VM: Rework vmalloc code to support mapping of arbitray pages

The vmalloc operation is split into two pieces:  allocate the backing
pages and map them into the kernel page tabels for virtually contingous
access. (Same for vfree).  A new set of interfaces, vmap & vunmap does
only the second part and thus allows mapping arbitray pages into 
kernel virtual memory.

The vmalloc.c internals have been completly overhauled to support this,
but the exported interfaces are unchanged.

arch/i386/mm/ioremap.c

@@ -159,7 +159,7 @@ void * __ioremap(unsigned long phys_addr, unsigned long size, unsigned long flag
 	area->phys_addr = phys_addr;
 	addr = area->addr;
 	if (remap_area_pages(VMALLOC_VMADDR(addr), phys_addr, size, flags)) {
-		vfree(addr);
+		vunmap(addr);
 		return NULL;
 	}
 	return (void *) (offset + (char *)addr);
@@ -215,13 +215,13 @@ void iounmap(void *addr)
 	struct vm_struct *p;
 	if (addr <= high_memory) 
 		return; 
-	p = remove_kernel_area((void *) (PAGE_MASK & (unsigned long) addr));
+	p = remove_vm_area((void *) (PAGE_MASK & (unsigned long) addr));
 	if (!p) { 
 		printk("__iounmap: bad address %p\n", addr);
 		return;
 	} 
 
-	vmfree_area_pages(VMALLOC_VMADDR(p->addr), p->size);	
+	unmap_vm_area(p);
 	if (p->flags && p->phys_addr < virt_to_phys(high_memory)) { 
 		change_page_attr(virt_to_page(__va(p->phys_addr)),
 				 p->size >> PAGE_SHIFT,

arch/sparc64/mm/modutil.c

@@ -4,6 +4,8 @@
  *  Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
  *  Based upon code written by Linus Torvalds and others.
  */
+
+#warning "major untested changes to this file  --hch (2002/08/05)"
  
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
@@ -16,6 +18,7 @@ static struct vm_struct * modvmlist = NULL;
 void module_unmap (void * addr)
 {
 	struct vm_struct **p, *tmp;
+	int i;
 
 	if (!addr)
 		return;
@@ -23,21 +26,38 @@ void module_unmap (void * addr)
 		printk("Trying to unmap module with bad address (%p)\n", addr);
 		return;
 	}
+
 	for (p = &modvmlist ; (tmp = *p) ; p = &tmp->next) {
 		if (tmp->addr == addr) {
 			*p = tmp->next;
-			vmfree_area_pages(VMALLOC_VMADDR(tmp->addr), tmp->size);
-			kfree(tmp);
-			return;
 		}
 	}
 	printk("Trying to unmap nonexistent module vm area (%p)\n", addr);
+	return;
+
+found:
+
+	unmap_vm_area(tmp);
+	
+	for (i = 0; i < tmp->nr_pages; i++) {
+		if (unlikely(!tmp->pages[i]))
+			BUG();
+		__free_page(tmp->pages[i]);
+	}
+
+	kfree(tmp->pages);
+	kfree(tmp);
 }
 
+
 void * module_map (unsigned long size)
 {
-	void * addr;
 	struct vm_struct **p, *tmp, *area;
+	struct vm_struct *area;
+	struct page **pages;
+	void * addr;
+	unsigned int nr_pages, array_size, i;
+
 
 	size = PAGE_ALIGN(size);
 	if (!size || size > MODULES_LEN) return NULL;
@@ -55,11 +75,32 @@ void * module_map (unsigned long size)
 	area->size = size + PAGE_SIZE;
 	area->addr = addr;
 	area->next = *p;
+	area->pages = NULL;
+	area->nr_pages = 0;
+	area->phys_addr = 0;
 	*p = area;
 
-	if (vmalloc_area_pages(VMALLOC_VMADDR(addr), size, GFP_KERNEL, PAGE_KERNEL)) {
-		module_unmap(addr);
+	nr_pages = (size+PAGE_SIZE) >> PAGE_SHIFT;
+	array_size = (nr_pages * sizeof(struct page *));
+
+	area->nr_pages = nr_pages;
+	area->pages = pages = kmalloc(array_size, (gfp_mask & ~__GFP_HIGHMEM));
+	if (!area->pages)
 		return NULL;
+	memset(area->pages, 0, array_size);
+
+	for (i = 0; i < area->nr_pages; i++) {
+		area->pages[i] = alloc_page(gfp_mask);
+		if (unlikely(!area->pages[i]))
+			goto fail;
 	}
-	return addr;
+	
+	if (map_vm_area(area, prot, &pages))
+		goto fail;
+	return area->addr;
+
+fail:
+	vfree(area->addr);
+	return NULL;
+}
 }

drivers/char/mem.c

@@ -210,6 +210,9 @@ static int mmap_mem(struct file * file, struct vm_area_struct * vma)
 	return 0;
 }
 
