- 28 Dec, 2018 40 commits
-
-
Aaron Lu authored
page_frag_free() calls __free_pages_ok() to free the page back to Buddy. This is OK for high order page, but for order-0 pages, it misses the optimization opportunity of using Per-Cpu-Pages and can cause zone lock contention when called frequently. Pawel Staszewski recently shared his result of 'how Linux kernel handles normal traffic'[1] and from perf data, Jesper Dangaard Brouer found the lock contention comes from page allocator: mlx5e_poll_tx_cq | --16.34%--napi_consume_skb | |--12.65%--__free_pages_ok | | | --11.86%--free_one_page | | | |--10.10%--queued_spin_lock_slowpath | | | --0.65%--_raw_spin_lock | |--1.55%--page_frag_free | --1.44%--skb_release_data Jesper explained how it happened: mlx5 driver RX-page recycle mechanism is not effective in this workload and pages have to go through the page allocator. The lock contention happens during mlx5 DMA TX completion cycle. And the page allocator cannot keep up at these speeds.[2] I thought that __free_pages_ok() are mostly freeing high order pages and thought this is an lock contention for high order pages but Jesper explained in detail that __free_pages_ok() here are actually freeing order-0 pages because mlx5 is using order-0 pages to satisfy its page pool allocation request.[3] The free path as pointed out by Jesper is: skb_free_head() -> skb_free_frag() -> page_frag_free() And the pages being freed on this path are order-0 pages. Fix this by doing similar things as in __page_frag_cache_drain() - send the being freed page to PCP if it's an order-0 page, or directly to Buddy if it is a high order page. With this change, Paweł hasn't noticed lock contention yet in his workload and Jesper has noticed a 7% performance improvement using a micro benchmark and lock contention is gone. Ilias' test on a 'low' speed 1Gbit interface on an cortex-a53 shows ~11% performance boost testing with 64byte packets and __free_pages_ok() disappeared from perf top. [1]: https://www.spinics.net/lists/netdev/msg531362.html [2]: https://www.spinics.net/lists/netdev/msg531421.html [3]: https://www.spinics.net/lists/netdev/msg531556.html [akpm@linux-foundation.org: add comment] Link: http://lkml.kernel.org/r/20181120014544.GB10657@intel.comSigned-off-by:Aaron Lu <aaron.lu@intel.com> Reported-by:
Pawel Staszewski <pstaszewski@itcare.pl> Analysed-by:
Jesper Dangaard Brouer <brouer@redhat.com> Acked-by:
Vlastimil Babka <vbabka@suse.cz> Acked-by:
Mel Gorman <mgorman@techsingularity.net> Acked-by:
Ilias Apalodimas <ilias.apalodimas@linaro.org> Tested-by:
Alexander Duyck <alexander.h.duyck@linux.intel.com> Acked-by:
Tariq Toukan <tariqt@mellanox.com> Acked-by:
Pankaj gupta <pagupta@redhat.com> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Dan Williams authored
At Maintainer Summit, Greg brought up a topic I proposed around EXPORT_SYMBOL_GPL usage. The motivation was considerations for when EXPORT_SYMBOL_GPL is warranted and the criteria for taking the exceptional step of reclassifying an existing export. Specifically, I wanted to make the case that although the line is fuzzy and hard to specify in abstract terms, it is nonetheless clear that devm_memremap_pages() and HMM (Heterogeneous Memory Management) have crossed it. The devm_memremap_pages() facility should have been EXPORT_SYMBOL_GPL from the beginning, and HMM as a derivative of that functionality should have naturally picked up that designation as well. Contrary to typical rules, the HMM infrastructure was merged upstream with zero in-tree consumers. There was a promise at the time that those users would be merged "soon", but it has been over a year with no drivers arriving. While the Nouveau driver is about to belatedly make good on that promise it is clear that HMM was targeted first and foremost at an out-of-tree consumer. HMM is derived from devm_memremap_pages(), a facility Christoph and I spearheaded to support persistent memory. It combines a device lifetime model with a dynamically created 'struct page' / memmap array for any physical address range. It enables coordination and control of the many code paths in the kernel built to interact with memory via 'struct page' objects. With HMM the integration goes even deeper by allowing device drivers to hook and manipulate page fault and page free events. One interpretation of when EXPORT_SYMBOL is suitable is when it is exporting stable and generic leaf functionality. The devm_memremap_pages() facility continues to see expanding use cases, peer-to-peer DMA being the most recent, with no clear end date when it will stop attracting reworks and semantic changes. It is not suitable to export devm_memremap_pages() as a stable 3rd party driver API due to the fact that it is still changing and manipulates core behavior. Moreover, it is not in the best interest of the long term development of the core memory management subsystem to permit any external driver to effectively define its own system-wide memory management policies with no encouragement to engage with upstream. I am also concerned that HMM was designed in a way to minimize further engagement with the core-MM. That, with these hooks in place, device-drivers are free to implement their own policies without much consideration for whether and how the core-MM could grow to meet that need. Going forward not only should HMM be EXPORT_SYMBOL_GPL, but the core-MM should be allowed the opportunity and stimulus to change and address these new use cases as first class functionality. Original changelog: hmm_devmem_add(), and