summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-09-08 12:55:35 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-09-08 12:55:35 -0700
commit2d338201d5311bcd79d42f66df4cecbcbc5f4f2c (patch)
tree75d87f65c31f4721ba6a5356d2a487af9e2961c3
parentcc09ee80c3b18ae1a897a30a17fe710b2b2f620a (diff)
parentb285437d1d929785a5bef3603da78d2cd5341893 (diff)
Merge branch 'akpm' (patches from Andrew)
Merge more updates from Andrew Morton: "147 patches, based on 7d2a07b769330c34b4deabeed939325c77a7ec2f. Subsystems affected by this patch series: mm (memory-hotplug, rmap, ioremap, highmem, cleanups, secretmem, kfence, damon, and vmscan), alpha, percpu, procfs, misc, core-kernel, MAINTAINERS, lib, checkpatch, epoll, init, nilfs2, coredump, fork, pids, criu, kconfig, selftests, ipc, and scripts" * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (94 commits) scripts: check_extable: fix typo in user error message mm/workingset: correct kernel-doc notations ipc: replace costly bailout check in sysvipc_find_ipc() selftests/memfd: remove unused variable Kconfig.debug: drop selecting non-existing HARDLOCKUP_DETECTOR_ARCH configs: remove the obsolete CONFIG_INPUT_POLLDEV prctl: allow to setup brk for et_dyn executables pid: cleanup the stale comment mentioning pidmap_init(). kernel/fork.c: unexport get_{mm,task}_exe_file coredump: fix memleak in dump_vma_snapshot() fs/coredump.c: log if a core dump is aborted due to changed file permissions nilfs2: use refcount_dec_and_lock() to fix potential UAF nilfs2: fix memory leak in nilfs_sysfs_delete_snapshot_group nilfs2: fix memory leak in nilfs_sysfs_create_snapshot_group nilfs2: fix memory leak in nilfs_sysfs_delete_##name##_group nilfs2: fix memory leak in nilfs_sysfs_create_##name##_group nilfs2: fix NULL pointer in nilfs_##name##_attr_release nilfs2: fix memory leak in nilfs_sysfs_create_device_group trap: cleanup trap_init() init: move usermodehelper_enable() to populate_rootfs() ...
-rw-r--r--Documentation/admin-guide/mm/damon/index.rst15
-rw-r--r--Documentation/admin-guide/mm/damon/start.rst114
-rw-r--r--Documentation/admin-guide/mm/damon/usage.rst112
-rw-r--r--Documentation/admin-guide/mm/index.rst1
-rw-r--r--Documentation/admin-guide/mm/memory-hotplug.rst800
-rw-r--r--Documentation/dev-tools/kfence.rst98
-rw-r--r--Documentation/kbuild/llvm.rst5
-rw-r--r--Documentation/vm/damon/api.rst20
-rw-r--r--Documentation/vm/damon/design.rst166
-rw-r--r--Documentation/vm/damon/faq.rst51
-rw-r--r--Documentation/vm/damon/index.rst30
-rw-r--r--Documentation/vm/index.rst1
-rw-r--r--MAINTAINERS15
-rw-r--r--arch/Kconfig2
-rw-r--r--arch/alpha/include/asm/agp.h4
-rw-r--r--arch/alpha/kernel/pci-sysfs.c12
-rw-r--r--arch/arc/kernel/traps.c5
-rw-r--r--arch/arm/configs/dove_defconfig1
-rw-r--r--arch/arm/configs/pxa_defconfig1
-rw-r--r--arch/arm/kernel/traps.c5
-rw-r--r--arch/arm64/mm/mmu.c3
-rw-r--r--arch/h8300/kernel/traps.c4
-rw-r--r--arch/hexagon/kernel/traps.c4
-rw-r--r--arch/ia64/mm/init.c3
-rw-r--r--arch/mips/configs/lemote2f_defconfig1
-rw-r--r--arch/mips/configs/pic32mzda_defconfig1
-rw-r--r--arch/mips/configs/rt305x_defconfig1
-rw-r--r--arch/mips/configs/xway_defconfig1
-rw-r--r--arch/nds32/kernel/traps.c5
-rw-r--r--arch/nios2/kernel/traps.c5
-rw-r--r--arch/openrisc/kernel/traps.c5
-rw-r--r--arch/parisc/configs/generic-32bit_defconfig1
-rw-r--r--arch/parisc/kernel/traps.c4
-rw-r--r--arch/powerpc/kernel/traps.c5
-rw-r--r--arch/powerpc/mm/mem.c3
-rw-r--r--arch/powerpc/platforms/pseries/hotplug-memory.c9
-rw-r--r--arch/riscv/Kconfig2
-rw-r--r--arch/riscv/kernel/traps.c5
-rw-r--r--arch/s390/mm/init.c3
-rw-r--r--arch/sh/mm/init.c3
-rw-r--r--arch/um/kernel/trap.c4
-rw-r--r--arch/x86/configs/i386_defconfig1
-rw-r--r--arch/x86/configs/x86_64_defconfig1
-rw-r--r--arch/x86/mm/init_32.c3
-rw-r--r--arch/x86/mm/init_64.c3
-rw-r--r--drivers/acpi/acpi_memhotplug.c46
-rw-r--r--drivers/base/memory.c225
-rw-r--r--drivers/base/node.c2
-rw-r--r--drivers/dax/kmem.c43
-rw-r--r--drivers/devfreq/devfreq.c2
-rw-r--r--drivers/hwmon/mr75203.c2
-rw-r--r--drivers/iio/common/hid-sensors/hid-sensor-attributes.c3
-rw-r--r--drivers/iio/light/as73211.c3
-rw-r--r--drivers/media/i2c/ov02a10.c2
-rw-r--r--drivers/mtd/nand/raw/intel-nand-controller.c2
-rw-r--r--drivers/phy/st/phy-stm32-usbphyc.c2
-rw-r--r--drivers/thermal/devfreq_cooling.c2
-rw-r--r--drivers/virtio/virtio_mem.c26
-rw-r--r--fs/coredump.c15
-rw-r--r--fs/eventpoll.c18
-rw-r--r--fs/nilfs2/sysfs.c26
-rw-r--r--fs/nilfs2/the_nilfs.c9
-rw-r--r--fs/proc/array.c18
-rw-r--r--fs/proc/base.c5
-rw-r--r--include/asm-generic/early_ioremap.h6
-rw-r--r--include/linux/damon.h268
-rw-r--r--include/linux/highmem-internal.h27
-rw-r--r--include/linux/memory.h55
-rw-r--r--include/linux/memory_hotplug.h34
-rw-r--r--include/linux/mmzone.h19
-rw-r--r--include/linux/once.h2
-rw-r--r--include/linux/page-flags.h8
-rw-r--r--include/linux/page_ext.h2
-rw-r--r--include/linux/page_idle.h6
-rw-r--r--include/linux/pagemap.h7
-rw-r--r--include/linux/sched/user.h3
-rw-r--r--include/linux/threads.h2
-rw-r--r--include/linux/units.h10
-rw-r--r--include/linux/vmalloc.h3
-rw-r--r--include/trace/events/damon.h43
-rw-r--r--include/trace/events/mmflags.h2
-rw-r--r--include/trace/events/page_ref.h4
-rw-r--r--init/initramfs.c2
-rw-r--r--init/main.c3
-rw-r--r--init/noinitramfs.c2
-rw-r--r--ipc/util.c16
-rw-r--r--kernel/acct.c2
-rw-r--r--kernel/fork.c2
-rw-r--r--kernel/profile.c21
-rw-r--r--kernel/sys.c7
-rw-r--r--kernel/user.c25
-rw-r--r--lib/Kconfig.debug9
-rw-r--r--lib/dump_stack.c3
-rw-r--r--lib/iov_iter.c8
-rw-r--r--lib/math/Kconfig2
-rw-r--r--lib/math/rational.c3
-rw-r--r--lib/test_printf.c2
-rw-r--r--lib/test_sort.c40
-rw-r--r--lib/vsprintf.c2
-rw-r--r--mm/Kconfig15
-rw-r--r--mm/Makefile4
-rw-r--r--mm/compaction.c20
-rw-r--r--mm/damon/Kconfig68
-rw-r--r--mm/damon/Makefile5
-rw-r--r--mm/damon/core-test.h253
-rw-r--r--mm/damon/core.c720
-rw-r--r--mm/damon/dbgfs-test.h126
-rw-r--r--mm/damon/dbgfs.c623
-rw-r--r--mm/damon/vaddr-test.h329
-rw-r--r--mm/damon/vaddr.c672
-rw-r--r--mm/early_ioremap.c5
-rw-r--r--mm/highmem.c2
-rw-r--r--mm/ioremap.c25
-rw-r--r--mm/kfence/core.c3
-rw-r--r--mm/kfence/kfence.h2
-rw-r--r--mm/kfence/kfence_test.c3
-rw-r--r--mm/kfence/report.c19
-rw-r--r--mm/kmemleak.c2
-rw-r--r--mm/memory_hotplug.c374
-rw-r--r--mm/memremap.c5
-rw-r--r--mm/page_alloc.c27
-rw-r--r--mm/page_ext.c12
-rw-r--r--mm/page_idle.c10
-rw-r--r--mm/page_isolation.c7
-rw-r--r--mm/page_owner.c14
-rw-r--r--mm/percpu.c1
-rw-r--r--mm/rmap.c6
-rw-r--r--mm/secretmem.c9
-rw-r--r--mm/vmalloc.c22
-rw-r--r--mm/workingset.c2
-rwxr-xr-xscripts/check_extable.sh2
-rwxr-xr-xscripts/checkpatch.pl93
-rw-r--r--tools/include/linux/bitmap.h4
-rw-r--r--tools/perf/bench/find-bit-bench.c2
-rw-r--r--tools/perf/builtin-c2c.c6
-rw-r--r--tools/perf/builtin-record.c2
-rw-r--r--tools/perf/tests/bitmap.c2
-rw-r--r--tools/perf/tests/mem2node.c2
-rw-r--r--tools/perf/util/affinity.c4
-rw-r--r--tools/perf/util/header.c4
-rw-r--r--tools/perf/util/metricgroup.c2
-rw-r--r--tools/perf/util/mmap.c4
-rw-r--r--tools/testing/selftests/damon/Makefile7
-rw-r--r--tools/testing/selftests/damon/_chk_dependency.sh28
-rw-r--r--tools/testing/selftests/damon/debugfs_attrs.sh75
-rw-r--r--tools/testing/selftests/kvm/dirty_log_perf_test.c2
-rw-r--r--tools/testing/selftests/kvm/dirty_log_test.c4
-rw-r--r--tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c2
-rw-r--r--tools/testing/selftests/memfd/memfd_test.c2
149 files changed, 5341 insertions, 930 deletions
diff --git a/Documentation/admin-guide/mm/damon/index.rst b/Documentation/admin-guide/mm/damon/index.rst
new file mode 100644
index 000000000000..8c5dde3a5754
--- /dev/null
+++ b/Documentation/admin-guide/mm/damon/index.rst
@@ -0,0 +1,15 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+========================
+Monitoring Data Accesses
+========================
+
+:doc:`DAMON </vm/damon/index>` allows light-weight data access monitoring.
+Using DAMON, users can analyze the memory access patterns of their systems and
+optimize those.
+
+.. toctree::
+ :maxdepth: 2
+
+ start
+ usage
diff --git a/Documentation/admin-guide/mm/damon/start.rst b/Documentation/admin-guide/mm/damon/start.rst
new file mode 100644
index 000000000000..d5eb89a8fc38
--- /dev/null
+++ b/Documentation/admin-guide/mm/damon/start.rst
@@ -0,0 +1,114 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===============
+Getting Started
+===============
+
+This document briefly describes how you can use DAMON by demonstrating its
+default user space tool. Please note that this document describes only a part
+of its features for brevity. Please refer to :doc:`usage` for more details.
+
+
+TL; DR
+======
+
+Follow the commands below to monitor and visualize the memory access pattern of
+your workload. ::
+
+ # # build the kernel with CONFIG_DAMON_*=y, install it, and reboot
+ # mount -t debugfs none /sys/kernel/debug/
+ # git clone https://github.com/awslabs/damo
+ # ./damo/damo record $(pidof <your workload>)
+ # ./damo/damo report heat --plot_ascii
+
+The final command draws the access heatmap of ``<your workload>``. The heatmap
+shows which memory region (x-axis) is accessed when (y-axis) and how frequently
+(number; the higher the more accesses have been observed). ::
+
+ 111111111111111111111111111111111111111111111111111111110000
+ 111121111111111111111111111111211111111111111111111111110000
+ 000000000000000000000000000000000000000000000000001555552000
+ 000000000000000000000000000000000000000000000222223555552000
+ 000000000000000000000000000000000000000011111677775000000000
+ 000000000000000000000000000000000000000488888000000000000000
+ 000000000000000000000000000000000177888400000000000000000000
+ 000000000000000000000000000046666522222100000000000000000000
+ 000000000000000000000014444344444300000000000000000000000000
+ 000000000000000002222245555510000000000000000000000000000000
+ # access_frequency: 0 1 2 3 4 5 6 7 8 9
+ # x-axis: space (140286319947776-140286426374096: 101.496 MiB)
+ # y-axis: time (605442256436361-605479951866441: 37.695430s)
+ # resolution: 60x10 (1.692 MiB and 3.770s for each character)
+
+
+Prerequisites
+=============
+
+Kernel
+------
+
+You should first ensure your system is running on a kernel built with
+``CONFIG_DAMON_*=y``.
+
+
+User Space Tool
+---------------
+
+For the demonstration, we will use the default user space tool for DAMON,
+called DAMON Operator (DAMO). It is available at
+https://github.com/awslabs/damo. The examples below assume that ``damo`` is on
+your ``$PATH``. It's not mandatory, though.
+
+Because DAMO is using the debugfs interface (refer to :doc:`usage` for the
+detail) of DAMON, you should ensure debugfs is mounted. Mount it manually as
+below::
+
+ # mount -t debugfs none /sys/kernel/debug/
+
+or append the following line to your ``/etc/fstab`` file so that your system
+can automatically mount debugfs upon booting::
+
+ debugfs /sys/kernel/debug debugfs defaults 0 0
+
+
+Recording Data Access Patterns
+==============================
+
+The commands below record the memory access patterns of a program and save the
+monitoring results to a file. ::
+
+ $ git clone https://github.com/sjp38/masim
+ $ cd masim; make; ./masim ./configs/zigzag.cfg &
+ $ sudo damo record -o damon.data $(pidof masim)
+
+The first two lines of the commands download an artificial memory access
+generator program and run it in the background. The generator will repeatedly
+access two 100 MiB sized memory regions one by one. You can substitute this
+with your real workload. The last line asks ``damo`` to record the access
+pattern in the ``damon.data`` file.
+
+
+Visualizing Recorded Patterns
+=============================
+
+The following three commands visualize the recorded access patterns and save
+the results as separate image files. ::
+
+ $ damo report heats --heatmap access_pattern_heatmap.png
+ $ damo report wss --range 0 101 1 --plot wss_dist.png
+ $ damo report wss --range 0 101 1 --sortby time --plot wss_chron_change.png
+
+- ``access_pattern_heatmap.png`` will visualize the data access pattern in a
+ heatmap, showing which memory region (y-axis) got accessed when (x-axis)
+ and how frequently (color).
+- ``wss_dist.png`` will show the distribution of the working set size.
+- ``wss_chron_change.png`` will show how the working set size has
+ chronologically changed.
+
+You can view the visualizations of this example workload at [1]_.
+Visualizations of other realistic workloads are available at [2]_ [3]_ [4]_.
+
+.. [1] https://damonitor.github.io/doc/html/v17/admin-guide/mm/damon/start.html#visualizing-recorded-patterns
+.. [2] https://damonitor.github.io/test/result/visual/latest/rec.heatmap.1.png.html
+.. [3] https://damonitor.github.io/test/result/visual/latest/rec.wss_sz.png.html
+.. [4] https://damonitor.github.io/test/result/visual/latest/rec.wss_time.png.html
diff --git a/Documentation/admin-guide/mm/damon/usage.rst b/Documentation/admin-guide/mm/damon/usage.rst
new file mode 100644
index 000000000000..a72cda374aba
--- /dev/null
+++ b/Documentation/admin-guide/mm/damon/usage.rst
@@ -0,0 +1,112 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===============
+Detailed Usages
+===============
+
+DAMON provides below three interfaces for different users.
+
+- *DAMON user space tool.*
+ This is for privileged people such as system administrators who want a
+ just-working human-friendly interface. Using this, users can use the DAMON’s
+ major features in a human-friendly way. It may not be highly tuned for
+ special cases, though. It supports only virtual address spaces monitoring.
+- *debugfs interface.*
+ This is for privileged user space programmers who want more optimized use of
+ DAMON. Using this, users can use DAMON’s major features by reading
+ from and writing to special debugfs files. Therefore, you can write and use
+ your personalized DAMON debugfs wrapper programs that reads/writes the
+ debugfs files instead of you. The DAMON user space tool is also a reference
+ implementation of such programs. It supports only virtual address spaces
+ monitoring.
+- *Kernel Space Programming Interface.*
+ This is for kernel space programmers. Using this, users can utilize every
+ feature of DAMON most flexibly and efficiently by writing kernel space
+ DAMON application programs for you. You can even extend DAMON for various
+ address spaces.
+
+Nevertheless, you could write your own user space tool using the debugfs
+interface. A reference implementation is available at
+https://github.com/awslabs/damo. If you are a kernel programmer, you could
+refer to :doc:`/vm/damon/api` for the kernel space programming interface. For
+the reason, this document describes only the debugfs interface
+
+debugfs Interface
+=================
+
+DAMON exports three files, ``attrs``, ``target_ids``, and ``monitor_on`` under
+its debugfs directory, ``<debugfs>/damon/``.
+
+
+Attributes
+----------
+
+Users can get and set the ``sampling interval``, ``aggregation interval``,
+``regions update interval``, and min/max number of monitoring target regions by
+reading from and writing to the ``attrs`` file. To know about the monitoring
+attributes in detail, please refer to the :doc:`/vm/damon/design`. For
+example, below commands set those values to 5 ms, 100 ms, 1,000 ms, 10 and
+1000, and then check it again::
+
+ # cd <debugfs>/damon
+ # echo 5000 100000 1000000 10 1000 > attrs
+ # cat attrs
+ 5000 100000 1000000 10 1000
+
+
+Target IDs
+----------
+
+Some types of address spaces supports multiple monitoring target. For example,
+the virtual memory address spaces monitoring can have multiple processes as the
+monitoring targets. Users can set the targets by writing relevant id values of
+the targets to, and get the ids of the current targets by reading from the
+``target_ids`` file. In case of the virtual address spaces monitoring, the
+values should be pids of the monitoring target processes. For example, below
+commands set processes having pids 42 and 4242 as the monitoring targets and
+check it again::
+
+ # cd <debugfs>/damon
+ # echo 42 4242 > target_ids
+ # cat target_ids
+ 42 4242
+
+Note that setting the target ids doesn't start the monitoring.
+
+
+Turning On/Off
+--------------
+
+Setting the files as described above doesn't incur effect unless you explicitly
+start the monitoring. You can start, stop, and check the current status of the
+monitoring by writing to and reading from the ``monitor_on`` file. Writing
+``on`` to the file starts the monitoring of the targets with the attributes.
+Writing ``off`` to the file stops those. DAMON also stops if every target
+process is terminated. Below example commands turn on, off, and check the
+status of DAMON::
+
+ # cd <debugfs>/damon
+ # echo on > monitor_on
+ # echo off > monitor_on
+ # cat monitor_on
+ off
+
+Please note that you cannot write to the above-mentioned debugfs files while
+the monitoring is turned on. If you write to the files while DAMON is running,
+an error code such as ``-EBUSY`` will be returned.
+
+
+Tracepoint for Monitoring Results
+=================================
+
+DAMON provides the monitoring results via a tracepoint,
+``damon:damon_aggregated``. While the monitoring is turned on, you could
+record the tracepoint events and show results using tracepoint supporting tools
+like ``perf``. For example::
+
+ # echo on > monitor_on
+ # perf record -e damon:damon_aggregated &
+ # sleep 5
+ # kill 9 $(pidof perf)
+ # echo off > monitor_on
+ # perf script
diff --git a/Documentation/admin-guide/mm/index.rst b/Documentation/admin-guide/mm/index.rst
index 4b14d8b50e9e..cbd19d5e625f 100644
--- a/Documentation/admin-guide/mm/index.rst
+++ b/Documentation/admin-guide/mm/index.rst
@@ -27,6 +27,7 @@ the Linux memory management.
concepts
cma_debugfs
+ damon/index
hugetlbpage
idle_page_tracking
ksm
diff --git a/Documentation/admin-guide/mm/memory-hotplug.rst b/Documentation/admin-guide/mm/memory-hotplug.rst
index c6bae2d77160..03dfbc925252 100644
--- a/Documentation/admin-guide/mm/memory-hotplug.rst
+++ b/Documentation/admin-guide/mm/memory-hotplug.rst
@@ -1,466 +1,576 @@
.. _admin_guide_memory_hotplug:
-==============
-Memory Hotplug
-==============
+==================
+Memory Hot(Un)Plug
+==================
-:Created: Jul 28 2007
-:Updated: Add some details about locking internals: Aug 20 2018
-
-This document is about memory hotplug including how-to-use and current status.
-Because Memory Hotplug is still under development, contents of this text will
-be changed often.
+This document describes generic Linux support for memory hot(un)plug with
+a focus on System RAM, including ZONE_MOVABLE support.
.. contents:: :local:
-.. note::
+Introduction
+============
- (1) x86_64's has special implementation for memory hotplug.
- This text does not describe it.
- (2) This text assumes that sysfs is mounted at ``/sys``.
+Memory hot(un)plug allows for increasing and decreasing the size of physical
+memory available to a machine at runtime. In the simplest case, it consists of
+physically plugging or unplugging a DIMM at runtime, coordinated with the
+operating system.
+Memory hot(un)plug is used for various purposes:
-Introduction
-============
+- The physical memory available to a machine can be adjusted at runtime, up- or
+ downgrading the memory capacity. This dynamic memory resizing, sometimes
+ referred to as "capacity on demand", is frequently used with virtual machines
+ and logical partitions.
+
+- Replacing hardware, such as DIMMs or whole NUMA nodes, without downtime. One
+ example is replacing failing memory modules.
-Purpose of memory hotplug
--------------------------
+- Reducing energy consumption either by physically unplugging memory modules or
+ by logically unplugging (parts of) memory modules from Linux.
-Memory Hotplug allows users to increase/decrease the amount of memory.
-Generally, there are two purposes.
+Further, the basic memory hot(un)plug infrastructure in Linux is nowadays also
+used to expose persistent memory, other performance-differentiated memory and
+reserved memory regions as ordinary system RAM to Linux.
-(A) For changing the amount of memory.
- This is to allow a feature like capacity on demand.
-(B) For installing/removing DIMMs or NUMA-nodes physically.
- This is to exchange DIMMs/NUMA-nodes, reduce power consumption, etc.
+Linux only supports memory hot(un)plug on selected 64 bit architectures, such as
+x86_64, arm64, ppc64, s390x and ia64.
-(A) is required by highly virtualized environments and (B) is required by
-hardware which supports memory power management.
+Memory Hot(Un)Plug Granularity
+------------------------------
-Linux memory hotplug is designed for both purpose.
+Memory hot(un)plug in Linux uses the SPARSEMEM memory model, which divides the
+physical memory address space into chunks of the same size: memory sections. The
+size of a memory section is architecture dependent. For example, x86_64 uses
+128 MiB and ppc64 uses 16 MiB.
-Phases of memory hotplug
+Memory sections are combined into chunks referred to as "memory blocks". The
+size of a memory block is architecture dependent and corresponds to the smallest
+granularity that can be hot(un)plugged. The default size of a memory block is
+the same as memory section size, unless an architecture specifies otherwise.
+
+All memory blocks have the same size.
+
+Phases of Memory Hotplug
------------------------
-There are 2 phases in Memory Hotplug:
+Memory hotplug consists of two phases:
- 1) Physical Memory Hotplug phase
- 2) Logical Memory Hotplug phase.
+(1) Adding the memory to Linux
+(2) Onlining memory blocks
-The First phase is to communicate hardware/firmware and make/erase
-environment for hotplugged memory. Basically, this phase is necessary
-for the purpose (B), but this is good phase for communication between
-highly virtualized environments too.
+In the first phase, metadata, such as the memory map ("memmap") and page tables
+for the direct mapping, is allocated and initialized, and memory blocks are
+created; the latter also creates sysfs files for managing newly created memory
+blocks.
-When memory is hotplugged, the kernel recognizes new memory, makes new memory
-management tables, and makes sysfs files for new memory's operation.
+In the second phase, added memory is exposed to the page allocator. After this
+phase, the memory is visible in memory statistics, such as free and total
+memory, of the system.
-If firmware supports notification of connection of new memory to OS,
-this phase is triggered automatically. ACPI can notify this event. If not,
-"probe" operation by system administration is used instead.
-(see :ref:`memory_hotplug_physical_mem`).
+Phases of Memory Hotunplug
+--------------------------
-Logical Memory Hotplug phase is to change memory state into
-available/unavailable for users. Amount of memory from user's view is
-changed by this phase. The kernel makes all memory in it as free pages
-when a memory range is available.
+Memory hotunplug consists of two phases:
-In this document, this phase is described as online/offline.
+(1) Offlining memory blocks
+(2) Removing the memory from Linux
-Logical Memory Hotplug phase is triggered by write of sysfs file by system
-administrator. For the hot-add case, it must be executed after Physical Hotplug
-phase by hand.
-(However, if you writes udev's hotplug scripts for memory hotplug, these
-phases can be execute in seamless way.)
+In the fist phase, memory is "hidden" from the page allocator again, for
+example, by migrating busy memory to other memory locations and removing all
+relevant free pages from the page allocator After this phase, the memory is no
+longer visible in memory statistics of the system.
-Unit of Memory online/offline operation
----------------------------------------
+In the second phase, the memory blocks are removed and metadata is freed.
-Memory hotplug uses SPARSEMEM memory model which allows memory to be divided
-into chunks of the same size. These chunks are called "sections". The size of
-a memory section is architecture dependent. For example, power uses 16MiB, ia64
-uses 1GiB.
+Memory Hotplug Notifications
+============================
-Memory sections are combined into chunks referred to as "memory blocks". The
-size of a memory block is architecture dependent and represents the logical
-unit upon which memory online/offline operations are to be performed. The
-default size of a memory block is the same as memory section size unless an
-architecture specifies otherwise. (see :ref:`memory_hotplug_sysfs_files`.)
+There are various ways how Linux is notified about memory hotplug events such
+that it can start adding hotplugged memory. This description is limited to
+systems that support ACPI; mechanisms specific to other firmware interfaces or
+virtual machines are not described.
-To determine the size (in bytes) of a memory block please read this file::
+ACPI Notifications
+------------------
- /sys/devices/system/memory/block_size_bytes
+Platforms that support ACPI, such as x86_64, can support memory hotplug
+notifications via ACPI.
-Kernel Configuration
-====================
+In general, a firmware supporting memory hotplug defines a memory class object
+HID "PNP0C80". When notified about hotplug of a new memory device, the ACPI
+driver will hotplug the memory to Linux.
-To use memory hotplug feature, kernel must be compiled with following
-config options.
+If the firmware supports hotplug of NUMA nodes, it defines an object _HID
+"ACPI0004", "PNP0A05", or "PNP0A06". When notified about an hotplug event, all
+assigned memory devices are added to Linux by the ACPI driver.
-- For all memory hotplug:
- - Memory model -> Sparse Memory (``CONFIG_SPARSEMEM``)
- - Allow for memory hot-add (``CONFIG_MEMORY_HOTPLUG``)
+Similarly, Linux can be notified about requests to hotunplug a memory device or
+a NUMA node via ACPI. The ACPI driver will try offlining all relevant memory
+blocks, and, if successful, hotunplug the memory from Linux.
-- To enable memory removal, the following are also necessary:
- - Allow for memory hot remove (``CONFIG_MEMORY_HOTREMOVE``)
- - Page Migration (``CONFIG_MIGRATION``)
+Manual Probing
+--------------
-- For ACPI memory hotplug, the following are also necessary:
- - Memory hotplug (under ACPI Support menu) (``CONFIG_ACPI_HOTPLUG_MEMORY``)
- - This option can be kernel module.
+On some architectures, the firmware may not be able to notify the operating
+system about a memory hotplug event. Instead, the memory has to be manually
+probed from user space.
-- As a related configuration, if your box has a feature of NUMA-node hotplug
- via ACPI, then this option is necessary too.
+The probe interface is located at::
- - ACPI0004,PNP0A05 and PNP0A06 Container Driver (under ACPI Support menu)
- (``CONFIG_ACPI_CONTAINER``).
+ /sys/devices/system/memory/probe
- This option can be kernel module too.
+Only complete memory blocks can be probed. Individual memory blocks are probed
+by providing the physical start address of the memory block::
+ % echo addr > /sys/devices/system/memory/probe
-.. _memory_hotplug_sysfs_files:
+Which results in a memory block for the range [addr, addr + memory_block_size)
+being created.
-sysfs files for memory hotplug
-==============================
+.. note::
-All memory blocks have their device information in sysfs. Each memory block
-is described under ``/sys/devices/system/memory`` as::
+ Using the probe interface is discouraged as it is easy to crash the kernel,
+ because Linux cannot validate user input; this interface might be removed in
+ the future.
- /sys/devices/system/memory/memoryXXX
+Onlining and Offlining Memory Blocks
+====================================
-where XXX is the memory block id.
+After a memory block has been created, Linux has to be instructed to actually
+make use of that memory: the memory block has to be "online".
-For the memory block covered by the sysfs directory. It is expected that all
-memory sections in this range are present and no memory holes exist in the
-range. Currently there is no way to determine if there is a memory hole, but
-the existence of one should not affect the hotplug capabilities of the memory
-block.
+Before a memory block can be removed, Linux has to stop using any memory part of
+the memory block: the memory block has to be "offlined".
-For example, assume 1GiB memory block size. A device for a memory starting at
-0x100000000 is ``/sys/device/system/memory/memory4``::
+The Linux kernel can be configured to automatically online added memory blocks
+and drivers automatically trigger offlining of memory blocks when trying
+hotunplug of memory. Memory blocks can only be removed once offlining succeeded
+and drivers may trigger offlining of memory blocks when attempting hotunplug of
+memory.
- (0x100000000 / 1Gib = 4)
+Onlining Memory Blocks Manually
+-------------------------------
-This device covers address range [0x100000000 ... 0x140000000)
+If auto-onlining of memory blocks isn't enabled, user-space has to manually
+trigger onlining of memory blocks. Often, udev rules are used to automate this
+task in user space.
-Under each memory block, you can see 5 files:
+Onlining of a memory block can be triggered via::
-- ``/sys/devices/system/memory/memoryXXX/phys_index``
-- ``/sys/devices/system/memory/memoryXXX/phys_device``
-- ``/sys/devices/system/memory/memoryXXX/state``
-- ``/sys/devices/system/memory/memoryXXX/removable``
-- ``/sys/devices/system/memory/memoryXXX/valid_zones``
+ % echo online > /sys/devices/system/memory/memoryXXX/state
-=================== ============================================================
-``phys_index`` read-only and contains memory block id, same as XXX.
-``state`` read-write
+Or alternatively::
- - at read: contains online/offline state of memory.
- - at write: user can specify "online_kernel",
+ % echo 1 > /sys/devices/system/memory/memoryXXX/online
- "online_movable", "online", "offline" command
- which will be performed on all sections in the block.
-``phys_device`` read-only: legacy interface only ever used on s390x to
- expose the covered storage increment.
-``removable`` read-only: legacy interface that indicated whether a memory
- block was likely to be offlineable or not. Newer kernel
- versions return "1" if and only if the kernel supports
- memory offlining.
-``valid_zones`` read-only: designed to show by which zone memory provided by
- a memory block is managed, and to show by which zone memory
- provided by an offline memory block could be managed when
- onlining.
-
- The first column shows it`s default zone.
-
- "memory6/valid_zones: Normal Movable" shows this memoryblock
- can be onlined to ZONE_NORMAL by default and to ZONE_MOVABLE
- by online_movable.
-
- "memory7/valid_zones: Movable Normal" shows this memoryblock
- can be onlined to ZONE_MOVABLE by default and to ZONE_NORMAL
- by online_kernel.
-=================== ============================================================
+The kernel will select the target zone automatically, usually defaulting to
+``ZONE_NORMAL`` unless ``movablecore=1`` has been specified on the kernel
+command line or if the memory block would intersect the ZONE_MOVABLE already.
-.. note::
+One can explicitly request to associate an offline memory block with
+ZONE_MOVABLE by::
- These directories/files appear after physical memory hotplug phase.
+ % echo online_movable > /sys/devices/system/memory/memoryXXX/state
-If CONFIG_NUMA is enabled the memoryXXX/ directories can also be accessed
-via symbolic links located in the ``/sys/devices/system/node/node*`` directories.
+Or one can explicitly request a kernel zone (usually ZONE_NORMAL) by::
-For example::
+ % echo online_kernel > /sys/devices/system/memory/memoryXXX/state
- /sys/devices/system/node/node0/memory9 -> ../../memory/memory9
+In any case, if onlining succeeds, the state of the memory block is changed to
+be "online". If it fails, the state of the memory block will remain unchanged
+and the above commands will fail.
-A backlink will also be created::
+Onlining Memory Blocks Automatically
+------------------------------------
- /sys/devices/system/memory/memory9/node0 -> ../../node/node0
+The kernel can be configured to try auto-onlining of newly added memory blocks.
+If this feature is disabled, the memory blocks will stay offline until
+explicitly onlined from user space.
-.. _memory_hotplug_physical_mem:
+The configured auto-online behavior can be observed via::
-Physical memory hot-add phase
-=============================
+ % cat /sys/devices/system/memory/auto_online_blocks
-Hardware(Firmware) Support
---------------------------
+Auto-onlining can be enabled by writing ``online``, ``online_kernel`` or
+``online_movable`` to that file, like::
-On x86_64/ia64 platform, memory hotplug by ACPI is supported.
+ % echo online > /sys/devices/system/memory/auto_online_blocks
-In general, the firmware (ACPI) which supports memory hotplug defines
-memory class object of _HID "PNP0C80". When a notify is asserted to PNP0C80,
-Linux's ACPI handler does hot-add memory to the system and calls a hotplug udev
-script. This will be done automatically.
+Modifying the auto-online behavior will only affect all subsequently added
+memory blocks only.
-But scripts for memory hotplug are not contained in generic udev package(now).
-You may have to write it by yourself or online/offline memory by hand.
-Please see :ref:`memory_hotplug_how_to_online_memory` and
-:ref:`memory_hotplug_how_to_offline_memory`.
+.. note::
-If firmware supports NUMA-node hotplug, and defines an object _HID "ACPI0004",
-"PNP0A05", or "PNP0A06", notification is asserted to it, and ACPI handler
-calls hotplug code for all of objects which are defined in it.
-If memory device is found, memory hotplug code will be called.
+ In corner cases, auto-onlining can fail. The kernel won't retry. Note that
+ auto-onlining is not expected to fail in default configurations.
-Notify memory hot-add event by hand
------------------------------------
+.. note::
-On some architectures, the firmware may not notify the kernel of a memory
-hotplug event. Therefore, the memory "probe" interface is supported to
-explicitly notify the kernel. This interface depends on
-CONFIG_ARCH_MEMORY_PROBE and can be configured on powerpc, sh, and x86
-if hotplug is supported, although for x86 this should be handled by ACPI
-notification.
+ DLPAR on ppc64 ignores the ``offline`` setting and will still online added
+ memory blocks; if onlining fails, memory blocks are removed again.
-Probe interface is located at::
+Offlining Memory Blocks
+-----------------------
- /sys/devices/system/memory/probe
+In the current implementation, Linux's memory offlining will try migrating all
+movable pages off the affected memory block. As most kernel allocations, such as
+page tables, are unmovable, page migration can fail and, therefore, inhibit
+memory offlining from succeeding.
-You can tell the physical address of new memory to the kernel by::
+Having the memory provided by memory block managed by ZONE_MOVABLE significantly
+increases memory offlining reliability; still, memory offlining can fail in
+some corner cases.
- % echo start_address_of_new_memory > /sys/devices/system/memory/probe
+Further, memory offlining might retry for a long time (or even forever), until
+aborted by the user.
-Then, [start_address_of_new_memory, start_address_of_new_memory +
-memory_block_size] memory range is hot-added. In this case, hotplug script is
-not called (in current implementation). You'll have to online memory by
-yourself. Please see :ref:`memory_hotplug_how_to_online_memory`.
+Offlining of a memory block can be triggered via::
-Logical Memory hot-add phase
-============================
+ % echo offline > /sys/devices/system/memory/memoryXXX/state
-State of memory
----------------
+Or alternatively::
-To see (online/offline) state of a memory block, read 'state' file::
+ % echo 0 > /sys/devices/system/memory/memoryXXX/online
- % cat /sys/device/system/memory/memoryXXX/state
+If offlining succeeds, the state of the memory block is changed to be "offline".
+If it fails, the state of the memory block will remain unchanged and the above
+commands will fail, for example, via::
+ bash: echo: write error: Device or resource busy
-- If the memory block is online, you'll read "online".
-- If the memory block is offline, you'll read "offline".
+or via::
+ bash: echo: write error: Invalid argument
-.. _memory_hotplug_how_to_online_memory:
+Observing the State of Memory Blocks
+------------------------------------
-How to online memory
---------------------
+The state (online/offline/going-offline) of a memory block can be observed
+either via::
-When the memory is hot-added, the kernel decides whether or not to "online"
-it according to the policy which can be read from "auto_online_blocks" file::
+ % cat /sys/device/system/memory/memoryXXX/state
- % cat /sys/devices/system/memory/auto_online_blocks
+Or alternatively (1/0) via::
-The default depends on the CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE kernel config
-option. If it is disabled the default is "offline" which means the newly added
-memory is not in a ready-to-use state and you have to "online" the newly added
-memory blocks manually. Automatic onlining can be requested by writing "online"
-to "auto_online_blocks" file::
+ % cat /sys/device/system/memory/memoryXXX/online
- % echo online > /sys/devices/system/memory/auto_online_blocks
+For an online memory block, the managing zone can be observed via::
-This sets a global policy and impacts all memory blocks that will subsequently
-be hotplugged. Currently offline blocks keep their state. It is possible, under
-certain circumstances, that some memory blocks will be added but will fail to
-online. User space tools can check their "state" files
-(``/sys/devices/system/memory/memoryXXX/state``) and try to online them manually.
+ % cat /sys/device/system/memory/memoryXXX/valid_zones
-If the automatic onlining wasn't requested, failed, or some memory block was
-offlined it is possible to change the individual block's state by writing to the
-"state" file::
+Configuring Memory Hot(Un)Plug
+==============================
- % echo online > /sys/devices/system/memory/memoryXXX/state
+There are various ways how system administrators can configure memory
+hot(un)plug and interact with memory blocks, especially, to online them.
-This onlining will not change the ZONE type of the target memory block,
-If the memory block doesn't belong to any zone an appropriate kernel zone
-(usually ZONE_NORMAL) will be used unless movable_node kernel command line
-option is specified when ZONE_MOVABLE will be used.
+Memory Hot(Un)Plug Configuration via Sysfs
+------------------------------------------
-You can explicitly request to associate it with ZONE_MOVABLE by::
+Some memory hot(un)plug properties can be configured or inspected via sysfs in::
- % echo online_movable > /sys/devices/system/memory/memoryXXX/state
+ /sys/devices/system/memory/
-.. note:: current limit: this memory block must be adjacent to ZONE_MOVABLE
+The following files are currently defined:
-Or you can explicitly request a kernel zone (usually ZONE_NORMAL) by::
+====================== =========================================================
+``auto_online_blocks`` read-write: set or get the default state of new memory
+ blocks; configure auto-onlining.
- % echo online_kernel > /sys/devices/system/memory/memoryXXX/state
+ The default value depends on the
+ CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE kernel configuration
+ option.
-.. note:: current limit: this memory block must be adjacent to ZONE_NORMAL
+ See the ``state`` property of memory blocks for details.
+``block_size_bytes`` read-only: the size in bytes of a memory block.
+``probe`` write-only: add (probe) selected memory blocks manually
+ from user space by supplying the physical start address.
-An explicit zone onlining can fail (e.g. when the range is already within
-and existing and incompatible zone already).
+ Availability depends on the CONFIG_ARCH_MEMORY_PROBE
+ kernel configuration option.
+``uevent`` read-write: generic udev file for device subsystems.
+====================== =========================================================
-After this, memory block XXX's state will be 'online' and the amount of
-available memory will be increased.
+.. note::
-This may be changed in future.
+ When the CONFIG_MEMORY_FAILURE kernel configuration option is enabled, two
+ additional files ``hard_offline_page`` and ``soft_offline_page`` are available
+ to trigger hwpoisoning of pages, for example, for testing purposes. Note that
+ this functionality is not really related to memory hot(un)plug or actual
+ offlining of memory blocks.
-Logical memory remove
-=====================
+Memory Block Configuration via Sysfs
+------------------------------------
-Memory offline and ZONE_MOVABLE
--------------------------------
+Each memory block is represented as a memory block device that can be
+onlined or offlined. All memory blocks have their device information located in
+sysfs. Each present memory block is listed under
+``/sys/devices/system/memory`` as::
-Memory offlining is more complicated than memory online. Because memory offline
-has to make the whole memory block be unused, memory offline can fail if
-the memory block includes memory which cannot be freed.
+ /sys/devices/system/memory/memoryXXX
-In general, memory offline can use 2 techniques.
+where XXX is the memory block id; the number of digits is variable.
-(1) reclaim and free all memory in the memory block.
-(2) migrate all pages in the memory block.
+A present memory block indicates that some memory in the range is present;
+however, a memory block might span memory holes. A memory block spanning memory
+holes cannot be offlined.
-In the current implementation, Linux's memory offline uses method (2), freeing
-all pages in the memory block by page migration. But not all pages are
-migratable. Under current Linux, migratable pages are anonymous pages and
-page caches. For offlining a memory block by migration, the kernel has to
-guarantee that the memory block contains only migratable pages.
+For example, assume 1 GiB memory block size. A device for a memory starting at
+0x100000000 is ``/sys/device/system/memory/memory4``::
-Now, a boot option for making a memory block which consists of migratable pages
-is supported. By specifying "kernelcore=" or "movablecore=" boot option, you can
-create ZONE_MOVABLE...a zone which is just used for movable pages.
