From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andrew Morton Subject: incoming Date: Thu, 28 Jul 2016 15:42:36 -0700 Message-ID: <20160728154236.7e9c6a6a3c6ef5de29904b05@linux-foundation.org> Reply-To: linux-kernel@vger.kernel.org Mime-Version: 1.0 Content-Type: multipart/signed; protocol="application/pgp-signature"; micalg="PGP-SHA1"; boundary="Signature=_Thu__28_Jul_2016_15_42_36_-0700_JaN7X5K82ED1uyWX" Return-path: Received: from mail.linuxfoundation.org ([140.211.169.12]:56519 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750752AbcG1Wmn (ORCPT ); Thu, 28 Jul 2016 18:42:43 -0400 Sender: mm-commits-owner@vger.kernel.org List-Id: mm-commits@vger.kernel.org To: Linus Torvalds Cc: mm-commits@vger.kernel.org --Signature=_Thu__28_Jul_2016_15_42_36_-0700_JaN7X5K82ED1uyWX Content-Type: text/plain; charset=US-ASCII Content-Disposition: inline Content-Transfer-Encoding: quoted-printable - the rest of MM 101 patches, based on 194dc870a5890e855ecffb30f3b80ba7c88f96d6: Subject: proc, oom: drop bogus task_lock and mm check Subject: proc, oom: drop bogus sighand lock Subject: proc, oom_adj: extract oom_score_adj setting into a helper Subject: mm, oom_adj: make sure processes sharing mm have same view of oom_= score_adj Subject: mm, oom: skip vforked tasks from being selected Subject: mm, oom: kill all tasks sharing the mm Subject: mm, oom: fortify task_will_free_mem() Subject: mm, oom: task_will_free_mem should skip oom_reaped tasks Subject: mm, oom_reaper: do not attempt to reap a task more than twice Subject: mm, oom: hide mm which is shared with kthread or global init Subject: mm, oom: tighten task_will_free_mem() locking Subject: mm: update the comment in __isolate_free_page Subject: mm: fix vm-scalability regression in cgroup-aware workingset code Subject: mm/compaction: remove unnecessary order check in try_to_compact_pa= ges() Subject: freezer, oom: check TIF_MEMDIE on the correct task Subject: cpuset, mm: fix TIF_MEMDIE check in cpuset_change_task_nodemask Subject: mm, meminit: remove early_page_nid_uninitialised Subject: mm, vmstat: add infrastructure for per-node vmstats Subject: mm, vmscan: move lru_lock to the node Subject: mm, vmscan: move LRU lists to node Subject: mm, mmzone: clarify the usage of zone padding Subject: mm, vmscan: begin reclaiming pages on a per-node basis Subject: mm, vmscan: have kswapd only scan based on the highest requested z= one Subject: mm, vmscan: make kswapd reclaim in terms of nodes Subject: mm, vmscan: remove balance gap Subject: mm, vmscan: simplify the logic deciding whether kswapd sleeps Subject: mm, vmscan: by default have direct reclaim only shrink once per no= de Subject: mm, vmscan: remove duplicate logic clearing node congestion and di= rty state Subject: mm: vmscan: do not reclaim from kswapd if there is any eligible zo= ne Subject: mm, vmscan: make shrink_node decisions more node-centric Subject: mm, memcg: move memcg limit enforcement from zones to nodes Subject: mm, workingset: make working set detection node-aware Subject: mm, page_alloc: consider dirtyable memory in terms of nodes Subject: mm: move page mapped accounting to the node Subject: mm: rename NR_ANON_PAGES to NR_ANON_MAPPED Subject: mm: move most file-based accounting to the node Subject: mm: move vmscan writes and file write accounting to the node Subject: mm, vmscan: only wakeup kswapd once per node for the requested cla= sszone Subject: mm, page_alloc: wake kswapd based on the highest eligible zone Subject: mm: convert zone_reclaim to node_reclaim Subject: mm, vmscan: avoid passing in classzone_idx unnecessarily to shrink= _node Subject: mm, vmscan: avoid passing in classzone_idx unnecessarily to compac= tion_ready Subject: mm, vmscan: avoid passing in `remaining' unnecessarily to prepare_= kswapd_sleep() Subject: mm, vmscan: Have kswapd reclaim from all zones if reclaiming and b= uffer_heads_over_limit Subject: mm, vmscan: add classzone information to tracepoints Subject: mm, page_alloc: remove fair zone allocation policy Subject: mm: page_alloc: cache the last node whose dirty limit is reached Subject: mm: vmstat: replace __count_zone_vm_events with a zone id equivale= nt Subject: mm: vmstat: account per-zone stalls and pages skipped during recla= im Subject: mm, vmstat: print node-based stats in zoneinfo