Merge branch 'akpm' (patches from Andrew)

Pull updates from Andrew Morton:
 "Most of -mm and quite a number of other subsystems: hotfixes, scripts,
  ocfs2, misc, lib, binfmt, init, reiserfs, exec, dma-mapping, kcov.

  MM is fairly quiet this time.  Holidays, I assume"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (118 commits)
  kcov: ignore fault-inject and stacktrace
  include/linux/io-mapping.h-mapping: use PHYS_PFN() macro in io_mapping_map_atomic_wc()
  execve: warn if process starts with executable stack
  reiserfs: prevent NULL pointer dereference in reiserfs_insert_item()
  init/main.c: fix misleading "This architecture does not have kernel memory protection" message
  init/main.c: fix quoted value handling in unknown_bootoption
  init/main.c: remove unnecessary repair_env_string in do_initcall_level
  init/main.c: log arguments and environment passed to init
  fs/binfmt_elf.c: coredump: allow process with empty address space to coredump
  fs/binfmt_elf.c: coredump: delete duplicated overflow check
  fs/binfmt_elf.c: coredump: allocate core ELF header on stack
  fs/binfmt_elf.c: make BAD_ADDR() unlikely
  fs/binfmt_elf.c: better codegen around current->mm
  fs/binfmt_elf.c: don't copy ELF header around
  fs/binfmt_elf.c: fix ->start_code calculation
  fs/binfmt_elf.c: smaller code generation around auxv vector fill
  lib/find_bit.c: uninline helper _find_next_bit()
  lib/find_bit.c: join _find_next_bit{_le}
  uapi: rename ext2_swab() to swab() and share globally in swab.h
  lib/scatterlist.c: adjust indentation in __sg_alloc_table
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -834,6 +834,18 @@
 			dump out devices still on the deferred probe list after
 			retrying.
 
+	dfltcc=		[HW,S390]
+			Format: { on | off | def_only | inf_only | always }
+			on:       s390 zlib hardware support for compression on
+			          level 1 and decompression (default)
+			off:      No s390 zlib hardware support
+			def_only: s390 zlib hardware support for deflate
+			          only (compression on level 1)
+			inf_only: s390 zlib hardware support for inflate
+			          only (decompression)
+			always:   Same as 'on' but ignores the selected compression
+			          level always using hardware support (used for debugging)
+
 	dhash_entries=	[KNL]
 			Set number of hash buckets for dentry cache.
 

Documentation/core-api/index.rst

@@ -31,6 +31,7 @@ Core utilities
    generic-radix-tree
    memory-allocation
    mm-api
+   pin_user_pages
    gfp_mask-from-fs-io
    timekeeping
    boot-time-mm

