Merge branch 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:
  powerpc: Fix up dma_alloc_coherent() on platforms without cache coherency.
  powerpc: Minor cleanups of kernel virt address space definitions
  powerpc: Move dma-noncoherent.c from arch/powerpc/lib to arch/powerpc/mm
  Revert "powerpc: Rework dma-noncoherent to use generic vmalloc layer"

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

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)

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

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;
@@ -55,9 +55,31 @@ extern int icache_44x_need_flush;
 #define pgd_ERROR(e) \
 	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

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);

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

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

arch/powerpc/lib/dma-noncoherent.c → arch/powerpc/mm/dma-noncoherent.c

@@ -29,38 +29,166 @@
 #include <linux/types.h>
 #include <linux/highmem.h>
 #include <linux/dma-mapping.h>
-#include <linux/vmalloc.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(size_t size, dma_addr_t *handle, gfp_t gfp)
+__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;
-	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);
+	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) {
-		printk(KERN_WARNING "coherent allocation too big (requested "
-				"%#x mask %#Lx)\n", size, 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;
 
@@ -68,8 +196,6 @@ __dma_alloc_coherent(size_t size, dma_addr_t *handle, gfp_t gfp)
 	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.
@@ -80,59 +206,44 @@ __dma_alloc_coherent(size_t size, dma_addr_t *handle, gfp_t gfp)
 		flush_dcache_range(kaddr, kaddr + size);
 	}
 
-	split_page(page, order);
-
 	/*
-	 * Set the "dma handle"
+	 * Allocate a virtual address in the consistent mapping region.
 	 */
-	*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;
+	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);
 
-	area->pages = pages;
-	area->nr_pages = nr_pages;
+		split_page(page, order);
 
-	for (i = 0; i < nr_pages; i++)
-		pages[i] = page + i;
+		/*
+		 * Set the "dma handle"
+		 */
+		*handle = page_to_phys(page);
 
-	if (map_vm_area(area, pgprot_noncached(PAGE_KERNEL), &pages))
-		goto out_unmap;
+		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.
-	 */
-	page += nr_pages;
-	while (page < end) {
-		__free_page(page);
-		page++;
+		/*
+		 * Free the otherwise unused pages.
+		 */
+		while (page < end) {
+			__free_page(page);
+			page++;
+		}
+
+		return (void *)c->vm_start;
 	}
 
-	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:
+ no_page:
 	return NULL;
 }
 EXPORT_SYMBOL(__dma_alloc_coherent);
@@ -142,8 +253,60 @@ EXPORT_SYMBOL(__dma_alloc_coherent);
  */
 void __dma_free_coherent(size_t size, void *vaddr)
 {
-	vfree(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);
 

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)

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;
 }
 

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)
 {