+/*
+ * Free and unmap a vmap area, caller ensuring flush_cache_vunmap had been
+ * called for the correct range previously.
+ */
+static void free_unmap_vmap_area_noflush(struct vmap_area *va)
+{
+ va->flags |= VM_LAZY_FREE;
+ atomic_add((va->va_end - va->va_start) >> PAGE_SHIFT, &vmap_lazy_nr);
+ if (unlikely(atomic_read(&vmap_lazy_nr) > lazy_max_pages()))
+ try_purge_vmap_area_lazy();
+}
+
+/*
+ * Free and unmap a vmap area
+ */
+static void free_unmap_vmap_area(struct vmap_area *va)
+{
+ flush_cache_vunmap(va->va_start, va->va_end);
+ free_unmap_vmap_area_noflush(va);
+}
+
+static struct vmap_area *find_vmap_area(unsigned long addr)
+{
+ struct vmap_area *va;
+
+ spin_lock(&vmap_area_lock);
+ va = __find_vmap_area(addr);
+ spin_unlock(&vmap_area_lock);
+
+ return va;
+}
+
+static void free_unmap_vmap_area_addr(unsigned long addr)
+{
+ struct vmap_area *va;
+
+ va = find_vmap_area(addr);
+ BUG_ON(!va);
+ free_unmap_vmap_area(va);
+}
+
+
+/*** Per cpu kva allocator ***/
+
+/*
+ * vmap space is limited especially on 32 bit architectures. Ensure there is
+ * room for at least 16 percpu vmap blocks per CPU.
+ */
+/*
+ * If we had a constant VMALLOC_START and VMALLOC_END, we'd like to be able
+ * to #define VMALLOC_SPACE (VMALLOC_END-VMALLOC_START). Guess
+ * instead (we just need a rough idea)
+ */
+#if BITS_PER_LONG == 32
+#define VMALLOC_SPACE (128UL*1024*1024)
+#else
+#define VMALLOC_SPACE (128UL*1024*1024*1024)
+#endif
+
+#define VMALLOC_PAGES (VMALLOC_SPACE / PAGE_SIZE)
+#define VMAP_MAX_ALLOC BITS_PER_LONG /* 256K with 4K pages */
+#define VMAP_BBMAP_BITS_MAX 1024 /* 4MB with 4K pages */
+#define VMAP_BBMAP_BITS_MIN (VMAP_MAX_ALLOC*2)
+#define VMAP_MIN(x, y) ((x) < (y) ? (x) : (y)) /* can't use min() */
+#define VMAP_MAX(x, y) ((x) > (y) ? (x) : (y)) /* can't use max() */
+#define VMAP_BBMAP_BITS VMAP_MIN(VMAP_BBMAP_BITS_MAX, \
+ VMAP_MAX(VMAP_BBMAP_BITS_MIN, \
+ VMALLOC_PAGES / NR_CPUS / 16))
+
+#define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE)
+
+static bool vmap_initialized __read_mostly = false;
+
+struct vmap_block_queue {
+ spinlock_t lock;
+ struct list_head free;
+ struct list_head dirty;
+ unsigned int nr_dirty;
+};
+
+struct vmap_block {
+ spinlock_t lock;
+ struct vmap_area *va;
+ struct vmap_block_queue *vbq;
+ unsigned long free, dirty;
+ DECLARE_BITMAP(alloc_map, VMAP_BBMAP_BITS);
+ DECLARE_BITMAP(dirty_map, VMAP_BBMAP_BITS);
+ union {
+ struct list_head free_list;
+ struct rcu_head rcu_head;
+ };
+};
+
+/* Queue of free and dirty vmap blocks, for allocation and flushing purposes */
+static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue);
+
+/*
+ * Radix tree of vmap blocks, indexed by address, to quickly find a vmap block
+ * in the free path. Could get rid of this if we change the API to return a
+ * "cookie" from alloc, to be passed to free. But no big deal yet.
+ */
+static DEFINE_SPINLOCK(vmap_block_tree_lock);
+static RADIX_TREE(vmap_block_tree, GFP_ATOMIC);
+
+/*
+ * We should probably have a fallback mechanism to allocate virtual memory
+ * out of partially filled vmap blocks. However vmap block sizing should be
+ * fairly reasonable according to the vmalloc size, so it shouldn't be a
+ * big problem.