-(See also Documentation/admin-guide/kernel-parameters.rst)
+ (0x100000000 / 1Gib = 4)
-Assume the system has "TOTAL" amount of memory at boot time, this boot option
-creates ZONE_MOVABLE as following.
+This device covers address range [0x100000000 ... 0x140000000)
-1) When kernelcore=YYYY boot option is used,
- Size of memory not for movable pages (not for offline) is YYYY.
- Size of memory for movable pages (for offline) is TOTAL-YYYY.
+The following files are currently defined:
-2) When movablecore=ZZZZ boot option is used,
- Size of memory not for movable pages (not for offline) is TOTAL - ZZZZ.
- Size of memory for movable pages (for offline) is ZZZZ.
+=================== ============================================================
+``online`` read-write: simplified interface to trigger onlining /
+ offlining and to observe the state of a memory block.
+ When onlining, the zone is selected automatically.
+``phys_device`` read-only: legacy interface only ever used on s390x to
+ expose the covered storage increment.
+``phys_index`` read-only: the memory block id (XXX).
+``removable`` read-only: legacy interface that indicated whether a memory
+ block was likely to be offlineable or not. Nowadays, the
+ kernel return ``1`` if and only if it supports memory
+ offlining.
+``state`` read-write: advanced interface to trigger onlining /
+ offlining and to observe the state of a memory block.
+
+ When writing, ``online``, ``offline``, ``online_kernel`` and
+ ``online_movable`` are supported.
+
+ ``online_movable`` specifies onlining to ZONE_MOVABLE.
+ ``online_kernel`` specifies onlining to the default kernel
+ zone for the memory block, such as ZONE_NORMAL.
+ ``online`` let's the kernel select the zone automatically.
+
+ When reading, ``online``, ``offline`` and ``going-offline``
+ may be returned.
+``uevent`` read-write: generic uevent file for devices.
+``valid_zones`` read-only: when a block is online, shows the zone it
+ belongs to; when a block is offline, shows what zone will
+ manage it when the block will be onlined.
+
+ For online memory blocks, ``DMA``, ``DMA32``, ``Normal``,
+ ``Movable`` and ``none`` may be returned. ``none`` indicates
+ that memory provided by a memory block is managed by
+ multiple zones or spans multiple nodes; such memory blocks
+ cannot be offlined. ``Movable`` indicates ZONE_MOVABLE.
+ Other values indicate a kernel zone.
+
+ For offline memory blocks, the first column shows the
+ zone the kernel would select when onlining the memory block
+ right now without further specifying a zone.
+
+ Availability depends on the CONFIG_MEMORY_HOTREMOVE
+ kernel configuration option.
+=================== ============================================================
.. note::
- Unfortunately, there is no information to show which memory block belongs
- to ZONE_MOVABLE. This is TBD.
+ If the CONFIG_NUMA kernel configuration option is enabled, the memoryXXX/
+ directories can also be accessed via symbolic links located in the
+ ``/sys/devices/system/node/node*`` directories.
+
+ For example::
+
+ /sys/devices/system/node/node0/memory9 -> ../../memory/memory9
+
+ A backlink will also be created::
+
+ /sys/devices/system/memory/memory9/node0 -> ../../node/node0
+
+Command Line Parameters
+-----------------------
+
+Some command line parameters affect memory hot(un)plug handling. The following
+command line parameters are relevant:
+
+======================== =======================================================
+``memhp_default_state`` configure auto-onlining by essentially setting
+ ``/sys/devices/system/memory/auto_online_blocks``.
+``movablecore`` configure automatic zone selection of the kernel. When
+ set, the kernel will default to ZONE_MOVABLE, unless
+ other zones can be kept contiguous.
+======================== =======================================================
+
+Module Parameters
+------------------
- Memory offlining can fail when dissolving a free huge page on ZONE_MOVABLE
- and the feature of freeing unused vmemmap pages associated with each hugetlb
- page is enabled.
+Instead of additional command line parameters or sysfs files, the
+``memory_hotplug`` subsystem now provides a dedicated namespace for module
+parameters. Module parameters can be set via the command line by predicating
+them with ``memory_hotplug.`` such as::
+
+ memory_hotplug.memmap_on_memory=1
+
+and they can be observed (and some even modified at runtime) via::
+
+ /sys/modules/memory_hotplug/parameters/
+
+The following module parameters are currently defined:
+
+======================== =======================================================
+``memmap_on_memory`` read-write: Allocate memory for the memmap from the
+ added memory block itself. Even if enabled, actual
+ support depends on various other system properties and
+ should only be regarded as a hint whether the behavior
+ would be desired.
+
+ While allocating the memmap from the memory block
+ itself makes memory hotplug less likely to fail and
+ keeps the memmap on the same NUMA node in any case, it
+ can fragment physical memory in a way that huge pages
+ in bigger granularity cannot be formed on hotplugged
+ memory.
+======================== =======================================================
+
+ZONE_MOVABLE
+============
+
+ZONE_MOVABLE is an important mechanism for more reliable memory offlining.
+Further, having system RAM managed by ZONE_MOVABLE instead of one of the
+kernel zones can increase the number of possible transparent huge pages and
+dynamically allocated huge pages.
+
+Most kernel allocations are unmovable. Important examples include the memory
+map (usually 1/64ths of memory), page tables, and kmalloc(). Such allocations
+can only be served from the kernel zones.
+
+Most user space pages, such as anonymous memory, and page cache pages are
+movable. Such allocations can be served from ZONE_MOVABLE and the kernel zones.
+
+Only movable allocations are served from ZONE_MOVABLE, resulting in unmovable
+allocations being limited to the kernel zones. Without ZONE_MOVABLE, there is
+absolutely no guarantee whether a memory block can be offlined successfully.
+
+Zone Imbalances
+---------------
- This can happen when we have plenty of ZONE_MOVABLE memory, but not enough
- kernel memory to allocate vmemmmap pages. We may even be able to migrate
- huge page contents, but will not be able to dissolve the source huge page.
- This will prevent an offline operation and is unfortunate as memory offlining
- is expected to succeed on movable zones. Users that depend on memory hotplug
- to succeed for movable zones should carefully consider whether the memory
- savings gained from this feature are worth the risk of possibly not being
- able to offline memory in certain situations.
+Having too much system RAM managed by ZONE_MOVABLE is called a zone imbalance,
+which can harm the system or degrade performance. As one example, the kernel
+might crash because it runs out of free memory for unmovable allocations,
+although there is still plenty of free memory left in ZONE_MOVABLE.
+
+Usually, MOVABLE:KERNEL ratios of up to 3:1 or even 4:1 are fine. Ratios of 63:1
+are definitely impossible due to the overhead for the memory map.
+
+Actual safe zone ratios depend on the workload. Extreme cases, like excessive
+long-term pinning of pages, might not be able to deal with ZONE_MOVABLE at all.
.. note::
- Techniques that rely on long-term pinnings of memory (especially, RDMA and
- vfio) are fundamentally problematic with ZONE_MOVABLE and, therefore, memory
- hot remove. Pinned pages cannot reside on ZONE_MOVABLE, to guarantee that
- memory can still get hot removed - be aware that pinning can fail even if
- there is plenty of free memory in ZONE_MOVABLE. In addition, using
- ZONE_MOVABLE might make page pinning more expensive, because pages have to be
- migrated off that zone first.
-.. _memory_hotplug_how_to_offline_memory:
+ CMA memory part of a kernel zone essentially behaves like memory in
+ ZONE_MOVABLE and similar considerations apply, especially when combining
+ CMA with ZONE_MOVABLE.
-How to offline memory
----------------------
+ZONE_MOVABLE Sizing Considerations
+----------------------------------
-You can offline a memory block by using the same sysfs interface that was used
-in memory onlining::
+We usually expect that a large portion of available system RAM will actually
+be consumed by user space, either directly or indirectly via the page cache. In
+the normal case, ZONE_MOVABLE can be used when allocating such pages just fine.
- % echo offline > /sys/devices/system/memory/memoryXXX/state
+With that in mind, it makes sense that we can have a big portion of system RAM
+managed by ZONE_MOVABLE. However, there are some things to consider when using
+ZONE_MOVABLE, especially when fine-tuning zone ratios:
+
+- Having a lot of offline memory blocks. Even offline memory blocks consume
+ memory for metadata and page tables in the direct map; having a lot of offline
+ memory blocks is not a typical case, though.
+
+- Memory ballooning without balloon compaction is incompatible with
+ ZONE_MOVABLE. Only some implementations, such as virtio-balloon and
+ pseries CMM, fully support balloon compaction.
+
+ Further, the CONFIG_BALLOON_COMPACTION kernel configuration option might be
+ disabled. In that case, balloon inflation will only perform unmovable
+ allocations and silently create a zone imbalance, usually triggered by
+ inflation requests from the hypervisor.
+
+- Gigantic pages are unmovable, resulting in user space consuming a
+ lot of unmovable memory.
+
+- Huge pages are unmovable when an architectures does not support huge
+ page migration, resulting in a similar issue as with gigantic pages.
+
+- Page tables are unmovable. Excessive swapping, mapping extremely large
+ files or ZONE_DEVICE memory can be problematic, although only really relevant
+ in corner cases. When we manage a lot of user space memory that has been
+ swapped out or is served from a file/persistent memory/... we still need a lot
+ of page tables to manage that memory once user space accessed that memory.
+
+- In certain DAX configurations the memory map for the device memory will be
+ allocated from the kernel zones.
+
+- KASAN can have a significant memory overhead, for example, consuming 1/8th of
+ the total system memory size as (unmovable) tracking metadata.
+
+- Long-term pinning of pages. Techniques that rely on long-term pinnings
+ (especially, RDMA and vfio/mdev) are fundamentally problematic with
+ ZONE_MOVABLE, and therefore, memory offlining. Pinned pages cannot reside
+ on ZONE_MOVABLE as that would turn these pages unmovable. Therefore, they
+ have to be migrated off that zone while pinning. Pinning a page can fail
+ even if there is plenty of free memory in ZONE_MOVABLE.
+
+ In addition, using ZONE_MOVABLE might make page pinning more expensive,
+ because of the page migration overhead.
+
+By default, all the memory configured at boot time is managed by the kernel
+zones and ZONE_MOVABLE is not used.
+
+To enable ZONE_MOVABLE to include the memory present at boot and to control the
+ratio between movable and kernel zones there are two command line options:
+``kernelcore=`` and ``movablecore=``. See
+Documentation/admin-guide/kernel-parameters.rst for their description.
+
+Memory Offlining and ZONE_MOVABLE
+---------------------------------
+
+Even with ZONE_MOVABLE, there are some corner cases where offlining a memory
+block might fail:
+
+- Memory blocks with memory holes; this applies to memory blocks present during
+ boot and can apply to memory blocks hotplugged via the XEN balloon and the
+ Hyper-V balloon.
+
+- Mixed NUMA nodes and mixed zones within a single memory block prevent memory
+ offlining; this applies to memory blocks present during boot only.
+
+- Special memory blocks prevented by the system from getting offlined. Examples
+ include any memory available during boot on arm64 or memory blocks spanning
+ the crashkernel area on s390x; this usually applies to memory blocks present
+ during boot only.
+
+- Memory blocks overlapping with CMA areas cannot be offlined, this applies to
+ memory blocks present during boot only.
+
+- Concurrent activity that operates on the same physical memory area, such as
+ allocating gigantic pages, can result in temporary offlining failures.
+
+- Out of memory when dissolving huge pages, especially when freeing unused
+ vmemmap pages associated with each hugetlb page is enabled.
+
+ Offlining code may be able to migrate huge page contents, but may not be able
+ to dissolve the source huge page because it fails allocating (unmovable) pages
+ for the vmemmap, because the system might not have free memory in the kernel
+ zones left.
+
+ Users that depend on memory offlining to succeed for movable zones should
+ carefully consider whether the memory savings gained from this feature are
+ worth the risk of possibly not being able to offline memory in certain
+ situations.
+
+Further, when running into out of memory situations while migrating pages, or
+when still encountering permanently unmovable pages within ZONE_MOVABLE
+(-> BUG), memory offlining will keep retrying until it eventually succeeds.
+
+When offlining is triggered from user space, the offlining context can be
+terminated by sending a fatal signal. A timeout based offlining can easily be
+implemented via::
-If offline succeeds, the state of the memory block is changed to be "offline".
-If it fails, some error core (like -EBUSY) will be returned by the kernel.
-Even if a memory block does not belong to ZONE_MOVABLE, you can try to offline
-it. If it doesn't contain 'unmovable' memory, you'll get success.
-
-A memory block under ZONE_MOVABLE is considered to be able to be offlined
-easily. But under some busy state, it may return -EBUSY. Even if a memory
-block cannot be offlined due to -EBUSY, you can retry offlining it and may be
-able to offline it (or not). (For example, a page is referred to by some kernel
-internal call and released soon.)
-
-Consideration:
- Memory hotplug's design direction is to make the possibility of memory
- offlining higher and to guarantee unplugging memory under any situation. But
- it needs more work. Returning -EBUSY under some situation may be good because
- the user can decide to retry more or not by himself. Currently, memory
- offlining code does some amount of retry with 120 seconds timeout.
-
-Physical memory remove
-======================
-
-Need more implementation yet....
- - Notification completion of remove works by OS to firmware.
- - Guard from remove if not yet.
-
-
-Locking Internals
-=================
-
-When adding/removing memory that uses memory block devices (i.e. ordinary RAM),
-the device_hotplug_lock should be held to:
-
-- synchronize against online/offline requests (e.g. via sysfs). This way, memory
- block devices can only be accessed (.online/.state attributes) by user
- space once memory has been fully added. And when removing memory, we
- know nobody is in critical sections.
-- synchronize against CPU hotplug and similar (e.g. relevant for ACPI and PPC)
-
-Especially, there is a possible lock inversion that is avoided using
-device_hotplug_lock when adding memory and user space tries to online that
-memory faster than expected:
-
-- device_online() will first take the device_lock(), followed by
- mem_hotplug_lock
-- add_memory_resource() will first take the mem_hotplug_lock, followed by
- the device_lock() (while creating the devices, during bus_add_device()).
-
-As the device is visible to user space before taking the device_lock(), this
-can result in a lock inversion.
-
-onlining/offlining of memory should be done via device_online()/
-device_offline() - to make sure it is properly synchronized to actions
-via sysfs. Holding device_hotplug_lock is advised (to e.g. protect online_type)
-
-When adding/removing/onlining/offlining memory or adding/removing
-heterogeneous/device memory, we should always hold the mem_hotplug_lock in
-write mode to serialise memory hotplug (e.g. access to global/zone
-variables).
-
-In addition, mem_hotplug_lock (in contrast to device_hotplug_lock) in read
-mode allows for a quite efficient get_online_mems/put_online_mems
-implementation, so code accessing memory can protect from that memory
-vanishing.
-
-
-Future Work
-===========
-
- - allowing memory hot-add to ZONE_MOVABLE. maybe we need some switch like
- sysctl or new control file.
- - showing memory block and physical device relationship.
- - test and make it better memory offlining.
- - support HugeTLB page migration and offlining.
- - memmap removing at memory offline.
- - physical remove memory.
+ % timeout $TIMEOUT offline_block | failure_handling
diff --git a/Documentation/dev-tools/kfence.rst b/Documentation/dev-tools/kfence.rst
index fdf04e741ea5..0fbe3308bf37 100644
--- a/Documentation/dev-tools/kfence.rst
+++ b/Documentation/dev-tools/kfence.rst
@@ -65,25 +65,27 @@ Error reports
A typical out-of-bounds access looks like this::
==================================================================
- BUG: KFENCE: out-of-bounds read in test_out_of_bounds_read+0xa3/0x22b
+ BUG: KFENCE: out-of-bounds read in test_out_of_bounds_read+0xa6/0x234
- Out-of-bounds read at 0xffffffffb672efff (1B left of kfence-#17):
- test_out_of_bounds_read+0xa3/0x22b
- kunit_try_run_case+0x51/0x85
+ Out-of-bounds read at 0xffff8c3f2e291fff (1B left of kfence-#72):
+ test_out_of_bounds_read+0xa6/0x234
+ kunit_try_run_case+0x61/0xa0
kunit_generic_run_threadfn_adapter+0x16/0x30
- kthread+0x137/0x160
+ kthread+0x176/0x1b0
ret_from_fork+0x22/0x30
- kfence-#17 [0xffffffffb672f000-0xffffffffb672f01f, size=32, cache=kmalloc-32] allocated by task 507:
- test_alloc+0xf3/0x25b
- test_out_of_bounds_read+0x98/0x22b
- kunit_try_run_case+0x51/0x85
+ kfence-#72: 0xffff8c3f2e292000-0xffff8c3f2e29201f, size=32, cache=kmalloc-32
+
+ allocated by task 484 on cpu 0 at 32.919330s:
+ test_alloc+0xfe/0x738
+ test_out_of_bounds_read+0x9b/0x234
+ kunit_try_run_case+0x61/0xa0
kunit_generic_run_threadfn_adapter+0x16/0x30
- kthread+0x137/0x160
+ kthread+0x176/0x1b0
ret_from_fork+0x22/0x30
- CPU: 4 PID: 107 Comm: kunit_try_catch Not tainted 5.8.0-rc6+ #7
- Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014
+ CPU: 0 PID: 484 Comm: kunit_try_catch Not tainted 5.13.0-rc3+ #7
+ Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014
==================================================================
The header of the report provides a short summary of the function involved in
@@ -96,30 +98,32 @@ Use-after-free accesses are reported as::
==================================================================
BUG: KFENCE: use-after-free read in test_use_after_free_read+0xb3/0x143
- Use-after-free read at 0xffffffffb673dfe0 (in kfence-#24):
+ Use-after-free read at 0xffff8c3f2e2a0000 (in kfence-#79):
test_use_after_free_read+0xb3/0x143
- kunit_try_run_case+0x51/0x85
+ kunit_try_run_case+0x61/0xa0
kunit_generic_run_threadfn_adapter+0x16/0x30
- kthread+0x137/0x160
+ kthread+0x176/0x1b0
ret_from_fork+0x22/0x30
- kfence-#24 [0xffffffffb673dfe0-0xffffffffb673dfff, size=32, cache=kmalloc-32] allocated by task 507:
- test_alloc+0xf3/0x25b
+ kfence-#79: 0xffff8c3f2e2a0000-0xffff8c3f2e2a001f, size=32, cache=kmalloc-32
+
+ allocated by task 488 on cpu 2 at 33.871326s:
+ test_alloc+0xfe/0x738
test_use_after_free_read+0x76/0x143
- kunit_try_run_case+0x51/0x85
+ kunit_try_run_case+0x61/0xa0
kunit_generic_run_threadfn_adapter+0x16/0x30
- kthread+0x137/0x160
+ kthread+0x176/0x1b0
ret_from_fork+0x22/0x30
- freed by task 507:
+ freed by task 488 on cpu 2 at 33.871358s:
test_use_after_free_read+0xa8/0x143
- kunit_try_run_case+0x51/0x85
+ kunit_try_run_case+0x61/0xa0
kunit_generic_run_threadfn_adapter+0x16/0x30
- kthread+0x137/0x160
+ kthread+0x176/0x1b0
ret_from_fork+0x22/0x30
- CPU: 4 PID: 109 Comm: kunit_try_catch Tainted: G W 5.8.0-rc6+ #7
- Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014
+ CPU: 2 PID: 488 Comm: kunit_try_catch Tainted: G B 5.13.0-rc3+ #7
+ Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014
==================================================================
KFENCE also reports on invalid frees, such as double-frees::
@@ -127,30 +131,32 @@ KFENCE also reports on invalid frees, such as double-frees::
==================================================================
BUG: KFENCE: invalid free in test_double_free+0xdc/0x171
- Invalid free of 0xffffffffb6741000:
+ Invalid free of 0xffff8c3f2e2a4000 (in kfence-#81):
test_double_free+0xdc/0x171
- kunit_try_run_case+0x51/0x85
+ kunit_try_run_case+0x61/0xa0
kunit_generic_run_threadfn_adapter+0x16/0x30
- kthread+0x137/0x160
+ kthread+0x176/0x1b0
ret_from_fork+0x22/0x30
- kfence-#26 [0xffffffffb6741000-0xffffffffb674101f, size=32, cache=kmalloc-32] allocated by task 507:
- test_alloc+0xf3/0x25b
+ kfence-#81: 0xffff8c3f2e2a4000-0xffff8c3f2e2a401f, size=32, cache=kmalloc-32
+
+ allocated by task 490 on cpu 1 at 34.175321s:
+ test_alloc+0xfe/0x738
test_double_free+0x76/0x171
- kunit_try_run_case+0x51/0x85
+ kunit_try_run_case+0x61/0xa0
kunit_generic_run_threadfn_adapter+0x16/0x30
- kthread+0x137/0x160
+ kthread+0x176/0x1b0
ret_from_fork+0x22/0x30
- freed by task 507:
+ freed by task 490 on cpu 1 at 34.175348s:
test_double_free+0xa8/0x171
- kunit_try_run_case+0x51/0x85
+ kunit_try_run_case+0x61/0xa0
kunit_generic_run_threadfn_adapter+0x16/0x30
- kthread+0x137/0x160
+ kthread+0x176/0x1b0
ret_from_fork+0x22/0x30
- CPU: 4 PID: 111 Comm: kunit_try_catch Tainted: G W 5.8.0-rc6+ #7
- Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014
+ CPU: 1 PID: 490 Comm: kunit_try_catch Tainted: G B 5.13.0-rc3+ #7
+ Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014
==================================================================
KFENCE also uses pattern-based redzones on the other side of an object's guard
@@ -160,23 +166,25 @@ These are reported on frees::
==================================================================
BUG: KFENCE: memory corruption in test_kmalloc_aligned_oob_write+0xef/0x184
- Corrupted memory at 0xffffffffb6797ff9 [ 0xac . . . . . . ] (in kfence-#69):
+ Corrupted memory at 0xffff8c3f2e33aff9 [ 0xac . . . . . . ] (in kfence-#156):
test_kmalloc_aligned_oob_write+0xef/0x184
- kunit_try_run_case+0x51/0x85
+ kunit_try_run_case+0x61/0xa0
kunit_generic_run_threadfn_adapter+0x16/0x30
- kthread+0x137/0x160
+ kthread+0x176/0x1b0
ret_from_fork+0x22/0x30
- kfence-#69 [0xffffffffb6797fb0-0xffffffffb6797ff8, size=73, cache=kmalloc-96] allocated by task 507:
- test_alloc+0xf3/0x25b
+ kfence-#156: 0xffff8c3f2e33afb0-0xffff8c3f2e33aff8, size=73, cache=kmalloc-96
+
+ allocated by task 502 on cpu 7 at 42.159302s:
+ test_alloc+0xfe/0x738
test_kmalloc_aligned_oob_write+0x57/0x184
- kunit_try_run_case+0x51/0x85
+ kunit_try_run_case+0x61/0xa0
kunit_generic_run_threadfn_adapter+0x16/0x30
- kthread+0x137/0x160
+ kthread+0x176/0x1b0
ret_from_fork+0x22/0x30
- CPU: 4 PID: 120 Comm: kunit_try_catch Tainted: G W 5.8.0-rc6+ #7
- Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014
+ CPU: 7 PID: 502 Comm: kunit_try_catch Tainted: G B 5.13.0-rc3+ #7
+ Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014
==================================================================
For such errors, the address where the corruption occurred as well as the
diff --git a/Documentation/kbuild/llvm.rst b/Documentation/kbuild/llvm.rst
index e87ed5479963..d32616891dcf 100644
--- a/Documentation/kbuild/llvm.rst
+++ b/Documentation/kbuild/llvm.rst
@@ -130,9 +130,10 @@ Getting Help
------------
- `Website <https://clangbuiltlinux.github.io/>`_
-- `Mailing List <https://groups.google.com/forum/#!forum/clang-built-linux>`_: <clang-built-linux@googlegroups.com>
+- `Mailing List <https://lore.kernel.org/llvm/>`_: <llvm@lists.linux.dev>
+- `Old Mailing List Archives <https://groups.google.com/g/clang-built-linux>`_
- `Issue Tracker <https://github.com/ClangBuiltLinux/linux/issues>`_
-- IRC: #clangbuiltlinux on chat.freenode.net
+- IRC: #clangbuiltlinux on irc.libera.chat
- `Telegram <https://t.me/ClangBuiltLinux>`_: @ClangBuiltLinux
- `Wiki <https://github.com/ClangBuiltLinux/linux/wiki>`_
- `Beginner Bugs <https://github.com/ClangBuiltLinux/linux/issues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22>`_
diff --git a/Documentation/vm/damon/api.rst b/Documentation/vm/damon/api.rst
new file mode 100644
index 000000000000..08f34df45523
--- /dev/null
+++ b/Documentation/vm/damon/api.rst
@@ -0,0 +1,20 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=============
+API Reference
+=============
+
+Kernel space programs can use every feature of DAMON using below APIs. All you
+need to do is including ``damon.h``, which is located in ``include/linux/`` of
+the source tree.
+
+Structures
+==========
+
+.. kernel-doc:: include/linux/damon.h
+
+
+Functions
+=========
+
+.. kernel-doc:: mm/damon/core.c
diff --git a/Documentation/vm/damon/design.rst b/Documentation/vm/damon/design.rst
new file mode 100644
index 000000000000..b05159c295f4
--- /dev/null
+++ b/Documentation/vm/damon/design.rst
@@ -0,0 +1,166 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+======
+Design
+======
+
+Configurable Layers
+===================
+
+DAMON provides data access monitoring functionality while making the accuracy
+and the overhead controllable. The fundamental access monitorings require
+primitives that dependent on and optimized for the target address space. On
+the other hand, the accuracy and overhead tradeoff mechanism, which is the core
+of DAMON, is in the pure logic space. DAMON separates the two parts in
+different layers and defines its interface to allow various low level
+primitives implementations configurable with the core logic.
+
+Due to this separated design and the configurable interface, users can extend
+DAMON for any address space by configuring the core logics with appropriate low
+level primitive implementations. If appropriate one is not provided, users can
+implement the primitives on their own.
+
+For example, physical memory, virtual memory, swap space, those for specific
+processes, NUMA nodes, files, and backing memory devices would be supportable.
+Also, if some architectures or devices support special optimized access check
+primitives, those will be easily configurable.
+
+
+Reference Implementations of Address Space Specific Primitives
+==============================================================
+
+The low level primitives for the fundamental access monitoring are defined in
+two parts:
+
+1. Identification of the monitoring target address range for the address space.
+2. Access check of specific address range in the target space.
+
+DAMON currently provides the implementation of the primitives for only the
+virtual address spaces. Below two subsections describe how it works.
+
+
+VMA-based Target Address Range Construction
+-------------------------------------------
+
+Only small parts in the super-huge virtual address space of the processes are
+mapped to the physical memory and accessed. Thus, tracking the unmapped
+address regions is just wasteful. However, because DAMON can deal with some
+level of noise using the adaptive regions adjustment mechanism, tracking every
+mapping is not strictly required but could even incur a high overhead in some
+cases. That said, too huge unmapped areas inside the monitoring target should
+be removed to not take the time for the adaptive mechanism.
+
+For the reason, this implementation converts the complex mappings to three
+distinct regions that cover every mapped area of the address space. The two
+gaps between the three regions are the two biggest unmapped areas in the given
+address space. The two biggest unmapped areas would be the gap between the
+heap and the uppermost mmap()-ed region, and the gap between the lowermost
+mmap()-ed region and the stack in most of the cases. Because these gaps are
+exceptionally huge in usual address spaces, excluding these will be sufficient
+to make a reasonable trade-off. Below shows this in detail::
+
+ <heap>
+ <BIG UNMAPPED REGION 1>
+ <uppermost mmap()-ed region>
+ (small mmap()-ed regions and munmap()-ed regions)
+ <lowermost mmap()-ed region>
+ <BIG UNMAPPED REGION 2>
+ <stack>
+
+
+PTE Accessed-bit Based Access Check
+-----------------------------------
+
+The implementation for the virtual address space uses PTE Accessed-bit for
+basic access checks. It finds the relevant PTE Accessed bit from the address
+by walking the page table for the target task of the address. In this way, the
+implementation finds and clears the bit for next sampling target address and
+checks whether the bit set again after one sampling period. This could disturb
+other kernel subsystems using the Accessed bits, namely Idle page tracking and
+the reclaim logic. To avoid such disturbances, DAMON makes it mutually
+exclusive with Idle page tracking and uses ``PG_idle`` and ``PG_young`` page
+flags to solve the conflict with the reclaim logic, as Idle page tracking does.
+
+
+Address Space Independent Core Mechanisms
+=========================================
+
+Below four sections describe each of the DAMON core mechanisms and the five
+monitoring attributes, ``sampling interval``, ``aggregation interval``,
+``regions update interval``, ``minimum number of regions``, and ``maximum
+number of regions``.
+
+
+Access Frequency Monitoring
+---------------------------
+
+The output of DAMON says what pages are how frequently accessed for a given
+duration. The resolution of the access frequency is controlled by setting
+``sampling interval`` and ``aggregation interval``. In detail, DAMON checks
+access to each page per ``sampling interval`` and aggregates the results. In
+other words, counts the number of the accesses to each page. After each
+``aggregation interval`` passes, DAMON calls callback functions that previously
+registered by users so that users can read the aggregated results and then
+clears the results. This can be described in below simple pseudo-code::
+
+ while monitoring_on:
+ for page in monitoring_target:
+ if accessed(page):
+ nr_accesses[page] += 1
+ if time() % aggregation_interval == 0:
+ for callback in user_registered_callbacks:
+ callback(monitoring_target, nr_accesses)
+ for page in monitoring_target:
+ nr_accesses[page] = 0
+ sleep(sampling interval)
+
+The monitoring overhead of this mechanism will arbitrarily increase as the
+size of the target workload grows.
+
+
+Region Based Sampling
+---------------------
+
+To avoid the unbounded increase of the overhead, DAMON groups adjacent pages
+that assumed to have the same access frequencies into a region. As long as the
+assumption (pages in a region have the same access frequencies) is kept, only
+one page in the region is required to be checked. Thus, for each ``sampling
+interval``, DAMON randomly picks one page in each region, waits for one
+``sampling interval``, checks whether the page is accessed meanwhile, and
+increases the access frequency of the region if so. Therefore, the monitoring
+overhead is controllable by setting the number of regions. DAMON allows users
+to set the minimum and the maximum number of regions for the trade-off.
+
+This scheme, however, cannot preserve the quality of the output if the
+assumption is not guaranteed.
+
+
+Adaptive Regions Adjustment
+---------------------------
+
+Even somehow the initial monitoring target regions are well constructed to
+fulfill the assumption (pages in same region have similar access frequencies),
+the data access pattern can be dynamically changed. This will result in low
+monitoring quality. To keep the assumption as much as possible, DAMON
+adaptively merges and splits each region based on their access frequency.
+
+For each ``aggregation interval``, it compares the access frequencies of
+adjacent regions and merges those if the frequency difference is small. Then,
+after it reports and clears the aggregated access frequency of each region, it
+splits each region into two or three regions if the total number of regions
+will not exceed the user-specified maximum number of regions after the split.
+
+In this way, DAMON provides its best-effort quality and minimal overhead while
+keeping the bounds users set for their trade-off.
+
+
+Dynamic Target Space Updates Handling
+-------------------------------------
+
+The monitoring target address range could dynamically changed. For example,
+virtual memory could be dynamically mapped and unmapped. Physical memory could
+be hot-plugged.
+
+As the changes could be quite frequent in some cases, DAMON checks the dynamic
+memory mapping changes and applies it to the abstracted target area only for
+each of a user-specified time interval (``regions update interval``).
diff --git a/Documentation/vm/damon/faq.rst b/Documentation/vm/damon/faq.rst
new file mode 100644
index 000000000000..cb3d8b585a8b
--- /dev/null
+++ b/Documentation/vm/damon/faq.rst
@@ -0,0 +1,51 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==========================
+Frequently Asked Questions
+==========================
+
+Why a new subsystem, instead of extending perf or other user space tools?
+=========================================================================
+
+First, because it needs to be lightweight as much as possible so that it can be
+used online, any unnecessary overhead such as kernel - user space context
+switching cost should be avoided. Second, DAMON aims to be used by other
+programs including the kernel. Therefore, having a dependency on specific
+tools like perf is not desirable. These are the two biggest reasons why DAMON
+is implemented in the kernel space.
+
+
+Can 'idle pages tracking' or 'perf mem' substitute DAMON?
+=========================================================
+
+Idle page tracking is a low level primitive for access check of the physical
+address space. 'perf mem' is similar, though it can use sampling to minimize
+the overhead. On the other hand, DAMON is a higher-level framework for the
+monitoring of various address spaces. It is focused on memory management
+optimization and provides sophisticated accuracy/overhead handling mechanisms.
+Therefore, 'idle pages tracking' and 'perf mem' could provide a subset of
+DAMON's output, but cannot substitute DAMON.
+
+
+Does DAMON support virtual memory only?
+=======================================
+
+No. The core of the DAMON is address space independent. The address space
+specific low level primitive parts including monitoring target regions
+constructions and actual access checks can be implemented and configured on the
+DAMON core by the users. In this way, DAMON users can monitor any address
+space with any access check technique.
+
+Nonetheless, DAMON provides vma tracking and PTE Accessed bit check based
+implementations of the address space dependent functions for the virtual memory
+by default, for a reference and convenient use. In near future, we will
+provide those for physical memory address space.
+
+
+Can I simply monitor page granularity?
+======================================
+
+Yes. You can do so by setting the ``min_nr_regions`` attribute higher than the
+working set size divided by the page size. Because the monitoring target
+regions size is forced to be ``>=page size``, the region split will make no
+effect.
diff --git a/Documentation/vm/damon/index.rst b/Documentation/vm/damon/index.rst
new file mode 100644
index 000000000000..a2858baf3bf1
--- /dev/null
+++ b/Documentation/vm/damon/index.rst
@@ -0,0 +1,30 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==========================
+DAMON: Data Access MONitor
+==========================
+
+DAMON is a data access monitoring framework subsystem for the Linux kernel.
+The core mechanisms of DAMON (refer to :doc:`design` for the detail) make it
+
+ - *accurate* (the monitoring output is useful enough for DRAM level memory
+ management; It might not appropriate for CPU Cache levels, though),
+ - *light-weight* (the monitoring overhead is low enough to be applied online),
+ and
+ - *scalable* (the upper-bound of the overhead is in constant range regardless
+ of the size of target workloads).
+
+Using this framework, therefore, the kernel's memory management mechanisms can
+make advanced decisions. Experimental memory management optimization works
+that incurring high data accesses monitoring overhead could implemented again.
+In user space, meanwhile, users who have some special workloads can write
+personalized applications for better understanding and optimizations of their
+workloads and systems.
+
+.. toctree::
+ :maxdepth: 2
+
+ faq
+ design
+ api
+ plans
diff --git a/Documentation/vm/index.rst b/Documentation/vm/index.rst
index eff5fbd492d0..b51f0d8992f8 100644
--- a/Documentation/vm/index.rst
+++ b/Documentation/vm/index.rst
@@ -32,6 +32,7 @@ descriptions of data structures and algorithms.
arch_pgtable_helpers
balance
cleancache
+ damon/index
free_page_reporting
frontswap
highmem
diff --git a/MAINTAINERS b/MAINTAINERS
index 27989b08b725..9af529acb6a6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4526,7 +4526,7 @@ F: .clang-format
CLANG/LLVM BUILD SUPPORT
M: Nathan Chancellor <nathan@kernel.org>
M: Nick Desaulniers <ndesaulniers@google.com>
-L: clang-built-linux@googlegroups.com
+L: llvm@lists.linux.dev
S: Supported
W: https://clangbuiltlinux.github.io/
B: https://github.com/ClangBuiltLinux/linux/issues
@@ -4542,7 +4542,7 @@ M: Sami Tolvanen <samitolvanen@google.com>
M: Kees Cook <keescook@chromium.org>
R: Nathan Chancellor <nathan@kernel.org>
R: Nick Desaulniers <ndesaulniers@google.com>
-L: clang-built-linux@googlegroups.com
+L: llvm@lists.linux.dev
S: Supported
B: https://github.com/ClangBuiltLinux/linux/issues
T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/clang/features
@@ -5149,6 +5149,17 @@ F: net/ax25/ax25_out.c
F: net/ax25/ax25_timer.c
F: net/ax25/sysctl_net_ax25.c
+DATA ACCESS MONITOR
+M: SeongJae Park <sjpark@amazon.de>
+L: linux-mm@kvack.org
+S: Maintained
+F: Documentation/admin-guide/mm/damon/
+F: Documentation/vm/damon/
+F: include/linux/damon.h
+F: include/trace/events/damon.h
+F: mm/damon/
+F: tools/testing/selftests/damon/
+
DAVICOM FAST ETHERNET (DMFE) NETWORK DRIVER
L: netdev@vger.kernel.org
S: Orphan
diff --git a/arch/Kconfig b/arch/Kconfig
index 3743174da870..8df1c7102643 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -889,7 +889,7 @@ config HAVE_SOFTIRQ_ON_OWN_STACK
bool
help
Architecture provides a function to run __do_softirq() on a
- seperate stack.
+ separate stack.
config PGTABLE_LEVELS
int
diff --git a/arch/alpha/include/asm/agp.h b/arch/alpha/include/asm/agp.h
index 7173eada1567..7874f063d000 100644
--- a/arch/alpha/include/asm/agp.h
+++ b/arch/alpha/include/asm/agp.h
@@ -6,8 +6,8 @@
/* dummy for now */
-#define map_page_into_agp(page)
-#define unmap_page_from_agp(page)
+#define map_page_into_agp(page) do { } while (0)
+#define unmap_page_from_agp(page) do { } while (0)
#define flush_agp_cache() mb()
/* GATT allocation. Returns/accepts GATT kernel virtual address. */
diff --git a/arch/alpha/kernel/pci-sysfs.c b/arch/alpha/kernel/pci-sysfs.c
index 0021580d79ad..5808a66e2a81 100644
--- a/arch/alpha/kernel/pci-sysfs.c
+++ b/arch/alpha/kernel/pci-sysfs.c
@@ -60,6 +60,8 @@ static int __pci_mmap_fits(struct pci_dev *pdev, int num,
* @sparse: address space type
*
* Use the bus mapping routines to map a PCI resource into userspace.
+ *
+ * Return: %0 on success, negative error code otherwise
*/
static int pci_mmap_resource(struct kobject *kobj,
struct bin_attribute *attr,
@@ -106,7 +108,7 @@ static int pci_mmap_resource_dense(struct file *filp, struct kobject *kobj,
/**
* pci_remove_resource_files - cleanup resource files
- * @dev: dev to cleanup
+ * @pdev: pci_dev to cleanup
*
* If we created resource files for @dev, remove them from sysfs and
* free their resources.
@@ -221,10 +223,12 @@ static int pci_create_attr(struct pci_dev *pdev, int num)
}
/**
- * pci_create_resource_files - create resource files in sysfs for @dev
- * @dev: dev in question
+ * pci_create_resource_files - create resource files in sysfs for @pdev
+ * @pdev: pci_dev in question
*
* Walk the resources in @dev creating files for each resource available.
