Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:
 "Incoming:

   - a small number of updates to scripts/, ocfs2 and fs/buffer.c

   - most of MM

  I still have quite a lot of material (mostly not MM) staged after
  linux-next due to -next dependencies. I'll send those across next week
  as the preprequisites get merged up"

* emailed patches from Andrew Morton <[email protected]>: (135 commits)
  mm/page_io.c: annotate refault stalls from swap_readpage
  mm/Kconfig: fix trivial help text punctuation
  mm/Kconfig: fix indentation
  mm/memory_hotplug.c: remove __online_page_set_limits()
  mm: fix typos in comments when calling __SetPageUptodate()
  mm: fix struct member name in function comments
  mm/shmem.c: cast the type of unmap_start to u64
  mm: shmem: use proper gfp flags for shmem_writepage()
  mm/shmem.c: make array 'values' static const, makes object smaller
  userfaultfd: require CAP_SYS_PTRACE for UFFD_FEATURE_EVENT_FORK
  fs/userfaultfd.c: wp: clear VM_UFFD_MISSING or VM_UFFD_WP during userfaultfd_register()
  userfaultfd: wrap the common dst_vma check into an inlined function
  userfaultfd: remove unnecessary WARN_ON() in __mcopy_atomic_hugetlb()
  userfaultfd: use vma_pagesize for all huge page size calculation
  mm/madvise.c: use PAGE_ALIGN[ED] for range checking
  mm/madvise.c: replace with page_size() in madvise_inject_error()
  mm/mmap.c: make vma_merge() comment more easy to understand
  mm/hwpoison-inject: use DEFINE_DEBUGFS_ATTRIBUTE to define debugfs fops
  autonuma: reduce cache footprint when scanning page tables
  autonuma: fix watermark checking in migrate_balanced_pgdat()
  ...

Documentation/admin-guide/cgroup-v2.rst

@@ -1288,7 +1288,12 @@ PAGE_SIZE multiple when read back.
 	  inactive_anon, active_anon, inactive_file, active_file, unevictable
 		Amount of memory, swap-backed and filesystem-backed,
 		on the internal memory management lists used by the
-		page reclaim algorithm
+		page reclaim algorithm.
+
+		As these represent internal list state (eg. shmem pages are on anon
+		memory management lists), inactive_foo + active_foo may not be equal to
+		the value for the foo counter, since the foo counter is type-based, not
+		list-based.
 
 	  slab_reclaimable
 		Part of "slab" that might be reclaimed, such as

Documentation/dev-tools/kasan.rst

@@ -218,3 +218,66 @@ brk handler is used to print bug reports.
 A potential expansion of this mode is a hardware tag-based mode, which would
 use hardware memory tagging support instead of compiler instrumentation and
 manual shadow memory manipulation.
+
+What memory accesses are sanitised by KASAN?
+--------------------------------------------
+
+The kernel maps memory in a number of different parts of the address
+space. This poses something of a problem for KASAN, which requires
+that all addresses accessed by instrumented code have a valid shadow
+region.
+
+The range of kernel virtual addresses is large: there is not enough
+real memory to support a real shadow region for every address that
+could be accessed by the kernel.
+
+By default
+~~~~~~~~~~
+
+By default, architectures only map real memory over the shadow region
+for the linear mapping (and potentially other small areas). For all
+other areas - such as vmalloc and vmemmap space - a single read-only
+page is mapped over the shadow area. This read-only shadow page
+declares all memory accesses as permitted.
+
+This presents a problem for modules: they do not live in the linear
+mapping, but in a dedicated module space. By hooking in to the module
+allocator, KASAN can temporarily map real shadow memory to cover
+them. This allows detection of invalid accesses to module globals, for
+example.
+
+This also creates an incompatibility with ``VMAP_STACK``: if the stack
+lives in vmalloc space, it will be shadowed by the read-only page, and
+the kernel will fault when trying to set up the shadow data for stack
+variables.
+
+CONFIG_KASAN_VMALLOC
+~~~~~~~~~~~~~~~~~~~~
+
+With ``CONFIG_KASAN_VMALLOC``, KASAN can cover vmalloc space at the
+cost of greater memory usage. Currently this is only supported on x86.
+
+This works by hooking into vmalloc and vmap, and dynamically
+allocating real shadow memory to back the mappings.
+
+Most mappings in vmalloc space are small, requiring less than a full
+page of shadow space. Allocating a full shadow page per mapping would
+therefore be wasteful. Furthermore, to ensure that different mappings
+use different shadow pages, mappings would have to be aligned to
+``KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE``.
+
+Instead, we share backing space across multiple mappings. We allocate
+a backing page when a mapping in vmalloc space uses a particular page
+of the shadow region. This page can be shared by other vmalloc
+mappings later on.
+
+We hook in to the vmap infrastructure to lazily clean up unused shadow
+memory.
+
+To avoid the difficulties around swapping mappings around, we expect
+that the part of the shadow region that covers the vmalloc space will
+not be covered by the early shadow page, but will be left
+unmapped. This will require changes in arch-specific code.
+
+This allows ``VMAP_STACK`` support on x86, and can simplify support of
+architectures that do not have a fixed module region.

