Merge branch 'akpm-current/current'

61 files changed, 1141 insertions, 314 deletions

diff --git a/Documentation/ABI/testing/sysfs-class-bdi b/Documentation/ABI/testing/sysfs-class-bdi
index d773d5697cf5..3187a18af6da 100644
--- a/Documentation/ABI/testing/sysfs-class-bdi
+++ b/Documentation/ABI/testing/sysfs-class-bdi
@@ -53,3 +53,11 @@ stable_pages_required (read-only)
 
 	If set, the backing device requires that all pages comprising a write
 	request must not be changed until writeout is complete.
+
+strictlimit (read-write)
+
+	Forces per-BDI checks for the share of given device in the write-back
+	cache even before the global background dirty limit is reached. This
+	is useful in situations where the global limit is much higher than
+	affordable for given relatively slow (or untrusted) device. Turning
+	strictlimit on has no visible effect if max_ratio is equal to 100%.
diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt
index 74cdeaed9f7a..f728e55602b2 100644
--- a/Documentation/cgroup-v2.txt
+++ b/Documentation/cgroup-v2.txt
@@ -48,6 +48,7 @@ v1 is available under Documentation/cgroup-v1/.
        5-2-1. Memory Interface Files
        5-2-2. Usage Guidelines
        5-2-3. Memory Ownership
+       5-2-4. OOM Killer
      5-3. IO
        5-3-1. IO Interface Files
        5-3-2. Writeback
@@ -1039,6 +1040,31 @@ PAGE_SIZE multiple when read back.
 	high limit is used and monitored properly, this limit's
 	utility is limited to providing the final safety net.
 
+  memory.oom_group
+
+	A read-write single value file which exists on non-root
+	cgroups.  The default is "0".
+
+	If set, OOM killer will consider the memory cgroup as an
+	indivisible memory consumers and compare it with other memory
+	consumers by it's memory footprint.
+	If such memory cgroup is selected as an OOM victim, all
+	processes belonging to it or it's descendants will be killed.
+
+	This applies to system-wide OOM conditions and reaching
+	the hard memory limit of the cgroup and their ancestor.
+	If OOM condition happens in a descendant cgroup with it's own
+	memory limit, the memory cgroup can't be considered
+	as an OOM victim, and OOM killer will not kill all belonging
+	tasks.
+
+	Also, OOM killer respects the /proc/pid/oom_score_adj value -1000,
+	and will never kill the unkillable task, even if memory.oom_group
+	is set.
+
+	If cgroup-aware OOM killer is not enabled, ENOTSUPP error
+	is returned on attempt to access the file.
+
   memory.events
 	A read-only flat-keyed file which exists on non-root cgroups.
 	The following entries are defined.  Unless specified
@@ -1242,6 +1268,54 @@ to be accessed repeatedly by other cgroups, it may make sense to use
 POSIX_FADV_DONTNEED to relinquish the ownership of memory areas
 belonging to the affected files to ensure correct memory ownership.
 
+OOM Killer
+~~~~~~~~~~
+
+Cgroup v2 memory controller implements a cgroup-aware OOM killer.
+It means that it treats cgroups as first class OOM entities.
+
+Cgroup-aware OOM logic is turned off by default and requires
+passing the "groupoom" option on mounting cgroupfs. It can also
+by remounting cgroupfs with the following command::
+
+  # mount -o remount,groupoom $MOUNT_POINT
+
+Under OOM conditions the memory controller tries to make the best
+choice of a victim, looking for a memory cgroup with the largest
+memory footprint, considering leaf cgroups and cgroups with the
+memory.oom_group option set, which are considered to be an indivisible
+memory consumers.
+
+By default, OOM killer will kill the biggest task in the selected
+memory cgroup. A user can change this behavior by enabling
+the per-cgroup memory.oom_group option. If set, it causes
+the OOM killer to kill all processes attached to the cgroup,
+except processes with oom_score_adj set to -1000.
+
+This affects both system- and cgroup-wide OOMs. For a cgroup-wide OOM
+the memory controller considers only cgroups belonging to the sub-tree
+of the OOM'ing cgroup.
+
+Leaf cgroups and cgroups with oom_group option set are compared based
+on their cumulative memory usage. The root cgroup is treated as a
+leaf memory cgroup as well, so it is compared with other leaf memory
+cgroups. Due to internal implementation restrictions the size of
+the root cgroup is the cumulative sum of oom_badness of all its tasks
+(in other words oom_score_adj of each task is obeyed). Relying on
+oom_score_adj (apart from OOM_SCORE_ADJ_MIN) can lead to over- or
+underestimation of the root cgroup consumption and it is therefore
+discouraged. This might change in the future, however.
+
+If there are no cgroups with the enabled memory controller,
+the OOM killer is using the "traditional" process-based approach.
+
+Please, note that memory charges are not migrating if tasks
+are moved between different memory cgroups. Moving tasks with
+significant memory footprint may affect OOM victim selection logic.
+If it's a case, please, consider creating a common ancestor for
+the source and destination memory cgroups and enabling oom_group
+on ancestor layer.
+
 
 IO
 --
diff --git a/MAINTAINERS b/MAINTAINERS
index 909fb93b28fc..f9bf4651db41 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1373,7 +1373,8 @@ F:	arch/arm/mach-ebsa110/
 F:	drivers/net/ethernet/amd/am79c961a.*
 
 ARM/ENERGY MICRO (SILICON LABS) EFM32 SUPPORT
-M:	Uwe Kleine-König <kernel@pengutronix.de>
+M:	Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
+R:	Pengutronix Kernel Team <kernel@pengutronix.de>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 N:	efm32
@@ -1401,7 +1402,8 @@ F:	arch/arm/mach-footbridge/
 
 ARM/FREESCALE IMX / MXC ARM ARCHITECTURE
 M:	Shawn Guo <shawnguo@kernel.org>
-M:	Sascha Hauer <kernel@pengutronix.de>
+M:	Sascha Hauer <s.hauer@pengutronix.de>
+R:	Pengutronix Kernel Team <kernel@pengutronix.de>
 R:	Fabio Estevam <fabio.estevam@nxp.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
@@ -1416,7 +1418,8 @@ F:	include/soc/imx/
 
 ARM/FREESCALE VYBRID ARM ARCHITECTURE
 M:	Shawn Guo <shawnguo@kernel.org>
-M:	Sascha Hauer <kernel@pengutronix.de>
+M:	Sascha Hauer <s.hauer@pengutronix.de>
+R:	Pengutronix Kernel Team <kernel@pengutronix.de>
 R:	Stefan Agner <stefan@agner.ch>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
@@ -5652,7 +5655,8 @@ F:	drivers/net/ethernet/freescale/fec.h
 F:	Documentation/devicetree/bindings/net/fsl-fec.txt
 
 FREESCALE IMX / MXC FRAMEBUFFER DRIVER
-M:	Sascha Hauer <kernel@pengutronix.de>
+M:	Sascha Hauer <s.hauer@pengutronix.de>
+R:	Pengutronix Kernel Team <kernel@pengutronix.de>
 L:	linux-fbdev@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
@@ -12814,7 +12818,8 @@ F:	include/linux/siphash.h
 
 SIOX
 M:	Gavin Schenk <g.schenk@eckelmann.de>
-M:	Uwe Kleine-König <kernel@pengutronix.de>
+M:	Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
+R:	Pengutronix Kernel Team <kernel@pengutronix.de>
 S:	Supported
 F:	drivers/siox/*
 F:	include/trace/events/siox.h
diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
index 4355f0ec44d6..f98baaec0a15 100644
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@@ -17,6 +17,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/personality.h>	/* For READ_IMPLIES_EXEC */
+
 #ifndef CONFIG_MMU
 
 #include <asm/page-nommu.h>
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 9033c8194eda..ccc421503363 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -1093,7 +1093,7 @@ static int show_spu_loadavg(struct seq_file *s, void *private)
 		LOAD_INT(c), LOAD_FRAC(c),
 		count_active_contexts(),
 		atomic_read(&nr_spu_contexts),
-		idr_get_cursor(&task_active_pid_ns(current)->idr));
+		idr_get_cursor(&task_active_pid_ns(current)->idr) - 1);
 	return 0;
 }
 
diff --git a/block/genhd.c b/block/genhd.c
index dc7e089373b9..10dcc29b5e9d 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -991,7 +991,7 @@ static int show_partition(struct seq_file *seqf, void *v)
 	char buf[BDEVNAME_SIZE];
 
 	/* Don't show non-partitionable removeable devices or empty devices */
-	if (!get_capacity(sgp) || (!disk_max_parts(sgp) &&
+	if (!get_capacity(sgp) || (!(disk_max_parts(sgp) > 1) &&
 				   (sgp->flags & GENHD_FL_REMOVABLE)))
 		return 0;
 	if (sgp->flags & GENHD_FL_SUPPRESS_PARTITION_INFO)
diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c
index 9d27016c899e..0434ab7b6497 100644
--- a/drivers/rapidio/devices/rio_mport_cdev.c
+++ b/drivers/rapidio/devices/rio_mport_cdev.c
@@ -740,10 +740,7 @@ static int do_dma_request(struct mport_dma_req *req,
 	tx->callback = dma_xfer_callback;
 	tx->callback_param = req;
 
-	req->dmach = chan;
-	req->sync = sync;
 	req->status = DMA_IN_PROGRESS;
-	init_completion(&req->req_comp);
 	kref_get(&req->refcount);
 
 	cookie = dmaengine_submit(tx);
@@ -831,13 +828,20 @@ rio_dma_transfer(struct file *filp, u32 transfer_mode,
 	if (!req)
 		return -ENOMEM;
 
-	kref_init(&req->refcount);
-
 	ret = get_dma_channel(priv);
 	if (ret) {
 		kfree(req);
 		return ret;
 	}
+	chan = priv->dmach;
+
+	kref_init(&req->refcount);
+	init_completion(&req->req_comp);
+	req->dir = dir;
+	req->filp = filp;
+	req->priv = priv;
+	req->dmach = chan;
+	req->sync = sync;
 
 	/*
 	 * If parameter loc_addr != NULL, we are transferring data from/to
@@ -925,11 +929,6 @@ rio_dma_transfer(struct file *filp, u32 transfer_mode,
 				xfer->offset, xfer->length);
 	}
 
-	req->dir = dir;
-	req->filp = filp;
-	req->priv = priv;
-	chan = priv->dmach;
-
 	nents = dma_map_sg(chan->device->dev,
 			   req->sgt.sgl, req->sgt.nents, dir);
 	if (nents == 0) {
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 82e8f6edfb48..b12e37f27530 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -749,7 +749,7 @@ static int autofs4_dir_mkdir(struct inode *dir,
 
 	autofs4_del_active(dentry);
 
-	inode = autofs4_get_inode(dir->i_sb, S_IFDIR | 0555);
+	inode = autofs4_get_inode(dir->i_sb, S_IFDIR | mode);
 	if (!inode)
 		return -ENOMEM;
 	d_add(dentry, inode);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 41e04183e4ce..64ae6b1ebdd9 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1621,8 +1621,8 @@ static int fill_files_note(struct memelfnote *note)
 	if (size >= MAX_FILE_NOTE_SIZE) /* paranoia check */
 		return -EINVAL;
 	size = round_up(size, PAGE_SIZE);
-	data = vmalloc(size);
-	if (!data)
+	data = kvmalloc(size, GFP_KERNEL);
+	if (ZERO_OR_NULL_PTR(data))
 		return -ENOMEM;
 
 	start_end_ofs = data + 2;
@@ -1639,7 +1639,7 @@ static int fill_files_note(struct memelfnote *note)
 		filename = file_path(file, name_curpos, remaining);
 		if (IS_ERR(filename)) {
 			if (PTR_ERR(filename) == -ENAMETOOLONG) {
-				vfree(data);
+				kvfree(data);
 				size = size * 5 / 4;
 				goto alloc;
 			}
@@ -1932,7 +1932,7 @@ static void free_note_info(struct elf_note_info *info)
 		kfree(t);
 	}
 	kfree(info->psinfo.data);
-	vfree(info->files.data);
+	kvfree(info->files.data);
 }
 
 #else
@@ -2148,7 +2148,7 @@ static void free_note_info(struct elf_note_info *info)
 
