Merge branch 'akpm' (patches from Andrew)

7eec11d3 · Linus Torvalds <[email protected]> · 2020-01-31 12:16:36 -08:00

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 <[email protected]>: (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
  ...

Commit: 7eec11d3a784a283f916590e5aa30b855c2ccfd7
Parents: ddaefe89 · 43e76af8

Merge commit. Changes below are compared with the first parent: ddaefe89.

Changes

136 files changed · +2724 −1293

File	Status	Add	Del	Content
Documentation/admin-guide/kernel-parameters.txt	modified	+12	−0	View file
Documentation/core-api/index.rst	modified	+1	−0	View file
Documentation/core-api/pin_user_pages.rst	added	+232	−0	View file
Documentation/vm/zswap.rst	modified	+13	−0	View file
arch/powerpc/mm/book3s64/iommu_api.c	modified	+5	−5	View file
arch/s390/boot/compressed/decompressor.c	modified	+4	−4	View file
arch/s390/boot/ipl_parm.c	modified	+14	−0	View file
arch/s390/include/asm/setup.h	modified	+7	−0	View file
arch/s390/kernel/setup.c	modified	+5	−9	View file
drivers/acpi/thermal.c	modified	+18	−16	View file
drivers/base/memory.c	modified	+3	−22	View file
drivers/block/zram/zram_drv.c	modified	+6	−4	View file
drivers/gpu/drm/via/via_dmablit.c	modified	+3	−3	View file
drivers/iio/adc/qcom-vadc-common.c	modified	+3	−3	View file
drivers/iio/adc/qcom-vadc-common.h	modified	+0	−1	View file
drivers/infiniband/core/umem.c	modified	+7	−12	View file
drivers/infiniband/core/umem_odp.c	modified	+6	−7	View file
drivers/infiniband/hw/hfi1/user_pages.c	modified	+2	−2	View file
drivers/infiniband/hw/mthca/mthca_memfree.c	modified	+4	−4	View file
drivers/infiniband/hw/qib/qib_user_pages.c	modified	+2	−2	View file
drivers/infiniband/hw/qib/qib_user_sdma.c	modified	+4	−4	View file
drivers/infiniband/hw/usnic/usnic_uiom.c	modified	+2	−2	View file
drivers/infiniband/sw/siw/siw_mem.c	modified	+2	−2	View file
drivers/media/v4l2-core/videobuf-dma-sg.c	modified	+4	−4	View file
drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h	modified	+0	−1	View file
drivers/net/wireless/intel/iwlegacy/4965-mac.c	modified	+2	−1	View file
drivers/net/wireless/intel/iwlegacy/4965.c	modified	+9	−8	View file
drivers/net/wireless/intel/iwlegacy/common.h	modified	+0	−3	View file
drivers/net/wireless/intel/iwlwifi/dvm/dev.h	modified	+0	−5	View file
drivers/net/wireless/intel/iwlwifi/dvm/devices.c	modified	+4	−2	View file
drivers/nvdimm/pmem.c	modified	+0	−6	View file
drivers/nvme/host/hwmon.c	modified	+5	−8	View file
drivers/platform/goldfish/goldfish_pipe.c	modified	+12	−23	View file
drivers/platform/x86/asus-wmi.c	modified	+3	−4	View file
drivers/platform/x86/intel_menlow.c	modified	+6	−3	View file
drivers/thermal/armada_thermal.c	modified	+0	−2	View file
drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c	modified	+4	−3	View file
drivers/thermal/intel/intel_pch_thermal.c	modified	+2	−1	View file
drivers/vfio/vfio_iommu_type1.c	modified	+7	−28	View file
fs/binfmt_elf.c	modified	+74	−70	View file
fs/btrfs/compression.c	modified	+1	−1	View file
fs/btrfs/zlib.c	modified	+100	−35	View file
fs/exec.c	modified	+5	−0	View file
fs/fs-writeback.c	modified	+1	−1	View file
fs/io_uring.c	modified	+3	−3	View file
fs/ocfs2/cluster/quorum.c	modified	+1	−1	View file
fs/ocfs2/dlm/Makefile	modified	+0	−2	View file
fs/ocfs2/dlm/dlmast.c	modified	+4	−4	View file
fs/ocfs2/dlm/dlmcommon.h	modified	+0	−4	View file
fs/ocfs2/dlm/dlmconvert.c	modified	+4	−4	View file
fs/ocfs2/dlm/dlmdebug.c	modified	+4	−4	View file
fs/ocfs2/dlm/dlmdomain.c	modified	+4	−4	View file
fs/ocfs2/dlm/dlmlock.c	modified	+4	−4	View file
fs/ocfs2/dlm/dlmmaster.c	modified	+4	−6	View file
fs/ocfs2/dlm/dlmrecovery.c	modified	+5	−5	View file
fs/ocfs2/dlm/dlmthread.c	modified	+4	−4	View file
