Merge branch 'akpm-current/current'

69 files changed, 1364 insertions, 570 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/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 8a2c52d5c53b..2d4c4cf72008 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -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
@@ -1069,6 +1070,31 @@ 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
@@ -1293,6 +1319,54 @@ 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/Documentation/sysctl/fs.txt b/Documentation/sysctl/fs.txt
index 6c00c1e2743f..819caf8ca05f 100644
--- a/Documentation/sysctl/fs.txt
+++ b/Documentation/sysctl/fs.txt
@@ -34,7 +34,9 @@ Currently, these files are in /proc/sys/fs:
 - overflowgid
 - pipe-user-pages-hard
 - pipe-user-pages-soft
+- protected_fifos
 - protected_hardlinks
+- protected_regular
 - protected_symlinks
 - suid_dumpable
 - super-max
@@ -182,6 +184,24 @@ applied.
 
 ==============================================================
 
+protected_fifos:
+
+The intent of this protection is to avoid unintentional writes to
+an attacker-controlled FIFO, where a program expected to create a regular
+file.
+
+When set to "0", writing to FIFOs is unrestricted.
+
+When set to "1" don't allow O_CREAT open on FIFOs that we don't own
+in world writable sticky directories, unless they are owned by the
+owner of the directory.
+
+When set to "2" it also applies to group writable sticky directories.
+
+This protection is based on the restrictions in Openwall.
+
+==============================================================
+
 protected_hardlinks:
 
 A long-standing class of security issues is the hardlink-based
@@ -202,6 +222,22 @@ This protection is based on the restrictions in Openwall and grsecurity.
 
 ==============================================================
 
+protected_regular:
+
+This protection is similar to protected_fifos, but it
+avoids writes to an attacker-controlled regular file, where a program
+expected to create one.
+
+When set to "0", writing to regular files is unrestricted.
+
+When set to "1" don't allow O_CREAT open on regular files that we
+don't own in world writable sticky directories, unless they are
+owned by the owner of the directory.
+
+When set to "2" it also applies to group writable sticky directories.
+
+==============================================================
+
 protected_symlinks:
 
 A long-standing class of security issues is the symlink-based
diff --git a/Documentation/vm/hmm.rst b/Documentation/vm/hmm.rst
index cdf3911582c8..b6e0ae47709b 100644
--- a/Documentation/vm/hmm.rst
+++ b/Documentation/vm/hmm.rst
@@ -277,7 +277,6 @@ region needing a struct page. This is offered through a very simple API::
  struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,
                                    struct device *device,
                                    unsigned long size);
- void hmm_devmem_remove(struct hmm_devmem *devmem);
 
 The hmm_devmem_ops is where most of the important things are::
 
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 2a78bdef9a24..47eb26dc2427 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -8,9 +8,10 @@ config ARM
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FORTIFY_SOURCE
+	select ARCH_HAS_KCOV
 	select ARCH_HAS_PTE_SPECIAL if ARM_LPAE
-	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_PHYS_TO_DMA
+	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_STRICT_KERNEL_RWX if MMU && !XIP_KERNEL
 	select ARCH_HAS_STRICT_MODULE_RWX if MMU
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index a3c5fbcad4ab..1f5a5ffe7fcf 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -25,6 +25,9 @@ endif
 
 GCOV_PROFILE		:= n
 
+# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
+KCOV_INSTRUMENT		:= n
+
 #
 # Architecture dependencies
 #
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/arm/kvm/hyp/Makefile b/arch/arm/kvm/hyp/Makefile
index 7fc0638f263a..d2b5ec9c4b92 100644
--- a/arch/arm/kvm/hyp/Makefile
+++ b/arch/arm/kvm/hyp/Makefile
@@ -23,3 +23,11 @@ obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o
 obj-$(CONFIG_KVM_ARM_HOST) += switch.o
 CFLAGS_switch.o		   += $(CFLAGS_ARMV7VE)
 obj-$(CONFIG_KVM_ARM_HOST) += s2-setup.o
+
+# KVM code is run at a different exception code with a different map, so
+# compiler instrumentation that inserts callbacks or checks into the code may
+# cause crashes. Just disable it.
+GCOV_PROFILE	:= n
+KASAN_SANITIZE	:= n
+UBSAN_SANITIZE	:= n
+KCOV_INSTRUMENT	:= n
diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile
index bb4118213fee..f4efff9d3afb 100644
--- a/arch/arm/vdso/Makefile
+++ b/arch/arm/vdso/Makefile
@@ -30,6 +30,9 @@ CFLAGS_vgettimeofday.o = -O2
 # Disable gcov profiling for VDSO code
 GCOV_PROFILE := n
 
+# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
+KCOV_INSTRUMENT := n
+
 # Force dependency
 $(obj)/vdso.o : $(obj)/vdso.so
 
diff --git a/block/genhd.c b/block/genhd.c
index f1543a45e73b..cb65a3013480 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1003,7 +1003,7 @@ 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/fs/bfs/inode.c b/fs/bfs/inode.c
index 9a69392f1fb3..d81c148682e7 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -350,7 +350,8 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent)
 
 	s->s_magic = BFS_MAGIC;
 
-	if (le32_to_cpu(bfs_sb->s_start) > le32_to_cpu(bfs_sb->s_end)) {
+	if (le32_to_cpu(bfs_sb->s_start) > le32_to_cpu(bfs_sb->s_end) ||
+	    le32_to_cpu(bfs_sb->s_start) < BFS_BSIZE) {
 		printf("Superblock is corrupted\n");
 		goto out1;
 	}
@@ -359,9 +360,11 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent)
 					sizeof(struct bfs_inode)
 					+ BFS_ROOT_INO - 1;
 	imap_len = (info->si_lasti / 8) + 1;
-	info->si_imap = kzalloc(imap_len, GFP_KERNEL);
-	if (!info->si_imap)
+	info->si_imap = kzalloc(imap_len, GFP_KERNEL | __GFP_NOWARN);
+	if (!info->si_imap) {
+		printf("Cannot allocate %u bytes\n", imap_len);
 		goto out1;
+	}
 	for (i = 0; i < BFS_ROOT_INO; i++)
 		set_bit(i, info->si_imap);
 
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 4ad6f669fe34..8676bb01b5a9 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 0e8e5de3c48a..c30a8ae46096 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;
 	}
diff --git a/fs/exec.c b/fs/exec.c
index 2d4e0075bd24..360b70755173 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 ddbf87246898..1b8b44637e70 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..199590f36203 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) {
+		struct __1_page_stripe *stripe = &sp2d->_1p_stripes[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;
+			stripe->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.
+		 */
+		stripe->pages = (void *)__a1pa;
+		stripe->scribble = stripe->pages + group_width;
+		stripe->page_is_read = (char *)stripe->scribble + group_width;
+		__a1pa += sizeof__a1pa;
 	}
 
 	sp2d->parity = parity;
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 719a3152da80..41cf2fbee50d 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()
+	 */
+	const 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/fat/inode.c b/fs/fat/inode.c
index 13271ea2b453..3b24975fb822 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -158,8 +158,13 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock,
 	err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create, false);
 	if (err)
 		return err;
+	if (!phys) {
+		fat_fs_error(sb,
+			     "invalid FAT chain (i_pos %lld, last_block %ld)",
+			     MSDOS_I(inode)->i_pos, last_block);
+		return -EIO;
+	}
 
