*
* See Documentation/nommu-mmap.txt
*
- * Copyright (c) 2004-2005 David Howells <dhowells@redhat.com>
+ * Copyright (c) 2004-2008 David Howells <dhowells@redhat.com>
* Copyright (c) 2000-2003 David McCullough <davidm@snapgear.com>
* Copyright (c) 2000-2001 D Jeff Dionne <jeff@uClinux.org>
* Copyright (c) 2002 Greg Ungerer <gerg@snapgear.com>
+ * Copyright (c) 2007-2010 Paul Mundt <lethal@linux-sh.org>
*/
+#include <linux/module.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
-#include <linux/ptrace.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/mount.h>
#include <linux/personality.h>
#include <linux/security.h>
#include <linux/syscalls.h>
+#include <linux/audit.h>
#include <asm/uaccess.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
+#include <asm/mmu_context.h>
+#include "internal.h"
+
+#if 0
+#define kenter(FMT, ...) \
+ printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__)
+#define kleave(FMT, ...) \
+ printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__)
+#define kdebug(FMT, ...) \
+ printk(KERN_DEBUG "xxx" FMT"yyy\n", ##__VA_ARGS__)
+#else
+#define kenter(FMT, ...) \
+ no_printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__)
+#define kleave(FMT, ...) \
+ no_printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__)
+#define kdebug(FMT, ...) \
+ no_printk(KERN_DEBUG FMT"\n", ##__VA_ARGS__)
+#endif
void *high_memory;
struct page *mem_map;
unsigned long max_mapnr;
unsigned long num_physpages;
-unsigned long askedalloc, realalloc;
-atomic_t vm_committed_space = ATOMIC_INIT(0);
+unsigned long highest_memmap_pfn;
+struct percpu_counter vm_committed_as;
int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */
int sysctl_overcommit_ratio = 50; /* default is 50% */
int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
+int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS;
int heap_stack_gap = 0;
+atomic_long_t mmap_pages_allocated;
+
EXPORT_SYMBOL(mem_map);
EXPORT_SYMBOL(num_physpages);
-/* list of shareable VMAs */
-struct rb_root nommu_vma_tree = RB_ROOT;
-DECLARE_RWSEM(nommu_vma_sem);
+/* list of mapped, potentially shareable regions */
+static struct kmem_cache *vm_region_jar;
+struct rb_root nommu_region_tree = RB_ROOT;
+DECLARE_RWSEM(nommu_region_sem);
-struct vm_operations_struct generic_file_vm_ops = {
+const struct vm_operations_struct generic_file_vm_ops = {
};
-/*
- * Handle all mappings that got truncated by a "truncate()"
- * system call.
- *
- * NOTE! We have to be ready to update the memory sharing
- * between the file and the memory map for a potential last
- * incomplete page. Ugly, but necessary.
- */
-int vmtruncate(struct inode *inode, loff_t offset)
-{
- struct address_space *mapping = inode->i_mapping;
- unsigned long limit;
-
- if (inode->i_size < offset)
- goto do_expand;
- i_size_write(inode, offset);
-
- truncate_inode_pages(mapping, offset);
- goto out_truncate;
-
-do_expand:
- limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
- if (limit != RLIM_INFINITY && offset > limit)
- goto out_sig;
- if (offset > inode->i_sb->s_maxbytes)
- goto out;
- i_size_write(inode, offset);
-
-out_truncate:
- if (inode->i_op && inode->i_op->truncate)
- inode->i_op->truncate(inode);
- return 0;
-out_sig:
- send_sig(SIGXFSZ, current, 0);
-out:
- return -EFBIG;
-}
-
-EXPORT_SYMBOL(vmtruncate);
-
/*
* Return the total memory allocated for this pointer, not
* just what the caller asked for.
{
struct page *page;
- if (!objp || !((page = virt_to_page(objp))))
+ /*
+ * If the object we have should not have ksize performed on it,
+ * return size of 0
+ */
+ if (!objp || !virt_addr_valid(objp))
return 0;
+ page = virt_to_head_page(objp);
+
+ /*
+ * If the allocator sets PageSlab, we know the pointer came from
+ * kmalloc().
+ */
if (PageSlab(page))
return ksize(objp);
- BUG_ON(page->index < 0);
- BUG_ON(page->index >= MAX_ORDER);
+ /*
+ * If it's not a compound page, see if we have a matching VMA
+ * region. This test is intentionally done in reverse order,
+ * so if there's no VMA, we still fall through and hand back
+ * PAGE_SIZE for 0-order pages.
+ */
+ if (!PageCompound(page)) {
+ struct vm_area_struct *vma;
+
+ vma = find_vma(current->mm, (unsigned long)objp);
+ if (vma)
+ return vma->vm_end - vma->vm_start;
+ }
- return (PAGE_SIZE << page->index);
+ /*
+ * The ksize() function is only guaranteed to work for pointers
+ * returned by kmalloc(). So handle arbitrary pointers here.
+ */
+ return PAGE_SIZE << compound_order(page);
}
-/*
- * get a list of pages in an address range belonging to the specified process
- * and indicate the VMA that covers each page
- * - this is potentially dodgy as we may end incrementing the page count of a
- * slab page or a secondary page from a compound page
- * - don't permit access to VMAs that don't support it, such as I/O mappings
- */
-int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
- unsigned long start, int len, int write, int force,
- struct page **pages, struct vm_area_struct **vmas)
+int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long start, int nr_pages, unsigned int foll_flags,
+ struct page **pages, struct vm_area_struct **vmas,
+ int *retry)
{
struct vm_area_struct *vma;
unsigned long vm_flags;
int i;
/* calculate required read or write permissions.
- * - if 'force' is set, we only require the "MAY" flags.
+ * If FOLL_FORCE is set, we only require the "MAY" flags.
*/
- vm_flags = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
- vm_flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
+ vm_flags = (foll_flags & FOLL_WRITE) ?
+ (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
+ vm_flags &= (foll_flags & FOLL_FORCE) ?
+ (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
- for (i = 0; i < len; i++) {
+ for (i = 0; i < nr_pages; i++) {
vma = find_vma(mm, start);
if (!vma)
goto finish_or_fault;
/* protect what we can, including chardevs */
- if (vma->vm_flags & (VM_IO | VM_PFNMAP) ||
+ if ((vma->vm_flags & (VM_IO | VM_PFNMAP)) ||
!(vm_flags & vma->vm_flags))
goto finish_or_fault;
}
if (vmas)
vmas[i] = vma;
- start += PAGE_SIZE;
+ start = (start + PAGE_SIZE) & PAGE_MASK;
}
return i;
finish_or_fault:
return i ? : -EFAULT;
}
+
+/*
+ * get a list of pages in an address range belonging to the specified process
+ * and indicate the VMA that covers each page
+ * - this is potentially dodgy as we may end incrementing the page count of a
+ * slab page or a secondary page from a compound page
+ * - don't permit access to VMAs that don't support it, such as I/O mappings
+ */
+int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long start, int nr_pages, int write, int force,
+ struct page **pages, struct vm_area_struct **vmas)
+{
+ int flags = 0;
+
+ if (write)
+ flags |= FOLL_WRITE;
+ if (force)
+ flags |= FOLL_FORCE;
+
+ return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas,
+ NULL);
+}
EXPORT_SYMBOL(get_user_pages);
+/**
+ * follow_pfn - look up PFN at a user virtual address
+ * @vma: memory mapping
+ * @address: user virtual address
+ * @pfn: location to store found PFN
+ *
+ * Only IO mappings and raw PFN mappings are allowed.
+ *
+ * Returns zero and the pfn at @pfn on success, -ve otherwise.
+ */
+int follow_pfn(struct vm_area_struct *vma, unsigned long address,
+ unsigned long *pfn)
+{
+ if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
+ return -EINVAL;
+
+ *pfn = address >> PAGE_SHIFT;
+ return 0;
+}
+EXPORT_SYMBOL(follow_pfn);
+
DEFINE_RWLOCK(vmlist_lock);
struct vm_struct *vmlist;
-void vfree(void *addr)
+void vfree(const void *addr)
{
kfree(addr);
}
void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
{
/*
- * kmalloc doesn't like __GFP_HIGHMEM for some reason
+ * You can't specify __GFP_HIGHMEM with kmalloc() since kmalloc()
+ * returns only a logical address.
