Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:

 - more ocfs2 work

 - various leftovers

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  memory_hotplug: cond_resched in __remove_pages
  bfs: add sanity check at bfs_fill_super()
  kernel/sysctl.c: remove duplicated include
  kernel/kexec_file.c: remove some duplicated includes
  mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask
  ocfs2: fix clusters leak in ocfs2_defrag_extent()
  ocfs2: dlmglue: clean up timestamp handling
  ocfs2: don't put and assigning null to bh allocated outside
  ocfs2: fix a misuse a of brelse after failing ocfs2_check_dir_entry
  ocfs2: don't use iocb when EIOCBQUEUED returns
  ocfs2: without quota support, avoid calling quota recovery
  ocfs2: remove ocfs2_is_o2cb_active()
  mm: thp: relax __GFP_THISNODE for MADV_HUGEPAGE mappings
  include/linux/notifier.h: SRCU: fix ctags
  mm: handle no memcg case in memcg_kmem_charge() properly

fs/bfs/inode.c

@@ -350,7 +350,8 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent)
 
 	s->s_magic = BFS_MAGIC;
 
-	if (le32_to_cpu(bfs_sb->s_start) > le32_to_cpu(bfs_sb->s_end)) {
+	if (le32_to_cpu(bfs_sb->s_start) > le32_to_cpu(bfs_sb->s_end) ||
+	    le32_to_cpu(bfs_sb->s_start) < BFS_BSIZE) {
 		printf("Superblock is corrupted\n");
 		goto out1;
 	}
@@ -359,9 +360,11 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent)
 					sizeof(struct bfs_inode)
 					+ BFS_ROOT_INO - 1;
 	imap_len = (info->si_lasti / 8) + 1;
-	info->si_imap = kzalloc(imap_len, GFP_KERNEL);
-	if (!info->si_imap)
+	info->si_imap = kzalloc(imap_len, GFP_KERNEL | __GFP_NOWARN);
+	if (!info->si_imap) {
+		printf("Cannot allocate %u bytes\n", imap_len);
 		goto out1;
+	}
 	for (i = 0; i < BFS_ROOT_INO; i++)
 		set_bit(i, info->si_imap);
 

fs/ocfs2/buffer_head_io.c

@@ -99,25 +99,34 @@ int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh,
 	return ret;
 }
 
+/* Caller must provide a bhs[] with all NULL or non-NULL entries, so it
+ * will be easier to handle read failure.
+ */
 int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
 			   unsigned int nr, struct buffer_head *bhs[])
 {
 	int status = 0;
 	unsigned int i;
 	struct buffer_head *bh;
+	int new_bh = 0;
 
 	trace_ocfs2_read_blocks_sync((unsigned long long)block, nr);
 
 	if (!nr)
 		goto bail;
 
+	/* Don't put buffer head and re-assign it to NULL if it is allocated
+	 * outside since the caller can't be aware of this alternation!
+	 */
+	new_bh = (bhs[0] == NULL);
+
 	for (i = 0 ; i < nr ; i++) {
 		if (bhs[i] == NULL) {
 			bhs[i] = sb_getblk(osb->sb, block++);
 			if (bhs[i] == NULL) {
 				status = -ENOMEM;
 				mlog_errno(status);
-				goto bail;
+				break;
 			}
 		}
 		bh = bhs[i];
@@ -158,9 +167,26 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
 		submit_bh(REQ_OP_READ, 0, bh);
 	}
 
+read_failure:
 	for (i = nr; i > 0; i--) {
 		bh = bhs[i - 1];
 
+		if (unlikely(status)) {
+			if (new_bh && bh) {
+				/* If middle bh fails, let previous bh
+				 * finish its read and then put it to
+				 * aovoid bh leak
+				 */
+				if (!buffer_jbd(bh))
+					wait_on_buffer(bh);
+				put_bh(bh);
+				bhs[i - 1] = NULL;
+			} else if (bh && buffer_uptodate(bh)) {
+				clear_buffer_uptodate(bh);
+			}
+			continue;
+		}
+
 		/* No need to wait on the buffer if it's managed by JBD. */
 		if (!buffer_jbd(bh))
 			wait_on_buffer(bh);
@@ -170,8 +196,7 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
 			 * so we can safely record this and loop back
 			 * to cleanup the other buffers. */
 			status = -EIO;
-			put_bh(bh);
-			bhs[i - 1] = NULL;
+			goto read_failure;
 		}
 	}
 