-	BUG_ON(!phys);
 	BUG_ON(*max_blocks != mapped_blocks);
 	set_buffer_new(bh_result);
 	map_bh(bh_result, sb, phys);
diff --git a/fs/namei.c b/fs/namei.c
index ff211205f489..6cc5798afa4d 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -887,6 +887,8 @@ static inline void put_link(struct nameidata *nd)
 
 int sysctl_protected_symlinks __read_mostly = 0;
 int sysctl_protected_hardlinks __read_mostly = 0;
+int sysctl_protected_fifos __read_mostly;
+int sysctl_protected_regular __read_mostly;
 
 /**
  * may_follow_link - Check symlink following for unsafe situations
@@ -1003,6 +1005,45 @@ static int may_linkat(struct path *link)
 	return -EPERM;
 }
 
+/**
+ * may_create_in_sticky - Check whether an O_CREAT open in a sticky directory
+ *			  should be allowed, or not, on files that already
+ *			  exist.
+ * @dir: the sticky parent directory
+ * @inode: the inode of the file to open
+ *
+ * Block an O_CREAT open of a FIFO (or a regular file) when:
+ *   - sysctl_protected_fifos (or sysctl_protected_regular) is enabled
+ *   - the file already exists
+ *   - we are in a sticky directory
+ *   - we don't own the file
+ *   - the owner of the directory doesn't own the file
+ *   - the directory is world writable
+ * If the sysctl_protected_fifos (or sysctl_protected_regular) is set to 2
+ * the directory doesn't have to be world writable: being group writable will
+ * be enough.
+ *
+ * Returns 0 if the open is allowed, -ve on error.
+ */
+static int may_create_in_sticky(struct dentry * const dir,
+				struct inode * const inode)
+{
+	if ((!sysctl_protected_fifos && S_ISFIFO(inode->i_mode)) ||
+	    (!sysctl_protected_regular && S_ISREG(inode->i_mode)) ||
+	    likely(!(dir->d_inode->i_mode & S_ISVTX)) ||
+	    uid_eq(inode->i_uid, dir->d_inode->i_uid) ||
+	    uid_eq(current_fsuid(), inode->i_uid))
+		return 0;
+
+	if (likely(dir->d_inode->i_mode & 0002) ||
+	    (dir->d_inode->i_mode & 0020 &&
+	     ((sysctl_protected_fifos >= 2 && S_ISFIFO(inode->i_mode)) ||
+	      (sysctl_protected_regular >= 2 && S_ISREG(inode->i_mode))))) {
+		return -EACCES;
+	}
+	return 0;
+}
+
 static __always_inline
 const char *get_link(struct nameidata *nd)
 {
@@ -3347,9 +3388,15 @@ finish_open:
 	if (error)
 		return error;
 	audit_inode(nd->name, nd->path.dentry, 0);
-	error = -EISDIR;
-	if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry))
-		goto out;
+	if (open_flag & O_CREAT) {
+		error = -EISDIR;
+		if (d_is_dir(nd->path.dentry))
+			goto out;
+		error = may_create_in_sticky(dir,
+					     d_backing_inode(nd->path.dentry));
+		if (unlikely(error))
+			goto out;
+	}
 	error = -ENOTDIR;
 	if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry))
 		goto out;
diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index d9ebe11c8990..9f0304f89fc3 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -99,25 +99,34 @@ out:
 	return ret;
 }
 
+/* Caller must provide a bhs[] with all NULL or non-NULL entries, so it
+ * will be easier to handle read failure.
+ */
 int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
 			   unsigned int nr, struct buffer_head *bhs[])
 {
 	int status = 0;
 	unsigned int i;
 	struct buffer_head *bh;
+	int new_bh = 0;
 
 	trace_ocfs2_read_blocks_sync((unsigned long long)block, nr);
 
 	if (!nr)
 		goto bail;
 
+	/* Don't put buffer head and re-assign it to NULL if it is allocated
+	 * outside since the caller can't be aware of this alternation!
+	 */
+	new_bh = (bhs[0] == NULL);
+
 	for (i = 0 ; i < nr ; i++) {
 		if (bhs[i] == NULL) {
 			bhs[i] = sb_getblk(osb->sb, block++);
 			if (bhs[i] == NULL) {
 				status = -ENOMEM;
 				mlog_errno(status);
-				goto bail;
+				break;
 			}
 		}
 		bh = bhs[i];
@@ -158,9 +167,26 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
 		submit_bh(REQ_OP_READ, 0, bh);
 	}
 
+read_failure:
 	for (i = nr; i > 0; i--) {
 		bh = bhs[i - 1];
 
+		if (unlikely(status)) {
+			if (new_bh && bh) {
+				/* If middle bh fails, let previous bh
+				 * finish its read and then put it to
+				 * aovoid bh leak
+				 */
+				if (!buffer_jbd(bh))
+					wait_on_buffer(bh);
+				put_bh(bh);
+				bhs[i - 1] = NULL;
+			} else if (bh && buffer_uptodate(bh)) {
+				clear_buffer_uptodate(bh);
+			}
+			continue;
+		}
+
 		/* No need to wait on the buffer if it's managed by JBD. */
 		if (!buffer_jbd(bh))
 			wait_on_buffer(bh);
@@ -170,8 +196,7 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
 			 * so we can safely record this and loop back
 			 * to cleanup the other buffers. */
 			status = -EIO;
-			put_bh(bh);
-			bhs[i - 1] = NULL;
+			goto read_failure;
 		}
 	}
 
@@ -179,6 +204,9 @@ bail:
 	return status;
 }
 
+/* Caller must provide a bhs[] with all NULL or non-NULL entries, so it
+ * will be easier to handle read failure.
+ */
 int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 		      struct buffer_head *bhs[], int flags,
 		      int (*validate)(struct super_block *sb,
@@ -188,6 +216,7 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 	int i, ignore_cache = 0;
 	struct buffer_head *bh;
 	struct super_block *sb = ocfs2_metadata_cache_get_super(ci);
+	int new_bh = 0;
 
 	trace_ocfs2_read_blocks_begin(ci, (unsigned long long)block, nr, flags);
 
@@ -213,6 +242,11 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 		goto bail;
 	}
 
+	/* Don't put buffer head and re-assign it to NULL if it is allocated
+	 * outside since the caller can't be aware of this alternation!
+	 */
+	new_bh = (bhs[0] == NULL);
+
 	ocfs2_metadata_cache_io_lock(ci);
 	for (i = 0 ; i < nr ; i++) {
 		if (bhs[i] == NULL) {
@@ -221,7 +255,8 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 				ocfs2_metadata_cache_io_unlock(ci);
 				status = -ENOMEM;
 				mlog_errno(status);
-				goto bail;
+				/* Don't forget to put previous bh! */
+				break;
 			}
 		}
 		bh = bhs[i];
@@ -316,16 +351,27 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 		}
 	}
 