+ */
+
+static unsigned long addr_to_vb_idx(unsigned long addr)
+{
+ addr -= VMALLOC_START & ~(VMAP_BLOCK_SIZE-1);
+ addr /= VMAP_BLOCK_SIZE;
+ return addr;
+}
+
+static struct vmap_block *new_vmap_block(gfp_t gfp_mask)
+{
+ struct vmap_block_queue *vbq;
+ struct vmap_block *vb;
+ struct vmap_area *va;
+ unsigned long vb_idx;
+ int node, err;
+
+ node = numa_node_id();
+
+ vb = kmalloc_node(sizeof(struct vmap_block),
+ gfp_mask & GFP_RECLAIM_MASK, node);
+ if (unlikely(!vb))
+ return ERR_PTR(-ENOMEM);
+
+ va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE,
+ VMALLOC_START, VMALLOC_END,
+ node, gfp_mask);
+ if (unlikely(IS_ERR(va))) {
+ kfree(vb);
+ return ERR_PTR(PTR_ERR(va));
+ }
+
+ err = radix_tree_preload(gfp_mask);
+ if (unlikely(err)) {
+ kfree(vb);
+ free_vmap_area(va);
+ return ERR_PTR(err);
+ }
+
+ spin_lock_init(&vb->lock);
+ vb->va = va;
+ vb->free = VMAP_BBMAP_BITS;
+ vb->dirty = 0;
+ bitmap_zero(vb->alloc_map, VMAP_BBMAP_BITS);
+ bitmap_zero(vb->dirty_map, VMAP_BBMAP_BITS);
+ INIT_LIST_HEAD(&vb->free_list);
+
+ vb_idx = addr_to_vb_idx(va->va_start);
+ spin_lock(&vmap_block_tree_lock);
+ err = radix_tree_insert(&vmap_block_tree, vb_idx, vb);
+ spin_unlock(&vmap_block_tree_lock);
+ BUG_ON(err);
+ radix_tree_preload_end();
+
+ vbq = &get_cpu_var(vmap_block_queue);
+ vb->vbq = vbq;
+ spin_lock(&vbq->lock);
+ list_add(&vb->free_list, &vbq->free);
+ spin_unlock(&vbq->lock);
+ put_cpu_var(vmap_cpu_blocks);
+
+ return vb;
+}
+
+static void rcu_free_vb(struct rcu_head *head)
+{
+ struct vmap_block *vb = container_of(head, struct vmap_block, rcu_head);
+
+ kfree(vb);
+}
+
+static void free_vmap_block(struct vmap_block *vb)
+{
+ struct vmap_block *tmp;
+ unsigned long vb_idx;
+
+ BUG_ON(!list_empty(&vb->free_list));
+
+ vb_idx = addr_to_vb_idx(vb->va->va_start);
+ spin_lock(&vmap_block_tree_lock);
+ tmp = radix_tree_delete(&vmap_block_tree, vb_idx);
+ spin_unlock(&vmap_block_tree_lock);
+ BUG_ON(tmp != vb);
+
+ free_unmap_vmap_area_noflush(vb->va);
+ call_rcu(&vb->rcu_head, rcu_free_vb);
+}
+
+static void *vb_alloc(unsigned long size, gfp_t gfp_mask)
+{
+ struct vmap_block_queue *vbq;
+ struct vmap_block *vb;
+ unsigned long addr = 0;
+ unsigned int order;
+
+ BUG_ON(size & ~PAGE_MASK);
+ BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
+ order = get_order(size);
+
+again:
+ rcu_read_lock();
+ vbq = &get_cpu_var(vmap_block_queue);
+ list_for_each_entry_rcu(vb, &vbq->free, free_list) {
+ int i;
+
+ spin_lock(&vb->lock);
+ i = bitmap_find_free_region(vb->alloc_map,
+ VMAP_BBMAP_BITS, order);
+
+ if (i >= 0) {
+ addr = vb->va->va_start + (i << PAGE_SHIFT);
+ BUG_ON(addr_to_vb_idx(addr) !=
+ addr_to_vb_idx(vb->va->va_start));
+ vb->free -= 1UL << order;
+ if (vb->free == 0) {
+ spin_lock(&vbq->lock);
+ list_del_init(&vb->free_list);
+ spin_unlock(&vbq->lock);
+ }
+ spin_unlock(&vb->lock);
+ break;
+ }
+ spin_unlock(&vb->lock);
+ }
+ put_cpu_var(vmap_cpu_blocks);
+ rcu_read_unlock();
+
+ if (!addr) {
+ vb = new_vmap_block(gfp_mask);
+ if (IS_ERR(vb))
+ return vb;
+ goto again;
+ }
+
+ return (void *)addr;
+}
+
+static void vb_free(const void *addr, unsigned long size)
+{
+ unsigned long offset;
+ unsigned long vb_idx;
+ unsigned int order;
+ struct vmap_block *vb;
+
+ BUG_ON(size & ~PAGE_MASK);
+ BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
+
+ flush_cache_vunmap((unsigned long)addr, (unsigned long)addr + size);
+
+ order = get_order(size);
+
+ offset = (unsigned long)addr & (VMAP_BLOCK_SIZE - 1);
+
+ vb_idx = addr_to_vb_idx((unsigned long)addr);
+ rcu_read_lock();
+ vb = radix_tree_lookup(&vmap_block_tree, vb_idx);
+ rcu_read_unlock();
+ BUG_ON(!vb);
+
+ spin_lock(&vb->lock);
+ bitmap_allocate_region(vb->dirty_map, offset >> PAGE_SHIFT, order);
+
+ vb->dirty += 1UL << order;
+ if (vb->dirty == VMAP_BBMAP_BITS) {
+ BUG_ON(vb->free || !list_empty(&vb->free_list));
+ spin_unlock(&vb->lock);
+ free_vmap_block(vb);
+ } else
+ spin_unlock(&vb->lock);
+}
+
+/**
+ * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer
+ *
+ * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily
+ * to amortize TLB flushing overheads. What this means is that any page you
+ * have now, may, in a former life, have been mapped into kernel virtual
+ * address by the vmap layer and so there might be some CPUs with TLB entries
+ * still referencing that page (additional to the regular 1:1 kernel mapping).
+ *
+ * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can
+ * be sure that none of the pages we have control over will have any aliases
+ * from the vmap layer.
+ */
+void vm_unmap_aliases(void)
+{
+ unsigned long start = ULONG_MAX, end = 0;
+ int cpu;
+ int flush = 0;
+
+ if (unlikely(!vmap_initialized))
+ return;
+
+ for_each_possible_cpu(cpu) {
+ struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu);
+ struct vmap_block *vb;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(vb, &vbq->free, free_list) {
+ int i;
+
+ spin_lock(&vb->lock);
+ i = find_first_bit(vb->dirty_map, VMAP_BBMAP_BITS);
+ while (i < VMAP_BBMAP_BITS) {
+ unsigned long s, e;
+ int j;
+ j = find_next_zero_bit(vb->dirty_map,
+ VMAP_BBMAP_BITS, i);
+
+ s = vb->va->va_start + (i << PAGE_SHIFT);
+ e = vb->va->va_start + (j << PAGE_SHIFT);
+ vunmap_page_range(s, e);
+ flush = 1;
+
+ if (s < start)
+ start = s;
+ if (e > end)
+ end = e;
+
+ i = j;
+ i = find_next_bit(vb->dirty_map,
+ VMAP_BBMAP_BITS, i);
+ }
+ spin_unlock(&vb->lock);
+ }
+ rcu_read_unlock();
+ }
+
+ __purge_vmap_area_lazy(&start, &end, 1, flush);
+}
+EXPORT_SYMBOL_GPL(vm_unmap_aliases);
+
+/**
+ * vm_unmap_ram - unmap linear kernel address space set up by vm_map_ram
+ * @mem: the pointer returned by vm_map_ram
+ * @count: the count passed to that vm_map_ram call (cannot unmap partial)
+ */
+void vm_unmap_ram(const void *mem, unsigned int count)
+{
+ unsigned long size = count << PAGE_SHIFT;
+ unsigned long addr = (unsigned long)mem;
+
+ BUG_ON(!addr);
+ BUG_ON(addr < VMALLOC_START);
+ BUG_ON(addr > VMALLOC_END);
+ BUG_ON(addr & (PAGE_SIZE-1));
+
+ debug_check_no_locks_freed(mem, size);
+ vmap_debug_free_range(addr, addr+size);
+
+ if (likely(count <= VMAP_MAX_ALLOC))
+ vb_free(mem, size);
+ else
+ free_unmap_vmap_area_addr(addr);
+}
+EXPORT_SYMBOL(vm_unmap_ram);
+
+/**
+ * vm_map_ram - map pages linearly into kernel virtual address (vmalloc space)
+ * @pages: an array of pointers to the pages to be mapped
+ * @count: number of pages
+ * @node: prefer to allocate data structures on this node
+ * @prot: memory protection to use. PAGE_KERNEL for regular RAM
+ *
