diff options
157 files changed, 4125 insertions, 2294 deletions
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-damon b/Documentation/ABI/testing/sysfs-kernel-mm-damon index 420b30f09cf0..b35649a46a2f 100644 --- a/Documentation/ABI/testing/sysfs-kernel-mm-damon +++ b/Documentation/ABI/testing/sysfs-kernel-mm-damon @@ -151,6 +151,13 @@ Contact: SeongJae Park <[email protected]> Description: Writing to and reading from this file sets and gets the action of the scheme. +What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/apply_interval_us +Date: Sep 2023 +Contact: SeongJae Park <[email protected]> +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/<K>/contexts/<C>/schemes/<S>/access_pattern/sz/min Date: Mar 2022 Contact: SeongJae Park <[email protected]> diff --git a/Documentation/admin-guide/cgroup-v1/memory.rst b/Documentation/admin-guide/cgroup-v1/memory.rst index ff456871bf4b..ca7d9402f6be 100644 --- a/Documentation/admin-guide/cgroup-v1/memory.rst +++ b/Documentation/admin-guide/cgroup-v1/memory.rst @@ -551,6 +551,7 @@ memory.stat file includes following statistics: event happens each time a page is unaccounted from the cgroup. swap # of bytes of swap usage + swapcached # of bytes of swap cached in memory dirty # of bytes that are waiting to get written back to the disk. writeback # of bytes of file/anon cache that are queued for syncing to disk. diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index b26b5274eaaf..622a7f28db1f 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1532,6 +1532,15 @@ PAGE_SIZE multiple when read back. collapsing an existing range of pages. This counter is not present when CONFIG_TRANSPARENT_HUGEPAGE is not set. + thp_swpout (npn) + Number of transparent hugepages which are swapout in one piece + without splitting. + + thp_swpout_fallback (npn) + Number of transparent hugepages which were split before swapout. + Usually because failed to allocate some continuous swap space + for the huge page. + memory.numa_stat A read-only nested-keyed file which exists on non-root cgroups. diff --git a/Documentation/admin-guide/mm/damon/usage.rst b/Documentation/admin-guide/mm/damon/usage.rst index 8da1b7281827..8507a6e45d86 100644 --- a/Documentation/admin-guide/mm/damon/usage.rst +++ b/Documentation/admin-guide/mm/damon/usage.rst @@ -20,18 +20,18 @@ DAMON provides below interfaces for different users. 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 <https://github.com/awslabs/damo>`_ is one example of such programs. -- *debugfs interface. (DEPRECATED!)* - :ref:`This <debugfs_interface>` is almost identical to :ref:`sysfs interface - <sysfs_interface>`. This is deprecated, so users should move to the - :ref:`sysfs interface <sysfs_interface>`. If you depend on this and cannot - move, please report your usecase to [email protected] and - *Kernel Space Programming Interface.* :doc:`This </mm/damon/api>` is for kernel space programmers. Using this, users can utilize every feature of DAMON most flexibly and efficiently by writing kernel space DAMON application programs for you. You can even extend DAMON for various address spaces. For detail, please refer to the interface :doc:`document </mm/damon/api>`. +- *debugfs interface. (DEPRECATED!)* + :ref:`This <debugfs_interface>` is almost identical to :ref:`sysfs interface + <sysfs_interface>`. This is deprecated, so users should move to the + :ref:`sysfs interface <sysfs_interface>`. If you depend on this and cannot + move, please report your usecase to [email protected] and .. _sysfs_interface: @@ -76,7 +76,7 @@ comma (","). :: │ │ │ │ │ │ │ │ ... │ │ │ │ │ │ ... │ │ │ │ │ schemes/nr_schemes - │ │ │ │ │ │ 0/action + │ │ │ │ │ │ 0/action,apply_interval_us │ │ │ │ │ │ │ access_pattern/ │ │ │ │ │ │ │ │ sz/min,max │ │ │ │ │ │ │ │ nr_accesses/min,max @@ -105,14 +105,12 @@ 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 +controlling the kdamonds (refer to +:ref:`design <damon_design_execution_model_and_data_structures>` for more +details) exists. 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/<N>/ @@ -150,9 +148,10 @@ kdamonds/<N>/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. +``0`` to ``N-1``. Each directory represents each monitoring context (refer to +:ref:`design <damon_design_execution_model_and_data_structures>` for more +details). At the moment, only one context per kdamond is supported, so only +``0`` or ``1`` can be written to the file. .. _sysfs_contexts: @@ -270,8 +269,8 @@ schemes/<N>/ ------------ In each scheme directory, five directories (``access_pattern``, ``quotas``, -``watermarks``, ``filters``, ``stats``, and ``tried_regions``) and one file -(``action``) exist. +``watermarks``, ``filters``, ``stats``, and ``tried_regions``) and two files +(``action`` and ``apply_interval``) exist. The ``action`` file is for setting and getting the scheme's :ref:`action <damon_design_damos_action>`. The keywords that can be written to and read @@ -297,6 +296,9 @@ Note that support of each action depends on the running DAMON operations set - ``stat``: Do nothing but count the statistics. Supported by all operations sets. +The ``apply_interval_us`` file is for setting and getting the scheme's +:ref:`apply_interval <damon_design_damos>` in microseconds. + schemes/<N>/access_pattern/ --------------------------- @@ -392,7 +394,7 @@ pages of all memory cgroups except ``/having_care_already``.:: echo N > 1/matching Note that ``anon`` and ``memcg`` filters are currently supported only when -``paddr`` `implementation <sysfs_contexts>` is being used. +``paddr`` :ref:`implementation <sysfs_contexts>` is being used. Also, memory regions that are filtered out by ``addr`` or ``target`` filters are not counted as the scheme has tried to those, while regions that filtered @@ -495,6 +497,62 @@ Please note that it's highly recommended to use user space tools like `damo <https://github.com/awslabs/damo>`_ rather than manually reading and writing the files as above. Above is only for an example. +.. _tracepoint: + +Tracepoints for Monitoring Results +================================== + +Users can get the monitoring results via the :ref:`tried_regions +<sysfs_schemes_tried_regions>`. The interface is useful for getting a +snapshot, but it could be inefficient for fully recording all the monitoring +results. For the purpose, two trace points, namely ``damon:damon_aggregated`` +and ``damon:damos_before_apply``, are provided. ``damon:damon_aggregated`` +provides the whole monitoring results, while ``damon:damos_before_apply`` +provides the monitoring results for regions that each DAMON-based Operation +Scheme (:ref:`DAMOS <damon_design_damos>`) is gonna be applied. Hence, +``damon:damos_before_apply`` is more useful for recording internal behavior of +DAMOS, or DAMOS target access +:ref:`pattern <damon_design_damos_access_pattern>` based query-like efficient +monitoring results recording. + +While the monitoring is turned on, you could record the tracepoint events and +show results using tracepoint supporting tools like ``perf``. For example:: + + # echo on > monitor_on + # perf record -e damon:damon_aggregated & + # sleep 5 + # kill 9 $(pidof perf) + # echo off > monitor_on + # perf script + kdamond.0 46568 [027] 79357.842179: damon:damon_aggregated: target_id=0 nr_regions=11 122509119488-135708762112: 0 864 + [...] + +Each line of the perf script output represents each monitoring region. The +first five fields are as usual other tracepoint outputs. The sixth field +(``target_id=X``) shows the ide of the monitoring target of the region. The +seventh field (``nr_regions=X``) shows the total number of monitoring regions +for the target. The eighth field (``X-Y:``) shows the start (``X``) and end +(``Y``) addresses of the region in bytes. The ninth field (``X``) shows the +``nr_accesses`` of the region (refer to +:ref:`design <damon_design_region_based_sampling>` for more details of the +counter). Finally the tenth field (``X``) shows the ``age`` of the region +(refer to :ref:`design <damon_design_age_tracking>` for more details of the +counter). + +If the event was ``damon:damos_beofre_apply``, the ``perf script`` output would +be somewhat like below:: + + kdamond.0 47293 [000] 80801.060214: damon:damos_before_apply: ctx_idx=0 scheme_idx=0 target_idx=0 nr_regions=11 121932607488-135128711168: 0 136 + [...] + +Each line of the output represents each monitoring region that each DAMON-based +Operation Scheme was about to be applied at the traced time. The first five +fields are as usual. It shows the index of the DAMON context (``ctx_idx=X``) +of the scheme in the list of the contexts of the context's kdamond, the index +of the scheme (``scheme_idx=X``) in the list of the schemes of the context, in +addition to the output of ``damon_aggregated`` tracepoint. + + .. _debugfs_interface: debugfs Interface (DEPRECATED!) @@ -790,23 +848,3 @@ directory by putting the name of the context to the ``rm_contexts`` file. :: Note that ``mk_contexts``, ``rm_contexts``, and ``monitor_on`` files are in the root directory only. - - -.. _tracepoint: - -Tracepoint for Monitoring Results -================================= - -Users can get the monitoring results via the :ref:`tried_regions -<sysfs_schemes_tried_regions>` or a tracepoint, ``damon:damon_aggregated``. -While the tried regions directory is useful for getting a snapshot, the -tracepoint is useful for getting a full record of the results. While the -monitoring is turned on, you could record the tracepoint events and show -results using tracepoint supporting tools like ``perf``. For example:: - - # echo on > monitor_on - # perf record -e damon:damon_aggregated & - # sleep 5 - # kill 9 $(pidof perf) - # echo off > monitor_on - # perf script diff --git a/Documentation/admin-guide/mm/ksm.rst b/Documentation/admin-guide/mm/ksm.rst index 776f244bdae4..e59231ac6bb7 100644 --- a/Documentation/admin-guide/mm/ksm.rst +++ b/Documentation/admin-guide/mm/ksm.rst @@ -155,6 +155,15 @@ stable_node_chains_prune_millisecs scan. It's a noop if not a single KSM page hit the ``max_page_sharing`` yet. +smart_scan + Historically KSM checked every candidate page for each scan. It did + not take into account historic information. When smart scan is + enabled, pages that have previously not been de-duplicated get + skipped. How often these pages are skipped depends on how often + de-duplication has already been tried and failed. By default this + optimization is enabled. The ``pages_skipped`` metric shows how + effective the setting is. + The effectiveness of KSM and MADV_MERGEABLE is shown in ``/sys/kernel/mm/ksm/``: general_profit @@ -169,6 +178,8 @@ pages_unshared how many pages unique but repeatedly checked for merging pages_volatile how many pages changing too fast to be placed in a tree +pages_skipped + how many pages did the "smart" page scanning algorithm skip full_scans how many times all mergeable areas have been scanned stable_node_chains diff --git a/Documentation/mm/damon/design.rst b/Documentation/mm/damon/design.rst index a20383d01a95..1f7e0586b5fa 100644 --- a/Documentation/mm/damon/design.rst +++ b/Documentation/mm/damon/design.rst @@ -154,6 +154,8 @@ The monitoring overhead of this mechanism will arbitrarily increase as the size of the target workload grows. +.. _damon_design_region_based_sampling: + Region Based Sampling ~~~~~~~~~~~~~~~~~~~~~ @@ -163,9 +165,10 @@ assumption (pages in a region have the same access frequencies) is kept, only one page in the region is required to be checked. Thus, for each ``sampling interval``, DAMON randomly picks one page in each region, waits for one ``sampling interval``, checks whether the page is accessed meanwhile, and -increases the access frequency of the region if so. Therefore, the monitoring -overhead is controllable by setting the number of regions. DAMON allows users -to set the minimum and the maximum number of regions for the trade-off. +increases the access frequency counter of the region if so. The counter is +called ``nr_regions`` of the region. Therefore, the monitoring overhead is +controllable by setting the number of regions. DAMON allows users to set the +minimum and the maximum number of regions for the trade-off. This scheme, however, cannot preserve the quality of the output if the assumption is not guaranteed. @@ -190,6 +193,8 @@ In this way, DAMON provides its best-effort quality and minimal overhead while keeping the bounds users set for their trade-off. +.. _damon_design_age_tracking: + Age Tracking ~~~~~~~~~~~~ @@ -254,7 +259,8 @@ works, DAMON provides a feature called Data Access Monitoring-based Operation Schemes (DAMOS). It lets users specify their desired schemes at a high level. For such specifications, DAMON starts monitoring, finds regions having the access pattern of interest, and applies the user-desired operation actions -to the regions as soon as found. +to the regions, for every user-specified time interval called +``apply_interval``. .. _damon_design_damos_action: @@ -471,3 +477,15 @@ modules for proactive reclamation and LRU lists manipulation are provided. For more detail, please read the usage documents for those (:doc:`/admin-guide/mm/damon/reclaim` and :doc:`/admin-guide/mm/damon/lru_sort`). + + +.. _damon_design_execution_model_and_data_structures: + +Execution Model and Data Structures +=================================== + +The monitoring-related information including the monitoring request +specification and DAMON-based operation schemes are stored in a data structure +called DAMON ``context``. DAMON executes each context with a kernel thread +called ``kdamond``. Multiple kdamonds could run in parallel, for different +types of monitoring. diff --git a/Documentation/trace/postprocess/trace-vmscan-postprocess.pl b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl index e24c009789a0..048dc0dbce64 100644 --- a/Documentation/trace/postprocess/trace-vmscan-postprocess.pl +++ b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl @@ -107,14 +107,14 @@ GetOptions( ); # Defaults for dynamically discovered regex's -my $regex_direct_begin_default = 'order=([0-9]*) may_writepage=([0-9]*) gfp_flags=([A-Z_|]*)'; +my $regex_direct_begin_default = 'order=([0-9]*) gfp_flags=([A-Z_|]*)'; my $regex_direct_end_default = 'nr_reclaimed=([0-9]*)'; my $regex_kswapd_wake_default = 'nid=([0-9]*) order=([0-9]*)'; my $regex_kswapd_sleep_default = 'nid=([0-9]*)'; -my $regex_wakeup_kswapd_default = 'nid=([0-9]*) zid=([0-9]*) order=([0-9]*) gfp_flags=([A-Z_|]*)'; -my $regex_lru_isolate_default = 'isolate_mode=([0-9]*) classzone_idx=([0-9]*) order=([0-9]*) nr_requested=([0-9]*) nr_scanned=([0-9]*) nr_skipped=([0-9]*) nr_taken=([0-9]*) lru=([a-z_]*)'; +my $regex_wakeup_kswapd_default = 'nid=([0-9]*) order=([0-9]*) gfp_flags=([A-Z_|]*)'; +my $regex_lru_isolate_default = 'classzone=([0-9]*) order=([0-9]*) nr_requested=([0-9]*) nr_scanned=([0-9]*) nr_skipped=([0-9]*) nr_taken=([0-9]*) lru=([a-z_]*)'; my $regex_lru_shrink_inactive_default = 'nid=([0-9]*) nr_scanned=([0-9]*) nr_reclaimed=([0-9]*) nr_dirty=([0-9]*) nr_writeback=([0-9]*) nr_congested=([0-9]*) nr_immediate=([0-9]*) nr_activate_anon=([0-9]*) nr_activate_file=([0-9]*) nr_ref_keep=([0-9]*) nr_unmap_fail=([0-9]*) priority=([0-9]*) flags=([A-Z_|]*)'; -my $regex_lru_shrink_active_default = 'lru=([A-Z_]*) nr_scanned=([0-9]*) nr_rotated=([0-9]*) priority=([0-9]*)'; +my $regex_lru_shrink_active_default = 'lru=([A-Z_]*) nr_taken=([0-9]*) nr_active=([0-9]*) nr_deactivated=([0-9]*) nr_referenced=([0-9]*) priority=([0-9]*) flags=([A-Z_|]*)' ; my $regex_writepage_default = 'page=([0-9a-f]*) pfn=([0-9]*) flags=([A-Z_|]*)'; # Dyanically discovered regex @@ -184,8 +184,7 @@ sub generate_traceevent_regex { $regex_direct_begin = generate_traceevent_regex( "vmscan/mm_vmscan_direct_reclaim_begin", $regex_direct_begin_default, - "order", "may_writepage", - "gfp_flags"); + "order", "gfp_flags"); $regex_direct_end = generate_traceevent_regex( "vmscan/mm_vmscan_direct_reclaim_end", $regex_direct_end_default, @@ -201,11 +200,11 @@ $regex_kswapd_sleep = generate_traceevent_regex( $regex_wakeup_kswapd = generate_traceevent_regex( "vmscan/mm_vmscan_wakeup_kswapd", $regex_wakeup_kswapd_default, - "nid", "zid", "order", "gfp_flags"); + "nid", "order", "gfp_flags"); $regex_lru_isolate = generate_traceevent_regex( "vmscan/mm_vmscan_lru_isolate", $regex_lru_isolate_default, - "isolate_mode", "classzone_idx", "order", + "classzone", "order", "nr_requested", "nr_scanned", "nr_skipped", "nr_taken", "lru"); $regex_lru_shrink_inactive = generate_traceevent_regex( @@ -218,11 +217,10 @@ $regex_lru_shrink_inactive = generate_traceevent_regex( $regex_lru_shrink_active = generate_traceevent_regex( "vmscan/mm_vmscan_lru_shrink_active", $regex_lru_shrink_active_default, - "nid", "zid", - "lru", - "nr_scanned", "nr_rotated", "priority"); + "nid", "nr_taken", "nr_active", "nr_deactivated", "nr_referenced", + "priority", "flags"); $regex_writepage = generate_traceevent_regex( - "vmscan/mm_vmscan_writepage", + "vmscan/mm_vmscan_write_folio", $regex_writepage_default, "page", "pfn", "flags"); @@ -371,7 +369,7 @@ EVENT_PROCESS: print " $regex_wakeup_kswapd\n"; next; } - my $order = $3; + my $order = $2; $perprocesspid{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD_PERORDER}[$order]++; } elsif ($tracepoint eq "mm_vmscan_lru_isolate") { $details = $6; @@ -381,18 +379,14 @@ EVENT_PROCESS: print " $regex_lru_isolate/o\n"; next; } - my $isolate_mode = $1; - my $nr_scanned = $5; - my $file = $8; - - # To closer match vmstat scanning statistics, only count isolate_both - # and isolate_inactive as scanning. isolate_active is rotation - # isolate_inactive == 1 - # isolate_active == 2 - # isolate_both == 3 - if ($isolate_mode != 2) { + my $nr_scanned = $4; + my $lru = $7; + + # To closer match vmstat scanning statistics, only count + # inactive lru as scanning + if ($lru =~ /inactive_/) { $perprocesspid{$process_pid}->{HIGH_NR_SCANNED} += $nr_scanned; - if ($file =~ /_file/) { + if ($lru =~ /_file/) { $perprocesspid{$process_pid}->{HIGH_NR_FILE_SCANNED} += $nr_scanned; } else { $perprocesspid{$process_pid}->{HIGH_NR_ANON_SCANNED} += $nr_scanned; diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index 2c29239d05c3..846c563689a8 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -96,7 +96,10 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp, unsigned long addr) { - tlb_remove_ptdesc(tlb, virt_to_ptdesc(pudp)); + struct ptdesc *ptdesc = virt_to_ptdesc(pudp); + + pagetable_pud_dtor(ptdesc); + tlb_remove_ptdesc(tlb, ptdesc); } #endif diff --git a/arch/loongarch/include/asm/pgalloc.h b/arch/loongarch/include/asm/pgalloc.h index 79470f0b4f1d..4e2d6b7ca2ee 100644 --- a/arch/loongarch/include/asm/pgalloc.h +++ b/arch/loongarch/include/asm/pgalloc.h @@ -84,6 +84,7 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) if (!ptdesc) return NULL; + pagetable_pud_ctor(ptdesc); pud = ptdesc_address(ptdesc); pud_init(pud); diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h index 40e40a7eb94a..f4440edcd8fe 100644 --- a/arch/mips/include/asm/pgalloc.h +++ b/arch/mips/include/asm/pgalloc.h @@ -95,6 +95,7 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) if (!ptdesc) return NULL; + pagetable_pud_ctor(ptdesc); pud = ptdesc_address(ptdesc); pud_init(pud); diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c index 02042100e267..7f830634dbe7 100644 --- a/arch/mips/mm/cache.c +++ b/arch/mips/mm/cache.c @@ -117,7 +117,7 @@ void __flush_dcache_pages(struct page *page, unsigned int nr) * get faulted into the tlb (and thus flushed) anyways. */ for (i = 0; i < nr; i++) { - addr = (unsigned long)kmap_local_page(page + i); + addr = (unsigned long)kmap_local_page(nth_page(page, i)); flush_data_cache_page(addr); kunmap_local((void *)addr); } diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index f7901cb4d2fa..077d01d931de 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -6785,11 +6785,7 @@ static unsigned long mmu_shrink_count(struct shrinker *shrink, return percpu_counter_read_positive(&kvm_total_used_mmu_pages); } -static struct shrinker mmu_shrinker = { - .count_objects = mmu_shrink_count, - .scan_objects = mmu_shrink_scan, - .seeks = DEFAULT_SEEKS * 10, -}; +static struct shrinker *mmu_shrinker; static void mmu_destroy_caches(void) { @@ -6922,10 +6918,16 @@ int kvm_mmu_vendor_module_init(void) if (percpu_counter_init(&kvm_total_used_mmu_pages, 0, GFP_KERNEL)) goto out; - ret = register_shrinker(&mmu_shrinker, "x86-mmu"); - if (ret) + mmu_shrinker = shrinker_alloc(0, "x86-mmu"); + if (!mmu_shrinker) goto out_shrinker; + mmu_shrinker->count_objects = mmu_shrink_count; + mmu_shrinker->scan_objects = mmu_shrink_scan; + mmu_shrinker->seeks = DEFAULT_SEEKS * 10; + + shrinker_register(mmu_shrinker); + return 0; out_shrinker: @@ -6947,7 +6949,7 @@ void kvm_mmu_vendor_module_exit(void) { mmu_destroy_caches(); percpu_counter_destroy(&kvm_total_used_mmu_pages); - unregister_shrinker(&mmu_shrinker); + shrinker_free(mmu_shrinker); } /* diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 9deadf517f14..0cbc1b8e8e3d 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -76,6 +76,9 @@ void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) #if CONFIG_PGTABLE_LEVELS > 3 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud) { + struct ptdesc *ptdesc = virt_to_ptdesc(pud); + + pagetable_pud_dtor(ptdesc); paravirt_release_pud(__pa(pud) >> PAGE_SHIFT); paravirt_tlb_remove_table(tlb, virt_to_page(pud)); } diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c index 7a453c5ff303..7f073ca64f0e 100644 --- a/drivers/acpi/acpi_pad.c +++ b/drivers/acpi/acpi_pad.c @@ -100,7 +100,7 @@ static void round_robin_cpu(unsigned int tsk_index) for_each_cpu(cpu, pad_busy_cpus) cpumask_or(tmp, tmp, topology_sibling_cpumask(cpu)); cpumask_andnot(tmp, cpu_online_mask, tmp); - /* avoid HT sibilings if possible */ + /* avoid HT siblings if possible */ if (cpumask_empty(tmp)) cpumask_andnot(tmp, cpu_online_mask, pad_busy_cpus); if (cpumask_empty(tmp)) { diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c index bba268ecd802..9ef5f1bdcfdb 100644 --- a/drivers/acpi/numa/hmat.c +++ b/drivers/acpi/numa/hmat.c @@ -24,6 +24,7 @@ #include <linux/node.h> #include <linux/sysfs.h> #include <linux/dax.h> +#include <linux/memory-tiers.h> static u8 hmat_revision; static int hmat_disable __initdata; @@ -582,28 +583,25 @@ static int initiators_to_nodemask(unsigned long *p_nodes) return 0; } -static void hmat_register_target_initiators(struct memory_target *target) +static void hmat_update_target_attrs(struct memory_target *target, + unsigned long *p_nodes, int access) { - static DECLARE_BITMAP(p_nodes, MAX_NUMNODES); struct memory_initiator *initiator; - unsigned int mem_nid, cpu_nid; + unsigned int cpu_nid; struct memory_locality *loc = NULL; u32 best = 0; - bool access0done = false; int i; - mem_nid = pxm_to_node(target->memory_pxm); + bitmap_zero(p_nodes, MAX_NUMNODES); /* - * If the Address Range Structure provides a local processor pxm, link + * If the Address Range Structure provides a local processor pxm, set * only that one. Otherwise, find the best performance attributes and - * register all initiators that match. + * collect all initiators that match. */ if (target->processor_pxm != PXM_INVAL) { cpu_nid = pxm_to_node(target->processor_pxm); - register_memory_node_under_compute_node(mem_nid, cpu_nid, 0); - access0done = true; - if (node_state(cpu_nid, N_CPU)) { - register_memory_node_under_compute_node(mem_nid, cpu_nid, 1); + if (access == 0 || node_state(cpu_nid, N_CPU)) { + set_bit(target->processor_pxm, p_nodes); return; } } @@ -617,47 +615,10 @@ static void hmat_register_target_initiators(struct memory_target *target) * We'll also use the sorting to prime the candidate nodes with known * initiators. */ - bitmap_zero(p_nodes, MAX_NUMNODES); list_sort(NULL, &initiators, initiator_cmp); if (initiators_to_nodemask(p_nodes) < 0) return; - if (!access0done) { - for (i = WRITE_LATENCY; i <= READ_BANDWIDTH; i++) { - loc = localities_types[i]; - if (!loc) - continue; - - best = 0; - list_for_each_entry(initiator, &initiators, node) { - u32 value; - - if (!test_bit(initiator->processor_pxm, p_nodes)) - continue; - - value = hmat_initiator_perf(target, initiator, - loc->hmat_loc); - if (hmat_update_best(loc->hmat_loc->data_type, value, &best)) - bitmap_clear(p_nodes, 0, initiator->processor_pxm); - if (value != best) - clear_bit(initiator->processor_pxm, p_nodes); - } - if (best) - hmat_update_target_access(target, loc->hmat_loc->data_type, - best, 0); - } - - for_each_set_bit(i, p_nodes, MAX_NUMNODES) { - cpu_nid = pxm_to_node(i); - register_memory_node_under_compute_node(mem_nid, cpu_nid, 0); - } - } - - /* Access 1 ignores Generic Initiators */ - bitmap_zero(p_nodes, MAX_NUMNODES); - if (initiators_to_nodemask(p_nodes) < 0) - return; - for (i = WRITE_LATENCY; i <= READ_BANDWIDTH; i++) { loc = localities_types[i]; if (!loc) @@ -667,7 +628,7 @@ static void hmat_register_target_initiators(struct memory_target *target) list_for_each_entry(initiator, &initiators, node) { u32 value; - if (!initiator->has_cpu) { + if (access == 1 && !initiator->has_cpu) { clear_bit(initiator->processor_pxm, p_nodes); continue; } @@ -681,14 +642,33 @@ static void hmat_register_target_initiators(struct memory_target *target) clear_bit(initiator->processor_pxm, p_nodes); } if (best) - hmat_update_target_access(target, loc->hmat_loc->data_type, best, 1); + hmat_update_target_access(target, loc->hmat_loc->data_type, best, access); } +} + +static void __hmat_register_target_initiators(struct memory_target *target, + unsigned long *p_nodes, + int access) +{ + unsigned int mem_nid, cpu_nid; + int i; + + mem_nid = pxm_to_node(target->memory_pxm); + hmat_update_target_attrs(target, p_nodes, access); for_each_set_bit(i, p_nodes, MAX_NUMNODES) { cpu_nid = pxm_to_node(i); - register_memory_node_under_compute_node(mem_nid, cpu_nid, 1); + register_memory_node_under_compute_node(mem_nid, cpu_nid, access); } } +static void hmat_register_target_initiators(struct memory_target *target) +{ + static DECLARE_BITMAP(p_nodes, MAX_NUMNODES); + + __hmat_register_target_initiators(target, p_nodes, 0); + __hmat_register_target_initiators(target, p_nodes, 1); +} + static void hmat_register_target_cache(struct memory_target *target) { unsigned mem_nid = pxm_to_node(target->memory_pxm); @@ -780,6 +760,61 @@ static int hmat_callback(struct notifier_block *self, return NOTIFY_OK; } +static int hmat_set_default_dram_perf(void) +{ + int rc; + int nid, pxm; + struct memory_target *target; + struct node_hmem_attrs *attrs; + + if (!default_dram_type) + return -EIO; + + for_each_node_mask(nid, default_dram_type->nodes) { + pxm = node_to_pxm(nid); + target = find_mem_target(pxm); + if (!target) + continue; + attrs = &target->hmem_attrs[1]; + rc = mt_set_default_dram_perf(nid, attrs, "ACPI HMAT"); + if (rc) + return rc; + } + + return 0; +} + +static int hmat_calculate_adistance(struct notifier_block *self, + unsigned long nid, void *data) +{ + static DECLARE_BITMAP(p_nodes, MAX_NUMNODES); + struct memory_target *target; + struct node_hmem_attrs *perf; + int *adist = data; + int pxm; + + pxm = node_to_pxm(nid); + target = find_mem_target(pxm); + if (!target) + return NOTIFY_OK; + + mutex_lock(&target_lock); + hmat_update_target_attrs(target, p_nodes, 1); + mutex_unlock(&target_lock); + + perf = &target->hmem_attrs[1]; + + if (mt_perf_to_adistance(perf, adist)) + return NOTIFY_OK; + + return NOTIFY_STOP; +} + +static struct notifier_block hmat_adist_nb __meminitdata = { + .notifier_call = hmat_calculate_adistance, + .priority = 100, +}; + static __init void hmat_free_structures(void) { struct memory_target *target, *tnext; @@ -862,8 +897,13 @@ static __init int hmat_init(void) hmat_register_targets(); /* Keep the table and structures if the notifier may use them */ - if (!hotplug_memory_notifier(hmat_callback, HMAT_CALLBACK_PRI)) - return 0; + if (hotplug_memory_notifier(hmat_callback, HMAT_CALLBACK_PRI)) + goto out_put; + + if (!hmat_set_default_dram_perf()) + register_mt_adistance_algorithm(&hmat_adist_nb); + + return 0; out_put: hmat_free_structures(); acpi_put_table(tbl); diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index e3db8297095a..138f6d43d13b 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -1053,11 +1053,7 @@ binder_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) NULL, sc->nr_to_scan); } -static struct shrinker binder_shrinker = { - .count_objects = binder_shrink_count, - .scan_objects = binder_shrink_scan, - .seeks = DEFAULT_SEEKS, -}; +static struct shrinker *binder_shrinker; /** * binder_alloc_init() - called by binder_open() for per-proc initialization @@ -1077,19 +1073,29 @@ void binder_alloc_init(struct binder_alloc *alloc) int binder_alloc_shrinker_init(void) { - int ret = list_lru_init(&binder_alloc_lru); + int ret; - if (ret == 0) { - ret = register_shrinker(&binder_shrinker, "android-binder"); - if (ret) - list_lru_destroy(&binder_alloc_lru); + ret = list_lru_init(&binder_alloc_lru); + if (ret) + return ret; + + binder_shrinker = shrinker_alloc(0, "android-binder"); + if (!binder_shrinker) { + list_lru_destroy(&binder_alloc_lru); + return -ENOMEM; } - return ret; + + binder_shrinker->count_objects = binder_shrink_count; + binder_shrinker->scan_objects = binder_shrink_scan; + + shrinker_register(binder_shrinker); + + return 0; } void binder_alloc_shrinker_exit(void) { - unregister_shrinker(&binder_shrinker); + shrinker_free(binder_shrinker); list_lru_destroy(&binder_alloc_lru); } diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c index c57acb73e3db..369c698b7706 100644 --- a/drivers/dax/kmem.c +++ b/drivers/dax/kmem.c @@ -49,14 +49,52 @@ struct dax_kmem_data { struct resource *res[]; }; -static struct memory_dev_type *dax_slowmem_type; +static DEFINE_MUTEX(kmem_memory_type_lock); +static LIST_HEAD(kmem_memory_types); + +static struct memory_dev_type *kmem_find_alloc_memory_type(int adist) +{ + bool found = false; + struct memory_dev_type *mtype; + + mutex_lock(&kmem_memory_type_lock); + list_for_each_entry(mtype, &kmem_memory_types, list) { + if (mtype->adistance == adist) { + found = true; + break; + } + } + if (!found) { + mtype = alloc_memory_type(adist); + if (!IS_ERR(mtype)) + list_add(&mtype->list, &kmem_memory_types); + } + mutex_unlock(&kmem_memory_type_lock); + + return mtype; +} + +static void kmem_put_memory_types(void) +{ + struct memory_dev_type *mtype, *mtn; + + mutex_lock(&kmem_memory_type_lock); + list_for_each_entry_safe(mtype, mtn, &kmem_memory_types, list) { + list_del(&mtype->list); + put_memory_type(mtype); + } + mutex_unlock(&kmem_memory_type_lock); +} + static int dev_dax_kmem_probe(struct dev_dax *dev_dax) { struct device *dev = &dev_dax->dev; unsigned long total_len = 0; struct dax_kmem_data *data; + struct memory_dev_type *mtype; int i, rc, mapped = 0; int numa_node; + int adist = MEMTIER_DEFAULT_DAX_ADISTANCE; /* * Ensure good NUMA information for the persistent memory. @@ -71,6 +109,11 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax) return -EINVAL; } + mt_calc_adistance(numa_node, &adist); + mtype = kmem_find_alloc_memory_type(adist); + if (IS_ERR(mtype)) + return PTR_ERR(mtype); + for (i = 0; i < dev_dax->nr_range; i++) { struct range range; @@ -88,7 +131,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax) return -EINVAL; } - init_node_memory_type(numa_node, dax_slowmem_type); + init_node_memory_type(numa_node, mtype); rc = -ENOMEM; data = kzalloc(struct_size(data, res, dev_dax->nr_range), GFP_KERNEL); @@ -167,7 +210,7 @@ err_reg_mgid: err_res_name: kfree(data); err_dax_kmem_data: - clear_node_memory_type(numa_node, dax_slowmem_type); + clear_node_memory_type(numa_node, mtype); return rc; } @@ -219,7 +262,7 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax) * for that. This implies this reference will be around * till next reboot. */ - clear_node_memory_type(node, dax_slowmem_type); + clear_node_memory_type(node, NULL); } } #else @@ -251,12 +294,6 @@ static int __init dax_kmem_init(void) if (!kmem_name) return -ENOMEM; - dax_slowmem_type = alloc_memory_type(MEMTIER_DEFAULT_DAX_ADISTANCE); - if (IS_ERR(dax_slowmem_type)) { - rc = PTR_ERR(dax_slowmem_type); - goto err_dax_slowmem_type; - } - rc = dax_driver_register(&device_dax_kmem_driver); if (rc) goto error_dax_driver; @@ -264,8 +301,7 @@ static int __init dax_kmem_init(void) return rc; error_dax_driver: - put_memory_type(dax_slowmem_type); -err_dax_slowmem_type: + kmem_put_memory_types(); kfree_const(kmem_name); return rc; } @@ -275,7 +311,7 @@ static void __exit dax_kmem_exit(void) dax_driver_unregister(&device_dax_kmem_driver); if (!any_hotremove_failed) kfree_const(kmem_name); - put_memory_type(dax_slowmem_type); + kmem_put_memory_types(); } MODULE_AUTHOR("Intel Corporation"); diff --git a/drivers/firmware/efi/unaccepted_memory.c b/drivers/firmware/efi/unaccepted_memory.c index 853f7dc3c21d..79ba576b22e3 100644 --- a/drivers/firmware/efi/unaccepted_memory.c +++ b/drivers/firmware/efi/unaccepted_memory.c @@ -3,6 +3,7 @@ #include <linux/efi.h> #include <linux/memblock.h> #include <linux/spinlock.h> +#include <linux/crash_dump.h> #include <asm/unaccepted_memory.h> /* Protects unaccepted memory bitmap */ @@ -145,3 +146,22 @@ bool range_contains_unaccepted_memory(phys_addr_t start, phys_addr_t end) return ret; } + +#ifdef CONFIG_PROC_VMCORE +static bool unaccepted_memory_vmcore_pfn_is_ram(struct vmcore_cb *cb, + unsigned long pfn) +{ + return !pfn_is_unaccepted_memory(pfn); +} + +static struct vmcore_cb vmcore_cb = { + .pfn_is_ram = unaccepted_memory_vmcore_pfn_is_ram, +}; + +static int __init unaccepted_memory_init_kdump(void) +{ + register_vmcore_cb(&vmcore_cb); + return 0; +} +core_initcall(unaccepted_memory_init_kdump); +#endif /* CONFIG_PROC_VMCORE */ diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index 214763942aa2..e07ffbd9eab3 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -284,8 +284,7 @@ unsigned long i915_gem_shrink_all(struct drm_i915_private *i915) static unsigned long i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc) { - struct drm_i915_private *i915 = - container_of(shrinker, struct drm_i915_private, mm.shrinker); + struct drm_i915_private *i915 = shrinker->private_data; unsigned long num_objects; unsigned long count; @@ -302,8 +301,8 @@ i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc) if (num_objects) { unsigned long avg = 2 * count / num_objects; - i915->mm.shrinker.batch = - max((i915->mm.shrinker.batch + avg) >> 1, + i915->mm.shrinker->batch = + max((i915->mm.shrinker->batch + avg) >> 1, 128ul /* default SHRINK_BATCH */); } @@ -313,8 +312,7 @@ i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc) static unsigned long i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) { - struct drm_i915_private *i915 = - container_of(shrinker, struct drm_i915_private, mm.shrinker); + struct drm_i915_private *i915 = shrinker->private_data; unsigned long freed; sc->nr_scanned = 0; @@ -422,12 +420,17 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr void i915_gem_driver_register__shrinker(struct drm_i915_private *i915) { - i915->mm.shrinker.scan_objects = i915_gem_shrinker_scan; - i915->mm.shrinker.count_objects = i915_gem_shrinker_count; - i915->mm.shrinker.seeks = DEFAULT_SEEKS; - i915->mm.shrinker.batch = 4096; - drm_WARN_ON(&i915->drm, register_shrinker(&i915->mm.shrinker, - "drm-i915_gem")); + i915->mm.shrinker = shrinker_alloc(0, "drm-i915_gem"); + if (!i915->mm.shrinker) { + drm_WARN_ON(&i915->drm, 1); + } else { + i915->mm.shrinker->scan_objects = i915_gem_shrinker_scan; + i915->mm.shrinker->count_objects = i915_gem_shrinker_count; + i915->mm.shrinker->batch = 4096; + i915->mm.shrinker->private_data = i915; + + shrinker_register(i915->mm.shrinker); + } i915->mm.oom_notifier.notifier_call = i915_gem_shrinker_oom; drm_WARN_ON(&i915->drm, register_oom_notifier(&i915->mm.oom_notifier)); @@ -443,7 +446,7 @@ void i915_gem_driver_unregister__shrinker(struct drm_i915_private *i915) unregister_vmap_purge_notifier(&i915->mm.vmap_notifier)); drm_WARN_ON(&i915->drm, unregister_oom_notifier(&i915->mm.oom_notifier)); - unregister_shrinker(&i915->mm.shrinker); + shrinker_free(i915->mm.shrinker); } void i915_gem_shrinker_taints_mutex(struct drm_i915_private *i915, diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 7a8ce7239bc9..f2f21da4d7f9 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -163,7 +163,7 @@ struct i915_gem_mm { struct notifier_block oom_notifier; struct notifier_block vmap_notifier; - struct shrinker shrinker; + struct shrinker *shrinker; #ifdef CONFIG_MMU_NOTIFIER /** diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 4bd028fa7500..7f20249d6071 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -462,7 +462,9 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv) if (ret) goto err_msm_uninit; - msm_gem_shrinker_init(ddev); + ret = msm_gem_shrinker_init(ddev); + if (ret) + goto err_msm_uninit; if (priv->kms_init) { ret = priv->kms_init(ddev); diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index 02fd6c7d0bb7..e2fc56f161b5 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -221,7 +221,7 @@ struct msm_drm_private { } vram; struct notifier_block vmap_notifier; - struct shrinker shrinker; + struct shrinker *shrinker; struct drm_atomic_state *pm_state; @@ -283,7 +283,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, unsigned long msm_gem_shrinker_shrink(struct drm_device *dev, unsigned long nr_to_scan); #endif -void msm_gem_shrinker_init(struct drm_device *dev); +int msm_gem_shrinker_init(struct drm_device *dev); void msm_gem_shrinker_cleanup(struct drm_device *dev); struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj); diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c index f38296ad8743..5a7d48c02c4b 100644 --- a/drivers/gpu/drm/msm/msm_gem_shrinker.c +++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c @@ -34,8 +34,7 @@ static bool can_block(struct shrink_control *sc) static unsigned long msm_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc) { - struct msm_drm_private *priv = - container_of(shrinker, struct msm_drm_private, shrinker); + struct msm_drm_private *priv = shrinker->private_data; unsigned count = priv->lru.dontneed.count; if (can_swap()) @@ -100,8 +99,7 @@ active_evict(struct drm_gem_object *obj) static unsigned long msm_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) { - struct msm_drm_private *priv = - container_of(shrinker, struct msm_drm_private, shrinker); + struct msm_drm_private *priv = shrinker->private_data; struct { struct drm_gem_lru *lru; bool (*shrink)(struct drm_gem_object *obj); @@ -148,10 +146,11 @@ msm_gem_shrinker_shrink(struct drm_device *dev, unsigned long nr_to_scan) struct shrink_control sc = { .nr_to_scan = nr_to_scan, }; - int ret; + unsigned long ret = SHRINK_STOP; fs_reclaim_acquire(GFP_KERNEL); - ret = msm_gem_shrinker_scan(&priv->shrinker, &sc); + if (priv->shrinker) + ret = msm_gem_shrinker_scan(priv->shrinker, &sc); fs_reclaim_release(GFP_KERNEL); return ret; @@ -210,16 +209,24 @@ msm_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr) * * This function registers and sets up the msm shrinker. */ -void msm_gem_shrinker_init(struct drm_device *dev) +int msm_gem_shrinker_init(struct drm_device *dev) { struct msm_drm_private *priv = dev->dev_private; - priv->shrinker.count_objects = msm_gem_shrinker_count; - priv->shrinker.scan_objects = msm_gem_shrinker_scan; - priv->shrinker.seeks = DEFAULT_SEEKS; - WARN_ON(register_shrinker(&priv->shrinker, "drm-msm_gem")); + + priv->shrinker = shrinker_alloc(0, "drm-msm_gem"); + if (!priv->shrinker) + return -ENOMEM; + + priv->shrinker->count_objects = msm_gem_shrinker_count; + priv->shrinker->scan_objects = msm_gem_shrinker_scan; + priv->shrinker->private_data = priv; + + shrinker_register(priv->shrinker); priv->vmap_notifier.notifier_call = msm_gem_shrinker_vmap; WARN_ON(register_vmap_purge_notifier(&priv->vmap_notifier)); + + return 0; } /** @@ -232,8 +239,8 @@ void msm_gem_shrinker_cleanup(struct drm_device *dev) { struct msm_drm_private *priv = dev->dev_private; - if (priv->shrinker.nr_deferred) { + if (priv->shrinker) { WARN_ON(unregister_vmap_purge_notifier(&priv->vmap_notifier)); - unregister_shrinker(&priv->shrinker); + shrinker_free(priv->shrinker); } } diff --git a/drivers/gpu/drm/panfrost/panfrost_device.h b/drivers/gpu/drm/panfrost/panfrost_device.h index b0126b9fbadc..e667e5689353 100644 --- a/drivers/gpu/drm/panfrost/panfrost_device.h +++ b/drivers/gpu/drm/panfrost/panfrost_device.h @@ -118,7 +118,7 @@ struct panfrost_device { struct mutex shrinker_lock; struct list_head shrinker_list; - struct shrinker shrinker; + struct shrinker *shrinker; struct panfrost_devfreq pfdevfreq; }; diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index a2ab99698ca8..e1d0e3a23757 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -601,10 +601,14 @@ static int panfrost_probe(struct platform_device *pdev) if (err < 0) goto err_out1; - panfrost_gem_shrinker_init(ddev); + err = panfrost_gem_shrinker_init(ddev); + if (err) + goto err_out2; return 0; +err_out2: + drm_dev_unregister(ddev); err_out1: pm_runtime_disable(pfdev->dev); panfrost_device_fini(pfdev); diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.h b/drivers/gpu/drm/panfrost/panfrost_gem.h index ad2877eeeccd..863d2ec8d4f0 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem.h +++ b/drivers/gpu/drm/panfrost/panfrost_gem.h @@ -81,7 +81,7 @@ panfrost_gem_mapping_get(struct panfrost_gem_object *bo, void panfrost_gem_mapping_put(struct panfrost_gem_mapping *mapping); void panfrost_gem_teardown_mappings_locked(struct panfrost_gem_object *bo); -void panfrost_gem_shrinker_init(struct drm_device *dev); +int panfrost_gem_shrinker_init(struct drm_device *dev); void panfrost_gem_shrinker_cleanup(struct drm_device *dev); #endif /* __PANFROST_GEM_H__ */ diff --git a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c index 6a71a2555f85..3d9f51bd48b6 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c +++ b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c @@ -18,8 +18,7 @@ static unsigned long panfrost_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc) { - struct panfrost_device *pfdev = - container_of(shrinker, struct panfrost_device, shrinker); + struct panfrost_device *pfdev = shrinker->private_data; struct drm_gem_shmem_object *shmem; unsigned long count = 0; @@ -65,8 +64,7 @@ unlock_mappings: static unsigned long panfrost_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) { - struct panfrost_device *pfdev = - container_of(shrinker, struct panfrost_device, shrinker); + struct panfrost_device *pfdev = shrinker->private_data; struct drm_gem_shmem_object *shmem, *tmp; unsigned long freed = 0; @@ -97,13 +95,21 @@ panfrost_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) * * This function registers and sets up the panfrost shrinker. */ -void panfrost_gem_shrinker_init(struct drm_device *dev) +int panfrost_gem_shrinker_init(struct drm_device *dev) { struct panfrost_device *pfdev = dev->dev_private; - pfdev->shrinker.count_objects = panfrost_gem_shrinker_count; - pfdev->shrinker.scan_objects = panfrost_gem_shrinker_scan; - pfdev->shrinker.seeks = DEFAULT_SEEKS; - WARN_ON(register_shrinker(&pfdev->shrinker, "drm-panfrost")); + + pfdev->shrinker = shrinker_alloc(0, "drm-panfrost"); + if (!pfdev->shrinker) + return -ENOMEM; + + pfdev->shrinker->count_objects = panfrost_gem_shrinker_count; + pfdev->shrinker->scan_objects = panfrost_gem_shrinker_scan; + pfdev->shrinker->private_data = pfdev; + + shrinker_register(pfdev->shrinker); + + return 0; } /** @@ -116,7 +122,6 @@ void panfrost_gem_shrinker_cleanup(struct drm_device *dev) { struct panfrost_device *pfdev = dev->dev_private; - if (pfdev->shrinker.nr_deferred) { - unregister_shrinker(&pfdev->shrinker); - } + if (pfdev->shrinker) + shrinker_free(pfdev->shrinker); } diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index cddb9151d20f..fe610a3cace0 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -73,7 +73,8 @@ static struct ttm_pool_type global_dma32_uncached[MAX_ORDER + 1]; static spinlock_t shrinker_lock; static struct list_head shrinker_list; -static struct shrinker mm_shrinker; +static struct shrinker *mm_shrinker; +static DECLARE_RWSEM(pool_shrink_rwsem); /* Allocate pages of size 1 << order with the given gfp_flags */ static struct page *ttm_pool_alloc_page(struct ttm_pool *pool, gfp_t gfp_flags, @@ -317,6 +318,7 @@ static unsigned int ttm_pool_shrink(void) unsigned int num_pages; struct page *p; + down_read(&pool_shrink_rwsem); spin_lock(&shrinker_lock); pt = list_first_entry(&shrinker_list, typeof(*pt), shrinker_list); list_move_tail(&pt->shrinker_list, &shrinker_list); @@ -329,6 +331,7 @@ static unsigned int ttm_pool_shrink(void) } else { num_pages = 0; } + up_read(&pool_shrink_rwsem); return num_pages; } @@ -573,6 +576,18 @@ void ttm_pool_init(struct ttm_pool *pool, struct device *dev, EXPORT_SYMBOL(ttm_pool_init); /** + * ttm_pool_synchronize_shrinkers - Wait for all running shrinkers to complete. + * + * This is useful to guarantee that all shrinker invocations have seen an + * update, before freeing memory, similar to rcu. + */ +static void ttm_pool_synchronize_shrinkers(void) +{ + down_write(&pool_shrink_rwsem); + up_write(&pool_shrink_rwsem); +} + +/** * ttm_pool_fini - Cleanup a pool * * @pool: the pool to clean up @@ -593,7 +608,7 @@ void ttm_pool_fini(struct ttm_pool *pool) /* We removed the pool types from the LRU, but we need to also make sure * that no shrinker is concurrently freeing pages from the pool. */ - synchronize_shrinkers(); + ttm_pool_synchronize_shrinkers(); } EXPORT_SYMBOL(ttm_pool_fini); @@ -734,8 +749,8 @@ static int ttm_pool_debugfs_shrink_show(struct seq_file *m, void *data) struct shrink_control sc = { .gfp_mask = GFP_NOFS }; fs_reclaim_acquire(GFP_KERNEL); - seq_printf(m, "%lu/%lu\n", ttm_pool_shrinker_count(&mm_shrinker, &sc), - ttm_pool_shrinker_scan(&mm_shrinker, &sc)); + seq_printf(m, "%lu/%lu\n", ttm_pool_shrinker_count(mm_shrinker, &sc), + ttm_pool_shrinker_scan(mm_shrinker, &sc)); fs_reclaim_release(GFP_KERNEL); return 