- 12 Jul, 2019 40 commits
-
-
Mike Rapoport authored
alpha allocates PTE pages with __get_free_page() and uses GFP_KERNEL | __GFP_ZERO for the allocations. Switch it to the generic version that does exactly the same thing for the kernel page tables and adds __GFP_ACCOUNT for the user PTEs. The alpha pte_free() and pte_free_kernel() versions are identical to the generic ones and can be simply dropped. Link: http://lkml.kernel.org/r/1557296232-15361-3-git-send-email-rppt@linux.ibm.comSigned-off-by:
Mike Rapoport <rppt@linux.ibm.com> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Anton Ivanov <anton.ivanov@cambridgegreys.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Guo Ren <guoren@kernel.org> Cc: Guo Ren <ren_guo@c-sky.com> Cc: Helge Deller <deller@gmx.de> Cc: Ley Foon Tan <lftan@altera.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Matt Turner <mattst88@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Hocko <mhocko@suse.com> Cc: Palmer Dabbelt <palmer@sifive.com> Cc: Paul Burton <paul.burton@mips.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Richard Weinberger <richard@nod.at> Cc: Russell King <linux@armlinux.org.uk> Cc: Sam Creasey <sammy@sammy.net> Cc: Vincent Chen <deanbo422@gmail.com> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Mike Rapoport authored
Most architectures have identical or very similar implementation of pte_alloc_one_kernel(), pte_alloc_one(), pte_free_kernel() and pte_free(). Add a generic implementation that can be reused across architectures and enable its use on x86. The generic implementation uses GFP_KERNEL | __GFP_ZERO for the kernel page tables and GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT for the user page tables. The "base" functions for PTE allocation, namely __pte_alloc_one_kernel() and __pte_alloc_one() are intended for the architectures that require additional actions after actual memory allocation or must use non-default GFP flags. x86 is switched to use generic pte_alloc_one_kernel(), pte_free_kernel() and pte_free(). x86 still implements pte_alloc_one() to allow run-time control of GFP flags required for "userpte" command line option. Link: http://lkml.kernel.org/r/1557296232-15361-2-git-send-email-rppt@linux.ibm.comSigned-off-by:
-
Guenter Roeck authored
Several mips builds generate the following build warning. mm/gup.c:1788:13: warning: 'undo_dev_pagemap' defined but not used The function is declared unconditionally but only called from behind various ifdefs. Mark it __maybe_unused. Link: http://lkml.kernel.org/r/1562072523-22311-1-git-send-email-linux@roeck-us.netSigned-off-by:
Guenter Roeck <linux@roeck-us.net> Reviewed-by:
-
Andy Lutomirski authored
If we end up without a PGD or PUD entry backing the gate area, don't BUG -- just fail gracefully. It's not entirely implausible that this could happen some day on x86. It doesn't right now even with an execute-only emulated vsyscall page because the fixmap shares the PUD, but the core mm code shouldn't rely on that particular detail to avoid OOPSing. Link: http://lkml.kernel.org/r/a1d9f4efb75b9d464e59fd6af00104b21c58f6f7.1561610798.git.luto@kernel.orgSigned-off-by:
Andy Lutomirski <luto@kernel.org> Reviewed-by:
Kees Cook <keescook@chromium.org> Reviewed-by:
-
Pingfan Liu authored
Both hugetlb and thp locate on the same migration type of pageblock, since they are allocated from a free_list[]. Based on this fact, it is enough to check on a single subpage to decide the migration type of the whole huge page. By this way, it saves (2M/4K - 1) times loop for pmd_huge on x86, similar on other archs. Furthermore, when executing isolate_huge_page(), it avoid taking global hugetlb_lock many times, and meanless remove/add to the local link list cma_page_list. [akpm@linux-foundation.org: make `i' and `step' unsigned] Link: http://lkml.kernel.org/r/1561612545-28997-1-git-send-email-kernelfans@gmail.comSigned-off-by:
Pingfan Liu <kernelfans@gmail.com> Reviewed-by:
Ira Weiny <ira.weiny@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: John Hubbard <jhubbard@nvidia.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Keith Busch <keith.busch@intel.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Signed-off-by:
-
Christoph Hellwig authored
All other get_user_page_fast cases mark the page referenced, so do this here as well. Link: http://lkml.kernel.org/r/20190625143715.1689-17-hch@lst.deSigned-off-by:
Christoph Hellwig <hch@lst.de> Cc: Andrey Konovalov <andreyknvl@google.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Miller <davem@davemloft.net> Cc: James Hogan <jhogan@kernel.org> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Khalid Aziz <khalid.aziz@oracle.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Paul Burton <paul.burton@mips.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Rich Felker <dalias@libc.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by:
-
Christoph Hellwig authored
This applies the overflow fixes from 8fde12ca ("mm: prevent get_user_pages() from overflowing page refcount") to the powerpc hugepd code and brings it back in sync with the other GUP cases. Link: http://lkml.kernel.org/r/20190625143715.1689-16-hch@lst.deSigned-off-by:
-
Christoph Hellwig authored
While only powerpc supports the hugepd case, the code is pretty generic and I'd like to keep all GUP internals in one place. Link: http://lkml.kernel.org/r/20190625143715.1689-15-hch@lst.deSigned-off-by:
-
Christoph Hellwig authored
We can only deal with FOLL_WRITE and/or FOLL_LONGTERM in get_user_pages_fast, so reject all other flags. Link: http://lkml.kernel.org/r/20190625143715.1689-14-hch@lst.deSigned-off-by:
-
Christoph Hellwig authored
Always build mm/gup.c so that we don't have to provide separate nommu stubs. Also merge the get_user_pages_fast and __get_user_pages_fast stubs when HAVE_FAST_GUP into the main implementations, which will never call the fast path if HAVE_FAST_GUP is not set. This also ensures the new put_user_pages* helpers are available for nommu, as those are currently missing, which would create a problem as soon as we actually grew users for it. Link: http://lkml.kernel.org/r/20190625143715.1689-13-hch@lst.deSigned-off-by:
-
Christoph Hellwig authored
This moves the actually exported functions towards the end of the file, and reorders some functions to be in more logical blocks as a preparation for moving various stubs inline into the main functionality using IS_ENABLED(). Link: http://lkml.kernel.org/r/20190625143715.1689-12-hch@lst.deSigned-off-by:
-
Christoph Hellwig authored
We only support the generic GUP now, so rename the config option to be more clear, and always use the mm/Kconfig definition of the symbol and select it from the arch Kconfigs. Link: http://lkml.kernel.org/r/20190625143715.1689-11-hch@lst.deSigned-off-by:
Khalid Aziz <khalid.aziz@oracle.com> Reviewed-by:
Jason Gunthorpe <jgg@mellanox.com> Cc: Andrey Konovalov <andreyknvl@google.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Miller <davem@davemloft.net> Cc: James Hogan <jhogan@kernel.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Paul Burton <paul.burton@mips.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Rich Felker <dalias@libc.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by:
-
Christoph Hellwig authored
The sparc64 code is mostly equivalent to the generic one, minus various bugfixes and two arch overrides that this patch adds to pgtable.h. Link: http://lkml.kernel.org/r/20190625143715.1689-10-hch@lst.deSigned-off-by:
-
Christoph Hellwig authored
Add a helper to untag a user pointer. This is needed for ADI support in get_user_pages_fast. Link: http://lkml.kernel.org/r/20190625143715.1689-9-hch@lst.deSigned-off-by:
-
Christoph Hellwig authored
sparc64 only had pgd_page_vaddr, but not pgd_page. [hch@lst.de: fix sparc64 build] Link: http://lkml.kernel.org/r/20190626131318.GA5101@lst.de Link: http://lkml.kernel.org/r/20190625143715.1689-8-hch@lst.deSigned-off-by:
-
Christoph Hellwig authored
The sh code is mostly equivalent to the generic one, minus various bugfixes and two arch overrides that this patch adds to pgtable.h. Link: http://lkml.kernel.org/r/20190625143715.1689-7-hch@lst.deSigned-off-by:
-
Christoph Hellwig authored
sh only had pud_page_vaddr, but not pud_page. [hch@lst.de: sh: stub out pud_page] Link: http://lkml.kernel.org/r/20190701151818.32227-2-hch@lst.de Link: http://lkml.kernel.org/r/20190625143715.1689-6-hch@lst.deSigned-off-by:
-
Christoph Hellwig authored
The mips code is mostly equivalent to the generic one, minus various bugfixes and an arch override for gup_fast_permitted. Note that this defines ARCH_HAS_PTE_SPECIAL for mips as mips has pte_special and pte_mkspecial implemented and used in the existing gup code. They are no-op stubs, though which makes me a little unsure if this is really right thing to do. Note that this also adds back a missing cpu_has_dc_aliases check for __get_user_pages_fast, which the old code was only doing for get_user_pages_fast. This clearly looks like an oversight, as any condition that makes get_user_pages_fast unsafe also applies to __get_user_pages_fast. [hch@lst.de: MIPS: don't select ARCH_HAS_PTE_SPECIAL] Link: http://lkml.kernel.org/r/20190701151818.32227-3-hch@lst.de Link: http://lkml.kernel.org/r/20190625143715.1689-5-hch@lst.deSigned-off-by:
-
Christoph Hellwig authored
The split low/high access is the only non-READ_ONCE version of gup_get_pte that did show up in the various arch implemenations. Lift it to common code and drop the ifdef based arch override. Link: http://lkml.kernel.org/r/20190625143715.1689-4-hch@lst.deSigned-off-by:
-
Christoph Hellwig authored
Pass in the already calculated end value instead of recomputing it, and leave the end > start check in the callers instead of duplicating them in the arch code. Link: http://lkml.kernel.org/r/20190625143715.1689-3-hch@lst.deSigned-off-by:
-
Christoph Hellwig authored
Patch series "switch the remaining architectures to use generic GUP", v4. A series to switch mips, sh and sparc64 to use the generic GUP code so that we only have one codebase to touch for further improvements to this code. This patch (of 16): This will allow sparc64, or any future architecture with memory tagging to override its tags for get_user_pages and get_user_pages_fast. Link: http://lkml.kernel.org/r/20190625143715.1689-2-hch@lst.deSigned-off-by:
-
Waiman Long authored
There are concerns about memory leaks from extensive use of memory cgroups as each memory cgroup creates its own set of kmem caches. There is a possiblity that the memcg kmem caches may remain even after the memory cgroups have been offlined. Therefore, it will be useful to show the status of each of memcg kmem caches. This patch introduces a new <debugfs>/memcg_slabinfo file which is somewhat similar to /proc/slabinfo in format, but lists only information about kmem caches that have child memcg kmem caches. Information available in /proc/slabinfo are not repeated in memcg_slabinfo. A portion of a sample output of the file was: # <name> <css_id[:dead]> <active_objs> <num_objs> <active_slabs> <num_slabs> rpc_inode_cache root 13 51 1 1 rpc_inode_cache 48 0 0 0 0 fat_inode_cache root 1 45 1 1 fat_inode_cache 41 2 45 1 1 xfs_inode root 770 816 24 24 xfs_inode 92 22 34 1 1 xfs_inode 88:dead 1 34 1 1 xfs_inode 89:dead 23 34 1 1 xfs_inode 85 4 34 1 1 xfs_inode 84 9 34 1 1 The css id of the memcg is also listed. If a memcg is not online, the tag ":dead" will be attached as shown above. [longman@redhat.com: memcg: add ":deact" tag for reparented kmem caches in memcg_slabinfo] Link: http://lkml.kernel.org/r/20190621173005.31514-1-longman@redhat.com [longman@redhat.com: set the flag in the common code as suggested by Roman] Link: http://lkml.kernel.org/r/20190627184324.5875-1-longman@redhat.com Link: http://lkml.kernel.org/r/20190619171621.26209-1-longman@redhat.comSigned-off-by:
Waiman Long <longman@redhat.com> Suggested-by:
Shakeel Butt <shakeelb@google.com> Reviewed-by:
Roman Gushchin <guro@fb.com> Acked-by:
David Rientjes <rientjes@google.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Signed-off-by:
-
Roman Gushchin authored
Let's reparent non-root kmem_caches on memcg offlining. This allows us to release the memory cgroup without waiting for the last outstanding kernel object (e.g. dentry used by another application). Since the parent cgroup is already charged, everything we need to do is to splice the list of kmem_caches to the parent's kmem_caches list, swap the memcg pointer, drop the css refcounter for each kmem_cache and adjust the parent's css refcounter. Please, note that kmem_cache->memcg_params.memcg isn't a stable pointer anymore. It's safe to read it under rcu_read_lock(), cgroup_mutex held, or any other way that protects the memory cgroup from being released. We can race with the slab allocation and deallocation paths. It's not a big problem: parent's charge and slab global stats are always correct, and we don't care anymore about the child usage and global stats. The child cgroup is already offline, so we don't use or show it anywhere. Local slab stats (NR_SLAB_RECLAIMABLE and NR_SLAB_UNRECLAIMABLE) aren't used anywhere except count_shadow_nodes(). But even there it won't break anything: after reparenting "nodes" will be 0 on child level (because we're already reparenting shrinker lists), and on parent level page stats always were 0, and this patch won't change anything. [guro@fb.com: properly handle kmem_caches reparented to root_mem_cgroup] Link: http://lkml.kernel.org/r/20190620213427.1691847-1-guro@fb.com Link: http://lkml.kernel.org/r/20190611231813.3148843-11-guro@fb.comSigned-off-by:
Vladimir Davydov <vdavydov.dev@gmail.com> Reviewed-by:
-
Roman Gushchin authored
Every slab page charged to a non-root memory cgroup has a pointer to the memory cgroup and holds a reference to it, which protects a non-empty memory cgroup from being released. At the same time the page has a pointer to the corresponding kmem_cache, and also hold a reference to the kmem_cache. And kmem_cache by itself holds a reference to the cgroup. So there is clearly some redundancy, which allows to stop setting the page->mem_cgroup pointer and rely on getting memcg pointer indirectly via kmem_cache. Further it will allow to change this pointer easier, without a need to go over all charged pages. So let's stop setting page->mem_cgroup pointer for slab pages, and stop using the css refcounter directly for protecting the memory cgroup from going away. Instead rely on kmem_cache as an intermediate object. Make sure that vmstats and shrinker lists are working as previously, as well as /proc/kpagecgroup interface. Link: http://lkml.kernel.org/r/20190611231813.3148843-10-guro@fb.comSigned-off-by:
-
Roman Gushchin authored
