On Fri, Mar 24, 2023 at 8:34 AM Jiaqi Yan <jiaqiyan@xxxxxxxxxx> wrote:
>
> On Thu, Mar 23, 2023 at 2:38 PM Yang Shi <shy828301@xxxxxxxxx> wrote:
> >
> > On Sat, Mar 4, 2023 at 10:51 PM Jiaqi Yan <jiaqiyan@xxxxxxxxxx> wrote:
> > >
> > > Make __collapse_huge_page_copy return whether copying anonymous pages
> > > succeeded, and make collapse_huge_page handle the return status.
> > >
> > > Break existing PTE scan loop into two for-loops. The first loop copies
> > > source pages into target huge page, and can fail gracefully when running
> > > into memory errors in source pages. If copying all pages succeeds, the
> > > second loop releases and clears up these normal pages. Otherwise, the
> > > second loop rolls back the page table and page states by:
> > > - re-establishing the original PTEs-to-PMD connection.
> > > - releasing source pages back to their LRU list.
> > >
> > > Tested manually:
> > > 0. Enable khugepaged on system under test.
> > > 1. Start a two-thread application. Each thread allocates a chunk of
> > > non-huge anonymous memory buffer.
> > > 2. Pick 4 random buffer locations (2 in each thread) and inject
> > > uncorrectable memory errors at corresponding physical addresses.
> > > 3. Signal both threads to make their memory buffer collapsible, i.e.
> > > calling madvise(MADV_HUGEPAGE).
> > > 4. Wait and check kernel log: khugepaged is able to recover from poisoned
> > > pages and skips collapsing them.
> > > 5. Signal both threads to inspect their buffer contents and make sure no
> > > data corruption.
> > >
> > > Signed-off-by: Jiaqi Yan <jiaqiyan@xxxxxxxxxx>
> > > ---
> > > include/trace/events/huge_memory.h | 3 +-
> > > mm/khugepaged.c | 148 ++++++++++++++++++++++++-----
> > > 2 files changed, 128 insertions(+), 23 deletions(-)
> > >
> > > diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h
> > > index 3e6fb05852f9a..46cce509957ba 100644
> > > --- a/include/trace/events/huge_memory.h
> > > +++ b/include/trace/events/huge_memory.h
> > > @@ -36,7 +36,8 @@
> > > EM( SCAN_ALLOC_HUGE_PAGE_FAIL, "alloc_huge_page_failed") \
> > > EM( SCAN_CGROUP_CHARGE_FAIL, "ccgroup_charge_failed") \
> > > EM( SCAN_TRUNCATED, "truncated") \
> > > - EMe(SCAN_PAGE_HAS_PRIVATE, "page_has_private") \
> > > + EM( SCAN_PAGE_HAS_PRIVATE, "page_has_private") \
> > > + EMe(SCAN_COPY_MC, "copy_poisoned_page") \
> > >
> > > #undef EM
> > > #undef EMe
> > > diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> > > index 27956d4404134..c3c217f6ebc6e 100644
> > > --- a/mm/khugepaged.c
> > > +++ b/mm/khugepaged.c
> > > @@ -19,6 +19,7 @@
> > > #include <linux/page_table_check.h>
> > > #include <linux/swapops.h>
> > > #include <linux/shmem_fs.h>
> > > +#include <linux/kmsan.h>
> > >
> > > #include <asm/tlb.h>
> > > #include <asm/pgalloc.h>
> > > @@ -55,6 +56,7 @@ enum scan_result {
> > > SCAN_CGROUP_CHARGE_FAIL,
> > > SCAN_TRUNCATED,
> > > SCAN_PAGE_HAS_PRIVATE,
> > > + SCAN_COPY_MC,
> > > };
> > >
> > > #define CREATE_TRACE_POINTS
> > > @@ -681,47 +683,47 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
> > > return result;
> > > }
> > >
> > > -static void __collapse_huge_page_copy(pte_t *pte, struct page *page,
> > > - struct vm_area_struct *vma,
> > > - unsigned long address,
> > > - spinlock_t *ptl,
> > > - struct list_head *compound_pagelist)
> > > +static void __collapse_huge_page_copy_succeeded(pte_t *pte,
> > > + pmd_t *pmd,
> > > + struct vm_area_struct *vma,
> > > + unsigned long address,
> > > + spinlock_t *pte_ptl,
> > > + struct list_head *compound_pagelist)
> > > {
> > > struct page *src_page, *tmp;
> > > pte_t *_pte;
> > > - for (_pte = pte; _pte < pte + HPAGE_PMD_NR;
> > > - _pte++, page++, address += PAGE_SIZE) {
> > > - pte_t pteval = *_pte;
> > > + pte_t pteval;
> > > + unsigned long _address;
> > >
> > > + for (_pte = pte, _address = address; _pte < pte + HPAGE_PMD_NR;
> > > + _pte++, _address += PAGE_SIZE) {
> > > + pteval = *_pte;
> > > if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
> > > - clear_user_highpage(page, address);
> > > add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1);
> > > if (is_zero_pfn(pte_pfn(pteval))) {
> > > /*
> > > - * ptl mostly unnecessary.
