* 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) 2007-2008 Paul Mundt <lethal@linux-sh.org>
+ * Copyright (c) 2007-2010 Paul Mundt <lethal@linux-sh.org>
*/
-#include <linux/module.h>
+#include <linux/export.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/tracehook.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"
-static inline __attribute__((format(printf, 1, 2)))
-void no_printk(const char *fmt, ...)
-{
-}
-
#if 0
#define kenter(FMT, ...) \
printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__)
no_printk(KERN_DEBUG FMT"\n", ##__VA_ARGS__)
#endif
-#include "internal.h"
-
void *high_memory;
struct page *mem_map;
unsigned long max_mapnr;
unsigned long num_physpages;
-atomic_long_t vm_committed_space = ATOMIC_LONG_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 = 1; /* page trimming behaviour */
+int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS;
int heap_stack_gap = 0;
-atomic_t mmap_pages_allocated;
+atomic_long_t mmap_pages_allocated;
EXPORT_SYMBOL(mem_map);
EXPORT_SYMBOL(num_physpages);
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->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.
*
return ksize(objp);
/*
+ * 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;
+ }
+
+ /*
* The ksize() function is only guaranteed to work for pointers
* returned by kmalloc(). So handle arbitrary pointers here.
*/
}
int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
- unsigned long start, int len, int flags,
- struct page **pages, struct vm_area_struct **vmas)
+ 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;
- int write = !!(flags & GUP_FLAGS_WRITE);
- int force = !!(flags & GUP_FLAGS_FORCE);
- int ignore = !!(flags & GUP_FLAGS_IGNORE_VMA_PERMISSIONS);
/* 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) ||
- (!ignore && !(vm_flags & vma->vm_flags)))
+ if ((vma->vm_flags & (VM_IO | VM_PFNMAP)) ||
+ !(vm_flags & vma->vm_flags))
goto finish_or_fault;
if (pages) {
}
if (vmas)
vmas[i] = vma;
- start += PAGE_SIZE;
+ start = (start + PAGE_SIZE) & PAGE_MASK;
}
return i;
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
* - 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,
+ unsigned long start, int nr_pages, int write, int force,
struct page **pages, struct vm_area_struct **vmas)
{
int flags = 0;
if (write)
- flags |= GUP_FLAGS_WRITE;
+ flags |= FOLL_WRITE;
if (force)
- flags |= GUP_FLAGS_FORCE;
+ flags |= FOLL_FORCE;
- return __get_user_pages(tsk, mm,
- start, len, flags,
- pages, vmas);
+ 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;
}
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
}
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, pte_t **ptes)
+{
+ 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;
}
*/
void __init mmap_init(void)
{
- vm_region_jar = kmem_cache_create("vm_region_jar",
- sizeof(struct vm_region), 0,
- SLAB_PANIC, NULL);
- vm_area_cachep = kmem_cache_create("vm_area_struct",
- sizeof(struct vm_area_struct), 0,
- SLAB_PANIC, NULL);
+ int ret;
+
+ ret = percpu_counter_init(&vm_committed_as, 0);
+ VM_BUG_ON(ret);
+ vm_region_jar = KMEM_CACHE(vm_region, SLAB_PANIC);
}
/*
return;
last = rb_entry(lastp, struct vm_region, vm_rb);
- if (unlikely(last->vm_end <= last->vm_start))
- BUG();
- if (unlikely(last->vm_top < last->vm_end))
- BUG();
+ BUG_ON(unlikely(last->vm_end <= last->vm_start));
+ BUG_ON(unlikely(last->vm_top < last->vm_end));
while ((p = rb_next(lastp))) {
region = rb_entry(p, struct vm_region, vm_rb);
last = rb_entry(lastp, struct vm_region, vm_rb);