Currently each charged slab page holds a reference to the cgroup to which it's charged. Kmem_caches are held by the memcg and are released all together with the memory cgroup. It means that none of kmem_caches are released unless at least one reference to the memcg exists, which is very far from optimal. Let's rework it in a way that allows releasing individual kmem_caches as soon as the cgroup is offline, the kmem_cache is empty and there are no pending allocations. To make it possible, let's introduce a new percpu refcounter for non-root kmem caches. The counter is initialized to the percpu mode, and is switched to the atomic mode during kmem_cache deactivation. The counter is bumped for every charged page and also for every running allocation. So the kmem_cache can't be released unless all allocations complete. To shutdown non-active empty kmem_caches, let's reuse the work queue, previously used for the kmem_cache deactivation. Once the reference counter reaches 0, let's schedule an asynchronous kmem_cache release. * I used the following simple approach to test the performance (stolen from another patchset by T. Harding): time find / -name fname-no-exist echo 2 > /proc/sys/vm/drop_caches repeat 10 times Results: orig patched real 0m1.455s real 0m1.355s user 0m0.206s user 0m0.219s sys 0m0.855s sys 0m0.807s real 0m1.487s real 0m1.699s user 0m0.221s user 0m0.256s sys 0m0.806s sys 0m0.948s real 0m1.515s real 0m1.505s user 0m0.183s user 0m0.215s sys 0m0.876s sys 0m0.858s real 0m1.291s real 0m1.380s user 0m0.193s user 0m0.198s sys 0m0.843s sys 0m0.786s real 0m1.364s real 0m1.374s user 0m0.180s user 0m0.182s sys 0m0.868s sys 0m0.806s real 0m1.352s real 0m1.312s user 0m0.201s user 0m0.212s sys 0m0.820s sys 0m0.761s real 0m1.302s real 0m1.349s user 0m0.205s user 0m0.203s sys 0m0.803s sys 0m0.792s real 0m1.334s real 0m1.301s user 0m0.194s user 0m0.201s sys 0m0.806s sys 0m0.779s real 0m1.426s real 0m1.434s user 0m0.216s user 0m0.181s sys 0m0.824s sys 0m0.864s real 0m1.350s real 0m1.295s user 0m0.200s user 0m0.190s sys 0m0.842s sys 0m0.811s So it looks like the difference is not noticeable in this test. [cai@lca.pw: fix an use-after-free in kmemcg_workfn()] Link: http://lkml.kernel.org/r/1560977573-10715-1-git-send-email-cai@lca.pw Link: http://lkml.kernel.org/r/20190611231813.3148843-9-guro@fb.comSigned-off-by:Qian Cai <cai@lca.pw> Acked-by:
-
Roman Gushchin authored
Currently the memcg_params.dying flag and the corresponding workqueue used for the asynchronous deactivation of kmem_caches is synchronized using the slab_mutex. It makes impossible to check this flag from the irq context, which will be required in order to implement asynchronous release of kmem_caches. So let's switch over to the irq-save flavor of the spinlock-based synchronization. Link: http://lkml.kernel.org/r/20190611231813.3148843-8-guro@fb.comSigned-off-by:
-
Roman Gushchin authored
There is no point in checking the root_cache->memcg_params.dying flag on kmem_cache creation path. New allocations shouldn't be performed using a dead root kmem_cache, so no new memcg kmem_cache creation can be scheduled after the flag is set. And if it was scheduled before, flush_memcg_workqueue() will wait for it anyway. So let's drop this check to simplify the code. Link: http://lkml.kernel.org/r/20190611231813.3148843-7-guro@fb.comSigned-off-by:
-
Roman Gushchin authored
Currently the page accounting code is duplicated in SLAB and SLUB internals. Let's move it into new (un)charge_slab_page helpers in the slab_common.c file. These helpers will be responsible for statistics (global and memcg-aware) and memcg charging. So they are replacing direct memcg_(un)charge_slab() calls. Link: http://lkml.kernel.org/r/20190611231813.3148843-6-guro@fb.comSigned-off-by:
Christoph Lameter <cl@linux.com> Acked-by:
Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Waiman Long <longman@redhat.com> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Andrei Vagin <avagin@gmail.com> Cc: Qian Cai <cai@lca.pw> Signed-off-by:
-
Roman Gushchin authored
Let's separate the page counter modification code out of __memcg_kmem_uncharge() in a way similar to what __memcg_kmem_charge() and __memcg_kmem_charge_memcg() work. This will allow to reuse this code later using a new memcg_kmem_uncharge_memcg() wrapper, which calls __memcg_kmem_uncharge_memcg() if memcg_kmem_enabled() check is passed. Link: http://lkml.kernel.org/r/20190611231813.3148843-5-guro@fb.comSigned-off-by:
-
Roman Gushchin authored
Currently SLUB uses a work scheduled after an RCU grace period to deactivate a non-root kmem_cache. This mechanism can be reused for kmem_caches release, but requires generalization for SLAB case. Introduce kmemcg_cache_deactivate() function, which calls allocator-specific __kmem_cache_deactivate() and schedules execution of __kmem_cache_deactivate_after_rcu() with all necessary locks in a worker context after an rcu grace period. Here is the new calling scheme: kmemcg_cache_deactivate() __kmemcg_cache_deactivate() SLAB/SLUB-specific kmemcg_rcufn() rcu kmemcg_workfn() work __kmemcg_cache_deactivate_after_rcu() SLAB/SLUB-specific instead of: __kmemcg_cache_deactivate() SLAB/SLUB-specific slab_deactivate_memcg_cache_rcu_sched() SLUB-only kmemcg_rcufn() rcu kmemcg_workfn() work kmemcg_cache_deact_after_rcu() SLUB-only For consistency, all allocator-specific functions start with "__". Link: http://lkml.kernel.org/r/20190611231813.3148843-4-guro@fb.comSigned-off-by: -
Roman Gushchin authored
