Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "15 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  ocfs2/dlm: fix deadlock when dispatch assert master
  membarrier: clean up selftest
  vmscan: fix sane_reclaim helper for legacy memcg
  lib/iommu-common.c: do not try to deref a null iommu->lazy_flush() pointer when n < pool->hint
  x86, efi, kasan: #undef memset/memcpy/memmove per arch
  mm: migrate: hugetlb: putback destination hugepage to active list
  mm, dax: VMA with vm_ops->pfn_mkwrite wants to be write-notified
  userfaultfd: register uapi generic syscall (aarch64)
  userfaultfd: selftest: don't error out if pthread_mutex_t isn't identical
  userfaultfd: selftest: return an error if BOUNCE_VERIFY fails
  userfaultfd: selftest: avoid my_bcmp false positives with powerpc
  userfaultfd: selftest: only warn if __NR_userfaultfd is undefined
  userfaultfd: selftest: headers fixup
  userfaultfd: selftests: vm: pick up sanitized kernel headers
  userfaultfd: revert "userfaultfd: waitqueue: add nr wake parameter to __wake_up_locked_key"

arch/x86/include/asm/efi.h

@@ -86,6 +86,16 @@ extern u64 asmlinkage efi_call(void *fp, ...);
 extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size,
 					u32 type, u64 attribute);
 
+/*
+ * CONFIG_KASAN may redefine memset to __memset.  __memset function is present
+ * only in kernel binary.  Since the EFI stub linked into a separate binary it
+ * doesn't have __memset().  So we should use standard memset from
+ * arch/x86/boot/compressed/string.c.  The same applies to memcpy and memmove.
+ */
+#undef memcpy
+#undef memset
+#undef memmove
+
 #endif /* CONFIG_X86_32 */
 
 extern struct efi_scratch efi_scratch;

drivers/firmware/efi/libstub/efistub.h

@@ -5,10 +5,6 @@
 /* error code which can't be mistaken for valid address */
 #define EFI_ERROR	(~0UL)
 
-#undef memcpy
-#undef memset
-#undef memmove
-
 void efi_char16_printk(efi_system_table_t *, efi_char16_t *);
 
 efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, void *__image,

fs/ocfs2/dlm/dlmmaster.c

@@ -1439,6 +1439,7 @@ int dlm_master_request_handler(struct o2net_msg *msg, u32 len, void *data,
 	int found, ret;
 	int set_maybe;
 	int dispatch_assert = 0;
+	int dispatched = 0;
 
 	if (!dlm_grab(dlm))
 		return DLM_MASTER_RESP_NO;
@@ -1658,15 +1659,18 @@ send_response:
 			mlog(ML_ERROR, "failed to dispatch assert master work\n");
 			response = DLM_MASTER_RESP_ERROR;
 			dlm_lockres_put(res);
-		} else
+		} else {
+			dispatched = 1;
 			__dlm_lockres_grab_inflight_worker(dlm, res);
+		}
 		spin_unlock(&res->spinlock);
 	} else {
 		if (res)
 			dlm_lockres_put(res);
 	}
 
-	dlm_put(dlm);
+	if (!dispatched)
+		dlm_put(dlm);
 	return response;
 }
 
@@ -2090,7 +2094,6 @@ int dlm_dispatch_assert_master(struct dlm_ctxt *dlm,
 
 
 	/* queue up work for dlm_assert_master_worker */
-	dlm_grab(dlm);  /* get an extra ref for the work item */
 	dlm_init_work_item(dlm, item, dlm_assert_master_worker, NULL);
 	item->u.am.lockres = res; /* already have a ref */
 	/* can optionally ignore node numbers higher than this node */

fs/ocfs2/dlm/dlmrecovery.c

@@ -1694,6 +1694,7 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
 	unsigned int hash;
 	int master = DLM_LOCK_RES_OWNER_UNKNOWN;
 	u32 flags = DLM_ASSERT_MASTER_REQUERY;
+	int dispatched = 0;
 
 	if (!dlm_grab(dlm)) {
 		/* since the domain has gone away on this
@@ -1719,8 +1720,10 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
 				dlm_put(dlm);
 				/* sender will take care of this and retry */
 				return ret;
-			} else
+			} else {
+				dispatched = 1;
 				__dlm_lockres_grab_inflight_worker(dlm, res);
+			}
 			spin_unlock(&res->spinlock);
 		} else {
 			/* put.. incase we are not the master */
@@ -1730,7 +1733,8 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
 	}
 	spin_unlock(&dlm->spinlock);
 
