- 01 Jul, 2021 5 commits
-
-
Muchun Song authored
In the subsequent patch, we should allocate the vmemmap pages when freeing a HugeTLB page. But update_and_free_page() can be called under any context, so we cannot use GFP_KERNEL to allocate vmemmap pages. However, we can defer the actual freeing in a kworker to prevent from using GFP_ATOMIC to allocate the vmemmap pages. The __update_and_free_page() is where the call to allocate vmemmmap pages will be inserted. Link: https://lkml.kernel.org/r/20210510030027.56044-6-songmuchun@bytedance.comSigned-off-by:
Muchun Song <songmuchun@bytedance.com> Reviewed-by:
Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by:
Oscar Salvador <osalvador@suse.de> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andy Lutomirski <luto@kernel.org> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Barry Song <song.bao.hua@hisilicon.com> Cc: Bodeddula Balasubramaniam <bodeddub@amazon.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Chen Huang <chenhuang5@huawei.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Rientjes <rientjes@google.com> Cc: HORIGUCHI NAOYA <naoya.horiguchi@nec.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Joerg Roedel <jroedel@suse.de> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Matthew Wilcox <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Mina Almasry <almasrymina@google.com> Cc: Oliver Neukum <oneukum@suse.com> Cc: Paul E. McKenney <paulmck@kernel.org> Cc: Pawan Gupta <pawan.kumar.gupta@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Xiongchun Duan <duanxiongchun@bytedance.com> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Muchun Song authored
Every HugeTLB has more than one struct page structure. We __know__ that we only use the first 4 (__NR_USED_SUBPAGE) struct page structures to store metadata associated with each HugeTLB. There are a lot of struct page structures associated with each HugeTLB page. For tail pages, the value of compound_head is the same. So we can reuse first page of tail page structures. We map the virtual addresses of the remaining pages of tail page structures to the first tail page struct, and then free these page frames. Therefore, we need to reserve two pages as vmemmap areas. When we allocate a HugeTLB page from the buddy, we can free some vmemmap pages associated with each HugeTLB page. It is more appropriate to do it in the prep_new_huge_page(). The free_vmemmap_pages_per_hpage(), which indicates how many vmemmap pages associated with a HugeTLB page can be freed, returns zero for now, which means the feature is disabled. We will enable it once all the infrastructure is there. [willy@infradead.org: fix documentation warning] Link: https://lkml.kernel.org/r/20210615200242.1716568-5-willy@infradead.org Link: https://lkml.kernel.org/r/20210510030027.56044-5-songmuchun@bytedance.comSigned-off-by:
Matthew Wilcox (Oracle) <willy@infradead.org> Reviewed-by:
Chen Huang <chenhuang5@huawei.com> Tested-by:
Bodeddula Balasubramaniam <bodeddub@amazon.com> Acked-by:
Michal Hocko <mhocko@suse.com> Reviewed-by:
-
Muchun Song authored
For HugeTLB page, there are more metadata to save in the struct page. But the head struct page cannot meet our needs, so we have to abuse other tail struct page to store the metadata. In order to avoid conflicts caused by subsequent use of more tail struct pages, we can gather these discrete indexes of tail struct page. In this case, it will be easier to add a new tail page index later. Link: https://lkml.kernel.org/r/20210510030027.56044-4-songmuchun@bytedance.comSigned-off-by:
Miaohe Lin <linmiaohe@huawei.com> Tested-by:
-
Muchun Song authored
The option HUGETLB_PAGE_FREE_VMEMMAP allows for the freeing of some vmemmap pages associated with pre-allocated HugeTLB pages. For example, on X86_64 6 vmemmap pages of size 4KB each can be saved for each 2MB HugeTLB page. 4094 vmemmap pages of size 4KB each can be saved for each 1GB HugeTLB page. When a HugeTLB page is allocated or freed, the vmemmap array representing the range associated with the page will need to be remapped. When a page is allocated, vmemmap pages are freed after remapping. When a page is freed, previously discarded vmemmap pages must be allocated before remapping. The config option is introduced early so that supporting code can be written to depend on the option. The initial version of the code only provides support for x86-64. If config HAVE_BOOTMEM_INFO_NODE is enabled, the freeing vmemmap page code denpend on it to free vmemmap pages. Otherwise, just use free_reserved_page() to free vmemmmap pages. The routine register_page_bootmem_info() is used to register bootmem info. Therefore, make sure register_page_bootmem_info is enabled if HUGETLB_PAGE_FREE_VMEMMAP is defined. Link: https://lkml.kernel.org/r/20210510030027.56044-3-songmuchun@bytedance.comSigned-off-by:
Balbir Singh <bsingharora@gmail.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andy Lutomirski <luto@kernel.org> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Barry Song <song.bao.hua@hisilicon.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Rientjes <rientjes@google.com> Cc: HORIGUCHI NAOYA <naoya.horiguchi@nec.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Joerg Roedel <jroedel@suse.de> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Mina Almasry <almasrymina@google.com> Cc: Oliver Neukum <oneukum@suse.com> Cc: Paul E. McKenney <paulmck@kernel.org> Cc: Pawan Gupta <pawan.kumar.gupta@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Xiongchun Duan <duanxiongchun@bytedance.com> Signed-off-by:
-
Muchun Song authored
Patch series "Free some vmemmap pages of HugeTLB page", v23. This patch series will free some vmemmap pages(struct page structures) associated with each HugeTLB page when preallocated to save memory. In order to reduce the difficulty of the first version of code review. In this version, we disable PMD/huge page mapping of vmemmap if this feature was enabled. This acutely eliminates a bunch of the complex code doing page table manipulation. When this patch series is solid, we cam add the code of vmemmap page table manipulation in the future. The struct page structures (page structs) are used to describe a physical page frame. By default, there is an one-to-one mapping from a page frame to it's corresponding page struct. The HugeTLB pages consist of multiple base page size pages and is supported by many architectures. See hugetlbpage.rst in the Documentation directory for more details. On the x86 architecture, HugeTLB pages of size 2MB and 1GB are currently supported. Since the base page size on x86 is 4KB, a 2MB HugeTLB page consists of 512 base pages and a 1GB HugeTLB page consists of 4096 base pages. For each base page, there is a corresponding page struct. Within the HugeTLB subsystem, only the first 4 page structs are used to contain unique information about a HugeTLB page. HUGETLB_CGROUP_MIN_ORDER provides this upper limit. The only 'useful' information in the remaining page structs is the compound_head field, and this field is the same for all tail pages. By removing redundant page structs for HugeTLB pages, memory can returned to the buddy allocator for other uses. When the system boot up, every 2M HugeTLB has 512 struct page structs which size is 8 pages(sizeof(struct page) * 512 / PAGE_SIZE). HugeTLB struct pages(8 pages) page frame(8 pages) +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+ | | | 0 | -------------> | 0 | | | +-----------+ +-----------+ | | | 1 | -------------> | 1 | | | +-----------+ +-----------+ | | | 2 | -------------> | 2 | | | +-----------+ +-----------+ | | | 3 | -------------> | 3 | | | +-----------+ +-----------+ | | | 4 | -------------> | 4 | | 2MB | +-----------+ +-----------+ | | | 5 | -------------> | 5 | | | +-----------+ +-----------+ | | | 6 | -------------> | 6 | | | +-----------+ +-----------+ | | | 7 | -------------> | 7 | | | +-----------+ +-----------+ | | | | | | +-----------+ The value of page->compound_head is the same for all tail pages. The first page of page structs (page 0) associated with the HugeTLB page contains the 4 page structs necessary to describe the HugeTLB. The only use of the remaining pages of page structs (page 1 to page 7) is to point to page->compound_head. Therefore, we can remap pages 2 to 7 to page 1. Only 2 pages of page structs will be used for each HugeTLB page. This will allow us to free the remaining 6 pages to the buddy allocator. Here is how things look after remapping. HugeTLB struct pages(8 pages) page frame(8 pages) +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+ | | | 0 | -------------> | 0 | | | +-----------+ +-----------+ | | | 1 | -------------> | 1 | | | +-----------+ +-----------+ | | | 2 | ----------------^ ^ ^ ^ ^ ^ | | +-----------+ | | | | | | | | 3 | ------------------+ | | | | | | +-----------+ | | | | | | | 4 | --------------------+ | | | | 2MB | +-----------+ | | | | | | 5 | ----------------------+ | | | | +-----------+ | | | | | 6 | ------------------------+ | | | +-----------+ | | | | 7 | --------------------------+ | | +-----------+ | | | | | | +-----------+ When a HugeTLB is freed to the buddy system, we should allocate 6 pages for vmemmap pages and restore the previous mapping relationship. Apart from 2MB HugeTLB page, we also have 1GB HugeTLB page. It is similar to the 2MB HugeTLB page. We also can use this approach to free the vmemmap pages. In this case, for the 1GB HugeTLB page, we can save 4094 pages. This is a very substantial gain. On our server, run some SPDK/QEMU applications which will use 1024GB HugeTLB page. With this feature enabled, we can save ~16GB (1G hugepage)/~12GB (2MB hugepage) memory. Because there are vmemmap page tables reconstruction on the freeing/allocating path, it increases some overhead. Here are some overhead analysis. 1) Allocating 10240 2MB HugeTLB pages. a) With this patch series applied: # time echo 10240 > /proc/sys/vm/nr_hugepages real 0m0.166s user 0m0.000s sys 0m0.166s # bpftrace -e 'kprobe:alloc_fresh_huge_page { @start[tid] = nsecs; } kretprobe:alloc_fresh_huge_page /@start[tid]/ { @latency = hist(nsecs - @start[tid]); delete(@start[tid]); }' Attaching 2 probes... @latency: [8K, 16K) 5476 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@| [16K, 32K) 4760 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ | [32K, 64K) 4 | | b) Without this patch series: # time echo 10240 > /proc/sys/vm/nr_hugepages real 0m0.067s user 0m0.000s sys 0m0.067s # bpftrace -e 'kprobe:alloc_fresh_huge_page { @start[tid] = nsecs; } kretprobe:alloc_fresh_huge_page /@start[tid]/ { @latency = hist(nsecs - @start[tid]); delete(@start[tid]); }' Attaching 2 probes... @latency: [4K, 8K) 10147 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@| [8K, 16K) 93 | | Summarize: this feature is about ~2x slower than before. 