Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "15 patches.

  Subsystems affected by this patch series: ipc, hexagon, mm (swap,
  slab-generic, kmemleak, hugetlb, kasan, damon, and highmem), and proc"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  proc/vmcore: fix clearing user buffer by properly using clear_user()
  kmap_local: don't assume kmap PTEs are linear arrays in memory
  mm/damon/dbgfs: fix missed use of damon_dbgfs_lock
  mm/damon/dbgfs: use '__GFP_NOWARN' for user-specified size buffer allocation
  kasan: test: silence intentional read overflow warnings
  hugetlb, userfaultfd: fix reservation restore on userfaultfd error
  hugetlb: fix hugetlb cgroup refcounting during mremap
  mm: kmemleak: slob: respect SLAB_NOLEAKTRACE flag
  hexagon: ignore vmlinux.lds
  hexagon: clean up timer-regs.h
  hexagon: export raw I/O routines for modules
  mm: emit the "free" trace report before freeing memory in kmem_cache_free()
  shm: extend forced shm destroy to support objects from several IPC nses
  ipc: WARN if trying to remove ipc object which is absent
  mm/swap.c:put_pages_list(): reinitialise the page list

arch/arm/Kconfig

@@ -1463,6 +1463,7 @@ config HIGHMEM
 	bool "High Memory Support"
 	depends on MMU
 	select KMAP_LOCAL
+	select KMAP_LOCAL_NON_LINEAR_PTE_ARRAY
 	help
 	  The address space of ARM processors is only 4 Gigabytes large
 	  and it has to accommodate user address space, kernel address

arch/hexagon/include/asm/timer-regs.h

-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Timer support for Hexagon
- *
- * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
- */
-
-#ifndef _ASM_TIMER_REGS_H
-#define _ASM_TIMER_REGS_H
-
-/*  This stuff should go into a platform specific file  */
-#define TCX0_CLK_RATE		19200
-#define TIMER_ENABLE		0
-#define TIMER_CLR_ON_MATCH	1
-
-/*
- * 8x50 HDD Specs 5-8.  Simulator co-sim not fixed until
- * release 1.1, and then it's "adjustable" and probably not defaulted.
- */
-#define RTOS_TIMER_INT		3
-#ifdef CONFIG_HEXAGON_COMET
-#define RTOS_TIMER_REGS_ADDR	0xAB000000UL
-#endif
-#define SLEEP_CLK_RATE		32000
-
-#endif

arch/hexagon/include/asm/timex.h

@@ -7,11 +7,10 @@
 #define _ASM_TIMEX_H
 
 #include <asm-generic/timex.h>
-#include <asm/timer-regs.h>
 #include <asm/hexagon_vm.h>
 
 /* Using TCX0 as our clock.  CLOCK_TICK_RATE scheduled to be removed. */
-#define CLOCK_TICK_RATE              TCX0_CLK_RATE
+#define CLOCK_TICK_RATE              19200
 
 #define ARCH_HAS_READ_CURRENT_TIMER
 

arch/hexagon/kernel/.gitignore

+vmlinux.lds

arch/hexagon/kernel/time.c

@@ -17,9 +17,10 @@
 #include <linux/of_irq.h>
 #include <linux/module.h>
 
-#include <asm/timer-regs.h>
 #include <asm/hexagon_vm.h>
 
+#define TIMER_ENABLE		BIT(0)
+
 /*
  * For the clocksource we need:
  *	pcycle frequency (600MHz)
@@ -33,6 +34,13 @@ cycles_t	pcycle_freq_mhz;
 cycles_t	thread_freq_mhz;
 cycles_t	sleep_clk_freq;
 
+/*
+ * 8x50 HDD Specs 5-8.  Simulator co-sim not fixed until
+ * release 1.1, and then it's "adjustable" and probably not defaulted.
+ */
+#define RTOS_TIMER_INT		3
+#define RTOS_TIMER_REGS_ADDR	0xAB000000UL
+
 static struct resource rtos_timer_resources[] = {
 	{
 		.start	= RTOS_TIMER_REGS_ADDR,
@@ -80,7 +88,7 @@ static int set_next_event(unsigned long delta, struct clock_event_device *evt)
 	iowrite32(0, &rtos_timer->clear);
 
 	iowrite32(delta, &rtos_timer->match);
-	iowrite32(1 << TIMER_ENABLE, &rtos_timer->enable);
+	iowrite32(TIMER_ENABLE, &rtos_timer->enable);
 	return 0;
 }
 

arch/hexagon/lib/io.c

@@ -27,6 +27,7 @@ void __raw_readsw(const void __iomem *addr, void *data, int len)
 		*dst++ = *src;
 
