mm: skip over all consecutive none ptes in do_zap_pte_range()

Skip over all consecutive none ptes in do_zap_pte_range(), which helps
optimize away need_resched() + force_break + incremental pte/addr
increments etc.

Link: https://lkml.kernel.org/r/8ecffbf990afd1c8ccc195a2ec321d55f0923908.1733305182.git.zhengqi.arch@bytedance.com
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Suggested-by: David Hildenbrand <david@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.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 378576e..576eb9c 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1665,17 +1665,30 @@ static inline int do_zap_pte_range(struct mmu_gather *tlb,
 {
        pte_t ptent = ptep_get(pte);
        int max_nr = (end - addr) / PAGE_SIZE;
+       int nr = 0;
 
-       if (pte_none(ptent))
-               return 1;
+       /* Skip all consecutive none ptes */
+       if (pte_none(ptent)) {
+               for (nr = 1; nr < max_nr; nr++) {
+                       ptent = ptep_get(pte + nr);
+                       if (!pte_none(ptent))
+                               break;
+               }
+               max_nr -= nr;
+               if (!max_nr)
+                       return nr;
+               pte += nr;
+               addr += nr * PAGE_SIZE;
+       }
 
        if (pte_present(ptent))
-               return zap_present_ptes(tlb, vma, pte, ptent, max_nr,
-                                       addr, details, rss, force_flush,
-                                       force_break);
+               nr += zap_present_ptes(tlb, vma, pte, ptent, max_nr, addr,
+                                      details, rss, force_flush, force_break);
+       else
+               nr += zap_nonpresent_ptes(tlb, vma, pte, ptent, max_nr, addr,
+                                         details, rss);
 
-       return zap_nonpresent_ptes(tlb, vma, pte, ptent, max_nr, addr,
-                                        details, rss);
+       return nr;
 }
 
 static unsigned long zap_pte_range(struct mmu_gather *tlb,