*/
return kmalloc(size, (gfp_mask | __GFP_COMP) & ~__GFP_HIGHMEM);
}
EXPORT_SYMBOL(__vmalloc);
-struct page * vmalloc_to_page(void *addr)
+void *vmalloc_user(unsigned long size)
+{
+ void *ret;
+
+ ret = __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
+ PAGE_KERNEL);
+ if (ret) {
+ struct vm_area_struct *vma;
+
+ down_write(¤t->mm->mmap_sem);
+ vma = find_vma(current->mm, (unsigned long)ret);
+ if (vma)
+ vma->vm_flags |= VM_USERMAP;
+ up_write(¤t->mm->mmap_sem);
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL(vmalloc_user);
+
+struct page *vmalloc_to_page(const void *addr)
{
return virt_to_page(addr);
}
EXPORT_SYMBOL(vmalloc_to_page);
-unsigned long vmalloc_to_pfn(void *addr)
+unsigned long vmalloc_to_pfn(const void *addr)
{
return page_to_pfn(virt_to_page(addr));
}
}
EXPORT_SYMBOL(vmalloc);
+/*
+ * vzalloc - allocate virtually continguos memory with zero fill
+ *
+ * @size: allocation size
+ *
+ * Allocate enough pages to cover @size from the page level
+ * allocator and map them into continguos kernel virtual space.
+ * The memory allocated is set to zero.
+ *
+ * For tight control over page level allocator and protection flags
+ * use __vmalloc() instead.
+ */
+void *vzalloc(unsigned long size)
+{
+ return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
+ PAGE_KERNEL);
+}
+EXPORT_SYMBOL(vzalloc);
+
+/**
+ * vmalloc_node - allocate memory on a specific node
+ * @size: allocation size
+ * @node: numa node
+ *
+ * Allocate enough pages to cover @size from the page level
+ * allocator and map them into contiguous kernel virtual space.
+ *
+ * For tight control over page level allocator and protection flags
+ * use __vmalloc() instead.
+ */
void *vmalloc_node(unsigned long size, int node)
{
return vmalloc(size);
}
EXPORT_SYMBOL(vmalloc_node);
+/**
+ * vzalloc_node - allocate memory on a specific node with zero fill
+ * @size: allocation size
+ * @node: numa node
+ *
+ * Allocate enough pages to cover @size from the page level
+ * allocator and map them into contiguous kernel virtual space.
+ * The memory allocated is set to zero.
+ *
+ * For tight control over page level allocator and protection flags
+ * use __vmalloc() instead.
+ */
+void *vzalloc_node(unsigned long size, int node)
+{
+ return vzalloc(size);
+}
+EXPORT_SYMBOL(vzalloc_node);
+
+#ifndef PAGE_KERNEL_EXEC
+# define PAGE_KERNEL_EXEC PAGE_KERNEL
+#endif
+
+/**
+ * vmalloc_exec - allocate virtually contiguous, executable memory
+ * @size: allocation size
+ *
+ * Kernel-internal function to allocate enough pages to cover @size
+ * the page level allocator and map them into contiguous and
+ * executable kernel virtual space.
+ *
+ * For tight control over page level allocator and protection flags
+ * use __vmalloc() instead.
+ */
+
+void *vmalloc_exec(unsigned long size)
+{
+ return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC);
+}
+
/**
* vmalloc_32 - allocate virtually contiguous memory (32bit addressable)
* @size: allocation size
*
* The resulting memory area is 32bit addressable and zeroed so it can be
* mapped to userspace without leaking data.
+ *
+ * VM_USERMAP is set on the corresponding VMA so that subsequent calls to
+ * remap_vmalloc_range() are permissible.
*/
void *vmalloc_32_user(unsigned long size)
{
- return __vmalloc(size, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL);
+ /*
+ * We'll have to sort out the ZONE_DMA bits for 64-bit,
+ * but for now this can simply use vmalloc_user() directly.
+ */
+ return vmalloc_user(size);
}
EXPORT_SYMBOL(vmalloc_32_user);
}
EXPORT_SYMBOL(vmap);
-void vunmap(void *addr)
+void vunmap(const void *addr)
{
BUG();
}
EXPORT_SYMBOL(vunmap);
+void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prot)
+{
+ BUG();
+ return NULL;
+}
+EXPORT_SYMBOL(vm_map_ram);
+
+void vm_unmap_ram(const void *mem, unsigned int count)
+{
+ BUG();
+}
+EXPORT_SYMBOL(vm_unmap_ram);
+
+void vm_unmap_aliases(void)
+{
+}
+EXPORT_SYMBOL_GPL(vm_unmap_aliases);
+
/*
* Implement a stub for vmalloc_sync_all() if the architecture chose not to
* have one.
{
}
+/**
+ * alloc_vm_area - allocate a range of kernel address space
+ * @size: size of the area
+ *
+ * Returns: NULL on failure, vm_struct on success
+ *
+ * This function reserves a range of kernel address space, and
+ * allocates pagetables to map that range. No actual mappings
+ * are created. If the kernel address space is not shared
+ * between processes, it syncs the pagetable across all
+ * processes.
+ */
+struct vm_struct *alloc_vm_area(size_t size)
+{
+ BUG();
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(alloc_vm_area);
+
+void free_vm_area(struct vm_struct *area)
+{
+ BUG();
+}
+EXPORT_SYMBOL_GPL(free_vm_area);
+
int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
struct page *page)
{
* to a regular file. in this case, the unmapping will need
* to invoke file system routines that need the global lock.
*/
-asmlinkage unsigned long sys_brk(unsigned long brk)
+SYSCALL_DEFINE1(brk, unsigned long, brk)
{
struct mm_struct *mm = current->mm;
/*
* Ok, looks good - let it rip.
*/
+ flush_icache_range(mm->brk, brk);
return mm->brk = brk;
}
-#ifdef DEBUG
-static void show_process_blocks(void)
+/*
+ * initialise the VMA and region record slabs
+ */
+void __init mmap_init(void)
{
- struct vm_list_struct *vml;
-
- printk("Process blocks %d:", current->pid);
+ int ret;
- for (vml = ¤t->mm->context.vmlist; vml; vml = vml->next) {
- printk(" %p: %p", vml, vml->vma);
- if (vml->vma)
- printk(" (%d @%lx #%d)",
- kobjsize((void *) vml->vma->vm_start),
- vml->vma->vm_start,
- atomic_read(&vml->vma->vm_usage));
- printk(vml->next ? " ->" : ".\n");
- }
+ ret = percpu_counter_init(&vm_committed_as, 0);
+ VM_BUG_ON(ret);
+ vm_region_jar = KMEM_CACHE(vm_region, SLAB_PANIC);
}
-#endif /* DEBUG */
/*
- * add a VMA into a process's mm_struct in the appropriate place in the list
- * - should be called with mm->mmap_sem held writelocked
+ * validate the region tree
+ * - the caller must hold the region lock
*/
-static void add_vma_to_mm(struct mm_struct *mm, struct vm_list_struct *vml)
+#ifdef CONFIG_DEBUG_NOMMU_REGIONS
+static noinline void validate_nommu_regions(void)
{
- struct vm_list_struct **ppv;
+ struct vm_region *region, *last;
+ struct rb_node *p, *lastp;
+
+ lastp = rb_first(&nommu_region_tree);
+ if (!lastp)
+ return;
- for (ppv = ¤t->mm->context.vmlist; *ppv; ppv = &(*ppv)->next)
- if ((*ppv)->vma->vm_start > vml->vma->vm_start)
- break;
+ last = rb_entry(lastp, struct vm_region, vm_rb);
+ BUG_ON(unlikely(last->vm_end <= last->vm_start));
+ BUG_ON(unlikely(last->vm_top < last->vm_end));
- vml->next = *ppv;
- *ppv = vml;
+ while ((p = rb_next(lastp))) {
+ region = rb_entry(p, struct vm_region, vm_rb);
+ last = rb_entry(lastp, struct vm_region, vm_rb);
+
+ BUG_ON(unlikely(region->vm_end <= region->vm_start));
+ BUG_ON(unlikely(region->vm_top < region->vm_end));
+ BUG_ON(unlikely(region->vm_start < last->vm_top));
+
+ lastp = p;
+ }
+}
+#else