-	status = 0;
-
+read_failure:
 	for (i = (nr - 1); i >= 0; i--) {
 		bh = bhs[i];
 
 		if (!(flags & OCFS2_BH_READAHEAD)) {
-			if (status) {
-				/* Clear the rest of the buffers on error */
-				put_bh(bh);
-				bhs[i] = NULL;
+			if (unlikely(status)) {
+				/* Clear the buffers on error including those
+				 * ever succeeded in reading
+				 */
+				if (new_bh && bh) {
+					/* If middle bh fails, let previous bh
+					 * finish its read and then put it to
+					 * aovoid bh leak
+					 */
+					if (!buffer_jbd(bh))
+						wait_on_buffer(bh);
+					put_bh(bh);
+					bhs[i] = NULL;
+				} else if (bh && buffer_uptodate(bh)) {
+					clear_buffer_uptodate(bh);
+				}
 				continue;
 			}
 			/* We know this can't have changed as we hold the
@@ -342,9 +388,7 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 				 * for this bh as it's not marked locally
 				 * uptodate. */
 				status = -EIO;
-				put_bh(bh);
-				bhs[i] = NULL;
-				continue;
+				goto read_failure;
 			}
 
 			if (buffer_needs_validate(bh)) {
@@ -354,11 +398,8 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 				BUG_ON(buffer_jbd(bh));
 				clear_buffer_needs_validate(bh);
 				status = validate(sb, bh);
-				if (status) {
-					put_bh(bh);
-					bhs[i] = NULL;
-					continue;
-				}
+				if (status)
+					goto read_failure;
 			}
 		}
 
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index b048d4fa3959..c121abbdfc7d 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -1897,8 +1897,7 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode,
 				/* On error, skip the f_pos to the
 				   next block. */
 				ctx->pos = (ctx->pos | (sb->s_blocksize - 1)) + 1;
-				brelse(bh);
-				continue;
+				break;
 			}
 			if (le64_to_cpu(de->inode)) {
 				unsigned char d_type = DT_UNKNOWN;
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 0ff424c6d17c..5502a5e8f0d9 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -3601,7 +3601,7 @@ 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/file.c b/fs/ocfs2/file.c
index dbce976dc3a4..3e8bbdc1aab3 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2343,7 +2343,7 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 
 	written = __generic_file_write_iter(iocb, from);
 	/* buffered aio wouldn't have proper lock coverage today */
-	BUG_ON(written == -EIOCBQUEUED && !(iocb->ki_flags & IOCB_DIRECT));
+	BUG_ON(written == -EIOCBQUEUED && !direct_io);
 
 	/*
 	 * deep in g_f_a_w_n()->ocfs2_direct_IO we pass in a ocfs2_dio_end_io
@@ -2463,7 +2463,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 	trace_generic_file_read_iter_ret(ret);
 
 	/* buffered aio wouldn't have proper lock coverage today */
-	BUG_ON(ret == -EIOCBQUEUED && !(iocb->ki_flags & IOCB_DIRECT));
+	BUG_ON(ret == -EIOCBQUEUED && !direct_io);
 
 	/* see ocfs2_file_write_iter */
 	if (ret == -EIOCBQUEUED || !ocfs2_iocb_is_rw_locked(iocb)) {
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 4aa9ce5df02f..677ab3eb6da1 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2438,14 +2438,11 @@ static struct dentry *proc_pident_lookup(struct inode *dir,
 	for (p = ents; p < last; p++) {
 		if (p->len != dentry->d_name.len)
 			continue;
-		if (!memcmp(dentry->d_name.name, p->name, p->len))
+		if (!memcmp(dentry->d_name.name, p->name, p->len)) {
+			res = proc_pident_instantiate(dentry, task, p);
 			break;
+		}
 	}
-	if (p >= last)
-		goto out;
-
-	res = proc_pident_instantiate(dentry, task, p);
-out:
 	put_task_struct(task);
 out_no_task:
 	return res;
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index c0e68f903011..92af04018176 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/fs.h b/include/linux/fs.h
index 5dd343e1a834..e9aeed6308aa 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -75,6 +75,8 @@ extern struct inodes_stat_t inodes_stat;
 extern int leases_enable, lease_break_time;
 extern int sysctl_protected_symlinks;
 extern int sysctl_protected_hardlinks;
+extern int sysctl_protected_fifos;
+extern int sysctl_protected_regular;
 
 typedef __kernel_rwf_t rwf_t;
 
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index 4c92e3ba3e16..5ec8635f602c 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -499,8 +499,7 @@ struct hmm_devmem {
  * enough and allocate struct page for it.
  *
  * The device driver can wrap the hmm_devmem struct inside a private device
- * driver struct. The device driver must call hmm_devmem_remove() before the
- * device goes away and before freeing the hmm_devmem struct memory.
+ * driver struct.
  */
 struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,
 				  struct device *device,
@@ -508,7 +507,6 @@ struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,
 struct hmm_devmem *hmm_devmem_add_resource(const struct hmm_devmem_ops *ops,
 					   struct device *device,
 					   struct resource *res);
-void hmm_devmem_remove(struct hmm_devmem *devmem);
 
 /*
  * hmm_devmem_page_set_drvdata - set per-page driver data field
diff --git a/include/linux/kcov.h b/include/linux/kcov.h
index 3ecf6f5e3a5f..b76a1807028d 100644
--- a/include/linux/kcov.h
+++ b/include/linux/kcov.h
@@ -22,13 +22,27 @@ enum kcov_mode {
 	KCOV_MODE_TRACE_CMP = 3,
 };
 
+#define KCOV_IN_CTXSW	(1 << 30)
+
 void kcov_task_init(struct task_struct *t);
 void kcov_task_exit(struct task_struct *t);
 
+#define kcov_prepare_switch(t)			\
+do {						\
+	(t)->kcov_mode |= KCOV_IN_CTXSW;	\
+} while (0)
+
+#define kcov_finish_switch(t)			\
+do {						\
+	(t)->kcov_mode &= ~KCOV_IN_CTXSW;	\
+} while (0)
+
 #else
 
 static inline void kcov_task_init(struct task_struct *t) {}
 static inline void kcov_task_exit(struct task_struct *t) {}
+static inline void kcov_prepare_switch(struct task_struct *t) {}
+static inline void kcov_finish_switch(struct task_struct *t) {}
 
 #endif /* CONFIG_KCOV */
 #endif /* _LINUX_KCOV_H */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 4f52ec755725..8af477bdf8d1 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 {
@@ -220,6 +221,13 @@ 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 */
 	struct cgroup_file events_file;
 
@@ -374,6 +382,11 @@ 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)
 
@@ -512,6 +525,13 @@ 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
@@ -819,6 +839,10 @@ 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,
@@ -1011,6 +1035,16 @@ 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/memremap.h b/include/linux/memremap.h
index f91f9e763557..56ed0a52f8f4 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -115,6 +115,7 @@ struct dev_pagemap {
 	dev_page_free_t page_free;
 	struct vmem_altmap altmap;
 	bool altmap_valid;
+	bool registered;
 	struct resource res;
 	struct percpu_ref *ref;
 	struct device *dev;
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 6adac113e96d..553eb37def7e 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;
 };
 
@@ -113,6 +121,8 @@ 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.h b/include/linux/sched.h
index 16e4d984fe51..d55989f13fb0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1130,7 +1130,7 @@ struct task_struct {
 
