Merge branch 'for-rmk' of git://gitorious.org/linux-gemini/mainline

30 files changed, 549 insertions, 309 deletions

diff --git a/arch/arm/mach-gemini/include/mach/hardware.h b/arch/arm/mach-gemini/include/mach/hardware.h
index de6752674c0..213a4fcfeb1 100644
--- a/arch/arm/mach-gemini/include/mach/hardware.h
+++ b/arch/arm/mach-gemini/include/mach/hardware.h
@@ -15,10 +15,9 @@
 /*
  * Memory Map definitions
  */
-/* FIXME: Does it really swap SRAM like this? */
 #ifdef CONFIG_GEMINI_MEM_SWAP
 # define GEMINI_DRAM_BASE	0x00000000
-# define GEMINI_SRAM_BASE	0x20000000
+# define GEMINI_SRAM_BASE	0x70000000
 #else
 # define GEMINI_SRAM_BASE	0x00000000
 # define GEMINI_DRAM_BASE	0x10000000
diff --git a/arch/blackfin/include/asm/.gitignore b/arch/blackfin/include/asm/.gitignore
deleted file mode 100644
index 7858564a446..00000000000
--- a/arch/blackfin/include/asm/.gitignore
+++ /dev/null
@@ -1 +0,0 @@
-+mach
diff --git a/arch/blackfin/include/asm/unistd.h b/arch/blackfin/include/asm/unistd.h
index 1e57b636e0b..cf5066d3efd 100644
--- a/arch/blackfin/include/asm/unistd.h
+++ b/arch/blackfin/include/asm/unistd.h
@@ -378,8 +378,10 @@
 #define __NR_dup3		363
 #define __NR_pipe2		364
 #define __NR_inotify_init1	365
+#define __NR_preadv		366
+#define __NR_pwritev		367
 
-#define __NR_syscall		366
+#define __NR_syscall		368
 #define NR_syscalls		__NR_syscall
 
 /* Old optional stuff no one actually uses */
diff --git a/arch/blackfin/kernel/.gitignore b/arch/blackfin/kernel/.gitignore
new file mode 100644
index 00000000000..c5f676c3c22
--- /dev/null
+++ b/arch/blackfin/kernel/.gitignore
@@ -0,0 +1 @@
+vmlinux.lds
diff --git a/arch/blackfin/lib/strncmp.c b/arch/blackfin/lib/strncmp.c
index 2aaae78a68e..46518b1d298 100644
--- a/arch/blackfin/lib/strncmp.c
+++ b/arch/blackfin/lib/strncmp.c
@@ -8,9 +8,8 @@
 
 #define strncmp __inline_strncmp
 #include <asm/string.h>
-#undef strncmp
-
 #include <linux/module.h>
+#undef strncmp
 
 int strncmp(const char *cs, const char *ct, size_t count)
 {
diff --git a/arch/blackfin/mach-common/entry.S b/arch/blackfin/mach-common/entry.S
index 21e65a339a2..a063a434f7e 100644
--- a/arch/blackfin/mach-common/entry.S
+++ b/arch/blackfin/mach-common/entry.S
@@ -1581,6 +1581,8 @@ ENTRY(_sys_call_table)
 	.long _sys_dup3
 	.long _sys_pipe2
 	.long _sys_inotify_init1	/* 365 */
+	.long _sys_preadv
+	.long _sys_pwritev
 
 	.rept NR_syscalls-(.-_sys_call_table)/4
 	.long _sys_ni_syscall
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index a0d1146a057..cdc9a6ff4be 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -868,6 +868,18 @@ config TASK_SIZE
 	default "0x80000000" if PPC_PREP || PPC_8xx
 	default "0xc0000000"
 
+config CONSISTENT_SIZE_BOOL
+	bool "Set custom consistent memory pool size"
+	depends on ADVANCED_OPTIONS && NOT_COHERENT_CACHE
+	help
+	  This option allows you to set the size of the
+	  consistent memory pool.  This pool of virtual memory
+	  is used to make consistent memory allocations.
+
+config CONSISTENT_SIZE
+	hex "Size of consistent memory pool" if CONSISTENT_SIZE_BOOL
+	default "0x00200000" if NOT_COHERENT_CACHE
+
 config PIN_TLB
 	bool "Pinned Kernel TLBs (860 ONLY)"
 	depends on ADVANCED_OPTIONS && 8xx
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index c69f2b5f0cc..cb448d68452 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -26,7 +26,9 @@
  * allocate the space "normally" and use the cache management functions
  * to ensure it is consistent.
  */
-extern void *__dma_alloc_coherent(size_t size, dma_addr_t *handle, gfp_t gfp);
+struct device;
+extern void *__dma_alloc_coherent(struct device *dev, size_t size,
+				  dma_addr_t *handle, gfp_t gfp);
 extern void __dma_free_coherent(size_t size, void *vaddr);
 extern void __dma_sync(void *vaddr, size_t size, int direction);
 extern void __dma_sync_page(struct page *page, unsigned long offset,
@@ -37,7 +39,7 @@ extern void __dma_sync_page(struct page *page, unsigned long offset,
  * Cache coherent cores.
  */
 
-#define __dma_alloc_coherent(gfp, size, handle)	NULL
+#define __dma_alloc_coherent(dev, gfp, size, handle)	NULL
 #define __dma_free_coherent(size, addr)		((void)0)
 #define __dma_sync(addr, size, rw)		((void)0)
 #define __dma_sync_page(pg, off, sz, rw)	((void)0)
diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h
index d60fd18f428..f1f4e23a84e 100644
--- a/arch/powerpc/include/asm/fixmap.h
+++ b/arch/powerpc/include/asm/fixmap.h
@@ -14,8 +14,6 @@
 #ifndef _ASM_FIXMAP_H
 #define _ASM_FIXMAP_H
 
