	debugfs_create_file("sync", S_IRUGO, NULL, NULL, &sync_debugfs_fops);
+	return 0;
+}
+
+late_initcall(sync_debugfs_init);
+
+#endif