The delayed work/rcu deactivation infrastructure of non-root kmem_caches can be also used for asynchronous release of these objects. Let's get rid of the word "deactivation" in corresponding names to make the code look better after generalization. It's easier to make the renaming first, so that the generalized code will look consistent from scratch. Let's rename struct memcg_cache_params fields: deact_fn -> work_fn deact_rcu_head -> rcu_head deact_work -> work And RCU/delayed work callbacks in slab common code: kmemcg_deactivate_rcufn -> kmemcg_rcufn kmemcg_deactivate_workfn -> kmemcg_workfn This patch contains no functional changes, only renamings. Link: http://lkml.kernel.org/r/20190611231813.3148843-3-guro@fb.comSigned-off-by:
-
Roman Gushchin authored
Patch series "mm: reparent slab memory on cgroup removal", v7. # Why do we need this? We've noticed that the number of dying cgroups is steadily growing on most of our hosts in production. The following investigation revealed an issue in the userspace memory reclaim code [1], accounting of kernel stacks [2], and also the main reason: slab objects. The underlying problem is quite simple: any page charged to a cgroup holds a reference to it, so the cgroup can't be reclaimed unless all charged pages are gone. If a slab object is actively used by other cgroups, it won't be reclaimed, and will prevent the origin cgroup from being reclaimed. Slab objects, and first of all vfs cache, is shared between cgroups, which are using the same underlying fs, and what's even more important, it's shared between multiple generations of the same workload. So if something is running periodically every time in a new cgroup (like how systemd works), we do accumulate multiple dying cgroups. Strictly speaking pagecache isn't different here, but there is a key difference: we disable protection and apply some extra pressure on LRUs of dying cgroups, and these LRUs contain all charged pages. My experiments show that with the disabled kernel memory accounting the number of dying cgroups stabilizes at a relatively small number (~100, depends on memory pressure and cgroup creation rate), and with kernel memory accounting it grows pretty steadily up to several thousands. Memory cgroups are quite complex and big objects (mostly due to percpu stats), so it leads to noticeable memory losses. Memory occupied by dying cgroups is measured in hundreds of megabytes. I've even seen a host with more than 100Gb of memory wasted for dying cgroups. It leads to a degradation of performance with the uptime, and generally limits the usage of cgroups. My previous attempt [3] to fix the problem by applying extra pressure on slab shrinker lists caused a regressions with xfs and ext4, and has been reverted [4]. The following attempts to find the right balance [5, 6] were not successful. So instead of trying to find a maybe non-existing balance, let's do reparent accounted slab caches to the parent cgroup on cgroup removal. # Implementation approach There is however a significant problem with reparenting of slab memory: there is no list of charged pages. Some of them are in shrinker lists, but not all. Introducing of a new list is really not an option. But fortunately there is a way forward: every slab page has a stable pointer to the corresponding kmem_cache. So the idea is to reparent kmem_caches instead of slab pages. It's actually simpler and cheaper, but requires some underlying changes: 1) Make kmem_caches to hold a single reference to the memory cgroup, instead of a separate reference per every slab page. 2) Stop setting page->mem_cgroup pointer for memcg slab pages and use page->kmem_cache->memcg indirection instead. It's used only on slab page release, so performance overhead shouldn't be a big issue. 3) Introduce a refcounter for non-root slab caches. It's required to be able to destroy kmem_caches when they become empty and release the associated memory cgroup. There is a bonus: currently we release all memcg kmem_caches all together with the memory cgroup itself. This patchset allows individual kmem_caches to be released as soon as they become inactive and free. Some additional implementation details are provided in corresponding commit messages. # Results Below is the average number of dying cgroups on two groups of our production hosts. They do run some sort of web frontend workload, the memory pressure is moderate. As we can see, with the kernel memory reparenting the number stabilizes in 60s range; however with the original version it grows almost linearly and doesn't show any signs of plateauing. The difference in slab and percpu usage between patched and unpatched versions also grows linearly. In 7 days it exceeded 200Mb. day 0 1 2 3 4 5 6 7 original 56 362 628 752 1070 1250 1490 1560 patched 23 46 51 55 60 57 67 69 mem diff(Mb) 22 74 123 152 164 182 214 241 # Links [1]: commit 68600f62 ("mm: don't miss the last page because of round-off error") [2]: commit 9b6f7e16 ("mm: rework memcg kernel stack accounting") [3]: commit 172b06c3 ("mm: slowly shrink slabs with a relatively small number of objects") [4]: commit a9a238e8 ("Revert "mm: slowly shrink slabs with a relatively small number of objects") [5]: https://lkml.org/lkml/2019/1/28/1865 [6]: https://marc.info/?l=linux-mm&m=155064763626437&w=2 This patch (of 10): Initialize kmem_cache->memcg_params.memcg pointer in memcg_link_cache() rather than in init_memcg_params(). Once kmem_cache will hold a reference to the memory cgroup, it will simplify the refcounting. For non-root kmem_caches memcg_link_cache() is always called before the kmem_cache becomes visible to a user, so it's safe. Link: http://lkml.kernel.org/r/20190611231813.3148843-2-guro@fb.comSigned-off-by:
-
Johannes Weiner authored
The current cgroup OOM memory info dump doesn't include all the memory we are tracking, nor does it give insight into what the VM tried to do leading up to the OOM. All that useful info is in memory.stat. Furthermore, the recursive printing for every child cgroup can generate absurd amounts of data on the console for larger cgroup trees, and it's not like we provide a per-cgroup breakdown during global OOM kills. When an OOM kill is triggered, print one set of recursive memory.stat items at the level whose limit triggered the OOM condition. Example output: stress invoked oom-killer: gfp_mask=0x100cca(GFP_HIGHUSER_MOVABLE), order=0, oom_score_adj=0 CPU: 2 PID: 210 Comm: stress Not tainted 5.2.0-rc2-mm1-00247-g47d49835983c #135 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-20181126_142135-anatol 04/01/2014 Call Trace: dump_stack+0x46/0x60 dump_header+0x4c/0x2d0 oom_kill_process.cold.10+0xb/0x10 out_of_memory+0x200/0x270 ? try_to_free_mem_cgroup_pages+0xdf/0x130 mem_cgroup_out_of_memory+0xb7/0xc0 try_charge+0x680/0x6f0 mem_cgroup_try_charge+0xb5/0x160 __add_to_page_cache_locked+0xc6/0x300 ? list_lru_destroy+0x80/0x80 add_to_page_cache_lru+0x45/0xc0 pagecache_get_page+0x11b/0x290 filemap_fault+0x458/0x6d0 ext4_filemap_fault+0x27/0x36 __do_fault+0x2f/0xb0 __handle_mm_fault+0x9c5/0x1140 ? apic_timer_interrupt+0xa/0x20 handle_mm_fault+0xc5/0x180 __do_page_fault+0x1ab/0x440 ? page_fault+0x8/0x30 page_fault+0x1e/0x30 RIP: 0033:0x55c32167fc10 Code: Bad RIP value. RSP: 002b:00007fff1d031c50 EFLAGS: 00010206 RAX: 000000000dc00000 RBX: 00007fd2db000010 RCX: 00007fd2db000010 RDX: 0000000000000000 RSI: 0000000010001000 RDI: 0000000000000000 RBP: 000055c321680a54 R08: 00000000ffffffff R09: 0000000000000000 R10: 0000000000000022 R11: 0000000000000246 R12: ffffffffffffffff R13: 0000000000000002 R14: 0000000000001000 R15: 0000000010000000 memory: usage 1024kB, limit 1024kB, failcnt 75131 swap: usage 0kB, limit 9007199254740988kB, failcnt 0 Memory cgroup stats for /foo: anon 0 file 0 kernel_stack 36864 slab 274432 sock 0 shmem 0 file_mapped 0 file_dirty 0 file_writeback 0 anon_thp 0 inactive_anon 126976 active_anon 0 inactive_file 0 active_file 0 unevictable 0 slab_reclaimable 0 slab_unreclaimable 274432 pgfault 59466 pgmajfault 1617 workingset_refault 2145 workingset_activate 0 workingset_nodereclaim 0 pgrefill 98952 pgscan 200060 pgsteal 59340 pgactivate 40095 pgdeactivate 96787 pglazyfree 0 pglazyfreed 0 thp_fault_alloc 0 thp_collapse_alloc 0 Tasks state (memory values in pages): [ pid ] uid tgid total_vm rss pgtables_bytes swapents oom_score_adj name [ 200] 0 200 1121 884 53248 29 0 bash [ 209] 0 209 905 246 45056 19 0 stress [ 210] 0 210 66442 56 499712 56349 0 stress oom-kill:constraint=CONSTRAINT_NONE,nodemask=(null),oom_memcg=/foo,task_memcg=/foo,task=stress,pid=210,uid=0 Memory cgroup out of memory: Killed process 210 (stress) total-vm:265768kB, anon-rss:0kB, file-rss:224kB, shmem-rss:0kB oom_reaper: reaped process 210 (stress), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB [hannes@cmpxchg.org: s/kvmalloc/kmalloc/ per Michal] Link: http://lkml.kernel.org/r/20190605161133.GA12453@cmpxchg.org Link: http://lkml.kernel.org/r/20190604210509.9744-1-hannes@cmpxchg.orgSigned-off-by:Michal Hocko <mhocko@suse.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Signed-off-by:
-
Shakeel Butt authored
The memory controller in cgroup v2 exposes memory.events file for each memcg which shows the number of times events like low, high, max, oom and oom_kill have happened for the whole tree rooted at that memcg. Users can also poll or register notification to monitor the changes in that file. Any event at any level of the tree rooted at memcg will notify all the listeners along the path till root_mem_cgroup. There are existing users which depend on this behavior. However there are users which are only interested in the events happening at a specific level of the memcg tree and not in the events in the underlying tree rooted at that memcg. One such use-case is a centralized resource monitor which can dynamically adjust the limits of the jobs running on a system. The jobs can create their sub-hierarchy for their own sub-tasks. The centralized monitor is only interested in the events at the top level memcgs of the jobs as it can then act and adjust the limits of the jobs. Using the current memory.events for such centralized monitor is very inconvenient. The monitor will keep