+ * Returns: a pointer to the address that has been mapped, or %NULL on failure
+ */
+void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prot)
+{
+ unsigned long size = count << PAGE_SHIFT;
+ unsigned long addr;
+ void *mem;
+
+ if (likely(count <= VMAP_MAX_ALLOC)) {
+ mem = vb_alloc(size, GFP_KERNEL);
+ if (IS_ERR(mem))
+ return NULL;
+ addr = (unsigned long)mem;
+ } else {
+ struct vmap_area *va;
+ va = alloc_vmap_area(size, PAGE_SIZE,
+ VMALLOC_START, VMALLOC_END, node, GFP_KERNEL);
+ if (IS_ERR(va))
+ return NULL;
+
+ addr = va->va_start;
+ mem = (void *)addr;
+ }
+ if (vmap_page_range(addr, addr + size, prot, pages) < 0) {
+ vm_unmap_ram(mem, count);
+ return NULL;
+ }
+ return mem;
+}
+EXPORT_SYMBOL(vm_map_ram);
+
+/**
+ * vm_area_register_early - register vmap area early during boot
+ * @vm: vm_struct to register
+ * @align: requested alignment
+ *
+ * This function is used to register kernel vm area before
+ * vmalloc_init() is called. @vm->size and @vm->flags should contain
+ * proper values on entry and other fields should be zero. On return,
+ * vm->addr contains the allocated address.
+ *
+ * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING.
+ */
+void __init vm_area_register_early(struct vm_struct *vm, size_t align)
+{
+ static size_t vm_init_off __initdata;
+ unsigned long addr;
+
+ addr = ALIGN(VMALLOC_START + vm_init_off, align);
+ vm_init_off = PFN_ALIGN(addr + vm->size) - VMALLOC_START;
+
+ vm->addr = (void *)addr;
+
+ vm->next = vmlist;
+ vmlist = vm;
+}
+
+void __init vmalloc_init(void)
+{
+ struct vmap_area *va;
+ struct vm_struct *tmp;
+ int i;
+
+ for_each_possible_cpu(i) {
+ struct vmap_block_queue *vbq;
+
+ vbq = &per_cpu(vmap_block_queue, i);
+ spin_lock_init(&vbq->lock);
+ INIT_LIST_HEAD(&vbq->free);
+ INIT_LIST_HEAD(&vbq->dirty);
+ vbq->nr_dirty = 0;
+ }
+
+ /* Import existing vmlist entries. */
+ for (tmp = vmlist; tmp; tmp = tmp->next) {
+ va = kzalloc(sizeof(struct vmap_area), GFP_NOWAIT);
+ va->flags = tmp->flags | VM_VM_AREA;
+ va->va_start = (unsigned long)tmp->addr;
+ va->va_end = va->va_start + tmp->size;
+ __insert_vmap_area(va);
+ }
+
+ vmap_area_pcpu_hole = VMALLOC_END;
+
+ vmap_initialized = true;
+}
+
+/**
+ * map_kernel_range_noflush - map kernel VM area with the specified pages
+ * @addr: start of the VM area to map
+ * @size: size of the VM area to map
+ * @prot: page protection flags to use
+ * @pages: pages to map
+ *
+ * Map PFN_UP(@size) pages at @addr. The VM area @addr and @size
+ * specify should have been allocated using get_vm_area() and its
+ * friends.
+ *
+ * NOTE:
+ * This function does NOT do any cache flushing. The caller is
+ * responsible for calling flush_cache_vmap() on to-be-mapped areas
+ * before calling this function.
+ *
+ * RETURNS:
+ * The number of pages mapped on success, -errno on failure.
+ */
+int map_kernel_range_noflush(unsigned long addr, unsigned long size,
+ pgprot_t prot, struct page **pages)
+{
+ return vmap_page_range_noflush(addr, addr + size, prot, pages);
+}
+
+/**
+ * unmap_kernel_range_noflush - unmap kernel VM area
+ * @addr: start of the VM area to unmap
+ * @size: size of the VM area to unmap
+ *
+ * Unmap PFN_UP(@size) pages at @addr. The VM area @addr and @size
+ * specify should have been allocated using get_vm_area() and its
+ * friends.
