Sync mm-stable with mm-hotfixes-stable to pick up dependent patches

Merge branch 'mm-hotfixes-stable' into mm-stable

.mailmap

@@ -130,6 +130,7 @@ Domen Puncer <domen@coderock.org>
 Douglas Gilbert <dougg@torque.net>
 Ed L. Cashin <ecashin@coraid.com>
 Erik Kaneda <erik.kaneda@intel.com> <erik.schmauss@intel.com>
+Eugen Hristev <eugen.hristev@collabora.com> <eugen.hristev@microchip.com>
 Evgeniy Polyakov <johnpol@2ka.mipt.ru>
 Ezequiel Garcia <ezequiel@vanguardiasur.com.ar> <ezequiel@collabora.com>
 Felipe W Damasio <felipewd@terra.com.br>

Documentation/admin-guide/cgroup-v2.rst

@@ -1245,13 +1245,17 @@ PAGE_SIZE multiple when read back.
 	This is a simple interface to trigger memory reclaim in the
 	target cgroup.
 
-	This file accepts a string which contains the number of bytes to
-	reclaim.
+	This file accepts a single key, the number of bytes to reclaim.
+	No nested keys are currently supported.
 
 	Example::
 
 	  echo "1G" > memory.reclaim
 
+	The interface can be later extended with nested keys to
+	configure the reclaim behavior. For example, specify the
+	type of memory to reclaim from (anon, file, ..).
+
 	Please note that the kernel can over or under reclaim from
 	the target cgroup. If less bytes are reclaimed than the
 	specified amount, -EAGAIN is returned.
@@ -1263,13 +1267,6 @@ PAGE_SIZE multiple when read back.
 	This means that the networking layer will not adapt based on
 	reclaim induced by memory.reclaim.
 
-	This file also allows the user to specify the nodes to reclaim from,
-	via the 'nodes=' key, for example::
-
-	  echo "1G nodes=0,1" > memory.reclaim
-
-	The above instructs the kernel to reclaim memory from nodes 0,1.
-
   memory.peak
 	A read-only single value file which exists on non-root
 	cgroups.

arch/ia64/kernel/sys_ia64.c

@@ -170,6 +170,9 @@ ia64_mremap (unsigned long addr, unsigned long old_len, unsigned long new_len, u
 asmlinkage long
 ia64_clock_getres(const clockid_t which_clock, struct __kernel_timespec __user *tp)
 {
+	struct timespec64 rtn_tp;
+	s64 tick_ns;
+
 	/*
 	 * ia64's clock_gettime() syscall is implemented as a vdso call
 	 * fsys_clock_gettime(). Currently it handles only
@@ -185,8 +188,8 @@ ia64_clock_getres(const clockid_t which_clock, struct __kernel_timespec __user *
 	switch (which_clock) {
 	case CLOCK_REALTIME:
 	case CLOCK_MONOTONIC:
-		s64 tick_ns = DIV_ROUND_UP(NSEC_PER_SEC, local_cpu_data->itc_freq);
-		struct timespec64 rtn_tp = ns_to_timespec64(tick_ns);
+		tick_ns = DIV_ROUND_UP(NSEC_PER_SEC, local_cpu_data->itc_freq);
+		rtn_tp = ns_to_timespec64(tick_ns);
 		return put_timespec64(&rtn_tp, tp);
 	}
 

arch/sh/kernel/vmlinux.lds.S

@@ -4,6 +4,7 @@
  * Written by Niibe Yutaka and Paul Mundt
  */
 OUTPUT_ARCH(sh)
+#define RUNTIME_DISCARD_EXIT
 #include <asm/thread_info.h>
 #include <asm/cache.h>
 #include <asm/vmlinux.lds.h>

drivers/of/fdt.c

@@ -26,7 +26,6 @@
 #include <linux/serial_core.h>
 #include <linux/sysfs.h>
 #include <linux/random.h>
-#include <linux/kmemleak.h>
 
 #include <asm/setup.h>  /* for COMMAND_LINE_SIZE */
 #include <asm/page.h>
@@ -525,12 +524,9 @@ static int __init __reserved_mem_reserve_reg(unsigned long node,
 		size = dt_mem_next_cell(dt_root_size_cells, &prop);
 
 		if (size &&
-		    early_init_dt_reserve_memory(base, size, nomap) == 0) {
+		    early_init_dt_reserve_memory(base, size, nomap) == 0)
 			pr_debug("Reserved memory: reserved region for node '%s': base %pa, size %lu MiB\n",
 				uname, &base, (unsigned long)(size / SZ_1M));
-			if (!nomap)
-				kmemleak_alloc_phys(base, size, 0);
-		}
 		else
 			pr_err("Reserved memory: failed to reserve memory for node '%s': base %pa, size %lu MiB\n",
 			       uname, &base, (unsigned long)(size / SZ_1M));

fs/freevxfs/Kconfig

@@ -8,7 +8,7 @@ config VXFS_FS
 	  of SCO UnixWare (and possibly others) and optionally available
 	  for Sunsoft Solaris, HP-UX and many other operating systems. However
 	  these particular OS implementations of vxfs may differ in on-disk
-	  data endianess and/or superblock offset. The vxfs module has been
+	  data endianness and/or superblock offset. The vxfs module has been
 	  tested with SCO UnixWare and HP-UX B.10.20 (pa-risc 1.1 arch.)
 	  Currently only readonly access is supported and VxFX versions
 	  2, 3 and 4. Tests were performed with HP-UX VxFS version 3.

