From 8587ca6f34152ea650bad4b2db68456601159024 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 5 Nov 2021 13:35:07 -0700 Subject: mm: move kvmalloc-related functions to slab.h Not all files in the kernel should include mm.h. Migrating callers from kmalloc to kvmalloc is easier if the kvmalloc functions are in slab.h. [akpm@linux-foundation.org: move the new kvrealloc() also] [akpm@linux-foundation.org: drivers/hwmon/occ/p9_sbe.c needs slab.h] Link: https://lkml.kernel.org/r/20210622215757.3525604-1-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Pekka Enberg Cc: Christoph Lameter Cc: David Rientjes Cc: Joonsoo Kim Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 34 ---------------------------------- include/linux/slab.h | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 34 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 73a52aba448f..32b2ecc47408 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -799,40 +799,6 @@ static inline int is_vmalloc_or_module_addr(const void *x) } #endif -extern void *kvmalloc_node(size_t size, gfp_t flags, int node); -static inline void *kvmalloc(size_t size, gfp_t flags) -{ - return kvmalloc_node(size, flags, NUMA_NO_NODE); -} -static inline void *kvzalloc_node(size_t size, gfp_t flags, int node) -{ - return kvmalloc_node(size, flags | __GFP_ZERO, node); -} -static inline void *kvzalloc(size_t size, gfp_t flags) -{ - return kvmalloc(size, flags | __GFP_ZERO); -} - -static inline void *kvmalloc_array(size_t n, size_t size, gfp_t flags) -{ - size_t bytes; - - if (unlikely(check_mul_overflow(n, size, &bytes))) - return NULL; - - return kvmalloc(bytes, flags); -} - -static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) -{ - return kvmalloc_array(n, size, flags | __GFP_ZERO); -} - -extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, - gfp_t flags); -extern void kvfree(const void *addr); -extern void kvfree_sensitive(const void *addr, size_t len); - static inline int head_compound_mapcount(struct page *head) { return atomic_read(compound_mapcount_ptr(head)) + 1; diff --git a/include/linux/slab.h b/include/linux/slab.h index 083f3ce550bc..c0d46b6fa12a 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -732,6 +732,40 @@ static inline void *kzalloc_node(size_t size, gfp_t flags, int node) return kmalloc_node(size, flags | __GFP_ZERO, node); } +extern void *kvmalloc_node(size_t size, gfp_t flags, int node); +static inline void *kvmalloc(size_t size, gfp_t flags) +{ + return kvmalloc_node(size, flags, NUMA_NO_NODE); +} +static inline void *kvzalloc_node(size_t size, gfp_t flags, int node) +{ + return kvmalloc_node(size, flags | __GFP_ZERO, node); +} +static inline void *kvzalloc(size_t size, gfp_t flags) +{ + return kvmalloc(size, flags | __GFP_ZERO); +} + +static inline void *kvmalloc_array(size_t n, size_t size, gfp_t flags) +{ + size_t bytes; + + if (unlikely(check_mul_overflow(n, size, &bytes))) + return NULL; + + return kvmalloc(bytes, flags); +} + +static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) +{ + return kvmalloc_array(n, size, flags | __GFP_ZERO); +} + +extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, + gfp_t flags); +extern void kvfree(const void *addr); +extern void kvfree_sensitive(const void *addr, size_t len); + unsigned int kmem_cache_size(struct kmem_cache *s); void __init kmem_cache_init_late(void); -- cgit v1.2.3 From b47291ef02b0bee85ffb7efd6c336060ad1fe1a4 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 5 Nov 2021 13:35:17 -0700 Subject: mm, slub: change percpu partial accounting from objects to pages With CONFIG_SLUB_CPU_PARTIAL enabled, SLUB keeps a percpu list of partial slabs that can be promoted to cpu slab when the previous one is depleted, without accessing the shared partial list. A slab can be added to this list by 1) refill of an empty list from get_partial_node() - once we really have to access the shared partial list, we acquire multiple slabs to amortize the cost of locking, and 2) first free to a previously full slab - instead of putting the slab on a shared partial list, we can more cheaply freeze it and put it on the per-cpu list. To control how large a percpu partial list can grow for a kmem cache, set_cpu_partial() calculates a target number of free objects on each cpu's percpu partial list, and this can be also set by the sysfs file cpu_partial. However, the tracking of actual number of objects is imprecise, in order to limit overhead from cpu X freeing an objects to a slab on percpu partial list of cpu Y. Basically, the percpu partial slabs form a single linked list, and when we add a new slab to the list with current head "oldpage", we set in the struct page of the slab we're adding: page->pages = oldpage->pages + 1; // this is precise page->pobjects = oldpage->pobjects + (page->objects - page->inuse); page->next = oldpage; Thus the real number of free objects in the slab (objects - inuse) is only determined at the moment of adding the slab to the percpu partial list, and further freeing doesn't update the pobjects counter nor propagate it to the current list head. As Jann reports [1], this can easily lead to large inaccuracies, where the target number of objects (up to 30 by default) can translate to the same number of (empty) slab pages on the list. In case 2) above, we put a slab with 1 free object on the list, thus only increase page->pobjects by 1, even if there are subsequent frees on the same slab. Jann has noticed this in practice and so did we [2] when investigating significant increase of kmemcg usage after switching from SLAB to SLUB. While this is no longer a problem in kmemcg context thanks to the accounting rewrite in 5.9, the memory waste is still not ideal and it's questionable whether it makes sense to perform free object count based control when object counts can easily become so much inaccurate. So this patch converts the accounting to be based on number of pages only (which is precise) and removes the page->pobjects field completely. This is also ultimately simpler. To retain the existing set_cpu_partial() heuristic, first calculate the target number of objects as previously, but then convert it to target number of pages by assuming the pages will be half-filled on average. This assumption might obviously also be inaccurate in practice, but cannot degrade to actual number of pages being equal to the target number of objects. We could also skip the intermediate step with target number of objects and rewrite the heuristic in terms of pages. However we still have the sysfs file cpu_partial which uses number of objects and could break existing users if it suddenly becomes number of pages, so this patch doesn't do that. In practice, after this patch the heuristics limit the size of percpu partial list up to 2 pages. In case of a reported regression (which would mean some workload has benefited from the previous imprecise object based counting), we can tune the heuristics to get a better compromise within the new scheme, while still avoid the unexpectedly long percpu partial lists. [1] https://lore.kernel.org/linux-mm/CAG48ez2Qx5K1Cab-m8BdSibp6wLTip6ro4=-umR7BLsEgjEYzA@mail.gmail.com/ [2] https://lore.kernel.org/all/2f0f46e8-2535-410a-1859-e9cfa4e57c18@suse.cz/ ========== Evaluation ========== Mel was kind enough to run v1 through mmtests machinery for netperf (localhost) and hackbench and, for most significant results see below. So there are some apparent regressions, especially with hackbench, which I think ultimately boils down to having shorter percpu partial lists on average and some benchmarks benefiting from longer ones. Monitoring slab usage also indicated less memory usage by slab. Based on that, the following patch will bump the defaults to allow longer percpu partial lists than after this patch. However the goal is certainly not such that we would limit the percpu partial lists to 30 pages just because previously a specific alloc/free pattern could lead to the limit of 30 objects translate to a limit to 30 pages - that would make little sense. This is a correctness patch, and if a workload benefits from larger lists, the sysfs tuning knobs are still there to allow that. Netperf 2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads per socket), 384GB RAM TCP-RR: hmean before 127045.79 after 121092.94 (-4.69%, worse) stddev before 2634.37 after 1254.08 UDP-RR: hmean before 166985.45 after 160668.94 ( -3.78%, worse) stddev before 4059.69 after 1943.63 2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads per socket), 512GB RAM TCP-RR: hmean before 84173.25 after 76914.72 ( -8.62%, worse) UDP-RR: hmean before 93571.12 after 96428.69 ( 3.05%, better) stddev before 23118.54 after 16828.14 2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads per socket), 64GB RAM TCP-RR: hmean before 49984.92 after 48922.27 ( -2.13%, worse) stddev before 6248.15 after 4740.51 UDP-RR: hmean before 61854.31 after 68761.81 ( 11.17%, better) stddev before 4093.54 after 5898.91 other machines - within 2% Hackbench (results before and after the patch, negative % means worse) 2-socket AMD EPYC 7713 (64 cores, 128 threads per core), 256GB RAM hackbench-process-sockets Amean 1 0.5380 0.5583 ( -3.78%) Amean 4 0.7510 0.8150 ( -8.52%) Amean 7 0.7930 0.9533 ( -20.22%) Amean 12 0.7853 1.1313 ( -44.06%) Amean 21 1.1520 1.4993 ( -30.15%) Amean 30 1.6223 1.9237 ( -18.57%) Amean 48 2.6767 2.9903 ( -11.72%) Amean 79 4.0257 5.1150 ( -27.06%) Amean 110 5.5193 7.4720 ( -35.38%) Amean 141 7.2207 9.9840 ( -38.27%) Amean 172 8.4770 12.1963 ( -43.88%) Amean 203 9.6473 14.3137 ( -48.37%) Amean 234 11.3960 18.7917 ( -64.90%) Amean 265 13.9627 22.4607 ( -60.86%) Amean 296 14.9163 26.0483 ( -74.63%) hackbench-thread-sockets Amean 1 0.5597 0.5877 ( -5.00%) Amean 4 0.7913 0.8960 ( -13.23%) Amean 7 0.8190 1.0017 ( -22.30%) Amean 12 0.9560 1.1727 ( -22.66%) Amean 21 1.7587 1.5660 ( 10.96%) Amean 30 2.4477 1.9807 ( 19.08%) Amean 48 3.4573 3.0630 ( 11.41%) Amean 79 4.7903 5.1733 ( -8.00%) Amean 110 6.1370 7.4220 ( -20.94%) Amean 141 7.5777 9.2617 ( -22.22%) Amean 172 9.2280 11.0907 ( -20.18%) Amean 203 10.2793 13.3470 ( -29.84%) Amean 234 11.2410 17.1070 ( -52.18%) Amean 265 12.5970 23.3323 ( -85.22%) Amean 296 17.1540 24.2857 ( -41.57%) 2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads per socket), 384GB RAM hackbench-process-sockets Amean 1 0.5760 0.4793 ( 16.78%) Amean 4 0.9430 0.9707 ( -2.93%) Amean 7 1.5517 1.8843 ( -21.44%) Amean 12 2.4903 2.7267 ( -9.49%) Amean 21 3.9560 4.2877 ( -8.38%) Amean 30 5.4613 5.8343 ( -6.83%) Amean 48 8.5337 9.2937 ( -8.91%) Amean 79 14.0670 15.2630 ( -8.50%) Amean 110 19.2253 21.2467 ( -10.51%) Amean 141 23.7557 25.8550 ( -8.84%) Amean 172 28.4407 29.7603 ( -4.64%) Amean 203 33.3407 33.9927 ( -1.96%) Amean 234 38.3633 39.1150 ( -1.96%) Amean 265 43.4420 43.8470 ( -0.93%) Amean 296 48.3680 48.9300 ( -1.16%) hackbench-thread-sockets Amean 1 0.6080 0.6493 ( -6.80%) Amean 4 1.0000 1.0513 ( -5.13%) Amean 7 1.6607 2.0260 ( -22.00%) Amean 12 2.7637 2.9273 ( -5.92%) Amean 21 5.0613 4.5153 ( 10.79%) Amean 30 6.3340 6.1140 ( 3.47%) Amean 48 9.0567 9.5577 ( -5.53%) Amean 79 14.5657 15.7983 ( -8.46%) Amean 110 19.6213 21.6333 ( -10.25%) Amean 141 24.1563 26.2697 ( -8.75%) Amean 172 28.9687 30.2187 ( -4.32%) Amean 203 33.9763 34.6970 ( -2.12%) Amean 234 38.8647 39.3207 ( -1.17%) Amean 265 44.0813 44.1507 ( -0.16%) Amean 296 49.2040 49.4330 ( -0.47%) 2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads per socket), 512GB RAM hackbench-process-sockets Amean 1 0.5027 0.5017 ( 0.20%) Amean 4 1.1053 1.2033 ( -8.87%) Amean 7 1.8760 2.1820 ( -16.31%) Amean 12 2.9053 3.1810 ( -9.49%) Amean 21 4.6777 4.9920 ( -6.72%) Amean 30 6.5180 6.7827 ( -4.06%) Amean 48 10.0710 10.5227 ( -4.48%) Amean 79 16.4250 17.5053 ( -6.58%) Amean 110 22.6203 24.4617 ( -8.14%) Amean 141 28.0967 31.0363 ( -10.46%) Amean 172 34.4030 36.9233 ( -7.33%) Amean 203 40.5933 43.0850 ( -6.14%) Amean 234 46.6477 48.7220 ( -4.45%) Amean 265 53.0530 53.9597 ( -1.71%) Amean 296 59.2760 59.9213 ( -1.09%) hackbench-thread-sockets Amean 1 0.5363 0.5330 ( 0.62%) Amean 4 1.1647 1.2157 ( -4.38%) Amean 7 1.9237 2.2833 ( -18.70%) Amean 12 2.9943 3.3110 ( -10.58%) Amean 21 4.9987 5.1880 ( -3.79%) Amean 30 6.7583 7.0043 ( -3.64%) Amean 48 10.4547 10.8353 ( -3.64%) Amean 79 16.6707 17.6790 ( -6.05%) Amean 110 22.8207 24.4403 ( -7.10%) Amean 141 28.7090 31.0533 ( -8.17%) Amean 172 34.9387 36.8260 ( -5.40%) Amean 203 41.1567 43.0450 ( -4.59%) Amean 234 47.3790 48.5307 ( -2.43%) Amean 265 53.9543 54.6987 ( -1.38%) Amean 296 60.0820 60.2163 ( -0.22%) 1-socket Intel(R) Xeon(R) CPU E3-1240 v5 @ 3.50GHz (4 cores, 8 threads), 32 GB RAM hackbench-process-sockets Amean 1 1.4760 1.5773 ( -6.87%) Amean 3 3.9370 4.0910 ( -3.91%) Amean 5 6.6797 6.9357 ( -3.83%) Amean 7 9.3367 9.7150 ( -4.05%) Amean 12 15.7627 16.1400 ( -2.39%) Amean 18 23.5360 23.6890 ( -0.65%) Amean 24 31.0663 31.3137 ( -0.80%) Amean 30 38.7283 39.0037 ( -0.71%) Amean 32 41.3417 41.6097 ( -0.65%) hackbench-thread-sockets Amean 1 1.5250 1.6043 ( -5.20%) Amean 3 4.0897 4.2603 ( -4.17%) Amean 5 6.7760 7.0933 ( -4.68%) Amean 7 9.4817 9.9157 ( -4.58%) Amean 12 15.9610 16.3937 ( -2.71%) Amean 18 23.9543 24.3417 ( -1.62%) Amean 24 31.4400 31.7217 ( -0.90%) Amean 30 39.2457 39.5467 ( -0.77%) Amean 32 41.8267 42.1230 ( -0.71%) 2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads per socket), 64GB RAM hackbench-process-sockets Amean 1 1.0347 1.0880 ( -5.15%) Amean 4 1.7267 1.8527 ( -7.30%) Amean 7 2.6707 2.8110 ( -5.25%) Amean 12 4.1617 4.3383 ( -4.25%) Amean 21 7.0070 7.2600 ( -3.61%) Amean 30 9.9187 10.2397 ( -3.24%) Amean 48 15.6710 16.3923 ( -4.60%) Amean 79 24.7743 26.1247 ( -5.45%) Amean 110 34.3000 35.9307 ( -4.75%) Amean 141 44.2043 44.8010 ( -1.35%) Amean 172 54.2430 54.7260 ( -0.89%) Amean 192 60.6557 60.9777 ( -0.53%) hackbench-thread-sockets Amean 1 1.0610 1.1353 ( -7.01%) Amean 4 1.7543 1.9140 ( -9.10%) Amean 7 2.7840 2.9573 ( -6.23%) Amean 12 4.3813 4.4937 ( -2.56%) Amean 21 7.3460 7.5350 ( -2.57%) Amean 30 10.2313 10.5190 ( -2.81%) Amean 48 15.9700 16.5940 ( -3.91%) Amean 79 25.3973 26.6637 ( -4.99%) Amean 110 35.1087 36.4797 ( -3.91%) Amean 141 45.8220 46.3053 ( -1.05%) Amean 172 55.4917 55.7320 ( -0.43%) Amean 192 62.7490 62.5410 ( 0.33%) Link: https://lkml.kernel.org/r/20211012134651.11258-1-vbabka@suse.cz Signed-off-by: Vlastimil Babka Reported-by: Jann Horn Cc: Roman Gushchin Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 -- include/linux/slub_def.h | 13 ++----------- 2 files changed, 2 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7f8ee09c711f..68ffa064b7a8 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -124,10 +124,8 @@ struct page { struct page *next; #ifdef CONFIG_64BIT int pages; /* Nr of pages left */ - int pobjects; /* Approximate count */ #else short int pages; - short int pobjects; #endif }; }; diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 85499f0586b0..0fa751b946fa 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -99,6 +99,8 @@ struct kmem_cache { #ifdef CONFIG_SLUB_CPU_PARTIAL /* Number of per cpu partial objects to keep around */ unsigned int cpu_partial; + /* Number of per cpu partial pages to keep around */ + unsigned int cpu_partial_pages; #endif struct kmem_cache_order_objects oo; @@ -141,17 +143,6 @@ struct kmem_cache { struct kmem_cache_node *node[MAX_NUMNODES]; }; -#ifdef CONFIG_SLUB_CPU_PARTIAL -#define slub_cpu_partial(s) ((s)->cpu_partial) -#define slub_set_cpu_partial(s, n) \ -({ \ - slub_cpu_partial(s) = (n); \ -}) -#else -#define slub_cpu_partial(s) (0) -#define slub_set_cpu_partial(s, n) -#endif /* CONFIG_SLUB_CPU_PARTIAL */ - #ifdef CONFIG_SYSFS #define SLAB_SUPPORTS_SYSFS void sysfs_slab_unlink(struct kmem_cache *); -- cgit v1.2.3 From 96c84dde362a3e4ff67a12eaac2ea6e88e963c07 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 5 Nov 2021 13:35:30 -0700 Subject: mm: don't include in Not required at all, and having this causes a huge kernel rebuild as soon as something in dax.h changes. Link: https://lkml.kernel.org/r/20210921082253.1859794-1-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Naoya Horiguchi Reviewed-by: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 4091692bed8c..097bbbb37493 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -8,7 +8,6 @@ #include #include -#include #include #include #include -- cgit v1.2.3 From 7857ccdf94e94f1dd56496b90084fdcaa5e655a4 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:35:33 -0700 Subject: lib/stackdepot: include gfp.h Patch series "stackdepot, kasan, workqueue: Avoid expanding stackdepot slabs when holding raw_spin_lock", v2. Shuah Khan reported [1]: | When CONFIG_PROVE_RAW_LOCK_NESTING=y and CONFIG_KASAN are enabled, | kasan_record_aux_stack() runs into "BUG: Invalid wait context" when | it tries to allocate memory attempting to acquire spinlock in page | allocation code while holding workqueue pool raw_spinlock. | | There are several instances of this problem when block layer tries | to __queue_work(). Call trace from one of these instances is below: | | kblockd_mod_delayed_work_on() | mod_delayed_work_on() | __queue_delayed_work() | __queue_work() (rcu_read_lock, raw_spin_lock pool->lock held) | insert_work() | kasan_record_aux_stack() | kasan_save_stack() | stack_depot_save() | alloc_pages() | __alloc_pages() | get_page_from_freelist() | rm_queue() | rm_queue_pcplist() | local_lock_irqsave(&pagesets.lock, flags); | [ BUG: Invalid wait context triggered ] PROVE_RAW_LOCK_NESTING is pointing out that (on RT kernels) the locking rules are being violated. More generally, memory is being allocated from a non-preemptive context (raw_spin_lock'd c-s) where it is not allowed. To properly fix this, we must prevent stackdepot from replenishing its "stack slab" pool if memory allocations cannot be done in the current context: it's a bug to use either GFP_ATOMIC nor GFP_NOWAIT in certain non-preemptive contexts, including raw_spin_locks (see gfp.h and commit ab00db216c9c7). The only downside is that saving a stack trace may fail if: stackdepot runs out of space AND the same stack trace has not been recorded before. I expect this to be unlikely, and a simple experiment (boot the kernel) didn't result in any failure to record stack trace from insert_work(). The series includes a few minor fixes to stackdepot that I noticed in preparing the series. It then introduces __stack_depot_save(), which exposes the option to force stackdepot to not allocate any memory. Finally, KASAN is changed to use the new stackdepot interface and provide kasan_record_aux_stack_noalloc(), which is then used by workqueue code. [1] https://lkml.kernel.org/r/20210902200134.25603-1-skhan@linuxfoundation.org This patch (of 6): refers to gfp_t, but doesn't include gfp.h. Fix it by including . Link: https://lkml.kernel.org/r/20210913112609.2651084-1-elver@google.com Link: https://lkml.kernel.org/r/20210913112609.2651084-2-elver@google.com Signed-off-by: Marco Elver Tested-by: Shuah Khan Acked-by: Sebastian Andrzej Siewior Reviewed-by: Andrey Konovalov Cc: Tejun Heo Cc: Lai Jiangshan Cc: Walter Wu Cc: Thomas Gleixner Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Vijayanand Jitta Cc: Vinayak Menon Cc: "Gustavo A. R. Silva" Cc: Taras Madan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stackdepot.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 6bb4bc1a5f54..97b36dc53301 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -11,6 +11,8 @@ #ifndef _LINUX_STACKDEPOT_H #define _LINUX_STACKDEPOT_H +#include + typedef u32 depot_stack_handle_t; depot_stack_handle_t stack_depot_save(unsigned long *entries, -- cgit v1.2.3 From 11ac25c62cd2f3bb8da9e1df2e71afdebe76f093 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:35:39 -0700 Subject: lib/stackdepot: introduce __stack_depot_save() Add __stack_depot_save(), which provides more fine-grained control over stackdepot's memory allocation behaviour, in case stackdepot runs out of "stack slabs". Normally stackdepot uses alloc_pages() in case it runs out of space; passing can_alloc==false to __stack_depot_save() prohibits this, at the cost of more likely failure to record a stack trace. Link: https://lkml.kernel.org/r/20210913112609.2651084-4-elver@google.com Signed-off-by: Marco Elver Tested-by: Shuah Khan Acked-by: Sebastian Andrzej Siewior Reviewed-by: Andrey Konovalov Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: "Gustavo A. R. Silva" Cc: Lai Jiangshan Cc: Taras Madan Cc: Tejun Heo Cc: Thomas Gleixner Cc: Vijayanand Jitta Cc: Vinayak Menon Cc: Walter Wu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stackdepot.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 97b36dc53301..b2f7e7c6ba54 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -15,6 +15,10 @@ typedef u32 depot_stack_handle_t; +depot_stack_handle_t __stack_depot_save(unsigned long *entries, + unsigned int nr_entries, + gfp_t gfp_flags, bool can_alloc); + depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int nr_entries, gfp_t gfp_flags); -- cgit v1.2.3 From 7cb3007ce2da27ec02a1a3211941e7fe6875b642 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:35:46 -0700 Subject: kasan: generic: introduce kasan_record_aux_stack_noalloc() Introduce a variant of kasan_record_aux_stack() that does not do any memory allocation through stackdepot. This will permit using it in contexts that cannot allocate any memory. Link: https://lkml.kernel.org/r/20210913112609.2651084-6-elver@google.com Signed-off-by: Marco Elver Tested-by: Shuah Khan Acked-by: Sebastian Andrzej Siewior Reviewed-by: Andrey Konovalov Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: "Gustavo A. R. Silva" Cc: Lai Jiangshan Cc: Taras Madan Cc: Tejun Heo Cc: Thomas Gleixner Cc: Vijayanand Jitta Cc: Vinayak Menon Cc: Walter Wu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index dd874a1ee862..736d7b458996 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -370,12 +370,14 @@ static inline void kasan_unpoison_task_stack(struct task_struct *task) {} void kasan_cache_shrink(struct kmem_cache *cache); void kasan_cache_shutdown(struct kmem_cache *cache); void kasan_record_aux_stack(void *ptr); +void kasan_record_aux_stack_noalloc(void *ptr); #else /* CONFIG_KASAN_GENERIC */ static inline void kasan_cache_shrink(struct kmem_cache *cache) {} static inline void kasan_cache_shutdown(struct kmem_cache *cache) {} static inline void kasan_record_aux_stack(void *ptr) {} +static inline void kasan_record_aux_stack_noalloc(void *ptr) {} #endif /* CONFIG_KASAN_GENERIC */ -- cgit v1.2.3 From 86cffecdeaa278444870c8745ab166a65865dbf0 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Nov 2021 13:36:19 -0700 Subject: Compiler Attributes: add __alloc_size() for better bounds checking GCC and Clang can use the "alloc_size" attribute to better inform the results of __builtin_object_size() (for compile-time constant values). Clang can additionally use alloc_size to inform the results of __builtin_dynamic_object_size() (for run-time values). Because GCC sees the frequent use of struct_size() as an allocator size argument, and notices it can return SIZE_MAX (the overflow indication), it complains about these call sites overflowing (since SIZE_MAX is greater than the default -Walloc-size-larger-than=PTRDIFF_MAX). This isn't helpful since we already know a SIZE_MAX will be caught at run-time (this was an intentional design). To deal with this, we must disable this check as it is both a false positive and redundant. (Clang does not have this warning option.) Unfortunately, just checking the -Wno-alloc-size-larger-than is not sufficient to make the __alloc_size attribute behave correctly under older GCC versions. The attribute itself must be disabled in those situations too, as there appears to be no way to reliably silence the SIZE_MAX constant expression cases for GCC versions less than 9.1: In file included from ./include/linux/resource_ext.h:11, from ./include/linux/pci.h:40, from drivers/net/ethernet/intel/ixgbe/ixgbe.h:9, from drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c:4: In function 'kmalloc_node', inlined from 'ixgbe_alloc_q_vector' at ./include/linux/slab.h:743:9: ./include/linux/slab.h:618:9: error: argument 1 value '18446744073709551615' exceeds maximum object size 9223372036854775807 [-Werror=alloc-size-larger-than=] return __kmalloc_node(size, flags, node); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ./include/linux/slab.h: In function 'ixgbe_alloc_q_vector': ./include/linux/slab.h:455:7: note: in a call to allocation function '__kmalloc_node' declared here void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_slab_alignment __malloc; ^~~~~~~~~~~~~~ Specifically: '-Wno-alloc-size-larger-than' is not correctly handled by GCC < 9.1 https://godbolt.org/z/hqsfG7q84 (doesn't disable) https://godbolt.org/z/P9jdrPTYh (doesn't admit to not knowing about option) https://godbolt.org/z/465TPMWKb (only warns when other warnings appear) '-Walloc-size-larger-than=18446744073709551615' is not handled by GCC < 8.2 https://godbolt.org/z/73hh1EPxz (ignores numeric value) Since anything marked with __alloc_size would also qualify for marking with __malloc, just include __malloc along with it to avoid redundant markings. (Suggested by Linus Torvalds.) Finally, make sure checkpatch.pl doesn't get confused about finding the __alloc_size attribute on functions. (Thanks to Joe Perches.) Link: https://lkml.kernel.org/r/20210930222704.2631604-3-keescook@chromium.org Signed-off-by: Kees Cook Tested-by: Randy Dunlap Cc: Andy Whitcroft Cc: Christoph Lameter Cc: Daniel Micay Cc: David Rientjes Cc: Dennis Zhou Cc: Dwaipayan Ray Cc: Joe Perches Cc: Joonsoo Kim Cc: Lukas Bulwahn Cc: Pekka Enberg Cc: Tejun Heo Cc: Vlastimil Babka Cc: Alexandre Bounine Cc: Gustavo A. R. Silva Cc: Ira Weiny Cc: Jing Xiangfeng Cc: John Hubbard Cc: kernel test robot Cc: Matt Porter Cc: Miguel Ojeda Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Souptick Joarder Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compiler-gcc.h | 8 ++++++++ include/linux/compiler_attributes.h | 10 ++++++++++ include/linux/compiler_types.h | 12 ++++++++++++ 3 files changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index bd2b881c6b63..b9d5f9c373a0 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -144,3 +144,11 @@ #else #define __diag_GCC_8(s) #endif + +/* + * Prior to 9.1, -Wno-alloc-size-larger-than (and therefore the "alloc_size" + * attribute) do not work, and must be disabled. + */ +#if GCC_VERSION < 90100 +#undef __alloc_size__ +#endif diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index e6ec63403965..3de06a8fae73 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -33,6 +33,15 @@ #define __aligned(x) __attribute__((__aligned__(x))) #define __aligned_largest __attribute__((__aligned__)) +/* + * Note: do not use this directly. Instead, use __alloc_size() since it is conditionally + * available and includes other attributes. + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-alloc_005fsize-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#alloc-size + */ +#define __alloc_size__(x, ...) __attribute__((__alloc_size__(x, ## __VA_ARGS__))) + /* * Note: users of __always_inline currently do not write "inline" themselves, * which seems to be required by gcc to apply the attribute according @@ -153,6 +162,7 @@ /* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-malloc-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#malloc */ #define __malloc __attribute__((__malloc__)) diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index b6ff83a714ca..4f2203c4a257 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -250,6 +250,18 @@ struct ftrace_likely_data { # define __cficanonical #endif +/* + * Any place that could be marked with the "alloc_size" attribute is also + * a place to be marked with the "malloc" attribute. Do this as part of the + * __alloc_size macro to avoid redundant attributes and to avoid missing a + * __malloc marking. + */ +#ifdef __alloc_size__ +# define __alloc_size(x, ...) __alloc_size__(x, ## __VA_ARGS__) __malloc +#else +# define __alloc_size(x, ...) __malloc +#endif + #ifndef asm_volatile_goto #define asm_volatile_goto(x...) asm goto(x) #endif -- cgit v1.2.3 From 72d67229f522e3331d1eabd9f58d36ae080eb228 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Nov 2021 13:36:23 -0700 Subject: slab: clean up function prototypes Based on feedback from Joe Perches and Linus Torvalds, regularize the slab function prototypes before making attribute changes. Link: https://lkml.kernel.org/r/20210930222704.2631604-4-keescook@chromium.org Signed-off-by: Kees Cook Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: Alexandre Bounine Cc: Andy Whitcroft Cc: Daniel Micay Cc: Dennis Zhou Cc: Dwaipayan Ray Cc: Gustavo A. R. Silva Cc: Ira Weiny Cc: Jing Xiangfeng Cc: Joe Perches Cc: John Hubbard Cc: kernel test robot Cc: Lukas Bulwahn Cc: Matt Porter Cc: Miguel Ojeda Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Randy Dunlap Cc: Souptick Joarder Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 68 ++++++++++++++++++++++++++-------------------------- 1 file changed, 34 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index c0d46b6fa12a..d05de03bdcdd 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -152,8 +152,8 @@ struct kmem_cache *kmem_cache_create_usercopy(const char *name, slab_flags_t flags, unsigned int useroffset, unsigned int usersize, void (*ctor)(void *)); -void kmem_cache_destroy(struct kmem_cache *); -int kmem_cache_shrink(struct kmem_cache *); +void kmem_cache_destroy(struct kmem_cache *s); +int kmem_cache_shrink(struct kmem_cache *s); /* * Please use this macro to create slab caches. Simply specify the @@ -181,11 +181,11 @@ int kmem_cache_shrink(struct kmem_cache *); /* * Common kmalloc functions provided by all allocators */ -void * __must_check krealloc(const void *, size_t, gfp_t); -void kfree(const void *); -void kfree_sensitive(const void *); -size_t __ksize(const void *); -size_t ksize(const void *); +void * __must_check krealloc(const void *objp, size_t new_size, gfp_t flags); +void kfree(const void *objp); +void kfree_sensitive(const void *objp); +size_t __ksize(const void *objp); +size_t ksize(const void *objp); #ifdef CONFIG_PRINTK bool kmem_valid_obj(void *object); void kmem_dump_obj(void *object); @@ -426,8 +426,8 @@ static __always_inline unsigned int __kmalloc_index(size_t size, #endif /* !CONFIG_SLOB */ void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __malloc; -void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags) __assume_slab_alignment __malloc; -void kmem_cache_free(struct kmem_cache *, void *); +void *kmem_cache_alloc(struct kmem_cache *s, gfp_t flags) __assume_slab_alignment __malloc; +void kmem_cache_free(struct kmem_cache *s, void *objp); /* * Bulk allocation and freeing operations. These are accelerated in an @@ -436,8 +436,8 @@ void kmem_cache_free(struct kmem_cache *, void *); * * Note that interrupts must be enabled when calling these functions. */ -void kmem_cache_free_bulk(struct kmem_cache *, size_t, void **); -int kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **); +void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p); +int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, void **p); /* * Caller must not use kfree_bulk() on memory not originally allocated @@ -450,7 +450,8 @@ static __always_inline void kfree_bulk(size_t size, void **p) #ifdef CONFIG_NUMA void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment __malloc; -void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node) __assume_slab_alignment __malloc; +void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment + __malloc; #else static __always_inline void *__kmalloc_node(size_t size, gfp_t flags, int node) { @@ -464,25 +465,24 @@ static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t f #endif #ifdef CONFIG_TRACING -extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t) __assume_slab_alignment __malloc; +extern void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) + __assume_slab_alignment __malloc; #ifdef CONFIG_NUMA -extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, - gfp_t gfpflags, - int node, size_t size) __assume_slab_alignment __malloc; +extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, + int node, size_t size) __assume_slab_alignment __malloc; #else -static __always_inline void * -kmem_cache_alloc_node_trace(struct kmem_cache *s, - gfp_t gfpflags, - int node, size_t size) +static __always_inline void *kmem_cache_alloc_node_trace(struct kmem_cache *s, + gfp_t gfpflags, int node, + size_t size) { return kmem_cache_alloc_trace(s, gfpflags, size); } #endif /* CONFIG_NUMA */ #else /* CONFIG_TRACING */ -static __always_inline void *kmem_cache_alloc_trace(struct kmem_cache *s, - gfp_t flags, size_t size) +static __always_inline void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t flags, + size_t size) { void *ret = kmem_cache_alloc(s, flags); @@ -490,10 +490,8 @@ static __always_inline void *kmem_cache_alloc_trace(struct kmem_cache *s, return ret; } -static __always_inline void * -kmem_cache_alloc_node_trace(struct kmem_cache *s, - gfp_t gfpflags, - int node, size_t size) +static __always_inline void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, + int node, size_t size) { void *ret = kmem_cache_alloc_node(s, gfpflags, node); @@ -502,13 +500,14 @@ kmem_cache_alloc_node_trace(struct kmem_cache *s, } #endif /* CONFIG_TRACING */ -extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment __malloc; +extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment + __malloc; #ifdef CONFIG_TRACING -extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment __malloc; +extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) + __assume_page_alignment __malloc; #else -static __always_inline void * -kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) +static __always_inline void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) { return kmalloc_order(size, flags, order); } @@ -638,8 +637,8 @@ static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags) * @new_size: new size of a single member of the array * @flags: the type of memory to allocate (see kmalloc) */ -static __must_check inline void * -krealloc_array(void *p, size_t new_n, size_t new_size, gfp_t flags) +static inline void * __must_check krealloc_array(void *p, size_t new_n, size_t new_size, + gfp_t flags) { size_t bytes; @@ -668,7 +667,7 @@ static inline void *kcalloc(size_t n, size_t size, gfp_t flags) * allocator where we care about the real place the memory allocation * request comes from. */ -extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long); +extern void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller); #define kmalloc_track_caller(size, flags) \ __kmalloc_track_caller(size, flags, _RET_IP_) @@ -691,7 +690,8 @@ static inline void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node) #ifdef CONFIG_NUMA -extern void *__kmalloc_node_track_caller(size_t, gfp_t, int, unsigned long); +extern void *__kmalloc_node_track_caller(size_t size, gfp_t flags, int node, + unsigned long caller); #define kmalloc_node_track_caller(size, flags, node) \ __kmalloc_node_track_caller(size, flags, node, \ _RET_IP_) -- cgit v1.2.3 From c37495d6254c237578db3121dcf79857e033f8ff Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Nov 2021 13:36:27 -0700 Subject: slab: add __alloc_size attributes for better bounds checking As already done in GrapheneOS, add the __alloc_size attribute for regular kmalloc interfaces, to provide additional hinting for better bounds checking, assisting CONFIG_FORTIFY_SOURCE and other compiler optimizations. Link: https://lkml.kernel.org/r/20210930222704.2631604-5-keescook@chromium.org Signed-off-by: Kees Cook Co-developed-by: Daniel Micay Signed-off-by: Daniel Micay Reviewed-by: Nick Desaulniers Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: Andy Whitcroft Cc: Dennis Zhou Cc: Dwaipayan Ray Cc: Joe Perches Cc: Lukas Bulwahn Cc: Miguel Ojeda Cc: Nathan Chancellor Cc: Tejun Heo Cc: Alexandre Bounine Cc: Gustavo A. R. Silva Cc: Ira Weiny Cc: Jing Xiangfeng Cc: John Hubbard Cc: kernel test robot Cc: Matt Porter Cc: Randy Dunlap Cc: Souptick Joarder Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 61 ++++++++++++++++++++++++++++------------------------ 1 file changed, 33 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index d05de03bdcdd..b5bf0537975b 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -181,7 +181,7 @@ int kmem_cache_shrink(struct kmem_cache *s); /* * Common kmalloc functions provided by all allocators */ -void * __must_check krealloc(const void *objp, size_t new_size, gfp_t flags); +void * __must_check krealloc(const void *objp, size_t new_size, gfp_t flags) __alloc_size(2); void kfree(const void *objp); void kfree_sensitive(const void *objp); size_t __ksize(const void *objp); @@ -425,7 +425,7 @@ static __always_inline unsigned int __kmalloc_index(size_t size, #define kmalloc_index(s) __kmalloc_index(s, true) #endif /* !CONFIG_SLOB */ -void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __malloc; +void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1); void *kmem_cache_alloc(struct kmem_cache *s, gfp_t flags) __assume_slab_alignment __malloc; void kmem_cache_free(struct kmem_cache *s, void *objp); @@ -449,11 +449,12 @@ static __always_inline void kfree_bulk(size_t size, void **p) } #ifdef CONFIG_NUMA -void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment __malloc; +void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment + __alloc_size(1); void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment __malloc; #else -static __always_inline void *__kmalloc_node(size_t size, gfp_t flags, int node) +static __always_inline __alloc_size(1) void *__kmalloc_node(size_t size, gfp_t flags, int node) { return __kmalloc(size, flags); } @@ -466,23 +467,23 @@ static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t f #ifdef CONFIG_TRACING extern void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) - __assume_slab_alignment __malloc; + __assume_slab_alignment __alloc_size(3); #ifdef CONFIG_NUMA extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, - int node, size_t size) __assume_slab_alignment __malloc; + int node, size_t size) __assume_slab_alignment + __alloc_size(4); #else -static __always_inline void *kmem_cache_alloc_node_trace(struct kmem_cache *s, - gfp_t gfpflags, int node, - size_t size) +static __always_inline __alloc_size(4) void *kmem_cache_alloc_node_trace(struct kmem_cache *s, + gfp_t gfpflags, int node, size_t size) { return kmem_cache_alloc_trace(s, gfpflags, size); } #endif /* CONFIG_NUMA */ #else /* CONFIG_TRACING */ -static __always_inline void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t flags, - size_t size) +static __always_inline __alloc_size(3) void *kmem_cache_alloc_trace(struct kmem_cache *s, + gfp_t flags, size_t size) { void *ret = kmem_cache_alloc(s, flags); @@ -501,19 +502,20 @@ static __always_inline void *kmem_cache_alloc_node_trace(struct kmem_cache *s, g #endif /* CONFIG_TRACING */ extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment - __malloc; + __alloc_size(1); #ifdef CONFIG_TRACING extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) - __assume_page_alignment __malloc; + __assume_page_alignment __alloc_size(1); #else -static __always_inline void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) +static __always_inline __alloc_size(1) void *kmalloc_order_trace(size_t size, gfp_t flags, + unsigned int order) { return kmalloc_order(size, flags, order); } #endif -static __always_inline void *kmalloc_large(size_t size, gfp_t flags) +static __always_inline __alloc_size(1) void *kmalloc_large(size_t size, gfp_t flags) { unsigned int order = get_order(size); return kmalloc_order_trace(size, flags, order); @@ -573,7 +575,7 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) * Try really hard to succeed the allocation but fail * eventually. */ -static __always_inline void *kmalloc(size_t size, gfp_t flags) +static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags) { if (__builtin_constant_p(size)) { #ifndef CONFIG_SLOB @@ -595,7 +597,7 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags) return __kmalloc(size, flags); } -static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) +static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t flags, int node) { #ifndef CONFIG_SLOB if (__builtin_constant_p(size) && @@ -619,7 +621,7 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ -static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags) +static inline __alloc_size(1, 2) void *kmalloc_array(size_t n, size_t size, gfp_t flags) { size_t bytes; @@ -637,8 +639,10 @@ static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags) * @new_size: new size of a single member of the array * @flags: the type of memory to allocate (see kmalloc) */ -static inline void * __must_check krealloc_array(void *p, size_t new_n, size_t new_size, - gfp_t flags) +static inline __alloc_size(2, 3) void * __must_check krealloc_array(void *p, + size_t new_n, + size_t new_size, + gfp_t flags) { size_t bytes; @@ -654,7 +658,7 @@ static inline void * __must_check krealloc_array(void *p, size_t new_n, size_t n * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ -static inline void *kcalloc(size_t n, size_t size, gfp_t flags) +static inline __alloc_size(1, 2) void *kcalloc(size_t n, size_t size, gfp_t flags) { return kmalloc_array(n, size, flags | __GFP_ZERO); } @@ -667,12 +671,13 @@ static inline void *kcalloc(size_t n, size_t size, gfp_t flags) * allocator where we care about the real place the memory allocation * request comes from. */ -extern void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller); +extern void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller) + __alloc_size(1); #define kmalloc_track_caller(size, flags) \ __kmalloc_track_caller(size, flags, _RET_IP_) -static inline void *kmalloc_array_node(size_t n, size_t size, gfp_t flags, - int node) +static inline __alloc_size(1, 2) void *kmalloc_array_node(size_t n, size_t size, gfp_t flags, + int node) { size_t bytes; @@ -683,7 +688,7 @@ static inline void *kmalloc_array_node(size_t n, size_t size, gfp_t flags, return __kmalloc_node(bytes, flags, node); } -static inline void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node) +static inline __alloc_size(1, 2) void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node) { return kmalloc_array_node(n, size, flags | __GFP_ZERO, node); } @@ -691,7 +696,7 @@ static inline void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node) #ifdef CONFIG_NUMA extern void *__kmalloc_node_track_caller(size_t size, gfp_t flags, int node, - unsigned long caller); + unsigned long caller) __alloc_size(1); #define kmalloc_node_track_caller(size, flags, node) \ __kmalloc_node_track_caller(size, flags, node, \ _RET_IP_) @@ -716,7 +721,7 @@ static inline void *kmem_cache_zalloc(struct kmem_cache *k, gfp_t flags) * @size: how many bytes of memory are required. * @flags: the type of memory to allocate (see kmalloc). */ -static inline void *kzalloc(size_t size, gfp_t flags) +static inline __alloc_size(1) void *kzalloc(size_t size, gfp_t flags) { return kmalloc(size, flags | __GFP_ZERO); } @@ -727,7 +732,7 @@ static inline void *kzalloc(size_t size, gfp_t flags) * @flags: the type of memory to allocate (see kmalloc). * @node: memory node from which to allocate */ -static inline void *kzalloc_node(size_t size, gfp_t flags, int node) +static inline __alloc_size(1) void *kzalloc_node(size_t size, gfp_t flags, int node) { return kmalloc_node(size, flags | __GFP_ZERO, node); } -- cgit v1.2.3 From 56bcf40f91c7d7f53b77abe161a7d18ef9f981ba Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Nov 2021 13:36:31 -0700 Subject: mm/kvmalloc: add __alloc_size attributes for better bounds checking As already done in GrapheneOS, add the __alloc_size attribute for regular kvmalloc interfaces, to provide additional hinting for better bounds checking, assisting CONFIG_FORTIFY_SOURCE and other compiler optimizations. Link: https://lkml.kernel.org/r/20210930222704.2631604-6-keescook@chromium.org Signed-off-by: Kees Cook Co-developed-by: Daniel Micay Signed-off-by: Daniel Micay Reviewed-by: Nick Desaulniers Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: Andy Whitcroft Cc: Dennis Zhou Cc: Dwaipayan Ray Cc: Joe Perches Cc: Lukas Bulwahn Cc: Miguel Ojeda Cc: Nathan Chancellor Cc: Tejun Heo Cc: Alexandre Bounine Cc: Gustavo A. R. Silva Cc: Ira Weiny Cc: Jing Xiangfeng Cc: John Hubbard Cc: kernel test robot Cc: Matt Porter Cc: Randy Dunlap Cc: Souptick Joarder Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index b5bf0537975b..837cb16232ef 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -737,21 +737,21 @@ static inline __alloc_size(1) void *kzalloc_node(size_t size, gfp_t flags, int n return kmalloc_node(size, flags | __GFP_ZERO, node); } -extern void *kvmalloc_node(size_t size, gfp_t flags, int node); -static inline void *kvmalloc(size_t size, gfp_t flags) +extern void *kvmalloc_node(size_t size, gfp_t flags, int node) __alloc_size(1); +static inline __alloc_size(1) void *kvmalloc(size_t size, gfp_t flags) { return kvmalloc_node(size, flags, NUMA_NO_NODE); } -static inline void *kvzalloc_node(size_t size, gfp_t flags, int node) +static inline __alloc_size(1) void *kvzalloc_node(size_t size, gfp_t flags, int node) { return kvmalloc_node(size, flags | __GFP_ZERO, node); } -static inline void *kvzalloc(size_t size, gfp_t flags) +static inline __alloc_size(1) void *kvzalloc(size_t size, gfp_t flags) { return kvmalloc(size, flags | __GFP_ZERO); } -static inline void *kvmalloc_array(size_t n, size_t size, gfp_t flags) +static inline __alloc_size(1, 2) void *kvmalloc_array(size_t n, size_t size, gfp_t flags) { size_t bytes; @@ -761,13 +761,13 @@ static inline void *kvmalloc_array(size_t n, size_t size, gfp_t flags) return kvmalloc(bytes, flags); } -static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) +static inline __alloc_size(1, 2) void *kvcalloc(size_t n, size_t size, gfp_t flags) { return kvmalloc_array(n, size, flags | __GFP_ZERO); } -extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, - gfp_t flags); +extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags) + __alloc_size(3); extern void kvfree(const void *addr); extern void kvfree_sensitive(const void *addr, size_t len); -- cgit v1.2.3 From 894f24bb569afd4fe4a874c636f82d47f1c9beed Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Nov 2021 13:36:34 -0700 Subject: mm/vmalloc: add __alloc_size attributes for better bounds checking As already done in GrapheneOS, add the __alloc_size attribute for appropriate vmalloc allocator interfaces, to provide additional hinting for better bounds checking, assisting CONFIG_FORTIFY_SOURCE and other compiler optimizations. Link: https://lkml.kernel.org/r/20210930222704.2631604-7-keescook@chromium.org Signed-off-by: Kees Cook Co-developed-by: Daniel Micay Signed-off-by: Daniel Micay Cc: Andy Whitcroft Cc: Christoph Lameter Cc: David Rientjes Cc: Dennis Zhou Cc: Dwaipayan Ray Cc: Joe Perches Cc: Joonsoo Kim Cc: Lukas Bulwahn Cc: Miguel Ojeda Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Pekka Enberg Cc: Tejun Heo Cc: Vlastimil Babka Cc: Alexandre Bounine Cc: Gustavo A. R. Silva Cc: Ira Weiny Cc: Jing Xiangfeng Cc: John Hubbard Cc: kernel test robot Cc: Matt Porter Cc: Randy Dunlap Cc: Souptick Joarder Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 671d402c3778..0ed56fc10c11 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -136,21 +136,21 @@ static inline void vmalloc_init(void) static inline unsigned long vmalloc_nr_pages(void) { return 0; } #endif -extern void *vmalloc(unsigned long size); -extern void *vzalloc(unsigned long size); -extern void *vmalloc_user(unsigned long size); -extern void *vmalloc_node(unsigned long size, int node); -extern void *vzalloc_node(unsigned long size, int node); -extern void *vmalloc_32(unsigned long size); -extern void *vmalloc_32_user(unsigned long size); -extern void *__vmalloc(unsigned long size, gfp_t gfp_mask); +extern void *vmalloc(unsigned long size) __alloc_size(1); +extern void *vzalloc(unsigned long size) __alloc_size(1); +extern void *vmalloc_user(unsigned long size) __alloc_size(1); +extern void *vmalloc_node(unsigned long size, int node) __alloc_size(1); +extern void *vzalloc_node(unsigned long size, int node) __alloc_size(1); +extern void *vmalloc_32(unsigned long size) __alloc_size(1); +extern void *vmalloc_32_user(unsigned long size) __alloc_size(1); +extern void *__vmalloc(unsigned long size, gfp_t gfp_mask) __alloc_size(1); extern void *__vmalloc_node_range(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, - const void *caller); + const void *caller) __alloc_size(1); void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, - int node, const void *caller); -void *vmalloc_no_huge(unsigned long size); + int node, const void *caller) __alloc_size(1); +void *vmalloc_no_huge(unsigned long size) __alloc_size(1); extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); -- cgit v1.2.3 From abd58f38dfb4771ef06e25d71a84aa0932c52f1a Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Nov 2021 13:36:38 -0700 Subject: mm/page_alloc: add __alloc_size attributes for better bounds checking As already done in GrapheneOS, add the __alloc_size attribute for appropriate page allocator interfaces, to provide additional hinting for better bounds checking, assisting CONFIG_FORTIFY_SOURCE and other compiler optimizations. Link: https://lkml.kernel.org/r/20210930222704.2631604-8-keescook@chromium.org Signed-off-by: Kees Cook Co-developed-by: Daniel Micay Signed-off-by: Daniel Micay Cc: Andy Whitcroft Cc: Christoph Lameter Cc: David Rientjes Cc: Dennis Zhou Cc: Dwaipayan Ray Cc: Joe Perches Cc: Joonsoo Kim Cc: Lukas Bulwahn Cc: Miguel Ojeda Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Pekka Enberg Cc: Tejun Heo Cc: Vlastimil Babka Cc: Alexandre Bounine Cc: Gustavo A. R. Silva Cc: Ira Weiny Cc: Jing Xiangfeng Cc: John Hubbard Cc: kernel test robot Cc: Matt Porter Cc: Randy Dunlap Cc: Souptick Joarder Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 55b2ec1f965a..fbd4abc33f24 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -608,9 +608,9 @@ static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); -void *alloc_pages_exact(size_t size, gfp_t gfp_mask); +void *alloc_pages_exact(size_t size, gfp_t gfp_mask) __alloc_size(1); void free_pages_exact(void *virt, size_t size); -void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask); +__meminit void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) __alloc_size(1); #define __get_free_page(gfp_mask) \ __get_free_pages((gfp_mask), 0) -- cgit v1.2.3 From 17197dd460469c6fca66e274f5cd51ee43bb6ddd Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Nov 2021 13:36:42 -0700 Subject: percpu: add __alloc_size attributes for better bounds checking As already done in GrapheneOS, add the __alloc_size attribute for appropriate percpu allocator interfaces, to provide additional hinting for better bounds checking, assisting CONFIG_FORTIFY_SOURCE and other compiler optimizations. Note that due to the implementation of the percpu API, this is unlikely to ever actually provide compile-time checking beyond very simple non-SMP builds. But, since they are technically allocators, mark them as such. Link: https://lkml.kernel.org/r/20210930222704.2631604-9-keescook@chromium.org Signed-off-by: Kees Cook Co-developed-by: Daniel Micay Signed-off-by: Daniel Micay Acked-by: Dennis Zhou Cc: Tejun Heo Cc: Christoph Lameter Cc: Andy Whitcroft Cc: David Rientjes Cc: Dwaipayan Ray Cc: Joe Perches Cc: Joonsoo Kim Cc: Lukas Bulwahn Cc: Miguel Ojeda Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Pekka Enberg Cc: Vlastimil Babka Cc: Alexandre Bounine Cc: Gustavo A. R. Silva Cc: Ira Weiny Cc: Jing Xiangfeng Cc: John Hubbard Cc: kernel test robot Cc: Matt Porter Cc: Randy Dunlap Cc: Souptick Joarder Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/percpu.