- 01 Jul, 2021 40 commits
-
-
Yang Shi authored
A quick grep shows x86_64, PowerPC (book3s), ARM64 and S390 support both NUMA balancing and THP. But S390 doesn't support THP migration so NUMA balancing actually can't migrate any misplaced pages. Skip make PMD PROT_NONE for such case otherwise CPU cycles may be wasted by pointless NUMA hinting faults on S390. Link: https://lkml.kernel.org/r/20210518200801.7413-8-shy828301@gmail.comSigned-off-by:
Yang Shi <shy828301@gmail.com> Acked-by:
Mel Gorman <mgorman@suse.de> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Hugh Dickins <hughd@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Yang Shi authored
The generic migration path will check refcount, so no need check refcount here. But the old code actually prevents from migrating shared THP (mapped by multiple processes), so bail out early if mapcount is > 1 to keep the behavior. Link: https://lkml.kernel.org/r/20210518200801.7413-7-shy828301@gmail.comSigned-off-by:
-
Yang Shi authored
The old behavior didn't split THP if migration is failed due to lack of memory on the target node. But the THP migration does split THP, so keep the old behavior for misplaced NUMA page migration. Link: https://lkml.kernel.org/r/20210518200801.7413-6-shy828301@gmail.comSigned-off-by:
-
Yang Shi authored
Now both base page and THP NUMA migration is done via migrate_misplaced_page(), keep the counters correctly for THP. Link: https://lkml.kernel.org/r/20210518200801.7413-5-shy828301@gmail.comSigned-off-by:
-
Yang Shi authored
When the THP NUMA fault support was added THP migration was not supported yet. So the ad hoc THP migration was implemented in NUMA fault handling. Since v4.14 THP migration has been supported so it doesn't make too much sense to still keep another THP migration implementation rather than using the generic migration code. This patch reworks the NUMA fault handling to use generic migration implementation to migrate misplaced page. There is no functional change. After the refactor the flow of NUMA fault handling looks just like its PTE counterpart: Acquire ptl Prepare for migration (elevate page refcount) Release ptl Isolate page from lru and elevate page refcount Migrate the misplaced THP If migration fails just restore the old normal PMD. In the old code anon_vma lock was needed to serialize THP migration against THP split, but since then the THP code has been reworked a lot, it seems anon_vma lock is not required anymore to avoid the race. The page refcount elevation when holding ptl should prevent from THP split. Use migrate_misplaced_page() for both base page and THP NUMA hinting fault and remove all the dead and duplicate code. [dan.carpenter@oracle.com: fix a double unlock bug] Link: https://lkml.kernel.org/r/YLX8uYN01JmfLnlK@mwanda Link: https://lkml.kernel.org/r/20210518200801.7413-4-shy828301@gmail.comSigned-off-by:
Dan Carpenter <dan.carpenter@oracle.com> Acked-by:
-
Yang Shi authored
The numa_migrate_prep() will be used by huge NUMA fault as well in the following patch, make it non-static. Link: https://lkml.kernel.org/r/20210518200801.7413-3-shy828301@gmail.comSigned-off-by:
-
Yang Shi authored
Pach series "mm: thp: use generic THP migration for NUMA hinting fault", v3. When the THP NUMA fault support was added THP migration was not supported yet. So the ad hoc THP migration was implemented in NUMA fault handling. Since v4.14 THP migration has been supported so it doesn't make too much sense to still keep another THP migration implementation rather than using the generic migration code. It is definitely a maintenance burden to keep two THP migration implementation for different code paths and it is more error prone. Using the generic THP migration implementation allows us remove the duplicate code and some hacks needed by the old ad hoc implementation. A quick grep shows x86_64, PowerPC (book3s), ARM64 ans S390 support both THP and NUMA balancing. The most of them support THP migration except for S390. Zi Yan tried to add THP migration support for S390 before but it was not accepted due to the design of S390 PMD. For the discussion, please see: https://lkml.org/lkml/2018/4/27/953. Per the discussion with Gerald Schaefer in v1 it is acceptible to skip huge PMD for S390 for now. I saw there were some hacks about gup from git history, but I didn't figure out if they have been removed or not since I just found FOLL_NUMA code in the current gup implementation and they seems useful. Patch #1 ~ #2 are preparation patches. Patch #3 is the real meat. Patch #4 ~ #6 keep consistent counters and behaviors with before. Patch #7 skips