/*
 *  linux/mm/vmalloc.c
 *
 *  Copyright (C) 1993  Linus Torvalds
 *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
 *  SMP-safe vmalloc/vfree/ioremap, Tigran Aivazian <tigran@veritas.com>, May 2000
 *  Major rework to support vmap/vunmap, Christoph Hellwig, SGI, August 2002
 */

#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/interrupt.h>

#include <linux/vmalloc.h>

#include <asm/uaccess.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>


rwlock_t vmlist_lock = RW_LOCK_UNLOCKED;
struct vm_struct *vmlist;

static inline void unmap_area_pte(pmd_t *pmd, unsigned long address,
                                  unsigned long size)
{
        unsigned long end;
        pte_t *pte;

        if (pmd_none(*pmd))
                return;
        if (pmd_bad(*pmd)) {
                pmd_ERROR(*pmd);
                pmd_clear(pmd);
                return;
        }

        pte = pte_offset_kernel(pmd, address);
        address &= ~PMD_MASK;
        end = address + size;
        if (end > PMD_SIZE)
                end = PMD_SIZE;

        do {
                pte_t page;
                page = ptep_get_and_clear(pte);
                address += PAGE_SIZE;
                pte++;
                if (pte_none(page))
                        continue;
                if (pte_present(page))
                        continue;
                printk(KERN_CRIT "Whee.. Swapped out page in kernel page table\n");
        } while (address < end);
}

static inline void unmap_area_pmd(pgd_t *dir, unsigned long address,
                                  unsigned long size)
{
        unsigned long end;
        pmd_t *pmd;

        if (pgd_none(*dir))
                return;
        if (pgd_bad(*dir)) {
                pgd_ERROR(*dir);
                pgd_clear(dir);
                return;
        }

        pmd = pmd_offset(dir, address);
        address &= ~PGDIR_MASK;
        end = address + size;
        if (end > PGDIR_SIZE)
                end = PGDIR_SIZE;

        do {
                unmap_area_pte(pmd, address, end - address);
                address = (address + PMD_SIZE) & PMD_MASK;
                pmd++;
        } while (address < end);
}

static inline int map_area_pte(pte_t *pte, unsigned long address,
                               unsigned long size, pgprot_t prot,
                               struct page ***pages)
{
        unsigned long end;

        address &= ~PMD_MASK;
        end = address + size;
        if (end > PMD_SIZE)
                end = PMD_SIZE;

        do {
                struct page *page = **pages;

                if (!pte_none(*pte))
                        printk(KERN_ERR "alloc_area_pte: page already exists\n");
                if (!page)
                        return -ENOMEM;

                set_pte(pte, mk_pte(page, prot));
                address += PAGE_SIZE;
                pte++;
                (*pages)++;
        } while (address < end);
        return 0;
}

static inline int map_area_pmd(pmd_t *pmd, unsigned long address,
                               unsigned long size, pgprot_t prot,
                               struct page ***pages)
{
        unsigned long end;

        address &= ~PGDIR_MASK;
        end = address + size;
        if (end > PGDIR_SIZE)
                end = PGDIR_SIZE;

        do {
                pte_t * pte = pte_alloc_kernel(&init_mm, pmd, address);
                if (!pte)
                        return -ENOMEM;
                if (map_area_pte(pte, address, end - address, prot, pages))
                        return -ENOMEM;
                address = (address + PMD_SIZE) & PMD_MASK;
                pmd++;
        } while (address < end);

        return 0;
}

void unmap_vm_area(struct vm_struct *area)
{
        unsigned long address = VMALLOC_VMADDR(area->addr);
        unsigned long end = (address + area->size);
        pgd_t *dir;

        dir = pgd_offset_k(address);
        flush_cache_all();
        do {
                unmap_area_pmd(dir, address, end - address);
                address = (address + PGDIR_SIZE) & PGDIR_MASK;
                dir++;
        } while (address && (address < end));
        flush_tlb_kernel_range(VMALLOC_VMADDR(area->addr), end);
}

int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages)
{
        unsigned long address = VMALLOC_VMADDR(area->addr);
        unsigned long end = address + (area->size-PAGE_SIZE);
        pgd_t *dir;
        int err = 0;

        dir = pgd_offset_k(address);
        spin_lock(&init_mm.page_table_lock);
        do {
                pmd_t *pmd = pmd_alloc(&init_mm, dir, address);
                if (!pmd) {
                        err = -ENOMEM;
                        break;
                }
                if (map_area_pmd(pmd, address, end - address, prot, pages)) {
                        err = -ENOMEM;
                        break;
                }

                address = (address + PGDIR_SIZE) & PGDIR_MASK;
                dir++;
        } while (address && (address < end));

        spin_unlock(&init_mm.page_table_lock);
        flush_cache_all();
        return err;
}


