Day45-回顾vmalloc()

vmalloc()概览

vmalloc()源码解析

__vmalloc()->__vmalloc_node()

在接口函数调用时，驱动往往会调用__vmalloc()函数， 在__vmalloc中会调用__vmalloc_node_range()

void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot){    return __vmalloc_node(size, 1, gfp_mask, prot, NUMA_NO_NODE,                __builtin_return_address(0));}static void *__vmalloc_node(unsigned long size, unsigned long align,                gfp_t gfp_mask, pgprot_t prot,                int node, const void *caller){    return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END,                gfp_mask, prot, 0, node, caller);}

VMALLOC_START:  是vmalloc区域的开始地址，以内核模块区域的结束地址为起始点

VMALLOC_END:  vmalloc区域的结束地址

__vmalloc_node_range()

void *__vmalloc_node_range(unsigned long size, unsigned long align,            unsigned long start, unsigned long end, gfp_t gfp_mask,            pgprot_t prot, unsigned long vm_flags, int node,            const void *caller){    struct vm_struct *area;    void *addr;    unsigned long real_size = size;​    size = PAGE_ALIGN(size);     //vmalloc分配的大小要以页面大小对其。不能小于0或者大于系统所有内存    if (!size || (size >> PAGE_SHIFT) > totalram_pages())        goto fail;    //调用__get_vm_area_node函数    area = __get_vm_area_node(real_size, align, VM_ALLOC | VM_UNINITIALIZED |                vm_flags, start, end, node, gfp_mask, caller);    if (!area)        goto fail;    //调用__vmalloc_area_node函数，分配物理内存，并和vm_struct建立映射关系    addr = __vmalloc_area_node(area, gfp_mask, prot, node);    if (!addr)        return NULL;​    /*     * In this function, newly allocated vm_struct has VM_UNINITIALIZED     * flag. It means that vm_struct is not fully initialized.     * Now, it is fully initialized, so remove this flag here.     */    clear_vm_uninitialized_flag(area);​    kmemleak_vmalloc(area, size, gfp_mask);​    return addr;​fail:    warn_alloc(gfp_mask, NULL,              "vmalloc: allocation failure: %lu bytes", real_size);    return NULL;}

__get_vm_area_node()

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, const void *caller){    struct vmap_area *va;    struct vm_struct *area;    unsigned long requested_size = size;​    BUG_ON(in_interrupt());    //再次对齐页面    size = PAGE_ALIGN(size);    if (unlikely(!size))        return NULL;    //如果分配的vmalloc区域是用于IOREMAP的，默认按照128个页面对齐    if (flags & VM_IOREMAP)        align = 1ul << clamp_t(int, get_count_order_long(size),                       PAGE_SHIFT, IOREMAP_MAX_ORDER);    //分配一个vm_struct数据结构描述vmalloc区域    area = kzalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node);    if (unlikely(!area))        return NULL;    //如果没有定义VM_NO_GUARD，则需要多分配一个页面备用。    //如分配4KB的内存，vmalloc会分配8KB内存块    if (!(flags & VM_NO_GUARD))        size += PAGE_SIZE;    //调用alloc_vmap_area分配vmalloc区域。    //alloc_vmap_area在vmalloc区域中查找一块大小合适且没有使用的空间    //这段空间称为缝隙hole    //start指VMALLOC_START，end指VMALLOC_END    va = alloc_vmap_area(size, align, start, end, node, gfp_mask);    if (IS_ERR(va)) {        kfree(area);        return NULL;    }    kasan_unpoison_vmalloc((void *)va->va_start, requested_size);    //调用setup_vmalloc_vm构建vm_struct空间并返回该vm_struct数据结构    setup_vmalloc_vm(area, va, flags, caller);    return area;}

setup_vmalloc_vm()

//调用setup_vmalloc_vm构建vm_struct空间并返回该vm_struct数据结构static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va,                  unsigned long flags, const void *caller){    spin_lock(&vmap_area_lock);    setup_vmalloc_vm_locked(vm, va, flags, caller);    spin_unlock(&vmap_area_lock);}

__vmalloc_area_node()

static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,                 pgprot_t prot, int node){    struct page **pages;    unsigned int nr_pages, array_size, i;    const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO;    const gfp_t alloc_mask = gfp_mask | __GFP_NOWARN;    const gfp_t highmem_mask = (gfp_mask & (GFP_DMA | GFP_DMA32)) ?                    0 :                    __GFP_HIGHMEM; //设置高端内存分配掩码，优先使用高端内存    //计算vm_struct区域包含的页面数量    nr_pages = get_vm_area_size(area) >> PAGE_SHIFT;    array_size = (nr_pages * sizeof(struct page *));​    /* Please note that the recursion is strictly bounded. */    if (array_size > PAGE_SIZE) {        pages = __vmalloc_node(array_size, 1, nested_gfp|highmem_mask,                PAGE_KERNEL, node, area->caller);    } else {        pages = kmalloc_node(array_size, nested_gfp, node);    }​    if (!pages) {        remove_vm_area(area->addr);        kfree(area);        return NULL;    }    //保存已分配页面的page数据结构的指针    area->pages = pages;    area->nr_pages = nr_pages;    //通过for循环遍历所有area->nr_pages页面，    //为每个页面调用alloc_page()接口函数分配实际的物理页面    //由于每个物理页面是单独调用alloc_page()    //因此物理页面可能不是连续的    for (i = 0; i < area->nr_pages; i++) {        struct page *page;​        if (node == NUMA_NO_NODE)            page = alloc_page(alloc_mask|highmem_mask);        else            page = alloc_pages_node(node, alloc_mask|highmem_mask, 0);​        if (unlikely(!page)) {            /* Successfully allocated i pages, free them in __vunmap() */            area->nr_pages = i;            atomic_long_add(area->nr_pages, &nr_vmalloc_pages);            goto fail;        }        area->pages[i] = page;        if (gfpflags_allow_blocking(gfp_mask))            cond_resched();    }    atomic_long_add(area->nr_pages, &nr_vmalloc_pages);    //调用map_vm_area函数建立页面映射，该函数最终会调用    //vmap_page_range_no_flush()遍历页表和填充对应的页表    if (map_vm_area(area, prot, pages))        goto fail;    //返回vm_struct区域的起始地址。    return area->addr;​fail:    warn_alloc(gfp_mask, NULL,              "vmalloc: allocation failure, allocated %ld of %ld bytes",              (area->nr_pages*PAGE_SIZE), area->size);    __vfree(area->addr);    return NULL;}