diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-damon b/Documentation/ABI/testing/sysfs-kernel-mm-damon new file mode 100644 index 0000000000000000000000000000000000000000..13397b8536926780fc0f967099b6e193d6b23f50 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-mm-damon @@ -0,0 +1,317 @@ +what: /sys/kernel/mm/damon/ +Date: Mar 2022 +Contact: SeongJae Park +Description: Interface for Data Access MONitoring (DAMON). Contains files + for controlling DAMON. For more details on DAMON itself, + please refer to Documentation/admin-guide/mm/damon/index.rst. + +What: /sys/kernel/mm/damon/admin/ +Date: Mar 2022 +Contact: SeongJae Park +Description: Interface for privileged users of DAMON. Contains files for + controlling DAMON that aimed to be used by privileged users. + +What: /sys/kernel/mm/damon/admin/kdamonds/nr_kdamonds +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing a number 'N' to this file creates the number of + directories for controlling each DAMON worker thread (kdamond) + named '0' to 'N-1' under the kdamonds/ directory. + +What: /sys/kernel/mm/damon/admin/kdamonds//state +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing 'on' or 'off' to this file makes the kdamond starts or + stops, respectively. Reading the file returns the keywords + based on the current status. Writing 'commit' to this file + makes the kdamond reads the user inputs in the sysfs files + except 'state' again. Writing 'update_schemes_stats' to the + file updates contents of schemes stats files of the kdamond. + Writing 'update_schemes_tried_regions' to the file updates + contents of 'tried_regions' directory of every scheme directory + of this kdamond. Writing 'clear_schemes_tried_regions' to the + file removes contents of the 'tried_regions' directory. + +What: /sys/kernel/mm/damon/admin/kdamonds//pid +Date: Mar 2022 +Contact: SeongJae Park +Description: Reading this file returns the pid of the kdamond if it is + running. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts/nr_contexts +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing a number 'N' to this file creates the number of + directories for controlling each DAMON context named '0' to + 'N-1' under the contexts/ directory. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//avail_operations +Date: Apr 2022 +Contact: SeongJae Park +Description: Reading this file returns the available monitoring operations + sets on the currently running kernel. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//operations +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing a keyword for a monitoring operations set ('vaddr' for + virtual address spaces monitoring, 'fvaddr' for fixed virtual + address ranges monitoring, and 'paddr' for the physical address + space monitoring) to this file makes the context to use the + operations set. Reading the file returns the keyword for the + operations set the context is set to use. + + Note that only the operations sets that listed in + 'avail_operations' file are valid inputs. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//monitoring_attrs/intervals/sample_us +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing a value to this file sets the sampling interval of the + DAMON context in microseconds as the value. Reading this file + returns the value. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//monitoring_attrs/intervals/aggr_us +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing a value to this file sets the aggregation interval of + the DAMON context in microseconds as the value. Reading this + file returns the value. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//monitoring_attrs/intervals/update_us +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing a value to this file sets the update interval of the + DAMON context in microseconds as the value. Reading this file + returns the value. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//monitoring_attrs/nr_regions/min + +WDate: Mar 2022 +Contact: SeongJae Park +Description: Writing a value to this file sets the minimum number of + monitoring regions of the DAMON context as the value. Reading + this file returns the value. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//monitoring_attrs/nr_regions/max +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing a value to this file sets the maximum number of + monitoring regions of the DAMON context as the value. Reading + this file returns the value. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//targets/nr_targets +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing a number 'N' to this file creates the number of + directories for controlling each DAMON target of the context + named '0' to 'N-1' under the contexts/ directory. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//targets//pid_target +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing to and reading from this file sets and gets the pid of + the target process if the context is for virtual address spaces + monitoring, respectively. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//targets//regions/nr_regions +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing a number 'N' to this file creates the number of + directories for setting each DAMON target memory region of the + context named '0' to 'N-1' under the regions/ directory. In + case of the virtual address space monitoring, DAMON + automatically sets the target memory region based on the target + processes' mappings. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//targets//regions//start +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing to and reading from this file sets and gets the start + address of the monitoring region. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//targets//regions//end +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing to and reading from this file sets and gets the end + address of the monitoring region. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes/nr_schemes +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing a number 'N' to this file creates the number of + directories for controlling each DAMON-based operation scheme + of the context named '0' to 'N-1' under the schemes/ directory. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//action +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing to and reading from this file sets and gets the action + of the scheme. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//access_pattern/sz/min +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing to and reading from this file sets and gets the mimimum + size of the scheme's target regions in bytes. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//access_pattern/sz/max +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing to and reading from this file sets and gets the maximum + size of the scheme's target regions in bytes. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//access_pattern/nr_accesses/min +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing to and reading from this file sets and gets the manimum + 'nr_accesses' of the scheme's target regions. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//access_pattern/nr_accesses/max +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing to and reading from this file sets and gets the maximum + 'nr_accesses' of the scheme's target regions. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//access_pattern/age/min +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing to and reading from this file sets and gets the minimum + 'age' of the scheme's target regions. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//access_pattern/age/max +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing to and reading from this file sets and gets the maximum + 'age' of the scheme's target regions. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//quotas/ms +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing to and reading from this file sets and gets the time + quota of the scheme in milliseconds. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//quotas/bytes +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing to and reading from this file sets and gets the size + quota of the scheme in bytes. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//quotas/reset_interval_ms +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing to and reading from this file sets and gets the quotas + charge reset interval of the scheme in milliseconds. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//quotas/weights/sz_permil +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing to and reading from this file sets and gets the + under-quota limit regions prioritization weight for 'size' in + permil. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//quotas/weights/nr_accesses_permil +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing to and reading from this file sets and gets the + under-quota limit regions prioritization weight for + 'nr_accesses' in permil. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//quotas/weights/age_permil +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing to and reading from this file sets and gets the + under-quota limit regions prioritization weight for 'age' in + permil. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//watermarks/metric +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing to and reading from this file sets and gets the metric + of the watermarks for the scheme. The writable/readable + keywords for this file are 'none' for disabling the watermarks + feature, or 'free_mem_rate' for the system's global free memory + rate in permil. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//watermarks/interval_us +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing to and reading from this file sets and gets the metric + check interval of the watermarks for the scheme in + microseconds. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//watermarks/high +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing to and reading from this file sets and gets the high + watermark of the scheme in permil. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//watermarks/mid +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing to and reading from this file sets and gets the mid + watermark of the scheme in permil. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//watermarks/low +Date: Mar 2022 +Contact: SeongJae Park +Description: Writing to and reading from this file sets and gets the low + watermark of the scheme in permil. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//stats/nr_tried +Date: Mar 2022 +Contact: SeongJae Park +Description: Reading this file returns the number of regions that the action + of the scheme has tried to be applied. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//stats/sz_tried +Date: Mar 2022 +Contact: SeongJae Park +Description: Reading this file returns the total size of regions that the + action of the scheme has tried to be applied in bytes. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//stats/nr_applied +Date: Mar 2022 +Contact: SeongJae Park +Description: Reading this file returns the number of regions that the action + of the scheme has successfully applied. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//stats/sz_applied +Date: Mar 2022 +Contact: SeongJae Park +Description: Reading this file returns the total size of regions that the + action of the scheme has successfully applied in bytes. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//stats/qt_exceeds +Date: Mar 2022 +Contact: SeongJae Park +Description: Reading this file returns the number of the exceed events of + the scheme's quotas. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//tried_regions//start +Date: Oct 2022 +Contact: SeongJae Park +Description: Reading this file returns the start address of a memory region + that corresponding DAMON-based Operation Scheme's action has + tried to be applied. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//tried_regions//end +Date: Oct 2022 +Contact: SeongJae Park +Description: Reading this file returns the end address of a memory region + that corresponding DAMON-based Operation Scheme's action has + tried to be applied. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//tried_regions//nr_accesses +Date: Oct 2022 +Contact: SeongJae Park +Description: Reading this file returns the 'nr_accesses' of a memory region + that corresponding DAMON-based Operation Scheme's action has + tried to be applied. + +What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//tried_regions//age +Date: Oct 2022 +Contact: SeongJae Park +Description: Reading this file returns the 'age' of a memory region that + corresponding DAMON-based Operation Scheme's action has tried + to be applied. diff --git a/Documentation/admin-guide/mm/damon/index.rst b/Documentation/admin-guide/mm/damon/index.rst index 61aff88347f3c00c96edfcac3a14a4d0e3c4d42b..53762770e0e443453e5322e2e7de9f658e2f9434 100644 --- a/Documentation/admin-guide/mm/damon/index.rst +++ b/Documentation/admin-guide/mm/damon/index.rst @@ -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 0000000000000000000000000000000000000000..c09cace80651626a03fdfdf1a7aa7f233548a274 --- /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.=`` on the kernel boot command line or write +proper values to ``/sys/modules/damon_lru_sort/parameters/`` 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 0af51a9705b106930c643bd915d62def8026960d..46306f1f34b1a77229cd20ea9cb87d6c169efe58 100644 --- a/Documentation/admin-guide/mm/damon/reclaim.rst +++ b/Documentation/admin-guide/mm/damon/reclaim.rst @@ -66,6 +66,17 @@ Setting it as ``N`` disables DAMON_RECLAIM. Note that DAMON_RECLAIM could do no real monitoring and reclamation due to the watermarks-based activation condition. Refer to below descriptions for the watermarks parameter for this. +commit_inputs +------------- + +Make DAMON_RECLAIM reads the input parameters again, except ``enabled``. + +Input parameters that updated while DAMON_RECLAIM is running are not applied +by default. Once this parameter is set as ``Y``, DAMON_RECLAIM 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_RECLAIM will be disabled. + min_age ------- diff --git a/Documentation/admin-guide/mm/damon/usage.rst b/Documentation/admin-guide/mm/damon/usage.rst index 59b84904a854380290e09a8c714e8af58c460c70..d16dcf23365e94041272e2436373b352f1ed65ec 100644 --- a/Documentation/admin-guide/mm/damon/usage.rst +++ b/Documentation/admin-guide/mm/damon/usage.rst @@ -4,7 +4,7 @@ Detailed Usages =============== -DAMON provides below three interfaces for different users. +DAMON provides below interfaces for different users. - *DAMON user space tool.* `This `_ is for privileged people such as @@ -14,17 +14,21 @@ DAMON provides below three interfaces for different users. virtual and physical address spaces monitoring. For more detail, please refer to its `usage document `_. -- *debugfs interface.* - :ref:`This ` is for privileged user space programmers who +- *sysfs interface.* + :ref:`This ` is for privileged user space programmers who want more optimized use of DAMON. Using this, users can use DAMON’s major - features by reading from and writing to special debugfs files. Therefore, - you can write and use your personalized DAMON debugfs wrapper programs that - reads/writes the debugfs files instead of you. The `DAMON user space tool + features by reading from and writing to special sysfs files. Therefore, + you can write and use your personalized DAMON sysfs wrapper programs that + reads/writes the sysfs files instead of you. The `DAMON user space tool `_ is one example of such programs. It supports both virtual and physical address spaces monitoring. Note that this interface provides only simple :ref:`statistics ` for the monitoring results. For detailed monitoring results, DAMON provides a :ref:`tracepoint `. +- *debugfs interface.* + :ref:`This ` is almost identical to :ref:`sysfs interface + `. This will be removed after next LTS kernel is released, + so users should move to the :ref:`sysfs interface `. - *Kernel Space Programming Interface.* :doc:`This ` is for kernel space programmers. Using this, users can utilize every feature of DAMON most flexibly and efficiently by @@ -32,6 +36,396 @@ DAMON provides below three interfaces for different users. DAMON for various address spaces. For detail, please refer to the interface :doc:`document `. +.. _sysfs_interface: + +sysfs Interface +=============== + +DAMON sysfs interface is built when ``CONFIG_DAMON_SYSFS`` is defined. It +creates multiple directories and files under its sysfs directory, +``/kernel/mm/damon/``. You can control DAMON by writing to and reading +from the files under the directory. + +For a short example, users can monitor the virtual address space of a given +workload as below. :: + + # cd /sys/kernel/mm/damon/admin/ + # echo 1 > kdamonds/nr && echo 1 > kdamonds/0/contexts/nr + # echo vaddr > kdamonds/0/contexts/0/operations + # echo 1 > kdamonds/0/contexts/0/targets/nr + # echo $(pidof ) > kdamonds/0/contexts/0/targets/0/pid + # echo on > kdamonds/0/state + +Files Hierarchy +--------------- + +The files hierarchy of DAMON sysfs interface is shown below. In the below +figure, parents-children relations are represented with indentations, each +directory is having ``/`` suffix, and files in each directory are separated by +comma (","). :: + + /sys/kernel/mm/damon/admin + │ kdamonds/nr_kdamonds + │ │ 0/state,pid + │ │ │ contexts/nr_contexts + │ │ │ │ 0/avail_operations,operations + │ │ │ │ │ monitoring_attrs/ + │ │ │ │ │ │ intervals/sample_us,aggr_us,update_us + │ │ │ │ │ │ nr_regions/min,max + │ │ │ │ │ targets/nr_targets + │ │ │ │ │ │ 0/pid_target + │ │ │ │ │ │ │ regions/nr_regions + │ │ │ │ │ │ │ │ 0/start,end + │ │ │ │ │ │ │ │ ... + │ │ │ │ │ │ ... + │ │ │ │ │ schemes/nr_schemes + │ │ │ │ │ │ 0/action + │ │ │ │ │ │ │ access_pattern/ + │ │ │ │ │ │ │ │ sz/min,max + │ │ │ │ │ │ │ │ nr_accesses/min,max + │ │ │ │ │ │ │ │ age/min,max + │ │ │ │ │ │ │ quotas/ms,bytes,reset_interval_ms + │ │ │ │ │ │ │ │ weights/sz_permil,nr_accesses_permil,age_permil + │ │ │ │ │ │ │ watermarks/metric,interval_us,high,mid,low + │ │ │ │ │ │ │ stats/nr_tried,sz_tried,nr_applied,sz_applied,qt_exceeds + │ │ │ │ │ │ │ tried_regions/ + │ │ │ │ │ │ │ │ 0/start,end,nr_accesses,age + │ │ │ │ │ │ │ │ ... + │ │ │ │ │ │ ... + │ │ │ │ ... + │ │ ... + +Root +---- + +The root of the DAMON sysfs interface is ``/kernel/mm/damon/``, and it +has one directory named ``admin``. The directory contains the files for +privileged user space programs' control of DAMON. User space tools or deamons +having the root permission could use this directory. + +kdamonds/ +--------- + +The monitoring-related information including request specifications and results +are called DAMON context. DAMON executes each context with a kernel thread +called kdamond, and multiple kdamonds could run in parallel. + +Under the ``admin`` directory, one directory, ``kdamonds``, which has files for +controlling the kdamonds exist. In the beginning, this directory has only one +file, ``nr_kdamonds``. Writing a number (``N``) to the file creates the number +of child directories named ``0`` to ``N-1``. Each directory represents each +kdamond. + +kdamonds// +------------- + +In each kdamond directory, two files (``state`` and ``pid``) and one directory +(``contexts``) exist. + +Reading ``state`` returns ``on`` if the kdamond is currently running, or +``off`` if it is not running. Writing ``on`` or ``off`` makes the kdamond be +in the state. Writing ``commit`` to the ``state`` file makes kdamond reads the +user inputs in the sysfs files except ``state`` file again. Writing +``update_schemes_stats`` to ``state`` file updates the contents of stats files +for each DAMON-based operation scheme of the kdamond. For details of the +stats, please refer to :ref:`stats section `. Writing +``update_schemes_tried_regions`` to ``state`` file updates the DAMON-based +operation scheme action tried regions directory for each DAMON-based operation +scheme of the kdamond. Writing ``clear_schemes_tried_regions`` to ``state`` +file clears the DAMON-based operating scheme action tried regions directory for +each DAMON-based operation scheme of the kdamond. For details of the +DAMON-based operation scheme action tried regions directory, please refer to +:ref:tried_regions section `. + +If the state is ``on``, reading ``pid`` shows the pid of the kdamond thread. + +``contexts`` directory contains files for controlling the monitoring contexts +that this kdamond will execute. + +kdamonds//contexts/ +---------------------- + +In the beginning, this directory has only one file, ``nr_contexts``. Writing a +number (``N``) to the file creates the number of child directories named as +``0`` to ``N-1``. Each directory represents each monitoring context. At the +moment, only one context per kdamond is supported, so only ``0`` or ``1`` can +be written to the file. + +contexts// +------------- + +In each context directory, two files (``avail_operations`` and ``operations``) +and three directories (``monitoring_attrs``, ``targets``, and ``schemes``) +exist. + +DAMON supports multiple types of monitoring operations, including those for +virtual address space and the physical address space. You can get the list of +available monitoring operations set on the currently running kernel by reading +``avail_operations`` file. Based on the kernel configuration, the file will +list some or all of below keywords. + + - vaddr: Monitor virtual address spaces of specific processes + - fvaddr: Monitor fixed virtual address ranges + - paddr: Monitor the physical address space of the system + +Please refer to :ref:`regions sysfs directory ` for detailed +differences between the operations sets in terms of the monitoring target +regions. + +You can set and get what type of monitoring operations DAMON will use for the +context by writing one of the keywords listed in ``avail_operations`` file and +reading from the ``operations`` file. + +.. _sysfs_monitoring_attrs: + +contexts//monitoring_attrs/ +------------------------------ + +Files for specifying attributes of the monitoring including required quality +and efficiency of the monitoring are in ``monitoring_attrs`` directory. +Specifically, two directories, ``intervals`` and ``nr_regions`` exist in this +directory. + +Under ``intervals`` directory, three files for DAMON's sampling interval +(``sample_us``), aggregation interval (``aggr_us``), and update interval +(``update_us``) exist. You can set and get the values in micro-seconds by +writing to and reading from the files. + +Under ``nr_regions`` directory, two files for the lower-bound and upper-bound +of DAMON's monitoring regions (``min`` and ``max``, respectively), which +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`). + +contexts//targets/ +--------------------- + +In the beginning, this directory has only one file, ``nr_targets``. Writing a +number (``N``) to the file creates the number of child directories named ``0`` +to ``N-1``. Each directory represents each monitoring target. + +targets// +------------ + +In each target directory, one file (``pid_target``) and one directory +(``regions``) exist. + +If you wrote ``vaddr`` to the ``contexts//operations``, each target should +be a process. You can specify the process to DAMON by writing the pid of the +process to the ``pid_target`` file. + +.. _sysfs_regions: + +targets//regions +------------------- + +When ``vaddr`` monitoring operations set is being used (``vaddr`` is written to +the ``contexts//operations`` file), DAMON automatically sets and updates the +monitoring target regions so that entire memory mappings of target processes +can be covered. However, users could want to set the initial monitoring region +to specific address ranges. + +In contrast, DAMON do not automatically sets and updates the monitoring target +regions when ``fvaddr`` or ``paddr`` monitoring operations sets are being used +(``fvaddr`` or ``paddr`` have written to the ``contexts//operations``). +Therefore, users should set the monitoring target regions by themselves in the +cases. + +For such cases, users can explicitly set the initial monitoring target regions +as they want, by writing proper values to the files under this directory. + +In the beginning, this directory has only one file, ``nr_regions``. Writing a +number (``N``) to the file creates the number of child directories named ``0`` +to ``N-1``. Each directory represents each initial monitoring target region. + +regions// +------------ + +In each region directory, you will find two files (``start`` and ``end``). You +can set and get the start and end addresses of the initial monitoring target +region by writing to and reading from the files, respectively. + +contexts//schemes/ +--------------------- + +For usual DAMON-based data access aware memory management optimizations, users +would normally want the system to apply a memory management action to a memory +region of a specific access pattern. DAMON receives such formalized operation +schemes from the user and applies those to the target memory regions. Users +can get and set the schemes by reading from and writing to files under this +directory. + +In the beginning, this directory has only one file, ``nr_schemes``. Writing a +number (``N``) to the file creates the number of child directories named ``0`` +to ``N-1``. Each directory represents each DAMON-based operation scheme. + +schemes// +------------ + +In each scheme directory, five directories (``access_pattern``, ``quotas``, +``watermarks``, ``stats``, and ``tried_regions``) and one file (``action``) +exist. + +The ``action`` file is for setting and getting what action you want to apply to +memory regions having specific access pattern of the interest. The keywords +that can be written to and read from the file and their meaning are as below. + + - ``willneed``: Call ``madvise()`` for the region with ``MADV_WILLNEED`` + - ``cold``: Call ``madvise()`` for the region with ``MADV_COLD`` + - ``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//access_pattern/ +--------------------------- + +The target access pattern of each DAMON-based operation scheme is constructed +with three ranges including the size of the region in bytes, number of +monitored accesses per aggregate interval, and number of aggregated intervals +for the age of the region. + +Under the ``access_pattern`` directory, three directories (``sz``, +``nr_accesses``, and ``age``) each having two files (``min`` and ``max``) +exist. You can set and get the access pattern for the given scheme by writing +to and reading from the ``min`` and ``max`` files under ``sz``, +``nr_accesses``, and ``age`` directories, respectively. + +schemes//quotas/ +------------------- + +Optimal ``target access pattern`` for each ``action`` is workload dependent, so +not easy to find. Worse yet, setting a scheme of some action too aggressive +can cause severe overhead. To avoid such overhead, users can limit time and +size quota for each scheme. In detail, users can ask DAMON to try to use only +up to specific time (``time quota``) for applying the action, and to apply the +action to only up to specific amount (``size quota``) of memory regions having +the target access pattern within a given time interval (``reset interval``). + +When the quota limit is expected to be exceeded, DAMON prioritizes found memory +regions of the ``target access pattern`` based on their size, access frequency, +and age. For personalized prioritization, users can set the weights for the +three properties. + +Under ``quotas`` directory, three files (``ms``, ``bytes``, +``reset_interval_ms``) and one directory (``weights``) having three files +(``sz_permil``, ``nr_accesses_permil``, and ``age_permil``) in it exist. + +You can set the ``time quota`` in milliseconds, ``size quota`` in bytes, and +``reset interval`` in milliseconds by writing the values to the three files, +respectively. You can also set the prioritization weights for size, access +frequency, and age in per-thousand unit by writing the values to the three +files under the ``weights`` directory. + +schemes//watermarks/ +----------------------- + +To allow easy activation and deactivation of each scheme based on system +status, DAMON provides a feature called watermarks. The feature receives five +values called ``metric``, ``interval``, ``high``, ``mid``, and ``low``. The +``metric`` is the system metric such as free memory ratio that can be measured. +If the metric value of the system is higher than the value in ``high`` or lower +than ``low`` at the memoent, the scheme is deactivated. If the value is lower +than ``mid``, the scheme is activated. + +Under the watermarks directory, five files (``metric``, ``interval_us``, +``high``, ``mid``, and ``low``) for setting each value exist. You can set and +get the five values by writing to the files, respectively. + +Keywords and meanings of those that can be written to the ``metric`` file are +as below. + + - none: Ignore the watermarks + - free_mem_rate: System's free memory rate (per thousand) + +The ``interval`` should written in microseconds unit. + +.. _sysfs_schemes_stats: + +schemes//stats/ +------------------ + +DAMON counts the total number and bytes of regions that each scheme is tried to +be applied, the two numbers for the regions that each scheme is successfully +applied, and the total number of the quota limit exceeds. This statistics can +be used for online analysis or tuning of the schemes. + +The statistics can be retrieved by reading the files under ``stats`` directory +(``nr_tried``, ``sz_tried``, ``nr_applied``, ``sz_applied``, and +``qt_exceeds``), respectively. The files are not updated in real time, so you +should ask DAMON sysfs interface to updte the content of the files for the +stats by writing a special keyword, ``update_schemes_stats`` to the relevant +``kdamonds//state`` file. + +.. _sysfs_schemes_tried_regions: + +schemes//tried_regions/ +-------------------------- + +When a special keyword, ``update_schemes_tried_regions``, is written to the +relevant ``kdamonds//state`` file, DAMON creates directories named integer +starting from ``0`` under this directory. Each directory contains files +exposing detailed information about each of the memory region that the +corresponding scheme's ``action`` has tried to be applied under this directory, +during next :ref:`aggregation interval `. The +information includes address range, ``nr_accesses``, , and ``age`` of the +region. + +The directories will be removed when another special keyword, +``clear_schemes_tried_regions``, is written to the relevant +``kdamonds//state`` file. + +tried_regions// +------------------ + +In each region directory, you will find four files (``start``, ``end``, +``nr_accesses``, and ``age``). Reading the files will show the start and end +addresses, ``nr_accesses``, and ``age`` of the region that corresponding +DAMON-based operation scheme ``action`` has tried to be applied. + +Example +~~~~~~~ + +Below commands applies a scheme saying "If a memory region of size in [4KiB, +8KiB] is showing accesses per aggregate interval in [0, 5] for aggregate +interval in [10, 20], page out the region. For the paging out, use only up to +10ms per second, and also don't page out more than 1GiB per second. Under the +limitation, page out memory regions having longer age first. Also, check the +free memory rate of the system every 5 seconds, start the monitoring and paging +out when the free memory rate becomes lower than 50%, but stop it if the free +memory rate becomes larger than 60%, or lower than 30%". :: + + # cd /kernel/mm/damon/admin + # # populate directories + # echo 1 > kdamonds/nr_kdamonds; echo 1 > kdamonds/0/contexts/nr_contexts; + # echo 1 > kdamonds/0/contexts/0/schemes/nr_schemes + # cd kdamonds/0/contexts/0/schemes/0 + # # set the basic access pattern and the action + # echo 4096 > access_patterns/sz/min + # echo 8192 > access_patterns/sz/max + # echo 0 > access_patterns/nr_accesses/min + # echo 5 > access_patterns/nr_accesses/max + # echo 10 > access_patterns/age/min + # echo 20 > access_patterns/age/max + # echo pageout > action + # # set quotas + # echo 10 > quotas/ms + # echo $((1024*1024*1024)) > quotas/bytes + # echo 1000 > quotas/reset_interval_ms + # # set watermark + # echo free_mem_rate > watermarks/metric + # echo 5000000 > watermarks/interval_us + # echo 600 > watermarks/high + # echo 500 > watermarks/mid + # echo 300 > watermarks/low + +Please note that it's highly recommended to use user space tools like `damo +`_ rather than manually reading and writing +the files as above. Above is only for an example. .. _debugfs_interface: diff --git a/MAINTAINERS b/MAINTAINERS index 1b5a590049fbab8c08e05f98f9761d7475e271e9..edd6bae857aaa15b613a9231afb416befa06f1d4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4886,6 +4886,7 @@ DATA ACCESS MONITOR M: SeongJae Park 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: include/linux/damon.h diff --git a/include/linux/damon.h b/include/linux/damon.h index 5e1e3a128b77a9bac6452a7fa40c69e2c2cc456b..7249ee0d3278eb98dcb6c0a15a86646af83b7ea0 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -60,19 +60,18 @@ struct damon_region { /** * struct damon_target - Represents a monitoring target. - * @id: Unique identifier for this target. + * @pid: The PID of the virtual address space to monitor. * @nr_regions: Number of monitoring target regions of this target. * @regions_list: Head of the monitoring target regions of this target. * @list: List head for siblings. * * Each monitoring context could have multiple targets. For example, a context * for virtual memory address spaces could have multiple target processes. The - * @id of each target should be unique among the targets of the context. For - * example, in the virtual address monitoring context, it could be a pidfd or - * an address of an mm_struct. + * @pid should be set for appropriate &struct damon_operations including the + * virtual address spaces monitoring operations. */ struct damon_target { - unsigned long id; + struct pid *pid; unsigned int nr_regions; struct list_head regions_list; struct list_head list; @@ -87,7 +86,10 @@ 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 */ enum damos_action { DAMOS_WILLNEED, @@ -95,7 +97,10 @@ 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, }; /** @@ -121,9 +126,9 @@ enum damos_action { * uses smaller one as the effective quota. * * For selecting regions within the quota, DAMON prioritizes current scheme's - * target memory regions using the &struct damon_primitive->get_scheme_score. + * target memory regions using the &struct damon_operations->get_scheme_score. * You could customize the prioritization logic by setting &weight_sz, - * &weight_nr_accesses, and &weight_age, because monitoring primitives are + * &weight_nr_accesses, and &weight_age, because monitoring operations are * encouraged to respect those. */ struct damos_quota { @@ -158,10 +163,12 @@ struct damos_quota { * * @DAMOS_WMARK_NONE: Ignore the watermarks of the given scheme. * @DAMOS_WMARK_FREE_MEM_RATE: Free memory rate of the system in [0,1000]. + * @NR_DAMOS_WMARK_METRICS: Total number of DAMOS watermark metrics */ enum damos_wmark_metric { DAMOS_WMARK_NONE, DAMOS_WMARK_FREE_MEM_RATE, + NR_DAMOS_WMARK_METRICS, }; /** @@ -209,13 +216,26 @@ struct damos_stat { }; /** - * struct damos - Represents a Data Access Monitoring-based Operation Scheme. + * struct damos_access_pattern - Target access pattern of the given scheme. * @min_sz_region: Minimum size of target regions. * @max_sz_region: Maximum size of target regions. * @min_nr_accesses: Minimum ``->nr_accesses`` of target regions. * @max_nr_accesses: Maximum ``->nr_accesses`` of target regions. * @min_age_region: Minimum age of target regions. * @max_age_region: Maximum age of target regions. + */ +struct damos_access_pattern { + unsigned long min_sz_region; + unsigned long max_sz_region; + unsigned int min_nr_accesses; + unsigned int max_nr_accesses; + unsigned int min_age_region; + unsigned int max_age_region; +}; + +/** + * struct damos - Represents a Data Access Monitoring-based Operation Scheme. + * @pattern: Access pattern of target regions. * @action: &damo_action to be applied to the target regions. * @quota: Control the aggressiveness of this scheme. * @wmarks: Watermarks for automated (in)activation of this scheme. @@ -223,10 +243,8 @@ struct damos_stat { * @list: List head for siblings. * * For each aggregation interval, DAMON finds regions which fit in the - * condition (&min_sz_region, &max_sz_region, &min_nr_accesses, - * &max_nr_accesses, &min_age_region, &max_age_region) and applies &action to - * those. To avoid consuming too much CPU time or IO resources for the - * &action, "a is used. + * &pattern and applies &action to those. To avoid consuming too much + * CPU time or IO resources for the &action, "a is used. * * To do the work only when needed, schemes can be activated for specific * system situations using &wmarks. If all schemes that registered to the @@ -241,12 +259,7 @@ struct damos_stat { * &action is applied. */ struct damos { - unsigned long min_sz_region; - unsigned long max_sz_region; - unsigned int min_nr_accesses; - unsigned int max_nr_accesses; - unsigned int min_age_region; - unsigned int max_age_region; + struct damos_access_pattern pattern; enum damos_action action; struct damos_quota quota; struct damos_watermarks wmarks; @@ -254,13 +267,29 @@ struct damos { struct list_head list; }; +/** + * enum damon_ops_id - Identifier for each monitoring operations implementation + * + * @DAMON_OPS_VADDR: Monitoring operations for virtual address spaces + * @DAMON_OPS_FVADDR: Monitoring operations for only fixed ranges of virtual + * address spaces + * @DAMON_OPS_PADDR: Monitoring operations for the physical address space + */ +enum damon_ops_id { + DAMON_OPS_VADDR, + DAMON_OPS_FVADDR, + DAMON_OPS_PADDR, + NR_DAMON_OPS, +}; + struct damon_ctx; /** - * struct damon_primitive - Monitoring primitives for given use cases. + * struct damon_operations - Monitoring operations for given use cases. * - * @init: Initialize primitive-internal data structures. - * @update: Update primitive-internal data structures. + * @id: Identifier of this operations set. + * @init: Initialize operations-related data structures. + * @update: Update operations-related data structures. * @prepare_access_checks: Prepare next access check of target regions. * @check_accesses: Check the accesses to target regions. * @reset_aggregated: Reset aggregated accesses monitoring results. @@ -270,18 +299,20 @@ struct damon_ctx; * @cleanup: Clean up the context. * * DAMON can be extended for various address spaces and usages. For this, - * users should register the low level primitives for their target address - * space and usecase via the &damon_ctx.primitive. Then, the monitoring thread + * users should register the low level operations for their target address + * space and usecase via the &damon_ctx.ops. Then, the monitoring thread * (&damon_ctx.kdamond) calls @init and @prepare_access_checks before starting - * the monitoring, @update after each &damon_ctx.primitive_update_interval, and + * the monitoring, @update after each &damon_ctx.ops_update_interval, and * @check_accesses, @target_valid and @prepare_access_checks after each * &damon_ctx.sample_interval. Finally, @reset_aggregated is called after each * &damon_ctx.aggr_interval. * - * @init should initialize primitive-internal data structures. For example, + * Each &struct damon_operations instance having valid @id can be registered + * via damon_register_ops() and selected by damon_select_ops() later. + * @init should initialize operations-related data structures. For example, * this could be used to construct proper monitoring target regions and link * those to @damon_ctx.adaptive_targets. - * @update should update the primitive-internal data structures. For example, + * @update should update the operations-related data structures. For example, * this could be used to update monitoring target regions for current status. * @prepare_access_checks should manipulate the monitoring regions to be * prepared for the next access check. @@ -301,7 +332,8 @@ struct damon_ctx; * monitoring. * @cleanup is called from @kdamond just before its termination. */ -struct damon_primitive { +struct damon_operations { + enum damon_ops_id id; void (*init)(struct damon_ctx *context); void (*update)(struct damon_ctx *context); void (*prepare_access_checks)(struct damon_ctx *context); @@ -313,7 +345,7 @@ struct damon_primitive { unsigned long (*apply_scheme)(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, struct damos *scheme); - bool (*target_valid)(void *target); + bool (*target_valid)(struct damon_target *t); void (*cleanup)(struct damon_ctx *context); }; @@ -321,8 +353,10 @@ struct damon_primitive { * struct damon_callback - Monitoring events notification callbacks. * * @before_start: Called before starting the monitoring. + * @after_wmarks_check: Called after each schemes' watermarks check. * @after_sampling: Called after each sampling. * @after_aggregation: Called after each aggregation. + * @before_damos_apply: Called before applying DAMOS action. * @before_terminate: Called before terminating the monitoring. * @private: User private data. * @@ -331,6 +365,11 @@ struct damon_primitive { * respectively. Therefore, those are good places for installing and cleaning * @private. * + * The monitoring thread calls @after_wmarks_check after each DAMON-based + * operation schemes' watermarks check. If users need to make changes to the + * attributes of the monitoring context while it's deactivated due to the + * watermarks, this is the good place to do. + * * The monitoring thread calls @after_sampling and @after_aggregation for each * of the sampling intervals and aggregation intervals, respectively. * Therefore, users can safely access the monitoring results without additional @@ -343,29 +382,50 @@ struct damon_callback { void *private; int (*before_start)(struct damon_ctx *context); + int (*after_wmarks_check)(struct damon_ctx *context); int (*after_sampling)(struct damon_ctx *context); int (*after_aggregation)(struct damon_ctx *context); + int (*before_damos_apply)(struct damon_ctx *context, + struct damon_target *target, + struct damon_region *region, + struct damos *scheme); void (*before_terminate)(struct damon_ctx *context); }; /** - * struct damon_ctx - Represents a context for each monitoring. This is the - * main interface that allows users to set the attributes and get the results - * of the monitoring. + * struct damon_attrs - Monitoring attributes for accuracy/overhead control. * * @sample_interval: The time between access samplings. * @aggr_interval: The time between monitor results aggregations. - * @primitive_update_interval: The time between monitoring primitive updates. + * @ops_update_interval: The time between monitoring operations updates. + * @min_nr_regions: The minimum number of adaptive monitoring + * regions. + * @max_nr_regions: The maximum number of adaptive monitoring + * regions. * * For each @sample_interval, DAMON checks whether each region is accessed or * not. It aggregates and keeps the access information (number of accesses to * each region) for @aggr_interval time. DAMON also checks whether the target * memory regions need update (e.g., by ``mmap()`` calls from the application, * in case of virtual memory monitoring) and applies the changes for each - * @primitive_update_interval. All time intervals are in micro-seconds. - * Please refer to &struct damon_primitive and &struct damon_callback for more + * @ops_update_interval. All time intervals are in micro-seconds. + * Please refer to &struct damon_operations and &struct damon_callback for more * detail. + */ +struct damon_attrs { + unsigned long sample_interval; + unsigned long aggr_interval; + unsigned long ops_update_interval; + unsigned long min_nr_regions; + unsigned long max_nr_regions; +}; + +/** + * struct damon_ctx - Represents a context for each monitoring. This is the + * main interface that allows users to set the attributes and get the results + * of the monitoring. * + * @attrs: Monitoring attributes for accuracy/overhead control. * @kdamond: Kernel thread who does the monitoring. * @kdamond_stop: Notifies whether kdamond should stop. * @kdamond_lock: Mutex for the synchronizations with @kdamond. @@ -375,7 +435,7 @@ 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_primitive.target_valid of @primitive. 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 @@ -385,32 +445,26 @@ struct damon_callback { * Note that the monitoring thread protects only @kdamond and @kdamond_stop via * @kdamond_lock. Accesses to other fields must be protected by themselves. * - * @primitive: Set of monitoring primitives for given use cases. + * @ops: Set of monitoring operations for given use cases. * @callback: Set of callbacks for monitoring events notifications. * - * @min_nr_regions: The minimum number of adaptive monitoring regions. - * @max_nr_regions: The maximum number of adaptive monitoring regions. * @adaptive_targets: Head of monitoring targets (&damon_target) list. * @schemes: Head of schemes (&damos) list. */ struct damon_ctx { - unsigned long sample_interval; - unsigned long aggr_interval; - unsigned long primitive_update_interval; + struct damon_attrs attrs; /* private: internal use only */ struct timespec64 last_aggregation; - struct timespec64 last_primitive_update; + struct timespec64 last_ops_update; /* public: */ struct task_struct *kdamond; struct mutex kdamond_lock; - struct damon_primitive primitive; + struct damon_operations ops; struct damon_callback callback; - unsigned long min_nr_regions; - unsigned long max_nr_regions; struct list_head adaptive_targets; struct list_head schemes; }; @@ -430,9 +484,23 @@ static inline struct damon_region *damon_last_region(struct damon_target *t) return list_last_entry(&t->regions_list, struct damon_region, list); } +static inline struct damon_region *damon_first_region(struct damon_target *t) +{ + return list_first_entry(&t->regions_list, struct damon_region, list); +} + +static inline unsigned long damon_sz_region(struct damon_region *r) +{ + return r->ar.end - r->ar.start; +} + + #define damon_for_each_region(r, t) \ list_for_each_entry(r, &t->regions_list, list) +#define damon_for_each_region_from(r, t) \ + list_for_each_entry_from(r, &t->regions_list, list) + #define damon_for_each_region_safe(r, next, t) \ list_for_each_entry_safe(r, next, &t->regions_list, list) @@ -465,17 +533,16 @@ static inline void damon_insert_region(struct damon_region *r, void damon_add_region(struct damon_region *r, struct damon_target *t); void damon_destroy_region(struct damon_region *r, struct damon_target *t); +int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges, + unsigned int nr_ranges); -struct damos *damon_new_scheme( - unsigned long min_sz_region, unsigned long max_sz_region, - unsigned int min_nr_accesses, unsigned int max_nr_accesses, - unsigned int min_age_region, unsigned int max_age_region, - enum damos_action action, struct damos_quota *quota, - struct damos_watermarks *wmarks); +struct damos *damon_new_scheme(struct damos_access_pattern *pattern, + enum damos_action action, struct damos_quota *quota, + struct damos_watermarks *wmarks); void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); void damon_destroy_scheme(struct damos *s); -struct damon_target *damon_new_target(unsigned long id); +struct damon_target *damon_new_target(void); void damon_add_target(struct damon_ctx *ctx, struct damon_target *t); bool damon_targets_empty(struct damon_ctx *ctx); void damon_free_target(struct damon_target *t); @@ -484,28 +551,26 @@ unsigned int damon_nr_regions(struct damon_target *t); struct damon_ctx *damon_new_ctx(void); void damon_destroy_ctx(struct damon_ctx *ctx); -int damon_set_targets(struct damon_ctx *ctx, - unsigned long *ids, ssize_t nr_ids); -int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, - unsigned long aggr_int, unsigned long primitive_upd_int, - unsigned long min_nr_reg, unsigned long max_nr_reg); -int damon_set_schemes(struct damon_ctx *ctx, +int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs); +void damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes, ssize_t nr_schemes); int damon_nr_running_ctxs(void); +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); -int damon_start(struct damon_ctx **ctxs, int nr_ctxs); -int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); +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; +} -#endif /* CONFIG_DAMON */ -#ifdef CONFIG_DAMON_VADDR -bool damon_va_target_valid(void *t); -void damon_va_set_primitives(struct damon_ctx *ctx); -#endif /* CONFIG_DAMON_VADDR */ +int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive); +int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); + +int damon_set_region_biggest_system_ram_default(struct damon_target *t, + unsigned long *start, unsigned long *end); -#ifdef CONFIG_DAMON_PADDR -bool damon_pa_target_valid(void *t); -void damon_pa_set_primitives(struct damon_ctx *ctx); -#endif /* CONFIG_DAMON_PADDR */ +#endif /* CONFIG_DAMON */ #endif /* _DAMON_H */ diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig index 5bcf05851ad078305362f897d958e2d3f3dd0167..436c6b4cb5ec57fb7e47d093569ec093d7ec7401 100644 --- a/mm/damon/Kconfig +++ b/mm/damon/Kconfig @@ -25,35 +25,42 @@ config DAMON_KUNIT_TEST If unsure, say N. config DAMON_VADDR - bool "Data access monitoring primitives for virtual address spaces" + bool "Data access monitoring operations for virtual address spaces" depends on DAMON && MMU select PAGE_IDLE_FLAG help - This builds the default data access monitoring primitives for DAMON + This builds the default data access monitoring operations for DAMON that work for virtual address spaces. config DAMON_PADDR - bool "Data access monitoring primitives for the physical address space" + bool "Data access monitoring operations for the physical address space" depends on DAMON && MMU select PAGE_IDLE_FLAG help - This builds the default data access monitoring primitives for DAMON + This builds the default data access monitoring operations for DAMON that works for the physical address space. config DAMON_VADDR_KUNIT_TEST - bool "Test for DAMON primitives" if !KUNIT_ALL_TESTS + bool "Test for DAMON operations" if !KUNIT_ALL_TESTS depends on DAMON_VADDR && KUNIT=y default KUNIT_ALL_TESTS help - This builds the DAMON virtual addresses primitives Kunit test suite. + This builds the DAMON virtual addresses operations Kunit test suite. For more information on KUnit and unit tests in general, please refer to the KUnit documentation. If unsure, say N. +config DAMON_SYSFS + bool "DAMON sysfs interface" + depends on DAMON && SYSFS + help + This builds the sysfs interface for DAMON. The user space can use + the interface for arbitrary data access monitoring. + config DAMON_DBGFS - bool "DAMON debugfs interface" + bool "DAMON debugfs interface (DEPRECATED!)" depends on DAMON_VADDR && DAMON_PADDR && DEBUG_FS help This builds the debugfs interface for DAMON. The user space admins @@ -61,6 +68,10 @@ config DAMON_DBGFS If unsure, say N. + This is deprecated, so users should move to the sysfs interface + (DAMON_SYSFS). If you depend on this and cannot move, please report + your usecase to damon@lists.linux.dev and linux-mm@kvack.org. + config DAMON_DBGFS_KUNIT_TEST bool "Test for damon debugfs interface" if !KUNIT_ALL_TESTS depends on DAMON_DBGFS && KUNIT=y @@ -85,4 +96,12 @@ 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 f7d5ac377a2bb5551e9fe60882b961825d4f492f..f7add3f4aa793b012bb644fbd85d677d1d3cbb98 100644 --- a/mm/damon/Makefile +++ b/mm/damon/Makefile @@ -1,7 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_DAMON) := core.o -obj-$(CONFIG_DAMON_VADDR) += prmtv-common.o vaddr.o -obj-$(CONFIG_DAMON_PADDR) += prmtv-common.o paddr.o +obj-y := core.o +obj-$(CONFIG_DAMON_VADDR) += ops-common.o vaddr.o +obj-$(CONFIG_DAMON_PADDR) += ops-common.o paddr.o +obj-$(CONFIG_DAMON_SYSFS) += sysfs-common.o sysfs-schemes.o sysfs.o obj-$(CONFIG_DAMON_DBGFS) += dbgfs.o -obj-$(CONFIG_DAMON_RECLAIM) += reclaim.o +obj-$(CONFIG_DAMON_RECLAIM) += modules-common.o reclaim.o +obj-$(CONFIG_DAMON_LRU_SORT) += modules-common.o lru_sort.o diff --git a/mm/damon/core-test.h b/mm/damon/core-test.h index 7008c3735e99f1d486109aeb8d9b3ccfbf68b6fb..3db9b73687562aebfb6d27e62bd716bc7e4b94c9 100644 --- a/mm/damon/core-test.h +++ b/mm/damon/core-test.h @@ -24,7 +24,7 @@ static void damon_test_regions(struct kunit *test) KUNIT_EXPECT_EQ(test, 2ul, r->ar.end); KUNIT_EXPECT_EQ(test, 0u, r->nr_accesses); - t = damon_new_target(42); + t = damon_new_target(); KUNIT_EXPECT_EQ(test, 0u, damon_nr_regions(t)); damon_add_region(r, t); @@ -52,8 +52,7 @@ static void damon_test_target(struct kunit *test) struct damon_ctx *c = damon_new_ctx(); struct damon_target *t; - t = damon_new_target(42); - KUNIT_EXPECT_EQ(test, 42ul, t->id); + t = damon_new_target(); KUNIT_EXPECT_EQ(test, 0u, nr_damon_targets(c)); damon_add_target(c, t); @@ -78,7 +77,6 @@ static void damon_test_target(struct kunit *test) static void damon_test_aggregate(struct kunit *test) { struct damon_ctx *ctx = damon_new_ctx(); - unsigned long target_ids[] = {1, 2, 3}; unsigned long saddr[][3] = {{10, 20, 30}, {5, 42, 49}, {13, 33, 55} }; unsigned long eaddr[][3] = {{15, 27, 40}, {31, 45, 55}, {23, 44, 66} }; unsigned long accesses[][3] = {{42, 95, 84}, {10, 20, 30}, {0, 1, 2} }; @@ -86,7 +84,10 @@ static void damon_test_aggregate(struct kunit *test) struct damon_region *r; int it, ir; - damon_set_targets(ctx, target_ids, 3); + for (it = 0; it < 3; it++) { + t = damon_new_target(); + damon_add_target(ctx, t); + } it = 0; damon_for_each_target(t, ctx) { @@ -122,10 +123,10 @@ static void damon_test_split_at(struct kunit *test) struct damon_target *t; struct damon_region *r; - t = damon_new_target(42); + t = damon_new_target(); r = damon_new_region(0, 100); damon_add_region(r, t); - damon_split_region_at(c, t, r, 25); + damon_split_region_at(t, r, 25); KUNIT_EXPECT_EQ(test, r->ar.start, 0ul); KUNIT_EXPECT_EQ(test, r->ar.end, 25ul); @@ -143,7 +144,7 @@ static void damon_test_merge_two(struct kunit *test) struct damon_region *r, *r2, *r3; int i; - t = damon_new_target(42); + t = damon_new_target(); r = damon_new_region(0, 100); r->nr_accesses = 10; damon_add_region(r, t); @@ -191,7 +192,7 @@ static void damon_test_merge_regions_of(struct kunit *test) unsigned long eaddrs[] = {112, 130, 156, 170, 230}; int i; - t = damon_new_target(42); + t = damon_new_target(); for (i = 0; i < ARRAY_SIZE(sa); i++) { r = damon_new_region(sa[i], ea[i]); r->nr_accesses = nrs[i]; @@ -215,22 +216,79 @@ static void damon_test_split_regions_of(struct kunit *test) struct damon_target *t; struct damon_region *r; - t = damon_new_target(42); + t = damon_new_target(); r = damon_new_region(0, 22); damon_add_region(r, t); - damon_split_regions_of(c, t, 2); + damon_split_regions_of(t, 2); KUNIT_EXPECT_LE(test, damon_nr_regions(t), 2u); damon_free_target(t); - t = damon_new_target(42); + t = damon_new_target(); r = damon_new_region(0, 220); damon_add_region(r, t); - damon_split_regions_of(c, t, 4); + damon_split_regions_of(t, 4); KUNIT_EXPECT_LE(test, damon_nr_regions(t), 4u); damon_free_target(t); damon_destroy_ctx(c); } +static void damon_test_ops_registration(struct kunit *test) +{ + struct damon_ctx *c = damon_new_ctx(); + struct damon_operations ops, bak; + + /* DAMON_OPS_{V,P}ADDR are registered on subsys_initcall */ + KUNIT_EXPECT_EQ(test, damon_select_ops(c, DAMON_OPS_VADDR), 0); + KUNIT_EXPECT_EQ(test, damon_select_ops(c, DAMON_OPS_PADDR), 0); + + /* Double-registration is prohibited */ + ops.id = DAMON_OPS_VADDR; + KUNIT_EXPECT_EQ(test, damon_register_ops(&ops), -EINVAL); + ops.id = DAMON_OPS_PADDR; + KUNIT_EXPECT_EQ(test, damon_register_ops(&ops), -EINVAL); + + /* Unknown ops id cannot be registered */ + KUNIT_EXPECT_EQ(test, damon_select_ops(c, NR_DAMON_OPS), -EINVAL); + + /* Registration should success after unregistration */ + mutex_lock(&damon_ops_lock); + bak = damon_registered_ops[DAMON_OPS_VADDR]; + damon_registered_ops[DAMON_OPS_VADDR] = (struct damon_operations){}; + mutex_unlock(&damon_ops_lock); + + ops.id = DAMON_OPS_VADDR; + KUNIT_EXPECT_EQ(test, damon_register_ops(&ops), 0); + + mutex_lock(&damon_ops_lock); + damon_registered_ops[DAMON_OPS_VADDR] = bak; + mutex_unlock(&damon_ops_lock); + + /* Check double-registration failure again */ + KUNIT_EXPECT_EQ(test, damon_register_ops(&ops), -EINVAL); +} + +static void damon_test_set_regions(struct kunit *test) +{ + struct damon_target *t = damon_new_target(); + struct damon_region *r1 = damon_new_region(4, 16); + struct damon_region *r2 = damon_new_region(24, 32); + struct damon_addr_range range = {.start = 8, .end = 28}; + unsigned long expects[] = {8, 16, 16, 24, 24, 28}; + int expect_idx = 0; + struct damon_region *r; + + damon_add_region(r1, t); + damon_add_region(r2, t); + damon_set_regions(t, &range, 1); + + KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 3); + damon_for_each_region(r, t) { + KUNIT_EXPECT_EQ(test, r->ar.start, expects[expect_idx++]); + KUNIT_EXPECT_EQ(test, r->ar.end, expects[expect_idx++]); + } + damon_destroy_target(t); +} + static struct kunit_case damon_test_cases[] = { KUNIT_CASE(damon_test_target), KUNIT_CASE(damon_test_regions), @@ -239,6 +297,8 @@ static struct kunit_case damon_test_cases[] = { KUNIT_CASE(damon_test_merge_two), KUNIT_CASE(damon_test_merge_regions_of), KUNIT_CASE(damon_test_split_regions_of), + KUNIT_CASE(damon_test_ops_registration), + KUNIT_CASE(damon_test_set_regions), {}, }; diff --git a/mm/damon/core.c b/mm/damon/core.c index 1dd153c31c9e2b8e5fd6bc7d608f830e768f9c1e..ceec75b88ef9604fb50b154da23a837abed1e37d 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -24,6 +24,93 @@ static DEFINE_MUTEX(damon_lock); static int nr_running_ctxs; +static bool running_exclusive_ctxs; + +static DEFINE_MUTEX(damon_ops_lock); +static struct damon_operations damon_registered_ops[NR_DAMON_OPS]; + +static struct kmem_cache *damon_region_cache __ro_after_init; + +/* Should be called under damon_ops_lock with id smaller than NR_DAMON_OPS */ +static bool __damon_is_registered_ops(enum damon_ops_id id) +{ + struct damon_operations empty_ops = {}; + + if (!memcmp(&empty_ops, &damon_registered_ops[id], sizeof(empty_ops))) + return false; + return true; +} + +/** + * damon_is_registered_ops() - Check if a given damon_operations is registered. + * @id: Id of the damon_operations to check if registered. + * + * Return: true if the ops is set, false otherwise. + */ +bool damon_is_registered_ops(enum damon_ops_id id) +{ + bool registered; + + if (id >= NR_DAMON_OPS) + return false; + mutex_lock(&damon_ops_lock); + registered = __damon_is_registered_ops(id); + mutex_unlock(&damon_ops_lock); + return registered; +} + +/** + * damon_register_ops() - Register a monitoring operations set to DAMON. + * @ops: monitoring operations set to register. + * + * This function registers a monitoring operations set of valid &struct + * damon_operations->id so that others can find and use them later. + * + * Return: 0 on success, negative error code otherwise. + */ +int damon_register_ops(struct damon_operations *ops) +{ + int err = 0; + + if (ops->id >= NR_DAMON_OPS) + return -EINVAL; + mutex_lock(&damon_ops_lock); + /* Fail for already registered ops */ + if (__damon_is_registered_ops(ops->id)) { + err = -EINVAL; + goto out; + } + damon_registered_ops[ops->id] = *ops; +out: + mutex_unlock(&damon_ops_lock); + return err; +} + +/** + * damon_select_ops() - Select a monitoring operations to use with the context. + * @ctx: monitoring context to use the operations. + * @id: id of the registered monitoring operations to select. + * + * This function finds registered monitoring operations set of @id and make + * @ctx to use it. + * + * Return: 0 on success, negative error code otherwise. + */ +int damon_select_ops(struct damon_ctx *ctx, enum damon_ops_id id) +{ + int err = 0; + + if (id >= NR_DAMON_OPS) + return -EINVAL; + + mutex_lock(&damon_ops_lock); + if (!__damon_is_registered_ops(id)) + err = -EINVAL; + else + ctx->ops = damon_registered_ops[id]; + mutex_unlock(&damon_ops_lock); + return err; +} /* * Construct a damon_region struct @@ -34,7 +121,7 @@ struct damon_region *damon_new_region(unsigned long start, unsigned long end) { struct damon_region *region; - region = kmalloc(sizeof(*region), GFP_KERNEL); + region = kmem_cache_alloc(damon_region_cache, GFP_KERNEL); if (!region) return NULL; @@ -63,7 +150,7 @@ static void damon_del_region(struct damon_region *r, struct damon_target *t) static void damon_free_region(struct damon_region *r) { - kfree(r); + kmem_cache_free(damon_region_cache, r); } void damon_destroy_region(struct damon_region *r, struct damon_target *t) @@ -72,47 +159,140 @@ void damon_destroy_region(struct damon_region *r, struct damon_target *t) damon_free_region(r); } -struct damos *damon_new_scheme( - unsigned long min_sz_region, unsigned long max_sz_region, - unsigned int min_nr_accesses, unsigned int max_nr_accesses, - unsigned int min_age_region, unsigned int max_age_region, - enum damos_action action, struct damos_quota *quota, - struct damos_watermarks *wmarks) +/* + * Check whether a region is intersecting an address range + * + * Returns true if it is. + */ +static bool damon_intersect(struct damon_region *r, + struct damon_addr_range *re) +{ + return !