Merge tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linuxgrafted

Pull io_uring fixes from Jens Axboe:

 - Fix a task_work add use-after-free with SQPOLL.

   The sqpoll thread could pop and complete the last request while
   io_req_normal_work_add() was still looking at them after the mpscq
   push.

   Use the same approach as DEFER_TASKRUN to protect from that, holding
   an RCU read lock across the add, and have exit wait for an RCU grace
   period for SQPOLL rings as well.

 - CQE32 ring fixes: correct the free entry check for 32b CQEs, zero the
   big_cqe for aux CQEs, and only post the dummy skip CQE on CQE_MIXED
   rings

 - Mark the source filter table as COW when cloning bpf filters, so
   registering another filter on the source doesn't modify the shared
   table in place

 - Initialize the task context before running the BPF loop

 - Requeue zcrx multishot receives stopped by a local resource

 - End a TX_TIMESTAMP multishot cmd when the CQ is full (lollipopkit)

* tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux:
  io_uring: fix task_work add use-after-free with SQPOLL
  io_uring/cmd_net: end TX_TIMESTAMP multishot when the CQ is full
  io_uring/zcrx: requeue multishot receives stopped by a local resource
  io_uring: initialize task context before running the BPF loop
  io_uring: zero big_cqe for aux CQEs on CQE32 rings
  io_uring: fix free entry check for 32b CQEs on CQE32 rings
  io_uring: only post the dummy skip CQE on CQE_MIXED rings
  io_uring/bpf_filter: mark source as COW when cloning filters

1 files changed, 1079 insertions, 0 deletions

diff --git a/mm/mprotect.c b/mm/mprotect.c
new file mode 100644
index 000000000..2888ee638
--- /dev/null
+++ b/mm/mprotect.c
@@ -0,0 +1,1079 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  mm/mprotect.c
+ *
+ *  (C) Copyright 1994 Linus Torvalds
+ *  (C) Copyright 2002 Christoph Hellwig
+ *
+ *  Address space accounting code	<alan@lxorguk.ukuu.org.uk>
+ *  (C) Copyright 2002 Red Hat Inc, All Rights Reserved
+ */
+
+#include <linux/pagewalk.h>
+#include <linux/hugetlb.h>
+#include <linux/shm.h>
+#include <linux/mman.h>
+#include <linux/fs.h>
+#include <linux/highmem.h>
+#include <linux/security.h>
+#include <linux/mempolicy.h>
+#include <linux/personality.h>
+#include <linux/syscalls.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/mmu_notifier.h>
+#include <linux/migrate.h>
+#include <linux/perf_event.h>
+#include <linux/pkeys.h>
+#include <linux/ksm.h>
+#include <linux/uaccess.h>
+#include <linux/mm_inline.h>
+#include <linux/pgtable.h>
+#include <linux/userfaultfd_k.h>
+#include <uapi/linux/mman.h>
+#include <asm/cacheflush.h>
+#include <asm/mmu_context.h>
+#include <asm/tlbflush.h>
+#include <asm/tlb.h>
+
+#include "internal.h"
+
+static bool maybe_change_pte_writable(struct vm_area_struct *vma, pte_t pte)
+{
+	if (WARN_ON_ONCE(!vma_test(vma, VMA_WRITE_BIT)))
+		return false;
+
+	/* Don't touch entries that are not even readable. */
+	if (pte_protnone(pte))
+		return false;
+
+	/* Do we need write faults for softdirty tracking? */
+	if (pte_needs_soft_dirty_wp(vma, pte))
+		return false;
+
+	/* Do we need write faults for uffd-wp tracking? */
+	if (userfaultfd_pte_wp(vma, pte))
+		return false;
+
+	return true;
+}
+
+static bool can_change_private_pte_writable(struct vm_area_struct *vma,
+					    unsigned long addr, pte_t pte)
+{
+	struct page *page;
+
+	if (!maybe_change_pte_writable(vma, pte))
+		return false;
+
+	/*
+	 * Writable MAP_PRIVATE mapping: We can only special-case on
+	 * exclusive anonymous pages, because we know that our
+	 * write-fault handler similarly would map them writable without
+	 * any additional checks while holding the PT lock.
+	 */
+	page = vm_normal_page(vma, addr, pte);
+	return page && PageAnon(page) && PageAnonExclusive(page);
+}
+
+static bool can_change_shared_pte_writable(struct vm_area_struct *vma,
+					   pte_t pte)
+{
+	if (!maybe_change_pte_writable(vma, pte))
+		return false;
+
+	VM_WARN_ON_ONCE(is_zero_pfn(pte_pfn(pte)) && pte_dirty(pte));
+
+	/*
+	 * Writable MAP_SHARED mapping: "clean" might indicate that the FS still
+	 * needs a real write-fault for writenotify
+	 * (see vma_wants_writenotify()). If "dirty", the assumption is that the
+	 * FS was already notified and we can simply mark the PTE writable
+	 * just like the write-fault handler would do.
