// SPDX-License-Identifier: GPL-2.0/* * Memory Migration functionality - linux/mm/migrate.c * * Copyright (C) 2006 Silicon Graphics, Inc., Christoph Lameter * * Page migration was first developed in the context of the memory hotplug * project. The main authors of the migration code are: * * IWAMOTO Toshihiro <iwamoto@valinux.co.jp> * Hirokazu Takahashi <taka@valinux.co.jp> * Dave Hansen <haveblue@us.ibm.com> * Christoph Lameter */ #include <linux/migrate.h>#include <linux/export.h>#include <linux/swap.h>#include <linux/leafops.h>#include <linux/pagemap.h>#include <linux/buffer_head.h>#include <linux/mm_inline.h>#include <linux/ksm.h>#include <linux/rmap.h>#include <linux/topology.h>#include <linux/cpu.h>#include <linux/cpuset.h>#include <linux/writeback.h>#include <linux/mempolicy.h>#include <linux/vmalloc.h>#include <linux/security.h>#include <linux/backing-dev.h>#include <linux/compaction.h>#include <linux/syscalls.h>#include <linux/compat.h>#include <linux/hugetlb.h>#include <linux/gfp.h>#include <linux/page_idle.h>#include <linux/page_owner.h>#include <linux/sched/mm.h>#include <linux/ptrace.h>#include <linux/memory.h>#include <linux/sched/sysctl.h>#include <linux/memory-tiers.h>#include <linux/pagewalk.h> #include <asm/tlbflush.h> #include <trace/events/migrate.h> #include "internal.h"#include "page_alloc.h"#include "swap.h" static const struct movable_operations *offline_movable_ops;static const struct movable_operations *zsmalloc_movable_ops; int set_movable_ops(const struct movable_operations *ops, enum pagetype type){ /* * We only allow for selected types and don't handle concurrent * registration attempts yet. */ switch (type) { case PGTY_offline: if (offline_movable_ops && ops) return -EBUSY; offline_movable_ops = ops; break; case PGTY_zsmalloc: if (zsmalloc_movable_ops && ops) return -EBUSY; zsmalloc_movable_ops = ops; break; default: return -EINVAL; } return 0;}EXPORT_SYMBOL_GPL(set_movable_ops); static const struct movable_operations *page_movable_ops(struct page *page){ VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(page), page); /* * If we enable page migration for a page of a certain type by marking * it as movable, the page type must be sticky until the page gets freed * back to the buddy. */ if (PageOffline(page)) /* Only balloon page migration sets PageOffline pages movable. */ return offline_movable_ops; if (PageZsmalloc(page)) return zsmalloc_movable_ops; return NULL;} /** * isolate_movable_ops_page - isolate a movable_ops page for migration * @page: The page. * @mode: The isolation mode. * * Try to isolate a movable_ops page for migration. Will fail if the page is * not a movable_ops page, if the page is already isolated for migration * or if the page was just was released by its owner. * * Once isolated, the page cannot get freed until it is either putback * or migrated. * * Returns true if isolation succeeded, otherwise false. */bool isolate_movable_ops_page(struct page *page, isolate_mode_t mode){ /* * TODO: these pages will not be folios in the future. All * folio dependencies will have to be removed. */ struct folio *folio = folio_get_nontail_page(page); const struct movable_operations *mops; /* * Avoid burning cycles with pages that are yet under __free_pages(), * or just got freed under us. * * In case we 'win' a race for a movable page being freed under us and * raise its refcount preventing __free_pages() from doing its job * the put_page() at the end of this block will take care of * release this page, thus avoiding a nasty leakage. */ if (!folio) goto out; /* * Check for movable_ops pages before taking the page lock because * we use non-atomic bitops on newly allocated page flags so * unconditionally grabbing the lock ruins page's owner side. * * Note that once a page has movable_ops, it will stay that way * until the page was freed. */ if (unlikely(!page_has_movable_ops(page))) goto