kernel/linux.git/arch/um/include/asm/page.h, branch linux-7.0.y

treewide: provide a generic clear_user_page() variant

2026-01-21T03:24:39+00:00

Patch series "mm: folio_zero_user: clear page ranges", v11. This series adds clearing of contiguous page ranges for hugepages. The series improves on the current discontiguous clearing approach in two ways: - clear pages in a contiguous fashion. - use batched clearing via clear_pages() wherever exposed. The first is useful because it allows us to make much better use of hardware prefetchers. The second, enables advertising the real extent to the processor. Where specific instructions support it (ex. string instructions on x86; "mops" on arm64 etc), a processor can optimize based on this because, instead of seeing a sequence of 8-byte stores, or a sequence of 4KB pages, it sees a larger unit being operated on. For instance, AMD Zen uarchs (for extents larger than LLC-size) switch to a mode where they start eliding cacheline allocation. This is helpful not just because it results in higher bandwidth, but also because now the cache is not evicting useful cachelines and replacing them with zeroes. Demand faulting a 64GB region shows performance improvement: $ perf bench mem mmap -p $pg-sz -f demand -s 64GB -l 5 baseline +series (GBps +- %stdev) (GBps +- %stdev) pg-sz=2MB 11.76 +- 1.10% 25.34 +- 1.18% [*] +115.47% preempt=* pg-sz=1GB 24.85 +- 2.41% 39.22 +- 2.32% + 57.82% preempt=none|voluntary pg-sz=1GB (similar) 52.73 +- 0.20% [#] +112.19% preempt=full|lazy [*] This improvement is because switching to sequential clearing allows the hardware prefetchers to do a much better job. [#] For pg-sz=1GB a large part of the improvement is because of the cacheline elision mentioned above. preempt=full|lazy improves upon that because, not needing explicit invocations of cond_resched() to ensure reasonable preemption latency, it can clear the full extent as a single unit. In comparison the maximum extent used for preempt=none|voluntary is PROCESS_PAGES_NON_PREEMPT_BATCH (32MB). When provided the full extent the processor forgoes allocating cachelines on this path almost entirely. (The hope is that eventually, in the fullness of time, the lazy preemption model will be able to do the same job that none or voluntary models are used for, allowing us to do away with cond_resched().) Raghavendra also tested previous version of the series on AMD Genoa and sees similar improvement [1] with preempt=lazy. $ perf bench mem map -p $page-size -f populate -s 64GB -l 10 base patched change pg-sz=2MB 12.731939 GB/sec 26.304263 GB/sec 106.6% pg-sz=1GB 26.232423 GB/sec 61.174836 GB/sec 133.2% This patch (of 8): Let's drop all variants that effectively map to clear_page() and provide it in a generic variant instead. We'll use the macro clear_user_page to indicate whether an architecture provides it's own variant. Also, clear_user_page() is only called from the generic variant of clear_user_highpage(), so define it only if the architecture does not provide a clear_user_highpage(). And, for simplicity define it in linux/highmem.h. Note that for parisc, clear_page() and clear_user_page() map to clear_page_asm(), so we can just get rid of the custom clear_user_page() implementation. There is a clear_user_page_asm() function on parisc, that seems to be unused. Not sure what's up with that. Link: https://lkml.kernel.org/r/20260107072009.1615991-1-ankur.a.arora@oracle.com Link: https://lkml.kernel.org/r/20260107072009.1615991-2-ankur.a.arora@oracle.com Signed-off-by: David Hildenbrand Co-developed-by: Ankur Arora Signed-off-by: Ankur Arora Cc: Andy Lutomirski Cc: Ankur Arora Cc: "Borislav Petkov (AMD)" Cc: Boris Ostrovsky Cc: David Hildenbrand Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Konrad Rzessutek Wilk Cc: Lance Yang Cc: "Liam R. Howlett" Cc: Li Zhe Cc: Lorenzo Stoakes Cc: Mateusz Guzik Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Mike Rapoport Cc: Peter Zijlstra Cc: Raghavendra K T Cc: Suren Baghdasaryan Cc: Thomas Gleixner Cc: Vlastimil Babka Signed-off-by: Andrew Morton

x86/um: Drop gate area handling

2025-11-06T12:02:33+00:00

With the removal of the vDSO passthrough from the host, FIXADDR_USER_START is always 0 and the gate area setup code is dead. Remove it. Signed-off-by: Thomas Weißschuh Link: https://patch.msgid.link/20251028-uml-remove-32bit-pseudo-vdso-v1-5-e930063eff5f@weissschuh.net Signed-off-by: Johannes Berg

um: Replace ASSEMBLY with ASSEMBLER in the usermode headers

2025-07-22T15:12:45+00:00

While the GCC and Clang compilers already define __ASSEMBLER__ automatically when compiling assembly code, __ASSEMBLY__ is a macro that only gets defined by the Makefiles in the kernel. This can be very confusing when switching between userspace and kernelspace coding, so let's standardize on the __ASSEMBLER__ macro that is provided by the compilers now. This is a completely mechanical patch (done with a simple "sed -i" statement). Cc: Richard Weinberger Cc: Anton Ivanov Cc: Johannes Berg Cc: linux-um@lists.infradead.org Signed-off-by: Thomas Huth Link: https://patch.msgid.link/20250314071013.1575167-36-thuth@redhat.com Signed-off-by: Johannes Berg