@@ -179,6 +204,9 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
 	return status;
 }
 
+/* Caller must provide a bhs[] with all NULL or non-NULL entries, so it
+ * will be easier to handle read failure.
+ */
 int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 		      struct buffer_head *bhs[], int flags,
 		      int (*validate)(struct super_block *sb,
@@ -188,6 +216,7 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 	int i, ignore_cache = 0;
 	struct buffer_head *bh;
 	struct super_block *sb = ocfs2_metadata_cache_get_super(ci);
+	int new_bh = 0;
 
 	trace_ocfs2_read_blocks_begin(ci, (unsigned long long)block, nr, flags);
 
@@ -213,6 +242,11 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 		goto bail;
 	}
 
+	/* Don't put buffer head and re-assign it to NULL if it is allocated
+	 * outside since the caller can't be aware of this alternation!
+	 */
+	new_bh = (bhs[0] == NULL);
+
 	ocfs2_metadata_cache_io_lock(ci);
 	for (i = 0 ; i < nr ; i++) {
 		if (bhs[i] == NULL) {
@@ -221,7 +255,8 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 				ocfs2_metadata_cache_io_unlock(ci);
 				status = -ENOMEM;
 				mlog_errno(status);
-				goto bail;
+				/* Don't forget to put previous bh! */
+				break;
 			}
 		}
 		bh = bhs[i];
@@ -316,16 +351,27 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 		}
 	}
 
-	status = 0;
-
+read_failure:
 	for (i = (nr - 1); i >= 0; i--) {
 		bh = bhs[i];
 
 		if (!(flags & OCFS2_BH_READAHEAD)) {
-			if (status) {
-				/* Clear the rest of the buffers on error */
+			if (unlikely(status)) {
+				/* Clear the buffers on error including those
+				 * ever succeeded in reading
+				 */
+				if (new_bh && bh) {
+					/* If middle bh fails, let previous bh
+					 * finish its read and then put it to
+					 * aovoid bh leak
+					 */
+					if (!buffer_jbd(bh))
+						wait_on_buffer(bh);
 					put_bh(bh);
 					bhs[i] = NULL;
+				} else if (bh && buffer_uptodate(bh)) {
+					clear_buffer_uptodate(bh);
+				}
 				continue;
 			}
 			/* We know this can't have changed as we hold the
@@ -343,9 +389,7 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 				 * uptodate. */
 				status = -EIO;
 				clear_buffer_needs_validate(bh);
-				put_bh(bh);
-				bhs[i] = NULL;
-				continue;
+				goto read_failure;
 			}
 
 			if (buffer_needs_validate(bh)) {
@@ -355,11 +399,8 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 				BUG_ON(buffer_jbd(bh));
 				clear_buffer_needs_validate(bh);
 				status = validate(sb, bh);
-				if (status) {
-					put_bh(bh);
-					bhs[i] = NULL;
-					continue;
-				}
+				if (status)
+					goto read_failure;
 			}
 		}
 

fs/ocfs2/dir.c

@@ -1897,8 +1897,7 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode,
 				/* On error, skip the f_pos to the
 				   next block. */
 				ctx->pos = (ctx->pos | (sb->s_blocksize - 1)) + 1;
-				brelse(bh);
-				continue;
+				break;
 			}
 			if (le64_to_cpu(de->inode)) {
 				unsigned char d_type = DT_UNKNOWN;

fs/ocfs2/dlmglue.c

@@ -2123,10 +2123,10 @@ static void ocfs2_downconvert_on_unlock(struct ocfs2_super *osb,
 