0; @@ -779,10 +794,17 @@ int ttm_pool_mgr_init(unsigned long num_pages) &ttm_pool_debugfs_shrink_fops); #endif - mm_shrinker.count_objects = ttm_pool_shrinker_count; - mm_shrinker.scan_objects = ttm_pool_shrinker_scan; - mm_shrinker.seeks = 1; - return register_shrinker(&mm_shrinker, "drm-ttm_pool"); + mm_shrinker = shrinker_alloc(0, "drm-ttm_pool"); + if (!mm_shrinker) + return -ENOMEM; + + mm_shrinker->count_objects = ttm_pool_shrinker_count; + mm_shrinker->scan_objects = ttm_pool_shrinker_scan; + mm_shrinker->seeks = 1; + + shrinker_register(mm_shrinker); + + return 0; } /** @@ -802,6 +824,6 @@ void ttm_pool_mgr_fini(void) ttm_pool_type_fini(&global_dma32_uncached[i]); } - unregister_shrinker(&mm_shrinker); + shrinker_free(mm_shrinker); WARN_ON(!list_empty(&shrinker_list)); } diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 5a79bb3c272f..c622bc50f81b 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -541,7 +541,7 @@ struct cache_set { struct bio_set bio_split; /* For the btree cache */ - struct shrinker shrink; + struct shrinker *shrink; /* For the btree cache and anything allocation related */ struct mutex bucket_lock; diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index fd121a61f17c..ae5cbb55861f 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -667,7 +667,7 @@ out_unlock: static unsigned long bch_mca_scan(struct shrinker *shrink, struct shrink_control *sc) { - struct cache_set *c = container_of(shrink, struct cache_set, shrink); + struct cache_set *c = shrink->private_data; struct btree *b, *t; unsigned long i, nr = sc->nr_to_scan; unsigned long freed = 0; @@ -734,7 +734,7 @@ out: static unsigned long bch_mca_count(struct shrinker *shrink, struct shrink_control *sc) { - struct cache_set *c = container_of(shrink, struct cache_set, shrink); + struct cache_set *c = shrink->private_data; if (c->shrinker_disabled) return 0; @@ -752,8 +752,8 @@ void bch_btree_cache_free(struct cache_set *c) closure_init_stack(&cl); - if (c->shrink.list.next) - unregister_shrinker(&c->shrink); + if (c->shrink) + shrinker_free(c->shrink); mutex_lock(&c->bucket_lock); @@ -828,14 +828,19 @@ int bch_btree_cache_alloc(struct cache_set *c) c->verify_data = NULL; #endif - c->shrink.count_objects = bch_mca_count; - c->shrink.scan_objects = bch_mca_scan; - c->shrink.seeks = 4; - c->shrink.batch = c->btree_pages * 2; + c->shrink = shrinker_alloc(0, "md-bcache:%pU", c->set_uuid); + if (!c->shrink) { + pr_warn("bcache: %s: could not allocate shrinker\n", __func__); + return 0; + } + + c->shrink->count_objects = bch_mca_count; + c->shrink->scan_objects = bch_mca_scan; + c->shrink->seeks = 4; + c->shrink->batch = c->btree_pages * 2; + c->shrink->private_data = c; - if (register_shrinker(&c->shrink, "md-bcache:%pU", c->set_uuid)) - pr_warn("bcache: %s: could not register shrinker\n", - __func__); + shrinker_register(c->shrink); return 0; } diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 0e2c1880f60b..45d8af755de6 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -866,7 +866,8 @@ STORE(__bch_cache_set) sc.gfp_mask = GFP_KERNEL; sc.nr_to_scan = strtoul_or_return(buf); - c->shrink.scan_objects(&c->shrink, &sc); + if (c->shrink) + c->shrink->scan_objects(c->shrink, &sc); } sysfs_strtoul_clamp(congested_read_threshold_us, diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index bc309e41d074..62eb27639c9b 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -963,7 +963,7 @@ struct dm_bufio_client { sector_t start; - struct shrinker shrinker; + struct shrinker *shrinker; struct work_struct shrink_work; atomic_long_t need_shrink; @@ -2368,7 +2368,7 @@ static unsigned long dm_bufio_shrink_scan(struct shrinker *shrink, struct shrink { struct dm_bufio_client *c; - c = container_of(shrink, struct dm_bufio_client, shrinker); + c = shrink->private_data; atomic_long_add(sc->nr_to_scan, &c->need_shrink); queue_work(dm_bufio_wq, &c->shrink_work); @@ -2377,7 +2377,7 @@ static unsigned long dm_bufio_shrink_scan(struct shrinker *shrink, struct shrink static unsigned long dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { - struct dm_bufio_client *c = container_of(shrink, struct dm_bufio_client, shrinker); + struct dm_bufio_client *c = shrink->private_data; unsigned long count = cache_total(&c->cache); unsigned long retain_target = get_retain_buffers(c); unsigned long queued_for_cleanup = atomic_long_read(&c->need_shrink); @@ -2490,14 +2490,20 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign INIT_WORK(&c->shrink_work, shrink_work); atomic_long_set(&c->need_shrink, 0); - c->shrinker.count_objects = dm_bufio_shrink_count; - c->shrinker.scan_objects = dm_bufio_shrink_scan; - c->shrinker.seeks = 1; - c->shrinker.batch = 0; - r = register_shrinker(&c->shrinker, "dm-bufio:(%u:%u)", - MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev)); - if (r) + c->shrinker = shrinker_alloc(0, "dm-bufio:(%u:%u)", + MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev)); + if (!c->shrinker) { + r = -ENOMEM; goto bad; + } + + c->shrinker->count_objects = dm_bufio_shrink_count; + c->shrinker->scan_objects = dm_bufio_shrink_scan; + c->shrinker->seeks = 1; + c->shrinker->batch = 0; + c->shrinker->private_data = c; + + shrinker_register(c->shrinker); mutex_lock(&dm_bufio_clients_lock); dm_bufio_client_count++; @@ -2537,7 +2543,7 @@ void dm_bufio_client_destroy(struct dm_bufio_client *c) drop_buffers(c); - unregister_shrinker(&c->shrinker); + shrinker_free(c->shrinker); flush_work(&c->shrink_work); mutex_lock(&dm_bufio_clients_lock); diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index acffed750e3e..9e0c69958587 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -1828,7 +1828,7 @@ int dm_cache_metadata_abort(struct dm_cache_metadata *cmd) * Replacement block manager (new_bm) is created and old_bm destroyed outside of * cmd root_lock to avoid ABBA deadlock that would result (due to life-cycle of * shrinker associated with the block manager's bufio client vs cmd root_lock). - * - must take shrinker_rwsem without holding cmd->root_lock + * - must take shrinker_mutex without holding cmd->root_lock */ new_bm = dm_block_manager_create(cmd->bdev, DM_CACHE_METADATA_BLOCK_SIZE << SECTOR_SHIFT, CACHE_MAX_CONCURRENT_LOCKS); diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index 9d3cca8e3dc9..60a4dc01ea18 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -187,7 +187,7 @@ struct dmz_metadata { struct rb_root mblk_rbtree; struct list_head mblk_lru_list; struct list_head mblk_dirty_list; - struct shrinker mblk_shrinker; + struct shrinker *mblk_shrinker; /* Zone allocation management */ struct mutex map_lock; @@ -615,7 +615,7 @@ static unsigned long dmz_shrink_mblock_cache(struct dmz_metadata *zmd, static unsigned long dmz_mblock_shrinker_count(struct shrinker *shrink, struct shrink_control *sc) { - struct dmz_metadata *zmd = container_of(shrink, struct dmz_metadata, mblk_shrinker); + struct dmz_metadata *zmd = shrink->private_data; return atomic_read(&zmd->nr_mblks); } @@ -626,7 +626,7 @@ static unsigned long dmz_mblock_shrinker_count(struct shrinker *shrink, static unsigned long dmz_mblock_shrinker_scan(struct shrinker *shrink, struct shrink_control *sc) { - struct dmz_metadata *zmd = container_of(shrink, struct dmz_metadata, mblk_shrinker); + struct dmz_metadata *zmd = shrink->private_data; unsigned long count; spin_lock(&zmd->mblk_lock); @@ -2936,19 +2936,23 @@ int dmz_ctr_metadata(struct dmz_dev *dev, int num_dev, */ zmd->min_nr_mblks = 2 + zmd->nr_map_blocks + zmd->zone_nr_bitmap_blocks * 16; zmd->max_nr_mblks = zmd->min_nr_mblks + 512; - zmd->mblk_shrinker.count_objects = dmz_mblock_shrinker_count; - zmd->mblk_shrinker.scan_objects = dmz_mblock_shrinker_scan; - zmd->mblk_shrinker.seeks = DEFAULT_SEEKS; /* Metadata cache shrinker */ - ret = register_shrinker(&zmd->mblk_shrinker, "dm-zoned-meta:(%u:%u)", - MAJOR(dev->bdev->bd_dev), - MINOR(dev->bdev->bd_dev)); - if (ret) { - dmz_zmd_err(zmd, "Register metadata cache shrinker failed"); + zmd->mblk_shrinker = shrinker_alloc(0, "dm-zoned-meta:(%u:%u)", + MAJOR(dev->bdev->bd_dev), + MINOR(dev->bdev->bd_dev)); + if (!zmd->mblk_shrinker) { + ret = -ENOMEM; + dmz_zmd_err(zmd, "Allocate metadata cache shrinker failed"); goto err; } + zmd->mblk_shrinker->count_objects = dmz_mblock_shrinker_count; + zmd->mblk_shrinker->scan_objects = dmz_mblock_shrinker_scan; + zmd->mblk_shrinker->private_data = zmd; + + shrinker_register(zmd->mblk_shrinker); + dmz_zmd_info(zmd, "DM-Zoned metadata version %d", zmd->sb_version); for (i = 0; i < zmd->nr_devs; i++) dmz_print_dev(zmd, i); @@ -2995,7 +2999,7 @@ err: */ void dmz_dtr_metadata(struct dmz_metadata *zmd) { - unregister_shrinker(&zmd->mblk_shrinker); + shrinker_free(zmd->mblk_shrinker); dmz_cleanup_metadata(zmd); kfree(zmd); } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 4cb9c608ee19..c8d2c6e50aa1 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -7401,7 +7401,7 @@ static void free_conf(struct r5conf *conf) log_exit(conf); - unregister_shrinker(&conf->shrinker); + shrinker_free(conf->shrinker); free_thread_groups(conf); shrink_stripes(conf); raid5_free_percpu(conf); @@ -7449,7 +7449,7 @@ static int raid5_alloc_percpu(struct r5conf *conf) static unsigned long raid5_cache_scan(struct shrinker *shrink, struct shrink_control *sc) { - struct r5conf *conf = container_of(shrink, struct r5conf, shrinker); + struct r5conf *conf = shrink->private_data; unsigned long ret = SHRINK_STOP; if (mutex_trylock(&conf->cache_size_mutex)) { @@ -7470,7 +7470,7 @@ static unsigned long raid5_cache_scan(struct shrinker *shrink, static unsigned long raid5_cache_count(struct shrinker *shrink, struct shrink_control *sc) { - struct r5conf *conf = container_of(shrink, struct r5conf, shrinker); + struct r5conf *conf = shrink->private_data; if (conf->max_nr_stripes < conf->min_nr_stripes) /* unlikely, but not impossible */ @@ -7705,18 +7705,22 @@ static struct r5conf *setup_conf(struct mddev *mddev) * it reduces the queue depth and so can hurt throughput. * So set it rather large, scaled by number of devices. */ - conf->shrinker.seeks = DEFAULT_SEEKS * conf->raid_disks * 4; - conf->shrinker.scan_objects = raid5_cache_scan; - conf->shrinker.count_objects = raid5_cache_count; - conf->shrinker.batch = 128; - conf->shrinker.flags = 0; - ret = register_shrinker(&conf->shrinker, "md-raid5:%s", mdname(mddev)); - if (ret) { - pr_warn("md/raid:%s: couldn't register shrinker.\n", + conf->shrinker = shrinker_alloc(0, "md-raid5:%s", mdname(mddev)); + if (!conf->shrinker) { + ret = -ENOMEM; + pr_warn("md/raid:%s: couldn't allocate shrinker.\n", mdname(mddev)); goto abort; } + conf->shrinker->seeks = DEFAULT_SEEKS * conf->raid_disks * 4; + conf->shrinker->scan_objects = raid5_cache_scan; + conf->shrinker->count_objects = raid5_cache_count; + conf->shrinker->batch = 128; + conf->shrinker->private_data = conf; + + shrinker_register(conf->shrinker); + sprintf(pers_name, "raid%d", mddev->new_level); rcu_assign_pointer(conf->thread, md_register_thread(raid5d, mddev, pers_name)); diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 97a795979a35..22bea20eccbd 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -670,7 +670,7 @@ struct r5conf { wait_queue_head_t wait_for_stripe; wait_queue_head_t wait_for_overlap; unsigned long cache_state; - struct shrinker shrinker; + struct shrinker *shrinker; int pool_size; /* number of disks in stripeheads in pool */ spinlock_t device_lock; struct disk_info *disks; diff --git a/drivers/misc/vmw_balloon.c b/drivers/misc/vmw_balloon.c index 9ce9b9e0e9b6..c817d8c21641 100644 --- a/drivers/misc/vmw_balloon.c +++ b/drivers/misc/vmw_balloon.c @@ -380,16 +380,7 @@ struct vmballoon { /** * @shrinker: shrinker interface that is used to avoid over-inflation. */ - struct shrinker shrinker; - - /** - * @shrinker_registered: whether the shrinker was registered. - * - * The shrinker interface does not handle gracefully the removal of - * shrinker that was not registered before. This indication allows to - * simplify the unregistration process. - */ - bool shrinker_registered; + struct shrinker *shrinker; }; static struct vmballoon balloon; @@ -1568,29 +1559,27 @@ static unsigned long vmballoon_shrinker_count(struct shrinker *shrinker, static void vmballoon_unregister_shrinker(struct vmballoon *b) { - if (b->shrinker_registered) - unregister_shrinker(&b->shrinker); - b->shrinker_registered = false; + shrinker_free(b->shrinker); + b->shrinker = NULL; } static int vmballoon_register_shrinker(struct vmballoon *b) { - int r; - /* Do nothing if the shrinker is not enabled */ if (!vmwballoon_shrinker_enable) return 0; - b->shrinker.scan_objects = vmballoon_shrinker_scan; - b->shrinker.count_objects = vmballoon_shrinker_count; - b->shrinker.seeks = DEFAULT_SEEKS; + b->shrinker = shrinker_alloc(0, "vmw-balloon"); + if (!b->shrinker) + return -ENOMEM; - r = register_shrinker(&b->shrinker, "vmw-balloon"); + b->shrinker->scan_objects = vmballoon_shrinker_scan; + b->shrinker->count_objects = vmballoon_shrinker_count; + b->shrinker->private_data = b; - if (r == 0) - b->shrinker_registered = true; + shrinker_register(b->shrinker); - return r; + return 0; } /* @@ -1883,7 +1872,7 @@ static int __init vmballoon_init(void) error = vmballoon_register_shrinker(&balloon); if (error) - goto fail; + return error; /* * Initialization of compaction must be done after the call to @@ -1905,9 +1894,6 @@ static int __init vmballoon_init(void) vmballoon_debugfs_init(&balloon); return 0; -fail: - vmballoon_unregister_shrinker(&balloon); - return error; } /* diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 5b15936a5214..5cdc7b081baa 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -111,7 +111,7 @@ struct virtio_balloon { struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR]; /* Shrinker to return free pages - VIRTIO_BALLOON_F_FREE_PAGE_HINT */ - struct shrinker shrinker; + struct shrinker *shrinker; /* OOM notifier to deflate on OOM - VIRTIO_BALLOON_F_DEFLATE_ON_OOM */ struct notifier_block oom_nb; @@ -816,8 +816,7 @@ static unsigned long shrink_free_pages(struct virtio_balloon *vb, static unsigned long virtio_balloon_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) { - struct virtio_balloon *vb = container_of(shrinker, - struct virtio_balloon, shrinker); + struct virtio_balloon *vb = shrinker->private_data; return shrink_free_pages(vb, sc->nr_to_scan); } @@ -825,8 +824,7 @@ static unsigned long virtio_balloon_shrinker_scan(struct shrinker *shrinker, static unsigned long virtio_balloon_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc) { - struct virtio_balloon *vb = container_of(shrinker, - struct virtio_balloon, shrinker); + struct virtio_balloon *vb = shrinker->private_data; return vb->num_free_page_blocks * VIRTIO_BALLOON_HINT_BLOCK_PAGES; } @@ -847,16 +845,22 @@ static int virtio_balloon_oom_notify(struct notifier_block *nb, static void virtio_balloon_unregister_shrinker(struct virtio_balloon *vb) { - unregister_shrinker(&vb->shrinker); + shrinker_free(vb->shrinker); } static int virtio_balloon_register_shrinker(struct virtio_balloon *vb) { - vb->shrinker.scan_objects = virtio_balloon_shrinker_scan; - vb->shrinker.count_objects = virtio_balloon_shrinker_count; - vb->shrinker.seeks = DEFAULT_SEEKS; + vb->shrinker = shrinker_alloc(0, "virtio-balloon"); + if (!vb->shrinker) + return -ENOMEM; - return register_shrinker(&vb->shrinker, "virtio-balloon"); + vb->shrinker->scan_objects = virtio_balloon_shrinker_scan; + vb->shrinker->count_objects = virtio_balloon_shrinker_count; + vb->shrinker->private_data = vb; + + shrinker_register(vb->shrinker); + + return 0; } static int virtballoon_probe(struct virtio_device *vdev) diff --git a/drivers/xen/xenbus/xenbus_probe_backend.c b/drivers/xen/xenbus/xenbus_probe_backend.c index da96c260e26b..5ebb7233076f 100644 --- a/drivers/xen/xenbus/xenbus_probe_backend.c +++ b/drivers/xen/xenbus/xenbus_probe_backend.c @@ -284,13 +284,9 @@ static unsigned long backend_shrink_memory_count(struct shrinker *shrinker, return 0; } -static struct shrinker backend_memory_shrinker = { - .count_objects = backend_shrink_memory_count, - .seeks = DEFAULT_SEEKS, -}; - static int __init xenbus_probe_backend_init(void) { + struct shrinker *backend_memory_shrinker; static struct notifier_block xenstore_notifier = { .notifier_call = backend_probe_and_watch }; @@ -305,8 +301,15 @@ static int __init xenbus_probe_backend_init(void) register_xenstore_notifier(&xenstore_notifier); - if (register_shrinker(&backend_memory_shrinker, "xen-backend")) - pr_warn("shrinker registration failed\n"); + backend_memory_shrinker = shrinker_alloc(0, "xen-backend"); + if (!backend_memory_shrinker) { + pr_warn("shrinker allocation failed\n"); + return 0; + } + + backend_memory_shrinker->count_objects = backend_shrink_memory_count; + + shrinker_register(backend_memory_shrinker); return 0; } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 1a093ec0f7e3..b1798bed68f2 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1519,7 +1519,7 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type, error = -EBUSY; } else { snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); - shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s", fs_type->name, + shrinker_debugfs_rename(s->s_shrink, "sb-%s:%s", fs_type->name, s->s_id); btrfs_sb(s)->bdev_holder = fs_type; error = btrfs_fill_super(s, fs_devices, data); diff --git a/fs/buffer.c b/fs/buffer.c index 12e9a71c693d..edec8652788c 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -915,16 +915,12 @@ int remove_inode_buffers(struct inode *inode) * which may not fail from ordinary buffer allocations. */ struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size, - bool retry) + gfp_t gfp) { struct buffer_head *bh, *head; - gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT; long offset; struct mem_cgroup *memcg, *old_memcg; - if (retry) - gfp |= __GFP_NOFAIL; - /* The folio lock pins the memcg */ memcg = folio_memcg(folio); old_memcg = set_active_memcg(memcg); @@ -967,7 +963,11 @@ EXPORT_SYMBOL_GPL(folio_alloc_buffers); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry) { - return folio_alloc_buffers(page_folio(page), size, retry); + gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT; + if (retry) + gfp |= __GFP_NOFAIL; + + return folio_alloc_buffers(page_folio(page), size, gfp); } EXPORT_SYMBOL_GPL(alloc_page_buffers); @@ -1043,20 +1043,11 @@ grow_dev_page(struct block_device *bdev, sector_t block, struct buffer_head *bh; sector_t end_block; int ret = 0; - gfp_t gfp_mask; - - gfp_mask = mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS) | gfp; - - /* - * XXX: __getblk_slow() can not really deal with failure and - * will endlessly loop on improvised global reclaim. Prefer - * looping in the allocator rather than here, at least that - * code knows what it's doing. - */ - gfp_mask |= __GFP_NOFAIL; folio = __filemap_get_folio(inode->i_mapping, index, - FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp_mask); + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp); + if (IS_ERR(folio)) + return PTR_ERR(folio); bh = folio_buffers(folio); if (bh) { @@ -1069,7 +1060,10 @@ grow_dev_page(struct block_device *bdev, sector_t block, goto failed; } - bh = folio_alloc_buffers(folio, size, true); + ret = -ENOMEM; + bh = folio_alloc_buffers(folio, size, gfp | __GFP_ACCOUNT); + if (!bh) + goto failed; /* * Link the folio to the buffers and initialise them. Take the @@ -1420,33 +1414,36 @@ __find_get_block(struct block_device *bdev, sector_t block, unsigned size) } EXPORT_SYMBOL(__find_get_block); -/* - * __getblk_gfp() will locate (and, if necessary, create) the buffer_head - * which corresponds to the passed block_device, block and size. The - * returned buffer has its reference count incremented. +/** + * bdev_getblk - Get a buffer_head in a block device's buffer cache. + * @bdev: The block device. + * @block: The block number. + * @size: The size of buffer_heads for this @bdev. + * @gfp: The memory allocation flags to use. * - * __getblk_gfp() will lock up the machine if grow_dev_page's - * try_to_free_buffers() attempt is failing. FIXME, perhaps? + * Return: The buffer head, or NULL if memory could not be allocated. */ -struct buffer_head * -__getblk_gfp(struct block_device *bdev, sector_t block, - unsigned size, gfp_t gfp) +struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block, + unsigned size, gfp_t gfp) { struct buffer_head *bh = __find_get_block(bdev, block, size); - might_sleep(); - if (bh == NULL) - bh = __getblk_slow(bdev, block, size, gfp); - return bh; + might_alloc(gfp); + if (bh) + return bh; + + return __getblk_slow(bdev, block, size, gfp); } -EXPORT_SYMBOL(__getblk_gfp); +EXPORT_SYMBOL(bdev_getblk); /* * Do async read-ahead on a buffer.. */ void __breadahead(struct block_device *bdev, sector_t block, unsigned size) { - struct buffer_head *bh = __getblk(bdev, block, size); + struct buffer_head *bh = bdev_getblk(bdev, block, size, + GFP_NOWAIT | __GFP_MOVABLE); + if (likely(bh)) { bh_readahead(bh, REQ_RAHEAD); brelse(bh); @@ -1470,7 +1467,17 @@ struct buffer_head * __bread_gfp(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { - struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp); + struct buffer_head *bh; + + gfp |= mapping_gfp_constraint(bdev->bd_inode->i_mapping, ~__GFP_FS); + + /* + * Prefer looping in the allocator rather than here, at least that + * code knows what it's doing. + */ + gfp |= __GFP_NOFAIL; + + bh = bdev_getblk(bdev, block, size, gfp); if (likely(bh) && !buffer_uptodate(bh)) bh = __bread_slow(bh); @@ -1644,8 +1651,9 @@ void folio_create_empty_buffers(struct folio *folio, unsigned long blocksize, unsigned long b_state) { struct buffer_head *bh, *head, *tail; + gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT | __GFP_NOFAIL; - head = folio_alloc_buffers(folio, blocksize, true); + head = folio_alloc_buffers(folio, blocksize, gfp); bh = head; do { bh->b_state |= b_state; @@ -412,23 +412,23 @@ static struct page *dax_busy_page(void *entry) return NULL; } -/* - * dax_lock_page - Lock the DAX entry corresponding to a page - * @page: The page whose entry we want to lock +/** + * dax_lock_folio - Lock the DAX entry corresponding to a folio + * @folio: The folio whose entry we want to lock * * Context: Process context. - * Return: A cookie to pass to dax_unlock_page() or 0 if the entry could + * Return: A cookie to pass to dax_unlock_folio() or 0 if the entry could * not be locked. */ -dax_entry_t dax_lock_page(struct page *page) +dax_entry_t dax_lock_folio(struct folio *folio) { XA_STATE(xas, NULL, 0); void *entry; - /* Ensure page->mapping isn't freed while we look at it */ + /* Ensure folio->mapping isn't freed while we look at it */ rcu_read_lock(); for (;;) { - struct address_space *mapping = READ_ONCE(page->mapping); + struct address_space *mapping = READ_ONCE(folio->mapping); entry = NULL; if (!mapping || !dax_mapping(mapping)) @@ -447,11 +447,11 @@ dax_entry_t dax_lock_page(struct page *page) xas.xa = &mapping->i_pages; xas_lock_irq(&xas); - if (mapping != page->mapping) { + if (mapping != folio->mapping) { xas_unlock_irq(&xas); continue; } - xas_set(&xas, page->index); + xas_set(&xas, folio->index); entry = xas_load(&xas); if (dax_is_locked(entry)) { rcu_read_unlock(); @@ -467,10 +467,10 @@ dax_entry_t dax_lock_page(struct page *page) return (dax_entry_t)entry; } -void dax_unlock_page(struct page *page, dax_entry_t cookie) +void dax_unlock_folio(struct folio *folio, dax_entry_t cookie) { - struct address_space *mapping = page->mapping; - XA_STATE(xas, &mapping->i_pages, page->index); + struct address_space *mapping = folio->mapping; + XA_STATE(xas, &mapping->i_pages, folio->index); if (S_ISCHR(mapping->host->i_mode)) return; diff --git a/fs/erofs/utils.c b/fs/erofs/utils.c index cc6fb9e98899..e9c25cd7b601 100644 --- a/fs/erofs/utils.c +++ b/fs/erofs/utils.c @@ -270,19 +270,24 @@ static unsigned long erofs_shrink_scan(struct shrinker *shrink, return freed; } -static struct shrinker erofs_shrinker_info = { - .scan_objects = erofs_shrink_scan, - .count_objects = erofs_shrink_count, - .seeks = DEFAULT_SEEKS, -}; +static struct shrinker *erofs_shrinker_info; int __init erofs_init_shrinker(void) { - return register_shrinker(&erofs_shrinker_info, "erofs-shrinker"); + erofs_shrinker_info = shrinker_alloc(0, "erofs-shrinker"); + if (!erofs_shrinker_info) + return -ENOMEM; + + erofs_shrinker_info->count_objects = erofs_shrink_count; + erofs_shrinker_info->scan_objects = erofs_shrink_scan; + + shrinker_register(erofs_shrinker_info); + + return 0; } void erofs_exit_shrinker(void) { - unregister_shrinker(&erofs_shrinker_info); + shrinker_free(erofs_shrinker_info); } #endif /* !CONFIG_EROFS_FS_ZIP */ diff --git a/fs/exec.c b/fs/exec.c index 6518e33ea813..4aa19b24f281 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -713,7 +713,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) * process cleanup to remove whatever mess we made. */ if (length != move_page_tables(vma, old_start, - vma, new_start, length, false)) + vma, new_start, length, false, true)) return -ENOMEM; lru_add_drain(); @@ -986,8 +986,6 @@ static int exec_mmap(struct mm_struct *mm) tsk = current; old_mm = current->mm; exec_mm_release(tsk, old_mm); - if (old_mm) - sync_mm_rss(old_mm); ret = down_write_killable(&tsk->signal->exec_update_lock); if (ret) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 9418359b1d9d..8eeff770992c 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1653,7 +1653,7 @@ struct ext4_sb_info { __u32 s_csum_seed; /* Reclaim extents from extent status tree */ - struct shrinker s_es_shrinker; + struct shrinker *s_es_shrinker; struct list_head s_es_list; /* List of inodes with reclaimable extents */ long s_es_nr_inode; struct ext4_es_stats s_es_stats; diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 6f7de14c0fa8..deec7d1f4e50 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -1606,7 +1606,7 @@ static unsigned long ext4_es_count(struct shrinker *shrink, unsigned long nr; struct ext4_sb_info *sbi; - sbi = container_of(shrink, struct ext4_sb_info, s_es_shrinker); + sbi = shrink->private_data; nr = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt); trace_ext4_es_shrink_count(sbi->s_sb, sc->nr_to_scan, nr); return nr; @@ -1615,8 +1615,7 @@ static unsigned long ext4_es_count(struct shrinker *shrink, static unsigned long ext4_es_scan(struct shrinker *shrink, struct shrink_control *sc) { - struct ext4_sb_info *sbi = container_of(shrink, - struct ext4_sb_info, s_es_shrinker); + struct ext4_sb_info *sbi = shrink->private_data; int nr_to_scan = sc->nr_to_scan; int ret, nr_shrunk; @@ -1700,13 +1699,17 @@ int ext4_es_register_shrinker(struct ext4_sb_info *sbi) if (err) goto err3; - sbi->s_es_shrinker.scan_objects = ext4_es_scan; - sbi->s_es_shrinker.count_objects = ext4_es_count; - sbi->s_es_shrinker.seeks = DEFAULT_SEEKS; - err = register_shrinker(&sbi->s_es_shrinker, "ext4-es:%s", - sbi->s_sb->s_id); - if (err) + sbi->s_es_shrinker = shrinker_alloc(0, "ext4-es:%s", sbi->s_sb->s_id); + if (!sbi->s_es_shrinker) { + err = -ENOMEM; goto err4; + } + + sbi->s_es_shrinker->scan_objects = ext4_es_scan; + sbi->s_es_shrinker->count_objects = ext4_es_count; + sbi->s_es_shrinker->private_data = sbi; + + shrinker_register(sbi->s_es_shrinker); return 0; err4: @@ -1726,7 +1729,7 @@ void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi) percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_misses); percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt); percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt); - unregister_shrinker(&sbi->s_es_shrinker); + shrinker_free(sbi->s_es_shrinker); } /* diff --git a/fs/ext4/super.c b/fs/ext4/super.c index dbebd8b3127e..c00ec159dea5 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -244,18 +244,25 @@ static struct buffer_head *__ext4_sb_bread_gfp(struct super_block *sb, struct buffer_head *ext4_sb_bread(struct super_block *sb, sector_t block, blk_opf_t op_flags) { - return __ext4_sb_bread_gfp(sb, block, op_flags, __GFP_MOVABLE); + gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_inode->i_mapping, + ~__GFP_FS) | __GFP_MOVABLE; + + return __ext4_sb_bread_gfp(sb, block, op_flags, gfp); } struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb, sector_t block) { - return __ext4_sb_bread_gfp(sb, block, 0, 0); + gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_inode->i_mapping, + ~__GFP_FS); + + return __ext4_sb_bread_gfp(sb, block, 0, gfp); } void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block) { - struct buffer_head *bh = sb_getblk_gfp(sb, block, 0); + struct buffer_head *bh = bdev_getblk(sb->s_bdev, block, + sb->s_blocksize, GFP_NOWAIT); if (likely(bh)) { if (trylock_buffer(bh)) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index a8c8232852bb..fe25ff9cebbe 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -83,11 +83,26 @@ void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate, #endif /* f2fs-wide shrinker description */ -static struct shrinker f2fs_shrinker_info = { - .scan_objects = f2fs_shrink_scan, - .count_objects = f2fs_shrink_count, - .seeks = DEFAULT_SEEKS, -}; +static struct shrinker *f2fs_shrinker_info; + +static int __init f2fs_init_shrinker(void) +{ + f2fs_shrinker_info = shrinker_alloc(0, "f2fs-shrinker"); + if (!f2fs_shrinker_info) + return -ENOMEM; + + f2fs_shrinker_info->count_objects = f2fs_shrink_count; + f2fs_shrinker_info->scan_objects = f2fs_shrink_scan; + + shrinker_register(f2fs_shrinker_info); + + return 0; +} + +static void f2fs_exit_shrinker(void) +{ + shrinker_free(f2fs_shrinker_info); +} enum { Opt_gc_background, @@ -4944,7 +4959,7 @@ static int __init init_f2fs_fs(void) err = f2fs_init_sysfs(); if (err) goto free_garbage_collection_cache; - err = register_shrinker(&f2fs_shrinker_info, "f2fs-shrinker"); + err = f2fs_init_shrinker(); if (err) goto free_sysfs; err = register_filesystem(&f2fs_fs_type); @@ -4989,7 +5004,7 @@ free_root_stats: f2fs_destroy_root_stats(); unregister_filesystem(&f2fs_fs_type); free_shrinker: - unregister_shrinker(&f2fs_shrinker_info); + f2fs_exit_shrinker(); free_sysfs: f2fs_exit_sysfs(); free_garbage_collection_cache: @@ -5021,7 +5036,7 @@ static void __exit exit_f2fs_fs(void) f2fs_destroy_post_read_processing(); f2fs_destroy_root_stats(); unregister_filesystem(&f2fs_fs_type); - unregister_shrinker(&f2fs_shrinker_info); + f2fs_exit_shrinker(); f2fs_exit_sysfs(); f2fs_destroy_garbage_collection_cache(); f2fs_destroy_extent_cache(); diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 4a280be229a6..482291bb08d8 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -2041,11 +2041,7 @@ static unsigned long gfs2_glock_shrink_count(struct shrinker *shrink, return vfs_pressure_ratio(atomic_read(&lru_count)); } -static struct shrinker glock_shrinker = { - .seeks = DEFAULT_SEEKS, - .count_objects = gfs2_glock_shrink_count, - .scan_objects = gfs2_glock_shrink_scan, -}; +static struct shrinker *glock_shrinker; /** * glock_hash_walk - Call a function for glock in a hash bucket @@ -2465,13 +2461,18 @@ int __init gfs2_glock_init(void) return -ENOMEM; } - ret = register_shrinker(&glock_shrinker, "gfs2-glock"); - if (ret) { + glock_shrinker = shrinker_alloc(0, "gfs2-glock"); + if (!glock_shrinker) { destroy_workqueue(glock_workqueue); rhashtable_destroy(&gl_hash_table); - return ret; + return -ENOMEM; } + glock_shrinker->count_objects = gfs2_glock_shrink_count; + glock_shrinker->scan_objects = gfs2_glock_shrink_scan; + + shrinker_register(glock_shrinker); + for (i = 0; i < GLOCK_WAIT_TABLE_SIZE; i++) init_waitqueue_head(glock_wait_table + i); @@ -2480,7 +2481,7 @@ int __init gfs2_glock_init(void) void gfs2_glock_exit(void) { - unregister_shrinker(&glock_shrinker); + shrinker_free(glock_shrinker); rhashtable_destroy(&gl_hash_table); destroy_workqueue(glock_workqueue); } diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 66eb98b690a2..79be0cdc730c 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -147,7 +147,7 @@ static int __init init_gfs2_fs(void) if (!gfs2_trans_cachep) goto fail_cachep8; - error = register_shrinker(&gfs2_qd_shrinker, "gfs2-qd"); + error = gfs2_qd_shrinker_init(); if (error) goto fail_shrinker; @@ -196,7 +196,7 @@ fail_wq3: fail_wq2: destroy_workqueue(gfs2_recovery_wq); fail_wq1: - unregister_shrinker(&gfs2_qd_shrinker); + gfs2_qd_shrinker_exit(); fail_shrinker: kmem_cache_destroy(gfs2_trans_cachep); fail_cachep8: @@ -229,7 +229,7 @@ fail_lru: static void __exit exit_gfs2_fs(void) { - unregister_shrinker(&gfs2_qd_shrinker); + gfs2_qd_shrinker_exit(); gfs2_glock_exit(); gfs2_unregister_debugfs(); unregister_filesystem(&gfs2_fs_type); diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 171b2713d2e5..d3d013d1d5ac 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -196,13 +196,26 @@ static unsigned long gfs2_qd_shrink_count(struct shrinker *shrink, return vfs_pressure_ratio(list_lru_shrink_count(&gfs2_qd_lru, sc)); } -struct shrinker gfs2_qd_shrinker = { - .count_objects = gfs2_qd_shrink_count, - .scan_objects = gfs2_qd_shrink_scan, - .seeks = DEFAULT_SEEKS, - .flags = SHRINKER_NUMA_AWARE, -}; +static struct shrinker *gfs2_qd_shrinker; + +int __init gfs2_qd_shrinker_init(void) +{ + gfs2_qd_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE, "gfs2-qd"); + if (!gfs2_qd_shrinker) + return -ENOMEM; + + gfs2_qd_shrinker->count_objects = gfs2_qd_shrink_count; + gfs2_qd_shrinker->scan_objects = gfs2_qd_shrink_scan; + + shrinker_register(gfs2_qd_shrinker); + return 0; +} + +void gfs2_qd_shrinker_exit(void) +{ + shrinker_free(gfs2_qd_shrinker); +} static u64 qd2index(struct gfs2_quota_data *qd) { diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h index 1429945215a0..36f54b426b0c 100644 --- a/fs/gfs2/quota.h +++ b/fs/gfs2/quota.h @@ -60,7 +60,8 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip, } extern const struct quotactl_ops gfs2_quotactl_ops; -extern struct shrinker gfs2_qd_shrinker; +int __init gfs2_qd_shrinker_init(void); +void gfs2_qd_shrinker_exit(void); extern struct list_lru gfs2_qd_lru; extern void __init gfs2_quota_hash_init(void); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 316c4cebd3f3..926d01c493fb 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -295,7 +295,7 @@ static size_t adjust_range_hwpoison(struct page *page, size_t offset, size_t byt size_t res = 0; /* First subpage to start the loop. */ - page += offset / PAGE_SIZE; + page = nth_page(page, offset / PAGE_SIZE); offset %= PAGE_SIZE; while (1) { if (is_raw_hwpoison_page_in_hugepage(page)) @@ -309,7 +309,7 @@ static size_t adjust_range_hwpoison(struct page *page, size_t offset, size_t byt break; offset += n; if (offset == PAGE_SIZE) { - page++; + page = nth_page(page, 1); offset = 0; } } @@ -334,7 +334,7 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to) ssize_t retval = 0; while (iov_iter_count(to)) { - struct page *page; + struct folio *folio; size_t nr, copied, want; /* nr is the maximum number of bytes to copy from this page */ @@ -352,18 +352,18 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to) } nr = nr - offset; - /* Find the page */ - page = find_lock_page(mapping, index); - if (unlikely(page == NULL)) { + /* Find the folio */ + folio = filemap_lock_hugetlb_folio(h, mapping, index); + if (IS_ERR(folio)) { /* * We have a HOLE, zero out the user-buffer for the * length of the hole or request. */ copied = iov_iter_zero(nr, to); } else { - unlock_page(page); + folio_unlock(folio); - if (!PageHWPoison(page)) + if (!folio_test_has_hwpoisoned(folio)) want = nr; else { /* @@ -371,19 +371,19 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to) * touching the 1st raw HWPOISON subpage after * offset. */ - want = adjust_range_hwpoison(page, offset, nr); + want = adjust_range_hwpoison(&folio->page, offset, nr); if (want == 0) { - put_page(page); + folio_put(folio); retval = -EIO; break; } } /* - * We have the page, copy it to user space buffer. + * We have the folio, copy it to user space buffer. */ - copied = copy_page_to_iter(page, offset, want, to); - put_page(page); + copied = copy_folio_to_iter(folio, offset, want, to); + folio_put(folio); } offset += copied; retval += copied; @@ -661,21 +661,20 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, { struct hstate *h = hstate_inode(inode); struct address_space *mapping = &inode->i_data; - const pgoff_t start = lstart >> huge_page_shift(h); - const pgoff_t end = lend >> huge_page_shift(h); + const pgoff_t end = lend >> PAGE_SHIFT; struct folio_batch fbatch; pgoff_t next, index; int i, freed = 0; bool truncate_op = (lend == LLONG_MAX); folio_batch_init(&fbatch); - next = start; + next = lstart >> PAGE_SHIFT; while (filemap_get_folios(mapping, &next, end - 1, &fbatch)) { for (i = 0; i < folio_batch_count(&fbatch); ++i) { struct folio *folio = fbatch.folios[i]; u32 hash = 0; - index = folio->index; + index = folio->index >> huge_page_order(h); hash = hugetlb_fault_mutex_hash(mapping, index); mutex_lock(&hugetlb_fault_mutex_table[hash]); @@ -693,7 +692,9 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, } if (truncate_op) - (void)hugetlb_unreserve_pages(inode, start, LONG_MAX, freed); + (void)hugetlb_unreserve_pages(inode, + lstart >> huge_page_shift(h), + LONG_MAX, freed); } static void hugetlbfs_evict_inode(struct inode *inode) @@ -741,7 +742,7 @@ static void hugetlbfs_zero_partial_page(struct hstate *h, pgoff_t idx = start >> huge_page_shift(h); struct folio *folio; - folio = filemap_lock_folio(mapping, idx); + folio = filemap_lock_hugetlb_folio(h, mapping, idx); if (IS_ERR(folio)) return; @@ -886,7 +887,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, mutex_lock(&hugetlb_fault_mutex_table[hash]); /* See if already present in mapping to avoid alloc/free */ - folio = filemap_get_folio(mapping, index); + folio = filemap_get_folio(mapping, index << huge_page_order(h)); if (!IS_ERR(folio)) { folio_put(folio); mutex_unlock(&hugetlb_fault_mutex_table[hash]); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 30dec2bd2ecc..ed53188472f9 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1290,7 +1290,7 @@ static int jbd2_min_tag_size(void) static unsigned long jbd2_journal_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { - journal_t *journal = container_of(shrink, journal_t, j_shrinker); + journal_t *journal = shrink->private_data; unsigned long nr_to_scan = sc->nr_to_scan; unsigned long nr_shrunk; unsigned long count; @@ -1316,7 +1316,7 @@ static unsigned long jbd2_journal_shrink_scan(struct shrinker *shrink, static unsigned long jbd2_journal_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { - journal_t *journal = container_of(shrink, journal_t, j_shrinker); + journal_t *journal = shrink->private_data; unsigned long count; count = percpu_counter_read_positive(&journal->j_checkpoint_jh_count); @@ -1588,14 +1588,21 @@ static journal_t *journal_init_common(struct block_device *bdev, goto err_cleanup; journal->j_shrink_transaction = NULL; - journal->j_shrinker.scan_objects = jbd2_journal_shrink_scan; - journal->j_shrinker.count_objects = jbd2_journal_shrink_count; - journal->j_shrinker.seeks = DEFAULT_SEEKS; - journal->j_shrinker.batch = journal->j_max_transaction_buffers; - err = register_shrinker(&journal->j_shrinker, "jbd2-journal:(%u:%u)", - MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev)); - if (err) + + journal->j_shrinker = shrinker_alloc(0, "jbd2-journal:(%u:%u)", + MAJOR(bdev->bd_dev), + MINOR(bdev->bd_dev)); + if (!journal->j_shrinker) { + err = -ENOMEM; goto err_cleanup; + } + + journal->j_shrinker->scan_objects = jbd2_journal_shrink_scan; + journal->j_shrinker->count_objects = jbd2_journal_shrink_count; + journal->j_shrinker->batch = journal->j_max_transaction_buffers; + journal->j_shrinker->private_data = journal; + + shrinker_register(journal->j_shrinker); return journal; @@ -2172,9 +2179,9 @@ int jbd2_journal_destroy(journal_t *journal) brelse(journal->j_sb_buffer); } - if (journal->j_shrinker.flags & SHRINKER_REGISTERED) { + if (journal->j_shrinker) { percpu_counter_destroy(&journal->j_checkpoint_jh_count); - unregister_shrinker(&journal->j_shrinker); + shrinker_free(journal->j_shrinker); } if (journal->j_proc_entry) jbd2_stats_proc_exit(journal); diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index c4bf26142eec..79b96e74a8a0 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -265,7 +265,7 @@ static int kernfs_fill_super(struct super_block *sb, struct kernfs_fs_context *k sb->s_time_gran = 1; /* sysfs dentries and inodes don't require IO to create */ - sb->s_shrink.seeks = 0; + sb->s_shrink->seeks = 0; /* get root inode, initialize and unlock it */ down_read(&kf_root->kernfs_rwsem); diff --git a/fs/mbcache.c b/fs/mbcache.c index 2a4b8b549e93..82aa7a35db26 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -37,7 +37,7 @@ struct mb_cache { struct list_head c_list; /* Number of entries in cache */ unsigned long c_entry_count; - struct shrinker c_shrink; + struct shrinker *c_shrink; /* Work for shrinking when the cache has too many entries */ struct work_struct c_shrink_work; }; @@ -293,8 +293,7 @@ EXPORT_SYMBOL(mb_cache_entry_touch); static unsigned long mb_cache_count(struct shrinker *shrink, struct shrink_control *sc) { - struct mb_cache *cache = container_of(shrink, struct mb_cache, - c_shrink); + struct mb_cache *cache = shrink->private_data; return cache->c_entry_count; } @@ -333,8 +332,7 @@ static unsigned long mb_cache_shrink(struct mb_cache *cache, static unsigned long mb_cache_scan(struct shrinker *shrink, struct shrink_control *sc) { - struct mb_cache *cache = container_of(shrink, struct mb_cache, - c_shrink); + struct mb_cache *cache = shrink->private_data; return mb_cache_shrink(cache, sc->nr_to_scan); } @@ -377,15 +375,19 @@ struct mb_cache *mb_cache_create(int bucket_bits) for (i = 0; i < bucket_count; i++) INIT_HLIST_BL_HEAD(&cache->c_hash[i]); - cache->c_shrink.count_objects = mb_cache_count; - cache->c_shrink.scan_objects = mb_cache_scan; - cache->c_shrink.seeks = DEFAULT_SEEKS; - if (register_shrinker(&cache->c_shrink, "mbcache-shrinker")) { + cache->c_shrink = shrinker_alloc(0, "mbcache-shrinker"); + if (!cache->c_shrink) { kfree(cache->c_hash); kfree(cache); goto err_out; } + cache->c_shrink->count_objects = mb_cache_count; + cache->c_shrink->scan_objects = mb_cache_scan; + cache->c_shrink->private_data = cache; + + shrinker_register(cache->c_shrink); + INIT_WORK(&cache->c_shrink_work, mb_cache_shrink_worker); return cache; @@ -406,7 +408,7 @@ void mb_cache_destroy(struct mb_cache *cache) { struct mb_cache_entry *entry, *next; - unregister_shrinker(&cache->c_shrink); + shrinker_free(cache->c_shrink); /* * We don't bother with any locking. Cache must not be used at this diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c index 911f634ba3da..2ad66a8922f4 100644 --- a/fs/nfs/nfs42xattr.c +++ b/fs/nfs/nfs42xattr.c @@ -796,28 +796,9 @@ static unsigned long nfs4_xattr_cache_scan(struct shrinker *shrink, static unsigned long nfs4_xattr_entry_scan(struct shrinker *shrink, struct shrink_control *sc); -static struct shrinker nfs4_xattr_cache_shrinker = { - .count_objects = nfs4_xattr_cache_count, - .scan_objects = nfs4_xattr_cache_scan, - .seeks = DEFAULT_SEEKS, - .flags = SHRINKER_MEMCG_AWARE, -}; - -static struct shrinker nfs4_xattr_entry_shrinker = { - .count_objects = nfs4_xattr_entry_count, - .scan_objects = nfs4_xattr_entry_scan, - .seeks = DEFAULT_SEEKS, - .batch = 512, - .flags = SHRINKER_MEMCG_AWARE, -}; - -static struct shrinker nfs4_xattr_large_entry_shrinker = { - .count_objects = nfs4_xattr_entry_count, - .scan_objects = nfs4_xattr_entry_scan, - .seeks = 1, - .batch = 512, - .flags = SHRINKER_MEMCG_AWARE, -}; +static struct shrinker *nfs4_xattr_cache_shrinker; +static struct shrinker *nfs4_xattr_entry_shrinker; +static struct shrinker *nfs4_xattr_large_entry_shrinker; static enum lru_status cache_lru_isolate(struct list_head *item, @@ -943,7 +924,7 @@ nfs4_xattr_entry_scan(struct shrinker *shrink, struct shrink_control *sc) struct nfs4_xattr_entry *entry; struct list_lru *lru; - lru = (shrink == &nfs4_xattr_large_entry_shrinker) ? + lru = (shrink == nfs4_xattr_large_entry_shrinker) ? &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru; freed = list_lru_shrink_walk(lru, sc, entry_lru_isolate, &dispose); @@ -971,7 +952,7 @@ nfs4_xattr_entry_count(struct shrinker *shrink, struct shrink_control *sc) unsigned long count; struct list_lru *lru; - lru = (shrink == &nfs4_xattr_large_entry_shrinker) ? + lru = (shrink == nfs4_xattr_large_entry_shrinker) ? &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru; count = list_lru_shrink_count(lru, sc); @@ -991,18 +972,34 @@ static void nfs4_xattr_cache_init_once(void *p) INIT_LIST_HEAD(&cache->dispose); } -static int nfs4_xattr_shrinker_init(struct shrinker *shrinker, - struct list_lru *lru, const char *name) +typedef unsigned long (*count_objects_cb)(struct shrinker *s, + struct shrink_control *sc); +typedef unsigned long (*scan_objects_cb)(struct shrinker *s, + struct shrink_control *sc); + +static int __init nfs4_xattr_shrinker_init(struct shrinker **shrinker, + struct list_lru *lru, const char *name, + count_objects_cb count, + scan_objects_cb scan, long batch, int seeks) { - int ret = 0; + int ret; - ret = register_shrinker(shrinker, name); - if (ret) + *shrinker = shrinker_alloc(SHRINKER_MEMCG_AWARE, name); + if (!