sync hh.org

[hh.org.git] / arch / arm / mm / consistent.c

/*
 *  linux/arch/arm/mm/consistent.c
 *
 *  Copyright (C) 2000-2004 Russell King
 *
 *  Device local coherent memory support added by Ian Molton (spyro@f2s.com)
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 *  DMA uncached mapping support.
 */
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/errno.h>
#include <linux/list.h>
#include <linux/init.h>
#include <linux/device.h>
#include <linux/dma-mapping.h>

#include <asm/memory.h>
#include <asm/cacheflush.h>
#include <asm/io.h>
#include <asm/tlbflush.h>
#include <asm/sizes.h>

/* Sanity check size */
#if (CONSISTENT_DMA_SIZE % SZ_2M)
#error "CONSISTENT_DMA_SIZE must be multiple of 2MiB"
#endif

#define CONSISTENT_END  (0xffe00000)
#define CONSISTENT_BASE (CONSISTENT_END - CONSISTENT_DMA_SIZE)

#define CONSISTENT_OFFSET(x)    (((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT)
#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PGDIR_SHIFT)
#define NUM_CONSISTENT_PTES (CONSISTENT_DMA_SIZE >> PGDIR_SHIFT)

struct dma_coherent_mem {
        void            *virt_base;
        u32             device_base;
        int             size;
        int             flags;
        unsigned long   *bitmap;
};

/*
 * These are the page tables (2MB each) covering uncached, DMA consistent allocations
 */
static pte_t *consistent_pte[NUM_CONSISTENT_PTES];
static DEFINE_SPINLOCK(consistent_lock);

/*
 * VM region handling support.
 *
 * This should become something generic, handling VM region allocations for
 * vmalloc and similar (ioremap, module space, etc).
 *
 * I envisage vmalloc()'s supporting vm_struct becoming:
 *
 *  struct vm_struct {
 *    struct vm_region  region;
 *    unsigned long     flags;
 *    struct page       **pages;
 *    unsigned int      nr_pages;
 *    unsigned long     phys_addr;
 *  };
 *
 * get_vm_area() would then call vm_region_alloc with an appropriate
 * struct vm_region head (eg):
 *
 *  struct vm_region vmalloc_head = {
 *      .vm_list        = LIST_HEAD_INIT(vmalloc_head.vm_list),
 *      .vm_start       = VMALLOC_START,
 *      .vm_end         = VMALLOC_END,
 *  };
 *
 * However, vmalloc_head.vm_start is variable (typically, it is dependent on
 * the amount of RAM found at boot time.)  I would imagine that get_vm_area()
 * would have to initialise this each time prior to calling vm_region_alloc().
 */
struct vm_region {
        struct list_head        vm_list;
        unsigned long           vm_start;
        unsigned long           vm_end;
        struct page             *vm_pages;
        int                     vm_active;
};

static struct vm_region consistent_head = {
        .vm_list        = LIST_HEAD_INIT(consistent_head.vm_list),
        .vm_start       = CONSISTENT_BASE,
        .vm_end         = CONSISTENT_END,
};

static struct vm_region *
vm_region_alloc(struct vm_region *head, size_t size, gfp_t gfp)
{
        unsigned long addr = head->vm_start, end = head->vm_end - size;
        unsigned long flags;
        struct vm_region *c, *new;

        new = kmalloc(sizeof(struct vm_region), gfp);
        if (!new)
                goto out;

        spin_lock_irqsave(&consistent_lock, flags);

        list_for_each_entry(c, &head->vm_list, vm_list) {
                if ((addr + size) < addr)
                        goto nospc;
                if ((addr + size) <= c->vm_start)
                        goto found;
                addr = c->vm_end;
                if (addr > end)
                        goto nospc;
        }

 found:
        /*
         * Insert this entry _before_ the one we found.
         */
        list_add_tail(&new->vm_list, &c->vm_list);
        new->vm_start = addr;
        new->vm_end = addr + size;
        new->vm_active = 1;

        spin_unlock_irqrestore(&consistent_lock, flags);
        return new;

 nospc:
        spin_unlock_irqrestore(&consistent_lock, flags);
        kfree(new);
 out:
        return NULL;
}

static struct vm_region *vm_region_find(struct vm_region *head, unsigned long addr)
{
        struct vm_region *c;
        
        list_for_each_entry(c, &head->vm_list, vm_list) {
                if (c->vm_active && c->vm_start == addr)
                        goto out;
        }
        c = NULL;
 out:
        return c;
}

#ifdef CONFIG_HUGETLB_PAGE
#error ARM Coherent DMA allocator does not (yet) support huge TLB
#endif

static void *
__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
            pgprot_t prot)
{
        struct page *page;
        struct vm_region *c;
        unsigned long order;
        u64 mask = ISA_DMA_THRESHOLD, limit;