change huge PMD to prot_none if thp migration is not supported. Test ---- Did some tests to measure the latency of do_huge_pmd_numa_page. The test VM has 80 vcpus and 64G memory. The test would create 2 processes to consume 128G memory together which would incur memory pressure to cause THP splits. And it also creates 80 processes to hog cpu, and the memory consumer processes are bound to different nodes periodically in order to increase NUMA faults. The below test script is used: echo 3 > /proc/sys/vm/drop_caches # Run stress-ng for 24 hours ./stress-ng/stress-ng --vm 2 --vm-bytes 64G --timeout 24h & PID=$! ./stress-ng/stress-ng --cpu $NR_CPUS --timeout 24h & # Wait for vm stressors forked sleep 5 PID_1=`pgrep -P $PID | awk 'NR == 1'` PID_2=`pgrep -P $PID | awk 'NR == 2'` JOB1=`pgrep -P $PID_1` JOB2=`pgrep -P $PID_2` # Bind load jobs to different nodes periodically to force generate # cross node memory access while [ -d "/proc/$PID" ] do taskset -apc 8 $JOB1 taskset -apc 8 $JOB2 sleep 300 taskset -apc 58 $JOB1 taskset -apc 58 $JOB2 sleep 300 done With the above test the histogram of latency of do_huge_pmd_numa_page is as shown below. Since the number of do_huge_pmd_numa_page varies drastically for each run (should be due to scheduler), so I converted the raw number to percentage. patched base @us[stress-ng]: [0] 3.57% 0.16% [1] 55.68% 18.36% [2, 4) 10.46% 40.44% [4, 8) 7.26% 17.82% [8, 16) 21.12% 13.41% [16, 32) 1.06% 4.27% [32, 64) 0.56% 4.07% [64, 128) 0.16% 0.35% [128, 256) < 0.1% < 0.1% [256, 512) < 0.1% < 0.1% [512, 1K) < 0.1% < 0.1% [1K, 2K) < 0.1% < 0.1% [2K, 4K) < 0.1% < 0.1% [4K, 8K) < 0.1% < 0.1% [8K, 16K) < 0.1% < 0.1% [16K, 32K) < 0.1% < 0.1% [32K, 64K) < 0.1% < 0.1% Per the result, patched kernel is even slightly better than the base kernel. I think this is because the lock contention against THP split is less than base kernel due to the refactor. To exclude the affect from THP split, I also did test w/o memory pressure. No obvious regression is spotted. The below is the test result *w/o* memory pressure. patched base @us[stress-ng]: [0] 7.97% 18.4% [1] 69.63% 58.24% [2, 4) 4.18% 2.63% [4, 8) 0.22% 0.17% [8, 16) 1.03% 0.92% [16, 32) 0.14% < 0.1% [32, 64) < 0.1% < 0.1% [64, 128) < 0.1% < 0.1% [128, 256) < 0.1% < 0.1% [256, 512) 0.45% 1.19% [512, 1K) 15.45% 17.27% [1K, 2K) < 0.1% < 0.1% [2K, 4K) < 0.1% < 0.1% [4K, 8K) < 0.1% < 0.1% [8K, 16K) 0.86% 0.88% [16K, 32K) < 0.1% 0.15% [32K, 64K) < 0.1% < 0.1% [64K, 128K) < 0.1% < 0.1% [128K, 256K) < 0.1% < 0.1% The series also survived a series of tests that exercise NUMA balancing migrations by Mel. This patch (of 7): Add orig_pmd to struct vm_fault so the "orig_pmd" parameter used by huge page fault could be removed, just like its PTE counterpart does. Link: https://lkml.kernel.org/r/20210518200801.7413-1-shy828301@gmail.com Link: https://lkml.kernel.org/r/20210518200801.7413-2-shy828301@gmail.comSigned-off-by:
-
Collin Fijalkovich authored
Transparent huge pages are supported for read-only non-shmem files, but are only used for vmas with VM_DENYWRITE. This condition ensures that file THPs are protected from writes while an application is running (ETXTBSY). Any existing file THPs are then dropped from the page cache when a file is opened for write in do_dentry_open(). Since sys_mmap ignores MAP_DENYWRITE, this constrains the use of file THPs to vmas produced by execve(). Systems that make heavy use of shared libraries (e.g. Android) are unable to apply VM_DENYWRITE through the dynamic linker, preventing them from benefiting from the resultant reduced contention on the TLB. This patch reduces the constraint on file THPs allowing use with any executable mapping from a file not opened for write (see inode_is_open_for_write()). It also introduces additional conditions to ensure that files opened for write will never be backed by file THPs. Restricting the use of THPs to executable mappings eliminates the risk that a read-only file later opened for write would encounter significant latencies due to page cache truncation. The ld linker flag '-z max-page-size=(hugepage size)' can be used to produce executables with the necessary layout. The dynamic linker must map these file's segments at a hugepage size aligned vma for the mapping to be backed with THPs. Comparison of the performance characteristics of 4KB and 2MB-backed libraries follows; the Android dex2oat tool was used to AOT compile an example application on a single ARM core. 4KB Pages: ========== count event_name # count / runtime 598,995,035,942 cpu-cycles # 1.800861 GHz 81,195,620,851 raw-stall-frontend # 244.112 M/sec 347,754,466,597 iTLB-loads # 1.046 G/sec 2,970,248,900 iTLB-load-misses # 0.854122% miss rate Total test time: 332.854998 seconds. 