fs/proc/task_mmu.c

@@ -745,9 +745,7 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
 			page = pfn_swap_entry_to_page(swpent);
 	}
 	if (page) {
-		int mapcount = page_mapcount(page);
-
-		if (mapcount >= 2)
+		if (page_mapcount(page) >= 2 || hugetlb_pmd_shared(pte))
 			mss->shared_hugetlb += huge_page_size(hstate_vma(vma));
 		else
 			mss->private_hugetlb += huge_page_size(hstate_vma(vma));

fs/squashfs/squashfs_fs.h

@@ -183,7 +183,7 @@ static inline int squashfs_block_size(__le32 raw)
 #define SQUASHFS_ID_BLOCK_BYTES(A)	(SQUASHFS_ID_BLOCKS(A) *\
 					sizeof(u64))
 /* xattr id lookup table defines */
-#define SQUASHFS_XATTR_BYTES(A)		((A) * sizeof(struct squashfs_xattr_id))
+#define SQUASHFS_XATTR_BYTES(A)		(((u64) (A)) * sizeof(struct squashfs_xattr_id))
 
 #define SQUASHFS_XATTR_BLOCK(A)		(SQUASHFS_XATTR_BYTES(A) / \
 					SQUASHFS_METADATA_SIZE)

fs/squashfs/squashfs_fs_sb.h

@@ -63,7 +63,7 @@ struct squashfs_sb_info {
 	long long				bytes_used;
 	unsigned int				inodes;
 	unsigned int				fragments;
-	int					xattr_ids;
+	unsigned int				xattr_ids;
 	unsigned int				ids;
 	bool					panic_on_errors;
 	const struct squashfs_decompressor_thread_ops *thread_ops;

fs/squashfs/xattr.h

@@ -10,12 +10,12 @@
 
 #ifdef CONFIG_SQUASHFS_XATTR
 extern __le64 *squashfs_read_xattr_id_table(struct super_block *, u64,
-		u64 *, int *);
+		u64 *, unsigned int *);
 extern int squashfs_xattr_lookup(struct super_block *, unsigned int, int *,
 		unsigned int *, unsigned long long *);
 #else
 static inline __le64 *squashfs_read_xattr_id_table(struct super_block *sb,
-		u64 start, u64 *xattr_table_start, int *xattr_ids)
+		u64 start, u64 *xattr_table_start, unsigned int *xattr_ids)
 {
 	struct squashfs_xattr_id_table *id_table;
 

fs/squashfs/xattr_id.c

@@ -56,7 +56,7 @@ int squashfs_xattr_lookup(struct super_block *sb, unsigned int index,
  * Read uncompressed xattr id lookup table indexes from disk into memory
  */
 __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start,
-		u64 *xattr_table_start, int *xattr_ids)
+		u64 *xattr_table_start, unsigned int *xattr_ids)
 {
 	struct squashfs_sb_info *msblk = sb->s_fs_info;
 	unsigned int len, indexes;
@@ -76,7 +76,7 @@ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start,
 	/* Sanity check values */
 
 	/* there is always at least one xattr id */
-	if (*xattr_ids == 0)
+	if (*xattr_ids <= 0)
 		return ERR_PTR(-EINVAL);
 
 	len = SQUASHFS_XATTR_BLOCK_BYTES(*xattr_ids);

include/linux/highmem-internal.h

@@ -200,7 +200,7 @@ static inline void *kmap_local_pfn(unsigned long pfn)
 static inline void __kunmap_local(const void *addr)
 {
 #ifdef ARCH_HAS_FLUSH_ON_KUNMAP
-	kunmap_flush_on_unmap(addr);
+	kunmap_flush_on_unmap(PTR_ALIGN_DOWN(addr, PAGE_SIZE));
 #endif
 }
 
@@ -227,7 +227,7 @@ static inline void *kmap_atomic_pfn(unsigned long pfn)
 static inline void __kunmap_atomic(const void *addr)
 {
 #ifdef ARCH_HAS_FLUSH_ON_KUNMAP
-	kunmap_flush_on_unmap(addr);
+	kunmap_flush_on_unmap(PTR_ALIGN_DOWN(addr, PAGE_SIZE));
 #endif
 	pagefault_enable();
 	if (IS_ENABLED(CONFIG_PREEMPT_RT))

include/linux/hugetlb.h

@@ -8,6 +8,7 @@
 #include <linux/fs.h>
 #include <linux/hugetlb_inline.h>
 #include <linux/cgroup.h>
+#include <linux/page_ref.h>
 #include <linux/list.h>
 #include <linux/kref.h>
 #include <linux/pgtable.h>
@@ -1225,6 +1226,18 @@ static inline __init void hugetlb_cma_reserve(int order)
 }
 #endif
 
+#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
+static inline bool hugetlb_pmd_shared(pte_t *pte)
+{
+	return page_count(virt_to_page(pte)) > 1;
+}
+#else
+static inline bool hugetlb_pmd_shared(pte_t *pte)
+{
+	return false;
+}
+#endif
+
 bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr);
 
 #ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE

include/linux/memcontrol.h

@@ -1688,10 +1688,13 @@ void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio,
 static inline void mem_cgroup_track_foreign_dirty(struct folio *folio,
 						  struct bdi_writeback *wb)
 {
+	struct mem_cgroup *memcg;
+
 	if (mem_cgroup_disabled())
 		return;
 