Documentation/core-api/pin_user_pages.rst

@@ -0,0 +1,232 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+====================================================
+pin_user_pages() and related calls
+====================================================
+
+.. contents:: :local:
+
+Overview
+========
+
+This document describes the following functions::
+
+ pin_user_pages()
+ pin_user_pages_fast()
+ pin_user_pages_remote()
+
+Basic description of FOLL_PIN
+=============================
+
+FOLL_PIN and FOLL_LONGTERM are flags that can be passed to the get_user_pages*()
+("gup") family of functions. FOLL_PIN has significant interactions and
+interdependencies with FOLL_LONGTERM, so both are covered here.
+
+FOLL_PIN is internal to gup, meaning that it should not appear at the gup call
+sites. This allows the associated wrapper functions  (pin_user_pages*() and
+others) to set the correct combination of these flags, and to check for problems
+as well.
+
+FOLL_LONGTERM, on the other hand, *is* allowed to be set at the gup call sites.
+This is in order to avoid creating a large number of wrapper functions to cover
+all combinations of get*(), pin*(), FOLL_LONGTERM, and more. Also, the
+pin_user_pages*() APIs are clearly distinct from the get_user_pages*() APIs, so
+that's a natural dividing line, and a good point to make separate wrapper calls.
+In other words, use pin_user_pages*() for DMA-pinned pages, and
+get_user_pages*() for other cases. There are four cases described later on in
+this document, to further clarify that concept.
+
+FOLL_PIN and FOLL_GET are mutually exclusive for a given gup call. However,
+multiple threads and call sites are free to pin the same struct pages, via both
+FOLL_PIN and FOLL_GET. It's just the call site that needs to choose one or the
+other, not the struct page(s).
+
+The FOLL_PIN implementation is nearly the same as FOLL_GET, except that FOLL_PIN
+uses a different reference counting technique.
+
+FOLL_PIN is a prerequisite to FOLL_LONGTERM. Another way of saying that is,
+FOLL_LONGTERM is a specific case, more restrictive case of FOLL_PIN.
+
+Which flags are set by each wrapper
+===================================
+
+For these pin_user_pages*() functions, FOLL_PIN is OR'd in with whatever gup
+flags the caller provides. The caller is required to pass in a non-null struct
+pages* array, and the function then pin pages by incrementing each by a special
+value. For now, that value is +1, just like get_user_pages*().::
+
+ Function
+ --------
+ pin_user_pages          FOLL_PIN is always set internally by this function.
+ pin_user_pages_fast     FOLL_PIN is always set internally by this function.
+ pin_user_pages_remote   FOLL_PIN is always set internally by this function.
+
+For these get_user_pages*() functions, FOLL_GET might not even be specified.
+Behavior is a little more complex than above. If FOLL_GET was *not* specified,
+but the caller passed in a non-null struct pages* array, then the function
+sets FOLL_GET for you, and proceeds to pin pages by incrementing the refcount
+of each page by +1.::
+
+ Function
+ --------
+ get_user_pages           FOLL_GET is sometimes set internally by this function.
+ get_user_pages_fast      FOLL_GET is sometimes set internally by this function.
+ get_user_pages_remote    FOLL_GET is sometimes set internally by this function.
+
+Tracking dma-pinned pages
+=========================
+
+Some of the key design constraints, and solutions, for tracking dma-pinned
+pages:
+
+* An actual reference count, per struct page, is required. This is because
+  multiple processes may pin and unpin a page.
+
+* False positives (reporting that a page is dma-pinned, when in fact it is not)
+  are acceptable, but false negatives are not.
+
+* struct page may not be increased in size for this, and all fields are already
+  used.
+
+* Given the above, we can overload the page->_refcount field by using, sort of,
+  the upper bits in that field for a dma-pinned count. "Sort of", means that,
+  rather than dividing page->_refcount into bit fields, we simple add a medium-
+  large value (GUP_PIN_COUNTING_BIAS, initially chosen to be 1024: 10 bits) to
+  page->_refcount. This provides fuzzy behavior: if a page has get_page() called
+  on it 1024 times, then it will appear to have a single dma-pinned count.
+  And again, that's acceptable.
+
+This also leads to limitations: there are only 31-10==21 bits available for a
+counter that increments 10 bits at a time.
+
+TODO: for 1GB and larger huge pages, this is cutting it close. That's because
+when pin_user_pages() follows such pages, it increments the head page by "1"
+(where "1" used to mean "+1" for get_user_pages(), but now means "+1024" for
+pin_user_pages()) for each tail page. So if you have a 1GB huge page:
+
+* There are 256K (18 bits) worth of 4 KB tail pages.
+* There are 21 bits available to count up via GUP_PIN_COUNTING_BIAS (that is,
+  10 bits at a time)
+* There are 21 - 18 == 3 bits available to count. Except that there aren't,
+  because you need to allow for a few normal get_page() calls on the head page,
+  as well. Fortunately, the approach of using addition, rather than "hard"
+  bitfields, within page->_refcount, allows for sharing these bits gracefully.
+  But we're still looking at about 8 references.
+
+This, however, is a missing feature more than anything else, because it's easily
+solved by addressing an obvious inefficiency in the original get_user_pages()
+approach of retrieving pages: stop treating all the pages as if they were
+PAGE_SIZE. Retrieve huge pages as huge pages. The callers need to be aware of
+this, so some work is required. Once that's in place, this limitation mostly
+disappears from view, because there will be ample refcounting range available.
+
+* Callers must specifically request "dma-pinned tracking of pages". In other
+  words, just calling get_user_pages() will not suffice; a new set of functions,
+  pin_user_page() and related, must be used.
+
+FOLL_PIN, FOLL_GET, FOLL_LONGTERM: when to use which flags
+==========================================================
+
+Thanks to Jan Kara, Vlastimil Babka and several other -mm people, for describing
+these categories:
+
+CASE 1: Direct IO (DIO)
+-----------------------
+There are GUP references to pages that are serving
+as DIO buffers. These buffers are needed for a relatively short time (so they
+are not "long term"). No special synchronization with page_mkclean() or
+munmap() is provided. Therefore, flags to set at the call site are: ::
+
+    FOLL_PIN
+
+...but rather than setting FOLL_PIN directly, call sites should use one of
+the pin_user_pages*() routines that set FOLL_PIN.
+
+CASE 2: RDMA
+------------
+There are GUP references to pages that are serving as DMA
+buffers. These buffers are needed for a long time ("long term"). No special
+synchronization with page_mkclean() or munmap() is provided. Therefore, flags
+to set at the call site are: ::
+
+    FOLL_PIN | FOLL_LONGTERM
+
+NOTE: Some pages, such as DAX pages, cannot be pinned with longterm pins. That's
+because DAX pages do not have a separate page cache, and so "pinning" implies
+locking down file system blocks, which is not (yet) supported in that way.
+
+CASE 3: Hardware with page faulting support
+-------------------------------------------
+Here, a well-written driver doesn't normally need to pin pages at all. However,
+if the driver does choose to do so, it can register MMU notifiers for the range,
+and will be called back upon invalidation. Either way (avoiding page pinning, or
+using MMU notifiers to unpin upon request), there is proper synchronization with
+both filesystem and mm (page_mkclean(), munmap(), etc).
+
+Therefore, neither flag needs to be set.
+
+In this case, ideally, neither get_user_pages() nor pin_user_pages() should be
+called. Instead, the software should be written so that it does not pin pages.
+This allows mm and filesystems to operate more efficiently and reliably.
+
+CASE 4: Pinning for struct page manipulation only
+-------------------------------------------------
+Here, normal GUP calls are sufficient, so neither flag needs to be set.
+
+page_dma_pinned(): the whole point of pinning
+=============================================
+
+The whole point of marking pages as "DMA-pinned" or "gup-pinned" is to be able
+to query, "is this page DMA-pinned?" That allows code such as page_mkclean()
+(and file system writeback code in general) to make informed decisions about
+what to do when a page cannot be unmapped due to such pins.
+
+What to do in those cases is the subject of a years-long series of discussions
+and debates (see the References at the end of this document). It's a TODO item
+here: fill in the details once that's worked out. Meanwhile, it's safe to say
+that having this available: ::
+
+        static inline bool page_dma_pinned(struct page *page)
+
+...is a prerequisite to solving the long-running gup+DMA problem.
+
+Another way of thinking about FOLL_GET, FOLL_PIN, and FOLL_LONGTERM
+===================================================================
+
+Another way of thinking about these flags is as a progression of restrictions:
+FOLL_GET is for struct page manipulation, without affecting the data that the
+struct page refers to. FOLL_PIN is a *replacement* for FOLL_GET, and is for
+short term pins on pages whose data *will* get accessed. As such, FOLL_PIN is
+a "more severe" form of pinning. And finally, FOLL_LONGTERM is an even more
+restrictive case that has FOLL_PIN as a prerequisite: this is for pages that
+will be pinned longterm, and whose data will be accessed.
+
+Unit testing
+============
+This file::
+
+ tools/testing/selftests/vm/gup_benchmark.c
+
+has the following new calls to exercise the new pin*() wrapper functions:
+
+* PIN_FAST_BENCHMARK (./gup_benchmark -a)
+* PIN_BENCHMARK (./gup_benchmark -b)
+
+You can monitor how many total dma-pinned pages have been acquired and released
+since the system was booted, via two new /proc/vmstat entries: ::
+
+    /proc/vmstat/nr_foll_pin_requested
+    /proc/vmstat/nr_foll_pin_requested
+
+Those are both going to show zero, unless CONFIG_DEBUG_VM is set. This is
+because there is a noticeable performance drop in unpin_user_page(), when they
+are activated.
+
+References
+==========
+
+* `Some slow progress on get_user_pages() (Apr 2, 2019) <https://lwn.net/Articles/784574/>`_
+* `DMA and get_user_pages() (LPC: Dec 12, 2018) <https://lwn.net/Articles/774411/>`_
+* `The trouble with get_user_pages() (Apr 30, 2018) <https://lwn.net/Articles/753027/>`_
+
+John Hubbard, October, 2019

