Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "17 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  hexagon: define ioremap_uc
  ocfs2: fix the crash due to call ocfs2_get_dlm_debug once less
  ocfs2: call journal flush to mark journal as empty after journal recovery when mount
  mm/hugetlb: defer freeing of huge pages if in non-task context
  mm/gup: fix memory leak in __gup_benchmark_ioctl
  mm/oom: fix pgtables units mismatch in Killed process message
  fs/posix_acl.c: fix kernel-doc warnings
  hexagon: work around compiler crash
  hexagon: parenthesize registers in asm predicates
  fs/namespace.c: make to_mnt_ns() static
  fs/nsfs.c: include headers for missing declarations
  fs/direct-io.c: include fs/internal.h for missing prototype
  mm: move_pages: return valid node id in status if the page is already on the target node
  memcg: account security cred as well to kmemcg
  kcov: fix struct layout for kcov_remote_arg
  mm/zsmalloc.c: fix the migrated zspage statistics.
  mm/memory_hotplug: shrink zones when offlining memory

Documentation/dev-tools/kcov.rst

@@ -251,11 +251,11 @@ selectively from different subsystems.
 .. code-block:: c
 
     struct kcov_remote_arg {
-	unsigned	trace_mode;
-	unsigned	area_size;
-	unsigned	num_handles;
-	uint64_t	common_handle;
-	uint64_t	handles[0];
+	__u32		trace_mode;
+	__u32		area_size;
+	__u32		num_handles;
+	__aligned_u64	common_handle;
+	__aligned_u64	handles[0];
     };
 
     #define KCOV_INIT_TRACE			_IOR('c', 1, unsigned long)

arch/arm64/mm/mmu.c

@@ -1070,7 +1070,6 @@ void arch_remove_memory(int nid, u64 start, u64 size,
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
-	struct zone *zone;
 
 	/*
 	 * FIXME: Cleanup page tables (also in arch_add_memory() in case
@@ -1079,7 +1078,6 @@ void arch_remove_memory(int nid, u64 start, u64 size,
 	 * unplug. ARCH_ENABLE_MEMORY_HOTREMOVE must not be
 	 * unlocked yet.
 	 */
-	zone = page_zone(pfn_to_page(start_pfn));
-	__remove_pages(zone, start_pfn, nr_pages, altmap);
+	__remove_pages(start_pfn, nr_pages, altmap);
 }
 #endif

arch/hexagon/include/asm/atomic.h

@@ -91,7 +91,7 @@ static inline void atomic_##op(int i, atomic_t *v)			\
 		"1:	%0 = memw_locked(%1);\n"			\
 		"	%0 = "#op "(%0,%2);\n"				\
 		"	memw_locked(%1,P3)=%0;\n"			\
-		"	if !P3 jump 1b;\n"				\
+		"	if (!P3) jump 1b;\n"				\
 		: "=&r" (output)					\
 		: "r" (&v->counter), "r" (i)				\
 		: "memory", "p3"					\
@@ -107,7 +107,7 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 		"1:	%0 = memw_locked(%1);\n"			\
 		"	%0 = "#op "(%0,%2);\n"				\
 		"	memw_locked(%1,P3)=%0;\n"			\
-		"	if !P3 jump 1b;\n"				\
+		"	if (!P3) jump 1b;\n"				\
 		: "=&r" (output)					\
 		: "r" (&v->counter), "r" (i)				\
 		: "memory", "p3"					\
@@ -124,7 +124,7 @@ static inline int atomic_fetch_##op(int i, atomic_t *v)			\
 		"1:	%0 = memw_locked(%2);\n"			\
 		"	%1 = "#op "(%0,%3);\n"				\
 		"	memw_locked(%2,P3)=%1;\n"			\
-		"	if !P3 jump 1b;\n"				\
+		"	if (!P3) jump 1b;\n"				\
 		: "=&r" (output), "=&r" (val)				\
 		: "r" (&v->counter), "r" (i)				\
 		: "memory", "p3"					\
@@ -173,7 +173,7 @@ static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 		"	}"
 		"	memw_locked(%2, p3) = %1;"
 		"	{"
-		"		if !p3 jump 1b;"
+		"		if (!p3) jump 1b;"
 		"	}"
 		"2:"
 		: "=&r" (__oldval), "=&r" (tmp)

