1 files changed, 195 insertions, 177 deletions

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 615b4e6d22c7..4c965ba77f9f 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -29,6 +29,7 @@
 #include <linux/workqueue.h>
 #include <linux/srcu.h>
 #include <linux/oom.h>          /* check_stable_address_space */
+#include <linux/pagewalk.h>
 
 #include <linux/uprobes.h>
 
@@ -152,91 +153,6 @@ static loff_t vaddr_to_offset(struct vm_area_struct *vma, unsigned long vaddr)
 }
 
 /**
- * __replace_page - replace page in vma by new page.
- * based on replace_page in mm/ksm.c
- *
- * @vma:      vma that holds the pte pointing to page
- * @addr:     address the old @page is mapped at
- * @old_page: the page we are replacing by new_page
- * @new_page: the modified page we replace page by
- *
- * If @new_page is NULL, only unmap @old_page.
- *
- * Returns 0 on success, negative error code otherwise.
- */
-static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
-				struct page *old_page, struct page *new_page)
-{
-	struct folio *old_folio = page_folio(old_page);
-	struct folio *new_folio;
-	struct mm_struct *mm = vma->vm_mm;
-	DEFINE_FOLIO_VMA_WALK(pvmw, old_folio, vma, addr, 0);
-	int err;
-	struct mmu_notifier_range range;
-	pte_t pte;
-
-	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr,
-				addr + PAGE_SIZE);
-
-	if (new_page) {
-		new_folio = page_folio(new_page);
-		err = mem_cgroup_charge(new_folio, vma->vm_mm, GFP_KERNEL);
-		if (err)
-			return err;
-	}
-
-	/* For folio_free_swap() below */
-	folio_lock(old_folio);
-
-	mmu_notifier_invalidate_range_start(&range);
-	err = -EAGAIN;
-	if (!page_vma_mapped_walk(&pvmw))
-		goto unlock;
-	VM_BUG_ON_PAGE(addr != pvmw.address, old_page);
-	pte = ptep_get(pvmw.pte);
-
-	/*
-	 * Handle PFN swap PTES, such as device-exclusive ones, that actually
-	 * map pages: simply trigger GUP again to fix it up.
-	 */
-	if (unlikely(!pte_present(pte))) {
-		page_vma_mapped_walk_done(&pvmw);
-		goto unlock;
-	}
-
-	if (new_page) {
-		folio_get(new_folio);
-		folio_add_new_anon_rmap(new_folio, vma, addr, RMAP_EXCLUSIVE);
-		folio_add_lru_vma(new_folio, vma);
-	} else
-		/* no new page, just dec_mm_counter for old_page */
-		dec_mm_counter(mm, MM_ANONPAGES);
-
-	if (!folio_test_anon(old_folio)) {
-		dec_mm_counter(mm, mm_counter_file(old_folio));
-		inc_mm_counter(mm, MM_ANONPAGES);
-	}
-
-	flush_cache_page(vma, addr, pte_pfn(pte));
-	ptep_clear_flush(vma, addr, pvmw.pte);
-	if (new_page)
-		set_pte_at(mm, addr, pvmw.pte,
-			   mk_pte(new_page, vma->vm_page_prot));
-
-	folio_remove_rmap_pte(old_folio, old_page, vma);
-	if (!folio_mapped(old_folio))
-		folio_free_swap(old_folio);
-	page_vma_mapped_walk_done(&pvmw);
-	folio_put(old_folio);
-
-	err = 0;
- unlock:
-	mmu_notifier_invalidate_range_end(&range);
-	folio_unlock(old_folio);
-	return err;
-}
-
-/**
  * is_swbp_insn - check if instruction is breakpoint instruction.
  * @insn: instruction to be checked.
  * Default implementation of is_swbp_insn
@@ -463,6 +379,95 @@ static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm,
 	return ret;
 }
 
