Re: [PATCH] mm: use memory barriers for non PMD-sized folios to sync

["David Hildenbrand (Arm)" <david@kernel.org>]

On 11/11/26 09:43, Baolin Wang wrote:
> 
> 
> On 11/11/26 3:48 PM, David Hildenbrand (Arm) wrote:
>> On 11/11/26 07:06, Baolin Wang wrote:
>>> Commit 243cf1f67b36 ("mm: memory: fix truncation removing mapped folios")
>>> uses PMD lock via sync_with_folio_pmd_zap() to synchronize when a cleared
>>> PMD is found while unmapping a folio.
>>>
>>> However, for non PMD-sized folios, the cleared PMD can only come from
>>> PTE table reclaim, which clears the PMD only after the rmaps for the
>>> table have been removed. This is plain message passing, and taking
>>> the PMD lock is more than needed, like I did in the previous patch[1].
>>>
>>> Without barriers, the walker can observe the cleared PMD but a stale
>>> mapcount on weakly ordered architectures:
>>>
>>> CPU 0 (unmap folio)                 CPU 1 (MADV_DONTNEED, full PMD)
>>> ================================    ================================
>>> folio_lock()
>>>                                      lock(ptl)
>>>                                      clear PTEs
>>>                                      remove rmaps   /* W mapcount */
>>> [mapcount load satisfied early,
>>>   folio still mapped]
>>>                                      pmd_clear()    /* W pmd */
>>>                                      unlock(ptl)
>>> pmdp_get_lockless() -> none         /* R pmd */
>>> skip the PMD
>>> folio_mapped() -> true              /* R mapcount, stale */
>>> unmapping assumed to have failed
>>>
>>> Pairing an smp_wmb() before the PMD clear with an smp_rmb() after the
>>> PMD read forbids this outcome:
>>>
>>> CPU 0 (unmap folio)                 CPU 1 (MADV_DONTNEED, full PMD)
>>> ================================    ================================
>>>                                      remove rmaps   /* W mapcount */
>>>                                      smp_wmb()
>>>                                      pmd_clear()    /* W pmd */
>>> pmdp_get_lockless() -> none         /* R pmd */
>>> smp_rmb()
>>> folio_mapped()                      /* R mapcount */
>>>
>>> If R pmd observes W pmd, R mapcount must observe W mapcount, so
>>> folio_mapped() no longer reports the removed mappings.
>>>
>>> No changes for PMD-sized folios unmapping.
>>>
>>> [1] https://lore.kernel.org/all/542c97482eae84f86704bcee56482633d1b32321.1791616645.git.baolin.wang@linux.alibaba.com/
>>> Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
>>> ---
>>>   mm/internal.h        | 26 ++++++++++++++++++++++----
>>>   mm/memory.c          | 12 ++++++++++--
>>>   mm/page_vma_mapped.c |  2 +-
>>>   3 files changed, 33 insertions(+), 7 deletions(-)
>>>
>>> diff --git a/mm/internal.h b/mm/internal.h
>>> index cd3675c044e0..a277bf4841f8 100644
>>> --- a/mm/internal.h
>>> +++ b/mm/internal.h
>>> @@ -592,6 +592,7 @@ void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte);
>>>    * sync_with_folio_pmd_zap - sync with concurrent zapping of folios
>>>    * @mm: The mm_struct.
>>>    * @pmdp: Pointer to the pmd that was found to be pmd_none().
>>> + * @nr_pages: The number of pages in the folio.
>>>    *
>>>    * When we find a pmd_none() while unmapping a folio without holding the PTL,
>>>    * zap_huge_pmd() may have cleared the PMD but not yet updated the folio
>>> @@ -600,13 +601,30 @@ void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte);
>>>    * against later mapcount reads. Skipping the PMD without synchronization
>>>    * could make folio unmapping code assume that unmapping failed.
>>>    *
>>> - * Wait for concurrent zapping to complete by grabbing the PTL.
>>> + * Wait for concurrent zapping to complete by grabbing the PTL for PMD-sized
>>> + * folios, otherwise smp_rmb() is sufficient.
>>>    */
>>> -static inline void sync_with_folio_pmd_zap(struct mm_struct *mm, pmd_t *pmdp)
>>> +static inline void sync_with_folio_pmd_zap(struct mm_struct *mm, pmd_t *pmdp,
>>> +		unsigned int nr_pages)
>>>   {
>>> -	spinlock_t *ptl = pmd_lock(mm, pmdp);
>>> +	if (nr_pages >= HPAGE_PMD_NR) {
>>> +		spinlock_t *ptl = pmd_lock(mm, pmdp);
>>>   
>>> -	spin_unlock(ptl);
>>> +		spin_unlock(ptl);
>>> +		return;
>>> +	}
>>> +