 }
+EXPORT_SYMBOL(__raw_readsw);
 
 /*
  * __raw_writesw - read words a short at a time
@@ -47,6 +48,7 @@ void __raw_writesw(void __iomem *addr, const void *data, int len)
 
 
 }
+EXPORT_SYMBOL(__raw_writesw);
 
 /*  Pretty sure len is pre-adjusted for the length of the access already */
 void __raw_readsl(const void __iomem *addr, void *data, int len)
@@ -62,6 +64,7 @@ void __raw_readsl(const void __iomem *addr, void *data, int len)
 
 
 }
+EXPORT_SYMBOL(__raw_readsl);
 
 void __raw_writesl(void __iomem *addr, const void *data, int len)
 {
@@ -76,3 +79,4 @@ void __raw_writesl(void __iomem *addr, const void *data, int len)
 
 
 }
+EXPORT_SYMBOL(__raw_writesl);

fs/proc/vmcore.c

@@ -154,9 +154,13 @@ ssize_t read_from_oldmem(char *buf, size_t count,
 			nr_bytes = count;
 
 		/* If pfn is not ram, return zeros for sparse dump files */
-		if (!pfn_is_ram(pfn))
-			memset(buf, 0, nr_bytes);
-		else {
+		if (!pfn_is_ram(pfn)) {
+			tmp = 0;
+			if (!userbuf)
+				memset(buf, 0, nr_bytes);
+			else if (clear_user(buf, nr_bytes))
+				tmp = -EFAULT;
+		} else {
 			if (encrypted)
 				tmp = copy_oldmem_page_encrypted(pfn, buf,
 								 nr_bytes,
@@ -165,12 +169,12 @@ ssize_t read_from_oldmem(char *buf, size_t count,
 			else
 				tmp = copy_oldmem_page(pfn, buf, nr_bytes,
 						       offset, userbuf);
-
-			if (tmp < 0) {
-				up_read(&vmcore_cb_rwsem);
-				return tmp;
-			}
 		}
+		if (tmp < 0) {
+			up_read(&vmcore_cb_rwsem);
+			return tmp;
+		}
+
 		*ppos += nr_bytes;
 		count -= nr_bytes;
 		buf += nr_bytes;

include/linux/hugetlb_cgroup.h

@@ -128,6 +128,13 @@ static inline void resv_map_dup_hugetlb_cgroup_uncharge_info(
 		css_get(resv_map->css);
 }
 
+static inline void resv_map_put_hugetlb_cgroup_uncharge_info(
+						struct resv_map *resv_map)
+{
+	if (resv_map->css)
+		css_put(resv_map->css);
+}
+
 extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
 					struct hugetlb_cgroup **ptr);
 extern int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages,
@@ -211,6 +218,11 @@ static inline void resv_map_dup_hugetlb_cgroup_uncharge_info(
 {
 }
 
+static inline void resv_map_put_hugetlb_cgroup_uncharge_info(
+						struct resv_map *resv_map)
+{
+}
+
 static inline int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
 					       struct hugetlb_cgroup **ptr)
 {

include/linux/ipc_namespace.h

@@ -131,6 +131,16 @@ static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns)
 	return ns;
 }
 
+static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns)
+{
+	if (ns) {
+		if (refcount_inc_not_zero(&ns->ns.count))
+			return ns;
+	}
+
+	return NULL;
+}
+
 extern void put_ipc_ns(struct ipc_namespace *ns);
 #else
 static inline struct ipc_namespace *copy_ipcs(unsigned long flags,
@@ -147,6 +157,11 @@ static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns)
 	return ns;
 }
 
