Commit fabc0e8d authored by Qi Zheng's avatar Qi Zheng Committed by Andrew Morton
Browse files

mm: introduce zap_nonpresent_ptes() 

Similar to zap_present_ptes(), let's introduce zap_nonpresent_ptes() to
handle non-present ptes, which can improve code readability.

No functional change.

Link: https://lkml.kernel.org/r/009ca882036d9c7a9f815489cfeafe0bdb79d62d.1733305182.git.zhengqi.arch@bytedance.com


Signed-off-by: default avatarQi Zheng <zhengqi.arch@bytedance.com>
Reviewed-by: default avatarJann Horn <jannh@google.com>
Acked-by: default avatarDavid 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: 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: default avatarAndrew Morton <akpm@linux-foundation.org>
parent dd95d278

mm/memory.c

+73 −63
Original line number Diff line number Diff line
@@ -1587,60 +1587,22 @@ static inline int zap_present_ptes(struct mmu_gather *tlb, 
	return 1;

}



static unsigned long zap_pte_range(struct mmu_gather *tlb,

				struct vm_area_struct *vma, pmd_t *pmd,

				unsigned long addr, unsigned long end,

				struct zap_details *details)

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)

{

	bool force_flush = false, force_break = false;

	struct mm_struct *mm = tlb->mm;

	int rss[NR_MM_COUNTERS];

	spinlock_t *ptl;

	pte_t *start_pte;

	pte_t *pte;

	swp_entry_t entry;

	int nr;



	tlb_change_page_size(tlb, PAGE_SIZE);

	init_rss_vec(rss);

	start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);

	if (!pte)

		return addr;



	flush_tlb_batched_pending(mm);

	arch_enter_lazy_mmu_mode();

	do {

		pte_t ptent = ptep_get(pte);

		struct folio *folio;

		struct page *page;

		int max_nr;



		nr = 1;

		if (pte_none(ptent))

			continue;



		if (need_resched())

			break;



		if (pte_present(ptent)) {

			max_nr = (end - addr) / PAGE_SIZE;

			nr = zap_present_ptes(tlb, vma, pte, ptent, max_nr,

					      addr, details, rss, &force_flush,

					      &force_break);

			if (unlikely(force_break)) {

				addr += nr * PAGE_SIZE;

				break;

			}

			continue;

		}

	int nr = 1;



	entry = pte_to_swp_entry(ptent);

	if (is_device_private_entry(entry) ||

		is_device_exclusive_entry(entry)) {

			page = pfn_swap_entry_to_page(entry);

			folio = page_folio(page);

		struct page *page = pfn_swap_entry_to_page(entry);

		struct folio *folio = page_folio(page);



		if (unlikely(!should_zap_folio(details, folio)))

				continue;

			return 1;

		/*

		 * Both device private/exclusive mappings should only

		 * work with anonymous page so far, so we don't need to
@@ -1653,26 +1615,26 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, 
			folio_remove_rmap_pte(folio, page, vma);

		folio_put(folio);

	} else if (!non_swap_entry(entry)) {

			max_nr = (end - addr) / PAGE_SIZE;

			nr = swap_pte_batch(pte, max_nr, ptent);

		/* Genuine swap entries, hence a private anon pages */

		if (!should_zap_cows(details))

				continue;

			return 1;



		nr = swap_pte_batch(pte, max_nr, ptent);

		rss[MM_SWAPENTS] -= nr;

		free_swap_and_cache_nr(entry, nr);

	} else if (is_migration_entry(entry)) {

			folio = pfn_swap_entry_folio(entry);

		struct folio *folio = pfn_swap_entry_folio(entry);



		if (!should_zap_folio(details, folio))

				continue;

			return 1;

		rss[mm_counter(folio)]--;

	} else if (pte_marker_entry_uffd_wp(entry)) {

		/*

		 * For anon: always drop the marker; for file: only

		 * drop the marker if explicitly requested.

		 */

			if (!vma_is_anonymous(vma) &&

			    !zap_drop_markers(details))

				continue;

		if (!vma_is_anonymous(vma) && !zap_drop_markers(details))

			return 1;

	} else if (is_guard_swp_entry(entry)) {

		/*

		 * Ordinary zapping should not remove guard PTE
@@ -1680,18 +1642,66 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, 
		 * in general.

		 */

		if (!zap_drop_markers(details))

				continue;

		} else if (is_hwpoison_entry(entry) ||

			   is_poisoned_swp_entry(entry)) {

			return 1;

	} else if (is_hwpoison_entry(entry) || is_poisoned_swp_entry(entry)) {

		if (!should_zap_cows(details))

				continue;

			return 1;

	} else {

		/* We should have covered all the swap entry types */

		pr_alert("unrecognized swap entry 0x%lx\n", entry.val);

		WARN_ON_ONCE(1);

	}

		clear_not_present_full_ptes(mm, addr, pte, nr, tlb->fullmm);

	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);



	return nr;

}



static unsigned long zap_pte_range(struct mmu_gather *tlb,

				struct vm_area_struct *vma, pmd_t *pmd,

				unsigned long addr, unsigned long end,

				struct zap_details *details)

{

	bool force_flush = false, force_break = false;

	struct mm_struct *mm = tlb->mm;

	int rss[NR_MM_COUNTERS];

	spinlock_t *ptl;

	pte_t *start_pte;

	pte_t *pte;

	int nr;



	tlb_change_page_size(tlb, PAGE_SIZE);

	init_rss_vec(rss);

	start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);

	if (!pte)

		return addr;



	flush_tlb_batched_pending(mm);

	arch_enter_lazy_mmu_mode();

	do {

		pte_t ptent = ptep_get(pte);

		int max_nr;



		nr = 1;

		if (pte_none(ptent))

			continue;



		if (need_resched())

			break;



		max_nr = (end - addr) / PAGE_SIZE;

		if (pte_present(ptent)) {

			nr = zap_present_ptes(tlb, vma, pte, ptent, max_nr,

					      addr, details, rss, &force_flush,

					      &force_break);

			if (unlikely(force_break)) {

				addr += nr * PAGE_SIZE;

				break;

			}

		} else {

			nr = zap_nonpresent_ptes(tlb, vma, pte, ptent, max_nr,

						 addr, details, rss);

		}

	} while (pte += nr, addr += PAGE_SIZE * nr, addr != end);



	add_mm_rss_vec(mm, rss);