 	/* Free data possibly allocated by fill_files_note(): */
 	if (info->notes_files)
-		vfree(info->notes_files->data);
+		kvfree(info->notes_files->data);
 
 	kfree(info->prstatus);
 	kfree(info->psinfo);
@@ -2294,8 +2294,8 @@ static int elf_core_dump(struct coredump_params *cprm)
 
 	if (segs - 1 > ULONG_MAX / sizeof(*vma_filesz))
 		goto end_coredump;
-	vma_filesz = vmalloc((segs - 1) * sizeof(*vma_filesz));
-	if (!vma_filesz)
+	vma_filesz = kvmalloc((segs - 1) * sizeof(*vma_filesz), GFP_KERNEL);
+	if (ZERO_OR_NULL_PTR(vma_filesz))
 		goto end_coredump;
 
 	for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
@@ -2402,7 +2402,7 @@ end_coredump:
 cleanup:
 	free_note_info(&info);
 	kfree(shdr4extnum);
-	vfree(vma_filesz);
+	kvfree(vma_filesz);
 	kfree(phdr4note);
 	kfree(elf);
 out:
diff --git a/fs/dcache.c b/fs/dcache.c
index 86d2de63461e..3507badeb60a 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -292,7 +292,8 @@ void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry
 		spin_unlock(&dentry->d_lock);
 		name->name = p->name;
 	} else {
-		memcpy(name->inline_name, dentry->d_iname, DNAME_INLINE_LEN);
+		memcpy(name->inline_name, dentry->d_iname,
+		       dentry->d_name.len + 1);
 		spin_unlock(&dentry->d_lock);
 		name->name = name->inline_name;
 	}
@@ -1488,6 +1489,7 @@ void shrink_dcache_parent(struct dentry *parent)
 			break;
 
 		shrink_dentry_list(&data.dispose);
+		cond_resched();
 	}
 }
 EXPORT_SYMBOL(shrink_dcache_parent);
diff --git a/fs/exec.c b/fs/exec.c
index 183059c427b9..32eea4c65909 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1338,6 +1338,7 @@ void setup_new_exec(struct linux_binprm * bprm)
 	if (bprm->secureexec) {
 		/* Make sure parent cannot signal privileged process. */
 		current->pdeath_signal = 0;
+		current->signal->pdeath_signal_proc = 0;
 
 		/*
 		 * For secureexec, reset the stack limit to sane default to
diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c
index 3c6a9c156b7a..cfa862ea19d2 100644
--- a/fs/exofs/ore.c
+++ b/fs/exofs/ore.c
@@ -146,68 +146,82 @@ int  _ore_get_io_state(struct ore_layout *layout,
 			struct ore_io_state **pios)
 {
 	struct ore_io_state *ios;
-	struct page **pages;
-	struct osd_sg_entry *sgilist;
+	size_t size_ios, size_extra, size_total;
+	void *ios_extra;
+
+	/*
+	 * The desired layout looks like this, with the extra_allocation
+	 * items pointed at from fields within ios or per_dev:
+
 	struct __alloc_all_io_state {
 		struct ore_io_state ios;
 		struct ore_per_dev_state per_dev[numdevs];
 		union {
 			struct osd_sg_entry sglist[sgs_per_dev * numdevs];
 			struct page *pages[num_par_pages];
-		};
-	} *_aios;
-
-	if (likely(sizeof(*_aios) <= PAGE_SIZE)) {
-		_aios = kzalloc(sizeof(*_aios), GFP_KERNEL);
-		if (unlikely(!_aios)) {
-			ORE_DBGMSG("Failed kzalloc bytes=%zd\n",
-				   sizeof(*_aios));
+		} extra_allocation;
+	} whole_allocation;
+
+	*/
+
+	/* This should never happen, so abort early if it ever does. */
+	if (sgs_per_dev && num_par_pages) {
+		ORE_DBGMSG("Tried to use both pages and sglist\n");
+		*pios = NULL;
+		return -EINVAL;
+	}
+
+	if (numdevs > (INT_MAX - sizeof(*ios)) /
+		       sizeof(struct ore_per_dev_state))
+		return -ENOMEM;
+	size_ios = sizeof(*ios) + sizeof(struct ore_per_dev_state) * numdevs;
+
+	if (sgs_per_dev * numdevs > INT_MAX / sizeof(struct osd_sg_entry))
+		return -ENOMEM;
+	if (num_par_pages > INT_MAX / sizeof(struct page *))
+		return -ENOMEM;
+	size_extra = max(sizeof(struct osd_sg_entry) * (sgs_per_dev * numdevs),
+			 sizeof(struct page *) * num_par_pages);
+
+	size_total = size_ios + size_extra;
+
+	if (likely(size_total <= PAGE_SIZE)) {
+		ios = kzalloc(size_total, GFP_KERNEL);
+		if (unlikely(!ios)) {
+			ORE_DBGMSG("Failed kzalloc bytes=%zd\n", size_total);
 			*pios = NULL;
 			return -ENOMEM;
 		}
-		pages = num_par_pages ? _aios->pages : NULL;
-		sgilist = sgs_per_dev ? _aios->sglist : NULL;
-		ios = &_aios->ios;
+		ios_extra = (char *)ios + size_ios;
 	} else {
-		struct __alloc_small_io_state {
-			struct ore_io_state ios;
-			struct ore_per_dev_state per_dev[numdevs];
-		} *_aio_small;
-		union __extra_part {
-			struct osd_sg_entry sglist[sgs_per_dev * numdevs];
-			struct page *pages[num_par_pages];
-		} *extra_part;
-
-		_aio_small = kzalloc(sizeof(*_aio_small), GFP_KERNEL);
-		if (unlikely(!_aio_small)) {
+		ios = kzalloc(size_ios, GFP_KERNEL);
+		if (unlikely(!ios)) {
 			ORE_DBGMSG("Failed alloc first part bytes=%zd\n",
-				   sizeof(*_aio_small));
+				   size_ios);
 			*pios = NULL;
 			return -ENOMEM;
 		}
-		extra_part = kzalloc(sizeof(*extra_part), GFP_KERNEL);
-		if (unlikely(!extra_part)) {
+		ios_extra = kzalloc(size_extra, GFP_KERNEL);
+		if (unlikely(!ios_extra)) {
 			ORE_DBGMSG("Failed alloc second part bytes=%zd\n",
-				   sizeof(*extra_part));
-			kfree(_aio_small);
+				   size_extra);
+			kfree(ios);
 			*pios = NULL;
 			return -ENOMEM;
 		}
 
-		pages = num_par_pages ? extra_part->pages : NULL;
-		sgilist = sgs_per_dev ? extra_part->sglist : NULL;
 		/* In this case the per_dev[0].sgilist holds the pointer to
 		 * be freed
 		 */
-		ios = &_aio_small->ios;
 		ios->extra_part_alloc = true;
 	}
 
-	if (pages) {
-		ios->parity_pages = pages;
+	if (num_par_pages) {
+		ios->parity_pages = ios_extra;
 		ios->max_par_pages = num_par_pages;
 	}
-	if (sgilist) {
+	if (sgs_per_dev) {
+		struct osd_sg_entry *sgilist = ios_extra;
 		unsigned d;
 
 		for (d = 0; d < numdevs; ++d) {
diff --git a/fs/exofs/ore_raid.c b/fs/exofs/ore_raid.c
index 27cbdb697649..659129d5e9f7 100644
--- a/fs/exofs/ore_raid.c
+++ b/fs/exofs/ore_raid.c
@@ -71,6 +71,11 @@ static int _sp2d_alloc(unsigned pages_in_unit, unsigned group_width,
 {
 	struct __stripe_pages_2d *sp2d;
 	unsigned data_devs = group_width - parity;
+
+	/*
+	 * Desired allocation layout is, though when larger than PAGE_SIZE,
+	 * each struct __alloc_1p_arrays is separately allocated:
+
 	struct _alloc_all_bytes {
 		struct __alloc_stripe_pages_2d {
 			struct __stripe_pages_2d sp2d;
@@ -82,55 +87,85 @@ static int _sp2d_alloc(unsigned pages_in_unit, unsigned group_width,
 			char page_is_read[data_devs];
 		} __a1pa[pages_in_unit];
 	} *_aab;
+
 	struct __alloc_1p_arrays *__a1pa;
 	struct __alloc_1p_arrays *__a1pa_end;
-	const unsigned sizeof__a1pa = sizeof(_aab->__a1pa[0]);
+
+	*/
+
+	char *__a1pa;
+	char *__a1pa_end;
+
+	const size_t sizeof_stripe_pages_2d =
+		sizeof(struct __stripe_pages_2d) +
+		sizeof(struct __1_page_stripe) * pages_in_unit;
+	const size_t sizeof__a1pa =
+		ALIGN(sizeof(struct page *) * (2 * group_width) + data_devs,
+		      sizeof(void *));
+	const size_t sizeof__a1pa_arrays = sizeof__a1pa * pages_in_unit;
+	const size_t alloc_total = sizeof_stripe_pages_2d +
+				   sizeof__a1pa_arrays;
+
 	unsigned num_a1pa, alloc_size, i;
 
 	/* FIXME: check these numbers in ore_verify_layout */
-	BUG_ON(sizeof(_aab->__asp2d) > PAGE_SIZE);
+	BUG_ON(sizeof_stripe_pages_2d > PAGE_SIZE);
 	BUG_ON(sizeof__a1pa > PAGE_SIZE);
 
-	if (sizeof(*_aab) > PAGE_SIZE) {
-		num_a1pa = (PAGE_SIZE - sizeof(_aab->__asp2d)) / sizeof__a1pa;
-		alloc_size = sizeof(_aab->__asp2d) + sizeof__a1pa * num_a1pa;
+	/*
+	 * If alloc_total would be larger than PAGE_SIZE, only allocate
+	 * as many a1pa items as would fill the rest of the page, instead
+	 * of the full pages_in_unit count.
+	 */
+	if (alloc_total > PAGE_SIZE) {
+		num_a1pa = (PAGE_SIZE - sizeof_stripe_pages_2d) / sizeof__a1pa;
+		alloc_size = sizeof_stripe_pages_2d + sizeof__a1pa * num_a1pa;
 	} else {
 		num_a1pa = pages_in_unit;
-		alloc_size = sizeof(*_aab);
+		alloc_size = alloc_total;
 	}
 
-	_aab = kzalloc(alloc_size, GFP_KERNEL);
-	if (unlikely(!_aab)) {
+	*psp2d = sp2d = kzalloc(alloc_size, GFP_KERNEL);
+	if (unlikely(!sp2d)) {
 		ORE_DBGMSG("!! Failed to alloc sp2d size=%d\n", alloc_size);
 		return -ENOMEM;
 	}
+	/* From here Just call _sp2d_free */
 
-	sp2d = &_aab->__asp2d.sp2d;
-	*psp2d = sp2d; /* From here Just call _sp2d_free */
-
-	__a1pa = _aab->__a1pa;
-	__a1pa_end = __a1pa + num_a1pa;
+	/* Find start of a1pa area. */
+	__a1pa = (char *)sp2d + sizeof_stripe_pages_2d;
+	/* Find end of the _allocated_ a1pa area. */
+	__a1pa_end = __a1pa + alloc_size;
 
+	/* Allocate additionally needed a1pa items in PAGE_SIZE chunks. */
 	for (i = 0; i < pages_in_unit; ++i) {
 		if (unlikely(__a1pa >= __a1pa_end)) {
 			num_a1pa = min_t(unsigned, PAGE_SIZE / sizeof__a1pa,
 							pages_in_unit - i);
+			alloc_size = sizeof__a1pa * num_a1pa;
 
-			__a1pa = kcalloc(num_a1pa, sizeof__a1pa, GFP_KERNEL);
+			__a1pa = kzalloc(alloc_size, GFP_KERNEL);
 			if (unlikely(!__a1pa)) {
 				ORE_DBGMSG("!! Failed to _alloc_1p_arrays=%d\n",
 					   num_a1pa);
 				return -ENOMEM;
 			}
-			__a1pa_end = __a1pa + num_a1pa;
+			__a1pa_end = __a1pa + alloc_size;
 			/* First *pages is marked for kfree of the buffer */
 			sp2d->_1p_stripes[i].alloc = true;
 		}
 
-		sp2d->_1p_stripes[i].pages = __a1pa->pages;
-		sp2d->_1p_stripes[i].scribble = __a1pa->scribble ;
-		sp2d->_1p_stripes[i].page_is_read = __a1pa->page_is_read;
-		++__a1pa;
+		/*
+		 * Attach all _lp_stripes pointers to the allocation for
+		 * it which was either part of the original PAGE_SIZE
+		 * allocation or the subsequent allocation in this loop.
+		 */
+		sp2d->_1p_stripes[i].pages = (void *)__a1pa;
+		sp2d->_1p_stripes[i].scribble =
+			sp2d->_1p_stripes[i].pages + group_width;
+		sp2d->_1p_stripes[i].page_is_read =
+			(char *)(sp2d->_1p_stripes[i].scribble + group_width);
+		__a1pa += sizeof__a1pa;
 	}
 
 	sp2d->parity = parity;
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 179cd5c2f52a..f3c29e9326f1 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -549,27 +549,26 @@ static int exofs_devs_2_odi(struct exofs_dt_device_info *dt_dev,
 static int __alloc_dev_table(struct exofs_sb_info *sbi, unsigned numdevs,
 		      struct exofs_dev **peds)
 {
-	struct __alloc_ore_devs_and_exofs_devs {
-		/* Twice bigger table: See exofs_init_comps() and comment at
-		 * exofs_read_lookup_dev_table()
-		 */
-		struct ore_dev *oreds[numdevs * 2 - 1];
-		struct exofs_dev eds[numdevs];
-	} *aoded;
+	/* Twice bigger table: See exofs_init_comps() and comment at
+	 * exofs_read_lookup_dev_table()
+	 */
+	size_t numores = numdevs * 2 - 1;
 	struct exofs_dev *eds;
 	unsigned i;
 