2) Freeing 10240 2MB HugeTLB pages. a) With this patch series applied: # time echo 0 > /proc/sys/vm/nr_hugepages real 0m0.213s user 0m0.000s sys 0m0.213s # bpftrace -e 'kprobe:free_pool_huge_page { @start[tid] = nsecs; } kretprobe:free_pool_huge_page /@start[tid]/ { @latency = hist(nsecs - @start[tid]); delete(@start[tid]); }' Attaching 2 probes... @latency: [8K, 16K) 6 | | [16K, 32K) 10227 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@| [32K, 64K) 7 | | b) Without this patch series: # time echo 0 > /proc/sys/vm/nr_hugepages real 0m0.081s user 0m0.000s sys 0m0.081s # bpftrace -e 'kprobe:free_pool_huge_page { @start[tid] = nsecs; } kretprobe:free_pool_huge_page /@start[tid]/ { @latency = hist(nsecs - @start[tid]); delete(@start[tid]); }' Attaching 2 probes... @latency: [4K, 8K) 6805 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@| [8K, 16K) 3427 |@@@@@@@@@@@@@@@@@@@@@@@@@@ | [16K, 32K) 8 | | Summary: The overhead of __free_hugepage is about ~2-3x slower than before. Although the overhead has increased, the overhead is not significant. Like Mike said, "However, remember that the majority of use cases create HugeTLB pages at or shortly after boot time and add them to the pool. So, additional overhead is at pool creation time. There is no change to 'normal run time' operations of getting a page from or returning a page to the pool (think page fault/unmap)". Despite the overhead and in addition to the memory gains from this series. The following data is obtained by Joao Martins. Very thanks to his effort. There's an additional benefit which is page (un)pinners will see an improvement and Joao presumes because there are fewer memmap pages and thus the tail/head pages are staying in cache more often. Out of the box Joao saw (when comparing linux-next against linux-next + this series) with gup_test and pinning a 16G HugeTLB file (with 1G pages): get_user_pages(): ~32k -> ~9k unpin_user_pages(): ~75k -> ~70k Usually any tight loop fetching compound_head(), or reading tail pages data (e.g. compound_head) benefit a lot. There's some unpinning inefficiencies Joao was fixing[2], but with that in added it shows even more: unpin_user_pages(): ~27k -> ~3.8k [1] https://lore.kernel.org/linux-mm/20210409205254.242291-1-mike.kravetz@oracle.com/ [2] https://lore.kernel.org/linux-mm/20210204202500.26474-1-joao.m.martins@oracle.com/ This patch (of 9): Move bootmem info registration common API to individual bootmem_info.c. And we will use {get,put}_page_bootmem() to initialize the page for the vmemmap pages or free the vmemmap pages to buddy in the later patch. So move them out of CONFIG_MEMORY_HOTPLUG_SPARSE. This is just code movement without any functional change. Link: https://lkml.kernel.org/r/20210510030027.56044-1-songmuchun@bytedance.com Link: https://lkml.kernel.org/r/20210510030027.56044-2-songmuchun@bytedance.comSigned-off-by:David Hildenbrand <david@redhat.com> Reviewed-by:
-
- 29 Jun, 2021 35 commits
-
-
Naoya Horiguchi authored
__get_hwpoison_page() could fail to grab refcount by some race condition, so it's helpful if we can handle it by retrying. We already have retry logic, so make get_hwpoison_page() call get_any_page() when called from memory_failure(). As a result, get_hwpoison_page() can return negative values (i.e. error code), so some callers are also changed to handle error cases. soft_offline_page() does nothing for -EBUSY because that's enough and users in userspace can easily handle it. unpoison_memory() is also unchanged because it's broken and need thorough fixes (will be done later). Link: https://lkml.kernel.org/r/20210603233632.2964832-3-nao.horiguchi@gmail.comSigned-off-by:
Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Muchun Song <songmuchun@bytedance.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Tony Luck <tony.luck@intel.com> Signed-off-by:
-
Naoya Horiguchi authored
Now an action required MCE in already hwpoisoned address surely sends a SIGBUS to current process, but the SIGBUS doesn't convey error virtual address. That's not optimal for hwpoison-aware applications. To fix the issue, make memory_failure() call kill_accessing_process(), that does pagetable walk to find the error virtual address. It could find multiple virtual addresses for the same error page, and it seems hard to tell which virtual address is correct one. But that's rare and sending incorrect virtual address could be better than no address. So let's report the first found virtual address for now. [naoya.horiguchi@nec.com: fix walk_page_range() return] Link: https://lkml.kernel.org/r/20210603051055.GA244241@hori.linux.bs1.fc.nec.co.jp Link: https://lkml.kernel.org/r/20210521030156.2612074-4-nao.horiguchi@gmail.comSigned-off-by:
-
Mel Gorman authored
Dave Hansen reported the following about Feng Tang's tests on a machine with persistent memory onlined as a DRAM-like device. Feng Tang tossed these on a "Cascade Lake" system with 96 threads and ~512G of persistent memory and 128G of DRAM. The PMEM is in "volatile use" mode and being managed via the buddy just like the normal RAM. The PMEM zones are big ones: present 65011712 = 248 G high 134595 = 525 M The PMEM nodes, of course, don't have any CPUs in them. With your series, the pcp->high value per-cpu is 69584 pages or about 270MB per CPU. Scaled up by the 96 CPU threads, that's ~26GB of worst-case memory in the pcps per zone, or roughly 10% of the size of the zone. This should not cause a problem as such although it could trigger reclaim due to pages being stored on per-cpu lists for CPUs remote to a node. It is not possible to treat cpuless nodes exactly the same as normal nodes but the worst-case scenario can be mitigated by splitting pcp->high across all online CPUs for cpuless memory nodes. Link: https://lkml.kernel.org/r/20210616110743.GK30378@techsingularity.netSuggested-by:Dave Hansen <dave.hansen@intel.com> Signed-off-by:
Mel Gorman <mgorman@techsingularity.net> Acked-by:
Vlastimil Babka <vbabka@suse.cz> Acked-by:
-
Mel Gorman authored
The per-cpu page allocator (PCP) only stores order-0 pages. This means that all THP and "cheap" high-order allocations including SLUB contends on the zone->lock. This patch extends the PCP allocator to store THP and "cheap" high-order pages. Note that struct per_cpu_pages increases in size to 256 bytes (4 cache lines) on x86-64. Note that this is not necessarily a universal performance win because of how it is implemented. High-order pages can cause pcp->high to be exceeded prematurely for lower-orders so for example, a large number of THP pages being freed could release order-0 pages from the PCP lists. Hence, much depends on the allocation/free pattern as observed by a single CPU to determine if caching helps or hurts a particular workload. That said, basic performance testing passed. The following is a netperf UDP_STREAM test which hits the relevant patches as some of the network allocations are high-order. netperf-udp 5.13.0-rc2 5.13.0-rc2 mm-pcpburst-v3r4 mm-pcphighorder-v1r7 Hmean send-64 261.46 ( 0.00%) 266.30 * 1.85%* Hmean send-128 516.35 ( 0.00%) 536.78 * 3.96%* Hmean send-256 1014.13 ( 0.00%) 1034.63 * 2.02%* Hmean send-1024 3907.65 ( 0.00%) 4046.11 * 3.54%* Hmean send-2048 7492.93 ( 0.00%) 7754.85 * 3.50%* Hmean send-3312 11410.04 ( 0.00%) 11772.32 * 3.18%* Hmean send-4096 13521.95 ( 0.00%) 13912.34 * 2.89%* Hmean send-8192 21660.50 ( 0.00%) 22730.72 * 4.94%* Hmean send-16384 31902.32 ( 0.00%) 32637.50 * 2.30%* Functionally, a patch like this is necessary to make bulk allocation of high-order pages work with similar performance to order-0 bulk allocations. The bulk allocator is not updated in this series as it would have to be determined by bulk allocation users how they want to track the order of pages allocated with the bulk allocator. Link: https://lkml.kernel.org/r/20210611135753.GC30378@techsingularity.netSigned-off-by: -
Mike Rapoport authored
After removal of the DISCONTIGMEM memory model the FLAT_NODE_MEM_MAP configuration option is equivalent to FLATMEM. Drop CONFIG_FLAT_NODE_MEM_MAP and use CONFIG_FLATMEM instead. Link: https://lkml.kernel.org/r/20210608091316.3622-10-rppt@kernel.orgSigned-off-by:
Mike Rapoport <rppt@linux.ibm.com> Acked-by:
Arnd Bergmann <arnd@arndb.de> Acked-by:
-
Mike Rapoport authored
After removal of DISCINTIGMEM the NEED_MULTIPLE_NODES and NUMA configuration options are equivalent. Drop CONFIG_NEED_MULTIPLE_NODES and use CONFIG_NUMA instead. Done with $ sed -i 's/CONFIG_NEED_MULTIPLE_NODES/CONFIG_NUMA/' \ $(git grep -wl CONFIG_NEED_MULTIPLE_NODES) $ sed -i 's/NEED_MULTIPLE_NODES/NUMA/' \ $(git grep -wl NEED_MULTIPLE_NODES) with manual tweaks afterwards. [rppt@linux.ibm.com: fix arm boot crash] Link: https://lkml.kernel.org/r/YMj9vHhHOiCVN4BF@linux.ibm.com Link: https://lkml.kernel.org/r/20210608091316.3622-9-rppt@kernel.orgSigned-off-by:
-
Mike Rapoport authored
Remove description of DISCONTIGMEM from the "Memory Models" document and update VM sysctl description so that it won't mention DISCONIGMEM. Link: https://lkml.kernel.org/r/20210608091316.3622-8-rppt@kernel.orgSigned-off-by:
-
Mike Rapoport authored
There are several places that mention DISCONIGMEM in comments or have stale code guarded by CONFIG_DISCONTIGMEM. Remove the dead code and update the comments. Link: https://lkml.kernel.org/r/20210608091316.3622-7-rppt@kernel.orgSigned-off-by:
-
Mike Rapoport authored
There are no architectures that support DISCONTIGMEM left. Remove the configuration option and the dead code it was guarding in the generic memory management code. Link: https://lkml.kernel.org/r/20210608091316.3622-6-rppt@kernel.orgSigned-off-by:
-
Mike Rapoport authored
DISCONTIGMEM was replaced by FLATMEM with freeing of the unused memory map in v5.11. Remove the support for DISCONTIGMEM entirely. Link: https://lkml.kernel.org/r/20210608091316.3622-5-rppt@kernel.orgSigned-off-by:
Geert Uytterhoeven <geert@linux-m68k.org> Acked-by:
-
Mike Rapoport authored
DISCONTIGMEM was replaced by FLATMEM with freeing of the unused memory map in v5.11. Remove the support for DISCONTIGMEM entirely. Link: https://lkml.kernel.org/r/20210608091316.3622-4-rppt@kernel.orgSigned-off-by:
Vineet Gupta <vgupta@synopsys.com> Acked-by:
-
Mike Rapoport authored
Arc does not use DISCONTIGMEM to implement high memory, update the comment describing how high memory works to reflect this. Link: https://lkml.kernel.org/r/20210608091316.3622-3-rppt@kernel.orgSigned-off-by:
-
Mike Rapoport authored
Patch series "Remove DISCONTIGMEM memory model", v3. SPARSEMEM memory model was supposed to entirely replace DISCONTIGMEM a (long) while ago. The last architectures that used DISCONTIGMEM were updated to use other memory models in v5.11 and it is about the time to entirely remove DISCONTIGMEM from the kernel. This set removes DISCONTIGMEM from alpha, arc and m68k, simplifies memory model selection in mm/Kconfig and replaces usage of redundant CONFIG_NEED_MULTIPLE_NODES and CONFIG_FLAT_NODE_MEM_MAP with CONFIG_NUMA and CONFIG_FLATMEM respectively. I've also removed NUMA support on alpha that was BROKEN for more than 15 years. There were also minor updates all over arch/ to remove mentions of DISCONTIGMEM in comments and #ifdefs. This patch (of 9): NUMA is marked broken on alpha for more than 15 years and DISCONTIGMEM was replaced with SPARSEMEM in v5.11. Remove both NUMA and DISCONTIGMEM support from alpha. Link: https://lkml.kernel.org/r/20210608091316.3622-1-rppt@kernel.org Link: https://lkml.kernel.org/r/20210608091316.3622-2-rppt@kernel.orgSigned-off-by:
-
Mel Gorman authored
Patch series "Allow high order pages to be stored on PCP", v2. The per-cpu page allocator (PCP) only handles order-0 pages. With the series "Use local_lock for pcp protection and reduce stat overhead" and "Calculate pcp->high based on zone sizes and active CPUs", it's now feasible to store high-order pages on PCP lists. This small series allows PCP to store "cheap" orders where cheap is determined by PAGE_ALLOC_COSTLY_ORDER and THP-sized allocations. This patch (of 2): In the next page, free_compount_page is going to use the common helper free_the_page. This patch moves the definition to ease review. No functional change. Link: https://lkml.kernel.org/r/20210603142220.10851-1-mgorman@techsingularity.net Link: https://lkml.kernel.org/r/20210603142220.10851-2-mgorman@techsingularity.netSigned-off-by:
-
Liu Shixin authored
commit f6366156 ("mm/page_alloc.c: clear out zone->lowmem_reserve[] if the zone is empty") clears out zone->lowmem_reserve[] if zone is empty. But when zone is not empty and sysctl_lowmem_reserve_ratio[i] is set to zero, zone_managed_pages(zone) is not counted in the managed_pages either. This is inconsistent with the description of lowmem_reserve, so fix it. Link: https://lkml.kernel.org/r/20210527125707.3760259-1-liushixin2@huawei.com Fixes: f6366156 ("mm/page_alloc.c: clear out zone->lowmem_reserve[] if the zone is empty") Signed-off-by:
Liu Shixin <liushixin2@huawei.com> Reported-by:
yangerkun <yangerkun@huawei.com> Reviewed-by:
Baoquan He <bhe@redhat.com> Acked-by:
-
Dong Aisheng authored
Make debug message more accurate. Link: https://lkml.kernel.org/r/20210531091908.1738465-6-aisheng.dong@nxp.comSigned-off-by:
Dong Aisheng <aisheng.dong@nxp.com> Reviewed-by:
-
Dong Aisheng authored
Actually SECTIONS_SHIFT is used in the kernel code, so the code comments is strictly incorrect. And since commit bbeae5b0 ("mm: move page flags layout to separate header"), SECTIONS_SHIFT definition has been moved to include/linux/page-flags-layout.h, since code itself looks quite straighforward, instead of moving the code comment into the new place as well, we just simply remove it. This also fixed a checkpatch complain derived from the original code: WARNING: please, no space before tabs + * SECTIONS_SHIFT ^I^I#bits space required to store a section #$ Link: https://lkml.kernel.org/r/20210531091908.1738465-2-aisheng.dong@nxp.comSigned-off-by:
Yu Zhao <yuzhao@google.com> Reviewed-by:
-
Mel Gorman authored
This introduces a new sysctl vm.percpu_pagelist_high_fraction. It is similar to the old vm.percpu_pagelist_fraction. The old sysctl increased both pcp->batch and pcp->high with the higher pcp->high potentially reducing zone->lock contention. However, the higher pcp->batch value also potentially increased allocation latency while the PCP was refilled. This sysctl only adjusts pcp->high so that zone->lock contention is potentially reduced but allocation latency during a PCP refill remains the same. # grep -E "high:|batch" /proc/zoneinfo | tail -2 high: 649 batch: 63 # sysctl vm.percpu_pagelist_high_fraction=8 # grep -E "high:|batch" /proc/zoneinfo | tail -2 high: 35071 batch: 63 # sysctl vm.percpu_pagelist_high_fraction=64 high: 4383 batch: 63 # sysctl vm.percpu_pagelist_high_fraction=0 high: 649 batch: 63 [mgorman@techsingularity.net: fix documentation] Link: https://lkml.kernel.org/r/20210528151010.GQ30378@techsingularity.net Link: https://lkml.kernel.org/r/20210525080119.5455-7-mgorman@techsingularity.netSigned-off-by:Dave Hansen <dave.hansen@linux.intel.com> Acked-by:
-
Mel Gorman authored
When kswapd is active then direct reclaim is potentially active. In either case, it is possible that a zone would be balanced if pages were not trapped on PCP lists. Instead of draining remote pages, simply limit the size of the PCP lists while kswapd is active. Link: https://lkml.kernel.org/r/20210525080119.5455-6-mgorman@techsingularity.netSigned-off-by:
-
Mel Gorman authored
When a task is freeing a large number of order-0 pages, it may acquire the zone->lock multiple times freeing pages in batches. This may unnecessarily contend on the zone lock when freeing very large number of pages. This patch adapts the size of the batch based on the recent pattern to scale the batch size for subsequent frees. As the machines I used were not large enough to test this are not large enough to illustrate a problem, a debugging patch shows patterns like the following (slightly editted for clarity) Baseline vanilla kernel time-unmap-14426 [...] free_pcppages_bulk: free 63 count 378 high 378 time-unmap-14426 [...] free_pcppages_bulk: free 63 count 378 high 378 time-unmap-14426 [...] free_pcppages_bulk: free 63 count 378 high 378 time-unmap-14426 [...] free_pcppages_bulk: free 63 count 378 high 378 time-unmap-14426 [...] free_pcppages_bulk: free 63 count 378 high 378 With patches time-unmap-7724 [...] free_pcppages_bulk: free 126 count 814 high 814 time-unmap-7724 [...] free_pcppages_bulk: free 252 count 814 high 814 time-unmap-7724 [...] free_pcppages_bulk: free 504 count 814 high 814 time-unmap-7724 [...] free_pcppages_bulk: free 751 count 814 high 814 time-unmap-7724 [...] free_pcppages_bulk: free 751 count 814 high 814 Link: https://lkml.kernel.org/r/20210525080119.5455-5-mgorman@techsingularity.netSigned-off-by:
-
Mel Gorman authored