arch/hexagon/include/asm/bitops.h

@@ -38,7 +38,7 @@ static inline int test_and_clear_bit(int nr, volatile void *addr)
 	"1:	R12 = memw_locked(R10);\n"
 	"	{ P0 = tstbit(R12,R11); R12 = clrbit(R12,R11); }\n"
 	"	memw_locked(R10,P1) = R12;\n"
-	"	{if !P1 jump 1b; %0 = mux(P0,#1,#0);}\n"
+	"	{if (!P1) jump 1b; %0 = mux(P0,#1,#0);}\n"
 	: "=&r" (oldval)
 	: "r" (addr), "r" (nr)
 	: "r10", "r11", "r12", "p0", "p1", "memory"
@@ -62,7 +62,7 @@ static inline int test_and_set_bit(int nr, volatile void *addr)
 	"1:	R12 = memw_locked(R10);\n"
 	"	{ P0 = tstbit(R12,R11); R12 = setbit(R12,R11); }\n"
 	"	memw_locked(R10,P1) = R12;\n"
-	"	{if !P1 jump 1b; %0 = mux(P0,#1,#0);}\n"
+	"	{if (!P1) jump 1b; %0 = mux(P0,#1,#0);}\n"
 	: "=&r" (oldval)
 	: "r" (addr), "r" (nr)
 	: "r10", "r11", "r12", "p0", "p1", "memory"
@@ -88,7 +88,7 @@ static inline int test_and_change_bit(int nr, volatile void *addr)
 	"1:	R12 = memw_locked(R10);\n"
 	"	{ P0 = tstbit(R12,R11); R12 = togglebit(R12,R11); }\n"
 	"	memw_locked(R10,P1) = R12;\n"
-	"	{if !P1 jump 1b; %0 = mux(P0,#1,#0);}\n"
+	"	{if (!P1) jump 1b; %0 = mux(P0,#1,#0);}\n"
 	: "=&r" (oldval)
 	: "r" (addr), "r" (nr)
 	: "r10", "r11", "r12", "p0", "p1", "memory"
@@ -223,7 +223,7 @@ static inline int ffs(int x)
 	int r;
 
 	asm("{ P0 = cmp.eq(%1,#0); %0 = ct0(%1);}\n"
-		"{ if P0 %0 = #0; if !P0 %0 = add(%0,#1);}\n"
+		"{ if (P0) %0 = #0; if (!P0) %0 = add(%0,#1);}\n"
 		: "=&r" (r)
 		: "r" (x)
 		: "p0");

arch/hexagon/include/asm/cmpxchg.h

@@ -30,7 +30,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
 	__asm__ __volatile__ (
 	"1:	%0 = memw_locked(%1);\n"    /*  load into retval */
 	"	memw_locked(%1,P0) = %2;\n" /*  store into memory */
-	"	if !P0 jump 1b;\n"
+	"	if (!P0) jump 1b;\n"
 	: "=&r" (retval)
 	: "r" (ptr), "r" (x)
 	: "memory", "p0"

arch/hexagon/include/asm/futex.h

@@ -16,7 +16,7 @@
 	    /* For example: %1 = %4 */ \
 	    insn \
 	"2: memw_locked(%3,p2) = %1;\n" \
-	"   if !p2 jump 1b;\n" \
+	"   if (!p2) jump 1b;\n" \
 	"   %1 = #0;\n" \
 	"3:\n" \
 	".section .fixup,\"ax\"\n" \
@@ -84,10 +84,10 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval,
 	"1: %1 = memw_locked(%3)\n"
 	"   {\n"
 	"      p2 = cmp.eq(%1,%4)\n"
-	"      if !p2.new jump:NT 3f\n"
+	"      if (!p2.new) jump:NT 3f\n"
 	"   }\n"
 	"2: memw_locked(%3,p2) = %5\n"
-	"   if !p2 jump 1b\n"
+	"   if (!p2) jump 1b\n"
 	"3:\n"
 	".section .fixup,\"ax\"\n"
 	"4: %0 = #%6\n"

arch/hexagon/include/asm/io.h

@@ -173,6 +173,7 @@ static inline void writel(u32 data, volatile void __iomem *addr)
 
 void __iomem *ioremap(unsigned long phys_addr, unsigned long size);
 #define ioremap_nocache ioremap
+#define ioremap_uc(X, Y) ioremap((X), (Y))
 