+ *
+ * Return: %0 on success, or negative error code
*/
int pci_create_resource_files(struct pci_dev *pdev)
{
@@ -296,7 +300,7 @@ int pci_mmap_legacy_page_range(struct pci_bus *bus, struct vm_area_struct *vma,
/**
* pci_adjust_legacy_attr - adjustment of legacy file attributes
- * @b: bus to create files under
+ * @bus: bus to create files under
* @mmap_type: I/O port or memory
*
* Adjust file name and size for sparse mappings.
diff --git a/arch/arc/kernel/traps.c b/arch/arc/kernel/traps.c
index 57235e5c0cea..6b83e3f2b41c 100644
--- a/arch/arc/kernel/traps.c
+++ b/arch/arc/kernel/traps.c
@@ -20,11 +20,6 @@
#include <asm/unaligned.h>
#include <asm/kprobes.h>
-void __init trap_init(void)
-{
- return;
-}
-
void die(const char *str, struct pt_regs *regs, unsigned long address)
{
show_kernel_fault_diag(str, regs, address);
diff --git a/arch/arm/configs/dove_defconfig b/arch/arm/configs/dove_defconfig
index b935162a8bba..33074fdab2ea 100644
--- a/arch/arm/configs/dove_defconfig
+++ b/arch/arm/configs/dove_defconfig
@@ -56,7 +56,6 @@ CONFIG_ATA=y
CONFIG_SATA_MV=y
CONFIG_NETDEVICES=y
CONFIG_MV643XX_ETH=y
-CONFIG_INPUT_POLLDEV=y
# CONFIG_INPUT_MOUSEDEV is not set
CONFIG_INPUT_EVDEV=y
# CONFIG_KEYBOARD_ATKBD is not set
diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig
index 363f1b1b08e3..58f4834289e6 100644
--- a/arch/arm/configs/pxa_defconfig
+++ b/arch/arm/configs/pxa_defconfig
@@ -284,7 +284,6 @@ CONFIG_RT2800USB=m
CONFIG_MWIFIEX=m
CONFIG_MWIFIEX_SDIO=m
CONFIG_INPUT_FF_MEMLESS=m
-CONFIG_INPUT_POLLDEV=y
CONFIG_INPUT_MATRIXKMAP=y
CONFIG_INPUT_MOUSEDEV=m
CONFIG_INPUT_MOUSEDEV_SCREEN_X=640
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 64308e3a5d0c..e9b4f2b49bd8 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -781,11 +781,6 @@ void abort(void)
panic("Oops failed to kill thread");
}
-void __init trap_init(void)
-{
- return;
-}
-
#ifdef CONFIG_KUSER_HELPERS
static void __init kuser_init(void *vectors)
{
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 9ff0de1b2b93..cfd9deb347c3 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1502,8 +1502,7 @@ int arch_add_memory(int nid, u64 start, u64 size,
return ret;
}
-void arch_remove_memory(int nid, u64 start, u64 size,
- struct vmem_altmap *altmap)
+void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
diff --git a/arch/h8300/kernel/traps.c b/arch/h8300/kernel/traps.c
index 5d8b969cd8f3..bdbe988d8dbc 100644
--- a/arch/h8300/kernel/traps.c
+++ b/arch/h8300/kernel/traps.c
@@ -39,10 +39,6 @@ void __init base_trap_init(void)
{
}
-void __init trap_init(void)
-{
-}
-
asmlinkage void set_esp0(unsigned long ssp)
{
current->thread.esp0 = ssp;
diff --git a/arch/hexagon/kernel/traps.c b/arch/hexagon/kernel/traps.c
index 904134b37232..edfc35dafeb1 100644
--- a/arch/hexagon/kernel/traps.c
+++ b/arch/hexagon/kernel/traps.c
@@ -28,10 +28,6 @@
#define TRAP_SYSCALL 1
#define TRAP_DEBUG 0xdb
-void __init trap_init(void)
-{
-}
-
#ifdef CONFIG_GENERIC_BUG
/* Maybe should resemble arch/sh/kernel/traps.c ?? */
int is_valid_bugaddr(unsigned long addr)
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 064a967a7b6e..5c6da8d83c1a 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -484,8 +484,7 @@ int arch_add_memory(int nid, u64 start, u64 size,
return ret;
}
-void arch_remove_memory(int nid, u64 start, u64 size,
- struct vmem_altmap *altmap)
+void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig
index aaf9d5e0aa2c..791894c4d8fb 100644
--- a/arch/mips/configs/lemote2f_defconfig
+++ b/arch/mips/configs/lemote2f_defconfig
@@ -116,7 +116,6 @@ CONFIG_8139TOO=y
CONFIG_R8169=y
CONFIG_USB_USBNET=m
CONFIG_USB_NET_CDC_EEM=m
-CONFIG_INPUT_POLLDEV=m
CONFIG_INPUT_EVDEV=y
# CONFIG_MOUSE_PS2_ALPS is not set
# CONFIG_MOUSE_PS2_LOGIPS2PP is not set
diff --git a/arch/mips/configs/pic32mzda_defconfig b/arch/mips/configs/pic32mzda_defconfig
index 63fe2da1b37f..fd567247adc7 100644
--- a/arch/mips/configs/pic32mzda_defconfig
+++ b/arch/mips/configs/pic32mzda_defconfig
@@ -34,7 +34,6 @@ CONFIG_SCSI_CONSTANTS=y
CONFIG_SCSI_SCAN_ASYNC=y
# CONFIG_SCSI_LOWLEVEL is not set
CONFIG_INPUT_LEDS=m
-CONFIG_INPUT_POLLDEV=y
CONFIG_INPUT_MOUSEDEV=m
CONFIG_INPUT_EVDEV=y
CONFIG_INPUT_EVBUG=m
diff --git a/arch/mips/configs/rt305x_defconfig b/arch/mips/configs/rt305x_defconfig
index fec5851c164b..eb359db15dba 100644
--- a/arch/mips/configs/rt305x_defconfig
+++ b/arch/mips/configs/rt305x_defconfig
@@ -90,7 +90,6 @@ CONFIG_PPPOE=m
CONFIG_PPP_ASYNC=m
CONFIG_ISDN=y
CONFIG_INPUT=m
-CONFIG_INPUT_POLLDEV=m
# CONFIG_KEYBOARD_ATKBD is not set
# CONFIG_INPUT_MOUSE is not set
CONFIG_INPUT_MISC=y
diff --git a/arch/mips/configs/xway_defconfig b/arch/mips/configs/xway_defconfig
index 9abbc0debc2a..eeb689f715cb 100644
--- a/arch/mips/configs/xway_defconfig
+++ b/arch/mips/configs/xway_defconfig
@@ -96,7 +96,6 @@ CONFIG_PPPOE=m
CONFIG_PPP_ASYNC=m
CONFIG_ISDN=y
CONFIG_INPUT=m
-CONFIG_INPUT_POLLDEV=m
# CONFIG_KEYBOARD_ATKBD is not set
# CONFIG_INPUT_MOUSE is not set
CONFIG_INPUT_MISC=y
diff --git a/arch/nds32/kernel/traps.c b/arch/nds32/kernel/traps.c
index ee0d9ae192a5..f06421c645af 100644
--- a/arch/nds32/kernel/traps.c
+++ b/arch/nds32/kernel/traps.c
@@ -183,11 +183,6 @@ void __pgd_error(const char *file, int line, unsigned long val)
}
extern char *exception_vector, *exception_vector_end;
-void __init trap_init(void)
-{
- return;
-}
-
void __init early_trap_init(void)
{
unsigned long ivb = 0;
diff --git a/arch/nios2/kernel/traps.c b/arch/nios2/kernel/traps.c
index b172da4eb1a9..596986a74a26 100644
--- a/arch/nios2/kernel/traps.c
+++ b/arch/nios2/kernel/traps.c
@@ -105,11 +105,6 @@ void show_stack(struct task_struct *task, unsigned long *stack,
printk("%s\n", loglvl);
}
-void __init trap_init(void)
-{
- /* Nothing to do here */
-}
-
/* Breakpoint handler */
asmlinkage void breakpoint_c(struct pt_regs *fp)
{
diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c
index 4d61333c2623..aa1e709405ac 100644
--- a/arch/openrisc/kernel/traps.c
+++ b/arch/openrisc/kernel/traps.c
@@ -231,11 +231,6 @@ void unhandled_exception(struct pt_regs *regs, int ea, int vector)
die("Oops", regs, 9);
}
-void __init trap_init(void)
-{
- /* Nothing needs to be done */
-}
-
asmlinkage void do_trap(struct pt_regs *regs, unsigned long address)
{
force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->pc);
diff --git a/arch/parisc/configs/generic-32bit_defconfig b/arch/parisc/configs/generic-32bit_defconfig
index 7611d48c599e..dd14e3131325 100644
--- a/arch/parisc/configs/generic-32bit_defconfig
+++ b/arch/parisc/configs/generic-32bit_defconfig
@@ -111,7 +111,6 @@ CONFIG_PPP_BSDCOMP=m
CONFIG_PPP_DEFLATE=m
CONFIG_PPPOE=m
# CONFIG_WLAN is not set
-CONFIG_INPUT_POLLDEV=y
CONFIG_KEYBOARD_HIL_OLD=m
CONFIG_KEYBOARD_HIL=m
CONFIG_MOUSE_SERIAL=y
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 8d8441d4562a..747c328fb886 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -859,7 +859,3 @@ void __init early_trap_init(void)
initialize_ivt(&fault_vector_20);
}
-
-void __init trap_init(void)
-{
-}
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 4390f8d72126..aac8c0412ff9 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -2219,11 +2219,6 @@ DEFINE_INTERRUPT_HANDLER(kernel_bad_stack)
die("Bad kernel stack pointer", regs, SIGABRT);
}
-void __init trap_init(void)
-{
-}
-
-
#ifdef CONFIG_PPC_EMULATED_STATS
#define WARN_EMULATED_SETUP(type) .type = { .name = #type }
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index ad198b439222..c3c4e31462ec 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -119,8 +119,7 @@ int __ref arch_add_memory(int nid, u64 start, u64 size,
return rc;
}
-void __ref arch_remove_memory(int nid, u64 start, u64 size,
- struct vmem_altmap *altmap)
+void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 44246ba59768..91cf23495ccb 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -286,7 +286,7 @@ static int pseries_remove_memblock(unsigned long base, unsigned long memblock_si
{
unsigned long block_sz, start_pfn;
int sections_per_block;
- int i, nid;
+ int i;
start_pfn = base >> PAGE_SHIFT;
@@ -297,10 +297,9 @@ static int pseries_remove_memblock(unsigned long base, unsigned long memblock_si
block_sz = pseries_memory_block_size();
sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;
- nid = memory_add_physaddr_to_nid(base);
for (i = 0; i < sections_per_block; i++) {
- __remove_memory(nid, base, MIN_MEMORY_BLOCK_SIZE);
+ __remove_memory(base, MIN_MEMORY_BLOCK_SIZE);
base += MIN_MEMORY_BLOCK_SIZE;
}
@@ -387,7 +386,7 @@ static int dlpar_remove_lmb(struct drmem_lmb *lmb)
block_sz = pseries_memory_block_size();
- __remove_memory(mem_block->nid, lmb->base_addr, block_sz);
+ __remove_memory(lmb->base_addr, block_sz);
put_device(&mem_block->dev);
/* Update memory regions for memory remove */
@@ -660,7 +659,7 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb)
rc = dlpar_online_lmb(lmb);
if (rc) {
- __remove_memory(nid, lmb->base_addr, block_sz);
+ __remove_memory(lmb->base_addr, block_sz);
invalidate_lmb_associativity_index(lmb);
} else {
lmb->flags |= DRCONF_MEM_ASSIGNED;
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index aac669a6c3d8..c79955655fa4 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -51,7 +51,7 @@ config RISCV
select GENERIC_EARLY_IOREMAP
select GENERIC_GETTIMEOFDAY if HAVE_GENERIC_VDSO
select GENERIC_IDLE_POLL_SETUP
- select GENERIC_IOREMAP
+ select GENERIC_IOREMAP if MMU
select GENERIC_IRQ_MULTI_HANDLER
select GENERIC_IRQ_SHOW
select GENERIC_IRQ_SHOW_LEVEL
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 0a98fd0ddfe9..0daaa3e4630d 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -199,11 +199,6 @@ int is_valid_bugaddr(unsigned long pc)
}
#endif /* CONFIG_GENERIC_BUG */
-/* stvec & scratch is already set from head.S */
-void __init trap_init(void)
-{
-}
-
#ifdef CONFIG_VMAP_STACK
static DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)],
overflow_stack)__aligned(16);
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index f14e7e61cd8e..a04faf49001a 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -307,8 +307,7 @@ int arch_add_memory(int nid, u64 start, u64 size,
return rc;
}
-void arch_remove_memory(int nid, u64 start, u64 size,
- struct vmem_altmap *altmap)
+void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index ce26c7f8950a..506784702430 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -414,8 +414,7 @@ int arch_add_memory(int nid, u64 start, u64 size,
return ret;
}
-void arch_remove_memory(int nid, u64 start, u64 size,
- struct vmem_altmap *altmap)
+void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
{
unsigned long start_pfn = PFN_DOWN(start);
unsigned long nr_pages = size >> PAGE_SHIFT;
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index ad12f78bda7e..3198c4767387 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -311,7 +311,3 @@ void winch(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
{
do_IRQ(WINCH_IRQ, regs);
}
-
-void trap_init(void)
-{
-}
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 9c9c4a888b1d..e81885384f60 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -156,7 +156,6 @@ CONFIG_FORCEDETH=y
CONFIG_8139TOO=y
# CONFIG_8139TOO_PIO is not set
CONFIG_R8169=y
-CONFIG_INPUT_POLLDEV=y
CONFIG_INPUT_EVDEV=y
CONFIG_INPUT_JOYSTICK=y
CONFIG_INPUT_TABLET=y
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index b60bd2d86034..e8a7a0af2bda 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -148,7 +148,6 @@ CONFIG_SKY2=y
CONFIG_FORCEDETH=y
CONFIG_8139TOO=y
CONFIG_R8169=y
-CONFIG_INPUT_POLLDEV=y
CONFIG_INPUT_EVDEV=y
CONFIG_INPUT_JOYSTICK=y
CONFIG_INPUT_TABLET=y
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 74b78840182d..bd90b8fe81e4 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -801,8 +801,7 @@ int arch_add_memory(int nid, u64 start, u64 size,
return __add_pages(nid, start_pfn, nr_pages, params);
}
-void arch_remove_memory(int nid, u64 start, u64 size,
- struct vmem_altmap *altmap)
+void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index ddeaba947eb3..a6e11763763f 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1255,8 +1255,7 @@ kernel_physical_mapping_remove(unsigned long start, unsigned long end)
remove_pagetable(start, end, true, NULL);
}
-void __ref arch_remove_memory(int nid, u64 start, u64 size,
- struct vmem_altmap *altmap)
+void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c
index 8cc195c4c861..24f662d8bd39 100644
--- a/drivers/acpi/acpi_memhotplug.c
+++ b/drivers/acpi/acpi_memhotplug.c
@@ -54,6 +54,7 @@ struct acpi_memory_info {
struct acpi_memory_device {
struct acpi_device *device;
struct list_head res_list;
+ int mgid;
};
static acpi_status
@@ -169,12 +170,33 @@ static void acpi_unbind_memory_blocks(struct acpi_memory_info *info)
static int acpi_memory_enable_device(struct acpi_memory_device *mem_device)
{
acpi_handle handle = mem_device->device->handle;
+ mhp_t mhp_flags = MHP_NID_IS_MGID;
int result, num_enabled = 0;
struct acpi_memory_info *info;
- mhp_t mhp_flags = MHP_NONE;
- int node;
+ u64 total_length = 0;
+ int node, mgid;
node = acpi_get_node(handle);
+
+ list_for_each_entry(info, &mem_device->res_list, list) {
+ if (!info->length)
+ continue;
+ /* We want a single node for the whole memory group */
+ if (node < 0)
+ node = memory_add_physaddr_to_nid(info->start_addr);
+ total_length += info->length;
+ }
+
+ if (!total_length) {
+ dev_err(&mem_device->device->dev, "device is empty\n");
+ return -EINVAL;
+ }
+
+ mgid = memory_group_register_static(node, PFN_UP(total_length));
+ if (mgid < 0)
+ return mgid;
+ mem_device->mgid = mgid;
+
/*
* Tell the VM there is more memory here...
* Note: Assume that this function returns zero on success
@@ -182,22 +204,16 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device)
* (i.e. memory-hot-remove function)
*/
list_for_each_entry(info, &mem_device->res_list, list) {
- if (info->enabled) { /* just sanity check...*/
- num_enabled++;
- continue;
- }
/*
* If the memory block size is zero, please ignore it.
* Don't try to do the following memory hotplug flowchart.
*/
if (!info->length)
continue;
- if (node < 0)
- node = memory_add_physaddr_to_nid(info->start_addr);
if (mhp_supports_memmap_on_memory(info->length))
mhp_flags |= MHP_MEMMAP_ON_MEMORY;
- result = __add_memory(node, info->start_addr, info->length,
+ result = __add_memory(mgid, info->start_addr, info->length,
mhp_flags);
/*
@@ -239,19 +255,14 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device)
static void acpi_memory_remove_memory(struct acpi_memory_device *mem_device)
{
- acpi_handle handle = mem_device->device->handle;
struct acpi_memory_info *info, *n;
- int nid = acpi_get_node(handle);
list_for_each_entry_safe(info, n, &mem_device->res_list, list) {
if (!info->enabled)
continue;
- if (nid == NUMA_NO_NODE)
- nid = memory_add_physaddr_to_nid(info->start_addr);
-
acpi_unbind_memory_blocks(info);
- __remove_memory(nid, info->start_addr, info->length);
+ __remove_memory(info->start_addr, info->length);
list_del(&info->list);
kfree(info);
}
@@ -262,6 +273,10 @@ static void acpi_memory_device_free(struct acpi_memory_device *mem_device)
if (!mem_device)
return;
+ /* In case we succeeded adding *some* memory, unregistering fails. */
+ if (mem_device->mgid >= 0)
+ memory_group_unregister(mem_device->mgid);
+
acpi_memory_free_device_resources(mem_device);
mem_device->device->driver_data = NULL;
kfree(mem_device);
@@ -282,6 +297,7 @@ static int acpi_memory_device_add(struct acpi_device *device,
INIT_LIST_HEAD(&mem_device->res_list);
mem_device->device = device;
+ mem_device->mgid = -1;
sprintf(acpi_device_name(device), "%s", ACPI_MEMORY_DEVICE_NAME);
sprintf(acpi_device_class(device), "%s", ACPI_MEMORY_DEVICE_CLASS);
device->driver_data = mem_device;
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index e3fd2dbf4eea..365cd4a7f239 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -82,6 +82,12 @@ static struct bus_type memory_subsys = {
*/
static DEFINE_XARRAY(memory_blocks);
+/*
+ * Memory groups, indexed by memory group id (mgid).
+ */
+static DEFINE_XARRAY_FLAGS(memory_groups, XA_FLAGS_ALLOC);
+#define MEMORY_GROUP_MARK_DYNAMIC XA_MARK_1
+
static BLOCKING_NOTIFIER_HEAD(memory_chain);
int register_memory_notifier(struct notifier_block *nb)
@@ -177,7 +183,8 @@ static int memory_block_online(struct memory_block *mem)
struct zone *zone;
int ret;
- zone = zone_for_pfn_range(mem->online_type, mem->nid, start_pfn, nr_pages);
+ zone = zone_for_pfn_range(mem->online_type, mem->nid, mem->group,
+ start_pfn, nr_pages);
/*
* Although vmemmap pages have a different lifecycle than the pages
@@ -193,7 +200,7 @@ static int memory_block_online(struct memory_block *mem)
}
ret = online_pages(start_pfn + nr_vmemmap_pages,
- nr_pages - nr_vmemmap_pages, zone);
+ nr_pages - nr_vmemmap_pages, zone, mem->group);
if (ret) {
if (nr_vmemmap_pages)
mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages);
@@ -205,7 +212,8 @@ static int memory_block_online(struct memory_block *mem)
* now already properly populated.
*/
if (nr_vmemmap_pages)
- adjust_present_page_count(zone, nr_vmemmap_pages);
+ adjust_present_page_count(pfn_to_page(start_pfn), mem->group,
+ nr_vmemmap_pages);
return ret;
}
@@ -215,24 +223,23 @@ static int memory_block_offline(struct memory_block *mem)
unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
unsigned long nr_vmemmap_pages = mem->nr_vmemmap_pages;
- struct zone *zone;
int ret;
/*
* Unaccount before offlining, such that unpopulated zone and kthreads
* can properly be torn down in offline_pages().
*/
- if (nr_vmemmap_pages) {
- zone = page_zone(pfn_to_page(start_pfn));
- adjust_present_page_count(zone, -nr_vmemmap_pages);
- }
+ if (nr_vmemmap_pages)
+ adjust_present_page_count(pfn_to_page(start_pfn), mem->group,
+ -nr_vmemmap_pages);
ret = offline_pages(start_pfn + nr_vmemmap_pages,
- nr_pages - nr_vmemmap_pages);
+ nr_pages - nr_vmemmap_pages, mem->group);
if (ret) {
/* offline_pages() failed. Account back. */
if (nr_vmemmap_pages)
- adjust_present_page_count(zone, nr_vmemmap_pages);
+ adjust_present_page_count(pfn_to_page(start_pfn),
+ mem->group, nr_vmemmap_pages);
return ret;
}
@@ -374,12 +381,13 @@ static ssize_t phys_device_show(struct device *dev,
#ifdef CONFIG_MEMORY_HOTREMOVE
static int print_allowed_zone(char *buf, int len, int nid,
+ struct memory_group *group,
unsigned long start_pfn, unsigned long nr_pages,
int online_type, struct zone *default_zone)
{
struct zone *zone;
- zone = zone_for_pfn_range(online_type, nid, start_pfn, nr_pages);
+ zone = zone_for_pfn_range(online_type, nid, group, start_pfn, nr_pages);
if (zone == default_zone)
return 0;
@@ -392,9 +400,10 @@ static ssize_t valid_zones_show(struct device *dev,
struct memory_block *mem = to_memory_block(dev);
unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
+ struct memory_group *group = mem->group;
struct zone *default_zone;
+ int nid = mem->nid;
int len = 0;
- int nid;
/*
* Check the existing zone. Make sure that we do that only on the
@@ -413,14 +422,13 @@ static ssize_t valid_zones_show(struct device *dev,
goto out;
}
- nid = mem->nid;
- default_zone = zone_for_pfn_range(MMOP_ONLINE, nid, start_pfn,
- nr_pages);
+ default_zone = zone_for_pfn_range(MMOP_ONLINE, nid, group,
+ start_pfn, nr_pages);
len += sysfs_emit_at(buf, len, "%s", default_zone->name);
- len += print_allowed_zone(buf, len, nid, start_pfn, nr_pages,
+ len += print_allowed_zone(buf, len, nid, group, start_pfn, nr_pages,
MMOP_ONLINE_KERNEL, default_zone);
- len += print_allowed_zone(buf, len, nid, start_pfn, nr_pages,
+ len += print_allowed_zone(buf, len, nid, group, start_pfn, nr_pages,
MMOP_ONLINE_MOVABLE, default_zone);
out:
len += sysfs_emit_at(buf, len, "\n");
@@ -634,7 +642,8 @@ int register_memory(struct memory_block *memory)
}
static int init_memory_block(unsigned long block_id, unsigned long state,
- unsigned long nr_vmemmap_pages)
+ unsigned long nr_vmemmap_pages,
+ struct memory_group *group)
{
struct memory_block *mem;
int ret = 0;
@@ -652,6 +661,12 @@ static int init_memory_block(unsigned long block_id, unsigned long state,
mem->state = state;
mem->nid = NUMA_NO_NODE;
mem->nr_vmemmap_pages = nr_vmemmap_pages;
+ INIT_LIST_HEAD(&mem->group_next);
+
+ if (group) {
+ mem->group = group;
+ list_add(&mem->group_next, &group->memory_blocks);
+ }
ret = register_memory(mem);
@@ -671,7 +686,7 @@ static int add_memory_block(unsigned long base_section_nr)
if (section_count == 0)
return 0;
return init_memory_block(memory_block_id(base_section_nr),
- MEM_ONLINE, 0);
+ MEM_ONLINE, 0, NULL);
}
static void unregister_memory(struct memory_block *memory)
@@ -681,6 +696,11 @@ static void unregister_memory(struct memory_block *memory)
WARN_ON(xa_erase(&memory_blocks, memory->dev.id) == NULL);
+ if (memory->group) {
+ list_del(&memory->group_next);
+ memory->group = NULL;
+ }
+
/* drop the ref. we got via find_memory_block() */
put_device(&memory->dev);
device_unregister(&memory->dev);
@@ -694,7 +714,8 @@ static void unregister_memory(struct memory_block *memory)
* Called under device_hotplug_lock.
*/
int create_memory_block_devices(unsigned long start, unsigned long size,
- unsigned long vmemmap_pages)
+ unsigned long vmemmap_pages,
+ struct memory_group *group)
{
const unsigned long start_block_id = pfn_to_block_id(PFN_DOWN(start));
unsigned long end_block_id = pfn_to_block_id(PFN_DOWN(start + size));
@@ -707,7 +728,8 @@ int create_memory_block_devices(unsigned long start, unsigned long size,
return -EINVAL;
for (block_id = start_block_id; block_id != end_block_id; block_id++) {
- ret = init_memory_block(block_id, MEM_OFFLINE, vmemmap_pages);
+ ret = init_memory_block(block_id, MEM_OFFLINE, vmemmap_pages,
+ group);
if (ret)
break;
}
@@ -891,3 +913,164 @@ int for_each_memory_block(void *arg, walk_memory_blocks_func_t func)
return bus_for_each_dev(&memory_subsys, NULL, &cb_data,
for_each_memory_block_cb);
}
+
+/*
+ * This is an internal helper to unify allocation and initialization of
+ * memory groups. Note that the passed memory group will be copied to a
+ * dynamically allocated memory group. After this call, the passed
+ * memory group should no longer be used.
+ */
+static int memory_group_register(struct memory_group group)
+{
+ struct memory_group *new_group;
+ uint32_t mgid;
+ int ret;
+
+ if (!node_possible(group.nid))
+ return -EINVAL;
+
+ new_group = kzalloc(sizeof(group), GFP_KERNEL);
+ if (!new_group)
+ return -ENOMEM;
+ *new_group = group;
+ INIT_LIST_HEAD(&new_group->memory_blocks);
+
+ ret = xa_alloc(&memory_groups, &mgid, new_group, xa_limit_31b,
+ GFP_KERNEL);
+ if (ret) {
+ kfree(new_group);
+ return ret;
+ } else if (group.is_dynamic) {
+ xa_set_mark(&memory_groups, mgid, MEMORY_GROUP_MARK_DYNAMIC);
+ }
+ return mgid;
+}
+
+/**
+ * memory_group_register_static() - Register a static memory group.
+ * @nid: The node id.
+ * @max_pages: The maximum number of pages we'll have in this static memory
+ * group.
+ *
+ * Register a new static memory group and return the memory group id.
+ * All memory in the group belongs to a single unit, such as a DIMM. All
+ * memory belonging to a static memory group is added in one go to be removed
+ * in one go -- it's static.
+ *
+ * Returns an error if out of memory, if the node id is invalid, if no new
+ * memory groups can be registered, or if max_pages is invalid (0). Otherwise,
+ * returns the new memory group id.
+ */
+int memory_group_register_static(int nid, unsigned long max_pages)
+{
+ struct memory_group group = {
+ .nid = nid,
+ .s = {
+ .max_pages = max_pages,
+ },
+ };
+
+ if (!max_pages)
+ return -EINVAL;
+ return memory_group_register(group);
+}
+EXPORT_SYMBOL_GPL(memory_group_register_static);
+
+/**
+ * memory_group_register_dynamic() - Register a dynamic memory group.
+ * @nid: The node id.
+ * @unit_pages: Unit in pages in which is memory added/removed in this dynamic
+ * memory group.
+ *
+ * Register a new dynamic memory group and return the memory group id.
+ * Memory within a dynamic memory group is added/removed dynamically
+ * in unit_pages.
+ *
+ * Returns an error if out of memory, if the node id is invalid, if no new
+ * memory groups can be registered, or if unit_pages is invalid (0, not a
+ * power of two, smaller than a single memory block). Otherwise, returns the
+ * new memory group id.
+ */
+int memory_group_register_dynamic(int nid, unsigned long unit_pages)
+{
+ struct memory_group group = {
+ .nid = nid,
+ .is_dynamic = true,
+ .d = {
+ .unit_pages = unit_pages,
+ },
+ };
+
+ if (!unit_pages || !is_power_of_2(unit_pages) ||
+ unit_pages < PHYS_PFN(memory_block_size_bytes()))
+ return -EINVAL;
+ return memory_group_register(group);
+}
+EXPORT_SYMBOL_GPL(memory_group_register_dynamic);
+
+/**
+ * memory_group_unregister() - Unregister a memory group.
+ * @mgid: the memory group id
+ *
+ * Unregister a memory group. If any memory block still belongs to this
+ * memory group, unregistering will fail.
+ *
+ * Returns -EINVAL if the memory group id is invalid, returns -EBUSY if some
+ * memory blocks still belong to this memory group and returns 0 if
+ * unregistering succeeded.
+ */
+int memory_group_unregister(int mgid)
+{
+ struct memory_group *group;
+
+ if (mgid < 0)
+ return -EINVAL;
+
+ group = xa_load(&memory_groups, mgid);
+ if (!group)
+ return -EINVAL;
+ if (!list_empty(&group->memory_blocks))
+ return -EBUSY;
+ xa_erase(&memory_groups, mgid);
+ kfree(group);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(memory_group_unregister);
+
+/*
+ * This is an internal helper only to be used in core memory hotplug code to
+ * lookup a memory group. We don't care about locking, as we don't expect a
+ * memory group to get unregistered while adding memory to it -- because
+ * the group and the memory is managed by the same driver.
+ */
+struct memory_group *memory_group_find_by_id(int mgid)
+{
+ return xa_load(&memory_groups, mgid);
+}
+
+/*
+ * This is an internal helper only to be used in core memory hotplug code to
+ * walk all dynamic memory groups excluding a given memory group, either
+ * belonging to a specific node, or belonging to any node.
+ */
+int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func,
+ struct memory_group *excluded, void *arg)
+{
+ struct memory_group *group;
+ unsigned long index;
+ int ret = 0;
+
+ xa_for_each_marked(&memory_groups, index, group,
+ MEMORY_GROUP_MARK_DYNAMIC) {
+ if (group == excluded)
+ continue;
+#ifdef CONFIG_NUMA
+ if (nid != NUMA_NO_NODE && group->nid != nid)
+ continue;
+#endif /* CONFIG_NUMA */
+ ret = func(group, arg);
+ if (ret)
+ break;
+ }
+ return ret;
+}
diff --git a/drivers/base/node.c b/drivers/base/node.c
index be16bbff11cc..c56d34f8158f 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -785,8 +785,6 @@ int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
static int __ref get_nid_for_pfn(unsigned long pfn)
{
- if (!pfn_valid_within(pfn))
- return -1;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
if (system_state < SYSTEM_RUNNING)
return early_pfn_to_nid(pfn);
diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index ac231cc36359..a37622060fff 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -37,15 +37,16 @@ static int dax_kmem_range(struct dev_dax *dev_dax, int i, struct range *r)
struct dax_kmem_data {
const char *res_name;
+ int mgid;
struct resource *res[];
};
static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
{
struct device *dev = &dev_dax->dev;
+ unsigned long total_len = 0;
struct dax_kmem_data *data;
- int rc = -ENOMEM;
- int i, mapped = 0;
+ int i, rc, mapped = 0;
int numa_node;
/*
@@ -61,24 +62,44 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
return -EINVAL;
}
+ for (i = 0; i < dev_dax->nr_range; i++) {
+ struct range range;
+
+ rc = dax_kmem_range(dev_dax, i, &range);
+ if (rc) {
+ dev_info(dev, "mapping%d: %#llx-%#llx too small after alignment\n",
+ i, range.start, range.end);
+ continue;
+ }
+ total_len += range_len(&range);
+ }
+
+ if (!total_len) {
+ dev_warn(dev, "rejecting DAX region without any memory after alignment\n");
+ return -EINVAL;
+ }
+
data = kzalloc(struct_size(data, res, dev_dax->nr_range), GFP_KERNEL);
if (!data)
return -ENOMEM;
+ rc = -ENOMEM;
data->res_name = kstrdup(dev_name(dev), GFP_KERNEL);
if (!data->res_name)
goto err_res_name;
+ rc = memory_group_register_static(numa_node, total_len);
+ if (rc < 0)
+ goto err_reg_mgid;
+ data->mgid = rc;
+
for (i = 0; i < dev_dax->nr_range; i++) {
struct resource *res;
struct range range;
rc = dax_kmem_range(dev_dax, i, &range);
- if (rc) {
- dev_info(dev, "mapping%d: %#llx-%#llx too small after alignment\n",
- i, range.start, range.end);
+ if (rc)
continue;
- }
/* Region is permanently reserved if hotremove fails. */
res = request_mem_region(range.start, range_len(&range), data->res_name);
@@ -108,8 +129,8 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
* Ensure that future kexec'd kernels will not treat
* this as RAM automatically.
*/
- rc = add_memory_driver_managed(numa_node, range.start,
- range_len(&range), kmem_name, MHP_NONE);
+ rc = add_memory_driver_managed(data->mgid, range.start,
+ range_len(&range), kmem_name, MHP_NID_IS_MGID);
if (rc) {
dev_warn(dev, "mapping%d: %#llx-%#llx memory add failed\n",
@@ -129,6 +150,8 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
return 0;
err_request_mem:
+ memory_group_unregister(data->mgid);
+err_reg_mgid:
kfree(data->res_name);
err_res_name:
kfree(data);
@@ -156,8 +179,7 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
if (rc)
continue;
- rc = remove_memory(dev_dax->target_node, range.start,
- range_len(&range));
+ rc = remove_memory(range.start, range_len(&range));
if (rc == 0) {
release_resource(data->res[i]);
kfree(data->res[i]);
@@ -172,6 +194,7 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
}
if (success >= dev_dax->nr_range) {
+ memory_group_unregister(data->mgid);
kfree(data->res_name);
kfree(data);
dev_set_drvdata(dev, NULL);
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 28f3e0ba6cdd..85faa7a5c7d1 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -27,6 +27,7 @@
#include <linux/hrtimer.h>
#include <linux/of.h>
#include <linux/pm_qos.h>
+#include <linux/units.h>
#include "governor.h"
#define CREATE_TRACE_POINTS
@@ -34,7 +35,6 @@
#define IS_SUPPORTED_FLAG(f, name) ((f & DEVFREQ_GOV_FLAG_##name) ? true : false)
#define IS_SUPPORTED_ATTR(f, name) ((f & DEVFREQ_GOV_ATTR_##name) ? true : false)
-#define HZ_PER_KHZ 1000
static struct class *devfreq_class;
static struct dentry *devfreq_debugfs;
diff --git a/drivers/hwmon/mr75203.c b/drivers/hwmon/mr75203.c
index 18da5a25e89a..868243dba1ee 100644
--- a/drivers/hwmon/mr75203.c
+++ b/drivers/hwmon/mr75203.c
@@ -17,6 +17,7 @@
#include <linux/property.h>
#include <linux/regmap.h>
#include <linux/reset.h>
+#include <linux/units.h>
/* PVT Common register */
#define PVT_IP_CONFIG 0x04
@@ -37,7 +38,6 @@
#define CLK_SYNTH_EN BIT(24)
#define CLK_SYS_CYCLES_MAX 514
#define CLK_SYS_CYCLES_MIN 2
-#define HZ_PER_MHZ 1000000L
#define SDIF_DISABLE 0x04
diff --git a/drivers/iio/common/hid-sensors/hid-sensor-attributes.c b/drivers/iio/common/hid-sensors/hid-sensor-attributes.c
index 043f199e7bc6..9b279937a24e 100644
--- a/drivers/iio/common/hid-sensors/hid-sensor-attributes.c
+++ b/drivers/iio/common/hid-sensors/hid-sensor-attributes.c
@@ -6,12 +6,11 @@
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/time.h>
+#include <linux/units.h>
#include <linux/hid-sensor-hub.h>
#include <linux/iio/iio.h>
-#define HZ_PER_MHZ 1000000L
-
static struct {
u32 usage_id;
int unit; /* 0 for default others from HID sensor spec */
diff --git a/drivers/iio/light/as73211.c b/drivers/iio/light/as73211.c
index 7b32dfaee9b3..3ba2378df3dd 100644
--- a/drivers/iio/light/as73211.c
+++ b/drivers/iio/light/as73211.c
@@ -24,8 +24,7 @@
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/pm.h>
-
-#define HZ_PER_KHZ 1000
+#include <linux/units.h>
#define AS73211_DRV_NAME "as73211"
diff --git a/drivers/media/i2c/ov02a10.c b/drivers/media/i2c/ov02a10.c
index a3ce5500d355..0f08c05333ea 100644
--- a/drivers/media/i2c/ov02a10.c
+++ b/drivers/media/i2c/ov02a10.c
@@ -9,6 +9,7 @@
#include <linux/module.h>
#include <linux/pm_runtime.h>
#include <linux/regulator/consumer.h>
+#include <linux/units.h>
#include <media/media-entity.h>
#include <media/v4l2-async.h>
#include <media/v4l2-ctrls.h>
@@ -64,7 +65,6 @@
/* Test pattern control */
#define OV02A10_REG_TEST_PATTERN 0xb6
-#define HZ_PER_MHZ 1000000L
#define OV02A10_LINK_FREQ_390MHZ (390 * HZ_PER_MHZ)
#define OV02A10_ECLK_FREQ (24 * HZ_PER_MHZ)
diff --git a/drivers/mtd/nand/raw/intel-nand-controller.c b/drivers/mtd/nand/raw/intel-nand-controller.c
index 29e8a546dcd6..b9784f3da7a1 100644
--- a/drivers/mtd/nand/raw/intel-nand-controller.c
+++ b/drivers/mtd/nand/raw/intel-nand-controller.c
@@ -20,6 +20,7 @@
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/types.h>
+#include <linux/units.h>
#include <asm/unaligned.h>
#define EBU_CLC 0x000
@@ -102,7 +103,6 @@
#define MAX_CS 2
-#define HZ_PER_MHZ 1000000L
#define USEC_PER_SEC 1000000L
struct ebu_nand_cs {
diff --git a/drivers/phy/st/phy-stm32-usbphyc.c b/drivers/phy/st/phy-stm32-usbphyc.c
index 3e491dfb2525..937a14fa7448 100644
--- a/drivers/phy/st/phy-stm32-usbphyc.c
+++ b/drivers/phy/st/phy-stm32-usbphyc.c
@@ -15,6 +15,7 @@
#include <linux/of_platform.h>
#include <linux/phy/phy.h>
#include <linux/reset.h>
+#include <linux/units.h>
#define STM32_USBPHYC_PLL 0x0
#define STM32_USBPHYC_MISC 0x8
@@ -47,7 +48,6 @@
#define PLL_FVCO_MHZ 2880
#define PLL_INFF_MIN_RATE_HZ 19200000
#define PLL_INFF_MAX_RATE_HZ 38400000
-#define HZ_PER_MHZ 1000000L
struct pll_params {
u8 ndiv;
diff --git a/drivers/thermal/devfreq_cooling.c b/drivers/thermal/devfreq_cooling.c
index 5a86cffd78f6..4310cb342a9f 100644
--- a/drivers/thermal/devfreq_cooling.c
+++ b/drivers/thermal/devfreq_cooling.c
@@ -18,10 +18,10 @@
#include <linux/pm_opp.h>
#include <linux/pm_qos.h>
#include <linux/thermal.h>
+#include <linux/units.h>
#include <trace/events/thermal.h>
-#define HZ_PER_KHZ 1000
#define SCALE_ERROR_MITIGATION 100
/**
diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index b91bc810a87e..bef8ad6bf466 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -143,6 +143,8 @@ struct virtio_mem {
* add_memory_driver_managed().
*/
const char *resource_name;
+ /* Memory group identification. */
+ int mgid;
/*
* We don't want to add too much memory if it's not getting onlined,
@@ -626,8 +628,8 @@ static int virtio_mem_add_memory(struct virtio_mem *vm, uint64_t addr,
addr + size - 1);
/* Memory might get onlined immediately. */
atomic64_add(size, &vm->offline_size);
- rc = add_memory_driver_managed(vm->nid, addr, size, vm->resource_name,
- MHP_MERGE_RESOURCE);
+ rc = add_memory_driver_managed(vm->mgid, addr, size, vm->resource_name,
+ MHP_MERGE_RESOURCE | MHP_NID_IS_MGID);
if (rc) {
atomic64_sub(size, &vm->offline_size);
dev_warn(&vm->vdev->dev, "adding memory failed: %d\n", rc);
@@ -677,7 +679,7 @@ static int virtio_mem_remove_memory(struct virtio_mem *vm, uint64_t addr,
dev_dbg(&vm->vdev->dev, "removing memory: 0x%llx - 0x%llx\n", addr,
addr + size - 1);
- rc = remove_memory(vm->nid, addr, size);
+ rc = remove_memory(addr, size);
if (!rc) {
atomic64_sub(size, &vm->offline_size);
/*
@@ -720,7 +722,7 @@ static int virtio_mem_offline_and_remove_memory(struct virtio_mem *vm,
"offlining and removing memory: 0x%llx - 0x%llx\n", addr,
addr + size - 1);
- rc = offline_and_remove_memory(vm->nid, addr, size);
+ rc = offline_and_remove_memory(addr, size);
if (!rc) {
atomic64_sub(size, &vm->offline_size);
/*
@@ -2569,6 +2571,7 @@ static bool virtio_mem_has_memory_added(struct virtio_mem *vm)
static int virtio_mem_probe(struct virtio_device *vdev)
{
struct virtio_mem *vm;
+ uint64_t unit_pages;
int rc;
BUILD_BUG_ON(sizeof(struct virtio_mem_req) != 24);
@@ -2603,6 +2606,16 @@ static int virtio_mem_probe(struct virtio_device *vdev)
if (rc)
goto out_del_vq;
+ /* use a single dynamic memory group to cover the whole memory device */
+ if (vm->in_sbm)
+ unit_pages = PHYS_PFN(memory_block_size_bytes());
+ else
+ unit_pages = PHYS_PFN(vm->bbm.bb_size);
+ rc = memory_group_register_dynamic(vm->nid, unit_pages);
+ if (rc < 0)
+ goto out_del_resource;
+ vm->mgid = rc;
+
/*
* If we still have memory plugged, we have to unplug all memory first.
* Registering our parent resource makes sure that this memory isn't
@@ -2617,7 +2630,7 @@ static int virtio_mem_probe(struct virtio_device *vdev)
vm->memory_notifier.notifier_call = virtio_mem_memory_notifier_cb;
rc = register_memory_notifier(&vm->memory_notifier);
if (rc)
- goto out_del_resource;
+ goto out_unreg_group;
rc = register_virtio_mem_device(vm);
if (rc)
goto out_unreg_mem;
@@ -2631,6 +2644,8 @@ static int virtio_mem_probe(struct virtio_device *vdev)
return 0;
out_unreg_mem:
unregister_memory_notifier(&vm->memory_notifier);
+out_unreg_group:
+ memory_group_unregister(vm->mgid);
out_del_resource:
virtio_mem_delete_resource(vm);
out_del_vq:
@@ -2695,6 +2710,7 @@ static void virtio_mem_remove(struct virtio_device *vdev)
} else {
virtio_mem_delete_resource(vm);
kfree_const(vm->resource_name);
+ memory_group_unregister(vm->mgid);
}
/* remove all tracking data - no locking needed */
diff --git a/fs/coredump.c b/fs/coredump.c
index 07afb5ddb1c4..3224dee44d30 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -782,10 +782,17 @@ void do_coredump(const kernel_siginfo_t *siginfo)
* filesystem.
