diff --git a/.mailmap b/.mailmap index 735470e21075b1..501d858cb43227 100644 --- a/.mailmap +++ b/.mailmap @@ -817,6 +817,7 @@ Simon Wunderlich Simon Wunderlich Simon Wunderlich Simon Wunderlich +SJ Park Sricharan Ramabadhran Srinivas Kandagatla Srinivas Kandagatla diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-damon b/Documentation/ABI/testing/sysfs-kernel-mm-damon index b73e6bc28ea5fc..4fdec63a47d4aa 100644 --- a/Documentation/ABI/testing/sysfs-kernel-mm-damon +++ b/Documentation/ABI/testing/sysfs-kernel-mm-damon @@ -1,26 +1,26 @@ what: /sys/kernel/mm/damon/ Date: Mar 2022 -Contact: SeongJae Park +Contact: SJ 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 +Contact: SJ 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 +Contact: SJ 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 +Contact: SJ 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 @@ -40,33 +40,33 @@ Description: Writing 'on' or 'off' to this file makes the kdamond starts or What: /sys/kernel/mm/damon/admin/kdamonds//pid Date: Mar 2022 -Contact: SeongJae Park +Contact: SJ Park Description: Reading this file returns the pid of the kdamond if it is running. What: /sys/kernel/mm/damon/admin/kdamonds//refresh_ms Date: Jul 2025 -Contact: SeongJae Park +Contact: SJ Park Description: Writing a value to this file sets the time interval for automatic DAMON status file contents update. Writing '0' disables the update. Reading this file returns the value. What: /sys/kernel/mm/damon/admin/kdamonds//contexts/nr_contexts Date: Mar 2022 -Contact: SeongJae Park +Contact: SJ 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 +Contact: SJ 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 +Contact: SJ 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 @@ -79,42 +79,42 @@ Description: Writing a keyword for a monitoring operations set ('vaddr' for What: /sys/kernel/mm/damon/admin/kdamonds//contexts//addr_unit Date: Aug 2025 -Contact: SeongJae Park +Contact: SJ Park Description: Writing an integer to this file sets the 'address unit' parameter of the given operations set of the context. Reading the file returns the last-written 'address unit' value. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//pause Date: Mar 2026 -Contact: SeongJae Park +Contact: SJ Park Description: Writing a boolean keyword to this file sets the 'pause' request parameter for the context. Reading the file returns the last-written 'pause' value. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//monitoring_attrs/intervals/sample_us Date: Mar 2022 -Contact: SeongJae Park +Contact: SJ 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 +Contact: SJ 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 +Contact: SJ 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/intervals/intrvals_goal/access_bp Date: Feb 2025 -Contact: SeongJae Park +Contact: SJ Park Description: Writing a value to this file sets the monitoring intervals auto-tuning target DAMON-observed access events ratio within the given time interval (aggrs in same directory), in bp @@ -122,7 +122,7 @@ Description: Writing a value to this file sets the monitoring intervals What: /sys/kernel/mm/damon/admin/kdamonds//contexts//monitoring_attrs/intervals/intrvals_goal/aggrs Date: Feb 2025 -Contact: SeongJae Park +Contact: SJ Park Description: Writing a value to this file sets the time interval to achieve the monitoring intervals auto-tuning target DAMON-observed access events ratio (access_bp in same directory) within. @@ -130,14 +130,14 @@ Description: Writing a value to this file sets the time interval to achieve What: /sys/kernel/mm/damon/admin/kdamonds//contexts//monitoring_attrs/intervals/intrvals_goal/min_sample_us Date: Feb 2025 -Contact: SeongJae Park +Contact: SJ Park Description: Writing a value to this file sets the minimum value of auto-tuned sampling interval in microseconds. Reading this file returns the value. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//monitoring_attrs/intervals/intrvals_goal/max_sample_us Date: Feb 2025 -Contact: SeongJae Park +Contact: SJ Park Description: Writing a value to this file sets the maximum value of auto-tuned sampling interval in microseconds. Reading this file returns the value. @@ -145,42 +145,42 @@ Description: Writing a value to this file sets the maximum value of What: /sys/kernel/mm/damon/admin/kdamonds//contexts//monitoring_attrs/nr_regions/min WDate: Mar 2022 -Contact: SeongJae Park +Contact: SJ 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 +Contact: SJ 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 +Contact: SJ 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 +Contact: SJ 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//obsolete_target Date: Oct 2025 -Contact: SeongJae Park +Contact: SJ Park Description: Writing to and reading from this file sets and gets the obsoleteness of the matching parameters commit destination target. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//targets//regions/nr_regions Date: Mar 2022 -Contact: SeongJae Park +Contact: SJ 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 @@ -190,181 +190,181 @@ Description: Writing a number 'N' to this file creates the number of What: /sys/kernel/mm/damon/admin/kdamonds//contexts//targets//regions//start Date: Mar 2022 -Contact: SeongJae Park +Contact: SJ 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 +Contact: SJ 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 +Contact: SJ 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 +Contact: SJ 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//target_nid Date: Jun 2024 -Contact: SeongJae Park +Contact: SJ Park Description: Action's target NUMA node id. Supported by only relevant actions. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//apply_interval_us Date: Sep 2023 -Contact: SeongJae Park +Contact: SJ Park Description: Writing a value to this file sets the action apply interval of the scheme in microseconds. Reading this file returns the value. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//access_pattern/sz/min Date: Mar 2022 -Contact: SeongJae Park +Contact: SJ Park Description: Writing to and reading from this file sets and gets the minimum 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 +Contact: SJ 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 +Contact: SJ 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 +Contact: SJ 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 +Contact: SJ 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 +Contact: SJ 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 +Contact: SJ 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 +Contact: SJ 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/effective_bytes Date: Feb 2024 -Contact: SeongJae Park +Contact: SJ Park Description: Reading from this file gets the effective size quota of the scheme in bytes, which adjusted for the time quota and goals. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//quotas/reset_interval_ms Date: Mar 2022 -Contact: SeongJae Park +Contact: SJ 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/goals/nr_goals Date: Nov 2023 -Contact: SeongJae Park +Contact: SJ Park Description: Writing a number 'N' to this file creates the number of directories for setting automatic tuning of the scheme's aggressiveness named '0' to 'N-1' under the goals/ directory. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//quotas/goals//target_metric Date: Feb 2024 -Contact: SeongJae Park +Contact: SJ Park Description: Writing to and reading from this file sets and gets the quota auto-tuning goal metric. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//quotas/goals//target_value Date: Nov 2023 -Contact: SeongJae Park +Contact: SJ Park Description: Writing to and reading from this file sets and gets the target value of the goal metric. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//quotas/goals//current_value Date: Nov 2023 -Contact: SeongJae Park +Contact: SJ Park Description: Writing to and reading from this file sets and gets the current value of the goal metric. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//quotas/goals//nid Date: Apr 2025 -Contact: SeongJae Park +Contact: SJ Park Description: Writing to and reading from this file sets and gets the nid parameter of the goal. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//quotas/goals//path Date: Oct 2025 -Contact: SeongJae Park +Contact: SJ Park Description: Writing to and reading from this file sets and gets the path parameter of the goal. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//quotas/goal_tuner Date: Mar 2026 -Contact: SeongJae Park +Contact: SJ Park Description: Writing to and reading from this file sets and gets the goal-based effective quota auto-tuning algorithm to use. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//quotas/fail_charge_num Date: Mar 2026 -Contact: SeongJae Park +Contact: SJ Park Description: Writing to and reading from this file sets and gets the action-failed memory quota charging ratio numerator. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//quotas/fail_charge_denom Date: Mar 2026 -Contact: SeongJae Park +Contact: SJ Park Description: Writing to and reading from this file sets and gets the action-failed memory quota charging ratio denominator. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//quotas/weights/sz_permil Date: Mar 2022 -Contact: SeongJae Park +Contact: SJ 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 +Contact: SJ 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 +Contact: SJ 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 +Contact: SJ 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 @@ -373,44 +373,44 @@ Description: Writing to and reading from this file sets and gets the metric What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//watermarks/interval_us Date: Mar 2022 -Contact: SeongJae Park +Contact: SJ 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 +Contact: SJ 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 +Contact: SJ 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 +Contact: SJ 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//core_filters Date: Feb 2025 -Contact: SeongJae Park +Contact: SJ Park Description: Directory for DAMON core layer-handled DAMOS filters. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//core_filters/nr_filters Date: Feb 2025 -Contact: SeongJae Park +Contact: SJ Park Description: Writing a number 'N' to this file creates the number of directories for setting filters of the scheme named '0' to 'N-1' under the core_filters/ directory. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//core_filters//type Date: Feb 2025 -Contact: SeongJae Park +Contact: SJ Park Description: Writing to and reading from this file sets and gets the type of the memory of the interest. 'anon' for anonymous pages, 'memcg' for specific memory cgroup, 'young' for young pages, @@ -419,62 +419,62 @@ Description: Writing to and reading from this file sets and gets the type of What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//core_filters//memcg_path Date: Feb 2025 -Contact: SeongJae Park +Contact: SJ Park Description: If 'memcg' is written to the 'type' file, writing to and reading from this file sets and gets the path to the memory cgroup of the interest. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//core_filters//addr_start Date: Feb 2025 -Contact: SeongJae Park +Contact: SJ Park Description: If 'addr' is written to the 'type' file, writing to or reading from this file sets or gets the start address of the address range for the filter. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//core_filters//addr_end Date: Feb 2025 -Contact: SeongJae Park +Contact: SJ Park Description: If 'addr' is written to the 'type' file, writing to or reading from this file sets or gets the end address of the address range for the filter. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//core_filters//min Date: Feb 2025 -Contact: SeongJae Park +Contact: SJ Park Description: If 'hugepage_size' is written to the 'type' file, writing to or reading from this file sets or gets the minimum size of the hugepage for the filter. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//core_filters//max Date: Feb 2025 -Contact: SeongJae Park +Contact: SJ Park Description: If 'hugepage_size' is written to the 'type' file, writing to or reading from this file sets or gets the maximum size of the hugepage for the filter. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//core_filters//damon_target_idx Date: Feb 2025 -Contact: SeongJae Park +Contact: SJ Park Description: If 'target' is written to the 'type' file, writing to or reading from this file sets or gets the index of the DAMON monitoring target of the interest. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//core_filters//matching Date: Feb 2025 -Contact: SeongJae Park +Contact: SJ Park Description: Writing 'Y' or 'N' to this file sets whether the filter is for the memory of the 'type', or all except the 'type'. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//core_filters//allow Date: Feb 2025 -Contact: SeongJae Park +Contact: SJ Park Description: Writing 'Y' or 'N' to this file sets whether to allow or reject applying the scheme's action to the memory that satisfies the 'type' and the 'matching' of the directory. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//ops_filters Date: Feb 2025 -Contact: SeongJae Park +Contact: SJ Park Description: Directory for DAMON operations set layer-handled DAMOS filters. Files under this directory works same to those of /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//core_filters @@ -482,7 +482,7 @@ Description: Directory for DAMON operations set layer-handled DAMOS filters. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//filters Date: Dec 2022 -Contact: SeongJae Park +Contact: SJ Park Description: Directory for DAMOS filters. Files under this directory works same to those of /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//{core,ops}_filters @@ -491,14 +491,14 @@ Description: Directory for DAMOS filters. Files under this directory works What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//dests/nr_dests Date: Jul 2025 -Contact: SeongJae Park +Contact: SJ Park Description: Writing a number 'N' to this file creates the number of directories for setting action destinations of the scheme named '0' to 'N-1' under the dests/ directory. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//dests//id Date: Jul 2025 -Contact: SeongJae Park +Contact: SJ Park Description: Writing to and reading from this file sets and gets the id of the DAMOS action destination. For DAMOS_MIGRATE_{HOT,COLD} actions, the destination node's node id can be written and @@ -506,98 +506,98 @@ Description: Writing to and reading from this file sets and gets the id of What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//dests//weight Date: Jul 2025 -Contact: SeongJae Park +Contact: SJ Park Description: Writing to and reading from this file sets and gets the weight of the DAMOS action destination to select as the destination of each action among the destinations. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//stats/nr_tried Date: Mar 2022 -Contact: SeongJae Park +Contact: SJ 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 +Contact: SJ 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 +Contact: SJ 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 +Contact: SJ 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/sz_ops_filter_passed Date: Dec 2024 -Contact: SeongJae Park +Contact: SJ Park Description: Reading this file returns the total size of memory that passed DAMON operations layer-handled filters of the scheme in bytes. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//stats/qt_exceeds Date: Mar 2022 -Contact: SeongJae Park +Contact: SJ 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//stats/nr_snapshots Date: Dec 2025 -Contact: SeongJae Park +Contact: SJ Park Description: Reading this file returns the total number of DAMON snapshots that the scheme has tried to be applied. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//stats/max_nr_snapshots Date: Dec 2025 -Contact: SeongJae Park +Contact: SJ Park Description: Writing a number to this file sets the upper limit of nr_snapshots that deactivates the scheme when the limit is reached or exceeded. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//tried_regions/total_bytes Date: Jul 2023 -Contact: SeongJae Park +Contact: SJ Park Description: Reading this file returns the total amount of memory that corresponding DAMON-based Operation Scheme's action has tried to be applied. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//tried_regions//start Date: Oct 2022 -Contact: SeongJae Park +Contact: SJ 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 +Contact: SJ 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 +Contact: SJ 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 +Contact: SJ 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. What: /sys/kernel/mm/damon/admin/kdamonds//contexts//schemes//tried_regions//sz_filter_passed Date: Dec 2024 -Contact: SeongJae Park +Contact: SJ Park Description: Reading this file returns the size of the memory in the region that passed DAMON operations layer-handled filters of the scheme in bytes. diff --git a/MAINTAINERS b/MAINTAINERS index a674e36529f757..1ab8736850ea37 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7125,7 +7125,7 @@ W: https://docs.dasharo.com/ F: drivers/platform/x86/dasharo-acpi.c DAMON -M: SeongJae Park +M: SJ Park L: damon@lists.linux.dev L: linux-mm@kvack.org S: Maintained @@ -17257,6 +17257,7 @@ R: Ryan Roberts R: Dev Jain R: Barry Song R: Lance Yang +R: Usama Arif L: linux-mm@kvack.org S: Maintained W: http://www.linux-mm.org diff --git a/Makefile b/Makefile index bfb47ad8cb9a74..11539c3fd405cc 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 7 PATCHLEVEL = 2 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/m68k/include/asm/page_mm.h b/arch/m68k/include/asm/page_mm.h index ed782609ca413f..0971a0651d490b 100644 --- a/arch/m68k/include/asm/page_mm.h +++ b/arch/m68k/include/asm/page_mm.h @@ -55,10 +55,12 @@ static inline void clear_page(void *page) #define clear_user_page(addr, vaddr, page) \ do { clear_page(addr); \ flush_dcache_page(page); \ + (void)(vaddr); \ } while (0) #define copy_user_page(to, from, vaddr, page) \ do { copy_page(to, from); \ flush_dcache_page(page); \ + (void)(vaddr); \ } while (0) extern unsigned long m68k_memoffset; diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index c0a6992933e411..f7028caaeae06e 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -157,7 +157,7 @@ config RISCV select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS if MMU select HAVE_DYNAMIC_FTRACE if MMU && (CLANG_SUPPORTS_DYNAMIC_FTRACE || GCC_SUPPORTS_DYNAMIC_FTRACE) - select FUNCTION_ALIGNMENT_4B if HAVE_DYNAMIC_FTRACE && RISCV_ISA_C + select FUNCTION_ALIGNMENT_4B if DYNAMIC_FTRACE && RISCV_ISA_C select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS if HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS if (DYNAMIC_FTRACE_WITH_ARGS && !CFI) select HAVE_DYNAMIC_FTRACE_WITH_ARGS if HAVE_DYNAMIC_FTRACE diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h index 8cfe59483a8f28..c2b0a2928f0674 100644 --- a/arch/riscv/include/asm/cacheflush.h +++ b/arch/riscv/include/asm/cacheflush.h @@ -40,7 +40,7 @@ do { \ flush_icache_mm(vma->vm_mm, 0); \ } while (0) -#ifdef CONFIG_64BIT +#if defined(CONFIG_64BIT) && defined(CONFIG_MMU) /* This is accessed in assembly code. cpumask_var_t would be too complex. */ extern DECLARE_BITMAP(new_valid_map_cpus, NR_CPUS); extern char _end[]; @@ -56,7 +56,8 @@ static inline void mark_new_valid_map(void) #define flush_cache_vmap flush_cache_vmap static inline void flush_cache_vmap(unsigned long start, unsigned long end) { - if (is_vmalloc_or_module_addr((void *)start)) + if (is_vmalloc_or_module_addr((void *)start) || + (start >= VMEMMAP_START && end <= VMEMMAP_END)) mark_new_valid_map(); } #define flush_cache_vmap_early(start, end) local_flush_tlb_kernel_range(start, end) diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h index 09bb5f57a9d346..92d5f831f3495a 100644 --- a/arch/riscv/include/asm/io.h +++ b/arch/riscv/include/asm/io.h @@ -102,12 +102,14 @@ __io_reads_ins(reads, u32, l, __io_br(), __io_ar(addr)) #define readsw(addr, buffer, count) __readsw(addr, buffer, count) #define readsl(addr, buffer, count) __readsl(addr, buffer, count) +#ifdef CONFIG_HAS_IOPORT __io_reads_ins(ins, u8, b, __io_pbr(), __io_par(addr)) __io_reads_ins(ins, u16, w, __io_pbr(), __io_par(addr)) __io_reads_ins(ins, u32, l, __io_pbr(), __io_par(addr)) #define insb(addr, buffer, count) __insb(PCI_IOBASE + (addr), buffer, count) #define insw(addr, buffer, count) __insw(PCI_IOBASE + (addr), buffer, count) #define insl(addr, buffer, count) __insl(PCI_IOBASE + (addr), buffer, count) +#endif __io_writes_outs(writes, u8, b, __io_bw(), __io_aw()) __io_writes_outs(writes, u16, w, __io_bw(), __io_aw()) @@ -116,26 +118,32 @@ __io_writes_outs(writes, u32, l, __io_bw(), __io_aw()) #define writesw(addr, buffer, count) __writesw(addr, buffer, count) #define writesl(addr, buffer, count) __writesl(addr, buffer, count) +#ifdef CONFIG_HAS_IOPORT __io_writes_outs(outs, u8, b, __io_pbw(), __io_paw()) __io_writes_outs(outs, u16, w, __io_pbw(), __io_paw()) __io_writes_outs(outs, u32, l, __io_pbw(), __io_paw()) #define outsb(addr, buffer, count) __outsb(PCI_IOBASE + (addr), buffer, count) #define outsw(addr, buffer, count) __outsw(PCI_IOBASE + (addr), buffer, count) #define outsl(addr, buffer, count) __outsl(PCI_IOBASE + (addr), buffer, count) +#endif #ifdef CONFIG_64BIT __io_reads_ins(reads, u64, q, __io_br(), __io_ar(addr)) #define