Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "The usual shower of hotfixes.

  Chris's memcg patches aren't actually fixes - they're mature but a few
  niggling review issues were late to arrive.

  The ocfs2 fixes are quite old - those took some time to get reviewer
  attention.

  Subsystems affected by this patch series: ocfs2, hotfixes, mm/memcg,
  mm/slab-generic"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm, sl[aou]b: guarantee natural alignment for kmalloc(power-of-two)
  mm, sl[ou]b: improve memory accounting
  mm, memcg: make scan aggression always exclude protection
  mm, memcg: make memory.emin the baseline for utilisation determination
  mm, memcg: proportional memory.{low,min} reclaim
  mm/vmpressure.c: fix a signedness bug in vmpressure_register_event()
  mm/page_alloc.c: fix a crash in free_pages_prepare()
  mm/z3fold.c: claim page in the beginning of free
  kernel/sysctl.c: do not override max_threads provided by userspace
  memcg: only record foreign writebacks with dirty pages when memcg is not disabled
  mm: fix -Wmissing-prototypes warnings
  writeback: fix use-after-free in finish_writeback_work()
  mm/memremap: drop unused SECTION_SIZE and SECTION_MASK
  panic: ensure preemption is disabled during panic()
  fs: ocfs2: fix a possible null-pointer dereference in ocfs2_info_scan_inode_alloc()
  fs: ocfs2: fix a possible null-pointer dereference in ocfs2_write_end_nolock()
  fs: ocfs2: fix possible null-pointer dereferences in ocfs2_xa_prepare_entry()
  ocfs2: clear zero in unaligned direct IO

Documentation/admin-guide/cgroup-v2.rst

@@ -615,8 +615,8 @@ on an IO device and is an example of this type.
 Protections
 -----------
 
-A cgroup is protected to be allocated upto the configured amount of
-the resource if the usages of all its ancestors are under their
+A cgroup is protected upto the configured amount of the resource
+as long as the usages of all its ancestors are under their
 protected levels.  Protections can be hard guarantees or best effort
 soft boundaries.  Protections can also be over-committed in which case
 only upto the amount available to the parent is protected among
@@ -1096,7 +1096,10 @@ PAGE_SIZE multiple when read back.
 	is within its effective min boundary, the cgroup's memory
 	won't be reclaimed under any conditions. If there is no
 	unprotected reclaimable memory available, OOM killer
-	is invoked.
+	is invoked. Above the effective min boundary (or
+	effective low boundary if it is higher), pages are reclaimed
+	proportionally to the overage, reducing reclaim pressure for
+	smaller overages.
 
        Effective min boundary is limited by memory.min values of
 	all ancestor cgroups. If there is memory.min overcommitment
@@ -1118,7 +1121,10 @@ PAGE_SIZE multiple when read back.
 	Best-effort memory protection.  If the memory usage of a
 	cgroup is within its effective low boundary, the cgroup's
 	memory won't be reclaimed unless memory can be reclaimed
-	from unprotected cgroups.
+	from unprotected cgroups.  Above the effective low boundary (or
+	effective min boundary if it is higher), pages are reclaimed
+	proportionally to the overage, reducing reclaim pressure for
+	smaller overages.
 
 	Effective low boundary is limited by memory.low values of
 	all ancestor cgroups. If there is memory.low overcommitment
@@ -2482,8 +2488,10 @@ system performance due to overreclaim, to the point where the feature
 becomes self-defeating.
 
 The memory.low boundary on the other hand is a top-down allocated
-reserve.  A cgroup enjoys reclaim protection when it's within its low,
-which makes delegation of subtrees possible.
+reserve.  A cgroup enjoys reclaim protection when it's within its
+effective low, which makes delegation of subtrees possible. It also
+enjoys having reclaim pressure proportional to its overage when
+above its effective low.
 
 The original high boundary, the hard limit, is defined as a strict
 limit that can not budge, even if the OOM killer has to be called.

Documentation/core-api/memory-allocation.rst

@@ -98,6 +98,10 @@ limited. The actual limit depends on the hardware and the kernel
 configuration, but it is a good practice to use `kmalloc` for objects
 smaller than page size.
 