-extern unsigned long FIXADDR_TOP;
-
 #ifndef __ASSEMBLY__
 #include <linux/kernel.h>
 #include <asm/page.h>
@@ -24,6 +22,8 @@ extern unsigned long FIXADDR_TOP;
 #include <asm/kmap_types.h>
 #endif
 
+#define FIXADDR_TOP	((unsigned long)(-PAGE_SIZE))
+
 /*
  * Here we define all the compile-time 'special' virtual
  * addresses. The point is to have a constant address at
diff --git a/arch/powerpc/include/asm/pgtable-ppc32.h b/arch/powerpc/include/asm/pgtable-ppc32.h
index ba45c997830..c9ff9d75990 100644
--- a/arch/powerpc/include/asm/pgtable-ppc32.h
+++ b/arch/powerpc/include/asm/pgtable-ppc32.h
@@ -10,7 +10,7 @@
 
 extern unsigned long va_to_phys(unsigned long address);
 extern pte_t *va_to_pte(unsigned long address);
-extern unsigned long ioremap_bot, ioremap_base;
+extern unsigned long ioremap_bot;
 
 #ifdef CONFIG_44x
 extern int icache_44x_need_flush;
@@ -56,8 +56,30 @@ extern int icache_44x_need_flush;
 	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
 
 /*
+ * This is the bottom of the PKMAP area with HIGHMEM or an arbitrary
+ * value (for now) on others, from where we can start layout kernel
+ * virtual space that goes below PKMAP and FIXMAP
+ */
+#ifdef CONFIG_HIGHMEM
+#define KVIRT_TOP	PKMAP_BASE
+#else
+#define KVIRT_TOP	(0xfe000000UL)	/* for now, could be FIXMAP_BASE ? */
+#endif
+
+/*
+ * ioremap_bot starts at that address. Early ioremaps move down from there,
+ * until mem_init() at which point this becomes the top of the vmalloc
+ * and ioremap space
+ */
+#ifdef CONFIG_NOT_COHERENT_CACHE
+#define IOREMAP_TOP	((KVIRT_TOP - CONFIG_CONSISTENT_SIZE) & PAGE_MASK)
+#else
+#define IOREMAP_TOP	KVIRT_TOP
+#endif
+
+/*
  * Just any arbitrary offset to the start of the vmalloc VM area: the
- * current 64MB value just means that there will be a 64MB "hole" after the
+ * current 16MB value just means that there will be a 64MB "hole" after the
  * physical memory until the kernel virtual memory starts.  That means that
  * any out-of-bounds memory accesses will hopefully be caught.
  * The vmalloc() routines leaves a hole of 4kB between each vmalloced
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 53c7788cba7..6b02793dc75 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -32,7 +32,7 @@ void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 {
 	void *ret;
 #ifdef CONFIG_NOT_COHERENT_CACHE
-	ret = __dma_alloc_coherent(size, dma_handle, flag);
+	ret = __dma_alloc_coherent(dev, size, dma_handle, flag);
 	if (ret == NULL)
 		return NULL;
 	*dma_handle += get_dma_direct_offset(dev);
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 8db35278a4b..29b742b90f1 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -18,7 +18,6 @@ obj-$(CONFIG_PPC64)	+= copypage_64.o copyuser_64.o \
 			   memcpy_64.o usercopy_64.o mem_64.o string.o
 obj-$(CONFIG_XMON)	+= sstep.o
 obj-$(CONFIG_KPROBES)	+= sstep.o
-obj-$(CONFIG_NOT_COHERENT_CACHE)	+= dma-noncoherent.o
 