2MB Pages: ========== count event_name # count / runtime 592,872,663,047 cpu-cycles # 1.800358 GHz 76,485,624,143 raw-stall-frontend # 232.261 M/sec 350,478,413,710 iTLB-loads # 1.064 G/sec 803,233,322 iTLB-load-misses # 0.229182% miss rate Total test time: 329.826087 seconds A check of /proc/$(pidof dex2oat64)/smaps shows THPs in use: /apex/com.android.art/lib64/libart.so FilePmdMapped: 4096 kB /apex/com.android.art/lib64/libart-compiler.so FilePmdMapped: 2048 kB Link: https://lkml.kernel.org/r/20210406000930.3455850-1-cfijalkovich@google.comSigned-off-by:Collin Fijalkovich <cfijalkovich@google.com> Acked-by:
Hugh Dickins <hughd@google.com> Reviewed-by:
William Kucharski <william.kucharski@oracle.com> Acked-by:
Song Liu <song@kernel.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Hridya Valsaraju <hridya@google.com> Cc: Kalesh Singh <kaleshsingh@google.com> Cc: Tim Murray <timmurray@google.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Signed-off-by:
-
Muchun Song authored
Since commit d6995da3 ("hugetlb: use page.private for hugetlb specific page flags") converts page.private for hugetlb specific page flags. We should use hugetlb_page_subpool() to get the subpool pointer instead of page_private(). This 'could' prevent the migration of hugetlb pages. page_private(hpage) is now used for hugetlb page specific flags. At migration time, the only flag which could be set is HPageVmemmapOptimized. This flag will only be set if the new vmemmap reduction feature is enabled. In addition, !page_mapping() implies an anonymous mapping. So, this will prevent migration of hugetb pages in anonymous mappings if the vmemmap reduction feature is enabled. In addition, that if statement checked for the rare race condition of a page being migrated while in the process of being freed. Since that check is now wrong, we could leak hugetlb subpool usage counts. The commit forgot to update it in the page migration routine. So fix it. [songmuchun@bytedance.com: fix compiler error when !CONFIG_HUGETLB_PAGE reported by Randy] Link: https://lkml.kernel.org/r/20210521022747.35736-1-songmuchun@bytedance.com Link: https://lkml.kernel.org/r/20210520025949.1866-1-songmuchun@bytedance.com Fixes: d6995da3 ("hugetlb: use page.private for hugetlb specific page flags") Signed-off-by:
Muchun Song <songmuchun@bytedance.com> Reported-by:
Anshuman Khandual <anshuman.khandual@arm.com> Reviewed-by:
Mike Kravetz <mike.kravetz@oracle.com> Acked-by:
Michal Hocko <mhocko@suse.com> Tested-by: Anshuman Khandual <anshuman.khandual@arm.com> [arm64] Cc: Oscar Salvador <osalvador@suse.de> Cc: David Hildenbrand <david@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Xiongchun Duan <duanxiongchun@bytedance.com> Signed-off-by:
-
Anshuman Khandual authored
CONFIG_SPARSEMEM_VMEMMAP is now the only available memory model on arm64 platforms and free_unused_memmap() would just return without creating any holes in the memmap mapping. There is no need for any special handling in pfn_valid() and HAVE_ARCH_PFN_VALID can just be dropped. This also moves the pfn upper bits sanity check into generic pfn_valid(). Link: https://lkml.kernel.org/r/1621947349-25421-1-git-send-email-anshuman.khandual@arm.comSigned-off-by:
David Hildenbrand <david@redhat.com> Acked-by:
Mike Rapoport <rppt@linux.ibm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will@kernel.org> Cc: David Hildenbrand <david@redhat.com> Cc: Mike Rapoport <rppt@kernel.org> Signed-off-by:
-
Mike Rapoport authored
The arm64's version of pfn_valid() differs from the generic because of two reasons: * Parts of the memory map are freed during boot. This makes it necessary to verify that there is actual physical memory that corresponds to a pfn which is done by querying memblock. * There are NOMAP memory regions. These regions are not mapped in the linear map and until the previous commit the struct pages representing these areas had default values. As the consequence of absence of the special treatment of NOMAP regions in the memory map it was necessary to use memblock_is_map_memory() in pfn_valid() and to have pfn_valid_within() aliased to pfn_valid() so that generic mm functionality would not treat a NOMAP page as a normal page. Since the NOMAP regions are now marked as PageReserved(), pfn walkers and the rest of core mm will treat them as unusable memory and thus pfn_valid_within() is no longer required at all and can be disabled on arm64. pfn_valid() can be slightly simplified by replacing memblock_is_map_memory() with memblock_is_memory(). [rppt@kernel.org: fix merge fix] Link: https://lkml.kernel.org/r/YJtoQhidtIJOhYsV@kernel.org Link: https://lkml.kernel.org/r/20210511100550.28178-5-rppt@kernel.orgSigned-off-by:
Ard Biesheuvel <ardb@kernel.org> Reviewed-by:
Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Will Deacon <will@kernel.org> Signed-off-by:
-
Mike Rapoport authored
The intended semantics of pfn_valid() is to verify whether there is a struct page for the pfn in question and nothing else. Yet, on arm64 it is used to distinguish memory areas that are mapped in the linear map vs those that require ioremap() to access them. Introduce a dedicated pfn_is_map_memory() wrapper for memblock_is_map_memory() to perform such check and use it where appropriate. Using a wrapper allows to avoid cyclic include dependencies. While here also update style of pfn_valid() so that both pfn_valid() and pfn_is_map_memory() declarations will be consistent. Link: https://lkml.kernel.org/r/20210511100550.28178-4-rppt@kernel.orgSigned-off-by:
-
Mike Rapoport authored
The struct pages representing a reserved memory region are initialized using reserve_bootmem_range() function. This function is called for each reserved region just before the memory is freed from memblock to the buddy page allocator. The struct pages for MEMBLOCK_NOMAP regions are kept with the default values set by the memory map initialization which makes it necessary to have a special treatment for such pages in pfn_valid() and pfn_valid_within(). Split out initialization of the reserved pages to a function with a meaningful name and treat the MEMBLOCK_NOMAP regions the same way as the reserved regions and mark struct pages for the NOMAP regions as PageReserved. Link: https://lkml.kernel.org/r/20210511100550.28178-3-rppt@kernel.orgSigned-off-by:
-
Mike Rapoport authored
Patch series "arm64: drop pfn_valid_within() and simplify pfn_valid()", v4. These patches aim to remove CONFIG_HOLES_IN_ZONE and essentially hardwire pfn_valid_within() to 1. The idea is to mark NOMAP pages as reserved in the memory map and restore the intended semantics of pfn_valid() to designate availability of struct page for a pfn. With this the core mm will be able to cope with the fact that it cannot use NOMAP pages and the holes created by NOMAP ranges within MAX_ORDER blocks will be treated correctly even without the need for pfn_valid_within. This patch (of 4): Add comment describing the semantics of pfn_valid() that clarifies that pfn_valid() only checks for availability of a memory map entry (i.e. struct page) for a PFN rather than availability of usable memory backing that PFN. The most "generic" version of pfn_valid() used by the configurations with SPARSEMEM enabled resides in include/linux/mmzone.h so this is the most suitable place for documentation about semantics of pfn_valid(). Link: https://lkml.kernel.org/r/20210511100550.28178-1-rppt@kernel.org Link: https://lkml.kernel.org/r/20210511100550.28178-2-rppt@kernel.orgSigned-off-by:
-
Ben Widawsky authored
Current structure 'mempolicy' uses a union to store the node info for bind/interleave/perfer policies. union { short preferred_node; /* preferred */ nodemask_t nodes; /* interleave/bind */ /* undefined for default */ } v; Since preferred node can also be represented by a nodemask_t with only ont bit set, unify these policies with using one nodemask_t 'nodes', which can remove a union, simplify the code and make it easier to support future's new policy's node info. Link: https://lore.kernel.org/r/20200630212517.308045-7-ben.widawsky@intel.com Link: https://lkml.kernel.org/r/1623399825-75651-1-git-send-email-feng.tang@intel.comCo-developed-by:Feng Tang <feng.tang@intel.com> Signed-off-by:
Ben Widawsky <ben.widawsky@intel.com> Signed-off-by:
-
Yang Shi authored
When trying to migrate pages to obey mempolicy, the huge zero page is split by inserting base zero pfn to all PTEs, then the page table walk fallback to PTE level and just skips zero page. Skipping zero page for mempolicy has been the behavior of kernel since v2.6.16 due to commit f4598c8b ("[PATCH] migration: make sure there is no attempt to migrate reserved pages."). So it seems pointless to split huge zero page, it could be just skipped like base zero page. Set ACTION_CONTINUE to prevent the walk_page_range() split the pmd for this case. Link: https://lkml.kernel.org/r/20210609172146.3594-1-shy828301@gmail.com Link: https://lkml.kernel.org/r/20210604203513.240709-1-shy828301@gmail.comSigned-off-by:
Zi Yan <ziy@nvidia.com> Acked-by:
-
Feng Tang authored