-	if (unlikely(&folio_memcg(folio)->css != wb->memcg_css))
+	memcg = folio_memcg(folio);
+	if (unlikely(memcg && &memcg->css != wb->memcg_css))
 		mem_cgroup_track_foreign_dirty_slowpath(folio, wb);
 }
 

include/linux/swap.h

@@ -418,8 +418,7 @@ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 						  unsigned long nr_pages,
 						  gfp_t gfp_mask,
-						  unsigned int reclaim_options,
-						  nodemask_t *nodemask);
+						  unsigned int reclaim_options);
 extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem,
 						gfp_t gfp_mask, bool noswap,
 						pg_data_t *pgdat,

lib/Kconfig.debug

@@ -754,6 +754,7 @@ config DEBUG_KMEMLEAK
 	select KALLSYMS
 	select CRC32
 	select STACKDEPOT
+	select STACKDEPOT_ALWAYS_INIT if !DEBUG_KMEMLEAK_DEFAULT_OFF
 	help
 	  Say Y here if you want to enable the memory leak
 	  detector. The memory allocation/freeing is traced in a way
@@ -1207,7 +1208,7 @@ config SCHED_DEBUG
 	depends on DEBUG_KERNEL && PROC_FS
 	default y
 	help
-	  If you say Y here, the /proc/sched_debug file will be provided
+	  If you say Y here, the /sys/kernel/debug/sched file will be provided
 	  that can help debug the scheduler. The runtime overhead of this
 	  option is minimal.
 

lib/maple_tree.c

@@ -667,12 +667,13 @@ static inline unsigned long mte_pivot(const struct maple_enode *mn,
 				 unsigned char piv)
 {
 	struct maple_node *node = mte_to_node(mn);
+	enum maple_type type = mte_node_type(mn);
 
-	if (piv >= mt_pivots[piv]) {
+	if (piv >= mt_pivots[type]) {
 		WARN_ON(1);
 		return 0;
 	}
-	switch (mte_node_type(mn)) {
+	switch (type) {
 	case maple_arange_64:
 		return node->ma64.pivot[piv];
 	case maple_range_64:
@@ -4876,7 +4877,7 @@ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size)
 	unsigned long *pivots, *gaps;
 	void __rcu **slots;
 	unsigned long gap = 0;
-	unsigned long max, min, index;
+	unsigned long max, min;
 	unsigned char offset;
 
 	if (unlikely(mas_is_err(mas)))
@@ -4898,8 +4899,7 @@ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size)
 		min = mas_safe_min(mas, pivots, --offset);
 
 	max = mas_safe_pivot(mas, pivots, offset, type);
-	index = mas->index;
-	while (index <= max) {
+	while (mas->index <= max) {
 		gap = 0;
 		if (gaps)
 			gap = gaps[offset];
@@ -4930,10 +4930,8 @@ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size)
 		min = mas_safe_min(mas, pivots, offset);
 	}
 
-	if (unlikely(index > max)) {
-		mas_set_err(mas, -EBUSY);
-		return false;
-	}
+	if (unlikely((mas->index > max) || (size - 1 > max - mas->index)))
+		goto no_space;
 
 	if (unlikely(ma_is_leaf(type))) {
 		mas->offset = offset;
@@ -4950,9 +4948,11 @@ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size)
 	return false;
 
 ascend:
-	if (mte_is_root(mas->node))
-		mas_set_err(mas, -EBUSY);
+	if (!mte_is_root(mas->node))
+		return false;
 
+no_space:
+	mas_set_err(mas, -EBUSY);
 	return false;
 }
 

lib/test_maple_tree.c

@@ -2517,6 +2517,91 @@ static noinline void check_bnode_min_spanning(struct maple_tree *mt)
 	mt_set_non_kernel(0);
 }
 
+static noinline void check_empty_area_window(struct maple_tree *mt)
+{
+	unsigned long i, nr_entries = 20;
+	MA_STATE(mas, mt, 0, 0);
+
+	for (i = 1; i <= nr_entries; i++)
+		mtree_store_range(mt, i*10, i*10 + 9,
+				  xa_mk_value(i), GFP_KERNEL);
+
+	/* Create another hole besides the one at 0 */
+	mtree_store_range(mt, 160, 169, NULL, GFP_KERNEL);
+
+	/* Check lower bounds that don't fit */
+	rcu_read_lock();
+	MT_BUG_ON(mt, mas_empty_area_rev(&mas, 5, 90, 10) != -EBUSY);
+
+	mas_reset(&mas);
+	MT_BUG_ON(mt, mas_empty_area_rev(&mas, 6, 90, 5) != -EBUSY);
+
+	/* Check lower bound that does fit */
+	mas_reset(&mas);
+	MT_BUG_ON(mt, mas_empty_area_rev(&mas, 5, 90, 5) != 0);
+	MT_BUG_ON(mt, mas.index != 5);
+	MT_BUG_ON(mt, mas.last != 9);
+	rcu_read_unlock();
+
+	/* Check one gap that doesn't fit and one that does */
+	rcu_read_lock();
+	mas_reset(&mas);
+	MT_BUG_ON(mt, mas_empty_area_rev(&mas, 5, 217, 9) != 0);
+	MT_BUG_ON(mt, mas.index != 161);
+	MT_BUG_ON(mt, mas.last != 169);
+
+	/* Check one gap that does fit above the min */
+	mas_reset(&mas);
+	MT_BUG_ON(mt, mas_empty_area_rev(&mas, 100, 218, 3) != 0);
+	MT_BUG_ON(mt, mas.index != 216);
+	MT_BUG_ON(mt, mas.last != 218);
+
+	/* Check size that doesn't fit any gap */
+	mas_reset(&mas);
+	MT_BUG_ON(mt, mas_empty_area_rev(&mas, 100, 218, 16) != -EBUSY);
+
+	/*
+	 * Check size that doesn't fit the lower end of the window but
+	 * does fit the gap
+	 */
+	mas_reset(&mas);
+	MT_BUG_ON(mt, mas_empty_area_rev(&mas, 167, 200, 4) != -EBUSY);
+
+	/*
+	 * Check size that doesn't fit the upper end of the window but
+	 * does fit the gap
+	 */
+	mas_reset(&mas);
+	MT_BUG_ON(mt, mas_empty_area_rev(&mas, 100, 162, 4) != -EBUSY);
+
+	/* Check mas_empty_area forward */
+	mas_reset(&mas);
+	MT_BUG_ON(mt, mas_empty_area(&mas, 0, 100, 9) != 0);
+	MT_BUG_ON(mt, mas.index != 0);
+	MT_BUG_ON(mt, mas.last != 8);
+
+	mas_reset(&mas);
+	MT_BUG_ON(mt, mas_empty_area(&mas, 0, 100, 4) != 0);
+	MT_BUG_ON(mt, mas.index != 0);
+	MT_BUG_ON(mt, mas.last != 3);
+
+	mas_reset(&mas);
+	MT_BUG_ON(mt, mas_empty_area(&mas, 0, 100, 11) != -EBUSY);
+
+	mas_reset(&mas);
+	MT_BUG_ON(mt, mas_empty_area(&mas, 5, 100, 6) != -EBUSY);
+
+	mas_reset(&mas);
+	MT_BUG_ON(mt, mas_empty_area(&mas, 0, 8, 10) != -EBUSY);
+
+	mas_reset(&mas);
+	mas_empty_area(&mas, 100, 165, 3);
+
+	mas_reset(&mas);
+	MT_BUG_ON(mt, mas_empty_area(&mas, 100, 163, 6) != -EBUSY);
+	rcu_read_unlock();
+}
+
 static DEFINE_MTREE(tree);
 static int maple_tree_seed(void)
 {
@@ -2765,6 +2850,10 @@ static int maple_tree_seed(void)
 	check_bnode_min_spanning(&tree);
 	mtree_destroy(&tree);
 