fs/ocfs2/dlm/dlmunlock.c	modified	+4	−4	View file
fs/ocfs2/dlmfs/Makefile	modified	+0	−2	View file
fs/ocfs2/dlmfs/dlmfs.c	modified	+2	−2	View file
fs/ocfs2/dlmfs/userdlm.c	modified	+3	−3	View file
fs/ocfs2/dlmglue.c	modified	+1	−1	View file
fs/ocfs2/journal.h	modified	+5	−3	View file
fs/ocfs2/namei.c	modified	+1	−2	View file
fs/reiserfs/stree.c	modified	+2	−1	View file
include/linux/backing-dev.h	modified	+10	−0	View file
include/linux/bitops.h	modified	+1	−0	View file
include/linux/fs.h	modified	+5	−1	View file
include/linux/io-mapping.h	modified	+2	−3	View file
include/linux/memblock.h	modified	+3	−4	View file
include/linux/memory.h	modified	+0	−29	View file
include/linux/memory_hotplug.h	modified	+2	−1	View file
include/linux/mm.h	modified	+70	−34	View file
include/linux/mmzone.h	modified	+1	−1	View file
include/linux/page-isolation.h	modified	+2	−2	View file
include/linux/swab.h	modified	+1	−0	View file
include/linux/thermal.h	modified	+0	−11	View file
include/linux/units.h	added	+84	−0	View file
include/linux/zlib.h	modified	+6	−0	View file
include/trace/events/kmem.h	modified	+2	−2	View file
include/trace/events/writeback.h	modified	+17	−20	View file
include/uapi/linux/swab.h	modified	+10	−0	View file
include/uapi/linux/sysctl.h	modified	+1	−1	View file
init/main.c	modified	+27	−9	View file
kernel/Makefile	modified	+1	−0	View file
lib/Kconfig	modified	+7	−0	View file
lib/Makefile	modified	+2	−0	View file
lib/decompress_inflate.c	modified	+13	−0	View file
lib/find_bit.c	modified	+20	−58	View file
lib/scatterlist.c	modified	+1	−1	View file
lib/test_bitmap.c	modified	+5	−4	View file
lib/test_kasan.c	modified	+1	−0	View file
lib/zlib_deflate/deflate.c	modified	+47	−38	View file
lib/zlib_deflate/deflate_syms.c	modified	+1	−0	View file
lib/zlib_deflate/deftree.c	modified	+0	−54	View file
lib/zlib_deflate/defutil.h	modified	+124	−10	View file
lib/zlib_dfltcc/Makefile	added	+11	−0	View file
lib/zlib_dfltcc/dfltcc.c	added	+55	−0	View file
lib/zlib_dfltcc/dfltcc.h	added	+155	−0	View file
lib/zlib_dfltcc/dfltcc_deflate.c	added	+279	−0	View file
lib/zlib_dfltcc/dfltcc_inflate.c	added	+149	−0	View file
lib/zlib_dfltcc/dfltcc_syms.c	added	+17	−0	View file
lib/zlib_dfltcc/dfltcc_util.h	added	+103	−0	View file
lib/zlib_inflate/inflate.c	modified	+24	−8	View file
lib/zlib_inflate/inflate.h	modified	+8	−0	View file
lib/zlib_inflate/infutil.h	modified	+16	−2	View file
mm/Makefile	modified	+1	−0	View file
mm/backing-dev.c	modified	+1	−0	View file
mm/debug.c	modified	+13	−3	View file
mm/early_ioremap.c	modified	+4	−4	View file
mm/filemap.c	modified	+6	−28	View file
mm/gup.c	modified	+310	−191	View file
mm/gup_benchmark.c	modified	+6	−3	View file
mm/huge_memory.c	modified	+18	−26	View file
mm/kmemleak.c	modified	+56	−56	View file
mm/memblock.c	modified	+17	−5	View file
mm/memcontrol.c	modified	+3	−22	View file
mm/memory_hotplug.c	modified	+9	−15	View file
mm/mempolicy.c	modified	+3	−3	View file
mm/memremap.c	modified	+35	−40	View file
mm/migrate.c	modified	+51	−26	View file
mm/mmap.c	modified	+16	−20	View file
mm/oom_kill.c	modified	+2	−0	View file
mm/page_alloc.c	modified	+44	−31	View file
mm/page_isolation.c	modified	+18	−35	View file
mm/page_vma_mapped.c	modified	+8	−4	View file
mm/process_vm_access.c	modified	+15	−13	View file
mm/slub.c	modified	+47	−41	View file
mm/sparse.c	modified	+1	−1	View file
mm/swap.c	modified	+26	−1	View file
mm/swapfile.c	modified	+1	−1	View file
mm/vmscan.c	modified	+3	−21	View file
mm/zswap.c	modified	+55	−31	View file
net/xdp/xdp_umem.c	modified	+2	−2	View file
scripts/spelling.txt	modified	+14	−0	View file
tools/testing/selftests/vm/gup_benchmark.c	modified	+5	−1	View file
tools/vm/slabinfo.c	modified	+2	−2	View file