arch/Kconfig

@@ -836,16 +836,17 @@ config HAVE_ARCH_VMAP_STACK
 config VMAP_STACK
 	default y
 	bool "Use a virtually-mapped stack"
-	depends on HAVE_ARCH_VMAP_STACK && !KASAN
+	depends on HAVE_ARCH_VMAP_STACK
+	depends on !KASAN || KASAN_VMALLOC
 	---help---
 	  Enable this if you want the use virtually-mapped kernel stacks
 	  with guard pages.  This causes kernel stack overflows to be
 	  caught immediately rather than causing difficult-to-diagnose
 	  corruption.
 
-	  This is presently incompatible with KASAN because KASAN expects
-	  the stack to map directly to the KASAN shadow map using a formula
-	  that is incorrect if the stack is in vmalloc space.
+	  To use this with KASAN, the architecture must support backing
+	  virtual mappings with real shadow memory, and KASAN_VMALLOC must
+	  be enabled.
 
 config ARCH_OPTIONAL_KERNEL_RWX
 	def_bool n

arch/arc/include/asm/pgtable.h

@@ -33,7 +33,6 @@
 #define _ASM_ARC_PGTABLE_H
 
 #include <linux/bits.h>
-#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 #include <asm/page.h>
 #include <asm/mmu.h>	/* to propagate CONFIG_ARC_MMU_VER <n> */

arch/arc/mm/fault.c

@@ -30,6 +30,7 @@ noinline static int handle_kernel_vaddr_fault(unsigned long address)
 	 * with the 'reference' page table.
 	 */
 	pgd_t *pgd, *pgd_k;
+	p4d_t *p4d, *p4d_k;
 	pud_t *pud, *pud_k;
 	pmd_t *pmd, *pmd_k;
 
@@ -39,8 +40,13 @@ noinline static int handle_kernel_vaddr_fault(unsigned long address)
 	if (!pgd_present(*pgd_k))
 		goto bad_area;
 
-	pud = pud_offset(pgd, address);
-	pud_k = pud_offset(pgd_k, address);
+	p4d = p4d_offset(pgd, address);
+	p4d_k = p4d_offset(pgd_k, address);
+	if (!p4d_present(*p4d_k))
+		goto bad_area;
+
+	pud = pud_offset(p4d, address);
+	pud_k = pud_offset(p4d_k, address);
 	if (!pud_present(*pud_k))
 		goto bad_area;
 

arch/arc/mm/highmem.c

@@ -111,12 +111,14 @@ EXPORT_SYMBOL(__kunmap_atomic);
 static noinline pte_t * __init alloc_kmap_pgtable(unsigned long kvaddr)
 {
 	pgd_t *pgd_k;
+	p4d_t *p4d_k;
 	pud_t *pud_k;
 	pmd_t *pmd_k;
 	pte_t *pte_k;
 
 	pgd_k = pgd_offset_k(kvaddr);
-	pud_k = pud_offset(pgd_k, kvaddr);
+	p4d_k = p4d_offset(pgd_k, kvaddr);
+	pud_k = pud_offset(p4d_k, kvaddr);
 	pmd_k = pmd_offset(pud_k, kvaddr);
 
 	pte_k = (pte_t *)memblock_alloc_low(PAGE_SIZE, PAGE_SIZE);

arch/powerpc/include/asm/book3s/64/pgtable-4k.h

@@ -70,9 +70,6 @@ static inline int get_hugepd_cache_index(int index)
 	/* should not reach */
 }
 
-#else /* !CONFIG_HUGETLB_PAGE */
-static inline int pmd_huge(pmd_t pmd) { return 0; }
-static inline int pud_huge(pud_t pud) { return 0; }
 #endif /* CONFIG_HUGETLB_PAGE */
 
 #endif /* __ASSEMBLY__ */

arch/powerpc/include/asm/book3s/64/pgtable-64k.h

@@ -59,9 +59,6 @@ static inline int get_hugepd_cache_index(int index)
 	BUG();
 }
 