 
 #define __raw_writel writel

arch/hexagon/include/asm/spinlock.h

@@ -30,9 +30,9 @@ static inline void arch_read_lock(arch_rwlock_t *lock)
 	__asm__ __volatile__(
 		"1:	R6 = memw_locked(%0);\n"
 		"	{ P3 = cmp.ge(R6,#0); R6 = add(R6,#1);}\n"
-		"	{ if !P3 jump 1b; }\n"
+		"	{ if (!P3) jump 1b; }\n"
 		"	memw_locked(%0,P3) = R6;\n"
-		"	{ if !P3 jump 1b; }\n"
+		"	{ if (!P3) jump 1b; }\n"
 		:
 		: "r" (&lock->lock)
 		: "memory", "r6", "p3"
@@ -46,7 +46,7 @@ static inline void arch_read_unlock(arch_rwlock_t *lock)
 		"1:	R6 = memw_locked(%0);\n"
 		"	R6 = add(R6,#-1);\n"
 		"	memw_locked(%0,P3) = R6\n"
-		"	if !P3 jump 1b;\n"
+		"	if (!P3) jump 1b;\n"
 		:
 		: "r" (&lock->lock)
 		: "memory", "r6", "p3"
@@ -61,7 +61,7 @@ static inline int arch_read_trylock(arch_rwlock_t *lock)
 	__asm__ __volatile__(
 		"	R6 = memw_locked(%1);\n"
 		"	{ %0 = #0; P3 = cmp.ge(R6,#0); R6 = add(R6,#1);}\n"
-		"	{ if !P3 jump 1f; }\n"
+		"	{ if (!P3) jump 1f; }\n"
 		"	memw_locked(%1,P3) = R6;\n"
 		"	{ %0 = P3 }\n"
 		"1:\n"
@@ -78,9 +78,9 @@ static inline void arch_write_lock(arch_rwlock_t *lock)
 	__asm__ __volatile__(
 		"1:	R6 = memw_locked(%0)\n"
 		"	{ P3 = cmp.eq(R6,#0);  R6 = #-1;}\n"
-		"	{ if !P3 jump 1b; }\n"
+		"	{ if (!P3) jump 1b; }\n"
 		"	memw_locked(%0,P3) = R6;\n"
-		"	{ if !P3 jump 1b; }\n"
+		"	{ if (!P3) jump 1b; }\n"
 		:
 		: "r" (&lock->lock)
 		: "memory", "r6", "p3"
@@ -94,7 +94,7 @@ static inline int arch_write_trylock(arch_rwlock_t *lock)
 	__asm__ __volatile__(
 		"	R6 = memw_locked(%1)\n"
 		"	{ %0 = #0; P3 = cmp.eq(R6,#0);  R6 = #-1;}\n"
-		"	{ if !P3 jump 1f; }\n"
+		"	{ if (!P3) jump 1f; }\n"
 		"	memw_locked(%1,P3) = R6;\n"
 		"	%0 = P3;\n"
 		"1:\n"
@@ -117,9 +117,9 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 	__asm__ __volatile__(
 		"1:	R6 = memw_locked(%0);\n"
 		"	P3 = cmp.eq(R6,#0);\n"
-		"	{ if !P3 jump 1b; R6 = #1; }\n"
+		"	{ if (!P3) jump 1b; R6 = #1; }\n"
 		"	memw_locked(%0,P3) = R6;\n"
-		"	{ if !P3 jump 1b; }\n"
+		"	{ if (!P3) jump 1b; }\n"
 		:
 		: "r" (&lock->lock)
 		: "memory", "r6", "p3"
@@ -139,7 +139,7 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock)
 	__asm__ __volatile__(
 		"	R6 = memw_locked(%1);\n"
 		"	P3 = cmp.eq(R6,#0);\n"
-		"	{ if !P3 jump 1f; R6 = #1; %0 = #0; }\n"
+		"	{ if (!P3) jump 1f; R6 = #1; %0 = #0; }\n"
 		"	memw_locked(%1,P3) = R6;\n"
 		"	%0 = P3;\n"
 		"1:\n"

