mm: do_zap_pte_range: return any_skipped information to the caller

Let the caller of do_zap_pte_range() know whether we skip zap ptes or
reinstall uffd-wp ptes through any_skipped parameter, so that subsequent
commits can use this information in zap_pte_range() to detect whether the
PTE page can be reclaimed.

Link: https://lkml.kernel.org/r/59f33ec9f74e9f058ed319b0bfadd76b0f7adf9b.1733305182.git.zhengqi.arch@bytedance.com
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Peter Xu <peterx@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will@kernel.org>
Cc: Zach O'Keefe <zokeefe@google.com>
Cc: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/memory.c b/mm/memory.c
index 67406cb662eae11ac99f0f87d18dec1b4732418b..694156ecaf9563ee2abe987e6d98cc0a921ef18e 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1501,7 +1501,7 @@ static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb,
                struct vm_area_struct *vma, struct folio *folio,
                struct page *page, pte_t *pte, pte_t ptent, unsigned int nr,
                unsigned long addr, struct zap_details *details, int *rss,
-               bool *force_flush, bool *force_break)
+               bool *force_flush, bool *force_break, bool *any_skipped)
 {
        struct mm_struct *mm = tlb->mm;
        bool delay_rmap = false;
@@ -1527,8 +1527,8 @@ static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb,
        arch_check_zapped_pte(vma, ptent);
        tlb_remove_tlb_entries(tlb, pte, nr, addr);
        if (unlikely(userfaultfd_pte_wp(vma, ptent)))
-               zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details,
-                                             ptent);
+               *any_skipped = zap_install_uffd_wp_if_needed(vma, addr, pte,
+                                                            nr, details, ptent);
 
        if (!delay_rmap) {
                folio_remove_rmap_ptes(folio, page, nr, vma);
@@ -1552,7 +1552,7 @@ static inline int zap_present_ptes(struct mmu_gather *tlb,
                struct vm_area_struct *vma, pte_t *pte, pte_t ptent,
                unsigned int max_nr, unsigned long addr,
                struct zap_details *details, int *rss, bool *force_flush,
-               bool *force_break)
+               bool *force_break, bool *any_skipped)
 {
        const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY;
        struct mm_struct *mm = tlb->mm;
@@ -1567,15 +1567,17 @@ static inline int zap_present_ptes(struct mmu_gather *tlb,
                arch_check_zapped_pte(vma, ptent);
                tlb_remove_tlb_entry(tlb, pte, addr);
                if (userfaultfd_pte_wp(vma, ptent))
-                       zap_install_uffd_wp_if_needed(vma, addr, pte, 1,
-                                                     details, ptent);
+                       *any_skipped = zap_install_uffd_wp_if_needed(vma, addr,
+                                               pte, 1, details, ptent);
                ksm_might_unmap_zero_page(mm, ptent);
                return 1;
        }
 
        folio = page_folio(page);
-       if (unlikely(!should_zap_folio(details, folio)))
+       if (unlikely(!should_zap_folio(details, folio))) {
+               *any_skipped = true;
                return 1;
+       }
 
        /*
         * Make sure that the common "small folio" case is as fast as possible
@@ -1587,22 +1589,23 @@ static inline int zap_present_ptes(struct mmu_gather *tlb,
 
                zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, nr,
                                       addr, details, rss, force_flush,
-                                      force_break);
+                                      force_break, any_skipped);
                return nr;
        }
        zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, 1, addr,
-                              details, rss, force_flush, force_break);
+                              details, rss, force_flush, force_break, any_skipped);
        return 1;
 }
 
 static inline int zap_nonpresent_ptes(struct mmu_gather *tlb,
                struct vm_area_struct *vma, pte_t *pte, pte_t ptent,
                unsigned int max_nr, unsigned long addr,
-               struct zap_details *details, int *rss)
+               struct zap_details *details, int *rss, bool *any_skipped)
 {
        swp_entry_t entry;
        int nr = 1;
 
+       *any_skipped = true;
        entry = pte_to_swp_entry(ptent);
        if (is_device_private_entry(entry) ||
                is_device_exclusive_entry(entry)) {
@@ -1660,7 +1663,7 @@ static inline int zap_nonpresent_ptes(struct mmu_gather *tlb,
                WARN_ON_ONCE(1);
        }
        clear_not_present_full_ptes(vma->vm_mm, addr, pte, nr, tlb->fullmm);
-       zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details, ptent);
+       *any_skipped = zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details, ptent);
 
        return nr;
 }
@@ -1669,7 +1672,8 @@ static inline int do_zap_pte_range(struct mmu_gather *tlb,
                                   struct vm_area_struct *vma, pte_t *pte,
                                   unsigned long addr, unsigned long end,
                                   struct zap_details *details, int *rss,
-                                  bool *force_flush, bool *force_break)
+                                  bool *force_flush, bool *force_break,
+                                  bool *any_skipped)
 {
        pte_t ptent = ptep_get(pte);
        int max_nr = (end - addr) / PAGE_SIZE;
@@ -1691,10 +1695,11 @@ static inline int do_zap_pte_range(struct mmu_gather *tlb,
 
        if (pte_present(ptent))
                nr += zap_present_ptes(tlb, vma, pte, ptent, max_nr, addr,
-                                      details, rss, force_flush, force_break);
+                                      details, rss, force_flush, force_break,
+                                      any_skipped);
        else
                nr += zap_nonpresent_ptes(tlb, vma, pte, ptent, max_nr, addr,
-                                         details, rss);
+                                         details, rss, any_skipped);
 
        return nr;
 }
@@ -1705,6 +1710,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
                                struct zap_details *details)
 {
        bool force_flush = false, force_break = false;
+       bool any_skipped = false;
        struct mm_struct *mm = tlb->mm;
        int rss[NR_MM_COUNTERS];
        spinlock_t *ptl;
@@ -1725,7 +1731,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
                        break;
 
                nr = do_zap_pte_range(tlb, vma, pte, addr, end, details, rss,
-                                     &force_flush, &force_break);
+                                     &force_flush, &force_break, &any_skipped);
                if (unlikely(force_break)) {
                        addr += nr * PAGE_SIZE;
                        break;