Currently the kernel_mbind() and kernel_set_mempolicy() do almost the same operation for parameter sanity check. Add a helper function to unify the code to reduce the redundancy, and make it easier for changing the sanity check code in future. [thanks to David Rientjes for suggesting using helper function instead of macro]. [feng.tang@intel.com: add comment] Link: https://lkml.kernel.org/r/1622560492-1294-4-git-send-email-feng.tang@intel.com Link: https://lkml.kernel.org/r/1622469956-82897-4-git-send-email-feng.tang@intel.comSigned-off-by:
-
Feng Tang authored
MPOL_LOCAL policy has been setup as a real policy, but it is still handled like a faked POL_PREFERRED policy with one internal MPOL_F_LOCAL flag bit set, and there are many places having to judge the real 'prefer' or the 'local' policy, which are quite confusing. In current code, there are 4 cases that MPOL_LOCAL are used: 1. user specifies 'local' policy 2. user specifies 'prefer' policy, but with empty nodemask 3. system 'default' policy is used 4. 'prefer' policy + valid 'preferred' node with MPOL_F_STATIC_NODES flag set, and when it is 'rebind' to a nodemask which doesn't contains the 'preferred' node, it will perform as 'local' policy So make 'local' a real policy instead of a fake 'prefer' one, and kill MPOL_F_LOCAL bit, which can greatly reduce the confusion for code reading. For case 4, the logic of mpol_rebind_preferred() is confusing, as Michal Hocko pointed out: : I do believe that rebinding preferred policy is just bogus and it should : be dropped altogether on the ground that a preference is a mere hint from : userspace where to start the allocation. Unless I am missing something : cpusets will be always authoritative for the final placement. The : preferred node just acts as a starting point and it should be really : preserved when cpusets changes. Otherwise we have a very subtle behavior : corner cases. So dump all the tricky transformation between 'prefer' and 'local', and just record the new nodemask of rebinding. [feng.tang@intel.com: fix a problem in mpol_set_nodemask(), per Michal Hocko] Link: https://lkml.kernel.org/r/1622560492-1294-3-git-send-email-feng.tang@intel.com [feng.tang@intel.com: refine code and comments of mpol_set_nodemask(), per Michal] Link: https://lkml.kernel.org/r/20210603081807.GE56979@shbuild999.sh.intel.com Link: https://lkml.kernel.org/r/1622469956-82897-3-git-send-email-feng.tang@intel.comSigned-off-by:
-
Feng Tang authored
Patch series "mm/mempolicy: some fix and semantics cleanup", v4. Current memory policy code has some confusing and ambiguous part about MPOL_LOCAL policy, as it is handled as a faked MPOL_PREFERRED one, and there are many places having to distinguish them. Also the nodemask intersection check needs cleanup to be more explicit for OOM use, and handle MPOL_INTERLEAVE correctly. This patchset cleans up these and unifies the parameter sanity check for mbind() and set_mempolicy(). This patch (of 3): mempolicy_nodemask_intersects seem to be a general purpose mempolicy function. In fact it is partially tailored for the OOM purpose instead. The oom proper is the only existing user so rename the function to make that purpose explicit. While at it drop the MPOL_INTERLEAVE as those allocations never has a nodemask defined (see alloc_page_interleave) so this is a dead code and a confusing one because MPOL_INTERLEAVE is a hint rather than a hard requirement so it shouldn't be considered during the OOM. The final code can be reduced to a check for MPOL_BIND which is the only memory policy that is a hard requirement and thus relevant to a constrained OOM logic. [mhocko@suse.com: changelog edits] Link: https://lkml.kernel.org/r/1622560492-1294-1-git-send-email-feng.tang@intel.com Link: https://lkml.kernel.org/r/1622560492-1294-2-git-send-email-feng.tang@intel.com Link: https://lkml.kernel.org/r/1622469956-82897-1-git-send-email-feng.tang@intel.com Link: https://lkml.kernel.org/r/1622469956-82897-2-git-send-email-feng.tang@intel.comSigned-off-by:
-
Wonhyuk Yang authored