*shrinker) + return -ENOMEM; + + ret = list_lru_init_memcg(lru, *shrinker); + if (ret) { + shrinker_free(*shrinker); return ret; + } - ret = list_lru_init_memcg(lru, shrinker); - if (ret) - unregister_shrinker(shrinker); + (*shrinker)->count_objects = count; + (*shrinker)->scan_objects = scan; + (*shrinker)->batch = batch; + (*shrinker)->seeks = seeks; + + shrinker_register(*shrinker); return ret; } @@ -1010,7 +1007,7 @@ static int nfs4_xattr_shrinker_init(struct shrinker *shrinker, static void nfs4_xattr_shrinker_destroy(struct shrinker *shrinker, struct list_lru *lru) { - unregister_shrinker(shrinker); + shrinker_free(shrinker); list_lru_destroy(lru); } @@ -1026,27 +1023,31 @@ int __init nfs4_xattr_cache_init(void) return -ENOMEM; ret = nfs4_xattr_shrinker_init(&nfs4_xattr_cache_shrinker, - &nfs4_xattr_cache_lru, - "nfs-xattr_cache"); + &nfs4_xattr_cache_lru, "nfs-xattr_cache", + nfs4_xattr_cache_count, + nfs4_xattr_cache_scan, 0, DEFAULT_SEEKS); if (ret) goto out1; ret = nfs4_xattr_shrinker_init(&nfs4_xattr_entry_shrinker, - &nfs4_xattr_entry_lru, - "nfs-xattr_entry"); + &nfs4_xattr_entry_lru, "nfs-xattr_entry", + nfs4_xattr_entry_count, + nfs4_xattr_entry_scan, 512, DEFAULT_SEEKS); if (ret) goto out2; ret = nfs4_xattr_shrinker_init(&nfs4_xattr_large_entry_shrinker, &nfs4_xattr_large_entry_lru, - "nfs-xattr_large_entry"); + "nfs-xattr_large_entry", + nfs4_xattr_entry_count, + nfs4_xattr_entry_scan, 512, 1); if (!ret) return 0; - nfs4_xattr_shrinker_destroy(&nfs4_xattr_entry_shrinker, + nfs4_xattr_shrinker_destroy(nfs4_xattr_entry_shrinker, &nfs4_xattr_entry_lru); out2: - nfs4_xattr_shrinker_destroy(&nfs4_xattr_cache_shrinker, + nfs4_xattr_shrinker_destroy(nfs4_xattr_cache_shrinker, &nfs4_xattr_cache_lru); out1: kmem_cache_destroy(nfs4_xattr_cache_cachep); @@ -1056,11 +1057,11 @@ out1: void nfs4_xattr_cache_exit(void) { - nfs4_xattr_shrinker_destroy(&nfs4_xattr_large_entry_shrinker, + nfs4_xattr_shrinker_destroy(nfs4_xattr_large_entry_shrinker, &nfs4_xattr_large_entry_lru); - nfs4_xattr_shrinker_destroy(&nfs4_xattr_entry_shrinker, + nfs4_xattr_shrinker_destroy(nfs4_xattr_entry_shrinker, &nfs4_xattr_entry_lru); - nfs4_xattr_shrinker_destroy(&nfs4_xattr_cache_shrinker, + nfs4_xattr_shrinker_destroy(nfs4_xattr_cache_shrinker, &nfs4_xattr_cache_lru); kmem_cache_destroy(nfs4_xattr_cache_cachep); } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 0d6473cb00cb..09ded7f63acf 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -129,11 +129,7 @@ static void nfs_ssc_unregister_ops(void) } #endif /* CONFIG_NFS_V4_2 */ -static struct shrinker acl_shrinker = { - .count_objects = nfs_access_cache_count, - .scan_objects = nfs_access_cache_scan, - .seeks = DEFAULT_SEEKS, -}; +static struct shrinker *acl_shrinker; /* * Register the NFS filesystems @@ -153,9 +149,18 @@ int __init register_nfs_fs(void) ret = nfs_register_sysctl(); if (ret < 0) goto error_2; - ret = register_shrinker(&acl_shrinker, "nfs-acl"); - if (ret < 0) + + acl_shrinker = shrinker_alloc(0, "nfs-acl"); + if (!acl_shrinker) { + ret = -ENOMEM; goto error_3; + } + + acl_shrinker->count_objects = nfs_access_cache_count; + acl_shrinker->scan_objects = nfs_access_cache_scan; + + shrinker_register(acl_shrinker); + #ifdef CONFIG_NFS_V4_2 nfs_ssc_register_ops(); #endif @@ -175,7 +180,7 @@ error_0: */ void __exit unregister_nfs_fs(void) { - unregister_shrinker(&acl_shrinker); + shrinker_free(acl_shrinker); nfs_unregister_sysctl(); unregister_nfs4_fs(); #ifdef CONFIG_NFS_V4_2 diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index ee9c923192e0..9c62b4502539 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -521,11 +521,7 @@ nfsd_file_lru_scan(struct shrinker *s, struct shrink_control *sc) return ret; } -static struct shrinker nfsd_file_shrinker = { - .scan_objects = nfsd_file_lru_scan, - .count_objects = nfsd_file_lru_count, - .seeks = 1, -}; +static struct shrinker *nfsd_file_shrinker; /** * nfsd_file_cond_queue - conditionally unhash and queue a nfsd_file @@ -746,12 +742,19 @@ nfsd_file_cache_init(void) goto out_err; } - ret = register_shrinker(&nfsd_file_shrinker, "nfsd-filecache"); - if (ret) { - pr_err("nfsd: failed to register nfsd_file_shrinker: %d\n", ret); + nfsd_file_shrinker = shrinker_alloc(0, "nfsd-filecache"); + if (!nfsd_file_shrinker) { + ret = -ENOMEM; + pr_err("nfsd: failed to allocate nfsd_file_shrinker\n"); goto out_lru; } + nfsd_file_shrinker->count_objects = nfsd_file_lru_count; + nfsd_file_shrinker->scan_objects = nfsd_file_lru_scan; + nfsd_file_shrinker->seeks = 1; + + shrinker_register(nfsd_file_shrinker); + ret = lease_register_notifier(&nfsd_file_lease_notifier); if (ret) { pr_err("nfsd: unable to register lease notifier: %d\n", ret); @@ -774,7 +777,7 @@ out: out_notifier: lease_unregister_notifier(&nfsd_file_lease_notifier); out_shrinker: - unregister_shrinker(&nfsd_file_shrinker); + shrinker_free(nfsd_file_shrinker); out_lru: list_lru_destroy(&nfsd_file_lru); out_err: @@ -891,7 +894,7 @@ nfsd_file_cache_shutdown(void) return; lease_unregister_notifier(&nfsd_file_lease_notifier); - unregister_shrinker(&nfsd_file_shrinker); + shrinker_free(nfsd_file_shrinker); /* * make sure all callers of nfsd_file_lru_cb are done before * calling nfsd_file_cache_purge diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index ec49b200b797..ab303a8b77d5 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -177,7 +177,7 @@ struct nfsd_net { /* size of cache when we saw the longest hash chain */ unsigned int longest_chain_cachesize; - struct shrinker nfsd_reply_cache_shrinker; + struct shrinker *nfsd_reply_cache_shrinker; /* tracking server-to-server copy mounts */ spinlock_t nfsd_ssc_lock; @@ -195,7 +195,7 @@ struct nfsd_net { int nfs4_max_clients; atomic_t nfsd_courtesy_clients; - struct shrinker nfsd_client_shrinker; + struct shrinker *nfsd_client_shrinker; struct work_struct nfsd_shrinker_work; }; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 8534693eb6a4..23b3b38c8cda 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -4400,8 +4400,7 @@ static unsigned long nfsd4_state_shrinker_count(struct shrinker *shrink, struct shrink_control *sc) { int count; - struct nfsd_net *nn = container_of(shrink, - struct nfsd_net, nfsd_client_shrinker); + struct nfsd_net *nn = shrink->private_data; count = atomic_read(&nn->nfsd_courtesy_clients); if (!count) @@ -8149,12 +8148,16 @@ static int nfs4_state_create_net(struct net *net) INIT_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker); get_net(net); - nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan; - nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count; - nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS; - - if (register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client")) + nn->nfsd_client_shrinker = shrinker_alloc(0, "nfsd-client"); + if (!nn->nfsd_client_shrinker) goto err_shrinker; + + nn->nfsd_client_shrinker->scan_objects = nfsd4_state_shrinker_scan; + nn->nfsd_client_shrinker->count_objects = nfsd4_state_shrinker_count; + nn->nfsd_client_shrinker->private_data = nn; + + shrinker_register(nn->nfsd_client_shrinker); + return 0; err_shrinker: @@ -8252,7 +8255,7 @@ nfs4_state_shutdown_net(struct net *net) struct list_head *pos, *next, reaplist; struct nfsd_net *nn = net_generic(net, nfsd_net_id); - unregister_shrinker(&nn->nfsd_client_shrinker); + shrinker_free(nn->nfsd_client_shrinker); cancel_work(&nn->nfsd_shrinker_work); cancel_delayed_work_sync(&nn->laundromat_work); locks_end_grace(&nn->nfsd4_manager); diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 80621a709510..fd56a52aa5fb 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -201,26 +201,29 @@ int nfsd_reply_cache_init(struct nfsd_net *nn) { unsigned int hashsize; unsigned int i; - int status = 0; nn->max_drc_entries = nfsd_cache_size_limit(); atomic_set(&nn->num_drc_entries, 0); hashsize = nfsd_hashsize(nn->max_drc_entries); nn->maskbits = ilog2(hashsize); - nn->nfsd_reply_cache_shrinker.scan_objects = nfsd_reply_cache_scan; - nn->nfsd_reply_cache_shrinker.count_objects = nfsd_reply_cache_count; - nn->nfsd_reply_cache_shrinker.seeks = 1; - status = register_shrinker(&nn->nfsd_reply_cache_shrinker, - "nfsd-reply:%s", nn->nfsd_name); - if (status) - return status; - nn->drc_hashtbl = kvzalloc(array_size(hashsize, sizeof(*nn->drc_hashtbl)), GFP_KERNEL); if (!nn->drc_hashtbl) + return -ENOMEM; + + nn->nfsd_reply_cache_shrinker = shrinker_alloc(0, "nfsd-reply:%s", + nn->nfsd_name); + if (!nn->nfsd_reply_cache_shrinker) goto out_shrinker; + nn->nfsd_reply_cache_shrinker->scan_objects = nfsd_reply_cache_scan; + nn->nfsd_reply_cache_shrinker->count_objects = nfsd_reply_cache_count; + nn->nfsd_reply_cache_shrinker->seeks = 1; + nn->nfsd_reply_cache_shrinker->private_data = nn; + + shrinker_register(nn->nfsd_reply_cache_shrinker); + for (i = 0; i < hashsize; i++) { INIT_LIST_HEAD(&nn->drc_hashtbl[i].lru_head); spin_lock_init(&nn->drc_hashtbl[i].cache_lock); @@ -229,7 +232,7 @@ int nfsd_reply_cache_init(struct nfsd_net *nn) return 0; out_shrinker: - unregister_shrinker(&nn->nfsd_reply_cache_shrinker); + kvfree(nn->drc_hashtbl); printk(KERN_ERR "nfsd: failed to allocate reply cache\n"); return -ENOMEM; } @@ -239,7 +242,7 @@ void nfsd_reply_cache_shutdown(struct nfsd_net *nn) struct nfsd_cacherep *rp; unsigned int i; - unregister_shrinker(&nn->nfsd_reply_cache_shrinker); + shrinker_free(nn->nfsd_reply_cache_shrinker); for (i = 0; i < nn->drc_hashsize; i++) { struct list_head *head = &nn->drc_hashtbl[i].lru_head; @@ -323,8 +326,7 @@ nfsd_prune_bucket_locked(struct nfsd_net *nn, struct nfsd_drc_bucket *b, static unsigned long nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc) { - struct nfsd_net *nn = container_of(shrink, - struct nfsd_net, nfsd_reply_cache_shrinker); + struct nfsd_net *nn = shrink->private_data; return atomic_read(&nn->num_drc_entries); } @@ -343,8 +345,7 @@ nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc) static unsigned long nfsd_reply_cache_scan(struct shrinker *shrink, struct shrink_control *sc) { - struct nfsd_net *nn = container_of(shrink, - struct nfsd_net, nfsd_reply_cache_shrinker); + struct nfsd_net *nn = shrink->private_data; unsigned long freed = 0; LIST_HEAD(dispose); unsigned int i; diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 23fc24d16b31..6422e569b080 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -546,7 +546,8 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) * and explicitly excluded physical ranges. */ if (!page || PageOffline(page) || - is_page_hwpoison(page) || !pfn_is_ram(pfn)) { + is_page_hwpoison(page) || !pfn_is_ram(pfn) || + pfn_is_unaccepted_memory(pfn)) { if (iov_iter_zero(tsz, iter) != tsz) { ret = -EFAULT; goto out; diff --git a/fs/proc/root.c b/fs/proc/root.c index 9191248f2dac..b55dbc70287b 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -188,7 +188,7 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc) s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH; /* procfs dentries and inodes don't require IO to create */ - s->s_shrink.seeks = 0; + s->s_shrink->seeks = 0; pde_get(&proc_root); root_inode = proc_get_inode(s, &proc_root); diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 9e72bfe8bbad..15030b0cd1c8 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -791,12 +791,6 @@ dqcache_shrink_count(struct shrinker *shrink, struct shrink_control *sc) percpu_counter_read_positive(&dqstats.counter[DQST_FREE_DQUOTS])); } -static struct shrinker dqcache_shrinker = { - .count_objects = dqcache_shrink_count, - .scan_objects = dqcache_shrink_scan, - .seeks = DEFAULT_SEEKS, -}; - /* * Safely release dquot and put reference to dquot. */ @@ -2956,6 +2950,7 @@ static int __init dquot_init(void) { int i, ret; unsigned long nr_hash, order; + struct shrinker *dqcache_shrinker; printk(KERN_NOTICE "VFS: Disk quotas %s\n", __DQUOT_VERSION__); @@ -2990,8 +2985,14 @@ static int __init dquot_init(void) pr_info("VFS: Dquot-cache hash table entries: %ld (order %ld," " %ld bytes)\n", nr_hash, order, (PAGE_SIZE << order)); - if (register_shrinker(&dqcache_shrinker, "dquota-cache")) - panic("Cannot register dquot shrinker"); + dqcache_shrinker = shrinker_alloc(0, "dquota-cache"); + if (!dqcache_shrinker) + panic("Cannot allocate dquot shrinker"); + + dqcache_shrinker->count_objects = dqcache_shrink_count; + dqcache_shrinker->scan_objects = dqcache_shrink_scan; + + shrinker_register(dqcache_shrinker); return 0; } diff --git a/fs/super.c b/fs/super.c index 2d762ce67f6e..816a22a5cad1 100644 --- a/fs/super.c +++ b/fs/super.c @@ -178,7 +178,7 @@ static void super_wake(struct super_block *sb, unsigned int flag) * One thing we have to be careful of with a per-sb shrinker is that we don't * drop the last active reference to the superblock from within the shrinker. * If that happens we could trigger unregistering the shrinker from within the - * shrinker path and that leads to deadlock on the shrinker_rwsem. Hence we + * shrinker path and that leads to deadlock on the shrinker_mutex. Hence we * take a passive reference to the superblock to avoid this from occurring. */ static unsigned long super_cache_scan(struct shrinker *shrink, @@ -191,7 +191,7 @@ static unsigned long super_cache_scan(struct shrinker *shrink, long dentries; long inodes; - sb = container_of(shrink, struct super_block, s_shrink); + sb = shrink->private_data; /* * Deadlock avoidance. We may hold various FS locks, and we don't want @@ -244,7 +244,7 @@ static unsigned long super_cache_count(struct shrinker *shrink, struct super_block *sb; long total_objects = 0; - sb = container_of(shrink, struct super_block, s_shrink); + sb = shrink->private_data; /* * We don't call super_trylock_shared() here as it is a scalability @@ -306,7 +306,7 @@ static void destroy_unused_super(struct super_block *s) security_sb_free(s); put_user_ns(s->s_user_ns); kfree(s->s_subtype); - free_prealloced_shrinker(&s->s_shrink); + shrinker_free(s->s_shrink); /* no delays needed */ destroy_super_work(&s->destroy_work); } @@ -383,16 +383,19 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags, s->s_time_min = TIME64_MIN; s->s_time_max = TIME64_MAX; - s->s_shrink.seeks = DEFAULT_SEEKS; - s->s_shrink.scan_objects = super_cache_scan; - s->s_shrink.count_objects = super_cache_count; - s->s_shrink.batch = 1024; - s->s_shrink.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE; - if (prealloc_shrinker(&s->s_shrink, "sb-%s", type->name)) + s->s_shrink = shrinker_alloc(SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE, + "sb-%s", type->name); + if (!s->s_shrink) goto fail; - if (list_lru_init_memcg(&s->s_dentry_lru, &s->s_shrink)) + + s->s_shrink->scan_objects = super_cache_scan; + s->s_shrink->count_objects = super_cache_count; + s->s_shrink->batch = 1024; + s->s_shrink->private_data = s; + + if (list_lru_init_memcg(&s->s_dentry_lru, s->s_shrink)) goto fail; - if (list_lru_init_memcg(&s->s_inode_lru, &s->s_shrink)) + if (list_lru_init_memcg(&s->s_inode_lru, s->s_shrink)) goto fail; return s; @@ -477,7 +480,7 @@ void deactivate_locked_super(struct super_block *s) { struct file_system_type *fs = s->s_type; if (atomic_dec_and_test(&s->s_active)) { - unregister_shrinker(&s->s_shrink); + shrinker_free(s->s_shrink); fs->kill_sb(s); kill_super_notify(s); @@ -818,7 +821,7 @@ retry: hlist_add_head(&s->s_instances, &s->s_type->fs_supers); spin_unlock(&sb_lock); get_filesystem(s->s_type); - register_shrinker_prepared(&s->s_shrink); + shrinker_register(s->s_shrink); return s; share_extant_sb: @@ -901,7 +904,7 @@ retry: hlist_add_head(&s->s_instances, &type->fs_supers); spin_unlock(&sb_lock); get_filesystem(type); - register_shrinker_prepared(&s->s_shrink); + shrinker_register(s->s_shrink); return s; } EXPORT_SYMBOL(sget); @@ -1522,7 +1525,7 @@ int setup_bdev_super(struct super_block *sb, int sb_flags, mutex_unlock(&bdev->bd_fsfreeze_mutex); snprintf(sb->s_id, sizeof(sb->s_id), "%pg", bdev); - shrinker_debugfs_rename(&sb->s_shrink, "sb-%s:%s", sb->s_type->name, + shrinker_debugfs_rename(sb->s_shrink, "sb-%s:%s", sb->s_type->name, sb->s_id); sb_set_blocksize(sb, block_size(bdev)); return 0; diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index b08fb28d16b5..96f6a9118207 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -54,11 +54,7 @@ module_param_cb(default_version, &ubifs_default_version_ops, &ubifs_default_vers static struct kmem_cache *ubifs_inode_slab; /* UBIFS TNC shrinker description */ -static struct shrinker ubifs_shrinker_info = { - .scan_objects = ubifs_shrink_scan, - .count_objects = ubifs_shrink_count, - .seeks = DEFAULT_SEEKS, -}; +static struct shrinker *ubifs_shrinker_info; /** * validate_inode - validate inode. @@ -2373,7 +2369,7 @@ static void inode_slab_ctor(void *obj) static int __init ubifs_init(void) { - int err; + int err = -ENOMEM; BUILD_BUG_ON(sizeof(struct ubifs_ch) != 24); @@ -2439,10 +2435,15 @@ static int __init ubifs_init(void) if (!ubifs_inode_slab) return -ENOMEM; - err = register_shrinker(&ubifs_shrinker_info, "ubifs-slab"); - if (err) + ubifs_shrinker_info = shrinker_alloc(0, "ubifs-slab"); + if (!ubifs_shrinker_info) goto out_slab; + ubifs_shrinker_info->count_objects = ubifs_shrink_count; + ubifs_shrinker_info->scan_objects = ubifs_shrink_scan; + + shrinker_register(ubifs_shrinker_info); + err = ubifs_compressors_init(); if (err) goto out_shrinker; @@ -2467,7 +2468,7 @@ out_dbg: dbg_debugfs_exit(); ubifs_compressors_exit(); out_shrinker: - unregister_shrinker(&ubifs_shrinker_info); + shrinker_free(ubifs_shrinker_info); out_slab: kmem_cache_destroy(ubifs_inode_slab); return err; @@ -2483,7 +2484,7 @@ static void __exit ubifs_exit(void) dbg_debugfs_exit(); ubifs_sysfs_exit(); ubifs_compressors_exit(); - unregister_shrinker(&ubifs_shrinker_info); + shrinker_free(ubifs_shrinker_info); /* * Make sure all delayed rcu free inodes are flushed before we diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index c1ece4a08ff4..9e7ba04572db 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1913,8 +1913,7 @@ xfs_buftarg_shrink_scan( struct shrinker *shrink, struct shrink_control *sc) { - struct xfs_buftarg *btp = container_of(shrink, - struct xfs_buftarg, bt_shrinker); + struct xfs_buftarg *btp = shrink->private_data; LIST_HEAD(dispose); unsigned long freed; @@ -1936,8 +1935,7 @@ xfs_buftarg_shrink_count( struct shrinker *shrink, struct shrink_control *sc) { - struct xfs_buftarg *btp = container_of(shrink, - struct xfs_buftarg, bt_shrinker); + struct xfs_buftarg *btp = shrink->private_data; return list_lru_shrink_count(&btp->bt_lru, sc); } @@ -1947,7 +1945,7 @@ xfs_free_buftarg( { struct block_device *bdev = btp->bt_bdev; - unregister_shrinker(&btp->bt_shrinker); + shrinker_free(btp->bt_shrinker); ASSERT(percpu_counter_sum(&btp->bt_io_count) == 0); percpu_counter_destroy(&btp->bt_io_count); list_lru_destroy(&btp->bt_lru); @@ -2031,13 +2029,17 @@ xfs_alloc_buftarg( if (percpu_counter_init(&btp->bt_io_count, 0, GFP_KERNEL)) goto error_lru; - btp->bt_shrinker.count_objects = xfs_buftarg_shrink_count; - btp->bt_shrinker.scan_objects = xfs_buftarg_shrink_scan; - btp->bt_shrinker.seeks = DEFAULT_SEEKS; - btp->bt_shrinker.flags = SHRINKER_NUMA_AWARE; - if (register_shrinker(&btp->bt_shrinker, "xfs-buf:%s", - mp->m_super->s_id)) + btp->bt_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE, "xfs-buf:%s", + mp->m_super->s_id); + if (!btp->bt_shrinker) goto error_pcpu; + + btp->bt_shrinker->count_objects = xfs_buftarg_shrink_count; + btp->bt_shrinker->scan_objects = xfs_buftarg_shrink_scan; + btp->bt_shrinker->private_data = btp; + + shrinker_register(btp->bt_shrinker); + return btp; error_pcpu: diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index df8f47953bb4..702e7d9ea2ac 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -108,7 +108,7 @@ typedef struct xfs_buftarg { size_t bt_logical_sectormask; /* LRU control structures */ - struct shrinker bt_shrinker; + struct shrinker *bt_shrinker; struct list_lru bt_lru; struct percpu_counter bt_io_count; diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 3c210ac83713..dba514a2c84d 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -2165,8 +2165,7 @@ xfs_inodegc_shrinker_count( struct shrinker *shrink, struct shrink_control *sc) { - struct xfs_mount *mp = container_of(shrink, struct xfs_mount, - m_inodegc_shrinker); + struct xfs_mount *mp = shrink->private_data; struct xfs_inodegc *gc; int cpu; @@ -2187,8 +2186,7 @@ xfs_inodegc_shrinker_scan( struct shrinker *shrink, struct shrink_control *sc) { - struct xfs_mount *mp = container_of(shrink, struct xfs_mount, - m_inodegc_shrinker); + struct xfs_mount *mp = shrink->private_data; struct xfs_inodegc *gc; int cpu; bool no_items = true; @@ -2224,13 +2222,19 @@ int xfs_inodegc_register_shrinker( struct xfs_mount *mp) { - struct shrinker *shrink = &mp->m_inodegc_shrinker; + mp->m_inodegc_shrinker = shrinker_alloc(SHRINKER_NONSLAB, + "xfs-inodegc:%s", + mp->m_super->s_id); + if (!mp->m_inodegc_shrinker) + return -ENOMEM; + + mp->m_inodegc_shrinker->count_objects = xfs_inodegc_shrinker_count; + mp->m_inodegc_shrinker->scan_objects = xfs_inodegc_shrinker_scan; + mp->m_inodegc_shrinker->seeks = 0; + mp->m_inodegc_shrinker->batch = XFS_INODEGC_SHRINKER_BATCH; + mp->m_inodegc_shrinker->private_data = mp; - shrink->count_objects = xfs_inodegc_shrinker_count; - shrink->scan_objects = xfs_inodegc_shrinker_scan; - shrink->seeks = 0; - shrink->flags = SHRINKER_NONSLAB; - shrink->batch = XFS_INODEGC_SHRINKER_BATCH; + shrinker_register(mp->m_inodegc_shrinker); - return register_shrinker(shrink, "xfs-inodegc:%s", mp->m_super->s_id); + return 0; } diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 0a0fd19573d8..aed5be5508fe 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -1021,7 +1021,7 @@ xfs_mountfs( out_log_dealloc: xfs_log_mount_cancel(mp); out_inodegc_shrinker: - unregister_shrinker(&mp->m_inodegc_shrinker); + shrinker_free(mp->m_inodegc_shrinker); out_fail_wait: if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) xfs_buftarg_drain(mp->m_logdev_targp); @@ -1104,7 +1104,7 @@ xfs_unmountfs( #if defined(DEBUG) xfs_errortag_clearall(mp); #endif - unregister_shrinker(&mp->m_inodegc_shrinker); + shrinker_free(mp->m_inodegc_shrinker); xfs_free_perag(mp); xfs_errortag_del(mp); diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index d19cca099bc3..219681d29fbc 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -219,7 +219,7 @@ typedef struct xfs_mount { atomic_t m_agirotor; /* last ag dir inode alloced */ /* Memory shrinker to throttle and reprioritize inodegc */ - struct shrinker m_inodegc_shrinker; + struct shrinker *m_inodegc_shrinker; /* * Workqueue item so that we can coalesce multiple inode flush attempts * into a single flush. diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 086e78a6143a..94a7932ac570 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -504,8 +504,7 @@ xfs_qm_shrink_scan( struct shrinker *shrink, struct shrink_control *sc) { - struct xfs_quotainfo *qi = container_of(shrink, - struct xfs_quotainfo, qi_shrinker); + struct xfs_quotainfo *qi = shrink->private_data; struct xfs_qm_isolate isol; unsigned long freed; int error; @@ -539,8 +538,7 @@ xfs_qm_shrink_count( struct shrinker *shrink, struct shrink_control *sc) { - struct xfs_quotainfo *qi = container_of(shrink, - struct xfs_quotainfo, qi_shrinker); + struct xfs_quotainfo *qi = shrink->private_data; return list_lru_shrink_count(&qi->qi_lru, sc); } @@ -680,15 +678,18 @@ xfs_qm_init_quotainfo( if (XFS_IS_PQUOTA_ON(mp)) xfs_qm_set_defquota(mp, XFS_DQTYPE_PROJ, qinf); - qinf->qi_shrinker.count_objects = xfs_qm_shrink_count; - qinf->qi_shrinker.scan_objects = xfs_qm_shrink_scan; - qinf->qi_shrinker.seeks = DEFAULT_SEEKS; - qinf->qi_shrinker.flags = SHRINKER_NUMA_AWARE; - - error = register_shrinker(&qinf->qi_shrinker, "xfs-qm:%s", - mp->m_super->s_id); - if (error) + qinf->qi_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE, "xfs-qm:%s", + mp->m_super->s_id); + if (!qinf->qi_shrinker) { + error = -ENOMEM; goto out_free_inos; + } + + qinf->qi_shrinker->count_objects = xfs_qm_shrink_count; + qinf->qi_shrinker->scan_objects = xfs_qm_shrink_scan; + qinf->qi_shrinker->private_data = qinf; + + shrinker_register(qinf->qi_shrinker); return 0; @@ -718,7 +719,7 @@ xfs_qm_destroy_quotainfo( qi = mp->m_quotainfo; ASSERT(qi != NULL); - unregister_shrinker(&qi->qi_shrinker); + shrinker_free(qi->qi_shrinker); list_lru_destroy(&qi->qi_lru); xfs_qm_destroy_quotainos(qi); mutex_destroy(&qi->qi_tree_lock); diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h index 9683f0457d19..d5c9fc4ba591 100644 --- a/fs/xfs/xfs_qm.h +++ b/fs/xfs/xfs_qm.h @@ -63,7 +63,7 @@ struct xfs_quotainfo { struct xfs_def_quota qi_usr_default; struct xfs_def_quota qi_grp_default; struct xfs_def_quota qi_prj_default; - struct shrinker qi_shrinker; + struct shrinker *qi_shrinker; /* Minimum and maximum quota expiration timestamp values. */ time64_t qi_expiry_min; diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h index c75d4a753849..879e5f8aa5e9 100644 --- a/include/asm-generic/pgalloc.h +++ b/include/asm-generic/pgalloc.h @@ -169,6 +169,8 @@ static inline pud_t *__pud_alloc_one(struct mm_struct *mm, unsigned long addr) ptdesc = pagetable_alloc(gfp, 0); if (!ptdesc) return NULL; + + pagetable_pud_ctor(ptdesc); return ptdesc_address(ptdesc); } @@ -190,8 +192,11 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) static inline void __pud_free(struct mm_struct *mm, pud_t *pud) { + struct ptdesc *ptdesc = virt_to_ptdesc(pud); + BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); - pagetable_free(virt_to_ptdesc(pud)); + pagetable_pud_dtor(ptdesc); + pagetable_free(ptdesc); } #ifndef __HAVE_ARCH_PUD_FREE diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 44e9de51eedf..3dc4720e4773 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -198,7 +198,7 @@ void touch_buffer(struct buffer_head *bh); void folio_set_bh(struct buffer_head *bh, struct folio *folio, unsigned long offset); struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size, - bool retry); + gfp_t gfp); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry); void create_empty_buffers(struct page *, unsigned long, @@ -227,8 +227,8 @@ void __wait_on_buffer(struct buffer_head *); wait_queue_head_t *bh_waitq_head(struct buffer_head *bh); struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block, unsigned size); -struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block, - unsigned size, gfp_t gfp); +struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block, + unsigned size, gfp_t gfp); void __brelse(struct buffer_head *); void __bforget(struct buffer_head *); void __breadahead(struct block_device *, sector_t block, unsigned int size); @@ -338,17 +338,38 @@ sb_breadahead(struct super_block *sb, sector_t block) __breadahead(sb->s_bdev, block, sb->s_blocksize); } -static inline struct buffer_head * -sb_getblk(struct super_block *sb, sector_t block) +static inline struct buffer_head *getblk_unmovable(struct block_device *bdev, + sector_t block, unsigned size) { - return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE); + gfp_t gfp; + + gfp = mapping_gfp_constraint(bdev->bd_inode->i_mapping, ~__GFP_FS); + gfp |= __GFP_NOFAIL; + + return bdev_getblk(bdev, block, size, gfp); } +static inline struct buffer_head *__getblk(struct block_device *bdev, + sector_t block, unsigned size) +{ + gfp_t gfp; -static inline struct buffer_head * -sb_getblk_gfp(struct super_block *sb, sector_t block, gfp_t gfp) + gfp = mapping_gfp_constraint(bdev->bd_inode->i_mapping, ~__GFP_FS); + gfp |= __GFP_MOVABLE | __GFP_NOFAIL; + + return bdev_getblk(bdev, block, size, gfp); +} + +static inline struct buffer_head *sb_getblk(struct super_block *sb, + sector_t block) { - return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, gfp); + return __getblk(sb->s_bdev, block, sb->s_blocksize); +} + +static inline struct buffer_head *sb_getblk_gfp(struct super_block *sb, + sector_t block, gfp_t gfp) +{ + return bdev_getblk(sb->s_bdev, block, sb->s_blocksize, gfp); } static inline struct buffer_head * @@ -385,20 +406,6 @@ static inline void lock_buffer(struct buffer_head *bh) __lock_buffer(bh); } -static inline struct buffer_head *getblk_unmovable(struct block_device *bdev, - sector_t block, - unsigned size) -{ - return __getblk_gfp(bdev, block, size, 0); -} - -static inline struct buffer_head *__getblk(struct block_device *bdev, - sector_t block, - unsigned size) -{ - return __getblk_gfp(bdev, block, size, __GFP_MOVABLE); -} - static inline void bh_readahead(struct buffer_head *bh, blk_opf_t op_flags) { if (!buffer_uptodate(bh) && trylock_buffer(bh)) { diff --git a/include/linux/damon.h b/include/linux/damon.h index ae2664d1d5f1..27b995c22497 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -40,9 +40,24 @@ struct damon_addr_range { * @ar: The address range of the region. * @sampling_addr: Address of the sample for the next access check. * @nr_accesses: Access frequency of this region. + * @nr_accesses_bp: @nr_accesses in basis point (0.01%) that updated for + * each sampling interval. * @list: List head for siblings. * @age: Age of this region. * + * @nr_accesses is reset to zero for every &damon_attrs->aggr_interval and be + * increased for every &damon_attrs->sample_interval if an access to the region + * during the last sampling interval is found. The update of this field should + * not be done with direct access but with the helper function, + * damon_update_region_access_rate(). + * + * @nr_accesses_bp is another representation of @nr_accesses in basis point + * (1 in 10,000) that updated for every &damon_attrs->sample_interval in a + * manner similar to moving sum. By the algorithm, this value becomes + * @nr_accesses * 10000 for every &struct damon_attrs->aggr_interval. This can + * be used when the aggregation interval is too huge and therefore cannot wait + * for it before getting the access monitoring results. + * * @age is initially zero, increased for each aggregation interval, and reset * to zero again if the access frequency is significantly changed. If two * regions are merged into a new region, both @nr_accesses and @age of the new @@ -52,6 +67,7 @@ struct damon_region { struct damon_addr_range ar; unsigned long sampling_addr; unsigned int nr_accesses; + unsigned int nr_accesses_bp; struct list_head list; unsigned int age; @@ -298,24 +314,24 @@ struct damos_access_pattern { * 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. + * @apply_interval_us: The time between applying the @action. * @quota: Control the aggressiveness of this scheme. * @wmarks: Watermarks for automated (in)activation of this scheme. * @filters: Additional set of &struct damos_filter for &action. * @stat: Statistics of this scheme. * @list: List head for siblings. * - * For each aggregation interval, DAMON finds regions which fit in the + * For each @apply_interval_us, DAMON finds regions which fit in the * &pattern and applies &action to those. To avoid consuming too much * CPU time or IO resources for the &action, "a is used. * + * If @apply_interval_us is zero, &damon_attrs->aggr_interval is used instead. + * * To do the work only when needed, schemes can be activated for specific * system situations using &wmarks. If all schemes that registered to the * monitoring context are inactive, DAMON stops monitoring either, and just * repeatedly checks the watermarks. * - * If all schemes that registered to a &struct damon_ctx are inactive, DAMON - * stops monitoring and just repeatedly checks the watermarks. - * * Before applying the &action to a memory region, &struct damon_operations * implementation could check pages of the region and skip &action to respect * &filters @@ -327,6 +343,14 @@ struct damos_access_pattern { struct damos { struct damos_access_pattern pattern; enum damos_action action; + unsigned long apply_interval_us; +/* private: internal use only */ + /* + * number of sample intervals that should be passed before applying + * @action + */ + unsigned long next_apply_sis; +/* public: */ struct damos_quota quota; struct damos_watermarks wmarks; struct list_head filters; @@ -472,13 +496,14 @@ struct damon_callback { * 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 - * @ops_update_interval. All time intervals are in micro-seconds. - * Please refer to &struct damon_operations and &struct damon_callback for more - * detail. + * not during the last @sample_interval. If such access is found, DAMON + * aggregates the information by increasing &damon_region->nr_accesses for + * @aggr_interval time. For each @aggr_interval, the count is reset. 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 @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; @@ -522,8 +547,18 @@ struct damon_ctx { struct damon_attrs attrs; /* private: internal use only */ - struct timespec64 last_aggregation; - struct timespec64 last_ops_update; + /* number of sample intervals that passed since this context started */ + unsigned long passed_sample_intervals; + /* + * number of sample intervals that should be passed before next + * aggregation + */ + unsigned long next_aggregation_sis; + /* + * number of sample intervals that should be passed before next ops + * update + */ + unsigned long next_ops_update_sis; /* public: */ struct task_struct *kdamond; @@ -608,6 +643,8 @@ 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); +void damon_update_region_access_rate(struct damon_region *r, bool accessed, + struct damon_attrs *attrs); struct damos_filter *damos_new_filter(enum damos_filter_type type, bool matching); @@ -615,7 +652,9 @@ void damos_add_filter(struct damos *s, struct damos_filter *f); void damos_destroy_filter(struct damos_filter *f); struct damos *damon_new_scheme(struct damos_access_pattern *pattern, - enum damos_action action, struct damos_quota *quota, + enum damos_action action, + unsigned long apply_interval_us, + 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); diff --git a/include/linux/dax.h b/include/linux/dax.h index 22cd9902345d..b463502b16e1 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -159,8 +159,8 @@ int dax_writeback_mapping_range(struct address_space *mapping, struct page *dax_layout_busy_page(struct address_space *mapping); struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end); -dax_entry_t dax_lock_page(struct page *page); -void dax_unlock_page(struct page *page, dax_entry_t cookie); +dax_entry_t dax_lock_folio(struct folio *folio); +void dax_unlock_folio(struct folio *folio, dax_entry_t cookie); dax_entry_t dax_lock_mapping_entry(struct address_space *mapping, unsigned long index, struct page **page); void dax_unlock_mapping_entry(struct address_space *mapping, @@ -182,14 +182,14 @@ static inline int dax_writeback_mapping_range(struct address_space *mapping, return -EOPNOTSUPP; } -static inline dax_entry_t dax_lock_page(struct page *page) +static inline dax_entry_t dax_lock_folio(struct folio *folio) { - if (IS_DAX(page->mapping->host)) + if (IS_DAX(folio->mapping->host)) return ~0UL; return 0; } -static inline void dax_unlock_page(struct page *page, dax_entry_t cookie) +static inline void dax_unlock_folio(struct folio *folio, dax_entry_t cookie) { } diff --git a/include/linux/fs.h b/include/linux/fs.h index b528f063e8ff..fd539c9fef8e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1265,7 +1265,7 @@ struct super_block { const struct dentry_operations *s_d_op; /* default d_op for dentries */ - struct shrinker s_shrink; /* per-sb shrinker handle */ + struct shrinker *s_shrink; /* per-sb shrinker handle */ /* Number of inodes with nlink == 0 but still referenced */ atomic_long_t s_remove_count; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 47d25a5e1933..e5b9f7e62eeb 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -844,6 +844,12 @@ static inline unsigned int blocks_per_huge_page(struct hstate *h) return huge_page_size(h) / 512; } +static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h, + struct address_space *mapping, pgoff_t idx) +{ + return filemap_lock_folio(mapping, idx << huge_page_order(h)); +} + #include <asm/hugetlb.h> #ifndef is_hugepage_only_range @@ -1040,6 +1046,12 @@ static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio return NULL; } +static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h, + struct address_space *mapping, pgoff_t idx) +{ + return NULL; +} + static inline int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) { diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 52772c826c86..6dcbb4eb80fb 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -886,7 +886,7 @@ struct journal_s * Journal head shrinker, reclaim buffer's journal head which * has been written back. */ - struct shrinker j_shrinker; + struct shrinker *j_shrinker; /** * @j_checkpoint_jh_count: diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 1c1072e3ca06..ae3bde302f70 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -40,6 +40,8 @@ extern unsigned long long max_possible_pfn; * via a driver, and never indicated in the firmware-provided memory map as * system RAM. This corresponds to IORESOURCE_SYSRAM_DRIVER_MANAGED in the * kernel resource tree. + * @MEMBLOCK_RSRV_NOINIT: memory region for which struct pages are + * not initialized (only for reserved regions). */ enum memblock_flags { MEMBLOCK_NONE = 0x0, /* No special request */ @@ -47,6 +49,7 @@ enum memblock_flags { MEMBLOCK_MIRROR = 0x2, /* mirrored region */ MEMBLOCK_NOMAP = 0x4, /* don't add to kernel direct mapping */ MEMBLOCK_DRIVER_MANAGED = 0x8, /* always detected via a driver */ + MEMBLOCK_RSRV_NOINIT = 0x10, /* don't initialize struct pages */ }; /** @@ -125,6 +128,7 @@ int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size); int memblock_mark_mirror(phys_addr_t base, phys_addr_t size); int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); +int memblock_reserved_mark_noinit(phys_addr_t base, phys_addr_t size); void memblock_free_all(void); void memblock_free(void *ptr, size_t size); @@ -259,6 +263,11 @@ static inline bool memblock_is_nomap(struct memblock_region *m) return m->flags & MEMBLOCK_NOMAP; } +static inline bool memblock_is_reserved_noinit(struct memblock_region *m) +{ + return m->flags & MEMBLOCK_RSRV_NOINIT; +} + static inline bool memblock_is_driver_managed(struct memblock_region *m) { return m->flags & MEMBLOCK_DRIVER_MANAGED; diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e4e24da16d2c..031102ac9311 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -21,6 +21,7 @@ #include <linux/vmstat.h> #include <linux/writeback.h> #include <linux/page-flags.h> +#include <linux/shrinker.h> struct mem_cgroup; struct obj_cgroup; @@ -88,17 +89,6 @@ struct mem_cgroup_reclaim_iter { unsigned int generation; }; -/* - * Bitmap and deferred work of shrinker::id corresponding to memcg-aware - * shrinkers, which have elements charged to this memcg. - */ -struct shrinker_info { - struct rcu_head rcu; - atomic_long_t *nr_deferred; - unsigned long *map; - int map_nr_max; -}; - struct lruvec_stats_percpu { /* Local (CPU and cgroup) state */ long state[NR_VM_NODE_STAT_ITEMS]; diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h index 437441cdf78f..1e39d27bee41 100644 --- a/include/linux/memory-tiers.h +++ b/include/linux/memory-tiers.h @@ -6,6 +6,7 @@ #include <linux/nodemask.h> #include <linux/kref.h> #include <linux/mmzone.h> +#include <linux/notifier.h> /* * Each tier cover a abstrace distance chunk size of 128 */ @@ -22,7 +23,9 @@ struct memory_tier; struct memory_dev_type { /* list of memory types that are part of same tier as this type */ - struct list_head tier_sibiling; + struct list_head tier_sibling; + /* list of memory types that are managed by one driver */ + struct list_head list; /* abstract distance for this specific memory type */ int adistance; /* Nodes of same abstract distance */ @@ -30,12 +33,21 @@ struct memory_dev_type { struct kref kref; }; +struct node_hmem_attrs; + #ifdef CONFIG_NUMA extern bool numa_demotion_enabled; +extern struct memory_dev_type *default_dram_type; struct memory_dev_type *alloc_memory_type(int adistance); void put_memory_type(struct memory_dev_type *memtype); void init_node_memory_type(int node, struct memory_dev_type *default_type); void clear_node_memory_type(int node, struct memory_dev_type *memtype); +int register_mt_adistance_algorithm(struct notifier_block *nb); +int unregister_mt_adistance_algorithm(struct notifier_block *nb); +int mt_calc_adistance(int node, int *adist); +int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf, + const char *source); +int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist); #ifdef CONFIG_MIGRATION int next_demotion_node(int node); void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets); @@ -60,6 +72,7 @@ static inline bool node_is_toptier(int node) #else #define numa_demotion_enabled false +#define default_dram_type NULL /* * CONFIG_NUMA implementation returns non NULL error. */ @@ -97,5 +110,31 @@ static inline bool node_is_toptier(int node) { return true; } + +static inline int register_mt_adistance_algorithm(struct notifier_block *nb) +{ + return 0; +} + +static inline int unregister_mt_adistance_algorithm(struct notifier_block *nb) +{ + return 0; +} + +static inline int mt_calc_adistance(int node, int *adist) +{ + return NOTIFY_DONE; +} + +static inline int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf, + const char *source) +{ + return -EIO; +} + +static inline int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist) +{ + return -EIO; +} #endif /* CONFIG_NUMA */ #endif /* _LINUX_MEMORY_TIERS_H */ diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index d232de7cdc56..6c2754d7bfed 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -174,7 +174,7 @@ extern void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol); /* Check if a vma is migratable */ extern bool vma_migratable(struct vm_area_struct *vma); -extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long); +int mpol_misplaced(struct folio *, struct vm_area_struct *, unsigned long); extern void mpol_put_task_policy(struct task_struct *); static inline bool mpol_is_preferred_many(struct mempolicy *pol) @@ -278,7 +278,8 @@ static inline int mpol_parse_str(char *str, struct mempolicy **mpol) } #endif -static inline int mpol_misplaced(struct page *page, struct vm_area_struct *vma, +static inline int mpol_misplaced(struct folio *folio, + struct vm_area_struct *vma, unsigned long address) { return -1; /* no node preference */ diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 711dd9412561..2ce13e8a309b 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -142,10 +142,10 @@ const struct movable_operations *page_movable_ops(struct page *page) } #ifdef CONFIG_NUMA_BALANCING -int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, +int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma, int node); #else -static inline int migrate_misplaced_page(struct page *page, +static inline int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma, int node) { return -EAGAIN; /* can't migrate now */ diff --git a/include/linux/mm.h b/include/linux/mm.h index bf5d0b1b16f4..52c40b3d0813 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2327,6 +2327,8 @@ struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); +struct folio *vm_normal_folio_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t pmd); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); @@ -2480,7 +2482,7 @@ int get_cmdline(struct task_struct *task, char *buffer, int buflen); extern unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len, - bool need_rmap_locks); + bool need_rmap_locks, bool for_stack); /* * Flags used by change_protection(). For now we make it a bitmap so @@ -2628,14 +2630,6 @@ static inline void setmax_mm_hiwater_rss(unsigned long *maxrss, *maxrss = hiwater_rss; } -#if defined(SPLIT_RSS_COUNTING) -void sync_mm_rss(struct mm_struct *mm); -#else -static inline void sync_mm_rss(struct mm_struct *mm) -{ -} -#endif - #ifndef CONFIG_ARCH_HAS_PTE_SPECIAL static inline int pte_special(pte_t pte) { @@ -3057,6 +3051,22 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) return ptl; } +static inline void pagetable_pud_ctor(struct ptdesc *ptdesc) +{ + struct folio *folio = ptdesc_folio(ptdesc); + + __folio_set_pgtable(folio); + lruvec_stat_add_folio(folio, NR_PAGETABLE); +} + +static inline void pagetable_pud_dtor(struct ptdesc *ptdesc) +{ + struct folio *folio = ptdesc_folio(ptdesc); + + __folio_clear_pgtable(folio); + lruvec_stat_sub_folio(folio, NR_PAGETABLE); +} + extern void __init pagecache_init(void); extern void free_initmem(void); @@ -4062,4 +4072,11 @@ static inline void accept_memory(phys_addr_t start, phys_addr_t end) #endif +static inline bool pfn_is_unaccepted_memory(unsigned long pfn) +{ + phys_addr_t paddr = pfn << PAGE_SHIFT; + + return range_contains_unaccepted_memory(paddr, paddr + PAGE_SIZE); +} + #endif /* _LINUX_MM_H */ diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 6e3c857606f1..f349e08a9dfe 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -459,7 +459,14 @@ mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) lock_map_release(&__mmu_notifier_invalidate_range_start_map); } -static inline int +/* + * This version of mmu_notifier_invalidate_range_start() avoids blocking, but it + * can return an error if a notifier can't proceed without blocking, in which + * case you're not allowed to modify PTEs in the specified range. + * + * This is mainly intended for OOM handling. + */ +static inline int __must_check mmu_notifier_invalidate_range_start_nonblock(struct mmu_notifier_range *range) { int ret = 0; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 4106fbc5b4b3..486587fcd27f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -639,8 +639,6 @@ struct lruvec { #endif }; -/* Isolate unmapped pages */ -#define ISOLATE_UNMAPPED ((__force isolate_mode_t)0x2) /* Isolate for asynchronous migration */ #define ISOLATE_ASYNC_MIGRATE ((__force isolate_mode_t)0x4) /* Isolate unevictable pages */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 351c3b7f93a1..759b29d9a69a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -789,9 +789,6 @@ static inline pgoff_t folio_next_index(struct folio *folio) */ static inline struct page *folio_file_page(struct folio *folio, pgoff_t index) { - /* HugeTLBfs indexes the page cache in units of hpage_size */ - if (folio_test_hugetlb(folio)) - return &folio->page; return folio_page(folio, index & (folio_nr_pages(folio) - 1)); } @@ -807,9 +804,6 @@ static inline struct page *folio_file_page(struct folio *folio, pgoff_t index) */ static inline bool folio_contains(struct folio *folio, pgoff_t index) { - /* HugeTLBfs indexes the page cache in units of hpage_size */ - if (folio_test_hugetlb(folio)) - return folio->index == index; return index - folio_index(folio) < folio_nr_pages(folio); } @@ -867,10 +861,9 @@ static inline