+static void validate_nommu_regions(void)
+{
}
+#endif
/*
- * look up the first VMA in which addr resides, NULL if none
- * - should be called with mm->mmap_sem at least held readlocked
+ * add a region into the global tree
*/
-struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
+static void add_nommu_region(struct vm_region *region)
{
- struct vm_list_struct *loop, *vml;
+ struct vm_region *pregion;
+ struct rb_node **p, *parent;
+
+ validate_nommu_regions();
- /* search the vm_start ordered list */
- vml = NULL;
- for (loop = mm->context.vmlist; loop; loop = loop->next) {
- if (loop->vma->vm_start > addr)
- break;
- vml = loop;
+ parent = NULL;
+ p = &nommu_region_tree.rb_node;
+ while (*p) {
+ parent = *p;
+ pregion = rb_entry(parent, struct vm_region, vm_rb);
+ if (region->vm_start < pregion->vm_start)
+ p = &(*p)->rb_left;
+ else if (region->vm_start > pregion->vm_start)
+ p = &(*p)->rb_right;
+ else if (pregion == region)
+ return;
+ else
+ BUG();
}
- if (vml && vml->vma->vm_end > addr)
- return vml->vma;
+ rb_link_node(®ion->vm_rb, parent, p);
+ rb_insert_color(®ion->vm_rb, &nommu_region_tree);
- return NULL;
+ validate_nommu_regions();
}
-EXPORT_SYMBOL(find_vma);
/*
- * find a VMA
- * - we don't extend stack VMAs under NOMMU conditions
+ * delete a region from the global tree
*/
-struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr)
+static void delete_nommu_region(struct vm_region *region)
{
- return find_vma(mm, addr);
+ BUG_ON(!nommu_region_tree.rb_node);
+
+ validate_nommu_regions();
+ rb_erase(®ion->vm_rb, &nommu_region_tree);
+ validate_nommu_regions();
}
-int expand_stack(struct vm_area_struct *vma, unsigned long address)
+/*
+ * free a contiguous series of pages
+ */
+static void free_page_series(unsigned long from, unsigned long to)
{
- return -ENOMEM;
+ for (; from < to; from += PAGE_SIZE) {
+ struct page *page = virt_to_page(from);
+
+ kdebug("- free %lx", from);
+ atomic_long_dec(&mmap_pages_allocated);
+ if (page_count(page) != 1)
+ kdebug("free page %p: refcount not one: %d",
+ page, page_count(page));
+ put_page(page);
+ }
}
/*
- * look up the first VMA exactly that exactly matches addr
- * - should be called with mm->mmap_sem at least held readlocked
+ * release a reference to a region
+ * - the caller must hold the region semaphore for writing, which this releases
+ * - the region may not have been added to the tree yet, in which case vm_top
+ * will equal vm_start
*/
-static inline struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
- unsigned long addr)
+static void __put_nommu_region(struct vm_region *region)
+ __releases(nommu_region_sem)
{
- struct vm_list_struct *vml;
+ kenter("%p{%d}", region, region->vm_usage);
- /* search the vm_start ordered list */
- for (vml = mm->context.vmlist; vml; vml = vml->next) {
- if (vml->vma->vm_start == addr)
- return vml->vma;
- if (vml->vma->vm_start > addr)
- break;
- }
+ BUG_ON(!nommu_region_tree.rb_node);
- return NULL;
+ if (--region->vm_usage == 0) {
+ if (region->vm_top > region->vm_start)
+ delete_nommu_region(region);
+ up_write(&nommu_region_sem);
+
+ if (region->vm_file)
+ fput(region->vm_file);
+
+ /* IO memory and memory shared directly out of the pagecache
+ * from ramfs/tmpfs mustn't be released here */
+ if (region->vm_flags & VM_MAPPED_COPY) {
+ kdebug("free series");
+ free_page_series(region->vm_start, region->vm_top);
+ }
+ kmem_cache_free(vm_region_jar, region);
+ } else {
+ up_write(&nommu_region_sem);
+ }
}
/*
- * find a VMA in the global tree
+ * release a reference to a region
*/
-static inline struct vm_area_struct *find_nommu_vma(unsigned long start)
+static void put_nommu_region(struct vm_region *region)
{
- struct vm_area_struct *vma;
- struct rb_node *n = nommu_vma_tree.rb_node;
-
- while (n) {
- vma = rb_entry(n, struct vm_area_struct, vm_rb);
+ down_write(&nommu_region_sem);
+ __put_nommu_region(region);
+}
- if (start < vma->vm_start)
- n = n->rb_left;
- else if (start > vma->vm_start)
- n = n->rb_right;
- else
- return vma;
+/*
+ * update protection on a vma
+ */
+static void protect_vma(struct vm_area_struct *vma, unsigned long flags)
+{
+#ifdef CONFIG_MPU
+ struct mm_struct *mm = vma->vm_mm;
+ long start = vma->vm_start & PAGE_MASK;
+ while (start < vma->vm_end) {
+ protect_page(mm, start, flags);
+ start += PAGE_SIZE;
}
-
- return NULL;
+ update_protections(mm);
+#endif
}
/*
- * add a VMA in the global tree
+ * add a VMA into a process's mm_struct in the appropriate place in the list
+ * and tree and add to the address space's page tree also if not an anonymous
+ * page
+ * - should be called with mm->mmap_sem held writelocked
*/
-static void add_nommu_vma(struct vm_area_struct *vma)
+static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
{
- struct vm_area_struct *pvma;
+ struct vm_area_struct *pvma, *prev;
struct address_space *mapping;
- struct rb_node **p = &nommu_vma_tree.rb_node;
- struct rb_node *parent = NULL;
+ struct rb_node **p, *parent, *rb_prev;
+
+ kenter(",%p", vma);
+
+ BUG_ON(!vma->vm_region);
+
+ mm->map_count++;
+ vma->vm_mm = mm;
+
+ protect_vma(vma, vma->vm_flags);
/* add the VMA to the mapping */
if (vma->vm_file) {
flush_dcache_mmap_unlock(mapping);
}
- /* add the VMA to the master list */
+ /* add the VMA to the tree */
+ parent = rb_prev = NULL;
+ p = &mm->mm_rb.rb_node;
while (*p) {
parent = *p;
pvma = rb_entry(parent, struct vm_area_struct, vm_rb);
- if (vma->vm_start < pvma->vm_start) {
+ /* sort by: start addr, end addr, VMA struct addr in that order
+ * (the latter is necessary as we may get identical VMAs) */
+ if (vma->vm_start < pvma->vm_start)
p = &(*p)->rb_left;
- }
else if (vma->vm_start > pvma->vm_start) {
+ rb_prev = parent;
p = &(*p)->rb_right;
- }
- else {
- /* mappings are at the same address - this can only
- * happen for shared-mem chardevs and shared file
- * mappings backed by ramfs/tmpfs */
- BUG_ON(!(pvma->vm_flags & VM_SHARED));
-
- if (vma < pvma)
- p = &(*p)->rb_left;
- else if (vma > pvma)
- p = &(*p)->rb_right;
- else
- BUG();
- }
+ } else if (vma->vm_end < pvma->vm_end)
+ p = &(*p)->rb_left;
+ else if (vma->vm_end > pvma->vm_end) {
+ rb_prev = parent;
+ p = &(*p)->rb_right;
+ } else if (vma < pvma)
+ p = &(*p)->rb_left;
+ else if (vma > pvma) {
+ rb_prev = parent;
+ p = &(*p)->rb_right;
+ } else
+ BUG();
}
rb_link_node(&vma->vm_rb, parent, p);
- rb_insert_color(&vma->vm_rb, &nommu_vma_tree);
+ rb_insert_color(&vma->vm_rb, &mm->mm_rb);
+
+ /* add VMA to the VMA list also */
+ prev = NULL;
+ if (rb_prev)
+ prev = rb_entry(rb_prev, struct vm_area_struct, vm_rb);
+
+ __vma_link_list(mm, vma, prev, parent);
}
/*
- * delete a VMA from the global list
+ * delete a VMA from its owning mm_struct and address space
*/
-static void delete_nommu_vma(struct vm_area_struct *vma)
+static void delete_vma_from_mm(struct vm_area_struct *vma)
{
struct address_space *mapping;
+ struct mm_struct *mm = vma->vm_mm;
+
+ kenter("%p", vma);
+
+ protect_vma(vma, 0);