+	 */
+	return pte_dirty(pte);
+}
+
+bool can_change_pte_writable(struct vm_area_struct *vma, unsigned long addr,
+			     pte_t pte)
+{
+	if (!vma_test(vma, VMA_SHARED_BIT))
+		return can_change_private_pte_writable(vma, addr, pte);
+
+	return can_change_shared_pte_writable(vma, pte);
+}
+
+static int mprotect_folio_pte_batch(struct folio *folio, pte_t *ptep,
+				    pte_t pte, int max_nr_ptes, fpb_t flags)
+{
+	/* No underlying folio, so cannot batch */
+	if (!folio)
+		return 1;
+
+	if (!folio_test_large(folio))
+		return 1;
+
+	return folio_pte_batch_flags(folio, NULL, ptep, &pte, max_nr_ptes, flags);
+}
+
+/* Set nr_ptes number of ptes, starting from idx */
+static __always_inline void prot_commit_flush_ptes(struct vm_area_struct *vma,
+		unsigned long addr, pte_t *ptep, pte_t oldpte, pte_t ptent,
+		int nr_ptes, int idx, bool set_write, struct mmu_gather *tlb)
+{
+	/*
+	 * Advance the position in the batch by idx; note that if idx > 0,
+	 * then the nr_ptes passed here is <= batch size - idx.
+	 */
+	addr += idx * PAGE_SIZE;
+	ptep += idx;
+	oldpte = pte_advance_pfn(oldpte, idx);
+	ptent = pte_advance_pfn(ptent, idx);
+
+	if (set_write)
+		ptent = pte_mkwrite(ptent, vma);
+
+	modify_prot_commit_ptes(vma, addr, ptep, oldpte, ptent, nr_ptes);
+	if (pte_needs_flush(oldpte, ptent))
+		tlb_flush_pte_range(tlb, addr, nr_ptes * PAGE_SIZE);
+}
+
+/*
+ * Get max length of consecutive ptes pointing to PageAnonExclusive() pages or
+ * !PageAnonExclusive() pages, starting from start_idx. Caller must enforce
+ * that the ptes point to consecutive pages of the same anon large folio.
+ */
+static __always_inline int page_anon_exclusive_batch(int start_idx, int max_len,
+		struct page *first_page, bool expected_anon_exclusive)
+{
+	int idx;
+
+	for (idx = start_idx + 1; idx < start_idx + max_len; ++idx) {
+		if (expected_anon_exclusive != PageAnonExclusive(first_page + idx))
+			break;
+	}
+	return idx - start_idx;
+}
+
+/*
+ * This function is a result of trying our very best to retain the
+ * "avoid the write-fault handler" optimization. In can_change_pte_writable(),
+ * if the vma is a private vma, and we cannot determine whether to change
+ * the pte to writable just from the vma and the pte, we then need to look
+ * at the actual page pointed to by the pte. Unfortunately, if we have a
+ * batch of ptes pointing to consecutive pages of the same anon large folio,
+ * the anon-exclusivity (or the negation) of the first page does not guarantee
+ * the anon-exclusivity (or the negation) of the other pages corresponding to
+ * the pte batch; hence in this case it is incorrect to decide to change or
+ * not change the ptes to writable just by using information from the first
+ * pte of the batch. Therefore, we must individually check all pages and
+ * retrieve sub-batches.
+ */
+static __always_inline void commit_anon_folio_batch(struct vm_area_struct *vma,
+		struct folio *folio, struct page *first_page, unsigned long addr, pte_t *ptep,
+		pte_t oldpte, pte_t ptent, int nr_ptes, struct mmu_gather *tlb)
+{
+	bool expected_anon_exclusive;
+	int batch_idx = 0;
+	int len;
+
+	while (nr_ptes) {
+		expected_anon_exclusive = PageAnonExclusive(first_page + batch_idx);
+		len = page_anon_exclusive_batch(batch_idx, nr_ptes,
+					first_page, expected_anon_exclusive);
+		prot_commit_flush_ptes(vma, addr, ptep, oldpte, ptent, len,
+				       batch_idx, expected_anon_exclusive, tlb);
+		batch_idx += len;
+		nr_ptes -= len;
+	}
+}
+
+static __always_inline void set_write_prot_commit_flush_ptes(struct vm_area_struct *vma,
+		struct folio *folio, struct page *page, unsigned long addr, pte_t *ptep,
+		pte_t oldpte, pte_t ptent, int nr_ptes, struct mmu_gather *tlb)
+{
+	bool set_write;
+
+	if (vma_test(vma, VMA_SHARED_BIT)) {
+		set_write = can_change_shared_pte_writable(vma, ptent);
+		prot_commit_flush_ptes(vma, addr, ptep, oldpte, ptent, nr_ptes,
+				       /* idx = */ 0, set_write, tlb);
+		return;
+	}
+
+	set_write = maybe_change_pte_writable(vma, ptent) &&
+		    (folio && folio_test_anon(folio));
+	if (!set_write) {
+		prot_commit_flush_ptes(vma, addr, ptep, oldpte, ptent, nr_ptes,
+				       /* idx = */ 0, set_write, tlb);
+		return;
+	}
+	commit_anon_folio_batch(vma, folio, page, addr, ptep, oldpte, ptent, nr_ptes, tlb);
+}
+
+static long change_softleaf_pte(struct vm_area_struct *vma,
+	unsigned long addr, pte_t *pte, pte_t oldpte, unsigned long cp_flags)
+{
+	const bool uffd_prot = cp_flags & (MM_CP_UFFD_WP | MM_CP_UFFD_RWP);
+	const bool uffd_prot_resolve = cp_flags &
+		(MM_CP_UFFD_WP_RESOLVE | MM_CP_UFFD_RWP_RESOLVE);
+	softleaf_t entry = softleaf_from_pte(oldpte);
+	pte_t newpte;
+
+	if (softleaf_is_migration_write(entry)) {
+		const struct folio *folio = softleaf_to_folio(entry);
+
+		/*
+		 * A protection check is difficult so
+		 * just be safe and disable write
+		 */
+		if (folio_test_anon(folio))
+			entry = make_readable_exclusive_migration_entry(swp_offset(entry));
+		else
+			entry = make_readable_migration_entry(swp_offset(entry));
+		newpte = swp_entry_to_pte(entry);
+		if (pte_swp_soft_dirty(oldpte))
+			newpte = pte_swp_mksoft_dirty(newpte);
+	} else if (softleaf_is_device_private_write(entry)) {
+		/*
+		 * We do not preserve soft-dirtiness. See
+		 * copy_nonpresent_pte() for explanation.
