Two questions about copy_pte_range() in kernel












0















I've been trying to understand how fork() works and finally arrived at copy_pte_range(). Most of the functions are understandable but few are quite questionable.



Kernel: 4.14.84



static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma,
unsigned long addr, unsigned long end)
{
pte_t *orig_src_pte, *orig_dst_pte;
pte_t *src_pte, *dst_pte;
spinlock_t *src_ptl, *dst_ptl;
int progress = 0;
int rss[NR_MM_COUNTERS];
swp_entry_t entry = (swp_entry_t){0};

again:
init_rss_vec(rss);

dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl);
if (!dst_pte)
return -ENOMEM;
src_pte = pte_offset_map(src_pmd, addr);
src_ptl = pte_lockptr(src_mm, src_pmd);
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
orig_src_pte = src_pte;
orig_dst_pte = dst_pte;
arch_enter_lazy_mmu_mode();

do {
/*
* We are holding two locks at this point - either of them
* could generate latencies in another task on another CPU.
*/
if (progress >= 32) {
progress = 0;
if (need_resched() ||
spin_needbreak(src_ptl) || spin_needbreak(dst_ptl))
break;
}
if (pte_none(*src_pte)) {
progress++;
continue;
}
entry.val = copy_one_pte(dst_mm, src_mm, dst_pte, src_pte,
vma, addr, rss);
if (entry.val)
break;
progress += 8;
} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);

arch_leave_lazy_mmu_mode();
spin_unlock(src_ptl);
pte_unmap(orig_src_pte);
add_mm_rss_vec(dst_mm, rss);
pte_unmap_unlock(orig_dst_pte, dst_ptl);
cond_resched();

if (entry.val) {
if (add_swap_count_continuation(entry, GFP_KERNEL) < 0)
return -ENOMEM;
progress = 0;
}
if (addr != end)
goto again;
return 0;
}



Questions

1. In the do {} while(), what is the purpose of progress variable?

2. After do {} while(), there is pte_unmap(orig_src_pte); Why is it needed? This is the process of fork(). Based on my knowledge, the parent pte(orig_src_pte) should still be mapped because the process is based on Copy-on-Write so I guess it doesn't have to be unmapped.










share|improve this question





























    0















    I've been trying to understand how fork() works and finally arrived at copy_pte_range(). Most of the functions are understandable but few are quite questionable.



    Kernel: 4.14.84



    static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
    pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma,
    unsigned long addr, unsigned long end)
    {
    pte_t *orig_src_pte, *orig_dst_pte;
    pte_t *src_pte, *dst_pte;
    spinlock_t *src_ptl, *dst_ptl;
    int progress = 0;
    int rss[NR_MM_COUNTERS];
    swp_entry_t entry = (swp_entry_t){0};

    again:
    init_rss_vec(rss);

    dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl);
    if (!dst_pte)
    return -ENOMEM;
    src_pte = pte_offset_map(src_pmd, addr);
    src_ptl = pte_lockptr(src_mm, src_pmd);
    spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
    orig_src_pte = src_pte;
    orig_dst_pte = dst_pte;
    arch_enter_lazy_mmu_mode();

    do {
    /*
    * We are holding two locks at this point - either of them
    * could generate latencies in another task on another CPU.
    */
    if (progress >= 32) {
    progress = 0;
    if (need_resched() ||
    spin_needbreak(src_ptl) || spin_needbreak(dst_ptl))
    break;
    }
    if (pte_none(*src_pte)) {
    progress++;
    continue;
    }
    entry.val = copy_one_pte(dst_mm, src_mm, dst_pte, src_pte,
    vma, addr, rss);
    if (entry.val)
    break;
    progress += 8;
    } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);

    arch_leave_lazy_mmu_mode();
    spin_unlock(src_ptl);
    pte_unmap(orig_src_pte);
    add_mm_rss_vec(dst_mm, rss);
    pte_unmap_unlock(orig_dst_pte, dst_ptl);
    cond_resched();

    if (entry.val) {
    if (add_swap_count_continuation(entry, GFP_KERNEL) < 0)
    return -ENOMEM;
    progress = 0;
    }
    if (addr != end)
    goto again;
    return 0;
    }



    Questions

    1. In the do {} while(), what is the purpose of progress variable?

    2. After do {} while(), there is pte_unmap(orig_src_pte); Why is it needed? This is the process of fork(). Based on my knowledge, the parent pte(orig_src_pte) should still be mapped because the process is based on Copy-on-Write so I guess it doesn't have to be unmapped.










    share|improve this question



























      0












      0








      0








      I've been trying to understand how fork() works and finally arrived at copy_pte_range(). Most of the functions are understandable but few are quite questionable.



