Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Mere overlapping changes in the conflicts here.

Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 195 insertions, 108 deletions

diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 2fa710bb6358..c15d8ae68c96 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -778,15 +778,17 @@ static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr,
 	return 0;
 }
 
-int kasan_populate_vmalloc(unsigned long requested_size, struct vm_struct *area)
+int kasan_populate_vmalloc(unsigned long addr, unsigned long size)
 {
 	unsigned long shadow_start, shadow_end;
 	int ret;
 
-	shadow_start = (unsigned long)kasan_mem_to_shadow(area->addr);
+	if (!is_vmalloc_or_module_addr((void *)addr))
+		return 0;
+
+	shadow_start = (unsigned long)kasan_mem_to_shadow((void *)addr);
 	shadow_start = ALIGN_DOWN(shadow_start, PAGE_SIZE);
-	shadow_end = (unsigned long)kasan_mem_to_shadow(area->addr +
-							area->size);
+	shadow_end = (unsigned long)kasan_mem_to_shadow((void *)addr + size);
 	shadow_end = ALIGN(shadow_end, PAGE_SIZE);
 
 	ret = apply_to_page_range(&init_mm, shadow_start,
@@ -797,10 +799,6 @@ int kasan_populate_vmalloc(unsigned long requested_size, struct vm_struct *area)
 
 	flush_cache_vmap(shadow_start, shadow_end);
 
-	kasan_unpoison_shadow(area->addr, requested_size);
-
-	area->flags |= VM_KASAN;
-
 	/*
 	 * We need to be careful about inter-cpu effects here. Consider:
 	 *
@@ -843,12 +841,23 @@ int kasan_populate_vmalloc(unsigned long requested_size, struct vm_struct *area)
  * Poison the shadow for a vmalloc region. Called as part of the
  * freeing process at the time the region is freed.
  */
-void kasan_poison_vmalloc(void *start, unsigned long size)
+void kasan_poison_vmalloc(const void *start, unsigned long size)
 {
+	if (!is_vmalloc_or_module_addr(start))
+		return;
+
 	size = round_up(size, KASAN_SHADOW_SCALE_SIZE);
 	kasan_poison_shadow(start, size, KASAN_VMALLOC_INVALID);
 }
 
+void kasan_unpoison_vmalloc(const void *start, unsigned long size)
+{
+	if (!is_vmalloc_or_module_addr(start))
+		return;
+
+	kasan_unpoison_shadow(start, size);
+}
+
 static int kasan_depopulate_vmalloc_pte(pte_t *ptep, unsigned long addr,
 					void *unused)
 {
@@ -948,6 +957,7 @@ void kasan_release_vmalloc(unsigned long start, unsigned long end,
 {
 	void *shadow_start, *shadow_end;
 	unsigned long region_start, region_end;
+	unsigned long size;
 
 	region_start = ALIGN(start, PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE);
 	region_end = ALIGN_DOWN(end, PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE);
@@ -970,9 +980,11 @@ void kasan_release_vmalloc(unsigned long start, unsigned long end,
 	shadow_end = kasan_mem_to_shadow((void *)region_end);
 
 	if (shadow_end > shadow_start) {
-		apply_to_page_range(&init_mm, (unsigned long)shadow_start,
-				    (unsigned long)(shadow_end - shadow_start),
-				    kasan_depopulate_vmalloc_pte, NULL);
+		size = shadow_end - shadow_start;
+		apply_to_existing_page_range(&init_mm,
+					     (unsigned long)shadow_start,
+					     size, kasan_depopulate_vmalloc_pte,
+					     NULL);
 		flush_tlb_kernel_range((unsigned long)shadow_start,
 				       (unsigned long)shadow_end);
 	}
diff --git a/mm/memory.c b/mm/memory.c
index 606da187d1de..45442d9a4f52 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2021,26 +2021,34 @@ EXPORT_SYMBOL(vm_iomap_memory);
 
 static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data)
+				     pte_fn_t fn, void *data, bool create)
 {
 	pte_t *pte;
-	int err;
+	int err = 0;
 	spinlock_t *uninitialized_var(ptl);
 