+
+ mm->map_count--;
+ if (mm->mmap_cache == vma)
+ mm->mmap_cache = NULL;
/* remove the VMA from the mapping */
if (vma->vm_file) {
flush_dcache_mmap_unlock(mapping);
}
- /* remove from the master list */
- rb_erase(&vma->vm_rb, &nommu_vma_tree);
+ /* remove from the MM's tree and list */
+ rb_erase(&vma->vm_rb, &mm->mm_rb);
+
+ if (vma->vm_prev)
+ vma->vm_prev->vm_next = vma->vm_next;
+ else
+ mm->mmap = vma->vm_next;
+
+ if (vma->vm_next)
+ vma->vm_next->vm_prev = vma->vm_prev;
+
+ vma->vm_mm = NULL;
+}
+
+/*
+ * destroy a VMA record
+ */
+static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma)
+{
+ kenter("%p", vma);
+ if (vma->vm_ops && vma->vm_ops->close)
+ vma->vm_ops->close(vma);
+ if (vma->vm_file) {
+ fput(vma->vm_file);
+ if (vma->vm_flags & VM_EXECUTABLE)
+ removed_exe_file_vma(mm);
+ }
+ put_nommu_region(vma->vm_region);
+ kmem_cache_free(vm_area_cachep, vma);
+}
+
+/*
+ * look up the first VMA in which addr resides, NULL if none
+ * - should be called with mm->mmap_sem at least held readlocked
+ */
+struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
+{
+ struct vm_area_struct *vma;
+
+ /* check the cache first */
+ vma = mm->mmap_cache;
+ if (vma && vma->vm_start <= addr && vma->vm_end > addr)
+ return vma;
+
+ /* trawl the list (there may be multiple mappings in which addr
+ * resides) */
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ if (vma->vm_start > addr)
+ return NULL;
+ if (vma->vm_end > addr) {
+ mm->mmap_cache = vma;
+ return vma;
+ }
+ }
+
+ return NULL;
+}
+EXPORT_SYMBOL(find_vma);
+
+/*
+ * find a VMA
+ * - we don't extend stack VMAs under NOMMU conditions
+ */
+struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr)
+{
+ return find_vma(mm, addr);
+}
+
+/*
+ * expand a stack to a given address
+ * - not supported under NOMMU conditions
+ */
+int expand_stack(struct vm_area_struct *vma, unsigned long address)
+{
+ return -ENOMEM;
+}
+
+/*
+ * look up the first VMA exactly that exactly matches addr
+ * - should be called with mm->mmap_sem at least held readlocked
+ */
+static struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
+ unsigned long addr,
+ unsigned long len)
+{
+ struct vm_area_struct *vma;
+ unsigned long end = addr + len;
+
+ /* check the cache first */
+ vma = mm->mmap_cache;
+ if (vma && vma->vm_start == addr && vma->vm_end == end)
+ return vma;
+
+ /* trawl the list (there may be multiple mappings in which addr
+ * resides) */
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ if (vma->vm_start < addr)
+ continue;
+ if (vma->vm_start > addr)
+ return NULL;
+ if (vma->vm_end == end) {
+ mm->mmap_cache = vma;
+ return vma;
+ }
+ }
+
+ return NULL;
}
/*
unsigned long pgoff,
unsigned long *_capabilities)
{
- unsigned long capabilities;
+ unsigned long capabilities, rlen;
unsigned long reqprot = prot;
int ret;
/* do the simple checks first */
- if (flags & MAP_FIXED || addr) {
+ if (flags & MAP_FIXED) {
printk(KERN_DEBUG
"%d: Can't do fixed-address/overlay mmap of RAM\n",
current->pid);
return -EINVAL;
/* Careful about overflows.. */
- len = PAGE_ALIGN(len);
- if (!len || len > TASK_SIZE)
+ rlen = PAGE_ALIGN(len);
+ if (!rlen || rlen > TASK_SIZE)
return -ENOMEM;
/* offset overflow? */
- if ((pgoff + (len >> PAGE_SHIFT)) < pgoff)
+ if ((pgoff + (rlen >> PAGE_SHIFT)) < pgoff)
return -EOVERFLOW;
if (file) {
if (!file->f_op->read)
capabilities &= ~BDI_CAP_MAP_COPY;
+ /* The file shall have been opened with read permission. */
+ if (!(file->f_mode & FMODE_READ))
+ return -EACCES;
+
if (flags & MAP_SHARED) {
/* do checks for writing, appending and locking */
if ((prot & PROT_WRITE) &&
if (!(capabilities & BDI_CAP_MAP_DIRECT))
return -ENODEV;
- if (((prot & PROT_READ) && !(capabilities & BDI_CAP_READ_MAP)) ||
- ((prot & PROT_WRITE) && !(capabilities & BDI_CAP_WRITE_MAP)) ||
- ((prot & PROT_EXEC) && !(capabilities & BDI_CAP_EXEC_MAP))
- ) {
- printk("MAP_SHARED not completely supported on !MMU\n");
- return -EINVAL;
- }
-
/* we mustn't privatise shared mappings */
capabilities &= ~BDI_CAP_MAP_COPY;
}
capabilities &= ~BDI_CAP_MAP_DIRECT;
}
+ if (capabilities & BDI_CAP_MAP_DIRECT) {
+ if (((prot & PROT_READ) && !(capabilities & BDI_CAP_READ_MAP)) ||
+ ((prot & PROT_WRITE) && !(capabilities & BDI_CAP_WRITE_MAP)) ||
+ ((prot & PROT_EXEC) && !(capabilities & BDI_CAP_EXEC_MAP))
+ ) {
+ capabilities &= ~BDI_CAP_MAP_DIRECT;
+ if (flags & MAP_SHARED) {
+ printk(KERN_WARNING
+ "MAP_SHARED not completely supported on !MMU\n");
+ return -EINVAL;
+ }
+ }
+ }
+
/* handle executable mappings and implied executable
* mappings */
if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) {
unsigned long vm_flags;
vm_flags = calc_vm_prot_bits(prot) | calc_vm_flag_bits(flags);
- vm_flags |= VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
/* vm_flags |= mm->def_flags; */
if (!(capabilities & BDI_CAP_MAP_DIRECT)) {
/* attempt to share read-only copies of mapped file chunks */
+ vm_flags |= VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
if (file && !(prot & PROT_WRITE))
vm_flags |= VM_MAYSHARE;
- }
- else {
+ } else {
/* overlay a shareable mapping on the backing device or inode
* if possible - used for chardevs, ramfs/tmpfs/shmfs and
* romfs/cramfs */
+ vm_flags |= VM_MAYSHARE | (capabilities & BDI_CAP_VMFLAGS);
if (flags & MAP_SHARED)
- vm_flags |= VM_MAYSHARE | VM_SHARED;
- else if ((((vm_flags & capabilities) ^ vm_flags) & BDI_CAP_VMFLAGS) == 0)
- vm_flags |= VM_MAYSHARE;
+ vm_flags |= VM_SHARED;
}
/* refuse to let anyone share private mappings with this process if
* it's being traced - otherwise breakpoints set in it may interfere
* with another untraced process
*/
- if ((flags & MAP_PRIVATE) && (current->ptrace & PT_PTRACED))
+ if ((flags & MAP_PRIVATE) && current->ptrace)
vm_flags &= ~VM_MAYSHARE;
return vm_flags;
}
/*
- * set up a shared mapping on a file
+ * set up a shared mapping on a file (the driver or filesystem provides and
+ * pins the storage)
*/
-static int do_mmap_shared_file(struct vm_area_struct *vma, unsigned long len)
+static int do_mmap_shared_file(struct vm_area_struct *vma)
{
int ret;
ret = vma->vm_file->f_op->mmap(vma->vm_file, vma);
+ if (ret == 0) {
+ vma->vm_region->vm_top = vma->vm_region->vm_end;
+ return 0;
+ }
if (ret != -ENOSYS)
return ret;
- /* getting an ENOSYS error indicates that direct mmap isn't
- * possible (as opposed to tried but failed) so we'll fall
- * through to making a private copy of the data and mapping
- * that if we can */
+ /* getting -ENOSYS indicates that direct mmap isn't possible (as
+ * opposed to tried but failed) so we can only give a suitable error as
+ * it's not possible to make a private copy if MAP_SHARED was given */
return -ENODEV;
}
/*
* set up a private mapping or an anonymous shared mapping
*/
-static int do_mmap_private(struct vm_area_struct *vma, unsigned long len)
+static int do_mmap_private(struct vm_area_struct *vma,
+ struct vm_region *region,
+ unsigned long len,