 /* LVB only has room for 64 bits of time here so we pack it for
  * now. */
-static u64 ocfs2_pack_timespec(struct timespec *spec)
+static u64 ocfs2_pack_timespec(struct timespec64 *spec)
 {
 	u64 res;
-	u64 sec = spec->tv_sec;
+	u64 sec = clamp_t(time64_t, spec->tv_sec, 0, 0x3ffffffffull);
 	u32 nsec = spec->tv_nsec;
 
 	res = (sec << OCFS2_SEC_SHIFT) | (nsec & OCFS2_NSEC_MASK);
@@ -2142,7 +2142,6 @@ static void __ocfs2_stuff_meta_lvb(struct inode *inode)
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
 	struct ocfs2_lock_res *lockres = &oi->ip_inode_lockres;
 	struct ocfs2_meta_lvb *lvb;
-	struct timespec ts;
 
 	lvb = ocfs2_dlm_lvb(&lockres->l_lksb);
 
@@ -2163,15 +2162,12 @@ static void __ocfs2_stuff_meta_lvb(struct inode *inode)
 	lvb->lvb_igid      = cpu_to_be32(i_gid_read(inode));
 	lvb->lvb_imode     = cpu_to_be16(inode->i_mode);
 	lvb->lvb_inlink    = cpu_to_be16(inode->i_nlink);
-	ts = timespec64_to_timespec(inode->i_atime);
 	lvb->lvb_iatime_packed  =
-		cpu_to_be64(ocfs2_pack_timespec(&ts));
-	ts = timespec64_to_timespec(inode->i_ctime);
+		cpu_to_be64(ocfs2_pack_timespec(&inode->i_atime));
 	lvb->lvb_ictime_packed =
-		cpu_to_be64(ocfs2_pack_timespec(&ts));
-	ts = timespec64_to_timespec(inode->i_mtime);
+		cpu_to_be64(ocfs2_pack_timespec(&inode->i_ctime));
 	lvb->lvb_imtime_packed =
-		cpu_to_be64(ocfs2_pack_timespec(&ts));
+		cpu_to_be64(ocfs2_pack_timespec(&inode->i_mtime));
 	lvb->lvb_iattr    = cpu_to_be32(oi->ip_attr);
 	lvb->lvb_idynfeatures = cpu_to_be16(oi->ip_dyn_features);
 	lvb->lvb_igeneration = cpu_to_be32(inode->i_generation);
@@ -2180,7 +2176,7 @@ static void __ocfs2_stuff_meta_lvb(struct inode *inode)
 	mlog_meta_lvb(0, lockres);
 }
 
-static void ocfs2_unpack_timespec(struct timespec *spec,
+static void ocfs2_unpack_timespec(struct timespec64 *spec,
 				  u64 packed_time)
 {
 	spec->tv_sec = packed_time >> OCFS2_SEC_SHIFT;
@@ -2189,7 +2185,6 @@ static void ocfs2_unpack_timespec(struct timespec *spec,
 
 static void ocfs2_refresh_inode_from_lvb(struct inode *inode)
 {
-	struct timespec ts;
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
 	struct ocfs2_lock_res *lockres = &oi->ip_inode_lockres;
 	struct ocfs2_meta_lvb *lvb;
@@ -2217,15 +2212,12 @@ static void ocfs2_refresh_inode_from_lvb(struct inode *inode)
 	i_gid_write(inode, be32_to_cpu(lvb->lvb_igid));
 	inode->i_mode    = be16_to_cpu(lvb->lvb_imode);
 	set_nlink(inode, be16_to_cpu(lvb->lvb_inlink));
-	ocfs2_unpack_timespec(&ts,
+	ocfs2_unpack_timespec(&inode->i_atime,
 			      be64_to_cpu(lvb->lvb_iatime_packed));
-	inode->i_atime = timespec_to_timespec64(ts);
-	ocfs2_unpack_timespec(&ts,
+	ocfs2_unpack_timespec(&inode->i_mtime,
 			      be64_to_cpu(lvb->lvb_imtime_packed));
-	inode->i_mtime = timespec_to_timespec64(ts);
-	ocfs2_unpack_timespec(&ts,
+	ocfs2_unpack_timespec(&inode->i_ctime,
 			      be64_to_cpu(lvb->lvb_ictime_packed));
-	inode->i_ctime = timespec_to_timespec64(ts);
 	spin_unlock(&oi->ip_lock);
 }
 