(r->ar.end <= re->start || re->end <= r->ar.start); +} + +/* + * Fill holes in regions with new regions. + */ +static int damon_fill_regions_holes(struct damon_region *first, + struct damon_region *last, struct damon_target *t) +{ + struct damon_region *r = first; + + damon_for_each_region_from(r, t) { + struct damon_region *next, *newr; + + if (r == last) + break; + next = damon_next_region(r); + if (r->ar.end != next->ar.start) { + newr = damon_new_region(r->ar.end, next->ar.start); + if (!newr) + return -ENOMEM; + damon_insert_region(newr, r, next, t); + } + } + return 0; +} + +/* + * damon_set_regions() - Set regions of a target for given address ranges. + * @t: the given target. + * @ranges: array of new monitoring target ranges. + * @nr_ranges: length of @ranges. + * + * This function adds new regions to, or modify existing regions of a + * monitoring target to fit in specific ranges. + * + * Return: 0 if success, or negative error code otherwise. + */ +int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges, + unsigned int nr_ranges) +{ + struct damon_region *r, *next; + unsigned int i; + int err; + + /* Remove regions which are not in the new ranges */ + damon_for_each_region_safe(r, next, t) { + for (i = 0; i < nr_ranges; i++) { + if (damon_intersect(r, &ranges[i])) + break; + } + if (i == nr_ranges) + damon_destroy_region(r, t); + } + + r = damon_first_region(t); + /* Add new regions or resize existing regions to fit in the ranges */ + for (i = 0; i < nr_ranges; i++) { + struct damon_region *first = NULL, *last, *newr; + struct damon_addr_range *range; + + range = &ranges[i]; + /* Get the first/last regions intersecting with the range */ + damon_for_each_region_from(r, t) { + if (damon_intersect(r, range)) { + if (!first) + first = r; + last = r; + } + if (r->ar.start >= range->end) + break; + } + if (!first) { + /* no region intersects with this range */ + newr = damon_new_region( + ALIGN_DOWN(range->start, + DAMON_MIN_REGION), + ALIGN(range->end, DAMON_MIN_REGION)); + if (!newr) + return -ENOMEM; + damon_insert_region(newr, damon_prev_region(r), r, t); + } else { + /* resize intersecting regions to fit in this range */ + first->ar.start = ALIGN_DOWN(range->start, + DAMON_MIN_REGION); + last->ar.end = ALIGN(range->end, DAMON_MIN_REGION); + + /* fill possible holes in the range */ + err = damon_fill_regions_holes(first, last, t); + if (err) + return err; + } + } + return 0; +} + +/* initialize private fields of damos_quota and return the pointer */ +static struct damos_quota *damos_quota_init_priv(struct damos_quota *quota) +{ + quota->total_charged_sz = 0; + quota->total_charged_ns = 0; + quota->esz = 0; + quota->charged_sz = 0; + quota->charged_from = 0; + quota->charge_target_from = NULL; + quota->charge_addr_from = 0; + return quota; +} + +struct damos *damon_new_scheme(struct damos_access_pattern *pattern, + enum damos_action action, struct damos_quota *quota, + struct damos_watermarks *wmarks) { struct damos *scheme; scheme = kmalloc(sizeof(*scheme), GFP_KERNEL); if (!scheme) return NULL; - scheme->min_sz_region = min_sz_region; - scheme->max_sz_region = max_sz_region; - scheme->min_nr_accesses = min_nr_accesses; - scheme->max_nr_accesses = max_nr_accesses; - scheme->min_age_region = min_age_region; - scheme->max_age_region = max_age_region; + scheme->pattern = *pattern; scheme->action = action; scheme->stat = (struct damos_stat){}; INIT_LIST_HEAD(&scheme->list); - scheme->quota.ms = quota->ms; - scheme->quota.sz = quota->sz; - scheme->quota.reset_interval = quota->reset_interval; - scheme->quota.weight_sz = quota->weight_sz; - scheme->quota.weight_nr_accesses = quota->weight_nr_accesses; - scheme->quota.weight_age = quota->weight_age; - scheme->quota.total_charged_sz = 0; - scheme->quota.total_charged_ns = 0; - scheme->quota.esz = 0; - scheme->quota.charged_sz = 0; - scheme->quota.charged_from = 0; - scheme->quota.charge_target_from = NULL; - scheme->quota.charge_addr_from = 0; - - scheme->wmarks.metric = wmarks->metric; - scheme->wmarks.interval = wmarks->interval; - scheme->wmarks.high = wmarks->high; - scheme->wmarks.mid = wmarks->mid; - scheme->wmarks.low = wmarks->low; + scheme->quota = *(damos_quota_init_priv(quota)); + + scheme->wmarks = *wmarks; scheme->wmarks.activated = true; return scheme; @@ -144,7 +324,7 @@ void damon_destroy_scheme(struct damos *s) * * Returns the pointer to the new struct if success, or NULL otherwise */ -struct damon_target *damon_new_target(unsigned long id) +struct damon_target *damon_new_target(void) { struct damon_target *t; @@ -152,9 +332,10 @@ struct damon_target *damon_new_target(unsigned long id) if (!t) return NULL; - t->id = id; + t->pid = NULL; t->nr_regions = 0; INIT_LIST_HEAD(&t->regions_list); + INIT_LIST_HEAD(&t->list); return t; } @@ -202,17 +383,17 @@ struct damon_ctx *damon_new_ctx(void) if (!ctx) return NULL; - ctx->sample_interval = 5 * 1000; - ctx->aggr_interval = 100 * 1000; - ctx->primitive_update_interval = 60 * 1000 * 1000; + ctx->attrs.sample_interval = 5 * 1000; + ctx->attrs.aggr_interval = 100 * 1000; + ctx->attrs.ops_update_interval = 60 * 1000 * 1000; ktime_get_coarse_ts64(&ctx->last_aggregation); - ctx->last_primitive_update = ctx->last_aggregation; + ctx->last_ops_update = ctx->last_aggregation; mutex_init(&ctx->kdamond_lock); - ctx->min_nr_regions = 10; - ctx->max_nr_regions = 1000; + ctx->attrs.min_nr_regions = 10; + ctx->attrs.max_nr_regions = 1000; INIT_LIST_HEAD(&ctx->adaptive_targets); INIT_LIST_HEAD(&ctx->schemes); @@ -224,8 +405,8 @@ static void damon_destroy_targets(struct damon_ctx *ctx) { struct damon_target *t, *next_t; - if (ctx->primitive.cleanup) { - ctx->primitive.cleanup(ctx); + if (ctx->ops.cleanup) { + ctx->ops.cleanup(ctx); return; } @@ -245,67 +426,24 @@ void damon_destroy_ctx(struct damon_ctx *ctx) kfree(ctx); } -/** - * damon_set_targets() - Set monitoring targets. - * @ctx: monitoring context - * @ids: array of target ids - * @nr_ids: number of entries in @ids - * - * This function should not be called while the kdamond is running. - * - * Return: 0 on success, negative error code otherwise. - */ -int damon_set_targets(struct damon_ctx *ctx, - unsigned long *ids, ssize_t nr_ids) -{ - ssize_t i; - struct damon_target *t, *next; - - damon_destroy_targets(ctx); - - for (i = 0; i < nr_ids; i++) { - t = damon_new_target(ids[i]); - if (!t) { - /* The caller should do cleanup of the ids itself */ - damon_for_each_target_safe(t, next, ctx) - damon_destroy_target(t); - return -ENOMEM; - } - damon_add_target(ctx, t); - } - - return 0; -} - /** * damon_set_attrs() - Set attributes for the monitoring. * @ctx: monitoring context - * @sample_int: time interval between samplings - * @aggr_int: time interval between aggregations - * @primitive_upd_int: time interval between monitoring primitive updates - * @min_nr_reg: minimal number of regions - * @max_nr_reg: maximum number of regions + * @attrs: monitoring attributes * * This function should not be called while the kdamond is running. * Every time interval is in micro-seconds. * * Return: 0 on success, negative error code otherwise. */ -int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, - unsigned long aggr_int, unsigned long primitive_upd_int, - unsigned long min_nr_reg, unsigned long max_nr_reg) +int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs) { - if (min_nr_reg < 3) + if (attrs->min_nr_regions < 3) return -EINVAL; - if (min_nr_reg > max_nr_reg) + if (attrs->min_nr_regions > attrs->max_nr_regions) return -EINVAL; - ctx->sample_interval = sample_int; - ctx->aggr_interval = aggr_int; - ctx->primitive_update_interval = primitive_upd_int; - ctx->min_nr_regions = min_nr_reg; - ctx->max_nr_regions = max_nr_reg; - + ctx->attrs = *attrs; return 0; } @@ -317,10 +455,8 @@ int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, * * This function should not be called while the kdamond of the context is * running. - * - * Return: 0 if success, or negative error code otherwise. */ -int damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes, +void damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes, ssize_t nr_schemes) { struct damos *s, *next; @@ -330,7 +466,6 @@ int damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes, damon_destroy_scheme(s); for (i = 0; i < nr_schemes; i++) damon_add_scheme(ctx, schemes[i]); - return 0; } /** @@ -356,11 +491,11 @@ static unsigned long damon_region_sz_limit(struct damon_ctx *ctx) damon_for_each_target(t, ctx) { damon_for_each_region(r, t) - sz += r->ar.end - r->ar.start; + sz += damon_sz_region(r); } - if (ctx->min_nr_regions) - sz /= ctx->min_nr_regions; + if (ctx->attrs.min_nr_regions) + sz /= ctx->attrs.min_nr_regions; if (sz < DAMON_MIN_REGION) sz = DAMON_MIN_REGION; @@ -400,22 +535,25 @@ static int __damon_start(struct damon_ctx *ctx) * damon_start() - Starts the monitorings for a given group of contexts. * @ctxs: an array of the pointers for contexts to start monitoring * @nr_ctxs: size of @ctxs + * @exclusive: exclusiveness of this contexts group * * This function starts a group of monitoring threads for a group of monitoring * contexts. One thread per each context is created and run in parallel. The - * caller should handle synchronization between the threads by itself. If a - * group of threads that created by other 'damon_start()' call is currently - * running, this function does nothing but returns -EBUSY. + * caller should handle synchronization between the threads by itself. If + * @exclusive is true and a group of threads that created by other + * 'damon_start()' call is currently running, this function does nothing but + * returns -EBUSY. * * Return: 0 on success, negative error code otherwise. */ -int damon_start(struct damon_ctx **ctxs, int nr_ctxs) +int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive) { int i; int err = 0; mutex_lock(&damon_lock); - if (nr_running_ctxs) { + if ((exclusive && nr_running_ctxs) || + (!exclusive && running_exclusive_ctxs)) { mutex_unlock(&damon_lock); return -EBUSY; } @@ -426,13 +564,15 @@ int damon_start(struct damon_ctx **ctxs, int nr_ctxs) break; nr_running_ctxs++; } + if (exclusive && nr_running_ctxs) + running_exclusive_ctxs = true; mutex_unlock(&damon_lock); return err; } /* - * __damon_stop() - Stops monitoring of given context. + * __damon_stop() - Stops monitoring of a given context. * @ctx: monitoring context * * Return: 0 on success, negative error code otherwise. @@ -470,9 +610,8 @@ int damon_stop(struct damon_ctx **ctxs, int nr_ctxs) /* nr_running_ctxs is decremented in kdamond_fn */ err = __damon_stop(ctxs[i]); if (err) - return err; + break; } - return err; } @@ -505,7 +644,7 @@ static bool damon_check_reset_time_interval(struct timespec64 *baseline, static bool kdamond_aggregate_interval_passed(struct damon_ctx *ctx) { return damon_check_reset_time_interval(&ctx->last_aggregation, - ctx->aggr_interval); + ctx->attrs.aggr_interval); } /* @@ -528,19 +667,20 @@ static void kdamond_reset_aggregated(struct damon_ctx *c) } } -static void damon_split_region_at(struct damon_ctx *ctx, - struct damon_target *t, struct damon_region *r, - unsigned long sz_r); +static void damon_split_region_at(struct damon_target *t, + struct damon_region *r, unsigned long sz_r); static bool __damos_valid_target(struct damon_region *r, struct damos *s) { unsigned long sz; - sz = r->ar.end - r->ar.start; - return s->min_sz_region <= sz && sz <= s->max_sz_region && - s->min_nr_accesses <= r->nr_accesses && - r->nr_accesses <= s->max_nr_accesses && - s->min_age_region <= r->age && r->age <= s->max_age_region; + sz = damon_sz_region(r); + return s->pattern.min_sz_region <= sz && + sz <= s->pattern.max_sz_region && + s->pattern.min_nr_accesses <= r->nr_accesses && + r->nr_accesses <= s->pattern.max_nr_accesses && + s->pattern.min_age_region <= r->age && + r->age <= s->pattern.max_age_region; } static bool damos_valid_target(struct damon_ctx *c, struct damon_target *t, @@ -548,10 +688,119 @@ static bool damos_valid_target(struct damon_ctx *c, struct damon_target *t, { bool ret = __damos_valid_target(r, s); - if (!ret || !s->quota.esz || !c->primitive.get_scheme_score) + if (!ret || !s->quota.esz || !c->ops.get_scheme_score) return ret; - return c->primitive.get_scheme_score(c, t, r, s) >= s->quota.min_score; + return c->ops.get_scheme_score(c, t, r, s) >= s->quota.min_score; +} + +/* + * damos_skip_charged_region() - Check if the given region or starting part of + * it is already charged for the DAMOS quota. + * @t: The target of the region. + * @rp: The pointer to the region. + * @s: The scheme to be applied. + * + * If a quota of a scheme has exceeded in a quota charge window, the scheme's + * action would applied to only a part of the target access pattern fulfilling + * regions. To avoid applying the scheme action to only already applied + * regions, DAMON skips applying the scheme action to the regions that charged + * in the previous charge window. + * + * This function checks if a given region should be skipped or not for the + * reason. If only the starting part of the region has previously charged, + * this function splits the region into two so that the second one covers the + * area that not charged in the previous charge widnow and saves the second + * region in *rp and returns false, so that the caller can apply DAMON action + * to the second one. + * + * Return: true if the region should be entirely skipped, false otherwise. + */ +static bool damos_skip_charged_region(struct damon_target *t, + struct damon_region **rp, struct damos *s) +{ + struct damon_region *r = *rp; + struct damos_quota *quota = &s->quota; + unsigned long sz_to_skip; + + /* Skip previously charged regions */ + if (quota->charge_target_from) { + if (t != quota->charge_target_from) + return true; + if (r == damon_last_region(t)) { + quota->charge_target_from = NULL; + quota->charge_addr_from = 0; + return true; + } + if (quota->charge_addr_from && + r->ar.end <= quota->charge_addr_from) + return true; + + if (quota->charge_addr_from && r->ar.start < + quota->charge_addr_from) { + sz_to_skip = ALIGN_DOWN(quota->charge_addr_from - + r->ar.start, DAMON_MIN_REGION); + if (!sz_to_skip) { + if (damon_sz_region(r) <= DAMON_MIN_REGION) + return true; + sz_to_skip = DAMON_MIN_REGION; + } + damon_split_region_at(t, r, sz_to_skip); + r = damon_next_region(r); + *rp = r; + } + quota->charge_target_from = NULL; + quota->charge_addr_from = 0; + } + return false; +} + +static void damos_update_stat(struct damos *s, + unsigned long sz_tried, unsigned long sz_applied) +{ + s->stat.nr_tried++; + s->stat.sz_tried += sz_tried; + if (sz_applied) + s->stat.nr_applied++; + s->stat.sz_applied += sz_applied; +} + +static void damos_apply_scheme(struct damon_ctx *c, struct damon_target *t, + struct damon_region *r, struct damos *s) +{ + struct damos_quota *quota = &s->quota; + unsigned long sz = damon_sz_region(r); + struct timespec64 begin, end; + unsigned long sz_applied = 0; + int err = 0; + + if (c->ops.apply_scheme) { + if (quota->esz && quota->charged_sz + sz > quota->esz) { + sz = ALIGN_DOWN(quota->esz - quota->charged_sz, + DAMON_MIN_REGION); + if (!sz) + goto update_stat; + damon_split_region_at(t, r, sz); + } + ktime_get_coarse_ts64(&begin); + if (c->callback.before_damos_apply) + err = c->callback.before_damos_apply(c, t, r, s); + if (!err) + sz_applied = c->ops.apply_scheme(c, t, r, s); + ktime_get_coarse_ts64(&end); + quota->total_charged_ns += timespec64_to_ns(&end) - + timespec64_to_ns(&begin); + quota->charged_sz += sz; + if (quota->esz && quota->charged_sz >= quota->esz) { + quota->charge_target_from = t; + quota->charge_addr_from = r->ar.end + 1; + } + } + if (s->action != DAMOS_STAT) + r->age = 0; + +update_stat: + damos_update_stat(s, sz, sz_applied); } static void damon_do_apply_schemes(struct damon_ctx *c, @@ -562,9 +811,6 @@ static void damon_do_apply_schemes(struct damon_ctx *c, damon_for_each_scheme(s, c) { struct damos_quota *quota = &s->quota; - unsigned long sz = r->ar.end - r->ar.start; - struct timespec64 begin, end; - unsigned long sz_applied = 0; if (!s->wmarks.activated) continue; @@ -573,70 +819,13 @@ static void damon_do_apply_schemes(struct damon_ctx *c, if (quota->esz && quota->charged_sz >= quota->esz) continue; - /* Skip previously charged regions */ - if (quota->charge_target_from) { - if (t != quota->charge_target_from) - continue; - if (r == damon_last_region(t)) { - quota->charge_target_from = NULL; - quota->charge_addr_from = 0; - continue; - } - if (quota->charge_addr_from && - r->ar.end <= quota->charge_addr_from) - continue; - - if (quota->charge_addr_from && r->ar.start < - quota->charge_addr_from) { - sz = ALIGN_DOWN(quota->charge_addr_from - - r->ar.start, DAMON_MIN_REGION); - if (!sz) { - if (r->ar.end - r->ar.start <= - DAMON_MIN_REGION) - continue; - sz = DAMON_MIN_REGION; - } - damon_split_region_at(c, t, r, sz); - r = damon_next_region(r); - sz = r->ar.end - r->ar.start; - } - quota->charge_target_from = NULL; - quota->charge_addr_from = 0; - } + if (damos_skip_charged_region(t, &r, s)) + continue; if (!damos_valid_target(c, t, r, s)) continue; - /* Apply the scheme */ - if (c->primitive.apply_scheme) { - if (quota->esz && - quota->charged_sz + sz > quota->esz) { - sz = ALIGN_DOWN(quota->esz - quota->charged_sz, - DAMON_MIN_REGION); - if (!sz) - goto update_stat; - damon_split_region_at(c, t, r, sz); - } - ktime_get_coarse_ts64(&begin); - sz_applied = c->primitive.apply_scheme(c, t, r, s); - ktime_get_coarse_ts64(&end); - quota->total_charged_ns += timespec64_to_ns(&end) - - timespec64_to_ns(&begin); - quota->charged_sz += sz; - if (quota->esz && quota->charged_sz >= quota->esz) { - quota->charge_target_from = t; - quota->charge_addr_from = r->ar.end + 1; - } - } - if (s->action != DAMOS_STAT) - r->age = 0; - -update_stat: - s->stat.nr_tried++; - s->stat.sz_tried += sz; - if (sz_applied) - s->stat.nr_applied++; - s->stat.sz_applied += sz_applied; + damos_apply_scheme(c, t, r, s); } } @@ -663,60 +852,64 @@ static void damos_set_effective_quota(struct damos_quota *quota) quota->esz = esz; } -static void kdamond_apply_schemes(struct damon_ctx *c) +static void damos_adjust_quota(struct damon_ctx *c, struct damos *s) { + struct damos_quota *quota = &s->quota; struct damon_target *t; - struct damon_region *r, *next_r; - struct damos *s; + struct damon_region *r; + unsigned long cumulated_sz; + unsigned int score, max_score = 0; - damon_for_each_scheme(s, c) { - struct damos_quota *quota = &s->quota; - unsigned long cumulated_sz; - unsigned int score, max_score = 0; + if (!quota->ms && !quota->sz) + return; - if (!s->wmarks.activated) - continue; + /* New charge window starts */ + if (time_after_eq(jiffies, quota->charged_from + + msecs_to_jiffies(quota->reset_interval))) { + if (quota->esz && quota->charged_sz >= quota->esz) + s->stat.qt_exceeds++; + quota->total_charged_sz += quota->charged_sz; + quota->charged_from = jiffies; + quota->charged_sz = 0; + damos_set_effective_quota(quota); + } - if (!quota->ms && !quota->sz) - continue; + if (!c->ops.get_scheme_score) + return; - /* New charge window starts */ - if (time_after_eq(jiffies, quota->charged_from + - msecs_to_jiffies( - quota->reset_interval))) { - if (quota->esz && quota->charged_sz >= quota->esz) - s->stat.qt_exceeds++; - quota->total_charged_sz += quota->charged_sz; - quota->charged_from = jiffies; - quota->charged_sz = 0; - damos_set_effective_quota(quota); + /* Fill up the score histogram */ + memset(quota->histogram, 0, sizeof(quota->histogram)); + damon_for_each_target(t, c) { + damon_for_each_region(r, t) { + if (!__damos_valid_target(r, s)) + continue; + score = c->ops.get_scheme_score(c, t, r, s); + quota->histogram[score] += damon_sz_region(r); + if (score > max_score) + max_score = score; } + } - if (!c->primitive.get_scheme_score) - continue; + /* Set the min score limit */ + for (cumulated_sz = 0, score = max_score; ; score--) { + cumulated_sz += quota->histogram[score]; + if (cumulated_sz >= quota->esz || !score) + break; + } + quota->min_score = score; +} - /* Fill up the score histogram */ - memset(quota->histogram, 0, sizeof(quota->histogram)); - damon_for_each_target(t, c) { - damon_for_each_region(r, t) { - if (!__damos_valid_target(r, s)) - continue; - score = c->primitive.get_scheme_score( - c, t, r, s); - quota->histogram[score] += - r->ar.end - r->ar.start; - if (score > max_score) - max_score = score; - } - } +static void kdamond_apply_schemes(struct damon_ctx *c) +{ + struct damon_target *t; + struct damon_region *r, *next_r; + struct damos *s; - /* Set the min score limit */ - for (cumulated_sz = 0, score = max_score; ; score--) { - cumulated_sz += quota->histogram[score]; - if (cumulated_sz >= quota->esz || !score) - break; - } - quota->min_score = score; + damon_for_each_scheme(s, c) { + if (!s->wmarks.activated) + continue; + + damos_adjust_quota(c, s); } damon_for_each_target(t, c) { @@ -725,18 +918,13 @@ static void kdamond_apply_schemes(struct damon_ctx *c) } } -static inline unsigned long sz_damon_region(struct damon_region *r) -{ - return r->ar.end - r->ar.start; -} - /* * Merge two adjacent regions into one region */ static void damon_merge_two_regions(struct damon_target *t, struct damon_region *l, struct damon_region *r) { - unsigned long sz_l = sz_damon_region(l), sz_r = sz_damon_region(r); + unsigned long sz_l = damon_sz_region(l), sz_r = damon_sz_region(r); l->nr_accesses = (l->nr_accesses * sz_l + r->nr_accesses * sz_r) / (sz_l + sz_r); @@ -765,7 +953,7 @@ static void damon_merge_regions_of(struct damon_target *t, unsigned int thres, if (prev && prev->ar.end == r->ar.start && abs(prev->nr_accesses - r->nr_accesses) <= thres && - sz_damon_region(prev) + sz_damon_region(r) <= sz_limit) + damon_sz_region(prev) + damon_sz_region(r) <= sz_limit) damon_merge_two_regions(t, prev, r); else prev = r; @@ -798,9 +986,8 @@ static void kdamond_merge_regions(struct damon_ctx *c, unsigned int threshold, * r the region to be split * sz_r size of the first sub-region that will be made */ -static void damon_split_region_at(struct damon_ctx *ctx, - struct damon_target *t, struct damon_region *r, - unsigned long sz_r) +static void damon_split_region_at(struct damon_target *t, + struct damon_region *r, unsigned long sz_r) { struct damon_region *new; @@ -817,15 +1004,14 @@ static void damon_split_region_at(struct damon_ctx *ctx, } /* Split every region in the given target into 'nr_subs' regions */ -static void damon_split_regions_of(struct damon_ctx *ctx, - struct damon_target *t, int nr_subs) +static void damon_split_regions_of(struct damon_target *t, int nr_subs) { struct damon_region *r, *next; unsigned long sz_region, sz_sub = 0; int i; damon_for_each_region_safe(r, next, t) { - sz_region = r->ar.end - r->ar.start; + sz_region = damon_sz_region(r); for (i = 0; i < nr_subs - 1 && sz_region > 2 * DAMON_MIN_REGION; i++) { @@ -839,7 +1025,7 @@ static void damon_split_regions_of(struct damon_ctx *ctx, if (sz_sub == 0 || sz_sub >= sz_region) continue; - damon_split_region_at(ctx, t, r, sz_sub); + damon_split_region_at(t, r, sz_sub); sz_region = sz_sub; } } @@ -865,29 +1051,30 @@ static void kdamond_split_regions(struct damon_ctx *ctx) damon_for_each_target(t, ctx) nr_regions += damon_nr_regions(t); - if (nr_regions > ctx->max_nr_regions / 2) + if (nr_regions > ctx->attrs.max_nr_regions / 2) return; /* Maybe the middle of the region has different access frequency */ if (last_nr_regions == nr_regions && - nr_regions < ctx->max_nr_regions / 3) + nr_regions < ctx->attrs.max_nr_regions / 3) nr_subregions = 3; damon_for_each_target(t, ctx) - damon_split_regions_of(ctx, t, nr_subregions); + damon_split_regions_of(t, nr_subregions); last_nr_regions = nr_regions; } /* - * Check whether it is time to check and apply the target monitoring regions + * Check whether it is time to check and apply the operations-related data + * structures. * * Returns true if it is. */ -static bool kdamond_need_update_primitive(struct damon_ctx *ctx) +static bool kdamond_need_update_operations(struct damon_ctx *ctx) { - return damon_check_reset_time_interval(&ctx->last_primitive_update, - ctx->primitive_update_interval); + return damon_check_reset_time_interval(&ctx->last_ops_update, + ctx->attrs.ops_update_interval); } /* @@ -905,11 +1092,11 @@ static bool kdamond_need_stop(struct damon_ctx *ctx) if (kthread_should_stop()) return true; - if (!ctx->primitive.target_valid) + if (!ctx->ops.target_valid) return false; damon_for_each_target(t, ctx) { - if (ctx->primitive.target_valid(t)) + if (ctx->ops.target_valid(t)) return false; } @@ -979,17 +1166,24 @@ static int kdamond_wait_activation(struct damon_ctx *ctx) struct damos *s; unsigned long wait_time; unsigned long min_wait_time = 0; + bool init_wait_time = false; while (!kdamond_need_stop(ctx)) { damon_for_each_scheme(s, ctx) { wait_time = damos_wmark_wait_us(s); - if (!min_wait_time || wait_time < min_wait_time) + if (!init_wait_time || wait_time < min_wait_time) { + init_wait_time = true; min_wait_time = wait_time; + } } if (!min_wait_time) return 0; kdamond_usleep(min_wait_time); + + if (ctx->callback.after_wmarks_check && + ctx->callback.after_wmarks_check(ctx)) + break; } return -EBUSY; } @@ -999,36 +1193,35 @@ static int kdamond_wait_activation(struct damon_ctx *ctx) */ static int kdamond_fn(void *data) { - struct damon_ctx *ctx = (struct damon_ctx *)data; + struct damon_ctx *ctx = data; struct damon_target *t; struct damon_region *r, *next; unsigned int max_nr_accesses = 0; unsigned long sz_limit = 0; - bool done = false; pr_debug("kdamond (%d) starts\n", current->pid); - if (ctx->primitive.init) - ctx->primitive.init(ctx); + if (ctx->ops.init) + ctx->ops.init(ctx); if (ctx->callback.before_start && ctx->callback.before_start(ctx)) - done = true; + goto done; sz_limit = damon_region_sz_limit(ctx); - while (!kdamond_need_stop(ctx) && !done) { + while (!kdamond_need_stop(ctx)) { if (kdamond_wait_activation(ctx)) - continue; + break; - if (ctx->primitive.prepare_access_checks) - ctx->primitive.prepare_access_checks(ctx); + if (ctx->ops.prepare_access_checks) + ctx->ops.prepare_access_checks(ctx); if (ctx->callback.after_sampling && ctx->callback.after_sampling(ctx)) - done = true; + break; - kdamond_usleep(ctx->sample_interval); + kdamond_usleep(ctx->attrs.sample_interval); - if (ctx->primitive.check_accesses) - max_nr_accesses = ctx->primitive.check_accesses(ctx); + if (ctx->ops.check_accesses) + max_nr_accesses = ctx->ops.check_accesses(ctx); if (kdamond_aggregate_interval_passed(ctx)) { kdamond_merge_regions(ctx, @@ -1036,20 +1229,21 @@ static int kdamond_fn(void *data) sz_limit); if (ctx->callback.after_aggregation && ctx->callback.after_aggregation(ctx)) - done = true; + break; kdamond_apply_schemes(ctx); kdamond_reset_aggregated(ctx); kdamond_split_regions(ctx); - if (ctx->primitive.reset_aggregated) - ctx->primitive.reset_aggregated(ctx); + if (ctx->ops.reset_aggregated) + ctx->ops.reset_aggregated(ctx); } - if (kdamond_need_update_primitive(ctx)) { - if (ctx->primitive.update) - ctx->primitive.update(ctx); + if (kdamond_need_update_operations(ctx)) { + if (ctx->ops.update) + ctx->ops.update(ctx); sz_limit = damon_region_sz_limit(ctx); } } +done: damon_for_each_target(t, ctx) { damon_for_each_region_safe(r, next, t) damon_destroy_region(r, t); @@ -1057,8 +1251,8 @@ static int kdamond_fn(void *data) if (ctx->callback.before_terminate) ctx->callback.before_terminate(ctx); - if (ctx->primitive.cleanup) - ctx->primitive.cleanup(ctx); + if (ctx->ops.cleanup) + ctx->ops.cleanup(ctx); pr_debug("kdamond (%d) finishes\n", current->pid); mutex_lock(&ctx->kdamond_lock); @@ -1067,9 +1261,97 @@ static int kdamond_fn(void *data) mutex_lock(&damon_lock); nr_running_ctxs--; + if (!nr_running_ctxs && running_exclusive_ctxs) + running_exclusive_ctxs = false; mutex_unlock(&damon_lock); return 0; } +/* + * struct damon_system_ram_region - System RAM resource address region of + * [@start, @end). + * @start: Start address of the region (inclusive). + * @end: End address of the region (exclusive). + */ +struct damon_system_ram_region { + unsigned long start; + unsigned long end; +}; + +static int walk_system_ram(struct resource *res, void *arg) +{ + struct damon_system_ram_region *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 damon_find_biggest_system_ram(unsigned long *start, + unsigned long *end) + +{ + struct damon_system_ram_region 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; +} + +/** + * damon_set_region_biggest_system_ram_default() - Set the region of the given + * monitoring target as requested, or biggest 'System RAM'. + * @t: The monitoring target to set the region. + * @start: The pointer to the start address of the region. + * @end: The pointer to the end address of the region. + * + * This function sets the region of @t as requested by @start and @end. If the + * values of @start and @end are zero, however, this function finds the biggest + * 'System RAM' resource and sets the region to cover the resource. In the + * latter case, this function saves the start and end addresses of the resource + * in @start and @end, respectively. + * + * Return: 0 on success, negative error code otherwise. + */ +int damon_set_region_biggest_system_ram_default(struct damon_target *t, + unsigned long *start, unsigned long *end) +{ + struct damon_addr_range addr_range; + + if (*start > *end) + return -EINVAL; + + if (!*start && !