readsq(addr, buffer, count) __readsq(addr, buffer, count) +#ifdef CONFIG_HAS_IOPORT __io_reads_ins(ins, u64, q, __io_pbr(), __io_par(addr)) #define insq(addr, buffer, count) __insq(PCI_IOBASE + (addr), buffer, count) +#endif __io_writes_outs(writes, u64, q, __io_bw(), __io_aw()) #define writesq(addr, buffer, count) __writesq(addr, buffer, count) +#ifdef CONFIG_HAS_IOPORT __io_writes_outs(outs, u64, q, __io_pbr(), __io_paw()) #define outsq(addr, buffer, count) __outsq(PCI_IOBASE + (addr), buffer, count) #endif +#endif #include diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 08df724e13b9db..d799c4e56f8049 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -137,7 +137,7 @@ SYM_CODE_START(handle_exception) .Lrestore_kernel_tpsp: csrr tp, CSR_SCRATCH -#ifdef CONFIG_64BIT +#if defined(CONFIG_64BIT) && defined(CONFIG_MMU) /* * The RISC-V kernel does not flush TLBs on all CPUS after each new * vmalloc mapping or kfence_unprotect(), which may result in diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c index 1659d31fd288fc..caf6762427c87e 100644 --- a/arch/riscv/kernel/sys_hwprobe.c +++ b/arch/riscv/kernel/sys_hwprobe.c @@ -450,6 +450,7 @@ static int hwprobe_get_cpus(struct riscv_hwprobe __user *pairs, if (cpusetsize > cpumask_size()) cpusetsize = cpumask_size(); + cpumask_clear(&cpus); ret = copy_from_user(&cpus, cpus_user, cpusetsize); if (ret) return -EFAULT; diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index a842dc034571da..43ee881f6c6fd1 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -69,9 +69,9 @@ CPPFLAGS_$(vdso_lds) += -DHAS_VGETTIMEOFDAY endif # Disable -pg to prevent insert call site -CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) -CFLAGS_REMOVE_getrandom.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) -CFLAGS_REMOVE_hwprobe.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) +CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) $(CC_FLAGS_LTO) +CFLAGS_REMOVE_getrandom.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) $(CC_FLAGS_LTO) +CFLAGS_REMOVE_hwprobe.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) $(CC_FLAGS_LTO) # Force dependency $(obj)/$(vdso_o): $(obj)/$(vdso_so) diff --git a/arch/riscv/kernel/vdso/rt_sigreturn.S b/arch/riscv/kernel/vdso/rt_sigreturn.S index e82987dc37394b..d6f96b1abe409b 100644 --- a/arch/riscv/kernel/vdso/rt_sigreturn.S +++ b/arch/riscv/kernel/vdso/rt_sigreturn.S @@ -7,11 +7,19 @@ #include #include +/* + * WARNING: Do NOT add a CFI landing pad at the start of this function. + * Unwinders such as libgcc identify the sigreturn trampoline by matching the + * instruction sequence. Adding a landing pad here would break unwinding from + * signal handlers. + * + * This trampoline is used only for signal return and not via an indirect + * call/jump from userspace, so adding CFI landing pad is unnecessary. + */ .text SYM_FUNC_START(__vdso_rt_sigreturn) .cfi_startproc .cfi_signal_frame - vdso_lpad li a7, __NR_rt_sigreturn ecall .cfi_endproc diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 5b1b3c88b4d130..3e450890be07e4 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -37,7 +37,9 @@ #include "../kernel/head.h" +#if defined(CONFIG_64BIT) && defined(CONFIG_MMU) DECLARE_BITMAP(new_valid_map_cpus, NR_CPUS); +#endif struct kernel_mapping kernel_map __ro_after_init; EXPORT_SYMBOL(kernel_map); diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c index f196b1d1ddf867..aed27604c11f0b 100644 --- a/arch/x86/boot/compressed/acpi.c +++ b/arch/x86/boot/compressed/acpi.c @@ -184,10 +184,15 @@ static unsigned long get_cmdline_acpi_rsdp(void) char val[MAX_ADDR_LEN] = { }; int ret; - ret = cmdline_find_option("acpi_rsdp", val, MAX_ADDR_LEN); + ret = cmdline_find_option("acpi_rsdp", val, sizeof(val)); if (ret < 0) return 0; + if (ret >= sizeof(val)) { + warn("acpi_rsdp= value too long; ignoring"); + return 0; + } + if (boot_kstrtoul(val, 16, &addr)) return 0; #endif diff --git a/arch/x86/boot/early_serial_console.c b/arch/x86/boot/early_serial_console.c index 023bf1c3de8b7a..5b83beab89e150 100644 --- a/arch/x86/boot/early_serial_console.c +++ b/arch/x86/boot/early_serial_console.c @@ -117,7 +117,7 @@ static unsigned int probe_baud(int port) static void parse_console_uart8250(void) { char optstr[64], *options; - int baud = DEFAULT_BAUD; + int baud; int port = 0; /* @@ -136,10 +136,13 @@ static void parse_console_uart8250(void) else return; - if (options && (options[0] == ',')) - baud = simple_strtoull(options + 1, &options, 0); - else + if (options && (options[0] == ',')) { + baud = simple_strtoull(options + 1, NULL, 0); + if (!baud) + baud = DEFAULT_BAUD; + } else { baud = probe_baud(port); + } if (port) early_serial_init(port, baud); diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index d2e8a849f18057..5b1070ec85d946 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -46,7 +46,6 @@ obj-$(CONFIG_CPU_SUP_HYGON) += hygon.o obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o -obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o obj-$(CONFIG_CPU_SUP_ZHAOXIN) += zhaoxin.o obj-$(CONFIG_CPU_SUP_VORTEX_32) += vortex.o diff --git a/block/bio.c b/block/bio.c index f2a5f4d0a9672b..6a2f6fc3413e89 100644 --- a/block/bio.c +++ b/block/bio.c @@ -555,6 +555,14 @@ struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, bio = bio_alloc_percpu_cache(bs); } else { opf &= ~REQ_ALLOC_CACHE; + } + + /* + * For a bioset without a percpu cache, or when the percpu cache was + * empty, try a slab allocation with optimistic GFP_ flags before + * falling back to the mempool. + */ + if (!bio) { p = kmem_cache_alloc(bs->bio_slab, gfp); if (p) bio = p + bs->front_pad; @@ -1191,7 +1199,7 @@ void bio_iov_bvec_set(struct bio *bio, const struct iov_iter *iter) * for the next iteration. */ static int bio_iov_iter_align_down(struct bio *bio, struct iov_iter *iter, - unsigned len_align_mask) + struct bio_vec *bv, unsigned len_align_mask) { size_t nbytes = bio->bi_iter.bi_size & len_align_mask; @@ -1200,23 +1208,16 @@ static int bio_iov_iter_align_down(struct bio *bio, struct iov_iter *iter, iov_iter_revert(iter, nbytes); bio->bi_iter.bi_size -= nbytes; - do { - struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; - - if (nbytes < bv->bv_len) { - bv->bv_len -= nbytes; - break; - } - + while (nbytes >= bv->bv_len) { if (bio_flagged(bio, BIO_PAGE_PINNED)) unpin_user_page(bv->bv_page); - bio->bi_vcnt--; + if (!