@@ -3603,7 +3595,7 @@ static int ocfs2_downconvert_lock(struct ocfs2_super *osb,
 	 * we can recover correctly from node failure. Otherwise, we may get
 	 * invalid LVB in LKB, but without DLM_SBF_VALNOTVALID being set.
 	 */
-	if (!ocfs2_is_o2cb_active() &&
+	if (ocfs2_userspace_stack(osb) &&
 	    lockres->l_ops->flags & LOCK_TYPE_USES_LVB)
 		lvb = 1;
 

fs/ocfs2/file.c

@@ -2343,7 +2343,7 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 
 	written = __generic_file_write_iter(iocb, from);
 	/* buffered aio wouldn't have proper lock coverage today */
-	BUG_ON(written == -EIOCBQUEUED && !(iocb->ki_flags & IOCB_DIRECT));
+	BUG_ON(written == -EIOCBQUEUED && !direct_io);
 
 	/*
 	 * deep in g_f_a_w_n()->ocfs2_direct_IO we pass in a ocfs2_dio_end_io
@@ -2463,7 +2463,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 	trace_generic_file_read_iter_ret(ret);
 
 	/* buffered aio wouldn't have proper lock coverage today */
-	BUG_ON(ret == -EIOCBQUEUED && !(iocb->ki_flags & IOCB_DIRECT));
+	BUG_ON(ret == -EIOCBQUEUED && !direct_io);
 
 	/* see ocfs2_file_write_iter */
 	if (ret == -EIOCBQUEUED || !ocfs2_iocb_is_rw_locked(iocb)) {

fs/ocfs2/journal.c

@@ -1378,16 +1378,24 @@ static int __ocfs2_recovery_thread(void *arg)
 	int rm_quota_used = 0, i;
 	struct ocfs2_quota_recovery *qrec;
 
+	/* Whether the quota supported. */
+	int quota_enabled = OCFS2_HAS_RO_COMPAT_FEATURE(osb->sb,
+			OCFS2_FEATURE_RO_COMPAT_USRQUOTA)
+		|| OCFS2_HAS_RO_COMPAT_FEATURE(osb->sb,
+			OCFS2_FEATURE_RO_COMPAT_GRPQUOTA);
+
 	status = ocfs2_wait_on_mount(osb);
 	if (status < 0) {
 		goto bail;
 	}
 
+	if (quota_enabled) {
 		rm_quota = kcalloc(osb->max_slots, sizeof(int), GFP_NOFS);
 		if (!rm_quota) {
 			status = -ENOMEM;
 			goto bail;
 		}
+	}
 restart:
 	status = ocfs2_super_lock(osb, 1);
 	if (status < 0) {
@@ -1422,9 +1430,14 @@ static int __ocfs2_recovery_thread(void *arg)
 		 * then quota usage would be out of sync until some node takes
 		 * the slot. So we remember which nodes need quota recovery
 		 * and when everything else is done, we recover quotas. */
-		for (i = 0; i < rm_quota_used && rm_quota[i] != slot_num; i++);
+		if (quota_enabled) {
+			for (i = 0; i < rm_quota_used
+					&& rm_quota[i] != slot_num; i++)
+				;
+
 			if (i == rm_quota_used)
 				rm_quota[rm_quota_used++] = slot_num;
+		}
 
 		status = ocfs2_recover_node(osb, node_num, slot_num);
 skip_recovery:
@@ -1452,6 +1465,7 @@ static int __ocfs2_recovery_thread(void *arg)
 	/* Now it is right time to recover quotas... We have to do this under
 	 * superblock lock so that no one can start using the slot (and crash)
 	 * before we recover it */
+	if (quota_enabled) {
 		for (i = 0; i < rm_quota_used; i++) {
 			qrec = ocfs2_begin_quota_recovery(osb, rm_quota[i]);
 			if (IS_ERR(qrec)) {
@@ -1459,10 +1473,12 @@ static int __ocfs2_recovery_thread(void *arg)
 				mlog_errno(status);
 				continue;
 			}
-		ocfs2_queue_recovery_completion(osb->journal, rm_quota[i],
+			ocfs2_queue_recovery_completion(osb->journal,
+					rm_quota[i],
 					NULL, NULL, qrec,
 					ORPHAN_NEED_TRUNCATE);
 		}
+	}
 
 	ocfs2_super_unlock(osb, 1);
 