+static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns)
+{
+	return ns;
+}
+
 static inline void put_ipc_ns(struct ipc_namespace *ns)
 {
 }

include/linux/sched/task.h

@@ -158,7 +158,7 @@ static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
  * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
  * subscriptions and synchronises with wait4().  Also used in procfs.  Also
  * pins the final release of task.io_context.  Also protects ->cpuset and
- * ->cgroup.subsys[]. And ->vfork_done.
+ * ->cgroup.subsys[]. And ->vfork_done. And ->sysvshm.shm_clist.
  *
  * Nests both inside and outside of read_lock(&tasklist_lock).
  * It must not be nested with write_lock_irq(&tasklist_lock),

ipc/shm.c

@@ -62,9 +62,18 @@ struct shmid_kernel /* private to the kernel */
 	struct pid		*shm_lprid;
 	struct ucounts		*mlock_ucounts;
 
-	/* The task created the shm object.  NULL if the task is dead. */
+	/*
+	 * The task created the shm object, for
+	 * task_lock(shp->shm_creator)
+	 */
 	struct task_struct	*shm_creator;
-	struct list_head	shm_clist;	/* list by creator */
+
+	/*
+	 * List by creator. task_lock(->shm_creator) required for read/write.
+	 * If list_empty(), then the creator is dead already.
+	 */
+	struct list_head	shm_clist;
+	struct ipc_namespace	*ns;
 } __randomize_layout;
 
 /* shm_mode upper byte flags */
@@ -115,6 +124,7 @@ static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 	struct shmid_kernel *shp;
 
 	shp = container_of(ipcp, struct shmid_kernel, shm_perm);
+	WARN_ON(ns != shp->ns);
 
 	if (shp->shm_nattch) {
 		shp->shm_perm.mode |= SHM_DEST;
@@ -225,10 +235,43 @@ static void shm_rcu_free(struct rcu_head *head)
 	kfree(shp);
 }
 
-static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s)
+/*
+ * It has to be called with shp locked.
+ * It must be called before ipc_rmid()
+ */
+static inline void shm_clist_rm(struct shmid_kernel *shp)
 {
-	list_del(&s->shm_clist);
-	ipc_rmid(&shm_ids(ns), &s->shm_perm);
+	struct task_struct *creator;
+
+	/* ensure that shm_creator does not disappear */
+	rcu_read_lock();
+
+	/*
+	 * A concurrent exit_shm may do a list_del_init() as well.
+	 * Just do nothing if exit_shm already did the work
+	 */
+	if (!list_empty(&shp->shm_clist)) {
+		/*
+		 * shp->shm_creator is guaranteed to be valid *only*
+		 * if shp->shm_clist is not empty.
+		 */
+		creator = shp->shm_creator;
+
+		task_lock(creator);
+		/*
+		 * list_del_init() is a nop if the entry was already removed
+		 * from the list.
+		 */
+		list_del_init(&shp->shm_clist);
+		task_unlock(creator);
+	}
+	rcu_read_unlock();
+}
+
+static inline void shm_rmid(struct shmid_kernel *s)
+{
+	shm_clist_rm(s);
+	ipc_rmid(&shm_ids(s->ns), &s->shm_perm);
 }
 
 
@@ -283,7 +326,7 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
 	shm_file = shp->shm_file;
 	shp->shm_file = NULL;
 	ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	shm_rmid(ns, shp);
+	shm_rmid(shp);
 	shm_unlock(shp);
 	if (!is_file_hugepages(shm_file))
 		shmem_lock(shm_file, 0, shp->mlock_ucounts);
@@ -303,10 +346,10 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
  *
  * 2) sysctl kernel.shm_rmid_forced is set to 1.
  */
-static bool shm_may_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
+static bool shm_may_destroy(struct shmid_kernel *shp)
 {
 	return (shp->shm_nattch == 0) &&
-	       (ns->shm_rmid_forced ||
+	       (shp->ns->shm_rmid_forced ||
 		(shp->shm_perm.mode & SHM_DEST));
 }
 