+ *
+ * NOTE:
+ * This function does NOT do any cache flushing. The caller is
+ * responsible for calling flush_cache_vunmap() on to-be-mapped areas
+ * before calling this function and flush_tlb_kernel_range() after.
+ */
+void unmap_kernel_range_noflush(unsigned long addr, unsigned long size)
+{
+ vunmap_page_range(addr, addr + size);
+}
+
+/**
+ * unmap_kernel_range - unmap kernel VM area and flush cache and TLB
+ * @addr: start of the VM area to unmap
+ * @size: size of the VM area to unmap
+ *
+ * Similar to unmap_kernel_range_noflush() but flushes vcache before
+ * the unmapping and tlb after.
+ */
+void unmap_kernel_range(unsigned long addr, unsigned long size)
+{
+ unsigned long end = addr + size;
+
+ flush_cache_vunmap(addr, end);
+ vunmap_page_range(addr, end);
+ flush_tlb_kernel_range(addr, end);
+}
+
+int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages)
+{
+ unsigned long addr = (unsigned long)area->addr;
+ unsigned long end = addr + area->size - PAGE_SIZE;
+ int err;
+
+ err = vmap_page_range(addr, end, prot, *pages);
+ if (err > 0) {
+ *pages += err;
+ err = 0;
+ }
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(map_vm_area);
+
+/*** Old vmalloc interfaces ***/
+DEFINE_RWLOCK(vmlist_lock);
+struct vm_struct *vmlist;
+
+static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va,
+ unsigned long flags, void *caller)
+{
+ struct vm_struct *tmp, **p;
+
+ vm->flags = flags;
+ vm->addr = (void *)va->va_start;
+ vm->size = va->va_end - va->va_start;
+ vm->caller = caller;
+ va->private = vm;
+ va->flags |= VM_VM_AREA;
+
+ write_lock(&vmlist_lock);
+ for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) {
+ if (tmp->addr >= vm->addr)
+ break;
+ }
+ vm->next = *p;
+ *p = vm;
+ write_unlock(&vmlist_lock);
+}
+
+static struct vm_struct *__get_vm_area_node(unsigned long size,
+ unsigned long align, unsigned long flags, unsigned long start,
+ unsigned long end, int node, gfp_t gfp_mask, void *caller)
+{
+ static struct vmap_area *va;
+ struct vm_struct *area;
+
+ BUG_ON(in_interrupt());
+ if (flags & VM_IOREMAP) {
+ int bit = fls(size);
+
+ if (bit > IOREMAP_MAX_ORDER)
+ bit = IOREMAP_MAX_ORDER;
+ else if (bit < PAGE_SHIFT)
+ bit = PAGE_SHIFT;
+
+ align = 1ul << bit;
+ }
+
+ size = PAGE_ALIGN(size);
+ if (unlikely(!size))
+ return NULL;
+
+ area = kzalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node);
+ if (unlikely(!area))
+ return NULL;
+
+ /*
+ * We always allocate a guard page.
+ */
+ size += PAGE_SIZE;
+
+ va = alloc_vmap_area(size, align, start, end, node, gfp_mask);
+ if (IS_ERR(va)) {
+ kfree(area);
+ return NULL;
+ }
+
+ insert_vmalloc_vm(area, va, flags, caller);
+ return area;
+}
+
+struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
+ unsigned long start, unsigned long end)
+{
+ return __get_vm_area_node(size, 1, flags, start, end, -1, GFP_KERNEL,
+ __builtin_return_address(0));
+}
+EXPORT_SYMBOL_GPL(__get_vm_area);
+
+struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags,
+ unsigned long start, unsigned long end,
+ void *caller)
+{
+ return __get_vm_area_node(size, 1, flags, start, end, -1, GFP_KERNEL,
+ caller);
+}
+
+/**
+ * get_vm_area - reserve a contiguous kernel virtual area
+ * @size: size of the area
+ * @flags: %VM_IOREMAP for I/O mappings or VM_ALLOC
+ *
+ * Search an area of @size in the kernel virtual mapping area,
+ * and reserved it for out purposes. Returns the area descriptor
+ * on success or %NULL on failure.