- if (unlikely(region->vm_end <= region->vm_start))
- BUG();
- if (unlikely(region->vm_top < region->vm_end))
- BUG();
- if (unlikely(region->vm_start < last->vm_top))
- BUG();
+ 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
-#define validate_nommu_regions() do {} while(0)
+static void validate_nommu_regions(void)
+{
+}
#endif
/*
validate_nommu_regions();
- BUG_ON(region->vm_start & ~PAGE_MASK);
-
parent = NULL;
p = &nommu_region_tree.rb_node;
while (*p) {
struct page *page = virt_to_page(from);
kdebug("- free %lx", from);
- atomic_dec(&mmap_pages_allocated);
+ atomic_long_dec(&mmap_pages_allocated);
if (page_count(page) != 1)
- kdebug("free page %p [%d]", page, page_count(page));
+ kdebug("free page %p: refcount not one: %d",
+ page, page_count(page));
put_page(page);
}
}
/*
* release a reference to a region
- * - the caller must hold the region semaphore, which this releases
+ * - 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 void __put_nommu_region(struct vm_region *region)
__releases(nommu_region_sem)
{
- kenter("%p{%d}", region, atomic_read(®ion->vm_usage));
+ kenter("%p{%d}", region, region->vm_usage);
BUG_ON(!nommu_region_tree.rb_node);
- if (atomic_dec_and_test(®ion->vm_usage)) {
+ if (--region->vm_usage == 0) {
if (region->vm_top > region->vm_start)
delete_nommu_region(region);
up_write(&nommu_region_sem);
}
/*
+ * 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;
+ }
+ update_protections(mm);
+#endif
+}
+
+/*
* 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
*/
static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
{
- struct vm_area_struct *pvma, **pp;
+ struct vm_area_struct *pvma, *prev;
struct address_space *mapping;
- struct rb_node **p, *parent;
+ struct rb_node **p, *parent, *rb_prev;
kenter(",%p", vma);
mm->map_count++;
vma->vm_mm = mm;
+ protect_vma(vma, vma->vm_flags);
+
/* add the VMA to the mapping */
if (vma->vm_file) {
mapping = vma->vm_file->f_mapping;
+ mutex_lock(&mapping->i_mmap_mutex);
flush_dcache_mmap_lock(mapping);
vma_prio_tree_insert(vma, &mapping->i_mmap);
flush_dcache_mmap_unlock(mapping);
+ mutex_unlock(&mapping->i_mmap_mutex);
}
/* add the VMA to the tree */
- parent = NULL;
+ parent = rb_prev = NULL;
p = &mm->mm_rb.rb_node;
while (*p) {
parent = *p;
* (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)
+ else if (vma->vm_start > pvma->vm_start) {
+ rb_prev = parent;
p = &(*p)->rb_right;
- else if (vma->vm_end < pvma->vm_end)
+ } else if (vma->vm_end < pvma->vm_end)
p = &(*p)->rb_left;
- else if (vma->vm_end > pvma->vm_end)
+ else if (vma->vm_end > pvma->vm_end) {
+ rb_prev = parent;
p = &(*p)->rb_right;
- else if (vma < pvma)
+ } else if (vma < pvma)
p = &(*p)->rb_left;
- else if (vma > pvma)
+ else if (vma > pvma) {
+ rb_prev = parent;
p = &(*p)->rb_right;
- else
+ } else
BUG();
}
rb_insert_color(&vma->vm_rb, &mm->mm_rb);
/* add VMA to the VMA list also */
- for (pp = &mm->mmap; (pvma = *pp); pp = &(*pp)->vm_next) {
- if (pvma->vm_start > vma->vm_start)
- break;
- if (pvma->vm_start < vma->vm_start)
- continue;
- if (pvma->vm_end < vma->vm_end)
- break;
- }
+ prev = NULL;
+ if (rb_prev)
+ prev = rb_entry(rb_prev, struct vm_area_struct, vm_rb);
- vma->vm_next = *pp;
- *pp = vma;
+ __vma_link_list(mm, vma, prev, parent);
}
/*
*/
static void delete_vma_from_mm(struct vm_area_struct *vma)
{
- struct vm_area_struct **pp;
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;
if (vma->vm_file) {
mapping = vma->vm_file->f_mapping;
+ mutex_lock(&mapping->i_mmap_mutex);
