page cache問題

firkraag

回復(fù) 50# embeddedlwp
我覺得這個(gè)值就是vm_start/PAGE_SIZE，得0是就是在線性地址小于4k時(shí)。

embeddedlwp

回復(fù) 51# firkraag


也就是說(shuō)vma->pgoff在filemap與anon的時(shí)候是不一樣的含義是吧
在anon的時(shí)候是vm_start/PAGE_SIZE

不知理解對(duì)不對(duì)


   

firkraag

回復(fù) 52# embeddedlwp
是的。


   

embeddedlwp

回復(fù) 43# firkraag

忘記了是哪個(gè)帖子啦，能不能給個(gè)鏈接  


   

firkraag

回復(fù) 54# embeddedlwp
http://72891.cn/thread-3731204-1-1.html

   

embeddedlwp

回復(fù) 55# firkraag

COW的page fault函數(shù)是do_wp_page函數(shù)，do_wp_page函數(shù)首先獲取與缺頁(yè)異常相關(guān)的頁(yè)框描述符。在2.6.11代碼中也就是一句：
pfn_to_page(pfn);
但是在2.6.24中確實(shí)下邊龐大的函數(shù)，不知紅色部分的注釋怎么理解，比如什么叫raw PFN

/*
* This function gets the "struct page" associated with a pte.
*
* NOTE! Some mappings do not have "struct pages". A raw PFN mapping
* will have each page table entry just pointing to a raw page frame
* number, and as far as the VM layer is concerned, those do not have
* pages associated with them - even if the PFN might point to memory
* that otherwise is perfectly fine and has a "struct page".
*
* The way we recognize those mappings is through the rules set up
* by "remap_pfn_range()": the vma will have the VM_PFNMAP bit set,
* and the vm_pgoff will point to the first PFN mapped: thus every
* page that is a raw mapping will always honor the rule
*
*        pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT)
*
* and if that isn't true, the page has been COW'ed (in which case it
* _does_ have a "struct page" associated with it even if it is in a
* VM_PFNMAP range).
*/
struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte)
{
        unsigned long pfn = pte_pfn(pte);

        if (unlikely(vma->vm_flags & VM_PFNMAP)) {
                unsigned long off = (addr - vma->vm_start) >> PAGE_SHIFT;
                if (pfn == vma->vm_pgoff + off)
                        return NULL;
                if (!is_cow_mapping(vma->vm_flags))
                        return NULL;
        }

#ifdef CONFIG_DEBUG_VM
        /*
         * Add some anal sanity checks for now. Eventually,
         * we should just do "return pfn_to_page(pfn)", but
         * in the meantime we check that we get a valid pfn,
         * and that the resulting page looks ok.
         */
        if (unlikely(!pfn_valid(pfn))) {
                print_bad_pte(vma, pte, addr);
                return NULL;
        }
#endif

        /*
         * NOTE! We still have PageReserved() pages in the page
         * tables.
         *
         * The PAGE_ZERO() pages and various VDSO mappings can
         * cause them to exist.
         */
        return pfn_to_page(pfn);
}

   

embeddedlwp

回復(fù) 55# firkraag

非線性內(nèi)存映射主要用于什么場(chǎng)合？

在handle_pte_fault函數(shù)中，為什么根據(jù)pte設(shè)置_PAGE_FILE就可以確定是非線性內(nèi)存映射：

if (pte_file(entry))
                        return do_nonlinear_fault(mm, vma, address,
                                        pte, pmd, write_access, entry);


   

firkraag

回復(fù) 57# embeddedlwp
這個(gè)_PAGE_FILE就是_PAGE_DIRTY,對(duì)于不存在于內(nèi)存中的臟頁(yè)（這種情況應(yīng)該不存在吧），就認(rèn)為是Non-Linear Memory Mapping頁(yè)。
   
systemcall:
http://lwn.net/Articles/24468/

firkraag

回復(fù) 56# embeddedlwp

見remap_pfn_range系統(tǒng)調(diào)用：
http://gnugeneration.com/books/linux/2.6.20/kernel-api/re286.html

就是直接修改頁(yè)表項(xiàng)，讓它指向一個(gè)頁(yè)幀,不管該頁(yè)幀是否與一個(gè)page結(jié)構(gòu)相關(guān)。
   

firkraag

回復(fù) 59# firkraag
感覺就是要滿足這樣一種需求：“不管這個(gè)物理頁(yè)是否被使用，用戶都要能看到它的內(nèi)容，如果權(quán)限允許，還可以修改它�！�
這樣極端的需求給我的感覺就好像是在操作未經(jīng)加工（raw)的物理頁(yè)。