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 5e76af742c80..98a9371133f8 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -123,7 +123,7 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_populate_pte_fn_t populate_pte_fn); #endif -extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align); +extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align) __alloc_size(1); extern bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr); extern bool is_kernel_percpu_address(unsigned long addr); @@ -131,8 +131,8 @@ extern bool is_kernel_percpu_address(unsigned long addr); extern void __init setup_per_cpu_areas(void); #endif -extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp); -extern void __percpu *__alloc_percpu(size_t size, size_t align); +extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp) __alloc_size(1); +extern void __percpu *__alloc_percpu(size_t size, size_t align) __alloc_size(1); extern void free_percpu(void __percpu *__pdata); extern phys_addr_t per_cpu_ptr_to_phys(void *addr); -- cgit v1.2.3 From 0b3ea0926afb8dde70cfab00316ae0a70b93a7cc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 5 Nov 2021 13:36:58 -0700 Subject: fs: explicitly unregister per-superblock BDIs Add a new SB_I_ flag to mark superblocks that have an ephemeral bdi associated with them, and unregister it when the superblock is shut down. Link: https://lkml.kernel.org/r/20211021124441.668816-4-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Cc: Miquel Raynal Cc: Richard Weinberger Cc: Vignesh Raghavendra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index e7a633353fd2..226de651f52e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1443,6 +1443,7 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_I_UNTRUSTED_MOUNTER 0x00000040 #define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ +#define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ /* Possible states of 'frozen' field */ enum { -- cgit v1.2.3 From efee17134ca464639a2f5b4d036ce40caf1b247a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 5 Nov 2021 13:37:04 -0700 Subject: mm: simplify bdi refcounting Move grabbing and releasing the bdi refcount out of the common wb_init/wb_exit helpers into code that is only used for the non-default memcg driven bdi_writeback structures. [hch@lst.de: add comment] Link: https://lkml.kernel.org/r/20211027074207.GA12793@lst.de [akpm@linux-foundation.org: fix typo] Link: https://lkml.kernel.org/r/20211021124441.668816-6-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Cc: Miquel Raynal Cc: Richard Weinberger Cc: Vignesh Raghavendra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev-defs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 33207004cfde..993c5628a726 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -103,6 +103,9 @@ struct wb_completion { * change as blkcg is disabled and enabled higher up in the hierarchy, a wb * is tested for blkcg after lookup and removed from index on mismatch so * that a new wb for the combination can be created. + * + * Each bdi_writeback that is not embedded into the backing_dev_info must hold + * a reference to the parent backing_dev_info. See cgwb_create() for details. */ struct bdi_writeback { struct backing_dev_info *bdi; /* our parent bdi */ -- cgit v1.2.3 From e80216d9f1f5c90b3cab834cd4fb492d731f70aa Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Fri, 5 Nov 2021 13:37:56 -0700 Subject: mm: memcontrol: remove the kmem states Now the kmem states is only used to indicate whether the kmem is offline. However, we can set ->kmemcg_id to -1 to indicate whether the kmem is offline. Finally, we can remove the kmem states to simplify the code. Link: https://lkml.kernel.org/r/20211025125259.56624-1-songmuchun@bytedance.com Signed-off-by: Muchun Song Acked-by: Roman Gushchin Cc: Michal Hocko Cc: Shakeel Butt Cc: Matthew Wilcox (Oracle) Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 3096c9a0ee01..f207f98bdb76 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -180,12 +180,6 @@ struct mem_cgroup_thresholds { struct mem_cgroup_threshold_ary *spare; }; -enum memcg_kmem_state { - KMEM_NONE, - KMEM_ALLOCATED, - KMEM_ONLINE, -}; - #if defined(CONFIG_SMP) struct memcg_padding { char x[0]; @@ -318,7 +312,6 @@ struct mem_cgroup { #ifdef CONFIG_MEMCG_KMEM int kmemcg_id; - enum memcg_kmem_state kmem_state; struct obj_cgroup __rcu *objcg; struct list_head objcg_list; /* list of inherited objcgs */ #endif -- cgit v1.2.3 From f1dc0db296bd25960273649fc6ef2ecbf5aaa0e0 Mon Sep 17 00:00:00 2001 From: Rolf Eike Beer Date: Fri, 5 Nov 2021 13:38:15 -0700 Subject: mm: use __pfn_to_section() instead of open coding it It is defined in the same file just a few lines above. Link: https://lkml.kernel.org/r/4598487.Rc0NezkW7i@mobilepool36.emlix.com Signed-off-by: Rolf Eike Beer Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 6a1d79d84675..832aa49d0d8e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1481,7 +1481,7 @@ static inline int pfn_valid(unsigned long pfn) if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; - ms = __nr_to_section(pfn_to_section_nr(pfn)); + ms = __pfn_to_section(pfn); if (!valid_section(ms)) return 0; /* @@ -1496,7 +1496,7 @@ static inline int pfn_in_present_section(unsigned long pfn) { if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; - return present_section(__nr_to_section(pfn_to_section_nr(pfn))); + return present_section(__pfn_to_section(pfn)); } static inline unsigned long next_present_section_nr(unsigned long section_nr) -- cgit v1.2.3 From 232a6a1c0619d1b4d9cd8d21949b2f13821be0af Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 5 Nov 2021 13:38:31 -0700 Subject: mm: drop first_index/last_index in zap_details The first_index/last_index parameters in zap_details are actually only used in unmap_mapping_range_tree(). At the meantime, this function is only called by unmap_mapping_pages() once. Instead of passing these two variables through the whole stack of page zapping code, remove them from zap_details and let them simply be parameters of unmap_mapping_range_tree(), which is inlined. Link: https://lkml.kernel.org/r/20210915181535.11238-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Alistair Popple Reviewed-by: David Hildenbrand Reviewed-by: Liam Howlett Acked-by: Hugh Dickins Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Mike Rapoport Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 32b2ecc47408..c5b600d7f85b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1688,8 +1688,6 @@ extern void user_shm_unlock(size_t, struct ucounts *); */ struct zap_details { struct address_space *check_mapping; /* Check page->mapping if set */ - pgoff_t first_index; /* Lowest page->index to unmap */ - pgoff_t last_index; /* Highest page->index to unmap */ struct page *single_page; /* Locked page to be unmapped */ }; -- cgit v1.2.3 From 91b61ef333cf43f96b3522a086c9ac925763d6e5 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 5 Nov 2021 13:38:34 -0700 Subject: mm: add zap_skip_check_mapping() helper Use the helper for the checks. Rename "check_mapping" into "zap_mapping" because "check_mapping" looks like a bool but in fact it stores the mapping itself. When it's set, we check the mapping (it must be non-NULL). When it's cleared we skip the check, which works like the old way. Move the duplicated comments to the helper too. Link: https://lkml.kernel.org/r/20210915181538.11288-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Liam Howlett Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Mike Rapoport Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c5b600d7f85b..6e29deb1e0d4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1687,10 +1687,24 @@ extern void user_shm_unlock(size_t, struct ucounts *); * Parameter block passed down to zap_pte_range in exceptional cases. */ struct zap_details { - struct address_space *check_mapping; /* Check page->mapping if set */ + struct address_space *zap_mapping; /* Check page->mapping if set */ struct page *single_page; /* Locked page to be unmapped */ }; +/* + * We set details->zap_mappings when we want to unmap shared but keep private + * pages. Return true if skip zapping this page, false otherwise. + */ +static inline bool +zap_skip_check_mapping(struct zap_details *details, struct page *page) +{ + if (!details || !page) + return false; + + return details->zap_mapping && + (details->zap_mapping != page_rmapping(page)); +} + struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, -- cgit v1.2.3 From e26e0cc30b48cad5f2704f6a22fa5cac9fdaaece Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Fri, 5 Nov 2021 13:39:00 -0700 Subject: memory: remove unused CONFIG_MEM_BLOCK_SIZE Commit 3947be1969a9 ("[PATCH] memory hotplug: sysfs and add/remove functions") defines CONFIG_MEM_BLOCK_SIZE, but this has never been utilized anywhere. It is a good practice to keep the CONFIG_* defines exclusively for the Kbuild system. So, drop this unused definition. This issue was noticed due to running ./scripts/checkkconfigsymbols.py. Link: https://lkml.kernel.org/r/20211006120354.7468-1-lukas.bulwahn@gmail.com Signed-off-by: Lukas Bulwahn Reviewed-by: David Hildenbrand Cc: Michal Hocko Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 182c606adb06..053a530c7bdd 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -140,7 +140,6 @@ typedef int (*walk_memory_blocks_func_t)(struct memory_block *, void *); extern int walk_memory_blocks(unsigned long start, unsigned long size, void *arg, walk_memory_blocks_func_t func); extern int for_each_memory_block(void *arg, walk_memory_blocks_func_t func); -#define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION< Date: Fri, 5 Nov 2021 13:39:10 -0700 Subject: include/linux/io-mapping.h: remove fallback for writecombine The fallback was introduced in commit 80c33624e472 ("io-mapping: Fixup for different names of writecombine") to fix the build on microblaze. 5 years later, it seems all archs now provide a pgprot_writecombine(), so just remove the other possible fallbacks. For microblaze, pgprot_writecombine() is available since commit 97ccedd793ac ("microblaze: Provide pgprot_device/writecombine macros for nommu"). This is build-tested on microblaze with a hack to always build mm/io-mapping.o and without DIYing on an x86-only macro (_PAGE_CACHE_MASK) Link: https://lkml.kernel.org/r/20211020204838.1142908-1-lucas.demarchi@intel.com Signed-off-by: Lucas De Marchi Cc: Chris Wilson Cc: Daniel Vetter Cc: Joonas Lahtinen Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/io-mapping.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index e9743cfd8585..66a774d2710e 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -132,13 +132,7 @@ io_mapping_init_wc(struct io_mapping *iomap, iomap->base = base; iomap->size = size; -#if defined(pgprot_noncached_wc) /* archs can't agree on a name ... */ - iomap->prot = pgprot_noncached_wc(PAGE_KERNEL); -#elif defined(pgprot_writecombine) iomap->prot = pgprot_writecombine(PAGE_KERNEL); -#else - iomap->prot = pgprot_noncached(PAGE_KERNEL); -#endif return iomap; } -- cgit v1.2.3 From bd1a8fb2d43f7c293383f76691d7a55f7f89d9da Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 5 Nov 2021 13:39:22 -0700 Subject: mm/vmalloc: don't allow VM_NO_GUARD on vmap() The vmalloc guard pages are added on top of each allocation, thereby isolating any two allocations from one another. The top guard of the lower allocation is the bottom guard guard of the higher allocation etc. Therefore VM_NO_GUARD is dangerous; it breaks the basic premise of isolating separate allocations. There are only two in-tree users of this flag, neither of which use it through the exported interface. Ensure it stays this way. Link: https://lkml.kernel.org/r/YUMfdA36fuyZ+/xt@hirez.programming.kicks-ass.net Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Christoph Hellwig Reviewed-by: David Hildenbrand Acked-by: Will Deacon Acked-by: Kees Cook Cc: Andrey Konovalov Cc: Mel Gorman Cc: Uladzislau Rezki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 0ed56fc10c11..6e022cc712e6 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -22,7 +22,7 @@ struct notifier_block; /* in notifier.h */ #define VM_USERMAP 0x00000008 /* suitable for remap_vmalloc_range */ #define VM_DMA_COHERENT 0x00000010 /* dma_alloc_coherent */ #define VM_UNINITIALIZED 0x00000020 /* vm_struct is not fully initialized */ -#define VM_NO_GUARD 0x00000040 /* don't add guard page */ +#define VM_NO_GUARD 0x00000040 /* ***DANGEROUS*** don't add guard page */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ #define VM_FLUSH_RESET_PERMS 0x00000100 /* reset direct map and flush TLB on unmap, can't be freed in atomic context */ #define VM_MAP_PUT_PAGES 0x00000200 /* put pages and free array in vfree */ -- cgit v1.2.3 From 3252b1d8309ea42bc6329d9341072ecf1c9505c0 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 5 Nov 2021 13:39:47 -0700 Subject: kasan: arm64: fix pcpu_page_first_chunk crash with KASAN_VMALLOC With KASAN_VMALLOC and NEED_PER_CPU_PAGE_FIRST_CHUNK the kernel crashes: Unable to handle kernel paging request at virtual address ffff7000028f2000 ... swapper pgtable: 64k pages, 48-bit VAs, pgdp=0000000042440000 [ffff7000028f2000] pgd=000000063e7c0003, p4d=000000063e7c0003, pud=000000063e7c0003, pmd=000000063e7b0003, pte=0000000000000000 Internal error: Oops: 96000007 [#1] PREEMPT SMP Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 5.13.0-rc4-00003-gc6e6e28f3f30-dirty #62 Hardware name: linux,dummy-virt (DT) pstate: 200000c5 (nzCv daIF -PAN -UAO -TCO BTYPE=--) pc : kasan_check_range+0x90/0x1a0 lr : memcpy+0x88/0xf4 sp : ffff80001378fe20 ... Call trace: kasan_check_range+0x90/0x1a0 pcpu_page_first_chunk+0x3f0/0x568 setup_per_cpu_areas+0xb8/0x184 start_kernel+0x8c/0x328 The vm area used in vm_area_register_early() has no kasan shadow memory, Let's add a new kasan_populate_early_vm_area_shadow() function to populate the vm area shadow memory to fix the issue. [wangkefeng.wang@huawei.com: fix redefinition of 'kasan_populate_early_vm_area_shadow'] Link: https://lkml.kernel.org/r/20211011123211.3936196-1-wangkefeng.wang@huawei.com Link: https://lkml.kernel.org/r/20210910053354.26721-4-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Acked-by: Marco Elver [KASAN] Acked-by: Andrey Konovalov [KASAN] Acked-by: Catalin Marinas Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Greg Kroah-Hartman Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 736d7b458996..65487a3b2a71 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -436,6 +436,8 @@ void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end); +void kasan_populate_early_vm_area_shadow(void *start, unsigned long size); + #else /* CONFIG_KASAN_VMALLOC */ static inline int kasan_populate_vmalloc(unsigned long start, @@ -453,6 +455,10 @@ static inline void kasan_release_vmalloc(unsigned long start, unsigned long free_region_start, unsigned long free_region_end) {} +static inline void kasan_populate_early_vm_area_shadow(void *start, + unsigned long size) +{ } + #endif /* CONFIG_KASAN_VMALLOC */ #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ -- cgit v1.2.3 From c00b6b9610991c042ff4c3153daaa3ea8522c210 Mon Sep 17 00:00:00 2001 From: Chen Wandun Date: Fri, 5 Nov 2021 13:39:53 -0700 Subject: mm/vmalloc: introduce alloc_pages_bulk_array_mempolicy to accelerate memory allocation Commit ffb29b1c255a ("mm/vmalloc: fix numa spreading for large hash tables") can cause significant performance regressions in some situations as Andrew mentioned in [1]. The main situation is vmalloc, vmalloc will allocate pages with NUMA_NO_NODE by default, that will result in alloc page one by one; In order to solve this, __alloc_pages_bulk and mempolicy should be considered at the same time. 1) If node is specified in memory allocation request, it will alloc all pages by __alloc_pages_bulk. 2) If interleaving allocate memory, it will cauculate how many pages should be allocated in each node, and use __alloc_pages_bulk to alloc pages in each node. [1]: https://lore.kernel.org/lkml/CALvZod4G3SzP3kWxQYn0fj+VgG-G3yWXz=gz17+3N57ru1iajw@mail.gmail.com/t/#m750c8e3231206134293b089feaa090590afa0f60 [akpm@linux-foundation.org: coding style fixes] [akpm@linux-foundation.org: make two functions static] [akpm@linux-foundation.org: fix CONFIG_NUMA=n build] Link: https://lkml.kernel.org/r/20211021080744.874701-3-chenwandun@huawei.com Signed-off-by: Chen Wandun Reviewed-by: Uladzislau Rezki (Sony) Cc: Eric Dumazet Cc: Shakeel Butt Cc: Nicholas Piggin Cc: Kefeng Wang Cc: Hanjun Guo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index fbd4abc33f24..c1b262725dca 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -535,6 +535,10 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, struct list_head *page_list, struct page **page_array); +unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp, + unsigned long nr_pages, + struct page **page_array); + /* Bulk allocate order-0 pages */ static inline unsigned long alloc_pages_bulk_list(gfp_t gfp, unsigned long nr_pages, struct list_head *list) -- cgit v1.2.3 From 8ca1b5a49885f0c0c486544da46a9e0ac790831d Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Fri, 5 Nov 2021 13:40:34 -0700 Subject: mm/page_alloc: detect allocation forbidden by cpuset and bail out early There was a report that starting an Ubuntu in docker while using cpuset to bind it to movable nodes (a node only has movable zone, like a node for hotplug or a Persistent Memory node in normal usage) will fail due to memory allocation failure, and then OOM is involved and many other innocent processes got killed. It can be reproduced with command: $ docker run -it --rm --cpuset-mems 4 ubuntu:latest bash -c "grep Mems_allowed /proc/self/status" (where node 4 is a movable node) runc:[2:INIT] invoked oom-killer: gfp_mask=0x500cc2(GFP_HIGHUSER|__GFP_ACCOUNT), order=0, oom_score_adj=0 CPU: 8 PID: 8291 Comm: runc:[2:INIT] Tainted: G W I E 5.8.2-0.g71b519a-default #1 openSUSE Tumbleweed (unreleased) Hardware name: Dell Inc. PowerEdge R640/0PHYDR, BIOS 2.6.4 04/09/2020 Call Trace: dump_stack+0x6b/0x88 dump_header+0x4a/0x1e2 oom_kill_process.cold+0xb/0x10 out_of_memory.part.0+0xaf/0x230 out_of_memory+0x3d/0x80 __alloc_pages_slowpath.constprop.0+0x954/0xa20 __alloc_pages_nodemask+0x2d3/0x300 pipe_write+0x322/0x590 new_sync_write+0x196/0x1b0 vfs_write+0x1c3/0x1f0 ksys_write+0xa7/0xe0 do_syscall_64+0x52/0xd0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Mem-Info: active_anon:392832 inactive_anon:182 isolated_anon:0 active_file:68130 inactive_file:151527 isolated_file:0 unevictable:2701 dirty:0 writeback:7 slab_reclaimable:51418 slab_unreclaimable:116300 mapped:45825 shmem:735 pagetables:2540 bounce:0 free:159849484 free_pcp:73 free_cma:0 Node 4 active_anon:1448kB inactive_anon:0kB active_file:0kB inactive_file:0kB unevictable:0kB isolated(anon):0kB isolated(file):0kB mapped:0kB dirty:0kB writeback:0kB shmem:0kB shmem_thp: 0kB shmem_pmdmapped: 0kB anon_thp: 0kB writeback_tmp:0kB all_unreclaimable? no Node 4 Movable free:130021408kB min:9140kB low:139160kB high:269180kB reserved_highatomic:0KB active_anon:1448kB inactive_anon:0kB active_file:0kB inactive_file:0kB unevictable:0kB writepending:0kB present:130023424kB managed:130023424kB mlocked:0kB kernel_stack:0kB pagetables:0kB bounce:0kB free_pcp:292kB local_pcp:84kB free_cma:0kB lowmem_reserve[]: 0 0 0 0 0 Node 4 Movable: 1*4kB (M) 0*8kB 0*16kB 1*32kB (M) 0*64kB 0*128kB 1*256kB (M) 1*512kB (M) 1*1024kB (M) 0*2048kB 31743*4096kB (M) = 130021156kB oom-kill:constraint=CONSTRAINT_CPUSET,nodemask=(null),cpuset=docker-9976a269caec812c134fa317f27487ee36e1129beba7278a463dd53e5fb9997b.scope,mems_allowed=4,global_oom,task_memcg=/system.slice/containerd.service,task=containerd,pid=4100,uid=0 Out of memory: Killed process 4100 (containerd) total-vm:4077036kB, anon-rss:51184kB, file-rss:26016kB, shmem-rss:0kB, UID:0 pgtables:676kB oom_score_adj:0 oom_reaper: reaped process 8248 (docker), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB oom_reaper: reaped process 2054 (node_exporter), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB oom_reaper: reaped process 1452 (systemd-journal), now anon-rss:0kB, file-rss:8564kB, shmem-rss:4kB oom_reaper: reaped process 2146 (munin-node), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB oom_reaper: reaped process 8291 (runc:[2:INIT]), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB The reason is that in this case, the target cpuset nodes only have movable zone, while the creation of an OS in docker sometimes needs to allocate memory in non-movable zones (dma/dma32/normal) like GFP_HIGHUSER, and the cpuset limit forbids the allocation, then out-of-memory killing is involved even when normal nodes and movable nodes both have many free memory. The OOM killer cannot help to resolve the situation as there is no usable memory for the request in the cpuset scope. The only reasonable measure to take is to fail the allocation right away and have the caller to deal with it. So add a check for cases like this in the slowpath of allocation, and bail out early returning NULL for the allocation. As page allocation is one of the hottest path in kernel, this check will hurt all users with sane cpuset configuration, add a static branch check and detect the abnormal config in cpuset memory binding setup so that the extra check cost in page allocation is not paid by everyone. [thanks to Micho Hocko and David Rientjes for suggesting not handling it inside OOM code, adding cpuset check, refining comments] Link: https://lkml.kernel.org/r/1632481657-68112-1-git-send-email-feng.tang@intel.com Signed-off-by: Feng Tang Suggested-by: Michal Hocko Acked-by: Michal Hocko Cc: David Rientjes Cc: Tejun Heo Cc: Zefan Li Cc: Johannes Weiner Cc: Mel Gorman Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpuset.h | 17 +++++++++++++++++ include/linux/mmzone.h | 22 ++++++++++++++++++++++ 2 files changed, 39 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index d2b9c41c8edf..d58e0476ee8e 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -34,6 +34,8 @@ */ extern struct static_key_false cpusets_pre_enable_key; extern struct static_key_false cpusets_enabled_key; +extern struct static_key_false cpusets_insane_config_key; + static inline bool cpusets_enabled(void) { return static_branch_unlikely(&cpusets_enabled_key); @@ -51,6 +53,19 @@ static inline void cpuset_dec(void) static_branch_dec_cpuslocked(&cpusets_pre_enable_key); } +/* + * This will get enabled whenever a cpuset configuration is considered + * unsupportable in general. E.g. movable only node which cannot satisfy + * any non movable allocations (see update_nodemask). Page allocator + * needs to make additional checks for those configurations and this + * check is meant to guard those checks without any overhead for sane + * configurations. + */ +static inline bool cpusets_insane_config(void) +{ + return static_branch_unlikely(&cpusets_insane_config_key); +} + extern int cpuset_init(void); extern void cpuset_init_smp(void); extern void cpuset_force_rebuild(void); @@ -167,6 +182,8 @@ static inline void set_mems_allowed(nodemask_t nodemask) static inline bool cpusets_enabled(void) { return false; } +static inline bool cpusets_insane_config(void) { return false; } + static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 832aa49d0d8e..fb36a29e3aae 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1220,6 +1220,28 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, #define for_each_zone_zonelist(zone, z, zlist, highidx) \ for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, NULL) +/* Whether the 'nodes' are all movable nodes */ +static inline bool movable_only_nodes(nodemask_t *nodes) +{ + struct zonelist *zonelist; + struct zoneref *z; + int nid; + + if (nodes_empty(*nodes)) + return false; + + /* + * We can chose arbitrary node from the nodemask to get a + * zonelist as they are interlinked. We just need to find + * at least one zone that can satisfy kernel allocations. + */ + nid = first_node(*nodes); + zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK]; + z = first_zones_zonelist(zonelist, ZONE_NORMAL, nodes); + return (!z->zone) ? true : false; +} + + #ifdef CONFIG_SPARSEMEM #include #endif -- cgit v1.2.3 From d2635f2012a44e3d469ab9a4022162dbe0e53f21 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 5 Nov 2021 13:40:40 -0700 Subject: mm: create a new system state and fix core_kernel_text() core_kernel_text() considers that until system_state in at least SYSTEM_RUNNING, init memory is valid. But init memory is freed a few lines before setting SYSTEM_RUNNING, so we have a small period of time when core_kernel_text() is wrong. Create an intermediate system state called SYSTEM_FREEING_INIT that is set before starting freeing init memory, and use it in core_kernel_text() to report init memory invalid earlier. Link: https://lkml.kernel.org/r/9ecfdee7dd4d741d172cb93ff1d87f1c58127c9a.1633001016.git.christophe.leroy@csgroup.eu Signed-off-by: Christophe Leroy Cc: Gerald Schaefer Cc: Kefeng Wang Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Heiko Carstens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 2776423a587e..471bc0593679 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -248,6 +248,7 @@ extern bool early_boot_irqs_disabled; extern enum system_states { SYSTEM_BOOTING, SYSTEM_SCHEDULING, + SYSTEM_FREEING_INITMEM, SYSTEM_RUNNING, SYSTEM_HALT, SYSTEM_POWER_OFF, -- cgit v1.2.3 From 477d01fce8dacb41cae9363136ea56812e8baa59 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:40:58 -0700 Subject: mm: fix data race in PagePoisoned() PagePoisoned() accesses page->flags which can be updated concurrently: | BUG: KCSAN: data-race in next_uptodate_page / unlock_page | | write (marked) to 0xffffea00050f37c0 of 8 bytes by task 1872 on cpu 1: | instrument_atomic_write include/linux/instrumented.h:87 [inline] | clear_bit_unlock_is_negative_byte include/asm-generic/bitops/instrumented-lock.h:74 [inline] | unlock_page+0x102/0x1b0 mm/filemap.c:1465 | filemap_map_pages+0x6c6/0x890 mm/filemap.c:3057 | ... | read to 0xffffea00050f37c0 of 8 bytes by task 1873 on cpu 0: | PagePoisoned include/linux/page-flags.h:204 [inline] | PageReadahead include/linux/page-flags.h:382 [inline] | next_uptodate_page+0x456/0x830 mm/filemap.c:2975 | ... | CPU: 0 PID: 1873 Comm: systemd-udevd Not tainted 5.11.0-rc4-00001-gf9ce0be71d1f #1 To avoid the compiler tearing or otherwise optimizing the access, use READ_ONCE() to access flags. Link: https://lore.kernel.org/all/20210826144157.GA26950@xsang-OptiPlex-9020/ Link: https://lkml.kernel.org/r/20210913113542.2658064-1-elver@google.com Reported-by: kernel test robot Signed-off-by: Marco Elver Acked-by: Kirill A. Shutemov Acked-by: Will Deacon Cc: Marco Elver Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index fbfd3fad48f2..dd80cf0bb579 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -215,7 +215,7 @@ static __always_inline int PageCompound(struct page *page) #define PAGE_POISON_PATTERN -1l static inline int PagePoisoned(const struct page *page) { - return page->flags == PAGE_POISON_PATTERN; + return READ_ONCE(page->flags) == PAGE_POISON_PATTERN; } #ifdef CONFIG_DEBUG_VM -- cgit v1.2.3 From 73c54763482b841d9c14bad87eec98f80f700e0b Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 5 Nov 2021 13:41:17 -0700 Subject: mm/hugetlb: drop __unmap_hugepage_range definition from hugetlb.h Remove __unmap_hugepage_range() from the header file, because it is only used in hugetlb.c. Link: https://lkml.kernel.org/r/20210917165108.9341-1-peterx@redhat.com Signed-off-by: Peter Xu Suggested-by: Mike Kravetz Reviewed-by: Mike Kravetz Reviewed-by: John Hubbard Reviewed-by: Muchun Song Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 1faebe1cd0ed..3cbf60464398 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -143,9 +143,6 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page); -void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, - unsigned long start, unsigned long end, - struct page *ref_page); void hugetlb_report_meminfo(struct seq_file *); int hugetlb_report_node_meminfo(char *buf, int len, int nid); void hugetlb_show_meminfo(void); @@ -385,13 +382,6 @@ static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb, BUG(); } -static inline void __unmap_hugepage_range(struct mmu_gather *tlb, - struct vm_area_struct *vma, unsigned long start, - unsigned long end, struct page *ref_page) -{ - BUG(); -} - static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags) -- cgit v1.2.3 From 79dfc695525f60c8410015362b8aa4eb5c57210c Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 5 Nov 2021 13:41:20 -0700 Subject: hugetlb: add demote hugetlb page sysfs interfaces Patch series "hugetlb: add demote/split page functionality", v4. The concurrent use of multiple hugetlb page sizes on a single system is becoming more common. One of the reasons is better TLB support for gigantic page sizes on x86 hardware. In addition, hugetlb pages are being used to back VMs in hosting environments. When using hugetlb pages to back VMs, it is often desirable to preallocate hugetlb pools. This avoids the delay and uncertainty of allocating hugetlb pages at VM startup. In addition, preallocating huge pages minimizes the issue of memory fragmentation that increases the longer the system is up and running. In such environments, a combination of larger and smaller hugetlb pages are preallocated in anticipation of backing VMs of various sizes. Over time, the preallocated pool of smaller hugetlb pages may become depleted while larger hugetlb pages still remain. In such situations, it is desirable to convert larger hugetlb pages to smaller hugetlb pages. Converting larger to smaller hugetlb pages can be accomplished today by first freeing the larger page to the buddy allocator and then allocating the smaller pages. For example, to convert 50 GB pages on x86: gb_pages=`cat .../hugepages-1048576kB/nr_hugepages` m2_pages=`cat .../hugepages-2048kB/nr_hugepages` echo $(($gb_pages - 50)) > .../hugepages-1048576kB/nr_hugepages echo $(($m2_pages + 25600)) > .../hugepages-2048kB/nr_hugepages On an idle system this operation is fairly reliable and results are as expected. The number of 2MB pages is increased as expected and the time of the operation is a second or two. However, when there is activity on the system the following issues arise: 1) This process can take quite some time, especially if allocation of the smaller pages is not immediate and requires migration/compaction. 