struct folio *read_mapping_folio(struct address_space *mapping, } /* - * Get index of the page within radix-tree (but not for hugetlb pages). - * (TODO: remove once hugetlb pages will have ->index in PAGE_SIZE) + * Get the offset in PAGE_SIZE (even for hugetlb pages). */ -static inline pgoff_t page_to_index(struct page *page) +static inline pgoff_t page_to_pgoff(struct page *page) { struct page *head; @@ -885,19 +878,6 @@ static inline pgoff_t page_to_index(struct page *page) return head->index + page - head; } -extern pgoff_t hugetlb_basepage_index(struct page *page); - -/* - * Get the offset in PAGE_SIZE (even for hugetlb pages). - * (TODO: hugetlb pages should have ->index in PAGE_SIZE) - */ -static inline pgoff_t page_to_pgoff(struct page *page) -{ - if (unlikely(PageHuge(page))) - return hugetlb_basepage_index(page); - return page_to_index(page); -} - /* * Return byte-offset into filesystem object for page. */ @@ -934,24 +914,16 @@ static inline loff_t folio_file_pos(struct folio *folio) /* * Get the offset in PAGE_SIZE (even for hugetlb folios). - * (TODO: hugetlb folios should have ->index in PAGE_SIZE) */ static inline pgoff_t folio_pgoff(struct folio *folio) { - if (unlikely(folio_test_hugetlb(folio))) - return hugetlb_basepage_index(&folio->page); return folio->index; } -extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma, - unsigned long address); - static inline pgoff_t linear_page_index(struct vm_area_struct *vma, unsigned long address) { pgoff_t pgoff; - if (unlikely(is_vm_hugetlb_page(vma))) - return linear_hugepage_index(vma, address); pgoff = (address - vma->vm_start) >> PAGE_SHIFT; pgoff += vma->vm_pgoff; return pgoff; diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 51cc21ebb568..d22f4d21a11c 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -203,7 +203,7 @@ void folio_add_file_rmap_range(struct folio *, struct page *, unsigned int nr, void page_remove_rmap(struct page *, struct vm_area_struct *, bool compound); -void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, +void hugepage_add_anon_rmap(struct folio *, struct vm_area_struct *, unsigned long address, rmap_t flags); void hugepage_add_new_anon_rmap(struct folio *, struct vm_area_struct *, unsigned long address); diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 0ee96ea7a0e9..02f5090ffea2 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -71,6 +71,7 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ #define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ #define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ +#define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_OOM_REAP_QUEUED 25 /* mm was queued for oom_reaper */ #define MMF_MULTIPROCESS 26 /* mm is shared between processes */ /* @@ -85,10 +86,22 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_HAS_MDWE 28 #define MMF_HAS_MDWE_MASK (1 << MMF_HAS_MDWE) -#define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) + +#define MMF_HAS_MDWE_NO_INHERIT 29 + +#define MMF_VM_MERGE_ANY 30 +#define MMF_VM_MERGE_ANY_MASK (1 << MMF_VM_MERGE_ANY) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ - MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK) + MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK |\ + MMF_VM_MERGE_ANY_MASK) + +static inline unsigned long mmf_init_flags(unsigned long flags) +{ + if (flags & (1UL << MMF_HAS_MDWE_NO_INHERIT)) + flags &= ~((1UL << MMF_HAS_MDWE) | + (1UL << MMF_HAS_MDWE_NO_INHERIT)); + return flags & MMF_INIT_MASK; +} -#define MMF_VM_MERGE_ANY 29 #endif /* _LINUX_SCHED_COREDUMP_H */ diff --git a/include/linux/sched/numa_balancing.h b/include/linux/sched/numa_balancing.h index 3988762efe15..06a9d35650f0 100644 --- a/include/linux/sched/numa_balancing.h +++ b/include/linux/sched/numa_balancing.h @@ -20,8 +20,8 @@ extern void task_numa_fault(int last_node, int node, int pages, int flags); extern pid_t task_numa_group_id(struct task_struct *p); extern void set_numabalancing_state(bool enabled); extern void task_numa_free(struct task_struct *p, bool final); -extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page, - int src_nid, int dst_cpu); +bool should_numa_migrate_memory(struct task_struct *p, struct folio *folio, + int src_nid, int dst_cpu); #else static inline void task_numa_fault(int last_node, int node, int pages, int flags) @@ -38,7 +38,7 @@ static inline void task_numa_free(struct task_struct *p, bool final) { } static inline bool should_numa_migrate_memory(struct task_struct *p, - struct page *page, int src_nid, int dst_cpu) + struct folio *folio, int src_nid, int dst_cpu) { return true; } diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 224293b2dd06..e4f93120e0ab 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -4,6 +4,25 @@ #include <linux/atomic.h> #include <linux/types.h> +#include <linux/refcount.h> +#include <linux/completion.h> + +#define SHRINKER_UNIT_BITS BITS_PER_LONG + +/* + * Bitmap and deferred work of shrinker::id corresponding to memcg-aware + * shrinkers, which have elements charged to the memcg. + */ +struct shrinker_info_unit { + atomic_long_t nr_deferred[SHRINKER_UNIT_BITS]; + DECLARE_BITMAP(map, SHRINKER_UNIT_BITS); +}; + +struct shrinker_info { + struct rcu_head rcu; + int map_nr_max; + struct shrinker_info_unit *unit[]; +}; /* * This struct is used to pass information from page reclaim to the shrinkers. @@ -70,6 +89,19 @@ struct shrinker { int seeks; /* seeks to recreate an obj */ unsigned flags; + /* + * The reference count of this shrinker. Registered shrinker have an + * initial refcount of 1, then the lookup operations are now allowed + * to use it via shrinker_try_get(). Later in the unregistration step, + * the initial refcount will be discarded, and will free the shrinker + * asynchronously via RCU after its refcount reaches 0. + */ + refcount_t refcount; + struct completion done; /* use to wait for refcount to reach 0 */ + struct rcu_head rcu; + + void *private_data; + /* These are for internal use */ struct list_head list; #ifdef CONFIG_MEMCG @@ -86,48 +118,38 @@ struct shrinker { }; #define DEFAULT_SEEKS 2 /* A good number if you don't know better. */ -/* Flags */ -#define SHRINKER_REGISTERED (1 << 0) -#define SHRINKER_NUMA_AWARE (1 << 1) -#define SHRINKER_MEMCG_AWARE (1 << 2) +/* Internal flags */ +#define SHRINKER_REGISTERED BIT(0) +#define SHRINKER_ALLOCATED BIT(1) + +/* Flags for users to use */ +#define SHRINKER_NUMA_AWARE BIT(2) +#define SHRINKER_MEMCG_AWARE BIT(3) /* * It just makes sense when the shrinker is also MEMCG_AWARE for now, * non-MEMCG_AWARE shrinker should not have this flag set. */ -#define SHRINKER_NONSLAB (1 << 3) +#define SHRINKER_NONSLAB BIT(4) -extern int __printf(2, 3) prealloc_shrinker(struct shrinker *shrinker, - const char *fmt, ...); -extern void register_shrinker_prepared(struct shrinker *shrinker); -extern int __printf(2, 3) register_shrinker(struct shrinker *shrinker, - const char *fmt, ...); -extern void unregister_shrinker(struct shrinker *shrinker); -extern void free_prealloced_shrinker(struct shrinker *shrinker); -extern void synchronize_shrinkers(void); +struct shrinker *shrinker_alloc(unsigned int flags, const char *fmt, ...); +void shrinker_register(struct shrinker *shrinker); +void shrinker_free(struct shrinker *shrinker); -#ifdef CONFIG_SHRINKER_DEBUG -extern int shrinker_debugfs_add(struct shrinker *shrinker); -extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, - int *debugfs_id); -extern void shrinker_debugfs_remove(struct dentry *debugfs_entry, - int debugfs_id); -extern int __printf(2, 3) shrinker_debugfs_rename(struct shrinker *shrinker, - const char *fmt, ...); -#else /* CONFIG_SHRINKER_DEBUG */ -static inline int shrinker_debugfs_add(struct shrinker *shrinker) -{ - return 0; -} -static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, - int *debugfs_id) +static inline bool shrinker_try_get(struct shrinker *shrinker) { - *debugfs_id = -1; - return NULL; + return refcount_inc_not_zero(&shrinker->refcount); } -static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, - int debugfs_id) + +static inline void shrinker_put(struct shrinker *shrinker) { + if (refcount_dec_and_test(&shrinker->refcount)) + complete(&shrinker->done); } + +#ifdef CONFIG_SHRINKER_DEBUG +extern int __printf(2, 3) shrinker_debugfs_rename(struct shrinker *shrinker, + const char *fmt, ...); +#else /* CONFIG_SHRINKER_DEBUG */ static inline __printf(2, 3) int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) { diff --git a/include/trace/events/damon.h b/include/trace/events/damon.h index c79f1d4c39af..23200aabccac 100644 --- a/include/trace/events/damon.h +++ b/include/trace/events/damon.h @@ -9,12 +9,51 @@ #include <linux/types.h> #include <linux/tracepoint.h> +TRACE_EVENT_CONDITION(damos_before_apply, + + TP_PROTO(unsigned int context_idx, unsigned int scheme_idx, + unsigned int target_idx, struct damon_region *r, + unsigned int nr_regions, bool do_trace), + + TP_ARGS(context_idx, target_idx, scheme_idx, r, nr_regions, do_trace), + + TP_CONDITION(do_trace), + + TP_STRUCT__entry( + __field(unsigned int, context_idx) + __field(unsigned int, scheme_idx) + __field(unsigned long, target_idx) + __field(unsigned long, start) + __field(unsigned long, end) + __field(unsigned int, nr_accesses) + __field(unsigned int, age) + __field(unsigned int, nr_regions) + ), + + TP_fast_assign( + __entry->context_idx = context_idx; + __entry->scheme_idx = scheme_idx; + __entry->target_idx = target_idx; + __entry->start = r->ar.start; + __entry->end = r->ar.end; + __entry->nr_accesses = r->nr_accesses_bp / 10000; + __entry->age = r->age; + __entry->nr_regions = nr_regions; + ), + + TP_printk("ctx_idx=%u scheme_idx=%u target_idx=%lu nr_regions=%u %lu-%lu: %u %u", + __entry->context_idx, __entry->scheme_idx, + __entry->target_idx, __entry->nr_regions, + __entry->start, __entry->end, + __entry->nr_accesses, __entry->age) +); + TRACE_EVENT(damon_aggregated, - TP_PROTO(struct damon_target *t, unsigned int target_id, - struct damon_region *r, unsigned int nr_regions), + TP_PROTO(unsigned int target_id, struct damon_region *r, + unsigned int nr_regions), - TP_ARGS(t, target_id, r, nr_regions), + TP_ARGS(target_id, r, nr_regions), TP_STRUCT__entry( __field(unsigned long, target_id) diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index d2123dd960d5..1a488c30afa5 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -285,10 +285,9 @@ TRACE_EVENT(mm_vmscan_lru_isolate, unsigned long nr_scanned, unsigned long nr_skipped, unsigned long nr_taken, - isolate_mode_t isolate_mode, int lru), - TP_ARGS(highest_zoneidx, order, nr_requested, nr_scanned, nr_skipped, nr_taken, isolate_mode, lru), + TP_ARGS(highest_zoneidx, order, nr_requested, nr_scanned, nr_skipped, nr_taken, lru), TP_STRUCT__entry( __field(int, highest_zoneidx) @@ -297,7 +296,6 @@ TRACE_EVENT(mm_vmscan_lru_isolate, __field(unsigned long, nr_scanned) __field(unsigned long, nr_skipped) __field(unsigned long, nr_taken) - __field(unsigned int, isolate_mode) __field(int, lru) ), @@ -308,7 +306,6 @@ TRACE_EVENT(mm_vmscan_lru_isolate, __entry->nr_scanned = nr_scanned; __entry->nr_skipped = nr_skipped; __entry->nr_taken = nr_taken; - __entry->isolate_mode = (__force unsigned int)isolate_mode; __entry->lru = lru; ), @@ -316,8 +313,7 @@ TRACE_EVENT(mm_vmscan_lru_isolate, * classzone is previous name of the highest_zoneidx. * Reason not to change it is the ABI requirement of the tracepoint. */ - TP_printk("isolate_mode=%d classzone=%d order=%d nr_requested=%lu nr_scanned=%lu nr_skipped=%lu nr_taken=%lu lru=%s", - __entry->isolate_mode, + TP_printk("classzone=%d order=%d nr_requested=%lu nr_scanned=%lu nr_skipped=%lu nr_taken=%lu lru=%s", __entry->highest_zoneidx, __entry->order, __entry->nr_requested, diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 3c36aeade991..370ed14b1ae0 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -283,7 +283,8 @@ struct prctl_mm_map { /* Memory deny write / execute */ #define PR_SET_MDWE 65 -# define PR_MDWE_REFUSE_EXEC_GAIN 1 +# define PR_MDWE_REFUSE_EXEC_GAIN (1UL << 0) +# define PR_MDWE_NO_INHERIT (1UL << 1) #define PR_GET_MDWE 66 diff --git a/kernel/exit.c b/kernel/exit.c index edb50b4c9972..3cdbe797008f 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -539,7 +539,6 @@ static void exit_mm(void) exit_mm_release(current, mm); if (!mm) return; - sync_mm_rss(mm); mmap_read_lock(mm); mmgrab_lazy_tlb(mm); BUG_ON(mm != current->active_mm); @@ -829,9 +828,6 @@ void __noreturn do_exit(long code) io_uring_files_cancel(); exit_signals(tsk); /* sets PF_EXITING */ - /* sync mm's RSS info before statistics gathering */ - if (tsk->mm) - sync_mm_rss(tsk->mm); acct_update_integrals(tsk); group_dead = atomic_dec_and_test(&tsk->signal->live); if (group_dead) { diff --git a/kernel/fork.c b/kernel/fork.c index 3b6d20dfb9a8..e45a4457ba83 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1288,7 +1288,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, hugetlb_count_init(mm); if (current->mm) { - mm->flags = current->mm->flags & MMF_INIT_MASK; + mm->flags = mmf_init_flags(current->mm->flags); mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK; } else { mm->flags = default_dump_filter; @@ -2406,10 +2406,6 @@ __latent_entropy struct task_struct *copy_process( p->io_uring = NULL; #endif -#if defined(SPLIT_RSS_COUNTING) - memset(&p->rss_stat, 0, sizeof(p->rss_stat)); -#endif - p->default_timer_slack_ns = current->timer_slack_ns; #ifdef CONFIG_PSI diff --git a/kernel/kthread.c b/kernel/kthread.c index 1eea53050bab..c46128ec0c0a 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -1469,7 +1469,6 @@ void kthread_unuse_mm(struct mm_struct *mm) * clearing tsk->mm. */ smp_mb__after_spinlock(); - sync_mm_rss(mm); local_irq_disable(); tsk->mm = NULL; membarrier_update_current_mm(NULL); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index cb1caefa8bd0..06e2ed495c02 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3449,13 +3449,6 @@ kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) return freed == 0 ? SHRINK_STOP : freed; } -static struct shrinker kfree_rcu_shrinker = { - .count_objects = kfree_rcu_shrink_count, - .scan_objects = kfree_rcu_shrink_scan, - .batch = 0, - .seeks = DEFAULT_SEEKS, -}; - void __init kfree_rcu_scheduler_running(void) { int cpu; @@ -4931,6 +4924,7 @@ static void __init kfree_rcu_batch_init(void) { int cpu; int i, j; + struct shrinker *kfree_rcu_shrinker; /* Clamp it to [0:100] seconds interval. */ if (rcu_delay_page_cache_fill_msec < 0 || @@ -4962,8 +4956,17 @@ static void __init kfree_rcu_batch_init(void) INIT_DELAYED_WORK(&krcp->page_cache_work, fill_page_cache_func); krcp->initialized = true; } - if (register_shrinker(&kfree_rcu_shrinker, "rcu-kfree")) - pr_err("Failed to register kfree_rcu() shrinker!\n"); + + kfree_rcu_shrinker = shrinker_alloc(0, "rcu-kfree"); + if (!kfree_rcu_shrinker) { + pr_err("Failed to allocate kfree_rcu() shrinker!\n"); + return; + } + + kfree_rcu_shrinker->count_objects = kfree_rcu_shrink_count; + kfree_rcu_shrinker->scan_objects = kfree_rcu_shrink_scan; + + shrinker_register(kfree_rcu_shrinker); } void __init rcu_init(void) diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h index 5598212d1f27..4efbf7333d4e 100644 --- a/kernel/rcu/tree_nocb.h +++ b/kernel/rcu/tree_nocb.h @@ -1396,13 +1396,6 @@ lazy_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) return count ? count : SHRINK_STOP; } - -static struct shrinker lazy_rcu_shrinker = { - .count_objects = lazy_rcu_shrink_count, - .scan_objects = lazy_rcu_shrink_scan, - .batch = 0, - .seeks = DEFAULT_SEEKS, -}; #endif // #ifdef CONFIG_RCU_LAZY void __init rcu_init_nohz(void) @@ -1410,6 +1403,7 @@ void __init rcu_init_nohz(void) int cpu; struct rcu_data *rdp; const struct cpumask *cpumask = NULL; + struct shrinker * __maybe_unused lazy_rcu_shrinker; #if defined(CONFIG_NO_HZ_FULL) if (tick_nohz_full_running && !cpumask_empty(tick_nohz_full_mask)) @@ -1436,8 +1430,15 @@ void __init rcu_init_nohz(void) return; #ifdef CONFIG_RCU_LAZY - if (register_shrinker(&lazy_rcu_shrinker, "rcu-lazy")) - pr_err("Failed to register lazy_rcu shrinker!\n"); + lazy_rcu_shrinker = shrinker_alloc(0, "rcu-lazy"); + if (!lazy_rcu_shrinker) { + pr_err("Failed to allocate lazy_rcu shrinker!\n"); + } else { + lazy_rcu_shrinker->count_objects = lazy_rcu_shrink_count; + lazy_rcu_shrinker->scan_objects = lazy_rcu_shrink_scan; + + shrinker_register(lazy_rcu_shrinker); + } #endif // #ifdef CONFIG_RCU_LAZY if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) { diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index cb225921bbca..42aefe7e6fdc 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1722,12 +1722,12 @@ static bool pgdat_free_space_enough(struct pglist_data *pgdat) * The smaller the hint page fault latency, the higher the possibility * for the page to be hot. */ -static int numa_hint_fault_latency(struct page *page) +static int numa_hint_fault_latency(struct folio *folio) { int last_time, time; time = jiffies_to_msecs(jiffies); - last_time = xchg_page_access_time(page, time); + last_time = xchg_page_access_time(&folio->page, time); return (time - last_time) & PAGE_ACCESS_TIME_MASK; } @@ -1784,7 +1784,7 @@ static void numa_promotion_adjust_threshold(struct pglist_data *pgdat, } } -bool should_numa_migrate_memory(struct task_struct *p, struct page * page, +bool should_numa_migrate_memory(struct task_struct *p, struct folio *folio, int src_nid, int dst_cpu) { struct numa_group *ng = deref_curr_numa_group(p); @@ -1814,16 +1814,16 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page, numa_promotion_adjust_threshold(pgdat, rate_limit, def_th); th = pgdat->nbp_threshold ? : def_th; - latency = numa_hint_fault_latency(page); + latency = numa_hint_fault_latency(folio); if (latency >= th) return false; return !numa_promotion_rate_limit(pgdat, rate_limit, - thp_nr_pages(page)); + folio_nr_pages(folio)); } this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid); - last_cpupid = page_cpupid_xchg_last(page, this_cpupid); + last_cpupid = page_cpupid_xchg_last(&folio->page, this_cpupid); if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) && !node_is_toptier(src_nid) && !cpupid_valid(last_cpupid)) diff --git a/kernel/sys.c b/kernel/sys.c index 2410e3999ebe..4a8073c1b255 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2368,19 +2368,41 @@ static int prctl_set_vma(unsigned long opt, unsigned long start, } #endif /* CONFIG_ANON_VMA_NAME */ +static inline unsigned long get_current_mdwe(void) +{ + unsigned long ret = 0; + + if (test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) + ret |= PR_MDWE_REFUSE_EXEC_GAIN; + if (test_bit(MMF_HAS_MDWE_NO_INHERIT, ¤t->mm->flags)) + ret |= PR_MDWE_NO_INHERIT; + + return ret; +} + static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3, unsigned long arg4, unsigned long arg5) { + unsigned long current_bits; + if (arg3 || arg4 || arg5) return -EINVAL; - if (bits & ~(PR_MDWE_REFUSE_EXEC_GAIN)) + if (bits & ~(PR_MDWE_REFUSE_EXEC_GAIN | PR_MDWE_NO_INHERIT)) + return -EINVAL; + + /* NO_INHERIT only makes sense with REFUSE_EXEC_GAIN */ + if (bits & PR_MDWE_NO_INHERIT && !(bits & PR_MDWE_REFUSE_EXEC_GAIN)) return -EINVAL; + current_bits = get_current_mdwe(); + if (current_bits && current_bits != bits) + return -EPERM; /* Cannot unset the flags */ + + if (bits & PR_MDWE_NO_INHERIT) + set_bit(MMF_HAS_MDWE_NO_INHERIT, ¤t->mm->flags); if (bits & PR_MDWE_REFUSE_EXEC_GAIN) set_bit(MMF_HAS_MDWE, ¤t->mm->flags); - else if (test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) - return -EPERM; /* Cannot unset the flag */ return 0; } @@ -2390,9 +2412,7 @@ static inline int prctl_get_mdwe(unsigned long arg2, unsigned long arg3, { if (arg2 || arg3 || arg4 || arg5) return -EINVAL; - - return test_bit(MMF_HAS_MDWE, ¤t->mm->flags) ? - PR_MDWE_REFUSE_EXEC_GAIN : 0; + return get_current_mdwe(); } static int prctl_get_auxv(void __user *addr, unsigned long len) diff --git a/mm/Kconfig b/mm/Kconfig index 264a2df5ecf5..45f2971ef642 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -130,6 +130,7 @@ config ZSWAP_COMPRESSOR_DEFAULT choice prompt "Default allocator" depends on ZSWAP + default ZSWAP_ZPOOL_DEFAULT_ZSMALLOC if MMU default ZSWAP_ZPOOL_DEFAULT_ZBUD help Selects the default allocator for the compressed cache for diff --git a/mm/Makefile b/mm/Makefile index ec65984e2ade..33873c8aedb3 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -48,8 +48,8 @@ endif obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ maccess.o page-writeback.o folio-compat.o \ - readahead.o swap.o truncate.o vmscan.o shmem.o \ - util.o mmzone.o vmstat.o backing-dev.o \ + readahead.o swap.o truncate.o vmscan.o shrinker.o \ + shmem.o util.o mmzone.o vmstat.o backing-dev.o \ mm_init.o percpu.o slab_common.o \ compaction.o show_mem.o shmem_quota.o\ interval_tree.o list_lru.o workingset.o \ @@ -505,7 +505,7 @@ struct page *cma_alloc(struct cma *cma, unsigned long count, */ if (page) { for (i = 0; i < count; i++) - page_kasan_tag_reset(page + i); + page_kasan_tag_reset(nth_page(page, i)); } if (ret && !no_warn) { diff --git a/mm/compaction.c b/mm/compaction.c index 38c8d216c6a3..01ba298739dd 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -382,6 +382,7 @@ static void __reset_isolation_suitable(struct zone *zone) bool source_set = false; bool free_set = false; + /* Only flush if a full compaction finished recently */ if (!zone->compact_blockskip_flush) return; @@ -434,9 +435,7 @@ void reset_isolation_suitable(pg_data_t *pgdat) if (!populated_zone(zone)) continue; - /* Only flush if a full compaction finished recently */ - if (zone->compact_blockskip_flush) - __reset_isolation_suitable(zone); + __reset_isolation_suitable(zone); } } @@ -626,11 +625,12 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, if (PageCompound(page)) { const unsigned int order = compound_order(page); - if (likely(order <= MAX_ORDER)) { + if (blockpfn + (1UL << order) <= end_pfn) { blockpfn += (1UL << order) - 1; page += (1UL << order) - 1; nr_scanned += (1UL << order) - 1; } + goto isolate_fail; } @@ -678,8 +678,7 @@ isolate_fail: spin_unlock_irqrestore(&cc->zone->lock, flags); /* - * There is a tiny chance that we have read bogus compound_order(), - * so be careful to not go outside of the pageblock. + * Be careful to not go outside of the pageblock. */ if (unlikely(blockpfn > end_pfn)) blockpfn = end_pfn; @@ -1395,8 +1394,8 @@ move_freelist_head(struct list_head *freelist, struct page *freepage) { LIST_HEAD(sublist); - if (!list_is_last(freelist, &freepage->lru)) { - list_cut_before(&sublist, freelist, &freepage->lru); + if (!list_is_first(&freepage->buddy_list, freelist)) { + list_cut_before(&sublist, freelist, &freepage->buddy_list); list_splice_tail(&sublist, freelist); } } @@ -1412,8 +1411,8 @@ move_freelist_tail(struct list_head *freelist, struct page *freepage) { LIST_HEAD(sublist); - if (!list_is_first(freelist, &freepage->lru)) { - list_cut_position(&sublist, freelist, &freepage->lru); + if (!list_is_last(&freepage->buddy_list, freelist)) { + list_cut_position(&sublist, freelist, &freepage->buddy_list); list_splice_tail(&sublist, freelist); } } @@ -2066,8 +2065,10 @@ static isolate_migrate_t isolate_migratepages(struct compact_control *cc) } /* - * order == -1 is expected when compacting via - * /proc/sys/vm/compact_memory + * order == -1 is expected when compacting proactively via + * 1. /proc/sys/vm/compact_memory + * 2. /sys/devices/system/node/nodex/compact + * 3. /proc/sys/vm/compaction_proactiveness */ static inline bool is_via_compact_memory(int order) { @@ -2377,6 +2378,30 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order, return false; } +/* + * Should we do compaction for target allocation order. + * Return COMPACT_SUCCESS if allocation for target order can be already + * satisfied + * Return COMPACT_SKIPPED if compaction for target order is likely to fail + * Return COMPACT_CONTINUE if compaction for target order should be ran + */ +static enum compact_result +compaction_suit_allocation_order(struct zone *zone, unsigned int order, + int highest_zoneidx, unsigned int alloc_flags) +{ + unsigned long watermark; + + watermark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK); + if (zone_watermark_ok(zone, order, watermark, highest_zoneidx, + alloc_flags)) + return COMPACT_SUCCESS; + + if (!compaction_suitable(zone, order, highest_zoneidx)) + return COMPACT_SKIPPED; + + return COMPACT_CONTINUE; +} + static enum compact_result compact_zone(struct compact_control *cc, struct capture_control *capc) { @@ -2402,19 +2427,11 @@ compact_zone(struct compact_control *cc, struct capture_control *capc) cc->migratetype = gfp_migratetype(cc->gfp_mask); if (!is_via_compact_memory(cc->order)) { - unsigned long watermark; - - /* Allocation can already succeed, nothing to do */ - watermark = wmark_pages(cc->zone, - cc->alloc_flags & ALLOC_WMARK_MASK); - if (zone_watermark_ok(cc->zone, cc->order, watermark, - cc->highest_zoneidx, cc->alloc_flags)) - return COMPACT_SUCCESS; - - /* Compaction is likely to fail */ - if (!compaction_suitable(cc->zone, cc->order, - cc->highest_zoneidx)) - return COMPACT_SKIPPED; + ret = compaction_suit_allocation_order(cc->zone, cc->order, + cc->highest_zoneidx, + cc->alloc_flags); + if (ret != COMPACT_CONTINUE) + return ret; } /* @@ -2913,6 +2930,7 @@ static bool kcompactd_node_suitable(pg_data_t *pgdat) int zoneid; struct zone *zone; enum zone_type highest_zoneidx = pgdat->kcompactd_highest_zoneidx; + enum compact_result ret; for (zoneid = 0; zoneid <= highest_zoneidx; zoneid++) { zone = &pgdat->node_zones[zoneid]; @@ -2920,14 +2938,10 @@ static bool kcompactd_node_suitable(pg_data_t *pgdat) if (!populated_zone(zone)) continue; - /* Allocation can already succeed, check other zones */ - if (zone_watermark_ok(zone, pgdat->kcompactd_max_order, - min_wmark_pages(zone), - highest_zoneidx, 0)) - continue; - - if (compaction_suitable(zone, pgdat->kcompactd_max_order, - highest_zoneidx)) + ret = compaction_suit_allocation_order(zone, + pgdat->kcompactd_max_order, + highest_zoneidx, ALLOC_WMARK_MIN); + if (ret == COMPACT_CONTINUE) return true; } @@ -2950,6 +2964,8 @@ static void kcompactd_do_work(pg_data_t *pgdat) .ignore_skip_hint = false, .gfp_mask = GFP_KERNEL, }; + enum compact_result ret; + trace_mm_compaction_kcompactd_wake(pgdat->node_id, cc.order, cc.highest_zoneidx); count_compact_event(KCOMPACTD_WAKE); @@ -2964,12 +2980,9 @@ static void kcompactd_do_work(pg_data_t *pgdat) if (compaction_deferred(zone, cc.order)) continue; - /* Allocation can already succeed, nothing to do */ - if (zone_watermark_ok(zone, cc.order, - min_wmark_pages(zone), zoneid, 0)) - continue; - - if (!compaction_suitable(zone, cc.order, zoneid)) + ret = compaction_suit_allocation_order(zone, + cc.order, zoneid, ALLOC_WMARK_MIN); + if (ret != COMPACT_CONTINUE) continue; if (kthread_should_stop()) diff --git a/mm/damon/core-test.h b/mm/damon/core-test.h index 6cc8b245586d..649adf91ebc5 100644 --- a/mm/damon/core-test.h +++ b/mm/damon/core-test.h @@ -30,7 +30,7 @@ static void damon_test_regions(struct kunit *test) damon_add_region(r, t); KUNIT_EXPECT_EQ(test, 1u, damon_nr_regions(t)); - damon_del_region(r, t); + damon_destroy_region(r, t); KUNIT_EXPECT_EQ(test, 0u, damon_nr_regions(t)); damon_free_target(t); @@ -94,6 +94,7 @@ static void damon_test_aggregate(struct kunit *test) for (ir = 0; ir < 3; ir++) { r = damon_new_region(saddr[it][ir], eaddr[it][ir]); r->nr_accesses = accesses[it][ir]; + r->nr_accesses_bp = accesses[it][ir] * 10000; damon_add_region(r, t); } it++; @@ -147,9 +148,11 @@ static void damon_test_merge_two(struct kunit *test) t = damon_new_target(); r = damon_new_region(0, 100); r->nr_accesses = 10; + r->nr_accesses_bp = 100000; damon_add_region(r, t); r2 = damon_new_region(100, 300); r2->nr_accesses = 20; + r2->nr_accesses_bp = 200000; damon_add_region(r2, t); damon_merge_two_regions(t, r, r2); @@ -196,6 +199,7 @@ static void damon_test_merge_regions_of(struct kunit *test) for (i = 0; i < ARRAY_SIZE(sa); i++) { r = damon_new_region(sa[i], ea[i]); r->nr_accesses = nrs[i]; + r->nr_accesses_bp = nrs[i] * 10000; damon_add_region(r, t); } @@ -265,6 +269,8 @@ static void damon_test_ops_registration(struct kunit *test) /* Check double-registration failure again */ KUNIT_EXPECT_EQ(test, damon_register_ops(&ops), -EINVAL); + + damon_destroy_ctx(c); } static void damon_test_set_regions(struct kunit *test) @@ -297,6 +303,7 @@ static void damon_test_update_monitoring_result(struct kunit *test) struct damon_region *r = damon_new_region(3, 7); r->nr_accesses = 15; + r->nr_accesses_bp = 150000; r->age = 20; new_attrs = (struct damon_attrs){ @@ -316,6 +323,8 @@ static void damon_test_update_monitoring_result(struct kunit *test) damon_update_monitoring_result(r, &old_attrs, &new_attrs); KUNIT_EXPECT_EQ(test, r->nr_accesses, 150); KUNIT_EXPECT_EQ(test, r->age, 20); + + damon_free_region(r); } static void damon_test_set_attrs(struct kunit *test) @@ -339,6 +348,23 @@ static void damon_test_set_attrs(struct kunit *test) invalid_attrs = valid_attrs; invalid_attrs.aggr_interval = 4999; KUNIT_EXPECT_EQ(test, damon_set_attrs(c, &invalid_attrs), -EINVAL); + + damon_destroy_ctx(c); +} + +static void damon_test_moving_sum(struct kunit *test) +{ + unsigned int mvsum = 50000, nomvsum = 50000, len_window = 10; + unsigned int new_values[] = {10000, 0, 10000, 0, 0, 0, 10000, 0, 0, 0}; + unsigned int expects[] = {55000, 50000, 55000, 50000, 45000, 40000, + 45000, 40000, 35000, 30000}; + int i; + + for (i = 0; i < ARRAY_SIZE(new_values); i++) { + mvsum = damon_moving_sum(mvsum, nomvsum, len_window, + new_values[i]); + KUNIT_EXPECT_EQ(test, mvsum, expects[i]); + } } static void damos_test_new_filter(struct kunit *test) @@ -425,6 +451,7 @@ static struct kunit_case damon_test_cases[] = { KUNIT_CASE(damon_test_set_regions), KUNIT_CASE(damon_test_update_monitoring_result), KUNIT_CASE(damon_test_set_attrs), + KUNIT_CASE(damon_test_moving_sum), KUNIT_CASE(damos_test_new_filter), KUNIT_CASE(damos_test_filter_out), {}, diff --git a/mm/damon/core.c b/mm/damon/core.c index bcd2bd9d6c10..9f4f7c378cf3 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -128,6 +128,7 @@ struct damon_region *damon_new_region(unsigned long start, unsigned long end) region->ar.start = start; region->ar.end = end; region->nr_accesses = 0; + region->nr_accesses_bp = 0; INIT_LIST_HEAD(®ion->list); region->age = 0; @@ -312,7 +313,9 @@ static struct damos_quota *damos_quota_init_priv(struct damos_quota *quota) } struct damos *damon_new_scheme(struct damos_access_pattern *pattern, - enum damos_action action, struct damos_quota *quota, + enum damos_action action, + unsigned long apply_interval_us, + struct damos_quota *quota, struct damos_watermarks *wmarks) { struct damos *scheme; @@ -322,6 +325,13 @@ struct damos *damon_new_scheme(struct damos_access_pattern *pattern, return NULL; scheme->pattern = *pattern; scheme->action = action; + scheme->apply_interval_us = apply_interval_us; + /* + * next_apply_sis will be set when kdamond starts. While kdamond is + * running, it will also updated when it is added to the DAMON context, + * or damon_attrs are updated. + */ + scheme->next_apply_sis = 0; INIT_LIST_HEAD(&scheme->filters); scheme->stat = (struct damos_stat){}; INIT_LIST_HEAD(&scheme->list); @@ -334,9 +344,21 @@ struct damos *damon_new_scheme(struct damos_access_pattern *pattern, return scheme; } +static void damos_set_next_apply_sis(struct damos *s, struct damon_ctx *ctx) +{ + unsigned long sample_interval = ctx->attrs.sample_interval ? + ctx->attrs.sample_interval : 1; + unsigned long apply_interval = s->apply_interval_us ? + s->apply_interval_us : ctx->attrs.aggr_interval; + + s->next_apply_sis = ctx->passed_sample_intervals + + apply_interval / sample_interval; +} + void damon_add_scheme(struct damon_ctx *ctx, struct damos *s) { list_add_tail(&s->list, &ctx->schemes); + damos_set_next_apply_sis(s, ctx); } static void damon_del_scheme(struct damos *s) @@ -427,8 +449,10 @@ struct damon_ctx *damon_new_ctx(void) ctx->attrs.aggr_interval = 100 * 1000; ctx->attrs.ops_update_interval = 60 * 1000 * 1000; - ktime_get_coarse_ts64(&ctx->last_aggregation); - ctx->last_ops_update = ctx->last_aggregation; + ctx->passed_sample_intervals = 0; + /* These will be set from kdamond_init_intervals_sis() */ + ctx->next_aggregation_sis = 0; + ctx->next_ops_update_sis = 0; mutex_init(&ctx->kdamond_lock); @@ -506,6 +530,7 @@ static void damon_update_monitoring_result(struct damon_region *r, { r->nr_accesses = damon_nr_accesses_for_new_attrs(r->nr_accesses, old_attrs, new_attrs); + r->nr_accesses_bp = r->nr_accesses * 10000; r->age = damon_age_for_new_attrs(r->age, old_attrs, new_attrs); } @@ -541,13 +566,21 @@ static void damon_update_monitoring_results(struct damon_ctx *ctx, * @ctx: monitoring context * @attrs: monitoring attributes * - * This function should not be called while the kdamond is running. + * This function should be called while the kdamond is not running, or an + * access check results aggregation is not ongoing (e.g., from + * &struct damon_callback->after_aggregation or + * &struct damon_callback->after_wmarks_check callbacks). + * * Every time interval is in micro-seconds. * * Return: 0 on success, negative error code otherwise. */ int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs) { + unsigned long sample_interval = attrs->sample_interval ? + attrs->sample_interval : 1; + struct damos *s; + if (attrs->min_nr_regions < 3) return -EINVAL; if (attrs->min_nr_regions > attrs->max_nr_regions) @@ -555,8 +588,17 @@ int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs) if (attrs->sample_interval > attrs->aggr_interval) return -EINVAL; + ctx->next_aggregation_sis = ctx->passed_sample_intervals + + attrs->aggr_interval / sample_interval; + ctx->next_ops_update_sis = ctx->passed_sample_intervals + + attrs->ops_update_interval / sample_interval; + damon_update_monitoring_results(ctx, attrs); ctx->attrs = *attrs; + + damon_for_each_scheme(s, ctx) + damos_set_next_apply_sis(s, ctx); + return 0; } @@ -729,38 +771,6 @@ int damon_stop(struct damon_ctx **ctxs, int nr_ctxs) } /* - * damon_check_reset_time_interval() - Check if a time interval is elapsed. - * @baseline: the time to check whether the interval has elapsed since - * @interval: the time interval (microseconds) - * - * See whether the given time interval has passed since the given baseline - * time. If so, it also updates the baseline to current time for next check. - * - * Return: true if the time interval has passed, or false otherwise. - */ -static bool damon_check_reset_time_interval(struct timespec64 *baseline, - unsigned long interval) -{ - struct timespec64 now; - - ktime_get_coarse_ts64(&now); - if ((timespec64_to_ns(&now) - timespec64_to_ns(baseline)) < - interval * 1000) - return false; - *baseline = now; - return true; -} - -/* - * Check whether it is time to flush the aggregated information - */ -static bool kdamond_aggregate_interval_passed(struct damon_ctx *ctx) -{ - return damon_check_reset_time_interval(&ctx->last_aggregation, - ctx->attrs.aggr_interval); -} - -/* * Reset the aggregated monitoring results ('nr_accesses' of each region). */ static void kdamond_reset_aggregated(struct damon_ctx *c) @@ -772,7 +782,7 @@ static void kdamond_reset_aggregated(struct damon_ctx *c) struct damon_region *r; damon_for_each_region(r, t) { - trace_damon_aggregated(t, ti, r, damon_nr_regions(t)); + trace_damon_aggregated(ti, r, damon_nr_regions(t)); r->last_nr_accesses = r->nr_accesses; r->nr_accesses = 0; } @@ -786,12 +796,13 @@ static void damon_split_region_at(struct damon_target *t, static bool __damos_valid_target(struct damon_region *r, struct damos *s) { unsigned long sz; + unsigned int nr_accesses = r->nr_accesses_bp / 10000; 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_nr_accesses <= nr_accesses && + nr_accesses <= s->pattern.max_nr_accesses && s->pattern.min_age_region <= r->age && r->age <= s->pattern.max_age_region; } @@ -946,6 +957,33 @@ static void damos_apply_scheme(struct damon_ctx *c, struct damon_target *t, struct timespec64 begin, end; unsigned long sz_applied = 0; int err = 0; + /* + * We plan to support multiple context per kdamond, as DAMON sysfs + * implies with 'nr_contexts' file. Nevertheless, only single context + * per kdamond is supported for now. So, we can simply use '0' context + * index here. + */ + unsigned int cidx = 0; + struct damos *siter; /* schemes iterator */ + unsigned int sidx = 0; + struct damon_target *titer; /* targets iterator */ + unsigned int tidx = 0; + bool do_trace = false; + + /* get indices for trace_damos_before_apply() */ + if (trace_damos_before_apply_enabled()) { + damon_for_each_scheme(siter, c) { + if (siter == s) + break; + sidx++; + } + damon_for_each_target(titer, c) { + if (titer == t) + break; + tidx++; + } + do_trace = true; + } if (c->ops.apply_scheme) { if (quota->esz && quota->charged_sz + sz > quota->esz) { @@ -960,8 +998,11 @@ static void damos_apply_scheme(struct damon_ctx *c, struct damon_target *t, ktime_get_coarse_ts64(&begin); if (c->callback.before_damos_apply) err = c->callback.before_damos_apply(c, t, r, s); - if (!err) + if (!err) { + trace_damos_before_apply(cidx, sidx, tidx, r, + damon_nr_regions(t), do_trace); 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); @@ -1079,14 +1120,29 @@ static void kdamond_apply_schemes(struct damon_ctx *c) struct damon_target *t; struct damon_region *r, *next_r; struct damos *s; + unsigned long sample_interval = c->attrs.sample_interval ? + c->attrs.sample_interval : 1; + bool has_schemes_to_apply = false; damon_for_each_scheme(s, c) { + if (c->passed_sample_intervals != s->next_apply_sis) + continue; + + s->next_apply_sis += + (s->apply_interval_us ? s->apply_interval_us : + c->attrs.aggr_interval) / sample_interval; + if (!s->wmarks.activated) continue; + has_schemes_to_apply = true; + damos_adjust_quota(c, s); } + if (!has_schemes_to_apply) + return; + damon_for_each_target(t, c) { damon_for_each_region_safe(r, next_r, t) damon_do_apply_schemes(c, t, r); @@ -1103,6 +1159,7 @@ static void damon_merge_two_regions(struct damon_target *t, l->nr_accesses = (l->nr_accesses * sz_l + r->nr_accesses * sz_r) / (sz_l + sz_r); + l->nr_accesses_bp = l->nr_accesses * 10000; l->age = (l->age * sz_l + r->age * sz_r) / (sz_l + sz_r); l->ar.end = r->ar.end; damon_destroy_region(r, t); @@ -1174,6 +1231,7 @@ static void damon_split_region_at(struct damon_target *t, new->age = r->age; new->last_nr_accesses = r->last_nr_accesses; + new->nr_accesses_bp = r->nr_accesses_bp; damon_insert_region(new, r, damon_next_region(r), t); } @@ -1241,18 +1299,6 @@ static void kdamond_split_regions(struct damon_ctx *ctx) } /* - * Check whether it is time to check and apply the operations-related data - * structures. - * - * Returns true if it is. - */ -static bool kdamond_need_update_operations(struct damon_ctx *ctx) -{ - return damon_check_reset_time_interval(&ctx->last_ops_update, - ctx->attrs.ops_update_interval); -} - -/* * Check whether current monitoring should be stopped * * The monitoring is stopped when either the user requested to stop, or all @@ -1280,12 +1326,10 @@ static bool kdamond_need_stop(struct damon_ctx *ctx) static unsigned long damos_wmark_metric_value(enum damos_wmark_metric metric) { - struct sysinfo i; - switch (metric) { case DAMOS_WMARK_FREE_MEM_RATE: - si_meminfo(&i); - return i.freeram * 1000 / i.totalram; + return global_zone_page_state(NR_FREE_PAGES) * 1000 / + totalram_pages(); default: break; } @@ -1363,6 +1407,25 @@ static int kdamond_wait_activation(struct damon_ctx *ctx) return -EBUSY; } +static void kdamond_init_intervals_sis(struct damon_ctx *ctx) +{ + unsigned long sample_interval = ctx->attrs.sample_interval ? + ctx->attrs.sample_interval : 1; + unsigned long apply_interval; + struct damos *scheme; + + ctx->passed_sample_intervals = 0; + ctx->next_aggregation_sis = ctx->attrs.aggr_interval / sample_interval; + ctx->next_ops_update_sis = ctx->attrs.ops_update_interval / + sample_interval; + + damon_for_each_scheme(scheme, ctx) { + apply_interval = scheme->apply_interval_us ? + scheme->apply_interval_us : ctx->attrs.aggr_interval; + scheme->next_apply_sis = apply_interval / sample_interval; + } +} + /* * The monitoring daemon that runs as a kernel thread */ @@ -1376,6 +1439,8 @@ static int kdamond_fn(void *data) pr_debug("kdamond (%d) starts\n", current->pid); + kdamond_init_intervals_sis(ctx); + if (ctx->ops.init) ctx->ops.init(ctx); if (ctx->callback.before_start && ctx->callback.before_start(ctx)) @@ -1384,6 +1449,17 @@ static int kdamond_fn(void *data) sz_limit = damon_region_sz_limit(ctx); while (!kdamond_need_stop(ctx)) { + /* + * ctx->attrs and ctx->next_{aggregation,ops_update}_sis could + * be changed from after_wmarks_check() or after_aggregation() + * callbacks. Read the values here, and use those for this + * iteration. That is, damon_set_attrs() updated new values + * are respected from next iteration. + */ + unsigned long next_aggregation_sis = ctx->next_aggregation_sis; + unsigned long next_ops_update_sis = ctx->next_ops_update_sis; + unsigned long sample_interval = ctx->attrs.sample_interval; + if (kdamond_wait_activation(ctx)) break; @@ -1393,27 +1469,44 @@ static int kdamond_fn(void *data) ctx->callback.after_sampling(ctx)) break; - kdamond_usleep(ctx->attrs.sample_interval); + kdamond_usleep(sample_interval); + ctx->passed_sample_intervals++; if (ctx->ops.check_accesses) max_nr_accesses = ctx->ops.check_accesses(ctx); - if (kdamond_aggregate_interval_passed(ctx)) { + if (ctx->passed_sample_intervals == next_aggregation_sis) { kdamond_merge_regions(ctx, max_nr_accesses / 10, sz_limit); if (ctx->callback.after_aggregation && ctx->callback.after_aggregation(ctx)) break; - if (!list_empty(&ctx->schemes)) - kdamond_apply_schemes(ctx); + } + + /* + * do kdamond_apply_schemes() after kdamond_merge_regions() if + * possible, to reduce overhead + */ + if (!list_empty(&ctx->schemes)) + kdamond_apply_schemes(ctx); + + sample_interval = ctx->attrs.sample_interval ? + ctx->attrs.sample_interval : 1; + if (ctx->passed_sample_intervals == next_aggregation_sis) { + ctx->next_aggregation_sis = next_aggregation_sis + + ctx->attrs.aggr_interval / sample_interval; + kdamond_reset_aggregated(ctx); kdamond_split_regions(ctx); if (ctx->ops.reset_aggregated) ctx->ops.reset_aggregated(ctx); } - if (kdamond_need_update_operations(ctx)) { + if (ctx->passed_sample_intervals == next_ops_update_sis) { + ctx->next_ops_update_sis = next_ops_update_sis + + ctx->attrs.ops_update_interval / + sample_interval; if (ctx->ops.update) ctx->ops.update(ctx); sz_limit = damon_region_sz_limit(ctx); @@ -1517,6 +1610,76 @@ int damon_set_region_biggest_system_ram_default(struct damon_target *t, return damon_set_regions(t, &addr_range, 1); } +/* + * damon_moving_sum() - Calculate an inferred moving sum value. + * @mvsum: Inferred sum of the last @len_window values. + * @nomvsum: Non-moving sum of the last discrete @len_window window values. + * @len_window: The number of last values to take care of. + * @new_value: New value that will be added to the pseudo moving sum. + * + * Moving sum (moving average * window size) is good for handling noise, but + * the cost of keeping past values can be high for arbitrary window size. This + * function implements a lightweight pseudo moving sum function that doesn't + * keep the past window values. + * + * It simply assumes there was no noise in the past, and get the no-noise + * assumed past value to drop from @nomvsum and @len_window. @nomvsum is a + * non-moving sum of the last window. For example, if @len_window is 10 and we + * have 25 values, @nomvsum is the sum of the 11th to 20th values of the 25 + * values. Hence, this function simply drops @nomvsum / @len_window from + * given @mvsum and add @new_value. + * + * For example, if @len_window is 10 and @nomvsum is 50, the last 10 values for + * the last window could be vary, e.g., 0, 10, 0, 10, 0, 10, 0, 0, 0, 20. For + * calculating next moving sum with a new value, we should drop 0 from 50 and + * add the new value. However, this function assumes it got value 5 for each + * of the last ten times. Based on the assumption, when the next value is + * measured, it drops the assumed past value, 5 from the current sum, and add + * the new value to get the updated pseduo-moving average. + * + * This means the value could have errors, but the errors will be disappeared + * for every @len_window aligned calls. For example, if @len_window is 10, the + * pseudo moving sum with 11th value to 19th value would have an error. But + * the sum with 20th value will not have the error. + * + * Return: Pseudo-moving average after getting the @new_value. + */ +static unsigned int damon_moving_sum(unsigned int mvsum, unsigned int nomvsum, + unsigned int len_window, unsigned int new_value) +{ + return mvsum - nomvsum / len_window + new_value; +} + +/** + * damon_update_region_access_rate() - Update the access rate of a region. + * @r: The DAMON region to update for its access check result. + * @accessed: Whether the region has accessed during last sampling interval. + * @attrs: The damon_attrs of the DAMON context. + * + * Update the access rate of a region with the region's last sampling interval + * access check result. + * + * Usually this will be called by &damon_operations->check_accesses callback. + */ +void damon_update_region_access_rate(struct damon_region *r, bool accessed, + struct damon_attrs *attrs) +{ + unsigned int len_window = 1; + + /* + * sample_interval can be zero, but cannot be larger than + * aggr_interval, owing to validation of damon_set_attrs(). + */ + if (attrs->sample_interval) + len_window = attrs->aggr_interval / attrs->sample_interval; + r->nr_accesses_bp = damon_moving_sum(r->nr_accesses_bp, + r->last_nr_accesses * 10000, len_window, + accessed ? 