receiving events which it is not interested and to find if the received event is interesting, it has to read memory.event files of the next level and compare it with the top level one. So, let's introduce memory.events.local to the memcg which shows and notify for the events at the memcg level. Now, does memory.stat and memory.pressure need their local versions. IMHO no due to the no internal process contraint of the cgroup v2. The memory.stat file of the top level memcg of a job shows the stats and vmevents of the whole tree. The local stats or vmevents of the top level memcg will only change if there is a process running in that memcg but v2 does not allow that. Similarly for memory.pressure there will not be any process in the internal nodes and thus no chance of local pressure. Link: http://lkml.kernel.org/r/20190527174643.209172-1-shakeelb@google.comSigned-off-by:
-
Shakeel Butt authored
Commit d46eb14b ("fs: fsnotify: account fsnotify metadata to kmemcg") added remote memcg charging for fanotify and inotify event objects. The aim was to charge the memory to the listener who is interested in the events but without triggering the OOM killer. Otherwise there would be security concerns for the listener. At the time, oom-kill trigger was not in the charging path. A parallel work added the oom-kill back to charging path i.e. commit 29ef680a ("memcg, oom: move out_of_memory back to the charge path"). So to not trigger oom-killer in the remote memcg, explicitly add __GFP_RETRY_MAYFAIL to the fanotigy and inotify event allocations. Link: http://lkml.kernel.org/r/20190514212259.156585-2-shakeelb@google.comSigned-off-by:
Jan Kara <jack@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Amir Goldstein <amir73il@gmail.com> Signed-off-by:
-
Shakeel Butt authored
The documentation of __GFP_RETRY_MAYFAIL clearly mentioned that the OOM killer will not be triggered and indeed the page alloc does not invoke OOM killer for such allocations. However we do trigger memcg OOM killer for __GFP_RETRY_MAYFAIL. Fix that. This flag will used later to not trigger oom-killer in the charging path for fanotify and inotify event allocations. Link: http://lkml.kernel.org/r/20190514212259.156585-1-shakeelb@google.comSigned-off-by:
-
Huang Ying authored
Via commit 4b3ef9da ("mm/swap: split swap cache into 64MB trunks"), after swapoff, the address_space associated with the swap device will be freed. So swap_address_space() users which touch the address_space need some kind of mechanism to prevent the address_space from being freed during accessing. When mincore processes an unmapped range for swapped shmem pages, it doesn't hold the lock to prevent swap device from being swapped off. So the following race is possible: CPU1 CPU2 do_mincore() swapoff() walk_page_range() mincore_unmapped_range() __mincore_unmapped_range mincore_page as = swap_address_space() ... exit_swap_address_space() ... kvfree(spaces) find_get_page(as) The address space may be accessed after being freed. To fix the race, get_swap_device()/put_swap_device() is used to enclose find_get_page() to check whether the swap entry is valid and prevent the swap device from being swapoff during accessing. Link: http://lkml.kernel.org/r/20190611020510.28251-1-ying.huang@intel.com Fixes: 4b3ef9da ("mm/swap: split swap cache into 64MB trunks") Signed-off-by:
"Huang, Ying" <ying.huang@intel.com> Reviewed-by:
-
Aaron Lu authored
swap_extent is used to map swap page offset to backing device's block offset. For a continuous block range, one swap_extent is used and all these swap_extents are managed in a linked list. These swap_extents are used by map_swap_entry() during swap's read and write path. To find out the backing device's block offset for a page offset, the swap_extent list will be traversed linearly, with curr_swap_extent being used as a cache to speed up the search. This works well as long as swap_extents are not huge or when the number of processes that access swap device are few, but when the swap device has many extents and there are a number of processes accessing the swap device concurrently, it can be a problem. On one of our servers, the disk's remaining size is tight: $df -h Filesystem Size Used Avail Use% Mounted on ... ... /dev/nvme0n1p1 1.8T 1.3T 504G 72% /home/t4 When creating a 80G swapfile there, there are as many as 84656 swap extents. The end result is, kernel spends abou 30% time in map_swap_entry() and swap throughput is only 70MB/s. As a comparison, when I used smaller sized swapfile, like 4G whose swap_extent dropped to 2000, swap throughput is back to 400-500MB/s and map_swap_entry() is about 3%. One downside of using rbtree for swap_extent is, 'struct rbtree' takes 24 bytes while 'struct list_head' takes 16 bytes, that's 8 bytes more for each swap_extent. For a swapfile that has 80k swap_extents, that means 625KiB more memory consumed. Test: Since it's not possible to reboot that server, I can not test this patch diretly there. Instead, I tested it on another server with NVMe disk. I created a 20G swapfile on an NVMe backed XFS fs. By