Merge tag 'uml-for-linus-6.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/uml/linux

2024-11-30T18:34:54+00:00

Pull UML updates from Richard Weinberger: - Lots of cleanups, mostly from Benjamin Berg and Tiwei Bie - Removal of unused code - Fix for sparse warnings - Cleanup around stub_exe() * tag 'uml-for-linus-6.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/uml/linux: (68 commits) hostfs: Fix the NULL vs IS_ERR() bug for __filemap_get_folio() um: move thread info into task um: Always dump trace for specified task in show_stack um: vector: Do not use drvdata in release um: net: Do not use drvdata in release um: ubd: Do not use drvdata in release um: ubd: Initialize ubd's disk pointer in ubd_add um: virtio_uml: query the number of vqs if supported um: virtio_uml: fix call_fd IRQ allocation um: virtio_uml: send SET_MEM_TABLE message with the exact size um: remove broken double fault detection um: remove duplicate UM_NSEC_PER_SEC definition um: remove file sync for stub data um: always include kconfig.h and compiler-version.h um: set DONTDUMP and DONTFORK flags on KASAN shadow memory um: fix sparse warnings in signal code um: fix sparse warnings from regset refactor um: Remove double zero check um: fix stub exe build with CONFIG_GCOV um: Use os_set_pdeathsig helper in winch thread/process ...

um: Rename _PAGE_NEWPAGE to _PAGE_NEEDSYNC

2024-10-23T07:52:49+00:00

The _PAGE_NEWPAGE bit does not really indicate that this is a new page, but rather whether this entry needs to be synced or not. Renaming it to _PAGE_NEEDSYNC will make it more clear how everything ties together. Suggested-by: Benjamin Berg Signed-off-by: Tiwei Bie Link: https://patch.msgid.link/20241011102354.1682626-3-tiwei.btw@antgroup.com Signed-off-by: Johannes Berg

vdso: Introduce vdso/page.h

2024-10-15T22:13:04+00:00

The VDSO implementation includes headers from outside of the vdso/ namespace. Introduce vdso/page.h to make sure that the generic library uses only the allowed namespace. Signed-off-by: Vincenzo Frascino Signed-off-by: Thomas Gleixner Reviewed-by: Arnd Bergmann Acked-by: Geert Uytterhoeven # m68k Link: https://lore.kernel.org/all/20241014151340.1639555-3-vincenzo.frascino@arm.com

um: Switch to 4 level page tables on 64 bit

2024-10-10T11:37:22+00:00

The larger memory space is useful to support more applications inside UML. One example for this is ASAN instrumentation of userspace applications which requires addresses that would otherwise not be available. Signed-off-by: Benjamin Berg Link: https://patch.msgid.link/20240919124511.282088-11-benjamin@sipsolutions.net Signed-off-by: Johannes Berg

um: Remove 3-level page table support on i386

2024-10-10T10:06:43+00:00

The highmem support has been removed by commit a98a6d864d3b ("um: Remove broken highmem support"). The 2-level page table is sufficient on UML/i386 now. Remove the 3-level page table support on UML/i386 which is still marked as experimental. Suggested-by: Benjamin Berg Signed-off-by: Tiwei Bie Link: https://patch.msgid.link/20240918061702.614837-1-tiwei.btw@antgroup.com Signed-off-by: Johannes Berg

arch: define CONFIG_PAGE_SIZE_*KB on all architectures

2024-03-06T18:29:09+00:00

Most architectures only support a single hardcoded page size. In order to ensure that each one of these sets the corresponding Kconfig symbols, change over the PAGE_SHIFT definition to the common one and allow only the hardware page size to be selected. Acked-by: Guo Ren Acked-by: Heiko Carstens Acked-by: Stafford Horne Acked-by: Johannes Berg Acked-by: Geert Uytterhoeven Reviewed-by: Thomas Gleixner Signed-off-by: Arnd Bergmann

mm, arch: add generic implementation of pfn_valid() for FLATMEM

2023-02-10T00:51:41+00:00

Every architecture that supports FLATMEM memory model defines its own version of pfn_valid() that essentially compares a pfn to max_mapnr. Use mips/powerpc version implemented as static inline as a generic implementation of pfn_valid() and drop its per-architecture definitions. [rppt@kernel.org: fix the generic pfn_valid()] Link: https://lkml.kernel.org/r/Y9lg7R1Yd931C+y5@kernel.org Link: https://lkml.kernel.org/r/20230129124235.209895-5-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: Arnd Bergmann Acked-by: Guo Ren [csky] Acked-by: Huacai Chen [LoongArch] Acked-by: Stafford Horne [OpenRISC] Acked-by: Michael Ellerman [powerpc] Reviewed-by: David Hildenbrand Tested-by: Conor Dooley Cc: Brian Cain Cc: "David S. Miller" Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Greg Ungerer Cc: Helge Deller Cc: Huacai Chen Cc: Matt Turner Cc: Max Filippov Cc: Michal Simek Cc: Palmer Dabbelt Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Thomas Bogendoerfer Cc: Vineet Gupta Cc: WANG Xuerui Cc: Yoshinori Sato Signed-off-by: Andrew Morton