 ifeq ($(CONFIG_PPC64),y)
 obj-$(CONFIG_SMP)	+= locks.o
diff --git a/arch/powerpc/lib/dma-noncoherent.c b/arch/powerpc/lib/dma-noncoherent.c
deleted file mode 100644
index 005a28d380a..00000000000
--- a/arch/powerpc/lib/dma-noncoherent.c
+++ /dev/null
@@ -1,237 +0,0 @@
-/*
- *  PowerPC version derived from arch/arm/mm/consistent.c
- *    Copyright (C) 2001 Dan Malek (dmalek@jlc.net)
- *
- *  Copyright (C) 2000 Russell King
- *
- * Consistent memory allocators.  Used for DMA devices that want to
- * share uncached memory with the processor core.  The function return
- * is the virtual address and 'dma_handle' is the physical address.
- * Mostly stolen from the ARM port, with some changes for PowerPC.
- *						-- Dan
- *
- * Reorganized to get rid of the arch-specific consistent_* functions
- * and provide non-coherent implementations for the DMA API. -Matt
- *
- * Added in_interrupt() safe dma_alloc_coherent()/dma_free_coherent()
- * implementation. This is pulled straight from ARM and barely
- * modified. -Matt
- *
- * 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.
- */
-
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <linux/highmem.h>
-#include <linux/dma-mapping.h>
-#include <linux/vmalloc.h>
-
-#include <asm/tlbflush.h>
-
-/*
- * Allocate DMA-coherent memory space and return both the kernel remapped
- * virtual and bus address for that space.
- */
-void *
-__dma_alloc_coherent(size_t size, dma_addr_t *handle, gfp_t gfp)
-{
-	struct page *page;
-	unsigned long order;
-	int i;
-	unsigned int nr_pages = PAGE_ALIGN(size)>>PAGE_SHIFT;
-	unsigned int array_size = nr_pages * sizeof(struct page *);
-	struct page **pages;
-	struct page *end;
-	u64 mask = 0x00ffffff, limit; /* ISA default */
-	struct vm_struct *area;
-
-	BUG_ON(!mem_init_done);
-	size = PAGE_ALIGN(size);
-	limit = (mask + 1) & ~mask;
-	if (limit && size >= limit) {
-		printk(KERN_WARNING "coherent allocation too big (requested "
-				"%#x mask %#Lx)\n", size, mask);
-		return NULL;
-	}
-
-	order = get_order(size);
-
-	if (mask != 0xffffffff)
-		gfp |= GFP_DMA;
-
-	page = alloc_pages(gfp, order);
-	if (!page)
-		goto no_page;
-
-	end = page + (1 << order);
-
-	/*
-	 * Invalidate any data that might be lurking in the
-	 * kernel direct-mapped region for device DMA.
-	 */
-	{
-		unsigned long kaddr = (unsigned long)page_address(page);
-		memset(page_address(page), 0, size);
-		flush_dcache_range(kaddr, kaddr + size);
-	}
-
-	split_page(page, order);
-
-	/*
-	 * Set the "dma handle"
-	 */
-	*handle = page_to_phys(page);
-
-	area = get_vm_area_caller(size, VM_IOREMAP,
-			__builtin_return_address(1));
-	if (!area)
-		goto out_free_pages;
-
-	if (array_size > PAGE_SIZE) {
-		pages = vmalloc(array_size);
-		area->flags |= VM_VPAGES;
-	} else {
-		pages = kmalloc(array_size, GFP_KERNEL);
-	}
-	if (!pages)
-		goto out_free_area;
-
-	area->pages = pages;
-	area->nr_pages = nr_pages;
-
-	for (i = 0; i < nr_pages; i++)
-		pages[i] = page + i;
-
-	if (map_vm_area(area, pgprot_noncached(PAGE_KERNEL), &pages))
-		goto out_unmap;
-
-	/*
-	 * Free the otherwise unused pages.
-	 */
-	page += nr_pages;
-	while (page < end) {
-		__free_page(page);
-		page++;
-	}
-
-	return area->addr;
-out_unmap:
-	vunmap(area->addr);
-	if (array_size > PAGE_SIZE)
-		vfree(pages);
-	else
-		kfree(pages);
-	goto out_free_pages;
-out_free_area:
-	free_vm_area(area);
-out_free_pages:
-	if (page)
-		__free_pages(page, order);
-no_page:
-	return NULL;
-}
-EXPORT_SYMBOL(__dma_alloc_coherent);
-
-/*
- * free a page as defined by the above mapping.
- */
-void __dma_free_coherent(size_t size, void *vaddr)
-{
-	vfree(vaddr);
-
-}
-EXPORT_SYMBOL(__dma_free_coherent);
-
-/*
- * make an area consistent.
- */
-void __dma_sync(void *vaddr, size_t size, int direction)
-{
-	unsigned long start = (unsigned long)vaddr;
-	unsigned long end   = start + size;
-
-	switch (direction) {
-	case DMA_NONE:
-		BUG();
-	case DMA_FROM_DEVICE:
-		/*
-		 * invalidate only when cache-line aligned otherwise there is
-		 * the potential for discarding uncommitted data from the cache
-		 */
-		if ((start & (L1_CACHE_BYTES - 1)) || (size & (L1_CACHE_BYTES - 1)))
-			flush_dcache_range(start, end);
-		else
-			invalidate_dcache_range(start, end);
-		break;
-	case DMA_TO_DEVICE:		/* writeback only */
-		clean_dcache_range(start, end);
-		break;
-	case DMA_BIDIRECTIONAL:	/* writeback and invalidate */
-		flush_dcache_range(start, end);
-		break;
-	}
-}
-EXPORT_SYMBOL(__dma_sync);
-
-#ifdef CONFIG_HIGHMEM
-/*
- * __dma_sync_page() implementation for systems using highmem.
- * In this case, each page of a buffer must be kmapped/kunmapped
- * in order to have a virtual address for __dma_sync(). This must
- * not sleep so kmap_atomic()/kunmap_atomic() are used.
- *
- * Note: yes, it is possible and correct to have a buffer extend
- * beyond the first page.
- */
-static inline void __dma_sync_page_highmem(struct page *page,
-		unsigned long offset, size_t size, int direction)
-{
-	size_t seg_size = min((size_t)(PAGE_SIZE - offset), size);
-	size_t cur_size = seg_size;
-	unsigned long flags, start, seg_offset = offset;
-	int nr_segs = 1 + ((size - seg_size) + PAGE_SIZE - 1)/PAGE_SIZE;
-	int seg_nr = 0;
-
-	local_irq_save(flags);
-
-	do {
-		start = (unsigned long)kmap_atomic(page + seg_nr,
-				KM_PPC_SYNC_PAGE) + seg_offset;
-
-		/* Sync this buffer segment */
-		__dma_sync((void *)start, seg_size, direction);
-		kunmap_atomic((void *)start, KM_PPC_SYNC_PAGE);
-		seg_nr++;
-
-		/* Calculate next buffer segment size */
-		seg_size = min((size_t)PAGE_SIZE, size - cur_size);
-
-		/* Add the segment size to our running total */
-		cur_size += seg_size;
-		seg_offset = 0;
-	} while (seg_nr < nr_segs);
-
-	local_irq_restore(flags);
-}
-#endif /* CONFIG_HIGHMEM */
-
-/*
