9 files changed, 435 insertions, 14 deletions

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/fault.c b/arch/powerpc/mm/fault.c
index 76993941cac..5beffc8f481 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -29,6 +29,7 @@
 #include <linux/module.h>
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
+#include <linux/perf_counter.h>
 
 #include <asm/firmware.h>
 #include <asm/page.h>
@@ -170,6 +171,8 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 		die("Weird page fault", regs, SIGSEGV);
 	}
 
+	perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
+
 	/* When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
 	 * kernel and should generate an OOPS.  Unfortunately, in the case of an
@@ -309,6 +312,8 @@ good_area:
 	}
 	if (ret & VM_FAULT_MAJOR) {
 		current->maj_flt++;
+		perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
+				     regs, address);
 #ifdef CONFIG_PPC_SMLPAR
 		if (firmware_has_feature(FW_FEATURE_CMO)) {
 			preempt_disable();
@@ -316,8 +321,11 @@ good_area:
 			preempt_enable();
 		}
 #endif
-	} else
+	} else {
 		current->min_flt++;
+		perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
+				     regs, address);
+	}
 	up_read(&mm->mmap_sem);
 	return 0;
 
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.c b/arch/powerpc/mm/pgtable.c
index f5c6fd42265..ae1d67cc090 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -219,7 +219,8 @@ int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
 		entry = do_dcache_icache_coherency(entry);
 	changed = !pte_same(*(ptep), entry);
 	if (changed) {
-		assert_pte_locked(vma->vm_mm, address);
+		if (!(vma->vm_flags & VM_HUGETLB))
+			assert_pte_locked(vma->vm_mm, address);
 		__ptep_set_access_flags(ptep, entry);
 		flush_tlb_page_nohash(vma, address);
 	}
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/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index 89497fb0428..3b52c80e5e3 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -2,7 +2,7 @@
  * PowerPC64 SLB support.
  *
  * Copyright (C) 2004 David Gibson <dwg@au.ibm.com>, IBM
- * Based on earlier code writteh by:
+ * Based on earlier code written by:
  * Dave Engebretsen and Mike Corrigan {engebret|mikejc}@us.ibm.com
  *    Copyright (c) 2001 Dave Engebretsen
  * Copyright (C) 2002 Anton Blanchard <anton@au.ibm.com>, IBM