+	mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE);
+	check_empty_area_window(&tree);
+	mtree_destroy(&tree);
+
 #if defined(BENCH)
 skip:
 #endif

mm/khugepaged.c

@@ -847,6 +847,10 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
 	return SCAN_SUCCEED;
 }
 
+/*
+ * See pmd_trans_unstable() for how the result may change out from
+ * underneath us, even if we hold mmap_lock in read.
+ */
 static int find_pmd_or_thp_or_none(struct mm_struct *mm,
 				   unsigned long address,
 				   pmd_t **pmd)
@@ -865,8 +869,12 @@ static int find_pmd_or_thp_or_none(struct mm_struct *mm,
 #endif
 	if (pmd_none(pmde))
 		return SCAN_PMD_NONE;
+	if (!pmd_present(pmde))
+		return SCAN_PMD_NULL;
 	if (pmd_trans_huge(pmde))
 		return SCAN_PMD_MAPPED;
+	if (pmd_devmap(pmde))
+		return SCAN_PMD_NULL;
 	if (pmd_bad(pmde))
 		return SCAN_PMD_NULL;
 	return SCAN_SUCCEED;
@@ -1642,7 +1650,7 @@ static int retract_page_tables(struct address_space *mapping, pgoff_t pgoff,
 		 * has higher cost too. It would also probably require locking
 		 * the anon_vma.
 		 */
-		if (vma->anon_vma) {
+		if (READ_ONCE(vma->anon_vma)) {
 			result = SCAN_PAGE_ANON;
 			goto next;
 		}
@@ -1670,6 +1678,18 @@ static int retract_page_tables(struct address_space *mapping, pgoff_t pgoff,
 		result = SCAN_PTE_MAPPED_HUGEPAGE;
 		if ((cc->is_khugepaged || is_target) &&
 		    mmap_write_trylock(mm)) {
+			/*
+			 * Re-check whether we have an ->anon_vma, because
+			 * collapse_and_free_pmd() requires that either no
+			 * ->anon_vma exists or the anon_vma is locked.
+			 * We already checked ->anon_vma above, but that check
+			 * is racy because ->anon_vma can be populated under the
+			 * mmap lock in read mode.
+			 */
+			if (vma->anon_vma) {
+				result = SCAN_PAGE_ANON;
+				goto unlock_next;
+			}
 			/*
 			 * When a vma is registered with uffd-wp, we can't
 			 * recycle the pmd pgtable because there can be pte

mm/kmemleak.c

@@ -2070,8 +2070,10 @@ static int __init kmemleak_boot_config(char *str)
 		return -EINVAL;
 	if (strcmp(str, "off") == 0)
 		kmemleak_disable();
-	else if (strcmp(str, "on") == 0)
+	else if (strcmp(str, "on") == 0) {
 		kmemleak_skip_disable = 1;
+		stack_depot_want_early_init();
+	}
 	else
 		return -EINVAL;
 	return 0;
@@ -2093,7 +2095,6 @@ void __init kmemleak_init(void)
 	if (kmemleak_error)
 		return;
 
-	stack_depot_init();
 	jiffies_min_age = msecs_to_jiffies(MSECS_MIN_AGE);
 	jiffies_scan_wait = msecs_to_jiffies(SECS_SCAN_WAIT * 1000);
 

mm/memcontrol.c

@@ -63,7 +63,6 @@
 #include <linux/resume_user_mode.h>
 #include <linux/psi.h>
 #include <linux/seq_buf.h>
-#include <linux/parser.h>
 #include "internal.h"
 #include <net/sock.h>
 #include <net/ip.h>
@@ -2403,8 +2402,7 @@ static unsigned long reclaim_high(struct mem_cgroup *memcg,
 		psi_memstall_enter(&pflags);
 		nr_reclaimed += try_to_free_mem_cgroup_pages(memcg, nr_pages,
 							gfp_mask,
-							MEMCG_RECLAIM_MAY_SWAP,
-							NULL);
+							MEMCG_RECLAIM_MAY_SWAP);
 		psi_memstall_leave(&pflags);
 	} while ((memcg = parent_mem_cgroup(memcg)) &&
 		 !mem_cgroup_is_root(memcg));
@@ -2695,8 +2693,7 @@ static int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask,
 