-#else /* !CONFIG_HUGETLB_PAGE */
-static inline int pmd_huge(pmd_t pmd) { return 0; }
-static inline int pud_huge(pud_t pud) { return 0; }
 #endif /* CONFIG_HUGETLB_PAGE */
 
 static inline int remap_4k_pfn(struct vm_area_struct *vma, unsigned long addr,

arch/powerpc/mm/book3s64/radix_pgtable.c

@@ -13,6 +13,7 @@
 #include <linux/memblock.h>
 #include <linux/of_fdt.h>
 #include <linux/mm.h>
+#include <linux/hugetlb.h>
 #include <linux/string_helpers.h>
 #include <linux/stop_machine.h>
 

arch/x86/Kconfig

@@ -134,6 +134,7 @@ config X86
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE
 	select HAVE_ARCH_KASAN			if X86_64
+	select HAVE_ARCH_KASAN_VMALLOC		if X86_64
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_MMAP_RND_BITS		if MMU
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS	if MMU && COMPAT

arch/x86/mm/kasan_init_64.c

@@ -245,6 +245,49 @@ static void __init kasan_map_early_shadow(pgd_t *pgd)
 	} while (pgd++, addr = next, addr != end);
 }
 
+static void __init kasan_shallow_populate_p4ds(pgd_t *pgd,
+					       unsigned long addr,
+					       unsigned long end)
+{
+	p4d_t *p4d;
+	unsigned long next;
+	void *p;
+
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+
+		if (p4d_none(*p4d)) {
+			p = early_alloc(PAGE_SIZE, NUMA_NO_NODE, true);
+			p4d_populate(&init_mm, p4d, p);
+		}
+	} while (p4d++, addr = next, addr != end);
+}
+
+static void __init kasan_shallow_populate_pgds(void *start, void *end)
+{
+	unsigned long addr, next;
+	pgd_t *pgd;
+	void *p;
+
+	addr = (unsigned long)start;
+	pgd = pgd_offset_k(addr);
+	do {
+		next = pgd_addr_end(addr, (unsigned long)end);
+
+		if (pgd_none(*pgd)) {
+			p = early_alloc(PAGE_SIZE, NUMA_NO_NODE, true);
+			pgd_populate(&init_mm, pgd, p);
+		}
+
+		/*
+		 * we need to populate p4ds to be synced when running in
+		 * four level mode - see sync_global_pgds_l4()
+		 */
+		kasan_shallow_populate_p4ds(pgd, addr, next);
+	} while (pgd++, addr = next, addr != (unsigned long)end);
+}
+
 #ifdef CONFIG_KASAN_INLINE
 static int kasan_die_handler(struct notifier_block *self,
 			     unsigned long val,
@@ -354,6 +397,24 @@ void __init kasan_init(void)
 
 	kasan_populate_early_shadow(
 		kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM),
+		kasan_mem_to_shadow((void *)VMALLOC_START));
+
+	/*
+	 * If we're in full vmalloc mode, don't back vmalloc space with early
+	 * shadow pages. Instead, prepopulate pgds/p4ds so they are synced to
+	 * the global table and we can populate the lower levels on demand.
+	 */
+	if (IS_ENABLED(CONFIG_KASAN_VMALLOC))
+		kasan_shallow_populate_pgds(
+			kasan_mem_to_shadow((void *)VMALLOC_START),
+			kasan_mem_to_shadow((void *)VMALLOC_END));
+	else
+		kasan_populate_early_shadow(
+			kasan_mem_to_shadow((void *)VMALLOC_START),
+			kasan_mem_to_shadow((void *)VMALLOC_END));
+
+	kasan_populate_early_shadow(
+		kasan_mem_to_shadow((void *)VMALLOC_END + 1),
 		shadow_cpu_entry_begin);
 
 	kasan_populate_shadow((unsigned long)shadow_cpu_entry_begin,

drivers/base/memory.c

@@ -19,15 +19,12 @@
 #include <linux/memory.h>
 #include <linux/memory_hotplug.h>
 #include <linux/mm.h>
-#include <linux/mutex.h>
 #include <linux/stat.h>
 #include <linux/slab.h>
 
 #include <linux/atomic.h>
 #include <linux/uaccess.h>
 
-static DEFINE_MUTEX(mem_sysfs_mutex);
-
 #define MEMORY_CLASS_NAME	"memory"
 