*end && + !damon_find_biggest_system_ram(start, end)) + return -EINVAL; + + addr_range.start = *start; + addr_range.end = *end; + return damon_set_regions(t, &addr_range, 1); +} + +static int __init damon_init(void) +{ + damon_region_cache = KMEM_CACHE(damon_region, 0); + if (unlikely(!damon_region_cache)) { + pr_err("creating damon_region_cache fails\n"); + return -ENOMEM; + } + + return 0; +} + +subsys_initcall(damon_init); + #include "core-test.h" diff --git a/mm/damon/dbgfs-test.h b/mm/damon/dbgfs-test.h index 86b9f9528231efb52bfe1b791aaaffeb01315492..0bb0d532b15905a0cb2f0ae04784355f6f476688 100644 --- a/mm/damon/dbgfs-test.h +++ b/mm/damon/dbgfs-test.h @@ -12,66 +12,58 @@ #include -static void damon_dbgfs_test_str_to_target_ids(struct kunit *test) +static void damon_dbgfs_test_str_to_ints(struct kunit *test) { char *question; - unsigned long *answers; - unsigned long expected[] = {12, 35, 46}; + int *answers; + int expected[] = {12, 35, 46}; ssize_t nr_integers = 0, i; question = "123"; - answers = str_to_target_ids(question, strlen(question), - &nr_integers); + answers = str_to_ints(question, strlen(question), &nr_integers); KUNIT_EXPECT_EQ(test, (ssize_t)1, nr_integers); - KUNIT_EXPECT_EQ(test, 123ul, answers[0]); + KUNIT_EXPECT_EQ(test, 123, answers[0]); kfree(answers); question = "123abc"; - answers = str_to_target_ids(question, strlen(question), - &nr_integers); + answers = str_to_ints(question, strlen(question), &nr_integers); KUNIT_EXPECT_EQ(test, (ssize_t)1, nr_integers); - KUNIT_EXPECT_EQ(test, 123ul, answers[0]); + KUNIT_EXPECT_EQ(test, 123, answers[0]); kfree(answers); question = "a123"; - answers = str_to_target_ids(question, strlen(question), - &nr_integers); + answers = str_to_ints(question, strlen(question), &nr_integers); KUNIT_EXPECT_EQ(test, (ssize_t)0, nr_integers); kfree(answers); question = "12 35"; - answers = str_to_target_ids(question, strlen(question), - &nr_integers); + answers = str_to_ints(question, strlen(question), &nr_integers); KUNIT_EXPECT_EQ(test, (ssize_t)2, nr_integers); for (i = 0; i < nr_integers; i++) KUNIT_EXPECT_EQ(test, expected[i], answers[i]); kfree(answers); question = "12 35 46"; - answers = str_to_target_ids(question, strlen(question), - &nr_integers); + answers = str_to_ints(question, strlen(question), &nr_integers); KUNIT_EXPECT_EQ(test, (ssize_t)3, nr_integers); for (i = 0; i < nr_integers; i++) KUNIT_EXPECT_EQ(test, expected[i], answers[i]); kfree(answers); question = "12 35 abc 46"; - answers = str_to_target_ids(question, strlen(question), - &nr_integers); + answers = str_to_ints(question, strlen(question), &nr_integers); KUNIT_EXPECT_EQ(test, (ssize_t)2, nr_integers); for (i = 0; i < 2; i++) KUNIT_EXPECT_EQ(test, expected[i], answers[i]); kfree(answers); question = ""; - answers = str_to_target_ids(question, strlen(question), - &nr_integers); + answers = str_to_ints(question, strlen(question), &nr_integers); KUNIT_EXPECT_EQ(test, (ssize_t)0, nr_integers); kfree(answers); question = "\n"; - answers = str_to_target_ids(question, strlen(question), - &nr_integers); + answers = str_to_ints(question, strlen(question), &nr_integers); KUNIT_EXPECT_EQ(test, (ssize_t)0, nr_integers); kfree(answers); } @@ -79,30 +71,20 @@ static void damon_dbgfs_test_str_to_target_ids(struct kunit *test) static void damon_dbgfs_test_set_targets(struct kunit *test) { struct damon_ctx *ctx = dbgfs_new_ctx(); - unsigned long ids[] = {1, 2, 3}; char buf[64]; - /* Make DAMON consider target id as plain number */ - ctx->primitive.target_valid = NULL; - ctx->primitive.cleanup = NULL; + /* Make DAMON consider target has no pid */ + damon_select_ops(ctx, DAMON_OPS_PADDR); - damon_set_targets(ctx, ids, 3); - sprint_target_ids(ctx, buf, 64); - KUNIT_EXPECT_STREQ(test, (char *)buf, "1 2 3\n"); - - damon_set_targets(ctx, NULL, 0); + dbgfs_set_targets(ctx, 0, NULL); sprint_target_ids(ctx, buf, 64); KUNIT_EXPECT_STREQ(test, (char *)buf, "\n"); - damon_set_targets(ctx, (unsigned long []){1, 2}, 2); + dbgfs_set_targets(ctx, 1, NULL); sprint_target_ids(ctx, buf, 64); - KUNIT_EXPECT_STREQ(test, (char *)buf, "1 2\n"); + KUNIT_EXPECT_STREQ(test, (char *)buf, "42\n"); - damon_set_targets(ctx, (unsigned long []){2}, 1); - sprint_target_ids(ctx, buf, 64); - KUNIT_EXPECT_STREQ(test, (char *)buf, "2\n"); - - damon_set_targets(ctx, NULL, 0); + dbgfs_set_targets(ctx, 0, NULL); sprint_target_ids(ctx, buf, 64); KUNIT_EXPECT_STREQ(test, (char *)buf, "\n"); @@ -112,25 +94,26 @@ static void damon_dbgfs_test_set_targets(struct kunit *test) static void damon_dbgfs_test_set_init_regions(struct kunit *test) { struct damon_ctx *ctx = damon_new_ctx(); - unsigned long ids[] = {1, 2, 3}; - /* Each line represents one region in `` `` */ - char * const valid_inputs[] = {"2 10 20\n 2 20 30\n2 35 45", - "2 10 20\n", - "2 10 20\n1 39 59\n1 70 134\n 2 20 25\n", + /* Each line represents one region in `` `` */ + char * const valid_inputs[] = {"1 10 20\n 1 20 30\n1 35 45", + "1 10 20\n", + "1 10 20\n0 39 59\n0 70 134\n 1 20 25\n", ""}; /* Reading the file again will show sorted, clean output */ - char * const valid_expects[] = {"2 10 20\n2 20 30\n2 35 45\n", - "2 10 20\n", - "1 39 59\n1 70 134\n2 10 20\n2 20 25\n", + char * const valid_expects[] = {"1 10 20\n1 20 30\n1 35 45\n", + "1 10 20\n", + "0 39 59\n0 70 134\n1 10 20\n1 20 25\n", ""}; - char * const invalid_inputs[] = {"4 10 20\n", /* target not exists */ - "2 10 20\n 2 14 26\n", /* regions overlap */ - "1 10 20\n2 30 40\n 1 5 8"}; /* not sorted by address */ + char * const invalid_inputs[] = {"3 10 20\n", /* target not exists */ + "1 10 20\n 1 14 26\n", /* regions overlap */ + "0 10 20\n1 30 40\n 0 5 8"}; /* not sorted by address */ char *input, *expect; int i, rc; char buf[256]; - damon_set_targets(ctx, ids, 3); + damon_select_ops(ctx, DAMON_OPS_PADDR); + + dbgfs_set_targets(ctx, 3, NULL); /* Put valid inputs and check the results */ for (i = 0; i < ARRAY_SIZE(valid_inputs); i++) { @@ -158,12 +141,12 @@ static void damon_dbgfs_test_set_init_regions(struct kunit *test) KUNIT_EXPECT_STREQ(test, (char *)buf, ""); } - damon_set_targets(ctx, NULL, 0); + dbgfs_set_targets(ctx, 0, NULL); damon_destroy_ctx(ctx); } static struct kunit_case damon_test_cases[] = { - KUNIT_CASE(damon_dbgfs_test_str_to_target_ids), + KUNIT_CASE(damon_dbgfs_test_str_to_ints), KUNIT_CASE(damon_dbgfs_test_set_targets), KUNIT_CASE(damon_dbgfs_test_set_init_regions), {}, diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index 5b899601e56c3fd13b434d118ea0e50cb7ab73ff..124f0f8c97b755f48a7e88717c5e557925f9c80b 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -20,6 +20,14 @@ static int dbgfs_nr_ctxs; static struct dentry **dbgfs_dirs; static DEFINE_MUTEX(damon_dbgfs_lock); +static void damon_dbgfs_warn_deprecation(void) +{ + pr_warn_once("DAMON debugfs interface is deprecated, " + "so users should move to DAMON_SYSFS. If you cannot, " + "please report your usecase to damon@lists.linux.dev and " + "linux-mm@kvack.org.\n"); +} + /* * Returns non-empty string on success, negative error code otherwise. */ @@ -55,9 +63,9 @@ static ssize_t dbgfs_attrs_read(struct file *file, mutex_lock(&ctx->kdamond_lock); ret = scnprintf(kbuf, ARRAY_SIZE(kbuf), "%lu %lu %lu %lu %lu\n", - ctx->sample_interval, ctx->aggr_interval, - ctx->primitive_update_interval, ctx->min_nr_regions, - ctx->max_nr_regions); + ctx->attrs.sample_interval, ctx->attrs.aggr_interval, + ctx->attrs.ops_update_interval, + ctx->attrs.min_nr_regions, ctx->attrs.max_nr_regions); mutex_unlock(&ctx->kdamond_lock); return simple_read_from_buffer(buf, count, ppos, kbuf, ret); @@ -67,7 +75,7 @@ static ssize_t dbgfs_attrs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct damon_ctx *ctx = file->private_data; - unsigned long s, a, r, minr, maxr; + struct damon_attrs attrs; char *kbuf; ssize_t ret; @@ -76,7 +84,10 @@ static ssize_t dbgfs_attrs_write(struct file *file, return PTR_ERR(kbuf); if (sscanf(kbuf, "%lu %lu %lu %lu %lu", - &s, &a, &r, &minr, &maxr) != 5) { + &attrs.sample_interval, &attrs.aggr_interval, + &attrs.ops_update_interval, + &attrs.min_nr_regions, + &attrs.max_nr_regions) != 5) { ret = -EINVAL; goto out; } @@ -87,7 +98,7 @@ static ssize_t dbgfs_attrs_write(struct file *file, goto unlock_out; } - ret = damon_set_attrs(ctx, s, a, r, minr, maxr); + ret = damon_set_attrs(ctx, &attrs); if (!ret) ret = count; unlock_out: @@ -97,6 +108,31 @@ static ssize_t dbgfs_attrs_write(struct file *file, 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; @@ -106,10 +142,13 @@ static ssize_t sprint_schemes(struct damon_ctx *c, char *buf, ssize_t len) damon_for_each_scheme(s, c) { rc = scnprintf(&buf[written], len - written, "%lu %lu %u %u %u %u %d %lu %lu %lu %u %u %u %d %lu %lu %lu %lu %lu %lu %lu %lu %lu\n", - 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, + s->pattern.min_sz_region, + s->pattern.max_sz_region, + s->pattern.min_nr_accesses, + s->pattern.max_nr_accesses, + s->pattern.min_age_region, + s->pattern.max_age_region, + damos_action_to_dbgfs_scheme_action(s->action), s->quota.ms, s->quota.sz, s->quota.reset_interval, s->quota.weight_sz, @@ -160,18 +199,27 @@ 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; } } @@ -187,9 +235,8 @@ static struct damos **str_to_schemes(const char *str, ssize_t len, struct damos *scheme, **schemes; const int max_nr_schemes = 256; 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); @@ -198,13 +245,18 @@ static struct damos **str_to_schemes(const char *str, ssize_t len, *nr_schemes = 0; while (pos < len && *nr_schemes < max_nr_schemes) { + struct damos_access_pattern pattern = {}; struct damos_quota quota = {}; struct damos_watermarks wmarks; 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, + &pattern.min_sz_region, &pattern.max_sz_region, + &pattern.min_nr_accesses, + &pattern.max_nr_accesses, + &pattern.min_age_region, + &pattern.max_age_region, + &action_input, "a.ms, "a.sz, "a.reset_interval, "a.weight_sz, "a.weight_nr_accesses, "a.weight_age, &wmarks.metric, @@ -212,10 +264,13 @@ 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) + if (pattern.min_sz_region > pattern.max_sz_region || + pattern.min_nr_accesses > pattern.max_nr_accesses || + pattern.min_age_region > pattern.max_age_region) goto fail; if (wmarks.high < wmarks.mid || wmarks.high < wmarks.low || @@ -223,8 +278,7 @@ static struct damos **str_to_schemes(const char *str, ssize_t len, goto fail; pos += parsed; - scheme = damon_new_scheme(min_sz, max_sz, min_nr_a, max_nr_a, - min_age, max_age, action, "a, &wmarks); + scheme = damon_new_scheme(&pattern, action, "a, &wmarks); if (!scheme) goto fail; @@ -261,11 +315,9 @@ static ssize_t dbgfs_schemes_write(struct file *file, const char __user *buf, goto unlock_out; } - ret = damon_set_schemes(ctx, schemes, nr_schemes); - if (!ret) { - ret = count; - nr_schemes = 0; - } + damon_set_schemes(ctx, schemes, nr_schemes); + ret = count; + nr_schemes = 0; unlock_out: mutex_unlock(&ctx->kdamond_lock); @@ -275,25 +327,22 @@ static ssize_t dbgfs_schemes_write(struct file *file, const char __user *buf, return ret; } -static inline bool targetid_is_pid(const struct damon_ctx *ctx) -{ - return ctx->primitive.target_valid == damon_va_target_valid; -} - static ssize_t sprint_target_ids(struct damon_ctx *ctx, char *buf, ssize_t len) { struct damon_target *t; - unsigned long id; + int id; int written = 0; int rc; damon_for_each_target(t, ctx) { - id = t->id; - if (targetid_is_pid(ctx)) + if (damon_target_has_pid(ctx)) /* Show pid numbers to debugfs users */ - id = (unsigned long)pid_vnr((struct pid *)id); + id = pid_vnr(t->pid); + else + /* Show 42 for physical address space, just for fun */ + id = 42; - rc = scnprintf(&buf[written], len - written, "%lu ", id); + rc = scnprintf(&buf[written], len - written, "%d ", id); if (!rc) return -ENOMEM; written += rc; @@ -321,54 +370,129 @@ static ssize_t dbgfs_target_ids_read(struct file *file, } /* - * Converts a string into an array of unsigned long integers + * Converts a string into an integers array * - * Returns an array of unsigned long integers if the conversion success, or - * NULL otherwise. + * Returns an array of integers array if the conversion success, or NULL + * otherwise. */ -static unsigned long *str_to_target_ids(const char *str, ssize_t len, - ssize_t *nr_ids) +static int *str_to_ints(const char *str, ssize_t len, ssize_t *nr_ints) { - unsigned long *ids; - const int max_nr_ids = 32; - unsigned long id; + int *array; + const int max_nr_ints = 32; + int nr; int pos = 0, parsed, ret; - *nr_ids = 0; - ids = kmalloc_array(max_nr_ids, sizeof(id), GFP_KERNEL); - if (!ids) + *nr_ints = 0; + array = kmalloc_array(max_nr_ints, sizeof(*array), GFP_KERNEL); + if (!array) return NULL; - while (*nr_ids < max_nr_ids && pos < len) { - ret = sscanf(&str[pos], "%lu%n", &id, &parsed); + while (*nr_ints < max_nr_ints && pos < len) { + ret = sscanf(&str[pos], "%d%n", &nr, &parsed); pos += parsed; if (ret != 1) break; - ids[*nr_ids] = id; - *nr_ids += 1; + array[*nr_ints] = nr; + *nr_ints += 1; } - return ids; + return array; } -static void dbgfs_put_pids(unsigned long *ids, int nr_ids) +static void dbgfs_put_pids(struct pid **pids, int nr_pids) { int i; - for (i = 0; i < nr_ids; i++) - put_pid((struct pid *)ids[i]); + for (i = 0; i < nr_pids; i++) + put_pid(pids[i]); +} + +/* + * Converts a string into an struct pid pointers array + * + * Returns an array of struct pid pointers if the conversion success, or NULL + * otherwise. + */ +static struct pid **str_to_pids(const char *str, ssize_t len, ssize_t *nr_pids) +{ + int *ints; + ssize_t nr_ints; + struct pid **pids; + + *nr_pids = 0; + + ints = str_to_ints(str, len, &nr_ints); + if (!ints) + return NULL; + + pids = kmalloc_array(nr_ints, sizeof(*pids), GFP_KERNEL); + if (!pids) + goto out; + + for (; *nr_pids < nr_ints; (*nr_pids)++) { + pids[*nr_pids] = find_get_pid(ints[*nr_pids]); + if (!pids[*nr_pids]) { + dbgfs_put_pids(pids, *nr_pids); + kfree(ints); + kfree(pids); + return NULL; + } + } + +out: + kfree(ints); + return pids; +} + +/* + * dbgfs_set_targets() - Set monitoring targets. + * @ctx: monitoring context + * @nr_targets: number of targets + * @pids: array of target pids (size is same to @nr_targets) + * + * This function should not be called while the kdamond is running. @pids is + * ignored if the context is not configured to have pid in each target. On + * failure, reference counts of all pids in @pids are decremented. + * + * Return: 0 on success, negative error code otherwise. + */ +static int dbgfs_set_targets(struct damon_ctx *ctx, ssize_t nr_targets, + struct pid **pids) +{ + ssize_t i; + struct damon_target *t, *next; + + damon_for_each_target_safe(t, next, ctx) { + if (damon_target_has_pid(ctx)) + put_pid(t->pid); + damon_destroy_target(t); + } + + for (i = 0; i < nr_targets; i++) { + t = damon_new_target(); + if (!t) { + damon_for_each_target_safe(t, next, ctx) + damon_destroy_target(t); + if (damon_target_has_pid(ctx)) + dbgfs_put_pids(pids, nr_targets); + return -ENOMEM; + } + if (damon_target_has_pid(ctx)) + t->pid = pids[i]; + damon_add_target(ctx, t); + } + + return 0; } static ssize_t dbgfs_target_ids_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct damon_ctx *ctx = file->private_data; - struct damon_target *t, *next_t; bool id_is_pid = true; char *kbuf; - unsigned long *targets; + struct pid **target_pids = NULL; ssize_t nr_targets; ssize_t ret; - int i; kbuf = user_input_str(buf, count, ppos); if (IS_ERR(kbuf)) @@ -376,61 +500,47 @@ static ssize_t dbgfs_target_ids_write(struct file *file, if (!strncmp(kbuf, "paddr\n", count)) { id_is_pid = false; - /* target id is meaningless here, but we set it just for fun */ - scnprintf(kbuf, count, "42 "); - } - - targets = str_to_target_ids(kbuf, count, &nr_targets); - if (!targets) { - ret = -ENOMEM; - goto out; + nr_targets = 1; } if (id_is_pid) { - for (i = 0; i < nr_targets; i++) { - targets[i] = (unsigned long)find_get_pid( - (int)targets[i]); - if (!targets[i]) { - dbgfs_put_pids(targets, i); - ret = -EINVAL; - goto free_targets_out; - } + target_pids = str_to_pids(kbuf, count, &nr_targets); + if (!target_pids) { + ret = -ENOMEM; + goto out; } } mutex_lock(&ctx->kdamond_lock); if (ctx->kdamond) { if (id_is_pid) - dbgfs_put_pids(targets, nr_targets); + dbgfs_put_pids(target_pids, nr_targets); ret = -EBUSY; goto unlock_out; } /* remove previously set targets */ - damon_for_each_target_safe(t, next_t, ctx) { - if (targetid_is_pid(ctx)) - put_pid((struct pid *)t->id); - damon_destroy_target(t); + dbgfs_set_targets(ctx, 0, NULL); + if (!nr_targets) { + ret = count; + goto unlock_out; } /* Configure the context for the address space type */ if (id_is_pid) - damon_va_set_primitives(ctx); + ret = damon_select_ops(ctx, DAMON_OPS_VADDR); else - damon_pa_set_primitives(ctx); + ret = damon_select_ops(ctx, DAMON_OPS_PADDR); + if (ret) + goto unlock_out; - ret = damon_set_targets(ctx, targets, nr_targets); - if (ret) { - if (id_is_pid) - dbgfs_put_pids(targets, nr_targets); - } else { + ret = dbgfs_set_targets(ctx, nr_targets, target_pids); + if (!ret) ret = count; - } unlock_out: mutex_unlock(&ctx->kdamond_lock); -free_targets_out: - kfree(targets); + kfree(target_pids); out: kfree(kbuf); return ret; @@ -440,18 +550,20 @@ static ssize_t sprint_init_regions(struct damon_ctx *c, char *buf, ssize_t len) { struct damon_target *t; struct damon_region *r; + int target_idx = 0; int written = 0; int rc; damon_for_each_target(t, c) { damon_for_each_region(r, t) { rc = scnprintf(&buf[written], len - written, - "%lu %lu %lu\n", - t->id, r->ar.start, r->ar.end); + "%d %lu %lu\n", + target_idx, r->ar.start, r->ar.end); if (!rc) return -ENOMEM; written += rc; } + target_idx++; } return written; } @@ -485,22 +597,19 @@ static ssize_t dbgfs_init_regions_read(struct file *file, char __user *buf, return len; } -static int add_init_region(struct damon_ctx *c, - unsigned long target_id, struct damon_addr_range *ar) +static int add_init_region(struct damon_ctx *c, int target_idx, + struct damon_addr_range *ar) { struct damon_target *t; struct damon_region *r, *prev; - unsigned long id; + unsigned long idx = 0; int rc = -EINVAL; if (ar->start >= ar->end) return -EINVAL; damon_for_each_target(t, c) { - id = t->id; - if (targetid_is_pid(c)) - id = (unsigned long)pid_vnr((struct pid *)id); - if (id == target_id) { + if (idx++ == target_idx) { r = damon_new_region(ar->start, ar->end); if (!r) return -ENOMEM; @@ -523,7 +632,7 @@ static int set_init_regions(struct damon_ctx *c, const char *str, ssize_t len) struct damon_target *t; struct damon_region *r, *next; int pos = 0, parsed, ret; - unsigned long target_id; + int target_idx; struct damon_addr_range ar; int err; @@ -533,11 +642,11 @@ static int set_init_regions(struct damon_ctx *c, const char *str, ssize_t len) } while (pos < len) { - ret = sscanf(&str[pos], "%lu %lu %lu%n", - &target_id, &ar.start, &ar.end, &parsed); + ret = sscanf(&str[pos], "%d %lu %lu%n", + &target_idx, &ar.start, &ar.end, &parsed); if (ret != 3) break; - err = add_init_region(c, target_id, &ar); + err = add_init_region(c, target_idx, &ar); if (err) goto fail; pos += parsed; @@ -610,6 +719,8 @@ static ssize_t dbgfs_kdamond_pid_read(struct file *file, static int damon_dbgfs_open(struct inode *inode, struct file *file) { + damon_dbgfs_warn_deprecation(); + file->private_data = inode->i_private; return nonseekable_open(inode, file); @@ -660,12 +771,12 @@ static void dbgfs_before_terminate(struct damon_ctx *ctx) { struct damon_target *t, *next; - if (!targetid_is_pid(ctx)) + if (!damon_target_has_pid(ctx)) return; mutex_lock(&ctx->kdamond_lock); damon_for_each_target_safe(t, next, ctx) { - put_pid((struct pid *)t->id); + put_pid(t->pid); damon_destroy_target(t); } mutex_unlock(&ctx->kdamond_lock); @@ -679,7 +790,11 @@ static struct damon_ctx *dbgfs_new_ctx(void) if (!ctx) return NULL; - damon_va_set_primitives(ctx); + if (damon_select_ops(ctx, DAMON_OPS_VADDR) && + damon_select_ops(ctx, DAMON_OPS_PADDR)) { + damon_destroy_ctx(ctx); + return NULL; + } ctx->callback.before_terminate = dbgfs_before_terminate; return ctx; } @@ -721,6 +836,9 @@ static int dbgfs_mk_context(char *name) return -ENOENT; new_dir = debugfs_create_dir(name, root); + /* Below check is required for a potential duplicated name case */ + if (IS_ERR(new_dir)) + return PTR_ERR(new_dir); dbgfs_dirs[dbgfs_nr_ctxs] = new_dir; new_ctx = dbgfs_new_ctx(); @@ -782,8 +900,10 @@ static ssize_t dbgfs_mk_context_write(struct file *file, static int dbgfs_rm_context(char *name) { struct dentry *root, *dir, **new_dirs; + struct inode *inode; struct damon_ctx **new_ctxs; int i, j; + int ret = 0; if (damon_nr_running_ctxs()) return -EBUSY; @@ -796,16 +916,24 @@ static int dbgfs_rm_context(char *name) if (!dir) return -ENOENT; + inode = d_inode(dir); + if (!S_ISDIR(inode->i_mode)) { + ret = -EINVAL; + goto out_dput; + } + new_dirs = kmalloc_array(dbgfs_nr_ctxs - 1, sizeof(*dbgfs_dirs), GFP_KERNEL); - if (!new_dirs) - return -ENOMEM; + if (!new_dirs) { + ret = -ENOMEM; + goto out_dput; + } new_ctxs = kmalloc_array(dbgfs_nr_ctxs - 1, sizeof(*dbgfs_ctxs), GFP_KERNEL); if (!new_ctxs) { - kfree(new_dirs); - return -ENOMEM; + ret = -ENOMEM; + goto out_new_dirs; } for (i = 0, j = 0; i < dbgfs_nr_ctxs; i++) { @@ -825,7 +953,13 @@ static int dbgfs_rm_context(char *name) dbgfs_ctxs = new_ctxs; dbgfs_nr_ctxs--; - return 0; + goto out_dput; + +out_new_dirs: + kfree(new_dirs); +out_dput: + dput(dir); + return ret; } static ssize_t dbgfs_rm_context_write(struct file *file, @@ -901,7 +1035,7 @@ static ssize_t dbgfs_monitor_on_write(struct file *file, return -EINVAL; } } - ret = damon_start(dbgfs_ctxs, dbgfs_nr_ctxs); + ret = damon_start(dbgfs_ctxs, dbgfs_nr_ctxs, true); } else if (!strncmp(kbuf, "off", count)) { ret = damon_stop(dbgfs_ctxs, dbgfs_nr_ctxs); } else { @@ -915,15 +1049,24 @@ static ssize_t dbgfs_monitor_on_write(struct file *file, return ret; } +static int damon_dbgfs_static_file_open(struct inode *inode, struct file *file) +{ + damon_dbgfs_warn_deprecation(); + return nonseekable_open(inode, file); +} + static const struct file_operations mk_contexts_fops = { + .open = damon_dbgfs_static_file_open, .write = dbgfs_mk_context_write, }; static const struct file_operations rm_contexts_fops = { + .open = damon_dbgfs_static_file_open, .write = dbgfs_rm_context_write, }; static const struct file_operations monitor_on_fops = { + .open = damon_dbgfs_static_file_open, .read = dbgfs_monitor_on_read, .write = dbgfs_monitor_on_write, }; @@ -944,7 +1087,7 @@ static int __init __damon_dbgfs_init(void) fops[i]); dbgfs_fill_ctx_dir(dbgfs_root, dbgfs_ctxs[0]); - dbgfs_dirs = kmalloc_array(1, sizeof(dbgfs_root), GFP_KERNEL); + dbgfs_dirs = kmalloc(sizeof(dbgfs_root), GFP_KERNEL); if (!dbgfs_dirs) { debugfs_remove(dbgfs_root); return -ENOMEM; diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c new file mode 100644 index 0000000000000000000000000000000000000000..e39fef0135c0e595300f8d6c640010b4bb497dd0 --- /dev/null +++ b/mm/damon/lru_sort.c @@ -0,0 +1,324 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DAMON-based LRU-lists Sorting + * + * Author: SeongJae Park + */ + +#define pr_fmt(fmt) "damon-lru-sort: " fmt + +#include +#include +#include +#include + +#include "modules-common.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); + +static struct damos_quota damon_lru_sort_quota = { + /* Use up to 10 ms per 1 sec, by default */ + .ms = 10, + .sz = 0, + .reset_interval = 1000, + /* Within the quota, mark hotter regions accessed first. */ + .weight_sz = 0, + .weight_nr_accesses = 1, + .weight_age = 0, +}; +DEFINE_DAMON_MODULES_DAMOS_TIME_QUOTA(damon_lru_sort_quota); + +static struct damos_watermarks damon_lru_sort_wmarks = { + .metric = DAMOS_WMARK_FREE_MEM_RATE, + .interval = 5000000, /* 5 seconds */ + .high = 200, /* 20 percent */ + .mid = 150, /* 15 percent */ + .low = 50, /* 5 percent */ +}; +DEFINE_DAMON_MODULES_WMARKS_PARAMS(damon_lru_sort_wmarks); + +static struct damon_attrs damon_lru_sort_mon_attrs = { + .sample_interval = 5000, /* 5 ms */ + .aggr_interval = 100000, /* 100 ms */ + .ops_update_interval = 0, + .min_nr_regions = 10, + .max_nr_regions = 1000, +}; +DEFINE_DAMON_MODULES_MON_ATTRS_PARAMS(damon_lru_sort_mon_attrs); + +/* + * 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); + +static struct damos_stat damon_lru_sort_hot_stat; +DEFINE_DAMON_MODULES_DAMOS_STATS_PARAMS(damon_lru_sort_hot_stat, + lru_sort_tried_hot_regions, lru_sorted_hot_regions, + hot_quota_exceeds); + +static struct damos_stat damon_lru_sort_cold_stat; +DEFINE_DAMON_MODULES_DAMOS_STATS_PARAMS(damon_lru_sort_cold_stat, + lru_sort_tried_cold_regions, lru_sorted_cold_regions, + cold_quota_exceeds); + +static struct damos_access_pattern damon_lru_sort_stub_pattern = { + /* Find regions having PAGE_SIZE or larger size */ + .min_sz_region = PAGE_SIZE, + .max_sz_region = ULONG_MAX, + /* no matter its access frequency */ + .min_nr_accesses = 0, + .max_nr_accesses = UINT_MAX, + /* no matter its age */ + .min_age_region = 0, + .max_age_region = UINT_MAX, +}; + +static struct damon_ctx *ctx; +static struct damon_target *target; + +static struct damos *damon_lru_sort_new_scheme( + struct damos_access_pattern *pattern, enum damos_action action) +{ + struct damos_quota quota = damon_lru_sort_quota; + + /* Use half of total quota for hot/cold pages sorting */ + quota.ms = quota.ms / 2; + + return damon_new_scheme( + /* find the pattern, and */ + pattern, + /* (de)prioritize on LRU-lists */ + action, + /* under the quota. */ + "a, + /* (De)activate this according to the watermarks. */ + &damon_lru_sort_wmarks); +} + +/* 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_access_pattern pattern = damon_lru_sort_stub_pattern; + + pattern.min_nr_accesses = hot_thres; + return damon_lru_sort_new_scheme(&pattern, DAMOS_LRU_PRIO); +} + +/* 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_access_pattern pattern = damon_lru_sort_stub_pattern; + + pattern.max_nr_accesses = 0; + pattern.min_age_region = cold_thres; + return damon_lru_sort_new_scheme(&pattern, DAMOS_LRU_DEPRIO); +} + +static int damon_lru_sort_apply_parameters(void) +{ + struct damos *scheme; + unsigned int hot_thres, cold_thres; + int err = 0; + + err = damon_set_attrs(ctx, &damon_lru_sort_mon_attrs); + if (err) + return err; + + /* aggr_interval / sample_interval is the maximum nr_accesses */ + hot_thres = damon_lru_sort_mon_attrs.aggr_interval / + damon_lru_sort_mon_attrs.sample_interval * + hot_thres_access_freq / 1000; + scheme = damon_lru_sort_new_hot_scheme(hot_thres); + if (!scheme) + return -ENOMEM; + damon_set_schemes(ctx, &scheme, 1); + + cold_thres = cold_min_age / damon_lru_sort_mon_attrs.aggr_interval; + scheme = damon_lru_sort_new_cold_scheme(cold_thres); + if (!scheme) + return -ENOMEM; + damon_add_scheme(ctx, scheme); + + return damon_set_region_biggest_system_ram_default(target, + &monitor_region_start, + &monitor_region_end); +} + +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 int damon_lru_sort_enabled_store(const char *val, + const struct kernel_param *kp) +{ + bool is_enabled = enabled; + bool enable; + int err; + + err = strtobool(val, &enable); + if (err) + return err; + + if (is_enabled == enable) + return 0; + + /* Called before init function. The function will handle this. */ + if (!ctx) + goto set_param_out; + + err = damon_lru_sort_turn(enable); + if (err) + return err; + +set_param_out: + enabled = enable; + return err; +} + +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) + damon_lru_sort_hot_stat = s->stat; + else if (s->action == DAMOS_LRU_DEPRIO) + damon_lru_sort_cold_stat = s->stat; + } + + 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) +{ + int err = damon_modules_new_paddr_ctx_target(&ctx, &target); + + if (err) + return err; + + ctx->callback.after_wmarks_check = damon_lru_sort_after_wmarks_check; + ctx->callback.after_aggregation = damon_lru_sort_after_aggregation; + + /* 'enabled' has set before this function, probably via command line */ + if (enabled) + err = damon_lru_sort_turn(true); + + return err; +} + +module_init(damon_lru_sort_init); diff --git a/mm/damon/modules-common.c b/mm/damon/modules-common.c new file mode 100644 index 0000000000000000000000000000000000000000..b2381a8466ecf5d0f5b4ac02e7ecd42f26697654 --- /dev/null +++ b/mm/damon/modules-common.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Common Primitives for DAMON Modules + * + * Author: SeongJae Park + */ + +#include + +#include "modules-common.h" + +/* + * Allocate, set, and return a DAMON context for the physical address space. + * @ctxp: Pointer to save the point to the newly created context + * @targetp: Pointer to save the point to the newly created target + */ +int damon_modules_new_paddr_ctx_target(struct damon_ctx **ctxp, + struct damon_target **targetp) +{ + struct damon_ctx *ctx; + struct damon_target *target; + + ctx = damon_new_ctx(); + if (!ctx) + return -ENOMEM; + + if (damon_select_ops(ctx, DAMON_OPS_PADDR)) { + damon_destroy_ctx(ctx); + return -EINVAL; + } + + target = damon_new_target(); + if (!target) { + damon_destroy_ctx(ctx); + return -ENOMEM; + } + damon_add_target(ctx, target); + + *ctxp = ctx; + *targetp = target; + return 0; +} diff --git a/mm/damon/modules-common.h b/mm/damon/modules-common.h new file mode 100644 index 0000000000000000000000000000000000000000..f49cdb4170051eb6cf8aa7a71846e2aee6c219f2 --- /dev/null +++ b/mm/damon/modules-common.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Common Primitives for DAMON Modules + * + * Author: SeongJae Park + */ + +#include + +#define DEFINE_DAMON_MODULES_MON_ATTRS_PARAMS(attrs) \ + module_param_named(sample_interval, attrs.sample_interval, \ + ulong, 0600); \ + module_param_named(aggr_interval, attrs.aggr_interval, ulong, \ + 0600); \ + module_param_named(min_nr_regions, attrs.min_nr_regions, ulong, \ + 0600); \ + module_param_named(max_nr_regions, attrs.max_nr_regions, ulong, \ + 0600); + +#define DEFINE_DAMON_MODULES_DAMOS_TIME_QUOTA(quota) \ + module_param_named(quota_ms, quota.ms, ulong, 0600); \ + module_param_named(quota_reset_interval_ms, \ + quota.reset_interval, ulong, 0600); + +#define DEFINE_DAMON_MODULES_DAMOS_QUOTAS(quota) \ + DEFINE_DAMON_MODULES_DAMOS_TIME_QUOTA(quota) \ + module_param_named(quota_sz, quota.sz, ulong, 0600); + +#define DEFINE_DAMON_MODULES_WMARKS_PARAMS(wmarks) \ + module_param_named(wmarks_interval, wmarks.interval, ulong, \ + 0600); \ + module_param_named(wmarks_high, wmarks.high, ulong, 0600); \ + module_param_named(wmarks_mid, wmarks.mid, ulong, 0600); \ + module_param_named(wmarks_low, wmarks.low, ulong, 0600); + +#define DEFINE_DAMON_MODULES_DAMOS_STATS_PARAMS(stat, try_name, \ + succ_name, qt_exceed_name) \ + module_param_named(nr_##try_name, stat.nr_tried, ulong, 0400); \ + module_param_named(bytes_##try_name, stat.sz_tried, ulong, \ + 0400); \ + module_param_named(nr_##succ_name, stat.nr_applied, ulong, \ + 0400); \ + module_param_named(bytes_##succ_name, stat.sz_applied, ulong, \ + 0400); \ + module_param_named(nr_##qt_exceed_name, stat.qt_exceeds, ulong, \ + 0400); + +int damon_modules_new_paddr_ctx_target(struct damon_ctx **ctxp, + struct damon_target **targetp); diff --git a/mm/damon/prmtv-common.c b/mm/damon/ops-common.c similarity index 86% rename from mm/damon/prmtv-common.c rename to mm/damon/ops-common.c index 92a04f5831d6bdab339e472c4fafa1da932c4630..75409601f9349f65241a6eb9b6558bdf574e1f9b 100644 --- a/mm/damon/prmtv-common.c +++ b/mm/damon/ops-common.c @@ -10,7 +10,7 @@ #include #include -#include "prmtv-common.h" +#include "ops-common.h" /* * Get an online page for a pfn if it's in the LRU list. Otherwise, returns @@ -73,8 +73,7 @@ void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr) } #ifdef CONFIG_MMU_NOTIFIER - if (mmu_notifier_clear_young(mm, addr, - addr + ((1UL) << HPAGE_PMD_SHIFT))) + if (mmu_notifier_clear_young(mm, addr, addr + HPAGE_PMD_SIZE)) referenced = true; #endif /* CONFIG_MMU_NOTIFIER */ @@ -89,7 +88,7 @@ void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr) #define DAMON_MAX_SUBSCORE (100) #define DAMON_MAX_AGE_IN_LOG (32) -int damon_pageout_score(struct damon_ctx *c, struct damon_region *r, +int damon_hot_score(struct damon_ctx *c, struct damon_region *r, struct damos *s) { unsigned int max_nr_accesses; @@ -100,10 +99,10 @@ int damon_pageout_score(struct damon_ctx *c, struct damon_region *r, unsigned int age_weight = s->quota.weight_age; int hotness; - max_nr_accesses = c->aggr_interval / c->sample_interval; + max_nr_accesses = c->attrs.aggr_interval / c->attrs.sample_interval; freq_subscore = r->nr_accesses * DAMON_MAX_SUBSCORE / max_nr_accesses; - age_in_sec = (unsigned long)r->age * c->aggr_interval / 1000000; + age_in_sec = (unsigned long)r->age * c->attrs.