10000 : 0); + + if (accessed) + r->nr_accesses++; +} + static int __init damon_init(void) { damon_region_cache = KMEM_CACHE(damon_region, 0); diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index 124f0f8c97b7..dc0ea1fc30ca 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -278,7 +278,8 @@ static struct damos **str_to_schemes(const char *str, ssize_t len, goto fail; pos += parsed; - scheme = damon_new_scheme(&pattern, action, "a, &wmarks); + scheme = damon_new_scheme(&pattern, action, 0, "a, + &wmarks); if (!scheme) goto fail; diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c index 7b8fce2f67a8..3ecdcc029443 100644 --- a/mm/damon/lru_sort.c +++ b/mm/damon/lru_sort.c @@ -158,6 +158,8 @@ static struct damos *damon_lru_sort_new_scheme( pattern, /* (de)prioritize on LRU-lists */ action, + /* for each aggregation interval */ + 0, /* under the quota. */ "a, /* (De)activate this according to the watermarks. */ diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index 909db25efb35..081e2a325778 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -148,7 +148,8 @@ out: return accessed; } -static void __damon_pa_check_access(struct damon_region *r) +static void __damon_pa_check_access(struct damon_region *r, + struct damon_attrs *attrs) { static unsigned long last_addr; static unsigned long last_folio_sz = PAGE_SIZE; @@ -157,14 +158,12 @@ static void __damon_pa_check_access(struct damon_region *r) /* If the region is in the last checked page, reuse the result */ if (ALIGN_DOWN(last_addr, last_folio_sz) == ALIGN_DOWN(r->sampling_addr, last_folio_sz)) { - if (last_accessed) - r->nr_accesses++; + damon_update_region_access_rate(r, last_accessed, attrs); return; } last_accessed = damon_pa_young(r->sampling_addr, &last_folio_sz); - if (last_accessed) - r->nr_accesses++; + damon_update_region_access_rate(r, last_accessed, attrs); last_addr = r->sampling_addr; } @@ -177,7 +176,7 @@ 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(r); + __damon_pa_check_access(r, &ctx->attrs); max_nr_accesses = max(r->nr_accesses, max_nr_accesses); } } diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c index 648d2a85523a..ab974e477d2f 100644 --- a/mm/damon/reclaim.c +++ b/mm/damon/reclaim.c @@ -142,6 +142,8 @@ static struct damos *damon_reclaim_new_scheme(void) &pattern, /* page out those, as soon as found */ DAMOS_PAGEOUT, + /* for each aggregation interval */ + 0, /* under the quota. */ &damon_reclaim_quota, /* (De)activate this according to the watermarks. */ diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index 527e7d17eb3b..a7d70b95c4dd 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -31,7 +31,7 @@ static struct damon_sysfs_scheme_region *damon_sysfs_scheme_region_alloc( return NULL; sysfs_region->kobj = (struct kobject){}; sysfs_region->ar = region->ar; - sysfs_region->nr_accesses = region->nr_accesses; + sysfs_region->nr_accesses = region->nr_accesses_bp / 10000; sysfs_region->age = region->age; INIT_LIST_HEAD(&sysfs_region->list); return sysfs_region; @@ -1121,6 +1121,7 @@ struct damon_sysfs_scheme { struct kobject kobj; enum damos_action action; struct damon_sysfs_access_pattern *access_pattern; + unsigned long apply_interval_us; struct damon_sysfs_quotas *quotas; struct damon_sysfs_watermarks *watermarks; struct damon_sysfs_scheme_filters *filters; @@ -1141,7 +1142,7 @@ static const char * const damon_sysfs_damos_action_strs[] = { }; static struct damon_sysfs_scheme *damon_sysfs_scheme_alloc( - enum damos_action action) + enum damos_action action, unsigned long apply_interval_us) { struct damon_sysfs_scheme *scheme = kmalloc(sizeof(*scheme), GFP_KERNEL); @@ -1150,6 +1151,7 @@ static struct damon_sysfs_scheme *damon_sysfs_scheme_alloc( return NULL; scheme->kobj = (struct kobject){}; scheme->action = action; + scheme->apply_interval_us = apply_interval_us; return scheme; } @@ -1353,6 +1355,25 @@ static ssize_t action_store(struct kobject *kobj, struct kobj_attribute *attr, return -EINVAL; } +static ssize_t apply_interval_us_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, "%lu\n", scheme->apply_interval_us); +} + +static ssize_t apply_interval_us_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); + int err = kstrtoul(buf, 0, &scheme->apply_interval_us); + + return err ? err : count; +} + static void damon_sysfs_scheme_release(struct kobject *kobj) { kfree(container_of(kobj, struct damon_sysfs_scheme, kobj)); @@ -1361,8 +1382,12 @@ static void damon_sysfs_scheme_release(struct kobject *kobj) static struct kobj_attribute damon_sysfs_scheme_action_attr = __ATTR_RW_MODE(action, 0600); +static struct kobj_attribute damon_sysfs_scheme_apply_interval_us_attr = + __ATTR_RW_MODE(apply_interval_us, 0600); + static struct attribute *damon_sysfs_scheme_attrs[] = { &damon_sysfs_scheme_action_attr.attr, + &damon_sysfs_scheme_apply_interval_us_attr.attr, NULL, }; ATTRIBUTE_GROUPS(damon_sysfs_scheme); @@ -1413,7 +1438,11 @@ static int damon_sysfs_schemes_add_dirs(struct damon_sysfs_schemes *schemes, schemes->schemes_arr = schemes_arr; for (i = 0; i < nr_schemes; i++) { - scheme = damon_sysfs_scheme_alloc(DAMOS_STAT); + /* + * apply_interval_us as 0 means same to aggregation interval + * (same to before-apply_interval behavior) + */ + scheme = damon_sysfs_scheme_alloc(DAMOS_STAT, 0); if (!scheme) { damon_sysfs_schemes_rm_dirs(schemes); return -ENOMEM; @@ -1610,8 +1639,8 @@ static struct damos *damon_sysfs_mk_scheme( .low = sysfs_wmarks->low, }; - scheme = damon_new_scheme(&pattern, sysfs_scheme->action, "a, - &wmarks); + scheme = damon_new_scheme(&pattern, sysfs_scheme->action, + sysfs_scheme->apply_interval_us, "a, &wmarks); if (!scheme) return NULL; @@ -1641,6 +1670,7 @@ static void damon_sysfs_update_scheme(struct damos *scheme, scheme->pattern.max_age_region = access_pattern->age->max; scheme->action = sysfs_scheme->action; + scheme->apply_interval_us = sysfs_scheme->apply_interval_us; scheme->quota.ms = sysfs_quotas->ms; scheme->quota.sz = sysfs_quotas->sz; diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index cf8a9fc5c9d1..a4d1f63c5b23 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -558,23 +558,27 @@ static bool damon_va_young(struct mm_struct *mm, unsigned long addr, * r the region to be checked */ static void __damon_va_check_access(struct mm_struct *mm, - struct damon_region *r, bool same_target) + struct damon_region *r, bool same_target, + struct damon_attrs *attrs) { static unsigned long last_addr; static unsigned long last_folio_sz = PAGE_SIZE; static bool last_accessed; + if (!mm) { + damon_update_region_access_rate(r, false, attrs); + return; + } + /* If the region is in the last checked page, reuse the result */ if (same_target && (ALIGN_DOWN(last_addr, last_folio_sz) == ALIGN_DOWN(r->sampling_addr, last_folio_sz))) { - if (last_accessed) - r->nr_accesses++; + damon_update_region_access_rate(r, last_accessed, attrs); return; } last_accessed = damon_va_young(mm, r->sampling_addr, &last_folio_sz); - if (last_accessed) - r->nr_accesses++; + damon_update_region_access_rate(r, last_accessed, attrs); last_addr = r->sampling_addr; } @@ -589,15 +593,15 @@ static unsigned int damon_va_check_accesses(struct damon_ctx *ctx) 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(mm, r, same_target); + __damon_va_check_access(mm, r, same_target, + &ctx->attrs); max_nr_accesses = max(r->nr_accesses, max_nr_accesses); same_target = true; } - mmput(mm); + if (mm) + mmput(mm); } return max_nr_accesses; diff --git a/mm/filemap.c b/mm/filemap.c index f0a15ce1bd1b..340c693112a9 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -131,11 +131,8 @@ static void page_cache_delete(struct address_space *mapping, mapping_set_update(&xas, mapping); - /* hugetlb pages are represented by a single entry in the xarray */ - if (!folio_test_hugetlb(folio)) { - xas_set_order(&xas, folio->index, folio_order(folio)); - nr = folio_nr_pages(folio); - } + xas_set_order(&xas, folio->index, folio_order(folio)); + nr = folio_nr_pages(folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); @@ -234,7 +231,7 @@ void filemap_free_folio(struct address_space *mapping, struct folio *folio) if (free_folio) free_folio(folio); - if (folio_test_large(folio) && !folio_test_hugetlb(folio)) + if (folio_test_large(folio)) refs = folio_nr_pages(folio); folio_put_refs(folio, refs); } @@ -855,14 +852,15 @@ noinline int __filemap_add_folio(struct address_space *mapping, if (!huge) { int error = mem_cgroup_charge(folio, NULL, gfp); - VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio); if (error) return error; charged = true; - xas_set_order(&xas, index, folio_order(folio)); - nr = folio_nr_pages(folio); } + VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio); + xas_set_order(&xas, index, folio_order(folio)); + nr = folio_nr_pages(folio); + gfp &= GFP_RECLAIM_MASK; folio_ref_add(folio, nr); folio->mapping = mapping; @@ -2040,7 +2038,7 @@ unsigned find_get_entries(struct address_space *mapping, pgoff_t *start, int idx = folio_batch_count(fbatch) - 1; folio = fbatch->folios[idx]; - if (!xa_is_value(folio) && !folio_test_hugetlb(folio)) + if (!xa_is_value(folio)) nr = folio_nr_pages(folio); *start = indices[idx] + nr; } @@ -2104,7 +2102,7 @@ put: int idx = folio_batch_count(fbatch) - 1; folio = fbatch->folios[idx]; - if (!xa_is_value(folio) && !folio_test_hugetlb(folio)) + if (!xa_is_value(folio)) nr = folio_nr_pages(folio); *start = indices[idx] + nr; } @@ -2145,9 +2143,6 @@ unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start, continue; if (!folio_batch_add(fbatch, folio)) { unsigned long nr = folio_nr_pages(folio); - - if (folio_test_hugetlb(folio)) - nr = 1; *start = folio->index + nr; goto out; } @@ -2213,9 +2208,6 @@ unsigned filemap_get_folios_contig(struct address_space *mapping, if (!folio_batch_add(fbatch, folio)) { nr = folio_nr_pages(folio); - - if (folio_test_hugetlb(folio)) - nr = 1; *start = folio->index + nr; goto out; } @@ -2232,10 +2224,7 @@ update_start: if (nr) { folio = fbatch->folios[nr - 1]; - if (folio_test_hugetlb(folio)) - *start = folio->index + 1; - else - *start = folio_next_index(folio); + *start = folio->index + folio_nr_pages(folio); } out: rcu_read_unlock(); @@ -2273,9 +2262,6 @@ unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start, continue; if (!folio_batch_add(fbatch, folio)) { unsigned long nr = folio_nr_pages(folio); - - if (folio_test_hugetlb(folio)) - nr = 1; *start = folio->index + nr; goto out; } @@ -3591,7 +3577,7 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, addr += (xas.xa_index - last_pgoff) << PAGE_SHIFT; vmf->pte += xas.xa_index - last_pgoff; last_pgoff = xas.xa_index; - end = folio->index + folio_nr_pages(folio) - 1; + end = folio_next_index(folio) - 1; nr_pages = min(end, end_pgoff) - xas.xa_index + 1; if (!folio_test_large(folio)) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 064fbd90822b..aa0224556132 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -65,7 +65,11 @@ unsigned long transparent_hugepage_flags __read_mostly = (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)| (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); -static struct shrinker deferred_split_shrinker; +static struct shrinker *deferred_split_shrinker; +static unsigned long deferred_split_count(struct shrinker *shrink, + struct shrink_control *sc); +static unsigned long deferred_split_scan(struct shrinker *shrink, + struct shrink_control *sc); static atomic_t huge_zero_refcount; struct page *huge_zero_page __read_mostly; @@ -229,11 +233,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, return 0; } -static struct shrinker huge_zero_page_shrinker = { - .count_objects = shrink_huge_zero_page_count, - .scan_objects = shrink_huge_zero_page_scan, - .seeks = DEFAULT_SEEKS, -}; +static struct shrinker *huge_zero_page_shrinker; #ifdef CONFIG_SYSFS static ssize_t enabled_show(struct kobject *kobj, @@ -454,6 +454,38 @@ static inline void hugepage_exit_sysfs(struct kobject *hugepage_kobj) } #endif /* CONFIG_SYSFS */ +static int __init thp_shrinker_init(void) +{ + huge_zero_page_shrinker = shrinker_alloc(0, "thp-zero"); + if (!huge_zero_page_shrinker) + return -ENOMEM; + + deferred_split_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE | + SHRINKER_MEMCG_AWARE | + SHRINKER_NONSLAB, + "thp-deferred_split"); + if (!deferred_split_shrinker) { + shrinker_free(huge_zero_page_shrinker); + return -ENOMEM; + } + + huge_zero_page_shrinker->count_objects = shrink_huge_zero_page_count; + huge_zero_page_shrinker->scan_objects = shrink_huge_zero_page_scan; + shrinker_register(huge_zero_page_shrinker); + + deferred_split_shrinker->count_objects = deferred_split_count; + deferred_split_shrinker->scan_objects = deferred_split_scan; + shrinker_register(deferred_split_shrinker); + + return 0; +} + +static void __init thp_shrinker_exit(void) +{ + shrinker_free(huge_zero_page_shrinker); + shrinker_free(deferred_split_shrinker); +} + static int __init hugepage_init(void) { int err; @@ -482,12 +514,9 @@ static int __init hugepage_init(void) if (err) goto err_slab; - err = register_shrinker(&huge_zero_page_shrinker, "thp-zero"); - if (err) - goto err_hzp_shrinker; - err = register_shrinker(&deferred_split_shrinker, "thp-deferred_split"); + err = thp_shrinker_init(); if (err) - goto err_split_shrinker; + goto err_shrinker; /* * By default disable transparent hugepages on smaller systems, @@ -505,10 +534,8 @@ static int __init hugepage_init(void) return 0; err_khugepaged: - unregister_shrinker(&deferred_split_shrinker); -err_split_shrinker: - unregister_shrinker(&huge_zero_page_shrinker); -err_hzp_shrinker: + thp_shrinker_exit(); +err_shrinker: khugepaged_destroy(); err_slab: hugepage_exit_sysfs(hugepage_kobj); @@ -1490,9 +1517,9 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; pmd_t oldpmd = vmf->orig_pmd; pmd_t pmd; - struct page *page; + struct folio *folio; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; - int page_nid = NUMA_NO_NODE; + int nid = NUMA_NO_NODE; int target_nid, last_cpupid = (-1 & LAST_CPUPID_MASK); bool migrated = false, writable = false; int flags = 0; @@ -1514,36 +1541,34 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) can_change_pmd_writable(vma, vmf->address, pmd)) writable = true; - page = vm_normal_page_pmd(vma, haddr, pmd); - if (!page) + folio = vm_normal_folio_pmd(vma, haddr, pmd); + if (!folio) goto out_map; /* See similar comment in do_numa_page for explanation */ if (!writable) flags |= TNF_NO_GROUP; - page_nid = page_to_nid(page); + nid = folio_nid(folio); /* * For memory tiering mode, cpupid of slow memory page is used * to record page access time. So use default value. */ - if (node_is_toptier(page_nid)) - last_cpupid = page_cpupid_last(page); - target_nid = numa_migrate_prep(page, vma, haddr, page_nid, - &flags); - + if (node_is_toptier(nid)) + last_cpupid = page_cpupid_last(&folio->page); + target_nid = numa_migrate_prep(folio, vma, haddr, nid, &flags); if (target_nid == NUMA_NO_NODE) { - put_page(page); + folio_put(folio); goto out_map; } spin_unlock(vmf->ptl); writable = false; - migrated = migrate_misplaced_page(page, vma, target_nid); + migrated = migrate_misplaced_folio(folio, vma, target_nid); if (migrated) { flags |= TNF_MIGRATED; - page_nid = target_nid; + nid = target_nid; } else { flags |= TNF_MIGRATE_FAIL; vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); @@ -1555,9 +1580,8 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) } out: - if (page_nid != NUMA_NO_NODE) - task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, - flags); + if (nid != NUMA_NO_NODE) + task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); return 0; @@ -2828,7 +2852,7 @@ void deferred_split_folio(struct folio *folio) #ifdef CONFIG_MEMCG if (memcg) set_shrinker_bit(memcg, folio_nid(folio), - deferred_split_shrinker.id); + deferred_split_shrinker->id); #endif } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); @@ -2902,14 +2926,6 @@ next: return split; } -static struct shrinker deferred_split_shrinker = { - .count_objects = deferred_split_count, - .scan_objects = deferred_split_scan, - .seeks = DEFAULT_SEEKS, - .flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE | - SHRINKER_NONSLAB, -}; - #ifdef CONFIG_DEBUG_FS static void split_huge_pages_all(void) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 1301ba7b2c9a..3fb3a5232173 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -984,7 +984,7 @@ static long region_count(struct resv_map *resv, long f, long t) /* * Convert the address within this vma to the page offset within - * the mapping, in pagecache page units; huge pages here. + * the mapping, huge page units here. */ static pgoff_t vma_hugecache_offset(struct hstate *h, struct vm_area_struct *vma, unsigned long address) @@ -993,13 +993,6 @@ static pgoff_t vma_hugecache_offset(struct hstate *h, (vma->vm_pgoff >> huge_page_order(h)); } -pgoff_t linear_hugepage_index(struct vm_area_struct *vma, - unsigned long address) -{ - return vma_hugecache_offset(hstate_vma(vma), vma, address); -} -EXPORT_SYMBOL_GPL(linear_hugepage_index); - /** * vma_kernel_pagesize - Page size granularity for this VMA. * @vma: The user mapping. @@ -1478,7 +1471,7 @@ static int hstate_next_node_to_alloc(struct hstate *h, } /* - * helper for remove_pool_huge_page() - return the previously saved + * helper for remove_pool_hugetlb_folio() - return the previously saved * node ["this node"] from which to free a huge page. Advance the * next node id whether or not we find a free huge page to free so * that the next attempt to free addresses the next node. @@ -1752,7 +1745,12 @@ static void __update_and_free_hugetlb_folio(struct hstate *h, if (folio_test_hugetlb_raw_hwp_unreliable(folio)) return; - if (hugetlb_vmemmap_restore(h, &folio->page)) { + /* + * If folio is not vmemmap optimized (!clear_dtor), then the folio + * is no longer identified as a hugetlb page. hugetlb_vmemmap_restore + * can only be passed hugetlb pages and will BUG otherwise. + */ + if (clear_dtor && hugetlb_vmemmap_restore(h, &folio->page)) { spin_lock_irq(&hugetlb_lock); /* * If we cannot allocate vmemmap pages, just refuse to free the @@ -1814,22 +1812,22 @@ static void free_hpage_workfn(struct work_struct *work) node = llist_del_all(&hpage_freelist); while (node) { - struct page *page; + struct folio *folio; struct hstate *h; - page = container_of((struct address_space **)node, - struct page, mapping); + folio = container_of((struct address_space **)node, + struct folio, mapping); node = node->next; - page->mapping = NULL; + folio->mapping = NULL; /* * The VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio) in * folio_hstate() is going to trigger because a previous call to * remove_hugetlb_folio() will clear the hugetlb bit, so do * not use folio_hstate() directly. */ - h = size_to_hstate(page_size(page)); + h = size_to_hstate(folio_size(folio)); - __update_and_free_hugetlb_folio(h, page_folio(page)); + __update_and_free_hugetlb_folio(h, folio); cond_resched(); } @@ -1863,11 +1861,9 @@ static void update_and_free_hugetlb_folio(struct hstate *h, struct folio *folio, static void update_and_free_pages_bulk(struct hstate *h, struct list_head *list) { - struct page *page, *t_page; - struct folio *folio; + struct folio *folio, *t_folio; - list_for_each_entry_safe(page, t_page, list, lru) { - folio = page_folio(page); + list_for_each_entry_safe(folio, t_folio, list, lru) { update_and_free_hugetlb_folio(h, folio, false); cond_resched(); } @@ -1962,9 +1958,9 @@ static void __prep_account_new_huge_page(struct hstate *h, int nid) static void __prep_new_hugetlb_folio(struct hstate *h, struct folio *folio) { + folio_set_hugetlb(folio); hugetlb_vmemmap_optimize(h, &folio->page); INIT_LIST_HEAD(&folio->lru); - folio_set_hugetlb(folio); hugetlb_set_folio_subpool(folio, NULL); set_hugetlb_cgroup(folio, NULL); set_hugetlb_cgroup_rsvd(folio, NULL); @@ -2103,20 +2099,6 @@ struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage) return NULL; } -pgoff_t hugetlb_basepage_index(struct page *page) -{ - struct page *page_head = compound_head(page); - pgoff_t index = page_index(page_head); - unsigned long compound_idx; - - if (compound_order(page_head) > MAX_ORDER) - compound_idx = page_to_pfn(page) - page_to_pfn(page_head); - else - compound_idx = page - page_head; - - return (index << compound_order(page_head)) + compound_idx; -} - static struct folio *alloc_buddy_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) @@ -2251,13 +2233,11 @@ static int alloc_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, * an additional call to free the page to low level allocators. * Called with hugetlb_lock locked. */ -static struct page *remove_pool_huge_page(struct hstate *h, - nodemask_t *nodes_allowed, - bool acct_surplus) +static struct folio *remove_pool_hugetlb_folio(struct hstate *h, + nodemask_t *nodes_allowed, bool acct_surplus) { int nr_nodes, node; - struct page *page = NULL; - struct folio *folio; + struct folio *folio = NULL; lockdep_assert_held(&hugetlb_lock); for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { @@ -2267,15 +2247,14 @@ static struct page *remove_pool_huge_page(struct hstate *h, */ if ((!acct_surplus || h->surplus_huge_pages_node[node]) && !list_empty(&h->hugepage_freelists[node])) { - page = list_entry(h->hugepage_freelists[node].next, - struct page, lru); - folio = page_folio(page); + folio = list_entry(h->hugepage_freelists[node].next, + struct folio, lru); remove_hugetlb_folio(h, folio, acct_surplus); break; } } - return page; + return folio; } /* @@ -2629,7 +2608,6 @@ static void return_unused_surplus_pages(struct hstate *h, unsigned long unused_resv_pages) { unsigned long nr_pages; - struct page *page; LIST_HEAD(page_list); lockdep_assert_held(&hugetlb_lock); @@ -2650,15 +2628,17 @@ static void return_unused_surplus_pages(struct hstate *h, * evenly across all nodes with memory. Iterate across these nodes * until we can no longer free unreserved surplus pages. This occurs * when the nodes with surplus pages have no free pages. - * remove_pool_huge_page() will balance the freed pages across the + * remove_pool_hugetlb_folio() will balance the freed pages across the * on-line nodes with memory and will handle the hstate accounting. */ while (nr_pages--) { - page = remove_pool_huge_page(h, &node_states[N_MEMORY], 1); - if (!page) + struct folio *folio; + + folio = remove_pool_hugetlb_folio(h, &node_states[N_MEMORY], 1); + if (!folio) goto out; - list_add(&page->lru, &page_list); + list_add(&folio->lru, &page_list); } out: @@ -3196,6 +3176,16 @@ int __alloc_bootmem_huge_page(struct hstate *h, int nid) } found: + + /* + * Only initialize the head struct page in memmap_init_reserved_pages, + * rest of the struct pages will be initialized by the HugeTLB + * subsystem itself. + * The head struct page is used to get folio information by the HugeTLB + * subsystem like zone id and node id. + */ + memblock_reserved_mark_noinit(virt_to_phys((void *)m + PAGE_SIZE), + huge_page_size(h) - PAGE_SIZE); /* Put them into a private list first because mem_map is not up yet */ INIT_LIST_HEAD(&m->list); list_add(&m->list, &huge_boot_pages); @@ -3203,6 +3193,43 @@ found: return 1; } +/* Initialize [start_page:end_page_number] tail struct pages of a hugepage */ +static void __init hugetlb_folio_init_tail_vmemmap(struct folio *folio, + unsigned long start_page_number, + unsigned long end_page_number) +{ + enum zone_type zone = zone_idx(folio_zone(folio)); + int nid = folio_nid(folio); + unsigned long head_pfn = folio_pfn(folio); + unsigned long pfn, end_pfn = head_pfn + end_page_number; + int ret; + + for (pfn = head_pfn + start_page_number; pfn < end_pfn; pfn++) { + struct page *page = pfn_to_page(pfn); + + __init_single_page(page, pfn, zone, nid); + prep_compound_tail((struct page *)folio, pfn - head_pfn); + ret = page_ref_freeze(page, 1); + VM_BUG_ON(!ret); + } +} + +static void __init hugetlb_folio_init_vmemmap(struct folio *folio, + struct hstate *h, + unsigned long nr_pages) +{ + int ret; + + /* Prepare folio head */ + __folio_clear_reserved(folio); + __folio_set_head(folio); + ret = folio_ref_freeze(folio, 1); + VM_BUG_ON(!ret); + /* Initialize the necessary tail struct pages */ + hugetlb_folio_init_tail_vmemmap(folio, 1, nr_pages); + prep_compound_head((struct page *)folio, huge_page_order(h)); +} + /* * Put bootmem huge pages into the standard lists after mem_map is up. * Note: This only applies to gigantic (order > MAX_ORDER) pages. @@ -3213,19 +3240,21 @@ static void __init gather_bootmem_prealloc(void) list_for_each_entry(m, &huge_boot_pages, list) { struct page *page = virt_to_page(m); - struct folio *folio = page_folio(page); + struct folio *folio = (void *)page; struct hstate *h = m->hstate; VM_BUG_ON(!hstate_is_gigantic(h)); WARN_ON(folio_ref_count(folio) != 1); - if (prep_compound_gigantic_folio(folio, huge_page_order(h))) { - WARN_ON(folio_test_reserved(folio)); - prep_new_hugetlb_folio(h, folio, folio_nid(folio)); - free_huge_folio(folio); /* add to the hugepage allocator */ - } else { - /* VERY unlikely inflated ref count on a tail page */ - free_gigantic_folio(folio, huge_page_order(h)); - } + + hugetlb_folio_init_vmemmap(folio, h, + HUGETLB_VMEMMAP_RESERVE_PAGES); + prep_new_hugetlb_folio(h, folio, folio_nid(folio)); + /* If HVO fails, initialize all tail struct pages */ + if (!HPageVmemmapOptimized(&folio->page)) + hugetlb_folio_init_tail_vmemmap(folio, + HUGETLB_VMEMMAP_RESERVE_PAGES, + pages_per_huge_page(h)); + free_huge_folio(folio); /* add to the hugepage allocator */ /* * We need to restore the 'stolen' pages to totalram_pages @@ -3236,6 +3265,7 @@ static void __init gather_bootmem_prealloc(void) cond_resched(); } } + static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid) { unsigned long i; @@ -3391,15 +3421,15 @@ static void try_to_free_low(struct hstate *h, unsigned long count, * Collect pages to be freed on a list, and free after dropping lock */ for_each_node_mask(i, *nodes_allowed) { - struct page *page, *next; + struct folio *folio, *next; struct list_head *freel = &h->hugepage_freelists[i]; - list_for_each_entry_safe(page, next, freel, lru) { + list_for_each_entry_safe(folio, next, freel, lru) { if (count >= h->nr_huge_pages) goto out; - if (PageHighMem(page)) + if (folio_test_highmem(folio)) continue; - remove_hugetlb_folio(h, page_folio(page), false); - list_add(&page->lru, &page_list); + remove_hugetlb_folio(h, folio, false); + list_add(&folio->lru, &page_list); } } @@ -3453,7 +3483,6 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, nodemask_t *nodes_allowed) { unsigned long min_count, ret; - struct page *page; LIST_HEAD(page_list); NODEMASK_ALLOC(nodemask_t, node_alloc_noretry, GFP_KERNEL); @@ -3484,7 +3513,9 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, if (nid != NUMA_NO_NODE) { unsigned long old_count = count; - count += h->nr_huge_pages - h->nr_huge_pages_node[nid]; + count += persistent_huge_pages(h) - + (h->nr_huge_pages_node[nid] - + h->surplus_huge_pages_node[nid]); /* * User may have specified a large count value which caused the * above calculation to overflow. In this case, they wanted @@ -3573,11 +3604,13 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, * Collect pages to be removed on list without dropping lock */ while (min_count < persistent_huge_pages(h)) { - page = remove_pool_huge_page(h, nodes_allowed, 0); - if (!page) + struct folio *folio; + + folio = remove_pool_hugetlb_folio(h, nodes_allowed, 0); + if (!folio) break; - list_add(&page->lru, &page_list); + list_add(&folio->lru, &page_list); } /* free the pages after dropping lock */ spin_unlock_irq(&hugetlb_lock); @@ -3612,13 +3645,21 @@ static int demote_free_hugetlb_folio(struct hstate *h, struct folio *folio) remove_hugetlb_folio_for_demote(h, folio, false); spin_unlock_irq(&hugetlb_lock); - rc = hugetlb_vmemmap_restore(h, &folio->page); - if (rc) { - /* Allocation of vmemmmap failed, we can not demote folio */ - spin_lock_irq(&hugetlb_lock); - folio_ref_unfreeze(folio, 1); - add_hugetlb_folio(h, folio, false); - return rc; + /* + * If vmemmap already existed for folio, the remove routine above would + * have cleared the hugetlb folio flag. Hence the folio is technically + * no longer a hugetlb folio. hugetlb_vmemmap_restore can only be + * passed hugetlb folios and will BUG otherwise. + */ + if (folio_test_hugetlb(folio)) { + rc = hugetlb_vmemmap_restore(h, &folio->page); + if (rc) { + /* Allocation of vmemmmap failed, we can not demote folio */ + spin_lock_irq(&hugetlb_lock); + folio_ref_unfreeze(folio, 1); + add_hugetlb_folio(h, folio, false); + return rc; + } } /* @@ -5752,7 +5793,7 @@ static bool hugetlbfs_pagecache_present(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { struct address_space *mapping = vma->vm_file->f_mapping; - pgoff_t idx = vma_hugecache_offset(h, vma, address); + pgoff_t idx = linear_page_index(vma, address); struct folio *folio; folio = filemap_get_folio(mapping, idx); @@ -5769,6 +5810,7 @@ int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping struct hstate *h = hstate_inode(inode); int err; + idx <<= huge_page_order(h); __folio_set_locked(folio); err = __filemap_add_folio(mapping, folio, idx, GFP_KERNEL, NULL); @@ -5876,7 +5918,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, * before we get page_table_lock. */ new_folio = false; - folio = filemap_lock_folio(mapping, idx); + folio = filemap_lock_hugetlb_folio(h, mapping, idx); if (IS_ERR(folio)) { size = i_size_read(mapping->host) >> huge_page_shift(h); if (idx >= size) @@ -6185,7 +6227,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, haddr); - pagecache_folio = filemap_lock_folio(mapping, idx); + pagecache_folio = filemap_lock_hugetlb_folio(h, mapping, idx); if (IS_ERR(pagecache_folio)) pagecache_folio = NULL; } @@ -6318,7 +6360,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, if (is_continue) { ret = -EFAULT; - folio = filemap_lock_folio(mapping, idx); + folio = filemap_lock_hugetlb_folio(h, mapping, idx); if (IS_ERR(folio)) goto out; folio_in_pagecache = true; @@ -6520,7 +6562,7 @@ struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma, } } - page += ((address & ~huge_page_mask(h)) >> PAGE_SHIFT); + page = nth_page(page, ((address & ~huge_page_mask(h)) >> PAGE_SHIFT)); /* * Note that page may be a sub-page, and with vmemmap diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index 4b9734777f69..76682d1d79a7 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -13,6 +13,7 @@ #include <linux/pgtable.h> #include <linux/moduleparam.h> #include <linux/bootmem_info.h> +#include <linux/mmdebug.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include "hugetlb_vmemmap.h" @@ -318,9 +319,8 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end, .reuse_addr = reuse, .vmemmap_pages = &vmemmap_pages, }; - int nid = page_to_nid((struct page *)start); - gfp_t gfp_mask = GFP_KERNEL | __GFP_THISNODE | __GFP_NORETRY | - __GFP_NOWARN; + int nid = page_to_nid((struct page *)reuse); + gfp_t gfp_mask = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; /* * Allocate a new head vmemmap page to avoid breaking a contiguous @@ -380,7 +380,7 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end, static int alloc_vmemmap_page_list(unsigned long start, unsigned long end, struct list_head *list) { - gfp_t gfp_mask = GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_THISNODE; + gfp_t gfp_mask = GFP_KERNEL | __GFP_RETRY_MAYFAIL; unsigned long nr_pages = (end - start) >> PAGE_SHIFT; int nid = page_to_nid((struct page *)start); struct page *page, *next; @@ -456,6 +456,7 @@ int hugetlb_vmemmap_restore(const struct hstate *h, struct page *head) unsigned long vmemmap_start = (unsigned long)head, vmemmap_end; unsigned long vmemmap_reuse; + VM_WARN_ON_ONCE(!PageHuge(head)); if (!HPageVmemmapOptimized(head)) return 0; @@ -550,6 +551,7 @@ void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head) unsigned long vmemmap_start = (unsigned long)head, vmemmap_end; unsigned long vmemmap_reuse; + VM_WARN_ON_ONCE(!PageHuge(head)); if (!vmemmap_should_optimize(h, head)) return; @@ -586,7 +588,7 @@ static int __init hugetlb_vmemmap_init(void) const struct hstate *h; /* HUGETLB_VMEMMAP_RESERVE_SIZE should cover all used struct pages */ - BUILD_BUG_ON(__NR_USED_SUBPAGE * sizeof(struct page) > HUGETLB_VMEMMAP_RESERVE_SIZE); + BUILD_BUG_ON(__NR_USED_SUBPAGE > HUGETLB_VMEMMAP_RESERVE_PAGES); for_each_hstate(h) { if (hugetlb_vmemmap_optimizable(h)) { diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h index 25bd0e002431..4573899855d7 100644 --- a/mm/hugetlb_vmemmap.h +++ b/mm/hugetlb_vmemmap.h @@ -10,15 +10,16 @@ #define _LINUX_HUGETLB_VMEMMAP_H #include <linux/hugetlb.h> -#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP -int hugetlb_vmemmap_restore(const struct hstate *h, struct page *head); -void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head); - /* * Reserve one vmemmap page, all vmemmap addresses are mapped to it. See * Documentation/vm/vmemmap_dedup.rst. */ #define HUGETLB_VMEMMAP_RESERVE_SIZE PAGE_SIZE +#define HUGETLB_VMEMMAP_RESERVE_PAGES (HUGETLB_VMEMMAP_RESERVE_SIZE / sizeof(struct page)) + +#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP +int hugetlb_vmemmap_restore(const struct hstate *h, struct page *head); +void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head); static inline unsigned int hugetlb_vmemmap_size(const struct hstate *h) { diff --git a/mm/internal.h b/mm/internal.h index 30cf724ddbce..5a5c923725d3 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -586,6 +586,56 @@ extern long faultin_vma_page_range(struct vm_area_struct *vma, bool write, int *locked); extern bool mlock_future_ok(struct mm_struct *mm, unsigned long flags, unsigned long bytes); + +/* + * NOTE: This function can't tell whether the folio is "fully mapped" in the + * range. + * "fully mapped" means all the pages of folio is associated with the page + * table of range while this function just check whether the folio range is + * within the range [start, end). Funcation caller nees to do page table + * check if it cares about the page table association. + * + * Typical usage (like mlock or madvise) is: + * Caller knows at least 1 page of folio is associated with page table of VMA + * and the range [start, end) is intersect with the VMA range. Caller wants + * to know whether the folio is fully associated with the range. It calls + * this function to check whether the folio is in the range first. Then checks + * the page table to know whether the folio is fully mapped to the range. + */ +static inline bool +folio_within_range(struct folio *folio, struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + pgoff_t pgoff, addr; + unsigned long vma_pglen = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; + + VM_WARN_ON_FOLIO(folio_test_ksm(folio), folio); + if (start > end) + return false; + + if (start < vma->vm_start) + start = vma->vm_start; + + if (end > vma->vm_end) + end = vma->vm_end; + + pgoff = folio_pgoff(folio); + + /* if folio start address is not in vma range */ + if (!in_range(pgoff, vma->vm_pgoff, vma_pglen)) + return false; + + addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + + return !(addr < start || end - addr < folio_size(folio)); +} + +static inline bool +folio_within_vma(struct folio *folio, struct vm_area_struct *vma) +{ + return folio_within_range(folio, vma, vma->vm_start, vma->vm_end); +} + /* * mlock_vma_folio() and munlock_vma_folio(): * should be called with vma's mmap_lock held for read or write, @@ -594,14 +644,10 @@ extern bool mlock_future_ok(struct mm_struct *mm, unsigned long flags, * mlock is usually called at the end of page_add_*_rmap(), munlock at * the end of page_remove_rmap(); but new anon folios are managed by * folio_add_lru_vma() calling mlock_new_folio(). - * - * @compound is used to include pmd mappings of THPs, but filter out - * pte mappings of THPs, which cannot be consistently counted: a pte - * mapping of the THP head cannot be distinguished by the page alone. */ void mlock_folio(struct folio *folio); static inline void mlock_vma_folio(struct folio *folio, - struct vm_area_struct *vma, bool compound) + struct vm_area_struct *vma) { /* * The VM_SPECIAL check here serves two purposes. @@ -611,17 +657,24 @@ static inline void mlock_vma_folio(struct folio *folio, * file->f_op->mmap() is using vm_insert_page(s), when VM_LOCKED may * still be set while VM_SPECIAL bits are added: so ignore it then. */ - if (unlikely((vma->vm_flags & (VM_LOCKED|VM_SPECIAL)) == VM_LOCKED) && - (compound || !folio_test_large(folio))) + if (unlikely((vma->vm_flags & (VM_LOCKED|VM_SPECIAL)) == VM_LOCKED)) mlock_folio(folio); } void munlock_folio(struct folio *folio); static inline void munlock_vma_folio(struct folio *folio, - struct vm_area_struct *vma, bool compound) + struct vm_area_struct *vma) { - if (unlikely(vma->vm_flags & VM_LOCKED) && - (compound || !folio_test_large(folio))) + /* + * munlock if the function is called. Ideally, we should only + * do munlock if any page of folio is unmapped from VMA and + * cause folio not fully mapped to VMA. + * + * But it's not easy to confirm that's the situation. So we + * always munlock the folio and page reclaim will correct it + * if it's wrong. + */ + if (unlikely(vma->vm_flags & VM_LOCKED)) munlock_folio(folio); } @@ -930,7 +983,7 @@ void vunmap_range_noflush(unsigned long start, unsigned long end); void __vunmap_range_noflush(unsigned long start, unsigned long end); -int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, +int numa_migrate_prep(struct folio *folio, struct vm_area_struct *vma, unsigned long addr, int page_nid, int *flags); void free_zone_device_page(struct page *page); @@ -1154,4 +1207,57 @@ struct vma_prepare { struct vm_area_struct *remove; struct vm_area_struct *remove2; }; + +void __meminit __init_single_page(struct page *page, unsigned long pfn, + unsigned long zone, int nid); + +/* shrinker related functions */ +unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, + int priority); + +#ifdef CONFIG_SHRINKER_DEBUG +static inline int shrinker_debugfs_name_alloc(struct shrinker *shrinker, + const char *fmt, va_list ap) +{ + shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); + + return shrinker->name ? 0 : -ENOMEM; +} + +static inline void shrinker_debugfs_name_free(struct shrinker *shrinker) +{ + kfree_const(shrinker->name); + shrinker->name = NULL; +} + +extern int shrinker_debugfs_add(struct shrinker *shrinker); +extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id); +extern void shrinker_debugfs_remove(struct dentry *debugfs_entry, + int debugfs_id); +#else /* CONFIG_SHRINKER_DEBUG */ +static inline int shrinker_debugfs_add(struct shrinker *shrinker) +{ + return 0; +} +static inline int shrinker_debugfs_name_alloc(struct shrinker *shrinker, + const char *fmt, va_list ap) +{ + return 0; +} +static inline void shrinker_debugfs_name_free(struct shrinker *shrinker) +{ +} +static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id) +{ + *debugfs_id = -1; + return NULL; +} +static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, + int debugfs_id) +{ +} +#endif /* CONFIG_SHRINKER_DEBUG */ + #endif /* __MM_INTERNAL_H */ diff --git a/mm/kmsan/core.c b/mm/kmsan/core.c index 3adb4c1d3b19..c19f47af0424 100644 --- a/mm/kmsan/core.c +++ b/mm/kmsan/core.c @@ -83,131 +83,66 @@ depot_stack_handle_t kmsan_save_stack_with_flags(gfp_t flags, /* Copy the metadata following the memmove() behavior. */ void kmsan_internal_memmove_metadata(void *dst, void *src, size_t n) { + depot_stack_handle_t prev_old_origin = 0, prev_new_origin = 0; + int i, iter, step, src_off, dst_off, oiter_src, oiter_dst; depot_stack_handle_t old_origin = 0, new_origin = 0; - int src_slots, dst_slots, i, iter, step, skip_bits; depot_stack_handle_t *origin_src, *origin_dst; - void *shadow_src, *shadow_dst; - u32 *align_shadow_src, shadow; + u8 *shadow_src, *shadow_dst; + u32 *align_shadow_dst; bool backwards; shadow_dst = kmsan_get_metadata(dst, KMSAN_META_SHADOW); if (!shadow_dst) return; KMSAN_WARN_ON(!kmsan_metadata_is_contiguous(dst, n)); + align_shadow_dst = + (u32 *)ALIGN_DOWN((u64)shadow_dst, KMSAN_ORIGIN_SIZE); shadow_src = kmsan_get_metadata(src, KMSAN_META_SHADOW); if (!shadow_src) { - /* - * @src is untracked: zero out destination shadow, ignore the - * origins, we're done. - */ - __memset(shadow_dst, 0, n); + /* @src is untracked: mark @dst as initialized. */ + kmsan_internal_unpoison_memory(dst, n, /*checked*/ false); return; } KMSAN_WARN_ON(!kmsan_metadata_is_contiguous(src, n)); - __memmove(shadow_dst, shadow_src, n); - origin_dst = kmsan_get_metadata(dst, KMSAN_META_ORIGIN); origin_src = kmsan_get_metadata(src, KMSAN_META_ORIGIN); KMSAN_WARN_ON(!origin_dst || !origin_src); - src_slots = (ALIGN((u64)src + n, KMSAN_ORIGIN_SIZE) - - ALIGN_DOWN((u64)src, KMSAN_ORIGIN_SIZE)) / - KMSAN_ORIGIN_SIZE; - dst_slots = (ALIGN((u64)dst + n, KMSAN_ORIGIN_SIZE) - - ALIGN_DOWN((u64)dst, KMSAN_ORIGIN_SIZE)) / - KMSAN_ORIGIN_SIZE; - KMSAN_WARN_ON((src_slots < 1) || (dst_slots < 1)); - KMSAN_WARN_ON((src_slots - dst_slots > 1) || - (dst_slots - src_slots < -1)); backwards = dst > src; - i = backwards ? min(src_slots, dst_slots) - 1 : 0; - iter = backwards ? -1 : 1; - - align_shadow_src = - (u32 *)ALIGN_DOWN((u64)shadow_src, KMSAN_ORIGIN_SIZE); - for (step = 0; step < min(src_slots, dst_slots); step++, i += iter) { - KMSAN_WARN_ON(i < 0); - shadow = align_shadow_src[i]; - if (i == 0) { - /* - * If @src isn't aligned on KMSAN_ORIGIN_SIZE, don't - * look at the first @src % KMSAN_ORIGIN_SIZE bytes - * of the first shadow slot. - */ - skip_bits = ((u64)src % KMSAN_ORIGIN_SIZE) * 8; - shadow = (shadow >> skip_bits) << skip_bits; + step = backwards ? -1 : 1; + iter = backwards ? n - 1 : 0; + src_off = (u64)src % KMSAN_ORIGIN_SIZE; + dst_off = (u64)dst % KMSAN_ORIGIN_SIZE; + + /* Copy shadow bytes one by one, updating the origins if necessary. */ + for (i = 0; i < n; i++, iter += step) { + oiter_src = (iter + src_off) / KMSAN_ORIGIN_SIZE; + oiter_dst = (iter + dst_off) / KMSAN_ORIGIN_SIZE; + if (!shadow_src[iter]) { + shadow_dst[iter] = 0; + if (!align_shadow_dst[oiter_dst]) + origin_dst[oiter_dst] = 0; + continue; } - if (i == src_slots - 1) { - /* - * If @src + n isn't aligned on - * KMSAN_ORIGIN_SIZE, don't look at the last - * (@src + n) % KMSAN_ORIGIN_SIZE bytes of the - * last shadow slot. - */ - skip_bits = (((u64)src + n) % KMSAN_ORIGIN_SIZE) * 8; - shadow = (shadow << skip_bits) >> skip_bits; - } - /* - * Overwrite the origin only if the corresponding - * shadow is nonempty. - */ - if (origin_src[i] && (origin_src[i] != old_origin) && shadow) { - old_origin = origin_src[i]; - new_origin = kmsan_internal_chain_origin(old_origin); + shadow_dst[iter] = shadow_src[iter]; + old_origin = origin_src[oiter_src]; + if (old_origin == prev_old_origin) + new_origin = prev_new_origin; + else { /* * kmsan_internal_chain_origin() may return * NULL, but we don't want to lose the previous * origin value. */ + new_origin = kmsan_internal_chain_origin(old_origin); if (!new_origin) new_origin = old_origin; } - if (shadow) - origin_dst[i] = new_origin; - else - origin_dst[i] = 0; - } - /* - * If dst_slots is greater than src_slots (i.e. - * dst_slots == src_slots + 1), there is an extra origin slot at the - * beginning or end of the destination buffer, for which we take the - * origin from the previous slot. - * This is only done if the part of the source shadow corresponding to - * slot is non-zero. - * - * E.g. if we copy 8 aligned bytes that are marked as uninitialized - * and have origins o111 and o222, to an unaligned buffer with offset 1, - * these two origins are copied to three origin slots, so one of then - * needs to be duplicated, depending on the copy direction (@backwards) - * - * src shadow: |uuuu|uuuu|....| - * src origin: |o111|o222|....| - * - * backwards = 0: - * dst shadow: |.uuu|uuuu|u...| - * dst origin: |....|o111|o222| - fill the empty slot with o111 - * backwards = 1: - * dst shadow: |.uuu|uuuu|u...| - * dst origin: |o111|o222|....