+extern long vread(char *buf, char *addr, unsigned long count);
+extern long vwrite(char *buf, char *addr, unsigned long count);
+
 /*
  * This function reads the *virtual* memory as seen by the kernel.
  */
@@ -273,8 +276,6 @@ static ssize_t read_kmem(struct file *file, char *buf,
  	return virtr + read;
 }
 
-extern long vwrite(char *buf, char *addr, unsigned long count);
-
 /*
  * This function writes to the *virtual* memory as seen by the kernel.
  */

include/linux/vmalloc.h

-#ifndef __LINUX_VMALLOC_H
-#define __LINUX_VMALLOC_H
+#ifndef _LINUX_VMALLOC_H
+#define _LINUX_VMALLOC_H
 
 #include <linux/spinlock.h>
 
-#include <asm/pgtable.h>
-
 /* bits in vm_struct->flags */
 #define VM_IOREMAP	0x00000001	/* ioremap() and friends */
 #define VM_ALLOC	0x00000002	/* vmalloc() */
+#define VM_MAP		0x00000004	/* vmap()ed pages */
 
 struct vm_struct {
-	unsigned long flags;
-	void * addr;
-	unsigned long size;
-	unsigned long phys_addr;
-	struct vm_struct * next;
+	void			*addr;
+	unsigned long		size;
+	unsigned long		flags;
+	struct page		**pages;
+	unsigned int		nr_pages;
+	unsigned long		phys_addr;
+	struct vm_struct	*next;
 };
 
-extern struct vm_struct * get_vm_area (unsigned long size, unsigned long flags);
-extern void vfree(void * addr);
-extern void * __vmalloc (unsigned long size, int gfp_mask, pgprot_t prot);
-extern long vread(char *buf, char *addr, unsigned long count);
-extern void vmfree_area_pages(unsigned long address, unsigned long size);
-extern int vmalloc_area_pages(unsigned long address, unsigned long size,
-                              int gfp_mask, pgprot_t prot);
-extern struct vm_struct *remove_kernel_area(void *addr);
-
 /*
- * Various ways to allocate pages.
+ *	Highlevel APIs for driver use
  */
-
-extern void * vmalloc(unsigned long size);
-extern void * vmalloc_32(unsigned long size);
+extern void *vmalloc(unsigned long size);
+extern void *vmalloc_32(unsigned long size);
+extern void *__vmalloc(unsigned long size, int gfp_mask, pgprot_t prot);
+extern void vfree(void *addr);
+
+extern void *vmap(struct page **pages, unsigned int count);
+extern void vunmap(void *addr);
+ 
+/*
+ *	Lowlevel-APIs (not for driver use!)
+ */
+extern struct vm_struct *get_vm_area(unsigned long size, unsigned long flags);
+extern struct vm_struct *remove_vm_area(void *addr);
+extern int map_vm_area(struct vm_struct *area, pgprot_t prot,
+			struct page ***pages);
+extern void unmap_vm_area(struct vm_struct *area);
 
 /*
- * vmlist_lock is a read-write spinlock that protects vmlist
- * Used in mm/vmalloc.c (get_vm_area() and vfree()) and fs/proc/kcore.c.
+ *	Internals.  Dont't use..
  */
 extern rwlock_t vmlist_lock;
+extern struct vm_struct *vmlist;
 
-extern struct vm_struct * vmlist;
-#endif
-
+#endif /* _LINUX_VMALLOC_H */

kernel/ksyms.c

@@ -109,6 +109,8 @@ EXPORT_SYMBOL(vfree);
 EXPORT_SYMBOL(__vmalloc);
 EXPORT_SYMBOL(vmalloc);
 EXPORT_SYMBOL(vmalloc_32);
+EXPORT_SYMBOL(vmap);
+EXPORT_SYMBOL(vunmap);
 EXPORT_SYMBOL(vmalloc_to_page);
 EXPORT_SYMBOL(mem_map);
 EXPORT_SYMBOL(remap_page_range);