- * __dma_sync_page makes memory consistent. identical to __dma_sync, but
- * takes a struct page instead of a virtual address
- */
-void __dma_sync_page(struct page *page, unsigned long offset,
-	size_t size, int direction)
-{
-#ifdef CONFIG_HIGHMEM
-	__dma_sync_page_highmem(page, offset, size, direction);
-#else
-	unsigned long start = (unsigned long)page_address(page) + offset;
-	__dma_sync((void *)start, size, direction);
-#endif
-}
-EXPORT_SYMBOL(__dma_sync_page);
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 17290bcedc5..b746f4ca420 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -26,3 +26,4 @@ obj-$(CONFIG_NEED_MULTIPLE_NODES) += numa.o
 obj-$(CONFIG_PPC_MM_SLICES)	+= slice.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_PPC_SUBPAGE_PROT)	+= subpage-prot.o
+obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c
new file mode 100644
index 00000000000..36692f5c9a7
--- /dev/null
+++ b/arch/powerpc/mm/dma-noncoherent.c
@@ -0,0 +1,400 @@
+/*
+ *  PowerPC version derived from arch/arm/mm/consistent.c
+ *    Copyright (C) 2001 Dan Malek (dmalek@jlc.net)
+ *
+ *  Copyright (C) 2000 Russell King
+ *
+ * Consistent memory allocators.  Used for DMA devices that want to
+ * share uncached memory with the processor core.  The function return
+ * is the virtual address and 'dma_handle' is the physical address.
+ * Mostly stolen from the ARM port, with some changes for PowerPC.
+ *						-- Dan
+ *
+ * Reorganized to get rid of the arch-specific consistent_* functions
+ * and provide non-coherent implementations for the DMA API. -Matt
+ *
+ * Added in_interrupt() safe dma_alloc_coherent()/dma_free_coherent()
+ * implementation. This is pulled straight from ARM and barely
+ * modified. -Matt
+ *
+ * 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.
+ */
+
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/highmem.h>
+#include <linux/dma-mapping.h>
+
+#include <asm/tlbflush.h>
+
+#include "mmu_decl.h"
+
+/*
+ * This address range defaults to a value that is safe for all
+ * platforms which currently set CONFIG_NOT_COHERENT_CACHE. It
+ * can be further configured for specific applications under
+ * the "Advanced Setup" menu. -Matt
+ */
+#define CONSISTENT_BASE		(IOREMAP_TOP)
+#define CONSISTENT_END 		(CONSISTENT_BASE + CONFIG_CONSISTENT_SIZE)
+#define CONSISTENT_OFFSET(x)	(((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT)
+
+/*
+ * This is the page table (2MB) covering uncached, DMA consistent allocations
+ */
+static DEFINE_SPINLOCK(consistent_lock);
+
+/*
+ * VM region handling support.
+ *
+ * This should become something generic, handling VM region allocations for
+ * vmalloc and similar (ioremap, module space, etc).
+ *
+ * I envisage vmalloc()'s supporting vm_struct becoming:
+ *
+ *  struct vm_struct {
+ *    struct vm_region	region;
+ *    unsigned long	flags;
+ *    struct page	**pages;
+ *    unsigned int	nr_pages;
+ *    unsigned long	phys_addr;
+ *  };
+ *
+ * get_vm_area() would then call vm_region_alloc with an appropriate
+ * struct vm_region head (eg):
+ *
+ *  struct vm_region vmalloc_head = {
+ *	.vm_list	= LIST_HEAD_INIT(vmalloc_head.vm_list),
+ *	.vm_start	= VMALLOC_START,
+ *	.vm_end		= VMALLOC_END,
+ *  };
+ *
+ * However, vmalloc_head.vm_start is variable (typically, it is dependent on
+ * the amount of RAM found at boot time.)  I would imagine that get_vm_area()
+ * would have to initialise this each time prior to calling vm_region_alloc().
+ */
+struct ppc_vm_region {
+	struct list_head	vm_list;
+	unsigned long		vm_start;
+	unsigned long		vm_end;
+};
+
+static struct ppc_vm_region consistent_head = {
+	.vm_list	= LIST_HEAD_INIT(consistent_head.vm_list),
+	.vm_start	= CONSISTENT_BASE,
+	.vm_end		= CONSISTENT_END,
+};
+
+static struct ppc_vm_region *
+ppc_vm_region_alloc(struct ppc_vm_region *head, size_t size, gfp_t gfp)
+{
+	unsigned long addr = head->vm_start, end = head->vm_end - size;
+	unsigned long flags;
+	struct ppc_vm_region *c, *new;
+
+	new = kmalloc(sizeof(struct ppc_vm_region), gfp);
+	if (!new)
+		goto out;
+
+	spin_lock_irqsave(&consistent_lock, flags);
+
+	list_for_each_entry(c, &head->vm_list, vm_list) {
+		if ((addr + size) < addr)
+			goto nospc;
+		if ((addr + size) <= c->vm_start)
+			goto found;
+		addr = c->vm_end;
+		if (addr > end)
+			goto nospc;
+	}
+
+ found:
+	/*
+	 * Insert this entry _before_ the one we found.
+	 */
+	list_add_tail(&new->vm_list, &c->vm_list);
+	new->vm_start = addr;
+	new->vm_end = addr + size;
+
+	spin_unlock_irqrestore(&consistent_lock, flags);
+	return new;
+
+ nospc:
+	spin_unlock_irqrestore(&consistent_lock, flags);
+	kfree(new);
+ out:
+	return NULL;
+}
+
+static struct ppc_vm_region *ppc_vm_region_find(struct ppc_vm_region *head, unsigned long addr)
+{
+	struct ppc_vm_region *c;
+
+	list_for_each_entry(c, &head->vm_list, vm_list) {
+		if (c->vm_start == addr)
+			goto out;
+	}
+	c = NULL;
+ out:
+	return c;
+}
+
+/*
+ * Allocate DMA-coherent memory space and return both the kernel remapped
+ * virtual and bus address for that space.
+ */
+void *
+__dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp)
+{
+	struct page *page;
+	struct ppc_vm_region *c;
+	unsigned long order;
+	u64 mask = ISA_DMA_THRESHOLD, limit;
+
+	if (dev) {
+		mask = dev->coherent_dma_mask;
+
+		/*
+		 * Sanity check the DMA mask - it must be non-zero, and
+		 * must be able to be satisfied by a DMA allocation.
+		 */
+		if (mask == 0) {
+			dev_warn(dev, "coherent DMA mask is unset\n");
+			goto no_page;
+		}
+
+		if ((~mask) & ISA_DMA_THRESHOLD) {
+			dev_warn(dev, "coherent DMA mask %#llx is smaller "
+				 "than system GFP_DMA mask %#llx\n",
+				 mask, (unsigned long long)ISA_DMA_THRESHOLD);
+			goto no_page;
+		}
+	}
+
+
+	size = PAGE_ALIGN(size);
+	limit = (mask + 1) & ~mask;
