@@ -30,7 +30,7 @@ static void mte_sync_page_tags(struct page *page, pte_t *ptep, bool check_swap)
{
pte_t old_pte = READ_ONCE(*ptep);
- if (check_swap && is_swap_pte(old_pte)) {
+ if (check_swap && pte_has_swap_entry(old_pte)) {
swp_entry_t entry = pte_to_swp_entry(old_pte);
if (!non_swap_entry(entry) && mte_restore_tags(entry, page))
@@ -498,7 +498,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
if (pte_present(*pte)) {
page = vm_normal_page(vma, addr, *pte);
- } else if (is_swap_pte(*pte)) {
+ } else if (pte_has_swap_entry(*pte)) {
swp_entry_t swpent = pte_to_swp_entry(*pte);
if (!non_swap_entry(swpent)) {
@@ -518,8 +518,10 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
page = migration_entry_to_page(swpent);
else if (is_device_private_entry(swpent))
page = device_private_entry_to_page(swpent);
- } else if (unlikely(IS_ENABLED(CONFIG_SHMEM) && mss->check_shmem_swap
- && pte_none(*pte))) {
+ } else if (unlikely(IS_ENABLED(CONFIG_SHMEM) &&
+ mss->check_shmem_swap &&
+ /* Here swap special pte is the same as none pte */
+ (pte_none(*pte) || is_swap_special_pte(*pte)))) {
page = xa_load(&vma->vm_file->f_mapping->i_pages,
linear_page_index(vma, addr));
if (xa_is_value(page))
@@ -691,7 +693,7 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
if (pte_present(*pte)) {
page = vm_normal_page(vma, addr, *pte);
- } else if (is_swap_pte(*pte)) {
+ } else if (pte_has_swap_entry(*pte)) {
swp_entry_t swpent = pte_to_swp_entry(*pte);
if (is_migration_entry(swpent))
@@ -1075,7 +1077,7 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
ptent = pte_wrprotect(old_pte);
ptent = pte_clear_soft_dirty(ptent);
ptep_modify_prot_commit(vma, addr, pte, old_pte, ptent);
- } else if (is_swap_pte(ptent)) {
+ } else if (pte_has_swap_entry(ptent)) {
ptent = pte_swp_clear_soft_dirty(ptent);
set_pte_at(vma->vm_mm, addr, pte, ptent);
}
@@ -1375,7 +1377,7 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
page = vm_normal_page(vma, addr, pte);
if (pte_soft_dirty(pte))
flags |= PM_SOFT_DIRTY;
- } else if (is_swap_pte(pte)) {
+ } else if (pte_has_swap_entry(pte)) {
swp_entry_t entry;
if (pte_swp_soft_dirty(pte))
flags |= PM_SOFT_DIRTY;
@@ -5,6 +5,7 @@
#include <linux/radix-tree.h>
#include <linux/bug.h>
#include <linux/mm_types.h>
+#include <linux/userfaultfd_k.h>
#ifdef CONFIG_MMU
@@ -52,12 +53,48 @@ static inline pgoff_t swp_offset(swp_entry_t entry)
return entry.val & SWP_OFFSET_MASK;
}
-/* check whether a pte points to a swap entry */
+/*
+ * is_swap_pte() returns true for three cases:
+ *
+ * (a) The pte contains a swap entry.
+ *
+ * (a.1) The pte has a normal swap entry (non_swap_entry()==false). For
+ * example, when an anonymous page got swapped out.
+ *
+ * (a.2) The pte has a special swap entry (non_swap_entry()==true). For
+ * example, a migration entry, a hw-poison entry, etc.
+ *
+ * (b) The pte does not contain a swap entry at all (so it cannot be passed
+ * into pte_to_swp_entry()). For example, uffd-wp special swap pte.
+ */
static inline int is_swap_pte(pte_t pte)
{
return !pte_none(pte) && !pte_present(pte);
}
+/*
+ * A swap-like special pte should only be used as special marker to trigger a
+ * page fault. We should treat them similarly as pte_none() in most cases,
+ * except that it may contain some special information that can persist within
+ * the pte. Currently the only special swap pte is UFFD_WP_SWP_PTE_SPECIAL.
+ *
+ * Note: we should never call pte_to_swp_entry() upon a special swap pte,
+ * Because a swap special pte does not contain a swap entry!
+ */
+static inline bool is_swap_special_pte(pte_t pte)
+{
+ return pte_swp_uffd_wp_special(pte);
+}
+
+/*
+ * Returns true if the pte contains a swap entry. This includes not only the
+ * normal swp entry case, but also for migration entries, etc.
