- 18 Jul, 2022 3 commits
-
-
Alex Sierra authored
Patch series "Add MEMORY_DEVICE_COHERENT for coherent device memory mapping", v9. This patch series introduces MEMORY_DEVICE_COHERENT, a type of memory owned by a device that can be mapped into CPU page tables like MEMORY_DEVICE_GENERIC and can also be migrated like MEMORY_DEVICE_PRIVATE. This patch series is mostly self-contained except for a few places where it needs to update other subsystems to handle the new memory type. System stability and performance are not affected according to our ongoing testing, including xfstests. How it works: The system BIOS advertises the GPU device memory (aka VRAM) as SPM (special purpose memory) in the UEFI system address map. The amdgpu driver registers the memory with devmap as MEMORY_DEVICE_COHERENT using devm_memremap_pages. The initial user for this hardware page migration capability is the Frontier supercomputer project. This functionality is not AMD-specific. We expect other GPU vendors to find this functionality useful, and possibly other hardware types in the future. Our test nodes in the lab are similar to the Frontier configuration, with .5 TB of system memory plus 256 GB of device memory split across 4 GPUs, all in a single coherent address space. Page migration is expected to improve application efficiency significantly. We will report empirical results as they become available. Coherent device type pages at gup are now migrated back to system memory if they are being pinned long-term (FOLL_LONGTERM). The reason is, that long-term pinning would interfere with the device memory manager owning the device-coherent pages (e.g. evictions in TTM). These series incorporate Alistair Popple patches to do this migration from pin_user_pages() calls. hmm_gup_test has been added to hmm-test to test different get user pages calls. This series includes handling of device-managed anonymous pages returned by vm_normal_pages. Although they behave like normal pages for purposes of mapping in CPU page tables and for COW, they do not support LRU lists, NUMA migration or THP. We also introduced a FOLL_LRU flag that adds the same behaviour to follow_page and related APIs, to allow callers to specify that they expect to put pages on an LRU list. This patch (of 14): is_pinnable_page() and folio_is_pinnable() are renamed to is_longterm_pinnable_page() and folio_is_longterm_pinnable() respectively. These functions are used in the FOLL_LONGTERM flag context. Link: https://lkml.kernel.org/r/20220715150521.18165-1-alex.sierra@amd.com Link: https://lkml.kernel.org/r/20220715150521.18165-2-alex.sierra@amd.comSigned-off-by:
Alex Sierra <alex.sierra@amd.com> Reviewed-by:
David Hildenbrand <david@redhat.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Felix Kuehling <Felix.Kuehling@amd.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org>
-
Kalpana Shetty authored
Add "protected_keys" tests to "run_vmtests.sh" would help run all VM related tests from a single shell script. [kalpana.shetty@amd.com: Shuah Khan's review comments incorporated, added -x executable check] Link: https://lkml.kernel.org/r/20220617202931.357-1-kalpana.shetty@amd.com Link: https://lkml.kernel.org/r/20220610090704.296-1-kalpana.shetty@amd.com Link: https://lkml.kernel.org/r/20220531102556.388-1-kalpana.shetty@amd.comSigned-off-by:
Kalpana Shetty <kalpana.shetty@amd.com> Cc: Shuah Khan <shuah@kernel.org> Signed-off-by:
-
SeongJae Park authored
damon_lru_sort_init() returns an error when damon_select_ops() fails without freeing 'ctx' which allocated before. This commit fixes the potential memory leak by freeing 'ctx' under the situation. Link: https://lkml.kernel.org/r/20220714170458.49727-1-sj@kernel.org Fixes: 40e983cc ("mm/damon: introduce DAMON-based LRU-lists Sorting") Signed-off-by:
SeongJae Park <sj@kernel.org> Signed-off-by:
-
- 04 Jul, 2022 37 commits
-
-
Adam Sindelar authored
The test va_128TBswitch.c expects to be able to pass mmap an address hint and length that cross the address 1<<47. On x86_64, this is not possible without 5-level page tables, so the test fails. The test is already only run on 64-bit powerpc and x86_64 archs, but this patch adds an additional check on x86_64 that skips the test if PG_TABLE_LEVELS < 5. There is precedent for checking /proc/config.gz in selftests, e.g. in selftests/firmware. Running the tests produces the desired output: sudo make -C tools/testing/selftests TARGETS=vm run_tests --------------------------- running ./va_128TBswitch.sh --------------------------- ./va_128TBswitch.sh: PG_TABLE_LEVELS=4, must be >= 5 to run this test [SKIP] ------------------------------- [adam@wowsignal.io: restrict the check to x86_64] Link: https://lkml.kernel.org/r/20220628163654.337600-1-adam@wowsignal.io [adam@wowsignal.io: fix formatting issues, rename "die" to "fail"] Link: https://lkml.kernel.org/r/20220701163030.415735-1-adam@wowsignal.io Link: https://lkml.kernel.org/r/20220627163912.5581-1-adam@wowsignal.ioSigned-off-by:
Adam Sindelar <adam@wowsignal.io> Cc: Adam Sindelar <ats@fb.com> Cc: David Vernet <void@manifault.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by:
-
Miaohe Lin authored
Transhuge swapcaches won't be freed in __collapse_huge_page_copy(). It's because release_pte_page() is not called for these pages and thus free_page_and_swap_cache can't grab the page lock. These pages won't be freed from swap cache even if we are the only user until next time reclaim. It shouldn't hurt indeed, but we could try to free these pages to save more memory for system. Link: https://lkml.kernel.org/r/20220625092816.4856-8-linmiaohe@huawei.comSigned-off-by:
Miaohe Lin <linmiaohe@huawei.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: NeilBrown <neilb@suse.de> Cc: Peter Xu <peterx@redhat.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Cc: Zach O'Keefe <zokeefe@google.com> Signed-off-by:
-
Miaohe Lin authored
The return value of khugepaged_add_pte_mapped_thp() is always 0 and also ignored. Remove it to clean up the code. Link: https://lkml.kernel.org/r/20220625092816.4856-7-linmiaohe@huawei.comSigned-off-by:
Zach O'Keefe <zokeefe@google.com> Reviewed-by:
Yang Shi <shy828301@gmail.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: NeilBrown <neilb@suse.de> Cc: Peter Xu <peterx@redhat.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by:
-
Miaohe Lin authored
Use helper macro __ATTR_RW to define the khugepaged attributes. Minor readability improvement. Link: https://lkml.kernel.org/r/20220625092816.4856-6-linmiaohe@huawei.comSigned-off-by:
-
Miaohe Lin authored
nr_none is always 0 for non-shmem case because the page can be read from the backend store. So when nr_none ! = 0, it must be in is_shmem case. Also only adjust the nrpages and uncharge shmem when nr_none != 0 to save cpu cycles. Link: https://lkml.kernel.org/r/20220625092816.4856-5-linmiaohe@huawei.comSigned-off-by:
-
Miaohe Lin authored
Fix some typos and tweak the code to meet codestyle. No functional change intended. Link: https://lkml.kernel.org/r/20220625092816.4856-4-linmiaohe@huawei.comSigned-off-by:
-
Miaohe Lin authored
When do_swap_page returns VM_FAULT_RETRY, we do not retry here and thus swap entry will remain in pagetable. This will result in later failure. So stop swapping in pages in this case to save cpu cycles. As A further optimization, mmap_lock is released when __collapse_huge_page_swapin() fails to avoid relocking mmap_lock. And "swapped_in++" is moved after error handling to make it more accurate. Link: https://lkml.kernel.org/r/20220625092816.4856-3-linmiaohe@huawei.comSigned-off-by:
-
Miaohe Lin authored
Patch series "A few cleanup patches for khugepaged", v2. This series contains a few cleaup patches to remove unneeded return value, use helper macro, fix typos and so on. More details can be found in the respective changelogs. This patch (of 7): If we reach here, khugepaged_scan_mm_slot() has already made sure that hugepage is enabled for shmem, via its call to hugepage_vma_check(). Remove this duplicated check. Link: https://lkml.kernel.org/r/20220625092816.4856-1-linmiaohe@huawei.com Link: https://lkml.kernel.org/r/20220625092816.4856-2-linmiaohe@huawei.comSigned-off-by:
-
XueBing Chen authored
there is an unexpected word 'a' in the comments that need to be dropped Link: https://lkml.kernel.org/r/24fbdae3.c86.1819a0f31b9.Coremail.chenxuebing@jari.cnSigned-off-by:
XueBing Chen <chenxuebing@jari.cn> Signed-off-by:
-
Qi Zheng authored