hmm_devmem_add_resource() duplicated devm_memremap_pages() and are now simple now wrappers around the core facility to inject a dev_pagemap instance into the global pgmap_radix and hook page-idle events. The devm_memremap_pages() interface is base infrastructure for HMM. HMM has more and deeper ties into the kernel memory management implementation than base ZONE_DEVICE which is itself a EXPORT_SYMBOL_GPL facility. Originally, the HMM page structure creation routines copied the devm_memremap_pages() code and reused ZONE_DEVICE. A cleanup to unify the implementations was discussed during the initial review: http://lkml.iu.edu/hypermail/linux/kernel/1701.2/00812.html Recent work to extend devm_memremap_pages() for the peer-to-peer-DMA facility enabled this cleanup to move forward. In addition to the integration with devm_memremap_pages() HMM depends on other GPL-only symbols: mmu_notifier_unregister_no_release percpu_ref region_intersects __class_create It goes further to consume / indirectly expose functionality that is not exported to any other driver: alloc_pages_vma walk_page_range HMM is derived from devm_memremap_pages(), and extends deep core-kernel fundamentals. Similar to devm_memremap_pages(), mark its entry points EXPORT_SYMBOL_GPL(). [logang@deltatee.com: PCI/P2PDMA: match interface changes to devm_memremap_pages()] Link: http://lkml.kernel.org/r/20181130225911.2900-1-logang@deltatee.com Link: http://lkml.kernel.org/r/154275560565.76910.15919297436557795278.stgit@dwillia2-desk3.amr.corp.intel.comSigned-off-by:
Dan Williams <dan.j.williams@intel.com> Signed-off-by:
Logan Gunthorpe <logang@deltatee.com> Reviewed-by:
Christoph Hellwig <hch@lst.de> Cc: Logan Gunthorpe <logang@deltatee.com> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Balbir Singh <bsingharora@gmail.com>, Cc: Michal Hocko <mhocko@suse.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: <stable@vger.kernel.org> Signed-off-by:
-
Dan Williams authored
Commit e8d51348 ("memremap: change devm_memremap_pages interface to use struct dev_pagemap") refactored devm_memremap_pages() to allow a dev_pagemap instance to be supplied. Passing in a dev_pagemap interface simplifies the design of pgmap type drivers in that they can rely on container_of() to lookup any private data associated with the given dev_pagemap instance. In addition to the cleanups this also gives hmm users multi-order-radix improvements that arrived with commit ab1b597e "mm, devm_memremap_pages: use multi-order radix for ZONE_DEVICE lookups" As part of the conversion to the devm_memremap_pages() method of handling the percpu_ref relative to when pages are put, the percpu_ref completion needs to move to hmm_devmem_ref_exit(). See 71389703 ("mm, zone_device: Replace {get, put}_zone_device_page...") for details. Link: http://lkml.kernel.org/r/154275560053.76910.10870962637383152392.stgit@dwillia2-desk3.amr.corp.intel.comSigned-off-by:
Jérôme Glisse <jglisse@redhat.com> Acked-by:
Balbir Singh <bsingharora@gmail.com> Cc: Logan Gunthorpe <logang@deltatee.com> Cc: Michal Hocko <mhocko@suse.com> Cc: <stable@vger.kernel.org> Signed-off-by:
-
Dan Williams authored
devm semantics arrange for resources to be torn down when device-driver-probe fails or when device-driver-release completes. Similar to devm_memremap_pages() there is no need to support an explicit remove operation when the users properly adhere to devm semantics. Note that devm_kzalloc() automatically handles allocating node-local memory. Link: http://lkml.kernel.org/r/154275559545.76910.9186690723515469051.stgit@dwillia2-desk3.amr.corp.intel.comSigned-off-by:
-
Dan Williams authored
In preparation for consolidating all ZONE_DEVICE enabling via devm_memremap_pages(), teach it how to handle the constraints of MEMORY_DEVICE_PRIVATE ranges. [jglisse@redhat.com: call move_pfn_range_to_zone for MEMORY_DEVICE_PRIVATE] Link: http://lkml.kernel.org/r/154275559036.76910.12434636179931292607.stgit@dwillia2-desk3.amr.corp.intel.comSigned-off-by:
-
Dan Williams authored
The last step before devm_memremap_pages() returns success is to allocate a release action, devm_memremap_pages_release(), to tear the entire setup down. However, the result from devm_add_action() is not checked. Checking the error from devm_add_action() is not enough. The api currently relies on the fact that the percpu_ref it is using is killed by the time the devm_memremap_pages_release() is run. Rather than continue this awkward situation, offload the responsibility of killing the percpu_ref to devm_memremap_pages_release() directly. This allows devm_memremap_pages() to do the right thing relative to init failures and shutdown. Without this change we could fail to register the teardown of devm_memremap_pages(). The likelihood of hitting this failure is tiny as small memory allocations almost always succeed. However, the impact of the failure is large given any future reconfiguration, or disable/enable, of an nvdimm namespace will fail forever as subsequent calls to devm_memremap_pages() will fail to setup the pgmap_radix since there will be stale entries for the physical address range. An argument could be made to require that the ->kill() operation be set in the @pgmap arg rather than passed in separately. However, it helps code readability, tracking the lifetime of a given instance, to be able to grep the kill routine directly at the devm_memremap_pages() call site. Link: http://lkml.kernel.org/r/154275558526.76910.7535251937849268605.stgit@dwillia2-desk3.amr.corp.intel.comSigned-off-by:
-
Dan Williams authored
