summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--Documentation/admin-guide/kernel-parameters.txt12
-rw-r--r--Documentation/core-api/index.rst1
-rw-r--r--Documentation/core-api/pin_user_pages.rst232
-rw-r--r--Documentation/vm/zswap.rst13
-rw-r--r--arch/powerpc/mm/book3s64/iommu_api.c10
-rw-r--r--arch/s390/boot/compressed/decompressor.c8
-rw-r--r--arch/s390/boot/ipl_parm.c14
-rw-r--r--arch/s390/include/asm/setup.h7
-rw-r--r--arch/s390/kernel/setup.c14
-rw-r--r--drivers/acpi/thermal.c34
-rw-r--r--drivers/base/memory.c25
-rw-r--r--drivers/block/zram/zram_drv.c10
-rw-r--r--drivers/gpu/drm/via/via_dmablit.c6
-rw-r--r--drivers/iio/adc/qcom-vadc-common.c6
-rw-r--r--drivers/iio/adc/qcom-vadc-common.h1
-rw-r--r--drivers/infiniband/core/umem.c19
-rw-r--r--drivers/infiniband/core/umem_odp.c13
-rw-r--r--drivers/infiniband/hw/hfi1/user_pages.c4
-rw-r--r--drivers/infiniband/hw/mthca/mthca_memfree.c8
-rw-r--r--drivers/infiniband/hw/qib/qib_user_pages.c4
-rw-r--r--drivers/infiniband/hw/qib/qib_user_sdma.c8
-rw-r--r--drivers/infiniband/hw/usnic/usnic_uiom.c4
-rw-r--r--drivers/infiniband/sw/siw/siw_mem.c4
-rw-r--r--drivers/media/v4l2-core/videobuf-dma-sg.c8
-rw-r--r--drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h1
-rw-r--r--drivers/net/wireless/intel/iwlegacy/4965-mac.c3
-rw-r--r--drivers/net/wireless/intel/iwlegacy/4965.c17
-rw-r--r--drivers/net/wireless/intel/iwlegacy/common.h3
-rw-r--r--drivers/net/wireless/intel/iwlwifi/dvm/dev.h5
-rw-r--r--drivers/net/wireless/intel/iwlwifi/dvm/devices.c6
-rw-r--r--drivers/nvdimm/pmem.c6
-rw-r--r--drivers/nvme/host/hwmon.c13
-rw-r--r--drivers/platform/goldfish/goldfish_pipe.c35
-rw-r--r--drivers/platform/x86/asus-wmi.c7
-rw-r--r--drivers/platform/x86/intel_menlow.c9
-rw-r--r--drivers/thermal/armada_thermal.c2
-rw-r--r--drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c7
-rw-r--r--drivers/thermal/intel/intel_pch_thermal.c3
-rw-r--r--drivers/vfio/vfio_iommu_type1.c35
-rw-r--r--fs/binfmt_elf.c144
-rw-r--r--fs/btrfs/compression.c2
-rw-r--r--fs/btrfs/zlib.c135
-rw-r--r--fs/exec.c5
-rw-r--r--fs/fs-writeback.c2
-rw-r--r--fs/io_uring.c6
-rw-r--r--fs/ocfs2/cluster/quorum.c2
-rw-r--r--fs/ocfs2/dlm/Makefile2
-rw-r--r--fs/ocfs2/dlm/dlmast.c8
-rw-r--r--fs/ocfs2/dlm/dlmcommon.h4
-rw-r--r--fs/ocfs2/dlm/dlmconvert.c8
-rw-r--r--fs/ocfs2/dlm/dlmdebug.c8
-rw-r--r--fs/ocfs2/dlm/dlmdomain.c8
-rw-r--r--fs/ocfs2/dlm/dlmlock.c8
-rw-r--r--fs/ocfs2/dlm/dlmmaster.c10
-rw-r--r--fs/ocfs2/dlm/dlmrecovery.c10
-rw-r--r--fs/ocfs2/dlm/dlmthread.c8
-rw-r--r--fs/ocfs2/dlm/dlmunlock.c8
-rw-r--r--fs/ocfs2/dlmfs/Makefile2
-rw-r--r--fs/ocfs2/dlmfs/dlmfs.c4
-rw-r--r--fs/ocfs2/dlmfs/userdlm.c6
-rw-r--r--fs/ocfs2/dlmglue.c2
-rw-r--r--fs/ocfs2/journal.h8
-rw-r--r--fs/ocfs2/namei.c3
-rw-r--r--fs/reiserfs/stree.c3
-rw-r--r--include/linux/backing-dev.h10
-rw-r--r--include/linux/bitops.h1
-rw-r--r--include/linux/fs.h6
-rw-r--r--include/linux/io-mapping.h5
-rw-r--r--include/linux/memblock.h7
-rw-r--r--include/linux/memory.h29
-rw-r--r--include/linux/memory_hotplug.h3
-rw-r--r--include/linux/mm.h104
-rw-r--r--include/linux/mmzone.h2
-rw-r--r--include/linux/page-isolation.h4
-rw-r--r--include/linux/swab.h1
-rw-r--r--include/linux/thermal.h11
-rw-r--r--include/linux/units.h84
-rw-r--r--include/linux/zlib.h6
-rw-r--r--include/trace/events/kmem.h4
-rw-r--r--include/trace/events/writeback.h37
-rw-r--r--include/uapi/linux/swab.h10
-rw-r--r--include/uapi/linux/sysctl.h2
-rw-r--r--init/main.c36
-rw-r--r--kernel/Makefile1
-rw-r--r--lib/Kconfig7
-rw-r--r--lib/Makefile2
-rw-r--r--lib/decompress_inflate.c13
-rw-r--r--lib/find_bit.c78
-rw-r--r--lib/scatterlist.c2
-rw-r--r--lib/test_bitmap.c9
-rw-r--r--lib/test_kasan.c1
-rw-r--r--lib/zlib_deflate/deflate.c85
-rw-r--r--lib/zlib_deflate/deflate_syms.c1
-rw-r--r--lib/zlib_deflate/deftree.c54
-rw-r--r--lib/zlib_deflate/defutil.h134
-rw-r--r--lib/zlib_dfltcc/Makefile11
-rw-r--r--lib/zlib_dfltcc/dfltcc.c55
-rw-r--r--lib/zlib_dfltcc/dfltcc.h155
-rw-r--r--lib/zlib_dfltcc/dfltcc_deflate.c279
-rw-r--r--lib/zlib_dfltcc/dfltcc_inflate.c149
-rw-r--r--lib/zlib_dfltcc/dfltcc_syms.c17
-rw-r--r--lib/zlib_dfltcc/dfltcc_util.h103
-rw-r--r--lib/zlib_inflate/inflate.c32
-rw-r--r--lib/zlib_inflate/inflate.h8
-rw-r--r--lib/zlib_inflate/infutil.h18
-rw-r--r--mm/Makefile1
-rw-r--r--mm/backing-dev.c1
-rw-r--r--mm/debug.c16
-rw-r--r--mm/early_ioremap.c8
-rw-r--r--mm/filemap.c34
-rw-r--r--mm/gup.c501
-rw-r--r--mm/gup_benchmark.c9
-rw-r--r--mm/huge_memory.c44
-rw-r--r--mm/kmemleak.c112
-rw-r--r--mm/memblock.c22
-rw-r--r--mm/memcontrol.c25
-rw-r--r--mm/memory_hotplug.c24
-rw-r--r--mm/mempolicy.c6
-rw-r--r--mm/memremap.c75
-rw-r--r--mm/migrate.c77
-rw-r--r--mm/mmap.c36
-rw-r--r--mm/oom_kill.c2
-rw-r--r--mm/page_alloc.c75
-rw-r--r--mm/page_isolation.c53
-rw-r--r--mm/page_vma_mapped.c12
-rw-r--r--mm/process_vm_access.c28
-rw-r--r--mm/slub.c88
-rw-r--r--mm/sparse.c2
-rw-r--r--mm/swap.c27
-rw-r--r--mm/swapfile.c2
-rw-r--r--mm/vmscan.c24
-rw-r--r--mm/zswap.c86
-rw-r--r--net/xdp/xdp_umem.c4
-rw-r--r--scripts/spelling.txt14
-rw-r--r--tools/testing/selftests/vm/gup_benchmark.c6
-rw-r--r--tools/vm/slabinfo.c4
136 files changed, 2724 insertions, 1293 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index ec92120a7952..ddc5ccdd4cd1 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.
diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst
index bc0c727d7fd8..a501dc1c90d0 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
diff --git a/Documentation/core-api/pin_user_pages.rst b/Documentation/core-api/pin_user_pages.rst
new file mode 100644
index 000000000000..1d490155ecd7
--- /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
diff --git a/Documentation/vm/zswap.rst b/Documentation/vm/zswap.rst
index 1444ecd40911..61f6185188cd 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.
diff --git a/arch/powerpc/mm/book3s64/iommu_api.c b/arch/powerpc/mm/book3s64/iommu_api.c
index 56cc84520577..eba73ebd8ae5 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;
}
}
diff --git a/arch/s390/boot/compressed/decompressor.c b/arch/s390/boot/compressed/decompressor.c
index 45046630c56a..368fd372c875 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)
{
diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c
index 24ef67eb1cef..357adad991d2 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)
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 69289e99cabd..b241ddb67caf 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;
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 87a467dff5eb..b2c2f75860e8 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();
}
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index d831a61e0010..19067a5e5293 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:
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 799b43191dea..15659306ad69 100644
--- a/drivers/base/memory.c
+++ b/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;
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 4285e75e52c3..1bdb5793842b 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/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);
diff --git a/drivers/gpu/drm/via/via_dmablit.c b/drivers/gpu/drm/via/via_dmablit.c
index d13a3897506e..551fa31629af 100644
--- a/drivers/gpu/drm/via/via_dmablit.c
+++ b/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);
diff --git a/drivers/iio/adc/qcom-vadc-common.c b/drivers/iio/adc/qcom-vadc-common.c
index dcd7fb5b9fb2..2bb78d1c4daa 100644
--- a/drivers/iio/adc/qcom-vadc-common.c
+++ b/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;
}
diff --git a/drivers/iio/adc/qcom-vadc-common.h b/drivers/iio/adc/qcom-vadc-common.h
index bbb1fa02b382..e074902a24cc 100644
--- a/drivers/iio/adc/qcom-vadc-common.h
+++ b/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
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 146f98fbf22b..c3769a5f096d 100644
--- a/drivers/infiniband/core/umem.c
+++ b/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);
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index dac3fd2ebc26..a71ce0ae2031 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/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;
}
}
diff --git a/drivers/infiniband/hw/hfi1/user_pages.c b/drivers/infiniband/hw/hfi1/user_pages.c
index 469acb961fbd..3b505006c0a6 100644
--- a/drivers/infiniband/hw/hfi1/user_pages.c
+++ b/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);
diff --git a/drivers/infiniband/hw/mthca/mthca_memfree.c b/drivers/infiniband/hw/mthca/mthca_memfree.c
index edccfd6e178f..78a48aea3faf 100644
--- a/drivers/infiniband/hw/mthca/mthca_memfree.c
+++ b/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));
}
}
diff --git a/drivers/infiniband/hw/qib/qib_user_pages.c b/drivers/infiniband/hw/qib/qib_user_pages.c
index 6bf764e41891..342e3172ca40 100644
--- a/drivers/infiniband/hw/qib/qib_user_pages.c
+++ b/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);
diff --git a/drivers/infiniband/hw/qib/qib_user_sdma.c b/drivers/infiniband/hw/qib/qib_user_sdma.c
index 05190edc2611..a67599b5a550 100644
--- a/drivers/infiniband/hw/qib/qib_user_sdma.c
+++ b/drivers/infiniband/hw/qib/qib_user_sdma.c
@@ -317,7 +317,7 @@ static int qib_user_sdma_page_to_frags(const struct qib_devdata *dd,
* the caller can ignore this page.
*/
if (put) {
- put_user_page(page);
+ unpin_user_page(page);
} else {
/* coalesce case */
kunmap(page);
@@ -631,7 +631,7 @@ static void qib_user_sdma_free_pkt_frag(struct device *dev,
kunmap(pkt->addr[i].page);
if (pkt->addr[i].put_page)
- put_user_page(pkt->addr[i].page);
+ unpin_user_page(pkt->addr[i].page);
else
__free_page(pkt->addr[i].page);
} else if (pkt->addr[i].kvaddr) {
@@ -670,7 +670,7 @@ static int qib_user_sdma_pin_pages(const struct qib_devdata *dd,
else
j = npages;
- ret = get_user_pages_fast(addr, j, FOLL_LONGTERM, pages);
+ ret = pin_user_pages_fast(addr, j, FOLL_LONGTERM, pages);
if (ret != j) {
i = 0;
j = ret;
@@ -706,7 +706,7 @@ static int qib_user_sdma_pin_pages(const struct qib_devdata *dd,
/* if error, return all pages not managed by pkt */
free_pages:
while (i < j)
- put_user_page(pages[i++]);
+ unpin_user_page(pages[i++]);
done:
return ret;
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c
index 62e6ffa9ad78..bd9f944b68fc 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom.c
@@ -75,7 +75,7 @@ static void usnic_uiom_put_pages(struct list_head *chunk_list, int dirty)
for_each_sg(chunk->page_list, sg, chunk->nents, i) {
page = sg_page(sg);
pa = sg_phys(sg);
- put_user_pages_dirty_lock(&page, 1, dirty);
+ unpin_user_pages_dirty_lock(&page, 1, dirty);
usnic_dbg("pa: %pa\n", &pa);
}
kfree(chunk);
@@ -141,7 +141,7 @@ static int usnic_uiom_get_pages(unsigned long addr, size_t size, int writable,
ret = 0;
while (npages) {
- ret = get_user_pages(cur_base,
+ ret = pin_user_pages(cur_base,
min_t(unsigned long, npages,
PAGE_SIZE / sizeof(struct page *)),
gup_flags | FOLL_LONGTERM,
diff --git a/drivers/infiniband/sw/siw/siw_mem.c b/drivers/infiniband/sw/siw/siw_mem.c
index e99983f07663..e2061dc0b043 100644
--- a/drivers/infiniband/sw/siw/siw_mem.c
+++ b/drivers/infiniband/sw/siw/siw_mem.c
@@ -63,7 +63,7 @@ struct siw_mem *siw_mem_id2obj(struct siw_device *sdev, int stag_index)
static void siw_free_plist(struct siw_page_chunk *chunk, int num_pages,
bool dirty)
{
- put_user_pages_dirty_lock(chunk->plist, num_pages, dirty);
+ unpin_user_pages_dirty_lock(chunk->plist, num_pages, dirty);
}
void siw_umem_release(struct siw_umem *umem, bool dirty)
@@ -426,7 +426,7 @@ struct siw_umem *siw_umem_get(u64 start, u64 len, bool writable)
while (nents) {
struct page **plist = &umem->page_chunk[i].plist[got];
- rv = get_user_pages(first_page_va, nents,
+ rv = pin_user_pages(first_page_va, nents,
foll_flags | FOLL_LONGTERM,
plist, NULL);
if (rv < 0)
diff --git a/drivers/media/v4l2-core/videobuf-dma-sg.c b/drivers/media/v4l2-core/videobuf-dma-sg.c
index 66a6c6c236a7..13b65ed9e74c 100644
--- a/drivers/media/v4l2-core/videobuf-dma-sg.c
+++ b/drivers/media/v4l2-core/videobuf-dma-sg.c
@@ -183,12 +183,12 @@ static int videobuf_dma_init_user_locked(struct videobuf_dmabuf *dma,
dprintk(1, "init user [0x%lx+0x%lx => %d pages]\n",
data, size, dma->nr_pages);
- err = get_user_pages(data & PAGE_MASK, dma->nr_pages,
+ err = pin_user_pages(data & PAGE_MASK, dma->nr_pages,
flags | FOLL_LONGTERM, dma->pages, NULL);
if (err != dma->nr_pages) {
dma->nr_pages = (err >= 0) ? err : 0;
- dprintk(1, "get_user_pages: err=%d [%d]\n", err,
+ dprintk(1, "pin_user_pages: err=%d [%d]\n", err,
dma->nr_pages);
return err < 0 ? err : -EINVAL;
}
@@ -349,8 +349,8 @@ int videobuf_dma_free(struct videobuf_dmabuf *dma)
BUG_ON(dma->sglen);
if (dma->pages) {
- for (i = 0; i < dma->nr_pages; i++)
- put_page(dma->pages[i]);
+ unpin_user_pages_dirty_lock(dma->pages, dma->nr_pages,
+ dma->direction == DMA_FROM_DEVICE);
kfree(dma->pages);
dma->pages = NULL;
}
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h
index 066765fbef06..0a59a09ef82f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h
@@ -296,7 +296,6 @@ static inline void bnx2x_dcb_config_qm(struct bnx2x *bp, enum cos_mode mode,
* possible, the driver should only write the valid vnics into the internal
* ram according to the appropriate port mode.
*/
-#define BITS_TO_BYTES(x) ((x)/8)
/* CMNG constants, as derived from system spec calculations */
diff --git a/drivers/net/wireless/intel/iwlegacy/4965-mac.c b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
index d1e17589dbeb..da6d4202611c 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
@@ -27,6 +27,7 @@
#include <linux/firmware.h>
#include <linux/etherdevice.h>
#include <linux/if_arp.h>
+#include <linux/units.h>
#include <net/mac80211.h>
@@ -6468,7 +6469,7 @@ il4965_set_hw_params(struct il_priv *il)
il->hw_params.valid_rx_ant = il->cfg->valid_rx_ant;
il->hw_params.ct_kill_threshold =
- CELSIUS_TO_KELVIN(CT_KILL_THRESHOLD_LEGACY);
+ celsius_to_kelvin(CT_KILL_THRESHOLD_LEGACY);
il->hw_params.sens = &il4965_sensitivity;
il->hw_params.beacon_time_tsf_bits = IL4965_EXT_BEACON_TIME_POS;
diff --git a/drivers/net/wireless/intel/iwlegacy/4965.c b/drivers/net/wireless/intel/iwlegacy/4965.c
index 32699b6a68c2..34d0579132ce 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965.c
@@ -17,6 +17,7 @@
#include <linux/sched.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
+#include <linux/units.h>
#include <net/mac80211.h>
#include <linux/etherdevice.h>
#include <asm/unaligned.h>
@@ -1104,7 +1105,7 @@ il4965_fill_txpower_tbl(struct il_priv *il, u8 band, u16 channel, u8 is_ht40,
/* get current temperature (Celsius) */
current_temp = max(il->temperature, IL_TX_POWER_TEMPERATURE_MIN);
current_temp = min(il->temperature, IL_TX_POWER_TEMPERATURE_MAX);
- current_temp = KELVIN_TO_CELSIUS(current_temp);
+ current_temp = kelvin_to_celsius(current_temp);
/* select thermal txpower adjustment params, based on channel group
* (same frequency group used for mimo txatten adjustment) */
@@ -1610,8 +1611,8 @@ il4965_hw_get_temperature(struct il_priv *il)
temperature =
(temperature * 97) / 100 + TEMPERATURE_CALIB_KELVIN_OFFSET;
- D_TEMP("Calibrated temperature: %dK, %dC\n", temperature,
- KELVIN_TO_CELSIUS(temperature));
+ D_TEMP("Calibrated temperature: %dK, %ldC\n", temperature,
+ kelvin_to_celsius(temperature));
return temperature;
}
@@ -1670,12 +1671,12 @@ il4965_temperature_calib(struct il_priv *il)
if (il->temperature != temp) {
if (il->temperature)
- D_TEMP("Temperature changed " "from %dC to %dC\n",
- KELVIN_TO_CELSIUS(il->temperature),
- KELVIN_TO_CELSIUS(temp));
+ D_TEMP("Temperature changed " "from %ldC to %ldC\n",
+ kelvin_to_celsius(il->temperature),
+ kelvin_to_celsius(temp));
else
- D_TEMP("Temperature " "initialized to %dC\n",
- KELVIN_TO_CELSIUS(temp));
+ D_TEMP("Temperature " "initialized to %ldC\n",
+ kelvin_to_celsius(temp));
}
il->temperature = temp;
diff --git a/drivers/net/wireless/intel/iwlegacy/common.h b/drivers/net/wireless/intel/iwlegacy/common.h
index e7fb8e6bb9e7..bc9cd7e5ccb8 100644
--- a/drivers/net/wireless/intel/iwlegacy/common.h
+++ b/drivers/net/wireless/intel/iwlegacy/common.h
@@ -779,9 +779,6 @@ struct il_sensitivity_ranges {
u16 nrg_th_cca;
};
-#define KELVIN_TO_CELSIUS(x) ((x)-273)
-#define CELSIUS_TO_KELVIN(x) ((x)+273)
-
/**
* struct il_hw_params
* @bcast_id: f/w broadcast station ID
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/dev.h b/drivers/net/wireless/intel/iwlwifi/dvm/dev.h
index be5ef4c3e9d0..8d8380026180 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/dev.h
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/dev.h
@@ -237,11 +237,6 @@ struct iwl_sensitivity_ranges {
u16 nrg_th_cca;
};
-
-#define KELVIN_TO_CELSIUS(x) ((x)-273)
-#define CELSIUS_TO_KELVIN(x) ((x)+273)
-
-
/******************************************************************************
*
* Functions implemented in core module which are forward declared here
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/devices.c b/drivers/net/wireless/intel/iwlwifi/dvm/devices.c
index dc3f197f94d9..d42bc46fe566 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/devices.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/devices.c
@@ -10,6 +10,8 @@
*
*****************************************************************************/
+#include <linux/units.h>
+
/*
* DVM device-specific data & functions
*/
@@ -345,7 +347,7 @@ static s32 iwl_temp_calib_to_offset(struct iwl_priv *priv)
static void iwl5150_set_ct_threshold(struct iwl_priv *priv)
{
const s32 volt2temp_coef = IWL_5150_VOLTAGE_TO_TEMPERATURE_COEFF;
- s32 threshold = (s32)CELSIUS_TO_KELVIN(CT_KILL_THRESHOLD_LEGACY) -
+ s32 threshold = (s32)celsius_to_kelvin(CT_KILL_THRESHOLD_LEGACY) -
iwl_temp_calib_to_offset(priv);
priv->hw_params.ct_kill_threshold = threshold * volt2temp_coef;
@@ -381,7 +383,7 @@ static void iwl5150_temperature(struct iwl_priv *priv)
vt = le32_to_cpu(priv->statistics.common.temperature);
vt = vt / IWL_5150_VOLTAGE_TO_TEMPERATURE_COEFF + offset;
/* now vt hold the temperature in Kelvin */
- priv->temperature = KELVIN_TO_CELSIUS(vt);
+ priv->temperature = kelvin_to_celsius(vt);
iwl_tt_handler(priv);
}
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index ad8e4df1282b..4eae441f86c9 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -337,13 +337,7 @@ static void pmem_release_disk(void *__pmem)
put_disk(pmem->disk);
}
-static void pmem_pagemap_page_free(struct page *page)
-{
- wake_up_var(&page->_refcount);
-}
-
static const struct dev_pagemap_ops fsdax_pagemap_ops = {
- .page_free = pmem_pagemap_page_free,
.kill = pmem_pagemap_kill,
.cleanup = pmem_pagemap_cleanup,
};
diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c
index a5af21f5d370..2e6477ed420f 100644
--- a/drivers/nvme/host/hwmon.c
+++ b/drivers/nvme/host/hwmon.c
@@ -5,14 +5,11 @@
*/
#include <linux/hwmon.h>
+#include <linux/units.h>
#include <asm/unaligned.h>
#include "nvme.h"
-/* These macros should be moved to linux/temperature.h */
-#define MILLICELSIUS_TO_KELVIN(t) DIV_ROUND_CLOSEST((t) + 273150, 1000)
-#define KELVIN_TO_MILLICELSIUS(t) ((t) * 1000L - 273150)
-
struct nvme_hwmon_data {
struct nvme_ctrl *ctrl;
struct nvme_smart_log log;
@@ -35,7 +32,7 @@ static int nvme_get_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under,
return -EIO;
if (ret < 0)
return ret;
- *temp = KELVIN_TO_MILLICELSIUS(status & NVME_TEMP_THRESH_MASK);
+ *temp = kelvin_to_millicelsius(status & NVME_TEMP_THRESH_MASK);
return 0;
}
@@ -46,7 +43,7 @@ static int nvme_set_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under,
unsigned int threshold = sensor << NVME_TEMP_THRESH_SELECT_SHIFT;
int ret;
- temp = MILLICELSIUS_TO_KELVIN(temp);
+ temp = millicelsius_to_kelvin(temp);
threshold |= clamp_val(temp, 0, NVME_TEMP_THRESH_MASK);
if (under)
@@ -88,7 +85,7 @@ static int nvme_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
case hwmon_temp_min:
return nvme_get_temp_thresh(data->ctrl, channel, true, val);
case hwmon_temp_crit:
- *val = KELVIN_TO_MILLICELSIUS(data->ctrl->cctemp);
+ *val = kelvin_to_millicelsius(data->ctrl->cctemp);
return 0;
default:
break;
@@ -105,7 +102,7 @@ static int nvme_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
temp = get_unaligned_le16(log->temperature);
else
temp = le16_to_cpu(log->temp_sensor[channel - 1]);
- *val = KELVIN_TO_MILLICELSIUS(temp);
+ *val = kelvin_to_millicelsius(temp);
break;
case hwmon_temp_alarm:
*val = !!(log->critical_warning & NVME_SMART_CRIT_TEMPERATURE);
diff --git a/drivers/platform/goldfish/goldfish_pipe.c b/drivers/platform/goldfish/goldfish_pipe.c
index cef0133aa47a..1ab207ec9c94 100644
--- a/drivers/platform/goldfish/goldfish_pipe.c
+++ b/drivers/platform/goldfish/goldfish_pipe.c
@@ -257,12 +257,12 @@ static int goldfish_pipe_error_convert(int status)
}
}
-static int pin_user_pages(unsigned long first_page,
- unsigned long last_page,
- unsigned int last_page_size,
- int is_write,
- struct page *pages[MAX_BUFFERS_PER_COMMAND],
- unsigned int *iter_last_page_size)
+static int goldfish_pin_pages(unsigned long first_page,
+ unsigned long last_page,
+ unsigned int last_page_size,
+ int is_write,
+ struct page *pages[MAX_BUFFERS_PER_COMMAND],
+ unsigned int *iter_last_page_size)
{
int ret;
int requested_pages = ((last_page - first_page) >> PAGE_SHIFT) + 1;
@@ -274,7 +274,7 @@ static int pin_user_pages(unsigned long first_page,
*iter_last_page_size = last_page_size;
}
- ret = get_user_pages_fast(first_page, requested_pages,
+ ret = pin_user_pages_fast(first_page, requested_pages,
!is_write ? FOLL_WRITE : 0,
pages);
if (ret <= 0)
@@ -285,18 +285,6 @@ static int pin_user_pages(unsigned long first_page,
return ret;
}
-static void release_user_pages(struct page **pages, int pages_count,
- int is_write, s32 consumed_size)
-{
- int i;
-
- for (i = 0; i < pages_count; i++) {
- if (!is_write && consumed_size > 0)
- set_page_dirty(pages[i]);
- put_page(pages[i]);
- }
-}
-
/* Populate the call parameters, merging adjacent pages together */
static void populate_rw_params(struct page **pages,
int pages_count,
@@ -354,9 +342,9 @@ static int transfer_max_buffers(struct goldfish_pipe *pipe,
if (mutex_lock_interruptible(&pipe->lock))
return -ERESTARTSYS;
- pages_count = pin_user_pages(first_page, last_page,
- last_page_size, is_write,
- pipe->pages, &iter_last_page_size);
+ pages_count = goldfish_pin_pages(first_page, last_page,
+ last_page_size, is_write,
+ pipe->pages, &iter_last_page_size);
if (pages_count < 0) {
mutex_unlock(&pipe->lock);
return pages_count;
@@ -372,7 +360,8 @@ static int transfer_max_buffers(struct goldfish_pipe *pipe,
*consumed_size = pipe->command_buffer->rw_params.consumed_size;
- release_user_pages(pipe->pages, pages_count, is_write, *consumed_size);
+ unpin_user_pages_dirty_lock(pipe->pages, pages_count,
+ !is_write && *consumed_size > 0);
mutex_unlock(&pipe->lock);
return 0;
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 43bb15e05529..612ef5526226 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -33,9 +33,9 @@
#include <linux/seq_file.h>
#include <linux/platform_data/x86/asus-wmi.h>
#include <linux/platform_device.h>
-#include <linux/thermal.h>
#include <linux/acpi.h>
#include <linux/dmi.h>
+#include <linux/units.h>
#include <acpi/battery.h>
#include <acpi/video.h>
@@ -1514,9 +1514,8 @@ static ssize_t asus_hwmon_temp1(struct device *dev,
if (err < 0)
return err;
- value = DECI_KELVIN_TO_CELSIUS((value & 0xFFFF)) * 1000;
-
- return sprintf(buf, "%d\n", value);
+ return sprintf(buf, "%ld\n",
+ deci_kelvin_to_millicelsius(value & 0xFFFF));
}
/* Fan1 */
diff --git a/drivers/platform/x86/intel_menlow.c b/drivers/platform/x86/intel_menlow.c
index b102f6dd5693..101d7e791a13 100644
--- a/drivers/platform/x86/intel_menlow.c
+++ b/drivers/platform/x86/intel_menlow.c
@@ -22,6 +22,7 @@
#include <linux/slab.h>
#include <linux/thermal.h>
#include <linux/types.h>
+#include <linux/units.h>
MODULE_AUTHOR("Thomas Sujith");
MODULE_AUTHOR("Zhang Rui");
@@ -302,8 +303,10 @@ static ssize_t aux_show(struct device *dev, struct device_attribute *dev_attr,
int result;
result = sensor_get_auxtrip(attr->handle, idx, &value);
+ if (result)
+ return result;
- return result ? result : sprintf(buf, "%lu", DECI_KELVIN_TO_CELSIUS(value));
+ return sprintf(buf, "%lu", deci_kelvin_to_celsius(value));
}
static ssize_t aux0_show(struct device *dev,
@@ -332,8 +335,8 @@ static ssize_t aux_store(struct device *dev, struct device_attribute *dev_attr,
if (value < 0)
return -EINVAL;
- result = sensor_set_auxtrip(attr->handle, idx,
- CELSIUS_TO_DECI_KELVIN(value));
+ result = sensor_set_auxtrip(attr->handle, idx,
+ celsius_to_deci_kelvin(value));
return result ? result : count;
}
diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
index 8c4d1244ee7a..7c447cd149e7 100644
--- a/drivers/thermal/armada_thermal.c
+++ b/drivers/thermal/armada_thermal.c
@@ -21,8 +21,6 @@
#include "thermal_core.h"
-#define TO_MCELSIUS(c) ((c) * 1000)
-
/* Thermal Manager Control and Status Register */
#define PMU_TDC0_SW_RST_MASK (0x1 << 1)
#define PMU_TM_DISABLE_OFFS 0
diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
index 75484d6c5056..432213272f1e 100644
--- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
+++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
@@ -8,6 +8,7 @@
#include <linux/init.h>
#include <linux/acpi.h>
#include <linux/thermal.h>
+#include <linux/units.h>
#include "int340x_thermal_zone.h"
static int int340x_thermal_get_zone_temp(struct thermal_zone_device *zone,
@@ -34,7 +35,7 @@ static int int340x_thermal_get_zone_temp(struct thermal_zone_device *zone,
*temp = (unsigned long)conv_temp * 10;
} else
/* _TMP returns the temperature in tenths of degrees Kelvin */
- *temp = DECI_KELVIN_TO_MILLICELSIUS(tmp);
+ *temp = deci_kelvin_to_millicelsius(tmp);
return 0;
}
@@ -116,7 +117,7 @@ static int int340x_thermal_set_trip_temp(struct thermal_zone_device *zone,
snprintf(name, sizeof(name), "PAT%d", trip);
status = acpi_execute_simple_method(d->adev->handle, name,
- MILLICELSIUS_TO_DECI_KELVIN(temp));
+ millicelsius_to_deci_kelvin(temp));
if (ACPI_FAILURE(status))
return -EIO;
@@ -163,7 +164,7 @@ static int int340x_thermal_get_trip_config(acpi_handle handle, char *name,
if (ACPI_FAILURE(status))
return -EIO;
- *temp = DECI_KELVIN_TO_MILLICELSIUS(r);
+ *temp = deci_kelvin_to_millicelsius(r);
return 0;
}
diff --git a/drivers/thermal/intel/intel_pch_thermal.c b/drivers/thermal/intel/intel_pch_thermal.c
index ed75a0c603e7..56401fd4708d 100644
--- a/drivers/thermal/intel/intel_pch_thermal.c
+++ b/drivers/thermal/intel/intel_pch_thermal.c
@@ -13,6 +13,7 @@
#include <linux/pci.h>
#include <linux/acpi.h>
#include <linux/thermal.h>
+#include <linux/units.h>
#include <linux/pm.h>
/* Intel PCH thermal Device IDs */
@@ -93,7 +94,7 @@ static void pch_wpt_add_acpi_psv_trip(struct pch_thermal_device *ptd,
if (ACPI_SUCCESS(status)) {
unsigned long trip_temp;
- trip_temp = DECI_KELVIN_TO_MILLICELSIUS(r);
+ trip_temp = deci_kelvin_to_millicelsius(r);
if (trip_temp) {
ptd->psv_temp = trip_temp;
ptd->psv_trip_id = *nr_trips;
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 2ada8e6cdb88..a177bf2c6683 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -309,9 +309,8 @@ static int put_pfn(unsigned long pfn, int prot)
{
if (!is_invalid_reserved_pfn(pfn)) {
struct page *page = pfn_to_page(pfn);
- if (prot & IOMMU_WRITE)
- SetPageDirty(page);
- put_page(page);
+
+ unpin_user_pages_dirty_lock(&page, 1, prot & IOMMU_WRITE);
return 1;
}
return 0;
@@ -322,7 +321,6 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
{
struct page *page[1];
struct vm_area_struct *vma;
- struct vm_area_struct *vmas[1];
unsigned int flags = 0;
int ret;
@@ -330,33 +328,14 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
flags |= FOLL_WRITE;
down_read(&mm->mmap_sem);
- if (mm == current->mm) {
- ret = get_user_pages(vaddr, 1, flags | FOLL_LONGTERM, page,
- vmas);
- } else {
- ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags, page,
- vmas, NULL);
- /*
- * The lifetime of a vaddr_get_pfn() page pin is
- * userspace-controlled. In the fs-dax case this could
- * lead to indefinite stalls in filesystem operations.