 #ifdef CONFIG_KCOV
 	/* Coverage collection mode enabled for this task (0 if disabled): */
-	enum kcov_mode			kcov_mode;
+	unsigned int			kcov_mode;
 
 	/* Size of the kcov_area: */
 	unsigned int			kcov_size;
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 113d1ad1ced7..54b65dc992af 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/slab.h b/include/linux/slab.h
index 4d759e1ddc33..14e3fe4bd6a1 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -600,6 +600,7 @@ struct memcg_cache_params {
 			struct memcg_cache_array __rcu *memcg_caches;
 			struct list_head __root_caches_node;
 			struct list_head children;
+			bool dying;
 		};
 		struct {
 			struct mem_cgroup *memcg;
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/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index db9f15f5db04..61490e7808df 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -219,4 +219,8 @@ struct prctl_mm_map {
 # define PR_SPEC_DISABLE		(1UL << 2)
 # define PR_SPEC_FORCE_DISABLE		(1UL << 3)
 
+/* Process-based variant of PDEATHSIG */
+#define PR_SET_PDEATHSIG_PROC		48
+#define PR_GET_PDEATHSIG_PROC		49
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/ipc/sem.c b/ipc/sem.c
index cfd94d48a9aa..20f649eed8c6 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -85,6 +85,7 @@
 #include <linux/nsproxy.h>
 #include <linux/ipc_namespace.h>
 #include <linux/sched/wake_q.h>
+#include <linux/nospec.h>
 
 #include <linux/uaccess.h>
 #include "util.h"
@@ -368,6 +369,7 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
 			      int nsops)
 {
 	struct sem *sem;
+	int idx;
 
 	if (nsops != 1) {
 		/* Complex operation - acquire a full lock */
@@ -385,7 +387,8 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
 	 *
 	 * Both facts are tracked by use_global_mode.
 	 */
-	sem = &sma->sems[sops->sem_num];
+	idx = array_index_nospec(sops->sem_num, sma->sem_nsems);
+	sem = &sma->sems[idx];
 
 	/*
 	 * Initial check for use_global_lock. Just an optimization,
@@ -638,7 +641,8 @@ static int perform_atomic_semop_slow(struct sem_array *sma, struct sem_queue *q)
 	un = q->undo;
 
 	for (sop = sops; sop < sops + nsops; sop++) {
-		curr = &sma->sems[sop->sem_num];
+		int idx = array_index_nospec(sop->sem_num, sma->sem_nsems);
+		curr = &sma->sems[idx];
 		sem_op = sop->sem_op;
 		result = curr->semval;
 
@@ -718,7 +722,9 @@ static int perform_atomic_semop(struct sem_array *sma, struct sem_queue *q)
 	 * until the operations can go through.
 	 */
 	for (sop = sops; sop < sops + nsops; sop++) {
-		curr = &sma->sems[sop->sem_num];
+		int idx = array_index_nospec(sop->sem_num, sma->sem_nsems);
+
+		curr = &sma->sems[idx];
 		sem_op = sop->sem_op;
 		result = curr->semval;
 
@@ -1356,6 +1362,7 @@ static int semctl_setval(struct ipc_namespace *ns, int semid, int semnum,
 		return -EIDRM;
 	}
 
+	semnum = array_index_nospec(semnum, sma->sem_nsems);
 	curr = &sma->sems[semnum];
 
 	ipc_assert_locked_object(&sma->sem_perm);
@@ -1509,6 +1516,8 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		err = -EIDRM;
 		goto out_unlock;
 	}
+
+	semnum = array_index_nospec(semnum, nsems);
 	curr = &sma->sems[semnum];
 
 	switch (cmd) {
@@ -2081,7 +2090,8 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops,
 	 */
 	if (nsops == 1) {
 		struct sem *curr;
-		curr = &sma->sems[sops->sem_num];
+		int idx = array_index_nospec(sops->sem_num, sma->sem_nsems);
+		curr = &sma->sems[idx];
 
 		if (alter) {
 			if (sma->complex_count) {
diff --git a/ipc/shm.c b/ipc/shm.c
index 29978ee76c2e..051a3e1fb8df 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -408,7 +408,7 @@ void exit_shm(struct task_struct *task)
 	up_write(&shm_ids(ns).rwsem);
 }
 
-static int shm_fault(struct vm_fault *vmf)
+static vm_fault_t shm_fault(struct vm_fault *vmf)
 {
 	struct file *file = vmf->vma->vm_file;
 	struct shm_file_data *sfd = shm_file_data(file);
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 7f689728f16f..f13a72ad49a7 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1748,6 +1748,9 @@ 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);
@@ -1764,6 +1767,11 @@ 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;
 	}
 }
 
@@ -1771,6 +1779,8 @@ 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;
 }
 
@@ -5958,7 +5968,8 @@ 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 08c6e5e217a0..03341e1854b4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -440,6 +440,14 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 			continue;
 		}
 		charge = 0;
+		/*
+		 * Don't duplicate many vmas if we've been oom-killed (for
+		 * example)
+		 */
+		if (fatal_signal_pending(current)) {
+			retval = -EINTR;
+			goto out;
+		}
 		if (mpnt->vm_flags & VM_ACCOUNT) {
 			unsigned long len = vma_pages(mpnt);
 
@@ -1471,6 +1479,8 @@ 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/kcov.c b/kernel/kcov.c
index 2c16f1ab5e10..3ebd09efe72a 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -58,7 +58,7 @@ struct kcov {
 
 static bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t)
 {
-	enum kcov_mode mode;
+	unsigned int mode;
 
 	/*
 	 * We are interested in code coverage as a function of a syscall inputs,
@@ -241,7 +241,8 @@ static void kcov_put(struct kcov *kcov)
 
 void kcov_task_init(struct task_struct *t)
 {
-	t->kcov_mode = KCOV_MODE_DISABLED;
+	WRITE_ONCE(t->kcov_mode, KCOV_MODE_DISABLED);
+	barrier();
 	t->kcov_size = 0;
 	t->kcov_area = NULL;
 	t->kcov = NULL;
@@ -323,6 +324,21 @@ static int kcov_close(struct inode *inode, struct file *filep)
 	return 0;
 }
 
+/*
+ * Fault in a lazily-faulted vmalloc area before it can be used by
+ * __santizer_cov_trace_pc(), to avoid recursion issues if any code on the
+ * vmalloc fault handling path is instrumented.
+ */
+static void kcov_fault_in_area(struct kcov *kcov)
+{
+	unsigned long stride = PAGE_SIZE / sizeof(unsigned long);
+	unsigned long *area = kcov->area;
+	unsigned long offset;
+
+	for (offset = 0; offset < kcov->size; offset += stride)
+		READ_ONCE(area[offset]);
+}
+
 static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
 			     unsigned long arg)
 {
@@ -371,6 +387,7 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
 #endif
 		else
 			return -EINVAL;
+		kcov_fault_in_area(kcov);
 		/* Cache in task struct for performance. */
 		t->kcov_size = kcov->size;
 		t->kcov_area = kcov->area;
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 5857267a4af5..fc698e8a21a2 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -124,7 +124,7 @@ static void devm_memremap_pages_release(void *data)
 	for_each_device_pfn(pfn, pgmap)
 		put_page(pfn_to_page(pfn));
 