2) There is no guarantee that the total size of smaller pages allocated will match the size of the larger page which was freed. This is because the area freed by the larger page could quickly be fragmented. In a test environment with a load that continually fills the page cache with clean pages, results such as the following can be observed: Unexpected number of 2MB pages allocated: Expected 25600, have 19944 real 0m42.092s user 0m0.008s sys 0m41.467s To address these issues, introduce the concept of hugetlb page demotion. Demotion provides a means of 'in place' splitting of a hugetlb page to pages of a smaller size. This avoids freeing pages to buddy and then trying to allocate from buddy. Page demotion is controlled via sysfs files that reside in the per-hugetlb page size and per node directories. - demote_size Target page size for demotion, a smaller huge page size. File can be written to chose a smaller huge page size if multiple are available. - demote Writable number of hugetlb pages to be demoted To demote 50 GB huge pages, one would: cat .../hugepages-1048576kB/free_hugepages /* optional, verify free pages */ cat .../hugepages-1048576kB/demote_size /* optional, verify target size */ echo 50 > .../hugepages-1048576kB/demote Only hugetlb pages which are free at the time of the request can be demoted. Demotion does not add to the complexity of surplus pages and honors reserved huge pages. Therefore, when a value is written to the sysfs demote file, that value is only the maximum number of pages which will be demoted. It is possible fewer will actually be demoted. The recently introduced per-hstate mutex is used to synchronize demote operations with other operations that modify hugetlb pools. Real world use cases -------------------- The above scenario describes a real world use case where hugetlb pages are used to back VMs on x86. Both issues of long allocation times and not necessarily getting the expected number of smaller huge pages after a free and allocate cycle have been experienced. The occurrence of these issues is dependent on other activity within the host and can not be predicted. This patch (of 5): Two new sysfs files are added to demote hugtlb pages. These files are both per-hugetlb page size and per node. Files are: demote_size - The size in Kb that pages are demoted to. (read-write) demote - The number of huge pages to demote. (write-only) By default, demote_size is the next smallest huge page size. Valid huge page sizes less than huge page size may be written to this file. When huge pages are demoted, they are demoted to this size. Writing a value to demote will result in an attempt to demote that number of hugetlb pages to an appropriate number of demote_size pages. NOTE: Demote interfaces are only provided for huge page sizes if there is a smaller target demote huge page size. For example, on x86 1GB huge pages will have demote interfaces. 2MB huge pages will not have demote interfaces. This patch does not provide full demote functionality. It only provides the sysfs interfaces. It also provides documentation for the new interfaces. [mike.kravetz@oracle.com: n_mask initialization does not need to be protected by the mutex] Link: https://lkml.kernel.org/r/0530e4ef-2492-5186-f919-5db68edea654@oracle.com Link: https://lkml.kernel.org/r/20211007181918.136982-2-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reviewed-by: Oscar Salvador Cc: David Hildenbrand Cc: Michal Hocko Cc: Zi Yan Cc: Muchun Song Cc: Naoya Horiguchi Cc: David Rientjes Cc: "Aneesh Kumar K . V" Cc: Nghia Le Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 3cbf60464398..2bddd6c38204 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -586,6 +586,7 @@ struct hstate { int next_nid_to_alloc; int next_nid_to_free; unsigned int order; + unsigned int demote_order; unsigned long mask; unsigned long max_huge_pages; unsigned long nr_huge_pages; -- cgit v1.2.3 From 9871e2ded6c1ff61a59988d7a0e975f012105d52 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 5 Nov 2021 13:41:23 -0700 Subject: mm/cma: add cma_pages_valid to determine if pages are in CMA Add new interface cma_pages_valid() which indicates if the specified pages are part of a CMA region. This interface will be used in a subsequent patch by hugetlb code. In order to keep the same amount of DEBUG information, a pr_debug() call was added to cma_pages_valid(). In the case where the page passed to cma_release is not in cma region, the debug message will be printed from cma_pages_valid as opposed to cma_release. Link: https://lkml.kernel.org/r/20211007181918.136982-3-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Acked-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: "Aneesh Kumar K . V" Cc: David Rientjes Cc: Michal Hocko Cc: Muchun Song Cc: Naoya Horiguchi Cc: Nghia Le Cc: Zi Yan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cma.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cma.h b/include/linux/cma.h index 53fd8c3cdbd0..bd801023504b 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -46,6 +46,7 @@ extern int cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, struct cma **res_cma); extern struct page *cma_alloc(struct cma *cma, unsigned long count, unsigned int align, bool no_warn); +extern bool cma_pages_valid(struct cma *cma, const struct page *pages, unsigned long count); extern bool cma_release(struct cma *cma, const struct page *pages, unsigned long count); extern int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data); -- cgit v1.2.3 From bd3400ea173fb611cdf2030d03620185ff6c0b0e Mon Sep 17 00:00:00 2001 From: Liangcai Fan Date: Fri, 5 Nov 2021 13:41:36 -0700 Subject: mm: khugepaged: recalculate min_free_kbytes after stopping khugepaged When initializing transparent huge pages, min_free_kbytes would be calculated according to what khugepaged expected. So when transparent huge pages get disabled, min_free_kbytes should be recalculated instead of the higher value set by khugepaged. Link: https://lkml.kernel.org/r/1633937809-16558-1-git-send-email-liangcaifan19@gmail.com Signed-off-by: Liangcai Fan Signed-off-by: Chunyan Zhang Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6e29deb1e0d4..7e37c726b9db 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2453,6 +2453,7 @@ extern void memmap_init_range(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int migratetype); extern void setup_per_zone_wmarks(void); +extern void calculate_min_free_kbytes(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); extern void __init mmap_init(void); -- cgit v1.2.3 From 550a7d60bd5e35a56942dba6d8a26752beb26c9f Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Fri, 5 Nov 2021 13:41:40 -0700 Subject: mm, hugepages: add mremap() support for hugepage backed vma Support mremap() for hugepage backed vma segment by simply repositioning page table entries. The page table entries are repositioned to the new virtual address on mremap(). Hugetlb mremap() support is of course generic; my motivating use case is a library (hugepage_text), which reloads the ELF text of executables in hugepages. This significantly increases the execution performance of said executables. Restrict the mremap operation on hugepages to up to the size of the original mapping as the underlying hugetlb reservation is not yet capable of handling remapping to a larger size. During the mremap() operation we detect pmd_share'd mappings and we unshare those during the mremap(). On access and fault the sharing is established again. Link: https://lkml.kernel.org/r/20211013195825.3058275-1-almasrymina@google.com Signed-off-by: Mina Almasry Reviewed-by: Mike Kravetz Cc: Ken Chen Cc: Chris Kennelly Cc: Michal Hocko Cc: Vlastimil Babka Cc: Kirill Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 2bddd6c38204..c0a20781b28e 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -124,6 +124,7 @@ struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, void hugepage_put_subpool(struct hugepage_subpool *spool); void reset_vma_resv_huge_pages(struct vm_area_struct *vma); +void clear_vma_resv_huge_pages(struct vm_area_struct *vma); int hugetlb_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int hugetlb_overcommit_handler(struct ctl_table *, int, void *, size_t *, loff_t *); @@ -132,6 +133,10 @@ int hugetlb_treat_movable_handler(struct ctl_table *, int, void *, size_t *, int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); +int move_hugetlb_page_tables(struct vm_area_struct *vma, + struct vm_area_struct *new_vma, + unsigned long old_addr, unsigned long new_addr, + unsigned long len); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, @@ -215,6 +220,10 @@ static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma) { } +static inline void clear_vma_resv_huge_pages(struct vm_area_struct *vma) +{ +} + static inline unsigned long hugetlb_total_pages(void) { return 0; @@ -262,6 +271,16 @@ static inline int copy_hugetlb_page_range(struct mm_struct *dst, return 0; } +static inline int move_hugetlb_page_tables(struct vm_area_struct *vma, + struct vm_area_struct *new_vma, + unsigned long old_addr, + unsigned long new_addr, + unsigned long len) +{ + BUG(); + return 0; +} + static inline void hugetlb_report_meminfo(struct seq_file *m) { } -- cgit v1.2.3 From 8cd7c588decf470bf7e14f2be93b709f839a965e Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 5 Nov 2021 13:42:25 -0700 Subject: mm/vmscan: throttle reclaim until some writeback completes if congested Patch series "Remove dependency on congestion_wait in mm/", v5. This series that removes all calls to congestion_wait in mm/ and deletes wait_iff_congested. It's not a clever implementation but congestion_wait has been broken for a long time [1]. Even if congestion throttling worked, it was never a great idea. While excessive dirty/writeback pages at the tail of the LRU is one possibility that reclaim may be slow, there is also the problem of too many pages being isolated and reclaim failing for other reasons (elevated references, too many pages isolated, excessive LRU contention etc). This series replaces the "congestion" throttling with 3 different types. - If there are too many dirty/writeback pages, sleep until a timeout or enough pages get cleaned - If too many pages are isolated, sleep until enough isolated pages are either reclaimed or put back on the LRU - If no progress is being made, direct reclaim tasks sleep until another task makes progress with acceptable efficiency. This was initially tested with a mix of workloads that used to trigger corner cases that no longer work. A new test case was created called "stutterp" (pagereclaim-stutterp-noreaders in mmtests) using a freshly created XFS filesystem. Note that it may be necessary to increase the timeout of ssh if executing remotely as ssh itself can get throttled and the connection may timeout. stutterp varies the number of "worker" processes from 4 up to NR_CPUS*4 to check the impact as the number of direct reclaimers increase. It has four types of worker. - One "anon latency" worker creates small mappings with mmap() and times how long it takes to fault the mapping reading it 4K at a time - X file writers which is fio randomly writing X files where the total size of the files add up to the allowed dirty_ratio. fio is allowed to run for a warmup period to allow some file-backed pages to accumulate. The duration of the warmup is based on the best-case linear write speed of the storage. - Y file readers which is fio randomly reading small files - Z anon memory hogs which continually map (100-dirty_ratio)% of memory - Total estimated WSS = (100+dirty_ration) percentage of memory X+Y+Z+1 == NR_WORKERS varying from 4 up to NR_CPUS*4 The intent is to maximise the total WSS with a mix of file and anon memory where some anonymous memory must be swapped and there is a high likelihood of dirty/writeback pages reaching the end of the LRU. The test can be configured to have no background readers to stress dirty/writeback pages. The results below are based on having zero readers. The short summary of the results is that the series works and stalls until some event occurs but the timeouts may need adjustment. The test results are not broken down by patch as the series should be treated as one block that replaces a broken throttling mechanism with a working one. Finally, three machines were tested but I'm reporting the worst set of results. The other two machines had much better latencies for example. First the results of the "anon latency" latency stutterp 5.15.0-rc1 5.15.0-rc1 vanilla mm-reclaimcongest-v5r4 Amean mmap-4 31.4003 ( 0.00%) 2661.0198 (-8374.52%) Amean mmap-7 38.1641 ( 0.00%) 149.2891 (-291.18%) Amean mmap-12 60.0981 ( 0.00%) 187.8105 (-212.51%) Amean mmap-21 161.2699 ( 0.00%) 213.9107 ( -32.64%) Amean mmap-30 174.5589 ( 0.00%) 377.7548 (-116.41%) Amean mmap-48 8106.8160 ( 0.00%) 1070.5616 ( 86.79%) Stddev mmap-4 41.3455 ( 0.00%) 27573.9676 (-66591.66%) Stddev mmap-7 53.5556 ( 0.00%) 4608.5860 (-8505.23%) Stddev mmap-12 171.3897 ( 0.00%) 5559.4542 (-3143.75%) Stddev mmap-21 1506.6752 ( 0.00%) 5746.2507 (-281.39%) Stddev mmap-30 557.5806 ( 0.00%) 7678.1624 (-1277.05%) Stddev mmap-48 61681.5718 ( 0.00%) 14507.2830 ( 76.48%) Max-90 mmap-4 31.4243 ( 0.00%) 83.1457 (-164.59%) Max-90 mmap-7 41.0410 ( 0.00%) 41.0720 ( -0.08%) Max-90 mmap-12 66.5255 ( 0.00%) 53.9073 ( 18.97%) Max-90 mmap-21 146.7479 ( 0.00%) 105.9540 ( 27.80%) Max-90 mmap-30 193.9513 ( 0.00%) 64.3067 ( 66.84%) Max-90 mmap-48 277.9137 ( 0.00%) 591.0594 (-112.68%) Max mmap-4 1913.8009 ( 0.00%) 299623.9695 (-15555.96%) Max mmap-7 2423.9665 ( 0.00%) 204453.1708 (-8334.65%) Max mmap-12 6845.6573 ( 0.00%) 221090.3366 (-3129.64%) Max mmap-21 56278.6508 ( 0.00%) 213877.3496 (-280.03%) Max mmap-30 19716.2990 ( 0.00%) 216287.6229 (-997.00%) Max mmap-48 477923.9400 ( 0.00%) 245414.8238 ( 48.65%) For most thread counts, the time to mmap() is unfortunately increased. In earlier versions of the series, this was lower but a large number of throttling events were reaching their timeout increasing the amount of inefficient scanning of the LRU. There is no prioritisation of reclaim tasks making progress based on each tasks rate of page allocation versus progress of reclaim. The variance is also impacted for high worker counts but in all cases, the differences in latency are not statistically significant due to very large maximum outliers. Max-90 shows that 90% of the stalls are comparable but the Max results show the massive outliers which are increased to to stalling. It is expected that this will be very machine dependant. Due to the test design, reclaim is difficult so allocations stall and there are variances depending on whether THPs can be allocated or not. The amount of memory will affect exactly how bad the corner cases are and how often they trigger. The warmup period calculation is not ideal as it's based on linear writes where as fio is randomly writing multiple files from multiple tasks so the start state of the test is variable. For example, these are the latencies on a single-socket machine that had more memory Amean mmap-4 42.2287 ( 0.00%) 49.6838 * -17.65%* Amean mmap-7 216.4326 ( 0.00%) 47.4451 * 78.08%* Amean mmap-12 2412.0588 ( 0.00%) 51.7497 ( 97.85%) Amean mmap-21 5546.2548 ( 0.00%) 51.8862 ( 99.06%) Amean mmap-30 1085.3121 ( 0.00%) 72.1004 ( 93.36%) The overall system CPU usage and elapsed time is as follows 5.15.0-rc3 5.15.0-rc3 vanilla mm-reclaimcongest-v5r4 Duration User 6989.03 983.42 Duration System 7308.12 799.68 Duration Elapsed 2277.67 2092.98 The patches reduce system CPU usage by 89% as the vanilla kernel is rarely stalling. The high-level /proc/vmstats show 5.15.0-rc1 5.15.0-rc1 vanilla mm-reclaimcongest-v5r2 Ops Direct pages scanned 1056608451.00 503594991.00 Ops Kswapd pages scanned 109795048.00 147289810.00 Ops Kswapd pages reclaimed 63269243.00 31036005.00 Ops Direct pages reclaimed 10803973.00 6328887.00 Ops Kswapd efficiency % 57.62 21.07 Ops Kswapd velocity 48204.98 57572.86 Ops Direct efficiency % 1.02 1.26 Ops Direct velocity 463898.83 196845.97 Kswapd scanned less pages but the detailed pattern is different. The vanilla kernel scans slowly over time where as the patches exhibits burst patterns of scan activity. Direct reclaim scanning is reduced by 52% due to stalling. The pattern for stealing pages is also slightly different. Both kernels exhibit spikes but the vanilla kernel when reclaiming shows pages being reclaimed over a period of time where as the patches tend to reclaim in spikes. The difference is that vanilla is not throttling and instead scanning constantly finding some pages over time where as the patched kernel throttles and reclaims in spikes. Ops Percentage direct scans 90.59 77.37 For direct reclaim, vanilla scanned 90.59% of pages where as with the patches, 77.37% were direct reclaim due to throttling Ops Page writes by reclaim 2613590.00 1687131.00 Page writes from reclaim context are reduced. Ops Page writes anon 2932752.00 1917048.00 And there is less swapping. Ops Page reclaim immediate 996248528.00 107664764.00 The number of pages encountered at the tail of the LRU tagged for immediate reclaim but still dirty/writeback is reduced by 89%. Ops Slabs scanned 164284.00 153608.00 Slab scan activity is similar. ftrace was used to gather stall activity Vanilla ------- 1 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=16000 2 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=12000 8 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=8000 29 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=4000 82394 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=0 The fast majority of wait_iff_congested calls do not stall at all. What is likely happening is that cond_resched() reschedules the task for a short period when the BDI is not registering congestion (which it never will in this test setup). 1 writeback_congestion_wait: usec_timeout=100000 usec_delayed=120000 2 writeback_congestion_wait: usec_timeout=100000 usec_delayed=132000 4 writeback_congestion_wait: usec_timeout=100000 usec_delayed=112000 380 writeback_congestion_wait: usec_timeout=100000 usec_delayed=108000 778 writeback_congestion_wait: usec_timeout=100000 usec_delayed=104000 congestion_wait if called always exceeds the timeout as there is no trigger to wake it up. Bottom line: Vanilla will throttle but it's not effective. Patch series ------------ Kswapd throttle activity was always due to scanning pages tagged for immediate reclaim at the tail of the LRU 1 usec_timeout=100000 usect_delayed=72000 reason=VMSCAN_THROTTLE_WRITEBACK 4 usec_timeout=100000 usect_delayed=20000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=12000 reason=VMSCAN_THROTTLE_WRITEBACK 6 usec_timeout=100000 usect_delayed=16000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=100000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=8000 reason=VMSCAN_THROTTLE_WRITEBACK 94 usec_timeout=100000 usect_delayed=0 reason=VMSCAN_THROTTLE_WRITEBACK 112 usec_timeout=100000 usect_delayed=4000 reason=VMSCAN_THROTTLE_WRITEBACK The majority of events did not stall or stalled for a short period. Roughly 16% of stalls reached the timeout before expiry. For direct reclaim, the number of times stalled for each reason were 6624 reason=VMSCAN_THROTTLE_ISOLATED 93246 reason=VMSCAN_THROTTLE_NOPROGRESS 96934 reason=VMSCAN_THROTTLE_WRITEBACK The most common reason to stall was due to excessive pages tagged for immediate reclaim at the tail of the LRU followed by a failure to make forward. A relatively small number were due to too many pages isolated from the LRU by parallel threads For VMSCAN_THROTTLE_ISOLATED, the breakdown of delays was 9 usec_timeout=20000 usect_delayed=4000 reason=VMSCAN_THROTTLE_ISOLATED 12 usec_timeout=20000 usect_delayed=16000 reason=VMSCAN_THROTTLE_ISOLATED 83 usec_timeout=20000 usect_delayed=20000 reason=VMSCAN_THROTTLE_ISOLATED 6520 usec_timeout=20000 usect_delayed=0 reason=VMSCAN_THROTTLE_ISOLATED Most did not stall at all. A small number reached the timeout. For VMSCAN_THROTTLE_NOPROGRESS, the breakdown of stalls were all over the map 1 usec_timeout=500000 usect_delayed=324000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=332000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=348000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=360000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=228000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=260000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=340000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=364000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=372000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=428000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=460000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=464000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=244000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=252000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=272000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=188000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=268000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=328000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=380000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=392000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=432000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=204000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=220000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=412000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=436000 reason=VMSCAN_THROTTLE_NOPROGRESS 6 usec_timeout=500000 usect_delayed=488000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=212000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=300000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=316000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=472000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=248000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=356000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=456000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=124000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=376000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=484000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=172000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=420000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=452000 reason=VMSCAN_THROTTLE_NOPROGRESS 11 usec_timeout=500000 usect_delayed=256000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=112000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=116000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=144000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=152000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=264000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=384000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=424000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=492000 reason=VMSCAN_THROTTLE_NOPROGRESS 13 usec_timeout=500000 usect_delayed=184000 reason=VMSCAN_THROTTLE_NOPROGRESS 13 usec_timeout=500000 usect_delayed=444000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=308000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=440000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=476000 reason=VMSCAN_THROTTLE_NOPROGRESS 16 usec_timeout=500000 usect_delayed=140000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=232000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=240000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=280000 reason=VMSCAN_THROTTLE_NOPROGRESS 18 usec_timeout=500000 usect_delayed=404000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=148000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=216000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=468000 reason=VMSCAN_THROTTLE_NOPROGRESS 21 usec_timeout=500000 usect_delayed=448000 reason=VMSCAN_THROTTLE_NOPROGRESS 23 usec_timeout=500000 usect_delayed=168000 reason=VMSCAN_THROTTLE_NOPROGRESS 23 usec_timeout=500000 usect_delayed=296000 reason=VMSCAN_THROTTLE_NOPROGRESS 25 usec_timeout=500000 usect_delayed=132000 reason=VMSCAN_THROTTLE_NOPROGRESS 25 usec_timeout=500000 usect_delayed=352000 reason=VMSCAN_THROTTLE_NOPROGRESS 26 usec_timeout=500000 usect_delayed=180000 reason=VMSCAN_THROTTLE_NOPROGRESS 27 usec_timeout=500000 usect_delayed=284000 reason=VMSCAN_THROTTLE_NOPROGRESS 28 usec_timeout=500000 usect_delayed=164000 reason=VMSCAN_THROTTLE_NOPROGRESS 29 usec_timeout=500000 usect_delayed=136000 reason=VMSCAN_THROTTLE_NOPROGRESS 30 usec_timeout=500000 usect_delayed=200000 reason=VMSCAN_THROTTLE_NOPROGRESS 30 usec_timeout=500000 usect_delayed=400000 reason=VMSCAN_THROTTLE_NOPROGRESS 31 usec_timeout=500000 usect_delayed=196000 reason=VMSCAN_THROTTLE_NOPROGRESS 32 usec_timeout=500000 usect_delayed=156000 reason=VMSCAN_THROTTLE_NOPROGRESS 33 usec_timeout=500000 usect_delayed=224000 reason=VMSCAN_THROTTLE_NOPROGRESS 35 usec_timeout=500000 usect_delayed=128000 reason=VMSCAN_THROTTLE_NOPROGRESS 35 usec_timeout=500000 usect_delayed=176000 reason=VMSCAN_THROTTLE_NOPROGRESS 36 usec_timeout=500000 usect_delayed=368000 reason=VMSCAN_THROTTLE_NOPROGRESS 36 usec_timeout=500000 usect_delayed=496000 reason=VMSCAN_THROTTLE_NOPROGRESS 37 usec_timeout=500000 usect_delayed=312000 reason=VMSCAN_THROTTLE_NOPROGRESS 38 usec_timeout=500000 usect_delayed=304000 reason=VMSCAN_THROTTLE_NOPROGRESS 40 usec_timeout=500000 usect_delayed=288000 