Documentation/vm/zswap.rst

@@ -130,6 +130,19 @@ checking for the same-value filled pages during store operation. However, the
 existing pages which are marked as same-value filled pages remain stored
 unchanged in zswap until they are either loaded or invalidated.
 
+To prevent zswap from shrinking pool when zswap is full and there's a high
+pressure on swap (this will result in flipping pages in and out zswap pool
+without any real benefit but with a performance drop for the system), a
+special parameter has been introduced to implement a sort of hysteresis to
+refuse taking pages into zswap pool until it has sufficient space if the limit
+has been hit. To set the threshold at which zswap would start accepting pages
+again after it became full, use the sysfs ``accept_threhsold_percent``
+attribute, e. g.::
+
+	echo 80 > /sys/module/zswap/parameters/accept_threhsold_percent
+
+Setting this parameter to 100 will disable the hysteresis.
+
 A debugfs interface is provided for various statistic about pool size, number
 of pages stored, same-value filled pages and various counters for the reasons
 pages are rejected.

arch/powerpc/mm/book3s64/iommu_api.c

@@ -103,7 +103,7 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 	for (entry = 0; entry < entries; entry += chunk) {
 		unsigned long n = min(entries - entry, chunk);
 
-		ret = get_user_pages(ua + (entry << PAGE_SHIFT), n,
+		ret = pin_user_pages(ua + (entry << PAGE_SHIFT), n,
 				FOLL_WRITE | FOLL_LONGTERM,
 				mem->hpages + entry, NULL);
 		if (ret == n) {
@@ -167,9 +167,8 @@ good_exit:
 	return 0;
 
 free_exit:
-	/* free the reference taken */
-	for (i = 0; i < pinned; i++)
-		put_page(mem->hpages[i]);
+	/* free the references taken */
+	unpin_user_pages(mem->hpages, pinned);
 
 	vfree(mem->hpas);
 	kfree(mem);
@@ -215,7 +214,8 @@ static void mm_iommu_unpin(struct mm_iommu_table_group_mem_t *mem)
 		if (mem->hpas[i] & MM_IOMMU_TABLE_GROUP_PAGE_DIRTY)
 			SetPageDirty(page);
 