+ unsigned long capabilities)
{
+ struct page *pages;
+ unsigned long total, point, n;
void *base;
- int ret;
+ int ret, order;
/* invoke the file's mapping function so that it can keep track of
* shared mappings on devices or memory
* - VM_MAYSHARE will be set if it may attempt to share
*/
- if (vma->vm_file) {
+ if (capabilities & BDI_CAP_MAP_DIRECT) {
ret = vma->vm_file->f_op->mmap(vma->vm_file, vma);
- if (ret != -ENOSYS) {
+ if (ret == 0) {
/* shouldn't return success if we're not sharing */
- BUG_ON(ret == 0 && !(vma->vm_flags & VM_MAYSHARE));
- return ret; /* success or a real error */
+ BUG_ON(!(vma->vm_flags & VM_MAYSHARE));
+ vma->vm_region->vm_top = vma->vm_region->vm_end;
+ return 0;
}
+ if (ret != -ENOSYS)
+ return ret;
/* getting an ENOSYS error indicates that direct mmap isn't
* possible (as opposed to tried but failed) so we'll try to
* make a private copy of the data and map that instead */
}
+
/* allocate some memory to hold the mapping
* - note that this may not return a page-aligned address if the object
* we're allocating is smaller than a page
*/
- base = kmalloc(len, GFP_KERNEL|__GFP_COMP);
- if (!base)
+ order = get_order(len);
+ kdebug("alloc order %d for %lx", order, len);
+
+ pages = alloc_pages(GFP_KERNEL, order);
+ if (!pages)
goto enomem;
- vma->vm_start = (unsigned long) base;
- vma->vm_end = vma->vm_start + len;
- vma->vm_flags |= VM_MAPPED_COPY;
+ total = 1 << order;
+ atomic_long_add(total, &mmap_pages_allocated);
+
+ point = len >> PAGE_SHIFT;
+
+ /* we allocated a power-of-2 sized page set, so we may want to trim off
+ * the excess */
+ if (sysctl_nr_trim_pages && total - point >= sysctl_nr_trim_pages) {
+ while (total > point) {
+ order = ilog2(total - point);
+ n = 1 << order;
+ kdebug("shave %lu/%lu @%lu", n, total - point, total);
+ atomic_long_sub(n, &mmap_pages_allocated);
+ total -= n;
+ set_page_refcounted(pages + total);
+ __free_pages(pages + total, order);
+ }
+ }
+
+ for (point = 1; point < total; point++)
+ set_page_refcounted(&pages[point]);
-#ifdef WARN_ON_SLACK
- if (len + WARN_ON_SLACK <= kobjsize(result))
- printk("Allocation of %lu bytes from process %d has %lu bytes of slack\n",
- len, current->pid, kobjsize(result) - len);
-#endif
+ base = page_address(pages);
+ region->vm_flags = vma->vm_flags |= VM_MAPPED_COPY;
+ region->vm_start = (unsigned long) base;
+ region->vm_end = region->vm_start + len;
+ region->vm_top = region->vm_start + (total << PAGE_SHIFT);
+
+ vma->vm_start = region->vm_start;
+ vma->vm_end = region->vm_start + len;
if (vma->vm_file) {
/* read the contents of a file into the copy */
if (ret < len)
memset(base + ret, 0, len - ret);
- } else {
- /* if it's an anonymous mapping, then just clear it */
- memset(base, 0, len);
}
return 0;
error_free:
- kfree(base);
- vma->vm_start = 0;
+ free_page_series(region->vm_start, region->vm_top);
+ region->vm_start = vma->vm_start = 0;
+ region->vm_end = vma->vm_end = 0;
+ region->vm_top = 0;
return ret;
enomem:
- printk("Allocation of length %lu from process %d failed\n",
- len, current->pid);
- show_free_areas();
+ printk("Allocation of length %lu from process %d (%s) failed\n",
+ len, current->pid, current->comm);
+ show_free_areas(0);
return -ENOMEM;
}
unsigned long flags,
unsigned long pgoff)
{
- struct vm_list_struct *vml = NULL;
- struct vm_area_struct *vma = NULL;
+ struct vm_area_struct *vma;
+ struct vm_region *region;
struct rb_node *rb;
- unsigned long capabilities, vm_flags;
- void *result;
+ unsigned long capabilities, vm_flags, result;
int ret;
+ kenter(",%lx,%lx,%lx,%lx,%lx", addr, len, prot, flags, pgoff);
+
/* decide whether we should attempt the mapping, and if so what sort of
* mapping */
ret = validate_mmap_request(file, addr, len, prot, flags, pgoff,
&capabilities);
- if (ret < 0)
+ if (ret < 0) {
+ kleave(" = %d [val]", ret);
return ret;
+ }
+
+ /* we ignore the address hint */
+ addr = 0;
+ len = PAGE_ALIGN(len);
/* we've determined that we can make the mapping, now translate what we
* now know into VMA flags */
vm_flags = determine_vm_flags(file, prot, flags, capabilities);
- /* we're going to need to record the mapping if it works */
- vml = kzalloc(sizeof(struct vm_list_struct), GFP_KERNEL);
- if (!vml)
- goto error_getting_vml;
+ /* we're going to need to record the mapping */
+ region = kmem_cache_zalloc(vm_region_jar, GFP_KERNEL);
+ if (!region)
+ goto error_getting_region;
+
+ vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+ if (!vma)
+ goto error_getting_vma;
+
+ region->vm_usage = 1;
+ region->vm_flags = vm_flags;
+ region->vm_pgoff = pgoff;
+
+ INIT_LIST_HEAD(&vma->anon_vma_chain);
+ vma->vm_flags = vm_flags;
+ vma->vm_pgoff = pgoff;
+
+ if (file) {
+ region->vm_file = file;
+ get_file(file);
+ vma->vm_file = file;
+ get_file(file);
+ if (vm_flags & VM_EXECUTABLE) {
+ added_exe_file_vma(current->mm);
+ vma->vm_mm = current->mm;
+ }
+ }
- down_write(&nommu_vma_sem);
+ down_write(&nommu_region_sem);
- /* if we want to share, we need to check for VMAs created by other
+ /* if we want to share, we need to check for regions created by other
* mmap() calls that overlap with our proposed mapping
- * - we can only share with an exact match on most regular files
+ * - we can only share with a superset match on most regular files
* - shared mappings on character devices and memory backed files are
* permitted to overlap inexactly as far as we are concerned for in
* these cases, sharing is handled in the driver or filesystem rather
* than here
*/
if (vm_flags & VM_MAYSHARE) {
- unsigned long pglen = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
- unsigned long vmpglen;
+ struct vm_region *pregion;
+ unsigned long pglen, rpglen, pgend, rpgend, start;
- /* suppress VMA sharing for shared regions */
- if (vm_flags & VM_SHARED &&
- capabilities & BDI_CAP_MAP_DIRECT)
- goto dont_share_VMAs;
+ pglen = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ pgend = pgoff + pglen;
- for (rb = rb_first(&nommu_vma_tree); rb; rb = rb_next(rb)) {
- vma = rb_entry(rb, struct vm_area_struct, vm_rb);
+ for (rb = rb_first(&nommu_region_tree); rb; rb = rb_next(rb)) {
+ pregion = rb_entry(rb, struct vm_region, vm_rb);
- if (!(vma->vm_flags & VM_MAYSHARE))
+ if (!(pregion->vm_flags & VM_MAYSHARE))
continue;
/* search for overlapping mappings on the same file */
- if (vma->vm_file->f_path.dentry->d_inode != file->f_path.dentry->d_inode)
+ if (pregion->vm_file->f_path.dentry->d_inode !=
+ file->f_path.dentry->d_inode)
continue;
- if (vma->vm_pgoff >= pgoff + pglen)
+ if (pregion->vm_pgoff >= pgend)
continue;
- vmpglen = vma->vm_end - vma->vm_start + PAGE_SIZE - 1;
- vmpglen >>= PAGE_SHIFT;
- if (pgoff >= vma->vm_pgoff + vmpglen)
+ rpglen = pregion->vm_end - pregion->vm_start;
+ rpglen = (rpglen + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ rpgend = pregion->vm_pgoff + rpglen;
+ if (pgoff >= rpgend)
continue;
- /* handle inexactly overlapping matches between mappings */