 #define to_memory_block(dev) container_of(dev, struct memory_block, dev)
@@ -538,12 +535,7 @@ static ssize_t soft_offline_page_store(struct device *dev,
 	if (kstrtoull(buf, 0, &pfn) < 0)
 		return -EINVAL;
 	pfn >>= PAGE_SHIFT;
-	if (!pfn_valid(pfn))
-		return -ENXIO;
-	/* Only online pages can be soft-offlined (esp., not ZONE_DEVICE). */
-	if (!pfn_to_online_page(pfn))
-		return -EIO;
-	ret = soft_offline_page(pfn_to_page(pfn), 0);
+	ret = soft_offline_page(pfn, 0);
 	return ret == 0 ? count : ret;
 }
 
@@ -705,6 +697,8 @@ static void unregister_memory(struct memory_block *memory)
  * Create memory block devices for the given memory area. Start and size
  * have to be aligned to memory block granularity. Memory block devices
  * will be initialized as offline.
+ *
+ * Called under device_hotplug_lock.
  */
 int create_memory_block_devices(unsigned long start, unsigned long size)
 {
@@ -718,7 +712,6 @@ int create_memory_block_devices(unsigned long start, unsigned long size)
 			 !IS_ALIGNED(size, memory_block_size_bytes())))
 		return -EINVAL;
 
-	mutex_lock(&mem_sysfs_mutex);
 	for (block_id = start_block_id; block_id != end_block_id; block_id++) {
 		ret = init_memory_block(&mem, block_id, MEM_OFFLINE);
 		if (ret)
@@ -730,18 +723,21 @@ int create_memory_block_devices(unsigned long start, unsigned long size)
 		for (block_id = start_block_id; block_id != end_block_id;
 		     block_id++) {
 			mem = find_memory_block_by_id(block_id);
+			if (WARN_ON_ONCE(!mem))
+				continue;
 			mem->section_count = 0;
 			unregister_memory(mem);
 		}
 	}
-	mutex_unlock(&mem_sysfs_mutex);
 	return ret;
 }
 
 /*
  * Remove memory block devices for the given memory area. Start and size
  * have to be aligned to memory block granularity. Memory block devices
  * have to be offline.
+ *
+ * Called under device_hotplug_lock.
  */
 void remove_memory_block_devices(unsigned long start, unsigned long size)
 {
@@ -754,7 +750,6 @@ void remove_memory_block_devices(unsigned long start, unsigned long size)
 			 !IS_ALIGNED(size, memory_block_size_bytes())))
 		return;
 
-	mutex_lock(&mem_sysfs_mutex);
 	for (block_id = start_block_id; block_id != end_block_id; block_id++) {
 		mem = find_memory_block_by_id(block_id);
 		if (WARN_ON_ONCE(!mem))
@@ -763,7 +758,6 @@ void remove_memory_block_devices(unsigned long start, unsigned long size)
 		unregister_memory_block_under_nodes(mem);
 		unregister_memory(mem);
 	}
-	mutex_unlock(&mem_sysfs_mutex);
 }
 
 /* return true if the memory block is offlined, otherwise, return false */
@@ -797,12 +791,13 @@ static const struct attribute_group *memory_root_attr_groups[] = {
 };
 
 /*
- * Initialize the sysfs support for memory devices...
+ * Initialize the sysfs support for memory devices. At the time this function
+ * is called, we cannot have concurrent creation/deletion of memory block
+ * devices, the device_hotplug_lock is not needed.
  */
 void __init memory_dev_init(void)
 {
 	int ret;
-	int err;
 	unsigned long block_sz, nr;
 
 	/* Validate the configured memory block size */
@@ -813,24 +808,19 @@ void __init memory_dev_init(void)
 
 	ret = subsys_system_register(&memory_subsys, memory_root_attr_groups);
 	if (ret)
-		goto out;
+		panic("%s() failed to register subsystem: %d\n", __func__, ret);
 
 	/*
 	 * Create entries for memory sections that were found
 	 * during boot and have been initialized
 	 */
-	mutex_lock(&mem_sysfs_mutex);
 	for (nr = 0; nr <= __highest_present_section_nr;
 	     nr += sections_per_block) {
-		err = add_memory_block(nr);
-		if (!ret)
-			ret = err;
+		ret = add_memory_block(nr);
+		if (ret)
+			panic("%s() failed to add memory block: %d\n", __func__,
+			      ret);
 	}
-	mutex_unlock(&mem_sysfs_mutex);
-
-out:
-	if (ret)
-		panic("%s() failed: %d\n", __func__, ret);
 }
 
 /**