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) ; @@ -128,6 +127,14 @@ int damon_pageout_score(struct damon_ctx *c, struct damon_region *r, */ hotness = hotness * DAMOS_MAX_SCORE / DAMON_MAX_SUBSCORE; + return hotness; +} + +int damon_cold_score(struct damon_ctx *c, struct damon_region *r, + struct damos *s) +{ + int hotness = damon_hot_score(c, r, s); + /* Return coldness of the region */ return DAMOS_MAX_SCORE - hotness; } diff --git a/mm/damon/prmtv-common.h b/mm/damon/ops-common.h similarity index 71% rename from mm/damon/prmtv-common.h rename to mm/damon/ops-common.h index e790cb5f8fe05913ef868bd41743604c91d4aacf..8d82d37222042ffd1f52e6d73e0d46a0a8e74f34 100644 --- a/mm/damon/prmtv-common.h +++ b/mm/damon/ops-common.h @@ -12,5 +12,7 @@ struct page *damon_get_page(unsigned long pfn); void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr); 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, +int damon_cold_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 5e8244f65a1a243291cc4c060366589c43486522..5945e1e379382a55f97b35d60d2505518fa00fb4 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -14,7 +14,7 @@ #include #include "../internal.h" -#include "prmtv-common.h" +#include "ops-common.h" static bool __damon_pa_mkold(struct page *page, struct vm_area_struct *vma, unsigned long addr, void *arg) @@ -65,8 +65,7 @@ static void damon_pa_mkold(unsigned long paddr) put_page(page); } -static void __damon_pa_prepare_access_check(struct damon_ctx *ctx, - struct damon_region *r) +static void __damon_pa_prepare_access_check(struct damon_region *r) { r->sampling_addr = damon_rand(r->ar.start, r->ar.end); @@ -80,7 +79,7 @@ static void damon_pa_prepare_access_checks(struct damon_ctx *ctx) damon_for_each_target(t, ctx) { damon_for_each_region(r, t) - __damon_pa_prepare_access_check(ctx, r); + __damon_pa_prepare_access_check(r); } } @@ -112,7 +111,7 @@ static bool __damon_pa_young(struct page *page, struct vm_area_struct *vma, result->accessed = pmd_young(*pvmw.pmd) || !page_is_idle(page) || mmu_notifier_test_young(vma->vm_mm, addr); - result->page_sz = ((1UL) << HPAGE_PMD_SHIFT); + result->page_sz = HPAGE_PMD_SIZE; #else WARN_ON_ONCE(1); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -156,7 +155,7 @@ static bool damon_pa_young(unsigned long paddr, unsigned long *page_sz) need_lock = !PageAnon(page) || PageKsm(page); if (need_lock && !trylock_page(page)) { put_page(page); - return NULL; + return false; } rmap_walk(page, &rwc); @@ -170,8 +169,7 @@ static bool damon_pa_young(unsigned long paddr, unsigned long *page_sz) return result.accessed; } -static void __damon_pa_check_access(struct damon_ctx *ctx, - struct damon_region *r) +static void __damon_pa_check_access(struct damon_region *r) { static unsigned long last_addr; static unsigned long last_page_sz = PAGE_SIZE; @@ -200,7 +198,7 @@ static unsigned int damon_pa_check_accesses(struct damon_ctx *ctx) damon_for_each_target(t, ctx) { damon_for_each_region(r, t) { - __damon_pa_check_access(ctx, r); + __damon_pa_check_access(r); max_nr_accesses = max(r->nr_accesses, max_nr_accesses); } } @@ -208,21 +206,11 @@ static unsigned int damon_pa_check_accesses(struct damon_ctx *ctx) return max_nr_accesses; } -bool damon_pa_target_valid(void *t) -{ - return true; -} - -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)); @@ -235,25 +223,78 @@ static unsigned long damon_pa_apply_scheme(struct damon_ctx *ctx, put_page(page); continue; } - if (PageUnevictable(page)) { + if (PageUnevictable(page)) putback_lru_page(page); - } else { + else list_add(&page->lru, &page_list); - put_page(page); - } + put_page(page); } applied = reclaim_pages(&page_list); cond_resched(); return applied * PAGE_SIZE; } +static inline unsigned long damon_pa_mark_accessed_or_deactivate( + struct damon_region *r, bool mark_accessed) +{ + 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; + if (mark_accessed) + mark_page_accessed(page); + else + deactivate_page(page); + put_page(page); + applied++; + } + return applied * PAGE_SIZE; +} + +static unsigned long damon_pa_mark_accessed(struct damon_region *r) +{ + return damon_pa_mark_accessed_or_deactivate(r, true); +} + +static unsigned long damon_pa_deactivate_pages(struct damon_region *r) +{ + return damon_pa_mark_accessed_or_deactivate(r, false); +} + +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); + case DAMOS_STAT: + break; + default: + /* DAMOS actions that not yet supported by 'paddr'. */ + break; + } + return 0; +} + static int damon_pa_scheme_score(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, struct damos *scheme) { switch (scheme->action) { case DAMOS_PAGEOUT: - return damon_pageout_score(context, r, scheme); + return damon_cold_score(context, r, scheme); + case DAMOS_LRU_PRIO: + return damon_hot_score(context, r, scheme); + case DAMOS_LRU_DEPRIO: + return damon_cold_score(context, r, scheme); default: break; } @@ -261,15 +302,22 @@ static int damon_pa_scheme_score(struct damon_ctx *context, return DAMOS_MAX_SCORE; } -void damon_pa_set_primitives(struct damon_ctx *ctx) +static int __init damon_pa_initcall(void) { - ctx->primitive.init = NULL; - ctx->primitive.update = NULL; - ctx->primitive.prepare_access_checks = damon_pa_prepare_access_checks; - ctx->primitive.check_accesses = damon_pa_check_accesses; - ctx->primitive.reset_aggregated = NULL; - ctx->primitive.target_valid = damon_pa_target_valid; - ctx->primitive.cleanup = NULL; - ctx->primitive.apply_scheme = damon_pa_apply_scheme; - ctx->primitive.get_scheme_score = damon_pa_scheme_score; -} + struct damon_operations ops = { + .id = DAMON_OPS_PADDR, + .init = NULL, + .update = NULL, + .prepare_access_checks = damon_pa_prepare_access_checks, + .check_accesses = damon_pa_check_accesses, + .reset_aggregated = NULL, + .target_valid = NULL, + .cleanup = NULL, + .apply_scheme = damon_pa_apply_scheme, + .get_scheme_score = damon_pa_scheme_score, + }; + + return damon_register_ops(&ops); +}; + +subsys_initcall(damon_pa_initcall); diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c index bc476cef688e8d6c9f9799e5090774be7f47f465..408b9f7688ded79ae1c24f48d86d65e3fe2076a2 100644 --- a/mm/damon/reclaim.c +++ b/mm/damon/reclaim.c @@ -11,7 +11,8 @@ #include #include #include -#include + +#include "modules-common.h" #ifdef MODULE_PARAM_PREFIX #undef MODULE_PARAM_PREFIX @@ -28,7 +29,18 @@ * this. */ static bool enabled __read_mostly; -module_param(enabled, bool, 0600); + +/* + * Make DAMON_RECLAIM reads the input parameters again, except ``enabled``. + * + * Input parameters that updated while DAMON_RECLAIM is running are not applied + * by default. Once this parameter is set as ``Y``, DAMON_RECLAIM 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_RECLAIM will be disabled. + */ +static bool commit_inputs __read_mostly; +module_param(commit_inputs, bool, 0600); /* * Time threshold for cold memory regions identification in microseconds. @@ -39,124 +51,35 @@ module_param(enabled, bool, 0600); static unsigned long min_age __read_mostly = 120000000; module_param(min_age, ulong, 0600); -/* - * Limit of time for trying the reclamation in milliseconds. - * - * DAMON_RECLAIM tries to use only up to this time within a time window - * (quota_reset_interval_ms) for trying reclamation of cold pages. This can be - * used for limiting CPU consumption of DAMON_RECLAIM. 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); - -/* - * Limit of size of memory for the reclamation in bytes. - * - * DAMON_RECLAIM charges amount of memory which it tried to reclaim within a - * time window (quota_reset_interval_ms) and makes no more than this limit is - * tried. This can be used for limiting consumption of CPU and IO. If this - * value is zero, the limit is disabled. - * - * 128 MiB by default. - */ -static unsigned long quota_sz __read_mostly = 128 * 1024 * 1024; -module_param(quota_sz, ulong, 0600); - -/* - * The time/size quota charge reset interval in milliseconds. - * - * The charge reset interval for the quota of time (quota_ms) and size - * (quota_sz). That is, DAMON_RECLAIM does not try reclamation 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_RECLAIM 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_RECLAIM becomes inactive, so it does nothing but periodically - * checks the watermarks. 500 (50%) by default. - */ -static unsigned long wmarks_high __read_mostly = 500; -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_RECLAIM becomes active, so starts the monitoring - * and the reclaiming. 400 (40%) by default. - */ -static unsigned long wmarks_mid __read_mostly = 400; -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_RECLAIM becomes inactive, so it does nothing but periodically checks - * the watermarks. In the case, the system falls back to the LRU-based page - * granularity reclamation logic. 200 (20%) by default. - */ -static unsigned long wmarks_low __read_mostly = 200; -module_param(wmarks_low, ulong, 0600); - -/* - * Sampling interval for the monitoring in microseconds. - * - * The sampling interval of DAMON for the 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 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 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 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); +static struct damos_quota damon_reclaim_quota = { + /* use up to 10 ms time, reclaim up to 128 MiB per 1 sec by default */ + .ms = 10, + .sz = 128 * 1024 * 1024, + .reset_interval = 1000, + /* Within the quota, page out older regions first. */ + .weight_sz = 0, + .weight_nr_accesses = 0, + .weight_age = 1 +}; +DEFINE_DAMON_MODULES_DAMOS_QUOTAS(damon_reclaim_quota); + +static struct damos_watermarks damon_reclaim_wmarks = { + .metric = DAMOS_WMARK_FREE_MEM_RATE, + .interval = 5000000, /* 5 seconds */ + .high = 500, /* 50 percent */ + .mid = 400, /* 40 percent */ + .low = 200, /* 20 percent */ +}; +DEFINE_DAMON_MODULES_WMARKS_PARAMS(damon_reclaim_wmarks); + +static struct damon_attrs damon_reclaim_mon_attrs = { + .sample_interval = 5000, /* 5 ms */ + .aggr_interval = 100000, /* 100 ms */ + .ops_update_interval = 0, + .min_nr_regions = 10, + .max_nr_regions = 1000, +}; +DEFINE_DAMON_MODULES_MON_ATTRS_PARAMS(damon_reclaim_mon_attrs); /* * Start of the target memory region in physical address. @@ -185,115 +108,60 @@ module_param(monitor_region_end, ulong, 0600); static int kdamond_pid __read_mostly = -1; module_param(kdamond_pid, int, 0400); -/* - * Number of memory regions that tried to be reclaimed. - */ -static unsigned long nr_reclaim_tried_regions __read_mostly; -module_param(nr_reclaim_tried_regions, ulong, 0400); - -/* - * Total bytes of memory regions that tried to be reclaimed. - */ -static unsigned long bytes_reclaim_tried_regions __read_mostly; -module_param(bytes_reclaim_tried_regions, ulong, 0400); - -/* - * Number of memory regions that successfully be reclaimed. - */ -static unsigned long nr_reclaimed_regions __read_mostly; -module_param(nr_reclaimed_regions, ulong, 0400); - -/* - * Total bytes of memory regions that successfully be reclaimed. - */ -static unsigned long bytes_reclaimed_regions __read_mostly; -module_param(bytes_reclaimed_regions, ulong, 0400); - -/* - * Number of times that the time/space quota limits have exceeded - */ -static unsigned long nr_quota_exceeds __read_mostly; -module_param(nr_quota_exceeds, ulong, 0400); +static struct damos_stat damon_reclaim_stat; +DEFINE_DAMON_MODULES_DAMOS_STATS_PARAMS(damon_reclaim_stat, + reclaim_tried_regions, reclaimed_regions, quota_exceeds); static struct damon_ctx *ctx; static struct damon_target *target; -struct damon_reclaim_ram_walk_arg { - unsigned long start; - unsigned long end; -}; - -static int walk_system_ram(struct resource *res, void *arg) -{ - struct damon_reclaim_ram_walk_arg *a = arg; - - if (a->end - a->start < res->end - res->start) { - 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_reclaim_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; -} - static struct damos *damon_reclaim_new_scheme(void) { - struct damos_watermarks wmarks = { - .metric = DAMOS_WMARK_FREE_MEM_RATE, - .interval = wmarks_interval, - .high = wmarks_high, - .mid = wmarks_mid, - .low = wmarks_low, + struct damos_access_pattern pattern = { + /* Find regions having PAGE_SIZE or larger size */ + .min_sz_region = PAGE_SIZE, + .max_sz_region = ULONG_MAX, + /* and not accessed at all */ + .min_nr_accesses = 0, + .max_nr_accesses = 0, + /* for min_age or more micro-seconds */ + .min_age_region = min_age / + damon_reclaim_mon_attrs.aggr_interval, + .max_age_region = UINT_MAX, }; - struct damos_quota quota = { - /* - * Do not try reclamation for more than quota_ms milliseconds - * or quota_sz bytes within quota_reset_interval_ms. - */ - .ms = quota_ms, - .sz = quota_sz, - .reset_interval = quota_reset_interval_ms, - /* Within the quota, page out older regions 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 min_age or more micro-seconds, and */ - min_age / aggr_interval, UINT_MAX, + + return damon_new_scheme( + &pattern, /* page out those, as soon as found */ DAMOS_PAGEOUT, /* under the quota. */ - "a, + &damon_reclaim_quota, /* (De)activate this according to the watermarks. */ - &wmarks); + &damon_reclaim_wmarks); +} - return scheme; +static int damon_reclaim_apply_parameters(void) +{ + struct damos *scheme; + int err = 0; + + err = damon_set_attrs(ctx, &damon_reclaim_mon_attrs); + if (err) + return err; + + /* Will be freed by next 'damon_set_schemes()' below */ + scheme = damon_reclaim_new_scheme(); + if (!scheme) + return -ENOMEM; + damon_set_schemes(ctx, &scheme, 1); + + return damon_set_region_biggest_system_ram_default(target, + &monitor_region_start, + &monitor_region_end); } static int damon_reclaim_turn(bool on) { - struct damon_region *region; - struct damos *scheme; int err; if (!on) { @@ -303,100 +171,96 @@ static int damon_reclaim_turn(bool on) return err; } - err = damon_set_attrs(ctx, sample_interval, aggr_interval, 0, - min_nr_regions, max_nr_regions); + err = damon_reclaim_apply_parameters(); if (err) return err; - 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; - /* DAMON will free this on its own when finish monitoring */ - region = damon_new_region(monitor_region_start, monitor_region_end); - if (!region) - return -ENOMEM; - damon_add_region(region, target); + err = damon_start(&ctx, 1, true); + if (err) + return err; + kdamond_pid = ctx->kdamond->pid; + return 0; +} - /* Will be freed by 'damon_set_schemes()' below */ - scheme = damon_reclaim_new_scheme(); - if (!scheme) { - err = -ENOMEM; - goto free_region_out; - } - err = damon_set_schemes(ctx, &scheme, 1); +static int damon_reclaim_enabled_store(const char *val, + const struct kernel_param *kp) +{ + bool is_enabled = enabled; + bool enable; + int err; + + err = strtobool(val, &enable); if (err) - goto free_scheme_out; + return err; - err = damon_start(&ctx, 1); - if (!err) { - kdamond_pid = ctx->kdamond->pid; + if (is_enabled == enable) return 0; - } -free_scheme_out: - damon_destroy_scheme(scheme); -free_region_out: - damon_destroy_region(region, target); + /* Called before init function. The function will handle this. */ + if (!ctx) + goto set_param_out; + + err = damon_reclaim_turn(enable); + if (err) + return err; + +set_param_out: + enabled = enable; return err; } -#define ENABLE_CHECK_INTERVAL_MS 1000 -static struct delayed_work damon_reclaim_timer; -static void damon_reclaim_timer_fn(struct work_struct *work) +static const struct kernel_param_ops enabled_param_ops = { + .set = damon_reclaim_enabled_store, + .get = param_get_bool, +}; + +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) { - static bool last_enabled; - bool now_enabled; - - now_enabled = enabled; - if (last_enabled != now_enabled) { - if (!damon_reclaim_turn(now_enabled)) - last_enabled = now_enabled; - else - enabled = last_enabled; - } + int err; + + if (!commit_inputs) + return 0; - schedule_delayed_work(&damon_reclaim_timer, - msecs_to_jiffies(ENABLE_CHECK_INTERVAL_MS)); + err = damon_reclaim_apply_parameters(); + commit_inputs = false; + return err; } -static DECLARE_DELAYED_WORK(damon_reclaim_timer, damon_reclaim_timer_fn); static int damon_reclaim_after_aggregation(struct damon_ctx *c) { struct damos *s; /* update the stats parameter */ - damon_for_each_scheme(s, c) { - nr_reclaim_tried_regions = s->stat.nr_tried; - bytes_reclaim_tried_regions = s->stat.sz_tried; - nr_reclaimed_regions = s->stat.nr_applied; - bytes_reclaimed_regions = s->stat.sz_applied; - nr_quota_exceeds = s->stat.qt_exceeds; - } - return 0; + damon_for_each_scheme(s, c) + damon_reclaim_stat = s->stat; + + return damon_reclaim_handle_commit_inputs(); +} + +static int damon_reclaim_after_wmarks_check(struct damon_ctx *c) +{ + return damon_reclaim_handle_commit_inputs(); } static int __init damon_reclaim_init(void) { - ctx = damon_new_ctx(); - if (!ctx) - return -ENOMEM; + int err = damon_modules_new_paddr_ctx_target(&ctx, &target); + + if (err) + return err; - damon_pa_set_primitives(ctx); + ctx->callback.after_wmarks_check = damon_reclaim_after_wmarks_check; ctx->callback.after_aggregation = damon_reclaim_after_aggregation; - /* 4242 means nothing but fun */ - target = damon_new_target(4242); - if (!target) { - damon_destroy_ctx(ctx); - return -ENOMEM; - } - damon_add_target(ctx, target); + /* 'enabled' has set before this function, probably via command line */ + if (enabled) + err = damon_reclaim_turn(true); - schedule_delayed_work(&damon_reclaim_timer, 0); - return 0; + return err; } module_init(damon_reclaim_init); diff --git a/mm/damon/sysfs-common.c b/mm/damon/sysfs-common.c new file mode 100644 index 0000000000000000000000000000000000000000..52bebf242f74211098814d4b8a215d89dc26261d --- /dev/null +++ b/mm/damon/sysfs-common.c @@ -0,0 +1,107 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Common Primitives for DAMON Sysfs Interface + * + * Author: SeongJae Park + */ + +#include + +#include "sysfs-common.h" + +DEFINE_MUTEX(damon_sysfs_lock); + +/* + * unsigned long range directory + */ + +struct damon_sysfs_ul_range *damon_sysfs_ul_range_alloc( + unsigned long min, + unsigned long max) +{ + struct damon_sysfs_ul_range *range = kmalloc(sizeof(*range), + GFP_KERNEL); + + if (!range) + return NULL; + range->kobj = (struct kobject){}; + range->min = min; + range->max = max; + + return range; +} + +static ssize_t min_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct damon_sysfs_ul_range *range = container_of(kobj, + struct damon_sysfs_ul_range, kobj); + + return sysfs_emit(buf, "%lu\n", range->min); +} + +static ssize_t min_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct damon_sysfs_ul_range *range = container_of(kobj, + struct damon_sysfs_ul_range, kobj); + unsigned long min; + int err; + + err = kstrtoul(buf, 0, &min); + if (err) + return err; + + range->min = min; + return count; +} + +static ssize_t max_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct damon_sysfs_ul_range *range = container_of(kobj, + struct damon_sysfs_ul_range, kobj); + + return sysfs_emit(buf, "%lu\n", range->max); +} + +static ssize_t max_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct damon_sysfs_ul_range *range = container_of(kobj, + struct damon_sysfs_ul_range, kobj); + unsigned long max; + int err; + + err = kstrtoul(buf, 0, &max); + if (err) + return err; + + range->max = max; + return count; +} + +void damon_sysfs_ul_range_release(struct kobject *kobj) +{ + kfree(container_of(kobj, struct damon_sysfs_ul_range, kobj)); +} + +static struct kobj_attribute damon_sysfs_ul_range_min_attr = + __ATTR_RW_MODE(min, 0600); + +static struct kobj_attribute damon_sysfs_ul_range_max_attr = + __ATTR_RW_MODE(max, 0600); + +static struct attribute *damon_sysfs_ul_range_attrs[] = { + &damon_sysfs_ul_range_min_attr.attr, + &damon_sysfs_ul_range_max_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(damon_sysfs_ul_range); + +struct kobj_type damon_sysfs_ul_range_ktype = { + .release = damon_sysfs_ul_range_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damon_sysfs_ul_range_groups, +}; + diff --git a/mm/damon/sysfs-common.h b/mm/damon/sysfs-common.h new file mode 100644 index 0000000000000000000000000000000000000000..604a6cbc3edeab2e019a0dadd92282f147eafdf9 --- /dev/null +++ b/mm/damon/sysfs-common.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Common Primitives for DAMON Sysfs Interface + * + * Author: SeongJae Park + */ + +#include +#include + +extern struct mutex damon_sysfs_lock; + +struct damon_sysfs_ul_range { + struct kobject kobj; + unsigned long min; + unsigned long max; +}; + +struct damon_sysfs_ul_range *damon_sysfs_ul_range_alloc( + unsigned long min, + unsigned long max); +void damon_sysfs_ul_range_release(struct kobject *kobj); + +extern struct kobj_type damon_sysfs_ul_range_ktype; + +/* + * schemes directory + */ + +struct damon_sysfs_schemes { + struct kobject kobj; + struct damon_sysfs_scheme **schemes_arr; + int nr; +}; + +struct damon_sysfs_schemes *damon_sysfs_schemes_alloc(void); +void damon_sysfs_schemes_rm_dirs(struct damon_sysfs_schemes *schemes); + +extern struct kobj_type damon_sysfs_schemes_ktype; + +int damon_sysfs_set_schemes(struct damon_ctx *ctx, + struct damon_sysfs_schemes *sysfs_schemes); + +void damon_sysfs_schemes_update_stats( + struct damon_sysfs_schemes *sysfs_schemes, + struct damon_ctx *ctx); + +int damon_sysfs_schemes_update_regions_start( + struct damon_sysfs_schemes *sysfs_schemes, + struct damon_ctx *ctx); + +int damon_sysfs_schemes_update_regions_stop(struct damon_ctx *ctx); + +int damon_sysfs_schemes_clear_regions( + struct damon_sysfs_schemes *sysfs_schemes, + struct damon_ctx *ctx); diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c new file mode 100644 index 0000000000000000000000000000000000000000..81fc4d27f4e45d9789b6752f6f47ab14235d7a12 --- /dev/null +++ b/mm/damon/sysfs-schemes.c @@ -0,0 +1,1338 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DAMON sysfs Interface + * + * Copyright (c) 2022 SeongJae Park + */ + +#include + +#include "sysfs-common.h" + +/* + * scheme region directory + */ + +struct damon_sysfs_scheme_region { + struct kobject kobj; + struct damon_addr_range ar; + unsigned int nr_accesses; + unsigned int age; + struct list_head list; +}; + +static struct damon_sysfs_scheme_region *damon_sysfs_scheme_region_alloc( + struct damon_region *region) +{ + struct damon_sysfs_scheme_region *sysfs_region = kmalloc( + sizeof(*sysfs_region), GFP_KERNEL); + + if (!sysfs_region) + return NULL; + sysfs_region->kobj = (struct kobject){}; + sysfs_region->ar = region->ar; + sysfs_region->nr_accesses = region->nr_accesses; + sysfs_region->age = region->age; + INIT_LIST_HEAD(&sysfs_region->list); + return sysfs_region; +} + +static ssize_t start_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct damon_sysfs_scheme_region *region = container_of(kobj, + struct damon_sysfs_scheme_region, kobj); + + return sysfs_emit(buf, "%lu\n", region->ar.start); +} + +static ssize_t end_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct damon_sysfs_scheme_region *region = container_of(kobj, + struct damon_sysfs_scheme_region, kobj); + + return sysfs_emit(buf, "%lu\n", region->ar.end); +} + +static ssize_t nr_accesses_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_scheme_region *region = container_of(kobj, + struct damon_sysfs_scheme_region, kobj); + + return sysfs_emit(buf, "%u\n", region->nr_accesses); +} + +static ssize_t age_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct damon_sysfs_scheme_region *region = container_of(kobj, + struct damon_sysfs_scheme_region, kobj); + + return sysfs_emit(buf, "%u\n", region->age); +} + +static void damon_sysfs_scheme_region_release(struct kobject *kobj) +{ + struct damon_sysfs_scheme_region *region = container_of(kobj, + struct damon_sysfs_scheme_region, kobj); + + list_del(®ion->list); + kfree(region); +} + +static struct kobj_attribute damon_sysfs_scheme_region_start_attr = + __ATTR_RO_MODE(start, 0400); + +static struct kobj_attribute damon_sysfs_scheme_region_end_attr = + __ATTR_RO_MODE(end, 0400); + +static struct kobj_attribute damon_sysfs_scheme_region_nr_accesses_attr = + __ATTR_RO_MODE(nr_accesses, 0400); + +static struct kobj_attribute damon_sysfs_scheme_region_age_attr = + __ATTR_RO_MODE(age, 0400); + +static struct attribute *damon_sysfs_scheme_region_attrs[] = { + &damon_sysfs_scheme_region_start_attr.attr, + &damon_sysfs_scheme_region_end_attr.attr, + &damon_sysfs_scheme_region_nr_accesses_attr.attr, + &damon_sysfs_scheme_region_age_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(damon_sysfs_scheme_region); + +static struct kobj_type damon_sysfs_scheme_region_ktype = { + .release = damon_sysfs_scheme_region_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damon_sysfs_scheme_region_groups, +}; + +/* + * scheme regions directory + */ + +struct damon_sysfs_scheme_regions { + struct kobject kobj; + struct list_head regions_list; + int nr_regions; +}; + +static struct damon_sysfs_scheme_regions * +damon_sysfs_scheme_regions_alloc(void) +{ + struct damon_sysfs_scheme_regions *regions = kmalloc(sizeof(*regions), + GFP_KERNEL); + + regions->kobj = (struct kobject){}; + INIT_LIST_HEAD(®ions->regions_list); + regions->nr_regions = 0; + return regions; +} + +static void damon_sysfs_scheme_regions_rm_dirs( + struct damon_sysfs_scheme_regions *regions) +{ + struct damon_sysfs_scheme_region *r, *next; + + list_for_each_entry_safe(r, next, ®ions->regions_list, list) { + /* release function deletes it from the list */ + kobject_put(&r->kobj); + regions->nr_regions--; + } +} + +static void damon_sysfs_scheme_regions_release(struct kobject *kobj) +{ + kfree(container_of(kobj, struct damon_sysfs_scheme_regions, kobj)); +} + +static struct attribute *damon_sysfs_scheme_regions_attrs[] = { + NULL, +}; +ATTRIBUTE_GROUPS(damon_sysfs_scheme_regions); + +static struct kobj_type damon_sysfs_scheme_regions_ktype = { + .release = damon_sysfs_scheme_regions_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damon_sysfs_scheme_regions_groups, +}; + +/* + * schemes/stats directory + */ + +struct damon_sysfs_stats { + struct kobject kobj; + unsigned long nr_tried; + unsigned long sz_tried; + unsigned long nr_applied; + unsigned long sz_applied; + unsigned long qt_exceeds; +}; + +static struct damon_sysfs_stats *damon_sysfs_stats_alloc(void) +{ + return kzalloc(sizeof(struct damon_sysfs_stats), GFP_KERNEL); +} + +static ssize_t nr_tried_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct damon_sysfs_stats *stats = container_of(kobj, + struct damon_sysfs_stats, kobj); + + return sysfs_emit(buf, "%lu\n", stats->nr_tried); +} + +static ssize_t sz_tried_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct damon_sysfs_stats *stats = container_of(kobj, + struct damon_sysfs_stats, kobj); + + return sysfs_emit(buf, "%lu\n", stats->sz_tried); +} + +static ssize_t nr_applied_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_stats *stats = container_of(kobj, + struct damon_sysfs_stats, kobj); + + return sysfs_emit(buf, "%lu\n", stats->nr_applied); +} + +static ssize_t sz_applied_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_stats *stats = container_of(kobj, + struct damon_sysfs_stats, kobj); + + return sysfs_emit(buf, "%lu\n", stats->sz_applied); +} + +static ssize_t qt_exceeds_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_stats *stats = container_of(kobj, + struct damon_sysfs_stats, kobj); + + return sysfs_emit(buf, "%lu\n", stats->qt_exceeds); +} + +static void damon_sysfs_stats_release(struct kobject *kobj) +{ + kfree(container_of(kobj, struct damon_sysfs_stats, kobj)); +} + +static struct kobj_attribute damon_sysfs_stats_nr_tried_attr = + __ATTR_RO_MODE(nr_tried, 0400); + +static struct kobj_attribute damon_sysfs_stats_sz_tried_attr = + __ATTR_RO_MODE(sz_tried, 0400); + +static struct kobj_attribute damon_sysfs_stats_nr_applied_attr = + __ATTR_RO_MODE(nr_applied, 0400); + +static struct kobj_attribute damon_sysfs_stats_sz_applied_attr = + __ATTR_RO_MODE(sz_applied, 0400); + +static struct kobj_attribute damon_sysfs_stats_qt_exceeds_attr = + __ATTR_RO_MODE(qt_exceeds, 0400); + +static struct attribute *damon_sysfs_stats_attrs[] = { + &damon_sysfs_stats_nr_tried_attr.attr, + &damon_sysfs_stats_sz_tried_attr.attr, + &damon_sysfs_stats_nr_applied_attr.attr, + &damon_sysfs_stats_sz_applied_attr.attr, + &damon_sysfs_stats_qt_exceeds_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(damon_sysfs_stats); + +static struct kobj_type damon_sysfs_stats_ktype = { + .release = damon_sysfs_stats_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damon_sysfs_stats_groups, +}; + +/* + * watermarks directory + */ + +struct damon_sysfs_watermarks { + struct kobject kobj; + enum damos_wmark_metric metric; + unsigned long interval_us; + unsigned long high; + unsigned long mid; + unsigned long low; +}; + +static struct damon_sysfs_watermarks *damon_sysfs_watermarks_alloc( + enum damos_wmark_metric metric, unsigned long interval_us, + unsigned long high, unsigned long mid, unsigned long low) +{ + struct damon_sysfs_watermarks *watermarks = kmalloc( + sizeof(*watermarks), GFP_KERNEL); + + if (!watermarks) + return NULL; + watermarks->kobj = (struct kobject){}; + watermarks->metric = metric; + watermarks->interval_us = interval_us; + watermarks->high = high; + watermarks->mid = mid; + watermarks->low = low; + return watermarks; +} + +/* Should match with enum damos_wmark_metric */ +static const char * const damon_sysfs_wmark_metric_strs[] = { + "none", + "free_mem_rate", +}; + +static ssize_t metric_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct damon_sysfs_watermarks *watermarks = container_of(kobj, + struct damon_sysfs_watermarks, kobj); + + return sysfs_emit(buf, "%s\n", + damon_sysfs_wmark_metric_strs[watermarks->metric]); +} + +static ssize_t metric_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct damon_sysfs_watermarks *watermarks = container_of(kobj, + struct damon_sysfs_watermarks, kobj); + enum damos_wmark_metric metric; + + for (metric = 0; metric < NR_DAMOS_WMARK_METRICS; metric++) { + if (sysfs_streq(buf, damon_sysfs_wmark_metric_strs[metric])) { + watermarks->metric = metric; + return count; + } + } + return -EINVAL; +} + +static ssize_t interval_us_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_watermarks *watermarks = container_of(kobj, + struct damon_sysfs_watermarks, kobj); + + return sysfs_emit(buf, "%lu\n", watermarks->interval_us); +} + +static ssize_t interval_us_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damon_sysfs_watermarks *watermarks = container_of(kobj, + struct damon_sysfs_watermarks, kobj); + int err = kstrtoul(buf, 0, &watermarks->interval_us); + + return err ? err : count; +} + +static ssize_t high_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_watermarks *watermarks = container_of(kobj, + struct damon_sysfs_watermarks, kobj); + + return sysfs_emit(buf, "%lu\n", watermarks->high); +} + +static ssize_t high_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damon_sysfs_watermarks *watermarks = container_of(kobj, + struct damon_sysfs_watermarks, kobj); + int err = kstrtoul(buf, 0, &watermarks->high); + + return err ? err : count; +} + +static ssize_t