+	if ((limit && size >= limit) ||
+	    size >= (CONSISTENT_END - CONSISTENT_BASE)) {
+		printk(KERN_WARNING "coherent allocation too big (requested %#x mask %#Lx)\n",
+		       size, mask);
+		return NULL;
+	}
+
+	order = get_order(size);
+
+	/* Might be useful if we ever have a real legacy DMA zone... */
+	if (mask != 0xffffffff)
+		gfp |= GFP_DMA;
+
+	page = alloc_pages(gfp, order);
+	if (!page)
+		goto no_page;
+
+	/*
+	 * Invalidate any data that might be lurking in the
+	 * kernel direct-mapped region for device DMA.
+	 */
+	{
+		unsigned long kaddr = (unsigned long)page_address(page);
+		memset(page_address(page), 0, size);
+		flush_dcache_range(kaddr, kaddr + size);
+	}
+
+	/*
+	 * Allocate a virtual address in the consistent mapping region.
+	 */
+	c = ppc_vm_region_alloc(&consistent_head, size,
+			    gfp & ~(__GFP_DMA | __GFP_HIGHMEM));
+	if (c) {
+		unsigned long vaddr = c->vm_start;
+		struct page *end = page + (1 << order);
+
+		split_page(page, order);
+
+		/*
+		 * Set the "dma handle"
+		 */
+		*handle = page_to_phys(page);
+
+		do {
+			SetPageReserved(page);
+			map_page(vaddr, page_to_phys(page),
+				 pgprot_noncached(PAGE_KERNEL));
+			page++;
+			vaddr += PAGE_SIZE;
+		} while (size -= PAGE_SIZE);
+
+		/*
+		 * Free the otherwise unused pages.
+		 */
+		while (page < end) {
+			__free_page(page);
+			page++;
+		}
+
+		return (void *)c->vm_start;
+	}
+
+	if (page)
+		__free_pages(page, order);
+ no_page:
+	return NULL;
+}
+EXPORT_SYMBOL(__dma_alloc_coherent);
+
+/*
+ * free a page as defined by the above mapping.
+ */
+void __dma_free_coherent(size_t size, void *vaddr)
+{
+	struct ppc_vm_region *c;
+	unsigned long flags, addr;
+	
+	size = PAGE_ALIGN(size);
+
+	spin_lock_irqsave(&consistent_lock, flags);
+
+	c = ppc_vm_region_find(&consistent_head, (unsigned long)vaddr);
+	if (!c)
+		goto no_area;
+
+	if ((c->vm_end - c->vm_start) != size) {
+		printk(KERN_ERR "%s: freeing wrong coherent size (%ld != %d)\n",
+		       __func__, c->vm_end - c->vm_start, size);
+		dump_stack();
+		size = c->vm_end - c->vm_start;
+	}
+
+	addr = c->vm_start;
+	do {
+		pte_t *ptep;
+		unsigned long pfn;
+
+		ptep = pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(addr),
+							       addr),
+						    addr),
+					 addr);
+		if (!pte_none(*ptep) && pte_present(*ptep)) {
+			pfn = pte_pfn(*ptep);
+			pte_clear(&init_mm, addr, ptep);
+			if (pfn_valid(pfn)) {
+				struct page *page = pfn_to_page(pfn);
+
+				ClearPageReserved(page);
+				__free_page(page);
+			}
+		}
+		addr += PAGE_SIZE;
+	} while (size -= PAGE_SIZE);
+
+	flush_tlb_kernel_range(c->vm_start, c->vm_end);
+
+	list_del(&c->vm_list);
+
+	spin_unlock_irqrestore(&consistent_lock, flags);
+
+	kfree(c);
+	return;
+
+ no_area:
+	spin_unlock_irqrestore(&consistent_lock, flags);
+	printk(KERN_ERR "%s: trying to free invalid coherent area: %p\n",
+	       __func__, vaddr);
+	dump_stack();
+}
+EXPORT_SYMBOL(__dma_free_coherent);
+
+/*
+ * make an area consistent.
+ */
+void __dma_sync(void *vaddr, size_t size, int direction)
+{
+	unsigned long start = (unsigned long)vaddr;
+	unsigned long end   = start + size;
+
+	switch (direction) {
+	case DMA_NONE:
+		BUG();
+	case DMA_FROM_DEVICE:
+		/*
+		 * invalidate only when cache-line aligned otherwise there is
+		 * the potential for discarding uncommitted data from the cache
+		 */
+		if ((start & (L1_CACHE_BYTES - 1)) || (size & (L1_CACHE_BYTES - 1)))
+			flush_dcache_range(start, end);
+		else
+			invalidate_dcache_range(start, end);
+		break;
+	case DMA_TO_DEVICE:		/* writeback only */
+		clean_dcache_range(start, end);
+		break;
+	case DMA_BIDIRECTIONAL:	/* writeback and invalidate */
+		flush_dcache_range(start, end);
+		break;
+	}
+}
+EXPORT_SYMBOL(__dma_sync);
+
+#ifdef CONFIG_HIGHMEM
+/*
+ * __dma_sync_page() implementation for systems using highmem.
+ * In this case, each page of a buffer must be kmapped/kunmapped
+ * in order to have a virtual address for __dma_sync(). This must
+ * not sleep so kmap_atomic()/kunmap_atomic() are used.
+ *
+ * Note: yes, it is possible and correct to have a buffer extend
+ * beyond the first page.
+ */
+static inline void __dma_sync_page_highmem(struct page *page,
+		unsigned long offset, size_t size, int direction)
+{
+	size_t seg_size = min((size_t)(PAGE_SIZE - offset), size);
+	size_t cur_size = seg_size;
+	unsigned long flags, start, seg_offset = offset;
+	int nr_segs = 1 + ((size - seg_size) + PAGE_SIZE - 1)/PAGE_SIZE;
+	int seg_nr = 0;
+
+	local_irq_save(flags);
+
+	do {
+		start = (unsigned long)kmap_atomic(page + seg_nr,
+				KM_PPC_SYNC_PAGE) + seg_offset;
+
+		/* Sync this buffer segment */
+		__dma_sync((void *)start, seg_size, direction);
+		kunmap_atomic((void *)start, KM_PPC_SYNC_PAGE);
+		seg_nr++;
+
+		/* Calculate next buffer segment size */
+		seg_size = min((size_t)PAGE_SIZE, size - cur_size);
+
+		/* Add the segment size to our running total */
+		cur_size += seg_size;
+		seg_offset = 0;
+	} while (seg_nr < nr_segs);
+
+	local_irq_restore(flags);
+}
+#endif /* CONFIG_HIGHMEM */
+
+/*
+ * __dma_sync_page makes memory consistent. identical to __dma_sync, but
+ * takes a struct page instead of a virtual address
+ */
+void __dma_sync_page(struct page *page, unsigned long offset,
+	size_t size, int direction)
+{
+#ifdef CONFIG_HIGHMEM
+	__dma_sync_page_highmem(page, offset, size, direction);
+#else
+	unsigned long start = (unsigned long)page_address(page) + offset;
+	__dma_sync((void *)start, size, direction);
+#endif
+}
+EXPORT_SYMBOL(__dma_sync_page);
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index 666a5e8a5be..3de6a0d9382 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -168,12 +168,8 @@ void __init MMU_init(void)
 		ppc_md.progress("MMU:mapin", 0x301);
 	mapin_ram();
 