-	aoded = kzalloc(sizeof(*aoded), GFP_KERNEL);
-	if (unlikely(!aoded)) {
+	sbi->oc.ods = kzalloc(numores * sizeof(struct ore_dev *) +
+			      numdevs * sizeof(struct exofs_dev), GFP_KERNEL);
+	if (unlikely(!sbi->oc.ods)) {
 		EXOFS_ERR("ERROR: failed allocating Device array[%d]\n",
 			  numdevs);
 		return -ENOMEM;
 	}
 
-	sbi->oc.ods = aoded->oreds;
-	*peds = eds = aoded->eds;
+	/* Start of allocated struct exofs_dev entries */
+	*peds = eds = (void *)sbi->oc.ods[numores];
+	/* Initialize pointers into struct exofs_dev */
 	for (i = 0; i < numdevs; ++i)
-		aoded->oreds[i] = &eds[i].ored;
+		sbi->oc.ods[i] = &eds[i].ored;
 	return 0;
 }
 
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 4b12ba70a895..47d7c151fcba 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -745,11 +745,12 @@ int inode_congested(struct inode *inode, int cong_bits)
 	 */
 	if (inode && inode_to_wb_is_valid(inode)) {
 		struct bdi_writeback *wb;
-		bool locked, congested;
+		struct wb_lock_cookie lock_cookie = {};
+		bool congested;
 
-		wb = unlocked_inode_to_wb_begin(inode, &locked);
+		wb = unlocked_inode_to_wb_begin(inode, &lock_cookie);
 		congested = wb_congested(wb, cong_bits);
-		unlocked_inode_to_wb_end(inode, locked);
+		unlocked_inode_to_wb_end(inode, &lock_cookie);
 		return congested;
 	}
 
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 91a8889abf9b..2809e29d612d 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -540,11 +540,12 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg,
 	struct bio *bio;
 	struct page *page;
 
+#define O2HB_BIO_VECS 16
 	/* Testing has shown this allocation to take long enough under
 	 * GFP_KERNEL that the local node can get fenced. It would be
 	 * nicest if we could pre-allocate these bios and avoid this
 	 * all together. */
-	bio = bio_alloc(GFP_ATOMIC, 16);
+	bio = bio_alloc(GFP_ATOMIC, O2HB_BIO_VECS);
 	if (!bio) {
 		mlog(ML_ERROR, "Could not alloc slots BIO!\n");
 		bio = ERR_PTR(-ENOMEM);
@@ -570,7 +571,10 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg,
 		     current_page, vec_len, vec_start);
 
 		len = bio_add_page(bio, page, vec_len, vec_start);
-		if (len != vec_len) {
+		if (len == 0 && current_page == O2HB_BIO_VECS) {
+			/* bio is full now. */
+			goto bail;
+		} else if (len != vec_len) {
 			mlog(ML_ERROR, "Adding page[%d] to bio failed, "
 			     "page %p, len %d, vec_len %u, vec_start %u, "
 			     "bi_sector %llu\n", current_page, page, len,
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 97a972efab83..ce33ac354602 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -3534,7 +3534,7 @@ 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;
 
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index e5dcea6cee5f..b63c97f4318e 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1378,15 +1378,23 @@ 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;
 	}
 
-	rm_quota = kzalloc(osb->max_slots * sizeof(int), GFP_NOFS);
-	if (!rm_quota) {
-		status = -ENOMEM;
-		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);
@@ -1422,9 +1430,14 @@ restart:
 		 * 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 (i == rm_quota_used)
-			rm_quota[rm_quota_used++] = slot_num;
+		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:
@@ -1452,16 +1465,19 @@ skip_recovery:
 	/* 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 */
-	for (i = 0; i < rm_quota_used; i++) {
-		qrec = ocfs2_begin_quota_recovery(osb, rm_quota[i]);
-		if (IS_ERR(qrec)) {
-			status = PTR_ERR(qrec);
-			mlog_errno(status);
-			continue;
+	if (quota_enabled) {
+		for (i = 0; i < rm_quota_used; i++) {
+			qrec = ocfs2_begin_quota_recovery(osb, rm_quota[i]);
+			if (IS_ERR(qrec)) {
+				status = PTR_ERR(qrec);
+				mlog_errno(status);
+				continue;
+			}
+			ocfs2_queue_recovery_completion(osb->journal,
+					rm_quota[i],
+					NULL, NULL, qrec,
+					ORPHAN_NEED_TRUNCATE);
 		}
-		ocfs2_queue_recovery_completion(osb->journal, rm_quota[i],
-						NULL, NULL, qrec,
-						ORPHAN_NEED_TRUNCATE);
 	}
 
 	ocfs2_super_unlock(osb, 1);
@@ -1483,7 +1499,8 @@ bail:
 
 	mutex_unlock(&osb->recovery_lock);
 
-	kfree(rm_quota);
+	if (quota_enabled)
+		kfree(rm_quota);
 
 	/* no one is callint kthread_stop() for us so the kthread() api
 	 * requires that we call do_exit().  And it isn't exported, but
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index d6c350ba25b9..c4b029c43464 100644
--- a/fs/ocfs2/stackglue.c
+++ b/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;
diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h
index e3036e1790e8..f2dce10fae54 100644
--- a/fs/ocfs2/stackglue.h
+++ b/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 */
diff --git a/fs/proc/base.c b/fs/proc/base.c
index eafa39a3a88c..1b2ede6abcdf 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1693,6 +1693,12 @@ void task_dump_owner(struct task_struct *task, umode_t mode,
 	kuid_t uid;
 	kgid_t gid;
 
+	if (unlikely(task->flags & PF_KTHREAD)) {
+		*ruid = GLOBAL_ROOT_UID;
+		*rgid = GLOBAL_ROOT_GID;
+		return;
+	}
+
 	/* Default to the tasks effective ownership */
 	rcu_read_lock();
 	cred = __task_cred(task);
diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c
index a000d7547479..b572cc865b92 100644
--- a/fs/proc/loadavg.c
+++ b/fs/proc/loadavg.c
@@ -24,7 +24,7 @@ static int loadavg_proc_show(struct seq_file *m, void *v)
 		LOAD_INT(avnrun[1]), LOAD_FRAC(avnrun[1]),
 		LOAD_INT(avnrun[2]), LOAD_FRAC(avnrun[2]),
 		nr_running(), nr_threads,
-		idr_get_cursor(&task_active_pid_ns(current)->idr));
+		idr_get_cursor(&task_active_pid_ns(current)->idr) - 1);
 	return 0;
 }
 
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 333cda80c3dd..30d8ee9ed46a 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1310,9 +1310,11 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
 		else if (is_swap_pmd(pmd)) {
 			swp_entry_t entry = pmd_to_swp_entry(pmd);
+			unsigned long offset = swp_offset(entry);
 
+			offset += (addr & ~PMD_MASK) >> PAGE_SHIFT;
 			frame = swp_type(entry) |
-				(swp_offset(entry) << MAX_SWAPFILES_SHIFT);
+				(offset << MAX_SWAPFILES_SHIFT);
 			flags |= PM_SWAP;
 			if (pmd_swp_soft_dirty(pmd))
 				flags |= PM_SOFT_DIRTY;
@@ -1332,6 +1334,8 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 				break;
 			if (pm->show_pfn && (flags & PM_PRESENT))
 				frame++;
+			else if (flags & PM_SWAP)
+				frame += (1 << MAX_SWAPFILES_SHIFT);
 		}
 		spin_unlock(ptl);
 		return err;
diff --git a/fs/seq_file.c b/fs/seq_file.c
index c6c27f1f9c98..8389da9d0eb8 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -709,11 +709,6 @@ void seq_put_decimal_ull_width(struct seq_file *m, const char *delimiter,
 	if (m->count + width >= m->size)
 		goto overflow;
 
-	if (num < 10) {
-		m->buf[m->count++] = num + '0';
-		return;
-	}
-
 	len = num_to_str(m->buf + m->count, m->size - m->count, num, width);
 	if (!len)
 		goto overflow;
@@ -800,11 +795,6 @@ void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num
 		num = -num;
 	}
 
-	if (num < 10) {
-		m->buf[m->count++] = num + '0';
-		return;
-	}
-
 	len = num_to_str(m->buf + m->count, m->size - m->count, num, 0);
 	if (!len)
 		goto overflow;
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index bfe86b54f6c1..0bd432a4d7bd 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -223,6 +223,11 @@ static inline void set_bdi_congested(struct backing_dev_info *bdi, int sync)
 	set_wb_congested(bdi->wb.congested, sync);
 }
 
+struct wb_lock_cookie {
+	bool locked;
+	unsigned long flags;
+};
+
 #ifdef CONFIG_CGROUP_WRITEBACK
 
 /**
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 84adb5ec4011..d4561cb27d24 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -347,7 +347,7 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode)
 /**
  * unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction
  * @inode: target inode
- * @lockedp: temp bool output param, to be passed to the end function
+ * @cookie: output param, to be passed to the end function
  *
  * The caller wants to access the wb associated with @inode but isn't
  * holding inode->i_lock, the i_pages lock or wb->list_lock.  This
@@ -355,12 +355,12 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode)
  * association doesn't change until the transaction is finished with
  * unlocked_inode_to_wb_end().
  *
- * The caller must call unlocked_inode_to_wb_end() with *@lockdep
- * afterwards and can't sleep during transaction.  IRQ may or may not be
- * disabled on return.
+ * The caller must call unlocked_inode_to_wb_end() with *@cookie afterwards and
+ * can't sleep during the transaction.  IRQs may or may not be disabled on
+ * return.
  */
 static inline struct bdi_writeback *
-unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
+unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie)
 {
 	rcu_read_lock();
 
@@ -368,10 +368,10 @@ unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
 	 * Paired with store_release in inode_switch_wb_work_fn() and
 	 * ensures that we see the new wb if we see cleared I_WB_SWITCH.
 	 */
-	*lockedp = smp_load_acquire(&inode->i_state) & I_WB_SWITCH;
+	cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH;
 
-	if (unlikely(*lockedp))
-		xa_lock_irq(&inode->i_mapping->i_pages);
+	if (unlikely(cookie->locked))
+		xa_lock_irqsave(&inode->i_mapping->i_pages, cookie->flags);
 
 	/*
 	 * Protected by either !I_WB_SWITCH + rcu_read_lock() or the i_pages
@@ -383,12 +383,13 @@ unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
 /**
  * unlocked_inode_to_wb_end - end inode wb access transaction
  * @inode: target inode
- * @locked: *@lockedp from unlocked_inode_to_wb_begin()
+ * @cookie: @cookie from unlocked_inode_to_wb_begin()
  */
-static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked)
+static inline void unlocked_inode_to_wb_end(struct inode *inode,
+					    struct wb_lock_cookie *cookie)
 {
-	if (unlikely(locked))
-		xa_unlock_irq(&inode->i_mapping->i_pages);
+	if (unlikely(cookie->locked))
+		xa_unlock_irqrestore(&inode->i_mapping->i_pages, cookie->flags);
 
 	rcu_read_unlock();
 }
@@ -435,12 +436,13 @@ static inline struct bdi_writeback *inode_to_wb(struct inode *inode)
 }
 
 static inline struct bdi_writeback *
-unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
+unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie)
 {
 	return inode_to_wb(inode);
 }
 
-static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked)
+static inline void unlocked_inode_to_wb_end(struct inode *inode,
+					    struct wb_lock_cookie *cookie)
 {
 }
 
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index dc5b70449dc6..9b2879bba00e 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -81,6 +81,11 @@ enum {
 	 * Enable cpuset controller in v1 cgroup to use v2 behavior.
 	 */
 	CGRP_ROOT_CPUSET_V2_MODE = (1 << 4),
+
+	/*
+	 * Enable cgroup-aware OOM killer.
+	 */
+	CGRP_GROUP_OOM = (1 << 5),
 };
 
 /* cftype->flags */
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index ceb96ecab96e..5a1d8580febe 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -25,6 +25,11 @@
 #define __SANITIZE_ADDRESS__
 #endif
 
+#ifdef CONFIG_KASAN
+#undef __no_sanitize_address
+#define __no_sanitize_address __attribute__((no_sanitize("address")))
+#endif
+
 /* Clang doesn't have a way to turn it off per-function, yet. */
 #ifdef __noretpoline
 #undef __noretpoline
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index d99b71bc2c66..2da009958798 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -35,6 +35,7 @@ struct mem_cgroup;
 struct page;
 struct mm_struct;
 struct kmem_cache;
+struct oom_control;
 