arch/hexagon/kernel/stacktrace.c

@@ -11,8 +11,6 @@
 #include <linux/thread_info.h>
 #include <linux/module.h>
 
-register unsigned long current_frame_pointer asm("r30");
-
 struct stackframe {
 	unsigned long fp;
 	unsigned long rets;
@@ -30,7 +28,7 @@ void save_stack_trace(struct stack_trace *trace)
 
 	low = (unsigned long)task_stack_page(current);
 	high = low + THREAD_SIZE;
-	fp = current_frame_pointer;
+	fp = (unsigned long)__builtin_frame_address(0);
 
 	while (fp >= low && fp <= (high - sizeof(*frame))) {
 		frame = (struct stackframe *)fp;

arch/hexagon/kernel/vm_entry.S

@@ -369,7 +369,7 @@ ret_from_fork:
 		R26.L = #LO(do_work_pending);
 		R0 = #VM_INT_DISABLE;
 	}
-	if P0 jump check_work_pending
+	if (P0) jump check_work_pending
 	{
 		R0 = R25;
 		callr R24

arch/ia64/mm/init.c

@@ -689,9 +689,7 @@ void arch_remove_memory(int nid, u64 start, u64 size,
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
-	struct zone *zone;
 
-	zone = page_zone(pfn_to_page(start_pfn));
-	__remove_pages(zone, start_pfn, nr_pages, altmap);
+	__remove_pages(start_pfn, nr_pages, altmap);
 }
 #endif

arch/powerpc/mm/mem.c

@@ -151,10 +151,9 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size,
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
-	struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap);
 	int ret;
 
-	__remove_pages(page_zone(page), start_pfn, nr_pages, altmap);
+	__remove_pages(start_pfn, nr_pages, altmap);
 
 	/* Remove htab bolted mappings for this section of memory */
 	start = (unsigned long)__va(start);

arch/s390/mm/init.c

@@ -292,10 +292,8 @@ void arch_remove_memory(int nid, u64 start, u64 size,
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
-	struct zone *zone;
 
-	zone = page_zone(pfn_to_page(start_pfn));
-	__remove_pages(zone, start_pfn, nr_pages, altmap);
+	__remove_pages(start_pfn, nr_pages, altmap);
 	vmem_remove_mapping(start, size);
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */

arch/sh/mm/init.c

@@ -434,9 +434,7 @@ void arch_remove_memory(int nid, u64 start, u64 size,
 {
 	unsigned long start_pfn = PFN_DOWN(start);
 	unsigned long nr_pages = size >> PAGE_SHIFT;
-	struct zone *zone;
 
-	zone = page_zone(pfn_to_page(start_pfn));
-	__remove_pages(zone, start_pfn, nr_pages, altmap);
+	__remove_pages(start_pfn, nr_pages, altmap);
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */

arch/x86/mm/init_32.c

@@ -865,10 +865,8 @@ void arch_remove_memory(int nid, u64 start, u64 size,
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
-	struct zone *zone;
 
-	zone = page_zone(pfn_to_page(start_pfn));
-	__remove_pages(zone, start_pfn, nr_pages, altmap);
+	__remove_pages(start_pfn, nr_pages, altmap);
 }
 #endif
 

arch/x86/mm/init_64.c

@@ -1212,10 +1212,8 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size,
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
-	struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap);
-	struct zone *zone = page_zone(page);
 