@@ -1483,6 +1499,7 @@ static int __ocfs2_recovery_thread(void *arg)
 
 	mutex_unlock(&osb->recovery_lock);
 
+	if (quota_enabled)
 		kfree(rm_quota);
 
 	/* no one is callint kthread_stop() for us so the kthread() api

fs/ocfs2/move_extents.c

@@ -25,6 +25,7 @@
 #include "ocfs2_ioctl.h"
 
 #include "alloc.h"
+#include "localalloc.h"
 #include "aops.h"
 #include "dlmglue.h"
 #include "extent_map.h"
@@ -233,6 +234,7 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context,
 	struct ocfs2_refcount_tree *ref_tree = NULL;
 	u32 new_phys_cpos, new_len;
 	u64 phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos);
+	int need_free = 0;
 
 	if ((ext_flags & OCFS2_EXT_REFCOUNTED) && *len) {
 		BUG_ON(!ocfs2_is_refcount_inode(inode));
@@ -308,6 +310,7 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context,
 		if (!partial) {
 			context->range->me_flags &= ~OCFS2_MOVE_EXT_FL_COMPLETE;
 			ret = -ENOSPC;
+			need_free = 1;
 			goto out_commit;
 		}
 	}
@@ -332,6 +335,20 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context,
 		mlog_errno(ret);
 
 out_commit:
+	if (need_free && context->data_ac) {
+		struct ocfs2_alloc_context *data_ac = context->data_ac;
+
+		if (context->data_ac->ac_which == OCFS2_AC_USE_LOCAL)
+			ocfs2_free_local_alloc_bits(osb, handle, data_ac,
+					new_phys_cpos, new_len);
+		else
+			ocfs2_free_clusters(handle,
+					data_ac->ac_inode,
+					data_ac->ac_bh,
+					ocfs2_clusters_to_blocks(osb->sb, new_phys_cpos),
+					new_len);
+	}
+
 	ocfs2_commit_trans(osb, handle);
 
 out_unlock_mutex:

fs/ocfs2/stackglue.c

@@ -48,12 +48,6 @@ static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl";
  */
 static struct ocfs2_stack_plugin *active_stack;
 
-inline int ocfs2_is_o2cb_active(void)
-{
-	return !strcmp(active_stack->sp_name, OCFS2_STACK_PLUGIN_O2CB);
-}
-EXPORT_SYMBOL_GPL(ocfs2_is_o2cb_active);
-
 static struct ocfs2_stack_plugin *ocfs2_stack_lookup(const char *name)
 {
 	struct ocfs2_stack_plugin *p;

fs/ocfs2/stackglue.h

@@ -298,9 +298,6 @@ void ocfs2_stack_glue_set_max_proto_version(struct ocfs2_protocol_version *max_p
 int ocfs2_stack_glue_register(struct ocfs2_stack_plugin *plugin);
 void ocfs2_stack_glue_unregister(struct ocfs2_stack_plugin *plugin);
 
-/* In ocfs2_downconvert_lock(), we need to know which stack we are using */
-int ocfs2_is_o2cb_active(void);
-
 extern struct kset *ocfs2_kset;
 
 #endif  /* STACKGLUE_H */

include/linux/gfp.h

@@ -510,22 +510,18 @@ alloc_pages(gfp_t gfp_mask, unsigned int order)
 }
 extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
 			struct vm_area_struct *vma, unsigned long addr,
-			int node, bool hugepage);
-#define alloc_hugepage_vma(gfp_mask, vma, addr, order)	\
-	alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true)
+			int node);
 #else
 #define alloc_pages(gfp_mask, order) \
 		alloc_pages_node(numa_node_id(), gfp_mask, order)
-#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\
-	alloc_pages(gfp_mask, order)
-#define alloc_hugepage_vma(gfp_mask, vma, addr, order)	\
+#define alloc_pages_vma(gfp_mask, order, vma, addr, node)\
 	alloc_pages(gfp_mask, order)
 #endif
 #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
 #define alloc_page_vma(gfp_mask, vma, addr)			\
-	alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false)
+	alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id())
 #define alloc_page_vma_node(gfp_mask, vma, addr, node)		\
-	alloc_pages_vma(gfp_mask, 0, vma, addr, node, false)
+	alloc_pages_vma(gfp_mask, 0, vma, addr, node)
 
 extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order);
 extern unsigned long get_zeroed_page(gfp_t gfp_mask);

include/linux/mempolicy.h

@@ -139,6 +139,8 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp,
 struct mempolicy *get_task_policy(struct task_struct *p);
 struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
 		unsigned long addr);
+struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
+						unsigned long addr);
 bool vma_policy_mof(struct vm_area_struct *vma);
 
 extern void numa_default_policy(void);

include/linux/notifier.h

@@ -122,8 +122,7 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh);
 
 #ifdef CONFIG_TREE_SRCU
 #define _SRCU_NOTIFIER_HEAD(name, mod)				\
-	static DEFINE_PER_CPU(struct srcu_data,			\
-			name##_head_srcu_data);			\
+	static DEFINE_PER_CPU(struct srcu_data, name##_head_srcu_data); \
 	mod struct srcu_notifier_head name =			\
 			SRCU_NOTIFIER_INIT(name, name##_head_srcu_data)
 

kernel/kexec_file.c

@@ -25,8 +25,6 @@
 #include <linux/elf.h>
 #include <linux/elfcore.h>
 #include <linux/kernel.h>
-#include <linux/kexec.h>
-#include <linux/slab.h>
 #include <linux/syscalls.h>
 #include <linux/vmalloc.h>
 #include "kexec_internal.h"

kernel/sysctl.c

@@ -66,7 +66,6 @@
 #include <linux/kexec.h>
 #include <linux/bpf.h>
 #include <linux/mount.h>
-#include <linux/pipe_fs_i.h>
 
 #include <linux/uaccess.h>
 #include <asm/processor.h>

mm/huge_memory.c

@@ -629,21 +629,40 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
  *	    available
  * never: never stall for any thp allocation
  */
-static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma)
+static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma, unsigned long addr)
 {
 	const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE);
+	gfp_t this_node = 0;
+
+#ifdef CONFIG_NUMA
+	struct mempolicy *pol;
+	/*
+	 * __GFP_THISNODE is used only when __GFP_DIRECT_RECLAIM is not
+	 * specified, to express a general desire to stay on the current
+	 * node for optimistic allocation attempts. If the defrag mode
+	 * and/or madvise hint requires the direct reclaim then we prefer
+	 * to fallback to other node rather than node reclaim because that
+	 * can lead to excessive reclaim even though there is free memory
+	 * on other nodes. We expect that NUMA preferences are specified
+	 * by memory policies.
+	 */
+	pol = get_vma_policy(vma, addr);
+	if (pol->mode != MPOL_BIND)
+		this_node = __GFP_THISNODE;
+	mpol_cond_put(pol);
+#endif
 
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
 		return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY);
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
-		return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM;
+		return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM | this_node;
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags))
 		return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
-							     __GFP_KSWAPD_RECLAIM);
+							     __GFP_KSWAPD_RECLAIM | this_node);
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
 		return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
-							     0);
-	return GFP_TRANSHUGE_LIGHT;
+							     this_node);
+	return GFP_TRANSHUGE_LIGHT | this_node;
 }
 