out_putfolio; /* * As movable pages are not isolated from LRU lists, concurrent * compaction threads can race against page migration functions * as well as race against the releasing a page. * * In order to avoid having an already isolated movable page * being (wrongly) re-isolated while it is under migration, * or to avoid attempting to isolate pages being released, * lets be sure we have the page lock * before proceeding with the movable page isolation steps. */ if (unlikely(!folio_trylock(folio))) goto out_putfolio; VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(page), page); if (PageMovableOpsIsolated(page)) goto out_no_isolated; mops = page_movable_ops(page); if (WARN_ON_ONCE(!mops)) goto out_no_isolated; if (!mops->isolate_page(page, mode)) goto out_no_isolated; /* Driver shouldn't use the isolated flag */ VM_WARN_ON_ONCE_PAGE(PageMovableOpsIsolated(page), page); SetPageMovableOpsIsolated(page); folio_unlock(folio); return true; out_no_isolated: folio_unlock(folio);out_putfolio: folio_put(folio);out: return false;} /** * putback_movable_ops_page - putback an isolated movable_ops page * @page: The isolated page. * * Putback an isolated movable_ops page. * * After the page was putback, it might get freed instantly. */static void putback_movable_ops_page(struct page *page){ /* * TODO: these pages will not be folios in the future. All * folio dependencies will have to be removed. */ struct folio *folio = page_folio(page); VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(page), page); VM_WARN_ON_ONCE_PAGE(!PageMovableOpsIsolated(page), page); folio_lock(folio); page_movable_ops(page)->putback_page(page); ClearPageMovableOpsIsolated(page); folio_unlock(folio); folio_put(folio);} /** * migrate_movable_ops_page - migrate an isolated movable_ops page * @dst: The destination page. * @src: The source page. * @mode: The migration mode. * * Migrate an isolated movable_ops page. * * If the src page was already released by its owner, the src page is * un-isolated (putback) and migration succeeds; the migration core will be the * owner of both pages. * * If the src page was not released by its owner and the migration was * successful, the owner of the src page and the dst page are swapped and * the src page is un-isolated. * * If migration fails, the ownership stays unmodified and the src page * remains isolated: migration may be retried later or the page can be putback. * * TODO: migration core will treat both pages as folios and lock them before * this call to unlock them after this call. Further, the folio refcounts on * src and dst are also released by migration core. These pages will not be * folios in the future, so that must be reworked. * * Returns 0 on success, otherwise a negative error code. */static int migrate_movable_ops_page(struct page *dst, struct page *src, enum migrate_mode mode){ int rc; VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(src), src); VM_WARN_ON_ONCE_PAGE(!PageMovableOpsIsolated(src), src); rc = page_movable_ops(src)->migrate_page(dst, src, mode); if (!rc) ClearPageMovableOpsIsolated(src); return rc;} /* * Put previously isolated pages back onto the appropriate lists * from where they were once taken off for compaction/migration. * * This function shall be used whenever the isolated pageset has been * built from lru, balloon, hugetlbfs page. See isolate_migratepages_range() * and folio_isolate_hugetlb(). */void putback_movable_pages(struct list_head *l){ struct folio *folio; struct folio *folio2; list_for_each_entry_safe(folio, folio2, l, lru) { if (unlikely(folio_test_hugetlb(folio))) { folio_putback_hugetlb(folio); continue; } list_del(&folio->lru); if (unlikely(page_has_movable_ops(&folio->page))) { putback_movable_ops_page(&folio->page); } else { node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), -folio_nr_pages(folio)); folio_putback_lru(folio); } }} /* Must