-	__remove_pages(zone, start_pfn, nr_pages, altmap);
+	__remove_pages(start_pfn, nr_pages, altmap);
 	kernel_physical_mapping_remove(start, start + size);
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */

fs/direct-io.c

@@ -39,6 +39,8 @@
 #include <linux/atomic.h>
 #include <linux/prefetch.h>
 
+#include "internal.h"
+
 /*
  * How many user pages to map in one call to get_user_pages().  This determines
  * the size of a structure in the slab cache

fs/namespace.c

@@ -1728,7 +1728,7 @@ static bool is_mnt_ns_file(struct dentry *dentry)
 	       dentry->d_fsdata == &mntns_operations;
 }
 
-struct mnt_namespace *to_mnt_ns(struct ns_common *ns)
+static struct mnt_namespace *to_mnt_ns(struct ns_common *ns)
 {
 	return container_of(ns, struct mnt_namespace, ns);
 }

fs/nsfs.c

@@ -3,6 +3,7 @@
 #include <linux/pseudo_fs.h>
 #include <linux/file.h>
 #include <linux/fs.h>
+#include <linux/proc_fs.h>
 #include <linux/proc_ns.h>
 #include <linux/magic.h>
 #include <linux/ktime.h>
@@ -11,6 +12,8 @@
 #include <linux/nsfs.h>
 #include <linux/uaccess.h>
 
+#include "internal.h"
+
 static struct vfsmount *nsfs_mnt;
 
 static long ns_ioctl(struct file *filp, unsigned int ioctl,

fs/ocfs2/dlmglue.c

@@ -3282,6 +3282,7 @@ static void ocfs2_dlm_init_debug(struct ocfs2_super *osb)
 
 	debugfs_create_u32("locking_filter", 0600, osb->osb_debug_root,
 			   &dlm_debug->d_filter_secs);
+	ocfs2_get_dlm_debug(dlm_debug);
 }
 
 static void ocfs2_dlm_shutdown_debug(struct ocfs2_super *osb)

fs/ocfs2/journal.c

@@ -1066,6 +1066,14 @@ int ocfs2_journal_load(struct ocfs2_journal *journal, int local, int replayed)
 
 	ocfs2_clear_journal_error(osb->sb, journal->j_journal, osb->slot_num);
 
+	if (replayed) {
+		jbd2_journal_lock_updates(journal->j_journal);
+		status = jbd2_journal_flush(journal->j_journal);
+		jbd2_journal_unlock_updates(journal->j_journal);
+		if (status < 0)
+			mlog_errno(status);
+	}
+
 	status = ocfs2_journal_toggle_dirty(osb, 1, replayed);
 	if (status < 0) {
 		mlog_errno(status);

fs/posix_acl.c

@@ -631,12 +631,15 @@ EXPORT_SYMBOL_GPL(posix_acl_create);
 
 /**
  * posix_acl_update_mode  -  update mode in set_acl
+ * @inode: target inode
+ * @mode_p: mode (pointer) for update
+ * @acl: acl pointer
  *
  * Update the file mode when setting an ACL: compute the new file permission
  * bits based on the ACL.  In addition, if the ACL is equivalent to the new
- * file mode, set *acl to NULL to indicate that no ACL should be set.
+ * file mode, set *@acl to NULL to indicate that no ACL should be set.
  *
- * As with chmod, clear the setgit bit if the caller is not in the owning group
+ * As with chmod, clear the setgid bit if the caller is not in the owning group
  * or capable of CAP_FSETID (see inode_change_ok).
  *
  * Called from set_acl inode operations.

include/linux/memory_hotplug.h

@@ -122,8 +122,8 @@ static inline bool movable_node_is_enabled(void)
 
 extern void arch_remove_memory(int nid, u64 start, u64 size,
 			       struct vmem_altmap *altmap);
-extern void __remove_pages(struct zone *zone, unsigned long start_pfn,
-			   unsigned long nr_pages, struct vmem_altmap *altmap);
+extern void __remove_pages(unsigned long start_pfn, unsigned long nr_pages,
+			   struct vmem_altmap *altmap);
 