Because of 'min(1, ...)', fast_isolate_freepages set 'limit' to 0 or 1. This takes away the opportunities of find candinate pages. So, by making enough scans available, increases the probability of finding the appropriate freepage. Tested it on the thpscale and the results are as follows. 5.12.0 5.12.0 valnilla patched Amean fault-both-1 598.15 ( 0.00%) 592.56 ( 0.93%) Amean fault-both-3 1494.47 ( 0.00%) 1514.35 ( -1.33%) Amean fault-both-5 2519.48 ( 0.00%) 2471.76 ( 1.89%) Amean fault-both-7 3173.85 ( 0.00%) 3079.19 ( 2.98%) Amean fault-both-12 8063.83 ( 0.00%) 7858.29 ( 2.55%) Amean fault-both-18 8781.20 ( 0.00%) 7827.70 * 10.86%* Amean fault-both-24 12576.44 ( 0.00%) 12250.20 ( 2.59%) Amean fault-both-30 18503.27 ( 0.00%) 17528.11 * 5.27%* Amean fault-both-32 16133.69 ( 0.00%) 13874.24 * 14.00%* 5.12.0 5.12.0 vanilla patched Ops Compaction migrate scanned 6547133.00 5963901.00 Ops Compaction free scanned 32452453.00 26609101.00 5.12 5.12 vanilla patched Duration User 27.99 28.84 Duration System 244.08 236.76 Duration Elapsed 78.27 78.38 Link: https://lkml.kernel.org/r/20210626082443.22547-1-vvghjk1234@gmail.com Fixes: 5a811889 ("mm, compaction: use free lists to quickly locate a migration target") Signed-off-by:Wonhyuk Yang <vvghjk1234@gmail.com> Acked-by:
Mel Gorman <mgorman@techsingularity.net> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by:
-
Liu Xiang authored
The list_splice_tail(&sublist, freelist) also do !list_empty(&sublist) check, so remove the duplicate call. Link: https://lkml.kernel.org/r/20210609095409.19920-1-liu.xiang@zlingsmart.comSigned-off-by:
Liu Xiang <liu.xiang@zlingsmart.com> Reviewed-by:
-
YueHaibing authored
Use DEVICE_ATTR_WO helper instead of plain DEVICE_ATTR, which makes the code a bit shorter and easier to read. Link: https://lkml.kernel.org/r/20210523064521.32912-1-yuehaibing@huawei.comSigned-off-by:
YueHaibing <yuehaibing@huawei.com> Reviewed-by:
-
Miaohe Lin authored
The zbud doesn't need to export any API and it is meant to be used via zpool API since the commit 12d79d64 ("mm/zpool: update zswap to use zpool"). So we can remove the unneeded zbud.h and move down zpool API to avoid any forward declaration. [linmiaohe@huawei.com: fix unused function warnings when CONFIG_ZPOOL is disabled] Link: https://lkml.kernel.org/r/20210619025508.1239386-1-linmiaohe@huawei.com Link: https://lkml.kernel.org/r/20210608114515.206992-3-linmiaohe@huawei.comSigned-off-by:
Miaohe Lin <linmiaohe@huawei.com> Cc: Dan Streetman <ddstreet@ieee.org> Cc: Seth Jennings <sjenning@redhat.com> Cc: Nathan Chancellor <nathan@kernel.org> Signed-off-by:
-
Miaohe Lin authored
Patch series "Cleanups for zbud", v2. This series contains just cleanups to save some possible memory in zbud_pool and avoid exporting any unneeded zbud API. More details can be found in the respective changelogs This patch (of 2): Since commit 9d8c5b52 ("mm: zbud: fix condition check on allocation size"), zbud_pool.unbuddied[0] is always unused. We can reuse it as buddied field to save some possible memory. Link: https://lkml.kernel.org/r/20210608114515.206992-1-linmiaohe@huawei.com Link: https://lkml.kernel.org/r/20210608114515.206992-2-linmiaohe@huawei.comSigned-off-by:
-
Miaohe Lin authored
We should use release_z3fold_page_locked() to release z3fold page when it's locked, although it looks harmless to use release_z3fold_page() now. Link: https://lkml.kernel.org/r/20210619093151.1492174-7-linmiaohe@huawei.com Fixes: dcf5aedb ("z3fold: stricter locking and more careful reclaim") Signed-off-by:
Vitaly Wool <vitaly.wool@konsulko.com> Cc: Hillf Danton <hdanton@sina.com> Signed-off-by:
-
Miaohe Lin authored
There is a memory leak in z3fold_destroy_pool() as it forgets to free_percpu pool->unbuddied. Call free_percpu for pool->unbuddied to fix this issue. Link: https://lkml.kernel.org/r/20210619093151.1492174-6-linmiaohe@huawei.com Fixes: d30561c5 ("z3fold: use per-cpu unbuddied lists") Signed-off-by:
-
Miaohe Lin authored
handle_to_z3fold_header() is unused now. So we can remove it. As a result, get_z3fold_header() becomes the only caller of __get_z3fold_header() and the argument lock is always true. Therefore we could further fold the __get_z3fold_header() into get_z3fold_header() with lock = true. Link: https://lkml.kernel.org/r/20210619093151.1492174-5-linmiaohe@huawei.comSigned-off-by:
-
Miaohe Lin authored
It's meaningless to pass a magic number 2 to __alloc_percpu() as there is a minimum alignment size of PCPU_MIN_ALLOC_SIZE (> 2) in it. Also there is no special alignment requirement for unbuddied. So we could replace this magic number with nature alignment, i.e. __alignof__(struct list_head), to improve readability. Link: https://lkml.kernel.org/r/20210619093151.1492174-4-linmiaohe@huawei.comSigned-off-by:
-
Miaohe Lin authored
It is not enough to just make sure the z3fold header is not larger than the page size. When z3fold header is equal to PAGE_SIZE, we would underflow when check alloc size against PAGE_SIZE - ZHDR_SIZE_ALIGNED - CHUNK_SIZE in z3fold_alloc(). Make sure there has remaining spaces for its buddy to fix this theoretical issue. Link: https://lkml.kernel.org/r/20210619093151.1492174-3-linmiaohe@huawei.comSigned-off-by:
-