Given the fact that devm_memremap_pages() requires a percpu_ref that is torn down by devm_memremap_pages_release() the current support for mapping RAM is broken. Support for remapping "System RAM" has been broken since the beginning and there is no existing user of this this code path, so just kill the support and make it an explicit error. This cleanup also simplifies a follow-on patch to fix the error path when setting a devm release action for devm_memremap_pages_release() fails. Link: http://lkml.kernel.org/r/154275557997.76910.14689813630968180480.stgit@dwillia2-desk3.amr.corp.intel.comSigned-off-by:
-
Dan Williams authored
devm_memremap_pages() is a facility that can create struct page entries for any arbitrary range and give drivers the ability to subvert core aspects of page management. Specifically the facility is tightly integrated with the kernel's memory hotplug functionality. It injects an altmap argument deep into the architecture specific vmemmap implementation to allow allocating from specific reserved pages, and it has Linux specific assumptions about page structure reference counting relative to get_user_pages() and get_user_pages_fast(). It was an oversight and a mistake that this was not marked EXPORT_SYMBOL_GPL from the outset. Again, devm_memremap_pagex() exposes and relies upon core kernel internal assumptions and will continue to evolve along with 'struct page', memory hotplug, and support for new memory types / topologies. Only an in-kernel GPL-only driver is expected to keep up with this ongoing evolution. This interface, and functionality derived from this interface, is not suitable for kernel-external drivers. Link: http://lkml.kernel.org/r/154275557457.76910.16923571232582744134.stgit@dwillia2-desk3.amr.corp.intel.comSigned-off-by:
Michal Hocko <mhocko@suse.com> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Logan Gunthorpe <logang@deltatee.com> Cc: <stable@vger.kernel.org> Signed-off-by:
-
Huang Shijie authored
In the enum migratetype definition, MIGRATE_MOVABLE is before MIGRATE_RECLAIMABLE. Change the order of them to match the enumeration's order. Link: http://lkml.kernel.org/r/20181121085821.3442-1-sjhuang@iluvatar.aiSigned-off-by:
Huang Shijie <sjhuang@iluvatar.ai> Reviewed-by:
-
Eric Biggers authored
Reference counters should use refcount_t rather than atomic_t, since the refcount_t implementation can prevent overflows, reducing the exploitability of reference leak bugs. userfaultfd_ctx::refcount is a reference counter with the usual semantics, so convert it to refcount_t. Note: I replaced the BUG() on incrementing a 0 refcount with just refcount_inc(), since part of the semantics of refcount_t is that that incrementing a 0 refcount is not allowed; with CONFIG_REFCOUNT_FULL, refcount_inc() already checks for it and warns. Link: http://lkml.kernel.org/r/20181115003916.63381-1-ebiggers@kernel.orgSigned-off-by:
Eric Biggers <ebiggers@google.com> Reviewed-by:
Mike Rapoport <rppt@linux.ibm.com> Signed-off-by:
-
Aaron Lu authored
Since a2468cc9 ("swap: choose swap device according to numa node"), avail_lists field of swap_info_struct is changed to an array with MAX_NUMNODES elements. This made swap_info_struct size increased to 40KiB and needs an order-4 page to hold it. This is not optimal in that: 1 Most systems have way less than MAX_NUMNODES(1024) nodes so it is a waste of memory; 2 It could cause swapon failure if the swap device is swapped on after system has been running for a while, due to no order-4 page is available as pointed out by Vasily Averin. Solve the above two issues by using nr_node_ids(which is the actual possible node number the running system has) for avail_lists instead of MAX_NUMNODES. nr_node_ids is unknown at compile time so can't be directly used when declaring this array. What I did here is to declare avail_lists as zero element array and allocate space for it when allocating space for swap_info_struct. The reason why keep using array but not pointer is plist_for_each_entry needs the field to be part of the struct, so pointer will not work. This patch is on top of Vasily Averin's fix commit. I think the use of kvzalloc for swap_info_struct is still needed in case nr_node_ids is really big on some systems. Link: http://lkml.kernel.org/r/20181115083847.GA11129@intel.comSigned-off-by:
-
Wei Yang authored
Commit fa5e084e ("vmscan: do not unconditionally treat zones that fail zone_reclaim() as full") changed the return value of node_reclaim(). The original return value 0 means NODE_RECLAIM_SOME after this commit. While the return value of node_reclaim() when CONFIG_NUMA is n is not changed. This will leads to call zone_watermark_ok() again. This patch fixes the return value by adjusting to NODE_RECLAIM_NOSCAN. Since node_reclaim() is only called in page_alloc.c, move it to mm/internal.h. Link: http://lkml.kernel.org/r/20181113080436.22078-1-richard.weiyang@gmail.comSigned-off-by:
Wei Yang <richard.weiyang@gmail.com> Acked-by:
Matthew Wilcox <willy@infradead.org> Cc: Mel Gorman <mgorman@techsingularity.net> Signed-off-by:
-
Arun KS authored
Now that totalram_pages and managed_pages are atomic varibles, no need of managed_page_count spinlock. The lock had really a weak consistency guarantee. It hasn't been used for anything but the update but no reader actually cares about all the values being updated to be in sync. Link: http://lkml.kernel.org/r/1542090790-21750-5-git-send-email-arunks@codeaurora.orgSigned-off-by:
Arun KS <arunks@codeaurora.org> Reviewed-by:
Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Acked-by:
Pavel Tatashin <pasha.tatashin@soleen.com> Signed-off-by:
-
Arun KS authored
totalram_pages and totalhigh_pages are made static inline function. Main motivation was that managed_page_count_lock handling was complicating things. It was discussed in length here, https://lore.kernel.org/patchwork/patch/995739/#1181785 So it seemes better to remove the lock and convert variables to atomic, with preventing poteintial store-to-read tearing as a bonus. [akpm@linux-foundation.org: coding style fixes] Link: http://lkml.kernel.org/r/1542090790-21750-4-git-send-email-arunks@codeaurora.orgSigned-off-by:
-
Arun KS authored
totalram_pages, zone->managed_pages and totalhigh_pages updates are protected by managed_page_count_lock, but readers never care about it. Convert these variables to atomic to avoid readers potentially seeing a store tear. This patch converts zone->managed_pages. Subsequent patches will convert totalram_panges, totalhigh_pages and eventually managed_page_count_lock will be removed. Main motivation was that managed_page_count_lock handling was complicating things. It was discussed in length here, https://lore.kernel.org/patchwork/patch/995739/#1181785 So it seemes better to remove the lock and convert variables to atomic, with preventing poteintial store-to-read tearing as a bonus. Link: http://lkml.kernel.org/r/1542090790-21750-3-git-send-email-arunks@codeaurora.orgSigned-off-by:
David Hildenbrand <david@redhat.com> Acked-by:
-
Arun KS authored
Patch series "mm: convert totalram_pages, totalhigh_pages and managed pages to atomic", v5. This series converts totalram_pages, totalhigh_pages and zone->managed_pages to atomic variables. totalram_pages, zone->managed_pages and totalhigh_pages updates are protected by managed_page_count_lock, but readers never care about it. Convert these variables to atomic to avoid readers potentially seeing a store tear. Main motivation was that managed_page_count_lock handling was complicating things. It was discussed in length here, https://lore.kernel.org/patchwork/patch/995739/#1181785 It seemes better to remove the lock and convert variables to atomic. With the change, preventing poteintial store-to-read tearing comes as a bonus. This patch (of 4): This is in preparation to a later patch which converts totalram_pages and zone->managed_pages to atomic variables. Please note that re-reading the value might lead to a different value and as such it could lead to unexpected behavior. There are no known bugs as a result of the current code but it is better to prevent from them in principle. Link: http://lkml.kernel.org/r/1542090790-21750-2-git-send-email-arunks@codeaurora.orgSigned-off-by:
-
Wei Yang authored
per_cpu_pageset is cleared by memset, it is not necessary to reset it again. Link: http://lkml.kernel.org/r/20181021023920.5501-1-richard.weiyang@gmail.comSigned-off-by:
-
Michal Hocko authored
Per-cpu numa_node provides a default node for each possible cpu. The association gets initialized during the boot when the architecture specific code explores cpu->NUMA affinity. When the whole NUMA node is removed though we are clearing this association try_offline_node check_and_unmap_cpu_on_node unmap_cpu_on_node numa_clear_node numa_set_node(cpu, NUMA_NO_NODE) This means that whoever calls cpu_to_node for a cpu associated with such a node will get NUMA_NO_NODE. This is problematic for two reasons. First it is fragile because __alloc_pages_node would simply blow up on an out-of-bound access. We have encountered this when loading kvm module BUG: unable to handle kernel paging request at 00000000000021c0 IP: __alloc_pages_nodemask+0x93/0xb70 PGD 800000ffe853e067 PUD 7336bbc067 PMD 0 Oops: 0000 [#1] SMP [...] CPU: 88 PID: 1223749 Comm: modprobe Tainted: G W 4.4.156-94.64-default #1 RIP: __alloc_pages_nodemask+0x93/0xb70 RSP: 0018:ffff887354493b40 EFLAGS: 00010202 RAX: 00000000000021c0 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000002 RDI: 00000000014000c0 RBP: 00000000014000c0 R08: ffffffffffffffff R09: 0000000000000000 R10: ffff88fffc89e790 R11: 0000000000014000 R12: 0000000000000101 R13: ffffffffa0772cd4 R14: ffffffffa0769ac0 R15: 0000000000000000 FS: 00007fdf2f2f1700(0000) GS:ffff88fffc880000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000021c0 CR3: 00000077205ee000 CR4: 0000000000360670 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: alloc_vmcs_cpu+0x3d/0x90 [kvm_intel] hardware_setup+0x781/0x849 [kvm_intel] kvm_arch_hardware_setup+0x28/0x190 [kvm] kvm_init+0x7c/0x2d0 [kvm] vmx_init+0x1e/0x32c [kvm_intel] do_one_initcall+0xca/0x1f0 do_init_module+0x5a/0x1d7 load_module+0x1393/0x1c90 SYSC_finit_module+0x70/0xa0 entry_SYSCALL_64_fastpath+0x1e/0xb7 DWARF2 unwinder stuck at entry_SYSCALL_64_fastpath+0x1e/0xb7 on an older kernel but the code is basically the same in the current Linus tree as well. alloc_vmcs_cpu could use alloc_pages_nodemask which would recognize NUMA_NO_NODE and use alloc_pages_node which would translate it to numa_mem_id but that is wrong as well because it would use a cpu affinity of the local CPU which might be quite far from the original node. It is also reasonable to expect that cpu_to_node will provide a sane value and there might be many more callers like that. The second problem is that __register_one_node relies on cpu_to_node to properly associate cpus back to the node when it is onlined. We do not want to lose that link as there is no arch independent way to get it from the early boot time AFAICS. Drop the whole check_and_unmap_cpu_on_node machinery and keep the association to fix both issues. The NODE_DATA(nid) is not deallocated so it will stay in place and if anybody wants to allocate from that node then a fallback node will be used. Thanks to Vlastimil Babka for his live system debugging skills that helped debugging the issue. Link: http://lkml.kernel.org/r/20181108100413.966-1-mhocko@kernel.org Fixes: e13fe869 ("cpu-hotplug,memory-hotplug: clear cpu_to_node() when offlining the node") Signed-off-by:Miroslav Benes <mbenes@suse.cz> Acked-by:
Anshuman Khandual <anshuman.khandual@arm.com> Signed-off-by:
-
Yangtao Li authored
We should get rid of this function. It no longer serves its purpose. This is a historical artifact from 2005 where do_brk was called outside of the core mm. We do have a proper abstraction in vm_brk_flags and that one does the locking properly so there is no need to use this function. Link: http://lkml.kernel.org/r/20181108174856.10811-1-tiny.windzz@gmail.comSigned-off-by:
Yangtao Li <tiny.windzz@gmail.com> Acked-by:
David Rientjes <rientjes@google.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dominik Brodowski <linux@dominikbrodowski.net> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Woodhouse <dwmw2@infradead.org> Signed-off-by:
-
Timofey Titovets authored
Replace jhash2 with xxhash. Perf numbers: Intel(R) Xeon(R) CPU E5-2420 v2 @ 2.20GHz ksm: crc32c hash() 12081 MB/s ksm: xxh64 hash() 8770 MB/s ksm: xxh32 hash() 4529 MB/s ksm: jhash2 hash() 1569 MB/s Sioh Lee did some testing: crc32c_intel: 1084.10ns crc32c (no hardware acceleration): 7012.51ns xxhash32: 2227.75ns xxhash64: 1413.16ns jhash2: 5128.30ns As jhash2 always will be slower (for data size like PAGE_SIZE). Don't use it in ksm at all. Use only xxhash for now, because for using crc32c, cryptoapi must be initialized first - that requires some tricky solution to work well in all situations. Link: http://lkml.kernel.org/r/20181023182554.23464-3-nefelim4ag@gmail.comSigned-off-by:
Timofey Titovets <nefelim4ag@gmail.com> Signed-off-by:
leesioh <solee@os.korea.ac.kr> Reviewed-by:
Pavel Tatashin <pavel.tatashin@microsoft.com> Reviewed-by:
Mike Rapoport <rppt@linux.vnet.ibm.com> Reviewed-by:
-
Timofey Titovets authored
Patch series "Currently used jhash are slow enough and replace it allow as to make KSM", v8. Apeed (in kernel): ksm: crc32c hash() 12081 MB/s ksm: xxh64 hash() 8770 MB/s ksm: xxh32 hash() 4529 MB/s ksm: jhash2 hash() 1569 MB/s Sioh Lee's testing (copy from other mail): Test platform: openstack cloud platform (NEWTON version) Experiment node: openstack based cloud compute node (CPU: xeon E5-2620 v3, memory 64gb) VM: (2 VCPU, RAM 4GB, DISK 20GB) * 4 Linux kernel: 4.14 (latest version) KSM setup - sleep_millisecs: 200ms, pages_to_scan: 200 Experiment process: Firstly, we turn off KSM and launch 4 VMs. Then we turn on the KSM and measure the checksum computation time until full_scans become two. The experimental results (the experimental value is the average of the measured values) crc32c_intel: 1084.10ns crc32c (no hardware acceleration): 7012.51ns xxhash32: 2227.75ns xxhash64: 1413.16ns jhash2: 5128.30ns In summary, the result shows that crc32c_intel has advantages over all of the hash function used in the experiment. (decreased by 84.54% compared to crc32c, 78.86% compared to jhash2, 51.33% xxhash32, 23.28% compared to xxhash64) the results are similar to those of Timofey. But, use only xxhash for now, because for using crc32c, cryptoapi must be initialized first - that require some tricky solution to work good in all situations. So: - First patch implement compile time pickup of fastest implementation of xxhash for target platform. - The second patch replaces jhash2 with xxhash This patch (of 2): xxh32() - fast on both 32/64-bit platforms xxh64() - fast only on 64-bit platform Create xxhash() which will pick up the fastest version at compile time. Link: http://lkml.kernel.org/r/20181023182554.23464-2-nefelim4ag@gmail.comSigned-off-by: -
Michal Hocko authored
Heiko has complained that his log is swamped by warnings from has_unmovable_pages [ 20.536664] page dumped because: has_unmovable_pages [ 20.536792] page:000003d081ff4080 count:1 mapcount:0 mapping:000000008ff88600 index:0x0 compound_mapcount: 0 [ 20.536794] flags: 0x3fffe0000010200(slab|head) [ 20.536795] raw: 03fffe0000010200 0000000000000100 0000000000000200 000000008ff88600 [ 20.536796] raw: 0000000000000000 0020004100000000 ffffffff00000001 0000000000000000 [ 20.536797] page dumped because: has_unmovable_pages [ 20.536814] page:000003d0823b0000 count:1 mapcount:0 mapping:0000000000000000 index:0x0 [ 20.536815] flags: 0x7fffe0000000000() [ 20.536817] raw: 07fffe0000000000 0000000000000100 0000000000000200 0000000000000000 [ 20.536818] raw: 0000000000000000 0000000000000000 ffffffff00000001 0000000000000000 which are not triggered by the memory hotplug but rather CMA allocator. The original idea behind dumping the page state for all call paths was that these messages will be helpful debugging failures. From the above it seems that this is not the case for the CMA path because we are lacking much more context. E.g the second reported page might be a CMA allocated page. It is still interesting to see a slab page in the CMA area but it is hard to tell whether this is bug from the above output alone. Address this issue by dumping the page state only on request. Both start_isolate_page_range and has_unmovable_pages already have an argument to ignore hwpoison pages so make this argument more generic and turn it into flags and allow callers to combine non-default modes into a mask. While we are at it, has_unmovable_pages call from is_pageblock_removable_nolock (sysfs removable file) is questionable to report the failure so drop it from there as well. Link: http://lkml.kernel.org/r/20181218092802.31429-1-mhocko@kernel.orgSigned-off-by:
Heiko Carstens <heiko.carstens@de.ibm.com> Reviewed-by:
Oscar Salvador <osalvador@suse.de> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by:
-
Michal Hocko authored
There is only very limited information printed when the memory offlining fails: [ 1984.506184] rac1 kernel: memory offlining [mem 0x82600000000-0x8267fffffff] failed due to signal backoff This tells us that the failure is triggered by the userspace intervention but it doesn't tell us much more about the underlying reason. It might be that the page migration failes repeatedly and the userspace timeout expires and send a signal or it might be some of the earlier steps (isolation, memory notifier) takes too long. If the migration failes then it would be really helpful to see which page that and its state. The same applies to the isolation phase. If we fail to isolate a page from the allocator then knowing the state of the page would be helpful as well. Dump the page state that fails to get isolated or migrated. This will tell us more about the failure and what to focus on during debugging. [akpm@linux-foundation.org: add missing printk arg] [mhocko@suse.com: tweak dump_page() `reason' text] Link: http://lkml.kernel.org/r/20181116083020.20260-6-mhocko@kernel.org Link: http://lkml.kernel.org/r/20181107101830.17405-6-mhocko@kernel.orgSigned-off-by:
-
Michal Hocko authored
The memory offlining failure reporting is inconsistent and insufficient. Some error paths simply do not report the failure to the log at all. When we do report there are no details about the reason of the failure and there are several of them which makes memory offlining failures hard to debug. Make sure that the memory offlining [mem %#010llx-%#010llx] failed message is printed for all failures and also provide a short textual reason for the failure e.g. [ 1984.506184] rac1 kernel: memory offlining [mem 0x82600000000-0x8267fffffff] failed due to signal backoff this tells us that the offlining has failed because of a signal pending aka user intervention. [akpm@linux-foundation.org: tweak messages a bit] Link: http://lkml.kernel.org/r/20181107101830.17405-5-mhocko@kernel.orgSigned-off-by:
-
Michal Hocko authored
This function is never called from a context which would provide misaligned pfn range so drop the pointless check. Link: http://lkml.kernel.org/r/20181107101830.17405-4-mhocko@kernel.orgSigned-off-by:
-
Michal Hocko authored
__dump_page messages use KERN_EMERG resp. KERN_ALERT loglevel (this is the case since 2004). Most callers of this function are really detecting a critical page state and BUG right after. On the other hand the function is called also from contexts which just want to inform about the page state and those would rather not disrupt logs that much (e.g. some systems route these messages to the normal console). Reduce the loglevel to KERN_WARNING to make dump_page easier to reuse for other contexts while those messages will still make it to the kernel log in most setups. Even if the loglevel setup filters warnings away those paths that are really critical already print the more targeted error or panic and that should make it to the kernel log. [mhocko@kernel.org: fix __dump_page()] Link: http://lkml.kernel.org/r/20181212142540.GA7378@dhcp22.suse.cz [akpm@linux-foundation.org: s/KERN_WARN/KERN_WARNING/, per Michal] Link: http://lkml.kernel.org/r/20181107101830.17405-3-mhocko@kernel.orgSigned-off-by:
-
Michal Hocko authored
I have been promissing to improve memory offlining failures debugging for quite some time. As things stand now we get only very limited information in the kernel log when the offlining fails. It is usually only [ 1984.506184] rac1 kernel: memory offlining [mem 0x82600000000-0x8267fffffff] failed with no further details. We do not know what exactly fails and for what reason. Whenever I was forced to debug such a failure I've always had to do a debugging patch to tell me more. We can enable some tracepoints but it would be much better to get a better picture without using them. This patch series does 2 things. The first one is to make dump_page more usable by printing more information about the mapping patch 1. Then it reduces the log level from emerg to warning so that this function is usable from less critical context patch 2. Then I have added more detailed information about the offlining failure patch 4 and finally add dump_page to isolation and offlining migration paths. Patch 3 is a trivial cleanup. This patch (of 6): __dump_page prints the mapping pointer but that is quite unhelpful for many reports because the pointer itself only helps to distinguish anon/ksm mappings from other ones (because of lowest bits set). Sometimes it would be much more helpful to know what kind of mapping that is actually and if we know this is a file mapping then also try to resolve the dentry name. [dan.carpenter@oracle.com: fix a width vs precision bug in printk] Link: http://lkml.kernel.org/r/20181123072135.gqvblm2vdujbvfjs@kili.mountain [mhocko@kernel.org: use %dp to print dentry] Link: http://lkml.kernel.org/r/20181125080834.GB12455@dhcp22.suse.cz Link: http://lkml.kernel.org/r/20181107101830.17405-2-mhocko@kernel.orgSigned-off-by:
William Kucharski <william.kucharski@oracle.com> Cc: Oscar Salvador <OSalvador@suse.com> Cc: Baoquan He <bhe@redhat.com> Cc: Oscar Salvador <osalvador@suse.de> Signed-off-by:
-