*/
mnt_userns = file_mnt_user_ns(cprm.file);
- if (!uid_eq(i_uid_into_mnt(mnt_userns, inode), current_fsuid()))
+ if (!uid_eq(i_uid_into_mnt(mnt_userns, inode),
+ current_fsuid())) {
+ pr_info_ratelimited("Core dump to %s aborted: cannot preserve file owner\n",
+ cn.corename);
goto close_fail;
- if ((inode->i_mode & 0677) != 0600)
+ }
+ if ((inode->i_mode & 0677) != 0600) {
+ pr_info_ratelimited("Core dump to %s aborted: cannot preserve file permissions\n",
+ cn.corename);
goto close_fail;
+ }
if (!(cprm.file->f_mode & FMODE_CAN_WRITE))
goto close_fail;
if (do_truncate(mnt_userns, cprm.file->f_path.dentry,
@@ -1127,8 +1134,10 @@ int dump_vma_snapshot(struct coredump_params *cprm, int *vma_count,
mmap_write_unlock(mm);
- if (WARN_ON(i != *vma_count))
+ if (WARN_ON(i != *vma_count)) {
+ kvfree(*vma_meta);
return -EFAULT;
+ }
*vma_data_size_ptr = vma_data_size;
return 0;
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 1e596e1d0bba..648ed77f4164 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -723,7 +723,7 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi)
*/
call_rcu(&epi->rcu, epi_rcu_free);
- atomic_long_dec(&ep->user->epoll_watches);
+ percpu_counter_dec(&ep->user->epoll_watches);
return 0;
}
@@ -1439,7 +1439,6 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
{
int error, pwake = 0;
__poll_t revents;
- long user_watches;
struct epitem *epi;
struct ep_pqueue epq;
struct eventpoll *tep = NULL;
@@ -1449,11 +1448,15 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
lockdep_assert_irqs_enabled();
- user_watches = atomic_long_read(&ep->user->epoll_watches);
- if (unlikely(user_watches >= max_user_watches))
+ if (unlikely(percpu_counter_compare(&ep->user->epoll_watches,
+ max_user_watches) >= 0))
return -ENOSPC;
- if (!(epi = kmem_cache_zalloc(epi_cache, GFP_KERNEL)))
+ percpu_counter_inc(&ep->user->epoll_watches);
+
+ if (!(epi = kmem_cache_zalloc(epi_cache, GFP_KERNEL))) {
+ percpu_counter_dec(&ep->user->epoll_watches);
return -ENOMEM;
+ }
/* Item initialization follow here ... */
INIT_LIST_HEAD(&epi->rdllink);
@@ -1466,17 +1469,16 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
mutex_lock_nested(&tep->mtx, 1);
/* Add the current item to the list of active epoll hook for this file */
if (unlikely(attach_epitem(tfile, epi) < 0)) {
- kmem_cache_free(epi_cache, epi);
if (tep)
mutex_unlock(&tep->mtx);
+ kmem_cache_free(epi_cache, epi);
+ percpu_counter_dec(&ep->user->epoll_watches);
return -ENOMEM;
}
if (full_check && !tep)
list_file(tfile);
- atomic_long_inc(&ep->user->epoll_watches);
-
/*
* Add the current item to the RB tree. All RB tree operations are
* protected by "mtx", and ep_insert() is called with "mtx" held.
diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c
index 68e8d61e28dd..62f8a7ac19c8 100644
--- a/fs/nilfs2/sysfs.c
+++ b/fs/nilfs2/sysfs.c
@@ -51,11 +51,9 @@ static const struct sysfs_ops nilfs_##name##_attr_ops = { \
#define NILFS_DEV_INT_GROUP_TYPE(name, parent_name) \
static void nilfs_##name##_attr_release(struct kobject *kobj) \
{ \
- struct nilfs_sysfs_##parent_name##_subgroups *subgroups; \
- struct the_nilfs *nilfs = container_of(kobj->parent, \
- struct the_nilfs, \
- ns_##parent_name##_kobj); \
- subgroups = nilfs->ns_##parent_name##_subgroups; \
+ struct nilfs_sysfs_##parent_name##_subgroups *subgroups = container_of(kobj, \
+ struct nilfs_sysfs_##parent_name##_subgroups, \
+ sg_##name##_kobj); \
complete(&subgroups->sg_##name##_kobj_unregister); \
} \
static struct kobj_type nilfs_##name##_ktype = { \
@@ -81,12 +79,12 @@ static int nilfs_sysfs_create_##name##_group(struct the_nilfs *nilfs) \
err = kobject_init_and_add(kobj, &nilfs_##name##_ktype, parent, \
#name); \
if (err) \
- return err; \
- return 0; \
+ kobject_put(kobj); \
+ return err; \
} \
static void nilfs_sysfs_delete_##name##_group(struct the_nilfs *nilfs) \
{ \
- kobject_del(&nilfs->ns_##parent_name##_subgroups->sg_##name##_kobj); \
+ kobject_put(&nilfs->ns_##parent_name##_subgroups->sg_##name##_kobj); \
}
/************************************************************************
@@ -197,14 +195,14 @@ int nilfs_sysfs_create_snapshot_group(struct nilfs_root *root)
}
if (err)
- return err;
+ kobject_put(&root->snapshot_kobj);
- return 0;
+ return err;
}
void nilfs_sysfs_delete_snapshot_group(struct nilfs_root *root)
{
- kobject_del(&root->snapshot_kobj);
+ kobject_put(&root->snapshot_kobj);
}
/************************************************************************
@@ -986,7 +984,7 @@ int nilfs_sysfs_create_device_group(struct super_block *sb)
err = kobject_init_and_add(&nilfs->ns_dev_kobj, &nilfs_dev_ktype, NULL,
"%s", sb->s_id);
if (err)
- goto free_dev_subgroups;
+ goto cleanup_dev_kobject;
err = nilfs_sysfs_create_mounted_snapshots_group(nilfs);
if (err)
@@ -1023,9 +1021,7 @@ delete_mounted_snapshots_group:
nilfs_sysfs_delete_mounted_snapshots_group(nilfs);
cleanup_dev_kobject:
- kobject_del(&nilfs->ns_dev_kobj);
-
-free_dev_subgroups:
+ kobject_put(&nilfs->ns_dev_kobj);
kfree(nilfs->ns_dev_subgroups);
failed_create_device_group:
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 8b7b01a380ce..c8bfc01da5d7 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -792,14 +792,13 @@ nilfs_find_or_create_root(struct the_nilfs *nilfs, __u64 cno)
void nilfs_put_root(struct nilfs_root *root)
{
- if (refcount_dec_and_test(&root->count)) {
- struct the_nilfs *nilfs = root->nilfs;
+ struct the_nilfs *nilfs = root->nilfs;
- nilfs_sysfs_delete_snapshot_group(root);
-
- spin_lock(&nilfs->ns_cptree_lock);
+ if (refcount_dec_and_lock(&root->count, &nilfs->ns_cptree_lock)) {
rb_erase(&root->rb_node, &nilfs->ns_cptree);
spin_unlock(&nilfs->ns_cptree_lock);
+
+ nilfs_sysfs_delete_snapshot_group(root);
iput(root->ifile);
kfree(root);
diff --git a/fs/proc/array.c b/fs/proc/array.c
index ee0ce8cecc4a..49be8c8ef555 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -98,27 +98,17 @@
void proc_task_name(struct seq_file *m, struct task_struct *p, bool escape)
{
- char *buf;
- size_t size;
char tcomm[64];
- int ret;
if (p->flags & PF_WQ_WORKER)
wq_worker_comm(tcomm, sizeof(tcomm), p);
else
__get_task_comm(tcomm, sizeof(tcomm), p);
- size = seq_get_buf(m, &buf);
- if (escape) {
- ret = string_escape_str(tcomm, buf, size,
- ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\");
- if (ret >= size)
- ret = -1;
- } else {
- ret = strscpy(buf, tcomm, size);
- }
-
- seq_commit(m, ret);
+ if (escape)
+ seq_escape_str(m, tcomm, ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\");
+ else
+ seq_printf(m, "%.64s", tcomm);
}
/*
diff --git a/fs/proc/base.c b/fs/proc/base.c
index e5b5f7709d48..533d5836eb9a 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -95,6 +95,7 @@
#include <linux/posix-timers.h>
#include <linux/time_namespace.h>
#include <linux/resctrl.h>
+#include <linux/cn_proc.h>
#include <trace/events/oom.h>
#include "internal.h"
#include "fd.h"
@@ -1674,8 +1675,10 @@ static ssize_t comm_write(struct file *file, const char __user *buf,
if (!p)
return -ESRCH;
- if (same_thread_group(current, p))
+ if (same_thread_group(current, p)) {
set_task_comm(p, buffer);
+ proc_comm_connector(p);
+ }
else
count = -EINVAL;
diff --git a/include/asm-generic/early_ioremap.h b/include/asm-generic/early_ioremap.h
index 9def22e6e2b3..9d0479f50f97 100644
--- a/include/asm-generic/early_ioremap.h
+++ b/include/asm-generic/early_ioremap.h
@@ -19,12 +19,6 @@ extern void *early_memremap_prot(resource_size_t phys_addr,
extern void early_iounmap(void __iomem *addr, unsigned long size);
extern void early_memunmap(void *addr, unsigned long size);
-/*
- * Weak function called by early_ioremap_reset(). It does nothing, but
- * architectures may provide their own version to do any needed cleanups.
- */
-extern void early_ioremap_shutdown(void);
-
#if defined(CONFIG_GENERIC_EARLY_IOREMAP) && defined(CONFIG_MMU)
/* Arch-specific initialization */
extern void early_ioremap_init(void);
diff --git a/include/linux/damon.h b/include/linux/damon.h
new file mode 100644
index 000000000000..d68b67b8d458
--- /dev/null
+++ b/include/linux/damon.h
@@ -0,0 +1,268 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * DAMON api
+ *
+ * Author: SeongJae Park <sjpark@amazon.de>
+ */
+
+#ifndef _DAMON_H_
+#define _DAMON_H_
+
+#include <linux/mutex.h>
+#include <linux/time64.h>
+#include <linux/types.h>
+
+/* Minimal region size. Every damon_region is aligned by this. */
+#define DAMON_MIN_REGION PAGE_SIZE
+
+/**
+ * struct damon_addr_range - Represents an address region of [@start, @end).
+ * @start: Start address of the region (inclusive).
+ * @end: End address of the region (exclusive).
+ */
+struct damon_addr_range {
+ unsigned long start;
+ unsigned long end;
+};
+
+/**
+ * struct damon_region - Represents a monitoring target region.
+ * @ar: The address range of the region.
+ * @sampling_addr: Address of the sample for the next access check.
+ * @nr_accesses: Access frequency of this region.
+ * @list: List head for siblings.
+ */
+struct damon_region {
+ struct damon_addr_range ar;
+ unsigned long sampling_addr;
+ unsigned int nr_accesses;
+ struct list_head list;
+};
+
+/**
+ * struct damon_target - Represents a monitoring target.
+ * @id: Unique identifier for this target.
+ * @nr_regions: Number of monitoring target regions of this target.
+ * @regions_list: Head of the monitoring target regions of this target.
+ * @list: List head for siblings.
+ *
+ * Each monitoring context could have multiple targets. For example, a context
+ * for virtual memory address spaces could have multiple target processes. The
+ * @id of each target should be unique among the targets of the context. For
+ * example, in the virtual address monitoring context, it could be a pidfd or
+ * an address of an mm_struct.
+ */
+struct damon_target {
+ unsigned long id;
+ unsigned int nr_regions;
+ struct list_head regions_list;
+ struct list_head list;
+};
+
+struct damon_ctx;
+
+/**
+ * struct damon_primitive Monitoring primitives for given use cases.
+ *
+ * @init: Initialize primitive-internal data structures.
+ * @update: Update primitive-internal data structures.
+ * @prepare_access_checks: Prepare next access check of target regions.
+ * @check_accesses: Check the accesses to target regions.
+ * @reset_aggregated: Reset aggregated accesses monitoring results.
+ * @target_valid: Determine if the target is valid.
+ * @cleanup: Clean up the context.
+ *
+ * DAMON can be extended for various address spaces and usages. For this,
+ * users should register the low level primitives for their target address
+ * space and usecase via the &damon_ctx.primitive. Then, the monitoring thread
+ * (&damon_ctx.kdamond) calls @init and @prepare_access_checks before starting
+ * the monitoring, @update after each &damon_ctx.primitive_update_interval, and
+ * @check_accesses, @target_valid and @prepare_access_checks after each
+ * &damon_ctx.sample_interval. Finally, @reset_aggregated is called after each
+ * &damon_ctx.aggr_interval.
+ *
+ * @init should initialize primitive-internal data structures. For example,
+ * this could be used to construct proper monitoring target regions and link
+ * those to @damon_ctx.adaptive_targets.
+ * @update should update the primitive-internal data structures. For example,
+ * this could be used to update monitoring target regions for current status.
+ * @prepare_access_checks should manipulate the monitoring regions to be
+ * prepared for the next access check.
+ * @check_accesses should check the accesses to each region that made after the
+ * last preparation and update the number of observed accesses of each region.
+ * It should also return max number of observed accesses that made as a result
+ * of its update. The value will be used for regions adjustment threshold.
+ * @reset_aggregated should reset the access monitoring results that aggregated
+ * by @check_accesses.
+ * @target_valid should check whether the target is still valid for the
+ * monitoring.
+ * @cleanup is called from @kdamond just before its termination.
+ */
+struct damon_primitive {
+ void (*init)(struct damon_ctx *context);
+ void (*update)(struct damon_ctx *context);
+ void (*prepare_access_checks)(struct damon_ctx *context);
+ unsigned int (*check_accesses)(struct damon_ctx *context);
+ void (*reset_aggregated)(struct damon_ctx *context);
+ bool (*target_valid)(void *target);
+ void (*cleanup)(struct damon_ctx *context);
+};
+
+/*
+ * struct damon_callback Monitoring events notification callbacks.
+ *
+ * @before_start: Called before starting the monitoring.
+ * @after_sampling: Called after each sampling.
+ * @after_aggregation: Called after each aggregation.
+ * @before_terminate: Called before terminating the monitoring.
+ * @private: User private data.
+ *
+ * The monitoring thread (&damon_ctx.kdamond) calls @before_start and
+ * @before_terminate just before starting and finishing the monitoring,
+ * respectively. Therefore, those are good places for installing and cleaning
+ * @private.
+ *
+ * The monitoring thread calls @after_sampling and @after_aggregation for each
+ * of the sampling intervals and aggregation intervals, respectively.
+ * Therefore, users can safely access the monitoring results without additional
+ * protection. For the reason, users are recommended to use these callback for
+ * the accesses to the results.
+ *
+ * If any callback returns non-zero, monitoring stops.
+ */
+struct damon_callback {
+ void *private;
+
+ int (*before_start)(struct damon_ctx *context);
+ int (*after_sampling)(struct damon_ctx *context);
+ int (*after_aggregation)(struct damon_ctx *context);
+ int (*before_terminate)(struct damon_ctx *context);
+};
+
+/**
+ * struct damon_ctx - Represents a context for each monitoring. This is the
+ * main interface that allows users to set the attributes and get the results
+ * of the monitoring.
+ *
+ * @sample_interval: The time between access samplings.
+ * @aggr_interval: The time between monitor results aggregations.
+ * @primitive_update_interval: The time between monitoring primitive updates.
+ *
+ * For each @sample_interval, DAMON checks whether each region is accessed or
+ * not. It aggregates and keeps the access information (number of accesses to
+ * each region) for @aggr_interval time. DAMON also checks whether the target
+ * memory regions need update (e.g., by ``mmap()`` calls from the application,
+ * in case of virtual memory monitoring) and applies the changes for each
+ * @primitive_update_interval. All time intervals are in micro-seconds.
+ * Please refer to &struct damon_primitive and &struct damon_callback for more
+ * detail.
+ *
+ * @kdamond: Kernel thread who does the monitoring.
+ * @kdamond_stop: Notifies whether kdamond should stop.
+ * @kdamond_lock: Mutex for the synchronizations with @kdamond.
+ *
+ * For each monitoring context, one kernel thread for the monitoring is
+ * created. The pointer to the thread is stored in @kdamond.
+ *
+ * Once started, the monitoring thread runs until explicitly required to be
+ * terminated or every monitoring target is invalid. The validity of the
+ * targets is checked via the &damon_primitive.target_valid of @primitive. The
+ * termination can also be explicitly requested by writing non-zero to
+ * @kdamond_stop. The thread sets @kdamond to NULL when it terminates.
+ * Therefore, users can know whether the monitoring is ongoing or terminated by
+ * reading @kdamond. Reads and writes to @kdamond and @kdamond_stop from
+ * outside of the monitoring thread must be protected by @kdamond_lock.
+ *
+ * Note that the monitoring thread protects only @kdamond and @kdamond_stop via
+ * @kdamond_lock. Accesses to other fields must be protected by themselves.
+ *
+ * @primitive: Set of monitoring primitives for given use cases.
+ * @callback: Set of callbacks for monitoring events notifications.
+ *
+ * @min_nr_regions: The minimum number of adaptive monitoring regions.
+ * @max_nr_regions: The maximum number of adaptive monitoring regions.
+ * @adaptive_targets: Head of monitoring targets (&damon_target) list.
+ */
+struct damon_ctx {
+ unsigned long sample_interval;
+ unsigned long aggr_interval;
+ unsigned long primitive_update_interval;
+
+/* private: internal use only */
+ struct timespec64 last_aggregation;
+ struct timespec64 last_primitive_update;
+
+/* public: */
+ struct task_struct *kdamond;
+ bool kdamond_stop;
+ struct mutex kdamond_lock;
+
+ struct damon_primitive primitive;
+ struct damon_callback callback;
+
+ unsigned long min_nr_regions;
+ unsigned long max_nr_regions;
+ struct list_head adaptive_targets;
+};
+
+#define damon_next_region(r) \
+ (container_of(r->list.next, struct damon_region, list))
+
+#define damon_prev_region(r) \
+ (container_of(r->list.prev, struct damon_region, list))
+
+#define damon_for_each_region(r, t) \
+ list_for_each_entry(r, &t->regions_list, list)
+
+#define damon_for_each_region_safe(r, next, t) \
+ list_for_each_entry_safe(r, next, &t->regions_list, list)
+
+#define damon_for_each_target(t, ctx) \
+ list_for_each_entry(t, &(ctx)->adaptive_targets, list)
+
+#define damon_for_each_target_safe(t, next, ctx) \
+ list_for_each_entry_safe(t, next, &(ctx)->adaptive_targets, list)
+
+#ifdef CONFIG_DAMON
+
+struct damon_region *damon_new_region(unsigned long start, unsigned long end);
+inline void damon_insert_region(struct damon_region *r,
+ struct damon_region *prev, struct damon_region *next,
+ struct damon_target *t);
+void damon_add_region(struct damon_region *r, struct damon_target *t);
+void damon_destroy_region(struct damon_region *r, struct damon_target *t);
+
+struct damon_target *damon_new_target(unsigned long id);
+void damon_add_target(struct damon_ctx *ctx, struct damon_target *t);
+void damon_free_target(struct damon_target *t);
+void damon_destroy_target(struct damon_target *t);
+unsigned int damon_nr_regions(struct damon_target *t);
+
+struct damon_ctx *damon_new_ctx(void);
+void damon_destroy_ctx(struct damon_ctx *ctx);
+int damon_set_targets(struct damon_ctx *ctx,
+ unsigned long *ids, ssize_t nr_ids);
+int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int,
+ unsigned long aggr_int, unsigned long primitive_upd_int,
+ unsigned long min_nr_reg, unsigned long max_nr_reg);
+int damon_nr_running_ctxs(void);
+
+int damon_start(struct damon_ctx **ctxs, int nr_ctxs);
+int damon_stop(struct damon_ctx **ctxs, int nr_ctxs);
+
+#endif /* CONFIG_DAMON */
+
+#ifdef CONFIG_DAMON_VADDR
+
+/* Monitoring primitives for virtual memory address spaces */
+void damon_va_init(struct damon_ctx *ctx);
+void damon_va_update(struct damon_ctx *ctx);
+void damon_va_prepare_access_checks(struct damon_ctx *ctx);
+unsigned int damon_va_check_accesses(struct damon_ctx *ctx);
+bool damon_va_target_valid(void *t);
+void damon_va_cleanup(struct damon_ctx *ctx);
+void damon_va_set_primitives(struct damon_ctx *ctx);
+
+#endif /* CONFIG_DAMON_VADDR */
+
+#endif /* _DAMON_H */
diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h
index 7902c7d8b55f..4aa1031d3e4c 100644
--- a/include/linux/highmem-internal.h
+++ b/include/linux/highmem-internal.h
@@ -90,7 +90,11 @@ static inline void __kunmap_local(void *vaddr)
static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
{
- preempt_disable();
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ migrate_disable();
+ else
+ preempt_disable();
+
pagefault_disable();
return __kmap_local_page_prot(page, prot);
}
@@ -102,7 +106,11 @@ static inline void *kmap_atomic(struct page *page)
static inline void *kmap_atomic_pfn(unsigned long pfn)
{
- preempt_disable();
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ migrate_disable();
+ else
+ preempt_disable();
+
pagefault_disable();
return __kmap_local_pfn_prot(pfn, kmap_prot);
}
@@ -111,7 +119,10 @@ static inline void __kunmap_atomic(void *addr)
{
kunmap_local_indexed(addr);
pagefault_enable();
- preempt_enable();
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ migrate_enable();
+ else
+ preempt_enable();
}
unsigned int __nr_free_highpages(void);
@@ -179,7 +190,10 @@ static inline void __kunmap_local(void *addr)
static inline void *kmap_atomic(struct page *page)
{
- preempt_disable();
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ migrate_disable();
+ else
+ preempt_disable();
pagefault_disable();
return page_address(page);
}
@@ -200,7 +214,10 @@ static inline void __kunmap_atomic(void *addr)
kunmap_flush_on_unmap(addr);
#endif
pagefault_enable();
- preempt_enable();
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ migrate_enable();
+ else
+ preempt_enable();
}
static inline unsigned int nr_free_highpages(void) { return 0; }
diff --git a/include/linux/memory.h b/include/linux/memory.h
index d9a0b61cd432..7efc0a7c14c9 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -23,6 +23,48 @@
#define MIN_MEMORY_BLOCK_SIZE (1UL << SECTION_SIZE_BITS)
+/**
+ * struct memory_group - a logical group of memory blocks
+ * @nid: The node id for all memory blocks inside the memory group.
+ * @blocks: List of all memory blocks belonging to this memory group.
+ * @present_kernel_pages: Present (online) memory outside ZONE_MOVABLE of this
+ * memory group.
+ * @present_movable_pages: Present (online) memory in ZONE_MOVABLE of this
+ * memory group.
+ * @is_dynamic: The memory group type: static vs. dynamic
+ * @s.max_pages: Valid with &memory_group.is_dynamic == false. The maximum
+ * number of pages we'll have in this static memory group.
+ * @d.unit_pages: Valid with &memory_group.is_dynamic == true. Unit in pages
+ * in which memory is added/removed in this dynamic memory group.
+ * This granularity defines the alignment of a unit in physical
+ * address space; it has to be at least as big as a single
+ * memory block.
+ *
+ * A memory group logically groups memory blocks; each memory block
+ * belongs to at most one memory group. A memory group corresponds to
+ * a memory device, such as a DIMM or a NUMA node, which spans multiple
+ * memory blocks and might even span multiple non-contiguous physical memory
+ * ranges.
+ *
+ * Modification of members after registration is serialized by memory
+ * hot(un)plug code.
+ */
+struct memory_group {
+ int nid;
+ struct list_head memory_blocks;
+ unsigned long present_kernel_pages;
+ unsigned long present_movable_pages;
+ bool is_dynamic;
+ union {
+ struct {
+ unsigned long max_pages;
+ } s;
+ struct {
+ unsigned long unit_pages;
+ } d;
+ };
+};
+
struct memory_block {
unsigned long start_section_nr;
unsigned long state; /* serialized by the dev->lock */
@@ -34,6 +76,8 @@ struct memory_block {
* lay at the beginning of the memory block.
*/
unsigned long nr_vmemmap_pages;
+ struct memory_group *group; /* group (if any) for this block */
+ struct list_head group_next; /* next block inside memory group */
};
int arch_get_memory_phys_device(unsigned long start_pfn);
@@ -86,7 +130,8 @@ static inline int memory_notify(unsigned long val, void *v)
extern int register_memory_notifier(struct notifier_block *nb);
extern void unregister_memory_notifier(struct notifier_block *nb);
int create_memory_block_devices(unsigned long start, unsigned long size,
- unsigned long vmemmap_pages);
+ unsigned long vmemmap_pages,
+ struct memory_group *group);
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);
@@ -96,6 +141,14 @@ extern int walk_memory_blocks(unsigned long start, unsigned long size,
void *arg, walk_memory_blocks_func_t func);
extern int for_each_memory_block(void *arg, walk_memory_blocks_func_t func);
#define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION<<PAGE_SHIFT)
+
+extern int memory_group_register_static(int nid, unsigned long max_pages);
+extern int memory_group_register_dynamic(int nid, unsigned long unit_pages);
+extern int memory_group_unregister(int mgid);
+struct memory_group *memory_group_find_by_id(int mgid);
+typedef int (*walk_memory_groups_func_t)(struct memory_group *, void *);
+int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func,
+ struct memory_group *excluded, void *arg);
#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
#ifdef CONFIG_MEMORY_HOTPLUG
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index a7fd2c3ccb77..e5a867c950b2 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -12,6 +12,7 @@ struct zone;
struct pglist_data;
struct mem_section;
struct memory_block;
+struct memory_group;
struct resource;
struct vmem_altmap;
@@ -50,6 +51,11 @@ typedef int __bitwise mhp_t;
* Only selected architectures support it with SPARSE_VMEMMAP.
*/
#define MHP_MEMMAP_ON_MEMORY ((__force mhp_t)BIT(1))
+/*
+ * The nid field specifies a memory group id (mgid) instead. The memory group
+ * implies the node id (nid).
+ */
+#define MHP_NID_IS_MGID ((__force mhp_t)BIT(2))
/*
* Extended parameters for memory hotplug:
@@ -95,13 +101,15 @@ static inline void zone_seqlock_init(struct zone *zone)
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);
-extern void adjust_present_page_count(struct zone *zone, long nr_pages);
+extern void adjust_present_page_count(struct page *page,
+ struct memory_group *group,
+ long nr_pages);
/* VM interface that may be used by firmware interface */
extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages,
struct zone *zone);
extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages);
extern int online_pages(unsigned long pfn, unsigned long nr_pages,
- struct zone *zone);
+ struct zone *zone, struct memory_group *group);
extern struct zone *test_pages_in_a_zone(unsigned long start_pfn,
unsigned long end_pfn);
extern void __offline_isolated_pages(unsigned long start_pfn,
@@ -130,8 +138,7 @@ static inline bool movable_node_is_enabled(void)
return movable_node_enabled;
}
-extern void arch_remove_memory(int nid, u64 start, u64 size,
- struct vmem_altmap *altmap);
+extern void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap);
extern void __remove_pages(unsigned long start_pfn, unsigned long nr_pages,
struct vmem_altmap *altmap);
@@ -292,25 +299,27 @@ static inline void pgdat_resize_init(struct pglist_data *pgdat) {}
#ifdef CONFIG_MEMORY_HOTREMOVE
extern void try_offline_node(int nid);
-extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
-extern int remove_memory(int nid, u64 start, u64 size);
-extern void __remove_memory(int nid, u64 start, u64 size);
-extern int offline_and_remove_memory(int nid, u64 start, u64 size);
+extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
+ struct memory_group *group);
+extern int remove_memory(u64 start, u64 size);
+extern void __remove_memory(u64 start, u64 size);
+extern int offline_and_remove_memory(u64 start, u64 size);
#else
static inline void try_offline_node(int nid) {}
-static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
+static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
+ struct memory_group *group)
{
return -EINVAL;
}
-static inline int remove_memory(int nid, u64 start, u64 size)
+static inline int remove_memory(u64 start, u64 size)
{
return -EBUSY;
}
-static inline void __remove_memory(int nid, u64 start, u64 size) {}
+static inline void __remove_memory(u64 start, u64 size) {}
#endif /* CONFIG_MEMORY_HOTREMOVE */
extern void set_zone_contiguous(struct zone *zone);
@@ -339,7 +348,8 @@ extern void sparse_remove_section(struct mem_section *ms,
unsigned long map_offset, struct vmem_altmap *altmap);
extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
unsigned long pnum);
-extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn,
+extern struct zone *zone_for_pfn_range(int online_type, int nid,
+ struct memory_group *group, unsigned long start_pfn,
unsigned long nr_pages);
extern int arch_create_linear_mapping(int nid, u64 start, u64 size,
struct mhp_params *params);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 1bd5f5955f9a..6a1d79d84675 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -540,6 +540,10 @@ struct zone {
* is calculated as:
* present_pages = spanned_pages - absent_pages(pages in holes);
*
+ * present_early_pages is present pages existing within the zone
+ * located on memory available since early boot, excluding hotplugged
+ * memory.
+ *
* managed_pages is present pages managed by the buddy system, which
* is calculated as (reserved_pages includes pages allocated by the
* bootmem allocator):
@@ -572,6 +576,9 @@ struct zone {
atomic_long_t managed_pages;
unsigned long spanned_pages;
unsigned long present_pages;
+#if defined(CONFIG_MEMORY_HOTPLUG)
+ unsigned long present_early_pages;
+#endif
#ifdef CONFIG_CMA
unsigned long cma_pages;
#endif
@@ -1525,18 +1532,6 @@ void sparse_init(void);
#define subsection_map_init(_pfn, _nr_pages) do {} while (0)
#endif /* CONFIG_SPARSEMEM */
-/*
- * If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we
- * need to check pfn validity within that MAX_ORDER_NR_PAGES block.
- * pfn_valid_within() should be used in this case; we optimise this away
- * when we have no holes within a MAX_ORDER_NR_PAGES block.
- */
-#ifdef CONFIG_HOLES_IN_ZONE
-#define pfn_valid_within(pfn) pfn_valid(pfn)
-#else
-#define pfn_valid_within(pfn) (1)
-#endif
-
#endif /* !__GENERATING_BOUNDS.H */
#endif /* !__ASSEMBLY__ */
#endif /* _LINUX_MMZONE_H */
diff --git a/include/linux/once.h b/include/linux/once.h
index ae6f4eb41cbe..d361fb14ac3a 100644
--- a/include/linux/once.h
+++ b/include/linux/once.h
@@ -16,7 +16,7 @@ void __do_once_done(bool *done, struct static_key_true *once_key,
* out the condition into a nop. DO_ONCE() guarantees type safety of
* arguments!
*
- * Not that the following is not equivalent ...
+ * Note that the following is not equivalent ...
*
* DO_ONCE(func, arg);
* DO_ONCE(func, arg);
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 4ca160053b1f..a558d67ee86f 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -131,7 +131,7 @@ enum pageflags {
#ifdef CONFIG_MEMORY_FAILURE
PG_hwpoison, /* hardware poisoned page. Don't touch */
#endif
-#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
+#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT)
PG_young,
PG_idle,
#endif
@@ -178,6 +178,8 @@ enum pageflags {
PG_reported = PG_uptodate,
};
+#define PAGEFLAGS_MASK ((1UL << NR_PAGEFLAGS) - 1)
+
#ifndef __GENERATING_BOUNDS_H
static inline unsigned long _compound_head(const struct page *page)
@@ -439,7 +441,7 @@ PAGEFLAG_FALSE(HWPoison)
#define __PG_HWPOISON 0
#endif
-#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
+#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT)
TESTPAGEFLAG(Young, young, PF_ANY)
SETPAGEFLAG(Young, young, PF_ANY)
TESTCLEARFLAG(Young, young, PF_ANY)
@@ -831,7 +833,7 @@ static inline void ClearPageSlabPfmemalloc(struct page *page)
* alloc-free cycle to prevent from reusing the page.
*/
#define PAGE_FLAGS_CHECK_AT_PREP \
- (((1UL << NR_PAGEFLAGS) - 1) & ~__PG_HWPOISON)
+ (PAGEFLAGS_MASK & ~__PG_HWPOISON)
#define PAGE_FLAGS_PRIVATE \
(1UL << PG_private | 1UL << PG_private_2)
diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h
index aff81ba31bd8..fabb2e1e087f 100644
--- a/include/linux/page_ext.h
+++ b/include/linux/page_ext.h
@@ -19,7 +19,7 @@ struct page_ext_operations {
enum page_ext_flags {
PAGE_EXT_OWNER,
PAGE_EXT_OWNER_ALLOCATED,
-#if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT)
+#if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT)
PAGE_EXT_YOUNG,
PAGE_EXT_IDLE,
#endif
diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h
index 1e894d34bdce..d8a6aecf99cb 100644
--- a/include/linux/page_idle.h
+++ b/include/linux/page_idle.h
@@ -6,7 +6,7 @@
#include <linux/page-flags.h>
#include <linux/page_ext.h>
-#ifdef CONFIG_IDLE_PAGE_TRACKING
+#ifdef CONFIG_PAGE_IDLE_FLAG
#ifdef CONFIG_64BIT
static inline bool page_is_young(struct page *page)
@@ -106,7 +106,7 @@ static inline void clear_page_idle(struct page *page)
}
#endif /* CONFIG_64BIT */
-#else /* !CONFIG_IDLE_PAGE_TRACKING */
+#else /* !CONFIG_PAGE_IDLE_FLAG */
static inline bool page_is_young(struct page *page)
{
@@ -135,6 +135,6 @@ static inline void clear_page_idle(struct page *page)
{
}
-#endif /* CONFIG_IDLE_PAGE_TRACKING */
+#endif /* CONFIG_PAGE_IDLE_FLAG */
#endif /* _LINUX_MM_PAGE_IDLE_H */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 5dcf446f42e5..62db6b0176b9 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -521,18 +521,17 @@ static inline struct page *read_mapping_page(struct address_space *mapping,
*/
static inline pgoff_t page_to_index(struct page *page)
{
- pgoff_t pgoff;
+ struct page *head;
if (likely(!PageTransTail(page)))
return page->index;
+ head = compound_head(page);
/*
* We don't initialize ->index for tail pages: calculate based on
* head page
*/
- pgoff = compound_head(page)->index;
- pgoff += page - compound_head(page);
- return pgoff;
+ return head->index + page - head;
}
extern pgoff_t hugetlb_basepage_index(struct page *page);
diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h
index 2462f7d07695..00ed419dd464 100644
--- a/include/linux/sched/user.h
+++ b/include/linux/sched/user.h
@@ -4,6 +4,7 @@
#include <linux/uidgid.h>
#include <linux/atomic.h>
+#include <linux/percpu_counter.h>
#include <linux/refcount.h>
#include <linux/ratelimit.h>
@@ -13,7 +14,7 @@
struct user_struct {
refcount_t __count; /* reference count */
#ifdef CONFIG_EPOLL
- atomic_long_t epoll_watches; /* The number of file descriptors currently watched */
+ struct percpu_counter epoll_watches; /* The number of file descriptors currently watched */
#endif
unsigned long unix_inflight; /* How many files in flight in unix sockets */
atomic_long_t pipe_bufs; /* how many pages are allocated in pipe buffers */
diff --git a/include/linux/threads.h b/include/linux/threads.h
index 18d5a74bcc3d..c34173e6c5f1 100644
--- a/include/linux/threads.h
+++ b/include/linux/threads.h
@@ -38,7 +38,7 @@
* Define a minimum number of pids per cpu. Heuristically based
* on original pid max of 32k for 32 cpus. Also, increase the
* minimum settable value for pid_max on the running system based
- * on similar defaults. See kernel/pid.c:pidmap_init() for details.
+ * on similar defaults. See kernel/pid.c:pid_idr_init() for details.
*/
#define PIDS_PER_CPU_DEFAULT 1024
#define PIDS_PER_CPU_MIN 8
diff --git a/include/linux/units.h b/include/linux/units.h
index 4a25e0cc8fb3..681fc652e3d7 100644
--- a/include/linux/units.h
+++ b/include/linux/units.h
@@ -20,9 +20,13 @@
#define PICO 1000000000000ULL
#define FEMTO 1000000000000000ULL
-#define MILLIWATT_PER_WATT 1000L
-#define MICROWATT_PER_MILLIWATT 1000L
-#define MICROWATT_PER_WATT 1000000L
+#define HZ_PER_KHZ 1000UL
+#define KHZ_PER_MHZ 1000UL
+#define HZ_PER_MHZ 1000000UL
+
+#define MILLIWATT_PER_WATT 1000UL
+#define MICROWATT_PER_MILLIWATT 1000UL
+#define MICROWATT_PER_WATT 1000000UL
#define ABSOLUTE_ZERO_MILLICELSIUS -273150
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 2644425b6dce..671d402c3778 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -225,9 +225,6 @@ static inline bool is_vm_area_hugepages(const void *addr)
}
#ifdef CONFIG_MMU
-int vmap_range(unsigned long addr, unsigned long end,
- phys_addr_t phys_addr, pgprot_t prot,
- unsigned int max_page_shift);
void vunmap_range(unsigned long addr, unsigned long end);
static inline void set_vm_flush_reset_perms(void *addr)
{
diff --git a/include/trace/events/damon.h b/include/trace/events/damon.h
new file mode 100644
index 000000000000..2f422f4f1fb9
--- /dev/null
+++ b/include/trace/events/damon.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM damon
+
+#if !defined(_TRACE_DAMON_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_DAMON_H
+
+#include <linux/damon.h>
+#include <linux/types.h>
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(damon_aggregated,
+
+ TP_PROTO(struct damon_target *t, struct damon_region *r,
+ unsigned int nr_regions),
+
+ TP_ARGS(t, r, nr_regions),
+
+ TP_STRUCT__entry(
+ __field(unsigned long, target_id)
+ __field(unsigned int, nr_regions)
+ __field(unsigned long, start)
+ __field(unsigned long, end)
+ __field(unsigned int, nr_accesses)
+ ),
+
+ TP_fast_assign(
+ __entry->target_id = t->id;
+ __entry->nr_regions = nr_regions;
+ __entry->start = r->ar.start;
+ __entry->end = r->ar.end;
+ __entry->nr_accesses = r->nr_accesses;
+ ),
+
+ TP_printk("target_id=%lu nr_regions=%u %lu-%lu: %u",
+ __entry->target_id, __entry->nr_regions,
+ __entry->start, __entry->end, __entry->nr_accesses)
+);
+
+#endif /* _TRACE_DAMON_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 0b53e855c4ac..116ed4d5d0f8 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -75,7 +75,7 @@
#define IF_HAVE_PG_HWPOISON(flag,string)
#endif
-#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
+#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT)
#define IF_HAVE_PG_IDLE(flag,string) ,{1UL << flag, string}
#else
#define IF_HAVE_PG_IDLE(flag,string)
diff --git a/include/trace/events/page_ref.h b/include/trace/events/page_ref.h
index 5d2ea93956ce..8a99c1cd417b 100644
--- a/include/trace/events/page_ref.h
+++ b/include/trace/events/page_ref.h
@@ -38,7 +38,7 @@ DECLARE_EVENT_CLASS(page_ref_mod_template,
TP_printk("pfn=0x%lx flags=%s count=%d mapcount=%d mapping=%p mt=%d val=%d",
__entry->pfn,
- show_page_flags(__entry->flags & ((1UL << NR_PAGEFLAGS) - 1)),
+ show_page_flags(__entry->flags & PAGEFLAGS_MASK),
__entry->count,
__entry->mapcount, __entry->mapping, __entry->mt,
__entry->val)
@@ -88,7 +88,7 @@ DECLARE_EVENT_CLASS(page_ref_mod_and_test_template,
TP_printk("pfn=0x%lx flags=%s count=%d mapcount=%d mapping=%p mt=%d val=%d ret=%d",
__entry->pfn,
- show_page_flags(__entry->flags & ((1UL << NR_PAGEFLAGS) - 1)),
+ show_page_flags(__entry->flags & PAGEFLAGS_MASK),
__entry->count,
__entry->mapcount, __entry->mapping, __entry->mt,
__entry->val, __entry->ret)
diff --git a/init/initramfs.c b/init/initramfs.c
index af27abc59643..a842c0544745 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -15,6 +15,7 @@
#include <linux/mm.h>
#include <linux/namei.h>
#include <linux/init_syscalls.h>
+#include <linux/umh.h>
static ssize_t __init xwrite(struct file *file, const char *p, size_t count,
loff_t *pos)
@@ -727,6 +728,7 @@ static int __init populate_rootfs(void)
{
initramfs_cookie = async_schedule_domain(do_populate_rootfs, NULL,
&initramfs_domain);
+ usermodehelper_enable();
if (!initramfs_async)
wait_for_initramfs();
return 0;
diff --git a/init/main.c b/init/main.c
index daad6979f782..733e1471d95f 100644
--- a/init/main.c
+++ b/init/main.c
@@ -777,6 +777,8 @@ void __init __weak poking_init(void) { }
void __init __weak pgtable_cache_init(void) { }
+void __init __weak trap_init(void) { }
+
bool initcall_debug;
core_param(initcall_debug, initcall_debug, bool, 0644);
@@ -1392,7 +1394,6 @@ static void __init do_basic_setup(void)
driver_init();
init_irq_proc();
do_ctors();
- usermodehelper_enable();
do_initcalls();
}
diff --git a/init/noinitramfs.c b/init/noinitramfs.c
index 3d62b07f3bb9..d1d26b93d25c 100644
--- a/init/noinitramfs.c
+++ b/init/noinitramfs.c
@@ -10,6 +10,7 @@
#include <linux/kdev_t.h>
#include <linux/syscalls.h>
#include <linux/init_syscalls.h>
+#include <linux/umh.h>
/*
* Create a simple rootfs that is similar to the default initramfs
@@ -18,6 +19,7 @@ static int __init default_rootfs(void)
{
int err;
+ usermodehelper_enable();
err = init_mkdir("/dev", 0755);
if (err < 0)
goto out;
diff --git a/ipc/util.c b/ipc/util.c
index 0027e47626b7..d48d8cfa1f3f 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -788,21 +788,13 @@ struct pid_namespace *ipc_seq_pid_ns(struct seq_file *s)
static struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t pos,
loff_t *new_pos)
{
- struct kern_ipc_perm *ipc;
- int total, id;
-
- total = 0;
- for (id = 0; id < pos && total < ids->in_use; id++) {
- ipc = idr_find(&ids->ipcs_idr, id);
- if (ipc != NULL)
- total++;
- }
+ struct kern_ipc_perm *ipc = NULL;
+ int max_idx = ipc_get_maxidx(ids);
- ipc = NULL;
- if (total >= ids->in_use)
+ if (max_idx == -1 || pos > max_idx)
goto out;
- for (; pos < ipc_mni; pos++) {
+ for (; pos <= max_idx; pos++) {
ipc = idr_find(&ids->ipcs_idr, pos);
if (ipc != NULL) {
rcu_read_lock();
diff --git a/kernel/acct.c b/kernel/acct.c
index a64102be2bb0..23a7ab8e6cbc 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -478,7 +478,7 @@ static void do_acct_process(struct bsd_acct_struct *acct)
/*
* Accounting records are not subject to resource limits.