reason=VMSCAN_THROTTLE_NOPROGRESS 43 usec_timeout=500000 usect_delayed=408000 reason=VMSCAN_THROTTLE_NOPROGRESS 55 usec_timeout=500000 usect_delayed=416000 reason=VMSCAN_THROTTLE_NOPROGRESS 56 usec_timeout=500000 usect_delayed=76000 reason=VMSCAN_THROTTLE_NOPROGRESS 58 usec_timeout=500000 usect_delayed=120000 reason=VMSCAN_THROTTLE_NOPROGRESS 59 usec_timeout=500000 usect_delayed=208000 reason=VMSCAN_THROTTLE_NOPROGRESS 61 usec_timeout=500000 usect_delayed=68000 reason=VMSCAN_THROTTLE_NOPROGRESS 71 usec_timeout=500000 usect_delayed=192000 reason=VMSCAN_THROTTLE_NOPROGRESS 71 usec_timeout=500000 usect_delayed=480000 reason=VMSCAN_THROTTLE_NOPROGRESS 79 usec_timeout=500000 usect_delayed=60000 reason=VMSCAN_THROTTLE_NOPROGRESS 82 usec_timeout=500000 usect_delayed=320000 reason=VMSCAN_THROTTLE_NOPROGRESS 82 usec_timeout=500000 usect_delayed=92000 reason=VMSCAN_THROTTLE_NOPROGRESS 85 usec_timeout=500000 usect_delayed=64000 reason=VMSCAN_THROTTLE_NOPROGRESS 85 usec_timeout=500000 usect_delayed=80000 reason=VMSCAN_THROTTLE_NOPROGRESS 88 usec_timeout=500000 usect_delayed=84000 reason=VMSCAN_THROTTLE_NOPROGRESS 90 usec_timeout=500000 usect_delayed=160000 reason=VMSCAN_THROTTLE_NOPROGRESS 90 usec_timeout=500000 usect_delayed=292000 reason=VMSCAN_THROTTLE_NOPROGRESS 94 usec_timeout=500000 usect_delayed=56000 reason=VMSCAN_THROTTLE_NOPROGRESS 118 usec_timeout=500000 usect_delayed=88000 reason=VMSCAN_THROTTLE_NOPROGRESS 119 usec_timeout=500000 usect_delayed=72000 reason=VMSCAN_THROTTLE_NOPROGRESS 126 usec_timeout=500000 usect_delayed=108000 reason=VMSCAN_THROTTLE_NOPROGRESS 146 usec_timeout=500000 usect_delayed=52000 reason=VMSCAN_THROTTLE_NOPROGRESS 148 usec_timeout=500000 usect_delayed=36000 reason=VMSCAN_THROTTLE_NOPROGRESS 148 usec_timeout=500000 usect_delayed=48000 reason=VMSCAN_THROTTLE_NOPROGRESS 159 usec_timeout=500000 usect_delayed=28000 reason=VMSCAN_THROTTLE_NOPROGRESS 178 usec_timeout=500000 usect_delayed=44000 reason=VMSCAN_THROTTLE_NOPROGRESS 183 usec_timeout=500000 usect_delayed=40000 reason=VMSCAN_THROTTLE_NOPROGRESS 237 usec_timeout=500000 usect_delayed=100000 reason=VMSCAN_THROTTLE_NOPROGRESS 266 usec_timeout=500000 usect_delayed=32000 reason=VMSCAN_THROTTLE_NOPROGRESS 313 usec_timeout=500000 usect_delayed=24000 reason=VMSCAN_THROTTLE_NOPROGRESS 347 usec_timeout=500000 usect_delayed=96000 reason=VMSCAN_THROTTLE_NOPROGRESS 470 usec_timeout=500000 usect_delayed=20000 reason=VMSCAN_THROTTLE_NOPROGRESS 559 usec_timeout=500000 usect_delayed=16000 reason=VMSCAN_THROTTLE_NOPROGRESS 964 usec_timeout=500000 usect_delayed=12000 reason=VMSCAN_THROTTLE_NOPROGRESS 2001 usec_timeout=500000 usect_delayed=104000 reason=VMSCAN_THROTTLE_NOPROGRESS 2447 usec_timeout=500000 usect_delayed=8000 reason=VMSCAN_THROTTLE_NOPROGRESS 7888 usec_timeout=500000 usect_delayed=4000 reason=VMSCAN_THROTTLE_NOPROGRESS 22727 usec_timeout=500000 usect_delayed=0 reason=VMSCAN_THROTTLE_NOPROGRESS 51305 usec_timeout=500000 usect_delayed=500000 reason=VMSCAN_THROTTLE_NOPROGRESS The full timeout is often hit but a large number also do not stall at all. The remainder slept a little allowing other reclaim tasks to make progress. While this timeout could be further increased, it could also negatively impact worst-case behaviour when there is no prioritisation of what task should make progress. For VMSCAN_THROTTLE_WRITEBACK, the breakdown was 1 usec_timeout=100000 usect_delayed=44000 reason=VMSCAN_THROTTLE_WRITEBACK 2 usec_timeout=100000 usect_delayed=76000 reason=VMSCAN_THROTTLE_WRITEBACK 3 usec_timeout=100000 usect_delayed=80000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=48000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=84000 reason=VMSCAN_THROTTLE_WRITEBACK 6 usec_timeout=100000 usect_delayed=72000 reason=VMSCAN_THROTTLE_WRITEBACK 7 usec_timeout=100000 usect_delayed=88000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=56000 reason=VMSCAN_THROTTLE_WRITEBACK 12 usec_timeout=100000 usect_delayed=64000 reason=VMSCAN_THROTTLE_WRITEBACK 16 usec_timeout=100000 usect_delayed=92000 reason=VMSCAN_THROTTLE_WRITEBACK 24 usec_timeout=100000 usect_delayed=68000 reason=VMSCAN_THROTTLE_WRITEBACK 28 usec_timeout=100000 usect_delayed=32000 reason=VMSCAN_THROTTLE_WRITEBACK 30 usec_timeout=100000 usect_delayed=60000 reason=VMSCAN_THROTTLE_WRITEBACK 30 usec_timeout=100000 usect_delayed=96000 reason=VMSCAN_THROTTLE_WRITEBACK 32 usec_timeout=100000 usect_delayed=52000 reason=VMSCAN_THROTTLE_WRITEBACK 42 usec_timeout=100000 usect_delayed=40000 reason=VMSCAN_THROTTLE_WRITEBACK 77 usec_timeout=100000 usect_delayed=28000 reason=VMSCAN_THROTTLE_WRITEBACK 99 usec_timeout=100000 usect_delayed=36000 reason=VMSCAN_THROTTLE_WRITEBACK 137 usec_timeout=100000 usect_delayed=24000 reason=VMSCAN_THROTTLE_WRITEBACK 190 usec_timeout=100000 usect_delayed=20000 reason=VMSCAN_THROTTLE_WRITEBACK 339 usec_timeout=100000 usect_delayed=16000 reason=VMSCAN_THROTTLE_WRITEBACK 518 usec_timeout=100000 usect_delayed=12000 reason=VMSCAN_THROTTLE_WRITEBACK 852 usec_timeout=100000 usect_delayed=8000 reason=VMSCAN_THROTTLE_WRITEBACK 3359 usec_timeout=100000 usect_delayed=4000 reason=VMSCAN_THROTTLE_WRITEBACK 7147 usec_timeout=100000 usect_delayed=0 reason=VMSCAN_THROTTLE_WRITEBACK 83962 usec_timeout=100000 usect_delayed=100000 reason=VMSCAN_THROTTLE_WRITEBACK The majority hit the timeout in direct reclaim context although a sizable number did not stall at all. This is very different to kswapd where only a tiny percentage of stalls due to writeback reached the timeout. Bottom line, the throttling appears to work and the wakeup events may limit worst case stalls. There might be some grounds for adjusting timeouts but it's likely futile as the worst-case scenarios depend on the workload, memory size and the speed of the storage. A better approach to improve the series further would be to prioritise tasks based on their rate of allocation with the caveat that it may be very expensive to track. This patch (of 5): Page reclaim throttles on wait_iff_congested under the following conditions: - kswapd is encountering pages under writeback and marked for immediate reclaim implying that pages are cycling through the LRU faster than pages can be cleaned. - Direct reclaim will stall if all dirty pages are backed by congested inodes. wait_iff_congested is almost completely broken with few exceptions. This patch adds a new node-based workqueue and tracks the number of throttled tasks and pages written back since throttling started. If enough pages belonging to the node are written back then the throttled tasks will wake early. If not, the throttled tasks sleeps until the timeout expires. [neilb@suse.de: Uninterruptible sleep and simpler wakeups] [hdanton@sina.com: Avoid race when reclaim starts] [vbabka@suse.cz: vmstat irq-safe api, clarifications] Link: https://lore.kernel.org/linux-mm/45d8b7a6-8548-65f5-cccf-9f451d4ae3d4@kernel.dk/ [1] Link: https://lkml.kernel.org/r/20211022144651.19914-1-mgorman@techsingularity.net Link: https://lkml.kernel.org/r/20211022144651.19914-2-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: NeilBrown Cc: "Theodore Ts'o" Cc: Andreas Dilger Cc: "Darrick J . Wong" Cc: Matthew Wilcox Cc: Michal Hocko Cc: Dave Chinner Cc: Rik van Riel Cc: Johannes Weiner Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev.h | 1 - include/linux/mmzone.h | 13 +++++++++++++ 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index ac7f231b8825..9fb1f0ae273c 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -154,7 +154,6 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) } long congestion_wait(int sync, long timeout); -long wait_iff_congested(int sync, long timeout); static inline bool mapping_can_writeback(struct address_space *mapping) { diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fb36a29e3aae..5a5e19b90dab 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -199,6 +199,7 @@ enum node_stat_item { NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ + NR_THROTTLED_WRITTEN, /* NR_WRITTEN while reclaim throttled */ NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ NR_FOLL_PIN_ACQUIRED, /* via: pin_user_page(), gup flag: FOLL_PIN */ NR_FOLL_PIN_RELEASED, /* pages returned via unpin_user_page() */ @@ -272,6 +273,11 @@ enum lru_list { NR_LRU_LISTS }; +enum vmscan_throttle_state { + VMSCAN_THROTTLE_WRITEBACK, + NR_VMSCAN_THROTTLE, +}; + #define for_each_lru(lru) for (lru = 0; lru < NR_LRU_LISTS; lru++) #define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++) @@ -841,6 +847,13 @@ typedef struct pglist_data { int node_id; wait_queue_head_t kswapd_wait; wait_queue_head_t pfmemalloc_wait; + + /* workqueues for throttling reclaim for different reasons. */ + wait_queue_head_t reclaim_wait[NR_VMSCAN_THROTTLE]; + + atomic_t nr_writeback_throttled;/* nr of writeback-throttled tasks */ + unsigned long nr_reclaim_start; /* nr pages written while throttled + * when throttling started. */ struct task_struct *kswapd; /* Protected by mem_hotplug_begin/end() */ int kswapd_order; -- cgit v1.2.3 From d818fca1cac31b1fc9301bda83e195a46fb4ebaa Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 5 Nov 2021 13:42:29 -0700 Subject: mm/vmscan: throttle reclaim and compaction when too may pages are isolated Page reclaim throttles on congestion if too many parallel reclaim instances have isolated too many pages. This makes no sense, excessive parallelisation has nothing to do with writeback or congestion. This patch creates an additional workqueue to sleep on when too many pages are isolated. The throttled tasks are woken when the number of isolated pages is reduced or a timeout occurs. There may be some false positive wakeups for GFP_NOIO/GFP_NOFS callers but the tasks will throttle again if necessary. [shy828301@gmail.com: Wake up from compaction context] [vbabka@suse.cz: Account number of throttled tasks only for writeback] Link: https://lkml.kernel.org/r/20211022144651.19914-3-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Andreas Dilger Cc: "Darrick J . Wong" Cc: Dave Chinner Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Michal Hocko Cc: NeilBrown Cc: Rik van Riel Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 5a5e19b90dab..312c1ea9aafa 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -275,6 +275,7 @@ enum lru_list { enum vmscan_throttle_state { VMSCAN_THROTTLE_WRITEBACK, + VMSCAN_THROTTLE_ISOLATED, NR_VMSCAN_THROTTLE, }; -- cgit v1.2.3 From 69392a403f49e6e33f9dfb1d6edb87c8006f83c2 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 5 Nov 2021 13:42:32 -0700 Subject: mm/vmscan: throttle reclaim when no progress is being made Memcg reclaim throttles on congestion if no reclaim progress is made. This makes little sense, it might be due to writeback or a host of other factors. For !memcg reclaim, it's messy. Direct reclaim primarily is throttled in the page allocator if it is failing to make progress. Kswapd throttles if too many pages are under writeback and marked for immediate reclaim. This patch explicitly throttles if reclaim is failing to make progress. [vbabka@suse.cz: Remove redundant code] Link: https://lkml.kernel.org/r/20211022144651.19914-4-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Andreas Dilger Cc: "Darrick J . Wong" Cc: Dave Chinner Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Michal Hocko Cc: NeilBrown Cc: Rik van Riel Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 312c1ea9aafa..58e744b78c2c 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -276,6 +276,7 @@ enum lru_list { enum vmscan_throttle_state { VMSCAN_THROTTLE_WRITEBACK, VMSCAN_THROTTLE_ISOLATED, + VMSCAN_THROTTLE_NOPROGRESS, NR_VMSCAN_THROTTLE, }; -- cgit v1.2.3 From 7e6ec49c18988f1b8dab0677271dafde5f8d9a43 Mon Sep 17 00:00:00 2001 From: Yuanzheng Song Date: Fri, 5 Nov 2021 13:42:52 -0700 Subject: mm/vmpressure: fix data-race with memcg->socket_pressure When reading memcg->socket_pressure in mem_cgroup_under_socket_pressure() and writing memcg->socket_pressure in vmpressure() at the same time, the following data-race occurs: BUG: KCSAN: data-race in __sk_mem_reduce_allocated / vmpressure write to 0xffff8881286f4938 of 8 bytes by task 24550 on cpu 3: vmpressure+0x218/0x230 mm/vmpressure.c:307 shrink_node_memcgs+0x2b9/0x410 mm/vmscan.c:2658 shrink_node+0x9d2/0x11d0 mm/vmscan.c:2769 shrink_zones+0x29f/0x470 mm/vmscan.c:2972 do_try_to_free_pages+0x193/0x6e0 mm/vmscan.c:3027 try_to_free_mem_cgroup_pages+0x1c0/0x3f0 mm/vmscan.c:3345 reclaim_high mm/memcontrol.c:2440 [inline] mem_cgroup_handle_over_high+0x18b/0x4d0 mm/memcontrol.c:2624 tracehook_notify_resume include/linux/tracehook.h:197 [inline] exit_to_user_mode_loop kernel/entry/common.c:164 [inline] exit_to_user_mode_prepare+0x110/0x170 kernel/entry/common.c:191 syscall_exit_to_user_mode+0x16/0x30 kernel/entry/common.c:266 ret_from_fork+0x15/0x30 arch/x86/entry/entry_64.S:289 read to 0xffff8881286f4938 of 8 bytes by interrupt on cpu 1: mem_cgroup_under_socket_pressure include/linux/memcontrol.h:1483 [inline] sk_under_memory_pressure include/net/sock.h:1314 [inline] __sk_mem_reduce_allocated+0x1d2/0x270 net/core/sock.c:2696 __sk_mem_reclaim+0x44/0x50 net/core/sock.c:2711 sk_mem_reclaim include/net/sock.h:1490 [inline] ...... net_rx_action+0x17a/0x480 net/core/dev.c:6864 __do_softirq+0x12c/0x2af kernel/softirq.c:298 run_ksoftirqd+0x13/0x20 kernel/softirq.c:653 smpboot_thread_fn+0x33f/0x510 kernel/smpboot.c:165 kthread+0x1fc/0x220 kernel/kthread.c:292 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:296 Fix it by using READ_ONCE() and WRITE_ONCE() to read and write memcg->socket_pressure. Link: https://lkml.kernel.org/r/20211025082843.671690-1-songyuanzheng@huawei.com Signed-off-by: Yuanzheng Song Reviewed-by: Muchun Song Cc: Shakeel Butt Cc: Roman Gushchin Cc: Johannes Weiner Cc: Michal Hocko Cc: Matthew Wilcox (Oracle) Cc: Alex Shi Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index f207f98bdb76..9d96238d9c21 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1606,7 +1606,7 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure) return true; do { - if (time_before(jiffies, memcg->socket_pressure)) + if (time_before(jiffies, READ_ONCE(memcg->socket_pressure))) return true; } while ((memcg = parent_mem_cgroup(memcg))); return false; -- cgit v1.2.3 From fa27717110ae51b9b9013ced0b5143888257bb79 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 5 Nov 2021 13:43:13 -0700 Subject: memblock: drop memblock_free_early_nid() and memblock_free_early() memblock_free_early_nid() is unused and memblock_free_early() is an alias for memblock_free(). Replace calls to memblock_free_early() with calls to memblock_free() and remove memblock_free_early() and memblock_free_early_nid(). Link: https://lkml.kernel.org/r/20210930185031.18648-4-rppt@kernel.org Signed-off-by: Mike Rapoport Cc: Christophe Leroy Cc: Juergen Gross Cc: Shahab Vahedi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 34de69b3b8ba..fc8183be340c 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -441,18 +441,6 @@ static inline void *memblock_alloc_node(phys_addr_t size, MEMBLOCK_ALLOC_ACCESSIBLE, nid); } -static inline void memblock_free_early(phys_addr_t base, - phys_addr_t size) -{ - memblock_free(base, size); -} - -static inline void memblock_free_early_nid(phys_addr_t base, - phys_addr_t size, int nid) -{ - memblock_free(base, size); -} - static inline void memblock_free_late(phys_addr_t base, phys_addr_t size) { __memblock_free_late(base, size); -- cgit v1.2.3 From 621d973901cf9fa6c6e31b31bdd36c5c5f3c9c9e Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 5 Nov 2021 13:43:16 -0700 Subject: memblock: stop aliasing __memblock_free_late with memblock_free_late memblock_free_late() is a NOP wrapper for __memblock_free_late(), there is no point to keep this indirection. Drop the wrapper and rename __memblock_free_late() to memblock_free_late(). Link: https://lkml.kernel.org/r/20210930185031.18648-5-rppt@kernel.org Signed-off-by: Mike Rapoport Cc: Christophe Leroy Cc: Juergen Gross Cc: Shahab Vahedi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index fc8183be340c..e25f964fdd60 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -133,7 +133,7 @@ void __next_mem_range_rev(u64 *idx, int nid, enum memblock_flags flags, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid); -void __memblock_free_late(phys_addr_t base, phys_addr_t size); +void memblock_free_late(phys_addr_t base, phys_addr_t size); #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, @@ -441,11 +441,6 @@ static inline void *memblock_alloc_node(phys_addr_t size, MEMBLOCK_ALLOC_ACCESSIBLE, nid); } -static inline void memblock_free_late(phys_addr_t base, phys_addr_t size) -{ - __memblock_free_late(base, size); -} - /* * Set the allocation direction to bottom-up or top-down. */ -- cgit v1.2.3 From 3ecc68349bbab6bff1d12cbc7951ca6019b2faf6 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 5 Nov 2021 13:43:19 -0700 Subject: memblock: rename memblock_free to memblock_phys_free Since memblock_free() operates on a physical range, make its name reflect it and rename it to memblock_phys_free(), so it will be a logical counterpart to memblock_phys_alloc(). The callers are updated with the below semantic patch: @@ expression addr; expression size; @@ - memblock_free(addr, size); + memblock_phys_free(addr, size); Link: https://lkml.kernel.org/r/20210930185031.18648-6-rppt@kernel.org Signed-off-by: Mike Rapoport Cc: Christophe Leroy Cc: Juergen Gross Cc: Shahab Vahedi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index e25f964fdd60..d32d41709513 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -103,7 +103,7 @@ void memblock_allow_resize(void); int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid); int memblock_add(phys_addr_t base, phys_addr_t size); int memblock_remove(phys_addr_t base, phys_addr_t size); -int memblock_free(phys_addr_t base, phys_addr_t size); +int memblock_phys_free(phys_addr_t base, phys_addr_t size); int memblock_reserve(phys_addr_t base, phys_addr_t size); #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP int memblock_physmem_add(phys_addr_t base, phys_addr_t size); -- cgit v1.2.3 From 4421cca0a3e4833b3bf0f20de98eb580ab8c7290 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 5 Nov 2021 13:43:22 -0700 Subject: memblock: use memblock_free for freeing virtual pointers Rename memblock_free_ptr() to memblock_free() and use memblock_free() when freeing a virtual pointer so that memblock_free() will be a counterpart of memblock_alloc() The callers are updated with the below semantic patch and manual addition of (void *) casting to pointers that are represented by unsigned long variables. @@ identifier vaddr; expression size; @@ ( - memblock_phys_free(__pa(vaddr), size); + memblock_free(vaddr, size); | - memblock_free_ptr(vaddr, size); + memblock_free(vaddr, size); ) [sfr@canb.auug.org.au: fixup] Link: https://lkml.kernel.org/r/20211018192940.3d1d532f@canb.auug.org.au Link: https://lkml.kernel.org/r/20210930185031.18648-7-rppt@kernel.org Signed-off-by: Mike Rapoport Signed-off-by: Stephen Rothwell Cc: Christophe Leroy Cc: Juergen Gross Cc: Shahab Vahedi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index d32d41709513..484650681bee 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -118,7 +118,7 @@ int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); void memblock_free_all(void); -void memblock_free_ptr(void *ptr, size_t size); +void memblock_free(void *ptr, size_t size); void reset_node_managed_pages(pg_data_t *pgdat); void reset_all_zones_managed_pages(void); -- cgit v1.2.3 From b5389086ad7be0453c55e0069a89856d1fbdf605 Mon Sep 17 00:00:00 2001 From: Zhenguo Yao Date: Fri, 5 Nov 2021 13:43:28 -0700 Subject: hugetlbfs: extend the definition of hugepages parameter to support node allocation We can specify the number of hugepages to allocate at boot. But the hugepages is balanced in all nodes at present. In some scenarios, we only need hugepages in one node. For example: DPDK needs hugepages which are in the same node as NIC. If DPDK needs four hugepages of 1G size in node1 and system has 16 numa nodes we must reserve 64 hugepages on the kernel cmdline. But only four hugepages are used. The others should be free after boot. If the system memory is low(for example: 64G), it will be an impossible task. So extend the hugepages parameter to support specifying hugepages on a specific node. For example add following parameter: hugepagesz=1G hugepages=0:1,1:3 It will allocate 1 hugepage in node0 and 3 hugepages in node1. Link: https://lkml.kernel.org/r/20211005054729.86457-1-yaozhenguo1@gmail.com Signed-off-by: Zhenguo Yao Reviewed-by: Mike Kravetz Cc: Zhenguo Yao Cc: Dan Carpenter Cc: Nathan Chancellor Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Jonathan Corbet Cc: Mike Rapoport Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index c0a20781b28e..44c2ab0dfa59 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -615,6 +615,7 @@ struct hstate { unsigned long nr_overcommit_huge_pages; struct list_head hugepage_activelist; struct list_head hugepage_freelists[MAX_NUMNODES]; + unsigned int max_huge_pages_node[MAX_NUMNODES]; unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; @@ -647,8 +648,9 @@ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct page *page); /* arch callback */ -int __init __alloc_bootmem_huge_page(struct hstate *h); -int __init alloc_bootmem_huge_page(struct hstate *h); +int __init __alloc_bootmem_huge_page(struct hstate *h, int nid); +int __init alloc_bootmem_huge_page(struct hstate *h, int nid); +bool __init hugetlb_node_alloc_supported(void); void __init hugetlb_add_hstate(unsigned order); bool __init arch_hugetlb_valid_size(unsigned long size); -- cgit v1.2.3 From 8eb42beac8d369f5443addd469879d152422a28d Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Fri, 5 Nov 2021 13:43:32 -0700 Subject: mm/migrate: de-duplicate migrate_reason strings In order to remove the need to manually keep three different files in synch, provide a common definition of the mapping between enum migrate_reason, and the associated strings for each enum item. 1. Use the tracing system's mapping of enums to strings, by redefining and reusing the MIGRATE_REASON and supporting macros, and using that to populate the string array in mm/debug.c. 2. Move enum migrate_reason to migrate_mode.h. This is not strictly necessary for this patch, but migrate mode and migrate reason go together, so this will slightly clarify things. Link: https://lkml.kernel.org/r/20210922041755.141817-2-jhubbard@nvidia.com Signed-off-by: John Hubbard Reviewed-by: Weizhao Ouyang Cc: "Huang, Ying" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 19 +------------------ include/linux/migrate_mode.h | 13 +++++++++++++ 2 files changed, 14 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index c8077e936691..3d154fe03c96 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -19,24 +19,7 @@ struct migration_target_control; */ #define MIGRATEPAGE_SUCCESS 0 -/* - * Keep sync with: - * - macro MIGRATE_REASON in include/trace/events/migrate.h - * - migrate_reason_names[MR_TYPES] in mm/debug.c - */ -enum migrate_reason { - MR_COMPACTION, - MR_MEMORY_FAILURE, - MR_MEMORY_HOTPLUG, - MR_SYSCALL, /* also applies to cpusets */ - MR_MEMPOLICY_MBIND, - MR_NUMA_MISPLACED, - MR_CONTIG_RANGE, - MR_LONGTERM_PIN, - MR_DEMOTION, - MR_TYPES -}; - +/* Defined in mm/debug.c: */ extern const char *migrate_reason_names[MR_TYPES]; #ifdef CONFIG_MIGRATION diff --git a/include/linux/migrate_mode.h b/include/linux/migrate_mode.h index 883c99249033..f37cc03f9369 100644 --- a/include/linux/migrate_mode.h +++ b/include/linux/migrate_mode.h @@ -19,4 +19,17 @@ enum migrate_mode { MIGRATE_SYNC_NO_COPY, }; +enum migrate_reason { + MR_COMPACTION, + MR_MEMORY_FAILURE, + MR_MEMORY_HOTPLUG, + MR_SYSCALL, /* also applies to cpusets */ + MR_MEMPOLICY_MBIND, + MR_NUMA_MISPLACED, + MR_CONTIG_RANGE, + MR_LONGTERM_PIN, + MR_DEMOTION, + MR_TYPES +}; + #endif /* MIGRATE_MODE_H_INCLUDED */ -- cgit v1.2.3 From 20f9ba4f995247bb79e243741b8fdddbd76dd923 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 5 Nov 2021 13:43:35 -0700 Subject: mm: migrate: make demotion knob depend on migration The memory demotion needs to call migrate_pages() to do the jobs. And it is controlled by a knob, however, the knob doesn't depend on CONFIG_MIGRATION. The knob could be truned on even though MIGRATION is disabled, this will not cause any crash since migrate_pages() would just return -ENOSYS. But it is definitely not optimal to go through demotion path then retry regular swap every time. And it doesn't make too much sense to have the knob visible to the users when !MIGRATION. Move the related code from mempolicy.[h|c] to migrate.