- * Disallow attempts to pin fs-dax pages via this
- * interface.
- */
- if (ret > 0 && vma_is_fsdax(vmas[0])) {
- ret = -EOPNOTSUPP;
- put_page(page[0]);
- }
- }
- up_read(&mm->mmap_sem);
-
+ ret = pin_user_pages_remote(NULL, mm, vaddr, 1, flags | FOLL_LONGTERM,
+ page, NULL, NULL);
if (ret == 1) {
*pfn = page_to_pfn(page[0]);
- return 0;
+ ret = 0;
+ goto done;
}
- down_read(&mm->mmap_sem);
-
vaddr = untagged_addr(vaddr);
vma = find_vma_intersection(mm, vaddr, vaddr + 1);
@@ -366,7 +345,7 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
if (is_invalid_reserved_pfn(*pfn))
ret = 0;
}
-
+done:
up_read(&mm->mmap_sem);
return ret;
}
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index ecd8d2698515..f4713ea76e82 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -97,7 +97,7 @@ static struct linux_binfmt elf_format = {
.min_coredump = ELF_EXEC_PAGESIZE,
};
-#define BAD_ADDR(x) ((unsigned long)(x) >= TASK_SIZE)
+#define BAD_ADDR(x) (unlikely((unsigned long)(x) >= TASK_SIZE))
static int set_brk(unsigned long start, unsigned long end, int prot)
{
@@ -161,9 +161,11 @@ static int padzero(unsigned long elf_bss)
#endif
static int
-create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
- unsigned long load_addr, unsigned long interp_load_addr)
+create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec,
+ unsigned long load_addr, unsigned long interp_load_addr,
+ unsigned long e_entry)
{
+ struct mm_struct *mm = current->mm;
unsigned long p = bprm->p;
int argc = bprm->argc;
int envc = bprm->envc;
@@ -176,7 +178,7 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
unsigned char k_rand_bytes[16];
int items;
elf_addr_t *elf_info;
- int ei_index = 0;
+ int ei_index;
const struct cred *cred = current_cred();
struct vm_area_struct *vma;
@@ -226,12 +228,12 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
return -EFAULT;
/* Create the ELF interpreter info */
- elf_info = (elf_addr_t *)current->mm->saved_auxv;
+ elf_info = (elf_addr_t *)mm->saved_auxv;
/* update AT_VECTOR_SIZE_BASE if the number of NEW_AUX_ENT() changes */
#define NEW_AUX_ENT(id, val) \
do { \
- elf_info[ei_index++] = id; \
- elf_info[ei_index++] = val; \
+ *elf_info++ = id; \
+ *elf_info++ = val; \
} while (0)
#ifdef ARCH_DLINFO
@@ -251,7 +253,7 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
NEW_AUX_ENT(AT_PHNUM, exec->e_phnum);
NEW_AUX_ENT(AT_BASE, interp_load_addr);
NEW_AUX_ENT(AT_FLAGS, 0);
- NEW_AUX_ENT(AT_ENTRY, exec->e_entry);
+ NEW_AUX_ENT(AT_ENTRY, e_entry);
NEW_AUX_ENT(AT_UID, from_kuid_munged(cred->user_ns, cred->uid));
NEW_AUX_ENT(AT_EUID, from_kuid_munged(cred->user_ns, cred->euid));
NEW_AUX_ENT(AT_GID, from_kgid_munged(cred->user_ns, cred->gid));
@@ -275,12 +277,13 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
}
#undef NEW_AUX_ENT
/* AT_NULL is zero; clear the rest too */
- memset(&elf_info[ei_index], 0,
- sizeof current->mm->saved_auxv - ei_index * sizeof elf_info[0]);
+ memset(elf_info, 0, (char *)mm->saved_auxv +
+ sizeof(mm->saved_auxv) - (char *)elf_info);
/* And advance past the AT_NULL entry. */
- ei_index += 2;
+ elf_info += 2;
+ ei_index = elf_info - (elf_addr_t *)mm->saved_auxv;
sp = STACK_ADD(p, ei_index);
items = (argc + 1) + (envc + 1) + 1;
@@ -299,7 +302,7 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
* Grow the stack manually; some architectures have a limit on how
* far ahead a user-space access may be in order to grow the stack.
*/
- vma = find_extend_vma(current->mm, bprm->p);
+ vma = find_extend_vma(mm, bprm->p);
if (!vma)
return -EFAULT;
@@ -308,7 +311,7 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
return -EFAULT;
/* Populate list of argv pointers back to argv strings. */
- p = current->mm->arg_end = current->mm->arg_start;
+ p = mm->arg_end = mm->arg_start;
while (argc-- > 0) {
size_t len;
if (__put_user((elf_addr_t)p, sp++))
@@ -320,10 +323,10 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
}
if (__put_user(0, sp++))
return -EFAULT;
- current->mm->arg_end = p;
+ mm->arg_end = p;
/* Populate list of envp pointers back to envp strings. */
- current->mm->env_end = current->mm->env_start = p;
+ mm->env_end = mm->env_start = p;
while (envc-- > 0) {
size_t len;
if (__put_user((elf_addr_t)p, sp++))
@@ -335,10 +338,10 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
}
if (__put_user(0, sp++))
return -EFAULT;
- current->mm->env_end = p;
+ mm->env_end = p;
/* Put the elf_info on the stack in the right place. */
- if (copy_to_user(sp, elf_info, ei_index * sizeof(elf_addr_t)))
+ if (copy_to_user(sp, mm->saved_auxv, ei_index * sizeof(elf_addr_t)))
return -EFAULT;
return 0;
}
@@ -689,15 +692,17 @@ static int load_elf_binary(struct linux_binprm *bprm)
int bss_prot = 0;
int retval, i;
unsigned long elf_entry;
+ unsigned long e_entry;
unsigned long interp_load_addr = 0;
unsigned long start_code, end_code, start_data, end_data;
unsigned long reloc_func_desc __maybe_unused = 0;
int executable_stack = EXSTACK_DEFAULT;
+ struct elfhdr *elf_ex = (struct elfhdr *)bprm->buf;
struct {
- struct elfhdr elf_ex;
struct elfhdr interp_elf_ex;
} *loc;
struct arch_elf_state arch_state = INIT_ARCH_ELF_STATE;
+ struct mm_struct *mm;
struct pt_regs *regs;
loc = kmalloc(sizeof(*loc), GFP_KERNEL);
@@ -705,30 +710,27 @@ static int load_elf_binary(struct linux_binprm *bprm)
retval = -ENOMEM;
goto out_ret;
}
-
- /* Get the exec-header */
- loc->elf_ex = *((struct elfhdr *)bprm->buf);
retval = -ENOEXEC;
/* First of all, some simple consistency checks */
- if (memcmp(loc->elf_ex.e_ident, ELFMAG, SELFMAG) != 0)
+ if (memcmp(elf_ex->e_ident, ELFMAG, SELFMAG) != 0)
goto out;
- if (loc->elf_ex.e_type != ET_EXEC && loc->elf_ex.e_type != ET_DYN)
+ if (elf_ex->e_type != ET_EXEC && elf_ex->e_type != ET_DYN)
goto out;
- if (!elf_check_arch(&loc->elf_ex))
+ if (!elf_check_arch(elf_ex))
goto out;
- if (elf_check_fdpic(&loc->elf_ex))
+ if (elf_check_fdpic(elf_ex))
goto out;
if (!bprm->file->f_op->mmap)
goto out;
- elf_phdata = load_elf_phdrs(&loc->elf_ex, bprm->file);
+ elf_phdata = load_elf_phdrs(elf_ex, bprm->file);
if (!elf_phdata)
goto out;
elf_ppnt = elf_phdata;
- for (i = 0; i < loc->elf_ex.e_phnum; i++, elf_ppnt++) {
+ for (i = 0; i < elf_ex->e_phnum; i++, elf_ppnt++) {
char *elf_interpreter;
if (elf_ppnt->p_type != PT_INTERP)
@@ -782,7 +784,7 @@ out_free_interp:
}
elf_ppnt = elf_phdata;
- for (i = 0; i < loc->elf_ex.e_phnum; i++, elf_ppnt++)
+ for (i = 0; i < elf_ex->e_phnum; i++, elf_ppnt++)
switch (elf_ppnt->p_type) {
case PT_GNU_STACK:
if (elf_ppnt->p_flags & PF_X)
@@ -792,7 +794,7 @@ out_free_interp:
break;
case PT_LOPROC ... PT_HIPROC:
- retval = arch_elf_pt_proc(&loc->elf_ex, elf_ppnt,
+ retval = arch_elf_pt_proc(elf_ex, elf_ppnt,
bprm->file, false,
&arch_state);
if (retval)
@@ -836,7 +838,7 @@ out_free_interp:
* still possible to return an error to the code that invoked
* the exec syscall.
*/
- retval = arch_check_elf(&loc->elf_ex,
+ retval = arch_check_elf(elf_ex,
!!interpreter, &loc->interp_elf_ex,
&arch_state);
if (retval)
@@ -849,8 +851,8 @@ out_free_interp:
/* Do this immediately, since STACK_TOP as used in setup_arg_pages
may depend on the personality. */
- SET_PERSONALITY2(loc->elf_ex, &arch_state);
- if (elf_read_implies_exec(loc->elf_ex, executable_stack))
+ SET_PERSONALITY2(*elf_ex, &arch_state);
+ if (elf_read_implies_exec(*elf_ex, executable_stack))
current->personality |= READ_IMPLIES_EXEC;
if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
@@ -877,7 +879,7 @@ out_free_interp:
/* Now we do a little grungy work by mmapping the ELF image into
the correct location in memory. */
for(i = 0, elf_ppnt = elf_phdata;
- i < loc->elf_ex.e_phnum; i++, elf_ppnt++) {
+ i < elf_ex->e_phnum; i++, elf_ppnt++) {
int elf_prot, elf_flags;
unsigned long k, vaddr;
unsigned long total_size = 0;
@@ -921,9 +923,9 @@ out_free_interp:
* If we are loading ET_EXEC or we have already performed
* the ET_DYN load_addr calculations, proceed normally.
*/
- if (loc->elf_ex.e_type == ET_EXEC || load_addr_set) {
+ if (elf_ex->e_type == ET_EXEC || load_addr_set) {
elf_flags |= MAP_FIXED;
- } else if (loc->elf_ex.e_type == ET_DYN) {
+ } else if (elf_ex->e_type == ET_DYN) {
/*
* This logic is run once for the first LOAD Program
* Header for ET_DYN binaries to calculate the
@@ -972,7 +974,7 @@ out_free_interp:
load_bias = ELF_PAGESTART(load_bias - vaddr);
total_size = total_mapping_size(elf_phdata,
- loc->elf_ex.e_phnum);
+ elf_ex->e_phnum);
if (!total_size) {
retval = -EINVAL;
goto out_free_dentry;
@@ -990,7 +992,7 @@ out_free_interp:
if (!load_addr_set) {
load_addr_set = 1;
load_addr = (elf_ppnt->p_vaddr - elf_ppnt->p_offset);
- if (loc->elf_ex.e_type == ET_DYN) {
+ if (elf_ex->e_type == ET_DYN) {
load_bias += error -
ELF_PAGESTART(load_bias + vaddr);
load_addr += load_bias;
@@ -998,7 +1000,7 @@ out_free_interp:
}
}
k = elf_ppnt->p_vaddr;
- if (k < start_code)
+ if ((elf_ppnt->p_flags & PF_X) && k < start_code)
start_code = k;
if (start_data < k)
start_data = k;
@@ -1031,7 +1033,7 @@ out_free_interp:
}
}
- loc->elf_ex.e_entry += load_bias;
+ e_entry = elf_ex->e_entry + load_bias;
elf_bss += load_bias;
elf_brk += load_bias;
start_code += load_bias;
@@ -1074,7 +1076,7 @@ out_free_interp:
allow_write_access(interpreter);
fput(interpreter);
} else {
- elf_entry = loc->elf_ex.e_entry;
+ elf_entry = e_entry;
if (BAD_ADDR(elf_entry)) {
retval = -EINVAL;
goto out_free_dentry;
@@ -1092,15 +1094,17 @@ out_free_interp:
goto out;
#endif /* ARCH_HAS_SETUP_ADDITIONAL_PAGES */
- retval = create_elf_tables(bprm, &loc->elf_ex,
- load_addr, interp_load_addr);
+ retval = create_elf_tables(bprm, elf_ex,
+ load_addr, interp_load_addr, e_entry);
if (retval < 0)
goto out;
- current->mm->end_code = end_code;
- current->mm->start_code = start_code;
- current->mm->start_data = start_data;
- current->mm->end_data = end_data;
- current->mm->start_stack = bprm->p;
+
+ mm = current->mm;
+ mm->end_code = end_code;
+ mm->start_code = start_code;
+ mm->start_data = start_data;
+ mm->end_data = end_data;
+ mm->start_stack = bprm->p;
if ((current->flags & PF_RANDOMIZE) && (randomize_va_space > 1)) {
/*
@@ -1111,12 +1115,11 @@ out_free_interp:
* growing down), and into the unused ELF_ET_DYN_BASE region.
*/
if (IS_ENABLED(CONFIG_ARCH_HAS_ELF_RANDOMIZE) &&
- loc->elf_ex.e_type == ET_DYN && !interpreter)
- current->mm->brk = current->mm->start_brk =
- ELF_ET_DYN_BASE;
+ elf_ex->e_type == ET_DYN && !interpreter) {
+ mm->brk = mm->start_brk = ELF_ET_DYN_BASE;
+ }
- current->mm->brk = current->mm->start_brk =
- arch_randomize_brk(current->mm);
+ mm->brk = mm->start_brk = arch_randomize_brk(mm);
#ifdef compat_brk_randomized
current->brk_randomized = 1;
#endif
@@ -1574,6 +1577,7 @@ static void fill_siginfo_note(struct memelfnote *note, user_siginfo_t *csigdata,
*/
static int fill_files_note(struct memelfnote *note)
{
+ struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
unsigned count, size, names_ofs, remaining, n;
user_long_t *data;
@@ -1581,7 +1585,7 @@ static int fill_files_note(struct memelfnote *note)
char *name_base, *name_curpos;
/* *Estimated* file count and total data size needed */
- count = current->mm->map_count;
+ count = mm->map_count;
if (count > UINT_MAX / 64)
return -EINVAL;
size = count * 64;
@@ -1591,6 +1595,10 @@ static int fill_files_note(struct memelfnote *note)
if (size >= MAX_FILE_NOTE_SIZE) /* paranoia check */
return -EINVAL;
size = round_up(size, PAGE_SIZE);
+ /*
+ * "size" can be 0 here legitimately.
+ * Let it ENOMEM and omit NT_FILE section which will be empty anyway.
+ */
data = kvmalloc(size, GFP_KERNEL);
if (ZERO_OR_NULL_PTR(data))
return -ENOMEM;
@@ -1599,7 +1607,7 @@ static int fill_files_note(struct memelfnote *note)
name_base = name_curpos = ((char *)data) + names_ofs;
remaining = size - names_ofs;
count = 0;
- for (vma = current->mm->mmap; vma != NULL; vma = vma->vm_next) {
+ for (vma = mm->mmap; vma != NULL; vma = vma->vm_next) {
struct file *file;
const char *filename;
@@ -1633,10 +1641,10 @@ static int fill_files_note(struct memelfnote *note)
data[0] = count;
data[1] = PAGE_SIZE;
/*
- * Count usually is less than current->mm->map_count,
+ * Count usually is less than mm->map_count,
* we need to move filenames down.
*/
- n = current->mm->map_count - count;
+ n = mm->map_count - count;
if (n != 0) {
unsigned shift_bytes = n * 3 * sizeof(data[0]);
memmove(name_base - shift_bytes, name_base,
@@ -2182,7 +2190,7 @@ static int elf_core_dump(struct coredump_params *cprm)
int segs, i;
size_t vma_data_size = 0;
struct vm_area_struct *vma, *gate_vma;
- struct elfhdr *elf = NULL;
+ struct elfhdr elf;
loff_t offset = 0, dataoff;
struct elf_note_info info = { };
struct elf_phdr *phdr4note = NULL;
@@ -2203,10 +2211,6 @@ static int elf_core_dump(struct coredump_params *cprm)
* exists while dumping the mm->vm_next areas to the core file.
*/
- /* alloc memory for large data structures: too large to be on stack */
- elf = kmalloc(sizeof(*elf), GFP_KERNEL);
- if (!elf)
- goto out;
/*
* The number of segs are recored into ELF header as 16bit value.
* Please check DEFAULT_MAX_MAP_COUNT definition when you modify here.
@@ -2230,7 +2234,7 @@ static int elf_core_dump(struct coredump_params *cprm)
* Collect all the non-memory information about the process for the
* notes. This also sets up the file header.
*/
- if (!fill_note_info(elf, e_phnum, &info, cprm->siginfo, cprm->regs))
+ if (!fill_note_info(&elf, e_phnum, &info, cprm->siginfo, cprm->regs))
goto cleanup;
has_dumped = 1;
@@ -2238,7 +2242,7 @@ static int elf_core_dump(struct coredump_params *cprm)
fs = get_fs();
set_fs(KERNEL_DS);
- offset += sizeof(*elf); /* Elf header */
+ offset += sizeof(elf); /* Elf header */
offset += segs * sizeof(struct elf_phdr); /* Program headers */
/* Write notes phdr entry */
@@ -2257,11 +2261,13 @@ static int elf_core_dump(struct coredump_params *cprm)
dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
- if (segs - 1 > ULONG_MAX / sizeof(*vma_filesz))
- goto end_coredump;
+ /*
+ * Zero vma process will get ZERO_SIZE_PTR here.
+ * Let coredump continue for register state at least.
+ */
vma_filesz = kvmalloc(array_size(sizeof(*vma_filesz), (segs - 1)),
GFP_KERNEL);
- if (ZERO_OR_NULL_PTR(vma_filesz))
+ if (!vma_filesz)
goto end_coredump;
for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
@@ -2281,12 +2287,12 @@ static int elf_core_dump(struct coredump_params *cprm)
shdr4extnum = kmalloc(sizeof(*shdr4extnum), GFP_KERNEL);
if (!shdr4extnum)
goto end_coredump;
- fill_extnum_info(elf, shdr4extnum, e_shoff, segs);
+ fill_extnum_info(&elf, shdr4extnum, e_shoff, segs);
}
offset = dataoff;
- if (!dump_emit(cprm, elf, sizeof(*elf)))
+ if (!dump_emit(cprm, &elf, sizeof(elf)))
goto end_coredump;
if (!dump_emit(cprm, phdr4note, sizeof(*phdr4note)))
@@ -2370,8 +2376,6 @@ cleanup:
kfree(shdr4extnum);
kvfree(vma_filesz);
kfree(phdr4note);
- kfree(elf);
-out:
return has_dumped;
}
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index de95ad27722f..9ab610cc9114 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -1290,7 +1290,7 @@ int btrfs_decompress_buf2page(const char *buf, unsigned long buf_start,
/* copy bytes from the working buffer into the pages */
while (working_bytes > 0) {
bytes = min_t(unsigned long, bvec.bv_len,
- PAGE_SIZE - buf_offset);
+ PAGE_SIZE - (buf_offset % PAGE_SIZE));
bytes = min(bytes, working_bytes);
kaddr = kmap_atomic(bvec.bv_page);
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index a6c90a003c12..05615a1099db 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -20,9 +20,13 @@
#include <linux/refcount.h>
#include "compression.h"
+/* workspace buffer size for s390 zlib hardware support */
+#define ZLIB_DFLTCC_BUF_SIZE (4 * PAGE_SIZE)
+
struct workspace {
z_stream strm;
char *buf;
+ unsigned int buf_size;
struct list_head list;
int level;
};
@@ -61,7 +65,21 @@ struct list_head *zlib_alloc_workspace(unsigned int level)
zlib_inflate_workspacesize());
workspace->strm.workspace = kvmalloc(workspacesize, GFP_KERNEL);
workspace->level = level;
- workspace->buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ workspace->buf = NULL;
+ /*
+ * In case of s390 zlib hardware support, allocate lager workspace
+ * buffer. If allocator fails, fall back to a single page buffer.
+ */
+ if (zlib_deflate_dfltcc_enabled()) {
+ workspace->buf = kmalloc(ZLIB_DFLTCC_BUF_SIZE,
+ __GFP_NOMEMALLOC | __GFP_NORETRY |
+ __GFP_NOWARN | GFP_NOIO);
+ workspace->buf_size = ZLIB_DFLTCC_BUF_SIZE;
+ }
+ if (!workspace->buf) {
+ workspace->buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ workspace->buf_size = PAGE_SIZE;
+ }
if (!workspace->strm.workspace || !workspace->buf)
goto fail;
@@ -85,6 +103,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
struct page *in_page = NULL;
struct page *out_page = NULL;
unsigned long bytes_left;
+ unsigned int in_buf_pages;
unsigned long len = *total_out;
unsigned long nr_dest_pages = *out_pages;
const unsigned long max_out = nr_dest_pages * PAGE_SIZE;
@@ -102,9 +121,6 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
workspace->strm.total_in = 0;
workspace->strm.total_out = 0;
- in_page = find_get_page(mapping, start >> PAGE_SHIFT);
- data_in = kmap(in_page);
-
out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
if (out_page == NULL) {
ret = -ENOMEM;
@@ -114,12 +130,51 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
pages[0] = out_page;
nr_pages = 1;
- workspace->strm.next_in = data_in;
+ workspace->strm.next_in = workspace->buf;
+ workspace->strm.avail_in = 0;
workspace->strm.next_out = cpage_out;
workspace->strm.avail_out = PAGE_SIZE;
- workspace->strm.avail_in = min(len, PAGE_SIZE);
while (workspace->strm.total_in < len) {
+ /*
+ * Get next input pages and copy the contents to
+ * the workspace buffer if required.
+ */
+ if (workspace->strm.avail_in == 0) {
+ bytes_left = len - workspace->strm.total_in;
+ in_buf_pages = min(DIV_ROUND_UP(bytes_left, PAGE_SIZE),
+ workspace->buf_size / PAGE_SIZE);
+ if (in_buf_pages > 1) {
+ int i;
+
+ for (i = 0; i < in_buf_pages; i++) {
+ if (in_page) {
+ kunmap(in_page);
+ put_page(in_page);
+ }
+ in_page = find_get_page(mapping,
+ start >> PAGE_SHIFT);
+ data_in = kmap(in_page);
+ memcpy(workspace->buf + i * PAGE_SIZE,
+ data_in, PAGE_SIZE);
+ start += PAGE_SIZE;
+ }
+ workspace->strm.next_in = workspace->buf;
+ } else {
+ if (in_page) {
+ kunmap(in_page);
+ put_page(in_page);
+ }
+ in_page = find_get_page(mapping,
+ start >> PAGE_SHIFT);
+ data_in = kmap(in_page);
+ start += PAGE_SIZE;
+ workspace->strm.next_in = data_in;
+ }
+ workspace->strm.avail_in = min(bytes_left,
+ (unsigned long) workspace->buf_size);
+ }
+
ret = zlib_deflate(&workspace->strm, Z_SYNC_FLUSH);
if (ret != Z_OK) {
pr_debug("BTRFS: deflate in loop returned %d\n",
@@ -161,33 +216,43 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
/* we're all done */
if (workspace->strm.total_in >= len)
break;
-
- /* we've read in a full page, get a new one */
- if (workspace->strm.avail_in == 0) {
- if (workspace->strm.total_out > max_out)
- break;
-
- bytes_left = len - workspace->strm.total_in;
- kunmap(in_page);
- put_page(in_page);
-
- start += PAGE_SIZE;
- in_page = find_get_page(mapping,
- start >> PAGE_SHIFT);
- data_in = kmap(in_page);
- workspace->strm.avail_in = min(bytes_left,
- PAGE_SIZE);
- workspace->strm.next_in = data_in;
- }
+ if (workspace->strm.total_out > max_out)
+ break;
}
workspace->strm.avail_in = 0;
- ret = zlib_deflate(&workspace->strm, Z_FINISH);
- zlib_deflateEnd(&workspace->strm);
-
- if (ret != Z_STREAM_END) {
- ret = -EIO;
- goto out;
+ /*
+ * Call deflate with Z_FINISH flush parameter providing more output
+ * space but no more input data, until it returns with Z_STREAM_END.
+ */
+ while (ret != Z_STREAM_END) {
+ ret = zlib_deflate(&workspace->strm, Z_FINISH);
+ if (ret == Z_STREAM_END)
+ break;
+ if (ret != Z_OK && ret != Z_BUF_ERROR) {
+ zlib_deflateEnd(&workspace->strm);
+ ret = -EIO;
+ goto out;
+ } else if (workspace->strm.avail_out == 0) {
+ /* get another page for the stream end */
+ kunmap(out_page);
+ if (nr_pages == nr_dest_pages) {
+ out_page = NULL;
+ ret = -E2BIG;
+ goto out;
+ }
+ out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
+ if (out_page == NULL) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ cpage_out = kmap(out_page);
+ pages[nr_pages] = out_page;
+ nr_pages++;
+ workspace->strm.avail_out = PAGE_SIZE;
+ workspace->strm.next_out = cpage_out;
+ }
}
+ zlib_deflateEnd(&workspace->strm);
if (workspace->strm.total_out >= workspace->strm.total_in) {
ret = -E2BIG;
@@ -231,7 +296,7 @@ int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
workspace->strm.total_out = 0;
workspace->strm.next_out = workspace->buf;
- workspace->strm.avail_out = PAGE_SIZE;
+ workspace->strm.avail_out = workspace->buf_size;
/* If it's deflate, and it's got no preset dictionary, then
we can tell zlib to skip the adler32 check. */
@@ -270,7 +335,7 @@ int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
}
workspace->strm.next_out = workspace->buf;
- workspace->strm.avail_out = PAGE_SIZE;
+ workspace->strm.avail_out = workspace->buf_size;
if (workspace->strm.avail_in == 0) {
unsigned long tmp;
@@ -320,7 +385,7 @@ int zlib_decompress(struct list_head *ws, unsigned char *data_in,
workspace->strm.total_in = 0;
workspace->strm.next_out = workspace->buf;
- workspace->strm.avail_out = PAGE_SIZE;
+ workspace->strm.avail_out = workspace->buf_size;
workspace->strm.total_out = 0;
/* If it's deflate, and it's got no preset dictionary, then
we can tell zlib to skip the adler32 check. */
@@ -364,7 +429,7 @@ int zlib_decompress(struct list_head *ws, unsigned char *data_in,
buf_offset = 0;
bytes = min(PAGE_SIZE - pg_offset,
- PAGE_SIZE - buf_offset);
+ PAGE_SIZE - (buf_offset % PAGE_SIZE));
bytes = min(bytes, bytes_left);
kaddr = kmap_atomic(dest_page);
@@ -375,7 +440,7 @@ int zlib_decompress(struct list_head *ws, unsigned char *data_in,
bytes_left -= bytes;
next:
workspace->strm.next_out = workspace->buf;
- workspace->strm.avail_out = PAGE_SIZE;
+ workspace->strm.avail_out = workspace->buf_size;
}
if (ret != Z_STREAM_END && bytes_left != 0)
diff --git a/fs/exec.c b/fs/exec.c
index 3dd09e1e3e5e..db17be51b112 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -760,6 +760,11 @@ int setup_arg_pages(struct linux_binprm *bprm,
goto out_unlock;
BUG_ON(prev != vma);
+ if (unlikely(vm_flags & VM_EXEC)) {
+ pr_warn_once("process '%pD4' started with executable stack\n",
+ bprm->file);
+ }
+
/* Move stack pages down in memory. */
if (stack_shift) {
ret = shift_arg_pages(vma, stack_shift);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 335607b8c5c0..76ac9c7d32ec 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -2063,7 +2063,7 @@ void wb_workfn(struct work_struct *work)
struct bdi_writeback, dwork);
long pages_written;
- set_worker_desc("flush-%s", dev_name(wb->bdi->dev));
+ set_worker_desc("flush-%s", bdi_dev_name(wb->bdi));
current->flags |= PF_SWAPWRITE;
if (likely(!current_is_workqueue_rescuer() ||
diff --git a/fs/io_uring.c b/fs/io_uring.c
index ac5340fdcdfe..1806afddfea5 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -6005,7 +6005,7 @@ static int io_sqe_buffer_unregister(struct io_ring_ctx *ctx)
struct io_mapped_ubuf *imu = &ctx->user_bufs[i];
for (j = 0; j < imu->nr_bvecs; j++)
- put_user_page(imu->bvec[j].bv_page);
+ unpin_user_page(imu->bvec[j].bv_page);
if (ctx->account_mem)
io_unaccount_mem(ctx->user, imu->nr_bvecs);
@@ -6126,7 +6126,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
ret = 0;
down_read(&current->mm->mmap_sem);
- pret = get_user_pages(ubuf, nr_pages,
+ pret = pin_user_pages(ubuf, nr_pages,
FOLL_WRITE | FOLL_LONGTERM,
pages, vmas);
if (pret == nr_pages) {
@@ -6150,7 +6150,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
* release any pages we did get
*/
if (pret > 0)
- put_user_pages(pages, pret);
+ unpin_user_pages(pages, pret);
if (ctx->account_mem)
io_unaccount_mem(ctx->user, nr_pages);
kvfree(imu->bvec);
diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c
index 5c424a099280..1ef24574f481 100644
--- a/fs/ocfs2/cluster/quorum.c
+++ b/fs/ocfs2/cluster/quorum.c
@@ -73,7 +73,7 @@ static void o2quo_fence_self(void)
"system by restarting ***\n");
emergency_restart();
break;
- };
+ }
}
/* Indicate that a timeout occurred on a heartbeat region write. The
diff --git a/fs/ocfs2/dlm/Makefile b/fs/ocfs2/dlm/Makefile
index 38b224372776..5e700b45d32d 100644
--- a/fs/ocfs2/dlm/Makefile
+++ b/fs/ocfs2/dlm/Makefile
@@ -1,6 +1,4 @@
# SPDX-License-Identifier: GPL-2.0-only
-ccflags-y := -I $(srctree)/$(src)/..