 	psi_memstall_enter(&pflags);
 	nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages,
-						    gfp_mask, reclaim_options,
-						    NULL);
+						    gfp_mask, reclaim_options);
 	psi_memstall_leave(&pflags);
 
 	if (mem_cgroup_margin(mem_over_limit) >= nr_pages)
@@ -3516,8 +3513,7 @@ static int mem_cgroup_resize_max(struct mem_cgroup *memcg,
 		}
 
 		if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL,
-					memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP,
-					NULL)) {
+					memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP)) {
 			ret = -EBUSY;
 			break;
 		}
@@ -3631,8 +3627,7 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
 			return -EINTR;
 
 		if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL,
-						  MEMCG_RECLAIM_MAY_SWAP,
-						  NULL))
+						  MEMCG_RECLAIM_MAY_SWAP))
 			nr_retries--;
 	}
 
@@ -6473,8 +6468,7 @@ static ssize_t memory_high_write(struct kernfs_open_file *of,
 		}
 
 		reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_pages - high,
-					GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP,
-					NULL);
+					GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP);
 
 		if (!reclaimed && !nr_retries--)
 			break;
@@ -6523,8 +6517,7 @@ static ssize_t memory_max_write(struct kernfs_open_file *of,
 
 		if (nr_reclaims) {
 			if (!try_to_free_mem_cgroup_pages(memcg, nr_pages - max,
-					GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP,
-					NULL))
+					GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP))
 				nr_reclaims--;
 			continue;
 		}
@@ -6647,54 +6640,21 @@ static ssize_t memory_oom_group_write(struct kernfs_open_file *of,
 	return nbytes;
 }
 
-enum {
-	MEMORY_RECLAIM_NODES = 0,
-	MEMORY_RECLAIM_NULL,
-};
-
-static const match_table_t if_tokens = {
-	{ MEMORY_RECLAIM_NODES, "nodes=%s" },
-	{ MEMORY_RECLAIM_NULL, NULL },
-};
-
 static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf,
 			      size_t nbytes, loff_t off)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
 	unsigned int nr_retries = MAX_RECLAIM_RETRIES;
 	unsigned long nr_to_reclaim, nr_reclaimed = 0;
-	unsigned int reclaim_options = MEMCG_RECLAIM_MAY_SWAP |
-				       MEMCG_RECLAIM_PROACTIVE;
-	char *old_buf, *start;
-	substring_t args[MAX_OPT_ARGS];
-	int token;
-	char value[256];
-	nodemask_t nodemask = NODE_MASK_ALL;
-
-	buf = strstrip(buf);
-
-	old_buf = buf;
-	nr_to_reclaim = memparse(buf, &buf) / PAGE_SIZE;
-	if (buf == old_buf)
-		return -EINVAL;
+	unsigned int reclaim_options;
+	int err;
 
 	buf = strstrip(buf);
+	err = page_counter_memparse(buf, "", &nr_to_reclaim);
+	if (err)
+		return err;
 
-	while ((start = strsep(&buf, " ")) != NULL) {
-		if (!strlen(start))
-			continue;
-		token = match_token(start, if_tokens, args);
-		match_strlcpy(value, args, sizeof(value));
-		switch (token) {
-		case MEMORY_RECLAIM_NODES:
-			if (nodelist_parse(value, nodemask) < 0)
-				return -EINVAL;
-			break;
-		default:
-			return -EINVAL;
-		}
-	}
-
+	reclaim_options	= MEMCG_RECLAIM_MAY_SWAP | MEMCG_RECLAIM_PROACTIVE;
 	while (nr_reclaimed < nr_to_reclaim) {
 		unsigned long reclaimed;
 
@@ -6711,8 +6671,7 @@ static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf,
 
 		reclaimed = try_to_free_mem_cgroup_pages(memcg,
 						nr_to_reclaim - nr_reclaimed,
-						GFP_KERNEL, reclaim_options,
-						&nodemask);
+						GFP_KERNEL, reclaim_options);
 
 		if (!reclaimed && !nr_retries--)
 			return -EAGAIN;

mm/mempolicy.c

@@ -600,7 +600,8 @@ static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask,
 
 	/* With MPOL_MF_MOVE, we migrate only unshared hugepage. */
 	if (flags & (MPOL_MF_MOVE_ALL) ||
-	    (flags & MPOL_MF_MOVE && page_mapcount(page) == 1)) {
+	    (flags & MPOL_MF_MOVE && page_mapcount(page) == 1 &&
+	     !hugetlb_pmd_shared(pte))) {
 		if (isolate_hugetlb(page, qp->pagelist) &&
 			(flags & MPOL_MF_STRICT))
 			/*

mm/mremap.c

@@ -1027,16 +1027,29 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 			}
 
 			/*
-			 * Function vma_merge() is called on the extension we are adding to
-			 * the already existing vma, vma_merge() will merge this extension with
-			 * the already existing vma (expand operation itself) and possibly also
-			 * with the next vma if it becomes adjacent to the expanded vma and
-			 * otherwise compatible.
+			 * Function vma_merge() is called on the extension we
+			 * are adding to the already existing vma, vma_merge()
+			 * will merge this extension with the already existing
+			 * vma (expand operation itself) and possibly also with
+			 * the next vma if it becomes adjacent to the expanded
+			 * vma and  otherwise compatible.
+			 *
+			 * However, vma_merge() can currently fail due to
+			 * is_mergeable_vma() check for vm_ops->close (see the
+			 * comment there). Yet this should not prevent vma
+			 * expanding, so perform a simple expand for such vma.
+			 * Ideally the check for close op should be only done
+			 * when a vma would be actually removed due to a merge.
 			 */
-			vma = vma_merge(mm, vma, extension_start, extension_end,
+			if (!vma->vm_ops || !vma->vm_ops->close) {
+				vma = vma_merge(mm, vma, extension_start, extension_end,
 					vma->vm_flags, vma->anon_vma, vma->vm_file,
 					extension_pgoff, vma_policy(vma),
 					vma->vm_userfaultfd_ctx, anon_vma_name(vma));
+			} else if (vma_adjust(vma, vma->vm_start, addr + new_len,
+				   vma->vm_pgoff, NULL)) {
+				vma = NULL;
+			}
 			if (!vma) {
 				vm_unacct_memory(pages);
 				ret = -ENOMEM;