+The address of a chunk allocated with `kmalloc` is aligned to at least
+ARCH_KMALLOC_MINALIGN bytes.  For sizes which are a power of two, the
+alignment is also guaranteed to be at least the respective size.
+
 For large allocations you can use :c:func:`vmalloc` and
 :c:func:`vzalloc`, or directly request pages from the page
 allocator. The memory allocated by `vmalloc` and related functions is

fs/fs-writeback.c

@@ -164,8 +164,13 @@ static void finish_writeback_work(struct bdi_writeback *wb,
 
 	if (work->auto_free)
 		kfree(work);
-	if (done && atomic_dec_and_test(&done->cnt))
-		wake_up_all(done->waitq);
+	if (done) {
+		wait_queue_head_t *waitq = done->waitq;
+
+		/* @done can't be accessed after the following dec */
+		if (atomic_dec_and_test(&done->cnt))
+			wake_up_all(waitq);
+	}
 }
 
 static void wb_queue_work(struct bdi_writeback *wb,

fs/ocfs2/aops.c

@@ -2049,7 +2049,8 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 		inode->i_mtime = inode->i_ctime = current_time(inode);
 		di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
 		di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
-		ocfs2_update_inode_fsync_trans(handle, inode, 1);
+		if (handle)
+			ocfs2_update_inode_fsync_trans(handle, inode, 1);
 	}
 	if (handle)
 		ocfs2_journal_dirty(handle, wc->w_di_bh);
@@ -2146,13 +2147,30 @@ static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock,
 	struct ocfs2_dio_write_ctxt *dwc = NULL;
 	struct buffer_head *di_bh = NULL;
 	u64 p_blkno;
-	loff_t pos = iblock << inode->i_sb->s_blocksize_bits;
+	unsigned int i_blkbits = inode->i_sb->s_blocksize_bits;
+	loff_t pos = iblock << i_blkbits;
+	sector_t endblk = (i_size_read(inode) - 1) >> i_blkbits;
 	unsigned len, total_len = bh_result->b_size;
 	int ret = 0, first_get_block = 0;
 
 	len = osb->s_clustersize - (pos & (osb->s_clustersize - 1));
 	len = min(total_len, len);
 
+	/*
+	 * bh_result->b_size is count in get_more_blocks according to write
+	 * "pos" and "end", we need map twice to return different buffer state:
+	 * 1. area in file size, not set NEW;
+	 * 2. area out file size, set  NEW.
+	 *
+	 *		   iblock    endblk
+	 * |--------|---------|---------|---------
+	 * |<-------area in file------->|
+	 */
+
+	if ((iblock <= endblk) &&
+	    ((iblock + ((len - 1) >> i_blkbits)) > endblk))
+		len = (endblk - iblock + 1) << i_blkbits;
+
 	mlog(0, "get block of %lu at %llu:%u req %u\n",
 			inode->i_ino, pos, len, total_len);
 
@@ -2236,6 +2254,9 @@ static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock,
 	if (desc->c_needs_zero)
 		set_buffer_new(bh_result);
 
+	if (iblock > endblk)
+		set_buffer_new(bh_result);
+
 	/* May sleep in end_io. It should not happen in a irq context. So defer
 	 * it to dio work queue. */
 	set_buffer_defer_completion(bh_result);

fs/ocfs2/ioctl.c

@@ -283,7 +283,7 @@ static int ocfs2_info_scan_inode_alloc(struct ocfs2_super *osb,
 	if (inode_alloc)
 		inode_lock(inode_alloc);
 
-	if (o2info_coherent(&fi->ifi_req)) {
+	if (inode_alloc && o2info_coherent(&fi->ifi_req)) {
 		status = ocfs2_inode_lock(inode_alloc, &bh, 0);
 		if (status < 0) {
 			mlog_errno(status);

fs/ocfs2/xattr.c

@@ -1490,18 +1490,6 @@ static int ocfs2_xa_check_space(struct ocfs2_xa_loc *loc,
 	return loc->xl_ops->xlo_check_space(loc, xi);
 }
 
