On Page table walk.
mind entropy
mindentropy at gmail.com
Mon Oct 6 12:29:03 EDT 2014
On Wed, Oct 1, 2014 at 7:17 PM, mind entropy <mindentropy at gmail.com> wrote:
>> ------------------------------
>>
>> Message: 5
>> Date: Mon, 29 Sep 2014 23:05:44 +0530
>> From: mind entropy <mindentropy at gmail.com>
>> Subject: On Page table walk.
>> To: kernelnewbies <kernelnewbies at kernelnewbies.org>
>> Message-ID:
>> <CAM2a4uyLDgFztL+xpos3GG76K3i71vp+63PpZKyVErrVUPU8XA at mail.gmail.com>
>> Content-Type: text/plain; charset=UTF-8
>>
>> Hi,
>>
>> I am experimenting with page table walking. I run a user space
>> program and set the device attribute (of my sample device driver) in
>> the sysfs. (DEVICE_ATTR) which is the address of the variable in the
>> user space. I get the current->mm to get the current task memory
>> descriptor and use it to walk the pages. Once I get the pte address I
>> reboot and dump the memory at that point using u-boot. (md.b <addr> 1)
>> but I do not find the value present there.
>>
>> Sample code: (This is just for illustration and experimenting and does
>> not contain error checks etc.).
>>
>> --------------------------------------------------------------------------------------------
>> ssize_t process_mem_test_attr_store(struct device *dev,
>> struct device_attribute *attr,
>> const char *buf,
>> size_t count)
>> {
>>
>> struct task_struct *current_task;
>> unsigned long addr_res;
>> struct vm_area_struct *vmarea_struct_addr;
>> pgd_t *pgd;
>> pmd_t *pmd;
>> pud_t *pud;
>> pte_t *ptep, pte;
>> struct page *page;
>> int kval;
>> int uval;
>>
>> DEFINE_SPINLOCK(test_lock);
>>
>> spin_lock_irq(&test_lock);
>>
>> current_task = current;
>>
>> if(current_task != NULL) {
>>
>> printk(KERN_ALERT "\nCurrent task pid: %d\n",
>> current_task->pid);
>>
>> printk(KERN_ALERT "mm: 0x%lx, active_mm 0x%lx\n",
>> current_task->mm,current_task->active_mm);
>> printk(KERN_ALERT "Page global directory : 0x%lx\n",
>> current_task->mm->pgd);
>> printk(KERN_ALERT "mmap base : 0x%lx",
>> current_task->mm->mmap_base);
>>
>> vmarea_struct_addr = current_task->mm->mmap;
>>
>> while(vmarea_struct_addr != NULL) {
>> printk(KERN_ALERT "vm_start : 0x%lx, vm_end : 0x%lx\n",
>> vmarea_struct_addr->vm_start,
>> vmarea_struct_addr->vm_end);
>>
>> vmarea_struct_addr = vmarea_struct_addr->vm_next;
>> }
>>
>>
>> } else {
>> printk(KERN_ALERT "Current task NULL\n");
>> }
>>
>> if(kstrtol(buf,10,&addr_res) != 0) {
>> printk(KERN_ALERT "Error converting to long\n");
>> return count;
>> }
>>
>> copy_from_user(&kval,(unsigned int *)addr_res,4);
>>
>> printk(KERN_ALERT "kval : %x\n",kval);
>> printk(KERN_ALERT "addr: %lx\n",addr_res);
>>
>> pgd = pgd_offset(current_task->mm,addr_res);
>>
>> if(pgd_none(*pgd) || pgd_bad(*pgd)) {
>> printk(KERN_ALERT "pgd bad\n");
>> return count;
>> } else {
>> printk(KERN_ALERT "pgd 0x%lx\n",pgd);
>> }
>>
>> pud = pud_offset(pgd,addr_res);
>>
>> if(pud_none(*pud) || pud_bad(*pud)) {