mm/swapfile.c

@@ -1100,6 +1100,7 @@ int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size)
 			goto check_out;
 		pr_debug("scan_swap_map of si %d failed to find offset\n",
 			si->type);
+		cond_resched();
 
 		spin_lock(&swap_avail_lock);
 nextsi:

mm/vmscan.c

@@ -3335,13 +3335,16 @@ void lru_gen_migrate_mm(struct mm_struct *mm)
 	if (mem_cgroup_disabled())
 		return;
 
+	/* migration can happen before addition */
+	if (!mm->lru_gen.memcg)
+		return;
+
 	rcu_read_lock();
 	memcg = mem_cgroup_from_task(task);
 	rcu_read_unlock();
 	if (memcg == mm->lru_gen.memcg)
 		return;
 
-	VM_WARN_ON_ONCE(!mm->lru_gen.memcg);
 	VM_WARN_ON_ONCE(list_empty(&mm->lru_gen.list));
 
 	lru_gen_del_mm(mm);
@@ -7022,8 +7025,7 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
 unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 					   unsigned long nr_pages,
 					   gfp_t gfp_mask,
-					   unsigned int reclaim_options,
-					   nodemask_t *nodemask)
+					   unsigned int reclaim_options)
 {
 	unsigned long nr_reclaimed;
 	unsigned int noreclaim_flag;
@@ -7038,7 +7040,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 		.may_unmap = 1,
 		.may_swap = !!(reclaim_options & MEMCG_RECLAIM_MAY_SWAP),
 		.proactive = !!(reclaim_options & MEMCG_RECLAIM_PROACTIVE),
-		.nodemask = nodemask,
 	};
 	/*
 	 * Traverse the ZONELIST_FALLBACK zonelist of the current node to put

mm/zsmalloc.c

@@ -113,7 +113,23 @@
  * have room for two bit at least.
  */
 #define OBJ_ALLOCATED_TAG 1
-#define OBJ_TAG_BITS 1
+
+#ifdef CONFIG_ZPOOL
+/*
+ * The second least-significant bit in the object's header identifies if the
+ * value stored at the header is a deferred handle from the last reclaim
+ * attempt.
+ *
+ * As noted above, this is valid because we have room for two bits.
+ */
+#define OBJ_DEFERRED_HANDLE_TAG	2
+#define OBJ_TAG_BITS	2
+#define OBJ_TAG_MASK	(OBJ_ALLOCATED_TAG | OBJ_DEFERRED_HANDLE_TAG)
+#else
+#define OBJ_TAG_BITS	1
+#define OBJ_TAG_MASK	OBJ_ALLOCATED_TAG
+#endif /* CONFIG_ZPOOL */
+
 #define OBJ_INDEX_BITS	(BITS_PER_LONG - _PFN_BITS - OBJ_TAG_BITS)
 #define OBJ_INDEX_MASK	((_AC(1, UL) << OBJ_INDEX_BITS) - 1)
 
@@ -222,6 +238,12 @@ struct link_free {
 		 * Handle of allocated object.
 		 */
 		unsigned long handle;
+#ifdef CONFIG_ZPOOL
+		/*
+		 * Deferred handle of a reclaimed object.
+		 */
+		unsigned long deferred_handle;
+#endif
 	};
 };
 
@@ -272,8 +294,6 @@ struct zspage {
 	/* links the zspage to the lru list in the pool */
 	struct list_head lru;
 	bool under_reclaim;
-	/* list of unfreed handles whose objects have been reclaimed */
-	unsigned long *deferred_handles;
 #endif
 
 	struct zs_pool *pool;
@@ -897,7 +917,8 @@ static unsigned long handle_to_obj(unsigned long handle)
 	return *(unsigned long *)handle;
 }
 
-static bool obj_allocated(struct page *page, void *obj, unsigned long *phandle)
+static bool obj_tagged(struct page *page, void *obj, unsigned long *phandle,
+		int tag)
 {
 	unsigned long handle;
 	struct zspage *zspage = get_zspage(page);
@@ -908,13 +929,27 @@ static bool obj_allocated(struct page *page, void *obj, unsigned long *phandle)
 	} else
 		handle = *(unsigned long *)obj;
 
-	if (!(handle & OBJ_ALLOCATED_TAG))
+	if (!(handle & tag))
 		return false;
 
-	*phandle = handle & ~OBJ_ALLOCATED_TAG;
+	/* Clear all tags before returning the handle */
+	*phandle = handle & ~OBJ_TAG_MASK;
 	return true;
 }
 
+static inline bool obj_allocated(struct page *page, void *obj, unsigned long *phandle)
+{
+	return obj_tagged(page, obj, phandle, OBJ_ALLOCATED_TAG);
+}
+
+#ifdef CONFIG_ZPOOL
+static bool obj_stores_deferred_handle(struct page *page, void *obj,
+		unsigned long *phandle)
+{
+	return obj_tagged(page, obj, phandle, OBJ_DEFERRED_HANDLE_TAG);
+}
+#endif
+
 static void reset_page(struct page *page)
 {
 	__ClearPageMovable(page);
@@ -946,22 +981,36 @@ static int trylock_zspage(struct zspage *zspage)
 }
 