-
obj-$(CONFIG_OCFS2_FS_O2CB) += ocfs2_dlm.o
ocfs2_dlm-objs := dlmdomain.o dlmdebug.o dlmthread.o dlmrecovery.o \
diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c
index 4de89af96abf..6abaded3ff6b 100644
--- a/fs/ocfs2/dlm/dlmast.c
+++ b/fs/ocfs2/dlm/dlmast.c
@@ -23,15 +23,15 @@
#include <linux/spinlock.h>
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
#include "dlmapi.h"
#include "dlmcommon.h"
#define MLOG_MASK_PREFIX ML_DLM
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
static void dlm_update_lvb(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
struct dlm_lock *lock);
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index aaf24548b02a..0463dce65bb2 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -688,10 +688,6 @@ struct dlm_begin_reco
__be32 pad2;
};
-
-#define BITS_PER_BYTE 8
-#define BITS_TO_BYTES(bits) (((bits)+BITS_PER_BYTE-1)/BITS_PER_BYTE)
-
struct dlm_query_join_request
{
u8 node_idx;
diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c
index 965f45dbe17b..6051edc33aef 100644
--- a/fs/ocfs2/dlm/dlmconvert.c
+++ b/fs/ocfs2/dlm/dlmconvert.c
@@ -23,9 +23,9 @@
#include <linux/spinlock.h>
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
#include "dlmapi.h"
#include "dlmcommon.h"
@@ -33,7 +33,7 @@
#include "dlmconvert.h"
#define MLOG_MASK_PREFIX ML_DLM
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
/* NOTE: __dlmconvert_master is the only function in here that
* needs a spinlock held on entry (res->spinlock) and it is the
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index 4d0b452012b2..c5c6efba7b5e 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -17,9 +17,9 @@
#include <linux/debugfs.h>
#include <linux/export.h>
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
#include "dlmapi.h"
#include "dlmcommon.h"
@@ -27,7 +27,7 @@
#include "dlmdebug.h"
#define MLOG_MASK_PREFIX ML_DLM
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
static int stringify_lockname(const char *lockname, int locklen, char *buf,
int len);
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index ee6f459f9770..357cfc702ce3 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -20,9 +20,9 @@
#include <linux/debugfs.h>
#include <linux/sched/signal.h>
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
#include "dlmapi.h"
#include "dlmcommon.h"
@@ -30,7 +30,7 @@
#include "dlmdebug.h"
#define MLOG_MASK_PREFIX (ML_DLM|ML_DLM_DOMAIN)
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
/*
* ocfs2 node maps are array of long int, which limits to send them freely
diff --git a/fs/ocfs2/dlm/dlmlock.c b/fs/ocfs2/dlm/dlmlock.c
index baff087f3863..83f0760e4fba 100644
--- a/fs/ocfs2/dlm/dlmlock.c
+++ b/fs/ocfs2/dlm/dlmlock.c
@@ -25,9 +25,9 @@
#include <linux/delay.h>
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
#include "dlmapi.h"
#include "dlmcommon.h"
@@ -35,7 +35,7 @@
#include "dlmconvert.h"
#define MLOG_MASK_PREFIX ML_DLM
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
static struct kmem_cache *dlm_lock_cache;
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 74b768ca1cd8..900f7e466d11 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -25,9 +25,9 @@
#include <linux/delay.h>
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
#include "dlmapi.h"
#include "dlmcommon.h"
@@ -35,7 +35,7 @@
#include "dlmdebug.h"
#define MLOG_MASK_PREFIX (ML_DLM|ML_DLM_MASTER)
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
static void dlm_mle_node_down(struct dlm_ctxt *dlm,
struct dlm_master_list_entry *mle,
@@ -2554,8 +2554,6 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
if (!dlm_grab(dlm))
return -EINVAL;
- BUG_ON(target == O2NM_MAX_NODES);
-
name = res->lockname.name;
namelen = res->lockname.len;
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 064ce5bbc3f6..4b566e88582f 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -26,16 +26,16 @@
#include <linux/delay.h>
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
#include "dlmapi.h"
#include "dlmcommon.h"
#include "dlmdomain.h"
#define MLOG_MASK_PREFIX (ML_DLM|ML_DLM_RECOVERY)
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node);
@@ -1668,7 +1668,7 @@ static int dlm_lockres_master_requery(struct dlm_ctxt *dlm,
int dlm_do_master_requery(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
u8 nodenum, u8 *real_master)
{
- int ret = -EINVAL;
+ int ret;
struct dlm_master_requery req;
int status = DLM_LOCK_RES_OWNER_UNKNOWN;
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index 61c51c268460..fd40c17cd022 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -25,16 +25,16 @@
#include <linux/delay.h>
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
#include "dlmapi.h"
#include "dlmcommon.h"
#include "dlmdomain.h"
#define MLOG_MASK_PREFIX (ML_DLM|ML_DLM_THREAD)
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
static int dlm_thread(void *data);
static void dlm_flush_asts(struct dlm_ctxt *dlm);
diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c
index 3883633e82eb..dcb17ca8ae74 100644
--- a/fs/ocfs2/dlm/dlmunlock.c
+++ b/fs/ocfs2/dlm/dlmunlock.c
@@ -23,15 +23,15 @@
#include <linux/spinlock.h>
#include <linux/delay.h>
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
#include "dlmapi.h"
#include "dlmcommon.h"
#define MLOG_MASK_PREFIX ML_DLM
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
#define DLM_UNLOCK_FREE_LOCK 0x00000001
#define DLM_UNLOCK_CALL_AST 0x00000002
diff --git a/fs/ocfs2/dlmfs/Makefile b/fs/ocfs2/dlmfs/Makefile
index a9874e441bd4..c7895f65be0e 100644
--- a/fs/ocfs2/dlmfs/Makefile
+++ b/fs/ocfs2/dlmfs/Makefile
@@ -1,6 +1,4 @@
# SPDX-License-Identifier: GPL-2.0-only
-ccflags-y := -I $(srctree)/$(src)/..
-
obj-$(CONFIG_OCFS2_FS) += ocfs2_dlmfs.o
ocfs2_dlmfs-objs := userdlm.o dlmfs.o
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 4f1668c81e1f..8e4f1ace467c 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -33,11 +33,11 @@
#include <linux/uaccess.h>
-#include "stackglue.h"
+#include "../stackglue.h"
#include "userdlm.h"
#define MLOG_MASK_PREFIX ML_DLMFS
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
static const struct super_operations dlmfs_ops;
diff --git a/fs/ocfs2/dlmfs/userdlm.c b/fs/ocfs2/dlmfs/userdlm.c
index 525b14ddfba5..3df5be25bfb1 100644
--- a/fs/ocfs2/dlmfs/userdlm.c
+++ b/fs/ocfs2/dlmfs/userdlm.c
@@ -21,12 +21,12 @@
#include <linux/types.h>
#include <linux/crc32.h>
-#include "ocfs2_lockingver.h"
-#include "stackglue.h"
+#include "../ocfs2_lockingver.h"
+#include "../stackglue.h"
#include "userdlm.h"
#define MLOG_MASK_PREFIX ML_DLMFS
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
static inline struct user_lock_res *user_lksb_to_lock_res(struct ocfs2_dlm_lksb *lksb)
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index cda1027d0819..cb9e6a73bea9 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -570,7 +570,7 @@ void ocfs2_inode_lock_res_init(struct ocfs2_lock_res *res,
mlog_bug_on_msg(1, "type: %d\n", type);
ops = NULL; /* thanks, gcc */
break;
- };
+ }
ocfs2_build_lock_name(type, OCFS2_I(inode)->ip_blkno,
generation, res->l_name);
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 3103ba7f97a2..bfe611ed1b1d 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -597,9 +597,11 @@ static inline void ocfs2_update_inode_fsync_trans(handle_t *handle,
{
struct ocfs2_inode_info *oi = OCFS2_I(inode);
- oi->i_sync_tid = handle->h_transaction->t_tid;
- if (datasync)
- oi->i_datasync_tid = handle->h_transaction->t_tid;
+ if (!is_handle_aborted(handle)) {
+ oi->i_sync_tid = handle->h_transaction->t_tid;
+ if (datasync)
+ oi->i_datasync_tid = handle->h_transaction->t_tid;
+ }
}
#endif /* OCFS2_JOURNAL_H */
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 8ea51cf27b97..da65251ef815 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -586,8 +586,7 @@ static int __ocfs2_mknod_locked(struct inode *dir,
mlog_errno(status);
}
- oi->i_sync_tid = handle->h_transaction->t_tid;
- oi->i_datasync_tid = handle->h_transaction->t_tid;
+ ocfs2_update_inode_fsync_trans(handle, inode, 1);
leave:
if (status < 0) {
diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c
index 6051e7bbc221..8bf88d690729 100644
--- a/fs/reiserfs/stree.c
+++ b/fs/reiserfs/stree.c
@@ -2240,7 +2240,8 @@ error_out:
/* also releases the path */
unfix_nodes(&s_ins_balance);
#ifdef REISERQUOTA_DEBUG
- reiserfs_debug(th->t_super, REISERFS_DEBUG_CODE,
+ if (inode)
+ reiserfs_debug(th->t_super, REISERFS_DEBUG_CODE,
"reiserquota insert_item(): freeing %u id=%u type=%c",
quota_bytes, inode->i_uid, head2type(ih));
#endif
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 97967ce06de3..f88197c1ffc2 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -13,6 +13,7 @@
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/blkdev.h>
+#include <linux/device.h>
#include <linux/writeback.h>
#include <linux/blk-cgroup.h>
#include <linux/backing-dev-defs.h>
@@ -504,4 +505,13 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi)
(1 << WB_async_congested));
}
+extern const char *bdi_unknown_name;
+
+static inline const char *bdi_dev_name(struct backing_dev_info *bdi)
+{
+ if (!bdi || !bdi->dev)
+ return bdi_unknown_name;
+ return dev_name(bdi->dev);
+}
+
#endif /* _LINUX_BACKING_DEV_H */
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index e479067c202c..6c7c4133c25c 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -13,6 +13,7 @@
#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE)
#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(long))
+#define BITS_TO_BYTES(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(char))
extern unsigned int __sw_hweight8(unsigned int w);
extern unsigned int __sw_hweight16(unsigned int w);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 40be2ccb87f3..41584f50af0d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2737,7 +2737,6 @@ static inline int filemap_fdatawait(struct address_space *mapping)
extern bool filemap_range_has_page(struct address_space *, loff_t lstart,
loff_t lend);
-extern int filemap_write_and_wait(struct address_space *mapping);
extern int filemap_write_and_wait_range(struct address_space *mapping,
loff_t lstart, loff_t lend);
extern int __filemap_fdatawrite_range(struct address_space *mapping,
@@ -2747,6 +2746,11 @@ extern int filemap_fdatawrite_range(struct address_space *mapping,
extern int filemap_check_errors(struct address_space *mapping);
extern void __filemap_set_wb_err(struct address_space *mapping, int err);
+static inline int filemap_write_and_wait(struct address_space *mapping)
+{
+ return filemap_write_and_wait_range(mapping, 0, LLONG_MAX);
+}
+
extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart,
loff_t lend);
extern int __must_check file_check_and_advance_wb_err(struct file *file);
diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h
index 6e125e9b4187..837058bc1c9f 100644
--- a/include/linux/io-mapping.h
+++ b/include/linux/io-mapping.h
@@ -28,6 +28,7 @@ struct io_mapping {
#ifdef CONFIG_HAVE_ATOMIC_IOMAP
+#include <linux/pfn.h>
#include <asm/iomap.h>
/*
* For small address space machines, mapping large objects
@@ -64,12 +65,10 @@ io_mapping_map_atomic_wc(struct io_mapping *mapping,
unsigned long offset)
{
resource_size_t phys_addr;
- unsigned long pfn;
BUG_ON(offset >= mapping->size);
phys_addr = mapping->base + offset;
- pfn = (unsigned long) (phys_addr >> PAGE_SHIFT);
- return iomap_atomic_prot_pfn(pfn, mapping->prot);
+ return iomap_atomic_prot_pfn(PHYS_PFN(phys_addr), mapping->prot);
}
static inline void
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index b38bbefabfab..079d17d96410 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -113,6 +113,9 @@ int memblock_add(phys_addr_t base, phys_addr_t size);
int memblock_remove(phys_addr_t base, phys_addr_t size);
int memblock_free(phys_addr_t base, phys_addr_t size);
int memblock_reserve(phys_addr_t base, phys_addr_t size);
+#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
+int memblock_physmem_add(phys_addr_t base, phys_addr_t size);
+#endif
void memblock_trim_memory(phys_addr_t align);
bool memblock_overlaps_region(struct memblock_type *type,
phys_addr_t base, phys_addr_t size);
@@ -127,10 +130,6 @@ void reset_node_managed_pages(pg_data_t *pgdat);
void reset_all_zones_managed_pages(void);
/* Low level functions */
-int memblock_add_range(struct memblock_type *type,
- phys_addr_t base, phys_addr_t size,
- int nid, enum memblock_flags flags);
-
void __next_mem_range(u64 *idx, int nid, enum memblock_flags flags,
struct memblock_type *type_a,
struct memblock_type *type_b, phys_addr_t *out_start,
diff --git a/include/linux/memory.h b/include/linux/memory.h
index 4c75dae8dd29..0b8d791b6669 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -29,8 +29,6 @@ struct memory_block {
int section_count; /* serialized by mem_sysfs_mutex */
int online_type; /* for passing data to online routine */
int phys_device; /* to which fru does this belong? */
- void *hw; /* optional pointer to fw/hw data */
- int (*phys_callback)(struct memory_block *);
struct device dev;
int nid; /* NID for this memory block */
};
@@ -55,19 +53,6 @@ struct memory_notify {
int status_change_nid;
};
-/*
- * During pageblock isolation, count the number of pages within the
- * range [start_pfn, start_pfn + nr_pages) which are owned by code
- * in the notifier chain.
- */
-#define MEM_ISOLATE_COUNT (1<<0)
-
-struct memory_isolate_notify {
- unsigned long start_pfn; /* Start of range to check */
- unsigned int nr_pages; /* # pages in range to check */
- unsigned int pages_found; /* # pages owned found by callbacks */
-};
-
struct notifier_block;
struct mem_section;
@@ -94,27 +79,13 @@ static inline int memory_notify(unsigned long val, void *v)
{
return 0;
}
-static inline int register_memory_isolate_notifier(struct notifier_block *nb)
-{
- return 0;
-}
-static inline void unregister_memory_isolate_notifier(struct notifier_block *nb)
-{
-}
-static inline int memory_isolate_notify(unsigned long val, void *v)
-{
- return 0;
-}
#else
extern int register_memory_notifier(struct notifier_block *nb);
extern void unregister_memory_notifier(struct notifier_block *nb);
-extern int register_memory_isolate_notifier(struct notifier_block *nb);
-extern void unregister_memory_isolate_notifier(struct notifier_block *nb);
int create_memory_block_devices(unsigned long start, unsigned long size);
void remove_memory_block_devices(unsigned long start, unsigned long size);
extern void memory_dev_init(void);
extern int memory_notify(unsigned long val, void *v);
-extern int memory_isolate_notify(unsigned long val, void *v);
extern struct memory_block *find_memory_block(struct mem_section *);
typedef int (*walk_memory_blocks_func_t)(struct memory_block *, void *);
extern int walk_memory_blocks(unsigned long start, unsigned long size,
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index ba0dca6aac6e..ffa6ad12d84a 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -94,7 +94,8 @@ extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages);
extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages);
extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
/* VM interface that may be used by firmware interface */
-extern int online_pages(unsigned long, unsigned long, int);
+extern int online_pages(unsigned long pfn, unsigned long nr_pages,
+ int online_type, int nid);
extern int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
unsigned long *valid_start, unsigned long *valid_end);
extern unsigned long __offline_isolated_pages(unsigned long start_pfn,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1233bf45164d..73a044ed6981 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -70,11 +70,6 @@ static inline void totalram_pages_add(long count)
atomic_long_add(count, &_totalram_pages);
}
-static inline void totalram_pages_set(long val)
-{
- atomic_long_set(&_totalram_pages, val);
-}
-
extern void * high_memory;
extern int page_cluster;
@@ -916,10 +911,6 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf);
#define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0))
-#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS
-#error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS
-#endif
-
#define ZONES_MASK ((1UL << ZONES_WIDTH) - 1)
#define NODES_MASK ((1UL << NODES_WIDTH) - 1)
#define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1)
@@ -947,9 +938,10 @@ static inline bool is_zone_device_page(const struct page *page)
#endif
#ifdef CONFIG_DEV_PAGEMAP_OPS
-void __put_devmap_managed_page(struct page *page);
+void free_devmap_managed_page(struct page *page);
DECLARE_STATIC_KEY_FALSE(devmap_managed_key);
-static inline bool put_devmap_managed_page(struct page *page)
+
+static inline bool page_is_devmap_managed(struct page *page)
{
if (!static_branch_unlikely(&devmap_managed_key))
return false;
@@ -958,7 +950,6 @@ static inline bool put_devmap_managed_page(struct page *page)
switch (page->pgmap->type) {
case MEMORY_DEVICE_PRIVATE:
case MEMORY_DEVICE_FS_DAX:
- __put_devmap_managed_page(page);
return true;
default:
break;
@@ -966,11 +957,17 @@ static inline bool put_devmap_managed_page(struct page *page)
return false;
}
+void put_devmap_managed_page(struct page *page);
+
#else /* CONFIG_DEV_PAGEMAP_OPS */
-static inline bool put_devmap_managed_page(struct page *page)
+static inline bool page_is_devmap_managed(struct page *page)
{
return false;
}
+
+static inline void put_devmap_managed_page(struct page *page)
+{
+}
#endif /* CONFIG_DEV_PAGEMAP_OPS */
static inline bool is_device_private_page(const struct page *page)
@@ -1023,37 +1020,37 @@ static inline void put_page(struct page *page)
* need to inform the device driver through callback. See
* include/linux/memremap.h and HMM for details.
*/
- if (put_devmap_managed_page(page))
+ if (page_is_devmap_managed(page)) {
+ put_devmap_managed_page(page);
return;
+ }
if (put_page_testzero(page))
__put_page(page);
}
/**
- * put_user_page() - release a gup-pinned page
+ * unpin_user_page() - release a gup-pinned page
* @page: pointer to page to be released
*
- * Pages that were pinned via get_user_pages*() must be released via
- * either put_user_page(), or one of the put_user_pages*() routines
- * below. This is so that eventually, pages that are pinned via
- * get_user_pages*() can be separately tracked and uniquely handled. In
- * particular, interactions with RDMA and filesystems need special
- * handling.
+ * Pages that were pinned via pin_user_pages*() must be released via either
+ * unpin_user_page(), or one of the unpin_user_pages*() routines. This is so
+ * that eventually such pages can be separately tracked and uniquely handled. In
+ * particular, interactions with RDMA and filesystems need special handling.
*
- * put_user_page() and put_page() are not interchangeable, despite this early
- * implementation that makes them look the same. put_user_page() calls must
- * be perfectly matched up with get_user_page() calls.
+ * unpin_user_page() and put_page() are not interchangeable, despite this early
+ * implementation that makes them look the same. unpin_user_page() calls must
+ * be perfectly matched up with pin*() calls.
*/
-static inline void put_user_page(struct page *page)
+static inline void unpin_user_page(struct page *page)
{
put_page(page);
}
-void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
- bool make_dirty);
+void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
+ bool make_dirty);
-void put_user_pages(struct page **pages, unsigned long npages);
+void unpin_user_pages(struct page **pages, unsigned long npages);
#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
#define SECTION_IN_PAGE_FLAGS
@@ -1501,9 +1498,16 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages,
struct vm_area_struct **vmas, int *locked);
+long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages,
+ struct vm_area_struct **vmas, int *locked);
long get_user_pages(unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages,
struct vm_area_struct **vmas);
+long pin_user_pages(unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages,
+ struct vm_area_struct **vmas);
long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages, int *locked);
long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
@@ -1511,6 +1515,8 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
int get_user_pages_fast(unsigned long start, int nr_pages,
unsigned int gup_flags, struct page **pages);
+int pin_user_pages_fast(unsigned long start, int nr_pages,
+ unsigned int gup_flags, struct page **pages);
int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc);
int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc,
@@ -2575,13 +2581,15 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
#define FOLL_ANON 0x8000 /* don't do file mappings */
#define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */
#define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */
+#define FOLL_PIN 0x40000 /* pages must be released via unpin_user_page */
/*
- * NOTE on FOLL_LONGTERM:
+ * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each
+ * other. Here is what they mean, and how to use them:
*
* FOLL_LONGTERM indicates that the page will be held for an indefinite time
- * period _often_ under userspace control. This is contrasted with
- * iov_iter_get_pages() where usages which are transient.
+ * period _often_ under userspace control. This is in contrast to
+ * iov_iter_get_pages(), whose usages are transient.
*
* FIXME: For pages which are part of a filesystem, mappings are subject to the
* lifetime enforced by the filesystem and we need guarantees that longterm
@@ -2596,11 +2604,39 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
* Currently only get_user_pages() and get_user_pages_fast() support this flag
* and calls to get_user_pages_[un]locked are specifically not allowed. This
* is due to an incompatibility with the FS DAX check and
- * FAULT_FLAG_ALLOW_RETRY
+ * FAULT_FLAG_ALLOW_RETRY.
*
- * In the CMA case: longterm pins in a CMA region would unnecessarily fragment
- * that region. And so CMA attempts to migrate the page before pinning when
+ * In the CMA case: long term pins in a CMA region would unnecessarily fragment
+ * that region. And so, CMA attempts to migrate the page before pinning, when
* FOLL_LONGTERM is specified.
+ *
+ * FOLL_PIN indicates that a special kind of tracking (not just page->_refcount,
+ * but an additional pin counting system) will be invoked. This is intended for
+ * anything that gets a page reference and then touches page data (for example,
+ * Direct IO). This lets the filesystem know that some non-file-system entity is
+ * potentially changing the pages' data. In contrast to FOLL_GET (whose pages
+ * are released via put_page()), FOLL_PIN pages must be released, ultimately, by
+ * a call to unpin_user_page().
+ *
+ * FOLL_PIN is similar to FOLL_GET: both of these pin pages. They use different
+ * and separate refcounting mechanisms, however, and that means that each has
+ * its own acquire and release mechanisms:
+ *
+ * FOLL_GET: get_user_pages*() to acquire, and put_page() to release.
+ *
+ * FOLL_PIN: pin_user_pages*() to acquire, and unpin_user_pages to release.
+ *
+ * FOLL_PIN and FOLL_GET are mutually exclusive for a given function call.
+ * (The underlying pages may experience both FOLL_GET-based and FOLL_PIN-based
+ * calls applied to them, and that's perfectly OK. This is a constraint on the
+ * callers, not on the pages.)
+ *
+ * FOLL_PIN should be set internally by the pin_user_pages*() APIs, never
+ * directly by the caller. That's in order to help avoid mismatches when
+ * releasing pages: get_user_pages*() pages must be released via put_page(),
+ * while pin_user_pages*() pages must be released via unpin_user_page().
+ *
+ * Please see Documentation/vm/pin_user_pages.rst for more information.
*/
static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 5334ad8fc7bd..c2bc309d1634 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -758,7 +758,7 @@ typedef struct pglist_data {
#ifdef CONFIG_NUMA
/*
- * zone reclaim becomes active if more unmapped pages exist.
+ * node reclaim becomes active if more unmapped pages exist.
*/
unsigned long min_unmapped_pages;
unsigned long min_slab_pages;
diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 6861df759fad..572458016331 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -33,8 +33,8 @@ static inline bool is_migrate_isolate(int migratetype)
#define MEMORY_OFFLINE 0x1
#define REPORT_FAILURE 0x2
-bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
- int migratetype, int flags);
+struct page *has_unmovable_pages(struct zone *zone, struct page *page,
+ int migratetype, int flags);
void set_pageblock_migratetype(struct page *page, int migratetype);
int move_freepages_block(struct zone *zone, struct page *page,
int migratetype, int *num_movable);
diff --git a/include/linux/swab.h b/include/linux/swab.h
index e466fd159c85..bcff5149861a 100644
--- a/include/linux/swab.h
+++ b/include/linux/swab.h
@@ -7,6 +7,7 @@
# define swab16 __swab16
# define swab32 __swab32
# define swab64 __swab64
+# define swab __swab
# define swahw32 __swahw32
# define swahb32 __swahb32
# define swab16p __swab16p
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index d9111aebb97d..126913c6a53b 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -32,17 +32,6 @@
/* use value, which < 0K, to indicate an invalid/uninitialized temperature */
#define THERMAL_TEMP_INVALID -274000
-/* Unit conversion macros */
-#define DECI_KELVIN_TO_CELSIUS(t) ({ \
- long _t = (t); \
- ((_t-2732 >= 0) ? (_t-2732+5)/10 : (_t-2732-5)/10); \
-})
-#define CELSIUS_TO_DECI_KELVIN(t) ((t)*10+2732)
-#define DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(t, off) (((t) - (off)) * 100)
-#define DECI_KELVIN_TO_MILLICELSIUS(t) DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(t, 2732)
-#define MILLICELSIUS_TO_DECI_KELVIN_WITH_OFFSET(t, off) (((t) / 100) + (off))
-#define MILLICELSIUS_TO_DECI_KELVIN(t) MILLICELSIUS_TO_DECI_KELVIN_WITH_OFFSET(t, 2732)
-
/* Default Thermal Governor */
#if defined(CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE)
#define DEFAULT_THERMAL_GOVERNOR "step_wise"
diff --git a/include/linux/units.h b/include/linux/units.h
new file mode 100644
index 000000000000..aaf716364ec3
--- /dev/null
+++ b/include/linux/units.h
@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_UNITS_H
+#define _LINUX_UNITS_H
+
+#include <linux/kernel.h>
+
+#define ABSOLUTE_ZERO_MILLICELSIUS -273150
+
+static inline long milli_kelvin_to_millicelsius(long t)
+{
+ return t + ABSOLUTE_ZERO_MILLICELSIUS;
+}
+
+static inline long millicelsius_to_milli_kelvin(long t)
+{
+ return t - ABSOLUTE_ZERO_MILLICELSIUS;
+}
+
+#define MILLIDEGREE_PER_DEGREE 1000
+#define MILLIDEGREE_PER_DECIDEGREE 100
+
+static inline long kelvin_to_millicelsius(long t)
+{
+ return milli_kelvin_to_millicelsius(t * MILLIDEGREE_PER_DEGREE);
+}
+
+static inline long millicelsius_to_kelvin(long t)
+{
+ t = millicelsius_to_milli_kelvin(t);
+
+ return DIV_ROUND_CLOSEST(t, MILLIDEGREE_PER_DEGREE);
+}
+
+static inline long deci_kelvin_to_celsius(long t)
+{
+ t = milli_kelvin_to_millicelsius(t * MILLIDEGREE_PER_DECIDEGREE);
+
+ return DIV_ROUND_CLOSEST(t, MILLIDEGREE_PER_DEGREE);
+}
+
+static inline long celsius_to_deci_kelvin(long t)
+{
+ t = millicelsius_to_milli_kelvin(t * MILLIDEGREE_PER_DEGREE);
+
+ return DIV_ROUND_CLOSEST(t, MILLIDEGREE_PER_DECIDEGREE);
+}
+
+/**
+ * deci_kelvin_to_millicelsius_with_offset - convert Kelvin to Celsius
+ * @t: temperature value in decidegrees Kelvin
+ * @offset: difference between Kelvin and Celsius in millidegrees
+ *
+ * Return: temperature value in millidegrees Celsius
+ */
+static inline long deci_kelvin_to_millicelsius_with_offset(long t, long offset)
+{
+ return t * MILLIDEGREE_PER_DECIDEGREE - offset;
+}
+
+static inline long deci_kelvin_to_millicelsius(long t)
+{
+ return milli_kelvin_to_millicelsius(t * MILLIDEGREE_PER_DECIDEGREE);
+}
+
+static inline long millicelsius_to_deci_kelvin(long t)
+{
+ t = millicelsius_to_milli_kelvin(t);
+
+ return DIV_ROUND_CLOSEST(t, MILLIDEGREE_PER_DECIDEGREE);
+}
+
+static inline long kelvin_to_celsius(long t)
+{
+ return t + DIV_ROUND_CLOSEST(ABSOLUTE_ZERO_MILLICELSIUS,
+ MILLIDEGREE_PER_DEGREE);
+}
+
+static inline long celsius_to_kelvin(long t)
+{
+ return t - DIV_ROUND_CLOSEST(ABSOLUTE_ZERO_MILLICELSIUS,
+ MILLIDEGREE_PER_DEGREE);
+}
+
+#endif /* _LINUX_UNITS_H */
diff --git a/include/linux/zlib.h b/include/linux/zlib.h
index 92dbbd3f6c75..c757d848a758 100644
--- a/include/linux/zlib.h
+++ b/include/linux/zlib.h
@@ -191,6 +191,12 @@ extern int zlib_deflate_workspacesize (int windowBits, int memLevel);
exceed those passed here.
*/
+extern int zlib_deflate_dfltcc_enabled (void);
+/*
+ Returns 1 if Deflate-Conversion facility is installed and enabled,
+ otherwise 0.
+*/
+
/*
extern int deflateInit (z_streamp strm, int level);
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index ad7e642bd497..f65b1f6db22d 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -88,8 +88,8 @@ DECLARE_EVENT_CLASS(kmem_alloc_node,
__entry->node = node;
),
- TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d",
- __entry->call_site,
+ TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d",
+ (void *)__entry->call_site,
__entry->ptr,
__entry->bytes_req,
__entry->bytes_alloc,
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index ef50be4e5e6c..d94def25e4dc 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -67,8 +67,8 @@ DECLARE_EVENT_CLASS(writeback_page_template,
TP_fast_assign(
strscpy_pad(__entry->name,
- mapping ? dev_name(inode_to_bdi(mapping->host)->dev) : "(unknown)",
- 32);
+ bdi_dev_name(mapping ? inode_to_bdi(mapping->host) :
+ NULL), 32);
__entry->ino = mapping ? mapping->host->i_ino : 0;
__entry->index = page->index;
),
@@ -111,8 +111,7 @@ DECLARE_EVENT_CLASS(writeback_dirty_inode_template,
struct backing_dev_info *bdi = inode_to_bdi(inode);
/* may be called for files on pseudo FSes w/ unregistered bdi */
- strscpy_pad(__entry->name,
- bdi->dev ? dev_name(bdi->dev) : "(unknown)", 32);
+ strscpy_pad(__entry->name, bdi_dev_name(bdi), 32);
__entry->ino = inode->i_ino;
__entry->state = inode->i_state;
__entry->flags = flags;
@@ -193,7 +192,7 @@ TRACE_EVENT(inode_foreign_history,
),
TP_fast_assign(
- strncpy(__entry->name, dev_name(inode_to_bdi(inode)->dev), 32);
+ strncpy(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32);
__entry->ino = inode->i_ino;
__entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc);
__entry->history = history;
@@ -222,7 +221,7 @@ TRACE_EVENT(inode_switch_wbs,
),
TP_fast_assign(
- strncpy(__entry->name, dev_name(old_wb->bdi->dev), 32);
+ strncpy(__entry->name, bdi_dev_name(old_wb->bdi), 32);
__entry->ino = inode->i_ino;
__entry->old_cgroup_ino = __trace_wb_assign_cgroup(old_wb);
__entry->new_cgroup_ino = __trace_wb_assign_cgroup(new_wb);
@@ -255,7 +254,7 @@ TRACE_EVENT(track_foreign_dirty,
struct address_space *mapping = page_mapping(page);
struct inode *inode = mapping ? mapping->host : NULL;
- strncpy(__entry->name, dev_name(wb->bdi->dev), 32);
+ strncpy(__entry->name, bdi_dev_name(wb->bdi), 32);
__entry->bdi_id = wb->bdi->id;
__entry->ino = inode ? inode->i_ino : 0;
__entry->memcg_id = wb->memcg_css->id;
@@ -288,7 +287,7 @@ TRACE_EVENT(flush_foreign,
),
TP_fast_assign(
- strncpy(__entry->name, dev_name(wb->bdi->dev), 32);
+ strncpy(__entry->name, bdi_dev_name(wb->bdi), 32);
__entry->cgroup_ino = __trace_wb_assign_cgroup(wb);
__entry->frn_bdi_id = frn_bdi_id;
__entry->frn_memcg_id = frn_memcg_id;
@@ -318,7 +317,7 @@ DECLARE_EVENT_CLASS(writeback_write_inode_template,
TP_fast_assign(
strscpy_pad(__entry->name,
- dev_name(inode_to_bdi(inode)->dev), 32);
+ bdi_dev_name(inode_to_bdi(inode)), 32);
__entry->ino = inode->i_ino;
__entry->sync_mode = wbc->sync_mode;
__entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc);
@@ -361,9 +360,7 @@ DECLARE_EVENT_CLASS(writeback_work_class,
__field(ino_t, cgroup_ino)
),
TP_fast_assign(
- strscpy_pad(__entry->name,
- wb->bdi->dev ? dev_name(wb->bdi->dev) :
- "(unknown)", 32);
+ strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32);
__entry->nr_pages = work->nr_pages;
__entry->sb_dev = work->sb ? work->sb->s_dev : 0;
__entry->sync_mode = work->sync_mode;
@@ -416,7 +413,7 @@ DECLARE_EVENT_CLASS(writeback_class,
__field(ino_t, cgroup_ino)
),
TP_fast_assign(
- strscpy_pad(__entry->name, dev_name(wb->bdi->dev), 32);
+ strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32);
__entry->cgroup_ino = __trace_wb_assign_cgroup(wb);
),
TP_printk("bdi %s: cgroup_ino=%lu",
@@ -438,7 +435,7 @@ TRACE_EVENT(writeback_bdi_register,
__array(char, name, 32)
),
TP_fast_assign(
- strscpy_pad(__entry->name, dev_name(bdi->dev), 32);
+ strscpy_pad(__entry->name, bdi_dev_name(bdi), 32);
),
TP_printk("bdi %s",
__entry->name
@@ -463,7 +460,7 @@ DECLARE_EVENT_CLASS(wbc_class,
),
TP_fast_assign(
- strscpy_pad(__entry->name, dev_name(bdi->dev), 32);
+ strscpy_pad(__entry->name, bdi_dev_name(bdi), 32);
__entry->nr_to_write = wbc->nr_to_write;
__entry->pages_skipped = wbc->pages_skipped;
__entry->sync_mode = wbc->sync_mode;
@@ -514,7 +511,7 @@ TRACE_EVENT(writeback_queue_io,
),
TP_fast_assign(
unsigned long *older_than_this = work->older_than_this;
- strscpy_pad(__entry->name, dev_name(wb->bdi->dev), 32);
+ strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32);
__entry->older = older_than_this ? *older_than_this : 0;
__entry->age = older_than_this ?
(jiffies - *older_than_this) * 1000 / HZ : -1;
@@ -600,7 +597,7 @@ TRACE_EVENT(bdi_dirty_ratelimit,
),
TP_fast_assign(
- strscpy_pad(__entry->bdi, dev_name(wb->bdi->dev), 32);
+ strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32);
__entry->write_bw = KBps(wb->write_bandwidth);
__entry->avg_write_bw = KBps(wb->avg_write_bandwidth);
__entry->dirty_rate = KBps(dirty_rate);
@@ -665,7 +662,7 @@ TRACE_EVENT(balance_dirty_pages,
TP_fast_assign(
unsigned long freerun = (thresh + bg_thresh) / 2;
- strscpy_pad(__entry->bdi, dev_name(wb->bdi->dev), 32);
+ strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32);
__entry->limit = global_wb_domain.dirty_limit;
__entry->setpoint = (global_wb_domain.dirty_limit +
@@ -726,7 +723,7 @@ TRACE_EVENT(writeback_sb_inodes_requeue,
TP_fast_assign(
strscpy_pad(__entry->name,
- dev_name(inode_to_bdi(inode)->dev), 32);
+ bdi_dev_name(inode_to_bdi(inode)), 32);
__entry->ino = inode->i_ino;
__entry->state = inode->i_state;
__entry->dirtied_when = inode->dirtied_when;
@@ -800,7 +797,7 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template,
TP_fast_assign(
strscpy_pad(__entry->name,
- dev_name(inode_to_bdi(inode)->dev), 32);
+ bdi_dev_name(inode_to_bdi(inode)), 32);
__entry->ino = inode->i_ino;
__entry->state = inode->i_state;
__entry->dirtied_when = inode->dirtied_when;
diff --git a/include/uapi/linux/swab.h b/include/uapi/linux/swab.h
index 23cd84868cc3..fa7f97da5b76 100644
--- a/include/uapi/linux/swab.h
+++ b/include/uapi/linux/swab.h
@@ -4,6 +4,7 @@
#include <linux/types.h>
#include <linux/compiler.h>
+#include <asm/bitsperlong.h>
#include <asm/swab.h>
/*
@@ -132,6 +133,15 @@ static inline __attribute_const__ __u32 __fswahb32(__u32 val)
__fswab64(x))
#endif
+static __always_inline unsigned long __swab(const unsigned long y)
+{
+#if BITS_PER_LONG == 64
+ return __swab64(y);
+#else /* BITS_PER_LONG == 32 */
+ return __swab32(y);
+#endif
+}
+
/**
* __swahw32 - return a word-swapped 32-bit value
* @x: value to wordswap
diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h
index 87aa2a6d9125..27c1ed2822e6 100644
--- a/include/uapi/linux/sysctl.h
+++ b/include/uapi/linux/sysctl.h
@@ -195,7 +195,7 @@ enum
VM_MIN_UNMAPPED=32, /* Set min percent of unmapped pages */
VM_PANIC_ON_OOM=33, /* panic at out-of-memory */
VM_VDSO_ENABLED=34, /* map VDSO into new processes? */
- VM_MIN_SLAB=35, /* Percent pages ignored by zone reclaim */
+ VM_MIN_SLAB=35, /* Percent pages ignored by node reclaim */
};
diff --git a/init/main.c b/init/main.c
index db13a76c036e..d8c7e86c2d28 100644
--- a/init/main.c
+++ b/init/main.c
@@ -246,8 +246,7 @@ static int __init loglevel(char *str)
early_param("loglevel", loglevel);
/* Change NUL term back to "=", to make "param" the whole string. */
-static int __init repair_env_string(char *param, char *val,
- const char *unused, void *arg)
+static void __init repair_env_string(char *param, char *val)
{
if (val) {
/* param=val or param="val"? */
@@ -256,11 +255,9 @@ static int __init repair_env_string(char *param, char *val,
else if (val == param+strlen(param)+2) {
val[-2] = '=';
memmove(val-1, val, strlen(val)+1);
- val--;
} else
BUG();
}
- return 0;
}
/* Anything after -- gets handed straight to init. */
@@ -272,7 +269,7 @@ static int __init set_init_arg(char *param, char *val,
if (panic_later)
return 0;
- repair_env_string(param, val, unused, NULL);
+ repair_env_string(param, val);
for (i = 0; argv_init[i]; i++) {
if (i == MAX_INIT_ARGS) {
@@ -292,14 +289,16 @@ static int __init set_init_arg(char *param, char *val,
static int __init unknown_bootoption(char *param, char *val,
const char *unused, void *arg)
{
- repair_env_string(param, val, unused, NULL);
+ size_t len = strlen(param);
+
+ repair_env_string(param, val);
/* Handle obsolete-style parameters */
if (obsolete_checksetup(param))
return 0;
/* Unused module parameter. */
- if (strchr(param, '.') && (!val || strchr(param, '.') < val))
+ if (strnchr(param, len, '.'))
