[PATCH v3 00/11] Introduce cmpxchg128() – aka. the demise of cmpxchg_double() (Peter Zijlstra) https://lkml.kernel.org/r/20230515075659.118447996@infradead.org
This patchset introduces an alternative for cmpxchg_double(), namely cmpxchg128(), and replace the old usages of cmpxchg_double(). This is because Linus hates cmpxchg_double()[1].
[1] https://lore.kernel.org/all/Y2U3WdU61FvYlpUh@hirez.programming.kicks-ass.net/T/#u
[PATCH 0/6] Memory Mapping (VMA) protection using PKU - set 1 (Jeff Xu) https://lkml.kernel.org/r/20230515130553.2311248-1-jeffxu@chromium.org
[Invitation] Linux MM Alignment Session on Code Tagging on Wednesday (David Rientjes) https://lkml.kernel.org/r/CAE-26VDomF_pZybGjgCBJZuWusX0z3MTEJmkwtuQXx3PyrN6fw@mail.gmail.com
Google is hosting Linux MM alignment session.
[PATCH 0/2] Optimization of CMA allocation and reclaiming (Zhaoyang Huang) https://lkml.kernel.org/r/1683538383-19685-1-git-send-email-zhaoyang.huang@unisoc.com
This patchset avoids being OOMed when all free pages are composed of CMA.
[RFC PATCH 0/2] mm: Working Set Reporting (Yuanchu Xie) https://lkml.kernel.org/r/20230509185419.1088297-1-yuanchu@google.com
This RFC patch adds working set size reporting structure for each node and total, using MGLRU as its core, and extends virtio-balloon for letting the host get the information.
[PATCH] MAINTAINERS: repair pattern in DIALOG SEMICONDUCTOR DRIVERS (Lukas Bulwahn) https://lkml.
[PATCH v2 0/2] Reduce lock contention related with large folio (Yin Fengwei) https://lkml.kernel.org/r/20230425084627.3573866-1-fengwei.yin@intel.com
Ryan found large anonymous folios exposes some lock contention unlike large page cache folios, because anonymous mapping is allocated/freed more frequently. This patchset mitigates the lock contention by avoid acquiring queue lock unnecessarily, and allowing batched large folio list adds to lru list.
[PATCH v2 0/3] fs: multigrain timestamps (Jeff Layton) https://lkml.kernel.org/r/20230424151104.175456-1-jlayton@kernel.org
This patchset makes file system to support not single-gran timestamp but multi-gran timestamps.
[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.