@@ -337,7 +380,7 @@ static void shm_close(struct vm_area_struct *vma)
 	ipc_update_pid(&shp->shm_lprid, task_tgid(current));
 	shp->shm_dtim = ktime_get_real_seconds();
 	shp->shm_nattch--;
-	if (shm_may_destroy(ns, shp))
+	if (shm_may_destroy(shp))
 		shm_destroy(ns, shp);
 	else
 		shm_unlock(shp);
@@ -358,10 +401,10 @@ static int shm_try_destroy_orphaned(int id, void *p, void *data)
 	 *
 	 * As shp->* are changed under rwsem, it's safe to skip shp locking.
 	 */
-	if (shp->shm_creator != NULL)
+	if (!list_empty(&shp->shm_clist))
 		return 0;
 
-	if (shm_may_destroy(ns, shp)) {
+	if (shm_may_destroy(shp)) {
 		shm_lock_by_ptr(shp);
 		shm_destroy(ns, shp);
 	}
@@ -379,48 +422,97 @@ void shm_destroy_orphaned(struct ipc_namespace *ns)
 /* Locking assumes this will only be called with task == current */
 void exit_shm(struct task_struct *task)
 {
-	struct ipc_namespace *ns = task->nsproxy->ipc_ns;
-	struct shmid_kernel *shp, *n;
+	for (;;) {
+		struct shmid_kernel *shp;
+		struct ipc_namespace *ns;
 
-	if (list_empty(&task->sysvshm.shm_clist))
-		return;
+		task_lock(task);
+
+		if (list_empty(&task->sysvshm.shm_clist)) {
+			task_unlock(task);
+			break;
+		}
+
+		shp = list_first_entry(&task->sysvshm.shm_clist, struct shmid_kernel,
+				shm_clist);
 
-	/*
-	 * If kernel.shm_rmid_forced is not set then only keep track of
-	 * which shmids are orphaned, so that a later set of the sysctl
-	 * can clean them up.
-	 */
-	if (!ns->shm_rmid_forced) {
-		down_read(&shm_ids(ns).rwsem);
-		list_for_each_entry(shp, &task->sysvshm.shm_clist, shm_clist)
-			shp->shm_creator = NULL;
 		/*
-		 * Only under read lock but we are only called on current
-		 * so no entry on the list will be shared.
+		 * 1) Get pointer to the ipc namespace. It is worth to say
+		 * that this pointer is guaranteed to be valid because
+		 * shp lifetime is always shorter than namespace lifetime
+		 * in which shp lives.
+		 * We taken task_lock it means that shp won't be freed.
 		 */
-		list_del(&task->sysvshm.shm_clist);
-		up_read(&shm_ids(ns).rwsem);
-		return;
-	}
+		ns = shp->ns;
 
-	/*
-	 * Destroy all already created segments, that were not yet mapped,
-	 * and mark any mapped as orphan to cover the sysctl toggling.
-	 * Destroy is skipped if shm_may_destroy() returns false.
-	 */
-	down_write(&shm_ids(ns).rwsem);
-	list_for_each_entry_safe(shp, n, &task->sysvshm.shm_clist, shm_clist) {
-		shp->shm_creator = NULL;
+		/*
+		 * 2) If kernel.shm_rmid_forced is not set then only keep track of
+		 * which shmids are orphaned, so that a later set of the sysctl
+		 * can clean them up.
+		 */
+		if (!ns->shm_rmid_forced)
+			goto unlink_continue;
 
-		if (shm_may_destroy(ns, shp)) {
-			shm_lock_by_ptr(shp);
-			shm_destroy(ns, shp);
+		/*
+		 * 3) get a reference to the namespace.
+		 *    The refcount could be already 0. If it is 0, then
+		 *    the shm objects will be free by free_ipc_work().
+		 */
+		ns = get_ipc_ns_not_zero(ns);
+		if (!ns) {
+unlink_continue:
+			list_del_init(&shp->shm_clist);
+			task_unlock(task);
+			continue;
 		}
-	}
 
