kernel

[PATCH 00/33] Split ptdesc from struct page (Vishal Moola) https://lkml.kernel.org/r/20230417205048.15870-1-vishal.moola@gmail.com To reduce the struct page overhead, which is about 1.5% of the whole system memory, people are working on to reduce some fileds in struct page. As one of the approach, this patchset prepares for splitting ptdesc from struct page. [RFC PATCH v1 0/5] Introduce objects folding mechanism (Alexey Romanov) https://lkml.kernel.org/r/20230418062503.62121-1-avromanov@sberdevices.ru This patchset adds a feature which allowing folding identical zsmalloc objects into single one.

[PATCH v5] mm: oom: introduce cpuset oom (Gang Li) https://lkml.kernel.org/r/20230411134539.45046-1-ligang.bdlg@bytedance.com This patch makes oomkiller to aware of numa nodes of processes that assigned via cpuset so that real memory pressure tirggeered process can be picked as victim of the pressure. [LSF/MM/BPF TOPIC] Reducing zombie memcgs (T.J. Mercier) https://lkml.kernel.org/r/CABdmKX2M6koq4Q0Cmp_-=wbP0Qa190HdEGGaHfxNS05gAkUtPA@mail.gmail.com Memcg lives in the kernel until the reference count drops to zero, even if it’s removed by userspace. This zombie-like memcg consumes system resource and makes kernel operations that get affected by the total number of memcg less efficient.

[PATCH 0/6] Avoid the mmap lock for fault-around (Matthew Wilcox) https://lkml.kernel.org/r/20230404135850.3673404-1-willy@infradead.org A patchset for gradually pushing the mmap lock down. No specific regression found, but also no special performance improvement measured. [PATCH] memcg-v1: Enable setting memory min, low, high (Shaun Tancheff) https://lkml.kernel.org/r/20230405110107.127156-1-shaun.tancheff@gmail.com For users who cannot update to memcg v2, this patch provides a way for memcg v1 to effectively apply memory pressure, which can be used for effectively throttle file I/O.

[PATCH] LoongArch: Add kernel address sanitizer support (Qing Zhang) https://lkml.kernel.org/r/20230328111714.2056-1-zhangqing@loongson.cn Loongarch has arch specific memory holes and mapping formula. This patch adds kasan support for Loongarch. [PATCH v2 0/7] Split a folio to any lower order folios (Zi Yan) https://lkml.kernel.org/r/20230329011712.3242298-1-zi.yan@sent.com Currently, split_huge_page() splits huge page to only order 0 pages. This patchset adds support of splitting a huge page to any lower order pages. [PATCHv9 00/14] mm, x86/cc: Implement support for unaccepted memory (Kirill A.

[PATCH 00/15] mm: move core MM initialization to mm/mm_init.c (Mike Rapoport) https://lkml.kernel.org/r/20230319220008.2138576-1-rppt@kernel.org This patchset consolidates MM initialization code to mm/mm_init.c file for better maintainability. [PATCH -next v6 0/2] Delay the initialization of zswap (Liu Shixin) https://lkml.kernel.org/r/20230322102006.780624-1-liushixin2@huawei.com This patchset delays zswap initialization until it gets enabled to save about 18MB of memory, which is allocated during the initialization. [PATCH V6 1/2] mm: compaction: move compaction sysctl to its own file (Minhao Chi) https://lkml.

[LSF/MM/BPF TOPIC] SLOB+SLAB allocators removal and future SLUB improvements (Vlastimil Babka) https://lkml.kernel.org/r/4b9fc9c6-b48c-198f-5f80-811a44737e5f@suse.cz Linux kernel has three objects allocators, namely SLOB, SLAB, and SLUB. Vlastimil and many developers have tried to make it only one single allocator. Deprecation of SLOB has made some progress so far. Vlastimil proposes an LSF/MM/BPF topic for discussing deprecation of SLAB and SLUB futur eimprovement. [GIT PULL] hotfixes for 6.3-rc1 (Andrew Morton) https://lkml.kernel.org/r/20230314165437.a2d992731a970582fe36aaba@linux-foundation.org Yet another mm subsystem hotfixes pull request has sent to Linus Torvalds.

[Invitation] Linux MM Alignment Session on Wednesday (David Rientjes) https://lkml.kernel.org/r/CAE-26VAFJtSu5xEbzNUgPVn3W13-B1bGvvU8-+i-hkS4GtupCw@mail.gmail.com David is hosting biweekly meetings for Linux memory management developments called Linux MM Alignment, and he is publicly inviting people to the meetings. The next instance will be held on 10:00 PST, 2023-03-08, at https://meet.google.com/csb-wcds-xya THP backed thread stacks (Mike Kravetz) https://lkml.kernel.org/r/20230306235730.GA31451@monkey Mike found THP-always’s memory bloat issue due to THP usage for threads’ stacks. Mike feels it might make no sense to use THP for stacks even if the THP policy is ‘always’, and starting discussions on improvment of the situation.

[GIT PULL] MM updates for 6.3-rc1 (Andrew Morton) https://lkml.kernel.org/r/20230220135225.91b0f28344c01d5306c31230@linux-foundation.org The mm updates pull request for v6.3-rc1 has posted by Andrew. [GIT PULL] Compute Express Link (CXL) for 6.3 (Dan Williams) https://lkml.kernel.org/r/63f5a4e2277b1_c94229453@dwillia2-mobl3.amr.corp.intel.com.notmuch A pull request for makincg CXL handling including CXL memory layout parsing/updating and events/errors reporting has posted for v6.3. Without this patchset, currently the works are dependents on platform-firmware. [RFC v2 0/5] tmpfs: add the option to disable swap (Luis Chamberlain) https://lkml.

[PATCH] mm/userfaultfd: Support operation on multiple VMAs (Muhammad Usama Anjum) https://lkml.kernel.org/r/20230213104323.1792839-1-usama.anjum@collabora.com mwriteprotect_range() handle only single VMA, but there are usecases which need to handle multiple VMAs in a memory range of interest. This commit fixes the case. [v2 PATCH 0/5] Introduce mempool pages bulk allocator and use it in dm-crypt (Yang Shi) https://lkml.kernel.org/r/20230214190221.1156876-1-shy828301@gmail.com Noticeable overhead on disc encryption due to page allocations have found. The overhead was because the allocation logic in dm-crypt allocates one page in each pass of a loop.

[LSF/MM/BPF TOPIC] sframe: An orc like stack unwinder for the kernel to get a user space stacktrace (Steven Rostedt) https://lkml.kernel.org/r/20230206103828.6efcb28f@rorschach.local.home Steven Rostedt proposes yet another LSF/MM/BPF topic for using sframe section, which is introduced by binutils, for more efficient user space stack tracing. [PATCH v4 00/14] Introduce Copy-On-Write to Page Table (Chih-En Lin) https://lkml.kernel.org/r/20230207035139.272707-1-shiyn.lin@gmail.com Fourth version of the patchset making copy-on-write be used for page table, while it is currently only used for the mapped memory.