*/
- flim = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
+ flim = rlimit(RLIMIT_FSIZE);
current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY;
/* Perform file operations on behalf of whoever enabled accounting */
orig_cred = override_creds(file->f_cred);
diff --git a/kernel/fork.c b/kernel/fork.c
index 6d2e10a3df0b..ff5be23800af 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1262,7 +1262,6 @@ struct file *get_mm_exe_file(struct mm_struct *mm)
rcu_read_unlock();
return exe_file;
}
-EXPORT_SYMBOL(get_mm_exe_file);
/**
* get_task_exe_file - acquire a reference to the task's executable file
@@ -1285,7 +1284,6 @@ struct file *get_task_exe_file(struct task_struct *task)
task_unlock(task);
return exe_file;
}
-EXPORT_SYMBOL(get_task_exe_file);
/**
* get_task_mm - acquire a reference to the task's mm
diff --git a/kernel/profile.c b/kernel/profile.c
index c2ebddb5e974..eb9c7f0f5ac5 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -41,7 +41,8 @@ struct profile_hit {
#define NR_PROFILE_GRP (NR_PROFILE_HIT/PROFILE_GRPSZ)
static atomic_t *prof_buffer;
-static unsigned long prof_len, prof_shift;
+static unsigned long prof_len;
+static unsigned short int prof_shift;
int prof_on __read_mostly;
EXPORT_SYMBOL_GPL(prof_on);
@@ -67,8 +68,8 @@ int profile_setup(char *str)
if (str[strlen(sleepstr)] == ',')
str += strlen(sleepstr) + 1;
if (get_option(&str, &par))
- prof_shift = par;
- pr_info("kernel sleep profiling enabled (shift: %ld)\n",
+ prof_shift = clamp(par, 0, BITS_PER_LONG - 1);
+ pr_info("kernel sleep profiling enabled (shift: %u)\n",
prof_shift);
#else
pr_warn("kernel sleep profiling requires CONFIG_SCHEDSTATS\n");
@@ -78,21 +79,21 @@ int profile_setup(char *str)
if (str[strlen(schedstr)] == ',')
str += strlen(schedstr) + 1;
if (get_option(&str, &par))
- prof_shift = par;
- pr_info("kernel schedule profiling enabled (shift: %ld)\n",
+ prof_shift = clamp(par, 0, BITS_PER_LONG - 1);
+ pr_info("kernel schedule profiling enabled (shift: %u)\n",
prof_shift);
} else if (!strncmp(str, kvmstr, strlen(kvmstr))) {
prof_on = KVM_PROFILING;
if (str[strlen(kvmstr)] == ',')
str += strlen(kvmstr) + 1;
if (get_option(&str, &par))
- prof_shift = par;
- pr_info("kernel KVM profiling enabled (shift: %ld)\n",
+ prof_shift = clamp(par, 0, BITS_PER_LONG - 1);
+ pr_info("kernel KVM profiling enabled (shift: %u)\n",
prof_shift);
} else if (get_option(&str, &par)) {
- prof_shift = par;
+ prof_shift = clamp(par, 0, BITS_PER_LONG - 1);
prof_on = CPU_PROFILING;
- pr_info("kernel profiling enabled (shift: %ld)\n",
+ pr_info("kernel profiling enabled (shift: %u)\n",
prof_shift);
}
return 1;
@@ -468,7 +469,7 @@ read_profile(struct file *file, char __user *buf, size_t count, loff_t *ppos)
unsigned long p = *ppos;
ssize_t read;
char *pnt;
- unsigned int sample_step = 1 << prof_shift;
+ unsigned long sample_step = 1UL << prof_shift;
profile_flip_buffers();
if (p >= (prof_len+1)*sizeof(unsigned int))
diff --git a/kernel/sys.c b/kernel/sys.c
index b6aa704f861d..8fdac0d90504 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1930,13 +1930,6 @@ static int validate_prctl_map_addr(struct prctl_mm_map *prctl_map)
error = -EINVAL;
/*
- * @brk should be after @end_data in traditional maps.
- */
- if (prctl_map->start_brk <= prctl_map->end_data ||
- prctl_map->brk <= prctl_map->end_data)
- goto out;
-
- /*
* Neither we should allow to override limits if they set.
*/
if (check_data_rlimit(rlimit(RLIMIT_DATA), prctl_map->brk,
diff --git a/kernel/user.c b/kernel/user.c
index c82399c1618a..e2cf8c22b539 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -129,6 +129,22 @@ static struct user_struct *uid_hash_find(kuid_t uid, struct hlist_head *hashent)
return NULL;
}
+static int user_epoll_alloc(struct user_struct *up)
+{
+#ifdef CONFIG_EPOLL
+ return percpu_counter_init(&up->epoll_watches, 0, GFP_KERNEL);
+#else
+ return 0;
+#endif
+}
+
+static void user_epoll_free(struct user_struct *up)
+{
+#ifdef CONFIG_EPOLL
+ percpu_counter_destroy(&up->epoll_watches);
+#endif
+}
+
/* IRQs are disabled and uidhash_lock is held upon function entry.
* IRQ state (as stored in flags) is restored and uidhash_lock released
* upon function exit.
@@ -138,6 +154,7 @@ static void free_user(struct user_struct *up, unsigned long flags)
{
uid_hash_remove(up);
spin_unlock_irqrestore(&uidhash_lock, flags);
+ user_epoll_free(up);
kmem_cache_free(uid_cachep, up);
}
@@ -185,6 +202,10 @@ struct user_struct *alloc_uid(kuid_t uid)
new->uid = uid;
refcount_set(&new->__count, 1);
+ if (user_epoll_alloc(new)) {
+ kmem_cache_free(uid_cachep, new);
+ return NULL;
+ }
ratelimit_state_init(&new->ratelimit, HZ, 100);
ratelimit_set_flags(&new->ratelimit, RATELIMIT_MSG_ON_RELEASE);
@@ -195,6 +216,7 @@ struct user_struct *alloc_uid(kuid_t uid)
spin_lock_irq(&uidhash_lock);
up = uid_hash_find(uid, hashent);
if (up) {
+ user_epoll_free(new);
kmem_cache_free(uid_cachep, new);
} else {
uid_hash_insert(new, hashent);
@@ -216,6 +238,9 @@ static int __init uid_cache_init(void)
for(n = 0; n < UIDHASH_SZ; ++n)
INIT_HLIST_HEAD(uidhash_table + n);
+ if (user_epoll_alloc(&root_user))
+ panic("root_user epoll percpu counter alloc failed");
+
/* Insert the root user immediately (init already runs as root) */
spin_lock_irq(&uidhash_lock);
uid_hash_insert(&root_user, uidhashentry(GLOBAL_ROOT_UID));
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 0f61b1ec385d..ed4a31e34098 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1064,7 +1064,6 @@ config HARDLOCKUP_DETECTOR
depends on HAVE_HARDLOCKUP_DETECTOR_PERF || HAVE_HARDLOCKUP_DETECTOR_ARCH
select LOCKUP_DETECTOR
select HARDLOCKUP_DETECTOR_PERF if HAVE_HARDLOCKUP_DETECTOR_PERF
- select HARDLOCKUP_DETECTOR_ARCH if HAVE_HARDLOCKUP_DETECTOR_ARCH
help
Say Y here to enable the kernel to act as a watchdog to detect
hard lockups.
@@ -2061,8 +2060,9 @@ config TEST_MIN_HEAP
If unsure, say N.
config TEST_SORT
- tristate "Array-based sort test"
- depends on DEBUG_KERNEL || m
+ tristate "Array-based sort test" if !KUNIT_ALL_TESTS
+ depends on KUNIT
+ default KUNIT_ALL_TESTS
help
This option enables the self-test function of 'sort()' at boot,
or at module load time.
@@ -2443,8 +2443,7 @@ config SLUB_KUNIT_TEST
config RATIONAL_KUNIT_TEST
tristate "KUnit test for rational.c" if !KUNIT_ALL_TESTS
- depends on KUNIT
- select RATIONAL
+ depends on KUNIT && RATIONAL
default KUNIT_ALL_TESTS
help
This builds the rational math unit test.
diff --git a/lib/dump_stack.c b/lib/dump_stack.c
index cd3387bb34e5..6b7f1bf6715d 100644
--- a/lib/dump_stack.c
+++ b/lib/dump_stack.c
@@ -89,7 +89,8 @@ static void __dump_stack(const char *log_lvl)
}
/**
- * dump_stack - dump the current task information and its stack trace
+ * dump_stack_lvl - dump the current task information and its stack trace
+ * @log_lvl: log level
*
* Architectures can override this implementation by implementing its own.
*/
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index e23123ae3a13..f2d50d69a6c3 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -672,7 +672,7 @@ static size_t copy_mc_pipe_to_iter(const void *addr, size_t bytes,
* _copy_mc_to_iter - copy to iter with source memory error exception handling
* @addr: source kernel address
* @bytes: total transfer length
- * @iter: destination iterator
+ * @i: destination iterator
*
* The pmem driver deploys this for the dax operation
* (dax_copy_to_iter()) for dax reads (bypass page-cache and the
@@ -690,6 +690,8 @@ static size_t copy_mc_pipe_to_iter(const void *addr, size_t bytes,
* * ITER_KVEC, ITER_PIPE, and ITER_BVEC can return short copies.
* Compare to copy_to_iter() where only ITER_IOVEC attempts might return
* a short copy.
+ *
+ * Return: number of bytes copied (may be %0)
*/
size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
{
@@ -744,7 +746,7 @@ EXPORT_SYMBOL(_copy_from_iter_nocache);
* _copy_from_iter_flushcache - write destination through cpu cache
* @addr: destination kernel address
* @bytes: total transfer length
- * @iter: source iterator
+ * @i: source iterator
*
* The pmem driver arranges for filesystem-dax to use this facility via
* dax_copy_from_iter() for ensuring that writes to persistent memory
@@ -753,6 +755,8 @@ EXPORT_SYMBOL(_copy_from_iter_nocache);
* all iterator types. The _copy_from_iter_nocache() only attempts to
* bypass the cache for the ITER_IOVEC case, and on some archs may use
* instructions that strand dirty-data in the cache.
+ *
+ * Return: number of bytes copied (may be %0)
*/
size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
{
diff --git a/lib/math/Kconfig b/lib/math/Kconfig
index f19bc9734fa7..0634b428d0cb 100644
--- a/lib/math/Kconfig
+++ b/lib/math/Kconfig
@@ -14,4 +14,4 @@ config PRIME_NUMBERS
If unsure, say N.
config RATIONAL
- bool
+ tristate
diff --git a/lib/math/rational.c b/lib/math/rational.c
index c0ab51d8fbb9..ec59d426ea63 100644
--- a/lib/math/rational.c
+++ b/lib/math/rational.c
@@ -13,6 +13,7 @@
#include <linux/export.h>
#include <linux/minmax.h>
#include <linux/limits.h>
+#include <linux/module.h>
/*
* calculate best rational approximation for a given fraction
@@ -106,3 +107,5 @@ void rational_best_approximation(
}
EXPORT_SYMBOL(rational_best_approximation);
+
+MODULE_LICENSE("GPL v2");
diff --git a/lib/test_printf.c b/lib/test_printf.c
index 8a48b61c3763..55082432f37e 100644
--- a/lib/test_printf.c
+++ b/lib/test_printf.c
@@ -614,7 +614,7 @@ page_flags_test(int section, int node, int zone, int last_cpupid,
bool append = false;
int i;
- flags &= BIT(NR_PAGEFLAGS) - 1;
+ flags &= PAGEFLAGS_MASK;
if (flags) {
page_flags |= flags;
snprintf(cmp_buf + size, BUF_SIZE - size, "%s", name);
diff --git a/lib/test_sort.c b/lib/test_sort.c
index 52edbe10f2e5..be02e3a098cf 100644
--- a/lib/test_sort.c
+++ b/lib/test_sort.c
@@ -1,4 +1,7 @@
// SPDX-License-Identifier: GPL-2.0-only
+
+#include <kunit/test.h>
+
#include <linux/sort.h>
#include <linux/slab.h>
#include <linux/module.h>
@@ -7,18 +10,17 @@
#define TEST_LEN 1000
-static int __init cmpint(const void *a, const void *b)
+static int cmpint(const void *a, const void *b)
{
return *(int *)a - *(int *)b;
}
-static int __init test_sort_init(void)
+static void test_sort(struct kunit *test)
{
- int *a, i, r = 1, err = -ENOMEM;
+ int *a, i, r = 1;
- a = kmalloc_array(TEST_LEN, sizeof(*a), GFP_KERNEL);
- if (!a)
- return err;
+ a = kunit_kmalloc_array(test, TEST_LEN, sizeof(*a), GFP_KERNEL);
+ KUNIT_ASSERT_NOT_ERR_OR_NULL(test, a);
for (i = 0; i < TEST_LEN; i++) {
r = (r * 725861) % 6599;
@@ -27,24 +29,20 @@ static int __init test_sort_init(void)
sort(a, TEST_LEN, sizeof(*a), cmpint, NULL);
- err = -EINVAL;
for (i = 0; i < TEST_LEN-1; i++)
- if (a[i] > a[i+1]) {
- pr_err("test has failed\n");
- goto exit;
- }
- err = 0;
- pr_info("test passed\n");
-exit:
- kfree(a);
- return err;
+ KUNIT_ASSERT_LE(test, a[i], a[i + 1]);
}
-static void __exit test_sort_exit(void)
-{
-}
+static struct kunit_case sort_test_cases[] = {
+ KUNIT_CASE(test_sort),
+ {}
+};
+
+static struct kunit_suite sort_test_suite = {
+ .name = "lib_sort",
+ .test_cases = sort_test_cases,
+};
-module_init(test_sort_init);
-module_exit(test_sort_exit);
+kunit_test_suites(&sort_test_suite);
MODULE_LICENSE("GPL");
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 3bcb7be03f93..d7ad44f2c8f5 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -2019,7 +2019,7 @@ static const struct page_flags_fields pff[] = {
static
char *format_page_flags(char *buf, char *end, unsigned long flags)
{
- unsigned long main_flags = flags & (BIT(NR_PAGEFLAGS) - 1);
+ unsigned long main_flags = flags & PAGEFLAGS_MASK;
bool append = false;
int i;
diff --git a/mm/Kconfig b/mm/Kconfig
index 40a9bfcd5062..d16ba9249bc5 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -96,9 +96,6 @@ config HAVE_FAST_GUP
depends on MMU
bool
-config HOLES_IN_ZONE
- bool
-
# Don't discard allocated memory used to track "memory" and "reserved" memblocks
# after early boot, so it can still be used to test for validity of memory.
# Also, memblocks are updated with memory hot(un)plug.
@@ -742,10 +739,18 @@ config DEFERRED_STRUCT_PAGE_INIT
lifetime of the system until these kthreads finish the
initialisation.
+config PAGE_IDLE_FLAG
+ bool
+ select PAGE_EXTENSION if !64BIT
+ help
+ This adds PG_idle and PG_young flags to 'struct page'. PTE Accessed
+ bit writers can set the state of the bit in the flags so that PTE
+ Accessed bit readers may avoid disturbance.
+
config IDLE_PAGE_TRACKING
bool "Enable idle page tracking"
depends on SYSFS && MMU
- select PAGE_EXTENSION if !64BIT
+ select PAGE_IDLE_FLAG
help
This feature allows to estimate the amount of user pages that have
not been touched during a given period of time. This information can
@@ -889,4 +894,6 @@ config IO_MAPPING
config SECRETMEM
def_bool ARCH_HAS_SET_DIRECT_MAP && !EMBEDDED
+source "mm/damon/Kconfig"
+
endmenu
diff --git a/mm/Makefile b/mm/Makefile
index e3436741d539..fc60a40ce954 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -38,7 +38,7 @@ mmu-y := nommu.o
mmu-$(CONFIG_MMU) := highmem.o memory.o mincore.o \
mlock.o mmap.o mmu_gather.o mprotect.o mremap.o \
msync.o page_vma_mapped.o pagewalk.o \
- pgtable-generic.o rmap.o vmalloc.o ioremap.o
+ pgtable-generic.o rmap.o vmalloc.o
ifdef CONFIG_CROSS_MEMORY_ATTACH
@@ -118,6 +118,7 @@ obj-$(CONFIG_CMA_SYSFS) += cma_sysfs.o
obj-$(CONFIG_USERFAULTFD) += userfaultfd.o
obj-$(CONFIG_IDLE_PAGE_TRACKING) += page_idle.o
obj-$(CONFIG_DEBUG_PAGE_REF) += debug_page_ref.o
+obj-$(CONFIG_DAMON) += damon/
obj-$(CONFIG_HARDENED_USERCOPY) += usercopy.o
obj-$(CONFIG_PERCPU_STATS) += percpu-stats.o
obj-$(CONFIG_ZONE_DEVICE) += memremap.o
@@ -128,3 +129,4 @@ obj-$(CONFIG_PTDUMP_CORE) += ptdump.o
obj-$(CONFIG_PAGE_REPORTING) += page_reporting.o
obj-$(CONFIG_IO_MAPPING) += io-mapping.o
obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o
+obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o
diff --git a/mm/compaction.c b/mm/compaction.c
index fa9b2b598eab..bfc93da1c2c7 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -306,16 +306,14 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source,
* is necessary for the block to be a migration source/target.
*/
do {
- if (pfn_valid_within(pfn)) {
- if (check_source && PageLRU(page)) {
- clear_pageblock_skip(page);
- return true;
- }
+ if (check_source && PageLRU(page)) {
+ clear_pageblock_skip(page);
+ return true;
+ }
- if (check_target && PageBuddy(page)) {
- clear_pageblock_skip(page);
- return true;
- }
+ if (check_target && PageBuddy(page)) {
+ clear_pageblock_skip(page);
+ return true;
}
page += (1 << PAGE_ALLOC_COSTLY_ORDER);
@@ -585,8 +583,6 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
break;
nr_scanned++;
- if (!pfn_valid_within(blockpfn))
- goto isolate_fail;
/*
* For compound pages such as THP and hugetlbfs, we can save
@@ -885,8 +881,6 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
cond_resched();
}
- if (!pfn_valid_within(low_pfn))
- goto isolate_fail;
nr_scanned++;
page = pfn_to_page(low_pfn);
diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig
new file mode 100644
index 000000000000..37024798a97c
--- /dev/null
+++ b/mm/damon/Kconfig
@@ -0,0 +1,68 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+menu "Data Access Monitoring"
+
+config DAMON
+ bool "DAMON: Data Access Monitoring Framework"
+ help
+ This builds a framework that allows kernel subsystems to monitor
+ access frequency of each memory region. The information can be useful
+ for performance-centric DRAM level memory management.
+
+ See https://damonitor.github.io/doc/html/latest-damon/index.html for
+ more information.
+
+config DAMON_KUNIT_TEST
+ bool "Test for damon" if !KUNIT_ALL_TESTS
+ depends on DAMON && KUNIT=y
+ default KUNIT_ALL_TESTS
+ help
+ This builds the DAMON Kunit test suite.
+
+ For more information on KUnit and unit tests in general, please refer
+ to the KUnit documentation.
+
+ If unsure, say N.
+
+config DAMON_VADDR
+ bool "Data access monitoring primitives for virtual address spaces"
+ depends on DAMON && MMU
+ select PAGE_IDLE_FLAG
+ help
+ This builds the default data access monitoring primitives for DAMON
+ that works for virtual address spaces.
+
+config DAMON_VADDR_KUNIT_TEST
+ bool "Test for DAMON primitives" if !KUNIT_ALL_TESTS
+ depends on DAMON_VADDR && KUNIT=y
+ default KUNIT_ALL_TESTS
+ help
+ This builds the DAMON virtual addresses primitives Kunit test suite.
+
+ For more information on KUnit and unit tests in general, please refer
+ to the KUnit documentation.
+
+ If unsure, say N.
+
+config DAMON_DBGFS
+ bool "DAMON debugfs interface"
+ depends on DAMON_VADDR && DEBUG_FS
+ help
+ This builds the debugfs interface for DAMON. The user space admins
+ can use the interface for arbitrary data access monitoring.
+
+ If unsure, say N.
+
+config DAMON_DBGFS_KUNIT_TEST
+ bool "Test for damon debugfs interface" if !KUNIT_ALL_TESTS
+ depends on DAMON_DBGFS && KUNIT=y
+ default KUNIT_ALL_TESTS
+ help
+ This builds the DAMON debugfs interface Kunit test suite.
+
+ For more information on KUnit and unit tests in general, please refer
+ to the KUnit documentation.
+
+ If unsure, say N.
+
+endmenu
diff --git a/mm/damon/Makefile b/mm/damon/Makefile
new file mode 100644
index 000000000000..fed4be3bace3
--- /dev/null
+++ b/mm/damon/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_DAMON) := core.o
+obj-$(CONFIG_DAMON_VADDR) += vaddr.o
+obj-$(CONFIG_DAMON_DBGFS) += dbgfs.o
diff --git a/mm/damon/core-test.h b/mm/damon/core-test.h
new file mode 100644
index 000000000000..c938a9c34e6c
--- /dev/null
+++ b/mm/damon/core-test.h
@@ -0,0 +1,253 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Data Access Monitor Unit Tests
+ *
+ * Copyright 2019 Amazon.com, Inc. or its affiliates. All rights reserved.
+ *
+ * Author: SeongJae Park <sjpark@amazon.de>
+ */
+
+#ifdef CONFIG_DAMON_KUNIT_TEST
+
+#ifndef _DAMON_CORE_TEST_H
+#define _DAMON_CORE_TEST_H
+
+#include <kunit/test.h>
+
+static void damon_test_regions(struct kunit *test)
+{
+ struct damon_region *r;
+ struct damon_target *t;
+
+ r = damon_new_region(1, 2);
+ KUNIT_EXPECT_EQ(test, 1ul, r->ar.start);
+ KUNIT_EXPECT_EQ(test, 2ul, r->ar.end);
+ KUNIT_EXPECT_EQ(test, 0u, r->nr_accesses);
+
+ t = damon_new_target(42);
+ KUNIT_EXPECT_EQ(test, 0u, damon_nr_regions(t));
+
+ damon_add_region(r, t);
+ KUNIT_EXPECT_EQ(test, 1u, damon_nr_regions(t));
+
+ damon_del_region(r, t);
+ KUNIT_EXPECT_EQ(test, 0u, damon_nr_regions(t));
+
+ damon_free_target(t);
+}
+
+static unsigned int nr_damon_targets(struct damon_ctx *ctx)
+{
+ struct damon_target *t;
+ unsigned int nr_targets = 0;
+
+ damon_for_each_target(t, ctx)
+ nr_targets++;
+
+ return nr_targets;
+}
+
+static void damon_test_target(struct kunit *test)
+{
+ struct damon_ctx *c = damon_new_ctx();
+ struct damon_target *t;
+
+ t = damon_new_target(42);
+ KUNIT_EXPECT_EQ(test, 42ul, t->id);
+ KUNIT_EXPECT_EQ(test, 0u, nr_damon_targets(c));
+
+ damon_add_target(c, t);
+ KUNIT_EXPECT_EQ(test, 1u, nr_damon_targets(c));
+
+ damon_destroy_target(t);
+ KUNIT_EXPECT_EQ(test, 0u, nr_damon_targets(c));
+
+ damon_destroy_ctx(c);
+}
+
+/*
+ * Test kdamond_reset_aggregated()
+ *
+ * DAMON checks access to each region and aggregates this information as the
+ * access frequency of each region. In detail, it increases '->nr_accesses' of
+ * regions that an access has confirmed. 'kdamond_reset_aggregated()' flushes
+ * the aggregated information ('->nr_accesses' of each regions) to the result
+ * buffer. As a result of the flushing, the '->nr_accesses' of regions are
+ * initialized to zero.
+ */
+static void damon_test_aggregate(struct kunit *test)
+{
+ struct damon_ctx *ctx = damon_new_ctx();
+ unsigned long target_ids[] = {1, 2, 3};
+ unsigned long saddr[][3] = {{10, 20, 30}, {5, 42, 49}, {13, 33, 55} };
+ unsigned long eaddr[][3] = {{15, 27, 40}, {31, 45, 55}, {23, 44, 66} };
+ unsigned long accesses[][3] = {{42, 95, 84}, {10, 20, 30}, {0, 1, 2} };
+ struct damon_target *t;
+ struct damon_region *r;
+ int it, ir;
+
+ damon_set_targets(ctx, target_ids, 3);
+
+ it = 0;
+ damon_for_each_target(t, ctx) {
+ for (ir = 0; ir < 3; ir++) {
+ r = damon_new_region(saddr[it][ir], eaddr[it][ir]);
+ r->nr_accesses = accesses[it][ir];
+ damon_add_region(r, t);
+ }
+ it++;
+ }
+ kdamond_reset_aggregated(ctx);
+ it = 0;
+ damon_for_each_target(t, ctx) {
+ ir = 0;
+ /* '->nr_accesses' should be zeroed */
+ damon_for_each_region(r, t) {
+ KUNIT_EXPECT_EQ(test, 0u, r->nr_accesses);
+ ir++;
+ }
+ /* regions should be preserved */
+ KUNIT_EXPECT_EQ(test, 3, ir);
+ it++;
+ }
+ /* targets also should be preserved */
+ KUNIT_EXPECT_EQ(test, 3, it);
+
+ damon_destroy_ctx(ctx);
+}
+
+static void damon_test_split_at(struct kunit *test)
+{
+ struct damon_ctx *c = damon_new_ctx();
+ struct damon_target *t;
+ struct damon_region *r;
+
+ t = damon_new_target(42);
+ r = damon_new_region(0, 100);
+ damon_add_region(r, t);
+ damon_split_region_at(c, t, r, 25);
+ KUNIT_EXPECT_EQ(test, r->ar.start, 0ul);
+ KUNIT_EXPECT_EQ(test, r->ar.end, 25ul);
+
+ r = damon_next_region(r);
+ KUNIT_EXPECT_EQ(test, r->ar.start, 25ul);
+ KUNIT_EXPECT_EQ(test, r->ar.end, 100ul);
+
+ damon_free_target(t);
+ damon_destroy_ctx(c);
+}
+
+static void damon_test_merge_two(struct kunit *test)
+{
+ struct damon_target *t;
+ struct damon_region *r, *r2, *r3;
+ int i;
+
+ t = damon_new_target(42);
+ r = damon_new_region(0, 100);
+ r->nr_accesses = 10;
+ damon_add_region(r, t);
+ r2 = damon_new_region(100, 300);
+ r2->nr_accesses = 20;
+ damon_add_region(r2, t);
+
+ damon_merge_two_regions(t, r, r2);
+ KUNIT_EXPECT_EQ(test, r->ar.start, 0ul);
+ KUNIT_EXPECT_EQ(test, r->ar.end, 300ul);
+ KUNIT_EXPECT_EQ(test, r->nr_accesses, 16u);
+
+ i = 0;
+ damon_for_each_region(r3, t) {
+ KUNIT_EXPECT_PTR_EQ(test, r, r3);
+ i++;
+ }
+ KUNIT_EXPECT_EQ(test, i, 1);
+
+ damon_free_target(t);
+}
+
+static struct damon_region *__nth_region_of(struct damon_target *t, int idx)
+{
+ struct damon_region *r;
+ unsigned int i = 0;
+
+ damon_for_each_region(r, t) {
+ if (i++ == idx)
+ return r;
+ }
+
+ return NULL;
+}
+
+static void damon_test_merge_regions_of(struct kunit *test)
+{
+ struct damon_target *t;
+ struct damon_region *r;
+ unsigned long sa[] = {0, 100, 114, 122, 130, 156, 170, 184};
+ unsigned long ea[] = {100, 112, 122, 130, 156, 170, 184, 230};
+ unsigned int nrs[] = {0, 0, 10, 10, 20, 30, 1, 2};
+
+ unsigned long saddrs[] = {0, 114, 130, 156, 170};
+ unsigned long eaddrs[] = {112, 130, 156, 170, 230};
+ int i;
+
+ t = damon_new_target(42);
+ for (i = 0; i < ARRAY_SIZE(sa); i++) {
+ r = damon_new_region(sa[i], ea[i]);
+ r->nr_accesses = nrs[i];
+ damon_add_region(r, t);
+ }
+
+ damon_merge_regions_of(t, 9, 9999);
+ /* 0-112, 114-130, 130-156, 156-170 */
+ KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 5u);
+ for (i = 0; i < 5; i++) {
+ r = __nth_region_of(t, i);
+ KUNIT_EXPECT_EQ(test, r->ar.start, saddrs[i]);
+ KUNIT_EXPECT_EQ(test, r->ar.end, eaddrs[i]);
+ }
+ damon_free_target(t);
+}
+
+static void damon_test_split_regions_of(struct kunit *test)
+{
+ struct damon_ctx *c = damon_new_ctx();
+ struct damon_target *t;
+ struct damon_region *r;
+
+ t = damon_new_target(42);
+ r = damon_new_region(0, 22);
+ damon_add_region(r, t);
+ damon_split_regions_of(c, t, 2);
+ KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 2u);
+ damon_free_target(t);
+
+ t = damon_new_target(42);
+ r = damon_new_region(0, 220);
+ damon_add_region(r, t);
+ damon_split_regions_of(c, t, 4);
+ KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 4u);
+ damon_free_target(t);
+ damon_destroy_ctx(c);
+}
+
+static struct kunit_case damon_test_cases[] = {
+ KUNIT_CASE(damon_test_target),
+ KUNIT_CASE(damon_test_regions),
+ KUNIT_CASE(damon_test_aggregate),
+ KUNIT_CASE(damon_test_split_at),
+ KUNIT_CASE(damon_test_merge_two),
+ KUNIT_CASE(damon_test_merge_regions_of),
+ KUNIT_CASE(damon_test_split_regions_of),
+ {},
+};
+
+static struct kunit_suite damon_test_suite = {
+ .name = "damon",
+ .test_cases = damon_test_cases,
+};
+kunit_test_suite(damon_test_suite);
+
+#endif /* _DAMON_CORE_TEST_H */
+
+#endif /* CONFIG_DAMON_KUNIT_TEST */
diff --git a/mm/damon/core.c b/mm/damon/core.c
new file mode 100644
index 000000000000..30e9211f494a
--- /dev/null
+++ b/mm/damon/core.c
@@ -0,0 +1,720 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Data Access Monitor
+ *
+ * Author: SeongJae Park <sjpark@amazon.de>
+ */
+
+#define pr_fmt(fmt) "damon: " fmt
+
+#include <linux/damon.h>
+#include <linux/delay.h>
+#include <linux/kthread.h>
+#include <linux/random.h>
+#include <linux/slab.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/damon.h>
+
+#ifdef CONFIG_DAMON_KUNIT_TEST
+#undef DAMON_MIN_REGION
+#define DAMON_MIN_REGION 1
+#endif
+
+/* Get a random number in [l, r) */
+#define damon_rand(l, r) (l + prandom_u32_max(r - l))
+
+static DEFINE_MUTEX(damon_lock);
+static int nr_running_ctxs;
+
+/*
+ * Construct a damon_region struct
+ *
+ * Returns the pointer to the new struct if success, or NULL otherwise
+ */
+struct damon_region *damon_new_region(unsigned long start, unsigned long end)
+{
+ struct damon_region *region;
+
+ region = kmalloc(sizeof(*region), GFP_KERNEL);
+ if (!region)
+ return NULL;
+
+ region->ar.start = start;
+ region->ar.end = end;
+ region->nr_accesses = 0;
+ INIT_LIST_HEAD(&region->list);
+
+ return region;
+}
+
+/*
+ * Add a region between two other regions
+ */
+inline void damon_insert_region(struct damon_region *r,
+ struct damon_region *prev, struct damon_region *next,
+ struct damon_target *t)
+{
+ __list_add(&r->list, &prev->list, &next->list);
+ t->nr_regions++;
+}
+
+void damon_add_region(struct damon_region *r, struct damon_target *t)
+{
+ list_add_tail(&r->list, &t->regions_list);
+ t->nr_regions++;
+}
+
+static void damon_del_region(struct damon_region *r, struct damon_target *t)
+{
+ list_del(&r->list);
+ t->nr_regions--;
+}
+
+static void damon_free_region(struct damon_region *r)
+{
+ kfree(r);
+}
+
+void damon_destroy_region(struct damon_region *r, struct damon_target *t)
+{
+ damon_del_region(r, t);
+ damon_free_region(r);
+}
+
+/*
+ * Construct a damon_target struct
+ *
+ * Returns the pointer to the new struct if success, or NULL otherwise
+ */
+struct damon_target *damon_new_target(unsigned long id)
+{
+ struct damon_target *t;
+
+ t = kmalloc(sizeof(*t), GFP_KERNEL);
+ if (!t)
+ return NULL;
+
+ t->id = id;
+ t->nr_regions = 0;
+ INIT_LIST_HEAD(&t->regions_list);
+
+ return t;
+}
+
+void damon_add_target(struct damon_ctx *ctx, struct damon_target *t)
+{
+ list_add_tail(&t->list, &ctx->adaptive_targets);
+}
+
+static void damon_del_target(struct damon_target *t)
+{
+ list_del(&t->list);
+}
+
+void damon_free_target(struct damon_target *t)
+{
+ struct damon_region *r, *next;
+
+ damon_for_each_region_safe(r, next, t)
+ damon_free_region(r);
+ kfree(t);
+}
+
+void damon_destroy_target(struct damon_target *t)
+{
+ damon_del_target(t);
+ damon_free_target(t);
+}
+
+unsigned int damon_nr_regions(struct damon_target *t)
+{
+ return t->nr_regions;
+}
+
+struct damon_ctx *damon_new_ctx(void)
+{
+ struct damon_ctx *ctx;
+
+ ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+ if (!ctx)
+ return NULL;
+
+ ctx->sample_interval = 5 * 1000;
+ ctx->aggr_interval = 100 * 1000;
+ ctx->primitive_update_interval = 60 * 1000 * 1000;
+
+ ktime_get_coarse_ts64(&ctx->last_aggregation);
+ ctx->last_primitive_update = ctx->last_aggregation;
+
+ mutex_init(&ctx->kdamond_lock);
+
+ ctx->min_nr_regions = 10;
+ ctx->max_nr_regions = 1000;
+
+ INIT_LIST_HEAD(&ctx->adaptive_targets);
+
+ return ctx;
+}
+
+static void damon_destroy_targets(struct damon_ctx *ctx)
+{
+ struct damon_target *t, *next_t;
+
+ if (ctx->primitive.cleanup) {
+ ctx->primitive.cleanup(ctx);
+ return;
+ }
+
+ damon_for_each_target_safe(t, next_t, ctx)
+ damon_destroy_target(t);
+}
+
+void damon_destroy_ctx(struct damon_ctx *ctx)
+{
+ damon_destroy_targets(ctx);
+ kfree(ctx);
+}
+
+/**
+ * damon_set_targets() - Set monitoring targets.
+ * @ctx: monitoring context
+ * @ids: array of target ids
+ * @nr_ids: number of entries in @ids
+ *
+ * This function should not be called while the kdamond is running.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int damon_set_targets(struct damon_ctx *ctx,
+ unsigned long *ids, ssize_t nr_ids)
+{
+ ssize_t i;
+ struct damon_target *t, *next;
+
+ damon_destroy_targets(ctx);
+
+ for (i = 0; i < nr_ids; i++) {
+ t = damon_new_target(ids[i]);
+ if (!t) {
+ pr_err("Failed to alloc damon_target\n");
+ /* The caller should do cleanup of the ids itself */
+ damon_for_each_target_safe(t, next, ctx)
+ damon_destroy_target(t);
+ return -ENOMEM;
+ }
+ damon_add_target(ctx, t);
+ }
+
+ return 0;
+}
+
+/**
+ * damon_set_attrs() - Set attributes for the monitoring.
+ * @ctx: monitoring context
+ * @sample_int: time interval between samplings
+ * @aggr_int: time interval between aggregations
+ * @primitive_upd_int: time interval between monitoring primitive updates
+ * @min_nr_reg: minimal number of regions
+ * @max_nr_reg: maximum number of regions
+ *
+ * This function should not be called while the kdamond is running.
+ * Every time interval is in micro-seconds.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int,
+ unsigned long aggr_int, unsigned long primitive_upd_int,
+ unsigned long min_nr_reg, unsigned long max_nr_reg)
+{
+ if (min_nr_reg < 3) {
+ pr_err("min_nr_regions (%lu) must be at least 3\n",
+ min_nr_reg);
+ return -EINVAL;
+ }
+ if (min_nr_reg > max_nr_reg) {
+ pr_err("invalid nr_regions. min (%lu) > max (%lu)\n",
+ min_nr_reg, max_nr_reg);
+ return -EINVAL;
+ }
+
+ ctx->sample_interval = sample_int;
+ ctx->aggr_interval = aggr_int;
+ ctx->primitive_update_interval = primitive_upd_int;
+ ctx->min_nr_regions = min_nr_reg;
+ ctx->max_nr_regions = max_nr_reg;
+
+ return 0;
+}
+
+/**
+ * damon_nr_running_ctxs() - Return number of currently running contexts.
+ */
+int damon_nr_running_ctxs(void)
+{
+ int nr_ctxs;
+
+ mutex_lock(&damon_lock);
+ nr_ctxs = nr_running_ctxs;
+ mutex_unlock(&damon_lock);
+
+ return nr_ctxs;
+}
+
+/* Returns the size upper limit for each monitoring region */
+static unsigned long damon_region_sz_limit(struct damon_ctx *ctx)
+{
+ struct damon_target *t;
+ struct damon_region *r;
+ unsigned long sz = 0;
+
+ damon_for_each_target(t, ctx) {
+ damon_for_each_region(r, t)
+ sz += r->ar.end - r->ar.start;
+ }
+
+ if (ctx->min_nr_regions)
+ sz /= ctx->min_nr_regions;
+ if (sz < DAMON_MIN_REGION)
+ sz = DAMON_MIN_REGION;
+
+ return sz;
+}
+
+static bool damon_kdamond_running(struct damon_ctx *ctx)
+{
+ bool running;
+
+ mutex_lock(&ctx->kdamond_lock);
+ running = ctx->kdamond != NULL;
+ mutex_unlock(&ctx->kdamond_lock);
+
+ return running;
+}
+
+static int kdamond_fn(void *data);
+
+/*
+ * __damon_start() - Starts monitoring with given context.
+ * @ctx: monitoring context
+ *
+ * This function should be called while damon_lock is hold.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+static int __damon_start(struct damon_ctx *ctx)
+{
+ int err = -EBUSY;
+
+ mutex_lock(&ctx->kdamond_lock);
+ if (!ctx->kdamond) {
+ err = 0;
+ ctx->kdamond_stop = false;
+ ctx->kdamond = kthread_run(kdamond_fn, ctx, "kdamond.%d",
+ nr_running_ctxs);
+ if (IS_ERR(ctx->kdamond)) {
+ err = PTR_ERR(ctx->kdamond);
+ ctx->kdamond = 0;
+ }
+ }
+ mutex_unlock(&ctx->kdamond_lock);
+
+ return err;
+}
+
+/**
+ * damon_start() - Starts the monitorings for a given group of contexts.
+ * @ctxs: an array of the pointers for contexts to start monitoring
+ * @nr_ctxs: size of @ctxs
+ *
+ * This function starts a group of monitoring threads for a group of monitoring
+ * contexts. One thread per each context is created and run in parallel. The
+ * caller should handle synchronization between the threads by itself. If a
+ * group of threads that created by other 'damon_start()' call is currently
+ * running, this function does nothing but returns -EBUSY.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int damon_start(struct damon_ctx **ctxs, int nr_ctxs)
+{
+ int i;
+ int err = 0;
+
+ mutex_lock(&damon_lock);
+ if (nr_running_ctxs) {
+ mutex_unlock(&damon_lock);
+ return -EBUSY;
+ }
+
+ for (i = 0; i < nr_ctxs; i++) {
+ err = __damon_start(ctxs[i]);
+ if (err)
+ break;
+ nr_running_ctxs++;
+ }
+ mutex_unlock(&damon_lock);
+
+ return err;
+}
+
+/*
+ * __damon_stop() - Stops monitoring of given context.
+ * @ctx: monitoring context
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+static int __damon_stop(struct damon_ctx *ctx)
+{
+ mutex_lock(&ctx->kdamond_lock);
+ if (ctx->kdamond) {
+ ctx->kdamond_stop = true;
+ mutex_unlock(&ctx->kdamond_lock);
+ while (damon_kdamond_running(ctx))
+ usleep_range(ctx->sample_interval,
+ ctx->sample_interval * 2);
+ return 0;
+ }
+ mutex_unlock(&ctx->kdamond_lock);
+
+ return -EPERM;
+}
+
+/**
+ * damon_stop() - Stops the monitorings for a given group of contexts.
+ * @ctxs: an array of the pointers for contexts to stop monitoring
+ * @nr_ctxs: size of @ctxs
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int damon_stop(struct damon_ctx **ctxs, int nr_ctxs)
+{
+ int i, err = 0;
+
+ for (i = 0; i < nr_ctxs; i++) {
+ /* nr_running_ctxs is decremented in kdamond_fn */
+ err = __damon_stop(ctxs[i]);
+ if (err)
+ return err;
+ }
+
+ return err;
+}
+
+/*
+ * damon_check_reset_time_interval() - Check if a time interval is elapsed.
+ * @baseline: the time to check whether the interval has elapsed since
+ * @interval: the time interval (microseconds)
+ *
+ * See whether the given time interval has passed since the given baseline
+ * time. If so, it also updates the baseline to current time for next check.
+ *
+ * Return: true if the time interval has passed, or false otherwise.
+ */
+static bool damon_check_reset_time_interval(struct timespec64 *baseline,
+ unsigned long interval)
+{
+ struct timespec64 now;
+
+ ktime_get_coarse_ts64(&now);
+ if ((timespec64_to_ns(&now) - timespec64_to_ns(baseline)) <
+ interval * 1000)
+ return false;
+ *baseline = now;
+ return true;
+}
+
+/*
+ * Check whether it is time to flush the aggregated information
+ */
+static bool kdamond_aggregate_interval_passed(struct damon_ctx *ctx)
+{
+ return damon_check_reset_time_interval(&ctx->last_aggregation,
+ ctx->aggr_interval);
+}
+
+/*
+ * Reset the aggregated monitoring results ('nr_accesses' of each region).
+ */
+static void kdamond_reset_aggregated(struct damon_ctx *c)
+{
+ struct damon_target *t;
+
+ damon_for_each_target(t, c) {
+ struct damon_region *r;
+
+ damon_for_each_region(r, t) {
+ trace_damon_aggregated(t, r, damon_nr_regions(t));
+ r->nr_accesses = 0;
+ }
+ }
+}
+
+#define sz_damon_region(r) (r->ar.end - r->ar.start)
+
+/*
+ * Merge two adjacent regions into one region
+ */
+static void damon_merge_two_regions(struct damon_target *t,
+ struct damon_region *l, struct damon_region *r)
+{
+ unsigned long sz_l = sz_damon_region(l), sz_r = sz_damon_region(r);
+
+ l->nr_accesses = (l->nr_accesses * sz_l + r->nr_accesses * sz_r) /
+ (sz_l + sz_r);
+ l->ar.end = r->ar.end;
+ damon_destroy_region(r, t);
+}
+
+#define diff_of(a, b) (a > b ? a - b : b - a)
+
+/*
+ * Merge adjacent regions having similar access frequencies
+ *
+ * t target affected by this merge operation
+ * thres '->nr_accesses' diff threshold for the merge
+ * sz_limit size upper limit of each region
+ */
+static void damon_merge_regions_of(struct damon_target *t, unsigned int thres,
+ unsigned long sz_limit)
+{
+ struct damon_region *r, *prev = NULL, *next;
+
+ damon_for_each_region_safe(r, next, t) {
+ if (prev && prev->ar.end == r->ar.start &&
+ diff_of(prev->nr_accesses, r->nr_accesses) <= thres &&
+ sz_damon_region(prev) + sz_damon_region(r) <= sz_limit)
+ damon_merge_two_regions(t, prev, r);
+ else
+ prev = r;
+ }
+}
+
+/*
+ * Merge adjacent regions having similar access frequencies
+ *
+ * threshold '->nr_accesses' diff threshold for the merge
+ * sz_limit size upper limit of each region
+ *
+ * This function merges monitoring target regions which are adjacent and their
+ * access frequencies are similar. This is for minimizing the monitoring
+ * overhead under the dynamically changeable access pattern. If a merge was
+ * unnecessarily made, later 'kdamond_split_regions()' will revert it.
+ */
+static void kdamond_merge_regions(struct damon_ctx *c, unsigned int threshold,
+ unsigned long sz_limit)
+{
+ struct damon_target *t;
+
+ damon_for_each_target(t, c)
+ damon_merge_regions_of(t, threshold, sz_limit);
+}
+
+/*
+ * Split a region in two
+ *
+ * r the region to be split
+ * sz_r size of the first sub-region that will be made
+ */
+static void damon_split_region_at(struct damon_ctx *ctx,
+ struct damon_target *t, struct damon_region *r,
+ unsigned long sz_r)
+{
+ struct damon_region *new;
+
+ new = damon_new_region(r->ar.start + sz_r, r->ar.end);
+ if (!new)
+ return;
+
+ r->ar.end = new->ar.start;
+
+ damon_insert_region(new, r, damon_next_region(r), t);
+}
+
+/* Split every region in the given target into 'nr_subs' regions */
+static void damon_split_regions_of(struct damon_ctx *ctx,
+ struct damon_target *t, int nr_subs)
+{
+ struct damon_region *r, *next;
+ unsigned long sz_region, sz_sub = 0;
+ int i;
+
+ damon_for_each_region_safe(r, next, t) {
+ sz_region = r->ar.end - r->ar.start;
+
+ for (i = 0; i < nr_subs - 1 &&
+ sz_region > 2 * DAMON_MIN_REGION; i++) {
+ /*
+ * Randomly select size of left sub-region to be at
+ * least 10 percent and at most 90% of original region
+ */
+ sz_sub = ALIGN_DOWN(damon_rand(1, 10) *
+ sz_region / 10, DAMON_MIN_REGION);
+ /* Do not allow blank region */
+ if (sz_sub == 0 || sz_sub >= sz_region)
+ continue;
+
+ damon_split_region_at(ctx, t, r, sz_sub);
+ sz_region = sz_sub;
+ }
+ }
+}
+
+/*
+ * Split every target region into randomly-sized small regions
+ *
+ * This function splits every target region into random-sized small regions if
+ * current total number of the regions is equal or smaller than half of the
+ * user-specified maximum number of regions. This is for maximizing the
+ * monitoring accuracy under the dynamically changeable access patterns. If a
+ * split was unnecessarily made, later 'kdamond_merge_regions()' will revert
+ * it.
+ */
+static void kdamond_split_regions(struct damon_ctx *ctx)
+{
+ struct damon_target *t;
+ unsigned int nr_regions = 0;
+ static unsigned int last_nr_regions;
+ int nr_subregions = 2;
+
+ damon_for_each_target(t, ctx)
+ nr_regions += damon_nr_regions(t);
+
+ if (nr_regions > ctx->max_nr_regions / 2)
+ return;
+
+ /* Maybe the middle of the region has different access frequency */
+ if (last_nr_regions == nr_regions &&
+ nr_regions < ctx->max_nr_regions / 3)
+ nr_subregions = 3;
+
+ damon_for_each_target(t, ctx)
+ damon_split_regions_of(ctx, t, nr_subregions);
+
+ last_nr_regions = nr_regions;
+}
+
+/*
+ * Check whether it is time to check and apply the target monitoring regions
+ *
+ * Returns true if it is.
+ */
+static bool kdamond_need_update_primitive(struct damon_ctx *ctx)
+{
+ return damon_check_reset_time_interval(&ctx->last_primitive_update,
+ ctx->primitive_update_interval);
+}
+
+/*
+ * Check whether current monitoring should be stopped
+ *
+ * The monitoring is stopped when either the user requested to stop, or all
+ * monitoring targets are invalid.
+ *
+ * Returns true if need to stop current monitoring.
+ */
+static bool kdamond_need_stop(struct damon_ctx *ctx)
+{
+ struct damon_target *t;
+ bool stop;
+
+ mutex_lock(&ctx->kdamond_lock);
+ stop = ctx->kdamond_stop;
+ mutex_unlock(&ctx->kdamond_lock);
+ if (stop)
+ return true;
+
+ if (!ctx->primitive.target_valid)
+ return false;
+
+ damon_for_each_target(t, ctx) {
+ if (ctx->primitive.target_valid(t))
+ return false;
+ }
+
+ return true;
+}
+
+static void set_kdamond_stop(struct damon_ctx *ctx)
+{
+ mutex_lock(&ctx->kdamond_lock);
+ ctx->kdamond_stop = true;
+ mutex_unlock(&ctx->kdamond_lock);
+}
+
+/*
+ * The monitoring daemon that runs as a kernel thread
+ */
+static int kdamond_fn(void *data)
+{
+ struct damon_ctx *ctx = (struct damon_ctx *)data;
+ struct damon_target *t;
+ struct damon_region *r, *next;
+ unsigned int max_nr_accesses = 0;
+ unsigned long sz_limit = 0;
+
+ mutex_lock(&ctx->kdamond_lock);
+ pr_info("kdamond (%d) starts\n", ctx->kdamond->pid);
+ mutex_unlock(&ctx->kdamond_lock);
+
+ if (ctx->primitive.init)
+ ctx->primitive.init(ctx);
+ if (ctx->callback.before_start && ctx->callback.before_start(ctx))
+ set_kdamond_stop(ctx);
+
+ sz_limit = damon_region_sz_limit(ctx);
+
+ while (!kdamond_need_stop(ctx)) {
+ if (ctx->primitive.prepare_access_checks)
+ ctx->primitive.prepare_access_checks(ctx);
+ if (ctx->callback.after_sampling &&
+ ctx->callback.after_sampling(ctx))
+ set_kdamond_stop(ctx);
+
+ usleep_range(ctx->sample_interval, ctx->sample_interval + 1);
+
+ if (ctx->primitive.check_accesses)
+ max_nr_accesses = ctx->primitive.check_accesses(ctx);
+
+ if (kdamond_aggregate_interval_passed(ctx)) {
+ kdamond_merge_regions(ctx,
+ max_nr_accesses / 10,
+ sz_limit);
+ if (ctx->callback.after_aggregation &&
+ ctx->callback.after_aggregation(ctx))
+ set_kdamond_stop(ctx);
+ kdamond_reset_aggregated(ctx);
+ kdamond_split_regions(ctx);
+ if (ctx->primitive.reset_aggregated)
+ ctx->primitive.reset_aggregated(ctx);
+ }
+
+ if (kdamond_need_update_primitive(ctx)) {
+ if (ctx->primitive.update)
+ ctx->primitive.update(ctx);
+ sz_limit = damon_region_sz_limit(ctx);
+ }
+ }
+ damon_for_each_target(t, ctx) {
+ damon_for_each_region_safe(r, next, t)
+ damon_destroy_region(r, t);
+ }
+
+ if (ctx->callback.before_terminate &&
+ ctx->callback.before_terminate(ctx))
+ set_kdamond_stop(ctx);
+ if (ctx->primitive.cleanup)
+ ctx->primitive.cleanup(ctx);
+
+ pr_debug("kdamond (%d) finishes\n", ctx->kdamond->pid);
+ mutex_lock(&ctx->kdamond_lock);
+ ctx->kdamond = NULL;
+ mutex_unlock(&ctx->kdamond_lock);
+
+ mutex_lock(&damon_lock);
+ nr_running_ctxs--;
+ mutex_unlock(&damon_lock);
+
+ do_exit(0);
+}
+
+#include "core-test.h"
diff --git a/mm/damon/dbgfs-test.h b/mm/damon/dbgfs-test.h
new file mode 100644
index 000000000000..930e83bceef0
--- /dev/null
+++ b/mm/damon/dbgfs-test.h
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * DAMON Debugfs Interface Unit Tests
+ *
+ * Author: SeongJae Park <sjpark@amazon.de>
+ */
+
+#ifdef CONFIG_DAMON_DBGFS_KUNIT_TEST
+
+#ifndef _DAMON_DBGFS_TEST_H
+#define _DAMON_DBGFS_TEST_H
+
+#include <kunit/test.h>
+
+static void damon_dbgfs_test_str_to_target_ids(struct kunit *test)
+{
+ char *question;
+ unsigned long *answers;
+ unsigned long expected[] = {12, 35, 46};
+ ssize_t nr_integers = 0, i;
+
+ question = "123";
+ answers = str_to_target_ids(question, strnlen(question, 128),
+ &nr_integers);
+ KUNIT_EXPECT_EQ(test, (ssize_t)1, nr_integers);
+ KUNIT_EXPECT_EQ(test, 123ul, answers[0]);
+ kfree(answers);
+
+ question = "123abc";
+ answers = str_to_target_ids(question, strnlen(question, 128),
+ &nr_integers);
+ KUNIT_EXPECT_EQ(test, (ssize_t)1, nr_integers);
+ KUNIT_EXPECT_EQ(test, 123ul, answers[0]);
+ kfree(answers);
+
+ question = "a123";
+ answers = str_to_target_ids(question, strnlen(question, 128),
+ &nr_integers);
+ KUNIT_EXPECT_EQ(test, (ssize_t)0, nr_integers);
+ kfree(answers);
+
+ question = "12 35";
+ answers = str_to_target_ids(question, strnlen(question, 128),
+ &nr_integers);
+ KUNIT_EXPECT_EQ(test, (ssize_t)2, nr_integers);
+ for (i = 0; i < nr_integers; i++)
+ KUNIT_EXPECT_EQ(test, expected[i], answers[i]);
+ kfree(answers);
+
+ question = "12 35 46";
+ answers = str_to_target_ids(question, strnlen(question, 128),
+ &nr_integers);
+ KUNIT_EXPECT_EQ(test, (ssize_t)3, nr_integers);
+ for (i = 0; i < nr_integers; i++)
+ KUNIT_EXPECT_EQ(test, expected[i], answers[i]);
+ kfree(answers);
+
+ question = "12 35 abc 46";
+ answers = str_to_target_ids(question, strnlen(question, 128),
+ &nr_integers);
+ KUNIT_EXPECT_EQ(test, (ssize_t)2, nr_integers);
+ for (i = 0; i < 2; i++)
+ KUNIT_EXPECT_EQ(test, expected[i], answers[i]);
+ kfree(answers);
+
+ question = "";
+ answers = str_to_target_ids(question, strnlen(question, 128),
+ &nr_integers);
+ KUNIT_EXPECT_EQ(test, (ssize_t)0, nr_integers);
+ kfree(answers);
+
+ question = "\n";
+ answers = str_to_target_ids(question, strnlen(question, 128),
+ &nr_integers);
+ KUNIT_EXPECT_EQ(test, (ssize_t)0, nr_integers);
+ kfree(answers);
+}
+
+static void damon_dbgfs_test_set_targets(struct kunit *test)
+{
+ struct damon_ctx *ctx = dbgfs_new_ctx();
+ unsigned long ids[] = {1, 2, 3};
+ char buf[64];
+
+ /* Make DAMON consider target id as plain number */
+ ctx->primitive.target_valid = NULL;
+ ctx->primitive.cleanup = NULL;
+
+ damon_set_targets(ctx, ids, 3);
+ sprint_target_ids(ctx, buf, 64);
+ KUNIT_EXPECT_STREQ(test, (char *)buf, "1 2 3\n");
+
+ damon_set_targets(ctx, NULL, 0);
+ sprint_target_ids(ctx, buf, 64);
+ KUNIT_EXPECT_STREQ(test, (char *)buf, "\n");
+
+ damon_set_targets(ctx, (unsigned long []){1, 2}, 2);
+ sprint_target_ids(ctx, buf, 64);
+ KUNIT_EXPECT_STREQ(test, (char *)buf, "1 2\n");
+
+ damon_set_targets(ctx, (unsigned long []){2}, 1);
+ sprint_target_ids(ctx, buf, 64);
+ KUNIT_EXPECT_STREQ(test, (char *)buf, "2\n");
+
+ damon_set_targets(ctx, NULL, 0);
+ sprint_target_ids(ctx, buf, 64);
+ KUNIT_EXPECT_STREQ(test, (char *)buf, "\n");
+
+ dbgfs_destroy_ctx(ctx);
+}
+
+static struct kunit_case damon_test_cases[] = {
+ KUNIT_CASE(damon_dbgfs_test_str_to_target_ids),
+ KUNIT_CASE(damon_dbgfs_test_set_targets),
+ {},
+};
+
+static struct kunit_suite damon_test_suite = {
+ .name = "damon-dbgfs",
+ .test_cases = damon_test_cases,
+};
+kunit_test_suite(damon_test_suite);
+
+#endif /* _DAMON_TEST_H */
+
+#endif /* CONFIG_DAMON_KUNIT_TEST */
diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c
new file mode 100644
index 000000000000..faee070977d8
--- /dev/null
+++ b/mm/damon/dbgfs.c
@@ -0,0 +1,623 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DAMON Debugfs Interface
+ *
+ * Author: SeongJae Park <sjpark@amazon.de>
+ */
+
+#define pr_fmt(fmt) "damon-dbgfs: " fmt
+
+#include <linux/damon.h>
+#include <linux/debugfs.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/page_idle.h>
+#include <linux/slab.h>
+
+static struct damon_ctx **dbgfs_ctxs;
+static int dbgfs_nr_ctxs;
+static struct dentry **dbgfs_dirs;
+static DEFINE_MUTEX(damon_dbgfs_lock);
+
+/*
+ * Returns non-empty string on success, negative error code otherwise.
+ */
+static char *user_input_str(const char __user *buf, size_t count, loff_t *ppos)
+{
+ char *kbuf;
+ ssize_t ret;
+
+ /* We do not accept continuous write */
+ if (*ppos)
+ return ERR_PTR(-EINVAL);
+
+ kbuf = kmalloc(count + 1, GFP_KERNEL);
+ if (!kbuf)
+ return ERR_PTR(-ENOMEM);
+
+ ret = simple_write_to_buffer(kbuf, count + 1, ppos, buf, count);
+ if (ret != count) {
+ kfree(kbuf);
+ return ERR_PTR(-EIO);
+ }
+ kbuf[ret] = '\0';
+
+ return kbuf;
+}
+
+static ssize_t dbgfs_attrs_read(struct file *file,
+ char __user *buf, size_t count, loff_t *ppos)
+{
+ struct damon_ctx *ctx = file->private_data;
+ char kbuf[128];
+ int ret;
+
+ mutex_lock(&ctx->kdamond_lock);
+ ret = scnprintf(kbuf, ARRAY_SIZE(kbuf), "%lu %lu %lu %lu %lu\n",
+ ctx->sample_interval, ctx->aggr_interval,
+ ctx->primitive_update_interval, ctx->min_nr_regions,
+ ctx->max_nr_regions);
+ mutex_unlock(&ctx->kdamond_lock);
+
+ return simple_read_from_buffer(buf, count, ppos, kbuf, ret);
+}
+
+static ssize_t dbgfs_attrs_write(struct file *file,
+ const char __user *buf, size_t count, loff_t *ppos)
+{
+ struct damon_ctx *ctx = file->private_data;
+ unsigned long s, a, r, minr, maxr;
+ char *kbuf;
+ ssize_t ret = count;
+ int err;
+
+ kbuf = user_input_str(buf, count, ppos);
+ if (IS_ERR(kbuf))
+ return PTR_ERR(kbuf);
+
+ if (sscanf(kbuf, "%lu %lu %lu %lu %lu",
+ &s, &a, &r, &minr, &maxr) != 5) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ mutex_lock(&ctx->kdamond_lock);
+ if (ctx->kdamond) {
+ ret = -EBUSY;
+ goto unlock_out;
+ }
+
+ err = damon_set_attrs(ctx, s, a, r, minr, maxr);
+ if (err)
+ ret = err;
+unlock_out:
+ mutex_unlock(&ctx->kdamond_lock);
+out:
+ kfree(kbuf);
+ return ret;
+}
+
+static inline bool targetid_is_pid(const struct damon_ctx *ctx)
+{
+ return ctx->primitive.target_valid == damon_va_target_valid;
+}
+
+static ssize_t sprint_target_ids(struct damon_ctx *ctx, char *buf, ssize_t len)
+{
+ struct damon_target *t;
+ unsigned long id;
+ int written = 0;
+ int rc;
+
+ damon_for_each_target(t, ctx) {
+ id = t->id;
+ if (targetid_is_pid(ctx))
+ /* Show pid numbers to debugfs users */
+ id = (unsigned long)pid_vnr((struct pid *)id);
+
+ rc = scnprintf(&buf[written], len - written, "%lu ", id);
+ if (!rc)
+ return -ENOMEM;
+ written += rc;
+ }
+ if (written)
+ written -= 1;
+ written += scnprintf(&buf[written], len - written, "\n");
+ return written;
+}
+
+static ssize_t dbgfs_target_ids_read(struct file *file,
+ char __user *buf, size_t count, loff_t *ppos)
+{
+ struct damon_ctx *ctx = file->private_data;
+ ssize_t len;
+ char ids_buf[320];
+
+ mutex_lock(&ctx->kdamond_lock);
+ len = sprint_target_ids(ctx, ids_buf, 320);
+ mutex_unlock(&ctx->kdamond_lock);
+ if (len < 0)
+ return len;
+
+ return simple_read_from_buffer(buf, count, ppos, ids_buf, len);
+}
+
+/*
+ * Converts a string into an array of unsigned long integers
+ *
+ * Returns an array of unsigned long integers if the conversion success, or
+ * NULL otherwise.
+ */
+static unsigned long *str_to_target_ids(const char *str, ssize_t len,
+ ssize_t *nr_ids)
+{
+ unsigned long *ids;
+ const int max_nr_ids = 32;
+ unsigned long id;
+ int pos = 0, parsed, ret;
+
+ *nr_ids = 0;
+ ids = kmalloc_array(max_nr_ids, sizeof(id), GFP_KERNEL);
+ if (!ids)
+ return NULL;
+ while (*nr_ids < max_nr_ids && pos < len) {
+ ret = sscanf(&str[pos], "%lu%n", &id, &parsed);
+ pos += parsed;
+ if (ret != 1)
+ break;
+ ids[*nr_ids] = id;
+ *nr_ids += 1;
+ }
+
+ return ids;
+}
+
+static void dbgfs_put_pids(unsigned long *ids, int nr_ids)
+{
+ int i;
+
+ for (i = 0; i < nr_ids; i++)
+ put_pid((struct pid *)ids[i]);
+}
+
+static ssize_t dbgfs_target_ids_write(struct file *file,
+ const char __user *buf, size_t count, loff_t *ppos)
+{
+ struct damon_ctx *ctx = file->private_data;
+ char *kbuf, *nrs;
+ unsigned long *targets;
+ ssize_t nr_targets;
+ ssize_t ret = count;
+ int i;
+ int err;
+
+ kbuf = user_input_str(buf, count, ppos);
+ if (IS_ERR(kbuf))
+ return PTR_ERR(kbuf);
+
+ nrs = kbuf;
+
+ targets = str_to_target_ids(nrs, ret, &nr_targets);
+ if (!targets) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ if (targetid_is_pid(ctx)) {
+ for (i = 0; i < nr_targets; i++) {
+ targets[i] = (unsigned long)find_get_pid(
+ (int)targets[i]);
+ if (!targets[i]) {
+ dbgfs_put_pids(targets, i);
+ ret = -EINVAL;
+ goto free_targets_out;
+ }
+ }
+ }
+
+ mutex_lock(&ctx->kdamond_lock);
+ if (ctx->kdamond) {
+ if (targetid_is_pid(ctx))
+ dbgfs_put_pids(targets, nr_targets);
+ ret = -EBUSY;
+ goto unlock_out;
+ }
+
+ err = damon_set_targets(ctx, targets, nr_targets);
+ if (err) {
+ if (targetid_is_pid(ctx))
+ dbgfs_put_pids(targets, nr_targets);
+ ret = err;
+ }
+
+unlock_out:
+ mutex_unlock(&ctx->kdamond_lock);
+free_targets_out:
+ kfree(targets);
+out:
+ kfree(kbuf);
+ return ret;
+}
+
+static ssize_t dbgfs_kdamond_pid_read(struct file *file,
+ char __user *buf, size_t count, loff_t *ppos)
+{
+ struct damon_ctx *ctx = file->private_data;
+ char *kbuf;
+ ssize_t len;
+
+ kbuf = kmalloc(count, GFP_KERNEL);
+ if (!kbuf)
+ return -ENOMEM;
+
+ mutex_lock(&ctx->kdamond_lock);
+ if (ctx->kdamond)
+ len = scnprintf(kbuf, count, "%d\n", ctx->kdamond->pid);
+ else
+ len = scnprintf(kbuf, count, "none\n");
+ mutex_unlock(&ctx->kdamond_lock);
+ if (!len)
+ goto out;
+ len = simple_read_from_buffer(buf, count, ppos, kbuf, len);
+
+out:
+ kfree(kbuf);
+ return len;
+}
+
+static int damon_dbgfs_open(struct inode *inode, struct file *file)
+{
+ file->private_data = inode->i_private;
+
+ return nonseekable_open(inode, file);
+}
+
+static const struct file_operations attrs_fops = {
+ .open = damon_dbgfs_open,
+ .read = dbgfs_attrs_read,
+ .write = dbgfs_attrs_write,
+};
+
+static const struct file_operations target_ids_fops = {
+ .open = damon_dbgfs_open,
+ .read = dbgfs_target_ids_read,
+ .write = dbgfs_target_ids_write,
+};
+
+static const struct file_operations kdamond_pid_fops = {
+ .open = damon_dbgfs_open,
+ .read = dbgfs_kdamond_pid_read,
+};
+
+static void dbgfs_fill_ctx_dir(struct dentry *dir, struct damon_ctx *ctx)
+{
+ const char * const file_names[] = {"attrs", "target_ids",
+ "kdamond_pid"};
+ const struct file_operations *fops[] = {&attrs_fops, &target_ids_fops,
+ &kdamond_pid_fops};
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(file_names); i++)
+ debugfs_create_file(file_names[i], 0600, dir, ctx, fops[i]);
+}
+
+static int dbgfs_before_terminate(struct damon_ctx *ctx)
+{
+ struct damon_target *t, *next;
+
+ if (!targetid_is_pid(ctx))
+ return 0;
+
+ damon_for_each_target_safe(t, next, ctx) {
+ put_pid((struct pid *)t->id);
+ damon_destroy_target(t);
+ }
+ return 0;
+}
+
+static struct damon_ctx *dbgfs_new_ctx(void)
+{
+ struct damon_ctx *ctx;
+
+ ctx = damon_new_ctx();
+ if (!ctx)
+ return NULL;
+
+ damon_va_set_primitives(ctx);
+ ctx->callback.before_terminate = dbgfs_before_terminate;
+ return ctx;
+}
+
+static void dbgfs_destroy_ctx(struct damon_ctx *ctx)
+{
+ damon_destroy_ctx(ctx);
+}
+
+/*
+ * Make a context of @name and create a debugfs directory for it.
+ *
+ * This function should be called while holding damon_dbgfs_lock.
+ *
+ * Returns 0 on success, negative error code otherwise.
+ */
+static int dbgfs_mk_context(char *name)
+{
+ struct dentry *root, **new_dirs, *new_dir;
+ struct damon_ctx **new_ctxs, *new_ctx;
+
+ if (damon_nr_running_ctxs())
+ return -EBUSY;
+
+ new_ctxs = krealloc(dbgfs_ctxs, sizeof(*dbgfs_ctxs) *
+ (dbgfs_nr_ctxs + 1), GFP_KERNEL);
+ if (!new_ctxs)
+ return -ENOMEM;
+ dbgfs_ctxs = new_ctxs;
+
+ new_dirs = krealloc(dbgfs_dirs, sizeof(*dbgfs_dirs) *
+ (dbgfs_nr_ctxs + 1), GFP_KERNEL);
+ if (!new_dirs)
+ return -ENOMEM;
+ dbgfs_dirs = new_dirs;
+
+ root = dbgfs_dirs[0];
+ if (!root)
+ return -ENOENT;
+
+ new_dir = debugfs_create_dir(name, root);
+ dbgfs_dirs[dbgfs_nr_ctxs] = new_dir;
+
+ new_ctx = dbgfs_new_ctx();
+ if (!new_ctx) {
+ debugfs_remove(new_dir);
+ dbgfs_dirs[dbgfs_nr_ctxs] = NULL;
+ return -ENOMEM;
+ }
+
+ dbgfs_ctxs[dbgfs_nr_ctxs] = new_ctx;
+ dbgfs_fill_ctx_dir(dbgfs_dirs[dbgfs_nr_ctxs],
+ dbgfs_ctxs[dbgfs_nr_ctxs]);
+ dbgfs_nr_ctxs++;
+
+ return 0;
+}
+
+static ssize_t dbgfs_mk_context_write(struct file *file,
+ const char __user *buf, size_t count, loff_t *ppos)
+{
+ char *kbuf;
+ char *ctx_name;
+ ssize_t ret = count;
+ int err;
+
+ kbuf = user_input_str(buf, count, ppos);
+ if (IS_ERR(kbuf))
+ return PTR_ERR(kbuf);
+ ctx_name = kmalloc(count + 1, GFP_KERNEL);
+ if (!ctx_name) {
+ kfree(kbuf);
+ return -ENOMEM;
+ }
+
+ /* Trim white space */
+ if (sscanf(kbuf, "%s", ctx_name) != 1) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ mutex_lock(&damon_dbgfs_lock);
+ err = dbgfs_mk_context(ctx_name);
+ if (err)
+ ret = err;
+ mutex_unlock(&damon_dbgfs_lock);
+
+out:
+ kfree(kbuf);
+ kfree(ctx_name);
+ return ret;
+}
+
+/*
+ * Remove a context of @name and its debugfs directory.
+ *
+ * This function should be called while holding damon_dbgfs_lock.
+ *
+ * Return 0 on success, negative error code otherwise.
+ */
+static int dbgfs_rm_context(char *name)
+{
+ struct dentry *root, *dir, **new_dirs;
+ struct damon_ctx **new_ctxs;
+ int i, j;
+
+ if (damon_nr_running_ctxs())
+ return -EBUSY;
+
+ root = dbgfs_dirs[0];
+ if (!root)
+ return -ENOENT;
+
+ dir = debugfs_lookup(name, root);
+ if (!dir)
+ return -ENOENT;
+
+ new_dirs = kmalloc_array(dbgfs_nr_ctxs - 1, sizeof(*dbgfs_dirs),
+ GFP_KERNEL);
+ if (!new_dirs)
+ return -ENOMEM;
+
+ new_ctxs = kmalloc_array(dbgfs_nr_ctxs - 1, sizeof(*dbgfs_ctxs),
+ GFP_KERNEL);
+ if (!new_ctxs) {
+ kfree(new_dirs);
+ return -ENOMEM;
+ }
+
+ for (i = 0, j = 0; i < dbgfs_nr_ctxs; i++) {
+ if (dbgfs_dirs[i] == dir) {
+ debugfs_remove(dbgfs_dirs[i]);
+ dbgfs_destroy_ctx(dbgfs_ctxs[i]);
+ continue;
+ }
+ new_dirs[j] = dbgfs_dirs[i];
+ new_ctxs[j++] = dbgfs_ctxs[i];
+ }
+
+ kfree(dbgfs_dirs);
+ kfree(dbgfs_ctxs);
+
+ dbgfs_dirs = new_dirs;
+ dbgfs_ctxs = new_ctxs;
+ dbgfs_nr_ctxs--;
+
+ return 0;
+}
+
+static ssize_t dbgfs_rm_context_write(struct file *file,
+ const char __user *buf, size_t count, loff_t *ppos)
+{
+ char *kbuf;
+ ssize_t ret = count;
+ int err;
+ char *ctx_name;
+
+ kbuf = user_input_str(buf, count, ppos);
+ if (IS_ERR(kbuf))
+ return PTR_ERR(kbuf);
+ ctx_name = kmalloc(count + 1, GFP_KERNEL);
+ if (!ctx_name) {
+ kfree(kbuf);
+ return -ENOMEM;
+ }
+
+ /* Trim white space */
+ if (sscanf(kbuf, "%s", ctx_name) != 1) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ mutex_lock(&damon_dbgfs_lock);
+ err = dbgfs_rm_context(ctx_name);
+ if (err)
+ ret = err;
+ mutex_unlock(&damon_dbgfs_lock);
+
+out:
+ kfree(kbuf);
+ kfree(ctx_name);
+ return ret;
+}
+
+static ssize_t dbgfs_monitor_on_read(struct file *file,
+ char __user *buf, size_t count, loff_t *ppos)
+{
+ char monitor_on_buf[5];
+ bool monitor_on = damon_nr_running_ctxs() != 0;
+ int len;
+
+ len = scnprintf(monitor_on_buf, 5, monitor_on ? "on\n" : "off\n");
+
+ return simple_read_from_buffer(buf, count, ppos, monitor_on_buf, len);
+}
+
+static ssize_t dbgfs_monitor_on_write(struct file *file,
+ const char __user *buf, size_t count, loff_t *ppos)
+{
+ ssize_t ret = count;
+ char *kbuf;
+ int err;
+
+ kbuf = user_input_str(buf, count, ppos);
+ if (IS_ERR(kbuf))
+ return PTR_ERR(kbuf);
+
+ /* Remove white space */
+ if (sscanf(kbuf, "%s", kbuf) != 1) {
+ kfree(kbuf);
+ return -EINVAL;
+ }
+
+ if (!strncmp(kbuf, "on", count))
+ err = damon_start(dbgfs_ctxs, dbgfs_nr_ctxs);
+ else if (!strncmp(kbuf, "off", count))
+ err = damon_stop(dbgfs_ctxs, dbgfs_nr_ctxs);
+ else
+ err = -EINVAL;
+
+ if (err)
+ ret = err;
+ kfree(kbuf);
+ return ret;
+}
+
+static const struct file_operations mk_contexts_fops = {
+ .write = dbgfs_mk_context_write,
+};
+
+static const struct file_operations rm_contexts_fops = {
+ .write = dbgfs_rm_context_write,
+};
+
+static const struct file_operations monitor_on_fops = {
+ .read = dbgfs_monitor_on_read,
+ .write = dbgfs_monitor_on_write,
+};
+
+static int __init __damon_dbgfs_init(void)
+{
+ struct dentry *dbgfs_root;
+ const char * const file_names[] = {"mk_contexts", "rm_contexts",
+ "monitor_on"};
+ const struct file_operations *fops[] = {&mk_contexts_fops,
+ &rm_contexts_fops, &monitor_on_fops};
+ int i;
+
+ dbgfs_root = debugfs_create_dir("damon", NULL);
+
+ for (i = 0; i < ARRAY_SIZE(file_names); i++)
+ debugfs_create_file(file_names[i], 0600, dbgfs_root, NULL,
+ fops[i]);
+ dbgfs_fill_ctx_dir(dbgfs_root, dbgfs_ctxs[0]);
+
+ dbgfs_dirs = kmalloc_array(1, sizeof(dbgfs_root), GFP_KERNEL);
+ if (!dbgfs_dirs) {
+ debugfs_remove(dbgfs_root);
+ return -ENOMEM;
+ }
+ dbgfs_dirs[0] = dbgfs_root;
+
+ return 0;
+}
+
+/*
+ * Functions for the initialization
+ */
+
+static int __init damon_dbgfs_init(void)
+{
+ int rc;
+
+ dbgfs_ctxs = kmalloc(sizeof(*dbgfs_ctxs), GFP_KERNEL);
+ if (!dbgfs_ctxs)
+ return -ENOMEM;
+ dbgfs_ctxs[0] = dbgfs_new_ctx();
+ if (!dbgfs_ctxs[0]) {
+ kfree(dbgfs_ctxs);
+ return -ENOMEM;
+ }
+ dbgfs_nr_ctxs = 1;
+
+ rc = __damon_dbgfs_init();
+ if (rc) {
+ kfree(dbgfs_ctxs[0]);
+ kfree(dbgfs_ctxs);
+ pr_err("%s: dbgfs init failed\n", __func__);
+ }
+
+ return rc;
+}
+
+module_init(damon_dbgfs_init);
+
+#include "dbgfs-test.h"
diff --git a/mm/damon/vaddr-test.h b/mm/damon/vaddr-test.h
new file mode 100644
index 000000000000..1f5c13257dba
--- /dev/null
+++ b/mm/damon/vaddr-test.h
@@ -0,0 +1,329 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Data Access Monitor Unit Tests
+ *
+ * Copyright 2019 Amazon.com, Inc. or its affiliates. All rights reserved.
+ *
+ * Author: SeongJae Park <sjpark@amazon.de>
+ */
+
+#ifdef CONFIG_DAMON_VADDR_KUNIT_TEST
+
+#ifndef _DAMON_VADDR_TEST_H
+#define _DAMON_VADDR_TEST_H
+
+#include <kunit/test.h>
+
+static void __link_vmas(struct vm_area_struct *vmas, ssize_t nr_vmas)
+{
+ int i, j;
+ unsigned long largest_gap, gap;
+
+ if (!nr_vmas)
+ return;
+
+ for (i = 0; i < nr_vmas - 1; i++) {
+ vmas[i].vm_next = &vmas[i + 1];
+
+ vmas[i].vm_rb.rb_left = NULL;
+ vmas[i].vm_rb.rb_right = &vmas[i + 1].vm_rb;
+
+ largest_gap = 0;
+ for (j = i; j < nr_vmas; j++) {
+ if (j == 0)
+ continue;
+ gap = vmas[j].vm_start - vmas[j - 1].vm_end;
+ if (gap > largest_gap)
+ largest_gap = gap;
+ }
+ vmas[i].rb_subtree_gap = largest_gap;
+ }
+ vmas[i].vm_next = NULL;
+ vmas[i].vm_rb.rb_right = NULL;
+ vmas[i].rb_subtree_gap = 0;
+}
+
+/*
+ * Test __damon_va_three_regions() function
+ *
+ * In case of virtual memory address spaces monitoring, DAMON converts the
+ * complex and dynamic memory mappings of each target task to three
+ * discontiguous regions which cover every mapped areas. However, the three
+ * regions should not include the two biggest unmapped areas in the original
+ * mapping, because the two biggest areas are normally the areas between 1)
+ * heap and the mmap()-ed regions, and 2) the mmap()-ed regions and stack.
+ * Because these two unmapped areas are very huge but obviously never accessed,
+ * covering the region is just a waste.
+ *
+ * '__damon_va_three_regions() receives an address space of a process. It
+ * first identifies the start of mappings, end of mappings, and the two biggest
+ * unmapped areas. After that, based on the information, it constructs the
+ * three regions and returns. For more detail, refer to the comment of
+ * 'damon_init_regions_of()' function definition in 'mm/damon.c' file.
+ *
+ * For example, suppose virtual address ranges of 10-20, 20-25, 200-210,
+ * 210-220, 300-305, and 307-330 (Other comments represent this mappings in
+ * more short form: 10-20-25, 200-210-220, 300-305, 307-330) of a process are
+ * mapped. To cover every mappings, the three regions should start with 10,
+ * and end with 305. The process also has three unmapped areas, 25-200,
+ * 220-300, and 305-307. Among those, 25-200 and 220-300 are the biggest two
+ * unmapped areas, and thus it should be converted to three regions of 10-25,
+ * 200-220, and 300-330.
+ */
+static void damon_test_three_regions_in_vmas(struct kunit *test)
+{
+ struct damon_addr_range regions[3] = {0,};
+ /* 10-20-25, 200-210-220, 300-305, 307-330 */
+ struct vm_area_struct vmas[] = {
+ (struct vm_area_struct) {.vm_start = 10, .vm_end = 20},
+ (struct vm_area_struct) {.vm_start = 20, .vm_end = 25},
+ (struct vm_area_struct) {.vm_start = 200, .vm_end = 210},
+ (struct vm_area_struct) {.vm_start = 210, .vm_end = 220},
+ (struct vm_area_struct) {.vm_start = 300, .vm_end = 305},
+ (struct vm_area_struct) {.vm_start = 307, .vm_end = 330},
+ };
+
+ __link_vmas(vmas, 6);
+
+ __damon_va_three_regions(&vmas[0], regions);
+
+ KUNIT_EXPECT_EQ(test, 10ul, regions[0].start);
+ KUNIT_EXPECT_EQ(test, 25ul, regions[0].end);
+ KUNIT_EXPECT_EQ(test, 200ul, regions[1].start);
+ KUNIT_EXPECT_EQ(test, 220ul, regions[1].end);
+ KUNIT_EXPECT_EQ(test, 300ul, regions[2].start);
+ KUNIT_EXPECT_EQ(test, 330ul, regions[2].end);
+}
+
+static struct damon_region *__nth_region_of(struct damon_target *t, int idx)
+{
+ struct damon_region *r;
+ unsigned int i = 0;
+
+ damon_for_each_region(r, t) {
+ if (i++ == idx)
+ return r;
+ }
+
+ return NULL;
+}
+
+/*
+ * Test 'damon_va_apply_three_regions()'
+ *
+ * test kunit object
+ * regions an array containing start/end addresses of current
+ * monitoring target regions
+ * nr_regions the number of the addresses in 'regions'
+ * three_regions The three regions that need to be applied now
+ * expected start/end addresses of monitoring target regions that
+ * 'three_regions' are applied
+ * nr_expected the number of addresses in 'expected'
+ *
+ * The memory mapping of the target processes changes dynamically. To follow
+ * the change, DAMON periodically reads the mappings, simplifies it to the
+ * three regions, and updates the monitoring target regions to fit in the three
+ * regions. The update of current target regions is the role of
+ * 'damon_va_apply_three_regions()'.
+ *
+ * This test passes the given target regions and the new three regions that
+ * need to be applied to the function and check whether it updates the regions
+ * as expected.
+ */
+static void damon_do_test_apply_three_regions(struct kunit *test,
+ unsigned long *regions, int nr_regions,
+ struct damon_addr_range *three_regions,
+ unsigned long *expected, int nr_expected)
+{
+ struct damon_ctx *ctx = damon_new_ctx();
+ struct damon_target *t;
+ struct damon_region *r;
+ int i;
+
+ t = damon_new_target(42);
+ for (i = 0; i < nr_regions / 2; i++) {
+ r = damon_new_region(regions[i * 2], regions[i * 2 + 1]);
+ damon_add_region(r, t);
+ }
+ damon_add_target(ctx, t);
+
+ damon_va_apply_three_regions(t, three_regions);
+
+ for (i = 0; i < nr_expected / 2; i++) {
+ r = __nth_region_of(t, i);
+ KUNIT_EXPECT_EQ(test, r->ar.start, expected[i * 2]);
+ KUNIT_EXPECT_EQ(test, r->ar.end, expected[i * 2 + 1]);
+ }
+
+ damon_destroy_ctx(ctx);
+}
+
+/*
+ * This function test most common case where the three big regions are only
+ * slightly changed. Target regions should adjust their boundary (10-20-30,
+ * 50-55, 70-80, 90-100) to fit with the new big regions or remove target
+ * regions (57-79) that now out of the three regions.
+ */
+static void damon_test_apply_three_regions1(struct kunit *test)
+{
+ /* 10-20-30, 50-55-57-59, 70-80-90-100 */
+ unsigned long regions[] = {10, 20, 20, 30, 50, 55, 55, 57, 57, 59,
+ 70, 80, 80, 90, 90, 100};
+ /* 5-27, 45-55, 73-104 */
+ struct damon_addr_range new_three_regions[3] = {
+ (struct damon_addr_range){.start = 5, .end = 27},
+ (struct damon_addr_range){.start = 45, .end = 55},
+ (struct damon_addr_range){.start = 73, .end = 104} };
+ /* 5-20-27, 45-55, 73-80-90-104 */
+ unsigned long expected[] = {5, 20, 20, 27, 45, 55,
+ 73, 80, 80, 90, 90, 104};
+
+ damon_do_test_apply_three_regions(test, regions, ARRAY_SIZE(regions),
+ new_three_regions, expected, ARRAY_SIZE(expected));
+}
+
+/*
+ * Test slightly bigger change. Similar to above, but the second big region
+ * now require two target regions (50-55, 57-59) to be removed.
+ */
+static void damon_test_apply_three_regions2(struct kunit *test)
+{
+ /* 10-20-30, 50-55-57-59, 70-80-90-100 */
+ unsigned long regions[] = {10, 20, 20, 30, 50, 55, 55, 57, 57, 59,
+ 70, 80, 80, 90, 90, 100};
+ /* 5-27, 56-57, 65-104 */
+ struct damon_addr_range new_three_regions[3] = {
+ (struct damon_addr_range){.start = 5, .end = 27},
+ (struct damon_addr_range){.start = 56, .end = 57},
+ (struct damon_addr_range){.start = 65, .end = 104} };
+ /* 5-20-27, 56-57, 65-80-90-104 */
+ unsigned long expected[] = {5, 20, 20, 27, 56, 57,
+ 65, 80, 80, 90, 90, 104};
+
+ damon_do_test_apply_three_regions(test, regions, ARRAY_SIZE(regions),
+ new_three_regions, expected, ARRAY_SIZE(expected));
+}
+
+/*
+ * Test a big change. The second big region has totally freed and mapped to
+ * different area (50-59 -> 61-63). The target regions which were in the old
+ * second big region (50-55-57-59) should be removed and new target region
+ * covering the second big region (61-63) should be created.
+ */
+static void damon_test_apply_three_regions3(struct kunit *test)
+{
+ /* 10-20-30, 50-55-57-59, 70-80-90-100 */
+ unsigned long regions[] = {10, 20, 20, 30, 50, 55, 55, 57, 57, 59,
+ 70, 80, 80, 90, 90, 100};
+ /* 5-27, 61-63, 65-104 */
+ struct damon_addr_range new_three_regions[3] = {
+ (struct damon_addr_range){.start = 5, .end = 27},
+ (struct damon_addr_range){.start = 61, .end = 63},
+ (struct damon_addr_range){.start = 65, .end = 104} };
+ /* 5-20-27, 61-63, 65-80-90-104 */
+ unsigned long expected[] = {5, 20, 20, 27, 61, 63,
+ 65, 80, 80, 90, 90, 104};
+
+ damon_do_test_apply_three_regions(test, regions, ARRAY_SIZE(regions),
+ new_three_regions, expected, ARRAY_SIZE(expected));
+}
+
+/*
+ * Test another big change. Both of the second and third big regions (50-59
+ * and 70-100) has totally freed and mapped to different area (30-32 and
+ * 65-68). The target regions which were in the old second and third big
+ * regions should now be removed and new target regions covering the new second
+ * and third big regions should be crated.
+ */
+static void damon_test_apply_three_regions4(struct kunit *test)
+{
+ /* 10-20-30, 50-55-57-59, 70-80-90-100 */
+ unsigned long regions[] = {10, 20, 20, 30, 50, 55, 55, 57, 57, 59,
+ 70, 80, 80, 90, 90, 100};
+ /* 5-7, 30-32, 65-68 */
+ struct damon_addr_range new_three_regions[3] = {
+ (struct damon_addr_range){.start = 5, .end = 7},
+ (struct damon_addr_range){.start = 30, .end = 32},
+ (struct damon_addr_range){.start = 65, .end = 68} };
+ /* expect 5-7, 30-32, 65-68 */
+ unsigned long expected[] = {5, 7, 30, 32, 65, 68};
+
+ damon_do_test_apply_three_regions(test, regions, ARRAY_SIZE(regions),
+ new_three_regions, expected, ARRAY_SIZE(expected));
+}
+
+static void damon_test_split_evenly(struct kunit *test)
+{
+ struct damon_ctx *c = damon_new_ctx();
+ struct damon_target *t;
+ struct damon_region *r;
+ unsigned long i;
+
+ KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(NULL, NULL, 5),
+ -EINVAL);
+
+ t = damon_new_target(42);
+ r = damon_new_region(0, 100);
+ KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 0), -EINVAL);
+
+ damon_add_region(r, t);
+ KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 10), 0);
+ KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 10u);
+
+ i = 0;
+ damon_for_each_region(r, t) {
+ KUNIT_EXPECT_EQ(test, r->ar.start, i++ * 10);
+ KUNIT_EXPECT_EQ(test, r->ar.end, i * 10);
+ }
+ damon_free_target(t);
+
+ t = damon_new_target(42);
+ r = damon_new_region(5, 59);
+ damon_add_region(r, t);
+ KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 5), 0);
+ KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 5u);
+
+ i = 0;
+ damon_for_each_region(r, t) {
+ if (i == 4)
+ break;
+ KUNIT_EXPECT_EQ(test, r->ar.start, 5 + 10 * i++);
+ KUNIT_EXPECT_EQ(test, r->ar.end, 5 + 10 * i);
+ }
+ KUNIT_EXPECT_EQ(test, r->ar.start, 5 + 10 * i);
+ KUNIT_EXPECT_EQ(test, r->ar.end, 59ul);
+ damon_free_target(t);
+
+ t = damon_new_target(42);
+ r = damon_new_region(5, 6);
+ damon_add_region(r, t);
+ KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 2), -EINVAL);
+ KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 1u);
+
+ damon_for_each_region(r, t) {
+ KUNIT_EXPECT_EQ(test, r->ar.start, 5ul);
+ KUNIT_EXPECT_EQ(test, r->ar.end, 6ul);
+ }
+ damon_free_target(t);
+ damon_destroy_ctx(c);
+}
+
+static struct kunit_case damon_test_cases[] = {
+ KUNIT_CASE(damon_test_three_regions_in_vmas),
+ KUNIT_CASE(damon_test_apply_three_regions1),
+ KUNIT_CASE(damon_test_apply_three_regions2),
+ KUNIT_CASE(damon_test_apply_three_regions3),
+ KUNIT_CASE(damon_test_apply_three_regions4),
+ KUNIT_CASE(damon_test_split_evenly),
+ {},
+};
+
+static struct kunit_suite damon_test_suite = {
+ .name = "damon-primitives",
+ .test_cases = damon_test_cases,
+};
+kunit_test_suite(damon_test_suite);
+
+#endif /* _DAMON_VADDR_TEST_H */
+
+#endif /* CONFIG_DAMON_VADDR_KUNIT_TEST */
diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
new file mode 100644
index 000000000000..58c1fb2aafa9
--- /dev/null
+++ b/mm/damon/vaddr.c
@@ -0,0 +1,672 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DAMON Primitives for Virtual Address Spaces
+ *
+ * Author: SeongJae Park <sjpark@amazon.de>
+ */
+
+#define pr_fmt(fmt) "damon-va: " fmt
+
+#include <linux/damon.h>
+#include <linux/hugetlb.h>
+#include <linux/mm.h>
+#include <linux/mmu_notifier.h>
+#include <linux/highmem.h>
+#include <linux/page_idle.h>
+#include <linux/pagewalk.h>
+#include <linux/random.h>
+#include <linux/sched/mm.h>
+#include <linux/slab.h>
+
+#ifdef CONFIG_DAMON_VADDR_KUNIT_TEST
+#undef DAMON_MIN_REGION
+#define DAMON_MIN_REGION 1
+#endif
+
+/* Get a random number in [l, r) */
+#define damon_rand(l, r) (l + prandom_u32_max(r - l))
+
+/*
+ * 't->id' should be the pointer to the relevant 'struct pid' having reference
+ * count. Caller must put the returned task, unless it is NULL.
+ */
+#define damon_get_task_struct(t) \
+ (get_pid_task((struct pid *)t->id, PIDTYPE_PID))
+
+/*
+ * Get the mm_struct of the given target
+ *
+ * Caller _must_ put the mm_struct after use, unless it is NULL.
+ *
+ * Returns the mm_struct of the target on success, NULL on failure
+ */
+static struct mm_struct *damon_get_mm(struct damon_target *t)
+{
+ struct task_struct *task;
+ struct mm_struct *mm;
+
+ task = damon_get_task_struct(t);
+ if (!task)
+ return NULL;
+
+ mm = get_task_mm(task);
+ put_task_struct(task);
+ return mm;
+}
+
+/*
+ * Functions for the initial monitoring target regions construction
+ */
+
+/*
+ * Size-evenly split a region into 'nr_pieces' small regions
+ *
+ * Returns 0 on success, or negative error code otherwise.
+ */
+static int damon_va_evenly_split_region(struct damon_target *t,
+ struct damon_region *r, unsigned int nr_pieces)
+{
+ unsigned long sz_orig, sz_piece, orig_end;
+ struct damon_region *n = NULL, *next;
+ unsigned long start;
+
+ if (!r || !nr_pieces)
+ return -EINVAL;
+
+ orig_end = r->ar.end;
+ sz_orig = r->ar.end - r->ar.start;
+ sz_piece = ALIGN_DOWN(sz_orig / nr_pieces, DAMON_MIN_REGION);
+
+ if (!sz_piece)
+ return -EINVAL;
+
+ r->ar.end = r->ar.start + sz_piece;
+ next = damon_next_region(r);
+ for (start = r->ar.end; start + sz_piece <= orig_end;
+ start += sz_piece) {
+ n = damon_new_region(start, start + sz_piece);
+ if (!n)
+ return -ENOMEM;
+ damon_insert_region(n, r, next, t);
+ r = n;
+ }
+ /* complement last region for possible rounding error */
+ if (n)
+ n->ar.end = orig_end;
+
+ return 0;
+}
+
+static unsigned long sz_range(struct damon_addr_range *r)
+{
+ return r->end - r->start;
+}
+
+static void swap_ranges(struct damon_addr_range *r1,
+ struct damon_addr_range *r2)
+{
+ struct damon_addr_range tmp;
+
+ tmp = *r1;
+ *r1 = *r2;
+ *r2 = tmp;
+}
+
+/*
+ * Find three regions separated by two biggest unmapped regions
+ *
+ * vma the head vma of the target address space
+ * regions an array of three address ranges that results will be saved
+ *
+ * This function receives an address space and finds three regions in it which
+ * separated by the two biggest unmapped regions in the space. Please refer to
+ * below comments of '__damon_va_init_regions()' function to know why this is
+ * necessary.
+ *
+ * Returns 0 if success, or negative error code otherwise.
+ */
+static int __damon_va_three_regions(struct vm_area_struct *vma,
+ struct damon_addr_range regions[3])
+{
+ struct damon_addr_range gap = {0}, first_gap = {0}, second_gap = {0};
+ struct vm_area_struct *last_vma = NULL;
+ unsigned long start = 0;
+ struct rb_root rbroot;
+
+ /* Find two biggest gaps so that first_gap > second_gap > others */
+ for (; vma; vma = vma->vm_next) {
+ if (!last_vma) {
+ start = vma->vm_start;
+ goto next;
+ }
+
+ if (vma->rb_subtree_gap <= sz_range(&second_gap)) {
+ rbroot.rb_node = &vma->vm_rb;
+ vma = rb_entry(rb_last(&rbroot),
+ struct vm_area_struct, vm_rb);
+ goto next;
+ }
+
+ gap.start = last_vma->vm_end;
+ gap.end = vma->vm_start;
+ if (sz_range(&gap) > sz_range(&second_gap)) {
+ swap_ranges(&gap, &second_gap);
+ if (sz_range(&second_gap) > sz_range(&first_gap))
+ swap_ranges(&second_gap, &first_gap);
+ }
+next:
+ last_vma = vma;
+ }
+
+ if (!sz_range(&second_gap) || !sz_range(&first_gap))
+ return -EINVAL;
+
+ /* Sort the two biggest gaps by address */
+ if (first_gap.start > second_gap.start)
+ swap_ranges(&first_gap, &second_gap);
+
+ /* Store the result */
+ regions[0].start = ALIGN(start, DAMON_MIN_REGION);
+ regions[0].end = ALIGN(first_gap.start, DAMON_MIN_REGION);
+ regions[1].start = ALIGN(first_gap.end, DAMON_MIN_REGION);
+ regions[1].end = ALIGN(second_gap.start, DAMON_MIN_REGION);
+ regions[2].start = ALIGN(second_gap.end, DAMON_MIN_REGION);
+ regions[2].end = ALIGN(last_vma->vm_end, DAMON_MIN_REGION);
+
+ return 0;
+}
+
+/*
+ * Get the three regions in the given target (task)
+ *
+ * Returns 0 on success, negative error code otherwise.
+ */
+static int damon_va_three_regions(struct damon_target *t,
+ struct damon_addr_range regions[3])
+{
+ struct mm_struct *mm;
+ int rc;
+
+ mm = damon_get_mm(t);
+ if (!mm)
+ return -EINVAL;
+
+ mmap_read_lock(mm);
+ rc = __damon_va_three_regions(mm->mmap, regions);
+ mmap_read_unlock(mm);
+
+ mmput(mm);
+ return rc;
+}
+
+/*
+ * Initialize the monitoring target regions for the given target (task)
+ *
+ * t the given target
+ *
+ * Because only a number of small portions of the entire address space
+ * is actually mapped to the memory and accessed, monitoring the unmapped
+ * regions is wasteful. That said, because we can deal with small noises,
+ * tracking every mapping is not strictly required but could even incur a high
+ * overhead if the mapping frequently changes or the number of mappings is
+ * high. The adaptive regions adjustment mechanism will further help to deal
+ * with the noise by simply identifying the unmapped areas as a region that
+ * has no access. Moreover, applying the real mappings that would have many
+ * unmapped areas inside will make the adaptive mechanism quite complex. That
+ * said, too huge unmapped areas inside the monitoring target should be removed
+ * to not take the time for the adaptive mechanism.
+ *
+ * For the reason, we convert the complex mappings to three distinct regions
+ * that cover every mapped area of the address space. Also the two gaps
+ * between the three regions are the two biggest unmapped areas in the given
+ * address space. In detail, this function first identifies the start and the
+ * end of the mappings and the two biggest unmapped areas of the address space.
+ * Then, it constructs the three regions as below:
+ *
+ * [mappings[0]->start, big_two_unmapped_areas[0]->start)
+ * [big_two_unmapped_areas[0]->end, big_two_unmapped_areas[1]->start)
+ * [big_two_unmapped_areas[1]->end, mappings[nr_mappings - 1]->end)
+ *
+ * As usual memory map of processes is as below, the gap between the heap and
+ * the uppermost mmap()-ed region, and the gap between the lowermost mmap()-ed
+ * region and the stack will be two biggest unmapped regions. Because these
+ * gaps are exceptionally huge areas in usual address space, excluding these
+ * two biggest unmapped regions will be sufficient to make a trade-off.
+ *
+ * <heap>
+ * <BIG UNMAPPED REGION 1>
+ * <uppermost mmap()-ed region>
+ * (other mmap()-ed regions and small unmapped regions)
+ * <lowermost mmap()-ed region>
+ * <BIG UNMAPPED REGION 2>
+ * <stack>
+ */
+static void __damon_va_init_regions(struct damon_ctx *ctx,
+ struct damon_target *t)
+{
+ struct damon_region *r;
+ struct damon_addr_range regions[3];
+ unsigned long sz = 0, nr_pieces;
+ int i;
+
+ if (damon_va_three_regions(t, regions)) {
+ pr_err("Failed to get three regions of target %lu\n", t->id);
+ return;
+ }
+
+ for (i = 0; i < 3; i++)
+ sz += regions[i].end - regions[i].start;
+ if (ctx->min_nr_regions)
+ sz /= ctx->min_nr_regions;
+ if (sz < DAMON_MIN_REGION)
+ sz = DAMON_MIN_REGION;
+
+ /* Set the initial three regions of the target */
+ for (i = 0; i < 3; i++) {
+ r = damon_new_region(regions[i].start, regions[i].end);
+ if (!r) {
+ pr_err("%d'th init region creation failed\n", i);
+ return;
+ }
+ damon_add_region(r, t);
+
+ nr_pieces = (regions[i].end - regions[i].start) / sz;
+ damon_va_evenly_split_region(t, r, nr_pieces);
+ }
+}
+
+/* Initialize '->regions_list' of every target (task) */
+void damon_va_init(struct damon_ctx *ctx)
+{
+ struct damon_target *t;
+
+ damon_for_each_target(t, ctx) {
+ /* the user may set the target regions as they want */
+ if (!damon_nr_regions(t))
+ __damon_va_init_regions(ctx, t);
+ }
+}
+
+/*
+ * Functions for the dynamic monitoring target regions update
+ */
+
+/*
+ * Check whether a region is intersecting an address range
+ *
+ * Returns true if it is.
+ */
+static bool damon_intersect(struct damon_region *r, struct damon_addr_range *re)
+{
+ return !(r->ar.end <= re->start || re->end <= r->ar.start);
+}
+
+/*
+ * Update damon regions for the three big regions of the given target
+ *
+ * t the given target
+ * bregions the three big regions of the target
+ */
+static void damon_va_apply_three_regions(struct damon_target *t,
+ struct damon_addr_range bregions[3])
+{
+ struct damon_region *r, *next;
+ unsigned int i = 0;
+
+ /* Remove regions which are not in the three big regions now */
+ damon_for_each_region_safe(r, next, t) {
+ for (i = 0; i < 3; i++) {
+ if (damon_intersect(r, &bregions[i]))
+ break;
+ }
+ if (i == 3)
+ damon_destroy_region(r, t);
+ }
+
+ /* Adjust intersecting regions to fit with the three big regions */
+ for (i = 0; i < 3; i++) {
+ struct damon_region *first = NULL, *last;
+ struct damon_region *newr;
+ struct damon_addr_range *br;
+
+ br = &bregions[i];
+ /* Get the first and last regions which intersects with br */
+ damon_for_each_region(r, t) {
+ if (damon_intersect(r, br)) {
+ if (!first)
+ first = r;
+ last = r;
+ }
+ if (r->ar.start >= br->end)
+ break;
+ }
+ if (!first) {
+ /* no damon_region intersects with this big region */
+ newr = damon_new_region(
+ ALIGN_DOWN(br->start,
+ DAMON_MIN_REGION),
+ ALIGN(br->end, DAMON_MIN_REGION));
+ if (!newr)
+ continue;
+ damon_insert_region(newr, damon_prev_region(r), r, t);
+ } else {
+ first->ar.start = ALIGN_DOWN(br->start,
+ DAMON_MIN_REGION);
+ last->ar.end = ALIGN(br->end, DAMON_MIN_REGION);
+ }
+ }
+}
+
+/*
+ * Update regions for current memory mappings
+ */
+void damon_va_update(struct damon_ctx *ctx)
+{
+ struct damon_addr_range three_regions[3];
+ struct damon_target *t;
+
+ damon_for_each_target(t, ctx) {
+ if (damon_va_three_regions(t, three_regions))
+ continue;
+ damon_va_apply_three_regions(t, three_regions);
+ }
+}
+
+/*
+ * Get an online page for a pfn if it's in the LRU list. Otherwise, returns
+ * NULL.
+ *
+ * The body of this function is stolen from the 'page_idle_get_page()'. We
+ * steal rather than reuse it because the code is quite simple.
+ */
+static struct page *damon_get_page(unsigned long pfn)
+{
+ struct page *page = pfn_to_online_page(pfn);
+
+ if (!page || !PageLRU(page) || !get_page_unless_zero(page))
+ return NULL;
+
+ if (unlikely(!PageLRU(page))) {
+ put_page(page);
+ page = NULL;
+ }
+ return page;
+}
+
+static void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm,
+ unsigned long addr)
+{
+ bool referenced = false;
+ struct page *page = damon_get_page(pte_pfn(*pte));
+
+ if (!page)
+ return;
+
+ if (pte_young(*pte)) {
+ referenced = true;
+ *pte = pte_mkold(*pte);
+ }
+
+#ifdef CONFIG_MMU_NOTIFIER
+ if (mmu_notifier_clear_young(mm, addr, addr + PAGE_SIZE))
+ referenced = true;
+#endif /* CONFIG_MMU_NOTIFIER */
+
+ if (referenced)
+ set_page_young(page);
+
+ set_page_idle(page);
+ put_page(page);
+}
+
+static void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm,
+ unsigned long addr)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ bool referenced = false;
+ struct page *page = damon_get_page(pmd_pfn(*pmd));
+
+ if (!page)
+ return;
+
+ if (pmd_young(*pmd)) {
+ referenced = true;
+ *pmd = pmd_mkold(*pmd);
+ }
+
+#ifdef CONFIG_MMU_NOTIFIER
+ if (mmu_notifier_clear_young(mm, addr,
+ addr + ((1UL) << HPAGE_PMD_SHIFT)))
+ referenced = true;
+#endif /* CONFIG_MMU_NOTIFIER */
+
+ if (referenced)
+ set_page_young(page);
+
+ set_page_idle(page);
+ put_page(page);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+}
+
+static int damon_mkold_pmd_entry(pmd_t *pmd, unsigned long addr,
+ unsigned long next, struct mm_walk *walk)
+{
+ pte_t *pte;
+ spinlock_t *ptl;
+
+ if (pmd_huge(*pmd)) {
+ ptl = pmd_lock(walk->mm, pmd);
+ if (pmd_huge(*pmd)) {
+ damon_pmdp_mkold(pmd, walk->mm, addr);
+ spin_unlock(ptl);
+ return 0;
+ }
+ spin_unlock(ptl);
+ }
+
+ if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
+ return 0;
+ pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+ if (!pte_present(*pte))
+ goto out;
+ damon_ptep_mkold(pte, walk->mm, addr);
+out:
+ pte_unmap_unlock(pte, ptl);
+ return 0;
+}
+
+static struct mm_walk_ops damon_mkold_ops = {
+ .pmd_entry = damon_mkold_pmd_entry,
+};
+
+static void damon_va_mkold(struct mm_struct *mm, unsigned long addr)
+{
+ mmap_read_lock(mm);
+ walk_page_range(mm, addr, addr + 1, &damon_mkold_ops, NULL);
+ mmap_read_unlock(mm);
+}
+
+/*
+ * Functions for the access checking of the regions
+ */
+
+static void damon_va_prepare_access_check(struct damon_ctx *ctx,
+ struct mm_struct *mm, struct damon_region *r)
+{
+ r->sampling_addr = damon_rand(r->ar.start, r->ar.end);
+
+ damon_va_mkold(mm, r->sampling_addr);
+}
+
+void damon_va_prepare_access_checks(struct damon_ctx *ctx)
+{
+ struct damon_target *t;
+ struct mm_struct *mm;
+ struct damon_region *r;
+
+ damon_for_each_target(t, ctx) {
+ mm = damon_get_mm(t);
+ if (!mm)
+ continue;
+ damon_for_each_region(r, t)
+ damon_va_prepare_access_check(ctx, mm, r);
+ mmput(mm);
+ }
+}
+
+struct damon_young_walk_private {
+ unsigned long *page_sz;
+ bool young;
+};
+
+static int damon_young_pmd_entry(pmd_t *pmd, unsigned long addr,
+ unsigned long next, struct mm_walk *walk)
+{
+ pte_t *pte;
+ spinlock_t *ptl;
+ struct page *page;
+ struct damon_young_walk_private *priv = walk->private;
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ if (pmd_huge(*pmd)) {
+ ptl = pmd_lock(walk->mm, pmd);
+ if (!pmd_huge(*pmd)) {
+ spin_unlock(ptl);
+ goto regular_page;
+ }
+ page = damon_get_page(pmd_pfn(*pmd));
+ if (!page)
+ goto huge_out;
+ if (pmd_young(*pmd) || !page_is_idle(page) ||
+ mmu_notifier_test_young(walk->mm,
+ addr)) {
+ *priv->page_sz = ((1UL) << HPAGE_PMD_SHIFT);
+ priv->young = true;
+ }
+ put_page(page);
+huge_out:
+ spin_unlock(ptl);
+ return 0;
+ }
+
+regular_page:
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+ if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
+ return -EINVAL;
+ pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+ if (!pte_present(*pte))
+ goto out;
+ page = damon_get_page(pte_pfn(*pte));
+ if (!page)
+ goto out;
+ if (pte_young(*pte) || !page_is_idle(page) ||
+ mmu_notifier_test_young(walk->mm, addr)) {
+ *priv->page_sz = PAGE_SIZE;
+ priv->young = true;
+ }
+ put_page(page);
+out:
+ pte_unmap_unlock(pte, ptl);
+ return 0;
+}
+
+static struct mm_walk_ops damon_young_ops = {
+ .pmd_entry = damon_young_pmd_entry,
+};
+
+static bool damon_va_young(struct mm_struct *mm, unsigned long addr,
+ unsigned long *page_sz)
+{
+ struct damon_young_walk_private arg = {
+ .page_sz = page_sz,
+ .young = false,
+ };
+
+ mmap_read_lock(mm);
+ walk_page_range(mm, addr, addr + 1, &damon_young_ops, &arg);
+ mmap_read_unlock(mm);
+ return arg.young;
+}
+
+/*
+ * Check whether the region was accessed after the last preparation
+ *
+ * mm 'mm_struct' for the given virtual address space
+ * r the region to be checked
+ */
+static void damon_va_check_access(struct damon_ctx *ctx,
+ struct mm_struct *mm, struct damon_region *r)
+{
+ static struct mm_struct *last_mm;
+ static unsigned long last_addr;
+ static unsigned long last_page_sz = PAGE_SIZE;
+ static bool last_accessed;
+
+ /* If the region is in the last checked page, reuse the result */
+ if (mm == last_mm && (ALIGN_DOWN(last_addr, last_page_sz) ==
+ ALIGN_DOWN(r->sampling_addr, last_page_sz))) {
+ if (last_accessed)
+ r->nr_accesses++;
+ return;
+ }
+
+ last_accessed = damon_va_young(mm, r->sampling_addr, &last_page_sz);
+ if (last_accessed)
+ r->nr_accesses++;
+
+ last_mm = mm;
+ last_addr = r->sampling_addr;
+}
+
+unsigned int damon_va_check_accesses(struct damon_ctx *ctx)
+{
+ struct damon_target *t;
+ struct mm_struct *mm;
+ struct damon_region *r;
+ unsigned int max_nr_accesses = 0;
+
+ damon_for_each_target(t, ctx) {
+ mm = damon_get_mm(t);
+ if (!mm)
+ continue;
+ damon_for_each_region(r, t) {
+ damon_va_check_access(ctx, mm, r);
+ max_nr_accesses = max(r->nr_accesses, max_nr_accesses);
+ }
+ mmput(mm);
+ }
+
+ return max_nr_accesses;
+}
+
+/*
+ * Functions for the target validity check and cleanup
+ */
+
+bool damon_va_target_valid(void *target)
+{
+ struct damon_target *t = target;
+ struct task_struct *task;
+
+ task = damon_get_task_struct(t);
+ if (task) {
+ put_task_struct(task);
+ return true;
+ }
+
+ return false;
+}
+
+void damon_va_set_primitives(struct damon_ctx *ctx)
+{
+ ctx->primitive.init = damon_va_init;
+ ctx->primitive.update = damon_va_update;
+ ctx->primitive.prepare_access_checks = damon_va_prepare_access_checks;
+ ctx->primitive.check_accesses = damon_va_check_accesses;
+ ctx->primitive.reset_aggregated = NULL;
+ ctx->primitive.target_valid = damon_va_target_valid;
+ ctx->primitive.cleanup = NULL;
+}
+
+#include "vaddr-test.h"
diff --git a/mm/early_ioremap.c b/mm/early_ioremap.c
index 164607c7cdf1..74984c23a87e 100644
--- a/mm/early_ioremap.c
+++ b/mm/early_ioremap.c
@@ -38,13 +38,8 @@ pgprot_t __init __weak early_memremap_pgprot_adjust(resource_size_t phys_addr,
return prot;
}
-void __init __weak early_ioremap_shutdown(void)
-{
-}
-
void __init early_ioremap_reset(void)
{
- early_ioremap_shutdown();
after_paging_init = 1;
}
diff --git a/mm/highmem.c b/mm/highmem.c
index 4fb51d735aa6..4212ad0e4a19 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -436,7 +436,7 @@ EXPORT_SYMBOL(zero_user_segments);
static inline int kmap_local_idx_push(void)
{
- WARN_ON_ONCE(in_irq() && !irqs_disabled());
+ WARN_ON_ONCE(in_hardirq() && !irqs_disabled());
current->kmap_ctrl.idx += KM_INCR;
BUG_ON(current->kmap_ctrl.idx >= KM_MAX_IDX);
return current->kmap_ctrl.idx - 1;
diff --git a/mm/ioremap.c b/mm/ioremap.c
index 8ee0136f8cb0..5fe598ecd9b7 100644
--- a/mm/ioremap.c
+++ b/mm/ioremap.c
@@ -8,33 +8,9 @@
*/
#include <linux/vmalloc.h>
#include <linux/mm.h>
-#include <linux/sched.h>
#include <linux/io.h>
#include <linux/export.h>
-#include <asm/cacheflush.h>
-#include "pgalloc-track.h"
-
-#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-static unsigned int __ro_after_init iomap_max_page_shift = BITS_PER_LONG - 1;
-
-static int __init set_nohugeiomap(char *str)
-{
- iomap_max_page_shift = PAGE_SHIFT;
- return 0;
-}
-early_param("nohugeiomap", set_nohugeiomap);
-#else /* CONFIG_HAVE_ARCH_HUGE_VMAP */
-static const unsigned int iomap_max_page_shift = PAGE_SHIFT;
-#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
-
-int ioremap_page_range(unsigned long addr,
- unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
-{
- return vmap_range(addr, end, phys_addr, prot, iomap_max_page_shift);
-}
-
-#ifdef CONFIG_GENERIC_IOREMAP
void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long prot)
{
unsigned long offset, vaddr;
@@ -71,4 +47,3 @@ void iounmap(volatile void __iomem *addr)
vunmap((void *)((unsigned long)addr & PAGE_MASK));
}
EXPORT_SYMBOL(iounmap);
-#endif /* CONFIG_GENERIC_IOREMAP */
diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index 575c685aa642..7a97db8bc8e7 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -20,6 +20,7 @@
#include <linux/moduleparam.h>
#include <linux/random.h>
#include <linux/rcupdate.h>
+#include <linux/sched/clock.h>
#include <linux/sched/sysctl.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
@@ -196,6 +197,8 @@ static noinline void metadata_update_state(struct kfence_metadata *meta,
*/
track->num_stack_entries = stack_trace_save(track->stack_entries, KFENCE_STACK_DEPTH, 1);
track->pid = task_pid_nr(current);
+ track->cpu = raw_smp_processor_id();
+ track->ts_nsec = local_clock(); /* Same source as printk timestamps. */
/*
* Pairs with READ_ONCE() in
diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h
index 24065321ff8a..c1f23c61e5f9 100644
--- a/mm/kfence/kfence.h
+++ b/mm/kfence/kfence.h
@@ -36,6 +36,8 @@ enum kfence_object_state {
/* Alloc/free tracking information. */
struct kfence_track {
pid_t pid;
+ int cpu;
+ u64 ts_nsec;
int num_stack_entries;
unsigned long stack_entries[KFENCE_STACK_DEPTH];
};
diff --git a/mm/kfence/kfence_test.c b/mm/kfence/kfence_test.c
index eb6307c199ea..f1690cf54199 100644
--- a/mm/kfence/kfence_test.c
+++ b/mm/kfence/kfence_test.c
@@ -800,6 +800,9 @@ static int test_init(struct kunit *test)
unsigned long flags;
int i;
+ if (!__kfence_pool)
+ return -EINVAL;
+
spin_lock_irqsave(&observed.lock, flags);
for (i = 0; i < ARRAY_SIZE(observed.lines); i++)
observed.lines[i][0] = '\0';
diff --git a/mm/kfence/report.c b/mm/kfence/report.c
index 4b891dd75650..f93a7b2a338b 100644
--- a/mm/kfence/report.c
+++ b/mm/kfence/report.c
@@ -9,6 +9,7 @@
#include <linux/kernel.h>
#include <linux/lockdep.h>
+#include <linux/math.h>
#include <linux/printk.h>
#include <linux/sched/debug.h>
#include <linux/seq_file.h>
@@ -100,6 +101,13 @@ static void kfence_print_stack(struct seq_file *seq, const struct kfence_metadat
bool show_alloc)
{
const struct kfence_track *track = show_alloc ? &meta->alloc_track : &meta->free_track;
+ u64 ts_sec = track->ts_nsec;
+ unsigned long rem_nsec = do_div(ts_sec, NSEC_PER_SEC);
+
+ /* Timestamp matches printk timestamp format. */
+ seq_con_printf(seq, "%s by task %d on cpu %d at %lu.%06lus:\n",
+ show_alloc ? "allocated" : "freed", track->pid,
+ track->cpu, (unsigned long)ts_sec, rem_nsec / 1000);
if (track->num_stack_entries) {
/* Skip allocation/free internals stack. */
@@ -126,15 +134,14 @@ void kfence_print_object(struct seq_file *seq, const struct kfence_metadata *met
return;
}
- seq_con_printf(seq,
- "kfence-#%td [0x%p-0x%p"
- ", size=%d, cache=%s] allocated by task %d:\n",
- meta - kfence_metadata, (void *)start, (void *)(start + size - 1), size,
- (cache && cache->name) ? cache->name : "<destroyed>", meta->alloc_track.pid);
+ seq_con_printf(seq, "kfence-#%td: 0x%p-0x%p, size=%d, cache=%s\n\n",
+ meta - kfence_metadata, (void *)start, (void *)(start + size - 1),
+ size, (cache && cache->name) ? cache->name : "<destroyed>");
+
kfence_print_stack(seq, meta, true);
if (meta->state == KFENCE_OBJECT_FREED) {
- seq_con_printf(seq, "\nfreed by task %d:\n", meta->free_track.pid);
+ seq_con_printf(seq, "\n");
kfence_print_stack(seq, meta, false);
}
}
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 73d46d16d575..b59f1761d817 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -598,7 +598,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size,
object->checksum = 0;
/* task information */
- if (in_irq()) {
+ if (in_hardirq()) {
object->pid = 0;
strncpy(object->comm, "hardirq", sizeof(object->comm));
} else if (in_serving_softirq()) {
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 4c527a80b6c9..9fd0be32a281 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -52,6 +52,73 @@ module_param(memmap_on_memory, bool, 0444);
MODULE_PARM_DESC(memmap_on_memory, "Enable memmap on memory for memory hotplug");
#endif
+enum {
+ ONLINE_POLICY_CONTIG_ZONES = 0,
+ ONLINE_POLICY_AUTO_MOVABLE,
+};
+
+const char *online_policy_to_str[] = {
+ [ONLINE_POLICY_CONTIG_ZONES] = "contig-zones",
+ [ONLINE_POLICY_AUTO_MOVABLE] = "auto-movable",
+};
+
+static int set_online_policy(const char *val, const struct kernel_param *kp)
+{
+ int ret = sysfs_match_string(online_policy_to_str, val);
+
+ if (ret < 0)
+ return ret;
+ *((int *)kp->arg) = ret;
+ return 0;
+}
+
+static int get_online_policy(char *buffer, const struct kernel_param *kp)
+{
+ return sprintf(buffer, "%s\n", online_policy_to_str[*((int *)kp->arg)]);
+}
+
+/*
+ * memory_hotplug.online_policy: configure online behavior when onlining without
+ * specifying a zone (MMOP_ONLINE)
+ *
+ * "contig-zones": keep zone contiguous
+ * "auto-movable": online memory to ZONE_MOVABLE if the configuration
+ * (auto_movable_ratio, auto_movable_numa_aware) allows for it
+ */
+static int online_policy __read_mostly = ONLINE_POLICY_CONTIG_ZONES;
+static const struct kernel_param_ops online_policy_ops = {
+ .set = set_online_policy,
+ .get = get_online_policy,
+};
+module_param_cb(online_policy, &online_policy_ops, &online_policy, 0644);
+MODULE_PARM_DESC(online_policy,
+ "Set the online policy (\"contig-zones\", \"auto-movable\") "
+ "Default: \"contig-zones\"");
+
+/*
+ * memory_hotplug.auto_movable_ratio: specify maximum MOVABLE:KERNEL ratio
+ *
+ * The ratio represent an upper limit and the kernel might decide to not
+ * online some memory to ZONE_MOVABLE -- e.g., because hotplugged KERNEL memory
+ * doesn't allow for more MOVABLE memory.
+ */
+static unsigned int auto_movable_ratio __read_mostly = 301;
+module_param(auto_movable_ratio, uint, 0644);
+MODULE_PARM_DESC(auto_movable_ratio,
+ "Set the maximum ratio of MOVABLE:KERNEL memory in the system "
+ "in percent for \"auto-movable\" online policy. Default: 301");
+
+/*
+ * memory_hotplug.auto_movable_numa_aware: consider numa node stats
+ */
+#ifdef CONFIG_NUMA
+static bool auto_movable_numa_aware __read_mostly = true;
+module_param(auto_movable_numa_aware, bool, 0644);
+MODULE_PARM_DESC(auto_movable_numa_aware,
+ "Consider numa node stats in addition to global stats in "
+ "\"auto-movable\" online policy. Default: true");
+#endif /* CONFIG_NUMA */
+
/*
* online_page_callback contains pointer to current page onlining function.
* Initially it is generic_online_page(). If it is required it could be
@@ -410,15 +477,13 @@ void __ref remove_pfn_range_from_zone(struct zone *zone,
sizeof(struct page) * cur_nr_pages);
}
-#ifdef CONFIG_ZONE_DEVICE
/*
* Zone shrinking code cannot properly deal with ZONE_DEVICE. So
* we will not try to shrink the zones - which is okay as
* set_zone_contiguous() cannot deal with ZONE_DEVICE either way.
*/
- if (zone_idx(zone) == ZONE_DEVICE)
+ if (zone_is_zone_device(zone))
return;
-#endif
clear_zone_contiguous(zone);
@@ -663,6 +728,109 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
set_zone_contiguous(zone);
}
+struct auto_movable_stats {
+ unsigned long kernel_early_pages;
+ unsigned long movable_pages;
+};
+
+static void auto_movable_stats_account_zone(struct auto_movable_stats *stats,
+ struct zone *zone)
+{
+ if (zone_idx(zone) == ZONE_MOVABLE) {
+ stats->movable_pages += zone->present_pages;
+ } else {
+ stats->kernel_early_pages += zone->present_early_pages;
+#ifdef CONFIG_CMA
+ /*
+ * CMA pages (never on hotplugged memory) behave like
+ * ZONE_MOVABLE.
+ */
+ stats->movable_pages += zone->cma_pages;
+ stats->kernel_early_pages -= zone->cma_pages;
+#endif /* CONFIG_CMA */
+ }
+}
+struct auto_movable_group_stats {
+ unsigned long movable_pages;
+ unsigned long req_kernel_early_pages;
+};
+
+static int auto_movable_stats_account_group(struct memory_group *group,
+ void *arg)
+{
+ const int ratio = READ_ONCE(auto_movable_ratio);
+ struct auto_movable_group_stats *stats = arg;
+ long pages;
+
+ /*
+ * We don't support modifying the config while the auto-movable online
+ * policy is already enabled. Just avoid the division by zero below.
+ */
+ if (!ratio)
+ return 0;
+
+ /*
+ * Calculate how many early kernel pages this group requires to
+ * satisfy the configured zone ratio.
+ */
+ pages = group->present_movable_pages * 100 / ratio;
+ pages -= group->present_kernel_pages;
+
+ if (pages > 0)
+ stats->req_kernel_early_pages += pages;
+ stats->movable_pages += group->present_movable_pages;
+ return 0;
+}
+
+static bool auto_movable_can_online_movable(int nid, struct memory_group *group,
+ unsigned long nr_pages)
+{
+ unsigned long kernel_early_pages, movable_pages;
+ struct auto_movable_group_stats group_stats = {};
+ struct auto_movable_stats stats = {};
+ pg_data_t *pgdat = NODE_DATA(nid);
+ struct zone *zone;
+ int i;
+
+ /* Walk all relevant zones and collect MOVABLE vs. KERNEL stats. */
+ if (nid == NUMA_NO_NODE) {
+ /* TODO: cache values */
+ for_each_populated_zone(zone)
+ auto_movable_stats_account_zone(&stats, zone);
+ } else {
+ for (i = 0; i < MAX_NR_ZONES; i++) {
+ zone = pgdat->node_zones + i;
+ if (populated_zone(zone))
+ auto_movable_stats_account_zone(&stats, zone);
+ }
+ }
+
+ kernel_early_pages = stats.kernel_early_pages;
+ movable_pages = stats.movable_pages;
+
+ /*
+ * Kernel memory inside dynamic memory group allows for more MOVABLE
+ * memory within the same group. Remove the effect of all but the
+ * current group from the stats.
+ */
+ walk_dynamic_memory_groups(nid, auto_movable_stats_account_group,
+ group, &group_stats);
+ if (kernel_early_pages <= group_stats.req_kernel_early_pages)
+ return false;
+ kernel_early_pages -= group_stats.req_kernel_early_pages;
+ movable_pages -= group_stats.movable_pages;
+
+ if (group && group->is_dynamic)
+ kernel_early_pages += group->present_kernel_pages;
+
+ /*
+ * Test if we could online the given number of pages to ZONE_MOVABLE
+ * and still stay in the configured ratio.
+ */
+ movable_pages += nr_pages;
+ return movable_pages <= (auto_movable_ratio * kernel_early_pages) / 100;
+}
+
/*
* Returns a default kernel memory zone for the given pfn range.
* If no kernel zone covers this pfn range it will automatically go
@@ -684,6 +852,117 @@ static struct zone *default_kernel_zone_for_pfn(int nid, unsigned long start_pfn
return &pgdat->node_zones[ZONE_NORMAL];
}
+/*
+ * Determine to which zone to online memory dynamically based on user
+ * configuration and system stats. We care about the following ratio:
+ *
+ * MOVABLE : KERNEL
+ *
+ * Whereby MOVABLE is memory in ZONE_MOVABLE and KERNEL is memory in
+ * one of the kernel zones. CMA pages inside one of the kernel zones really
+ * behaves like ZONE_MOVABLE, so we treat them accordingly.
+ *
+ * We don't allow for hotplugged memory in a KERNEL zone to increase the
+ * amount of MOVABLE memory we can have, so we end up with:
+ *
+ * MOVABLE : KERNEL_EARLY
+ *
+ * Whereby KERNEL_EARLY is memory in one of the kernel zones, available sinze
+ * boot. We base our calculation on KERNEL_EARLY internally, because:
+ *
+ * a) Hotplugged memory in one of the kernel zones can sometimes still get
+ * hotunplugged, especially when hot(un)plugging individual memory blocks.
+ * There is no coordination across memory devices, therefore "automatic"
+ * hotunplugging, as implemented in hypervisors, could result in zone
+ * imbalances.
+ * b) Early/boot memory in one of the kernel zones can usually not get
+ * hotunplugged again (e.g., no firmware interface to unplug, fragmented
+ * with unmovable allocations). While there are corner cases where it might
+ * still work, it is barely relevant in practice.
+ *
+ * Exceptions are dynamic memory groups, which allow for more MOVABLE
+ * memory within the same memory group -- because in that case, there is
+ * coordination within the single memory device managed by a single driver.
+ *
+ * We rely on "present pages" instead of "managed pages", as the latter is
+ * highly unreliable and dynamic in virtualized environments, and does not
+ * consider boot time allocations. For example, memory ballooning adjusts the
+ * managed pages when inflating/deflating the balloon, and balloon compaction
+ * can even migrate inflated pages between zones.
+ *
+ * Using "present pages" is better but some things to keep in mind are:
+ *
+ * a) Some memblock allocations, such as for the crashkernel area, are
+ * effectively unused by the kernel, yet they account to "present pages".
+ * Fortunately, these allocations are comparatively small in relevant setups
+ * (e.g., fraction of system memory).
+ * b) Some hotplugged memory blocks in virtualized environments, esecially
+ * hotplugged by virtio-mem, look like they are completely present, however,
+ * only parts of the memory block are actually currently usable.
+ * "present pages" is an upper limit that can get reached at runtime. As
+ * we base our calculations on KERNEL_EARLY, this is not an issue.
+ */
+static struct zone *auto_movable_zone_for_pfn(int nid,
+ struct memory_group *group,
+ unsigned long pfn,
+ unsigned long nr_pages)
+{
+ unsigned long online_pages = 0, max_pages, end_pfn;
+ struct page *page;
+
+ if (!auto_movable_ratio)
+ goto kernel_zone;
+
+ if (group && !group->is_dynamic) {
+ max_pages = group->s.max_pages;
+ online_pages = group->present_movable_pages;
+
+ /* If anything is !MOVABLE online the rest !MOVABLE. */
+ if (group->present_kernel_pages)
+ goto kernel_zone;
+ } else if (!group || group->d.unit_pages == nr_pages) {
+ max_pages = nr_pages;
+ } else {
+ max_pages = group->d.unit_pages;
+ /*
+ * Take a look at all online sections in the current unit.
+ * We can safely assume that all pages within a section belong
+ * to the same zone, because dynamic memory groups only deal
+ * with hotplugged memory.
+ */
+ pfn = ALIGN_DOWN(pfn, group->d.unit_pages);
+ end_pfn = pfn + group->d.unit_pages;
+ for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+ page = pfn_to_online_page(pfn);
+ if (!page)
+ continue;
+ /* If anything is !MOVABLE online the rest !MOVABLE. */
+ if (page_zonenum(page) != ZONE_MOVABLE)
+ goto kernel_zone;
+ online_pages += PAGES_PER_SECTION;
+ }
+ }
+
+ /*
+ * Online MOVABLE if we could *currently* online all remaining parts
+ * MOVABLE. We expect to (add+) online them immediately next, so if
+ * nobody interferes, all will be MOVABLE if possible.
+ */
+ nr_pages = max_pages - online_pages;
+ if (!auto_movable_can_online_movable(NUMA_NO_NODE, group, nr_pages))
+ goto kernel_zone;
+
+#ifdef CONFIG_NUMA
+ if (auto_movable_numa_aware &&
+ !auto_movable_can_online_movable(nid, group, nr_pages))
+ goto kernel_zone;
+#endif /* CONFIG_NUMA */
+
+ return &NODE_DATA(nid)->node_zones[ZONE_MOVABLE];
+kernel_zone:
+ return default_kernel_zone_for_pfn(nid, pfn, nr_pages);
+}
+
static inline struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn,
unsigned long nr_pages)
{
@@ -708,7 +987,8 @@ static inline struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn
return movable_node_enabled ? movable_zone : kernel_zone;
}
-struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn,
+struct zone *zone_for_pfn_range(int online_type, int nid,
+ struct memory_group *group, unsigned long start_pfn,
unsigned long nr_pages)
{
if (online_type == MMOP_ONLINE_KERNEL)
@@ -717,6 +997,9 @@ struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn,
if (online_type == MMOP_ONLINE_MOVABLE)
return &NODE_DATA(nid)->node_zones[ZONE_MOVABLE];
+ if (online_policy == ONLINE_POLICY_AUTO_MOVABLE)
+ return auto_movable_zone_for_pfn(nid, group, start_pfn, nr_pages);
+
return default_zone_for_pfn(nid, start_pfn, nr_pages);
}
@@ -724,10 +1007,25 @@ struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn,
* This function should only be called by memory_block_{online,offline},
* and {online,offline}_pages.
*/
-void adjust_present_page_count(struct zone *zone, long nr_pages)
+void adjust_present_page_count(struct page *page, struct memory_group *group,
+ long nr_pages)
{
+ struct zone *zone = page_zone(page);
+ const bool movable = zone_idx(zone) == ZONE_MOVABLE;
+
+ /*
+ * We only support onlining/offlining/adding/removing of complete
+ * memory blocks; therefore, either all is either early or hotplugged.
+ */
+ if (early_section(__pfn_to_section(page_to_pfn(page))))
+ zone->present_early_pages += nr_pages;
zone->present_pages += nr_pages;
zone->zone_pgdat->node_present_pages += nr_pages;
+
+ if (group && movable)
+ group->present_movable_pages += nr_pages;
+ else if (group && !movable)
+ group->present_kernel_pages += nr_pages;
}
int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages,
@@ -773,7 +1071,8 @@ void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages)
kasan_remove_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages));
}
-int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone)
+int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
+ struct zone *zone, struct memory_group *group)
{
unsigned long flags;
int need_zonelists_rebuild = 0;
@@ -826,7 +1125,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *z
}
online_pages_range(pfn, nr_pages);
- adjust_present_page_count(zone, nr_pages);
+ adjust_present_page_count(pfn_to_page(pfn), group, nr_pages);
node_states_set_node(nid, &arg);
if (need_zonelists_rebuild)
@@ -1059,6 +1358,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
{
struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) };
struct vmem_altmap mhp_altmap = {};
+ struct memory_group *group = NULL;
u64 start, size;
bool new_node = false;
int ret;
@@ -1070,6 +1370,13 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
if (ret)
return ret;
+ if (mhp_flags & MHP_NID_IS_MGID) {
+ group = memory_group_find_by_id(nid);
+ if (!group)
+ return -EINVAL;
+ nid = group->nid;
+ }
+
if (!node_possible(nid)) {
WARN(1, "node %d was absent from the node_possible_map\n", nid);
return -EINVAL;
@@ -1104,9 +1411,10 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
goto error;
/* create memory block devices after memory was added */
- ret = create_memory_block_devices(start, size, mhp_altmap.alloc);
+ ret = create_memory_block_devices(start, size, mhp_altmap.alloc,
+ group);
if (ret) {
- arch_remove_memory(nid, start, size, NULL);
+ arch_remove_memory(start, size, NULL);
goto error;
}
@@ -1298,7 +1606,7 @@ struct zone *test_pages_in_a_zone(unsigned long start_pfn,
unsigned long pfn, sec_end_pfn;
struct zone *zone = NULL;
struct page *page;
- int i;
+
for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn + 1);
pfn < end_pfn;
pfn = sec_end_pfn, sec_end_pfn += PAGES_PER_SECTION) {
@@ -1307,17 +1615,10 @@ struct zone *test_pages_in_a_zone(unsigned long start_pfn,
continue;
for (; pfn < sec_end_pfn && pfn < end_pfn;
pfn += MAX_ORDER_NR_PAGES) {
- i = 0;
- /* This is just a CONFIG_HOLES_IN_ZONE check.*/
- while ((i < MAX_ORDER_NR_PAGES) &&
- !pfn_valid_within(pfn + i))
- i++;
- if (i == MAX_ORDER_NR_PAGES || pfn + i >= end_pfn)
- continue;
/* Check if we got outside of the zone */
- if (zone && !zone_spans_pfn(zone, pfn + i))
+ if (zone && !zone_spans_pfn(zone, pfn))
return NULL;
- page = pfn_to_page(pfn + i);
+ page = pfn_to_page(pfn);
if (zone && page_zone(page) != zone)
return NULL;
zone = page_zone(page);
@@ -1568,7 +1869,8 @@ static int count_system_ram_pages_cb(unsigned long start_pfn,
return 0;
}
-int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages)
+int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages,
+ struct memory_group *group)
{
const unsigned long end_pfn = start_pfn + nr_pages;
unsigned long pfn, system_ram_pages = 0;
@@ -1704,7 +2006,7 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages)
/* removal success */
adjust_managed_page_count(pfn_to_page(start_pfn), -nr_pages);
- adjust_present_page_count(zone, -nr_pages);
+ adjust_present_page_count(pfn_to_page(start_pfn), group, -nr_pages);
/* reinitialise watermarks and update pcp limits */
init_per_zone_wmark_min();
@@ -1746,7 +2048,9 @@ failed_removal:
static int check_memblock_offlined_cb(struct memory_block *mem, void *arg)
{
int ret = !is_memblock_offlined(mem);
+ int *nid = arg;
+ *nid = mem->nid;
if (unlikely(ret)) {
phys_addr_t beginpa, endpa;
@@ -1839,12 +2143,12 @@ void try_offline_node(int nid)
}
EXPORT_SYMBOL(try_offline_node);
-static int __ref try_remove_memory(int nid, u64 start, u64 size)
+static int __ref try_remove_memory(u64 start, u64 size)
{
- int rc = 0;
struct vmem_altmap mhp_altmap = {};
struct vmem_altmap *altmap = NULL;
unsigned long nr_vmemmap_pages;
+ int rc = 0, nid = NUMA_NO_NODE;
BUG_ON(check_hotplug_memory_range(start, size));
@@ -1852,8 +2156,12 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
* All memory blocks must be offlined before removing memory. Check
* whether all memory blocks in question are offline and return error
* if this is not the case.
+ *
+ * While at it, determine the nid. Note that if we'd have mixed nodes,
+ * we'd only try to offline the last determined one -- which is good
+ * enough for the cases we care about.
*/
- rc = walk_memory_blocks(start, size, NULL, check_memblock_offlined_cb);
+ rc = walk_memory_blocks(start, size, &nid, check_memblock_offlined_cb);
if (rc)
return rc;
@@ -1893,7 +2201,7 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
mem_hotplug_begin();
- arch_remove_memory(nid, start, size, altmap);
+ arch_remove_memory(start, size, altmap);
if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) {
memblock_free(start, size);
@@ -1902,7 +2210,8 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
release_mem_region_adjustable(start, size);
- try_offline_node(nid);
+ if (nid != NUMA_NO_NODE)
+ try_offline_node(nid);
mem_hotplug_done();
return 0;
@@ -1910,7 +2219,6 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
/**
* __remove_memory - Remove memory if every memory block is offline
- * @nid: the node ID
* @start: physical address of the region to remove
* @size: size of the region to remove
*
@@ -1918,14 +2226,14 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
* and online/offline operations before this call, as required by
* try_offline_node().
*/
-void __remove_memory(int nid, u64 start, u64 size)
+void __remove_memory(u64 start, u64 size)
{
/*
* trigger BUG() if some memory is not offlined prior to calling this
* function
*/
- if (try_remove_memory(nid, start, size))
+ if (try_remove_memory(start, size))
BUG();
}
@@ -1933,12 +2241,12 @@ void __remove_memory(int nid, u64 start, u64 size)
* Remove memory if every memory block is offline, otherwise return -EBUSY is
* some memory is not offline
*/
-int remove_memory(int nid, u64 start, u64 size)
+int remove_memory(u64 start, u64 size)
{
int rc;
lock_device_hotplug();
- rc = try_remove_memory(nid, start, size);
+ rc = try_remove_memory(start, size);
unlock_device_hotplug();
return rc;
@@ -1998,7 +2306,7 @@ static int try_reonline_memory_block(struct memory_block *mem, void *arg)
* unplugged all memory (so it's no longer in use) and want to offline + remove
* that memory.
*/
-int offline_and_remove_memory(int nid, u64 start, u64 size)
+int offline_and_remove_memory(u64 start, u64 size)
{
const unsigned long mb_count = size / memory_block_size_bytes();
uint8_t *online_types, *tmp;
@@ -2034,7 +2342,7 @@ int offline_and_remove_memory(int nid, u64 start, u64 size)
* This cannot fail as it cannot get onlined in the meantime.
*/
if (!rc) {
- rc = try_remove_memory(nid, start, size);
+ rc = try_remove_memory(start, size);
if (rc)
pr_err("%s: Failed to remove memory: %d", __func__, rc);
}
diff --git a/mm/memremap.c b/mm/memremap.c
index 15a074ffb8d7..ed593bf87109 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -140,14 +140,11 @@ static void pageunmap_range(struct dev_pagemap *pgmap, int range_id)
{
struct range *range = &pgmap->ranges[range_id];
struct page *first_page;
- int nid;
/* make sure to access a memmap that was actually initialized */
first_page = pfn_to_page(pfn_first(pgmap, range_id));
/* pages are dead and unused, undo the arch mapping */
- nid = page_to_nid(first_page);
-
mem_hotplug_begin();
remove_pfn_range_from_zone(page_zone(first_page), PHYS_PFN(range->start),
PHYS_PFN(range_len(range)));
@@ -155,7 +152,7 @@ static void pageunmap_range(struct dev_pagemap *pgmap, int range_id)
__remove_pages(PHYS_PFN(range->start),
PHYS_PFN(range_len(range)), NULL);
} else {
- arch_remove_memory(nid, range->start, range_len(range),
+ arch_remove_memory(range->start, range_len(range),
pgmap_altmap(pgmap));
kasan_remove_zero_shadow(__va(range->start), range_len(range));
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f95e1d2386a1..de309a1dfe65 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -594,8 +594,6 @@ static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
static int page_is_consistent(struct zone *zone, struct page *page)
{
- if (!pfn_valid_within(page_to_pfn(page)))
- return 0;
if (zone != page_zone(page))
return 0;
@@ -1025,16 +1023,12 @@ buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn,
if (order >= MAX_ORDER - 2)
return false;
- if (!pfn_valid_within(buddy_pfn))
- return false;
-
combined_pfn = buddy_pfn & pfn;
higher_page = page + (combined_pfn - pfn);
buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1);
higher_buddy = higher_page + (buddy_pfn - combined_pfn);
- return pfn_valid_within(buddy_pfn) &&
- page_is_buddy(higher_page, higher_buddy, order + 1);
+ return page_is_buddy(higher_page, higher_buddy, order + 1);
}
/*
@@ -1095,8 +1089,6 @@ continue_merging:
buddy_pfn = __find_buddy_pfn(pfn, order);
buddy = page + (buddy_pfn - pfn);
- if (!pfn_valid_within(buddy_pfn))
- goto done_merging;
if (!page_is_buddy(page, buddy, order))
goto done_merging;
/*
@@ -1754,9 +1746,7 @@ void __init memblock_free_pages(struct page *page, unsigned long pfn,
/*
* Check that the whole (or subset of) a pageblock given by the interval of
* [start_pfn, end_pfn) is valid and within the same zone, before scanning it
- * with the migration of free compaction scanner. The scanners then need to
- * use only pfn_valid_within() check for arches that allow holes within
- * pageblocks.
+ * with the migration of free compaction scanner.
*
* Return struct page pointer of start_pfn, or NULL if checks were not passed.
*
@@ -1872,8 +1862,6 @@ static inline void __init pgdat_init_report_one_done(void)
*/
static inline bool __init deferred_pfn_valid(unsigned long pfn)
{
- if (!pfn_valid_within(pfn))
- return false;
if (!(pfn & (pageblock_nr_pages - 1)) && !pfn_valid(pfn))
return false;
return true;
@@ -2520,11 +2508,6 @@ static int move_freepages(struct zone *zone,
int pages_moved = 0;
for (pfn = start_pfn; pfn <= end_pfn;) {
- if (!pfn_valid_within(pfn)) {
- pfn++;
- continue;
- }
-
page = pfn_to_page(pfn);
if (!PageBuddy(page)) {
/*
@@ -7271,6 +7254,9 @@ static void __init calculate_node_totalpages(struct pglist_data *pgdat,
zone->zone_start_pfn = 0;
zone->spanned_pages = size;
zone->present_pages = real_size;
+#if defined(CONFIG_MEMORY_HOTPLUG)
+ zone->present_early_pages = real_size;
+#endif
totalpages += size;
realtotalpages += real_size;
@@ -8828,9 +8814,6 @@ struct page *has_unmovable_pages(struct zone *zone, struct page *page,
}
for (; iter < pageblock_nr_pages - offset; iter++) {
- if (!pfn_valid_within(pfn + iter))
- continue;
-
page = pfn_to_page(pfn + iter);
/*
diff --git a/mm/page_ext.c b/mm/page_ext.c
index 293b2685fc48..dfb91653d359 100644
--- a/mm/page_ext.c
+++ b/mm/page_ext.c
@@ -58,11 +58,21 @@
* can utilize this callback to initialize the state of it correctly.
*/
+#if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT)
+static bool need_page_idle(void)
+{
+ return true;
+}
+struct page_ext_operations page_idle_ops = {
+ .need = need_page_idle,
+};
+#endif
+
static struct page_ext_operations *page_ext_ops[] = {
#ifdef CONFIG_PAGE_OWNER
&page_owner_ops,
#endif
-#if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT)
+#if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT)
&page_idle_ops,
#endif
};
diff --git a/mm/page_idle.c b/mm/page_idle.c
index 64e5344a992c..edead6a8a5f9 100644
--- a/mm/page_idle.c
+++ b/mm/page_idle.c
@@ -207,16 +207,6 @@ static const struct attribute_group page_idle_attr_group = {
.name = "page_idle",
};
-#ifndef CONFIG_64BIT
-static bool need_page_idle(void)
-{
- return true;
-}
-struct page_ext_operations page_idle_ops = {
- .need = need_page_idle,
-};
-#endif
-
static int __init page_idle_init(void)
{
int err;
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index fff55bb830f9..a95c2c6562d0 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -93,8 +93,7 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype)
buddy_pfn = __find_buddy_pfn(pfn, order);
buddy = page + (buddy_pfn - pfn);
- if (pfn_valid_within(buddy_pfn) &&
- !is_migrate_isolate_page(buddy)) {
+ if (!is_migrate_isolate_page(buddy)) {
__isolate_free_page(page, order);
isolated_page = true;
}
@@ -250,10 +249,6 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn,
struct page *page;
while (pfn < end_pfn) {
- if (!pfn_valid_within(pfn)) {
- pfn++;
- continue;
- }
page = pfn_to_page(pfn);
if (PageBuddy(page))
/*
diff --git a/mm/page_owner.c b/mm/page_owner.c
index f51a57e92aa3..62402d22539b 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -276,9 +276,6 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
pageblock_mt = get_pageblock_migratetype(page);
for (; pfn < block_end_pfn; pfn++) {
- if (!pfn_valid_within(pfn))
- continue;
-
/* The pageblock is online, no need to recheck. */
page = pfn_to_page(pfn);
@@ -479,10 +476,6 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
continue;
}
- /* Check for holes within a MAX_ORDER area */
- if (!pfn_valid_within(pfn))
- continue;
-
page = pfn_to_page(pfn);
if (PageBuddy(page)) {
unsigned long freepage_order = buddy_order_unsafe(page);
@@ -560,14 +553,9 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone)
block_end_pfn = min(block_end_pfn, end_pfn);
for (; pfn < block_end_pfn; pfn++) {
- struct page *page;
+ struct page *page = pfn_to_page(pfn);
struct page_ext *page_ext;
- if (!pfn_valid_within(pfn))
- continue;
-
- page = pfn_to_page(pfn);
-
if (page_zone(page) != zone)
continue;
diff --git a/mm/percpu.c b/mm/percpu.c
index e1c20837a42a..e0a986818903 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -146,7 +146,6 @@ static unsigned int pcpu_high_unit_cpu __ro_after_init;
/* the address of the first chunk which starts with the kernel static area */
void *pcpu_base_addr __ro_after_init;
-EXPORT_SYMBOL_GPL(pcpu_base_addr);
static const int *pcpu_unit_map __ro_after_init; /* cpu -> unit */
const unsigned long *pcpu_unit_offsets __ro_after_init; /* cpu -> unit offset */
diff --git a/mm/rmap.c b/mm/rmap.c
index 2d29a57d29e8..6aebd1747251 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1231,11 +1231,13 @@ void page_add_file_rmap(struct page *page, bool compound)
nr_pages);
} else {
if (PageTransCompound(page) && page_mapping(page)) {
+ struct page *head = compound_head(page);
+
VM_WARN_ON_ONCE(!PageLocked(page));
- SetPageDoubleMap(compound_head(page));
+ SetPageDoubleMap(head);
if (PageMlocked(page))
- clear_page_mlock(compound_head(page));
+ clear_page_mlock(head);
}
if (!atomic_inc_and_test(&page->_mapcount))
goto out;
diff --git a/mm/secretmem.c b/mm/secretmem.c
index 030f02ddc7c1..1fea68b8d5a6 100644
--- a/mm/secretmem.c
+++ b/mm/secretmem.c
@@ -18,6 +18,7 @@
#include <linux/secretmem.h>
#include <linux/set_memory.h>
#include <linux/sched/signal.h>
+#include <linux/refcount.h>
#include <uapi/linux/magic.h>
@@ -40,11 +41,11 @@ module_param_named(enable, secretmem_enable, bool, 0400);
MODULE_PARM_DESC(secretmem_enable,
"Enable secretmem and memfd_secret(2) system call");
-static atomic_t secretmem_users;
+static refcount_t secretmem_users;
bool secretmem_active(void)
{
- return !!atomic_read(&secretmem_users);
+ return !!refcount_read(&secretmem_users);
}
static vm_fault_t secretmem_fault(struct vm_fault *vmf)
@@ -103,7 +104,7 @@ static const struct vm_operations_struct secretmem_vm_ops = {
static int secretmem_release(struct inode *inode, struct file *file)
{
- atomic_dec(&secretmem_users);
+ refcount_dec(&secretmem_users);
return 0;
}
@@ -217,7 +218,7 @@ SYSCALL_DEFINE1(memfd_secret, unsigned int, flags)
file->f_flags |= O_LARGEFILE;
fd_install(fd, file);
- atomic_inc(&secretmem_users);
+ refcount_inc(&secretmem_users);
return fd;
err_put_fd:
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 3824dc16ce1c..d77830ff604c 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -44,6 +44,19 @@
#include "internal.h"
#include "pgalloc-track.h"
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+static unsigned int __ro_after_init ioremap_max_page_shift = BITS_PER_LONG - 1;
+
+static int __init set_nohugeiomap(char *str)
+{
+ ioremap_max_page_shift = PAGE_SHIFT;
+ return 0;
+}
+early_param("nohugeiomap", set_nohugeiomap);
+#else /* CONFIG_HAVE_ARCH_HUGE_VMAP */
+static const unsigned int ioremap_max_page_shift = PAGE_SHIFT;
+#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
+
#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
static bool __ro_after_init vmap_allow_huge = true;
@@ -298,15 +311,14 @@ static int vmap_range_noflush(unsigned long addr, unsigned long end,
return err;
}
-int vmap_range(unsigned long addr, unsigned long end,
- phys_addr_t phys_addr, pgprot_t prot,
- unsigned int max_page_shift)
+int ioremap_page_range(unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot)
{
int err;
- err = vmap_range_noflush(addr, end, phys_addr, prot, max_page_shift);
+ err = vmap_range_noflush(addr, end, phys_addr, pgprot_nx(prot),
+ ioremap_max_page_shift);
flush_cache_vmap(addr, end);
-
return err;
}
diff --git a/mm/workingset.c b/mm/workingset.c
index 5ba3e42446fa..d4268d8e9a82 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -249,7 +249,7 @@ void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages)
* @target_memcg: the cgroup that is causing the reclaim
* @page: the page being evicted
*
- * Returns a shadow entry to be stored in @page->mapping->i_pages in place
+ * Return: a shadow entry to be stored in @page->mapping->i_pages in place
* of the evicted @page so that a later refault can be detected.
*/
void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg)
diff --git a/scripts/check_extable.sh b/scripts/check_extable.sh
index 93af93c7b346..4b380564cf74 100755
--- a/scripts/check_extable.sh
+++ b/scripts/check_extable.sh
@@ -4,7 +4,7 @@
obj=$1
-file ${obj} | grep -q ELF || (echo "${obj} is not and ELF file." 1>&2 ; exit 0)
+file ${obj} | grep -q ELF || (echo "${obj} is not an ELF file." 1>&2 ; exit 0)
# Bail out early if there isn't an __ex_table section in this object file.
objdump -hj __ex_table ${obj} 2> /dev/null > /dev/null
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 461d4221e4a4..c27d2312cfc3 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -501,7 +501,7 @@ our $Binary = qr{(?i)0b[01]+$Int_type?};
our $Hex = qr{(?i)0x[0-9a-f]+$Int_type?};
our $Int = qr{[0-9]+$Int_type?};
our $Octal = qr{0[0-7]+$Int_type?};
-our $String = qr{"[X\t]*"};
+our $String = qr{(?:\b[Lu])?"[X\t]*"};
our $Float_hex = qr{(?i)0x[0-9a-f]+p-?[0-9]+[fl]?};
our $Float_dec = qr{(?i)(?:[0-9]+\.[0-9]*|[0-9]*\.[0-9]+)(?:e-?[0-9]+)?[fl]?};
our $Float_int = qr{(?i)[0-9]+e-?[0-9]+[fl]?};
@@ -1181,7 +1181,8 @@ sub git_commit_info {
# git log --format='%H %s' -1 $line |
# echo "commit $(cut -c 1-12,41-)"
# done
- } elsif ($lines[0] =~ /^fatal: ambiguous argument '$commit': unknown revision or path not in the working tree\./) {
+ } elsif ($lines[0] =~ /^fatal: ambiguous argument '$commit': unknown revision or path not in the working tree\./ ||
+ $lines[0] =~ /^fatal: bad object $commit/) {
$id = undef;
} else {
$id = substr($lines[0], 0, 12);
@@ -2587,6 +2588,8 @@ sub process {
my $reported_maintainer_file = 0;
my $non_utf8_charset = 0;
+ my $last_git_commit_id_linenr = -1;
+
my $last_blank_line = 0;
my $last_coalesced_string_linenr = -1;
@@ -2909,10 +2912,10 @@ sub process {
my ($email_name, $email_comment, $email_address, $comment1) = parse_email($ctx);
my ($author_name, $author_comment, $author_address, $comment2) = parse_email($author);
- if ($email_address eq $author_address && $email_name eq $author_name) {
+ if (lc $email_address eq lc $author_address && $email_name eq $author_name) {
$author_sob = $ctx;
$authorsignoff = 2;
- } elsif ($email_address eq $author_address) {
+ } elsif (lc $email_address eq lc $author_address) {
$author_sob = $ctx;
$authorsignoff = 3;
} elsif ($email_name eq $author_name) {
@@ -3170,10 +3173,20 @@ sub process {
}
# Check for git id commit length and improperly formed commit descriptions
- if ($in_commit_log && !$commit_log_possible_stack_dump &&
+# A correctly formed commit description is:
+# commit <SHA-1 hash length 12+ chars> ("Complete commit subject")
+# with the commit subject '("' prefix and '")' suffix
+# This is a fairly compilicated block as it tests for what appears to be
+# bare SHA-1 hash with minimum length of 5. It also avoids several types of
+# possible SHA-1 matches.
+# A commit match can span multiple lines so this block attempts to find a
+# complete typical commit on a maximum of 3 lines
+ if ($perl_version_ok &&
+ $in_commit_log && !$commit_log_possible_stack_dump &&
$line !~ /^\s*(?:Link|Patchwork|http|https|BugLink|base-commit):/i &&
$line !~ /^This reverts commit [0-9a-f]{7,40}/ &&
- ($line =~ /\bcommit\s+[0-9a-f]{5,}\b/i ||
+ (($line =~ /\bcommit\s+[0-9a-f]{5,}\b/i ||
+ ($line =~ /\bcommit\s*$/i && defined($rawlines[$linenr]) && $rawlines[$linenr] =~ /^\s*[0-9a-f]{5,}\b/i)) ||
($line =~ /(?:\s|^)[0-9a-f]{12,40}(?:[\s"'\(\[]|$)/i &&
$line !~ /[\<\[][0-9a-f]{12,40}[\>\]]/i &&
$line !~ /\bfixes:\s*[0-9a-f]{12,40}/i))) {
@@ -3183,49 +3196,56 @@ sub process {
my $long = 0;
my $case = 1;
my $space = 1;
- my $hasdesc = 0;
- my $hasparens = 0;
my $id = '0123456789ab';
my $orig_desc = "commit description";
my $description = "";
+ my $herectx = $herecurr;
+ my $has_parens = 0;
+ my $has_quotes = 0;
+
+ my $input = $line;
+ if ($line =~ /(?:\bcommit\s+[0-9a-f]{5,}|\bcommit\s*$)/i) {
+ for (my $n = 0; $n < 2; $n++) {
+ if ($input =~ /\bcommit\s+[0-9a-f]{5,}\s*($balanced_parens)/i) {
+ $orig_desc = $1;
+ $has_parens = 1;
+ # Always strip leading/trailing parens then double quotes if existing
+ $orig_desc = substr($orig_desc, 1, -1);
+ if ($orig_desc =~ /^".*"$/) {
+ $orig_desc = substr($orig_desc, 1, -1);
+ $has_quotes = 1;
+ }
+ last;
+ }
+ last if ($#lines < $linenr + $n);
+ $input .= " " . trim($rawlines[$linenr + $n]);
+ $herectx .= "$rawlines[$linenr + $n]\n";
+ }
+ $herectx = $herecurr if (!$has_parens);
+ }
- if ($line =~ /\b(c)ommit\s+([0-9a-f]{5,})\b/i) {
+ if ($input =~ /\b(c)ommit\s+([0-9a-f]{5,})\b/i) {
$init_char = $1;
$orig_commit = lc($2);
- } elsif ($line =~ /\b([0-9a-f]{12,40})\b/i) {
+ $short = 0 if ($input =~ /\bcommit\s+[0-9a-f]{12,40}/i);
+ $long = 1 if ($input =~ /\bcommit\s+[0-9a-f]{41,}/i);
+ $space = 0 if ($input =~ /\bcommit [0-9a-f]/i);
+ $case = 0 if ($input =~ /\b[Cc]ommit\s+[0-9a-f]{5,40}[^A-F]/);
+ } elsif ($input =~ /\b([0-9a-f]{12,40})\b/i) {
$orig_commit = lc($1);
}
- $short = 0 if ($line =~ /\bcommit\s+[0-9a-f]{12,40}/i);
- $long = 1 if ($line =~ /\bcommit\s+[0-9a-f]{41,}/i);
- $space = 0 if ($line =~ /\bcommit [0-9a-f]/i);
- $case = 0 if ($line =~ /\b[Cc]ommit\s+[0-9a-f]{5,40}[^A-F]/);
- if ($line =~ /\bcommit\s+[0-9a-f]{5,}\s+\("([^"]+)"\)/i) {
- $orig_desc = $1;
- $hasparens = 1;
- } elsif ($line =~ /\bcommit\s+[0-9a-f]{5,}\s*$/i &&
- defined $rawlines[$linenr] &&
- $rawlines[$linenr] =~ /^\s*\("([^"]+)"\)/) {
- $orig_desc = $1;
- $hasparens = 1;
- } elsif ($line =~ /\bcommit\s+[0-9a-f]{5,}\s+\("[^"]+$/i &&
- defined $rawlines[$linenr] &&
- $rawlines[$linenr] =~ /^\s*[^"]+"\)/) {
- $line =~ /\bcommit\s+[0-9a-f]{5,}\s+\("([^"]+)$/i;
- $orig_desc = $1;
- $rawlines[$linenr] =~ /^\s*([^"]+)"\)/;
- $orig_desc .= " " . $1;
- $hasparens = 1;
- }
-
($id, $description) = git_commit_info($orig_commit,
$id, $orig_desc);
if (defined($id) &&
- ($short || $long || $space || $case || ($orig_desc ne $description) || !$hasparens)) {
+ ($short || $long || $space || $case || ($orig_desc ne $description) || !$has_quotes) &&
+ $last_git_commit_id_linenr != $linenr - 1) {
ERROR("GIT_COMMIT_ID",
- "Please use git commit description style 'commit <12+ chars of sha1> (\"<title line>\")' - ie: '${init_char}ommit $id (\"$description\")'\n" . $herecurr);
+ "Please use git commit description style 'commit <12+ chars of sha1> (\"<title line>\")' - ie: '${init_char}ommit $id (\"$description\")'\n" . $herectx);
}
+ #don't report the next line if this line ends in commit and the sha1 hash is the next line
+ $last_git_commit_id_linenr = $linenr if ($line =~ /\bcommit\s*$/i);
}
# Check for added, moved or deleted files
@@ -6132,7 +6152,8 @@ sub process {
}
# concatenated string without spaces between elements
- if ($line =~ /$String[A-Za-z0-9_]/ || $line =~ /[A-Za-z0-9_]$String/) {
+ if ($line =~ /$String[A-Z_]/ ||
+ ($line =~ /([A-Za-z0-9_]+)$String/ && $1 !~ /^[Lu]$/)) {
if (CHK("CONCATENATED_STRING",
"Concatenated strings should use spaces between elements\n" . $herecurr) &&
$fix) {
@@ -6145,7 +6166,7 @@ sub process {
}
# uncoalesced string fragments
- if ($line =~ /$String\s*"/) {
+ if ($line =~ /$String\s*[Lu]?"/) {
if (WARN("STRING_FRAGMENTS",
"Consecutive strings are generally better as a single string\n" . $herecurr) &&
$fix) {
diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index 9d959bc24859..95611df1d26e 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -111,10 +111,10 @@ static inline int test_and_clear_bit(int nr, unsigned long *addr)
}
/**
- * bitmap_alloc - Allocate bitmap
+ * bitmap_zalloc - Allocate bitmap
* @nbits: Number of bits
*/
-static inline unsigned long *bitmap_alloc(int nbits)
+static inline unsigned long *bitmap_zalloc(int nbits)
{
return calloc(1, BITS_TO_LONGS(nbits) * sizeof(unsigned long));
}
diff --git a/tools/perf/bench/find-bit-bench.c b/tools/perf/bench/find-bit-bench.c
index 73b5bcc5946a..22b5cfe97023 100644
--- a/tools/perf/bench/find-bit-bench.c
+++ b/tools/perf/bench/find-bit-bench.c
@@ -54,7 +54,7 @@ static bool asm_test_bit(long nr, const unsigned long *addr)
static int do_for_each_set_bit(unsigned int num_bits)
{
- unsigned long *to_test = bitmap_alloc(num_bits);
+ unsigned long *to_test = bitmap_zalloc(num_bits);
struct timeval start, end, diff;
u64 runtime_us;
struct stats fb_time_stats, tb_time_stats;
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index a812f32cf5d9..a192014fa52b 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -139,11 +139,11 @@ static void *c2c_he_zalloc(size_t size)
if (!c2c_he)
return NULL;
- c2c_he->cpuset = bitmap_alloc(c2c.cpus_cnt);
+ c2c_he->cpuset = bitmap_zalloc(c2c.cpus_cnt);
if (!c2c_he->cpuset)
return NULL;
- c2c_he->nodeset = bitmap_alloc(c2c.nodes_cnt);
+ c2c_he->nodeset = bitmap_zalloc(c2c.nodes_cnt);
if (!c2c_he->nodeset)
return NULL;
@@ -2047,7 +2047,7 @@ static int setup_nodes(struct perf_session *session)
struct perf_cpu_map *map = n[node].map;
unsigned long *set;
- set = bitmap_alloc(c2c.cpus_cnt);
+ set = bitmap_zalloc(c2c.cpus_cnt);
if (!set)
return -ENOMEM;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 06c4dca0c466..b3509d9d20cc 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -2757,7 +2757,7 @@ int cmd_record(int argc, const char **argv)
if (rec->opts.affinity != PERF_AFFINITY_SYS) {
rec->affinity_mask.nbits = cpu__max_cpu();
- rec->affinity_mask.bits = bitmap_alloc(rec->affinity_mask.nbits);
+ rec->affinity_mask.bits = bitmap_zalloc(rec->affinity_mask.nbits);
if (!rec->affinity_mask.bits) {
pr_err("Failed to allocate thread mask for %zd cpus\n", rec->affinity_mask.nbits);
err = -ENOMEM;
diff --git a/tools/perf/tests/bitmap.c b/tools/perf/tests/bitmap.c
index 96c137360918..12b805efdca0 100644
--- a/tools/perf/tests/bitmap.c
+++ b/tools/perf/tests/bitmap.c
@@ -14,7 +14,7 @@ static unsigned long *get_bitmap(const char *str, int nbits)
unsigned long *bm = NULL;
int i;
- bm = bitmap_alloc(nbits);
+ bm = bitmap_zalloc(nbits);
if (map && bm) {
for (i = 0; i < map->nr; i++)
diff --git a/tools/perf/tests/mem2node.c b/tools/perf/tests/mem2node.c
index a258bd51f1a4..e4d0d58b97f8 100644
--- a/tools/perf/tests/mem2node.c
+++ b/tools/perf/tests/mem2node.c
@@ -27,7 +27,7 @@ static unsigned long *get_bitmap(const char *str, int nbits)
unsigned long *bm = NULL;
int i;
- bm = bitmap_alloc(nbits);
+ bm = bitmap_zalloc(nbits);
if (map && bm) {
for (i = 0; i < map->nr; i++) {
diff --git a/tools/perf/util/affinity.c b/tools/perf/util/affinity.c
index a5e31f826828..7b12bd7a3080 100644
--- a/tools/perf/util/affinity.c
+++ b/tools/perf/util/affinity.c
@@ -25,11 +25,11 @@ int affinity__setup(struct affinity *a)
{
int cpu_set_size = get_cpu_set_size();
- a->orig_cpus = bitmap_alloc(cpu_set_size * 8);
+ a->orig_cpus = bitmap_zalloc(cpu_set_size * 8);
if (!a->orig_cpus)
return -1;
sched_getaffinity(0, cpu_set_size, (cpu_set_t *)a->orig_cpus);
- a->sched_cpus = bitmap_alloc(cpu_set_size * 8);
+ a->sched_cpus = bitmap_zalloc(cpu_set_size * 8);
if (!a->sched_cpus) {
zfree(&a->orig_cpus);
return -1;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index d2231cb7c4f7..1c7414f66655 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -278,7 +278,7 @@ static int do_read_bitmap(struct feat_fd *ff, unsigned long **pset, u64 *psize)
if (ret)
return ret;
- set = bitmap_alloc(size);
+ set = bitmap_zalloc(size);
if (!set)
return -ENOMEM;
@@ -1294,7 +1294,7 @@ static int memory_node__read(struct memory_node *n, unsigned long idx)
size++;
- n->set = bitmap_alloc(size);
+ n->set = bitmap_zalloc(size);
if (!n->set) {
closedir(dir);
return -ENOMEM;
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 99d047c5ead0..29b747ac31c1 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -313,7 +313,7 @@ static int metricgroup__setup_events(struct list_head *groups,
struct evsel *evsel, *tmp;
unsigned long *evlist_used;
- evlist_used = bitmap_alloc(perf_evlist->core.nr_entries);
+ evlist_used = bitmap_zalloc(perf_evlist->core.nr_entries);
if (!evlist_used)
return -ENOMEM;
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index ab7108d22428..512dc8b9c168 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -106,7 +106,7 @@ static int perf_mmap__aio_bind(struct mmap *map, int idx, int cpu, int affinity)
data = map->aio.data[idx];
mmap_len = mmap__mmap_len(map);
node_index = cpu__get_node(cpu);
- node_mask = bitmap_alloc(node_index + 1);
+ node_mask = bitmap_zalloc(node_index + 1);
if (!node_mask) {
pr_err("Failed to allocate node mask for mbind: error %m\n");
return -1;
@@ -258,7 +258,7 @@ static void build_node_mask(int node, struct mmap_cpu_mask *mask)
static int perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *mp)
{
map->affinity_mask.nbits = cpu__max_cpu();
- map->affinity_mask.bits = bitmap_alloc(map->affinity_mask.nbits);
+ map->affinity_mask.bits = bitmap_zalloc(map->affinity_mask.nbits);
if (!map->affinity_mask.bits)
return -1;
diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile
new file mode 100644
index 000000000000..8a3f2cd9fec0
--- /dev/null
+++ b/tools/testing/selftests/damon/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for damon selftests
+
+TEST_FILES = _chk_dependency.sh
+TEST_PROGS = debugfs_attrs.sh
+
+include ../lib.mk
diff --git a/tools/testing/selftests/damon/_chk_dependency.sh b/tools/testing/selftests/damon/_chk_dependency.sh
new file mode 100644
index 000000000000..0189db81550b
--- /dev/null
+++ b/tools/testing/selftests/damon/_chk_dependency.sh
@@ -0,0 +1,28 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+DBGFS=/sys/kernel/debug/damon
+
+if [ $EUID -ne 0 ];
+then
+ echo "Run as root"
+ exit $ksft_skip
+fi
+
+if [ ! -d "$DBGFS" ]
+then
+ echo "$DBGFS not found"
+ exit $ksft_skip
+fi
+
+for f in attrs target_ids monitor_on
+do
+ if [ ! -f "$DBGFS/$f" ]
+ then
+ echo "$f not found"
+ exit 1
+ fi
+done
diff --git a/tools/testing/selftests/damon/debugfs_attrs.sh b/tools/testing/selftests/damon/debugfs_attrs.sh
new file mode 100644
index 000000000000..bfabb19dc0d3
--- /dev/null
+++ b/tools/testing/selftests/damon/debugfs_attrs.sh
@@ -0,0 +1,75 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+test_write_result() {
+ file=$1
+ content=$2
+ orig_content=$3
+ expect_reason=$4
+ expected=$5
+
+ echo "$content" > "$file"
+ if [ $? -ne "$expected" ]
+ then
+ echo "writing $content to $file doesn't return $expected"
+ echo "expected because: $expect_reason"
+ echo "$orig_content" > "$file"
+ exit 1
+ fi
+}
+
+test_write_succ() {
+ test_write_result "$1" "$2" "$3" "$4" 0
+}
+
+test_write_fail() {
+ test_write_result "$1" "$2" "$3" "$4" 1
+}
+
+test_content() {
+ file=$1
+ orig_content=$2
+ expected=$3
+ expect_reason=$4
+
+ content=$(cat "$file")
+ if [ "$content" != "$expected" ]
+ then
+ echo "reading $file expected $expected but $content"
+ echo "expected because: $expect_reason"
+ echo "$orig_content" > "$file"
+ exit 1
+ fi
+}
+
+source ./_chk_dependency.sh
+
+# Test attrs file
+# ===============
+
+file="$DBGFS/attrs"
+orig_content=$(cat "$file")
+
+test_write_succ "$file" "1 2 3 4 5" "$orig_content" "valid input"
+test_write_fail "$file" "1 2 3 4" "$orig_content" "no enough fields"
+test_write_fail "$file" "1 2 3 5 4" "$orig_content" \
+ "min_nr_regions > max_nr_regions"
+test_content "$file" "$orig_content" "1 2 3 4 5" "successfully written"
+echo "$orig_content" > "$file"
+
+# Test target_ids file
+# ====================
+
+file="$DBGFS/target_ids"
+orig_content=$(cat "$file")
+
+test_write_succ "$file" "1 2 3 4" "$orig_content" "valid input"
+test_write_succ "$file" "1 2 abc 4" "$orig_content" "still valid input"
+test_content "$file" "$orig_content" "1 2" "non-integer was there"
+test_write_succ "$file" "abc 2 3" "$orig_content" "the file allows wrong input"
+test_content "$file" "$orig_content" "" "wrong input written"
+test_write_succ "$file" "" "$orig_content" "empty input"
+test_content "$file" "$orig_content" "" "empty input written"
+echo "$orig_content" > "$file"
+
+echo "PASS"
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 3c30d0045d8d..479868570d59 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -171,7 +171,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm);
guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
host_num_pages = vm_num_host_pages(mode, guest_num_pages);
- bmap = bitmap_alloc(host_num_pages);
+ bmap = bitmap_zalloc(host_num_pages);
if (dirty_log_manual_caps) {
cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 5fe0140e407e..792c60e1b17d 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -749,8 +749,8 @@ static void run_test(enum vm_guest_mode mode, void *arg)
pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
- bmap = bitmap_alloc(host_num_pages);
- host_bmap_track = bitmap_alloc(host_num_pages);
+ bmap = bitmap_zalloc(host_num_pages);
+ host_bmap_track = bitmap_zalloc(host_num_pages);
/* Add an extra memory slot for testing dirty logging */
vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
index 06a64980a5d2..68f26a8b4f42 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
@@ -111,7 +111,7 @@ int main(int argc, char *argv[])
nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096);
nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096);
- bmap = bitmap_alloc(TEST_MEM_PAGES);
+ bmap = bitmap_zalloc(TEST_MEM_PAGES);
host_test_mem = addr_gpa2hva(vm, GUEST_TEST_MEM);
while (!done) {
diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c
index 74baab83fec3..192a2899bae8 100644
--- a/tools/testing/selftests/memfd/memfd_test.c
+++ b/tools/testing/selftests/memfd/memfd_test.c
@@ -56,7 +56,7 @@ static int mfd_assert_new(const char *name, loff_t sz, unsigned int flags)
static int mfd_assert_reopen_fd(int fd_in)
{
- int r, fd;
+ int fd;
char path[100];
sprintf(path, "/proc/self/fd/%d", fd_in);