/**
 *      get_vm_area  -  reserve a contingous 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)
{
        struct vm_struct **p, *tmp, *area;
        unsigned long addr = VMALLOC_START;

        area = kmalloc(sizeof(*area), GFP_KERNEL);
        if (unlikely(!area))
                return NULL;

        /*
         * We always allocate a guard page.
         */
        size += PAGE_SIZE;

        write_lock(&vmlist_lock);
        for (p = &vmlist; (tmp = *p) ;p = &tmp->next) {
                if ((size + addr) < addr)
                        goto out;
                if (size + addr <= (unsigned long)tmp->addr)
                        goto found;
                addr = tmp->size + (unsigned long)tmp->addr;
                if (addr > VMALLOC_END-size)
                        goto out;
        }

found:
        area->next = *p;
        *p = area;

        area->flags = flags;
        area->addr = (void *)addr;
        area->size = size;
        area->pages = NULL;
        area->nr_pages = 0;
        area->phys_addr = 0;
        write_unlock(&vmlist_lock);

        return area;

out:
        write_unlock(&vmlist_lock);
        kfree(area);
        return NULL;
}

/**
 *      remove_vm_area  -  find and remove a contingous 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.
 */
struct vm_struct *remove_vm_area(void *addr)
{
        struct vm_struct **p, *tmp;

        write_lock(&vmlist_lock);
        for (p = &vmlist ; (tmp = *p) ;p = &tmp->next) {
                 if (tmp->addr == addr)
                         goto found;
        }
        write_unlock(&vmlist_lock);
        return NULL;

found:
        *p = tmp->next;
        write_unlock(&vmlist_lock);
        return tmp;
}

void __vunmap(void *addr, int deallocate_pages)
{
        struct vm_struct *area;

        if (!addr)
                return;

        if ((PAGE_SIZE-1) & (unsigned long)addr) {
                printk(KERN_ERR "Trying to vfree() bad address (%p)\n", addr);
                return;
        }

        area = remove_vm_area(addr);
        if (unlikely(!area)) {
                printk(KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n",
                                addr);
                return;
        }

        unmap_vm_area(area);
        
        if (deallocate_pages) {
                int i;

                for (i = 0; i < area->nr_pages; i++) {
                        if (unlikely(!area->pages[i]))
                                BUG();
                        __free_page(area->pages[i]);
                }

                kfree(area->pages);
        }

        kfree(area);
        return;
}

/**
 *      vfree  -  release memory allocated by vmalloc()
 *
 *      @addr:          memory base address
 *
 *      Free the virtually continguos memory area starting at @addr, as
 *      obtained from vmalloc(), vmalloc_32() or __vmalloc().
 *
 *      May not be called in interrupt context.
 */
void vfree(void *addr)
{
        BUG_ON(in_interrupt());
        __vunmap(addr, 1);
}

/**
 *      vunmap  -  release virtual mapping obtained by vmap()
 *
 *      @addr:          memory base address
 *
 *      Free the virtually continguos memory area starting at @addr,
 *      which was created from the page array passed to vmap().
 *
 *      May not be called in interrupt context.
 */
void vunmap(void *addr)
{
        BUG_ON(in_interrupt());
        __vunmap(addr, 0);
}

/**
 *      vmap  -  map an array of pages into virtually continguos space
 *
 *      @pages:         array of page pointers
 *      @count:         number of pages to map
 *
 *      Maps @count pages from @pages into continguos kernel virtual
 *      space.
 */
void *vmap(struct page **pages, unsigned int count)
{
        struct vm_struct *area;

        if (count > num_physpages)
                return NULL;

        area = get_vm_area((count << PAGE_SHIFT), VM_MAP);
        if (!area)
                return NULL;
        if (map_vm_area(area, PAGE_KERNEL, &pages)) {
                vunmap(area->addr);
                return NULL;
        }