| - fill the empty slot with o222 - */ - if (src_slots < dst_slots) { - if (backwards) { - shadow = align_shadow_src[src_slots - 1]; - skip_bits = (((u64)dst + n) % KMSAN_ORIGIN_SIZE) * 8; - shadow = (shadow << skip_bits) >> skip_bits; - if (shadow) - /* src_slots > 0, therefore dst_slots is at least 2 */ - origin_dst[dst_slots - 1] = - origin_dst[dst_slots - 2]; - } else { - shadow = align_shadow_src[0]; - skip_bits = ((u64)dst % KMSAN_ORIGIN_SIZE) * 8; - shadow = (shadow >> skip_bits) << skip_bits; - if (shadow) - origin_dst[0] = origin_dst[1]; - } + origin_dst[oiter_dst] = new_origin; + prev_new_origin = new_origin; + prev_old_origin = old_origin; } } diff --git a/mm/kmsan/kmsan_test.c b/mm/kmsan/kmsan_test.c index 312989aa2865..07d3a3a5a9c5 100644 --- a/mm/kmsan/kmsan_test.c +++ b/mm/kmsan/kmsan_test.c @@ -67,6 +67,17 @@ static bool report_available(void) return READ_ONCE(observed.available); } +/* Reset observed.available, so that the test can trigger another report. */ +static void report_reset(void) +{ + unsigned long flags; + + spin_lock_irqsave(&observed.lock, flags); + WRITE_ONCE(observed.available, false); + observed.ignore = false; + spin_unlock_irqrestore(&observed.lock, flags); +} + /* Information we expect in a report. */ struct expect_report { const char *error_type; /* Error type. */ @@ -407,33 +418,25 @@ static void test_printk(struct kunit *test) KUNIT_EXPECT_TRUE(test, report_matches(&expect)); } -/* - * Prevent the compiler from optimizing @var away. Without this, Clang may - * notice that @var is uninitialized and drop memcpy() calls that use it. - * - * There is OPTIMIZER_HIDE_VAR() in linux/compier.h that we cannot use here, - * because it is implemented as inline assembly receiving @var as a parameter - * and will enforce a KMSAN check. Same is true for e.g. barrier_data(var). - */ -#define DO_NOT_OPTIMIZE(var) barrier() +/* Prevent the compiler from inlining a memcpy() call. */ +static noinline void *memcpy_noinline(volatile void *dst, + const volatile void *src, size_t size) +{ + return memcpy((void *)dst, (const void *)src, size); +} -/* - * Test case: ensure that memcpy() correctly copies initialized values. - * Also serves as a regression test to ensure DO_NOT_OPTIMIZE() does not cause - * extra checks. - */ +/* Test case: ensure that memcpy() correctly copies initialized values. */ static void test_init_memcpy(struct kunit *test) { EXPECTATION_NO_REPORT(expect); - volatile int src; - volatile int dst = 0; + volatile long long src; + volatile long long dst = 0; - DO_NOT_OPTIMIZE(src); src = 1; kunit_info( test, "memcpy()ing aligned initialized src to aligned dst (no reports)\n"); - memcpy((void *)&dst, (void *)&src, sizeof(src)); + memcpy_noinline((void *)&dst, (void *)&src, sizeof(src)); kmsan_check_memory((void *)&dst, sizeof(dst)); KUNIT_EXPECT_TRUE(test, report_matches(&expect)); } @@ -451,8 +454,7 @@ static void test_memcpy_aligned_to_aligned(struct kunit *test) kunit_info( test, "memcpy()ing aligned uninit src to aligned dst (UMR report)\n"); - DO_NOT_OPTIMIZE(uninit_src); - memcpy((void *)&dst, (void *)&uninit_src, sizeof(uninit_src)); + memcpy_noinline((void *)&dst, (void *)&uninit_src, sizeof(uninit_src)); kmsan_check_memory((void *)&dst, sizeof(dst)); KUNIT_EXPECT_TRUE(test, report_matches(&expect)); } @@ -463,7 +465,7 @@ static void test_memcpy_aligned_to_aligned(struct kunit *test) * * Copying aligned 4-byte value to an unaligned one leads to touching two * aligned 4-byte values. This test case checks that KMSAN correctly reports an - * error on the first of the two values. + * error on the mentioned two values. */ static void test_memcpy_aligned_to_unaligned(struct kunit *test) { @@ -474,33 +476,65 @@ static void test_memcpy_aligned_to_unaligned(struct kunit *test) kunit_info( test, "memcpy()ing aligned uninit src to unaligned dst (UMR report)\n"); - DO_NOT_OPTIMIZE(uninit_src); - memcpy((void *)&dst[1], (void *)&uninit_src, sizeof(uninit_src)); + kmsan_check_memory((void *)&uninit_src, sizeof(uninit_src)); + memcpy_noinline((void *)&dst[1], (void *)&uninit_src, + sizeof(uninit_src)); kmsan_check_memory((void *)dst, 4); KUNIT_EXPECT_TRUE(test, report_matches(&expect)); + report_reset(); + kmsan_check_memory((void *)&dst[4], sizeof(uninit_src)); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); } /* - * Test case: ensure that memcpy() correctly copies uninitialized values between - * aligned `src` and unaligned `dst`. + * Test case: ensure that origin slots do not accidentally get overwritten with + * zeroes during memcpy(). * - * Copying aligned 4-byte value to an unaligned one leads to touching two - * aligned 4-byte values. This test case checks that KMSAN correctly reports an - * error on the second of the two values. + * Previously, when copying memory from an aligned buffer to an unaligned one, + * if there were zero origins corresponding to zero shadow values in the source + * buffer, they could have ended up being copied to nonzero shadow values in the + * destination buffer: + * + * memcpy(0xffff888080a00000, 0xffff888080900002, 8) + * + * src (0xffff888080900002): ..xx .... xx.. + * src origins: o111 0000 o222 + * dst (0xffff888080a00000): xx.. ..xx + * dst origins: o111 0000 + * (or 0000 o222) + * + * (here . stands for an initialized byte, and x for an uninitialized one. + * + * Ensure that this does not happen anymore, and for both destination bytes + * the origin is nonzero (i.e. KMSAN reports an error). */ -static void test_memcpy_aligned_to_unaligned2(struct kunit *test) +static void test_memcpy_initialized_gap(struct kunit *test) { - EXPECTATION_UNINIT_VALUE_FN(expect, - "test_memcpy_aligned_to_unaligned2"); - volatile int uninit_src; + EXPECTATION_UNINIT_VALUE_FN(expect, "test_memcpy_initialized_gap"); + volatile char uninit_src[12]; volatile char dst[8] = { 0 }; kunit_info( test, - "memcpy()ing aligned uninit src to unaligned dst - part 2 (UMR report)\n"); - DO_NOT_OPTIMIZE(uninit_src); - memcpy((void *)&dst[1], (void *)&uninit_src, sizeof(uninit_src)); - kmsan_check_memory((void *)&dst[4], sizeof(uninit_src)); + "unaligned 4-byte initialized value gets a nonzero origin after memcpy() - (2 UMR reports)\n"); + + uninit_src[0] = 42; + uninit_src[1] = 42; + uninit_src[4] = 42; + uninit_src[5] = 42; + uninit_src[6] = 42; + uninit_src[7] = 42; + uninit_src[10] = 42; + uninit_src[11] = 42; + memcpy_noinline((void *)&dst[0], (void *)&uninit_src[2], 8); + + kmsan_check_memory((void *)&dst[0], 4); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); + report_reset(); + kmsan_check_memory((void *)&dst[2], 4); + KUNIT_EXPECT_FALSE(test, report_matches(&expect)); + report_reset(); + kmsan_check_memory((void *)&dst[4], 4); KUNIT_EXPECT_TRUE(test, report_matches(&expect)); } @@ -513,7 +547,6 @@ static void test_memcpy_aligned_to_unaligned2(struct kunit *test) \ kunit_info(test, \ "memset" #size "() should initialize memory\n"); \ - DO_NOT_OPTIMIZE(uninit); \ memset##size((uint##size##_t *)&uninit, 0, 1); \ kmsan_check_memory((void *)&uninit, sizeof(uninit)); \ KUNIT_EXPECT_TRUE(test, report_matches(&expect)); \ @@ -598,7 +631,7 @@ static struct kunit_case kmsan_test_cases[] = { KUNIT_CASE(test_init_memcpy), KUNIT_CASE(test_memcpy_aligned_to_aligned), KUNIT_CASE(test_memcpy_aligned_to_unaligned), - KUNIT_CASE(test_memcpy_aligned_to_unaligned2), + KUNIT_CASE(test_memcpy_initialized_gap), KUNIT_CASE(test_memset16), KUNIT_CASE(test_memset32), KUNIT_CASE(test_memset64), @@ -56,6 +56,8 @@ #define DO_NUMA(x) do { } while (0) #endif +typedef u8 rmap_age_t; + /** * DOC: Overview * @@ -193,6 +195,8 @@ struct ksm_stable_node { * @node: rb node of this rmap_item in the unstable tree * @head: pointer to stable_node heading this list in the stable tree * @hlist: link into hlist of rmap_items hanging off that stable_node + * @age: number of scan iterations since creation + * @remaining_skips: how many scans to skip */ struct ksm_rmap_item { struct ksm_rmap_item *rmap_list; @@ -205,6 +209,8 @@ struct ksm_rmap_item { struct mm_struct *mm; unsigned long address; /* + low bits used for flags below */ unsigned int oldchecksum; /* when unstable */ + rmap_age_t age; + rmap_age_t remaining_skips; union { struct rb_node node; /* when node of unstable tree */ struct { /* when listed from stable tree */ @@ -281,9 +287,16 @@ static unsigned int zero_checksum __read_mostly; /* Whether to merge empty (zeroed) pages with actual zero pages */ static bool ksm_use_zero_pages __read_mostly; +/* Skip pages that couldn't be de-duplicated previously */ +/* Default to true at least temporarily, for testing */ +static bool ksm_smart_scan = true; + /* The number of zero pages which is placed by KSM */ unsigned long ksm_zero_pages; +/* The number of pages that have been skipped due to "smart scanning" */ +static unsigned long ksm_pages_skipped; + #ifdef CONFIG_NUMA /* Zeroed when merging across nodes is not allowed */ static unsigned int ksm_merge_across_nodes = 1; @@ -2305,6 +2318,74 @@ static struct ksm_rmap_item *get_next_rmap_item(struct ksm_mm_slot *mm_slot, return rmap_item; } +/* + * Calculate skip age for the ksm page age. The age determines how often + * de-duplicating has already been tried unsuccessfully. If the age is + * smaller, the scanning of this page is skipped for less scans. + * + * @age: rmap_item age of page + */ +static unsigned int skip_age(rmap_age_t age) +{ + if (age <= 3) + return 1; + if (age <= 5) + return 2; + if (age <= 8) + return 4; + + return 8; +} + +/* + * Determines if a page should be skipped for the current scan. + * + * @page: page to check + * @rmap_item: associated rmap_item of page + */ +static bool should_skip_rmap_item(struct page *page, + struct ksm_rmap_item *rmap_item) +{ + rmap_age_t age; + + if (!ksm_smart_scan) + return false; + + /* + * Never skip pages that are already KSM; pages cmp_and_merge_page() + * will essentially ignore them, but we still have to process them + * properly. + */ + if (PageKsm(page)) + return false; + + age = rmap_item->age; + if (age != U8_MAX) + rmap_item->age++; + + /* + * Smaller ages are not skipped, they need to get a chance to go + * through the different phases of the KSM merging. + */ + if (age < 3) + return false; + + /* + * Are we still allowed to skip? If not, then don't skip it + * and determine how much more often we are allowed to skip next. + */ + if (!rmap_item->remaining_skips) { + rmap_item->remaining_skips = skip_age(age); + return false; + } + + /* Skip this page */ + ksm_pages_skipped++; + rmap_item->remaining_skips--; + remove_rmap_item_from_tree(rmap_item); + return true; +} + static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page) { struct mm_struct *mm; @@ -2409,6 +2490,10 @@ next_mm: if (rmap_item) { ksm_scan.rmap_list = &rmap_item->rmap_list; + + if (should_skip_rmap_item(*page, rmap_item)) + goto next_page; + ksm_scan.address += PAGE_SIZE; } else put_page(*page); @@ -3383,6 +3468,13 @@ static ssize_t pages_volatile_show(struct kobject *kobj, } KSM_ATTR_RO(pages_volatile); +static ssize_t pages_skipped_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%lu\n", ksm_pages_skipped); +} +KSM_ATTR_RO(pages_skipped); + static ssize_t ksm_zero_pages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -3449,6 +3541,28 @@ static ssize_t full_scans_show(struct kobject *kobj, } KSM_ATTR_RO(full_scans); +static ssize_t smart_scan_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%u\n", ksm_smart_scan); +} + +static ssize_t smart_scan_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + bool value; + + err = kstrtobool(buf, &value); + if (err) + return -EINVAL; + + ksm_smart_scan = value; + return count; +} +KSM_ATTR(smart_scan); + static struct attribute *ksm_attrs[] = { &sleep_millisecs_attr.attr, &pages_to_scan_attr.attr, @@ -3458,6 +3572,7 @@ static struct attribute *ksm_attrs[] = { &pages_sharing_attr.attr, &pages_unshared_attr.attr, &pages_volatile_attr.attr, + &pages_skipped_attr.attr, &ksm_zero_pages_attr.attr, &full_scans_attr.attr, #ifdef CONFIG_NUMA @@ -3469,6 +3584,7 @@ static struct attribute *ksm_attrs[] = { &stable_node_chains_prune_millisecs_attr.attr, &use_zero_pages_attr.attr, &general_profit_attr.attr, + &smart_scan_attr.attr, NULL, }; diff --git a/mm/madvise.c b/mm/madvise.c index 4dded5d27e7e..59e8860c86af 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -746,11 +746,8 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, folio_mark_lazyfree(folio); } - if (nr_swap) { - if (current->mm == mm) - sync_mm_rss(mm); + if (nr_swap) add_mm_counter(mm, MM_SWAPENTS, nr_swap); - } if (start_pte) { arch_leave_lazy_mmu_mode(); pte_unmap_unlock(start_pte, ptl); diff --git a/mm/memblock.c b/mm/memblock.c index 913b2520a9a0..fd492e5bbdbc 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -892,6 +892,7 @@ int __init_memblock memblock_physmem_add(phys_addr_t base, phys_addr_t size) /** * memblock_setclr_flag - set or clear flag for a memory region + * @type: memblock type to set/clear flag for * @base: base address of the region * @size: size of the region * @set: set or clear the flag @@ -901,10 +902,9 @@ int __init_memblock memblock_physmem_add(phys_addr_t base, phys_addr_t size) * * Return: 0 on success, -errno on failure. */ -static int __init_memblock memblock_setclr_flag(phys_addr_t base, - phys_addr_t size, int set, int flag) +static int __init_memblock memblock_setclr_flag(struct memblock_type *type, + phys_addr_t base, phys_addr_t size, int set, int flag) { - struct memblock_type *type = &memblock.memory; int i, ret, start_rgn, end_rgn; ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); @@ -933,7 +933,7 @@ static int __init_memblock memblock_setclr_flag(phys_addr_t base, */ int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size) { - return memblock_setclr_flag(base, size, 1, MEMBLOCK_HOTPLUG); + return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_HOTPLUG); } /** @@ -945,7 +945,7 @@ int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size) */ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size) { - return memblock_setclr_flag(base, size, 0, MEMBLOCK_HOTPLUG); + return memblock_setclr_flag(&memblock.memory, base, size, 0, MEMBLOCK_HOTPLUG); } /** @@ -962,7 +962,7 @@ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size) system_has_some_mirror = true; - return memblock_setclr_flag(base, size, 1, MEMBLOCK_MIRROR); + return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_MIRROR); } /** @@ -982,7 +982,7 @@ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size) */ int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size) { - return memblock_setclr_flag(base, size, 1, MEMBLOCK_NOMAP); + return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_NOMAP); } /** @@ -994,7 +994,25 @@ int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size) */ int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size) { - return memblock_setclr_flag(base, size, 0, MEMBLOCK_NOMAP); + return memblock_setclr_flag(&memblock.memory, base, size, 0, MEMBLOCK_NOMAP); +} + +/** + * memblock_reserved_mark_noinit - Mark a reserved memory region with flag + * MEMBLOCK_RSRV_NOINIT which results in the struct pages not being initialized + * for this region. + * @base: the base phys addr of the region + * @size: the size of the region + * + * struct pages will not be initialized for reserved memory regions marked with + * %MEMBLOCK_RSRV_NOINIT. + * + * Return: 0 on success, -errno on failure. + */ +int __init_memblock memblock_reserved_mark_noinit(phys_addr_t base, phys_addr_t size) +{ + return memblock_setclr_flag(&memblock.reserved, base, size, 1, + MEMBLOCK_RSRV_NOINIT); } static bool should_skip_region(struct memblock_type *type, @@ -2113,13 +2131,18 @@ static void __init memmap_init_reserved_pages(void) memblock_set_node(start, end, &memblock.reserved, nid); } - /* initialize struct pages for the reserved regions */ + /* + * initialize struct pages for reserved regions that don't have + * the MEMBLOCK_RSRV_NOINIT flag set + */ for_each_reserved_mem_region(region) { - nid = memblock_get_region_node(region); - start = region->base; - end = start + region->size; + if (!memblock_is_reserved_noinit(region)) { + nid = memblock_get_region_node(region); + start = region->base; + end = start + region->size; - reserve_bootmem_region(start, end, nid); + reserve_bootmem_region(start, end, nid); + } } } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5b009b233ab8..8713bc796c77 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -704,6 +704,8 @@ static const unsigned int memcg_vm_event_stat[] = { #ifdef CONFIG_TRANSPARENT_HUGEPAGE THP_FAULT_ALLOC, THP_COLLAPSE_ALLOC, + THP_SWPOUT, + THP_SWPOUT_FALLBACK, #endif }; @@ -4066,7 +4068,10 @@ static const unsigned int memcg1_stats[] = { NR_WRITEBACK, WORKINGSET_REFAULT_ANON, WORKINGSET_REFAULT_FILE, +#ifdef CONFIG_SWAP MEMCG_SWAP, + NR_SWAPCACHE, +#endif }; static const char *const memcg1_stat_names[] = { @@ -4081,7 +4086,10 @@ static const char *const memcg1_stat_names[] = { "writeback", "workingset_refault_anon", "workingset_refault_file", +#ifdef CONFIG_SWAP "swap", + "swapcached", +#endif }; /* Universal VM events cgroup1 shows, original sort order */ @@ -4105,8 +4113,6 @@ static void memcg1_stat_format(struct mem_cgroup *memcg, struct seq_buf *s) for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) { unsigned long nr; - if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account()) - continue; nr = memcg_page_state_local(memcg, memcg1_stats[i]); seq_buf_printf(s, "%s %lu\n", memcg1_stat_names[i], nr * memcg_page_state_unit(memcg1_stats[i])); @@ -4129,15 +4135,12 @@ static void memcg1_stat_format(struct mem_cgroup *memcg, struct seq_buf *s) } seq_buf_printf(s, "hierarchical_memory_limit %llu\n", (u64)memory * PAGE_SIZE); - if (do_memsw_account()) - seq_buf_printf(s, "hierarchical_memsw_limit %llu\n", - (u64)memsw * PAGE_SIZE); + seq_buf_printf(s, "hierarchical_memsw_limit %llu\n", + (u64)memsw * PAGE_SIZE); for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) { unsigned long nr; - if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account()) - continue; nr = memcg_page_state(memcg, memcg1_stats[i]); seq_buf_printf(s, "total_%s %llu\n", memcg1_stat_names[i], (u64)nr * memcg_page_state_unit(memcg1_stats[i])); diff --git a/mm/memfd.c b/mm/memfd.c index 2dba2cb6f0d0..d3a1ba4208c9 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -315,12 +315,6 @@ SYSCALL_DEFINE2(memfd_create, if ((flags & MFD_EXEC) && (flags & MFD_NOEXEC_SEAL)) return -EINVAL; - if (!(flags & (MFD_EXEC | MFD_NOEXEC_SEAL))) { - pr_warn_once( - "%s[%d]: memfd_create() called without MFD_EXEC or MFD_NOEXEC_SEAL set\n", - current->comm, task_pid_nr(current)); - } - error = check_sysctl_memfd_noexec(&flags); if (error < 0) return error; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 4d6e43c88489..660c21859118 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1713,32 +1713,35 @@ static void unmap_and_kill(struct list_head *to_kill, unsigned long pfn, kill_procs(to_kill, flags & MF_MUST_KILL, false, pfn, flags); } +/* + * Only dev_pagemap pages get here, such as fsdax when the filesystem + * either do not claim or fails to claim a hwpoison event, or devdax. + * The fsdax pages are initialized per base page, and the devdax pages + * could be initialized either as base pages, or as compound pages with + * vmemmap optimization enabled. Devdax is simplistic in its dealing with + * hwpoison, such that, if a subpage of a compound page is poisoned, + * simply mark the compound head page is by far sufficient. + */ static int mf_generic_kill_procs(unsigned long long pfn, int flags, struct dev_pagemap *pgmap) { - struct page *page = pfn_to_page(pfn); + struct folio *folio = pfn_folio(pfn); LIST_HEAD(to_kill); dax_entry_t cookie; int rc = 0; /* - * Pages instantiated by device-dax (not filesystem-dax) - * may be compound pages. - */ - page = compound_head(page); - - /* * Prevent the inode from being freed while we are interrogating * the address_space, typically this would be handled by * lock_page(), but dax pages do not use the page lock. This * also prevents changes to the mapping of this pfn until * poison signaling is complete. */ - cookie = dax_lock_page(page); + cookie = dax_lock_folio(folio); if (!cookie) return -EBUSY; - if (hwpoison_filter(page)) { + if (hwpoison_filter(&folio->page)) { rc = -EOPNOTSUPP; goto unlock; } @@ -1760,7 +1763,7 @@ static int mf_generic_kill_procs(unsigned long long pfn, int flags, * Use this flag as an indication that the dax page has been * remapped UC to prevent speculative consumption of poison. */ - SetPageHWPoison(page); + SetPageHWPoison(&folio->page); /* * Unlike System-RAM there is no possibility to swap in a @@ -1769,11 +1772,11 @@ static int mf_generic_kill_procs(unsigned long long pfn, int flags, * SIGBUS (i.e. MF_MUST_KILL) */ flags |= MF_ACTION_REQUIRED | MF_MUST_KILL; - collect_procs(page, &to_kill, true); + collect_procs(&folio->page, &to_kill, true); - unmap_and_kill(&to_kill, pfn, page->mapping, page->index, flags); + unmap_and_kill(&to_kill, pfn, folio->mapping, folio->index, flags); unlock: - dax_unlock_page(page, cookie); + dax_unlock_folio(folio, cookie); return rc; } diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c index 37a4f59d9585..8d5291add2bc 100644 --- a/mm/memory-tiers.c +++ b/mm/memory-tiers.c @@ -5,6 +5,7 @@ #include <linux/kobject.h> #include <linux/memory.h> #include <linux/memory-tiers.h> +#include <linux/notifier.h> #include "internal.h" @@ -36,7 +37,7 @@ struct node_memory_type_map { static DEFINE_MUTEX(memory_tier_lock); static LIST_HEAD(memory_tiers); static struct node_memory_type_map node_memory_types[MAX_NUMNODES]; -static struct memory_dev_type *default_dram_type; +struct memory_dev_type *default_dram_type; static struct bus_type memory_tier_subsys = { .name = "memory_tiering", @@ -105,6 +106,13 @@ static int top_tier_adistance; static struct demotion_nodes *node_demotion __read_mostly; #endif /* CONFIG_MIGRATION */ +static BLOCKING_NOTIFIER_HEAD(mt_adistance_algorithms); + +static bool default_dram_perf_error; +static struct node_hmem_attrs default_dram_perf; +static int default_dram_perf_ref_nid = NUMA_NO_NODE; +static const char *default_dram_perf_ref_source; + static inline struct memory_tier *to_memory_tier(struct device *device) { return container_of(device, struct memory_tier, dev); @@ -115,7 +123,7 @@ static __always_inline nodemask_t get_memtier_nodemask(struct memory_tier *memti nodemask_t nodes = NODE_MASK_NONE; struct memory_dev_type *memtype; - list_for_each_entry(memtype, &memtier->memory_types, tier_sibiling) + list_for_each_entry(memtype, &memtier->memory_types, tier_sibling) nodes_or(nodes, nodes, memtype->nodes); return nodes; @@ -174,7 +182,7 @@ static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memty * If the memtype is already part of a memory tier, * just return that. */ - if (!list_empty(&memtype->tier_sibiling)) { + if (!list_empty(&memtype->tier_sibling)) { list_for_each_entry(memtier, &memory_tiers, list) { if (adistance == memtier->adistance_start) return memtier; @@ -218,7 +226,7 @@ static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memty memtier = new_memtier; link_memtype: - list_add(&memtype->tier_sibiling, &memtier->memory_types); + list_add(&memtype->tier_sibling, &memtier->memory_types); return memtier; } @@ -527,7 +535,7 @@ static bool clear_node_memory_tier(int node) memtype = node_memory_types[node].memtype; node_clear(node, memtype->nodes); if (nodes_empty(memtype->nodes)) { - list_del_init(&memtype->tier_sibiling); + list_del_init(&memtype->tier_sibling); if (list_empty(&memtier->memory_types)) destroy_memory_tier(memtier); } @@ -553,7 +561,7 @@ struct memory_dev_type *alloc_memory_type(int adistance) return ERR_PTR(-ENOMEM); memtype->adistance = adistance; - INIT_LIST_HEAD(&memtype->tier_sibiling); + INIT_LIST_HEAD(&memtype->tier_sibling); memtype->nodes = NODE_MASK_NONE; kref_init(&memtype->kref); return memtype; @@ -578,13 +586,14 @@ EXPORT_SYMBOL_GPL(init_node_memory_type); void clear_node_memory_type(int node, struct memory_dev_type *memtype) { mutex_lock(&memory_tier_lock); - if (node_memory_types[node].memtype == memtype) + if (node_memory_types[node].memtype == memtype || !memtype) node_memory_types[node].map_count--; /* * If we umapped all the attached devices to this node, * clear the node memory type. */ if (!node_memory_types[node].map_count) { + memtype = node_memory_types[node].memtype; node_memory_types[node].memtype = NULL; put_memory_type(memtype); } @@ -592,6 +601,158 @@ void clear_node_memory_type(int node, struct memory_dev_type *memtype) } EXPORT_SYMBOL_GPL(clear_node_memory_type); +static void dump_hmem_attrs(struct node_hmem_attrs *attrs, const char *prefix) +{ + pr_info( +"%sread_latency: %u, write_latency: %u, read_bandwidth: %u, write_bandwidth: %u\n", + prefix, attrs->read_latency, attrs->write_latency, + attrs->read_bandwidth, attrs->write_bandwidth); +} + +int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf, + const char *source) +{ + int rc = 0; + + mutex_lock(&memory_tier_lock); + if (default_dram_perf_error) { + rc = -EIO; + goto out; + } + + if (perf->read_latency + perf->write_latency == 0 || + perf->read_bandwidth + perf->write_bandwidth == 0) { + rc = -EINVAL; + goto out; + } + + if (default_dram_perf_ref_nid == NUMA_NO_NODE) { + default_dram_perf = *perf; + default_dram_perf_ref_nid = nid; + default_dram_perf_ref_source = kstrdup(source, GFP_KERNEL); + goto out; + } + + /* + * The performance of all default DRAM nodes is expected to be + * same (that is, the variation is less than 10%). And it + * will be used as base to calculate the abstract distance of + * other memory nodes. + */ + if (abs(perf->read_latency - default_dram_perf.read_latency) * 10 > + default_dram_perf.read_latency || + abs(perf->write_latency - default_dram_perf.write_latency) * 10 > + default_dram_perf.write_latency || + abs(perf->read_bandwidth - default_dram_perf.read_bandwidth) * 10 > + default_dram_perf.read_bandwidth || + abs(perf->write_bandwidth - default_dram_perf.write_bandwidth) * 10 > + default_dram_perf.write_bandwidth) { + pr_info( +"memory-tiers: the performance of DRAM node %d mismatches that of the reference\n" +"DRAM node %d.\n", nid, default_dram_perf_ref_nid); + pr_info(" performance of reference DRAM node %d:\n", + default_dram_perf_ref_nid); + dump_hmem_attrs(&default_dram_perf, " "); + pr_info(" performance of DRAM node %d:\n", nid); + dump_hmem_attrs(perf, " "); + pr_info( +" disable default DRAM node performance based abstract distance algorithm.\n"); + default_dram_perf_error = true; + rc = -EINVAL; + } + +out: + mutex_unlock(&memory_tier_lock); + return rc; +} + +int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist) +{ + if (default_dram_perf_error) + return -EIO; + + if (default_dram_perf_ref_nid == NUMA_NO_NODE) + return -ENOENT; + + if (perf->read_latency + perf->write_latency == 0 || + perf->read_bandwidth + perf->write_bandwidth == 0) + return -EINVAL; + + mutex_lock(&memory_tier_lock); + /* + * The abstract distance of a memory node is in direct proportion to + * its memory latency (read + write) and inversely proportional to its + * memory bandwidth (read + write). The abstract distance, memory + * latency, and memory bandwidth of the default DRAM nodes are used as + * the base. + */ + *adist = MEMTIER_ADISTANCE_DRAM * + (perf->read_latency + perf->write_latency) / + (default_dram_perf.read_latency + default_dram_perf.write_latency) * + (default_dram_perf.read_bandwidth + default_dram_perf.write_bandwidth) / + (perf->read_bandwidth + perf->write_bandwidth); + mutex_unlock(&memory_tier_lock); + + return 0; +} +EXPORT_SYMBOL_GPL(mt_perf_to_adistance); + +/** + * register_mt_adistance_algorithm() - Register memory tiering abstract distance algorithm + * @nb: The notifier block which describe the algorithm + * + * Return: 0 on success, errno on error. + * + * Every memory tiering abstract distance algorithm provider needs to + * register the algorithm with register_mt_adistance_algorithm(). To + * calculate the abstract distance for a specified memory node, the + * notifier function will be called unless some high priority + * algorithm has provided result. The prototype of the notifier + * function is as follows, + * + * int (*algorithm_notifier)(struct notifier_block *nb, + * unsigned long nid, void *data); + * + * Where "nid" specifies the memory node, "data" is the pointer to the + * returned abstract distance (that is, "int *adist"). If the + * algorithm provides the result, NOTIFY_STOP should be returned. + * Otherwise, return_value & %NOTIFY_STOP_MASK == 0 to allow the next + * algorithm in the chain to provide the result. + */ +int register_mt_adistance_algorithm(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&mt_adistance_algorithms, nb); +} +EXPORT_SYMBOL_GPL(register_mt_adistance_algorithm); + +/** + * unregister_mt_adistance_algorithm() - Unregister memory tiering abstract distance algorithm + * @nb: the notifier block which describe the algorithm + * + * Return: 0 on success, errno on error. + */ +int unregister_mt_adistance_algorithm(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&mt_adistance_algorithms, nb); +} +EXPORT_SYMBOL_GPL(unregister_mt_adistance_algorithm); + +/** + * mt_calc_adistance() - Calculate abstract distance with registered algorithms + * @node: the node to calculate abstract distance for + * @adist: the returned abstract distance + * + * Return: if return_value & %NOTIFY_STOP_MASK != 0, then some + * abstract distance algorithm provides the result, and return it via + * @adist. Otherwise, no algorithm can provide the result and @adist + * will be kept as it is. + */ +int mt_calc_adistance(int node, int *adist) +{ + return blocking_notifier_call_chain(&mt_adistance_algorithms, node, adist); +} +EXPORT_SYMBOL_GPL(mt_calc_adistance); + static int __meminit memtier_hotplug_callback(struct notifier_block *self, unsigned long action, void *_arg) { diff --git a/mm/memory.c b/mm/memory.c index 517221f01303..2d209bc4d18c 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -471,8 +471,6 @@ static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss) { int i; - if (current->mm == mm) - sync_mm_rss(mm); for (i = 0; i < NR_MM_COUNTERS; i++) if (rss[i]) add_mm_counter(mm, i, rss[i]); @@ -691,6 +689,16 @@ struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, out: return pfn_to_page(pfn); } + +struct folio *vm_normal_folio_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t pmd) +{ + struct page *page = vm_normal_page_pmd(vma, addr, pmd); + + if (page) + return page_folio(page); + return NULL; +} #endif static void restore_exclusive_pte(struct vm_area_struct *vma, @@ -4719,10 +4727,10 @@ static vm_fault_t do_fault(struct vm_fault *vmf) return ret; } -int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, +int numa_migrate_prep(struct folio *folio, struct vm_area_struct *vma, unsigned long addr, int page_nid, int *flags) { - get_page(page); + folio_get(folio); /* Record the current PID acceesing VMA */ vma_set_access_pid_bit(vma); @@ -4733,14 +4741,14 @@ int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, *flags |= TNF_FAULT_LOCAL; } - return mpol_misplaced(page, vma, addr); + return mpol_misplaced(folio, vma, addr); } static vm_fault_t do_numa_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; - struct page *page = NULL; - int page_nid = NUMA_NO_NODE; + struct folio *folio = NULL; + int nid = NUMA_NO_NODE; bool writable = false; int last_cpupid; int target_nid; @@ -4771,12 +4779,12 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) can_change_pte_writable(vma, vmf->address, pte)) writable = true; - page = vm_normal_page(vma, vmf->address, pte); - if (!page || is_zone_device_page(page)) + folio = vm_normal_folio(vma, vmf->address, pte); + if (!folio || folio_is_zone_device(folio)) goto out_map; /* TODO: handle PTE-mapped THP */ - if (PageCompound(page)) + if (folio_test_large(folio)) goto out_map; /* @@ -4791,34 +4799,33 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) flags |= TNF_NO_GROUP; /* - * Flag if the page is shared between multiple address spaces. This + * Flag if the folio is shared between multiple address spaces. This * is later used when determining whether to group tasks together */ - if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED)) + if (folio_estimated_sharers(folio) > 1 && (vma->vm_flags & VM_SHARED)) flags |= TNF_SHARED; - page_nid = page_to_nid(page); + nid = folio_nid(folio); /* * For memory tiering mode, cpupid of slow memory page is used * to record page access time. So use default value. */ if ((sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) && - !node_is_toptier(page_nid)) + !node_is_toptier(nid)) last_cpupid = (-1 & LAST_CPUPID_MASK); else - last_cpupid = page_cpupid_last(page); - target_nid = numa_migrate_prep(page, vma, vmf->address, page_nid, - &flags); + last_cpupid = page_cpupid_last(&folio->page); + target_nid = numa_migrate_prep(folio, vma, vmf->address, nid, &flags); if (target_nid == NUMA_NO_NODE) { - put_page(page); + folio_put(folio); goto out_map; } pte_unmap_unlock(vmf->pte, vmf->ptl); writable = false; /* Migrate to the requested node */ - if (migrate_misplaced_page(page, vma, target_nid)) { - page_nid = target_nid; + if (migrate_misplaced_folio(folio, vma, target_nid)) { + nid = target_nid; flags |= TNF_MIGRATED; } else { flags |= TNF_MIGRATE_FAIL; @@ -4834,8 +4841,8 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) } out: - if (page_nid != NUMA_NO_NODE) - task_numa_fault(last_cpupid, page_nid, 1, flags); + if (nid != NUMA_NO_NODE) + task_numa_fault(last_cpupid, nid, 1, flags); return 0; out_map: /* diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 1b03f4ec6fd2..3b301c4023ff 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1689,7 +1689,7 @@ static int scan_movable_pages(unsigned long start, unsigned long end, */ if (HPageMigratable(head)) goto found; - skip = compound_nr(head) - (page - head); + skip = compound_nr(head) - (pfn - page_to_pfn(head)); pfn += skip - 1; } return -ENOENT; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 29ebf1e7898c..38a47fa33ef4 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2566,24 +2566,25 @@ static void sp_free(struct sp_node *n) } /** - * mpol_misplaced - check whether current page node is valid in policy + * mpol_misplaced - check whether current folio node is valid in policy * - * @page: page to be checked - * @vma: vm area where page mapped - * @addr: virtual address where page mapped + * @folio: folio to be checked + * @vma: vm area where folio mapped + * @addr: virtual address in @vma for shared policy lookup and interleave policy * - * Lookup current policy node id for vma,addr and "compare to" page's + * Lookup current policy node id for vma,addr and "compare to" folio's * node id. Policy determination "mimics" alloc_page_vma(). * Called from fault path where we know the vma and faulting address. * * Return: NUMA_NO_NODE if the page is in a node that is valid for this - * policy, or a suitable node ID to allocate a replacement page from. + * policy, or a suitable node ID to allocate a replacement folio from. */ -int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long addr) +int mpol_misplaced(struct folio *folio, struct vm_area_struct *vma, + unsigned long addr) { struct mempolicy *pol; struct zoneref *z; - int curnid = page_to_nid(page); + int curnid = folio_nid(folio); unsigned long pgoff; int thiscpu = raw_smp_processor_id(); int thisnid = cpu_to_node(thiscpu); @@ -2639,11 +2640,12 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long BUG(); } - /* Migrate the page towards the node whose CPU is referencing it */ + /* Migrate the folio towards the node whose CPU is referencing it */ if (pol->flags & MPOL_F_MORON) { polnid = thisnid; - if (!should_numa_migrate_memory(current, page, curnid, thiscpu)) + if (!should_numa_migrate_memory(current, folio, curnid, + thiscpu)) goto out; } diff --git a/mm/migrate.c b/mm/migrate.c index 06086dc9da28..482f478ea3fe 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -157,8 +157,8 @@ void putback_movable_pages(struct list_head *l) list_del(&folio->lru); /* * We isolated non-lru movable folio so here we can use - * __PageMovable because LRU folio's mapping cannot have - * PAGE_MAPPING_MOVABLE. + * __folio_test_movable because LRU folio's mapping cannot + * have PAGE_MAPPING_MOVABLE. */ if (unlikely(__folio_test_movable(folio))) { VM_BUG_ON_FOLIO(!folio_test_isolated(folio), folio); @@ -249,7 +249,7 @@ static bool remove_migration_pte(struct folio *folio, pte = arch_make_huge_pte(pte, shift, vma->vm_flags); if (folio_test_anon(folio)) - hugepage_add_anon_rmap(new, vma, pvmw.address, + hugepage_add_anon_rmap(folio, vma, pvmw.address, rmap_flags); else page_dup_file_rmap(new, true); @@ -524,7 +524,7 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, int expected_count; xas_lock_irq(&xas); - expected_count = 2 + folio_has_private(src); + expected_count = folio_expected_refs(mapping, src); if (!folio_ref_freeze(src, expected_count)) { xas_unlock_irq(&xas); return -EAGAIN; @@ -533,11 +533,11 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, dst->index = src->index; dst->mapping = src->mapping; - folio_get(dst); + folio_ref_add(dst, folio_nr_pages(dst)); xas_store(&xas, dst); - folio_ref_unfreeze(src, expected_count - 1); + folio_ref_unfreeze(src, expected_count - folio_nr_pages(src)); xas_unlock_irq(&xas); @@ -946,7 +946,7 @@ static int move_to_new_folio(struct folio *dst, struct folio *src, enum migrate_mode mode) { int rc = -EAGAIN; - bool is_lru = !__PageMovable(&src->page); + bool is_lru = !__folio_test_movable(src); VM_BUG_ON_FOLIO(!folio_test_locked(src), src); VM_BUG_ON_FOLIO(!folio_test_locked(dst), dst); @@ -993,7 +993,7 @@ static int move_to_new_folio(struct folio *dst, struct folio *src, * src is freed; but stats require that PageAnon be left as PageAnon. */ if (rc == MIGRATEPAGE_SUCCESS) { - if (__PageMovable(&src->page)) { + if (__folio_test_movable(src)) { VM_BUG_ON_FOLIO(!folio_test_isolated(src), src); /* @@ -1085,7 +1085,7 @@ static void migrate_folio_done(struct folio *src, /* * Compaction can migrate also non-LRU pages which are * not accounted to NR_ISOLATED_*. They can be recognized - * as __PageMovable + * as __folio_test_movable */ if (likely(!__folio_test_movable(src))) mod_node_page_state(folio_pgdat(src), NR_ISOLATED_ANON + @@ -1106,7 +1106,7 @@ static int migrate_folio_unmap(new_folio_t get_new_folio, int rc = -EAGAIN; int page_was_mapped = 0; struct anon_vma *anon_vma = NULL; - bool is_lru = !__PageMovable(&src->page); + bool is_lru = !__folio_test_movable(src); bool locked = false; bool dst_locked = false; @@ -1264,7 +1264,7 @@ static int migrate_folio_move(free_folio_t put_new_folio, unsigned long private, int rc; int page_was_mapped = 0; struct anon_vma *anon_vma = NULL; - bool is_lru = !__PageMovable(&src->page); + bool is_lru = !__folio_test_movable(src); struct list_head *prev; __migrate_folio_extract(dst, &page_was_mapped, &anon_vma); @@ -2060,8 +2060,8 @@ static int add_page_for_migration(struct mm_struct *mm, const void __user *p, struct vm_area_struct *vma; unsigned long addr; struct page *page; + struct folio *folio; int err; - bool isolated; mmap_read_lock(mm); addr = (unsigned long)untagged_addr_remote(mm, p); @@ -2082,45 +2082,38 @@ static int add_page_for_migration(struct mm_struct *mm, const void __user *p, if (!page) goto out; - if (is_zone_device_page(page)) - goto out_putpage; + folio = page_folio(page); + if (folio_is_zone_device(folio)) + goto out_putfolio; err = 0; - if (page_to_nid(page) == node) - goto out_putpage; + if (folio_nid(folio) == node) + goto out_putfolio; err = -EACCES; if (page_mapcount(page) > 1 && !migrate_all) - goto out_putpage; + goto out_putfolio; - if (PageHuge(page)) { - if (PageHead(page)) { - isolated = isolate_hugetlb(page_folio(page), pagelist); - err = isolated ? 1 : -EBUSY; - } + err = -EBUSY; + if (folio_test_hugetlb(folio)) { + if (isolate_hugetlb(folio, pagelist)) + err = 1; } else { - struct page *head; - - head = compound_head(page); - isolated = isolate_lru_page(head); - if (!isolated) { - err = -EBUSY; - goto out_putpage; - } + if (!folio_isolate_lru(folio)) + goto out_putfolio; err = 1; - list_add_tail(&head->lru, pagelist); - mod_node_page_state(page_pgdat(head), - NR_ISOLATED_ANON + page_is_file_lru(head), - thp_nr_pages(head)); + list_add_tail(&folio->lru, pagelist); + node_stat_mod_folio(folio, + NR_ISOLATED_ANON + folio_is_file_lru(folio), + folio_nr_pages(folio)); } -out_putpage: +out_putfolio: /* - * Either remove the duplicate refcount from - * isolate_lru_page() or drop the page ref if it was - * not isolated. + * Either remove the duplicate refcount from folio_isolate_lru() + * or drop the folio ref if it was not isolated. */ - put_page(page); + folio_put(folio); out: mmap_read_unlock(mm); return err; @@ -2491,16 +2484,9 @@ static struct folio *alloc_misplaced_dst_folio(struct folio *src, return __folio_alloc_node(gfp, order, nid); } -static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) +static int numamigrate_isolate_folio(pg_data_t *pgdat, struct folio *folio) { - int nr_pages = thp_nr_pages(page); - int order = compound_order(page); - - VM_BUG_ON_PAGE(order && !PageTransHuge(page), page); - - /* Do not migrate THP mapped by multiple processes */ - if (PageTransHuge(page) && total_mapcount(page) > 1) - return 0; + int nr_pages = folio_nr_pages(folio); /* Avoid migrating to a node that is nearly full */ if (!migrate_balanced_pgdat(pgdat, nr_pages)) { @@ -2512,75 +2498,79 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) if (managed_zone(pgdat->node_zones + z)) break; } - wakeup_kswapd(pgdat->node_zones + z, 0, order, ZONE_MOVABLE); + wakeup_kswapd(pgdat->node_zones + z, 0, + folio_order(folio), ZONE_MOVABLE); return 0; } - if (!isolate_lru_page(page)) + if (!folio_isolate_lru(folio)) return 0; - mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_is_file_lru(page), + node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), nr_pages); /* - * Isolating the page has taken another reference, so the - * caller's reference can be safely dropped without the page + * Isolating the folio has taken another reference, so the + * caller's reference can be safely dropped without the folio * disappearing underneath us during migration. */ - put_page(page); + folio_put(folio); return 1; } /* - * Attempt to migrate a misplaced page to the specified destination + * Attempt to migrate a misplaced folio to the specified destination * node. Caller is expected to have an elevated reference count on - * the page that will be dropped by this function before returning. + * the folio that will be dropped by this function before returning. */ -int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, - int node) +int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma, + int node) { pg_data_t *pgdat = NODE_DATA(node); int isolated; int nr_remaining; unsigned int nr_succeeded; LIST_HEAD(migratepages); - int nr_pages = thp_nr_pages(page); + int nr_pages = folio_nr_pages(folio); /* - * Don't migrate file pages that are mapped in multiple processes + * Don't migrate file folios that are mapped in multiple processes * with execute permissions as they are probably shared libraries. + * To check if the folio is shared, ideally we want to make sure + * every page is mapped to the same process. Doing that is very + * expensive, so check the estimated mapcount of the folio instead. */ - if (page_mapcount(page) != 1 && page_is_file_lru(page) && + if (folio_estimated_sharers(folio) != 1 && folio_is_file_lru(folio) && (vma->vm_flags & VM_EXEC)) goto out; /* - * Also do not migrate dirty pages as not all filesystems can move - * dirty pages in MIGRATE_ASYNC mode which is a waste of cycles. + * Also do not migrate dirty folios as not all filesystems can move + * dirty folios in MIGRATE_ASYNC mode which is a waste of cycles. */ - if (page_is_file_lru(page) && PageDirty(page)) + if (folio_is_file_lru(folio) && folio_test_dirty(folio)) goto out; - isolated = numamigrate_isolate_page(pgdat, page); + isolated = numamigrate_isolate_folio(pgdat, folio); if (!isolated) goto out; - list_add(&page->lru, &migratepages); + list_add(&folio->lru, &migratepages); nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_folio, NULL, node, MIGRATE_ASYNC, MR_NUMA_MISPLACED, &nr_succeeded); if (nr_remaining) { if (!list_empty(&migratepages)) { - list_del(&page->lru); - mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + - page_is_file_lru(page), -nr_pages); - putback_lru_page(page); + list_del(&folio->lru); + node_stat_mod_folio(folio, NR_ISOLATED_ANON + + folio_is_file_lru(folio), -nr_pages); + folio_putback_lru(folio); } isolated = 0; } if (nr_succeeded) { count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_succeeded); - if (!node_is_toptier(page_to_nid(page)) && node_is_toptier(node)) + if (!node_is_toptier(folio_nid(folio)) && node_is_toptier(node)) mod_node_page_state(pgdat, PGPROMOTE_SUCCESS, nr_succeeded); } @@ -2588,7 +2578,7 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, return isolated; out: - put_page(page); + folio_put(folio); return 0; } #endif /* CONFIG_NUMA_BALANCING */ diff --git a/mm/mlock.c b/mm/mlock.c index 06bdfab83b58..42b6865f8f82 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -305,6 +305,58 @@ void munlock_folio(struct folio *folio) local_unlock(&mlock_fbatch.lock); } +static inline unsigned int folio_mlock_step(struct folio *folio, + pte_t *pte, unsigned long addr, unsigned long end) +{ + unsigned int count, i, nr = folio_nr_pages(folio); + unsigned long pfn = folio_pfn(folio); + pte_t ptent = ptep_get(pte); + + if (!folio_test_large(folio)) + return 1; + + count = pfn + nr - pte_pfn(ptent); + count = min_t(unsigned int, count, (end - addr) >> PAGE_SHIFT); + + for (i = 0; i < count; i++, pte++) { + pte_t entry = ptep_get(pte); + + if (!pte_present(entry)) + break; + if (pte_pfn(entry) - pfn >= nr) + break; + } + + return i; +} + +static inline bool allow_mlock_munlock(struct folio *folio, + struct vm_area_struct *vma, unsigned long start, + unsigned long end, unsigned int step) +{ + /* + * For unlock, allow munlock large folio which is partially + * mapped to VMA. As it's possible that large folio is + * mlocked and VMA is split later. + * + * During memory pressure, such kind of large folio can + * be split. And the pages are not in VM_LOCKed VMA + * can be reclaimed. + */ + if (!