+		 */
+		entry = make_readable_device_private_entry(swp_offset(entry));
+		newpte = swp_entry_to_pte(entry);
+		if (pte_swp_uffd(oldpte))
+			newpte = pte_swp_mkuffd(newpte);
+	} else if (softleaf_is_marker(entry)) {
+		/*
+		 * Ignore error swap entries unconditionally,
+		 * because any access should sigbus/sigsegv
+		 * anyway.
+		 */
+		if (softleaf_is_poison_marker(entry) ||
+		    softleaf_is_guard_marker(entry))
+			return 0;
+		/*
+		 * If this is uffd-wp pte marker and we'd like
+		 * to unprotect it, drop it; the next page
+		 * fault will trigger without uffd trapping.
+		 */
+		if (uffd_prot_resolve) {
+			pte_clear(vma->vm_mm, addr, pte);
+			return 1;
+		}
+		return 0;
+	} else {
+		newpte = oldpte;
+	}
+
+	if (uffd_prot)
+		newpte = pte_swp_mkuffd(newpte);
+	else if (uffd_prot_resolve)
+		newpte = pte_swp_clear_uffd(newpte);
+
+	if (!pte_same(oldpte, newpte)) {
+		set_pte_at(vma->vm_mm, addr, pte, newpte);
+		return 1;
+	}
+	return 0;
+}
+
+static __always_inline void change_present_ptes(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
+		int nr_ptes, unsigned long end, pgprot_t newprot,
+		struct folio *folio, struct page *page, unsigned long cp_flags)
+{
+	const bool uffd_prot = cp_flags & (MM_CP_UFFD_WP | MM_CP_UFFD_RWP);
+	const bool uffd_prot_resolve = cp_flags &
+		(MM_CP_UFFD_WP_RESOLVE | MM_CP_UFFD_RWP_RESOLVE);
+	pte_t ptent, oldpte;
+
+	oldpte = modify_prot_start_ptes(vma, addr, ptep, nr_ptes);
+	ptent = pte_modify(oldpte, newprot);
+
+	if (uffd_prot)
+		ptent = pte_mkuffd(ptent);
+	else if (uffd_prot_resolve)
+		ptent = pte_clear_uffd(ptent);
+
+	/*
+	 * The uffd bit on a VM_UFFD_RWP VMA carries PROT_NONE
+	 * semantics. If mprotect() or NUMA hinting changed the
+	 * base protection, restore PAGE_NONE so the PTE still
+	 * traps on any access. pte_modify() preserves
+	 * _PAGE_UFFD.
+	 */
+	if (userfaultfd_rwp(vma) && pte_uffd(ptent))
+		ptent = pte_modify(ptent, PAGE_NONE);
+
+	/*
+	 * In some writable, shared mappings, we might want
+	 * to catch actual write access -- see
+	 * vma_wants_writenotify().
+	 *
+	 * In all writable, private mappings, we have to
+	 * properly handle COW.
+	 *
+	 * In both cases, we can sometimes still change PTEs
+	 * writable and avoid the write-fault handler, for
+	 * example, if a PTE is already dirty and no other
+	 * COW or special handling is required.