-static void ocfs2_xa_add_entry(struct ocfs2_xa_loc *loc, u32 name_hash)
-{
-	loc->xl_ops->xlo_add_entry(loc, name_hash);
-	loc->xl_entry->xe_name_hash = cpu_to_le32(name_hash);
-	/*
-	 * We can't leave the new entry's xe_name_offset at zero or
-	 * add_namevalue() will go nuts.  We set it to the size of our
-	 * storage so that it can never be less than any other entry.
-	 */
-	loc->xl_entry->xe_name_offset = cpu_to_le16(loc->xl_size);
-}
-
 static void ocfs2_xa_add_namevalue(struct ocfs2_xa_loc *loc,
 				   struct ocfs2_xattr_info *xi)
 {
@@ -2133,29 +2121,31 @@ static int ocfs2_xa_prepare_entry(struct ocfs2_xa_loc *loc,
 	if (rc)
 		goto out;
 
-	if (loc->xl_entry) {
-		if (ocfs2_xa_can_reuse_entry(loc, xi)) {
-			orig_value_size = loc->xl_entry->xe_value_size;
-			rc = ocfs2_xa_reuse_entry(loc, xi, ctxt);
-			if (rc)
-				goto out;
-			goto alloc_value;
-		}
+	if (!loc->xl_entry) {
+		rc = -EINVAL;
+		goto out;
+	}
 
-		if (!ocfs2_xattr_is_local(loc->xl_entry)) {
-			orig_clusters = ocfs2_xa_value_clusters(loc);
-			rc = ocfs2_xa_value_truncate(loc, 0, ctxt);
-			if (rc) {
-				mlog_errno(rc);
-				ocfs2_xa_cleanup_value_truncate(loc,
-								"overwriting",
-								orig_clusters);
-				goto out;
-			}
+	if (ocfs2_xa_can_reuse_entry(loc, xi)) {
+		orig_value_size = loc->xl_entry->xe_value_size;
+		rc = ocfs2_xa_reuse_entry(loc, xi, ctxt);
+		if (rc)
+			goto out;
+		goto alloc_value;
+	}
+
+	if (!ocfs2_xattr_is_local(loc->xl_entry)) {
+		orig_clusters = ocfs2_xa_value_clusters(loc);
+		rc = ocfs2_xa_value_truncate(loc, 0, ctxt);
+		if (rc) {
+			mlog_errno(rc);
+			ocfs2_xa_cleanup_value_truncate(loc,
+							"overwriting",
+							orig_clusters);
+			goto out;
 		}
-		ocfs2_xa_wipe_namevalue(loc);
-	} else
-		ocfs2_xa_add_entry(loc, name_hash);
+	}
+	ocfs2_xa_wipe_namevalue(loc);
 
 	/*
 	 * If we get here, we have a blank entry.  Fill it.  We grow our

include/linux/memcontrol.h

@@ -356,6 +356,19 @@ static inline bool mem_cgroup_disabled(void)
 	return !cgroup_subsys_enabled(memory_cgrp_subsys);
 }
 
+static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg,
+						  bool in_low_reclaim)
+{
+	if (mem_cgroup_disabled())
+		return 0;
+
+	if (in_low_reclaim)
+		return READ_ONCE(memcg->memory.emin);
+
+	return max(READ_ONCE(memcg->memory.emin),
+		   READ_ONCE(memcg->memory.elow));
+}
+
 enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
 						struct mem_cgroup *memcg);
 
@@ -537,6 +550,8 @@ void mem_cgroup_handle_over_high(void);
 
 unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg);
 
+unsigned long mem_cgroup_size(struct mem_cgroup *memcg);
+
 void mem_cgroup_print_oom_context(struct mem_cgroup *memcg,
 				struct task_struct *p);
 
@@ -829,6 +844,12 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm,
 {
 }
 
+static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg,
+						  bool in_low_reclaim)
+{
+	return 0;
+}
+
 static inline enum mem_cgroup_protection mem_cgroup_protected(
 	struct mem_cgroup *root, struct mem_cgroup *memcg)
 {
@@ -968,6 +989,11 @@ static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg)
 	return 0;
 }
 