- if (vma->vm_pgoff != pgoff || vmpglen != pglen) {
+ /* handle inexactly overlapping matches between
+ * mappings */
+ if ((pregion->vm_pgoff != pgoff || rpglen != pglen) &&
+ !(pgoff >= pregion->vm_pgoff && pgend <= rpgend)) {
+ /* new mapping is not a subset of the region */
if (!(capabilities & BDI_CAP_MAP_DIRECT))
goto sharing_violation;
continue;
}
- /* we've found a VMA we can share */
- atomic_inc(&vma->vm_usage);
-
- vml->vma = vma;
- result = (void *) vma->vm_start;
- goto shared;
+ /* we've found a region we can share */
+ pregion->vm_usage++;
+ vma->vm_region = pregion;
+ start = pregion->vm_start;
+ start += (pgoff - pregion->vm_pgoff) << PAGE_SHIFT;
+ vma->vm_start = start;
+ vma->vm_end = start + len;
+
+ if (pregion->vm_flags & VM_MAPPED_COPY) {
+ kdebug("share copy");
+ vma->vm_flags |= VM_MAPPED_COPY;
+ } else {
+ kdebug("share mmap");
+ ret = do_mmap_shared_file(vma);
+ if (ret < 0) {
+ vma->vm_region = NULL;
+ vma->vm_start = 0;
+ vma->vm_end = 0;
+ pregion->vm_usage--;
+ pregion = NULL;
+ goto error_just_free;
+ }
+ }
+ fput(region->vm_file);
+ kmem_cache_free(vm_region_jar, region);
+ region = pregion;
+ result = start;
+ goto share;
}
- dont_share_VMAs:
- vma = NULL;
-
/* obtain the address at which to make a shared mapping
* - this is the hook for quasi-memory character devices to
* tell us the location of a shared mapping
*/
- if (file && file->f_op->get_unmapped_area) {
+ if (capabilities & BDI_CAP_MAP_DIRECT) {
addr = file->f_op->get_unmapped_area(file, addr, len,
pgoff, flags);
- if (IS_ERR((void *) addr)) {
+ if (IS_ERR_VALUE(addr)) {
ret = addr;
- if (ret != (unsigned long) -ENOSYS)
- goto error;
+ if (ret != -ENOSYS)
+ goto error_just_free;
/* the driver refused to tell us where to site
* the mapping so we'll have to attempt to copy
* it */
- ret = (unsigned long) -ENODEV;
+ ret = -ENODEV;
if (!(capabilities & BDI_CAP_MAP_COPY))
- goto error;
+ goto error_just_free;
capabilities &= ~BDI_CAP_MAP_DIRECT;
+ } else {
+ vma->vm_start = region->vm_start = addr;
+ vma->vm_end = region->vm_end = addr + len;
}
}
}
- /* we're going to need a VMA struct as well */
- vma = kzalloc(sizeof(struct vm_area_struct), GFP_KERNEL);
- if (!vma)
- goto error_getting_vma;
-
- INIT_LIST_HEAD(&vma->anon_vma_node);
- atomic_set(&vma->vm_usage, 1);
- if (file)
- get_file(file);
- vma->vm_file = file;
- vma->vm_flags = vm_flags;
- vma->vm_start = addr;
- vma->vm_end = addr + len;
- vma->vm_pgoff = pgoff;
-
- vml->vma = vma;
+ vma->vm_region = region;
- /* set up the mapping */
+ /* set up the mapping
+ * - the region is filled in if BDI_CAP_MAP_DIRECT is still set
+ */
if (file && vma->vm_flags & VM_SHARED)
- ret = do_mmap_shared_file(vma, len);
+ ret = do_mmap_shared_file(vma);
else
- ret = do_mmap_private(vma, len);
+ ret = do_mmap_private(vma, region, len, capabilities);
if (ret < 0)
- goto error;
-
- /* okay... we have a mapping; now we have to register it */
- result = (void *) vma->vm_start;
+ goto error_just_free;
+ add_nommu_region(region);
- if (vma->vm_flags & VM_MAPPED_COPY) {
- realalloc += kobjsize(result);
- askedalloc += len;
- }
+ /* clear anonymous mappings that don't ask for uninitialized data */
+ if (!vma->vm_file && !(flags & MAP_UNINITIALIZED))
+ memset((void *)region->vm_start, 0,
+ region->vm_end - region->vm_start);
- realalloc += kobjsize(vma);
- askedalloc += sizeof(*vma);
+ /* okay... we have a mapping; now we have to register it */
+ result = vma->vm_start;
current->mm->total_vm += len >> PAGE_SHIFT;
- add_nommu_vma(vma);
-
- shared:
- realalloc += kobjsize(vml);
- askedalloc += sizeof(*vml);
+share:
+ add_vma_to_mm(current->mm, vma);
- add_vma_to_mm(current->mm, vml);
-
- up_write(&nommu_vma_sem);
-
- if (prot & PROT_EXEC)
- flush_icache_range((unsigned long) result,
- (unsigned long) result + len);
+ /* we flush the region from the icache only when the first executable
+ * mapping of it is made */
+ if (vma->vm_flags & VM_EXEC && !region->vm_icache_flushed) {
+ flush_icache_range(region->vm_start, region->vm_end);
+ region->vm_icache_flushed = true;
+ }
-#ifdef DEBUG
- printk("do_mmap:\n");
- show_process_blocks();
-#endif
+ up_write(&nommu_region_sem);
- return (unsigned long) result;
+ kleave(" = %lx", result);
+ return result;
- error:
- up_write(&nommu_vma_sem);
- kfree(vml);
- if (vma) {
- if (vma->vm_file)
- fput(vma->vm_file);
- kfree(vma);
- }
+error_just_free:
+ up_write(&nommu_region_sem);
+error:
+ if (region->vm_file)
+ fput(region->vm_file);
+ kmem_cache_free(vm_region_jar, region);
+ if (vma->vm_file)
+ fput(vma->vm_file);
+ if (vma->vm_flags & VM_EXECUTABLE)
+ removed_exe_file_vma(vma->vm_mm);
+ kmem_cache_free(vm_area_cachep, vma);
+ kleave(" = %d", ret);
return ret;
- sharing_violation:
- up_write(&nommu_vma_sem);
- printk("Attempt to share mismatched mappings\n");
- kfree(vml);
- return -EINVAL;
+sharing_violation:
+ up_write(&nommu_region_sem);
+ printk(KERN_WARNING "Attempt to share mismatched mappings\n");
+ ret = -EINVAL;
+ goto error;
- error_getting_vma:
- up_write(&nommu_vma_sem);
- kfree(vml);
- printk("Allocation of vma for %lu byte allocation from process %d failed\n",
+error_getting_vma:
+ kmem_cache_free(vm_region_jar, region);
+ printk(KERN_WARNING "Allocation of vma for %lu byte allocation"
+ " from process %d failed\n",
len, current->pid);
- show_free_areas();
+ show_free_areas(0);
return -ENOMEM;
- error_getting_vml:
- printk("Allocation of vml for %lu byte allocation from process %d failed\n",
+error_getting_region:
+ printk(KERN_WARNING "Allocation of vm region for %lu byte allocation"
+ " from process %d failed\n",
len, current->pid);
- show_free_areas();
+ show_free_areas(0);
return -ENOMEM;
}
EXPORT_SYMBOL(do_mmap_pgoff);
+SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
+ unsigned long, prot, unsigned long, flags,
+ unsigned long, fd, unsigned long, pgoff)
+{
+ struct file *file = NULL;
+ unsigned long retval = -EBADF;
+
+ audit_mmap_fd(fd, flags);
+ if (!(flags & MAP_ANONYMOUS)) {
+ file = fget(fd);
+ if (!file)
+ goto out;
+ }
+
+ flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
+
+ down_write(¤t->mm->mmap_sem);
+ retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
+ up_write(¤t->mm->mmap_sem);
+
+ if (file)
+ fput(file);
+out:
+ return retval;
+}
+
+#ifdef __ARCH_WANT_SYS_OLD_MMAP
+struct mmap_arg_struct {
+ unsigned long addr;
+ unsigned long len;
+ unsigned long prot;
+ unsigned long flags;
+ unsigned long fd;
+ unsigned long offset;
+};
+
+SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
+{
+ struct mmap_arg_struct a;
+
+ if (copy_from_user(&a, arg, sizeof(a)))
+ return -EFAULT;
+ if (a.offset & ~PAGE_MASK)
+ return -EINVAL;
+
+ return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
+ a.offset >> PAGE_SHIFT);
+}
+#endif /* __ARCH_WANT_SYS_OLD_MMAP */
+
/*
- * handle mapping disposal for uClinux
+ * split a vma into two pieces at address 'addr', a new vma is allocated either
+ * for the first part or the tail.