+	 */
+	if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) &&
+	     !pte_write(ptent))
+		set_write_prot_commit_flush_ptes(vma, folio, page,
+			addr, ptep, oldpte, ptent, nr_ptes, tlb);
+	else
+		prot_commit_flush_ptes(vma, addr, ptep, oldpte, ptent,
+			nr_ptes, /* idx = */ 0, /* set_write = */ false, tlb);
+}
+
+static long change_pte_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
+{
+	pte_t *pte, oldpte;
+	spinlock_t *ptl;
+	long pages = 0;
+	bool is_private_single_threaded;
+	bool prot_numa = cp_flags & MM_CP_PROT_NUMA;
+	bool uffd_rwp = cp_flags & MM_CP_UFFD_RWP;
+	bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
+	int nr_ptes;
+
+	tlb_change_page_size(tlb, PAGE_SIZE);
+	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+	if (!pte)
+		return -EAGAIN;
+
+	if (prot_numa)
+		is_private_single_threaded = vma_is_single_threaded_private(vma);
+
+	flush_tlb_batched_pending(vma->vm_mm);
+	lazy_mmu_mode_enable();
+	do {
+		nr_ptes = 1;
+		oldpte = ptep_get(pte);
+		if (pte_present(oldpte)) {
+			const fpb_t flags = FPB_RESPECT_SOFT_DIRTY | FPB_RESPECT_WRITE;
+			int max_nr_ptes = (end - addr) >> PAGE_SHIFT;
+			struct folio *folio = NULL;
+			struct page *page;
+
+			/* Already in the desired state. */
+			if (prot_numa && pte_protnone(oldpte))
+				continue;
+			/*
+			 * RWP-protected PTEs carry _PAGE_UFFD as a marker on
+			 * top of PROT_NONE. Skip only entries already in that
+			 * exact state; plain PROT_NONE from mprotect() still needs
+			 * to be promoted so future faults can be distinguished.
+			 */
+			if (uffd_rwp && pte_protnone(oldpte) && pte_uffd(oldpte))
+				continue;
+
+			page = vm_normal_page(vma, addr, oldpte);
+			if (page)
+				folio = page_folio(page);
+
+			/*
+			 * Avoid trapping faults against the zero or KSM
+			 * pages. See similar comment in change_huge_pmd.
+			 * Skip this filter for uffd RWP which
+			 * must set protnone regardless of NUMA placement.
+			 */
+			if (prot_numa &&
+			    !folio_can_map_prot_numa(folio, vma,
+						is_private_single_threaded)) {
+
+				/* determine batch to skip */
+				nr_ptes = mprotect_folio_pte_batch(folio,
+					  pte, oldpte, max_nr_ptes, /* flags = */ 0);
+				continue;
+			}
+
+			nr_ptes = mprotect_folio_pte_batch(folio, pte, oldpte, max_nr_ptes, flags);
+
+			/*
+			 * Optimize for the small-folio common case by
+			 * special-casing it here. Compiler constant propagation
+			 * plus copious amounts of __always_inline does wonders.
+			 */
+			if (likely(nr_ptes == 1)) {
+				change_present_ptes(tlb, vma, addr, pte, 1,
+					end, newprot, folio, page, cp_flags);
+			} else {
+				change_present_ptes(tlb, vma, addr, pte,
+					nr_ptes, end, newprot, folio, page,
+					cp_flags);
+			}
+
+			pages += nr_ptes;
+		} else if (pte_none(oldpte)) {
+			/*
+			 * Nobody plays with any none ptes besides
+			 * userfaultfd when applying the protections.
+			 */
+			if (likely(!uffd_wp))
+				continue;
+
+			if (userfaultfd_wp_use_markers(vma)) {
+				/*
+				 * For file-backed mem, we need to be able to
+				 * wr-protect a none pte, because even if the
+				 * pte is none, the page/swap cache could
+				 * exist.  Doing that by install a marker.
+				 */
+				set_pte_at(vma->vm_mm, addr, pte,
+					   make_pte_marker(PTE_MARKER_UFFD_WP));
+				pages++;
+			}
+		} else  {
+			pages += change_softleaf_pte(vma, addr, pte, oldpte, cp_flags);
+		}
+	} while (pte += nr_ptes, addr += nr_ptes * PAGE_SIZE, addr != end);
+	lazy_mmu_mode_disable();
+	pte_unmap_unlock(pte - 1, ptl);
+
+	return pages;
+}
+
+/*
+ * Return true if we want to split THPs into PTE mappings in change
+ * protection procedure, false otherwise.
+ */
+static inline bool
+pgtable_split_needed(struct vm_area_struct *vma, unsigned long cp_flags)
+{
+	/*
+	 * pte markers only resides in pte level, if we need pte markers,
+	 * we need to split.  For example, we cannot wr-protect a file thp
+	 * (e.g. 2M shmem) because file thp is handled differently when
+	 * split by erasing the pmd so far.
+	 */
+	return (cp_flags & (MM_CP_UFFD_WP | MM_CP_UFFD_RWP)) && !vma_is_anonymous(vma);
+}
+
+/*
+ * Return true if we want to populate pgtables in change protection
+ * procedure, false otherwise
+ */
+static inline bool
+pgtable_populate_needed(struct vm_area_struct *vma, unsigned long cp_flags)
+{
+	/* If not within ioctl(UFFDIO_WRITEPROTECT), then don't bother */
+	if (!(cp_flags & MM_CP_UFFD_WP))
+		return false;
+
+	/* Populate if the userfaultfd mode requires pte markers */
+	return userfaultfd_wp_use_markers(vma);
+}
+
+/*
+ * Populate the pgtable underneath for whatever reason if requested.
+ * When {pte|pmd|...}_alloc() failed we treat it the same way as pgtable
+ * allocation failures during page faults by kicking OOM and returning
+ * error.
