- 12 Dec, 2022 40 commits
-
-
Sidhartha Kumar authored
Many hugetlb allocation helper functions have now been converting to folios, update their higher level callers to be compatible with folios. alloc_pool_huge_page is reorganized to avoid a smatch warning reporting the folio variable is uninitialized. [sidhartha.kumar@oracle.com: update alloc_and_dissolve_hugetlb_folio comments] Link: https://lkml.kernel.org/r/20221206233512.146535-1-sidhartha.kumar@oracle.com Link: https://lkml.kernel.org/r/20221129225039.82257-11-sidhartha.kumar@oracle.comSigned-off-by:
Sidhartha Kumar <sidhartha.kumar@oracle.com> Reported-by:
Wei Chen <harperchen1110@gmail.com> Suggested-by:
John Hubbard <jhubbard@nvidia.com> Suggested-by:
Rasmus Villemoes <linux@rasmusvillemoes.dk> Reviewed-by:
Mike Kravetz <mike.kravetz@oracle.com> Cc: David Hildenbrand <david@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Mina Almasry <almasrymina@google.com> Cc: Muchun Song <songmuchun@bytedance.com> Cc: Tarun Sahu <tsahu@linux.ibm.com> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org>
-
Sidhartha Kumar authored
Convert prep_new_huge_page() and __prep_compound_gigantic_page() to folios. Link: https://lkml.kernel.org/r/20221129225039.82257-10-sidhartha.kumar@oracle.comSigned-off-by:
-
Sidhartha Kumar authored
Convert callers of free_gigantic_page() to use folios, function is then renamed to free_gigantic_folio(). Link: https://lkml.kernel.org/r/20221129225039.82257-9-sidhartha.kumar@oracle.comSigned-off-by:
-
Sidhartha Kumar authored
Convert callers of enqueue_huge_page() to pass in a folio, function is renamed to enqueue_hugetlb_folio(). Link: https://lkml.kernel.org/r/20221129225039.82257-8-sidhartha.kumar@oracle.comSigned-off-by:
-
Sidhartha Kumar authored
Convert add_hugetlb_page() to take in a folio, also convert hugetlb_cma_page() to take in a folio. Link: https://lkml.kernel.org/r/20221129225039.82257-7-sidhartha.kumar@oracle.comSigned-off-by:
-
Sidhartha Kumar authored
Make more progress on converting the free_huge_page() destructor to operate on folios by converting update_and_free_page() to folios. Link: https://lkml.kernel.org/r/20221129225039.82257-6-sidhartha.kumar@oracle.com Signed-off-by: Sidhartha Kumar <sidhartha.kumar@oracle.com>\ Reviewed-by:
-
Sidhartha Kumar authored
Removes page_folio() call by converting callers to directly pass a folio into __remove_hugetlb_page(). Link: https://lkml.kernel.org/r/20221129225039.82257-5-sidhartha.kumar@oracle.comSigned-off-by:
-
Sidhartha Kumar authored
Removes compound_head() call by using a folio rather than a head page. Link: https://lkml.kernel.org/r/20221129225039.82257-4-sidhartha.kumar@oracle.comSigned-off-by:
-
Sidhartha Kumar authored
Convert page operations within __destroy_compound_gigantic_page() to the corresponding folio operations. Link: https://lkml.kernel.org/r/20221129225039.82257-3-sidhartha.kumar@oracle.comSigned-off-by:
-
Sidhartha Kumar authored
Patch series "convert core hugetlb functions to folios", v5. ============== OVERVIEW =========================== Now that many hugetlb helper functions that deal with hugetlb specific flags[1] and hugetlb cgroups[2] are converted to folios, higher level allocation, prep, and freeing functions within hugetlb can also be converted to operate in folios. Patch 1 of this series implements the wrapper functions around setting the compound destructor and compound order for a folio. Besides the user added in patch 1, patch 2 and patch 9 also use these helper functions. Patches 2-10 convert the higher level hugetlb functions to folios. ============== TESTING =========================== LTP: Ran 10 back to back rounds of the LTP hugetlb test suite. Gigantic Huge Pages: Test allocation and freeing via hugeadm commands: hugeadm --pool-pages-min 1GB:10 hugeadm --pool-pages-min 1GB:0 Demote: Demote 1 1GB hugepages to 512 2MB hugepages echo 1 > /sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages echo 1 > /sys/kernel/mm/hugepages/hugepages-1048576kB/demote cat /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages # 512 cat /sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages # 0 [1] https://lore.kernel.org/lkml/20220922154207.1575343-1-sidhartha.kumar@oracle.com/ [2] https://lore.kernel.org/linux-mm/20221101223059.460937-1-sidhartha.kumar@oracle.com/ This patch (of 10): Add folio equivalents for set_compound_order() and set_compound_page_dtor(). Also remove extra new-lines introduced by mm/hugetlb: convert move_hugetlb_state() to folios and mm/hugetlb_cgroup: convert hugetlb_cgroup_uncharge_page() to folios. [sidhartha.kumar@oracle.com: clarify folio_set_compound_order() zero support] Link: https://lkml.kernel.org/r/20221207223731.32784-1-sidhartha.kumar@oracle.com Link: https://lkml.kernel.org/r/20221129225039.82257-1-sidhartha.kumar@oracle.com Link: https://lkml.kernel.org/r/20221129225039.82257-2-sidhartha.kumar@oracle.comSigned-off-by:
Muchun Song <songmuchun@bytedance.com> Reviewed-by:
-
Vishal Moola (Oracle) authored
There are no longer any callers of lru_cache_add(), so remove it. This saves 79 bytes of kernel text. Also cleanup some comments such that they reference the new folio_add_lru() instead. Link: https://lkml.kernel.org/r/20221101175326.13265-6-vishal.moola@gmail.comSigned-off-by:
Vishal Moola (Oracle) <vishal.moola@gmail.com> Reviewed-by:
Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Miklos Szeredi <mszeredi@redhat.com> Signed-off-by:
-
Vishal Moola (Oracle) authored
Replaces some calls with their folio equivalents. This is in preparation for the removal of lru_cache_add(). This replaces 3 calls to compound_head() with 1. Link: https://lkml.kernel.org/r/20221101175326.13265-5-vishal.moola@gmail.comSigned-off-by:
-
Vishal Moola (Oracle) authored
Replaces lru_cache_add() and lru_cache_add_inactive_or_unevictable() with folio_add_lru() and folio_add_lru_vma(). This is in preparation for the removal of lru_cache_add(). Link: https://lkml.kernel.org/r/20221101175326.13265-4-vishal.moola@gmail.comSigned-off-by:
-
Vishal Moola (Oracle) authored
Converts the function to try to move folios instead of pages. Also converts fuse_check_page() to fuse_get_folio() since this is its only caller. This change removes 15 calls to compound_head(). Link: https://lkml.kernel.org/r/20221101175326.13265-3-vishal.moola@gmail.comSigned-off-by:
Miklos Szeredi <mszeredi@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Signed-off-by:
-
Vishal Moola (Oracle) authored
Patch series "Removing the lru_cache_add() wrapper". This patchset replaces all calls of lru_cache_add() with the folio equivalent: folio_add_lru(). This is allows us to get rid of the wrapper The series passes xfstests and the userfaultfd selftests. This patch (of 5): Eliminates 7 calls to compound_head(). Link: https://lkml.kernel.org/r/20221101175326.13265-1-vishal.moola@gmail.com Link: https://lkml.kernel.org/r/20221101175326.13265-2-vishal.moola@gmail.comSigned-off-by:
-
Feiyang Chen authored
The feature of minimizing overhead of struct page associated with each HugeTLB page is implemented on x86_64. However, the infrastructure of this feature is already there, so just select ARCH_WANT_HUGETLB_PAGE_ OPTIMIZE_VMEMMAP is enough to enable this feature for LoongArch. Link: https://lkml.kernel.org/r/20221027125253.3458989-5-chenhuacai@loongson.cnSigned-off-by:
Feiyang Chen <chenfeiyang@loongson.cn> Signed-off-by:
Huacai Chen <chenhuacai@loongson.cn> Reviewed-by:
Philippe Mathieu-Daudé <philmd@linaro.org> Acked-by:
Arnd Bergmann <arnd@arndb.de> Cc: Andy Lutomirski <luto@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Dinh Nguyen <dinguyen@kernel.org> Cc: Guo Ren <guoren@kernel.org> Cc: Jiaxun Yang <jiaxun.yang@flygoat.com> Cc: Min Zhou <zhoumin@loongson.cn> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Will Deacon <will@kernel.org> Cc: Xuefeng Li <lixuefeng@loongson.cn> Cc: Xuerui Wang <kernel@xen0n.name> Signed-off-by:
-
Feiyang Chen authored
Generalise vmemmap_populate_hugepages() so ARM64 & X86 & LoongArch can share its implementation. Link: https://lkml.kernel.org/r/20221027125253.3458989-4-chenhuacai@loongson.cnSigned-off-by:
Will Deacon <will@kernel.org> Acked-by:
Dave Hansen <dave.hansen@linux.intel.com> Reviewed-by:
-
Feiyang Chen authored
Add sparse memory vmemmap support for LoongArch. SPARSEMEM_VMEMMAP uses a virtually mapped memmap to optimise pfn_to_page and page_to_pfn operations. This is the most efficient option when sufficient kernel resources are available. Link: https://lkml.kernel.org/r/20221027125253.3458989-3-chenhuacai@loongson.cnSigned-off-by:
Min Zhou <zhoumin@loongson.cn> Signed-off-by:
-
Feiyang Chen authored
Patch series "mm/sparse-vmemmap: Generalise helpers and enable for LoongArch", v14. This series is in order to enable sparse-vmemmap for LoongArch. But LoongArch cannot use generic helpers directly because MIPS&LoongArch need to call pgd_init()/pud_init()/pmd_init() when populating page tables. So we adjust the prototypes of p?d_init() to make generic helpers can call them, then enable sparse-vmemmap with generic helpers, and to be further, generalise vmemmap_populate_hugepages() for ARM64, X86 and LoongArch. This patch (of 4): We are preparing to add sparse vmemmap support to LoongArch. MIPS and LoongArch need to call pgd_init()/pud_init()/pmd_init() when populating page tables, so adjust their prototypes to make generic helpers can call them. NIOS2 declares pmd_init() but doesn't use, just remove it to avoid build errors. Link: https://lkml.kernel.org/r/20221027125253.3458989-1-chenhuacai@loongson.cn Link: https://lkml.kernel.org/r/20221027125253.3458989-2-chenhuacai@loongson.cnSigned-off-by:
Jiaxun Yang <jiaxun.yang@flygoat.com> Reviewed-by:
-
Alexander Potapenko authored
In certain cases (e.g. when handling a softirq) __msan_instrument_asm_store(&var, sizeof(var)) may be called with from within KMSAN runtime, but later the value of @var is used with !kmsan_in_runtime(), leading to false positives. Because kmsan_internal_unpoison_memory() doesn't take locks, it should be fine to call it without kmsan_in_runtime() checks, which fixes the mentioned false positives. Link: https://lkml.kernel.org/r/20221128094541.2645890-2-glider@google.comSigned-off-by:
Alexander Potapenko <glider@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Eric Biggers <ebiggers@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Marco Elver <elver@google.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Will Deacon <will@kernel.org> Signed-off-by:
-
Alexander Potapenko authored
Lockdep and KMSAN used to play badly together, causing deadlocks when KMSAN instrumentation of lockdep.c called lockdep functions recursively. Looks like this is no more the case, and a kernel can run (yet slower) with both KMSAN and lockdep enabled. This patch should fix false positives on wq_head->lock->dep_map, which KMSAN used to consider uninitialized because of lockdep.c not being instrumented. Link: https://lore.kernel.org/lkml/Y3b9AAEKp2Vr3e6O@sol.localdomain/ Link: https://lkml.kernel.org/r/20221128094541.2645890-1-glider@google.comSigned-off-by:
Eric Biggers <ebiggers@kernel.org> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Marco Elver <elver@google.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Will Deacon <will@kernel.org> Signed-off-by:
-
zhang songyi authored
Return value from ptep_get_and_clear_full() directly instead of taking this in another redundant variable. Link: https://lkml.kernel.org/r/202211282107437343474@zte.com.cnSigned-off-by:
zhang songyi <zhang.songyi@zte.com.cn> Signed-off-by:
-
Brian Foster authored
generic_fadvise() sets endbyte = -1 to specify end of file (i.e. if length == 0 is passed from userspace). Most other callers to filemap_fdatawrite_range() use LLONG_MAX for this purpose, particularly if they also call fdatawait_range() (which requires end >= start). For example, sync_file_range(), vfs_fsync() (where the range is passed down through per-fs ->fsync() callbacks), filemap_flush(), etc. generic_fadvise() does not currently wait on writeback, but fix the call up to be consistent with other callers. Link: https://lkml.kernel.org/r/20221128155632.3950447-3-bfoster@redhat.comSigned-off-by:
Brian Foster <bfoster@redhat.com> Reviewed-by:
Christoph Hellwig <hch@lst.de> Signed-off-by:
-
Brian Foster authored