The PCP high watermark is based on the number of online CPUs so the watermarks must be adjusted during CPU hotplug. At the time of hot-remove, the number of online CPUs is already adjusted but during hot-add, a delta needs to be applied to update PCP to the correct value. After this patch is applied, the high watermarks are adjusted correctly. # grep high: /proc/zoneinfo | tail -1 high: 649 # echo 0 > /sys/devices/system/cpu/cpu4/online # grep high: /proc/zoneinfo | tail -1 high: 664 # echo 1 > /sys/devices/system/cpu/cpu4/online # grep high: /proc/zoneinfo | tail -1 high: 649 Link: https://lkml.kernel.org/r/20210525080119.5455-4-mgorman@techsingularity.netSigned-off-by: -
Mel Gorman authored
The pcp high watermark is based on the batch size but there is no relationship between them other than it is convenient to use early in boot. This patch takes the first step and bases pcp->high on the zone low watermark split across the number of CPUs local to a zone while the batch size remains the same to avoid increasing allocation latencies. The intent behind the default pcp->high is "set the number of PCP pages such that if they are all full that background reclaim is not started prematurely". Note that in this patch the pcp->high values are adjusted after memory hotplug events, min_free_kbytes adjustments and watermark scale factor adjustments but not CPU hotplug events which is handled later in the series. On a test KVM instance; Before grep -E "high:|batch" /proc/zoneinfo | tail -2 high: 378 batch: 63 After grep -E "high:|batch" /proc/zoneinfo | tail -2 high: 649 batch: 63 [mgorman@techsingularity.net: fix __setup_per_zone_wmarks for parallel memory hotplug] Link: https://lkml.kernel.org/r/20210528105925.GN30378@techsingularity.net Link: https://lkml.kernel.org/r/20210525080119.5455-3-mgorman@techsingularity.netSigned-off-by: -
Mel Gorman authored
Patch series "Calculate pcp->high based on zone sizes and active CPUs", v2. The per-cpu page allocator (PCP) is meant to reduce contention on the zone lock but the sizing of batch and high is archaic and neither takes the zone size into account or the number of CPUs local to a zone. With larger zones and more CPUs per node, the contention is getting worse. Furthermore, the fact that vm.percpu_pagelist_fraction adjusts both batch and high values means that the sysctl can reduce zone lock contention but also increase allocation latencies. This series disassociates pcp->high from pcp->batch and then scales pcp->high based on the size of the local zone with limited impact to reclaim and accounting for active CPUs but leaves pcp->batch static. It also adapts the number of pages that can be on the pcp list based on recent freeing patterns. The motivation is partially to adjust to larger memory sizes but is also driven by the fact that large batches of page freeing via release_pages() often shows zone contention as a major part of the problem. Another is a bug report based on an older kernel where a multi-terabyte process can takes several minutes to exit. A workaround was to use vm.percpu_pagelist_fraction to increase the pcp->high value but testing indicated that a production workload could not use the same values because of an increase in allocation latencies. Unfortunately, I cannot reproduce this test case myself as the multi-terabyte machines are in active use but it should alleviate the problem. The series aims to address both and partially acts as a pre-requisite. pcp only works with order-0 which is useless for SLUB (when using high orders) and THP (unconditionally). To store high-order pages on PCP, the pcp->high values need to be increased first. This patch (of 6): The vm.percpu_pagelist_fraction is used to increase the batch and high limits for the per-cpu page allocator (PCP). The intent behind the sysctl is to reduce zone lock acquisition when allocating/freeing pages but it has a problem. While it can decrease contention, it can also increase latency on the allocation side due to unreasonably large batch sizes. This leads to games where an administrator adjusts percpu_pagelist_fraction on the fly to work around contention and allocation latency problems. This series aims to alleviate the problems with zone lock contention while avoiding the allocation-side latency problems. For the purposes of review, it's easier to remove this sysctl now and reintroduce a similar sysctl later in the series that deals only with pcp->high. Link: https://lkml.kernel.org/r/20210525080119.5455-1-mgorman@techsingularity.net Link: https://lkml.kernel.org/r/20210525080119.5455-2-mgorman@techsingularity.netSigned-off-by:
-
Minchan Kim authored
alloc_contig_dump_pages() aims for helping debugging page migration failure by elevated page refcount compared to expected_count. (for the detail, please look at migrate_page_move_mapping) However, -ENOMEM is just the case that system is under memory pressure state, not relevant with page refcount at all. Thus, the dumping page list is not helpful for the debugging point of view. Link: https://lkml.kernel.org/r/YKa2Wyo9xqIErpfa@google.comSigned-off-by:
Minchan Kim <minchan@kernel.org> Reviewed-by:
-
Mel Gorman authored
VM events do not need explicit protection by disabling IRQs so update the counter with IRQs enabled in __free_pages_ok. Link: https://lkml.kernel.org/r/20210512095458.30632-10-mgorman@techsingularity.netSigned-off-by:
Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jesper Dangaard Brouer <brouer@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by:
-
Mel Gorman authored