[h|c]. Link: https://lkml.kernel.org/r/20211015005559.246709-1-shy828301@gmail.com Signed-off-by: Yang Shi Acked-by: "Huang, Ying" Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 4 ---- include/linux/migrate.h | 4 ++++ 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 097bbbb37493..3c7595e81150 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -183,8 +183,6 @@ extern bool vma_migratable(struct vm_area_struct *vma); extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long); extern void mpol_put_task_policy(struct task_struct *); -extern bool numa_demotion_enabled; - static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return (pol->mode == MPOL_PREFERRED_MANY); @@ -300,8 +298,6 @@ static inline nodemask_t *policy_nodemask_current(gfp_t gfp) return NULL; } -#define numa_demotion_enabled false - static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return false; diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 3d154fe03c96..2d8130e05dc0 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -40,6 +40,8 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); extern int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, int extra_count); + +extern bool numa_demotion_enabled; #else static inline void putback_movable_pages(struct list_head *l) {} @@ -65,6 +67,8 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, { return -ENOSYS; } + +#define numa_demotion_enabled false #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_COMPACTION -- cgit v1.2.3 From 50f9481ed9fb8a2d2a06a155634c7f9eeff9fa61 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:24 -0700 Subject: mm/memory_hotplug: remove CONFIG_MEMORY_HOTPLUG_SPARSE CONFIG_MEMORY_HOTPLUG depends on CONFIG_SPARSEMEM, so there is no need for CONFIG_MEMORY_HOTPLUG_SPARSE anymore; adjust all instances to use CONFIG_MEMORY_HOTPLUG and remove CONFIG_MEMORY_HOTPLUG_SPARSE. Link: https://lkml.kernel.org/r/20210929143600.49379-3-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Shuah Khan [kselftest] Acked-by: Greg Kroah-Hartman Acked-by: Oscar Salvador Cc: Alex Shi Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jason Wang Cc: Jonathan Corbet Cc: Michael Ellerman Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Paul Mackerras Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 24 ++++++++++-------------- include/linux/node.h | 4 ++-- 2 files changed, 12 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 053a530c7bdd..0328ec039c38 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -110,7 +110,7 @@ struct mem_section; #define SLAB_CALLBACK_PRI 1 #define IPC_CALLBACK_PRI 10 -#ifndef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifndef CONFIG_MEMORY_HOTPLUG static inline void memory_dev_init(void) { return; @@ -126,7 +126,14 @@ static inline int memory_notify(unsigned long val, void *v) { return 0; } -#else +static inline int hotplug_memory_notifier(notifier_fn_t fn, int pri) +{ + return 0; +} +/* These aren't inline functions due to a GCC bug. */ +#define register_hotmemory_notifier(nb) ({ (void)(nb); 0; }) +#define unregister_hotmemory_notifier(nb) ({ (void)(nb); }) +#else /* CONFIG_MEMORY_HOTPLUG */ extern int register_memory_notifier(struct notifier_block *nb); extern void unregister_memory_notifier(struct notifier_block *nb); int create_memory_block_devices(unsigned long start, unsigned long size, @@ -148,9 +155,6 @@ struct memory_group *memory_group_find_by_id(int mgid); typedef int (*walk_memory_groups_func_t)(struct memory_group *, void *); int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, struct memory_group *excluded, void *arg); -#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ - -#ifdef CONFIG_MEMORY_HOTPLUG #define hotplug_memory_notifier(fn, pri) ({ \ static __meminitdata struct notifier_block fn##_mem_nb =\ { .notifier_call = fn, .priority = pri };\ @@ -158,15 +162,7 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, }) #define register_hotmemory_notifier(nb) register_memory_notifier(nb) #define unregister_hotmemory_notifier(nb) unregister_memory_notifier(nb) -#else -static inline int hotplug_memory_notifier(notifier_fn_t fn, int pri) -{ - return 0; -} -/* These aren't inline functions due to a GCC bug. */ -#define register_hotmemory_notifier(nb) ({ (void)(nb); 0; }) -#define unregister_hotmemory_notifier(nb) ({ (void)(nb); }) -#endif +#endif /* CONFIG_MEMORY_HOTPLUG */ /* * Kernel text modification mutex, used for code patching. Users of this lock diff --git a/include/linux/node.h b/include/linux/node.h index 8e5a29897936..bb21fd631b16 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -85,7 +85,7 @@ struct node { struct device dev; struct list_head access_list; -#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HUGETLBFS) +#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_HUGETLBFS) struct work_struct node_work; #endif #ifdef CONFIG_HMEM_REPORTING @@ -98,7 +98,7 @@ struct memory_block; extern struct node *node_devices[]; typedef void (*node_registration_func_t)(struct node *); -#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA) +#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_NUMA) void link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn, enum meminit_context context); -- cgit v1.2.3 From 6b740c6c3aa371cd70ac07f8d071f2a8af28c51c Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:31 -0700 Subject: mm/memory_hotplug: remove HIGHMEM leftovers We don't support CONFIG_MEMORY_HOTPLUG on 32 bit and consequently not HIGHMEM. Let's remove any leftover code -- including the unused "status_change_nid_high" field part of the memory notifier. Link: https://lkml.kernel.org/r/20210929143600.49379-5-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Alex Shi Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jason Wang Cc: Jonathan Corbet Cc: Michael Ellerman Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Paul Mackerras Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Shuah Khan Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 0328ec039c38..88eb587b5143 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -96,7 +96,6 @@ struct memory_notify { unsigned long start_pfn; unsigned long nr_pages; int status_change_nid_normal; - int status_change_nid_high; int status_change_nid; }; -- cgit v1.2.3 From 43e3aa2a3247c9ca348884866a9846d788ec5ed6 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:35 -0700 Subject: mm/memory_hotplug: remove stale function declarations These functions no longer exist. Link: https://lkml.kernel.org/r/20210929143600.49379-6-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Alex Shi Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jason Wang Cc: Jonathan Corbet Cc: Michael Ellerman Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Paul Mackerras Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Shuah Khan Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index e5a867c950b2..be48e003a518 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -98,9 +98,6 @@ static inline void zone_seqlock_init(struct zone *zone) { seqlock_init(&zone->span_seqlock); } -extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages); -extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages); -extern int add_one_highpage(struct page *page, int pfn, int bad_ppro); extern void adjust_present_page_count(struct page *page, struct memory_group *group, long nr_pages); -- cgit v1.2.3 From e14b41556d9ec20af60a9f672ac6f64dd450763c Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:46 -0700 Subject: memblock: improve MEMBLOCK_HOTPLUG documentation The description of MEMBLOCK_HOTPLUG is currently short and consequently misleading: we're actually dealing with a memory region that might get hotunplugged later (i.e., the platform+firmware supports it), yet it is indicated in the firmware-provided memory map as system ram that will just get used by the system for any purpose when not taking special care. The firmware marked this memory region as a hot(un)plugged (e.g., hotplugged before reboot), implying that it might get hotunplugged again later. Whether we consider this information depends on the "movable_node" kernel commandline parameter: only with "movable_node" set, we'll try keeping this memory hotunpluggable, for example, by not serving early allocations from this memory region and by letting the buddy manage it using the ZONE_MOVABLE. Let's make this clearer by extending the documentation. Note: kexec *has to* indicate this memory to the second kernel. With "movable_node" set, we don't want to place kexec-images on this memory. Without "movable_node" set, we don't care and can place kexec-images on this memory. In both cases, after successful memory hotunplug, kexec has to be re-armed to update the memory map for the second kernel and to place the kexec-images somewhere else. Link: https://lkml.kernel.org/r/20211004093605.5830-3-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Mike Rapoport Cc: "Aneesh Kumar K . V" Cc: Arnd Bergmann Cc: Christian Borntraeger Cc: Eric Biederman Cc: Geert Uytterhoeven Cc: Heiko Carstens Cc: Huacai Chen Cc: Jianyong Wu Cc: Jiaxun Yang Cc: Michal Hocko Cc: Oscar Salvador Cc: Shahab Vahedi Cc: Thomas Bogendoerfer Cc: Vasily Gorbik Cc: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 484650681bee..1d2b3e902a84 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -28,7 +28,11 @@ extern unsigned long long max_possible_pfn; /** * enum memblock_flags - definition of memory region attributes * @MEMBLOCK_NONE: no special request - * @MEMBLOCK_HOTPLUG: hotpluggable region + * @MEMBLOCK_HOTPLUG: memory region indicated in the firmware-provided memory + * map during early boot as hot(un)pluggable system RAM (e.g., memory range + * that might get hotunplugged later). With "movable_node" set on the kernel + * commandline, try keeping this memory region hotunpluggable. Does not apply + * to memblocks added ("hotplugged") after early boot. * @MEMBLOCK_MIRROR: mirrored region * @MEMBLOCK_NOMAP: don't add to kernel direct mapping and treat as * reserved in the memory map; refer to memblock_mark_nomap() description -- cgit v1.2.3 From 952eea9b01e4bbb7011329f1b7240844e61e5128 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:49 -0700 Subject: memblock: allow to specify flags with memblock_add_node() We want to specify flags when hotplugging memory. Let's prepare to pass flags to memblock_add_node() by adjusting all existing users. Note that when hotplugging memory the system is already up and running and we might have concurrent memblock users: for example, while we're hotplugging memory, kexec_file code might search for suitable memory regions to place kexec images. It's important to add the memory directly to memblock via a single call with the right flags, instead of adding the memory first and apply flags later: otherwise, concurrent memblock users might temporarily stumble over memblocks with wrong flags, which will be important in a follow-up patch that introduces a new flag to properly handle add_memory_driver_managed(). Link: https://lkml.kernel.org/r/20211004093605.5830-4-david@redhat.com Acked-by: Geert Uytterhoeven Acked-by: Heiko Carstens Signed-off-by: David Hildenbrand Acked-by: Shahab Vahedi [arch/arc] Reviewed-by: Mike Rapoport Cc: "Aneesh Kumar K . V" Cc: Arnd Bergmann Cc: Christian Borntraeger Cc: Eric Biederman Cc: Huacai Chen Cc: Jianyong Wu Cc: Jiaxun Yang Cc: Michal Hocko Cc: Oscar Salvador Cc: Thomas Bogendoerfer Cc: Vasily Gorbik Cc: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 3 ++- include/linux/mm.h | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 1d2b3e902a84..8b6560dc7a9e 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -104,7 +104,8 @@ static inline void memblock_discard(void) {} #endif void memblock_allow_resize(void); -int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid); +int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid, + enum memblock_flags flags); int memblock_add(phys_addr_t base, phys_addr_t size); int memblock_remove(phys_addr_t base, phys_addr_t size); int memblock_phys_free(phys_addr_t base, phys_addr_t size); diff --git a/include/linux/mm.h b/include/linux/mm.h index 7e37c726b9db..15058d9cec99 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2425,7 +2425,7 @@ static inline unsigned long get_num_physpages(void) * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn, * max_highmem_pfn}; * for_each_valid_physical_page_range() - * memblock_add_node(base, size, nid) + * memblock_add_node(base, size, nid, MEMBLOCK_NONE) * free_area_init(max_zone_pfns); */ void free_area_init(unsigned long *max_zone_pfn); -- cgit v1.2.3 From f7892d8e288d4b090176f26d9bf7943dbbb639a6 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:53 -0700 Subject: memblock: add MEMBLOCK_DRIVER_MANAGED to mimic IORESOURCE_SYSRAM_DRIVER_MANAGED Let's add a flag that corresponds to IORESOURCE_SYSRAM_DRIVER_MANAGED, indicating that we're dealing with a memory region that is never indicated in the firmware-provided memory map, but always detected and added by a driver. Similar to MEMBLOCK_HOTPLUG, most infrastructure has to treat such memory regions like ordinary MEMBLOCK_NONE memory regions -- for example, when selecting memory regions to add to the vmcore for dumping in the crashkernel via for_each_mem_range(). However, especially kexec_file is not supposed to select such memblocks via for_each_free_mem_range() / for_each_free_mem_range_reverse() to place kexec images, similar to how we handle IORESOURCE_SYSRAM_DRIVER_MANAGED without CONFIG_ARCH_KEEP_MEMBLOCK. We'll make sure that memory hotplug code sets the flag where applicable (IORESOURCE_SYSRAM_DRIVER_MANAGED) next. This prepares architectures that need CONFIG_ARCH_KEEP_MEMBLOCK, such as arm64, for virtio-mem support. Note that kexec *must not* indicate this memory to the second kernel and *must not* place kexec-images on this memory. Let's add a comment to kexec_walk_memblock(), documenting how we handle MEMBLOCK_DRIVER_MANAGED now just like using IORESOURCE_SYSRAM_DRIVER_MANAGED in locate_mem_hole_callback() for kexec_walk_resources(). Also note that MEMBLOCK_HOTPLUG cannot be reused due to different semantics: MEMBLOCK_HOTPLUG: memory is indicated as "System RAM" in the firmware-provided memory map and added to the system early during boot; kexec *has to* indicate this memory to the second kernel and can place kexec-images on this memory. After memory hotunplug, kexec has to be re-armed. We mostly ignore this flag when "movable_node" is not set on the kernel command line, because then we're told to not care about hotunpluggability of such memory regions. MEMBLOCK_DRIVER_MANAGED: memory is not indicated as "System RAM" in the firmware-provided memory map; this memory is always detected and added to the system by a driver; memory might not actually be physically hotunpluggable. kexec *must not* indicate this memory to the second kernel and *must not* place kexec-images on this memory. Link: https://lkml.kernel.org/r/20211004093605.5830-5-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Mike Rapoport Cc: "Aneesh Kumar K . V" Cc: Arnd Bergmann Cc: Christian Borntraeger Cc: Eric Biederman Cc: Geert Uytterhoeven Cc: Heiko Carstens Cc: Huacai Chen Cc: Jianyong Wu Cc: Jiaxun Yang Cc: Michal Hocko Cc: Oscar Salvador Cc: Shahab Vahedi Cc: Thomas Bogendoerfer Cc: Vasily Gorbik Cc: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 8b6560dc7a9e..7df557b16c1e 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -37,12 +37,17 @@ extern unsigned long long max_possible_pfn; * @MEMBLOCK_NOMAP: don't add to kernel direct mapping and treat as * reserved in the memory map; refer to memblock_mark_nomap() description * for further details + * @MEMBLOCK_DRIVER_MANAGED: memory region that is always detected and added + * 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. */ enum memblock_flags { MEMBLOCK_NONE = 0x0, /* No special request */ MEMBLOCK_HOTPLUG = 0x1, /* hotpluggable region */ MEMBLOCK_MIRROR = 0x2, /* mirrored region */ MEMBLOCK_NOMAP = 0x4, /* don't add to kernel direct mapping */ + MEMBLOCK_DRIVER_MANAGED = 0x8, /* always detected via a driver */ }; /** @@ -213,7 +218,8 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, */ #define for_each_mem_range(i, p_start, p_end) \ __for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, \ - MEMBLOCK_HOTPLUG, p_start, p_end, NULL) + MEMBLOCK_HOTPLUG | MEMBLOCK_DRIVER_MANAGED, \ + p_start, p_end, NULL) /** * for_each_mem_range_rev - reverse iterate through memblock areas from @@ -224,7 +230,8 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, */ #define for_each_mem_range_rev(i, p_start, p_end) \ __for_each_mem_range_rev(i, &memblock.memory, NULL, NUMA_NO_NODE, \ - MEMBLOCK_HOTPLUG, p_start, p_end, NULL) + MEMBLOCK_HOTPLUG | MEMBLOCK_DRIVER_MANAGED,\ + p_start, p_end, NULL) /** * for_each_reserved_mem_range - iterate over all reserved memblock areas @@ -254,6 +261,11 @@ static inline bool memblock_is_nomap(struct memblock_region *m) return m->flags & MEMBLOCK_NOMAP; } +static inline bool memblock_is_driver_managed(struct memblock_region *m) +{ + return m->flags & MEMBLOCK_DRIVER_MANAGED; +} + int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn); void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, -- cgit v1.2.3 From d2c20e51e3966bc668ef1ef21fbe90704286c8d0 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Fri, 5 Nov 2021 13:45:06 -0700 Subject: mm/highmem: remove deprecated kmap_atomic kmap_atomic() is being deprecated in favor of kmap_local_page(). Replace the uses of kmap_atomic() within the highmem code. On profiling clear_huge_page() using ftrace an improvement of 62% was observed on the below setup. Setup:- Below data has been collected on Qualcomm's SM7250 SoC THP enabled (kernel v4.19.113) with only CPU-0(Cortex-A55) and CPU-7(Cortex-A76) switched on and set to max frequency, also DDR set to perf governor. FTRACE Data:- Base data:- Number of iterations: 48 Mean of allocation time: 349.5 us std deviation: 74.5 us v4 data:- Number of iterations: 48 Mean of allocation time: 131 us std deviation: 32.7 us The following simple userspace experiment to allocate 100MB(BUF_SZ) of pages and writing to it gave us a good insight, we observed an improvement of 42% in allocation and writing timings. ------------------------------------------------------------- Test code snippet ------------------------------------------------------------- clock_start(); buf = malloc(BUF_SZ); /* Allocate 100 MB of memory */ for(i=0; i < BUF_SZ_PAGES; i++) { *((int *)(buf + (i*PAGE_SIZE))) = 1; } clock_end(); ------------------------------------------------------------- Malloc test timings for 100MB anon allocation:- Base data:- Number of iterations: 100 Mean of allocation time: 31831 us std deviation: 4286 us v4 data:- Number of iterations: 100 Mean of allocation time: 18193 us std deviation: 4915 us [willy@infradead.org: fix zero_user_segments()] Link: https://lkml.kernel.org/r/YYVhHCJcm2DM2G9u@casper.infradead.org Link: https://lkml.kernel.org/r/20210204073255.20769-2-prathu.baronia@oneplus.com Signed-off-by: Ira Weiny Signed-off-by: Prathu Baronia Cc: Thomas Gleixner Cc: Matthew Wilcox Cc: Peter Zijlstra Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index b4c49f9cc379..31ebee36f26c 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -143,9 +143,9 @@ static inline void invalidate_kernel_vmap_range(void *vaddr, int size) #ifndef clear_user_highpage static inline void clear_user_highpage(struct page *page, unsigned long vaddr) { - void *addr = kmap_atomic(page); + void *addr = kmap_local_page(page); clear_user_page(addr, vaddr, page); - kunmap_atomic(addr); + kunmap_local(addr); } #endif @@ -177,9 +177,9 @@ alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma, static inline void clear_highpage(struct page *page) { - void *kaddr = kmap_atomic(page); + void *kaddr = kmap_local_page(page); clear_page(kaddr); - kunmap_atomic(kaddr); + kunmap_local(kaddr); } #ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE @@ -202,7 +202,7 @@ static inline void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2) { - void *kaddr = kmap_atomic(page); + void *kaddr = kmap_local_page(page); unsigned int i; BUG_ON(end1 > page_size(page) || end2 > page_size(page)); @@ -213,7 +213,7 @@ static inline void zero_user_segments(struct page *page, if (end2 > start2) memset(kaddr + start2, 0, end2 - start2); - kunmap_atomic(kaddr); + kunmap_local(kaddr); for (i = 0; i < compound_nr(page); i++) flush_dcache_page(page + i); } @@ -238,11 +238,11 @@ static inline void copy_user_highpage(struct page *to, struct page *from, { char *vfrom, *vto; - vfrom = kmap_atomic(from); - vto = kmap_atomic(to); + vfrom = kmap_local_page(from); + vto = kmap_local_page(to); copy_user_page(vto, vfrom, vaddr, to); - kunmap_atomic(vto); - kunmap_atomic(vfrom); + kunmap_local(vto); + kunmap_local(vfrom); } #endif @@ -253,11 +253,11 @@ static inline void copy_highpage(struct page *to, struct page *from) { char *vfrom, *vto; - vfrom = kmap_atomic(from); - vto = kmap_atomic(to); + vfrom = kmap_local_page(from); + vto = kmap_local_page(to); copy_page(vto, vfrom); - kunmap_atomic(vto); - kunmap_atomic(vfrom); + kunmap_local(vto); + kunmap_local(vfrom); } #endif -- cgit v1.2.3 From 53944f171a89dff4e2a3d76f42e6eedb551bb861 Mon Sep 17 00:00:00 2001 From: Stephen Kitt Date: Fri, 5 Nov 2021 13:45:18 -0700 Subject: mm: remove HARDENED_USERCOPY_FALLBACK This has served its purpose and is no longer used. All usercopy violations appear to have been handled by now, any remaining instances (or new bugs) will cause copies to be rejected. This isn't a direct revert of commit 2d891fbc3bb6 ("usercopy: Allow strict enforcement of whitelists"); since usercopy_fallback is effectively 0, the fallback handling is removed too. This also removes the usercopy_fallback module parameter on slab_common. Link: https://github.com/KSPP/linux/issues/153 Link: https://lkml.kernel.org/r/20210921061149.1091163-1-steve@sk2.org Signed-off-by: Stephen Kitt Suggested-by: Kees Cook Acked-by: Kees Cook Reviewed-by: Joel Stanley [defconfig change] Acked-by: David Rientjes Cc: Christoph Lameter Cc: Pekka Enberg Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: James Morris Cc: "Serge E . Hallyn" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 837cb16232ef..181045148b06 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -142,8 +142,6 @@ struct mem_cgroup; void __init kmem_cache_init(void); bool slab_is_available(void); -extern bool usercopy_fallback; - struct kmem_cache *kmem_cache_create(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, void (*ctor)(void *)); -- cgit v1.2.3 From a1554c002699cbc9ced2e9f44f9c1357181bead3 Mon Sep 17 00:00:00 2001 From: Mianhan Liu Date: Fri, 5 Nov 2021 13:45:21 -0700 Subject: include/linux/mm.h: move nr_free_buffer_pages from swap.h to mm.h nr_free_buffer_pages could be exposed through mm.h instead of swap.h. The advantage of this change is that it can reduce the obsolete includes. For example, net/ipv4/tcp.c wouldn't need swap.h any more since it has already included mm.h. Similarly, after checking all the other files, it comes that tcp.c, udp.c meter.c ,... follow the same rule, so these files can have swap.h removed too. Moreover, after preprocessing all the files that use nr_free_buffer_pages, it turns out that those files have already included mm.h.Thus, we can move nr_free_buffer_pages from swap.h to mm.h safely. This change will not affect the compilation of other files. Link: https://lkml.kernel.org/r/20210912133640.1624-1-liumh1@shanghaitech.edu.cn Signed-off-by: Mianhan Liu Cc: Jakub Kicinski CC: Ulf Hansson Cc: "David S . Miller" Cc: Simon Horman Cc: Pravin B Shelar Cc: Vlad Yasevich Cc: Marcelo Ricardo Leitner Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ include/linux/swap.h | 1 - 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 15058d9cec99..b1720aa63727 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -875,6 +875,8 @@ void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); void copy_huge_page(struct page *dst, struct page *src); +unsigned long nr_free_buffer_pages(void); + /* * Compound pages have a destructor function. Provide a * prototype for that function and accessor functions. diff --git a/include/linux/swap.h b/include/linux/swap.h index ba52f3a3478e..53f759a59996 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -335,7 +335,6 @@ void workingset_update_node(struct xa_node *node); /* linux/mm/page_alloc.c */ extern unsigned long totalreserve_pages; -extern unsigned long nr_free_buffer_pages(void); /* Definition of global_zone_page_state not available yet */ #define nr_free_pages() global_zone_page_state(NR_FREE_PAGES) -- cgit v1.2.3 From f39f21b3ddc7fc0f87eb6dc75ddc81b5bbfb7672 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:45:25 -0700 Subject: stacktrace: move filter_irq_stacks() to kernel/stacktrace.c filter_irq_stacks() has little to do with the stackdepot implementation, except that it is usually used by users (such as KASAN) of stackdepot to reduce the stack trace. However, filter_irq_stacks() itself is not useful without a stack trace as obtained by stack_trace_save() and friends. Therefore, move filter_irq_stacks() to kernel/stacktrace.c, so that new users of filter_irq_stacks() do not have to start depending on STACKDEPOT only for filter_irq_stacks(). Link: https://lkml.kernel.org/r/20210923104803.2620285-1-elver@google.com Signed-off-by: Marco Elver Acked-by: Dmitry Vyukov Cc: Alexander Potapenko Cc: Jann Horn Cc: Aleksandr Nogikh Cc: Taras Madan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stackdepot.h | 2 -- include/linux/stacktrace.h | 1 + 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index b2f7e7c6ba54..d29860966bc9 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -25,8 +25,6 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned long **entries); -unsigned int filter_irq_stacks(unsigned long *entries, unsigned int nr_entries); - #ifdef CONFIG_STACKDEPOT int stack_depot_init(void); #else diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index 9edecb494e9e..bef158815e83 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -21,6 +21,7 @@ unsigned int stack_trace_save_tsk(struct task_struct *task, unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store, unsigned int size, unsigned int skipnr); unsigned int stack_trace_save_user(unsigned long *store, unsigned int size); +unsigned int filter_irq_stacks(unsigned long *entries, unsigned int nr_entries); /* Internal interfaces. Do not use in generic code */ #ifdef CONFIG_ARCH_STACKWALK -- cgit v1.2.3 From 07e8481d3c38f461d7b79c1d5c9afe013b162b0c Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:45:46 -0700 Subject: kfence: always use static branches to guard kfence_alloc() Regardless of KFENCE mode (CONFIG_KFENCE_STATIC_KEYS: either using static keys to gate allocations, or using a simple dynamic branch), always use a static branch to avoid the dynamic branch in kfence_alloc() if KFENCE was disabled at boot. For CONFIG_KFENCE_STATIC_KEYS=n, this now avoids the dynamic branch if KFENCE was disabled at boot. To simplify, also unifies the location where kfence_allocation_gate is read-checked to just be inline in kfence_alloc(). Link: https://lkml.kernel.org/r/20211019102524.2807208-1-elver@google.com Signed-off-by: Marco Elver Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Jann Horn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfence.h | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kfence.h b/include/linux/kfence.h index 3fe6dd8a18c1..4b5e3679a72c 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -14,6 +14,9 @@ #ifdef CONFIG_KFENCE +#include +#include + /* * We allocate an even number of pages, as it simplifies calculations to map * address to metadata indices; effectively, the very first page serves as an @@ -22,13 +25,8 @@ #define KFENCE_POOL_SIZE ((CONFIG_KFENCE_NUM_OBJECTS + 1) * 2 * PAGE_SIZE) extern char *__kfence_pool; -#ifdef CONFIG_KFENCE_STATIC_KEYS -#include DECLARE_STATIC_KEY_FALSE(kfence_allocation_key); -#else -#include extern atomic_t kfence_allocation_gate; -#endif /** * is_kfence_address() - check if an address belongs to KFENCE pool @@ -116,13 +114,16 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags); */ static __always_inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) { -#ifdef CONFIG_KFENCE_STATIC_KEYS - if (static_branch_unlikely(&kfence_allocation_key)) +#if defined(CONFIG_KFENCE_STATIC_KEYS) || CONFIG_KFENCE_SAMPLE_INTERVAL == 0 + if (!static_branch_unlikely(&kfence_allocation_key)) + return NULL; #else - if (unlikely(!atomic_read(&kfence_allocation_gate))) + if (!static_branch_likely(&kfence_allocation_key)) + return NULL; #endif - return __kfence_alloc(s, size, flags); - return NULL; + if (likely(atomic_read(&kfence_allocation_gate))) + return NULL; + return __kfence_alloc(s, size, flags); } /** -- cgit v1.2.3 From d2f272b35a84ace2ef04334a9822fd726a7f061b Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:04 -0700 Subject: include/linux/damon.h: fix kernel-doc comments for 'damon_callback' A few Kernel-doc comments in 'damon.h' are broken. This fixes them. Link: https://lkml.kernel.org/r/20210917123958.3819-5-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index d68b67b8d458..755d70804705 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -62,7 +62,7 @@ struct damon_target { struct damon_ctx; /** - * struct damon_primitive Monitoring primitives for given use cases. + * struct damon_primitive - Monitoring primitives for given use cases. * * @init: Initialize primitive-internal data structures. * @update: Update primitive-internal data structures. @@ -108,8 +108,8 @@ struct damon_primitive { void (*cleanup)(struct damon_ctx *context); }; -/* - * struct damon_callback Monitoring events notification callbacks. +/** + * struct damon_callback - Monitoring events notification callbacks. * * @before_start: Called before starting the monitoring. * @after_sampling: Called after each sampling. -- cgit v1.2.3 From fda504fade7f124858d7022341dc46ff35b45274 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:18 -0700 Subject: mm/damon/core: account age of target regions Patch series "Implement Data Access Monitoring-based Memory Operation Schemes". Introduction ============ DAMON[1] can be used as a primitive for data access aware memory management optimizations. For that, users who want such optimizations should run DAMON, read the monitoring results, analyze it, plan a new memory management scheme, and apply the new scheme by themselves. Such efforts will be inevitable for some complicated optimizations. However, in many other cases, the users would simply want the system to apply a memory management action to a memory region of a specific size having a specific access frequency for a specific time. For example, "page out a memory region larger than 100 MiB keeping only rare accesses more than 2 minutes", or "Do not use THP for a memory region larger than 2 MiB rarely accessed for more than 1 seconds". To make the works easier and non-redundant, this patchset implements a new feature of DAMON, which is called Data Access Monitoring-based Operation Schemes (DAMOS). Using the feature, users can describe the normal schemes in a simple way and ask DAMON to execute those on its own. [1] https://damonitor.github.io Evaluations =========== DAMOS is accurate and useful for memory management optimizations. An experimental DAMON-based operation scheme for THP, 'ethp', removes 76.15% of THP memory overheads while preserving 51.25% of THP speedup. Another experimental DAMON-based 'proactive reclamation' implementation, 'prcl', reduces 93.38% of residential sets and 23.63% of system memory footprint while incurring only 1.22% runtime overhead in the best case (parsec3/freqmine). NOTE that the experimental THP optimization and proactive reclamation are not for production but only for proof of concepts. Please refer to the showcase web site's evaluation document[1] for detailed evaluation setup and results. [1] https://damonitor.github.io/doc/html/v34/vm/damon/eval.html Long-term Support Trees ----------------------- For people who want to test DAMON but using LTS kernels, there are another couple of trees based on two latest LTS kernels respectively and containing the 'damon/master' backports. - For v5.4.y: https://git.kernel.org/sj/h/damon/for-v5.4.y - For v5.10.y: https://git.kernel.org/sj/h/damon/for-v5.10.y Sequence Of Patches =================== The 1st patch accounts age of each region. The 2nd patch implements the core of the DAMON-based operation schemes feature. The 3rd patch makes the default monitoring primitives for virtual address spaces to support the schemes. From this point, the kernel space users can use DAMOS. The 4th patch exports the feature to the user space via the debugfs interface. The 5th patch implements schemes statistics feature for easier tuning of the schemes and runtime access pattern analysis, and the 6th patch adds selftests for these changes. Finally, the 7th patch documents this new feature. This patch (of 7): DAMON can be used for data access pattern aware memory management optimizations. For that, users should run DAMON, read the monitoring results, analyze it, plan a new memory management scheme, and apply the new scheme by themselves. It would not be too hard, but still require some level of effort. For complicated cases, this effort is inevitable. That said, in many cases, users would simply want to apply an actions to a memory region of a specific size having a specific access frequency for a specific time. For example, "page out a memory region larger than 100 MiB but having a low access frequency more than 10 minutes", or "Use THP for a memory region larger than 2 MiB having a high access frequency for more than 2 seconds". For such optimizations, users will need to first account the age of each region themselves. To reduce such efforts, this implements a simple age account of each region in DAMON. For each aggregation step, DAMON compares the access frequency with that from last aggregation and reset the age of the region if the change is significant. Else, the age is incremented. Also, in case of the merge of regions, the region size-weighted average of the ages is set as the age of merged new region. Link: https://lkml.kernel.org/r/20211001125604.29660-1-sj@kernel.org Link: https://lkml.kernel.org/r/20211001125604.29660-2-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Cameron Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Jonathan Corbet Cc: David Hildenbrand Cc: David Woodhouse Cc: Marco Elver Cc: Leonard Foerster Cc: Greg Thelen Cc: Markus Boehme Cc: David Rienjes Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 755d70804705..3e8215debbd4 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -31,12 +31,22 @@ struct damon_addr_range { * @sampling_addr: Address of the sample for the next access check. * @nr_accesses: Access frequency of this region. * @list: List head for siblings. + * @age: Age of this region. + * + * @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 + * region are set as region size-weighted average of those of the two regions. */ struct damon_region { struct damon_addr_range ar; unsigned long sampling_addr; unsigned int nr_accesses; struct list_head list; + + unsigned int age; +/* private: Internal value for age calculation. */ + unsigned int last_nr_accesses; }; /** -- cgit v1.2.3 From 1f366e421c8f69583ed37b56d86e3747331869c3 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:22 -0700 Subject: mm/damon/core: implement DAMON-based Operation Schemes (DAMOS) In many cases, users might use DAMON for simple data access aware memory management optimizations such as applying an operation scheme to a memory region of a specific size having a specific access frequency for a specific time. For example, "page out a memory region larger than 100 MiB but having a low access frequency more than 10 minutes", or "Use THP for a memory region larger than 2 MiB having a high access frequency for more than 2 seconds". Most simple form of the solution would be doing offline data access pattern profiling using DAMON and modifying the application source code or system configuration based on the profiling results. Or, developing a daemon constructed with two modules (one for access monitoring and the other for applying memory management actions via mlock(), madvise(), sysctl, etc) is imaginable. To avoid users spending their time for implementation of such simple data access monitoring-based operation schemes, this makes DAMON to handle such schemes directly. With this change, users can simply specify their desired schemes to DAMON. Then, DAMON will automatically apply the schemes to the user-specified target processes. Each of the schemes is composed with conditions for filtering of the target memory regions and desired memory management action for the target. Specifically, the format is:: The filtering conditions are size of memory region, number of accesses to the region monitored by DAMON, and the age of the region. The age of region is incremented periodically but reset when its addresses or access frequency has significantly changed or the action of a scheme was applied. For the action, current implementation supports a few of madvise()-like hints, ``WILLNEED``, ``COLD``, ``PAGEOUT``, ``HUGEPAGE``, and ``NOHUGEPAGE``. Because DAMON supports various address spaces and application of the actions to a monitoring target region is dependent to the type of the target address space, the application code should be implemented by each primitives and registered to the framework. Note that this only implements the framework part. Following commit will implement the action applications for virtual address spaces primitives. Link: https://lkml.kernel.org/r/20211001125604.29660-3-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 66 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 66 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 3e8215debbd4..dbe18b0fb795 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -69,6 +69,48 @@ struct damon_target { struct list_head list; }; +/** + * enum damos_action - Represents an action of a Data Access Monitoring-based + * Operation Scheme. + * + * @DAMOS_WILLNEED: Call ``madvise()`` for the region with MADV_WILLNEED. + * @DAMOS_COLD: Call ``madvise()`` for the region with MADV_COLD. + * @DAMOS_PAGEOUT: Call ``madvise()`` for the region with MADV_PAGEOUT. + * @DAMOS_HUGEPAGE: Call ``madvise()`` for the region with MADV_HUGEPAGE. + * @DAMOS_NOHUGEPAGE: Call ``madvise()`` for the region with MADV_NOHUGEPAGE. + */ +enum damos_action { + DAMOS_WILLNEED, + DAMOS_COLD, + DAMOS_PAGEOUT, + DAMOS_HUGEPAGE, + DAMOS_NOHUGEPAGE, +}; + +/** + * struct damos - Represents a Data Access Monitoring-based Operation Scheme. + * @min_sz_region: Minimum size of target regions. + * @max_sz_region: Maximum size of target regions. + * @min_nr_accesses: Minimum ``->nr_accesses`` of target regions. + * @max_nr_accesses: Maximum ``->nr_accesses`` of target regions. + * @min_age_region: Minimum age of target regions. + * @max_age_region: Maximum age of target regions. + * @action: &damo_action to be applied to the target regions. + * @list: List head for siblings. + * + * Note that both the minimums and the maximums are inclusive. + */ +struct damos { + unsigned long min_sz_region; + unsigned long max_sz_region; + unsigned int min_nr_accesses; + unsigned int max_nr_accesses; + unsigned int min_age_region; + unsigned int max_age_region; + enum damos_action action; + struct list_head list; +}; + struct damon_ctx; /** @@ -79,6 +121,7 @@ struct damon_ctx; * @prepare_access_checks: Prepare next access check of target regions. * @check_accesses: Check the accesses to target regions. * @reset_aggregated: Reset aggregated accesses monitoring results. + * @apply_scheme: Apply a DAMON-based operation scheme. * @target_valid: Determine if the target is valid. * @cleanup: Clean up the context. * @@ -104,6 +147,9 @@ struct damon_ctx; * of its update. The value will be used for regions adjustment threshold. * @reset_aggregated should reset the access monitoring results that aggregated * by @check_accesses. + * @apply_scheme is called from @kdamond when a region for user provided + * DAMON-based operation scheme is found. It should apply the scheme's action + * to the region. This is not used for &DAMON_ARBITRARY_TARGET case. * @target_valid should check whether the target is still valid for the * monitoring. * @cleanup is called from @kdamond just before its termination. @@ -114,6 +160,8 @@ struct damon_primitive { void (*prepare_access_checks)(struct damon_ctx *context); unsigned int (*check_accesses)(struct damon_ctx *context); void (*reset_aggregated)(struct damon_ctx *context); + int (*apply_scheme)(struct damon_ctx *context, struct damon_target *t, + struct damon_region *r, struct damos *scheme); bool (*target_valid)(void *target); void (*cleanup)(struct damon_ctx *context); }; @@ -192,6 +240,7 @@ struct damon_callback { * @min_nr_regions: The minimum number of adaptive monitoring regions. * @max_nr_regions: The maximum number of adaptive monitoring regions. * @adaptive_targets: Head of monitoring targets (&damon_target) list. + * @schemes: Head of schemes (&damos) list. */ struct damon_ctx { unsigned long sample_interval; @@ -213,6 +262,7 @@ struct damon_ctx { unsigned long min_nr_regions; unsigned long max_nr_regions; struct list_head adaptive_targets; + struct list_head schemes; }; #define damon_next_region(r) \ @@ -233,6 +283,12 @@ struct damon_ctx { #define damon_for_each_target_safe(t, next, ctx) \ list_for_each_entry_safe(t, next, &(ctx)->adaptive_targets, list) +#define damon_for_each_scheme(s, ctx) \ + list_for_each_entry(s, &(ctx)->schemes, list) + +#define damon_for_each_scheme_safe(s, next, ctx) \ + list_for_each_entry_safe(s, next, &(ctx)->schemes, list) + #ifdef CONFIG_DAMON struct damon_region *damon_new_region(unsigned long start, unsigned long end); @@ -242,6 +298,14 @@ inline void damon_insert_region(struct damon_region *r, void damon_add_region(struct damon_region *r, struct damon_target *t); void damon_destroy_region(struct damon_region *r, struct damon_target *t); +struct damos *damon_new_scheme( + unsigned long min_sz_region, unsigned long max_sz_region, + unsigned int min_nr_accesses, unsigned int max_nr_accesses, + unsigned int min_age_region, unsigned int max_age_region, + enum damos_action action); +void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); +void damon_destroy_scheme(struct damos *s); + struct damon_target *damon_new_target(unsigned long id); void damon_add_target(struct damon_ctx *ctx, struct damon_target *t); void damon_free_target(struct damon_target *t); @@ -255,6 +319,8 @@ int damon_set_targets(struct damon_ctx *ctx, int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, unsigned long aggr_int, unsigned long primitive_upd_int, unsigned long min_nr_reg, unsigned long max_nr_reg); +int damon_set_schemes(struct damon_ctx *ctx, + struct damos **schemes, ssize_t nr_schemes); int damon_nr_running_ctxs(void); int damon_start(struct damon_ctx **ctxs, int nr_ctxs); -- cgit v1.2.3 From 6dea8add4d2875b80843e4a4c8acd334a4db8c8f Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:25 -0700 Subject: mm/damon/vaddr: support DAMON-based Operation Schemes This makes DAMON's default primitives for virtual address spaces to support DAMON-based Operation Schemes (DAMOS) by implementing actions application functions and registering it to the monitoring context. The implementation simply links 'madvise()' for related DAMOS actions. That is, 'madvise(MADV_WILLNEED)' is called for 'WILLNEED' DAMOS action and similar for other actions ('COLD', 'PAGEOUT', 'HUGEPAGE', 'NOHUGEPAGE'). So, the kernel space DAMON users can now use the DAMON-based optimizations with only small amount of code. Link: https://lkml.kernel.org/r/20211001125604.29660-4-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index dbe18b0fb795..be6b6e81e8ee 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -337,6 +337,8 @@ void damon_va_prepare_access_checks(struct damon_ctx *ctx); unsigned int damon_va_check_accesses(struct damon_ctx *ctx); bool damon_va_target_valid(void *t); void damon_va_cleanup(struct damon_ctx *ctx); +int damon_va_apply_scheme(struct damon_ctx *context, struct damon_target *t, + struct damon_region *r, struct damos *scheme); void damon_va_set_primitives(struct damon_ctx *ctx); #endif /* CONFIG_DAMON_VADDR */ -- cgit v1.2.3 From 2f0b548c9f03a78f4ce6ab48986e3108028936a6 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:32 -0700 Subject: mm/damon/schemes: implement statistics feature To tune the DAMON-based operation schemes, knowing how many and how large regions are affected by each of the schemes will be helful. Those stats could be used for not only the tuning, but also monitoring of the working set size and the number of regions, if the scheme does not change the program behavior too much. For the reason, this implements the statistics for the schemes. The total number and size of the regions that each scheme is applied are exported to users via '->stat_count' and '->stat_sz' of 'struct damos'. Admins can also check the number by reading 'schemes' debugfs file. The last two integers now represents the stats. To allow collecting the stats without changing the program behavior, this also adds new scheme action, 'DAMOS_STAT'. Note that 'DAMOS_STAT' is not only making no memory operation actions, but also does not reset the age of regions. Link: https://lkml.kernel.org/r/20211001125604.29660-6-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index be6b6e81e8ee..f301bb53381c 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -78,6 +78,7 @@ struct damon_target { * @DAMOS_PAGEOUT: Call ``madvise()`` for the region with MADV_PAGEOUT. * @DAMOS_HUGEPAGE: Call ``madvise()`` for the region with MADV_HUGEPAGE. * @DAMOS_NOHUGEPAGE: Call ``madvise()`` for the region with MADV_NOHUGEPAGE. + * @DAMOS_STAT: Do nothing but count the stat. */ enum damos_action { DAMOS_WILLNEED, @@ -85,6 +86,7 @@ enum damos_action { DAMOS_PAGEOUT, DAMOS_HUGEPAGE, DAMOS_NOHUGEPAGE, + DAMOS_STAT, /* Do nothing but only record the stat */ }; /** @@ -96,9 +98,13 @@ enum damos_action { * @min_age_region: Minimum age of target regions. * @max_age_region: Maximum age of target regions. * @action: &damo_action to be applied to the target regions. + * @stat_count: Total number of regions that this scheme is applied. + * @stat_sz: Total size of regions that this scheme is applied. * @list: List head for siblings. * - * Note that both the minimums and the maximums are inclusive. + * For each aggregation interval, DAMON applies @action to monitoring target + * regions fit in the condition and updates the statistics. Note that both + * the minimums and the maximums are inclusive. */ struct damos { unsigned long min_sz_region; @@ -108,6 +114,8 @@ struct damos { unsigned int min_age_region; unsigned int max_age_region; enum damos_action action; + unsigned long stat_count; + unsigned long stat_sz; struct list_head list; }; -- cgit v1.2.3 From a28397beb55b68bd0f15c6778540e8ae1bc26d21 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:56 -0700 Subject: mm/damon: implement primitives for physical address space monitoring This implements the monitoring primitives for the physical memory address space. Internally, it uses the PTE Accessed bit, similar to that of the virtual address spaces monitoring primitives. It supports only user memory pages, as idle pages tracking does. If the monitoring target physical memory address range contains non-user memory pages, access check of the pages will do nothing but simply treat the pages as not accessed. Link: https://lkml.kernel.org/r/20211012205711.29216-6-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Brendan Higgins Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index f301bb53381c..715dadd21f7c 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -351,4 +351,14 @@ void damon_va_set_primitives(struct damon_ctx *ctx); #endif /* CONFIG_DAMON_VADDR */ +#ifdef CONFIG_DAMON_PADDR + +/* Monitoring primitives for the physical memory address space */ +void damon_pa_prepare_access_checks(struct damon_ctx *ctx); +unsigned int damon_pa_check_accesses(struct damon_ctx *ctx); +bool damon_pa_target_valid(void *t); +void damon_pa_set_primitives(struct damon_ctx *ctx); + +#endif /* CONFIG_DAMON_PADDR */ + #endif /* _DAMON_H */ -- cgit v1.2.3 From 57223ac295845b1d72ec1bd02b5fab992b77a021 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:13 -0700 Subject: mm/damon/paddr: support the pageout scheme Introduction ============ This patchset 1) makes the engine for general data access pattern-oriented memory management (DAMOS) be more useful for production environments, and 2) implements a static kernel module for lightweight proactive reclamation using the engine. Proactive Reclamation --------------------- On general memory over-committed systems, proactively reclaiming cold pages helps saving memory and reducing latency spikes that incurred by the direct reclaim or the CPU consumption of kswapd, while incurring only minimal performance degradation[2]. A Free Pages Reporting[8] based memory over-commit virtualization system would be one more specific use case. In the system, the guest VMs reports their free memory to host, and the host reallocates the reported memory to other guests. As a result, the system's memory utilization can be maximized. However, the guests could be not so memory-frugal, because some kernel subsystems and user-space applications are designed to use as much memory as available. Then, guests would report only small amount of free memory to host, results in poor memory utilization. Running the proactive reclamation in such guests could help mitigating this problem. Google has also implemented this idea and using it in their data center. They further proposed upstreaming it in LSFMM'19, and "the general consensus was that, while this sort of proactive reclaim would be useful for a number of users, the cost of this particular solution was too high to consider merging it upstream"[3]. The cost mainly comes from the coldness tracking. Roughly speaking, the implementation periodically scans the 'Accessed' bit of each page. For the reason, the overhead linearly increases as the size of the memory and the scanning frequency grows. As a result, Google is known to dedicating one CPU for the work. That's a reasonable option to someone like Google, but it wouldn't be so to some others. DAMON and DAMOS: An engine for data access pattern-oriented memory management ----------------------------------------------------------------------------- DAMON[4] is a framework for general data access monitoring. Its adaptive monitoring overhead control feature minimizes its monitoring overhead. It also let the upper-bound of the overhead be configurable by clients, regardless of the size of the monitoring target memory. While monitoring 70 GiB memory of a production system every 5 milliseconds, it consumes less than 1% single CPU time. For this, it could sacrify some of the quality of the monitoring results. Nevertheless, the lower-bound of the quality is configurable, and it uses a best-effort algorithm for better quality. Our test results[5] show the quality is practical enough. From the production system monitoring, we were able to find a 4 KiB region in the 70 GiB memory that shows highest access frequency. We normally don't monitor the data access pattern just for fun but to improve something like memory management. Proactive reclamation is one such usage. For such general cases, DAMON provides a feature called DAMon-based Operation Schemes (DAMOS)[6]. It makes DAMON an engine for general data access pattern oriented memory management. Using this, clients can ask DAMON to find memory regions of specific data access pattern and apply some memory management action (e.g., page out, move to head of the LRU list, use huge page, ...). We call the request 'scheme'. Proactive Reclamation on top of DAMON/DAMOS ------------------------------------------- Therefore, by using DAMON for the cold pages detection, the proactive reclamation's monitoring overhead issue can be solved. Actually, we previously implemented a version of proactive reclamation using DAMOS and achieved noticeable improvements with our evaluation setup[5]. Nevertheless, it more for a proof-of-concept, rather than production uses. It supports only virtual address spaces of processes, and require additional tuning efforts for given workloads and the hardware. For the tuning, we introduced a simple auto-tuning user space tool[8]. Google is also known to using a ML-based similar approach for their fleets[2]. But, making it just works with intuitive knobs in the kernel would be helpful for general users. To this end, this patchset improves DAMOS to be ready for such production usages, and implements another version of the proactive reclamation, namely DAMON_RECLAIM, on top of it. DAMOS Improvements: Aggressiveness Control, Prioritization, and Watermarks -------------------------------------------------------------------------- First of all, the current version of DAMOS supports only virtual address spaces. This patchset makes it supports the physical address space for the page out action. Next major problem of the current version of DAMOS is the lack of the aggressiveness control, which can results in arbitrary overhead. For example, if huge memory regions having the data access pattern of interest are found, applying the requested action to all of the regions could incur significant overhead. It can be controlled by tuning the target data access pattern with manual or automated approaches[2,7]. But, some people would prefer the kernel to just work with only intuitive tuning or default values. For such cases, this patchset implements a safeguard, namely time/size quota. Using this, the clients can specify up to how much time can be used for applying the action, and/or up to how much memory regions the action can be applied within a user-specified time duration. A followup question is, to which memory regions should the action applied within the limits? We implement a simple regions prioritization mechanism for each action and make DAMOS to apply the action to high priority regions first. It also allows clients tune the prioritization mechanism to use different weights for size, access frequency, and age of memory regions. This means we could use not only LRU but also LFU or some fancy algorithms like CAR[9] with lightweight overhead. Though DAMON is lightweight, someone would want to remove even the cold pages monitoring overhead when it is unnecessary. Currently, it should manually turned on and off by clients, but some clients would simply want to turn it on and off based on some metrics like free memory ratio or memory fragmentation. For such cases, this patchset implements a watermarks-based automatic activation feature. It allows the clients configure the metric of their interest, and three watermarks of the metric. If the metric is higher than the high watermark or lower than the low watermark, the scheme is deactivated. If the metric is lower than the mid watermark but higher than the low watermark, the scheme is activated. DAMON-based Reclaim ------------------- Using the improved version of DAMOS, this patchset implements a static kernel module called 'damon_reclaim'. It finds memory regions that didn't accessed for specific time duration and page out. Consuming too much CPU for the paging out operations, or doing pageout too frequently can be critical for systems configuring their swap devices with software-defined in-memory block devices like zram/zswap or total number of writes limited devices like SSDs, respectively. To avoid the problems, the time/size quotas can be configured. Under the quotas, it pages out memory regions that didn't accessed longer first. Also, to remove the monitoring overhead under peaceful situation, and to fall back to the LRU-list based page granularity reclamation when it doesn't make progress, the three watermarks based activation mechanism is used, with the free memory ratio as the watermark metric. For convenient configurations, it provides several