(vma->vm_flags & VM_LOCKED)) + return true; + + /* folio not in range [start, end), skip mlock */ + if (!folio_within_range(folio, vma, start, end)) + return false; + + /* folio is not fully mapped, skip mlock */ + if (step != folio_nr_pages(folio)) + return false; + + return true; +} + static int mlock_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -314,6 +366,8 @@ static int mlock_pte_range(pmd_t *pmd, unsigned long addr, pte_t *start_pte, *pte; pte_t ptent; struct folio *folio; + unsigned int step = 1; + unsigned long start = addr; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { @@ -334,6 +388,7 @@ static int mlock_pte_range(pmd_t *pmd, unsigned long addr, walk->action = ACTION_AGAIN; return 0; } + for (pte = start_pte; addr != end; pte++, addr += PAGE_SIZE) { ptent = ptep_get(pte); if (!pte_present(ptent)) @@ -341,12 +396,19 @@ static int mlock_pte_range(pmd_t *pmd, unsigned long addr, folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; - if (folio_test_large(folio)) - continue; + + step = folio_mlock_step(folio, pte, addr, end); + if (!allow_mlock_munlock(folio, vma, start, end, step)) + goto next_entry; + if (vma->vm_flags & VM_LOCKED) mlock_folio(folio); else munlock_folio(folio); + +next_entry: + pte += step - 1; + addr += (step - 1) << PAGE_SHIFT; } pte_unmap(start_pte); out: diff --git a/mm/mm_init.c b/mm/mm_init.c index 50f2f34745af..077bfe393b5e 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -555,7 +555,7 @@ out: node_states[N_MEMORY] = saved_node_state; } -static void __meminit __init_single_page(struct page *page, unsigned long pfn, +void __meminit __init_single_page(struct page *page, unsigned long pfn, unsigned long zone, int nid) { mm_zero_struct_page(page); @@ -1871,8 +1871,6 @@ void __init free_area_init(unsigned long *max_zone_pfn) pg_data_t *pgdat; if (!node_online(nid)) { - pr_info("Initializing node %d as memoryless\n", nid); - /* Allocator not initialized yet */ pgdat = arch_alloc_nodedata(nid); if (!pgdat) diff --git a/mm/mmap.c b/mm/mmap.c index 9e018d8dd7d6..011ba48d9e72 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2179,8 +2179,6 @@ struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned lon #else int expand_stack_locked(struct vm_area_struct *vma, unsigned long address) { - if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) - return -EINVAL; return expand_downwards(vma, address); } @@ -3298,7 +3296,8 @@ int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) } if (vma_link(mm, vma)) { - vm_unacct_memory(charged); + if (vma->vm_flags & VM_ACCOUNT) + vm_unacct_memory(charged); return -ENOMEM; } diff --git a/mm/mremap.c b/mm/mremap.c index 382e81c33fc4..ce8a23ef325a 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -489,10 +489,62 @@ static bool move_pgt_entry(enum pgt_entry entry, struct vm_area_struct *vma, return moved; } +/* + * A helper to check if aligning down is OK. The aligned address should fall + * on *no mapping*. For the stack moving down, that's a special move within + * the VMA that is created to span the source and destination of the move, + * so we make an exception for it. + */ +static bool can_align_down(struct vm_area_struct *vma, unsigned long addr_to_align, + unsigned long mask, bool for_stack) +{ + unsigned long addr_masked = addr_to_align & mask; + + /* + * If @addr_to_align of either source or destination is not the beginning + * of the corresponding VMA, we can't align down or we will destroy part + * of the current mapping. + */ + if (!for_stack && vma->vm_start != addr_to_align) + return false; + + /* In the stack case we explicitly permit in-VMA alignment. */ + if (for_stack && addr_masked >= vma->vm_start) + return true; + + /* + * Make sure the realignment doesn't cause the address to fall on an + * existing mapping. + */ + return find_vma_intersection(vma->vm_mm, addr_masked, vma->vm_start) == NULL; +} + +/* Opportunistically realign to specified boundary for faster copy. */ +static void try_realign_addr(unsigned long *old_addr, struct vm_area_struct *old_vma, + unsigned long *new_addr, struct vm_area_struct *new_vma, + unsigned long mask, bool for_stack) +{ + /* Skip if the addresses are already aligned. */ + if ((*old_addr & ~mask) == 0) + return; + + /* Only realign if the new and old addresses are mutually aligned. */ + if ((*old_addr & ~mask) != (*new_addr & ~mask)) + return; + + /* Ensure realignment doesn't cause overlap with existing mappings. */ + if (!can_align_down(old_vma, *old_addr, mask, for_stack) || + !can_align_down(new_vma, *new_addr, mask, for_stack)) + return; + + *old_addr = *old_addr & mask; + *new_addr = *new_addr & mask; +} + unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len, - bool need_rmap_locks) + bool need_rmap_locks, bool for_stack) { unsigned long extent, old_end; struct mmu_notifier_range range; @@ -508,6 +560,14 @@ unsigned long move_page_tables(struct vm_area_struct *vma, return move_hugetlb_page_tables(vma, new_vma, old_addr, new_addr, len); + /* + * If possible, realign addresses to PMD boundary for faster copy. + * Only realign if the mremap copying hits a PMD boundary. + */ + if (len >= PMD_SIZE - (old_addr & ~PMD_MASK)) + try_realign_addr(&old_addr, vma, &new_addr, new_vma, PMD_MASK, + for_stack); + flush_cache_range(vma, old_addr, old_end); mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma->vm_mm, old_addr, old_end); @@ -577,6 +637,13 @@ again: mmu_notifier_invalidate_range_end(&range); + /* + * Prevent negative return values when {old,new}_addr was realigned + * but we broke out of the above loop for the first PMD itself. + */ + if (len + old_addr < old_end) + return 0; + return len + old_addr - old_end; /* how much done */ } @@ -646,7 +713,7 @@ static unsigned long move_vma(struct vm_area_struct *vma, } moved_len = move_page_tables(vma, old_addr, new_vma, new_addr, old_len, - need_rmap_locks); + need_rmap_locks, false); if (moved_len < old_len) { err = -ENOMEM; } else if (vma->vm_ops && vma->vm_ops->mremap) { @@ -660,7 +727,7 @@ static unsigned long move_vma(struct vm_area_struct *vma, * and then proceed to unmap new area instead of old. */ move_page_tables(new_vma, new_addr, vma, old_addr, moved_len, - true); + true, false); vma = new_vma; old_len = new_len; old_addr = new_addr; @@ -1037,12 +1104,14 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, pgoff_t extension_pgoff = vma->vm_pgoff + ((extension_start - vma->vm_start) >> PAGE_SHIFT); VMA_ITERATOR(vmi, mm, extension_start); + long charged = 0; if (vma->vm_flags & VM_ACCOUNT) { if (security_vm_enough_memory_mm(mm, pages)) { ret = -ENOMEM; goto out; } + charged = pages; } /* @@ -1058,7 +1127,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, vma->vm_file, extension_pgoff, vma_policy(vma), vma->vm_userfaultfd_ctx, anon_vma_name(vma)); if (!vma) { - vm_unacct_memory(pages); + vm_unacct_memory(charged); ret = -ENOMEM; goto out; } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index b8d3d7040a50..001adbb4a180 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2679,7 +2679,7 @@ void __folio_mark_dirty(struct folio *folio, struct address_space *mapping, * @folio: Folio to be marked as dirty. * * Filesystems which do not use buffer heads should call this function - * from their set_page_dirty address space operation. It ignores the + * from their dirty_folio address space operation. It ignores the * contents of folio_get_private(), so if the filesystem marks individual * blocks as dirty, the filesystem should handle that itself. * diff --git a/mm/page_io.c b/mm/page_io.c index fe4c21af23f2..cb559ae324c6 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -208,8 +208,10 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) static inline void count_swpout_vm_event(struct folio *folio) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (unlikely(folio_test_pmd_mappable(folio))) + if (unlikely(folio_test_pmd_mappable(folio))) { + count_memcg_folio_events(folio, THP_SWPOUT, 1); count_vm_event(THP_SWPOUT); + } #endif count_vm_events(PSWPOUT, folio_nr_pages(folio)); } @@ -278,9 +280,6 @@ static void sio_write_complete(struct kiocb *iocb, long ret) set_page_dirty(page); ClearPageReclaim(page); } - } else { - for (p = 0; p < sio->pages; p++) - count_swpout_vm_event(page_folio(sio->bvec[p].bv_page)); } for (p = 0; p < sio->pages; p++) @@ -296,6 +295,7 @@ static void swap_writepage_fs(struct page *page, struct writeback_control *wbc) struct file *swap_file = sis->swap_file; loff_t pos = page_file_offset(page); + count_swpout_vm_event(page_folio(page)); set_page_writeback(page); unlock_page(page); if (wbc->swap_plug) diff --git a/mm/rmap.c b/mm/rmap.c index 9f795b93cf40..c6bb2339e35b 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -798,6 +798,7 @@ struct folio_referenced_arg { unsigned long vm_flags; struct mem_cgroup *memcg; }; + /* * arg: folio_referenced_arg will be passed */ @@ -807,17 +808,33 @@ static bool folio_referenced_one(struct folio *folio, struct folio_referenced_arg *pra = arg; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); int referenced = 0; + unsigned long start = address, ptes = 0; while (page_vma_mapped_walk(&pvmw)) { address = pvmw.address; - if ((vma->vm_flags & VM_LOCKED) && - (!folio_test_large(folio) || !pvmw.pte)) { - /* Restore the mlock which got missed */ - mlock_vma_folio(folio, vma, !pvmw.pte); - page_vma_mapped_walk_done(&pvmw); - pra->vm_flags |= VM_LOCKED; - return false; /* To break the loop */ + if (vma->vm_flags & VM_LOCKED) { + if (!folio_test_large(folio) || !pvmw.pte) { + /* Restore the mlock which got missed */ + mlock_vma_folio(folio, vma); + page_vma_mapped_walk_done(&pvmw); + pra->vm_flags |= VM_LOCKED; + return false; /* To break the loop */ + } + /* + * For large folio fully mapped to VMA, will + * be handled after the pvmw loop. + * + * For large folio cross VMA boundaries, it's + * expected to be picked by page reclaim. But + * should skip reference of pages which are in + * the range of VM_LOCKED vma. As page reclaim + * should just count the reference of pages out + * the range of VM_LOCKED vma. + */ + ptes++; + pra->mapcount--; + continue; } if (pvmw.pte) { @@ -842,6 +859,23 @@ static bool folio_referenced_one(struct folio *folio, pra->mapcount--; } + if ((vma->vm_flags & VM_LOCKED) && + folio_test_large(folio) && + folio_within_vma(folio, vma)) { + unsigned long s_align, e_align; + + s_align = ALIGN_DOWN(start, PMD_SIZE); + e_align = ALIGN_DOWN(start + folio_size(folio) - 1, PMD_SIZE); + + /* folio doesn't cross page table boundary and fully mapped */ + if ((s_align == e_align) && (ptes == folio_nr_pages(folio))) { + /* Restore the mlock which got missed */ + mlock_vma_folio(folio, vma); + pra->vm_flags |= VM_LOCKED; + return false; /* To break the loop */ + } + } + if (referenced) folio_clear_idle(folio); if (folio_test_clear_young(folio)) @@ -1122,27 +1156,22 @@ void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma) } /** - * __page_set_anon_rmap - set up new anonymous rmap - * @folio: Folio which contains page. - * @page: Page to add to rmap. - * @vma: VM area to add page to. + * __folio_set_anon - set up a new anonymous rmap for a folio + * @folio: The folio to set up the new anonymous rmap for. + * @vma: VM area to add the folio to. * @address: User virtual address of the mapping - * @exclusive: the page is exclusively owned by the current process + * @exclusive: Whether the folio is exclusive to the process. */ -static void __page_set_anon_rmap(struct folio *folio, struct page *page, - struct vm_area_struct *vma, unsigned long address, int exclusive) +static void __folio_set_anon(struct folio *folio, struct vm_area_struct *vma, + unsigned long address, bool exclusive) { struct anon_vma *anon_vma = vma->anon_vma; BUG_ON(!anon_vma); - if (folio_test_anon(folio)) - goto out; - /* - * If the page isn't exclusively mapped into this vma, - * we must use the _oldest_ possible anon_vma for the - * page mapping! + * If the folio isn't exclusive to this vma, we must use the _oldest_ + * possible anon_vma for the folio mapping! */ if (!exclusive) anon_vma = anon_vma->root; @@ -1156,9 +1185,6 @@ static void __page_set_anon_rmap(struct folio *folio, struct page *page, anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; WRITE_ONCE(folio->mapping, (struct address_space *) anon_vma); folio->index = linear_page_index(vma, address); -out: - if (exclusive) - SetPageAnonExclusive(page); } /** @@ -1207,7 +1233,7 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, atomic_t *mapped = &folio->_nr_pages_mapped; int nr = 0, nr_pmdmapped = 0; bool compound = flags & RMAP_COMPOUND; - bool first = true; + bool first; /* Is page being mapped by PTE? Is this its first map to be added? */ if (likely(!compound)) { @@ -1236,24 +1262,40 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, } } - VM_BUG_ON_PAGE(!first && (flags & RMAP_EXCLUSIVE), page); - VM_BUG_ON_PAGE(!first && PageAnonExclusive(page), page); - if (nr_pmdmapped) __lruvec_stat_mod_folio(folio, NR_ANON_THPS, nr_pmdmapped); if (nr) __lruvec_stat_mod_folio(folio, NR_ANON_MAPPED, nr); - if (likely(!folio_test_ksm(folio))) { - /* address might be in next vma when migration races vma_merge */ - if (first) - __page_set_anon_rmap(folio, page, vma, address, - !!(flags & RMAP_EXCLUSIVE)); - else - __page_check_anon_rmap(folio, page, vma, address); + if (unlikely(!folio_test_anon(folio))) { + VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); + /* + * For a PTE-mapped large folio, we only know that the single + * PTE is exclusive. Further, __folio_set_anon() might not get + * folio->index right when not given the address of the head + * page. + */ + VM_WARN_ON_FOLIO(folio_test_large(folio) && !compound, folio); + __folio_set_anon(folio, vma, address, + !!(flags & RMAP_EXCLUSIVE)); + } else if (likely(!folio_test_ksm(folio))) { + __page_check_anon_rmap(folio, page, vma, address); } + if (flags & RMAP_EXCLUSIVE) + SetPageAnonExclusive(page); + /* While PTE-mapping a THP we have a PMD and a PTE mapping. */ + VM_WARN_ON_FOLIO((atomic_read(&page->_mapcount) > 0 || + (folio_test_large(folio) && folio_entire_mapcount(folio) > 1)) && + PageAnonExclusive(page), folio); - mlock_vma_folio(folio, vma, compound); + /* + * For large folio, only mlock it if it's fully mapped to VMA. It's + * not easy to check whether the large folio is fully mapped to VMA + * here. Only mlock normal 4K folio and leave page reclaim to handle + * large folio. + */ + if (!folio_test_large(folio)) + mlock_vma_folio(folio, vma); } /** @@ -1290,7 +1332,8 @@ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, } __lruvec_stat_mod_folio(folio, NR_ANON_MAPPED, nr); - __page_set_anon_rmap(folio, &folio->page, vma, address, 1); + __folio_set_anon(folio, vma, address, true); + SetPageAnonExclusive(&folio->page); } /** @@ -1352,7 +1395,9 @@ void folio_add_file_rmap_range(struct folio *folio, struct page *page, if (nr) __lruvec_stat_mod_folio(folio, NR_FILE_MAPPED, nr); - mlock_vma_folio(folio, vma, compound); + /* See comments in page_add_anon_rmap() */ + if (!folio_test_large(folio)) + mlock_vma_folio(folio, vma); } /** @@ -1463,7 +1508,7 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma, * it's only reliable while mapped. */ - munlock_vma_folio(folio, vma, compound); + munlock_vma_folio(folio, vma); } /* @@ -1528,7 +1573,8 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, if (!(flags & TTU_IGNORE_MLOCK) && (vma->vm_flags & VM_LOCKED)) { /* Restore the mlock which got missed */ - mlock_vma_folio(folio, vma, false); + if (!folio_test_large(folio)) + mlock_vma_folio(folio, vma); page_vma_mapped_walk_done(&pvmw); ret = false; break; @@ -2540,22 +2586,16 @@ void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc) * * RMAP_COMPOUND is ignored. */ -void hugepage_add_anon_rmap(struct page *page, struct vm_area_struct *vma, +void hugepage_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { - struct folio *folio = page_folio(page); - struct anon_vma *anon_vma = vma->anon_vma; - int first; + VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); - BUG_ON(!folio_test_locked(folio)); - BUG_ON(!anon_vma); - /* address might be in next vma when migration races vma_merge */ - first = atomic_inc_and_test(&folio->_entire_mapcount); - VM_BUG_ON_PAGE(!first && (flags & RMAP_EXCLUSIVE), page); - VM_BUG_ON_PAGE(!first && PageAnonExclusive(page), page); - if (first) - __page_set_anon_rmap(folio, page, vma, address, - !!(flags & RMAP_EXCLUSIVE)); + atomic_inc(&folio->_entire_mapcount); + if (flags & RMAP_EXCLUSIVE) + SetPageAnonExclusive(&folio->page); + VM_WARN_ON_FOLIO(folio_entire_mapcount(folio) > 1 && + PageAnonExclusive(&folio->page), folio); } void hugepage_add_new_anon_rmap(struct folio *folio, @@ -2565,6 +2605,7 @@ void hugepage_add_new_anon_rmap(struct folio *folio, /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); folio_clear_hugetlb_restore_reserve(folio); - __page_set_anon_rmap(folio, &folio->page, vma, address, 1); + __folio_set_anon(folio, vma, address, true); + SetPageAnonExclusive(&folio->page); } #endif /* CONFIG_HUGETLB_PAGE */ diff --git a/mm/shmem.c b/mm/shmem.c index 69595d341882..8539d39ec9a3 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -4585,11 +4585,7 @@ static struct file_system_type shmem_fs_type = { .parameters = shmem_fs_parameters, #endif .kill_sb = kill_litter_super, -#ifdef CONFIG_SHMEM .fs_flags = FS_USERNS_MOUNT | FS_ALLOW_IDMAP, -#else - .fs_flags = FS_USERNS_MOUNT, -#endif }; void __init shmem_init(void) diff --git a/mm/show_mem.c b/mm/show_mem.c index 4b888b18bdde..ba0808d6917f 100644 --- a/mm/show_mem.c +++ b/mm/show_mem.c @@ -34,13 +34,8 @@ long si_mem_available(void) long available; unsigned long pagecache; unsigned long wmark_low = 0; - unsigned long pages[NR_LRU_LISTS]; unsigned long reclaimable; struct zone *zone; - int lru; - - for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++) - pages[lru] = global_node_page_state(NR_LRU_BASE + lru); for_each_zone(zone) wmark_low += low_wmark_pages(zone); @@ -56,7 +51,8 @@ long si_mem_available(void) * start swapping or thrashing. Assume at least half of the page * cache, or the low watermark worth of cache, needs to stay. */ - pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE]; + pagecache = global_node_page_state(NR_ACTIVE_FILE) + + global_node_page_state(NR_INACTIVE_FILE); pagecache -= min(pagecache / 2, wmark_low); available += pagecache; @@ -67,7 +63,8 @@ long si_mem_available(void) */ reclaimable = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B) + global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE); - available += reclaimable - min(reclaimable / 2, wmark_low); + reclaimable -= min(reclaimable / 2, wmark_low); + available += reclaimable; if (available < 0) available = 0; diff --git a/mm/shrinker.c b/mm/shrinker.c new file mode 100644 index 000000000000..dd91eab43ed3 --- /dev/null +++ b/mm/shrinker.c @@ -0,0 +1,809 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/memcontrol.h> +#include <linux/rwsem.h> +#include <linux/shrinker.h> +#include <linux/rculist.h> +#include <trace/events/vmscan.h> + +#include "internal.h" + +LIST_HEAD(shrinker_list); +DEFINE_MUTEX(shrinker_mutex); + +#ifdef CONFIG_MEMCG +static int shrinker_nr_max; + +static inline int shrinker_unit_size(int nr_items) +{ + return (DIV_ROUND_UP(nr_items, SHRINKER_UNIT_BITS) * sizeof(struct shrinker_info_unit *)); +} + +static inline void shrinker_unit_free(struct shrinker_info *info, int start) +{ + struct shrinker_info_unit **unit; + int nr, i; + + if (!info) + return; + + unit = info->unit; + nr = DIV_ROUND_UP(info->map_nr_max, SHRINKER_UNIT_BITS); + + for (i = start; i < nr; i++) { + if (!unit[i]) + break; + + kfree(unit[i]); + unit[i] = NULL; + } +} + +static inline int shrinker_unit_alloc(struct shrinker_info *new, + struct shrinker_info *old, int nid) +{ + struct shrinker_info_unit *unit; + int nr = DIV_ROUND_UP(new->map_nr_max, SHRINKER_UNIT_BITS); + int start = old ? DIV_ROUND_UP(old->map_nr_max, SHRINKER_UNIT_BITS) : 0; + int i; + + for (i = start; i < nr; i++) { + unit = kzalloc_node(sizeof(*unit), GFP_KERNEL, nid); + if (!unit) { + shrinker_unit_free(new, start); + return -ENOMEM; + } + + new->unit[i] = unit; + } + + return 0; +} + +void free_shrinker_info(struct mem_cgroup *memcg) +{ + struct mem_cgroup_per_node *pn; + struct shrinker_info *info; + int nid; + + for_each_node(nid) { + pn = memcg->nodeinfo[nid]; + info = rcu_dereference_protected(pn->shrinker_info, true); + shrinker_unit_free(info, 0); + kvfree(info); + rcu_assign_pointer(pn->shrinker_info, NULL); + } +} + +int alloc_shrinker_info(struct mem_cgroup *memcg) +{ + struct shrinker_info *info; + int nid, ret = 0; + int array_size = 0; + + mutex_lock(&shrinker_mutex); + array_size = shrinker_unit_size(shrinker_nr_max); + for_each_node(nid) { + info = kvzalloc_node(sizeof(*info) + array_size, GFP_KERNEL, nid); + if (!info) + goto err; + info->map_nr_max = shrinker_nr_max; + if (shrinker_unit_alloc(info, NULL, nid)) + goto err; + rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info); + } + mutex_unlock(&shrinker_mutex); + + return ret; + +err: + mutex_unlock(&shrinker_mutex); + free_shrinker_info(memcg); + return -ENOMEM; +} + +static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg, + int nid) +{ + return rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info, + lockdep_is_held(&shrinker_mutex)); +} + +static int expand_one_shrinker_info(struct mem_cgroup *memcg, int new_size, + int old_size, int new_nr_max) +{ + struct shrinker_info *new, *old; + struct mem_cgroup_per_node *pn; + int nid; + + for_each_node(nid) { + pn = memcg->nodeinfo[nid]; + old = shrinker_info_protected(memcg, nid); + /* Not yet online memcg */ + if (!old) + return 0; + + /* Already expanded this shrinker_info */ + if (new_nr_max <= old->map_nr_max) + continue; + + new = kvmalloc_node(sizeof(*new) + new_size, GFP_KERNEL, nid); + if (!new) + return -ENOMEM; + + new->map_nr_max = new_nr_max; + + memcpy(new->unit, old->unit, old_size); + if (shrinker_unit_alloc(new, old, nid)) { + kvfree(new); + return -ENOMEM; + } + + rcu_assign_pointer(pn->shrinker_info, new); + kvfree_rcu(old, rcu); + } + + return 0; +} + +static int expand_shrinker_info(int new_id) +{ + int ret = 0; + int new_nr_max = round_up(new_id + 1, SHRINKER_UNIT_BITS); + int new_size, old_size = 0; + struct mem_cgroup *memcg; + + if (!root_mem_cgroup) + goto out; + + lockdep_assert_held(&shrinker_mutex); + + new_size = shrinker_unit_size(new_nr_max); + old_size = shrinker_unit_size(shrinker_nr_max); + + memcg = mem_cgroup_iter(NULL, NULL, NULL); + do { + ret = expand_one_shrinker_info(memcg, new_size, old_size, + new_nr_max); + if (ret) { + mem_cgroup_iter_break(NULL, memcg); + goto out; + } + } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); +out: + if (!ret) + shrinker_nr_max = new_nr_max; + + return ret; +} + +static inline int shrinker_id_to_index(int shrinker_id) +{ + return shrinker_id / SHRINKER_UNIT_BITS; +} + +static inline int shrinker_id_to_offset(int shrinker_id) +{ + return shrinker_id % SHRINKER_UNIT_BITS; +} + +static inline int calc_shrinker_id(int index, int offset) +{ + return index * SHRINKER_UNIT_BITS + offset; +} + +void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) +{ + if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) { + struct shrinker_info *info; + struct shrinker_info_unit *unit; + + rcu_read_lock(); + info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); + unit = info->unit[shrinker_id_to_index(shrinker_id)]; + if (!WARN_ON_ONCE(shrinker_id >= info->map_nr_max)) { + /* Pairs with smp mb in shrink_slab() */ + smp_mb__before_atomic(); + set_bit(shrinker_id_to_offset(shrinker_id), unit->map); + } + rcu_read_unlock(); + } +} + +static DEFINE_IDR(shrinker_idr); + +static int shrinker_memcg_alloc(struct shrinker *shrinker) +{ + int id, ret = -ENOMEM; + + if (mem_cgroup_disabled()) + return -ENOSYS; + + mutex_lock(&shrinker_mutex); + id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL); + if (id < 0) + goto unlock; + + if (id >= shrinker_nr_max) { + if (expand_shrinker_info(id)) { + idr_remove(&shrinker_idr, id); + goto unlock; + } + } + shrinker->id = id; + ret = 0; +unlock: + mutex_unlock(&shrinker_mutex); + return ret; +} + +static void shrinker_memcg_remove(struct shrinker *shrinker) +{ + int id = shrinker->id; + + BUG_ON(id < 0); + + lockdep_assert_held(&shrinker_mutex); + + idr_remove(&shrinker_idr, id); +} + +static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, + struct mem_cgroup *memcg) +{ + struct shrinker_info *info; + struct shrinker_info_unit *unit; + long nr_deferred; + + rcu_read_lock(); + info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); + unit = info->unit[shrinker_id_to_index(shrinker->id)]; + nr_deferred = atomic_long_xchg(&unit->nr_deferred[shrinker_id_to_offset(shrinker->id)], 0); + rcu_read_unlock(); + + return nr_deferred; +} + +static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, + struct mem_cgroup *memcg) +{ + struct shrinker_info *info; + struct shrinker_info_unit *unit; + long nr_deferred; + + rcu_read_lock(); + info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); + unit = info->unit[shrinker_id_to_index(shrinker->id)]; + nr_deferred = + atomic_long_add_return(nr, &unit->nr_deferred[shrinker_id_to_offset(shrinker->id)]); + rcu_read_unlock(); + + return nr_deferred; +} + +void reparent_shrinker_deferred(struct mem_cgroup *memcg) +{ + int nid, index, offset; + long nr; + struct mem_cgroup *parent; + struct shrinker_info *child_info, *parent_info; + struct shrinker_info_unit *child_unit, *parent_unit; + + parent = parent_mem_cgroup(memcg); + if (!parent) + parent = root_mem_cgroup; + + /* Prevent from concurrent shrinker_info expand */ + mutex_lock(&shrinker_mutex); + for_each_node(nid) { + child_info = shrinker_info_protected(memcg, nid); + parent_info = shrinker_info_protected(parent, nid); + for (index = 0; index < shrinker_id_to_index(child_info->map_nr_max); index++) { + child_unit = child_info->unit[index]; + parent_unit = parent_info->unit[index]; + for (offset = 0; offset < SHRINKER_UNIT_BITS; offset++) { + nr = atomic_long_read(&child_unit->nr_deferred[offset]); + atomic_long_add(nr, &parent_unit->nr_deferred[offset]); + } + } + } + mutex_unlock(&shrinker_mutex); +} +#else +static int shrinker_memcg_alloc(struct shrinker *shrinker) +{ + return -ENOSYS; +} + +static void shrinker_memcg_remove(struct shrinker *shrinker) +{ +} + +static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, + struct mem_cgroup *memcg) +{ + return 0; +} + +static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, + struct mem_cgroup *memcg) +{ + return 0; +} +#endif /* CONFIG_MEMCG */ + +static long xchg_nr_deferred(struct shrinker *shrinker, + struct shrink_control *sc) +{ + int nid = sc->nid; + + if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) + nid = 0; + + if (sc->memcg && + (shrinker->flags & SHRINKER_MEMCG_AWARE)) + return xchg_nr_deferred_memcg(nid, shrinker, + sc->memcg); + + return atomic_long_xchg(&shrinker->nr_deferred[nid], 0); +} + + +static long add_nr_deferred(long nr, struct shrinker *shrinker, + struct shrink_control *sc) +{ + int nid = sc->nid; + + if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) + nid = 0; + + if (sc->memcg && + (shrinker->flags & SHRINKER_MEMCG_AWARE)) + return add_nr_deferred_memcg(nr, nid, shrinker, + sc->memcg); + + return atomic_long_add_return(nr, &shrinker->nr_deferred[nid]); +} + +#define SHRINK_BATCH 128 + +static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, + struct shrinker *shrinker, int priority) +{ + unsigned long freed = 0; + unsigned long long delta; + long total_scan; + long freeable; + long nr; + long new_nr; + long batch_size = shrinker->batch ? shrinker->batch + : SHRINK_BATCH; + long scanned = 0, next_deferred; + + freeable = shrinker->count_objects(shrinker, shrinkctl); + if (freeable == 0 || freeable == SHRINK_EMPTY) + return freeable; + + /* + * copy the current shrinker scan count into a local variable + * and zero it so that other concurrent shrinker invocations + * don't also do this scanning work. + */ + nr = xchg_nr_deferred(shrinker, shrinkctl); + + if (shrinker->seeks) { + delta = freeable >> priority; + delta *= 4; + do_div(delta, shrinker->seeks); + } else { + /* + * These objects don't require any IO to create. Trim + * them aggressively under memory pressure to keep + * them from causing refetches in the IO caches. + */ + delta = freeable / 2; + } + + total_scan = nr >> priority; + total_scan += delta; + total_scan = min(total_scan, (2 * freeable)); + + trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, + freeable, delta, total_scan, priority); + + /* + * Normally, we should not scan less than batch_size objects in one + * pass to avoid too frequent shrinker calls, but if the slab has less + * than batch_size objects in total and we are really tight on memory, + * we will try to reclaim all available objects, otherwise we can end + * up failing allocations although there are plenty of reclaimable + * objects spread over several slabs with usage less than the + * batch_size. + * + * We detect the "tight on memory" situations by looking at the total + * number of objects we want to scan (total_scan). If it is greater + * than the total number of objects on slab (freeable), we must be + * scanning at high prio and therefore should try to reclaim as much as + * possible. + */ + while (total_scan >= batch_size || + total_scan >= freeable) { + unsigned long ret; + unsigned long nr_to_scan = min(batch_size, total_scan); + + shrinkctl->nr_to_scan = nr_to_scan; + shrinkctl->nr_scanned = nr_to_scan; + ret = shrinker->scan_objects(shrinker, shrinkctl); + if (ret == SHRINK_STOP) + break; + freed += ret; + + count_vm_events(SLABS_SCANNED, shrinkctl->nr_scanned); + total_scan -= shrinkctl->nr_scanned; + scanned += shrinkctl->nr_scanned; + + cond_resched(); + } + + /* + * The deferred work is increased by any new work (delta) that wasn't + * done, decreased by old deferred work that was done now. + * + * And it is capped to two times of the freeable items. + */ + next_deferred = max_t(long, (nr + delta - scanned), 0); + next_deferred = min(next_deferred, (2 * freeable)); + + /* + * move the unused scan count back into the shrinker in a + * manner that handles concurrent updates. + */ + new_nr = add_nr_deferred(next_deferred, shrinker, shrinkctl); + + trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan); + return freed; +} + +#ifdef CONFIG_MEMCG +static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, + struct mem_cgroup *memcg, int priority) +{ + struct shrinker_info *info; + unsigned long ret, freed = 0; + int offset, index = 0; + + if (!mem_cgroup_online(memcg)) + return 0; + + /* + * lockless algorithm of memcg shrink. + * + * The shrinker_info may be freed asynchronously via RCU in the + * expand_one_shrinker_info(), so the rcu_read_lock() needs to be used + * to ensure the existence of the shrinker_info. + * + * The shrinker_info_unit is never freed unless its corresponding memcg + * is destroyed. Here we already hold the refcount of memcg, so the + * memcg will not be destroyed, and of course shrinker_info_unit will + * not be freed. + * + * So in the memcg shrink: + * step 1: use rcu_read_lock() to guarantee existence of the + * shrinker_info. + * step 2: after getting shrinker_info_unit we can safely release the + * RCU lock. + * step 3: traverse the bitmap and calculate shrinker_id + * step 4: use rcu_read_lock() to guarantee existence of the shrinker. + * step 5: use shrinker_id to find the shrinker, then use + * shrinker_try_get() to guarantee existence of the shrinker, + * then we can release the RCU lock to do do_shrink_slab() that + * may sleep. + * step 6: do shrinker_put() paired with step 5 to put the refcount, + * if the refcount reaches 0, then wake up the waiter in + * shrinker_free() by calling complete(). + * Note: here is different from the global shrink, we don't + * need to acquire the RCU lock to guarantee existence of + * the shrinker, because we don't need to use this + * shrinker to traverse the next shrinker in the bitmap. + * step 7: we have already exited the read-side of rcu critical section + * before calling do_shrink_slab(), the shrinker_info may be + * released in expand_one_shrinker_info(), so go back to step 1 + * to reacquire the shrinker_info. + */ +again: + rcu_read_lock(); + info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); + if (unlikely(!info)) + goto unlock; + + if (index < shrinker_id_to_index(info->map_nr_max)) { + struct shrinker_info_unit *unit; + + unit = info->unit[index]; + + rcu_read_unlock(); + + for_each_set_bit(offset, unit->map, SHRINKER_UNIT_BITS) { + struct shrink_control sc = { + .gfp_mask = gfp_mask, + .nid = nid, + .memcg = memcg, + }; + struct shrinker *shrinker; + int shrinker_id = calc_shrinker_id(index, offset); + + rcu_read_lock(); + shrinker = idr_find(&shrinker_idr, shrinker_id); + if (unlikely(!shrinker || !shrinker_try_get(shrinker))) { + clear_bit(offset, unit->map); + rcu_read_unlock(); + continue; + } + rcu_read_unlock(); + + /* Call non-slab shrinkers even though kmem is disabled */ + if (!memcg_kmem_online() && + !(shrinker->flags & SHRINKER_NONSLAB)) + continue; + + ret = do_shrink_slab(&sc, shrinker, priority); + if (ret == SHRINK_EMPTY) { + clear_bit(offset, unit->map); + /* + * After the shrinker reported that it had no objects to + * free, but before we cleared the corresponding bit in + * the memcg shrinker map, a new object might have been + * added. To make sure, we have the bit set in this + * case, we invoke the shrinker one more time and reset + * the bit if it reports that it is not empty anymore. + * The memory barrier here pairs with the barrier in + * set_shrinker_bit(): + * + * list_lru_add() shrink_slab_memcg() + * list_add_tail() clear_bit() + * <MB> <MB> + * set_bit() do_shrink_slab() + */ + smp_mb__after_atomic(); + ret = do_shrink_slab(&sc, shrinker, priority); + if (ret == SHRINK_EMPTY) + ret = 0; + else + set_shrinker_bit(memcg, nid, shrinker_id); + } + freed += ret; + shrinker_put(shrinker); + } + + index++; + goto again; + } +unlock: + rcu_read_unlock(); + return freed; +} +#else /* !CONFIG_MEMCG */ +static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, + struct mem_cgroup *memcg, int priority) +{ + return 0; +} +#endif /* CONFIG_MEMCG */ + +/** + * shrink_slab - shrink slab caches + * @gfp_mask: allocation context + * @nid: node whose slab caches to target + * @memcg: memory cgroup whose slab caches to target + * @priority: the reclaim priority + * + * Call the shrink functions to age shrinkable caches. + * + * @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set, + * unaware shrinkers will receive a node id of 0 instead. + * + * @memcg specifies the memory cgroup to target. Unaware shrinkers + * are called only if it is the root cgroup. + * + * @priority is sc->priority, we take the number of objects and >> by priority + * in order to get the scan target. + * + * Returns the number of reclaimed slab objects. + */ +unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, + int priority) +{ + unsigned long ret, freed = 0; + struct shrinker *shrinker; + + /* + * The root memcg might be allocated even though memcg is disabled + * via "cgroup_disable=memory" boot parameter. This could make + * mem_cgroup_is_root() return false, then just run memcg slab + * shrink, but skip global shrink. This may result in premature + * oom. + */ + if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) + return shrink_slab_memcg(gfp_mask, nid, memcg, priority); + + /* + * lockless algorithm of global shrink. + * + * In the unregistration setp, the shrinker will be freed asynchronously + * via RCU after its refcount reaches 0. So both rcu_read_lock() and + * shrinker_try_get() can be used to ensure the existence of the shrinker. + * + * So in the global shrink: + * step 1: use rcu_read_lock() to guarantee existence of the shrinker + * and the validity of the shrinker_list walk. + * step 2: use shrinker_try_get() to try get the refcount, if successful, + * then the existence of the shrinker can also be guaranteed, + * so we can release the RCU lock to do do_shrink_slab() that + * may sleep. + * step 3: *MUST* to reacquire the RCU lock before calling shrinker_put(), + * which ensures that neither this shrinker nor the next shrinker + * will be freed in the next traversal operation. + * step 4: do shrinker_put() paired with step 2 to put the refcount, + * if the refcount reaches 0, then wake up the waiter in + * shrinker_free() by calling complete(). + */ + rcu_read_lock(); + list_for_each_entry_rcu(shrinker, &shrinker_list, list) { + struct shrink_control sc = { + .gfp_mask = gfp_mask, + .nid = nid, + .memcg = memcg, + }; + + if (!shrinker_try_get(shrinker)) + continue; + + rcu_read_unlock(); + + ret = do_shrink_slab(&sc, shrinker, priority); + if (ret == SHRINK_EMPTY) + ret = 0; + freed += ret; + + rcu_read_lock(); + shrinker_put(shrinker); + } + + rcu_read_unlock(); + cond_resched(); + return freed; +} + +struct shrinker *shrinker_alloc(unsigned int flags, const char *fmt, ...) +{ + struct shrinker *shrinker; + unsigned int size; + va_list ap; + int err; + + shrinker = kzalloc(sizeof(struct shrinker), GFP_KERNEL); + if (!shrinker) + return NULL; + + va_start(ap, fmt); + err = shrinker_debugfs_name_alloc(shrinker, fmt, ap); + va_end(ap); + if (err) + goto err_name; + + shrinker->flags = flags | SHRINKER_ALLOCATED; + shrinker->seeks = DEFAULT_SEEKS; + + if (flags & SHRINKER_MEMCG_AWARE) { + err = shrinker_memcg_alloc(shrinker); + if (err == -ENOSYS) { + /* Memcg is not supported, fallback to non-memcg-aware shrinker. */ + shrinker->flags &= ~SHRINKER_MEMCG_AWARE; + goto non_memcg; + } + + if (err) + goto err_flags; + + return shrinker; + } + +non_memcg: + /* + * The nr_deferred is available on per memcg level for memcg aware + * shrinkers, so only allocate nr_deferred in the following cases: + * - non-memcg-aware shrinkers + * - !CONFIG_MEMCG + * - memcg is disabled by kernel command line + */ + size = sizeof(*shrinker->nr_deferred); + if (flags & SHRINKER_NUMA_AWARE) + size *= nr_node_ids; + + shrinker->nr_deferred = kzalloc(size, GFP_KERNEL); + if (!shrinker->nr_deferred) + goto err_flags; + + return shrinker; + +err_flags: + shrinker_debugfs_name_free(shrinker); +err_name: + kfree(shrinker); + return NULL; +} +EXPORT_SYMBOL_GPL(shrinker_alloc); + +void shrinker_register(struct shrinker *shrinker) +{ + if (unlikely(!(shrinker->flags & SHRINKER_ALLOCATED))) { + pr_warn("Must use shrinker_alloc() to dynamically allocate the shrinker"); + return; + } + + mutex_lock(&shrinker_mutex); + list_add_tail_rcu(&shrinker->list, &shrinker_list); + shrinker->flags |= SHRINKER_REGISTERED; + shrinker_debugfs_add(shrinker); + mutex_unlock(&shrinker_mutex); + + init_completion(&shrinker->done); + /* + * Now the shrinker is fully set up, take the first reference to it to + * indicate that lookup operations are now allowed to use it via + * shrinker_try_get(). + */ + refcount_set(&shrinker->refcount, 1); +} +EXPORT_SYMBOL_GPL(shrinker_register); + +static void shrinker_free_rcu_cb(struct rcu_head *head) +{ + struct shrinker *shrinker = container_of(head, struct shrinker, rcu); + + kfree(shrinker->nr_deferred); + kfree(shrinker); +} + +void shrinker_free(struct shrinker *shrinker) +{ + struct dentry *debugfs_entry = NULL; + int debugfs_id; + + if (!shrinker) + return; + + if (shrinker->flags & SHRINKER_REGISTERED) { + /* drop the initial refcount */ + shrinker_put(shrinker); + /* + * Wait for all lookups of the shrinker to complete, after that, + * no shrinker is running or will run again, then we can safely + * free it asynchronously via RCU and safely free the structure + * where the shrinker is located, such as super_block etc. + */ + wait_for_completion(&shrinker->done); + } + + mutex_lock(&shrinker_mutex); + if (shrinker->flags & SHRINKER_REGISTERED) { + /* + * Now we can safely remove it from the shrinker_list and then + * free it. + */ + list_del_rcu(&shrinker->list); + debugfs_entry = shrinker_debugfs_detach(shrinker, &debugfs_id); + shrinker->flags &= ~SHRINKER_REGISTERED; + } + + shrinker_debugfs_name_free(shrinker); + + if (shrinker->flags & SHRINKER_MEMCG_AWARE) + shrinker_memcg_remove(shrinker); + mutex_unlock(&shrinker_mutex); + + if (debugfs_entry) + shrinker_debugfs_remove(debugfs_entry, debugfs_id); + + call_rcu(&shrinker->rcu, shrinker_free_rcu_cb); +} +EXPORT_SYMBOL_GPL(shrinker_free); diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c index 3ab53fad8876..12ea5486a3e9 100644 --- a/mm/shrinker_debug.c +++ b/mm/shrinker_debug.c @@ -6,8 +6,10 @@ #include <linux/shrinker.h> #include <linux/memcontrol.h> +#include "internal.h" + /* defined in vmscan.c */ -extern struct rw_semaphore shrinker_rwsem; +extern struct mutex shrinker_mutex; extern struct list_head shrinker_list; static DEFINE_IDA(shrinker_debugfs_ida); @@ -49,17 +51,12 @@ static int shrinker_debugfs_count_show(struct seq_file *m, void *v) struct mem_cgroup *memcg; unsigned long total; bool memcg_aware; - int ret, nid; + int ret = 0, nid; count_per_node = kcalloc(nr_node_ids, sizeof(unsigned long), GFP_KERNEL); if (!count_per_node) return -ENOMEM; - ret = down_read_killable(&shrinker_rwsem); - if (ret) { - kfree(count_per_node); - return ret; - } rcu_read_lock(); memcg_aware = shrinker->flags & SHRINKER_MEMCG_AWARE; @@ -92,7 +89,6 @@ static int shrinker_debugfs_count_show(struct seq_file *m, void *v) } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); rcu_read_unlock(); - up_read(&shrinker_rwsem); kfree(count_per_node); return ret; @@ -117,7 +113,6 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file, struct mem_cgroup *memcg = NULL; int nid; char kbuf[72]; - ssize_t ret; read_len = size < (sizeof(kbuf) - 1) ? size : (sizeof(kbuf) - 1); if (copy_from_user(kbuf, buf, read_len)) @@ -146,12 +141,6 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file, return -EINVAL; } - ret = down_read_killable(&shrinker_rwsem); - if (ret) { - mem_cgroup_put(memcg); - return ret; - } - sc.nid = nid; sc.memcg = memcg; sc.nr_to_scan = nr_to_scan; @@ -159,7 +148,6 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file, shrinker->scan_objects(shrinker, &sc); - up_read(&shrinker_rwsem); mem_cgroup_put(memcg); return size; @@ -177,7 +165,7 @@ int shrinker_debugfs_add(struct shrinker *shrinker) char buf[128]; int id; - lockdep_assert_held(&shrinker_rwsem); + lockdep_assert_held(&shrinker_mutex); /* debugfs isn't initialized yet, add debugfs entries later. */ if (!shrinker_debugfs_root) @@ -220,7 +208,7 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) if (!new) return -ENOMEM; - down_write(&shrinker_rwsem); + mutex_lock(&shrinker_mutex); old = shrinker->name; shrinker->name = new; @@ -238,7 +226,7 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) shrinker->debugfs_entry = entry; } - up_write(&shrinker_rwsem); + mutex_unlock(&shrinker_mutex); kfree_const(old); @@ -251,10 +239,7 @@ struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, { struct dentry *entry = shrinker->debugfs_entry; - lockdep_assert_held(&shrinker_rwsem); - - kfree_const(shrinker->name); - shrinker->name = NULL; + lockdep_assert_held(&shrinker_mutex); *debugfs_id = entry ? shrinker->debugfs_id : -1; shrinker->debugfs_entry = NULL; @@ -280,14 +265,14 @@ static int __init shrinker_debugfs_init(void) shrinker_debugfs_root = dentry; /* Create debugfs entries for shrinkers registered at boot */ - down_write(&shrinker_rwsem); + mutex_lock(&shrinker_mutex); list_for_each_entry(shrinker, &shrinker_list, list) if (!shrinker->debugfs_entry) { ret = shrinker_debugfs_add(shrinker); if (ret) break; } - up_write(&shrinker_rwsem); + mutex_unlock(&shrinker_mutex); return ret; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 6f13394b112e..55424215f759 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -35,7 +35,6 @@ #include <linux/cpuset.h> #include <linux/compaction.h> #include <linux/notifier.h> -#include <linux/rwsem.