-	/* Remove the list head from any segments still attached. */
-	list_del(&task->sysvshm.shm_clist);
-	up_write(&shm_ids(ns).rwsem);
+		/*
+		 * 4) get a reference to shp.
+		 *   This cannot fail: shm_clist_rm() is called before
+		 *   ipc_rmid(), thus the refcount cannot be 0.
+		 */
+		WARN_ON(!ipc_rcu_getref(&shp->shm_perm));
+
+		/*
+		 * 5) unlink the shm segment from the list of segments
+		 *    created by current.
+		 *    This must be done last. After unlinking,
+		 *    only the refcounts obtained above prevent IPC_RMID
+		 *    from destroying the segment or the namespace.
+		 */
+		list_del_init(&shp->shm_clist);
+
+		task_unlock(task);
+
+		/*
+		 * 6) we have all references
+		 *    Thus lock & if needed destroy shp.
+		 */
+		down_write(&shm_ids(ns).rwsem);
+		shm_lock_by_ptr(shp);
+		/*
+		 * rcu_read_lock was implicitly taken in shm_lock_by_ptr, it's
+		 * safe to call ipc_rcu_putref here
+		 */
+		ipc_rcu_putref(&shp->shm_perm, shm_rcu_free);
+
+		if (ipc_valid_object(&shp->shm_perm)) {
+			if (shm_may_destroy(shp))
+				shm_destroy(ns, shp);
+			else
+				shm_unlock(shp);
+		} else {
+			/*
+			 * Someone else deleted the shp from namespace
+			 * idr/kht while we have waited.
+			 * Just unlock and continue.
+			 */
+			shm_unlock(shp);
+		}
+
+		up_write(&shm_ids(ns).rwsem);
+		put_ipc_ns(ns); /* paired with get_ipc_ns_not_zero */
+	}
 }
 
 static vm_fault_t shm_fault(struct vm_fault *vmf)
@@ -676,7 +768,11 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 	if (error < 0)
 		goto no_id;
 
+	shp->ns = ns;
+
+	task_lock(current);
 	list_add(&shp->shm_clist, &current->sysvshm.shm_clist);
+	task_unlock(current);
 
 	/*
 	 * shmid gets reported as "inode#" in /proc/pid/maps.
@@ -1567,7 +1663,8 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg,
 	down_write(&shm_ids(ns).rwsem);
 	shp = shm_lock(ns, shmid);
 	shp->shm_nattch--;
-	if (shm_may_destroy(ns, shp))
+
+	if (shm_may_destroy(shp))
 		shm_destroy(ns, shp);
 	else
 		shm_unlock(shp);

ipc/util.c

@@ -447,8 +447,8 @@ static int ipcget_public(struct ipc_namespace *ns, struct ipc_ids *ids,
 static void ipc_kht_remove(struct ipc_ids *ids, struct kern_ipc_perm *ipcp)
 {
 	if (ipcp->key != IPC_PRIVATE)
-		rhashtable_remove_fast(&ids->key_ht, &ipcp->khtnode,
-				       ipc_kht_params);
+		WARN_ON_ONCE(rhashtable_remove_fast(&ids->key_ht, &ipcp->khtnode,
+				       ipc_kht_params));
 }
 
 /**
@@ -498,7 +498,7 @@ void ipc_rmid(struct ipc_ids *ids, struct kern_ipc_perm *ipcp)
 {
 	int idx = ipcid_to_idx(ipcp->id);
 
-	idr_remove(&ids->ipcs_idr, idx);
+	WARN_ON_ONCE(idr_remove(&ids->ipcs_idr, idx) != ipcp);
 	ipc_kht_remove(ids, ipcp);
 	ids->in_use--;
 	ipcp->deleted = true;

lib/test_kasan.c

@@ -869,6 +869,7 @@ static void kasan_memchr(struct kunit *test)
 	ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 
+	OPTIMIZER_HIDE_VAR(size);
 	KUNIT_EXPECT_KASAN_FAIL(test,
 		kasan_ptr_result = memchr(ptr, '1', size + 1));
 
@@ -894,6 +895,7 @@ static void kasan_memcmp(struct kunit *test)
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 	memset(arr, 0, sizeof(arr));
 
+	OPTIMIZER_HIDE_VAR(size);
 	KUNIT_EXPECT_KASAN_FAIL(test,
 		kasan_int_result = memcmp(ptr, arr, size+1));
 	kfree(ptr);

mm/Kconfig

@@ -890,6 +890,9 @@ config MAPPING_DIRTY_HELPERS
 config KMAP_LOCAL
 	bool
 
+config KMAP_LOCAL_NON_LINEAR_PTE_ARRAY
+	bool
+
 # struct io_mapping based helper.  Selected by drivers that need them
 config IO_MAPPING
 	bool

mm/damon/dbgfs.c

@@ -32,7 +32,7 @@ static char *user_input_str(const char __user *buf, size_t count, loff_t *ppos)
 	if (*ppos)
 		return ERR_PTR(-EINVAL);
 