>> printk(KERN_ALERT "pud bad\n");
>> return count;
>> } else {
>> printk(KERN_ALERT "pud 0x%lx\n",pud);
>> }
>>
>> pmd = pmd_offset(pud,addr_res);
>>
>> if(pmd_none(*pmd) || pmd_bad(*pmd)) {
>> printk(KERN_ALERT "pmd bad\n");
>> return count;
>> } else {
>> printk(KERN_ALERT "pmd 0x%lx\n",pmd);
>> }
>>
>>
>> ptep = pte_offset_map(pmd,addr_res);
>> if(!ptep) {
>> printk(KERN_ALERT "ptep bad\n");
>> } else {
>> printk(KERN_ALERT "ptep 0x%lx\n",ptep);
>> }
>>
>> pte = *ptep;
>>
>>
>> if(pte_present(pte)) {
>> printk(KERN_ALERT "pte : 0x%lx\n",pte);
>> page = pte_page(pte);
>>
>> } else {
>> printk(KERN_ALERT "pte not present\n");
>> }
>>
>> printk(KERN_ALERT "pte with offset 0x%lx offset : 0x%lx\n",
>> pte+((addr_res) & ((1<<PAGE_SHIFT)-1)),
>> addr_res & ((1<<PAGE_SHIFT)-1));
>>
>>
>> while(1)
>> ;
>>
>> printk(KERN_ALERT "After lock\n"); //Should not print this.
>>
>>
>> return count;
>> }
>> --------------------------------------------------------------------------------------------
>>
>> I use a spinlock to prevent the process from getting swapped. I
>> disable the irq and make it spin on while(1); after which I reboot.
>> After doing a memoy dump I find the value in the address but at an
>> offset from pte value printed. What seems to be wrong with my
>> approach?
>>
>> Thanks in advance.
>>
>>
>>
>> ------------------------------
>
>
> Hope somebody can give me some clue. My PHYS_OFFSET starts at 0x30000000.
>
> A sample output in the dmesg is as follows:
>
> ------------------------------
>
>
> Sample session:
>
> [ 92.086535] Current task pid: 2382
> [ 92.086632] mm: 0xc2d79480, active_mm 0xc2d79480
> [ 92.090522] Page global directory : 0xc2cb4000
> [ 92.094783] mmap base : 0xb6fe0000
> [ 92.097896] vm_start : 0x8000, vm_end : 0x9000
> [ 92.102454] vm_start : 0x10000, vm_end : 0x11000
> [ 92.106942] vm_start : 0xb6e7c000, vm_end : 0xb6fa5000
> [ 92.111983] vm_start : 0xb6fa5000, vm_end : 0xb6fac000
> [ 92.116995] vm_start : 0xb6fac000, vm_end : 0xb6fae000
> [ 92.122054] vm_start : 0xb6fae000, vm_end : 0xb6faf000
> [ 92.127062] vm_start : 0xb6faf000, vm_end : 0xb6fb2000
> [ 92.132121] vm_start : 0xb6fba000, vm_end : 0xb6fd7000
> [ 92.137177] vm_start : 0xb6fda000, vm_end : 0xb6fdd000
> [ 92.142223] vm_start : 0xb6fdd000, vm_end : 0xb6fde000
> [ 92.147203] vm_start : 0xb6fde000, vm_end : 0xb6fdf000
> [ 92.152275] vm_start : 0xb6fdf000, vm_end : 0xb6fe0000
> [ 92.157291] vm_start : 0xbe852000, vm_end : 0xbe874000
> [ 92.162345] kval : 1234
> [ 92.164670] addr: 10830
> [ 92.167145] pgd 0xc2cb4000
> [ 92.169705] pud 0xc2cb4000
> [ 92.172407] pmd 0xc2cb4000
> [ 92.174995] ptep 0xc3b78040
> [ 92.177774] pte : 0x326dc14f
> [ 92.180545] pte with offset 0x326dc97f offset : 0x830
[Solved]. If anybody is interested I had some help in the "mm" list.
Cross post here http://marc.info/?l=linux-mm&m=141261100710499&w=2
More information about the Kernelnewbies
mailing list