+ */
+static inline bool pte_has_swap_entry(pte_t pte)
+{
+ return is_swap_pte(pte) && !is_swap_special_pte(pte);
+}
+
/*
* Convert the arch-dependent pte representation of a swp_entry_t into an
* arch-independent swp_entry_t.
@@ -474,7 +474,7 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
*/
if (likely(!(flags & FOLL_MIGRATION)))
goto no_page;
- if (pte_none(pte))
+ if (!pte_has_swap_entry(pte))
goto no_page;
entry = pte_to_swp_entry(pte);
if (!is_migration_entry(entry))
@@ -237,7 +237,7 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
pte_t pte = *ptep;
uint64_t pfn_req_flags = *hmm_pfn;
- if (pte_none(pte)) {
+ if (pte_none(pte) || is_swap_special_pte(pte)) {
required_fault =
hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0);
if (required_fault)
@@ -1019,7 +1019,7 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
vmf.pte = pte_offset_map(pmd, address);
vmf.orig_pte = *vmf.pte;
- if (!is_swap_pte(vmf.orig_pte)) {
+ if (!pte_has_swap_entry(vmf.orig_pte)) {
pte_unmap(vmf.pte);
continue;
}
@@ -1248,6 +1248,15 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
_pte++, _address += PAGE_SIZE) {
pte_t pteval = *_pte;
if (is_swap_pte(pteval)) {
+ if (is_swap_special_pte(pteval)) {
+ /*
+ * Reuse SCAN_PTE_UFFD_WP. If there will be
+ * new users of is_swap_special_pte(), we'd
+ * better introduce a new result type.
+ */
+ result = SCAN_PTE_UFFD_WP;
+ goto out_unmap;
+ }
if (++unmapped <= khugepaged_max_ptes_swap) {
/*
* Always be strict with uffd-wp
@@ -202,7 +202,7 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
pte = *(orig_pte + ((index - start) / PAGE_SIZE));
pte_unmap_unlock(orig_pte, ptl);
- if (pte_present(pte) || pte_none(pte))
+ if (!pte_has_swap_entry(pte))
continue;
entry = pte_to_swp_entry(pte);
if (unlikely(non_swap_entry(entry)))
@@ -594,7 +594,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
for (; addr != end; pte++, addr += PAGE_SIZE) {
ptent = *pte;
- if (pte_none(ptent))
+ if (pte_none(ptent) || is_swap_special_pte(ptent))
continue;
/*
* If the pte has swp_entry, just clear page table to
@@ -5558,7 +5558,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
if (pte_present(ptent))
page = mc_handle_present_pte(vma, addr, ptent);
- else if (is_swap_pte(ptent))
+ else if (pte_has_swap_entry(ptent))
page = mc_handle_swap_pte(vma, ptent, &ent);
else if (pte_none(ptent))
page = mc_handle_file_pte(vma, addr, ptent, &ent);
@@ -3312,6 +3312,13 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
if (!pte_unmap_same(vmf))
goto out;
+ /*
+ * We should never call do_swap_page upon a swap special pte; just be
+ * safe to bail out if it happens.
+ */
+ if (WARN_ON_ONCE(is_swap_special_pte(vmf->orig_pte)))
+ goto out;
+
entry = pte_to_swp_entry(vmf->orig_pte);
if (unlikely(non_swap_entry(entry))) {
if (is_migration_entry(entry)) {
@@ -314,7 +314,7 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
spin_lock(ptl);
pte = *ptep;
- if (!is_swap_pte(pte))
+ if (!pte_has_swap_entry(pte))
goto out;
entry = pte_to_swp_entry(pte);
@@ -2425,7 +2425,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
pte = *ptep;
- if (pte_none(pte)) {
+ if (pte_none(pte) || is_swap_special_pte(pte)) {
if (vma_is_anonymous(vma)) {
mpfn = MIGRATE_PFN_MIGRATE;
migrate->cpages++;
@@ -121,7 +121,7 @@ static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
for (; addr != end; ptep++, addr += PAGE_SIZE) {
pte_t pte = *ptep;
- if (pte_none(pte))
+ if (pte_none(pte) || is_swap_special_pte(pte))
__mincore_unmapped_range(addr, addr + PAGE_SIZE,
vma, vec);
else if (pte_present(pte))
@@ -139,7 +139,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
}
ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent);
pages++;
- } else if (is_swap_pte(oldpte)) {
+ } else if (pte_has_swap_entry(oldpte)) {
swp_entry_t entry = pte_to_swp_entry(oldpte);
pte_t newpte;
@@ -124,7 +124,7 @@ static pte_t move_soft_dirty_pte(pte_t pte)
#ifdef CONFIG_MEM_SOFT_DIRTY
if (pte_present(pte))
pte = pte_mksoft_dirty(pte);
- else if (is_swap_pte(pte))
+ else if (pte_has_swap_entry(pte))
pte = pte_swp_mksoft_dirty(pte);
#endif
return pte;
@@ -36,7 +36,7 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw)
* For more details on device private memory see HMM
* (include/linux/hmm.h or mm/hmm.c).