return 0;
if (panic_later)
@@ -313,7 +312,7 @@ static int __init unknown_bootoption(char *param, char *val,
panic_later = "env";
panic_param = param;
}
- if (!strncmp(param, envp_init[i], val - param))
+ if (!strncmp(param, envp_init[i], len+1))
break;
}
envp_init[i] = param;
@@ -991,6 +990,12 @@ static const char *initcall_level_names[] __initdata = {
"late",
};
+static int __init ignore_unknown_bootoption(char *param, char *val,
+ const char *unused, void *arg)
+{
+ return 0;
+}
+
static void __init do_initcall_level(int level)
{
initcall_entry_t *fn;
@@ -1000,7 +1005,7 @@ static void __init do_initcall_level(int level)
initcall_command_line, __start___param,
__stop___param - __start___param,
level, level,
- NULL, &repair_env_string);
+ NULL, ignore_unknown_bootoption);
trace_initcall_level(initcall_level_names[level]);
for (fn = initcall_levels[level]; fn < initcall_levels[level+1]; fn++)
@@ -1043,8 +1048,16 @@ static void __init do_pre_smp_initcalls(void)
static int run_init_process(const char *init_filename)
{
+ const char *const *p;
+
argv_init[0] = init_filename;
pr_info("Run %s as init process\n", init_filename);
+ pr_debug(" with arguments:\n");
+ for (p = argv_init; *p; p++)
+ pr_debug(" %s\n", *p);
+ pr_debug(" with environment:\n");
+ for (p = envp_init; *p; p++)
+ pr_debug(" %s\n", *p);
return do_execve(getname_kernel(init_filename),
(const char __user *const __user *)argv_init,
(const char __user *const __user *)envp_init);
@@ -1091,6 +1104,11 @@ static void mark_readonly(void)
} else
pr_info("Kernel memory protection disabled.\n");
}
+#elif defined(CONFIG_ARCH_HAS_STRICT_KERNEL_RWX)
+static inline void mark_readonly(void)
+{
+ pr_warn("Kernel memory protection not selected by kernel config.\n");
+}
#else
static inline void mark_readonly(void)
{
diff --git a/kernel/Makefile b/kernel/Makefile
index f2cc0d118a0b..4cb4130ced32 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -27,6 +27,7 @@ KCOV_INSTRUMENT_softirq.o := n
# and produce insane amounts of uninteresting coverage.
KCOV_INSTRUMENT_module.o := n
KCOV_INSTRUMENT_extable.o := n
+KCOV_INSTRUMENT_stacktrace.o := n
# Don't self-instrument.
KCOV_INSTRUMENT_kcov.o := n
KASAN_SANITIZE_kcov.o := n
diff --git a/lib/Kconfig b/lib/Kconfig
index 6e790dc55c5b..bc7e56370129 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -278,6 +278,13 @@ config ZLIB_DEFLATE
tristate
select BITREVERSE
+config ZLIB_DFLTCC
+ def_bool y
+ depends on S390
+ prompt "Enable s390x DEFLATE CONVERSION CALL support for kernel zlib"
+ help
+ Enable s390x hardware support for zlib in the kernel.
+
config LZO_COMPRESS
tristate
diff --git a/lib/Makefile b/lib/Makefile
index c20b1debe9b4..23ca78d43d24 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -16,6 +16,7 @@ KCOV_INSTRUMENT_rbtree.o := n
KCOV_INSTRUMENT_list_debug.o := n
KCOV_INSTRUMENT_debugobjects.o := n
KCOV_INSTRUMENT_dynamic_debug.o := n
+KCOV_INSTRUMENT_fault-inject.o := n
# Early boot use of cmdline, don't instrument it
ifdef CONFIG_AMD_MEM_ENCRYPT
@@ -140,6 +141,7 @@ obj-$(CONFIG_842_COMPRESS) += 842/
obj-$(CONFIG_842_DECOMPRESS) += 842/
obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate/
obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate/
+obj-$(CONFIG_ZLIB_DFLTCC) += zlib_dfltcc/
obj-$(CONFIG_REED_SOLOMON) += reed_solomon/
obj-$(CONFIG_BCH) += bch.o
obj-$(CONFIG_LZO_COMPRESS) += lzo/
diff --git a/lib/decompress_inflate.c b/lib/decompress_inflate.c
index 63b4b7eee138..6130c42b8e59 100644
--- a/lib/decompress_inflate.c
+++ b/lib/decompress_inflate.c
@@ -10,6 +10,10 @@
#include "zlib_inflate/inftrees.c"
#include "zlib_inflate/inffast.c"
#include "zlib_inflate/inflate.c"
+#ifdef CONFIG_ZLIB_DFLTCC
+#include "zlib_dfltcc/dfltcc.c"
+#include "zlib_dfltcc/dfltcc_inflate.c"
+#endif
#else /* STATIC */
/* initramfs et al: linked */
@@ -76,7 +80,12 @@ STATIC int INIT __gunzip(unsigned char *buf, long len,
}
strm->workspace = malloc(flush ? zlib_inflate_workspacesize() :
+#ifdef CONFIG_ZLIB_DFLTCC
+ /* Always allocate the full workspace for DFLTCC */
+ zlib_inflate_workspacesize());
+#else
sizeof(struct inflate_state));
+#endif
if (strm->workspace == NULL) {
error("Out of memory while allocating workspace");
goto gunzip_nomem4;
@@ -123,10 +132,14 @@ STATIC int INIT __gunzip(unsigned char *buf, long len,
rc = zlib_inflateInit2(strm, -MAX_WBITS);
+#ifdef CONFIG_ZLIB_DFLTCC
+ /* Always keep the window for DFLTCC */
+#else
if (!flush) {
WS(strm)->inflate_state.wsize = 0;
WS(strm)->inflate_state.window = NULL;
}
+#endif
while (rc == Z_OK) {
if (strm->avail_in == 0) {
diff --git a/lib/find_bit.c b/lib/find_bit.c
index e35a76b291e6..49f875f1baf7 100644
--- a/lib/find_bit.c
+++ b/lib/find_bit.c
@@ -17,9 +17,9 @@
#include <linux/export.h>
#include <linux/kernel.h>
-#if !defined(find_next_bit) || !defined(find_next_zero_bit) || \
- !defined(find_next_and_bit)
-
+#if !defined(find_next_bit) || !defined(find_next_zero_bit) || \
+ !defined(find_next_bit_le) || !defined(find_next_zero_bit_le) || \
+ !defined(find_next_and_bit)
/*
* This is a common helper function for find_next_bit, find_next_zero_bit, and
* find_next_and_bit. The differences are:
@@ -27,11 +27,11 @@
* searching it for one bits.
* - The optional "addr2", which is anded with "addr1" if present.
*/
-static inline unsigned long _find_next_bit(const unsigned long *addr1,
+static unsigned long _find_next_bit(const unsigned long *addr1,
const unsigned long *addr2, unsigned long nbits,
- unsigned long start, unsigned long invert)
+ unsigned long start, unsigned long invert, unsigned long le)
{
- unsigned long tmp;
+ unsigned long tmp, mask;
if (unlikely(start >= nbits))
return nbits;
@@ -42,7 +42,12 @@ static inline unsigned long _find_next_bit(const unsigned long *addr1,
tmp ^= invert;
/* Handle 1st word. */
- tmp &= BITMAP_FIRST_WORD_MASK(start);
+ mask = BITMAP_FIRST_WORD_MASK(start);
+ if (le)
+ mask = swab(mask);
+
+ tmp &= mask;
+
start = round_down(start, BITS_PER_LONG);
while (!tmp) {
@@ -56,6 +61,9 @@ static inline unsigned long _find_next_bit(const unsigned long *addr1,
tmp ^= invert;
}
+ if (le)
+ tmp = swab(tmp);
+
return min(start + __ffs(tmp), nbits);
}
#endif
@@ -67,7 +75,7 @@ static inline unsigned long _find_next_bit(const unsigned long *addr1,
unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
unsigned long offset)
{
- return _find_next_bit(addr, NULL, size, offset, 0UL);
+ return _find_next_bit(addr, NULL, size, offset, 0UL, 0);
}
EXPORT_SYMBOL(find_next_bit);
#endif
@@ -76,7 +84,7 @@ EXPORT_SYMBOL(find_next_bit);
unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
unsigned long offset)
{
- return _find_next_bit(addr, NULL, size, offset, ~0UL);
+ return _find_next_bit(addr, NULL, size, offset, ~0UL, 0);
}
EXPORT_SYMBOL(find_next_zero_bit);
#endif
@@ -86,7 +94,7 @@ unsigned long find_next_and_bit(const unsigned long *addr1,
const unsigned long *addr2, unsigned long size,
unsigned long offset)
{
- return _find_next_bit(addr1, addr2, size, offset, 0UL);
+ return _find_next_bit(addr1, addr2, size, offset, 0UL, 0);
}
EXPORT_SYMBOL(find_next_and_bit);
#endif
@@ -149,57 +157,11 @@ EXPORT_SYMBOL(find_last_bit);
#ifdef __BIG_ENDIAN
-/* include/linux/byteorder does not support "unsigned long" type */
-static inline unsigned long ext2_swab(const unsigned long y)
-{
-#if BITS_PER_LONG == 64
- return (unsigned long) __swab64((u64) y);
-#elif BITS_PER_LONG == 32
- return (unsigned long) __swab32((u32) y);
-#else
-#error BITS_PER_LONG not defined
-#endif
-}
-
-#if !defined(find_next_bit_le) || !defined(find_next_zero_bit_le)
-static inline unsigned long _find_next_bit_le(const unsigned long *addr1,
- const unsigned long *addr2, unsigned long nbits,
- unsigned long start, unsigned long invert)
-{
- unsigned long tmp;
-
- if (unlikely(start >= nbits))
- return nbits;
-
- tmp = addr1[start / BITS_PER_LONG];
- if (addr2)
- tmp &= addr2[start / BITS_PER_LONG];
- tmp ^= invert;
-
- /* Handle 1st word. */
- tmp &= ext2_swab(BITMAP_FIRST_WORD_MASK(start));
- start = round_down(start, BITS_PER_LONG);
-
- while (!tmp) {
- start += BITS_PER_LONG;
- if (start >= nbits)
- return nbits;
-
- tmp = addr1[start / BITS_PER_LONG];
- if (addr2)
- tmp &= addr2[start / BITS_PER_LONG];
- tmp ^= invert;
- }
-
- return min(start + __ffs(ext2_swab(tmp)), nbits);
-}
-#endif
-
#ifndef find_next_zero_bit_le
unsigned long find_next_zero_bit_le(const void *addr, unsigned
long size, unsigned long offset)
{
- return _find_next_bit_le(addr, NULL, size, offset, ~0UL);
+ return _find_next_bit(addr, NULL, size, offset, ~0UL, 1);
}
EXPORT_SYMBOL(find_next_zero_bit_le);
#endif
@@ -208,7 +170,7 @@ EXPORT_SYMBOL(find_next_zero_bit_le);
unsigned long find_next_bit_le(const void *addr, unsigned
long size, unsigned long offset)
{
- return _find_next_bit_le(addr, NULL, size, offset, 0UL);
+ return _find_next_bit(addr, NULL, size, offset, 0UL, 1);
}
EXPORT_SYMBOL(find_next_bit_le);
#endif
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index c2cf2c311b7d..5813072bc589 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -311,7 +311,7 @@ int __sg_alloc_table(struct sg_table *table, unsigned int nents,
if (prv)
table->nents = ++table->orig_nents;
- return -ENOMEM;
+ return -ENOMEM;
}
sg_init_table(sg, alloc_size);
diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index e14a15ac250b..71ec3afe1681 100644
--- a/lib/test_bitmap.c
+++ b/lib/test_bitmap.c
@@ -275,22 +275,23 @@ static void __init test_copy(void)
static void __init test_replace(void)
{
unsigned int nbits = 64;
+ unsigned int nlongs = DIV_ROUND_UP(nbits, BITS_PER_LONG);
DECLARE_BITMAP(bmap, 1024);
bitmap_zero(bmap, 1024);
- bitmap_replace(bmap, &exp2[0], &exp2[1], exp2_to_exp3_mask, nbits);
+ bitmap_replace(bmap, &exp2[0 * nlongs], &exp2[1 * nlongs], exp2_to_exp3_mask, nbits);
expect_eq_bitmap(bmap, exp3_0_1, nbits);
bitmap_zero(bmap, 1024);
- bitmap_replace(bmap, &exp2[1], &exp2[0], exp2_to_exp3_mask, nbits);
+ bitmap_replace(bmap, &exp2[1 * nlongs], &exp2[0 * nlongs], exp2_to_exp3_mask, nbits);
expect_eq_bitmap(bmap, exp3_1_0, nbits);
bitmap_fill(bmap, 1024);
- bitmap_replace(bmap, &exp2[0], &exp2[1], exp2_to_exp3_mask, nbits);
+ bitmap_replace(bmap, &exp2[0 * nlongs], &exp2[1 * nlongs], exp2_to_exp3_mask, nbits);
expect_eq_bitmap(bmap, exp3_0_1, nbits);
bitmap_fill(bmap, 1024);
- bitmap_replace(bmap, &exp2[1], &exp2[0], exp2_to_exp3_mask, nbits);
+ bitmap_replace(bmap, &exp2[1 * nlongs], &exp2[0 * nlongs], exp2_to_exp3_mask, nbits);
expect_eq_bitmap(bmap, exp3_1_0, nbits);
}
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index 328d33beae36..3872d250ed2c 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -158,6 +158,7 @@ static noinline void __init kmalloc_oob_krealloc_more(void)
if (!ptr1 || !ptr2) {
pr_err("Allocation failed\n");
kfree(ptr1);
+ kfree(ptr2);
return;
}
diff --git a/lib/zlib_deflate/deflate.c b/lib/zlib_deflate/deflate.c
index d20ef458f137..8a878d0d892c 100644
--- a/lib/zlib_deflate/deflate.c
+++ b/lib/zlib_deflate/deflate.c
@@ -52,16 +52,19 @@
#include <linux/zutil.h>
#include "defutil.h"
+/* architecture-specific bits */
+#ifdef CONFIG_ZLIB_DFLTCC
+# include "../zlib_dfltcc/dfltcc.h"
+#else
+#define DEFLATE_RESET_HOOK(strm) do {} while (0)
+#define DEFLATE_HOOK(strm, flush, bstate) 0
+#define DEFLATE_NEED_CHECKSUM(strm) 1
+#define DEFLATE_DFLTCC_ENABLED() 0
+#endif
/* ===========================================================================
* Function prototypes.
*/
-typedef enum {
- need_more, /* block not completed, need more input or more output */
- block_done, /* block flush performed */
- finish_started, /* finish started, need only more output at next deflate */
- finish_done /* finish done, accept no more input or output */
-} block_state;
typedef block_state (*compress_func) (deflate_state *s, int flush);
/* Compression function. Returns the block state after the call. */
@@ -72,7 +75,6 @@ static block_state deflate_fast (deflate_state *s, int flush);
static block_state deflate_slow (deflate_state *s, int flush);
static void lm_init (deflate_state *s);
static void putShortMSB (deflate_state *s, uInt b);
-static void flush_pending (z_streamp strm);
static int read_buf (z_streamp strm, Byte *buf, unsigned size);
static uInt longest_match (deflate_state *s, IPos cur_match);
@@ -98,6 +100,25 @@ static void check_match (deflate_state *s, IPos start, IPos match,
* See deflate.c for comments about the MIN_MATCH+1.
*/
+/* Workspace to be allocated for deflate processing */
+typedef struct deflate_workspace {
+ /* State memory for the deflator */
+ deflate_state deflate_memory;
+#ifdef CONFIG_ZLIB_DFLTCC
+ /* State memory for s390 hardware deflate */
+ struct dfltcc_state dfltcc_memory;
+#endif
+ Byte *window_memory;
+ Pos *prev_memory;
+ Pos *head_memory;
+ char *overlay_memory;
+} deflate_workspace;
+
+#ifdef CONFIG_ZLIB_DFLTCC
+/* dfltcc_state must be doubleword aligned for DFLTCC call */
+static_assert(offsetof(struct deflate_workspace, dfltcc_memory) % 8 == 0);
+#endif
+
/* Values for max_lazy_match, good_match and max_chain_length, depending on
* the desired pack level (0..9). The values given below have been tuned to
* exclude worst case performance for pathological files. Better values may be
@@ -207,7 +228,15 @@ int zlib_deflateInit2(
*/
next = (char *) mem;
next += sizeof(*mem);
+#ifdef CONFIG_ZLIB_DFLTCC
+ /*
+ * DFLTCC requires the window to be page aligned.
+ * Thus, we overallocate and take the aligned portion of the buffer.
+ */
+ mem->window_memory = (Byte *) PTR_ALIGN(next, PAGE_SIZE);
+#else
mem->window_memory = (Byte *) next;
+#endif
next += zlib_deflate_window_memsize(windowBits);
mem->prev_memory = (Pos *) next;
next += zlib_deflate_prev_memsize(windowBits);
@@ -277,6 +306,8 @@ int zlib_deflateReset(
zlib_tr_init(s);
lm_init(s);
+ DEFLATE_RESET_HOOK(strm);
+
return Z_OK;
}
@@ -294,35 +325,6 @@ static void putShortMSB(
put_byte(s, (Byte)(b & 0xff));
}
-/* =========================================================================
- * Flush as much pending output as possible. All deflate() output goes
- * through this function so some applications may wish to modify it
- * to avoid allocating a large strm->next_out buffer and copying into it.
- * (See also read_buf()).
- */
-static void flush_pending(
- z_streamp strm
-)
-{
- deflate_state *s = (deflate_state *) strm->state;
- unsigned len = s->pending;
-
- if (len > strm->avail_out) len = strm->avail_out;
- if (len == 0) return;
-
- if (strm->next_out != NULL) {
- memcpy(strm->next_out, s->pending_out, len);
- strm->next_out += len;
- }
- s->pending_out += len;
- strm->total_out += len;
- strm->avail_out -= len;
- s->pending -= len;
- if (s->pending == 0) {
- s->pending_out = s->pending_buf;
- }
-}
-
/* ========================================================================= */
int zlib_deflate(
z_streamp strm,
@@ -404,7 +406,8 @@ int zlib_deflate(
(flush != Z_NO_FLUSH && s->status != FINISH_STATE)) {
block_state bstate;
- bstate = (*(configuration_table[s->level].func))(s, flush);
+ bstate = DEFLATE_HOOK(strm, flush, &bstate) ? bstate :
+ (*(configuration_table[s->level].func))(s, flush);
if (bstate == finish_started || bstate == finish_done) {
s->status = FINISH_STATE;
@@ -503,7 +506,8 @@ static int read_buf(
strm->avail_in -= len;
- if (!((deflate_state *)(strm->state))->noheader) {
+ if (!DEFLATE_NEED_CHECKSUM(strm)) {}
+ else if (!((deflate_state *)(strm->state))->noheader) {
strm->adler = zlib_adler32(strm->adler, strm->next_in, len);
}
memcpy(buf, strm->next_in, len);
@@ -1135,3 +1139,8 @@ int zlib_deflate_workspacesize(int windowBits, int memLevel)
+ zlib_deflate_head_memsize(memLevel)
+ zlib_deflate_overlay_memsize(memLevel);
}
+
+int zlib_deflate_dfltcc_enabled(void)
+{
+ return DEFLATE_DFLTCC_ENABLED();
+}
diff --git a/lib/zlib_deflate/deflate_syms.c b/lib/zlib_deflate/deflate_syms.c
index 72fe4b73be53..24b740b99678 100644
--- a/lib/zlib_deflate/deflate_syms.c
+++ b/lib/zlib_deflate/deflate_syms.c
@@ -12,6 +12,7 @@
#include <linux/zlib.h>
EXPORT_SYMBOL(zlib_deflate_workspacesize);
+EXPORT_SYMBOL(zlib_deflate_dfltcc_enabled);
EXPORT_SYMBOL(zlib_deflate);
EXPORT_SYMBOL(zlib_deflateInit2);
EXPORT_SYMBOL(zlib_deflateEnd);
diff --git a/lib/zlib_deflate/deftree.c b/lib/zlib_deflate/deftree.c
index 9b1756b12743..a4a34da512fe 100644
--- a/lib/zlib_deflate/deftree.c
+++ b/lib/zlib_deflate/deftree.c
@@ -76,11 +76,6 @@ static const uch bl_order[BL_CODES]
* probability, to avoid transmitting the lengths for unused bit length codes.
*/
-#define Buf_size (8 * 2*sizeof(char))
-/* Number of bits used within bi_buf. (bi_buf might be implemented on
- * more than 16 bits on some systems.)
- */
-
/* ===========================================================================
* Local data. These are initialized only once.
*/
@@ -147,7 +142,6 @@ static void send_all_trees (deflate_state *s, int lcodes, int dcodes,
static void compress_block (deflate_state *s, ct_data *ltree,
ct_data *dtree);
static void set_data_type (deflate_state *s);
-static void bi_windup (deflate_state *s);
static void bi_flush (deflate_state *s);
static void copy_block (deflate_state *s, char *buf, unsigned len,
int header);
@@ -170,54 +164,6 @@ static void copy_block (deflate_state *s, char *buf, unsigned len,
*/
/* ===========================================================================
- * Send a value on a given number of bits.
- * IN assertion: length <= 16 and value fits in length bits.
- */
-#ifdef DEBUG_ZLIB
-static void send_bits (deflate_state *s, int value, int length);
-
-static void send_bits(
- deflate_state *s,
- int value, /* value to send */
- int length /* number of bits */
-)
-{
- Tracevv((stderr," l %2d v %4x ", length, value));
- Assert(length > 0 && length <= 15, "invalid length");
- s->bits_sent += (ulg)length;
-
- /* If not enough room in bi_buf, use (valid) bits from bi_buf and
- * (16 - bi_valid) bits from value, leaving (width - (16-bi_valid))
- * unused bits in value.
- */
- if (s->bi_valid > (int)Buf_size - length) {
- s->bi_buf |= (value << s->bi_valid);
- put_short(s, s->bi_buf);
- s->bi_buf = (ush)value >> (Buf_size - s->bi_valid);
- s->bi_valid += length - Buf_size;
- } else {
- s->bi_buf |= value << s->bi_valid;
- s->bi_valid += length;
- }
-}
-#else /* !DEBUG_ZLIB */
-
-#define send_bits(s, value, length) \
-{ int len = length;\
- if (s->bi_valid > (int)Buf_size - len) {\
- int val = value;\
- s->bi_buf |= (val << s->bi_valid);\
- put_short(s, s->bi_buf);\
- s->bi_buf = (ush)val >> (Buf_size - s->bi_valid);\
- s->bi_valid += len - Buf_size;\
- } else {\
- s->bi_buf |= (value) << s->bi_valid;\
- s->bi_valid += len;\
- }\
-}
-#endif /* DEBUG_ZLIB */
-
-/* ===========================================================================
* Initialize the various 'constant' tables. In a multi-threaded environment,
* this function may be called by two threads concurrently, but this is
* harmless since both invocations do exactly the same thing.
diff --git a/lib/zlib_deflate/defutil.h b/lib/zlib_deflate/defutil.h
index a8c370897c9f..385333b22ec6 100644
--- a/lib/zlib_deflate/defutil.h
+++ b/lib/zlib_deflate/defutil.h
@@ -1,5 +1,7 @@
+#ifndef DEFUTIL_H
+#define DEFUTIL_H
-
+#include <linux/zutil.h>
#define Assert(err, str)
#define Trace(dummy)
@@ -238,17 +240,13 @@ typedef struct deflate_state {
} deflate_state;
-typedef struct deflate_workspace {
- /* State memory for the deflator */
- deflate_state deflate_memory;
- Byte *window_memory;
- Pos *prev_memory;
- Pos *head_memory;
- char *overlay_memory;
-} deflate_workspace;
-
+#ifdef CONFIG_ZLIB_DFLTCC
+#define zlib_deflate_window_memsize(windowBits) \
+ (2 * (1 << (windowBits)) * sizeof(Byte) + PAGE_SIZE)
+#else
#define zlib_deflate_window_memsize(windowBits) \
(2 * (1 << (windowBits)) * sizeof(Byte))
+#endif
#define zlib_deflate_prev_memsize(windowBits) \
((1 << (windowBits)) * sizeof(Pos))
#define zlib_deflate_head_memsize(memLevel) \
@@ -293,6 +291,24 @@ void zlib_tr_stored_type_only (deflate_state *);
}
/* ===========================================================================
+ * Reverse the first len bits of a code, using straightforward code (a faster
+ * method would use a table)
+ * IN assertion: 1 <= len <= 15
+ */
+static inline unsigned bi_reverse(
+ unsigned code, /* the value to invert */
+ int len /* its bit length */
+)
+{
+ register unsigned res = 0;
+ do {
+ res |= code & 1;
+ code >>= 1, res <<= 1;
+ } while (--len > 0);
+ return res >> 1;
+}
+
+/* ===========================================================================
* Flush the bit buffer, keeping at most 7 bits in it.
*/
static inline void bi_flush(deflate_state *s)
@@ -325,3 +341,101 @@ static inline void bi_windup(deflate_state *s)
#endif
}
+typedef enum {
+ need_more, /* block not completed, need more input or more output */
+ block_done, /* block flush performed */
+ finish_started, /* finish started, need only more output at next deflate */
+ finish_done /* finish done, accept no more input or output */
+} block_state;
+
+#define Buf_size (8 * 2*sizeof(char))
+/* Number of bits used within bi_buf. (bi_buf might be implemented on
+ * more than 16 bits on some systems.)
+ */
+
+/* ===========================================================================
+ * Send a value on a given number of bits.
+ * IN assertion: length <= 16 and value fits in length bits.
+ */
+#ifdef DEBUG_ZLIB
+static void send_bits (deflate_state *s, int value, int length);
+
+static void send_bits(
+ deflate_state *s,
+ int value, /* value to send */
+ int length /* number of bits */
+)
+{
+ Tracevv((stderr," l %2d v %4x ", length, value));
+ Assert(length > 0 && length <= 15, "invalid length");
+ s->bits_sent += (ulg)length;
+
+ /* If not enough room in bi_buf, use (valid) bits from bi_buf and
+ * (16 - bi_valid) bits from value, leaving (width - (16-bi_valid))
+ * unused bits in value.
+ */
+ if (s->bi_valid > (int)Buf_size - length) {
+ s->bi_buf |= (value << s->bi_valid);
+ put_short(s, s->bi_buf);
+ s->bi_buf = (ush)value >> (Buf_size - s->bi_valid);
+ s->bi_valid += length - Buf_size;
+ } else {
+ s->bi_buf |= value << s->bi_valid;
+ s->bi_valid += length;
+ }
+}
+#else /* !DEBUG_ZLIB */
+
+#define send_bits(s, value, length) \
+{ int len = length;\
+ if (s->bi_valid > (int)Buf_size - len) {\
+ int val = value;\
+ s->bi_buf |= (val << s->bi_valid);\
+ put_short(s, s->bi_buf);\
+ s->bi_buf = (ush)val >> (Buf_size - s->bi_valid);\
+ s->bi_valid += len - Buf_size;\
+ } else {\
+ s->bi_buf |= (value) << s->bi_valid;\
+ s->bi_valid += len;\
+ }\
+}
+#endif /* DEBUG_ZLIB */
+
+static inline void zlib_tr_send_bits(
+ deflate_state *s,
+ int value,
+ int length
+)
+{
+ send_bits(s, value, length);
+}
+
+/* =========================================================================
+ * Flush as much pending output as possible. All deflate() output goes
+ * through this function so some applications may wish to modify it
+ * to avoid allocating a large strm->next_out buffer and copying into it.
+ * (See also read_buf()).
+ */
+static inline void flush_pending(
+ z_streamp strm
+)
+{
+ deflate_state *s = (deflate_state *) strm->state;
+ unsigned len = s->pending;
+
+ if (len > strm->avail_out) len = strm->avail_out;
+ if (len == 0) return;
+
+ if (strm->next_out != NULL) {
+ memcpy(strm->next_out, s->pending_out, len);
+ strm->next_out += len;
+ }
+ s->pending_out += len;
+ strm->total_out += len;
+ strm->avail_out -= len;
+ s->pending -= len;
+ if (s->pending == 0) {
+ s->pending_out = s->pending_buf;
+ }
+}
+#endif /* DEFUTIL_H */
diff --git a/lib/zlib_dfltcc/Makefile b/lib/zlib_dfltcc/Makefile
new file mode 100644
index 000000000000..8e4d5afbbb10
--- /dev/null
+++ b/lib/zlib_dfltcc/Makefile
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# This is a modified version of zlib, which does all memory
+# allocation ahead of time.
+#
+# This is the code for s390 zlib hardware support.