+static inline unsigned long mem_cgroup_size(struct mem_cgroup *memcg)
+{
+	return 0;
+}
+
 static inline void
 mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p)
 {
@@ -1264,6 +1290,9 @@ void mem_cgroup_track_foreign_dirty_slowpath(struct page *page,
 static inline void mem_cgroup_track_foreign_dirty(struct page *page,
 						  struct bdi_writeback *wb)
 {
+	if (mem_cgroup_disabled())
+		return;
+
 	if (unlikely(&page->mem_cgroup->css != wb->memcg_css))
 		mem_cgroup_track_foreign_dirty_slowpath(page, wb);
 }

include/linux/slab.h

@@ -493,6 +493,10 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags)
  * kmalloc is the normal method of allocating memory
  * for objects smaller than page size in the kernel.
  *
+ * The allocated object address is aligned to at least ARCH_KMALLOC_MINALIGN
+ * bytes. For @size of power of two bytes, the alignment is also guaranteed
+ * to be at least to the size.
+ *
  * The @flags argument may be one of the GFP flags defined at
  * include/linux/gfp.h and described at
  * :ref:`Documentation/core-api/mm-api.rst <mm-api-gfp-flags>`

kernel/fork.c

@@ -2925,7 +2925,7 @@ int sysctl_max_threads(struct ctl_table *table, int write,
 	struct ctl_table t;
 	int ret;
 	int threads = max_threads;
-	int min = MIN_THREADS;
+	int min = 1;
 	int max = MAX_THREADS;
 
 	t = *table;
@@ -2937,7 +2937,7 @@ int sysctl_max_threads(struct ctl_table *table, int write,
 	if (ret || !write)
 		return ret;
 
-	set_max_threads(threads);
+	max_threads = threads;
 
 	return 0;
 }

kernel/panic.c

@@ -180,6 +180,7 @@ void panic(const char *fmt, ...)
 	 * after setting panic_cpu) from invoking panic() again.
 	 */
 	local_irq_disable();
+	preempt_disable_notrace();
 
 	/*
 	 * It's possible to come here directly from a panic-assertion and

mm/memcontrol.c

@@ -1567,6 +1567,11 @@ unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg)
 	return max;
 }
 
+unsigned long mem_cgroup_size(struct mem_cgroup *memcg)
+{
+	return page_counter_read(&memcg->memory);
+}
+
 static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 				     int order)
 {

mm/memremap.c

@@ -13,8 +13,6 @@
 #include <linux/xarray.h>
 
 static DEFINE_XARRAY(pgmap_array);
-#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
-#define SECTION_SIZE (1UL << PA_SECTION_SHIFT)
 
 #ifdef CONFIG_DEV_PAGEMAP_OPS
 DEFINE_STATIC_KEY_FALSE(devmap_managed_key);

mm/page_alloc.c

@@ -1175,11 +1175,17 @@ static __always_inline bool free_pages_prepare(struct page *page,
 		debug_check_no_obj_freed(page_address(page),
 					   PAGE_SIZE << order);
 	}
-	arch_free_page(page, order);
 	if (want_init_on_free())
 		kernel_init_free_pages(page, 1 << order);
 
 	kernel_poison_pages(page, 1 << order, 0);
+	/*
+	 * arch_free_page() can make the page's contents inaccessible.  s390
+	 * does this.  So nothing which can access the page's contents should
+	 * happen after this.
+	 */
+	arch_free_page(page, order);
+
 	if (debug_pagealloc_enabled())
 		kernel_map_pages(page, 1 << order, 0);
 

mm/shuffle.c

@@ -33,7 +33,7 @@ __meminit void page_alloc_shuffle(enum mm_shuffle_ctl ctl)
 }
 
 static bool shuffle_param;
-extern int shuffle_show(char *buffer, const struct kernel_param *kp)
+static int shuffle_show(char *buffer, const struct kernel_param *kp)
 {
 	return sprintf(buffer, "%c\n", test_bit(SHUFFLE_ENABLE, &shuffle_state)
 			? 'Y' : 'N');

mm/slab_common.c

@@ -1030,10 +1030,19 @@ void __init create_boot_cache(struct kmem_cache *s, const char *name,
 		unsigned int useroffset, unsigned int usersize)
 {
 	int err;
+	unsigned int align = ARCH_KMALLOC_MINALIGN;
 
 	s->name = name;
 	s->size = s->object_size = size;
-	s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size);
+
+	/*
+	 * For power of two sizes, guarantee natural alignment for kmalloc
+	 * caches, regardless of SL*B debugging options.
+	 */
+	if (is_power_of_2(size))
+		align = max(align, size);
+	s->align = calculate_alignment(flags, align, size);
+
 	s->useroffset = useroffset;
 	s->usersize = usersize;
 