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/freezer.h> @@ -188,246 +187,7 @@ struct scan_control { */ int vm_swappiness = 60; -LIST_HEAD(shrinker_list); -DECLARE_RWSEM(shrinker_rwsem); - #ifdef CONFIG_MEMCG -static int shrinker_nr_max; - -/* The shrinker_info is expanded in a batch of BITS_PER_LONG */ -static inline int shrinker_map_size(int nr_items) -{ - return (DIV_ROUND_UP(nr_items, BITS_PER_LONG) * sizeof(unsigned long)); -} - -static inline int shrinker_defer_size(int nr_items) -{ - return (round_up(nr_items, BITS_PER_LONG) * sizeof(atomic_long_t)); -} - -static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg, - int nid) -{ - return rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info, - lockdep_is_held(&shrinker_rwsem)); -} - -static int expand_one_shrinker_info(struct mem_cgroup *memcg, - int map_size, int defer_size, - int old_map_size, int old_defer_size, - int new_nr_max) -{ - struct shrinker_info *new, *old; - struct mem_cgroup_per_node *pn; - int nid; - int size = map_size + defer_size; - - for_each_node(nid) { - pn = memcg->nodeinfo[nid]; - old = shrinker_info_protected(memcg, nid); - /* Not yet online memcg */ - if (!old) - return 0; - - /* Already expanded this shrinker_info */ - if (new_nr_max <= old->map_nr_max) - continue; - - new = kvmalloc_node(sizeof(*new) + size, GFP_KERNEL, nid); - if (!new) - return -ENOMEM; - - new->nr_deferred = (atomic_long_t *)(new + 1); - new->map = (void *)new->nr_deferred + defer_size; - new->map_nr_max = new_nr_max; - - /* map: set all old bits, clear all new bits */ - memset(new->map, (int)0xff, old_map_size); - memset((void *)new->map + old_map_size, 0, map_size - old_map_size); - /* nr_deferred: copy old values, clear all new values */ - memcpy(new->nr_deferred, old->nr_deferred, old_defer_size); - memset((void *)new->nr_deferred + old_defer_size, 0, - defer_size - old_defer_size); - - rcu_assign_pointer(pn->shrinker_info, new); - kvfree_rcu(old, rcu); - } - - return 0; -} - -void free_shrinker_info(struct mem_cgroup *memcg) -{ - struct mem_cgroup_per_node *pn; - struct shrinker_info *info; - int nid; - - for_each_node(nid) { - pn = memcg->nodeinfo[nid]; - info = rcu_dereference_protected(pn->shrinker_info, true); - kvfree(info); - rcu_assign_pointer(pn->shrinker_info, NULL); - } -} - -int alloc_shrinker_info(struct mem_cgroup *memcg) -{ - struct shrinker_info *info; - int nid, size, ret = 0; - int map_size, defer_size = 0; - - down_write(&shrinker_rwsem); - map_size = shrinker_map_size(shrinker_nr_max); - defer_size = shrinker_defer_size(shrinker_nr_max); - size = map_size + defer_size; - for_each_node(nid) { - info = kvzalloc_node(sizeof(*info) + size, GFP_KERNEL, nid); - if (!info) { - free_shrinker_info(memcg); - ret = -ENOMEM; - break; - } - info->nr_deferred = (atomic_long_t *)(info + 1); - info->map = (void *)info->nr_deferred + defer_size; - info->map_nr_max = shrinker_nr_max; - rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info); - } - up_write(&shrinker_rwsem); - - return ret; -} - -static int expand_shrinker_info(int new_id) -{ - int ret = 0; - int new_nr_max = round_up(new_id + 1, BITS_PER_LONG); - int map_size, defer_size = 0; - int old_map_size, old_defer_size = 0; - struct mem_cgroup *memcg; - - if (!root_mem_cgroup) - goto out; - - lockdep_assert_held(&shrinker_rwsem); - - map_size = shrinker_map_size(new_nr_max); - defer_size = shrinker_defer_size(new_nr_max); - old_map_size = shrinker_map_size(shrinker_nr_max); - old_defer_size = shrinker_defer_size(shrinker_nr_max); - - memcg = mem_cgroup_iter(NULL, NULL, NULL); - do { - ret = expand_one_shrinker_info(memcg, map_size, defer_size, - old_map_size, old_defer_size, - new_nr_max); - if (ret) { - mem_cgroup_iter_break(NULL, memcg); - goto out; - } - } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); -out: - if (!ret) - shrinker_nr_max = new_nr_max; - - return ret; -} - -void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) -{ - if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) { - struct shrinker_info *info; - - rcu_read_lock(); - info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); - if (!WARN_ON_ONCE(shrinker_id >= info->map_nr_max)) { - /* Pairs with smp mb in shrink_slab() */ - smp_mb__before_atomic(); - set_bit(shrinker_id, info->map); - } - rcu_read_unlock(); - } -} - -static DEFINE_IDR(shrinker_idr); - -static int prealloc_memcg_shrinker(struct shrinker *shrinker) -{ - int id, ret = -ENOMEM; - - if (mem_cgroup_disabled()) - return -ENOSYS; - - down_write(&shrinker_rwsem); - /* This may call shrinker, so it must use down_read_trylock() */ - id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL); - if (id < 0) - goto unlock; - - if (id >= shrinker_nr_max) { - if (expand_shrinker_info(id)) { - idr_remove(&shrinker_idr, id); - goto unlock; - } - } - shrinker->id = id; - ret = 0; -unlock: - up_write(&shrinker_rwsem); - return ret; -} - -static void unregister_memcg_shrinker(struct shrinker *shrinker) -{ - int id = shrinker->id; - - BUG_ON(id < 0); - - lockdep_assert_held(&shrinker_rwsem); - - idr_remove(&shrinker_idr, id); -} - -static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, - struct mem_cgroup *memcg) -{ - struct shrinker_info *info; - - info = shrinker_info_protected(memcg, nid); - return atomic_long_xchg(&info->nr_deferred[shrinker->id], 0); -} - -static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, - struct mem_cgroup *memcg) -{ - struct shrinker_info *info; - - info = shrinker_info_protected(memcg, nid); - return atomic_long_add_return(nr, &info->nr_deferred[shrinker->id]); -} - -void reparent_shrinker_deferred(struct mem_cgroup *memcg) -{ - int i, nid; - long nr; - struct mem_cgroup *parent; - struct shrinker_info *child_info, *parent_info; - - parent = parent_mem_cgroup(memcg); - if (!parent) - parent = root_mem_cgroup; - - /* Prevent from concurrent shrinker_info expand */ - down_read(&shrinker_rwsem); - for_each_node(nid) { - child_info = shrinker_info_protected(memcg, nid); - parent_info = shrinker_info_protected(parent, nid); - for (i = 0; i < child_info->map_nr_max; i++) { - nr = atomic_long_read(&child_info->nr_deferred[i]); - atomic_long_add(nr, &parent_info->nr_deferred[i]); - } - } - up_read(&shrinker_rwsem); -} /* Returns true for reclaim through cgroup limits or cgroup interfaces. */ static bool cgroup_reclaim(struct scan_control *sc) @@ -468,27 +228,6 @@ static bool writeback_throttling_sane(struct scan_control *sc) return false; } #else -static int prealloc_memcg_shrinker(struct shrinker *shrinker) -{ - return -ENOSYS; -} - -static void unregister_memcg_shrinker(struct shrinker *shrinker) -{ -} - -static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, - struct mem_cgroup *memcg) -{ - return 0; -} - -static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, - struct mem_cgroup *memcg) -{ - return 0; -} - static bool cgroup_reclaim(struct scan_control *sc) { return false; @@ -557,39 +296,6 @@ static void flush_reclaim_state(struct scan_control *sc) } } -static long xchg_nr_deferred(struct shrinker *shrinker, - struct shrink_control *sc) -{ - int nid = sc->nid; - - if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) - nid = 0; - - if (sc->memcg && - (shrinker->flags & SHRINKER_MEMCG_AWARE)) - return xchg_nr_deferred_memcg(nid, shrinker, - sc->memcg); - - return atomic_long_xchg(&shrinker->nr_deferred[nid], 0); -} - - -static long add_nr_deferred(long nr, struct shrinker *shrinker, - struct shrink_control *sc) -{ - int nid = sc->nid; - - if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) - nid = 0; - - if (sc->memcg && - (shrinker->flags & SHRINKER_MEMCG_AWARE)) - return add_nr_deferred_memcg(nr, nid, shrinker, - sc->memcg); - - return atomic_long_add_return(nr, &shrinker->nr_deferred[nid]); -} - static bool can_demote(int nid, struct scan_control *sc) { if (!numa_demotion_enabled) @@ -671,413 +377,6 @@ static unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, return size; } -/* - * Add a shrinker callback to be called from the vm. - */ -static int __prealloc_shrinker(struct shrinker *shrinker) -{ - unsigned int size; - int err; - - if (shrinker->flags & SHRINKER_MEMCG_AWARE) { - err = prealloc_memcg_shrinker(shrinker); - if (err != -ENOSYS) - return err; - - shrinker->flags &= ~SHRINKER_MEMCG_AWARE; - } - - size = sizeof(*shrinker->nr_deferred); - if (shrinker->flags & SHRINKER_NUMA_AWARE) - size *= nr_node_ids; - - shrinker->nr_deferred = kzalloc(size, GFP_KERNEL); - if (!shrinker->nr_deferred) - return -ENOMEM; - - return 0; -} - -#ifdef CONFIG_SHRINKER_DEBUG -int prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...) -{ - va_list ap; - int err; - - va_start(ap, fmt); - shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); - va_end(ap); - if (!shrinker->name) - return -ENOMEM; - - err = __prealloc_shrinker(shrinker); - if (err) { - kfree_const(shrinker->name); - shrinker->name = NULL; - } - - return err; -} -#else -int prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...) -{ - return __prealloc_shrinker(shrinker); -} -#endif - -void free_prealloced_shrinker(struct shrinker *shrinker) -{ -#ifdef CONFIG_SHRINKER_DEBUG - kfree_const(shrinker->name); - shrinker->name = NULL; -#endif - if (shrinker->flags & SHRINKER_MEMCG_AWARE) { - down_write(&shrinker_rwsem); - unregister_memcg_shrinker(shrinker); - up_write(&shrinker_rwsem); - return; - } - - kfree(shrinker->nr_deferred); - shrinker->nr_deferred = NULL; -} - -void register_shrinker_prepared(struct shrinker *shrinker) -{ - down_write(&shrinker_rwsem); - list_add_tail(&shrinker->list, &shrinker_list); - shrinker->flags |= SHRINKER_REGISTERED; - shrinker_debugfs_add(shrinker); - up_write(&shrinker_rwsem); -} - -static int __register_shrinker(struct shrinker *shrinker) -{ - int err = __prealloc_shrinker(shrinker); - - if (err) - return err; - register_shrinker_prepared(shrinker); - return 0; -} - -#ifdef CONFIG_SHRINKER_DEBUG -int register_shrinker(struct shrinker *shrinker, const char *fmt, ...) -{ - va_list ap; - int err; - - va_start(ap, fmt); - shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); - va_end(ap); - if (!shrinker->name) - return -ENOMEM; - - err = __register_shrinker(shrinker); - if (err) { - kfree_const(shrinker->name); - shrinker->name = NULL; - } - return err; -} -#else -int register_shrinker(struct shrinker *shrinker, const char *fmt, ...) -{ - return __register_shrinker(shrinker); -} -#endif -EXPORT_SYMBOL(register_shrinker); - -/* - * Remove one - */ -void unregister_shrinker(struct shrinker *shrinker) -{ - struct dentry *debugfs_entry; - int debugfs_id; - - if (!(shrinker->flags & SHRINKER_REGISTERED)) - return; - - down_write(&shrinker_rwsem); - list_del(&shrinker->list); - shrinker->flags &= ~SHRINKER_REGISTERED; - if (shrinker->flags & SHRINKER_MEMCG_AWARE) - unregister_memcg_shrinker(shrinker); - debugfs_entry = shrinker_debugfs_detach(shrinker, &debugfs_id); - up_write(&shrinker_rwsem); - - shrinker_debugfs_remove(debugfs_entry, debugfs_id); - - kfree(shrinker->nr_deferred); - shrinker->nr_deferred = NULL; -} -EXPORT_SYMBOL(unregister_shrinker); - -/** - * synchronize_shrinkers - Wait for all running shrinkers to complete. - * - * This is equivalent to calling unregister_shrink() and register_shrinker(), - * but atomically and with less overhead. This is useful to guarantee that all - * shrinker invocations have seen an update, before freeing memory, similar to - * rcu. - */ -void synchronize_shrinkers(void) -{ - down_write(&shrinker_rwsem); - up_write(&shrinker_rwsem); -} -EXPORT_SYMBOL(synchronize_shrinkers); - -#define SHRINK_BATCH 128 - -static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, - struct shrinker *shrinker, int priority) -{ - unsigned long freed = 0; - unsigned long long delta; - long total_scan; - long freeable; - long nr; - long new_nr; - long batch_size = shrinker->batch ? shrinker->batch - : SHRINK_BATCH; - long scanned = 0, next_deferred; - - freeable = shrinker->count_objects(shrinker, shrinkctl); - if (freeable == 0 || freeable == SHRINK_EMPTY) - return freeable; - - /* - * copy the current shrinker scan count into a local variable - * and zero it so that other concurrent shrinker invocations - * don't also do this scanning work. - */ - nr = xchg_nr_deferred(shrinker, shrinkctl); - - if (shrinker->seeks) { - delta = freeable >> priority; - delta *= 4; - do_div(delta, shrinker->seeks); - } else { - /* - * These objects don't require any IO to create. Trim - * them aggressively under memory pressure to keep - * them from causing refetches in the IO caches. - */ - delta = freeable / 2; - } - - total_scan = nr >> priority; - total_scan += delta; - total_scan = min(total_scan, (2 * freeable)); - - trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, - freeable, delta, total_scan, priority); - - /* - * Normally, we should not scan less than batch_size objects in one - * pass to avoid too frequent shrinker calls, but if the slab has less - * than batch_size objects in total and we are really tight on memory, - * we will try to reclaim all available objects, otherwise we can end - * up failing allocations although there are plenty of reclaimable - * objects spread over several slabs with usage less than the - * batch_size. - * - * We detect the "tight on memory" situations by looking at the total - * number of objects we want to scan (total_scan). If it is greater - * than the total number of objects on slab (freeable), we must be - * scanning at high prio and therefore should try to reclaim as much as - * possible. - */ - while (total_scan >= batch_size || - total_scan >= freeable) { - unsigned long ret; - unsigned long nr_to_scan = min(batch_size, total_scan); - - shrinkctl->nr_to_scan = nr_to_scan; - shrinkctl->nr_scanned = nr_to_scan; - ret = shrinker->scan_objects(shrinker, shrinkctl); - if (ret == SHRINK_STOP) - break; - freed += ret; - - count_vm_events(SLABS_SCANNED, shrinkctl->nr_scanned); - total_scan -= shrinkctl->nr_scanned; - scanned += shrinkctl->nr_scanned; - - cond_resched(); - } - - /* - * The deferred work is increased by any new work (delta) that wasn't - * done, decreased by old deferred work that was done now. - * - * And it is capped to two times of the freeable items. - */ - next_deferred = max_t(long, (nr + delta - scanned), 0); - next_deferred = min(next_deferred, (2 * freeable)); - - /* - * move the unused scan count back into the shrinker in a - * manner that handles concurrent updates. - */ - new_nr = add_nr_deferred(next_deferred, shrinker, shrinkctl); - - trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan); - return freed; -} - -#ifdef CONFIG_MEMCG -static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, - struct mem_cgroup *memcg, int priority) -{ - struct shrinker_info *info; - unsigned long ret, freed = 0; - int i; - - if (!mem_cgroup_online(memcg)) - return 0; - - if (!down_read_trylock(&shrinker_rwsem)) - return 0; - - info = shrinker_info_protected(memcg, nid); - if (unlikely(!info)) - goto unlock; - - for_each_set_bit(i, info->map, info->map_nr_max) { - struct shrink_control sc = { - .gfp_mask = gfp_mask, - .nid = nid, - .memcg = memcg, - }; - struct shrinker *shrinker; - - shrinker = idr_find(&shrinker_idr, i); - if (unlikely(!shrinker || !(shrinker->flags & SHRINKER_REGISTERED))) { - if (!shrinker) - clear_bit(i, info->map); - continue; - } - - /* Call non-slab shrinkers even though kmem is disabled */ - if (!memcg_kmem_online() && - !(shrinker->flags & SHRINKER_NONSLAB)) - continue; - - ret = do_shrink_slab(&sc, shrinker, priority); - if (ret == SHRINK_EMPTY) { - clear_bit(i, info->map); - /* - * After the shrinker reported that it had no objects to - * free, but before we cleared the corresponding bit in - * the memcg shrinker map, a new object might have been - * added. To make sure, we have the bit set in this - * case, we invoke the shrinker one more time and reset - * the bit if it reports that it is not empty anymore. - * The memory barrier here pairs with the barrier in - * set_shrinker_bit(): - * - * list_lru_add() shrink_slab_memcg() - * list_add_tail() clear_bit() - * <MB> <MB> - * set_bit() do_shrink_slab() - */ - smp_mb__after_atomic(); - ret = do_shrink_slab(&sc, shrinker, priority); - if (ret == SHRINK_EMPTY) - ret = 0; - else - set_shrinker_bit(memcg, nid, i); - } - freed += ret; - - if (rwsem_is_contended(&shrinker_rwsem)) { - freed = freed ? : 1; - break; - } - } -unlock: - up_read(&shrinker_rwsem); - return freed; -} -#else /* CONFIG_MEMCG */ -static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, - struct mem_cgroup *memcg, int priority) -{ - return 0; -} -#endif /* CONFIG_MEMCG */ - -/** - * shrink_slab - shrink slab caches - * @gfp_mask: allocation context - * @nid: node whose slab caches to target - * @memcg: memory cgroup whose slab caches to target - * @priority: the reclaim priority - * - * Call the shrink functions to age shrinkable caches. - * - * @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set, - * unaware shrinkers will receive a node id of 0 instead. - * - * @memcg specifies the memory cgroup to target. Unaware shrinkers - * are called only if it is the root cgroup. - * - * @priority is sc->priority, we take the number of objects and >> by priority - * in order to get the scan target. - * - * Returns the number of reclaimed slab objects. - */ -static unsigned long shrink_slab(gfp_t gfp_mask, int nid, - struct mem_cgroup *memcg, - int priority) -{ - unsigned long ret, freed = 0; - struct shrinker *shrinker; - - /* - * The root memcg might be allocated even though memcg is disabled - * via "cgroup_disable=memory" boot parameter. This could make - * mem_cgroup_is_root() return false, then just run memcg slab - * shrink, but skip global shrink. This may result in premature - * oom. - */ - if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) - return shrink_slab_memcg(gfp_mask, nid, memcg, priority); - - if (!down_read_trylock(&shrinker_rwsem)) - goto out; - - list_for_each_entry(shrinker, &shrinker_list, list) { - struct shrink_control sc = { - .gfp_mask = gfp_mask, - .nid = nid, - .memcg = memcg, - }; - - ret = do_shrink_slab(&sc, shrinker, priority); - if (ret == SHRINK_EMPTY) - ret = 0; - freed += ret; - /* - * Bail out if someone want to register a new shrinker to - * prevent the registration from being stalled for long periods - * by parallel ongoing shrinking. - */ - if (rwsem_is_contended(&shrinker_rwsem)) { - freed = freed ? : 1; - break; - } - } - - up_read(&shrinker_rwsem); -out: - cond_resched(); - return freed; -} - static unsigned long drop_slab_node(int nid) { unsigned long freed = 0; @@ -1915,6 +1214,7 @@ retry: folio_list)) goto activate_locked; #ifdef CONFIG_TRANSPARENT_HUGEPAGE + count_memcg_folio_events(folio, THP_SWPOUT_FALLBACK, 1); count_vm_event(THP_SWPOUT_FALLBACK); #endif if (!add_to_swap(folio)) @@ -2271,7 +1571,7 @@ static bool skip_cma(struct folio *folio, struct scan_control *sc) { return !current_is_kswapd() && gfp_migratetype(sc->gfp_mask) != MIGRATE_MOVABLE && - get_pageblock_migratetype(&folio->page) == MIGRATE_CMA; + folio_migratetype(folio) == MIGRATE_CMA; } #else static bool skip_cma(struct folio *folio, struct scan_control *sc) @@ -2389,8 +1689,7 @@ move: } *nr_scanned = total_scan; trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, - total_scan, skipped, nr_taken, - sc->may_unmap ? 0 : ISOLATE_UNMAPPED, lru); + total_scan, skipped, nr_taken, lru); update_lru_sizes(lruvec, lru, nr_zone_taken); return nr_taken; } @@ -2909,7 +2208,7 @@ enum scan_balance { SCAN_FILE, }; -static void prepare_scan_count(pg_data_t *pgdat, struct scan_control *sc) +static void prepare_scan_control(pg_data_t *pgdat, struct scan_control *sc) { unsigned long file; struct lruvec *target_lruvec; @@ -6535,7 +5834,7 @@ again: nr_reclaimed = sc->nr_reclaimed; nr_scanned = sc->nr_scanned; - prepare_scan_count(pgdat, sc); + prepare_scan_control(pgdat, sc); shrink_node_memcgs(pgdat, sc); @@ -7892,8 +7191,9 @@ void __meminit kswapd_run(int nid) pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid); if (IS_ERR(pgdat->kswapd)) { /* failure at boot is fatal */ + pr_err("Failed to start kswapd on node %d，ret=%ld\n", + nid, PTR_ERR(pgdat->kswapd)); BUG_ON(system_state < SYSTEM_RUNNING); - pr_err("Failed to start kswapd on node %d\n", nid); pgdat->kswapd = NULL; } } @@ -8026,6 +7326,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in cond_resched(); psi_memstall_enter(&pflags); + delayacct_freepages_start(); fs_reclaim_acquire(sc.gfp_mask); /* * We need to be able to allocate from the reserves for RECLAIM_UNMAP @@ -8048,6 +7349,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(sc.gfp_mask); psi_memstall_leave(&pflags); + delayacct_freepages_end(); trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed); diff --git a/mm/vmstat.c b/mm/vmstat.c index 00e81e99c6ee..894e4c88d241 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -559,8 +559,10 @@ static inline void mod_zone_state(struct zone *zone, { struct per_cpu_zonestat __percpu *pcp = zone->per_cpu_zonestats; s8 __percpu *p = pcp->vm_stat_diff + item; - long o, n, t, z; + long n, t, z; + s8 o; + o = this_cpu_read(*p); do { z = 0; /* overflow to zone counters */ @@ -576,8 +578,7 @@ static inline void mod_zone_state(struct zone *zone, */ t = this_cpu_read(pcp->stat_threshold); - o = this_cpu_read(*p); - n = delta + o; + n = delta + (long)o; if (abs(n) > t) { int os = overstep_mode * (t >> 1) ; @@ -586,7 +587,7 @@ static inline void mod_zone_state(struct zone *zone, z = n + os; n = -os; } - } while (this_cpu_cmpxchg(*p, o, n) != o); + } while (!this_cpu_try_cmpxchg(*p, &o, n)); if (z) zone_page_state_add(z, zone, item); @@ -616,7 +617,8 @@ static inline void mod_node_state(struct pglist_data *pgdat, { struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats; s8 __percpu *p = pcp->vm_node_stat_diff + item; - long o, n, t, z; + long n, t, z; + s8 o; if (vmstat_item_in_bytes(item)) { /* @@ -629,6 +631,7 @@ static inline void mod_node_state(struct pglist_data *pgdat, delta >>= PAGE_SHIFT; } + o = this_cpu_read(*p); do { z = 0; /* overflow to node counters */ @@ -644,8 +647,7 @@ static inline void mod_node_state(struct pglist_data *pgdat, */ t = this_cpu_read(pcp->stat_threshold); - o = this_cpu_read(*p); - n = delta + o; + n = delta + (long)o; if (abs(n) > t) { int os = overstep_mode * (t >> 1) ; @@ -654,7 +656,7 @@ static inline void mod_node_state(struct pglist_data *pgdat, z = n + os; n = -os; } - } while (this_cpu_cmpxchg(*p, o, n) != o); + } while (!this_cpu_try_cmpxchg(*p, &o, n)); if (z) node_page_state_add(z, pgdat, item); diff --git a/mm/workingset.c b/mm/workingset.c index da58a26d0d4d..b192e44a0e7c 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -763,13 +763,6 @@ static unsigned long scan_shadow_nodes(struct shrinker *shrinker, NULL); } -static struct shrinker workingset_shadow_shrinker = { - .count_objects = count_shadow_nodes, - .scan_objects = scan_shadow_nodes, - .seeks = 0, /* ->count reports only fully expendable nodes */ - .flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE, -}; - /* * Our list_lru->lock is IRQ-safe as it nests inside the IRQ-safe * i_pages lock. @@ -778,9 +771,10 @@ static struct lock_class_key shadow_nodes_key; static int __init workingset_init(void) { + struct shrinker *workingset_shadow_shrinker; unsigned int timestamp_bits; unsigned int max_order; - int ret; + int ret = -ENOMEM; BUILD_BUG_ON(BITS_PER_LONG < EVICTION_SHIFT); /* @@ -797,17 +791,26 @@ static int __init workingset_init(void) pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n", timestamp_bits, max_order, bucket_order); - ret = prealloc_shrinker(&workingset_shadow_shrinker, "mm-shadow"); - if (ret) + workingset_shadow_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE | + SHRINKER_MEMCG_AWARE, + "mm-shadow"); + if (!workingset_shadow_shrinker) goto err; + ret = __list_lru_init(&shadow_nodes, true, &shadow_nodes_key, - &workingset_shadow_shrinker); + workingset_shadow_shrinker); if (ret) goto err_list_lru; - register_shrinker_prepared(&workingset_shadow_shrinker); + + workingset_shadow_shrinker->count_objects = count_shadow_nodes; + workingset_shadow_shrinker->scan_objects = scan_shadow_nodes; + /* ->count reports only fully expendable nodes */ + workingset_shadow_shrinker->seeks = 0; + + shrinker_register(workingset_shadow_shrinker); return 0; err_list_lru: - free_prealloced_shrinker(&workingset_shadow_shrinker); + shrinker_free(workingset_shadow_shrinker); err: return ret; } diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index b58f957429f0..c743ce7a5f49 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -229,7 +229,7 @@ struct zs_pool { struct zs_pool_stats stats; /* Compact classes */ - struct shrinker shrinker; + struct shrinker *shrinker; #ifdef CONFIG_ZSMALLOC_STAT struct dentry *stat_dentry; @@ -2086,8 +2086,7 @@ static unsigned long zs_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) { unsigned long pages_freed; - struct zs_pool *pool = container_of(shrinker, struct zs_pool, - shrinker); + struct zs_pool *pool = shrinker->private_data; /* * Compact classes and calculate compaction delta. @@ -2105,8 +2104,7 @@ static unsigned long zs_shrinker_count(struct shrinker *shrinker, int i; struct size_class *class; unsigned long pages_to_free = 0; - struct zs_pool *pool = container_of(shrinker, struct zs_pool, - shrinker); + struct zs_pool *pool = shrinker->private_data; for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) { class = pool->size_class[i]; @@ -2121,18 +2119,23 @@ static unsigned long zs_shrinker_count(struct shrinker *shrinker, static void zs_unregister_shrinker(struct zs_pool *pool) { - unregister_shrinker(&pool->shrinker); + shrinker_free(pool->shrinker); } static int zs_register_shrinker(struct zs_pool *pool) { - pool->shrinker.scan_objects = zs_shrinker_scan; - pool->shrinker.count_objects = zs_shrinker_count; - pool->shrinker.batch = 0; - pool->shrinker.seeks = DEFAULT_SEEKS; + pool->shrinker = shrinker_alloc(0, "mm-zspool:%s", pool->name); + if (!pool->shrinker) + return -ENOMEM; + + pool->shrinker->scan_objects = zs_shrinker_scan; + pool->shrinker->count_objects = zs_shrinker_count; + pool->shrinker->batch = 0; + pool->shrinker->private_data = pool; - return register_shrinker(&pool->shrinker, "mm-zspool:%s", - pool->name); + shrinker_register(pool->shrinker); + + return 0; } static int calculate_zspage_chain_size(int class_size) diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 2f16f9d17966..c9c270eececc 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -861,11 +861,7 @@ rpcauth_uptodatecred(struct rpc_task *task) test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) != 0; } -static struct shrinker rpc_cred_shrinker = { - .count_objects = rpcauth_cache_shrink_count, - .scan_objects = rpcauth_cache_shrink_scan, - .seeks = DEFAULT_SEEKS, -}; +static struct shrinker *rpc_cred_shrinker; int __init rpcauth_init_module(void) { @@ -874,9 +870,17 @@ int __init rpcauth_init_module(void) err = rpc_init_authunix(); if (err < 0) goto out1; - err = register_shrinker(&rpc_cred_shrinker, "sunrpc_cred"); - if (err < 0) + rpc_cred_shrinker = shrinker_alloc(0, "sunrpc_cred"); + if (!rpc_cred_shrinker) { + err = -ENOMEM; goto out2; + } + + rpc_cred_shrinker->count_objects = rpcauth_cache_shrink_count; + rpc_cred_shrinker->scan_objects = rpcauth_cache_shrink_scan; + + shrinker_register(rpc_cred_shrinker); + return 0; out2: rpc_destroy_authunix(); @@ -887,5 +891,5 @@ out1: void rpcauth_remove_module(void) { rpc_destroy_authunix(); - unregister_shrinker(&rpc_cred_shrinker); + shrinker_free(rpc_cred_shrinker); } diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 3c36aeade991..370ed14b1ae0 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -283,7 +283,8 @@ struct prctl_mm_map { /* Memory deny write / execute */ #define PR_SET_MDWE 65 -# define PR_MDWE_REFUSE_EXEC_GAIN 1 +# define PR_MDWE_REFUSE_EXEC_GAIN (1UL << 0) +# define PR_MDWE_NO_INHERIT (1UL << 1) #define PR_GET_MDWE 66 diff --git a/tools/testing/selftests/damon/sysfs.sh b/tools/testing/selftests/damon/sysfs.sh index 60a9a305aef0..56f0230a8b92 100644 --- a/tools/testing/selftests/damon/sysfs.sh +++ b/tools/testing/selftests/damon/sysfs.sh @@ -175,6 +175,7 @@ test_scheme() ensure_dir "$scheme_dir" "exist" ensure_file "$scheme_dir/action" "exist" "600" test_access_pattern "$scheme_dir/access_pattern" + ensure_file "$scheme_dir/apply_interval_us" "exist" "600" test_quotas "$scheme_dir/quotas" test_watermarks "$scheme_dir/watermarks" test_filters "$scheme_dir/filters" diff --git a/tools/testing/selftests/mm/gup_longterm.c b/tools/testing/selftests/mm/gup_longterm.c index d33d3e68ffab..ad168d35b23b 100644 --- a/tools/testing/selftests/mm/gup_longterm.c +++ b/tools/testing/selftests/mm/gup_longterm.c @@ -265,10 +265,11 @@ static void run_with_tmpfile(test_fn fn, const char *desc) fd = fileno(file); if (fd < 0) { ksft_test_result_fail("fileno() failed\n"); - return; + goto close; } fn(fd, pagesize); +close: fclose(file); } diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c index 901e950f9138..fbff0dd09191 100644 --- a/tools/testing/selftests/mm/ksm_functional_tests.c +++ b/tools/testing/selftests/mm/ksm_functional_tests.c @@ -26,6 +26,7 @@ #define KiB 1024u #define MiB (1024 * KiB) +#define FORK_EXEC_CHILD_PRG_NAME "ksm_fork_exec_child" static int mem_fd; static int ksm_fd; @@ -479,6 +480,64 @@ static void test_prctl_fork(void) ksft_test_result_pass("PR_SET_MEMORY_MERGE value is inherited\n"); } +static int ksm_fork_exec_child(void) +{ + /* Test if KSM is enabled for the process. */ + return prctl(PR_GET_MEMORY_MERGE, 0, 0, 0, 0) == 1; +} + +static void test_prctl_fork_exec(void) +{ + int ret, status; + pid_t child_pid; + + ksft_print_msg("[RUN] %s\n", __func__); + + ret = prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0); + if (ret < 0 && errno == EINVAL) { + ksft_test_result_skip("PR_SET_MEMORY_MERGE not supported\n"); + return; + } else if (ret) { + ksft_test_result_fail("PR_SET_MEMORY_MERGE=1 failed\n"); + return; + } + + child_pid = fork(); + if (child_pid == -1) { + ksft_test_result_skip("fork() failed\n"); + return; + } else if (child_pid == 0) { + char *prg_name = "./ksm_functional_tests"; + char *argv_for_program[] = { prg_name, FORK_EXEC_CHILD_PRG_NAME }; + + execv(prg_name, argv_for_program); + return; + } + + if (waitpid(child_pid, &status, 0) > 0) { + if (WIFEXITED(status)) { + status = WEXITSTATUS(status); + if (status) { + ksft_test_result_fail("KSM not enabled\n"); + return; + } + } else { + ksft_test_result_fail("program didn't terminate normally\n"); + return; + } + } else { + ksft_test_result_fail("waitpid() failed\n"); + return; + } + + if (prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0)) { + ksft_test_result_fail("PR_SET_MEMORY_MERGE=0 failed\n"); + return; + } + + ksft_test_result_pass("PR_SET_MEMORY_MERGE value is inherited\n"); +} + static void test_prctl_unmerge(void) { const unsigned int size = 2 * MiB; @@ -536,9 +595,13 @@ unmap: int main(int argc, char **argv) { - unsigned int tests = 7; + unsigned int tests = 8; int err; + if (argc > 1 && !strcmp(argv[1], FORK_EXEC_CHILD_PRG_NAME)) { + exit(ksm_fork_exec_child() == 1 ? 0 : 1); + } + #ifdef __NR_userfaultfd tests++; #endif @@ -576,6 +639,7 @@ int main(int argc, char **argv) test_prctl(); test_prctl_fork(); + test_prctl_fork_exec(); test_prctl_unmerge(); err = ksft_get_fail_cnt(); diff --git a/tools/testing/selftests/mm/mdwe_test.c b/tools/testing/selftests/mm/mdwe_test.c index bc91bef5d254..200bedcdc32e 100644 --- a/tools/testing/selftests/mm/mdwe_test.c +++ b/tools/testing/selftests/mm/mdwe_test.c @@ -22,15 +22,104 @@ TEST(prctl_flags) { + EXPECT_LT(prctl(PR_SET_MDWE, PR_MDWE_NO_INHERIT, 0L, 0L, 7L), 0); + EXPECT_EQ(errno, EINVAL); + EXPECT_LT(prctl(PR_SET_MDWE, 7L, 0L, 0L, 0L), 0); + EXPECT_EQ(errno, EINVAL); EXPECT_LT(prctl(PR_SET_MDWE, 0L, 7L, 0L, 0L), 0); + EXPECT_EQ(errno, EINVAL); EXPECT_LT(prctl(PR_SET_MDWE, 0L, 0L, 7L, 0L), 0); + EXPECT_EQ(errno, EINVAL); EXPECT_LT(prctl(PR_SET_MDWE, 0L, 0L, 0L, 7L), 0); + EXPECT_EQ(errno, EINVAL); EXPECT_LT(prctl(PR_GET_MDWE, 7L, 0L, 0L, 0L), 0); + EXPECT_EQ(errno, EINVAL); EXPECT_LT(prctl(PR_GET_MDWE, 0L, 7L, 0L, 0L), 0); + EXPECT_EQ(errno, EINVAL); EXPECT_LT(prctl(PR_GET_MDWE, 0L, 0L, 7L, 0L), 0); + EXPECT_EQ(errno, EINVAL); EXPECT_LT(prctl(PR_GET_MDWE, 0L, 0L, 0L, 7L), 0); + EXPECT_EQ(errno, EINVAL); +} + +FIXTURE(consecutive_prctl_flags) {}; +FIXTURE_SETUP(consecutive_prctl_flags) {} +FIXTURE_TEARDOWN(consecutive_prctl_flags) {} + +FIXTURE_VARIANT(consecutive_prctl_flags) +{ + unsigned long first_flags; + unsigned long second_flags; + bool should_work; +}; + +FIXTURE_VARIANT_ADD(consecutive_prctl_flags, can_keep_no_flags) +{ + .first_flags = 0, + .second_flags = 0, + .should_work = true, +}; + +FIXTURE_VARIANT_ADD(consecutive_prctl_flags, can_keep_exec_gain) +{ + .first_flags = PR_MDWE_REFUSE_EXEC_GAIN, + .second_flags = PR_MDWE_REFUSE_EXEC_GAIN, + .should_work = true, +}; + +FIXTURE_VARIANT_ADD(consecutive_prctl_flags, can_keep_both_flags) +{ + .first_flags = PR_MDWE_REFUSE_EXEC_GAIN | PR_MDWE_NO_INHERIT, + .second_flags = PR_MDWE_REFUSE_EXEC_GAIN | PR_MDWE_NO_INHERIT, + .should_work = true, +}; + +FIXTURE_VARIANT_ADD(consecutive_prctl_flags, cant_disable_mdwe) +{ + .first_flags = PR_MDWE_REFUSE_EXEC_GAIN, + .second_flags = 0, + .should_work = false, +}; + +FIXTURE_VARIANT_ADD(consecutive_prctl_flags, cant_disable_mdwe_no_inherit) +{ + .first_flags = PR_MDWE_REFUSE_EXEC_GAIN | PR_MDWE_NO_INHERIT, + .second_flags = 0, + .should_work = false, +}; + +FIXTURE_VARIANT_ADD(consecutive_prctl_flags, cant_disable_no_inherit) +{ + .first_flags = PR_MDWE_REFUSE_EXEC_GAIN | PR_MDWE_NO_INHERIT, + .second_flags = PR_MDWE_REFUSE_EXEC_GAIN, + .should_work = false, +}; + +FIXTURE_VARIANT_ADD(consecutive_prctl_flags, cant_enable_no_inherit) +{ + .first_flags = PR_MDWE_REFUSE_EXEC_GAIN, + .second_flags = PR_MDWE_REFUSE_EXEC_GAIN | PR_MDWE_NO_INHERIT, + .should_work = false, +}; + +TEST_F(consecutive_prctl_flags, two_prctls) +{ + int ret; + + EXPECT_EQ(prctl(PR_SET_MDWE, variant->first_flags, 0L, 0L, 0L), 0); + + ret = prctl(PR_SET_MDWE, variant->second_flags, 0L, 0L, 0L); + if (variant->should_work) { + EXPECT_EQ(ret, 0); + + ret = prctl(PR_GET_MDWE, 0L, 0L, 0L, 0L); + ASSERT_EQ(ret, variant->second_flags); + } else { + EXPECT_NE(ret, 0); + ASSERT_EQ(errno, EPERM); + } } FIXTURE(mdwe) @@ -45,28 +134,45 @@ FIXTURE_VARIANT(mdwe) { bool enabled; bool forked; + bool inherit; }; FIXTURE_VARIANT_ADD(mdwe, stock) { - .enabled = false, + .enabled = false, .forked = false, + .inherit = false, }; FIXTURE_VARIANT_ADD(mdwe, enabled) { - .enabled = true, + .enabled = true, .forked = false, + .inherit = true, +}; + +FIXTURE_VARIANT_ADD(mdwe, inherited) +{ + .enabled = true, + .forked = true, + .inherit = true, }; -FIXTURE_VARIANT_ADD(mdwe, forked) +FIXTURE_VARIANT_ADD(mdwe, not_inherited) { - .enabled = true, + .enabled = true, .forked = true, + .inherit = false, }; +static bool executable_map_should_fail(const FIXTURE_VARIANT(mdwe) *variant) +{ + return variant->enabled && (!variant->forked || variant->inherit); +} + FIXTURE_SETUP(mdwe) { + unsigned long mdwe_flags; int ret, status; self->p = NULL; @@ -76,13 +182,17 @@ FIXTURE_SETUP(mdwe) if (!variant->enabled) return; - ret = prctl(PR_SET_MDWE, PR_MDWE_REFUSE_EXEC_GAIN, 0L, 0L, 0L); + mdwe_flags = PR_MDWE_REFUSE_EXEC_GAIN; + if (!variant->inherit) + mdwe_flags |= PR_MDWE_NO_INHERIT; + + ret = prctl(PR_SET_MDWE, mdwe_flags, 0L, 0L, 0L); ASSERT_EQ(ret, 0) { TH_LOG("PR_SET_MDWE failed or unsupported"); } ret = prctl(PR_GET_MDWE, 0L, 0L, 0L, 0L); - ASSERT_EQ(ret, 1); + ASSERT_EQ(ret, mdwe_flags); if (variant->forked) { self->pid = fork(); @@ -113,7 +223,7 @@ TEST_F(mdwe, mmap_READ_EXEC) TEST_F(mdwe, mmap_WRITE_EXEC) { self->p = mmap(NULL, self->size, PROT_WRITE | PROT_EXEC, self->flags, 0, 0); - if (variant->enabled) { + if (executable_map_should_fail(variant)) { EXPECT_EQ(self->p, MAP_FAILED); } else { EXPECT_NE(self->p, MAP_FAILED); @@ -139,7 +249,7 @@ TEST_F(mdwe, mprotect_add_EXEC) ASSERT_NE(self->p, MAP_FAILED); ret = mprotect(self->p, self->size, PROT_READ | PROT_EXEC); - if (variant->enabled) { + if (executable_map_should_fail(variant)) { EXPECT_LT(ret, 0); } else { EXPECT_EQ(ret, 0); @@ -154,7 +264,7 @@ TEST_F(mdwe, mprotect_WRITE_EXEC) ASSERT_NE(self->p, MAP_FAILED); ret = mprotect(self->p, self->size, PROT_WRITE | PROT_EXEC); - if (variant->enabled) { + if (executable_map_should_fail(variant)) { EXPECT_LT(ret, 0); } else { EXPECT_EQ(ret, 0); @@ -168,13 +278,10 @@ TEST_F(mdwe, mmap_FIXED) self->p = mmap(NULL, self->size, PROT_READ, self->flags, 0, 0); ASSERT_NE(self->p, MAP_FAILED); - p = mmap(self->p + self->size, self->size, PROT_READ | PROT_EXEC, + /* MAP_FIXED unmaps the existing page before mapping which is allowed */ + p = mmap(self->p, self->size, PROT_READ | PROT_EXEC, self->flags | MAP_FIXED, 0, 0); - if (variant->enabled) { - EXPECT_EQ(p, MAP_FAILED); - } else { - EXPECT_EQ(p, self->p); - } + EXPECT_EQ(p, self->p); } TEST_F(mdwe, arm64_BTI) diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c index 5c3773de9f0f..1f836e670a37 100644 --- a/tools/testing/selftests/mm/mremap_test.c +++ b/tools/testing/selftests/mm/mremap_test.c @@ -23,12 +23,15 @@ #define VALIDATION_NO_THRESHOLD 0 /* Verify the entire region */ #define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) +#define SIZE_MB(m) ((size_t)m * (1024 * 1024)) +#define SIZE_KB(k) ((size_t)k * 1024) struct config { unsigned long long src_alignment; unsigned long long dest_alignment; unsigned long long region_size; int overlapping; + int dest_preamble_size; }; struct test { @@ -44,6 +47,7 @@ enum { _1MB = 1ULL << 20, _2MB = 2ULL << 20, _4MB = 4ULL << 20, + _5MB = 5ULL << 20, _1GB = 1ULL << 30, _2GB = 2ULL << 30, PMD = _2MB, @@ -146,6 +150,60 @@ static bool is_range_mapped(FILE *maps_fp, void *start, void *end) } /* + * Returns the start address of the mapping on success, else returns + * NULL on failure. + */ +static void *get_source_mapping(struct config c) +{ + unsigned long long addr = 0ULL; + void *src_addr = NULL; + unsigned long long mmap_min_addr; + + mmap_min_addr = get_mmap_min_addr(); + /* + * For some tests, we need to not have any mappings below the + * source mapping. Add some headroom to mmap_min_addr for this. + */ + mmap_min_addr += 10 * _4MB; + +retry: + addr += c.src_alignment; + if (addr < mmap_min_addr) + goto retry; + + src_addr = mmap((void *) addr, c.region_size, PROT_READ | PROT_WRITE, + MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, + -1, 0); + if (src_addr == MAP_FAILED) { + if (errno == EPERM || errno == EEXIST) + goto retry; + goto error; + } + /* + * Check that the address is aligned to the specified alignment. + * Addresses which have alignments that are multiples of that + * specified are not considered valid. For instance, 1GB address is + * 2MB-aligned, however it will not be considered valid for a + * requested alignment of 2MB. This is done to reduce coincidental + * alignment in the tests. + */ + if (((unsigned long long) src_addr & (c.src_alignment - 1)) || + !((unsigned long long) src_addr & c.src_alignment)) { + munmap(src_addr, c.region_size); + goto retry; + } + + if (!src_addr) + goto error; + + return src_addr; +error: + ksft_print_msg("Failed to map source region: %s\n", + strerror(errno)); + return NULL; +} + +/* * This test validates that merge is called when expanding a mapping. * Mapping containing three pages is created, middle page is unmapped * and then the mapping containing the first page is expanded so that @@ -225,59 +283,83 @@ out: } /* - * Returns the start address of the mapping on success, else returns - * NULL on failure. + * Verify that an mremap within a range does not cause corruption + * of unrelated part of range. + * + * Consider the following range which is 2MB aligned and is + * a part of a larger 20MB range which is not shown. Each + * character is 256KB below making the source and destination + * 2MB each. The lower case letters are moved (s to d) and the + * upper case letters are not moved. The below test verifies + * that the upper case S letters are not corrupted by the + * adjacent mremap. + * + * |DDDDddddSSSSssss| */ -static void *get_source_mapping(struct config c) +static void mremap_move_within_range(char pattern_seed) { - unsigned long long addr = 0ULL; - void *src_addr = NULL; - unsigned long long mmap_min_addr; + char *test_name = "mremap mremap move within range"; + void *src, *dest; + int i, success = 1; + + size_t size = SIZE_MB(20); + void *ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (ptr == MAP_FAILED) { + perror("mmap"); + success = 0; + goto out; + } + memset(ptr, 0, size); - mmap_min_addr = get_mmap_min_addr(); + src = ptr + SIZE_MB(6); + src = (void *)((unsigned long)src & ~(SIZE_MB(2) - 1)); -retry: - addr += c.src_alignment; - if (addr < mmap_min_addr) - goto retry; + /* Set byte pattern for source block. */ + srand(pattern_seed); + for (i = 0; i < SIZE_MB(2); i++) { + ((char *)src)[i] = (char) rand(); + } - src_addr = mmap((void *) addr, c.region_size, PROT_READ | PROT_WRITE, - MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, - -1, 0); - if (src_addr == MAP_FAILED) { - if (errno == EPERM || errno == EEXIST) - goto retry; - goto error; + dest = src - SIZE_MB(2); + + void *new_ptr = mremap(src + SIZE_MB(1), SIZE_MB(1), SIZE_MB(1), + MREMAP_MAYMOVE | MREMAP_FIXED, dest + SIZE_MB(1)); + if (new_ptr == MAP_FAILED) { + perror("mremap"); + success = 0; + goto out; } - /* - * Check that the address is aligned to the specified alignment. - * Addresses which have alignments that are multiples of that - * specified are not considered valid. For instance, 1GB address is - * 2MB-aligned, however it will not be considered valid for a - * requested alignment of 2MB. This is done to reduce coincidental - * alignment in the tests. - */ - if (((unsigned long long) src_addr & (c.src_alignment - 1)) || - !((unsigned long long) src_addr & c.src_alignment)) { - munmap(src_addr, c.region_size); - goto retry; + + /* Verify byte pattern after remapping */ + srand(pattern_seed); + for (i = 0; i < SIZE_MB(1); i++) { + char c = (char) rand(); + + if (((char *)src)[i] != c) { + ksft_print_msg("Data at src at %d got corrupted due to unrelated mremap\n", + i); + ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff, + ((char *) src)[i] & 0xff); + success = 0; + } } - if (!src_addr) - goto error; +out: + if (munmap(ptr, size) == -1) + perror("munmap"); - return src_addr; -error: - ksft_print_msg("Failed to map source region: %s\n", - strerror(errno)); - return NULL; + if (success) + ksft_test_result_pass("%s\n", test_name); + else + ksft_test_result_fail("%s\n", test_name); } /* Returns the time taken for the remap on success else returns -1. */ static long long remap_region(struct config c, unsigned int threshold_mb, char pattern_seed) { - void *addr, *src_addr, *dest_addr; + void *addr, *src_addr, *dest_addr, *dest_preamble_addr; unsigned long long i; struct timespec t_start = {0, 0}, t_end = {0, 0}; long long start_ns, end_ns, align_mask, ret, offset; @@ -294,7 +376,7 @@ static long long remap_region(struct config c, unsigned int threshold_mb, goto out; } - /* Set byte pattern */ + /* Set byte pattern for source block. */ srand(pattern_seed); for (i = 0; i < threshold; i++) memset((char *) src_addr + i, (char) rand(), 1); @@ -306,6 +388,9 @@ static long long remap_region(struct config c, unsigned int threshold_mb, addr = (void *) (((unsigned long long) src_addr + c.region_size + offset) & align_mask); + /* Remap after the destination block preamble. */ + addr += c.dest_preamble_size; + /* See comment in get_source_mapping() */ if (!((unsigned long long) addr & c.dest_alignment)) addr = (void *) ((unsigned long long) addr | c.dest_alignment); @@ -316,11 +401,29 @@ static long long remap_region(struct config c, unsigned int threshold_mb, if (addr + c.dest_alignment < addr) { ksft_print_msg("Couldn't find a valid region to remap to\n"); ret = -1; - goto out; + goto clean_up_src; } addr += c.dest_alignment; } + if (c.dest_preamble_size) { + dest_preamble_addr = mmap((void *) addr - c.dest_preamble_size, c.dest_preamble_size, + PROT_READ | PROT_WRITE, + MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, + -1, 0); + if (dest_preamble_addr == MAP_FAILED) { + ksft_print_msg("Failed to map dest preamble region: %s\n", + strerror(errno)); + ret = -1; + goto clean_up_src; + } + + /* Set byte pattern for the dest preamble block. */ + srand(pattern_seed); + for (i = 0; i < c.dest_preamble_size; i++) + memset((char *) dest_preamble_addr + i, (char) rand(), 1); + } + clock_gettime(CLOCK_MONOTONIC, &t_start); dest_addr = mremap(src_addr, c.region_size, c.region_size, MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr); @@ -329,7 +432,7 @@ static long long remap_region(struct config c, unsigned int threshold_mb, if (dest_addr == MAP_FAILED) { ksft_print_msg("mremap failed: %s\n", strerror(errno)); ret = -1; - goto clean_up_src; + goto clean_up_dest_preamble; } /* Verify byte pattern after remapping */ @@ -347,6 +450,23 @@ static long long remap_region(struct config c, unsigned int threshold_mb, } } + /* Verify the dest preamble byte pattern after remapping */ + if (c.dest_preamble_size) { + srand(pattern_seed); + for (i = 0; i < c.dest_preamble_size; i++) { + char c = (char) rand(); + + if (((char *) dest_preamble_addr)[i] != c) { + ksft_print_msg("Preamble data after remap doesn't match at offset %d\n", + i); + ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff, + ((char *) dest_preamble_addr)[i] & 0xff); + ret = -1; + goto clean_up_dest; + } + } + } + start_ns = t_start.tv_sec * NS_PER_SEC + t_start.tv_nsec; end_ns = t_end.tv_sec * NS_PER_SEC + t_end.tv_nsec; ret = end_ns - start_ns; @@ -359,12 +479,92 @@ static long long remap_region(struct config c, unsigned int threshold_mb, */ clean_up_dest: munmap(dest_addr, c.region_size); +clean_up_dest_preamble: + if (c.dest_preamble_size && dest_preamble_addr) + munmap(dest_preamble_addr, c.dest_preamble_size); clean_up_src: munmap(src_addr, c.region_size); out: return ret; } +/* + * Verify that an mremap aligning down does not destroy + * the beginning of the mapping just because the aligned + * down address landed on a mapping that maybe does not exist. + */ +static void mremap_move_1mb_from_start(char pattern_seed) +{ + char *test_name = "mremap move 1mb from start at 1MB+256KB aligned src"; + void *src = NULL, *dest = NULL; + int i, success = 1; + + /* Config to reuse get_source_mapping() to do an aligned mmap. */ + struct config c = { + .src_alignment = SIZE_MB(1) + SIZE_KB(256), + .region_size = SIZE_MB(6) + }; + + src = get_source_mapping(c); + if (!src) { + success = 0; + goto out; + } + + c.src_alignment = SIZE_MB(1) + SIZE_KB(256); + dest = get_source_mapping(c); + if (!dest) { + success = 0; + goto out; + } + + /* Set byte pattern for source block. */ + srand(pattern_seed); + for (i = 0; i < SIZE_MB(2); i++) { + ((char *)src)[i] = (char) rand(); + } + + /* + * Unmap the beginning of dest so that the aligned address + * falls on no mapping. + */ + munmap(dest, SIZE_MB(1)); + + void *new_ptr = mremap(src + SIZE_MB(1), SIZE_MB(1), SIZE_MB(1), + MREMAP_MAYMOVE | MREMAP_FIXED, dest + SIZE_MB(1)); + if (new_ptr == MAP_FAILED) { + perror("mremap"); + success = 0; + goto out; + } + + /* Verify byte pattern after remapping */ + srand(pattern_seed); + for (i = 0; i < SIZE_MB(1); i++) { + char c = (char) rand(); + + if (((char *)src)[i] != c) { + ksft_print_msg("Data at src at %d got corrupted due to unrelated mremap\n", + i); + ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff, + ((char *) src)[i] & 0xff); + success = 0; + } + } + +out: + if (src && munmap(src, c.region_size) == -1) + perror("munmap src"); + + if (dest && munmap(dest, c.region_size) == -1) + perror("munmap dest"); + + if (success) + ksft_test_result_pass("%s\n", test_name); + else + ksft_test_result_fail("%s\n", test_name); +} + static void run_mremap_test_case(struct test test_case, int *failures, unsigned int threshold_mb, unsigned int pattern_seed) @@ -434,7 +634,7 @@ static int parse_args(int argc, char **argv, unsigned int *threshold_mb, return 0; } -#define MAX_TEST 13 +#define MAX_TEST 15 #define MAX_PERF_TEST 3 int main(int argc, char **argv) { @@ -443,7 +643,8 @@ int main(int argc, char **argv) unsigned int threshold_mb = VALIDATION_DEFAULT_THRESHOLD; unsigned int pattern_seed; int num_expand_tests = 2; - struct test test_cases[MAX_TEST]; + int num_misc_tests = 2; + struct test test_cases[MAX_TEST] = {}; struct test perf_test_cases[MAX_PERF_TEST]; int page_size; time_t t; @@ -500,6 +701,15 @@ int main(int argc, char **argv) test_cases[12] = MAKE_TEST(PUD, PUD, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS, "2GB mremap - Source PUD-aligned, Destination PUD-aligned"); + /* Src and Dest addr 1MB aligned. 5MB mremap. */ + test_cases[13] = MAKE_TEST(_1MB, _1MB, _5MB, NON_OVERLAPPING, EXPECT_SUCCESS, + "5MB mremap - Source 1MB-aligned, Destination 1MB-aligned"); + + /* Src and Dest addr 1MB aligned. 5MB mremap. */ + test_cases[14] = MAKE_TEST(_1MB, _1MB, _5MB, NON_OVERLAPPING, EXPECT_SUCCESS, + "5MB mremap - Source 1MB-aligned, Dest 1MB-aligned with 40MB Preamble"); + test_cases[14].config.dest_preamble_size = 10 * _4MB; + perf_test_cases[0] = MAKE_TEST(page_size, page_size, _1GB, NON_OVERLAPPING, EXPECT_SUCCESS, "1GB mremap - Source PTE-aligned, Destination PTE-aligned"); /* @@ -515,7 +725,7 @@ int main(int argc, char **argv) (threshold_mb * _1MB >= _1GB); ksft_set_plan(ARRAY_SIZE(test_cases) + (run_perf_tests ? - ARRAY_SIZE(perf_test_cases) : 0) + num_expand_tests); + ARRAY_SIZE(perf_test_cases) : 0) + num_expand_tests + num_misc_tests); for (i = 0; i < ARRAY_SIZE(test_cases); i++) run_mremap_test_case(test_cases[i], &failures, threshold_mb, @@ -533,6 +743,9 @@ int main(int argc, char **argv) fclose(maps_fp); + mremap_move_within_range(pattern_seed); + mremap_move_1mb_from_start(pattern_seed); + if (run_perf_tests) { ksft_print_msg("\n%s\n", "mremap HAVE_MOVE_PMD/PUD optimization time comparison for 1GB region:"); |