 /* Caller must hold page table lock. */
@@ -715,8 +734,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 			pte_free(vma->vm_mm, pgtable);
 		return ret;
 	}
-	gfp = alloc_hugepage_direct_gfpmask(vma);
-	page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER);
+	gfp = alloc_hugepage_direct_gfpmask(vma, haddr);
+	page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, vma, haddr, numa_node_id());
 	if (unlikely(!page)) {
 		count_vm_event(THP_FAULT_FALLBACK);
 		return VM_FAULT_FALLBACK;
@@ -1286,8 +1305,9 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
 alloc:
 	if (transparent_hugepage_enabled(vma) &&
 	    !transparent_hugepage_debug_cow()) {
-		huge_gfp = alloc_hugepage_direct_gfpmask(vma);
-		new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER);
+		huge_gfp = alloc_hugepage_direct_gfpmask(vma, haddr);
+		new_page = alloc_pages_vma(huge_gfp, HPAGE_PMD_ORDER, vma,
+				haddr, numa_node_id());
 	} else
 		new_page = NULL;
 

mm/memcontrol.c

@@ -2593,7 +2593,7 @@ int memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
 	struct mem_cgroup *memcg;
 	int ret = 0;
 
-	if (memcg_kmem_bypass())
+	if (mem_cgroup_disabled() || memcg_kmem_bypass())
 		return 0;
 
 	memcg = get_mem_cgroup_from_current();

mm/memory_hotplug.c

@@ -586,6 +586,7 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
 	for (i = 0; i < sections_to_remove; i++) {
 		unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION;
 
+		cond_resched();
 		ret = __remove_section(zone, __pfn_to_section(pfn), map_offset,
 				altmap);
 		map_offset = 0;

mm/mempolicy.c

@@ -1116,8 +1116,8 @@ static struct page *new_page(struct page *page, unsigned long start)
 	} else if (PageTransHuge(page)) {
 		struct page *thp;
 
-		thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address,
-					 HPAGE_PMD_ORDER);
+		thp = alloc_pages_vma(GFP_TRANSHUGE, HPAGE_PMD_ORDER, vma,
+				address, numa_node_id());
 		if (!thp)
 			return NULL;
 		prep_transhuge_page(thp);
@@ -1662,7 +1662,7 @@ struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
  * freeing by another task.  It is the caller's responsibility to free the
  * extra reference for shared policies.
  */
-static struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
+struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
 						unsigned long addr)
 {
 	struct mempolicy *pol = __get_vma_policy(vma, addr);
@@ -2011,7 +2011,6 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
  * 	@vma:  Pointer to VMA or NULL if not available.
  *	@addr: Virtual Address of the allocation. Must be inside the VMA.
  *	@node: Which node to prefer for allocation (modulo policy).
- *	@hugepage: for hugepages try only the preferred node if possible
  *
  * 	This function allocates a page from the kernel page pool and applies
  *	a NUMA policy associated with the VMA or the current process.
@@ -2022,7 +2021,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
  */
 struct page *
 alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
-		unsigned long addr, int node, bool hugepage)
+		unsigned long addr, int node)
 {
 	struct mempolicy *pol;
 	struct page *page;
@@ -2040,32 +2039,6 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 		goto out;
 	}
 
-	if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) {
-		int hpage_node = node;
-
-		/*
-		 * For hugepage allocation and non-interleave policy which
-		 * allows the current node (or other explicitly preferred
-		 * node) we only try to allocate from the current/preferred
-		 * node and don't fall back to other nodes, as the cost of
-		 * remote accesses would likely offset THP benefits.
-		 *
-		 * If the policy is interleave, or does not allow the current
-		 * node in its nodemask, we allocate the standard way.
-		 */
-		if (pol->mode == MPOL_PREFERRED &&
-						!(pol->flags & MPOL_F_LOCAL))
-			hpage_node = pol->v.preferred_node;
-
-		nmask = policy_nodemask(gfp, pol);
-		if (!nmask || node_isset(hpage_node, *nmask)) {
-			mpol_cond_put(pol);
-			page = __alloc_pages_node(hpage_node,
-						gfp | __GFP_THISNODE, order);
-			goto out;
-		}
-	}
-
 	nmask = policy_nodemask(gfp, pol);
 	preferred_nid = policy_node(gfp, pol, node);
 	page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask);

mm/shmem.c

@@ -1435,7 +1435,7 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp,
 
 	shmem_pseudo_vma_init(&pvma, info, hindex);
 	page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN,
-			HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true);
+			HPAGE_PMD_ORDER, &pvma, 0, numa_node_id());
 	shmem_pseudo_vma_destroy(&pvma);
 	if (page)
 		prep_transhuge_page(page);