Commit e5251fd4 ("mm/hugetlb: introduce set_huge_swap_pte_at() helper") add set_huge_swap_pte_at() to handle swap entries on architectures that support hugepages consisting of contiguous ptes. And currently the set_huge_swap_pte_at() is only overridden by arm64. set_huge_swap_pte_at() provide a sz parameter to help determine the number of entries to be updated. But in fact, all hugetlb swap entries contain pfn information, so we can find the corresponding folio through the pfn recorded in the swap entry, then the folio_size() is the number of entries that need to be updated. And considering that users will easily cause bugs by ignoring the difference between set_huge_swap_pte_at() and set_huge_pte_at(). Let's handle swap entries in set_huge_pte_at() and remove the set_huge_swap_pte_at(), then we can call set_huge_pte_at() anywhere, which simplifies our coding. Link: https://lkml.kernel.org/r/20220626145717.53572-1-zhengqi.arch@bytedance.comSigned-off-by:
Qi Zheng <zhengqi.arch@bytedance.com> Acked-by:
Muchun Song <songmuchun@bytedance.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will@kernel.org> Signed-off-by:
-
Yang Yang authored
Not all systems use swap, so estimating available memory would help to prevent swapping or OOM of system that not use swap. And we need to reserve some page cache to prevent swapping or thrashing. If somebody is accessing the pages in pagecache, and if too much would be freed, most accesses might mean reading data from disk, i.e. thrashing. Link: https://lkml.kernel.org/r/20220623020833.972979-1-yang.yang29@zte.com.cnSigned-off-by:
Yang Yang <yang.yang29@zte.com.cn> Signed-off-by:
CGEL ZTE <cgel.zte@gmail.com> Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by:
-
Sergey Senozhatsky authored
Always use crypto_has_comp() so that crypto can lookup module, call usermodhelper to load the modules, wait for usermodhelper to finish and so on. Otherwise crypto will do all of these steps under CPU hot-plug lock and this looks like too much stuff to handle under the CPU hot-plug lock. Besides this can end up in a deadlock when usermodhelper triggers a code path that attempts to lock the CPU hot-plug lock, that zram already holds. An example of such deadlock: - path A. zram grabs CPU hot-plug lock, execs /sbin/modprobe from crypto and waits for modprobe to finish disksize_store zcomp_create __cpuhp_state_add_instance __cpuhp_state_add_instance_cpuslocked zcomp_cpu_up_prepare crypto_alloc_base crypto_alg_mod_lookup call_usermodehelper_exec wait_for_completion_killable do_wait_for_common schedule - path B. async work kthread that brings in scsi device. It wants to register CPUHP states at some point, and it needs the CPU hot-plug lock for that, which is owned by zram. async_run_entry_fn scsi_probe_and_add_lun scsi_mq_alloc_queue blk_mq_init_queue blk_mq_init_allocated_queue blk_mq_realloc_hw_ctxs __cpuhp_state_add_instance __cpuhp_state_add_instance_cpuslocked mutex_lock schedule - path C. modprobe sleeps, waiting for all aync works to finish. load_module do_init_module async_synchronize_full async_synchronize_cookie_domain schedule [senozhatsky@chromium.org: add comment] Link: https://lkml.kernel.org/r/20220624060606.1014474-1-senozhatsky@chromium.org Link: https://lkml.kernel.org/r/20220622023501.517125-1-senozhatsky@chromium.orgSigned-off-by:Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Signed-off-by:
-
Yun-Ze Li authored
Comments that mention mem_hotplug_end() are confusing as there is no function called mem_hotplug_end(). Fix them by replacing all the occurences of mem_hotplug_end() in the comments with mem_hotplug_done(). [akpm@linux-foundation.org: grammatical fixes] Link: https://lkml.kernel.org/r/20220620071516.1286101-1-p76091292@gs.ncku.edu.twSigned-off-by:
Yun-Ze Li <p76091292@gs.ncku.edu.tw> Cc: Souptick Joarder <jrdr.linux@gmail.com> Signed-off-by:
-
Vincent Whitchurch authored
Pss is the sum of the sizes of clean and dirty private pages, and the proportional sizes of clean and dirty shared pages: Private = Private_Dirty + Private_Clean Shared_Proportional = Shared_Dirty_Proportional + Shared_Clean_Proportional Pss = Private + Shared_Proportional The Shared*Proportional fields are not present in smaps, so it is not always possible to determine how much of the Pss is from dirty pages and how much is from clean pages. This information can be useful for measuring memory usage for the purpose of optimisation, since clean pages can usually be discarded by the kernel immediately while dirty pages cannot. The smaps routines in the kernel already have access to this data, so add a Pss_Dirty to show it to userspace. Pss_Clean is not added since it can be calculated from Pss and Pss_Dirty. Link: https://lkml.kernel.org/r/20220620081251.2928103-1-vincent.whitchurch@axis.comSigned-off-by:
Vincent Whitchurch <vincent.whitchurch@axis.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by:
-
Baolin Wang authored
According to previous discussion [1], there are so many levels of indenting to handle the hugetlb case when unmapping or migration. We can combine folio_test_anon() and huge_pmd_unshare() to save one level of indenting, by adding a local variable and moving the VM_BUG_ON() a little forward. No intended functional changes in this patch. [1] https://lore.kernel.org/all/0b986dc4-5843-3e2d-c2df-5a2e9f13e6ab@oracle.com/ Link: https://lkml.kernel.org/r/28414b1b96f095e838c1e548074f8e0fc70d78cf.1655724713.git.baolin.wang@linux.alibaba.comSigned-off-by:
Baolin Wang <baolin.wang@linux.alibaba.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Muchun Song <songmuchun@bytedance.com> Signed-off-by:
-
Miaohe Lin authored
Passing index to pte_offset_map_lock() directly so the below calculation can be avoided. Rename orig_pte to ptep as it's not changed. Also use helper is_swap_pte() to improve the readability. No functional change intended. [akpm@linux-foundation.org: reduce scope of `ptep'] Link: https://lkml.kernel.org/r/20220618090527.37843-1-linmiaohe@huawei.comSigned-off-by:
-
Muchun Song authored
commit 641844f5 ("mm/hugetlb: introduce minimum hugepage order") fixed a static checker warning and introduced a global variable minimum_order to fix the warning. However, the local variable in dissolve_free_huge_pages() can be initialized to huge_page_order(&default_hstate) to fix the warning. So remove minimum_order to simplify the code. Link: https://lkml.kernel.org/r/20220616033846.96937-1-songmuchun@bytedance.comSigned-off-by:
Oscar Salvador <osalvador@suse.de> Reviewed-by:
Mike Kravetz <mike.kravetz@oracle.com> Signed-off-by:
-
Muchun Song authored
For now, the feature of hugetlb_free_vmemmap is not compatible with the feature of memory_hotplug.memmap_on_memory, and hugetlb_free_vmemmap takes precedence over memory_hotplug.memmap_on_memory. However, someone wants to make memory_hotplug.memmap_on_memory takes precedence over hugetlb_free_vmemmap since memmap_on_memory makes it more likely to succeed memory hotplug in close-to-OOM situations. So the decision of making hugetlb_free_vmemmap take precedence is not wise and elegant. The proper approach is to have hugetlb_vmemmap.c do the check whether the section which the HugeTLB pages belong to can be optimized. If the section's vmemmap pages are allocated from the added memory block itself, hugetlb_free_vmemmap should refuse to optimize the vmemmap, otherwise, do the optimization. Then both kernel parameters are compatible. So this patch introduces VmemmapSelfHosted to mask any non-optimizable vmemmap pages. The hugetlb_vmemmap can use this flag to detect if a vmemmap page can be optimized. [songmuchun@bytedance.com: walk vmemmap page tables to avoid false-positive] Link: https://lkml.kernel.org/r/20220620110616.12056-3-songmuchun@bytedance.com Link: https://lkml.kernel.org/r/20220617135650.74901-3-songmuchun@bytedance.comSigned-off-by:
-
Muchun Song authored
Patch series "make hugetlb_optimize_vmemmap compatible with memmap_on_memory", v3. This series makes hugetlb_optimize_vmemmap compatible with memmap_on_memory. This patch (of 2): We are almost running out of section flags, only one bit is available in the worst case (powerpc with 256k pages). However, there are still some free bits (in ->section_mem_map) on other architectures (e.g. x86_64 has 10 bits available, arm64 has 8 bits available with worst case of 64K pages). We have hard coded those numbers in code, it is inconvenient to use those bits on other architectures except powerpc. So transfer those section flags to enumeration to make it easy to add new section flags in the future. Also, move SECTION_TAINT_ZONE_DEVICE into the scope of CONFIG_ZONE_DEVICE to save a bit on non-zone-device case. [songmuchun@bytedance.com: replace enum with defines per David] Link: https://lkml.kernel.org/r/20220620110616.12056-2-songmuchun@bytedance.com Link: https://lkml.kernel.org/r/20220617135650.74901-1-songmuchun@bytedance.com Link: https://lkml.kernel.org/r/20220617135650.74901-2-songmuchun@bytedance.comSigned-off-by:
-
Matthew Wilcox (Oracle) authored
All callers now have a folio, so convert the entire function to operate on folios. Link: https://lkml.kernel.org/r/20220617175020.717127-23-willy@infradead.orgSigned-off-by:
Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by:
-
Matthew Wilcox (Oracle) authored