-	dlm_put(dlm);
+	if (!dispatched)
+		dlm_put(dlm);
 	return master;
 }
 

fs/userfaultfd.c

@@ -467,8 +467,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 	 * the fault_*wqh.
 	 */
 	spin_lock(&ctx->fault_pending_wqh.lock);
-	__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, 0, &range);
-	__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, 0, &range);
+	__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, &range);
+	__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, &range);
 	spin_unlock(&ctx->fault_pending_wqh.lock);
 
 	wake_up_poll(&ctx->fd_wqh, POLLHUP);
@@ -650,10 +650,10 @@ static void __wake_userfault(struct userfaultfd_ctx *ctx,
 	spin_lock(&ctx->fault_pending_wqh.lock);
 	/* wake all in the range and autoremove */
 	if (waitqueue_active(&ctx->fault_pending_wqh))
-		__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, 0,
+		__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL,
 				     range);
 	if (waitqueue_active(&ctx->fault_wqh))
-		__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, 0, range);
+		__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, range);
 	spin_unlock(&ctx->fault_pending_wqh.lock);
 }
 

include/linux/wait.h

@@ -147,8 +147,7 @@ __remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old)
 
 typedef int wait_bit_action_f(struct wait_bit_key *);
 void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
-void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, int nr,
-			  void *key);
+void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
 void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
 void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr);
 void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr);
@@ -180,7 +179,7 @@ wait_queue_head_t *bit_waitqueue(void *, int);
 #define wake_up_poll(x, m)						\
 	__wake_up(x, TASK_NORMAL, 1, (void *) (m))
 #define wake_up_locked_poll(x, m)					\
-	__wake_up_locked_key((x), TASK_NORMAL, 1, (void *) (m))
+	__wake_up_locked_key((x), TASK_NORMAL, (void *) (m))
 #define wake_up_interruptible_poll(x, m)				\
 	__wake_up(x, TASK_INTERRUPTIBLE, 1, (void *) (m))
 #define wake_up_interruptible_sync_poll(x, m)				\

include/uapi/asm-generic/unistd.h

@@ -709,17 +709,19 @@ __SYSCALL(__NR_memfd_create, sys_memfd_create)
 __SYSCALL(__NR_bpf, sys_bpf)
 #define __NR_execveat 281
 __SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat)
-#define __NR_membarrier 282
+#define __NR_userfaultfd 282
+__SYSCALL(__NR_userfaultfd, sys_userfaultfd)
+#define __NR_membarrier 283
 __SYSCALL(__NR_membarrier, sys_membarrier)
 
 #undef __NR_syscalls
-#define __NR_syscalls 283
+#define __NR_syscalls 284
 
 /*
  * All syscalls below here should go away really,
  * these are provided for both review and as a porting
  * help for the C library version.
-*
+ *
  * Last chance: are any of these important enough to
  * enable by default?
  */

kernel/sched/wait.c

@@ -106,10 +106,9 @@ void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr)
 }
 EXPORT_SYMBOL_GPL(__wake_up_locked);
 
-void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, int nr,
-			  void *key)
+void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
 {
-	__wake_up_common(q, mode, nr, 0, key);
+	__wake_up_common(q, mode, 1, 0, key);
 }
 EXPORT_SYMBOL_GPL(__wake_up_locked_key);
 
@@ -284,7 +283,7 @@ void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
 	if (!list_empty(&wait->task_list))
 		list_del_init(&wait->task_list);
 	else if (waitqueue_active(q))
-		__wake_up_locked_key(q, mode, 1, key);
+		__wake_up_locked_key(q, mode, key);
 	spin_unlock_irqrestore(&q->lock, flags);
 }
 EXPORT_SYMBOL(abort_exclusive_wait);

lib/iommu-common.c

@@ -21,8 +21,7 @@ static	DEFINE_PER_CPU(unsigned int, iommu_hash_common);
 