-	if (percpu_ref_tryget_live(pgmap->ref)) {
+	if (pgmap->registered && percpu_ref_tryget_live(pgmap->ref)) {
 		dev_WARN(dev, "%s: page mapping is still live!\n", __func__);
 		percpu_ref_put(pgmap->ref);
 	}
@@ -223,11 +223,32 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 		goto err_pfn_remap;
 
 	mem_hotplug_begin();
-	error = arch_add_memory(nid, align_start, align_size, altmap, false);
-	if (!error)
-		move_pfn_range_to_zone(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
-					align_start >> PAGE_SHIFT,
+
+	/*
+	 * For device private memory we call add_pages() as we only need to
+	 * allocate and initialize struct page for the device memory. More-
+	 * over the device memory is un-accessible thus we do not want to
+	 * create a linear mapping for the memory like arch_add_memory()
+	 * would do.
+	 *
+	 * For all other device memory types, which are accessible by
+	 * the CPU, we do want the linear mapping and thus use
+	 * arch_add_memory().
+	 */
+	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
+		error = add_pages(nid, align_start >> PAGE_SHIFT,
+				align_size >> PAGE_SHIFT, NULL, false);
+	} else {
+		struct zone *zone;
+
+		error = arch_add_memory(nid, align_start, align_size, altmap,
+				false);
+		zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
+		if (!error)
+			move_pfn_range_to_zone(zone, align_start >> PAGE_SHIFT,
 					align_size >> PAGE_SHIFT, altmap);
+	}
+
 	mem_hotplug_done();
 	if (error)
 		goto err_add_memory;
@@ -246,7 +267,11 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 		percpu_ref_get(pgmap->ref);
 	}
 
-	devm_add_action(dev, devm_memremap_pages_release, pgmap);
+	error = devm_add_action_or_reset(dev, devm_memremap_pages_release,
+			pgmap);
+	if (error)
+		return ERR_PTR(error);
+	pgmap->registered = true;
 
 	return __va(res->start);
 
@@ -257,7 +282,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 	pgmap_radix_release(res, pgoff);
 	return ERR_PTR(error);
 }
-EXPORT_SYMBOL(devm_memremap_pages);
+EXPORT_SYMBOL_GPL(devm_memremap_pages);
 
 unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
 {
diff --git a/kernel/relay.c b/kernel/relay.c
index c955b10c973c..ae79846ced82 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -39,7 +39,7 @@ static void relay_file_mmap_close(struct vm_area_struct *vma)
 /*
  * fault() vm_op implementation for relay file mapping.
  */
-static int relay_buf_fault(struct vm_fault *vmf)
+static vm_fault_t relay_buf_fault(struct vm_fault *vmf)
 {
 	struct page *page;
 	struct rchan_buf *buf = vmf->vma->vm_private_data;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a98d54cd5535..78d8facba456 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -10,6 +10,8 @@
 #include <linux/kthread.h>
 #include <linux/nospec.h>
 
+#include <linux/kcov.h>
+
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
 
@@ -2633,6 +2635,7 @@ static inline void
 prepare_task_switch(struct rq *rq, struct task_struct *prev,
 		    struct task_struct *next)
 {
+	kcov_prepare_switch(prev);
 	sched_info_switch(rq, prev, next);
 	perf_event_task_sched_out(prev, next);
 	rseq_preempt(prev);
@@ -2702,6 +2705,7 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	finish_task(prev);
 	finish_lock_switch(rq);
 	finish_arch_post_lock_switch();
+	kcov_finish_switch(current);
 
 	fire_sched_in_preempt_notifiers(current);
 	/*
diff --git a/kernel/sys.c b/kernel/sys.c
index 38509dc1f77b..fcc370a2629d 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2289,6 +2289,17 @@ 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/kernel/sysctl.c b/kernel/sysctl.c
index 6a78cf70761d..f45ed9e696eb 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1805,6 +1805,24 @@ static struct ctl_table fs_table[] = {
 		.extra2		= &one,
 	},
 	{
+		.procname	= "protected_fifos",
+		.data		= &sysctl_protected_fifos,
+		.maxlen		= sizeof(int),
+		.mode		= 0600,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &two,
+	},
+	{
+		.procname	= "protected_regular",
+		.data		= &sysctl_protected_regular,
+		.maxlen		= sizeof(int),
+		.mode		= 0600,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &two,
+	},
+	{
 		.procname	= "suid_dumpable",
 		.data		= &suid_dumpable,
 		.maxlen		= sizeof(int),
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index d543c65ce0eb..8838d1158d19 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1506,6 +1506,10 @@ config NETDEV_NOTIFIER_ERROR_INJECT
 
 	  If unsure, say N.
 
+config FUNCTION_ERROR_INJECTION
+	def_bool y
+	depends on HAVE_FUNCTION_ERROR_INJECTION && KPROBES
+
 config FAULT_INJECTION
 	bool "Fault-injection framework"
 	depends on DEBUG_KERNEL
@@ -1513,10 +1517,6 @@ config FAULT_INJECTION
 	  Provide fault-injection framework.
 	  For more details, see Documentation/fault-injection/.
 
-config FUNCTION_ERROR_INJECTION
-	def_bool y
-	depends on HAVE_FUNCTION_ERROR_INJECTION && KPROBES
-
 config FAILSLAB
 	bool "Fault-injection capability for kmalloc"
 	depends on FAULT_INJECTION
@@ -1547,16 +1547,6 @@ config FAIL_IO_TIMEOUT
 	  Only works with drivers that use the generic timeout handling,
 	  for others it wont do anything.
 
-config FAIL_MMC_REQUEST
-	bool "Fault-injection capability for MMC IO"
-	depends on FAULT_INJECTION_DEBUG_FS && MMC
-	help
-	  Provide fault-injection capability for MMC IO.
-	  This will make the mmc core return data errors. This is
-	  useful to test the error handling in the mmc block device
-	  and to test how the mmc host driver handles retries from
-	  the block device.
-
 config FAIL_FUTEX
 	bool "Fault-injection capability for futexes"
 	select DEBUG_FS
@@ -1564,6 +1554,12 @@ config FAIL_FUTEX
 	help
 	  Provide fault-injection capability for futexes.
 
+config FAULT_INJECTION_DEBUG_FS
+	bool "Debugfs entries for fault-injection capabilities"
+	depends on FAULT_INJECTION && SYSFS && DEBUG_FS
+	help
+	  Enable configuration of fault-injection capabilities via debugfs.
+
 config FAIL_FUNCTION
 	bool "Fault-injection capability for functions"
 	depends on FAULT_INJECTION_DEBUG_FS && FUNCTION_ERROR_INJECTION
@@ -1574,11 +1570,15 @@ config FAIL_FUNCTION
 	  an error value and have to handle it. This is useful to test the
 	  error handling in various subsystems.
 