@@ -1287,12 +1296,16 @@ void __init create_kmalloc_caches(slab_flags_t flags)
  */
 void *kmalloc_order(size_t size, gfp_t flags, unsigned int order)
 {
-	void *ret;
+	void *ret = NULL;
 	struct page *page;
 
 	flags |= __GFP_COMP;
 	page = alloc_pages(flags, order);
-	ret = page ? page_address(page) : NULL;
+	if (likely(page)) {
+		ret = page_address(page);
+		mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE,
+				    1 << order);
+	}
 	ret = kasan_kmalloc_large(ret, size, flags);
 	/* As ret might get tagged, call kmemleak hook after KASAN. */
 	kmemleak_alloc(ret, size, 1, flags);

mm/slob.c

@@ -190,7 +190,7 @@ static int slob_last(slob_t *s)
 
 static void *slob_new_pages(gfp_t gfp, int order, int node)
 {
-	void *page;
+	struct page *page;
 
 #ifdef CONFIG_NUMA
 	if (node != NUMA_NO_NODE)
@@ -202,14 +202,21 @@ static void *slob_new_pages(gfp_t gfp, int order, int node)
 	if (!page)
 		return NULL;
 
+	mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE,
+			    1 << order);
 	return page_address(page);
 }
 
 static void slob_free_pages(void *b, int order)
 {
+	struct page *sp = virt_to_page(b);
+
 	if (current->reclaim_state)
 		current->reclaim_state->reclaimed_slab += 1 << order;
-	free_pages((unsigned long)b, order);
+
+	mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE,
+			    -(1 << order));
+	__free_pages(sp, order);
 }
 
 /*
@@ -217,6 +224,7 @@ static void slob_free_pages(void *b, int order)
  * @sp: Page to look in.
  * @size: Size of the allocation.
  * @align: Allocation alignment.
+ * @align_offset: Offset in the allocated block that will be aligned.
  * @page_removed_from_list: Return parameter.
  *
  * Tries to find a chunk of memory at least @size bytes big within @page.
@@ -227,7 +235,7 @@ static void slob_free_pages(void *b, int order)
  *         true (set to false otherwise).
  */
 static void *slob_page_alloc(struct page *sp, size_t size, int align,
-			     bool *page_removed_from_list)
+			      int align_offset, bool *page_removed_from_list)
 {
 	slob_t *prev, *cur, *aligned = NULL;
 	int delta = 0, units = SLOB_UNITS(size);
@@ -236,8 +244,17 @@ static void *slob_page_alloc(struct page *sp, size_t size, int align,
 	for (prev = NULL, cur = sp->freelist; ; prev = cur, cur = slob_next(cur)) {
 		slobidx_t avail = slob_units(cur);
 
+		/*
+		 * 'aligned' will hold the address of the slob block so that the
+		 * address 'aligned'+'align_offset' is aligned according to the
+		 * 'align' parameter. This is for kmalloc() which prepends the
+		 * allocated block with its size, so that the block itself is
+		 * aligned when needed.
+		 */
 		if (align) {
-			aligned = (slob_t *)ALIGN((unsigned long)cur, align);
+			aligned = (slob_t *)
+				(ALIGN((unsigned long)cur + align_offset, align)
+				 - align_offset);
 			delta = aligned - cur;
 		}
 		if (avail >= units + delta) { /* room enough? */
@@ -281,7 +298,8 @@ static void *slob_page_alloc(struct page *sp, size_t size, int align,
 /*
  * slob_alloc: entry point into the slob allocator.
  */
-static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
+static void *slob_alloc(size_t size, gfp_t gfp, int align, int node,
+							int align_offset)
 {
 	struct page *sp;
 	struct list_head *slob_list;
@@ -312,7 +330,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
 		if (sp->units < SLOB_UNITS(size))
 			continue;
 