 static inline bool need_flush(struct iommu_map_table *iommu)
 {
-	return (iommu->lazy_flush != NULL &&
-		(iommu->flags & IOMMU_NEED_FLUSH) != 0);
+	return ((iommu->flags & IOMMU_NEED_FLUSH) != 0);
 }
 
 static inline void set_flush(struct iommu_map_table *iommu)
@@ -211,7 +210,8 @@ unsigned long iommu_tbl_range_alloc(struct device *dev,
 			goto bail;
 		}
 	}
-	if (n < pool->hint || need_flush(iommu)) {
+	if (iommu->lazy_flush &&
+	    (n < pool->hint || need_flush(iommu))) {
 		clear_flush(iommu);
 		iommu->lazy_flush(iommu);
 	}

mm/migrate.c

@@ -1075,7 +1075,7 @@ out:
 	if (rc != MIGRATEPAGE_SUCCESS && put_new_page)
 		put_new_page(new_hpage, private);
 	else
-		put_page(new_hpage);
+		putback_active_hugepage(new_hpage);
 
 	if (result) {
 		if (rc)

mm/mmap.c

@@ -1490,13 +1490,14 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
 int vma_wants_writenotify(struct vm_area_struct *vma)
 {
 	vm_flags_t vm_flags = vma->vm_flags;
+	const struct vm_operations_struct *vm_ops = vma->vm_ops;
 
 	/* If it was private or non-writable, the write bit is already clear */
 	if ((vm_flags & (VM_WRITE|VM_SHARED)) != ((VM_WRITE|VM_SHARED)))
 		return 0;
 
 	/* The backer wishes to know when pages are first written to? */
-	if (vma->vm_ops && vma->vm_ops->page_mkwrite)
+	if (vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite))
 		return 1;
 
 	/* The open routine did something to the protections that pgprot_modify

mm/vmscan.c

@@ -175,7 +175,7 @@ static bool sane_reclaim(struct scan_control *sc)
 	if (!memcg)
 		return true;
 #ifdef CONFIG_CGROUP_WRITEBACK
-	if (memcg->css.cgroup)
+	if (cgroup_on_dfl(memcg->css.cgroup))
 		return true;
 #endif
 	return false;

net/sunrpc/sched.c

@@ -297,7 +297,7 @@ static int rpc_complete_task(struct rpc_task *task)
 	clear_bit(RPC_TASK_ACTIVE, &task->tk_runstate);
 	ret = atomic_dec_and_test(&task->tk_count);
 	if (waitqueue_active(wq))
-		__wake_up_locked_key(wq, TASK_NORMAL, 1, &k);
+		__wake_up_locked_key(wq, TASK_NORMAL, &k);
 	spin_unlock_irqrestore(&wq->lock, flags);
 	return ret;
 }

tools/testing/selftests/membarrier/Makefile

@@ -1,11 +1,10 @@
 CFLAGS += -g -I../../../../usr/include/
 
-all:
-	$(CC) $(CFLAGS) membarrier_test.c -o membarrier_test
-
 TEST_PROGS := membarrier_test
 
+all: $(TEST_PROGS)
+
 include ../lib.mk
 
 clean:
-	$(RM) membarrier_test
+	$(RM) $(TEST_PROGS)

tools/testing/selftests/membarrier/membarrier_test.c

@@ -1,9 +1,6 @@
 #define _GNU_SOURCE
-#define __EXPORTED_HEADERS__
-
 #include <linux/membarrier.h>
-#include <asm-generic/unistd.h>
-#include <sys/syscall.h>
+#include <syscall.h>
 #include <stdio.h>
 #include <errno.h>
 #include <string.h>

tools/testing/selftests/vm/Makefile

@@ -1,6 +1,6 @@
 # Makefile for vm selftests
 
-CFLAGS = -Wall
+CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS)
 BINARIES = compaction_test
 BINARIES += hugepage-mmap
 BINARIES += hugepage-shm
@@ -12,8 +12,11 @@ BINARIES += userfaultfd
 all: $(BINARIES)
 %: %.c
 	$(CC) $(CFLAGS) -o $@ $^ -lrt
-userfaultfd: userfaultfd.c
-	$(CC) $(CFLAGS) -O2 -o $@ $^ -lpthread
+userfaultfd: userfaultfd.c ../../../../usr/include/linux/kernel.h
+	$(CC) $(CFLAGS) -O2 -o $@ $< -lpthread
+
+../../../../usr/include/linux/kernel.h:
+	make -C ../../../.. headers_install
 