 /* Cgroup-specific page state, on top of universal node page state */
 enum memcg_stat_item {
@@ -204,6 +205,13 @@ struct mem_cgroup {
 	/* OOM-Killer disable */
 	int		oom_kill_disable;
 
+	/*
+	 * Treat the sub-tree as an indivisible memory consumer,
+	 * kill all belonging tasks if the memory cgroup selected
+	 * as OOM victim.
+	 */
+	bool oom_group;
+
 	/* memory.events */
 	atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS];
 	struct cgroup_file events_file;
@@ -348,6 +356,11 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
 	return css ? container_of(css, struct mem_cgroup, css) : NULL;
 }
 
+static inline void mem_cgroup_put(struct mem_cgroup *memcg)
+{
+	css_put(&memcg->css);
+}
+
 #define mem_cgroup_from_counter(counter, member)	\
 	container_of(counter, struct mem_cgroup, member)
 
@@ -486,6 +499,13 @@ static inline bool task_in_memcg_oom(struct task_struct *p)
 
 bool mem_cgroup_oom_synchronize(bool wait);
 
+bool mem_cgroup_select_oom_victim(struct oom_control *oc);
+
+static inline bool mem_cgroup_oom_group(struct mem_cgroup *memcg)
+{
+	return memcg->oom_group;
+}
+
 #ifdef CONFIG_MEMCG_SWAP
 extern int do_swap_account;
 #endif
@@ -793,6 +813,10 @@ static inline bool task_in_mem_cgroup(struct task_struct *task,
 	return true;
 }
 
+static inline void mem_cgroup_put(struct mem_cgroup *memcg)
+{
+}
+
 static inline struct mem_cgroup *
 mem_cgroup_iter(struct mem_cgroup *root,
 		struct mem_cgroup *prev,
@@ -985,6 +1009,16 @@ static inline
 void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx)
 {
 }
+
+static inline bool mem_cgroup_select_oom_victim(struct oom_control *oc)
+{
+	return false;
+}
+
+static inline bool mem_cgroup_oom_group(struct mem_cgroup *memcg)
+{
+	return false;
+}
 #endif /* CONFIG_MEMCG */
 
 /* idx can be of type enum memcg_stat_item or node_stat_item */
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 5bad038ac012..d4d41c01a74d 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -10,6 +10,13 @@
 #include <linux/sched/coredump.h> /* MMF_* */
 #include <linux/mm.h> /* VM_FAULT* */
 
+
+/*
+ * Special value returned by victim selection functions to indicate
+ * that are inflight OOM victims.
+ */
+#define INFLIGHT_VICTIM ((void *)-1UL)
+
 struct zonelist;
 struct notifier_block;
 struct mem_cgroup;
@@ -40,7 +47,8 @@ struct oom_control {
 
 	/* Used by oom implementation, do not set */
 	unsigned long totalpages;
-	struct task_struct *chosen;
+	struct task_struct *chosen_task;
+	struct mem_cgroup *chosen_memcg;
 	unsigned long chosen_points;
 };
 
@@ -111,6 +119,8 @@ extern void oom_killer_enable(void);
 
 extern struct task_struct *find_lock_task_mm(struct task_struct *p);
 
+extern int oom_evaluate_task(struct task_struct *task, void *arg);
+
 /* sysctls */
 extern int sysctl_oom_dump_tasks;
 extern int sysctl_oom_kill_allocating_task;
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index a7ce74c74e49..a52683a5fe90 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -104,6 +104,9 @@ struct signal_struct {
 	int			group_stop_count;
 	unsigned int		flags; /* see SIGNAL_* flags below */
 
+	/* The signal sent when the parent dies: */
+	int			pdeath_signal_proc;
+
 	/*
 	 * PR_SET_CHILD_SUBREAPER marks a process, like a service
 	 * manager, to re-parent orphan (double-forking) child processes
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index 388ff2936a87..a3894918a436 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -75,6 +75,6 @@ struct shrinker {
 #define SHRINKER_NUMA_AWARE	(1 << 0)
 #define SHRINKER_MEMCG_AWARE	(1 << 1)
 
-extern int register_shrinker(struct shrinker *);
+extern __must_check int register_shrinker(struct shrinker *);
 extern void unregister_shrinker(struct shrinker *);
 #endif
diff --git a/include/linux/swap.h b/include/linux/swap.h
index c063443d8638..f73eafcaf4e9 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -172,8 +172,9 @@ enum {
 	SWP_PAGE_DISCARD = (1 << 9),	/* freed swap page-cluster discards */
 	SWP_STABLE_WRITES = (1 << 10),	/* no overwrite PG_writeback pages */
 	SWP_SYNCHRONOUS_IO = (1 << 11),	/* synchronous IO is efficient */
+	SWP_VALID	= (1 << 12),	/* swap is valid to be operated on? */
 					/* add others here before... */
-	SWP_SCANNING	= (1 << 12),	/* refcount in scan_swap_map */
+	SWP_SCANNING	= (1 << 13),	/* refcount in scan_swap_map */
 };
 
 #define SWAP_CLUSTER_MAX 32UL
@@ -460,7 +461,7 @@ extern unsigned int count_swap_pages(int, int);
 extern sector_t map_swap_page(struct page *, struct block_device **);
 extern sector_t swapdev_block(int, pgoff_t);
 extern int page_swapcount(struct page *);
-extern int __swap_count(struct swap_info_struct *si, swp_entry_t entry);
+extern int __swap_count(swp_entry_t entry);
 extern int __swp_swapcount(swp_entry_t entry);
 extern int swp_swapcount(swp_entry_t entry);
 extern struct swap_info_struct *page_swap_info(struct page *);
@@ -470,6 +471,12 @@ extern int try_to_free_swap(struct page *);
 struct backing_dev_info;
 extern int init_swap_address_space(unsigned int type, unsigned long nr_pages);
 extern void exit_swap_address_space(unsigned int type);
+extern struct swap_info_struct *get_swap_device(swp_entry_t entry);
+
+static inline void put_swap_device(struct swap_info_struct *si)
+{
+	preempt_enable();
+}
 
 #else /* CONFIG_SWAP */
 
@@ -575,7 +582,7 @@ static inline int page_swapcount(struct page *page)
 	return 0;
 }
 
-static inline int __swap_count(struct swap_info_struct *si, swp_entry_t entry)
+static inline int __swap_count(swp_entry_t entry)
 {
 	return 0;
 }
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 34f053a150a9..cf2862bd134a 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -43,11 +43,7 @@ enum {
 #define THREAD_ALIGN	THREAD_SIZE
 #endif
 
-#if IS_ENABLED(CONFIG_DEBUG_STACK_USAGE) || IS_ENABLED(CONFIG_DEBUG_KMEMLEAK)
-# define THREADINFO_GFP		(GFP_KERNEL_ACCOUNT | __GFP_ZERO)
-#else
-# define THREADINFO_GFP		(GFP_KERNEL_ACCOUNT)
-#endif
+#define THREADINFO_GFP		(GFP_KERNEL_ACCOUNT | __GFP_ZERO)
 
 /*
  * flag set/clear/test wrappers
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index af5f8c2df87a..3165863aa187 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -207,4 +207,8 @@ struct prctl_mm_map {
 # define PR_SVE_VL_LEN_MASK		0xffff
 # define PR_SVE_VL_INHERIT		(1 << 17) /* inherit across exec */
 
+/* Process-based variant of PDEATHSIG */
+#define PR_SET_PDEATHSIG_PROC		48
+#define PR_GET_PDEATHSIG_PROC		49
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index b07335be7164..b3232bda8f19 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1732,6 +1732,9 @@ static int parse_cgroup_root_flags(char *data, unsigned int *root_flags)
 		if (!strcmp(token, "nsdelegate")) {
 			*root_flags |= CGRP_ROOT_NS_DELEGATE;
 			continue;
+		} else if (!strcmp(token, "groupoom")) {
+			*root_flags |= CGRP_GROUP_OOM;
+			continue;
 		}
 
 		pr_err("cgroup2: unknown option \"%s\"\n", token);
@@ -1748,6 +1751,11 @@ static void apply_cgroup_root_flags(unsigned int root_flags)
 			cgrp_dfl_root.flags |= CGRP_ROOT_NS_DELEGATE;
 		else
 			cgrp_dfl_root.flags &= ~CGRP_ROOT_NS_DELEGATE;
+
+		if (root_flags & CGRP_GROUP_OOM)
+			cgrp_dfl_root.flags |= CGRP_GROUP_OOM;
+		else
+			cgrp_dfl_root.flags &= ~CGRP_GROUP_OOM;
 	}
 }
 
@@ -1755,6 +1763,8 @@ static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root
 {
 	if (cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE)
 		seq_puts(seq, ",nsdelegate");
+	if (cgrp_dfl_root.flags & CGRP_GROUP_OOM)
+		seq_puts(seq, ",groupoom");
 	return 0;
 }
 
@@ -5915,7 +5925,8 @@ static struct kobj_attribute cgroup_delegate_attr = __ATTR_RO(delegate);
 static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr,
 			     char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "nsdelegate\n");
+	return snprintf(buf, PAGE_SIZE, "nsdelegate\n"
+					"groupoom\n");
 }
 static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features);
 
diff --git a/kernel/cred.c b/kernel/cred.c
index ecf03657e71c..0192a94670e1 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -448,6 +448,7 @@ int commit_creds(struct cred *new)
 		if (task->mm)
 			set_dumpable(task->mm, suid_dumpable);
 		task->pdeath_signal = 0;
+		task->signal->pdeath_signal_proc = 0;
 		smp_wmb();
 	}
 
diff --git a/kernel/exit.c b/kernel/exit.c
index c3c7ac560114..63f7cea6456e 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -635,6 +635,10 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 	if (unlikely(p->exit_state == EXIT_DEAD))
 		return;
 
+	if (p->signal->pdeath_signal_proc)
+		group_send_sig_info(p->signal->pdeath_signal_proc,
+				    SEND_SIG_NOINFO, p);
+
 	/* We don't want people slaying init. */
 	p->exit_signal = SIGCHLD;
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 242c8c93d285..3398037de1cb 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -216,10 +216,9 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
 		if (!s)
 			continue;
 
-#ifdef CONFIG_DEBUG_KMEMLEAK
 		/* Clear stale pointers from reused stack. */
 		memset(s->addr, 0, THREAD_SIZE);
-#endif
+
 		tsk->stack_vm_area = s;
 		return s->addr;
 	}
@@ -1471,6 +1470,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 
 	mutex_init(&sig->cred_guard_mutex);
 
+	sig->pdeath_signal_proc = current->signal->pdeath_signal_proc;
+
 	return 0;
 }
 
diff --git a/kernel/sys.c b/kernel/sys.c
index ad692183dfe9..f1b4c598f810 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2265,6 +2265,17 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_GET_PDEATHSIG:
 		error = put_user(me->pdeath_signal, (int __user *)arg2);
 		break;
+	case PR_SET_PDEATHSIG_PROC:
+		if (!valid_signal(arg2)) {
+			error = -EINVAL;
+			break;
+		}
+		me->signal->pdeath_signal_proc = arg2;
+		break;
+	case PR_GET_PDEATHSIG_PROC:
+		error = put_user(me->signal->pdeath_signal_proc,
+				 (int __user *)arg2);
+		break;
 	case PR_GET_DUMPABLE:
 		error = get_dumpable(me->mm);
 		break;
diff --git a/lib/reed_solomon/decode_rs.c b/lib/reed_solomon/decode_rs.c
index 0ec3f257ffdf..3e3becb836a6 100644
--- a/lib/reed_solomon/decode_rs.c
+++ b/lib/reed_solomon/decode_rs.c
@@ -31,9 +31,10 @@
 	 * of nroots is 8. So the necessary stack size will be about
 	 * 220 bytes max.
 	 */
-	uint16_t lambda[nroots + 1], syn[nroots];
-	uint16_t b[nroots + 1], t[nroots + 1], omega[nroots + 1];
-	uint16_t root[nroots], reg[nroots + 1], loc[nroots];
+	uint16_t lambda[RS_MAX_ROOTS + 1], syn[RS_MAX_ROOTS];
+	uint16_t b[RS_MAX_ROOTS + 1], t[RS_MAX_ROOTS + 1];
+	uint16_t omega[RS_MAX_ROOTS + 1], root[RS_MAX_ROOTS];
+	uint16_t reg[RS_MAX_ROOTS + 1], loc[RS_MAX_ROOTS];
 	int count = 0;
 	uint16_t msk = (uint16_t) rs->nn;
 
diff --git a/lib/reed_solomon/reed_solomon.c b/lib/reed_solomon/reed_solomon.c
index 06d04cfa9339..3e218e70ac2e 100644
--- a/lib/reed_solomon/reed_solomon.c
+++ b/lib/reed_solomon/reed_solomon.c
@@ -51,6 +51,9 @@ static LIST_HEAD (rslist);
 /* Protection for the list */
 static DEFINE_MUTEX(rslistlock);
 