-config FAULT_INJECTION_DEBUG_FS
-	bool "Debugfs entries for fault-injection capabilities"
-	depends on FAULT_INJECTION && SYSFS && DEBUG_FS
+config FAIL_MMC_REQUEST
+	bool "Fault-injection capability for MMC IO"
+	depends on FAULT_INJECTION_DEBUG_FS && MMC
 	help
-	  Enable configuration of fault-injection capabilities via debugfs.
+	  Provide fault-injection capability for MMC IO.
+	  This will make the mmc core return data errors. This is
+	  useful to test the error handling in the mmc block device
+	  and to test how the mmc host driver handles retries from
+	  the block device.
 
 config FAULT_INJECTION_STACKTRACE_FILTER
 	bool "stacktrace filter for fault-injection capabilities"
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 347cc834c04a..7215c0d5cb10 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -221,11 +221,46 @@ 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/hmm.c b/mm/hmm.c
index de7b6bf77201..0a76ad7c993c 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -966,173 +966,6 @@ static void hmm_devmem_free(struct page *page, void *data)
 	devmem->ops->free(devmem, page);
 }
 
-static DEFINE_MUTEX(hmm_devmem_lock);
-static RADIX_TREE(hmm_devmem_radix, GFP_KERNEL);
-
-static void hmm_devmem_radix_release(struct resource *resource)
-{
-	resource_size_t key, align_start, align_size;
-
-	align_start = resource->start & ~(PA_SECTION_SIZE - 1);
-	align_size = ALIGN(resource_size(resource), PA_SECTION_SIZE);
-
-	mutex_lock(&hmm_devmem_lock);
-	for (key = resource->start;
-	     key <= resource->end;
-	     key += PA_SECTION_SIZE)
-		radix_tree_delete(&hmm_devmem_radix, key >> PA_SECTION_SHIFT);
-	mutex_unlock(&hmm_devmem_lock);
-}
-
-static void hmm_devmem_release(struct device *dev, void *data)
-{
-	struct hmm_devmem *devmem = data;
-	struct resource *resource = devmem->resource;
-	unsigned long start_pfn, npages;
-	struct zone *zone;
-	struct page *page;
-
-	if (percpu_ref_tryget_live(&devmem->ref)) {
-		dev_WARN(dev, "%s: page mapping is still live!\n", __func__);
-		percpu_ref_put(&devmem->ref);
-	}
-
-	/* pages are dead and unused, undo the arch mapping */
-	start_pfn = (resource->start & ~(PA_SECTION_SIZE - 1)) >> PAGE_SHIFT;
-	npages = ALIGN(resource_size(resource), PA_SECTION_SIZE) >> PAGE_SHIFT;
-
-	page = pfn_to_page(start_pfn);
-	zone = page_zone(page);
-
-	mem_hotplug_begin();
-	if (resource->desc == IORES_DESC_DEVICE_PRIVATE_MEMORY)
-		__remove_pages(zone, start_pfn, npages, NULL);
-	else
-		arch_remove_memory(start_pfn << PAGE_SHIFT,
-				   npages << PAGE_SHIFT, NULL);
-	mem_hotplug_done();
-
-	hmm_devmem_radix_release(resource);
-}
-
-static int hmm_devmem_pages_create(struct hmm_devmem *devmem)
-{
-	resource_size_t key, align_start, align_size, align_end;
-	struct device *device = devmem->device;
-	int ret, nid, is_ram;
-	unsigned long pfn;
-
-	align_start = devmem->resource->start & ~(PA_SECTION_SIZE - 1);
-	align_size = ALIGN(devmem->resource->start +
-			   resource_size(devmem->resource),
-			   PA_SECTION_SIZE) - align_start;
-
-	is_ram = region_intersects(align_start, align_size,
-				   IORESOURCE_SYSTEM_RAM,
-				   IORES_DESC_NONE);
-	if (is_ram == REGION_MIXED) {
-		WARN_ONCE(1, "%s attempted on mixed region %pr\n",
-				__func__, devmem->resource);
-		return -ENXIO;
-	}
-	if (is_ram == REGION_INTERSECTS)
-		return -ENXIO;
-
-	if (devmem->resource->desc == IORES_DESC_DEVICE_PUBLIC_MEMORY)
-		devmem->pagemap.type = MEMORY_DEVICE_PUBLIC;
-	else
-		devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
-
-	devmem->pagemap.res = *devmem->resource;
-	devmem->pagemap.page_fault = hmm_devmem_fault;
-	devmem->pagemap.page_free = hmm_devmem_free;
-	devmem->pagemap.dev = devmem->device;
-	devmem->pagemap.ref = &devmem->ref;
-	devmem->pagemap.data = devmem;
-
-	mutex_lock(&hmm_devmem_lock);
-	align_end = align_start + align_size - 1;
-	for (key = align_start; key <= align_end; key += PA_SECTION_SIZE) {
-		struct hmm_devmem *dup;
-
-		dup = radix_tree_lookup(&hmm_devmem_radix,
-					key >> PA_SECTION_SHIFT);
-		if (dup) {
-			dev_err(device, "%s: collides with mapping for %s\n",
-				__func__, dev_name(dup->device));
-			mutex_unlock(&hmm_devmem_lock);
-			ret = -EBUSY;
-			goto error;
-		}
-		ret = radix_tree_insert(&hmm_devmem_radix,
-					key >> PA_SECTION_SHIFT,
-					devmem);
-		if (ret) {
-			dev_err(device, "%s: failed: %d\n", __func__, ret);
-			mutex_unlock(&hmm_devmem_lock);
-			goto error_radix;
-		}
-	}
-	mutex_unlock(&hmm_devmem_lock);
-
-	nid = dev_to_node(device);
-	if (nid < 0)
-		nid = numa_mem_id();
-
-	mem_hotplug_begin();
-	/*
-	 * For device private memory we call add_pages() as we only need to
-	 * allocate and initialize struct page for the device memory. More-
-	 * over the device memory is un-accessible thus we do not want to
-	 * create a linear mapping for the memory like arch_add_memory()
-	 * would do.
-	 *
-	 * For device public memory, which is accesible by the CPU, we do
-	 * want the linear mapping and thus use arch_add_memory().
-	 */
-	if (devmem->pagemap.type == MEMORY_DEVICE_PUBLIC)
-		ret = arch_add_memory(nid, align_start, align_size, NULL,
-				false);
-	else
-		ret = add_pages(nid, align_start >> PAGE_SHIFT,
-				align_size >> PAGE_SHIFT, NULL, false);
-	if (ret) {
-		mem_hotplug_done();
-		goto error_add_memory;
-	}
-	move_pfn_range_to_zone(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
-				align_start >> PAGE_SHIFT,
-				align_size >> PAGE_SHIFT, NULL);
-	mem_hotplug_done();
-
-	for (pfn = devmem->pfn_first; pfn < devmem->pfn_last; pfn++) {
-		struct page *page = pfn_to_page(pfn);
-
-		page->pgmap = &devmem->pagemap;
-	}
-	return 0;
-
-error_add_memory:
-	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
-error_radix:
-	hmm_devmem_radix_release(devmem->resource);
-error:
-	return ret;
-}
-
-static int hmm_devmem_match(struct device *dev, void *data, void *match_data)
-{
-	struct hmm_devmem *devmem = data;
-
-	return devmem->resource == match_data;
-}
-
-static void hmm_devmem_pages_remove(struct hmm_devmem *devmem)
-{
-	devres_release(devmem->device, &hmm_devmem_release,
-		       &hmm_devmem_match, devmem->resource);
-}
-
 /*
  * hmm_devmem_add() - hotplug ZONE_DEVICE memory for device memory
  *
@@ -1156,12 +989,12 @@ struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,
 {
 	struct hmm_devmem *devmem;
 	resource_size_t addr;
+	void *result;
 	int ret;
 
 	dev_pagemap_get_ops();
 