+ */
+#define  change_pmd_prepare(vma, pmd, cp_flags)				\
+	({								\
+		long err = 0;						\
+		if (unlikely(pgtable_populate_needed(vma, cp_flags))) {	\
+			if (pte_alloc(vma->vm_mm, pmd))			\
+				err = -ENOMEM;				\
+		}							\
+		err;							\
+	})
+
+/*
+ * This is the general pud/p4d/pgd version of change_pmd_prepare(). We need to
+ * have separate change_pmd_prepare() because pte_alloc() returns 0 on success,
+ * while {pmd|pud|p4d}_alloc() returns the valid pointer on success.
+ */
+#define  change_prepare(vma, high, low, addr, cp_flags)			\
+	  ({								\
+		long err = 0;						\
+		if (unlikely(pgtable_populate_needed(vma, cp_flags))) {	\
+			low##_t *p = low##_alloc(vma->vm_mm, high, addr); \
+			if (p == NULL)					\
+				err = -ENOMEM;				\
+		}							\
+		err;							\
+	})
+
+static inline long change_pmd_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, pud_t *pud, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
+{
+	pmd_t *pmd;
+	unsigned long next;
+	long pages = 0;
+	unsigned long nr_huge_updates = 0;
+
+	pmd = pmd_offset(pud, addr);
+	do {
+		long ret;
+		pmd_t _pmd;
+again:
+		next = pmd_addr_end(addr, end);
+
+		ret = change_pmd_prepare(vma, pmd, cp_flags);
+		if (ret) {
+			pages = ret;
+			break;
+		}
+
+		if (pmd_none(*pmd))
+			goto next;
+
+		_pmd = pmdp_get_lockless(pmd);
+		if (pmd_is_huge(_pmd)) {
+			if ((next - addr != HPAGE_PMD_SIZE) ||
+			    pgtable_split_needed(vma, cp_flags)) {
+				__split_huge_pmd(vma, pmd, addr, false);
+				/*
+				 * For file-backed, the pmd could have been
+				 * cleared; make sure pmd populated if
+				 * necessary, then fall-through to pte level.
+				 */
+				ret = change_pmd_prepare(vma, pmd, cp_flags);
+				if (ret) {
+					pages = ret;
+					break;
+				}
+			} else {
+				ret = change_huge_pmd(tlb, vma, pmd,
+						addr, newprot, cp_flags);
+				if (ret) {
+					if (ret == HPAGE_PMD_NR) {
+						pages += HPAGE_PMD_NR;
+						nr_huge_updates++;
+					}
+
+					/* huge pmd was handled */
+					goto next;
+				}
+			}
+			/* fall through, the trans huge pmd just split */
+		}
+
+		ret = change_pte_range(tlb, vma, pmd, addr, next, newprot,
+				       cp_flags);
+		if (ret < 0)
+			goto again;
+		pages += ret;
+next:
+		cond_resched();
+	} while (pmd++, addr = next, addr != end);
+
+	if (nr_huge_updates)
+		count_vm_numa_events(NUMA_HUGE_PTE_UPDATES, nr_huge_updates);
+	return pages;
+}
+
+static inline long change_pud_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
+{
+	struct mmu_notifier_range range;
+	pud_t *pudp, pud;
+	unsigned long next;
+	long pages = 0, ret;
+
+	range.start = 0;
+
+	pudp = pud_offset(p4d, addr);
+	do {
+again:
+		next = pud_addr_end(addr, end);
+		ret = change_prepare(vma, pudp, pmd, addr, cp_flags);
+		if (ret) {
+			pages = ret;
+			break;
+		}
+
+		pud = pudp_get(pudp);
+		if (pud_none(pud))
+			continue;
+
+		if (!range.start) {
+			mmu_notifier_range_init(&range,
+						MMU_NOTIFY_PROTECTION_VMA, 0,
+						vma->vm_mm, addr, end);
+			mmu_notifier_invalidate_range_start(&range);
+		}
+
+		if (pud_leaf(pud)) {
+			if ((next - addr != PUD_SIZE) ||
+			    pgtable_split_needed(vma, cp_flags)) {
+				__split_huge_pud(vma, pudp, addr);
+				goto again;
+			} else {
+				ret = change_huge_pud(tlb, vma, pudp,
+						      addr, newprot, cp_flags);
+				if (ret == 0)
+					goto again;
+				/* huge pud was handled */
+				if (ret == HPAGE_PUD_NR)
+					pages += HPAGE_PUD_NR;
+				continue;
+			}
+		}
+
+		pages += change_pmd_range(tlb, vma, pudp, addr, next, newprot,
+					  cp_flags);
+	} while (pudp++, addr = next, addr != end);
+
+	if (range.start)
+		mmu_notifier_invalidate_range_end(&range);
+
+	return pages;
+}
+
+static inline long change_p4d_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
+{
+	p4d_t *p4d;
+	unsigned long next;
+	long pages = 0, ret;
+
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		ret = change_prepare(vma, p4d, pud, addr, cp_flags);
+		if (ret)
+			return ret;
+		if (p4d_none_or_clear_bad(p4d))
+			continue;
+		pages += change_pud_range(tlb, vma, p4d, addr, next, newprot,
+					  cp_flags);
+	} while (p4d++, addr = next, addr != end);
+
+	return pages;
+}
+
+static long change_protection_range(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, unsigned long addr,
+		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	pgd_t *pgd;
+	unsigned long next;
+	long pages = 0, ret;
+
+	BUG_ON(addr >= end);
+	pgd = pgd_offset(mm, addr);
+	tlb_start_vma(tlb, vma);
+	do {
+		next = pgd_addr_end(addr, end);
+		ret = change_prepare(vma, pgd, p4d, addr, cp_flags);
+		if (ret) {
+			pages = ret;
+			break;
+		}
+		if (pgd_none_or_clear_bad(pgd))
+			continue;
+		pages += change_p4d_range(tlb, vma, pgd, addr, next, newprot,
+					  cp_flags);
+	} while (pgd++, addr = next, addr != end);
+
+	tlb_end_vma(tlb, vma);
+
+	return pages;
+}
+
+long change_protection(struct mmu_gather *tlb,
+		       struct vm_area_struct *vma, unsigned long start,
+		       unsigned long end, unsigned long cp_flags)
+{
+	pgprot_t newprot = vma->vm_page_prot;
+	long pages;
+
+	/*
+	 * MM_CP_UFFD_{WP,RWP} and _RESOLVE are mutually exclusive within one
+	 * change, and WP and RWP cannot mix. Miswired callers get a warn and
+	 * a no-op; userspace cannot reach this state.