-		put_page(page);
+		unpin_user_page(page);
+
 		mem->hpas[i] = 0;
 	}
 }

arch/s390/boot/compressed/decompressor.c

@@ -30,13 +30,13 @@ extern unsigned char _compressed_start[];
 extern unsigned char _compressed_end[];
 
 #ifdef CONFIG_HAVE_KERNEL_BZIP2
-#define HEAP_SIZE	0x400000
+#define BOOT_HEAP_SIZE	0x400000
 #else
-#define HEAP_SIZE	0x10000
+#define BOOT_HEAP_SIZE	0x10000
 #endif
 
 static unsigned long free_mem_ptr = (unsigned long) _end;
-static unsigned long free_mem_end_ptr = (unsigned long) _end + HEAP_SIZE;
+static unsigned long free_mem_end_ptr = (unsigned long) _end + BOOT_HEAP_SIZE;
 
 #ifdef CONFIG_KERNEL_GZIP
 #include "../../../../lib/decompress_inflate.c"
@@ -62,7 +62,7 @@ static unsigned long free_mem_end_ptr = (unsigned long) _end + HEAP_SIZE;
 #include "../../../../lib/decompress_unxz.c"
 #endif
 
-#define decompress_offset ALIGN((unsigned long)_end + HEAP_SIZE, PAGE_SIZE)
+#define decompress_offset ALIGN((unsigned long)_end + BOOT_HEAP_SIZE, PAGE_SIZE)
 
 unsigned long mem_safe_offset(void)
 {

arch/s390/boot/ipl_parm.c

@@ -14,6 +14,7 @@
 char __bootdata(early_command_line)[COMMAND_LINE_SIZE];
 struct ipl_parameter_block __bootdata_preserved(ipl_block);
 int __bootdata_preserved(ipl_block_valid);
+unsigned int __bootdata_preserved(zlib_dfltcc_support) = ZLIB_DFLTCC_FULL;
 
 unsigned long __bootdata(vmalloc_size) = VMALLOC_DEFAULT_SIZE;
 unsigned long __bootdata(memory_end);
@@ -229,6 +230,19 @@ void parse_boot_command_line(void)
 		if (!strcmp(param, "vmalloc") && val)
 			vmalloc_size = round_up(memparse(val, NULL), PAGE_SIZE);
 
+		if (!strcmp(param, "dfltcc")) {
+			if (!strcmp(val, "off"))
+				zlib_dfltcc_support = ZLIB_DFLTCC_DISABLED;
+			else if (!strcmp(val, "on"))
+				zlib_dfltcc_support = ZLIB_DFLTCC_FULL;
+			else if (!strcmp(val, "def_only"))
+				zlib_dfltcc_support = ZLIB_DFLTCC_DEFLATE_ONLY;
+			else if (!strcmp(val, "inf_only"))
+				zlib_dfltcc_support = ZLIB_DFLTCC_INFLATE_ONLY;
+			else if (!strcmp(val, "always"))
+				zlib_dfltcc_support = ZLIB_DFLTCC_FULL_DEBUG;
+		}
+
 		if (!strcmp(param, "noexec")) {
 			rc = kstrtobool(val, &enabled);
 			if (!rc && !enabled)

arch/s390/include/asm/setup.h

@@ -79,6 +79,13 @@ struct parmarea {
 	char command_line[ARCH_COMMAND_LINE_SIZE];	/* 0x10480 */
 };
 
+extern unsigned int zlib_dfltcc_support;
+#define ZLIB_DFLTCC_DISABLED		0
+#define ZLIB_DFLTCC_FULL		1
+#define ZLIB_DFLTCC_DEFLATE_ONLY	2
+#define ZLIB_DFLTCC_INFLATE_ONLY	3
+#define ZLIB_DFLTCC_FULL_DEBUG		4
+
 extern int noexec_disabled;
 extern int memory_end_set;
 extern unsigned long memory_end;

arch/s390/kernel/setup.c

@@ -111,6 +111,8 @@ unsigned long __bootdata_preserved(__etext_dma);
 unsigned long __bootdata_preserved(__sdma);
 unsigned long __bootdata_preserved(__edma);
 unsigned long __bootdata_preserved(__kaslr_offset);
+unsigned int __bootdata_preserved(zlib_dfltcc_support);
+EXPORT_SYMBOL(zlib_dfltcc_support);
 
 unsigned long VMALLOC_START;
 EXPORT_SYMBOL(VMALLOC_START);
@@ -759,14 +761,6 @@ static void __init free_mem_detect_info(void)
 		memblock_free(start, size);
 }
 