module parameters. Using these, sysadmins can enable/disable it, and tune its parameters including the coldness identification time threshold, the time/size quotas and the three watermarks. Evaluation ========== In short, DAMON_RECLAIM with 50ms/s time quota and regions prioritization on v5.15-rc5 Linux kernel with ZRAM swap device achieves 38.58% memory saving with only 1.94% runtime overhead. For this, DAMON_RECLAIM consumes only 4.97% of single CPU time. Setup ----- We evaluate DAMON_RECLAIM to show how each of the DAMOS improvements make effect. For this, we measure DAMON_RECLAIM's CPU consumption, entire system memory footprint, total number of major page faults, and runtime of 24 realistic workloads in PARSEC3 and SPLASH-2X benchmark suites on my QEMU/KVM based virtual machine. The virtual machine runs on an i3.metal AWS instance, has 130GiB memory, and runs a linux kernel built on latest -mm tree[1] plus this patchset. It also utilizes a 4 GiB ZRAM swap device. We repeats the measurement 5 times and use averages. [1] https://github.com/hnaz/linux-mm/tree/v5.15-rc5-mmots-2021-10-13-19-55 Detailed Results ---------------- The results are summarized in the below table. With coldness identification threshold of 5 seconds, DAMON_RECLAIM without the time quota-based speed limit achieves 47.21% memory saving, but incur 4.59% runtime slowdown to the workloads on average. For this, DAMON_RECLAIM consumes about 11.28% single CPU time. Applying time quotas of 200ms/s, 50ms/s, and 10ms/s without the regions prioritization reduces the slowdown to 4.89%, 2.65%, and 1.5%, respectively. Time quota of 200ms/s (20%) makes no real change compared to the quota unapplied version, because the quota unapplied version consumes only 11.28% CPU time. DAMON_RECLAIM's CPU utilization also similarly reduced: 11.24%, 5.51%, and 2.01% of single CPU time. That is, the overhead is proportional to the speed limit. Nevertheless, it also reduces the memory saving because it becomes less aggressive. In detail, the three variants show 48.76%, 37.83%, and 7.85% memory saving, respectively. Applying the regions prioritization (page out regions that not accessed longer first within the time quota) further reduces the performance degradation. Runtime slowdowns and total number of major page faults increase has been 4.89%/218,690% -> 4.39%/166,136% (200ms/s), 2.65%/111,886% -> 1.94%/59,053% (50ms/s), and 1.5%/34,973.40% -> 2.08%/8,781.75% (10ms/s). The runtime under 10ms/s time quota has increased with prioritization, but apparently that's under the margin of error. time quota prioritization memory_saving cpu_util slowdown pgmajfaults overhead N N 47.21% 11.28% 4.59% 194,802% 200ms/s N 48.76% 11.24% 4.89% 218,690% 50ms/s N 37.83% 5.51% 2.65% 111,886% 10ms/s N 7.85% 2.01% 1.5% 34,793.40% 200ms/s Y 50.08% 10.38% 4.39% 166,136% 50ms/s Y 38.58% 4.97% 1.94% 59,053% 10ms/s Y 3.63% 1.73% 2.08% 8,781.75% Baseline and Complete Git Trees =============================== The patches are based on the latest -mm tree (v5.15-rc5-mmots-2021-10-13-19-55). You can also clone the complete git tree from: $ git clone git://github.com/sjp38/linux -b damon_reclaim/patches/v1 The web is also available: https://git.kernel.org/pub/scm/linux/kernel/git/sj/linux.git/tag/?h=damon_reclaim/patches/v1 Sequence Of Patches =================== The first patch makes DAMOS support the physical address space for the page out action. Following five patches (patches 2-6) implement the time/size quotas. Next four patches (patches 7-10) implement the memory regions prioritization within the limit. Then, three following patches (patches 11-13) implement the watermarks-based schemes activation. Finally, the last two patches (patches 14-15) implement and document the DAMON-based reclamation using the advanced DAMOS. [1] https://www.kernel.org/doc/html/v5.15-rc1/vm/damon/index.html [2] https://research.google/pubs/pub48551/ [3] https://lwn.net/Articles/787611/ [4] https://damonitor.github.io [5] https://damonitor.github.io/doc/html/latest/vm/damon/eval.html [6] https://lore.kernel.org/linux-mm/20211001125604.29660-1-sj@kernel.org/ [7] https://github.com/awslabs/damoos [8] https://www.kernel.org/doc/html/latest/vm/free_page_reporting.html [9] https://www.usenix.org/conference/fast-04/car-clock-adaptive-replacement This patch (of 15): This makes the DAMON primitives for physical address space support the pageout action for DAMON-based Operation Schemes. With this commit, hence, users can easily implement system-level data access-aware reclamations using DAMOS. [sj@kernel.org: fix missing-prototype build warning] Link: https://lkml.kernel.org/r/20211025064220.13904-1-sj@kernel.org Link: https://lkml.kernel.org/r/20211019150731.16699-1-sj@kernel.org Link: https://lkml.kernel.org/r/20211019150731.16699-2-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Cameron Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Jonathan Corbet Cc: David Hildenbrand Cc: David Woodhouse Cc: Marco Elver Cc: Leonard Foerster Cc: Greg Thelen Cc: Markus Boehme Cc: David Rientjes Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 715dadd21f7c..9a327bc787b5 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -357,6 +357,8 @@ void damon_va_set_primitives(struct damon_ctx *ctx); void damon_pa_prepare_access_checks(struct damon_ctx *ctx); unsigned int damon_pa_check_accesses(struct damon_ctx *ctx); bool damon_pa_target_valid(void *t); +int damon_pa_apply_scheme(struct damon_ctx *context, struct damon_target *t, + struct damon_region *r, struct damos *scheme); void damon_pa_set_primitives(struct damon_ctx *ctx); #endif /* CONFIG_DAMON_PADDR */ -- cgit v1.2.3 From 2b8a248d5873343aa16f6c5ede30517693995f13 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:16 -0700 Subject: mm/damon/schemes: implement size quota for schemes application speed control There could be arbitrarily large memory regions fulfilling the target data access pattern of a DAMON-based operation scheme. In the case, applying the action of the scheme could incur too high overhead. To provide an intuitive way for avoiding it, this implements a feature called size quota. If the quota is set, DAMON tries to apply the action only up to the given amount of memory regions within a given time window. Link: https://lkml.kernel.org/r/20211019150731.16699-3-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 36 ++++++++++++++++++++++++++++++++---- 1 file changed, 32 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 9a327bc787b5..3a1ce9d9921c 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -89,6 +89,26 @@ enum damos_action { DAMOS_STAT, /* Do nothing but only record the stat */ }; +/** + * struct damos_quota - Controls the aggressiveness of the given scheme. + * @sz: Maximum bytes of memory that the action can be applied. + * @reset_interval: Charge reset interval in milliseconds. + * + * To avoid consuming too much CPU time or IO resources for applying the + * &struct damos->action to large memory, DAMON allows users to set a size + * quota. The quota can be set by writing non-zero values to &sz. If the size + * quota is set, DAMON tries to apply the action only up to &sz bytes within + * &reset_interval. + */ +struct damos_quota { + unsigned long sz; + unsigned long reset_interval; + +/* private: For charging the quota */ + unsigned long charged_sz; + unsigned long charged_from; +}; + /** * struct damos - Represents a Data Access Monitoring-based Operation Scheme. * @min_sz_region: Minimum size of target regions. @@ -98,13 +118,20 @@ enum damos_action { * @min_age_region: Minimum age of target regions. * @max_age_region: Maximum age of target regions. * @action: &damo_action to be applied to the target regions. + * @quota: Control the aggressiveness of this scheme. * @stat_count: Total number of regions that this scheme is applied. * @stat_sz: Total size of regions that this scheme is applied. * @list: List head for siblings. * - * For each aggregation interval, DAMON applies @action to monitoring target - * regions fit in the condition and updates the statistics. Note that both - * the minimums and the maximums are inclusive. + * For each aggregation interval, DAMON finds regions which fit in the + * condition (&min_sz_region, &max_sz_region, &min_nr_accesses, + * &max_nr_accesses, &min_age_region, &max_age_region) and applies &action to + * those. To avoid consuming too much CPU time or IO resources for the + * &action, "a is used. + * + * After applying the &action to each region, &stat_count and &stat_sz is + * updated to reflect the number of regions and total size of regions that the + * &action is applied. */ struct damos { unsigned long min_sz_region; @@ -114,6 +141,7 @@ struct damos { unsigned int min_age_region; unsigned int max_age_region; enum damos_action action; + struct damos_quota quota; unsigned long stat_count; unsigned long stat_sz; struct list_head list; @@ -310,7 +338,7 @@ struct damos *damon_new_scheme( unsigned long min_sz_region, unsigned long max_sz_region, unsigned int min_nr_accesses, unsigned int max_nr_accesses, unsigned int min_age_region, unsigned int max_age_region, - enum damos_action action); + enum damos_action action, struct damos_quota *quota); void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); void damon_destroy_scheme(struct damos *s); -- cgit v1.2.3 From 50585192bc2ef9309d32dabdbb5e735679f4f128 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:20 -0700 Subject: mm/damon/schemes: skip already charged targets and regions If DAMOS has stopped applying action in the middle of a group of memory regions due to its size quota, it starts the work again from the beginning of the address space in the next charge window. If there is a huge memory region at the beginning of the address space and it fulfills the scheme's target data access pattern always, the action will applied to only the region. This mitigates the case by skipping memory regions that charged in current charge window at the beginning of next charge window. Link: https://lkml.kernel.org/r/20211019150731.16699-4-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 3a1ce9d9921c..585d985768fd 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -107,6 +107,8 @@ struct damos_quota { /* private: For charging the quota */ unsigned long charged_sz; unsigned long charged_from; + struct damon_target *charge_target_from; + unsigned long charge_addr_from; }; /** @@ -307,6 +309,9 @@ struct damon_ctx { #define damon_prev_region(r) \ (container_of(r->list.prev, struct damon_region, list)) +#define damon_last_region(t) \ + (list_last_entry(&t->regions_list, struct damon_region, list)) + #define damon_for_each_region(r, t) \ list_for_each_entry(r, &t->regions_list, list) -- cgit v1.2.3 From 1cd2430300594a230dba9178ac9e286d868d9da2 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:23 -0700 Subject: mm/damon/schemes: implement time quota The size quota feature of DAMOS is useful for IO resource-critical systems, but not so intuitive for CPU time-critical systems. Systems using zram or zswap-like swap device would be examples. To provide another intuitive ways for such systems, this implements time-based quota for DAMON-based Operation Schemes. If the quota is set, DAMOS tries to use only up to the user-defined quota of CPU time within a given time window. Link: https://lkml.kernel.org/r/20211019150731.16699-5-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 25 ++++++++++++++++++++----- 1 file changed, 20 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 585d985768fd..1e7671bf3d23 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -91,20 +91,35 @@ enum damos_action { /** * struct damos_quota - Controls the aggressiveness of the given scheme. + * @ms: Maximum milliseconds that the scheme can use. * @sz: Maximum bytes of memory that the action can be applied. * @reset_interval: Charge reset interval in milliseconds. * * To avoid consuming too much CPU time or IO resources for applying the - * &struct damos->action to large memory, DAMON allows users to set a size - * quota. The quota can be set by writing non-zero values to &sz. If the size - * quota is set, DAMON tries to apply the action only up to &sz bytes within - * &reset_interval. + * &struct damos->action to large memory, DAMON allows users to set time and/or + * size quotas. The quotas can be set by writing non-zero values to &ms and + * &sz, respectively. If the time quota is set, DAMON tries to use only up to + * &ms milliseconds within &reset_interval for applying the action. If the + * size quota is set, DAMON tries to apply the action only up to &sz bytes + * within &reset_interval. + * + * Internally, the time quota is transformed to a size quota using estimated + * throughput of the scheme's action. DAMON then compares it against &sz and + * uses smaller one as the effective quota. */ struct damos_quota { + unsigned long ms; unsigned long sz; unsigned long reset_interval; -/* private: For charging the quota */ +/* private: */ + /* For throughput estimation */ + unsigned long total_charged_sz; + unsigned long total_charged_ns; + + unsigned long esz; /* Effective size quota in bytes */ + + /* For charging the quota */ unsigned long charged_sz; unsigned long charged_from; struct damon_target *charge_target_from; -- cgit v1.2.3 From 38683e003153f7abfa612d7b7fe147efa4624af2 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:33 -0700 Subject: mm/damon/schemes: prioritize regions within the quotas This makes DAMON apply schemes to regions having higher priority first, if it cannot apply schemes to all regions due to the quotas. The prioritization function should be implemented in the monitoring primitives. Those would commonly calculate the priority of the region using attributes of regions, namely 'size', 'nr_accesses', and 'age'. For example, some primitive would calculate the priority of each region using a weighted sum of 'nr_accesses' and 'age' of the region. The optimal weights would depend on give environments, so this makes those customizable. Nevertheless, the score calculation functions are only encouraged to respect the weights, not mandated. Link: https://lkml.kernel.org/r/20211019150731.16699-8-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 1e7671bf3d23..5d47ad9e3911 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -14,6 +14,8 @@ /* Minimal region size. Every damon_region is aligned by this. */ #define DAMON_MIN_REGION PAGE_SIZE +/* Max priority score for DAMON-based operation schemes */ +#define DAMOS_MAX_SCORE (99) /** * struct damon_addr_range - Represents an address region of [@start, @end). @@ -95,6 +97,10 @@ enum damos_action { * @sz: Maximum bytes of memory that the action can be applied. * @reset_interval: Charge reset interval in milliseconds. * + * @weight_sz: Weight of the region's size for prioritization. + * @weight_nr_accesses: Weight of the region's nr_accesses for prioritization. + * @weight_age: Weight of the region's age for prioritization. + * * To avoid consuming too much CPU time or IO resources for applying the * &struct damos->action to large memory, DAMON allows users to set time and/or * size quotas. The quotas can be set by writing non-zero values to &ms and @@ -106,12 +112,22 @@ enum damos_action { * Internally, the time quota is transformed to a size quota using estimated * throughput of the scheme's action. DAMON then compares it against &sz and * uses smaller one as the effective quota. + * + * For selecting regions within the quota, DAMON prioritizes current scheme's + * target memory regions using the &struct damon_primitive->get_scheme_score. + * You could customize the prioritization logic by setting &weight_sz, + * &weight_nr_accesses, and &weight_age, because monitoring primitives are + * encouraged to respect those. */ struct damos_quota { unsigned long ms; unsigned long sz; unsigned long reset_interval; + unsigned int weight_sz; + unsigned int weight_nr_accesses; + unsigned int weight_age; + /* private: */ /* For throughput estimation */ unsigned long total_charged_sz; @@ -124,6 +140,10 @@ struct damos_quota { unsigned long charged_from; struct damon_target *charge_target_from; unsigned long charge_addr_from; + + /* For prioritization */ + unsigned long histogram[DAMOS_MAX_SCORE + 1]; + unsigned int min_score; }; /** @@ -174,6 +194,7 @@ struct damon_ctx; * @prepare_access_checks: Prepare next access check of target regions. * @check_accesses: Check the accesses to target regions. * @reset_aggregated: Reset aggregated accesses monitoring results. + * @get_scheme_score: Get the score of a region for a scheme. * @apply_scheme: Apply a DAMON-based operation scheme. * @target_valid: Determine if the target is valid. * @cleanup: Clean up the context. @@ -200,6 +221,8 @@ struct damon_ctx; * of its update. The value will be used for regions adjustment threshold. * @reset_aggregated should reset the access monitoring results that aggregated * by @check_accesses. + * @get_scheme_score should return the priority score of a region for a scheme + * as an integer in [0, &DAMOS_MAX_SCORE]. * @apply_scheme is called from @kdamond when a region for user provided * DAMON-based operation scheme is found. It should apply the scheme's action * to the region. This is not used for &DAMON_ARBITRARY_TARGET case. @@ -213,6 +236,9 @@ struct damon_primitive { void (*prepare_access_checks)(struct damon_ctx *context); unsigned int (*check_accesses)(struct damon_ctx *context); void (*reset_aggregated)(struct damon_ctx *context); + int (*get_scheme_score)(struct damon_ctx *context, + struct damon_target *t, struct damon_region *r, + struct damos *scheme); int (*apply_scheme)(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, struct damos *scheme); bool (*target_valid)(void *target); -- cgit v1.2.3 From 198f0f4c58b9f481e4e51c8c70a6ab9852bbab7f Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:37 -0700 Subject: mm/damon/vaddr,paddr: support pageout prioritization This makes the default monitoring primitives for virtual address spaces and the physical address sapce to support memory regions prioritization for 'PAGEOUT' DAMOS action. It calculates hotness of each region as weighted sum of 'nr_accesses' and 'age' of the region and get the priority score as reverse of the hotness, so that cold regions can be paged out first. Link: https://lkml.kernel.org/r/20211019150731.16699-9-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 5d47ad9e3911..1217566a0ebc 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -421,6 +421,8 @@ bool damon_va_target_valid(void *t); void damon_va_cleanup(struct damon_ctx *ctx); int damon_va_apply_scheme(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, struct damos *scheme); +int damon_va_scheme_score(struct damon_ctx *context, struct damon_target *t, + struct damon_region *r, struct damos *scheme); void damon_va_set_primitives(struct damon_ctx *ctx); #endif /* CONFIG_DAMON_VADDR */ @@ -433,6 +435,8 @@ unsigned int damon_pa_check_accesses(struct damon_ctx *ctx); bool damon_pa_target_valid(void *t); int damon_pa_apply_scheme(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, struct damos *scheme); +int damon_pa_scheme_score(struct damon_ctx *context, struct damon_target *t, + struct damon_region *r, struct damos *scheme); void damon_pa_set_primitives(struct damon_ctx *ctx); #endif /* CONFIG_DAMON_PADDR */ -- cgit v1.2.3 From ee801b7dd7822a82fd7663048ad649545fac6df3 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:47 -0700 Subject: mm/damon/schemes: activate schemes based on a watermarks mechanism DAMON-based operation schemes need to be manually turned on and off. In some use cases, however, the condition for turning a scheme on and off would depend on the system's situation. For example, schemes for proactive pages reclamation would need to be turned on when some memory pressure is detected, and turned off when the system has enough free memory. For easier control of schemes activation based on the system situation, this introduces a watermarks-based mechanism. The client can describe the watermark metric (e.g., amount of free memory in the system), watermark check interval, and three watermarks, namely high, mid, and low. If the scheme is deactivated, it only gets the metric and compare that to the three watermarks for every check interval. If the metric is higher than the high watermark, the scheme is deactivated. If the metric is between the mid watermark and the low watermark, the scheme is activated. If the metric is lower than the low watermark, the scheme is deactivated again. This is to allow users fall back to traditional page-granularity mechanisms. Link: https://lkml.kernel.org/r/20211019150731.16699-12-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 51 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 1217566a0ebc..c93325efddd7 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -146,6 +146,45 @@ struct damos_quota { unsigned int min_score; }; +/** + * enum damos_wmark_metric - Represents the watermark metric. + * + * @DAMOS_WMARK_NONE: Ignore the watermarks of the given scheme. + * @DAMOS_WMARK_FREE_MEM_RATE: Free memory rate of the system in [0,1000]. + */ +enum damos_wmark_metric { + DAMOS_WMARK_NONE, + DAMOS_WMARK_FREE_MEM_RATE, +}; + +/** + * struct damos_watermarks - Controls when a given scheme should be activated. + * @metric: Metric for the watermarks. + * @interval: Watermarks check time interval in microseconds. + * @high: High watermark. + * @mid: Middle watermark. + * @low: Low watermark. + * + * If &metric is &DAMOS_WMARK_NONE, the scheme is always active. Being active + * means DAMON does monitoring and applying the action of the scheme to + * appropriate memory regions. Else, DAMON checks &metric of the system for at + * least every &interval microseconds and works as below. + * + * If &metric is higher than &high, the scheme is inactivated. If &metric is + * between &mid and &low, the scheme is activated. If &metric is lower than + * &low, the scheme is inactivated. + */ +struct damos_watermarks { + enum damos_wmark_metric metric; + unsigned long interval; + unsigned long high; + unsigned long mid; + unsigned long low; + +/* private: */ + bool activated; +}; + /** * struct damos - Represents a Data Access Monitoring-based Operation Scheme. * @min_sz_region: Minimum size of target regions. @@ -156,6 +195,7 @@ struct damos_quota { * @max_age_region: Maximum age of target regions. * @action: &damo_action to be applied to the target regions. * @quota: Control the aggressiveness of this scheme. + * @wmarks: Watermarks for automated (in)activation of this scheme. * @stat_count: Total number of regions that this scheme is applied. * @stat_sz: Total size of regions that this scheme is applied. * @list: List head for siblings. @@ -166,6 +206,14 @@ struct damos_quota { * those. To avoid consuming too much CPU time or IO resources for the * &action, "a is used. * + * To do the work only when needed, schemes can be activated for specific + * system situations using &wmarks. If all schemes that registered to the + * 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. + * * After applying the &action to each region, &stat_count and &stat_sz is * updated to reflect the number of regions and total size of regions that the * &action is applied. @@ -179,6 +227,7 @@ struct damos { unsigned int max_age_region; enum damos_action action; struct damos_quota quota; + struct damos_watermarks wmarks; unsigned long stat_count; unsigned long stat_sz; struct list_head list; @@ -384,7 +433,8 @@ struct damos *damon_new_scheme( unsigned long min_sz_region, unsigned long max_sz_region, unsigned int min_nr_accesses, unsigned int max_nr_accesses, unsigned int min_age_region, unsigned int max_age_region, - enum damos_action action, struct damos_quota *quota); + enum damos_action action, struct damos_quota *quota, + struct damos_watermarks *wmarks); void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); void damon_destroy_scheme(struct damos *s); -- cgit v1.2.3 From b5ca3e83ddb05342b1b30700b999cb9b107511f6 Mon Sep 17 00:00:00 2001 From: Xin Hao Date: Fri, 5 Nov 2021 13:48:07 -0700 Subject: mm/damon/dbgfs: add adaptive_targets list check before enable monitor_on When the ctx->adaptive_targets list is empty, I did some test on monitor_on interface like this. # cat /sys/kernel/debug/damon/target_ids # # echo on > /sys/kernel/debug/damon/monitor_on # damon: kdamond (5390) starts Though the ctx->adaptive_targets list is empty, but the kthread_run still be called, and the kdamond.x thread still be created, this is meaningless. So there adds a judgment in 'dbgfs_monitor_on_write', if the ctx->adaptive_targets list is empty, return -EINVAL. Link: https://lkml.kernel.org/r/0a60a6e8ec9d71989e0848a4dc3311996ca3b5d4.1634720326.git.xhao@linux.alibaba.com Signed-off-by: Xin Hao Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index c93325efddd7..fa7f32614b65 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -440,6 +440,7 @@ void damon_destroy_scheme(struct damos *s); struct damon_target *damon_new_target(unsigned long id); void damon_add_target(struct damon_ctx *ctx, struct damon_target *t); +bool damon_targets_empty(struct damon_ctx *ctx); void damon_free_target(struct damon_target *t); void damon_destroy_target(struct damon_target *t); unsigned int damon_nr_regions(struct damon_target *t); -- cgit v1.2.3 From 0f91d13366a402420bf98eaaf393db03946c13e0 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Fri, 5 Nov 2021 13:48:22 -0700 Subject: mm/damon: simplify stop mechanism A kernel thread can exit gracefully with kthread_stop(). So we don't need a new flag 'kdamond_stop'. And to make sure the task struct is not freed when accessing it, get reference to it before termination. Link: https://lkml.kernel.org/r/20211027130517.4404-1-changbin.du@gmail.com Signed-off-by: Changbin Du Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index fa7f32614b65..321de9d72360 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -381,7 +381,6 @@ struct damon_ctx { /* public: */ struct task_struct *kdamond; - bool kdamond_stop; struct mutex kdamond_lock; struct damon_primitive primitive; -- cgit v1.2.3 From 658f9ae761b5965893727dd4edcdad56e5a439bb Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Fri, 5 Nov 2021 13:48:27 -0700 Subject: mm/damon: remove return value from before_terminate callback Since the return value of 'before_terminate' callback is never used, we make it have no return value. Link: https://lkml.kernel.org/r/20211029005023.8895-1-changbin.du@gmail.com Signed-off-by: Changbin Du Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 321de9d72360..b4d4be3cc987 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -322,7 +322,7 @@ struct damon_callback { int (*before_start)(struct damon_ctx *context); int (*after_sampling)(struct damon_ctx *context); int (*after_aggregation)(struct damon_ctx *context); - int (*before_terminate)(struct damon_ctx *context); + void (*before_terminate)(struct damon_ctx *context); }; /** -- cgit v1.2.3