 TEST_PROGS := run_vmtests
 TEST_FILES := $(BINARIES)

tools/testing/selftests/vm/userfaultfd.c

@@ -64,19 +64,9 @@
 #include <sys/syscall.h>
 #include <sys/ioctl.h>
 #include <pthread.h>
-#include "../../../../include/uapi/linux/userfaultfd.h"
+#include <linux/userfaultfd.h>
 
-#ifdef __x86_64__
-#define __NR_userfaultfd 323
-#elif defined(__i386__)
-#define __NR_userfaultfd 374
-#elif defined(__powewrpc__)
-#define __NR_userfaultfd 364
-#elif defined(__s390__)
-#define __NR_userfaultfd 355
-#else
-#error "missing __NR_userfaultfd definition"
-#endif
+#ifdef __NR_userfaultfd
 
 static unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size;
 
@@ -432,7 +422,7 @@ static int userfaultfd_stress(void)
 	struct uffdio_register uffdio_register;
 	struct uffdio_api uffdio_api;
 	unsigned long cpu;
-	int uffd_flags;
+	int uffd_flags, err;
 	unsigned long userfaults[nr_cpus];
 
 	if (posix_memalign(&area, page_size, nr_pages * page_size)) {
@@ -475,6 +465,14 @@ static int userfaultfd_stress(void)
 		*area_mutex(area_src, nr) = (pthread_mutex_t)
 			PTHREAD_MUTEX_INITIALIZER;
 		count_verify[nr] = *area_count(area_src, nr) = 1;
+		/*
+		 * In the transition between 255 to 256, powerpc will
+		 * read out of order in my_bcmp and see both bytes as
+		 * zero, so leave a placeholder below always non-zero
+		 * after the count, to avoid my_bcmp to trigger false
+		 * positives.
+		 */
+		*(area_count(area_src, nr) + 1) = 1;
 	}
 
 	pipefd = malloc(sizeof(int) * nr_cpus * 2);
@@ -501,6 +499,7 @@ static int userfaultfd_stress(void)
 	pthread_attr_init(&attr);
 	pthread_attr_setstacksize(&attr, 16*1024*1024);
 
+	err = 0;
 	while (bounces--) {
 		unsigned long expected_ioctls;
 
@@ -581,20 +580,13 @@ static int userfaultfd_stress(void)
 		/* verification */
 		if (bounces & BOUNCE_VERIFY) {
 			for (nr = 0; nr < nr_pages; nr++) {
-				if (my_bcmp(area_dst,
-					    area_dst + nr * page_size,
-					    sizeof(pthread_mutex_t))) {
-					fprintf(stderr,
-						"error mutex 2 %lu\n",
-						nr);
-					bounces = 0;
-				}
 				if (*area_count(area_dst, nr) != count_verify[nr]) {
 					fprintf(stderr,
 						"error area_count %Lu %Lu %lu\n",
 						*area_count(area_src, nr),
 						count_verify[nr],
 						nr);
+					err = 1;
 					bounces = 0;
 				}
 			}
@@ -611,7 +603,7 @@ static int userfaultfd_stress(void)
 		printf("\n");
 	}
 
-	return 0;
+	return err;
 }
 
 int main(int argc, char **argv)
@@ -620,8 +612,8 @@ int main(int argc, char **argv)
 		fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1);
 	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
 	page_size = sysconf(_SC_PAGE_SIZE);
-	if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) >
-	    page_size)
+	if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) * 2
+	    > page_size)
 		fprintf(stderr, "Impossible to run this test\n"), exit(2);
 	nr_pages_per_cpu = atol(argv[1]) * 1024*1024 / page_size /
 		nr_cpus;
@@ -639,3 +631,15 @@ int main(int argc, char **argv)
 	       nr_pages, nr_pages_per_cpu);
 	return userfaultfd_stress();
 }
+
+#else /* __NR_userfaultfd */
+
+#warning "missing __NR_userfaultfd definition"
+
+int main(void)
+{
+	printf("skip: Skipping userfaultfd test (missing __NR_userfaultfd)\n");
+	return 0;
+}
+
+#endif /* __NR_userfaultfd */