be called with an elevated refcount on the non-hugetlb folio */bool isolate_folio_to_list(struct folio *folio, struct list_head *list){ if (folio_test_hugetlb(folio)) return folio_isolate_hugetlb(folio, list); if (page_has_movable_ops(&folio->page)) { if (!isolate_movable_ops_page(&folio->page, ISOLATE_UNEVICTABLE)) return false; } else { if (!folio_isolate_lru(folio)) return false; node_stat_add_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio)); } list_add(&folio->lru, list); return true;} static bool try_to_map_unused_to_zeropage(struct page_vma_mapped_walk *pvmw, struct folio *folio, pte_t old_pte, unsigned long idx){ struct page *page = folio_page(folio, idx); pte_t newpte; if (PageCompound(page) || PageHWPoison(page)) return false; VM_BUG_ON_PAGE(!PageAnon(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(pte_present(old_pte), page); VM_WARN_ON_ONCE_FOLIO(folio_is_device_private(folio), folio); if (folio_test_mlocked(folio) || (pvmw->vma->vm_flags & VM_LOCKED) || mm_forbids_zeropage(pvmw->vma->vm_mm)) return false; /* * The pmd entry mapping the old thp was flushed and the pte mapping * this subpage has been non present. If the subpage is only zero-filled * then map it to the shared zeropage. */ if (!pages_identical(page, ZERO_PAGE(0))) return false; newpte = pte_mkspecial(pfn_pte(zero_pfn(pvmw->address), pvmw->vma->vm_page_prot)); if (pte_swp_soft_dirty(old_pte)) newpte = pte_mksoft_dirty(newpte); if (pte_swp_uffd(old_pte)) newpte = pte_mkuffd(newpte); /* See remove_migration_pte(): restore PAGE_NONE for RWP */ if (pte_swp_uffd(old_pte) && userfaultfd_rwp(pvmw->vma)) newpte = pte_modify(newpte, PAGE_NONE); set_pte_at(pvmw->vma->vm_mm, pvmw->address, pvmw->pte, newpte); dec_mm_counter(pvmw->vma->vm_mm, mm_counter(folio)); return true;} struct rmap_walk_arg { struct folio *folio; bool map_unused_to_zeropage;}; /* * Restore a potential migration pte to a working pte entry */static bool remove_migration_pte(struct folio *folio, struct vm_area_struct *vma, unsigned long addr, void *arg){ struct rmap_walk_arg *rmap_walk_arg = arg; DEFINE_FOLIO_VMA_WALK(pvmw, rmap_walk_arg->folio, vma, addr, PVMW_SYNC | PVMW_MIGRATION); while (page_vma_mapped_walk(&pvmw)) { rmap_t rmap_flags = RMAP_NONE; unsigned long idx = 0; softleaf_t entry; struct page *new; pte_t old_pte; pte_t pte; #ifdef CONFIG_ARCH_HAS_PMD_SOFTLEAVES /* PMD-mapped THP migration entry */ if (!pvmw.pte) { VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) || !folio_test_pmd_mappable(folio), folio); remove_migration_pmd(&pvmw, folio); continue; }#endif if (folio_test_hugetlb(folio)) old_pte = huge_ptep_get(vma->vm_mm, pvmw.address, pvmw.pte); else old_pte = ptep_get(pvmw.pte); entry = softleaf_from_pte(old_pte); if (folio_test_large(folio) && !folio_test_hugetlb(folio)) idx = softleaf_to_pfn(entry) - pvmw.pfn; if (rmap_walk_arg->map_unused_to_zeropage && try_to_map_unused_to_zeropage(&pvmw, folio, old_pte, idx)) continue; folio_get(folio); new = folio_page(folio, idx); pte = mk_pte(new, READ_ONCE(vma->vm_page_prot)); if (!softleaf_is_migration_young(entry)) pte = pte_mkold(pte); if (folio_test_dirty(folio) && softleaf_is_migration_dirty(entry)) pte = pte_mkdirty(pte); if (pte_swp_soft_dirty(old_pte)) pte = pte_mksoft_dirty(pte); else pte = pte_clear_soft_dirty(pte); if (softleaf_is_migration_write(entry)) pte = pte_mkwrite(pte, vma); else if (pte_swp_uffd(old_pte)) pte = pte_mkuffd(pte); /* See do_swap_page(): restore PAGE_NONE for RWP */ if (pte_swp_uffd(old_pte) && userfaultfd_rwp(vma)) pte = pte_modify(pte, PAGE_NONE); if (folio_test_anon(folio) && !softleaf_is_migration_read(entry)) rmap_flags |= RMAP_EXCLUSIVE; if (unlikely(is_device_private_page(new))) { if (pte_write(pte)) entry = make_writable_device_private_entry( page_to_pfn(new)); else entry = make_readable_device_private_entry( page_to_pfn(new)); pte = softleaf_to_pte(entry); if (pte_swp_soft_dirty(old_pte)) pte = pte_swp_mksoft_dirty(pte); if (pte_swp_uffd(old_pte)) pte = pte_swp_mkuffd(pte); } #ifdef CONFIG_HUGETLB_PAGE if (folio_test_hugetlb(folio)) { struct hstate *h = hstate_vma(vma); unsigned int shift = huge_page_shift(h); unsigned long psize = huge_page_size(h); pte = arch_make_huge_pte(pte, shift, vma->vm_flags); if (folio_test_anon(folio)) hugetlb_add_anon_rmap(folio, vma, pvmw.address, rmap_flags); else hugetlb_add_file_rmap(folio); set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte, psize); } else#endif { if (folio_test_anon(folio)) folio_add_anon_rmap_pte(folio, new, vma, pvmw.address, rmap_flags); else folio_add_file_rmap_pte(folio, new, vma); set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); } if (READ_ONCE(vma->vm_flags) & VM_LOCKED) mlock_drain_local(); trace_remove_migration_pte(pvmw.address, pte_val(pte), compound_order(new)); /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, pvmw.address, pvmw.pte); } return true;} /* * Get rid of all migration entries and replace them by * references to the indicated page. */void remove_migration_ptes(struct folio *src, struct folio *dst, enum ttu_flags flags){ struct rmap_walk_arg rmap_walk_arg = { .folio = src, .map_unused_to_zeropage = flags & TTU_USE_SHARED_ZEROPAGE, }; struct rmap_walk_control rwc = { .rmap_one = remove_migration_pte, .arg = &rmap_walk_arg, }; VM_BUG_ON_FOLIO((flags & TTU_USE_SHARED_ZEROPAGE) && (src != dst), src); if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(dst, &rwc); else rmap_walk(dst, &rwc);} /* * Something used the pte of a page under migration. We need to * get to the page and wait until migration is finished. * When we return from this function the fault will be retried. */void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address){ spinlock_t *ptl; pte_t *ptep; pte_t pte; softleaf_t entry; Lines 1–500 of 2782. Load more
// SPDX-License-Identifier: GPL-2.0 /* * Memory Migration functionality - linux/mm/migrate.c * * Copyright (C) 2006 Silicon Graphics, Inc., Christoph Lameter * * Page migration was first developed in the context of the memory hotplug * project. The main authors of the migration code are: * * IWAMOTO Toshihiro <iwamoto@valinux.co.jp> * Hirokazu Takahashi <taka@valinux.co.jp> * Dave Hansen <haveblue@us.ibm.com> * Christoph Lameter */ #include <linux/migrate.h> #include <linux/export.h> #include <linux/swap.h> #include <linux/leafops.h> #include <linux/pagemap.h> #include <linux/buffer_head.h> #include <linux/mm_inline.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/topology.h> #include <linux/cpu.h> #include <linux/cpuset.h> #include <linux/writeback.h> #include <linux/mempolicy.h> #include <linux/vmalloc.h> #include <linux/security.h> #include <linux/backing-dev.h> #include <linux/compaction.h> #include <linux/syscalls.h> #include <linux/compat.h> #include <linux/hugetlb.h> #include <linux/gfp.h> #include <linux/page_idle.h> #include <linux/page_owner.h> #include <linux/sched/mm.h> #include <linux/ptrace.h> #include <linux/memory.h> #include <linux/sched/sysctl.h> #include <linux/memory-tiers.h> #include <linux/pagewalk.h> #include <asm/tlbflush.h> #include <trace/events/migrate.h> #include "internal.h" #include "page_alloc.h" #include "swap.h" static const struct movable_operations *offline_movable_ops; static const struct movable_operations *zsmalloc_movable_ops; int set_movable_ops(const struct movable_operations *ops, enum pagetype type) { /* * We only allow for selected types and don't handle concurrent * registration attempts yet. */ switch (type) { case PGTY_offline: if (offline_movable_ops && ops) return -EBUSY; offline_movable_ops = ops; break; case PGTY_zsmalloc: if (zsmalloc_movable_ops && ops) return -EBUSY; zsmalloc_movable_ops = ops; break; default: return -EINVAL; } return 