        /* Following is a work-around (a.k.a. hack) to prevent pages
         * with __GFP_COMP being passed to split_page() which cannot
         * handle them.  The real problem is that this flag probably
         * should be 0 on ARM as it is not supported on this
         * platform--see CONFIG_HUGETLB_PAGE. */
        gfp &= ~(__GFP_COMP);

        if (!consistent_pte[0]) {
                printk(KERN_ERR "%s: not initialised\n", __func__);
                dump_stack();
                return NULL;
        }

        if (dev) {

                if(dev->dma_mem) {
                        unsigned long flags;
                        int page;
                        void *ret;

                        spin_lock_irqsave(&consistent_lock, flags);
                        page = bitmap_find_free_region(dev->dma_mem->bitmap,
                                                       dev->dma_mem->size,
                                                       get_order(size));
                        spin_unlock_irqrestore(&consistent_lock, flags);

                        if (page >= 0) {
                                *handle = dev->dma_mem->device_base + (page << PAGE_SHIFT);
                                ret = dev->dma_mem->virt_base + (page << PAGE_SHIFT);
                                memset(ret, 0, size);
                                return ret;
                        }
                }

                mask = dev->coherent_dma_mask;

                /*
                 * Sanity check the DMA mask - it must be non-zero, and
                 * must be able to be satisfied by a DMA allocation.
                 */
                if (mask == 0) {
                        dev_warn(dev, "coherent DMA mask is unset\n");
                        goto no_page;
                }

                if ((~mask) & ISA_DMA_THRESHOLD) {
                        dev_warn(dev, "coherent DMA mask %#llx is smaller "
                                 "than system GFP_DMA mask %#llx\n",
                                 mask, (unsigned long long)ISA_DMA_THRESHOLD);
                        goto no_page;
                }

                if (dev->dma_mem && dev->dma_mem->flags & DMA_MEMORY_EXCLUSIVE)
                        return NULL;
        }

        /*
         * Sanity check the allocation size.
         */
        size = PAGE_ALIGN(size);
        limit = (mask + 1) & ~mask;
        if ((limit && size >= limit) ||
            size >= (CONSISTENT_END - CONSISTENT_BASE)) {
                printk(KERN_WARNING "coherent allocation too big "
                       "(requested %#x mask %#llx)\n", size, mask);
                goto no_page;
        }

        order = get_order(size);

        if (mask != 0xffffffff)
                gfp |= GFP_DMA;

        page = alloc_pages(gfp, order);
        if (!page)
                goto no_page;

        /*
         * Invalidate any data that might be lurking in the
         * kernel direct-mapped region for device DMA.
         */
        {
                unsigned long kaddr = (unsigned long)page_address(page);
                memset(page_address(page), 0, size);
                dmac_flush_range(kaddr, kaddr + size);
        }

        /*
         * Allocate a virtual address in the consistent mapping region.
         */
        c = vm_region_alloc(&consistent_head, size,
                            gfp & ~(__GFP_DMA | __GFP_HIGHMEM));
        if (c) {
                pte_t *pte;
                struct page *end = page + (1 << order);
                int idx = CONSISTENT_PTE_INDEX(c->vm_start);
                u32 off = CONSISTENT_OFFSET(c->vm_start) & (PTRS_PER_PTE-1);

                pte = consistent_pte[idx] + off;
                c->vm_pages = page;

                split_page(page, order);

                /*
                 * Set the "dma handle"
                 */
                *handle = page_to_dma(dev, page);

                do {
                        BUG_ON(!pte_none(*pte));

                        /*
                         * x86 does not mark the pages reserved...
                         */
                        SetPageReserved(page);
                        set_pte(pte, mk_pte(page, prot));
                        page++;
                        pte++;
                        off++;
                        if (off >= PTRS_PER_PTE) {
                                off = 0;
                                pte = consistent_pte[++idx];
                        }
                } while (size -= PAGE_SIZE);

                /*
                 * Free the otherwise unused pages.
                 */
                while (page < end) {
                        __free_page(page);
                        page++;
                }

                return (void *)c->vm_start;
        }

        if (page)
                __free_pages(page, order);
 no_page:
        *handle = ~0;
        return NULL;
}

/*
 * Allocate DMA-coherent memory space and return both the kernel remapped
 * virtual and bus address for that space.
 */
void *
dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp)
{
        if (arch_is_coherent()) {
                void *virt;

                virt = kmalloc(size, gfp);
                if (!virt)
                        return NULL;
                *handle =  virt_to_dma(dev, virt);

                return virt;
        }

        return __dma_alloc(dev, size, handle, gfp,
                           pgprot_noncached(pgprot_kernel));
}
EXPORT_SYMBOL(dma_alloc_coherent);