--bio->bi_vcnt) + return -EFAULT; nbytes -= bv->bv_len; - } while (nbytes); - - if (!bio->bi_vcnt) - return -EFAULT; + bv--; + } + bv->bv_len -= nbytes; return 0; } @@ -1276,7 +1277,8 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter, if (is_pci_p2pdma_page(bio->bi_io_vec->bv_page)) bio->bi_opf |= REQ_NOMERGE; - return bio_iov_iter_align_down(bio, iter, len_align_mask); + return bio_iov_iter_align_down(bio, iter, + &bio->bi_io_vec[bio->bi_vcnt - 1], len_align_mask); } static struct folio *folio_alloc_greedy(gfp_t gfp, size_t *size, @@ -1285,7 +1287,8 @@ static struct folio *folio_alloc_greedy(gfp_t gfp, size_t *size, struct folio *folio; while (*size > minsize) { - folio = folio_alloc(gfp | __GFP_NORETRY, get_order(*size)); + folio = folio_alloc(gfp | __GFP_NORETRY | __GFP_NOWARN, + get_order(*size)); if (folio) return folio; *size = rounddown_pow_of_two(*size - 1); @@ -1302,7 +1305,7 @@ static void bio_free_folios(struct bio *bio) bio_for_each_bvec_all(bv, bio, i) { struct folio *folio = bvec_folio(bv); - if (!is_zero_folio(folio)) + if (!is_zero_folio(folio) && !is_huge_zero_folio(folio)) folio_put(folio); } } @@ -1360,7 +1363,8 @@ static int bio_iov_iter_bounce_write(struct bio *bio, struct iov_iter *iter, if (!bio->bi_iter.bi_size) return -ENOMEM; - return bio_iov_iter_align_down(bio, iter, minsize - 1); + return bio_iov_iter_align_down(bio, iter, + &bio->bi_io_vec[bio->bi_vcnt - 1], minsize - 1); } static int bio_iov_iter_bounce_read(struct bio *bio, struct iov_iter *iter, @@ -1368,21 +1372,18 @@ static int bio_iov_iter_bounce_read(struct bio *bio, struct iov_iter *iter, { size_t len = min3(iov_iter_count(iter), maxlen, SZ_1M); struct folio *folio; + ssize_t ret; folio = folio_alloc_greedy(GFP_KERNEL, &len, minsize); if (!folio) return -ENOMEM; do { - ssize_t ret; - ret = iov_iter_extract_bvecs(iter, bio->bi_io_vec + 1, len, &bio->bi_vcnt, bio->bi_max_vecs - 1, 0); if (ret <= 0) { - if (!bio->bi_vcnt) { - folio_put(folio); - return ret; - } + if (!bio->bi_vcnt) + goto out_folio_put; break; } len -= ret; @@ -1398,7 +1399,20 @@ static int bio_iov_iter_bounce_read(struct bio *bio, struct iov_iter *iter, bvec_set_folio(&bio->bi_io_vec[0], folio, bio->bi_iter.bi_size, 0); if (iov_iter_extract_will_pin(iter)) bio_set_flag(bio, BIO_PAGE_PINNED); - return bio_iov_iter_align_down(bio, iter, minsize - 1); + + /* The first vec stores the bounce buffer, so do not subtract 1 here. */ + ret = bio_iov_iter_align_down(bio, iter, + &bio->bi_io_vec[bio->bi_vcnt], minsize - 1); + if (ret) + goto out_folio_put; + + /* Update the bounc buffer bv_len to the aligned down size. */ + bio->bi_io_vec[0].bv_len = bio->bi_iter.bi_size; + return 0; + +out_folio_put: + folio_put(folio); + return ret; } /** diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index d2a1f5903f248a..d9676126c5b5da 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -434,15 +434,15 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct gendisk *disk, blkg->pd[i]->online = true; } } + blkg->online = true; } - blkg->online = true; spin_unlock(&blkcg->lock); if (!ret) return blkg; /* @blkg failed fully initialized, use the usual release path */ - blkg_put(blkg); + percpu_ref_kill(&blkg->refcnt); return ERR_PTR(ret); err_free_blkg: diff --git a/block/blk-map.c b/block/blk-map.c index 768549f19f97ec..d1d6bbe0ecf1f9 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -653,6 +653,7 @@ int blk_rq_map_kern(struct request *rq, void *kbuf, unsigned int len, gfp_t gfp_mask) { unsigned long addr = (unsigned long) kbuf; + bool do_copy; struct bio *bio; int ret; @@ -661,7 +662,8 @@ int blk_rq_map_kern(struct request *rq, void *kbuf, unsigned int len, if (!len || !kbuf) return -EINVAL; - if (!blk_rq_aligned(rq->q, addr, len) || object_is_on_stack(kbuf)) + do_copy = !blk_rq_aligned(rq->q, addr, len) || object_is_on_stack(kbuf); + if (do_copy) bio = bio_copy_kern(rq, kbuf, len, gfp_mask); else bio = bio_map_kern(rq, kbuf, len, gfp_mask); @@ -670,8 +672,11 @@ int blk_rq_map_kern(struct request *rq, void *kbuf, unsigned int len, return PTR_ERR(bio); ret = blk_rq_append_bio(rq, bio); - if (unlikely(ret)) + if (unlikely(ret)) { + if (do_copy) + bio_free_pages(bio); blk_mq_map_bio_put(bio); + } return ret; } EXPORT_SYMBOL(blk_rq_map_kern); diff --git a/block/blk.h b/block/blk.h index fb95d3c58950c1..eaac05815cb036 100644 --- a/block/blk.h +++ b/block/blk.h @@ -717,6 +717,7 @@ static inline int req_ref_read(struct request *req) static inline u64 blk_time_get_ns(void) { struct blk_plug *plug = current->plug; + u64 now; if (!plug || !in_task()) return ktime_get_ns(); @@ -725,12 +726,18 @@ static inline u64 blk_time_get_ns(void) * 0 could very well be a valid time, but rather than flag "this is * a valid timestamp" separately, just accept that we'll do an extra * ktime_get_ns() if we just happen to get 0 as the current time. + * + * cur_ktime can be zeroed by pre-emption the moment PF_BLOCK_TS is set. */ - if (!plug->cur_ktime) { - plug->cur_ktime = ktime_get_ns(); + now = READ_ONCE(plug->cur_ktime); + if (!now) { + now = ktime_get_ns(); + WRITE_ONCE(plug->cur_ktime, now); + /* Ensure PF_BLOCK_TS is set after cur_ktime. */ + barrier(); current->flags |= PF_BLOCK_TS; } - return plug->cur_ktime; + return now; } static inline ktime_t blk_time_get(void) diff --git a/block/elevator.c b/block/elevator.c index 3bcd37c2aa3401..2161b6eea680ca 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -812,8 +812,13 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *buf, * reference during concurrent disk deletion: * update_nr_hwq_lock -> kn->active (via del_gendisk -> kobject_del) * kn->active -> update_nr_hwq_lock (via this sysfs write path) + * + * Use the writer lock instead of the reader lock of update_nr_hwq_lock + * to serialize the two-stage elevator switch steps in + * elevator_change(): the core switch step under the elevator lock and + * the elevator_change_done() step outside the elevator lock. */ - if (!down_read_trylock(&set->update_nr_hwq_lock)) { + if (!down_write_trylock(&set->update_nr_hwq_lock)) { ret = -EBUSY; goto out; } @@ -824,7 +829,7 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *buf, } else { ret = -ENOENT; } - up_read(&set->update_nr_hwq_lock); + up_write(&set->update_nr_hwq_lock); out: if (ctx.type) diff --git a/block/error-injection.c b/block/error-injection.c index cfb83138960c86..e14bc4b723efb0 100644 --- a/block/error-injection.c +++ b/block/error-injection.c @@ -276,9 +276,10 @@ static int blk_error_injection_show(struct seq_file *s, void *private) rcu_read_lock(); list_for_each_entry_rcu(inj, &disk->error_injection_list, entry) { - seq_printf(s, "%llu:%llu status=%s,chance=%u", - inj->start, inj->end, - blk_status_to_tag(inj->status), inj->chance); + seq_printf(s, "%llu:%llu op=%s,status=%s,chance=%u", + inj->start, inj->end, + blk_op_str(inj->op), + blk_status_to_tag(inj->status), inj->chance); seq_putc(s, '\n'); } rcu_read_unlock(); diff --git a/block/partitions/aix.c b/block/partitions/aix.c index f3c4174e003e9d..689837deba279b 100644 --- a/block/partitions/aix.c +++ b/block/partitions/aix.c @@ -208,7 +208,14 @@ int aix_partition(struct parsed_partitions *state) if (n) { int foundlvs = 0; - for (i = 0; foundlvs < numlvs && i < state->limit; i += 1) { + /* + * The lvd array was read as a single sector; only the + * struct lvd entries that fit in it are valid. Bound the + * scan so an on-disk numlvs larger than that cannot walk + * the read buffer out of bounds. + */ + for (i = 0; foundlvs < numlvs && i < state->limit && + i < SECTOR_SIZE / (int)sizeof(struct lvd); i++) { lvip[i].pps_per_lv = be16_to_cpu(p[i].num_lps); if (lvip[i].pps_per_lv) foundlvs += 1; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 310de0463beb14..1faecef330092b 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1113,6 +1113,7 @@ static void __loop_clr_fd(struct loop_device *lo) struct queue_limits lim; struct file *filp; gfp_t gfp = lo->old_gfp_mask; + int err; spin_lock_irq(&lo->lo_lock); filp = lo->lo_backing_file; @@ -1146,26 +1147,21 @@ static void __loop_clr_fd(struct loop_device *lo) disk_force_media_change(lo->lo_disk); - if (lo->lo_flags & LO_FLAGS_PARTSCAN) { - int err; - - /* - * open_mutex has been