mid_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_watermarks *watermarks = container_of(kobj, + struct damon_sysfs_watermarks, kobj); + + return sysfs_emit(buf, "%lu\n", watermarks->mid); +} + +static ssize_t mid_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damon_sysfs_watermarks *watermarks = container_of(kobj, + struct damon_sysfs_watermarks, kobj); + int err = kstrtoul(buf, 0, &watermarks->mid); + + return err ? err : count; +} + +static ssize_t low_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_watermarks *watermarks = container_of(kobj, + struct damon_sysfs_watermarks, kobj); + + return sysfs_emit(buf, "%lu\n", watermarks->low); +} + +static ssize_t low_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damon_sysfs_watermarks *watermarks = container_of(kobj, + struct damon_sysfs_watermarks, kobj); + int err = kstrtoul(buf, 0, &watermarks->low); + + return err ? err : count; +} + +static void damon_sysfs_watermarks_release(struct kobject *kobj) +{ + kfree(container_of(kobj, struct damon_sysfs_watermarks, kobj)); +} + +static struct kobj_attribute damon_sysfs_watermarks_metric_attr = + __ATTR_RW_MODE(metric, 0600); + +static struct kobj_attribute damon_sysfs_watermarks_interval_us_attr = + __ATTR_RW_MODE(interval_us, 0600); + +static struct kobj_attribute damon_sysfs_watermarks_high_attr = + __ATTR_RW_MODE(high, 0600); + +static struct kobj_attribute damon_sysfs_watermarks_mid_attr = + __ATTR_RW_MODE(mid, 0600); + +static struct kobj_attribute damon_sysfs_watermarks_low_attr = + __ATTR_RW_MODE(low, 0600); + +static struct attribute *damon_sysfs_watermarks_attrs[] = { + &damon_sysfs_watermarks_metric_attr.attr, + &damon_sysfs_watermarks_interval_us_attr.attr, + &damon_sysfs_watermarks_high_attr.attr, + &damon_sysfs_watermarks_mid_attr.attr, + &damon_sysfs_watermarks_low_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(damon_sysfs_watermarks); + +static struct kobj_type damon_sysfs_watermarks_ktype = { + .release = damon_sysfs_watermarks_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damon_sysfs_watermarks_groups, +}; + +/* + * scheme/weights directory + */ + +struct damon_sysfs_weights { + struct kobject kobj; + unsigned int sz; + unsigned int nr_accesses; + unsigned int age; +}; + +static struct damon_sysfs_weights *damon_sysfs_weights_alloc(unsigned int sz, + unsigned int nr_accesses, unsigned int age) +{ + struct damon_sysfs_weights *weights = kmalloc(sizeof(*weights), + GFP_KERNEL); + + if (!weights) + return NULL; + weights->kobj = (struct kobject){}; + weights->sz = sz; + weights->nr_accesses = nr_accesses; + weights->age = age; + return weights; +} + +static ssize_t sz_permil_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_weights *weights = container_of(kobj, + struct damon_sysfs_weights, kobj); + + return sysfs_emit(buf, "%u\n", weights->sz); +} + +static ssize_t sz_permil_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damon_sysfs_weights *weights = container_of(kobj, + struct damon_sysfs_weights, kobj); + int err = kstrtouint(buf, 0, &weights->sz); + + return err ? err : count; +} + +static ssize_t nr_accesses_permil_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_weights *weights = container_of(kobj, + struct damon_sysfs_weights, kobj); + + return sysfs_emit(buf, "%u\n", weights->nr_accesses); +} + +static ssize_t nr_accesses_permil_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damon_sysfs_weights *weights = container_of(kobj, + struct damon_sysfs_weights, kobj); + int err = kstrtouint(buf, 0, &weights->nr_accesses); + + return err ? err : count; +} + +static ssize_t age_permil_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_weights *weights = container_of(kobj, + struct damon_sysfs_weights, kobj); + + return sysfs_emit(buf, "%u\n", weights->age); +} + +static ssize_t age_permil_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damon_sysfs_weights *weights = container_of(kobj, + struct damon_sysfs_weights, kobj); + int err = kstrtouint(buf, 0, &weights->age); + + return err ? err : count; +} + +static void damon_sysfs_weights_release(struct kobject *kobj) +{ + kfree(container_of(kobj, struct damon_sysfs_weights, kobj)); +} + +static struct kobj_attribute damon_sysfs_weights_sz_attr = + __ATTR_RW_MODE(sz_permil, 0600); + +static struct kobj_attribute damon_sysfs_weights_nr_accesses_attr = + __ATTR_RW_MODE(nr_accesses_permil, 0600); + +static struct kobj_attribute damon_sysfs_weights_age_attr = + __ATTR_RW_MODE(age_permil, 0600); + +static struct attribute *damon_sysfs_weights_attrs[] = { + &damon_sysfs_weights_sz_attr.attr, + &damon_sysfs_weights_nr_accesses_attr.attr, + &damon_sysfs_weights_age_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(damon_sysfs_weights); + +static struct kobj_type damon_sysfs_weights_ktype = { + .release = damon_sysfs_weights_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damon_sysfs_weights_groups, +}; + +/* + * quotas directory + */ + +struct damon_sysfs_quotas { + struct kobject kobj; + struct damon_sysfs_weights *weights; + unsigned long ms; + unsigned long sz; + unsigned long reset_interval_ms; +}; + +static struct damon_sysfs_quotas *damon_sysfs_quotas_alloc(void) +{ + return kzalloc(sizeof(struct damon_sysfs_quotas), GFP_KERNEL); +} + +static int damon_sysfs_quotas_add_dirs(struct damon_sysfs_quotas *quotas) +{ + struct damon_sysfs_weights *weights; + int err; + + weights = damon_sysfs_weights_alloc(0, 0, 0); + if (!weights) + return -ENOMEM; + + err = kobject_init_and_add(&weights->kobj, &damon_sysfs_weights_ktype, + "as->kobj, "weights"); + if (err) + kobject_put(&weights->kobj); + else + quotas->weights = weights; + return err; +} + +static void damon_sysfs_quotas_rm_dirs(struct damon_sysfs_quotas *quotas) +{ + kobject_put("as->weights->kobj); +} + +static ssize_t ms_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct damon_sysfs_quotas *quotas = container_of(kobj, + struct damon_sysfs_quotas, kobj); + + return sysfs_emit(buf, "%lu\n", quotas->ms); +} + +static ssize_t ms_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct damon_sysfs_quotas *quotas = container_of(kobj, + struct damon_sysfs_quotas, kobj); + int err = kstrtoul(buf, 0, "as->ms); + + if (err) + return -EINVAL; + return count; +} + +static ssize_t bytes_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct damon_sysfs_quotas *quotas = container_of(kobj, + struct damon_sysfs_quotas, kobj); + + return sysfs_emit(buf, "%lu\n", quotas->sz); +} + +static ssize_t bytes_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damon_sysfs_quotas *quotas = container_of(kobj, + struct damon_sysfs_quotas, kobj); + int err = kstrtoul(buf, 0, "as->sz); + + if (err) + return -EINVAL; + return count; +} + +static ssize_t reset_interval_ms_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_quotas *quotas = container_of(kobj, + struct damon_sysfs_quotas, kobj); + + return sysfs_emit(buf, "%lu\n", quotas->reset_interval_ms); +} + +static ssize_t reset_interval_ms_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damon_sysfs_quotas *quotas = container_of(kobj, + struct damon_sysfs_quotas, kobj); + int err = kstrtoul(buf, 0, "as->reset_interval_ms); + + if (err) + return -EINVAL; + return count; +} + +static void damon_sysfs_quotas_release(struct kobject *kobj) +{ + kfree(container_of(kobj, struct damon_sysfs_quotas, kobj)); +} + +static struct kobj_attribute damon_sysfs_quotas_ms_attr = + __ATTR_RW_MODE(ms, 0600); + +static struct kobj_attribute damon_sysfs_quotas_sz_attr = + __ATTR_RW_MODE(bytes, 0600); + +static struct kobj_attribute damon_sysfs_quotas_reset_interval_ms_attr = + __ATTR_RW_MODE(reset_interval_ms, 0600); + +static struct attribute *damon_sysfs_quotas_attrs[] = { + &damon_sysfs_quotas_ms_attr.attr, + &damon_sysfs_quotas_sz_attr.attr, + &damon_sysfs_quotas_reset_interval_ms_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(damon_sysfs_quotas); + +static struct kobj_type damon_sysfs_quotas_ktype = { + .release = damon_sysfs_quotas_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damon_sysfs_quotas_groups, +}; + +/* + * access_pattern directory + */ + +struct damon_sysfs_access_pattern { + struct kobject kobj; + struct damon_sysfs_ul_range *sz; + struct damon_sysfs_ul_range *nr_accesses; + struct damon_sysfs_ul_range *age; +}; + +static +struct damon_sysfs_access_pattern *damon_sysfs_access_pattern_alloc(void) +{ + struct damon_sysfs_access_pattern *access_pattern = + kmalloc(sizeof(*access_pattern), GFP_KERNEL); + + if (!access_pattern) + return NULL; + access_pattern->kobj = (struct kobject){}; + return access_pattern; +} + +static int damon_sysfs_access_pattern_add_range_dir( + struct damon_sysfs_access_pattern *access_pattern, + struct damon_sysfs_ul_range **range_dir_ptr, + char *name) +{ + struct damon_sysfs_ul_range *range = damon_sysfs_ul_range_alloc(0, 0); + int err; + + if (!range) + return -ENOMEM; + err = kobject_init_and_add(&range->kobj, &damon_sysfs_ul_range_ktype, + &access_pattern->kobj, name); + if (err) + kobject_put(&range->kobj); + else + *range_dir_ptr = range; + return err; +} + +static int damon_sysfs_access_pattern_add_dirs( + struct damon_sysfs_access_pattern *access_pattern) +{ + int err; + + err = damon_sysfs_access_pattern_add_range_dir(access_pattern, + &access_pattern->sz, "sz"); + if (err) + goto put_sz_out; + + err = damon_sysfs_access_pattern_add_range_dir(access_pattern, + &access_pattern->nr_accesses, "nr_accesses"); + if (err) + goto put_nr_accesses_sz_out; + + err = damon_sysfs_access_pattern_add_range_dir(access_pattern, + &access_pattern->age, "age"); + if (err) + goto put_age_nr_accesses_sz_out; + return 0; + +put_age_nr_accesses_sz_out: + kobject_put(&access_pattern->age->kobj); + access_pattern->age = NULL; +put_nr_accesses_sz_out: + kobject_put(&access_pattern->nr_accesses->kobj); + access_pattern->nr_accesses = NULL; +put_sz_out: + kobject_put(&access_pattern->sz->kobj); + access_pattern->sz = NULL; + return err; +} + +static void damon_sysfs_access_pattern_rm_dirs( + struct damon_sysfs_access_pattern *access_pattern) +{ + kobject_put(&access_pattern->sz->kobj); + kobject_put(&access_pattern->nr_accesses->kobj); + kobject_put(&access_pattern->age->kobj); +} + +static void damon_sysfs_access_pattern_release(struct kobject *kobj) +{ + kfree(container_of(kobj, struct damon_sysfs_access_pattern, kobj)); +} + +static struct attribute *damon_sysfs_access_pattern_attrs[] = { + NULL, +}; +ATTRIBUTE_GROUPS(damon_sysfs_access_pattern); + +static struct kobj_type damon_sysfs_access_pattern_ktype = { + .release = damon_sysfs_access_pattern_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damon_sysfs_access_pattern_groups, +}; + +/* + * scheme directory + */ + +struct damon_sysfs_scheme { + struct kobject kobj; + enum damos_action action; + struct damon_sysfs_access_pattern *access_pattern; + struct damon_sysfs_quotas *quotas; + struct damon_sysfs_watermarks *watermarks; + struct damon_sysfs_stats *stats; + struct damon_sysfs_scheme_regions *tried_regions; +}; + +/* This should match with enum damos_action */ +static const char * const damon_sysfs_damos_action_strs[] = { + "willneed", + "cold", + "pageout", + "hugepage", + "nohugepage", + "lru_prio", + "lru_deprio", + "stat", +}; + +static struct damon_sysfs_scheme *damon_sysfs_scheme_alloc( + enum damos_action action) +{ + struct damon_sysfs_scheme *scheme = kmalloc(sizeof(*scheme), + GFP_KERNEL); + + if (!scheme) + return NULL; + scheme->kobj = (struct kobject){}; + scheme->action = action; + return scheme; +} + +static int damon_sysfs_scheme_set_access_pattern( + struct damon_sysfs_scheme *scheme) +{ + struct damon_sysfs_access_pattern *access_pattern; + int err; + + access_pattern = damon_sysfs_access_pattern_alloc(); + if (!access_pattern) + return -ENOMEM; + err = kobject_init_and_add(&access_pattern->kobj, + &damon_sysfs_access_pattern_ktype, &scheme->kobj, + "access_pattern"); + if (err) + goto out; + err = damon_sysfs_access_pattern_add_dirs(access_pattern); + if (err) + goto out; + scheme->access_pattern = access_pattern; + return 0; + +out: + kobject_put(&access_pattern->kobj); + return err; +} + +static int damon_sysfs_scheme_set_quotas(struct damon_sysfs_scheme *scheme) +{ + struct damon_sysfs_quotas *quotas = damon_sysfs_quotas_alloc(); + int err; + + if (!quotas) + return -ENOMEM; + err = kobject_init_and_add("as->kobj, &damon_sysfs_quotas_ktype, + &scheme->kobj, "quotas"); + if (err) + goto out; + err = damon_sysfs_quotas_add_dirs(quotas); + if (err) + goto out; + scheme->quotas = quotas; + return 0; + +out: + kobject_put("as->kobj); + return err; +} + +static int damon_sysfs_scheme_set_watermarks(struct damon_sysfs_scheme *scheme) +{ + struct damon_sysfs_watermarks *watermarks = + damon_sysfs_watermarks_alloc(DAMOS_WMARK_NONE, 0, 0, 0, 0); + int err; + + if (!watermarks) + return -ENOMEM; + err = kobject_init_and_add(&watermarks->kobj, + &damon_sysfs_watermarks_ktype, &scheme->kobj, + "watermarks"); + if (err) + kobject_put(&watermarks->kobj); + else + scheme->watermarks = watermarks; + return err; +} + +static int damon_sysfs_scheme_set_stats(struct damon_sysfs_scheme *scheme) +{ + struct damon_sysfs_stats *stats = damon_sysfs_stats_alloc(); + int err; + + if (!stats) + return -ENOMEM; + err = kobject_init_and_add(&stats->kobj, &damon_sysfs_stats_ktype, + &scheme->kobj, "stats"); + if (err) + kobject_put(&stats->kobj); + else + scheme->stats = stats; + return err; +} + +static int damon_sysfs_scheme_set_tried_regions( + struct damon_sysfs_scheme *scheme) +{ + struct damon_sysfs_scheme_regions *tried_regions = + damon_sysfs_scheme_regions_alloc(); + int err; + + if (!tried_regions) + return -ENOMEM; + err = kobject_init_and_add(&tried_regions->kobj, + &damon_sysfs_scheme_regions_ktype, &scheme->kobj, + "tried_regions"); + if (err) + kobject_put(&tried_regions->kobj); + else + scheme->tried_regions = tried_regions; + return err; +} + +static int damon_sysfs_scheme_add_dirs(struct damon_sysfs_scheme *scheme) +{ + int err; + + err = damon_sysfs_scheme_set_access_pattern(scheme); + if (err) + return err; + err = damon_sysfs_scheme_set_quotas(scheme); + if (err) + goto put_access_pattern_out; + err = damon_sysfs_scheme_set_watermarks(scheme); + if (err) + goto put_quotas_access_pattern_out; + err = damon_sysfs_scheme_set_stats(scheme); + if (err) + goto put_watermarks_quotas_access_pattern_out; + err = damon_sysfs_scheme_set_tried_regions(scheme); + if (err) + goto put_tried_regions_out; + return 0; + +put_tried_regions_out: + kobject_put(&scheme->tried_regions->kobj); + scheme->tried_regions = NULL; +put_watermarks_quotas_access_pattern_out: + kobject_put(&scheme->watermarks->kobj); + scheme->watermarks = NULL; +put_quotas_access_pattern_out: + kobject_put(&scheme->quotas->kobj); + scheme->quotas = NULL; +put_access_pattern_out: + kobject_put(&scheme->access_pattern->kobj); + scheme->access_pattern = NULL; + return err; +} + +static void damon_sysfs_scheme_rm_dirs(struct damon_sysfs_scheme *scheme) +{ + damon_sysfs_access_pattern_rm_dirs(scheme->access_pattern); + kobject_put(&scheme->access_pattern->kobj); + damon_sysfs_quotas_rm_dirs(scheme->quotas); + kobject_put(&scheme->quotas->kobj); + kobject_put(&scheme->watermarks->kobj); + kobject_put(&scheme->stats->kobj); + damon_sysfs_scheme_regions_rm_dirs(scheme->tried_regions); + kobject_put(&scheme->tried_regions->kobj); +} + +static ssize_t action_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct damon_sysfs_scheme *scheme = container_of(kobj, + struct damon_sysfs_scheme, kobj); + + return sysfs_emit(buf, "%s\n", + damon_sysfs_damos_action_strs[scheme->action]); +} + +static ssize_t action_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct damon_sysfs_scheme *scheme = container_of(kobj, + struct damon_sysfs_scheme, kobj); + enum damos_action action; + + for (action = 0; action < NR_DAMOS_ACTIONS; action++) { + if (sysfs_streq(buf, damon_sysfs_damos_action_strs[action])) { + scheme->action = action; + return count; + } + } + return -EINVAL; +} + +static void damon_sysfs_scheme_release(struct kobject *kobj) +{ + kfree(container_of(kobj, struct damon_sysfs_scheme, kobj)); +} + +static struct kobj_attribute damon_sysfs_scheme_action_attr = + __ATTR_RW_MODE(action, 0600); + +static struct attribute *damon_sysfs_scheme_attrs[] = { + &damon_sysfs_scheme_action_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(damon_sysfs_scheme); + +static struct kobj_type damon_sysfs_scheme_ktype = { + .release = damon_sysfs_scheme_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damon_sysfs_scheme_groups, +}; + +/* + * schemes directory + */ + +struct damon_sysfs_schemes *damon_sysfs_schemes_alloc(void) +{ + return kzalloc(sizeof(struct damon_sysfs_schemes), GFP_KERNEL); +} + +void damon_sysfs_schemes_rm_dirs(struct damon_sysfs_schemes *schemes) +{ + struct damon_sysfs_scheme **schemes_arr = schemes->schemes_arr; + int i; + + for (i = 0; i < schemes->nr; i++) { + damon_sysfs_scheme_rm_dirs(schemes_arr[i]); + kobject_put(&schemes_arr[i]->kobj); + } + schemes->nr = 0; + kfree(schemes_arr); + schemes->schemes_arr = NULL; +} + +static int damon_sysfs_schemes_add_dirs(struct damon_sysfs_schemes *schemes, + int nr_schemes) +{ + struct damon_sysfs_scheme **schemes_arr, *scheme; + int err, i; + + damon_sysfs_schemes_rm_dirs(schemes); + if (!nr_schemes) + return 0; + + schemes_arr = kmalloc_array(nr_schemes, sizeof(*schemes_arr), + GFP_KERNEL | __GFP_NOWARN); + if (!schemes_arr) + return -ENOMEM; + schemes->schemes_arr = schemes_arr; + + for (i = 0; i < nr_schemes; i++) { + scheme = damon_sysfs_scheme_alloc(DAMOS_STAT); + if (!scheme) { + damon_sysfs_schemes_rm_dirs(schemes); + return -ENOMEM; + } + + err = kobject_init_and_add(&scheme->kobj, + &damon_sysfs_scheme_ktype, &schemes->kobj, + "%d", i); + if (err) + goto out; + err = damon_sysfs_scheme_add_dirs(scheme); + if (err) + goto out; + + schemes_arr[i] = scheme; + schemes->nr++; + } + return 0; + +out: + damon_sysfs_schemes_rm_dirs(schemes); + kobject_put(&scheme->kobj); + return err; +} + +static ssize_t nr_schemes_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_schemes *schemes = container_of(kobj, + struct damon_sysfs_schemes, kobj); + + return sysfs_emit(buf, "%d\n", schemes->nr); +} + +static ssize_t nr_schemes_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damon_sysfs_schemes *schemes; + int nr, err = kstrtoint(buf, 0, &nr); + + if (err) + return err; + if (nr < 0) + return -EINVAL; + + schemes = container_of(kobj, struct damon_sysfs_schemes, kobj); + + if (!mutex_trylock(&damon_sysfs_lock)) + return -EBUSY; + err = damon_sysfs_schemes_add_dirs(schemes, nr); + mutex_unlock(&damon_sysfs_lock); + if (err) + return err; + return count; +} + +static void damon_sysfs_schemes_release(struct kobject *kobj) +{ + kfree(container_of(kobj, struct damon_sysfs_schemes, kobj)); +} + +static struct kobj_attribute damon_sysfs_schemes_nr_attr = + __ATTR_RW_MODE(nr_schemes, 0600); + +static struct attribute *damon_sysfs_schemes_attrs[] = { + &damon_sysfs_schemes_nr_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(damon_sysfs_schemes); + +struct kobj_type damon_sysfs_schemes_ktype = { + .release = damon_sysfs_schemes_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damon_sysfs_schemes_groups, +}; + +static struct damos *damon_sysfs_mk_scheme( + struct damon_sysfs_scheme *sysfs_scheme) +{ + struct damon_sysfs_access_pattern *access_pattern = + sysfs_scheme->access_pattern; + struct damon_sysfs_quotas *sysfs_quotas = sysfs_scheme->quotas; + struct damon_sysfs_weights *sysfs_weights = sysfs_quotas->weights; + struct damon_sysfs_watermarks *sysfs_wmarks = sysfs_scheme->watermarks; + + struct damos_access_pattern pattern = { + .min_sz_region = access_pattern->sz->min, + .max_sz_region = access_pattern->sz->max, + .min_nr_accesses = access_pattern->nr_accesses->min, + .max_nr_accesses = access_pattern->nr_accesses->max, + .min_age_region = access_pattern->age->min, + .max_age_region = access_pattern->age->max, + }; + struct damos_quota quota = { + .ms = sysfs_quotas->ms, + .sz = sysfs_quotas->sz, + .reset_interval = sysfs_quotas->reset_interval_ms, + .weight_sz = sysfs_weights->sz, + .weight_nr_accesses = sysfs_weights->nr_accesses, + .weight_age = sysfs_weights->age, + }; + struct damos_watermarks wmarks = { + .metric = sysfs_wmarks->metric, + .interval = sysfs_wmarks->interval_us, + .high = sysfs_wmarks->high, + .mid = sysfs_wmarks->mid, + .low = sysfs_wmarks->low, + }; + + return damon_new_scheme(&pattern, sysfs_scheme->action, "a, + &wmarks); +} + +static void damon_sysfs_update_scheme(struct damos *scheme, + struct damon_sysfs_scheme *sysfs_scheme) +{ + struct damon_sysfs_access_pattern *access_pattern = + sysfs_scheme->access_pattern; + struct damon_sysfs_quotas *sysfs_quotas = sysfs_scheme->quotas; + struct damon_sysfs_weights *sysfs_weights = sysfs_quotas->weights; + struct damon_sysfs_watermarks *sysfs_wmarks = sysfs_scheme->watermarks; + + scheme->pattern.min_sz_region = access_pattern->sz->min; + scheme->pattern.max_sz_region = access_pattern->sz->max; + scheme->pattern.min_nr_accesses = access_pattern->nr_accesses->min; + scheme->pattern.max_nr_accesses = access_pattern->nr_accesses->max; + scheme->pattern.min_age_region = access_pattern->age->min; + scheme->pattern.max_age_region = access_pattern->age->max; + + scheme->action = sysfs_scheme->action; + + scheme->quota.ms = sysfs_quotas->ms; + scheme->quota.sz = sysfs_quotas->sz; + scheme->quota.reset_interval = sysfs_quotas->reset_interval_ms; + scheme->quota.weight_sz = sysfs_weights->sz; + scheme->quota.weight_nr_accesses = sysfs_weights->nr_accesses; + scheme->quota.weight_age = sysfs_weights->age; + + scheme->wmarks.metric = sysfs_wmarks->metric; + scheme->wmarks.interval = sysfs_wmarks->interval_us; + scheme->wmarks.high = sysfs_wmarks->high; + scheme->wmarks.mid = sysfs_wmarks->mid; + scheme->wmarks.low = sysfs_wmarks->low; +} + +int damon_sysfs_set_schemes(struct damon_ctx *ctx, + struct damon_sysfs_schemes *sysfs_schemes) +{ + struct damos *scheme, *next; + int i = 0; + + damon_for_each_scheme_safe(scheme, next, ctx) { + if (i < sysfs_schemes->nr) + damon_sysfs_update_scheme(scheme, + sysfs_schemes->schemes_arr[i]); + else + damon_destroy_scheme(scheme); + i++; + } + + for (; i < sysfs_schemes->nr; i++) { + struct damos *scheme, *next; + + scheme = damon_sysfs_mk_scheme(sysfs_schemes->schemes_arr[i]); + if (!scheme) { + damon_for_each_scheme_safe(scheme, next, ctx) + damon_destroy_scheme(scheme); + return -ENOMEM; + } + damon_add_scheme(ctx, scheme); + } + return 0; +} + +void damon_sysfs_schemes_update_stats( + struct damon_sysfs_schemes *sysfs_schemes, + struct damon_ctx *ctx) +{ + struct damos *scheme; + int schemes_idx = 0; + + damon_for_each_scheme(scheme, ctx) { + struct damon_sysfs_stats *sysfs_stats; + + /* user could have removed the scheme sysfs dir */ + if (schemes_idx >= sysfs_schemes->nr) + break; + + sysfs_stats = sysfs_schemes->schemes_arr[schemes_idx++]->stats; + sysfs_stats->nr_tried = scheme->stat.nr_tried; + sysfs_stats->sz_tried = scheme->stat.sz_tried; + sysfs_stats->nr_applied = scheme->stat.nr_applied; + sysfs_stats->sz_applied = scheme->stat.sz_applied; + sysfs_stats->qt_exceeds = scheme->stat.qt_exceeds; + } +} + +/* + * damon_sysfs_schemes that need to update its schemes regions dir. Protected + * by damon_sysfs_lock + */ +static struct damon_sysfs_schemes *damon_sysfs_schemes_for_damos_callback; +static int damon_sysfs_schemes_region_idx; + +/* + * DAMON callback that called before damos apply. While this callback is + * registered, damon_sysfs_lock should be held to ensure the regions + * directories exist. + */ +static int damon_sysfs_before_damos_apply(struct damon_ctx *ctx, + struct damon_target *t, struct damon_region *r, + struct damos *s) +{ + struct damos *scheme; + struct damon_sysfs_scheme_regions *sysfs_regions; + struct damon_sysfs_scheme_region *region; + struct damon_sysfs_schemes *sysfs_schemes = + damon_sysfs_schemes_for_damos_callback; + int schemes_idx = 0; + + damon_for_each_scheme(scheme, ctx) { + if (scheme == s) + break; + schemes_idx++; + } + + /* user could have removed the scheme sysfs dir */ + if (schemes_idx >= sysfs_schemes->nr) + return 0; + + sysfs_regions = sysfs_schemes->schemes_arr[schemes_idx]->tried_regions; + region = damon_sysfs_scheme_region_alloc(r); + list_add_tail(®ion->list, &sysfs_regions->regions_list); + sysfs_regions->nr_regions++; + if (kobject_init_and_add(®ion->kobj, + &damon_sysfs_scheme_region_ktype, + &sysfs_regions->kobj, "%d", + damon_sysfs_schemes_region_idx++)) { + kobject_put(®ion->kobj); + } + return 0; +} + +/* Called from damon_sysfs_cmd_request_callback under damon_sysfs_lock */ +int damon_sysfs_schemes_clear_regions( + struct damon_sysfs_schemes *sysfs_schemes, + struct damon_ctx *ctx) +{ + struct damos *scheme; + int schemes_idx = 0; + + damon_for_each_scheme(scheme, ctx) { + struct damon_sysfs_scheme *sysfs_scheme; + + /* user could have removed the scheme sysfs dir */ + if (schemes_idx >= sysfs_schemes->nr) + break; + + sysfs_scheme = sysfs_schemes->schemes_arr[schemes_idx++]; + damon_sysfs_scheme_regions_rm_dirs( + sysfs_scheme->tried_regions); + } + return 0; +} + +/* Called from damon_sysfs_cmd_request_callback under damon_sysfs_lock */ +int damon_sysfs_schemes_update_regions_start( + struct damon_sysfs_schemes *sysfs_schemes, + struct damon_ctx *ctx) +{ + damon_sysfs_schemes_clear_regions(sysfs_schemes, ctx); + damon_sysfs_schemes_for_damos_callback = sysfs_schemes; + ctx->callback.before_damos_apply = damon_sysfs_before_damos_apply; + return 0; +} + +/* + * Called from damon_sysfs_cmd_request_callback under damon_sysfs_lock. Caller + * should unlock damon_sysfs_lock which held before + * damon_sysfs_schemes_update_regions_start() + */ +int damon_sysfs_schemes_update_regions_stop(struct damon_ctx *ctx) +{ + damon_sysfs_schemes_for_damos_callback = NULL; + ctx->callback.before_damos_apply = NULL; + damon_sysfs_schemes_region_idx = 0; + return 0; +} diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c new file mode 100644 index 0000000000000000000000000000000000000000..aeb0beb1da913a350c94749c00fa5d1066e5e10e --- /dev/null +++ b/mm/damon/sysfs.c @@ -0,0 +1,1795 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DAMON sysfs Interface + * + * Copyright (c) 2022 SeongJae Park + */ + +#include +#include +#include + +#include "sysfs-common.h" + +/* + * init region directory + */ + +struct damon_sysfs_region { + struct kobject kobj; + struct damon_addr_range ar; +}; + +static struct damon_sysfs_region *damon_sysfs_region_alloc(void) +{ + return kzalloc(sizeof(struct damon_sysfs_region), GFP_KERNEL); +} + +static ssize_t start_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct damon_sysfs_region *region = container_of(kobj, + struct damon_sysfs_region, kobj); + + return sysfs_emit(buf, "%lu\n", region->ar.start); +} + +static ssize_t start_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct damon_sysfs_region *region = container_of(kobj, + struct damon_sysfs_region, kobj); + int err = kstrtoul(buf, 0, ®ion->ar.start); + + return err ? err : count; +} + +static ssize_t end_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct damon_sysfs_region *region = container_of(kobj, + struct damon_sysfs_region, kobj); + + return sysfs_emit(buf, "%lu\n", region->ar.end); +} + +static ssize_t end_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct damon_sysfs_region *region = container_of(kobj, + struct damon_sysfs_region, kobj); + int err = kstrtoul(buf, 0, ®ion->ar.end); + + return err ? err : count; +} + +static void damon_sysfs_region_release(struct kobject *kobj) +{ + kfree(container_of(kobj, struct damon_sysfs_region, kobj)); +} + +static struct kobj_attribute damon_sysfs_region_start_attr = + __ATTR_RW_MODE(start, 0600); + +static struct kobj_attribute damon_sysfs_region_end_attr = + __ATTR_RW_MODE(end, 0600); + +static struct attribute *damon_sysfs_region_attrs[] = { + &damon_sysfs_region_start_attr.attr, + &damon_sysfs_region_end_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(damon_sysfs_region); + +static struct kobj_type damon_sysfs_region_ktype = { + .release = damon_sysfs_region_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damon_sysfs_region_groups, +}; + +/* + * init_regions directory + */ + +struct damon_sysfs_regions { + struct kobject kobj; + struct damon_sysfs_region **regions_arr; + int nr; +}; + +static struct damon_sysfs_regions *damon_sysfs_regions_alloc(void) +{ + return kzalloc(sizeof(struct damon_sysfs_regions), GFP_KERNEL); +} + +static void damon_sysfs_regions_rm_dirs(struct damon_sysfs_regions *regions) +{ + struct damon_sysfs_region **regions_arr = regions->regions_arr; + int i; + + for (i = 0; i < regions->nr; i++) + kobject_put(®ions_arr[i]->kobj); + regions->nr = 0; + kfree(regions_arr); + regions->regions_arr = NULL; +} + +static int damon_sysfs_regions_add_dirs(struct damon_sysfs_regions *regions, + int nr_regions) +{ + struct damon_sysfs_region **regions_arr, *region; + int err, i; + + damon_sysfs_regions_rm_dirs(regions); + if (!nr_regions) + return 0; + + regions_arr = kmalloc_array(nr_regions, sizeof(*regions_arr), + GFP_KERNEL | __GFP_NOWARN); + if (!regions_arr) + return -ENOMEM; + regions->regions_arr = regions_arr; + + for (i = 0; i < nr_regions; i++) { + region = damon_sysfs_region_alloc(); + if (!region) { + damon_sysfs_regions_rm_dirs(regions); + return -ENOMEM; + } + + err = kobject_init_and_add(®ion->kobj, + &damon_sysfs_region_ktype, ®ions->kobj, + "%d", i); + if (err) { + kobject_put(®ion->kobj); + damon_sysfs_regions_rm_dirs(regions); + return err; + } + + regions_arr[i] = region; + regions->nr++; + } + return 0; +} + +static ssize_t nr_regions_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_regions *regions = container_of(kobj, + struct damon_sysfs_regions, kobj); + + return sysfs_emit(buf, "%d\n", regions->nr); +} + +static ssize_t nr_regions_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damon_sysfs_regions *regions; + int nr, err = kstrtoint(buf, 0, &nr); + + if (err) + return err; + if (nr < 0) + return -EINVAL; + + regions = container_of(kobj, struct damon_sysfs_regions, kobj); + + if (!mutex_trylock(&damon_sysfs_lock)) + return -EBUSY; + err = damon_sysfs_regions_add_dirs(regions, nr); + mutex_unlock(&damon_sysfs_lock); + if (err) + return err; + + return count; +} + +static void damon_sysfs_regions_release(struct kobject *kobj) +{ + kfree(container_of(kobj, struct damon_sysfs_regions, kobj)); +} + +static struct kobj_attribute damon_sysfs_regions_nr_attr = + __ATTR_RW_MODE(nr_regions, 0600); + +static struct attribute *damon_sysfs_regions_attrs[] = { + &damon_sysfs_regions_nr_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(damon_sysfs_regions); + +static struct kobj_type damon_sysfs_regions_ktype = { + .release = damon_sysfs_regions_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damon_sysfs_regions_groups, +}; + +/* + * target directory + */ + +struct damon_sysfs_target { + struct kobject