Patch series "filemap: skip write and wait if end offset precedes start", v2. A fix for the odd write and wait behavior described in the patch 1 commit log. Technically patch 1 could simply remove the check rather than lift it into the callers, but this seemed a bit more user friendly to me. Patch 2 is appended after observation that fadvise() interacted poorly with the v1 patch. This is no longer a problem with v2, making patch 2 purely a cleanup. This series survived both fstests and ltp regression runs without observable problems. I had (end < start) warning checks in each relevant function, with fadvise() being the only caller that triggered them. That said, I dropped the warnings after testing because there seemed to much potential for noise from the various other callers. This patch (of 2): A call to file[map]_write_and_wait_range() with an end offset that precedes the start offset but happens to land in the same page can trigger writeback submission but fails to wait on the submitted page. Writeback submission occurs because __filemap_fdatawrite_range() passes both offsets down into write_cache_pages(), which rounds down to page indexes before it starts processing writeback. However, __filemap_fdatawait_range() immediately returns if the byte-granular end offset precedes the start offset. This behavior was observed in the form of unpredictable latency from a frequent write and wait call with incorrect parameters. The behavior gave the impression that the fdatawait path might occasionally fail to wait on writeback, but further investigation showed the latency was from write_cache_pages() waiting on writeback state to clear for a page already under writeback. Therefore, this indicated that fdatawait actually never waits on writeback in this particular situation. The byte granular check in __filemap_fdatawait_range() goes all the way back to the old wait_on_page_writeback() helper. It originally used page offsets and so would have waited in this problematic case. That changed to byte granularity file offsets in commit 94004ed7 ("kill wait_on_page_writeback_range"), which subtly changed this behavior. The check itself has become somewhat redundant since the error checking code that used to follow the wait loop (at the time of the aforementioned commit) has now been removed and lifted into the higher level callers. Therefore, we can restore historical fdatawait behavior by simply removing the check. Since the current fdatawait behavior has been in place for quite some time and is consistent with other interfaces that use file offsets, instead lift the check into the file[map]_write_and_wait_range() helpers to provide consistent behavior between the write and wait. Link: https://lkml.kernel.org/r/20221128155632.3950447-1-bfoster@redhat.com Link: https://lkml.kernel.org/r/20221128155632.3950447-2-bfoster@redhat.comSigned-off-by:
-
Nhat Pham authored
This commit adds the writeback mechanism for zsmalloc, analogous to the zbud allocator. Zsmalloc will attempt to determine the coldest zspage (i.e least recently used) in the pool, and attempt to write back all the stored compressed objects via the pool's evict handler. Link: https://lkml.kernel.org/r/20221128191616.1261026-7-nphamcs@gmail.comSigned-off-by:
Nhat Pham <nphamcs@gmail.com> Acked-by:
Johannes Weiner <hannes@cmpxchg.org> Reviewed-by:
Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Dan Streetman <ddstreet@ieee.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Seth Jennings <sjenning@redhat.com> Cc: Vitaly Wool <vitaly.wool@konsulko.com> Signed-off-by:
-
Nhat Pham authored
This adds a new field to zs_pool to store evict handlers for writeback, analogous to the zbud allocator. Link: https://lkml.kernel.org/r/20221128191616.1261026-6-nphamcs@gmail.comSigned-off-by:
Minchan Kim <minchan@kernel.org> Acked-by:
-
Nhat Pham authored
This helps determines the coldest zspages as candidates for writeback. Link: https://lkml.kernel.org/r/20221128191616.1261026-5-nphamcs@gmail.comSigned-off-by:
-
Nhat Pham authored