-	pte = (mm == &init_mm) ?
-		pte_alloc_kernel(pmd, addr) :
-		pte_alloc_map_lock(mm, pmd, addr, &ptl);
-	if (!pte)
-		return -ENOMEM;
+	if (create) {
+		pte = (mm == &init_mm) ?
+			pte_alloc_kernel(pmd, addr) :
+			pte_alloc_map_lock(mm, pmd, addr, &ptl);
+		if (!pte)
+			return -ENOMEM;
+	} else {
+		pte = (mm == &init_mm) ?
+			pte_offset_kernel(pmd, addr) :
+			pte_offset_map_lock(mm, pmd, addr, &ptl);
+	}
 
 	BUG_ON(pmd_huge(*pmd));
 
 	arch_enter_lazy_mmu_mode();
 
 	do {
-		err = fn(pte++, addr, data);
-		if (err)
-			break;
+		if (create || !pte_none(*pte)) {
+			err = fn(pte++, addr, data);
+			if (err)
+				break;
+		}
 	} while (addr += PAGE_SIZE, addr != end);
 
 	arch_leave_lazy_mmu_mode();
@@ -2052,77 +2060,95 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 
 static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data)
+				     pte_fn_t fn, void *data, bool create)
 {
 	pmd_t *pmd;
 	unsigned long next;
-	int err;
+	int err = 0;
 
 	BUG_ON(pud_huge(*pud));
 
-	pmd = pmd_alloc(mm, pud, addr);
-	if (!pmd)
-		return -ENOMEM;
+	if (create) {
+		pmd = pmd_alloc(mm, pud, addr);
+		if (!pmd)
+			return -ENOMEM;
+	} else {
+		pmd = pmd_offset(pud, addr);
+	}
 	do {
 		next = pmd_addr_end(addr, end);
-		err = apply_to_pte_range(mm, pmd, addr, next, fn, data);
-		if (err)
-			break;
+		if (create || !pmd_none_or_clear_bad(pmd)) {
+			err = apply_to_pte_range(mm, pmd, addr, next, fn, data,
+						 create);
+			if (err)
+				break;
+		}
 	} while (pmd++, addr = next, addr != end);
 	return err;
 }
 
 static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data)
+				     pte_fn_t fn, void *data, bool create)
 {
 	pud_t *pud;
 	unsigned long next;
-	int err;
+	int err = 0;
 
-	pud = pud_alloc(mm, p4d, addr);
-	if (!pud)
-		return -ENOMEM;
+	if (create) {
+		pud = pud_alloc(mm, p4d, addr);
+		if (!pud)
+			return -ENOMEM;
+	} else {
+		pud = pud_offset(p4d, addr);
+	}
 	do {
 		next = pud_addr_end(addr, end);
-		err = apply_to_pmd_range(mm, pud, addr, next, fn, data);
-		if (err)
-			break;
+		if (create || !pud_none_or_clear_bad(pud)) {
+			err = apply_to_pmd_range(mm, pud, addr, next, fn, data,
+						 create);
+			if (err)
+				break;
+		}
 	} while (pud++, addr = next, addr != end);
 	return err;
 }
 
 static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd,
 				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data)
+				     pte_fn_t fn, void *data, bool create)
 {
 	p4d_t *p4d;
 	unsigned long next;
-	int err;
+	int err = 0;
 
-	p4d = p4d_alloc(mm, pgd, addr);
-	if (!p4d)
-		return -ENOMEM;
+	if (create) {
+		p4d = p4d_alloc(mm, pgd, addr);
+		if (!p4d)
+			return -ENOMEM;
+	} else {
+		p4d = p4d_offset(pgd, addr);
+	}
 	do {
 		next = p4d_addr_end(addr, end);
-		err = apply_to_pud_range(mm, p4d, addr, next, fn, data);
-		if (err)
-			break;
+		if (create || !p4d_none_or_clear_bad(p4d)) {
+			err = apply_to_pud_range(mm, p4d, addr, next, fn, data,
+						 create);
+			if (err)
+				break;
+		}
 	} while (p4d++, addr = next, addr != end);
 	return err;
 }
 