+/* Ultimately controls the upper bounds of the on-stack buffers. */
+#define RS_MAX_ROOTS	24
+
 /**
  * rs_init - Initialize a Reed-Solomon codec
  * @symsize:	symbol size, bits (1-8)
@@ -210,7 +213,7 @@ static struct rs_control *init_rs_internal(int symsize, int gfpoly,
     		return NULL;
 	if (prim <= 0 || prim >= (1<<symsize))
     		return NULL;
-	if (nroots < 0 || nroots >= (1<<symsize))
+	if (nroots < 0 || nroots >= (1<<symsize) || nroots > RS_MAX_ROOTS)
 		return NULL;
 
 	mutex_lock(&rslistlock);
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 023190c69dce..2fc3f38e4c4f 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -220,11 +220,46 @@ static ssize_t stable_pages_required_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(stable_pages_required);
 
+static ssize_t strictlimit_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+	unsigned int val;
+	ssize_t ret;
+
+	ret = kstrtouint(buf, 10, &val);
+	if (ret < 0)
+		return ret;
+
+	switch (val) {
+	case 0:
+		bdi->capabilities &= ~BDI_CAP_STRICTLIMIT;
+		break;
+	case 1:
+		bdi->capabilities |= BDI_CAP_STRICTLIMIT;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return count;
+}
+static ssize_t strictlimit_show(struct device *dev,
+		struct device_attribute *attr, char *page)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+
+	return snprintf(page, PAGE_SIZE-1, "%d\n",
+			!!(bdi->capabilities & BDI_CAP_STRICTLIMIT));
+}
+static DEVICE_ATTR_RW(strictlimit);
+
 static struct attribute *bdi_dev_attrs[] = {
 	&dev_attr_read_ahead_kb.attr,
 	&dev_attr_min_ratio.attr,
 	&dev_attr_max_ratio.attr,
 	&dev_attr_stable_pages_required.attr,
+	&dev_attr_strictlimit.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(bdi_dev);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 3e8cda7beb7f..323acdd14e6e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2925,7 +2925,10 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
 		pmde = maybe_pmd_mkwrite(pmde, vma);
 
 	flush_cache_range(vma, mmun_start, mmun_start + HPAGE_PMD_SIZE);
-	page_add_anon_rmap(new, vma, mmun_start, true);
+	if (PageAnon(new))
+		page_add_anon_rmap(new, vma, mmun_start, true);
+	else
+		page_add_file_rmap(new, true);
 	set_pmd_at(mm, mmun_start, pvmw->pmd, pmde);
 	if (vma->vm_flags & VM_LOCKED)
 		mlock_vma_page(new);
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index bc0e68f7dc75..135ce2838c89 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -792,6 +792,41 @@ DEFINE_ASAN_SET_SHADOW(f5);
 DEFINE_ASAN_SET_SHADOW(f8);
 
 #ifdef CONFIG_MEMORY_HOTPLUG
+static bool shadow_mapped(unsigned long addr)
+{
+	pgd_t *pgd = pgd_offset_k(addr);
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	if (pgd_none(*pgd))
+		return false;
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none(*p4d))
+		return false;
+	pud = pud_offset(p4d, addr);
+	if (pud_none(*pud))
+		return false;
+
+	/*
+	 * We can't use pud_large() or pud_huge(), the first one
+	 * is arch-specific, the last one depend on HUGETLB_PAGE.
+	 * So let's abuse pud_bad(), if bud is bad it's has to
+	 * because it's huge.
+	 */
+	if (pud_bad(*pud))
+		return true;
+	pmd = pmd_offset(pud, addr);
+	if (pmd_none(*pmd))
+		return false;
+
+	if (pmd_bad(*pmd))
+		return true;
+	pte = pte_offset_kernel(pmd, addr);
+	return !pte_none(*pte);
+}
+
 static int __meminit kasan_mem_notifier(struct notifier_block *nb,
 			unsigned long action, void *data)
 {
@@ -813,6 +848,14 @@ static int __meminit kasan_mem_notifier(struct notifier_block *nb,
 	case MEM_GOING_ONLINE: {
 		void *ret;
 
+		/*
+		 * If shadow is mapped already than it must have been mapped
+		 * during the boot. This could happen if we onlining previously
+		 * offlined memory.
+		 */
+		if (shadow_mapped(shadow_start))
+			return NOTIFY_OK;
+
 		ret = __vmalloc_node_range(shadow_size, PAGE_SIZE, shadow_start,
 					shadow_end, GFP_KERNEL,
 					PAGE_KERNEL, VM_NO_GUARD,
@@ -824,8 +867,18 @@ static int __meminit kasan_mem_notifier(struct notifier_block *nb,
 		kmemleak_ignore(ret);
 		return NOTIFY_OK;
 	}
-	case MEM_OFFLINE:
-		vfree((void *)shadow_start);
+	case MEM_OFFLINE: {
+		struct vm_struct *vm;
+
+		/*
+		 * Only hot-added memory have vm_area. Freeing shadow
+		 * mapped during boot would be tricky, so we'll just
+		 * have to keep it.
+		 */
+		vm = find_vm_area((void *)shadow_start);
+		if (vm)
+			vfree((void *)shadow_start);
+	}
 	}
 
 	return NOTIFY_OK;
diff --git a/mm/list_lru.c b/mm/list_lru.c
index fcfb6c89ed47..d9c84c5bda1d 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/list_lru.h>
+#include <linux/prefetch.h>
 #include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/memcontrol.h>
@@ -133,6 +134,12 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item)
 	struct list_lru_node *nlru = &lru->node[nid];
 	struct list_lru_one *l;
 
+	/*
+	 * Prefetch the neighboring list entries to reduce lock hold time.
+	 */
+	prefetchw(item->prev);
+	prefetchw(item->next);
+
 	spin_lock(&nlru->lock);
 	if (!list_empty(item)) {
 		l = list_lru_from_kmem(nlru, item);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e074f7c637aa..d455bc08eb55 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -888,7 +888,8 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
  * value, the function breaks the iteration loop and returns the value.
  * Otherwise, it will iterate over all tasks and return 0.
  *
- * This function must not be called for the root memory cgroup.
+ * If memcg is the root memory cgroup, this function will iterate only
+ * over tasks belonging directly to the root memory cgroup.
  */
 int mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
 			  int (*fn)(struct task_struct *, void *), void *arg)
@@ -896,8 +897,6 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
 	struct mem_cgroup *iter;
 	int ret = 0;
 
-	BUG_ON(memcg == root_mem_cgroup);
-
 	for_each_mem_cgroup_tree(iter, memcg) {
 		struct css_task_iter it;
 		struct task_struct *task;
@@ -906,7 +905,7 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
 		while (!ret && (task = css_task_iter_next(&it)))
 			ret = fn(task, arg);
 		css_task_iter_end(&it);
-		if (ret) {
+		if (ret || memcg == root_mem_cgroup) {
 			mem_cgroup_iter_break(memcg, iter);
 			break;
 		}
@@ -2592,6 +2591,224 @@ static inline bool memcg_has_children(struct mem_cgroup *memcg)
 	return ret;
 }
 
+static long memcg_oom_badness(struct mem_cgroup *memcg,
+			      const nodemask_t *nodemask,
+			      unsigned long totalpages)
+{
+	long points = 0;
+	int nid;
+	pg_data_t *pgdat;
+
+	for_each_node_state(nid, N_MEMORY) {
+		if (nodemask && !node_isset(nid, *nodemask))
+			continue;
+
+		points += mem_cgroup_node_nr_lru_pages(memcg, nid,
+				LRU_ALL_ANON | BIT(LRU_UNEVICTABLE));
+
+		pgdat = NODE_DATA(nid);
+		points += lruvec_page_state(mem_cgroup_lruvec(pgdat, memcg),
+					    NR_SLAB_UNRECLAIMABLE);
+	}
+
+	points += memcg_page_state(memcg, MEMCG_KERNEL_STACK_KB) /
+		(PAGE_SIZE / 1024);
+	points += memcg_page_state(memcg, MEMCG_SOCK);
+	points += memcg_page_state(memcg, MEMCG_SWAP);
+
+	return points;
+}
+
+/*
+ * Checks if the given memcg is a valid OOM victim and returns a number,
+ * which means the folowing:
+ *   -1: there are inflight OOM victim tasks, belonging to the memcg
+ *    0: memcg is not eligible, e.g. all belonging tasks are protected
+ *       by oom_score_adj set to OOM_SCORE_ADJ_MIN
+ *   >0: memcg is eligible, and the returned value is an estimation
+ *       of the memory footprint
+ */
+static long oom_evaluate_memcg(struct mem_cgroup *memcg,
+			       const nodemask_t *nodemask,
+			       unsigned long totalpages)
+{
+	struct css_task_iter it;
+	struct task_struct *task;
+	int eligible = 0;
+
+	/*
+	 * Root memory cgroup is a special case:
+	 * we don't have necessary stats to evaluate it exactly as
+	 * leaf memory cgroups, so we approximate it's oom_score
+	 * by summing oom_score of all belonging tasks, which are
+	 * owners of their mm structs.
+	 *
+	 * If there are inflight OOM victim tasks inside
+	 * the root memcg, we return -1.
+	 */
+	if (memcg == root_mem_cgroup) {
+		struct css_task_iter it;
+		struct task_struct *task;
+		long score = 0;
+
+		css_task_iter_start(&memcg->css, 0, &it);
+		while ((task = css_task_iter_next(&it))) {
+			if (tsk_is_oom_victim(task) &&
+			    !test_bit(MMF_OOM_SKIP,
+				      &task->signal->oom_mm->flags)) {
+				score = -1;
+				break;
+			}
+
+			task_lock(task);
+			if (!task->mm || task->mm->owner != task) {
+				task_unlock(task);
+				continue;
+			}
+			task_unlock(task);
+
+			score += oom_badness(task, memcg, nodemask,
+					     totalpages);
+		}
+		css_task_iter_end(&it);
+
+		return score;
+	}
+
+	/*
+	 * Memcg is OOM eligible if there are OOM killable tasks inside.
+	 *
+	 * We treat tasks with oom_score_adj set to OOM_SCORE_ADJ_MIN
+	 * as unkillable.
+	 *
+	 * If there are inflight OOM victim tasks inside the memcg,
+	 * we return -1.
+	 */
+	css_task_iter_start(&memcg->css, 0, &it);
+	while ((task = css_task_iter_next(&it))) {
+		if (!eligible &&
+		    task->signal->oom_score_adj != OOM_SCORE_ADJ_MIN)
+			eligible = 1;
+
+		if (tsk_is_oom_victim(task) &&
+		    !test_bit(MMF_OOM_SKIP, &task->signal->oom_mm->flags)) {
+			eligible = -1;
+			break;
+		}
+	}
+	css_task_iter_end(&it);
+
+	if (eligible <= 0)
+		return eligible;
+
+	return memcg_oom_badness(memcg, nodemask, totalpages);
+}
+
+static void select_victim_memcg(struct mem_cgroup *root, struct oom_control *oc)
+{
+	struct mem_cgroup *iter, *group = NULL;
+	long group_score = 0;
+
+	oc->chosen_memcg = NULL;
+	oc->chosen_points = 0;
+
+	/*
+	 * If OOM is memcg-wide, and the memcg has the oom_group flag set,
+	 * all tasks belonging to the memcg should be killed.
+	 * So, we mark the memcg as a victim.
+	 */
+	if (oc->memcg && mem_cgroup_oom_group(oc->memcg)) {
+		oc->chosen_memcg = oc->memcg;
+		css_get(&oc->chosen_memcg->css);
+		return;
+	}
+
+	/*
+	 * The oom_score is calculated for leaf memory cgroups (including
+	 * the root memcg).
+	 * Non-leaf oom_group cgroups accumulating score of descendant
+	 * leaf memory cgroups.
+	 */
+	rcu_read_lock();
+	for_each_mem_cgroup_tree(iter, root) {
+		long score;
+
+		/*
+		 * We don't consider non-leaf non-oom_group memory cgroups
+		 * as OOM victims.
+		 */
+		if (memcg_has_children(iter) && iter != root_mem_cgroup &&
+		    !mem_cgroup_oom_group(iter))
+			continue;
+
+		/*
+		 * If group is not set or we've ran out of the group's sub-tree,
+		 * we should set group and reset group_score.
+		 */
+		if (!group || group == root_mem_cgroup ||
+		    !mem_cgroup_is_descendant(iter, group)) {
+			group = iter;
+			group_score = 0;
+		}
+
+		if (memcg_has_children(iter) && iter != root_mem_cgroup)
+			continue;
+
+		score = oom_evaluate_memcg(iter, oc->nodemask, oc->totalpages);
+
+		/*
+		 * Ignore empty and non-eligible memory cgroups.
+		 */
+		if (score == 0)
+			continue;
+
+		/*
+		 * If there are inflight OOM victims, we don't need
+		 * to look further for new victims.
+		 */
+		if (score == -1) {
+			oc->chosen_memcg = INFLIGHT_VICTIM;
+			mem_cgroup_iter_break(root, iter);
+			break;
+		}
+
+		group_score += score;
+
+		if (group_score > oc->chosen_points) {
+			oc->chosen_points = group_score;
+			oc->chosen_memcg = group;
+		}
+	}
+
+	if (oc->chosen_memcg && oc->chosen_memcg != INFLIGHT_VICTIM)
+		css_get(&oc->chosen_memcg->css);
+
+	rcu_read_unlock();
+}
+
+bool mem_cgroup_select_oom_victim(struct oom_control *oc)
+{
+	struct mem_cgroup *root;
+
+	if (mem_cgroup_disabled())
+		return false;
+
+	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
+		return false;
+
+	if (!(cgrp_dfl_root.flags & CGRP_GROUP_OOM))
+		return false;
+
+	if (oc->memcg)
+		root = oc->memcg;
+	else
+		root = root_mem_cgroup;
+
+	select_victim_memcg(root, oc);
+
+	return oc->chosen_memcg;
+}
+
 /*
  * Reclaims as many pages from the given memcg as possible.
  *
@@ -4031,6 +4248,14 @@ static struct cftype mem_cgroup_legacy_files[] = {
 
 static DEFINE_IDR(mem_cgroup_idr);
 