kobj; + struct damon_sysfs_regions *regions; + int pid; +}; + +static struct damon_sysfs_target *damon_sysfs_target_alloc(void) +{ + return kzalloc(sizeof(struct damon_sysfs_target), GFP_KERNEL); +} + +static int damon_sysfs_target_add_dirs(struct damon_sysfs_target *target) +{ + struct damon_sysfs_regions *regions = damon_sysfs_regions_alloc(); + int err; + + if (!regions) + return -ENOMEM; + + err = kobject_init_and_add(®ions->kobj, &damon_sysfs_regions_ktype, + &target->kobj, "regions"); + if (err) + kobject_put(®ions->kobj); + else + target->regions = regions; + return err; +} + +static void damon_sysfs_target_rm_dirs(struct damon_sysfs_target *target) +{ + damon_sysfs_regions_rm_dirs(target->regions); + kobject_put(&target->regions->kobj); +} + +static ssize_t pid_target_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_target *target = container_of(kobj, + struct damon_sysfs_target, kobj); + + return sysfs_emit(buf, "%d\n", target->pid); +} + +static ssize_t pid_target_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damon_sysfs_target *target = container_of(kobj, + struct damon_sysfs_target, kobj); + int err = kstrtoint(buf, 0, &target->pid); + + if (err) + return -EINVAL; + return count; +} + +static void damon_sysfs_target_release(struct kobject *kobj) +{ + kfree(container_of(kobj, struct damon_sysfs_target, kobj)); +} + +static struct kobj_attribute damon_sysfs_target_pid_attr = + __ATTR_RW_MODE(pid_target, 0600); + +static struct attribute *damon_sysfs_target_attrs[] = { + &damon_sysfs_target_pid_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(damon_sysfs_target); + +static struct kobj_type damon_sysfs_target_ktype = { + .release = damon_sysfs_target_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damon_sysfs_target_groups, +}; + +/* + * targets directory + */ + +struct damon_sysfs_targets { + struct kobject kobj; + struct damon_sysfs_target **targets_arr; + int nr; +}; + +static struct damon_sysfs_targets *damon_sysfs_targets_alloc(void) +{ + return kzalloc(sizeof(struct damon_sysfs_targets), GFP_KERNEL); +} + +static void damon_sysfs_targets_rm_dirs(struct damon_sysfs_targets *targets) +{ + struct damon_sysfs_target **targets_arr = targets->targets_arr; + int i; + + for (i = 0; i < targets->nr; i++) { + damon_sysfs_target_rm_dirs(targets_arr[i]); + kobject_put(&targets_arr[i]->kobj); + } + targets->nr = 0; + kfree(targets_arr); + targets->targets_arr = NULL; +} + +static int damon_sysfs_targets_add_dirs(struct damon_sysfs_targets *targets, + int nr_targets) +{ + struct damon_sysfs_target **targets_arr, *target; + int err, i; + + damon_sysfs_targets_rm_dirs(targets); + if (!nr_targets) + return 0; + + targets_arr = kmalloc_array(nr_targets, sizeof(*targets_arr), + GFP_KERNEL | __GFP_NOWARN); + if (!targets_arr) + return -ENOMEM; + targets->targets_arr = targets_arr; + + for (i = 0; i < nr_targets; i++) { + target = damon_sysfs_target_alloc(); + if (!target) { + damon_sysfs_targets_rm_dirs(targets); + return -ENOMEM; + } + + err = kobject_init_and_add(&target->kobj, + &damon_sysfs_target_ktype, &targets->kobj, + "%d", i); + if (err) + goto out; + + err = damon_sysfs_target_add_dirs(target); + if (err) + goto out; + + targets_arr[i] = target; + targets->nr++; + } + return 0; + +out: + damon_sysfs_targets_rm_dirs(targets); + kobject_put(&target->kobj); + return err; +} + +static ssize_t nr_targets_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_targets *targets = container_of(kobj, + struct damon_sysfs_targets, kobj); + + return sysfs_emit(buf, "%d\n", targets->nr); +} + +static ssize_t nr_targets_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damon_sysfs_targets *targets; + int nr, err = kstrtoint(buf, 0, &nr); + + if (err) + return err; + if (nr < 0) + return -EINVAL; + + targets = container_of(kobj, struct damon_sysfs_targets, kobj); + + if (!mutex_trylock(&damon_sysfs_lock)) + return -EBUSY; + err = damon_sysfs_targets_add_dirs(targets, nr); + mutex_unlock(&damon_sysfs_lock); + if (err) + return err; + + return count; +} + +static void damon_sysfs_targets_release(struct kobject *kobj) +{ + kfree(container_of(kobj, struct damon_sysfs_targets, kobj)); +} + +static struct kobj_attribute damon_sysfs_targets_nr_attr = + __ATTR_RW_MODE(nr_targets, 0600); + +static struct attribute *damon_sysfs_targets_attrs[] = { + &damon_sysfs_targets_nr_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(damon_sysfs_targets); + +static struct kobj_type damon_sysfs_targets_ktype = { + .release = damon_sysfs_targets_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damon_sysfs_targets_groups, +}; + +/* + * intervals directory + */ + +struct damon_sysfs_intervals { + struct kobject kobj; + unsigned long sample_us; + unsigned long aggr_us; + unsigned long update_us; +}; + +static struct damon_sysfs_intervals *damon_sysfs_intervals_alloc( + unsigned long sample_us, unsigned long aggr_us, + unsigned long update_us) +{ + struct damon_sysfs_intervals *intervals = kmalloc(sizeof(*intervals), + GFP_KERNEL); + + if (!intervals) + return NULL; + + intervals->kobj = (struct kobject){}; + intervals->sample_us = sample_us; + intervals->aggr_us = aggr_us; + intervals->update_us = update_us; + return intervals; +} + +static ssize_t sample_us_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_intervals *intervals = container_of(kobj, + struct damon_sysfs_intervals, kobj); + + return sysfs_emit(buf, "%lu\n", intervals->sample_us); +} + +static ssize_t sample_us_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damon_sysfs_intervals *intervals = container_of(kobj, + struct damon_sysfs_intervals, kobj); + unsigned long us; + int err = kstrtoul(buf, 0, &us); + + if (err) + return err; + + intervals->sample_us = us; + return count; +} + +static ssize_t aggr_us_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct damon_sysfs_intervals *intervals = container_of(kobj, + struct damon_sysfs_intervals, kobj); + + return sysfs_emit(buf, "%lu\n", intervals->aggr_us); +} + +static ssize_t aggr_us_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct damon_sysfs_intervals *intervals = container_of(kobj, + struct damon_sysfs_intervals, kobj); + unsigned long us; + int err = kstrtoul(buf, 0, &us); + + if (err) + return err; + + intervals->aggr_us = us; + return count; +} + +static ssize_t update_us_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_intervals *intervals = container_of(kobj, + struct damon_sysfs_intervals, kobj); + + return sysfs_emit(buf, "%lu\n", intervals->update_us); +} + +static ssize_t update_us_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damon_sysfs_intervals *intervals = container_of(kobj, + struct damon_sysfs_intervals, kobj); + unsigned long us; + int err = kstrtoul(buf, 0, &us); + + if (err) + return err; + + intervals->update_us = us; + return count; +} + +static void damon_sysfs_intervals_release(struct kobject *kobj) +{ + kfree(container_of(kobj, struct damon_sysfs_intervals, kobj)); +} + +static struct kobj_attribute damon_sysfs_intervals_sample_us_attr = + __ATTR_RW_MODE(sample_us, 0600); + +static struct kobj_attribute damon_sysfs_intervals_aggr_us_attr = + __ATTR_RW_MODE(aggr_us, 0600); + +static struct kobj_attribute damon_sysfs_intervals_update_us_attr = + __ATTR_RW_MODE(update_us, 0600); + +static struct attribute *damon_sysfs_intervals_attrs[] = { + &damon_sysfs_intervals_sample_us_attr.attr, + &damon_sysfs_intervals_aggr_us_attr.attr, + &damon_sysfs_intervals_update_us_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(damon_sysfs_intervals); + +static struct kobj_type damon_sysfs_intervals_ktype = { + .release = damon_sysfs_intervals_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damon_sysfs_intervals_groups, +}; + +/* + * monitoring_attrs directory + */ + +struct damon_sysfs_attrs { + struct kobject kobj; + struct damon_sysfs_intervals *intervals; + struct damon_sysfs_ul_range *nr_regions_range; +}; + +static struct damon_sysfs_attrs *damon_sysfs_attrs_alloc(void) +{ + struct damon_sysfs_attrs *attrs = kmalloc(sizeof(*attrs), GFP_KERNEL); + + if (!attrs) + return NULL; + attrs->kobj = (struct kobject){}; + return attrs; +} + +static int damon_sysfs_attrs_add_dirs(struct damon_sysfs_attrs *attrs) +{ + struct damon_sysfs_intervals *intervals; + struct damon_sysfs_ul_range *nr_regions_range; + int err; + + intervals = damon_sysfs_intervals_alloc(5000, 100000, 60000000); + if (!intervals) + return -ENOMEM; + + err = kobject_init_and_add(&intervals->kobj, + &damon_sysfs_intervals_ktype, &attrs->kobj, + "intervals"); + if (err) + goto put_intervals_out; + attrs->intervals = intervals; + + nr_regions_range = damon_sysfs_ul_range_alloc(10, 1000); + if (!nr_regions_range) { + err = -ENOMEM; + goto put_intervals_out; + } + + err = kobject_init_and_add(&nr_regions_range->kobj, + &damon_sysfs_ul_range_ktype, &attrs->kobj, + "nr_regions"); + if (err) + goto put_nr_regions_intervals_out; + attrs->nr_regions_range = nr_regions_range; + return 0; + +put_nr_regions_intervals_out: + kobject_put(&nr_regions_range->kobj); + attrs->nr_regions_range = NULL; +put_intervals_out: + kobject_put(&intervals->kobj); + attrs->intervals = NULL; + return err; +} + +static void damon_sysfs_attrs_rm_dirs(struct damon_sysfs_attrs *attrs) +{ + kobject_put(&attrs->nr_regions_range->kobj); + kobject_put(&attrs->intervals->kobj); +} + +static void damon_sysfs_attrs_release(struct kobject *kobj) +{ + kfree(container_of(kobj, struct damon_sysfs_attrs, kobj)); +} + +static struct attribute *damon_sysfs_attrs_attrs[] = { + NULL, +}; +ATTRIBUTE_GROUPS(damon_sysfs_attrs); + +static struct kobj_type damon_sysfs_attrs_ktype = { + .release = damon_sysfs_attrs_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damon_sysfs_attrs_groups, +}; + +/* + * context directory + */ + +/* This should match with enum damon_ops_id */ +static const char * const damon_sysfs_ops_strs[] = { + "vaddr", + "fvaddr", + "paddr", +}; + +struct damon_sysfs_context { + struct kobject kobj; + enum damon_ops_id ops_id; + struct damon_sysfs_attrs *attrs; + struct damon_sysfs_targets *targets; + struct damon_sysfs_schemes *schemes; +}; + +static struct damon_sysfs_context *damon_sysfs_context_alloc( + enum damon_ops_id ops_id) +{ + struct damon_sysfs_context *context = kmalloc(sizeof(*context), + GFP_KERNEL); + + if (!context) + return NULL; + context->kobj = (struct kobject){}; + context->ops_id = ops_id; + return context; +} + +static int damon_sysfs_context_set_attrs(struct damon_sysfs_context *context) +{ + struct damon_sysfs_attrs *attrs = damon_sysfs_attrs_alloc(); + int err; + + if (!attrs) + return -ENOMEM; + err = kobject_init_and_add(&attrs->kobj, &damon_sysfs_attrs_ktype, + &context->kobj, "monitoring_attrs"); + if (err) + goto out; + err = damon_sysfs_attrs_add_dirs(attrs); + if (err) + goto out; + context->attrs = attrs; + return 0; + +out: + kobject_put(&attrs->kobj); + return err; +} + +static int damon_sysfs_context_set_targets(struct damon_sysfs_context *context) +{ + struct damon_sysfs_targets *targets = damon_sysfs_targets_alloc(); + int err; + + if (!targets) + return -ENOMEM; + err = kobject_init_and_add(&targets->kobj, &damon_sysfs_targets_ktype, + &context->kobj, "targets"); + if (err) { + kobject_put(&targets->kobj); + return err; + } + context->targets = targets; + return 0; +} + +static int damon_sysfs_context_set_schemes(struct damon_sysfs_context *context) +{ + struct damon_sysfs_schemes *schemes = damon_sysfs_schemes_alloc(); + int err; + + if (!schemes) + return -ENOMEM; + err = kobject_init_and_add(&schemes->kobj, &damon_sysfs_schemes_ktype, + &context->kobj, "schemes"); + if (err) { + kobject_put(&schemes->kobj); + return err; + } + context->schemes = schemes; + return 0; +} + +static int damon_sysfs_context_add_dirs(struct damon_sysfs_context *context) +{ + int err; + + err = damon_sysfs_context_set_attrs(context); + if (err) + return err; + + err = damon_sysfs_context_set_targets(context); + if (err) + goto put_attrs_out; + + err = damon_sysfs_context_set_schemes(context); + if (err) + goto put_targets_attrs_out; + return 0; + +put_targets_attrs_out: + kobject_put(&context->targets->kobj); + context->targets = NULL; +put_attrs_out: + kobject_put(&context->attrs->kobj); + context->attrs = NULL; + return err; +} + +static void damon_sysfs_context_rm_dirs(struct damon_sysfs_context *context) +{ + damon_sysfs_attrs_rm_dirs(context->attrs); + kobject_put(&context->attrs->kobj); + damon_sysfs_targets_rm_dirs(context->targets); + kobject_put(&context->targets->kobj); + damon_sysfs_schemes_rm_dirs(context->schemes); + kobject_put(&context->schemes->kobj); +} + +static ssize_t avail_operations_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + enum damon_ops_id id; + int len = 0; + + for (id = 0; id < NR_DAMON_OPS; id++) { + if (!damon_is_registered_ops(id)) + continue; + len += sysfs_emit_at(buf, len, "%s\n", + damon_sysfs_ops_strs[id]); + } + return len; +} + +static ssize_t operations_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_context *context = container_of(kobj, + struct damon_sysfs_context, kobj); + + return sysfs_emit(buf, "%s\n", damon_sysfs_ops_strs[context->ops_id]); +} + +static ssize_t operations_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damon_sysfs_context *context = container_of(kobj, + struct damon_sysfs_context, kobj); + enum damon_ops_id id; + + for (id = 0; id < NR_DAMON_OPS; id++) { + if (sysfs_streq(buf, damon_sysfs_ops_strs[id])) { + context->ops_id = id; + return count; + } + } + return -EINVAL; +} + +static void damon_sysfs_context_release(struct kobject *kobj) +{ + kfree(container_of(kobj, struct damon_sysfs_context, kobj)); +} + +static struct kobj_attribute damon_sysfs_context_avail_operations_attr = + __ATTR_RO_MODE(avail_operations, 0400); + +static struct kobj_attribute damon_sysfs_context_operations_attr = + __ATTR_RW_MODE(operations, 0600); + +static struct attribute *damon_sysfs_context_attrs[] = { + &damon_sysfs_context_avail_operations_attr.attr, + &damon_sysfs_context_operations_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(damon_sysfs_context); + +static struct kobj_type damon_sysfs_context_ktype = { + .release = damon_sysfs_context_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damon_sysfs_context_groups, +}; + +/* + * contexts directory + */ + +struct damon_sysfs_contexts { + struct kobject kobj; + struct damon_sysfs_context **contexts_arr; + int nr; +}; + +static struct damon_sysfs_contexts *damon_sysfs_contexts_alloc(void) +{ + return kzalloc(sizeof(struct damon_sysfs_contexts), GFP_KERNEL); +} + +static void damon_sysfs_contexts_rm_dirs(struct damon_sysfs_contexts *contexts) +{ + struct damon_sysfs_context **contexts_arr = contexts->contexts_arr; + int i; + + for (i = 0; i < contexts->nr; i++) { + damon_sysfs_context_rm_dirs(contexts_arr[i]); + kobject_put(&contexts_arr[i]->kobj); + } + contexts->nr = 0; + kfree(contexts_arr); + contexts->contexts_arr = NULL; +} + +static int damon_sysfs_contexts_add_dirs(struct damon_sysfs_contexts *contexts, + int nr_contexts) +{ + struct damon_sysfs_context **contexts_arr, *context; + int err, i; + + damon_sysfs_contexts_rm_dirs(contexts); + if (!nr_contexts) + return 0; + + contexts_arr = kmalloc_array(nr_contexts, sizeof(*contexts_arr), + GFP_KERNEL | __GFP_NOWARN); + if (!contexts_arr) + return -ENOMEM; + contexts->contexts_arr = contexts_arr; + + for (i = 0; i < nr_contexts; i++) { + context = damon_sysfs_context_alloc(DAMON_OPS_VADDR); + if (!context) { + damon_sysfs_contexts_rm_dirs(contexts); + return -ENOMEM; + } + + err = kobject_init_and_add(&context->kobj, + &damon_sysfs_context_ktype, &contexts->kobj, + "%d", i); + if (err) + goto out; + + err = damon_sysfs_context_add_dirs(context); + if (err) + goto out; + + contexts_arr[i] = context; + contexts->nr++; + } + return 0; + +out: + damon_sysfs_contexts_rm_dirs(contexts); + kobject_put(&context->kobj); + return err; +} + +static ssize_t nr_contexts_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_contexts *contexts = container_of(kobj, + struct damon_sysfs_contexts, kobj); + + return sysfs_emit(buf, "%d\n", contexts->nr); +} + +static ssize_t nr_contexts_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damon_sysfs_contexts *contexts; + int nr, err; + + err = kstrtoint(buf, 0, &nr); + if (err) + return err; + /* TODO: support multiple contexts per kdamond */ + if (nr < 0 || 1 < nr) + return -EINVAL; + + contexts = container_of(kobj, struct damon_sysfs_contexts, kobj); + if (!mutex_trylock(&damon_sysfs_lock)) + return -EBUSY; + err = damon_sysfs_contexts_add_dirs(contexts, nr); + mutex_unlock(&damon_sysfs_lock); + if (err) + return err; + + return count; +} + +static void damon_sysfs_contexts_release(struct kobject *kobj) +{ + kfree(container_of(kobj, struct damon_sysfs_contexts, kobj)); +} + +static struct kobj_attribute damon_sysfs_contexts_nr_attr + = __ATTR_RW_MODE(nr_contexts, 0600); + +static struct attribute *damon_sysfs_contexts_attrs[] = { + &damon_sysfs_contexts_nr_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(damon_sysfs_contexts); + +static struct kobj_type damon_sysfs_contexts_ktype = { + .release = damon_sysfs_contexts_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damon_sysfs_contexts_groups, +}; + +/* + * kdamond directory + */ + +struct damon_sysfs_kdamond { + struct kobject kobj; + struct damon_sysfs_contexts *contexts; + struct damon_ctx *damon_ctx; +}; + +static struct damon_sysfs_kdamond *damon_sysfs_kdamond_alloc(void) +{ + return kzalloc(sizeof(struct damon_sysfs_kdamond), GFP_KERNEL); +} + +static int damon_sysfs_kdamond_add_dirs(struct damon_sysfs_kdamond *kdamond) +{ + struct damon_sysfs_contexts *contexts; + int err; + + contexts = damon_sysfs_contexts_alloc(); + if (!contexts) + return -ENOMEM; + + err = kobject_init_and_add(&contexts->kobj, + &damon_sysfs_contexts_ktype, &kdamond->kobj, + "contexts"); + if (err) { + kobject_put(&contexts->kobj); + return err; + } + kdamond->contexts = contexts; + + return err; +} + +static void damon_sysfs_kdamond_rm_dirs(struct damon_sysfs_kdamond *kdamond) +{ + damon_sysfs_contexts_rm_dirs(kdamond->contexts); + kobject_put(&kdamond->contexts->kobj); +} + +static bool damon_sysfs_ctx_running(struct damon_ctx *ctx) +{ + bool running; + + mutex_lock(&ctx->kdamond_lock); + running = ctx->kdamond != NULL; + mutex_unlock(&ctx->kdamond_lock); + return running; +} + +/* + * enum damon_sysfs_cmd - Commands for a specific kdamond. + */ +enum damon_sysfs_cmd { + /* @DAMON_SYSFS_CMD_ON: Turn the kdamond on. */ + DAMON_SYSFS_CMD_ON, + /* @DAMON_SYSFS_CMD_OFF: Turn the kdamond off. */ + DAMON_SYSFS_CMD_OFF, + /* @DAMON_SYSFS_CMD_COMMIT: Update kdamond inputs. */ + DAMON_SYSFS_CMD_COMMIT, + /* + * @DAMON_SYSFS_CMD_UPDATE_SCHEMES_STATS: Update scheme stats sysfs + * files. + */ + DAMON_SYSFS_CMD_UPDATE_SCHEMES_STATS, + /* + * @DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_REGIONS: Update schemes tried + * regions + */ + DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_REGIONS, + /* + * @DAMON_SYSFS_CMD_CLEAR_SCHEMES_TRIED_REGIONS: Clear schemes tried + * regions + */ + DAMON_SYSFS_CMD_CLEAR_SCHEMES_TRIED_REGIONS, + /* + * @NR_DAMON_SYSFS_CMDS: Total number of DAMON sysfs commands. + */ + NR_DAMON_SYSFS_CMDS, +}; + +/* Should match with enum damon_sysfs_cmd */ +static const char * const damon_sysfs_cmd_strs[] = { + "on", + "off", + "commit", + "update_schemes_stats", + "update_schemes_tried_regions", + "clear_schemes_tried_regions", +}; + +/* + * struct damon_sysfs_cmd_request - A request to the DAMON callback. + * @cmd: The command that needs to be handled by the callback. + * @kdamond: The kobject wrapper that associated to the kdamond thread. + * + * This structure represents a sysfs command request that need to access some + * DAMON context-internal data. Because DAMON context-internal data can be + * safely accessed from DAMON callbacks without additional synchronization, the + * request will be handled by the DAMON callback. None-``NULL`` @kdamond means + * the request is valid. + */ +struct damon_sysfs_cmd_request { + enum damon_sysfs_cmd cmd; + struct damon_sysfs_kdamond *kdamond; +}; + +/* Current DAMON callback request. Protected by damon_sysfs_lock. */ +static struct damon_sysfs_cmd_request damon_sysfs_cmd_request; + +static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct damon_sysfs_kdamond *kdamond = container_of(kobj, + struct damon_sysfs_kdamond, kobj); + struct damon_ctx *ctx = kdamond->damon_ctx; + bool running; + + if (!ctx) + running = false; + else + running = damon_sysfs_ctx_running(ctx); + + return sysfs_emit(buf, "%s\n", running ? + damon_sysfs_cmd_strs[DAMON_SYSFS_CMD_ON] : + damon_sysfs_cmd_strs[DAMON_SYSFS_CMD_OFF]); +} + +static int damon_sysfs_set_attrs(struct damon_ctx *ctx, + struct damon_sysfs_attrs *sys_attrs) +{ + struct damon_sysfs_intervals *sys_intervals = sys_attrs->intervals; + struct damon_sysfs_ul_range *sys_nr_regions = + sys_attrs->nr_regions_range; + struct damon_attrs attrs = { + .sample_interval = sys_intervals->sample_us, + .aggr_interval = sys_intervals->aggr_us, + .ops_update_interval = sys_intervals->update_us, + .min_nr_regions = sys_nr_regions->min, + .max_nr_regions = sys_nr_regions->max, + }; + return damon_set_attrs(ctx, &attrs); +} + +static void damon_sysfs_destroy_targets(struct damon_ctx *ctx) +{ + struct damon_target *t, *next; + bool has_pid = damon_target_has_pid(ctx); + + damon_for_each_target_safe(t, next, ctx) { + if (has_pid) + put_pid(t->pid); + damon_destroy_target(t); + } +} + +static int damon_sysfs_set_regions(struct damon_target *t, + struct damon_sysfs_regions *sysfs_regions) +{ + struct damon_addr_range *ranges = kmalloc_array(sysfs_regions->nr, + sizeof(*ranges), GFP_KERNEL | __GFP_NOWARN); + int i, err = -EINVAL; + + if (!ranges) + return -ENOMEM; + for (i = 0; i < sysfs_regions->nr; i++) { + struct damon_sysfs_region *sys_region = + sysfs_regions->regions_arr[i]; + + if (sys_region->ar.start > sys_region->ar.end) + goto out; + + ranges[i].start = sys_region->ar.start; + ranges[i].end = sys_region->ar.end; + if (i == 0) + continue; + if (ranges[i - 1].end > ranges[i].start) + goto out; + } + err = damon_set_regions(t, ranges, sysfs_regions->nr); +out: + kfree(ranges); + return err; + +} + +static int damon_sysfs_add_target(struct damon_sysfs_target *sys_target, + struct damon_ctx *ctx) +{ + struct damon_target *t = damon_new_target(); + int err = -EINVAL; + + if (!t) + return -ENOMEM; + damon_add_target(ctx, t); + if (damon_target_has_pid(ctx)) { + t->pid = find_get_pid(sys_target->pid); + if (!t->pid) + goto destroy_targets_out; + } + err = damon_sysfs_set_regions(t, sys_target->regions); + if (err) + goto destroy_targets_out; + return 0; + +destroy_targets_out: + damon_sysfs_destroy_targets(ctx); + return err; +} + +/* + * Search a target in a context that corresponds to the sysfs target input. + * + * Return: pointer to the target if found, NULL if not found, or negative + * error code if the search failed. + */ +static struct damon_target *damon_sysfs_existing_target( + struct damon_sysfs_target *sys_target, struct damon_ctx *ctx) +{ + struct pid *pid; + struct damon_target *t; + + if (!damon_target_has_pid(ctx)) { + /* Up to only one target for paddr could exist */ + damon_for_each_target(t, ctx) + return t; + return NULL; + } + + /* ops.id should be DAMON_OPS_VADDR or DAMON_OPS_FVADDR */ + pid = find_get_pid(sys_target->pid); + if (!pid) + return ERR_PTR(-EINVAL); + damon_for_each_target(t, ctx) { + if (t->pid == pid) { + put_pid(pid); + return t; + } + } + put_pid(pid); + return NULL; +} + +static int damon_sysfs_set_targets(struct damon_ctx *ctx, + struct damon_sysfs_targets *sysfs_targets) +{ + int i, err; + + /* Multiple physical address space monitoring targets makes no sense */ + if (ctx->ops.id == DAMON_OPS_PADDR && sysfs_targets->nr > 1) + return -EINVAL; + + for (i = 0; i < sysfs_targets->nr; i++) { + struct damon_sysfs_target *st = sysfs_targets->targets_arr[i]; + struct damon_target *t = damon_sysfs_existing_target(st, ctx); + + if (IS_ERR(t)) + return PTR_ERR(t); + if (!t) + err = damon_sysfs_add_target(st, ctx); + else + err = damon_sysfs_set_regions(t, st->regions); + if (err) + return err; + } + return 0; +} + +static void damon_sysfs_before_terminate(struct damon_ctx *ctx) +{ + struct damon_target *t, *next; + struct damon_sysfs_kdamond *kdamond; + + /* damon_sysfs_schemes_update_regions_stop() might not yet called */ + kdamond = damon_sysfs_cmd_request.kdamond; + if (kdamond && damon_sysfs_cmd_request.cmd == + DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_REGIONS && + ctx == kdamond->damon_ctx) { + damon_sysfs_schemes_update_regions_stop(ctx); + mutex_unlock(&damon_sysfs_lock); + } + + if (!damon_target_has_pid(ctx)) + return; + + mutex_lock(&ctx->kdamond_lock); + damon_for_each_target_safe(t, next, ctx) { + put_pid(t->pid); + damon_destroy_target(t); + } + mutex_unlock(&ctx->kdamond_lock); +} + +/* + * damon_sysfs_upd_schemes_stats() - Update schemes stats sysfs files. + * @kdamond: The kobject wrapper that associated to the kdamond thread. + * + * This function reads the schemes stats of specific kdamond and update the + * related values for sysfs files. This function should be called from DAMON + * callbacks while holding ``damon_syfs_lock``, to safely access the DAMON + * contexts-internal data and DAMON sysfs variables. + */ +static int damon_sysfs_upd_schemes_stats(struct damon_sysfs_kdamond *kdamond) +{ + struct damon_ctx *ctx = kdamond->damon_ctx; + + if (!ctx) + return -EINVAL; + damon_sysfs_schemes_update_stats( + kdamond->contexts->contexts_arr[0]->schemes, ctx); + return 0; +} + +static int damon_sysfs_upd_schemes_regions_start( + struct damon_sysfs_kdamond *kdamond) +{ + struct damon_ctx *ctx = kdamond->damon_ctx; + + if (!ctx) + return -EINVAL; + return damon_sysfs_schemes_update_regions_start( + kdamond->contexts->contexts_arr[0]->schemes, ctx); +} + +static int damon_sysfs_upd_schemes_regions_stop( + struct damon_sysfs_kdamond *kdamond) +{ + struct damon_ctx *ctx = kdamond->damon_ctx; + + if (!ctx) + return -EINVAL; + return damon_sysfs_schemes_update_regions_stop(ctx); +} + +static int damon_sysfs_clear_schemes_regions( + struct damon_sysfs_kdamond *kdamond) +{ + struct damon_ctx *ctx = kdamond->damon_ctx; + + if (!ctx) + return -EINVAL; + return damon_sysfs_schemes_clear_regions( + kdamond->contexts->contexts_arr[0]->schemes, ctx); +} + +static inline bool damon_sysfs_kdamond_running( + struct damon_sysfs_kdamond *kdamond) +{ + return kdamond->damon_ctx && + 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. + * + * If the sysfs input is wrong, the kdamond will be terminated. + */ +static int damon_sysfs_commit_input(struct damon_sysfs_kdamond *kdamond) +{ + if (!damon_sysfs_kdamond_running(kdamond)) + return -EINVAL; + /* TODO: Support multiple contexts per kdamond */ + if (kdamond->contexts->nr != 1) + return -EINVAL; + + return damon_sysfs_apply_inputs(kdamond->damon_ctx, + kdamond->contexts->contexts_arr[0]); +} + +/* + * damon_sysfs_cmd_request_callback() - DAMON callback for handling requests. + * @c: The DAMON context of the callback. + * + * This function is periodically called back from the kdamond thread for @c. + * Then, it checks if there is a waiting DAMON sysfs request and handles it. + */ +static int damon_sysfs_cmd_request_callback(struct damon_ctx *c) +{ + struct damon_sysfs_kdamond *kdamond; + static bool damon_sysfs_schemes_regions_updating; + int err = 0; + + /* avoid deadlock due to concurrent state_store('off') */ + if (!damon_sysfs_schemes_regions_updating && + !mutex_trylock(&damon_sysfs_lock)) + return 0; + kdamond = damon_sysfs_cmd_request.kdamond; + if (!kdamond || kdamond->damon_ctx != c) + goto out; + switch (damon_sysfs_cmd_request.cmd) { + case DAMON_SYSFS_CMD_UPDATE_SCHEMES_STATS: + err = damon_sysfs_upd_schemes_stats(kdamond); + break; + case DAMON_SYSFS_CMD_COMMIT: + err = damon_sysfs_commit_input(kdamond); + break; + case DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_REGIONS: + if (!damon_sysfs_schemes_regions_updating) { + err = damon_sysfs_upd_schemes_regions_start(kdamond); + if (!err) { + damon_sysfs_schemes_regions_updating = true; + goto keep_lock_out; + } + } else { + err = damon_sysfs_upd_schemes_regions_stop(kdamond); + damon_sysfs_schemes_regions_updating = false; + } + break; + case DAMON_SYSFS_CMD_CLEAR_SCHEMES_TRIED_REGIONS: + err = damon_sysfs_clear_schemes_regions(kdamond); + break; + default: + break; + } + /* Mark the request as invalid now. */ + damon_sysfs_cmd_request.kdamond = NULL; +out: + if (!damon_sysfs_schemes_regions_updating) + mutex_unlock(&damon_sysfs_lock); +keep_lock_out: + return err; +} + +static struct damon_ctx *damon_sysfs_build_ctx( + struct damon_sysfs_context *sys_ctx) +{ + struct damon_ctx *ctx = damon_new_ctx(); + int err; + + if (!ctx) + return ERR_PTR(-ENOMEM); + + 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; +} + +static int damon_sysfs_turn_damon_on(struct damon_sysfs_kdamond *kdamond) +{ + struct damon_ctx *ctx; + int err; + + if (damon_sysfs_kdamond_running(kdamond)) + return -EBUSY; + if (damon_sysfs_cmd_request.kdamond == kdamond) + return -EBUSY; + /* TODO: support multiple contexts per kdamond */ + if (kdamond->contexts->nr != 1) + return -EINVAL; + + if (kdamond->damon_ctx) + damon_destroy_ctx(kdamond->damon_ctx); + kdamond->damon_ctx = NULL; + + ctx = damon_sysfs_build_ctx(kdamond->contexts->contexts_arr[0]); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + err = damon_start(&ctx, 1, false); + if (err) { + damon_destroy_ctx(ctx); + return err; + } + kdamond->damon_ctx = ctx; + return err; +} + +static int damon_sysfs_turn_damon_off(struct damon_sysfs_kdamond *kdamond) +{ + if (!kdamond->damon_ctx) + return -EINVAL; + return damon_stop(&kdamond->damon_ctx, 1); + /* + * To allow users show final monitoring results of already turned-off + * DAMON, we free kdamond->damon_ctx in next + * damon_sysfs_turn_damon_on(), or kdamonds_nr_store() + */ +} + +/* + * damon_sysfs_handle_cmd() - Handle a command for a specific kdamond. + * @cmd: The command to handle. + * @kdamond: The kobject wrapper for the associated kdamond. + * + * This function handles a DAMON sysfs command for a kdamond. For commands + * that need to access running DAMON context-internal data, it requests + * handling of the command to the DAMON callback + * (@damon_sysfs_cmd_request_callback()) and wait until it is properly handled, + * or the context is completed. + * + * Return: 0 on success, negative error code otherwise. + */ +static int damon_sysfs_handle_cmd(enum damon_sysfs_cmd cmd, + struct damon_sysfs_kdamond *kdamond) +{ + bool need_wait = true; + + /* Handle commands that doesn't access DAMON context-internal data */ + switch (cmd) { + case DAMON_SYSFS_CMD_ON: + return damon_sysfs_turn_damon_on(kdamond); + case DAMON_SYSFS_CMD_OFF: + return damon_sysfs_turn_damon_off(kdamond); + default: + break; + } + + /* Pass the command to DAMON callback for safe DAMON context access */ + if (damon_sysfs_cmd_request.kdamond) + return -EBUSY; + if (!damon_sysfs_kdamond_running(kdamond)) + return -EINVAL; + damon_sysfs_cmd_request.cmd = cmd; + damon_sysfs_cmd_request.kdamond = kdamond; + + /* + * wait until damon_sysfs_cmd_request_callback() handles the request + * from kdamond context + */ + mutex_unlock(&damon_sysfs_lock); + while (need_wait) { + schedule_timeout_idle(msecs_to_jiffies(100)); + if (!mutex_trylock(&damon_sysfs_lock)) + continue; + if (!damon_sysfs_cmd_request.kdamond) { + /* damon_sysfs_cmd_request_callback() handled */ + need_wait = false; + } else if (!damon_sysfs_kdamond_running(kdamond)) { + /* kdamond has already finished */ + need_wait = false; + damon_sysfs_cmd_request.kdamond = NULL; + } + mutex_unlock(&damon_sysfs_lock); + } + mutex_lock(&damon_sysfs_lock); + return 0; +} + +static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct damon_sysfs_kdamond *kdamond = container_of(kobj, + struct damon_sysfs_kdamond, kobj); + enum damon_sysfs_cmd cmd; + ssize_t ret = -EINVAL; + + if (!mutex_trylock(&damon_sysfs_lock)) + return -EBUSY; + for (cmd = 0; cmd < NR_DAMON_SYSFS_CMDS; cmd++) { + if (sysfs_streq(buf, damon_sysfs_cmd_strs[cmd])) { + ret = damon_sysfs_handle_cmd(cmd, kdamond); + break; + } + } + mutex_unlock(&damon_sysfs_lock); + if (!ret) + ret = count; + return ret; +} + +static ssize_t pid_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_kdamond *kdamond = container_of(kobj, + struct damon_sysfs_kdamond, kobj); + struct damon_ctx *ctx; + int pid = -1; + + if (!mutex_trylock(&damon_sysfs_lock)) + return -EBUSY; + ctx = kdamond->damon_ctx; + if (!ctx) + goto out; + + mutex_lock(&ctx->kdamond_lock); + if (ctx->kdamond) + pid = ctx->kdamond->pid; + mutex_unlock(&ctx->kdamond_lock); +out: + mutex_unlock(&damon_sysfs_lock); + return sysfs_emit(buf, "%d\n", pid); +} + +static void damon_sysfs_kdamond_release(struct kobject *kobj) +{ + struct damon_sysfs_kdamond *kdamond = container_of(kobj, + struct damon_sysfs_kdamond, kobj); + + if (kdamond->damon_ctx) + damon_destroy_ctx(kdamond->damon_ctx); + kfree(kdamond); +} + +static struct kobj_attribute damon_sysfs_kdamond_state_attr = + __ATTR_RW_MODE(state, 0600); + +static struct kobj_attribute damon_sysfs_kdamond_pid_attr = + __ATTR_RO_MODE(pid, 0400); + +static struct attribute *damon_sysfs_kdamond_attrs[] = { + &damon_sysfs_kdamond_state_attr.attr, + &damon_sysfs_kdamond_pid_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(damon_sysfs_kdamond); + +static struct kobj_type damon_sysfs_kdamond_ktype = { + .release = damon_sysfs_kdamond_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damon_sysfs_kdamond_groups, +}; + +/* + * kdamonds directory + */ + +struct damon_sysfs_kdamonds { + struct kobject kobj; + struct damon_sysfs_kdamond **kdamonds_arr; + int nr; +}; + +static struct damon_sysfs_kdamonds *damon_sysfs_kdamonds_alloc(void) +{ + return kzalloc(sizeof(struct damon_sysfs_kdamonds), GFP_KERNEL); +} + +static void damon_sysfs_kdamonds_rm_dirs(struct damon_sysfs_kdamonds *kdamonds) +{ + struct damon_sysfs_kdamond **kdamonds_arr = kdamonds->kdamonds_arr; + int i; + + for (i = 0; i < kdamonds->nr; i++) { + damon_sysfs_kdamond_rm_dirs(kdamonds_arr[i]); + kobject_put(&kdamonds_arr[i]->kobj); + } + kdamonds->nr = 0; + kfree(kdamonds_arr); + kdamonds->kdamonds_arr = NULL; +} + +static bool damon_sysfs_kdamonds_busy(struct damon_sysfs_kdamond **kdamonds, + int nr_kdamonds) +{ + int i; + + for (i = 0; i < nr_kdamonds; i++) { + if (damon_sysfs_kdamond_running(kdamonds[i]) || + damon_sysfs_cmd_request.kdamond == kdamonds[i]) + return true; + } + + return false; +} + +static int damon_sysfs_kdamonds_add_dirs(struct damon_sysfs_kdamonds *kdamonds, + int nr_kdamonds) +{ + struct damon_sysfs_kdamond **kdamonds_arr, *kdamond; + int err, i; + + if (damon_sysfs_kdamonds_busy(kdamonds->kdamonds_arr, kdamonds->nr)) + return -EBUSY; + + damon_sysfs_kdamonds_rm_dirs(kdamonds); + if (!nr_kdamonds) + return 0; + + kdamonds_arr = kmalloc_array(nr_kdamonds, sizeof(*kdamonds_arr), + GFP_KERNEL | __GFP_NOWARN); + if (!kdamonds_arr) + return -ENOMEM; + kdamonds->kdamonds_arr = kdamonds_arr; + + for (i = 0; i < nr_kdamonds; i++) { + kdamond = damon_sysfs_kdamond_alloc(); + if (!kdamond) { + damon_sysfs_kdamonds_rm_dirs(kdamonds); + return -ENOMEM; + } + + err = kobject_init_and_add(&kdamond->kobj, + &damon_sysfs_kdamond_ktype, &kdamonds->kobj, + "%d", i); + if (err) + goto out; + + err = damon_sysfs_kdamond_add_dirs(kdamond); + if (err) + goto out; + + kdamonds_arr[i] = kdamond; + kdamonds->nr++; + } + return 0; + +out: + damon_sysfs_kdamonds_rm_dirs(kdamonds); + kobject_put(&kdamond->kobj); + return err; +} + +static ssize_t nr_kdamonds_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct damon_sysfs_kdamonds *kdamonds = container_of(kobj, + struct damon_sysfs_kdamonds, kobj); + + return sysfs_emit(buf, "%d\n", kdamonds->nr); +} + +static ssize_t nr_kdamonds_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + struct damon_sysfs_kdamonds *kdamonds; + int nr, err; + + err = kstrtoint(buf, 0, &nr); + if (err) + return err; + if (nr < 0) + return -EINVAL; + + kdamonds = container_of(kobj, struct damon_sysfs_kdamonds, kobj); + + if (!mutex_trylock(&damon_sysfs_lock)) + return -EBUSY; + err = damon_sysfs_kdamonds_add_dirs(kdamonds, nr); + mutex_unlock(&damon_sysfs_lock); + if (err) + return err; + + return count; +} + +static void damon_sysfs_kdamonds_release(struct kobject *kobj) +{ + kfree(container_of(kobj, struct damon_sysfs_kdamonds, kobj)); +} + +static struct kobj_attribute damon_sysfs_kdamonds_nr_attr = + __ATTR_RW_MODE(nr_kdamonds, 0600); + +static struct attribute *damon_sysfs_kdamonds_attrs[] = { + &damon_sysfs_kdamonds_nr_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(damon_sysfs_kdamonds); + +static struct kobj_type damon_sysfs_kdamonds_ktype = { + .release = damon_sysfs_kdamonds_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damon_sysfs_kdamonds_groups, +}; + +/* + * damon user interface directory + */ + +struct damon_sysfs_ui_dir { + struct kobject kobj; + struct damon_sysfs_kdamonds *kdamonds; +}; + +static struct damon_sysfs_ui_dir *damon_sysfs_ui_dir_alloc(void) +{ + return kzalloc(sizeof(struct damon_sysfs_ui_dir), GFP_KERNEL); +} + +static int damon_sysfs_ui_dir_add_dirs(struct damon_sysfs_ui_dir *ui_dir) +{ + struct damon_sysfs_kdamonds *kdamonds; + int err; + + kdamonds = damon_sysfs_kdamonds_alloc(); + if (!kdamonds) + return -ENOMEM; + + err = kobject_init_and_add(&kdamonds->kobj, + &damon_sysfs_kdamonds_ktype, &ui_dir->kobj, + "kdamonds"); + if (err) { + kobject_put(&kdamonds->kobj); + return err; + } + ui_dir->kdamonds = kdamonds; + return err; +} + +static void damon_sysfs_ui_dir_release(struct kobject *kobj) +{ + kfree(container_of(kobj, struct damon_sysfs_ui_dir, kobj)); +} + +static struct attribute *damon_sysfs_ui_dir_attrs[] = { + NULL, +}; +ATTRIBUTE_GROUPS(damon_sysfs_ui_dir); + +static struct kobj_type damon_sysfs_ui_dir_ktype = { + .release = damon_sysfs_ui_dir_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = damon_sysfs_ui_dir_groups, +}; + +static int __init damon_sysfs_init(void) +{ + struct kobject *damon_sysfs_root; + struct damon_sysfs_ui_dir *admin; + int err; + + damon_sysfs_root = kobject_create_and_add("damon", mm_kobj); + if (!damon_sysfs_root) + return -ENOMEM; + + admin = damon_sysfs_ui_dir_alloc(); + if (!admin) { + kobject_put(damon_sysfs_root); + return -ENOMEM; + } + err = kobject_init_and_add(&admin->kobj, &damon_sysfs_ui_dir_ktype, + damon_sysfs_root, "admin"); + if (err) + goto out; + err = damon_sysfs_ui_dir_add_dirs(admin); + if (err) + goto out; + return 0; + +out: + kobject_put(&admin->kobj); + kobject_put(damon_sysfs_root); + return err; +} +subsys_initcall(damon_sysfs_init); diff --git a/mm/damon/vaddr-test.h b/mm/damon/vaddr-test.h index 6a1b9272ea123a1f2991ad632daf17ef0b173c76..d4f55f3491007b4966a1ba4c4019b5aaa8ee0488 100644 --- a/mm/damon/vaddr-test.h +++ b/mm/damon/vaddr-test.h @@ -109,7 +109,7 @@ static struct damon_region *__nth_region_of(struct damon_target *t, int idx) } /* - * Test 'damon_va_apply_three_regions()' + * Test 'damon_set_regions()' * * test kunit object * regions an array containing start/end addresses of current @@ -124,7 +124,7 @@ static struct damon_region *__nth_region_of(struct damon_target *t, int idx) * the change, DAMON periodically reads the mappings, simplifies it to the * three regions, and updates the monitoring target regions to fit in the three * regions. The update of current target regions is the role of - * 'damon_va_apply_three_regions()'. + * 'damon_set_regions()'. * * This test passes the given target regions and the new three regions that * need to be applied to the function and check whether it updates the regions @@ -139,13 +139,13 @@ static void damon_do_test_apply_three_regions(struct kunit *test, struct damon_region *r; int i; - t = damon_new_target(42); + t = damon_new_target(); for (i = 0; i < nr_regions / 2; i++) { r = damon_new_region(regions[i * 2], regions[i * 2 + 1]); damon_add_region(r, t); } - damon_va_apply_three_regions(t, three_regions); + damon_set_regions(t, three_regions, 3); for (i = 0; i < nr_expected / 2; i++) { r = __nth_region_of(t, i); @@ -251,7 +251,7 @@ static void damon_test_apply_three_regions4(struct kunit *test) static void damon_test_split_evenly_fail(struct kunit *test, unsigned long start, unsigned long end, unsigned int nr_pieces) { - struct damon_target *t = damon_new_target(42); + struct damon_target *t = damon_new_target(); struct damon_region *r = damon_new_region(start, end); damon_add_region(r, t); @@ -270,7 +270,7 @@ static void damon_test_split_evenly_fail(struct kunit *test, static void damon_test_split_evenly_succ(struct kunit *test, unsigned long start, unsigned long end, unsigned int nr_pieces) { - struct damon_target *t = damon_new_target(42); + struct damon_target *t = damon_new_target(); struct damon_region *r = damon_new_region(start, end); unsigned long expected_width = (end - start) / nr_pieces; unsigned long i = 0; @@ -281,14 +281,16 @@ static void damon_test_split_evenly_succ(struct kunit *test, KUNIT_EXPECT_EQ(test, damon_nr_regions(t), nr_pieces); damon_for_each_region(r, t) { - if (i == nr_pieces - 1) + if (i == nr_pieces - 1) { + KUNIT_EXPECT_EQ(test, + r->ar.start, start + i * expected_width); + KUNIT_EXPECT_EQ(test, r->ar.end, end); break; + } KUNIT_EXPECT_EQ(test, r->ar.start, start + i++ * expected_width); KUNIT_EXPECT_EQ(test, r->ar.end, start + i * expected_width); } - KUNIT_EXPECT_EQ(test, r->ar.start, start + i * expected_width); - KUNIT_EXPECT_EQ(test, r->ar.end, end); damon_free_target(t); } @@ -314,7 +316,7 @@ static struct kunit_case damon_test_cases[] = { }; static struct kunit_suite damon_test_suite = { - .name = "damon-primitives", + .name = "damon-operations", .test_cases = damon_test_cases, }; kunit_test_suite(damon_test_suite); diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 89b6468da2b9b0d595a34bbcf4ded9231f80c2ad..4c953e4701f059b8d46418e58cd28e6e80b9bc20 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -15,7 +15,7 @@ #include #include -#include "prmtv-common.h" +#include "ops-common.h" #ifdef CONFIG_DAMON_VADDR_KUNIT_TEST #undef DAMON_MIN_REGION @@ -23,12 +23,12 @@ #endif /* - * 't->id' should be the pointer to the relevant 'struct pid' having reference + * 't->pid' should be the pointer to the relevant 'struct pid' having reference * count. Caller must put the returned task, unless it is NULL. */ static inline struct task_struct *damon_get_task_struct(struct damon_target *t) { - return get_pid_task((struct pid *)t->id, PIDTYPE_PID); + return get_pid_task(t->pid, PIDTYPE_PID); } /* @@ -72,7 +72,7 @@ static int damon_va_evenly_split_region(struct damon_target *t, return -EINVAL; orig_end = r->ar.end; - sz_orig = r->ar.end - r->ar.start; + sz_orig = damon_sz_region(r); sz_piece = ALIGN_DOWN(sz_orig / nr_pieces, DAMON_MIN_REGION); if (!sz_piece) @@ -250,8 +250,8 @@ static void __damon_va_init_regions(struct damon_ctx *ctx, for (i = 0; i < 3; i++) sz += regions[i].end - regions[i].start; - if (ctx->min_nr_regions) - sz /= ctx->min_nr_regions; + if (ctx->attrs.min_nr_regions) + sz /= ctx->attrs.min_nr_regions; if (sz < DAMON_MIN_REGION) sz = DAMON_MIN_REGION; @@ -281,77 +281,6 @@ static void damon_va_init(struct damon_ctx *ctx) } } -/* - * Functions for the dynamic monitoring target regions update - */ - -/* - * Check whether a region is intersecting an address range - * - * Returns true if it is. - */ -static bool damon_intersect(struct damon_region *r, - struct damon_addr_range *re) -{ - return !(r->ar.end <= re->start || re->end <= r->ar.start); -} - -/* - * Update damon regions for the three big regions of the given target - * - * t the given target - * bregions the three big regions of the target - */ -static void damon_va_apply_three_regions(struct damon_target *t, - struct damon_addr_range bregions[3]) -{ - struct damon_region *r, *next; - unsigned int i; - - /* Remove regions which are not in the three big regions now */ - damon_for_each_region_safe(r, next, t) { - for (i = 0; i < 3; i++) { - if (damon_intersect(r, &bregions[i])) - break; - } - if (i == 3) - damon_destroy_region(r, t); - } - - /* Adjust intersecting regions to fit with the three big regions */ - for (i = 0; i < 3; i++) { - struct damon_region *first = NULL, *last; - struct damon_region *newr; - struct damon_addr_range *br; - - br = &bregions[i]; - /* Get the first and last regions which intersects with br */ - damon_for_each_region(r, t) { - if (damon_intersect(r, br)) { - if (!first) - first = r; - last = r; - } - if (r->ar.start >= br->end) - break; - } - if (!first) { - /* no damon_region intersects with this big region */ - newr = damon_new_region( - ALIGN_DOWN(br->start, - DAMON_MIN_REGION), - ALIGN(br->end, DAMON_MIN_REGION)); - if (!newr) - continue; - damon_insert_region(newr, damon_prev_region(r), r, t); - } else { - first->ar.start = ALIGN_DOWN(br->start, - DAMON_MIN_REGION); - last->ar.end = ALIGN(br->end, DAMON_MIN_REGION); - } - } -} - /* * Update regions for current memory mappings */ @@ -363,7 +292,7 @@ static void damon_va_update(struct damon_ctx *ctx) damon_for_each_target(t, ctx) { if (damon_va_three_regions(t, three_regions)) continue; - damon_va_apply_three_regions(t, three_regions); + damon_set_regions(t, three_regions, 3); } } @@ -373,9 +302,14 @@ static int damon_mkold_pmd_entry(pmd_t *pmd, unsigned long addr, pte_t *pte; spinlock_t *ptl; - if (pmd_huge(*pmd)) { + if (pmd_trans_huge(*pmd)) { ptl = pmd_lock(walk->mm, pmd); - if (pmd_huge(*pmd)) { + if (!pmd_present(*pmd)) { + spin_unlock(ptl); + return 0; + } + + if (pmd_trans_huge(*pmd)) { damon_pmdp_mkold(pmd, walk->mm, addr); spin_unlock(ptl); return 0; @@ -402,16 +336,12 @@ static void damon_hugetlb_mkold(pte_t *pte, struct mm_struct *mm, pte_t entry = huge_ptep_get(pte); struct page *page = pte_page(entry); - if (!page) - return; - get_page(page); if (pte_young(entry)) { referenced = true; entry = pte_mkold(entry); - huge_ptep_set_access_flags(vma, addr, pte, entry, - vma->vm_flags & VM_WRITE); + set_huge_pte_at(mm, addr, pte, entry); } #ifdef CONFIG_MMU_NOTIFIER @@ -466,8 +396,8 @@ static void damon_va_mkold(struct mm_struct *mm, unsigned long addr) * Functions for the access checking of the regions */ -static void __damon_va_prepare_access_check(struct damon_ctx *ctx, - struct mm_struct *mm, struct damon_region *r) +static void __damon_va_prepare_access_check(struct mm_struct *mm, + struct damon_region *r) { r->sampling_addr = damon_rand(r->ar.start, r->ar.end); @@ -485,7 +415,7 @@ static void damon_va_prepare_access_checks(struct damon_ctx *ctx) if (!mm) continue; damon_for_each_region(r, t) - __damon_va_prepare_access_check(ctx, mm, r); + __damon_va_prepare_access_check(mm, r); mmput(mm); } } @@ -504,9 +434,14 @@ static int damon_young_pmd_entry(pmd_t *pmd, unsigned long addr, struct damon_young_walk_private *priv = walk->private; #ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (pmd_huge(*pmd)) { + if (pmd_trans_huge(*pmd)) { ptl = pmd_lock(walk->mm, pmd); - if (!pmd_huge(*pmd)) { + if (!pmd_present(*pmd)) { + spin_unlock(ptl); + return 0; + } + + if (!pmd_trans_huge(*pmd)) { spin_unlock(ptl); goto regular_page; } @@ -516,7 +451,7 @@ static int damon_young_pmd_entry(pmd_t *pmd, unsigned long addr, if (pmd_young(*pmd) || !page_is_idle(page) || mmu_notifier_test_young(walk->mm, addr)) { - *priv->page_sz = ((1UL) << HPAGE_PMD_SHIFT); + *priv->page_sz = HPAGE_PMD_SIZE; priv->young = true; } put_page(page); @@ -564,9 +499,6 @@ static int damon_young_hugetlb_entry(pte_t *pte, unsigned long hmask, goto out; page = pte_page(entry); - if (!page) - goto out; - get_page(page); if (pte_young(entry) || !page_is_idle(page) || @@ -610,16 +542,15 @@ static bool damon_va_young(struct mm_struct *mm, unsigned long addr, * mm 'mm_struct' for the given virtual address space * r the region to be checked */ -static void __damon_va_check_access(struct damon_ctx *ctx, - struct mm_struct *mm, struct damon_region *r) +static void __damon_va_check_access(struct mm_struct *mm, + struct damon_region *r, bool same_target) { - static struct mm_struct *last_mm; static unsigned long last_addr; static unsigned long last_page_sz = PAGE_SIZE; static bool last_accessed; /* If the region is in the last checked page, reuse the result */ - if (mm == last_mm && (ALIGN_DOWN(last_addr, last_page_sz) == + if (same_target && (ALIGN_DOWN(last_addr, last_page_sz) == ALIGN_DOWN(r->sampling_addr, last_page_sz))) { if (last_accessed) r->nr_accesses++; @@ -630,7 +561,6 @@ static void __damon_va_check_access(struct damon_ctx *ctx, if (last_accessed) r->nr_accesses++; - last_mm = mm; last_addr = r->sampling_addr; } @@ -640,14 +570,17 @@ static unsigned int damon_va_check_accesses(struct damon_ctx *ctx) struct mm_struct *mm; struct damon_region *r; unsigned int max_nr_accesses = 0; + bool same_target; damon_for_each_target(t, ctx) { mm = damon_get_mm(t); if (!mm) continue; + same_target = false; damon_for_each_region(r, t) { - __damon_va_check_access(ctx, mm, r); + __damon_va_check_access(mm, r, same_target); max_nr_accesses = max(r->nr_accesses, max_nr_accesses); + same_target = true; } mmput(mm); } @@ -659,9 +592,8 @@ static unsigned int damon_va_check_accesses(struct damon_ctx *ctx) * Functions for the target validity check and cleanup */ -bool damon_va_target_valid(void *target) +static bool damon_va_target_valid(struct damon_target *t) { - struct damon_target *t = target; struct task_struct *task; task = damon_get_task_struct(t); @@ -685,7 +617,7 @@ static unsigned long damos_madvise(struct damon_target *target, { struct mm_struct *mm; unsigned long start = PAGE_ALIGN(r->ar.start); - unsigned long len = PAGE_ALIGN(r->ar.end - r->ar.start); + unsigned long len = PAGE_ALIGN(damon_sz_region(r)); unsigned long applied; mm = damon_get_mm(target); @@ -724,6 +656,9 @@ static unsigned long damon_va_apply_scheme(struct damon_ctx *ctx, case DAMOS_STAT: return 0; default: + /* + * DAMOS actions that are not yet supported by 'vaddr'. + */ return 0; } @@ -737,7 +672,7 @@ static int damon_va_scheme_score(struct damon_ctx *context, switch (scheme->action) { case DAMOS_PAGEOUT: - return damon_pageout_score(context, r, scheme); + return damon_cold_score(context, r, scheme); default: break; } @@ -745,17 +680,35 @@ static int damon_va_scheme_score(struct damon_ctx *context, return DAMOS_MAX_SCORE; } -void damon_va_set_primitives(struct damon_ctx *ctx) +static int __init damon_va_initcall(void) { - ctx->primitive.init = damon_va_init; - ctx->primitive.update = damon_va_update; - ctx->primitive.prepare_access_checks = damon_va_prepare_access_checks; - ctx->primitive.check_accesses = damon_va_check_accesses; - ctx->primitive.reset_aggregated = NULL; - ctx->primitive.target_valid = damon_va_target_valid; - ctx->primitive.cleanup = NULL; - ctx->primitive.apply_scheme = damon_va_apply_scheme; - ctx->primitive.get_scheme_score = damon_va_scheme_score; -} + struct damon_operations ops = { + .id = DAMON_OPS_VADDR, + .init = damon_va_init, + .update = damon_va_update, + .prepare_access_checks = damon_va_prepare_access_checks, + .check_accesses = damon_va_check_accesses, + .reset_aggregated = NULL, + .target_valid = damon_va_target_valid, + .cleanup = NULL, + .apply_scheme = damon_va_apply_scheme, + .get_scheme_score = damon_va_scheme_score, + }; + /* ops for fixed virtual address ranges */ + struct damon_operations ops_fvaddr = ops; + int err; + + /* Don't set the monitoring target regions for the entire mapping */ + ops_fvaddr.id = DAMON_OPS_FVADDR; + ops_fvaddr.init = NULL; + ops_fvaddr.update = NULL; + + err = damon_register_ops(&ops); + if (err) + return err; + return damon_register_ops(&ops_fvaddr); +}; + +subsys_initcall(damon_va_initcall); #include "vaddr-test.h" diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile index 937d36ae9a69c2d8955791437e75049b9f0bc0f0..cc5b6ceb4f62013fe7485666b758c6b701bdfe4f 100644 --- a/tools/testing/selftests/damon/Makefile +++ b/tools/testing/selftests/damon/Makefile @@ -6,5 +6,7 @@ TEST_GEN_FILES += huge_count_read_write TEST_FILES = _chk_dependency.sh _debugfs_common.sh TEST_PROGS = debugfs_attrs.sh debugfs_schemes.sh debugfs_target_ids.sh TEST_PROGS += debugfs_empty_targets.sh debugfs_huge_count_read_write.sh +TEST_PROGS += sysfs.sh +TEST_PROGS += reclaim.sh lru_sort.sh include ../lib.mk diff --git a/tools/testing/selftests/damon/lru_sort.sh b/tools/testing/selftests/damon/lru_sort.sh new file mode 100644 index 0000000000000000000000000000000000000000..61b80197c89660cffb3db9d345a8aa6995a9853d --- /dev/null +++ b/tools/testing/selftests/damon/lru_sort.sh @@ -0,0 +1,41 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +if [ $EUID -ne 0 ] +then + echo "Run as root" + exit $ksft_skip +fi + +damon_lru_sort_enabled="/sys/module/damon_lru_sort/parameters/enabled" +if [ ! -f "$damon_lru_sort_enabled" ] +then + echo "No 'enabled' file. Maybe DAMON_LRU_SORT not built" + exit $ksft_skip +fi + +nr_kdamonds=$(pgrep kdamond | wc -l) +if [ "$nr_kdamonds" -ne 0 ] +then + echo "Another kdamond is running" + exit $ksft_skip +fi + +echo Y > "$damon_lru_sort_enabled" +nr_kdamonds=$(pgrep kdamond | wc -l) +if [ "$nr_kdamonds" -ne 1 ] +then + echo "kdamond is not turned on" + exit 1 +fi + +echo N > "$damon_lru_sort_enabled" +nr_kdamonds=$(pgrep kdamond | wc -l) +if [ "$nr_kdamonds" -ne 0 ] +then + echo "kdamond is not turned off" + exit 1 +fi diff --git a/tools/testing/selftests/damon/reclaim.sh b/tools/testing/selftests/damon/reclaim.sh new file mode 100644 index 0000000000000000000000000000000000000000..78dbc2334cbe123cbf5df50085c68a681a43cbe0 --- /dev/null +++ b/tools/testing/selftests/damon/reclaim.sh @@ -0,0 +1,42 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +if [ $EUID -ne 0 ] +then + echo "Run as root" + exit $ksft_skip +fi + +damon_reclaim_enabled="/sys/module/damon_reclaim/parameters/enabled" +if [ ! -f "$damon_reclaim_enabled" ] +then + echo "No 'enabled' file. Maybe DAMON_RECLAIM not built" + exit $ksft_skip +fi + +nr_kdamonds=$(pgrep kdamond | wc -l) +if [ "$nr_kdamonds" -ne 0 ] +then + echo "Another kdamond is running" + exit $ksft_skip +fi + +echo Y > "$damon_reclaim_enabled" + +nr_kdamonds=$(pgrep kdamond | wc -l) +if [ "$nr_kdamonds" -ne 1 ] +then + echo "kdamond is not turned on" + exit 1 +fi + +echo N > "$damon_reclaim_enabled" +nr_kdamonds=$(pgrep kdamond | wc -l) +if [ "$nr_kdamonds" -ne 0 ] +then + echo "kdamond is not turned off" + exit 1 +fi diff --git a/tools/testing/selftests/damon/sysfs.sh b/tools/testing/selftests/damon/sysfs.sh new file mode 100644 index 0000000000000000000000000000000000000000..db4942383a50f523ca8bb1cb1a682a13be521899 --- /dev/null +++ b/tools/testing/selftests/damon/sysfs.sh @@ -0,0 +1,314 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Kselftest frmework requirement - SKIP code is 4. +ksft_skip=4 + +ensure_write_succ() +{ + file=$1 + content=$2 + reason=$3 + + if ! echo "$content" > "$file" + then + echo "writing $content to $file failed" + echo "expected success because $reason" + exit 1 + fi +} + +ensure_write_fail() +{ + file=$1 + content=$2 + reason=$3 + + if echo "$content" > "$file" + then + echo "writing $content to $file succeed ($fail_reason)" + echo "expected failure because $reason" + exit 1 + fi +} + +ensure_dir() +{ + dir=$1 + to_ensure=$2 + if [ "$to_ensure" = "exist" ] && [ ! -d "$dir" ] + then + echo "$dir dir is expected but not found" + exit 1 + elif [ "$to_ensure" = "not_exist" ] && [ -d "$dir" ] + then + echo "$dir dir is not expected but found" + exit 1 + fi +} + +ensure_file() +{ + file=$1 + to_ensure=$2 + permission=$3 + if [ "$to_ensure" = "exist" ] + then + if [ ! -f "$file" ] + then + echo "$file is expected but not found" + exit 1 + fi + perm=$(stat -c "%a" "$file") + if [ ! "$perm" = "$permission" ] + then + echo "$file permission: expected $permission but $perm" + exit 1 + fi + elif [ "$to_ensure" = "not_exist" ] && [ -f "$dir" ] + then + echo "$file is not expected but found" + exit 1 + fi +} + +test_range() +{ + range_dir=$1 + ensure_dir "$range_dir" "exist" + ensure_file "$range_dir/min" "exist" 600 + ensure_file "$range_dir/max" "exist" 600 +} + +test_tried_regions() +{ + tried_regions_dir=$1 + ensure_dir "$tried_regions_dir" "exist" +} + +test_stats() +{ + stats_dir=$1 + ensure_dir "$stats_dir" "exist" + for f in nr_tried sz_tried nr_applied sz_applied qt_exceeds + do + ensure_file "$stats_dir/$f" "exist" "400" + done +} + +test_watermarks() +{ + watermarks_dir=$1 + ensure_dir "$watermarks_dir" "exist" + ensure_file "$watermarks_dir/metric" "exist" "600" + ensure_file "$watermarks_dir/interval_us" "exist" "600" + ensure_file "$watermarks_dir/high" "exist" "600" + ensure_file "$watermarks_dir/mid" "exist" "600" + ensure_file "$watermarks_dir/low" "exist" "600" +} + +test_weights() +{ + weights_dir=$1 + ensure_dir "$weights_dir" "exist" + ensure_file "$weights_dir/sz_permil" "exist" "600" + ensure_file "$weights_dir/nr_accesses_permil" "exist" "600" + ensure_file "$weights_dir/age_permil" "exist" "600" +} + +test_quotas() +{ + quotas_dir=$1 + ensure_dir "$quotas_dir" "exist" + ensure_file "$quotas_dir/ms" "exist" 600 + ensure_file "$quotas_dir/bytes" "exist" 600 + ensure_file "$quotas_dir/reset_interval_ms" "exist" 600 + test_weights "$quotas_dir/weights" +} + +test_access_pattern() +{ + access_pattern_dir=$1 + ensure_dir "$access_pattern_dir" "exist" + test_range "$access_pattern_dir/age" + test_range "$access_pattern_dir/nr_accesses" + test_range "$access_pattern_dir/sz" +} + +test_scheme() +{ + scheme_dir=$1 + ensure_dir "$scheme_dir" "exist" + ensure_file "$scheme_dir/action" "exist" "600" + test_access_pattern "$scheme_dir/access_pattern" + test_quotas "$scheme_dir/quotas" + test_watermarks "$scheme_dir/watermarks" + test_stats "$scheme_dir/stats" + test_tried_regions "$scheme_dir/tried_regions" +} + +test_schemes() +{ + schemes_dir=$1 + ensure_dir "$schemes_dir" "exist" + ensure_file "$schemes_dir/nr_schemes" "exist" 600 + + ensure_write_succ "$schemes_dir/nr_schemes" "1" "valid input" + test_scheme "$schemes_dir/0" + + ensure_write_succ "$schemes_dir/nr_schemes" "2" "valid input" + test_scheme "$schemes_dir/0" + test_scheme "$schemes_dir/1" + + ensure_write_succ "$schemes_dir/nr_schemes" "0" "valid input" + ensure_dir "$schemes_dir/0" "not_exist" + ensure_dir "$schemes_dir/1" "not_exist" +} + +test_region() +{ + region_dir=$1 + ensure_dir "$region_dir" "exist" + ensure_file "$region_dir/start" "exist" 600 + ensure_file "$region_dir/end" "exist" 600 +} + +test_regions() +{ + regions_dir=$1 + ensure_dir "$regions_dir" "exist" + ensure_file "$regions_dir/nr_regions" "exist" 600 + + ensure_write_succ "$regions_dir/nr_regions" "1" "valid input" + test_region "$regions_dir/0" + + ensure_write_succ "$regions_dir/nr_regions" "2" "valid input" + test_region "$regions_dir/0" + test_region "$regions_dir/1" + + ensure_write_succ "$regions_dir/nr_regions" "0" "valid input" + ensure_dir "$regions_dir/0" "not_exist" + ensure_dir "$regions_dir/1" "not_exist" +} + +test_target() +{ + target_dir=$1 + ensure_dir "$target_dir" "exist" + ensure_file "$target_dir/pid_target" "exist" "600" + test_regions "$target_dir/regions" +} + +test_targets() +{ + targets_dir=$1 + ensure_dir "$targets_dir" "exist" + ensure_file "$targets_dir/nr_targets" "exist" 600 + + ensure_write_succ "$targets_dir/nr_targets" "1" "valid input" + test_target "$targets_dir/0" + + ensure_write_succ "$targets_dir/nr_targets" "2" "valid input" + test_target "$targets_dir/0" + test_target "$targets_dir/1" + + ensure_write_succ "$targets_dir/nr_targets" "0" "valid input" + ensure_dir "$targets_dir/0" "not_exist" + ensure_dir "$targets_dir/1" "not_exist" +} + +test_intervals() +{ + intervals_dir=$1 + ensure_dir "$intervals_dir" "exist" + ensure_file "$intervals_dir/aggr_us" "exist" "600" + ensure_file "$intervals_dir/sample_us" "exist" "600" + ensure_file "$intervals_dir/update_us" "exist" "600" +} + +test_monitoring_attrs() +{ + monitoring_attrs_dir=$1 + ensure_dir "$monitoring_attrs_dir" "exist" + test_intervals "$monitoring_attrs_dir/intervals" + test_range "$monitoring_attrs_dir/nr_regions" +} + +test_context() +{ + context_dir=$1 + ensure_dir "$context_dir" "exist" + ensure_file "$context_dir/avail_operations" "exit" 400 + ensure_file "$context_dir/operations" "exist" 600 + test_monitoring_attrs "$context_dir/monitoring_attrs" + test_targets "$context_dir/targets" + test_schemes "$context_dir/schemes" +} + +test_contexts() +{ + contexts_dir=$1 + ensure_dir "$contexts_dir" "exist" + ensure_file "$contexts_dir/nr_contexts" "exist" 600 + + ensure_write_succ "$contexts_dir/nr_contexts" "1" "valid input" + test_context "$contexts_dir/0" + + ensure_write_fail "$contexts_dir/nr_contexts" "2" "only 0/1 are supported" + test_context "$contexts_dir/0" + + ensure_write_succ "$contexts_dir/nr_contexts" "0" "valid input" + ensure_dir "$contexts_dir/0" "not_exist" +} + +test_kdamond() +{ + kdamond_dir=$1 + ensure_dir "$kdamond_dir" "exist" + ensure_file "$kdamond_dir/state" "exist" "600" + ensure_file "$kdamond_dir/pid" "exist" 400 + test_contexts "$kdamond_dir/contexts" +} + +test_kdamonds() +{ + kdamonds_dir=$1 + ensure_dir "$kdamonds_dir" "exist" + + ensure_file "$kdamonds_dir/nr_kdamonds" "exist" "600" + + ensure_write_succ "$kdamonds_dir/nr_kdamonds" "1" "valid input" + test_kdamond "$kdamonds_dir/0" + + ensure_write_succ "$kdamonds_dir/nr_kdamonds" "2" "valid input" + test_kdamond "$kdamonds_dir/0" + test_kdamond "$kdamonds_dir/1" + + ensure_write_succ "$kdamonds_dir/nr_kdamonds" "0" "valid input" + ensure_dir "$kdamonds_dir/0" "not_exist" + ensure_dir "$kdamonds_dir/1" "not_exist" +} + +test_damon_sysfs() +{ + damon_sysfs=$1 + if [ ! -d "$damon_sysfs" ] + then + echo "$damon_sysfs not found" + exit $ksft_skip + fi + + test_kdamonds "$damon_sysfs/kdamonds" +} + +check_dependencies() +{ + if [ $EUID -ne 0 ] + then + echo "Run as root" + exit $ksft_skip + fi +} + +check_dependencies +test_damon_sysfs "/sys/kernel/mm/damon/admin"