All but one caller already has a folio, so convert it to use a folio. Link: https://lkml.kernel.org/r/20220617175020.717127-22-willy@infradead.orgSigned-off-by:
-
Matthew Wilcox (Oracle) authored
The only caller already has a folio, so push the folio->page conversion down a level. Link: https://lkml.kernel.org/r/20220617175020.717127-21-willy@infradead.orgSigned-off-by:
-
Matthew Wilcox (Oracle) authored
All callers now have a folio, so push the folio->page conversion down to this function. [akpm@linux-foundation.org: uninline destroy_large_folio() to fix build issue] Link: https://lkml.kernel.org/r/20220617175020.717127-20-willy@infradead.orgSigned-off-by:
-
Matthew Wilcox (Oracle) authored
All the callers now have a folio. Saves several calls to compound_head, totalling 502 bytes of text. Link: https://lkml.kernel.org/r/20220617175020.717127-19-willy@infradead.orgSigned-off-by:
-
Matthew Wilcox (Oracle) authored
All the callers now have a folio, so pass it in. This doesn't save any text, but it does save a call to compound_head() as folio_test_hugetlb() does not contain a call like PageHuge() does. Link: https://lkml.kernel.org/r/20220617175020.717127-18-willy@infradead.orgSigned-off-by:
-
Matthew Wilcox (Oracle) authored
Saves 56 bytes of text by removing a call to compound_head(). Link: https://lkml.kernel.org/r/20220617175020.717127-17-willy@infradead.orgSigned-off-by:
-
Matthew Wilcox (Oracle) authored
Saves 11 bytes of text by removing a check of PageTail. Link: https://lkml.kernel.org/r/20220617175020.717127-16-willy@infradead.orgSigned-off-by:
-
Matthew Wilcox (Oracle) authored
Pages linked through the LRU list cannot be tail pages as ->compound_head is in a union with one of the words of the list_head, and they cannot be ZONE_DEVICE pages as ->pgmap is in a union with the same word. Saves 60 bytes of text by removing a call to page_is_fake_head(). Link: https://lkml.kernel.org/r/20220617175020.717127-15-willy@infradead.orgSigned-off-by:
-
Matthew Wilcox (Oracle) authored
This function was already calling compound_head(), but now it can cache the result of calling compound_head() and avoid calling it again. Saves 299 bytes of text by avoiding various calls to compound_page() and avoiding checks of PageTail. Link: https://lkml.kernel.org/r/20220617175020.717127-14-willy@infradead.orgSigned-off-by:
-
Matthew Wilcox (Oracle) authored
Save a few calls to compound_head by converting the passed page to a folio. Reduces kernel text size by 74 bytes. Link: https://lkml.kernel.org/r/20220617175020.717127-13-willy@infradead.orgSigned-off-by:
-
Matthew Wilcox (Oracle) authored
Do the per-cpu dereferencing of the fbatches once which saves 14 bytes of text and several percpu relocations. Link: https://lkml.kernel.org/r/20220617175020.717127-12-willy@infradead.orgSigned-off-by:
-
Matthew Wilcox (Oracle) authored
The function is too long, so pull this complicated conditional out into cpu_needs_drain(). This ends up shrinking the text by 14 bytes, by allowing GCC to cache the result of calling per_cpu() instead of relocating each lookup individually. Link: https://lkml.kernel.org/r/20220617175020.717127-11-willy@infradead.orgSigned-off-by:
-
Matthew Wilcox (Oracle) authored
No change to generated code, but this struct no longer contains any pagevecs, and not all the folio batches it contains are lru. Link: https://lkml.kernel.org/r/20220617175020.717127-10-willy@infradead.orgSigned-off-by:
-
Matthew Wilcox (Oracle) authored
Rename it to just 'activate', saving 696 bytes of text from removals of compound_page() and the pagevec_lru_move_fn() infrastructure. Inline need_activate_page_drain() into its only caller. Link: https://lkml.kernel.org/r/20220617175020.717127-9-willy@infradead.orgSigned-off-by:
-
Matthew Wilcox (Oracle) authored
Using folios instead of pages removes several calls to compound_head(), shrinking the kernel by 1089 bytes of text. Link: https://lkml.kernel.org/r/20220617175020.717127-8-willy@infradead.orgSigned-off-by:
-
Matthew Wilcox (Oracle) authored
Using folios instead of pages shrinks deactivate_page() and lru_deactivate_fn() by 778 bytes between them. Link: https://lkml.kernel.org/r/20220617175020.717127-7-willy@infradead.orgSigned-off-by:
-
Matthew Wilcox (Oracle) authored
Use a folio throughout lru_deactivate_file_fn(), removing many hidden calls to compound_head(). Shrinks the kernel by 864 bytes of text. Link: https://lkml.kernel.org/r/20220617175020.717127-6-willy@infradead.orgSigned-off-by:
-