0; } EXPORT_SYMBOL_GPL(set_movable_ops); static const struct movable_operations *page_movable_ops(struct page *page) { VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(page), page); /* * If we enable page migration for a page of a certain type by marking * it as movable, the page type must be sticky until the page gets freed * back to the buddy. */ if (PageOffline(page)) /* Only balloon page migration sets PageOffline pages movable. */ return offline_movable_ops; if (PageZsmalloc(page)) return zsmalloc_movable_ops; return NULL; } /** * isolate_movable_ops_page - isolate a movable_ops page for migration * @page: The page. * @mode: The isolation mode. * * Try to isolate a movable_ops page for migration. Will fail if the page is * not a movable_ops page, if the page is already isolated for migration * or if the page was just was released by its owner. * * Once isolated, the page cannot get freed until it is either putback * or migrated. * * Returns true if isolation succeeded, otherwise false. */ bool isolate_movable_ops_page(struct page *page, isolate_mode_t mode) { /* * TODO: these pages will not be folios in the future. All * folio dependencies will have to be removed. */ struct folio *folio = folio_get_nontail_page(page); const struct movable_operations *mops; /* * Avoid burning cycles with pages that are yet under __free_pages(), * or just got freed under us. * * In case we 'win' a race for a movable page being freed under us and * raise its refcount preventing __free_pages() from doing its job * the put_page() at the end of this block will take care of * release this page, thus avoiding a nasty leakage. */ if (!folio) goto out; /* * Check for movable_ops pages before taking the page lock because * we use non-atomic bitops on newly allocated page flags so * unconditionally grabbing the lock ruins page's owner side. * * Note that once a page has movable_ops, it will stay that way * until the page was freed. */ if (unlikely(!page_has_movable_ops(page))) goto out_putfolio; /* * As movable pages are not isolated from LRU lists, concurrent * compaction threads can race against page migration functions * as well as race against the releasing a page. * * In order to avoid having an already isolated movable page * being (wrongly) re-isolated while it is under migration, * or to avoid attempting to isolate pages being released, * lets be sure we have the page lock * before proceeding with the movable page isolation steps. */ if (unlikely(!folio_trylock(folio))) goto out_putfolio; VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(page), page); if (PageMovableOpsIsolated(page)) goto out_no_isolated; mops = page_movable_ops(page); if (WARN_ON_ONCE(!mops)) goto out_no_isolated; if (!mops->isolate_page(page, mode)) goto out_no_isolated; /* Driver shouldn't use the isolated flag */ VM_WARN_ON_ONCE_PAGE(PageMovableOpsIsolated(page), page); SetPageMovableOpsIsolated(page); folio_unlock(folio); return true; out_no_isolated: folio_unlock(folio); out_putfolio: folio_put(folio); out: return false; } /** * putback_movable_ops_page - putback an isolated movable_ops page * @page: The isolated page. * * Putback an isolated movable_ops page. * * After the page was putback, it might get freed instantly. */ static void putback_movable_ops_page(struct page *page) { /* * TODO: these pages will not be folios in the future. All * folio dependencies will have to be removed. */ struct folio *folio = page_folio(page); VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(page), page); VM_WARN_ON_ONCE_PAGE(!PageMovableOpsIsolated(page), page); folio_lock(folio); page_movable_ops(page)->putback_page(page); ClearPageMovableOpsIsolated(page); folio_unlock(folio); folio_put(folio); } /** * migrate_movable_ops_page - migrate an isolated movable_ops page * @dst: The destination page. * @src: The source page. * @mode: The migration mode. * * Migrate an