-/*
- * Scan a region of virtual memory, filling in page tables as necessary
- * and calling a provided function on each leaf page table.
- */
-int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
-			unsigned long size, pte_fn_t fn, void *data)
+static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr,
+				 unsigned long size, pte_fn_t fn,
+				 void *data, bool create)
 {
 	pgd_t *pgd;
 	unsigned long next;
 	unsigned long end = addr + size;
-	int err;
+	int err = 0;
 
 	if (WARN_ON(addr >= end))
 		return -EINVAL;
@@ -2130,16 +2156,42 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 	pgd = pgd_offset(mm, addr);
 	do {
 		next = pgd_addr_end(addr, end);
-		err = apply_to_p4d_range(mm, pgd, addr, next, fn, data);
+		if (!create && pgd_none_or_clear_bad(pgd))
+			continue;
+		err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create);
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
 
 	return err;
 }
+
+/*
+ * Scan a region of virtual memory, filling in page tables as necessary
+ * and calling a provided function on each leaf page table.
+ */
+int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
+			unsigned long size, pte_fn_t fn, void *data)
+{
+	return __apply_to_page_range(mm, addr, size, fn, data, true);
+}
 EXPORT_SYMBOL_GPL(apply_to_page_range);
 
 /*
+ * Scan a region of virtual memory, calling a provided function on
+ * each leaf page table where it exists.
+ *
+ * Unlike apply_to_page_range, this does _not_ fill in page tables
+ * where they are absent.
+ */
+int apply_to_existing_page_range(struct mm_struct *mm, unsigned long addr,
+				 unsigned long size, pte_fn_t fn, void *data)
+{
+	return __apply_to_page_range(mm, addr, size, fn, data, false);
+}
+EXPORT_SYMBOL_GPL(apply_to_existing_page_range);
+
+/*
  * handle_pte_fault chooses page fault handler according to an entry which was
  * read non-atomically.  Before making any commitment, on those architectures
  * or configurations (e.g. i386 with PAE) which might give a mix of unmatched
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 4d3b3d60d893..e9681dc4aa75 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1062,6 +1062,26 @@ __alloc_vmap_area(unsigned long size, unsigned long align,
 }
 
 /*
+ * Free a region of KVA allocated by alloc_vmap_area
+ */
+static void free_vmap_area(struct vmap_area *va)
+{
+	/*
+	 * Remove from the busy tree/list.
+	 */
+	spin_lock(&vmap_area_lock);
+	unlink_va(va, &vmap_area_root);
+	spin_unlock(&vmap_area_lock);
+
+	/*
+	 * Insert/Merge it back to the free tree/list.
+	 */
+	spin_lock(&free_vmap_area_lock);
+	merge_or_add_vmap_area(va, &free_vmap_area_root, &free_vmap_area_list);
+	spin_unlock(&free_vmap_area_lock);
+}
+
+/*
  * Allocate a region of KVA of the specified size and alignment, within the
  * vstart and vend.
  */
@@ -1073,6 +1093,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
 	struct vmap_area *va, *pva;
 	unsigned long addr;
 	int purged = 0;
+	int ret;
 
 	BUG_ON(!size);
 	BUG_ON(offset_in_page(size));
@@ -1139,6 +1160,7 @@ retry:
 	va->va_end = addr + size;
 	va->vm = NULL;
 
+
 	spin_lock(&vmap_area_lock);
 	insert_vmap_area(va, &vmap_area_root, &vmap_area_list);
 	spin_unlock(&vmap_area_lock);
@@ -1147,6 +1169,12 @@ retry:
 	BUG_ON(va->va_start < vstart);
 	BUG_ON(va->va_end > vend);
 