*/
-static void put_vma(struct vm_area_struct *vma)
+int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long addr, int new_below)
{
- if (vma) {
- down_write(&nommu_vma_sem);
+ struct vm_area_struct *new;
+ struct vm_region *region;
+ unsigned long npages;
- if (atomic_dec_and_test(&vma->vm_usage)) {
- delete_nommu_vma(vma);
+ kenter("");
- if (vma->vm_ops && vma->vm_ops->close)
- vma->vm_ops->close(vma);
+ /* we're only permitted to split anonymous regions (these should have
+ * only a single usage on the region) */
+ if (vma->vm_file)
+ return -ENOMEM;
- /* IO memory and memory shared directly out of the pagecache from
- * ramfs/tmpfs mustn't be released here */
- if (vma->vm_flags & VM_MAPPED_COPY) {
- realalloc -= kobjsize((void *) vma->vm_start);
- askedalloc -= vma->vm_end - vma->vm_start;
- kfree((void *) vma->vm_start);
- }
+ if (mm->map_count >= sysctl_max_map_count)
+ return -ENOMEM;
- realalloc -= kobjsize(vma);
- askedalloc -= sizeof(*vma);
+ region = kmem_cache_alloc(vm_region_jar, GFP_KERNEL);
+ if (!region)
+ return -ENOMEM;
- if (vma->vm_file)
- fput(vma->vm_file);
- kfree(vma);
- }
+ new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+ if (!new) {
+ kmem_cache_free(vm_region_jar, region);
+ return -ENOMEM;
+ }
+
+ /* most fields are the same, copy all, and then fixup */
+ *new = *vma;
+ *region = *vma->vm_region;
+ new->vm_region = region;
- up_write(&nommu_vma_sem);
+ npages = (addr - vma->vm_start) >> PAGE_SHIFT;
+
+ if (new_below) {
+ region->vm_top = region->vm_end = new->vm_end = addr;
+ } else {
+ region->vm_start = new->vm_start = addr;
+ region->vm_pgoff = new->vm_pgoff += npages;
}
+
+ if (new->vm_ops && new->vm_ops->open)
+ new->vm_ops->open(new);
+
+ delete_vma_from_mm(vma);
+ down_write(&nommu_region_sem);
+ delete_nommu_region(vma->vm_region);
+ if (new_below) {
+ vma->vm_region->vm_start = vma->vm_start = addr;
+ vma->vm_region->vm_pgoff = vma->vm_pgoff += npages;
+ } else {
+ vma->vm_region->vm_end = vma->vm_end = addr;
+ vma->vm_region->vm_top = addr;
+ }
+ add_nommu_region(vma->vm_region);
+ add_nommu_region(new->vm_region);
+ up_write(&nommu_region_sem);
+ add_vma_to_mm(mm, vma);
+ add_vma_to_mm(mm, new);
+ return 0;
}
/*
- * release a mapping
- * - under NOMMU conditions the parameters must match exactly to the mapping to
- * be removed
+ * shrink a VMA by removing the specified chunk from either the beginning or
+ * the end
*/
-int do_munmap(struct mm_struct *mm, unsigned long addr, size_t len)
+static int shrink_vma(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ unsigned long from, unsigned long to)
{
- struct vm_list_struct *vml, **parent;
- unsigned long end = addr + len;
+ struct vm_region *region;
-#ifdef DEBUG
- printk("do_munmap:\n");
-#endif
+ kenter("");
- for (parent = &mm->context.vmlist; *parent; parent = &(*parent)->next) {
- if ((*parent)->vma->vm_start > addr)
- break;
- if ((*parent)->vma->vm_start == addr &&
- ((len == 0) || ((*parent)->vma->vm_end == end)))
- goto found;
+ /* adjust the VMA's pointers, which may reposition it in the MM's tree
+ * and list */
+ delete_vma_from_mm(vma);
+ if (from > vma->vm_start)
+ vma->vm_end = from;
+ else
+ vma->vm_start = to;
+ add_vma_to_mm(mm, vma);
+
+ /* cut the backing region down to size */
+ region = vma->vm_region;
+ BUG_ON(region->vm_usage != 1);
+
+ down_write(&nommu_region_sem);
+ delete_nommu_region(region);
+ if (from > region->vm_start) {
+ to = region->vm_top;
+ region->vm_top = region->vm_end = from;
+ } else {
+ region->vm_start = to;
}
+ add_nommu_region(region);
+ up_write(&nommu_region_sem);
- printk("munmap of non-mmaped memory by process %d (%s): %p\n",
- current->pid, current->comm, (void *) addr);
- return -EINVAL;
+ free_page_series(from, to);
+ return 0;
+}
- found:
- vml = *parent;
+/*
+ * release a mapping
+ * - under NOMMU conditions the chunk to be unmapped must be backed by a single
+ * VMA, though it need not cover the whole VMA
+ */
+int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
+{
+ struct vm_area_struct *vma;
+ unsigned long end;
+ int ret;
- put_vma(vml->vma);
+ kenter(",%lx,%zx", start, len);
- *parent = vml->next;
- realalloc -= kobjsize(vml);
- askedalloc -= sizeof(*vml);
- kfree(vml);
+ len = PAGE_ALIGN(len);
+ if (len == 0)
+ return -EINVAL;
- update_hiwater_vm(mm);
- mm->total_vm -= len >> PAGE_SHIFT;
+ end = start + len;
+
+ /* find the first potentially overlapping VMA */
+ vma = find_vma(mm, start);
+ if (!vma) {
+ static int limit = 0;
+ if (limit < 5) {
+ printk(KERN_WARNING
+ "munmap of memory not mmapped by process %d"
+ " (%s): 0x%lx-0x%lx\n",
+ current->pid, current->comm,
+ start, start + len - 1);
+ limit++;
+ }
+ return -EINVAL;
+ }
-#ifdef DEBUG
- show_process_blocks();
-#endif
+ /* we're allowed to split an anonymous VMA but not a file-backed one */
+ if (vma->vm_file) {
+ do {
+ if (start > vma->vm_start) {
+ kleave(" = -EINVAL [miss]");
+ return -EINVAL;
+ }
+ if (end == vma->vm_end)
+ goto erase_whole_vma;
+ vma = vma->vm_next;
+ } while (vma);
+ kleave(" = -EINVAL [split file]");
+ return -EINVAL;
+ } else {
+ /* the chunk must be a subset of the VMA found */
+ if (start == vma->vm_start && end == vma->vm_end)
+ goto erase_whole_vma;
+ if (start < vma->vm_start || end > vma->vm_end) {
+ kleave(" = -EINVAL [superset]");
+ return -EINVAL;
+ }
+ if (start & ~PAGE_MASK) {
+ kleave(" = -EINVAL [unaligned start]");
+ return -EINVAL;
+ }
+ if (end != vma->vm_end && end & ~PAGE_MASK) {
+ kleave(" = -EINVAL [unaligned split]");
+ return -EINVAL;
+ }
+ if (start != vma->vm_start && end != vma->vm_end) {
+ ret = split_vma(mm, vma, start, 1);
+ if (ret < 0) {
+ kleave(" = %d [split]", ret);
+ return ret;
+ }
+ }
+ return shrink_vma(mm, vma, start, end);
+ }
+erase_whole_vma:
+ delete_vma_from_mm(vma);
+ delete_vma(mm, vma);
+ kleave(" = 0");
return 0;
}
EXPORT_SYMBOL(do_munmap);
-asmlinkage long sys_munmap(unsigned long addr, size_t len)
+SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
{
int ret;
struct mm_struct *mm = current->mm;
}
/*
- * Release all mappings
+ * release all the mappings made in a process's VM space
*/
-void exit_mmap(struct mm_struct * mm)
+void exit_mmap(struct mm_struct *mm)
{
- struct vm_list_struct *tmp;
-
- if (mm) {
-#ifdef DEBUG
- printk("Exit_mmap:\n");
-#endif
+ struct vm_area_struct *vma;
- mm->total_vm = 0;
+ if (!mm)
+ return;
- while ((tmp = mm->context.vmlist)) {
- mm->context.vmlist = tmp->next;
- put_vma(tmp->vma);
+ kenter("");
- realalloc -= kobjsize(tmp);
- askedalloc -= sizeof(*tmp);
- kfree(tmp);
- }
+ mm->total_vm = 0;
-#ifdef DEBUG
- show_process_blocks();
-#endif
+ while ((vma = mm->mmap)) {
+ mm->mmap = vma->vm_next;
+ delete_vma_from_mm(vma);
+ delete_vma(mm, vma);
+ cond_resched();
}
+
+ kleave("");
}
unsigned long do_brk(unsigned long addr, unsigned long len)
* time (controlled by the MREMAP_MAYMOVE flag and available VM space)
*
* under NOMMU conditions, we only permit changing a mapping's size, and only
- * as long as it stays within the hole allocated by the kmalloc() call in
- * do_mmap_pgoff() and the block is not shareable
+ * as long as it stays within the region allocated by do_mmap_private() and the
+ * block is not shareable
*
* MREMAP_FIXED is not supported under NOMMU conditions
*/
struct vm_area_struct *vma;
/* insanity checks first */
- if (new_len == 0)
+ old_len = PAGE_ALIGN(old_len);
+ new_len = PAGE_ALIGN(new_len);
+ if (old_len == 0 || new_len == 0)
return (unsigned long) -EINVAL;
+ if (addr & ~PAGE_MASK)
+ return -EINVAL;
+
if (flags & MREMAP_FIXED && new_addr != addr)
return (unsigned long) -EINVAL;
- vma = find_vma_exact(current->mm, addr);
+ vma = find_vma_exact(current->mm, addr, old_len);
if (!vma)
return (unsigned long) -EINVAL;
if (vma->vm_flags & VM_MAYSHARE)
return (unsigned long) -EPERM;