+static bool orig_page_is_identical(struct vm_area_struct *vma,
+		unsigned long vaddr, struct page *page, bool *pmd_mappable)
+{
+	const pgoff_t index = vaddr_to_offset(vma, vaddr) >> PAGE_SHIFT;
+	struct folio *orig_folio = filemap_get_folio(vma->vm_file->f_mapping,
+						    index);
+	struct page *orig_page;
+	bool identical;
+
+	if (IS_ERR(orig_folio))
+		return false;
+	orig_page = folio_file_page(orig_folio, index);
+
+	*pmd_mappable = folio_test_pmd_mappable(orig_folio);
+	identical = folio_test_uptodate(orig_folio) &&
+		    pages_identical(page, orig_page);
+	folio_put(orig_folio);
+	return identical;
+}
+
+static int __uprobe_write_opcode(struct vm_area_struct *vma,
+		struct folio_walk *fw, struct folio *folio,
+		unsigned long opcode_vaddr, uprobe_opcode_t opcode)
+{
+	const unsigned long vaddr = opcode_vaddr & PAGE_MASK;
+	const bool is_register = !!is_swbp_insn(&opcode);
+	bool pmd_mappable;
+
+	/* For now, we'll only handle PTE-mapped folios. */
+	if (fw->level != FW_LEVEL_PTE)
+		return -EFAULT;
+
+	/*
+	 * See can_follow_write_pte(): we'd actually prefer a writable PTE here,
+	 * but the VMA might not be writable.
+	 */
+	if (!pte_write(fw->pte)) {
+		if (!PageAnonExclusive(fw->page))
+			return -EFAULT;
+		if (unlikely(userfaultfd_pte_wp(vma, fw->pte)))
+			return -EFAULT;
+		/* SOFTDIRTY is handled via pte_mkdirty() below. */
+	}
+
+	/*
+	 * We'll temporarily unmap the page and flush the TLB, such that we can
+	 * modify the page atomically.
+	 */
+	flush_cache_page(vma, vaddr, pte_pfn(fw->pte));
+	fw->pte = ptep_clear_flush(vma, vaddr, fw->ptep);
+	copy_to_page(fw->page, opcode_vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
+
+	/*
+	 * When unregistering, we may only zap a PTE if uffd is disabled and
+	 * there are no unexpected folio references ...
+	 */
+	if (is_register || userfaultfd_missing(vma) ||
+	    (folio_ref_count(folio) != folio_mapcount(folio) + 1 +
+	     folio_test_swapcache(folio) * folio_nr_pages(folio)))
+		goto remap;
+
+	/*
+	 * ... and the mapped page is identical to the original page that
+	 * would get faulted in on next access.
+	 */
+	if (!orig_page_is_identical(vma, vaddr, fw->page, &pmd_mappable))
+		goto remap;
+
+	dec_mm_counter(vma->vm_mm, MM_ANONPAGES);
+	folio_remove_rmap_pte(folio, fw->page, vma);
+	if (!folio_mapped(folio) && folio_test_swapcache(folio) &&
+	     folio_trylock(folio)) {
+		folio_free_swap(folio);
+		folio_unlock(folio);
+	}
+	folio_put(folio);
+
+	return pmd_mappable;
+remap:
+	/*
+	 * Make sure that our copy_to_page() changes become visible before the
+	 * set_pte_at() write.
+	 */
+	smp_wmb();
+	/* We modified the page. Make sure to mark the PTE dirty. */
+	set_pte_at(vma->vm_mm, vaddr, fw->ptep, pte_mkdirty(fw->pte));
+	return 0;
+}
+
 /*
  * NOTE:
  * Expect the breakpoint instruction to be the smallest size instruction for
@@ -474,146 +479,146 @@ static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm,
  *
  * uprobe_write_opcode - write the opcode at a given virtual address.
  * @auprobe: arch specific probepoint information.
- * @mm: the probed process address space.
- * @vaddr: the virtual address to store the opcode.
- * @opcode: opcode to be written at @vaddr.
+ * @vma: the probed virtual memory area.
+ * @opcode_vaddr: the virtual address to store the opcode.
+ * @opcode: opcode to be written at @opcode_vaddr.
  *
  * Called with mm->mmap_lock held for read or write.
  * Return 0 (success) or a negative errno.
  */
-int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
-			unsigned long vaddr, uprobe_opcode_t opcode)
+int uprobe_write_opcode(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
+		const unsigned long opcode_vaddr, uprobe_opcode_t opcode)
 {
+	const unsigned long vaddr = opcode_vaddr & PAGE_MASK;
+	struct mm_struct *mm = vma->vm_mm;
 	struct uprobe *uprobe;
-	struct page *old_page, *new_page;
-	struct vm_area_struct *vma;
 	int ret, is_register, ref_ctr_updated = 0;
-	bool orig_page_huge = false;
 	unsigned int gup_flags = FOLL_FORCE;
+	struct mmu_notifier_range range;
+	struct folio_walk fw;
+	struct folio *folio;
+	struct page *page;
 