-#ifdef CONFIG_HIGHMEM
-	ioremap_base = PKMAP_BASE;
-#else
-	ioremap_base = 0xfe000000UL;	/* for now, could be 0xfffff000 */
-#endif /* CONFIG_HIGHMEM */
-	ioremap_bot = ioremap_base;
+	/* Initialize early top-down ioremap allocator */
+	ioremap_bot = IOREMAP_TOP;
 
 	/* Map in I/O resources */
 	if (ppc_md.progress)
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index d0602a76bf7..579382c163a 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -380,6 +380,23 @@ void __init mem_init(void)
 		bsssize >> 10,
 		initsize >> 10);
 
+#ifdef CONFIG_PPC32
+	pr_info("Kernel virtual memory layout:\n");
+	pr_info("  * 0x%08lx..0x%08lx  : fixmap\n", FIXADDR_START, FIXADDR_TOP);
+#ifdef CONFIG_HIGHMEM
+	pr_info("  * 0x%08lx..0x%08lx  : highmem PTEs\n",
+		PKMAP_BASE, PKMAP_ADDR(LAST_PKMAP));
+#endif /* CONFIG_HIGHMEM */
+#ifdef CONFIG_NOT_COHERENT_CACHE
+	pr_info("  * 0x%08lx..0x%08lx  : consistent mem\n",
+		IOREMAP_TOP, IOREMAP_TOP + CONFIG_CONSISTENT_SIZE);
+#endif /* CONFIG_NOT_COHERENT_CACHE */
+	pr_info("  * 0x%08lx..0x%08lx  : early ioremap\n",
+		ioremap_bot, IOREMAP_TOP);
+	pr_info("  * 0x%08lx..0x%08lx  : vmalloc & ioremap\n",
+		VMALLOC_START, VMALLOC_END);
+#endif /* CONFIG_PPC32 */
+
 	mem_init_done = 1;
 }
 
diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c
index a70e311bd45..030d0005b4d 100644
--- a/arch/powerpc/mm/mmu_context_nohash.c
+++ b/arch/powerpc/mm/mmu_context_nohash.c
@@ -127,12 +127,12 @@ static unsigned int steal_context_up(unsigned int id)
 
 	pr_debug("[%d] steal context %d from mm @%p\n", cpu, id, mm);
 
-	/* Mark this mm has having no context anymore */
-	mm->context.id = MMU_NO_CONTEXT;
-
 	/* Flush the TLB for that context */
 	local_flush_tlb_mm(mm);
 