+#
+
+obj-$(CONFIG_ZLIB_DFLTCC) += zlib_dfltcc.o
+
+zlib_dfltcc-objs := dfltcc.o dfltcc_deflate.o dfltcc_inflate.o dfltcc_syms.o
diff --git a/lib/zlib_dfltcc/dfltcc.c b/lib/zlib_dfltcc/dfltcc.c
new file mode 100644
index 000000000000..c30de430b30c
--- /dev/null
+++ b/lib/zlib_dfltcc/dfltcc.c
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: Zlib
+/* dfltcc.c - SystemZ DEFLATE CONVERSION CALL support. */
+
+#include <linux/zutil.h>
+#include "dfltcc_util.h"
+#include "dfltcc.h"
+
+char *oesc_msg(
+ char *buf,
+ int oesc
+)
+{
+ if (oesc == 0x00)
+ return NULL; /* Successful completion */
+ else {
+#ifdef STATIC
+ return NULL; /* Ignore for pre-boot decompressor */
+#else
+ sprintf(buf, "Operation-Ending-Supplemental Code is 0x%.2X", oesc);
+ return buf;
+#endif
+ }
+}
+
+void dfltcc_reset(
+ z_streamp strm,
+ uInt size
+)
+{
+ struct dfltcc_state *dfltcc_state =
+ (struct dfltcc_state *)((char *)strm->state + size);
+ struct dfltcc_qaf_param *param =
+ (struct dfltcc_qaf_param *)&dfltcc_state->param;
+
+ /* Initialize available functions */
+ if (is_dfltcc_enabled()) {
+ dfltcc(DFLTCC_QAF, param, NULL, NULL, NULL, NULL, NULL);
+ memmove(&dfltcc_state->af, param, sizeof(dfltcc_state->af));
+ } else
+ memset(&dfltcc_state->af, 0, sizeof(dfltcc_state->af));
+
+ /* Initialize parameter block */
+ memset(&dfltcc_state->param, 0, sizeof(dfltcc_state->param));
+ dfltcc_state->param.nt = 1;
+
+ /* Initialize tuning parameters */
+ if (zlib_dfltcc_support == ZLIB_DFLTCC_FULL_DEBUG)
+ dfltcc_state->level_mask = DFLTCC_LEVEL_MASK_DEBUG;
+ else
+ dfltcc_state->level_mask = DFLTCC_LEVEL_MASK;
+ dfltcc_state->block_size = DFLTCC_BLOCK_SIZE;
+ dfltcc_state->block_threshold = DFLTCC_FIRST_FHT_BLOCK_SIZE;
+ dfltcc_state->dht_threshold = DFLTCC_DHT_MIN_SAMPLE_SIZE;
+ dfltcc_state->param.ribm = DFLTCC_RIBM;
+}
diff --git a/lib/zlib_dfltcc/dfltcc.h b/lib/zlib_dfltcc/dfltcc.h
new file mode 100644
index 000000000000..2a2fac1d050a
--- /dev/null
+++ b/lib/zlib_dfltcc/dfltcc.h
@@ -0,0 +1,155 @@
+// SPDX-License-Identifier: Zlib
+#ifndef DFLTCC_H
+#define DFLTCC_H
+
+#include "../zlib_deflate/defutil.h"
+#include <asm/facility.h>
+#include <asm/setup.h>
+
+/*
+ * Tuning parameters.
+ */
+#define DFLTCC_LEVEL_MASK 0x2 /* DFLTCC compression for level 1 only */
+#define DFLTCC_LEVEL_MASK_DEBUG 0x3fe /* DFLTCC compression for all levels */
+#define DFLTCC_BLOCK_SIZE 1048576
+#define DFLTCC_FIRST_FHT_BLOCK_SIZE 4096
+#define DFLTCC_DHT_MIN_SAMPLE_SIZE 4096
+#define DFLTCC_RIBM 0
+
+#define DFLTCC_FACILITY 151
+
+/*
+ * Parameter Block for Query Available Functions.
+ */
+struct dfltcc_qaf_param {
+ char fns[16];
+ char reserved1[8];
+ char fmts[2];
+ char reserved2[6];
+};
+
+static_assert(sizeof(struct dfltcc_qaf_param) == 32);
+
+#define DFLTCC_FMT0 0
+
+/*
+ * Parameter Block for Generate Dynamic-Huffman Table, Compress and Expand.
+ */
+struct dfltcc_param_v0 {
+ uint16_t pbvn; /* Parameter-Block-Version Number */
+ uint8_t mvn; /* Model-Version Number */
+ uint8_t ribm; /* Reserved for IBM use */
+ unsigned reserved32 : 31;
+ unsigned cf : 1; /* Continuation Flag */
+ uint8_t reserved64[8];
+ unsigned nt : 1; /* New Task */
+ unsigned reserved129 : 1;
+ unsigned cvt : 1; /* Check Value Type */
+ unsigned reserved131 : 1;
+ unsigned htt : 1; /* Huffman-Table Type */
+ unsigned bcf : 1; /* Block-Continuation Flag */
+ unsigned bcc : 1; /* Block Closing Control */
+ unsigned bhf : 1; /* Block Header Final */
+ unsigned reserved136 : 1;
+ unsigned reserved137 : 1;
+ unsigned dhtgc : 1; /* DHT Generation Control */
+ unsigned reserved139 : 5;
+ unsigned reserved144 : 5;
+ unsigned sbb : 3; /* Sub-Byte Boundary */
+ uint8_t oesc; /* Operation-Ending-Supplemental Code */
+ unsigned reserved160 : 12;
+ unsigned ifs : 4; /* Incomplete-Function Status */
+ uint16_t ifl; /* Incomplete-Function Length */
+ uint8_t reserved192[8];
+ uint8_t reserved256[8];
+ uint8_t reserved320[4];
+ uint16_t hl; /* History Length */
+ unsigned reserved368 : 1;
+ uint16_t ho : 15; /* History Offset */
+ uint32_t cv; /* Check Value */
+ unsigned eobs : 15; /* End-of-block Symbol */
+ unsigned reserved431: 1;
+ uint8_t eobl : 4; /* End-of-block Length */
+ unsigned reserved436 : 12;
+ unsigned reserved448 : 4;
+ uint16_t cdhtl : 12; /* Compressed-Dynamic-Huffman Table
+ Length */
+ uint8_t reserved464[6];
+ uint8_t cdht[288];
+ uint8_t reserved[32];
+ uint8_t csb[1152];
+};
+
+static_assert(sizeof(struct dfltcc_param_v0) == 1536);
+
+#define CVT_CRC32 0
+#define CVT_ADLER32 1
+#define HTT_FIXED 0
+#define HTT_DYNAMIC 1
+
+/*
+ * Extension of inflate_state and deflate_state for DFLTCC.
+ */
+struct dfltcc_state {
+ struct dfltcc_param_v0 param; /* Parameter block */
+ struct dfltcc_qaf_param af; /* Available functions */
+ uLong level_mask; /* Levels on which to use DFLTCC */
+ uLong block_size; /* New block each X bytes */
+ uLong block_threshold; /* New block after total_in > X */
+ uLong dht_threshold; /* New block only if avail_in >= X */
+ char msg[64]; /* Buffer for strm->msg */
+};
+
+/* Resides right after inflate_state or deflate_state */
+#define GET_DFLTCC_STATE(state) ((struct dfltcc_state *)((state) + 1))
+
+/* External functions */
+int dfltcc_can_deflate(z_streamp strm);
+int dfltcc_deflate(z_streamp strm,
+ int flush,
+ block_state *result);
+void dfltcc_reset(z_streamp strm, uInt size);
+int dfltcc_can_inflate(z_streamp strm);
+typedef enum {
+ DFLTCC_INFLATE_CONTINUE,
+ DFLTCC_INFLATE_BREAK,
+ DFLTCC_INFLATE_SOFTWARE,
+} dfltcc_inflate_action;
+dfltcc_inflate_action dfltcc_inflate(z_streamp strm,
+ int flush, int *ret);
+static inline int is_dfltcc_enabled(void)
+{
+return (zlib_dfltcc_support != ZLIB_DFLTCC_DISABLED &&
+ test_facility(DFLTCC_FACILITY));
+}
+
+#define DEFLATE_RESET_HOOK(strm) \
+ dfltcc_reset((strm), sizeof(deflate_state))
+
+#define DEFLATE_HOOK dfltcc_deflate
+
+#define DEFLATE_NEED_CHECKSUM(strm) (!dfltcc_can_deflate((strm)))
+
+#define DEFLATE_DFLTCC_ENABLED() is_dfltcc_enabled()
+
+#define INFLATE_RESET_HOOK(strm) \
+ dfltcc_reset((strm), sizeof(struct inflate_state))
+
+#define INFLATE_TYPEDO_HOOK(strm, flush) \
+ if (dfltcc_can_inflate((strm))) { \
+ dfltcc_inflate_action action; \
+\
+ RESTORE(); \
+ action = dfltcc_inflate((strm), (flush), &ret); \
+ LOAD(); \
+ if (action == DFLTCC_INFLATE_CONTINUE) \
+ break; \
+ else if (action == DFLTCC_INFLATE_BREAK) \
+ goto inf_leave; \
+ }
+
+#define INFLATE_NEED_CHECKSUM(strm) (!dfltcc_can_inflate((strm)))
+
+#define INFLATE_NEED_UPDATEWINDOW(strm) (!dfltcc_can_inflate((strm)))
+
+#endif /* DFLTCC_H */
diff --git a/lib/zlib_dfltcc/dfltcc_deflate.c b/lib/zlib_dfltcc/dfltcc_deflate.c
new file mode 100644
index 000000000000..00c185101c6d
--- /dev/null
+++ b/lib/zlib_dfltcc/dfltcc_deflate.c
@@ -0,0 +1,279 @@
+// SPDX-License-Identifier: Zlib
+
+#include "../zlib_deflate/defutil.h"
+#include "dfltcc_util.h"
+#include "dfltcc.h"
+#include <asm/setup.h>
+#include <linux/zutil.h>
+
+/*
+ * Compress.
+ */
+int dfltcc_can_deflate(
+ z_streamp strm
+)
+{
+ deflate_state *state = (deflate_state *)strm->state;
+ struct dfltcc_state *dfltcc_state = GET_DFLTCC_STATE(state);
+
+ /* Check for kernel dfltcc command line parameter */
+ if (zlib_dfltcc_support == ZLIB_DFLTCC_DISABLED ||
+ zlib_dfltcc_support == ZLIB_DFLTCC_INFLATE_ONLY)
+ return 0;
+
+ /* Unsupported compression settings */
+ if (!dfltcc_are_params_ok(state->level, state->w_bits, state->strategy,
+ dfltcc_state->level_mask))
+ return 0;
+
+ /* Unsupported hardware */
+ if (!is_bit_set(dfltcc_state->af.fns, DFLTCC_GDHT) ||
+ !is_bit_set(dfltcc_state->af.fns, DFLTCC_CMPR) ||
+ !is_bit_set(dfltcc_state->af.fmts, DFLTCC_FMT0))
+ return 0;
+
+ return 1;
+}
+
+static void dfltcc_gdht(
+ z_streamp strm
+)
+{
+ deflate_state *state = (deflate_state *)strm->state;
+ struct dfltcc_param_v0 *param = &GET_DFLTCC_STATE(state)->param;
+ size_t avail_in = avail_in = strm->avail_in;
+
+ dfltcc(DFLTCC_GDHT,
+ param, NULL, NULL,
+ &strm->next_in, &avail_in, NULL);
+}
+
+static dfltcc_cc dfltcc_cmpr(
+ z_streamp strm
+)
+{
+ deflate_state *state = (deflate_state *)strm->state;
+ struct dfltcc_param_v0 *param = &GET_DFLTCC_STATE(state)->param;
+ size_t avail_in = strm->avail_in;
+ size_t avail_out = strm->avail_out;
+ dfltcc_cc cc;
+
+ cc = dfltcc(DFLTCC_CMPR | HBT_CIRCULAR,
+ param, &strm->next_out, &avail_out,
+ &strm->next_in, &avail_in, state->window);
+ strm->total_in += (strm->avail_in - avail_in);
+ strm->total_out += (strm->avail_out - avail_out);
+ strm->avail_in = avail_in;
+ strm->avail_out = avail_out;
+ return cc;
+}
+
+static void send_eobs(
+ z_streamp strm,
+ const struct dfltcc_param_v0 *param
+)
+{
+ deflate_state *state = (deflate_state *)strm->state;
+
+ zlib_tr_send_bits(
+ state,
+ bi_reverse(param->eobs >> (15 - param->eobl), param->eobl),
+ param->eobl);
+ flush_pending(strm);
+ if (state->pending != 0) {
+ /* The remaining data is located in pending_out[0:pending]. If someone
+ * calls put_byte() - this might happen in deflate() - the byte will be
+ * placed into pending_buf[pending], which is incorrect. Move the
+ * remaining data to the beginning of pending_buf so that put_byte() is
+ * usable again.
+ */
+ memmove(state->pending_buf, state->pending_out, state->pending);
+ state->pending_out = state->pending_buf;
+ }
+#ifdef ZLIB_DEBUG
+ state->compressed_len += param->eobl;
+#endif
+}
+
+int dfltcc_deflate(
+ z_streamp strm,
+ int flush,
+ block_state *result
+)
+{
+ deflate_state *state = (deflate_state *)strm->state;
+ struct dfltcc_state *dfltcc_state = GET_DFLTCC_STATE(state);
+ struct dfltcc_param_v0 *param = &dfltcc_state->param;
+ uInt masked_avail_in;
+ dfltcc_cc cc;
+ int need_empty_block;
+ int soft_bcc;
+ int no_flush;
+
+ if (!dfltcc_can_deflate(strm))
+ return 0;
+
+again:
+ masked_avail_in = 0;
+ soft_bcc = 0;
+ no_flush = flush == Z_NO_FLUSH;
+
+ /* Trailing empty block. Switch to software, except when Continuation Flag
+ * is set, which means that DFLTCC has buffered some output in the
+ * parameter block and needs to be called again in order to flush it.
+ */
+ if (flush == Z_FINISH && strm->avail_in == 0 && !param->cf) {
+ if (param->bcf) {
+ /* A block is still open, and the hardware does not support closing
+ * blocks without adding data. Thus, close it manually.
+ */
+ send_eobs(strm, param);
+ param->bcf = 0;
+ }
+ return 0;
+ }
+
+ if (strm->avail_in == 0 && !param->cf) {
+ *result = need_more;
+ return 1;
+ }
+
+ /* There is an open non-BFINAL block, we are not going to close it just
+ * yet, we have compressed more than DFLTCC_BLOCK_SIZE bytes and we see
+ * more than DFLTCC_DHT_MIN_SAMPLE_SIZE bytes. Open a new block with a new
+ * DHT in order to adapt to a possibly changed input data distribution.
+ */
+ if (param->bcf && no_flush &&
+ strm->total_in > dfltcc_state->block_threshold &&
+ strm->avail_in >= dfltcc_state->dht_threshold) {
+ if (param->cf) {
+ /* We need to flush the DFLTCC buffer before writing the
+ * End-of-block Symbol. Mask the input data and proceed as usual.
+ */
+ masked_avail_in += strm->avail_in;
+ strm->avail_in = 0;
+ no_flush = 0;
+ } else {
+ /* DFLTCC buffer is empty, so we can manually write the
+ * End-of-block Symbol right away.
+ */
+ send_eobs(strm, param);
+ param->bcf = 0;
+ dfltcc_state->block_threshold =
+ strm->total_in + dfltcc_state->block_size;
+ if (strm->avail_out == 0) {
+ *result = need_more;
+ return 1;
+ }
+ }
+ }
+
+ /* The caller gave us too much data. Pass only one block worth of
+ * uncompressed data to DFLTCC and mask the rest, so that on the next
+ * iteration we start a new block.
+ */
+ if (no_flush && strm->avail_in > dfltcc_state->block_size) {
+ masked_avail_in += (strm->avail_in - dfltcc_state->block_size);
+ strm->avail_in = dfltcc_state->block_size;
+ }
+
+ /* When we have an open non-BFINAL deflate block and caller indicates that
+ * the stream is ending, we need to close an open deflate block and open a
+ * BFINAL one.
+ */
+ need_empty_block = flush == Z_FINISH && param->bcf && !param->bhf;
+
+ /* Translate stream to parameter block */
+ param->cvt = CVT_ADLER32;
+ if (!no_flush)
+ /* We need to close a block. Always do this in software - when there is
+ * no input data, the hardware will not nohor BCC. */
+ soft_bcc = 1;
+ if (flush == Z_FINISH && !param->bcf)
+ /* We are about to open a BFINAL block, set Block Header Final bit
+ * until the stream ends.
+ */
+ param->bhf = 1;
+ /* DFLTCC-CMPR will write to next_out, so make sure that buffers with
+ * higher precedence are empty.
+ */
+ Assert(state->pending == 0, "There must be no pending bytes");
+ Assert(state->bi_valid < 8, "There must be less than 8 pending bits");
+ param->sbb = (unsigned int)state->bi_valid;
+ if (param->sbb > 0)
+ *strm->next_out = (Byte)state->bi_buf;
+ if (param->hl)
+ param->nt = 0; /* Honor history */
+ param->cv = strm->adler;
+
+ /* When opening a block, choose a Huffman-Table Type */
+ if (!param->bcf) {
+ if (strm->total_in == 0 && dfltcc_state->block_threshold > 0) {
+ param->htt = HTT_FIXED;
+ }
+ else {
+ param->htt = HTT_DYNAMIC;
+ dfltcc_gdht(strm);
+ }
+ }
+
+ /* Deflate */
+ do {
+ cc = dfltcc_cmpr(strm);
+ if (strm->avail_in < 4096 && masked_avail_in > 0)
+ /* We are about to call DFLTCC with a small input buffer, which is
+ * inefficient. Since there is masked data, there will be at least
+ * one more DFLTCC call, so skip the current one and make the next
+ * one handle more data.
+ */
+ break;
+ } while (cc == DFLTCC_CC_AGAIN);
+
+ /* Translate parameter block to stream */
+ strm->msg = oesc_msg(dfltcc_state->msg, param->oesc);
+ state->bi_valid = param->sbb;
+ if (state->bi_valid == 0)
+ state->bi_buf = 0; /* Avoid accessing next_out */
+ else
+ state->bi_buf = *strm->next_out & ((1 << state->bi_valid) - 1);
+ strm->adler = param->cv;
+
+ /* Unmask the input data */
+ strm->avail_in += masked_avail_in;
+ masked_avail_in = 0;
+
+ /* If we encounter an error, it means there is a bug in DFLTCC call */
+ Assert(cc != DFLTCC_CC_OP2_CORRUPT || param->oesc == 0, "BUG");
+
+ /* Update Block-Continuation Flag. It will be used to check whether to call
+ * GDHT the next time.
+ */
+ if (cc == DFLTCC_CC_OK) {
+ if (soft_bcc) {
+ send_eobs(strm, param);
+ param->bcf = 0;
+ dfltcc_state->block_threshold =
+ strm->total_in + dfltcc_state->block_size;
+ } else
+ param->bcf = 1;
+ if (flush == Z_FINISH) {
+ if (need_empty_block)
+ /* Make the current deflate() call also close the stream */
+ return 0;
+ else {
+ bi_windup(state);
+ *result = finish_done;
+ }
+ } else {
+ if (flush == Z_FULL_FLUSH)
+ param->hl = 0; /* Clear history */
+ *result = flush == Z_NO_FLUSH ? need_more : block_done;
+ }
+ } else {
+ param->bcf = 1;
+ *result = need_more;
+ }
+ if (strm->avail_in != 0 && strm->avail_out != 0)
+ goto again; /* deflate() must use all input or all output */
+ return 1;
+}
diff --git a/lib/zlib_dfltcc/dfltcc_inflate.c b/lib/zlib_dfltcc/dfltcc_inflate.c
new file mode 100644
index 000000000000..aa9ef23474df
--- /dev/null
+++ b/lib/zlib_dfltcc/dfltcc_inflate.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: Zlib
+
+#include "../zlib_inflate/inflate.h"
+#include "dfltcc_util.h"
+#include "dfltcc.h"
+#include <asm/setup.h>
+#include <linux/zutil.h>
+
+/*
+ * Expand.
+ */
+int dfltcc_can_inflate(
+ z_streamp strm
+)
+{
+ struct inflate_state *state = (struct inflate_state *)strm->state;
+ struct dfltcc_state *dfltcc_state = GET_DFLTCC_STATE(state);
+
+ /* Check for kernel dfltcc command line parameter */
+ if (zlib_dfltcc_support == ZLIB_DFLTCC_DISABLED ||
+ zlib_dfltcc_support == ZLIB_DFLTCC_DEFLATE_ONLY)
+ return 0;
+
+ /* Unsupported compression settings */
+ if (state->wbits != HB_BITS)
+ return 0;
+
+ /* Unsupported hardware */
+ return is_bit_set(dfltcc_state->af.fns, DFLTCC_XPND) &&
+ is_bit_set(dfltcc_state->af.fmts, DFLTCC_FMT0);
+}
+
+static int dfltcc_was_inflate_used(
+ z_streamp strm
+)
+{
+ struct inflate_state *state = (struct inflate_state *)strm->state;
+ struct dfltcc_param_v0 *param = &GET_DFLTCC_STATE(state)->param;
+
+ return !param->nt;
+}
+
+static int dfltcc_inflate_disable(
+ z_streamp strm
+)
+{
+ struct inflate_state *state = (struct inflate_state *)strm->state;
+ struct dfltcc_state *dfltcc_state = GET_DFLTCC_STATE(state);
+
+ if (!dfltcc_can_inflate(strm))
+ return 0;
+ if (dfltcc_was_inflate_used(strm))
+ /* DFLTCC has already decompressed some data. Since there is not
+ * enough information to resume decompression in software, the call
+ * must fail.
+ */
+ return 1;
+ /* DFLTCC was not used yet - decompress in software */
+ memset(&dfltcc_state->af, 0, sizeof(dfltcc_state->af));
+ return 0;
+}
+
+static dfltcc_cc dfltcc_xpnd(
+ z_streamp strm
+)
+{
+ struct inflate_state *state = (struct inflate_state *)strm->state;
+ struct dfltcc_param_v0 *param = &GET_DFLTCC_STATE(state)->param;
+ size_t avail_in = strm->avail_in;
+ size_t avail_out = strm->avail_out;
+ dfltcc_cc cc;
+
+ cc = dfltcc(DFLTCC_XPND | HBT_CIRCULAR,
+ param, &strm->next_out, &avail_out,
+ &strm->next_in, &avail_in, state->window);
+ strm->avail_in = avail_in;
+ strm->avail_out = avail_out;
+ return cc;
+}
+
+dfltcc_inflate_action dfltcc_inflate(
+ z_streamp strm,
+ int flush,
+ int *ret
+)
+{
+ struct inflate_state *state = (struct inflate_state *)strm->state;
+ struct dfltcc_state *dfltcc_state = GET_DFLTCC_STATE(state);
+ struct dfltcc_param_v0 *param = &dfltcc_state->param;
+ dfltcc_cc cc;
+
+ if (flush == Z_BLOCK) {
+ /* DFLTCC does not support stopping on block boundaries */
+ if (dfltcc_inflate_disable(strm)) {
+ *ret = Z_STREAM_ERROR;
+ return DFLTCC_INFLATE_BREAK;
+ } else
+ return DFLTCC_INFLATE_SOFTWARE;
+ }
+
+ if (state->last) {
+ if (state->bits != 0) {
+ strm->next_in++;
+ strm->avail_in--;
+ state->bits = 0;
+ }
+ state->mode = CHECK;
+ return DFLTCC_INFLATE_CONTINUE;
+ }
+
+ if (strm->avail_in == 0 && !param->cf)
+ return DFLTCC_INFLATE_BREAK;
+
+ if (!state->window || state->wsize == 0) {
+ state->mode = MEM;
+ return DFLTCC_INFLATE_CONTINUE;
+ }
+
+ /* Translate stream to parameter block */
+ param->cvt = CVT_ADLER32;
+ param->sbb = state->bits;
+ param->hl = state->whave; /* Software and hardware history formats match */
+ param->ho = (state->write - state->whave) & ((1 << HB_BITS) - 1);
+ if (param->hl)
+ param->nt = 0; /* Honor history for the first block */
+ param->cv = state->flags ? REVERSE(state->check) : state->check;
+
+ /* Inflate */
+ do {
+ cc = dfltcc_xpnd(strm);
+ } while (cc == DFLTCC_CC_AGAIN);
+
+ /* Translate parameter block to stream */
+ strm->msg = oesc_msg(dfltcc_state->msg, param->oesc);
+ state->last = cc == DFLTCC_CC_OK;
+ state->bits = param->sbb;
+ state->whave = param->hl;
+ state->write = (param->ho + param->hl) & ((1 << HB_BITS) - 1);
+ state->check = state->flags ? REVERSE(param->cv) : param->cv;
+ if (cc == DFLTCC_CC_OP2_CORRUPT && param->oesc != 0) {
+ /* Report an error if stream is corrupted */
+ state->mode = BAD;
+ return DFLTCC_INFLATE_CONTINUE;
+ }
+ state->mode = TYPEDO;
+ /* Break if operands are exhausted, otherwise continue looping */
+ return (cc == DFLTCC_CC_OP1_TOO_SHORT || cc == DFLTCC_CC_OP2_TOO_SHORT) ?
+ DFLTCC_INFLATE_BREAK : DFLTCC_INFLATE_CONTINUE;
+}
diff --git a/lib/zlib_dfltcc/dfltcc_syms.c b/lib/zlib_dfltcc/dfltcc_syms.c
new file mode 100644
index 000000000000..6f23481804c1
--- /dev/null
+++ b/lib/zlib_dfltcc/dfltcc_syms.c
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * linux/lib/zlib_dfltcc/dfltcc_syms.c
+ *
+ * Exported symbols for the s390 zlib dfltcc support.
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/zlib.h>
+#include "dfltcc.h"
+
+EXPORT_SYMBOL(dfltcc_can_deflate);
+EXPORT_SYMBOL(dfltcc_deflate);
+EXPORT_SYMBOL(dfltcc_reset);
+MODULE_LICENSE("GPL");
diff --git a/lib/zlib_dfltcc/dfltcc_util.h b/lib/zlib_dfltcc/dfltcc_util.h
new file mode 100644
index 000000000000..4a46b5009f0d
--- /dev/null
+++ b/lib/zlib_dfltcc/dfltcc_util.h
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: Zlib
+#ifndef DFLTCC_UTIL_H
+#define DFLTCC_UTIL_H
+
+#include <linux/zutil.h>
+
+/*
+ * C wrapper for the DEFLATE CONVERSION CALL instruction.
+ */
+typedef enum {
+ DFLTCC_CC_OK = 0,
+ DFLTCC_CC_OP1_TOO_SHORT = 1,
+ DFLTCC_CC_OP2_TOO_SHORT = 2,
+ DFLTCC_CC_OP2_CORRUPT = 2,
+ DFLTCC_CC_AGAIN = 3,
+} dfltcc_cc;
+
+#define DFLTCC_QAF 0
+#define DFLTCC_GDHT 1
+#define DFLTCC_CMPR 2
+#define DFLTCC_XPND 4
+#define HBT_CIRCULAR (1 << 7)
+#define HB_BITS 15
+#define HB_SIZE (1 << HB_BITS)
+
+static inline dfltcc_cc dfltcc(
+ int fn,
+ void *param,
+ Byte **op1,
+ size_t *len1,
+ const Byte **op2,
+ size_t *len2,
+ void *hist
+)
+{
+ Byte *t2 = op1 ? *op1 : NULL;
+ size_t t3 = len1 ? *len1 : 0;
+ const Byte *t4 = op2 ? *op2 : NULL;
+ size_t t5 = len2 ? *len2 : 0;
+ register int r0 __asm__("r0") = fn;
+ register void *r1 __asm__("r1") = param;
+ register Byte *r2 __asm__("r2") = t2;
+ register size_t r3 __asm__("r3") = t3;
+ register const Byte *r4 __asm__("r4") = t4;
+ register size_t r5 __asm__("r5") = t5;
+ int cc;
+
+ __asm__ volatile(
+ ".insn rrf,0xb9390000,%[r2],%[r4],%[hist],0\n"
+ "ipm %[cc]\n"
+ : [r2] "+r" (r2)
+ , [r3] "+r" (r3)
+ , [r4] "+r" (r4)
+ , [r5] "+r" (r5)
+ , [cc] "=r" (cc)
+ : [r0] "r" (r0)
+ , [r1] "r" (r1)
+ , [hist] "r" (hist)
+ : "cc", "memory");
+ t2 = r2; t3 = r3; t4 = r4; t5 = r5;
+
+ if (op1)
+ *op1 = t2;
+ if (len1)
+ *len1 = t3;
+ if (op2)
+ *op2 = t4;
+ if (len2)
+ *len2 = t5;
+ return (cc >> 28) & 3;
+}
+
+static inline int is_bit_set(
+ const char *bits,
+ int n
+)
+{
+ return bits[n / 8] & (1 << (7 - (n % 8)));
+}
+
+static inline void turn_bit_off(
+ char *bits,
+ int n
+)
+{
+ bits[n / 8] &= ~(1 << (7 - (n % 8)));
+}
+
+static inline int dfltcc_are_params_ok(
+ int level,
+ uInt window_bits,
+ int strategy,
+ uLong level_mask
+)
+{
+ return (level_mask & (1 << level)) != 0 &&
+ (window_bits == HB_BITS) &&
+ (strategy == Z_DEFAULT_STRATEGY);
+}
+
+char *oesc_msg(char *buf, int oesc);
+
+#endif /* DFLTCC_UTIL_H */
diff --git a/lib/zlib_inflate/inflate.c b/lib/zlib_inflate/inflate.c
index 48f14cd58c77..67cc9b08ae9d 100644
--- a/lib/zlib_inflate/inflate.c
+++ b/lib/zlib_inflate/inflate.c
@@ -15,6 +15,16 @@
#include "inffast.h"
#include "infutil.h"
+/* architecture-specific bits */
+#ifdef CONFIG_ZLIB_DFLTCC
+# include "../zlib_dfltcc/dfltcc.h"
+#else
+#define INFLATE_RESET_HOOK(strm) do {} while (0)
+#define INFLATE_TYPEDO_HOOK(strm, flush) do {} while (0)
+#define INFLATE_NEED_UPDATEWINDOW(strm) 1
+#define INFLATE_NEED_CHECKSUM(strm) 1
+#endif
+
int zlib_inflate_workspacesize(void)
{
return sizeof(struct inflate_workspace);
@@ -42,6 +52,7 @@ int zlib_inflateReset(z_streamp strm)
state->write = 0;
state->whave = 0;
+ INFLATE_RESET_HOOK(strm);
return Z_OK;
}
@@ -66,7 +77,15 @@ int zlib_inflateInit2(z_streamp strm, int windowBits)
return Z_STREAM_ERROR;
}
state->wbits = (unsigned)windowBits;
+#ifdef CONFIG_ZLIB_DFLTCC
+ /*
+ * DFLTCC requires the window to be page aligned.
+ * Thus, we overallocate and take the aligned portion of the buffer.
+ */
+ state->window = PTR_ALIGN(&WS(strm)->working_window[0], PAGE_SIZE);
+#else
state->window = &WS(strm)->working_window[0];
+#endif
return zlib_inflateReset(strm);
}
@@ -227,11 +246,6 @@ static int zlib_inflateSyncPacket(z_streamp strm)
bits -= bits & 7; \
} while (0)
-/* Reverse the bytes in a 32-bit value */
-#define REVERSE(q) \
- ((((q) >> 24) & 0xff) + (((q) >> 8) & 0xff00) + \
- (((q) & 0xff00) << 8) + (((q) & 0xff) << 24))
-
/*
inflate() uses a state machine to process as much input data and generate as
much output data as possible before returning. The state machine is
@@ -395,6 +409,7 @@ int zlib_inflate(z_streamp strm, int flush)
if (flush == Z_BLOCK) goto inf_leave;
/* fall through */
case TYPEDO:
+ INFLATE_TYPEDO_HOOK(strm, flush);
if (state->last) {
BYTEBITS();
state->mode = CHECK;
@@ -692,7 +707,7 @@ int zlib_inflate(z_streamp strm, int flush)
out -= left;
strm->total_out += out;
state->total += out;
- if (out)
+ if (INFLATE_NEED_CHECKSUM(strm) && out)
strm->adler = state->check =
UPDATE(state->check, put - out, out);
out = left;
@@ -726,7 +741,8 @@ int zlib_inflate(z_streamp strm, int flush)
*/
inf_leave:
RESTORE();
- if (state->wsize || (state->mode < CHECK && out != strm->avail_out))
+ if (INFLATE_NEED_UPDATEWINDOW(strm) &&
+ (state->wsize || (state->mode < CHECK && out != strm->avail_out)))
zlib_updatewindow(strm, out);
in -= strm->avail_in;
@@ -734,7 +750,7 @@ int zlib_inflate(z_streamp strm, int flush)
strm->total_in += in;
strm->total_out += out;
state->total += out;
- if (state->wrap && out)
+ if (INFLATE_NEED_CHECKSUM(strm) && state->wrap && out)
strm->adler = state->check =
UPDATE(state->check, strm->next_out - out, out);
diff --git a/lib/zlib_inflate/inflate.h b/lib/zlib_inflate/inflate.h
index 3d17b3d1b21f..f79337ddf98c 100644
--- a/lib/zlib_inflate/inflate.h
+++ b/lib/zlib_inflate/inflate.h
@@ -11,6 +11,8 @@
subject to change. Applications should only use zlib.h.