 /* reasonably generic interface to expand the physical pages */
 extern int __add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
@@ -342,6 +342,9 @@ extern int add_memory(int nid, u64 start, u64 size);
 extern int add_memory_resource(int nid, struct resource *resource);
 extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
 		unsigned long nr_pages, struct vmem_altmap *altmap);
+extern void remove_pfn_range_from_zone(struct zone *zone,
+				       unsigned long start_pfn,
+				       unsigned long nr_pages);
 extern bool is_memblock_offlined(struct memory_block *mem);
 extern int sparse_add_section(int nid, unsigned long pfn,
 		unsigned long nr_pages, struct vmem_altmap *altmap);

include/uapi/linux/kcov.h

@@ -9,11 +9,11 @@
  * and the comment before kcov_remote_start() for usage details.
  */
 struct kcov_remote_arg {
-	unsigned int	trace_mode;	/* KCOV_TRACE_PC or KCOV_TRACE_CMP */
-	unsigned int	area_size;	/* Length of coverage buffer in words */
-	unsigned int	num_handles;	/* Size of handles array */
-	__u64		common_handle;
-	__u64		handles[0];
+	__u32		trace_mode;	/* KCOV_TRACE_PC or KCOV_TRACE_CMP */
+	__u32		area_size;	/* Length of coverage buffer in words */
+	__u32		num_handles;	/* Size of handles array */
+	__aligned_u64	common_handle;
+	__aligned_u64	handles[0];
 };
 
 #define KCOV_REMOTE_MAX_HANDLES		0x100

kernel/cred.c

@@ -223,7 +223,7 @@ struct cred *cred_alloc_blank(void)
 	new->magic = CRED_MAGIC;
 #endif
 
-	if (security_cred_alloc_blank(new, GFP_KERNEL) < 0)
+	if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
 
 	return new;
@@ -282,7 +282,7 @@ struct cred *prepare_creds(void)
 	new->security = NULL;
 #endif
 
-	if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
+	if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
 	validate_creds(new);
 	return new;
@@ -715,7 +715,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 #ifdef CONFIG_SECURITY
 	new->security = NULL;
 #endif
-	if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
+	if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
 
 	put_cred(old);

mm/gup_benchmark.c

@@ -26,6 +26,7 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
 	unsigned long i, nr_pages, addr, next;
 	int nr;
 	struct page **pages;
+	int ret = 0;
 
 	if (gup->size > ULONG_MAX)
 		return -EINVAL;
@@ -63,7 +64,9 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
 					    NULL);
 			break;
 		default:
-			return -1;
+			kvfree(pages);
+			ret = -EINVAL;
+			goto out;
 		}
 
 		if (nr <= 0)
@@ -85,7 +88,8 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
 	gup->put_delta_usec = ktime_us_delta(end_time, start_time);
 
 	kvfree(pages);
-	return 0;
+out:
+	return ret;
 }
 
 static long gup_benchmark_ioctl(struct file *filep, unsigned int cmd,

mm/hugetlb.c

@@ -27,6 +27,7 @@
 #include <linux/swapops.h>
 #include <linux/jhash.h>
 #include <linux/numa.h>
+#include <linux/llist.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
@@ -1136,7 +1137,7 @@ static inline void ClearPageHugeTemporary(struct page *page)
 	page[2].mapping = NULL;
 }
 
-void free_huge_page(struct page *page)
+static void __free_huge_page(struct page *page)
 {
 	/*
 	 * Can't pass hstate in here because it is called from the
@@ -1199,6 +1200,54 @@ void free_huge_page(struct page *page)
 	spin_unlock(&hugetlb_lock);
 }
 
+/*
+ * As free_huge_page() can be called from a non-task context, we have
+ * to defer the actual freeing in a workqueue to prevent potential
+ * hugetlb_lock deadlock.
+ *
+ * free_hpage_workfn() locklessly retrieves the linked list of pages to
+ * be freed and frees them one-by-one. As the page->mapping pointer is
+ * going to be cleared in __free_huge_page() anyway, it is reused as the
+ * llist_node structure of a lockless linked list of huge pages to be freed.
+ */
+static LLIST_HEAD(hpage_freelist);
+
+static void free_hpage_workfn(struct work_struct *work)
+{
+	struct llist_node *node;
+	struct page *page;
+
+	node = llist_del_all(&hpage_freelist);
+
+	while (node) {
+		page = container_of((struct address_space **)node,
+				     struct page, mapping);
+		node = node->next;
+		__free_huge_page(page);
+	}
+}
+static DECLARE_WORK(free_hpage_work, free_hpage_workfn);
+
+void free_huge_page(struct page *page)
+{
+	/*
+	 * Defer freeing if in non-task context to avoid hugetlb_lock deadlock.
+	 */
+	if (!in_task()) {
+		/*
+		 * Only call schedule_work() if hpage_freelist is previously
+		 * empty. Otherwise, schedule_work() had been called but the
+		 * workfn hasn't retrieved the list yet.
+		 */
+		if (llist_add((struct llist_node *)&page->mapping,
+			      &hpage_freelist))
+			schedule_work(&free_hpage_work);
+		return;
+	}
+
+	__free_huge_page(page);
+}
+
 static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 {
 	INIT_LIST_HEAD(&page->lru);