+static void mem_cgroup_id_remove(struct mem_cgroup *memcg)
+{
+	if (memcg->id.id > 0) {
+		idr_remove(&mem_cgroup_idr, memcg->id.id);
+		memcg->id.id = 0;
+	}
+}
+
 static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n)
 {
 	VM_BUG_ON(atomic_read(&memcg->id.ref) <= 0);
@@ -4041,8 +4266,7 @@ static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n)
 {
 	VM_BUG_ON(atomic_read(&memcg->id.ref) < n);
 	if (atomic_sub_and_test(n, &memcg->id.ref)) {
-		idr_remove(&mem_cgroup_idr, memcg->id.id);
-		memcg->id.id = 0;
+		mem_cgroup_id_remove(memcg);
 
 		/* Memcg ID pins CSS */
 		css_put(&memcg->css);
@@ -4179,8 +4403,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	idr_replace(&mem_cgroup_idr, memcg, memcg->id.id);
 	return memcg;
 fail:
-	if (memcg->id.id > 0)
-		idr_remove(&mem_cgroup_idr, memcg->id.id);
+	mem_cgroup_id_remove(memcg);
 	__mem_cgroup_free(memcg);
 	return NULL;
 }
@@ -4239,6 +4462,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 
 	return &memcg->css;
 fail:
+	mem_cgroup_id_remove(memcg);
 	mem_cgroup_free(memcg);
 	return ERR_PTR(-ENOMEM);
 }
@@ -5190,6 +5414,39 @@ static ssize_t memory_max_write(struct kernfs_open_file *of,
 	return nbytes;
 }
 
+static int memory_oom_group_show(struct seq_file *m, void *v)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+	bool oom_group = memcg->oom_group;
+
+	if (!(cgrp_dfl_root.flags & CGRP_GROUP_OOM))
+		return -ENOTSUPP;
+
+	seq_printf(m, "%d\n", oom_group);
+
+	return 0;
+}
+
+static ssize_t memory_oom_group_write(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes,
+				      loff_t off)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
+	int oom_group;
+	int err;
+
+	if (!(cgrp_dfl_root.flags & CGRP_GROUP_OOM))
+		return -ENOTSUPP;
+
+	err = kstrtoint(strstrip(buf), 0, &oom_group);
+	if (err)
+		return err;
+
+	memcg->oom_group = oom_group;
+
+	return nbytes;
+}
+
 static int memory_events_show(struct seq_file *m, void *v)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
@@ -5314,6 +5571,12 @@ static struct cftype memory_files[] = {
 		.write = memory_max_write,
 	},
 	{
+		.name = "oom_group",
+		.flags = CFTYPE_NOT_ON_ROOT | CFTYPE_NS_DELEGATABLE,
+		.seq_show = memory_oom_group_show,
+		.write = memory_oom_group_write,
+	},
+	{
 		.name = "events",
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.file_offset = offsetof(struct mem_cgroup, events_file),
diff --git a/mm/memory.c b/mm/memory.c
index 01f5464e0fd2..a1f990e33e38 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2925,7 +2925,7 @@ int do_swap_page(struct vm_fault *vmf)
 		struct swap_info_struct *si = swp_swap_info(entry);
 
 		if (si->flags & SWP_SYNCHRONOUS_IO &&
-				__swap_count(si, entry) == 1) {
+				__swap_count(entry) == 1) {
 			/* skip swapcache */
 			page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma,
 							vmf->address);
@@ -3035,7 +3035,6 @@ int do_swap_page(struct vm_fault *vmf)
 	flush_icache_page(vma, page);
 	if (pte_swp_soft_dirty(vmf->orig_pte))
 		pte = pte_mksoft_dirty(pte);
-	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
 	arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte);
 	vmf->orig_pte = pte;
 
@@ -3049,6 +3048,7 @@ int do_swap_page(struct vm_fault *vmf)
 		mem_cgroup_commit_charge(page, memcg, true, false);
 		activate_page(page);
 	}
+	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
 
 	swap_free(entry);
 	if (mem_cgroup_swap_full(page) ||
diff --git a/mm/migrate.c b/mm/migrate.c
index f65dd69e1fd1..bb6367d70a3e 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -472,7 +472,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
 	pslot = radix_tree_lookup_slot(&mapping->i_pages,
  					page_index(page));
 
-	expected_count += 1 + page_has_private(page);
+	expected_count += hpage_nr_pages(page) + page_has_private(page);
 	if (page_count(page) != expected_count ||
 		radix_tree_deref_slot_protected(pslot,
 					&mapping->i_pages.xa_lock) != page) {
@@ -505,7 +505,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
 	 */
 	newpage->index = page->index;
 	newpage->mapping = page->mapping;
-	get_page(newpage);	/* add cache reference */
+	page_ref_add(newpage, hpage_nr_pages(page)); /* add cache reference */
 	if (PageSwapBacked(page)) {
 		__SetPageSwapBacked(newpage);
 		if (PageSwapCache(page)) {
@@ -524,13 +524,26 @@ int migrate_page_move_mapping(struct address_space *mapping,
 	}
 
 	radix_tree_replace_slot(&mapping->i_pages, pslot, newpage);
+	if (PageTransHuge(page)) {
+		int i;
+		int index = page_index(page);
+
+		for (i = 0; i < HPAGE_PMD_NR; i++) {
+			pslot = radix_tree_lookup_slot(&mapping->i_pages,
+						       index + i);
+			radix_tree_replace_slot(&mapping->i_pages, pslot,
+						newpage + i);
+		}
+	} else {
+		radix_tree_replace_slot(&mapping->i_pages, pslot, newpage);
+	}
 
 	/*
 	 * Drop cache reference from old page by unfreezing
 	 * to one less reference.
 	 * We know this isn't the last reference.
 	 */
-	page_ref_unfreeze(page, expected_count - 1);
+	page_ref_unfreeze(page, expected_count - hpage_nr_pages(page));
 
 	xa_unlock(&mapping->i_pages);
 	/* Leave irq disabled to prevent preemption while updating stats */
diff --git a/mm/mincore.c b/mm/mincore.c
index fc37afe226e6..a66f2052c7b1 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -68,8 +68,16 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
 		 */
 		if (radix_tree_exceptional_entry(page)) {
 			swp_entry_t swp = radix_to_swp_entry(page);
-			page = find_get_page(swap_address_space(swp),
-					     swp_offset(swp));
+			struct swap_info_struct *si;
+
+			/* Prevent swap device to being swapoff under us */
+			si = get_swap_device(swp);
+			if (si) {
+				page = find_get_page(swap_address_space(swp),
+						     swp_offset(swp));
+				put_swap_device(si);
+			} else
+				page = NULL;
 		}
 	} else
 		page = find_get_page(mapping, pgoff);
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index ff992fa8760a..dfd370526909 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -304,7 +304,7 @@ static enum oom_constraint constrained_alloc(struct oom_control *oc)
 	return CONSTRAINT_NONE;
 }
 
-static int oom_evaluate_task(struct task_struct *task, void *arg)
+int oom_evaluate_task(struct task_struct *task, void *arg)
 {
 	struct oom_control *oc = arg;
 	unsigned long points;
@@ -338,26 +338,26 @@ static int oom_evaluate_task(struct task_struct *task, void *arg)
 		goto next;
 
 	/* Prefer thread group leaders for display purposes */
-	if (points == oc->chosen_points && thread_group_leader(oc->chosen))
+	if (points == oc->chosen_points && thread_group_leader(oc->chosen_task))
 		goto next;
 select:
-	if (oc->chosen)
-		put_task_struct(oc->chosen);
+	if (oc->chosen_task)
+		put_task_struct(oc->chosen_task);
 	get_task_struct(task);
-	oc->chosen = task;
+	oc->chosen_task = task;
 	oc->chosen_points = points;
 next:
 	return 0;
 abort:
-	if (oc->chosen)
-		put_task_struct(oc->chosen);
-	oc->chosen = (void *)-1UL;
+	if (oc->chosen_task)
+		put_task_struct(oc->chosen_task);
+	oc->chosen_task = INFLIGHT_VICTIM;
 	return 1;
 }
 
 /*
  * Simple selection loop. We choose the process with the highest number of
- * 'points'. In case scan was aborted, oc->chosen is set to -1.
+ * 'points'. In case scan was aborted, oc->chosen_task is set to -1.
  */
 static void select_bad_process(struct oom_control *oc)
 {
@@ -830,67 +830,22 @@ static bool task_will_free_mem(struct task_struct *task)
 	return ret;
 }
 
-static void oom_kill_process(struct oom_control *oc, const char *message)
+static void __oom_kill_process(struct task_struct *victim)
 {
-	struct task_struct *p = oc->chosen;
-	unsigned int points = oc->chosen_points;
-	struct task_struct *victim = p;
-	struct task_struct *child;
-	struct task_struct *t;
+	struct task_struct *p;
 	struct mm_struct *mm;
-	unsigned int victim_points = 0;
-	static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
-					      DEFAULT_RATELIMIT_BURST);
 	bool can_oom_reap = true;
 
 	/*
-	 * If the task is already exiting, don't alarm the sysadmin or kill
-	 * its children or threads, just give it access to memory reserves
-	 * so it can die quickly
+	 * __oom_kill_process() is used to kill all tasks belonging to
+	 * the selected memory cgroup, so we should check that we're not
+	 * trying to kill an unkillable task.
 	 */
-	task_lock(p);
-	if (task_will_free_mem(p)) {
-		mark_oom_victim(p);
-		wake_oom_reaper(p);
-		task_unlock(p);
-		put_task_struct(p);
+	if (is_global_init(victim) || (victim->flags & PF_KTHREAD) ||
+	    victim->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
+		put_task_struct(victim);
 		return;
 	}
-	task_unlock(p);
-
-	if (__ratelimit(&oom_rs))
-		dump_header(oc, p);
-
-	pr_err("%s: Kill process %d (%s) score %u or sacrifice child\n",
-		message, task_pid_nr(p), p->comm, points);
-
-	/*
-	 * If any of p's children has a different mm and is eligible for kill,
-	 * the one with the highest oom_badness() score is sacrificed for its
-	 * parent.  This attempts to lose the minimal amount of work done while
-	 * still freeing memory.
-	 */
-	read_lock(&tasklist_lock);
-	for_each_thread(p, t) {
-		list_for_each_entry(child, &t->children, sibling) {
-			unsigned int child_points;
-
-			if (process_shares_mm(child, p->mm))
-				continue;
-			/*
-			 * oom_badness() returns 0 if the thread is unkillable
-			 */
-			child_points = oom_badness(child,
-				oc->memcg, oc->nodemask, oc->totalpages);
-			if (child_points > victim_points) {
-				put_task_struct(victim);
-				victim = child;
-				victim_points = child_points;
-				get_task_struct(victim);
-			}
-		}
-	}
-	read_unlock(&tasklist_lock);
 
 	p = find_lock_task_mm(victim);
 	if (!p) {
@@ -965,6 +920,108 @@ static void oom_kill_process(struct oom_control *oc, const char *message)
 }
 #undef K
 