*/
- if (is_swap_pte(*pvmw->pte)) {
+ if (pte_has_swap_entry(*pvmw->pte)) {
swp_entry_t entry;
/* Handle un-addressable ZONE_DEVICE memory */
@@ -89,7 +89,7 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw)
if (pvmw->flags & PVMW_MIGRATION) {
swp_entry_t entry;
- if (!is_swap_pte(*pvmw->pte))
+ if (!pte_has_swap_entry(*pvmw->pte))
return false;
entry = pte_to_swp_entry(*pvmw->pte);
@@ -97,7 +97,7 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw)
return false;
pfn = migration_entry_to_pfn(entry);
- } else if (is_swap_pte(*pvmw->pte)) {
+ } else if (pte_has_swap_entry(*pvmw->pte)) {
swp_entry_t entry;
/* Handle un-addressable ZONE_DEVICE memory */
@@ -1964,7 +1964,7 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
si = swap_info[type];
pte = pte_offset_map(pmd, addr);
do {
- if (!is_swap_pte(*pte))
+ if (!pte_has_swap_entry(*pte))
continue;
entry = pte_to_swp_entry(*pte);
We used to have special swap entries, like migration entries, hw-poison entries, device private entries, etc. Those "special swap entries" reside in the range that they need to be at least swap entries first, and their types are decided by swp_type(entry). This patch introduces another idea called "special swap ptes". It's very easy to get confused against "special swap entries", but a speical swap pte should never contain a swap entry at all. It means, it's illegal to call pte_to_swp_entry() upon a special swap pte. Make the uffd-wp special pte to be the first special swap pte. Before this patch, is_swap_pte()==true means one of the below: (a.1) The pte has a normal swap entry (non_swap_entry()==false). For example, when an anonymous page got swapped out. (a.2) The pte has a special swap entry (non_swap_entry()==true). For example, a migration entry, a hw-poison entry, etc. After this patch, is_swap_pte()==true means one of the below, where case (b) is added: (a) The pte contains a swap entry. (a.1) The pte has a normal swap entry (non_swap_entry()==false). For example, when an anonymous page got swapped out. (a.2) The pte has a special swap entry (non_swap_entry()==true). For example, a migration entry, a hw-poison entry, etc. (b) The pte does not contain a swap entry at all (so it cannot be passed into pte_to_swp_entry()). For example, uffd-wp special swap pte. Teach the whole mm core about this new idea. It's done by introducing another helper called pte_has_swap_entry() which stands for case (a.1) and (a.2). Before this patch, it will be the same as is_swap_pte() because there's no special swap pte yet. Now for most of the previous use of is_swap_entry() in mm core, we'll need to use the new helper pte_has_swap_entry() instead, to make sure we won't try to parse a swap entry from a swap special pte (which does not contain a swap entry at all!). We either handle the swap special pte, or it'll naturally use the default "else" paths. Warn properly (e.g., in do_swap_page()) when we see a special swap pte - we should never call do_swap_page() upon those ptes, but just to bail out early if it happens. Signed-off-by: Peter Xu <peterx@redhat.com> --- arch/arm64/kernel/mte.c | 2 +- fs/proc/task_mmu.c | 14 ++++++++------ include/linux/swapops.h | 39 ++++++++++++++++++++++++++++++++++++++- mm/gup.c | 2 +- mm/hmm.c | 2 +- mm/khugepaged.c | 11 ++++++++++- mm/madvise.c | 4 ++-- mm/memcontrol.c | 2 +- mm/memory.c | 7 +++++++ mm/migrate.c | 4 ++-- mm/mincore.c | 2 +- mm/mprotect.c | 2 +- mm/mremap.c | 2 +- mm/page_vma_mapped.c | 6 +++--- mm/swapfile.c | 2 +- 15 files changed, 78 insertions(+), 23 deletions(-)