+	/* Mark this mm has having no context anymore */
+	mm->context.id = MMU_NO_CONTEXT;
+
 	/* XXX This clear should ultimately be part of local_flush_tlb_mm */
 	__clear_bit(id, stale_map[cpu]);
 
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 430d0908fa5..5422169626b 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -399,8 +399,6 @@ void kernel_map_pages(struct page *page, int numpages, int enable)
 #endif /* CONFIG_DEBUG_PAGEALLOC */
 
 static int fixmaps;
-unsigned long FIXADDR_TOP = (-PAGE_SIZE);
-EXPORT_SYMBOL(FIXADDR_TOP);
 
 void __set_fixmap (enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags)
 {
diff --git a/arch/x86/boot/compressed/relocs.c b/arch/x86/boot/compressed/relocs.c
index 857e492c571..bbeb0c3fbd9 100644
--- a/arch/x86/boot/compressed/relocs.c
+++ b/arch/x86/boot/compressed/relocs.c
@@ -504,8 +504,11 @@ static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym))
 			if (sym->st_shndx == SHN_ABS) {
 				continue;
 			}
-			if (r_type == R_386_PC32) {
-				/* PC relative relocations don't need to be adjusted */
+			if (r_type == R_386_NONE || r_type == R_386_PC32) {
+				/*
+				 * NONE can be ignored and and PC relative
+				 * relocations don't need to be adjusted.
+				 */
 			}
 			else if (r_type == R_386_32) {
 				/* Visit relocations that need to be adjusted */
diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c
index 5054c2ddd1a..74b3d2ba84e 100644
--- a/arch/x86/boot/memory.c
+++ b/arch/x86/boot/memory.c
@@ -17,11 +17,6 @@
 
 #define SMAP	0x534d4150	/* ASCII "SMAP" */
 
-struct e820_ext_entry {
-	struct e820entry std;
-	u32 ext_flags;
-} __attribute__((packed));
-
 static int detect_memory_e820(void)
 {
 	int count = 0;
@@ -29,13 +24,21 @@ static int detect_memory_e820(void)
 	u32 size, id, edi;
 	u8 err;
 	struct e820entry *desc = boot_params.e820_map;
-	static struct e820_ext_entry buf; /* static so it is zeroed */
+	static struct e820entry buf; /* static so it is zeroed */
 
 	/*
-	 * Set this here so that if the BIOS doesn't change this field
-	 * but still doesn't change %ecx, we're still okay...
+	 * Note: at least one BIOS is known which assumes that the
+	 * buffer pointed to by one e820 call is the same one as
+	 * the previous call, and only changes modified fields.  Therefore,
+	 * we use a temporary buffer and copy the results entry by entry.
+	 *
+	 * This routine deliberately does not try to account for
+	 * ACPI 3+ extended attributes.  This is because there are
+	 * BIOSes in the field which report zero for the valid bit for
+	 * all ranges, and we don't currently make any use of the
+	 * other attribute bits.  Revisit this if we see the extended
+	 * attribute bits deployed in a meaningful way in the future.
 	 */
-	buf.ext_flags = 1;
 
 	do {
 		size = sizeof buf;
@@ -66,13 +69,7 @@ static int detect_memory_e820(void)
 			break;
 		}
 
-		/* ACPI 3.0 added the extended flags support.  If bit 0
-		   in the extended flags is zero, we're supposed to simply
-		   ignore the entry -- a backwards incompatible change! */
-		if (size > 20 && !(buf.ext_flags & 1))
-			continue;
-
-		*desc++ = buf.std;
+		*desc++ = buf;
 		count++;
 	} while (next && count < ARRAY_SIZE(boot_params.e820_map));
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c1caefc82e6..77848d9fca6 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -114,6 +114,13 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
 } };
 EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
 
+static int __init x86_xsave_setup(char *s)
+{
+	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+	return 1;
+}
+__setup("noxsave", x86_xsave_setup);
+
 #ifdef CONFIG_X86_32
 static int cachesize_override __cpuinitdata = -1;
 static int disable_x86_serial_nr __cpuinitdata = 1;
diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
index 6ac55bd341a..86961519372 100644
--- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
+++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
@@ -168,6 +168,7 @@ static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c)
 		case 0x0E: /* Core */
 		case 0x0F: /* Core Duo */
 		case 0x16: /* Celeron Core */
+		case 0x1C: /* Atom */
 			p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS;
 			return speedstep_get_frequency(SPEEDSTEP_CPU_PCORE);
 		case 0x0D: /* Pentium M (Dothan) */
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
index 3c28ccd4974..a8363e5be4e 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c
@@ -168,10 +168,12 @@ static int check_powernow(void)
 	return 1;
 }
 
+#ifdef CONFIG_X86_POWERNOW_K7_ACPI
 static void invalidate_entry(unsigned int entry)
 {
 	powernow_table[entry].frequency = CPUFREQ_ENTRY_INVALID;
 }
+#endif
 
 static int get_ranges(unsigned char *pst)
 {
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 4709ead2db5..f6b32d11235 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -649,6 +649,20 @@ static void print_basics(struct powernow_k8_data *data)
 				data->batps);
 }
 
+static u32 freq_from_fid_did(u32 fid, u32 did)
+{
+	u32 mhz = 0;
+
+	if (boot_cpu_data.x86 == 0x10)
+		mhz = (100 * (fid + 0x10)) >> did;
+	else if (boot_cpu_data.x86 == 0x11)
+		mhz = (100 * (fid + 8)) >> did;
+	else
+		BUG();
+
+	return mhz * 1000;
+}
+
 static int fill_powernow_table(struct powernow_k8_data *data,
 		struct pst_s *pst, u8 maxvid)
 {
@@ -923,8 +937,13 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data,
 
 		powernow_table[i].index = index;
 