held already in release path, so don't - * acquire it if this function is called in such case. - * - * If the reread partition isn't from release path, lo_refcnt - * must be at least one and it can only become zero when the - * current holder is released. - */ - err = bdev_disk_changed(lo->lo_disk, false); - if (err) - pr_warn("%s: partition scan of loop%d failed (rc=%d)\n", - __func__, lo->lo_number, err); - /* Device is gone, no point in returning error */ - } + /* + * Remove all partitions, including partitions added manually with + * BLKPG, which may exist even if LO_FLAGS_PARTSCAN is not set. + * + * open_mutex has been held already in release path, so don't acquire + * it here. + */ + err = bdev_disk_changed(lo->lo_disk, false); + if (err) + pr_warn("%s: partition scan of loop%d failed (rc=%d)\n", + __func__, lo->lo_number, err); + /* Device is gone, no point in returning error */ /* - * lo->lo_state is set to Lo_unbound here after above partscan has + * lo->lo_state is set to Lo_unbound here after removing partitions has * finished. There cannot be anybody else entering __loop_clr_fd() as * Lo_rundown state protects us from all the other places trying to * change the 'lo' device. diff --git a/drivers/regulator/ltc3676.c b/drivers/regulator/ltc3676.c index 73d511eb1c1dce..768cdce0d4ecfb 100644 --- a/drivers/regulator/ltc3676.c +++ b/drivers/regulator/ltc3676.c @@ -45,11 +45,11 @@ #define LTC3676_DVBxA_REF_SELECT BIT(5) #define LTC3676_DVBxB_PGOOD_MASK BIT(5) -#define LTC3676_IRQSTAT_PGOOD_TIMEOUT BIT(3) -#define LTC3676_IRQSTAT_UNDERVOLT_WARN BIT(4) -#define LTC3676_IRQSTAT_UNDERVOLT_FAULT BIT(5) -#define LTC3676_IRQSTAT_THERMAL_WARN BIT(6) -#define LTC3676_IRQSTAT_THERMAL_FAULT BIT(7) +#define LTC3676_IRQSTAT_PGOOD_TIMEOUT BIT(2) +#define LTC3676_IRQSTAT_UNDERVOLT_WARN BIT(3) +#define LTC3676_IRQSTAT_UNDERVOLT_FAULT BIT(4) +#define LTC3676_IRQSTAT_THERMAL_WARN BIT(5) +#define LTC3676_IRQSTAT_THERMAL_FAULT BIT(6) enum ltc3676_reg { LTC3676_SW1, diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index aaba1a3ad57783..ecb0be39469651 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -382,12 +382,16 @@ static irqreturn_t cqspi_irq_handler(int this_irq, void *dev) /* Clear interrupt */ writel(irq_status, cqspi->iobase + CQSPI_REG_IRQSTATUS); - if (cqspi->use_dma_read && ddata && ddata->get_dma_status) - irq_status = ddata->get_dma_status(cqspi); - else if (cqspi->slow_sram) + if (cqspi->use_dma_read && ddata && ddata->get_dma_status) { + if (ddata->get_dma_status(cqspi)) { + complete(&cqspi->transfer_complete); + return IRQ_HANDLED; + } + } else if (cqspi->slow_sram) { irq_status &= CQSPI_IRQ_MASK_RD_SLOW_SRAM | CQSPI_IRQ_MASK_WR; - else + } else { irq_status &= CQSPI_IRQ_MASK_RD | CQSPI_IRQ_MASK_WR; + } if (irq_status) complete(&cqspi->transfer_complete); diff --git a/drivers/spi/spi-dw-dma.c b/drivers/spi/spi-dw-dma.c index bd70a7ed8067dc..f7d848fec9ab6d 100644 --- a/drivers/spi/spi-dw-dma.c +++ b/drivers/spi/spi-dw-dma.c @@ -282,7 +282,8 @@ static int dw_spi_dma_wait(struct dw_spi *dws, unsigned int len, u32 speed) static inline bool dw_spi_dma_tx_busy(struct dw_spi *dws) { - return !(dw_readl(dws, DW_SPI_SR) & DW_SPI_SR_TF_EMPT); + return (dw_readl(dws, DW_SPI_SR) & + (DW_SPI_SR_BUSY | DW_SPI_SR_TF_EMPT)) != DW_SPI_SR_TF_EMPT; } static int dw_spi_dma_wait_tx_done(struct dw_spi *dws, diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 088b3a0e6ce6cc..581ac799d97495 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -1017,10 +1017,6 @@ static int virtballoon_probe(struct virtio_device *vdev) unsigned int capacity; capacity = virtqueue_get_vring_size(vb->reporting_vq); - if (capacity < PAGE_REPORTING_CAPACITY) { - err = -ENOSPC; - goto out_unregister_oom; - } vb->pr_dev_info.order = PAGE_REPORTING_ORDER_UNSPECIFIED; @@ -1041,6 +1037,7 @@ static int virtballoon_probe(struct virtio_device *vdev) vb->pr_dev_info.order = 5; #endif + vb->pr_dev_info.capacity = capacity; err = page_reporting_register(&vb->pr_dev_info); if (err) goto out_unregister_oom; diff --git a/fs/fat/fat.h b/fs/fat/fat.h index 99ed9228a677be..2772675bd35a36 100644 --- a/fs/fat/fat.h +++ b/fs/fat/fat.h @@ -249,13 +249,13 @@ static inline unsigned char fat_checksum(const __u8 *name) return s; } -static inline sector_t fat_clus_to_blknr(struct msdos_sb_info *sbi, int clus) +static inline sector_t fat_clus_to_blknr(const struct msdos_sb_info *sbi, int clus) { return ((sector_t)clus - FAT_START_ENT) * sbi->sec_per_clus + sbi->data_start; } -static inline void fat_get_blknr_offset(struct msdos_sb_info *sbi, +static inline void fat_get_blknr_offset(const struct msdos_sb_info *sbi, loff_t i_pos, sector_t *blknr, int *offset) { *blknr = i_pos >> sbi->dir_per_block_bits; diff --git a/fs/fat/fat_test.c b/fs/fat/fat_test.c index 4eeed9dca54940..9583ce66dca3cd 100644 --- a/fs/fat/fat_test.c +++ b/fs/fat/fat_test.c @@ -22,7 +22,7 @@ static void fat_checksum_test(struct kunit *test) static void fat_clus_to_blknr_test(struct kunit *test) { - struct msdos_sb_info sbi = { + static const struct msdos_sb_info sbi = { .sec_per_clus = 4, .data_start = 100, }; @@ -34,7 +34,7 @@ static void fat_clus_to_blknr_test(struct kunit *test) static void fat_get_blknr_offset_test(struct kunit *test) { - struct msdos_sb_info sbi = { + static const struct msdos_sb_info sbi = { .dir_per_block = 16, .dir_per_block_bits = 4, }; diff --git a/include/linux/damon.h b/include/linux/damon.h index 02ac34537df9a7..cfbbf8ba28f632 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -1,8 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * DAMON api - * - * Author: SeongJae Park */ #ifndef _DAMON_H_ diff --git a/include/linux/page_reporting.h b/include/linux/page_reporting.h index 9d4ca5c218a0fb..272b1274efdc1c 100644 --- a/include/linux/page_reporting.h +++ b/include/linux/page_reporting.h @@ -5,7 +5,6 @@ #include #include -/* This value should always be a power of 2, see page_reporting_cycle() */ #define PAGE_REPORTING_CAPACITY 32 #define PAGE_REPORTING_ORDER_UNSPECIFIED -1 @@ -22,6 +21,9 @@ struct page_reporting_dev_info { /* Minimal order of page reporting */ unsigned int order; + + /* Max pages per report batch; 0 (default) means PAGE_REPORTING_CAPACITY */ + unsigned int capacity; }; /* Tear-down and bring-up for page reporting devices */ diff --git a/include/trace/events/memory-failure.h b/include/trace/events/memory-failure.h index aa57cc8f896bed..7a8ee5d1a44e4d 100644 --- a/include/trace/events/memory-failure.h +++ b/include/trace/events/memory-failure.h @@ -1,6 +1,10 @@ /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM -#define TRACE_SYSTEM memory_failure +/* + * For historical versions, memory_failure_event is in ras subsystem, + * some user programs depend on it. + */ +#define TRACE_SYSTEM ras #define TRACE_INCLUDE_FILE memory-failure #if !defined(_TRACE_MEMORY_FAILURE_H) || defined(TRACE_HEADER_MULTI_READ) diff --git a/io_uring/bpf-ops.c b/io_uring/bpf-ops.c index 5a50f0675fe58f..cf2bd068e331b5 100644 --- a/io_uring/bpf-ops.c +++ b/io_uring/bpf-ops.c @@ -168,6 +168,8 @@ static int io_install_bpf(struct io_ring_ctx *ctx, struct io_uring_bpf_ops *ops) if (ctx->bpf_ops) return -EBUSY; + if (ops->priv) + return -EBUSY; if (WARN_ON_ONCE(!ops->loop_step)) return -EINVAL; diff --git a/io_uring/fs.c b/io_uring/fs.c index