        return area->addr;
}

/**
 *      __vmalloc  -  allocate virtually continguos memory
 *
 *      @size:          allocation size
 *      @gfp_mask:      flags for the page level allocator
 *      @prot:          protection mask for the allocated pages
 *
 *      Allocate enough pages to cover @size from the page level
 *      allocator with @gfp_mask flags.  Map them into continguos
 *      kernel virtual space, using a pagetable protection of @prot.
 */
void *__vmalloc(unsigned long size, int gfp_mask, pgprot_t prot)
{
        struct vm_struct *area;
        struct page **pages;
        unsigned int nr_pages, array_size, i;

        size = PAGE_ALIGN(size);
        if (!size || (size >> PAGE_SHIFT) > num_physpages)
                return NULL;

        area = get_vm_area(size, VM_ALLOC);
        if (!area)
                return NULL;

        nr_pages = (size+PAGE_SIZE) >> PAGE_SHIFT;
        array_size = (nr_pages * sizeof(struct page *));

        area->nr_pages = nr_pages;
        area->pages = pages = kmalloc(array_size, (gfp_mask & ~__GFP_HIGHMEM));
        if (!area->pages) {
                remove_vm_area(area->addr);
                kfree(area);
                return NULL;
        }
        memset(area->pages, 0, array_size);

        for (i = 0; i < area->nr_pages; i++) {
                area->pages[i] = alloc_page(gfp_mask);
                if (unlikely(!area->pages[i])) {
                        /* Successfully allocated i pages, free them in __vunmap() */
                        area->nr_pages = i;
                        goto fail;
                }
        }
        
        if (map_vm_area(area, prot, &pages))
                goto fail;
        return area->addr;

fail:
        vfree(area->addr);
        return NULL;
}

/**
 *      vmalloc  -  allocate virtually continguos memory
 *
 *      @size:          allocation size
 *
 *      Allocate enough pages to cover @size from the page level
 *      allocator and map them into continguos kernel virtual space.
 *
 *      For tight cotrol over page level allocator and protection flags
 *      use __vmalloc() instead.
 */
void *vmalloc(unsigned long size)
{
       return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL);
}

/**
 *      vmalloc_32  -  allocate virtually continguos memory (32bit addressable)
 *
 *      @size:          allocation size
 *
 *      Allocate enough 32bit PA addressable pages to cover @size from the
 *      page level allocator and map them into continguos kernel virtual space.
 */
void *vmalloc_32(unsigned long size)
{
        return __vmalloc(size, GFP_KERNEL, PAGE_KERNEL);
}

long vread(char *buf, char *addr, unsigned long count)
{
        struct vm_struct *tmp;
        char *vaddr, *buf_start = buf;
        unsigned long n;

        /* Don't allow overflow */
        if ((unsigned long) addr + count < count)
                count = -(unsigned long) addr;

        read_lock(&vmlist_lock);
        for (tmp = vmlist; tmp; tmp = tmp->next) {
                vaddr = (char *) tmp->addr;
                if (addr >= vaddr + tmp->size - PAGE_SIZE)
                        continue;
                while (addr < vaddr) {
                        if (count == 0)
                                goto finished;
                        *buf = '\0';
                        buf++;
                        addr++;
                        count--;
                }
                n = vaddr + tmp->size - PAGE_SIZE - addr;
                do {
                        if (count == 0)
                                goto finished;
                        *buf = *addr;
                        buf++;
                        addr++;
                        count--;
                } while (--n > 0);
        }
finished:
        read_unlock(&vmlist_lock);
        return buf - buf_start;
}

long vwrite(char *buf, char *addr, unsigned long count)
{
        struct vm_struct *tmp;
        char *vaddr, *buf_start = buf;
        unsigned long n;

        /* Don't allow overflow */
        if ((unsigned long) addr + count < count)
                count = -(unsigned long) addr;

        read_lock(&vmlist_lock);
        for (tmp = vmlist; tmp; tmp = tmp->next) {
                vaddr = (char *) tmp->addr;
                if (addr >= vaddr + tmp->size - PAGE_SIZE)
                        continue;
                while (addr < vaddr) {
                        if (count == 0)
                                goto finished;
                        buf++;
                        addr++;
                        count--;
                }
                n = vaddr + tmp->size - PAGE_SIZE - addr;
                do {
                        if (count == 0)
                                goto finished;
                        *addr = *buf;
                        buf++;
                        addr++;
                        count--;
                } while (--n > 0);
        }
finished:
        read_unlock(&vmlist_lock);
        return buf - buf_start;
}