Historically when freeing pages, free_one_page() assumed that callers had IRQs disabled and the zone->lock could be acquired with spin_lock(). This confuses the scope of what local_lock_irq is protecting and what zone->lock is protecting in free_unref_page_list in particular. This patch uses spin_lock_irqsave() for the zone->lock in free_one_page() instead of relying on callers to have disabled IRQs. free_unref_page_commit() is changed to only deal with PCP pages protected by the local lock. free_unref_page_list() then first frees isolated pages to the buddy lists with free_one_page() and frees the rest of the pages to the PCP via free_unref_page_commit(). The end result is that free_one_page() is no longer depending on side-effects of local_lock to be correct. Note that this may incur a performance penalty while memory hot-remove is running but that is not a common operation. [lkp@intel.com: Ensure CMA pages get addded to correct pcp list] Link: https://lkml.kernel.org/r/20210512095458.30632-9-mgorman@techsingularity.netSigned-off-by:
-
Mel Gorman authored
__free_pages_ok() disables IRQs before calling a common helper free_one_page() that acquires the zone lock. This is not safe according to Documentation/locking/locktypes.rst and in this context, IRQ disabling is not protecting a per_cpu_pages structure either or a local_lock would be used. This patch explicitly acquires the lock with spin_lock_irqsave instead of relying on a helper. This removes the last instance of local_irq_save() in page_alloc.c. Link: https://lkml.kernel.org/r/20210512095458.30632-8-mgorman@techsingularity.netSigned-off-by:
-
Mel Gorman authored
IRQs are left disabled for the zone and node VM event counters. This is unnecessary as the affected counters are allowed to race for preemmption and IRQs. This patch reduces the scope of IRQs being disabled via local_[lock|unlock]_irq on !PREEMPT_RT kernels. One __mod_zone_freepage_state is still called with IRQs disabled. While this could be moved out, it's not free on all architectures as some require IRQs to be disabled for mod_zone_page_state on !PREEMPT_RT kernels. Link: https://lkml.kernel.org/r/20210512095458.30632-7-mgorman@techsingularity.netSigned-off-by:
-
Mel Gorman authored
Now that the zone_statistics are simple counters that do not require special protection, the bulk allocator accounting updates can be batch updated without adding too much complexity with protected RMW updates or using xchg. Link: https://lkml.kernel.org/r/20210512095458.30632-6-mgorman@techsingularity.netSigned-off-by:
-
Mel Gorman authored
__count_numa_event is small enough to be treated similarly to __count_vm_event so inline it. Link: https://lkml.kernel.org/r/20210512095458.30632-5-mgorman@techsingularity.netSigned-off-by:
-
Mel Gorman authored
NUMA statistics are maintained on the zone level for hits, misses, foreign etc but nothing relies on them being perfectly accurate for functional correctness. The counters are used by userspace to get a general overview of a workloads NUMA behaviour but the page allocator incurs a high cost to maintain perfect accuracy similar to what is required for a vmstat like NR_FREE_PAGES. There even is a sysctl vm.numa_stat to allow userspace to turn off the collection of NUMA statistics like NUMA_HIT. This patch converts NUMA_HIT and friends to be NUMA events with similar accuracy to VM events. There is a possibility that slight errors will be introduced but the overall trend as seen by userspace will be similar. The counters are no longer updated from vmstat_refresh context as it is unnecessary overhead for counters that may never be read by userspace. Note that counters could be maintained at the node level to save space but it would have a user-visible impact due to /proc/zoneinfo. [lkp@intel.com: Fix misplaced closing brace for !CONFIG_NUMA] Link: https://lkml.kernel.org/r/20210512095458.30632-4-mgorman@techsingularity.netSigned-off-by:
-
Mel Gorman authored
There is a lack of clarity of what exactly local_irq_save/local_irq_restore protects in page_alloc.c . It conflates the protection of per-cpu page allocation structures with per-cpu vmstat deltas. This patch protects the PCP structure using local_lock which for most configurations is identical to IRQ enabling/disabling. The scope of the lock is still wider than it should be but this is decreased later. It is possible for the local_lock to be embedded safely within struct per_cpu_pages but it adds complexity to free_unref_page_list. [akpm@linux-foundation.org: coding style fixes] [mgorman@techsingularity.net: work around a pahole limitation with zero-sized struct pagesets] Link: https://lkml.kernel.org/r/20210526080741.GW30378@techsingularity.net [lkp@intel.com: Make pagesets static] Link: https://lkml.kernel.org/r/20210512095458.30632-3-mgorman@techsingularity.netSigned-off-by:
-
Mel Gorman authored
The PCP (per-cpu page allocator in page_alloc.c) shares locking requirements with vmstat and the zone lock which is inconvenient and causes some issues. For example, the PCP list and vmstat share the same per-cpu space meaning that it's possible that vmstat updates dirty cache lines holding per-cpu lists across CPUs unless padding is used. Second, PREEMPT_RT does not want to disable IRQs for too long in the page allocator. This series splits the locking requirements and uses locks types more suitable for PREEMPT_RT, reduces the time when special locking is required for stats and reduces the time when IRQs need to be disabled on !PREEMPT_RT kernels. Why local_lock? PREEMPT_RT considers the following sequence to be unsafe as documented in Documentation/locking/locktypes.rst local_irq_disable(); spin_lock(&lock); The pcp allocator has this