d0580c754bf867..26ea841a22e700 100644 --- a/io_uring/fs.c +++ b/io_uring/fs.c @@ -110,7 +110,8 @@ int io_unlinkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) const char __user *fname; int err; - if (sqe->off || sqe->len || sqe->buf_index || sqe->splice_fd_in) + if (sqe->off || sqe->len || sqe->buf_index || sqe->splice_fd_in || + sqe->addr3 || sqe->__pad2[0]) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index b6b969b55e1224..de0129bceaba30 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -328,8 +328,8 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg, buf = io_ring_head_to_buf(br, ++head, bl->mask); } while (--nr_iovs); - if (arg->mode & KBUF_MODE_FREE) - kfree(arg->iovs); + if (arg->iovs != org_iovs && (arg->mode & KBUF_MODE_FREE)) + kfree(org_iovs); if (head == tail) req->flags |= REQ_F_BL_EMPTY; diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 40cfb38ac919d2..d459bef245f4a7 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -878,6 +878,7 @@ int rhashtable_walk_start_check(struct rhashtable_iter *iter) iter->walker.tbl = rht_dereference_rcu(ht->tbl, ht); iter->slot = 0; iter->skip = 0; + iter->p = NULL; return -EAGAIN; } diff --git a/mm/damon/core.c b/mm/damon/core.c index 7e4b9affc5b060..cff932b3317d08 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * Data Access Monitor - * - * Author: SeongJae Park */ #define pr_fmt(fmt) "damon: " fmt @@ -356,8 +354,21 @@ int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges, { struct damon_region *r, *next; unsigned int i; + unsigned long last_end; int err; + for (i = 0; i < nr_ranges; i++) { + unsigned long start, end; + + start = ALIGN_DOWN(ranges[i].start, min_region_sz); + end = ALIGN(ranges[i].end, min_region_sz); + if (start >= end) + return -EINVAL; + if (i > 0 && last_end > start) + return -EINVAL; + last_end = end; + } + /* Remove regions which are not in the new ranges */ damon_for_each_region_safe(r, next, t) { for (i = 0; i < nr_ranges; i++) { diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c index 8298c6001fd097..32f41491b726b2 100644 --- a/mm/damon/lru_sort.c +++ b/mm/damon/lru_sort.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * DAMON-based LRU-lists Sorting - * - * Author: SeongJae Park */ #define pr_fmt(fmt) "damon-lru-sort: " fmt diff --git a/mm/damon/modules-common.c b/mm/damon/modules-common.c index 86d58f8c4f6358..f87fa46a95a088 100644 --- a/mm/damon/modules-common.c +++ b/mm/damon/modules-common.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * Common Code for DAMON Modules - * - * Author: SeongJae Park */ #include diff --git a/mm/damon/modules-common.h b/mm/damon/modules-common.h index f103ad55636872..6fd45490e45b63 100644 --- a/mm/damon/modules-common.h +++ b/mm/damon/modules-common.h @@ -1,8 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Common Code for DAMON Modules - * - * Author: SeongJae Park */ #include diff --git a/mm/damon/ops-common.c b/mm/damon/ops-common.c index d1842e2b00ef83..6bdd1cfd3863a3 100644 --- a/mm/damon/ops-common.c +++ b/mm/damon/ops-common.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * Common Code for Data Access Monitoring - * - * Author: SeongJae Park */ #include diff --git a/mm/damon/ops-common.h b/mm/damon/ops-common.h index 5efa5b5970def7..38d295488fa181 100644 --- a/mm/damon/ops-common.h +++ b/mm/damon/ops-common.h @@ -1,8 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Common Code for Data Access Monitoring - * - * Author: SeongJae Park */ #include diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index d0598f5f268822..5c2da45f988cf9 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * DAMON Code for The Physical Address Space - * - * Author: SeongJae Park */ #define pr_fmt(fmt) "damon-pa: " fmt diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c index ce4499cf4b8b05..11b70d0a9a6f0a 100644 --- a/mm/damon/reclaim.c +++ b/mm/damon/reclaim.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * DAMON-based page reclamation - * - * Author: SeongJae Park */ #define pr_fmt(fmt) "damon-reclaim: " fmt diff --git a/mm/damon/sysfs-common.c b/mm/damon/sysfs-common.c index bdc6ae2639e4f9..c59d7bf7a73ae0 100644 --- a/mm/damon/sysfs-common.c +++ b/mm/damon/sysfs-common.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * Common Code for DAMON Sysfs Interface - * - * Author: SeongJae Park */ #include diff --git a/mm/damon/sysfs-common.h b/mm/damon/sysfs-common.h index 3079306966a910..733764716e8dd9 100644 --- a/mm/damon/sysfs-common.h +++ b/mm/damon/sysfs-common.h @@ -1,8 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Common Code for DAMON Sysfs Interface - * - * Author: SeongJae Park */ #include diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index 0134111c3c1ff6..3cbeccd436e40f 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * DAMON sysfs Interface - * - * Copyright (c) 2022 SeongJae Park */ #include diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index 2e95e3bac774dc..a9e187158067d4 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * DAMON sysfs Interface - * - * Copyright (c) 2022 SeongJae Park */ #include diff --git a/mm/damon/tests/core-kunit.h b/mm/damon/tests/core-kunit.h index 1cfb8c176b873e..fcf7c7fadb5fe5 100644 --- a/mm/damon/tests/core-kunit.h +++ b/mm/damon/tests/core-kunit.h @@ -1,10 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Data Access Monitor Unit Tests - * - * Copyright 2019 Amazon.com, Inc. or its affiliates. All rights reserved. - * - * Author: SeongJae Park */ #ifdef CONFIG_DAMON_KUNIT_TEST diff --git a/mm/damon/tests/sysfs-kunit.h b/mm/damon/tests/sysfs-kunit.h index f9ec5e795b34b6..138a4b8d14e734 100644 --- a/mm/damon/tests/sysfs-kunit.h +++ b/mm/damon/tests/sysfs-kunit.h @@ -1,8 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Data Access Monitor Unit Tests - * - * Author: SeongJae Park */ #ifdef CONFIG_DAMON_SYSFS_KUNIT_TEST diff --git a/mm/damon/tests/vaddr-kunit.h b/mm/damon/tests/vaddr-kunit.h index 563fbc7e3f4483..61f844336ffb50 100644 --- a/mm/damon/tests/vaddr-kunit.h +++ b/mm/damon/tests/vaddr-kunit.h @@ -1,10 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Data Access Monitor Unit Tests - * - * Copyright 2019 Amazon.com, Inc. or its affiliates. All rights reserved. - * - * Author: SeongJae Park */ #ifdef CONFIG_DAMON_VADDR_KUNIT_TEST diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index d271476035641b..e73ec1ce016e5b 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * DAMON Code for Virtual Address Spaces - * - * Author: SeongJae Park */ #define pr_fmt(fmt) "damon-va: " fmt diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2bccb0a53a0a60..b5d1e9d4463d00 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3587,10 +3587,6 @@ static void __split_folio_to_order(struct folio *folio, int old_order, (1L << PG_dropbehind) | LRU_GEN_MASK | LRU_REFS_MASK)); - if (handle_hwpoison && - page_range_has_hwpoisoned(new_head, new_nr_pages)) - folio_set_has_hwpoisoned(new_folio); - new_folio->mapping = folio->mapping; new_folio->index = folio->index + i; @@ -3612,6 +3608,14 @@ static void __split_folio_to_order(struct folio *folio, int old_order, folio_set_large_rmappable(new_folio); } + /* + * PG_has_hwpoisoned is on the 2nd page, so set it after + * the compound head is prepped. + */ + if (handle_hwpoison && + page_range_has_hwpoisoned(new_head, new_nr_pages)) + folio_set_has_hwpoisoned(new_folio); + if (folio_test_young(folio)) folio_set_young(new_folio); if (folio_test_idle(folio)) diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 7c7ba17ce7af00..e196f53f9b4620 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -687,7 +687,7 @@ static struct kmemleak_object *__alloc_object(gfp_t gfp) atomic_set(&object->use_count, 1); object->excess_ref = 0; object->count = 0; /* white color initially */ - object->checksum = 0; + object->checksum = ~0; object->del_state = 0; /* task information */ @@ -981,7 +981,7 @@ static void reset_checksum(unsigned long ptr) } raw_spin_lock_irqsave(&object->lock, flags); - object->checksum = 0; + object->checksum = ~0; raw_spin_unlock_irqrestore(&object->lock, flags); put_object(object); } @@ -1410,7 +1410,8 @@ static bool update_checksum(struct kmemleak_object *object) for_each_possible_cpu(cpu) { void *ptr = per_cpu_ptr((void __percpu *)object->pointer, cpu); - object->checksum ^= crc32(0, kasan_reset_tag((void *)ptr), object->size); + object->checksum = crc32(object->checksum, + kasan_reset_tag((void *)ptr), object->size); } } else { object->checksum = crc32(0, kasan_reset_tag((void *)object->pointer), object->size); diff --git a/mm/page_reporting.c b/mm/page_reporting.c index 7418f2e500bb48..942e84b6908af7 100644 --- a/mm/page_reporting.c +++ b/mm/page_reporting.c @@ -173,11 +173,8 @@ page_reporting_cycle(struct page_reporting_dev_info *prdev, struct zone *zone, * any pages that may have already been present from the previous * list processed. This should result in us reporting all pages on * an idle system in about 30 seconds. - * - * The division here should be cheap since PAGE_REPORTING_CAPACITY - * should always be a power of 2. */ - budget = DIV_ROUND_UP(area->nr_free, PAGE_REPORTING_CAPACITY * 16); + budget = DIV_ROUND_UP(area->nr_free, prdev->capacity * 16); /* loop through free list adding unreported pages to sg list */ list_for_each_entry_safe(page, next, list, lru) { @@ -222,10 +219,10 @@ page_reporting_cycle(struct page_reporting_dev_info *prdev, struct zone *zone, spin_unlock_irq(&zone->lock); /* begin processing pages in local list */ - err = prdev->report(prdev, sgl, PAGE_REPORTING_CAPACITY); + err = prdev->report(prdev, sgl, prdev->capacity); /* reset offset since the full list was reported */ - *offset = PAGE_REPORTING_CAPACITY; + *offset = prdev->capacity; /* update budget to reflect call to report function */ budget--; @@ -234,7 +231,7 @@ page_reporting_cycle(struct page_reporting_dev_info *prdev, struct zone *zone, spin_lock_irq(&zone->lock); /* flush reported pages from the sg list */ - page_reporting_drain(prdev, sgl, PAGE_REPORTING_CAPACITY, !err); + page_reporting_drain(prdev, sgl, prdev->capacity, !err); /* * Reset next to first entry, the old next isn't valid @@ -260,13 +257,13 @@ static int page_reporting_process_zone(struct page_reporting_dev_info *prdev, struct scatterlist *sgl, struct zone *zone) { - unsigned int order, mt, leftover, offset = PAGE_REPORTING_CAPACITY; + unsigned int order, mt, leftover, offset = prdev->capacity; unsigned long watermark; int err = 0; /* Generate minimum watermark to be able to guarantee progress */ watermark = low_wmark_pages(zone) + - (PAGE_REPORTING_CAPACITY << page_reporting_order); + (prdev->capacity << page_reporting_order); /* * Cancel request if insufficient free memory or if we failed @@ -290,7 +287,7 @@ page_reporting_process_zone(struct page_reporting_dev_info *prdev, } /* report the leftover pages before going idle */ - leftover = PAGE_REPORTING_CAPACITY - offset; + leftover = prdev->capacity - offset; if (leftover) { sgl = &sgl[offset]; err = prdev->report(prdev, sgl, leftover); @@ -322,11 +319,11 @@ static void page_reporting_process(struct work_struct *work) atomic_set(&prdev->state, state); /* allocate scatterlist to store pages being reported on */ - sgl = kmalloc_objs(*sgl, PAGE_REPORTING_CAPACITY); + sgl = kmalloc_objs(*sgl, prdev->capacity); if (!sgl) goto err_out; - sg_init_table(sgl, PAGE_REPORTING_CAPACITY); + sg_init_table(sgl, prdev->capacity); for_each_zone(zone) { err = page_reporting_process_zone(prdev, sgl, zone); @@ -377,6 +374,9 @@ int page_reporting_register(struct page_reporting_dev_info *prdev) page_reporting_order = pageblock_order; } + if (!prdev->capacity || prdev->capacity > PAGE_REPORTING_CAPACITY) + prdev->capacity = PAGE_REPORTING_CAPACITY; + /* initialize state and work structures */ atomic_set(&prdev->state, PAGE_REPORTING_IDLE); INIT_DELAYED_WORK(&prdev->work, &page_reporting_process); diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 2ccbabfb2cc17a..bac2eb5de63d61 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -243,21 +243,31 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) */ pmde = pmdp_get_lockless(pvmw->pmd); - if (pmd_trans_huge(pmde) || pmd_is_migration_entry(pmde)) { + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && + (pmd_trans_huge(pmde) || pmd_is_migration_entry(pmde) || + pmd_is_device_private_entry(pmde))) { pvmw->ptl = pmd_lock(mm, pvmw->pmd); pmde = *pvmw->pmd; - if (!pmd_present(pmde)) { + if (pmd_is_migration_entry(pmde)) { softleaf_t entry; - if (!thp_migration_supported() || - !(pvmw->flags & PVMW_MIGRATION)) + if (!(pvmw->flags & PVMW_MIGRATION)) return not_found(pvmw); entry = softleaf_from_pmd(pmde); + if (!check_pmd(softleaf_to_pfn(entry), pvmw)) + return not_found(pvmw); + return true; + } else if (pmd_is_device_private_entry(pmde)) { + softleaf_t entry; - if (!softleaf_is_migration(entry) || - !check_pmd(softleaf_to_pfn(entry), pvmw)) + if (pvmw->flags & PVMW_MIGRATION) + return not_found(pvmw); + entry = softleaf_from_pmd(pmde); + if (!check_pmd(softleaf_to_pfn(entry), pvmw)) return not_found(pvmw); return true; + } else if (!pmd_present(pmde)) { + return not_found(pvmw); } if (likely(pmd_trans_huge(pmde))) { if (pvmw->flags & PVMW_MIGRATION) @@ -266,17 +276,10 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) return not_found(pvmw); return true; } - /* THP pmd was split under us: handle on pte level */ + /* THP/device-private pmd was split under us: handle on pte level */ spin_unlock(pvmw->ptl); pvmw->ptl = NULL; } else if (!pmd_present(pmde)) { - const softleaf_t entry = softleaf_from_pmd(pmde); - - if (softleaf_is_device_private(entry)) { - pvmw->ptl = pmd_lock(mm, pvmw->pmd); - return true; - } - if ((pvmw->flags & PVMW_SYNC) && thp_vma_suitable_order(vma, pvmw->address, PMD_ORDER) && diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 99e2be39671b63..ebd3ac997f645b 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -564,6 +564,8 @@ struct page * __meminit __populate_section_memmap(unsigned long pfn, if (r < 0) return NULL; + flush_cache_vmap(start, end); + return pfn_to_page(pfn); } diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 246af12bf80142..c3adedaaf7d547 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -2111,7 +2111,10 @@ static bool vma_can_userfault(struct vm_area_struct *vma, vm_flags_t vm_flags, { const struct vm_uffd_ops *ops = vma_uffd_ops(vma); - if (vma->vm_flags & VM_DROPPABLE) + if (vma->vm_flags & (VM_DROPPABLE | VM_SHADOW_STACK)) + return false; + + if (!is_vm_hugetlb_page(vma) && (vma->vm_flags & VM_SPECIAL)) return false; vm_flags &= __VM_UFFD_FLAGS;