-static void __init memblock_physmem_add(phys_addr_t start, phys_addr_t size)
-{
-	memblock_dbg("memblock_physmem_add: [%#016llx-%#016llx]\n",
-		     start, start + size - 1);
-	memblock_add_range(&memblock.memory, start, size, 0, 0);
-	memblock_add_range(&memblock.physmem, start, size, 0, 0);
-}
-
 static const char * __init get_mem_info_source(void)
 {
 	switch (mem_detect.info_source) {
@@ -791,8 +785,10 @@ static void __init memblock_add_mem_detect_info(void)
 		     get_mem_info_source(), mem_detect.info_source);
 	/* keep memblock lists close to the kernel */
 	memblock_set_bottom_up(true);
-	for_each_mem_detect_block(i, &start, &end)
+	for_each_mem_detect_block(i, &start, &end) {
+		memblock_add(start, end - start);
 		memblock_physmem_add(start, end - start);
+	}
 	memblock_set_bottom_up(false);
 	memblock_dump_all();
 }

drivers/acpi/thermal.c

@@ -27,6 +27,7 @@
 #include <linux/acpi.h>
 #include <linux/workqueue.h>
 #include <linux/uaccess.h>
+#include <linux/units.h>
 
 #define PREFIX "ACPI: "
 
@@ -172,7 +173,7 @@ struct acpi_thermal {
 	struct acpi_handle_list devices;
 	struct thermal_zone_device *thermal_zone;
 	int tz_enabled;
-	int kelvin_offset;
+	int kelvin_offset;	/* in millidegrees */
 	struct work_struct thermal_check_work;
 };
 
@@ -297,7 +298,8 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag)
 			if (crt == -1) {
 				tz->trips.critical.flags.valid = 0;
 			} else if (crt > 0) {
-				unsigned long crt_k = CELSIUS_TO_DECI_KELVIN(crt);
+				unsigned long crt_k = celsius_to_deci_kelvin(crt);
+
 				/*
 				 * Allow override critical threshold
 				 */
@@ -333,7 +335,7 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag)
 		if (psv == -1) {
 			status = AE_SUPPORT;
 		} else if (psv > 0) {
-			tmp = CELSIUS_TO_DECI_KELVIN(psv);
+			tmp = celsius_to_deci_kelvin(psv);
 			status = AE_OK;
 		} else {
 			status = acpi_evaluate_integer(tz->device->handle,
@@ -413,7 +415,7 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag)
 					break;
 				if (i == 1)
 					tz->trips.active[0].temperature =
-						CELSIUS_TO_DECI_KELVIN(act);
+						celsius_to_deci_kelvin(act);
 				else
 					/*
 					 * Don't allow override higher than
@@ -421,9 +423,9 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag)
 					 */
 					tz->trips.active[i - 1].temperature =
 						(tz->trips.active[i - 2].temperature <
-						CELSIUS_TO_DECI_KELVIN(act) ?
+						celsius_to_deci_kelvin(act) ?
 						tz->trips.active[i - 2].temperature :
-						CELSIUS_TO_DECI_KELVIN(act));
+						celsius_to_deci_kelvin(act));
 				break;
 			} else {
 				tz->trips.active[i].temperature = tmp;
@@ -519,7 +521,7 @@ static int thermal_get_temp(struct thermal_zone_device *thermal, int *temp)
 	if (result)
 		return result;
 
-	*temp = DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(tz->temperature,
+	*temp = deci_kelvin_to_millicelsius_with_offset(tz->temperature,
 							tz->kelvin_offset);
 	return 0;
 }
@@ -624,7 +626,7 @@ static int thermal_get_trip_temp(struct thermal_zone_device *thermal,
 
 	if (tz->trips.critical.flags.valid) {
 		if (!trip) {
-			*temp = DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(
+			*temp = deci_kelvin_to_millicelsius_with_offset(
 				tz->trips.critical.temperature,
 				tz->kelvin_offset);
 			return 0;
@@ -634,7 +636,7 @@ static int thermal_get_trip_temp(struct thermal_zone_device *thermal,
 
 	if (tz->trips.hot.flags.valid) {
 		if (!trip) {
-			*temp = DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(
+			*temp = deci_kelvin_to_millicelsius_with_offset(
 				tz->trips.hot.temperature,
 				tz->kelvin_offset);
 			return 0;
@@ -644,7 +646,7 @@ static int thermal_get_trip_temp(struct thermal_zone_device *thermal,
 
 	if (tz->trips.passive.flags.valid) {
 		if (!trip) {
-			*temp = DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(
+			*temp = deci_kelvin_to_millicelsius_with_offset(
 				tz->trips.passive.temperature,
 				tz->kelvin_offset);
 			return 0;
@@ -655,7 +657,7 @@ static int thermal_get_trip_temp(struct thermal_zone_device *thermal,
 	for (i = 0; i < ACPI_THERMAL_MAX_ACTIVE &&
 		tz->trips.active[i].flags.valid; i++) {
 		if (!trip) {
-			*temp = DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(
+			*temp = deci_kelvin_to_millicelsius_with_offset(
 				tz->trips.active[i].temperature,
 				tz->kelvin_offset);
 			return 0;
@@ -672,7 +674,7 @@ static int thermal_get_crit_temp(struct thermal_zone_device *thermal,
 	struct acpi_thermal *tz = thermal->devdata;
 