+ */
+struct vm_struct *get_vm_area(unsigned long size, unsigned long flags)
+{
+ return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
+ -1, GFP_KERNEL, __builtin_return_address(0));
+}
+
+struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags,
+ void *caller)
+{
+ return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
+ -1, GFP_KERNEL, caller);
+}
+
+struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags,
+ int node, gfp_t gfp_mask)
+{
+ return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
+ node, gfp_mask, __builtin_return_address(0));
+}
+
+static struct vm_struct *find_vm_area(const void *addr)
+{
+ struct vmap_area *va;
+
+ va = find_vmap_area((unsigned long)addr);
+ if (va && va->flags & VM_VM_AREA)
+ return va->private;
+
+ return NULL;
+}
+
+/**
+ * remove_vm_area - find and remove a continuous kernel virtual area
+ * @addr: base address
+ *
+ * Search for the kernel VM area starting at @addr, and remove it.
+ * This function returns the found VM area, but using it is NOT safe
+ * on SMP machines, except for its size or flags.
+ */
+struct vm_struct *remove_vm_area(const void *addr)
+{
+ struct vmap_area *va;
+
+ va = find_vmap_area((unsigned long)addr);
+ if (va && va->flags & VM_VM_AREA) {
+ struct vm_struct *vm = va->private;
+ struct vm_struct *tmp, **p;
+ /*
+ * remove from list and disallow access to this vm_struct
+ * before unmap. (address range confliction is maintained by
+ * vmap.)
+ */
+ write_lock(&vmlist_lock);
+ for (p = &vmlist; (tmp = *p) != vm; p = &tmp->next)
+ ;
+ *p = tmp->next;
+ write_unlock(&vmlist_lock);
+
+ vmap_debug_free_range(va->va_start, va->va_end);
+ free_unmap_vmap_area(va);
+ vm->size -= PAGE_SIZE;
+
+ return vm;
+ }
+ return NULL;
+}
+
+static void __vunmap(const void *addr, int deallocate_pages)
+{
+ struct vm_struct *area;
+
+ if (!addr)
+ return;
+
+ if ((PAGE_SIZE-1) & (unsigned long)addr) {
+ WARN(1, KERN_ERR "Trying to vfree() bad address (%p)\n", addr);
+ return;
+ }
+
+ area = remove_vm_area(addr);
+ if (unlikely(!area)) {
+ WARN(1, KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n",
+ addr);
+ return;
+ }
+
+ debug_check_no_locks_freed(addr, area->size);
+ debug_check_no_obj_freed(addr, area->size);
+
+ if (deallocate_pages) {
+ int i;
+
+ for (i = 0; i < area->nr_pages; i++) {
+ struct page *page = area->pages[i];
+
+ BUG_ON(!page);
+ __free_page(page);
+ }
+
+ if (area->flags & VM_VPAGES)
+ vfree(area->pages);
+ else
+ kfree(area->pages);
+ }
+
+ kfree(area);
+ return;
+}
+
+/**
+ * vfree - release memory allocated by vmalloc()
+ * @addr: memory base address
+ *
+ * Free the virtually continuous memory area starting at @addr, as
+ * obtained from vmalloc(), vmalloc_32() or __vmalloc(). If @addr is
+ * NULL, no operation is performed.
+ *
+ * Must not be called in interrupt context.
+ */
+void vfree(const void *addr)
+{
+ BUG_ON(in_interrupt());
+
+ kmemleak_free(addr);
+
+ __vunmap(addr, 1);
+}
+EXPORT_SYMBOL(vfree);
+
+/**
+ * vunmap - release virtual mapping obtained by vmap()
+ * @addr: memory base address
+ *
+ * Free the virtually contiguous memory area starting at @addr,
+ * which was created from the page array passed to vmap().
+ *
+ * Must not be called in interrupt context.
+ */
+void vunmap(const void *addr)
+{
+ BUG_ON(in_interrupt());
+ might_sleep();
+ __vunmap(addr, 0);
+}
+EXPORT_SYMBOL(vunmap);
+
+/**
+ * vmap - map an array of pages into virtually contiguous space
+ * @pages: array of page pointers
+ * @count: number of pages to map
+ * @flags: vm_area->flags
+ * @prot: page protection for the mapping
+ *
+ * Maps @count pages from @pages into contiguous kernel virtual
+ * space.