-		powernow_table[i].frequency =
-			data->acpi_data.states[i].core_frequency * 1000;
+		/* Frequency may be rounded for these */
+		if (boot_cpu_data.x86 == 0x10 || boot_cpu_data.x86 == 0x11) {
+			powernow_table[i].frequency =
+				freq_from_fid_did(lo & 0x3f, (lo >> 6) & 7);
+		} else
+			powernow_table[i].frequency =
+				data->acpi_data.states[i].core_frequency * 1000;
 	}
 	return 0;
 }
@@ -1215,13 +1234,16 @@ static int powernowk8_verify(struct cpufreq_policy *pol)
 	return cpufreq_frequency_table_verify(pol, data->powernow_table);
 }
 
+static const char ACPI_PSS_BIOS_BUG_MSG[] =
+	KERN_ERR FW_BUG PFX "No compatible ACPI _PSS objects found.\n"
+	KERN_ERR FW_BUG PFX "Try again with latest BIOS.\n";
+
 /* per CPU init entry point to the driver */
 static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 {
 	struct powernow_k8_data *data;
 	cpumask_t oldmask;
 	int rc;
-	static int print_once;
 
 	if (!cpu_online(pol->cpu))
 		return -ENODEV;
@@ -1244,19 +1266,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 		 * an UP version, and is deprecated by AMD.
 		 */
 		if (num_online_cpus() != 1) {
-			/*
-			 * Replace this one with print_once as soon as such a
-			 * thing gets introduced
-			 */
-			if (!print_once) {
-				WARN_ONCE(1, KERN_ERR FW_BUG PFX "Your BIOS "
-					"does not provide ACPI _PSS objects "
-					"in a way that Linux understands. "
-					"Please report this to the Linux ACPI"
-					" maintainers and complain to your "
-					"BIOS vendor.\n");
-				print_once++;
-			}
+			printk_once(ACPI_PSS_BIOS_BUG_MSG);
 			goto err_out;
 		}
 		if (pol->cpu != 0) {
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 1340dad417f..667188e0b5a 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -232,6 +232,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Dell DXP061"),
 		},
 	},
+	{	/* Handle problems with rebooting on Sony VGN-Z540N */
+		.callback = set_bios_reboot,
+		.ident = "Sony VGN-Z540N",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "VGN-Z540N"),
+		},
+	},
 	{ }
 };
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 3a97a4cf187..8f0e13be36b 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -160,8 +160,10 @@ static ssize_t __init setup_pcpu_remap(size_t static_size)
 	/*
 	 * If large page isn't supported, there's no benefit in doing
 	 * this.  Also, on non-NUMA, embedding is better.
+	 *
+	 * NOTE: disabled for now.
 	 */
-	if (!cpu_has_pse || !pcpu_need_numa())
+	if (true || !cpu_has_pse || !pcpu_need_numa())
 		return -EINVAL;
 
 	/*
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index b6caf1329b1..32cf11e5728 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2897,8 +2897,7 @@ static int kvm_pv_mmu_write(struct kvm_vcpu *vcpu,
 
 static int kvm_pv_mmu_flush_tlb(struct kvm_vcpu *vcpu)
 {
-	kvm_x86_ops->tlb_flush(vcpu);
-	set_bit(KVM_REQ_MMU_SYNC, &vcpu->requests);
+	kvm_set_cr3(vcpu, vcpu->arch.cr3);
 	return 1;
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 49079a46687..3944e917e79 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -338,6 +338,9 @@ EXPORT_SYMBOL_GPL(kvm_lmsw);
 
 void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
+	unsigned long old_cr4 = vcpu->arch.cr4;
+	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE;
+
 	if (cr4 & CR4_RESERVED_BITS) {
 		printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n");
 		kvm_inject_gp(vcpu, 0);
@@ -351,7 +354,8 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 			kvm_inject_gp(vcpu, 0);
 			return;
 		}
-	} else if (is_paging(vcpu) && !is_pae(vcpu) && (cr4 & X86_CR4_PAE)
+	} else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
+		   && ((cr4 ^ old_cr4) & pdptr_bits)
 		   && !load_pdptrs(vcpu, vcpu->arch.cr3)) {
 		printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n");
 		kvm_inject_gp(vcpu, 0);
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 797f9f107cb..e17efed088c 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -153,7 +153,7 @@ static void __cpa_flush_all(void *arg)
 	 */
 	__flush_tlb_all();
 
-	if (cache && boot_cpu_data.x86_model >= 4)
+	if (cache && boot_cpu_data.x86 >= 4)
 		wbinvd();
 }
 
@@ -208,20 +208,15 @@ static void cpa_flush_array(unsigned long *start, int numpages, int cache,
 			    int in_flags, struct page **pages)
 {
 	unsigned int i, level;
+	unsigned long do_wbinvd = cache && numpages >= 1024; /* 4M threshold */
 
 	BUG_ON(irqs_disabled());
 
-	on_each_cpu(__cpa_flush_range, NULL, 1);
+	on_each_cpu(__cpa_flush_all, (void *) do_wbinvd, 1);
 
-	if (!cache)
+	if (!cache || do_wbinvd)
 		return;
 
-	/* 4M threshold */
-	if (numpages >= 1024) {
-		if (boot_cpu_data.x86_model >= 4)
-			wbinvd();
-		return;
-	}
 	/*
 	 * We only need to flush on one CPU,
 	 * clflush is a MESI-coherent instruction that