 	is_register = is_swbp_insn(&opcode);
 	uprobe = container_of(auprobe, struct uprobe, arch);
 
-retry:
+	if (WARN_ON_ONCE(!is_cow_mapping(vma->vm_flags)))
+		return -EINVAL;
+
+	/*
+	 * When registering, we have to break COW to get an exclusive anonymous
+	 * page that we can safely modify. Use FOLL_WRITE to trigger a write
+	 * fault if required. When unregistering, we might be lucky and the
+	 * anon page is already gone. So defer write faults until really
+	 * required. Use FOLL_SPLIT_PMD, because __uprobe_write_opcode()
+	 * cannot deal with PMDs yet.
+	 */
 	if (is_register)
-		gup_flags |= FOLL_SPLIT_PMD;
-	/* Read the page with vaddr into memory */
-	old_page = get_user_page_vma_remote(mm, vaddr, gup_flags, &vma);
-	if (IS_ERR(old_page))
-		return PTR_ERR(old_page);
+		gup_flags |= FOLL_WRITE | FOLL_SPLIT_PMD;
 
-	ret = verify_opcode(old_page, vaddr, &opcode);
+retry:
+	ret = get_user_pages_remote(mm, vaddr, 1, gup_flags, &page, NULL);
 	if (ret <= 0)
-		goto put_old;
-
-	if (is_zero_page(old_page)) {
-		ret = -EINVAL;
-		goto put_old;
-	}
+		goto out;
+	folio = page_folio(page);
 
-	if (WARN(!is_register && PageCompound(old_page),
-		 "uprobe unregister should never work on compound page\n")) {
-		ret = -EINVAL;
-		goto put_old;
+	ret = verify_opcode(page, opcode_vaddr, &opcode);
+	if (ret <= 0) {
+		folio_put(folio);
+		goto out;
 	}
 
 	/* We are going to replace instruction, update ref_ctr. */
 	if (!ref_ctr_updated && uprobe->ref_ctr_offset) {
 		ret = update_ref_ctr(uprobe, mm, is_register ? 1 : -1);
-		if (ret)
-			goto put_old;
+		if (ret) {
+			folio_put(folio);
+			goto out;
+		}
 
 		ref_ctr_updated = 1;
 	}
 
 	ret = 0;
-	if (!is_register && !PageAnon(old_page))
-		goto put_old;
-
-	ret = anon_vma_prepare(vma);
-	if (ret)
-		goto put_old;
-
-	ret = -ENOMEM;
-	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr);
-	if (!new_page)
-		goto put_old;
-
-	__SetPageUptodate(new_page);
-	copy_highpage(new_page, old_page);
-	copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
+	if (unlikely(!folio_test_anon(folio))) {
+		VM_WARN_ON_ONCE(is_register);
+		folio_put(folio);
+		goto out;
+	}
 