 #ifdef CONFIG_ZPOOL
+static unsigned long find_deferred_handle_obj(struct size_class *class,
+		struct page *page, int *obj_idx);
+
 /*
  * Free all the deferred handles whose objects are freed in zs_free.
  */
-static void free_handles(struct zs_pool *pool, struct zspage *zspage)
+static void free_handles(struct zs_pool *pool, struct size_class *class,
+		struct zspage *zspage)
 {
-	unsigned long handle = (unsigned long)zspage->deferred_handles;
+	int obj_idx = 0;
+	struct page *page = get_first_page(zspage);
+	unsigned long handle;
 
-	while (handle) {
-		unsigned long nxt_handle = handle_to_obj(handle);
+	while (1) {
+		handle = find_deferred_handle_obj(class, page, &obj_idx);
+		if (!handle) {
+			page = get_next_page(page);
+			if (!page)
+				break;
+			obj_idx = 0;
+			continue;
+		}
 
 		cache_free_handle(pool, handle);
-		handle = nxt_handle;
+		obj_idx++;
 	}
 }
 #else
-static inline void free_handles(struct zs_pool *pool, struct zspage *zspage) {}
+static inline void free_handles(struct zs_pool *pool, struct size_class *class,
+		struct zspage *zspage) {}
 #endif
 
 static void __free_zspage(struct zs_pool *pool, struct size_class *class,
@@ -979,7 +1028,7 @@ static void __free_zspage(struct zs_pool *pool, struct size_class *class,
 	VM_BUG_ON(fg != ZS_EMPTY);
 
 	/* Free all deferred handles from zs_free */
-	free_handles(pool, zspage);
+	free_handles(pool, class, zspage);
 
 	next = page = get_first_page(zspage);
 	do {
@@ -1067,7 +1116,6 @@ static void init_zspage(struct size_class *class, struct zspage *zspage)
 #ifdef CONFIG_ZPOOL
 	INIT_LIST_HEAD(&zspage->lru);
 	zspage->under_reclaim = false;
-	zspage->deferred_handles = NULL;
 #endif
 
 	set_freeobj(zspage, 0);
@@ -1568,7 +1616,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp)
 }
 EXPORT_SYMBOL_GPL(zs_malloc);
 
-static void obj_free(int class_size, unsigned long obj)
+static void obj_free(int class_size, unsigned long obj, unsigned long *handle)
 {
 	struct link_free *link;
 	struct zspage *zspage;
@@ -1582,15 +1630,29 @@ static void obj_free(int class_size, unsigned long obj)
 	zspage = get_zspage(f_page);
 
 	vaddr = kmap_atomic(f_page);
-
-	/* Insert this object in containing zspage's freelist */
 	link = (struct link_free *)(vaddr + f_offset);
-	if (likely(!ZsHugePage(zspage)))
-		link->next = get_freeobj(zspage) << OBJ_TAG_BITS;
-	else
-		f_page->index = 0;
+
+	if (handle) {
+#ifdef CONFIG_ZPOOL
+		/* Stores the (deferred) handle in the object's header */
+		*handle |= OBJ_DEFERRED_HANDLE_TAG;
+		*handle &= ~OBJ_ALLOCATED_TAG;
+
+		if (likely(!ZsHugePage(zspage)))
+			link->deferred_handle = *handle;
+		else
+			f_page->index = *handle;
+#endif
+	} else {
+		/* Insert this object in containing zspage's freelist */
+		if (likely(!ZsHugePage(zspage)))
+			link->next = get_freeobj(zspage) << OBJ_TAG_BITS;
+		else
+			f_page->index = 0;
+		set_freeobj(zspage, f_objidx);
+	}
+
 	kunmap_atomic(vaddr);
-	set_freeobj(zspage, f_objidx);
 	mod_zspage_inuse(zspage, -1);
 }
 
@@ -1615,7 +1677,6 @@ void zs_free(struct zs_pool *pool, unsigned long handle)
 	zspage = get_zspage(f_page);
 	class = zspage_class(pool, zspage);
 
-	obj_free(class->size, obj);
 	class_stat_dec(class, OBJ_USED, 1);
 
 #ifdef CONFIG_ZPOOL
@@ -1624,15 +1685,15 @@ void zs_free(struct zs_pool *pool, unsigned long handle)
 		 * Reclaim needs the handles during writeback. It'll free
 		 * them along with the zspage when it's done with them.
 		 *
-		 * Record current deferred handle at the memory location
-		 * whose address is given by handle.
+		 * Record current deferred handle in the object's header.
 		 */
-		record_obj(handle, (unsigned long)zspage->deferred_handles);
-		zspage->deferred_handles = (unsigned long *)handle;
+		obj_free(class->size, obj, &handle);
 		spin_unlock(&pool->lock);
 		return;
 	}
 #endif
+	obj_free(class->size, obj, NULL);
+
 	fullness = fix_fullness_group(class, zspage);
 	if (fullness == ZS_EMPTY)
 		free_zspage(pool, class, zspage);
@@ -1713,11 +1774,11 @@ static void zs_object_copy(struct size_class *class, unsigned long dst,
 }
 