-	kbuf = kmalloc(count + 1, GFP_KERNEL);
+	kbuf = kmalloc(count + 1, GFP_KERNEL | __GFP_NOWARN);
 	if (!kbuf)
 		return ERR_PTR(-ENOMEM);
 
@@ -133,7 +133,7 @@ static ssize_t dbgfs_schemes_read(struct file *file, char __user *buf,
 	char *kbuf;
 	ssize_t len;
 
-	kbuf = kmalloc(count, GFP_KERNEL);
+	kbuf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN);
 	if (!kbuf)
 		return -ENOMEM;
 
@@ -452,7 +452,7 @@ static ssize_t dbgfs_init_regions_read(struct file *file, char __user *buf,
 	char *kbuf;
 	ssize_t len;
 
-	kbuf = kmalloc(count, GFP_KERNEL);
+	kbuf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN);
 	if (!kbuf)
 		return -ENOMEM;
 
@@ -578,7 +578,7 @@ static ssize_t dbgfs_kdamond_pid_read(struct file *file,
 	char *kbuf;
 	ssize_t len;
 
-	kbuf = kmalloc(count, GFP_KERNEL);
+	kbuf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN);
 	if (!kbuf)
 		return -ENOMEM;
 
@@ -877,12 +877,14 @@ static ssize_t dbgfs_monitor_on_write(struct file *file,
 		return -EINVAL;
 	}
 
+	mutex_lock(&damon_dbgfs_lock);
 	if (!strncmp(kbuf, "on", count)) {
 		int i;
 
 		for (i = 0; i < dbgfs_nr_ctxs; i++) {
 			if (damon_targets_empty(dbgfs_ctxs[i])) {
 				kfree(kbuf);
+				mutex_unlock(&damon_dbgfs_lock);
 				return -EINVAL;
 			}
 		}
@@ -892,6 +894,7 @@ static ssize_t dbgfs_monitor_on_write(struct file *file,
 	} else {
 		ret = -EINVAL;
 	}
+	mutex_unlock(&damon_dbgfs_lock);
 
 	if (!ret)
 		ret = count;
@@ -944,15 +947,16 @@ static int __init __damon_dbgfs_init(void)
 
 static int __init damon_dbgfs_init(void)
 {
-	int rc;
+	int rc = -ENOMEM;
 
+	mutex_lock(&damon_dbgfs_lock);
 	dbgfs_ctxs = kmalloc(sizeof(*dbgfs_ctxs), GFP_KERNEL);
 	if (!dbgfs_ctxs)
-		return -ENOMEM;
+		goto out;
 	dbgfs_ctxs[0] = dbgfs_new_ctx();
 	if (!dbgfs_ctxs[0]) {
 		kfree(dbgfs_ctxs);
-		return -ENOMEM;
+		goto out;
 	}
 	dbgfs_nr_ctxs = 1;
 
@@ -963,6 +967,8 @@ static int __init damon_dbgfs_init(void)
 		pr_err("%s: dbgfs init failed\n", __func__);
 	}
 
+out:
+	mutex_unlock(&damon_dbgfs_lock);
 	return rc;
 }
 

mm/highmem.c

@@ -503,16 +503,22 @@ static inline int kmap_local_calc_idx(int idx)
 
 static pte_t *__kmap_pte;
 
-static pte_t *kmap_get_pte(void)
+static pte_t *kmap_get_pte(unsigned long vaddr, int idx)
 {
+	if (IS_ENABLED(CONFIG_KMAP_LOCAL_NON_LINEAR_PTE_ARRAY))
+		/*
+		 * Set by the arch if __kmap_pte[-idx] does not produce
+		 * the correct entry.
+		 */
+		return virt_to_kpte(vaddr);
 	if (!__kmap_pte)
 		__kmap_pte = virt_to_kpte(__fix_to_virt(FIX_KMAP_BEGIN));
-	return __kmap_pte;
+	return &__kmap_pte[-idx];
 }
 
 void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot)
 {
-	pte_t pteval, *kmap_pte = kmap_get_pte();
+	pte_t pteval, *kmap_pte;
 	unsigned long vaddr;
 	int idx;
 