-		b = slob_page_alloc(sp, size, align, &page_removed_from_list);
+		b = slob_page_alloc(sp, size, align, align_offset, &page_removed_from_list);
 		if (!b)
 			continue;
 
@@ -349,7 +367,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
 		INIT_LIST_HEAD(&sp->slab_list);
 		set_slob(b, SLOB_UNITS(PAGE_SIZE), b + SLOB_UNITS(PAGE_SIZE));
 		set_slob_page_free(sp, slob_list);
-		b = slob_page_alloc(sp, size, align, &_unused);
+		b = slob_page_alloc(sp, size, align, align_offset, &_unused);
 		BUG_ON(!b);
 		spin_unlock_irqrestore(&slob_lock, flags);
 	}
@@ -451,7 +469,7 @@ static __always_inline void *
 __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller)
 {
 	unsigned int *m;
-	int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
+	int minalign = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
 	void *ret;
 
 	gfp &= gfp_allowed_mask;
@@ -459,19 +477,28 @@ __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller)
 	fs_reclaim_acquire(gfp);
 	fs_reclaim_release(gfp);
 
-	if (size < PAGE_SIZE - align) {
+	if (size < PAGE_SIZE - minalign) {
+		int align = minalign;
+
+		/*
+		 * For power of two sizes, guarantee natural alignment for
+		 * kmalloc()'d objects.
+		 */
+		if (is_power_of_2(size))
+			align = max(minalign, (int) size);
+
 		if (!size)
 			return ZERO_SIZE_PTR;
 
-		m = slob_alloc(size + align, gfp, align, node);
+		m = slob_alloc(size + minalign, gfp, align, node, minalign);
 
 		if (!m)
 			return NULL;
 		*m = size;
-		ret = (void *)m + align;
+		ret = (void *)m + minalign;
 
 		trace_kmalloc_node(caller, ret,
-				   size, size + align, gfp, node);
+				   size, size + minalign, gfp, node);
 	} else {
 		unsigned int order = get_order(size);
 
@@ -521,8 +548,13 @@ void kfree(const void *block)
 		int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
 		unsigned int *m = (unsigned int *)(block - align);
 		slob_free(m, *m + align);
-	} else
-		__free_pages(sp, compound_order(sp));
+	} else {
+		unsigned int order = compound_order(sp);
+		mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE,
+				    -(1 << order));
+		__free_pages(sp, order);
+
+	}
 }
 EXPORT_SYMBOL(kfree);
 
@@ -567,7 +599,7 @@ static void *slob_alloc_node(struct kmem_cache *c, gfp_t flags, int node)
 	fs_reclaim_release(flags);
 
 	if (c->size < PAGE_SIZE) {
-		b = slob_alloc(c->size, flags, c->align, node);
+		b = slob_alloc(c->size, flags, c->align, node, 0);
 		trace_kmem_cache_alloc_node(_RET_IP_, b, c->object_size,
 					    SLOB_UNITS(c->size) * SLOB_UNIT,
 					    flags, node);

mm/slub.c

@@ -3821,11 +3821,15 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node)
 {
 	struct page *page;
 	void *ptr = NULL;
+	unsigned int order = get_order(size);
 
 	flags |= __GFP_COMP;
-	page = alloc_pages_node(node, flags, get_order(size));
-	if (page)
+	page = alloc_pages_node(node, flags, order);
+	if (page) {
 		ptr = page_address(page);
+		mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE,
+				    1 << order);
+	}
 
 	return kmalloc_large_node_hook(ptr, size, flags);
 }
@@ -3951,9 +3955,13 @@ void kfree(const void *x)
 
 	page = virt_to_head_page(x);
 	if (unlikely(!PageSlab(page))) {
+		unsigned int order = compound_order(page);
+
 		BUG_ON(!PageCompound(page));
 		kfree_hook(object);
-		__free_pages(page, compound_order(page));
+		mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE,
+				    -(1 << order));
+		__free_pages(page, order);
 		return;
 	}
 	slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_);

mm/sparse.c

@@ -219,7 +219,7 @@ static inline unsigned long first_present_section_nr(void)
 	return next_present_section_nr(-1);
 }
 