Currently, zsmalloc has a hierarchy of locks, which includes a pool-level migrate_lock, and a lock for each size class. We have to obtain both locks in the hotpath in most cases anyway, except for zs_malloc. This exception will no longer exist when we introduce a LRU into the zs_pool for the new writeback functionality - we will need to obtain a pool-level lock to synchronize LRU handling even in zs_malloc. In preparation for zsmalloc writeback, consolidate these locks into a single pool-level lock, which drastically reduces the complexity of synchronization in zsmalloc. We have also benchmarked the lock consolidation to see the performance effect of this change on zram. First, we ran a synthetic FS workload on a server machine with 36 cores (same machine for all runs), using fs_mark -d ../zram1mnt -s 100000 -n 2500 -t 32 -k before and after for btrfs and ext4 on zram (FS usage is 80%). Here is the result (unit is file/second): With lock consolidation (btrfs): Average: 13520.2, Median: 13531.0, Stddev: 137.5961482019028 Without lock consolidation (btrfs): Average: 13487.2, Median: 13575.0, Stddev: 309.08283679298665 With lock consolidation (ext4): Average: 16824.4, Median: 16839.0, Stddev: 89.97388510006668 Without lock consolidation (ext4) Average: 16958.0, Median: 16986.0, Stddev: 194.7370021336469 As you can see, we observe a 0.3% regression for btrfs, and a 0.9% regression for ext4. This is a small, barely measurable difference in my opinion. For a more realistic scenario, we also tries building the kernel on zram. Here is the time it takes (in seconds): With lock consolidation (btrfs): real Average: 319.6, Median: 320.0, Stddev: 0.8944271909999159 user Average: 6894.2, Median: 6895.0, Stddev: 25.528415540334656 sys Average: 521.4, Median: 522.0, Stddev: 1.51657508881031 Without lock consolidation (btrfs): real Average: 319.8, Median: 320.0, Stddev: 0.8366600265340756 user Average: 6896.6, Median: 6899.0, Stddev: 16.04057355583023 sys Average: 520.6, Median: 521.0, Stddev: 1.140175425099138 With lock consolidation (ext4): real Average: 320.0, Median: 319.0, Stddev: 1.4142135623730951 user Average: 6896.8, Median: 6878.0, Stddev: 28.621670111997307 sys Average: 521.2, Median: 521.0, Stddev: 1.7888543819998317 Without lock consolidation (ext4) real Average: 319.6, Median: 319.0, Stddev: 0.8944271909999159 user Average: 6886.2, Median: 6887.0, Stddev: 16.93221781102523 sys Average: 520.4, Median: 520.0, Stddev: 1.140175425099138 The difference is entirely within the noise of a typical run on zram. This hardly justifies the complexity of maintaining both the pool lock and the class lock. In fact, for writeback, we would need to introduce yet another lock to prevent data races on the pool's LRU, further complicating the lock handling logic. IMHO, it is just better to collapse all of these into a single pool-level lock. Link: https://lkml.kernel.org/r/20221128191616.1261026-4-nphamcs@gmail.comSigned-off-by:
-
Johannes Weiner authored
There is a lot of provision for flexibility that isn't actually needed or used. Zswap (the only zpool user) always passes zpool_ops with an .evict method set. The backends who reclaim only do so for zswap, so they can also directly call zpool_ops without indirection or checks. Finally, there is no need to check the retries parameters and bail with -EINVAL in the reclaim function, when that's called just a few lines below with a hard-coded 8. There is no need to duplicate the evictable and sleep_mapped attrs from the driver in zpool_ops. Link: https://lkml.kernel.org/r/20221128191616.1261026-3-nphamcs@gmail.comReviewed-by:
-
Johannes Weiner authored
Patch series "Implement writeback for zsmalloc", v7. Unlike other zswap allocators such as zbud or z3fold, zsmalloc currently lacks the writeback mechanism. This means that when the zswap pool is full, it will simply reject further allocations, and the pages will be written directly to swap. This series of patches implements writeback for zsmalloc. When the zswap pool becomes full, zsmalloc will attempt to evict all the compressed objects in the least-recently used zspages. This patch (of 6): zswap's customary lock order is tree->lock before pool->lock, because the tree->lock protects the entries' refcount, and the free callbacks in the backends acquire their respective pool locks to dispatch the backing object. zsmalloc's map callback takes the pool lock, so zswap must not grab the tree->lock while a handle is mapped. This currently only happens during writeback, which isn't implemented for zsmalloc. In preparation for it, move the tree->lock section out of the mapped entry section Link: https://lkml.kernel.org/r/20221128191616.1261026-1-nphamcs@gmail.com Link: https://lkml.kernel.org/r/20221128191616.1261026-2-nphamcs@gmail.comSigned-off-by:
-
Pavankumar Kondeti authored
When MADV_PAGEOUT is called on a private file mapping VMA region, we bail out early if the process is neither owner nor write capable of the file. However, this VMA may have both private/shared clean pages and private dirty pages. The opportunity of paging out the private dirty pages (Anon pages) is missed. Fix this behavior by allowing private file mappings pageout further and perform the file access check along with PageAnon() during page walk. We observe ~10% improvement in zram usage, thus leaving more available memory on a 4GB RAM system running Android. [quic_pkondeti@quicinc.com: v2] Link: https://lkml.kernel.org/r/1669962597-27724-1-git-send-email-quic_pkondeti@quicinc.com Link: https://lkml.kernel.org/r/1667971116-12900-1-git-send-email-quic_pkondeti@quicinc.comSigned-off-by:
Pavankumar Kondeti <quic_pkondeti@quicinc.com> Cc: Charan Teja Kalla <quic_charante@quicinc.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: David Hildenbrand <david@redhat.com> Signed-off-by:
-
Gautam Menghani authored
"mm_khugepaged_collapse_file" for capturing is_shmem. Currently, is_shmem is not being captured. Capturing is_shmem is useful as it can indicate if tmpfs is being used as a backing store instead of persistent storage. Add the tracepoint in collapse_file() named "mm_khugepaged_collapse_file" for capturing is_shmem. [gautammenghani201@gmail.com: swap is_shmem and addr to save space, per Steven Rostedt] Link: https://lkml.kernel.org/r/20221202201807.182829-1-gautammenghani201@gmail.com Link: https://lkml.kernel.org/r/20221026052218.148234-1-gautammenghani201@gmail.comSigned-off-by:
Gautam Menghani <gautammenghani201@gmail.com> Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org> [tracing] Cc: David Hildenbrand <david@redhat.com> Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Zach O'Keefe <zokeefe@google.com> Signed-off-by:
-
David Hildenbrand authored
Fortunately, the last user (KSM) is gone, so let's just remove this rather special code from generic GUP handling -- especially because KSM never required the PMD handling as KSM only deals with individual base pages. [akpm@linux-foundation.org: fix merge snafu]Link: https://lkml.kernel.org/r/20221021101141.84170-10-david@redhat.comSigned-off-by:
David Hildenbrand <david@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Peter Xu <peterx@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by:
-
David Hildenbrand authored
FOLL_MIGRATION exists only for the purpose of break_ksm(), and actually, there is not even the need to wait for the migration to finish, we only want to know if we're dealing with a KSM page. Using follow_page() just to identify a KSM page overcomplicates GUP code. Let's use walk_page_range_vma() instead, because we don't actually care about the page itself, we only need to know a single property -- no need to even grab a reference. So, get rid of follow_page() usage such that we can get rid of FOLL_MIGRATION now and eventually be able to get rid of follow_page() in the future. In my setup (AMD Ryzen 9 3900X), running the KSM selftest to test unmerge performance on 2 GiB (taskset 0x8 ./ksm_tests -D -s 2048), this results in a performance degradation of ~2% (old: ~5010 MiB/s, new: ~4900 MiB/s). I don't think we particularly care for now. Interestingly, the benchmark reduction is due to the single callback. Adding a second callback (e.g., pud_entry()) reduces the benchmark by another 100-200 MiB/s. Link: https://lkml.kernel.org/r/20221021101141.84170-9-david@redhat.comSigned-off-by:
-
David Hildenbrand authored
Let's add walk_page_range_vma(), which is similar to walk_page_vma(), however, is only interested in a subset of the VMA range. To be used in KSM code to stop using follow_page() next. Link: https://lkml.kernel.org/r/20221021101141.84170-8-david@redhat.comSigned-off-by:
-
David Hildenbrand authored