@@ -524,9 +530,10 @@ void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot)
 	preempt_disable();
 	idx = arch_kmap_local_map_idx(kmap_local_idx_push(), pfn);
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-	BUG_ON(!pte_none(*(kmap_pte - idx)));
+	kmap_pte = kmap_get_pte(vaddr, idx);
+	BUG_ON(!pte_none(*kmap_pte));
 	pteval = pfn_pte(pfn, prot);
-	arch_kmap_local_set_pte(&init_mm, vaddr, kmap_pte - idx, pteval);
+	arch_kmap_local_set_pte(&init_mm, vaddr, kmap_pte, pteval);
 	arch_kmap_local_post_map(vaddr, pteval);
 	current->kmap_ctrl.pteval[kmap_local_idx()] = pteval;
 	preempt_enable();
@@ -559,7 +566,7 @@ EXPORT_SYMBOL(__kmap_local_page_prot);
 void kunmap_local_indexed(void *vaddr)
 {
 	unsigned long addr = (unsigned long) vaddr & PAGE_MASK;
-	pte_t *kmap_pte = kmap_get_pte();
+	pte_t *kmap_pte;
 	int idx;
 
 	if (addr < __fix_to_virt(FIX_KMAP_END) ||
@@ -584,8 +591,9 @@ void kunmap_local_indexed(void *vaddr)
 	idx = arch_kmap_local_unmap_idx(kmap_local_idx(), addr);
 	WARN_ON_ONCE(addr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
 
+	kmap_pte = kmap_get_pte(addr, idx);
 	arch_kmap_local_pre_unmap(addr);
-	pte_clear(&init_mm, addr, kmap_pte - idx);
+	pte_clear(&init_mm, addr, kmap_pte);
 	arch_kmap_local_post_unmap(addr);
 	current->kmap_ctrl.pteval[kmap_local_idx()] = __pte(0);
 	kmap_local_idx_pop();
@@ -607,7 +615,7 @@ EXPORT_SYMBOL(kunmap_local_indexed);
 void __kmap_local_sched_out(void)
 {
 	struct task_struct *tsk = current;
-	pte_t *kmap_pte = kmap_get_pte();
+	pte_t *kmap_pte;
 	int i;
 
 	/* Clear kmaps */
@@ -634,8 +642,9 @@ void __kmap_local_sched_out(void)
 		idx = arch_kmap_local_map_idx(i, pte_pfn(pteval));
 
 		addr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+		kmap_pte = kmap_get_pte(addr, idx);
 		arch_kmap_local_pre_unmap(addr);
-		pte_clear(&init_mm, addr, kmap_pte - idx);
+		pte_clear(&init_mm, addr, kmap_pte);
 		arch_kmap_local_post_unmap(addr);
 	}
 }
@@ -643,7 +652,7 @@ void __kmap_local_sched_out(void)
 void __kmap_local_sched_in(void)
 {
 	struct task_struct *tsk = current;
-	pte_t *kmap_pte = kmap_get_pte();
+	pte_t *kmap_pte;
 	int i;
 
 	/* Restore kmaps */
@@ -663,7 +672,8 @@ void __kmap_local_sched_in(void)
 		/* See comment in __kmap_local_sched_out() */
 		idx = arch_kmap_local_map_idx(i, pte_pfn(pteval));
 		addr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-		set_pte_at(&init_mm, addr, kmap_pte - idx, pteval);
+		kmap_pte = kmap_get_pte(addr, idx);
+		set_pte_at(&init_mm, addr, kmap_pte, pteval);
 		arch_kmap_local_post_map(addr, pteval);
 	}
 }

mm/hugetlb.c

@@ -1037,8 +1037,10 @@ void clear_vma_resv_huge_pages(struct vm_area_struct *vma)
 	 */
 	struct resv_map *reservations = vma_resv_map(vma);
 