/*
 * Allocate a writecombining region, in much the same way as
 * dma_alloc_coherent above.
 */
void *
dma_alloc_writecombine(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp)
{
        return __dma_alloc(dev, size, handle, gfp,
                           pgprot_writecombine(pgprot_kernel));
}
EXPORT_SYMBOL(dma_alloc_writecombine);

static int dma_mmap(struct device *dev, struct vm_area_struct *vma,
                    void *cpu_addr, dma_addr_t dma_addr, size_t size)
{
        unsigned long flags, user_size, kern_size;
        struct vm_region *c;
        int ret = -ENXIO;

        user_size = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;

        spin_lock_irqsave(&consistent_lock, flags);
        c = vm_region_find(&consistent_head, (unsigned long)cpu_addr);
        spin_unlock_irqrestore(&consistent_lock, flags);

        if (c) {
                unsigned long off = vma->vm_pgoff;

                kern_size = (c->vm_end - c->vm_start) >> PAGE_SHIFT;

                if (off < kern_size &&
                    user_size <= (kern_size - off)) {
                        vma->vm_flags |= VM_RESERVED;
                        ret = remap_pfn_range(vma, vma->vm_start,
                                              page_to_pfn(c->vm_pages) + off,
                                              user_size << PAGE_SHIFT,
                                              vma->vm_page_prot);
                }
        }

        return ret;
}

int dma_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
                      void *cpu_addr, dma_addr_t dma_addr, size_t size)
{
        vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
        return dma_mmap(dev, vma, cpu_addr, dma_addr, size);
}
EXPORT_SYMBOL(dma_mmap_coherent);

int dma_mmap_writecombine(struct device *dev, struct vm_area_struct *vma,
                          void *cpu_addr, dma_addr_t dma_addr, size_t size)
{
        vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
        return dma_mmap(dev, vma, cpu_addr, dma_addr, size);
}
EXPORT_SYMBOL(dma_mmap_writecombine);

/*
 * free a page as defined by the above mapping.
 * Must not be called with IRQs disabled.
 */
void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, dma_addr_t handle)
{
        struct vm_region *c;
        unsigned long flags, addr;
        pte_t *ptep;
        int idx;
        u32 off;
        struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
        unsigned long order;

        WARN_ON(irqs_disabled());

        if (arch_is_coherent()) {
                kfree(cpu_addr);
                return;
        }

        size = PAGE_ALIGN(size);
        order = get_order(size);

        /* What if mem is valid and the range is not? */
        if (mem && cpu_addr >= mem->virt_base && cpu_addr < (mem->virt_base + (mem->size << PAGE_SHIFT)))
        {
                int page = (cpu_addr - mem->virt_base) >> PAGE_SHIFT;

                bitmap_release_region(mem->bitmap, page, order);
                return;
        }

        spin_lock_irqsave(&consistent_lock, flags);
        c = vm_region_find(&consistent_head, (unsigned long)cpu_addr);
        if (!c)
                goto no_area;

        c->vm_active = 0;
        spin_unlock_irqrestore(&consistent_lock, flags);

        if ((c->vm_end - c->vm_start) != size) {
                printk(KERN_ERR "%s: freeing wrong coherent size (%ld != %d)\n",
                       __func__, c->vm_end - c->vm_start, size);
                dump_stack();
                size = c->vm_end - c->vm_start;
        }

        idx = CONSISTENT_PTE_INDEX(c->vm_start);
        off = CONSISTENT_OFFSET(c->vm_start) & (PTRS_PER_PTE-1);
        ptep = consistent_pte[idx] + off;
        addr = c->vm_start;
        do {
                pte_t pte = ptep_get_and_clear(&init_mm, addr, ptep);
                unsigned long pfn;

                ptep++;
                addr += PAGE_SIZE;
                off++;
                if (off >= PTRS_PER_PTE) {
                        off = 0;
                        ptep = consistent_pte[++idx];
                }

                if (!pte_none(pte) && pte_present(pte)) {
                        pfn = pte_pfn(pte);

                        if (pfn_valid(pfn)) {
                                struct page *page = pfn_to_page(pfn);

                                /*
                                 * x86 does not mark the pages reserved...
                                 */
                                ClearPageReserved(page);