- if (new_len > kobjsize((void *) addr))
+ if (new_len > vma->vm_region->vm_end - vma->vm_region->vm_start)
return (unsigned long) -ENOMEM;
/* all checks complete - do it */
vma->vm_end = vma->vm_start + new_len;
-
- askedalloc -= old_len;
- askedalloc += new_len;
-
return vma->vm_start;
}
EXPORT_SYMBOL(do_mremap);
-asmlinkage unsigned long sys_mremap(unsigned long addr,
- unsigned long old_len, unsigned long new_len,
- unsigned long flags, unsigned long new_addr)
+SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
+ unsigned long, new_len, unsigned long, flags,
+ unsigned long, new_addr)
{
unsigned long ret;
return NULL;
}
-int remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
- unsigned long to, unsigned long size, pgprot_t prot)
+int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
+ unsigned long pfn, unsigned long size, pgprot_t prot)
{
- vma->vm_start = vma->vm_pgoff << PAGE_SHIFT;
+ if (addr != (pfn << PAGE_SHIFT))
+ return -EINVAL;
+
+ vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
return 0;
}
EXPORT_SYMBOL(remap_pfn_range);
-void swap_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
+int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
+ unsigned long pgoff)
{
+ unsigned int size = vma->vm_end - vma->vm_start;
+
+ if (!(vma->vm_flags & VM_USERMAP))
+ return -EINVAL;
+
+ vma->vm_start = (unsigned long)(addr + (pgoff << PAGE_SHIFT));
+ vma->vm_end = vma->vm_start + size;
+
+ return 0;
}
+EXPORT_SYMBOL(remap_vmalloc_range);
unsigned long arch_get_unmapped_area(struct file *file, unsigned long addr,
unsigned long len, unsigned long pgoff, unsigned long flags)
}
EXPORT_SYMBOL(unmap_mapping_range);
-/*
- * ask for an unmapped area at which to create a mapping on a file
- */
-unsigned long get_unmapped_area(struct file *file, unsigned long addr,
- unsigned long len, unsigned long pgoff,
- unsigned long flags)
-{
- unsigned long (*get_area)(struct file *, unsigned long, unsigned long,
- unsigned long, unsigned long);
-
- get_area = current->mm->get_unmapped_area;
- if (file && file->f_op && file->f_op->get_unmapped_area)
- get_area = file->f_op->get_unmapped_area;
-
- if (!get_area)
- return -ENOSYS;
-
- return get_area(file, addr, len, pgoff, flags);
-}
-EXPORT_SYMBOL(get_unmapped_area);
-
/*
* Check that a process has enough memory to allocate a new virtual
* mapping. 0 means there is enough memory for the allocation to
return 0;
if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) {
- unsigned long n;
+ free = global_page_state(NR_FREE_PAGES);
+ free += global_page_state(NR_FILE_PAGES);
+
+ /*
+ * shmem pages shouldn't be counted as free in this
+ * case, they can't be purged, only swapped out, and
+ * that won't affect the overall amount of available
+ * memory in the system.
+ */
+ free -= global_page_state(NR_SHMEM);
- free = global_page_state(NR_FILE_PAGES);
free += nr_swap_pages;
/*
*/
free += global_page_state(NR_SLAB_RECLAIMABLE);
- /*
- * Leave the last 3% for root
- */
- if (!cap_sys_admin)
- free -= free / 32;
-
- if (free > pages)
- return 0;
-
- /*
- * nr_free_pages() is very expensive on large systems,
- * only call if we're about to fail.
- */
- n = nr_free_pages();
-
/*
* Leave reserved pages. The pages are not for anonymous pages.
*/
- if (n <= totalreserve_pages)
+ if (free <= totalreserve_pages)
goto error;
else
- n -= totalreserve_pages;
+ free -= totalreserve_pages;
/*
* Leave the last 3% for root
*/
if (!cap_sys_admin)
- n -= n / 32;
- free += n;
+ free -= free / 32;
if (free > pages)
return 0;
/* Don't let a single process grow too big:
leave 3% of the size of this process for other processes */
- allowed -= current->mm->total_vm / 32;
+ if (mm)
+ allowed -= mm->total_vm / 32;
- /*
- * cast `allowed' as a signed long because vm_committed_space
- * sometimes has a negative value
- */
- if (atomic_read(&vm_committed_space) < (long)allowed)
+ if (percpu_counter_read_positive(&vm_committed_as) < allowed)
return 0;
+
error:
vm_unacct_memory(pages);
return -ENOMEM;
}
-int in_gate_area_no_task(unsigned long addr)
+int in_gate_area_no_mm(unsigned long addr)
{
return 0;
}
}
EXPORT_SYMBOL(filemap_fault);
-/*
- * Access another process' address space.
- * - source/target buffer must be kernel space
- */
-int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write)
+static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long addr, void *buf, int len, int write)
{
struct vm_area_struct *vma;
- struct mm_struct *mm;
-
- if (addr + len < addr)
- return 0;
-
- mm = get_task_mm(tsk);
- if (!mm)
- return 0;
down_read(&mm->mmap_sem);
/* only read or write mappings where it is permitted */
if (write && vma->vm_flags & VM_MAYWRITE)
- len -= copy_to_user((void *) addr, buf, len);
+ copy_to_user_page(vma, NULL, addr,
+ (void *) addr, buf, len);
else if (!write && vma->vm_flags & VM_MAYREAD)
- len -= copy_from_user(buf, (void *) addr, len);
+ copy_from_user_page(vma, NULL, addr,
+ buf, (void *) addr, len);
else
len = 0;
} else {
}
up_read(&mm->mmap_sem);
+
+ return len;
+}
+
+/**
+ * @access_remote_vm - access another process' address space
+ * @mm: the mm_struct of the target address space
+ * @addr: start address to access
+ * @buf: source or destination buffer
+ * @len: number of bytes to transfer
+ * @write: whether the access is a write
+ *
+ * The caller must hold a reference on @mm.
+ */
+int access_remote_vm(struct mm_struct *mm, unsigned long addr,
+ void *buf, int len, int write)
+{
+ return __access_remote_vm(NULL, mm, addr, buf, len, write);
+}
+
+/*
+ * Access another process' address space.
+ * - source/target buffer must be kernel space
+ */
+int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write)
+{
+ struct mm_struct *mm;
+
+ if (addr + len < addr)
+ return 0;
+
+ mm = get_task_mm(tsk);
+ if (!mm)
+ return 0;
+
+ len = __access_remote_vm(tsk, mm, addr, buf, len, write);
+
mmput(mm);
return len;
}
+
+/**
+ * nommu_shrink_inode_mappings - Shrink the shared mappings on an inode
+ * @inode: The inode to check
+ * @size: The current filesize of the inode
+ * @newsize: The proposed filesize of the inode
+ *
+ * Check the shared mappings on an inode on behalf of a shrinking truncate to
+ * make sure that that any outstanding VMAs aren't broken and then shrink the
+ * vm_regions that extend that beyond so that do_mmap_pgoff() doesn't
+ * automatically grant mappings that are too large.
+ */
+int nommu_shrink_inode_mappings(struct inode *inode, size_t size,
+ size_t newsize)
+{
+ struct vm_area_struct *vma;
+ struct prio_tree_iter iter;
+ struct vm_region *region;
+ pgoff_t low, high;
+ size_t r_size, r_top;
+
+ low = newsize >> PAGE_SHIFT;
+ high = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+ down_write(&nommu_region_sem);
+
+ /* search for VMAs that fall within the dead zone */
+ vma_prio_tree_foreach(vma, &iter, &inode->i_mapping->i_mmap,
+ low, high) {
+ /* found one - only interested if it's shared out of the page
+ * cache */
+ if (vma->vm_flags & VM_SHARED) {
+ up_write(&nommu_region_sem);
+ return -ETXTBSY; /* not quite true, but near enough */
+ }
+ }
+
+ /* reduce any regions that overlap the dead zone - if in existence,
+ * these will be pointed to by VMAs that don't overlap the dead zone
+ *
+ * we don't check for any regions that start beyond the EOF as there
+ * shouldn't be any
+ */
+ vma_prio_tree_foreach(vma, &iter, &inode->i_mapping->i_mmap,
+ 0, ULONG_MAX) {
+ if (!(vma->vm_flags & VM_SHARED))
+ continue;
+
+ region = vma->vm_region;
+ r_size = region->vm_top - region->vm_start;
+ r_top = (region->vm_pgoff << PAGE_SHIFT) + r_size;
+
+ if (r_top > newsize) {
+ region->vm_top -= r_top - newsize;
+ if (region->vm_end > region->vm_top)
+ region->vm_end = region->vm_top;
+ }
+ }
+
+ up_write(&nommu_region_sem);
+ return 0;
+}
Code Review / linux-2.6.git / blobdiff