 	if (!is_register) {
-		struct page *orig_page;
-		pgoff_t index;
-
-		VM_BUG_ON_PAGE(!PageAnon(old_page), old_page);
-
-		index = vaddr_to_offset(vma, vaddr & PAGE_MASK) >> PAGE_SHIFT;
-		orig_page = find_get_page(vma->vm_file->f_inode->i_mapping,
-					  index);
-
-		if (orig_page) {
-			if (PageUptodate(orig_page) &&
-			    pages_identical(new_page, orig_page)) {
-				/* let go new_page */
-				put_page(new_page);
-				new_page = NULL;
-
-				if (PageCompound(orig_page))
-					orig_page_huge = true;
-			}
-			put_page(orig_page);
-		}
+		/*
+		 * In the common case, we'll be able to zap the page when
+		 * unregistering. So trigger MMU notifiers now, as we won't
+		 * be able to do it under PTL.
+		 */
+		mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm,
+					vaddr, vaddr + PAGE_SIZE);
+		mmu_notifier_invalidate_range_start(&range);
+	}
+
+	ret = -EAGAIN;
+	/* Walk the page tables again, to perform the actual update. */
+	if (folio_walk_start(&fw, vma, vaddr, 0)) {
+		if (fw.page == page)
+			ret = __uprobe_write_opcode(vma, &fw, folio, opcode_vaddr, opcode);
+		folio_walk_end(&fw, vma);
 	}
 
-	ret = __replace_page(vma, vaddr & PAGE_MASK, old_page, new_page);
-	if (new_page)
-		put_page(new_page);
-put_old:
-	put_page(old_page);
+	if (!is_register)
+		mmu_notifier_invalidate_range_end(&range);
 
-	if (unlikely(ret == -EAGAIN))
+	folio_put(folio);
+	switch (ret) {
+	case -EFAULT:
+		gup_flags |= FOLL_WRITE | FOLL_SPLIT_PMD;
+		fallthrough;
+	case -EAGAIN:
 		goto retry;
+	default:
+		break;
+	}
 
+out:
 	/* Revert back reference counter if instruction update failed. */
-	if (ret && is_register && ref_ctr_updated)
+	if (ret < 0 && is_register && ref_ctr_updated)
 		update_ref_ctr(uprobe, mm, -1);
 
 	/* try collapse pmd for compound page */
-	if (!ret && orig_page_huge)
+	if (ret > 0)
 		collapse_pte_mapped_thp(mm, vaddr, false);
 
-	return ret;
+	return ret < 0 ? ret : 0;
 }
 
 /**
  * set_swbp - store breakpoint at a given address.
  * @auprobe: arch specific probepoint information.
- * @mm: the probed process address space.
+ * @vma: the probed virtual memory area.
  * @vaddr: the virtual address to insert the opcode.
  *
  * For mm @mm, store the breakpoint instruction at @vaddr.
  * Return 0 (success) or a negative errno.
  */
-int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
+int __weak set_swbp(struct arch_uprobe *auprobe, struct vm_area_struct *vma,
+		unsigned long vaddr)
 {
-	return uprobe_write_opcode(auprobe, mm, vaddr, UPROBE_SWBP_INSN);
+	return uprobe_write_opcode(auprobe, vma, vaddr, UPROBE_SWBP_INSN);
 }
 
 /**
  * set_orig_insn - Restore the original instruction.
- * @mm: the probed process address space.
+ * @vma: the probed virtual memory area.
  * @auprobe: arch specific probepoint information.
  * @vaddr: the virtual address to insert the opcode.
  *
  * For mm @mm, restore the original opcode (opcode) at @vaddr.
  * Return 0 (success) or a negative errno.
  */
-int __weak
-set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
+int __weak set_orig_insn(struct arch_uprobe *auprobe,
+		struct vm_area_struct *vma, unsigned long vaddr)
 {
-	return uprobe_write_opcode(auprobe, mm, vaddr,
+	return uprobe_write_opcode(auprobe, vma, vaddr,
 			*(uprobe_opcode_t *)&auprobe->insn);
 }
 
@@ -1134,10 +1139,10 @@ static bool filter_chain(struct uprobe *uprobe, struct mm_struct *mm)
 	return ret;
 }
 
-static int
-install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
-			struct vm_area_struct *vma, unsigned long vaddr)
+static int install_breakpoint(struct uprobe *uprobe, struct vm_area_struct *vma,
+		unsigned long vaddr)
 {
+	struct mm_struct *mm = vma->vm_mm;
 	bool first_uprobe;
 	int ret;
 