Miaohe Lin authored
Patch series "Cleanup and fixup for z3fold". This series contains cleanups to remove unused function, redefine macro to improve readability and so on. Also this fixes several bugs in z3fold, such as memory leak in z3fold_destroy_pool(). More details can be found in the respective changelogs. This patch (of 6): To improve code readability, we could define macro NCHUNKS as TOTAL_CHUNKS - ZHDR_CHUNKS. No functional change intended. Link: https://lkml.kernel.org/r/20210619093151.1492174-1-linmiaohe@huawei.com Link: https://lkml.kernel.org/r/20210619093151.1492174-2-linmiaohe@huawei.comSigned-off-by:
-
David Hildenbrand authored
Let's properly synchronize with drivers that set PageOffline(). Unfreeze/thaw every now and then, so drivers that want to set PageOffline() can make progress. Link: https://lkml.kernel.org/r/20210526093041.8800-7-david@redhat.comSigned-off-by:
Oscar Salvador <osalvador@suse.de> Cc: Aili Yao <yaoaili@kingsoft.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Alex Shi <alex.shi@linux.alibaba.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Jiri Bohac <jbohac@suse.cz> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Roman Gushchin <guro@fb.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Steven Price <steven.price@arm.com> Cc: Wei Liu <wei.liu@kernel.org> Signed-off-by:
-
David Hildenbrand authored
Let's properly use page_offline_(start|end) to synchronize setting PageOffline(), so we won't have valid page access to unplugged memory regions from /proc/kcore. Existing balloon implementations usually allow reading inflated memory; doing so might result in unnecessary overhead in the hypervisor, which is currently the case with virtio-mem. For future virtio-mem use cases, it will be different when using shmem, huge pages, !anonymous private mappings, ... as backing storage for a VM. virtio-mem unplugged memory must no longer be accessed and access might result in undefined behavior. There will be a virtio spec extension to document this change, including a new feature flag indicating the changed behavior. We really don't want to race against PFN walkers reading random page content. Link: https://lkml.kernel.org/r/20210526093041.8800-6-david@redhat.comSigned-off-by:
Michael S. Tsirkin <mst@redhat.com> Acked-by:
-
David Hildenbrand authored
A driver might set a page logically offline -- PageOffline() -- and turn the page inaccessible in the hypervisor; after that, access to page content can be fatal. One example is virtio-mem; while unplugged memory -- marked as PageOffline() can currently be read in the hypervisor, this will no longer be the case in the future; for example, when having a virtio-mem device backed by huge pages in the hypervisor. Some special PFN walkers -- i.e., /proc/kcore -- read content of random pages after checking PageOffline(); however, these PFN walkers can race with drivers that set PageOffline(). Let's introduce page_offline_(begin|end|freeze|thaw) for synchronizing. page_offline_freeze()/page_offline_thaw() allows for a subsystem to synchronize with such drivers, achieving that a page cannot be set PageOffline() while frozen. page_offline_begin()/page_offline_end() is used by drivers that care about such races when setting a page PageOffline(). For simplicity, use a rwsem for now; neither drivers nor users are performance sensitive. Link: https://lkml.kernel.org/r/20210526093041.8800-5-david@redhat.comSigned-off-by:
-
David Hildenbrand authored
Let's avoid reading: 1) Offline memory sections: the content of offline memory sections is stale as the memory is effectively unused by the kernel. On s390x with standby memory, offline memory sections (belonging to offline storage increments) are not accessible. With virtio-mem and the hyper-v balloon, we can have unavailable memory chunks that should not be accessed inside offline memory sections. Last but not least, offline memory sections might contain hwpoisoned pages which we can no longer identify because the memmap is stale. 2) PG_offline pages: logically offline pages that are documented as "The content of these pages is effectively stale. Such pages should not be touched (read/write/dump/save) except by their owner.". Examples include pages inflated in a balloon or unavailble memory ranges inside hotplugged memory sections with virtio-mem or the hyper-v balloon. 