+	 */
+	if (WARN_ON_ONCE((cp_flags & MM_CP_UFFD_WP_ALL) == MM_CP_UFFD_WP_ALL ||
+			 (cp_flags & MM_CP_UFFD_RWP_ALL) == MM_CP_UFFD_RWP_ALL ||
+			 ((cp_flags & MM_CP_UFFD_WP_ALL) &&
+			  (cp_flags & MM_CP_UFFD_RWP_ALL))))
+		return 0;
+
+#ifdef CONFIG_NUMA_BALANCING
+	/*
+	 * Ordinary protection updates (mprotect, uffd-wp, softdirty tracking)
+	 * are expected to reflect their requirements via VMA flags such that
+	 * vma_set_page_prot() will adjust vma->vm_page_prot accordingly.
+	 */
+	if (cp_flags & MM_CP_PROT_NUMA)
+		newprot = PAGE_NONE;
+#else
+	WARN_ON_ONCE(cp_flags & MM_CP_PROT_NUMA);
+#endif
+
+	if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_PROTNONE) &&
+	    (cp_flags & MM_CP_UFFD_RWP))
+		newprot = PAGE_NONE;
+
+	if (is_vm_hugetlb_page(vma))
+		pages = hugetlb_change_protection(vma, start, end, newprot,
+						  cp_flags);
+	else
+		pages = change_protection_range(tlb, vma, start, end, newprot,
+						cp_flags);
+
+	return pages;
+}
+
+static int prot_none_pte_entry(pte_t *pte, unsigned long addr,
+			       unsigned long next, struct mm_walk *walk)
+{
+	return pfn_modify_allowed(pte_pfn(ptep_get(pte)),
+				  *(pgprot_t *)(walk->private)) ?
+		0 : -EACCES;
+}
+
+#ifdef CONFIG_HUGETLB_PAGE
+static int prot_none_hugetlb_entry(pte_t *pte, unsigned long hmask,
+				   unsigned long addr, unsigned long next,
+				   struct mm_walk *walk)
+{
+	const pte_t entry = huge_ptep_get(walk->mm, addr, pte);
+
+	if (pfn_modify_allowed(pte_pfn(entry), *(pgprot_t *)(walk->private)))
+		return 0;
+	return -EACCES;
+}
+#else
+#define prot_none_hugetlb_entry	NULL
+#endif
+
+static const struct mm_walk_ops prot_none_walk_ops = {
+	.pte_entry		= prot_none_pte_entry,
+	.hugetlb_entry		= prot_none_hugetlb_entry,
+	.walk_lock		= PGWALK_WRLOCK,
+};
+
+int
+mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb,
+	       struct vm_area_struct *vma, struct vm_area_struct **pprev,
+	       unsigned long start, unsigned long end, vm_flags_t newflags)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	const vma_flags_t old_vma_flags = READ_ONCE(vma->flags);
+	vma_flags_t new_vma_flags = legacy_to_vma_flags(newflags);
+	long nrpages = (end - start) >> PAGE_SHIFT;
+	unsigned int mm_cp_flags = 0;
+	unsigned long charged = 0;
+	int error;
+
+	if (vma_is_sealed(vma))
+		return -EPERM;
+
+	if (vma_flags_same_pair(&old_vma_flags, &new_vma_flags)) {
+		*pprev = vma;
+		return 0;
+	}
+
+	/*
+	 * Do PROT_NONE PFN permission checks here when we can still
+	 * bail out without undoing a lot of state. This is a rather
+	 * uncommon case, so doesn't need to be very optimized.