 	if (tz->trips.critical.flags.valid) {
-		*temperature = DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(
+		*temperature = deci_kelvin_to_millicelsius_with_offset(
 				tz->trips.critical.temperature,
 				tz->kelvin_offset);
 		return 0;
@@ -692,7 +694,7 @@ static int thermal_get_trend(struct thermal_zone_device *thermal,
 
 	if (type == THERMAL_TRIP_ACTIVE) {
 		int trip_temp;
-		int temp = DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(
+		int temp = deci_kelvin_to_millicelsius_with_offset(
 					tz->temperature, tz->kelvin_offset);
 		if (thermal_get_trip_temp(thermal, trip, &trip_temp))
 			return -EINVAL;
@@ -1043,9 +1045,9 @@ static void acpi_thermal_guess_offset(struct acpi_thermal *tz)
 {
 	if (tz->trips.critical.flags.valid &&
 	    (tz->trips.critical.temperature % 5) == 1)
-		tz->kelvin_offset = 2731;
+		tz->kelvin_offset = 273100;
 	else
-		tz->kelvin_offset = 2732;
+		tz->kelvin_offset = 273200;
 }
 
 static void acpi_thermal_check_fn(struct work_struct *work)
@@ -1087,7 +1089,7 @@ static int acpi_thermal_add(struct acpi_device *device)
 	INIT_WORK(&tz->thermal_check_work, acpi_thermal_check_fn);
 
 	pr_info(PREFIX "%s [%s] (%ld C)\n", acpi_device_name(device),
-		acpi_device_bid(device), DECI_KELVIN_TO_CELSIUS(tz->temperature));
+		acpi_device_bid(device), deci_kelvin_to_celsius(tz->temperature));
 	goto end;
 
 free_memory:

drivers/base/memory.c

@@ -70,20 +70,6 @@ void unregister_memory_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL(unregister_memory_notifier);
 
-static ATOMIC_NOTIFIER_HEAD(memory_isolate_chain);
-
-int register_memory_isolate_notifier(struct notifier_block *nb)
-{
-	return atomic_notifier_chain_register(&memory_isolate_chain, nb);
-}
-EXPORT_SYMBOL(register_memory_isolate_notifier);
-
-void unregister_memory_isolate_notifier(struct notifier_block *nb)
-{
-	atomic_notifier_chain_unregister(&memory_isolate_chain, nb);
-}
-EXPORT_SYMBOL(unregister_memory_isolate_notifier);
-
 static void memory_block_release(struct device *dev)
 {
 	struct memory_block *mem = to_memory_block(dev);
@@ -175,11 +161,6 @@ int memory_notify(unsigned long val, void *v)
 	return blocking_notifier_call_chain(&memory_chain, val, v);
 }
 
-int memory_isolate_notify(unsigned long val, void *v)
-{
-	return atomic_notifier_call_chain(&memory_isolate_chain, val, v);
-}
-
 /*
  * The probe routines leave the pages uninitialized, just as the bootmem code
  * does. Make sure we do not access them, but instead use only information from
@@ -225,7 +206,7 @@ static bool pages_correctly_probed(unsigned long start_pfn)
  */
 static int
 memory_block_action(unsigned long start_section_nr, unsigned long action,
-		    int online_type)
+		    int online_type, int nid)
 {
 	unsigned long start_pfn;
 	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
@@ -238,7 +219,7 @@ memory_block_action(unsigned long start_section_nr, unsigned long action,
 		if (!pages_correctly_probed(start_pfn))
 			return -EBUSY;
 
-		ret = online_pages(start_pfn, nr_pages, online_type);
+		ret = online_pages(start_pfn, nr_pages, online_type, nid);
 		break;
 	case MEM_OFFLINE:
 		ret = offline_pages(start_pfn, nr_pages);
@@ -264,7 +245,7 @@ static int memory_block_change_state(struct memory_block *mem,
 		mem->state = MEM_GOING_OFFLINE;
 
 	ret = memory_block_action(mem->start_section_nr, to_state,
-				mem->online_type);
+				  mem->online_type, mem->nid);
 
 	mem->state = ret ? from_state_req : to_state;
 

drivers/block/zram/zram_drv.c

@@ -207,14 +207,17 @@ static inline void zram_fill_page(void *ptr, unsigned long len,
 
 static bool page_same_filled(void *ptr, unsigned long *element)
 {
-	unsigned int pos;
 	unsigned long *page;
 	unsigned long val;
+	unsigned int pos, last_pos = PAGE_SIZE / sizeof(*page) - 1;
 
 	page = (unsigned long *)ptr;
 	val = page[0];
 
-	for (pos = 1; pos < PAGE_SIZE / sizeof(*page); pos++) {
+	if (val != page[last_pos])
+		return false;
+
+	for (pos = 1; pos < last_pos; pos++) {
 		if (val != page[pos])
 			return false;
 	}
@@ -626,7 +629,7 @@ static ssize_t writeback_store(struct device *dev,
 	struct bio bio;
 	struct bio_vec bio_vec;
 	struct page *page;
-	ssize_t ret;
+	ssize_t ret = len;
 	int mode;
 	unsigned long blk_idx = 0;
 