Only the first 600 diff lines are shown. Download the complete patch.

Documentation/admin-guide/kernel-parameters.txt

View file

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index ec92120..ddc5ccd 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/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

View file

diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst
index bc0c727..a501dc1 100644
--- a/Documentation/core-api/index.rst
+++ b/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

View file

diff --git a/Documentation/core-api/pin_user_pages.rst b/Documentation/core-api/pin_user_pages.rst
new file mode 100644
index 0000000..1d49015
--- /dev/null
+++ b/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

View file

diff --git a/Documentation/vm/zswap.rst b/Documentation/vm/zswap.rst
index 1444ecd..61f6185 100644
--- a/Documentation/vm/zswap.rst
+++ b/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

View file

diff --git a/arch/powerpc/mm/book3s64/iommu_api.c b/arch/powerpc/mm/book3s64/iommu_api.c
index 56cc845..eba73eb 100644
--- a/arch/powerpc/mm/book3s64/iommu_api.c
+++ b/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

View file

diff --git a/arch/s390/boot/compressed/decompressor.c b/arch/s390/boot/compressed/decompressor.c
index 4504663..368fd37 100644
--- a/arch/s390/boot/compressed/decompressor.c
+++ b/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

View file

diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c
index 24ef67e..357adad 100644
--- a/arch/s390/boot/ipl_parm.c
+++ b/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

View file

diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 69289e9..b241ddb 100644
--- a/arch/s390/include/asm/setup.h
+++ b/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

View file

diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 87a467d..b2c2f75 100644
--- a/arch/s390/kernel/setup.c
+++ b/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

View file

diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index d831a61..19067a5 100644
--- a/drivers/acpi/thermal.c
+++ b/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: