diff options
380 files changed, 7165 insertions, 3216 deletions
diff --git a/Documentation/ABI/testing/procfs-smaps_rollup b/Documentation/ABI/testing/procfs-smaps_rollup index a4e31c465194..b446a7154a1b 100644 --- a/Documentation/ABI/testing/procfs-smaps_rollup +++ b/Documentation/ABI/testing/procfs-smaps_rollup @@ -22,6 +22,7 @@ Description: MMUPageSize: 4 kB Rss: 884 kB Pss: 385 kB + Pss_Dirty: 68 kB Pss_Anon: 301 kB Pss_File: 80 kB Pss_Shmem: 4 kB diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-ksm b/Documentation/ABI/testing/sysfs-kernel-mm-ksm index 1c9bed5595f5..d244674a9480 100644 --- a/Documentation/ABI/testing/sysfs-kernel-mm-ksm +++ b/Documentation/ABI/testing/sysfs-kernel-mm-ksm @@ -41,7 +41,7 @@ Description: Kernel Samepage Merging daemon sysfs interface sleep_millisecs: how many milliseconds ksm should sleep between scans. - See Documentation/vm/ksm.rst for more information. + See Documentation/mm/ksm.rst for more information. What: /sys/kernel/mm/ksm/merge_across_nodes Date: January 2013 diff --git a/Documentation/ABI/testing/sysfs-kernel-slab b/Documentation/ABI/testing/sysfs-kernel-slab index c440f4946e12..cd5fb8fa3ddf 100644 --- a/Documentation/ABI/testing/sysfs-kernel-slab +++ b/Documentation/ABI/testing/sysfs-kernel-slab @@ -37,7 +37,7 @@ Description: The alloc_calls file is read-only and lists the kernel code locations from which allocations for this cache were performed. The alloc_calls file only contains information if debugging is - enabled for that cache (see Documentation/vm/slub.rst). + enabled for that cache (see Documentation/mm/slub.rst). What: /sys/kernel/slab/<cache>/alloc_fastpath Date: February 2008 @@ -219,7 +219,7 @@ Contact: Pekka Enberg <penberg@cs.helsinki.fi>, Description: The free_calls file is read-only and lists the locations of object frees if slab debugging is enabled (see - Documentation/vm/slub.rst). + Documentation/mm/slub.rst). What: /sys/kernel/slab/<cache>/free_fastpath Date: February 2008 diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index bf842b80bde9..be4a77baf784 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1237,6 +1237,13 @@ PAGE_SIZE multiple when read back. the target cgroup. If less bytes are reclaimed than the specified amount, -EAGAIN is returned. + Please note that the proactive reclaim (triggered by this + interface) is not meant to indicate memory pressure on the + memory cgroup. Therefore socket memory balancing triggered by + the memory reclaim normally is not exercised in this case. + This means that the networking layer will not adapt based on + reclaim induced by memory.reclaim. + memory.peak A read-only single value file which exists on non-root cgroups. @@ -1441,6 +1448,24 @@ PAGE_SIZE multiple when read back. workingset_nodereclaim Number of times a shadow node has been reclaimed + pgscan (npn) + Amount of scanned pages (in an inactive LRU list) + + pgsteal (npn) + Amount of reclaimed pages + + pgscan_kswapd (npn) + Amount of scanned pages by kswapd (in an inactive LRU list) + + pgscan_direct (npn) + Amount of scanned pages directly (in an inactive LRU list) + + pgsteal_kswapd (npn) + Amount of reclaimed pages by kswapd + + pgsteal_direct (npn) + Amount of reclaimed pages directly + pgfault (npn) Total number of page faults incurred @@ -1450,12 +1475,6 @@ PAGE_SIZE multiple when read back. pgrefill (npn) Amount of scanned pages (in an active LRU list) - pgscan (npn) - Amount of scanned pages (in an inactive LRU list) - - pgsteal (npn) - Amount of reclaimed pages - pgactivate (npn) Amount of pages moved to the active LRU list diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index ef9f80b1ddde..43c31e9de7c7 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1728,9 +1728,11 @@ Built with CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON=y, the default is on. - This is not compatible with memory_hotplug.memmap_on_memory. - If both parameters are enabled, hugetlb_free_vmemmap takes - precedence over memory_hotplug.memmap_on_memory. + Note that the vmemmap pages may be allocated from the added + memory block itself when memory_hotplug.memmap_on_memory is + enabled, those vmemmap pages cannot be optimized even if this + feature is enabled. Other vmemmap pages not allocated from + the added memory block itself do not be affected. hung_task_panic= [KNL] Should the hung task detector generate panics. @@ -3073,10 +3075,12 @@ [KNL,X86,ARM] Boolean flag to enable this feature. Format: {on | off (default)} When enabled, runtime hotplugged memory will - allocate its internal metadata (struct pages) - from the hotadded memory which will allow to - hotadd a lot of memory without requiring - additional memory to do so. + allocate its internal metadata (struct pages, + those vmemmap pages cannot be optimized even + if hugetlb_free_vmemmap is enabled) from the + hotadded memory which will allow to hotadd a + lot of memory without requiring additional + memory to do so. This feature is disabled by default because it has some implication on large (e.g. GB) allocations in some configurations (e.g. small @@ -3086,10 +3090,6 @@ Note that even when enabled, there are a few cases where the feature is not effective. - This is not compatible with hugetlb_free_vmemmap. If - both parameters are enabled, hugetlb_free_vmemmap takes - precedence over memory_hotplug.memmap_on_memory. - memtest= [KNL,X86,ARM,M68K,PPC,RISCV] Enable memtest Format: <integer> default : 0 <disable> @@ -5502,7 +5502,7 @@ cache (risks via metadata attacks are mostly unchanged). Debug options disable merging on their own. - For more information see Documentation/vm/slub.rst. + For more information see Documentation/mm/slub.rst. slab_max_order= [MM, SLAB] Determines the maximum allowed order for slabs. @@ -5516,13 +5516,13 @@ slub_debug can create guard zones around objects and may poison objects when not in use. Also tracks the last alloc / free. For more information see - Documentation/vm/slub.rst. + Documentation/mm/slub.rst. slub_max_order= [MM, SLUB] Determines the maximum allowed order for slabs. A high setting may cause OOMs due to memory fragmentation. For more information see - Documentation/vm/slub.rst. + Documentation/mm/slub.rst. slub_min_objects= [MM, SLUB] The minimum number of objects per slab. SLUB will @@ -5531,12 +5531,12 @@ the number of objects indicated. The higher the number of objects the smaller the overhead of tracking slabs and the less frequently locks need to be acquired. - For more information see Documentation/vm/slub.rst. + For more information see Documentation/mm/slub.rst. slub_min_order= [MM, SLUB] Determines the minimum page order for slabs. Must be lower than slub_max_order. - For more information see Documentation/vm/slub.rst. + For more information see Documentation/mm/slub.rst. slub_merge [MM, SLUB] Same with slab_merge. diff --git a/Documentation/admin-guide/mm/concepts.rst b/Documentation/admin-guide/mm/concepts.rst index b966fcff993b..c79f1e336222 100644 --- a/Documentation/admin-guide/mm/concepts.rst +++ b/Documentation/admin-guide/mm/concepts.rst @@ -125,7 +125,7 @@ processor. Each bank is referred to as a `node` and for each node Linux constructs an independent memory management subsystem. A node has its own set of zones, lists of free and used pages and various statistics counters. You can find more details about NUMA in -:ref:`Documentation/vm/numa.rst <numa>` and in +:ref:`Documentation/mm/numa.rst <numa>` and in :ref:`Documentation/admin-guide/mm/numa_memory_policy.rst <numa_memory_policy>`. Page cache diff --git a/Documentation/admin-guide/mm/damon/index.rst b/Documentation/admin-guide/mm/damon/index.rst index 61aff88347f3..05500042f777 100644 --- a/Documentation/admin-guide/mm/damon/index.rst +++ b/Documentation/admin-guide/mm/damon/index.rst @@ -4,7 +4,7 @@ Monitoring Data Accesses ======================== -:doc:`DAMON </vm/damon/index>` allows light-weight data access monitoring. +:doc:`DAMON </mm/damon/index>` allows light-weight data access monitoring. Using DAMON, users can analyze the memory access patterns of their systems and optimize those. @@ -14,3 +14,4 @@ optimize those. start usage reclaim + lru_sort diff --git a/Documentation/admin-guide/mm/damon/lru_sort.rst b/Documentation/admin-guide/mm/damon/lru_sort.rst new file mode 100644 index 000000000000..c09cace80651 --- /dev/null +++ b/Documentation/admin-guide/mm/damon/lru_sort.rst @@ -0,0 +1,294 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============================= +DAMON-based LRU-lists Sorting +============================= + +DAMON-based LRU-lists Sorting (DAMON_LRU_SORT) is a static kernel module that +aimed to be used for proactive and lightweight data access pattern based +(de)prioritization of pages on their LRU-lists for making LRU-lists a more +trusworthy data access pattern source. + +Where Proactive LRU-lists Sorting is Required? +============================================== + +As page-granularity access checking overhead could be significant on huge +systems, LRU lists are normally not proactively sorted but partially and +reactively sorted for special events including specific user requests, system +calls and memory pressure. As a result, LRU lists are sometimes not so +perfectly prepared to be used as a trustworthy access pattern source for some +situations including reclamation target pages selection under sudden memory +pressure. + +Because DAMON can identify access patterns of best-effort accuracy while +inducing only user-specified range of overhead, proactively running +DAMON_LRU_SORT could be helpful for making LRU lists more trustworthy access +pattern source with low and controlled overhead. + +How It Works? +============= + +DAMON_LRU_SORT finds hot pages (pages of memory regions that showing access +rates that higher than a user-specified threshold) and cold pages (pages of +memory regions that showing no access for a time that longer than a +user-specified threshold) using DAMON, and prioritizes hot pages while +deprioritizing cold pages on their LRU-lists. To avoid it consuming too much +CPU for the prioritizations, a CPU time usage limit can be configured. Under +the limit, it prioritizes and deprioritizes more hot and cold pages first, +respectively. System administrators can also configure under what situation +this scheme should automatically activated and deactivated with three memory +pressure watermarks. + +Its default parameters for hotness/coldness thresholds and CPU quota limit are +conservatively chosen. That is, the module under its default parameters could +be widely used without harm for common situations while providing a level of +benefits for systems having clear hot/cold access patterns under memory +pressure while consuming only a limited small portion of CPU time. + +Interface: Module Parameters +============================ + +To use this feature, you should first ensure your system is running on a kernel +that is built with ``CONFIG_DAMON_LRU_SORT=y``. + +To let sysadmins enable or disable it and tune for the given system, +DAMON_LRU_SORT utilizes module parameters. That is, you can put +``damon_lru_sort.<parameter>=<value>`` on the kernel boot command line or write +proper values to ``/sys/modules/damon_lru_sort/parameters/<parameter>`` files. + +Below are the description of each parameter. + +enabled +------- + +Enable or disable DAMON_LRU_SORT. + +You can enable DAMON_LRU_SORT by setting the value of this parameter as ``Y``. +Setting it as ``N`` disables DAMON_LRU_SORT. Note that DAMON_LRU_SORT could do +no real monitoring and LRU-lists sorting due to the watermarks-based activation +condition. Refer to below descriptions for the watermarks parameter for this. + +commit_inputs +------------- + +Make DAMON_LRU_SORT reads the input parameters again, except ``enabled``. + +Input parameters that updated while DAMON_LRU_SORT is running are not applied +by default. Once this parameter is set as ``Y``, DAMON_LRU_SORT reads values +of parametrs except ``enabled`` again. Once the re-reading is done, this +parameter is set as ``N``. If invalid parameters are found while the +re-reading, DAMON_LRU_SORT will be disabled. + +hot_thres_access_freq +--------------------- + +Access frequency threshold for hot memory regions identification in permil. + +If a memory region is accessed in frequency of this or higher, DAMON_LRU_SORT +identifies the region as hot, and mark it as accessed on the LRU list, so that +it could not be reclaimed under memory pressure. 50% by default. + +cold_min_age +------------ + +Time threshold for cold memory regions identification in microseconds. + +If a memory region is not accessed for this or longer time, DAMON_LRU_SORT +identifies the region as cold, and mark it as unaccessed on the LRU list, so +that it could be reclaimed first under memory pressure. 120 seconds by +default. + +quota_ms +-------- + +Limit of time for trying the LRU lists sorting in milliseconds. + +DAMON_LRU_SORT tries to use only up to this time within a time window +(quota_reset_interval_ms) for trying LRU lists sorting. This can be used +for limiting CPU consumption of DAMON_LRU_SORT. If the value is zero, the +limit is disabled. + +10 ms by default. + +quota_reset_interval_ms +----------------------- + +The time quota charge reset interval in milliseconds. + +The charge reset interval for the quota of time (quota_ms). That is, +DAMON_LRU_SORT does not try LRU-lists sorting for more than quota_ms +milliseconds or quota_sz bytes within quota_reset_interval_ms milliseconds. + +1 second by default. + +wmarks_interval +--------------- + +The watermarks check time interval in microseconds. + +Minimal time to wait before checking the watermarks, when DAMON_LRU_SORT is +enabled but inactive due to its watermarks rule. 5 seconds by default. + +wmarks_high +----------- + +Free memory rate (per thousand) for the high watermark. + +If free memory of the system in bytes per thousand bytes is higher than this, +DAMON_LRU_SORT becomes inactive, so it does nothing but periodically checks the +watermarks. 200 (20%) by default. + +wmarks_mid +---------- + +Free memory rate (per thousand) for the middle watermark. + +If free memory of the system in bytes per thousand bytes is between this and +the low watermark, DAMON_LRU_SORT becomes active, so starts the monitoring and +the LRU-lists sorting. 150 (15%) by default. + +wmarks_low +---------- + +Free memory rate (per thousand) for the low watermark. + +If free memory of the system in bytes per thousand bytes is lower than this, +DAMON_LRU_SORT becomes inactive, so it does nothing but periodically checks the +watermarks. 50 (5%) by default. + +sample_interval +--------------- + +Sampling interval for the monitoring in microseconds. + +The sampling interval of DAMON for the cold memory monitoring. Please refer to +the DAMON documentation (:doc:`usage`) for more detail. 5ms by default. + +aggr_interval +------------- + +Aggregation interval for the monitoring in microseconds. + +The aggregation interval of DAMON for the cold memory monitoring. Please +refer to the DAMON documentation (:doc:`usage`) for more detail. 100ms by +default. + +min_nr_regions +-------------- + +Minimum number of monitoring regions. + +The minimal number of monitoring regions of DAMON for the cold memory +monitoring. This can be used to set lower-bound of the monitoring quality. +But, setting this too high could result in increased monitoring overhead. +Please refer to the DAMON documentation (:doc:`usage`) for more detail. 10 by +default. + +max_nr_regions +-------------- + +Maximum number of monitoring regions. + +The maximum number of monitoring regions of DAMON for the cold memory +monitoring. This can be used to set upper-bound of the monitoring overhead. +However, setting this too low could result in bad monitoring quality. Please +refer to the DAMON documentation (:doc:`usage`) for more detail. 1000 by +defaults. + +monitor_region_start +-------------------- + +Start of target memory region in physical address. + +The start physical address of memory region that DAMON_LRU_SORT will do work +against. By default, biggest System RAM is used as the region. + +monitor_region_end +------------------ + +End of target memory region in physical address. + +The end physical address of memory region that DAMON_LRU_SORT will do work +against. By default, biggest System RAM is used as the region. + +kdamond_pid +----------- + +PID of the DAMON thread. + +If DAMON_LRU_SORT is enabled, this becomes the PID of the worker thread. Else, +-1. + +nr_lru_sort_tried_hot_regions +----------------------------- + +Number of hot memory regions that tried to be LRU-sorted. + +bytes_lru_sort_tried_hot_regions +-------------------------------- + +Total bytes of hot memory regions that tried to be LRU-sorted. + +nr_lru_sorted_hot_regions +------------------------- + +Number of hot memory regions that successfully be LRU-sorted. + +bytes_lru_sorted_hot_regions +---------------------------- + +Total bytes of hot memory regions that successfully be LRU-sorted. + +nr_hot_quota_exceeds +-------------------- + +Number of times that the time quota limit for hot regions have exceeded. + +nr_lru_sort_tried_cold_regions +------------------------------ + +Number of cold memory regions that tried to be LRU-sorted. + +bytes_lru_sort_tried_cold_regions +--------------------------------- + +Total bytes of cold memory regions that tried to be LRU-sorted. + +nr_lru_sorted_cold_regions +-------------------------- + +Number of cold memory regions that successfully be LRU-sorted. + +bytes_lru_sorted_cold_regions +----------------------------- + +Total bytes of cold memory regions that successfully be LRU-sorted. + +nr_cold_quota_exceeds +--------------------- + +Number of times that the time quota limit for cold regions have exceeded. + +Example +======= + +Below runtime example commands make DAMON_LRU_SORT to find memory regions +having >=50% access frequency and LRU-prioritize while LRU-deprioritizing +memory regions that not accessed for 120 seconds. The prioritization and +deprioritization is limited to be done using only up to 1% CPU time to avoid +DAMON_LRU_SORT consuming too much CPU time for the (de)prioritization. It also +asks DAMON_LRU_SORT to do nothing if the system's free memory rate is more than +50%, but start the real works if it becomes lower than 40%. If DAMON_RECLAIM +doesn't make progress and therefore the free memory rate becomes lower than +20%, it asks DAMON_LRU_SORT to do nothing again, so that we can fall back to +the LRU-list based page granularity reclamation. :: + + # cd /sys/modules/damon_lru_sort/parameters + # echo 500 > hot_thres_access_freq + # echo 120000000 > cold_min_age + # echo 10 > quota_ms + # echo 1000 > quota_reset_interval_ms + # echo 500 > wmarks_high + # echo 400 > wmarks_mid + # echo 200 > wmarks_low + # echo Y > enabled diff --git a/Documentation/admin-guide/mm/damon/reclaim.rst b/Documentation/admin-guide/mm/damon/reclaim.rst index 46306f1f34b1..4f1479a11e63 100644 --- a/Documentation/admin-guide/mm/damon/reclaim.rst +++ b/Documentation/admin-guide/mm/damon/reclaim.rst @@ -48,12 +48,6 @@ DAMON_RECLAIM utilizes module parameters. That is, you can put ``damon_reclaim.<parameter>=<value>`` on the kernel boot command line or write proper values to ``/sys/modules/damon_reclaim/parameters/<parameter>`` files. -Note that the parameter values except ``enabled`` are applied only when -DAMON_RECLAIM starts. Therefore, if you want to apply new parameter values in -runtime and DAMON_RECLAIM is already enabled, you should disable and re-enable -it via ``enabled`` parameter file. Writing of the new values to proper -parameter values should be done before the re-enablement. - Below are the description of each parameter. enabled @@ -268,4 +262,4 @@ granularity reclamation. :: .. [1] https://research.google/pubs/pub48551/ .. [2] https://lwn.net/Articles/787611/ -.. [3] https://www.kernel.org/doc/html/latest/vm/free_page_reporting.html +.. [3] https://www.kernel.org/doc/html/latest/mm/free_page_reporting.html diff --git a/Documentation/admin-guide/mm/damon/usage.rst b/Documentation/admin-guide/mm/damon/usage.rst index 1bb7b72414b2..d52f572a9029 100644 --- a/Documentation/admin-guide/mm/damon/usage.rst +++ b/Documentation/admin-guide/mm/damon/usage.rst @@ -30,11 +30,11 @@ DAMON provides below interfaces for different users. <sysfs_interface>`. This will be removed after next LTS kernel is released, so users should move to the :ref:`sysfs interface <sysfs_interface>`. - *Kernel Space Programming Interface.* - :doc:`This </vm/damon/api>` is for kernel space programmers. Using this, + :doc:`This </mm/damon/api>` 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. For detail, please refer to the interface - :doc:`document </vm/damon/api>`. + :doc:`document </mm/damon/api>`. .. _sysfs_interface: @@ -185,7 +185,7 @@ controls the monitoring overhead, exist. You can set and get the values by writing to and rading from the files. For more details about the intervals and monitoring regions range, please refer -to the Design document (:doc:`/vm/damon/design`). +to the Design document (:doc:`/mm/damon/design`). contexts/<N>/targets/ --------------------- @@ -264,6 +264,8 @@ that can be written to and read from the file and their meaning are as below. - ``pageout``: Call ``madvise()`` for the region with ``MADV_PAGEOUT`` - ``hugepage``: Call ``madvise()`` for the region with ``MADV_HUGEPAGE`` - ``nohugepage``: Call ``madvise()`` for the region with ``MADV_NOHUGEPAGE`` + - ``lru_prio``: Prioritize the region on its LRU lists. + - ``lru_deprio``: Deprioritize the region on its LRU lists. - ``stat``: Do nothing but count the statistics schemes/<N>/access_pattern/ @@ -402,7 +404,7 @@ Attributes Users can get and set the ``sampling interval``, ``aggregation interval``, ``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 +attributes in detail, please refer to the :doc:`/mm/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:: diff --git a/Documentation/admin-guide/mm/index.rst b/Documentation/admin-guide/mm/index.rst index c21b5823f126..1bd11118dfb1 100644 --- a/Documentation/admin-guide/mm/index.rst +++ b/Documentation/admin-guide/mm/index.rst @@ -36,6 +36,7 @@ the Linux memory management. numa_memory_policy numaperf pagemap + shrinker_debugfs soft-dirty swap_numa transhuge diff --git a/Documentation/admin-guide/mm/shrinker_debugfs.rst b/Documentation/admin-guide/mm/shrinker_debugfs.rst new file mode 100644 index 000000000000..3887f0b294fe --- /dev/null +++ b/Documentation/admin-guide/mm/shrinker_debugfs.rst @@ -0,0 +1,135 @@ +.. _shrinker_debugfs: + +========================== +Shrinker Debugfs Interface +========================== + +Shrinker debugfs interface provides a visibility into the kernel memory +shrinkers subsystem and allows to get information about individual shrinkers +and interact with them. + +For each shrinker registered in the system a directory in **<debugfs>/shrinker/** +is created. The directory's name is composed from the shrinker's name and an +unique id: e.g. *kfree_rcu-0* or *sb-xfs:vda1-36*. + +Each shrinker directory contains **count** and **scan** files, which allow to +trigger *count_objects()* and *scan_objects()* callbacks for each memcg and +numa node (if applicable). + +Usage: +------ + +1. *List registered shrinkers* + + :: + + $ cd /sys/kernel/debug/shrinker/ + $ ls + dquota-cache-16 sb-devpts-28 sb-proc-47 sb-tmpfs-42 + mm-shadow-18 sb-devtmpfs-5 sb-proc-48 sb-tmpfs-43 + mm-zspool:zram0-34 sb-hugetlbfs-17 sb-pstore-31 sb-tmpfs-44 + rcu-kfree-0 sb-hugetlbfs-33 sb-rootfs-2 sb-tmpfs-49 + sb-aio-20 sb-iomem-12 sb-securityfs-6 sb-tracefs-13 + sb-anon_inodefs-15 sb-mqueue-21 sb-selinuxfs-22 sb-xfs:vda1-36 + sb-bdev-3 sb-nsfs-4 sb-sockfs-8 sb-zsmalloc-19 + sb-bpf-32 sb-pipefs-14 sb-sysfs-26 thp-deferred_split-10 + sb-btrfs:vda2-24 sb-proc-25 sb-tmpfs-1 thp-zero-9 + sb-cgroup2-30 sb-proc-39 sb-tmpfs-27 xfs-buf:vda1-37 + sb-configfs-23 sb-proc-41 sb-tmpfs-29 xfs-inodegc:vda1-38 + sb-dax-11 sb-proc-45 sb-tmpfs-35 + sb-debugfs-7 sb-proc-46 sb-tmpfs-40 + +2. *Get information about a specific shrinker* + + :: + + $ cd sb-btrfs\:vda2-24/ + $ ls + count scan + +3. *Count objects* + + Each line in the output has the following format:: + + <cgroup inode id> <nr of objects on node 0> <nr of objects on node 1> ... + <cgroup inode id> <nr of objects on node 0> <nr of objects on node 1> ... + ... + + If there are no objects on all numa nodes, a line is omitted. If there + are no objects at all, the output might be empty. + + If the shrinker is not memcg-aware or CONFIG_MEMCG is off, 0 is printed + as cgroup inode id. If the shrinker is not numa-aware, 0's are printed + for all nodes except the first one. + :: + + $ cat count + 1 224 2 + 21 98 0 + 55 818 10 + 2367 2 0 + 2401 30 0 + 225 13 0 + 599 35 0 + 939 124 0 + 1041 3 0 + 1075 1 0 + 1109 1 0 + 1279 60 0 + 1313 7 0 + 1347 39 0 + 1381 3 0 + 1449 14 0 + 1483 63 0 + 1517 53 0 + 1551 6 0 + 1585 1 0 + 1619 6 0 + 1653 40 0 + 1687 11 0 + 1721 8 0 + 1755 4 0 + 1789 52 0 + 1823 888 0 + 1857 1 0 + 1925 2 0 + 1959 32 0 + 2027 22 0 + 2061 9 0 + 2469 799 0 + 2537 861 0 + 2639 1 0 + 2707 70 0 + 2775 4 0 + 2877 84 0 + 293 1 0 + 735 8 0 + +4. *Scan objects* + + The expected input format:: + + <cgroup inode id> <numa id> <number of objects to scan> + + For a non-memcg-aware shrinker or on a system with no memory + cgrups **0** should be passed as cgroup id. + :: + + $ cd /sys/kernel/debug/shrinker/ + $ cd sb-btrfs\:vda2-24/ + + $ cat count | head -n 5 + 1 212 0 + 21 97 0 + 55 802 5 + 2367 2 0 + 225 13 0 + + $ echo "55 0 200" > scan + + $ cat count | head -n 5 + 1 212 0 + 21 96 0 + 55 752 5 + 2367 2 0 + 225 13 0 diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst index 5c9aa171a0d3..f74f722ad702 100644 --- a/Documentation/admin-guide/sysctl/vm.rst +++ b/Documentation/admin-guide/sysctl/vm.rst @@ -565,9 +565,8 @@ See Documentation/admin-guide/mm/hugetlbpage.rst hugetlb_optimize_vmemmap ======================== -This knob is not available when memory_hotplug.memmap_on_memory (kernel parameter) -is configured or the size of 'struct page' (a structure defined in -include/linux/mm_types.h) is not power of two (an unusual system config could +This knob is not available when the size of 'struct page' (a structure defined +in include/linux/mm_types.h) is not power of two (an unusual system config could result in this). Enable (set to 1) or disable (set to 0) the feature of optimizing vmemmap pages @@ -760,7 +759,7 @@ and don't use much of it. The default value is 0. -See Documentation/vm/overcommit-accounting.rst and +See Documentation/mm/overcommit-accounting.rst and mm/util.c::__vm_enough_memory() for more information. diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst index 726065a3095e..dc95df462eea 100644 --- a/Documentation/core-api/index.rst +++ b/Documentation/core-api/index.rst @@ -86,7 +86,7 @@ Memory management ================= How to allocate and use memory in the kernel. Note that there is a lot -more memory-management documentation in Documentation/vm/index.rst. +more memory-management documentation in Documentation/mm/index.rst. .. toctree:: :maxdepth: 1 diff --git a/Documentation/dev-tools/kmemleak.rst b/Documentation/dev-tools/kmemleak.rst index 1c935f41cd3a..5483fd39ef29 100644 --- a/Documentation/dev-tools/kmemleak.rst +++ b/Documentation/dev-tools/kmemleak.rst @@ -174,7 +174,6 @@ mapping: - ``kmemleak_alloc_phys`` - ``kmemleak_free_part_phys`` -- ``kmemleak_not_leak_phys`` - ``kmemleak_ignore_phys`` Dealing with false positives/negatives diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 1bc91fb8c321..e7aafc82be99 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -448,6 +448,7 @@ Memory Area, or VMA) there is a series of lines such as the following:: MMUPageSize: 4 kB Rss: 892 kB Pss: 374 kB + Pss_Dirty: 0 kB Shared_Clean: 892 kB Shared_Dirty: 0 kB Private_Clean: 0 kB @@ -479,7 +480,9 @@ dirty shared and private pages in the mapping. The "proportional set size" (PSS) of a process is the count of pages it has in memory, where each page is divided by the number of processes sharing it. So if a process has 1000 pages all to itself, and 1000 shared with one other -process, its PSS will be 1500. +process, its PSS will be 1500. "Pss_Dirty" is the portion of PSS which +consists of dirty pages. ("Pss_Clean" is not included, but it can be +calculated by subtracting "Pss_Dirty" from "Pss".) Note that even a page which is part of a MAP_SHARED mapping, but has only a single pte mapped, i.e. is currently used by only one process, is accounted @@ -514,8 +517,10 @@ replaced by copy-on-write) part of the underlying shmem object out on swap. "SwapPss" shows proportional swap share of this mapping. Unlike "Swap", this does not take into account swapped out page of underlying shmem objects. "Locked" indicates whether the mapping is locked in memory or not. + "THPeligible" indicates whether the mapping is eligible for allocating THP -pages - 1 if true, 0 otherwise. It just shows the current status. +pages as well as the THP is PMD mappable or not - 1 if true, 0 otherwise. +It just shows the current status. "VmFlags" field deserves a separate description. This member represents the kernel flags associated with the particular virtual memory area in two letter @@ -1109,7 +1114,7 @@ CommitLimit yield a CommitLimit of 7.3G. For more details, see the memory overcommit documentation - in vm/overcommit-accounting. + in mm/overcommit-accounting. Committed_AS The amount of memory presently allocated on the system. The committed memory is a sum of all of the memory which diff --git a/Documentation/index.rst b/Documentation/index.rst index 67036a05b771..4737c18c97ff 100644 --- a/Documentation/index.rst +++ b/Documentation/index.rst @@ -128,7 +128,7 @@ needed). sound/index crypto/index filesystems/index - vm/index + mm/index bpf/index usb/index PCI/index diff --git a/Documentation/vm/active_mm.rst b/Documentation/mm/active_mm.rst index 6f8269c284ed..6f8269c284ed 100644 --- a/Documentation/vm/active_mm.rst +++ b/Documentation/mm/active_mm.rst diff --git a/Documentation/vm/arch_pgtable_helpers.rst b/Documentation/mm/arch_pgtable_helpers.rst index cbaee9e59241..cbaee9e59241 100644 --- a/Documentation/vm/arch_pgtable_helpers.rst +++ b/Documentation/mm/arch_pgtable_helpers.rst diff --git a/Documentation/vm/balance.rst b/Documentation/mm/balance.rst index 6a1fadf3e173..6a1fadf3e173 100644 --- a/Documentation/vm/balance.rst +++ b/Documentation/mm/balance.rst diff --git a/Documentation/vm/bootmem.rst b/Documentation/mm/bootmem.rst index eb2b31eedfa1..eb2b31eedfa1 100644 --- a/Documentation/vm/bootmem.rst +++ b/Documentation/mm/bootmem.rst diff --git a/Documentation/vm/damon/api.rst b/Documentation/mm/damon/api.rst index 08f34df45523..08f34df45523 100644 --- a/Documentation/vm/damon/api.rst +++ b/Documentation/mm/damon/api.rst diff --git a/Documentation/vm/damon/design.rst b/Documentation/mm/damon/design.rst index 0cff6fac6b7e..0cff6fac6b7e 100644 --- a/Documentation/vm/damon/design.rst +++ b/Documentation/mm/damon/design.rst diff --git a/Documentation/vm/damon/faq.rst b/Documentation/mm/damon/faq.rst index dde7e2414ee6..dde7e2414ee6 100644 --- a/Documentation/vm/damon/faq.rst +++ b/Documentation/mm/damon/faq.rst diff --git a/Documentation/vm/damon/index.rst b/Documentation/mm/damon/index.rst index 48c0bbff98b2..48c0bbff98b2 100644 --- a/Documentation/vm/damon/index.rst +++ b/Documentation/mm/damon/index.rst diff --git a/Documentation/vm/free_page_reporting.rst b/Documentation/mm/free_page_reporting.rst index 8c05e62d8b2b..8c05e62d8b2b 100644 --- a/Documentation/vm/free_page_reporting.rst +++ b/Documentation/mm/free_page_reporting.rst diff --git a/Documentation/vm/frontswap.rst b/Documentation/mm/frontswap.rst index feecc5e24477..feecc5e24477 100644 --- a/Documentation/vm/frontswap.rst +++ b/Documentation/mm/frontswap.rst diff --git a/Documentation/vm/highmem.rst b/Documentation/mm/highmem.rst index c9887f241c6c..c9887f241c6c 100644 --- a/Documentation/vm/highmem.rst +++ b/Documentation/mm/highmem.rst diff --git a/Documentation/vm/hmm.rst b/Documentation/mm/hmm.rst index f2a59ed82ed3..f2a59ed82ed3 100644 --- a/Documentation/vm/hmm.rst +++ b/Documentation/mm/hmm.rst diff --git a/Documentation/vm/hugetlbfs_reserv.rst b/Documentation/mm/hugetlbfs_reserv.rst index f143954e0d05..f143954e0d05 100644 --- a/Documentation/vm/hugetlbfs_reserv.rst +++ b/Documentation/mm/hugetlbfs_reserv.rst diff --git a/Documentation/vm/hwpoison.rst b/Documentation/mm/hwpoison.rst index b9d5253c1305..b9d5253c1305 100644 --- a/Documentation/vm/hwpoison.rst +++ b/Documentation/mm/hwpoison.rst diff --git a/Documentation/vm/index.rst b/Documentation/mm/index.rst index 575ccd40e30c..575ccd40e30c 100644 --- a/Documentation/vm/index.rst +++ b/Documentation/mm/index.rst diff --git a/Documentation/vm/ksm.rst b/Documentation/mm/ksm.rst index 9e37add068e6..9e37add068e6 100644 --- a/Documentation/vm/ksm.rst +++ b/Documentation/mm/ksm.rst diff --git a/Documentation/vm/memory-model.rst b/Documentation/mm/memory-model.rst index 30e8fbed6914..3779e562dc76 100644 --- a/Documentation/vm/memory-model.rst +++ b/Documentation/mm/memory-model.rst @@ -170,7 +170,7 @@ The users of `ZONE_DEVICE` are: * hmm: Extend `ZONE_DEVICE` with `->page_fault()` and `->page_free()` event callbacks to allow a device-driver to coordinate memory management events related to device-memory, typically GPU memory. See - Documentation/vm/hmm.rst. + Documentation/mm/hmm.rst. * p2pdma: Create `struct page` objects to allow peer devices in a PCI/-E topology to coordinate direct-DMA operations between themselves, diff --git a/Documentation/vm/mmu_notifier.rst b/Documentation/mm/mmu_notifier.rst index df5d7777fc6b..df5d7777fc6b 100644 --- a/Documentation/vm/mmu_notifier.rst +++ b/Documentation/mm/mmu_notifier.rst diff --git a/Documentation/vm/numa.rst b/Documentation/mm/numa.rst index 99fdeca917ca..99fdeca917ca 100644 --- a/Documentation/vm/numa.rst +++ b/Documentation/mm/numa.rst diff --git a/Documentation/vm/oom.rst b/Documentation/mm/oom.rst index 18e9e40c1ec1..18e9e40c1ec1 100644 --- a/Documentation/vm/oom.rst +++ b/Documentation/mm/oom.rst diff --git a/Documentation/vm/overcommit-accounting.rst b/Documentation/mm/overcommit-accounting.rst index a4895d6fc1c2..a4895d6fc1c2 100644 --- a/Documentation/vm/overcommit-accounting.rst +++ b/Documentation/mm/overcommit-accounting.rst diff --git a/Documentation/vm/page_allocation.rst b/Documentation/mm/page_allocation.rst index d9b4495561f1..d9b4495561f1 100644 --- a/Documentation/vm/page_allocation.rst +++ b/Documentation/mm/page_allocation.rst diff --git a/Documentation/vm/page_cache.rst b/Documentation/mm/page_cache.rst index 75eba7c431b2..75eba7c431b2 100644 --- a/Documentation/vm/page_cache.rst +++ b/Documentation/mm/page_cache.rst diff --git a/Documentation/vm/page_frags.rst b/Documentation/mm/page_frags.rst index 7d6f9385d129..7d6f9385d129 100644 --- a/Documentation/vm/page_frags.rst +++ b/Documentation/mm/page_frags.rst diff --git a/Documentation/vm/page_migration.rst b/Documentation/mm/page_migration.rst index 11493bad7112..11493bad7112 100644 --- a/Documentation/vm/page_migration.rst +++ b/Documentation/mm/page_migration.rst diff --git a/Documentation/vm/page_owner.rst b/Documentation/mm/page_owner.rst index f5c954afe97c..f5c954afe97c 100644 --- a/Documentation/vm/page_owner.rst +++ b/Documentation/mm/page_owner.rst diff --git a/Documentation/vm/page_reclaim.rst b/Documentation/mm/page_reclaim.rst index 50a30b7f8ac3..50a30b7f8ac3 100644 --- a/Documentation/vm/page_reclaim.rst +++ b/Documentation/mm/page_reclaim.rst diff --git a/Documentation/vm/page_table_check.rst b/Documentation/mm/page_table_check.rst index 1a09472f10a3..1a09472f10a3 100644 --- a/Documentation/vm/page_table_check.rst +++ b/Documentation/mm/page_table_check.rst diff --git a/Documentation/vm/page_tables.rst b/Documentation/mm/page_tables.rst index 96939571d7bc..96939571d7bc 100644 --- a/Documentation/vm/page_tables.rst +++ b/Documentation/mm/page_tables.rst diff --git a/Documentation/vm/physical_memory.rst b/Documentation/mm/physical_memory.rst index 2ab7b8c1c863..2ab7b8c1c863 100644 --- a/Documentation/vm/physical_memory.rst +++ b/Documentation/mm/physical_memory.rst diff --git a/Documentation/vm/process_addrs.rst b/Documentation/mm/process_addrs.rst index e8618fbc62c9..e8618fbc62c9 100644 --- a/Documentation/vm/process_addrs.rst +++ b/Documentation/mm/process_addrs.rst diff --git a/Documentation/vm/remap_file_pages.rst b/Documentation/mm/remap_file_pages.rst index 7bef6718e3a9..7bef6718e3a9 100644 --- a/Documentation/vm/remap_file_pages.rst +++ b/Documentation/mm/remap_file_pages.rst diff --git a/Documentation/vm/shmfs.rst b/Documentation/mm/shmfs.rst index 8b01ebb4c30e..8b01ebb4c30e 100644 --- a/Documentation/vm/shmfs.rst +++ b/Documentation/mm/shmfs.rst diff --git a/Documentation/vm/slab.rst b/Documentation/mm/slab.rst index 87d5a5bb172f..87d5a5bb172f 100644 --- a/Documentation/vm/slab.rst +++ b/Documentation/mm/slab.rst diff --git a/Documentation/vm/slub.rst b/Documentation/mm/slub.rst index 43063ade737a..43063ade737a 100644 --- a/Documentation/vm/slub.rst +++ b/Documentation/mm/slub.rst diff --git a/Documentation/vm/split_page_table_lock.rst b/Documentation/mm/split_page_table_lock.rst index c08919662704..c08919662704 100644 --- a/Documentation/vm/split_page_table_lock.rst +++ b/Documentation/mm/split_page_table_lock.rst diff --git a/Documentation/vm/swap.rst b/Documentation/mm/swap.rst index 78819bd4d745..78819bd4d745 100644 --- a/Documentation/vm/swap.rst +++ b/Documentation/mm/swap.rst diff --git a/Documentation/vm/transhuge.rst b/Documentation/mm/transhuge.rst index 216db1d67d04..216db1d67d04 100644 --- a/Documentation/vm/transhuge.rst +++ b/Documentation/mm/transhuge.rst diff --git a/Documentation/vm/unevictable-lru.rst b/Documentation/mm/unevictable-lru.rst index b280367d6a44..b280367d6a44 100644 --- a/Documentation/vm/unevictable-lru.rst +++ b/Documentation/mm/unevictable-lru.rst diff --git a/Documentation/vm/vmalloc.rst b/Documentation/mm/vmalloc.rst index 363fe20d6b9f..363fe20d6b9f 100644 --- a/Documentation/vm/vmalloc.rst +++ b/Documentation/mm/vmalloc.rst diff --git a/Documentation/vm/vmalloced-kernel-stacks.rst b/Documentation/mm/vmalloced-kernel-stacks.rst index fc8c67833af6..fc8c67833af6 100644 --- a/Documentation/vm/vmalloced-kernel-stacks.rst +++ b/Documentation/mm/vmalloced-kernel-stacks.rst diff --git a/Documentation/vm/vmemmap_dedup.rst b/Documentation/mm/vmemmap_dedup.rst index c9c495f62d12..c9c495f62d12 100644 --- a/Documentation/vm/vmemmap_dedup.rst +++ b/Documentation/mm/vmemmap_dedup.rst diff --git a/Documentation/vm/z3fold.rst b/Documentation/mm/z3fold.rst index 224e3c61d686..224e3c61d686 100644 --- a/Documentation/vm/z3fold.rst +++ b/Documentation/mm/z3fold.rst diff --git a/Documentation/vm/zsmalloc.rst b/Documentation/mm/zsmalloc.rst index 6e79893d6132..6e79893d6132 100644 --- a/Documentation/vm/zsmalloc.rst +++ b/Documentation/mm/zsmalloc.rst diff --git a/Documentation/translations/zh_CN/admin-guide/mm/damon/index.rst b/Documentation/translations/zh_CN/admin-guide/mm/damon/index.rst index 0c8276109fc0..30c69e1f44fe 100644 --- a/Documentation/translations/zh_CN/admin-guide/mm/damon/index.rst +++ b/Documentation/translations/zh_CN/admin-guide/mm/damon/index.rst @@ -13,7 +13,7 @@ 监测数æ®è®¿é—® ============ -:doc:`DAMON </vm/damon/index>` å…许轻é‡çº§çš„æ•°æ®è®¿é—®ç›‘测。使用DAMON， +:doc:`DAMON </mm/damon/index>` å…许轻é‡çº§çš„æ•°æ®è®¿é—®ç›‘测。使用DAMON， 用户å¯ä»¥åˆ†æžä»–们系统的内å˜è®¿é—®æ¨¡å¼ï¼Œå¹¶ä¼˜åŒ–它们。 .. toctree:: diff --git a/Documentation/translations/zh_CN/admin-guide/mm/damon/reclaim.rst b/Documentation/translations/zh_CN/admin-guide/mm/damon/reclaim.rst index 1500bdbf338a..c976f3e33ffd 100644 --- a/Documentation/translations/zh_CN/admin-guide/mm/damon/reclaim.rst +++ b/Documentation/translations/zh_CN/admin-guide/mm/damon/reclaim.rst @@ -229,4 +229,4 @@ DAMON_RECLAIMå†æ¬¡ä»€ä¹ˆéƒ½ä¸åšï¼Œè¿™æ ·æˆ‘们就å¯ä»¥é€€å›žåˆ°åŸºäºŽLRU列è .. [1] https://research.google/pubs/pub48551/ .. [2] https://lwn.net/Articles/787611/ -.. [3] https://www.kernel.org/doc/html/latest/vm/free_page_reporting.html +.. [3] https://www.kernel.org/doc/html/latest/mm/free_page_reporting.html diff --git a/Documentation/translations/zh_CN/admin-guide/mm/damon/usage.rst b/Documentation/translations/zh_CN/admin-guide/mm/damon/usage.rst index 2c7d9106e399..aeae2ab65dd8 100644 --- a/Documentation/translations/zh_CN/admin-guide/mm/damon/usage.rst +++ b/Documentation/translations/zh_CN/admin-guide/mm/damon/usage.rst @@ -33,9 +33,9 @@ DAMON 为ä¸åŒçš„用户æ供了下é¢è¿™äº›æŽ¥å£ã€‚ å£ç›¸åŒã€‚这将在下一个LTSå†…æ ¸å‘布åŽè¢«ç§»é™¤ï¼Œæ‰€ä»¥ç”¨æˆ·åº”该转移到 :ref:`sysfs interface <sysfs_interface>`。 - *å†…æ ¸ç©ºé—´ç¼–ç¨‹æŽ¥å£ã€‚* - :doc:`è¿™ </vm/damon/api>` è¿™æ˜¯ä¸ºå†…æ ¸ç©ºé—´ç¨‹åºå‘˜å‡†å¤‡çš„。使用它，用户å¯ä»¥é€šè¿‡ä¸ºä½ 编写内 + :doc:`è¿™ </mm/damon/api>` è¿™æ˜¯ä¸ºå†…æ ¸ç©ºé—´ç¨‹åºå‘˜å‡†å¤‡çš„。使用它，用户å¯ä»¥é€šè¿‡ä¸ºä½ 编写内 æ ¸ç©ºé—´çš„DAMON应用程åºï¼Œæœ€çµæ´»æœ‰æ•ˆåœ°åˆ©ç”¨DAMONçš„æ¯ä¸€ä¸ªåŠŸèƒ½ã€‚ä½ ç”šè‡³å¯ä»¥ä¸ºå„ç§åœ°å€ç©ºé—´æ‰©å±•DAMON。 - 详细情况请å‚è€ƒæŽ¥å£ :doc:`文件 </vm/damon/api>`。 + 详细情况请å‚è€ƒæŽ¥å£ :doc:`文件 </mm/damon/api>`。 sysfsæŽ¥å£ ========= @@ -148,7 +148,7 @@ contexts/<N>/monitoring_attrs/ 在 ``nr_regions`` 目录下，有两个文件分别用于DAMON监测区域的下é™å’Œä¸Šé™ï¼ˆ``min`` å’Œ ``max`` ）， 这两个文件控制ç€ç›‘æµ‹çš„å¼€é”€ã€‚ä½ å¯ä»¥é€šè¿‡å‘这些文件的写入和读出æ¥è®¾ç½®å’ŒèŽ·å–这些值。 -关于间隔和监测区域范围的更多细节，请å‚考设计文件 (:doc:`/vm/damon/design`)。 +关于间隔和监测区域范围的更多细节，请å‚考设计文件 (:doc:`/mm/damon/design`)。 contexts/<N>/targets/ --------------------- @@ -320,7 +320,7 @@ DAMON导出了八个文件, ``attrs``, ``target_ids``, ``init_regions``, ---- 用户å¯ä»¥é€šè¿‡è¯»å–和写入 ``attrs`` 文件获得和设置 ``é‡‡æ ·é—´éš”`` 〠``èšé›†é—´éš”`` 〠``æ›´æ–°é—´éš”`` -以åŠç›‘æµ‹ç›®æ ‡åŒºåŸŸçš„æœ€å°/最大数é‡ã€‚è¦è¯¦ç»†äº†è§£ç›‘测属性，请å‚考 `:doc:/vm/damon/design` 。例如， +以åŠç›‘æµ‹ç›®æ ‡åŒºåŸŸçš„æœ€å°/最大数é‡ã€‚è¦è¯¦ç»†äº†è§£ç›‘测属性，请å‚考 `:doc:/mm/damon/design` 。例如， 下é¢çš„命令将这些值设置为5msã€100msã€1000msã€10å’Œ1000，然åŽå†æ¬¡æ£€æŸ¥:: # cd <debugfs>/damon diff --git a/Documentation/translations/zh_CN/core-api/index.rst b/Documentation/translations/zh_CN/core-api/index.rst index 10bc438504ac..8a94ad87465d 100644 --- a/Documentation/translations/zh_CN/core-api/index.rst +++ b/Documentation/translations/zh_CN/core-api/index.rst @@ -101,7 +101,7 @@ Todolist: ======== å¦‚ä½•åœ¨å†…æ ¸ä¸åˆ†é…和使用内å˜ã€‚请注æ„，在 -:doc:`/vm/index` ä¸æœ‰æ›´å¤šçš„内å˜ç®¡ç†æ–‡æ¡£ã€‚ +:doc:`/mm/index` ä¸æœ‰æ›´å¤šçš„内å˜ç®¡ç†æ–‡æ¡£ã€‚ .. toctree:: :maxdepth: 1 diff --git a/Documentation/translations/zh_CN/index.rst b/Documentation/translations/zh_CN/index.rst index ad7bb8c17562..bf85baca8b3e 100644 --- a/Documentation/translations/zh_CN/index.rst +++ b/Documentation/translations/zh_CN/index.rst @@ -118,7 +118,7 @@ TODOList: sound/index filesystems/index scheduler/index - vm/index + mm/index peci/index TODOList: diff --git a/Documentation/translations/zh_CN/vm/active_mm.rst b/Documentation/translations/zh_CN/mm/active_mm.rst index 366609ea4f37..c2816f523bd7 100644 --- a/Documentation/translations/zh_CN/vm/active_mm.rst +++ b/Documentation/translations/zh_CN/mm/active_mm.rst @@ -1,6 +1,6 @@ .. include:: ../disclaimer-zh_CN.rst -:Original: Documentation/vm/active_mm.rst +:Original: Documentation/mm/active_mm.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/balance.rst b/Documentation/translations/zh_CN/mm/balance.rst index e98a47ef24a8..6fd79209c307 100644 --- a/Documentation/translations/zh_CN/vm/balance.rst +++ b/Documentation/translations/zh_CN/mm/balance.rst @@ -1,6 +1,6 @@ .. include:: ../disclaimer-zh_CN.rst -:Original: Documentation/vm/balance.rst +:Original: Documentation/mm/balance.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/damon/api.rst b/Documentation/translations/zh_CN/mm/damon/api.rst index 21143eea4ebe..5593a83c86bc 100644 --- a/Documentation/translations/zh_CN/vm/damon/api.rst +++ b/Documentation/translations/zh_CN/mm/damon/api.rst @@ -1,6 +1,6 @@ .. SPDX-License-Identifier: GPL-2.0 -:Original: Documentation/vm/damon/api.rst +:Original: Documentation/mm/damon/api.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/damon/design.rst b/Documentation/translations/zh_CN/mm/damon/design.rst index 46128b77c2b3..16e3db34a7dd 100644 --- a/Documentation/translations/zh_CN/vm/damon/design.rst +++ b/Documentation/translations/zh_CN/mm/damon/design.rst @@ -1,6 +1,6 @@ .. SPDX-License-Identifier: GPL-2.0 -:Original: Documentation/vm/damon/design.rst +:Original: Documentation/mm/damon/design.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/damon/faq.rst b/Documentation/translations/zh_CN/mm/damon/faq.rst index 07b4ac19407d..de4be417494a 100644 --- a/Documentation/translations/zh_CN/vm/damon/faq.rst +++ b/Documentation/translations/zh_CN/mm/damon/faq.rst @@ -1,6 +1,6 @@ .. SPDX-License-Identifier: GPL-2.0 -:Original: Documentation/vm/damon/faq.rst +:Original: Documentation/mm/damon/faq.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/damon/index.rst b/Documentation/translations/zh_CN/mm/damon/index.rst index 84d36d90c9b0..b03bf307204f 100644 --- a/Documentation/translations/zh_CN/vm/damon/index.rst +++ b/Documentation/translations/zh_CN/mm/damon/index.rst @@ -1,6 +1,6 @@ .. SPDX-License-Identifier: GPL-2.0 -:Original: Documentation/vm/damon/index.rst +:Original: Documentation/mm/damon/index.rst :翻译: @@ -14,7 +14,7 @@ DAMON:æ•°æ®è®¿é—®ç›‘视器 ========================== DAMON是Linuxå†…æ ¸çš„ä¸€ä¸ªæ•°æ®è®¿é—®ç›‘控框架å系统。DAMONçš„æ ¸å¿ƒæœºåˆ¶ä½¿å…¶æˆä¸º -ï¼ˆè¯¥æ ¸å¿ƒæœºåˆ¶è¯¦è§(Documentation/translations/zh_CN/vm/damon/design.rst)） +ï¼ˆè¯¥æ ¸å¿ƒæœºåˆ¶è¯¦è§(Documentation/translations/zh_CN/mm/damon/design.rst)） - *准确度* （监测输出对DRAM级别的内å˜ç®¡ç†è¶³å¤Ÿæœ‰ç”¨ï¼›ä½†å¯èƒ½ä¸é€‚åˆCPU Cache级别）， - *è½»é‡çº§* （监控开销低到å¯ä»¥åœ¨çº¿åº”ç”¨ï¼‰ï¼Œä»¥åŠ @@ -30,4 +30,3 @@ DAMON是Linuxå†…æ ¸çš„ä¸€ä¸ªæ•°æ®è®¿é—®ç›‘控框架å系统。DAMONçš„æ ¸å¿ƒæœ faq design api - diff --git a/Documentation/translations/zh_CN/vm/free_page_reporting.rst b/Documentation/translations/zh_CN/mm/free_page_reporting.rst index 14336a3aa5f4..5bfd58014c94 100644 --- a/Documentation/translations/zh_CN/vm/free_page_reporting.rst +++ b/Documentation/translations/zh_CN/mm/free_page_reporting.rst @@ -1,6 +1,6 @@ .. include:: ../disclaimer-zh_CN.rst -:Original: Documentation/vm/free_page_reporting.rst +:Original: Documentation/mm/free_page_reporting.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/frontswap.rst b/Documentation/translations/zh_CN/mm/frontswap.rst index 98aa6f581ea7..434975390b48 100644 --- a/Documentation/translations/zh_CN/vm/frontswap.rst +++ b/Documentation/translations/zh_CN/mm/frontswap.rst @@ -1,4 +1,4 @@ -:Original: Documentation/vm/free_page_reporting.rst +:Original: Documentation/mm/frontswap.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/highmem.rst b/Documentation/translations/zh_CN/mm/highmem.rst index 200321774646..f74800a6d9a7 100644 --- a/Documentation/translations/zh_CN/vm/highmem.rst +++ b/Documentation/translations/zh_CN/mm/highmem.rst @@ -1,6 +1,6 @@ .. include:: ../disclaimer-zh_CN.rst -:Original: Documentation/vm/highmem.rst +:Original: Documentation/mm/highmem.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/hmm.rst b/Documentation/translations/zh_CN/mm/hmm.rst index 2379df95aa58..5024a8a15516 100644 --- a/Documentation/translations/zh_CN/vm/hmm.rst +++ b/Documentation/translations/zh_CN/mm/hmm.rst @@ -1,6 +1,6 @@ .. include:: ../disclaimer-zh_CN.rst -:Original: Documentation/vm/hmm.rst +:Original: Documentation/mm/hmm.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/hugetlbfs_reserv.rst b/Documentation/translations/zh_CN/mm/hugetlbfs_reserv.rst index c6d471ce2131..752e5696cd47 100644 --- a/Documentation/translations/zh_CN/vm/hugetlbfs_reserv.rst +++ b/Documentation/translations/zh_CN/mm/hugetlbfs_reserv.rst @@ -1,6 +1,6 @@ .. include:: ../disclaimer-zh_CN.rst -:Original: Documentation/vm/hugetlbfs_reserv.rst +:Original: Documentation/mm/hugetlbfs_reserv.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/hwpoison.rst b/Documentation/translations/zh_CN/mm/hwpoison.rst index c6e1e7bdb05b..310862edc937 100644 --- a/Documentation/translations/zh_CN/vm/hwpoison.rst +++ b/Documentation/translations/zh_CN/mm/hwpoison.rst @@ -1,5 +1,5 @@ -:Original: Documentation/vm/hwpoison.rst +:Original: Documentation/mm/hwpoison.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/index.rst b/Documentation/translations/zh_CN/mm/index.rst index c77a56553845..2f53e37b8049 100644 --- a/Documentation/translations/zh_CN/vm/index.rst +++ b/Documentation/translations/zh_CN/mm/index.rst @@ -1,6 +1,6 @@ .. include:: ../disclaimer-zh_CN.rst -:Original: Documentation/vm/index.rst +:Original: Documentation/mm/index.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/ksm.rst b/Documentation/translations/zh_CN/mm/ksm.rst index 83b0c73984da..d1f82e857ad7 100644 --- a/Documentation/translations/zh_CN/vm/ksm.rst +++ b/Documentation/translations/zh_CN/mm/ksm.rst @@ -1,6 +1,6 @@ .. include:: ../disclaimer-zh_CN.rst -:Original: Documentation/vm/ksm.rst +:Original: Documentation/mm/ksm.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/memory-model.rst b/Documentation/translations/zh_CN/mm/memory-model.rst index 013e30c88d72..77ec149a970c 100644 --- a/Documentation/translations/zh_CN/vm/memory-model.rst +++ b/Documentation/translations/zh_CN/mm/memory-model.rst @@ -1,6 +1,6 @@ .. SPDX-License-Identifier: GPL-2.0 -:Original: Documentation/vm/memory-model.rst +:Original: Documentation/mm/memory-model.rst :翻译: @@ -129,7 +129,7 @@ ZONE_DEVICE * pmem: 通过DAXæ˜ å°„å°†å¹³å°æŒä¹…性内å˜ä½œä¸ºç›´æŽ¥I/Oç›®æ ‡ä½¿ç”¨ã€‚ * hmm: 用 `->page_fault()` å’Œ `->page_free()` 事件回调扩展 `ZONE_DEVICE` ， - 以å…许设备驱动程åºå调与设备内å˜ç›¸å…³çš„内å˜ç®¡ç†äº‹ä»¶ï¼Œé€šå¸¸æ˜¯GPU内å˜ã€‚å‚è§/vm/hmm.rst。 + 以å…许设备驱动程åºå调与设备内å˜ç›¸å…³çš„内å˜ç®¡ç†äº‹ä»¶ï¼Œé€šå¸¸æ˜¯GPU内å˜ã€‚å‚è§Documentation/mm/hmm.rst。 * p2pdma: 创建 `struct page` 对象，å…许PCI/E拓扑结构ä¸çš„peer设备å调它们之间的 直接DMAæ“作，å³ç»•è¿‡ä¸»æœºå†…å˜ã€‚ diff --git a/Documentation/translations/zh_CN/vm/mmu_notifier.rst b/Documentation/translations/zh_CN/mm/mmu_notifier.rst index b29a37b33628..ce3664d1a410 100644 --- a/Documentation/translations/zh_CN/vm/mmu_notifier.rst +++ b/Documentation/translations/zh_CN/mm/mmu_notifier.rst @@ -1,4 +1,4 @@ -:Original: Documentation/vm/mmu_notifier.rst +:Original: Documentation/mm/mmu_notifier.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/numa.rst b/Documentation/translations/zh_CN/mm/numa.rst index 6af412b924ad..b15cfeeb6dfb 100644 --- a/Documentation/translations/zh_CN/vm/numa.rst +++ b/Documentation/translations/zh_CN/mm/numa.rst @@ -1,4 +1,4 @@ -:Original: Documentation/vm/numa.rst +:Original: Documentation/mm/numa.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/overcommit-accounting.rst b/Documentation/translations/zh_CN/mm/overcommit-accounting.rst index 8765cb118f24..d8452d8b7fbb 100644 --- a/Documentation/translations/zh_CN/vm/overcommit-accounting.rst +++ b/Documentation/translations/zh_CN/mm/overcommit-accounting.rst @@ -1,4 +1,4 @@ -:Original: Documentation/vm/overcommit-accounting.rst +:Original: Documentation/mm/overcommit-accounting.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/page_frags.rst b/Documentation/translations/zh_CN/mm/page_frags.rst index 38ecddb9e1c0..20bd3fafdc8c 100644 --- a/Documentation/translations/zh_CN/vm/page_frags.rst +++ b/Documentation/translations/zh_CN/mm/page_frags.rst @@ -1,4 +1,4 @@ -:Original: Documentation/vm/page_frags.rst +:Original: Documentation/mm/page_frags.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/page_migration.rst b/Documentation/translations/zh_CN/mm/page_migration.rst index 566880a41ea0..076081dc1635 100644 --- a/Documentation/translations/zh_CN/vm/page_migration.rst +++ b/Documentation/translations/zh_CN/mm/page_migration.rst @@ -1,6 +1,6 @@ .. include:: ../disclaimer-zh_CN.rst -:Original: Documentation/vm/index.rst +:Original: Documentation/mm/page_migration.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/page_owner.rst b/Documentation/translations/zh_CN/mm/page_owner.rst index 7bd740bc5bf4..b7f81d7a6589 100644 --- a/Documentation/translations/zh_CN/vm/page_owner.rst +++ b/Documentation/translations/zh_CN/mm/page_owner.rst @@ -1,4 +1,4 @@ -:Original: Documentation/vm/page_owner.rst +:Original: Documentation/mm/page_owner.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/page_table_check.rst b/Documentation/translations/zh_CN/mm/page_table_check.rst index a29fc1b360e6..e8077310a76c 100644 --- a/Documentation/translations/zh_CN/vm/page_table_check.rst +++ b/Documentation/translations/zh_CN/mm/page_table_check.rst @@ -1,6 +1,6 @@ .. SPDX-License-Identifier: GPL-2.0 -:Original: Documentation/vm/page_table_check.rst +:Original: Documentation/mm/page_table_check.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/remap_file_pages.rst b/Documentation/translations/zh_CN/mm/remap_file_pages.rst index af6b7e28af23..31e0c54dc36f 100644 --- a/Documentation/translations/zh_CN/vm/remap_file_pages.rst +++ b/Documentation/translations/zh_CN/mm/remap_file_pages.rst @@ -1,4 +1,4 @@ -:Original: Documentation/vm/remap_file_pages.rst +:Original: Documentation/mm/remap_file_pages.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/split_page_table_lock.rst b/Documentation/translations/zh_CN/mm/split_page_table_lock.rst index 50694d97c426..4fb7aa666037 100644 --- a/Documentation/translations/zh_CN/vm/split_page_table_lock.rst +++ b/Documentation/translations/zh_CN/mm/split_page_table_lock.rst @@ -1,4 +1,4 @@ -:Original: Documentation/vm/split_page_table_lock.rst +:Original: Documentation/mm/split_page_table_lock.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/vmalloced-kernel-stacks.rst b/Documentation/translations/zh_CN/mm/vmalloced-kernel-stacks.rst index ad23f274f6d7..d02a23f7f07e 100644 --- a/Documentation/translations/zh_CN/vm/vmalloced-kernel-stacks.rst +++ b/Documentation/translations/zh_CN/mm/vmalloced-kernel-stacks.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 .. include:: ../disclaimer-zh_CN.rst -:Original: Documentation/vm/vmalloced-kernel-stacks.rst +:Original: Documentation/mm/vmalloced-kernel-stacks.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/z3fold.rst b/Documentation/translations/zh_CN/mm/z3fold.rst index 57204aa08caa..9569a6d88270 100644 --- a/Documentation/translations/zh_CN/vm/z3fold.rst +++ b/Documentation/translations/zh_CN/mm/z3fold.rst @@ -1,4 +1,4 @@ -:Original: Documentation/vm/z3fold.rst +:Original: Documentation/mm/z3fold.rst :翻译: diff --git a/Documentation/translations/zh_CN/vm/zsmalloc.rst b/Documentation/translations/zh_CN/mm/zsmalloc.rst index 45a9b7ab2a51..4c8c9b1006a9 100644 --- a/Documentation/translations/zh_CN/vm/zsmalloc.rst +++ b/Documentation/translations/zh_CN/mm/zsmalloc.rst @@ -1,4 +1,4 @@ -:Original: Documentation/vm/zsmalloc.rst +:Original: Documentation/mm/zsmalloc.rst :翻译: diff --git a/Documentation/translations/zh_TW/index.rst b/Documentation/translations/zh_TW/index.rst index e1ce9d8c06f8..e97d7d578751 100644 --- a/Documentation/translations/zh_TW/index.rst +++ b/Documentation/translations/zh_TW/index.rst @@ -128,7 +128,7 @@ TODOList: * security/index * sound/index * crypto/index -* vm/index +* mm/index * bpf/index * usb/index * PCI/index diff --git a/Documentation/vm/.gitignore b/Documentation/vm/.gitignore deleted file mode 100644 index bc74f5643008..000000000000 --- a/Documentation/vm/.gitignore +++ /dev/null @@ -1,3 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -page-types -slabinfo diff --git a/MAINTAINERS b/MAINTAINERS index b995141d251f..f692bd93d6d0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5668,7 +5668,7 @@ L: linux-mm@kvack.org S: Maintained F: Documentation/ABI/testing/sysfs-kernel-mm-damon F: Documentation/admin-guide/mm/damon/ -F: Documentation/vm/damon/ +F: Documentation/mm/damon/ F: include/linux/damon.h F: include/trace/events/damon.h F: mm/damon/ @@ -9252,7 +9252,7 @@ HMM - Heterogeneous Memory Management M: Jérôme Glisse <jglisse@redhat.com> L: linux-mm@kvack.org S: Maintained -F: Documentation/vm/hmm.rst +F: Documentation/mm/hmm.rst F: include/linux/hmm* F: lib/test_hmm* F: mm/hmm* @@ -9350,8 +9350,8 @@ L: linux-mm@kvack.org S: Maintained F: Documentation/ABI/testing/sysfs-kernel-mm-hugepages F: Documentation/admin-guide/mm/hugetlbpage.rst -F: Documentation/vm/hugetlbfs_reserv.rst -F: Documentation/vm/vmemmap_dedup.rst +F: Documentation/mm/hugetlbfs_reserv.rst +F: Documentation/mm/vmemmap_dedup.rst F: fs/hugetlbfs/ F: include/linux/hugetlb.h F: mm/hugetlb.c @@ -15338,7 +15338,7 @@ M: Pasha Tatashin <pasha.tatashin@soleen.com> M: Andrew Morton <akpm@linux-foundation.org> L: linux-mm@kvack.org S: Maintained -F: Documentation/vm/page_table_check.rst +F: Documentation/mm/page_table_check.rst F: include/linux/page_table_check.h F: mm/page_table_check.c @@ -22480,7 +22480,7 @@ M: Nitin Gupta <ngupta@vflare.org> R: Sergey Senozhatsky <senozhatsky@chromium.org> L: linux-mm@kvack.org S: Maintained -F: Documentation/vm/zsmalloc.rst +F: Documentation/mm/zsmalloc.rst F: include/linux/zsmalloc.h F: mm/zsmalloc.c diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h index 170451fde043..3ea9661c09ff 100644 --- a/arch/alpha/include/asm/pgtable.h +++ b/arch/alpha/include/asm/pgtable.h @@ -116,23 +116,6 @@ struct vm_area_struct; * arch/alpha/mm/fault.c) */ /* xwr */ -#define __P000 _PAGE_P(_PAGE_FOE | _PAGE_FOW | _PAGE_FOR) -#define __P001 _PAGE_P(_PAGE_FOE | _PAGE_FOW) -#define __P010 _PAGE_P(_PAGE_FOE) -#define __P011 _PAGE_P(_PAGE_FOE) -#define __P100 _PAGE_P(_PAGE_FOW | _PAGE_FOR) -#define __P101 _PAGE_P(_PAGE_FOW) -#define __P110 _PAGE_P(0) -#define __P111 _PAGE_P(0) - -#define __S000 _PAGE_S(_PAGE_FOE | _PAGE_FOW | _PAGE_FOR) -#define __S001 _PAGE_S(_PAGE_FOE | _PAGE_FOW) -#define __S010 _PAGE_S(_PAGE_FOE) -#define __S011 _PAGE_S(_PAGE_FOE) -#define __S100 _PAGE_S(_PAGE_FOW | _PAGE_FOR) -#define __S101 _PAGE_S(_PAGE_FOW) -#define __S110 _PAGE_S(0) -#define __S111 _PAGE_S(0) /* * pgprot_noncached() is only for infiniband pci support, and a real diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index ec20c1004abf..ef427a6bdd1a 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -155,6 +155,10 @@ retry: if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c index 7511723b7669..a155180d7a83 100644 --- a/arch/alpha/mm/init.c +++ b/arch/alpha/mm/init.c @@ -280,3 +280,25 @@ mem_init(void) high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); memblock_free_all(); } + +static const pgprot_t protection_map[16] = { + [VM_NONE] = _PAGE_P(_PAGE_FOE | _PAGE_FOW | + _PAGE_FOR), + [VM_READ] = _PAGE_P(_PAGE_FOE | _PAGE_FOW), + [VM_WRITE] = _PAGE_P(_PAGE_FOE), + [VM_WRITE | VM_READ] = _PAGE_P(_PAGE_FOE), + [VM_EXEC] = _PAGE_P(_PAGE_FOW | _PAGE_FOR), + [VM_EXEC | VM_READ] = _PAGE_P(_PAGE_FOW), + [VM_EXEC | VM_WRITE] = _PAGE_P(0), + [VM_EXEC | VM_WRITE | VM_READ] = _PAGE_P(0), + [VM_SHARED] = _PAGE_S(_PAGE_FOE | _PAGE_FOW | + _PAGE_FOR), + [VM_SHARED | VM_READ] = _PAGE_S(_PAGE_FOE | _PAGE_FOW), + [VM_SHARED | VM_WRITE] = _PAGE_S(_PAGE_FOE), + [VM_SHARED | VM_WRITE | VM_READ] = _PAGE_S(_PAGE_FOE), + [VM_SHARED | VM_EXEC] = _PAGE_S(_PAGE_FOW | _PAGE_FOR), + [VM_SHARED | VM_EXEC | VM_READ] = _PAGE_S(_PAGE_FOW), + [VM_SHARED | VM_EXEC | VM_WRITE] = _PAGE_S(0), + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = _PAGE_S(0) +}; +DECLARE_VM_GET_PAGE_PROT diff --git a/arch/arc/include/asm/pgtable-bits-arcv2.h b/arch/arc/include/asm/pgtable-bits-arcv2.h index 183d23bc1e00..b23be557403e 100644 --- a/arch/arc/include/asm/pgtable-bits-arcv2.h +++ b/arch/arc/include/asm/pgtable-bits-arcv2.h @@ -72,24 +72,6 @@ * This is to enable COW mechanism */ /* xwr */ -#define __P000 PAGE_U_NONE -#define __P001 PAGE_U_R -#define __P010 PAGE_U_R /* Pvt-W => !W */ -#define __P011 PAGE_U_R /* Pvt-W => !W */ -#define __P100 PAGE_U_X_R /* X => R */ -#define __P101 PAGE_U_X_R -#define __P110 PAGE_U_X_R /* Pvt-W => !W and X => R */ -#define __P111 PAGE_U_X_R /* Pvt-W => !W */ - -#define __S000 PAGE_U_NONE -#define __S001 PAGE_U_R -#define __S010 PAGE_U_W_R /* W => R */ -#define __S011 PAGE_U_W_R -#define __S100 PAGE_U_X_R /* X => R */ -#define __S101 PAGE_U_X_R -#define __S110 PAGE_U_X_W_R /* X => R */ -#define __S111 PAGE_U_X_W_R - #ifndef __ASSEMBLY__ #define pte_write(pte) (pte_val(pte) & _PAGE_WRITE) diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index dad27e4d69ff..5ca59a482632 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -146,6 +146,10 @@ retry: return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* * Fault retry nuances, mmap_lock already relinquished by core mm */ diff --git a/arch/arc/mm/mmap.c b/arch/arc/mm/mmap.c index 722d26b94307..fce5fa2b4f52 100644 --- a/arch/arc/mm/mmap.c +++ b/arch/arc/mm/mmap.c @@ -74,3 +74,23 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, info.align_offset = pgoff << PAGE_SHIFT; return vm_unmapped_area(&info); } + +static const pgprot_t protection_map[16] = { + [VM_NONE] = PAGE_U_NONE, + [VM_READ] = PAGE_U_R, + [VM_WRITE] = PAGE_U_R, + [VM_WRITE | VM_READ] = PAGE_U_R, + [VM_EXEC] = PAGE_U_X_R, + [VM_EXEC | VM_READ] = PAGE_U_X_R, + [VM_EXEC | VM_WRITE] = PAGE_U_X_R, + [VM_EXEC | VM_WRITE | VM_READ] = PAGE_U_X_R, + [VM_SHARED] = PAGE_U_NONE, + [VM_SHARED | VM_READ] = PAGE_U_R, + [VM_SHARED | VM_WRITE] = PAGE_U_W_R, + [VM_SHARED | VM_WRITE | VM_READ] = PAGE_U_W_R, + [VM_SHARED | VM_EXEC] = PAGE_U_X_R, + [VM_SHARED | VM_EXEC | VM_READ] = PAGE_U_X_R, + [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_U_X_W_R, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_U_X_W_R +}; +DECLARE_VM_GET_PAGE_PROT diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index cd1f84bb40ae..78a532068fec 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -137,23 +137,6 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, * 2) If we could do execute protection, then read is implied * 3) write implies read permissions */ -#define __P000 __PAGE_NONE -#define __P001 __PAGE_READONLY -#define __P010 __PAGE_COPY -#define __P011 __PAGE_COPY -#define __P100 __PAGE_READONLY_EXEC -#define __P101 __PAGE_READONLY_EXEC -#define __P110 __PAGE_COPY_EXEC -#define __P111 __PAGE_COPY_EXEC - -#define __S000 __PAGE_NONE -#define __S001 __PAGE_READONLY -#define __S010 __PAGE_SHARED -#define __S011 __PAGE_SHARED -#define __S100 __PAGE_READONLY_EXEC -#define __S101 __PAGE_READONLY_EXEC -#define __S110 __PAGE_SHARED_EXEC -#define __S111 __PAGE_SHARED_EXEC #ifndef __ASSEMBLY__ /* diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 500612d3da2e..29e2900178a1 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -38,10 +38,10 @@ #ifdef CONFIG_ARM_LPAE /* LPAE requires an additional page for the PGD */ #define PG_DIR_SIZE 0x5000 -#define PMD_ORDER 3 +#define PMD_ENTRY_ORDER 3 /* PMD entry size is 2^PMD_ENTRY_ORDER */ #else #define PG_DIR_SIZE 0x4000 -#define PMD_ORDER 2 +#define PMD_ENTRY_ORDER 2 #endif .globl swapper_pg_dir @@ -240,7 +240,7 @@ __create_page_tables: mov r6, r6, lsr #SECTION_SHIFT 1: orr r3, r7, r5, lsl #SECTION_SHIFT @ flags + kernel base - str r3, [r4, r5, lsl #PMD_ORDER] @ identity mapping + str r3, [r4, r5, lsl #PMD_ENTRY_ORDER] @ identity mapping cmp r5, r6 addlo r5, r5, #1 @ next section blo 1b @@ -250,7 +250,7 @@ __create_page_tables: * set two variables to indicate the physical start and end of the * kernel. */ - add r0, r4, #KERNEL_OFFSET >> (SECTION_SHIFT - PMD_ORDER) + add r0, r4, #KERNEL_OFFSET >> (SECTION_SHIFT - PMD_ENTRY_ORDER) ldr r6, =(_end - 1) adr_l r5, kernel_sec_start @ _pa(kernel_sec_start) #if defined CONFIG_CPU_ENDIAN_BE8 || defined CONFIG_CPU_ENDIAN_BE32 @@ -259,8 +259,8 @@ __create_page_tables: str r8, [r5] @ Save physical start of kernel (LE) #endif orr r3, r8, r7 @ Add the MMU flags - add r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER) -1: str r3, [r0], #1 << PMD_ORDER + add r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ENTRY_ORDER) +1: str r3, [r0], #1 << PMD_ENTRY_ORDER add r3, r3, #1 << SECTION_SHIFT cmp r0, r6 bls 1b @@ -280,14 +280,14 @@ __create_page_tables: mov r3, pc mov r3, r3, lsr #SECTION_SHIFT orr r3, r7, r3, lsl #SECTION_SHIFT - add r0, r4, #(XIP_START & 0xff000000) >> (SECTION_SHIFT - PMD_ORDER) - str r3, [r0, #((XIP_START & 0x00f00000) >> SECTION_SHIFT) << PMD_ORDER]! + add r0, r4, #(XIP_START & 0xff000000) >> (SECTION_SHIFT - PMD_ENTRY_ORDER) + str r3, [r0, #((XIP_START & 0x00f00000) >> SECTION_SHIFT) << PMD_ENTRY_ORDER]! ldr r6, =(_edata_loc - 1) - add r0, r0, #1 << PMD_ORDER - add r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER) + add r0, r0, #1 << PMD_ENTRY_ORDER + add r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ENTRY_ORDER) 1: cmp r0, r6 add r3, r3, #1 << SECTION_SHIFT - strls r3, [r0], #1 << PMD_ORDER + strls r3, [r0], #1 << PMD_ENTRY_ORDER bls 1b #endif @@ -297,10 +297,10 @@ __create_page_tables: */ mov r0, r2, lsr #SECTION_SHIFT cmp r2, #0 - ldrne r3, =FDT_FIXED_BASE >> (SECTION_SHIFT - PMD_ORDER) + ldrne r3, =FDT_FIXED_BASE >> (SECTION_SHIFT - PMD_ENTRY_ORDER) addne r3, r3, r4 orrne r6, r7, r0, lsl #SECTION_SHIFT - strne r6, [r3], #1 << PMD_ORDER + strne r6, [r3], #1 << PMD_ENTRY_ORDER addne r6, r6, #1 << SECTION_SHIFT strne r6, [r3] @@ -319,7 +319,7 @@ __create_page_tables: addruart r7, r3, r0 mov r3, r3, lsr #SECTION_SHIFT - mov r3, r3, lsl #PMD_ORDER + mov r3, r3, lsl #PMD_ENTRY_ORDER add r0, r4, r3 mov r3, r7, lsr #SECTION_SHIFT @@ -349,7 +349,7 @@ __create_page_tables: * If we're using the NetWinder or CATS, we also need to map * in the 16550-type serial port for the debug messages */ - add r0, r4, #0xff000000 >> (SECTION_SHIFT - PMD_ORDER) + add r0, r4, #0xff000000 >> (SECTION_SHIFT - PMD_ENTRY_ORDER) orr r3, r7, #0x7c000000 str r3, [r0] #endif @@ -359,10 +359,10 @@ __create_page_tables: * Similar reasons here - for debug. This is * only for Acorn RiscPC architectures. */ - add r0, r4, #0x02000000 >> (SECTION_SHIFT - PMD_ORDER) + add r0, r4, #0x02000000 >> (SECTION_SHIFT - PMD_ENTRY_ORDER) orr r3, r7, #0x02000000 str r3, [r0] - add r0, r4, #0xd8000000 >> (SECTION_SHIFT - PMD_ORDER) + add r0, r4, #0xd8000000 >> (SECTION_SHIFT - PMD_ENTRY_ORDER) str r3, [r0] #endif #endif diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c index c30b689bec2e..14eecaaf295f 100644 --- a/arch/arm/lib/uaccess_with_memcpy.c +++ b/arch/arm/lib/uaccess_with_memcpy.c @@ -237,7 +237,7 @@ static int __init test_size_treshold(void) if (!dst_page) goto no_dst; kernel_ptr = page_address(src_page); - user_ptr = vmap(&dst_page, 1, VM_IOREMAP, __pgprot(__P010)); + user_ptr = vmap(&dst_page, 1, VM_IOREMAP, __pgprot(__PAGE_COPY)); if (!user_ptr) goto no_vmap; diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index a062e07516dd..46cccd6bf705 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -322,6 +322,10 @@ retry: return 0; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (!(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index cd17e324aa51..a49f0b9c0f75 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -412,6 +412,26 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot) local_flush_tlb_kernel_range(vaddr, vaddr + PAGE_SIZE); } +static pgprot_t protection_map[16] __ro_after_init = { + [VM_NONE] = __PAGE_NONE, + [VM_READ] = __PAGE_READONLY, + [VM_WRITE] = __PAGE_COPY, + [VM_WRITE | VM_READ] = __PAGE_COPY, + [VM_EXEC] = __PAGE_READONLY_EXEC, + [VM_EXEC | VM_READ] = __PAGE_READONLY_EXEC, + [VM_EXEC | VM_WRITE] = __PAGE_COPY_EXEC, + [VM_EXEC | VM_WRITE | VM_READ] = __PAGE_COPY_EXEC, + [VM_SHARED] = __PAGE_NONE, + [VM_SHARED | VM_READ] = __PAGE_READONLY, + [VM_SHARED | VM_WRITE] = __PAGE_SHARED, + [VM_SHARED | VM_WRITE | VM_READ] = __PAGE_SHARED, + [VM_SHARED | VM_EXEC] = __PAGE_READONLY_EXEC, + [VM_SHARED | VM_EXEC | VM_READ] = __PAGE_READONLY_EXEC, + [VM_SHARED | VM_EXEC | VM_WRITE] = __PAGE_SHARED_EXEC, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = __PAGE_SHARED_EXEC +}; +DECLARE_VM_GET_PAGE_PROT + /* * Adjust the PMD section entries according to the CPU in use. */ diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 6bb50124a7e9..571cc234d0b3 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -45,7 +45,6 @@ config ARM64 select ARCH_HAS_SYSCALL_WRAPPER select ARCH_HAS_TEARDOWN_DMA_OPS if IOMMU_SUPPORT select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_HAS_ZONE_DMA_SET if EXPERT select ARCH_HAVE_ELF_PROT select ARCH_HAVE_NMI_SAFE_CMPXCHG diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index 1fd2846dbefe..d20f5da2d76f 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -46,9 +46,6 @@ extern void huge_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long sz); #define __HAVE_ARCH_HUGE_PTEP_GET extern pte_t huge_ptep_get(pte_t *ptep); -extern void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte, unsigned long sz); -#define set_huge_swap_pte_at set_huge_swap_pte_at void __init arm64_hugetlb_cma_reserve(void); diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 4e4c171f070b..9dd08cd339c3 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -381,6 +381,15 @@ static inline bool defer_reserve_crashkernel(void) # define INIT_MEMBLOCK_RESERVED_REGIONS (INIT_MEMBLOCK_REGIONS + NR_CPUS + 1) #endif +/* + * memory regions which marked with flag MEMBLOCK_NOMAP(for example, the memory + * of the EFI_UNUSABLE_MEMORY type) may divide a continuous memory block into + * multiple parts. As a result, the number of memory regions is large. + */ +#ifdef CONFIG_EFI +#define INIT_MEMBLOCK_MEMORY_REGIONS (INIT_MEMBLOCK_REGIONS * 8) +#endif + #include <asm-generic/memory_model.h> #endif /* __ASM_MEMORY_H */ diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 62e0ebeed720..9b165117a454 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -89,24 +89,6 @@ extern bool arm64_use_ng_mappings; #define PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN) #define PAGE_EXECONLY __pgprot(_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN) -#define __P000 PAGE_NONE -#define __P001 PAGE_READONLY -#define __P010 PAGE_READONLY -#define __P011 PAGE_READONLY -#define __P100 PAGE_READONLY_EXEC /* PAGE_EXECONLY if Enhanced PAN */ -#define __P101 PAGE_READONLY_EXEC -#define __P110 PAGE_READONLY_EXEC -#define __P111 PAGE_READONLY_EXEC - -#define __S000 PAGE_NONE -#define __S001 PAGE_READONLY -#define __S010 PAGE_SHARED -#define __S011 PAGE_SHARED -#define __S100 PAGE_READONLY_EXEC /* PAGE_EXECONLY if Enhanced PAN */ -#define __S101 PAGE_READONLY_EXEC -#define __S110 PAGE_SHARED_EXEC -#define __S111 PAGE_SHARED_EXEC - #endif /* __ASSEMBLY__ */ #endif /* __ASM_PGTABLE_PROT_H */ diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index cdf3ffa0c223..c33f1fad2745 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -608,6 +608,10 @@ retry: return 0; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (fault & VM_FAULT_RETRY) { mm_flags |= FAULT_FLAG_TRIED; goto retry; diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 5307ffdefb8d..0795028f017c 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -241,6 +241,13 @@ static void clear_flush(struct mm_struct *mm, flush_tlb_range(&vma, saddr, addr); } +static inline struct folio *hugetlb_swap_entry_to_folio(swp_entry_t entry) +{ + VM_BUG_ON(!is_migration_entry(entry) && !is_hwpoison_entry(entry)); + + return page_folio(pfn_to_page(swp_offset(entry))); +} + void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { @@ -250,11 +257,16 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, unsigned long pfn, dpfn; pgprot_t hugeprot; - /* - * Code needs to be expanded to handle huge swap and migration - * entries. Needed for HUGETLB and MEMORY_FAILURE. - */ - WARN_ON(!pte_present(pte)); + if (!pte_present(pte)) { + struct folio *folio; + + folio = hugetlb_swap_entry_to_folio(pte_to_swp_entry(pte)); + ncontig = num_contig_ptes(folio_size(folio), &pgsize); + + for (i = 0; i < ncontig; i++, ptep++) + set_pte_at(mm, addr, ptep, pte); + return; + } if (!pte_cont(pte)) { set_pte_at(mm, addr, ptep, pte); @@ -272,18 +284,6 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot)); } -void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte, unsigned long sz) -{ - int i, ncontig; - size_t pgsize; - - ncontig = num_contig_ptes(sz, &pgsize); - - for (i = 0; i < ncontig; i++, ptep++) - set_pte(ptep, pte); -} - pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz) { @@ -371,6 +371,28 @@ pte_t *huge_pte_offset(struct mm_struct *mm, return NULL; } +unsigned long hugetlb_mask_last_page(struct hstate *h) +{ + unsigned long hp_size = huge_page_size(h); + + switch (hp_size) { +#ifndef __PAGETABLE_PMD_FOLDED + case PUD_SIZE: + return PGDIR_SIZE - PUD_SIZE; +#endif + case CONT_PMD_SIZE: + return PUD_SIZE - CONT_PMD_SIZE; + case PMD_SIZE: + return PUD_SIZE - PMD_SIZE; + case CONT_PTE_SIZE: + return PMD_SIZE - CONT_PTE_SIZE; + default: + break; + } + + return 0UL; +} + pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) { size_t pagesize = 1UL << shift; diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 78e9490f748d..8f5b7ce857ed 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -13,6 +13,27 @@ #include <asm/cpufeature.h> #include <asm/page.h> +static pgprot_t protection_map[16] __ro_after_init = { + [VM_NONE] = PAGE_NONE, + [VM_READ] = PAGE_READONLY, + [VM_WRITE] = PAGE_READONLY, + [VM_WRITE | VM_READ] = PAGE_READONLY, + /* PAGE_EXECONLY if Enhanced PAN */ + [VM_EXEC] = PAGE_READONLY_EXEC, + [VM_EXEC | VM_READ] = PAGE_READONLY_EXEC, + [VM_EXEC | VM_WRITE] = PAGE_READONLY_EXEC, + [VM_EXEC | VM_WRITE | VM_READ] = PAGE_READONLY_EXEC, + [VM_SHARED] = PAGE_NONE, + [VM_SHARED | VM_READ] = PAGE_READONLY, + [VM_SHARED | VM_WRITE] = PAGE_SHARED, + [VM_SHARED | VM_WRITE | VM_READ] = PAGE_SHARED, + /* PAGE_EXECONLY if Enhanced PAN */ + [VM_SHARED | VM_EXEC] = PAGE_READONLY_EXEC, + [VM_SHARED | VM_EXEC | VM_READ] = PAGE_READONLY_EXEC, + [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_SHARED_EXEC, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_SHARED_EXEC +}; + /* * You really shouldn't be using read() or write() on /dev/mem. This might go * away in the future. diff --git a/arch/csky/include/asm/pgalloc.h b/arch/csky/include/asm/pgalloc.h index bbbd0698b397..7d57e5da0914 100644 --- a/arch/csky/include/asm/pgalloc.h +++ b/arch/csky/include/asm/pgalloc.h @@ -44,7 +44,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) pgd_t *ret; pgd_t *init; - ret = (pgd_t *) __get_free_pages(GFP_KERNEL, PGD_ORDER); + ret = (pgd_t *) __get_free_page(GFP_KERNEL); if (ret) { init = pgd_offset(&init_mm, 0UL); pgd_init((unsigned long *)ret); diff --git a/arch/csky/include/asm/pgtable.h b/arch/csky/include/asm/pgtable.h index bbe245117777..c3d9b92cbe61 100644 --- a/arch/csky/include/asm/pgtable.h +++ b/arch/csky/include/asm/pgtable.h @@ -18,12 +18,10 @@ /* * C-SKY is two-level paging structure: */ -#define PGD_ORDER 0 -#define PTE_ORDER 0 -#define PTRS_PER_PGD ((PAGE_SIZE << PGD_ORDER) / sizeof(pgd_t)) +#define PTRS_PER_PGD (PAGE_SIZE / sizeof(pgd_t)) #define PTRS_PER_PMD 1 -#define PTRS_PER_PTE ((PAGE_SIZE << PTE_ORDER) / sizeof(pte_t)) +#define PTRS_PER_PTE (PAGE_SIZE / sizeof(pte_t)) #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, (e).pte_low) @@ -77,24 +75,6 @@ #define MAX_SWAPFILES_CHECK() \ BUILD_BUG_ON(MAX_SWAPFILES_SHIFT != 5) -#define __P000 PAGE_NONE -#define __P001 PAGE_READ -#define __P010 PAGE_READ -#define __P011 PAGE_READ -#define __P100 PAGE_READ -#define __P101 PAGE_READ -#define __P110 PAGE_READ -#define __P111 PAGE_READ - -#define __S000 PAGE_NONE -#define __S001 PAGE_READ -#define __S010 PAGE_WRITE -#define __S011 PAGE_WRITE -#define __S100 PAGE_READ -#define __S101 PAGE_READ -#define __S110 PAGE_WRITE -#define __S111 PAGE_WRITE - extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) diff --git a/arch/csky/mm/fault.c b/arch/csky/mm/fault.c index 7215a46b6b8e..e15f736cca4b 100644 --- a/arch/csky/mm/fault.c +++ b/arch/csky/mm/fault.c @@ -285,6 +285,10 @@ good_area: return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely((fault & VM_FAULT_RETRY) && (flags & FAULT_FLAG_ALLOW_RETRY))) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/csky/mm/init.c b/arch/csky/mm/init.c index bf2004aa811a..bde7cabd23df 100644 --- a/arch/csky/mm/init.c +++ b/arch/csky/mm/init.c @@ -197,3 +197,23 @@ void __init fixaddr_init(void) vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK; fixrange_init(vaddr, vaddr + PMD_SIZE, swapper_pg_dir); } + +static const pgprot_t protection_map[16] = { + [VM_NONE] = PAGE_NONE, + [VM_READ] = PAGE_READ, + [VM_WRITE] = PAGE_READ, + [VM_WRITE | VM_READ] = PAGE_READ, + [VM_EXEC] = PAGE_READ, + [VM_EXEC | VM_READ] = PAGE_READ, + [VM_EXEC | VM_WRITE] = PAGE_READ, + [VM_EXEC | VM_WRITE | VM_READ] = PAGE_READ, + [VM_SHARED] = PAGE_NONE, + [VM_SHARED | VM_READ] = PAGE_READ, + [VM_SHARED | VM_WRITE] = PAGE_WRITE, + [VM_SHARED | VM_WRITE | VM_READ] = PAGE_WRITE, + [VM_SHARED | VM_EXEC] = PAGE_READ, + [VM_SHARED | VM_EXEC | VM_READ] = PAGE_READ, + [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_WRITE, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_WRITE +}; +DECLARE_VM_GET_PAGE_PROT diff --git a/arch/hexagon/include/asm/pgtable.h b/arch/hexagon/include/asm/pgtable.h index 0610724d6a28..f7048c18b6f9 100644 --- a/arch/hexagon/include/asm/pgtable.h +++ b/arch/hexagon/include/asm/pgtable.h @@ -126,33 +126,6 @@ extern unsigned long _dflt_cache_att; */ #define CACHEDEF (CACHE_DEFAULT << 6) -/* Private (copy-on-write) page protections. */ -#define __P000 __pgprot(_PAGE_PRESENT | _PAGE_USER | CACHEDEF) -#define __P001 __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ | CACHEDEF) -#define __P010 __P000 /* Write-only copy-on-write */ -#define __P011 __P001 /* Read/Write copy-on-write */ -#define __P100 __pgprot(_PAGE_PRESENT | _PAGE_USER | \ - _PAGE_EXECUTE | CACHEDEF) -#define __P101 __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_EXECUTE | \ - _PAGE_READ | CACHEDEF) -#define __P110 __P100 /* Write/execute copy-on-write */ -#define __P111 __P101 /* Read/Write/Execute, copy-on-write */ - -/* Shared page protections. */ -#define __S000 __P000 -#define __S001 __P001 -#define __S010 __pgprot(_PAGE_PRESENT | _PAGE_USER | \ - _PAGE_WRITE | CACHEDEF) -#define __S011 __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ | \ - _PAGE_WRITE | CACHEDEF) -#define __S100 __pgprot(_PAGE_PRESENT | _PAGE_USER | \ - _PAGE_EXECUTE | CACHEDEF) -#define __S101 __P101 -#define __S110 __pgprot(_PAGE_PRESENT | _PAGE_USER | \ - _PAGE_EXECUTE | _PAGE_WRITE | CACHEDEF) -#define __S111 __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ | \ - _PAGE_EXECUTE | _PAGE_WRITE | CACHEDEF) - extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; /* located in head.S */ /* HUGETLB not working currently */ diff --git a/arch/hexagon/mm/init.c b/arch/hexagon/mm/init.c index 3167a3b5c97b..146115c9de61 100644 --- a/arch/hexagon/mm/init.c +++ b/arch/hexagon/mm/init.c @@ -234,3 +234,45 @@ void __init setup_arch_memory(void) * which is called by start_kernel() later on in the process */ } + +static const pgprot_t protection_map[16] = { + [VM_NONE] = __pgprot(_PAGE_PRESENT | _PAGE_USER | + CACHEDEF), + [VM_READ] = __pgprot(_PAGE_PRESENT | _PAGE_USER | + _PAGE_READ | CACHEDEF), + [VM_WRITE] = __pgprot(_PAGE_PRESENT | _PAGE_USER | + CACHEDEF), + [VM_WRITE | VM_READ] = __pgprot(_PAGE_PRESENT | _PAGE_USER | + _PAGE_READ | CACHEDEF), + [VM_EXEC] = __pgprot(_PAGE_PRESENT | _PAGE_USER | + _PAGE_EXECUTE | CACHEDEF), + [VM_EXEC | VM_READ] = __pgprot(_PAGE_PRESENT | _PAGE_USER | + _PAGE_EXECUTE | _PAGE_READ | + CACHEDEF), + [VM_EXEC | VM_WRITE] = __pgprot(_PAGE_PRESENT | _PAGE_USER | + _PAGE_EXECUTE | CACHEDEF), + [VM_EXEC | VM_WRITE | VM_READ] = __pgprot(_PAGE_PRESENT | _PAGE_USER | + _PAGE_EXECUTE | _PAGE_READ | + CACHEDEF), + [VM_SHARED] = __pgprot(_PAGE_PRESENT | _PAGE_USER | + CACHEDEF), + [VM_SHARED | VM_READ] = __pgprot(_PAGE_PRESENT | _PAGE_USER | + _PAGE_READ | CACHEDEF), + [VM_SHARED | VM_WRITE] = __pgprot(_PAGE_PRESENT | _PAGE_USER | + _PAGE_WRITE | CACHEDEF), + [VM_SHARED | VM_WRITE | VM_READ] = __pgprot(_PAGE_PRESENT | _PAGE_USER | + _PAGE_READ | _PAGE_WRITE | + CACHEDEF), + [VM_SHARED | VM_EXEC] = __pgprot(_PAGE_PRESENT | _PAGE_USER | + _PAGE_EXECUTE | CACHEDEF), + [VM_SHARED | VM_EXEC | VM_READ] = __pgprot(_PAGE_PRESENT | _PAGE_USER | + _PAGE_EXECUTE | _PAGE_READ | + CACHEDEF), + [VM_SHARED | VM_EXEC | VM_WRITE] = __pgprot(_PAGE_PRESENT | _PAGE_USER | + _PAGE_EXECUTE | _PAGE_WRITE | + CACHEDEF), + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = __pgprot(_PAGE_PRESENT | _PAGE_USER | + _PAGE_READ | _PAGE_EXECUTE | + _PAGE_WRITE | CACHEDEF) +}; +DECLARE_VM_GET_PAGE_PROT diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c index 4fac4b9eb316..f73c7cbfe326 100644 --- a/arch/hexagon/mm/vm_fault.c +++ b/arch/hexagon/mm/vm_fault.c @@ -96,6 +96,10 @@ good_area: if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* The most common case -- we are done. */ if (likely(!(fault & VM_FAULT_ERROR))) { if (fault & VM_FAULT_RETRY) { diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h index 7aa8f2330fb1..6925e28ae61d 100644 --- a/arch/ia64/include/asm/pgtable.h +++ b/arch/ia64/include/asm/pgtable.h @@ -161,24 +161,6 @@ * attempts to write to the page. */ /* xwr */ -#define __P000 PAGE_NONE -#define __P001 PAGE_READONLY -#define __P010 PAGE_READONLY /* write to priv pg -> copy & make writable */ -#define __P011 PAGE_READONLY /* ditto */ -#define __P100 __pgprot(__ACCESS_BITS | _PAGE_PL_3 | _PAGE_AR_X_RX) -#define __P101 __pgprot(__ACCESS_BITS | _PAGE_PL_3 | _PAGE_AR_RX) -#define __P110 PAGE_COPY_EXEC -#define __P111 PAGE_COPY_EXEC - -#define __S000 PAGE_NONE -#define __S001 PAGE_READONLY -#define __S010 PAGE_SHARED /* we don't have (and don't need) write-only */ -#define __S011 PAGE_SHARED -#define __S100 __pgprot(__ACCESS_BITS | _PAGE_PL_3 | _PAGE_AR_X_RX) -#define __S101 __pgprot(__ACCESS_BITS | _PAGE_PL_3 | _PAGE_AR_RX) -#define __S110 __pgprot(__ACCESS_BITS | _PAGE_PL_3 | _PAGE_AR_RWX) -#define __S111 __pgprot(__ACCESS_BITS | _PAGE_PL_3 | _PAGE_AR_RWX) - #define pgd_ERROR(e) printk("%s:%d: bad pgd %016lx.\n", __FILE__, __LINE__, pgd_val(e)) #if CONFIG_PGTABLE_LEVELS == 4 #define pud_ERROR(e) printk("%s:%d: bad pud %016lx.\n", __FILE__, __LINE__, pud_val(e)) diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 07379d1a227f..ef78c2d66cdd 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -139,6 +139,10 @@ retry: if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { /* * We ran out of memory, or some other thing happened diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 855d949d81df..fc4e4217e87f 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -273,7 +273,7 @@ static int __init gate_vma_init(void) gate_vma.vm_start = FIXADDR_USER_START; gate_vma.vm_end = FIXADDR_USER_END; gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; - gate_vma.vm_page_prot = __P101; + gate_vma.vm_page_prot = __pgprot(__ACCESS_BITS | _PAGE_PL_3 | _PAGE_AR_RX); return 0; } @@ -490,3 +490,29 @@ void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) __remove_pages(start_pfn, nr_pages, altmap); } #endif + +static const pgprot_t protection_map[16] = { + [VM_NONE] = PAGE_NONE, + [VM_READ] = PAGE_READONLY, + [VM_WRITE] = PAGE_READONLY, + [VM_WRITE | VM_READ] = PAGE_READONLY, + [VM_EXEC] = __pgprot(__ACCESS_BITS | _PAGE_PL_3 | + _PAGE_AR_X_RX), + [VM_EXEC | VM_READ] = __pgprot(__ACCESS_BITS | _PAGE_PL_3 | + _PAGE_AR_RX), + [VM_EXEC | VM_WRITE] = PAGE_COPY_EXEC, + [VM_EXEC | VM_WRITE | VM_READ] = PAGE_COPY_EXEC, + [VM_SHARED] = PAGE_NONE, + [VM_SHARED | VM_READ] = PAGE_READONLY, + [VM_SHARED | VM_WRITE] = PAGE_SHARED, + [VM_SHARED | VM_WRITE | VM_READ] = PAGE_SHARED, + [VM_SHARED | VM_EXEC] = __pgprot(__ACCESS_BITS | _PAGE_PL_3 | + _PAGE_AR_X_RX), + [VM_SHARED | VM_EXEC | VM_READ] = __pgprot(__ACCESS_BITS | _PAGE_PL_3 | + _PAGE_AR_RX), + [VM_SHARED | VM_EXEC | VM_WRITE] = __pgprot(__ACCESS_BITS | _PAGE_PL_3 | + _PAGE_AR_RWX), + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = __pgprot(__ACCESS_BITS | _PAGE_PL_3 | + _PAGE_AR_RWX) +}; +DECLARE_VM_GET_PAGE_PROT diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index fc2465892a60..ae15610a9427 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -407,7 +407,7 @@ config ARCH_SPARSEMEM_ENABLE Say Y to support efficient handling of sparse physical memory, for architectures which are either NUMA (Non-Uniform Memory Access) or have huge holes in the physical address space for other reasons. - See <file:Documentation/vm/numa.rst> for more. + See <file:Documentation/mm/numa.rst> for more. config ARCH_ENABLE_THP_MIGRATION def_bool y diff --git a/arch/loongarch/include/asm/pgalloc.h b/arch/loongarch/include/asm/pgalloc.h index b0a57b25c131..4bfeb3c9c9ac 100644 --- a/arch/loongarch/include/asm/pgalloc.h +++ b/arch/loongarch/include/asm/pgalloc.h @@ -66,12 +66,12 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) pmd_t *pmd; struct page *pg; - pg = alloc_pages(GFP_KERNEL_ACCOUNT, PMD_ORDER); + pg = alloc_page(GFP_KERNEL_ACCOUNT); if (!pg) return NULL; if (!pgtable_pmd_page_ctor(pg)) { - __free_pages(pg, PMD_ORDER); + __free_page(pg); return NULL; } @@ -90,7 +90,7 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) { pud_t *pud; - pud = (pud_t *) __get_free_pages(GFP_KERNEL, PUD_ORDER); + pud = (pud_t *) __get_free_page(GFP_KERNEL); if (pud) pud_init((unsigned long)pud, (unsigned long)invalid_pmd_table); return pud; diff --git a/arch/loongarch/include/asm/pgtable-bits.h b/arch/loongarch/include/asm/pgtable-bits.h index 3badd112d9ab..9ca147a29bab 100644 --- a/arch/loongarch/include/asm/pgtable-bits.h +++ b/arch/loongarch/include/asm/pgtable-bits.h @@ -83,25 +83,6 @@ _PAGE_GLOBAL | _PAGE_KERN | _CACHE_SUC) #define PAGE_KERNEL_WUC __pgprot(_PAGE_PRESENT | __READABLE | __WRITEABLE | \ _PAGE_GLOBAL | _PAGE_KERN | _CACHE_WUC) - -#define __P000 __pgprot(_CACHE_CC | _PAGE_USER | _PAGE_PROTNONE | _PAGE_NO_EXEC | _PAGE_NO_READ) -#define __P001 __pgprot(_CACHE_CC | _PAGE_VALID | _PAGE_USER | _PAGE_PRESENT | _PAGE_NO_EXEC) -#define __P010 __pgprot(_CACHE_CC | _PAGE_VALID | _PAGE_USER | _PAGE_PRESENT | _PAGE_NO_EXEC) -#define __P011 __pgprot(_CACHE_CC | _PAGE_VALID | _PAGE_USER | _PAGE_PRESENT | _PAGE_NO_EXEC) -#define __P100 __pgprot(_CACHE_CC | _PAGE_VALID | _PAGE_USER | _PAGE_PRESENT) -#define __P101 __pgprot(_CACHE_CC | _PAGE_VALID | _PAGE_USER | _PAGE_PRESENT) -#define __P110 __pgprot(_CACHE_CC | _PAGE_VALID | _PAGE_USER | _PAGE_PRESENT) -#define __P111 __pgprot(_CACHE_CC | _PAGE_VALID | _PAGE_USER | _PAGE_PRESENT) - -#define __S000 __pgprot(_CACHE_CC | _PAGE_USER | _PAGE_PROTNONE | _PAGE_NO_EXEC | _PAGE_NO_READ) -#define __S001 __pgprot(_CACHE_CC | _PAGE_VALID | _PAGE_USER | _PAGE_PRESENT | _PAGE_NO_EXEC) -#define __S010 __pgprot(_CACHE_CC | _PAGE_VALID | _PAGE_USER | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE) -#define __S011 __pgprot(_CACHE_CC | _PAGE_VALID | _PAGE_USER | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE) -#define __S100 __pgprot(_CACHE_CC | _PAGE_VALID | _PAGE_USER | _PAGE_PRESENT) -#define __S101 __pgprot(_CACHE_CC | _PAGE_VALID | _PAGE_USER | _PAGE_PRESENT) -#define __S110 __pgprot(_CACHE_CC | _PAGE_VALID | _PAGE_USER | _PAGE_PRESENT | _PAGE_WRITE) -#define __S111 __pgprot(_CACHE_CC | _PAGE_VALID | _PAGE_USER | _PAGE_PRESENT | _PAGE_WRITE) - #ifndef __ASSEMBLY__ #define pgprot_noncached pgprot_noncached diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index d9e86cfa53e2..e03443abaf7d 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -21,41 +21,36 @@ #include <asm-generic/pgtable-nop4d.h> #endif -#define PGD_ORDER 0 -#define PUD_ORDER 0 -#define PMD_ORDER 0 -#define PTE_ORDER 0 - #if CONFIG_PGTABLE_LEVELS == 2 -#define PGDIR_SHIFT (PAGE_SHIFT + (PAGE_SHIFT + PTE_ORDER - 3)) +#define PGDIR_SHIFT (PAGE_SHIFT + (PAGE_SHIFT - 3)) #elif CONFIG_PGTABLE_LEVELS == 3 -#define PMD_SHIFT (PAGE_SHIFT + (PAGE_SHIFT + PTE_ORDER - 3)) +#define PMD_SHIFT (PAGE_SHIFT + (PAGE_SHIFT - 3)) #define PMD_SIZE (1UL << PMD_SHIFT) #define PMD_MASK (~(PMD_SIZE-1)) -#define PGDIR_SHIFT (PMD_SHIFT + (PAGE_SHIFT + PMD_ORDER - 3)) +#define PGDIR_SHIFT (PMD_SHIFT + (PAGE_SHIFT - 3)) #elif CONFIG_PGTABLE_LEVELS == 4 -#define PMD_SHIFT (PAGE_SHIFT + (PAGE_SHIFT + PTE_ORDER - 3)) +#define PMD_SHIFT (PAGE_SHIFT + (PAGE_SHIFT - 3)) #define PMD_SIZE (1UL << PMD_SHIFT) #define PMD_MASK (~(PMD_SIZE-1)) -#define PUD_SHIFT (PMD_SHIFT + (PAGE_SHIFT + PMD_ORDER - 3)) +#define PUD_SHIFT (PMD_SHIFT + (PAGE_SHIFT - 3)) #define PUD_SIZE (1UL << PUD_SHIFT) #define PUD_MASK (~(PUD_SIZE-1)) -#define PGDIR_SHIFT (PUD_SHIFT + (PAGE_SHIFT + PUD_ORDER - 3)) +#define PGDIR_SHIFT (PUD_SHIFT + (PAGE_SHIFT - 3)) #endif #define PGDIR_SIZE (1UL << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE-1)) -#define VA_BITS (PGDIR_SHIFT + (PAGE_SHIFT + PGD_ORDER - 3)) +#define VA_BITS (PGDIR_SHIFT + (PAGE_SHIFT - 3)) -#define PTRS_PER_PGD ((PAGE_SIZE << PGD_ORDER) >> 3) +#define PTRS_PER_PGD (PAGE_SIZE >> 3) #if CONFIG_PGTABLE_LEVELS > 3 -#define PTRS_PER_PUD ((PAGE_SIZE << PUD_ORDER) >> 3) +#define PTRS_PER_PUD (PAGE_SIZE >> 3) #endif #if CONFIG_PGTABLE_LEVELS > 2 -#define PTRS_PER_PMD ((PAGE_SIZE << PMD_ORDER) >> 3) +#define PTRS_PER_PMD (PAGE_SIZE >> 3) #endif -#define PTRS_PER_PTE ((PAGE_SIZE << PTE_ORDER) >> 3) +#define PTRS_PER_PTE (PAGE_SIZE >> 3) #define USER_PTRS_PER_PGD ((TASK_SIZE64 / PGDIR_SIZE)?(TASK_SIZE64 / PGDIR_SIZE):1) diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c index 20cd9e16a95a..d256b81c397a 100644 --- a/arch/loongarch/kernel/asm-offsets.c +++ b/arch/loongarch/kernel/asm-offsets.c @@ -189,12 +189,6 @@ void output_mm_defines(void) #endif DEFINE(_PTE_T_LOG2, PTE_T_LOG2); BLANK(); - DEFINE(_PGD_ORDER, PGD_ORDER); -#ifndef __PAGETABLE_PMD_FOLDED - DEFINE(_PMD_ORDER, PMD_ORDER); -#endif - DEFINE(_PTE_ORDER, PTE_ORDER); - BLANK(); DEFINE(_PMD_SHIFT, PMD_SHIFT); DEFINE(_PGDIR_SHIFT, PGDIR_SHIFT); BLANK(); diff --git a/arch/loongarch/mm/cache.c b/arch/loongarch/mm/cache.c index 9e5ce5aa73f7..e8c68dcf6ab2 100644 --- a/arch/loongarch/mm/cache.c +++ b/arch/loongarch/mm/cache.c @@ -139,3 +139,49 @@ void cpu_cache_init(void) shm_align_mask = PAGE_SIZE - 1; } + +static const pgprot_t protection_map[16] = { + [VM_NONE] = __pgprot(_CACHE_CC | _PAGE_USER | + _PAGE_PROTNONE | _PAGE_NO_EXEC | + _PAGE_NO_READ), + [VM_READ] = __pgprot(_CACHE_CC | _PAGE_VALID | + _PAGE_USER | _PAGE_PRESENT | + _PAGE_NO_EXEC), + [VM_WRITE] = __pgprot(_CACHE_CC | _PAGE_VALID | + _PAGE_USER | _PAGE_PRESENT | + _PAGE_NO_EXEC), + [VM_WRITE | VM_READ] = __pgprot(_CACHE_CC | _PAGE_VALID | + _PAGE_USER | _PAGE_PRESENT | + _PAGE_NO_EXEC), + [VM_EXEC] = __pgprot(_CACHE_CC | _PAGE_VALID | + _PAGE_USER | _PAGE_PRESENT), + [VM_EXEC | VM_READ] = __pgprot(_CACHE_CC | _PAGE_VALID | + _PAGE_USER | _PAGE_PRESENT), + [VM_EXEC | VM_WRITE] = __pgprot(_CACHE_CC | _PAGE_VALID | + _PAGE_USER | _PAGE_PRESENT), + [VM_EXEC | VM_WRITE | VM_READ] = __pgprot(_CACHE_CC | _PAGE_VALID | + _PAGE_USER | _PAGE_PRESENT), + [VM_SHARED] = __pgprot(_CACHE_CC | _PAGE_USER | + _PAGE_PROTNONE | _PAGE_NO_EXEC | + _PAGE_NO_READ), + [VM_SHARED | VM_READ] = __pgprot(_CACHE_CC | _PAGE_VALID | + _PAGE_USER | _PAGE_PRESENT | + _PAGE_NO_EXEC), + [VM_SHARED | VM_WRITE] = __pgprot(_CACHE_CC | _PAGE_VALID | + _PAGE_USER | _PAGE_PRESENT | + _PAGE_NO_EXEC | _PAGE_WRITE), + [VM_SHARED | VM_WRITE | VM_READ] = __pgprot(_CACHE_CC | _PAGE_VALID | + _PAGE_USER | _PAGE_PRESENT | + _PAGE_NO_EXEC | _PAGE_WRITE), + [VM_SHARED | VM_EXEC] = __pgprot(_CACHE_CC | _PAGE_VALID | + _PAGE_USER | _PAGE_PRESENT), + [VM_SHARED | VM_EXEC | VM_READ] = __pgprot(_CACHE_CC | _PAGE_VALID | + _PAGE_USER | _PAGE_PRESENT), + [VM_SHARED | VM_EXEC | VM_WRITE] = __pgprot(_CACHE_CC | _PAGE_VALID | + _PAGE_USER | _PAGE_PRESENT | + _PAGE_WRITE), + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = __pgprot(_CACHE_CC | _PAGE_VALID | + _PAGE_USER | _PAGE_PRESENT | + _PAGE_WRITE) +}; +DECLARE_VM_GET_PAGE_PROT diff --git a/arch/loongarch/mm/pgtable.c b/arch/loongarch/mm/pgtable.c index 0569647152e9..ee179ccd3e3f 100644 --- a/arch/loongarch/mm/pgtable.c +++ b/arch/loongarch/mm/pgtable.c @@ -13,7 +13,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *ret, *init; - ret = (pgd_t *) __get_free_pages(GFP_KERNEL, PGD_ORDER); + ret = (pgd_t *) __get_free_page(GFP_KERNEL); if (ret) { init = pgd_offset(&init_mm, 0UL); pgd_init((unsigned long)ret); diff --git a/arch/loongarch/mm/tlbex.S b/arch/loongarch/mm/tlbex.S index de19fa2d7f0d..39743337999e 100644 --- a/arch/loongarch/mm/tlbex.S +++ b/arch/loongarch/mm/tlbex.S @@ -83,7 +83,7 @@ vmalloc_done_load: bnez t0, tlb_huge_update_load csrrd t0, LOONGARCH_CSR_BADV - srli.d t0, t0, (PAGE_SHIFT + PTE_ORDER) + srli.d t0, t0, PAGE_SHIFT andi t0, t0, (PTRS_PER_PTE - 1) slli.d t0, t0, _PTE_T_LOG2 add.d t1, ra, t0 @@ -247,7 +247,7 @@ vmalloc_done_store: bnez t0, tlb_huge_update_store csrrd t0, LOONGARCH_CSR_BADV - srli.d t0, t0, (PAGE_SHIFT + PTE_ORDER) + srli.d t0, t0, PAGE_SHIFT andi t0, t0, (PTRS_PER_PTE - 1) slli.d t0, t0, _PTE_T_LOG2 add.d t1, ra, t0 @@ -414,7 +414,7 @@ vmalloc_done_modify: bnez t0, tlb_huge_update_modify csrrd t0, LOONGARCH_CSR_BADV - srli.d t0, t0, (PAGE_SHIFT + PTE_ORDER) + srli.d t0, t0, PAGE_SHIFT andi t0, t0, (PTRS_PER_PTE - 1) slli.d t0, t0, _PTE_T_LOG2 add.d t1, ra, t0 diff --git a/arch/m68k/include/asm/mcf_pgtable.h b/arch/m68k/include/asm/mcf_pgtable.h index 94f38d76e278..b619b22823f8 100644 --- a/arch/m68k/include/asm/mcf_pgtable.h +++ b/arch/m68k/include/asm/mcf_pgtable.h @@ -86,65 +86,6 @@ | CF_PAGE_READABLE \ | CF_PAGE_DIRTY) -/* - * Page protections for initialising protection_map. See mm/mmap.c - * for use. In general, the bit positions are xwr, and P-items are - * private, the S-items are shared. - */ -#define __P000 PAGE_NONE -#define __P001 __pgprot(CF_PAGE_VALID \ - | CF_PAGE_ACCESSED \ - | CF_PAGE_READABLE) -#define __P010 __pgprot(CF_PAGE_VALID \ - | CF_PAGE_ACCESSED \ - | CF_PAGE_WRITABLE) -#define __P011 __pgprot(CF_PAGE_VALID \ - | CF_PAGE_ACCESSED \ - | CF_PAGE_READABLE \ - | CF_PAGE_WRITABLE) -#define __P100 __pgprot(CF_PAGE_VALID \ - | CF_PAGE_ACCESSED \ - | CF_PAGE_EXEC) -#define __P101 __pgprot(CF_PAGE_VALID \ - | CF_PAGE_ACCESSED \ - | CF_PAGE_READABLE \ - | CF_PAGE_EXEC) -#define __P110 __pgprot(CF_PAGE_VALID \ - | CF_PAGE_ACCESSED \ - | CF_PAGE_WRITABLE \ - | CF_PAGE_EXEC) -#define __P111 __pgprot(CF_PAGE_VALID \ - | CF_PAGE_ACCESSED \ - | CF_PAGE_READABLE \ - | CF_PAGE_WRITABLE \ - | CF_PAGE_EXEC) - -#define __S000 PAGE_NONE -#define __S001 __pgprot(CF_PAGE_VALID \ - | CF_PAGE_ACCESSED \ - | CF_PAGE_READABLE) -#define __S010 PAGE_SHARED -#define __S011 __pgprot(CF_PAGE_VALID \ - | CF_PAGE_ACCESSED \ - | CF_PAGE_SHARED \ - | CF_PAGE_READABLE) -#define __S100 __pgprot(CF_PAGE_VALID \ - | CF_PAGE_ACCESSED \ - | CF_PAGE_EXEC) -#define __S101 __pgprot(CF_PAGE_VALID \ - | CF_PAGE_ACCESSED \ - | CF_PAGE_READABLE \ - | CF_PAGE_EXEC) -#define __S110 __pgprot(CF_PAGE_VALID \ - | CF_PAGE_ACCESSED \ - | CF_PAGE_SHARED \ - | CF_PAGE_EXEC) -#define __S111 __pgprot(CF_PAGE_VALID \ - | CF_PAGE_ACCESSED \ - | CF_PAGE_SHARED \ - | CF_PAGE_READABLE \ - | CF_PAGE_EXEC) - #define PTE_MASK PAGE_MASK #define CF_PAGE_CHG_MASK (PTE_MASK | CF_PAGE_ACCESSED | CF_PAGE_DIRTY) diff --git a/arch/m68k/include/asm/motorola_pgtable.h b/arch/m68k/include/asm/motorola_pgtable.h index 7c9b56e2a750..7ac3d64c6b33 100644 --- a/arch/m68k/include/asm/motorola_pgtable.h +++ b/arch/m68k/include/asm/motorola_pgtable.h @@ -76,35 +76,6 @@ extern unsigned long mm_cachebits; #define PAGE_READONLY __pgprot(_PAGE_PRESENT | _PAGE_RONLY | _PAGE_ACCESSED | mm_cachebits) #define PAGE_KERNEL __pgprot(_PAGE_PRESENT | _PAGE_DIRTY | _PAGE_ACCESSED | mm_cachebits) -/* Alternate definitions that are compile time constants, for - initializing protection_map. The cachebits are fixed later. */ -#define PAGE_NONE_C __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED) -#define PAGE_SHARED_C __pgprot(_PAGE_PRESENT | _PAGE_ACCESSED) -#define PAGE_COPY_C __pgprot(_PAGE_PRESENT | _PAGE_RONLY | _PAGE_ACCESSED) -#define PAGE_READONLY_C __pgprot(_PAGE_PRESENT | _PAGE_RONLY | _PAGE_ACCESSED) - -/* - * The m68k can't do page protection for execute, and considers that the same are read. - * Also, write permissions imply read permissions. This is the closest we can get.. - */ -#define __P000 PAGE_NONE_C -#define __P001 PAGE_READONLY_C -#define __P010 PAGE_COPY_C -#define __P011 PAGE_COPY_C -#define __P100 PAGE_READONLY_C -#define __P101 PAGE_READONLY_C -#define __P110 PAGE_COPY_C -#define __P111 PAGE_COPY_C - -#define __S000 PAGE_NONE_C -#define __S001 PAGE_READONLY_C -#define __S010 PAGE_SHARED_C -#define __S011 PAGE_SHARED_C -#define __S100 PAGE_READONLY_C -#define __S101 PAGE_READONLY_C -#define __S110 PAGE_SHARED_C -#define __S111 PAGE_SHARED_C - #define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd)) /* diff --git a/arch/m68k/include/asm/sun3_pgtable.h b/arch/m68k/include/asm/sun3_pgtable.h index 5e4e753f0d24..90d57e537eb1 100644 --- a/arch/m68k/include/asm/sun3_pgtable.h +++ b/arch/m68k/include/asm/sun3_pgtable.h @@ -66,29 +66,6 @@ | SUN3_PAGE_SYSTEM \ | SUN3_PAGE_NOCACHE) -/* - * Page protections for initialising protection_map. The sun3 has only two - * protection settings, valid (implying read and execute) and writeable. These - * are as close as we can get... - */ -#define __P000 PAGE_NONE -#define __P001 PAGE_READONLY -#define __P010 PAGE_COPY -#define __P011 PAGE_COPY -#define __P100 PAGE_READONLY -#define __P101 PAGE_READONLY -#define __P110 PAGE_COPY -#define __P111 PAGE_COPY - -#define __S000 PAGE_NONE -#define __S001 PAGE_READONLY -#define __S010 PAGE_SHARED -#define __S011 PAGE_SHARED -#define __S100 PAGE_READONLY -#define __S101 PAGE_READONLY -#define __S110 PAGE_SHARED -#define __S111 PAGE_SHARED - /* Use these fake page-protections on PMDs. */ #define SUN3_PMD_VALID (0x00000001) #define SUN3_PMD_MASK (0x0000003F) diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index 71aa9f6315dc..4d2837eb3e2a 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -141,6 +141,10 @@ good_area: if (fault_signal_pending(fault, regs)) return 0; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index 6f1f25125294..70aa0979e027 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -234,3 +234,58 @@ void steal_context(void) destroy_context(mm); } +static const pgprot_t protection_map[16] = { + [VM_NONE] = PAGE_NONE, + [VM_READ] = __pgprot(CF_PAGE_VALID | + CF_PAGE_ACCESSED | + CF_PAGE_READABLE), + [VM_WRITE] = __pgprot(CF_PAGE_VALID | + CF_PAGE_ACCESSED | + CF_PAGE_WRITABLE), + [VM_WRITE | VM_READ] = __pgprot(CF_PAGE_VALID | + CF_PAGE_ACCESSED | + CF_PAGE_READABLE | + CF_PAGE_WRITABLE), + [VM_EXEC] = __pgprot(CF_PAGE_VALID | + CF_PAGE_ACCESSED | + CF_PAGE_EXEC), + [VM_EXEC | VM_READ] = __pgprot(CF_PAGE_VALID | + CF_PAGE_ACCESSED | + CF_PAGE_READABLE | + CF_PAGE_EXEC), + [VM_EXEC | VM_WRITE] = __pgprot(CF_PAGE_VALID | + CF_PAGE_ACCESSED | + CF_PAGE_WRITABLE | + CF_PAGE_EXEC), + [VM_EXEC | VM_WRITE | VM_READ] = __pgprot(CF_PAGE_VALID | + CF_PAGE_ACCESSED | + CF_PAGE_READABLE | + CF_PAGE_WRITABLE | + CF_PAGE_EXEC), + [VM_SHARED] = PAGE_NONE, + [VM_SHARED | VM_READ] = __pgprot(CF_PAGE_VALID | + CF_PAGE_ACCESSED | + CF_PAGE_READABLE), + [VM_SHARED | VM_WRITE] = PAGE_SHARED, + [VM_SHARED | VM_WRITE | VM_READ] = __pgprot(CF_PAGE_VALID | + CF_PAGE_ACCESSED | + CF_PAGE_READABLE | + CF_PAGE_SHARED), + [VM_SHARED | VM_EXEC] = __pgprot(CF_PAGE_VALID | + CF_PAGE_ACCESSED | + CF_PAGE_EXEC), + [VM_SHARED | VM_EXEC | VM_READ] = __pgprot(CF_PAGE_VALID | + CF_PAGE_ACCESSED | + CF_PAGE_READABLE | + CF_PAGE_EXEC), + [VM_SHARED | VM_EXEC | VM_WRITE] = __pgprot(CF_PAGE_VALID | + CF_PAGE_ACCESSED | + CF_PAGE_SHARED | + CF_PAGE_EXEC), + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = __pgprot(CF_PAGE_VALID | + CF_PAGE_ACCESSED | + CF_PAGE_READABLE | + CF_PAGE_SHARED | + CF_PAGE_EXEC) +}; +DECLARE_VM_GET_PAGE_PROT diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c index df7f797c908a..2a375637e007 100644 --- a/arch/m68k/mm/motorola.c +++ b/arch/m68k/mm/motorola.c @@ -383,6 +383,35 @@ static void __init map_node(int node) } /* + * Alternate definitions that are compile time constants, for + * initializing protection_map. The cachebits are fixed later. + */ +#define PAGE_NONE_C __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED) +#define PAGE_SHARED_C __pgprot(_PAGE_PRESENT | _PAGE_ACCESSED) +#define PAGE_COPY_C __pgprot(_PAGE_PRESENT | _PAGE_RONLY | _PAGE_ACCESSED) +#define PAGE_READONLY_C __pgprot(_PAGE_PRESENT | _PAGE_RONLY | _PAGE_ACCESSED) + +static pgprot_t protection_map[16] __ro_after_init = { + [VM_NONE] = PAGE_NONE_C, + [VM_READ] = PAGE_READONLY_C, + [VM_WRITE] = PAGE_COPY_C, + [VM_WRITE | VM_READ] = PAGE_COPY_C, + [VM_EXEC] = PAGE_READONLY_C, + [VM_EXEC | VM_READ] = PAGE_READONLY_C, + [VM_EXEC | VM_WRITE] = PAGE_COPY_C, + [VM_EXEC | VM_WRITE | VM_READ] = PAGE_COPY_C, + [VM_SHARED] = PAGE_NONE_C, + [VM_SHARED | VM_READ] = PAGE_READONLY_C, + [VM_SHARED | VM_WRITE] = PAGE_SHARED_C, + [VM_SHARED | VM_WRITE | VM_READ] = PAGE_SHARED_C, + [VM_SHARED | VM_EXEC] = PAGE_READONLY_C, + [VM_SHARED | VM_EXEC | VM_READ] = PAGE_READONLY_C, + [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_SHARED_C, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_SHARED_C +}; +DECLARE_VM_GET_PAGE_PROT + +/* * paging_init() continues the virtual memory environment setup which * was begun by the code in arch/head.S. */ diff --git a/arch/m68k/mm/sun3mmu.c b/arch/m68k/mm/sun3mmu.c index dad494224497..b619d0d4319c 100644 --- a/arch/m68k/mm/sun3mmu.c +++ b/arch/m68k/mm/sun3mmu.c @@ -95,3 +95,23 @@ void __init paging_init(void) } + +static const pgprot_t protection_map[16] = { + [VM_NONE] = PAGE_NONE, + [VM_READ] = PAGE_READONLY, + [VM_WRITE] = PAGE_COPY, + [VM_WRITE | VM_READ] = PAGE_COPY, + [VM_EXEC] = PAGE_READONLY, + [VM_EXEC | VM_READ] = PAGE_READONLY, + [VM_EXEC | VM_WRITE] = PAGE_COPY, + [VM_EXEC | VM_WRITE | VM_READ] = PAGE_COPY, + [VM_SHARED] = PAGE_NONE, + [VM_SHARED | VM_READ] = PAGE_READONLY, + [VM_SHARED | VM_WRITE] = PAGE_SHARED, + [VM_SHARED | VM_WRITE | VM_READ] = PAGE_SHARED, + [VM_SHARED | VM_EXEC] = PAGE_READONLY, + [VM_SHARED | VM_EXEC | VM_READ] = PAGE_READONLY, + [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_SHARED, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_SHARED +}; +DECLARE_VM_GET_PAGE_PROT diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h index 0c72646370e1..ba348e997dbb 100644 --- a/arch/microblaze/include/asm/pgtable.h +++ b/arch/microblaze/include/asm/pgtable.h @@ -204,23 +204,6 @@ extern pte_t *va_to_pte(unsigned long address); * We consider execute permission the same as read. * Also, write permissions imply read permissions. */ -#define __P000 PAGE_NONE -#define __P001 PAGE_READONLY_X -#define __P010 PAGE_COPY -#define __P011 PAGE_COPY_X -#define __P100 PAGE_READONLY -#define __P101 PAGE_READONLY_X -#define __P110 PAGE_COPY -#define __P111 PAGE_COPY_X - -#define __S000 PAGE_NONE -#define __S001 PAGE_READONLY_X -#define __S010 PAGE_SHARED -#define __S011 PAGE_SHARED_X -#define __S100 PAGE_READONLY -#define __S101 PAGE_READONLY_X -#define __S110 PAGE_SHARED -#define __S111 PAGE_SHARED_X #ifndef __ASSEMBLY__ /* diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index a9626e6a68af..5c40c3ebe52f 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -222,6 +222,10 @@ good_area: if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index f4e503461d24..353fabdfcbc5 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -285,3 +285,23 @@ void * __ref zalloc_maybe_bootmem(size_t size, gfp_t mask) return p; } + +static const pgprot_t protection_map[16] = { + [VM_NONE] = PAGE_NONE, + [VM_READ] = PAGE_READONLY_X, + [VM_WRITE] = PAGE_COPY, + [VM_WRITE | VM_READ] = PAGE_COPY_X, + [VM_EXEC] = PAGE_READONLY, + [VM_EXEC | VM_READ] = PAGE_READONLY_X, + [VM_EXEC | VM_WRITE] = PAGE_COPY, + [VM_EXEC | VM_WRITE | VM_READ] = PAGE_COPY_X, + [VM_SHARED] = PAGE_NONE, + [VM_SHARED | VM_READ] = PAGE_READONLY_X, + [VM_SHARED | VM_WRITE] = PAGE_SHARED, + [VM_SHARED | VM_WRITE | VM_READ] = PAGE_SHARED_X, + [VM_SHARED | VM_EXEC] = PAGE_READONLY, + [VM_SHARED | VM_EXEC | VM_READ] = PAGE_READONLY_X, + [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_SHARED, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_SHARED_X +}; +DECLARE_VM_GET_PAGE_PROT diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h index 867e9c3db76e..796035784c73 100644 --- a/arch/mips/include/asm/pgalloc.h +++ b/arch/mips/include/asm/pgalloc.h @@ -51,7 +51,7 @@ extern pgd_t *pgd_alloc(struct mm_struct *mm); static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { - free_pages((unsigned long)pgd, PGD_ORDER); + free_pages((unsigned long)pgd, PGD_TABLE_ORDER); } #define __pte_free_tlb(tlb,pte,address) \ @@ -67,12 +67,12 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) pmd_t *pmd; struct page *pg; - pg = alloc_pages(GFP_KERNEL_ACCOUNT, PMD_ORDER); + pg = alloc_pages(GFP_KERNEL_ACCOUNT, PMD_TABLE_ORDER); if (!pg) return NULL; if (!pgtable_pmd_page_ctor(pg)) { - __free_pages(pg, PMD_ORDER); + __free_pages(pg, PMD_TABLE_ORDER); return NULL; } @@ -91,7 +91,7 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) { pud_t *pud; - pud = (pud_t *) __get_free_pages(GFP_KERNEL, PUD_ORDER); + pud = (pud_t *) __get_free_pages(GFP_KERNEL, PUD_TABLE_ORDER); if (pud) pud_init((unsigned long)pud, (unsigned long)invalid_pmd_table); return pud; diff --git a/arch/mips/include/asm/pgtable-32.h b/arch/mips/include/asm/pgtable-32.h index 95df9c293d8d..495c603c1a30 100644 --- a/arch/mips/include/asm/pgtable-32.h +++ b/arch/mips/include/asm/pgtable-32.h @@ -62,9 +62,9 @@ extern int add_temporary_entry(unsigned long entrylo0, unsigned long entrylo1, /* PGDIR_SHIFT determines what a third-level page table entry can map */ #if defined(CONFIG_MIPS_HUGE_TLB_SUPPORT) && !defined(CONFIG_PHYS_ADDR_T_64BIT) -# define PGDIR_SHIFT (2 * PAGE_SHIFT + PTE_ORDER - PTE_T_LOG2 - 1) +# define PGDIR_SHIFT (2 * PAGE_SHIFT - PTE_T_LOG2 - 1) #else -# define PGDIR_SHIFT (2 * PAGE_SHIFT + PTE_ORDER - PTE_T_LOG2) +# define PGDIR_SHIFT (2 * PAGE_SHIFT - PTE_T_LOG2) #endif #define PGDIR_SIZE (1UL << PGDIR_SHIFT) @@ -75,21 +75,20 @@ extern int add_temporary_entry(unsigned long entrylo0, unsigned long entrylo1, * we don't really have any PUD/PMD directory physically. */ #if defined(CONFIG_MIPS_HUGE_TLB_SUPPORT) && !defined(CONFIG_PHYS_ADDR_T_64BIT) -# define __PGD_ORDER (32 - 3 * PAGE_SHIFT + PGD_T_LOG2 + PTE_T_LOG2 + 1) +# define __PGD_TABLE_ORDER (32 - 3 * PAGE_SHIFT + PGD_T_LOG2 + PTE_T_LOG2 + 1) #else -# define __PGD_ORDER (32 - 3 * PAGE_SHIFT + PGD_T_LOG2 + PTE_T_LOG2) +# define __PGD_TABLE_ORDER (32 - 3 * PAGE_SHIFT + PGD_T_LOG2 + PTE_T_LOG2) #endif -#define PGD_ORDER (__PGD_ORDER >= 0 ? __PGD_ORDER : 0) -#define PUD_ORDER aieeee_attempt_to_allocate_pud -#define PMD_ORDER aieeee_attempt_to_allocate_pmd -#define PTE_ORDER 0 +#define PGD_TABLE_ORDER (__PGD_TABLE_ORDER >= 0 ? __PGD_TABLE_ORDER : 0) +#define PUD_TABLE_ORDER aieeee_attempt_to_allocate_pud +#define PMD_TABLE_ORDER aieeee_attempt_to_allocate_pmd #define PTRS_PER_PGD (USER_PTRS_PER_PGD * 2) #if defined(CONFIG_MIPS_HUGE_TLB_SUPPORT) && !defined(CONFIG_PHYS_ADDR_T_64BIT) -# define PTRS_PER_PTE ((PAGE_SIZE << PTE_ORDER) / sizeof(pte_t) / 2) +# define PTRS_PER_PTE (PAGE_SIZE / sizeof(pte_t) / 2) #else -# define PTRS_PER_PTE ((PAGE_SIZE << PTE_ORDER) / sizeof(pte_t)) +# define PTRS_PER_PTE (PAGE_SIZE / sizeof(pte_t)) #endif #define USER_PTRS_PER_PGD (0x80000000UL/PGDIR_SIZE) diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h index 41921acdc9d8..a259ca4d1272 100644 --- a/arch/mips/include/asm/pgtable-64.h +++ b/arch/mips/include/asm/pgtable-64.h @@ -42,24 +42,24 @@ /* PGDIR_SHIFT determines what a third-level page table entry can map */ #ifdef __PAGETABLE_PMD_FOLDED -#define PGDIR_SHIFT (PAGE_SHIFT + PAGE_SHIFT + PTE_ORDER - 3) +#define PGDIR_SHIFT (PAGE_SHIFT + PAGE_SHIFT - 3) #else /* PMD_SHIFT determines the size of the area a second-level page table can map */ -#define PMD_SHIFT (PAGE_SHIFT + (PAGE_SHIFT + PTE_ORDER - 3)) +#define PMD_SHIFT (PAGE_SHIFT + (PAGE_SHIFT - 3)) #define PMD_SIZE (1UL << PMD_SHIFT) #define PMD_MASK (~(PMD_SIZE-1)) # ifdef __PAGETABLE_PUD_FOLDED -# define PGDIR_SHIFT (PMD_SHIFT + (PAGE_SHIFT + PMD_ORDER - 3)) +# define PGDIR_SHIFT (PMD_SHIFT + (PAGE_SHIFT + PMD_TABLE_ORDER - 3)) # endif #endif #ifndef __PAGETABLE_PUD_FOLDED -#define PUD_SHIFT (PMD_SHIFT + (PAGE_SHIFT + PMD_ORDER - 3)) +#define PUD_SHIFT (PMD_SHIFT + (PAGE_SHIFT + PMD_TABLE_ORDER - 3)) #define PUD_SIZE (1UL << PUD_SHIFT) #define PUD_MASK (~(PUD_SIZE-1)) -#define PGDIR_SHIFT (PUD_SHIFT + (PAGE_SHIFT + PUD_ORDER - 3)) +#define PGDIR_SHIFT (PUD_SHIFT + (PAGE_SHIFT + PUD_TABLE_ORDER - 3)) #endif #define PGDIR_SIZE (1UL << PGDIR_SHIFT) @@ -85,56 +85,51 @@ */ #ifdef CONFIG_PAGE_SIZE_4KB # ifdef CONFIG_MIPS_VA_BITS_48 -# define PGD_ORDER 0 -# define PUD_ORDER 0 +# define PGD_TABLE_ORDER 0 +# define PUD_TABLE_ORDER 0 # else -# define PGD_ORDER 1 -# define PUD_ORDER aieeee_attempt_to_allocate_pud +# define PGD_TABLE_ORDER 1 +# define PUD_TABLE_ORDER aieeee_attempt_to_allocate_pud # endif -#define PMD_ORDER 0 -#define PTE_ORDER 0 +#define PMD_TABLE_ORDER 0 #endif #ifdef CONFIG_PAGE_SIZE_8KB -#define PGD_ORDER 0 -#define PUD_ORDER aieeee_attempt_to_allocate_pud -#define PMD_ORDER 0 -#define PTE_ORDER 0 +#define PGD_TABLE_ORDER 0 +#define PUD_TABLE_ORDER aieeee_attempt_to_allocate_pud +#define PMD_TABLE_ORDER 0 #endif #ifdef CONFIG_PAGE_SIZE_16KB #ifdef CONFIG_MIPS_VA_BITS_48 -#define PGD_ORDER 1 +#define PGD_TABLE_ORDER 1 #else -#define PGD_ORDER 0 +#define PGD_TABLE_ORDER 0 #endif -#define PUD_ORDER aieeee_attempt_to_allocate_pud -#define PMD_ORDER 0 -#define PTE_ORDER 0 +#define PUD_TABLE_ORDER aieeee_attempt_to_allocate_pud +#define PMD_TABLE_ORDER 0 #endif #ifdef CONFIG_PAGE_SIZE_32KB -#define PGD_ORDER 0 -#define PUD_ORDER aieeee_attempt_to_allocate_pud -#define PMD_ORDER 0 -#define PTE_ORDER 0 +#define PGD_TABLE_ORDER 0 +#define PUD_TABLE_ORDER aieeee_attempt_to_allocate_pud +#define PMD_TABLE_ORDER 0 #endif #ifdef CONFIG_PAGE_SIZE_64KB -#define PGD_ORDER 0 -#define PUD_ORDER aieeee_attempt_to_allocate_pud +#define PGD_TABLE_ORDER 0 +#define PUD_TABLE_ORDER aieeee_attempt_to_allocate_pud #ifdef CONFIG_MIPS_VA_BITS_48 -#define PMD_ORDER 0 +#define PMD_TABLE_ORDER 0 #else -#define PMD_ORDER aieeee_attempt_to_allocate_pmd +#define PMD_TABLE_ORDER aieeee_attempt_to_allocate_pmd #endif -#define PTE_ORDER 0 #endif -#define PTRS_PER_PGD ((PAGE_SIZE << PGD_ORDER) / sizeof(pgd_t)) +#define PTRS_PER_PGD ((PAGE_SIZE << PGD_TABLE_ORDER) / sizeof(pgd_t)) #ifndef __PAGETABLE_PUD_FOLDED -#define PTRS_PER_PUD ((PAGE_SIZE << PUD_ORDER) / sizeof(pud_t)) +#define PTRS_PER_PUD ((PAGE_SIZE << PUD_TABLE_ORDER) / sizeof(pud_t)) #endif #ifndef __PAGETABLE_PMD_FOLDED -#define PTRS_PER_PMD ((PAGE_SIZE << PMD_ORDER) / sizeof(pmd_t)) +#define PTRS_PER_PMD ((PAGE_SIZE << PMD_TABLE_ORDER) / sizeof(pmd_t)) #endif -#define PTRS_PER_PTE ((PAGE_SIZE << PTE_ORDER) / sizeof(pte_t)) +#define PTRS_PER_PTE (PAGE_SIZE / sizeof(pte_t)) #define USER_PTRS_PER_PGD ((TASK_SIZE64 / PGDIR_SIZE)?(TASK_SIZE64 / PGDIR_SIZE):1) diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 374c6322775d..6caec386ad2f 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -41,28 +41,6 @@ struct vm_area_struct; * by reasonable means.. */ -/* - * Dummy values to fill the table in mmap.c - * The real values will be generated at runtime - */ -#define __P000 __pgprot(0) -#define __P001 __pgprot(0) -#define __P010 __pgprot(0) -#define __P011 __pgprot(0) -#define __P100 __pgprot(0) -#define __P101 __pgprot(0) -#define __P110 __pgprot(0) -#define __P111 __pgprot(0) - -#define __S000 __pgprot(0) -#define __S001 __pgprot(0) -#define __S010 __pgprot(0) -#define __S011 __pgprot(0) -#define __S100 __pgprot(0) -#define __S101 __pgprot(0) -#define __S110 __pgprot(0) -#define __S111 __pgprot(0) - extern unsigned long _page_cachable_default; extern void __update_cache(unsigned long address, pte_t pte); diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c index 04ca75278f02..c4501897b870 100644 --- a/arch/mips/kernel/asm-offsets.c +++ b/arch/mips/kernel/asm-offsets.c @@ -196,11 +196,6 @@ void output_mm_defines(void) #endif DEFINE(_PTE_T_LOG2, PTE_T_LOG2); BLANK(); - DEFINE(_PGD_ORDER, PGD_ORDER); -#ifndef __PAGETABLE_PMD_FOLDED - DEFINE(_PMD_ORDER, PMD_ORDER); -#endif - DEFINE(_PTE_ORDER, PTE_ORDER); BLANK(); DEFINE(_PMD_SHIFT, PMD_SHIFT); DEFINE(_PGDIR_SHIFT, PGDIR_SHIFT); diff --git a/arch/mips/kernel/mips-mt.c b/arch/mips/kernel/mips-mt.c index d5f7362e8c24..dc023a979803 100644 --- a/arch/mips/kernel/mips-mt.c +++ b/arch/mips/kernel/mips-mt.c @@ -230,7 +230,7 @@ void mips_mt_set_cpuoptions(void) struct class *mt_class; -static int __init mt_init(void) +static int __init mips_mt_init(void) { struct class *mtc; @@ -243,4 +243,4 @@ static int __init mt_init(void) return 0; } -subsys_initcall(mt_init); +subsys_initcall(mips_mt_init); diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index 1bfd1b501d82..db17e870bdff 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -80,7 +80,7 @@ pgd_t *kvm_pgd_alloc(void) { pgd_t *ret; - ret = (pgd_t *)__get_free_pages(GFP_KERNEL, PGD_ORDER); + ret = (pgd_t *)__get_free_pages(GFP_KERNEL, PGD_TABLE_ORDER); if (ret) kvm_pgd_init(ret); diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c index 7be7240f7703..11b3e7ddafd5 100644 --- a/arch/mips/mm/cache.c +++ b/arch/mips/mm/cache.c @@ -159,6 +159,9 @@ EXPORT_SYMBOL(_page_cachable_default); #define PM(p) __pgprot(_page_cachable_default | (p)) +static pgprot_t protection_map[16] __ro_after_init; +DECLARE_VM_GET_PAGE_PROT + static inline void setup_protection_map(void) { protection_map[0] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ); diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index b08bc556d30d..a27045f5a556 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -162,6 +162,10 @@ good_area: return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/mips/mm/pgtable.c b/arch/mips/mm/pgtable.c index 05560b042d82..3b7590660a04 100644 --- a/arch/mips/mm/pgtable.c +++ b/arch/mips/mm/pgtable.c @@ -12,7 +12,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *ret, *init; - ret = (pgd_t *) __get_free_pages(GFP_KERNEL, PGD_ORDER); + ret = (pgd_t *) __get_free_pages(GFP_KERNEL, PGD_TABLE_ORDER); if (ret) { init = pgd_offset(&init_mm, 0UL); pgd_init((unsigned long)ret); diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 8dbbd99fc7e8..a57519ae96b1 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -818,7 +818,7 @@ void build_get_pmde64(u32 **p, struct uasm_label **l, struct uasm_reloc **r, * everything but the lower xuseg addresses goes down * the module_alloc/vmalloc path. */ - uasm_i_dsrl_safe(p, ptr, tmp, PGDIR_SHIFT + PGD_ORDER + PAGE_SHIFT - 3); + uasm_i_dsrl_safe(p, ptr, tmp, PGDIR_SHIFT + PGD_TABLE_ORDER + PAGE_SHIFT - 3); uasm_il_bnez(p, r, ptr, label_vmalloc); } else { uasm_il_bltz(p, r, tmp, label_vmalloc); @@ -1127,7 +1127,7 @@ build_fast_tlb_refill_handler (u32 **p, struct uasm_label **l, UASM_i_SW(p, scratch, scratchpad_offset(0), 0); uasm_i_dsrl_safe(p, scratch, tmp, - PGDIR_SHIFT + PGD_ORDER + PAGE_SHIFT - 3); + PGDIR_SHIFT + PGD_TABLE_ORDER + PAGE_SHIFT - 3); uasm_il_bnez(p, r, scratch, label_vmalloc); if (pgd_reg == -1) { @@ -1493,12 +1493,12 @@ static void setup_pw(void) #endif pgd_i = PGDIR_SHIFT; /* 1st level PGD */ #ifndef __PAGETABLE_PMD_FOLDED - pgd_w = PGDIR_SHIFT - PMD_SHIFT + PGD_ORDER; + pgd_w = PGDIR_SHIFT - PMD_SHIFT + PGD_TABLE_ORDER; pmd_i = PMD_SHIFT; /* 2nd level PMD */ pmd_w = PMD_SHIFT - PAGE_SHIFT; #else - pgd_w = PGDIR_SHIFT - PAGE_SHIFT + PGD_ORDER; + pgd_w = PGDIR_SHIFT - PAGE_SHIFT + PGD_TABLE_ORDER; #endif pt_i = PAGE_SHIFT; /* 3rd level PTE */ @@ -1536,7 +1536,7 @@ static void build_loongson3_tlb_refill_handler(void) if (check_for_high_segbits) { uasm_i_dmfc0(&p, K0, C0_BADVADDR); - uasm_i_dsrl_safe(&p, K1, K0, PGDIR_SHIFT + PGD_ORDER + PAGE_SHIFT - 3); + uasm_i_dsrl_safe(&p, K1, K0, PGDIR_SHIFT + PGD_TABLE_ORDER + PAGE_SHIFT - 3); uasm_il_beqz(&p, &r, K1, label_vmalloc); uasm_i_nop(&p); @@ -2065,7 +2065,7 @@ build_r4000_tlbchange_handler_head(u32 **p, struct uasm_label **l, UASM_i_MFC0(p, wr.r1, C0_BADVADDR); UASM_i_LW(p, wr.r2, 0, wr.r2); - UASM_i_SRL(p, wr.r1, wr.r1, PAGE_SHIFT + PTE_ORDER - PTE_T_LOG2); + UASM_i_SRL(p, wr.r1, wr.r1, PAGE_SHIFT - PTE_T_LOG2); uasm_i_andi(p, wr.r1, wr.r1, (PTRS_PER_PTE - 1) << PTE_T_LOG2); UASM_i_ADDU(p, wr.r2, wr.r2, wr.r1); @@ -2611,7 +2611,7 @@ void build_tlb_refill_handler(void) check_pabits(); #ifdef CONFIG_64BIT - check_for_high_segbits = current_cpu_data.vmbits > (PGDIR_SHIFT + PGD_ORDER + PAGE_SHIFT - 3); + check_for_high_segbits = current_cpu_data.vmbits > (PGDIR_SHIFT + PGD_TABLE_ORDER + PAGE_SHIFT - 3); #endif if (cpu_has_3kex) { diff --git a/arch/nios2/include/asm/pgtable.h b/arch/nios2/include/asm/pgtable.h index 262d0609268c..b3d45e815295 100644 --- a/arch/nios2/include/asm/pgtable.h +++ b/arch/nios2/include/asm/pgtable.h @@ -40,24 +40,8 @@ struct mm_struct; */ /* Remove W bit on private pages for COW support */ -#define __P000 MKP(0, 0, 0) -#define __P001 MKP(0, 0, 1) -#define __P010 MKP(0, 0, 0) /* COW */ -#define __P011 MKP(0, 0, 1) /* COW */ -#define __P100 MKP(1, 0, 0) -#define __P101 MKP(1, 0, 1) -#define __P110 MKP(1, 0, 0) /* COW */ -#define __P111 MKP(1, 0, 1) /* COW */ /* Shared pages can have exact HW mapping */ -#define __S000 MKP(0, 0, 0) -#define __S001 MKP(0, 0, 1) -#define __S010 MKP(0, 1, 0) -#define __S011 MKP(0, 1, 1) -#define __S100 MKP(1, 0, 0) -#define __S101 MKP(1, 0, 1) -#define __S110 MKP(1, 1, 0) -#define __S111 MKP(1, 1, 1) /* Used all over the kernel */ #define PAGE_KERNEL __pgprot(_PAGE_PRESENT | _PAGE_CACHED | _PAGE_READ | \ @@ -68,11 +52,8 @@ struct mm_struct; #define PAGE_COPY MKP(0, 0, 1) -#define PGD_ORDER 0 -#define PTE_ORDER 0 - -#define PTRS_PER_PGD ((PAGE_SIZE << PGD_ORDER) / sizeof(pgd_t)) -#define PTRS_PER_PTE ((PAGE_SIZE << PTE_ORDER) / sizeof(pte_t)) +#define PTRS_PER_PGD (PAGE_SIZE / sizeof(pgd_t)) +#define PTRS_PER_PTE (PAGE_SIZE / sizeof(pte_t)) #define USER_PTRS_PER_PGD \ (CONFIG_NIOS2_KERNEL_MMU_REGION_BASE / PGDIR_SIZE) diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c index a32f14cd72f2..edaca0a6c1c1 100644 --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -139,6 +139,10 @@ good_area: if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/nios2/mm/init.c b/arch/nios2/mm/init.c index 613fcaa5988a..7bc82ee889c9 100644 --- a/arch/nios2/mm/init.c +++ b/arch/nios2/mm/init.c @@ -78,9 +78,8 @@ void __init mmu_init(void) flush_tlb_all(); } -#define __page_aligned(order) __aligned(PAGE_SIZE << (order)) -pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned(PGD_ORDER); -pte_t invalid_pte_table[PTRS_PER_PTE] __page_aligned(PTE_ORDER); +pgd_t swapper_pg_dir[PTRS_PER_PGD] __aligned(PAGE_SIZE); +pte_t invalid_pte_table[PTRS_PER_PTE] __aligned(PAGE_SIZE); static struct page *kuser_page[1]; static int alloc_kuser_page(void) @@ -124,3 +123,23 @@ const char *arch_vma_name(struct vm_area_struct *vma) { return (vma->vm_start == KUSER_BASE) ? "[kuser]" : NULL; } + +static const pgprot_t protection_map[16] = { + [VM_NONE] = MKP(0, 0, 0), + [VM_READ] = MKP(0, 0, 1), + [VM_WRITE] = MKP(0, 0, 0), + [VM_WRITE | VM_READ] = MKP(0, 0, 1), + [VM_EXEC] = MKP(1, 0, 0), + [VM_EXEC | VM_READ] = MKP(1, 0, 1), + [VM_EXEC | VM_WRITE] = MKP(1, 0, 0), + [VM_EXEC | VM_WRITE | VM_READ] = MKP(1, 0, 1), + [VM_SHARED] = MKP(0, 0, 0), + [VM_SHARED | VM_READ] = MKP(0, 0, 1), + [VM_SHARED | VM_WRITE] = MKP(0, 1, 0), + [VM_SHARED | VM_WRITE | VM_READ] = MKP(0, 1, 1), + [VM_SHARED | VM_EXEC] = MKP(1, 0, 0), + [VM_SHARED | VM_EXEC | VM_READ] = MKP(1, 0, 1), + [VM_SHARED | VM_EXEC | VM_WRITE] = MKP(1, 1, 0), + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = MKP(1, 1, 1) +}; +DECLARE_VM_GET_PAGE_PROT diff --git a/arch/nios2/mm/pgtable.c b/arch/nios2/mm/pgtable.c index 9b587fd592dd..7c76e8a7447a 100644 --- a/arch/nios2/mm/pgtable.c +++ b/arch/nios2/mm/pgtable.c @@ -54,7 +54,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *ret, *init; - ret = (pgd_t *) __get_free_pages(GFP_KERNEL, PGD_ORDER); + ret = (pgd_t *) __get_free_page(GFP_KERNEL); if (ret) { init = pgd_offset(&init_mm, 0UL); pgd_init(ret); diff --git a/arch/openrisc/include/asm/pgtable.h b/arch/openrisc/include/asm/pgtable.h index c3abbf71e09f..dcae8aea132f 100644 --- a/arch/openrisc/include/asm/pgtable.h +++ b/arch/openrisc/include/asm/pgtable.h @@ -176,24 +176,6 @@ extern void paging_init(void); __pgprot(_PAGE_ALL | _PAGE_SRE | _PAGE_SWE \ | _PAGE_SHARED | _PAGE_DIRTY | _PAGE_EXEC | _PAGE_CI) -#define __P000 PAGE_NONE -#define __P001 PAGE_READONLY_X -#define __P010 PAGE_COPY -#define __P011 PAGE_COPY_X -#define __P100 PAGE_READONLY -#define __P101 PAGE_READONLY_X -#define __P110 PAGE_COPY -#define __P111 PAGE_COPY_X - -#define __S000 PAGE_NONE -#define __S001 PAGE_READONLY_X -#define __S010 PAGE_SHARED -#define __S011 PAGE_SHARED_X -#define __S100 PAGE_READONLY -#define __S101 PAGE_READONLY_X -#define __S110 PAGE_SHARED -#define __S111 PAGE_SHARED_X - /* zero page used for uninitialized stuff */ extern unsigned long empty_zero_page[2048]; #define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index 53b760af3bb7..b4762d66e9ef 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -165,6 +165,10 @@ good_area: if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c index 3a021ab6f1ae..d531ab82be12 100644 --- a/arch/openrisc/mm/init.c +++ b/arch/openrisc/mm/init.c @@ -208,3 +208,23 @@ void __init mem_init(void) mem_init_done = 1; return; } + +static const pgprot_t protection_map[16] = { + [VM_NONE] = PAGE_NONE, + [VM_READ] = PAGE_READONLY_X, + [VM_WRITE] = PAGE_COPY, + [VM_WRITE | VM_READ] = PAGE_COPY_X, + [VM_EXEC] = PAGE_READONLY, + [VM_EXEC | VM_READ] = PAGE_READONLY_X, + [VM_EXEC | VM_WRITE] = PAGE_COPY, + [VM_EXEC | VM_WRITE | VM_READ] = PAGE_COPY_X, + [VM_SHARED] = PAGE_NONE, + [VM_SHARED | VM_READ] = PAGE_READONLY_X, + [VM_SHARED | VM_WRITE] = PAGE_SHARED, + [VM_SHARED | VM_WRITE | VM_READ] = PAGE_SHARED_X, + [VM_SHARED | VM_EXEC] = PAGE_READONLY, + [VM_SHARED | VM_EXEC | VM_READ] = PAGE_READONLY_X, + [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_SHARED, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_SHARED_X +}; +DECLARE_VM_GET_PAGE_PROT diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h index 54b63374579b..e3e142b1c5c5 100644 --- a/arch/parisc/include/asm/pgalloc.h +++ b/arch/parisc/include/asm/pgalloc.h @@ -20,18 +20,18 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *pgd; - pgd = (pgd_t *) __get_free_pages(GFP_KERNEL, PGD_ORDER); + pgd = (pgd_t *) __get_free_pages(GFP_KERNEL, PGD_TABLE_ORDER); if (unlikely(pgd == NULL)) return NULL; - memset(pgd, 0, PAGE_SIZE << PGD_ORDER); + memset(pgd, 0, PAGE_SIZE << PGD_TABLE_ORDER); return pgd; } static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { - free_pages((unsigned long)pgd, PGD_ORDER); + free_pages((unsigned long)pgd, PGD_TABLE_ORDER); } #if CONFIG_PGTABLE_LEVELS == 3 diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 69765a6dbe89..df7b931865d2 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -118,9 +118,9 @@ extern void __update_cache(pte_t pte); #if CONFIG_PGTABLE_LEVELS == 3 #define PMD_TABLE_ORDER 1 -#define PGD_ORDER 0 +#define PGD_TABLE_ORDER 0 #else -#define PGD_ORDER 1 +#define PGD_TABLE_ORDER 1 #endif /* Definitions for 3rd level (we use PLD here for Page Lower directory @@ -144,10 +144,10 @@ extern void __update_cache(pte_t pte); /* Definitions for 1st level */ #define PGDIR_SHIFT (PLD_SHIFT + BITS_PER_PTE + BITS_PER_PMD) -#if (PGDIR_SHIFT + PAGE_SHIFT + PGD_ORDER - BITS_PER_PGD_ENTRY) > BITS_PER_LONG +#if (PGDIR_SHIFT + PAGE_SHIFT + PGD_TABLE_ORDER - BITS_PER_PGD_ENTRY) > BITS_PER_LONG #define BITS_PER_PGD (BITS_PER_LONG - PGDIR_SHIFT) #else -#define BITS_PER_PGD (PAGE_SHIFT + PGD_ORDER - BITS_PER_PGD_ENTRY) +#define BITS_PER_PGD (PAGE_SHIFT + PGD_TABLE_ORDER - BITS_PER_PGD_ENTRY) #endif #define PGDIR_SIZE (1UL << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE-1)) @@ -271,24 +271,6 @@ extern void __update_cache(pte_t pte); */ /*xwr*/ -#define __P000 PAGE_NONE -#define __P001 PAGE_READONLY -#define __P010 __P000 /* copy on write */ -#define __P011 __P001 /* copy on write */ -#define __P100 PAGE_EXECREAD -#define __P101 PAGE_EXECREAD -#define __P110 __P100 /* copy on write */ -#define __P111 __P101 /* copy on write */ - -#define __S000 PAGE_NONE -#define __S001 PAGE_READONLY -#define __S010 PAGE_WRITEONLY -#define __S011 PAGE_SHARED -#define __S100 PAGE_EXECREAD -#define __S101 PAGE_EXECREAD -#define __S110 PAGE_RWX -#define __S111 PAGE_RWX - extern pgd_t swapper_pg_dir[]; /* declared in init_task.c */ diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index c9d48bcdc933..869204e97ec9 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -311,6 +311,10 @@ good_area: if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { /* * We hit a shared mapping outside of the file, or some diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 8e2f7b8ceb70..b0c43f3b0a5f 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -871,3 +871,23 @@ void flush_tlb_all(void) spin_unlock(&sid_lock); } #endif + +static const pgprot_t protection_map[16] = { + [VM_NONE] = PAGE_NONE, + [VM_READ] = PAGE_READONLY, + [VM_WRITE] = PAGE_NONE, + [VM_WRITE | VM_READ] = PAGE_READONLY, + [VM_EXEC] = PAGE_EXECREAD, + [VM_EXEC | VM_READ] = PAGE_EXECREAD, + [VM_EXEC | VM_WRITE] = PAGE_EXECREAD, + [VM_EXEC | VM_WRITE | VM_READ] = PAGE_EXECREAD, + [VM_SHARED] = PAGE_NONE, + [VM_SHARED | VM_READ] = PAGE_READONLY, + [VM_SHARED | VM_WRITE] = PAGE_WRITEONLY, + [VM_SHARED | VM_WRITE | VM_READ] = PAGE_SHARED, + [VM_SHARED | VM_EXEC] = PAGE_EXECREAD, + [VM_SHARED | VM_EXEC | VM_READ] = PAGE_EXECREAD, + [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_RWX, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_RWX +}; +DECLARE_VM_GET_PAGE_PROT diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 88a738117312..af612d4c4bcc 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -140,7 +140,6 @@ config PPC select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UACCESS_FLUSHCACHE select ARCH_HAS_UBSAN_SANITIZE_ALL - select ARCH_HAS_VM_GET_PAGE_PROT if PPC_BOOK3S_64 select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_KEEP_MEMBLOCK select ARCH_MIGHT_HAVE_PC_PARPORT diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index cb9d5fd39d7f..392ff48f77df 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1273,7 +1273,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, * should return true. * We should not call this on a hugetlb entry. We should check for HugeTLB * entry using vma->vm_flags - * The page table walk rule is explained in Documentation/vm/transhuge.rst + * The page table walk rule is explained in Documentation/mm/transhuge.rst */ static inline int pmd_trans_huge(pmd_t pmd) { diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index d564d0ecd4cd..33f4bf8d22b0 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -20,25 +20,6 @@ struct mm_struct; #include <asm/nohash/pgtable.h> #endif /* !CONFIG_PPC_BOOK3S */ -/* Note due to the way vm flags are laid out, the bits are XWR */ -#define __P000 PAGE_NONE -#define __P001 PAGE_READONLY -#define __P010 PAGE_COPY -#define __P011 PAGE_COPY -#define __P100 PAGE_READONLY_X -#define __P101 PAGE_READONLY_X -#define __P110 PAGE_COPY_X -#define __P111 PAGE_COPY_X - -#define __S000 PAGE_NONE -#define __S001 PAGE_READONLY -#define __S010 PAGE_SHARED -#define __S011 PAGE_SHARED -#define __S100 PAGE_READONLY_X -#define __S101 PAGE_READONLY_X -#define __S110 PAGE_SHARED_X -#define __S111 PAGE_SHARED_X - #ifndef __ASSEMBLY__ #ifndef MAX_PTRS_PER_PGD @@ -79,6 +60,7 @@ extern void paging_init(void); void poking_init(void); extern unsigned long ioremap_bot; +extern const pgprot_t protection_map[16]; /* * kern_addr_valid is intended to indicate whether an address is a valid diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c index c1cb21a00884..7c507fb48182 100644 --- a/arch/powerpc/mm/copro_fault.c +++ b/arch/powerpc/mm/copro_fault.c @@ -65,6 +65,11 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, ret = 0; *flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0, NULL); + + /* The fault is fully completed (including releasing mmap lock) */ + if (*flt & VM_FAULT_COMPLETED) + return 0; + if (unlikely(*flt & VM_FAULT_ERROR)) { if (*flt & VM_FAULT_OOM) { ret = -ENOMEM; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index d53fed4eccbd..014005428687 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -511,6 +511,10 @@ retry: if (fault_signal_pending(fault, regs)) return user_mode(regs) ? 0 : SIGBUS; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + goto out; + /* * Handle the retry right now, the mmap_lock has been released in that * case. @@ -525,6 +529,7 @@ retry: if (unlikely(fault & VM_FAULT_ERROR)) return mm_fault_error(regs, address, fault); +out: /* * Major/minor page fault accounting. */ diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index e6166b71d36d..cb2dcdb18f8e 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -472,3 +472,27 @@ out: return ret_pte; } EXPORT_SYMBOL_GPL(__find_linux_pte); + +/* Note due to the way vm flags are laid out, the bits are XWR */ +const pgprot_t protection_map[16] = { + [VM_NONE] = PAGE_NONE, + [VM_READ] = PAGE_READONLY, + [VM_WRITE] = PAGE_COPY, + [VM_WRITE | VM_READ] = PAGE_COPY, + [VM_EXEC] = PAGE_READONLY_X, + [VM_EXEC | VM_READ] = PAGE_READONLY_X, + [VM_EXEC | VM_WRITE] = PAGE_COPY_X, + [VM_EXEC | VM_WRITE | VM_READ] = PAGE_COPY_X, + [VM_SHARED] = PAGE_NONE, + [VM_SHARED | VM_READ] = PAGE_READONLY, + [VM_SHARED | VM_WRITE] = PAGE_SHARED, + [VM_SHARED | VM_WRITE | VM_READ] = PAGE_SHARED, + [VM_SHARED | VM_EXEC] = PAGE_READONLY_X, + [VM_SHARED | VM_EXEC | VM_READ] = PAGE_READONLY_X, + [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_SHARED_X, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_SHARED_X +}; + +#ifndef CONFIG_PPC_BOOK3S_64 +DECLARE_VM_GET_PAGE_PROT +#endif diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 5dbd6610729b..7ec936910a96 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -186,26 +186,6 @@ extern struct pt_alloc_ops pt_ops __initdata; extern pgd_t swapper_pg_dir[]; -/* MAP_PRIVATE permissions: xwr (copy-on-write) */ -#define __P000 PAGE_NONE -#define __P001 PAGE_READ -#define __P010 PAGE_COPY -#define __P011 PAGE_COPY -#define __P100 PAGE_EXEC -#define __P101 PAGE_READ_EXEC -#define __P110 PAGE_COPY_EXEC -#define __P111 PAGE_COPY_READ_EXEC - -/* MAP_SHARED permissions: xwr */ -#define __S000 PAGE_NONE -#define __S001 PAGE_READ -#define __S010 PAGE_SHARED -#define __S011 PAGE_SHARED -#define __S100 PAGE_EXEC -#define __S101 PAGE_READ_EXEC -#define __S110 PAGE_SHARED_EXEC -#define __S111 PAGE_SHARED_EXEC - #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int pmd_present(pmd_t pmd) { diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 40694f0cab9e..f2fbd1400b7c 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -326,6 +326,10 @@ good_area: if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_RETRY)) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index d466ec670e1f..a88b7dc31a68 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -288,6 +288,26 @@ static pmd_t __maybe_unused early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAG #define early_pg_dir ((pgd_t *)XIP_FIXUP(early_pg_dir)) #endif /* CONFIG_XIP_KERNEL */ +static const pgprot_t protection_map[16] = { + [VM_NONE] = PAGE_NONE, + [VM_READ] = PAGE_READ, + [VM_WRITE] = PAGE_COPY, + [VM_WRITE | VM_READ] = PAGE_COPY, + [VM_EXEC] = PAGE_EXEC, + [VM_EXEC | VM_READ] = PAGE_READ_EXEC, + [VM_EXEC | VM_WRITE] = PAGE_COPY_EXEC, + [VM_EXEC | VM_WRITE | VM_READ] = PAGE_COPY_READ_EXEC, + [VM_SHARED] = PAGE_NONE, + [VM_SHARED | VM_READ] = PAGE_READ, + [VM_SHARED | VM_WRITE] = PAGE_SHARED, + [VM_SHARED | VM_WRITE | VM_READ] = PAGE_SHARED, + [VM_SHARED | VM_EXEC] = PAGE_EXEC, + [VM_SHARED | VM_EXEC | VM_READ] = PAGE_READ_EXEC, + [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_SHARED_EXEC, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_SHARED_EXEC +}; +DECLARE_VM_GET_PAGE_PROT + void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot) { unsigned long addr = __fix_to_virt(idx); diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index cf81acf3879c..f019df19884d 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -424,23 +424,6 @@ static inline int is_module_addr(void *addr) * implies read permission. */ /*xwr*/ -#define __P000 PAGE_NONE -#define __P001 PAGE_RO -#define __P010 PAGE_RO -#define __P011 PAGE_RO -#define __P100 PAGE_RX -#define __P101 PAGE_RX -#define __P110 PAGE_RX -#define __P111 PAGE_RX - -#define __S000 PAGE_NONE -#define __S001 PAGE_RO -#define __S010 PAGE_RW -#define __S011 PAGE_RW -#define __S100 PAGE_RX -#define __S101 PAGE_RX -#define __S110 PAGE_RWX -#define __S111 PAGE_RWX /* * Segment entry (large page) protection definitions. diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index ee7871f770fb..13449941516c 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -433,6 +433,17 @@ retry: goto out_up; goto out; } + + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) { + if (gmap) { + mmap_read_lock(mm); + goto out_gmap; + } + fault = 0; + goto out; + } + if (unlikely(fault & VM_FAULT_ERROR)) goto out_up; @@ -452,6 +463,7 @@ retry: mmap_read_lock(mm); goto retry; } +out_gmap: if (IS_ENABLED(CONFIG_PGSTE) && gmap) { address = __gmap_link(gmap, current->thread.gmap_addr, address); diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index d545f5c39f7e..5980ce348832 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -188,3 +188,23 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) mm->get_unmapped_area = arch_get_unmapped_area_topdown; } } + +static const pgprot_t protection_map[16] = { + [VM_NONE] = PAGE_NONE, + [VM_READ] = PAGE_RO, + [VM_WRITE] = PAGE_RO, + [VM_WRITE | VM_READ] = PAGE_RO, + [VM_EXEC] = PAGE_RX, + [VM_EXEC | VM_READ] = PAGE_RX, + [VM_EXEC | VM_WRITE] = PAGE_RX, + [VM_EXEC | VM_WRITE | VM_READ] = PAGE_RX, + [VM_SHARED] = PAGE_NONE, + [VM_SHARED | VM_READ] = PAGE_RO, + [VM_SHARED | VM_WRITE] = PAGE_RW, + [VM_SHARED | VM_WRITE | VM_READ] = PAGE_RW, + [VM_SHARED | VM_EXEC] = PAGE_RX, + [VM_SHARED | VM_EXEC | VM_READ] = PAGE_RX, + [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_RWX, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_RWX +}; +DECLARE_VM_GET_PAGE_PROT diff --git a/arch/sh/include/asm/pgtable.h b/arch/sh/include/asm/pgtable.h index d7ddb1ec86a0..6fb9ec54cf9b 100644 --- a/arch/sh/include/asm/pgtable.h +++ b/arch/sh/include/asm/pgtable.h @@ -89,23 +89,6 @@ static inline unsigned long phys_addr_mask(void) * completely separate permission bits for user and kernel space. */ /*xwr*/ -#define __P000 PAGE_NONE -#define __P001 PAGE_READONLY -#define __P010 PAGE_COPY -#define __P011 PAGE_COPY -#define __P100 PAGE_EXECREAD -#define __P101 PAGE_EXECREAD -#define __P110 PAGE_COPY -#define __P111 PAGE_COPY - -#define __S000 PAGE_NONE -#define __S001 PAGE_READONLY -#define __S010 PAGE_WRITEONLY -#define __S011 PAGE_SHARED -#define __S100 PAGE_EXECREAD -#define __S101 PAGE_EXECREAD -#define __S110 PAGE_RWX -#define __S111 PAGE_RWX typedef pte_t *pte_addr_t; diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index e175667b1363..acd2f5e50bfc 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -485,6 +485,10 @@ good_area: if (mm_fault_error(regs, error_code, address, fault)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/sh/mm/mmap.c b/arch/sh/mm/mmap.c index 6a1a1297baae..b82199878b45 100644 --- a/arch/sh/mm/mmap.c +++ b/arch/sh/mm/mmap.c @@ -19,6 +19,26 @@ unsigned long shm_align_mask = PAGE_SIZE - 1; /* Sane caches */ EXPORT_SYMBOL(shm_align_mask); #ifdef CONFIG_MMU +static const pgprot_t protection_map[16] = { + [VM_NONE] = PAGE_NONE, + [VM_READ] = PAGE_READONLY, + [VM_WRITE] = PAGE_COPY, + [VM_WRITE | VM_READ] = PAGE_COPY, + [VM_EXEC] = PAGE_EXECREAD, + [VM_EXEC | VM_READ] = PAGE_EXECREAD, + [VM_EXEC | VM_WRITE] = PAGE_COPY, + [VM_EXEC | VM_WRITE | VM_READ] = PAGE_COPY, + [VM_SHARED] = PAGE_NONE, + [VM_SHARED | VM_READ] = PAGE_READONLY, + [VM_SHARED | VM_WRITE] = PAGE_WRITEONLY, + [VM_SHARED | VM_WRITE | VM_READ] = PAGE_SHARED, + [VM_SHARED | VM_EXEC] = PAGE_EXECREAD, + [VM_SHARED | VM_EXEC | VM_READ] = PAGE_EXECREAD, + [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_RWX, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_RWX +}; +DECLARE_VM_GET_PAGE_PROT + /* * To avoid cache aliases, we map the shared page with same color. */ diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 02f0a6084f04..1c852bb530ec 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -86,7 +86,6 @@ config SPARC64 select PERF_USE_VMALLOC select ARCH_HAVE_NMI_SAFE_CMPXCHG select HAVE_C_RECORDMCOUNT - select ARCH_HAS_VM_GET_PAGE_PROT select HAVE_ARCH_AUDITSYSCALL select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_DEBUG_PAGEALLOC diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h index 4866625da314..8ff549004fac 100644 --- a/arch/sparc/include/asm/pgtable_32.h +++ b/arch/sparc/include/asm/pgtable_32.h @@ -64,25 +64,6 @@ void paging_init(void); extern unsigned long ptr_in_current_pgd; -/* xwr */ -#define __P000 PAGE_NONE -#define __P001 PAGE_READONLY -#define __P010 PAGE_COPY -#define __P011 PAGE_COPY -#define __P100 PAGE_READONLY -#define __P101 PAGE_READONLY -#define __P110 PAGE_COPY -#define __P111 PAGE_COPY - -#define __S000 PAGE_NONE -#define __S001 PAGE_READONLY -#define __S010 PAGE_SHARED -#define __S011 PAGE_SHARED -#define __S100 PAGE_READONLY -#define __S101 PAGE_READONLY -#define __S110 PAGE_SHARED -#define __S111 PAGE_SHARED - /* First physical page can be anywhere, the following is needed so that * va-->pa and vice versa conversions work properly without performance * hit for all __pa()/__va() operations. diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 4679e45c8348..a779418ceba9 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -187,25 +187,6 @@ bool kern_addr_valid(unsigned long addr); #define _PAGE_SZHUGE_4U _PAGE_SZ4MB_4U #define _PAGE_SZHUGE_4V _PAGE_SZ4MB_4V -/* These are actually filled in at boot time by sun4{u,v}_pgprot_init() */ -#define __P000 __pgprot(0) -#define __P001 __pgprot(0) -#define __P010 __pgprot(0) -#define __P011 __pgprot(0) -#define __P100 __pgprot(0) -#define __P101 __pgprot(0) -#define __P110 __pgprot(0) -#define __P111 __pgprot(0) - -#define __S000 __pgprot(0) -#define __S001 __pgprot(0) -#define __S010 __pgprot(0) -#define __S011 __pgprot(0) -#define __S100 __pgprot(0) -#define __S101 __pgprot(0) -#define __S110 __pgprot(0) -#define __S111 __pgprot(0) - #ifndef __ASSEMBLY__ pte_t mk_pte_io(unsigned long, pgprot_t, int, unsigned long); diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index ad569d9bd124..91259f291c54 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -190,6 +190,10 @@ good_area: if (fault_signal_pending(fault, regs)) return; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 253e07043298..4acc12eafbf5 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -427,6 +427,10 @@ good_area: if (fault_signal_pending(fault, regs)) goto exit_exception; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + goto lock_released; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; @@ -449,6 +453,7 @@ good_area: } mmap_read_unlock(mm); +lock_released: mm_rss = get_mm_rss(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) mm_rss -= (mm->context.thp_pte_count * (HPAGE_SIZE / PAGE_SIZE)); diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index 1e9f577f084d..d88e774c8eb4 100644 --- a/arch/sparc/mm/init_32.c +++ b/arch/sparc/mm/init_32.c @@ -302,3 +302,23 @@ void sparc_flush_page_to_ram(struct page *page) __flush_page_to_ram(vaddr); } EXPORT_SYMBOL(sparc_flush_page_to_ram); + +static const pgprot_t protection_map[16] = { + [VM_NONE] = PAGE_NONE, + [VM_READ] = PAGE_READONLY, + [VM_WRITE] = PAGE_COPY, + [VM_WRITE | VM_READ] = PAGE_COPY, + [VM_EXEC] = PAGE_READONLY, + [VM_EXEC | VM_READ] = PAGE_READONLY, + [VM_EXEC | VM_WRITE] = PAGE_COPY, + [VM_EXEC | VM_WRITE | VM_READ] = PAGE_COPY, + [VM_SHARED] = PAGE_NONE, + [VM_SHARED | VM_READ] = PAGE_READONLY, + [VM_SHARED | VM_WRITE] = PAGE_SHARED, + [VM_SHARED | VM_WRITE | VM_READ] = PAGE_SHARED, + [VM_SHARED | VM_EXEC] = PAGE_READONLY, + [VM_SHARED | VM_EXEC | VM_READ] = PAGE_READONLY, + [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_SHARED, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_SHARED +}; +DECLARE_VM_GET_PAGE_PROT diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index f6174df2d5af..d6faee23c77d 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2634,6 +2634,9 @@ void vmemmap_free(unsigned long start, unsigned long end, } #endif /* CONFIG_SPARSEMEM_VMEMMAP */ +/* These are actually filled in at boot time by sun4{u,v}_pgprot_init() */ +static pgprot_t protection_map[16] __ro_after_init; + static void prot_init_common(unsigned long page_none, unsigned long page_shared, unsigned long page_copy, diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h index 167e236d9bb8..66bc3f99d9be 100644 --- a/arch/um/include/asm/pgtable.h +++ b/arch/um/include/asm/pgtable.h @@ -68,23 +68,6 @@ extern unsigned long end_iomem; * Also, write permissions imply read permissions. This is the closest we can * get.. */ -#define __P000 PAGE_NONE -#define __P001 PAGE_READONLY -#define __P010 PAGE_COPY -#define __P011 PAGE_COPY -#define __P100 PAGE_READONLY -#define __P101 PAGE_READONLY -#define __P110 PAGE_COPY -#define __P111 PAGE_COPY - -#define __S000 PAGE_NONE -#define __S001 PAGE_READONLY -#define __S010 PAGE_SHARED -#define __S011 PAGE_SHARED -#define __S100 PAGE_READONLY -#define __S101 PAGE_READONLY -#define __S110 PAGE_SHARED -#define __S111 PAGE_SHARED /* * ZERO_PAGE is a global shared page that is always zero: used diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index 276a1f0b91f1..38d5a71a579b 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -216,3 +216,23 @@ void *uml_kmalloc(int size, int flags) { return kmalloc(size, flags); } + +static const pgprot_t protection_map[16] = { + [VM_NONE] = PAGE_NONE, + [VM_READ] = PAGE_READONLY, + [VM_WRITE] = PAGE_COPY, + [VM_WRITE | VM_READ] = PAGE_COPY, + [VM_EXEC] = PAGE_READONLY, + [VM_EXEC | VM_READ] = PAGE_READONLY, + [VM_EXEC | VM_WRITE] = PAGE_COPY, + [VM_EXEC | VM_WRITE | VM_READ] = PAGE_COPY, + [VM_SHARED] = PAGE_NONE, + [VM_SHARED | VM_READ] = PAGE_READONLY, + [VM_SHARED | VM_WRITE] = PAGE_SHARED, + [VM_SHARED | VM_WRITE | VM_READ] = PAGE_SHARED, + [VM_SHARED | VM_EXEC] = PAGE_READONLY, + [VM_SHARED | VM_EXEC | VM_READ] = PAGE_READONLY, + [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_SHARED, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_SHARED +}; +DECLARE_VM_GET_PAGE_PROT diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index d1d5d0be0308..d3ce21c4ca32 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -76,6 +76,10 @@ good_area: if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) goto out_nosemaphore; + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return 0; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) { goto out_of_memory; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index cca4c0ac39cc..f9920f1341c8 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -94,7 +94,6 @@ config X86 select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE select ARCH_HAS_SYSCALL_WRAPPER select ARCH_HAS_UBSAN_SANITIZE_ALL - select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_HAS_DEBUG_WX select ARCH_HAS_ZONE_DMA_SET if EXPERT select ARCH_HAVE_NMI_SAFE_CMPXCHG diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 88ceaf3648b3..72ca90552b6a 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -89,6 +89,8 @@ static inline void mem_encrypt_free_decrypted_mem(void) { } /* Architecture __weak replacement functions */ void __init mem_encrypt_init(void); +void add_encrypt_protection_map(void); + /* * The __sme_pa() and __sme_pa_nodebug() macros are meant for use when * writing to or comparing values from the cr3 register. Having the diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index bdaf8391e2e0..aa174fed3a71 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -230,25 +230,6 @@ enum page_cache_mode { #endif /* __ASSEMBLY__ */ -/* xwr */ -#define __P000 PAGE_NONE -#define __P001 PAGE_READONLY -#define __P010 PAGE_COPY -#define __P011 PAGE_COPY -#define __P100 PAGE_READONLY_EXEC -#define __P101 PAGE_READONLY_EXEC -#define __P110 PAGE_COPY_EXEC -#define __P111 PAGE_COPY_EXEC - -#define __S000 PAGE_NONE -#define __S001 PAGE_READONLY -#define __S010 PAGE_SHARED -#define __S011 PAGE_SHARED -#define __S100 PAGE_READONLY_EXEC -#define __S101 PAGE_READONLY_EXEC -#define __S110 PAGE_SHARED_EXEC -#define __S111 PAGE_SHARED_EXEC - /* * early identity mapping pte attrib macros. */ diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 4236a28b9be5..06ac8c7cef67 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -6740,7 +6740,7 @@ int kvm_mmu_vendor_module_init(void) if (percpu_counter_init(&kvm_total_used_mmu_pages, 0, GFP_KERNEL)) goto out; - ret = register_shrinker(&mmu_shrinker); + ret = register_shrinker(&mmu_shrinker, "x86-mmu"); if (ret) goto out; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 971977c438fc..fa71a5d12e87 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1408,6 +1408,10 @@ good_area: return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + /* * If we need to retry the mmap_lock has already been released, * and if there is a fatal signal pending there is no guarantee diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index a0d023cb4292..509408da0da1 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -19,44 +19,6 @@ #include <asm/tlbflush.h> #include <asm/elf.h> -#if 0 /* This is just for testing */ -struct page * -follow_huge_addr(struct mm_struct *mm, unsigned long address, int write) -{ - unsigned long start = address; - int length = 1; - int nr; - struct page *page; - struct vm_area_struct *vma; - - vma = find_vma(mm, addr); - if (!vma || !is_vm_hugetlb_page(vma)) - return ERR_PTR(-EINVAL); - - pte = huge_pte_offset(mm, address, vma_mmu_pagesize(vma)); - - /* hugetlb should be locked, and hence, prefaulted */ - WARN_ON(!pte || pte_none(*pte)); - - page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)]; - - WARN_ON(!PageHead(page)); - - return page; -} - -int pmd_huge(pmd_t pmd) -{ - return 0; -} - -int pud_huge(pud_t pud) -{ - return 0; -} - -#else - /* * pmd_huge() returns 1 if @pmd is hugetlb related entry, that is normal * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry. @@ -72,7 +34,6 @@ int pud_huge(pud_t pud) { return !!(pud_val(pud) & _PAGE_PSE); } -#endif #ifdef CONFIG_HUGETLB_PAGE static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index 97452688f99f..9c4d8dbcb129 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -26,6 +26,7 @@ #include <asm/tlbflush.h> #include <asm/fixmap.h> #include <asm/setup.h> +#include <asm/mem_encrypt.h> #include <asm/bootparam.h> #include <asm/set_memory.h> #include <asm/cacheflush.h> @@ -486,8 +487,6 @@ void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, boo void __init sme_early_init(void) { - unsigned int i; - if (!sme_me_mask) return; @@ -496,8 +495,7 @@ void __init sme_early_init(void) __supported_pte_mask = __sme_set(__supported_pte_mask); /* Update the protection map with memory encryption mask */ - for (i = 0; i < ARRAY_SIZE(protection_map); i++) - protection_map[i] = pgprot_encrypted(protection_map[i]); + add_encrypt_protection_map(); x86_platform.guest.enc_status_change_prepare = amd_enc_status_change_prepare; x86_platform.guest.enc_status_change_finish = amd_enc_status_change_finish; diff --git a/arch/x86/mm/pgprot.c b/arch/x86/mm/pgprot.c index 763742782286..c84bd9540b16 100644 --- a/arch/x86/mm/pgprot.c +++ b/arch/x86/mm/pgprot.c @@ -3,6 +3,34 @@ #include <linux/export.h> #include <linux/mm.h> #include <asm/pgtable.h> +#include <asm/mem_encrypt.h> + +static pgprot_t protection_map[16] __ro_after_init = { + [VM_NONE] = PAGE_NONE, + [VM_READ] = PAGE_READONLY, + [VM_WRITE] = PAGE_COPY, + [VM_WRITE | VM_READ] = PAGE_COPY, + [VM_EXEC] = PAGE_READONLY_EXEC, + [VM_EXEC | VM_READ] = PAGE_READONLY_EXEC, + [VM_EXEC | VM_WRITE] = PAGE_COPY_EXEC, + [VM_EXEC | VM_WRITE | VM_READ] = PAGE_COPY_EXEC, + [VM_SHARED] = PAGE_NONE, + [VM_SHARED | VM_READ] = PAGE_READONLY, + [VM_SHARED | VM_WRITE] = PAGE_SHARED, + [VM_SHARED | VM_WRITE | VM_READ] = PAGE_SHARED, + [VM_SHARED | VM_EXEC] = PAGE_READONLY_EXEC, + [VM_SHARED | VM_EXEC | VM_READ] = PAGE_READONLY_EXEC, + [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_SHARED_EXEC, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_SHARED_EXEC +}; + +void add_encrypt_protection_map(void) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(protection_map); i++) + protection_map[i] = pgprot_encrypted(protection_map[i]); +} pgprot_t vm_get_page_prot(unsigned long vm_flags) { diff --git a/arch/x86/um/mem_32.c b/arch/x86/um/mem_32.c index 19c5dbd46770..cafd01f730da 100644 --- a/arch/x86/um/mem_32.c +++ b/arch/x86/um/mem_32.c @@ -17,7 +17,7 @@ static int __init gate_vma_init(void) gate_vma.vm_start = FIXADDR_USER_START; gate_vma.vm_end = FIXADDR_USER_END; gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; - gate_vma.vm_page_prot = __P101; + gate_vma.vm_page_prot = PAGE_READONLY; return 0; } diff --git a/arch/xtensa/include/asm/pgalloc.h b/arch/xtensa/include/asm/pgalloc.h index eeb2de3a89e5..7fc0f9126dd3 100644 --- a/arch/xtensa/include/asm/pgalloc.h +++ b/arch/xtensa/include/asm/pgalloc.h @@ -29,7 +29,7 @@ static inline pgd_t* pgd_alloc(struct mm_struct *mm) { - return (pgd_t*) __get_free_pages(GFP_KERNEL | __GFP_ZERO, PGD_ORDER); + return (pgd_t*) __get_free_page(GFP_KERNEL | __GFP_ZERO); } static inline void ptes_clear(pte_t *ptep) diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h index 0a91376131c5..54f577c13afa 100644 --- a/arch/xtensa/include/asm/pgtable.h +++ b/arch/xtensa/include/asm/pgtable.h @@ -57,7 +57,6 @@ #define PTRS_PER_PTE 1024 #define PTRS_PER_PTE_SHIFT 10 #define PTRS_PER_PGD 1024 -#define PGD_ORDER 0 #define USER_PTRS_PER_PGD (TASK_SIZE/PGDIR_SIZE) #define FIRST_USER_PGD_NR (FIRST_USER_ADDRESS >> PGDIR_SHIFT) @@ -200,24 +199,6 @@ * What follows is the closest we can get by reasonable means.. * See linux/mm/mmap.c for protection_map[] array that uses these definitions. */ -#define __P000 PAGE_NONE /* private --- */ -#define __P001 PAGE_READONLY /* private --r */ -#define __P010 PAGE_COPY /* private -w- */ -#define __P011 PAGE_COPY /* private -wr */ -#define __P100 PAGE_READONLY_EXEC /* private x-- */ -#define __P101 PAGE_READONLY_EXEC /* private x-r */ -#define __P110 PAGE_COPY_EXEC /* private xw- */ -#define __P111 PAGE_COPY_EXEC /* private xwr */ - -#define __S000 PAGE_NONE /* shared --- */ -#define __S001 PAGE_READONLY /* shared --r */ -#define __S010 PAGE_SHARED /* shared -w- */ -#define __S011 PAGE_SHARED /* shared -wr */ -#define __S100 PAGE_READONLY_EXEC /* shared x-- */ -#define __S101 PAGE_READONLY_EXEC /* shared x-r */ -#define __S110 PAGE_SHARED_EXEC /* shared xw- */ -#define __S111 PAGE_SHARED_EXEC /* shared xwr */ - #ifndef __ASSEMBLY__ #define pte_ERROR(e) \ diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 16f0a5ff5799..8c781b05c0bd 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -172,6 +172,10 @@ good_area: return; } + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index 6a32b2cf2718..b2587a1a7c46 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -216,3 +216,25 @@ static int __init parse_memmap_opt(char *str) return 0; } early_param("memmap", parse_memmap_opt); + +#ifdef CONFIG_MMU +static const pgprot_t protection_map[16] = { + [VM_NONE] = PAGE_NONE, + [VM_READ] = PAGE_READONLY, + [VM_WRITE] = PAGE_COPY, + [VM_WRITE | VM_READ] = PAGE_COPY, + [VM_EXEC] = PAGE_READONLY_EXEC, + [VM_EXEC | VM_READ] = PAGE_READONLY_EXEC, + [VM_EXEC | VM_WRITE] = PAGE_COPY_EXEC, + [VM_EXEC | VM_WRITE | VM_READ] = PAGE_COPY_EXEC, + [VM_SHARED] = PAGE_NONE, + [VM_SHARED | VM_READ] = PAGE_READONLY, + [VM_SHARED | VM_WRITE] = PAGE_SHARED, + [VM_SHARED | VM_WRITE | VM_READ] = PAGE_SHARED, + [VM_SHARED | VM_EXEC] = PAGE_READONLY_EXEC, + [VM_SHARED | VM_EXEC | VM_READ] = PAGE_READONLY_EXEC, + [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_SHARED_EXEC, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_SHARED_EXEC +}; +DECLARE_VM_GET_PAGE_PROT +#endif diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 5649a0371a1f..1014beb12802 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -213,7 +213,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate, if (mm) { mmap_read_lock(mm); - vma = alloc->vma; + vma = vma_lookup(mm, alloc->vma_addr); } if (!vma && need_mm) { @@ -313,16 +313,22 @@ err_no_vma: static inline void binder_alloc_set_vma(struct binder_alloc *alloc, struct vm_area_struct *vma) { - if (vma) - alloc->vma_vm_mm = vma->vm_mm; + unsigned long vm_start = 0; + /* - * If we see alloc->vma is not NULL, buffer data structures set up - * completely. Look at smp_rmb side binder_alloc_get_vma. - * We also want to guarantee new alloc->vma_vm_mm is always visible - * if alloc->vma is set. + * Allow clearing the vma with holding just the read lock to allow + * munmapping downgrade of the write lock before freeing and closing the + * file using binder_alloc_vma_close(). */ - smp_wmb(); - alloc->vma = vma; + if (vma) { + vm_start = vma->vm_start; + alloc->vma_vm_mm = vma->vm_mm; + mmap_assert_write_locked(alloc->vma_vm_mm); + } else { + mmap_assert_locked(alloc->vma_vm_mm); + } + + alloc->vma_addr = vm_start; } static inline struct vm_area_struct *binder_alloc_get_vma( @@ -330,11 +336,9 @@ static inline struct vm_area_struct *binder_alloc_get_vma( { struct vm_area_struct *vma = NULL; - if (alloc->vma) { - /* Look at description in binder_alloc_set_vma */ - smp_rmb(); - vma = alloc->vma; - } + if (alloc->vma_addr) + vma = vma_lookup(alloc->vma_vm_mm, alloc->vma_addr); + return vma; } @@ -817,7 +821,8 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc) buffers = 0; mutex_lock(&alloc->mutex); - BUG_ON(alloc->vma); + BUG_ON(alloc->vma_addr && + vma_lookup(alloc->vma_vm_mm, alloc->vma_addr)); while ((n = rb_first(&alloc->allocated_buffers))) { buffer = rb_entry(n, struct binder_buffer, rb_node); @@ -1084,7 +1089,7 @@ int binder_alloc_shrinker_init(void) int ret = list_lru_init(&binder_alloc_lru); if (ret == 0) { - ret = register_shrinker(&binder_shrinker); + ret = register_shrinker(&binder_shrinker, "android-binder"); if (ret) list_lru_destroy(&binder_alloc_lru); } diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h index 7dea57a84c79..1e4fd37af5e0 100644 --- a/drivers/android/binder_alloc.h +++ b/drivers/android/binder_alloc.h @@ -100,7 +100,7 @@ struct binder_lru_page { */ struct binder_alloc { struct mutex mutex; - struct vm_area_struct *vma; + unsigned long vma_addr; struct mm_struct *vma_vm_mm; void __user *buffer; struct list_head buffers; diff --git a/drivers/android/binder_alloc_selftest.c b/drivers/android/binder_alloc_selftest.c index c2b323bc3b3a..43a881073a42 100644 --- a/drivers/android/binder_alloc_selftest.c +++ b/drivers/android/binder_alloc_selftest.c @@ -287,7 +287,7 @@ void binder_selftest_alloc(struct binder_alloc *alloc) if (!binder_selftest_run) return; mutex_lock(&binder_selftest_lock); - if (!binder_selftest_run || !alloc->vma) + if (!binder_selftest_run || !alloc->vma_addr) goto done; pr_info("STARTED\n"); binder_selftest_alloc_offset(alloc, end_offset, 0); diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c index 052aa3f65514..0916de952e09 100644 --- a/drivers/block/zram/zcomp.c +++ b/drivers/block/zram/zcomp.c @@ -63,12 +63,6 @@ static int zcomp_strm_init(struct zcomp_strm *zstrm, struct zcomp *comp) bool zcomp_available_algorithm(const char *comp) { - int i; - - i = sysfs_match_string(backends, comp); - if (i >= 0) - return true; - /* * Crypto does not ignore a trailing new line symbol, * so make sure you don't supply a string containing @@ -217,6 +211,11 @@ struct zcomp *zcomp_create(const char *compress) struct zcomp *comp; int error; + /* + * Crypto API will execute /sbin/modprobe if the compression module + * is not loaded yet. We must do it here, otherwise we are about to + * call /sbin/modprobe under CPU hot-plug lock. + */ if (!zcomp_available_algorithm(compress)) return ERR_PTR(-EINVAL); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 4abeb261b833..92cb929a45b7 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -52,7 +52,9 @@ static unsigned int num_devices = 1; static size_t huge_class_size; static const struct block_device_operations zram_devops; +#ifdef CONFIG_ZRAM_WRITEBACK static const struct block_device_operations zram_wb_devops; +#endif static void zram_free_page(struct zram *zram, size_t index); static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, @@ -1387,9 +1389,9 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, __GFP_HIGHMEM | __GFP_MOVABLE); - if (unlikely(!handle)) { + if (IS_ERR((void *)handle)) { zcomp_stream_put(zram->comp); - return -ENOMEM; + return PTR_ERR((void *)handle); } alloced_pages = zs_get_total_pages(zram->mem_pool); diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 50a08b2ec247..9b5e2a5eb0ae 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -22,6 +22,8 @@ * @private: dax driver private data * @flags: state and boolean properties * @ops: operations for this device + * @holder_data: holder of a dax_device: could be filesystem or mapped device + * @holder_ops: operations for the inner holder */ struct dax_device { struct inode inode; @@ -29,6 +31,8 @@ struct dax_device { void *private; unsigned long flags; const struct dax_operations *ops; + void *holder_data; + const struct dax_holder_operations *holder_ops; }; static dev_t dax_devt; @@ -71,8 +75,11 @@ EXPORT_SYMBOL_GPL(dax_remove_host); * fs_dax_get_by_bdev() - temporary lookup mechanism for filesystem-dax * @bdev: block device to find a dax_device for * @start_off: returns the byte offset into the dax_device that @bdev starts + * @holder: filesystem or mapped device inside the dax_device + * @ops: operations for the inner holder */ -struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off) +struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off, + void *holder, const struct dax_holder_operations *ops) { struct dax_device *dax_dev; u64 part_size; @@ -92,11 +99,26 @@ struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off) dax_dev = xa_load(&dax_hosts, (unsigned long)bdev->bd_disk); if (!dax_dev || !dax_alive(dax_dev) || !igrab(&dax_dev->inode)) dax_dev = NULL; + else if (holder) { + if (!cmpxchg(&dax_dev->holder_data, NULL, holder)) + dax_dev->holder_ops = ops; + else + dax_dev = NULL; + } dax_read_unlock(id); return dax_dev; } EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev); + +void fs_put_dax(struct dax_device *dax_dev, void *holder) +{ + if (dax_dev && holder && + cmpxchg(&dax_dev->holder_data, holder, NULL) == holder) + dax_dev->holder_ops = NULL; + put_dax(dax_dev); +} +EXPORT_SYMBOL_GPL(fs_put_dax); #endif /* CONFIG_BLOCK && CONFIG_FS_DAX */ enum dax_device_flags { @@ -204,6 +226,29 @@ size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff, } EXPORT_SYMBOL_GPL(dax_recovery_write); +int dax_holder_notify_failure(struct dax_device *dax_dev, u64 off, + u64 len, int mf_flags) +{ + int rc, id; + + id = dax_read_lock(); + if (!dax_alive(dax_dev)) { + rc = -ENXIO; + goto out; + } + + if (!dax_dev->holder_ops) { + rc = -EOPNOTSUPP; + goto out; + } + + rc = dax_dev->holder_ops->notify_failure(dax_dev, off, len, mf_flags); +out: + dax_read_unlock(id); + return rc; +} +EXPORT_SYMBOL_GPL(dax_holder_notify_failure); + #ifdef CONFIG_ARCH_HAS_PMEM_API void arch_wb_cache_pmem(void *addr, size_t size); void dax_flush(struct dax_device *dax_dev, void *addr, size_t size) @@ -277,8 +322,15 @@ void kill_dax(struct dax_device *dax_dev) if (!dax_dev) return; + if (dax_dev->holder_data != NULL) + dax_holder_notify_failure(dax_dev, 0, U64_MAX, 0); + clear_bit(DAXDEV_ALIVE, &dax_dev->flags); synchronize_srcu(&dax_srcu); + + /* clear holder data */ + dax_dev->holder_ops = NULL; + dax_dev->holder_data = NULL; } EXPORT_SYMBOL_GPL(kill_dax); @@ -421,6 +473,19 @@ void put_dax(struct dax_device *dax_dev) EXPORT_SYMBOL_GPL(put_dax); /** + * dax_holder() - obtain the holder of a dax device + * @dax_dev: a dax_device instance + + * Return: the holder's data which represents the holder if registered, + * otherwize NULL. + */ +void *dax_holder(struct dax_device *dax_dev) +{ + return dax_dev->holder_data; +} +EXPORT_SYMBOL_GPL(dax_holder); + +/** * inode_dax: convert a public inode into its dax_dev * @inode: An inode with i_cdev pointing to a dax_dev * diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index 373e5bfd4e91..b059a77b6081 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -685,13 +685,15 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, migrate.vma = vma; migrate.start = start; migrate.end = end; - migrate.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE; migrate.pgmap_owner = SVM_ADEV_PGMAP_OWNER(adev); + if (adev->gmc.xgmi.connected_to_cpu) + migrate.flags = MIGRATE_VMA_SELECT_DEVICE_COHERENT; + else + migrate.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE; buf = kvcalloc(npages, 2 * sizeof(*migrate.src) + sizeof(uint64_t) + sizeof(dma_addr_t), GFP_KERNEL); - if (!buf) goto out; @@ -974,7 +976,7 @@ int svm_migrate_init(struct amdgpu_device *adev) { struct kfd_dev *kfddev = adev->kfd.dev; struct dev_pagemap *pgmap; - struct resource *res; + struct resource *res = NULL; unsigned long size; void *r; @@ -989,28 +991,34 @@ int svm_migrate_init(struct amdgpu_device *adev) * should remove reserved size */ size = ALIGN(adev->gmc.real_vram_size, 2ULL << 20); - res = devm_request_free_mem_region(adev->dev, &iomem_resource, size); - if (IS_ERR(res)) - return -ENOMEM; + if (adev->gmc.xgmi.connected_to_cpu) { + pgmap->range.start = adev->gmc.aper_base; + pgmap->range.end = adev->gmc.aper_base + adev->gmc.aper_size - 1; + pgmap->type = MEMORY_DEVICE_COHERENT; + } else { + res = devm_request_free_mem_region(adev->dev, &iomem_resource, size); + if (IS_ERR(res)) + return -ENOMEM; + pgmap->range.start = res->start; + pgmap->range.end = res->end; + pgmap->type = MEMORY_DEVICE_PRIVATE; + } - pgmap->type = MEMORY_DEVICE_PRIVATE; pgmap->nr_range = 1; - pgmap->range.start = res->start; - pgmap->range.end = res->end; pgmap->ops = &svm_migrate_pgmap_ops; pgmap->owner = SVM_ADEV_PGMAP_OWNER(adev); - pgmap->flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE; - + pgmap->flags = 0; /* Device manager releases device-specific resources, memory region and * pgmap when driver disconnects from device. */ r = devm_memremap_pages(adev->dev, pgmap); if (IS_ERR(r)) { pr_err("failed to register HMM device memory\n"); - /* Disable SVM support capability */ pgmap->type = 0; - devm_release_mem_region(adev->dev, res->start, resource_size(res)); + if (pgmap->type == MEMORY_DEVICE_PRIVATE) + devm_release_mem_region(adev->dev, res->start, + res->end - res->start + 1); return PTR_ERR(r); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index 1030053571a2..8dc5c8874d8a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -426,7 +426,8 @@ void i915_gem_driver_register__shrinker(struct drm_i915_private *i915) i915->mm.shrinker.count_objects = i915_gem_shrinker_count; i915->mm.shrinker.seeks = DEFAULT_SEEKS; i915->mm.shrinker.batch = 4096; - drm_WARN_ON(&i915->drm, register_shrinker(&i915->mm.shrinker)); + drm_WARN_ON(&i915->drm, register_shrinker(&i915->mm.shrinker, + "drm-i915_gem")); i915->mm.oom_notifier.notifier_call = i915_gem_shrinker_oom; drm_WARN_ON(&i915->drm, register_oom_notifier(&i915->mm.oom_notifier)); diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c index 6e39d959b9f0..0317055e3253 100644 --- a/drivers/gpu/drm/msm/msm_gem_shrinker.c +++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c @@ -221,7 +221,7 @@ void msm_gem_shrinker_init(struct drm_device *dev) priv->shrinker.count_objects = msm_gem_shrinker_count; priv->shrinker.scan_objects = msm_gem_shrinker_scan; priv->shrinker.seeks = DEFAULT_SEEKS; - WARN_ON(register_shrinker(&priv->shrinker)); + WARN_ON(register_shrinker(&priv->shrinker, "drm-msm_gem")); priv->vmap_notifier.notifier_call = msm_gem_shrinker_vmap; WARN_ON(register_vmap_purge_notifier(&priv->vmap_notifier)); diff --git a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c index 77e7cb6d1ae3..bf0170782f25 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c +++ b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c @@ -103,7 +103,7 @@ void panfrost_gem_shrinker_init(struct drm_device *dev) pfdev->shrinker.count_objects = panfrost_gem_shrinker_count; pfdev->shrinker.scan_objects = panfrost_gem_shrinker_scan; pfdev->shrinker.seeks = DEFAULT_SEEKS; - WARN_ON(register_shrinker(&pfdev->shrinker)); + WARN_ON(register_shrinker(&pfdev->shrinker, "drm-panfrost")); } /** diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index 1bba0a0ed3f9..21b61631f73a 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -722,7 +722,7 @@ int ttm_pool_mgr_init(unsigned long num_pages) mm_shrinker.count_objects = ttm_pool_shrinker_count; mm_shrinker.scan_objects = ttm_pool_shrinker_scan; mm_shrinker.seeks = 1; - return register_shrinker(&mm_shrinker); + return register_shrinker(&mm_shrinker, "drm-ttm_pool"); } /** diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index e136d6edc1ed..147c493a989a 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -812,7 +812,7 @@ int bch_btree_cache_alloc(struct cache_set *c) c->shrink.seeks = 4; c->shrink.batch = c->btree_pages * 2; - if (register_shrinker(&c->shrink)) + if (register_shrinker(&c->shrink, "md-bcache:%pU", c->set_uuid)) pr_warn("bcache: %s: could not register shrinker\n", __func__); diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index dc01ce33265b..514a802e499b 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1804,7 +1804,8 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign c->shrinker.scan_objects = dm_bufio_shrink_scan; c->shrinker.seeks = 1; c->shrinker.batch = 0; - r = register_shrinker(&c->shrinker); + r = register_shrinker(&c->shrinker, "md-%s:(%u:%u)", slab_name, + MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev)); if (r) goto bad; diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index 34db364c23a8..0278482fac94 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -2945,7 +2945,9 @@ int dmz_ctr_metadata(struct dmz_dev *dev, int num_dev, zmd->mblk_shrinker.seeks = DEFAULT_SEEKS; /* Metadata cache shrinker */ - ret = register_shrinker(&zmd->mblk_shrinker); + ret = register_shrinker(&zmd->mblk_shrinker, "md-meta:(%u:%u)", + MAJOR(dev->bdev->bd_dev), + MINOR(dev->bdev->bd_dev)); if (ret) { dmz_zmd_err(zmd, "Register metadata cache shrinker failed"); goto err; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 28bd4a35b86b..60549b65c799 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -752,7 +752,7 @@ static int open_table_device(struct table_device *td, dev_t dev, } td->dm_dev.bdev = bdev; - td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev, &part_off); + td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev, &part_off, NULL, NULL); return 0; } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 860c45c10a57..31a0cbf63384 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -7644,7 +7644,7 @@ static struct r5conf *setup_conf(struct mddev *mddev) conf->shrinker.count_objects = raid5_cache_count; conf->shrinker.batch = 128; conf->shrinker.flags = 0; - ret = register_shrinker(&conf->shrinker); + ret = register_shrinker(&conf->shrinker, "md-raid5:%s", mdname(mddev)); if (ret) { pr_warn("md/raid:%s: couldn't register shrinker.\n", mdname(mddev)); diff --git a/drivers/misc/vmw_balloon.c b/drivers/misc/vmw_balloon.c index 85dd6aa33df6..61a2be712bf7 100644 --- a/drivers/misc/vmw_balloon.c +++ b/drivers/misc/vmw_balloon.c @@ -1585,7 +1585,7 @@ static int vmballoon_register_shrinker(struct vmballoon *b) b->shrinker.count_objects = vmballoon_shrinker_count; b->shrinker.seeks = DEFAULT_SEEKS; - r = register_shrinker(&b->shrinker); + r = register_shrinker(&b->shrinker, "vmw-balloon"); if (r == 0) b->shrinker_registered = true; diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index f36efcc11f67..7e88cd242380 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -453,6 +453,21 @@ static void pmem_release_disk(void *__pmem) put_disk(pmem->disk); } +static int pmem_pagemap_memory_failure(struct dev_pagemap *pgmap, + unsigned long pfn, unsigned long nr_pages, int mf_flags) +{ + struct pmem_device *pmem = + container_of(pgmap, struct pmem_device, pgmap); + u64 offset = PFN_PHYS(pfn) - pmem->phys_addr - pmem->data_offset; + u64 len = nr_pages << PAGE_SHIFT; + + return dax_holder_notify_failure(pmem->dax_dev, offset, len, mf_flags); +} + +static const struct dev_pagemap_ops fsdax_pagemap_ops = { + .memory_failure = pmem_pagemap_memory_failure, +}; + static int pmem_attach_disk(struct device *dev, struct nd_namespace_common *ndns) { @@ -514,6 +529,7 @@ static int pmem_attach_disk(struct device *dev, pmem->pfn_flags = PFN_DEV; if (is_nd_pfn(dev)) { pmem->pgmap.type = MEMORY_DEVICE_FS_DAX; + pmem->pgmap.ops = &fsdax_pagemap_ops; addr = devm_memremap_pages(dev, &pmem->pgmap); pfn_sb = nd_pfn->pfn_sb; pmem->data_offset = le64_to_cpu(pfn_sb->dataoff); @@ -527,6 +543,7 @@ static int pmem_attach_disk(struct device *dev, pmem->pgmap.range.end = res->end; pmem->pgmap.nr_range = 1; pmem->pgmap.type = MEMORY_DEVICE_FS_DAX; + pmem->pgmap.ops = &fsdax_pagemap_ops; addr = devm_memremap_pages(dev, &pmem->pgmap); pmem->pfn_flags |= PFN_MAP; bb_range = pmem->pgmap.range; diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index e02a30c92719..d170c88359fe 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -529,7 +529,7 @@ static int __init __reserved_mem_reserve_reg(unsigned long node, pr_debug("Reserved memory: reserved region for node '%s': base %pa, size %lu MiB\n", uname, &base, (unsigned long)(size / SZ_1M)); if (!nomap) - kmemleak_alloc_phys(base, size, 0, 0); + kmemleak_alloc_phys(base, size, 0); } else pr_err("Reserved memory: failed to reserve memory for node '%s': base %pa, size %lu MiB\n", diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index bd360b91e9d3..3f78a3a1eb75 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -856,7 +856,7 @@ static int virtio_balloon_register_shrinker(struct virtio_balloon *vb) vb->shrinker.count_objects = virtio_balloon_shrinker_count; vb->shrinker.seeks = DEFAULT_SEEKS; - return register_shrinker(&vb->shrinker); + return register_shrinker(&vb->shrinker, "virtio-balloon"); } static int virtballoon_probe(struct virtio_device *vdev) diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c index e07486f01999..0c2892ec6817 100644 --- a/drivers/virtio/virtio_mem.c +++ b/drivers/virtio/virtio_mem.c @@ -862,8 +862,7 @@ static void virtio_mem_sbm_notify_online(struct virtio_mem *vm, unsigned long mb_id, unsigned long start_pfn) { - const bool is_movable = page_zonenum(pfn_to_page(start_pfn)) == - ZONE_MOVABLE; + const bool is_movable = is_zone_movable_page(pfn_to_page(start_pfn)); int new_state; switch (virtio_mem_sbm_get_mb_state(vm, mb_id)) { @@ -1158,8 +1157,7 @@ static void virtio_mem_fake_online(unsigned long pfn, unsigned long nr_pages) */ static int virtio_mem_fake_offline(unsigned long pfn, unsigned long nr_pages) { - const bool is_movable = page_zonenum(pfn_to_page(pfn)) == - ZONE_MOVABLE; + const bool is_movable = is_zone_movable_page(pfn_to_page(pfn)); int rc, retry_count; /* diff --git a/drivers/xen/xenbus/xenbus_probe_backend.c b/drivers/xen/xenbus/xenbus_probe_backend.c index 5abded97e1a7..9c09f89d8278 100644 --- a/drivers/xen/xenbus/xenbus_probe_backend.c +++ b/drivers/xen/xenbus/xenbus_probe_backend.c @@ -305,7 +305,7 @@ static int __init xenbus_probe_backend_init(void) register_xenstore_notifier(&xenstore_notifier); - if (register_shrinker(&backend_memory_shrinker)) + if (register_shrinker(&backend_memory_shrinker, "xen-backend")) pr_warn("shrinker registration failed\n"); return 0; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 4c7089b1681b..f89beac3c665 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1816,6 +1816,8 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type, error = -EBUSY; } else { snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); + shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s", fs_type->name, + s->s_id); btrfs_sb(s)->bdev_holder = fs_type; if (!strstr(crc32c_impl(), "generic")) set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); @@ -334,13 +334,35 @@ static unsigned long dax_end_pfn(void *entry) for (pfn = dax_to_pfn(entry); \ pfn < dax_end_pfn(entry); pfn++) +static inline bool dax_mapping_is_cow(struct address_space *mapping) +{ + return (unsigned long)mapping == PAGE_MAPPING_DAX_COW; +} + /* - * TODO: for reflink+dax we need a way to associate a single page with - * multiple address_space instances at different linear_page_index() - * offsets. + * Set the page->mapping with FS_DAX_MAPPING_COW flag, increase the refcount. + */ +static inline void dax_mapping_set_cow(struct page *page) +{ + if ((uintptr_t)page->mapping != PAGE_MAPPING_DAX_COW) { + /* + * Reset the index if the page was already mapped + * regularly before. + */ + if (page->mapping) + page->index = 1; + page->mapping = (void *)PAGE_MAPPING_DAX_COW; + } + page->index++; +} + +/* + * When it is called in dax_insert_entry(), the cow flag will indicate that + * whether this entry is shared by multiple files. If so, set the page->mapping + * FS_DAX_MAPPING_COW, and use page->index as refcount. */ static void dax_associate_entry(void *entry, struct address_space *mapping, - struct vm_area_struct *vma, unsigned long address) + struct vm_area_struct *vma, unsigned long address, bool cow) { unsigned long size = dax_entry_size(entry), pfn, index; int i = 0; @@ -352,9 +374,13 @@ static void dax_associate_entry(void *entry, struct address_space *mapping, for_each_mapped_pfn(entry, pfn) { struct page *page = pfn_to_page(pfn); - WARN_ON_ONCE(page->mapping); - page->mapping = mapping; - page->index = index + i++; + if (cow) { + dax_mapping_set_cow(page); + } else { + WARN_ON_ONCE(page->mapping); + page->mapping = mapping; + page->index = index + i++; + } } } @@ -370,7 +396,12 @@ static void dax_disassociate_entry(void *entry, struct address_space *mapping, struct page *page = pfn_to_page(pfn); WARN_ON_ONCE(trunc && page_ref_count(page) > 1); - WARN_ON_ONCE(page->mapping && page->mapping != mapping); + if (dax_mapping_is_cow(page->mapping)) { + /* keep the CoW flag if this page is still shared */ + if (page->index-- > 0) + continue; + } else + WARN_ON_ONCE(page->mapping && page->mapping != mapping); page->mapping = NULL; page->index = 0; } @@ -456,6 +487,69 @@ void dax_unlock_page(struct page *page, dax_entry_t cookie) } /* + * dax_lock_mapping_entry - Lock the DAX entry corresponding to a mapping + * @mapping: the file's mapping whose entry we want to lock + * @index: the offset within this file + * @page: output the dax page corresponding to this dax entry + * + * Return: A cookie to pass to dax_unlock_mapping_entry() or 0 if the entry + * could not be locked. + */ +dax_entry_t dax_lock_mapping_entry(struct address_space *mapping, pgoff_t index, + struct page **page) +{ + XA_STATE(xas, NULL, 0); + void *entry; + + rcu_read_lock(); + for (;;) { + entry = NULL; + if (!dax_mapping(mapping)) + break; + + xas.xa = &mapping->i_pages; + xas_lock_irq(&xas); + xas_set(&xas, index); + entry = xas_load(&xas); + if (dax_is_locked(entry)) { + rcu_read_unlock(); + wait_entry_unlocked(&xas, entry); + rcu_read_lock(); + continue; + } + if (!entry || + dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) { + /* + * Because we are looking for entry from file's mapping + * and index, so the entry may not be inserted for now, + * or even a zero/empty entry. We don't think this is + * an error case. So, return a special value and do + * not output @page. + */ + entry = (void *)~0UL; + } else { + *page = pfn_to_page(dax_to_pfn(entry)); + dax_lock_entry(&xas, entry); + } + xas_unlock_irq(&xas); + break; + } + rcu_read_unlock(); + return (dax_entry_t)entry; +} + +void dax_unlock_mapping_entry(struct address_space *mapping, pgoff_t index, + dax_entry_t cookie) +{ + XA_STATE(xas, &mapping->i_pages, index); + + if (cookie == ~0UL) + return; + + dax_unlock_entry(&xas, (void *)cookie); +} + +/* * Find page cache entry at given index. If it is a DAX entry, return it * with the entry locked. If the page cache doesn't contain an entry at * that index, add a locked empty entry. @@ -736,22 +830,42 @@ static int copy_cow_page_dax(struct vm_fault *vmf, const struct iomap_iter *iter } /* + * MAP_SYNC on a dax mapping guarantees dirty metadata is + * flushed on write-faults (non-cow), but not read-faults. + */ +static bool dax_fault_is_synchronous(const struct iomap_iter *iter, + struct vm_area_struct *vma) +{ + return (iter->flags & IOMAP_WRITE) && (vma->vm_flags & VM_SYNC) && + (iter->iomap.flags & IOMAP_F_DIRTY); +} + +static bool dax_fault_is_cow(const struct iomap_iter *iter) +{ + return (iter->flags & IOMAP_WRITE) && + (iter->iomap.flags & IOMAP_F_SHARED); +} + +/* * By this point grab_mapping_entry() has ensured that we have a locked entry * of the appropriate size so we don't have to worry about downgrading PMDs to * PTEs. If we happen to be trying to insert a PTE and there is a PMD * already in the tree, we will skip the insertion and just dirty the PMD as * appropriate. */ -static void *dax_insert_entry(struct xa_state *xas, - struct address_space *mapping, struct vm_fault *vmf, - void *entry, pfn_t pfn, unsigned long flags, bool dirty) +static void *dax_insert_entry(struct xa_state *xas, struct vm_fault *vmf, + const struct iomap_iter *iter, void *entry, pfn_t pfn, + unsigned long flags) { + struct address_space *mapping = vmf->vma->vm_file->f_mapping; void *new_entry = dax_make_entry(pfn, flags); + bool dirty = !dax_fault_is_synchronous(iter, vmf->vma); + bool cow = dax_fault_is_cow(iter); if (dirty) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); - if (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE)) { + if (cow || (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE))) { unsigned long index = xas->xa_index; /* we are replacing a zero page with block mapping */ if (dax_is_pmd_entry(entry)) @@ -763,11 +877,12 @@ static void *dax_insert_entry(struct xa_state *xas, xas_reset(xas); xas_lock_irq(xas); - if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) { + if (cow || dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) { void *old; dax_disassociate_entry(entry, mapping, false); - dax_associate_entry(new_entry, mapping, vmf->vma, vmf->address); + dax_associate_entry(new_entry, mapping, vmf->vma, vmf->address, + cow); /* * Only swap our new entry into the page cache if the current * entry is a zero page or an empty entry. If a normal PTE or @@ -787,6 +902,9 @@ static void *dax_insert_entry(struct xa_state *xas, if (dirty) xas_set_mark(xas, PAGECACHE_TAG_DIRTY); + if (cow) + xas_set_mark(xas, PAGECACHE_TAG_TOWRITE); + xas_unlock_irq(xas); return entry; } @@ -931,20 +1049,22 @@ int dax_writeback_mapping_range(struct address_space *mapping, } EXPORT_SYMBOL_GPL(dax_writeback_mapping_range); -static int dax_iomap_pfn(const struct iomap *iomap, loff_t pos, size_t size, - pfn_t *pfnp) +static int dax_iomap_direct_access(const struct iomap *iomap, loff_t pos, + size_t size, void **kaddr, pfn_t *pfnp) { pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); - int id, rc; + int id, rc = 0; long length; id = dax_read_lock(); length = dax_direct_access(iomap->dax_dev, pgoff, PHYS_PFN(size), - DAX_ACCESS, NULL, pfnp); + DAX_ACCESS, kaddr, pfnp); if (length < 0) { rc = length; goto out; } + if (!pfnp) + goto out_check_addr; rc = -EINVAL; if (PFN_PHYS(length) < size) goto out; @@ -954,11 +1074,71 @@ static int dax_iomap_pfn(const struct iomap *iomap, loff_t pos, size_t size, if (length > 1 && !pfn_t_devmap(*pfnp)) goto out; rc = 0; + +out_check_addr: + if (!kaddr) + goto out; + if (!*kaddr) + rc = -EFAULT; out: dax_read_unlock(id); return rc; } +/** + * dax_iomap_cow_copy - Copy the data from source to destination before write + * @pos: address to do copy from. + * @length: size of copy operation. + * @align_size: aligned w.r.t align_size (either PMD_SIZE or PAGE_SIZE) + * @srcmap: iomap srcmap + * @daddr: destination address to copy to. + * + * This can be called from two places. Either during DAX write fault (page + * aligned), to copy the length size data to daddr. Or, while doing normal DAX + * write operation, dax_iomap_actor() might call this to do the copy of either + * start or end unaligned address. In the latter case the rest of the copy of + * aligned ranges is taken care by dax_iomap_actor() itself. + */ +static int dax_iomap_cow_copy(loff_t pos, uint64_t length, size_t align_size, + const struct iomap *srcmap, void *daddr) +{ + loff_t head_off = pos & (align_size - 1); + size_t size = ALIGN(head_off + length, align_size); + loff_t end = pos + length; + loff_t pg_end = round_up(end, align_size); + bool copy_all = head_off == 0 && end == pg_end; + void *saddr = 0; + int ret = 0; + + ret = dax_iomap_direct_access(srcmap, pos, size, &saddr, NULL); + if (ret) + return ret; + + if (copy_all) { + ret = copy_mc_to_kernel(daddr, saddr, length); + return ret ? -EIO : 0; + } + + /* Copy the head part of the range */ + if (head_off) { + ret = copy_mc_to_kernel(daddr, saddr, head_off); + if (ret) + return -EIO; + } + + /* Copy the tail part of the range */ + if (end < pg_end) { + loff_t tail_off = head_off + length; + loff_t tail_len = pg_end - end; + + ret = copy_mc_to_kernel(daddr + tail_off, saddr + tail_off, + tail_len); + if (ret) + return -EIO; + } + return 0; +} + /* * The user has performed a load from a hole in the file. Allocating a new * page in the file would cause excessive storage usage for workloads with @@ -966,17 +1146,15 @@ out: * If this page is ever written to we will re-fault and change the mapping to * point to real DAX storage instead. */ -static vm_fault_t dax_load_hole(struct xa_state *xas, - struct address_space *mapping, void **entry, - struct vm_fault *vmf) +static vm_fault_t dax_load_hole(struct xa_state *xas, struct vm_fault *vmf, + const struct iomap_iter *iter, void **entry) { - struct inode *inode = mapping->host; + struct inode *inode = iter->inode; unsigned long vaddr = vmf->address; pfn_t pfn = pfn_to_pfn_t(my_zero_pfn(vaddr)); vm_fault_t ret; - *entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn, - DAX_ZERO_PAGE, false); + *entry = dax_insert_entry(xas, vmf, iter, *entry, pfn, DAX_ZERO_PAGE); ret = vmf_insert_mixed(vmf->vma, vaddr, pfn); trace_dax_load_hole(inode, vmf, ret); @@ -985,7 +1163,7 @@ static vm_fault_t dax_load_hole(struct xa_state *xas, #ifdef CONFIG_FS_DAX_PMD static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, - const struct iomap *iomap, void **entry) + const struct iomap_iter *iter, void **entry) { struct address_space *mapping = vmf->vma->vm_file->f_mapping; unsigned long pmd_addr = vmf->address & PMD_MASK; @@ -1003,8 +1181,8 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, goto fallback; pfn = page_to_pfn_t(zero_page); - *entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn, - DAX_PMD | DAX_ZERO_PAGE, false); + *entry = dax_insert_entry(xas, vmf, iter, *entry, pfn, + DAX_PMD | DAX_ZERO_PAGE); if (arch_needs_pgtable_deposit()) { pgtable = pte_alloc_one(vma->vm_mm); @@ -1037,23 +1215,34 @@ fallback: } #else static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, - const struct iomap *iomap, void **entry) + const struct iomap_iter *iter, void **entry) { return VM_FAULT_FALLBACK; } #endif /* CONFIG_FS_DAX_PMD */ -static int dax_memzero(struct dax_device *dax_dev, pgoff_t pgoff, - unsigned int offset, size_t size) +static int dax_memzero(struct iomap_iter *iter, loff_t pos, size_t size) { + const struct iomap *iomap = &iter->iomap; + const struct iomap *srcmap = iomap_iter_srcmap(iter); + unsigned offset = offset_in_page(pos); + pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); void *kaddr; long ret; - ret = dax_direct_access(dax_dev, pgoff, 1, DAX_ACCESS, &kaddr, NULL); - if (ret > 0) { - memset(kaddr + offset, 0, size); - dax_flush(dax_dev, kaddr + offset, size); - } + ret = dax_direct_access(iomap->dax_dev, pgoff, 1, DAX_ACCESS, &kaddr, + NULL); + if (ret < 0) + return ret; + memset(kaddr + offset, 0, size); + if (srcmap->addr != iomap->addr) { + ret = dax_iomap_cow_copy(pos, size, PAGE_SIZE, srcmap, + kaddr); + if (ret < 0) + return ret; + dax_flush(iomap->dax_dev, kaddr, PAGE_SIZE); + } else + dax_flush(iomap->dax_dev, kaddr + offset, size); return ret; } @@ -1080,7 +1269,7 @@ static s64 dax_zero_iter(struct iomap_iter *iter, bool *did_zero) if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE) rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1); else - rc = dax_memzero(iomap->dax_dev, pgoff, offset, size); + rc = dax_memzero(iter, pos, size); dax_read_unlock(id); if (rc < 0) @@ -1129,15 +1318,17 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, struct iov_iter *iter) { const struct iomap *iomap = &iomi->iomap; + const struct iomap *srcmap = &iomi->srcmap; loff_t length = iomap_length(iomi); loff_t pos = iomi->pos; struct dax_device *dax_dev = iomap->dax_dev; loff_t end = pos + length, done = 0; + bool write = iov_iter_rw(iter) == WRITE; ssize_t ret = 0; size_t xfer; int id; - if (iov_iter_rw(iter) == READ) { + if (!write) { end = min(end, i_size_read(iomi->inode)); if (pos >= end) return 0; @@ -1146,7 +1337,12 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, return iov_iter_zero(min(length, end - pos), iter); } - if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED)) + /* + * In DAX mode, enforce either pure overwrites of written extents, or + * writes to unwritten extents as part of a copy-on-write operation. + */ + if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED && + !(iomap->flags & IOMAP_F_SHARED))) return -EIO; /* @@ -1188,6 +1384,14 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, break; } + if (write && + srcmap->type != IOMAP_HOLE && srcmap->addr != iomap->addr) { + ret = dax_iomap_cow_copy(pos, length, PAGE_SIZE, srcmap, + kaddr); + if (ret) + break; + } + map_len = PFN_PHYS(map_len); kaddr += offset; map_len -= offset; @@ -1197,7 +1401,7 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, if (recovery) xfer = dax_recovery_write(dax_dev, pgoff, kaddr, map_len, iter); - else if (iov_iter_rw(iter) == WRITE) + else if (write) xfer = dax_copy_from_iter(dax_dev, pgoff, kaddr, map_len, iter); else @@ -1268,17 +1472,6 @@ static vm_fault_t dax_fault_return(int error) } /* - * MAP_SYNC on a dax mapping guarantees dirty metadata is - * flushed on write-faults (non-cow), but not read-faults. - */ -static bool dax_fault_is_synchronous(unsigned long flags, - struct vm_area_struct *vma, const struct iomap *iomap) -{ - return (flags & IOMAP_WRITE) && (vma->vm_flags & VM_SYNC) - && (iomap->flags & IOMAP_F_DIRTY); -} - -/* * When handling a synchronous page fault and the inode need a fsync, we can * insert the PTE/PMD into page tables only after that fsync happened. Skip * insertion for now and return the pfn so that caller can insert it after the @@ -1335,15 +1528,15 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf, const struct iomap_iter *iter, pfn_t *pfnp, struct xa_state *xas, void **entry, bool pmd) { - struct address_space *mapping = vmf->vma->vm_file->f_mapping; const struct iomap *iomap = &iter->iomap; + const struct iomap *srcmap = &iter->srcmap; size_t size = pmd ? PMD_SIZE : PAGE_SIZE; loff_t pos = (loff_t)xas->xa_index << PAGE_SHIFT; - bool write = vmf->flags & FAULT_FLAG_WRITE; - bool sync = dax_fault_is_synchronous(iter->flags, vmf->vma, iomap); + bool write = iter->flags & IOMAP_WRITE; unsigned long entry_flags = pmd ? DAX_PMD : 0; int err = 0; pfn_t pfn; + void *kaddr; if (!pmd && vmf->cow_page) return dax_fault_cow_page(vmf, iter); @@ -1352,23 +1545,29 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf, if (!write && (iomap->type == IOMAP_UNWRITTEN || iomap->type == IOMAP_HOLE)) { if (!pmd) - return dax_load_hole(xas, mapping, entry, vmf); - return dax_pmd_load_hole(xas, vmf, iomap, entry); + return dax_load_hole(xas, vmf, iter, entry); + return dax_pmd_load_hole(xas, vmf, iter, entry); } - if (iomap->type != IOMAP_MAPPED) { + if (iomap->type != IOMAP_MAPPED && !(iomap->flags & IOMAP_F_SHARED)) { WARN_ON_ONCE(1); return pmd ? VM_FAULT_FALLBACK : VM_FAULT_SIGBUS; } - err = dax_iomap_pfn(&iter->iomap, pos, size, &pfn); + err = dax_iomap_direct_access(iomap, pos, size, &kaddr, &pfn); if (err) return pmd ? VM_FAULT_FALLBACK : dax_fault_return(err); - *entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn, entry_flags, - write && !sync); + *entry = dax_insert_entry(xas, vmf, iter, *entry, pfn, entry_flags); + + if (write && + srcmap->type != IOMAP_HOLE && srcmap->addr != iomap->addr) { + err = dax_iomap_cow_copy(pos, size, size, srcmap, kaddr); + if (err) + return dax_fault_return(err); + } - if (sync) + if (dax_fault_is_synchronous(iter, vmf->vma)) return dax_fault_synchronous_pfnp(pfnp, pfn); /* insert PMD pfn */ @@ -1674,3 +1873,85 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, return dax_insert_pfn_mkwrite(vmf, pfn, order); } EXPORT_SYMBOL_GPL(dax_finish_sync_fault); + +static loff_t dax_range_compare_iter(struct iomap_iter *it_src, + struct iomap_iter *it_dest, u64 len, bool *same) +{ + const struct iomap *smap = &it_src->iomap; + const struct iomap *dmap = &it_dest->iomap; + loff_t pos1 = it_src->pos, pos2 = it_dest->pos; + void *saddr, *daddr; + int id, ret; + + len = min(len, min(smap->length, dmap->length)); + + if (smap->type == IOMAP_HOLE && dmap->type == IOMAP_HOLE) { + *same = true; + return len; + } + + if (smap->type == IOMAP_HOLE || dmap->type == IOMAP_HOLE) { + *same = false; + return 0; + } + + id = dax_read_lock(); + ret = dax_iomap_direct_access(smap, pos1, ALIGN(pos1 + len, PAGE_SIZE), + &saddr, NULL); + if (ret < 0) + goto out_unlock; + + ret = dax_iomap_direct_access(dmap, pos2, ALIGN(pos2 + len, PAGE_SIZE), + &daddr, NULL); + if (ret < 0) + goto out_unlock; + + *same = !memcmp(saddr, daddr, len); + if (!*same) + len = 0; + dax_read_unlock(id); + return len; + +out_unlock: + dax_read_unlock(id); + return -EIO; +} + +int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff, + struct inode *dst, loff_t dstoff, loff_t len, bool *same, + const struct iomap_ops *ops) +{ + struct iomap_iter src_iter = { + .inode = src, + .pos = srcoff, + .len = len, + .flags = IOMAP_DAX, + }; + struct iomap_iter dst_iter = { + .inode = dst, + .pos = dstoff, + .len = len, + .flags = IOMAP_DAX, + }; + int ret; + + while ((ret = iomap_iter(&src_iter, ops)) > 0) { + while ((ret = iomap_iter(&dst_iter, ops)) > 0) { + dst_iter.processed = dax_range_compare_iter(&src_iter, + &dst_iter, len, same); + } + if (ret <= 0) + src_iter.processed = ret; + } + return ret; +} + +int dax_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *len, unsigned int remap_flags, + const struct iomap_ops *ops) +{ + return __generic_remap_file_range_prep(file_in, pos_in, file_out, + pos_out, len, remap_flags, ops); +} +EXPORT_SYMBOL_GPL(dax_remap_file_range_prep); diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 95addc5c9d34..3173debeaa5a 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -255,7 +255,8 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb, if (IS_ERR(bdev)) return PTR_ERR(bdev); dif->bdev = bdev; - dif->dax_dev = fs_dax_get_by_bdev(bdev, &dif->dax_part_off); + dif->dax_dev = fs_dax_get_by_bdev(bdev, &dif->dax_part_off, + NULL, NULL); } dif->blocks = le32_to_cpu(dis->blocks); @@ -720,7 +721,8 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) } sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, - &sbi->dax_part_off); + &sbi->dax_part_off, + NULL, NULL); } err = erofs_read_superblock(sb); @@ -812,7 +814,7 @@ static int erofs_release_device_info(int id, void *ptr, void *data) { struct erofs_device_info *dif = ptr; - fs_put_dax(dif->dax_dev); + fs_put_dax(dif->dax_dev, NULL); if (dif->bdev) blkdev_put(dif->bdev, FMODE_READ | FMODE_EXCL); erofs_fscache_unregister_cookie(&dif->fscache); @@ -886,7 +888,7 @@ static void erofs_kill_sb(struct super_block *sb) return; erofs_free_dev_context(sbi->devs); - fs_put_dax(sbi->dax_dev); + fs_put_dax(sbi->dax_dev, NULL); erofs_fscache_unregister_cookie(&sbi->s_fscache); erofs_fscache_unregister_fs(sb); kfree(sbi->opt.fsid); diff --git a/fs/erofs/utils.c b/fs/erofs/utils.c index ec9a1d780dc1..46627cb69abe 100644 --- a/fs/erofs/utils.c +++ b/fs/erofs/utils.c @@ -282,7 +282,7 @@ static struct shrinker erofs_shrinker_info = { int __init erofs_init_shrinker(void) { - return register_shrinker(&erofs_shrinker_info); + return register_shrinker(&erofs_shrinker_info, "erofs-shrinker"); } void erofs_exit_shrinker(void) diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 27a0a8c74f7a..252c742379cf 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -171,7 +171,7 @@ static void ext2_put_super (struct super_block * sb) brelse (sbi->s_sbh); sb->s_fs_info = NULL; kfree(sbi->s_blockgroup_lock); - fs_put_dax(sbi->s_daxdev); + fs_put_dax(sbi->s_daxdev, NULL); kfree(sbi); } @@ -833,7 +833,8 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) } sb->s_fs_info = sbi; sbi->s_sb_block = sb_block; - sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off); + sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off, + NULL, NULL); spin_lock_init(&sbi->s_lock); ret = -EINVAL; @@ -1210,7 +1211,7 @@ failed_mount_group_desc: failed_mount: brelse(bh); failed_sbi: - fs_put_dax(sbi->s_daxdev); + fs_put_dax(sbi->s_daxdev, NULL); sb->s_fs_info = NULL; kfree(sbi->s_blockgroup_lock); kfree(sbi); diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 9a3a8996aacf..23167efda95e 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -1654,7 +1654,8 @@ int ext4_es_register_shrinker(struct ext4_sb_info *sbi) sbi->s_es_shrinker.scan_objects = ext4_es_scan; sbi->s_es_shrinker.count_objects = ext4_es_count; sbi->s_es_shrinker.seeks = DEFAULT_SEEKS; - err = register_shrinker(&sbi->s_es_shrinker); + err = register_shrinker(&sbi->s_es_shrinker, "ext4-es:%s", + sbi->s_sb->s_id); if (err) goto err4; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 8f907e9d9c76..9a66abcca1a8 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1307,7 +1307,7 @@ static void ext4_put_super(struct super_block *sb) if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); kfree(sbi->s_blockgroup_lock); - fs_put_dax(sbi->s_daxdev); + fs_put_dax(sbi->s_daxdev, NULL); fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); #if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); @@ -4281,7 +4281,7 @@ static void ext4_free_sbi(struct ext4_sb_info *sbi) return; kfree(sbi->s_blockgroup_lock); - fs_put_dax(sbi->s_daxdev); + fs_put_dax(sbi->s_daxdev, NULL); kfree(sbi); } @@ -4293,7 +4293,8 @@ static struct ext4_sb_info *ext4_alloc_sbi(struct super_block *sb) if (!sbi) return NULL; - sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off); + sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off, + NULL, NULL); sbi->s_blockgroup_lock = kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL); @@ -4305,7 +4306,7 @@ static struct ext4_sb_info *ext4_alloc_sbi(struct super_block *sb) sbi->s_sb = sb; return sbi; err_out: - fs_put_dax(sbi->s_daxdev); + fs_put_dax(sbi->s_daxdev, NULL); kfree(sbi); return NULL; } diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 37221e94e5ef..bce02306f7a0 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -4579,7 +4579,7 @@ static int __init init_f2fs_fs(void) err = f2fs_init_sysfs(); if (err) goto free_garbage_collection_cache; - err = register_shrinker(&f2fs_shrinker_info); + err = register_shrinker(&f2fs_shrinker_info, "f2fs-shrinker"); if (err) goto free_sysfs; err = register_filesystem(&f2fs_fs_type); diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index c992d53013d3..dca842379cab 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -2533,7 +2533,7 @@ int __init gfs2_glock_init(void) return -ENOMEM; } - ret = register_shrinker(&glock_shrinker); + ret = register_shrinker(&glock_shrinker, "gfs2-glock"); if (ret) { destroy_workqueue(gfs2_delete_workqueue); destroy_workqueue(glock_workqueue); diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 244187e3e70f..b66a3e1ec152 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -148,7 +148,7 @@ static int __init init_gfs2_fs(void) if (!gfs2_trans_cachep) goto fail_cachep8; - error = register_shrinker(&gfs2_qd_shrinker); + error = register_shrinker(&gfs2_qd_shrinker, "gfs2-qd"); if (error) goto fail_shrinker; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 20336cb3c040..fe0e374b02a3 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -11,7 +11,6 @@ #include <linux/thread_info.h> #include <asm/current.h> -#include <linux/sched/signal.h> /* remove ASAP */ #include <linux/falloc.h> #include <linux/fs.h> #include <linux/mount.h> @@ -40,7 +39,6 @@ #include <linux/uaccess.h> #include <linux/sched/mm.h> -static const struct super_operations hugetlbfs_ops; static const struct address_space_operations hugetlbfs_aops; const struct file_operations hugetlbfs_file_operations; static const struct inode_operations hugetlbfs_dir_inode_operations; @@ -315,8 +313,7 @@ hugetlbfs_read_actor(struct page *page, unsigned long offset, /* * Support for read() - Find the page attached to f_mapping and copy out the - * data. Its *very* similar to generic_file_buffered_read(), we can't use that - * since it has PAGE_SIZE assumptions. + * data. This provides functionality similar to filemap_read(). */ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to) { @@ -1082,7 +1079,7 @@ static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_bsize = huge_page_size(h); if (sbinfo) { spin_lock(&sbinfo->stat_lock); - /* If no limits set, just report 0 for max/free/used + /* If no limits set, just report 0 or -1 for max/free/used * blocks, like simple_statfs() */ if (sbinfo->spool) { long free_pages; @@ -1309,7 +1306,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par ps = memparse(param->string, &rest); ctx->hstate = size_to_hstate(ps); if (!ctx->hstate) { - pr_err("Unsupported page size %lu MB\n", ps >> 20); + pr_err("Unsupported page size %lu MB\n", ps / SZ_1M); return -EINVAL; } return 0; @@ -1385,7 +1382,7 @@ hugetlbfs_fill_super(struct super_block *sb, struct fs_context *fc) /* * Allocate and initialize subpool if maximum or minimum size is * specified. Any needed reservations (for minimum size) are taken - * taken when the subpool is created. + * when the subpool is created. */ if (ctx->max_hpages != -1 || ctx->min_hpages != -1) { sbinfo->spool = hugepage_new_subpool(ctx->hstate, @@ -1555,7 +1552,7 @@ static struct vfsmount *__init mount_one_hugetlbfs(struct hstate *h) } if (IS_ERR(mnt)) pr_err("Cannot mount internal hugetlbfs for page size %luK", - huge_page_size(h) >> 10); + huge_page_size(h) / SZ_1K); return mnt; } diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index b083961ea383..6350d3857c89 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1415,7 +1415,8 @@ static journal_t *journal_init_common(struct block_device *bdev, if (percpu_counter_init(&journal->j_checkpoint_jh_count, 0, GFP_KERNEL)) goto err_cleanup; - if (register_shrinker(&journal->j_shrinker)) { + if (register_shrinker(&journal->j_shrinker, "jbd2-journal:(%u:%u)", + MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev))) { percpu_counter_destroy(&journal->j_checkpoint_jh_count); goto err_cleanup; } diff --git a/fs/mbcache.c b/fs/mbcache.c index 96f1d49d30a5..47ccfcbe0a22 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -375,7 +375,7 @@ struct mb_cache *mb_cache_create(int bucket_bits) cache->c_shrink.count_objects = mb_cache_count; cache->c_shrink.scan_objects = mb_cache_scan; cache->c_shrink.seeks = DEFAULT_SEEKS; - if (register_shrinker(&cache->c_shrink)) { + if (register_shrinker(&cache->c_shrink, "mbcache-shrinker")) { kfree(cache->c_hash); kfree(cache); goto err_out; diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c index e7b34f7e0614..a9bf09fdf2c3 100644 --- a/fs/nfs/nfs42xattr.c +++ b/fs/nfs/nfs42xattr.c @@ -1017,15 +1017,16 @@ int __init nfs4_xattr_cache_init(void) if (ret) goto out2; - ret = register_shrinker(&nfs4_xattr_cache_shrinker); + ret = register_shrinker(&nfs4_xattr_cache_shrinker, "nfs-xattr_cache"); if (ret) goto out1; - ret = register_shrinker(&nfs4_xattr_entry_shrinker); + ret = register_shrinker(&nfs4_xattr_entry_shrinker, "nfs-xattr_entry"); if (ret) goto out; - ret = register_shrinker(&nfs4_xattr_large_entry_shrinker); + ret = register_shrinker(&nfs4_xattr_large_entry_shrinker, + "nfs-xattr_large_entry"); if (!ret) return 0; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 6ab5eeb000dc..82944e14fcea 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -149,7 +149,7 @@ int __init register_nfs_fs(void) ret = nfs_register_sysctl(); if (ret < 0) goto error_2; - ret = register_shrinker(&acl_shrinker); + ret = register_shrinker(&acl_shrinker, "nfs-acl"); if (ret < 0) goto error_3; #ifdef CONFIG_NFS_V4_2 diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 9cb2d590c036..a605c0e39b09 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -670,7 +670,7 @@ nfsd_file_cache_init(void) goto out_err; } - ret = register_shrinker(&nfsd_file_shrinker); + ret = register_shrinker(&nfsd_file_shrinker, "nfsd-filecache"); if (ret) { pr_err("nfsd: failed to register nfsd_file_shrinker: %d\n", ret); goto out_lru; diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 7da88bdc0d6c..9b31e1103e7b 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -176,7 +176,8 @@ int nfsd_reply_cache_init(struct nfsd_net *nn) nn->nfsd_reply_cache_shrinker.scan_objects = nfsd_reply_cache_scan; nn->nfsd_reply_cache_shrinker.count_objects = nfsd_reply_cache_count; nn->nfsd_reply_cache_shrinker.seeks = 1; - status = register_shrinker(&nn->nfsd_reply_cache_shrinker); + status = register_shrinker(&nn->nfsd_reply_cache_shrinker, + "nfsd-reply:%s", nn->nfsd_name); if (status) goto out_stats_destroy; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 2d04e3470d4c..a3398d0f1927 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -406,6 +406,7 @@ struct mem_size_stats { u64 pss_anon; u64 pss_file; u64 pss_shmem; + u64 pss_dirty; u64 pss_locked; u64 swap_pss; }; @@ -427,6 +428,7 @@ static void smaps_page_accumulate(struct mem_size_stats *mss, mss->pss_locked += pss; if (dirty || PageDirty(page)) { + mss->pss_dirty += pss; if (private) mss->private_dirty += size; else @@ -808,6 +810,7 @@ static void __show_smap(struct seq_file *m, const struct mem_size_stats *mss, { SEQ_PUT_DEC("Rss: ", mss->resident); SEQ_PUT_DEC(" kB\nPss: ", mss->pss >> PSS_SHIFT); + SEQ_PUT_DEC(" kB\nPss_Dirty: ", mss->pss_dirty >> PSS_SHIFT); if (rollup_mode) { /* * These are meaningful only for smaps_rollup, otherwise two of @@ -860,7 +863,7 @@ static int show_smap(struct seq_file *m, void *v) __show_smap(m, &mss, false); seq_printf(m, "THPeligible: %d\n", - transparent_hugepage_active(vma)); + hugepage_vma_check(vma, vma->vm_flags, true, false)); if (arch_pkeys_enabled()) seq_printf(m, "ProtectionKey: %8u\n", vma_pkey(vma)); @@ -1792,7 +1795,7 @@ static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma, return NULL; page = vm_normal_page(vma, addr, pte); - if (!page) + if (!page || is_zone_device_page(page)) return NULL; if (PageReserved(page)) diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 28966da7834e..0427b44bfee5 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -3002,7 +3002,7 @@ static int __init dquot_init(void) pr_info("VFS: Dquot-cache hash table entries: %ld (order %ld," " %ld bytes)\n", nr_hash, order, (PAGE_SIZE << order)); - if (register_shrinker(&dqcache_shrinker)) + if (register_shrinker(&dqcache_shrinker, "dquota-cache")) panic("Cannot register dquot shrinker"); return 0; diff --git a/fs/remap_range.c b/fs/remap_range.c index 046a513dbc3a..654912d06862 100644 --- a/fs/remap_range.c +++ b/fs/remap_range.c @@ -14,6 +14,7 @@ #include <linux/compat.h> #include <linux/mount.h> #include <linux/fs.h> +#include <linux/dax.h> #include "internal.h" #include <linux/uaccess.h> @@ -263,9 +264,11 @@ out_error: * If there's an error, then the usual negative error code is returned. * Otherwise returns 0 with *len set to the request length. */ -int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - loff_t *len, unsigned int remap_flags) +int +__generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *len, unsigned int remap_flags, + const struct iomap_ops *dax_read_ops) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); @@ -325,8 +328,18 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, if (remap_flags & REMAP_FILE_DEDUP) { bool is_same = false; - ret = vfs_dedupe_file_range_compare(file_in, pos_in, - file_out, pos_out, *len, &is_same); + if (*len == 0) + return 0; + + if (!IS_DAX(inode_in)) + ret = vfs_dedupe_file_range_compare(file_in, pos_in, + file_out, pos_out, *len, &is_same); + else if (dax_read_ops) + ret = dax_dedupe_file_range_compare(inode_in, pos_in, + inode_out, pos_out, *len, &is_same, + dax_read_ops); + else + return -EINVAL; if (ret) return ret; if (!is_same) @@ -344,6 +357,14 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, return ret; } + +int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *len, unsigned int remap_flags) +{ + return __generic_remap_file_range_prep(file_in, pos_in, file_out, + pos_out, len, remap_flags, NULL); +} EXPORT_SYMBOL(generic_remap_file_range_prep); loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, diff --git a/fs/super.c b/fs/super.c index 60f57c7bc0a6..4fca6657f442 100644 --- a/fs/super.c +++ b/fs/super.c @@ -265,7 +265,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags, s->s_shrink.count_objects = super_cache_count; s->s_shrink.batch = 1024; s->s_shrink.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE; - if (prealloc_shrinker(&s->s_shrink)) + if (prealloc_shrinker(&s->s_shrink, "sb-%s", type->name)) goto fail; if (list_lru_init_memcg(&s->s_dentry_lru, &s->s_shrink)) goto fail; @@ -1288,6 +1288,8 @@ int get_tree_bdev(struct fs_context *fc, } else { s->s_mode = mode; snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); + shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s", + fc->fs_type->name, s->s_id); sb_set_blocksize(s, block_size(bdev)); error = fill_super(s, fc); if (error) { @@ -1363,6 +1365,8 @@ struct dentry *mount_bdev(struct file_system_type *fs_type, } else { s->s_mode = mode; snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); + shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s", + fs_type->name, s->s_id); sb_set_blocksize(s, block_size(bdev)); error = fill_super(s, data, flags & SB_SILENT ? 1 : 0); if (error) { diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 0978d01b0ea4..d0c9a09988bc 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -2430,7 +2430,7 @@ static int __init ubifs_init(void) if (!ubifs_inode_slab) return -ENOMEM; - err = register_shrinker(&ubifs_shrinker_info); + err = register_shrinker(&ubifs_shrinker_info, "ubifs-slab"); if (err) goto out_slab; diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index de86f5b2859f..1c44bf75f916 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1925,10 +1925,8 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx, ret = -EFAULT; if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api))) goto out; - features = uffdio_api.features; - ret = -EINVAL; - if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES)) - goto err_out; + /* Ignore unsupported features (userspace built against newer kernel) */ + features = uffdio_api.features & UFFD_API_FEATURES; ret = -EPERM; if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE)) goto err_out; diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index 1131dd01e4fe..03135a1c31b6 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -130,6 +130,11 @@ xfs-$(CONFIG_SYSCTL) += xfs_sysctl.o xfs-$(CONFIG_COMPAT) += xfs_ioctl32.o xfs-$(CONFIG_EXPORTFS_BLOCK_OPS) += xfs_pnfs.o +# notify failure +ifeq ($(CONFIG_MEMORY_FAILURE),y) +xfs-$(CONFIG_FS_DAX) += xfs_notify_failure.o +endif + # online scrub/repair ifeq ($(CONFIG_XFS_ONLINE_SCRUB),y) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 584afe076923..dde346450952 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -5,6 +5,7 @@ */ #include "xfs.h" #include <linux/backing-dev.h> +#include <linux/dax.h> #include "xfs_shared.h" #include "xfs_format.h" @@ -1944,7 +1945,7 @@ xfs_free_buftarg( list_lru_destroy(&btp->bt_lru); blkdev_issue_flush(btp->bt_bdev); - fs_put_dax(btp->bt_daxdev); + fs_put_dax(btp->bt_daxdev, btp->bt_mount); kmem_free(btp); } @@ -1991,13 +1992,18 @@ xfs_alloc_buftarg( struct block_device *bdev) { xfs_buftarg_t *btp; + const struct dax_holder_operations *ops = NULL; +#if defined(CONFIG_FS_DAX) && defined(CONFIG_MEMORY_FAILURE) + ops = &xfs_dax_holder_operations; +#endif btp = kmem_zalloc(sizeof(*btp), KM_NOFS); btp->bt_mount = mp; btp->bt_dev = bdev->bd_dev; btp->bt_bdev = bdev; - btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off); + btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off, + mp, ops); /* * Buffer IO error rate limiting. Limit it to no more than 10 messages @@ -2019,7 +2025,8 @@ xfs_alloc_buftarg( btp->bt_shrinker.scan_objects = xfs_buftarg_shrink_scan; btp->bt_shrinker.seeks = DEFAULT_SEEKS; btp->bt_shrinker.flags = SHRINKER_NUMA_AWARE; - if (register_shrinker(&btp->bt_shrinker)) + if (register_shrinker(&btp->bt_shrinker, "xfs-buf:%s", + mp->m_super->s_id)) goto error_pcpu; return btp; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 8d9b14d2b912..aa7e458ab169 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -25,6 +25,7 @@ #include "xfs_iomap.h" #include "xfs_reflink.h" +#include <linux/dax.h> #include <linux/falloc.h> #include <linux/backing-dev.h> #include <linux/mman.h> @@ -669,7 +670,7 @@ xfs_file_dax_write( pos = iocb->ki_pos; trace_xfs_file_dax_write(iocb, from); - ret = dax_iomap_rw(iocb, from, &xfs_direct_write_iomap_ops); + ret = dax_iomap_rw(iocb, from, &xfs_dax_write_iomap_ops); if (ret > 0 && iocb->ki_pos > i_size_read(inode)) { i_size_write(inode, iocb->ki_pos); error = xfs_setfilesize(ip, pos, ret); @@ -806,7 +807,7 @@ xfs_wait_dax_page( xfs_ilock(ip, XFS_MMAPLOCK_EXCL); } -static int +int xfs_break_dax_layouts( struct inode *inode, bool *retry) @@ -1253,6 +1254,31 @@ xfs_file_llseek( return vfs_setpos(file, offset, inode->i_sb->s_maxbytes); } +#ifdef CONFIG_FS_DAX +static int +xfs_dax_fault( + struct vm_fault *vmf, + enum page_entry_size pe_size, + bool write_fault, + pfn_t *pfn) +{ + return dax_iomap_fault(vmf, pe_size, pfn, NULL, + (write_fault && !vmf->cow_page) ? + &xfs_dax_write_iomap_ops : + &xfs_read_iomap_ops); +} +#else +static int +xfs_dax_fault( + struct vm_fault *vmf, + enum page_entry_size pe_size, + bool write_fault, + pfn_t *pfn) +{ + return 0; +} +#endif + /* * Locking for serialisation of IO during page faults. This results in a lock * ordering of: @@ -1284,10 +1310,7 @@ __xfs_filemap_fault( pfn_t pfn; xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); - ret = dax_iomap_fault(vmf, pe_size, &pfn, NULL, - (write_fault && !vmf->cow_page) ? - &xfs_direct_write_iomap_ops : - &xfs_read_iomap_ops); + ret = xfs_dax_fault(vmf, pe_size, write_fault, &pfn); if (ret & VM_FAULT_NEEDDSYNC) ret = dax_finish_sync_fault(vmf, pe_size, pfn); xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 5fe9af24dfcd..13851c0d640b 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -531,6 +531,9 @@ xfs_do_force_shutdown( } else if (flags & SHUTDOWN_CORRUPT_INCORE) { tag = XFS_PTAG_SHUTDOWN_CORRUPT; why = "Corruption of in-memory data"; + } else if (flags & SHUTDOWN_CORRUPT_ONDISK) { + tag = XFS_PTAG_SHUTDOWN_CORRUPT; + why = "Corruption of on-disk metadata"; } else { tag = XFS_PTAG_SHUTDOWN_IOERROR; why = "Metadata I/O Error"; diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index e3b2304bb4d2..2bbe7916a998 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -2221,5 +2221,5 @@ xfs_inodegc_register_shrinker( shrink->flags = SHRINKER_NONSLAB; shrink->batch = XFS_INODEGC_SHRINKER_BATCH; - return register_shrinker(shrink); + return register_shrinker(shrink, "xfs-inodegc:%s", mp->m_super->s_id); } diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 3022918bf96a..28493c8e9bb2 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -3447,6 +3447,50 @@ retry: return 0; } +static int +xfs_mmaplock_two_inodes_and_break_dax_layout( + struct xfs_inode *ip1, + struct xfs_inode *ip2) +{ + int error; + bool retry; + struct page *page; + + if (ip1->i_ino > ip2->i_ino) + swap(ip1, ip2); + +again: + retry = false; + /* Lock the first inode */ + xfs_ilock(ip1, XFS_MMAPLOCK_EXCL); + error = xfs_break_dax_layouts(VFS_I(ip1), &retry); + if (error || retry) { + xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL); + if (error == 0 && retry) + goto again; + return error; + } + + if (ip1 == ip2) + return 0; + + /* Nested lock the second inode */ + xfs_ilock(ip2, xfs_lock_inumorder(XFS_MMAPLOCK_EXCL, 1)); + /* + * We cannot use xfs_break_dax_layouts() directly here because it may + * need to unlock & lock the XFS_MMAPLOCK_EXCL which is not suitable + * for this nested lock case. + */ + page = dax_layout_busy_page(VFS_I(ip2)->i_mapping); + if (page && page_ref_count(page) != 1) { + xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL); + xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL); + goto again; + } + + return 0; +} + /* * Lock two inodes so that userspace cannot initiate I/O via file syscalls or * mmap activity. @@ -3461,8 +3505,19 @@ xfs_ilock2_io_mmap( ret = xfs_iolock_two_inodes_and_break_layout(VFS_I(ip1), VFS_I(ip2)); if (ret) return ret; - filemap_invalidate_lock_two(VFS_I(ip1)->i_mapping, - VFS_I(ip2)->i_mapping); + + if (IS_DAX(VFS_I(ip1)) && IS_DAX(VFS_I(ip2))) { + ret = xfs_mmaplock_two_inodes_and_break_dax_layout(ip1, ip2); + if (ret) { + inode_unlock(VFS_I(ip2)); + if (ip1 != ip2) + inode_unlock(VFS_I(ip1)); + return ret; + } + } else + filemap_invalidate_lock_two(VFS_I(ip1)->i_mapping, + VFS_I(ip2)->i_mapping); + return 0; } @@ -3472,8 +3527,14 @@ xfs_iunlock2_io_mmap( struct xfs_inode *ip1, struct xfs_inode *ip2) { - filemap_invalidate_unlock_two(VFS_I(ip1)->i_mapping, - VFS_I(ip2)->i_mapping); + if (IS_DAX(VFS_I(ip1)) && IS_DAX(VFS_I(ip2))) { + xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL); + if (ip1 != ip2) + xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL); + } else + filemap_invalidate_unlock_two(VFS_I(ip1)->i_mapping, + VFS_I(ip2)->i_mapping); + inode_unlock(VFS_I(ip2)); if (ip1 != ip2) inode_unlock(VFS_I(ip1)); diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 4d626f4321bc..fa780f08dc89 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -531,6 +531,7 @@ xfs_itruncate_extents( } /* from xfs_file.c */ +int xfs_break_dax_layouts(struct inode *inode, bool *retry); int xfs_break_layouts(struct inode *inode, uint *iolock, enum layout_break_reason reason); diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 2817d3dd25eb..07da03976ec1 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -773,7 +773,8 @@ xfs_direct_write_iomap_begin( /* may drop and re-acquire the ilock */ error = xfs_reflink_allocate_cow(ip, &imap, &cmap, &shared, - &lockmode, flags & IOMAP_DIRECT); + &lockmode, + (flags & IOMAP_DIRECT) || IS_DAX(inode)); if (error) goto out_unlock; if (shared) @@ -868,6 +869,33 @@ const struct iomap_ops xfs_direct_write_iomap_ops = { }; static int +xfs_dax_write_iomap_end( + struct inode *inode, + loff_t pos, + loff_t length, + ssize_t written, + unsigned flags, + struct iomap *iomap) +{ + struct xfs_inode *ip = XFS_I(inode); + + if (!xfs_is_cow_inode(ip)) + return 0; + + if (!written) { + xfs_reflink_cancel_cow_range(ip, pos, length, true); + return 0; + } + + return xfs_reflink_end_cow(ip, pos, written); +} + +const struct iomap_ops xfs_dax_write_iomap_ops = { + .iomap_begin = xfs_direct_write_iomap_begin, + .iomap_end = xfs_dax_write_iomap_end, +}; + +static int xfs_buffered_write_iomap_begin( struct inode *inode, loff_t offset, diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index e88dc162c785..c782e8c0479c 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -51,5 +51,6 @@ extern const struct iomap_ops xfs_direct_write_iomap_ops; extern const struct iomap_ops xfs_read_iomap_ops; extern const struct iomap_ops xfs_seek_iomap_ops; extern const struct iomap_ops xfs_xattr_iomap_ops; +extern const struct iomap_ops xfs_dax_write_iomap_ops; #endif /* __XFS_IOMAP_H__*/ diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index d2eaebd85abf..8aca2cc173ac 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -454,6 +454,7 @@ void xfs_do_force_shutdown(struct xfs_mount *mp, uint32_t flags, char *fname, #define SHUTDOWN_LOG_IO_ERROR (1u << 1) /* write attempt to the log failed */ #define SHUTDOWN_FORCE_UMOUNT (1u << 2) /* shutdown from a forced unmount */ #define SHUTDOWN_CORRUPT_INCORE (1u << 3) /* corrupt in-memory structures */ +#define SHUTDOWN_CORRUPT_ONDISK (1u << 4) /* corrupt metadata on device */ #define XFS_SHUTDOWN_STRINGS \ { SHUTDOWN_META_IO_ERROR, "metadata_io" }, \ diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c new file mode 100644 index 000000000000..69d9c83ea4b2 --- /dev/null +++ b/fs/xfs/xfs_notify_failure.c @@ -0,0 +1,226 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022 Fujitsu. All Rights Reserved. + */ + +#include "xfs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_alloc.h" +#include "xfs_bit.h" +#include "xfs_btree.h" +#include "xfs_inode.h" +#include "xfs_icache.h" +#include "xfs_rmap.h" +#include "xfs_rmap_btree.h" +#include "xfs_rtalloc.h" +#include "xfs_trans.h" +#include "xfs_ag.h" + +#include <linux/mm.h> +#include <linux/dax.h> + +struct failure_info { + xfs_agblock_t startblock; + xfs_extlen_t blockcount; + int mf_flags; +}; + +static pgoff_t +xfs_failure_pgoff( + struct xfs_mount *mp, + const struct xfs_rmap_irec *rec, + const struct failure_info *notify) +{ + loff_t pos = XFS_FSB_TO_B(mp, rec->rm_offset); + + if (notify->startblock > rec->rm_startblock) + pos += XFS_FSB_TO_B(mp, + notify->startblock - rec->rm_startblock); + return pos >> PAGE_SHIFT; +} + +static unsigned long +xfs_failure_pgcnt( + struct xfs_mount *mp, + const struct xfs_rmap_irec *rec, + const struct failure_info *notify) +{ + xfs_agblock_t end_rec; + xfs_agblock_t end_notify; + xfs_agblock_t start_cross; + xfs_agblock_t end_cross; + + start_cross = max(rec->rm_startblock, notify->startblock); + + end_rec = rec->rm_startblock + rec->rm_blockcount; + end_notify = notify->startblock + notify->blockcount; + end_cross = min(end_rec, end_notify); + + return XFS_FSB_TO_B(mp, end_cross - start_cross) >> PAGE_SHIFT; +} + +static int +xfs_dax_failure_fn( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *data) +{ + struct xfs_mount *mp = cur->bc_mp; + struct xfs_inode *ip; + struct failure_info *notify = data; + int error = 0; + + if (XFS_RMAP_NON_INODE_OWNER(rec->rm_owner) || + (rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK))) { + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK); + return -EFSCORRUPTED; + } + + /* Get files that incore, filter out others that are not in use. */ + error = xfs_iget(mp, cur->bc_tp, rec->rm_owner, XFS_IGET_INCORE, + 0, &ip); + /* Continue the rmap query if the inode isn't incore */ + if (error == -ENODATA) + return 0; + if (error) + return error; + + error = mf_dax_kill_procs(VFS_I(ip)->i_mapping, + xfs_failure_pgoff(mp, rec, notify), + xfs_failure_pgcnt(mp, rec, notify), + notify->mf_flags); + xfs_irele(ip); + return error; +} + +static int +xfs_dax_notify_ddev_failure( + struct xfs_mount *mp, + xfs_daddr_t daddr, + xfs_daddr_t bblen, + int mf_flags) +{ + struct xfs_trans *tp = NULL; + struct xfs_btree_cur *cur = NULL; + struct xfs_buf *agf_bp = NULL; + int error = 0; + xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, daddr); + xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, fsbno); + xfs_fsblock_t end_fsbno = XFS_DADDR_TO_FSB(mp, daddr + bblen); + xfs_agnumber_t end_agno = XFS_FSB_TO_AGNO(mp, end_fsbno); + + error = xfs_trans_alloc_empty(mp, &tp); + if (error) + return error; + + for (; agno <= end_agno; agno++) { + struct xfs_rmap_irec ri_low = { }; + struct xfs_rmap_irec ri_high; + struct failure_info notify; + struct xfs_agf *agf; + xfs_agblock_t agend; + struct xfs_perag *pag; + + pag = xfs_perag_get(mp, agno); + error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp); + if (error) { + xfs_perag_put(pag); + break; + } + + cur = xfs_rmapbt_init_cursor(mp, tp, agf_bp, pag); + + /* + * Set the rmap range from ri_low to ri_high, which represents + * a [start, end] where we looking for the files or metadata. + */ + memset(&ri_high, 0xFF, sizeof(ri_high)); + ri_low.rm_startblock = XFS_FSB_TO_AGBNO(mp, fsbno); + if (agno == end_agno) + ri_high.rm_startblock = XFS_FSB_TO_AGBNO(mp, end_fsbno); + + agf = agf_bp->b_addr; + agend = min(be32_to_cpu(agf->agf_length), + ri_high.rm_startblock); + notify.startblock = ri_low.rm_startblock; + notify.blockcount = agend - ri_low.rm_startblock; + + error = xfs_rmap_query_range(cur, &ri_low, &ri_high, + xfs_dax_failure_fn, ¬ify); + xfs_btree_del_cursor(cur, error); + xfs_trans_brelse(tp, agf_bp); + xfs_perag_put(pag); + if (error) + break; + + fsbno = XFS_AGB_TO_FSB(mp, agno + 1, 0); + } + + xfs_trans_cancel(tp); + return error; +} + +static int +xfs_dax_notify_failure( + struct dax_device *dax_dev, + u64 offset, + u64 len, + int mf_flags) +{ + struct xfs_mount *mp = dax_holder(dax_dev); + u64 ddev_start; + u64 ddev_end; + + if (!(mp->m_sb.sb_flags & SB_BORN)) { + xfs_warn(mp, "filesystem is not ready for notify_failure()!"); + return -EIO; + } + + if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_daxdev == dax_dev) { + xfs_warn(mp, + "notify_failure() not supported on realtime device!"); + return -EOPNOTSUPP; + } + + if (mp->m_logdev_targp && mp->m_logdev_targp->bt_daxdev == dax_dev && + mp->m_logdev_targp != mp->m_ddev_targp) { + xfs_err(mp, "ondisk log corrupt, shutting down fs!"); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK); + return -EFSCORRUPTED; + } + + if (!xfs_has_rmapbt(mp)) { + xfs_warn(mp, "notify_failure() needs rmapbt enabled!"); + return -EOPNOTSUPP; + } + + ddev_start = mp->m_ddev_targp->bt_dax_part_off; + ddev_end = ddev_start + bdev_nr_bytes(mp->m_ddev_targp->bt_bdev) - 1; + + /* Ignore the range out of filesystem area */ + if (offset + len < ddev_start) + return -ENXIO; + if (offset > ddev_end) + return -ENXIO; + + /* Calculate the real range when it touches the boundary */ + if (offset > ddev_start) + offset -= ddev_start; + else { + len -= ddev_start - offset; + offset = 0; + } + if (offset + len > ddev_end) + len -= ddev_end - offset; + + return xfs_dax_notify_ddev_failure(mp, BTOBB(offset), BTOBB(len), + mf_flags); +} + +const struct dax_holder_operations xfs_dax_holder_operations = { + .notify_failure = xfs_dax_notify_failure, +}; diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 57dd3b722265..fbff7924ff3f 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -677,7 +677,8 @@ xfs_qm_init_quotainfo( qinf->qi_shrinker.seeks = DEFAULT_SEEKS; qinf->qi_shrinker.flags = SHRINKER_NUMA_AWARE; - error = register_shrinker(&qinf->qi_shrinker); + error = register_shrinker(&qinf->qi_shrinker, "xfs-qm:%s", + mp->m_super->s_id); if (error) goto out_free_inos; diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 724806c7ce3e..e17a84e8b527 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1364,12 +1364,16 @@ xfs_reflink_remap_prep( if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest)) goto out_unlock; - /* Don't share DAX file data for now. */ - if (IS_DAX(inode_in) || IS_DAX(inode_out)) + /* Don't share DAX file data with non-DAX file. */ + if (IS_DAX(inode_in) != IS_DAX(inode_out)) goto out_unlock; - ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out, - len, remap_flags); + if (!IS_DAX(inode_in)) + ret = generic_remap_file_range_prep(file_in, pos_in, file_out, + pos_out, len, remap_flags); + else + ret = dax_remap_file_range_prep(file_in, pos_in, file_out, + pos_out, len, remap_flags, &xfs_read_iomap_ops); if (ret || *len == 0) goto out_unlock; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 3d27ba1295c9..9ac59814bbb6 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -351,8 +351,10 @@ xfs_setup_dax_always( goto disable_dax; } - if (xfs_has_reflink(mp)) { - xfs_alert(mp, "DAX and reflink cannot be used together!"); + if (xfs_has_reflink(mp) && + bdev_is_partition(mp->m_ddev_targp->bt_bdev)) { + xfs_alert(mp, + "DAX and reflink cannot work with multi-partitions!"); return -EINVAL; } diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h index 3cd5a51bace1..364e2c2648a8 100644 --- a/fs/xfs/xfs_super.h +++ b/fs/xfs/xfs_super.h @@ -92,6 +92,7 @@ extern xfs_agnumber_t xfs_set_inode_alloc(struct xfs_mount *, extern const struct export_operations xfs_export_operations; extern const struct quotactl_ops xfs_quotactl_operations; +extern const struct dax_holder_operations xfs_dax_holder_operations; extern void xfs_reinit_percpu_counters(struct xfs_mount *mp); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index d452071db572..439815cc1ab9 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -140,12 +140,6 @@ static inline bool mapping_can_writeback(struct address_space *mapping) return inode_to_bdi(mapping->host)->capabilities & BDI_CAP_WRITEBACK; } -static inline int bdi_sched_wait(void *word) -{ - schedule(); - return 0; -} - #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi, @@ -236,18 +230,6 @@ wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) } /** - * inode_to_wb_is_valid - test whether an inode has a wb associated - * @inode: inode of interest - * - * Returns %true if @inode has a wb associated. May be called without any - * locking. - */ -static inline bool inode_to_wb_is_valid(struct inode *inode) -{ - return inode->i_wb; -} - -/** * inode_to_wb - determine the wb of an inode * @inode: inode of interest * @@ -345,11 +327,6 @@ wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) return &bdi->wb; } -static inline bool inode_to_wb_is_valid(struct inode *inode) -{ - return true; -} - static inline struct bdi_writeback *inode_to_wb(struct inode *inode) { return &inode_to_bdi(inode)->wb; diff --git a/include/linux/damon.h b/include/linux/damon.h index 7c62da31ce4b..7b1f4a488230 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -86,6 +86,8 @@ struct damon_target { * @DAMOS_PAGEOUT: Call ``madvise()`` for the region with MADV_PAGEOUT. * @DAMOS_HUGEPAGE: Call ``madvise()`` for the region with MADV_HUGEPAGE. * @DAMOS_NOHUGEPAGE: Call ``madvise()`` for the region with MADV_NOHUGEPAGE. + * @DAMOS_LRU_PRIO: Prioritize the region on its LRU lists. + * @DAMOS_LRU_DEPRIO: Deprioritize the region on its LRU lists. * @DAMOS_STAT: Do nothing but count the stat. * @NR_DAMOS_ACTIONS: Total number of DAMOS actions */ @@ -95,6 +97,8 @@ enum damos_action { DAMOS_PAGEOUT, DAMOS_HUGEPAGE, DAMOS_NOHUGEPAGE, + DAMOS_LRU_PRIO, + DAMOS_LRU_DEPRIO, DAMOS_STAT, /* Do nothing but only record the stat */ NR_DAMOS_ACTIONS, }; @@ -397,7 +401,6 @@ struct damon_callback { * 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 @@ -406,14 +409,14 @@ struct damon_callback { * 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_operations.target_valid of @ops. 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. + * termination can also be explicitly requested by calling damon_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 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. + * Note that the monitoring thread protects only @kdamond via @kdamond_lock. + * Accesses to other fields must be protected by themselves. * * @ops: Set of monitoring operations for given use cases. * @callback: Set of callbacks for monitoring events notifications. @@ -526,6 +529,12 @@ bool damon_is_registered_ops(enum damon_ops_id id); int damon_register_ops(struct damon_operations *ops); int damon_select_ops(struct damon_ctx *ctx, enum damon_ops_id id); +static inline bool damon_target_has_pid(const struct damon_ctx *ctx) +{ + return ctx->ops.id == DAMON_OPS_VADDR || ctx->ops.id == DAMON_OPS_FVADDR; +} + + int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive); int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); diff --git a/include/linux/dax.h b/include/linux/dax.h index e7b81634c52a..ba985333e26b 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -43,8 +43,21 @@ struct dax_operations { void *addr, size_t bytes, struct iov_iter *iter); }; +struct dax_holder_operations { + /* + * notify_failure - notify memory failure into inner holder device + * @dax_dev: the dax device which contains the holder + * @offset: offset on this dax device where memory failure occurs + * @len: length of this memory failure event + * @flags: action flags for memory failure handler + */ + int (*notify_failure)(struct dax_device *dax_dev, u64 offset, + u64 len, int mf_flags); +}; + #if IS_ENABLED(CONFIG_DAX) struct dax_device *alloc_dax(void *private, const struct dax_operations *ops); +void *dax_holder(struct dax_device *dax_dev); void put_dax(struct dax_device *dax_dev); void kill_dax(struct dax_device *dax_dev); void dax_write_cache(struct dax_device *dax_dev, bool wc); @@ -66,6 +79,10 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, return dax_synchronous(dax_dev); } #else +static inline void *dax_holder(struct dax_device *dax_dev) +{ + return NULL; +} static inline struct dax_device *alloc_dax(void *private, const struct dax_operations *ops) { @@ -114,12 +131,9 @@ struct writeback_control; #if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX) int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk); void dax_remove_host(struct gendisk *disk); -struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, - u64 *start_off); -static inline void fs_put_dax(struct dax_device *dax_dev) -{ - put_dax(dax_dev); -} +struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off, + void *holder, const struct dax_holder_operations *ops); +void fs_put_dax(struct dax_device *dax_dev, void *holder); #else static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk) { @@ -129,11 +143,12 @@ static inline void dax_remove_host(struct gendisk *disk) { } static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, - u64 *start_off) + u64 *start_off, void *holder, + const struct dax_holder_operations *ops) { return NULL; } -static inline void fs_put_dax(struct dax_device *dax_dev) +static inline void fs_put_dax(struct dax_device *dax_dev, void *holder) { } #endif /* CONFIG_BLOCK && CONFIG_FS_DAX */ @@ -146,6 +161,10 @@ struct page *dax_layout_busy_page(struct address_space *mapping); struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end); dax_entry_t dax_lock_page(struct page *page); void dax_unlock_page(struct page *page, dax_entry_t cookie); +dax_entry_t dax_lock_mapping_entry(struct address_space *mapping, + unsigned long index, struct page **page); +void dax_unlock_mapping_entry(struct address_space *mapping, + unsigned long index, dax_entry_t cookie); #else static inline struct page *dax_layout_busy_page(struct address_space *mapping) { @@ -173,6 +192,17 @@ static inline dax_entry_t dax_lock_page(struct page *page) static inline void dax_unlock_page(struct page *page, dax_entry_t cookie) { } + +static inline dax_entry_t dax_lock_mapping_entry(struct address_space *mapping, + unsigned long index, struct page **page) +{ + return 0; +} + +static inline void dax_unlock_mapping_entry(struct address_space *mapping, + unsigned long index, dax_entry_t cookie) +{ +} #endif int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, @@ -203,6 +233,8 @@ size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, size_t nr_pages); +int dax_holder_notify_failure(struct dax_device *dax_dev, u64 off, u64 len, + int mf_flags); void dax_flush(struct dax_device *dax_dev, void *addr, size_t size); ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, @@ -214,6 +246,14 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); +int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff, + struct inode *dest, loff_t destoff, + loff_t len, bool *is_same, + const struct iomap_ops *ops); +int dax_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *len, unsigned int remap_flags, + const struct iomap_ops *ops); static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); diff --git a/include/linux/fs.h b/include/linux/fs.h index cc64873d76c5..a3522bd811f9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -74,6 +74,7 @@ struct fsverity_operations; struct fs_context; struct fs_parameter_spec; struct fileattr; +struct iomap_ops; extern void __init inode_init(void); extern void __init inode_init_early(void); @@ -2200,10 +2201,13 @@ extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len, unsigned int flags); -extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - loff_t *count, - unsigned int remap_flags); +int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *len, unsigned int remap_flags, + const struct iomap_ops *dax_read_ops); +int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *count, unsigned int remap_flags); extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 56d6a0196534..177b07944640 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -243,6 +243,16 @@ static inline void clear_highpage(struct page *page) kunmap_local(kaddr); } +static inline void clear_highpage_kasan_tagged(struct page *page) +{ + u8 tag; + + tag = page_kasan_tag(page); + page_kasan_tag_reset(page); + clear_highpage(page); + page_kasan_tag_set(page, tag); +} + #ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE static inline void tag_clear_highpage(struct page *page) @@ -336,19 +346,6 @@ static inline void memcpy_page(struct page *dst_page, size_t dst_off, kunmap_local(dst); } -static inline void memmove_page(struct page *dst_page, size_t dst_off, - struct page *src_page, size_t src_off, - size_t len) -{ - char *dst = kmap_local_page(dst_page); - char *src = kmap_local_page(src_page); - - VM_BUG_ON(dst_off + len > PAGE_SIZE || src_off + len > PAGE_SIZE); - memmove(dst + dst_off, src + src_off, len); - kunmap_local(src); - kunmap_local(dst); -} - static inline void memset_page(struct page *page, size_t offset, int val, size_t len) { diff --git a/include/linux/hmm.h b/include/linux/hmm.h index d5a6f101f843..126a36571667 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -4,7 +4,7 @@ * * Authors: Jérôme Glisse <jglisse@redhat.com> * - * See Documentation/vm/hmm.rst for reasons and overview of what HMM is. + * See Documentation/mm/hmm.rst for reasons and overview of what HMM is. */ #ifndef LINUX_HMM_H #define LINUX_HMM_H @@ -100,7 +100,7 @@ struct hmm_range { }; /* - * Please see Documentation/vm/hmm.rst for how to use the range API. + * Please see Documentation/mm/hmm.rst for how to use the range API. */ int hmm_range_fault(struct hmm_range *range); diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 4ddaf6ad73ef..768e5261fdae 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -116,9 +116,30 @@ extern struct kobj_attribute shmem_enabled_attr; extern unsigned long transparent_hugepage_flags; +#define hugepage_flags_enabled() \ + (transparent_hugepage_flags & \ + ((1<<TRANSPARENT_HUGEPAGE_FLAG) | \ + (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG))) +#define hugepage_flags_always() \ + (transparent_hugepage_flags & \ + (1<<TRANSPARENT_HUGEPAGE_FLAG)) + +/* + * Do the below checks: + * - For file vma, check if the linear page offset of vma is + * HPAGE_PMD_NR aligned within the file. The hugepage is + * guaranteed to be hugepage-aligned within the file, but we must + * check that the PMD-aligned addresses in the VMA map to + * PMD-aligned offsets within the file, else the hugepage will + * not be PMD-mappable. + * - For all vmas, check if the haddr is in an aligned HPAGE_PMD_SIZE + * area. + */ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, - unsigned long haddr) + unsigned long addr) { + unsigned long haddr; + /* Don't have to check pgoff for anonymous vma */ if (!vma_is_anonymous(vma)) { if (!IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, @@ -126,53 +147,13 @@ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, return false; } - if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) - return false; - return true; -} + haddr = addr & HPAGE_PMD_MASK; -static inline bool transhuge_vma_enabled(struct vm_area_struct *vma, - unsigned long vm_flags) -{ - /* Explicitly disabled through madvise. */ - if ((vm_flags & VM_NOHUGEPAGE) || - test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) return false; return true; } -/* - * to be used on vmas which are known to support THP. - * Use transparent_hugepage_active otherwise - */ -static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) -{ - - /* - * If the hardware/firmware marked hugepage support disabled. - */ - if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_NEVER_DAX)) - return false; - - if (!transhuge_vma_enabled(vma, vma->vm_flags)) - return false; - - if (vma_is_temporary_stack(vma)) - return false; - - if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG)) - return true; - - if (vma_is_dax(vma)) - return true; - - if (transparent_hugepage_flags & - (1 << TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)) - return !!(vma->vm_flags & VM_HUGEPAGE); - - return false; -} - static inline bool file_thp_enabled(struct vm_area_struct *vma) { struct inode *inode; @@ -187,7 +168,9 @@ static inline bool file_thp_enabled(struct vm_area_struct *vma) !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode); } -bool transparent_hugepage_active(struct vm_area_struct *vma); +bool hugepage_vma_check(struct vm_area_struct *vma, + unsigned long vm_flags, + bool smaps, bool in_pf); #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ @@ -290,7 +273,7 @@ static inline bool is_huge_zero_page(struct page *page) static inline bool is_huge_zero_pmd(pmd_t pmd) { - return READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd) && pmd_present(pmd); + return pmd_present(pmd) && READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd); } static inline bool is_huge_zero_pud(pud_t pud) @@ -311,8 +294,8 @@ static inline bool thp_migration_supported(void) static inline struct list_head *page_deferred_list(struct page *page) { /* - * Global or memcg deferred list in the second tail pages is - * occupied by compound_head. + * See organization of tail pages of compound page in + * "struct page" definition. */ return &page[2].deferred_list; } @@ -331,24 +314,15 @@ static inline bool folio_test_pmd_mappable(struct folio *folio) return false; } -static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) -{ - return false; -} - -static inline bool transparent_hugepage_active(struct vm_area_struct *vma) -{ - return false; -} - static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, - unsigned long haddr) + unsigned long addr) { return false; } -static inline bool transhuge_vma_enabled(struct vm_area_struct *vma, - unsigned long vm_flags) +static inline bool hugepage_vma_check(struct vm_area_struct *vma, + unsigned long vm_flags, + bool smaps, bool in_pf) { return false; } diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index e4cff27d1198..4cdfce976644 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -152,7 +152,7 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb, struct page *ref_page, zap_flags_t zap_flags); void hugetlb_report_meminfo(struct seq_file *); int hugetlb_report_node_meminfo(char *buf, int len, int nid); -void hugetlb_show_meminfo(void); +void hugetlb_show_meminfo_node(int nid); unsigned long hugetlb_total_pages(void); vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); @@ -170,7 +170,7 @@ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, vm_flags_t vm_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); -bool isolate_huge_page(struct page *page, struct list_head *list); +int isolate_hugetlb(struct page *page, struct list_head *list); int get_hwpoison_huge_page(struct page *page, bool *hugetlb); int get_huge_page_for_hwpoison(unsigned long pfn, int flags); void putback_active_hugepage(struct page *page); @@ -194,8 +194,9 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz); pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); +unsigned long hugetlb_mask_last_page(struct hstate *h); int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long *addr, pte_t *ptep); + unsigned long addr, pte_t *ptep); void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end); struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, @@ -242,7 +243,7 @@ static inline struct address_space *hugetlb_page_mapping_lock_write( static inline int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long *addr, pte_t *ptep) + unsigned long addr, pte_t *ptep) { return 0; } @@ -297,7 +298,7 @@ static inline int hugetlb_report_node_meminfo(char *buf, int len, int nid) return 0; } -static inline void hugetlb_show_meminfo(void) +static inline void hugetlb_show_meminfo_node(int nid) { } @@ -376,9 +377,9 @@ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, return NULL; } -static inline bool isolate_huge_page(struct page *page, struct list_head *list) +static inline int isolate_hugetlb(struct page *page, struct list_head *list) { - return false; + return -EBUSY; } static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb) @@ -903,14 +904,6 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm) atomic_long_sub(l, &mm->hugetlb_usage); } -#ifndef set_huge_swap_pte_at -static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte, unsigned long sz) -{ - set_huge_pte_at(mm, addr, ptep, pte); -} -#endif - #ifndef huge_ptep_modify_prot_start #define huge_ptep_modify_prot_start huge_ptep_modify_prot_start static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, @@ -1094,11 +1087,6 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm) { } -static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte, unsigned long sz) -{ -} - static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index 392d34c3c59a..384f034ae947 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -10,8 +10,6 @@ extern struct attribute_group khugepaged_attr_group; extern int khugepaged_init(void); extern void khugepaged_destroy(void); extern int start_stop_khugepaged(void); -extern bool hugepage_vma_check(struct vm_area_struct *vma, - unsigned long vm_flags); extern void __khugepaged_enter(struct mm_struct *mm); extern void __khugepaged_exit(struct mm_struct *mm); extern void khugepaged_enter_vma(struct vm_area_struct *vma, @@ -26,20 +24,6 @@ static inline void collapse_pte_mapped_thp(struct mm_struct *mm, } #endif -#define khugepaged_enabled() \ - (transparent_hugepage_flags & \ - ((1<<TRANSPARENT_HUGEPAGE_FLAG) | \ - (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG))) -#define khugepaged_always() \ - (transparent_hugepage_flags & \ - (1<<TRANSPARENT_HUGEPAGE_FLAG)) -#define khugepaged_req_madv() \ - (transparent_hugepage_flags & \ - (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)) -#define khugepaged_defrag() \ - (transparent_hugepage_flags & \ - (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)) - static inline void khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) { if (test_bit(MMF_VM_HUGEPAGE, &oldmm->flags)) @@ -51,16 +35,6 @@ static inline void khugepaged_exit(struct mm_struct *mm) if (test_bit(MMF_VM_HUGEPAGE, &mm->flags)) __khugepaged_exit(mm); } - -static inline void khugepaged_enter(struct vm_area_struct *vma, - unsigned long vm_flags) -{ - if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) && - khugepaged_enabled()) { - if (hugepage_vma_check(vma, vm_flags)) - __khugepaged_enter(vma->vm_mm); - } -} #else /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline void khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) { @@ -68,10 +42,6 @@ static inline void khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm static inline void khugepaged_exit(struct mm_struct *mm) { } -static inline void khugepaged_enter(struct vm_area_struct *vma, - unsigned long vm_flags) -{ -} static inline void khugepaged_enter_vma(struct vm_area_struct *vma, unsigned long vm_flags) { diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h index 34684b2026ab..6a3cd1bf4680 100644 --- a/include/linux/kmemleak.h +++ b/include/linux/kmemleak.h @@ -29,10 +29,9 @@ extern void kmemleak_not_leak(const void *ptr) __ref; extern void kmemleak_ignore(const void *ptr) __ref; extern void kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp) __ref; extern void kmemleak_no_scan(const void *ptr) __ref; -extern void kmemleak_alloc_phys(phys_addr_t phys, size_t size, int min_count, +extern void kmemleak_alloc_phys(phys_addr_t phys, size_t size, gfp_t gfp) __ref; extern void kmemleak_free_part_phys(phys_addr_t phys, size_t size) __ref; -extern void kmemleak_not_leak_phys(phys_addr_t phys) __ref; extern void kmemleak_ignore_phys(phys_addr_t phys) __ref; static inline void kmemleak_alloc_recursive(const void *ptr, size_t size, @@ -107,15 +106,12 @@ static inline void kmemleak_no_scan(const void *ptr) { } static inline void kmemleak_alloc_phys(phys_addr_t phys, size_t size, - int min_count, gfp_t gfp) + gfp_t gfp) { } static inline void kmemleak_free_part_phys(phys_addr_t phys, size_t size) { } -static inline void kmemleak_not_leak_phys(phys_addr_t phys) -{ -} static inline void kmemleak_ignore_phys(phys_addr_t phys) { } diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 9ecead1042b9..4d31ce55b1c0 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -837,6 +837,15 @@ static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) } struct mem_cgroup *mem_cgroup_from_id(unsigned short id); +#ifdef CONFIG_SHRINKER_DEBUG +static inline unsigned long mem_cgroup_ino(struct mem_cgroup *memcg) +{ + return memcg ? cgroup_ino(memcg->css.cgroup) : 0; +} + +struct mem_cgroup *mem_cgroup_get_from_ino(unsigned long ino); +#endif + static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { return mem_cgroup_from_css(seq_css(m)); @@ -1343,6 +1352,18 @@ static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) return NULL; } +#ifdef CONFIG_SHRINKER_DEBUG +static inline unsigned long mem_cgroup_ino(struct mem_cgroup *memcg) +{ + return 0; +} + +static inline struct mem_cgroup *mem_cgroup_get_from_ino(unsigned long ino) +{ + return NULL; +} +#endif + static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { return NULL; @@ -1740,6 +1761,7 @@ static inline int memcg_kmem_id(struct mem_cgroup *memcg) } struct mem_cgroup *mem_cgroup_from_obj(void *p); +struct mem_cgroup *mem_cgroup_from_slab_obj(void *p); static inline void count_objcg_event(struct obj_cgroup *objcg, enum vm_event_item idx) @@ -1755,6 +1777,42 @@ static inline void count_objcg_event(struct obj_cgroup *objcg, rcu_read_unlock(); } +/** + * get_mem_cgroup_from_obj - get a memcg associated with passed kernel object. + * @p: pointer to object from which memcg should be extracted. It can be NULL. + * + * Retrieves the memory group into which the memory of the pointed kernel + * object is accounted. If memcg is found, its reference is taken. + * If a passed kernel object is uncharged, or if proper memcg cannot be found, + * as well as if mem_cgroup is disabled, NULL is returned. + * + * Return: valid memcg pointer with taken reference or NULL. + */ +static inline struct mem_cgroup *get_mem_cgroup_from_obj(void *p) +{ + struct mem_cgroup *memcg; + + rcu_read_lock(); + do { + memcg = mem_cgroup_from_obj(p); + } while (memcg && !css_tryget(&memcg->css)); + rcu_read_unlock(); + return memcg; +} + +/** + * mem_cgroup_or_root - always returns a pointer to a valid memory cgroup. + * @memcg: pointer to a valid memory cgroup or NULL. + * + * If passed argument is not NULL, returns it without any additional checks + * and changes. Otherwise, root_mem_cgroup is returned. + * + * NOTE: root_mem_cgroup can be NULL during early boot. + */ +static inline struct mem_cgroup *mem_cgroup_or_root(struct mem_cgroup *memcg) +{ + return memcg ? memcg : root_mem_cgroup; +} #else static inline bool mem_cgroup_kmem_disabled(void) { @@ -1798,7 +1856,12 @@ static inline int memcg_kmem_id(struct mem_cgroup *memcg) static inline struct mem_cgroup *mem_cgroup_from_obj(void *p) { - return NULL; + return NULL; +} + +static inline struct mem_cgroup *mem_cgroup_from_slab_obj(void *p) +{ + return NULL; } static inline void count_objcg_event(struct obj_cgroup *objcg, @@ -1806,6 +1869,15 @@ static inline void count_objcg_event(struct obj_cgroup *objcg, { } +static inline struct mem_cgroup *get_mem_cgroup_from_obj(void *p) +{ + return NULL; +} + +static inline struct mem_cgroup *mem_cgroup_or_root(struct mem_cgroup *memcg) +{ + return NULL; +} #endif /* CONFIG_MEMCG_KMEM */ #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 20d7edf62a6a..e0b2209ab71c 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -351,13 +351,4 @@ void arch_remove_linear_mapping(u64 start, u64 size); extern bool mhp_supports_memmap_on_memory(unsigned long size); #endif /* CONFIG_MEMORY_HOTPLUG */ -#ifdef CONFIG_MHP_MEMMAP_ON_MEMORY -bool mhp_memmap_on_memory(void); -#else -static inline bool mhp_memmap_on_memory(void) -{ - return false; -} -#endif - #endif /* __LINUX_MEMORY_HOTPLUG_H */ diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 8af304f6b504..19010491a603 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -2,7 +2,7 @@ #ifndef _LINUX_MEMREMAP_H_ #define _LINUX_MEMREMAP_H_ -#include <linux/mm.h> +#include <linux/mmzone.h> #include <linux/range.h> #include <linux/ioport.h> #include <linux/percpu-refcount.h> @@ -39,7 +39,14 @@ struct vmem_altmap { * must be treated as an opaque object, rather than a "normal" struct page. * * A more complete discussion of unaddressable memory may be found in - * include/linux/hmm.h and Documentation/vm/hmm.rst. + * include/linux/hmm.h and Documentation/mm/hmm.rst. + * + * MEMORY_DEVICE_COHERENT: + * Device memory that is cache coherent from device and CPU point of view. This + * is used on platforms that have an advanced system bus (like CAPI or CXL). A + * driver can hotplug the device memory using ZONE_DEVICE and with that memory + * type. Any page of a process can be migrated to such memory. However no one + * should be allowed to pin such memory so that it can always be evicted. * * MEMORY_DEVICE_FS_DAX: * Host memory that has similar access semantics as System RAM i.e. DMA @@ -61,6 +68,7 @@ struct vmem_altmap { enum memory_type { /* 0 is reserved to catch uninitialized type fields */ MEMORY_DEVICE_PRIVATE = 1, + MEMORY_DEVICE_COHERENT, MEMORY_DEVICE_FS_DAX, MEMORY_DEVICE_GENERIC, MEMORY_DEVICE_PCI_P2PDMA, @@ -79,6 +87,18 @@ struct dev_pagemap_ops { * the page back to a CPU accessible page. */ vm_fault_t (*migrate_to_ram)(struct vm_fault *vmf); + + /* + * Handle the memory failure happens on a range of pfns. Notify the + * processes who are using these pfns, and try to recover the data on + * them if necessary. The mf_flags is finally passed to the recover + * function through the whole notify routine. + * + * When this is not implemented, or it returns -EOPNOTSUPP, the caller + * will fall back to a common handler called mf_generic_kill_procs(). + */ + int (*memory_failure)(struct dev_pagemap *pgmap, unsigned long pfn, + unsigned long nr_pages, int mf_flags); }; #define PGMAP_ALTMAP_VALID (1 << 0) @@ -150,6 +170,17 @@ static inline bool is_pci_p2pdma_page(const struct page *page) page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; } +static inline bool is_device_coherent_page(const struct page *page) +{ + return is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_COHERENT; +} + +static inline bool folio_is_device_coherent(const struct folio *folio) +{ + return is_device_coherent_page(&folio->page); +} + #ifdef CONFIG_ZONE_DEVICE void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); diff --git a/include/linux/migrate.h b/include/linux/migrate.h index ae5bb67a9ba1..22c0a0cf5e0c 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -182,6 +182,7 @@ static inline unsigned long migrate_pfn(unsigned long pfn) enum migrate_vma_direction { MIGRATE_VMA_SELECT_SYSTEM = 1 << 0, MIGRATE_VMA_SELECT_DEVICE_PRIVATE = 1 << 1, + MIGRATE_VMA_SELECT_DEVICE_COHERENT = 1 << 2, }; struct migrate_vma { diff --git a/include/linux/mm.h b/include/linux/mm.h index a37b8c062daa..18e01474cf6b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -28,6 +28,7 @@ #include <linux/sched.h> #include <linux/pgtable.h> #include <linux/kasan.h> +#include <linux/memremap.h> struct mempolicy; struct anon_vma; @@ -427,7 +428,6 @@ extern unsigned int kobjsize(const void *objp); * mapping from the currently active vm_flags protection bits (the * low four bits) to a page protection mask.. */ -extern pgprot_t protection_map[16]; /* * The default fault flags that should be used by most of the @@ -858,7 +858,7 @@ static inline struct folio *virt_to_folio(const void *x) return page_folio(page); } -void __put_page(struct page *page); +void __folio_put(struct folio *folio); void put_pages_list(struct list_head *pages); @@ -895,11 +895,7 @@ static inline void set_compound_page_dtor(struct page *page, page[1].compound_dtor = compound_dtor; } -static inline void destroy_compound_page(struct page *page) -{ - VM_BUG_ON_PAGE(page[1].compound_dtor >= NR_COMPOUND_DTORS, page); - compound_page_dtors[page[1].compound_dtor](page); -} +void destroy_large_folio(struct folio *folio); static inline int head_compound_pincount(struct page *head) { @@ -1052,84 +1048,6 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); * back into memory. */ -/* - * The zone field is never updated after free_area_init_core() - * sets it, so none of the operations on it need to be atomic. - */ - -/* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_CPUPID] | ... | FLAGS | */ -#define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH) -#define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH) -#define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) -#define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH) -#define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH) - -/* - * Define the bit shifts to access each section. For non-existent - * sections we define the shift as 0; that plus a 0 mask ensures - * the compiler will optimise away reference to them. - */ -#define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0)) -#define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) -#define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) -#define LAST_CPUPID_PGSHIFT (LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0)) -#define KASAN_TAG_PGSHIFT (KASAN_TAG_PGOFF * (KASAN_TAG_WIDTH != 0)) - -/* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ -#ifdef NODE_NOT_IN_PAGE_FLAGS -#define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT) -#define ZONEID_PGOFF ((SECTIONS_PGOFF < ZONES_PGOFF)? \ - SECTIONS_PGOFF : ZONES_PGOFF) -#else -#define ZONEID_SHIFT (NODES_SHIFT + ZONES_SHIFT) -#define ZONEID_PGOFF ((NODES_PGOFF < ZONES_PGOFF)? \ - NODES_PGOFF : ZONES_PGOFF) -#endif - -#define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0)) - -#define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) -#define NODES_MASK ((1UL << NODES_WIDTH) - 1) -#define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) -#define LAST_CPUPID_MASK ((1UL << LAST_CPUPID_SHIFT) - 1) -#define KASAN_TAG_MASK ((1UL << KASAN_TAG_WIDTH) - 1) -#define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) - -static inline enum zone_type page_zonenum(const struct page *page) -{ - ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT); - return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; -} - -static inline enum zone_type folio_zonenum(const struct folio *folio) -{ - return page_zonenum(&folio->page); -} - -#ifdef CONFIG_ZONE_DEVICE -static inline bool is_zone_device_page(const struct page *page) -{ - return page_zonenum(page) == ZONE_DEVICE; -} -extern void memmap_init_zone_device(struct zone *, unsigned long, - unsigned long, struct dev_pagemap *); -#else -static inline bool is_zone_device_page(const struct page *page) -{ - return false; -} -#endif - -static inline bool folio_is_zone_device(const struct folio *folio) -{ - return is_zone_device_page(&folio->page); -} - -static inline bool is_zone_movable_page(const struct page *page) -{ - return page_zonenum(page) == ZONE_MOVABLE; -} - #if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_FS_DAX) DECLARE_STATIC_KEY_FALSE(devmap_managed_key); @@ -1204,7 +1122,7 @@ static inline __must_check bool try_get_page(struct page *page) static inline void folio_put(struct folio *folio) { if (folio_put_testzero(folio)) - __put_page(&folio->page); + __folio_put(folio); } /** @@ -1224,7 +1142,26 @@ static inline void folio_put(struct folio *folio) static inline void folio_put_refs(struct folio *folio, int refs) { if (folio_ref_sub_and_test(folio, refs)) - __put_page(&folio->page); + __folio_put(folio); +} + +void release_pages(struct page **pages, int nr); + +/** + * folios_put - Decrement the reference count on an array of folios. + * @folios: The folios. + * @nr: How many folios there are. + * + * Like folio_put(), but for an array of folios. This is more efficient + * than writing the loop yourself as it will optimise the locks which + * need to be taken if the folios are freed. + * + * Context: May be called in process or interrupt context, but not in NMI + * context. May be called while holding a spinlock. + */ +static inline void folios_put(struct folio **folios, unsigned int nr) +{ + release_pages((struct page **)folios, nr); } static inline void put_page(struct page *page) @@ -1599,7 +1536,7 @@ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, /* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */ #ifdef CONFIG_MIGRATION -static inline bool is_pinnable_page(struct page *page) +static inline bool is_longterm_pinnable_page(struct page *page) { #ifdef CONFIG_CMA int mt = get_pageblock_migratetype(page); @@ -1607,18 +1544,20 @@ static inline bool is_pinnable_page(struct page *page) if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE) return false; #endif - return !is_zone_movable_page(page) || is_zero_pfn(page_to_pfn(page)); + return !(is_device_coherent_page(page) || + is_zone_movable_page(page) || + is_zero_pfn(page_to_pfn(page))); } #else -static inline bool is_pinnable_page(struct page *page) +static inline bool is_longterm_pinnable_page(struct page *page) { return true; } #endif -static inline bool folio_is_pinnable(struct folio *folio) +static inline bool folio_is_longterm_pinnable(struct folio *folio) { - return is_pinnable_page(&folio->page); + return is_longterm_pinnable_page(&folio->page); } static inline void set_page_zone(struct page *page, enum zone_type zone) @@ -1969,8 +1908,12 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma, * for now all the callers are only use one of the flags at the same * time. */ -/* Whether we should allow dirty bit accounting */ -#define MM_CP_DIRTY_ACCT (1UL << 0) +/* + * Whether we should manually check if we can map individual PTEs writable, + * because something (e.g., COW, uffd-wp) blocks that from happening for all + * PTEs automatically in a writable mapping. + */ +#define MM_CP_TRY_CHANGE_WRITABLE (1UL << 0) /* Whether this protection change is for NUMA hints */ #define MM_CP_PROT_NUMA (1UL << 1) /* Whether this change is for write protecting */ @@ -3241,6 +3184,8 @@ enum mf_flags { MF_UNPOISON = 1 << 4, MF_SW_SIMULATED = 1 << 5, }; +int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index, + unsigned long count, int mf_flags); extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue(unsigned long pfn, int flags); extern void memory_failure_queue_kick(int cpu); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c29ab4c0cd5c..cf97f3884fda 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -87,6 +87,7 @@ struct page { */ union { struct list_head lru; + /* Or, for the Unevictable "LRU list" slot */ struct { /* Always even, to negate PageTail */ @@ -94,6 +95,10 @@ struct page { /* Count page's or folio's mlocks */ unsigned int mlock_count; }; + + /* Or, free page */ + struct list_head buddy_list; + struct list_head pcp_list; }; /* See page-flags.h for PAGE_MAPPING_FLAGS */ struct address_space *mapping; @@ -729,6 +734,7 @@ typedef __bitwise unsigned int vm_fault_t; * @VM_FAULT_NEEDDSYNC: ->fault did not modify page tables and needs * fsync() to complete (for synchronous page faults * in DAX) + * @VM_FAULT_COMPLETED: ->fault completed, meanwhile mmap lock released * @VM_FAULT_HINDEX_MASK: mask HINDEX value * */ @@ -746,6 +752,7 @@ enum vm_fault_reason { VM_FAULT_FALLBACK = (__force vm_fault_t)0x000800, VM_FAULT_DONE_COW = (__force vm_fault_t)0x001000, VM_FAULT_NEEDDSYNC = (__force vm_fault_t)0x002000, + VM_FAULT_COMPLETED = (__force vm_fault_t)0x004000, VM_FAULT_HINDEX_MASK = (__force vm_fault_t)0x0f0000, }; diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 45fc2c81e370..d6c06e140277 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -198,7 +198,7 @@ struct mmu_notifier_ops { * invalidate_range_start()/end() notifiers, as * invalidate_range() already catches the points in time when an * external TLB range needs to be flushed. For more in depth - * discussion on this see Documentation/vm/mmu_notifier.rst + * discussion on this see Documentation/mm/mmu_notifier.rst * * Note that this function might be called with just a sub-range * of what was passed to invalidate_range_start()/end(), if diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index aab70355d64f..e24b40c52468 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -355,15 +355,18 @@ enum zone_watermarks { }; /* - * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER plus one additional - * for pageblock size for THP if configured. + * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. One additional list + * for THP which will usually be GFP_MOVABLE. Even if it is another type, + * it should not contribute to serious fragmentation causing THP allocation + * failures. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define NR_PCP_THP 1 #else #define NR_PCP_THP 0 #endif -#define NR_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1 + NR_PCP_THP)) +#define NR_LOWORDER_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1)) +#define NR_PCP_LISTS (NR_LOWORDER_PCP_LISTS + NR_PCP_THP) /* * Shift to encode migratetype and order in the same integer, with order @@ -379,6 +382,7 @@ enum zone_watermarks { /* Fields and list protected by pagesets local_lock in page_alloc.c */ struct per_cpu_pages { + spinlock_t lock; /* Protects lists field */ int count; /* number of pages in the list */ int high; /* high watermark, emptying needed */ int batch; /* chunk size for buddy add/remove */ @@ -389,7 +393,7 @@ struct per_cpu_pages { /* Lists of pages, one per migrate type stored on the pcp-lists */ struct list_head lists[NR_PCP_LISTS]; -}; +} ____cacheline_aligned_in_smp; struct per_cpu_zonestat { #ifdef CONFIG_SMP @@ -591,8 +595,8 @@ struct zone { * give them a chance of being in the same cacheline. * * Write access to present_pages at runtime should be protected by - * mem_hotplug_begin/end(). Any reader who can't tolerant drift of - * present_pages should get_online_mems() to get a stable value. + * mem_hotplug_begin/done(). Any reader who can't tolerant drift of + * present_pages should use get_online_mems() to get a stable value. */ atomic_long_t managed_pages; unsigned long spanned_pages; @@ -730,6 +734,86 @@ static inline bool zone_is_empty(struct zone *zone) return zone->spanned_pages == 0; } +#ifndef BUILD_VDSO32_64 +/* + * The zone field is never updated after free_area_init_core() + * sets it, so none of the operations on it need to be atomic. + */ + +/* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_CPUPID] | ... | FLAGS | */ +#define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH) +#define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH) +#define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) +#define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH) +#define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH) + +/* + * Define the bit shifts to access each section. For non-existent + * sections we define the shift as 0; that plus a 0 mask ensures + * the compiler will optimise away reference to them. + */ +#define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0)) +#define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) +#define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) +#define LAST_CPUPID_PGSHIFT (LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0)) +#define KASAN_TAG_PGSHIFT (KASAN_TAG_PGOFF * (KASAN_TAG_WIDTH != 0)) + +/* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ +#ifdef NODE_NOT_IN_PAGE_FLAGS +#define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT) +#define ZONEID_PGOFF ((SECTIONS_PGOFF < ZONES_PGOFF) ? \ + SECTIONS_PGOFF : ZONES_PGOFF) +#else +#define ZONEID_SHIFT (NODES_SHIFT + ZONES_SHIFT) +#define ZONEID_PGOFF ((NODES_PGOFF < ZONES_PGOFF) ? \ + NODES_PGOFF : ZONES_PGOFF) +#endif + +#define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0)) + +#define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) +#define NODES_MASK ((1UL << NODES_WIDTH) - 1) +#define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) +#define LAST_CPUPID_MASK ((1UL << LAST_CPUPID_SHIFT) - 1) +#define KASAN_TAG_MASK ((1UL << KASAN_TAG_WIDTH) - 1) +#define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) + +static inline enum zone_type page_zonenum(const struct page *page) +{ + ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT); + return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; +} + +static inline enum zone_type folio_zonenum(const struct folio *folio) +{ + return page_zonenum(&folio->page); +} + +#ifdef CONFIG_ZONE_DEVICE +static inline bool is_zone_device_page(const struct page *page) +{ + return page_zonenum(page) == ZONE_DEVICE; +} +extern void memmap_init_zone_device(struct zone *, unsigned long, + unsigned long, struct dev_pagemap *); +#else +static inline bool is_zone_device_page(const struct page *page) +{ + return false; +} +#endif + +static inline bool folio_is_zone_device(const struct folio *folio) +{ + return is_zone_device_page(&folio->page); +} + +static inline bool is_zone_movable_page(const struct page *page) +{ + return page_zonenum(page) == ZONE_MOVABLE; +} +#endif + /* * Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty * intersection with the given zone @@ -870,7 +954,7 @@ typedef struct pglist_data { unsigned long nr_reclaim_start; /* nr pages written while throttled * when throttling started. */ struct task_struct *kswapd; /* Protected by - mem_hotplug_begin/end() */ + mem_hotplug_begin/done() */ int kswapd_order; enum zone_type kswapd_highest_zoneidx; @@ -1053,15 +1137,6 @@ static inline int is_highmem_idx(enum zone_type idx) #endif } -#ifdef CONFIG_ZONE_DMA -bool has_managed_dma(void); -#else -static inline bool has_managed_dma(void) -{ - return false; -} -#endif - /** * is_highmem - helper function to quickly check if a struct zone is a * highmem zone or not. This is an attempt to keep references @@ -1071,12 +1146,17 @@ static inline bool has_managed_dma(void) */ static inline int is_highmem(struct zone *zone) { -#ifdef CONFIG_HIGHMEM return is_highmem_idx(zone_idx(zone)); +} + +#ifdef CONFIG_ZONE_DMA +bool has_managed_dma(void); #else - return 0; -#endif +static inline bool has_managed_dma(void) +{ + return false; } +#endif /* These two functions are used to setup the per zone pages min values */ struct ctl_table; @@ -1418,16 +1498,32 @@ extern size_t mem_section_usage_size(void); * (equal SECTION_SIZE_BITS - PAGE_SHIFT), and the * worst combination is powerpc with 256k pages, * which results in PFN_SECTION_SHIFT equal 6. - * To sum it up, at least 6 bits are available. + * To sum it up, at least 6 bits are available on all architectures. + * However, we can exceed 6 bits on some other architectures except + * powerpc (e.g. 15 bits are available on x86_64, 13 bits are available + * with the worst case of 64K pages on arm64) if we make sure the + * exceeded bit is not applicable to powerpc. */ -#define SECTION_MARKED_PRESENT (1UL<<0) -#define SECTION_HAS_MEM_MAP (1UL<<1) -#define SECTION_IS_ONLINE (1UL<<2) -#define SECTION_IS_EARLY (1UL<<3) -#define SECTION_TAINT_ZONE_DEVICE (1UL<<4) -#define SECTION_MAP_LAST_BIT (1UL<<5) -#define SECTION_MAP_MASK (~(SECTION_MAP_LAST_BIT-1)) -#define SECTION_NID_SHIFT 6 +enum { + SECTION_MARKED_PRESENT_BIT, + SECTION_HAS_MEM_MAP_BIT, + SECTION_IS_ONLINE_BIT, + SECTION_IS_EARLY_BIT, +#ifdef CONFIG_ZONE_DEVICE + SECTION_TAINT_ZONE_DEVICE_BIT, +#endif + SECTION_MAP_LAST_BIT, +}; + +#define SECTION_MARKED_PRESENT BIT(SECTION_MARKED_PRESENT_BIT) +#define SECTION_HAS_MEM_MAP BIT(SECTION_HAS_MEM_MAP_BIT) +#define SECTION_IS_ONLINE BIT(SECTION_IS_ONLINE_BIT) +#define SECTION_IS_EARLY BIT(SECTION_IS_EARLY_BIT) +#ifdef CONFIG_ZONE_DEVICE +#define SECTION_TAINT_ZONE_DEVICE BIT(SECTION_TAINT_ZONE_DEVICE_BIT) +#endif +#define SECTION_MAP_MASK (~(BIT(SECTION_MAP_LAST_BIT) - 1)) +#define SECTION_NID_SHIFT SECTION_MAP_LAST_BIT static inline struct page *__section_mem_map_addr(struct mem_section *section) { @@ -1466,12 +1562,19 @@ static inline int online_section(struct mem_section *section) return (section && (section->section_mem_map & SECTION_IS_ONLINE)); } +#ifdef CONFIG_ZONE_DEVICE static inline int online_device_section(struct mem_section *section) { unsigned long flags = SECTION_IS_ONLINE | SECTION_TAINT_ZONE_DEVICE; return section && ((section->section_mem_map & flags) == flags); } +#else +static inline int online_device_section(struct mem_section *section) +{ + return 0; +} +#endif static inline int online_section_nr(unsigned long nr) { diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 3f5490f6f038..ea19528564d1 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -193,6 +193,11 @@ enum pageflags { /* Only valid for buddy pages. Used to track pages that are reported */ PG_reported = PG_uptodate, + +#ifdef CONFIG_MEMORY_HOTPLUG + /* For self-hosted memmap pages */ + PG_vmemmap_self_hosted = PG_owner_priv_1, +#endif }; #define PAGEFLAGS_MASK ((1UL << NR_PAGEFLAGS) - 1) @@ -628,6 +633,12 @@ PAGEFLAG_FALSE(SkipKASanPoison, skip_kasan_poison) */ __PAGEFLAG(Reported, reported, PF_NO_COMPOUND) +#ifdef CONFIG_MEMORY_HOTPLUG +PAGEFLAG(VmemmapSelfHosted, vmemmap_self_hosted, PF_ANY) +#else +PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted) +#endif + /* * On an anonymous page mapped into a user virtual memory area, * page->mapping points to its anon_vma, not to a struct address_space; @@ -650,6 +661,12 @@ __PAGEFLAG(Reported, reported, PF_NO_COMPOUND) #define PAGE_MAPPING_KSM (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) #define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) +/* + * Different with flags above, this flag is used only for fsdax mode. It + * indicates that this page->mapping is now under reflink case. + */ +#define PAGE_MAPPING_DAX_COW 0x1 + static __always_inline bool folio_mapping_flags(struct folio *folio) { return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) != 0; @@ -670,6 +687,12 @@ static __always_inline bool PageAnon(struct page *page) return folio_test_anon(page_folio(page)); } +static __always_inline bool __folio_test_movable(const struct folio *folio) +{ + return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) == + PAGE_MAPPING_MOVABLE; +} + static __always_inline int __PageMovable(struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index cc9adbaddb59..0178b2040ea3 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -345,8 +345,6 @@ static inline void filemap_nr_thps_dec(struct address_space *mapping) #endif } -void release_pages(struct page **pages, int nr); - struct address_space *page_mapping(struct page *); struct address_space *folio_mapping(struct folio *); struct address_space *swapcache_mapping(struct folio *); diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index 6649154a2115..215eb6c3bdc9 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -26,7 +26,6 @@ struct pagevec { }; void __pagevec_release(struct pagevec *pvec); -void __pagevec_lru_add(struct pagevec *pvec); unsigned pagevec_lookup_range_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag); diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 3cdc16cfd867..014ee8f0fbaa 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1689,4 +1689,32 @@ typedef unsigned int pgtbl_mod_mask; #define MAX_PTRS_PER_P4D PTRS_PER_P4D #endif +/* description of effects of mapping type and prot in current implementation. + * this is due to the limited x86 page protection hardware. The expected + * behavior is in parens: + * + * map_type prot + * PROT_NONE PROT_READ PROT_WRITE PROT_EXEC + * MAP_SHARED r: (no) no r: (yes) yes r: (no) yes r: (no) yes + * w: (no) no w: (no) no w: (yes) yes w: (no) no + * x: (no) no x: (no) yes x: (no) yes x: (yes) yes + * + * MAP_PRIVATE r: (no) no r: (yes) yes r: (no) yes r: (no) yes + * w: (no) no w: (no) no w: (copy) copy w: (no) no + * x: (no) no x: (no) yes x: (no) yes x: (yes) yes + * + * On arm64, PROT_EXEC has the following behaviour for both MAP_SHARED and + * MAP_PRIVATE (with Enhanced PAN supported): + * r: (no) no + * w: (no) no + * x: (yes) yes + */ +#define DECLARE_VM_GET_PAGE_PROT \ +pgprot_t vm_get_page_prot(unsigned long vm_flags) \ +{ \ + return protection_map[vm_flags & \ + (VM_READ | VM_WRITE | VM_EXEC | VM_SHARED)]; \ +} \ +EXPORT_SYMBOL(vm_get_page_prot); + #endif /* _LINUX_PGTABLE_H */ diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 9ec23138e410..bf80adca980b 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -325,8 +325,8 @@ struct page_vma_mapped_walk { #define DEFINE_PAGE_VMA_WALK(name, _page, _vma, _address, _flags) \ struct page_vma_mapped_walk name = { \ .pfn = page_to_pfn(_page), \ - .nr_pages = compound_nr(page), \ - .pgoff = page_to_pgoff(page), \ + .nr_pages = compound_nr(_page), \ + .pgoff = page_to_pgoff(_page), \ .vma = _vma, \ .address = _address, \ .flags = _flags, \ diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 8cd975a8bfeb..2a243616f222 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -29,7 +29,7 @@ extern struct mm_struct *mm_alloc(void); * * Use mmdrop() to release the reference acquired by mmgrab(). * - * See also <Documentation/vm/active_mm.rst> for an in-depth explanation + * See also <Documentation/mm/active_mm.rst> for an in-depth explanation * of &mm_struct.mm_count vs &mm_struct.mm_users. */ static inline void mmgrab(struct mm_struct *mm) @@ -92,7 +92,7 @@ static inline void mmdrop_sched(struct mm_struct *mm) * * Use mmput() to release the reference acquired by mmget(). * - * See also <Documentation/vm/active_mm.rst> for an in-depth explanation + * See also <Documentation/mm/active_mm.rst> for an in-depth explanation * of &mm_struct.mm_count vs &mm_struct.mm_users. */ static inline void mmget(struct mm_struct *mm) diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index a68f982f22d1..1b6c4013f691 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -25,9 +25,20 @@ struct shmem_inode_info { struct simple_xattrs xattrs; /* list of xattrs */ atomic_t stop_eviction; /* hold when working on inode */ struct timespec64 i_crtime; /* file creation time */ + unsigned int fsflags; /* flags for FS_IOC_[SG]ETFLAGS */ struct inode vfs_inode; }; +#define SHMEM_FL_USER_VISIBLE FS_FL_USER_VISIBLE +#define SHMEM_FL_USER_MODIFIABLE FS_FL_USER_MODIFIABLE +#define SHMEM_FL_INHERITED FS_FL_USER_MODIFIABLE + +/* Flags that are appropriate for regular files (all but dir-specific ones). */ +#define SHMEM_REG_FLMASK (~(FS_DIRSYNC_FL | FS_TOPDIR_FL)) + +/* Flags that are appropriate for non-directories/regular files. */ +#define SHMEM_OTHER_FLMASK (FS_NODUMP_FL | FS_NOATIME_FL) + struct shmem_sb_info { unsigned long max_blocks; /* How many blocks are allowed */ struct percpu_counter used_blocks; /* How many are allocated */ diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 76fbf92b04d9..08e6054e061f 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -73,6 +73,11 @@ struct shrinker { /* ID in shrinker_idr */ int id; #endif +#ifdef CONFIG_SHRINKER_DEBUG + int debugfs_id; + const char *name; + struct dentry *debugfs_entry; +#endif /* objs pending delete, per node */ atomic_long_t *nr_deferred; }; @@ -88,10 +93,32 @@ struct shrinker { */ #define SHRINKER_NONSLAB (1 << 3) -extern int prealloc_shrinker(struct shrinker *shrinker); +extern int __printf(2, 3) prealloc_shrinker(struct shrinker *shrinker, + const char *fmt, ...); extern void register_shrinker_prepared(struct shrinker *shrinker); -extern int register_shrinker(struct shrinker *shrinker); +extern int __printf(2, 3) register_shrinker(struct shrinker *shrinker, + const char *fmt, ...); extern void unregister_shrinker(struct shrinker *shrinker); extern void free_prealloced_shrinker(struct shrinker *shrinker); extern void synchronize_shrinkers(void); -#endif + +#ifdef CONFIG_SHRINKER_DEBUG +extern int shrinker_debugfs_add(struct shrinker *shrinker); +extern void shrinker_debugfs_remove(struct shrinker *shrinker); +extern int __printf(2, 3) shrinker_debugfs_rename(struct shrinker *shrinker, + const char *fmt, ...); +#else /* CONFIG_SHRINKER_DEBUG */ +static inline int shrinker_debugfs_add(struct shrinker *shrinker) +{ + return 0; +} +static inline void shrinker_debugfs_remove(struct shrinker *shrinker) +{ +} +static inline __printf(2, 3) +int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) +{ + return 0; +} +#endif /* CONFIG_SHRINKER_DEBUG */ +#endif /* _LINUX_SHRINKER_H */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 8672a7123ccd..43150b9bbc5c 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -74,7 +74,7 @@ static inline int current_is_kswapd(void) /* * Unaddressable device memory support. See include/linux/hmm.h and - * Documentation/vm/hmm.rst. Short description is we need struct pages for + * Documentation/mm/hmm.rst. Short description is we need struct pages for * device memory that is unaddressable (inaccessible) by CPU, so that we can * migrate part of a process memory to device memory. * @@ -411,10 +411,13 @@ extern void lru_cache_add_inactive_or_unevictable(struct page *page, extern unsigned long zone_reclaimable_pages(struct zone *zone); extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); + +#define MEMCG_RECLAIM_MAY_SWAP (1 << 1) +#define MEMCG_RECLAIM_PROACTIVE (1 << 2) extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, - bool may_swap); + unsigned int reclaim_options); extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, @@ -456,6 +459,7 @@ static inline unsigned long total_swapcache_pages(void) return global_node_page_state(NR_SWAPCACHE); } +extern void free_swap_cache(struct page *page); extern void free_page_and_swap_cache(struct page *); extern void free_pages_and_swap_cache(struct page **, int); /* linux/mm/swapfile.c */ @@ -540,6 +544,10 @@ static inline void put_swap_device(struct swap_info_struct *si) /* used to sanity check ptes in zap_pte_range when CONFIG_SWAP=0 */ #define free_swap_and_cache(e) is_pfn_swap_entry(e) +static inline void free_swap_cache(struct page *page) +{ +} + static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask) { return 0; diff --git a/include/linux/swapops.h b/include/linux/swapops.h index f24775b41880..bb7afd03a324 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -244,8 +244,10 @@ extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl); extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address); -extern void migration_entry_wait_huge(struct vm_area_struct *vma, - struct mm_struct *mm, pte_t *pte); +#ifdef CONFIG_HUGETLB_PAGE +extern void __migration_entry_wait_huge(pte_t *ptep, spinlock_t *ptl); +extern void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte); +#endif #else static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { @@ -271,8 +273,10 @@ static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl) { } static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } -static inline void migration_entry_wait_huge(struct vm_area_struct *vma, - struct mm_struct *mm, pte_t *pte) { } +#ifdef CONFIG_HUGETLB_PAGE +static inline void __migration_entry_wait_huge(pte_t *ptep, spinlock_t *ptl) { } +static inline void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte) { } +#endif static inline int is_writable_migration_entry(swp_entry_t entry) { return 0; diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 3dc968006ad0..79aea7df4345 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -4574,7 +4574,7 @@ static void __init kfree_rcu_batch_init(void) INIT_DELAYED_WORK(&krcp->page_cache_work, fill_page_cache_func); krcp->initialized = true; } - if (register_shrinker(&kfree_rcu_shrinker)) + if (register_shrinker(&kfree_rcu_shrinker, "rcu-kfree")) pr_err("Failed to register kfree_rcu() shrinker!\n"); } diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 35cd8287642a..403071ff0bcf 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -699,6 +699,14 @@ config DEBUG_OBJECTS_ENABLE_DEFAULT help Debug objects boot parameter default value +config SHRINKER_DEBUG + bool "Enable shrinker debugging support" + depends on DEBUG_FS + help + Say Y to enable the shrinker debugfs interface which provides + visibility into the kernel memory shrinkers subsystem. + Disable it to avoid an extra memory footprint. + config HAVE_DEBUG_KMEMLEAK bool diff --git a/lib/test_free_pages.c b/lib/test_free_pages.c index 25ae1ac2624a..9ebf6f5549f3 100644 --- a/lib/test_free_pages.c +++ b/lib/test_free_pages.c @@ -17,7 +17,7 @@ static void test_free_pages(gfp_t gfp) for (i = 0; i < 1000 * 1000; i++) { unsigned long addr = __get_free_pages(gfp, 3); - struct page *page = virt_to_page(addr); + struct page *page = virt_to_page((void *)addr); /* Simulate page cache getting a speculative reference */ get_page(page); diff --git a/lib/test_hmm.c b/lib/test_hmm.c index cfe632047839..e3965cafd27c 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -32,11 +32,32 @@ #include "test_hmm_uapi.h" -#define DMIRROR_NDEVICES 2 +#define DMIRROR_NDEVICES 4 #define DMIRROR_RANGE_FAULT_TIMEOUT 1000 #define DEVMEM_CHUNK_SIZE (256 * 1024 * 1024U) #define DEVMEM_CHUNKS_RESERVE 16 +/* + * For device_private pages, dpage is just a dummy struct page + * representing a piece of device memory. dmirror_devmem_alloc_page + * allocates a real system memory page as backing storage to fake a + * real device. zone_device_data points to that backing page. But + * for device_coherent memory, the struct page represents real + * physical CPU-accessible memory that we can use directly. + */ +#define BACKING_PAGE(page) (is_device_private_page((page)) ? \ + (page)->zone_device_data : (page)) + +static unsigned long spm_addr_dev0; +module_param(spm_addr_dev0, long, 0644); +MODULE_PARM_DESC(spm_addr_dev0, + "Specify start address for SPM (special purpose memory) used for device 0. By setting this Coherent device type will be used. Make sure spm_addr_dev1 is set too. Minimum SPM size should be DEVMEM_CHUNK_SIZE."); + +static unsigned long spm_addr_dev1; +module_param(spm_addr_dev1, long, 0644); +MODULE_PARM_DESC(spm_addr_dev1, + "Specify start address for SPM (special purpose memory) used for device 1. By setting this Coherent device type will be used. Make sure spm_addr_dev0 is set too. Minimum SPM size should be DEVMEM_CHUNK_SIZE."); + static const struct dev_pagemap_ops dmirror_devmem_ops; static const struct mmu_interval_notifier_ops dmirror_min_ops; static dev_t dmirror_dev; @@ -87,6 +108,7 @@ struct dmirror_chunk { struct dmirror_device { struct cdev cdevice; struct hmm_devmem *devmem; + unsigned int zone_device_type; unsigned int devmem_capacity; unsigned int devmem_count; @@ -114,6 +136,21 @@ static int dmirror_bounce_init(struct dmirror_bounce *bounce, return 0; } +static bool dmirror_is_private_zone(struct dmirror_device *mdevice) +{ + return (mdevice->zone_device_type == + HMM_DMIRROR_MEMORY_DEVICE_PRIVATE) ? true : false; +} + +static enum migrate_vma_direction +dmirror_select_device(struct dmirror *dmirror) +{ + return (dmirror->mdevice->zone_device_type == + HMM_DMIRROR_MEMORY_DEVICE_PRIVATE) ? + MIGRATE_VMA_SELECT_DEVICE_PRIVATE : + MIGRATE_VMA_SELECT_DEVICE_COHERENT; +} + static void dmirror_bounce_fini(struct dmirror_bounce *bounce) { vfree(bounce->ptr); @@ -454,28 +491,44 @@ fini: return ret; } -static bool dmirror_allocate_chunk(struct dmirror_device *mdevice, +static int dmirror_allocate_chunk(struct dmirror_device *mdevice, struct page **ppage) { struct dmirror_chunk *devmem; - struct resource *res; + struct resource *res = NULL; unsigned long pfn; unsigned long pfn_first; unsigned long pfn_last; void *ptr; + int ret = -ENOMEM; devmem = kzalloc(sizeof(*devmem), GFP_KERNEL); if (!devmem) - return false; + return ret; - res = request_free_mem_region(&iomem_resource, DEVMEM_CHUNK_SIZE, - "hmm_dmirror"); - if (IS_ERR(res)) + switch (mdevice->zone_device_type) { + case HMM_DMIRROR_MEMORY_DEVICE_PRIVATE: + res = request_free_mem_region(&iomem_resource, DEVMEM_CHUNK_SIZE, + "hmm_dmirror"); + if (IS_ERR_OR_NULL(res)) + goto err_devmem; + devmem->pagemap.range.start = res->start; + devmem->pagemap.range.end = res->end; + devmem->pagemap.type = MEMORY_DEVICE_PRIVATE; + break; + case HMM_DMIRROR_MEMORY_DEVICE_COHERENT: + devmem->pagemap.range.start = (MINOR(mdevice->cdevice.dev) - 2) ? + spm_addr_dev0 : + spm_addr_dev1; + devmem->pagemap.range.end = devmem->pagemap.range.start + + DEVMEM_CHUNK_SIZE - 1; + devmem->pagemap.type = MEMORY_DEVICE_COHERENT; + break; + default: + ret = -EINVAL; goto err_devmem; + } - devmem->pagemap.type = MEMORY_DEVICE_PRIVATE; - devmem->pagemap.range.start = res->start; - devmem->pagemap.range.end = res->end; devmem->pagemap.nr_range = 1; devmem->pagemap.ops = &dmirror_devmem_ops; devmem->pagemap.owner = mdevice; @@ -496,10 +549,14 @@ static bool dmirror_allocate_chunk(struct dmirror_device *mdevice, mdevice->devmem_capacity = new_capacity; mdevice->devmem_chunks = new_chunks; } - ptr = memremap_pages(&devmem->pagemap, numa_node_id()); - if (IS_ERR(ptr)) + if (IS_ERR_OR_NULL(ptr)) { + if (ptr) + ret = PTR_ERR(ptr); + else + ret = -EFAULT; goto err_release; + } devmem->mdevice = mdevice; pfn_first = devmem->pagemap.range.start >> PAGE_SHIFT; @@ -528,30 +585,35 @@ static bool dmirror_allocate_chunk(struct dmirror_device *mdevice, } spin_unlock(&mdevice->lock); - return true; + return 0; err_release: mutex_unlock(&mdevice->devmem_lock); - release_mem_region(devmem->pagemap.range.start, range_len(&devmem->pagemap.range)); + if (res && devmem->pagemap.type == MEMORY_DEVICE_PRIVATE) + release_mem_region(devmem->pagemap.range.start, + range_len(&devmem->pagemap.range)); err_devmem: kfree(devmem); - return false; + return ret; } static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice) { struct page *dpage = NULL; - struct page *rpage; + struct page *rpage = NULL; /* - * This is a fake device so we alloc real system memory to store - * our device memory. + * For ZONE_DEVICE private type, this is a fake device so we allocate + * real system memory to store our device memory. + * For ZONE_DEVICE coherent type we use the actual dpage to store the + * data and ignore rpage. */ - rpage = alloc_page(GFP_HIGHUSER); - if (!rpage) - return NULL; - + if (dmirror_is_private_zone(mdevice)) { + rpage = alloc_page(GFP_HIGHUSER); + if (!rpage) + return NULL; + } spin_lock(&mdevice->lock); if (mdevice->free_pages) { @@ -561,7 +623,7 @@ static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice) spin_unlock(&mdevice->lock); } else { spin_unlock(&mdevice->lock); - if (!dmirror_allocate_chunk(mdevice, &dpage)) + if (dmirror_allocate_chunk(mdevice, &dpage)) goto error; } @@ -570,7 +632,8 @@ static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice) return dpage; error: - __free_page(rpage); + if (rpage) + __free_page(rpage); return NULL; } @@ -596,12 +659,16 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args, * unallocated pte_none() or read-only zero page. */ spage = migrate_pfn_to_page(*src); + if (WARN(spage && is_zone_device_page(spage), + "page already in device spage pfn: 0x%lx\n", + page_to_pfn(spage))) + continue; dpage = dmirror_devmem_alloc_page(mdevice); if (!dpage) continue; - rpage = dpage->zone_device_data; + rpage = BACKING_PAGE(dpage); if (spage) copy_highpage(rpage, spage); else @@ -615,6 +682,8 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args, */ rpage->zone_device_data = dmirror; + pr_debug("migrating from sys to dev pfn src: 0x%lx pfn dst: 0x%lx\n", + page_to_pfn(spage), page_to_pfn(dpage)); *dst = migrate_pfn(page_to_pfn(dpage)); if ((*src & MIGRATE_PFN_WRITE) || (!spage && args->vma->vm_flags & VM_WRITE)) @@ -692,11 +761,7 @@ static int dmirror_migrate_finalize_and_map(struct migrate_vma *args, if (!dpage) continue; - /* - * Store the page that holds the data so the page table - * doesn't have to deal with ZONE_DEVICE private pages. - */ - entry = dpage->zone_device_data; + entry = BACKING_PAGE(dpage); if (*dst & MIGRATE_PFN_WRITE) entry = xa_tag_pointer(entry, DPT_XA_TAG_WRITE); entry = xa_store(&dmirror->pt, pfn, entry, GFP_ATOMIC); @@ -732,7 +797,7 @@ static int dmirror_exclusive(struct dmirror *dmirror, mmap_read_lock(mm); for (addr = start; addr < end; addr = next) { - unsigned long mapped; + unsigned long mapped = 0; int i; if (end < addr + (ARRAY_SIZE(pages) << PAGE_SHIFT)) @@ -741,7 +806,13 @@ static int dmirror_exclusive(struct dmirror *dmirror, next = addr + (ARRAY_SIZE(pages) << PAGE_SHIFT); ret = make_device_exclusive_range(mm, addr, next, pages, NULL); - mapped = dmirror_atomic_map(addr, next, pages, dmirror); + /* + * Do dmirror_atomic_map() iff all pages are marked for + * exclusive access to avoid accessing uninitialized + * fields of pages. + */ + if (ret == (next - addr) >> PAGE_SHIFT) + mapped = dmirror_atomic_map(addr, next, pages, dmirror); for (i = 0; i < ret; i++) { if (pages[i]) { unlock_page(pages[i]); @@ -776,15 +847,126 @@ static int dmirror_exclusive(struct dmirror *dmirror, return ret; } -static int dmirror_migrate(struct dmirror *dmirror, - struct hmm_dmirror_cmd *cmd) +static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args, + struct dmirror *dmirror) +{ + const unsigned long *src = args->src; + unsigned long *dst = args->dst; + unsigned long start = args->start; + unsigned long end = args->end; + unsigned long addr; + + for (addr = start; addr < end; addr += PAGE_SIZE, + src++, dst++) { + struct page *dpage, *spage; + + spage = migrate_pfn_to_page(*src); + if (!spage || !(*src & MIGRATE_PFN_MIGRATE)) + continue; + + if (WARN_ON(!is_device_private_page(spage) && + !is_device_coherent_page(spage))) + continue; + spage = BACKING_PAGE(spage); + dpage = alloc_page_vma(GFP_HIGHUSER_MOVABLE, args->vma, addr); + if (!dpage) + continue; + pr_debug("migrating from dev to sys pfn src: 0x%lx pfn dst: 0x%lx\n", + page_to_pfn(spage), page_to_pfn(dpage)); + + lock_page(dpage); + xa_erase(&dmirror->pt, addr >> PAGE_SHIFT); + copy_highpage(dpage, spage); + *dst = migrate_pfn(page_to_pfn(dpage)); + if (*src & MIGRATE_PFN_WRITE) + *dst |= MIGRATE_PFN_WRITE; + } + return 0; +} + +static unsigned long +dmirror_successful_migrated_pages(struct migrate_vma *migrate) +{ + unsigned long cpages = 0; + unsigned long i; + + for (i = 0; i < migrate->npages; i++) { + if (migrate->src[i] & MIGRATE_PFN_VALID && + migrate->src[i] & MIGRATE_PFN_MIGRATE) + cpages++; + } + return cpages; +} + +static int dmirror_migrate_to_system(struct dmirror *dmirror, + struct hmm_dmirror_cmd *cmd) { unsigned long start, end, addr; unsigned long size = cmd->npages << PAGE_SHIFT; struct mm_struct *mm = dmirror->notifier.mm; struct vm_area_struct *vma; - unsigned long src_pfns[64]; - unsigned long dst_pfns[64]; + unsigned long src_pfns[64] = { 0 }; + unsigned long dst_pfns[64] = { 0 }; + struct migrate_vma args; + unsigned long next; + int ret; + + start = cmd->addr; + end = start + size; + if (end < start) + return -EINVAL; + + /* Since the mm is for the mirrored process, get a reference first. */ + if (!mmget_not_zero(mm)) + return -EINVAL; + + cmd->cpages = 0; + mmap_read_lock(mm); + for (addr = start; addr < end; addr = next) { + vma = vma_lookup(mm, addr); + if (!vma || !(vma->vm_flags & VM_READ)) { + ret = -EINVAL; + goto out; + } + next = min(end, addr + (ARRAY_SIZE(src_pfns) << PAGE_SHIFT)); + if (next > vma->vm_end) + next = vma->vm_end; + + args.vma = vma; + args.src = src_pfns; + args.dst = dst_pfns; + args.start = addr; + args.end = next; + args.pgmap_owner = dmirror->mdevice; + args.flags = dmirror_select_device(dmirror); + + ret = migrate_vma_setup(&args); + if (ret) + goto out; + + pr_debug("Migrating from device mem to sys mem\n"); + dmirror_devmem_fault_alloc_and_copy(&args, dmirror); + + migrate_vma_pages(&args); + cmd->cpages += dmirror_successful_migrated_pages(&args); + migrate_vma_finalize(&args); + } +out: + mmap_read_unlock(mm); + mmput(mm); + + return ret; +} + +static int dmirror_migrate_to_device(struct dmirror *dmirror, + struct hmm_dmirror_cmd *cmd) +{ + unsigned long start, end, addr; + unsigned long size = cmd->npages << PAGE_SHIFT; + struct mm_struct *mm = dmirror->notifier.mm; + struct vm_area_struct *vma; + unsigned long src_pfns[64] = { 0 }; + unsigned long dst_pfns[64] = { 0 }; struct dmirror_bounce bounce; struct migrate_vma args; unsigned long next; @@ -821,6 +1003,7 @@ static int dmirror_migrate(struct dmirror *dmirror, if (ret) goto out; + pr_debug("Migrating from sys mem to device mem\n"); dmirror_migrate_alloc_and_copy(&args, dmirror); migrate_vma_pages(&args); dmirror_migrate_finalize_and_map(&args, dmirror); @@ -829,7 +1012,10 @@ static int dmirror_migrate(struct dmirror *dmirror, mmap_read_unlock(mm); mmput(mm); - /* Return the migrated data for verification. */ + /* + * Return the migrated data for verification. + * Only for pages in device zone + */ ret = dmirror_bounce_init(&bounce, start, size); if (ret) return ret; @@ -872,6 +1058,12 @@ static void dmirror_mkentry(struct dmirror *dmirror, struct hmm_range *range, *perm = HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL; else *perm = HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE; + } else if (is_device_coherent_page(page)) { + /* Is the page migrated to this device or some other? */ + if (dmirror->mdevice == dmirror_page_to_device(page)) + *perm = HMM_DMIRROR_PROT_DEV_COHERENT_LOCAL; + else + *perm = HMM_DMIRROR_PROT_DEV_COHERENT_REMOTE; } else if (is_zero_pfn(page_to_pfn(page))) *perm = HMM_DMIRROR_PROT_ZERO; else @@ -1059,8 +1251,12 @@ static long dmirror_fops_unlocked_ioctl(struct file *filp, ret = dmirror_write(dmirror, &cmd); break; - case HMM_DMIRROR_MIGRATE: - ret = dmirror_migrate(dmirror, &cmd); + case HMM_DMIRROR_MIGRATE_TO_DEV: + ret = dmirror_migrate_to_device(dmirror, &cmd); + break; + + case HMM_DMIRROR_MIGRATE_TO_SYS: + ret = dmirror_migrate_to_system(dmirror, &cmd); break; case HMM_DMIRROR_EXCLUSIVE: @@ -1122,14 +1318,13 @@ static const struct file_operations dmirror_fops = { static void dmirror_devmem_free(struct page *page) { - struct page *rpage = page->zone_device_data; + struct page *rpage = BACKING_PAGE(page); struct dmirror_device *mdevice; - if (rpage) + if (rpage != page) __free_page(rpage); mdevice = dmirror_page_to_device(page); - spin_lock(&mdevice->lock); mdevice->cfree++; page->zone_device_data = mdevice->free_pages; @@ -1137,43 +1332,11 @@ static void dmirror_devmem_free(struct page *page) spin_unlock(&mdevice->lock); } -static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args, - struct dmirror *dmirror) -{ - const unsigned long *src = args->src; - unsigned long *dst = args->dst; - unsigned long start = args->start; - unsigned long end = args->end; - unsigned long addr; - - for (addr = start; addr < end; addr += PAGE_SIZE, - src++, dst++) { - struct page *dpage, *spage; - - spage = migrate_pfn_to_page(*src); - if (!spage || !(*src & MIGRATE_PFN_MIGRATE)) - continue; - spage = spage->zone_device_data; - - dpage = alloc_page_vma(GFP_HIGHUSER_MOVABLE, args->vma, addr); - if (!dpage) - continue; - - lock_page(dpage); - xa_erase(&dmirror->pt, addr >> PAGE_SHIFT); - copy_highpage(dpage, spage); - *dst = migrate_pfn(page_to_pfn(dpage)); - if (*src & MIGRATE_PFN_WRITE) - *dst |= MIGRATE_PFN_WRITE; - } - return 0; -} - static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf) { struct migrate_vma args; - unsigned long src_pfns; - unsigned long dst_pfns; + unsigned long src_pfns = 0; + unsigned long dst_pfns = 0; struct page *rpage; struct dmirror *dmirror; vm_fault_t ret; @@ -1193,7 +1356,7 @@ static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf) args.src = &src_pfns; args.dst = &dst_pfns; args.pgmap_owner = dmirror->mdevice; - args.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE; + args.flags = dmirror_select_device(dmirror); if (migrate_vma_setup(&args)) return VM_FAULT_SIGBUS; @@ -1231,10 +1394,8 @@ static int dmirror_device_init(struct dmirror_device *mdevice, int id) if (ret) return ret; - /* Build a list of free ZONE_DEVICE private struct pages */ - dmirror_allocate_chunk(mdevice, NULL); - - return 0; + /* Build a list of free ZONE_DEVICE struct pages */ + return dmirror_allocate_chunk(mdevice, NULL); } static void dmirror_device_remove(struct dmirror_device *mdevice) @@ -1247,8 +1408,9 @@ static void dmirror_device_remove(struct dmirror_device *mdevice) mdevice->devmem_chunks[i]; memunmap_pages(&devmem->pagemap); - release_mem_region(devmem->pagemap.range.start, - range_len(&devmem->pagemap.range)); + if (devmem->pagemap.type == MEMORY_DEVICE_PRIVATE) + release_mem_region(devmem->pagemap.range.start, + range_len(&devmem->pagemap.range)); kfree(devmem); } kfree(mdevice->devmem_chunks); @@ -1260,14 +1422,26 @@ static void dmirror_device_remove(struct dmirror_device *mdevice) static int __init hmm_dmirror_init(void) { int ret; - int id; + int id = 0; + int ndevices = 0; ret = alloc_chrdev_region(&dmirror_dev, 0, DMIRROR_NDEVICES, "HMM_DMIRROR"); if (ret) goto err_unreg; - for (id = 0; id < DMIRROR_NDEVICES; id++) { + memset(dmirror_devices, 0, DMIRROR_NDEVICES * sizeof(dmirror_devices[0])); + dmirror_devices[ndevices++].zone_device_type = + HMM_DMIRROR_MEMORY_DEVICE_PRIVATE; + dmirror_devices[ndevices++].zone_device_type = + HMM_DMIRROR_MEMORY_DEVICE_PRIVATE; + if (spm_addr_dev0 && spm_addr_dev1) { + dmirror_devices[ndevices++].zone_device_type = + HMM_DMIRROR_MEMORY_DEVICE_COHERENT; + dmirror_devices[ndevices++].zone_device_type = + HMM_DMIRROR_MEMORY_DEVICE_COHERENT; + } + for (id = 0; id < ndevices; id++) { ret = dmirror_device_init(dmirror_devices + id, id); if (ret) goto err_chrdev; @@ -1289,7 +1463,8 @@ static void __exit hmm_dmirror_exit(void) int id; for (id = 0; id < DMIRROR_NDEVICES; id++) - dmirror_device_remove(dmirror_devices + id); + if (dmirror_devices[id].zone_device_type) + dmirror_device_remove(dmirror_devices + id); unregister_chrdev_region(dmirror_dev, DMIRROR_NDEVICES); } diff --git a/lib/test_hmm_uapi.h b/lib/test_hmm_uapi.h index f14dea5dcd06..e31d58c9034a 100644 --- a/lib/test_hmm_uapi.h +++ b/lib/test_hmm_uapi.h @@ -31,10 +31,11 @@ struct hmm_dmirror_cmd { /* Expose the address space of the calling process through hmm device file */ #define HMM_DMIRROR_READ _IOWR('H', 0x00, struct hmm_dmirror_cmd) #define HMM_DMIRROR_WRITE _IOWR('H', 0x01, struct hmm_dmirror_cmd) -#define HMM_DMIRROR_MIGRATE _IOWR('H', 0x02, struct hmm_dmirror_cmd) -#define HMM_DMIRROR_SNAPSHOT _IOWR('H', 0x03, struct hmm_dmirror_cmd) -#define HMM_DMIRROR_EXCLUSIVE _IOWR('H', 0x04, struct hmm_dmirror_cmd) -#define HMM_DMIRROR_CHECK_EXCLUSIVE _IOWR('H', 0x05, struct hmm_dmirror_cmd) +#define HMM_DMIRROR_MIGRATE_TO_DEV _IOWR('H', 0x02, struct hmm_dmirror_cmd) +#define HMM_DMIRROR_MIGRATE_TO_SYS _IOWR('H', 0x03, struct hmm_dmirror_cmd) +#define HMM_DMIRROR_SNAPSHOT _IOWR('H', 0x04, struct hmm_dmirror_cmd) +#define HMM_DMIRROR_EXCLUSIVE _IOWR('H', 0x05, struct hmm_dmirror_cmd) +#define HMM_DMIRROR_CHECK_EXCLUSIVE _IOWR('H', 0x06, struct hmm_dmirror_cmd) /* * Values returned in hmm_dmirror_cmd.ptr for HMM_DMIRROR_SNAPSHOT. @@ -49,6 +50,8 @@ struct hmm_dmirror_cmd { * device the ioctl() is made * HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE: Migrated device private page on some * other device + * HMM_DMIRROR_PROT_DEV_COHERENT: Migrate device coherent page on the device + * the ioctl() is made */ enum { HMM_DMIRROR_PROT_ERROR = 0xFF, @@ -60,6 +63,14 @@ enum { HMM_DMIRROR_PROT_ZERO = 0x10, HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL = 0x20, HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE = 0x30, + HMM_DMIRROR_PROT_DEV_COHERENT_LOCAL = 0x40, + HMM_DMIRROR_PROT_DEV_COHERENT_REMOTE = 0x50, +}; + +enum { + /* 0 is reserved to catch uninitialized type fields */ + HMM_DMIRROR_MEMORY_DEVICE_PRIVATE = 1, + HMM_DMIRROR_MEMORY_DEVICE_COHERENT, }; #endif /* _LIB_TEST_HMM_UAPI_H */ diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c index cf41fd6df42a..4f2f2d1bac56 100644 --- a/lib/test_vmalloc.c +++ b/lib/test_vmalloc.c @@ -74,12 +74,13 @@ test_report_one_done(void) static int random_size_align_alloc_test(void) { - unsigned long size, align, rnd; + unsigned long size, align; + unsigned int rnd; void *ptr; int i; for (i = 0; i < test_loop_count; i++) { - get_random_bytes(&rnd, sizeof(rnd)); + rnd = prandom_u32(); /* * Maximum 1024 pages, if PAGE_SIZE is 4096. @@ -150,7 +151,7 @@ static int random_size_alloc_test(void) int i; for (i = 0; i < test_loop_count; i++) { - get_random_bytes(&n, sizeof(i)); + n = prandom_u32(); n = (n % 100) + 1; p = vmalloc(n * PAGE_SIZE); @@ -294,14 +295,14 @@ pcpu_alloc_test(void) for (i = 0; i < 35000; i++) { unsigned int r; - get_random_bytes(&r, sizeof(i)); + r = prandom_u32(); size = (r % (PAGE_SIZE / 4)) + 1; /* * Maximum PAGE_SIZE */ - get_random_bytes(&r, sizeof(i)); - align = 1 << ((i % 11) + 1); + r = prandom_u32(); + align = 1 << ((r % 11) + 1); pcpu[i] = __alloc_percpu(size, align); if (!pcpu[i]) @@ -396,7 +397,7 @@ static void shuffle_array(int *arr, int n) int i, j; for (i = n - 1; i > 0; i--) { - get_random_bytes(&rnd, sizeof(rnd)); + rnd = prandom_u32(); /* Cut the range. */ j = rnd % i; diff --git a/mm/Kconfig b/mm/Kconfig index b7a44b17c79f..e59cf5fe5ce9 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -33,7 +33,7 @@ config ZSWAP pages that are in the process of being swapped out and attempts to compress them into a dynamically allocated RAM-based memory pool. This can result in a significant I/O reduction on swap device and, - in the case where decompressing from RAM is faster that swap device + in the case where decompressing from RAM is faster than swap device reads, can also improve workload performance. This is marked experimental because it is a new feature (as of @@ -655,7 +655,7 @@ config KSM the many instances by a single page with that content, so saving memory until one or another app needs to modify the content. Recommended for use with KVM, or with other duplicative applications. - See Documentation/vm/ksm.rst for more information: KSM is inactive + See Documentation/mm/ksm.rst for more information: KSM is inactive until a program has madvised that an area is MADV_MERGEABLE, and root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set). @@ -943,9 +943,6 @@ config ARCH_HAS_CURRENT_STACK_POINTER register alias named "current_stack_pointer", this config can be selected. -config ARCH_HAS_VM_GET_PAGE_PROT - bool - config ARCH_HAS_PTE_DEVMAP bool diff --git a/mm/Makefile b/mm/Makefile index 6f9ffa968a1a..9a564f836403 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -133,3 +133,4 @@ 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 +obj-$(CONFIG_SHRINKER_DEBUG) += shrinker_debug.o diff --git a/mm/cma_debug.c b/mm/cma_debug.c index 2e7704955f4f..c3ffe253e055 100644 --- a/mm/cma_debug.c +++ b/mm/cma_debug.c @@ -163,7 +163,7 @@ DEFINE_DEBUGFS_ATTRIBUTE(cma_alloc_fops, NULL, cma_alloc_write, "%llu\n"); static void cma_debugfs_add_one(struct cma *cma, struct dentry *root_dentry) { struct dentry *tmp; - char name[16]; + char name[CMA_MAX_NAME]; scnprintf(name, sizeof(name), "cma-%s", cma->name); diff --git a/mm/compaction.c b/mm/compaction.c index a2c53fcf933e..640fa76228dd 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -613,6 +613,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, break; set_page_private(page, order); + nr_scanned += isolated - 1; total_isolated += isolated; cc->nr_freepages += isolated; list_add_tail(&page->lru, freelist); @@ -1099,6 +1100,7 @@ isolate_success: isolate_success_no_list: cc->nr_migratepages += compound_nr(page); nr_isolated += compound_nr(page); + nr_scanned += compound_nr(page) - 1; /* * Avoid isolating too much unless this block is being @@ -1502,6 +1504,7 @@ fast_isolate_freepages(struct compact_control *cc) if (__isolate_free_page(page, order)) { set_page_private(page, order); nr_isolated = 1 << order; + nr_scanned += nr_isolated - 1; cc->nr_freepages += nr_isolated; list_add_tail(&page->lru, &cc->freepages); count_compact_events(COMPACTISOLATED, nr_isolated); @@ -3009,7 +3012,7 @@ void kcompactd_run(int nid) /* * Called by memory hotplug when all memory in a node is offlined. Caller must - * hold mem_hotplug_begin/end(). + * be holding mem_hotplug_begin/done(). */ void kcompactd_stop(int nid) { diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig index 9b559c76d6dd..66265e3a9c65 100644 --- a/mm/damon/Kconfig +++ b/mm/damon/Kconfig @@ -92,4 +92,12 @@ config DAMON_RECLAIM reclamation under light memory pressure, while the traditional page scanning-based reclamation is used for heavy pressure. +config DAMON_LRU_SORT + bool "Build DAMON-based LRU-lists sorting (DAMON_LRU_SORT)" + depends on DAMON_PADDR + help + This builds the DAMON-based LRU-lists sorting subsystem. It tries to + protect frequently accessed (hot) pages while rarely accessed (cold) + pages reclaimed first under memory pressure. + endmenu diff --git a/mm/damon/Makefile b/mm/damon/Makefile index dbf7190b4144..3e6b8ad73858 100644 --- a/mm/damon/Makefile +++ b/mm/damon/Makefile @@ -6,3 +6,4 @@ obj-$(CONFIG_DAMON_PADDR) += ops-common.o paddr.o obj-$(CONFIG_DAMON_SYSFS) += sysfs.o obj-$(CONFIG_DAMON_DBGFS) += dbgfs.o obj-$(CONFIG_DAMON_RECLAIM) += reclaim.o +obj-$(CONFIG_DAMON_LRU_SORT) += lru_sort.o diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index a0dab8b5e45f..cb8a7e9926a4 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -97,6 +97,31 @@ out: return ret; } +/* + * Return corresponding dbgfs' scheme action value (int) for the given + * damos_action if the given damos_action value is valid and supported by + * dbgfs, negative error code otherwise. + */ +static int damos_action_to_dbgfs_scheme_action(enum damos_action action) +{ + switch (action) { + case DAMOS_WILLNEED: + return 0; + case DAMOS_COLD: + return 1; + case DAMOS_PAGEOUT: + return 2; + case DAMOS_HUGEPAGE: + return 3; + case DAMOS_NOHUGEPAGE: + return 4; + case DAMOS_STAT: + return 5; + default: + return -EINVAL; + } +} + static ssize_t sprint_schemes(struct damon_ctx *c, char *buf, ssize_t len) { struct damos *s; @@ -109,7 +134,7 @@ static ssize_t sprint_schemes(struct damon_ctx *c, char *buf, ssize_t len) s->min_sz_region, s->max_sz_region, s->min_nr_accesses, s->max_nr_accesses, s->min_age_region, s->max_age_region, - s->action, + damos_action_to_dbgfs_scheme_action(s->action), s->quota.ms, s->quota.sz, s->quota.reset_interval, s->quota.weight_sz, @@ -160,18 +185,27 @@ static void free_schemes_arr(struct damos **schemes, ssize_t nr_schemes) kfree(schemes); } -static bool damos_action_valid(int action) +/* + * Return corresponding damos_action for the given dbgfs input for a scheme + * action if the input is valid, negative error code otherwise. + */ +static enum damos_action dbgfs_scheme_action_to_damos_action(int dbgfs_action) { - switch (action) { - case DAMOS_WILLNEED: - case DAMOS_COLD: - case DAMOS_PAGEOUT: - case DAMOS_HUGEPAGE: - case DAMOS_NOHUGEPAGE: - case DAMOS_STAT: - return true; + switch (dbgfs_action) { + case 0: + return DAMOS_WILLNEED; + case 1: + return DAMOS_COLD; + case 2: + return DAMOS_PAGEOUT; + case 3: + return DAMOS_HUGEPAGE; + case 4: + return DAMOS_NOHUGEPAGE; + case 5: + return DAMOS_STAT; default: - return false; + return -EINVAL; } } @@ -189,7 +223,8 @@ static struct damos **str_to_schemes(const char *str, ssize_t len, int pos = 0, parsed, ret; unsigned long min_sz, max_sz; unsigned int min_nr_a, max_nr_a, min_age, max_age; - unsigned int action; + unsigned int action_input; + enum damos_action action; schemes = kmalloc_array(max_nr_schemes, sizeof(scheme), GFP_KERNEL); @@ -204,7 +239,7 @@ static struct damos **str_to_schemes(const char *str, ssize_t len, ret = sscanf(&str[pos], "%lu %lu %u %u %u %u %u %lu %lu %lu %u %u %u %u %lu %lu %lu %lu%n", &min_sz, &max_sz, &min_nr_a, &max_nr_a, - &min_age, &max_age, &action, "a.ms, + &min_age, &max_age, &action_input, "a.ms, "a.sz, "a.reset_interval, "a.weight_sz, "a.weight_nr_accesses, "a.weight_age, &wmarks.metric, @@ -212,7 +247,8 @@ static struct damos **str_to_schemes(const char *str, ssize_t len, &wmarks.low, &parsed); if (ret != 18) break; - if (!damos_action_valid(action)) + action = dbgfs_scheme_action_to_damos_action(action_input); + if ((int)action < 0) goto fail; if (min_sz > max_sz || min_nr_a > max_nr_a || min_age > max_age) @@ -275,11 +311,6 @@ out: return ret; } -static inline bool target_has_pid(const struct damon_ctx *ctx) -{ - return ctx->ops.id == DAMON_OPS_VADDR; -} - static ssize_t sprint_target_ids(struct damon_ctx *ctx, char *buf, ssize_t len) { struct damon_target *t; @@ -288,7 +319,7 @@ static ssize_t sprint_target_ids(struct damon_ctx *ctx, char *buf, ssize_t len) int rc; damon_for_each_target(t, ctx) { - if (target_has_pid(ctx)) + if (damon_target_has_pid(ctx)) /* Show pid numbers to debugfs users */ id = pid_vnr(t->pid); else @@ -415,7 +446,7 @@ static int dbgfs_set_targets(struct damon_ctx *ctx, ssize_t nr_targets, struct damon_target *t, *next; damon_for_each_target_safe(t, next, ctx) { - if (target_has_pid(ctx)) + if (damon_target_has_pid(ctx)) put_pid(t->pid); damon_destroy_target(t); } @@ -425,11 +456,11 @@ static int dbgfs_set_targets(struct damon_ctx *ctx, ssize_t nr_targets, if (!t) { damon_for_each_target_safe(t, next, ctx) damon_destroy_target(t); - if (target_has_pid(ctx)) + if (damon_target_has_pid(ctx)) dbgfs_put_pids(pids, nr_targets); return -ENOMEM; } - if (target_has_pid(ctx)) + if (damon_target_has_pid(ctx)) t->pid = pids[i]; damon_add_target(ctx, t); } @@ -722,7 +753,7 @@ static void dbgfs_before_terminate(struct damon_ctx *ctx) { struct damon_target *t, *next; - if (!target_has_pid(ctx)) + if (!damon_target_has_pid(ctx)) return; mutex_lock(&ctx->kdamond_lock); diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c new file mode 100644 index 000000000000..9de6f00a71c5 --- /dev/null +++ b/mm/damon/lru_sort.c @@ -0,0 +1,548 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DAMON-based LRU-lists Sorting + * + * Author: SeongJae Park <sj@kernel.org> + */ + +#define pr_fmt(fmt) "damon-lru-sort: " fmt + +#include <linux/damon.h> +#include <linux/ioport.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/workqueue.h> + +#ifdef MODULE_PARAM_PREFIX +#undef MODULE_PARAM_PREFIX +#endif +#define MODULE_PARAM_PREFIX "damon_lru_sort." + +/* + * Enable or disable DAMON_LRU_SORT. + * + * You can enable DAMON_LRU_SORT by setting the value of this parameter as + * ``Y``. Setting it as ``N`` disables DAMON_LRU_SORT. Note that + * DAMON_LRU_SORT could do no real monitoring and LRU-lists sorting due to the + * watermarks-based activation condition. Refer to below descriptions for the + * watermarks parameter for this. + */ +static bool enabled __read_mostly; + +/* + * Make DAMON_LRU_SORT reads the input parameters again, except ``enabled``. + * + * Input parameters that updated while DAMON_LRU_SORT is running are not + * applied by default. Once this parameter is set as ``Y``, DAMON_LRU_SORT + * reads values of parametrs except ``enabled`` again. Once the re-reading is + * done, this parameter is set as ``N``. If invalid parameters are found while + * the re-reading, DAMON_LRU_SORT will be disabled. + */ +static bool commit_inputs __read_mostly; +module_param(commit_inputs, bool, 0600); + +/* + * Access frequency threshold for hot memory regions identification in permil. + * + * If a memory region is accessed in frequency of this or higher, + * DAMON_LRU_SORT identifies the region as hot, and mark it as accessed on the + * LRU list, so that it could not be reclaimed under memory pressure. 50% by + * default. + */ +static unsigned long hot_thres_access_freq = 500; +module_param(hot_thres_access_freq, ulong, 0600); + +/* + * Time threshold for cold memory regions identification in microseconds. + * + * If a memory region is not accessed for this or longer time, DAMON_LRU_SORT + * identifies the region as cold, and mark it as unaccessed on the LRU list, so + * that it could be reclaimed first under memory pressure. 120 seconds by + * default. + */ +static unsigned long cold_min_age __read_mostly = 120000000; +module_param(cold_min_age, ulong, 0600); + +/* + * Limit of time for trying the LRU lists sorting in milliseconds. + * + * DAMON_LRU_SORT tries to use only up to this time within a time window + * (quota_reset_interval_ms) for trying LRU lists sorting. This can be used + * for limiting CPU consumption of DAMON_LRU_SORT. If the value is zero, the + * limit is disabled. + * + * 10 ms by default. + */ +static unsigned long quota_ms __read_mostly = 10; +module_param(quota_ms, ulong, 0600); + +/* + * The time quota charge reset interval in milliseconds. + * + * The charge reset interval for the quota of time (quota_ms). That is, + * DAMON_LRU_SORT does not try LRU-lists sorting for more than quota_ms + * milliseconds or quota_sz bytes within quota_reset_interval_ms milliseconds. + * + * 1 second by default. + */ +static unsigned long quota_reset_interval_ms __read_mostly = 1000; +module_param(quota_reset_interval_ms, ulong, 0600); + +/* + * The watermarks check time interval in microseconds. + * + * Minimal time to wait before checking the watermarks, when DAMON_LRU_SORT is + * enabled but inactive due to its watermarks rule. 5 seconds by default. + */ +static unsigned long wmarks_interval __read_mostly = 5000000; +module_param(wmarks_interval, ulong, 0600); + +/* + * Free memory rate (per thousand) for the high watermark. + * + * If free memory of the system in bytes per thousand bytes is higher than + * this, DAMON_LRU_SORT becomes inactive, so it does nothing but periodically + * checks the watermarks. 200 (20%) by default. + */ +static unsigned long wmarks_high __read_mostly = 200; +module_param(wmarks_high, ulong, 0600); + +/* + * Free memory rate (per thousand) for the middle watermark. + * + * If free memory of the system in bytes per thousand bytes is between this and + * the low watermark, DAMON_LRU_SORT becomes active, so starts the monitoring + * and the LRU-lists sorting. 150 (15%) by default. + */ +static unsigned long wmarks_mid __read_mostly = 150; +module_param(wmarks_mid, ulong, 0600); + +/* + * Free memory rate (per thousand) for the low watermark. + * + * If free memory of the system in bytes per thousand bytes is lower than this, + * DAMON_LRU_SORT becomes inactive, so it does nothing but periodically checks + * the watermarks. 50 (5%) by default. + */ +static unsigned long wmarks_low __read_mostly = 50; +module_param(wmarks_low, ulong, 0600); + +/* + * Sampling interval for the monitoring in microseconds. + * + * The sampling interval of DAMON for the hot/cold memory monitoring. Please + * refer to the DAMON documentation for more detail. 5 ms by default. + */ +static unsigned long sample_interval __read_mostly = 5000; +module_param(sample_interval, ulong, 0600); + +/* + * Aggregation interval for the monitoring in microseconds. + * + * The aggregation interval of DAMON for the hot/cold memory monitoring. + * Please refer to the DAMON documentation for more detail. 100 ms by default. + */ +static unsigned long aggr_interval __read_mostly = 100000; +module_param(aggr_interval, ulong, 0600); + +/* + * Minimum number of monitoring regions. + * + * The minimal number of monitoring regions of DAMON for the hot/cold memory + * monitoring. This can be used to set lower-bound of the monitoring quality. + * But, setting this too high could result in increased monitoring overhead. + * Please refer to the DAMON documentation for more detail. 10 by default. + */ +static unsigned long min_nr_regions __read_mostly = 10; +module_param(min_nr_regions, ulong, 0600); + +/* + * Maximum number of monitoring regions. + * + * The maximum number of monitoring regions of DAMON for the hot/cold memory + * monitoring. This can be used to set upper-bound of the monitoring overhead. + * However, setting this too low could result in bad monitoring quality. + * Please refer to the DAMON documentation for more detail. 1000 by default. + */ +static unsigned long max_nr_regions __read_mostly = 1000; +module_param(max_nr_regions, ulong, 0600); + +/* + * Start of the target memory region in physical address. + * + * The start physical address of memory region that DAMON_LRU_SORT will do work + * against. By default, biggest System RAM is used as the region. + */ +static unsigned long monitor_region_start __read_mostly; +module_param(monitor_region_start, ulong, 0600); + +/* + * End of the target memory region in physical address. + * + * The end physical address of memory region that DAMON_LRU_SORT will do work + * against. By default, biggest System RAM is used as the region. + */ +static unsigned long monitor_region_end __read_mostly; +module_param(monitor_region_end, ulong, 0600); + +/* + * PID of the DAMON thread + * + * If DAMON_LRU_SORT is enabled, this becomes the PID of the worker thread. + * Else, -1. + */ +static int kdamond_pid __read_mostly = -1; +module_param(kdamond_pid, int, 0400); + +/* + * Number of hot memory regions that tried to be LRU-sorted. + */ +static unsigned long nr_lru_sort_tried_hot_regions __read_mostly; +module_param(nr_lru_sort_tried_hot_regions, ulong, 0400); + +/* + * Total bytes of hot memory regions that tried to be LRU-sorted. + */ +static unsigned long bytes_lru_sort_tried_hot_regions __read_mostly; +module_param(bytes_lru_sort_tried_hot_regions, ulong, 0400); + +/* + * Number of hot memory regions that successfully be LRU-sorted. + */ +static unsigned long nr_lru_sorted_hot_regions __read_mostly; +module_param(nr_lru_sorted_hot_regions, ulong, 0400); + +/* + * Total bytes of hot memory regions that successfully be LRU-sorted. + */ +static unsigned long bytes_lru_sorted_hot_regions __read_mostly; +module_param(bytes_lru_sorted_hot_regions, ulong, 0400); + +/* + * Number of times that the time quota limit for hot regions have exceeded + */ +static unsigned long nr_hot_quota_exceeds __read_mostly; +module_param(nr_hot_quota_exceeds, ulong, 0400); + +/* + * Number of cold memory regions that tried to be LRU-sorted. + */ +static unsigned long nr_lru_sort_tried_cold_regions __read_mostly; +module_param(nr_lru_sort_tried_cold_regions, ulong, 0400); + +/* + * Total bytes of cold memory regions that tried to be LRU-sorted. + */ +static unsigned long bytes_lru_sort_tried_cold_regions __read_mostly; +module_param(bytes_lru_sort_tried_cold_regions, ulong, 0400); + +/* + * Number of cold memory regions that successfully be LRU-sorted. + */ +static unsigned long nr_lru_sorted_cold_regions __read_mostly; +module_param(nr_lru_sorted_cold_regions, ulong, 0400); + +/* + * Total bytes of cold memory regions that successfully be LRU-sorted. + */ +static unsigned long bytes_lru_sorted_cold_regions __read_mostly; +module_param(bytes_lru_sorted_cold_regions, ulong, 0400); + +/* + * Number of times that the time quota limit for cold regions have exceeded + */ +static unsigned long nr_cold_quota_exceeds __read_mostly; +module_param(nr_cold_quota_exceeds, ulong, 0400); + +static struct damon_ctx *ctx; +static struct damon_target *target; + +struct damon_lru_sort_ram_walk_arg { + unsigned long start; + unsigned long end; +}; + +static int walk_system_ram(struct resource *res, void *arg) +{ + struct damon_lru_sort_ram_walk_arg *a = arg; + + if (a->end - a->start < resource_size(res)) { + a->start = res->start; + a->end = res->end; + } + return 0; +} + +/* + * Find biggest 'System RAM' resource and store its start and end address in + * @start and @end, respectively. If no System RAM is found, returns false. + */ +static bool get_monitoring_region(unsigned long *start, unsigned long *end) +{ + struct damon_lru_sort_ram_walk_arg arg = {}; + + walk_system_ram_res(0, ULONG_MAX, &arg, walk_system_ram); + if (arg.end <= arg.start) + return false; + + *start = arg.start; + *end = arg.end; + return true; +} + +/* Create a DAMON-based operation scheme for hot memory regions */ +static struct damos *damon_lru_sort_new_hot_scheme(unsigned int hot_thres) +{ + struct damos_watermarks wmarks = { + .metric = DAMOS_WMARK_FREE_MEM_RATE, + .interval = wmarks_interval, + .high = wmarks_high, + .mid = wmarks_mid, + .low = wmarks_low, + }; + struct damos_quota quota = { + /* + * Do not try LRU-lists sorting of hot pages for more than half + * of quota_ms milliseconds within quota_reset_interval_ms. + */ + .ms = quota_ms / 2, + .sz = 0, + .reset_interval = quota_reset_interval_ms, + /* Within the quota, mark hotter regions accessed first. */ + .weight_sz = 0, + .weight_nr_accesses = 1, + .weight_age = 0, + }; + struct damos *scheme = damon_new_scheme( + /* Find regions having PAGE_SIZE or larger size */ + PAGE_SIZE, ULONG_MAX, + /* and accessed for more than the threshold */ + hot_thres, UINT_MAX, + /* no matter its age */ + 0, UINT_MAX, + /* prioritize those on LRU lists, as soon as found */ + DAMOS_LRU_PRIO, + /* under the quota. */ + "a, + /* (De)activate this according to the watermarks. */ + &wmarks); + + return scheme; +} + +/* Create a DAMON-based operation scheme for cold memory regions */ +static struct damos *damon_lru_sort_new_cold_scheme(unsigned int cold_thres) +{ + struct damos_watermarks wmarks = { + .metric = DAMOS_WMARK_FREE_MEM_RATE, + .interval = wmarks_interval, + .high = wmarks_high, + .mid = wmarks_mid, + .low = wmarks_low, + }; + struct damos_quota quota = { + /* + * Do not try LRU-lists sorting of cold pages for more than + * half of quota_ms milliseconds within + * quota_reset_interval_ms. + */ + .ms = quota_ms / 2, + .sz = 0, + .reset_interval = quota_reset_interval_ms, + /* Within the quota, mark colder regions not accessed first. */ + .weight_sz = 0, + .weight_nr_accesses = 0, + .weight_age = 1, + }; + struct damos *scheme = damon_new_scheme( + /* Find regions having PAGE_SIZE or larger size */ + PAGE_SIZE, ULONG_MAX, + /* and not accessed at all */ + 0, 0, + /* for cold_thres or more micro-seconds, and */ + cold_thres, UINT_MAX, + /* mark those as not accessed, as soon as found */ + DAMOS_LRU_DEPRIO, + /* under the quota. */ + "a, + /* (De)activate this according to the watermarks. */ + &wmarks); + + return scheme; +} + +static int damon_lru_sort_apply_parameters(void) +{ + struct damos *scheme, *next_scheme; + struct damon_addr_range addr_range; + unsigned int hot_thres, cold_thres; + int err = 0; + + err = damon_set_attrs(ctx, sample_interval, aggr_interval, 0, + min_nr_regions, max_nr_regions); + if (err) + return err; + + /* free previously set schemes */ + damon_for_each_scheme_safe(scheme, next_scheme, ctx) + damon_destroy_scheme(scheme); + + /* aggr_interval / sample_interval is the maximum nr_accesses */ + hot_thres = aggr_interval / sample_interval * hot_thres_access_freq / + 1000; + scheme = damon_lru_sort_new_hot_scheme(hot_thres); + if (!scheme) + return -ENOMEM; + damon_add_scheme(ctx, scheme); + + cold_thres = cold_min_age / aggr_interval; + scheme = damon_lru_sort_new_cold_scheme(cold_thres); + if (!scheme) + return -ENOMEM; + damon_add_scheme(ctx, scheme); + + if (monitor_region_start > monitor_region_end) + return -EINVAL; + if (!monitor_region_start && !monitor_region_end && + !get_monitoring_region(&monitor_region_start, + &monitor_region_end)) + return -EINVAL; + addr_range.start = monitor_region_start; + addr_range.end = monitor_region_end; + return damon_set_regions(target, &addr_range, 1); +} + +static int damon_lru_sort_turn(bool on) +{ + int err; + + if (!on) { + err = damon_stop(&ctx, 1); + if (!err) + kdamond_pid = -1; + return err; + } + + err = damon_lru_sort_apply_parameters(); + if (err) + return err; + + err = damon_start(&ctx, 1, true); + if (err) + return err; + kdamond_pid = ctx->kdamond->pid; + return 0; +} + +static struct delayed_work damon_lru_sort_timer; +static void damon_lru_sort_timer_fn(struct work_struct *work) +{ + static bool last_enabled; + bool now_enabled; + + now_enabled = enabled; + if (last_enabled != now_enabled) { + if (!damon_lru_sort_turn(now_enabled)) + last_enabled = now_enabled; + else + enabled = last_enabled; + } +} +static DECLARE_DELAYED_WORK(damon_lru_sort_timer, damon_lru_sort_timer_fn); + +static bool damon_lru_sort_initialized; + +static int damon_lru_sort_enabled_store(const char *val, + const struct kernel_param *kp) +{ + int rc = param_set_bool(val, kp); + + if (rc < 0) + return rc; + + if (!damon_lru_sort_initialized) + return rc; + + schedule_delayed_work(&damon_lru_sort_timer, 0); + + return 0; +} + +static const struct kernel_param_ops enabled_param_ops = { + .set = damon_lru_sort_enabled_store, + .get = param_get_bool, +}; + +module_param_cb(enabled, &enabled_param_ops, &enabled, 0600); +MODULE_PARM_DESC(enabled, + "Enable or disable DAMON_LRU_SORT (default: disabled)"); + +static int damon_lru_sort_handle_commit_inputs(void) +{ + int err; + + if (!commit_inputs) + return 0; + + err = damon_lru_sort_apply_parameters(); + commit_inputs = false; + return err; +} + +static int damon_lru_sort_after_aggregation(struct damon_ctx *c) +{ + struct damos *s; + + /* update the stats parameter */ + damon_for_each_scheme(s, c) { + if (s->action == DAMOS_LRU_PRIO) { + nr_lru_sort_tried_hot_regions = s->stat.nr_tried; + bytes_lru_sort_tried_hot_regions = s->stat.sz_tried; + nr_lru_sorted_hot_regions = s->stat.nr_applied; + bytes_lru_sorted_hot_regions = s->stat.sz_applied; + nr_hot_quota_exceeds = s->stat.qt_exceeds; + } else if (s->action == DAMOS_LRU_DEPRIO) { + nr_lru_sort_tried_cold_regions = s->stat.nr_tried; + bytes_lru_sort_tried_cold_regions = s->stat.sz_tried; + nr_lru_sorted_cold_regions = s->stat.nr_applied; + bytes_lru_sorted_cold_regions = s->stat.sz_applied; + nr_cold_quota_exceeds = s->stat.qt_exceeds; + } + } + + return damon_lru_sort_handle_commit_inputs(); +} + +static int damon_lru_sort_after_wmarks_check(struct damon_ctx *c) +{ + return damon_lru_sort_handle_commit_inputs(); +} + +static int __init damon_lru_sort_init(void) +{ + ctx = damon_new_ctx(); + if (!ctx) + return -ENOMEM; + + if (damon_select_ops(ctx, DAMON_OPS_PADDR)) { + damon_destroy_ctx(ctx); + return -EINVAL; + } + + ctx->callback.after_wmarks_check = damon_lru_sort_after_wmarks_check; + ctx->callback.after_aggregation = damon_lru_sort_after_aggregation; + + target = damon_new_target(); + if (!target) { + damon_destroy_ctx(ctx); + return -ENOMEM; + } + damon_add_target(ctx, target); + + schedule_delayed_work(&damon_lru_sort_timer, 0); + + damon_lru_sort_initialized = true; + return 0; +} + +module_init(damon_lru_sort_init); diff --git a/mm/damon/ops-common.c b/mm/damon/ops-common.c index 10ef20b2003f..b1335de200e7 100644 --- a/mm/damon/ops-common.c +++ b/mm/damon/ops-common.c @@ -130,3 +130,45 @@ int damon_pageout_score(struct damon_ctx *c, struct damon_region *r, /* Return coldness of the region */ return DAMOS_MAX_SCORE - hotness; } + +int damon_hot_score(struct damon_ctx *c, struct damon_region *r, + struct damos *s) +{ + unsigned int max_nr_accesses; + int freq_subscore; + unsigned int age_in_sec; + int age_in_log, age_subscore; + unsigned int freq_weight = s->quota.weight_nr_accesses; + unsigned int age_weight = s->quota.weight_age; + int hotness; + + max_nr_accesses = c->aggr_interval / c->sample_interval; + freq_subscore = r->nr_accesses * DAMON_MAX_SUBSCORE / max_nr_accesses; + + age_in_sec = (unsigned long)r->age * c->aggr_interval / 1000000; + for (age_in_log = 0; age_in_log < DAMON_MAX_AGE_IN_LOG && age_in_sec; + age_in_log++, age_in_sec >>= 1) + ; + + /* If frequency is 0, higher age means it's colder */ + if (freq_subscore == 0) + age_in_log *= -1; + + /* + * Now age_in_log is in [-DAMON_MAX_AGE_IN_LOG, DAMON_MAX_AGE_IN_LOG]. + * Scale it to be in [0, 100] and set it as age subscore. + */ + age_in_log += DAMON_MAX_AGE_IN_LOG; + age_subscore = age_in_log * DAMON_MAX_SUBSCORE / + DAMON_MAX_AGE_IN_LOG / 2; + + hotness = (freq_weight * freq_subscore + age_weight * age_subscore); + if (freq_weight + age_weight) + hotness /= freq_weight + age_weight; + /* + * Transform it to fit in [0, DAMOS_MAX_SCORE] + */ + hotness = hotness * DAMOS_MAX_SCORE / DAMON_MAX_SUBSCORE; + + return hotness; +} diff --git a/mm/damon/ops-common.h b/mm/damon/ops-common.h index e790cb5f8fe0..52329ff361cd 100644 --- a/mm/damon/ops-common.h +++ b/mm/damon/ops-common.h @@ -14,3 +14,5 @@ void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr); int damon_pageout_score(struct damon_ctx *c, struct damon_region *r, struct damos *s); +int damon_hot_score(struct damon_ctx *c, struct damon_region *r, + struct damos *s); diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index b40ff5811bb2..dc131c6a5403 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -204,16 +204,11 @@ static unsigned int damon_pa_check_accesses(struct damon_ctx *ctx) return max_nr_accesses; } -static unsigned long damon_pa_apply_scheme(struct damon_ctx *ctx, - struct damon_target *t, struct damon_region *r, - struct damos *scheme) +static unsigned long damon_pa_pageout(struct damon_region *r) { unsigned long addr, applied; LIST_HEAD(page_list); - if (scheme->action != DAMOS_PAGEOUT) - return 0; - for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) { struct page *page = damon_get_page(PHYS_PFN(addr)); @@ -238,6 +233,55 @@ static unsigned long damon_pa_apply_scheme(struct damon_ctx *ctx, return applied * PAGE_SIZE; } +static unsigned long damon_pa_mark_accessed(struct damon_region *r) +{ + unsigned long addr, applied = 0; + + for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) { + struct page *page = damon_get_page(PHYS_PFN(addr)); + + if (!page) + continue; + mark_page_accessed(page); + put_page(page); + applied++; + } + return applied * PAGE_SIZE; +} + +static unsigned long damon_pa_deactivate_pages(struct damon_region *r) +{ + unsigned long addr, applied = 0; + + for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) { + struct page *page = damon_get_page(PHYS_PFN(addr)); + + if (!page) + continue; + deactivate_page(page); + put_page(page); + applied++; + } + return applied * PAGE_SIZE; +} + +static unsigned long damon_pa_apply_scheme(struct damon_ctx *ctx, + struct damon_target *t, struct damon_region *r, + struct damos *scheme) +{ + switch (scheme->action) { + case DAMOS_PAGEOUT: + return damon_pa_pageout(r); + case DAMOS_LRU_PRIO: + return damon_pa_mark_accessed(r); + case DAMOS_LRU_DEPRIO: + return damon_pa_deactivate_pages(r); + default: + break; + } + return 0; +} + static int damon_pa_scheme_score(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, struct damos *scheme) @@ -245,6 +289,10 @@ static int damon_pa_scheme_score(struct damon_ctx *context, switch (scheme->action) { case DAMOS_PAGEOUT: return damon_pageout_score(context, r, scheme); + case DAMOS_LRU_PRIO: + return damon_hot_score(context, r, scheme); + case DAMOS_LRU_DEPRIO: + return damon_pageout_score(context, r, scheme); default: break; } diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c index 4b07c29effe9..a7faf51b4bd4 100644 --- a/mm/damon/reclaim.c +++ b/mm/damon/reclaim.c @@ -353,7 +353,6 @@ static int damon_reclaim_turn(bool on) return 0; } -#define ENABLE_CHECK_INTERVAL_MS 1000 static struct delayed_work damon_reclaim_timer; static void damon_reclaim_timer_fn(struct work_struct *work) { @@ -367,16 +366,12 @@ static void damon_reclaim_timer_fn(struct work_struct *work) else enabled = last_enabled; } - - if (enabled) - schedule_delayed_work(&damon_reclaim_timer, - msecs_to_jiffies(ENABLE_CHECK_INTERVAL_MS)); } static DECLARE_DELAYED_WORK(damon_reclaim_timer, damon_reclaim_timer_fn); static bool damon_reclaim_initialized; -static int enabled_store(const char *val, +static int damon_reclaim_enabled_store(const char *val, const struct kernel_param *kp) { int rc = param_set_bool(val, kp); @@ -388,14 +383,12 @@ static int enabled_store(const char *val, if (!damon_reclaim_initialized) return rc; - if (enabled) - schedule_delayed_work(&damon_reclaim_timer, 0); - + schedule_delayed_work(&damon_reclaim_timer, 0); return 0; } static const struct kernel_param_ops enabled_param_ops = { - .set = enabled_store, + .set = damon_reclaim_enabled_store, .get = param_get_bool, }; @@ -403,10 +396,21 @@ module_param_cb(enabled, &enabled_param_ops, &enabled, 0600); MODULE_PARM_DESC(enabled, "Enable or disable DAMON_RECLAIM (default: disabled)"); +static int damon_reclaim_handle_commit_inputs(void) +{ + int err; + + if (!commit_inputs) + return 0; + + err = damon_reclaim_apply_parameters(); + commit_inputs = false; + return err; +} + static int damon_reclaim_after_aggregation(struct damon_ctx *c) { struct damos *s; - int err = 0; /* update the stats parameter */ damon_for_each_scheme(s, c) { @@ -417,22 +421,12 @@ static int damon_reclaim_after_aggregation(struct damon_ctx *c) nr_quota_exceeds = s->stat.qt_exceeds; } - if (commit_inputs) { - err = damon_reclaim_apply_parameters(); - commit_inputs = false; - } - return err; + return damon_reclaim_handle_commit_inputs(); } static int damon_reclaim_after_wmarks_check(struct damon_ctx *c) { - int err = 0; - - if (commit_inputs) { - err = damon_reclaim_apply_parameters(); - commit_inputs = false; - } - return err; + return damon_reclaim_handle_commit_inputs(); } static int __init damon_reclaim_init(void) @@ -441,8 +435,10 @@ static int __init damon_reclaim_init(void) if (!ctx) return -ENOMEM; - if (damon_select_ops(ctx, DAMON_OPS_PADDR)) + if (damon_select_ops(ctx, DAMON_OPS_PADDR)) { + damon_destroy_ctx(ctx); return -EINVAL; + } ctx->callback.after_wmarks_check = damon_reclaim_after_wmarks_check; ctx->callback.after_aggregation = damon_reclaim_after_aggregation; diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index 09f9e8ca3d1f..7488e27c87c3 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -762,6 +762,8 @@ static const char * const damon_sysfs_damos_action_strs[] = { "pageout", "hugepage", "nohugepage", + "lru_prio", + "lru_deprio", "stat", }; @@ -2136,8 +2138,7 @@ static void damon_sysfs_destroy_targets(struct damon_ctx *ctx) struct damon_target *t, *next; damon_for_each_target_safe(t, next, ctx) { - if (ctx->ops.id == DAMON_OPS_VADDR || - ctx->ops.id == DAMON_OPS_FVADDR) + if (damon_target_has_pid(ctx)) put_pid(t->pid); damon_destroy_target(t); } @@ -2181,8 +2182,7 @@ static int damon_sysfs_add_target(struct damon_sysfs_target *sys_target, if (!t) return -ENOMEM; - if (ctx->ops.id == DAMON_OPS_VADDR || - ctx->ops.id == DAMON_OPS_FVADDR) { + if (damon_target_has_pid(ctx)) { t->pid = find_get_pid(sys_target->pid); if (!t->pid) goto destroy_targets_out; @@ -2210,7 +2210,7 @@ static struct damon_target *damon_sysfs_existing_target( struct pid *pid; struct damon_target *t; - if (ctx->ops.id == DAMON_OPS_PADDR) { + if (!damon_target_has_pid(ctx)) { /* Up to only one target for paddr could exist */ damon_for_each_target(t, ctx) return t; @@ -2359,6 +2359,23 @@ static inline bool damon_sysfs_kdamond_running( damon_sysfs_ctx_running(kdamond->damon_ctx); } +static int damon_sysfs_apply_inputs(struct damon_ctx *ctx, + struct damon_sysfs_context *sys_ctx) +{ + int err; + + err = damon_select_ops(ctx, sys_ctx->ops_id); + if (err) + return err; + err = damon_sysfs_set_attrs(ctx, sys_ctx->attrs); + if (err) + return err; + err = damon_sysfs_set_targets(ctx, sys_ctx->targets); + if (err) + return err; + return damon_sysfs_set_schemes(ctx, sys_ctx->schemes); +} + /* * damon_sysfs_commit_input() - Commit user inputs to a running kdamond. * @kdamond: The kobject wrapper for the associated kdamond. @@ -2367,31 +2384,14 @@ static inline bool damon_sysfs_kdamond_running( */ static int damon_sysfs_commit_input(struct damon_sysfs_kdamond *kdamond) { - struct damon_ctx *ctx = kdamond->damon_ctx; - struct damon_sysfs_context *sys_ctx; - int err = 0; - if (!damon_sysfs_kdamond_running(kdamond)) return -EINVAL; /* TODO: Support multiple contexts per kdamond */ if (kdamond->contexts->nr != 1) return -EINVAL; - sys_ctx = kdamond->contexts->contexts_arr[0]; - - err = damon_select_ops(ctx, sys_ctx->ops_id); - if (err) - return err; - err = damon_sysfs_set_attrs(ctx, sys_ctx->attrs); - if (err) - return err; - err = damon_sysfs_set_targets(ctx, sys_ctx->targets); - if (err) - return err; - err = damon_sysfs_set_schemes(ctx, sys_ctx->schemes); - if (err) - return err; - return err; + return damon_sysfs_apply_inputs(kdamond->damon_ctx, + kdamond->contexts->contexts_arr[0]); } /* @@ -2438,27 +2438,16 @@ static struct damon_ctx *damon_sysfs_build_ctx( if (!ctx) return ERR_PTR(-ENOMEM); - err = damon_select_ops(ctx, sys_ctx->ops_id); - if (err) - goto out; - err = damon_sysfs_set_attrs(ctx, sys_ctx->attrs); - if (err) - goto out; - err = damon_sysfs_set_targets(ctx, sys_ctx->targets); - if (err) - goto out; - err = damon_sysfs_set_schemes(ctx, sys_ctx->schemes); - if (err) - goto out; + err = damon_sysfs_apply_inputs(ctx, sys_ctx); + if (err) { + damon_destroy_ctx(ctx); + return ERR_PTR(err); + } ctx->callback.after_wmarks_check = damon_sysfs_cmd_request_callback; ctx->callback.after_aggregation = damon_sysfs_cmd_request_callback; ctx->callback.before_terminate = damon_sysfs_before_terminate; return ctx; - -out: - damon_destroy_ctx(ctx); - return ERR_PTR(err); } static int damon_sysfs_turn_damon_on(struct damon_sysfs_kdamond *kdamond) diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index 1ab091f49fc0..dc7df1254f0a 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -35,7 +35,7 @@ #include <asm/tlbflush.h> /* - * Please refer Documentation/vm/arch_pgtable_helpers.rst for the semantics + * Please refer Documentation/mm/arch_pgtable_helpers.rst for the semantics * expectations that are being validated here. All future changes in here * or the documentation need to be in sync. */ diff --git a/mm/filemap.c b/mm/filemap.c index 0dec96ea6688..15800334147b 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -667,7 +667,7 @@ EXPORT_SYMBOL_GPL(filemap_range_has_writeback); int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend) { - int err = 0; + int err = 0, err2; if (mapping_needs_writeback(mapping)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, @@ -678,18 +678,12 @@ int filemap_write_and_wait_range(struct address_space *mapping, * But the -EIO is special case, it may indicate the worst * thing (e.g. bug) happened, so we avoid waiting for it. */ - if (err != -EIO) { - int err2 = filemap_fdatawait_range(mapping, - lstart, lend); - if (!err) - err = err2; - } else { - /* Clear any previously stored errors */ - filemap_check_errors(mapping); - } - } else { - err = filemap_check_errors(mapping); + if (err != -EIO) + __filemap_fdatawait_range(mapping, lstart, lend); } + err2 = filemap_check_errors(mapping); + if (!err) + err = err2; return err; } EXPORT_SYMBOL(filemap_write_and_wait_range); diff --git a/mm/frontswap.c b/mm/frontswap.c index 6f69b044a8cc..1a97610308cb 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -4,7 +4,7 @@ * * This code provides the generic "frontend" layer to call a matching * "backend" driver implementation of frontswap. See - * Documentation/vm/frontswap.rst for more information. + * Documentation/mm/frontswap.rst for more information. * * Copyright (C) 2009-2012 Oracle Corp. All rights reserved. * Author: Dan Magenheimer @@ -134,7 +134,7 @@ struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags) * path. */ if (unlikely((flags & FOLL_LONGTERM) && - !is_pinnable_page(page))) + !is_longterm_pinnable_page(page))) return NULL; /* @@ -953,6 +953,25 @@ static int faultin_page(struct vm_area_struct *vma, } ret = handle_mm_fault(vma, address, fault_flags, NULL); + + if (ret & VM_FAULT_COMPLETED) { + /* + * With FAULT_FLAG_RETRY_NOWAIT we'll never release the + * mmap lock in the page fault handler. Sanity check this. + */ + WARN_ON_ONCE(fault_flags & FAULT_FLAG_RETRY_NOWAIT); + if (locked) + *locked = 0; + /* + * We should do the same as VM_FAULT_RETRY, but let's not + * return -EBUSY since that's not reflecting the reality of + * what has happened - we've just fully completed a page + * fault, with the mmap lock released. Use -EAGAIN to show + * that we want to take the mmap lock _again_. + */ + return -EAGAIN; + } + if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, *flags); @@ -1179,6 +1198,7 @@ retry: case 0: goto retry; case -EBUSY: + case -EAGAIN: ret = 0; fallthrough; case -EFAULT: @@ -1305,6 +1325,18 @@ retry: return -EINTR; ret = handle_mm_fault(vma, address, fault_flags, NULL); + + if (ret & VM_FAULT_COMPLETED) { + /* + * NOTE: it's a pity that we need to retake the lock here + * to pair with the unlock() in the callers. Ideally we + * could tell the callers so they do not need to unlock. + */ + mmap_read_lock(mm); + *unlocked = true; + return 0; + } + if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, 0); @@ -1370,7 +1402,7 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, /* VM_FAULT_RETRY couldn't trigger, bypass */ return ret; - /* VM_FAULT_RETRY cannot return errors */ + /* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */ if (!*locked) { BUG_ON(ret < 0); BUG_ON(ret >= nr_pages); @@ -1674,7 +1706,7 @@ static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start, goto finish_or_fault; if (pages) { - pages[i] = virt_to_page(start); + pages[i] = virt_to_page((void *)start); if (pages[i]) get_page(pages[i]); } @@ -1883,7 +1915,7 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages, unsigned long isolation_error_count = 0, i; struct folio *prev_folio = NULL; LIST_HEAD(movable_page_list); - bool drain_allow = true; + bool drain_allow = true, coherent_pages = false; int ret = 0; for (i = 0; i < nr_pages; i++) { @@ -1893,14 +1925,43 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages, continue; prev_folio = folio; - if (folio_is_pinnable(folio)) + /* + * Device coherent pages are managed by a driver and should not + * be pinned indefinitely as it prevents the driver moving the + * page. So when trying to pin with FOLL_LONGTERM instead try + * to migrate the page out of device memory. + */ + if (folio_is_device_coherent(folio)) { + /* + * We always want a new GUP lookup with device coherent + * pages. + */ + pages[i] = 0; + coherent_pages = true; + + /* + * Migration will fail if the page is pinned, so convert + * the pin on the source page to a normal reference. + */ + if (gup_flags & FOLL_PIN) { + get_page(&folio->page); + unpin_user_page(&folio->page); + } + + ret = migrate_device_coherent_page(&folio->page); + if (ret) + goto unpin_pages; + continue; + } + if (folio_is_longterm_pinnable(folio)) + continue; /* * Try to move out any movable page before pinning the range. */ if (folio_test_hugetlb(folio)) { - if (!isolate_huge_page(&folio->page, + if (isolate_hugetlb(&folio->page, &movable_page_list)) isolation_error_count++; continue; @@ -1921,7 +1982,8 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages, folio_nr_pages(folio)); } - if (!list_empty(&movable_page_list) || isolation_error_count) + if (!list_empty(&movable_page_list) || isolation_error_count || + coherent_pages) goto unpin_pages; /* @@ -1931,10 +1993,16 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages, return nr_pages; unpin_pages: - if (gup_flags & FOLL_PIN) { - unpin_user_pages(pages, nr_pages); - } else { - for (i = 0; i < nr_pages; i++) + /* + * pages[i] might be NULL if any device coherent pages were found. + */ + for (i = 0; i < nr_pages; i++) { + if (!pages[i]) + continue; + + if (gup_flags & FOLL_PIN) + unpin_user_page(pages[i]); + else put_page(pages[i]); } diff --git a/mm/gup_test.c b/mm/gup_test.c index d974dec19e1c..12b0a91767d3 100644 --- a/mm/gup_test.c +++ b/mm/gup_test.c @@ -53,7 +53,7 @@ static void verify_dma_pinned(unsigned int cmd, struct page **pages, dump_page(page, "gup_test failure"); break; } else if (cmd == PIN_LONGTERM_BENCHMARK && - WARN(!is_pinnable_page(page), + WARN(!is_longterm_pinnable_page(page), "pages[%lu] is NOT pinnable but pinned\n", i)) { dump_page(page, "gup_test failure"); diff --git a/mm/highmem.c b/mm/highmem.c index e32083e4ce0d..c707d7202d5f 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -150,7 +150,7 @@ struct page *__kmap_to_page(void *vaddr) return pte_page(pkmap_page_table[i]); } - return virt_to_page(addr); + return virt_to_page(vaddr); } EXPORT_SYMBOL(__kmap_to_page); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 15965084816d..8a7c1b344abe 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -70,21 +70,85 @@ static atomic_t huge_zero_refcount; struct page *huge_zero_page __read_mostly; unsigned long huge_zero_pfn __read_mostly = ~0UL; -bool transparent_hugepage_active(struct vm_area_struct *vma) +bool hugepage_vma_check(struct vm_area_struct *vma, + unsigned long vm_flags, + bool smaps, bool in_pf) { - /* The addr is used to check if the vma size fits */ - unsigned long addr = (vma->vm_end & HPAGE_PMD_MASK) - HPAGE_PMD_SIZE; + if (!vma->vm_mm) /* vdso */ + return false; + + /* + * Explicitly disabled through madvise or prctl, or some + * architectures may disable THP for some mappings, for + * example, s390 kvm. + * */ + if ((vm_flags & VM_NOHUGEPAGE) || + test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + return false; + /* + * If the hardware/firmware marked hugepage support disabled. + */ + if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_NEVER_DAX)) + return false; - if (!transhuge_vma_suitable(vma, addr)) + /* khugepaged doesn't collapse DAX vma, but page fault is fine. */ + if (vma_is_dax(vma)) + return in_pf; + + /* + * Special VMA and hugetlb VMA. + * Must be checked after dax since some dax mappings may have + * VM_MIXEDMAP set. + */ + if (vm_flags & VM_NO_KHUGEPAGED) return false; - if (vma_is_anonymous(vma)) - return __transparent_hugepage_enabled(vma); - if (vma_is_shmem(vma)) + + /* + * Check alignment for file vma and size for both file and anon vma. + * + * Skip the check for page fault. Huge fault does the check in fault + * handlers. And this check is not suitable for huge PUD fault. + */ + if (!in_pf && + !transhuge_vma_suitable(vma, (vma->vm_end - HPAGE_PMD_SIZE))) + return false; + + /* + * Enabled via shmem mount options or sysfs settings. + * Must be done before hugepage flags check since shmem has its + * own flags. + */ + if (!in_pf && shmem_file(vma->vm_file)) return shmem_huge_enabled(vma); - if (transhuge_vma_enabled(vma, vma->vm_flags) && file_thp_enabled(vma)) + + if (!hugepage_flags_enabled()) + return false; + + /* THP settings require madvise. */ + if (!(vm_flags & VM_HUGEPAGE) && !hugepage_flags_always()) + return false; + + /* Only regular file is valid */ + if (!in_pf && file_thp_enabled(vma)) return true; - return false; + if (!vma_is_anonymous(vma)) + return false; + + if (vma_is_temporary_stack(vma)) + return false; + + /* + * THPeligible bit of smaps should show 1 for proper VMAs even + * though anon_vma is not initialized yet. + * + * Allow page fault since anon_vma may be not initialized until + * the first page fault. + */ + if (!vma->anon_vma) + return (smaps || in_pf); + + return true; } static bool get_huge_zero_page(void) @@ -213,8 +277,8 @@ static ssize_t enabled_store(struct kobject *kobj, } return ret; } -static struct kobj_attribute enabled_attr = - __ATTR(enabled, 0644, enabled_show, enabled_store); + +static struct kobj_attribute enabled_attr = __ATTR_RW(enabled); ssize_t single_hugepage_flag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf, @@ -303,8 +367,7 @@ static ssize_t defrag_store(struct kobject *kobj, return count; } -static struct kobj_attribute defrag_attr = - __ATTR(defrag, 0644, defrag_show, defrag_store); +static struct kobj_attribute defrag_attr = __ATTR_RW(defrag); static ssize_t use_zero_page_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) @@ -318,8 +381,7 @@ static ssize_t use_zero_page_store(struct kobject *kobj, return single_hugepage_flag_store(kobj, attr, buf, count, TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); } -static struct kobj_attribute use_zero_page_attr = - __ATTR(use_zero_page, 0644, use_zero_page_show, use_zero_page_store); +static struct kobj_attribute use_zero_page_attr = __ATTR_RW(use_zero_page); static ssize_t hpage_pmd_size_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) @@ -424,10 +486,10 @@ static int __init hugepage_init(void) if (err) goto err_slab; - err = register_shrinker(&huge_zero_page_shrinker); + err = register_shrinker(&huge_zero_page_shrinker, "thp-zero"); if (err) goto err_hzp_shrinker; - err = register_shrinker(&deferred_split_shrinker); + err = register_shrinker(&deferred_split_shrinker, "thp-deferred_split"); if (err) goto err_split_shrinker; @@ -520,7 +582,7 @@ static inline struct deferred_split *get_deferred_split_queue(struct page *page) void prep_transhuge_page(struct page *page) { /* - * we use page->mapping and page->indexlru in second tail page + * we use page->mapping and page->index in second tail page * as list_head: assuming THP order >= 2 */ @@ -727,7 +789,7 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) return VM_FAULT_FALLBACK; if (unlikely(anon_vma_prepare(vma))) return VM_FAULT_OOM; - khugepaged_enter(vma, vma->vm_flags); + khugepaged_enter_vma(vma, vma->vm_flags); if (!(vmf->flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(vma->vm_mm) && @@ -957,15 +1019,15 @@ EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud_prot); #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ static void touch_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, int flags) + pmd_t *pmd, bool write) { pmd_t _pmd; _pmd = pmd_mkyoung(*pmd); - if (flags & FOLL_WRITE) + if (write) _pmd = pmd_mkdirty(_pmd); if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK, - pmd, _pmd, flags & FOLL_WRITE)) + pmd, _pmd, write)) update_mmu_cache_pmd(vma, addr, pmd); } @@ -998,7 +1060,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, return NULL; if (flags & FOLL_TOUCH) - touch_pmd(vma, addr, pmd, flags); + touch_pmd(vma, addr, pmd, flags & FOLL_WRITE); /* * device mapped pages can only be returned if the @@ -1121,15 +1183,15 @@ out: #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static void touch_pud(struct vm_area_struct *vma, unsigned long addr, - pud_t *pud, int flags) + pud_t *pud, bool write) { pud_t _pud; _pud = pud_mkyoung(*pud); - if (flags & FOLL_WRITE) + if (write) _pud = pud_mkdirty(_pud); if (pudp_set_access_flags(vma, addr & HPAGE_PUD_MASK, - pud, _pud, flags & FOLL_WRITE)) + pud, _pud, write)) update_mmu_cache_pud(vma, addr, pud); } @@ -1156,7 +1218,7 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, return NULL; if (flags & FOLL_TOUCH) - touch_pud(vma, addr, pud, flags); + touch_pud(vma, addr, pud, flags & FOLL_WRITE); /* * device mapped pages can only be returned if the @@ -1221,21 +1283,13 @@ out_unlock: void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) { - pud_t entry; - unsigned long haddr; bool write = vmf->flags & FAULT_FLAG_WRITE; vmf->ptl = pud_lock(vmf->vma->vm_mm, vmf->pud); if (unlikely(!pud_same(*vmf->pud, orig_pud))) goto unlock; - entry = pud_mkyoung(orig_pud); - if (write) - entry = pud_mkdirty(entry); - haddr = vmf->address & HPAGE_PUD_MASK; - if (pudp_set_access_flags(vmf->vma, haddr, vmf->pud, entry, write)) - update_mmu_cache_pud(vmf->vma, vmf->address, vmf->pud); - + touch_pud(vmf->vma, vmf->address, vmf->pud, write); unlock: spin_unlock(vmf->ptl); } @@ -1243,21 +1297,13 @@ unlock: void huge_pmd_set_accessed(struct vm_fault *vmf) { - pmd_t entry; - unsigned long haddr; bool write = vmf->flags & FAULT_FLAG_WRITE; - pmd_t orig_pmd = vmf->orig_pmd; vmf->ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); - if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) + if (unlikely(!pmd_same(*vmf->pmd, vmf->orig_pmd))) goto unlock; - entry = pmd_mkyoung(orig_pmd); - if (write) - entry = pmd_mkdirty(entry); - haddr = vmf->address & HPAGE_PMD_MASK; - if (pmdp_set_access_flags(vmf->vma, haddr, vmf->pmd, entry, write)) - update_mmu_cache_pmd(vmf->vma, vmf->address, vmf->pmd); + touch_pmd(vmf->vma, vmf->address, vmf->pmd, write); unlock: spin_unlock(vmf->ptl); @@ -1393,7 +1439,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, return ERR_PTR(-ENOMEM); if (flags & FOLL_TOUCH) - touch_pmd(vma, addr, pmd, flags); + touch_pmd(vma, addr, pmd, flags & FOLL_WRITE); page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page); @@ -1686,7 +1732,7 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, pmd = move_soft_dirty_pmd(pmd); set_pmd_at(mm, new_addr, new_pmd, pmd); if (force_flush) - flush_tlb_range(vma, old_addr, old_addr + PMD_SIZE); + flush_pmd_tlb_range(vma, old_addr, old_addr + PMD_SIZE); if (new_ptl != old_ptl) spin_unlock(new_ptl); spin_unlock(old_ptl); @@ -1843,10 +1889,10 @@ spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) } /* - * Returns true if a given pud maps a thp, false otherwise. + * Returns page table lock pointer if a given pud maps a thp, NULL otherwise. * - * Note that if it returns true, this routine returns without unlocking page - * table lock. So callers must unlock it. + * Note that if it returns page table lock pointer, this routine returns without + * unlocking page table lock. So callers must unlock it. */ spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma) { @@ -1868,12 +1914,7 @@ int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, ptl = __pud_trans_huge_lock(pud, vma); if (!ptl) return 0; - /* - * For architectures like ppc64 we look at deposited pgtable - * when calling pudp_huge_get_and_clear. So do the - * pgtable_trans_huge_withdraw after finishing pudp related - * operations. - */ + pudp_huge_get_and_clear_full(tlb->mm, addr, pud, tlb->fullmm); tlb_remove_pud_tlb_entry(tlb, pud, addr); if (vma_is_special_huge(vma)) { @@ -1938,7 +1979,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, * replacing a zero pmd write protected page with a zero pte write * protected page. * - * See Documentation/vm/mmu_notifier.rst + * See Documentation/mm/mmu_notifier.rst */ pmdp_huge_clear_flush(vma, haddr, pmd); @@ -2195,6 +2236,10 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || is_pmd_migration_entry(*pmd)) { + /* + * It's safe to call pmd_page when folio is set because it's + * guaranteed that pmd is present. + */ if (folio && folio != page_folio(pmd_page(*pmd))) goto out; __split_huge_pmd_locked(vma, pmd, range.start, freeze); @@ -2502,7 +2547,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, * requires taking the lru_lock so we do the put_page * of the tail pages after the split is complete. */ - put_page(subpage); + free_page_and_swap_cache(subpage); } } @@ -2821,9 +2866,12 @@ static void split_huge_pages_all(void) unsigned long total = 0, split = 0; pr_debug("Split all THPs\n"); - for_each_populated_zone(zone) { + for_each_zone(zone) { + if (!managed_zone(zone)) + continue; max_zone_pfn = zone_end_pfn(zone); for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) { + int nr_pages; if (!pfn_valid(pfn)) continue; @@ -2839,8 +2887,10 @@ static void split_huge_pages_all(void) total++; lock_page(page); + nr_pages = thp_nr_pages(page); if (!split_huge_page(page)) split++; + pfn += nr_pages - 1; unlock_page(page); next: put_page(page); @@ -2898,10 +2948,10 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start, * table filled with PTE-mapped THPs, each of which is distinct. */ for (addr = vaddr_start; addr < vaddr_end; addr += PAGE_SIZE) { - struct vm_area_struct *vma = find_vma(mm, addr); + struct vm_area_struct *vma = vma_lookup(mm, addr); struct page *page; - if (!vma || addr < vma->vm_start) + if (!vma) break; /* skip special VMA and hugetlb VMA */ @@ -2913,9 +2963,7 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start, /* FOLL_DUMP to ignore special (like zero) pages */ page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP); - if (IS_ERR(page)) - continue; - if (!page) + if (IS_ERR_OR_NULL(page) || is_zone_device_page(page)) continue; if (!is_transparent_hugepage(page)) @@ -3137,7 +3185,7 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) struct vm_area_struct *vma = pvmw->vma; struct mm_struct *mm = vma->vm_mm; unsigned long address = pvmw->address; - unsigned long mmun_start = address & HPAGE_PMD_MASK; + unsigned long haddr = address & HPAGE_PMD_MASK; pmd_t pmde; swp_entry_t entry; @@ -3146,7 +3194,7 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) entry = pmd_to_swp_entry(*pvmw->pmd); get_page(new); - pmde = pmd_mkold(mk_huge_pmd(new, vma->vm_page_prot)); + pmde = pmd_mkold(mk_huge_pmd(new, READ_ONCE(vma->vm_page_prot))); if (pmd_swp_soft_dirty(*pvmw->pmd)) pmde = pmd_mksoft_dirty(pmde); if (is_writable_migration_entry(entry)) @@ -3160,12 +3208,12 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) if (!is_readable_migration_entry(entry)) rmap_flags |= RMAP_EXCLUSIVE; - page_add_anon_rmap(new, vma, mmun_start, rmap_flags); + page_add_anon_rmap(new, vma, haddr, rmap_flags); } else { page_add_file_rmap(new, vma, true); } VM_BUG_ON(pmd_write(pmde) && PageAnon(new) && !PageAnonExclusive(new)); - set_pmd_at(mm, mmun_start, pvmw->pmd, pmde); + set_pmd_at(mm, haddr, pvmw->pmd, pmde); /* No need to invalidate - it was non-present before */ update_mmu_cache_pmd(vma, address, pvmw->pmd); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index aa39534898e0..f044962ad9df 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -66,12 +66,6 @@ static bool hugetlb_cma_page(struct page *page, unsigned int order) #endif static unsigned long hugetlb_cma_size __initdata; -/* - * Minimum page order among possible hugepage sizes, set to a proper value - * at boot time. - */ -static unsigned int minimum_order __read_mostly = UINT_MAX; - __initdata LIST_HEAD(huge_boot_pages); /* for command line parsing */ @@ -1135,7 +1129,7 @@ static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid) lockdep_assert_held(&hugetlb_lock); list_for_each_entry(page, &h->hugepage_freelists[nid], lru) { - if (pin && !is_pinnable_page(page)) + if (pin && !is_longterm_pinnable_page(page)) continue; if (PageHWPoison(page)) @@ -2152,11 +2146,17 @@ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn) unsigned long pfn; struct page *page; int rc = 0; + unsigned int order; + struct hstate *h; if (!hugepages_supported()) return rc; - for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) { + order = huge_page_order(&default_hstate); + for_each_hstate(h) + order = min(order, huge_page_order(h)); + + for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << order) { page = pfn_to_page(pfn); rc = dissolve_free_huge_page(page); if (rc) @@ -2766,8 +2766,7 @@ retry: * Fail with -EBUSY if not possible. */ spin_unlock_irq(&hugetlb_lock); - if (!isolate_huge_page(old_page, list)) - ret = -EBUSY; + ret = isolate_hugetlb(old_page, list); spin_lock_irq(&hugetlb_lock); goto free_new; } else if (!HPageFreed(old_page)) { @@ -2843,7 +2842,7 @@ int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) if (hstate_is_gigantic(h)) return -ENOMEM; - if (page_count(head) && isolate_huge_page(head, list)) + if (page_count(head) && !isolate_hugetlb(head, list)) ret = 0; else if (!page_count(head)) ret = alloc_and_dissolve_huge_page(h, head, list); @@ -3149,9 +3148,6 @@ static void __init hugetlb_init_hstates(void) struct hstate *h, *h2; for_each_hstate(h) { - if (minimum_order > huge_page_order(h)) - minimum_order = huge_page_order(h); - /* oversize hugepages were init'ed in early boot */ if (!hstate_is_gigantic(h)) hugetlb_hstate_alloc_pages(h); @@ -3176,7 +3172,6 @@ static void __init hugetlb_init_hstates(void) h->demote_order = h2->order; } } - VM_BUG_ON(minimum_order == UINT_MAX); } static void __init report_hugepages(void) @@ -4482,22 +4477,20 @@ int hugetlb_report_node_meminfo(char *buf, int len, int nid) nid, h->surplus_huge_pages_node[nid]); } -void hugetlb_show_meminfo(void) +void hugetlb_show_meminfo_node(int nid) { struct hstate *h; - int nid; if (!hugepages_supported()) return; - for_each_node_state(nid, N_MEMORY) - for_each_hstate(h) - pr_info("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n", - nid, - h->nr_huge_pages_node[nid], - h->free_huge_pages_node[nid], - h->surplus_huge_pages_node[nid], - huge_page_size(h) / SZ_1K); + for_each_hstate(h) + printk("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n", + nid, + h->nr_huge_pages_node[nid], + h->free_huge_pages_node[nid], + h->surplus_huge_pages_node[nid], + huge_page_size(h) / SZ_1K); } void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm) @@ -4732,6 +4725,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, unsigned long npages = pages_per_huge_page(h); struct address_space *mapping = src_vma->vm_file->f_mapping; struct mmu_notifier_range range; + unsigned long last_addr_mask; int ret = 0; if (cow) { @@ -4751,11 +4745,14 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, i_mmap_lock_read(mapping); } + last_addr_mask = hugetlb_mask_last_page(h); for (addr = src_vma->vm_start; addr < src_vma->vm_end; addr += sz) { spinlock_t *src_ptl, *dst_ptl; src_pte = huge_pte_offset(src, addr, sz); - if (!src_pte) + if (!src_pte) { + addr |= last_addr_mask; continue; + } dst_pte = huge_pte_alloc(dst, dst_vma, addr, sz); if (!dst_pte) { ret = -ENOMEM; @@ -4772,8 +4769,10 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, * after taking the lock below. */ dst_entry = huge_ptep_get(dst_pte); - if ((dst_pte == src_pte) || !huge_pte_none(dst_entry)) + if ((dst_pte == src_pte) || !huge_pte_none(dst_entry)) { + addr |= last_addr_mask; continue; + } dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); @@ -4808,12 +4807,11 @@ again: entry = swp_entry_to_pte(swp_entry); if (userfaultfd_wp(src_vma) && uffd_wp) entry = huge_pte_mkuffd_wp(entry); - set_huge_swap_pte_at(src, addr, src_pte, - entry, sz); + set_huge_pte_at(src, addr, src_pte, entry); } if (!userfaultfd_wp(dst_vma) && uffd_wp) entry = huge_pte_clear_uffd_wp(entry); - set_huge_swap_pte_at(dst, addr, dst_pte, entry, sz); + set_huge_pte_at(dst, addr, dst_pte, entry); } else if (unlikely(is_pte_marker(entry))) { /* * We copy the pte marker only if the dst vma has @@ -4880,7 +4878,7 @@ again: * table protection not changing it to point * to a new page. * - * See Documentation/vm/mmu_notifier.rst + * See Documentation/mm/mmu_notifier.rst */ huge_ptep_set_wrprotect(src, addr, src_pte); entry = huge_pte_wrprotect(entry); @@ -4939,7 +4937,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; unsigned long old_end = old_addr + len; - unsigned long old_addr_copy; + unsigned long last_addr_mask; pte_t *src_pte, *dst_pte; struct mmu_notifier_range range; bool shared_pmd = false; @@ -4954,23 +4952,23 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, flush_cache_range(vma, range.start, range.end); mmu_notifier_invalidate_range_start(&range); + last_addr_mask = hugetlb_mask_last_page(h); /* Prevent race with file truncation */ i_mmap_lock_write(mapping); for (; old_addr < old_end; old_addr += sz, new_addr += sz) { src_pte = huge_pte_offset(mm, old_addr, sz); - if (!src_pte) + if (!src_pte) { + old_addr |= last_addr_mask; + new_addr |= last_addr_mask; continue; + } if (huge_pte_none(huge_ptep_get(src_pte))) continue; - /* old_addr arg to huge_pmd_unshare() is a pointer and so the - * arg may be modified. Pass a copy instead to preserve the - * value in old_addr. - */ - old_addr_copy = old_addr; - - if (huge_pmd_unshare(mm, vma, &old_addr_copy, src_pte)) { + if (huge_pmd_unshare(mm, vma, old_addr, src_pte)) { shared_pmd = true; + old_addr |= last_addr_mask; + new_addr |= last_addr_mask; continue; } @@ -5004,6 +5002,7 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct mmu_notifier_range range; + unsigned long last_addr_mask; bool force_flush = false; WARN_ON(!is_vm_hugetlb_page(vma)); @@ -5024,17 +5023,21 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); mmu_notifier_invalidate_range_start(&range); + last_addr_mask = hugetlb_mask_last_page(h); address = start; for (; address < end; address += sz) { ptep = huge_pte_offset(mm, address, sz); - if (!ptep) + if (!ptep) { + address |= last_addr_mask; continue; + } ptl = huge_pte_lock(h, mm, ptep); - if (huge_pmd_unshare(mm, vma, &address, ptep)) { + if (huge_pmd_unshare(mm, vma, address, ptep)) { spin_unlock(ptl); tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); force_flush = true; + address |= last_addr_mask; continue; } @@ -5714,7 +5717,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, */ entry = huge_ptep_get(ptep); if (unlikely(is_hugetlb_entry_migration(entry))) { - migration_entry_wait_huge(vma, mm, ptep); + migration_entry_wait_huge(vma, ptep); return 0; } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) return VM_FAULT_HWPOISON_LARGE | @@ -6052,8 +6055,6 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); - (void)huge_ptep_set_access_flags(dst_vma, dst_addr, dst_pte, _dst_pte, - dst_vma->vm_flags & VM_WRITE); hugetlb_count_add(pages_per_huge_page(h), dst_mm); /* No need to invalidate - it was non-present before */ @@ -6305,6 +6306,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long pages = 0, psize = huge_page_size(h); bool shared_pmd = false; struct mmu_notifier_range range; + unsigned long last_addr_mask; bool uffd_wp = cp_flags & MM_CP_UFFD_WP; bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; @@ -6321,14 +6323,17 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, flush_cache_range(vma, range.start, range.end); mmu_notifier_invalidate_range_start(&range); + last_addr_mask = hugetlb_mask_last_page(h); i_mmap_lock_write(vma->vm_file->f_mapping); for (; address < end; address += psize) { spinlock_t *ptl; ptep = huge_pte_offset(mm, address, psize); - if (!ptep) + if (!ptep) { + address |= last_addr_mask; continue; + } ptl = huge_pte_lock(h, mm, ptep); - if (huge_pmd_unshare(mm, vma, &address, ptep)) { + if (huge_pmd_unshare(mm, vma, address, ptep)) { /* * When uffd-wp is enabled on the vma, unshare * shouldn't happen at all. Warn about it if it @@ -6338,6 +6343,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, pages++; spin_unlock(ptl); shared_pmd = true; + address |= last_addr_mask; continue; } pte = huge_ptep_get(ptep); @@ -6363,8 +6369,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, newpte = pte_swp_mkuffd_wp(newpte); else if (uffd_wp_resolve) newpte = pte_swp_clear_uffd_wp(newpte); - set_huge_swap_pte_at(mm, address, ptep, - newpte, psize); + set_huge_pte_at(mm, address, ptep, newpte); pages++; } spin_unlock(ptl); @@ -6415,7 +6420,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, * No need to call mmu_notifier_invalidate_range() we are downgrading * page table protection not changing it to point to a new page. * - * See Documentation/vm/mmu_notifier.rst + * See Documentation/mm/mmu_notifier.rst */ i_mmap_unlock_write(vma->vm_file->f_mapping); mmu_notifier_invalidate_range_end(&range); @@ -6761,11 +6766,11 @@ out: * 0 the underlying pte page is not shared, or it is the last user */ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long *addr, pte_t *ptep) + unsigned long addr, pte_t *ptep) { - pgd_t *pgd = pgd_offset(mm, *addr); - p4d_t *p4d = p4d_offset(pgd, *addr); - pud_t *pud = pud_offset(p4d, *addr); + pgd_t *pgd = pgd_offset(mm, addr); + p4d_t *p4d = p4d_offset(pgd, addr); + pud_t *pud = pud_offset(p4d, addr); i_mmap_assert_write_locked(vma->vm_file->f_mapping); BUG_ON(page_count(virt_to_page(ptep)) == 0); @@ -6775,14 +6780,6 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, pud_clear(pud); put_page(virt_to_page(ptep)); mm_dec_nr_pmds(mm); - /* - * This update of passed address optimizes loops sequentially - * processing addresses in increments of huge page size (PMD_SIZE - * in this case). By clearing the pud, a PUD_SIZE area is unmapped. - * Update address to the 'last page' in the cleared area so that - * calling loop can move to first page past this area. - */ - *addr |= PUD_SIZE - PMD_SIZE; return 1; } @@ -6794,7 +6791,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, } int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long *addr, pte_t *ptep) + unsigned long addr, pte_t *ptep) { return 0; } @@ -6877,6 +6874,37 @@ pte_t *huge_pte_offset(struct mm_struct *mm, return (pte_t *)pmd; } +/* + * Return a mask that can be used to update an address to the last huge + * page in a page table page mapping size. Used to skip non-present + * page table entries when linearly scanning address ranges. Architectures + * with unique huge page to page table relationships can define their own + * version of this routine. + */ +unsigned long hugetlb_mask_last_page(struct hstate *h) +{ + unsigned long hp_size = huge_page_size(h); + + if (hp_size == PUD_SIZE) + return P4D_SIZE - PUD_SIZE; + else if (hp_size == PMD_SIZE) + return PUD_SIZE - PMD_SIZE; + else + return 0UL; +} + +#else + +/* See description above. Architectures can provide their own version. */ +__weak unsigned long hugetlb_mask_last_page(struct hstate *h) +{ +#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE + if (huge_page_size(h) == PMD_SIZE) + return PUD_SIZE - PMD_SIZE; +#endif + return 0UL; +} + #endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */ /* @@ -6940,7 +6968,7 @@ retry: } else { if (is_hugetlb_entry_migration(pte)) { spin_unlock(ptl); - __migration_entry_wait(mm, (pte_t *)pmd, ptl); + __migration_entry_wait_huge((pte_t *)pmd, ptl); goto retry; } /* @@ -6972,15 +7000,15 @@ follow_huge_pgd(struct mm_struct *mm, unsigned long address, pgd_t *pgd, int fla return pte_page(*(pte_t *)pgd) + ((address & ~PGDIR_MASK) >> PAGE_SHIFT); } -bool isolate_huge_page(struct page *page, struct list_head *list) +int isolate_hugetlb(struct page *page, struct list_head *list) { - bool ret = true; + int ret = 0; spin_lock_irq(&hugetlb_lock); if (!PageHeadHuge(page) || !HPageMigratable(page) || !get_page_unless_zero(page)) { - ret = false; + ret = -EBUSY; goto unlock; } ClearHPageMigratable(page); @@ -7100,21 +7128,18 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) mmu_notifier_invalidate_range_start(&range); i_mmap_lock_write(vma->vm_file->f_mapping); for (address = start; address < end; address += PUD_SIZE) { - unsigned long tmp = address; - ptep = huge_pte_offset(mm, address, sz); if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); - /* We don't want 'address' to be changed */ - huge_pmd_unshare(mm, vma, &tmp, ptep); + huge_pmd_unshare(mm, vma, address, ptep); spin_unlock(ptl); } flush_hugetlb_tlb_range(vma, start, end); i_mmap_unlock_write(vma->vm_file->f_mapping); /* * No need to call mmu_notifier_invalidate_range(), see - * Documentation/vm/mmu_notifier.rst. + * Documentation/mm/mmu_notifier.rst. */ mmu_notifier_invalidate_range_end(&range); } diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index f9942841df18..c86691c431fd 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -772,6 +772,7 @@ static void __init __hugetlb_cgroup_file_dfl_init(int idx) /* Add the numa stat file */ cft = &h->cgroup_files_dfl[6]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.numa_stat", buf); + cft->private = MEMFILE_PRIVATE(idx, 0); cft->seq_show = hugetlb_cgroup_read_numa_stat; cft->flags = CFTYPE_NOT_ON_ROOT; diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index 1089ea8a9c98..1362feb3c6c9 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -6,11 +6,11 @@ * * Author: Muchun Song <songmuchun@bytedance.com> * - * See Documentation/vm/vmemmap_dedup.rst + * See Documentation/mm/vmemmap_dedup.rst */ #define pr_fmt(fmt) "HugeTLB: " fmt -#include <linux/memory_hotplug.h> +#include <linux/memory.h> #include "hugetlb_vmemmap.h" /* @@ -97,18 +97,68 @@ int hugetlb_vmemmap_alloc(struct hstate *h, struct page *head) return ret; } +static unsigned int vmemmap_optimizable_pages(struct hstate *h, + struct page *head) +{ + if (READ_ONCE(vmemmap_optimize_mode) == VMEMMAP_OPTIMIZE_OFF) + return 0; + + if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) { + pmd_t *pmdp, pmd; + struct page *vmemmap_page; + unsigned long vaddr = (unsigned long)head; + + /* + * Only the vmemmap page's vmemmap page can be self-hosted. + * Walking the page tables to find the backing page of the + * vmemmap page. + */ + pmdp = pmd_off_k(vaddr); + /* + * The READ_ONCE() is used to stabilize *pmdp in a register or + * on the stack so that it will stop changing under the code. + * The only concurrent operation where it can be changed is + * split_vmemmap_huge_pmd() (*pmdp will be stable after this + * operation). + */ + pmd = READ_ONCE(*pmdp); + if (pmd_leaf(pmd)) + vmemmap_page = pmd_page(pmd) + pte_index(vaddr); + else + vmemmap_page = pte_page(*pte_offset_kernel(pmdp, vaddr)); + /* + * Due to HugeTLB alignment requirements and the vmemmap pages + * being at the start of the hotplugged memory region in + * memory_hotplug.memmap_on_memory case. Checking any vmemmap + * page's vmemmap page if it is marked as VmemmapSelfHosted is + * sufficient. + * + * [ hotplugged memory ] + * [ section ][...][ section ] + * [ vmemmap ][ usable memory ] + * ^ | | | + * +---+ | | + * ^ | | + * +-------+ | + * ^ | + * +-------------------------------------------+ + */ + if (PageVmemmapSelfHosted(vmemmap_page)) + return 0; + } + + return hugetlb_optimize_vmemmap_pages(h); +} + void hugetlb_vmemmap_free(struct hstate *h, struct page *head) { unsigned long vmemmap_addr = (unsigned long)head; unsigned long vmemmap_end, vmemmap_reuse, vmemmap_pages; - vmemmap_pages = hugetlb_optimize_vmemmap_pages(h); + vmemmap_pages = vmemmap_optimizable_pages(h, head); if (!vmemmap_pages) return; - if (READ_ONCE(vmemmap_optimize_mode) == VMEMMAP_OPTIMIZE_OFF) - return; - static_branch_inc(&hugetlb_optimize_vmemmap_key); vmemmap_addr += RESERVE_VMEMMAP_SIZE; @@ -199,10 +249,10 @@ static struct ctl_table hugetlb_vmemmap_sysctls[] = { static __init int hugetlb_vmemmap_sysctls_init(void) { /* - * If "memory_hotplug.memmap_on_memory" is enabled or "struct page" - * crosses page boundaries, the vmemmap pages cannot be optimized. + * If "struct page" crosses page boundaries, the vmemmap pages cannot + * be optimized. */ - if (!mhp_memmap_on_memory() && is_power_of_2(sizeof(struct page))) + if (is_power_of_2(sizeof(struct page))) register_sysctl_init("vm", hugetlb_vmemmap_sysctls); return 0; diff --git a/mm/internal.h b/mm/internal.h index ddd2d6a46f1b..785409805ed7 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -853,6 +853,7 @@ int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, unsigned long addr, int page_nid, int *flags); void free_zone_device_page(struct page *page); +int migrate_device_coherent_page(struct page *page); /* * mm/gup.c @@ -863,4 +864,22 @@ DECLARE_PER_CPU(struct per_cpu_nodestat, boot_nodestats); extern bool mirrored_kernelcore; +static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma) +{ + /* + * NOTE: we must check this before VM_SOFTDIRTY on soft-dirty + * enablements, because when without soft-dirty being compiled in, + * VM_SOFTDIRTY is defined as 0x0, then !(vm_flags & VM_SOFTDIRTY) + * will be constantly true. + */ + if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY)) + return false; + + /* + * Soft-dirty is kind of special: its tracking is enabled when the + * vma flags not set. + */ + return !(vma->vm_flags & VM_SOFTDIRTY); +} + #endif /* __MM_INTERNAL_H */ diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 78be2beb7453..69f583855c8b 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -344,7 +344,7 @@ static inline bool ____kasan_slab_free(struct kmem_cache *cache, void *object, if (unlikely(nearest_obj(cache, virt_to_slab(object), object) != object)) { - kasan_report_invalid_free(tagged_object, ip); + kasan_report_invalid_free(tagged_object, ip, KASAN_REPORT_INVALID_FREE); return true; } @@ -353,7 +353,7 @@ static inline bool ____kasan_slab_free(struct kmem_cache *cache, void *object, return false; if (!kasan_byte_accessible(tagged_object)) { - kasan_report_invalid_free(tagged_object, ip); + kasan_report_invalid_free(tagged_object, ip, KASAN_REPORT_DOUBLE_FREE); return true; } @@ -378,12 +378,12 @@ bool __kasan_slab_free(struct kmem_cache *cache, void *object, static inline bool ____kasan_kfree_large(void *ptr, unsigned long ip) { if (ptr != page_address(virt_to_head_page(ptr))) { - kasan_report_invalid_free(ptr, ip); + kasan_report_invalid_free(ptr, ip, KASAN_REPORT_INVALID_FREE); return true; } if (!kasan_byte_accessible(ptr)) { - kasan_report_invalid_free(ptr, ip); + kasan_report_invalid_free(ptr, ip, KASAN_REPORT_DOUBLE_FREE); return true; } diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index 9e1b6544bfa8..9ad8eff71b28 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -257,27 +257,37 @@ static void unpoison_vmalloc_pages(const void *addr, u8 tag) } } +static void init_vmalloc_pages(const void *start, unsigned long size) +{ + const void *addr; + + for (addr = start; addr < start + size; addr += PAGE_SIZE) { + struct page *page = virt_to_page(addr); + + clear_highpage_kasan_tagged(page); + } +} + void *__kasan_unpoison_vmalloc(const void *start, unsigned long size, kasan_vmalloc_flags_t flags) { u8 tag; unsigned long redzone_start, redzone_size; - if (!kasan_vmalloc_enabled()) - return (void *)start; - - if (!is_vmalloc_or_module_addr(start)) + if (!kasan_vmalloc_enabled() || !is_vmalloc_or_module_addr(start)) { + if (flags & KASAN_VMALLOC_INIT) + init_vmalloc_pages(start, size); return (void *)start; + } /* - * Skip unpoisoning and assigning a pointer tag for non-VM_ALLOC - * mappings as: + * Don't tag non-VM_ALLOC mappings, as: * * 1. Unlike the software KASAN modes, hardware tag-based KASAN only * supports tagging physical memory. Therefore, it can only tag a * single mapping of normal physical pages. * 2. Hardware tag-based KASAN can only tag memory mapped with special - * mapping protection bits, see arch_vmalloc_pgprot_modify(). + * mapping protection bits, see arch_vmap_pgprot_tagged(). * As non-VM_ALLOC mappings can be mapped outside of vmalloc code, * providing these bits would require tracking all non-VM_ALLOC * mappers. @@ -289,15 +299,19 @@ void *__kasan_unpoison_vmalloc(const void *start, unsigned long size, * * For non-VM_ALLOC allocations, page_alloc memory is tagged as usual. */ - if (!(flags & KASAN_VMALLOC_VM_ALLOC)) + if (!(flags & KASAN_VMALLOC_VM_ALLOC)) { + WARN_ON(flags & KASAN_VMALLOC_INIT); return (void *)start; + } /* * Don't tag executable memory. * The kernel doesn't tolerate having the PC register tagged. */ - if (!(flags & KASAN_VMALLOC_PROT_NORMAL)) + if (!(flags & KASAN_VMALLOC_PROT_NORMAL)) { + WARN_ON(flags & KASAN_VMALLOC_INIT); return (void *)start; + } tag = kasan_random_tag(); start = set_tag(start, tag); diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 610d60d6e5b8..01c03e45acd4 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -125,6 +125,7 @@ static inline bool kasan_sync_fault_possible(void) enum kasan_report_type { KASAN_REPORT_ACCESS, KASAN_REPORT_INVALID_FREE, + KASAN_REPORT_DOUBLE_FREE, }; struct kasan_report_info { @@ -277,7 +278,7 @@ static inline void kasan_print_address_stack_frame(const void *addr) { } bool kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip); -void kasan_report_invalid_free(void *object, unsigned long ip); +void kasan_report_invalid_free(void *object, unsigned long ip, enum kasan_report_type type); struct page *kasan_addr_to_page(const void *addr); struct slab *kasan_addr_to_slab(const void *addr); diff --git a/mm/kasan/report.c b/mm/kasan/report.c index b341a191651d..fe3f606b3a98 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -176,8 +176,12 @@ static void end_report(unsigned long *flags, void *addr) static void print_error_description(struct kasan_report_info *info) { if (info->type == KASAN_REPORT_INVALID_FREE) { - pr_err("BUG: KASAN: double-free or invalid-free in %pS\n", - (void *)info->ip); + pr_err("BUG: KASAN: invalid-free in %pS\n", (void *)info->ip); + return; + } + + if (info->type == KASAN_REPORT_DOUBLE_FREE) { + pr_err("BUG: KASAN: double-free in %pS\n", (void *)info->ip); return; } @@ -433,7 +437,7 @@ static void print_report(struct kasan_report_info *info) } } -void kasan_report_invalid_free(void *ptr, unsigned long ip) +void kasan_report_invalid_free(void *ptr, unsigned long ip, enum kasan_report_type type) { unsigned long flags; struct kasan_report_info info; @@ -448,7 +452,7 @@ void kasan_report_invalid_free(void *ptr, unsigned long ip) start_report(&flags, true); - info.type = KASAN_REPORT_INVALID_FREE; + info.type = type; info.access_addr = ptr; info.first_bad_addr = kasan_reset_tag(ptr); info.access_size = 0; diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 6aff49f6b79e..c252081b11df 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -546,7 +546,7 @@ static unsigned long kfence_init_pool(void) if (!arch_kfence_init_pool()) return addr; - pages = virt_to_page(addr); + pages = virt_to_page(__kfence_pool); /* * Set up object pages: they must have PG_slab set, to avoid freeing @@ -660,7 +660,7 @@ static bool kfence_init_pool_late(void) /* Same as above. */ free_size = KFENCE_POOL_SIZE - (addr - (unsigned long)__kfence_pool); #ifdef CONFIG_CONTIG_ALLOC - free_contig_range(page_to_pfn(virt_to_page(addr)), free_size / PAGE_SIZE); + free_contig_range(page_to_pfn(virt_to_page((void *)addr)), free_size / PAGE_SIZE); #else free_pages_exact((void *)addr, free_size); #endif diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 16be62d493cd..01f71786d530 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -147,8 +147,7 @@ static ssize_t scan_sleep_millisecs_store(struct kobject *kobj, return count; } static struct kobj_attribute scan_sleep_millisecs_attr = - __ATTR(scan_sleep_millisecs, 0644, scan_sleep_millisecs_show, - scan_sleep_millisecs_store); + __ATTR_RW(scan_sleep_millisecs); static ssize_t alloc_sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, @@ -175,8 +174,7 @@ static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj, return count; } static struct kobj_attribute alloc_sleep_millisecs_attr = - __ATTR(alloc_sleep_millisecs, 0644, alloc_sleep_millisecs_show, - alloc_sleep_millisecs_store); + __ATTR_RW(alloc_sleep_millisecs); static ssize_t pages_to_scan_show(struct kobject *kobj, struct kobj_attribute *attr, @@ -200,8 +198,7 @@ static ssize_t pages_to_scan_store(struct kobject *kobj, return count; } static struct kobj_attribute pages_to_scan_attr = - __ATTR(pages_to_scan, 0644, pages_to_scan_show, - pages_to_scan_store); + __ATTR_RW(pages_to_scan); static ssize_t pages_collapsed_show(struct kobject *kobj, struct kobj_attribute *attr, @@ -221,22 +218,21 @@ static ssize_t full_scans_show(struct kobject *kobj, static struct kobj_attribute full_scans_attr = __ATTR_RO(full_scans); -static ssize_t khugepaged_defrag_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) +static ssize_t defrag_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) { return single_hugepage_flag_show(kobj, attr, buf, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); } -static ssize_t khugepaged_defrag_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) +static ssize_t defrag_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) { return single_hugepage_flag_store(kobj, attr, buf, count, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); } static struct kobj_attribute khugepaged_defrag_attr = - __ATTR(defrag, 0644, khugepaged_defrag_show, - khugepaged_defrag_store); + __ATTR_RW(defrag); /* * max_ptes_none controls if khugepaged should collapse hugepages over @@ -246,21 +242,21 @@ static struct kobj_attribute khugepaged_defrag_attr = * runs. Increasing max_ptes_none will instead potentially reduce the * free memory in the system during the khugepaged scan. */ -static ssize_t khugepaged_max_ptes_none_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) +static ssize_t max_ptes_none_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_none); } -static ssize_t khugepaged_max_ptes_none_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) +static ssize_t max_ptes_none_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) { int err; unsigned long max_ptes_none; err = kstrtoul(buf, 10, &max_ptes_none); - if (err || max_ptes_none > HPAGE_PMD_NR-1) + if (err || max_ptes_none > HPAGE_PMD_NR - 1) return -EINVAL; khugepaged_max_ptes_none = max_ptes_none; @@ -268,25 +264,24 @@ static ssize_t khugepaged_max_ptes_none_store(struct kobject *kobj, return count; } static struct kobj_attribute khugepaged_max_ptes_none_attr = - __ATTR(max_ptes_none, 0644, khugepaged_max_ptes_none_show, - khugepaged_max_ptes_none_store); + __ATTR_RW(max_ptes_none); -static ssize_t khugepaged_max_ptes_swap_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) +static ssize_t max_ptes_swap_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_swap); } -static ssize_t khugepaged_max_ptes_swap_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) +static ssize_t max_ptes_swap_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) { int err; unsigned long max_ptes_swap; err = kstrtoul(buf, 10, &max_ptes_swap); - if (err || max_ptes_swap > HPAGE_PMD_NR-1) + if (err || max_ptes_swap > HPAGE_PMD_NR - 1) return -EINVAL; khugepaged_max_ptes_swap = max_ptes_swap; @@ -295,25 +290,24 @@ static ssize_t khugepaged_max_ptes_swap_store(struct kobject *kobj, } static struct kobj_attribute khugepaged_max_ptes_swap_attr = - __ATTR(max_ptes_swap, 0644, khugepaged_max_ptes_swap_show, - khugepaged_max_ptes_swap_store); + __ATTR_RW(max_ptes_swap); -static ssize_t khugepaged_max_ptes_shared_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) +static ssize_t max_ptes_shared_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_shared); } -static ssize_t khugepaged_max_ptes_shared_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) +static ssize_t max_ptes_shared_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) { int err; unsigned long max_ptes_shared; err = kstrtoul(buf, 10, &max_ptes_shared); - if (err || max_ptes_shared > HPAGE_PMD_NR-1) + if (err || max_ptes_shared > HPAGE_PMD_NR - 1) return -EINVAL; khugepaged_max_ptes_shared = max_ptes_shared; @@ -322,8 +316,7 @@ static ssize_t khugepaged_max_ptes_shared_store(struct kobject *kobj, } static struct kobj_attribute khugepaged_max_ptes_shared_attr = - __ATTR(max_ptes_shared, 0644, khugepaged_max_ptes_shared_show, - khugepaged_max_ptes_shared_store); + __ATTR_RW(max_ptes_shared); static struct attribute *khugepaged_attr[] = { &khugepaged_defrag_attr.attr, @@ -437,43 +430,6 @@ static inline int khugepaged_test_exit(struct mm_struct *mm) return atomic_read(&mm->mm_users) == 0; } -bool hugepage_vma_check(struct vm_area_struct *vma, - unsigned long vm_flags) -{ - if (!transhuge_vma_enabled(vma, vm_flags)) - return false; - - if (vm_flags & VM_NO_KHUGEPAGED) - return false; - - /* Don't run khugepaged against DAX vma */ - if (vma_is_dax(vma)) - return false; - - if (vma->vm_file && !IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - - vma->vm_pgoff, HPAGE_PMD_NR)) - return false; - - /* Enabled via shmem mount options or sysfs settings. */ - if (shmem_file(vma->vm_file)) - return shmem_huge_enabled(vma); - - /* THP settings require madvise. */ - if (!(vm_flags & VM_HUGEPAGE) && !khugepaged_always()) - return false; - - /* Only regular file is valid */ - if (file_thp_enabled(vma)) - return true; - - if (!vma->anon_vma || !vma_is_anonymous(vma)) - return false; - if (vma_is_temporary_stack(vma)) - return false; - - return true; -} - void __khugepaged_enter(struct mm_struct *mm) { struct mm_slot *mm_slot; @@ -509,10 +465,8 @@ void khugepaged_enter_vma(struct vm_area_struct *vma, unsigned long vm_flags) { if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) && - khugepaged_enabled() && - (((vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK) < - (vma->vm_end & HPAGE_PMD_MASK))) { - if (hugepage_vma_check(vma, vm_flags)) + hugepage_flags_enabled()) { + if (hugepage_vma_check(vma, vm_flags, false, false)) __khugepaged_enter(vma->vm_mm); } } @@ -599,7 +553,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, int none_or_zero = 0, shared = 0, result = 0, referenced = 0; bool writable = false; - for (_pte = pte; _pte < pte+HPAGE_PMD_NR; + for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { pte_t pteval = *_pte; if (pte_none(pteval) || (pte_present(pteval) && @@ -618,7 +572,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, goto out; } page = vm_normal_page(vma, address, pteval); - if (unlikely(!page)) { + if (unlikely(!page) || unlikely(is_zone_device_page(page))) { result = SCAN_PAGE_NULL; goto out; } @@ -762,7 +716,12 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page, list_for_each_entry_safe(src_page, tmp, compound_pagelist, lru) { list_del(&src_page->lru); - release_pte_page(src_page); + mod_node_page_state(page_pgdat(src_page), + NR_ISOLATED_ANON + page_is_file_lru(src_page), + -compound_nr(src_page)); + unlock_page(src_page); + free_swap_cache(src_page); + putback_lru_page(src_page); } } @@ -802,6 +761,10 @@ static bool khugepaged_scan_abort(int nid) return false; } +#define khugepaged_defrag() \ + (transparent_hugepage_flags & \ + (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)) + /* Defrag for khugepaged will enter direct reclaim/compaction if necessary */ static inline gfp_t alloc_hugepage_khugepaged_gfpmask(void) { @@ -899,7 +862,7 @@ static struct page *khugepaged_alloc_hugepage(bool *wait) khugepaged_alloc_sleep(); } else count_vm_event(THP_COLLAPSE_ALLOC); - } while (unlikely(!hpage) && likely(khugepaged_enabled())); + } while (unlikely(!hpage) && likely(hugepage_flags_enabled())); return hpage; } @@ -947,7 +910,6 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, struct vm_area_struct **vmap) { struct vm_area_struct *vma; - unsigned long hstart, hend; if (unlikely(khugepaged_test_exit(mm))) return SCAN_ANY_PROCESS; @@ -956,13 +918,17 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, if (!vma) return SCAN_VMA_NULL; - hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; - hend = vma->vm_end & HPAGE_PMD_MASK; - if (address < hstart || address + HPAGE_PMD_SIZE > hend) + if (!transhuge_vma_suitable(vma, address)) return SCAN_ADDRESS_RANGE; - if (!hugepage_vma_check(vma, vma->vm_flags)) + if (!hugepage_vma_check(vma, vma->vm_flags, false, false)) return SCAN_VMA_CHECK; - /* Anon VMA expected */ + /* + * Anon VMA expected, the address may be unmapped then + * remapped to file after khugepaged reaquired the mmap_lock. + * + * hugepage_vma_check may return true for qualified file + * vmas. + */ if (!vma->anon_vma || !vma_is_anonymous(vma)) return SCAN_VMA_CHECK; return 0; @@ -972,8 +938,8 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, * Bring missing pages in from swap, to complete THP collapse. * Only done if khugepaged_scan_pmd believes it is worthwhile. * - * Called and returns without pte mapped or spinlocks held, - * but with mmap_lock held to protect against vma changes. + * Called and returns without pte mapped or spinlocks held. + * Note that if false is returned, mmap_lock will be released. */ static bool __collapse_huge_page_swapin(struct mm_struct *mm, @@ -1000,27 +966,24 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm, pte_unmap(vmf.pte); continue; } - swapped_in++; ret = do_swap_page(&vmf); - /* do_swap_page returns VM_FAULT_RETRY with released mmap_lock */ + /* + * do_swap_page returns VM_FAULT_RETRY with released mmap_lock. + * Note we treat VM_FAULT_RETRY as VM_FAULT_ERROR here because + * we do not retry here and swap entry will remain in pagetable + * resulting in later failure. + */ if (ret & VM_FAULT_RETRY) { - mmap_read_lock(mm); - if (hugepage_vma_revalidate(mm, haddr, &vma)) { - /* vma is no longer available, don't continue to swapin */ - trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0); - return false; - } - /* check if the pmd is still valid */ - if (mm_find_pmd(mm, haddr) != pmd) { - trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0); - return false; - } + trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0); + return false; } if (ret & VM_FAULT_ERROR) { + mmap_read_unlock(mm); trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0); return false; } + swapped_in++; } /* Drain LRU add pagevec to remove extra pin on the swapped in pages */ @@ -1086,13 +1049,12 @@ static void collapse_huge_page(struct mm_struct *mm, } /* - * __collapse_huge_page_swapin always returns with mmap_lock locked. - * If it fails, we release mmap_lock and jump out_nolock. + * __collapse_huge_page_swapin will return with mmap_lock released + * when it fails. So we jump out_nolock directly in that case. * Continuing to collapse causes inconsistency. */ if (unmapped && !__collapse_huge_page_swapin(mm, vma, address, pmd, referenced)) { - mmap_read_unlock(mm); goto out_nolock; } @@ -1219,7 +1181,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load)); pte = pte_offset_map_lock(mm, pmd, address, &ptl); - for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR; + for (_address = address, _pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, _address += PAGE_SIZE) { pte_t pteval = *_pte; if (is_swap_pte(pteval)) { @@ -1267,7 +1229,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, writable = true; page = vm_normal_page(vma, _address, pteval); - if (unlikely(!page)) { + if (unlikely(!page) || unlikely(is_zone_device_page(page))) { result = SCAN_PAGE_NULL; goto out_unmap; } @@ -1309,7 +1271,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, /* * Check if the page has any GUP (or other external) pins. * - * Here the check is racy it may see totmal_mapcount > refcount + * Here the check is racy it may see total_mapcount > refcount * in some cases. * For example, one process with one forked child process. * The parent has the PMD split due to MADV_DONTNEED, then @@ -1382,8 +1344,8 @@ static void collect_mm_slot(struct mm_slot *mm_slot) * Notify khugepaged that given addr of the mm is pte-mapped THP. Then * khugepaged should try to collapse the page table. */ -static int khugepaged_add_pte_mapped_thp(struct mm_struct *mm, - unsigned long addr) +static void khugepaged_add_pte_mapped_thp(struct mm_struct *mm, + unsigned long addr) { struct mm_slot *mm_slot; @@ -1394,7 +1356,6 @@ static int khugepaged_add_pte_mapped_thp(struct mm_struct *mm, if (likely(mm_slot && mm_slot->nr_pte_mapped_thp < MAX_PTE_MAPPED_THP)) mm_slot->pte_mapped_thp[mm_slot->nr_pte_mapped_thp++] = addr; spin_unlock(&khugepaged_mm_lock); - return 0; } static void collapse_and_free_pmd(struct mm_struct *mm, struct vm_area_struct *vma, @@ -1444,7 +1405,7 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) * the valid THP. Add extra VM_HUGEPAGE so hugepage_vma_check() * will not fail the vma for missing VM_HUGEPAGE */ - if (!hugepage_vma_check(vma, vma->vm_flags | VM_HUGEPAGE)) + if (!hugepage_vma_check(vma, vma->vm_flags | VM_HUGEPAGE, false, false)) return; /* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */ @@ -1479,7 +1440,8 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) goto abort; page = vm_normal_page(vma, addr, *pte); - + if (WARN_ON_ONCE(page && is_zone_device_page(page))) + page = NULL; /* * Note that uprobe, debugger, or MAP_PRIVATE may change the * page table, but the new page will not be a subpage of hpage. @@ -1497,6 +1459,8 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) if (pte_none(*pte)) continue; page = vm_normal_page(vma, addr, *pte); + if (WARN_ON_ONCE(page && is_zone_device_page(page))) + goto abort; page_remove_rmap(page, vma, false); } @@ -1557,7 +1521,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) * mmap_write_lock(mm) as PMD-mapping is likely to be split * later. * - * Not that vma->anon_vma check is racy: it can be set up after + * Note that vma->anon_vma check is racy: it can be set up after * the check but before we took mmap_lock by the fault path. * But page lock would prevent establishing any new ptes of the * page, so we are safe. @@ -1885,8 +1849,8 @@ out_unlock: if (nr_none) { __mod_lruvec_page_state(new_page, NR_FILE_PAGES, nr_none); - if (is_shmem) - __mod_lruvec_page_state(new_page, NR_SHMEM, nr_none); + /* nr_none is always 0 for non-shmem. */ + __mod_lruvec_page_state(new_page, NR_SHMEM, nr_none); } /* Join all the small entries into a single multi-index entry */ @@ -1950,10 +1914,10 @@ xa_unlocked: /* Something went wrong: roll back page cache changes */ xas_lock_irq(&xas); - mapping->nrpages -= nr_none; - - if (is_shmem) + if (nr_none) { + mapping->nrpages -= nr_none; shmem_uncharge(mapping->host, nr_none); + } xas_set(&xas, start); xas_for_each(&xas, page, end - 1) { @@ -2131,22 +2095,18 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, progress++; break; } - if (!hugepage_vma_check(vma, vma->vm_flags)) { + if (!hugepage_vma_check(vma, vma->vm_flags, false, false)) { skip: progress++; continue; } - hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; - hend = vma->vm_end & HPAGE_PMD_MASK; - if (hstart >= hend) - goto skip; + hstart = round_up(vma->vm_start, HPAGE_PMD_SIZE); + hend = round_down(vma->vm_end, HPAGE_PMD_SIZE); if (khugepaged_scan.address > hend) goto skip; if (khugepaged_scan.address < hstart) khugepaged_scan.address = hstart; VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK); - if (shmem_file(vma->vm_file) && !shmem_huge_enabled(vma)) - goto skip; while (khugepaged_scan.address < hend) { int ret; @@ -2216,7 +2176,7 @@ breakouterloop_mmap_lock: static int khugepaged_has_work(void) { return !list_empty(&khugepaged_scan.mm_head) && - khugepaged_enabled(); + hugepage_flags_enabled(); } static int khugepaged_wait_event(void) @@ -2281,7 +2241,7 @@ static void khugepaged_wait_work(void) return; } - if (khugepaged_enabled()) + if (hugepage_flags_enabled()) wait_event_freezable(khugepaged_wait, khugepaged_wait_event()); } @@ -2312,7 +2272,7 @@ static void set_recommended_min_free_kbytes(void) int nr_zones = 0; unsigned long recommended_min; - if (!khugepaged_enabled()) { + if (!hugepage_flags_enabled()) { calculate_min_free_kbytes(); goto update_wmarks; } @@ -2362,7 +2322,7 @@ int start_stop_khugepaged(void) int err = 0; mutex_lock(&khugepaged_mutex); - if (khugepaged_enabled()) { + if (hugepage_flags_enabled()) { if (!khugepaged_thread) khugepaged_thread = kthread_run(khugepaged, NULL, "khugepaged"); @@ -2388,7 +2348,7 @@ fail: void khugepaged_min_free_kbytes_update(void) { mutex_lock(&khugepaged_mutex); - if (khugepaged_enabled() && khugepaged_thread) + if (hugepage_flags_enabled() && khugepaged_thread) set_recommended_min_free_kbytes(); mutex_unlock(&khugepaged_mutex); } diff --git a/mm/kmemleak.c b/mm/kmemleak.c index a182f5ddaf68..1eddc0132f7f 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -14,14 +14,16 @@ * The following locks and mutexes are used by kmemleak: * * - kmemleak_lock (raw_spinlock_t): protects the object_list modifications and - * accesses to the object_tree_root. The object_list is the main list - * holding the metadata (struct kmemleak_object) for the allocated memory - * blocks. The object_tree_root is a red black tree used to look-up - * metadata based on a pointer to the corresponding memory block. The - * kmemleak_object structures are added to the object_list and - * object_tree_root in the create_object() function called from the - * kmemleak_alloc() callback and removed in delete_object() called from the - * kmemleak_free() callback + * accesses to the object_tree_root (or object_phys_tree_root). The + * object_list is the main list holding the metadata (struct kmemleak_object) + * for the allocated memory blocks. The object_tree_root and object_phys_tree_root + * are red black trees used to look-up metadata based on a pointer to the + * corresponding memory block. The object_phys_tree_root is for objects + * allocated with physical address. The kmemleak_object structures are + * added to the object_list and object_tree_root (or object_phys_tree_root) + * in the create_object() function called from the kmemleak_alloc() (or + * kmemleak_alloc_phys()) callback and removed in delete_object() called from + * the kmemleak_free() callback * - kmemleak_object.lock (raw_spinlock_t): protects a kmemleak_object. * Accesses to the metadata (e.g. count) are protected by this lock. Note * that some members of this structure may be protected by other means @@ -172,6 +174,8 @@ struct kmemleak_object { #define OBJECT_NO_SCAN (1 << 2) /* flag set to fully scan the object when scan_area allocation failed */ #define OBJECT_FULL_SCAN (1 << 3) +/* flag set for object allocated with physical address */ +#define OBJECT_PHYS (1 << 4) #define HEX_PREFIX " " /* number of bytes to print per line; must be 16 or 32 */ @@ -193,7 +197,9 @@ static int mem_pool_free_count = ARRAY_SIZE(mem_pool); static LIST_HEAD(mem_pool_free_list); /* search tree for object boundaries */ static struct rb_root object_tree_root = RB_ROOT; -/* protecting the access to object_list and object_tree_root */ +/* search tree for object (with OBJECT_PHYS flag) boundaries */ +static struct rb_root object_phys_tree_root = RB_ROOT; +/* protecting the access to object_list, object_tree_root (or object_phys_tree_root) */ static DEFINE_RAW_SPINLOCK(kmemleak_lock); /* allocation caches for kmemleak internal data */ @@ -285,6 +291,9 @@ static void hex_dump_object(struct seq_file *seq, const u8 *ptr = (const u8 *)object->pointer; size_t len; + if (WARN_ON_ONCE(object->flags & OBJECT_PHYS)) + return; + /* limit the number of lines to HEX_MAX_LINES */ len = min_t(size_t, object->size, HEX_MAX_LINES * HEX_ROW_SIZE); @@ -378,9 +387,11 @@ static void dump_object_info(struct kmemleak_object *object) * beginning of the memory block are allowed. The kmemleak_lock must be held * when calling this function. */ -static struct kmemleak_object *lookup_object(unsigned long ptr, int alias) +static struct kmemleak_object *__lookup_object(unsigned long ptr, int alias, + bool is_phys) { - struct rb_node *rb = object_tree_root.rb_node; + struct rb_node *rb = is_phys ? object_phys_tree_root.rb_node : + object_tree_root.rb_node; unsigned long untagged_ptr = (unsigned long)kasan_reset_tag((void *)ptr); while (rb) { @@ -406,6 +417,12 @@ static struct kmemleak_object *lookup_object(unsigned long ptr, int alias) return NULL; } +/* Look-up a kmemleak object which allocated with virtual address. */ +static struct kmemleak_object *lookup_object(unsigned long ptr, int alias) +{ + return __lookup_object(ptr, alias, false); +} + /* * Increment the object use_count. Return 1 if successful or 0 otherwise. Note * that once an object's use_count reached 0, the RCU freeing was already @@ -515,14 +532,15 @@ static void put_object(struct kmemleak_object *object) /* * Look up an object in the object search tree and increase its use_count. */ -static struct kmemleak_object *find_and_get_object(unsigned long ptr, int alias) +static struct kmemleak_object *__find_and_get_object(unsigned long ptr, int alias, + bool is_phys) { unsigned long flags; struct kmemleak_object *object; rcu_read_lock(); raw_spin_lock_irqsave(&kmemleak_lock, flags); - object = lookup_object(ptr, alias); + object = __lookup_object(ptr, alias, is_phys); raw_spin_unlock_irqrestore(&kmemleak_lock, flags); /* check whether the object is still available */ @@ -533,28 +551,39 @@ static struct kmemleak_object *find_and_get_object(unsigned long ptr, int alias) return object; } +/* Look up and get an object which allocated with virtual address. */ +static struct kmemleak_object *find_and_get_object(unsigned long ptr, int alias) +{ + return __find_and_get_object(ptr, alias, false); +} + /* - * Remove an object from the object_tree_root and object_list. Must be called - * with the kmemleak_lock held _if_ kmemleak is still enabled. + * Remove an object from the object_tree_root (or object_phys_tree_root) + * and object_list. Must be called with the kmemleak_lock held _if_ kmemleak + * is still enabled. */ static void __remove_object(struct kmemleak_object *object) { - rb_erase(&object->rb_node, &object_tree_root); + rb_erase(&object->rb_node, object->flags & OBJECT_PHYS ? + &object_phys_tree_root : + &object_tree_root); list_del_rcu(&object->object_list); } /* * Look up an object in the object search tree and remove it from both - * object_tree_root and object_list. The returned object's use_count should be - * at least 1, as initially set by create_object(). + * object_tree_root (or object_phys_tree_root) and object_list. The + * returned object's use_count should be at least 1, as initially set + * by create_object(). */ -static struct kmemleak_object *find_and_remove_object(unsigned long ptr, int alias) +static struct kmemleak_object *find_and_remove_object(unsigned long ptr, int alias, + bool is_phys) { unsigned long flags; struct kmemleak_object *object; raw_spin_lock_irqsave(&kmemleak_lock, flags); - object = lookup_object(ptr, alias); + object = __lookup_object(ptr, alias, is_phys); if (object) __remove_object(object); raw_spin_unlock_irqrestore(&kmemleak_lock, flags); @@ -572,10 +601,12 @@ static int __save_stack_trace(unsigned long *trace) /* * Create the metadata (struct kmemleak_object) corresponding to an allocated - * memory block and add it to the object_list and object_tree_root. + * memory block and add it to the object_list and object_tree_root (or + * object_phys_tree_root). */ -static struct kmemleak_object *create_object(unsigned long ptr, size_t size, - int min_count, gfp_t gfp) +static struct kmemleak_object *__create_object(unsigned long ptr, size_t size, + int min_count, gfp_t gfp, + bool is_phys) { unsigned long flags; struct kmemleak_object *object, *parent; @@ -595,7 +626,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size, INIT_HLIST_HEAD(&object->area_list); raw_spin_lock_init(&object->lock); atomic_set(&object->use_count, 1); - object->flags = OBJECT_ALLOCATED; + object->flags = OBJECT_ALLOCATED | (is_phys ? OBJECT_PHYS : 0); object->pointer = ptr; object->size = kfence_ksize((void *)ptr) ?: size; object->excess_ref = 0; @@ -628,9 +659,16 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size, raw_spin_lock_irqsave(&kmemleak_lock, flags); untagged_ptr = (unsigned long)kasan_reset_tag((void *)ptr); - min_addr = min(min_addr, untagged_ptr); - max_addr = max(max_addr, untagged_ptr + size); - link = &object_tree_root.rb_node; + /* + * Only update min_addr and max_addr with object + * storing virtual address. + */ + if (!is_phys) { + min_addr = min(min_addr, untagged_ptr); + max_addr = max(max_addr, untagged_ptr + size); + } + link = is_phys ? &object_phys_tree_root.rb_node : + &object_tree_root.rb_node; rb_parent = NULL; while (*link) { rb_parent = *link; @@ -654,7 +692,8 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size, } } rb_link_node(&object->rb_node, rb_parent, link); - rb_insert_color(&object->rb_node, &object_tree_root); + rb_insert_color(&object->rb_node, is_phys ? &object_phys_tree_root : + &object_tree_root); list_add_tail_rcu(&object->object_list, &object_list); out: @@ -662,6 +701,20 @@ out: return object; } +/* Create kmemleak object which allocated with virtual address. */ +static struct kmemleak_object *create_object(unsigned long ptr, size_t size, + int min_count, gfp_t gfp) +{ + return __create_object(ptr, size, min_count, gfp, false); +} + +/* Create kmemleak object which allocated with physical address. */ +static struct kmemleak_object *create_object_phys(unsigned long ptr, size_t size, + int min_count, gfp_t gfp) +{ + return __create_object(ptr, size, min_count, gfp, true); +} + /* * Mark the object as not allocated and schedule RCU freeing via put_object(). */ @@ -690,7 +743,7 @@ static void delete_object_full(unsigned long ptr) { struct kmemleak_object *object; - object = find_and_remove_object(ptr, 0); + object = find_and_remove_object(ptr, 0, false); if (!object) { #ifdef DEBUG kmemleak_warn("Freeing unknown object at 0x%08lx\n", @@ -706,12 +759,12 @@ static void delete_object_full(unsigned long ptr) * delete it. If the memory block is partially freed, the function may create * additional metadata for the remaining parts of the block. */ -static void delete_object_part(unsigned long ptr, size_t size) +static void delete_object_part(unsigned long ptr, size_t size, bool is_phys) { struct kmemleak_object *object; unsigned long start, end; - object = find_and_remove_object(ptr, 1); + object = find_and_remove_object(ptr, 1, is_phys); if (!object) { #ifdef DEBUG kmemleak_warn("Partially freeing unknown object at 0x%08lx (size %zu)\n", @@ -728,11 +781,11 @@ static void delete_object_part(unsigned long ptr, size_t size) start = object->pointer; end = object->pointer + object->size; if (ptr > start) - create_object(start, ptr - start, object->min_count, - GFP_KERNEL); + __create_object(start, ptr - start, object->min_count, + GFP_KERNEL, is_phys); if (ptr + size < end) - create_object(ptr + size, end - ptr - size, object->min_count, - GFP_KERNEL); + __create_object(ptr + size, end - ptr - size, object->min_count, + GFP_KERNEL, is_phys); __delete_object(object); } @@ -753,11 +806,11 @@ static void paint_it(struct kmemleak_object *object, int color) raw_spin_unlock_irqrestore(&object->lock, flags); } -static void paint_ptr(unsigned long ptr, int color) +static void paint_ptr(unsigned long ptr, int color, bool is_phys) { struct kmemleak_object *object; - object = find_and_get_object(ptr, 0); + object = __find_and_get_object(ptr, 0, is_phys); if (!object) { kmemleak_warn("Trying to color unknown object at 0x%08lx as %s\n", ptr, @@ -775,16 +828,16 @@ static void paint_ptr(unsigned long ptr, int color) */ static void make_gray_object(unsigned long ptr) { - paint_ptr(ptr, KMEMLEAK_GREY); + paint_ptr(ptr, KMEMLEAK_GREY, false); } /* * Mark the object as black-colored so that it is ignored from scans and * reporting. */ -static void make_black_object(unsigned long ptr) +static void make_black_object(unsigned long ptr, bool is_phys) { - paint_ptr(ptr, KMEMLEAK_BLACK); + paint_ptr(ptr, KMEMLEAK_BLACK, is_phys); } /* @@ -990,7 +1043,7 @@ void __ref kmemleak_free_part(const void *ptr, size_t size) pr_debug("%s(0x%p)\n", __func__, ptr); if (kmemleak_enabled && ptr && !IS_ERR(ptr)) - delete_object_part((unsigned long)ptr, size); + delete_object_part((unsigned long)ptr, size, false); } EXPORT_SYMBOL_GPL(kmemleak_free_part); @@ -1078,7 +1131,7 @@ void __ref kmemleak_ignore(const void *ptr) pr_debug("%s(0x%p)\n", __func__, ptr); if (kmemleak_enabled && ptr && !IS_ERR(ptr)) - make_black_object((unsigned long)ptr); + make_black_object((unsigned long)ptr, false); } EXPORT_SYMBOL(kmemleak_ignore); @@ -1125,15 +1178,18 @@ EXPORT_SYMBOL(kmemleak_no_scan); * address argument * @phys: physical address of the object * @size: size of the object - * @min_count: minimum number of references to this object. - * See kmemleak_alloc() * @gfp: kmalloc() flags used for kmemleak internal memory allocations */ -void __ref kmemleak_alloc_phys(phys_addr_t phys, size_t size, int min_count, - gfp_t gfp) +void __ref kmemleak_alloc_phys(phys_addr_t phys, size_t size, gfp_t gfp) { - if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) - kmemleak_alloc(__va(phys), size, min_count, gfp); + pr_debug("%s(0x%pa, %zu)\n", __func__, &phys, size); + + if (kmemleak_enabled) + /* + * Create object with OBJECT_PHYS flag and + * assume min_count 0. + */ + create_object_phys((unsigned long)phys, size, 0, gfp); } EXPORT_SYMBOL(kmemleak_alloc_phys); @@ -1146,22 +1202,12 @@ EXPORT_SYMBOL(kmemleak_alloc_phys); */ void __ref kmemleak_free_part_phys(phys_addr_t phys, size_t size) { - if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) - kmemleak_free_part(__va(phys), size); -} -EXPORT_SYMBOL(kmemleak_free_part_phys); + pr_debug("%s(0x%pa)\n", __func__, &phys); -/** - * kmemleak_not_leak_phys - similar to kmemleak_not_leak but taking a physical - * address argument - * @phys: physical address of the object - */ -void __ref kmemleak_not_leak_phys(phys_addr_t phys) -{ - if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) - kmemleak_not_leak(__va(phys)); + if (kmemleak_enabled) + delete_object_part((unsigned long)phys, size, true); } -EXPORT_SYMBOL(kmemleak_not_leak_phys); +EXPORT_SYMBOL(kmemleak_free_part_phys); /** * kmemleak_ignore_phys - similar to kmemleak_ignore but taking a physical @@ -1170,8 +1216,10 @@ EXPORT_SYMBOL(kmemleak_not_leak_phys); */ void __ref kmemleak_ignore_phys(phys_addr_t phys) { - if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) - kmemleak_ignore(__va(phys)); + pr_debug("%s(0x%pa)\n", __func__, &phys); + + if (kmemleak_enabled) + make_black_object((unsigned long)phys, true); } EXPORT_SYMBOL(kmemleak_ignore_phys); @@ -1182,6 +1230,9 @@ static bool update_checksum(struct kmemleak_object *object) { u32 old_csum = object->checksum; + if (WARN_ON_ONCE(object->flags & OBJECT_PHYS)) + return false; + kasan_disable_current(); kcsan_disable_current(); object->checksum = crc32(0, kasan_reset_tag((void *)object->pointer), object->size); @@ -1335,6 +1386,7 @@ static void scan_object(struct kmemleak_object *object) { struct kmemleak_scan_area *area; unsigned long flags; + void *obj_ptr; /* * Once the object->lock is acquired, the corresponding memory block @@ -1346,10 +1398,15 @@ static void scan_object(struct kmemleak_object *object) if (!(object->flags & OBJECT_ALLOCATED)) /* already freed object */ goto out; + + obj_ptr = object->flags & OBJECT_PHYS ? + __va((phys_addr_t)object->pointer) : + (void *)object->pointer; + if (hlist_empty(&object->area_list) || object->flags & OBJECT_FULL_SCAN) { - void *start = (void *)object->pointer; - void *end = (void *)(object->pointer + object->size); + void *start = obj_ptr; + void *end = obj_ptr + object->size; void *next; do { @@ -1413,18 +1470,21 @@ static void scan_gray_list(void) */ static void kmemleak_scan(void) { - unsigned long flags; struct kmemleak_object *object; struct zone *zone; int __maybe_unused i; int new_leaks = 0; + int loop1_cnt = 0; jiffies_last_scan = jiffies; /* prepare the kmemleak_object's */ rcu_read_lock(); list_for_each_entry_rcu(object, &object_list, object_list) { - raw_spin_lock_irqsave(&object->lock, flags); + bool obj_pinned = false; + + loop1_cnt++; + raw_spin_lock_irq(&object->lock); #ifdef DEBUG /* * With a few exceptions there should be a maximum of @@ -1436,12 +1496,45 @@ static void kmemleak_scan(void) dump_object_info(object); } #endif + + /* ignore objects outside lowmem (paint them black) */ + if ((object->flags & OBJECT_PHYS) && + !(object->flags & OBJECT_NO_SCAN)) { + unsigned long phys = object->pointer; + + if (PHYS_PFN(phys) < min_low_pfn || + PHYS_PFN(phys + object->size) >= max_low_pfn) + __paint_it(object, KMEMLEAK_BLACK); + } + /* reset the reference count (whiten the object) */ object->count = 0; - if (color_gray(object) && get_object(object)) + if (color_gray(object) && get_object(object)) { list_add_tail(&object->gray_list, &gray_list); + obj_pinned = true; + } - raw_spin_unlock_irqrestore(&object->lock, flags); + raw_spin_unlock_irq(&object->lock); + + /* + * Do a cond_resched() to avoid soft lockup every 64k objects. + * Make sure a reference has been taken so that the object + * won't go away without RCU read lock. + */ + if (!(loop1_cnt & 0xffff)) { + if (!obj_pinned && !get_object(object)) { + /* Try the next object instead */ + loop1_cnt--; + continue; + } + + rcu_read_unlock(); + cond_resched(); + rcu_read_lock(); + + if (!obj_pinned) + put_object(object); + } } rcu_read_unlock(); @@ -1509,14 +1602,21 @@ static void kmemleak_scan(void) */ rcu_read_lock(); list_for_each_entry_rcu(object, &object_list, object_list) { - raw_spin_lock_irqsave(&object->lock, flags); + /* + * This is racy but we can save the overhead of lock/unlock + * calls. The missed objects, if any, should be caught in + * the next scan. + */ + if (!color_white(object)) + continue; + raw_spin_lock_irq(&object->lock); if (color_white(object) && (object->flags & OBJECT_ALLOCATED) && update_checksum(object) && get_object(object)) { /* color it gray temporarily */ object->count = object->min_count; list_add_tail(&object->gray_list, &gray_list); } - raw_spin_unlock_irqrestore(&object->lock, flags); + raw_spin_unlock_irq(&object->lock); } rcu_read_unlock(); @@ -1536,7 +1636,14 @@ static void kmemleak_scan(void) */ rcu_read_lock(); list_for_each_entry_rcu(object, &object_list, object_list) { - raw_spin_lock_irqsave(&object->lock, flags); + /* + * This is racy but we can save the overhead of lock/unlock + * calls. The missed objects, if any, should be caught in + * the next scan. + */ + if (!color_white(object)) + continue; + raw_spin_lock_irq(&object->lock); if (unreferenced_object(object) && !(object->flags & OBJECT_REPORTED)) { object->flags |= OBJECT_REPORTED; @@ -1546,7 +1653,7 @@ static void kmemleak_scan(void) new_leaks++; } - raw_spin_unlock_irqrestore(&object->lock, flags); + raw_spin_unlock_irq(&object->lock); } rcu_read_unlock(); @@ -1748,15 +1855,14 @@ static int dump_str_object_info(const char *str) static void kmemleak_clear(void) { struct kmemleak_object *object; - unsigned long flags; rcu_read_lock(); list_for_each_entry_rcu(object, &object_list, object_list) { - raw_spin_lock_irqsave(&object->lock, flags); + raw_spin_lock_irq(&object->lock); if ((object->flags & OBJECT_REPORTED) && unreferenced_object(object)) __paint_it(object, KMEMLEAK_GREY); - raw_spin_unlock_irqrestore(&object->lock, flags); + raw_spin_unlock_irq(&object->lock); } rcu_read_unlock(); @@ -475,7 +475,7 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr) cond_resched(); page = follow_page(vma, addr, FOLL_GET | FOLL_MIGRATION | FOLL_REMOTE); - if (IS_ERR_OR_NULL(page)) + if (IS_ERR_OR_NULL(page) || is_zone_device_page(page)) break; if (PageKsm(page)) ret = handle_mm_fault(vma, addr, @@ -560,7 +560,7 @@ static struct page *get_mergeable_page(struct rmap_item *rmap_item) goto out; page = follow_page(vma, addr, FOLL_GET); - if (IS_ERR_OR_NULL(page)) + if (IS_ERR_OR_NULL(page) || is_zone_device_page(page)) goto out; if (PageAnon(page)) { flush_anon_page(vma, page, addr); @@ -1083,7 +1083,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, * No need to notify as we are downgrading page table to read * only not changing it to point to a new page. * - * See Documentation/vm/mmu_notifier.rst + * See Documentation/mm/mmu_notifier.rst */ entry = ptep_clear_flush(vma, pvmw.address, pvmw.pte); /* @@ -1186,7 +1186,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, * No need to notify as we are replacing a read only page with another * read only page with the same content. * - * See Documentation/vm/mmu_notifier.rst + * See Documentation/mm/mmu_notifier.rst */ ptep_clear_flush(vma, addr, ptep); set_pte_at_notify(mm, addr, ptep, newpte); @@ -2308,7 +2308,7 @@ next_mm: if (ksm_test_exit(mm)) break; *page = follow_page(vma, ksm_scan.address, FOLL_GET); - if (IS_ERR_OR_NULL(*page)) { + if (IS_ERR_OR_NULL(*page) || is_zone_device_page(*page)) { ksm_scan.address += PAGE_SIZE; cond_resched(); continue; diff --git a/mm/list_lru.c b/mm/list_lru.c index ba76428ceece..a05e5bef3b40 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -71,7 +71,7 @@ list_lru_from_kmem(struct list_lru *lru, int nid, void *ptr, if (!list_lru_memcg_aware(lru)) goto out; - memcg = mem_cgroup_from_obj(ptr); + memcg = mem_cgroup_from_slab_obj(ptr); if (!memcg) goto out; diff --git a/mm/madvise.c b/mm/madvise.c index 0316bbc6441b..5f0f0948a50e 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -195,7 +195,6 @@ success: static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, unsigned long end, struct mm_walk *walk) { - pte_t *orig_pte; struct vm_area_struct *vma = walk->private; unsigned long index; struct swap_iocb *splug = NULL; @@ -208,12 +207,13 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, swp_entry_t entry; struct page *page; spinlock_t *ptl; + pte_t *ptep; - orig_pte = pte_offset_map_lock(vma->vm_mm, pmd, start, &ptl); - pte = *(orig_pte + ((index - start) / PAGE_SIZE)); - pte_unmap_unlock(orig_pte, ptl); + ptep = pte_offset_map_lock(vma->vm_mm, pmd, index, &ptl); + pte = *ptep; + pte_unmap_unlock(ptep, ptl); - if (pte_present(pte) || pte_none(pte)) + if (!is_swap_pte(pte)) continue; entry = pte_to_swp_entry(pte); if (unlikely(non_swap_entry(entry))) @@ -421,7 +421,7 @@ regular_page: continue; page = vm_normal_page(vma, addr, ptent); - if (!page) + if (!page || is_zone_device_page(page)) continue; /* @@ -639,7 +639,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, } page = vm_normal_page(vma, addr, ptent); - if (!page) + if (!page || is_zone_device_page(page)) continue; /* diff --git a/mm/memblock.c b/mm/memblock.c index a9f18b988b7f..c0894c137954 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -29,6 +29,10 @@ # define INIT_MEMBLOCK_RESERVED_REGIONS INIT_MEMBLOCK_REGIONS #endif +#ifndef INIT_MEMBLOCK_MEMORY_REGIONS +#define INIT_MEMBLOCK_MEMORY_REGIONS INIT_MEMBLOCK_REGIONS +#endif + /** * DOC: memblock overview * @@ -55,9 +59,9 @@ * the allocator metadata. The "memory" and "reserved" types are nicely * wrapped with struct memblock. This structure is statically * initialized at build time. The region arrays are initially sized to - * %INIT_MEMBLOCK_REGIONS for "memory" and %INIT_MEMBLOCK_RESERVED_REGIONS - * for "reserved". The region array for "physmem" is initially sized to - * %INIT_PHYSMEM_REGIONS. + * %INIT_MEMBLOCK_MEMORY_REGIONS for "memory" and + * %INIT_MEMBLOCK_RESERVED_REGIONS for "reserved". The region array + * for "physmem" is initially sized to %INIT_PHYSMEM_REGIONS. * The memblock_allow_resize() enables automatic resizing of the region * arrays during addition of new regions. This feature should be used * with care so that memory allocated for the region array will not @@ -102,7 +106,7 @@ unsigned long min_low_pfn; unsigned long max_pfn; unsigned long long max_possible_pfn; -static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock; +static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_MEMORY_REGIONS] __initdata_memblock; static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_RESERVED_REGIONS] __initdata_memblock; #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS]; @@ -111,7 +115,7 @@ static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS struct memblock memblock __initdata_memblock = { .memory.regions = memblock_memory_init_regions, .memory.cnt = 1, /* empty dummy entry */ - .memory.max = INIT_MEMBLOCK_REGIONS, + .memory.max = INIT_MEMBLOCK_MEMORY_REGIONS, .memory.name = "memory", .reserved.regions = memblock_reserved_init_regions, @@ -1348,8 +1352,8 @@ __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, * from the regions with mirroring enabled and then retried from any * memory region. * - * In addition, function sets the min_count to 0 using kmemleak_alloc_phys for - * allocated boot memory block, so that it is never reported as leaks. + * In addition, function using kmemleak_alloc_phys for allocated boot + * memory block, it is never reported as leaks. * * Return: * Physical address of allocated memory block on success, %0 on failure. @@ -1401,12 +1405,12 @@ done: */ if (end != MEMBLOCK_ALLOC_NOLEAKTRACE) /* - * The min_count is set to 0 so that memblock allocated - * blocks are never reported as leaks. This is because many - * of these blocks are only referred via the physical - * address which is not looked up by kmemleak. + * Memblock allocated blocks are never reported as + * leaks. This is because many of these blocks are + * only referred via the physical address which is + * not looked up by kmemleak. */ - kmemleak_alloc_phys(found, size, 0, 0); + kmemleak_alloc_phys(found, size, 0); return found; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 618c366a2f07..b69979c9ced5 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -626,7 +626,14 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val) x = __this_cpu_add_return(stats_updates, abs(val)); if (x > MEMCG_CHARGE_BATCH) { - atomic_add(x / MEMCG_CHARGE_BATCH, &stats_flush_threshold); + /* + * If stats_flush_threshold exceeds the threshold + * (>num_online_cpus()), cgroup stats update will be triggered + * in __mem_cgroup_flush_stats(). Increasing this var further + * is redundant and simply adds overhead in atomic update. + */ + if (atomic_read(&stats_flush_threshold) <= num_online_cpus()) + atomic_add(x / MEMCG_CHARGE_BATCH, &stats_flush_threshold); __this_cpu_write(stats_updates, 0); } } @@ -783,7 +790,7 @@ void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) struct lruvec *lruvec; rcu_read_lock(); - memcg = mem_cgroup_from_obj(p); + memcg = mem_cgroup_from_slab_obj(p); /* * Untracked pages have no memcg, no lruvec. Update only the @@ -1460,14 +1467,35 @@ static inline unsigned long memcg_page_state_output(struct mem_cgroup *memcg, return memcg_page_state(memcg, item) * memcg_page_state_unit(item); } -static char *memory_stat_format(struct mem_cgroup *memcg) +/* Subset of vm_event_item to report for memcg event stats */ +static const unsigned int memcg_vm_event_stat[] = { + PGSCAN_KSWAPD, + PGSCAN_DIRECT, + PGSTEAL_KSWAPD, + PGSTEAL_DIRECT, + PGFAULT, + PGMAJFAULT, + PGREFILL, + PGACTIVATE, + PGDEACTIVATE, + PGLAZYFREE, + PGLAZYFREED, +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) + ZSWPIN, + ZSWPOUT, +#endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + THP_FAULT_ALLOC, + THP_COLLAPSE_ALLOC, +#endif +}; + +static void memory_stat_format(struct mem_cgroup *memcg, char *buf, int bufsize) { struct seq_buf s; int i; - seq_buf_init(&s, kmalloc(PAGE_SIZE, GFP_KERNEL), PAGE_SIZE); - if (!s.buffer) - return NULL; + seq_buf_init(&s, buf, bufsize); /* * Provide statistics on the state of the memory subsystem as @@ -1495,46 +1523,20 @@ static char *memory_stat_format(struct mem_cgroup *memcg) } /* Accumulated memory events */ - - seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGFAULT), - memcg_events(memcg, PGFAULT)); - seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGMAJFAULT), - memcg_events(memcg, PGMAJFAULT)); - seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGREFILL), - memcg_events(memcg, PGREFILL)); seq_buf_printf(&s, "pgscan %lu\n", memcg_events(memcg, PGSCAN_KSWAPD) + memcg_events(memcg, PGSCAN_DIRECT)); seq_buf_printf(&s, "pgsteal %lu\n", memcg_events(memcg, PGSTEAL_KSWAPD) + memcg_events(memcg, PGSTEAL_DIRECT)); - seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGACTIVATE), - memcg_events(memcg, PGACTIVATE)); - seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGDEACTIVATE), - memcg_events(memcg, PGDEACTIVATE)); - seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGLAZYFREE), - memcg_events(memcg, PGLAZYFREE)); - seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGLAZYFREED), - memcg_events(memcg, PGLAZYFREED)); - -#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) - seq_buf_printf(&s, "%s %lu\n", vm_event_name(ZSWPIN), - memcg_events(memcg, ZSWPIN)); - seq_buf_printf(&s, "%s %lu\n", vm_event_name(ZSWPOUT), - memcg_events(memcg, ZSWPOUT)); -#endif -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - seq_buf_printf(&s, "%s %lu\n", vm_event_name(THP_FAULT_ALLOC), - memcg_events(memcg, THP_FAULT_ALLOC)); - seq_buf_printf(&s, "%s %lu\n", vm_event_name(THP_COLLAPSE_ALLOC), - memcg_events(memcg, THP_COLLAPSE_ALLOC)); -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + for (i = 0; i < ARRAY_SIZE(memcg_vm_event_stat); i++) + seq_buf_printf(&s, "%s %lu\n", + vm_event_name(memcg_vm_event_stat[i]), + memcg_events(memcg, memcg_vm_event_stat[i])); /* The above should easily fit into one page */ WARN_ON_ONCE(seq_buf_has_overflowed(&s)); - - return s.buffer; } #define K(x) ((x) << (PAGE_SHIFT-10)) @@ -1570,7 +1572,10 @@ void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct * */ void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) { - char *buf; + /* Use static buffer, for the caller is holding oom_lock. */ + static char buf[PAGE_SIZE]; + + lockdep_assert_held(&oom_lock); pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n", K((u64)page_counter_read(&memcg->memory)), @@ -1591,11 +1596,8 @@ void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) pr_info("Memory cgroup stats for "); pr_cont_cgroup_path(memcg->css.cgroup); pr_cont(":"); - buf = memory_stat_format(memcg); - if (!buf) - return; + memory_stat_format(memcg, buf, sizeof(buf)); pr_info("%s", buf); - kfree(buf); } /* @@ -2331,7 +2333,8 @@ static unsigned long reclaim_high(struct mem_cgroup *memcg, psi_memstall_enter(&pflags); nr_reclaimed += try_to_free_mem_cgroup_pages(memcg, nr_pages, - gfp_mask, true); + gfp_mask, + MEMCG_RECLAIM_MAY_SWAP); psi_memstall_leave(&pflags); } while ((memcg = parent_mem_cgroup(memcg)) && !mem_cgroup_is_root(memcg)); @@ -2576,8 +2579,9 @@ static int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask, struct page_counter *counter; unsigned long nr_reclaimed; bool passed_oom = false; - bool may_swap = true; + unsigned int reclaim_options = MEMCG_RECLAIM_MAY_SWAP; bool drained = false; + bool raised_max_event = false; unsigned long pflags; retry: @@ -2593,7 +2597,7 @@ retry: mem_over_limit = mem_cgroup_from_counter(counter, memory); } else { mem_over_limit = mem_cgroup_from_counter(counter, memsw); - may_swap = false; + reclaim_options &= ~MEMCG_RECLAIM_MAY_SWAP; } if (batch > nr_pages) { @@ -2617,10 +2621,11 @@ retry: goto nomem; memcg_memory_event(mem_over_limit, MEMCG_MAX); + raised_max_event = true; psi_memstall_enter(&pflags); nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages, - gfp_mask, may_swap); + gfp_mask, reclaim_options); psi_memstall_leave(&pflags); if (mem_cgroup_margin(mem_over_limit) >= nr_pages) @@ -2684,6 +2689,13 @@ nomem: return -ENOMEM; force: /* + * If the allocation has to be enforced, don't forget to raise + * a MEMCG_MAX event. + */ + if (!raised_max_event) + memcg_memory_event(mem_over_limit, MEMCG_MAX); + + /* * The allocation either can't fail or will lead to more memory * being freed very soon. Allow memory usage go over the limit * temporarily by force charging it. @@ -2842,27 +2854,9 @@ int memcg_alloc_slab_cgroups(struct slab *slab, struct kmem_cache *s, return 0; } -/* - * Returns a pointer to the memory cgroup to which the kernel object is charged. - * - * A passed kernel object can be a slab object or a generic kernel page, so - * different mechanisms for getting the memory cgroup pointer should be used. - * In certain cases (e.g. kernel stacks or large kmallocs with SLUB) the caller - * can not know for sure how the kernel object is implemented. - * mem_cgroup_from_obj() can be safely used in such cases. - * - * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(), - * cgroup_mutex, etc. - */ -struct mem_cgroup *mem_cgroup_from_obj(void *p) +static __always_inline +struct mem_cgroup *mem_cgroup_from_obj_folio(struct folio *folio, void *p) { - struct folio *folio; - - if (mem_cgroup_disabled()) - return NULL; - - folio = virt_to_folio(p); - /* * Slab objects are accounted individually, not per-page. * Memcg membership data for each individual object is saved in @@ -2895,6 +2889,53 @@ struct mem_cgroup *mem_cgroup_from_obj(void *p) return page_memcg_check(folio_page(folio, 0)); } +/* + * Returns a pointer to the memory cgroup to which the kernel object is charged. + * + * A passed kernel object can be a slab object, vmalloc object or a generic + * kernel page, so different mechanisms for getting the memory cgroup pointer + * should be used. + * + * In certain cases (e.g. kernel stacks or large kmallocs with SLUB) the caller + * can not know for sure how the kernel object is implemented. + * mem_cgroup_from_obj() can be safely used in such cases. + * + * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(), + * cgroup_mutex, etc. + */ +struct mem_cgroup *mem_cgroup_from_obj(void *p) +{ + struct folio *folio; + + if (mem_cgroup_disabled()) + return NULL; + + if (unlikely(is_vmalloc_addr(p))) + folio = page_folio(vmalloc_to_page(p)); + else + folio = virt_to_folio(p); + + return mem_cgroup_from_obj_folio(folio, p); +} + +/* + * Returns a pointer to the memory cgroup to which the kernel object is charged. + * Similar to mem_cgroup_from_obj(), but faster and not suitable for objects, + * allocated using vmalloc(). + * + * A passed kernel object must be a slab object or a generic kernel page. + * + * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(), + * cgroup_mutex, etc. + */ +struct mem_cgroup *mem_cgroup_from_slab_obj(void *p) +{ + if (mem_cgroup_disabled()) + return NULL; + + return mem_cgroup_from_obj_folio(virt_to_folio(p), p); +} + static struct obj_cgroup *__get_obj_cgroup_from_memcg(struct mem_cgroup *memcg) { struct obj_cgroup *objcg = NULL; @@ -3402,8 +3443,8 @@ static int mem_cgroup_resize_max(struct mem_cgroup *memcg, continue; } - if (!try_to_free_mem_cgroup_pages(memcg, 1, - GFP_KERNEL, !memsw)) { + if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, + memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP)) { ret = -EBUSY; break; } @@ -3513,7 +3554,8 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg) if (signal_pending(current)) return -EINTR; - if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, true)) + if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, + MEMCG_RECLAIM_MAY_SWAP)) nr_retries--; } @@ -3625,7 +3667,7 @@ static int memcg_online_kmem(struct mem_cgroup *memcg) { struct obj_cgroup *objcg; - if (cgroup_memory_nokmem) + if (mem_cgroup_kmem_disabled()) return 0; if (unlikely(mem_cgroup_is_root(memcg))) @@ -3649,7 +3691,7 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg) { struct mem_cgroup *parent; - if (cgroup_memory_nokmem) + if (mem_cgroup_kmem_disabled()) return; if (unlikely(mem_cgroup_is_root(memcg))) @@ -5060,6 +5102,29 @@ struct mem_cgroup *mem_cgroup_from_id(unsigned short id) return idr_find(&mem_cgroup_idr, id); } +#ifdef CONFIG_SHRINKER_DEBUG +struct mem_cgroup *mem_cgroup_get_from_ino(unsigned long ino) +{ + struct cgroup *cgrp; + struct cgroup_subsys_state *css; + struct mem_cgroup *memcg; + + cgrp = cgroup_get_from_id(ino); + if (!cgrp) + return ERR_PTR(-ENOENT); + + css = cgroup_get_e_css(cgrp, &memory_cgrp_subsys); + if (css) + memcg = container_of(css, struct mem_cgroup, css); + else + memcg = ERR_PTR(-ENOENT); + + cgroup_put(cgrp); + + return memcg; +} +#endif + static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) { struct mem_cgroup_per_node *pn; @@ -5665,8 +5730,8 @@ out: * 2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a * target for charge migration. if @target is not NULL, the entry is stored * in target->ent. - * 3(MC_TARGET_DEVICE): like MC_TARGET_PAGE but page is MEMORY_DEVICE_PRIVATE - * (so ZONE_DEVICE page and thus not on the lru). + * 3(MC_TARGET_DEVICE): like MC_TARGET_PAGE but page is device memory and + * thus not on the lru. * For now we such page is charge like a regular page would be as for all * intent and purposes it is just special memory taking the place of a * regular page. @@ -5704,7 +5769,8 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, */ if (page_memcg(page) == mc.from) { ret = MC_TARGET_PAGE; - if (is_device_private_page(page)) + if (is_device_private_page(page) || + is_device_coherent_page(page)) ret = MC_TARGET_DEVICE; if (target) target->page = page; @@ -6241,7 +6307,7 @@ static ssize_t memory_high_write(struct kernfs_open_file *of, } reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_pages - high, - GFP_KERNEL, true); + GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP); if (!reclaimed && !nr_retries--) break; @@ -6290,7 +6356,7 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, if (nr_reclaims) { if (!try_to_free_mem_cgroup_pages(memcg, nr_pages - max, - GFP_KERNEL, true)) + GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP)) nr_reclaims--; continue; } @@ -6335,11 +6401,11 @@ static int memory_events_local_show(struct seq_file *m, void *v) static int memory_stat_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_seq(m); - char *buf; + char *buf = kmalloc(PAGE_SIZE, GFP_KERNEL); - buf = memory_stat_format(memcg); if (!buf) return -ENOMEM; + memory_stat_format(memcg, buf, PAGE_SIZE); seq_puts(m, buf); kfree(buf); return 0; @@ -6419,6 +6485,7 @@ static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf, struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); unsigned int nr_retries = MAX_RECLAIM_RETRIES; unsigned long nr_to_reclaim, nr_reclaimed = 0; + unsigned int reclaim_options; int err; buf = strstrip(buf); @@ -6426,6 +6493,7 @@ static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf, if (err) return err; + reclaim_options = MEMCG_RECLAIM_MAY_SWAP | MEMCG_RECLAIM_PROACTIVE; while (nr_reclaimed < nr_to_reclaim) { unsigned long reclaimed; @@ -6442,7 +6510,7 @@ static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf, reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_to_reclaim - nr_reclaimed, - GFP_KERNEL, true); + GFP_KERNEL, reclaim_options); if (!reclaimed && !nr_retries--) return -EAGAIN; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index b864c2eff641..9a7a228ad04a 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -33,6 +33,9 @@ * are rare we hope to get away with this. This avoids impacting the core * VM. */ + +#define pr_fmt(fmt) "Memory failure: " fmt + #include <linux/kernel.h> #include <linux/mm.h> #include <linux/page-flags.h> @@ -252,7 +255,7 @@ static int kill_proc(struct to_kill *tk, unsigned long pfn, int flags) short addr_lsb = tk->size_shift; int ret = 0; - pr_err("Memory failure: %#lx: Sending SIGBUS to %s:%d due to hardware memory corruption\n", + pr_err("%#lx: Sending SIGBUS to %s:%d due to hardware memory corruption\n", pfn, t->comm, t->pid); if ((flags & MF_ACTION_REQUIRED) && (t == current)) @@ -270,7 +273,7 @@ static int kill_proc(struct to_kill *tk, unsigned long pfn, int flags) ret = send_sig_mceerr(BUS_MCEERR_AO, (void __user *)tk->addr, addr_lsb, t); /* synchronous? */ if (ret < 0) - pr_info("Memory failure: Error sending signal to %s:%d: %d\n", + pr_info("Error sending signal to %s:%d: %d\n", t->comm, t->pid, ret); return ret; } @@ -297,10 +300,9 @@ void shake_page(struct page *p) } EXPORT_SYMBOL_GPL(shake_page); -static unsigned long dev_pagemap_mapping_shift(struct page *page, - struct vm_area_struct *vma) +static unsigned long dev_pagemap_mapping_shift(struct vm_area_struct *vma, + unsigned long address) { - unsigned long address = vma_address(page, vma); unsigned long ret = 0; pgd_t *pgd; p4d_t *p4d; @@ -340,23 +342,33 @@ static unsigned long dev_pagemap_mapping_shift(struct page *page, /* * Schedule a process for later kill. * Uses GFP_ATOMIC allocations to avoid potential recursions in the VM. + * + * Notice: @fsdax_pgoff is used only when @p is a fsdax page. + * In other cases, such as anonymous and file-backend page, the address to be + * killed can be caculated by @p itself. */ static void add_to_kill(struct task_struct *tsk, struct page *p, - struct vm_area_struct *vma, - struct list_head *to_kill) + pgoff_t fsdax_pgoff, struct vm_area_struct *vma, + struct list_head *to_kill) { struct to_kill *tk; tk = kmalloc(sizeof(struct to_kill), GFP_ATOMIC); if (!tk) { - pr_err("Memory failure: Out of memory while machine check handling\n"); + pr_err("Out of memory while machine check handling\n"); return; } tk->addr = page_address_in_vma(p, vma); - if (is_zone_device_page(p)) - tk->size_shift = dev_pagemap_mapping_shift(p, vma); - else + if (is_zone_device_page(p)) { + /* + * Since page->mapping is not used for fsdax, we need + * calculate the address based on the vma. + */ + if (p->pgmap->type == MEMORY_DEVICE_FS_DAX) + tk->addr = vma_pgoff_address(fsdax_pgoff, 1, vma); + tk->size_shift = dev_pagemap_mapping_shift(vma, tk->addr); + } else tk->size_shift = page_shift(compound_head(p)); /* @@ -370,7 +382,7 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, * has a mapping for the page. */ if (tk->addr == -EFAULT) { - pr_info("Memory failure: Unable to find user space address %lx in %s\n", + pr_info("Unable to find user space address %lx in %s\n", page_to_pfn(p), tsk->comm); } else if (tk->size_shift == 0) { kfree(tk); @@ -403,7 +415,7 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail, * signal and then access the memory. Just kill it. */ if (fail || tk->addr == -EFAULT) { - pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n", + pr_err("%#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n", pfn, tk->tsk->comm, tk->tsk->pid); do_send_sig_info(SIGKILL, SEND_SIG_PRIV, tk->tsk, PIDTYPE_PID); @@ -416,7 +428,7 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail, * process anyways. */ else if (kill_proc(tk, pfn, flags) < 0) - pr_err("Memory failure: %#lx: Cannot send advisory machine check signal to %s:%d\n", + pr_err("%#lx: Cannot send advisory machine check signal to %s:%d\n", pfn, tk->tsk->comm, tk->tsk->pid); } put_task_struct(tk->tsk); @@ -505,7 +517,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, if (!page_mapped_in_vma(page, vma)) continue; if (vma->vm_mm == t->mm) - add_to_kill(t, page, vma, to_kill); + add_to_kill(t, page, 0, vma, to_kill); } } read_unlock(&tasklist_lock); @@ -541,12 +553,40 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, * to be informed of all such data corruptions. */ if (vma->vm_mm == t->mm) - add_to_kill(t, page, vma, to_kill); + add_to_kill(t, page, 0, vma, to_kill); + } + } + read_unlock(&tasklist_lock); + i_mmap_unlock_read(mapping); +} + +#ifdef CONFIG_FS_DAX +/* + * Collect processes when the error hit a fsdax page. + */ +static void collect_procs_fsdax(struct page *page, + struct address_space *mapping, pgoff_t pgoff, + struct list_head *to_kill) +{ + struct vm_area_struct *vma; + struct task_struct *tsk; + + i_mmap_lock_read(mapping); + read_lock(&tasklist_lock); + for_each_process(tsk) { + struct task_struct *t = task_early_kill(tsk, true); + + if (!t) + continue; + vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { + if (vma->vm_mm == t->mm) + add_to_kill(t, page, pgoff, vma, to_kill); } } read_unlock(&tasklist_lock); i_mmap_unlock_read(mapping); } +#endif /* CONFIG_FS_DAX */ /* * Collect the processes who have the corrupted page mapped to kill. @@ -779,12 +819,10 @@ static int truncate_error_page(struct page *p, unsigned long pfn, int err = mapping->a_ops->error_remove_page(mapping, p); if (err != 0) { - pr_info("Memory failure: %#lx: Failed to punch page: %d\n", - pfn, err); + pr_info("%#lx: Failed to punch page: %d\n", pfn, err); } else if (page_has_private(p) && !try_to_release_page(p, GFP_NOIO)) { - pr_info("Memory failure: %#lx: failed to release buffers\n", - pfn); + pr_info("%#lx: failed to release buffers\n", pfn); } else { ret = MF_RECOVERED; } @@ -796,8 +834,7 @@ static int truncate_error_page(struct page *p, unsigned long pfn, if (invalidate_inode_page(p)) ret = MF_RECOVERED; else - pr_info("Memory failure: %#lx: Failed to invalidate\n", - pfn); + pr_info("%#lx: Failed to invalidate\n", pfn); } return ret; @@ -827,7 +864,7 @@ static bool has_extra_refcount(struct page_state *ps, struct page *p, count -= 1; if (count > 0) { - pr_err("Memory failure: %#lx: %s still referenced by %d users\n", + pr_err("%#lx: %s still referenced by %d users\n", page_to_pfn(p), action_page_types[ps->type], count); return true; } @@ -851,7 +888,7 @@ static int me_kernel(struct page_state *ps, struct page *p) */ static int me_unknown(struct page_state *ps, struct page *p) { - pr_err("Memory failure: %#lx: Unknown page state\n", page_to_pfn(p)); + pr_err("%#lx: Unknown page state\n", page_to_pfn(p)); unlock_page(p); return MF_FAILED; } @@ -1007,12 +1044,13 @@ static int me_swapcache_dirty(struct page_state *ps, struct page *p) static int me_swapcache_clean(struct page_state *ps, struct page *p) { + struct folio *folio = page_folio(p); int ret; - delete_from_swap_cache(p); + delete_from_swap_cache(folio); ret = delete_from_lru_cache(p) ? MF_FAILED : MF_RECOVERED; - unlock_page(p); + folio_unlock(folio); if (has_extra_refcount(ps, p, false)) ret = MF_FAILED; @@ -1135,7 +1173,7 @@ static void action_result(unsigned long pfn, enum mf_action_page_type type, trace_memory_failure_event(pfn, type, result); num_poisoned_pages_inc(); - pr_err("Memory failure: %#lx: recovery action for %s: %s\n", + pr_err("%#lx: recovery action for %s: %s\n", pfn, action_page_types[type], action_name[result]); } @@ -1210,8 +1248,7 @@ static int __get_hwpoison_page(struct page *page, unsigned long flags) if (head == compound_head(page)) return 1; - pr_info("Memory failure: %#lx cannot catch tail\n", - page_to_pfn(page)); + pr_info("%#lx cannot catch tail\n", page_to_pfn(page)); put_page(head); } @@ -1274,7 +1311,7 @@ try_again: } out: if (ret == -EIO) - pr_err("Memory failure: %#lx: unhandlable page.\n", page_to_pfn(p)); + pr_err("%#lx: unhandlable page.\n", page_to_pfn(p)); return ret; } @@ -1373,13 +1410,12 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, return true; if (PageKsm(p)) { - pr_err("Memory failure: %#lx: can't handle KSM pages.\n", pfn); + pr_err("%#lx: can't handle KSM pages.\n", pfn); return false; } if (PageSwapCache(p)) { - pr_err("Memory failure: %#lx: keeping poisoned page in swap cache\n", - pfn); + pr_err("%#lx: keeping poisoned page in swap cache\n", pfn); ttu |= TTU_IGNORE_HWPOISON; } @@ -1397,7 +1433,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, } else { kill = 0; ttu |= TTU_IGNORE_HWPOISON; - pr_info("Memory failure: %#lx: corrupted page was clean: dropped without side effects\n", + pr_info("%#lx: corrupted page was clean: dropped without side effects\n", pfn); } } @@ -1426,14 +1462,14 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, try_to_unmap(folio, ttu|TTU_RMAP_LOCKED); i_mmap_unlock_write(mapping); } else - pr_info("Memory failure: %#lx: could not lock mapping for mapped huge page\n", pfn); + pr_info("%#lx: could not lock mapping for mapped huge page\n", pfn); } else { try_to_unmap(folio, ttu); } unmap_success = !page_mapped(hpage); if (!unmap_success) - pr_err("Memory failure: %#lx: failed to unmap page (mapcount=%d)\n", + pr_err("%#lx: failed to unmap page (mapcount=%d)\n", pfn, page_mapcount(hpage)); /* @@ -1498,6 +1534,134 @@ static int try_to_split_thp_page(struct page *page, const char *msg) return 0; } +static void unmap_and_kill(struct list_head *to_kill, unsigned long pfn, + struct address_space *mapping, pgoff_t index, int flags) +{ + struct to_kill *tk; + unsigned long size = 0; + + list_for_each_entry(tk, to_kill, nd) + if (tk->size_shift) + size = max(size, 1UL << tk->size_shift); + + if (size) { + /* + * Unmap the largest mapping to avoid breaking up device-dax + * mappings which are constant size. The actual size of the + * mapping being torn down is communicated in siginfo, see + * kill_proc() + */ + loff_t start = (index << PAGE_SHIFT) & ~(size - 1); + + unmap_mapping_range(mapping, start, size, 0); + } + + kill_procs(to_kill, flags & MF_MUST_KILL, false, pfn, flags); +} + +static int mf_generic_kill_procs(unsigned long long pfn, int flags, + struct dev_pagemap *pgmap) +{ + struct page *page = pfn_to_page(pfn); + LIST_HEAD(to_kill); + dax_entry_t cookie; + int rc = 0; + + /* + * Pages instantiated by device-dax (not filesystem-dax) + * may be compound pages. + */ + page = compound_head(page); + + /* + * Prevent the inode from being freed while we are interrogating + * the address_space, typically this would be handled by + * lock_page(), but dax pages do not use the page lock. This + * also prevents changes to the mapping of this pfn until + * poison signaling is complete. + */ + cookie = dax_lock_page(page); + if (!cookie) + return -EBUSY; + + if (hwpoison_filter(page)) { + rc = -EOPNOTSUPP; + goto unlock; + } + + switch (pgmap->type) { + case MEMORY_DEVICE_PRIVATE: + case MEMORY_DEVICE_COHERENT: + /* + * TODO: Handle device pages which may need coordination + * with device-side memory. + */ + rc = -ENXIO; + goto unlock; + default: + break; + } + + /* + * Use this flag as an indication that the dax page has been + * remapped UC to prevent speculative consumption of poison. + */ + SetPageHWPoison(page); + + /* + * Unlike System-RAM there is no possibility to swap in a + * different physical page at a given virtual address, so all + * userspace consumption of ZONE_DEVICE memory necessitates + * SIGBUS (i.e. MF_MUST_KILL) + */ + flags |= MF_ACTION_REQUIRED | MF_MUST_KILL; + collect_procs(page, &to_kill, true); + + unmap_and_kill(&to_kill, pfn, page->mapping, page->index, flags); +unlock: + dax_unlock_page(page, cookie); + return rc; +} + +#ifdef CONFIG_FS_DAX +/** + * mf_dax_kill_procs - Collect and kill processes who are using this file range + * @mapping: address_space of the file in use + * @index: start pgoff of the range within the file + * @count: length of the range, in unit of PAGE_SIZE + * @mf_flags: memory failure flags + */ +int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index, + unsigned long count, int mf_flags) +{ + LIST_HEAD(to_kill); + dax_entry_t cookie; + struct page *page; + size_t end = index + count; + + mf_flags |= MF_ACTION_REQUIRED | MF_MUST_KILL; + + for (; index < end; index++) { + page = NULL; + cookie = dax_lock_mapping_entry(mapping, index, &page); + if (!cookie) + return -EBUSY; + if (!page) + goto unlock; + + SetPageHWPoison(page); + + collect_procs_fsdax(page, mapping, index, &to_kill); + unmap_and_kill(&to_kill, page_to_pfn(page), mapping, + index, mf_flags); +unlock: + dax_unlock_mapping_entry(mapping, index, cookie); + } + return 0; +} +EXPORT_SYMBOL_GPL(mf_dax_kill_procs); +#endif /* CONFIG_FS_DAX */ + /* * Called from hugetlb code with hugetlb_lock held. * @@ -1566,7 +1730,7 @@ retry: *hugetlb = 0; return 0; } else if (res == -EHWPOISON) { - pr_err("Memory failure: %#lx: already hardware poisoned\n", pfn); + pr_err("%#lx: already hardware poisoned\n", pfn); if (flags & MF_ACTION_REQUIRED) { head = compound_head(p); res = kill_accessing_process(current, page_to_pfn(head), flags); @@ -1633,23 +1797,20 @@ out: unlock_page(head); return res; } + #else static inline int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb) { return 0; } -#endif + +#endif /* CONFIG_HUGETLB_PAGE */ static int memory_failure_dev_pagemap(unsigned long pfn, int flags, struct dev_pagemap *pgmap) { struct page *page = pfn_to_page(pfn); - unsigned long size = 0; - struct to_kill *tk; - LIST_HEAD(tokill); - int rc = -EBUSY; - loff_t start; - dax_entry_t cookie; + int rc = -ENXIO; if (flags & MF_COUNT_INCREASED) /* @@ -1658,73 +1819,24 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags, put_page(page); /* device metadata space is not recoverable */ - if (!pgmap_pfn_valid(pgmap, pfn)) { - rc = -ENXIO; + if (!pgmap_pfn_valid(pgmap, pfn)) goto out; - } /* - * Pages instantiated by device-dax (not filesystem-dax) - * may be compound pages. + * Call driver's implementation to handle the memory failure, otherwise + * fall back to generic handler. */ - page = compound_head(page); - - /* - * Prevent the inode from being freed while we are interrogating - * the address_space, typically this would be handled by - * lock_page(), but dax pages do not use the page lock. This - * also prevents changes to the mapping of this pfn until - * poison signaling is complete. - */ - cookie = dax_lock_page(page); - if (!cookie) - goto out; - - if (hwpoison_filter(page)) { - rc = -EOPNOTSUPP; - goto unlock; - } - - if (pgmap->type == MEMORY_DEVICE_PRIVATE) { + if (pgmap->ops->memory_failure) { + rc = pgmap->ops->memory_failure(pgmap, pfn, 1, flags); /* - * TODO: Handle HMM pages which may need coordination - * with device-side memory. + * Fall back to generic handler too if operation is not + * supported inside the driver/device/filesystem. */ - goto unlock; + if (rc != -EOPNOTSUPP) + goto out; } - /* - * Use this flag as an indication that the dax page has been - * remapped UC to prevent speculative consumption of poison. - */ - SetPageHWPoison(page); - - /* - * Unlike System-RAM there is no possibility to swap in a - * different physical page at a given virtual address, so all - * userspace consumption of ZONE_DEVICE memory necessitates - * SIGBUS (i.e. MF_MUST_KILL) - */ - flags |= MF_ACTION_REQUIRED | MF_MUST_KILL; - collect_procs(page, &tokill, true); - - list_for_each_entry(tk, &tokill, nd) - if (tk->size_shift) - size = max(size, 1UL << tk->size_shift); - if (size) { - /* - * Unmap the largest mapping to avoid breaking up - * device-dax mappings which are constant size. The - * actual size of the mapping being torn down is - * communicated in siginfo, see kill_proc() - */ - start = (page->index << PAGE_SHIFT) & ~(size - 1); - unmap_mapping_range(page->mapping, start, size, 0); - } - kill_procs(&tokill, true, false, pfn, flags); - rc = 0; -unlock: - dax_unlock_page(page, cookie); + rc = mf_generic_kill_procs(pfn, flags, pgmap); out: /* drop pgmap ref acquired in caller */ put_dev_pagemap(pgmap); @@ -1787,8 +1899,7 @@ int memory_failure(unsigned long pfn, int flags) goto unlock_mutex; } } - pr_err("Memory failure: %#lx: memory outside kernel control\n", - pfn); + pr_err("%#lx: memory outside kernel control\n", pfn); res = -ENXIO; goto unlock_mutex; } @@ -1799,8 +1910,7 @@ try_again: goto unlock_mutex; if (TestSetPageHWPoison(p)) { - pr_err("Memory failure: %#lx: already hardware poisoned\n", - pfn); + pr_err("%#lx: already hardware poisoned\n", pfn); res = -EHWPOISON; if (flags & MF_ACTION_REQUIRED) res = kill_accessing_process(current, pfn, flags); @@ -2016,7 +2126,7 @@ void memory_failure_queue(unsigned long pfn, int flags) if (kfifo_put(&mf_cpu->fifo, entry)) schedule_work_on(smp_processor_id(), &mf_cpu->work); else - pr_err("Memory failure: buffer overflow when queuing memory failure at %#lx\n", + pr_err("buffer overflow when queuing memory failure at %#lx\n", pfn); spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); put_cpu_var(memory_failure_cpu); @@ -2073,6 +2183,8 @@ static int __init memory_failure_init(void) } core_initcall(memory_failure_init); +#undef pr_fmt +#define pr_fmt(fmt) "" fmt #define unpoison_pr_info(fmt, pfn, rs) \ ({ \ if (__ratelimit(rs)) \ @@ -2178,7 +2290,7 @@ static bool isolate_page(struct page *page, struct list_head *pagelist) bool lru = PageLRU(page); if (PageHuge(page)) { - isolated = isolate_huge_page(page, pagelist); + isolated = !isolate_hugetlb(page, pagelist); } else { if (lru) isolated = !isolate_lru_page(page); diff --git a/mm/memory.c b/mm/memory.c index 1c6027adc542..4ba73f5aa8bb 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -624,6 +624,14 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, if (is_zero_pfn(pfn)) return NULL; if (pte_devmap(pte)) + /* + * NOTE: New users of ZONE_DEVICE will not set pte_devmap() + * and will have refcounts incremented on their struct pages + * when they are inserted into PTEs, thus they are safe to + * return here. Legacy ZONE_DEVICE pages that set pte_devmap() + * do not have refcounts. Example of legacy ZONE_DEVICE is + * MEMORY_DEVICE_FS_DAX type in pmem or virtio_fs drivers. + */ return NULL; print_bad_pte(vma, addr, pte, NULL); @@ -736,7 +744,7 @@ static void restore_exclusive_pte(struct vm_area_struct *vma, * Currently device exclusive access only supports anonymous * memory so the entry shouldn't point to a filebacked page. */ - WARN_ON_ONCE(!PageAnon(page)); + WARN_ON_ONCE(1); set_pte_at(vma->vm_mm, address, ptep, pte); @@ -1245,7 +1253,7 @@ vma_needs_copy(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) if (userfaultfd_wp(dst_vma)) return true; - if (src_vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) + if (src_vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) return true; if (src_vma->anon_vma) @@ -3020,7 +3028,7 @@ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) balance_dirty_pages_ratelimited(mapping); if (fpin) { fput(fpin); - return VM_FAULT_RETRY; + return VM_FAULT_COMPLETED; } } @@ -4434,10 +4442,6 @@ late_initcall(fault_around_debugfs); * It uses vm_ops->map_pages() to map the pages, which skips the page if it's * not ready to be mapped: not up-to-date, locked, etc. * - * This function is called with the page table lock taken. In the split ptlock - * case the page table lock only protects only those entries which belong to - * the page table corresponding to the fault address. - * * This function doesn't cross the VMA boundaries, in order to call map_pages() * only once. * @@ -4696,7 +4700,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) pte = pte_modify(old_pte, vma->vm_page_prot); page = vm_normal_page(vma, vmf->address, pte); - if (!page) + if (!page || is_zone_device_page(page)) goto out_map; /* TODO: handle PTE-mapped THP */ @@ -4966,6 +4970,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, .gfp_mask = __get_fault_gfp_mask(vma), }; struct mm_struct *mm = vma->vm_mm; + unsigned long vm_flags = vma->vm_flags; pgd_t *pgd; p4d_t *p4d; vm_fault_t ret; @@ -4979,7 +4984,8 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, if (!vmf.pud) return VM_FAULT_OOM; retry_pud: - if (pud_none(*vmf.pud) && __transparent_hugepage_enabled(vma)) { + if (pud_none(*vmf.pud) && + hugepage_vma_check(vma, vm_flags, false, true)) { ret = create_huge_pud(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; @@ -5012,7 +5018,8 @@ retry_pud: if (pud_trans_unstable(vmf.pud)) goto retry_pud; - if (pmd_none(*vmf.pmd) && __transparent_hugepage_enabled(vma)) { + if (pmd_none(*vmf.pmd) && + hugepage_vma_check(vma, vm_flags, false, true)) { ret = create_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 1213d0c67a53..fad6d1f2262a 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -43,30 +43,22 @@ #include "shuffle.h" #ifdef CONFIG_MHP_MEMMAP_ON_MEMORY -static int memmap_on_memory_set(const char *val, const struct kernel_param *kp) -{ - if (hugetlb_optimize_vmemmap_enabled()) - return 0; - return param_set_bool(val, kp); -} - -static const struct kernel_param_ops memmap_on_memory_ops = { - .flags = KERNEL_PARAM_OPS_FL_NOARG, - .set = memmap_on_memory_set, - .get = param_get_bool, -}; - /* * memory_hotplug.memmap_on_memory parameter */ static bool memmap_on_memory __ro_after_init; -module_param_cb(memmap_on_memory, &memmap_on_memory_ops, &memmap_on_memory, 0444); +module_param(memmap_on_memory, bool, 0444); MODULE_PARM_DESC(memmap_on_memory, "Enable memmap on memory for memory hotplug"); -bool mhp_memmap_on_memory(void) +static inline bool mhp_memmap_on_memory(void) { return memmap_on_memory; } +#else +static inline bool mhp_memmap_on_memory(void) +{ + return false; +} #endif enum { @@ -237,8 +229,7 @@ static void release_memory_resource(struct resource *res) kfree(res); } -static int check_pfn_span(unsigned long pfn, unsigned long nr_pages, - const char *reason) +static int check_pfn_span(unsigned long pfn, unsigned long nr_pages) { /* * Disallow all operations smaller than a sub-section and only @@ -255,12 +246,8 @@ static int check_pfn_span(unsigned long pfn, unsigned long nr_pages, min_align = PAGES_PER_SUBSECTION; else min_align = PAGES_PER_SECTION; - if (!IS_ALIGNED(pfn, min_align) - || !IS_ALIGNED(nr_pages, min_align)) { - WARN(1, "Misaligned __%s_pages start: %#lx end: #%lx\n", - reason, pfn, pfn + nr_pages - 1); + if (!IS_ALIGNED(pfn | nr_pages, min_align)) return -EINVAL; - } return 0; } @@ -337,9 +324,10 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages, altmap->alloc = 0; } - err = check_pfn_span(pfn, nr_pages, "add"); - if (err) - return err; + if (check_pfn_span(pfn, nr_pages)) { + WARN(1, "Misaligned %s start: %#lx end: #%lx\n", __func__, pfn, pfn + nr_pages - 1); + return -EINVAL; + } for (; pfn < end_pfn; pfn += cur_nr_pages) { /* Select all remaining pages up to the next section boundary */ @@ -536,8 +524,10 @@ void __remove_pages(unsigned long pfn, unsigned long nr_pages, map_offset = vmem_altmap_offset(altmap); - if (check_pfn_span(pfn, nr_pages, "remove")) + if (check_pfn_span(pfn, nr_pages)) { + WARN(1, "Misaligned %s start: %#lx end: #%lx\n", __func__, pfn, pfn + nr_pages - 1); return; + } for (; pfn < end_pfn; pfn += cur_nr_pages) { cond_resched(); @@ -672,12 +662,18 @@ static void __meminit resize_pgdat_range(struct pglist_data *pgdat, unsigned lon } +#ifdef CONFIG_ZONE_DEVICE static void section_taint_zone_device(unsigned long pfn) { struct mem_section *ms = __pfn_to_section(pfn); ms->section_mem_map |= SECTION_TAINT_ZONE_DEVICE; } +#else +static inline void section_taint_zone_device(unsigned long pfn) +{ +} +#endif /* * Associate the pfn range with the given zone, initializing the memmaps @@ -936,7 +932,7 @@ static struct zone *auto_movable_zone_for_pfn(int nid, if (!page) continue; /* If anything is !MOVABLE online the rest !MOVABLE. */ - if (page_zonenum(page) != ZONE_MOVABLE) + if (!is_zone_movable_page(page)) goto kernel_zone; online_pages += PAGES_PER_SECTION; } @@ -1031,7 +1027,7 @@ int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, struct zone *zone) { unsigned long end_pfn = pfn + nr_pages; - int ret; + int ret, i; ret = kasan_add_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages)); if (ret) @@ -1039,6 +1035,9 @@ int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_UNMOVABLE); + for (i = 0; i < nr_pages; i++) + SetPageVmemmapSelfHosted(pfn_to_page(pfn + i)); + /* * It might be that the vmemmap_pages fully span sections. If that is * the case, mark those sections online here as otherwise they will be @@ -1643,7 +1642,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) if (PageHuge(page)) { pfn = page_to_pfn(head) + compound_nr(head) - 1; - isolate_huge_page(head, &source); + isolate_hugetlb(head, &source); continue; } else if (PageTransHuge(page)) pfn = page_to_pfn(head) + thp_nr_pages(page) - 1; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index d39b01fd52fe..b73d3248d976 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -465,9 +465,8 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, } page = pmd_page(*pmd); if (is_huge_zero_page(page)) { - spin_unlock(ptl); walk->action = ACTION_CONTINUE; - goto out; + goto unlock; } if (!queue_pages_required(page, qp)) goto unlock; @@ -484,7 +483,6 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, ret = -EIO; unlock: spin_unlock(ptl); -out: return ret; } @@ -523,7 +521,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, if (!pte_present(*pte)) continue; page = vm_normal_page(vma, addr, *pte); - if (!page) + if (!page || is_zone_device_page(page)) continue; /* * vm_normal_page() filters out zero pages, but there might @@ -602,7 +600,7 @@ static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask, /* With MPOL_MF_MOVE, we migrate only unshared hugepage. */ if (flags & (MPOL_MF_MOVE_ALL) || (flags & MPOL_MF_MOVE && page_mapcount(page) == 1)) { - if (!isolate_huge_page(page, qp->pagelist) && + if (isolate_hugetlb(page, qp->pagelist) && (flags & MPOL_MF_STRICT)) /* * Failed to isolate page but allow migrating pages @@ -1388,7 +1386,7 @@ static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask, unsigned long bits = min_t(unsigned long, maxnode, BITS_PER_LONG); unsigned long t; - if (get_bitmap(&t, &nmask[maxnode / BITS_PER_LONG], bits)) + if (get_bitmap(&t, &nmask[(maxnode - 1) / BITS_PER_LONG], bits)) return -EFAULT; if (maxnode - bits >= MAX_NUMNODES) { diff --git a/mm/mempool.c b/mm/mempool.c index b933d0fc21b8..96488b13a1ef 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -379,7 +379,7 @@ void *mempool_alloc(mempool_t *pool, gfp_t gfp_mask) gfp_t gfp_temp; VM_WARN_ON_ONCE(gfp_mask & __GFP_ZERO); - might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM); + might_alloc(gfp_mask); gfp_mask |= __GFP_NOMEMALLOC; /* don't allocate emergency reserves */ gfp_mask |= __GFP_NORETRY; /* don't loop in __alloc_pages */ diff --git a/mm/memremap.c b/mm/memremap.c index 745eea0f99c3..58b20c3c300b 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -141,10 +141,10 @@ void memunmap_pages(struct dev_pagemap *pgmap) for (i = 0; i < pgmap->nr_range; i++) percpu_ref_put_many(&pgmap->ref, pfn_len(pgmap, i)); wait_for_completion(&pgmap->done); - percpu_ref_exit(&pgmap->ref); for (i = 0; i < pgmap->nr_range; i++) pageunmap_range(pgmap, i); + percpu_ref_exit(&pgmap->ref); WARN_ONCE(pgmap->altmap.alloc, "failed to free all reserved pages\n"); devmap_managed_enable_put(pgmap); @@ -279,8 +279,8 @@ err_pfn_remap: /* - * Not device managed version of dev_memremap_pages, undone by - * memunmap_pages(). Please use dev_memremap_pages if you have a struct + * Not device managed version of devm_memremap_pages, undone by + * memunmap_pages(). Please use devm_memremap_pages if you have a struct * device available. */ void *memremap_pages(struct dev_pagemap *pgmap, int nid) @@ -315,6 +315,16 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid) return ERR_PTR(-EINVAL); } break; + case MEMORY_DEVICE_COHERENT: + if (!pgmap->ops->page_free) { + WARN(1, "Missing page_free method\n"); + return ERR_PTR(-EINVAL); + } + if (!pgmap->owner) { + WARN(1, "Missing owner\n"); + return ERR_PTR(-EINVAL); + } + break; case MEMORY_DEVICE_FS_DAX: if (IS_ENABLED(CONFIG_FS_DAX_LIMITED)) { WARN(1, "File system DAX not supported\n"); diff --git a/mm/migrate.c b/mm/migrate.c index 1b4b977809a1..6a1597c92261 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -132,7 +132,7 @@ static void putback_movable_page(struct page *page) * * This function shall be used whenever the isolated pageset has been * built from lru, balloon, hugetlbfs page. See isolate_migratepages_range() - * and isolate_huge_page(). + * and isolate_hugetlb(). */ void putback_movable_pages(struct list_head *l) { @@ -314,13 +314,28 @@ void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, __migration_entry_wait(mm, ptep, ptl); } -void migration_entry_wait_huge(struct vm_area_struct *vma, - struct mm_struct *mm, pte_t *pte) +#ifdef CONFIG_HUGETLB_PAGE +void __migration_entry_wait_huge(pte_t *ptep, spinlock_t *ptl) { - spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), mm, pte); - __migration_entry_wait(mm, pte, ptl); + pte_t pte; + + spin_lock(ptl); + pte = huge_ptep_get(ptep); + + if (unlikely(!is_hugetlb_entry_migration(pte))) + spin_unlock(ptl); + else + migration_entry_wait_on_locked(pte_to_swp_entry(pte), NULL, ptl); } +void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte) +{ + spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), vma->vm_mm, pte); + + __migration_entry_wait_huge(pte, ptl); +} +#endif + #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd) { @@ -1132,15 +1147,10 @@ static int unmap_and_move(new_page_t get_new_page, return -ENOSYS; if (page_count(page) == 1) { - /* page was freed from under us. So we are done. */ + /* Page was freed from under us. So we are done. */ ClearPageActive(page); ClearPageUnevictable(page); - if (unlikely(__PageMovable(page))) { - lock_page(page); - if (!PageMovable(page)) - ClearPageIsolated(page); - unlock_page(page); - } + /* free_pages_prepare() will clear PG_isolated. */ goto out; } @@ -1662,7 +1672,7 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr, goto out; err = -ENOENT; - if (!page) + if (!page || is_zone_device_page(page)) goto out; err = 0; @@ -1675,8 +1685,9 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr, if (PageHuge(page)) { if (PageHead(page)) { - isolate_huge_page(page, pagelist); - err = 1; + err = isolate_hugetlb(page, pagelist); + if (!err) + err = 1; } } else { struct page *head; @@ -1852,7 +1863,7 @@ static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages, if (IS_ERR(page)) goto set_status; - if (page) { + if (page && !is_zone_device_page(page)) { err = page_to_nid(page); put_page(page); } else { diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 5dd97c39ca6a..27fb37d65476 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -148,15 +148,21 @@ again: if (is_writable_device_private_entry(entry)) mpfn |= MIGRATE_PFN_WRITE; } else { - if (!(migrate->flags & MIGRATE_VMA_SELECT_SYSTEM)) - goto next; pfn = pte_pfn(pte); - if (is_zero_pfn(pfn)) { + if (is_zero_pfn(pfn) && + (migrate->flags & MIGRATE_VMA_SELECT_SYSTEM)) { mpfn = MIGRATE_PFN_MIGRATE; migrate->cpages++; goto next; } page = vm_normal_page(migrate->vma, addr, pte); + if (page && !is_zone_device_page(page) && + !(migrate->flags & MIGRATE_VMA_SELECT_SYSTEM)) + goto next; + else if (page && is_device_coherent_page(page) && + (!(migrate->flags & MIGRATE_VMA_SELECT_DEVICE_COHERENT) || + page->pgmap->owner != migrate->pgmap_owner)) + goto next; mpfn = migrate_pfn(pfn) | MIGRATE_PFN_MIGRATE; mpfn |= pte_write(pte) ? MIGRATE_PFN_WRITE : 0; } @@ -518,7 +524,7 @@ EXPORT_SYMBOL(migrate_vma_setup); * handle_pte_fault() * do_anonymous_page() * to map in an anonymous zero page but the struct page will be a ZONE_DEVICE - * private page. + * private or coherent page. */ static void migrate_vma_insert_page(struct migrate_vma *migrate, unsigned long addr, @@ -594,11 +600,8 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, page_to_pfn(page)); entry = swp_entry_to_pte(swp_entry); } else { - /* - * For now we only support migrating to un-addressable device - * memory. - */ - if (is_zone_device_page(page)) { + if (is_zone_device_page(page) && + !is_device_coherent_page(page)) { pr_warn_once("Unsupported ZONE_DEVICE page type.\n"); goto abort; } @@ -683,6 +686,12 @@ void migrate_vma_pages(struct migrate_vma *migrate) } if (!page) { + /* + * The only time there is no vma is when called from + * migrate_device_coherent_page(). However this isn't + * called if the page could not be unmapped. + */ + VM_BUG_ON(!migrate->vma); if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE)) continue; if (!notified) { @@ -701,10 +710,11 @@ void migrate_vma_pages(struct migrate_vma *migrate) mapping = page_mapping(page); - if (is_device_private_page(newpage)) { + if (is_device_private_page(newpage) || + is_device_coherent_page(newpage)) { /* - * For now only support private anonymous when migrating - * to un-addressable device memory. + * For now only support anonymous memory migrating to + * device private or coherent memory. */ if (mapping) { migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; @@ -791,3 +801,49 @@ void migrate_vma_finalize(struct migrate_vma *migrate) } } EXPORT_SYMBOL(migrate_vma_finalize); + +/* + * Migrate a device coherent page back to normal memory. The caller should have + * a reference on page which will be copied to the new page if migration is + * successful or dropped on failure. + */ +int migrate_device_coherent_page(struct page *page) +{ + unsigned long src_pfn, dst_pfn = 0; + struct migrate_vma args; + struct page *dpage; + + WARN_ON_ONCE(PageCompound(page)); + + lock_page(page); + src_pfn = migrate_pfn(page_to_pfn(page)) | MIGRATE_PFN_MIGRATE; + args.src = &src_pfn; + args.dst = &dst_pfn; + args.cpages = 1; + args.npages = 1; + args.vma = NULL; + + /* + * We don't have a VMA and don't need to walk the page tables to find + * the source page. So call migrate_vma_unmap() directly to unmap the + * page as migrate_vma_setup() will fail if args.vma == NULL. + */ + migrate_vma_unmap(&args); + if (!(src_pfn & MIGRATE_PFN_MIGRATE)) + return -EBUSY; + + dpage = alloc_page(GFP_USER | __GFP_NOWARN); + if (dpage) { + lock_page(dpage); + dst_pfn = migrate_pfn(page_to_pfn(dpage)); + } + + migrate_vma_pages(&args); + if (src_pfn & MIGRATE_PFN_MIGRATE) + copy_highpage(dpage, page); + migrate_vma_finalize(&args); + + if (src_pfn & MIGRATE_PFN_MIGRATE) + return 0; + return -EBUSY; +} diff --git a/mm/mlock.c b/mm/mlock.c index 716caf851043..b14e929084cc 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -333,7 +333,7 @@ static int mlock_pte_range(pmd_t *pmd, unsigned long addr, if (!pte_present(*pte)) continue; page = vm_normal_page(vma, addr, *pte); - if (!page) + if (!page || is_zone_device_page(page)) continue; if (PageTransCompound(page)) continue; diff --git a/mm/mmap.c b/mm/mmap.c index 61e6135c54ef..c035020d0c89 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -81,53 +81,6 @@ static void unmap_region(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, unsigned long start, unsigned long end); -/* description of effects of mapping type and prot in current implementation. - * this is due to the limited x86 page protection hardware. The expected - * behavior is in parens: - * - * map_type prot - * PROT_NONE PROT_READ PROT_WRITE PROT_EXEC - * MAP_SHARED r: (no) no r: (yes) yes r: (no) yes r: (no) yes - * w: (no) no w: (no) no w: (yes) yes w: (no) no - * x: (no) no x: (no) yes x: (no) yes x: (yes) yes - * - * MAP_PRIVATE r: (no) no r: (yes) yes r: (no) yes r: (no) yes - * w: (no) no w: (no) no w: (copy) copy w: (no) no - * x: (no) no x: (no) yes x: (no) yes x: (yes) yes - * - * On arm64, PROT_EXEC has the following behaviour for both MAP_SHARED and - * MAP_PRIVATE (with Enhanced PAN supported): - * r: (no) no - * w: (no) no - * x: (yes) yes - */ -pgprot_t protection_map[16] __ro_after_init = { - [VM_NONE] = __P000, - [VM_READ] = __P001, - [VM_WRITE] = __P010, - [VM_WRITE | VM_READ] = __P011, - [VM_EXEC] = __P100, - [VM_EXEC | VM_READ] = __P101, - [VM_EXEC | VM_WRITE] = __P110, - [VM_EXEC | VM_WRITE | VM_READ] = __P111, - [VM_SHARED] = __S000, - [VM_SHARED | VM_READ] = __S001, - [VM_SHARED | VM_WRITE] = __S010, - [VM_SHARED | VM_WRITE | VM_READ] = __S011, - [VM_SHARED | VM_EXEC] = __S100, - [VM_SHARED | VM_EXEC | VM_READ] = __S101, - [VM_SHARED | VM_EXEC | VM_WRITE] = __S110, - [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = __S111 -}; - -#ifndef CONFIG_ARCH_HAS_VM_GET_PAGE_PROT -pgprot_t vm_get_page_prot(unsigned long vm_flags) -{ - return protection_map[vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]; -} -EXPORT_SYMBOL(vm_get_page_prot); -#endif /* CONFIG_ARCH_HAS_VM_GET_PAGE_PROT */ - static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags) { return pgprot_modify(oldprot, vm_get_page_prot(vm_flags)); @@ -1694,7 +1647,7 @@ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) return 0; /* Do we need to track softdirty? */ - if (IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) && !(vm_flags & VM_SOFTDIRTY)) + if (vma_soft_dirty_enabled(vma)) return 1; /* Specialty mapping? */ @@ -1894,7 +1847,6 @@ unmap_and_free_vma: /* Undo any partial mapping done by a device driver. */ unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end); - charged = 0; if (vm_flags & VM_SHARED) mapping_unmap_writable(file->f_mapping); free_vma: @@ -2588,7 +2540,6 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) vma = find_vma_prev(mm, addr, &prev); if (vma && (vma->vm_start <= addr)) return vma; - /* don't alter vm_end if the coredump is running */ if (!prev || expand_stack(prev, addr)) return NULL; if (prev->vm_flags & VM_LOCKED) @@ -2944,7 +2895,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, unsigned long ret = -EINVAL; struct file *file; - pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/vm/remap_file_pages.rst.\n", + pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/mm/remap_file_pages.rst.\n", current->comm, current->pid); if (prot) diff --git a/mm/mprotect.c b/mm/mprotect.c index ba5592655ee3..3a23dde73723 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -38,6 +38,39 @@ #include "internal.h" +static inline bool can_change_pte_writable(struct vm_area_struct *vma, + unsigned long addr, pte_t pte) +{ + struct page *page; + + VM_BUG_ON(!(vma->vm_flags & VM_WRITE) || pte_write(pte)); + + if (pte_protnone(pte) || !pte_dirty(pte)) + return false; + + /* Do we need write faults for softdirty tracking? */ + if (vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte)) + return false; + + /* Do we need write faults for uffd-wp tracking? */ + if (userfaultfd_pte_wp(vma, pte)) + return false; + + if (!(vma->vm_flags & VM_SHARED)) { + /* + * We can only special-case on exclusive anonymous pages, + * because we know that our write-fault handler similarly would + * map them writable without any additional checks while holding + * the PT lock. + */ + page = vm_normal_page(vma, addr, pte); + if (!page || !PageAnon(page) || !PageAnonExclusive(page)) + return false; + } + + return true; +} + static unsigned long change_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t newprot, unsigned long cp_flags) @@ -46,7 +79,6 @@ static unsigned long change_pte_range(struct mmu_gather *tlb, spinlock_t *ptl; unsigned long pages = 0; int target_node = NUMA_NO_NODE; - bool dirty_accountable = cp_flags & MM_CP_DIRTY_ACCT; bool prot_numa = cp_flags & MM_CP_PROT_NUMA; bool uffd_wp = cp_flags & MM_CP_UFFD_WP; bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; @@ -95,7 +127,7 @@ static unsigned long change_pte_range(struct mmu_gather *tlb, continue; page = vm_normal_page(vma, addr, oldpte); - if (!page || PageKsm(page)) + if (!page || is_zone_device_page(page) || PageKsm(page)) continue; /* Also skip shared copy-on-write pages */ @@ -137,21 +169,27 @@ static unsigned long change_pte_range(struct mmu_gather *tlb, ptent = pte_wrprotect(ptent); ptent = pte_mkuffd_wp(ptent); } else if (uffd_wp_resolve) { - /* - * Leave the write bit to be handled - * by PF interrupt handler, then - * things like COW could be properly - * handled. - */ ptent = pte_clear_uffd_wp(ptent); } - /* Avoid taking write faults for known dirty pages */ - if (dirty_accountable && pte_dirty(ptent) && - (pte_soft_dirty(ptent) || - !(vma->vm_flags & VM_SOFTDIRTY))) { + /* + * In some writable, shared mappings, we might want + * to catch actual write access -- see + * vma_wants_writenotify(). + * + * In all writable, private mappings, we have to + * properly handle COW. + * + * In both cases, we can sometimes still change PTEs + * writable and avoid the write-fault handler, for + * example, if a PTE is already dirty and no other + * COW or special handling is required. + */ + if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) && + !pte_write(ptent) && + can_change_pte_writable(vma, addr, ptent)) ptent = pte_mkwrite(ptent); - } + ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent); if (pte_needs_flush(oldpte, ptent)) tlb_flush_pte_range(tlb, addr, PAGE_SIZE); @@ -505,9 +543,9 @@ mprotect_fixup(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long oldflags = vma->vm_flags; long nrpages = (end - start) >> PAGE_SHIFT; unsigned long charged = 0; + bool try_change_writable; pgoff_t pgoff; int error; - int dirty_accountable = 0; if (newflags == oldflags) { *pprev = vma; @@ -583,11 +621,20 @@ success: * held in write mode. */ vma->vm_flags = newflags; - dirty_accountable = vma_wants_writenotify(vma, vma->vm_page_prot); + /* + * We want to check manually if we can change individual PTEs writable + * if we can't do that automatically for all PTEs in a mapping. For + * private mappings, that's always the case when we have write + * permissions as we properly have to handle COW. + */ + if (vma->vm_flags & VM_SHARED) + try_change_writable = vma_wants_writenotify(vma, vma->vm_page_prot); + else + try_change_writable = !!(vma->vm_flags & VM_WRITE); vma_set_page_prot(vma); change_protection(tlb, vma, start, end, vma->vm_page_prot, - dirty_accountable ? MM_CP_DIRTY_ACCT : 0); + try_change_writable ? MM_CP_TRY_CHANGE_WRITABLE : 0); /* * Private VM_LOCKED VMA becoming writable: trigger COW to avoid major @@ -616,7 +663,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len, { unsigned long nstart, end, tmp, reqprot; struct vm_area_struct *vma, *prev; - int error = -EINVAL; + int error; const int grows = prot & (PROT_GROWSDOWN|PROT_GROWSUP); const bool rier = (current->personality & READ_IMPLIES_EXEC) && (prot & PROT_READ); diff --git a/mm/nommu.c b/mm/nommu.c index 9d7afc2d959e..e819cbc21b39 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -500,7 +500,7 @@ static void delete_nommu_region(struct vm_region *region) static void free_page_series(unsigned long from, unsigned long to) { for (; from < to; from += PAGE_SIZE) { - struct page *page = virt_to_page(from); + struct page *page = virt_to_page((void *)from); atomic_long_dec(&mmap_pages_allocated); put_page(page); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 170bbf144cfa..e5486d47406e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -126,13 +126,97 @@ typedef int __bitwise fpi_t; static DEFINE_MUTEX(pcp_batch_high_lock); #define MIN_PERCPU_PAGELIST_HIGH_FRACTION (8) -struct pagesets { - local_lock_t lock; -}; -static DEFINE_PER_CPU(struct pagesets, pagesets) = { - .lock = INIT_LOCAL_LOCK(lock), -}; +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT) +/* + * On SMP, spin_trylock is sufficient protection. + * On PREEMPT_RT, spin_trylock is equivalent on both SMP and UP. + */ +#define pcp_trylock_prepare(flags) do { } while (0) +#define pcp_trylock_finish(flag) do { } while (0) +#else + +/* UP spin_trylock always succeeds so disable IRQs to prevent re-entrancy. */ +#define pcp_trylock_prepare(flags) local_irq_save(flags) +#define pcp_trylock_finish(flags) local_irq_restore(flags) +#endif + +/* + * Locking a pcp requires a PCP lookup followed by a spinlock. To avoid + * a migration causing the wrong PCP to be locked and remote memory being + * potentially allocated, pin the task to the CPU for the lookup+lock. + * preempt_disable is used on !RT because it is faster than migrate_disable. + * migrate_disable is used on RT because otherwise RT spinlock usage is + * interfered with and a high priority task cannot preempt the allocator. + */ +#ifndef CONFIG_PREEMPT_RT +#define pcpu_task_pin() preempt_disable() +#define pcpu_task_unpin() preempt_enable() +#else +#define pcpu_task_pin() migrate_disable() +#define pcpu_task_unpin() migrate_enable() +#endif +/* + * Generic helper to lookup and a per-cpu variable with an embedded spinlock. + * Return value should be used with equivalent unlock helper. + */ +#define pcpu_spin_lock(type, member, ptr) \ +({ \ + type *_ret; \ + pcpu_task_pin(); \ + _ret = this_cpu_ptr(ptr); \ + spin_lock(&_ret->member); \ + _ret; \ +}) + +#define pcpu_spin_lock_irqsave(type, member, ptr, flags) \ +({ \ + type *_ret; \ + pcpu_task_pin(); \ + _ret = this_cpu_ptr(ptr); \ + spin_lock_irqsave(&_ret->member, flags); \ + _ret; \ +}) + +#define pcpu_spin_trylock_irqsave(type, member, ptr, flags) \ +({ \ + type *_ret; \ + pcpu_task_pin(); \ + _ret = this_cpu_ptr(ptr); \ + if (!spin_trylock_irqsave(&_ret->member, flags)) { \ + pcpu_task_unpin(); \ + _ret = NULL; \ + } \ + _ret; \ +}) + +#define pcpu_spin_unlock(member, ptr) \ +({ \ + spin_unlock(&ptr->member); \ + pcpu_task_unpin(); \ +}) + +#define pcpu_spin_unlock_irqrestore(member, ptr, flags) \ +({ \ + spin_unlock_irqrestore(&ptr->member, flags); \ + pcpu_task_unpin(); \ +}) + +/* struct per_cpu_pages specific helpers. */ +#define pcp_spin_lock(ptr) \ + pcpu_spin_lock(struct per_cpu_pages, lock, ptr) + +#define pcp_spin_lock_irqsave(ptr, flags) \ + pcpu_spin_lock_irqsave(struct per_cpu_pages, lock, ptr, flags) + +#define pcp_spin_trylock_irqsave(ptr, flags) \ + pcpu_spin_trylock_irqsave(struct per_cpu_pages, lock, ptr, flags) + +#define pcp_spin_unlock(ptr) \ + pcpu_spin_unlock(lock, ptr) + +#define pcp_spin_unlock_irqrestore(ptr, flags) \ + pcpu_spin_unlock_irqrestore(lock, ptr, flags) #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DEFINE_PER_CPU(int, numa_node); EXPORT_PER_CPU_SYMBOL(numa_node); @@ -151,13 +235,7 @@ DEFINE_PER_CPU(int, _numa_mem_); /* Kernel "local memory" node */ EXPORT_PER_CPU_SYMBOL(_numa_mem_); #endif -/* work_structs for global per-cpu drains */ -struct pcpu_drain { - struct zone *zone; - struct work_struct work; -}; static DEFINE_MUTEX(pcpu_drain_mutex); -static DEFINE_PER_CPU(struct pcpu_drain, pcpu_drain); #ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY volatile unsigned long latent_entropy __latent_entropy; @@ -524,7 +602,7 @@ void set_pfnblock_flags_mask(struct page *page, unsigned long flags, { unsigned long *bitmap; unsigned long bitidx, word_bitidx; - unsigned long old_word, word; + unsigned long word; BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4); BUILD_BUG_ON(MIGRATE_TYPES > (1 << PB_migratetype_bits)); @@ -540,12 +618,8 @@ void set_pfnblock_flags_mask(struct page *page, unsigned long flags, flags <<= bitidx; word = READ_ONCE(bitmap[word_bitidx]); - for (;;) { - old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags); - if (word == old_word) - break; - word = old_word; - } + do { + } while (!try_cmpxchg(&bitmap[word_bitidx], &word, (word & ~mask) | flags)); } void set_pageblock_migratetype(struct page *page, int migratetype) @@ -653,7 +727,7 @@ static inline unsigned int order_to_pindex(int migratetype, int order) #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (order > PAGE_ALLOC_COSTLY_ORDER) { VM_BUG_ON(order != pageblock_order); - base = PAGE_ALLOC_COSTLY_ORDER + 1; + return NR_LOWORDER_PCP_LISTS; } #else VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER); @@ -667,7 +741,7 @@ static inline int pindex_to_order(unsigned int pindex) int order = pindex / MIGRATE_PCPTYPES; #ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (order > PAGE_ALLOC_COSTLY_ORDER) + if (pindex == NR_LOWORDER_PCP_LISTS) order = pageblock_order; #else VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER); @@ -744,6 +818,14 @@ void prep_compound_page(struct page *page, unsigned int order) prep_compound_head(page, order); } +void destroy_large_folio(struct folio *folio) +{ + enum compound_dtor_id dtor = folio_page(folio, 1)->compound_dtor; + + VM_BUG_ON_FOLIO(dtor >= NR_COMPOUND_DTORS, folio); + compound_page_dtors[dtor](&folio->page); +} + #ifdef CONFIG_DEBUG_PAGEALLOC unsigned int _debug_guardpage_minorder; @@ -785,7 +867,7 @@ static inline bool set_page_guard(struct zone *zone, struct page *page, return false; __SetPageGuard(page); - INIT_LIST_HEAD(&page->lru); + INIT_LIST_HEAD(&page->buddy_list); set_page_private(page, order); /* Guard pages are not available for any usage */ __mod_zone_freepage_state(zone, -(1 << order), migratetype); @@ -928,7 +1010,7 @@ static inline void add_to_free_list(struct page *page, struct zone *zone, { struct free_area *area = &zone->free_area[order]; - list_add(&page->lru, &area->free_list[migratetype]); + list_add(&page->buddy_list, &area->free_list[migratetype]); area->nr_free++; } @@ -938,7 +1020,7 @@ static inline void add_to_free_list_tail(struct page *page, struct zone *zone, { struct free_area *area = &zone->free_area[order]; - list_add_tail(&page->lru, &area->free_list[migratetype]); + list_add_tail(&page->buddy_list, &area->free_list[migratetype]); area->nr_free++; } @@ -952,7 +1034,7 @@ static inline void move_to_free_list(struct page *page, struct zone *zone, { struct free_area *area = &zone->free_area[order]; - list_move_tail(&page->lru, &area->free_list[migratetype]); + list_move_tail(&page->buddy_list, &area->free_list[migratetype]); } static inline void del_page_from_free_list(struct page *page, struct zone *zone, @@ -962,7 +1044,7 @@ static inline void del_page_from_free_list(struct page *page, struct zone *zone, if (page_reported(page)) __ClearPageReported(page); - list_del(&page->lru); + list_del(&page->buddy_list); __ClearPageBuddy(page); set_page_private(page, 0); zone->free_area[order].nr_free--; @@ -1296,18 +1378,14 @@ static inline bool should_skip_kasan_poison(struct page *page, fpi_t fpi_flags) PageSkipKASanPoison(page); } -static void kernel_init_free_pages(struct page *page, int numpages) +static void kernel_init_pages(struct page *page, int numpages) { int i; /* s390's use of memset() could override KASAN redzones. */ kasan_disable_current(); - for (i = 0; i < numpages; i++) { - u8 tag = page_kasan_tag(page + i); - page_kasan_tag_reset(page + i); - clear_highpage(page + i); - page_kasan_tag_set(page + i, tag); - } + for (i = 0; i < numpages; i++) + clear_highpage_kasan_tagged(page + i); kasan_enable_current(); } @@ -1396,7 +1474,7 @@ static __always_inline bool free_pages_prepare(struct page *page, init = false; } if (init) - kernel_init_free_pages(page, 1 << order); + kernel_init_pages(page, 1 << order); /* * arch_free_page() can make the page's contents inaccessible. s390 @@ -1473,10 +1551,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, /* Ensure requested pindex is drained first. */ pindex = pindex - 1; - /* - * local_lock_irq held so equivalent to spin_lock_irqsave for - * both PREEMPT_RT and non-PREEMPT_RT configurations. - */ + /* Caller must hold IRQ-safe pcp->lock so IRQs are disabled. */ spin_lock(&zone->lock); isolated_pageblocks = has_isolate_pageblock(zone); @@ -1504,11 +1579,11 @@ static void free_pcppages_bulk(struct zone *zone, int count, do { int mt; - page = list_last_entry(list, struct page, lru); + page = list_last_entry(list, struct page, pcp_list); mt = get_pcppage_migratetype(page); /* must delete to avoid corrupting pcp list */ - list_del(&page->lru); + list_del(&page->pcp_list); count -= nr_pages; pcp->count -= nr_pages; @@ -2442,7 +2517,7 @@ inline void post_alloc_hook(struct page *page, unsigned int order, } /* If memory is still not initialized, do it now. */ if (init) - kernel_init_free_pages(page, 1 << order); + kernel_init_pages(page, 1 << order); /* Propagate __GFP_SKIP_KASAN_POISON to page flags. */ if (kasan_hw_tags_enabled() && (gfp_flags & __GFP_SKIP_KASAN_POISON)) SetPageSkipKASanPoison(page); @@ -3045,10 +3120,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, { int i, allocated = 0; - /* - * local_lock_irq held so equivalent to spin_lock_irqsave for - * both PREEMPT_RT and non-PREEMPT_RT configurations. - */ + /* Caller must hold IRQ-safe pcp->lock so IRQs are disabled. */ spin_lock(&zone->lock); for (i = 0; i < count; ++i) { struct page *page = __rmqueue(zone, order, migratetype, @@ -3069,7 +3141,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, * for IO devices that can merge IO requests if the physical * pages are ordered properly. */ - list_add_tail(&page->lru, list); + list_add_tail(&page->pcp_list, list); allocated++; if (is_migrate_cma(get_pcppage_migratetype(page))) __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, @@ -3092,51 +3164,48 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, * Called from the vmstat counter updater to drain pagesets of this * currently executing processor on remote nodes after they have * expired. - * - * Note that this function must be called with the thread pinned to - * a single processor. */ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) { - unsigned long flags; int to_drain, batch; - local_lock_irqsave(&pagesets.lock, flags); batch = READ_ONCE(pcp->batch); to_drain = min(pcp->count, batch); - if (to_drain > 0) + if (to_drain > 0) { + unsigned long flags; + + /* + * free_pcppages_bulk expects IRQs disabled for zone->lock + * so even though pcp->lock is not intended to be IRQ-safe, + * it's needed in this context. + */ + spin_lock_irqsave(&pcp->lock, flags); free_pcppages_bulk(zone, to_drain, pcp, 0); - local_unlock_irqrestore(&pagesets.lock, flags); + spin_unlock_irqrestore(&pcp->lock, flags); + } } #endif /* * Drain pcplists of the indicated processor and zone. - * - * The processor must either be the current processor and the - * thread pinned to the current processor or a processor that - * is not online. */ static void drain_pages_zone(unsigned int cpu, struct zone *zone) { - unsigned long flags; struct per_cpu_pages *pcp; - local_lock_irqsave(&pagesets.lock, flags); - pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); - if (pcp->count) - free_pcppages_bulk(zone, pcp->count, pcp, 0); + if (pcp->count) { + unsigned long flags; - local_unlock_irqrestore(&pagesets.lock, flags); + /* See drain_zone_pages on why this is disabling IRQs */ + spin_lock_irqsave(&pcp->lock, flags); + free_pcppages_bulk(zone, pcp->count, pcp, 0); + spin_unlock_irqrestore(&pcp->lock, flags); + } } /* * Drain pcplists of all zones on the indicated processor. - * - * The processor must either be the current processor and the - * thread pinned to the current processor or a processor that - * is not online. */ static void drain_pages(unsigned int cpu) { @@ -3149,9 +3218,6 @@ static void drain_pages(unsigned int cpu) /* * Spill all of this CPU's per-cpu pages back into the buddy allocator. - * - * The CPU has to be pinned. When zone parameter is non-NULL, spill just - * the single zone's pages. */ void drain_local_pages(struct zone *zone) { @@ -3163,24 +3229,6 @@ void drain_local_pages(struct zone *zone) drain_pages(cpu); } -static void drain_local_pages_wq(struct work_struct *work) -{ - struct pcpu_drain *drain; - - drain = container_of(work, struct pcpu_drain, work); - - /* - * drain_all_pages doesn't use proper cpu hotplug protection so - * we can race with cpu offline when the WQ can move this from - * a cpu pinned worker to an unbound one. We can operate on a different - * cpu which is alright but we also have to make sure to not move to - * a different one. - */ - migrate_disable(); - drain_local_pages(drain->zone); - migrate_enable(); -} - /* * The implementation of drain_all_pages(), exposing an extra parameter to * drain on all cpus. @@ -3202,13 +3250,6 @@ static void __drain_all_pages(struct zone *zone, bool force_all_cpus) static cpumask_t cpus_with_pcps; /* - * Make sure nobody triggers this path before mm_percpu_wq is fully - * initialized. - */ - if (WARN_ON_ONCE(!mm_percpu_wq)) - return; - - /* * Do not drain if one is already in progress unless it's specific to * a zone. Such callers are primarily CMA and memory hotplug and need * the drain to be complete when the call returns. @@ -3257,14 +3298,11 @@ static void __drain_all_pages(struct zone *zone, bool force_all_cpus) } for_each_cpu(cpu, &cpus_with_pcps) { - struct pcpu_drain *drain = per_cpu_ptr(&pcpu_drain, cpu); - - drain->zone = zone; - INIT_WORK(&drain->work, drain_local_pages_wq); - queue_work_on(cpu, mm_percpu_wq, &drain->work); + if (zone) + drain_pages_zone(cpu, zone); + else + drain_pages(cpu); } - for_each_cpu(cpu, &cpus_with_pcps) - flush_work(&per_cpu_ptr(&pcpu_drain, cpu)->work); mutex_unlock(&pcpu_drain_mutex); } @@ -3273,8 +3311,6 @@ static void __drain_all_pages(struct zone *zone, bool force_all_cpus) * Spill all the per-cpu pages from all CPUs back into the buddy allocator. * * When zone parameter is non-NULL, spill just the single zone's pages. - * - * Note that this can be extremely slow as the draining happens in a workqueue. */ void drain_all_pages(struct zone *zone) { @@ -3319,7 +3355,7 @@ void mark_free_pages(struct zone *zone) for_each_migratetype_order(order, t) { list_for_each_entry(page, - &zone->free_area[order].free_list[t], lru) { + &zone->free_area[order].free_list[t], buddy_list) { unsigned long i; pfn = page_to_pfn(page); @@ -3396,19 +3432,17 @@ static int nr_pcp_high(struct per_cpu_pages *pcp, struct zone *zone, return min(READ_ONCE(pcp->batch) << 2, high); } -static void free_unref_page_commit(struct page *page, int migratetype, +static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp, + struct page *page, int migratetype, unsigned int order) { - struct zone *zone = page_zone(page); - struct per_cpu_pages *pcp; int high; int pindex; bool free_high; __count_vm_event(PGFREE); - pcp = this_cpu_ptr(zone->per_cpu_pageset); pindex = order_to_pindex(migratetype, order); - list_add(&page->lru, &pcp->lists[pindex]); + list_add(&page->pcp_list, &pcp->lists[pindex]); pcp->count += 1 << order; /* @@ -3433,6 +3467,9 @@ static void free_unref_page_commit(struct page *page, int migratetype, void free_unref_page(struct page *page, unsigned int order) { unsigned long flags; + unsigned long __maybe_unused UP_flags; + struct per_cpu_pages *pcp; + struct zone *zone; unsigned long pfn = page_to_pfn(page); int migratetype; @@ -3455,9 +3492,16 @@ void free_unref_page(struct page *page, unsigned int order) migratetype = MIGRATE_MOVABLE; } - local_lock_irqsave(&pagesets.lock, flags); - free_unref_page_commit(page, migratetype, order); - local_unlock_irqrestore(&pagesets.lock, flags); + zone = page_zone(page); + pcp_trylock_prepare(UP_flags); + pcp = pcp_spin_trylock_irqsave(zone->per_cpu_pageset, flags); + if (pcp) { + free_unref_page_commit(zone, pcp, page, migratetype, order); + pcp_spin_unlock_irqrestore(pcp, flags); + } else { + free_one_page(zone, page, pfn, order, migratetype, FPI_NONE); + } + pcp_trylock_finish(UP_flags); } /* @@ -3466,6 +3510,8 @@ void free_unref_page(struct page *page, unsigned int order) void free_unref_page_list(struct list_head *list) { struct page *page, *next; + struct per_cpu_pages *pcp = NULL; + struct zone *locked_zone = NULL; unsigned long flags; int batch_count = 0; int migratetype; @@ -3490,8 +3536,18 @@ void free_unref_page_list(struct list_head *list) } } - local_lock_irqsave(&pagesets.lock, flags); list_for_each_entry_safe(page, next, list, lru) { + struct zone *zone = page_zone(page); + + /* Different zone, different pcp lock. */ + if (zone != locked_zone) { + if (pcp) + pcp_spin_unlock_irqrestore(pcp, flags); + + locked_zone = zone; + pcp = pcp_spin_lock_irqsave(locked_zone->per_cpu_pageset, flags); + } + /* * Non-isolated types over MIGRATE_PCPTYPES get added * to the MIGRATE_MOVABLE pcp list. @@ -3501,19 +3557,21 @@ void free_unref_page_list(struct list_head *list) migratetype = MIGRATE_MOVABLE; trace_mm_page_free_batched(page); - free_unref_page_commit(page, migratetype, 0); + free_unref_page_commit(zone, pcp, page, migratetype, 0); /* * Guard against excessive IRQ disabled times when we get * a large list of pages to free. */ if (++batch_count == SWAP_CLUSTER_MAX) { - local_unlock_irqrestore(&pagesets.lock, flags); + pcp_spin_unlock_irqrestore(pcp, flags); batch_count = 0; - local_lock_irqsave(&pagesets.lock, flags); + pcp = pcp_spin_lock_irqsave(locked_zone->per_cpu_pageset, flags); } } - local_unlock_irqrestore(&pagesets.lock, flags); + + if (pcp) + pcp_spin_unlock_irqrestore(pcp, flags); } /* @@ -3638,6 +3696,43 @@ static inline void zone_statistics(struct zone *preferred_zone, struct zone *z, #endif } +static __always_inline +struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone, + unsigned int order, unsigned int alloc_flags, + int migratetype) +{ + struct page *page; + unsigned long flags; + + do { + page = NULL; + spin_lock_irqsave(&zone->lock, flags); + /* + * order-0 request can reach here when the pcplist is skipped + * due to non-CMA allocation context. HIGHATOMIC area is + * reserved for high-order atomic allocation, so order-0 + * request should skip it. + */ + if (order > 0 && alloc_flags & ALLOC_HARDER) + page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); + if (!page) { + page = __rmqueue(zone, order, migratetype, alloc_flags); + if (!page) { + spin_unlock_irqrestore(&zone->lock, flags); + return NULL; + } + } + __mod_zone_freepage_state(zone, -(1 << order), + get_pcppage_migratetype(page)); + spin_unlock_irqrestore(&zone->lock, flags); + } while (check_new_pages(page, order)); + + __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); + zone_statistics(preferred_zone, zone, 1); + + return page; +} + /* Remove page from the per-cpu list, caller must protect the list */ static inline struct page *__rmqueue_pcplist(struct zone *zone, unsigned int order, @@ -3671,8 +3766,8 @@ struct page *__rmqueue_pcplist(struct zone *zone, unsigned int order, return NULL; } - page = list_first_entry(list, struct page, lru); - list_del(&page->lru); + page = list_first_entry(list, struct page, pcp_list); + list_del(&page->pcp_list); pcp->count -= 1 << order; } while (check_new_pcp(page, order)); @@ -3689,19 +3784,29 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, struct list_head *list; struct page *page; unsigned long flags; + unsigned long __maybe_unused UP_flags; - local_lock_irqsave(&pagesets.lock, flags); + /* + * spin_trylock may fail due to a parallel drain. In the future, the + * trylock will also protect against IRQ reentrancy. + */ + pcp_trylock_prepare(UP_flags); + pcp = pcp_spin_trylock_irqsave(zone->per_cpu_pageset, flags); + if (!pcp) { + pcp_trylock_finish(UP_flags); + return NULL; + } /* * On allocation, reduce the number of pages that are batch freed. * See nr_pcp_free() where free_factor is increased for subsequent * frees. */ - pcp = this_cpu_ptr(zone->per_cpu_pageset); pcp->free_factor >>= 1; list = &pcp->lists[order_to_pindex(migratetype, order)]; page = __rmqueue_pcplist(zone, order, migratetype, alloc_flags, pcp, list); - local_unlock_irqrestore(&pagesets.lock, flags); + pcp_spin_unlock_irqrestore(pcp, flags); + pcp_trylock_finish(UP_flags); if (page) { __count_zid_vm_events(PGALLOC, page_zonenum(page), 1); zone_statistics(preferred_zone, zone, 1); @@ -3718,9 +3823,14 @@ struct page *rmqueue(struct zone *preferred_zone, gfp_t gfp_flags, unsigned int alloc_flags, int migratetype) { - unsigned long flags; struct page *page; + /* + * We most definitely don't want callers attempting to + * allocate greater than order-1 page units with __GFP_NOFAIL. + */ + WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1)); + if (likely(pcp_allowed_order(order))) { /* * MIGRATE_MOVABLE pcplist could have the pages on CMA area and @@ -3730,53 +3840,23 @@ struct page *rmqueue(struct zone *preferred_zone, migratetype != MIGRATE_MOVABLE) { page = rmqueue_pcplist(preferred_zone, zone, order, gfp_flags, migratetype, alloc_flags); - goto out; + if (likely(page)) + goto out; } } - /* - * We most definitely don't want callers attempting to - * allocate greater than order-1 page units with __GFP_NOFAIL. - */ - WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1)); - - do { - page = NULL; - spin_lock_irqsave(&zone->lock, flags); - /* - * order-0 request can reach here when the pcplist is skipped - * due to non-CMA allocation context. HIGHATOMIC area is - * reserved for high-order atomic allocation, so order-0 - * request should skip it. - */ - if (order > 0 && alloc_flags & ALLOC_HARDER) - page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); - if (!page) { - page = __rmqueue(zone, order, migratetype, alloc_flags); - if (!page) - goto failed; - } - __mod_zone_freepage_state(zone, -(1 << order), - get_pcppage_migratetype(page)); - spin_unlock_irqrestore(&zone->lock, flags); - } while (check_new_pages(page, order)); - - __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); - zone_statistics(preferred_zone, zone, 1); + page = rmqueue_buddy(preferred_zone, zone, order, alloc_flags, + migratetype); out: /* Separate test+clear to avoid unnecessary atomics */ - if (test_bit(ZONE_BOOSTED_WATERMARK, &zone->flags)) { + if (unlikely(test_bit(ZONE_BOOSTED_WATERMARK, &zone->flags))) { clear_bit(ZONE_BOOSTED_WATERMARK, &zone->flags); wakeup_kswapd(zone, 0, 0, zone_idx(zone)); } VM_BUG_ON_PAGE(page && bad_range(zone, page), page); return page; - -failed: - spin_unlock_irqrestore(&zone->lock, flags); - return NULL; } #ifdef CONFIG_FAIL_PAGE_ALLOC @@ -4095,7 +4175,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags, retry: /* * Scan zonelist, looking for a zone with enough free. - * See also __cpuset_node_allowed() comment in kernel/cpuset.c. + * See also __cpuset_node_allowed() comment in kernel/cgroup/cpuset.c. */ no_fallback = alloc_flags & ALLOC_NOFRAGMENT; z = ac->preferred_zoneref; @@ -5202,10 +5282,7 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order, *alloc_flags |= ALLOC_CPUSET; } - fs_reclaim_acquire(gfp_mask); - fs_reclaim_release(gfp_mask); - - might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM); + might_alloc(gfp_mask); if (should_fail_alloc_page(gfp_mask, order)) return false; @@ -5253,6 +5330,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, { struct page *page; unsigned long flags; + unsigned long __maybe_unused UP_flags; struct zone *zone; struct zoneref *z; struct per_cpu_pages *pcp; @@ -5333,11 +5411,14 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, if (unlikely(!zone)) goto failed; + /* Is a parallel drain in progress? */ + pcp_trylock_prepare(UP_flags); + pcp = pcp_spin_trylock_irqsave(zone->per_cpu_pageset, flags); + if (!pcp) + goto failed_irq; + /* Attempt the batch allocation */ - local_lock_irqsave(&pagesets.lock, flags); - pcp = this_cpu_ptr(zone->per_cpu_pageset); pcp_list = &pcp->lists[order_to_pindex(ac.migratetype, 0)]; - while (nr_populated < nr_pages) { /* Skip existing pages */ @@ -5350,8 +5431,10 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, pcp, pcp_list); if (unlikely(!page)) { /* Try and allocate at least one page */ - if (!nr_account) + if (!nr_account) { + pcp_spin_unlock_irqrestore(pcp, flags); goto failed_irq; + } break; } nr_account++; @@ -5364,7 +5447,8 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, nr_populated++; } - local_unlock_irqrestore(&pagesets.lock, flags); + pcp_spin_unlock_irqrestore(pcp, flags); + pcp_trylock_finish(UP_flags); __count_zid_vm_events(PGALLOC, zone_idx(zone), nr_account); zone_statistics(ac.preferred_zoneref->zone, zone, nr_account); @@ -5373,7 +5457,7 @@ out: return nr_populated; failed_irq: - local_unlock_irqrestore(&pagesets.lock, flags); + pcp_trylock_finish(UP_flags); failed: page = __alloc_pages(gfp, 0, preferred_nid, nodemask); @@ -5804,14 +5888,14 @@ long si_mem_available(void) /* * Estimate the amount of memory available for userspace allocations, - * without causing swapping. + * without causing swapping or OOM. */ available = global_zone_page_state(NR_FREE_PAGES) - totalreserve_pages; /* * Not all the page cache can be freed, otherwise the system will - * start swapping. Assume at least half of the page cache, or the - * low watermark worth of cache, needs to stay. + * start swapping or thrashing. Assume at least half of the page + * cache, or the low watermark worth of cache, needs to stay. */ pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE]; pagecache -= min(pagecache / 2, wmark_low); @@ -5939,7 +6023,7 @@ static void show_migration_types(unsigned char type) void show_free_areas(unsigned int filter, nodemask_t *nodemask) { unsigned long free_pcp = 0; - int cpu; + int cpu, nid; struct zone *zone; pg_data_t *pgdat; @@ -6127,7 +6211,11 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) printk(KERN_CONT "= %lukB\n", K(total)); } - hugetlb_show_meminfo(); + for_each_online_node(nid) { + if (show_mem_node_skip(filter, nid, nodemask)) + continue; + hugetlb_show_meminfo_node(nid); + } printk("%ld total pagecache pages\n", global_node_page_state(NR_FILE_PAGES)); @@ -7013,6 +7101,7 @@ static void per_cpu_pages_init(struct per_cpu_pages *pcp, struct per_cpu_zonesta memset(pcp, 0, sizeof(*pcp)); memset(pzstats, 0, sizeof(*pzstats)); + spin_lock_init(&pcp->lock); for (pindex = 0; pindex < NR_PCP_LISTS; pindex++) INIT_LIST_HEAD(&pcp->lists[pindex]); diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index c10f839fc410..8e9e574d535a 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -174,8 +174,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) if (!pvmw->pte) return false; - pvmw->ptl = huge_pte_lockptr(hstate, mm, pvmw->pte); - spin_lock(pvmw->ptl); + pvmw->ptl = huge_pte_lock(hstate, mm, pvmw->pte); if (!check_pte(pvmw)) return not_found(pvmw); return true; @@ -243,7 +242,7 @@ restart: * cleared *pmd but not decremented compound_mapcount(). */ if ((pvmw->flags & PVMW_SYNC) && - transparent_hugepage_active(vma) && + transhuge_vma_suitable(vma, pvmw->address) && (pvmw->nr_pages >= HPAGE_PMD_NR)) { spinlock_t *ptl = pmd_lock(mm, pvmw->pmd); diff --git a/mm/percpu.c b/mm/percpu.c index 3633eeefaa0d..27697b2429c2 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -3104,7 +3104,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, goto out_free_areas; } /* kmemleak tracks the percpu allocations separately */ - kmemleak_free(ptr); + kmemleak_ignore_phys(__pa(ptr)); areas[group] = ptr; base = min(ptr, base); @@ -3304,7 +3304,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t goto enomem; } /* kmemleak tracks the percpu allocations separately */ - kmemleak_free(ptr); + kmemleak_ignore_phys(__pa(ptr)); pages[j++] = virt_to_page(ptr); } } @@ -3417,7 +3417,7 @@ void __init setup_per_cpu_areas(void) if (!ai || !fc) panic("Failed to allocate memory for percpu areas."); /* kmemleak tracks the percpu allocations separately */ - kmemleak_free(fc); + kmemleak_ignore_phys(__pa(fc)); ai->dyn_size = unit_size; ai->unit_size = unit_size; diff --git a/mm/rmap.c b/mm/rmap.c index 746c05acad27..edc06c52bc82 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -999,7 +999,7 @@ static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw) * downgrading page table protection not changing it to point * to a new page. * - * See Documentation/vm/mmu_notifier.rst + * See Documentation/mm/mmu_notifier.rst */ if (ret) cleaned++; @@ -1537,6 +1537,8 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, PageAnonExclusive(subpage); if (folio_test_hugetlb(folio)) { + bool anon = folio_test_anon(folio); + /* * The try_to_unmap() is only passed a hugetlb page * in the case where the hugetlb page is poisoned. @@ -1551,31 +1553,28 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, */ flush_cache_range(vma, range.start, range.end); - if (!folio_test_anon(folio)) { + /* + * To call huge_pmd_unshare, i_mmap_rwsem must be + * held in write mode. Caller needs to explicitly + * do this outside rmap routines. + */ + VM_BUG_ON(!anon && !(flags & TTU_RMAP_LOCKED)); + if (!anon && huge_pmd_unshare(mm, vma, address, pvmw.pte)) { + flush_tlb_range(vma, range.start, range.end); + mmu_notifier_invalidate_range(mm, range.start, + range.end); + /* - * To call huge_pmd_unshare, i_mmap_rwsem must be - * held in write mode. Caller needs to explicitly - * do this outside rmap routines. + * The ref count of the PMD page was dropped + * which is part of the way map counting + * is done for shared PMDs. Return 'true' + * here. When there is no other sharing, + * huge_pmd_unshare returns false and we will + * unmap the actual page and drop map count + * to zero. */ - VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); - - if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) { - flush_tlb_range(vma, range.start, range.end); - mmu_notifier_invalidate_range(mm, range.start, - range.end); - - /* - * The ref count of the PMD page was dropped - * which is part of the way map counting - * is done for shared PMDs. Return 'true' - * here. When there is no other sharing, - * huge_pmd_unshare returns false and we will - * unmap the actual page and drop map count - * to zero. - */ - page_vma_mapped_walk_done(&pvmw); - break; - } + page_vma_mapped_walk_done(&pvmw); + break; } pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); } else { @@ -1619,9 +1618,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); - set_huge_swap_pte_at(mm, address, - pvmw.pte, pteval, - vma_mmu_pagesize(vma)); + set_huge_pte_at(mm, address, pvmw.pte, pteval); } else { dec_mm_counter(mm, mm_counter(&folio->page)); set_pte_at(mm, address, pvmw.pte, pteval); @@ -1765,7 +1762,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, * to point at a new folio while a device is * still using this folio. * - * See Documentation/vm/mmu_notifier.rst + * See Documentation/mm/mmu_notifier.rst */ dec_mm_counter(mm, mm_counter_file(&folio->page)); } @@ -1775,7 +1772,7 @@ discard: * done above for all cases requiring it to happen under page * table lock before mmu_notifier_invalidate_range_end() * - * See Documentation/vm/mmu_notifier.rst + * See Documentation/mm/mmu_notifier.rst */ page_remove_rmap(subpage, vma, folio_test_hugetlb(folio)); if (vma->vm_flags & VM_LOCKED) @@ -1921,6 +1918,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, PageAnonExclusive(subpage); if (folio_test_hugetlb(folio)) { + bool anon = folio_test_anon(folio); + /* * huge_pmd_unshare may unmap an entire PMD page. * There is no way of knowing exactly which PMDs may @@ -1930,31 +1929,28 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, */ flush_cache_range(vma, range.start, range.end); - if (!folio_test_anon(folio)) { + /* + * To call huge_pmd_unshare, i_mmap_rwsem must be + * held in write mode. Caller needs to explicitly + * do this outside rmap routines. + */ + VM_BUG_ON(!anon && !(flags & TTU_RMAP_LOCKED)); + if (!anon && huge_pmd_unshare(mm, vma, address, pvmw.pte)) { + flush_tlb_range(vma, range.start, range.end); + mmu_notifier_invalidate_range(mm, range.start, + range.end); + /* - * To call huge_pmd_unshare, i_mmap_rwsem must be - * held in write mode. Caller needs to explicitly - * do this outside rmap routines. + * The ref count of the PMD page was dropped + * which is part of the way map counting + * is done for shared PMDs. Return 'true' + * here. When there is no other sharing, + * huge_pmd_unshare returns false and we will + * unmap the actual page and drop map count + * to zero. */ - VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); - - if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) { - flush_tlb_range(vma, range.start, range.end); - mmu_notifier_invalidate_range(mm, range.start, - range.end); - - /* - * The ref count of the PMD page was dropped - * which is part of the way map counting - * is done for shared PMDs. Return 'true' - * here. When there is no other sharing, - * huge_pmd_unshare returns false and we will - * unmap the actual page and drop map count - * to zero. - */ - page_vma_mapped_walk_done(&pvmw); - break; - } + page_vma_mapped_walk_done(&pvmw); + break; } /* Nuke the hugetlb page table entry */ @@ -1972,7 +1968,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, /* Update high watermark before we lower rss */ update_hiwater_rss(mm); - if (folio_is_zone_device(folio)) { + if (folio_is_device_private(folio)) { unsigned long pfn = folio_pfn(folio); swp_entry_t entry; pte_t swp_pte; @@ -2013,9 +2009,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); - set_huge_swap_pte_at(mm, address, - pvmw.pte, pteval, - vma_mmu_pagesize(vma)); + set_huge_pte_at(mm, address, pvmw.pte, pteval); } else { dec_mm_counter(mm, mm_counter(&folio->page)); set_pte_at(mm, address, pvmw.pte, pteval); @@ -2083,8 +2077,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); if (folio_test_hugetlb(folio)) - set_huge_swap_pte_at(mm, address, pvmw.pte, - swp_pte, vma_mmu_pagesize(vma)); + set_huge_pte_at(mm, address, pvmw.pte, swp_pte); else set_pte_at(mm, address, pvmw.pte, swp_pte); trace_set_migration_pte(address, pte_val(swp_pte), @@ -2100,7 +2093,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, * done above for all cases requiring it to happen under page * table lock before mmu_notifier_invalidate_range_end() * - * See Documentation/vm/mmu_notifier.rst + * See Documentation/mm/mmu_notifier.rst */ page_remove_rmap(subpage, vma, folio_test_hugetlb(folio)); if (vma->vm_flags & VM_LOCKED) @@ -2138,7 +2131,8 @@ void try_to_migrate(struct folio *folio, enum ttu_flags flags) TTU_SYNC))) return; - if (folio_is_zone_device(folio) && !folio_is_device_private(folio)) + if (folio_is_zone_device(folio) && + (!folio_is_device_private(folio) && !folio_is_device_coherent(folio))) return; /* diff --git a/mm/shmem.c b/mm/shmem.c index e5e43b990fdc..e975fcd9d2e1 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -28,6 +28,7 @@ #include <linux/ramfs.h> #include <linux/pagemap.h> #include <linux/file.h> +#include <linux/fileattr.h> #include <linux/mm.h> #include <linux/random.h> #include <linux/sched/signal.h> @@ -1057,6 +1058,15 @@ static int shmem_getattr(struct user_namespace *mnt_userns, shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); } + if (info->fsflags & FS_APPEND_FL) + stat->attributes |= STATX_ATTR_APPEND; + if (info->fsflags & FS_IMMUTABLE_FL) + stat->attributes |= STATX_ATTR_IMMUTABLE; + if (info->fsflags & FS_NODUMP_FL) + stat->attributes |= STATX_ATTR_NODUMP; + stat->attributes_mask |= (STATX_ATTR_APPEND | + STATX_ATTR_IMMUTABLE | + STATX_ATTR_NODUMP); generic_fillattr(&init_user_ns, inode, stat); if (shmem_is_huge(NULL, inode, 0)) @@ -1690,7 +1700,7 @@ static void shmem_set_folio_swapin_error(struct inode *inode, pgoff_t index, return; folio_wait_writeback(folio); - delete_from_swap_cache(&folio->page); + delete_from_swap_cache(folio); spin_lock_irq(&info->lock); /* * Don't treat swapin error folio as alloced. Otherwise inode->i_blocks won't @@ -1705,10 +1715,10 @@ static void shmem_set_folio_swapin_error(struct inode *inode, pgoff_t index, } /* - * Swap in the page pointed to by *pagep. - * Caller has to make sure that *pagep contains a valid swapped page. - * Returns 0 and the page in pagep if success. On failure, returns the - * error code and NULL in *pagep. + * Swap in the folio pointed to by *foliop. + * Caller has to make sure that *foliop contains a valid swapped folio. + * Returns 0 and the folio in foliop if success. On failure, returns the + * error code and NULL in *foliop. */ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, struct folio **foliop, enum sgp_type sgp, @@ -1748,7 +1758,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, } folio = page_folio(page); - /* We have to do this with page locked to prevent races */ + /* We have to do this with folio locked to prevent races */ folio_lock(folio); if (!folio_test_swapcache(folio) || folio_swap_entry(folio).val != swap.val || @@ -1788,7 +1798,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, if (sgp == SGP_WRITE) folio_mark_accessed(folio); - delete_from_swap_cache(&folio->page); + delete_from_swap_cache(folio); folio_mark_dirty(folio); swap_free(swap); @@ -2271,7 +2281,18 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma) return 0; } -static struct inode *shmem_get_inode(struct super_block *sb, const struct inode *dir, +/* Mask out flags that are inappropriate for the given type of inode. */ +static unsigned shmem_mask_flags(umode_t mode, __u32 flags) +{ + if (S_ISDIR(mode)) + return flags; + else if (S_ISREG(mode)) + return flags & SHMEM_REG_FLMASK; + else + return flags & SHMEM_OTHER_FLMASK; +} + +static struct inode *shmem_get_inode(struct super_block *sb, struct inode *dir, umode_t mode, dev_t dev, unsigned long flags) { struct inode *inode; @@ -2296,6 +2317,9 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode info->seals = F_SEAL_SEAL; info->flags = flags & VM_NORESERVE; info->i_crtime = inode->i_mtime; + info->fsflags = (dir == NULL) ? 0 : + SHMEM_I(dir)->fsflags & SHMEM_FL_INHERITED; + info->fsflags = shmem_mask_flags(mode, info->fsflags); INIT_LIST_HEAD(&info->shrinklist); INIT_LIST_HEAD(&info->swaplist); simple_xattrs_init(&info->xattrs); @@ -3137,6 +3161,40 @@ static const char *shmem_get_link(struct dentry *dentry, } #ifdef CONFIG_TMPFS_XATTR + +static int shmem_fileattr_get(struct dentry *dentry, struct fileattr *fa) +{ + struct shmem_inode_info *info = SHMEM_I(d_inode(dentry)); + + fileattr_fill_flags(fa, info->fsflags & SHMEM_FL_USER_VISIBLE); + + return 0; +} + +static int shmem_fileattr_set(struct user_namespace *mnt_userns, + struct dentry *dentry, struct fileattr *fa) +{ + struct inode *inode = d_inode(dentry); + struct shmem_inode_info *info = SHMEM_I(inode); + + if (fileattr_has_fsx(fa)) + return -EOPNOTSUPP; + + info->fsflags = (info->fsflags & ~SHMEM_FL_USER_MODIFIABLE) | + (fa->flags & SHMEM_FL_USER_MODIFIABLE); + + inode->i_flags &= ~(S_APPEND | S_IMMUTABLE | S_NOATIME); + if (info->fsflags & FS_APPEND_FL) + inode->i_flags |= S_APPEND; + if (info->fsflags & FS_IMMUTABLE_FL) + inode->i_flags |= S_IMMUTABLE; + if (info->fsflags & FS_NOATIME_FL) + inode->i_flags |= S_NOATIME; + + inode->i_ctime = current_time(inode); + return 0; +} + /* * Superblocks without xattr inode operations may get some security.* xattr * support from the LSM "for free". As soon as we have any other xattrs @@ -3824,6 +3882,8 @@ static const struct inode_operations shmem_inode_operations = { #ifdef CONFIG_TMPFS_XATTR .listxattr = shmem_listxattr, .set_acl = simple_set_acl, + .fileattr_get = shmem_fileattr_get, + .fileattr_set = shmem_fileattr_set, #endif }; @@ -3843,6 +3903,8 @@ static const struct inode_operations shmem_dir_inode_operations = { #endif #ifdef CONFIG_TMPFS_XATTR .listxattr = shmem_listxattr, + .fileattr_get = shmem_fileattr_get, + .fileattr_set = shmem_fileattr_set, #endif #ifdef CONFIG_TMPFS_POSIX_ACL .setattr = shmem_setattr, diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c new file mode 100644 index 000000000000..b05295bab322 --- /dev/null +++ b/mm/shrinker_debug.c @@ -0,0 +1,286 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/idr.h> +#include <linux/slab.h> +#include <linux/debugfs.h> +#include <linux/seq_file.h> +#include <linux/shrinker.h> +#include <linux/memcontrol.h> + +/* defined in vmscan.c */ +extern struct rw_semaphore shrinker_rwsem; +extern struct list_head shrinker_list; + +static DEFINE_IDA(shrinker_debugfs_ida); +static struct dentry *shrinker_debugfs_root; + +static unsigned long shrinker_count_objects(struct shrinker *shrinker, + struct mem_cgroup *memcg, + unsigned long *count_per_node) +{ + unsigned long nr, total = 0; + int nid; + + for_each_node(nid) { + if (nid == 0 || (shrinker->flags & SHRINKER_NUMA_AWARE)) { + struct shrink_control sc = { + .gfp_mask = GFP_KERNEL, + .nid = nid, + .memcg = memcg, + }; + + nr = shrinker->count_objects(shrinker, &sc); + if (nr == SHRINK_EMPTY) + nr = 0; + } else { + nr = 0; + } + + count_per_node[nid] = nr; + total += nr; + } + + return total; +} + +static int shrinker_debugfs_count_show(struct seq_file *m, void *v) +{ + struct shrinker *shrinker = m->private; + unsigned long *count_per_node; + struct mem_cgroup *memcg; + unsigned long total; + bool memcg_aware; + int ret, nid; + + count_per_node = kcalloc(nr_node_ids, sizeof(unsigned long), GFP_KERNEL); + if (!count_per_node) + return -ENOMEM; + + ret = down_read_killable(&shrinker_rwsem); + if (ret) { + kfree(count_per_node); + return ret; + } + rcu_read_lock(); + + memcg_aware = shrinker->flags & SHRINKER_MEMCG_AWARE; + + memcg = mem_cgroup_iter(NULL, NULL, NULL); + do { + if (memcg && !mem_cgroup_online(memcg)) + continue; + + total = shrinker_count_objects(shrinker, + memcg_aware ? memcg : NULL, + count_per_node); + if (total) { + seq_printf(m, "%lu", mem_cgroup_ino(memcg)); + for_each_node(nid) + seq_printf(m, " %lu", count_per_node[nid]); + seq_putc(m, '\n'); + } + + if (!memcg_aware) { + mem_cgroup_iter_break(NULL, memcg); + break; + } + + if (signal_pending(current)) { + mem_cgroup_iter_break(NULL, memcg); + ret = -EINTR; + break; + } + } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); + + rcu_read_unlock(); + up_read(&shrinker_rwsem); + + kfree(count_per_node); + return ret; +} +DEFINE_SHOW_ATTRIBUTE(shrinker_debugfs_count); + +static int shrinker_debugfs_scan_open(struct inode *inode, struct file *file) +{ + file->private_data = inode->i_private; + return nonseekable_open(inode, file); +} + +static ssize_t shrinker_debugfs_scan_write(struct file *file, + const char __user *buf, + size_t size, loff_t *pos) +{ + struct shrinker *shrinker = file->private_data; + unsigned long nr_to_scan = 0, ino, read_len; + struct shrink_control sc = { + .gfp_mask = GFP_KERNEL, + }; + struct mem_cgroup *memcg = NULL; + int nid; + char kbuf[72]; + ssize_t ret; + + read_len = size < (sizeof(kbuf) - 1) ? size : (sizeof(kbuf) - 1); + if (copy_from_user(kbuf, buf, read_len)) + return -EFAULT; + kbuf[read_len] = '\0'; + + if (sscanf(kbuf, "%lu %d %lu", &ino, &nid, &nr_to_scan) != 3) + return -EINVAL; + + if (nid < 0 || nid >= nr_node_ids) + return -EINVAL; + + if (nr_to_scan == 0) + return size; + + if (shrinker->flags & SHRINKER_MEMCG_AWARE) { + memcg = mem_cgroup_get_from_ino(ino); + if (!memcg || IS_ERR(memcg)) + return -ENOENT; + + if (!mem_cgroup_online(memcg)) { + mem_cgroup_put(memcg); + return -ENOENT; + } + } else if (ino != 0) { + return -EINVAL; + } + + ret = down_read_killable(&shrinker_rwsem); + if (ret) { + mem_cgroup_put(memcg); + return ret; + } + + sc.nid = nid; + sc.memcg = memcg; + sc.nr_to_scan = nr_to_scan; + sc.nr_scanned = nr_to_scan; + + shrinker->scan_objects(shrinker, &sc); + + up_read(&shrinker_rwsem); + mem_cgroup_put(memcg); + + return size; +} + +static const struct file_operations shrinker_debugfs_scan_fops = { + .owner = THIS_MODULE, + .open = shrinker_debugfs_scan_open, + .write = shrinker_debugfs_scan_write, +}; + +int shrinker_debugfs_add(struct shrinker *shrinker) +{ + struct dentry *entry; + char buf[128]; + int id; + + lockdep_assert_held(&shrinker_rwsem); + + /* debugfs isn't initialized yet, add debugfs entries later. */ + if (!shrinker_debugfs_root) + return 0; + + id = ida_alloc(&shrinker_debugfs_ida, GFP_KERNEL); + if (id < 0) + return id; + shrinker->debugfs_id = id; + + snprintf(buf, sizeof(buf), "%s-%d", shrinker->name, id); + + /* create debugfs entry */ + entry = debugfs_create_dir(buf, shrinker_debugfs_root); + if (IS_ERR(entry)) { + ida_free(&shrinker_debugfs_ida, id); + return PTR_ERR(entry); + } + shrinker->debugfs_entry = entry; + + debugfs_create_file("count", 0220, entry, shrinker, + &shrinker_debugfs_count_fops); + debugfs_create_file("scan", 0440, entry, shrinker, + &shrinker_debugfs_scan_fops); + return 0; +} + +int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) +{ + struct dentry *entry; + char buf[128]; + const char *new, *old; + va_list ap; + int ret = 0; + + va_start(ap, fmt); + new = kvasprintf_const(GFP_KERNEL, fmt, ap); + va_end(ap); + + if (!new) + return -ENOMEM; + + down_write(&shrinker_rwsem); + + old = shrinker->name; + shrinker->name = new; + + if (shrinker->debugfs_entry) { + snprintf(buf, sizeof(buf), "%s-%d", shrinker->name, + shrinker->debugfs_id); + + entry = debugfs_rename(shrinker_debugfs_root, + shrinker->debugfs_entry, + shrinker_debugfs_root, buf); + if (IS_ERR(entry)) + ret = PTR_ERR(entry); + else + shrinker->debugfs_entry = entry; + } + + up_write(&shrinker_rwsem); + + kfree_const(old); + + return ret; +} +EXPORT_SYMBOL(shrinker_debugfs_rename); + +void shrinker_debugfs_remove(struct shrinker *shrinker) +{ + lockdep_assert_held(&shrinker_rwsem); + + kfree_const(shrinker->name); + shrinker->name = NULL; + + if (!shrinker->debugfs_entry) + return; + + debugfs_remove_recursive(shrinker->debugfs_entry); + ida_free(&shrinker_debugfs_ida, shrinker->debugfs_id); +} + +static int __init shrinker_debugfs_init(void) +{ + struct shrinker *shrinker; + struct dentry *dentry; + int ret = 0; + + dentry = debugfs_create_dir("shrinker", NULL); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + shrinker_debugfs_root = dentry; + + /* Create debugfs entries for shrinkers registered at boot */ + down_write(&shrinker_rwsem); + list_for_each_entry(shrinker, &shrinker_list, list) + if (!shrinker->debugfs_entry) { + ret = shrinker_debugfs_add(shrinker); + if (ret) + break; + } + up_write(&shrinker_rwsem); + + return ret; +} +late_initcall(shrinker_debugfs_init); diff --git a/mm/slab.c b/mm/slab.c index 5e73e2d80222..10e96137b44f 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2958,12 +2958,6 @@ direct_grow: return ac->entry[--ac->avail]; } -static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep, - gfp_t flags) -{ - might_sleep_if(gfpflags_allow_blocking(flags)); -} - #if DEBUG static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, gfp_t flags, void *objp, unsigned long caller) @@ -3205,7 +3199,6 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, size_t orig_ if (unlikely(ptr)) goto out_hooks; - cache_alloc_debugcheck_before(cachep, flags); local_irq_save(save_flags); if (nodeid == NUMA_NO_NODE) @@ -3290,7 +3283,6 @@ slab_alloc(struct kmem_cache *cachep, struct list_lru *lru, gfp_t flags, if (unlikely(objp)) goto out; - cache_alloc_debugcheck_before(cachep, flags); local_irq_save(save_flags); objp = __do_cache_alloc(cachep, flags); local_irq_restore(save_flags); @@ -3527,8 +3519,6 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, if (!s) return 0; - cache_alloc_debugcheck_before(s, flags); - local_irq_disable(); for (i = 0; i < size; i++) { void *objp = kfence_alloc(s, s->object_size, flags) ?: __do_cache_alloc(s, flags); diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 3f7e4bd34a5b..5f0ed4717ed0 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -208,8 +208,8 @@ static int vmemmap_remap_range(unsigned long start, unsigned long end, unsigned long next; pgd_t *pgd; - VM_BUG_ON(!IS_ALIGNED(start, PAGE_SIZE)); - VM_BUG_ON(!IS_ALIGNED(end, PAGE_SIZE)); + VM_BUG_ON(!PAGE_ALIGNED(start)); + VM_BUG_ON(!PAGE_ALIGNED(end)); pgd = pgd_offset_k(addr); do { @@ -556,7 +556,7 @@ pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, } else { /* * When a PTE/PMD entry is freed from the init_mm - * there's a a free_pages() call to this page allocated + * there's a free_pages() call to this page allocated * above. Thus this get_page() is paired with the * put_page_testzero() on the freeing path. * This can only called by certain ZONE_DEVICE path, @@ -745,7 +745,7 @@ static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn, size = min(end - start, pgmap_vmemmap_nr(pgmap) * sizeof(struct page)); for (addr = start; addr < end; addr += size) { - unsigned long next = addr, last = addr + size; + unsigned long next, last = addr + size; /* Populate the head page vmemmap page */ pte = vmemmap_populate_address(addr, node, NULL, NULL); @@ -760,7 +760,7 @@ static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn, /* * Reuse the previous page for the rest of tail pages - * See layout diagram in Documentation/vm/vmemmap_dedup.rst + * See layout diagram in Documentation/mm/vmemmap_dedup.rst */ next += PAGE_SIZE; rc = vmemmap_populate_range(next, last, node, NULL, diff --git a/mm/sparse.c b/mm/sparse.c index cb3bfae64036..e5a8a3a0edd7 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -281,7 +281,7 @@ static unsigned long sparse_encode_mem_map(struct page *mem_map, unsigned long p { unsigned long coded_mem_map = (unsigned long)(mem_map - (section_nr_to_pfn(pnum))); - BUILD_BUG_ON(SECTION_MAP_LAST_BIT > (1UL<<PFN_SECTION_SHIFT)); + BUILD_BUG_ON(SECTION_MAP_LAST_BIT > PFN_SECTION_SHIFT); BUG_ON(coded_mem_map & ~SECTION_MAP_MASK); return coded_mem_map; } diff --git a/mm/swap.c b/mm/swap.c index 275a4ea1bc66..9cee7f6a3809 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -46,30 +46,30 @@ /* How many pages do we try to swap or page in/out together? */ int page_cluster; -/* Protecting only lru_rotate.pvec which requires disabling interrupts */ +/* Protecting only lru_rotate.fbatch which requires disabling interrupts */ struct lru_rotate { local_lock_t lock; - struct pagevec pvec; + struct folio_batch fbatch; }; static DEFINE_PER_CPU(struct lru_rotate, lru_rotate) = { .lock = INIT_LOCAL_LOCK(lock), }; /* - * The following struct pagevec are grouped together because they are protected + * The following folio batches are grouped together because they are protected * by disabling preemption (and interrupts remain enabled). */ -struct lru_pvecs { +struct cpu_fbatches { local_lock_t lock; - struct pagevec lru_add; - struct pagevec lru_deactivate_file; - struct pagevec lru_deactivate; - struct pagevec lru_lazyfree; + struct folio_batch lru_add; + struct folio_batch lru_deactivate_file; + struct folio_batch lru_deactivate; + struct folio_batch lru_lazyfree; #ifdef CONFIG_SMP - struct pagevec activate_page; + struct folio_batch activate; #endif }; -static DEFINE_PER_CPU(struct lru_pvecs, lru_pvecs) = { +static DEFINE_PER_CPU(struct cpu_fbatches, cpu_fbatches) = { .lock = INIT_LOCAL_LOCK(lock), }; @@ -77,36 +77,35 @@ static DEFINE_PER_CPU(struct lru_pvecs, lru_pvecs) = { * This path almost never happens for VM activity - pages are normally freed * via pagevecs. But it gets used by networking - and for compound pages. */ -static void __page_cache_release(struct page *page) +static void __page_cache_release(struct folio *folio) { - if (PageLRU(page)) { - struct folio *folio = page_folio(page); + if (folio_test_lru(folio)) { struct lruvec *lruvec; unsigned long flags; lruvec = folio_lruvec_lock_irqsave(folio, &flags); - del_page_from_lru_list(page, lruvec); - __clear_page_lru_flags(page); + lruvec_del_folio(lruvec, folio); + __folio_clear_lru_flags(folio); unlock_page_lruvec_irqrestore(lruvec, flags); } - /* See comment on PageMlocked in release_pages() */ - if (unlikely(PageMlocked(page))) { - int nr_pages = thp_nr_pages(page); + /* See comment on folio_test_mlocked in release_pages() */ + if (unlikely(folio_test_mlocked(folio))) { + long nr_pages = folio_nr_pages(folio); - __ClearPageMlocked(page); - mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages); + __folio_clear_mlocked(folio); + zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages); count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages); } } -static void __put_single_page(struct page *page) +static void __folio_put_small(struct folio *folio) { - __page_cache_release(page); - mem_cgroup_uncharge(page_folio(page)); - free_unref_page(page, 0); + __page_cache_release(folio); + mem_cgroup_uncharge(folio); + free_unref_page(&folio->page, 0); } -static void __put_compound_page(struct page *page) +static void __folio_put_large(struct folio *folio) { /* * __page_cache_release() is supposed to be called for thp, not for @@ -114,21 +113,21 @@ static void __put_compound_page(struct page *page) * (it's never listed to any LRU lists) and no memcg routines should * be called for hugetlb (it has a separate hugetlb_cgroup.) */ - if (!PageHuge(page)) - __page_cache_release(page); - destroy_compound_page(page); + if (!folio_test_hugetlb(folio)) + __page_cache_release(folio); + destroy_large_folio(folio); } -void __put_page(struct page *page) +void __folio_put(struct folio *folio) { - if (unlikely(is_zone_device_page(page))) - free_zone_device_page(page); - else if (unlikely(PageCompound(page))) - __put_compound_page(page); + if (unlikely(folio_is_zone_device(folio))) + free_zone_device_page(&folio->page); + else if (unlikely(folio_test_large(folio))) + __folio_put_large(folio); else - __put_single_page(page); + __folio_put_small(folio); } -EXPORT_SYMBOL(__put_page); +EXPORT_SYMBOL(__folio_put); /** * put_pages_list() - release a list of pages @@ -138,19 +137,19 @@ EXPORT_SYMBOL(__put_page); */ void put_pages_list(struct list_head *pages) { - struct page *page, *next; + struct folio *folio, *next; - list_for_each_entry_safe(page, next, pages, lru) { - if (!put_page_testzero(page)) { - list_del(&page->lru); + list_for_each_entry_safe(folio, next, pages, lru) { + if (!folio_put_testzero(folio)) { + list_del(&folio->lru); continue; } - if (PageHead(page)) { - list_del(&page->lru); - __put_compound_page(page); + if (folio_test_large(folio)) { + list_del(&folio->lru); + __folio_put_large(folio); continue; } - /* Cannot be PageLRU because it's passed to us using the lru */ + /* LRU flag must be clear because it's passed using the lru */ } free_unref_page_list(pages); @@ -188,36 +187,84 @@ int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write, } EXPORT_SYMBOL_GPL(get_kernel_pages); -static void pagevec_lru_move_fn(struct pagevec *pvec, - void (*move_fn)(struct page *page, struct lruvec *lruvec)) +typedef void (*move_fn_t)(struct lruvec *lruvec, struct folio *folio); + +static void lru_add_fn(struct lruvec *lruvec, struct folio *folio) +{ + int was_unevictable = folio_test_clear_unevictable(folio); + long nr_pages = folio_nr_pages(folio); + + VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); + + /* + * Is an smp_mb__after_atomic() still required here, before + * folio_evictable() tests the mlocked flag, to rule out the possibility + * of stranding an evictable folio on an unevictable LRU? I think + * not, because __munlock_page() only clears the mlocked flag + * while the LRU lock is held. + * + * (That is not true of __page_cache_release(), and not necessarily + * true of release_pages(): but those only clear the mlocked flag after + * folio_put_testzero() has excluded any other users of the folio.) + */ + if (folio_evictable(folio)) { + if (was_unevictable) + __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); + } else { + folio_clear_active(folio); + folio_set_unevictable(folio); + /* + * folio->mlock_count = !!folio_test_mlocked(folio)? + * But that leaves __mlock_page() in doubt whether another + * actor has already counted the mlock or not. Err on the + * safe side, underestimate, let page reclaim fix it, rather + * than leaving a page on the unevictable LRU indefinitely. + */ + folio->mlock_count = 0; + if (!was_unevictable) + __count_vm_events(UNEVICTABLE_PGCULLED, nr_pages); + } + + lruvec_add_folio(lruvec, folio); + trace_mm_lru_insertion(folio); +} + +static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn) { int i; struct lruvec *lruvec = NULL; unsigned long flags = 0; - for (i = 0; i < pagevec_count(pvec); i++) { - struct page *page = pvec->pages[i]; - struct folio *folio = page_folio(page); + for (i = 0; i < folio_batch_count(fbatch); i++) { + struct folio *folio = fbatch->folios[i]; - /* block memcg migration during page moving between lru */ - if (!TestClearPageLRU(page)) + /* block memcg migration while the folio moves between lru */ + if (move_fn != lru_add_fn && !folio_test_clear_lru(folio)) continue; lruvec = folio_lruvec_relock_irqsave(folio, lruvec, &flags); - (*move_fn)(page, lruvec); + move_fn(lruvec, folio); - SetPageLRU(page); + folio_set_lru(folio); } + if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); - release_pages(pvec->pages, pvec->nr); - pagevec_reinit(pvec); + folios_put(fbatch->folios, folio_batch_count(fbatch)); + folio_batch_init(fbatch); } -static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec) +static void folio_batch_add_and_move(struct folio_batch *fbatch, + struct folio *folio, move_fn_t move_fn) { - struct folio *folio = page_folio(page); + if (folio_batch_add(fbatch, folio) && !folio_test_large(folio) && + !lru_cache_disabled()) + return; + folio_batch_move_lru(fbatch, move_fn); +} +static void lru_move_tail_fn(struct lruvec *lruvec, struct folio *folio) +{ if (!folio_test_unevictable(folio)) { lruvec_del_folio(lruvec, folio); folio_clear_active(folio); @@ -226,18 +273,6 @@ static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec) } } -/* return true if pagevec needs to drain */ -static bool pagevec_add_and_need_flush(struct pagevec *pvec, struct page *page) -{ - bool ret = false; - - if (!pagevec_add(pvec, page) || PageCompound(page) || - lru_cache_disabled()) - ret = true; - - return ret; -} - /* * Writeback is about to end against a folio which has been marked for * immediate reclaim. If it still appears to be reclaimable, move it @@ -249,14 +284,13 @@ void folio_rotate_reclaimable(struct folio *folio) { if (!folio_test_locked(folio) && !folio_test_dirty(folio) && !folio_test_unevictable(folio) && folio_test_lru(folio)) { - struct pagevec *pvec; + struct folio_batch *fbatch; unsigned long flags; folio_get(folio); local_lock_irqsave(&lru_rotate.lock, flags); - pvec = this_cpu_ptr(&lru_rotate.pvec); - if (pagevec_add_and_need_flush(pvec, &folio->page)) - pagevec_lru_move_fn(pvec, pagevec_move_tail_fn); + fbatch = this_cpu_ptr(&lru_rotate.fbatch); + folio_batch_add_and_move(fbatch, folio, lru_move_tail_fn); local_unlock_irqrestore(&lru_rotate.lock, flags); } } @@ -307,7 +341,7 @@ void lru_note_cost_folio(struct folio *folio) folio_nr_pages(folio)); } -static void __folio_activate(struct folio *folio, struct lruvec *lruvec) +static void folio_activate_fn(struct lruvec *lruvec, struct folio *folio) { if (!folio_test_active(folio) && !folio_test_unevictable(folio)) { long nr_pages = folio_nr_pages(folio); @@ -324,41 +358,30 @@ static void __folio_activate(struct folio *folio, struct lruvec *lruvec) } #ifdef CONFIG_SMP -static void __activate_page(struct page *page, struct lruvec *lruvec) -{ - return __folio_activate(page_folio(page), lruvec); -} - -static void activate_page_drain(int cpu) +static void folio_activate_drain(int cpu) { - struct pagevec *pvec = &per_cpu(lru_pvecs.activate_page, cpu); + struct folio_batch *fbatch = &per_cpu(cpu_fbatches.activate, cpu); - if (pagevec_count(pvec)) - pagevec_lru_move_fn(pvec, __activate_page); -} - -static bool need_activate_page_drain(int cpu) -{ - return pagevec_count(&per_cpu(lru_pvecs.activate_page, cpu)) != 0; + if (folio_batch_count(fbatch)) + folio_batch_move_lru(fbatch, folio_activate_fn); } static void folio_activate(struct folio *folio) { if (folio_test_lru(folio) && !folio_test_active(folio) && !folio_test_unevictable(folio)) { - struct pagevec *pvec; + struct folio_batch *fbatch; folio_get(folio); - local_lock(&lru_pvecs.lock); - pvec = this_cpu_ptr(&lru_pvecs.activate_page); - if (pagevec_add_and_need_flush(pvec, &folio->page)) - pagevec_lru_move_fn(pvec, __activate_page); - local_unlock(&lru_pvecs.lock); + local_lock(&cpu_fbatches.lock); + fbatch = this_cpu_ptr(&cpu_fbatches.activate); + folio_batch_add_and_move(fbatch, folio, folio_activate_fn); + local_unlock(&cpu_fbatches.lock); } } #else -static inline void activate_page_drain(int cpu) +static inline void folio_activate_drain(int cpu) { } @@ -368,7 +391,7 @@ static void folio_activate(struct folio *folio) if (folio_test_clear_lru(folio)) { lruvec = folio_lruvec_lock_irq(folio); - __folio_activate(folio, lruvec); + folio_activate_fn(lruvec, folio); unlock_page_lruvec_irq(lruvec); folio_set_lru(folio); } @@ -377,32 +400,32 @@ static void folio_activate(struct folio *folio) static void __lru_cache_activate_folio(struct folio *folio) { - struct pagevec *pvec; + struct folio_batch *fbatch; int i; - local_lock(&lru_pvecs.lock); - pvec = this_cpu_ptr(&lru_pvecs.lru_add); + local_lock(&cpu_fbatches.lock); + fbatch = this_cpu_ptr(&cpu_fbatches.lru_add); /* - * Search backwards on the optimistic assumption that the page being - * activated has just been added to this pagevec. Note that only - * the local pagevec is examined as a !PageLRU page could be in the + * Search backwards on the optimistic assumption that the folio being + * activated has just been added to this batch. Note that only + * the local batch is examined as a !LRU folio could be in the * process of being released, reclaimed, migrated or on a remote - * pagevec that is currently being drained. Furthermore, marking - * a remote pagevec's page PageActive potentially hits a race where - * a page is marked PageActive just after it is added to the inactive + * batch that is currently being drained. Furthermore, marking + * a remote batch's folio active potentially hits a race where + * a folio is marked active just after it is added to the inactive * list causing accounting errors and BUG_ON checks to trigger. */ - for (i = pagevec_count(pvec) - 1; i >= 0; i--) { - struct page *pagevec_page = pvec->pages[i]; + for (i = folio_batch_count(fbatch) - 1; i >= 0; i--) { + struct folio *batch_folio = fbatch->folios[i]; - if (pagevec_page == &folio->page) { + if (batch_folio == folio) { folio_set_active(folio); break; } } - local_unlock(&lru_pvecs.lock); + local_unlock(&cpu_fbatches.lock); } /* @@ -427,9 +450,9 @@ void folio_mark_accessed(struct folio *folio) */ } else if (!folio_test_active(folio)) { /* - * If the page is on the LRU, queue it for activation via - * lru_pvecs.activate_page. Otherwise, assume the page is on a - * pagevec, mark it active and it'll be moved to the active + * If the folio is on the LRU, queue it for activation via + * cpu_fbatches.activate. Otherwise, assume the folio is in a + * folio_batch, mark it active and it'll be moved to the active * LRU on the next drain. */ if (folio_test_lru(folio)) @@ -450,22 +473,22 @@ EXPORT_SYMBOL(folio_mark_accessed); * * Queue the folio for addition to the LRU. The decision on whether * to add the page to the [in]active [file|anon] list is deferred until the - * pagevec is drained. This gives a chance for the caller of folio_add_lru() + * folio_batch is drained. This gives a chance for the caller of folio_add_lru() * have the folio added to the active list using folio_mark_accessed(). */ void folio_add_lru(struct folio *folio) { - struct pagevec *pvec; + struct folio_batch *fbatch; - VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); + VM_BUG_ON_FOLIO(folio_test_active(folio) && + folio_test_unevictable(folio), folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); folio_get(folio); - local_lock(&lru_pvecs.lock); - pvec = this_cpu_ptr(&lru_pvecs.lru_add); - if (pagevec_add_and_need_flush(pvec, &folio->page)) - __pagevec_lru_add(pvec); - local_unlock(&lru_pvecs.lock); + local_lock(&cpu_fbatches.lock); + fbatch = this_cpu_ptr(&cpu_fbatches.lru_add); + folio_batch_add_and_move(fbatch, folio, lru_add_fn); + local_unlock(&cpu_fbatches.lock); } EXPORT_SYMBOL(folio_add_lru); @@ -489,56 +512,57 @@ void lru_cache_add_inactive_or_unevictable(struct page *page, } /* - * If the page can not be invalidated, it is moved to the + * If the folio cannot be invalidated, it is moved to the * inactive list to speed up its reclaim. It is moved to the * head of the list, rather than the tail, to give the flusher * threads some time to write it out, as this is much more * effective than the single-page writeout from reclaim. * - * If the page isn't page_mapped and dirty/writeback, the page - * could reclaim asap using PG_reclaim. + * If the folio isn't mapped and dirty/writeback, the folio + * could be reclaimed asap using the reclaim flag. * - * 1. active, mapped page -> none - * 2. active, dirty/writeback page -> inactive, head, PG_reclaim - * 3. inactive, mapped page -> none - * 4. inactive, dirty/writeback page -> inactive, head, PG_reclaim + * 1. active, mapped folio -> none + * 2. active, dirty/writeback folio -> inactive, head, reclaim + * 3. inactive, mapped folio -> none + * 4. inactive, dirty/writeback folio -> inactive, head, reclaim * 5. inactive, clean -> inactive, tail * 6. Others -> none * - * In 4, why it moves inactive's head, the VM expects the page would - * be write it out by flusher threads as this is much more effective + * In 4, it moves to the head of the inactive list so the folio is + * written out by flusher threads as this is much more efficient * than the single-page writeout from reclaim. */ -static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec) +static void lru_deactivate_file_fn(struct lruvec *lruvec, struct folio *folio) { - bool active = PageActive(page); - int nr_pages = thp_nr_pages(page); + bool active = folio_test_active(folio); + long nr_pages = folio_nr_pages(folio); - if (PageUnevictable(page)) + if (folio_test_unevictable(folio)) return; - /* Some processes are using the page */ - if (page_mapped(page)) + /* Some processes are using the folio */ + if (folio_mapped(folio)) return; - del_page_from_lru_list(page, lruvec); - ClearPageActive(page); - ClearPageReferenced(page); + lruvec_del_folio(lruvec, folio); + folio_clear_active(folio); + folio_clear_referenced(folio); - if (PageWriteback(page) || PageDirty(page)) { + if (folio_test_writeback(folio) || folio_test_dirty(folio)) { /* - * PG_reclaim could be raced with end_page_writeback - * It can make readahead confusing. But race window - * is _really_ small and it's non-critical problem. + * Setting the reclaim flag could race with + * folio_end_writeback() and confuse readahead. But the + * race window is _really_ small and it's not a critical + * problem. */ - add_page_to_lru_list(page, lruvec); - SetPageReclaim(page); + lruvec_add_folio(lruvec, folio); + folio_set_reclaim(folio); } else { /* - * The page's writeback ends up during pagevec - * We move that page into tail of inactive. + * The folio's writeback ended while it was in the batch. + * We move that folio to the tail of the inactive list. */ - add_page_to_lru_list_tail(page, lruvec); + lruvec_add_folio_tail(lruvec, folio); __count_vm_events(PGROTATED, nr_pages); } @@ -549,15 +573,15 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec) } } -static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec) +static void lru_deactivate_fn(struct lruvec *lruvec, struct folio *folio) { - if (PageActive(page) && !PageUnevictable(page)) { - int nr_pages = thp_nr_pages(page); + if (folio_test_active(folio) && !folio_test_unevictable(folio)) { + long nr_pages = folio_nr_pages(folio); - del_page_from_lru_list(page, lruvec); - ClearPageActive(page); - ClearPageReferenced(page); - add_page_to_lru_list(page, lruvec); + lruvec_del_folio(lruvec, folio); + folio_clear_active(folio); + folio_clear_referenced(folio); + lruvec_add_folio(lruvec, folio); __count_vm_events(PGDEACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, @@ -565,22 +589,22 @@ static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec) } } -static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec) +static void lru_lazyfree_fn(struct lruvec *lruvec, struct folio *folio) { - if (PageAnon(page) && PageSwapBacked(page) && - !PageSwapCache(page) && !PageUnevictable(page)) { - int nr_pages = thp_nr_pages(page); + if (folio_test_anon(folio) && folio_test_swapbacked(folio) && + !folio_test_swapcache(folio) && !folio_test_unevictable(folio)) { + long nr_pages = folio_nr_pages(folio); - del_page_from_lru_list(page, lruvec); - ClearPageActive(page); - ClearPageReferenced(page); + lruvec_del_folio(lruvec, folio); + folio_clear_active(folio); + folio_clear_referenced(folio); /* - * Lazyfree pages are clean anonymous pages. They have - * PG_swapbacked flag cleared, to distinguish them from normal - * anonymous pages + * Lazyfree folios are clean anonymous folios. They have + * the swapbacked flag cleared, to distinguish them from normal + * anonymous folios */ - ClearPageSwapBacked(page); - add_page_to_lru_list(page, lruvec); + folio_clear_swapbacked(folio); + lruvec_add_folio(lruvec, folio); __count_vm_events(PGLAZYFREE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, @@ -589,71 +613,67 @@ static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec) } /* - * Drain pages out of the cpu's pagevecs. + * Drain pages out of the cpu's folio_batch. * Either "cpu" is the current CPU, and preemption has already been * disabled; or "cpu" is being hot-unplugged, and is already dead. */ void lru_add_drain_cpu(int cpu) { - struct pagevec *pvec = &per_cpu(lru_pvecs.lru_add, cpu); + struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu); + struct folio_batch *fbatch = &fbatches->lru_add; - if (pagevec_count(pvec)) - __pagevec_lru_add(pvec); + if (folio_batch_count(fbatch)) + folio_batch_move_lru(fbatch, lru_add_fn); - pvec = &per_cpu(lru_rotate.pvec, cpu); + fbatch = &per_cpu(lru_rotate.fbatch, cpu); /* Disabling interrupts below acts as a compiler barrier. */ - if (data_race(pagevec_count(pvec))) { + if (data_race(folio_batch_count(fbatch))) { unsigned long flags; /* No harm done if a racing interrupt already did this */ local_lock_irqsave(&lru_rotate.lock, flags); - pagevec_lru_move_fn(pvec, pagevec_move_tail_fn); + folio_batch_move_lru(fbatch, lru_move_tail_fn); local_unlock_irqrestore(&lru_rotate.lock, flags); } - pvec = &per_cpu(lru_pvecs.lru_deactivate_file, cpu); - if (pagevec_count(pvec)) - pagevec_lru_move_fn(pvec, lru_deactivate_file_fn); + fbatch = &fbatches->lru_deactivate_file; + if (folio_batch_count(fbatch)) + folio_batch_move_lru(fbatch, lru_deactivate_file_fn); - pvec = &per_cpu(lru_pvecs.lru_deactivate, cpu); - if (pagevec_count(pvec)) - pagevec_lru_move_fn(pvec, lru_deactivate_fn); + fbatch = &fbatches->lru_deactivate; + if (folio_batch_count(fbatch)) + folio_batch_move_lru(fbatch, lru_deactivate_fn); - pvec = &per_cpu(lru_pvecs.lru_lazyfree, cpu); - if (pagevec_count(pvec)) - pagevec_lru_move_fn(pvec, lru_lazyfree_fn); + fbatch = &fbatches->lru_lazyfree; + if (folio_batch_count(fbatch)) + folio_batch_move_lru(fbatch, lru_lazyfree_fn); - activate_page_drain(cpu); + folio_activate_drain(cpu); } /** - * deactivate_file_folio() - Forcefully deactivate a file folio. + * deactivate_file_folio() - Deactivate a file folio. * @folio: Folio to deactivate. * * This function hints to the VM that @folio is a good reclaim candidate, * for example if its invalidation fails due to the folio being dirty * or under writeback. * - * Context: Caller holds a reference on the page. + * Context: Caller holds a reference on the folio. */ void deactivate_file_folio(struct folio *folio) { - struct pagevec *pvec; + struct folio_batch *fbatch; - /* - * In a workload with many unevictable pages such as mprotect, - * unevictable folio deactivation for accelerating reclaim is pointless. - */ + /* Deactivating an unevictable folio will not accelerate reclaim */ if (folio_test_unevictable(folio)) return; folio_get(folio); - local_lock(&lru_pvecs.lock); - pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate_file); - - if (pagevec_add_and_need_flush(pvec, &folio->page)) - pagevec_lru_move_fn(pvec, lru_deactivate_file_fn); - local_unlock(&lru_pvecs.lock); + local_lock(&cpu_fbatches.lock); + fbatch = this_cpu_ptr(&cpu_fbatches.lru_deactivate_file); + folio_batch_add_and_move(fbatch, folio, lru_deactivate_file_fn); + local_unlock(&cpu_fbatches.lock); } /* @@ -666,15 +686,17 @@ void deactivate_file_folio(struct folio *folio) */ void deactivate_page(struct page *page) { - if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { - struct pagevec *pvec; - - local_lock(&lru_pvecs.lock); - pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate); - get_page(page); - if (pagevec_add_and_need_flush(pvec, page)) - pagevec_lru_move_fn(pvec, lru_deactivate_fn); - local_unlock(&lru_pvecs.lock); + struct folio *folio = page_folio(page); + + if (folio_test_lru(folio) && folio_test_active(folio) && + !folio_test_unevictable(folio)) { + struct folio_batch *fbatch; + + folio_get(folio); + local_lock(&cpu_fbatches.lock); + fbatch = this_cpu_ptr(&cpu_fbatches.lru_deactivate); + folio_batch_add_and_move(fbatch, folio, lru_deactivate_fn); + local_unlock(&cpu_fbatches.lock); } } @@ -687,24 +709,26 @@ void deactivate_page(struct page *page) */ void mark_page_lazyfree(struct page *page) { - if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && - !PageSwapCache(page) && !PageUnevictable(page)) { - struct pagevec *pvec; - - local_lock(&lru_pvecs.lock); - pvec = this_cpu_ptr(&lru_pvecs.lru_lazyfree); - get_page(page); - if (pagevec_add_and_need_flush(pvec, page)) - pagevec_lru_move_fn(pvec, lru_lazyfree_fn); - local_unlock(&lru_pvecs.lock); + struct folio *folio = page_folio(page); + + if (folio_test_lru(folio) && folio_test_anon(folio) && + folio_test_swapbacked(folio) && !folio_test_swapcache(folio) && + !folio_test_unevictable(folio)) { + struct folio_batch *fbatch; + + folio_get(folio); + local_lock(&cpu_fbatches.lock); + fbatch = this_cpu_ptr(&cpu_fbatches.lru_lazyfree); + folio_batch_add_and_move(fbatch, folio, lru_lazyfree_fn); + local_unlock(&cpu_fbatches.lock); } } void lru_add_drain(void) { - local_lock(&lru_pvecs.lock); + local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); - local_unlock(&lru_pvecs.lock); + local_unlock(&cpu_fbatches.lock); mlock_page_drain_local(); } @@ -716,19 +740,19 @@ void lru_add_drain(void) */ static void lru_add_and_bh_lrus_drain(void) { - local_lock(&lru_pvecs.lock); + local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); - local_unlock(&lru_pvecs.lock); + local_unlock(&cpu_fbatches.lock); invalidate_bh_lrus_cpu(); mlock_page_drain_local(); } void lru_add_drain_cpu_zone(struct zone *zone) { - local_lock(&lru_pvecs.lock); + local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); drain_local_pages(zone); - local_unlock(&lru_pvecs.lock); + local_unlock(&cpu_fbatches.lock); mlock_page_drain_local(); } @@ -741,6 +765,21 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy) lru_add_and_bh_lrus_drain(); } +static bool cpu_needs_drain(unsigned int cpu) +{ + struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu); + + /* Check these in order of likelihood that they're not zero */ + return folio_batch_count(&fbatches->lru_add) || + data_race(folio_batch_count(&per_cpu(lru_rotate.fbatch, cpu))) || + folio_batch_count(&fbatches->lru_deactivate_file) || + folio_batch_count(&fbatches->lru_deactivate) || + folio_batch_count(&fbatches->lru_lazyfree) || + folio_batch_count(&fbatches->activate) || + need_mlock_page_drain(cpu) || + has_bh_in_lru(cpu, NULL); +} + /* * Doesn't need any cpu hotplug locking because we do rely on per-cpu * kworkers being shut down before our page_alloc_cpu_dead callback is @@ -773,8 +812,9 @@ static inline void __lru_add_drain_all(bool force_all_cpus) return; /* - * Guarantee pagevec counter stores visible by this CPU are visible to - * other CPUs before loading the current drain generation. + * Guarantee folio_batch counter stores visible by this CPU + * are visible to other CPUs before loading the current drain + * generation. */ smp_mb(); @@ -800,8 +840,9 @@ static inline void __lru_add_drain_all(bool force_all_cpus) * (D) Increment global generation number * * Pairs with smp_load_acquire() at (B), outside of the critical - * section. Use a full memory barrier to guarantee that the new global - * drain generation number is stored before loading pagevec counters. + * section. Use a full memory barrier to guarantee that the + * new global drain generation number is stored before loading + * folio_batch counters. * * This pairing must be done here, before the for_each_online_cpu loop * below which drains the page vectors. @@ -823,14 +864,7 @@ static inline void __lru_add_drain_all(bool force_all_cpus) for_each_online_cpu(cpu) { struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); - if (pagevec_count(&per_cpu(lru_pvecs.lru_add, cpu)) || - data_race(pagevec_count(&per_cpu(lru_rotate.pvec, cpu))) || - pagevec_count(&per_cpu(lru_pvecs.lru_deactivate_file, cpu)) || - pagevec_count(&per_cpu(lru_pvecs.lru_deactivate, cpu)) || - pagevec_count(&per_cpu(lru_pvecs.lru_lazyfree, cpu)) || - need_activate_page_drain(cpu) || - need_mlock_page_drain(cpu) || - has_bh_in_lru(cpu, NULL)) { + if (cpu_needs_drain(cpu)) { INIT_WORK(work, lru_add_drain_per_cpu); queue_work_on(cpu, mm_percpu_wq, work); __cpumask_set_cpu(cpu, &has_work); @@ -906,8 +940,7 @@ void release_pages(struct page **pages, int nr) unsigned int lock_batch; for (i = 0; i < nr; i++) { - struct page *page = pages[i]; - struct folio *folio = page_folio(page); + struct folio *folio = page_folio(pages[i]); /* * Make sure the IRQ-safe lock-holding time does not get @@ -919,35 +952,34 @@ void release_pages(struct page **pages, int nr) lruvec = NULL; } - page = &folio->page; - if (is_huge_zero_page(page)) + if (is_huge_zero_page(&folio->page)) continue; - if (is_zone_device_page(page)) { + if (folio_is_zone_device(folio)) { if (lruvec) { unlock_page_lruvec_irqrestore(lruvec, flags); lruvec = NULL; } - if (put_devmap_managed_page(page)) + if (put_devmap_managed_page(&folio->page)) continue; - if (put_page_testzero(page)) - free_zone_device_page(page); + if (folio_put_testzero(folio)) + free_zone_device_page(&folio->page); continue; } - if (!put_page_testzero(page)) + if (!folio_put_testzero(folio)) continue; - if (PageCompound(page)) { + if (folio_test_large(folio)) { if (lruvec) { unlock_page_lruvec_irqrestore(lruvec, flags); lruvec = NULL; } - __put_compound_page(page); + __folio_put_large(folio); continue; } - if (PageLRU(page)) { + if (folio_test_lru(folio)) { struct lruvec *prev_lruvec = lruvec; lruvec = folio_lruvec_relock_irqsave(folio, lruvec, @@ -955,8 +987,8 @@ void release_pages(struct page **pages, int nr) if (prev_lruvec != lruvec) lock_batch = 0; - del_page_from_lru_list(page, lruvec); - __clear_page_lru_flags(page); + lruvec_del_folio(lruvec, folio); + __folio_clear_lru_flags(folio); } /* @@ -965,13 +997,13 @@ void release_pages(struct page **pages, int nr) * found set here. This does not indicate a problem, unless * "unevictable_pgs_cleared" appears worryingly large. */ - if (unlikely(PageMlocked(page))) { - __ClearPageMlocked(page); - dec_zone_page_state(page, NR_MLOCK); + if (unlikely(folio_test_mlocked(folio))) { + __folio_clear_mlocked(folio); + zone_stat_sub_folio(folio, NR_MLOCK); count_vm_event(UNEVICTABLE_PGCLEARED); } - list_add(&page->lru, &pages_to_free); + list_add(&folio->lru, &pages_to_free); } if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); @@ -987,8 +1019,8 @@ EXPORT_SYMBOL(release_pages); * OK from a correctness point of view but is inefficient - those pages may be * cache-warm and we want to give them back to the page allocator ASAP. * - * So __pagevec_release() will drain those queues here. __pagevec_lru_add() - * and __pagevec_lru_add_active() call release_pages() directly to avoid + * So __pagevec_release() will drain those queues here. + * folio_batch_move_lru() calls folios_put() directly to avoid * mutual recursion. */ void __pagevec_release(struct pagevec *pvec) @@ -1002,69 +1034,6 @@ void __pagevec_release(struct pagevec *pvec) } EXPORT_SYMBOL(__pagevec_release); -static void __pagevec_lru_add_fn(struct folio *folio, struct lruvec *lruvec) -{ - int was_unevictable = folio_test_clear_unevictable(folio); - long nr_pages = folio_nr_pages(folio); - - VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); - - folio_set_lru(folio); - /* - * Is an smp_mb__after_atomic() still required here, before - * folio_evictable() tests PageMlocked, to rule out the possibility - * of stranding an evictable folio on an unevictable LRU? I think - * not, because __munlock_page() only clears PageMlocked while the LRU - * lock is held. - * - * (That is not true of __page_cache_release(), and not necessarily - * true of release_pages(): but those only clear PageMlocked after - * put_page_testzero() has excluded any other users of the page.) - */ - if (folio_evictable(folio)) { - if (was_unevictable) - __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); - } else { - folio_clear_active(folio); - folio_set_unevictable(folio); - /* - * folio->mlock_count = !!folio_test_mlocked(folio)? - * But that leaves __mlock_page() in doubt whether another - * actor has already counted the mlock or not. Err on the - * safe side, underestimate, let page reclaim fix it, rather - * than leaving a page on the unevictable LRU indefinitely. - */ - folio->mlock_count = 0; - if (!was_unevictable) - __count_vm_events(UNEVICTABLE_PGCULLED, nr_pages); - } - - lruvec_add_folio(lruvec, folio); - trace_mm_lru_insertion(folio); -} - -/* - * Add the passed pages to the LRU, then drop the caller's refcount - * on them. Reinitialises the caller's pagevec. - */ -void __pagevec_lru_add(struct pagevec *pvec) -{ - int i; - struct lruvec *lruvec = NULL; - unsigned long flags = 0; - - for (i = 0; i < pagevec_count(pvec); i++) { - struct folio *folio = page_folio(pvec->pages[i]); - - lruvec = folio_lruvec_relock_irqsave(folio, lruvec, &flags); - __pagevec_lru_add_fn(folio, lruvec); - } - if (lruvec) - unlock_page_lruvec_irqrestore(lruvec, flags); - release_pages(pvec->pages, pvec->nr); - pagevec_reinit(pvec); -} - /** * folio_batch_remove_exceptionals() - Prune non-folios from a batch. * @fbatch: The batch to prune diff --git a/mm/swap.h b/mm/swap.h index 0193797b0c92..17936e068c1c 100644 --- a/mm/swap.h +++ b/mm/swap.h @@ -36,12 +36,11 @@ bool add_to_swap(struct folio *folio); void *get_shadow_from_swap_cache(swp_entry_t entry); int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp, void **shadowp); -void __delete_from_swap_cache(struct page *page, +void __delete_from_swap_cache(struct folio *folio, swp_entry_t entry, void *shadow); -void delete_from_swap_cache(struct page *page); +void delete_from_swap_cache(struct folio *folio); void clear_shadow_from_swap_cache(int type, unsigned long begin, unsigned long end); -void free_swap_cache(struct page *page); struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr); @@ -61,9 +60,9 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t flag, struct page *swapin_readahead(swp_entry_t entry, gfp_t flag, struct vm_fault *vmf); -static inline unsigned int page_swap_flags(struct page *page) +static inline unsigned int folio_swap_flags(struct folio *folio) { - return page_swap_info(page)->flags; + return page_swap_info(&folio->page)->flags; } #else /* CONFIG_SWAP */ struct swap_iocb; @@ -81,10 +80,6 @@ static inline struct address_space *swap_address_space(swp_entry_t entry) return NULL; } -static inline void free_swap_cache(struct page *page) -{ -} - static inline void show_swap_cache_info(void) { } @@ -135,12 +130,12 @@ static inline int add_to_swap_cache(struct page *page, swp_entry_t entry, return -1; } -static inline void __delete_from_swap_cache(struct page *page, +static inline void __delete_from_swap_cache(struct folio *folio, swp_entry_t entry, void *shadow) { } -static inline void delete_from_swap_cache(struct page *page) +static inline void delete_from_swap_cache(struct folio *folio) { } @@ -149,7 +144,7 @@ static inline void clear_shadow_from_swap_cache(int type, unsigned long begin, { } -static inline unsigned int page_swap_flags(struct page *page) +static inline unsigned int folio_swap_flags(struct folio *folio) { return 0; } diff --git a/mm/swap_state.c b/mm/swap_state.c index 0a2021fc55ad..e166051566f4 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -59,24 +59,11 @@ static bool enable_vma_readahead __read_mostly = true; #define GET_SWAP_RA_VAL(vma) \ (atomic_long_read(&(vma)->swap_readahead_info) ? : 4) -#define INC_CACHE_INFO(x) data_race(swap_cache_info.x++) -#define ADD_CACHE_INFO(x, nr) data_race(swap_cache_info.x += (nr)) - -static struct { - unsigned long add_total; - unsigned long del_total; - unsigned long find_success; - unsigned long find_total; -} swap_cache_info; - static atomic_t swapin_readahead_hits = ATOMIC_INIT(4); void show_swap_cache_info(void) { printk("%lu pages in swap cache\n", total_swapcache_pages()); - printk("Swap cache stats: add %lu, delete %lu, find %lu/%lu\n", - swap_cache_info.add_total, swap_cache_info.del_total, - swap_cache_info.find_success, swap_cache_info.find_total); printk("Free swap = %ldkB\n", get_nr_swap_pages() << (PAGE_SHIFT - 10)); printk("Total swap = %lukB\n", total_swap_pages << (PAGE_SHIFT - 10)); @@ -133,7 +120,6 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, address_space->nrpages += nr; __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr); __mod_lruvec_page_state(page, NR_SWAPCACHE, nr); - ADD_CACHE_INFO(add_total, nr); unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp)); @@ -147,32 +133,32 @@ unlock: } /* - * This must be called only on pages that have + * This must be called only on folios that have * been verified to be in the swap cache. */ -void __delete_from_swap_cache(struct page *page, +void __delete_from_swap_cache(struct folio *folio, swp_entry_t entry, void *shadow) { struct address_space *address_space = swap_address_space(entry); - int i, nr = thp_nr_pages(page); + int i; + long nr = folio_nr_pages(folio); pgoff_t idx = swp_offset(entry); XA_STATE(xas, &address_space->i_pages, idx); - VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(!PageSwapCache(page), page); - VM_BUG_ON_PAGE(PageWriteback(page), page); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + VM_BUG_ON_FOLIO(!folio_test_swapcache(folio), folio); + VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); for (i = 0; i < nr; i++) { void *entry = xas_store(&xas, shadow); - VM_BUG_ON_PAGE(entry != page, entry); - set_page_private(page + i, 0); + VM_BUG_ON_FOLIO(entry != folio, folio); + set_page_private(folio_page(folio, i), 0); xas_next(&xas); } - ClearPageSwapCache(page); + folio_clear_swapcache(folio); address_space->nrpages -= nr; - __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr); - __mod_lruvec_page_state(page, NR_SWAPCACHE, -nr); - ADD_CACHE_INFO(del_total, nr); + __node_stat_mod_folio(folio, NR_FILE_PAGES, -nr); + __lruvec_stat_mod_folio(folio, NR_SWAPCACHE, -nr); } /** @@ -237,22 +223,22 @@ fail: } /* - * This must be called only on pages that have + * This must be called only on folios that have * been verified to be in the swap cache and locked. - * It will never put the page into the free list, - * the caller has a reference on the page. + * It will never put the folio into the free list, + * the caller has a reference on the folio. */ -void delete_from_swap_cache(struct page *page) +void delete_from_swap_cache(struct folio *folio) { - swp_entry_t entry = { .val = page_private(page) }; + swp_entry_t entry = folio_swap_entry(folio); struct address_space *address_space = swap_address_space(entry); xa_lock_irq(&address_space->i_pages); - __delete_from_swap_cache(page, entry, NULL); + __delete_from_swap_cache(folio, entry, NULL); xa_unlock_irq(&address_space->i_pages); - put_swap_page(page, entry); - page_ref_sub(page, thp_nr_pages(page)); + put_swap_page(&folio->page, entry); + folio_ref_sub(folio, folio_nr_pages(folio)); } void clear_shadow_from_swap_cache(int type, unsigned long begin, @@ -348,12 +334,10 @@ struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma, page = find_get_page(swap_address_space(entry), swp_offset(entry)); put_swap_device(si); - INC_CACHE_INFO(find_total); if (page) { bool vma_ra = swap_use_vma_readahead(); bool readahead; - INC_CACHE_INFO(find_success); /* * At the moment, we don't support PG_readahead for anon THP * so let's bail out rather than confusing the readahead stat. diff --git a/mm/swapfile.c b/mm/swapfile.c index a2e66d855b19..1fdccd2f1422 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -695,7 +695,7 @@ static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, si->lowest_bit += nr_entries; if (end == si->highest_bit) WRITE_ONCE(si->highest_bit, si->highest_bit - nr_entries); - si->inuse_pages += nr_entries; + WRITE_ONCE(si->inuse_pages, si->inuse_pages + nr_entries); if (si->inuse_pages == si->pages) { si->lowest_bit = si->max; si->highest_bit = 0; @@ -732,7 +732,7 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset, add_to_avail_list(si); } atomic_long_add(nr_entries, &nr_swap_pages); - si->inuse_pages -= nr_entries; + WRITE_ONCE(si->inuse_pages, si->inuse_pages - nr_entries); if (si->flags & SWP_BLKDEV) swap_slot_free_notify = si->bdev->bd_disk->fops->swap_slot_free_notify; @@ -1568,16 +1568,15 @@ unlock_out: return ret; } -static bool page_swapped(struct page *page) +static bool folio_swapped(struct folio *folio) { swp_entry_t entry; struct swap_info_struct *si; - if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!PageTransCompound(page))) - return page_swapcount(page) != 0; + if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!folio_test_large(folio))) + return page_swapcount(&folio->page) != 0; - page = compound_head(page); - entry.val = page_private(page); + entry = folio_swap_entry(folio); si = _swap_info_get(entry); if (si) return swap_page_trans_huge_swapped(si, entry); @@ -1590,13 +1589,14 @@ static bool page_swapped(struct page *page) */ int try_to_free_swap(struct page *page) { - VM_BUG_ON_PAGE(!PageLocked(page), page); + struct folio *folio = page_folio(page); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); - if (!PageSwapCache(page)) + if (!folio_test_swapcache(folio)) return 0; - if (PageWriteback(page)) + if (folio_test_writeback(folio)) return 0; - if (page_swapped(page)) + if (folio_swapped(folio)) return 0; /* @@ -1617,9 +1617,8 @@ int try_to_free_swap(struct page *page) if (pm_suspended_storage()) return 0; - page = compound_head(page); - delete_from_swap_cache(page); - SetPageDirty(page); + delete_from_swap_cache(folio); + folio_set_dirty(folio); return 1; } @@ -2640,7 +2639,7 @@ static int swap_show(struct seq_file *swap, void *v) } bytes = si->pages << (PAGE_SHIFT - 10); - inuse = si->inuse_pages << (PAGE_SHIFT - 10); + inuse = READ_ONCE(si->inuse_pages) << (PAGE_SHIFT - 10); file = si->swap_file; len = seq_file_path(swap, file, " \t\n\\"); @@ -3259,7 +3258,7 @@ void si_swapinfo(struct sysinfo *val) struct swap_info_struct *si = swap_info[type]; if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK)) - nr_to_be_unused += si->inuse_pages; + nr_to_be_unused += READ_ONCE(si->inuse_pages); } val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; diff --git a/mm/util.c b/mm/util.c index 53af0e79d3e4..c9439c66d8cf 100644 --- a/mm/util.c +++ b/mm/util.c @@ -1005,7 +1005,7 @@ EXPORT_SYMBOL_GPL(vm_memory_committed); * succeed and -ENOMEM implies there is not. * * We currently support three overcommit policies, which are set via the - * vm.overcommit_memory sysctl. See Documentation/vm/overcommit-accounting.rst + * vm.overcommit_memory sysctl. See Documentation/mm/overcommit-accounting.rst * * Strict overcommit modes added 2002 Feb 26 by Alan Cox. * Additional code 2002 Jul 20 by Robert Love. diff --git a/mm/vmalloc.c b/mm/vmalloc.c index effd1ff6a4b4..dd6cdb201195 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -790,6 +790,7 @@ unsigned long vmalloc_nr_pages(void) return atomic_long_read(&nr_vmalloc_pages); } +/* Look up the first VA which satisfies addr < va_end, NULL if none. */ static struct vmap_area *find_vmap_area_exceed_addr(unsigned long addr) { struct vmap_area *va = NULL; @@ -814,9 +815,9 @@ static struct vmap_area *find_vmap_area_exceed_addr(unsigned long addr) return va; } -static struct vmap_area *__find_vmap_area(unsigned long addr) +static struct vmap_area *__find_vmap_area(unsigned long addr, struct rb_root *root) { - struct rb_node *n = vmap_area_root.rb_node; + struct rb_node *n = root->rb_node; addr = (unsigned long)kasan_reset_tag((void *)addr); @@ -874,11 +875,9 @@ find_va_links(struct vmap_area *va, * Trigger the BUG() if there are sides(left/right) * or full overlaps. */ - if (va->va_start < tmp_va->va_end && - va->va_end <= tmp_va->va_start) + if (va->va_end <= tmp_va->va_start) link = &(*link)->rb_left; - else if (va->va_end > tmp_va->va_start && - va->va_start >= tmp_va->va_end) + else if (va->va_start >= tmp_va->va_end) link = &(*link)->rb_right; else { WARN(1, "vmalloc bug: 0x%lx-0x%lx overlaps with 0x%lx-0x%lx\n", @@ -911,8 +910,9 @@ get_va_next_sibling(struct rb_node *parent, struct rb_node **link) } static __always_inline void -link_va(struct vmap_area *va, struct rb_root *root, - struct rb_node *parent, struct rb_node **link, struct list_head *head) +__link_va(struct vmap_area *va, struct rb_root *root, + struct rb_node *parent, struct rb_node **link, + struct list_head *head, bool augment) { /* * VA is still not in the list, but we can @@ -926,12 +926,12 @@ link_va(struct vmap_area *va, struct rb_root *root, /* Insert to the rb-tree */ rb_link_node(&va->rb_node, parent, link); - if (root == &free_vmap_area_root) { + if (augment) { /* * Some explanation here. Just perform simple insertion * to the tree. We do not set va->subtree_max_size to * its current size before calling rb_insert_augmented(). - * It is because of we populate the tree from the bottom + * It is because we populate the tree from the bottom * to parent levels when the node _is_ in the tree. * * Therefore we set subtree_max_size to zero after insertion, @@ -950,21 +950,49 @@ link_va(struct vmap_area *va, struct rb_root *root, } static __always_inline void -unlink_va(struct vmap_area *va, struct rb_root *root) +link_va(struct vmap_area *va, struct rb_root *root, + struct rb_node *parent, struct rb_node **link, + struct list_head *head) +{ + __link_va(va, root, parent, link, head, false); +} + +static __always_inline void +link_va_augment(struct vmap_area *va, struct rb_root *root, + struct rb_node *parent, struct rb_node **link, + struct list_head *head) +{ + __link_va(va, root, parent, link, head, true); +} + +static __always_inline void +__unlink_va(struct vmap_area *va, struct rb_root *root, bool augment) { if (WARN_ON(RB_EMPTY_NODE(&va->rb_node))) return; - if (root == &free_vmap_area_root) + if (augment) rb_erase_augmented(&va->rb_node, root, &free_vmap_area_rb_augment_cb); else rb_erase(&va->rb_node, root); - list_del(&va->list); + list_del_init(&va->list); RB_CLEAR_NODE(&va->rb_node); } +static __always_inline void +unlink_va(struct vmap_area *va, struct rb_root *root) +{ + __unlink_va(va, root, false); +} + +static __always_inline void +unlink_va_augment(struct vmap_area *va, struct rb_root *root) +{ + __unlink_va(va, root, true); +} + #if DEBUG_AUGMENT_PROPAGATE_CHECK /* * Gets called when remove the node and rotate. @@ -1060,7 +1088,7 @@ insert_vmap_area_augment(struct vmap_area *va, link = find_va_links(va, root, NULL, &parent); if (link) { - link_va(va, root, parent, link, head); + link_va_augment(va, root, parent, link, head); augment_tree_propagate_from(va); } } @@ -1077,8 +1105,8 @@ insert_vmap_area_augment(struct vmap_area *va, * ongoing. */ static __always_inline struct vmap_area * -merge_or_add_vmap_area(struct vmap_area *va, - struct rb_root *root, struct list_head *head) +__merge_or_add_vmap_area(struct vmap_area *va, + struct rb_root *root, struct list_head *head, bool augment) { struct vmap_area *sibling; struct list_head *next; @@ -1140,7 +1168,7 @@ merge_or_add_vmap_area(struct vmap_area *va, * "normalized" because of rotation operations. */ if (merged) - unlink_va(va, root); + __unlink_va(va, root, augment); sibling->va_end = va->va_end; @@ -1155,16 +1183,23 @@ merge_or_add_vmap_area(struct vmap_area *va, insert: if (!merged) - link_va(va, root, parent, link, head); + __link_va(va, root, parent, link, head, augment); return va; } static __always_inline struct vmap_area * +merge_or_add_vmap_area(struct vmap_area *va, + struct rb_root *root, struct list_head *head) +{ + return __merge_or_add_vmap_area(va, root, head, false); +} + +static __always_inline struct vmap_area * merge_or_add_vmap_area_augment(struct vmap_area *va, struct rb_root *root, struct list_head *head) { - va = merge_or_add_vmap_area(va, root, head); + va = __merge_or_add_vmap_area(va, root, head, true); if (va) augment_tree_propagate_from(va); @@ -1198,15 +1233,15 @@ is_within_this_va(struct vmap_area *va, unsigned long size, * overhead. */ static __always_inline struct vmap_area * -find_vmap_lowest_match(unsigned long size, unsigned long align, - unsigned long vstart, bool adjust_search_size) +find_vmap_lowest_match(struct rb_root *root, unsigned long size, + unsigned long align, unsigned long vstart, bool adjust_search_size) { struct vmap_area *va; struct rb_node *node; unsigned long length; /* Start from the root. */ - node = free_vmap_area_root.rb_node; + node = root->rb_node; /* Adjust the search size for alignment overhead. */ length = adjust_search_size ? size + align - 1 : size; @@ -1334,11 +1369,12 @@ classify_va_fit_type(struct vmap_area *va, } static __always_inline int -adjust_va_to_fit_type(struct vmap_area *va, - unsigned long nva_start_addr, unsigned long size, - enum fit_type type) +adjust_va_to_fit_type(struct rb_root *root, struct list_head *head, + struct vmap_area *va, unsigned long nva_start_addr, + unsigned long size) { struct vmap_area *lva = NULL; + enum fit_type type = classify_va_fit_type(va, nva_start_addr, size); if (type == FL_FIT_TYPE) { /* @@ -1348,7 +1384,7 @@ adjust_va_to_fit_type(struct vmap_area *va, * V NVA V * |---------------| */ - unlink_va(va, &free_vmap_area_root); + unlink_va_augment(va, root); kmem_cache_free(vmap_area_cachep, va); } else if (type == LE_FIT_TYPE) { /* @@ -1426,8 +1462,7 @@ adjust_va_to_fit_type(struct vmap_area *va, augment_tree_propagate_from(va); if (lva) /* type == NE_FIT_TYPE */ - insert_vmap_area_augment(lva, &va->rb_node, - &free_vmap_area_root, &free_vmap_area_list); + insert_vmap_area_augment(lva, &va->rb_node, root, head); } return 0; @@ -1438,13 +1473,13 @@ adjust_va_to_fit_type(struct vmap_area *va, * Otherwise a vend is returned that indicates failure. */ static __always_inline unsigned long -__alloc_vmap_area(unsigned long size, unsigned long align, +__alloc_vmap_area(struct rb_root *root, struct list_head *head, + unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend) { bool adjust_search_size = true; unsigned long nva_start_addr; struct vmap_area *va; - enum fit_type type; int ret; /* @@ -1459,7 +1494,7 @@ __alloc_vmap_area(unsigned long size, unsigned long align, if (align <= PAGE_SIZE || (align > PAGE_SIZE && (vend - vstart) == size)) adjust_search_size = false; - va = find_vmap_lowest_match(size, align, vstart, adjust_search_size); + va = find_vmap_lowest_match(root, size, align, vstart, adjust_search_size); if (unlikely(!va)) return vend; @@ -1472,14 +1507,9 @@ __alloc_vmap_area(unsigned long size, unsigned long align, if (nva_start_addr + size > vend) return vend; - /* Classify what we have found. */ - type = classify_va_fit_type(va, nva_start_addr, size); - if (WARN_ON_ONCE(type == NOTHING_FIT)) - return vend; - /* Update the free vmap_area. */ - ret = adjust_va_to_fit_type(va, nva_start_addr, size, type); - if (ret) + ret = adjust_va_to_fit_type(root, head, va, nva_start_addr, size); + if (WARN_ON_ONCE(ret)) return vend; #if DEBUG_AUGMENT_LOWEST_MATCH_CHECK @@ -1569,7 +1599,8 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, retry: preload_this_cpu_lock(&free_vmap_area_lock, gfp_mask, node); - addr = __alloc_vmap_area(size, align, vstart, vend); + addr = __alloc_vmap_area(&free_vmap_area_root, &free_vmap_area_list, + size, align, vstart, vend); spin_unlock(&free_vmap_area_lock); /* @@ -1663,7 +1694,7 @@ static atomic_long_t vmap_lazy_nr = ATOMIC_LONG_INIT(0); /* * Serialize vmap purging. There is no actual critical section protected - * by this look, but we want to avoid concurrent calls for performance + * by this lock, but we want to avoid concurrent calls for performance * reasons and to make the pcpu_get_vm_areas more deterministic. */ static DEFINE_MUTEX(vmap_purge_lock); @@ -1677,32 +1708,32 @@ static void purge_fragmented_blocks_allcpus(void); static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end) { unsigned long resched_threshold; - struct list_head local_pure_list; + struct list_head local_purge_list; struct vmap_area *va, *n_va; lockdep_assert_held(&vmap_purge_lock); spin_lock(&purge_vmap_area_lock); purge_vmap_area_root = RB_ROOT; - list_replace_init(&purge_vmap_area_list, &local_pure_list); + list_replace_init(&purge_vmap_area_list, &local_purge_list); spin_unlock(&purge_vmap_area_lock); - if (unlikely(list_empty(&local_pure_list))) + if (unlikely(list_empty(&local_purge_list))) return false; start = min(start, - list_first_entry(&local_pure_list, + list_first_entry(&local_purge_list, struct vmap_area, list)->va_start); end = max(end, - list_last_entry(&local_pure_list, + list_last_entry(&local_purge_list, struct vmap_area, list)->va_end); flush_tlb_kernel_range(start, end); resched_threshold = lazy_max_pages() << 1; spin_lock(&free_vmap_area_lock); - list_for_each_entry_safe(va, n_va, &local_pure_list, list) { + list_for_each_entry_safe(va, n_va, &local_purge_list, list) { unsigned long nr = (va->va_end - va->va_start) >> PAGE_SHIFT; unsigned long orig_start = va->va_start; unsigned long orig_end = va->va_end; @@ -1803,7 +1834,7 @@ struct vmap_area *find_vmap_area(unsigned long addr) struct vmap_area *va; spin_lock(&vmap_area_lock); - va = __find_vmap_area(addr); + va = __find_vmap_area(addr, &vmap_area_root); spin_unlock(&vmap_area_lock); return va; @@ -2546,7 +2577,7 @@ struct vm_struct *remove_vm_area(const void *addr) might_sleep(); spin_lock(&vmap_area_lock); - va = __find_vmap_area((unsigned long)addr); + va = __find_vmap_area((unsigned long)addr, &vmap_area_root); if (va && va->vm) { struct vm_struct *vm = va->vm; @@ -3168,15 +3199,15 @@ again: /* * Mark the pages as accessible, now that they are mapped. - * The init condition should match the one in post_alloc_hook() - * (except for the should_skip_init() check) to make sure that memory - * is initialized under the same conditions regardless of the enabled - * KASAN mode. + * The condition for setting KASAN_VMALLOC_INIT should complement the + * one in post_alloc_hook() with regards to the __GFP_SKIP_ZERO check + * to make sure that memory is initialized under the same conditions. * Tag-based KASAN modes only assign tags to normal non-executable * allocations, see __kasan_unpoison_vmalloc(). */ kasan_flags |= KASAN_VMALLOC_VM_ALLOC; - if (!want_init_on_free() && want_init_on_alloc(gfp_mask)) + if (!want_init_on_free() && want_init_on_alloc(gfp_mask) && + (gfp_mask & __GFP_SKIP_ZERO)) kasan_flags |= KASAN_VMALLOC_INIT; /* KASAN_VMALLOC_PROT_NORMAL already set if required. */ area->addr = kasan_unpoison_vmalloc(area->addr, real_size, kasan_flags); @@ -3735,7 +3766,6 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, int area, area2, last_area, term_area; unsigned long base, start, size, end, last_end, orig_start, orig_end; bool purged = false; - enum fit_type type; /* verify parameters and allocate data structures */ BUG_ON(offset_in_page(align) || !is_power_of_2(align)); @@ -3846,15 +3876,13 @@ retry: /* It is a BUG(), but trigger recovery instead. */ goto recovery; - type = classify_va_fit_type(va, start, size); - if (WARN_ON_ONCE(type == NOTHING_FIT)) + ret = adjust_va_to_fit_type(&free_vmap_area_root, + &free_vmap_area_list, + va, start, size); + if (WARN_ON_ONCE(unlikely(ret))) /* It is a BUG(), but trigger recovery instead. */ goto recovery; - ret = adjust_va_to_fit_type(va, start, size, type); - if (unlikely(ret)) - goto recovery; - /* Allocated area. */ va = vas[area]; va->va_start = start; diff --git a/mm/vmscan.c b/mm/vmscan.c index 04f8671caad9..b2b1431352dc 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -26,8 +26,7 @@ #include <linux/file.h> #include <linux/writeback.h> #include <linux/blkdev.h> -#include <linux/buffer_head.h> /* for try_to_release_page(), - buffer_heads_over_limit */ +#include <linux/buffer_head.h> /* for buffer_heads_over_limit */ #include <linux/mm_inline.h> #include <linux/backing-dev.h> #include <linux/rmap.h> @@ -102,6 +101,9 @@ struct scan_control { /* Can pages be swapped as part of reclaim? */ unsigned int may_swap:1; + /* Proactive reclaim invoked by userspace through memory.reclaim */ + unsigned int proactive:1; + /* * Cgroup memory below memory.low is protected as long as we * don't threaten to OOM. If any cgroup is reclaimed at @@ -160,17 +162,17 @@ struct scan_control { }; #ifdef ARCH_HAS_PREFETCHW -#define prefetchw_prev_lru_page(_page, _base, _field) \ +#define prefetchw_prev_lru_folio(_folio, _base, _field) \ do { \ - if ((_page)->lru.prev != _base) { \ - struct page *prev; \ + if ((_folio)->lru.prev != _base) { \ + struct folio *prev; \ \ - prev = lru_to_page(&(_page->lru)); \ + prev = lru_to_folio(&(_folio->lru)); \ prefetchw(&prev->_field); \ } \ } while (0) #else -#define prefetchw_prev_lru_page(_page, _base, _field) do { } while (0) +#define prefetchw_prev_lru_folio(_folio, _base, _field) do { } while (0) #endif /* @@ -190,8 +192,8 @@ static void set_task_reclaim_state(struct task_struct *task, task->reclaim_state = rs; } -static LIST_HEAD(shrinker_list); -static DECLARE_RWSEM(shrinker_rwsem); +LIST_HEAD(shrinker_list); +DECLARE_RWSEM(shrinker_rwsem); #ifdef CONFIG_MEMCG static int shrinker_nr_max; @@ -608,7 +610,7 @@ static unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, /* * Add a shrinker callback to be called from the vm. */ -int prealloc_shrinker(struct shrinker *shrinker) +static int __prealloc_shrinker(struct shrinker *shrinker) { unsigned int size; int err; @@ -632,8 +634,39 @@ int prealloc_shrinker(struct shrinker *shrinker) return 0; } +#ifdef CONFIG_SHRINKER_DEBUG +int prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...) +{ + va_list ap; + int err; + + va_start(ap, fmt); + shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); + va_end(ap); + if (!shrinker->name) + return -ENOMEM; + + err = __prealloc_shrinker(shrinker); + if (err) { + kfree_const(shrinker->name); + shrinker->name = NULL; + } + + return err; +} +#else +int prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...) +{ + return __prealloc_shrinker(shrinker); +} +#endif + void free_prealloced_shrinker(struct shrinker *shrinker) { +#ifdef CONFIG_SHRINKER_DEBUG + kfree_const(shrinker->name); + shrinker->name = NULL; +#endif if (shrinker->flags & SHRINKER_MEMCG_AWARE) { down_write(&shrinker_rwsem); unregister_memcg_shrinker(shrinker); @@ -650,18 +683,45 @@ void register_shrinker_prepared(struct shrinker *shrinker) down_write(&shrinker_rwsem); list_add_tail(&shrinker->list, &shrinker_list); shrinker->flags |= SHRINKER_REGISTERED; + shrinker_debugfs_add(shrinker); up_write(&shrinker_rwsem); } -int register_shrinker(struct shrinker *shrinker) +static int __register_shrinker(struct shrinker *shrinker) { - int err = prealloc_shrinker(shrinker); + int err = __prealloc_shrinker(shrinker); if (err) return err; register_shrinker_prepared(shrinker); return 0; } + +#ifdef CONFIG_SHRINKER_DEBUG +int register_shrinker(struct shrinker *shrinker, const char *fmt, ...) +{ + va_list ap; + int err; + + va_start(ap, fmt); + shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); + va_end(ap); + if (!shrinker->name) + return -ENOMEM; + + err = __register_shrinker(shrinker); + if (err) { + kfree_const(shrinker->name); + shrinker->name = NULL; + } + return err; +} +#else +int register_shrinker(struct shrinker *shrinker, const char *fmt, ...) +{ + return __register_shrinker(shrinker); +} +#endif EXPORT_SYMBOL(register_shrinker); /* @@ -677,6 +737,7 @@ void unregister_shrinker(struct shrinker *shrinker) shrinker->flags &= ~SHRINKER_REGISTERED; if (shrinker->flags & SHRINKER_MEMCG_AWARE) unregister_memcg_shrinker(shrinker); + shrinker_debugfs_remove(shrinker); up_write(&shrinker_rwsem); kfree(shrinker->nr_deferred); @@ -1276,7 +1337,7 @@ static int __remove_mapping(struct address_space *mapping, struct folio *folio, mem_cgroup_swapout(folio, swap); if (reclaimed && !mapping_exiting(mapping)) shadow = workingset_eviction(folio, target_memcg); - __delete_from_swap_cache(&folio->page, swap, shadow); + __delete_from_swap_cache(folio, swap, shadow); xa_unlock_irq(&mapping->i_pages); put_swap_page(&folio->page, swap); } else { @@ -1519,7 +1580,7 @@ static bool may_enter_fs(struct folio *folio, gfp_t gfp_mask) * but that will never affect SWP_FS_OPS, so the data_race * is safe. */ - return !data_race(page_swap_flags(&folio->page) & SWP_FS_OPS); + return !data_race(folio_swap_flags(folio) & SWP_FS_OPS); } /* @@ -1926,7 +1987,7 @@ free_it: * appear not as the counts should be low */ if (unlikely(folio_test_large(folio))) - destroy_compound_page(&folio->page); + destroy_large_folio(folio); else list_add(&folio->lru, &free_pages); continue; @@ -1987,7 +2048,7 @@ keep: } unsigned int reclaim_clean_pages_from_list(struct zone *zone, - struct list_head *page_list) + struct list_head *folio_list) { struct scan_control sc = { .gfp_mask = GFP_KERNEL, @@ -1995,16 +2056,16 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone, }; struct reclaim_stat stat; unsigned int nr_reclaimed; - struct page *page, *next; - LIST_HEAD(clean_pages); + struct folio *folio, *next; + LIST_HEAD(clean_folios); unsigned int noreclaim_flag; - list_for_each_entry_safe(page, next, page_list, lru) { - if (!PageHuge(page) && page_is_file_lru(page) && - !PageDirty(page) && !__PageMovable(page) && - !PageUnevictable(page)) { - ClearPageActive(page); - list_move(&page->lru, &clean_pages); + list_for_each_entry_safe(folio, next, folio_list, lru) { + if (!folio_test_hugetlb(folio) && folio_is_file_lru(folio) && + !folio_test_dirty(folio) && !__folio_test_movable(folio) && + !folio_test_unevictable(folio)) { + folio_clear_active(folio); + list_move(&folio->lru, &clean_folios); } } @@ -2015,11 +2076,11 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone, * change in the future. */ noreclaim_flag = memalloc_noreclaim_save(); - nr_reclaimed = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc, + nr_reclaimed = shrink_page_list(&clean_folios, zone->zone_pgdat, &sc, &stat, true); memalloc_noreclaim_restore(noreclaim_flag); - list_splice(&clean_pages, page_list); + list_splice(&clean_folios, folio_list); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)nr_reclaimed); /* @@ -2085,72 +2146,72 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, unsigned long nr_skipped[MAX_NR_ZONES] = { 0, }; unsigned long skipped = 0; unsigned long scan, total_scan, nr_pages; - LIST_HEAD(pages_skipped); + LIST_HEAD(folios_skipped); total_scan = 0; scan = 0; while (scan < nr_to_scan && !list_empty(src)) { struct list_head *move_to = src; - struct page *page; + struct folio *folio; - page = lru_to_page(src); - prefetchw_prev_lru_page(page, src, flags); + folio = lru_to_folio(src); + prefetchw_prev_lru_folio(folio, src, flags); - nr_pages = compound_nr(page); + nr_pages = folio_nr_pages(folio); total_scan += nr_pages; - if (page_zonenum(page) > sc->reclaim_idx) { - nr_skipped[page_zonenum(page)] += nr_pages; - move_to = &pages_skipped; + if (folio_zonenum(folio) > sc->reclaim_idx) { + nr_skipped[folio_zonenum(folio)] += nr_pages; + move_to = &folios_skipped; goto move; } /* - * Do not count skipped pages because that makes the function - * return with no isolated pages if the LRU mostly contains - * ineligible pages. This causes the VM to not reclaim any - * pages, triggering a premature OOM. - * Account all tail pages of THP. + * Do not count skipped folios because that makes the function + * return with no isolated folios if the LRU mostly contains + * ineligible folios. This causes the VM to not reclaim any + * folios, triggering a premature OOM. + * Account all pages in a folio. */ scan += nr_pages; - if (!PageLRU(page)) + if (!folio_test_lru(folio)) goto move; - if (!sc->may_unmap && page_mapped(page)) + if (!sc->may_unmap && folio_mapped(folio)) goto move; /* - * Be careful not to clear PageLRU until after we're - * sure the page is not being freed elsewhere -- the - * page release code relies on it. + * Be careful not to clear the lru flag until after we're + * sure the folio is not being freed elsewhere -- the + * folio release code relies on it. */ - if (unlikely(!get_page_unless_zero(page))) + if (unlikely(!folio_try_get(folio))) goto move; - if (!TestClearPageLRU(page)) { - /* Another thread is already isolating this page */ - put_page(page); + if (!folio_test_clear_lru(folio)) { + /* Another thread is already isolating this folio */ + folio_put(folio); goto move; } nr_taken += nr_pages; - nr_zone_taken[page_zonenum(page)] += nr_pages; + nr_zone_taken[folio_zonenum(folio)] += nr_pages; move_to = dst; move: - list_move(&page->lru, move_to); + list_move(&folio->lru, move_to); } /* - * Splice any skipped pages to the start of the LRU list. Note that + * Splice any skipped folios to the start of the LRU list. Note that * this disrupts the LRU order when reclaiming for lower zones but * we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX - * scanning would soon rescan the same pages to skip and waste lots + * scanning would soon rescan the same folios to skip and waste lots * of cpu cycles. */ - if (!list_empty(&pages_skipped)) { + if (!list_empty(&folios_skipped)) { int zid; - list_splice(&pages_skipped, src); + list_splice(&folios_skipped, src); for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_skipped[zid]) continue; @@ -2254,8 +2315,8 @@ static int too_many_isolated(struct pglist_data *pgdat, int file, } /* - * move_pages_to_lru() moves pages from private @list to appropriate LRU list. - * On return, @list is reused as a list of pages to be freed by the caller. + * move_pages_to_lru() moves folios from private @list to appropriate LRU list. + * On return, @list is reused as a list of folios to be freed by the caller. * * Returns the number of pages moved to the given lruvec. */ @@ -2263,42 +2324,42 @@ static unsigned int move_pages_to_lru(struct lruvec *lruvec, struct list_head *list) { int nr_pages, nr_moved = 0; - LIST_HEAD(pages_to_free); - struct page *page; + LIST_HEAD(folios_to_free); while (!list_empty(list)) { - page = lru_to_page(list); - VM_BUG_ON_PAGE(PageLRU(page), page); - list_del(&page->lru); - if (unlikely(!page_evictable(page))) { + struct folio *folio = lru_to_folio(list); + + VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); + list_del(&folio->lru); + if (unlikely(!folio_evictable(folio))) { spin_unlock_irq(&lruvec->lru_lock); - putback_lru_page(page); + folio_putback_lru(folio); spin_lock_irq(&lruvec->lru_lock); continue; } /* - * The SetPageLRU needs to be kept here for list integrity. + * The folio_set_lru needs to be kept here for list integrity. * Otherwise: * #0 move_pages_to_lru #1 release_pages - * if !put_page_testzero - * if (put_page_testzero()) - * !PageLRU //skip lru_lock - * SetPageLRU() - * list_add(&page->lru,) - * list_add(&page->lru,) + * if (!folio_put_testzero()) + * if (folio_put_testzero()) + * !lru //skip lru_lock + * folio_set_lru() + * list_add(&folio->lru,) + * list_add(&folio->lru,) */ - SetPageLRU(page); + folio_set_lru(folio); - if (unlikely(put_page_testzero(page))) { - __clear_page_lru_flags(page); + if (unlikely(folio_put_testzero(folio))) { + __folio_clear_lru_flags(folio); - if (unlikely(PageCompound(page))) { + if (unlikely(folio_test_large(folio))) { spin_unlock_irq(&lruvec->lru_lock); - destroy_compound_page(page); + destroy_large_folio(folio); spin_lock_irq(&lruvec->lru_lock); } else - list_add(&page->lru, &pages_to_free); + list_add(&folio->lru, &folios_to_free); continue; } @@ -2307,18 +2368,18 @@ static unsigned int move_pages_to_lru(struct lruvec *lruvec, * All pages were isolated from the same lruvec (and isolation * inhibits memcg migration). */ - VM_BUG_ON_PAGE(!folio_matches_lruvec(page_folio(page), lruvec), page); - add_page_to_lru_list(page, lruvec); - nr_pages = thp_nr_pages(page); + VM_BUG_ON_FOLIO(!folio_matches_lruvec(folio, lruvec), folio); + lruvec_add_folio(lruvec, folio); + nr_pages = folio_nr_pages(folio); nr_moved += nr_pages; - if (PageActive(page)) + if (folio_test_active(folio)) workingset_age_nonresident(lruvec, nr_pages); } /* * To save our caller's stack, now use input list for pages to free. */ - list_splice(&pages_to_free, list); + list_splice(&folios_to_free, list); return nr_moved; } @@ -2429,21 +2490,21 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, } /* - * shrink_active_list() moves pages from the active LRU to the inactive LRU. + * shrink_active_list() moves folios from the active LRU to the inactive LRU. * - * We move them the other way if the page is referenced by one or more + * We move them the other way if the folio is referenced by one or more * processes. * - * If the pages are mostly unmapped, the processing is fast and it is + * If the folios are mostly unmapped, the processing is fast and it is * appropriate to hold lru_lock across the whole operation. But if - * the pages are mapped, the processing is slow (folio_referenced()), so - * we should drop lru_lock around each page. It's impossible to balance - * this, so instead we remove the pages from the LRU while processing them. - * It is safe to rely on PG_active against the non-LRU pages in here because - * nobody will play with that bit on a non-LRU page. + * the folios are mapped, the processing is slow (folio_referenced()), so + * we should drop lru_lock around each folio. It's impossible to balance + * this, so instead we remove the folios from the LRU while processing them. + * It is safe to rely on the active flag against the non-LRU folios in here + * because nobody will play with that bit on a non-LRU folio. * - * The downside is that we have to touch page->_refcount against each page. - * But we had to alter page->flags anyway. + * The downside is that we have to touch folio->_refcount against each folio. + * But we had to alter folio->flags anyway. */ static void shrink_active_list(unsigned long nr_to_scan, struct lruvec *lruvec, @@ -2453,7 +2514,7 @@ static void shrink_active_list(unsigned long nr_to_scan, unsigned long nr_taken; unsigned long nr_scanned; unsigned long vm_flags; - LIST_HEAD(l_hold); /* The pages which were snipped off */ + LIST_HEAD(l_hold); /* The folios which were snipped off */ LIST_HEAD(l_active); LIST_HEAD(l_inactive); unsigned nr_deactivate, nr_activate; @@ -2478,23 +2539,21 @@ static void shrink_active_list(unsigned long nr_to_scan, while (!list_empty(&l_hold)) { struct folio *folio; - struct page *page; cond_resched(); folio = lru_to_folio(&l_hold); list_del(&folio->lru); - page = &folio->page; - if (unlikely(!page_evictable(page))) { - putback_lru_page(page); + if (unlikely(!folio_evictable(folio))) { + folio_putback_lru(folio); continue; } if (unlikely(buffer_heads_over_limit)) { - if (page_has_private(page) && trylock_page(page)) { - if (page_has_private(page)) - try_to_release_page(page, 0); - unlock_page(page); + if (folio_get_private(folio) && folio_trylock(folio)) { + if (folio_get_private(folio)) + filemap_release_folio(folio, 0); + folio_unlock(folio); } } @@ -2502,34 +2561,34 @@ static void shrink_active_list(unsigned long nr_to_scan, if (folio_referenced(folio, 0, sc->target_mem_cgroup, &vm_flags) != 0) { /* - * Identify referenced, file-backed active pages and + * Identify referenced, file-backed active folios and * give them one more trip around the active list. So * that executable code get better chances to stay in - * memory under moderate memory pressure. Anon pages + * memory under moderate memory pressure. Anon folios * are not likely to be evicted by use-once streaming - * IO, plus JVM can create lots of anon VM_EXEC pages, + * IO, plus JVM can create lots of anon VM_EXEC folios, * so we ignore them here. */ - if ((vm_flags & VM_EXEC) && page_is_file_lru(page)) { - nr_rotated += thp_nr_pages(page); - list_add(&page->lru, &l_active); + if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) { + nr_rotated += folio_nr_pages(folio); + list_add(&folio->lru, &l_active); continue; } } - ClearPageActive(page); /* we are de-activating */ - SetPageWorkingset(page); - list_add(&page->lru, &l_inactive); + folio_clear_active(folio); /* we are de-activating */ + folio_set_workingset(folio); + list_add(&folio->lru, &l_inactive); } /* - * Move pages back to the lru list. + * Move folios back to the lru list. */ spin_lock_irq(&lruvec->lru_lock); nr_activate = move_pages_to_lru(lruvec, &l_active); nr_deactivate = move_pages_to_lru(lruvec, &l_inactive); - /* Keep all free pages in l_active list */ + /* Keep all free folios in l_active list */ list_splice(&l_inactive, &l_active); __count_vm_events(PGDEACTIVATE, nr_deactivate); @@ -2568,34 +2627,33 @@ static unsigned int reclaim_page_list(struct list_head *page_list, return nr_reclaimed; } -unsigned long reclaim_pages(struct list_head *page_list) +unsigned long reclaim_pages(struct list_head *folio_list) { int nid; unsigned int nr_reclaimed = 0; - LIST_HEAD(node_page_list); - struct page *page; + LIST_HEAD(node_folio_list); unsigned int noreclaim_flag; - if (list_empty(page_list)) + if (list_empty(folio_list)) return nr_reclaimed; noreclaim_flag = memalloc_noreclaim_save(); - nid = page_to_nid(lru_to_page(page_list)); + nid = folio_nid(lru_to_folio(folio_list)); do { - page = lru_to_page(page_list); + struct folio *folio = lru_to_folio(folio_list); - if (nid == page_to_nid(page)) { - ClearPageActive(page); - list_move(&page->lru, &node_page_list); + if (nid == folio_nid(folio)) { + folio_clear_active(folio); + list_move(&folio->lru, &node_folio_list); continue; } - nr_reclaimed += reclaim_page_list(&node_page_list, NODE_DATA(nid)); - nid = page_to_nid(lru_to_page(page_list)); - } while (!list_empty(page_list)); + nr_reclaimed += reclaim_page_list(&node_folio_list, NODE_DATA(nid)); + nid = folio_nid(lru_to_folio(folio_list)); + } while (!list_empty(folio_list)); - nr_reclaimed += reclaim_page_list(&node_page_list, NODE_DATA(nid)); + nr_reclaimed += reclaim_page_list(&node_folio_list, NODE_DATA(nid)); memalloc_noreclaim_restore(noreclaim_flag); @@ -3125,9 +3183,10 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) sc->priority); /* Record the group's reclaim efficiency */ - vmpressure(sc->gfp_mask, memcg, false, - sc->nr_scanned - scanned, - sc->nr_reclaimed - reclaimed); + if (!sc->proactive) + vmpressure(sc->gfp_mask, memcg, false, + sc->nr_scanned - scanned, + sc->nr_reclaimed - reclaimed); } while ((memcg = mem_cgroup_iter(target_memcg, memcg, NULL))); } @@ -3250,9 +3309,10 @@ again: } /* Record the subtree's reclaim efficiency */ - vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true, - sc->nr_scanned - nr_scanned, - sc->nr_reclaimed - nr_reclaimed); + if (!sc->proactive) + vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true, + sc->nr_scanned - nr_scanned, + sc->nr_reclaimed - nr_reclaimed); if (sc->nr_reclaimed - nr_reclaimed) reclaimable = true; @@ -3534,8 +3594,9 @@ retry: __count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1); do { - vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup, - sc->priority); + if (!sc->proactive) + vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup, + sc->priority); sc->nr_scanned = 0; shrink_zones(zonelist, sc); @@ -3825,7 +3886,7 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, - bool may_swap) + unsigned int reclaim_options) { unsigned long nr_reclaimed; unsigned int noreclaim_flag; @@ -3838,7 +3899,8 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, .priority = DEF_PRIORITY, .may_writepage = !laptop_mode, .may_unmap = 1, - .may_swap = may_swap, + .may_swap = !!(reclaim_options & MEMCG_RECLAIM_MAY_SWAP), + .proactive = !!(reclaim_options & MEMCG_RECLAIM_PROACTIVE), }; /* * Traverse the ZONELIST_FALLBACK zonelist of the current node to put @@ -4595,7 +4657,7 @@ void kswapd_run(int nid) /* * Called by memory hotplug when all memory in a node is offlined. Caller must - * hold mem_hotplug_begin/end(). + * be holding mem_hotplug_begin/done(). */ void kswapd_stop(int nid) { diff --git a/mm/workingset.c b/mm/workingset.c index 592569a8974c..a5e84862fc86 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -625,7 +625,7 @@ static int __init workingset_init(void) pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n", timestamp_bits, max_order, bucket_order); - ret = prealloc_shrinker(&workingset_shadow_shrinker); + ret = prealloc_shrinker(&workingset_shadow_shrinker, "mm-shadow"); if (ret) goto err; ret = __list_lru_init(&shadow_nodes, true, &shadow_nodes_key, diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 71d6edcbea48..34f784a1604b 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -386,7 +386,10 @@ static int zs_zpool_malloc(void *pool, size_t size, gfp_t gfp, unsigned long *handle) { *handle = zs_malloc(pool, size, gfp); - return *handle ? 0 : -1; + + if (IS_ERR((void *)(*handle))) + return PTR_ERR((void *)*handle); + return 0; } static void zs_zpool_free(void *pool, unsigned long handle) { @@ -1388,7 +1391,7 @@ static unsigned long obj_malloc(struct zs_pool *pool, * @gfp: gfp flags when allocating object * * On success, handle to the allocated object is returned, - * otherwise 0. + * otherwise an ERR_PTR(). * Allocation requests with size > ZS_MAX_ALLOC_SIZE will fail. */ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) @@ -1399,11 +1402,11 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) struct zspage *zspage; if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE)) - return 0; + return (unsigned long)ERR_PTR(-EINVAL); handle = cache_alloc_handle(pool, gfp); if (!handle) - return 0; + return (unsigned long)ERR_PTR(-ENOMEM); /* extra space in chunk to keep the handle */ size += ZS_HANDLE_SIZE; @@ -1428,7 +1431,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) zspage = alloc_zspage(pool, class, gfp); if (!zspage) { cache_free_handle(pool, handle); - return 0; + return (unsigned long)ERR_PTR(-ENOMEM); } spin_lock(&class->lock); @@ -2169,7 +2172,8 @@ static int zs_register_shrinker(struct zs_pool *pool) pool->shrinker.batch = 0; pool->shrinker.seeks = DEFAULT_SEEKS; - return register_shrinker(&pool->shrinker); + return register_shrinker(&pool->shrinker, "mm-zspool:%s", + pool->name); } /** diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 0ec2f5906a27..6b9f19122ec1 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -18,6 +18,7 @@ #include <linux/user_namespace.h> #include <linux/net_namespace.h> #include <linux/sched/task.h> +#include <linux/sched/mm.h> #include <linux/uidgid.h> #include <linux/cookie.h> @@ -1143,7 +1144,13 @@ static int __register_pernet_operations(struct list_head *list, * setup_net() and cleanup_net() are not possible. */ for_each_net(net) { + struct mem_cgroup *old, *memcg; + + memcg = mem_cgroup_or_root(get_mem_cgroup_from_obj(net)); + old = set_active_memcg(memcg); error = ops_init(ops, net); + set_active_memcg(old); + mem_cgroup_put(memcg); if (error) goto out_undo; list_add_tail(&net->exit_list, &net_exit_list); diff --git a/net/core/page_pool.c b/net/core/page_pool.c index b74905fcc3a1..9b203d8660e4 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -16,7 +16,7 @@ #include <linux/dma-direction.h> #include <linux/dma-mapping.h> #include <linux/page-flags.h> -#include <linux/mm.h> /* for __put_page() */ +#include <linux/mm.h> /* for put_page() */ #include <linux/poison.h> #include <linux/ethtool.h> diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 682fcd24bf43..04e7b55fe0d9 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -874,7 +874,7 @@ int __init rpcauth_init_module(void) err = rpc_init_authunix(); if (err < 0) goto out1; - err = register_shrinker(&rpc_cred_shrinker); + err = register_shrinker(&rpc_cred_shrinker, "sunrpc_cred"); if (err < 0) goto out2; return 0; diff --git a/tools/cgroup/memcg_shrinker.py b/tools/cgroup/memcg_shrinker.py new file mode 100644 index 000000000000..706ab27666a4 --- /dev/null +++ b/tools/cgroup/memcg_shrinker.py @@ -0,0 +1,71 @@ +#!/usr/bin/env python3 +# +# Copyright (C) 2022 Roman Gushchin <roman.gushchin@linux.dev> +# Copyright (C) 2022 Meta + +import os +import argparse +import sys + + +def scan_cgroups(cgroup_root): + cgroups = {} + + for root, subdirs, _ in os.walk(cgroup_root): + for cgroup in subdirs: + path = os.path.join(root, cgroup) + ino = os.stat(path).st_ino + cgroups[ino] = path + + # (memcg ino, path) + return cgroups + + +def scan_shrinkers(shrinker_debugfs): + shrinkers = [] + + for root, subdirs, _ in os.walk(shrinker_debugfs): + for shrinker in subdirs: + count_path = os.path.join(root, shrinker, "count") + with open(count_path) as f: + for line in f.readlines(): + items = line.split(' ') + ino = int(items[0]) + # (count, shrinker, memcg ino) + shrinkers.append((int(items[1]), shrinker, ino)) + return shrinkers + + +def main(): + parser = argparse.ArgumentParser(description='Display biggest shrinkers') + parser.add_argument('-n', '--lines', type=int, help='Number of lines to print') + + args = parser.parse_args() + + cgroups = scan_cgroups("/sys/fs/cgroup/") + shrinkers = scan_shrinkers("/sys/kernel/debug/shrinker/") + shrinkers = sorted(shrinkers, reverse = True, key = lambda x: x[0]) + + n = 0 + for s in shrinkers: + count, name, ino = (s[0], s[1], s[2]) + if count == 0: + break + + if ino == 0 or ino == 1: + cg = "/" + else: + try: + cg = cgroups[ino] + except KeyError: + cg = "unknown (%d)" % ino + + print("%-8s %-20s %s" % (count, name, cg)) + + n += 1 + if args.lines and n >= args.lines: + break + + +if __name__ == '__main__': + main() diff --git a/tools/testing/memblock/linux/kmemleak.h b/tools/testing/memblock/linux/kmemleak.h index 462f8c5e8aa0..5fed13bb9ec4 100644 --- a/tools/testing/memblock/linux/kmemleak.h +++ b/tools/testing/memblock/linux/kmemleak.h @@ -7,7 +7,7 @@ static inline void kmemleak_free_part_phys(phys_addr_t phys, size_t size) } static inline void kmemleak_alloc_phys(phys_addr_t phys, size_t size, - int min_count, gfp_t gfp) + gfp_t gfp) { } diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 108587cb327a..d9fa6a9ea584 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -93,6 +93,7 @@ TEST_PROGS := run_vmtests.sh TEST_FILES := test_vmalloc.sh TEST_FILES += test_hmm.sh +TEST_FILES += va_128TBswitch.sh include ../lib.mk diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c index 203323967b50..529f53b40296 100644 --- a/tools/testing/selftests/vm/hmm-tests.c +++ b/tools/testing/selftests/vm/hmm-tests.c @@ -36,6 +36,7 @@ * in the usual include/uapi/... directory. */ #include "../../../../lib/test_hmm_uapi.h" +#include "../../../../mm/gup_test.h" struct hmm_buffer { void *ptr; @@ -46,12 +47,22 @@ struct hmm_buffer { uint64_t faults; }; +enum { + HMM_PRIVATE_DEVICE_ONE, + HMM_PRIVATE_DEVICE_TWO, + HMM_COHERENCE_DEVICE_ONE, + HMM_COHERENCE_DEVICE_TWO, +}; + #define TWOMEG (1 << 21) #define HMM_BUFFER_SIZE (1024 << 12) #define HMM_PATH_MAX 64 #define NTIMES 10 #define ALIGN(x, a) (((x) + (a - 1)) & (~((a) - 1))) +/* Just the flags we need, copied from mm.h: */ +#define FOLL_WRITE 0x01 /* check pte is writable */ +#define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite */ FIXTURE(hmm) { @@ -60,6 +71,21 @@ FIXTURE(hmm) unsigned int page_shift; }; +FIXTURE_VARIANT(hmm) +{ + int device_number; +}; + +FIXTURE_VARIANT_ADD(hmm, hmm_device_private) +{ + .device_number = HMM_PRIVATE_DEVICE_ONE, +}; + +FIXTURE_VARIANT_ADD(hmm, hmm_device_coherent) +{ + .device_number = HMM_COHERENCE_DEVICE_ONE, +}; + FIXTURE(hmm2) { int fd0; @@ -68,6 +94,24 @@ FIXTURE(hmm2) unsigned int page_shift; }; +FIXTURE_VARIANT(hmm2) +{ + int device_number0; + int device_number1; +}; + +FIXTURE_VARIANT_ADD(hmm2, hmm2_device_private) +{ + .device_number0 = HMM_PRIVATE_DEVICE_ONE, + .device_number1 = HMM_PRIVATE_DEVICE_TWO, +}; + +FIXTURE_VARIANT_ADD(hmm2, hmm2_device_coherent) +{ + .device_number0 = HMM_COHERENCE_DEVICE_ONE, + .device_number1 = HMM_COHERENCE_DEVICE_TWO, +}; + static int hmm_open(int unit) { char pathname[HMM_PATH_MAX]; @@ -81,12 +125,19 @@ static int hmm_open(int unit) return fd; } +static bool hmm_is_coherent_type(int dev_num) +{ + return (dev_num >= HMM_COHERENCE_DEVICE_ONE); +} + FIXTURE_SETUP(hmm) { self->page_size = sysconf(_SC_PAGE_SIZE); self->page_shift = ffs(self->page_size) - 1; - self->fd = hmm_open(0); + self->fd = hmm_open(variant->device_number); + if (self->fd < 0 && hmm_is_coherent_type(variant->device_number)) + SKIP(exit(0), "DEVICE_COHERENT not available"); ASSERT_GE(self->fd, 0); } @@ -95,9 +146,11 @@ FIXTURE_SETUP(hmm2) self->page_size = sysconf(_SC_PAGE_SIZE); self->page_shift = ffs(self->page_size) - 1; - self->fd0 = hmm_open(0); + self->fd0 = hmm_open(variant->device_number0); + if (self->fd0 < 0 && hmm_is_coherent_type(variant->device_number0)) + SKIP(exit(0), "DEVICE_COHERENT not available"); ASSERT_GE(self->fd0, 0); - self->fd1 = hmm_open(1); + self->fd1 = hmm_open(variant->device_number1); ASSERT_GE(self->fd1, 0); } @@ -211,6 +264,20 @@ static void hmm_nanosleep(unsigned int n) nanosleep(&t, NULL); } +static int hmm_migrate_sys_to_dev(int fd, + struct hmm_buffer *buffer, + unsigned long npages) +{ + return hmm_dmirror_cmd(fd, HMM_DMIRROR_MIGRATE_TO_DEV, buffer, npages); +} + +static int hmm_migrate_dev_to_sys(int fd, + struct hmm_buffer *buffer, + unsigned long npages) +{ + return hmm_dmirror_cmd(fd, HMM_DMIRROR_MIGRATE_TO_SYS, buffer, npages); +} + /* * Simple NULL test of device open/close. */ @@ -875,7 +942,7 @@ TEST_F(hmm, migrate) ptr[i] = i; /* Migrate memory to device. */ - ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages); + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); ASSERT_EQ(ret, 0); ASSERT_EQ(buffer->cpages, npages); @@ -923,7 +990,7 @@ TEST_F(hmm, migrate_fault) ptr[i] = i; /* Migrate memory to device. */ - ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages); + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); ASSERT_EQ(ret, 0); ASSERT_EQ(buffer->cpages, npages); @@ -936,7 +1003,7 @@ TEST_F(hmm, migrate_fault) ASSERT_EQ(ptr[i], i); /* Migrate memory to the device again. */ - ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages); + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); ASSERT_EQ(ret, 0); ASSERT_EQ(buffer->cpages, npages); @@ -976,7 +1043,7 @@ TEST_F(hmm, migrate_shared) ASSERT_NE(buffer->ptr, MAP_FAILED); /* Migrate memory to device. */ - ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages); + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); ASSERT_EQ(ret, -ENOENT); hmm_buffer_free(buffer); @@ -1015,7 +1082,7 @@ TEST_F(hmm2, migrate_mixed) p = buffer->ptr; /* Migrating a protected area should be an error. */ - ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, npages); + ret = hmm_migrate_sys_to_dev(self->fd1, buffer, npages); ASSERT_EQ(ret, -EINVAL); /* Punch a hole after the first page address. */ @@ -1023,7 +1090,7 @@ TEST_F(hmm2, migrate_mixed) ASSERT_EQ(ret, 0); /* We expect an error if the vma doesn't cover the range. */ - ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, 3); + ret = hmm_migrate_sys_to_dev(self->fd1, buffer, 3); ASSERT_EQ(ret, -EINVAL); /* Page 2 will be a read-only zero page. */ @@ -1055,13 +1122,13 @@ TEST_F(hmm2, migrate_mixed) /* Now try to migrate pages 2-5 to device 1. */ buffer->ptr = p + 2 * self->page_size; - ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, 4); + ret = hmm_migrate_sys_to_dev(self->fd1, buffer, 4); ASSERT_EQ(ret, 0); ASSERT_EQ(buffer->cpages, 4); /* Page 5 won't be migrated to device 0 because it's on device 1. */ buffer->ptr = p + 5 * self->page_size; - ret = hmm_dmirror_cmd(self->fd0, HMM_DMIRROR_MIGRATE, buffer, 1); + ret = hmm_migrate_sys_to_dev(self->fd0, buffer, 1); ASSERT_EQ(ret, -ENOENT); buffer->ptr = p; @@ -1070,8 +1137,12 @@ TEST_F(hmm2, migrate_mixed) } /* - * Migrate anonymous memory to device private memory and fault it back to system - * memory multiple times. + * Migrate anonymous memory to device memory and back to system memory + * multiple times. In case of private zone configuration, this is done + * through fault pages accessed by CPU. In case of coherent zone configuration, + * the pages from the device should be explicitly migrated back to system memory. + * The reason is Coherent device zone has coherent access by CPU, therefore + * it will not generate any page fault. */ TEST_F(hmm, migrate_multiple) { @@ -1107,8 +1178,7 @@ TEST_F(hmm, migrate_multiple) ptr[i] = i; /* Migrate memory to device. */ - ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, - npages); + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); ASSERT_EQ(ret, 0); ASSERT_EQ(buffer->cpages, npages); @@ -1116,7 +1186,13 @@ TEST_F(hmm, migrate_multiple) for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) ASSERT_EQ(ptr[i], i); - /* Fault pages back to system memory and check them. */ + /* Migrate back to system memory and check them. */ + if (hmm_is_coherent_type(variant->device_number)) { + ret = hmm_migrate_dev_to_sys(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + } + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) ASSERT_EQ(ptr[i], i); @@ -1354,13 +1430,13 @@ TEST_F(hmm2, snapshot) /* Page 5 will be migrated to device 0. */ buffer->ptr = p + 5 * self->page_size; - ret = hmm_dmirror_cmd(self->fd0, HMM_DMIRROR_MIGRATE, buffer, 1); + ret = hmm_migrate_sys_to_dev(self->fd0, buffer, 1); ASSERT_EQ(ret, 0); ASSERT_EQ(buffer->cpages, 1); /* Page 6 will be migrated to device 1. */ buffer->ptr = p + 6 * self->page_size; - ret = hmm_dmirror_cmd(self->fd1, HMM_DMIRROR_MIGRATE, buffer, 1); + ret = hmm_migrate_sys_to_dev(self->fd1, buffer, 1); ASSERT_EQ(ret, 0); ASSERT_EQ(buffer->cpages, 1); @@ -1377,9 +1453,16 @@ TEST_F(hmm2, snapshot) ASSERT_EQ(m[2], HMM_DMIRROR_PROT_ZERO | HMM_DMIRROR_PROT_READ); ASSERT_EQ(m[3], HMM_DMIRROR_PROT_READ); ASSERT_EQ(m[4], HMM_DMIRROR_PROT_WRITE); - ASSERT_EQ(m[5], HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL | - HMM_DMIRROR_PROT_WRITE); - ASSERT_EQ(m[6], HMM_DMIRROR_PROT_NONE); + if (!hmm_is_coherent_type(variant->device_number0)) { + ASSERT_EQ(m[5], HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL | + HMM_DMIRROR_PROT_WRITE); + ASSERT_EQ(m[6], HMM_DMIRROR_PROT_NONE); + } else { + ASSERT_EQ(m[5], HMM_DMIRROR_PROT_DEV_COHERENT_LOCAL | + HMM_DMIRROR_PROT_WRITE); + ASSERT_EQ(m[6], HMM_DMIRROR_PROT_DEV_COHERENT_REMOTE | + HMM_DMIRROR_PROT_WRITE); + } hmm_buffer_free(buffer); } @@ -1520,9 +1603,19 @@ TEST_F(hmm2, double_map) for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) ASSERT_EQ(ptr[i], i); - /* Punch a hole after the first page address. */ - ret = munmap(buffer->ptr + self->page_size, self->page_size); + /* Migrate pages to device 1 and try to read from device 0. */ + ret = hmm_migrate_sys_to_dev(self->fd1, buffer, npages); ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + ret = hmm_dmirror_cmd(self->fd0, HMM_DMIRROR_READ, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + ASSERT_EQ(buffer->faults, 1); + + /* Check what device 0 read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); hmm_buffer_free(buffer); } @@ -1685,4 +1778,190 @@ TEST_F(hmm, exclusive_cow) hmm_buffer_free(buffer); } +static int gup_test_exec(int gup_fd, unsigned long addr, int cmd, + int npages, int size, int flags) +{ + struct gup_test gup = { + .nr_pages_per_call = npages, + .addr = addr, + .gup_flags = FOLL_WRITE | flags, + .size = size, + }; + + if (ioctl(gup_fd, cmd, &gup)) { + perror("ioctl on error\n"); + return errno; + } + + return 0; +} + +/* + * Test get user device pages through gup_test. Setting PIN_LONGTERM flag. + * This should trigger a migration back to system memory for both, private + * and coherent type pages. + * This test makes use of gup_test module. Make sure GUP_TEST_CONFIG is added + * to your configuration before you run it. + */ +TEST_F(hmm, hmm_gup_test) +{ + struct hmm_buffer *buffer; + int gup_fd; + unsigned long npages; + unsigned long size; + unsigned long i; + int *ptr; + int ret; + unsigned char *m; + + gup_fd = open("/sys/kernel/debug/gup_test", O_RDWR); + if (gup_fd == -1) + SKIP(return, "Skipping test, could not find gup_test driver"); + + npages = 4; + size = npages << self->page_shift; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + + buffer->ptr = mmap(NULL, size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Migrate memory to device. */ + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + ASSERT_EQ(gup_test_exec(gup_fd, + (unsigned long)buffer->ptr, + GUP_BASIC_TEST, 1, self->page_size, 0), 0); + ASSERT_EQ(gup_test_exec(gup_fd, + (unsigned long)buffer->ptr + 1 * self->page_size, + GUP_FAST_BENCHMARK, 1, self->page_size, 0), 0); + ASSERT_EQ(gup_test_exec(gup_fd, + (unsigned long)buffer->ptr + 2 * self->page_size, + PIN_FAST_BENCHMARK, 1, self->page_size, FOLL_LONGTERM), 0); + ASSERT_EQ(gup_test_exec(gup_fd, + (unsigned long)buffer->ptr + 3 * self->page_size, + PIN_LONGTERM_BENCHMARK, 1, self->page_size, 0), 0); + + /* Take snapshot to CPU pagetables */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + m = buffer->mirror; + if (hmm_is_coherent_type(variant->device_number)) { + ASSERT_EQ(HMM_DMIRROR_PROT_DEV_COHERENT_LOCAL | HMM_DMIRROR_PROT_WRITE, m[0]); + ASSERT_EQ(HMM_DMIRROR_PROT_DEV_COHERENT_LOCAL | HMM_DMIRROR_PROT_WRITE, m[1]); + } else { + ASSERT_EQ(HMM_DMIRROR_PROT_WRITE, m[0]); + ASSERT_EQ(HMM_DMIRROR_PROT_WRITE, m[1]); + } + ASSERT_EQ(HMM_DMIRROR_PROT_WRITE, m[2]); + ASSERT_EQ(HMM_DMIRROR_PROT_WRITE, m[3]); + /* + * Check again the content on the pages. Make sure there's no + * corrupted data. + */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + close(gup_fd); + hmm_buffer_free(buffer); +} + +/* + * Test copy-on-write in device pages. + * In case of writing to COW private page(s), a page fault will migrate pages + * back to system memory first. Then, these pages will be duplicated. In case + * of COW device coherent type, pages are duplicated directly from device + * memory. + */ +TEST_F(hmm, hmm_cow_in_device) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + int *ptr; + int ret; + unsigned char *m; + pid_t pid; + int status; + + npages = 4; + size = npages << self->page_shift; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + + buffer->ptr = mmap(NULL, size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Migrate memory to device. */ + + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + pid = fork(); + if (pid == -1) + ASSERT_EQ(pid, 0); + if (!pid) { + /* Child process waitd for SIGTERM from the parent. */ + while (1) { + } + perror("Should not reach this\n"); + exit(0); + } + /* Parent process writes to COW pages(s) and gets a + * new copy in system. In case of device private pages, + * this write causes a migration to system mem first. + */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Terminate child and wait */ + EXPECT_EQ(0, kill(pid, SIGTERM)); + EXPECT_EQ(pid, waitpid(pid, &status, 0)); + EXPECT_NE(0, WIFSIGNALED(status)); + EXPECT_EQ(SIGTERM, WTERMSIG(status)); + + /* Take snapshot to CPU pagetables */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + m = buffer->mirror; + for (i = 0; i < npages; i++) + ASSERT_EQ(HMM_DMIRROR_PROT_WRITE, m[i]); + + hmm_buffer_free(buffer); +} TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/vm/hugepage-mremap.c b/tools/testing/selftests/vm/hugepage-mremap.c index 585978f181ed..e63a0214f639 100644 --- a/tools/testing/selftests/vm/hugepage-mremap.c +++ b/tools/testing/selftests/vm/hugepage-mremap.c @@ -107,7 +107,7 @@ static void register_region_with_uffd(char *addr, size_t len) int main(int argc, char *argv[]) { - size_t length; + size_t length = 0; if (argc != 2 && argc != 3) { printf("Usage: %s [length_in_MB] <hugetlb_file>\n", argv[0]); diff --git a/tools/testing/selftests/vm/hugetlb-madvise.c b/tools/testing/selftests/vm/hugetlb-madvise.c index 6c6af40f5747..3c9943131881 100644 --- a/tools/testing/selftests/vm/hugetlb-madvise.c +++ b/tools/testing/selftests/vm/hugetlb-madvise.c @@ -89,10 +89,11 @@ void write_fault_pages(void *addr, unsigned long nr_pages) void read_fault_pages(void *addr, unsigned long nr_pages) { - unsigned long i, tmp; + unsigned long dummy = 0; + unsigned long i; for (i = 0; i < nr_pages; i++) - tmp += *((unsigned long *)(addr + (i * huge_page_size))); + dummy += *((unsigned long *)(addr + (i * huge_page_size))); } int main(int argc, char **argv) diff --git a/tools/testing/selftests/vm/mrelease_test.c b/tools/testing/selftests/vm/mrelease_test.c index 96671c2f7d48..6c62966ab5db 100644 --- a/tools/testing/selftests/vm/mrelease_test.c +++ b/tools/testing/selftests/vm/mrelease_test.c @@ -62,19 +62,22 @@ static int alloc_noexit(unsigned long nr_pages, int pipefd) /* The process_mrelease calls in this test are expected to fail */ static void run_negative_tests(int pidfd) { + int res; /* Test invalid flags. Expect to fail with EINVAL error code. */ if (!syscall(__NR_process_mrelease, pidfd, (unsigned int)-1) || errno != EINVAL) { + res = (errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); perror("process_mrelease with wrong flags"); - exit(errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); + exit(res); } /* * Test reaping while process is alive with no pending SIGKILL. * Expect to fail with EINVAL error code. */ if (!syscall(__NR_process_mrelease, pidfd, 0) || errno != EINVAL) { + res = (errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); perror("process_mrelease on a live process"); - exit(errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); + exit(res); } } @@ -100,8 +103,9 @@ int main(void) /* Test a wrong pidfd */ if (!syscall(__NR_process_mrelease, -1, 0) || errno != EBADF) { + res = (errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); perror("process_mrelease with wrong pidfd"); - exit(errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); + exit(res); } /* Start the test with 1MB child memory allocation */ @@ -156,8 +160,9 @@ retry: run_negative_tests(pidfd); if (kill(pid, SIGKILL)) { + res = (errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); perror("kill"); - exit(errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); + exit(res); } success = (syscall(__NR_process_mrelease, pidfd, 0) == 0); @@ -172,9 +177,10 @@ retry: if (errno == ESRCH) { retry = (size <= MAX_SIZE_MB); } else { + res = (errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); perror("process_mrelease"); waitpid(pid, NULL, 0); - exit(errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); + exit(res); } } diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh index 41fce8bea929..de86983b8a0f 100755 --- a/tools/testing/selftests/vm/run_vmtests.sh +++ b/tools/testing/selftests/vm/run_vmtests.sh @@ -151,7 +151,7 @@ if [ $VADDR64 -ne 0 ]; then run_test ./virtual_address_range # virtual address 128TB switch test - run_test ./va_128TBswitch + run_test ./va_128TBswitch.sh fi # VADDR64 # vmalloc stability smoke test @@ -179,4 +179,17 @@ run_test ./ksm_tests -N -m 1 # KSM test with 2 NUMA nodes and merge_across_nodes = 0 run_test ./ksm_tests -N -m 0 +# protection_keys tests +if [ -x ./protection_keys_32 ] +then + run_test ./protection_keys_32 +fi + +if [ -x ./protection_keys_64 ] +then + run_test ./protection_keys_64 +fi + +run_test ./soft-dirty + exit $exitcode diff --git a/tools/testing/selftests/vm/soft-dirty.c b/tools/testing/selftests/vm/soft-dirty.c index 08ab62a4a9d0..e3a43f5d4fa2 100644 --- a/tools/testing/selftests/vm/soft-dirty.c +++ b/tools/testing/selftests/vm/soft-dirty.c @@ -121,13 +121,76 @@ static void test_hugepage(int pagemap_fd, int pagesize) free(map); } +static void test_mprotect(int pagemap_fd, int pagesize, bool anon) +{ + const char *type[] = {"file", "anon"}; + const char *fname = "./soft-dirty-test-file"; + int test_fd; + char *map; + + if (anon) { + map = mmap(NULL, pagesize, PROT_READ|PROT_WRITE, + MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); + if (!map) + ksft_exit_fail_msg("anon mmap failed\n"); + } else { + test_fd = open(fname, O_RDWR | O_CREAT); + if (test_fd < 0) { + ksft_test_result_skip("Test %s open() file failed\n", __func__); + return; + } + unlink(fname); + ftruncate(test_fd, pagesize); + map = mmap(NULL, pagesize, PROT_READ|PROT_WRITE, + MAP_SHARED, test_fd, 0); + if (!map) + ksft_exit_fail_msg("file mmap failed\n"); + } + + *map = 1; + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map) == 1, + "Test %s-%s dirty bit of new written page\n", + __func__, type[anon]); + clear_softdirty(); + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map) == 0, + "Test %s-%s soft-dirty clear after clear_refs\n", + __func__, type[anon]); + mprotect(map, pagesize, PROT_READ); + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map) == 0, + "Test %s-%s soft-dirty clear after marking RO\n", + __func__, type[anon]); + mprotect(map, pagesize, PROT_READ|PROT_WRITE); + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map) == 0, + "Test %s-%s soft-dirty clear after marking RW\n", + __func__, type[anon]); + *map = 2; + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map) == 1, + "Test %s-%s soft-dirty after rewritten\n", + __func__, type[anon]); + + munmap(map, pagesize); + + if (!anon) + close(test_fd); +} + +static void test_mprotect_anon(int pagemap_fd, int pagesize) +{ + test_mprotect(pagemap_fd, pagesize, true); +} + +static void test_mprotect_file(int pagemap_fd, int pagesize) +{ + test_mprotect(pagemap_fd, pagesize, false); +} + int main(int argc, char **argv) { int pagemap_fd; int pagesize; ksft_print_header(); - ksft_set_plan(5); + ksft_set_plan(15); pagemap_fd = open(PAGEMAP_FILE_PATH, O_RDONLY); if (pagemap_fd < 0) @@ -138,6 +201,8 @@ int main(int argc, char **argv) test_simple(pagemap_fd, pagesize); test_vma_reuse(pagemap_fd, pagesize); test_hugepage(pagemap_fd, pagesize); + test_mprotect_anon(pagemap_fd, pagesize); + test_mprotect_file(pagemap_fd, pagesize); close(pagemap_fd); diff --git a/tools/testing/selftests/vm/test_hmm.sh b/tools/testing/selftests/vm/test_hmm.sh index 0647b525a625..539c9371e592 100755 --- a/tools/testing/selftests/vm/test_hmm.sh +++ b/tools/testing/selftests/vm/test_hmm.sh @@ -40,11 +40,26 @@ check_test_requirements() load_driver() { - modprobe $DRIVER > /dev/null 2>&1 + if [ $# -eq 0 ]; then + modprobe $DRIVER > /dev/null 2>&1 + else + if [ $# -eq 2 ]; then + modprobe $DRIVER spm_addr_dev0=$1 spm_addr_dev1=$2 + > /dev/null 2>&1 + else + echo "Missing module parameters. Make sure pass"\ + "spm_addr_dev0 and spm_addr_dev1" + usage + fi + fi if [ $? == 0 ]; then major=$(awk "\$2==\"HMM_DMIRROR\" {print \$1}" /proc/devices) mknod /dev/hmm_dmirror0 c $major 0 mknod /dev/hmm_dmirror1 c $major 1 + if [ $# -eq 2 ]; then + mknod /dev/hmm_dmirror2 c $major 2 + mknod /dev/hmm_dmirror3 c $major 3 + fi fi } @@ -58,7 +73,7 @@ run_smoke() { echo "Running smoke test. Note, this test provides basic coverage." - load_driver + load_driver $1 $2 $(dirname "${BASH_SOURCE[0]}")/hmm-tests unload_driver } @@ -75,6 +90,9 @@ usage() echo "# Smoke testing" echo "./${TEST_NAME}.sh smoke" echo + echo "# Smoke testing with SPM enabled" + echo "./${TEST_NAME}.sh smoke <spm_addr_dev0> <spm_addr_dev1>" + echo exit 0 } @@ -84,7 +102,7 @@ function run_test() usage else if [ "$1" = "smoke" ]; then - run_smoke + run_smoke $2 $3 else usage fi diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 4bc24581760d..7c3f1b0ab468 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -931,7 +931,7 @@ static int faulting_process(int signal_test) unsigned long split_nr_pages; unsigned long lastnr; struct sigaction act; - unsigned long signalled = 0; + volatile unsigned long signalled = 0; split_nr_pages = (nr_pages + 1) / 2; @@ -946,7 +946,7 @@ static int faulting_process(int signal_test) } for (nr = 0; nr < split_nr_pages; nr++) { - int steps = 1; + volatile int steps = 1; unsigned long offset = nr * page_size; if (signal_test) { diff --git a/tools/testing/selftests/vm/va_128TBswitch.c b/tools/testing/selftests/vm/va_128TBswitch.c index da6ec3b53ea8..1d2068989883 100644 --- a/tools/testing/selftests/vm/va_128TBswitch.c +++ b/tools/testing/selftests/vm/va_128TBswitch.c @@ -231,7 +231,7 @@ static struct testcase hugetlb_testcases[] = { static int run_test(struct testcase *test, int count) { void *p; - int i, ret = 0; + int i, ret = KSFT_PASS; for (i = 0; i < count; i++) { struct testcase *t = test + i; @@ -242,13 +242,13 @@ static int run_test(struct testcase *test, int count) if (p == MAP_FAILED) { printf("FAILED\n"); - ret = 1; + ret = KSFT_FAIL; continue; } if (t->low_addr_required && p >= (void *)(ADDR_SWITCH_HINT)) { printf("FAILED\n"); - ret = 1; + ret = KSFT_FAIL; } else { /* * Do a dereference of the address returned so that we catch @@ -280,7 +280,7 @@ int main(int argc, char **argv) int ret; if (!supported_arch()) - return 0; + return KSFT_SKIP; ret = run_test(testcases, ARRAY_SIZE(testcases)); if (argc == 2 && !strcmp(argv[1], "--run-hugetlb")) diff --git a/tools/testing/selftests/vm/va_128TBswitch.sh b/tools/testing/selftests/vm/va_128TBswitch.sh new file mode 100755 index 000000000000..41580751dc51 --- /dev/null +++ b/tools/testing/selftests/vm/va_128TBswitch.sh @@ -0,0 +1,54 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (C) 2022 Adam Sindelar (Meta) <adam@wowsignal.io> +# +# This is a test for mmap behavior with 5-level paging. This script wraps the +# real test to check that the kernel is configured to support at least 5 +# pagetable levels. + +# 1 means the test failed +exitcode=1 + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +fail() +{ + echo "$1" + exit $exitcode +} + +check_supported_x86_64() +{ + local config="/proc/config.gz" + [[ -f "${config}" ]] || config="/boot/config-$(uname -r)" + [[ -f "${config}" ]] || fail "Cannot find kernel config in /proc or /boot" + + # gzip -dcfq automatically handles both compressed and plaintext input. + # See man 1 gzip under '-f'. + local pg_table_levels=$(gzip -dcfq "${config}" | grep PGTABLE_LEVELS | cut -d'=' -f 2) + + if [[ "${pg_table_levels}" -lt 5 ]]; then + echo "$0: PGTABLE_LEVELS=${pg_table_levels}, must be >= 5 to run this test" + exit $ksft_skip + fi +} + +check_test_requirements() +{ + # The test supports x86_64 and powerpc64. We currently have no useful + # eligibility check for powerpc64, and the test itself will reject other + # architectures. + case `uname -m` in + "x86_64") + check_supported_x86_64 + ;; + *) + return 0 + ;; + esac +} + +check_test_requirements +./va_128TBswitch diff --git a/tools/vm/page_owner_sort.c b/tools/vm/page_owner_sort.c index c149427eb1c9..ec2e67c85b84 100644 --- a/tools/vm/page_owner_sort.c +++ b/tools/vm/page_owner_sort.c @@ -8,7 +8,7 @@ * Or sort by total memory: * ./page_owner_sort -m page_owner_full.txt sorted_page_owner.txt * - * See Documentation/vm/page_owner.rst + * See Documentation/mm/page_owner.rst */ #include <stdio.h> @@ -470,23 +470,23 @@ static bool match_str_list(const char *str, char **list, int list_size) static bool is_need(char *buf) { - if ((filter & FILTER_UNRELEASE) && get_free_ts_nsec(buf) != 0) - return false; - if ((filter & FILTER_PID) && !match_num_list(get_pid(buf), fc.pids, fc.pids_size)) - return false; - if ((filter & FILTER_TGID) && - !match_num_list(get_tgid(buf), fc.tgids, fc.tgids_size)) - return false; + if ((filter & FILTER_UNRELEASE) && get_free_ts_nsec(buf) != 0) + return false; + if ((filter & FILTER_PID) && !match_num_list(get_pid(buf), fc.pids, fc.pids_size)) + return false; + if ((filter & FILTER_TGID) && + !match_num_list(get_tgid(buf), fc.tgids, fc.tgids_size)) + return false; - char *comm = get_comm(buf); + char *comm = get_comm(buf); - if ((filter & FILTER_COMM) && - !match_str_list(comm, fc.comms, fc.comms_size)) { - free(comm); - return false; - } + if ((filter & FILTER_COMM) && + !match_str_list(comm, fc.comms, fc.comms_size)) { free(comm); - return true; + return false; + } + free(comm); + return true; } static void add_list(char *buf, int len, char *ext_buf) diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c index 5b98f3ee58a5..0fffaeedee76 100644 --- a/tools/vm/slabinfo.c +++ b/tools/vm/slabinfo.c @@ -125,7 +125,7 @@ static void usage(void) "-n|--numa Show NUMA information\n" "-N|--lines=K Show the first K slabs\n" "-o|--ops Show kmem_cache_ops\n" - "-P|--partial Sort by number of partial slabs\n" + "-P|--partial Sort by number of partial slabs\n" "-r|--report Detailed report on single slabs\n" "-s|--shrink Shrink slabs\n" "-S|--Size Sort by size\n" @@ -1067,15 +1067,27 @@ static void sort_slabs(void) for (s2 = s1 + 1; s2 < slabinfo + slabs; s2++) { int result; - if (sort_size) - result = slab_size(s1) < slab_size(s2); - else if (sort_active) - result = slab_activity(s1) < slab_activity(s2); - else if (sort_loss) - result = slab_waste(s1) < slab_waste(s2); - else if (sort_partial) - result = s1->partial < s2->partial; - else + if (sort_size) { + if (slab_size(s1) == slab_size(s2)) + result = strcasecmp(s1->name, s2->name); + else + result = slab_size(s1) < slab_size(s2); + } else if (sort_active) { + if (slab_activity(s1) == slab_activity(s2)) + result = strcasecmp(s1->name, s2->name); + else + result = slab_activity(s1) < slab_activity(s2); + } else if (sort_loss) { + if (slab_waste(s1) == slab_waste(s2)) + result = strcasecmp(s1->name, s2->name); + else + result = slab_waste(s1) < slab_waste(s2); + } else if (sort_partial) { + if (s1->partial == s2->partial) + result = strcasecmp(s1->name, s2->name); + else + result = s1->partial < s2->partial; + } else result = strcasecmp(s1->name, s2->name); if (show_inverted) |