Gao Xiang authored
It's a trivial simplification for get_next_ra_size() and clear enough for humans to understand. It also fixes potential overflow if ra->size(< ra_pages) is too large. Link: http://lkml.kernel.org/r/1540707206-19649-1-git-send-email-hsiangkao@aol.comSigned-off-by:
Gao Xiang <hsiangkao@aol.com> Reviewed-by:
Fengguang Wu <fengguang.wu@intel.com> Reviewed-by:
-
Anders Roxell authored
This happened while running in qemu-system-aarch64, the AMBA PL011 UART driver when enabling CONFIG_DEBUG_TEST_DRIVER_REMOVE. arch_initcall(pl011_init) came before subsys_initcall(default_bdi_init), devtmpfs' handle_remove() crashes because the reference count is a NULL pointer only because wb->bdi hasn't been initialized yet. Rework so that wb_put have an extra check if wb->bdi before decrement wb->refcnt and also add a WARN_ON_ONCE to get a warning if it happens again in other drivers. Link: http://lkml.kernel.org/r/20181030113545.30999-2-anders.roxell@linaro.org Fixes: 52ebea74 ("writeback: make backing_dev_info host cgroup-specific bdi_writebacks") Signed-off-by:
Arnd Bergmann <arnd@arndb.de> Signed-off-by:
Anders Roxell <anders.roxell@linaro.org> Co-developed-by:
-
Sean Christopherson authored
Contrary to its name, mmu_notifier_synchronize() does not synchronize the notifier's SRCU instance, but rather waits for RCU callbacks to finish. i.e. it invokes rcu_barrier(). The RCU documentation is quite clear on this matter, explicitly calling out that rcu_barrier() does not imply synchronize_rcu(). As there are no callers of mmu_notifier_synchronize() and it's unclear whether any user of mmu_notifier_call_srcu() will ever want to barrier on their callbacks, simply remove the function. Link: http://lkml.kernel.org/r/20181106134705.14197-1-sean.j.christopherson@intel.comSigned-off-by:
Sean Christopherson <sean.j.christopherson@intel.com> Reviewed-by:
-
Balbir Singh authored
In hot remove, we try to clear poisoned pages, but a small optimization to check if num_poisoned_pages is 0 helps remove the iteration through nr_pages. [akpm@linux-foundation.org: tweak comment text] Link: http://lkml.kernel.org/r/20181102120001.4526-1-bsingharora@gmail.comSigned-off-by:
Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Signed-off-by:
-
Miles Chen authored
The (root-only) page owner read might allocate a large size of memory with a large read count. Allocation fails can easily occur when doing high order allocations. Clamp buffer size to PAGE_SIZE to avoid arbitrary size allocation and avoid allocation fails due to high order allocation. [akpm@linux-foundation.org: use min_t()] Link: http://lkml.kernel.org/r/1541091607-27402-1-git-send-email-miles.chen@mediatek.comSigned-off-by:
Miles Chen <miles.chen@mediatek.com> Acked-by:
-
Vlastimil Babka authored
Multiple people have reported the following sparse warning: ./include/linux/slab.h:332:43: warning: dubious: x & !y The minimal fix would be to change the logical & to boolean &&, which emits the same code, but Andrew has suggested that the branch-avoiding tricks are maybe not worthwile. David Laight provided a nice comparison of disassembly of multiple variants, which shows that the current version produces a 4 deep dependency chain, and fixing the sparse warning by changing logical and to multiplication emits an IMUL, making it even more expensive. The code as rewritten by this patch yielded the best disassembly, with a single predictable branch for the most common case, and a ternary operator for the rest, which gcc seems to compile without a branch or cmov by itself. The result should be more readable, without a sparse warning and probably also faster for the common case. Link: http://lkml.kernel.org/r/80340595-d7c5-97b9-4f6c-23fa893a91e9@suse.cz Fixes: 1291523f ("mm, slab/slub: introduce kmalloc-reclaimable caches") Reviewed-by:
Bart Van Assche <bvanassche@acm.org> Reported-by:
Darryl T. Agostinelli <dagostinelli@gmail.com> Reported-by:
Masahiro Yamada <yamada.masahiro@socionext.com> Suggested-by:
David Laight <David.Laight@ACULAB.COM> Signed-off-by:
-
Wei Yang authored
If __cmpxchg_double_slab() fails and (l != m), current code records transition states of slub action. Update the action after __cmpxchg_double_slab() success to record the final state. [akpm@linux-foundation.org: more whitespace cleanup] Link: http://lkml.kernel.org/r/20181107013119.3816-1-richard.weiyang@gmail.comSigned-off-by:
-
Wei Yang authored
node_match() is a static function and is only invoked in slub.c. In all three places, `page' is ensured to be valid. Link: http://lkml.kernel.org/r/20181106150245.1668-1-richard.weiyang@gmail.comSigned-off-by:
Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by:
-
Wei Yang authored
cpu_slab is a per cpu variable which is allocated in all or none. If a cpu_slab failed to be allocated, the slub is not usable. We could use cpu_slab without validation in __flush_cpu_slab(). Link: http://lkml.kernel.org/r/20181103141218.22844-1-richard.weiyang@gmail.comSigned-off-by:
-
Yangtao Li authored
WARN_ON() already contains an unlikely(), so it's not necessary to use unlikely. Also change WARN_ON() back to WARN_ON_ONCE() to avoid potentially spamming dmesg with user-triggerable large allocations. [akpm@linux-foundation.org: s/WARN_ON/WARN_ON_ONCE/, per Vlastimil] Link: http://lkml.kernel.org/r/20181104125028.3572-1-tiny.windzz@gmail.comSigned-off-by:
-
Junxiao Bi authored