@@ -1153,7 +1158,7 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
 	if (first_uprobe)
 		set_bit(MMF_HAS_UPROBES, &mm->flags);
 
-	ret = set_swbp(&uprobe->arch, mm, vaddr);
+	ret = set_swbp(&uprobe->arch, vma, vaddr);
 	if (!ret)
 		clear_bit(MMF_RECALC_UPROBES, &mm->flags);
 	else if (first_uprobe)
@@ -1162,11 +1167,13 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
 	return ret;
 }
 
-static int
-remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr)
+static int remove_breakpoint(struct uprobe *uprobe, struct vm_area_struct *vma,
+		unsigned long vaddr)
 {
+	struct mm_struct *mm = vma->vm_mm;
+
 	set_bit(MMF_RECALC_UPROBES, &mm->flags);
-	return set_orig_insn(&uprobe->arch, mm, vaddr);
+	return set_orig_insn(&uprobe->arch, vma, vaddr);
 }
 
 struct map_info {
@@ -1296,10 +1303,10 @@ register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new)
 		if (is_register) {
 			/* consult only the "caller", new consumer. */
 			if (consumer_filter(new, mm))
-				err = install_breakpoint(uprobe, mm, vma, info->vaddr);
+				err = install_breakpoint(uprobe, vma, info->vaddr);
 		} else if (test_bit(MMF_HAS_UPROBES, &mm->flags)) {
 			if (!filter_chain(uprobe, mm))
-				err |= remove_breakpoint(uprobe, mm, info->vaddr);
+				err |= remove_breakpoint(uprobe, vma, info->vaddr);
 		}
 
  unlock:
@@ -1472,7 +1479,7 @@ static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm)
 			continue;
 
 		vaddr = offset_to_vaddr(vma, uprobe->offset);
-		err |= remove_breakpoint(uprobe, mm, vaddr);
+		err |= remove_breakpoint(uprobe, vma, vaddr);
 	}
 	mmap_read_unlock(mm);
 
@@ -1610,7 +1617,7 @@ int uprobe_mmap(struct vm_area_struct *vma)
 		if (!fatal_signal_pending(current) &&
 		    filter_chain(uprobe, vma->vm_mm)) {
 			unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset);
-			install_breakpoint(uprobe, vma->vm_mm, vma, vaddr);
+			install_breakpoint(uprobe, vma, vaddr);
 		}
 		put_uprobe(uprobe);
 	}
@@ -1956,6 +1963,9 @@ static void free_ret_instance(struct uprobe_task *utask,
 	 * to-be-reused return instances for future uretprobes. If ri_timer()
 	 * happens to be running right now, though, we fallback to safety and
 	 * just perform RCU-delated freeing of ri.
+	 * Admittedly, this is a rather simple use of seqcount, but it nicely
+	 * abstracts away all the necessary memory barriers, so we use
+	 * a well-supported kernel primitive here.
 	 */
 	if (raw_seqcount_try_begin(&utask->ri_seqcount, seq)) {
 		/* immediate reuse of ri without RCU GP is OK */
@@ -2016,12 +2026,20 @@ static void ri_timer(struct timer_list *timer)
 	/* RCU protects return_instance from freeing. */
 	guard(rcu)();
 
-	write_seqcount_begin(&utask->ri_seqcount);
+	/*
+	 * See free_ret_instance() for notes on seqcount use.
+	 * We also employ raw API variants to avoid lockdep false-positive
+	 * warning complaining about enabled preemption. The timer can only be
+	 * invoked once for a uprobe_task. Therefore there can only be one
+	 * writer. The reader does not require an even sequence count to make
+	 * progress, so it is OK to remain preemptible on PREEMPT_RT.
+	 */
+	raw_write_seqcount_begin(&utask->ri_seqcount);
 
 	for_each_ret_instance_rcu(ri, utask->return_instances)
 		hprobe_expire(&ri->hprobe, false);
 
-	write_seqcount_end(&utask->ri_seqcount);
+	raw_write_seqcount_end(&utask->ri_seqcount);
 }
 
 static struct uprobe_task *alloc_utask(void)