-	if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER))
+	if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
+		resv_map_put_hugetlb_cgroup_uncharge_info(reservations);
 		kref_put(&reservations->refs, resv_map_release);
+	}
 
 	reset_vma_resv_huge_pages(vma);
 }
@@ -5734,13 +5736,14 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 	int ret = -ENOMEM;
 	struct page *page;
 	int writable;
-	bool new_pagecache_page = false;
+	bool page_in_pagecache = false;
 
 	if (is_continue) {
 		ret = -EFAULT;
 		page = find_lock_page(mapping, idx);
 		if (!page)
 			goto out;
+		page_in_pagecache = true;
 	} else if (!*pagep) {
 		/* If a page already exists, then it's UFFDIO_COPY for
 		 * a non-missing case. Return -EEXIST.
@@ -5828,7 +5831,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 		ret = huge_add_to_page_cache(page, mapping, idx);
 		if (ret)
 			goto out_release_nounlock;
-		new_pagecache_page = true;
+		page_in_pagecache = true;
 	}
 
 	ptl = huge_pte_lockptr(h, dst_mm, dst_pte);
@@ -5892,7 +5895,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 	if (vm_shared || is_continue)
 		unlock_page(page);
 out_release_nounlock:
-	if (!new_pagecache_page)
+	if (!page_in_pagecache)
 		restore_reserve_on_error(h, dst_vma, dst_addr, page);
 	put_page(page);
 	goto out;

mm/slab.c

@@ -3733,14 +3733,13 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp)
 	if (!cachep)
 		return;
 
+	trace_kmem_cache_free(_RET_IP_, objp, cachep->name);
 	local_irq_save(flags);
 	debug_check_no_locks_freed(objp, cachep->object_size);
 	if (!(cachep->flags & SLAB_DEBUG_OBJECTS))
 		debug_check_no_obj_freed(objp, cachep->object_size);
 	__cache_free(cachep, objp, _RET_IP_);
 	local_irq_restore(flags);
-
-	trace_kmem_cache_free(_RET_IP_, objp, cachep->name);
 }
 EXPORT_SYMBOL(kmem_cache_free);
 

mm/slab.h

@@ -147,7 +147,7 @@ static inline slab_flags_t kmem_cache_flags(unsigned int object_size,
 #define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \
 			  SLAB_TEMPORARY | SLAB_ACCOUNT)
 #else
-#define SLAB_CACHE_FLAGS (0)
+#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE)
 #endif
 
 /* Common flags available with current configuration */

mm/slob.c

@@ -666,6 +666,7 @@ static void kmem_rcu_free(struct rcu_head *head)
 void kmem_cache_free(struct kmem_cache *c, void *b)
 {
 	kmemleak_free_recursive(b, c->flags);
+	trace_kmem_cache_free(_RET_IP_, b, c->name);
 	if (unlikely(c->flags & SLAB_TYPESAFE_BY_RCU)) {
 		struct slob_rcu *slob_rcu;
 		slob_rcu = b + (c->size - sizeof(struct slob_rcu));
@@ -674,8 +675,6 @@ void kmem_cache_free(struct kmem_cache *c, void *b)
 	} else {
 		__kmem_cache_free(b, c->size);
 	}
-
-	trace_kmem_cache_free(_RET_IP_, b, c->name);
 }
 EXPORT_SYMBOL(kmem_cache_free);
 

mm/slub.c

@@ -3526,8 +3526,8 @@ void kmem_cache_free(struct kmem_cache *s, void *x)
 	s = cache_from_obj(s, x);
 	if (!s)
 		return;
-	slab_free(s, virt_to_head_page(x), x, NULL, 1, _RET_IP_);
 	trace_kmem_cache_free(_RET_IP_, x, s->name);
+	slab_free(s, virt_to_head_page(x), x, NULL, 1, _RET_IP_);
 }
 EXPORT_SYMBOL(kmem_cache_free);
 

mm/swap.c

@@ -156,6 +156,7 @@ void put_pages_list(struct list_head *pages)
 	}
 
 	free_unref_page_list(pages);
+	INIT_LIST_HEAD(pages);
 }
 EXPORT_SYMBOL(put_pages_list);