+	 */
+	if (arch_has_pfn_modify_check() &&
+	    vma_flags_test_any(&old_vma_flags, VMA_PFNMAP_BIT,
+			       VMA_MIXEDMAP_BIT) &&
+	    !vma_flags_test_any_mask(&new_vma_flags, VMA_ACCESS_FLAGS)) {
+		pgprot_t new_pgprot = vm_get_page_prot(newflags);
+
+		error = walk_page_range_vma(vma, start, end,
+				&prot_none_walk_ops, &new_pgprot);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * If we make a private mapping writable we increase our commit;
+	 * but (without finer accounting) cannot reduce our commit if we
+	 * make it unwritable again except in the anonymous case where no
+	 * anon_vma has yet to be assigned.
+	 *
+	 * hugetlb mapping were accounted for even if read-only so there is
+	 * no need to account for them here.
+	 */
+	if (vma_flags_test(&new_vma_flags, VMA_WRITE_BIT)) {
+		/* Check space limits when area turns into data. */
+		if (!may_expand_vm(mm, &new_vma_flags, nrpages) &&
+		    may_expand_vm(mm, &old_vma_flags, nrpages))
+			return -ENOMEM;
+		if (!vma_flags_test_any(&old_vma_flags,
+				VMA_ACCOUNT_BIT, VMA_WRITE_BIT, VMA_HUGETLB_BIT,
+				VMA_SHARED_BIT, VMA_NORESERVE_BIT)) {
+			charged = nrpages;
+			if (security_vm_enough_memory_mm(mm, charged))
+				return -ENOMEM;
+			vma_flags_set(&new_vma_flags, VMA_ACCOUNT_BIT);
+		}
+	} else if (vma_flags_test(&old_vma_flags, VMA_ACCOUNT_BIT) &&
+		   vma_is_anonymous(vma) && !vma->anon_vma) {
+		vma_flags_clear(&new_vma_flags, VMA_ACCOUNT_BIT);
+	}
+
+	vma = vma_modify_flags(vmi, *pprev, vma, start, end, &new_vma_flags);
+	if (IS_ERR(vma)) {
+		error = PTR_ERR(vma);
+		goto fail;
+	}
+
+	*pprev = vma;
+
+	/*
+	 * vm_flags and vm_page_prot are protected by the mmap_lock
+	 * held in write mode.
+	 */
+	vma_start_write(vma);
+	vma_flags_reset_once(vma, &new_vma_flags);
+	if (vma_wants_manual_pte_write_upgrade(vma))
+		mm_cp_flags |= MM_CP_TRY_CHANGE_WRITABLE;
+	vma_set_page_prot(vma);
+
+	change_protection(tlb, vma, start, end, mm_cp_flags);
+
+	if (vma_flags_test(&old_vma_flags, VMA_ACCOUNT_BIT) &&
+	    !vma_flags_test(&new_vma_flags, VMA_ACCOUNT_BIT))
+		vm_unacct_memory(nrpages);
+
+	/*
+	 * Private VMA_LOCKED_BIT VMA becoming writable: trigger COW to avoid
+	 * major fault on access.
+	 */
+	if (vma_flags_test(&new_vma_flags, VMA_WRITE_BIT) &&
+	    vma_flags_test(&old_vma_flags, VMA_LOCKED_BIT) &&
+	    !vma_flags_test_any(&old_vma_flags, VMA_WRITE_BIT, VMA_SHARED_BIT))
+		populate_vma_page_range(vma, start, end, NULL);
+
+	vm_stat_account(mm, vma_flags_to_legacy(old_vma_flags), -nrpages);
+	newflags = vma_flags_to_legacy(new_vma_flags);
+	vm_stat_account(mm, newflags, nrpages);
+	perf_event_mmap(vma);
+	return 0;
+
+fail:
+	vm_unacct_memory(charged);
+	return error;
+}
+
+/*
+ * pkey==-1 when doing a legacy mprotect()
+ */
+static int do_mprotect_pkey(unsigned long start, size_t len,
+		unsigned long prot, int pkey)
+{
+	unsigned long nstart, end, tmp, reqprot;
+	struct vm_area_struct *vma, *prev;
+	int error;
+	const int grows = prot & (PROT_GROWSDOWN|PROT_GROWSUP);
+	const bool rier = (current->personality & READ_IMPLIES_EXEC) &&
+				(prot & PROT_READ);
+	struct mmu_gather tlb;
+	struct vma_iterator vmi;
+
+	start = untagged_addr(start);
+
+	prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP);
+	if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */
+		return -EINVAL;
+
+	if (start & ~PAGE_MASK)
+		return -EINVAL;
+	if (!len)
+		return 0;
+	len = PAGE_ALIGN(len);
+	end = start + len;
+	if (end <= start)
+		return -ENOMEM;
+	if (!arch_validate_prot(prot, start))
+		return -EINVAL;
+
+	reqprot = prot;
+
+	if (mmap_write_lock_killable(current->mm))
+		return -EINTR;
+
+	/*
+	 * If userspace did not allocate the pkey, do not let
+	 * them use it here.