sequence for rmqueue_pcplist (local_irq_save) -> __rmqueue_pcplist -> rmqueue_bulk (spin_lock). While it's possible to separate this out, it generally means there are points where we enable IRQs and reenable them again immediately. To prevent a migration and the per-cpu pointer going stale, migrate_disable is also needed. That is a custom lock that is similar, but worse, than local_lock. Furthermore, on PREEMPT_RT, it's undesirable to leave IRQs disabled for too long. By converting to local_lock which disables migration on PREEMPT_RT, the locking requirements can be separated and start moving the protections for PCP, stats and the zone lock to PREEMPT_RT-safe equivalent locking. As a bonus, local_lock also means that PROVE_LOCKING does something useful. After that, it's obvious that zone_statistics incurs too much overhead and leaves IRQs disabled for longer than necessary on !PREEMPT_RT kernels. zone_statistics uses perfectly accurate counters requiring IRQs be disabled for parallel RMW sequences when inaccurate ones like vm_events would do. The series makes the NUMA statistics (NUMA_HIT and friends) inaccurate counters that then require no special protection on !PREEMPT_RT. The bulk page allocator can then do stat updates in bulk with IRQs enabled which should improve the efficiency. Technically, this could have been done without the local_lock and vmstat conversion work and the order simply reflects the timing of when different series were implemented. Finally, there are places where we conflate IRQs being disabled for the PCP with the IRQ-safe zone spinlock. The remainder of the series reduces the scope of what is protected by disabled IRQs on !PREEMPT_RT kernels. By the end of the series, page_alloc.c does not call local_irq_save so the locking scope is a bit clearer. The one exception is that modifying NR_FREE_PAGES still happens in places where it's known the IRQs are disabled as it's harmless for PREEMPT_RT and would be expensive to split the locking there. No performance data is included because despite the overhead of the stats, it's within the noise for most workloads on !PREEMPT_RT. However, Jesper Dangaard Brouer ran a page allocation microbenchmark on a E5-1650 v4 @ 3.60GHz CPU on the first version of this series. Focusing on the array variant of the bulk page allocator reveals the following. (CPU: Intel(R) Xeon(R) CPU E5-1650 v4 @ 3.60GHz) ARRAY variant: time_bulk_page_alloc_free_array: step=bulk size Baseline Patched 1 56.383 54.225 (+3.83%) 2 40.047 35.492 (+11.38%) 3 37.339 32.643 (+12.58%) 4 35.578 30.992 (+12.89%) 8 33.592 29.606 (+11.87%) 16 32.362 28.532 (+11.85%) 32 31.476 27.728 (+11.91%) 64 30.633 27.252 (+11.04%) 128 30.596 27.090 (+11.46%) While this is a positive outcome, the series is more likely to be interesting to the RT people in terms of getting parts of the PREEMPT_RT tree into mainline. This patch (of 9): The per-cpu page allocator lists and the per-cpu vmstat deltas are stored in the same struct per_cpu_pages even though vmstats have no direct impact on the per-cpu page lists. This is inconsistent because the vmstats for a node are stored on a dedicated structure. The bigger issue is that the per_cpu_pages structure is not cache-aligned and stat updates either cache conflict with adjacent per-cpu lists incurring a runtime cost or padding is required incurring a memory cost. This patch splits the per-cpu pagelists and the vmstat deltas into separate structures. It's mostly a mechanical conversion but some variable renaming is done to clearly distinguish the per-cpu pages structure (pcp) from the vmstats (pzstats). Superficially, this appears to increase the size of the per_cpu_pages structure but the movement of expire fills a structure hole so there is no impact overall. [mgorman@techsingularity.net: make it W=1 cleaner] Link: https://lkml.kernel.org/r/20210514144622.GA3735@techsingularity.net [mgorman@techsingularity.net: make it W=1 even cleaner] Link: https://lkml.kernel.org/r/20210516140705.GB3735@techsingularity.net [lkp@intel.com: check struct per_cpu_zonestat has a non-zero size] [vbabka@suse.cz: Init zone->per_cpu_zonestats properly] Link: https://lkml.kernel.org/r/20210512095458.30632-1-mgorman@techsingularity.net Link: https://lkml.kernel.org/r/20210512095458.30632-2-mgorman@techsingularity.netSigned-off-by: -
Andrii Nakryiko authored
Commit "mm/page_alloc: convert per-cpu list protection to local_lock" will introduce a zero-sized per-CPU variable, which causes pahole to generate invalid BTF. Only pahole versions 1.18 through 1.21 are impacted, as before 1.18 pahole doesn't know anything about per-CPU variables, and 1.22 contains the proper fix for the issue. Luckily, pahole 1.18 got --skip_encoding_btf_vars option disabling BTF generation for per-CPU variables in anticipation of some unanticipated problems. So use this escape hatch to disable per-CPU var BTF info on those problematic pahole versions. Users relying on availability of per-CPU var BTFs would need to upgrade to pahole 1.22+, but everyone won't notice any regressions. Link: https://lkml.kernel.org/r/20210530002536.3193829-1-andrii@kernel.orgSigned-off-by:
Andrii Nakryiko <andrii@kernel.org> Acked-by:
-
Heiner Kallweit authored
Having such debug messages in the dmesg log may confuse users. Therefore restrict debug output to cases where DEBUG is defined or dynamic debugging is enabled for the respective code piece. Link: https://lkml.kernel.org/r/976adb93-3041-ce63-48fc-55a6096a51c1@gmail.comSigned-off-by:
Heiner Kallweit <hkallweit1@gmail.com> Signed-off-by:
-