+	ret = kasan_populate_vmalloc(addr, size);
+	if (ret) {
+		free_vmap_area(va);
+		return ERR_PTR(ret);
+	}
+
 	return va;
 
 overflow:
@@ -1186,26 +1214,6 @@ int unregister_vmap_purge_notifier(struct notifier_block *nb)
 EXPORT_SYMBOL_GPL(unregister_vmap_purge_notifier);
 
 /*
- * Free a region of KVA allocated by alloc_vmap_area
- */
-static void free_vmap_area(struct vmap_area *va)
-{
-	/*
-	 * Remove from the busy tree/list.
-	 */
-	spin_lock(&vmap_area_lock);
-	unlink_va(va, &vmap_area_root);
-	spin_unlock(&vmap_area_lock);
-
-	/*
-	 * Insert/Merge it back to the free tree/list.
-	 */
-	spin_lock(&free_vmap_area_lock);
-	merge_or_add_vmap_area(va, &free_vmap_area_root, &free_vmap_area_list);
-	spin_unlock(&free_vmap_area_lock);
-}
-
-/*
  * Clear the pagetable entries of a given vmap_area
  */
 static void unmap_vmap_area(struct vmap_area *va)
@@ -1771,6 +1779,8 @@ void vm_unmap_ram(const void *mem, unsigned int count)
 	BUG_ON(addr > VMALLOC_END);
 	BUG_ON(!PAGE_ALIGNED(addr));
 
+	kasan_poison_vmalloc(mem, size);
+
 	if (likely(count <= VMAP_MAX_ALLOC)) {
 		debug_check_no_locks_freed(mem, size);
 		vb_free(mem, size);
@@ -1821,6 +1831,9 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t pro
 		addr = va->va_start;
 		mem = (void *)addr;
 	}
+
+	kasan_unpoison_vmalloc(mem, size);
+
 	if (vmap_page_range(addr, addr + size, prot, pages) < 0) {
 		vm_unmap_ram(mem, count);
 		return NULL;
@@ -2075,6 +2088,7 @@ static struct vm_struct *__get_vm_area_node(unsigned long size,
 {
 	struct vmap_area *va;
 	struct vm_struct *area;
+	unsigned long requested_size = size;
 
 	BUG_ON(in_interrupt());
 	size = PAGE_ALIGN(size);
@@ -2098,23 +2112,9 @@ static struct vm_struct *__get_vm_area_node(unsigned long size,
 		return NULL;
 	}
 
-	setup_vmalloc_vm(area, va, flags, caller);
+	kasan_unpoison_vmalloc((void *)va->va_start, requested_size);
 
-	/*
-	 * For KASAN, if we are in vmalloc space, we need to cover the shadow
-	 * area with real memory. If we come here through VM_ALLOC, this is
-	 * done by a higher level function that has access to the true size,
-	 * which might not be a full page.
-	 *
-	 * We assume module space comes via VM_ALLOC path.
-	 */
-	if (is_vmalloc_addr(area->addr) && !(area->flags & VM_ALLOC)) {
-		if (kasan_populate_vmalloc(area->size, area)) {
-			unmap_vmap_area(va);
-			kfree(area);
-			return NULL;
-		}
-	}
+	setup_vmalloc_vm(area, va, flags, caller);
 
 	return area;
 }
@@ -2293,8 +2293,7 @@ static void __vunmap(const void *addr, int deallocate_pages)
 	debug_check_no_locks_freed(area->addr, get_vm_area_size(area));
 	debug_check_no_obj_freed(area->addr, get_vm_area_size(area));
 
-	if (area->flags & VM_KASAN)
-		kasan_poison_vmalloc(area->addr, area->size);
+	kasan_poison_vmalloc(area->addr, area->size);
 
 	vm_remove_mappings(area, deallocate_pages);
 
@@ -2539,7 +2538,7 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 	if (!size || (size >> PAGE_SHIFT) > totalram_pages())
 		goto fail;
 