*/
+#include "inftrees.h"
+
/* Possible inflate modes between inflate() calls */
typedef enum {
HEAD, /* i: waiting for magic header */
@@ -108,4 +110,10 @@ struct inflate_state {
unsigned short work[288]; /* work area for code table building */
code codes[ENOUGH]; /* space for code tables */
};
+
+/* Reverse the bytes in a 32-bit value */
+#define REVERSE(q) \
+ ((((q) >> 24) & 0xff) + (((q) >> 8) & 0xff00) + \
+ (((q) & 0xff00) << 8) + (((q) & 0xff) << 24))
+
#endif
diff --git a/lib/zlib_inflate/infutil.h b/lib/zlib_inflate/infutil.h
index eb1a9007bd86..784ab33b7842 100644
--- a/lib/zlib_inflate/infutil.h
+++ b/lib/zlib_inflate/infutil.h
@@ -12,14 +12,28 @@
#define _INFUTIL_H
#include <linux/zlib.h>
+#ifdef CONFIG_ZLIB_DFLTCC
+#include "../zlib_dfltcc/dfltcc.h"
+#include <asm/page.h>
+#endif
/* memory allocation for inflation */
struct inflate_workspace {
struct inflate_state inflate_state;
- unsigned char working_window[1 << MAX_WBITS];
+#ifdef CONFIG_ZLIB_DFLTCC
+ struct dfltcc_state dfltcc_state;
+ unsigned char working_window[(1 << MAX_WBITS) + PAGE_SIZE];
+#else
+ unsigned char working_window[(1 << MAX_WBITS)];
+#endif
};
-#define WS(z) ((struct inflate_workspace *)(z->workspace))
+#ifdef CONFIG_ZLIB_DFLTCC
+/* dfltcc_state must be doubleword aligned for DFLTCC call */
+static_assert(offsetof(struct inflate_workspace, dfltcc_state) % 8 == 0);
+#endif
+
+#define WS(strm) ((struct inflate_workspace *)(strm->workspace))
#endif
diff --git a/mm/Makefile b/mm/Makefile
index 1937cc251883..32f08e22e824 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -20,6 +20,7 @@ KCOV_INSTRUMENT_kmemleak.o := n
KCOV_INSTRUMENT_memcontrol.o := n
KCOV_INSTRUMENT_mmzone.o := n
KCOV_INSTRUMENT_vmstat.o := n
+KCOV_INSTRUMENT_failslab.o := n
CFLAGS_init-mm.o += $(call cc-disable-warning, override-init)
CFLAGS_init-mm.o += $(call cc-disable-warning, initializer-overrides)
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index c360f6a6c844..62f05f605fb5 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -21,6 +21,7 @@ struct backing_dev_info noop_backing_dev_info = {
EXPORT_SYMBOL_GPL(noop_backing_dev_info);
static struct class *bdi_class;
+const char *bdi_unknown_name = "(unknown)";
/*
* bdi_lock protects bdi_tree and updates to bdi_list. bdi_list has RCU
diff --git a/mm/debug.c b/mm/debug.c
index 74ee73cf7079..ecccd9f17801 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -46,7 +46,15 @@ void __dump_page(struct page *page, const char *reason)
{
struct address_space *mapping;
bool page_poisoned = PagePoisoned(page);
+ /*
+ * Accessing the pageblock without the zone lock. It could change to
+ * "isolate" again in the meantime, but since we are just dumping the
+ * state for debugging, it should be fine to accept a bit of
+ * inaccuracy here due to racing.
+ */
+ bool page_cma = is_migrate_cma_page(page);
int mapcount;
+ char *type = "";
/*
* If struct page is poisoned don't access Page*() functions as that
@@ -78,9 +86,9 @@ void __dump_page(struct page *page, const char *reason)
page, page_ref_count(page), mapcount,
page->mapping, page_to_pgoff(page));
if (PageKsm(page))
- pr_warn("ksm flags: %#lx(%pGp)\n", page->flags, &page->flags);
+ type = "ksm ";
else if (PageAnon(page))
- pr_warn("anon flags: %#lx(%pGp)\n", page->flags, &page->flags);
+ type = "anon ";
else if (mapping) {
if (mapping->host && mapping->host->i_dentry.first) {
struct dentry *dentry;
@@ -88,10 +96,12 @@ void __dump_page(struct page *page, const char *reason)
pr_warn("%ps name:\"%pd\"\n", mapping->a_ops, dentry);
} else
pr_warn("%ps\n", mapping->a_ops);
- pr_warn("flags: %#lx(%pGp)\n", page->flags, &page->flags);
}
BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS + 1);
+ pr_warn("%sflags: %#lx(%pGp)%s\n", type, page->flags, &page->flags,
+ page_cma ? " CMA" : "");
+
hex_only:
print_hex_dump(KERN_WARNING, "raw: ", DUMP_PREFIX_NONE, 32,
sizeof(unsigned long), page,
diff --git a/mm/early_ioremap.c b/mm/early_ioremap.c
index 1826f191e72c..a0018ad1a1f6 100644
--- a/mm/early_ioremap.c
+++ b/mm/early_ioremap.c
@@ -121,8 +121,8 @@ __early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot)
}
}
- if (WARN(slot < 0, "%s(%08llx, %08lx) not found slot\n",
- __func__, (u64)phys_addr, size))
+ if (WARN(slot < 0, "%s(%pa, %08lx) not found slot\n",
+ __func__, &phys_addr, size))
return NULL;
/* Don't allow wraparound or zero size */
@@ -158,8 +158,8 @@ __early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot)
--idx;
--nrpages;
}
- WARN(early_ioremap_debug, "%s(%08llx, %08lx) [%d] => %08lx + %08lx\n",
- __func__, (u64)phys_addr, size, slot, offset, slot_virt[slot]);
+ WARN(early_ioremap_debug, "%s(%pa, %08lx) [%d] => %08lx + %08lx\n",
+ __func__, &phys_addr, size, slot, offset, slot_virt[slot]);
prev_map[slot] = (void __iomem *)(offset + slot_virt[slot]);
return prev_map[slot];
diff --git a/mm/filemap.c b/mm/filemap.c
index bf6aa30be58d..1784478270e1 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -632,33 +632,6 @@ static bool mapping_needs_writeback(struct address_space *mapping)
return mapping->nrpages;
}
-int filemap_write_and_wait(struct address_space *mapping)
-{
- int err = 0;
-
- if (mapping_needs_writeback(mapping)) {
- err = filemap_fdatawrite(mapping);
- /*
- * Even if the above returned error, the pages may be
- * written partially (e.g. -ENOSPC), so we wait for it.
- * But the -EIO is special case, it may indicate the worst
- * thing (e.g. bug) happened, so we avoid waiting for it.
- */
- if (err != -EIO) {
- int err2 = filemap_fdatawait(mapping);
- if (!err)
- err = err2;
- } else {
- /* Clear any previously stored errors */
- filemap_check_errors(mapping);
- }
- } else {
- err = filemap_check_errors(mapping);
- }
- return err;
-}
-EXPORT_SYMBOL(filemap_write_and_wait);
-
/**
* filemap_write_and_wait_range - write out & wait on a file range
* @mapping: the address_space for the pages
@@ -680,7 +653,12 @@ int filemap_write_and_wait_range(struct address_space *mapping,
if (mapping_needs_writeback(mapping)) {
err = __filemap_fdatawrite_range(mapping, lstart, lend,
WB_SYNC_ALL);
- /* See comment of filemap_write_and_wait() */
+ /*
+ * Even if the above returned error, the pages may be
+ * written partially (e.g. -ENOSPC), so we wait for it.
+ * But the -EIO is special case, it may indicate the worst
+ * thing (e.g. bug) happened, so we avoid waiting for it.
+ */
if (err != -EIO) {
int err2 = filemap_fdatawait_range(mapping,
lstart, lend);
diff --git a/mm/gup.c b/mm/gup.c
index 7646bf993b25..e13f4d211475 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -29,8 +29,23 @@ struct follow_page_context {
unsigned int page_mask;
};
+/*
+ * Return the compound head page with ref appropriately incremented,
+ * or NULL if that failed.
+ */
+static inline struct page *try_get_compound_head(struct page *page, int refs)
+{
+ struct page *head = compound_head(page);
+
+ if (WARN_ON_ONCE(page_ref_count(head) < 0))
+ return NULL;
+ if (unlikely(!page_cache_add_speculative(head, refs)))
+ return NULL;
+ return head;
+}
+
/**
- * put_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
+ * unpin_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
* @pages: array of pages to be maybe marked dirty, and definitely released.
* @npages: number of pages in the @pages array.
* @make_dirty: whether to mark the pages dirty
@@ -40,19 +55,19 @@ struct follow_page_context {
*
* For each page in the @pages array, make that page (or its head page, if a
* compound page) dirty, if @make_dirty is true, and if the page was previously
- * listed as clean. In any case, releases all pages using put_user_page(),
- * possibly via put_user_pages(), for the non-dirty case.
+ * listed as clean. In any case, releases all pages using unpin_user_page(),
+ * possibly via unpin_user_pages(), for the non-dirty case.
*
- * Please see the put_user_page() documentation for details.
+ * Please see the unpin_user_page() documentation for details.
*
* set_page_dirty_lock() is used internally. If instead, set_page_dirty() is
* required, then the caller should a) verify that this is really correct,
* because _lock() is usually required, and b) hand code it:
- * set_page_dirty_lock(), put_user_page().
+ * set_page_dirty_lock(), unpin_user_page().
*
*/
-void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
- bool make_dirty)
+void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
+ bool make_dirty)
{
unsigned long index;
@@ -63,7 +78,7 @@ void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
*/
if (!make_dirty) {
- put_user_pages(pages, npages);
+ unpin_user_pages(pages, npages);
return;
}
@@ -91,21 +106,21 @@ void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
*/
if (!PageDirty(page))
set_page_dirty_lock(page);
- put_user_page(page);
+ unpin_user_page(page);
}
}
-EXPORT_SYMBOL(put_user_pages_dirty_lock);
+EXPORT_SYMBOL(unpin_user_pages_dirty_lock);
/**
- * put_user_pages() - release an array of gup-pinned pages.
+ * unpin_user_pages() - release an array of gup-pinned pages.
* @pages: array of pages to be marked dirty and released.
* @npages: number of pages in the @pages array.
*
- * For each page in the @pages array, release the page using put_user_page().
+ * For each page in the @pages array, release the page using unpin_user_page().
*
- * Please see the put_user_page() documentation for details.
+ * Please see the unpin_user_page() documentation for details.
*/
-void put_user_pages(struct page **pages, unsigned long npages)
+void unpin_user_pages(struct page **pages, unsigned long npages)
{
unsigned long index;
@@ -115,9 +130,9 @@ void put_user_pages(struct page **pages, unsigned long npages)
* single operation to the head page should suffice.
*/
for (index = 0; index < npages; index++)
- put_user_page(pages[index]);
+ unpin_user_page(pages[index]);
}
-EXPORT_SYMBOL(put_user_pages);
+EXPORT_SYMBOL(unpin_user_pages);
#ifdef CONFIG_MMU
static struct page *no_page_table(struct vm_area_struct *vma,
@@ -179,6 +194,10 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
spinlock_t *ptl;
pte_t *ptep, pte;
+ /* FOLL_GET and FOLL_PIN are mutually exclusive. */
+ if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) ==
+ (FOLL_PIN | FOLL_GET)))
+ return ERR_PTR(-EINVAL);
retry:
if (unlikely(pmd_bad(*pmd)))
return no_page_table(vma, flags);
@@ -323,7 +342,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
pmdval = READ_ONCE(*pmd);
if (pmd_none(pmdval))
return no_page_table(vma, flags);
- if (pmd_huge(pmdval) && vma->vm_flags & VM_HUGETLB) {
+ if (pmd_huge(pmdval) && is_vm_hugetlb_page(vma)) {
page = follow_huge_pmd(mm, address, pmd, flags);
if (page)
return page;
@@ -433,7 +452,7 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma,
pud = pud_offset(p4dp, address);
if (pud_none(*pud))
return no_page_table(vma, flags);
- if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
+ if (pud_huge(*pud) && is_vm_hugetlb_page(vma)) {
page = follow_huge_pud(mm, address, pud, flags);
if (page)
return page;
@@ -796,7 +815,7 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
start = untagged_addr(start);
- VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));
+ VM_BUG_ON(!!pages != !!(gup_flags & (FOLL_GET | FOLL_PIN)));
/*
* If FOLL_FORCE is set then do not force a full fault as the hinting
@@ -1020,7 +1039,16 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
BUG_ON(*locked != 1);
}
- if (pages)
+ /*
+ * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior
+ * is to set FOLL_GET if the caller wants pages[] filled in (but has
+ * carelessly failed to specify FOLL_GET), so keep doing that, but only
+ * for FOLL_GET, not for the newer FOLL_PIN.
+ *
+ * FOLL_PIN always expects pages to be non-null, but no need to assert
+ * that here, as any failures will be obvious enough.
+ */
+ if (pages && !(flags & FOLL_PIN))
flags |= FOLL_GET;
pages_done = 0;
@@ -1096,88 +1124,6 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
return pages_done;
}
-/*
- * get_user_pages_remote() - pin user pages in memory
- * @tsk: the task_struct to use for page fault accounting, or
- * NULL if faults are not to be recorded.
- * @mm: mm_struct of target mm
- * @start: starting user address
- * @nr_pages: number of pages from start to pin
- * @gup_flags: flags modifying lookup behaviour
- * @pages: array that receives pointers to the pages pinned.
- * Should be at least nr_pages long. Or NULL, if caller
- * only intends to ensure the pages are faulted in.
- * @vmas: array of pointers to vmas corresponding to each page.
- * Or NULL if the caller does not require them.
- * @locked: pointer to lock flag indicating whether lock is held and
- * subsequently whether VM_FAULT_RETRY functionality can be
- * utilised. Lock must initially be held.
- *
- * Returns either number of pages pinned (which may be less than the
- * number requested), or an error. Details about the return value:
- *
- * -- If nr_pages is 0, returns 0.
- * -- If nr_pages is >0, but no pages were pinned, returns -errno.
- * -- If nr_pages is >0, and some pages were pinned, returns the number of
- * pages pinned. Again, this may be less than nr_pages.
- *
- * The caller is responsible for releasing returned @pages, via put_page().
- *
- * @vmas are valid only as long as mmap_sem is held.
- *
- * Must be called with mmap_sem held for read or write.
- *
- * get_user_pages walks a process's page tables and takes a reference to
- * each struct page that each user address corresponds to at a given
- * instant. That is, it takes the page that would be accessed if a user
- * thread accesses the given user virtual address at that instant.
- *
- * This does not guarantee that the page exists in the user mappings when
- * get_user_pages returns, and there may even be a completely different
- * page there in some cases (eg. if mmapped pagecache has been invalidated
- * and subsequently re faulted). However it does guarantee that the page
- * won't be freed completely. And mostly callers simply care that the page
- * contains data that was valid *at some point in time*. Typically, an IO
- * or similar operation cannot guarantee anything stronger anyway because
- * locks can't be held over the syscall boundary.
- *
- * If gup_flags & FOLL_WRITE == 0, the page must not be written to. If the page
- * is written to, set_page_dirty (or set_page_dirty_lock, as appropriate) must
- * be called after the page is finished with, and before put_page is called.
- *
- * get_user_pages is typically used for fewer-copy IO operations, to get a
- * handle on the memory by some means other than accesses via the user virtual
- * addresses. The pages may be submitted for DMA to devices or accessed via
- * their kernel linear mapping (via the kmap APIs). Care should be taken to
- * use the correct cache flushing APIs.
- *
- * See also get_user_pages_fast, for performance critical applications.
- *
- * get_user_pages should be phased out in favor of
- * get_user_pages_locked|unlocked or get_user_pages_fast. Nothing
- * should use get_user_pages because it cannot pass
- * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault.
- */
-long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
- unsigned long start, unsigned long nr_pages,
- unsigned int gup_flags, struct page **pages,
- struct vm_area_struct **vmas, int *locked)
-{
- /*
- * FIXME: Current FOLL_LONGTERM behavior is incompatible with
- * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
- * vmas. As there are no users of this flag in this call we simply
- * disallow this option for now.
- */
- if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
- return -EINVAL;
-
- return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
- locked,
- gup_flags | FOLL_TOUCH | FOLL_REMOTE);
-}
-EXPORT_SYMBOL(get_user_pages_remote);
-
/**
* populate_vma_page_range() - populate a range of pages in the vma.
* @vma: target vma
@@ -1612,6 +1558,116 @@ static __always_inline long __gup_longterm_locked(struct task_struct *tsk,
#endif /* CONFIG_FS_DAX || CONFIG_CMA */
/*
+ * get_user_pages_remote() - pin user pages in memory
+ * @tsk: the task_struct to use for page fault accounting, or
+ * NULL if faults are not to be recorded.
+ * @mm: mm_struct of target mm
+ * @start: starting user address
+ * @nr_pages: number of pages from start to pin
+ * @gup_flags: flags modifying lookup behaviour
+ * @pages: array that receives pointers to the pages pinned.
+ * Should be at least nr_pages long. Or NULL, if caller
+ * only intends to ensure the pages are faulted in.
+ * @vmas: array of pointers to vmas corresponding to each page.
+ * Or NULL if the caller does not require them.
+ * @locked: pointer to lock flag indicating whether lock is held and
+ * subsequently whether VM_FAULT_RETRY functionality can be
+ * utilised. Lock must initially be held.
+ *
+ * Returns either number of pages pinned (which may be less than the
+ * number requested), or an error. Details about the return value:
+ *
+ * -- If nr_pages is 0, returns 0.
+ * -- If nr_pages is >0, but no pages were pinned, returns -errno.
+ * -- If nr_pages is >0, and some pages were pinned, returns the number of
+ * pages pinned. Again, this may be less than nr_pages.
+ *
+ * The caller is responsible for releasing returned @pages, via put_page().
+ *
+ * @vmas are valid only as long as mmap_sem is held.
+ *
+ * Must be called with mmap_sem held for read or write.
+ *
+ * get_user_pages walks a process's page tables and takes a reference to
+ * each struct page that each user address corresponds to at a given
+ * instant. That is, it takes the page that would be accessed if a user
+ * thread accesses the given user virtual address at that instant.
+ *
+ * This does not guarantee that the page exists in the user mappings when
+ * get_user_pages returns, and there may even be a completely different
+ * page there in some cases (eg. if mmapped pagecache has been invalidated
+ * and subsequently re faulted). However it does guarantee that the page
+ * won't be freed completely. And mostly callers simply care that the page
+ * contains data that was valid *at some point in time*. Typically, an IO
+ * or similar operation cannot guarantee anything stronger anyway because
+ * locks can't be held over the syscall boundary.
+ *
+ * If gup_flags & FOLL_WRITE == 0, the page must not be written to. If the page
+ * is written to, set_page_dirty (or set_page_dirty_lock, as appropriate) must
+ * be called after the page is finished with, and before put_page is called.
+ *
+ * get_user_pages is typically used for fewer-copy IO operations, to get a
+ * handle on the memory by some means other than accesses via the user virtual
+ * addresses. The pages may be submitted for DMA to devices or accessed via
+ * their kernel linear mapping (via the kmap APIs). Care should be taken to
+ * use the correct cache flushing APIs.
+ *
+ * See also get_user_pages_fast, for performance critical applications.
+ *
+ * get_user_pages should be phased out in favor of
+ * get_user_pages_locked|unlocked or get_user_pages_fast. Nothing
+ * should use get_user_pages because it cannot pass
+ * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault.
+ */
+#ifdef CONFIG_MMU
+long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages,
+ struct vm_area_struct **vmas, int *locked)
+{
+ /*
+ * FOLL_PIN must only be set internally by the pin_user_pages*() APIs,
+ * never directly by the caller, so enforce that with an assertion:
+ */
+ if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
+ return -EINVAL;
+
+ /*
+ * Parts of FOLL_LONGTERM behavior are incompatible with
+ * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
+ * vmas. However, this only comes up if locked is set, and there are
+ * callers that do request FOLL_LONGTERM, but do not set locked. So,
+ * allow what we can.
+ */
+ if (gup_flags & FOLL_LONGTERM) {
+ if (WARN_ON_ONCE(locked))
+ return -EINVAL;
+ /*
+ * This will check the vmas (even if our vmas arg is NULL)
+ * and return -ENOTSUPP if DAX isn't allowed in this case:
+ */
+ return __gup_longterm_locked(tsk, mm, start, nr_pages, pages,
+ vmas, gup_flags | FOLL_TOUCH |
+ FOLL_REMOTE);
+ }
+
+ return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
+ locked,
+ gup_flags | FOLL_TOUCH | FOLL_REMOTE);
+}
+EXPORT_SYMBOL(get_user_pages_remote);
+
+#else /* CONFIG_MMU */
+long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages,
+ struct vm_area_struct **vmas, int *locked)
+{
+ return 0;
+}
+#endif /* !CONFIG_MMU */
+
+/*
* This is the same as get_user_pages_remote(), just with a
* less-flexible calling convention where we assume that the task
* and mm being operated on are the current task's and don't allow
@@ -1622,6 +1678,13 @@ long get_user_pages(unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages,
struct vm_area_struct **vmas)
{
+ /*
+ * FOLL_PIN must only be set internally by the pin_user_pages*() APIs,
+ * never directly by the caller, so enforce that with an assertion:
+ */
+ if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
+ return -EINVAL;
+
return __gup_longterm_locked(current, current->mm, start, nr_pages,
pages, vmas, gup_flags | FOLL_TOUCH);
}
@@ -1807,20 +1870,6 @@ static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start,
}
}
-/*
- * Return the compund head page with ref appropriately incremented,
- * or NULL if that failed.
- */
-static inline struct page *try_get_compound_head(struct page *page, int refs)
-{
- struct page *head = compound_head(page);
- if (WARN_ON_ONCE(page_ref_count(head) < 0))
- return NULL;
- if (unlikely(!page_cache_add_speculative(head, refs)))
- return NULL;
- return head;
-}
-
#ifdef CONFIG_ARCH_HAS_PTE_SPECIAL
static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
unsigned int flags, struct page **pages, int *nr)
@@ -1978,6 +2027,29 @@ static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr,
}
#endif
+static int record_subpages(struct page *page, unsigned long addr,
+ unsigned long end, struct page **pages)
+{
+ int nr;
+
+ for (nr = 0; addr != end; addr += PAGE_SIZE)
+ pages[nr++] = page++;
+
+ return nr;
+}
+
+static void put_compound_head(struct page *page, int refs)
+{
+ VM_BUG_ON_PAGE(page_ref_count(page) < refs, page);
+ /*
+ * Calling put_page() for each ref is unnecessarily slow. Only the last
+ * ref needs a put_page().
+ */
+ if (refs > 1)
+ page_ref_sub(page, refs - 1);
+ put_page(page);
+}
+
#ifdef CONFIG_ARCH_HAS_HUGEPD
static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
unsigned long sz)
@@ -2007,32 +2079,20 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
/* hugepages are never "special" */
VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
- refs = 0;
head = pte_page(pte);
-
page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
- do {
- VM_BUG_ON(compound_head(page) != head);
- pages[*nr] = page;
- (*nr)++;
- page++;
- refs++;
- } while (addr += PAGE_SIZE, addr != end);
+ refs = record_subpages(page, addr, end, pages + *nr);
head = try_get_compound_head(head, refs);
- if (!head) {
- *nr -= refs;
+ if (!head)
return 0;
- }
if (unlikely(pte_val(pte) != pte_val(*ptep))) {
- /* Could be optimized better */
- *nr -= refs;
- while (refs--)
- put_page(head);
+ put_compound_head(head, refs);
return 0;
}
+ *nr += refs;
SetPageReferenced(head);
return 1;
}
@@ -2079,28 +2139,19 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
return __gup_device_huge_pmd(orig, pmdp, addr, end, pages, nr);
}
- refs = 0;
page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
- do {
- pages[*nr] = page;
- (*nr)++;
- page++;
- refs++;
- } while (addr += PAGE_SIZE, addr != end);
+ refs = record_subpages(page, addr, end, pages + *nr);
head = try_get_compound_head(pmd_page(orig), refs);
- if (!head) {
- *nr -= refs;
+ if (!head)
return 0;
- }
if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
- *nr -= refs;
- while (refs--)
- put_page(head);
+ put_compound_head(head, refs);
return 0;
}
+ *nr += refs;
SetPageReferenced(head);
return 1;
}
@@ -2120,28 +2171,19 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
return __gup_device_huge_pud(orig, pudp, addr, end, pages, nr);
}
- refs = 0;
page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
- do {
- pages[*nr] = page;
- (*nr)++;
- page++;
- refs++;
- } while (addr += PAGE_SIZE, addr != end);
+ refs = record_subpages(page, addr, end, pages + *nr);
head = try_get_compound_head(pud_page(orig), refs);
- if (!head) {
- *nr -= refs;
+ if (!head)
return 0;
- }
if (unlikely(pud_val(orig) != pud_val(*pudp))) {
- *nr -= refs;
- while (refs--)
- put_page(head);
+ put_compound_head(head, refs);
return 0;
}
+ *nr += refs;
SetPageReferenced(head);
return 1;
}
@@ -2157,28 +2199,20 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
return 0;
BUILD_BUG_ON(pgd_devmap(orig));
- refs = 0;
+
page = pgd_page(orig) + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
- do {
- pages[*nr] = page;
- (*nr)++;
- page++;
- refs++;
- } while (addr += PAGE_SIZE, addr != end);
+ refs = record_subpages(page, addr, end, pages + *nr);
head = try_get_compound_head(pgd_page(orig), refs);
- if (!head) {
- *nr -= refs;
+ if (!head)
return 0;
- }
if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) {
- *nr -= refs;
- while (refs--)
- put_page(head);
+ put_compound_head(head, refs);
return 0;
}
+ *nr += refs;
SetPageReferenced(head);
return 1;
}
@@ -2237,7 +2271,7 @@ static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end,
pud_t pud = READ_ONCE(*pudp);
next = pud_addr_end(addr, end);
- if (pud_none(pud))
+ if (unlikely(!pud_present(pud)))
return 0;
if (unlikely(pud_huge(pud))) {
if (!gup_huge_pud(pud, pudp, addr, next, flags,
@@ -2393,29 +2427,15 @@ static int __gup_longterm_unlocked(unsigned long start, int nr_pages,
return ret;
}
-/**
- * get_user_pages_fast() - pin user pages in memory
- * @start: starting user address
- * @nr_pages: number of pages from start to pin
- * @gup_flags: flags modifying pin behaviour
- * @pages: array that receives pointers to the pages pinned.
- * Should be at least nr_pages long.
- *
- * Attempt to pin user pages in memory without taking mm->mmap_sem.
- * If not successful, it will fall back to taking the lock and
- * calling get_user_pages().
- *
- * Returns number of pages pinned. This may be fewer than the number
- * requested. If nr_pages is 0 or negative, returns 0. If no pages
- * were pinned, returns -errno.
- */
-int get_user_pages_fast(unsigned long start, int nr_pages,
- unsigned int gup_flags, struct page **pages)
+static int internal_get_user_pages_fast(unsigned long start, int nr_pages,
+ unsigned int gup_flags,
+ struct page **pages)
{
unsigned long addr, len, end;
int nr = 0, ret = 0;
- if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM)))
+ if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM |
+ FOLL_FORCE | FOLL_PIN)))
return -EINVAL;
start = untagged_addr(start) & PAGE_MASK;
@@ -2455,4 +2475,103 @@ int get_user_pages_fast(unsigned long start, int nr_pages,
return ret;
}
+
+/**
+ * get_user_pages_fast() - pin user pages in memory
+ * @start: starting user address
+ * @nr_pages: number of pages from start to pin
+ * @gup_flags: flags modifying pin behaviour
+ * @pages: array that receives pointers to the pages pinned.
+ * Should be at least nr_pages long.
+ *
+ * Attempt to pin user pages in memory without taking mm->mmap_sem.
+ * If not successful, it will fall back to taking the lock and
+ * calling get_user_pages().
+ *
+ * Returns number of pages pinned. This may be fewer than the number requested.
+ * If nr_pages is 0 or negative, returns 0. If no pages were pinned, returns
+ * -errno.
+ */
+int get_user_pages_fast(unsigned long start, int nr_pages,
+ unsigned int gup_flags, struct page **pages)
+{
+ /*
+ * FOLL_PIN must only be set internally by the pin_user_pages*() APIs,
+ * never directly by the caller, so enforce that:
+ */
+ if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
+ return -EINVAL;
+
+ return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages);
+}
EXPORT_SYMBOL_GPL(get_user_pages_fast);
+
+/**
+ * pin_user_pages_fast() - pin user pages in memory without taking locks
+ *
+ * For now, this is a placeholder function, until various call sites are
+ * converted to use the correct get_user_pages*() or pin_user_pages*() API. So,
+ * this is identical to get_user_pages_fast().
+ *
+ * This is intended for Case 1 (DIO) in Documentation/vm/pin_user_pages.rst. It
+ * is NOT intended for Case 2 (RDMA: long-term pins).
+ */
+int pin_user_pages_fast(unsigned long start, int nr_pages,
+ unsigned int gup_flags, struct page **pages)
+{
+ /*
+ * This is a placeholder, until the pin functionality is activated.
+ * Until then, just behave like the corresponding get_user_pages*()
+ * routine.
+ */
+ return get_user_pages_fast(start, nr_pages, gup_flags, pages);
+}
+EXPORT_SYMBOL_GPL(pin_user_pages_fast);
+
+/**
+ * pin_user_pages_remote() - pin pages of a remote process (task != current)
+ *
+ * For now, this is a placeholder function, until various call sites are
+ * converted to use the correct get_user_pages*() or pin_user_pages*() API. So,
+ * this is identical to get_user_pages_remote().
+ *
+ * This is intended for Case 1 (DIO) in Documentation/vm/pin_user_pages.rst. It
+ * is NOT intended for Case 2 (RDMA: long-term pins).
+ */
+long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages,
+ struct vm_area_struct **vmas, int *locked)
+{
+ /*
+ * This is a placeholder, until the pin functionality is activated.
+ * Until then, just behave like the corresponding get_user_pages*()
+ * routine.
+ */
+ return get_user_pages_remote(tsk, mm, start, nr_pages, gup_flags, pages,
+ vmas, locked);
+}
+EXPORT_SYMBOL(pin_user_pages_remote);
+
+/**
+ * pin_user_pages() - pin user pages in memory for use by other devices
+ *
+ * For now, this is a placeholder function, until various call sites are
+ * converted to use the correct get_user_pages*() or pin_user_pages*() API. So,
+ * this is identical to get_user_pages().
+ *
+ * This is intended for Case 1 (DIO) in Documentation/vm/pin_user_pages.rst. It
+ * is NOT intended for Case 2 (RDMA: long-term pins).
+ */
+long pin_user_pages(unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages,
+ struct vm_area_struct **vmas)
+{
+ /*
+ * This is a placeholder, until the pin functionality is activated.
+ * Until then, just behave like the corresponding get_user_pages*()
+ * routine.