-	devmem = devres_alloc_node(&hmm_devmem_release, sizeof(*devmem),
-				   GFP_KERNEL, dev_to_node(device));
+	devmem = devm_kzalloc(device, sizeof(*devmem), GFP_KERNEL);
 	if (!devmem)
 		return ERR_PTR(-ENOMEM);
 
@@ -1175,11 +1008,11 @@ struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,
 	ret = percpu_ref_init(&devmem->ref, &hmm_devmem_ref_release,
 			      0, GFP_KERNEL);
 	if (ret)
-		goto error_percpu_ref;
+		return ERR_PTR(ret);
 
-	ret = devm_add_action(device, hmm_devmem_ref_exit, &devmem->ref);
+	ret = devm_add_action_or_reset(device, hmm_devmem_ref_exit, &devmem->ref);
 	if (ret)
-		goto error_devm_add_action;
+		return ERR_PTR(ret);
 
 	size = ALIGN(size, PA_SECTION_SIZE);
 	addr = min((unsigned long)iomem_resource.end,
@@ -1199,54 +1032,45 @@ struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,
 
 		devmem->resource = devm_request_mem_region(device, addr, size,
 							   dev_name(device));
-		if (!devmem->resource) {
-			ret = -ENOMEM;
-			goto error_no_resource;
-		}
+		if (!devmem->resource)
+			return ERR_PTR(-ENOMEM);
 		break;
 	}
-	if (!devmem->resource) {
-		ret = -ERANGE;
-		goto error_no_resource;
-	}
+	if (!devmem->resource)
+		return ERR_PTR(-ERANGE);
 
 	devmem->resource->desc = IORES_DESC_DEVICE_PRIVATE_MEMORY;
 	devmem->pfn_first = devmem->resource->start >> PAGE_SHIFT;
 	devmem->pfn_last = devmem->pfn_first +
 			   (resource_size(devmem->resource) >> PAGE_SHIFT);
 
-	ret = hmm_devmem_pages_create(devmem);
-	if (ret)
-		goto error_pages;
+	devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
+	devmem->pagemap.res = *devmem->resource;
+	devmem->pagemap.page_fault = hmm_devmem_fault;
+	devmem->pagemap.page_free = hmm_devmem_free;
+	devmem->pagemap.altmap_valid = false;
+	devmem->pagemap.registered = false;
+	devmem->pagemap.ref = &devmem->ref;
+	devmem->pagemap.data = devmem;
 
-	devres_add(device, devmem);
+	result = devm_memremap_pages(devmem->device, &devmem->pagemap);
+	if (IS_ERR(result))
+		return result;
 
-	ret = devm_add_action(device, hmm_devmem_ref_kill, &devmem->ref);
-	if (ret) {
-		hmm_devmem_remove(devmem);
+	ret = devm_add_action_or_reset(device, hmm_devmem_ref_kill, &devmem->ref);
+	if (ret)
 		return ERR_PTR(ret);
-	}
 
 	return devmem;
-
-error_pages:
-	devm_release_mem_region(device, devmem->resource->start,
-				resource_size(devmem->resource));
-error_no_resource:
-error_devm_add_action:
-	hmm_devmem_ref_kill(&devmem->ref);
-	hmm_devmem_ref_exit(&devmem->ref);
-error_percpu_ref:
-	devres_free(devmem);
-	return ERR_PTR(ret);
 }
-EXPORT_SYMBOL(hmm_devmem_add);
+EXPORT_SYMBOL_GPL(hmm_devmem_add);
 
 struct hmm_devmem *hmm_devmem_add_resource(const struct hmm_devmem_ops *ops,
 					   struct device *device,
 					   struct resource *res)
 {
 	struct hmm_devmem *devmem;
+	void *result;
 	int ret;
 
 	if (res->desc != IORES_DESC_DEVICE_PUBLIC_MEMORY)
@@ -1254,8 +1078,7 @@ struct hmm_devmem *hmm_devmem_add_resource(const struct hmm_devmem_ops *ops,
 
 	dev_pagemap_get_ops();
 
-	devmem = devres_alloc_node(&hmm_devmem_release, sizeof(*devmem),
-				   GFP_KERNEL, dev_to_node(device));
+	devmem = devm_kzalloc(device, sizeof(*devmem), GFP_KERNEL);
 	if (!devmem)
 		return ERR_PTR(-ENOMEM);
 
@@ -1269,71 +1092,37 @@ struct hmm_devmem *hmm_devmem_add_resource(const struct hmm_devmem_ops *ops,
 	ret = percpu_ref_init(&devmem->ref, &hmm_devmem_ref_release,
 			      0, GFP_KERNEL);
 	if (ret)
-		goto error_percpu_ref;
+		return ERR_PTR(ret);
 
-	ret = devm_add_action(device, hmm_devmem_ref_exit, &devmem->ref);
+	ret = devm_add_action_or_reset(device, hmm_devmem_ref_exit,
+			&devmem->ref);
 	if (ret)
-		goto error_devm_add_action;
-
+		return ERR_PTR(ret);
 
 	devmem->pfn_first = devmem->resource->start >> PAGE_SHIFT;
 	devmem->pfn_last = devmem->pfn_first +
 			   (resource_size(devmem->resource) >> PAGE_SHIFT);
 
-	ret = hmm_devmem_pages_create(devmem);
-	if (ret)
-		goto error_devm_add_action;
+	devmem->pagemap.type = MEMORY_DEVICE_PUBLIC;
+	devmem->pagemap.res = *devmem->resource;
+	devmem->pagemap.page_fault = hmm_devmem_fault;
+	devmem->pagemap.page_free = hmm_devmem_free;
+	devmem->pagemap.altmap_valid = false;
+	devmem->pagemap.registered = false;
+	devmem->pagemap.ref = &devmem->ref;
+	devmem->pagemap.data = devmem;
 
-	devres_add(device, devmem);
+	result = devm_memremap_pages(devmem->device, &devmem->pagemap);
+	if (IS_ERR(result))
+		return result;
 
-	ret = devm_add_action(device, hmm_devmem_ref_kill, &devmem->ref);
-	if (ret) {
-		hmm_devmem_remove(devmem);
+	ret = devm_add_action_or_reset(device, hmm_devmem_ref_kill, &devmem->ref);
+	if (ret)
 		return ERR_PTR(ret);
-	}
 
 	return devmem;
-
-error_devm_add_action:
-	hmm_devmem_ref_kill(&devmem->ref);
-	hmm_devmem_ref_exit(&devmem->ref);
-error_percpu_ref:
-	devres_free(devmem);
-	return ERR_PTR(ret);
-}
-EXPORT_SYMBOL(hmm_devmem_add_resource);
-
-/*
- * hmm_devmem_remove() - remove device memory (kill and free ZONE_DEVICE)
- *
- * @devmem: hmm_devmem struct use to track and manage the ZONE_DEVICE memory
- *
- * This will hot-unplug memory that was hotplugged by hmm_devmem_add on behalf
- * of the device driver. It will free struct page and remove the resource that
- * reserved the physical address range for this device memory.
- */
-void hmm_devmem_remove(struct hmm_devmem *devmem)
-{
-	resource_size_t start, size;
-	struct device *device;
-	bool cdm = false;
-
-	if (!devmem)
-		return;
-
-	device = devmem->device;
-	start = devmem->resource->start;
-	size = resource_size(devmem->resource);
-
-	cdm = devmem->resource->desc == IORES_DESC_DEVICE_PUBLIC_MEMORY;
-	hmm_devmem_ref_kill(&devmem->ref);
-	hmm_devmem_ref_exit(&devmem->ref);
-	hmm_devmem_pages_remove(devmem);
-
-	if (!cdm)
-		devm_release_mem_region(device, start, size);
 }
-EXPORT_SYMBOL(hmm_devmem_remove);
+EXPORT_SYMBOL_GPL(hmm_devmem_add_resource);
 