> > > + * pte_ptl mostly unnecessary.
> > > */
> > > - spin_lock(ptl);
> > > - ptep_clear(vma->vm_mm, address, _pte);
> > > - spin_unlock(ptl);
> > > + spin_lock(pte_ptl);
> >
> > Why did you have to rename ptl to pte_ptl? It seems unnecessary.
>
> Thanks, I will use `ptl` in the next version.
>
> >
> > > + pte_clear(vma->vm_mm, _address, _pte);
> > > + spin_unlock(pte_ptl);
> > > }
> > > } else {
> > > src_page = pte_page(pteval);
> > > - copy_user_highpage(page, src_page, address, vma);
> > > if (!PageCompound(src_page))
> > > release_pte_page(src_page);
> > > /*
> > > - * ptl mostly unnecessary, but preempt has to
> > > - * be disabled to update the per-cpu stats
> > > + * pte_ptl mostly unnecessary, but preempt has
> > > + * to be disabled to update the per-cpu stats
> > > * inside page_remove_rmap().
> > > */
> > > - spin_lock(ptl);
> > > - ptep_clear(vma->vm_mm, address, _pte);
> > > + spin_lock(pte_ptl);
> > > + ptep_clear(vma->vm_mm, _address, _pte);
> > > page_remove_rmap(src_page, vma, false);
> > > - spin_unlock(ptl);
> > > + spin_unlock(pte_ptl);
> > > free_page_and_swap_cache(src_page);
> > > }
> > > }
> > > -
> > > list_for_each_entry_safe(src_page, tmp, compound_pagelist, lru) {
> > > list_del(&src_page->lru);
> > > mod_node_page_state(page_pgdat(src_page),
> > > @@ -733,6 +735,104 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page,
> > > }
> > > }
> > >
> > > +static void __collapse_huge_page_copy_failed(pte_t *pte,
> > > + pmd_t *pmd,
> > > + pmd_t orig_pmd,
> > > + struct vm_area_struct *vma,
> > > + unsigned long address,
> > > + struct list_head *compound_pagelist)
> > > +{
> > > + struct page *src_page, *tmp;
> > > + pte_t *_pte;
> > > + pte_t pteval;
> > > + unsigned long _address;
> > > + spinlock_t *pmd_ptl;
> > > +
> > > + /*
> > > + * Re-establish the PMD to point to the original page table
> > > + * entry. Restoring PMD needs to be done prior to releasing
> > > + * pages. Since pages are still isolated and locked here,
> > > + * acquiring anon_vma_lock_write is unnecessary.
> > > + */
> > > + pmd_ptl = pmd_lock(vma->vm_mm, pmd);
> > > + pmd_populate(vma->vm_mm, pmd, pmd_pgtable(orig_pmd));
> > > + spin_unlock(pmd_ptl);
> > > + /*
> > > + * Release both raw and compound pages isolated
> > > + * in __collapse_huge_page_isolate.
> > > + */
> >
> > It looks like the below code could be replaced by release_pte_pages()
> > with advancing _pte to (pte + HPAGE_PMD_NR - 1).
> >
>
> Yeah, but I think _pte should be (pte + HPAGE_PMR_NR) because _pte is
> decremented before comparison in release_pte_pages(pte, _pte,
> compound_pagelist):
>
> while (--_pte >= pte) {...}
>
> Advancing _pte to (pte + HPAGE_PMD_NR - 1) may leave the last page not released.
Yeah, good catch. I think it is because the only user of
release_pte_pages() is __collapse_huge_page_isolate(). Once the loop
in it is done _pte is pte + HPAGE_PMD_NR.
>
> >
> > > + for (_pte = pte, _address = address; _pte < pte + HPAGE_PMD_NR;
> > > + _pte++, _address += PAGE_SIZE) {
> > > + pteval = *_pte;
> > > + if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval)))
> > > + continue;
> > > + src_page = pte_page(pteval);
> > > + if (!PageCompound(src_page))
> > > + release_pte_page(src_page);
> > > + }
> > > + list_for_each_entry_safe(src_page, tmp, compound_pagelist, lru) {
> > > + list_del(&src_page->lru);
> > > + release_pte_page(src_page);
> > > + }
> > > +}
> > > +
> > > +/*
> > > + * __collapse_huge_page_copy - attempts to copy memory contents from raw
> > > + * pages to a hugepage. Cleans up the raw pages if copying succeeds;
> > > + * otherwise restores the original page table and releases isolated raw pages.
> > > + * Returns SCAN_SUCCEED if copying succeeds, otherwise returns SCAN_COPY_MC.
> > > + *
> > > + * @pte: starting of the PTEs to copy from
> > > + * @page: the new hugepage to copy contents to
> > > + * @pmd: pointer to the new hugepage's PMD
> > > + * @orig_pmd: the original raw pages' PMD
> > > + * @vma: the original raw pages' virtual memory area
> > > + * @address: starting address to copy
> > > + * @pte_ptl: lock on raw pages' PTEs
> > > + * @compound_pagelist: list that stores compound pages
> > > + */
> > > +static int __collapse_huge_page_copy(pte_t *pte,
> > > + struct page *page,
> > > + pmd_t *pmd,
> > > + pmd_t orig_pmd,
> > > + struct vm_area_struct *vma,
> > > + unsigned long address,
> > > + spinlock_t *pte_ptl,
> > > + struct list_head *compound_pagelist)
> > > +{
> > > + struct page *src_page;
> > > + pte_t *_pte;
> > > + pte_t pteval;
> > > + unsigned long _address;
> > > + int result = SCAN_SUCCEED;
> > > +
> > > + /*
> > > + * Copying pages' contents is subject to memory poison at any iteration.
> > > + */
> > > + for (_pte = pte, _address = address; _pte < pte + HPAGE_PMD_NR;
> > > + _pte++, page++, _address += PAGE_SIZE) {
> > > + pteval = *_pte;
> > > + if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
> > > + clear_user_highpage(page, _address);
> > > + continue;
> > > + }
> > > + src_page = pte_page(pteval);
> > > + if (copy_mc_user_highpage(page, src_page, _address, vma) > 0) {
> > > + result = SCAN_COPY_MC;
> > > + break;
> > > + }
> > > + }
> > > +
> > > + if (likely(result == SCAN_SUCCEED))
> > > + __collapse_huge_page_copy_succeeded(pte, pmd, vma, address,
> > > + pte_ptl, compound_pagelist);
> > > + else
> > > + __collapse_huge_page_copy_failed(pte, pmd, orig_pmd, vma,
> > > + address, compound_pagelist);
> > > +
> > > + return result;
> > > +}
> > > +
> > > static void khugepaged_alloc_sleep(void)
> > > {
> > > DEFINE_WAIT(wait);
> > > @@ -1106,9 +1206,13 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
> > > */
> > > anon_vma_unlock_write(vma->anon_vma);
> > >
> > > - __collapse_huge_page_copy(pte, hpage, vma, address, pte_ptl,
> > > - &compound_pagelist);
> > > + result = __collapse_huge_page_copy(pte, hpage, pmd, _pmd,
> > > + vma, address, pte_ptl,
> > > + &compound_pagelist);
> > > pte_unmap(pte);
> > > + if (unlikely(result != SCAN_SUCCEED))
> > > + goto out_up_write;
> > > +
> > > /*
> > > * spin_lock() below is not the equivalent of smp_wmb(), but
> > > * the smp_wmb() inside __SetPageUptodate() can be reused to
> > > --
> > > 2.40.0.rc0.216.gc4246ad0f0-goog
> > >