-void subsection_mask_set(unsigned long *map, unsigned long pfn,
+static void subsection_mask_set(unsigned long *map, unsigned long pfn,
 		unsigned long nr_pages)
 {
 	int idx = subsection_map_index(pfn);

mm/vmpressure.c

@@ -355,6 +355,9 @@ void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio)
  * "hierarchy" or "local").
  *
  * To be used as memcg event method.
+ *
+ * Return: 0 on success, -ENOMEM on memory failure or -EINVAL if @args could
+ * not be parsed.
  */
 int vmpressure_register_event(struct mem_cgroup *memcg,
 			      struct eventfd_ctx *eventfd, const char *args)
@@ -362,7 +365,7 @@ int vmpressure_register_event(struct mem_cgroup *memcg,
 	struct vmpressure *vmpr = memcg_to_vmpressure(memcg);
 	struct vmpressure_event *ev;
 	enum vmpressure_modes mode = VMPRESSURE_NO_PASSTHROUGH;
-	enum vmpressure_levels level = -1;
+	enum vmpressure_levels level;
 	char *spec, *spec_orig;
 	char *token;
 	int ret = 0;
@@ -375,20 +378,18 @@ int vmpressure_register_event(struct mem_cgroup *memcg,
 
 	/* Find required level */
 	token = strsep(&spec, ",");
-	level = match_string(vmpressure_str_levels, VMPRESSURE_NUM_LEVELS, token);
-	if (level < 0) {
-		ret = level;
+	ret = match_string(vmpressure_str_levels, VMPRESSURE_NUM_LEVELS, token);
+	if (ret < 0)
 		goto out;
-	}
+	level = ret;
 
 	/* Find optional mode */
 	token = strsep(&spec, ",");
 	if (token) {
-		mode = match_string(vmpressure_str_modes, VMPRESSURE_NUM_MODES, token);
-		if (mode < 0) {
-			ret = mode;
+		ret = match_string(vmpressure_str_modes, VMPRESSURE_NUM_MODES, token);
+		if (ret < 0)
 			goto out;
-		}
+		mode = ret;
 	}
 
 	ev = kzalloc(sizeof(*ev), GFP_KERNEL);
@@ -404,6 +405,7 @@ int vmpressure_register_event(struct mem_cgroup *memcg,
 	mutex_lock(&vmpr->events_lock);
 	list_add(&ev->node, &vmpr->events);
 	mutex_unlock(&vmpr->events_lock);
+	ret = 0;
 out:
 	kfree(spec_orig);
 	return ret;

mm/vmscan.c

@@ -2459,17 +2459,70 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 	*lru_pages = 0;
 	for_each_evictable_lru(lru) {
 		int file = is_file_lru(lru);
-		unsigned long size;
+		unsigned long lruvec_size;
 		unsigned long scan;
+		unsigned long protection;
+
+		lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
+		protection = mem_cgroup_protection(memcg,
+						   sc->memcg_low_reclaim);
+
+		if (protection) {
+			/*
+			 * Scale a cgroup's reclaim pressure by proportioning
+			 * its current usage to its memory.low or memory.min
+			 * setting.
+			 *
+			 * This is important, as otherwise scanning aggression
+			 * becomes extremely binary -- from nothing as we
+			 * approach the memory protection threshold, to totally
+			 * nominal as we exceed it.  This results in requiring
+			 * setting extremely liberal protection thresholds. It
+			 * also means we simply get no protection at all if we
+			 * set it too low, which is not ideal.
+			 *
+			 * If there is any protection in place, we reduce scan
+			 * pressure by how much of the total memory used is
+			 * within protection thresholds.
+			 *
+			 * There is one special case: in the first reclaim pass,
+			 * we skip over all groups that are within their low
+			 * protection. If that fails to reclaim enough pages to
+			 * satisfy the reclaim goal, we come back and override
+			 * the best-effort low protection. However, we still
+			 * ideally want to honor how well-behaved groups are in
+			 * that case instead of simply punishing them all
+			 * equally. As such, we reclaim them based on how much
+			 * memory they are using, reducing the scan pressure
+			 * again by how much of the total memory used is under
+			 * hard protection.
+			 */
+			unsigned long cgroup_size = mem_cgroup_size(memcg);
+
+			/* Avoid TOCTOU with earlier protection check */
+			cgroup_size = max(cgroup_size, protection);
+
+			scan = lruvec_size - lruvec_size * protection /
+				cgroup_size;
+
+			/*
+			 * Minimally target SWAP_CLUSTER_MAX pages to keep
+			 * reclaim moving forwards, avoiding decremeting
+			 * sc->priority further than desirable.
+			 */
+			scan = max(scan, SWAP_CLUSTER_MAX);
+		} else {
+			scan = lruvec_size;
+		}
+
+		scan >>= sc->priority;
 