 /*
  * A device driver that wants to handle multiple devices memory through a
diff --git a/mm/ksm.c b/mm/ksm.c
index e2d2886fb1df..a6d43cf9a982 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -216,6 +216,8 @@ struct rmap_item {
 #define SEQNR_MASK	0x0ff	/* low bits of unstable tree seqnr */
 #define UNSTABLE_FLAG	0x100	/* is a node of the unstable tree */
 #define STABLE_FLAG	0x200	/* is listed from the stable tree */
+#define KSM_FLAG_MASK	(SEQNR_MASK|UNSTABLE_FLAG|STABLE_FLAG)
+				/* to mask all the flags */
 
 /* The stable and unstable tree heads */
 static struct rb_root one_stable_tree[1] = { RB_ROOT };
@@ -2598,10 +2600,15 @@ again:
 		anon_vma_lock_read(anon_vma);
 		anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root,
 					       0, ULONG_MAX) {
+			unsigned long addr;
+
 			cond_resched();
 			vma = vmac->vma;
-			if (rmap_item->address < vma->vm_start ||
-			    rmap_item->address >= vma->vm_end)
+
+			/* Ignore the stable/unstable/sqnr flags */
+			addr = rmap_item->address & ~KSM_FLAG_MASK;
+
+			if (addr < vma->vm_start || addr >= vma->vm_end)
 				continue;
 			/*
 			 * Initially we examine only the vma which covers this
@@ -2615,8 +2622,7 @@ again:
 			if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))
 				continue;
 
-			if (!rwc->rmap_one(page, vma,
-					rmap_item->address, rwc->arg)) {
+			if (!rwc->rmap_one(page, vma, addr, rwc->arg)) {
 				anon_vma_unlock_read(anon_vma);
 				return;
 			}
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 c1e64d60ed02..700c2f1c312c 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;
 		}
@@ -2599,6 +2598,224 @@ 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_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.
  *
@@ -4036,6 +4253,14 @@ 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);
@@ -4046,8 +4271,7 @@ 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);
@@ -4184,8 +4408,7 @@ 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;
 }
@@ -4244,6 +4467,7 @@ 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);
 }
@@ -5227,6 +5451,39 @@ 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));
@@ -5357,6 +5614,12 @@ 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 7206a634270b..e9cac1c4fa69 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2934,7 +2934,7 @@ 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);
@@ -3044,7 +3044,6 @@ 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;
 
@@ -3058,6 +3057,7 @@ 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/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 6694348b27e9..8f7d8dd99e5d 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)
 {
@@ -835,67 +835,22 @@ 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) {
@@ -970,6 +925,108 @@ 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.
  */
@@ -1022,6 +1079,7 @@ 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;
@@ -1066,27 +1124,37 @@ 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_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/slab_common.c b/mm/slab_common.c
index 98dcdc352062..e74bae7cc4ab 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -136,6 +136,7 @@ void slab_init_memcg_params(struct kmem_cache *s)
 	s->memcg_params.root_cache = NULL;
 	RCU_INIT_POINTER(s->memcg_params.memcg_caches, NULL);
 	INIT_LIST_HEAD(&s->memcg_params.children);
+	s->memcg_params.dying = false;
 }
 
 static int init_memcg_params(struct kmem_cache *s,
@@ -608,7 +609,7 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
 	 * The memory cgroup could have been offlined while the cache
 	 * creation work was pending.
 	 */
-	if (memcg->kmem_state != KMEM_ONLINE)
+	if (memcg->kmem_state != KMEM_ONLINE || root_cache->memcg_params.dying)
 		goto out_unlock;
 
 	idx = memcg_cache_id(memcg);
@@ -712,6 +713,9 @@ void slab_deactivate_memcg_cache_rcu_sched(struct kmem_cache *s,
 	    WARN_ON_ONCE(s->memcg_params.deact_fn))
 		return;
 
+	if (s->memcg_params.root_cache->memcg_params.dying)
+		return;
+
 	/* pin memcg so that @s doesn't get destroyed in the middle */
 	css_get(&s->memcg_params.memcg->css);
 
@@ -823,11 +827,24 @@ static int shutdown_memcg_caches(struct kmem_cache *s)
 		return -EBUSY;
 	return 0;
 }
+
+static void flush_memcg_workqueue(struct kmem_cache *s)
+{
+	mutex_lock(&slab_mutex);
+	s->memcg_params.dying = true;
+	mutex_unlock(&slab_mutex);
+
+	flush_workqueue(memcg_kmem_cache_wq);
+}
 #else
 static inline int shutdown_memcg_caches(struct kmem_cache *s)
 {
 	return 0;
 }
+
+static inline void flush_memcg_workqueue(struct kmem_cache *s)
+{
+}
 #endif /* CONFIG_MEMCG && !CONFIG_SLOB */
 
 void slab_kmem_cache_release(struct kmem_cache *s)
@@ -845,6 +862,8 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	if (unlikely(!s))
 		return;
 
+	flush_memcg_workqueue(s);
+
 	get_online_cpus();
 	get_online_mems();
 
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 f13f2723950a..b2848cc6e32a 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -200,6 +200,12 @@ 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)
 {
@@ -229,6 +235,7 @@ 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++;
 		}
 	}
 }
@@ -444,7 +451,6 @@ 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 */
@@ -472,7 +478,6 @@ 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
@@ -484,10 +489,12 @@ 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;
@@ -564,7 +571,8 @@ 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;
@@ -572,21 +580,28 @@ 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 ab8e59cd18ea..c6b3eab73fde 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -334,8 +334,13 @@ 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) {
@@ -378,8 +383,8 @@ 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;
 
@@ -389,7 +394,12 @@ 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 78a015fcec3b..744d66666f82 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);
@@ -3365,22 +3464,16 @@ 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];
@@ -3426,11 +3519,9 @@ 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;
 }
 
 /*
@@ -3522,6 +3613,7 @@ 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
@@ -3529,15 +3621,15 @@ 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);
 
@@ -3555,9 +3647,8 @@ 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;
 	}
 
 	/*
@@ -3609,10 +3700,11 @@ 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 e3b7362b0ee4..a41e761fedf9 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 74f17376202b..fbb08bc78bee 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -695,6 +695,7 @@ 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 9a46dc24ac10..a85fac3345df 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -2654,6 +2654,7 @@ 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