default, the filesystem is quite clean and the created swapfile has only 2 extents. Testing vanilla and this patch shows no obvious performance difference when swapfile is not fragmented. To see the patch's effects, I used some tweaks to manually fragment the swapfile by breaking the extent at 1M boundary. This made the swapfile have 20K extents. nr_task=4 kernel swapout(KB/s) map_swap_entry(perf) swapin(KB/s) map_swap_entry(perf) vanilla 165191 90.77% 171798 90.21% patched 858993 +420% 2.16% 715827 +317% 0.77% nr_task=8 kernel swapout(KB/s) map_swap_entry(perf) swapin(KB/s) map_swap_entry(perf) vanilla 306783 92.19% 318145 87.76% patched 954437 +211% 2.35% 1073741 +237% 1.57% swapout: the throughput of swap out, in KB/s, higher is better 1st map_swap_entry: cpu cycles percent sampled by perf swapin: the throughput of swap in, in KB/s, higher is better. 2nd map_swap_entry: cpu cycles percent sampled by perf nr_task=1 doesn't show any difference, this is due to the curr_swap_extent can be effectively used to cache the correct swap extent for single task workload. [akpm@linux-foundation.org: s/BUG_ON(1)/BUG()/] Link: http://lkml.kernel.org/r/20190523142404.GA181@aaronluSigned-off-by:
Aaron Lu <ziqian.lzq@antfin.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Hugh Dickins <hughd@google.com> Signed-off-by:
-
Huang Ying authored
total_swapcache_pages() may race with swapper_spaces[] allocation and freeing. Previously, this is protected with a swapper_spaces[] specific RCU mechanism. To simplify the logic/code complexity, it is replaced with get/put_swap_device(). The code line number is reduced too. Although not so important, the swapoff() performance improves too because one synchronize_rcu() call during swapoff() is deleted. [ying.huang@intel.com: fix bad swap file entry warning] Link: http://lkml.kernel.org/r/20190531024102.21723-1-ying.huang@intel.com Link: http://lkml.kernel.org/r/20190527082714.12151-1-ying.huang@intel.comSigned-off-by:
Mike Kravetz <mike.kravetz@oracle.com> Cc: Hugh Dickins <hughd@google.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Yang Shi <yang.shi@linux.alibaba.com> Cc: David Rientjes <rientjes@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Daniel Jordan <daniel.m.jordan@oracle.com> Cc: Andrea Parri <andrea.parri@amarulasolutions.com> Signed-off-by:
-
Huang Ying authored
When swapin is performed, after getting the swap entry information from the page table, system will swap in the swap entry, without any lock held to prevent the swap device from being swapoff. This may cause the race like below, CPU 1 CPU 2 ----- ----- do_swap_page swapin_readahead __read_swap_cache_async swapoff swapcache_prepare p->swap_map = NULL __swap_duplicate p->swap_map[?] /* !!! NULL pointer access */ Because swapoff is usually done when system shutdown only, the race may not hit many people in practice. But it is still a race need to be fixed. To fix the race, get_swap_device() is added to check whether the specified swap entry is valid in its swap device. If so, it will keep the swap entry valid via preventing the swap device from being swapoff, until put_swap_device() is called. Because swapoff() is very rare code path, to make the normal path runs as fast as possible, rcu_read_lock/unlock() and synchronize_rcu() instead of reference count is used to implement get/put_swap_device(). >From get_swap_device() to put_swap_device(), RCU reader side is locked, so synchronize_rcu() in swapoff() will wait until put_swap_device() is called. In addition to swap_map, cluster_info, etc. data structure in the struct swap_info_struct, the swap cache radix tree will be freed after swapoff, so this patch fixes the race between swap cache looking up and swapoff too. Races between some other swap cache usages and swapoff are fixed too via calling synchronize_rcu() between clearing PageSwapCache() and freeing swap cache data structure. Another possible method to fix this is to use preempt_off() + stop_machine() to prevent the swap device from being swapoff when its data structure is being accessed. The overhead in hot-path of both methods is similar. The advantages of RCU based method are, 1. stop_machine() may disturb the normal execution code path on other CPUs. 2. File cache uses RCU to protect its radix tree. If the similar mechanism is used for swap cache too, it is easier to share code between them. 3. RCU is used to protect swap cache in total_swapcache_pages() and exit_swap_address_space() already. The two mechanisms can be merged to simplify the logic. Link: http://lkml.kernel.org/r/20190522015423.14418-1-ying.huang@intel.com Fixes: 235b6217 ("mm/swap: add cluster lock") Signed-off-by:
Andrea Parri <andrea.parri@amarulasolutions.com> Not-nacked-by:
Hugh Dickins <hughd@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Daniel Jordan <daniel.m.jordan@oracle.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Yang Shi <yang.shi@linux.alibaba.com> Cc: David Rientjes <rientjes@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Dave Jiang <dave.jiang@intel.com> Signed-off-by:
-