mm/memory_hotplug.c

@@ -483,7 +483,8 @@ static void update_pgdat_span(struct pglist_data *pgdat)
 	pgdat->node_spanned_pages = node_end_pfn - node_start_pfn;
 }
 
-static void __remove_zone(struct zone *zone, unsigned long start_pfn,
+void __ref remove_pfn_range_from_zone(struct zone *zone,
+				      unsigned long start_pfn,
 				      unsigned long nr_pages)
 {
 	struct pglist_data *pgdat = zone->zone_pgdat;
@@ -499,14 +500,18 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn,
 		return;
 #endif
 
+	clear_zone_contiguous(zone);
+
 	pgdat_resize_lock(zone->zone_pgdat, &flags);
 	shrink_zone_span(zone, start_pfn, start_pfn + nr_pages);
 	update_pgdat_span(pgdat);
 	pgdat_resize_unlock(zone->zone_pgdat, &flags);
+
+	set_zone_contiguous(zone);
 }
 
-static void __remove_section(struct zone *zone, unsigned long pfn,
-		unsigned long nr_pages, unsigned long map_offset,
+static void __remove_section(unsigned long pfn, unsigned long nr_pages,
+			     unsigned long map_offset,
 			     struct vmem_altmap *altmap)
 {
 	struct mem_section *ms = __nr_to_section(pfn_to_section_nr(pfn));
@@ -514,13 +519,11 @@ static void __remove_section(struct zone *zone, unsigned long pfn,
 	if (WARN_ON_ONCE(!valid_section(ms)))
 		return;
 
-	__remove_zone(zone, pfn, nr_pages);
 	sparse_remove_section(ms, pfn, nr_pages, map_offset, altmap);
 }
 
 /**
- * __remove_pages() - remove sections of pages from a zone
- * @zone: zone from which pages need to be removed
+ * __remove_pages() - remove sections of pages
  * @pfn: starting pageframe (must be aligned to start of a section)
  * @nr_pages: number of pages to remove (must be multiple of section size)
  * @altmap: alternative device page map or %NULL if default memmap is used
@@ -530,16 +533,14 @@ static void __remove_section(struct zone *zone, unsigned long pfn,
  * sure that pages are marked reserved and zones are adjust properly by
  * calling offline_pages().
  */
-void __remove_pages(struct zone *zone, unsigned long pfn,
-		    unsigned long nr_pages, struct vmem_altmap *altmap)
+void __remove_pages(unsigned long pfn, unsigned long nr_pages,
+		    struct vmem_altmap *altmap)
 {
 	unsigned long map_offset = 0;
 	unsigned long nr, start_sec, end_sec;
 
 	map_offset = vmem_altmap_offset(altmap);
 
-	clear_zone_contiguous(zone);
-
 	if (check_pfn_span(pfn, nr_pages, "remove"))
 		return;
 