flush_dcache_mmap_lock(mapping);
vma_prio_tree_remove(vma, &mapping->i_mmap);
flush_dcache_mmap_unlock(mapping);
+ mutex_unlock(&mapping->i_mmap_mutex);
}
/* remove from the MM's tree and list */
rb_erase(&vma->vm_rb, &mm->mm_rb);
- for (pp = &mm->mmap; *pp; pp = &(*pp)->vm_next) {
- if (*pp == vma) {
- *pp = vma->vm_next;
- break;
- }
- }
- vma->vm_mm = NULL;
+ 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;
}
/*
struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
{
struct vm_area_struct *vma;
- struct rb_node *n = mm->mm_rb.rb_node;
/* check the cache first */
vma = mm->mmap_cache;
if (vma && vma->vm_start <= addr && vma->vm_end > addr)
return vma;
- /* trawl the tree (there may be multiple mappings in which addr
+ /* trawl the list (there may be multiple mappings in which addr
* resides) */
- for (n = rb_first(&mm->mm_rb); n; n = rb_next(n)) {
- vma = rb_entry(n, struct vm_area_struct, vm_rb);
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
if (vma->vm_start > addr)
return NULL;
if (vma->vm_end > addr) {
unsigned long len)
{
struct vm_area_struct *vma;
- struct rb_node *n = mm->mm_rb.rb_node;
unsigned long end = addr + len;
/* check the cache first */
if (vma && vma->vm_start == addr && vma->vm_end == end)
return vma;
- /* trawl the tree (there may be multiple mappings in which addr
+ /* trawl the list (there may be multiple mappings in which addr
* resides) */
- for (n = rb_first(&mm->mm_rb); n; n = rb_next(n)) {
- vma = rb_entry(n, struct vm_area_struct, vm_rb);
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
if (vma->vm_start < addr)
continue;
if (vma->vm_start > addr)
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);
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) && tracehook_expect_breakpoints(current))
+ if ((flags & MAP_PRIVATE) && current->ptrace)
vm_flags &= ~VM_MAYSHARE;
return vm_flags;
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 ret;
+ 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;
}
*/
static int do_mmap_private(struct vm_area_struct *vma,
struct vm_region *region,
- unsigned long len)
+ unsigned long len,
+ unsigned long capabilities)
{
struct page *pages;
- unsigned long total, point, n, rlen;
+ unsigned long total, point, n;
void *base;
int ret, order;
* 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 == 0) {
/* shouldn't return success if we're not sharing */
BUG_ON(!(vma->vm_flags & VM_MAYSHARE));
vma->vm_region->vm_top = vma->vm_region->vm_end;
- return ret;
+ return 0;
}
if (ret != -ENOSYS)
return ret;
* make a private copy of the data and map that instead */
}
- rlen = PAGE_ALIGN(len);
/* 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
*/
- order = get_order(rlen);
+ order = get_order(len);
kdebug("alloc order %d for %lx", order, len);
pages = alloc_pages(GFP_KERNEL, order);
goto enomem;
total = 1 << order;
- atomic_add(total, &mmap_pages_allocated);
+ atomic_long_add(total, &mmap_pages_allocated);
- point = rlen >> PAGE_SHIFT;
+ point = len >> PAGE_SHIFT;
/* we allocated a power-of-2 sized page set, so we may want to trim off
* the excess */
order = ilog2(total - point);
n = 1 << order;
kdebug("shave %lu/%lu @%lu", n, total - point, total);
- atomic_sub(n, &mmap_pages_allocated);
+ atomic_long_sub(n, &mmap_pages_allocated);
total -= n;
set_page_refcounted(pages + total);
__free_pages(pages + total, order);
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 + rlen;
+ region->vm_end = region->vm_start + len;
region->vm_top = region->vm_start + (total << PAGE_SHIFT);