Let's stop breaking COW via a fake write fault and let's use FAULT_FLAG_UNSHARE instead. This avoids any wrong side effects of the fake write fault, such as mapping the PTE writable and marking the pte dirty/softdirty. Consequently, we will no longer trigger a fake write fault and break COW without any such side-effects. Also, this fixes KSM interaction with userfaultfd-wp: when we have a KSM page that's write-protected by userfaultfd, break_ksm()->handle_mm_fault() will fail with VM_FAULT_SIGBUS and will simply return in break_ksm() with 0 instead of actually breaking COW. For now, the KSM unmerge tests can trigger that: $ sudo ./ksm_functional_tests TAP version 13 1..3 # [RUN] test_unmerge ok 1 Pages were unmerged # [RUN] test_unmerge_discarded ok 2 Pages were unmerged # [RUN] test_unmerge_uffd_wp not ok 3 Pages were unmerged Bail out! 1 out of 3 tests failed # Planned tests != run tests (2 != 3) # Totals: pass:2 fail:1 xfail:0 xpass:0 skip:0 error:0 The warning in dmesg also indicates this wrong handling: [ 230.096368] FAULT_FLAG_ALLOW_RETRY missing 881 [ 230.100822] CPU: 1 PID: 1643 Comm: ksm-uffd-wp [...] [ 230.110124] Hardware name: [...] [ 230.117775] Call Trace: [ 230.120227] <TASK> [ 230.122334] dump_stack_lvl+0x44/0x5c [ 230.126010] handle_userfault.cold+0x14/0x19 [ 230.130281] ? tlb_finish_mmu+0x65/0x170 [ 230.134207] ? uffd_wp_range+0x65/0xa0 [ 230.137959] ? _raw_spin_unlock+0x15/0x30 [ 230.141972] ? do_wp_page+0x50/0x590 [ 230.145551] __handle_mm_fault+0x9f5/0xf50 [ 230.149652] ? mmput+0x1f/0x40 [ 230.152712] handle_mm_fault+0xb9/0x2a0 [ 230.156550] break_ksm+0x141/0x180 [ 230.159964] unmerge_ksm_pages+0x60/0x90 [ 230.163890] ksm_madvise+0x3c/0xb0 [ 230.167295] do_madvise.part.0+0x10c/0xeb0 [ 230.171396] ? do_syscall_64+0x67/0x80 [ 230.175157] __x64_sys_madvise+0x5a/0x70 [ 230.179082] do_syscall_64+0x58/0x80 [ 230.182661] ? do_syscall_64+0x67/0x80 [ 230.186413] entry_SYSCALL_64_after_hwframe+0x63/0xcd This is primarily a fix for KSM+userfaultfd-wp, however, the fake write fault was always questionable. As this fix is not easy to backport and it's not very critical, let's not cc stable. Link: https://lkml.kernel.org/r/20221021101141.84170-6-david@redhat.com Fixes: 529b930b ("userfaultfd: wp: hook userfault handler to write protection fault") Signed-off-by:Peter Xu <peterx@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Shuah Khan <shuah@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by:
-
David Hildenbrand authored
All users -- GUP and KSM -- are gone, let's just remove it. Link: https://lkml.kernel.org/r/20221021101141.84170-4-david@redhat.comSigned-off-by:
-
David Hildenbrand authored
Now that GUP no longer requires VM_FAULT_WRITE, break_ksm() is the sole remaining user of VM_FAULT_WRITE. As we also want to stop triggering a fake write fault and instead use FAULT_FLAG_UNSHARE -- similar to GUP-triggered unsharing when taking a R/O pin on a shared anonymous page (including KSM pages), let's stop relying on VM_FAULT_WRITE. Let's rework break_ksm() to not rely on the return value of handle_mm_fault() anymore to figure out whether COW-breaking was successful. Simply perform another follow_page() lookup to verify the result. While this makes break_ksm() slightly less efficient, we can simplify handle_mm_fault() a little and easily switch to FAULT_FLAG_UNSHARE without introducing similar KSM-specific behavior for FAULT_FLAG_UNSHARE. In my setup (AMD Ryzen 9 3900X), running the KSM selftest to test unmerge performance on 2 GiB (taskset 0x8 ./ksm_tests -D -s 2048), this results in a performance degradation of ~4% -- 5% (old: ~5250 MiB/s, new: ~5010 MiB/s). I don't think that we particularly care about that performance drop when unmerging. If it ever turns out to be an actual performance issue, we can think about a better alternative for FAULT_FLAG_UNSHARE -- let's just keep it simple for now. Link: https://lkml.kernel.org/r/20221021101141.84170-3-david@redhat.comSigned-off-by:
-
David Hildenbrand authored
Let's add a test to measure performance of KSM breaking not triggered via COW, but triggered by disabling KSM on an area filled with KSM pages via MADV_UNMERGEABLE. Link: https://lkml.kernel.org/r/20221021101141.84170-2-david@redhat.comSigned-off-by:
-
David Hildenbrand authored
As Peter points out, the caller passes a single VMA and can just do that check itself. And in fact, no existing users rely on test_walk() getting called. So let's just remove it and make the implementation slightly more efficient. Link: https://lkml.kernel.org/r/20221021101141.84170-7-david@redhat.comSigned-off-by:
-