+static void oom_kill_process(struct oom_control *oc, const char *message)
+{
+	struct task_struct *p = oc->chosen_task;
+	unsigned int points = oc->chosen_points;
+	struct task_struct *victim = p;
+	struct task_struct *child;
+	struct task_struct *t;
+	unsigned int victim_points = 0;
+	static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
+					      DEFAULT_RATELIMIT_BURST);
+
+	/*
+	 * If the task is already exiting, don't alarm the sysadmin or kill
+	 * its children or threads, just give it access to memory reserves
+	 * so it can die quickly
+	 */
+	task_lock(p);
+	if (task_will_free_mem(p)) {
+		mark_oom_victim(p);
+		wake_oom_reaper(p);
+		task_unlock(p);
+		put_task_struct(p);
+		return;
+	}
+	task_unlock(p);
+
+	if (__ratelimit(&oom_rs))
+		dump_header(oc, p);
+
+	pr_err("%s: Kill process %d (%s) score %u or sacrifice child\n",
+		message, task_pid_nr(p), p->comm, points);
+
+	/*
+	 * If any of p's children has a different mm and is eligible for kill,
+	 * the one with the highest oom_badness() score is sacrificed for its
+	 * parent.  This attempts to lose the minimal amount of work done while
+	 * still freeing memory.
+	 */
+	read_lock(&tasklist_lock);
+	for_each_thread(p, t) {
+		list_for_each_entry(child, &t->children, sibling) {
+			unsigned int child_points;
+
+			if (process_shares_mm(child, p->mm))
+				continue;
+			/*
+			 * oom_badness() returns 0 if the thread is unkillable
+			 */
+			child_points = oom_badness(child,
+				oc->memcg, oc->nodemask, oc->totalpages);
+			if (child_points > victim_points) {
+				put_task_struct(victim);
+				victim = child;
+				victim_points = child_points;
+				get_task_struct(victim);
+			}
+		}
+	}
+	read_unlock(&tasklist_lock);
+
+	__oom_kill_process(victim);
+}
+
+static int oom_kill_memcg_member(struct task_struct *task, void *unused)
+{
+	get_task_struct(task);
+	__oom_kill_process(task);
+	return 0;
+}
+
+static bool oom_kill_memcg_victim(struct oom_control *oc)
+{
+	if (oc->chosen_memcg == NULL || oc->chosen_memcg == INFLIGHT_VICTIM)
+		return oc->chosen_memcg;
+
+	/*
+	 * If memory.oom_group is set, kill all tasks belonging to the sub-tree
+	 * of the chosen memory cgroup, otherwise kill the task with the biggest
+	 * memory footprint.
+	 */
+	if (mem_cgroup_oom_group(oc->chosen_memcg)) {
+		mem_cgroup_scan_tasks(oc->chosen_memcg, oom_kill_memcg_member,
+				      NULL);
+		/* We have one or more terminating processes at this point. */
+		oc->chosen_task = INFLIGHT_VICTIM;
+	} else {
+		oc->chosen_points = 0;
+		oc->chosen_task = NULL;
+		mem_cgroup_scan_tasks(oc->chosen_memcg, oom_evaluate_task, oc);
+
+		if (oc->chosen_task == NULL ||
+		    oc->chosen_task == INFLIGHT_VICTIM)
+			goto out;
+
+		__oom_kill_process(oc->chosen_task);
+	}
+
+out:
+	mem_cgroup_put(oc->chosen_memcg);
+	return oc->chosen_task;
+}
+
 /*
  * Determines whether the kernel must panic because of the panic_on_oom sysctl.
  */
@@ -1017,6 +1074,7 @@ bool out_of_memory(struct oom_control *oc)
 {
 	unsigned long freed = 0;
 	enum oom_constraint constraint = CONSTRAINT_NONE;
+	bool delay = false; /* if set, delay next allocation attempt */
 
 	if (oom_killer_disabled)
 		return false;
@@ -1061,27 +1119,37 @@ bool out_of_memory(struct oom_control *oc)
 	    current->mm && !oom_unkillable_task(current, NULL, oc->nodemask) &&
 	    current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) {
 		get_task_struct(current);
-		oc->chosen = current;
+		oc->chosen_task = current;
 		oom_kill_process(oc, "Out of memory (oom_kill_allocating_task)");
 		return true;
 	}
 
+	if (mem_cgroup_select_oom_victim(oc) && oom_kill_memcg_victim(oc)) {
+		delay = true;
+		goto out;
+	}
+
 	select_bad_process(oc);
 	/* Found nothing?!?! Either we hang forever, or we panic. */
-	if (!oc->chosen && !is_sysrq_oom(oc) && !is_memcg_oom(oc)) {
+	if (!oc->chosen_task && !is_sysrq_oom(oc) && !is_memcg_oom(oc)) {
 		dump_header(oc, NULL);
 		panic("Out of memory and no killable processes...\n");
 	}
-	if (oc->chosen && oc->chosen != (void *)-1UL) {
+	if (oc->chosen_task && oc->chosen_task != INFLIGHT_VICTIM) {
 		oom_kill_process(oc, !is_memcg_oom(oc) ? "Out of memory" :
 				 "Memory cgroup out of memory");
-		/*
-		 * Give the killed process a good chance to exit before trying
-		 * to allocate memory again.
-		 */
-		schedule_timeout_killable(1);
+		delay = true;
 	}
-	return !!oc->chosen;
+
+out:
+	/*
+	 * Give the killed process a good chance to exit before trying
+	 * to allocate memory again.
+	 */
+	if (delay)
+		schedule_timeout_killable(1);
+
+	return !!oc->chosen_task;
 }
 
 /*
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 5c1a3279e63f..337c6afb3345 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2502,13 +2502,13 @@ void account_page_redirty(struct page *page)
 	if (mapping && mapping_cap_account_dirty(mapping)) {
 		struct inode *inode = mapping->host;
 		struct bdi_writeback *wb;
-		bool locked;
+		struct wb_lock_cookie cookie = {};
 
-		wb = unlocked_inode_to_wb_begin(inode, &locked);
+		wb = unlocked_inode_to_wb_begin(inode, &cookie);
 		current->nr_dirtied--;
 		dec_node_page_state(page, NR_DIRTIED);
 		dec_wb_stat(wb, WB_DIRTIED);
-		unlocked_inode_to_wb_end(inode, locked);
+		unlocked_inode_to_wb_end(inode, &cookie);
 	}
 }
 EXPORT_SYMBOL(account_page_redirty);
@@ -2614,15 +2614,15 @@ void __cancel_dirty_page(struct page *page)
 	if (mapping_cap_account_dirty(mapping)) {
 		struct inode *inode = mapping->host;
 		struct bdi_writeback *wb;
-		bool locked;
+		struct wb_lock_cookie cookie = {};
 
 		lock_page_memcg(page);
-		wb = unlocked_inode_to_wb_begin(inode, &locked);
+		wb = unlocked_inode_to_wb_begin(inode, &cookie);
 
 		if (TestClearPageDirty(page))
 			account_page_cleaned(page, mapping, wb);
 
-		unlocked_inode_to_wb_end(inode, locked);
+		unlocked_inode_to_wb_end(inode, &cookie);
 		unlock_page_memcg(page);
 	} else {
 		ClearPageDirty(page);
@@ -2654,7 +2654,7 @@ int clear_page_dirty_for_io(struct page *page)
 	if (mapping && mapping_cap_account_dirty(mapping)) {
 		struct inode *inode = mapping->host;
 		struct bdi_writeback *wb;
-		bool locked;
+		struct wb_lock_cookie cookie = {};
 
 		/*
 		 * Yes, Virginia, this is indeed insane.
@@ -2691,14 +2691,14 @@ int clear_page_dirty_for_io(struct page *page)
 		 * always locked coming in here, so we get the desired
 		 * exclusion.
 		 */
-		wb = unlocked_inode_to_wb_begin(inode, &locked);
+		wb = unlocked_inode_to_wb_begin(inode, &cookie);
 		if (TestClearPageDirty(page)) {
 			dec_lruvec_page_state(page, NR_FILE_DIRTY);
 			dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
 			dec_wb_stat(wb, WB_RECLAIMABLE);
 			ret = 1;
 		}
-		unlocked_inode_to_wb_end(inode, locked);
+		unlocked_inode_to_wb_end(inode, &cookie);
 		return ret;
 	}
 	return TestClearPageDirty(page);
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 75d21a2259b3..77d9e791ae8a 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -274,7 +274,7 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 	 */
 	for (; pfn < end_pfn; ) {
 		if (!pfn_valid(pfn)) {
-			pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES);
+			pfn = ALIGN(pfn + 1, pageblock_nr_pages);
 			continue;
 		}
 
@@ -541,7 +541,7 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone)
 		unsigned long block_end_pfn;
 
 		if (!pfn_valid(pfn)) {
-			pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES);
+			pfn = ALIGN(pfn + 1, pageblock_nr_pages);
 			continue;
 		}
 
diff --git a/mm/rmap.c b/mm/rmap.c
index 056213326651..6db729dc4c50 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1374,9 +1374,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 		if (!pvmw.pte && (flags & TTU_MIGRATION)) {
 			VM_BUG_ON_PAGE(PageHuge(page) || !PageTransCompound(page), page);
 
-			if (!PageAnon(page))
-				continue;
-
 			set_pmd_migration_entry(&pvmw, page);
 			continue;
 		}
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index bd0276d5f66b..640e68f8324b 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -303,7 +303,6 @@ void __init sparse_mem_maps_populate_node(struct page **map_map,
 		ms = __nr_to_section(pnum);
 		pr_err("%s: sparsemem memory map backing failed some memory will not be available\n",
 		       __func__);
-		ms->section_mem_map = 0;
 	}
 
 	if (vmemmap_buf_start) {
diff --git a/mm/sparse.c b/mm/sparse.c
index 62eef264a7bd..4a58f8809542 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -202,6 +202,12 @@ static inline int next_present_section_nr(int section_nr)
 	      (section_nr <= __highest_present_section_nr));	\
 	     section_nr = next_present_section_nr(section_nr))
 
+/*
+ * Record how many memory sections are marked as present
+ * during system bootup.
+ */
+static int __initdata nr_present_sections;
+
 /* Record a memory area against a node. */
 void __init memory_present(int nid, unsigned long start, unsigned long end)
 {
@@ -231,6 +237,7 @@ void __init memory_present(int nid, unsigned long start, unsigned long end)
 			ms->section_mem_map = sparse_encode_early_nid(nid) |
 							SECTION_IS_ONLINE;
 			section_mark_present(ms);
+			nr_present_sections++;
 		}
 	}
 }
@@ -446,7 +453,6 @@ void __init sparse_mem_maps_populate_node(struct page **map_map,
 		ms = __nr_to_section(pnum);
 		pr_err("%s: sparsemem memory map backing failed some memory will not be available\n",
 		       __func__);
-		ms->section_mem_map = 0;
 	}
 }
 #endif /* !CONFIG_SPARSEMEM_VMEMMAP */
@@ -474,7 +480,6 @@ static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
 
 	pr_err("%s: sparsemem memory map backing failed some memory will not be available\n",
 	       __func__);
-	ms->section_mem_map = 0;
 	return NULL;
 }
 #endif
@@ -486,10 +491,12 @@ void __weak __meminit vmemmap_populate_print_last(void)
 /**
  *  alloc_usemap_and_memmap - memory alloction for pageblock flags and vmemmap
  *  @map: usemap_map for pageblock flags or mmap_map for vmemmap
+ *  @unit_size: size of map unit
  */
 static void __init alloc_usemap_and_memmap(void (*alloc_func)
 					(void *, unsigned long, unsigned long,
-					unsigned long, int), void *data)
+					unsigned long, int), void *data,
+					int data_unit_size)
 {
 	unsigned long pnum;
 	unsigned long map_count;
@@ -566,7 +573,8 @@ void __init sparse_init(void)
 	if (!usemap_map)
 		panic("can not allocate usemap_map\n");
 	alloc_usemap_and_memmap(sparse_early_usemaps_alloc_node,
-							(void *)usemap_map);
+				(void *)usemap_map,
+				sizeof(usemap_map[0]));
 
 #ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
 	size2 = sizeof(struct page *) * NR_MEM_SECTIONS;
@@ -574,21 +582,28 @@ void __init sparse_init(void)
 	if (!map_map)
 		panic("can not allocate map_map\n");
 	alloc_usemap_and_memmap(sparse_early_mem_maps_alloc_node,
-							(void *)map_map);
+				(void *)map_map,
+				sizeof(map_map[0]));
 #endif
 
 	for_each_present_section_nr(0, pnum) {
+		struct mem_section *ms;
+		ms = __nr_to_section(pnum);
 		usemap = usemap_map[pnum];
-		if (!usemap)
+		if (!usemap) {
+			ms->section_mem_map = 0;
 			continue;
+		}
 