@@ -551,13 +552,11 @@ void __remove_pages(struct zone *zone, unsigned long pfn,
 		cond_resched();
 		pfns = min(nr_pages, PAGES_PER_SECTION
 				- (pfn & ~PAGE_SECTION_MASK));
-		__remove_section(zone, pfn, pfns, map_offset, altmap);
+		__remove_section(pfn, pfns, map_offset, altmap);
 		pfn += pfns;
 		nr_pages -= pfns;
 		map_offset = 0;
 	}
-
-	set_zone_contiguous(zone);
 }
 
 int set_online_page_callback(online_page_callback_t callback)
@@ -869,6 +868,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
 		 (unsigned long long) pfn << PAGE_SHIFT,
 		 (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1);
 	memory_notify(MEM_CANCEL_ONLINE, &arg);
+	remove_pfn_range_from_zone(zone, pfn, nr_pages);
 	mem_hotplug_done();
 	return ret;
 }
@@ -1628,6 +1628,7 @@ static int __ref __offline_pages(unsigned long start_pfn,
 	writeback_set_ratelimit();
 
 	memory_notify(MEM_OFFLINE, &arg);
+	remove_pfn_range_from_zone(zone, start_pfn, nr_pages);
 	mem_hotplug_done();
 	return 0;
 

mm/memremap.c

@@ -120,7 +120,7 @@ void memunmap_pages(struct dev_pagemap *pgmap)
 
 	mem_hotplug_begin();
 	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
-		__remove_pages(page_zone(first_page), PHYS_PFN(res->start),
+		__remove_pages(PHYS_PFN(res->start),
 			       PHYS_PFN(resource_size(res)), NULL);
 	} else {
 		arch_remove_memory(nid, res->start, resource_size(res),

mm/migrate.c

@@ -1512,9 +1512,11 @@ static int do_move_pages_to_node(struct mm_struct *mm,
 /*
  * Resolves the given address to a struct page, isolates it from the LRU and
  * puts it to the given pagelist.
- * Returns -errno if the page cannot be found/isolated or 0 when it has been
- * queued or the page doesn't need to be migrated because it is already on
- * the target node
+ * Returns:
+ *     errno - if the page cannot be found/isolated
+ *     0 - when it doesn't have to be migrated because it is already on the
+ *         target node
+ *     1 - when it has been queued
  */
 static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
 		int node, struct list_head *pagelist, bool migrate_all)
@@ -1553,7 +1555,7 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
 	if (PageHuge(page)) {
 		if (PageHead(page)) {
 			isolate_huge_page(page, pagelist);
-			err = 0;
+			err = 1;
 		}
 	} else {
 		struct page *head;
@@ -1563,7 +1565,7 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
 		if (err)
 			goto out_putpage;
 
-		err = 0;
+		err = 1;
 		list_add_tail(&head->lru, pagelist);
 		mod_node_page_state(page_pgdat(head),
 			NR_ISOLATED_ANON + page_is_file_cache(head),
@@ -1640,8 +1642,17 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
 		 */
 		err = add_page_for_migration(mm, addr, current_node,
 				&pagelist, flags & MPOL_MF_MOVE_ALL);
-		if (!err)
+
+		if (!err) {
+			/* The page is already on the target node */
+			err = store_status(status, i, current_node, 1);
+			if (err)
+				goto out_flush;
 			continue;
+		} else if (err > 0) {
+			/* The page is successfully queued for migration */
+			continue;
+		}
 
 		err = store_status(status, i, err, 1);
 		if (err)

mm/oom_kill.c

@@ -890,7 +890,7 @@ static void __oom_kill_process(struct task_struct *victim, const char *message)
 		K(get_mm_counter(mm, MM_FILEPAGES)),
 		K(get_mm_counter(mm, MM_SHMEMPAGES)),
 		from_kuid(&init_user_ns, task_uid(victim)),
-		mm_pgtables_bytes(mm), victim->signal->oom_score_adj);
+		mm_pgtables_bytes(mm) >> 10, victim->signal->oom_score_adj);
 	task_unlock(victim);
 
 	/*

mm/zsmalloc.c

@@ -2069,6 +2069,11 @@ static int zs_page_migrate(struct address_space *mapping, struct page *newpage,
 		zs_pool_dec_isolated(pool);
 	}
 
+	if (page_zone(newpage) != page_zone(page)) {
+		dec_zone_page_state(page, NR_ZSPAGES);
+		inc_zone_page_state(newpage, NR_ZSPAGES);
+	}
+
 	reset_page(page);
 	put_page(page);
 	page = newpage;