For sync io read in ocfs2_read_blocks_sync(), first clear bh uptodate flag and submit the io, second wait io done, last check whether bh uptodate, if not return io error. If two sync io for the same bh were issued, it could be the first io done and set uptodate flag, but just before check that flag, the second io came in and cleared uptodate, then ocfs2_read_blocks_sync() for the first io will return IO error. Indeed it's not necessary to clear uptodate flag, as the io end handler end_buffer_read_sync() will set or clear it based on io succeed or failed. The following message was found from a nfs server but the underlying storage returned no error. [4106438.567376] (nfsd,7146,3):ocfs2_get_suballoc_slot_bit:2780 ERROR: read block 1238823695 failed -5 [4106438.567569] (nfsd,7146,3):ocfs2_get_suballoc_slot_bit:2812 ERROR: status = -5 [4106438.567611] (nfsd,7146,3):ocfs2_test_inode_bit:2894 ERROR: get alloc slot and bit failed -5 [4106438.567643] (nfsd,7146,3):ocfs2_test_inode_bit:2932 ERROR: status = -5 [4106438.567675] (nfsd,7146,3):ocfs2_get_dentry:94 ERROR: test inode bit failed -5 Same issue in non sync read ocfs2_read_blocks(), fixed it as well. Link: http://lkml.kernel.org/r/20181121020023.3034-4-junxiao.bi@oracle.comSigned-off-by:
Junxiao Bi <junxiao.bi@oracle.com> Reviewed-by:
Changwei Ge <ge.changwei@h3c.com> Reviewed-by:
Yiwen Jiang <jiangyiwen@huawei.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Joseph Qi <jiangqi903@gmail.com> Cc: Jun Piao <piaojun@huawei.com> Cc: Mark Fasheh <mfasheh@versity.com> Signed-off-by:
-
Junxiao Bi authored
Dirty flag of the journal should be cleared at the last stage of umount, if do it before jbd2_journal_destroy(), then some metadata in uncommitted transaction could be lost due to io error, but as dirty flag of journal was already cleared, we can't find that until run a full fsck. This may cause system panic or other corruption. Link: http://lkml.kernel.org/r/20181121020023.3034-3-junxiao.bi@oracle.comSigned-off-by:
Joseph Qi <jiangqi903@gmail.com> Cc: Jun Piao <piaojun@huawei.com> Cc: Changwei Ge <ge.changwei@h3c.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Mark Fasheh <mfasheh@versity.com> Signed-off-by:
-
Junxiao Bi authored
mount.ocfs2 ignore the inconsistent error that journal is clean but local alloc is unrecovered. After mount, local alloc not empty, then reserver cluster didn't alloc a new local alloc window, reserveration map is empty(ocfs2_reservation_map.m_bitmap_len = 0), that triggered the following panic. This issue was reported at https://oss.oracle.com/pipermail/ocfs2-devel/2015-May/010854.html and was advised to fixed during mount. But this is a very unusual inconsistent state, usually journal dirty flag should be cleared at the last stage of umount until every other things go right. We may need do further debug to check that. Any way to avoid possible futher corruption, mount should be abort and fsck should be run. (mount.ocfs2,1765,1):ocfs2_load_local_alloc:353 ERROR: Local alloc hasn't been recovered! found = 6518, set = 6518, taken = 8192, off = 15912372 ocfs2: Mounting device (202,64) on (node 0, slot 3) with ordered data mode. o2dlm: Joining domain 89CEAC63CC4F4D03AC185B44E0EE0F3F ( 0 1 2 3 4 5 6 8 ) 8 nodes ocfs2: Mounting device (202,80) on (node 0, slot 3) with ordered data mode. o2hb: Region 89CEAC63CC4F4D03AC185B44E0EE0F3F (xvdf) is now a quorum device o2net: Accepted connection from node yvwsoa17p (num 7) at 172.22.77.88:7777 o2dlm: Node 7 joins domain 64FE421C8C984E6D96ED12C55FEE2435 ( 0 1 2 3 4 5 6 7 8 ) 9 nodes o2dlm: Node 7 joins domain 89CEAC63CC4F4D03AC185B44E0EE0F3F ( 0 1 2 3 4 5 6 7 8 ) 9 nodes ------------[ cut here ]------------ kernel BUG at fs/ocfs2/reservations.c:507! invalid opcode: 0000 [#1] SMP Modules linked in: ocfs2 rpcsec_gss_krb5 auth_rpcgss nfsv4 nfs fscache lockd grace ocfs2_dlmfs ocfs2_stack_o2cb ocfs2_dlm ocfs2_nodemanager ocfs2_stackglue configfs sunrpc ipt_REJECT nf_reject_ipv4 nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_reject_ipv6 nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables ib_ipoib rdma_ucm ib_ucm ib_uverbs ib_umad rdma_cm ib_cm iw_cm ib_sa ib_mad ib_core ib_addr ipv6 ovmapi ppdev parport_pc parport xen_netfront fb_sys_fops sysimgblt sysfillrect syscopyarea acpi_cpufreq pcspkr i2c_piix4 i2c_core sg ext4 jbd2 mbcache2 sr_mod cdrom xen_blkfront pata_acpi ata_generic ata_piix floppy dm_mirror dm_region_hash dm_log dm_mod CPU: 0 PID: 4349 Comm: startWebLogic.s Not tainted 4.1.12-124.19.2.el6uek.x86_64 #2 Hardware name: Xen HVM domU, BIOS 4.4.4OVM 09/06/2018 task: ffff8803fb04e200 ti: ffff8800ea4d8000 task.ti: ffff8800ea4d8000 RIP: 0010:[<ffffffffa05e96a8>] [<ffffffffa05e96a8>] __ocfs2_resv_find_window+0x498/0x760 [ocfs2] Call Trace: ocfs2_resmap_resv_bits+0x10d/0x400 [ocfs2] ocfs2_claim_local_alloc_bits+0xd0/0x640 [ocfs2] __ocfs2_claim_clusters+0x178/0x360 [ocfs2] ocfs2_claim_clusters+0x1f/0x30 [ocfs2] ocfs2_convert_inline_data_to_extents+0x634/0xa60 [ocfs2] ocfs2_write_begin_nolock+0x1c6/0x1da0 [ocfs2] ocfs2_write_begin+0x13e/0x230 [ocfs2] generic_perform_write+0xbf/0x1c0 __generic_file_write_iter+0x19c/0x1d0 ocfs2_file_write_iter+0x589/0x1360 [ocfs2] __vfs_write+0xb8/0x110 vfs_write+0xa9/0x1b0 SyS_write+0x46/0xb0 system_call_fastpath+0x18/0xd7 Code: ff ff 8b 75 b8 39 75 b0 8b 45 c8 89 45 98 0f 84 e5 fe ff ff 45 8b 74 24 18 41 8b 54 24 1c e9 56 fc ff ff 85 c0 0f 85 48 ff ff ff <0f> 0b 48 8b 05 cf c3 de ff 48 ba 00 00 00 00 00 00 00 10 48 85 RIP __ocfs2_resv_find_window+0x498/0x760 [ocfs2] RSP <ffff8800ea4db668> ---[ end trace 566f07529f2edf3c ]--- Kernel panic - not syncing: Fatal exception Kernel Offset: disabled Link: http://lkml.kernel.org/r/20181121020023.3034-2-junxiao.bi@oracle.comSigned-off-by:
-