@@ -762,7 +765,6 @@ next:
 
 	if (blk_idx)
 		free_block_bdev(zram, blk_idx);
-	ret = len;
 	__free_page(page);
 release_init_lock:
 	up_read(&zram->init_lock);

drivers/gpu/drm/via/via_dmablit.c

@@ -188,8 +188,8 @@ via_free_sg_info(struct pci_dev *pdev, drm_via_sg_info_t *vsg)
 		kfree(vsg->desc_pages);
 		/* fall through */
 	case dr_via_pages_locked:
-		put_user_pages_dirty_lock(vsg->pages, vsg->num_pages,
-					  (vsg->direction == DMA_FROM_DEVICE));
+		unpin_user_pages_dirty_lock(vsg->pages, vsg->num_pages,
+					   (vsg->direction == DMA_FROM_DEVICE));
 		/* fall through */
 	case dr_via_pages_alloc:
 		vfree(vsg->pages);
@@ -239,7 +239,7 @@ via_lock_all_dma_pages(drm_via_sg_info_t *vsg,  drm_via_dmablit_t *xfer)
 	vsg->pages = vzalloc(array_size(sizeof(struct page *), vsg->num_pages));
 	if (NULL == vsg->pages)
 		return -ENOMEM;
-	ret = get_user_pages_fast((unsigned long)xfer->mem_addr,
+	ret = pin_user_pages_fast((unsigned long)xfer->mem_addr,
 			vsg->num_pages,
 			vsg->direction == DMA_FROM_DEVICE ? FOLL_WRITE : 0,
 			vsg->pages);

drivers/iio/adc/qcom-vadc-common.c

@@ -6,6 +6,7 @@
 #include <linux/log2.h>
 #include <linux/err.h>
 #include <linux/module.h>
+#include <linux/units.h>
 
 #include "qcom-vadc-common.h"
 
@@ -236,8 +237,7 @@ static int qcom_vadc_scale_die_temp(const struct vadc_linear_graph *calib_graph,
 		voltage = 0;
 	}
 
-	voltage -= KELVINMIL_CELSIUSMIL;
-	*result_mdec = voltage;
+	*result_mdec = milli_kelvin_to_millicelsius(voltage);
 
 	return 0;
 }
@@ -325,7 +325,7 @@ static int qcom_vadc_scale_hw_calib_die_temp(
 {
 	*result_mdec = qcom_vadc_scale_code_voltage_factor(adc_code,
 				prescale, data, 2);
-	*result_mdec -= KELVINMIL_CELSIUSMIL;
+	*result_mdec = milli_kelvin_to_millicelsius(*result_mdec);
 
 	return 0;
 }

drivers/iio/adc/qcom-vadc-common.h

@@ -38,7 +38,6 @@
 #define VADC_AVG_SAMPLES_MAX			512
 #define ADC5_AVG_SAMPLES_MAX			16
 
-#define KELVINMIL_CELSIUSMIL			273150
 #define PMIC5_CHG_TEMP_SCALE_FACTOR		377500
 #define PMIC5_SMB_TEMP_CONSTANT			419400
 #define PMIC5_SMB_TEMP_SCALE_FACTOR		356

drivers/infiniband/core/umem.c

@@ -54,7 +54,7 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d
 
 	for_each_sg_page(umem->sg_head.sgl, &sg_iter, umem->sg_nents, 0) {
 		page = sg_page_iter_page(&sg_iter);
-		put_user_pages_dirty_lock(&page, 1, umem->writable && dirty);
+		unpin_user_pages_dirty_lock(&page, 1, umem->writable && dirty);
 	}
 
 	sg_free_table(&umem->sg_head);
@@ -257,16 +257,13 @@ struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr,
 	sg = umem->sg_head.sgl;
 
 	while (npages) {
-		down_read(&mm->mmap_sem);
-		ret = get_user_pages(cur_base,
-				     min_t(unsigned long, npages,
-					   PAGE_SIZE / sizeof (struct page *)),
-				     gup_flags | FOLL_LONGTERM,
-				     page_list, NULL);
-		if (ret < 0) {
-			up_read(&mm->mmap_sem);
+		ret = pin_user_pages_fast(cur_base,
+					  min_t(unsigned long, npages,
+						PAGE_SIZE /
+						sizeof(struct page *)),
+					  gup_flags | FOLL_LONGTERM, page_list);
+		if (ret < 0)
 			goto umem_release;
-		}
 
 		cur_base += ret * PAGE_SIZE;
 		npages   -= ret;
@@ -274,8 +271,6 @@ struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr,
 		sg = ib_umem_add_sg_table(sg, page_list, ret,
 			dma_get_max_seg_size(device->dma_device),
 			&umem->sg_nents);
-
-		up_read(&mm->mmap_sem);
 	}
 
 	sg_mark_end(sg);