+ */
+ return get_user_pages(start, nr_pages, gup_flags, pages, vmas);
+}
+EXPORT_SYMBOL(pin_user_pages);
diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c
index ad9d5b1c4473..8dba38e79a9f 100644
--- a/mm/gup_benchmark.c
+++ b/mm/gup_benchmark.c
@@ -49,18 +49,21 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
nr = (next - addr) / PAGE_SIZE;
}
+ /* Filter out most gup flags: only allow a tiny subset here: */
+ gup->flags &= FOLL_WRITE;
+
switch (cmd) {
case GUP_FAST_BENCHMARK:
- nr = get_user_pages_fast(addr, nr, gup->flags & 1,
+ nr = get_user_pages_fast(addr, nr, gup->flags,
pages + i);
break;
case GUP_LONGTERM_BENCHMARK:
nr = get_user_pages(addr, nr,
- (gup->flags & 1) | FOLL_LONGTERM,
+ gup->flags | FOLL_LONGTERM,
pages + i, NULL);
break;
case GUP_BENCHMARK:
- nr = get_user_pages(addr, nr, gup->flags & 1, pages + i,
+ nr = get_user_pages(addr, nr, gup->flags, pages + i,
NULL);
break;
default:
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f39689a29128..b08b199f9a11 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -177,16 +177,13 @@ static ssize_t enabled_store(struct kobject *kobj,
{
ssize_t ret = count;
- if (!memcmp("always", buf,
- min(sizeof("always")-1, count))) {
+ if (sysfs_streq(buf, "always")) {
clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
- } else if (!memcmp("madvise", buf,
- min(sizeof("madvise")-1, count))) {
+ } else if (sysfs_streq(buf, "madvise")) {
clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
- } else if (!memcmp("never", buf,
- min(sizeof("never")-1, count))) {
+ } else if (sysfs_streq(buf, "never")) {
clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
} else
@@ -250,32 +247,27 @@ static ssize_t defrag_store(struct kobject *kobj,
struct kobj_attribute *attr,
const char *buf, size_t count)
{
- if (!memcmp("always", buf,
- min(sizeof("always")-1, count))) {
+ if (sysfs_streq(buf, "always")) {
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
- } else if (!memcmp("defer+madvise", buf,
- min(sizeof("defer+madvise")-1, count))) {
+ } else if (sysfs_streq(buf, "defer+madvise")) {
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
- } else if (!memcmp("defer", buf,
- min(sizeof("defer")-1, count))) {
+ } else if (sysfs_streq(buf, "defer")) {
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
- } else if (!memcmp("madvise", buf,
- min(sizeof("madvise")-1, count))) {
+ } else if (sysfs_streq(buf, "madvise")) {
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
- } else if (!memcmp("never", buf,
- min(sizeof("never")-1, count))) {
+ } else if (sysfs_streq(buf, "never")) {
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
@@ -2715,7 +2707,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
{
struct page *head = compound_head(page);
struct pglist_data *pgdata = NODE_DATA(page_to_nid(head));
- struct deferred_split *ds_queue = get_deferred_split_queue(page);
+ struct deferred_split *ds_queue = get_deferred_split_queue(head);
struct anon_vma *anon_vma = NULL;
struct address_space *mapping = NULL;
int count, mapcount, extra_pins, ret;
@@ -2723,11 +2715,11 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
unsigned long flags;
pgoff_t end;
- VM_BUG_ON_PAGE(is_huge_zero_page(page), page);
- VM_BUG_ON_PAGE(!PageLocked(page), page);
- VM_BUG_ON_PAGE(!PageCompound(page), page);
+ VM_BUG_ON_PAGE(is_huge_zero_page(head), head);
+ VM_BUG_ON_PAGE(!PageLocked(head), head);
+ VM_BUG_ON_PAGE(!PageCompound(head), head);
- if (PageWriteback(page))
+ if (PageWriteback(head))
return -EBUSY;
if (PageAnon(head)) {
@@ -2778,7 +2770,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
goto out_unlock;
}
- mlocked = PageMlocked(page);
+ mlocked = PageMlocked(head);
unmap_page(head);
VM_BUG_ON_PAGE(compound_mapcount(head), head);
@@ -2810,14 +2802,14 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
ds_queue->split_queue_len--;
list_del(page_deferred_list(head));
}
+ spin_unlock(&ds_queue->split_queue_lock);
if (mapping) {
- if (PageSwapBacked(page))
- __dec_node_page_state(page, NR_SHMEM_THPS);
+ if (PageSwapBacked(head))
+ __dec_node_page_state(head, NR_SHMEM_THPS);
else
- __dec_node_page_state(page, NR_FILE_THPS);
+ __dec_node_page_state(head, NR_FILE_THPS);
}
- spin_unlock(&ds_queue->split_queue_lock);
__split_huge_page(page, list, end, flags);
if (PageSwapCache(head)) {
swp_entry_t entry = { .val = page_private(head) };
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 244607663363..3a4259eeb5a0 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -13,7 +13,7 @@
*
* The following locks and mutexes are used by kmemleak:
*
- * - kmemleak_lock (rwlock): protects the object_list modifications and
+ * - kmemleak_lock (raw_spinlock_t): protects the object_list modifications and
* accesses to the object_tree_root. The object_list is the main list
* holding the metadata (struct kmemleak_object) for the allocated memory
* blocks. The object_tree_root is a red black tree used to look-up
@@ -22,13 +22,13 @@
* object_tree_root in the create_object() function called from the
* kmemleak_alloc() callback and removed in delete_object() called from the
* kmemleak_free() callback
- * - kmemleak_object.lock (spinlock): protects a kmemleak_object. Accesses to
- * the metadata (e.g. count) are protected by this lock. Note that some
- * members of this structure may be protected by other means (atomic or
- * kmemleak_lock). This lock is also held when scanning the corresponding
- * memory block to avoid the kernel freeing it via the kmemleak_free()
- * callback. This is less heavyweight than holding a global lock like
- * kmemleak_lock during scanning
+ * - kmemleak_object.lock (raw_spinlock_t): protects a kmemleak_object.
+ * Accesses to the metadata (e.g. count) are protected by this lock. Note
+ * that some members of this structure may be protected by other means
+ * (atomic or kmemleak_lock). This lock is also held when scanning the
+ * corresponding memory block to avoid the kernel freeing it via the
+ * kmemleak_free() callback. This is less heavyweight than holding a global
+ * lock like kmemleak_lock during scanning.
* - scan_mutex (mutex): ensures that only one thread may scan the memory for
* unreferenced objects at a time. The gray_list contains the objects which
* are already referenced or marked as false positives and need to be
@@ -135,7 +135,7 @@ struct kmemleak_scan_area {
* (use_count) and freed using the RCU mechanism.
*/
struct kmemleak_object {
- spinlock_t lock;
+ raw_spinlock_t lock;
unsigned int flags; /* object status flags */
struct list_head object_list;
struct list_head gray_list;
@@ -191,8 +191,8 @@ static int mem_pool_free_count = ARRAY_SIZE(mem_pool);
static LIST_HEAD(mem_pool_free_list);
/* search tree for object boundaries */
static struct rb_root object_tree_root = RB_ROOT;
-/* rw_lock protecting the access to object_list and object_tree_root */
-static DEFINE_RWLOCK(kmemleak_lock);
+/* protecting the access to object_list and object_tree_root */
+static DEFINE_RAW_SPINLOCK(kmemleak_lock);
/* allocation caches for kmemleak internal data */
static struct kmem_cache *object_cache;
@@ -426,7 +426,7 @@ static struct kmemleak_object *mem_pool_alloc(gfp_t gfp)
}
/* slab allocation failed, try the memory pool */
- write_lock_irqsave(&kmemleak_lock, flags);
+ raw_spin_lock_irqsave(&kmemleak_lock, flags);
object = list_first_entry_or_null(&mem_pool_free_list,
typeof(*object), object_list);
if (object)
@@ -435,7 +435,7 @@ static struct kmemleak_object *mem_pool_alloc(gfp_t gfp)
object = &mem_pool[--mem_pool_free_count];
else
pr_warn_once("Memory pool empty, consider increasing CONFIG_DEBUG_KMEMLEAK_MEM_POOL_SIZE\n");
- write_unlock_irqrestore(&kmemleak_lock, flags);
+ raw_spin_unlock_irqrestore(&kmemleak_lock, flags);
return object;
}
@@ -453,9 +453,9 @@ static void mem_pool_free(struct kmemleak_object *object)
}
/* add the object to the memory pool free list */
- write_lock_irqsave(&kmemleak_lock, flags);
+ raw_spin_lock_irqsave(&kmemleak_lock, flags);
list_add(&object->object_list, &mem_pool_free_list);
- write_unlock_irqrestore(&kmemleak_lock, flags);
+ raw_spin_unlock_irqrestore(&kmemleak_lock, flags);
}
/*
@@ -514,9 +514,9 @@ static struct kmemleak_object *find_and_get_object(unsigned long ptr, int alias)
struct kmemleak_object *object;
rcu_read_lock();
- read_lock_irqsave(&kmemleak_lock, flags);
+ raw_spin_lock_irqsave(&kmemleak_lock, flags);
object = lookup_object(ptr, alias);
- read_unlock_irqrestore(&kmemleak_lock, flags);
+ raw_spin_unlock_irqrestore(&kmemleak_lock, flags);
/* check whether the object is still available */
if (object && !get_object(object))
@@ -546,11 +546,11 @@ static struct kmemleak_object *find_and_remove_object(unsigned long ptr, int ali
unsigned long flags;
struct kmemleak_object *object;
- write_lock_irqsave(&kmemleak_lock, flags);
+ raw_spin_lock_irqsave(&kmemleak_lock, flags);
object = lookup_object(ptr, alias);
if (object)
__remove_object(object);
- write_unlock_irqrestore(&kmemleak_lock, flags);
+ raw_spin_unlock_irqrestore(&kmemleak_lock, flags);
return object;
}
@@ -585,7 +585,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size,
INIT_LIST_HEAD(&object->object_list);
INIT_LIST_HEAD(&object->gray_list);
INIT_HLIST_HEAD(&object->area_list);
- spin_lock_init(&object->lock);
+ raw_spin_lock_init(&object->lock);
atomic_set(&object->use_count, 1);
object->flags = OBJECT_ALLOCATED;
object->pointer = ptr;
@@ -617,7 +617,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size,
/* kernel backtrace */
object->trace_len = __save_stack_trace(object->trace);
- write_lock_irqsave(&kmemleak_lock, flags);
+ raw_spin_lock_irqsave(&kmemleak_lock, flags);
untagged_ptr = (unsigned long)kasan_reset_tag((void *)ptr);
min_addr = min(min_addr, untagged_ptr);
@@ -649,7 +649,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size,
list_add_tail_rcu(&object->object_list, &object_list);
out:
- write_unlock_irqrestore(&kmemleak_lock, flags);
+ raw_spin_unlock_irqrestore(&kmemleak_lock, flags);
return object;
}
@@ -667,9 +667,9 @@ static void __delete_object(struct kmemleak_object *object)
* Locking here also ensures that the corresponding memory block
* cannot be freed when it is being scanned.
*/
- spin_lock_irqsave(&object->lock, flags);
+ raw_spin_lock_irqsave(&object->lock, flags);
object->flags &= ~OBJECT_ALLOCATED;
- spin_unlock_irqrestore(&object->lock, flags);
+ raw_spin_unlock_irqrestore(&object->lock, flags);
put_object(object);
}
@@ -739,9 +739,9 @@ static void paint_it(struct kmemleak_object *object, int color)
{
unsigned long flags;
- spin_lock_irqsave(&object->lock, flags);
+ raw_spin_lock_irqsave(&object->lock, flags);
__paint_it(object, color);
- spin_unlock_irqrestore(&object->lock, flags);
+ raw_spin_unlock_irqrestore(&object->lock, flags);
}
static void paint_ptr(unsigned long ptr, int color)
@@ -798,7 +798,7 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp)
if (scan_area_cache)
area = kmem_cache_alloc(scan_area_cache, gfp_kmemleak_mask(gfp));
- spin_lock_irqsave(&object->lock, flags);
+ raw_spin_lock_irqsave(&object->lock, flags);
if (!area) {
pr_warn_once("Cannot allocate a scan area, scanning the full object\n");
/* mark the object for full scan to avoid false positives */
@@ -820,7 +820,7 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp)
hlist_add_head(&area->node, &object->area_list);
out_unlock:
- spin_unlock_irqrestore(&object->lock, flags);
+ raw_spin_unlock_irqrestore(&object->lock, flags);
put_object(object);
}
@@ -842,9 +842,9 @@ static void object_set_excess_ref(unsigned long ptr, unsigned long excess_ref)
return;
}
- spin_lock_irqsave(&object->lock, flags);
+ raw_spin_lock_irqsave(&object->lock, flags);
object->excess_ref = excess_ref;
- spin_unlock_irqrestore(&object->lock, flags);
+ raw_spin_unlock_irqrestore(&object->lock, flags);
put_object(object);
}
@@ -864,9 +864,9 @@ static void object_no_scan(unsigned long ptr)
return;
}
- spin_lock_irqsave(&object->lock, flags);
+ raw_spin_lock_irqsave(&object->lock, flags);
object->flags |= OBJECT_NO_SCAN;
- spin_unlock_irqrestore(&object->lock, flags);
+ raw_spin_unlock_irqrestore(&object->lock, flags);
put_object(object);
}
@@ -1026,9 +1026,9 @@ void __ref kmemleak_update_trace(const void *ptr)
return;
}
- spin_lock_irqsave(&object->lock, flags);
+ raw_spin_lock_irqsave(&object->lock, flags);
object->trace_len = __save_stack_trace(object->trace);
- spin_unlock_irqrestore(&object->lock, flags);
+ raw_spin_unlock_irqrestore(&object->lock, flags);
put_object(object);
}
@@ -1233,7 +1233,7 @@ static void scan_block(void *_start, void *_end,
unsigned long flags;
unsigned long untagged_ptr;
- read_lock_irqsave(&kmemleak_lock, flags);
+ raw_spin_lock_irqsave(&kmemleak_lock, flags);
for (ptr = start; ptr < end; ptr++) {
struct kmemleak_object *object;
unsigned long pointer;
@@ -1268,7 +1268,7 @@ static void scan_block(void *_start, void *_end,
* previously acquired in scan_object(). These locks are
* enclosed by scan_mutex.
*/
- spin_lock_nested(&object->lock, SINGLE_DEPTH_NESTING);
+ raw_spin_lock_nested(&object->lock, SINGLE_DEPTH_NESTING);
/* only pass surplus references (object already gray) */
if (color_gray(object)) {
excess_ref = object->excess_ref;
@@ -1277,7 +1277,7 @@ static void scan_block(void *_start, void *_end,
excess_ref = 0;
update_refs(object);
}
- spin_unlock(&object->lock);
+ raw_spin_unlock(&object->lock);
if (excess_ref) {
object = lookup_object(excess_ref, 0);
@@ -1286,12 +1286,12 @@ static void scan_block(void *_start, void *_end,
if (object == scanned)
/* circular reference, ignore */
continue;
- spin_lock_nested(&object->lock, SINGLE_DEPTH_NESTING);
+ raw_spin_lock_nested(&object->lock, SINGLE_DEPTH_NESTING);
update_refs(object);
- spin_unlock(&object->lock);
+ raw_spin_unlock(&object->lock);
}
}
- read_unlock_irqrestore(&kmemleak_lock, flags);
+ raw_spin_unlock_irqrestore(&kmemleak_lock, flags);
}
/*
@@ -1324,7 +1324,7 @@ static void scan_object(struct kmemleak_object *object)
* Once the object->lock is acquired, the corresponding memory block
* cannot be freed (the same lock is acquired in delete_object).
*/
- spin_lock_irqsave(&object->lock, flags);
+ raw_spin_lock_irqsave(&object->lock, flags);
if (object->flags & OBJECT_NO_SCAN)
goto out;
if (!(object->flags & OBJECT_ALLOCATED))
@@ -1344,9 +1344,9 @@ static void scan_object(struct kmemleak_object *object)
if (start >= end)
break;
- spin_unlock_irqrestore(&object->lock, flags);
+ raw_spin_unlock_irqrestore(&object->lock, flags);
cond_resched();
- spin_lock_irqsave(&object->lock, flags);
+ raw_spin_lock_irqsave(&object->lock, flags);
} while (object->flags & OBJECT_ALLOCATED);
} else
hlist_for_each_entry(area, &object->area_list, node)
@@ -1354,7 +1354,7 @@ static void scan_object(struct kmemleak_object *object)
(void *)(area->start + area->size),
object);
out:
- spin_unlock_irqrestore(&object->lock, flags);
+ raw_spin_unlock_irqrestore(&object->lock, flags);
}
/*
@@ -1407,7 +1407,7 @@ static void kmemleak_scan(void)
/* prepare the kmemleak_object's */
rcu_read_lock();
list_for_each_entry_rcu(object, &object_list, object_list) {
- spin_lock_irqsave(&object->lock, flags);
+ raw_spin_lock_irqsave(&object->lock, flags);
#ifdef DEBUG
/*
* With a few exceptions there should be a maximum of
@@ -1424,7 +1424,7 @@ static void kmemleak_scan(void)
if (color_gray(object) && get_object(object))
list_add_tail(&object->gray_list, &gray_list);
- spin_unlock_irqrestore(&object->lock, flags);
+ raw_spin_unlock_irqrestore(&object->lock, flags);
}
rcu_read_unlock();
@@ -1492,14 +1492,14 @@ static void kmemleak_scan(void)
*/
rcu_read_lock();
list_for_each_entry_rcu(object, &object_list, object_list) {
- spin_lock_irqsave(&object->lock, flags);
+ raw_spin_lock_irqsave(&object->lock, flags);
if (color_white(object) && (object->flags & OBJECT_ALLOCATED)
&& update_checksum(object) && get_object(object)) {
/* color it gray temporarily */
object->count = object->min_count;
list_add_tail(&object->gray_list, &gray_list);
}
- spin_unlock_irqrestore(&object->lock, flags);
+ raw_spin_unlock_irqrestore(&object->lock, flags);
}
rcu_read_unlock();
@@ -1519,7 +1519,7 @@ static void kmemleak_scan(void)
*/
rcu_read_lock();
list_for_each_entry_rcu(object, &object_list, object_list) {
- spin_lock_irqsave(&object->lock, flags);
+ raw_spin_lock_irqsave(&object->lock, flags);
if (unreferenced_object(object) &&
!(object->flags & OBJECT_REPORTED)) {
object->flags |= OBJECT_REPORTED;
@@ -1529,7 +1529,7 @@ static void kmemleak_scan(void)
new_leaks++;
}
- spin_unlock_irqrestore(&object->lock, flags);
+ raw_spin_unlock_irqrestore(&object->lock, flags);
}
rcu_read_unlock();
@@ -1681,10 +1681,10 @@ static int kmemleak_seq_show(struct seq_file *seq, void *v)
struct kmemleak_object *object = v;
unsigned long flags;
- spin_lock_irqsave(&object->lock, flags);
+ raw_spin_lock_irqsave(&object->lock, flags);
if ((object->flags & OBJECT_REPORTED) && unreferenced_object(object))
print_unreferenced(seq, object);
- spin_unlock_irqrestore(&object->lock, flags);
+ raw_spin_unlock_irqrestore(&object->lock, flags);
return 0;
}
@@ -1714,9 +1714,9 @@ static int dump_str_object_info(const char *str)
return -EINVAL;
}
- spin_lock_irqsave(&object->lock, flags);
+ raw_spin_lock_irqsave(&object->lock, flags);
dump_object_info(object);
- spin_unlock_irqrestore(&object->lock, flags);
+ raw_spin_unlock_irqrestore(&object->lock, flags);
put_object(object);
return 0;
@@ -1735,11 +1735,11 @@ static void kmemleak_clear(void)
rcu_read_lock();
list_for_each_entry_rcu(object, &object_list, object_list) {
- spin_lock_irqsave(&object->lock, flags);
+ raw_spin_lock_irqsave(&object->lock, flags);
if ((object->flags & OBJECT_REPORTED) &&
unreferenced_object(object))
__paint_it(object, KMEMLEAK_GREY);
- spin_unlock_irqrestore(&object->lock, flags);
+ raw_spin_unlock_irqrestore(&object->lock, flags);
}
rcu_read_unlock();
diff --git a/mm/memblock.c b/mm/memblock.c
index 4bc2c7d8bf42..eba94ee3de0b 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -575,7 +575,7 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type,
* Return:
* 0 on success, -errno on failure.
*/
-int __init_memblock memblock_add_range(struct memblock_type *type,
+static int __init_memblock memblock_add_range(struct memblock_type *type,
phys_addr_t base, phys_addr_t size,
int nid, enum memblock_flags flags)
{
@@ -694,7 +694,7 @@ int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
{
phys_addr_t end = base + size - 1;
- memblock_dbg("memblock_add: [%pa-%pa] %pS\n",
+ memblock_dbg("%s: [%pa-%pa] %pS\n", __func__,
&base, &end, (void *)_RET_IP_);
return memblock_add_range(&memblock.memory, base, size, MAX_NUMNODES, 0);
@@ -795,7 +795,7 @@ int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size)
{
phys_addr_t end = base + size - 1;
- memblock_dbg("memblock_remove: [%pa-%pa] %pS\n",
+ memblock_dbg("%s: [%pa-%pa] %pS\n", __func__,
&base, &end, (void *)_RET_IP_);
return memblock_remove_range(&memblock.memory, base, size);
@@ -813,7 +813,7 @@ int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size)
{
phys_addr_t end = base + size - 1;
- memblock_dbg(" memblock_free: [%pa-%pa] %pS\n",
+ memblock_dbg("%s: [%pa-%pa] %pS\n", __func__,
&base, &end, (void *)_RET_IP_);
kmemleak_free_part_phys(base, size);
@@ -824,12 +824,24 @@ int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
{
phys_addr_t end = base + size - 1;
- memblock_dbg("memblock_reserve: [%pa-%pa] %pS\n",
+ memblock_dbg("%s: [%pa-%pa] %pS\n", __func__,
&base, &end, (void *)_RET_IP_);
return memblock_add_range(&memblock.reserved, base, size, MAX_NUMNODES, 0);
}
+#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
+int __init_memblock memblock_physmem_add(phys_addr_t base, phys_addr_t size)
+{
+ phys_addr_t end = base + size - 1;
+
+ memblock_dbg("%s: [%pa-%pa] %pS\n", __func__,
+ &base, &end, (void *)_RET_IP_);
+
+ return memblock_add_range(&memblock.physmem, base, size, MAX_NUMNODES, 0);
+}
+#endif
+
/**
* memblock_setclr_flag - set or clear flag for a memory region
* @base: base address of the region
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6c83cf4ed970..6f6dc8712e39 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5340,14 +5340,6 @@ static int mem_cgroup_move_account(struct page *page,
__mod_lruvec_state(to_vec, NR_WRITEBACK, nr_pages);
}
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- if (compound && !list_empty(page_deferred_list(page))) {
- spin_lock(&from->deferred_split_queue.split_queue_lock);
- list_del_init(page_deferred_list(page));
- from->deferred_split_queue.split_queue_len--;
- spin_unlock(&from->deferred_split_queue.split_queue_lock);
- }
-#endif
/*
* It is safe to change page->mem_cgroup here because the page
* is referenced, charged, and isolated - we can't race with
@@ -5357,16 +5349,6 @@ static int mem_cgroup_move_account(struct page *page,
/* caller should have done css_get */
page->mem_cgroup = to;
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- if (compound && list_empty(page_deferred_list(page))) {
- spin_lock(&to->deferred_split_queue.split_queue_lock);
- list_add_tail(page_deferred_list(page),
- &to->deferred_split_queue.split_queue);
- to->deferred_split_queue.split_queue_len++;
- spin_unlock(&to->deferred_split_queue.split_queue_lock);
- }
-#endif
-
spin_unlock_irqrestore(&from->move_lock, flags);
ret = 0;
@@ -6651,7 +6633,6 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
{
struct mem_cgroup *memcg;
unsigned int nr_pages;
- bool compound;
unsigned long flags;
VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage);
@@ -6673,8 +6654,7 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
return;
/* Force-charge the new page. The old one will be freed soon */
- compound = PageTransHuge(newpage);
- nr_pages = compound ? hpage_nr_pages(newpage) : 1;
+ nr_pages = hpage_nr_pages(newpage);
page_counter_charge(&memcg->memory, nr_pages);
if (do_memsw_account())
@@ -6684,7 +6664,8 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
commit_charge(newpage, memcg, false);
local_irq_save(flags);
- mem_cgroup_charge_statistics(memcg, newpage, compound, nr_pages);
+ mem_cgroup_charge_statistics(memcg, newpage, PageTransHuge(newpage),
+ nr_pages);
memcg_check_events(memcg, newpage);
local_irq_restore(flags);
}
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index a91a072f2b2c..36d80915ddc2 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -783,27 +783,18 @@ struct zone * zone_for_pfn_range(int online_type, int nid, unsigned start_pfn,
return default_zone_for_pfn(nid, start_pfn, nr_pages);
}
-int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type)
+int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
+ int online_type, int nid)
{
unsigned long flags;
unsigned long onlined_pages = 0;
struct zone *zone;
int need_zonelists_rebuild = 0;
- int nid;
int ret;
struct memory_notify arg;
- struct memory_block *mem;
mem_hotplug_begin();
- /*
- * We can't use pfn_to_nid() because nid might be stored in struct page
- * which is not yet initialized. Instead, we find nid from memory block.
- */
- mem = find_memory_block(__pfn_to_section(pfn));
- nid = mem->nid;
- put_device(&mem->dev);
-
/* associate pfn range with the zone */
zone = zone_for_pfn_range(online_type, nid, pfn, nr_pages);
move_pfn_range_to_zone(zone, pfn, nr_pages, NULL);
@@ -1182,7 +1173,7 @@ static bool is_pageblock_removable_nolock(unsigned long pfn)
if (!zone_spans_pfn(zone, pfn))
return false;
- return !has_unmovable_pages(zone, page, 0, MIGRATE_MOVABLE,
+ return !has_unmovable_pages(zone, page, MIGRATE_MOVABLE,
MEMORY_OFFLINE);
}
@@ -1764,8 +1755,6 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
BUG_ON(check_hotplug_memory_range(start, size));
- mem_hotplug_begin();
-
/*
* All memory blocks must be offlined before removing memory. Check
* whether all memory blocks in question are offline and return error
@@ -1778,9 +1767,14 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
/* remove memmap entry */
firmware_map_remove(start, start + size, "System RAM");
- /* remove memory block devices before removing memory */
+ /*
+ * Memory block device removal under the device_hotplug_lock is
+ * a barrier against racing online attempts.
+ */
remove_memory_block_devices(start, size);
+ mem_hotplug_begin();
+
arch_remove_memory(nid, start, size, NULL);
memblock_free(start, size);
memblock_remove(start, size);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index b2920ae87a61..977c641f78cf 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2821,6 +2821,9 @@ int mpol_parse_str(char *str, struct mempolicy **mpol)
char *flags = strchr(str, '=');
int err = 1, mode;
+ if (flags)
+ *flags++ = '\0'; /* terminate mode string */
+
if (nodelist) {
/* NUL-terminate mode or flags string */
*nodelist++ = '\0';
@@ -2831,9 +2834,6 @@ int mpol_parse_str(char *str, struct mempolicy **mpol)
} else
nodes_clear(nodes);
- if (flags)
- *flags++ = '\0'; /* terminate mode string */
-
mode = match_string(policy_modes, MPOL_MAX, str);
if (mode < 0)
goto out;
diff --git a/mm/memremap.c b/mm/memremap.c
index c51c6bd2fe34..4c723d2049d5 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -27,7 +27,8 @@ static void devmap_managed_enable_put(void)
static int devmap_managed_enable_get(struct dev_pagemap *pgmap)
{
- if (!pgmap->ops || !pgmap->ops->page_free) {
+ if (pgmap->type == MEMORY_DEVICE_PRIVATE &&
+ (!pgmap->ops || !pgmap->ops->page_free)) {
WARN(1, "Missing page_free method\n");
return -EINVAL;
}
@@ -410,48 +411,42 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
EXPORT_SYMBOL_GPL(get_dev_pagemap);
#ifdef CONFIG_DEV_PAGEMAP_OPS
-void __put_devmap_managed_page(struct page *page)
+void free_devmap_managed_page(struct page *page)
{
- int count = page_ref_dec_return(page);
-
- /*
- * If refcount is 1 then page is freed and refcount is stable as nobody
- * holds a reference on the page.
- */
- if (count == 1) {
- /* Clear Active bit in case of parallel mark_page_accessed */
- __ClearPageActive(page);
- __ClearPageWaiters(page);
+ /* notify page idle for dax */
+ if (!is_device_private_page(page)) {
+ wake_up_var(&page->_refcount);
+ return;
+ }
- mem_cgroup_uncharge(page);
+ /* Clear Active bit in case of parallel mark_page_accessed */
+ __ClearPageActive(page);
+ __ClearPageWaiters(page);
- /*
- * When a device_private page is freed, the page->mapping field
- * may still contain a (stale) mapping value. For example, the
- * lower bits of page->mapping may still identify the page as
- * an anonymous page. Ultimately, this entire field is just
- * stale and wrong, and it will cause errors if not cleared.
- * One example is:
- *
- * migrate_vma_pages()
- * migrate_vma_insert_page()
- * page_add_new_anon_rmap()
- * __page_set_anon_rmap()
- * ...checks page->mapping, via PageAnon(page) call,
- * and incorrectly concludes that the page is an
- * anonymous page. Therefore, it incorrectly,
- * silently fails to set up the new anon rmap.
- *
- * For other types of ZONE_DEVICE pages, migration is either
- * handled differently or not done at all, so there is no need
- * to clear page->mapping.
- */
- if (is_device_private_page(page))
- page->mapping = NULL;
+ mem_cgroup_uncharge(page);
- page->pgmap->ops->page_free(page);
- } else if (!count)
- __put_page(page);
+ /*
+ * When a device_private page is freed, the page->mapping field
+ * may still contain a (stale) mapping value. For example, the
+ * lower bits of page->mapping may still identify the page as an
+ * anonymous page. Ultimately, this entire field is just stale
+ * and wrong, and it will cause errors if not cleared. One
+ * example is:
+ *
+ * migrate_vma_pages()
+ * migrate_vma_insert_page()
+ * page_add_new_anon_rmap()
+ * __page_set_anon_rmap()
+ * ...checks page->mapping, via PageAnon(page) call,
+ * and incorrectly concludes that the page is an
+ * anonymous page. Therefore, it incorrectly,
+ * silently fails to set up the new anon rmap.
+ *
+ * For other types of ZONE_DEVICE pages, migration is either
+ * handled differently or not done at all, so there is no need
+ * to clear page->mapping.
+ */
+ page->mapping = NULL;
+ page->pgmap->ops->page_free(page);
}
-EXPORT_SYMBOL(__put_devmap_managed_page);
#endif /* CONFIG_DEV_PAGEMAP_OPS */
diff --git a/mm/migrate.c b/mm/migrate.c
index 86873b6f38a7..edf42ed90030 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -48,6 +48,7 @@
#include <linux/page_owner.h>
#include <linux/sched/mm.h>
#include <linux/ptrace.h>
+#include <linux/oom.h>
#include <asm/tlbflush.h>
@@ -986,7 +987,7 @@ static int move_to_new_page(struct page *newpage, struct page *page,
}
/*
- * Anonymous and movable page->mapping will be cleard by
+ * Anonymous and movable page->mapping will be cleared by
* free_pages_prepare so don't reset it here for keeping
* the type to work PageAnon, for example.
*/
@@ -1199,8 +1200,7 @@ out:
/*
* A page that has been migrated has all references
* removed and will be freed. A page that has not been
- * migrated will have kepts its references and be
- * restored.
+ * migrated will have kept its references and be restored.
*/
list_del(&page->lru);
@@ -1627,8 +1627,19 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
start = i;
} else if (node != current_node) {
err = do_move_pages_to_node(mm, &pagelist, current_node);
- if (err)
+ if (err) {
+ /*
+ * Positive err means the number of failed
+ * pages to migrate. Since we are going to
+ * abort and return the number of non-migrated
+ * pages, so need to incude the rest of the
+ * nr_pages that have not been attempted as
+ * well.
+ */
+ if (err > 0)
+ err += nr_pages - i - 1;
goto out;
+ }
err = store_status(status, start, current_node, i - start);
if (err)
goto out;
@@ -1659,8 +1670,11 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
goto out_flush;
err = do_move_pages_to_node(mm, &pagelist, current_node);
- if (err)
+ if (err) {
+ if (err > 0)
+ err += nr_pages - i - 1;
goto out;
+ }
if (i > start) {
err = store_status(status, start, current_node, i - start);
if (err)
@@ -1674,9 +1688,16 @@ out_flush:
/* Make sure we do not overwrite the existing error */
err1 = do_move_pages_to_node(mm, &pagelist, current_node);
+ /*
+ * Don't have to report non-attempted pages here since:
+ * - If the above loop is done gracefully all pages have been
+ * attempted.
+ * - If the above loop is aborted it means a fatal error
+ * happened, should return ret.
+ */
if (!err1)
err1 = store_status(status, start, current_node, i - start);
- if (!err)
+ if (err >= 0)
err = err1;
out:
return err;
@@ -2135,7 +2156,7 @@ static int migrate_vma_collect_hole(unsigned long start,
struct migrate_vma *migrate = walk->private;
unsigned long addr;
- for (addr = start & PAGE_MASK; addr < end; addr += PAGE_SIZE) {
+ for (addr = start; addr < end; addr += PAGE_SIZE) {
migrate->src[migrate->npages] = MIGRATE_PFN_MIGRATE;
migrate->dst[migrate->npages] = 0;
migrate->npages++;
@@ -2152,7 +2173,7 @@ static int migrate_vma_collect_skip(unsigned long start,
struct migrate_vma *migrate = walk->private;
unsigned long addr;
- for (addr = start & PAGE_MASK; addr < end; addr += PAGE_SIZE) {
+ for (addr = start; addr < end; addr += PAGE_SIZE) {
migrate->dst[migrate->npages] = 0;
migrate->src[migrate->npages++] = 0;
}
@@ -2675,6 +2696,14 @@ int migrate_vma_setup(struct migrate_vma *args)
}
EXPORT_SYMBOL(migrate_vma_setup);
+/*
+ * This code closely matches the code in:
+ * __handle_mm_fault()
+ * handle_pte_fault()
+ * do_anonymous_page()
+ * to map in an anonymous zero page but the struct page will be a ZONE_DEVICE
+ * private page.
+ */
static void migrate_vma_insert_page(struct migrate_vma *migrate,
unsigned long addr,
struct page *page,
@@ -2755,30 +2784,24 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
+ if (check_stable_address_space(mm))
+ goto unlock_abort;
+
if (pte_present(*ptep)) {
unsigned long pfn = pte_pfn(*ptep);
- if (!is_zero_pfn(pfn)) {
- pte_unmap_unlock(ptep, ptl);
- mem_cgroup_cancel_charge(page, memcg, false);
- goto abort;
- }
+ if (!is_zero_pfn(pfn))
+ goto unlock_abort;
flush = true;
- } else if (!pte_none(*ptep)) {
- pte_unmap_unlock(ptep, ptl);
- mem_cgroup_cancel_charge(page, memcg, false);
- goto abort;
- }
+ } else if (!pte_none(*ptep))
+ goto unlock_abort;
/*
- * Check for usefaultfd but do not deliver the fault. Instead,
+ * Check for userfaultfd but do not deliver the fault. Instead,
* just back off.