>>> +	/*
>>> +	 * For non PMD-sized folios zapping, concurrent zap_empty_pte_table()
>>> +	 * may clear the PMD after the rmaps for the table have been removed,
>>> +	 * but later mapcount reads could still be observed before the PMD
>>> +	 * read, making the folio appear to be still mapped after unmapping.
>>> +	 * Order the PMD read before later mapcount reads, so that observing
>>> +	 * the cleared PMD implies observing the rmap removals.
>>> +	 *
>>> +	 * Pairs with smp_wmb() in zap_pte_range().
>>> +	 */
>>> +	smp_rmb();
>>>   }
>>>   
>>>   struct zap_details;
>>> diff --git a/mm/memory.c b/mm/memory.c
>>> index fe72e66c9c2e..1ee286cdd3af 100644
>>> --- a/mm/memory.c
>>> +++ b/mm/memory.c
>>> @@ -2054,8 +2054,15 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
>>>   	 * Clear the PMD after the rmaps for the table have been removed, in case
>>>   	 * an incorrect mapcount is observed after unmapping the folio.
>>>   	 */
>>> -	if (can_reclaim_pt && direct_reclaim && addr == end)
>>> +	if (can_reclaim_pt && direct_reclaim && addr == end) {
>>> +		/*
>>> +		 * rmap changes need to be observed before page tables get zapped.
>>> +		 *
>>> +		 * Pairs with smp_rmb() in sync_with_folio_pmd_zap().
>>> +		 */
>>> +		smp_wmb();
>>>   		direct_reclaim = zap_empty_pte_table(mm, pmd, ptl, &pmdval);
>>> +	}
>>>   	pte_unmap_unlock(start_pte, ptl);
>>>   
>>>   	/*
>>> @@ -2110,7 +2117,8 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
>>>   			/* fall through */
>>>   		} else if (pmd_none(*pmd)) {
>>>   			if (details && details->single_folio)
>>> -				sync_with_folio_pmd_zap(tlb->mm, pmd);
>>> +				sync_with_folio_pmd_zap(tlb->mm, pmd,
>>> +						folio_nr_pages(details->single_folio));
>>>   			addr = next;
>>>   			continue;
>>>   		}
>>> diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
>>> index a931243ca42b..d793ad0c5364 100644
>>> --- a/mm/page_vma_mapped.c
>>> +++ b/mm/page_vma_mapped.c
>>> @@ -295,7 +295,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
>>>   			pvmw->ptl = NULL;
>>>   		} else if (!pmd_present(pmde)) {
>>>   			if (pvmw->flags & PVMW_SYNC)
>>> -				sync_with_folio_pmd_zap(mm, pvmw->pmd);
>>> +				sync_with_folio_pmd_zap(mm, pvmw->pmd, pvmw->nr_pages);
>>>
>>
>> If there is no folio, why do we care about the sync? Should there be a folio
>> here? Anyhow, I think sync_with_folio_pmd_zap() really should be consuming a folio.
> 
> Since there are only two cases without a folio: 
> mapping_wrprotect_range() and pfn_mkclean_range(), I'm hesitant to 
> modify all page_vma_mapped_walk() callers to pass in a 'folio' parameter 
> for these 2 cases.
> 
> Or should we add a new flag for the pfn walk?
> 
> / Walk a PFN range which need not belong to a folio /
> #define PVMW_PFN		(1 << 2)
> 
> Then the changes would be:
> } else if (!pmd_present(pmde)) {
> 	if ((pvmw->flags & (PVMW_SYNC | PVMW_PFN)) == PVMW_SYNC)
> 		sync_with_folio_pmd_zap(mm, pvmw->pmd,
>                              pfn_folio(pvmw->pfn));
If we're working on a folio, we better pass in a folio. That might require some cleanups, yes.

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 52fff8dc74213..80fb7ef9bab92 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -884,6 +884,7 @@ struct page *make_device_exclusive(struct mm_struct *mm, unsigned long addr,
 #define PVMW_PGTABLE_CROSSED   (1 << 16)

 struct page_vma_mapped_walk {
+       struct folio *folio;
        unsigned long pfn;
        unsigned long nr_pages;
        pgoff_t pgoff;  /* Only meaningful if nr_pages > 1 and not a KSM walk */
@@ -898,6 +899,7 @@ struct page_vma_mapped_walk {

 #define DEFINE_FOLIO_VMA_WALK(name, _folio, _vma, _address, _flags)    \
        struct page_vma_mapped_walk name = {                            \
+               .folio = folio,                                         \
                .pfn = folio_pfn(_folio),                               \
                .nr_pages = folio_nr_pages(_folio),                     \
                .pgoff = folio_pgoff(_folio),                           \


The question is really whether pfn_mkclean_range + mapping_wrprotect_range really need that
sync as well.

(we could identify by seeing !folio I guess)

-- 
Cheers,

David