 /*
- * Find alloced object in zspage from index object and
+ * Find object with a certain tag in zspage from index object and
  * return handle.
  */
-static unsigned long find_alloced_obj(struct size_class *class,
-					struct page *page, int *obj_idx)
+static unsigned long find_tagged_obj(struct size_class *class,
+					struct page *page, int *obj_idx, int tag)
 {
 	unsigned int offset;
 	int index = *obj_idx;
@@ -1728,7 +1789,7 @@ static unsigned long find_alloced_obj(struct size_class *class,
 	offset += class->size * index;
 
 	while (offset < PAGE_SIZE) {
-		if (obj_allocated(page, addr + offset, &handle))
+		if (obj_tagged(page, addr + offset, &handle, tag))
 			break;
 
 		offset += class->size;
@@ -1742,6 +1803,28 @@ static unsigned long find_alloced_obj(struct size_class *class,
 	return handle;
 }
 
+/*
+ * Find alloced object in zspage from index object and
+ * return handle.
+ */
+static unsigned long find_alloced_obj(struct size_class *class,
+					struct page *page, int *obj_idx)
+{
+	return find_tagged_obj(class, page, obj_idx, OBJ_ALLOCATED_TAG);
+}
+
+#ifdef CONFIG_ZPOOL
+/*
+ * Find object storing a deferred handle in header in zspage from index object
+ * and return handle.
+ */
+static unsigned long find_deferred_handle_obj(struct size_class *class,
+		struct page *page, int *obj_idx)
+{
+	return find_tagged_obj(class, page, obj_idx, OBJ_DEFERRED_HANDLE_TAG);
+}
+#endif
+
 struct zs_compact_control {
 	/* Source spage for migration which could be a subpage of zspage */
 	struct page *s_page;
@@ -1784,7 +1867,7 @@ static int migrate_zspage(struct zs_pool *pool, struct size_class *class,
 		zs_object_copy(class, free_obj, used_obj);
 		obj_idx++;
 		record_obj(handle, free_obj);
-		obj_free(class->size, used_obj);
+		obj_free(class->size, used_obj, NULL);
 	}
 
 	/* Remember last position in this iteration */
@@ -2475,6 +2558,90 @@ void zs_destroy_pool(struct zs_pool *pool)
 EXPORT_SYMBOL_GPL(zs_destroy_pool);
 
 #ifdef CONFIG_ZPOOL
+static void restore_freelist(struct zs_pool *pool, struct size_class *class,
+		struct zspage *zspage)
+{
+	unsigned int obj_idx = 0;
+	unsigned long handle, off = 0; /* off is within-page offset */
+	struct page *page = get_first_page(zspage);
+	struct link_free *prev_free = NULL;
+	void *prev_page_vaddr = NULL;
+
+	/* in case no free object found */
+	set_freeobj(zspage, (unsigned int)(-1UL));
+
+	while (page) {
+		void *vaddr = kmap_atomic(page);
+		struct page *next_page;
+
+		while (off < PAGE_SIZE) {
+			void *obj_addr = vaddr + off;
+
+			/* skip allocated object */
+			if (obj_allocated(page, obj_addr, &handle)) {
+				obj_idx++;
+				off += class->size;
+				continue;
+			}
+
+			/* free deferred handle from reclaim attempt */
+			if (obj_stores_deferred_handle(page, obj_addr, &handle))
+				cache_free_handle(pool, handle);
+
+			if (prev_free)
+				prev_free->next = obj_idx << OBJ_TAG_BITS;
+			else /* first free object found */
+				set_freeobj(zspage, obj_idx);
+
+			prev_free = (struct link_free *)vaddr + off / sizeof(*prev_free);
+			/* if last free object in a previous page, need to unmap */
+			if (prev_page_vaddr) {
+				kunmap_atomic(prev_page_vaddr);
+				prev_page_vaddr = NULL;
+			}
+
+			obj_idx++;
+			off += class->size;
+		}
+
+		/*
+		 * Handle the last (full or partial) object on this page.
+		 */
+		next_page = get_next_page(page);
+		if (next_page) {
+			if (!prev_free || prev_page_vaddr) {
+				/*
+				 * There is no free object in this page, so we can safely
+				 * unmap it.
+				 */
+				kunmap_atomic(vaddr);
+			} else {
+				/* update prev_page_vaddr since prev_free is on this page */
+				prev_page_vaddr = vaddr;
+			}
+		} else { /* this is the last page */
+			if (prev_free) {
+				/*
+				 * Reset OBJ_TAG_BITS bit to last link to tell
+				 * whether it's allocated object or not.
+				 */
+				prev_free->next = -1UL << OBJ_TAG_BITS;
+			}
+
+			/* unmap previous page (if not done yet) */
+			if (prev_page_vaddr) {
+				kunmap_atomic(prev_page_vaddr);
+				prev_page_vaddr = NULL;
+			}
+
+			kunmap_atomic(vaddr);
+		}
+
+		page = next_page;
+		off %= PAGE_SIZE;
+	}
+}
+
 static int zs_reclaim_page(struct zs_pool *pool, unsigned int retries)
 {
 	int i, obj_idx, ret = 0;
@@ -2558,6 +2725,12 @@ static int zs_reclaim_page(struct zs_pool *pool, unsigned int retries)
 			return 0;
 		}
 
+		/*
+		 * Eviction fails on one of the handles, so we need to restore zspage.
+		 * We need to rebuild its freelist (and free stored deferred handles),
+		 * put it back to the correct size class, and add it to the LRU list.
+		 */
+		restore_freelist(pool, class, zspage);
 		putback_zspage(class, zspage);
 		list_add(&zspage->lru, &pool->lru);
 		unlock_zspage(zspage);

tools/testing/selftests/mm/hugetlb-madvise.c

@@ -17,7 +17,6 @@
 #include <stdio.h>
 #include <unistd.h>
 #include <sys/mman.h>
-#define __USE_GNU
 #include <fcntl.h>
 
 #define MIN_FREE_PAGES	20