+ */
+void *vmap(struct page **pages, unsigned int count,
+ unsigned long flags, pgprot_t prot)
+{
+ struct vm_struct *area;
+
+ might_sleep();
+
+ if (count > totalram_pages)
+ return NULL;
+
+ area = get_vm_area_caller((count << PAGE_SHIFT), flags,
+ __builtin_return_address(0));
+ if (!area)
+ return NULL;
+
+ if (map_vm_area(area, prot, &pages)) {
+ vunmap(area->addr);
+ return NULL;
+ }
+
+ return area->addr;
+}
+EXPORT_SYMBOL(vmap);
+
+static void *__vmalloc_node(unsigned long size, unsigned long align,
+ gfp_t gfp_mask, pgprot_t prot,
+ int node, void *caller);
+static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
+ pgprot_t prot, int node, void *caller)
+{
+ struct page **pages;
+ unsigned int nr_pages, array_size, i;
+
+ nr_pages = (area->size - PAGE_SIZE) >> PAGE_SHIFT;
+ array_size = (nr_pages * sizeof(struct page *));
+
+ area->nr_pages = nr_pages;
+ /* Please note that the recursion is strictly bounded. */
+ if (array_size > PAGE_SIZE) {
+ pages = __vmalloc_node(array_size, 1, gfp_mask | __GFP_ZERO,
+ PAGE_KERNEL, node, caller);
+ area->flags |= VM_VPAGES;
+ } else {
+ pages = kmalloc_node(array_size,
+ (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO,
+ node);
+ }
+ area->pages = pages;
+ area->caller = caller;
+ if (!area->pages) {
+ remove_vm_area(area->addr);
+ kfree(area);
+ return NULL;
+ }
+
+ for (i = 0; i < area->nr_pages; i++) {
+ struct page *page;
+
+ if (node < 0)
+ page = alloc_page(gfp_mask);
+ else
+ page = alloc_pages_node(node, gfp_mask, 0);
+
+ if (unlikely(!page)) {
+ /* Successfully allocated i pages, free them in __vunmap() */
+ area->nr_pages = i;
+ goto fail;
+ }
+ area->pages[i] = page;
+ }
+
+ if (map_vm_area(area, prot, &pages))
+ goto fail;
+ return area->addr;
+
+fail:
+ vfree(area->addr);
+ return NULL;
+}
+
+void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot)
+{
+ void *addr = __vmalloc_area_node(area, gfp_mask, prot, -1,
+ __builtin_return_address(0));
+
+ /*
+ * A ref_count = 3 is needed because the vm_struct and vmap_area
+ * structures allocated in the __get_vm_area_node() function contain
+ * references to the virtual address of the vmalloc'ed block.
+ */
+ kmemleak_alloc(addr, area->size - PAGE_SIZE, 3, gfp_mask);
+
+ return addr;
+}
+
+/**
+ * __vmalloc_node - allocate virtually contiguous memory
+ * @size: allocation size
+ * @align: desired alignment
+ * @gfp_mask: flags for the page level allocator
+ * @prot: protection mask for the allocated pages
+ * @node: node to use for allocation or -1
+ * @caller: caller's return address
+ *
+ * Allocate enough pages to cover @size from the page level
+ * allocator with @gfp_mask flags. Map them into contiguous
+ * kernel virtual space, using a pagetable protection of @prot.
+ */
+static void *__vmalloc_node(unsigned long size, unsigned long align,
+ gfp_t gfp_mask, pgprot_t prot,
+ int node, void *caller)
+{
+ struct vm_struct *area;
+ void *addr;
+ unsigned long real_size = size;
+
+ size = PAGE_ALIGN(size);
+ if (!size || (size >> PAGE_SHIFT) > totalram_pages)
+ return NULL;
+
+ area = __get_vm_area_node(size, align, VM_ALLOC, VMALLOC_START,
+ VMALLOC_END, node, gfp_mask, caller);
+
+ if (!area)
+ return NULL;
+
+ addr = __vmalloc_area_node(area, gfp_mask, prot, node, caller);
+
+ /*
+ * A ref_count = 3 is needed because the vm_struct and vmap_area
+ * structures allocated in the __get_vm_area_node() function contain
+ * references to the virtual address of the vmalloc'ed block.
+ */
+ kmemleak_alloc(addr, real_size, 3, gfp_mask);
+
+ return addr;
+}
+
+void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
+{
+ return __vmalloc_node(size, 1, gfp_mask, prot, -1,
+ __builtin_return_address(0));
+}
+EXPORT_SYMBOL(__vmalloc);
+
+/**
+ * vmalloc - allocate virtually contiguous memory
+ * @size: allocation size
+ * 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(unsigned long size)
+{
+ return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL,
+ -1, __builtin_return_address(0));
+}