                                __free_page(page);
                                continue;
                        }
                }

                printk(KERN_CRIT "%s: bad page in kernel page table\n",
                       __func__);
        } while (size -= PAGE_SIZE);

        flush_tlb_kernel_range(c->vm_start, c->vm_end);

        spin_lock_irqsave(&consistent_lock, flags);
        list_del(&c->vm_list);
        spin_unlock_irqrestore(&consistent_lock, flags);

        kfree(c);
        return;

 no_area:
        spin_unlock_irqrestore(&consistent_lock, flags);
        printk(KERN_ERR "%s: trying to free invalid coherent area: %p\n",
               __func__, cpu_addr);
        dump_stack();
}
EXPORT_SYMBOL(dma_free_coherent);

int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
                                dma_addr_t device_addr, size_t size, int flags)
{
        void *mem_base;
        int pages = size >> PAGE_SHIFT;
        int bitmap_size = (pages + 31)/32;

        if ((flags & (DMA_MEMORY_MAP | DMA_MEMORY_IO)) == 0)
                goto out;
        if (!size)
                goto out;
        if (dev->dma_mem)
                goto out;

        /* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */
        mem_base = ioremap_nocache(bus_addr, size);
        if (!mem_base)
                goto out;

        dev->dma_mem = kmalloc(GFP_KERNEL, sizeof(struct dma_coherent_mem));
        if (!dev->dma_mem)
                goto out;
        memset(dev->dma_mem, 0, sizeof(struct dma_coherent_mem));
        dev->dma_mem->bitmap = kmalloc(GFP_KERNEL, bitmap_size);
        if (!dev->dma_mem->bitmap)
                goto free1_out;
        memset(dev->dma_mem->bitmap, 0, bitmap_size);

        dev->dma_mem->virt_base = mem_base;
        dev->dma_mem->device_base = device_addr;
        dev->dma_mem->size = pages;
        dev->dma_mem->flags = flags;

        if (flags & DMA_MEMORY_MAP)
                return DMA_MEMORY_MAP;

        return DMA_MEMORY_IO;

 free1_out:
        kfree(dev->dma_mem->bitmap);
 out:
        return 0;
}
EXPORT_SYMBOL(dma_declare_coherent_memory);

void dma_release_declared_memory(struct device *dev)
{
        struct dma_coherent_mem *mem = dev->dma_mem;
        
        if(!mem)
                return;
        dev->dma_mem = NULL;
        kfree(mem->bitmap);
        kfree(mem);
}
EXPORT_SYMBOL(dma_release_declared_memory);

void *dma_mark_declared_memory_occupied(struct device *dev,
                                        dma_addr_t device_addr, size_t size)
{
        struct dma_coherent_mem *mem = dev->dma_mem;
        int pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
        int pos, err;

        if (!mem)
                return ERR_PTR(-EINVAL);

        pos = (device_addr - mem->device_base) >> PAGE_SHIFT;
        err = bitmap_allocate_region(mem->bitmap, pos, get_order(pages));
        if (err != 0)
                return ERR_PTR(err);
        return mem->virt_base + (pos << PAGE_SHIFT);
 }
EXPORT_SYMBOL(dma_mark_declared_memory_occupied);

/*
 * Initialise the consistent memory allocation.
 */
static int __init consistent_init(void)
{
        pgd_t *pgd;
        pmd_t *pmd;
        pte_t *pte;
        int ret = 0, i = 0;
        u32 base = CONSISTENT_BASE;

        do {
                pgd = pgd_offset(&init_mm, base);
                pmd = pmd_alloc(&init_mm, pgd, base);
                if (!pmd) {
                        printk(KERN_ERR "%s: no pmd tables\n", __func__);
                        ret = -ENOMEM;
                        break;
                }
                WARN_ON(!pmd_none(*pmd));

                pte = pte_alloc_kernel(pmd, base);
                if (!pte) {
                        printk(KERN_ERR "%s: no pte tables\n", __func__);
                        ret = -ENOMEM;
                        break;
                }

                consistent_pte[i++] = pte;
                base += (1 << PGDIR_SHIFT);
        } while (base < CONSISTENT_END);

        return ret;
}

core_initcall(consistent_init);

/*
 * Make an area consistent for devices.
 * Note: Drivers should NOT use this function directly, as it will break
 * platforms with CONFIG_DMABOUNCE.
 * Use the driver DMA support - see dma-mapping.h (dma_sync_*)
 */
void consistent_sync(void *vaddr, size_t size, int direction)
{
        unsigned long start = (unsigned long)vaddr;
        unsigned long end   = start + size;

        switch (direction) {
        case DMA_FROM_DEVICE:           /* invalidate only */
                dmac_inv_range(start, end);
                break;
        case DMA_TO_DEVICE:             /* writeback only */
                dmac_clean_range(start, end);
                break;
        case DMA_BIDIRECTIONAL:         /* writeback and invalidate */
                dmac_flush_range(start, end);
                break;
        default:
                BUG();
        }
}
EXPORT_SYMBOL(consistent_sync);