vma->vm_start = region->vm_start;
old_fs = get_fs();
set_fs(KERNEL_DS);
- ret = vma->vm_file->f_op->read(vma->vm_file, base, rlen, &fpos);
+ ret = vma->vm_file->f_op->read(vma->vm_file, base, len, &fpos);
set_fs(old_fs);
if (ret < 0)
goto error_free;
/* clear the last little bit */
- if (ret < rlen)
- memset(base + ret, 0, rlen - ret);
+ if (ret < len)
+ memset(base + ret, 0, len - ret);
- } else {
- /* if it's an anonymous mapping, then just clear it */
- memset(base, 0, rlen);
}
return 0;
error_free:
- free_page_series(region->vm_start, region->vm_end);
+ 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;
}
/*
* handle mapping creation for uClinux
*/
-unsigned long do_mmap_pgoff(struct file *file,
+static unsigned long do_mmap_pgoff(struct file *file,
unsigned long addr,
unsigned long len,
unsigned long prot,
kenter(",%lx,%lx,%lx,%lx,%lx", addr, len, prot, flags, pgoff);
- if (!(flags & MAP_FIXED))
- addr = round_hint_to_min(addr);
-
/* decide whether we should attempt the mapping, and if so what sort of
* mapping */
ret = validate_mmap_request(file, addr, len, prot, flags, pgoff,
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);
if (!vma)
goto error_getting_vma;
- atomic_set(®ion->vm_usage, 1);
+ region->vm_usage = 1;
region->vm_flags = vm_flags;
region->vm_pgoff = pgoff;
- INIT_LIST_HEAD(&vma->anon_vma_node);
+ INIT_LIST_HEAD(&vma->anon_vma_chain);
vma->vm_flags = vm_flags;
vma->vm_pgoff = pgoff;
}
/* we've found a region we can share */
- atomic_inc(&pregion->vm_usage);
+ pregion->vm_usage++;
vma->vm_region = pregion;
start = pregion->vm_start;
start += (pgoff - pregion->vm_pgoff) << PAGE_SHIFT;
vma->vm_region = NULL;
vma->vm_start = 0;
vma->vm_end = 0;
- atomic_dec(&pregion->vm_usage);
+ pregion->vm_usage--;
pregion = NULL;
goto error_just_free;
}
* - 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)
+ 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_just_free;
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);
else
- ret = do_mmap_private(vma, region, len);
+ ret = do_mmap_private(vma, region, len, capabilities);
if (ret < 0)
- goto error_put_region;
-
+ goto error_just_free;
add_nommu_region(region);
+ /* 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);
+
/* okay... we have a mapping; now we have to register it */
result = vma->vm_start;
share:
add_vma_to_mm(current->mm, vma);
- up_write(&nommu_region_sem);
+ /* 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;
+ }
- if (prot & PROT_EXEC)
- flush_icache_range(result, result + len);
+ up_write(&nommu_region_sem);
kleave(" = %lx", result);
return result;
-error_put_region:
- __put_nommu_region(region);
- if (vma) {
- 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 [pr]", ret);
- return ret;
-
error_just_free:
up_write(&nommu_region_sem);
error:
- fput(region->vm_file);
+ if (region->vm_file)
+ fput(region->vm_file);
kmem_cache_free(vm_region_jar, region);
- fput(vma->vm_file);
+ 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);
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_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);
+
+unsigned long do_mmap(struct file *file, unsigned long addr,
+ unsigned long len, unsigned long prot,
+ unsigned long flag, unsigned long offset)
+{
+ if (unlikely(offset + PAGE_ALIGN(len) < offset))
+ return -EINVAL;
+ if (unlikely(offset & ~PAGE_MASK))
+ return -EINVAL;
+ return do_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
+}
+EXPORT_SYMBOL(do_mmap);
+
+unsigned long vm_mmap(struct file *file, unsigned long addr,
+ unsigned long len, unsigned long prot,
+ unsigned long flag, unsigned long offset)
+{
+ unsigned long ret;
+ struct mm_struct *mm = current->mm;
+
+ down_write(&mm->mmap_sem);
+ ret = do_mmap(file, addr, len, prot, flag, offset);
+ up_write(&mm->mmap_sem);
+ return ret;
+}
+EXPORT_SYMBOL(vm_mmap);
+
+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 */
/*
* split a vma into two pieces at address 'addr', a new vma is allocated either
kenter("");
- /* we're only permitted to split anonymous regions that have a single
- * owner */
- if (vma->vm_file ||
- atomic_read(&vma->vm_region->vm_usage) != 1)
+ /* we're only permitted to split anonymous regions (these should have
+ * only a single usage on the region) */
+ if (vma->vm_file)
return -ENOMEM;
if (mm->map_count >= sysctl_max_map_count)
/* cut the backing region down to size */
region = vma->vm_region;
- BUG_ON(atomic_read(®ion->vm_usage) != 1);
+ BUG_ON(region->vm_usage != 1);
down_write(&nommu_region_sem);
delete_nommu_region(region);
int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
{
struct vm_area_struct *vma;
- struct rb_node *rb;
- unsigned long end = start + len;
+ unsigned long end;
int ret;
kenter(",%lx,%zx", start, len);
+ len = PAGE_ALIGN(len);
if (len == 0)
return -EINVAL;
+ end = start + len;
+
/* find the first potentially overlapping VMA */
vma = find_vma(mm, start);
if (!vma) {
- 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);
+ 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;
}
}
if (end == vma->vm_end)
goto erase_whole_vma;
- rb = rb_next(&vma->vm_rb);
- vma = rb_entry(rb, struct vm_area_struct, vm_rb);
- } while (rb);
+ vma = vma->vm_next;
+ } while (vma);
kleave(" = -EINVAL [split file]");
return -EINVAL;
} else {
}
EXPORT_SYMBOL(do_munmap);
-asmlinkage long sys_munmap(unsigned long addr, size_t len)
+int vm_munmap(unsigned long addr, size_t len)
{
- int ret;
struct mm_struct *mm = current->mm;
+ int ret;
down_write(&mm->mmap_sem);
ret = do_munmap(mm, addr, len);
up_write(&mm->mmap_sem);
return ret;
}
+EXPORT_SYMBOL(vm_munmap);
+
+SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
+{
+ return vm_munmap(addr, len);
+}
/*
* release all the mappings made in a process's VM space
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)
+unsigned long vm_brk(unsigned long addr, unsigned long len)
{
return -ENOMEM;
}
struct vm_area_struct *vma;
/* insanity checks first */
+ old_len = PAGE_ALIGN(old_len);
+ new_len = PAGE_ALIGN(new_len);
if (old_len == 0 || new_len == 0)
return (unsigned long) -EINVAL;
}
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);
}
EXPORT_SYMBOL(remap_vmalloc_range);
-void swap_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
-{
-}
-
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
* succeed and -ENOMEM implies there is not.
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;
if (mm)
allowed -= mm->total_vm / 32;
- /*
- * cast `allowed' as a signed long because vm_committed_space
- * sometimes has a negative value
- */
- if (atomic_long_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);
+ mutex_lock(&inode->i_mapping->i_mmap_mutex);
+
+ /* 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) {
+ mutex_unlock(&inode->i_mapping->i_mmap_mutex);
+ 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;
+ }
+ }
+
+ mutex_unlock(&inode->i_mapping->i_mmap_mutex);
+ up_write(&nommu_region_sem);
+ return 0;
+}
projects / linux-flexiantxendom0-3.2.10.git / blobdiff