*/
- if (userfaultfd_missing(vma)) {
- pte_unmap_unlock(ptep, ptl);
- mem_cgroup_cancel_charge(page, memcg, false);
- goto abort;
- }
+ if (userfaultfd_missing(vma))
+ goto unlock_abort;
inc_mm_counter(mm, MM_ANONPAGES);
page_add_new_anon_rmap(page, vma, addr, false);
@@ -2802,6 +2825,9 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
*src = MIGRATE_PFN_MIGRATE;
return;
+unlock_abort:
+ pte_unmap_unlock(ptep, ptl);
+ mem_cgroup_cancel_charge(page, memcg, false);
abort:
*src &= ~MIGRATE_PFN_MIGRATE;
}
@@ -2834,9 +2860,8 @@ void migrate_vma_pages(struct migrate_vma *migrate)
}
if (!page) {
- if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE)) {
+ if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE))
continue;
- }
if (!notified) {
notified = true;
diff --git a/mm/mmap.c b/mm/mmap.c
index bc788548c4e5..6756b8bb0033 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1270,26 +1270,22 @@ static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_
*/
struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma)
{
- struct anon_vma *anon_vma;
- struct vm_area_struct *near;
-
- near = vma->vm_next;
- if (!near)
- goto try_prev;
-
- anon_vma = reusable_anon_vma(near, vma, near);
- if (anon_vma)
- return anon_vma;
-try_prev:
- near = vma->vm_prev;
- if (!near)
- goto none;
-
- anon_vma = reusable_anon_vma(near, near, vma);
- if (anon_vma)
- return anon_vma;
-none:
+ struct anon_vma *anon_vma = NULL;
+
+ /* Try next first. */
+ if (vma->vm_next) {
+ anon_vma = reusable_anon_vma(vma->vm_next, vma, vma->vm_next);
+ if (anon_vma)
+ return anon_vma;
+ }
+
+ /* Try prev next. */
+ if (vma->vm_prev)
+ anon_vma = reusable_anon_vma(vma->vm_prev, vma->vm_prev, vma);
+
/*
+ * We might reach here with anon_vma == NULL if we can't find
+ * any reusable anon_vma.
* There's no absolute need to look only at touching neighbours:
* we could search further afield for "compatible" anon_vmas.
* But it would probably just be a waste of time searching,
@@ -1297,7 +1293,7 @@ none:
* We're trying to allow mprotect remerging later on,
* not trying to minimize memory used for anon_vmas.
*/
- return NULL;
+ return anon_vma;
}
/*
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index d58c481b3df8..dfc357614e56 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -26,6 +26,7 @@
#include <linux/sched/mm.h>
#include <linux/sched/coredump.h>
#include <linux/sched/task.h>
+#include <linux/sched/debug.h>
#include <linux/swap.h>
#include <linux/timex.h>
#include <linux/jiffies.h>
@@ -620,6 +621,7 @@ static void oom_reap_task(struct task_struct *tsk)
pr_info("oom_reaper: unable to reap pid:%d (%s)\n",
task_pid_nr(tsk), tsk->comm);
+ sched_show_task(tsk);
debug_show_all_locks();
done:
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d047bf7d8fd4..15e908ad933b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5848,6 +5848,30 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn)
return false;
}
+#ifdef CONFIG_SPARSEMEM
+/* Skip PFNs that belong to non-present sections */
+static inline __meminit unsigned long next_pfn(unsigned long pfn)
+{
+ unsigned long section_nr;
+
+ section_nr = pfn_to_section_nr(++pfn);
+ if (present_section_nr(section_nr))
+ return pfn;
+
+ while (++section_nr <= __highest_present_section_nr) {
+ if (present_section_nr(section_nr))
+ return section_nr_to_pfn(section_nr);
+ }
+
+ return -1;
+}
+#else
+static inline __meminit unsigned long next_pfn(unsigned long pfn)
+{
+ return pfn++;
+}
+#endif
+
/*
* Initially all pages are reserved - free ones are freed
* up by memblock_free_all() once the early boot process is
@@ -5887,8 +5911,10 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
* function. They do not exist on hotplugged memory.
*/
if (context == MEMMAP_EARLY) {
- if (!early_pfn_valid(pfn))
+ if (!early_pfn_valid(pfn)) {
+ pfn = next_pfn(pfn) - 1;
continue;
+ }
if (!early_pfn_in_nid(pfn, nid))
continue;
if (overlap_memmap_init(zone, &pfn))
@@ -8154,20 +8180,22 @@ void *__init alloc_large_system_hash(const char *tablename,
/*
* This function checks whether pageblock includes unmovable pages or not.
- * If @count is not zero, it is okay to include less @count unmovable pages
*
* PageLRU check without isolation or lru_lock could race so that
* MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable
* check without lock_page also may miss some movable non-lru pages at
* race condition. So you can't expect this function should be exact.
+ *
+ * Returns a page without holding a reference. If the caller wants to
+ * dereference that page (e.g., dumping), it has to make sure that that it
+ * cannot get removed (e.g., via memory unplug) concurrently.
+ *
*/
-bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
- int migratetype, int flags)
+struct page *has_unmovable_pages(struct zone *zone, struct page *page,
+ int migratetype, int flags)
{
- unsigned long found;
unsigned long iter = 0;
unsigned long pfn = page_to_pfn(page);
- const char *reason = "unmovable page";
/*
* TODO we could make this much more efficient by not checking every
@@ -8184,22 +8212,19 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
* so consider them movable here.
*/
if (is_migrate_cma(migratetype))
- return false;
+ return NULL;
- reason = "CMA page";
- goto unmovable;
+ return page;
}
- for (found = 0; iter < pageblock_nr_pages; iter++) {
- unsigned long check = pfn + iter;
-
- if (!pfn_valid_within(check))
+ for (; iter < pageblock_nr_pages; iter++) {
+ if (!pfn_valid_within(pfn + iter))
continue;
- page = pfn_to_page(check);
+ page = pfn_to_page(pfn + iter);
if (PageReserved(page))
- goto unmovable;
+ return page;
/*
* If the zone is movable and we have ruled out all reserved
@@ -8219,7 +8244,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
unsigned int skip_pages;
if (!hugepage_migration_supported(page_hstate(head)))
- goto unmovable;
+ return page;
skip_pages = compound_nr(head) - (page - head);
iter += skip_pages - 1;
@@ -8245,11 +8270,9 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
if ((flags & MEMORY_OFFLINE) && PageHWPoison(page))
continue;
- if (__PageMovable(page))
+ if (__PageMovable(page) || PageLRU(page))
continue;
- if (!PageLRU(page))
- found++;
/*
* If there are RECLAIMABLE pages, we need to check
* it. But now, memory offline itself doesn't call
@@ -8263,15 +8286,9 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
* is set to both of a memory hole page and a _used_ kernel
* page at boot.
*/
- if (found > count)
- goto unmovable;
+ return page;
}
- return false;
-unmovable:
- WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE);
- if (flags & REPORT_FAILURE)
- dump_page(pfn_to_page(pfn + iter), reason);
- return true;
+ return NULL;
}
#ifdef CONFIG_CONTIG_ALLOC
@@ -8675,10 +8692,6 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
BUG_ON(!PageBuddy(page));
order = page_order(page);
offlined_pages += 1 << order;
-#ifdef CONFIG_DEBUG_VM
- pr_info("remove from free list %lx %d %lx\n",
- pfn, 1 << order, end_pfn);
-#endif
del_page_from_free_area(page, &zone->free_area[order]);
pfn += (1 << order);
}
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 04ee1663cdbe..a9fd7c740c23 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -17,10 +17,9 @@
static int set_migratetype_isolate(struct page *page, int migratetype, int isol_flags)
{
+ struct page *unmovable = NULL;
struct zone *zone;
- unsigned long flags, pfn;
- struct memory_isolate_notify arg;
- int notifier_ret;
+ unsigned long flags;
int ret = -EBUSY;
zone = page_zone(page);
@@ -35,41 +34,12 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_
if (is_migrate_isolate_page(page))
goto out;
- pfn = page_to_pfn(page);
- arg.start_pfn = pfn;
- arg.nr_pages = pageblock_nr_pages;
- arg.pages_found = 0;
-
- /*
- * It may be possible to isolate a pageblock even if the
- * migratetype is not MIGRATE_MOVABLE. The memory isolation
- * notifier chain is used by balloon drivers to return the
- * number of pages in a range that are held by the balloon
- * driver to shrink memory. If all the pages are accounted for
- * by balloons, are free, or on the LRU, isolation can continue.
- * Later, for example, when memory hotplug notifier runs, these
- * pages reported as "can be isolated" should be isolated(freed)
- * by the balloon driver through the memory notifier chain.
- */
- notifier_ret = memory_isolate_notify(MEM_ISOLATE_COUNT, &arg);
- notifier_ret = notifier_to_errno(notifier_ret);
- if (notifier_ret)
- goto out;
/*
* FIXME: Now, memory hotplug doesn't call shrink_slab() by itself.
* We just check MOVABLE pages.
*/
- if (!has_unmovable_pages(zone, page, arg.pages_found, migratetype,
- isol_flags))
- ret = 0;
-
- /*
- * immobile means "not-on-lru" pages. If immobile is larger than
- * removable-by-driver pages reported by notifier, we'll fail.
- */
-
-out:
- if (!ret) {
+ unmovable = has_unmovable_pages(zone, page, migratetype, isol_flags);
+ if (!unmovable) {
unsigned long nr_pages;
int mt = get_pageblock_migratetype(page);
@@ -79,11 +49,24 @@ out:
NULL);
__mod_zone_freepage_state(zone, -nr_pages, mt);
+ ret = 0;
}
+out:
spin_unlock_irqrestore(&zone->lock, flags);
- if (!ret)
+ if (!ret) {
drain_all_pages(zone);
+ } else {
+ WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE);
+
+ if ((isol_flags & REPORT_FAILURE) && unmovable)
+ /*
+ * printk() with zone->lock held will likely trigger a
+ * lockdep splat, so defer it here.
+ */
+ dump_page(unmovable, "unmovable page");
+ }
+
return ret;
}
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index eff4b4520c8d..719c35246cfa 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -52,12 +52,16 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw)
return true;
}
-static inline bool pfn_in_hpage(struct page *hpage, unsigned long pfn)
+static inline bool pfn_is_match(struct page *page, unsigned long pfn)
{
- unsigned long hpage_pfn = page_to_pfn(hpage);
+ unsigned long page_pfn = page_to_pfn(page);
+
+ /* normal page and hugetlbfs page */
+ if (!PageTransCompound(page) || PageHuge(page))
+ return page_pfn == pfn;
/* THP can be referenced by any subpage */
- return pfn >= hpage_pfn && pfn - hpage_pfn < hpage_nr_pages(hpage);
+ return pfn >= page_pfn && pfn - page_pfn < hpage_nr_pages(page);
}
/**
@@ -108,7 +112,7 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw)
pfn = pte_pfn(*pvmw->pte);
}
- return pfn_in_hpage(pvmw->page, pfn);
+ return pfn_is_match(pvmw->page, pfn);
}
/**
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index 357aa7bef6c0..de41e830cdac 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -42,12 +42,11 @@ static int process_vm_rw_pages(struct page **pages,
if (copy > len)
copy = len;
- if (vm_write) {
+ if (vm_write)
copied = copy_page_from_iter(page, offset, copy, iter);
- set_page_dirty_lock(page);
- } else {
+ else
copied = copy_page_to_iter(page, offset, copy, iter);
- }
+
len -= copied;
if (copied < copy && iov_iter_count(iter))
return -EFAULT;
@@ -96,7 +95,7 @@ static int process_vm_rw_single_vec(unsigned long addr,
flags |= FOLL_WRITE;
while (!rc && nr_pages && iov_iter_count(iter)) {
- int pages = min(nr_pages, max_pages_per_loop);
+ int pinned_pages = min(nr_pages, max_pages_per_loop);
int locked = 1;
size_t bytes;
@@ -106,14 +105,15 @@ static int process_vm_rw_single_vec(unsigned long addr,
* current/current->mm
*/
down_read(&mm->mmap_sem);
- pages = get_user_pages_remote(task, mm, pa, pages, flags,
- process_pages, NULL, &locked);
+ pinned_pages = pin_user_pages_remote(task, mm, pa, pinned_pages,
+ flags, process_pages,
+ NULL, &locked);
if (locked)
up_read(&mm->mmap_sem);
- if (pages <= 0)
+ if (pinned_pages <= 0)
return -EFAULT;
- bytes = pages * PAGE_SIZE - start_offset;
+ bytes = pinned_pages * PAGE_SIZE - start_offset;
if (bytes > len)
bytes = len;
@@ -122,10 +122,12 @@ static int process_vm_rw_single_vec(unsigned long addr,
vm_write);
len -= bytes;
start_offset = 0;
- nr_pages -= pages;
- pa += pages * PAGE_SIZE;
- while (pages)
- put_page(process_pages[--pages]);
+ nr_pages -= pinned_pages;
+ pa += pinned_pages * PAGE_SIZE;
+
+ /* If vm_write is set, the pages need to be made dirty: */
+ unpin_user_pages_dirty_lock(process_pages, pinned_pages,
+ vm_write);
}
return rc;
diff --git a/mm/slub.c b/mm/slub.c
index 0ab92ec8c2a6..17dc00e33115 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -439,19 +439,38 @@ static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page,
}
#ifdef CONFIG_SLUB_DEBUG
+static unsigned long object_map[BITS_TO_LONGS(MAX_OBJS_PER_PAGE)];
+static DEFINE_SPINLOCK(object_map_lock);
+
/*
* Determine a map of object in use on a page.
*
* Node listlock must be held to guarantee that the page does
* not vanish from under us.
*/
-static void get_map(struct kmem_cache *s, struct page *page, unsigned long *map)
+static unsigned long *get_map(struct kmem_cache *s, struct page *page)
{
void *p;
void *addr = page_address(page);
+ VM_BUG_ON(!irqs_disabled());
+
+ spin_lock(&object_map_lock);
+
+ bitmap_zero(object_map, page->objects);
+
for (p = page->freelist; p; p = get_freepointer(s, p))
- set_bit(slab_index(p, s, addr), map);
+ set_bit(slab_index(p, s, addr), object_map);
+
+ return object_map;
+}
+
+static void put_map(unsigned long *map)
+{
+ VM_BUG_ON(map != object_map);
+ lockdep_assert_held(&object_map_lock);
+
+ spin_unlock(&object_map_lock);
}
static inline unsigned int size_from_object(struct kmem_cache *s)
@@ -3675,13 +3694,12 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page,
#ifdef CONFIG_SLUB_DEBUG
void *addr = page_address(page);
void *p;
- unsigned long *map = bitmap_zalloc(page->objects, GFP_ATOMIC);
- if (!map)
- return;
+ unsigned long *map;
+
slab_err(s, page, text, s->name);
slab_lock(page);
- get_map(s, page, map);
+ map = get_map(s, page);
for_each_object(p, s, addr, page->objects) {
if (!test_bit(slab_index(p, s, addr), map)) {
@@ -3689,8 +3707,9 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page,
print_tracking(s, p);
}
}
+ put_map(map);
+
slab_unlock(page);
- bitmap_free(map);
#endif
}
@@ -4384,19 +4403,19 @@ static int count_total(struct page *page)
#endif
#ifdef CONFIG_SLUB_DEBUG
-static void validate_slab(struct kmem_cache *s, struct page *page,
- unsigned long *map)
+static void validate_slab(struct kmem_cache *s, struct page *page)
{
void *p;
void *addr = page_address(page);
+ unsigned long *map;
+
+ slab_lock(page);
if (!check_slab(s, page) || !on_freelist(s, page, NULL))
- return;
+ goto unlock;
/* Now we know that a valid freelist exists */
- bitmap_zero(map, page->objects);
-
- get_map(s, page, map);
+ map = get_map(s, page);
for_each_object(p, s, addr, page->objects) {
u8 val = test_bit(slab_index(p, s, addr), map) ?
SLUB_RED_INACTIVE : SLUB_RED_ACTIVE;
@@ -4404,18 +4423,13 @@ static void validate_slab(struct kmem_cache *s, struct page *page,
if (!check_object(s, page, p, val))
break;
}
-}
-
-static void validate_slab_slab(struct kmem_cache *s, struct page *page,
- unsigned long *map)
-{
- slab_lock(page);
- validate_slab(s, page, map);
+ put_map(map);
+unlock:
slab_unlock(page);
}
static int validate_slab_node(struct kmem_cache *s,
- struct kmem_cache_node *n, unsigned long *map)
+ struct kmem_cache_node *n)
{
unsigned long count = 0;
struct page *page;
@@ -4424,7 +4438,7 @@ static int validate_slab_node(struct kmem_cache *s,
spin_lock_irqsave(&n->list_lock, flags);
list_for_each_entry(page, &n->partial, slab_list) {
- validate_slab_slab(s, page, map);
+ validate_slab(s, page);
count++;
}
if (count != n->nr_partial)
@@ -4435,7 +4449,7 @@ static int validate_slab_node(struct kmem_cache *s,
goto out;
list_for_each_entry(page, &n->full, slab_list) {
- validate_slab_slab(s, page, map);
+ validate_slab(s, page);
count++;
}
if (count != atomic_long_read(&n->nr_slabs))
@@ -4452,15 +4466,11 @@ static long validate_slab_cache(struct kmem_cache *s)
int node;
unsigned long count = 0;
struct kmem_cache_node *n;
- unsigned long *map = bitmap_alloc(oo_objects(s->max), GFP_KERNEL);
-
- if (!map)
- return -ENOMEM;
flush_all(s);
for_each_kmem_cache_node(s, node, n)
- count += validate_slab_node(s, n, map);
- bitmap_free(map);
+ count += validate_slab_node(s, n);
+
return count;
}
/*
@@ -4590,18 +4600,17 @@ static int add_location(struct loc_track *t, struct kmem_cache *s,
}
static void process_slab(struct loc_track *t, struct kmem_cache *s,
- struct page *page, enum track_item alloc,
- unsigned long *map)
+ struct page *page, enum track_item alloc)
{
void *addr = page_address(page);
void *p;
+ unsigned long *map;
- bitmap_zero(map, page->objects);
- get_map(s, page, map);
-
+ map = get_map(s, page);
for_each_object(p, s, addr, page->objects)
if (!test_bit(slab_index(p, s, addr), map))
add_location(t, s, get_track(s, p, alloc));
+ put_map(map);
}
static int list_locations(struct kmem_cache *s, char *buf,
@@ -4612,11 +4621,9 @@ static int list_locations(struct kmem_cache *s, char *buf,
struct loc_track t = { 0, 0, NULL };
int node;
struct kmem_cache_node *n;
- unsigned long *map = bitmap_alloc(oo_objects(s->max), GFP_KERNEL);
- if (!map || !alloc_loc_track(&t, PAGE_SIZE / sizeof(struct location),
- GFP_KERNEL)) {
- bitmap_free(map);
+ if (!alloc_loc_track(&t, PAGE_SIZE / sizeof(struct location),
+ GFP_KERNEL)) {
return sprintf(buf, "Out of memory\n");
}
/* Push back cpu slabs */
@@ -4631,9 +4638,9 @@ static int list_locations(struct kmem_cache *s, char *buf,
spin_lock_irqsave(&n->list_lock, flags);
list_for_each_entry(page, &n->partial, slab_list)
- process_slab(&t, s, page, alloc, map);
+ process_slab(&t, s, page, alloc);
list_for_each_entry(page, &n->full, slab_list)
- process_slab(&t, s, page, alloc, map);
+ process_slab(&t, s, page, alloc);
spin_unlock_irqrestore(&n->list_lock, flags);
}
@@ -4682,7 +4689,6 @@ static int list_locations(struct kmem_cache *s, char *buf,
}
free_loc_track(&t);
- bitmap_free(map);
if (!t.count)
len += sprintf(buf, "No data\n");
return len;
diff --git a/mm/sparse.c b/mm/sparse.c
index 3822ecbd8a1f..3918fc3eaef1 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -789,7 +789,7 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
ms->usage = NULL;
}
memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
- ms->section_mem_map = sparse_encode_mem_map(NULL, section_nr);
+ ms->section_mem_map = (unsigned long)NULL;
}
if (section_is_early && memmap)
diff --git a/mm/swap.c b/mm/swap.c
index 5341ae93861f..cf39d24ada2a 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -813,8 +813,10 @@ void release_pages(struct page **pages, int nr)
* processing, and instead, expect a call to
* put_page_testzero().
*/
- if (put_devmap_managed_page(page))
+ if (page_is_devmap_managed(page)) {
+ put_devmap_managed_page(page);
continue;
+ }
}
page = compound_head(page);
@@ -1102,3 +1104,26 @@ void __init swap_setup(void)
* _really_ don't want to cluster much more
*/
}
+
+#ifdef CONFIG_DEV_PAGEMAP_OPS
+void put_devmap_managed_page(struct page *page)
+{
+ int count;
+
+ if (WARN_ON_ONCE(!page_is_devmap_managed(page)))
+ return;
+
+ count = page_ref_dec_return(page);
+
+ /*
+ * devmap page refcounts are 1-based, rather than 0-based: if
+ * refcount is 1, then the page is free and the refcount is
+ * stable because nobody holds a reference on the page.
+ */
+ if (count == 1)
+ free_devmap_managed_page(page);
+ else if (!count)
+ __put_page(page);
+}
+EXPORT_SYMBOL(put_devmap_managed_page);
+#endif
diff --git a/mm/swapfile.c b/mm/swapfile.c
index bb3261d45b6a..6febae9ad3cd 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2737,10 +2737,10 @@ static void *swap_next(struct seq_file *swap, void *v, loff_t *pos)
else
type = si->type + 1;
+ ++(*pos);
for (; (si = swap_type_to_swap_info(type)); type++) {
if (!(si->flags & SWP_USED) || !si->swap_map)
continue;
- ++*pos;
return si;
}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 572fb17c6273..c05eb9efec07 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -146,20 +146,6 @@ struct scan_control {
struct reclaim_state reclaim_state;
};
-#ifdef ARCH_HAS_PREFETCH
-#define prefetch_prev_lru_page(_page, _base, _field) \
- do { \
- if ((_page)->lru.prev != _base) { \
- struct page *prev; \
- \
- prev = lru_to_page(&(_page->lru)); \
- prefetch(&prev->_field); \
- } \
- } while (0)
-#else
-#define prefetch_prev_lru_page(_page, _base, _field) do { } while (0)
-#endif
-
#ifdef ARCH_HAS_PREFETCHW
#define prefetchw_prev_lru_page(_page, _base, _field) \
do { \
@@ -2695,7 +2681,7 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
} while ((memcg = mem_cgroup_iter(target_memcg, memcg, NULL)));
}
-static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
+static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
{
struct reclaim_state *reclaim_state = current->reclaim_state;
unsigned long nr_reclaimed, nr_scanned;
@@ -2874,8 +2860,6 @@ again:
*/
if (reclaimable)
pgdat->kswapd_failures = 0;
-
- return reclaimable;
}
/*
@@ -4126,10 +4110,8 @@ module_init(kswapd_init)
*/
int node_reclaim_mode __read_mostly;
-#define RECLAIM_OFF 0
-#define RECLAIM_ZONE (1<<0) /* Run shrink_inactive_list on the zone */
-#define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */
-#define RECLAIM_UNMAP (1<<2) /* Unmap pages during reclaim */
+#define RECLAIM_WRITE (1<<0) /* Writeout pages during reclaim */
+#define RECLAIM_UNMAP (1<<1) /* Unmap pages during reclaim */
/*
* Priority for NODE_RECLAIM. This determines the fraction of pages
diff --git a/mm/zswap.c b/mm/zswap.c
index 46a322316e52..55094e63b72d 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -32,6 +32,7 @@
#include <linux/swapops.h>
#include <linux/writeback.h>
#include <linux/pagemap.h>
+#include <linux/workqueue.h>
/*********************************
* statistics
@@ -65,6 +66,11 @@ static u64 zswap_reject_kmemcache_fail;
/* Duplicate store was encountered (rare) */
static u64 zswap_duplicate_entry;
+/* Shrinker work queue */
+static struct workqueue_struct *shrink_wq;
+/* Pool limit was hit, we need to calm down */
+static bool zswap_pool_reached_full;
+
/*********************************
* tunables
**********************************/
@@ -109,6 +115,11 @@ module_param_cb(zpool, &zswap_zpool_param_ops, &zswap_zpool_type, 0644);
static unsigned int zswap_max_pool_percent = 20;
module_param_named(max_pool_percent, zswap_max_pool_percent, uint, 0644);
+/* The threshold for accepting new pages after the max_pool_percent was hit */
+static unsigned int zswap_accept_thr_percent = 90; /* of max pool size */
+module_param_named(accept_threshold_percent, zswap_accept_thr_percent,
+ uint, 0644);
+
/* Enable/disable handling same-value filled pages (enabled by default) */
static bool zswap_same_filled_pages_enabled = true;
module_param_named(same_filled_pages_enabled, zswap_same_filled_pages_enabled,
@@ -123,7 +134,8 @@ struct zswap_pool {
struct crypto_comp * __percpu *tfm;
struct kref kref;
struct list_head list;
- struct work_struct work;
+ struct work_struct release_work;
+ struct work_struct shrink_work;
struct hlist_node node;
char tfm_name[CRYPTO_MAX_ALG_NAME];
};
@@ -214,6 +226,13 @@ static bool zswap_is_full(void)
DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE);
}
+static bool zswap_can_accept(void)
+{
+ return totalram_pages() * zswap_accept_thr_percent / 100 *
+ zswap_max_pool_percent / 100 >
+ DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE);
+}
+
static void zswap_update_total_size(void)
{
struct zswap_pool *pool;
@@ -501,6 +520,16 @@ static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor)
return NULL;
}
+static void shrink_worker(struct work_struct *w)
+{
+ struct zswap_pool *pool = container_of(w, typeof(*pool),
+ shrink_work);
+
+ if (zpool_shrink(pool->zpool, 1, NULL))
+ zswap_reject_reclaim_fail++;
+ zswap_pool_put(pool);
+}
+
static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
{
struct zswap_pool *pool;
@@ -551,6 +580,7 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
*/
kref_init(&pool->kref);
INIT_LIST_HEAD(&pool->list);
+ INIT_WORK(&pool->shrink_work, shrink_worker);
zswap_pool_debug("created", pool);
@@ -624,7 +654,8 @@ static int __must_check zswap_pool_get(struct zswap_pool *pool)
static void __zswap_pool_release(struct work_struct *work)
{
- struct zswap_pool *pool = container_of(work, typeof(*pool), work);
+ struct zswap_pool *pool = container_of(work, typeof(*pool),
+ release_work);
synchronize_rcu();
@@ -647,8 +678,8 @@ static void __zswap_pool_empty(struct kref *kref)
list_del_rcu(&pool->list);
- INIT_WORK(&pool->work, __zswap_pool_release);
- schedule_work(&pool->work);
+ INIT_WORK(&pool->release_work, __zswap_pool_release);
+ schedule_work(&pool->release_work);
spin_unlock(&zswap_pools_lock);
}
@@ -942,22 +973,6 @@ end:
return ret;
}
-static int zswap_shrink(void)
-{
- struct zswap_pool *pool;
- int ret;
-
- pool = zswap_pool_last_get();
- if (!pool)
- return -ENOENT;
-
- ret = zpool_shrink(pool->zpool, 1, NULL);
-
- zswap_pool_put(pool);
-
- return ret;
-}
-
static int zswap_is_page_same_filled(void *ptr, unsigned long *value)
{
unsigned int pos;
@@ -1011,21 +1026,23 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
/* reclaim space if needed */
if (zswap_is_full()) {
+ struct zswap_pool *pool;
+
zswap_pool_limit_hit++;
- if (zswap_shrink()) {
- zswap_reject_reclaim_fail++;
- ret = -ENOMEM;
- goto reject;
- }
+ zswap_pool_reached_full = true;
+ pool = zswap_pool_last_get();
+ if (pool)
+ queue_work(shrink_wq, &pool->shrink_work);
+ ret = -ENOMEM;
+ goto reject;
+ }
- /* A second zswap_is_full() check after
- * zswap_shrink() to make sure it's now
- * under the max_pool_percent
- */
- if (zswap_is_full()) {
+ if (zswap_pool_reached_full) {
+ if (!zswap_can_accept()) {
ret = -ENOMEM;
goto reject;
- }
+ } else
+ zswap_pool_reached_full = false;
}
/* allocate entry */
@@ -1332,11 +1349,18 @@ static int __init init_zswap(void)
zswap_enabled = false;
}
+ shrink_wq = create_workqueue("zswap-shrink");
+ if (!shrink_wq)
+ goto fallback_fail;
+
frontswap_register_ops(&zswap_frontswap_ops);
if (zswap_debugfs_init())
pr_warn("debugfs initialization failed\n");
return 0;
+fallback_fail:
+ if (pool)
+ zswap_pool_destroy(pool);
hp_fail:
cpuhp_remove_state(CPUHP_MM_ZSWP_MEM_PREPARE);
dstmem_fail:
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index f93e917e0929..fa7bb5e060d0 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -212,7 +212,7 @@ static int xdp_umem_map_pages(struct xdp_umem *umem)
static void xdp_umem_unpin_pages(struct xdp_umem *umem)
{
- put_user_pages_dirty_lock(umem->pgs, umem->npgs, true);
+ unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true);
kfree(umem->pgs);
umem->pgs = NULL;
@@ -291,7 +291,7 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem)
return -ENOMEM;
down_read(&current->mm->mmap_sem);
- npgs = get_user_pages(umem->address, umem->npgs,
+ npgs = pin_user_pages(umem->address, umem->npgs,
gup_flags | FOLL_LONGTERM, &umem->pgs[0], NULL);
up_read(&current->mm->mmap_sem);
diff --git a/scripts/spelling.txt b/scripts/spelling.txt
index 672b5931bc8d..ffa838f3a2b5 100644
--- a/scripts/spelling.txt
+++ b/scripts/spelling.txt
@@ -39,6 +39,8 @@ accout||account
accquire||acquire
accquired||acquired
accross||across
+accumalate||accumulate
+accumalator||accumulator
acessable||accessible
acess||access
acessing||accessing
@@ -106,6 +108,7 @@ alogrithm||algorithm
alot||a lot
alow||allow
alows||allows
+alreay||already
alredy||already
altough||although
alue||value
@@ -241,6 +244,7 @@ calender||calendar
calescing||coalescing
calle||called
callibration||calibration
+callled||called
calucate||calculate
calulate||calculate
cancelation||cancellation
@@ -311,6 +315,7 @@ compaibility||compatibility
comparsion||comparison
compatability||compatibility
compatable||compatible
+compatibililty||compatibility
compatibiliy||compatibility
compatibilty||compatibility
compatiblity||compatibility
@@ -330,6 +335,7 @@ comunication||communication
conbination||combination
conditionaly||conditionally
conditon||condition
+condtion||condition
conected||connected
conector||connector
connecetd||connected
@@ -388,6 +394,8 @@ dafault||default
deafult||default
deamon||daemon
debouce||debounce
+decendant||descendant
+decendants||descendants
decompres||decompress
decsribed||described
decription||description
@@ -411,11 +419,13 @@ delare||declare
delares||declares
delaring||declaring
delemiter||delimiter
+delievered||delivered
demodualtor||demodulator
demension||dimension
dependancies||dependencies
dependancy||dependency
dependant||dependent
+dependend||dependent
depreacted||deprecated
depreacte||deprecate
desactivate||deactivate
@@ -791,6 +801,7 @@ ireelevant||irrelevant
irrelevent||irrelevant
isnt||isn't
isssue||issue
+issus||issues
iternations||iterations
itertation||iteration
itslef||itself
@@ -995,6 +1006,7 @@ peice||piece
pendantic||pedantic
peprocessor||preprocessor
perfoming||performing
+perfomring||performing
peripherial||peripheral
permissons||permissions
peroid||period
@@ -1166,6 +1178,8 @@ retreive||retrieve
retreiving||retrieving
retrive||retrieve
retrived||retrieved
+retrun||return
+retun||return
retuned||returned
reudce||reduce
reuest||request
diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
index 485cf06ef013..389327e9b30a 100644
--- a/tools/testing/selftests/vm/gup_benchmark.c
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -18,6 +18,9 @@
#define GUP_LONGTERM_BENCHMARK _IOWR('g', 2, struct gup_benchmark)
#define GUP_BENCHMARK _IOWR('g', 3, struct gup_benchmark)
+/* Just the flags we need, copied from mm.h: */
+#define FOLL_WRITE 0x01 /* check pte is writable */
+
struct gup_benchmark {
__u64 get_delta_usec;
__u64 put_delta_usec;
@@ -85,7 +88,8 @@ int main(int argc, char **argv)
}
gup.nr_pages_per_call = nr_pages;
- gup.flags = write;
+ if (write)
+ gup.flags |= FOLL_WRITE;
fd = open("/sys/kernel/debug/gup_benchmark", O_RDWR);
if (fd == -1)
diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c
index 68092d15e12b..9b68658b6bb8 100644
--- a/tools/vm/slabinfo.c
+++ b/tools/vm/slabinfo.c
@@ -720,11 +720,11 @@ static void slab_debug(struct slabinfo *s)
return;
if (sanity && !s->sanity_checks) {
- set_obj(s, "sanity", 1);
+ set_obj(s, "sanity_checks", 1);
}
if (!sanity && s->sanity_checks) {
if (slab_empty(s))
- set_obj(s, "sanity", 0);
+ set_obj(s, "sanity_checks", 0);
else
fprintf(stderr, "%s not empty cannot disable sanity checks\n", s->name);
}