      Kernel: 4.14.84



      static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
      pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma,
      unsigned long addr, unsigned long end)
      {
      pte_t *orig_src_pte, *orig_dst_pte;
      pte_t *src_pte, *dst_pte;
      spinlock_t *src_ptl, *dst_ptl;
      int progress = 0;
      int rss[NR_MM_COUNTERS];
      swp_entry_t entry = (swp_entry_t){0};

      again:
      init_rss_vec(rss);

      dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl);
      if (!dst_pte)
      return -ENOMEM;
      src_pte = pte_offset_map(src_pmd, addr);
      src_ptl = pte_lockptr(src_mm, src_pmd);
      spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
      orig_src_pte = src_pte;
      orig_dst_pte = dst_pte;
      arch_enter_lazy_mmu_mode();

      do {
      /*
      * We are holding two locks at this point - either of them
      * could generate latencies in another task on another CPU.
      */
      if (progress >= 32) {
      progress = 0;
      if (need_resched() ||
      spin_needbreak(src_ptl) || spin_needbreak(dst_ptl))
      break;
      }
      if (pte_none(*src_pte)) {
      progress++;
      continue;
      }
      entry.val = copy_one_pte(dst_mm, src_mm, dst_pte, src_pte,
      vma, addr, rss);
      if (entry.val)
      break;
      progress += 8;
      } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);

      arch_leave_lazy_mmu_mode();
      spin_unlock(src_ptl);
      pte_unmap(orig_src_pte);
      add_mm_rss_vec(dst_mm, rss);
      pte_unmap_unlock(orig_dst_pte, dst_ptl);
      cond_resched();

      if (entry.val) {
      if (add_swap_count_continuation(entry, GFP_KERNEL) < 0)
      return -ENOMEM;
      progress = 0;
      }
      if (addr != end)
      goto again;
      return 0;
      }



      Questions

      1. In the do {} while(), what is the purpose of progress variable?

      2. After do {} while(), there is pte_unmap(orig_src_pte); Why is it needed? This is the process of fork(). Based on my knowledge, the parent pte(orig_src_pte) should still be mapped because the process is based on Copy-on-Write so I guess it doesn't have to be unmapped.










      share|improve this question
















      I've been trying to understand how fork() works and finally arrived at copy_pte_range(). Most of the functions are understandable but few are quite questionable.



      Kernel: 4.14.84



      static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
      pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma,
      unsigned long addr, unsigned long end)
      {
      pte_t *orig_src_pte, *orig_dst_pte;
      pte_t *src_pte, *dst_pte;
      spinlock_t *src_ptl, *dst_ptl;
      int progress = 0;
      int rss[NR_MM_COUNTERS];
      swp_entry_t entry = (swp_entry_t){0};

      again:
      init_rss_vec(rss);

      dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl);
      if (!dst_pte)
      return -ENOMEM;
      src_pte = pte_offset_map(src_pmd, addr);
      src_ptl = pte_lockptr(src_mm, src_pmd);
      spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
      orig_src_pte = src_pte;
      orig_dst_pte = dst_pte;
      arch_enter_lazy_mmu_mode();

      do {
      /*
      * We are holding two locks at this point - either of them
      * could generate latencies in another task on another CPU.
      */
      if (progress >= 32) {
      progress = 0;
      if (need_resched() ||
      spin_needbreak(src_ptl) || spin_needbreak(dst_ptl))
      break;
      }
      if (pte_none(*src_pte)) {
      progress++;
      continue;
      }
      entry.val = copy_one_pte(dst_mm, src_mm, dst_pte, src_pte,
      vma, addr, rss);
      if (entry.val)
      break;
      progress += 8;
      } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);

      arch_leave_lazy_mmu_mode();
      spin_unlock(src_ptl);
      pte_unmap(orig_src_pte);
      add_mm_rss_vec(dst_mm, rss);
      pte_unmap_unlock(orig_dst_pte, dst_ptl);
      cond_resched();

      if (entry.val) {
      if (add_swap_count_continuation(entry, GFP_KERNEL) < 0)
      return -ENOMEM;
      progress = 0;
      }
      if (addr != end)
      goto again;
      return 0;
      }



      Questions

      1. In the do {} while(), what is the purpose of progress variable?

      2. After do {} while(), there is pte_unmap(orig_src_pte); Why is it needed? This is the process of fork(). Based on my knowledge, the parent pte(orig_src_pte) should still be mapped because the process is based on Copy-on-Write so I guess it doesn't have to be unmapped.







      linux kernel x86






      share|improve this question















      share|improve this question













      share|improve this question




      share|improve this question








      edited 4 mins ago









      Stephen Kitt

      177k24402480




      177k24402480










      asked 2 hours ago









      Mr.NobodyMr.Nobody

      63




      63






















          1 Answer
          1






          active

          oldest

          votes


















          0















          1. The progress variable measures the cost of the operations performed under locks, and avoids holding those locks for too long. At most every 32 calls to pte_none, or 4 calls to copy_one_pte (which is expensive), or a combination thereof, the function checks whether a reschedule is needed, or if the locks are requested elsewhere; if so, it releases the locks and allows a reschedule. The function continues where it left off, thanks to the jump to again.


          2. The unmap call doesn’t unmap the original PTE in the source process, it undoes the effects of the src_pte = pte_offset_map(src_pmd, addr); line at the start of the function.






          share























            Your Answer








            StackExchange.ready(function() {
            var channelOptions = {
            tags: "".split(" "),
            id: "106"
            };
            initTagRenderer("".split(" "), "".split(" "), channelOptions);

            StackExchange.using("externalEditor", function() {
            // Have to fire editor after snippets, if snippets enabled
            if (StackExchange.settings.snippets.snippetsEnabled) {
            StackExchange.using("snippets", function() {
            createEditor();
            });
            }
            else {
            createEditor();
            }
            });

            function createEditor() {
            StackExchange.prepareEditor({
            heartbeatType: 'answer',
            autoActivateHeartbeat: false,
            convertImagesToLinks: false,
            noModals: true,
            showLowRepImageUploadWarning: true,
            reputationToPostImages: null,
            bindNavPrevention: true,
            postfix: "",
            imageUploader: {
            brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
            contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
            allowUrls: true
            },
            onDemand: true,
            discardSelector: ".discard-answer"
            ,immediatelyShowMarkdownHelp:true
            });


            }
            });














            draft saved

            draft discarded


















            StackExchange.ready(
            function () {
            StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2funix.stackexchange.com%2fquestions%2f507868%2ftwo-questions-about-copy-pte-range-in-kernel%23new-answer', 'question_page');
            }
            );

            Post as a guest















            Required, but never shown

























            1 Answer
            1






            active

            oldest

            votes








            1 Answer
            1






            active

            oldest

            votes









            active

            oldest

            votes






            active

            oldest

            votes









            0















            1. The progress variable measures the cost of the operations performed under locks, and avoids holding those locks for too long. At most every 32 calls to pte_none, or 4 calls to copy_one_pte (which is expensive), or a combination thereof, the function checks whether a reschedule is needed, or if the locks are requested elsewhere; if so, it releases the locks and allows a reschedule. The function continues where it left off, thanks to the jump to again.


            2. The unmap call doesn’t unmap the original PTE in the source process, it undoes the effects of the src_pte = pte_offset_map(src_pmd, addr); line at the start of the function.






            share




























              0















              1. The progress variable measures the cost of the operations performed under locks, and avoids holding those locks for too long. At most every 32 calls to pte_none, or 4 calls to copy_one_pte (which is expensive), or a combination thereof, the function checks whether a reschedule is needed, or if the locks are requested elsewhere; if so, it releases the locks and allows a reschedule. The function continues where it left off, thanks to the jump to again.


              2. The unmap call doesn’t unmap the original PTE in the source process, it undoes the effects of the src_pte = pte_offset_map(src_pmd, addr); line at the start of the function.






              share


























                0












                0








                0








                1. The progress variable measures the cost of the operations performed under locks, and avoids holding those locks for too long. At most every 32 calls to pte_none, or 4 calls to copy_one_pte (which is expensive), or a combination thereof, the function checks whether a reschedule is needed, or if the locks are requested elsewhere; if so, it releases the locks and allows a reschedule. The function continues where it left off, thanks to the jump to again.


                2. The unmap call doesn’t unmap the original PTE in the source process, it undoes the effects of the src_pte = pte_offset_map(src_pmd, addr); line at the start of the function.






                share














                1. The progress variable measures the cost of the operations performed under locks, and avoids holding those locks for too long. At most every 32 calls to pte_none, or 4 calls to copy_one_pte (which is expensive), or a combination thereof, the function checks whether a reschedule is needed, or if the locks are requested elsewhere; if so, it releases the locks and allows a reschedule. The function continues where it left off, thanks to the jump to again.


                2. The unmap call doesn’t unmap the original PTE in the source process, it undoes the effects of the src_pte = pte_offset_map(src_pmd, addr); line at the start of the function.







                share











                share


                share










                answered 5 mins ago









                Stephen KittStephen Kitt

                177k24402480




                177k24402480






























                    draft saved

                    draft discarded




















































                    Thanks for contributing an answer to Unix & Linux Stack Exchange!


                    • Please be sure to answer the question. Provide details and share your research!

                    But avoid



                    • Asking for help, clarification, or responding to other answers.

                    • Making statements based on opinion; back them up with references or personal experience.


                    To learn more, see our tips on writing great answers.




                    draft saved


                    draft discarded














                    StackExchange.ready(
                    function () {
                    StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2funix.stackexchange.com%2fquestions%2f507868%2ftwo-questions-about-copy-pte-range-in-kernel%23new-answer', 'question_page');
                    }
                    );

                    Post as a guest















                    Required, but never shown





















































                    Required, but never shown














                    Required, but never shown












                    Required, but never shown







                    Required, but never shown

































                    Required, but never shown














                    Required, but never shown












                    Required, but never shown







                    Required, but never shown







                    Popular posts from this blog

                    CARDNET

                    Boot-repair Failure: Unable to locate package grub-common:i386

                    Aws NAT - Aws IGW- Aws router