-		size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
-		scan = size >> sc->priority;
 		/*
 		 * If the cgroup's already been deleted, make sure to
 		 * scrape out the remaining cache.
 		 */
 		if (!scan && !mem_cgroup_online(memcg))
-			scan = min(size, SWAP_CLUSTER_MAX);
+			scan = min(lruvec_size, SWAP_CLUSTER_MAX);
 
 		switch (scan_balance) {
 		case SCAN_EQUAL:
@@ -2489,7 +2542,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 		case SCAN_ANON:
 			/* Scan one type exclusively */
 			if ((scan_balance == SCAN_FILE) != file) {
-				size = 0;
+				lruvec_size = 0;
 				scan = 0;
 			}
 			break;
@@ -2498,7 +2551,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 			BUG();
 		}
 
-		*lru_pages += size;
+		*lru_pages += lruvec_size;
 		nr[lru] = scan;
 	}
 }
@@ -2742,6 +2795,13 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 				memcg_memory_event(memcg, MEMCG_LOW);
 				break;
 			case MEMCG_PROT_NONE:
+				/*
+				 * All protection thresholds breached. We may
+				 * still choose to vary the scan pressure
+				 * applied based on by how much the cgroup in
+				 * question has exceeded its protection
+				 * thresholds (see get_scan_count).
+				 */
 				break;
 			}
 

mm/z3fold.c

@@ -998,9 +998,11 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
 	struct z3fold_header *zhdr;
 	struct page *page;
 	enum buddy bud;
+	bool page_claimed;
 
 	zhdr = handle_to_z3fold_header(handle);
 	page = virt_to_page(zhdr);
+	page_claimed = test_and_set_bit(PAGE_CLAIMED, &page->private);
 
 	if (test_bit(PAGE_HEADLESS, &page->private)) {
 		/* if a headless page is under reclaim, just leave.
@@ -1008,7 +1010,7 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
 		 * has not been set before, we release this page
 		 * immediately so we don't care about its value any more.
 		 */
-		if (!test_and_set_bit(PAGE_CLAIMED, &page->private)) {
+		if (!page_claimed) {
 			spin_lock(&pool->lock);
 			list_del(&page->lru);
 			spin_unlock(&pool->lock);
@@ -1044,13 +1046,15 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
 		atomic64_dec(&pool->pages_nr);
 		return;
 	}
-	if (test_bit(PAGE_CLAIMED, &page->private)) {
+	if (page_claimed) {
+		/* the page has not been claimed by us */
 		z3fold_page_unlock(zhdr);
 		return;
 	}
 	if (unlikely(PageIsolated(page)) ||
 	    test_and_set_bit(NEEDS_COMPACTING, &page->private)) {
 		z3fold_page_unlock(zhdr);
+		clear_bit(PAGE_CLAIMED, &page->private);
 		return;
 	}
 	if (zhdr->cpu < 0 || !cpu_online(zhdr->cpu)) {
@@ -1060,10 +1064,12 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
 		zhdr->cpu = -1;
 		kref_get(&zhdr->refcount);
 		do_compact_page(zhdr, true);
+		clear_bit(PAGE_CLAIMED, &page->private);
 		return;
 	}
 	kref_get(&zhdr->refcount);
 	queue_work_on(zhdr->cpu, pool->compact_wq, &zhdr->work);
+	clear_bit(PAGE_CLAIMED, &page->private);
 	z3fold_page_unlock(zhdr);
 }