drivers/infiniband/core/umem_odp.c

@@ -293,9 +293,8 @@ EXPORT_SYMBOL(ib_umem_odp_release);
  * The function returns -EFAULT if the DMA mapping operation fails. It returns
  * -EAGAIN if a concurrent invalidation prevents us from updating the page.
  *
- * The page is released via put_user_page even if the operation failed. For
- * on-demand pinning, the page is released whenever it isn't stored in the
- * umem.
+ * The page is released via put_page even if the operation failed. For on-demand
+ * pinning, the page is released whenever it isn't stored in the umem.
  */
 static int ib_umem_odp_map_dma_single_page(
 		struct ib_umem_odp *umem_odp,
@@ -348,7 +347,7 @@ static int ib_umem_odp_map_dma_single_page(
 	}
 
 out:
-	put_user_page(page);
+	put_page(page);
 	return ret;
 }
 
@@ -458,7 +457,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 					ret = -EFAULT;
 					break;
 				}
-				put_user_page(local_page_list[j]);
+				put_page(local_page_list[j]);
 				continue;
 			}
 
@@ -485,8 +484,8 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 			 * ib_umem_odp_map_dma_single_page().
 			 */
 			if (npages - (j + 1) > 0)
-				put_user_pages(&local_page_list[j+1],
-					       npages - (j + 1));
+				release_pages(&local_page_list[j+1],
+					      npages - (j + 1));
 			break;
 		}
 	}

drivers/infiniband/hw/hfi1/user_pages.c

@@ -106,7 +106,7 @@ int hfi1_acquire_user_pages(struct mm_struct *mm, unsigned long vaddr, size_t np
 	int ret;
 	unsigned int gup_flags = FOLL_LONGTERM | (writable ? FOLL_WRITE : 0);
 
-	ret = get_user_pages_fast(vaddr, npages, gup_flags, pages);
+	ret = pin_user_pages_fast(vaddr, npages, gup_flags, pages);
 	if (ret < 0)
 		return ret;
 
@@ -118,7 +118,7 @@ int hfi1_acquire_user_pages(struct mm_struct *mm, unsigned long vaddr, size_t np
 void hfi1_release_user_pages(struct mm_struct *mm, struct page **p,
 			     size_t npages, bool dirty)
 {
-	put_user_pages_dirty_lock(p, npages, dirty);
+	unpin_user_pages_dirty_lock(p, npages, dirty);
 
 	if (mm) { /* during close after signal, mm can be NULL */
 		atomic64_sub(npages, &mm->pinned_vm);

drivers/infiniband/hw/mthca/mthca_memfree.c

@@ -472,7 +472,7 @@ int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar,
 		goto out;
 	}
 
-	ret = get_user_pages_fast(uaddr & PAGE_MASK, 1,
+	ret = pin_user_pages_fast(uaddr & PAGE_MASK, 1,
 				  FOLL_WRITE | FOLL_LONGTERM, pages);
 	if (ret < 0)
 		goto out;
@@ -482,7 +482,7 @@ int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar,
 
 	ret = pci_map_sg(dev->pdev, &db_tab->page[i].mem, 1, PCI_DMA_TODEVICE);
 	if (ret < 0) {
-		put_user_page(pages[0]);
+		unpin_user_page(pages[0]);
 		goto out;
 	}
 
@@ -490,7 +490,7 @@ int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar,
 				 mthca_uarc_virt(dev, uar, i));
 	if (ret) {
 		pci_unmap_sg(dev->pdev, &db_tab->page[i].mem, 1, PCI_DMA_TODEVICE);
-		put_user_page(sg_page(&db_tab->page[i].mem));
+		unpin_user_page(sg_page(&db_tab->page[i].mem));
 		goto out;
 	}
 
@@ -556,7 +556,7 @@ void mthca_cleanup_user_db_tab(struct mthca_dev *dev, struct mthca_uar *uar,
 		if (db_tab->page[i].uvirt) {
 			mthca_UNMAP_ICM(dev, mthca_uarc_virt(dev, uar, i), 1);
 			pci_unmap_sg(dev->pdev, &db_tab->page[i].mem, 1, PCI_DMA_TODEVICE);
-			put_user_page(sg_page(&db_tab->page[i].mem));
+			unpin_user_page(sg_page(&db_tab->page[i].mem));
 		}
 	}
 

drivers/infiniband/hw/qib/qib_user_pages.c

@@ -40,7 +40,7 @@
 static void __qib_release_user_pages(struct page **p, size_t num_pages,
 				     int dirty)
 {
-	put_user_pages_dirty_lock(p, num_pages, dirty);
+	unpin_user_pages_dirty_lock(p, num_pages, dirty);
 }
 
 /**
@@ -108,7 +108,7 @@ int qib_get_user_pages(unsigned long start_page, size_t num_pages,
 
 	down_read(&current->mm->mmap_sem);
 	for (got = 0; got < num_pages; got += ret) {
-		ret = get_user_pages(start_page + got * PAGE_SIZE,
+		ret = pin_user_pages(start_page + got * PAGE_SIZE,
 				     num_pages - got,
 				     FOLL_LONGTERM | FOLL_WRITE | FOLL_FORCE,
 				     p + got, NULL);