isolated movable_ops page. * * If the src page was already released by its owner, the src page is * un-isolated (putback) and migration succeeds; the migration core will be the * owner of both pages. * * If the src page was not released by its owner and the migration was * successful, the owner of the src page and the dst page are swapped and * the src page is un-isolated. * * If migration fails, the ownership stays unmodified and the src page * remains isolated: migration may be retried later or the page can be putback. * * TODO: migration core will treat both pages as folios and lock them before * this call to unlock them after this call. Further, the folio refcounts on * src and dst are also released by migration core. These pages will not be * folios in the future, so that must be reworked. * * Returns 0 on success, otherwise a negative error code. */ static int migrate_movable_ops_page(struct page *dst, struct page *src, enum migrate_mode mode) { int rc; VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(src), src); VM_WARN_ON_ONCE_PAGE(!PageMovableOpsIsolated(src), src); rc = page_movable_ops(src)->migrate_page(dst, src, mode); if (!rc) ClearPageMovableOpsIsolated(src); return rc; } /* * Put previously isolated pages back onto the appropriate lists * from where they were once taken off for compaction/migration. * * This function shall be used whenever the isolated pageset has been * built from lru, balloon, hugetlbfs page. See isolate_migratepages_range() * and folio_isolate_hugetlb(). */ void putback_movable_pages(struct list_head *l) { struct folio *folio; struct folio *folio2; list_for_each_entry_safe(folio, folio2, l, lru) { if (unlikely(folio_test_hugetlb(folio))) { folio_putback_hugetlb(folio); continue; } list_del(&folio->lru); if (unlikely(page_has_movable_ops(&folio->page))) { putback_movable_ops_page(&folio->page); } else { node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), -folio_nr_pages(folio)); folio_putback_lru(folio); } } } /* Must be called with an elevated refcount on the non-hugetlb folio */ bool isolate_folio_to_list(struct folio *folio, struct list_head *list) { if (folio_test_hugetlb(folio)) return folio_isolate_hugetlb(folio, list); if (page_has_movable_ops(&folio->page)) { if (!isolate_movable_ops_page(&folio->page, ISOLATE_UNEVICTABLE)) return false; } else { if (!folio_isolate_lru(folio)) return false; node_stat_add_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio)); } list_add(&folio->lru, list); return true; } static bool try_to_map_unused_to_zeropage(struct page_vma_mapped_walk *pvmw, struct folio *folio, pte_t old_pte, unsigned long idx) { struct page *page = folio_page(folio, idx); pte_t newpte; if (PageCompound(page) || PageHWPoison(page)) return false; VM_BUG_ON_PAGE(!PageAnon(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(pte_present(old_pte), page); VM_WARN_ON_ONCE_FOLIO(folio_is_device_private(folio), folio); if (folio_test_mlocked(folio) || (pvmw->vma->vm_flags & VM_LOCKED) || mm_forbids_zeropage(pvmw->vma->vm_mm)) return false; /* * The pmd entry mapping the old thp was flushed and the pte mapping * this subpage has been non present. If the subpage is only zero-filled * then map it to the shared zeropage. */ if (!pages_identical(page, ZERO_PAGE(0))) return false; newpte = pte_mkspecial(pfn_pte(zero_pfn(pvmw->address), pvmw->vma->vm_page_prot)); if (pte_swp_soft_dirty(old_pte)) newpte = pte_mksoft_dirty(newpte); if (pte_swp_uffd(old_pte)) newpte = pte_mkuffd(newpte); /* See remove_migration_pte(): restore PAGE_NONE for RWP */ if (pte_swp_uffd(old_pte) && userfaultfd_rwp(pvmw->vma)) newpte = pte_modify(newpte, PAGE_NONE); set_pte_at(pvmw->vma->vm_mm, pvmw->address, pvmw->pte, newpte); dec_mm_counter(pvmw->vma->vm_mm, mm_counter(folio)); return true; } struct rmap_walk_arg { struct folio *folio; bool map_unused_to_zeropage; }; /* * Restore a