 #ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
 		map = map_map[pnum];
 #else
 		map = sparse_early_mem_map_alloc(pnum);
 #endif
-		if (!map)
+		if (!map) {
+			ms->section_mem_map = 0;
 			continue;
+		}
 
 		sparse_init_one_section(__nr_to_section(pnum), pnum, map,
 								usemap);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 07f9aa2340c3..fe079756bb18 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -337,8 +337,13 @@ struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma,
 			       unsigned long addr)
 {
 	struct page *page;
+	struct swap_info_struct *si;
 
+	si = get_swap_device(entry);
+	if (!si)
+		return NULL;
 	page = find_get_page(swap_address_space(entry), swp_offset(entry));
+	put_swap_device(si);
 
 	INC_CACHE_INFO(find_total);
 	if (page) {
@@ -381,8 +386,8 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 			struct vm_area_struct *vma, unsigned long addr,
 			bool *new_page_allocated)
 {
-	struct page *found_page, *new_page = NULL;
-	struct address_space *swapper_space = swap_address_space(entry);
+	struct page *found_page = NULL, *new_page = NULL;
+	struct swap_info_struct *si;
 	int err;
 	*new_page_allocated = false;
 
@@ -392,7 +397,12 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		 * called after lookup_swap_cache() failed, re-calling
 		 * that would confuse statistics.
 		 */
-		found_page = find_get_page(swapper_space, swp_offset(entry));
+		si = get_swap_device(entry);
+		if (!si)
+			break;
+		found_page = find_get_page(swap_address_space(entry),
+					   swp_offset(entry));
+		put_swap_device(si);
 		if (found_page)
 			break;
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index cc2cf04d9018..5a280972bd87 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -38,6 +38,7 @@
 #include <linux/export.h>
 #include <linux/swap_slots.h>
 #include <linux/sort.h>
+#include <linux/stop_machine.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
@@ -1107,6 +1108,64 @@ static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry,
 	return p;
 }
 
+/*
+ * Check whether swap entry is valid in the swap device.  If so,
+ * return pointer to swap_info_struct, and keep the swap entry valid
+ * via preventing the swap device from being swapoff, until
+ * put_swap_device() is called.  Otherwise return NULL.
+ *
+ * Notice that swapoff or swapoff+swapon can still happen before the
+ * preempt_disable() in get_swap_device() or after the
+ * preempt_enable() in put_swap_device() if there isn't any other way
+ * to prevent swapoff, such as page lock, page table lock, etc.  The
+ * caller must be prepared for that.  For example, the following
+ * situation is possible.
+ *
+ *   CPU1				CPU2
+ *   do_swap_page()
+ *     ...				swapoff+swapon
+ *     __read_swap_cache_async()
+ *       swapcache_prepare()
+ *         __swap_duplicate()
+ *           // check swap_map
+ *     // verify PTE not changed
+ *
+ * In __swap_duplicate(), the swap_map need to be checked before
+ * changing partly because the specified swap entry may be for another
+ * swap device which has been swapoff.  And in do_swap_page(), after
+ * the page is read from the swap device, the PTE is verified not
+ * changed with the page table locked to check whether the swap device
+ * has been swapoff or swapoff+swapon.
+ */
+struct swap_info_struct *get_swap_device(swp_entry_t entry)
+{
+	struct swap_info_struct *si;
+	unsigned long type, offset;
+
+	if (!entry.val)
+		goto out;
+	type = swp_type(entry);
+	if (type >= nr_swapfiles)
+		goto bad_nofile;
+	si = swap_info[type];
+
+	preempt_disable();
+	if (!(si->flags & SWP_VALID))
+		goto unlock_out;
+	offset = swp_offset(entry);
+	if (offset >= si->max)
+		goto unlock_out;
+
+	return si;
+bad_nofile:
+	pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val);
+out:
+	return NULL;
+unlock_out:
+	preempt_enable();
+	return NULL;
+}
+
 static unsigned char __swap_entry_free(struct swap_info_struct *p,
 				       swp_entry_t entry, unsigned char usage)
 {
@@ -1328,11 +1387,18 @@ int page_swapcount(struct page *page)
 	return count;
 }
 
-int __swap_count(struct swap_info_struct *si, swp_entry_t entry)
+int __swap_count(swp_entry_t entry)
 {
+	struct swap_info_struct *si;
 	pgoff_t offset = swp_offset(entry);
+	int count = 0;
 
-	return swap_count(si->swap_map[offset]);
+	si = get_swap_device(entry);
+	if (si) {
+		count = swap_count(si->swap_map[offset]);
+		put_swap_device(si);
+	}
+	return count;
 }
 
 static int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry)
@@ -1357,9 +1423,11 @@ int __swp_swapcount(swp_entry_t entry)
 	int count = 0;
 	struct swap_info_struct *si;
 
-	si = __swap_info_get(entry);
-	if (si)
+	si = get_swap_device(entry);
+	if (si) {
 		count = swap_swapcount(si, entry);
+		put_swap_device(si);
+	}
 	return count;
 }
 
@@ -1800,8 +1868,6 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
 	inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
 	get_page(page);
-	set_pte_at(vma->vm_mm, addr, pte,
-		   pte_mkold(mk_pte(page, vma->vm_page_prot)));
 	if (page == swapcache) {
 		page_add_anon_rmap(page, vma, addr, false);
 		mem_cgroup_commit_charge(page, memcg, true, false);
@@ -1810,6 +1876,8 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		mem_cgroup_commit_charge(page, memcg, false, false);
 		lru_cache_add_active_or_unevictable(page, vma);
 	}
+	set_pte_at(vma->vm_mm, addr, pte,
+		   pte_mkold(mk_pte(page, vma->vm_page_prot)));
 	swap_free(entry);
 	/*
 	 * Move the page to the active list so it is not
@@ -2451,9 +2519,9 @@ static int swap_node(struct swap_info_struct *p)
 	return bdev ? bdev->bd_disk->node_id : NUMA_NO_NODE;
 }
 
-static void _enable_swap_info(struct swap_info_struct *p, int prio,
-				unsigned char *swap_map,
-				struct swap_cluster_info *cluster_info)
+static void setup_swap_info(struct swap_info_struct *p, int prio,
+			    unsigned char *swap_map,
+			    struct swap_cluster_info *cluster_info)
 {
 	int i;
 
@@ -2478,7 +2546,11 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio,
 	}
 	p->swap_map = swap_map;
 	p->cluster_info = cluster_info;
-	p->flags |= SWP_WRITEOK;
+}
+
+static void _enable_swap_info(struct swap_info_struct *p)
+{
+	p->flags |= SWP_WRITEOK | SWP_VALID;
 	atomic_long_add(p->pages, &nr_swap_pages);
 	total_swap_pages += p->pages;
 
@@ -2497,6 +2569,11 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio,
 	add_to_avail_list(p);
 }
 
+static int swap_onoff_stop(void *arg)
+{
+	return 0;
+}
+
 static void enable_swap_info(struct swap_info_struct *p, int prio,
 				unsigned char *swap_map,
 				struct swap_cluster_info *cluster_info,
@@ -2505,7 +2582,17 @@ static void enable_swap_info(struct swap_info_struct *p, int prio,
 	frontswap_init(p->type, frontswap_map);
 	spin_lock(&swap_lock);
 	spin_lock(&p->lock);
-	 _enable_swap_info(p, prio, swap_map, cluster_info);
+	setup_swap_info(p, prio, swap_map, cluster_info);
+	spin_unlock(&p->lock);
+	spin_unlock(&swap_lock);
+	/*
+	 * Guarantee swap_map, cluster_info, etc. fields are used
+	 * between get/put_swap_device() only if SWP_VALID bit is set
+	 */
+	stop_machine(swap_onoff_stop, NULL, cpu_online_mask);
+	spin_lock(&swap_lock);
+	spin_lock(&p->lock);
+	_enable_swap_info(p);
 	spin_unlock(&p->lock);
 	spin_unlock(&swap_lock);
 }
@@ -2514,7 +2601,8 @@ static void reinsert_swap_info(struct swap_info_struct *p)
 {
 	spin_lock(&swap_lock);
 	spin_lock(&p->lock);
-	_enable_swap_info(p, p->prio, p->swap_map, p->cluster_info);
+	setup_swap_info(p, p->prio, p->swap_map, p->cluster_info);
+	_enable_swap_info(p);
 	spin_unlock(&p->lock);
 	spin_unlock(&swap_lock);
 }
@@ -2617,6 +2705,17 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 
 	reenable_swap_slots_cache_unlock();
 
+	spin_lock(&swap_lock);
+	spin_lock(&p->lock);
+	p->flags &= ~SWP_VALID;		/* mark swap device as invalid */
+	spin_unlock(&p->lock);
+	spin_unlock(&swap_lock);
+	/*
+	 * wait for swap operations protected by get/put_swap_device()
+	 * to complete
+	 */
+	stop_machine(swap_onoff_stop, NULL, cpu_online_mask);
+
 	flush_work(&p->discard_work);
 
 	destroy_swap_extents(p);
@@ -3360,22 +3459,16 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage)
 {
 	struct swap_info_struct *p;
 	struct swap_cluster_info *ci;
-	unsigned long offset, type;
+	unsigned long offset;
 	unsigned char count;
 	unsigned char has_cache;
 	int err = -EINVAL;
 
-	if (non_swap_entry(entry))
+	p = get_swap_device(entry);
+	if (!p)
 		goto out;
 
-	type = swp_type(entry);
-	if (type >= nr_swapfiles)
-		goto bad_file;
-	p = swap_info[type];
 	offset = swp_offset(entry);
-	if (unlikely(offset >= p->max))
-		goto out;
-
 	ci = lock_cluster_or_swap_info(p, offset);
 
 	count = p->swap_map[offset];
@@ -3421,11 +3514,9 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage)
 unlock_out:
 	unlock_cluster_or_swap_info(p, ci);
 out:
+	if (p)
+		put_swap_device(p);
 	return err;
-
-bad_file:
-	pr_err("swap_dup: %s%08lx\n", Bad_file, entry.val);
-	goto out;
 }
 
 /*
@@ -3517,6 +3608,7 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
 	struct page *list_page;
 	pgoff_t offset;
 	unsigned char count;
+	int ret = 0;
 
 	/*
 	 * When debugging, it's easier to use __GFP_ZERO here; but it's better
@@ -3524,15 +3616,15 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
 	 */
 	page = alloc_page(gfp_mask | __GFP_HIGHMEM);
 
-	si = swap_info_get(entry);
+	si = get_swap_device(entry);
 	if (!si) {
 		/*
 		 * An acceptable race has occurred since the failing
-		 * __swap_duplicate(): the swap entry has been freed,
-		 * perhaps even the whole swap_map cleared for swapoff.
+		 * __swap_duplicate(): the swap device may be swapoff
 		 */
 		goto outer;
 	}
+	spin_lock(&si->lock);
 
 	offset = swp_offset(entry);
 
@@ -3550,9 +3642,8 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
 	}
 
 	if (!page) {
-		unlock_cluster(ci);
-		spin_unlock(&si->lock);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto out;
 	}
 
 	/*
@@ -3604,10 +3695,11 @@ out_unlock_cont:
 out:
 	unlock_cluster(ci);
 	spin_unlock(&si->lock);
+	put_swap_device(si);
 outer:
 	if (page)
 		__free_page(page);
-	return 0;
+	return ret;
 }
 
 /*
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index e16d6713f236..24618dffc5cb 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -6257,6 +6257,13 @@ sub process {
 			     "Avoid using bool as bitfield.  Prefer bool bitfields as unsigned int or u<8|16|32>\n" . $herecurr);
 		}
 
+# check for bool use in .h files
+		if ($realfile =~ /\.h$/ &&
+		    $sline =~ /^.\s+bool\s*$Ident\s*(?::\s*d+\s*)?;/) {
+			CHK("BOOL_MEMBER",
+			    "Avoid using bool structure members because of possible alignment issues - see: https://lkml.org/lkml/2017/11/21/384\n" . $herecurr);
+		}
+
 # check for semaphores initialized locked
 		if ($line =~ /^.\s*sema_init.+,\W?0\W?\)/) {
 			WARN("CONSIDER_COMPLETION",
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index ce2b89e9ad94..cf00c8520d30 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -693,6 +693,7 @@ static void apparmor_bprm_committing_creds(struct linux_binprm *bprm)
 	aa_inherit_files(bprm->cred, current->files);
 
 	current->pdeath_signal = 0;
+	current->signal->pdeath_signal_proc = 0;
 
 	/* reset soft limits and set hard limits for the new label */
 	__aa_transition_rlimits(label, new_label);
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 4cafe6a19167..a5acf9dae6b7 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -2641,6 +2641,7 @@ static void selinux_bprm_committing_creds(struct linux_binprm *bprm)
 
 	/* Always clear parent death signal on SID transitions. */
 	current->pdeath_signal = 0;
+	current->signal->pdeath_signal_proc = 0;
 
 	/* Check whether the new SID can inherit resource limits from the old
 	 * SID.  If not, reset all soft limits to the lower of the current