+	 */
+	error = -EINVAL;
+	if ((pkey != -1) && !mm_pkey_is_allocated(current->mm, pkey))
+		goto out;
+
+	vma_iter_init(&vmi, current->mm, start);
+	vma = vma_find(&vmi, end);
+	error = -ENOMEM;
+	if (!vma)
+		goto out;
+
+	if (unlikely(grows & PROT_GROWSDOWN)) {
+		if (vma->vm_start >= end)
+			goto out;
+		start = vma->vm_start;
+		error = -EINVAL;
+		if (!vma_test(vma, VMA_GROWSDOWN_BIT))
+			goto out;
+	} else {
+		if (vma->vm_start > start)
+			goto out;
+		if (unlikely(grows & PROT_GROWSUP)) {
+			end = vma->vm_end;
+			error = -EINVAL;
+			if (!vma_test_single_mask(vma, VMA_GROWSUP))
+				goto out;
+		}
+	}
+
+	prev = vma_prev(&vmi);
+	if (start > vma->vm_start)
+		prev = vma;
+
+	tlb_gather_mmu(&tlb, current->mm);
+	nstart = start;
+	tmp = vma->vm_start;
+	for_each_vma_range(vmi, vma, end) {
+		vm_flags_t mask_off_old_flags;
+		vma_flags_t new_vma_flags;
+		vm_flags_t newflags;
+		int new_vma_pkey;
+
+		if (vma->vm_start != tmp) {
+			error = -ENOMEM;
+			break;
+		}
+
+		/* Does the application expect PROT_READ to imply PROT_EXEC */
+		if (rier && vma_test(vma, VMA_MAYEXEC_BIT))
+			prot |= PROT_EXEC;
+
+		/*
+		 * Each mprotect() call explicitly passes r/w/x permissions.
+		 * If a permission is not passed to mprotect(), it must be
+		 * cleared from the VMA.
+		 */
+		mask_off_old_flags = VM_ACCESS_FLAGS | VM_FLAGS_CLEAR;
+
+		new_vma_pkey = arch_override_mprotect_pkey(vma, prot, pkey);
+		newflags = calc_vm_prot_bits(prot, new_vma_pkey);
+		newflags |= (vma->vm_flags & ~mask_off_old_flags);
+		new_vma_flags = legacy_to_vma_flags(newflags);
+
+		/* newflags >> 4 shift VM_MAY% in place of VM_% */
+		if ((newflags & ~(newflags >> 4)) & VM_ACCESS_FLAGS) {
+			error = -EACCES;
+			break;
+		}
+
+		if (map_deny_write_exec(&vma->flags, &new_vma_flags)) {
+			error = -EACCES;
+			break;
+		}
+
+		/* Allow architectures to sanity-check the new flags */
+		if (!arch_validate_flags(newflags)) {
+			error = -EINVAL;
+			break;
+		}
+
+		error = security_file_mprotect(vma, reqprot, prot);
+		if (error)
+			break;
+
+		tmp = vma->vm_end;
+		if (tmp > end)
+			tmp = end;
+
+		if (vma->vm_ops && vma->vm_ops->mprotect) {
+			error = vma->vm_ops->mprotect(vma, nstart, tmp, newflags);
+			if (error)
+				break;
+		}
+
+		error = mprotect_fixup(&vmi, &tlb, vma, &prev, nstart, tmp, newflags);
+		if (error)
+			break;
+
+		tmp = vma_iter_end(&vmi);
+		nstart = tmp;
+		prot = reqprot;
+	}
+	tlb_finish_mmu(&tlb);
+
+	if (!error && tmp < end)
+		error = -ENOMEM;
+
+out:
+	mmap_write_unlock(current->mm);
+	return error;
+}
+
+SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
+		unsigned long, prot)
+{
+	return do_mprotect_pkey(start, len, prot, -1);
+}
+
+#ifdef CONFIG_ARCH_HAS_PKEYS
+
+SYSCALL_DEFINE4(pkey_mprotect, unsigned long, start, size_t, len,
+		unsigned long, prot, int, pkey)
+{
+	return do_mprotect_pkey(start, len, prot, pkey);
+}
+
+SYSCALL_DEFINE2(pkey_alloc, unsigned long, flags, unsigned long, init_val)
+{
+	int pkey;
+	int ret;
+
+	/* No flags supported yet. */
+	if (flags)
+		return -EINVAL;
+	/* check for unsupported init values */
+	if (init_val & ~PKEY_ACCESS_MASK)
+		return -EINVAL;
+
+	mmap_write_lock(current->mm);
+	pkey = mm_pkey_alloc(current->mm);
+
+	ret = -ENOSPC;
+	if (pkey == -1)
+		goto out;
+
+	ret = arch_set_user_pkey_access(pkey, init_val);
+	if (ret) {
+		mm_pkey_free(current->mm, pkey);
+		goto out;
+	}
+	ret = pkey;
+out:
+	mmap_write_unlock(current->mm);
+	return ret;
+}
+
+SYSCALL_DEFINE1(pkey_free, int, pkey)
+{
+	int ret;
+
+	mmap_write_lock(current->mm);
+	ret = mm_pkey_free(current->mm, pkey);
+	mmap_write_unlock(current->mm);
+
+	/*
+	 * We could provide warnings or errors if any VMA still
+	 * has the pkey set here.
+	 */
+	return ret;
+}
+
+#endif /* CONFIG_ARCH_HAS_PKEYS */