3) PG_hwpoison pages: Reading pages marked as hwpoisoned can be fatal. As documented: "Accessing is not safe since it may cause another machine check. Don't touch!" Introduce is_page_hwpoison(), adding a comment that it is inherently racy but best we can really do. Reading /proc/kcore now performs similar checks as when reading /proc/vmcore for kdump via makedumpfile: problematic pages are exclude. It's also similar to hibernation code, however, we don't skip hwpoisoned pages when processing pages in kernel/power/snapshot.c:saveable_page() yet. Note 1: we can race against memory offlining code, especially memory going offline and getting unplugged: however, we will properly tear down the identity mapping and handle faults gracefully when accessing this memory from kcore code. Note 2: we can race against drivers setting PageOffline() and turning memory inaccessible in the hypervisor. We'll handle this in a follow-up patch. Link: https://lkml.kernel.org/r/20210526093041.8800-4-david@redhat.comSigned-off-by:
-
David Hildenbrand authored
Let's resturcture the code, using switch-case, and checking pfn_is_ram() only when we are dealing with KCORE_RAM. Link: https://lkml.kernel.org/r/20210526093041.8800-3-david@redhat.comSigned-off-by:
-
David Hildenbrand authored
Patch series "fs/proc/kcore: don't read offline sections, logically offline pages and hwpoisoned pages", v3. Looking for places where the kernel might unconditionally read PageOffline() pages, I stumbled over /proc/kcore; turns out /proc/kcore needs some more love to not touch some other pages we really don't want to read -- i.e., hwpoisoned ones. Examples for PageOffline() pages are pages inflated in a balloon, memory unplugged via virtio-mem, and partially-present sections in memory added by the Hyper-V balloon. When reading pages inflated in a balloon, we essentially produce unnecessary load in the hypervisor; holes in partially present sections in case of Hyper-V are not accessible and already were a problem for /proc/vmcore, fixed in makedumpfile by detecting PageOffline() pages. In the future, virtio-mem might disallow reading unplugged memory -- marked as PageOffline() -- in some environments, resulting in undefined behavior when accessed; therefore, I'm trying to identify and rework all these (corner) cases. With this series, there is really only access via /dev/mem, /proc/vmcore and kdb left after I ripped out /dev/kmem. kdb is an advanced corner-case use case -- we won't care for now if someone explicitly tries to do nasty things by reading from/writing to physical addresses we better not touch. /dev/mem is a use case we won't support for virtio-mem, at least for now, so we'll simply disallow mapping any virtio-mem memory via /dev/mem next. /proc/vmcore is really only a problem when dumping the old kernel via something that's not makedumpfile (read: basically never), however, we'll try sanitizing that as well in the second kernel in the future. Tested via kcore_dump: https://github.com/schlafwandler/kcore_dump This patch (of 6): Commit db779ef6 ("proc/kcore: Remove unused kclist_add_remap()") removed the last user of KCORE_REMAP. Commit 595dd46e ("vfs/proc/kcore, x86/mm/kcore: Fix SMAP fault when dumping vsyscall user page") removed the last user of KCORE_OTHER. Let's drop both types. While at it, also drop vaddr in "struct kcore_list", used by KCORE_REMAP only. Link: https://lkml.kernel.org/r/20210526093041.8800-1-david@redhat.com Link: https://lkml.kernel.org/r/20210526093041.8800-2-david@redhat.comSigned-off-by:
-
Mike Rapoport authored
Add a paragraph that explains that it may happen that the counters in /proc/meminfo do not add up to the overall memory usage. Link: https://lkml.kernel.org/r/20210421061127.1182723-1-rppt@kernel.orgSigned-off-by:
Matthew Wilcox (Oracle) <willy@infradead.org> Acked-by:
Vlastimil Babka <vbabka@suse.cz> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by:
-
Kefeng Wang authored
commit a55749639dc1 ("ia64: drop marked broken DISCONTIGMEM and VIRTUAL_MEM_MAP") drop VIRTUAL_MEM_MAP, so there is no need HOLES_IN_ZONE on ia64. Also move HOLES_IN_ZONE into mm/Kconfig, select it if architecture needs this feature. Link: https://lkml.kernel.org/r/20210417075946.181402-1-wangkefeng.wang@huawei.comSigned-off-by: -
Miaohe Lin authored
The magic number 1 is used in several places in workingset.c. Define a macro WORKINGSET_SHIFT for it to improve code readability. Link: https://lkml.kernel.org/r/20210624122307.1759342-1-linmiaohe@huawei.comSigned-off-by:
-
Yu Zhao authored
mm_vmscan_inactive_list_is_low has no users after commit b91ac374 ("mm: vmscan: enforce inactive:active ratio at the reclaim root"). Remove it. Link: https://lkml.kernel.org/r/20210614194554.2683395-1-yuzhao@google.comSigned-off-by:
Yu Zhao <yuzhao@google.com> Acked-by:
Johannes Weiner <hannes@cmpxchg.org> Signed-off-by:
-