file Subject: mm, vmstat: remove zone and node double accounting by approximatin= g retries Subject: mm, page_alloc: fix dirtyable highmem calculation Subject: mm, pagevec: release/reacquire lru_lock on pgdat change Subject: mm: show node_pages_scanned per node, not zone Subject: mm, vmscan: Update all zone LRU sizes before updating memcg Subject: mm, vmscan: remove redundant check in shrink_zones() Subject: mm, vmscan: release/reacquire lru_lock on pgdat change Subject: mm: add per-zone lru list stat Subject: mm, vmscan: remove highmem_file_pages Subject: mm: remove reclaim and compaction retry approximations Subject: mm: consider whether to decivate based on eligible zones inactive = ratio Subject: mm, vmscan: account for skipped pages as a partial scan Subject: mm: bail out in shrink_inactive_list() Subject: mm/zsmalloc: use obj_index to keep consistent with others Subject: mm/zsmalloc: take obj index back from find_alloced_obj Subject: mm/zsmalloc: use class->objs_per_zspage to get num of max objects Subject: mm/zsmalloc: avoid calculate max objects of zspage twice Subject: mm/zsmalloc: keep comments consistent with code Subject: mm/zsmalloc: add __init,__exit attribute Subject: mm/zsmalloc: use helper to clear page->flags bit Subject: mm, THP: clean up return value of madvise_free_huge_pmd Subject: memblock: include instead of Subject: mm: CONFIG_ZONE_DEVICE stop depending on CONFIG_EXPERT Subject: mm: cleanup ifdef guards for vmem_altmap Subject: mm: track NR_KERNEL_STACK in KiB instead of number of stacks Subject: mm: fix memcg stack accounting for sub-page stacks Subject: kdb: use task_cpu() instead of task_thread_info()->cpu Subject: printk: when dumping regs, show the stack, not thread_info Subject: mm/memblock.c: add new infrastructure to address the mem limit iss= ue Subject: arm64:acpi: fix the acpi alignment exception when 'mem=3D' specifi= ed Subject: kmemleak: don't hang if user disables scanning early Subject: make __section_nr() more efficient Subject: mm: hwpoison: remove incorrect comments Subject: mm, compaction: don't isolate PageWriteback pages in MIGRATE_SYNC_= LIGHT mode Subject: Revert "mm, mempool: only set __GFP_NOMEMALLOC if there are free e= lements" Subject: mm: add cond_resched() to generic_swapfile_activate() Subject: mm: optimize copy_page_to/from_iter_iovec Subject: mem-hotplug: alloc new page from a nearest neighbor node when mem-= offline Subject: mm/memblock.c: fix index adjustment error in __next_mem_range_rev= () Subject: zsmalloc: Delete an unnecessary check before the function call "ip= ut" Subject: mm: fix use-after-free if memory allocation failed in vma_adjust() Subject: mm, kasan: account for object redzone in SLUB's nearest_obj() Subject: mm, kasan: switch SLUB to stackdepot, enable memory quarantine for= SLUB Subject: lib/stackdepot.c: use __GFP_NOWARN for stack allocations Subject: mm, page_alloc: set alloc_flags only once in slowpath Subject: mm, page_alloc: don't retry initial attempt in slowpath Subject: mm, page_alloc: restructure direct compaction handling in slowpath Subject: mm, page_alloc: make THP-specific decisions more generic Subject: mm, thp: remove __GFP_NORETRY from khugepaged and madvised allocat= ions Subject: mm, compaction: introduce direct compaction priority Subject: mm, compaction: simplify contended compaction handling --Signature=_Thu__28_Jul_2016_15_42_36_-0700_JaN7X5K82ED1uyWX Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (GNU/Linux) iQIcBAEBAgAGBQJXmopiAAoJEJxZ78cCqAIHtXsQAIPhmGFZtIDYAkgox5DovB1O 8jYJQ7j7pI1kAV1qN1UdOxChebjpPDpZkql2HUmeIsaej+fU4odxxJXppFULrfdJ PayCTKLw99U/LqqdQmRZysOvFef5rDkOVyRQUIebPZT7F59PZZvYEiUZHOCyQbNV MxOQtOZTV5kpfIsGb/zW5I0Xnj0H0McfLyts/xSAwwnlyR3oMrR9RgD4510Qt/s6 k0J1II99Eamv9+3aQ669pQzx9DnOBLBh8K4TIM2T0i9HrybN2kcJqXkaWsVnGZ5B 4xXD4Y1KSkTEIYU9VTAgiDkIstQ99sDbMdlTOi2RacL8Z5ArFliqNwxJuckK9fI6 SI5XgyAxu+scN8fXB7mrGKcdnlOtcV3S6FYvH/LwkglLM3Wz4X0SibnpPGVlVON6 1Kgky5cUAtR8S0R1GGeLKOknhVpl427asocODPf+4ThAUzPGOQrYYnaodNCak4Cv fq72YIhzQxNMaGIjn6TjpkTJ0nnHgkClxHoYcfHMS/irlvtiTqEJocZwn962VVMs /Qoh7vCXp2rOvHmiUeBu43HTEih4tzew8LdKgiKYkOcGvoJndvbLT64xKzByHr4S CaN6lUgX54x2A4mOgHIjuB//swkTOAYuRjhmJux9s0DJdymdpCl9H8X7/2/KpBjl HXJXLPJwh9/L9e21yU4c =BKIf -----END PGP SIGNATURE----- --Signature=_Thu__28_Jul_2016_15_42_36_-0700_JaN7X5K82ED1uyWX--