-	area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNINITIALIZED |
+	area = __get_vm_area_node(real_size, align, VM_ALLOC | VM_UNINITIALIZED |
 				vm_flags, start, end, node, gfp_mask, caller);
 	if (!area)
 		goto fail;
@@ -2548,11 +2547,6 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 	if (!addr)
 		return NULL;
 
-	if (is_vmalloc_or_module_addr(area->addr)) {
-		if (kasan_populate_vmalloc(real_size, area))
-			return NULL;
-	}
-
 	/*
 	 * In this function, newly allocated vm_struct has VM_UNINITIALIZED
 	 * flag. It means that vm_struct is not fully initialized.
@@ -3294,7 +3288,7 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
 	struct vmap_area **vas, *va;
 	struct vm_struct **vms;
 	int area, area2, last_area, term_area;
-	unsigned long base, start, size, end, last_end;
+	unsigned long base, start, size, end, last_end, orig_start, orig_end;
 	bool purged = false;
 	enum fit_type type;
 
@@ -3424,6 +3418,15 @@ retry:
 
 	spin_unlock(&free_vmap_area_lock);
 
+	/* populate the kasan shadow space */
+	for (area = 0; area < nr_vms; area++) {
+		if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area]))
+			goto err_free_shadow;
+
+		kasan_unpoison_vmalloc((void *)vas[area]->va_start,
+				       sizes[area]);
+	}
+
 	/* insert all vm's */
 	spin_lock(&vmap_area_lock);
 	for (area = 0; area < nr_vms; area++) {
@@ -3434,12 +3437,6 @@ retry:
 	}
 	spin_unlock(&vmap_area_lock);
 
-	/* populate the shadow space outside of the lock */
-	for (area = 0; area < nr_vms; area++) {
-		/* assume success here */
-		kasan_populate_vmalloc(sizes[area], vms[area]);
-	}
-
 	kfree(vas);
 	return vms;
 
@@ -3451,8 +3448,12 @@ recovery:
 	 * and when pcpu_get_vm_areas() is success.
 	 */
 	while (area--) {
-		merge_or_add_vmap_area(vas[area], &free_vmap_area_root,
-				       &free_vmap_area_list);
+		orig_start = vas[area]->va_start;
+		orig_end = vas[area]->va_end;
+		va = merge_or_add_vmap_area(vas[area], &free_vmap_area_root,
+					    &free_vmap_area_list);
+		kasan_release_vmalloc(orig_start, orig_end,
+				      va->va_start, va->va_end);
 		vas[area] = NULL;
 	}
 
@@ -3487,6 +3488,28 @@ err_free2:
 	kfree(vas);
 	kfree(vms);
 	return NULL;
+
+err_free_shadow:
+	spin_lock(&free_vmap_area_lock);
+	/*
+	 * We release all the vmalloc shadows, even the ones for regions that
+	 * hadn't been successfully added. This relies on kasan_release_vmalloc
+	 * being able to tolerate this case.
+	 */
+	for (area = 0; area < nr_vms; area++) {
+		orig_start = vas[area]->va_start;
+		orig_end = vas[area]->va_end;
+		va = merge_or_add_vmap_area(vas[area], &free_vmap_area_root,
+					    &free_vmap_area_list);
+		kasan_release_vmalloc(orig_start, orig_end,
+				      va->va_start, va->va_end);
+		vas[area] = NULL;
+		kfree(vms[area]);
+	}
+	spin_unlock(&free_vmap_area_lock);
+	kfree(vas);
+	kfree(vms);
+	return NULL;
 }
 
 /**
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 74e8edce83ca..572fb17c6273 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -387,7 +387,7 @@ void register_shrinker_prepared(struct shrinker *shrinker)
 {
 	down_write(&shrinker_rwsem);
 	list_add_tail(&shrinker->list, &shrinker_list);
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
 	if (shrinker->flags & SHRINKER_MEMCG_AWARE)
 		idr_replace(&shrinker_idr, shrinker, shrinker->id);
 #endif