potential migration pte to a working pte entry */ static bool remove_migration_pte(struct folio *folio, struct vm_area_struct *vma, unsigned long addr, void *arg) { struct rmap_walk_arg *rmap_walk_arg = arg; DEFINE_FOLIO_VMA_WALK(pvmw, rmap_walk_arg->folio, vma, addr, PVMW_SYNC | PVMW_MIGRATION); while (page_vma_mapped_walk(&pvmw)) { rmap_t rmap_flags = RMAP_NONE; unsigned long idx = 0; softleaf_t entry; struct page *new; pte_t old_pte; pte_t pte; #ifdef CONFIG_ARCH_HAS_PMD_SOFTLEAVES /* PMD-mapped THP migration entry */ if (!pvmw.pte) { VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) || !folio_test_pmd_mappable(folio), folio); remove_migration_pmd(&pvmw, folio); continue; } #endif if (folio_test_hugetlb(folio)) old_pte = huge_ptep_get(vma->vm_mm, pvmw.address, pvmw.pte); else old_pte = ptep_get(pvmw.pte); entry = softleaf_from_pte(old_pte); if (folio_test_large(folio) && !folio_test_hugetlb(folio)) idx = softleaf_to_pfn(entry) - pvmw.pfn; if (rmap_walk_arg->map_unused_to_zeropage && try_to_map_unused_to_zeropage(&pvmw, folio, old_pte, idx)) continue; folio_get(folio); new = folio_page(folio, idx); pte = mk_pte(new, READ_ONCE(vma->vm_page_prot)); if (!softleaf_is_migration_young(entry)) pte = pte_mkold(pte); if (folio_test_dirty(folio) && softleaf_is_migration_dirty(entry)) pte = pte_mkdirty(pte); if (pte_swp_soft_dirty(old_pte)) pte = pte_mksoft_dirty(pte); else pte = pte_clear_soft_dirty(pte); if (softleaf_is_migration_write(entry)) pte = pte_mkwrite(pte, vma); else if (pte_swp_uffd(old_pte)) pte = pte_mkuffd(pte); /* See do_swap_page(): restore PAGE_NONE for RWP */ if (pte_swp_uffd(old_pte) && userfaultfd_rwp(vma)) pte = pte_modify(pte, PAGE_NONE); if (folio_test_anon(folio) && !softleaf_is_migration_read(entry)) rmap_flags |= RMAP_EXCLUSIVE; if (unlikely(is_device_private_page(new))) { if (pte_write(pte)) entry = make_writable_device_private_entry( page_to_pfn(new)); else entry = make_readable_device_private_entry( page_to_pfn(new)); pte = softleaf_to_pte(entry); if (pte_swp_soft_dirty(old_pte)) pte = pte_swp_mksoft_dirty(pte); if (pte_swp_uffd(old_pte)) pte = pte_swp_mkuffd(pte); } #ifdef CONFIG_HUGETLB_PAGE if (folio_test_hugetlb(folio)) { struct hstate *h = hstate_vma(vma); unsigned int shift = huge_page_shift(h); unsigned long psize = huge_page_size(h); pte = arch_make_huge_pte(pte, shift, vma->vm_flags); if (folio_test_anon(folio)) hugetlb_add_anon_rmap(folio, vma, pvmw.address, rmap_flags); else hugetlb_add_file_rmap(folio); set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte, psize); } else #endif { if (folio_test_anon(folio)) folio_add_anon_rmap_pte(folio, new, vma, pvmw.address, rmap_flags); else folio_add_file_rmap_pte(folio, new, vma); set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); } if (READ_ONCE(vma->vm_flags) & VM_LOCKED) mlock_drain_local(); trace_remove_migration_pte(pvmw.address, pte_val(pte), compound_order(new)); /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, pvmw.address, pvmw.pte); } return true; } /* * Get rid of all migration entries and replace them by * references to the indicated page. */ void remove_migration_ptes(struct folio *src, struct folio *dst, enum ttu_flags flags) { struct rmap_walk_arg rmap_walk_arg = { .folio = src, .map_unused_to_zeropage = flags & TTU_USE_SHARED_ZEROPAGE, }; struct rmap_walk_control rwc = { .rmap_one = remove_migration_pte, .arg = &rmap_walk_arg, }; VM_BUG_ON_FOLIO((flags & TTU_USE_SHARED_ZEROPAGE) && (src != dst), src); if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(dst, &rwc); else rmap_walk(dst, &rwc); } /* * Something used the pte of a page under migration. We need to * get to the page and wait until migration is finished. * When we return from this function the fault will be retried. */ void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { spinlock_t *ptl; pte_t *ptep; pte_t pte; softleaf_t entry;