On Sun, 17 May 2026 09:54:02 -0400 Zi Yan <[email protected]> wrote: > Hi all, > > This patchset removes READ_ONLY_THP_FOR_FS Kconfig and enables creating > file-backed THPs for FSes with large folio support (the supported orders > need to include PMD_ORDER) by default, including for writable files.
Cool. Sashiko wasn't able to apply this (presumably because of Mike's CI-friendly series). I take it that the AI review from v5 (https://sashiko.dev/#/patchset/[email protected]) was considered? Also, please check that the below were considered: https://lore.kernel.org/[email protected] https://lore.kernel.org/[email protected] https://lore.kernel.org/[email protected] https://lore.kernel.org/[email protected] https://lore.kernel.org/[email protected] https://lore.kernel.org/[email protected] > is an in-place replacement of V5 in mm-new. It affects Mike Rapoport's > "make MM selftests more CI friendly", since "selftests/mm: khugepaged: > use kselftest framework" needs to be updated. I updated it and put it at > the end of this cover letter. Helpful, thanks. It was a little complicated because your email client messes with whitespace (it always has!), but I figured it out. > Changelog > === > >From V5[6]: > 1. added mapping_min_folio_order(mapping) <= PMD_ORDER check to > mapping_pmd_folio_support() in Patch 1 to correctly handle > filesystems whose minimum folio order exceeds PMD_ORDER. Also > improved the kernel-doc comment per David's suggestions. > > 2. cleaned up Patch 11 per David's review: use const for open_opt and > mmap_prot, remove mmap_opt (use MAP_SHARED for both read-only and > read-write mappings), inline file_fault_common() into separate > file_fault_read() and file_fault_write() functions, fix "read only" > typo to "read-only", update usage message to "with PMD-sized large > folio support". Also fixed run_vmtests.sh to use elif test_selected > thp for the SKIP case to avoid spurious [SKIP] output per Nico's > report. > > 3. revised stale comment in Patch 13: removed "There won't be new dirty > pages" and updated "khugepaged only works on read-only fd" to reflect > that writable files are now supported; merged the comment blocks per > David's suggestion. > Here's how v6 altered mm.git: include/linux/pagemap.h | 12 +++---- mm/khugepaged.c | 18 ++++------- tools/testing/selftests/mm/khugepaged.c | 35 ++++++++-------------- 3 files changed, 26 insertions(+), 39 deletions(-) --- a/include/linux/pagemap.h~b +++ a/include/linux/pagemap.h @@ -514,15 +514,15 @@ static inline bool mapping_large_folio_s } /** - * mapping_pmd_folio_support() - Check if a mapping support PMD-sized folio + * mapping_pmd_folio_support() - Check if a mapping supports PMD-sized folio * @mapping: The address_space * - * Some file supports large folio but does not support as large as PMD order. - * If a PMD-sized pagecache folio is attempted to be created on a filesystem, - * this check needs to be performed first. + * While some mappings support large folios, they might not support PMD-sized + * folios. This function checks whether a mapping supports PMD-sized folios. + * For example, khugepaged needs this information before attempting to + * collapsing THPs. * - * Return: true - PMD-sized folio is supported, false - PMD-sized folio is not - * supported. + * Return: True if PMD-sized folios are supported, otherwise false. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline bool mapping_pmd_folio_support(const struct address_space *mapping) --- a/mm/khugepaged.c~b +++ a/mm/khugepaged.c @@ -2342,23 +2342,19 @@ static enum scan_result collapse_file(st } else if (folio_test_dirty(folio)) { /* * This page is dirty because it hasn't - * been flushed since first write. There - * won't be new dirty pages. + * been flushed since first write. * - * Trigger async flush here and hope the - * writeback is done when khugepaged - * revisits this page. + * Trigger async flush for read-only files and + * hope the writeback is done when khugepaged + * revisits this page. Writable files can have + * their folios dirty at any time; blindly + * flushing them would cause undesirable + * system-wide writeback. * * This is a one-off situation. We are not * forcing writeback in loop. */ xas_unlock_irq(&xas); - /* - * Only flush for read-only files. Writable - * files can have their folios dirty at any - * time; blindly flushing them would cause - * undesirable system-wide writeback. - */ if (!inode_is_open_for_write(mapping->host)) filemap_flush(mapping); result = SCAN_PAGE_DIRTY_OR_WRITEBACK; --- a/tools/testing/selftests/mm/khugepaged.c~b +++ a/tools/testing/selftests/mm/khugepaged.c @@ -376,12 +376,11 @@ static bool anon_check_huge(void *addr, static void *file_setup_area_common(int nr_hpages, enum file_setup_ops setup) { + const int open_opt = setup == FILE_SETUP_READ_ONLY_FS ? O_RDONLY : O_RDWR; + const int mmap_prot = setup == FILE_SETUP_READ_ONLY_FS ? PROT_READ : (PROT_READ | PROT_WRITE); int fd; void *p; unsigned long size; - int open_opt = setup == FILE_SETUP_READ_ONLY_FS ? O_RDONLY : O_RDWR; - int mmap_prot = setup == FILE_SETUP_READ_ONLY_FS ? PROT_READ : (PROT_READ | PROT_WRITE); - int mmap_opt = setup == FILE_SETUP_READ_ONLY_FS ? MAP_PRIVATE : MAP_SHARED; unlink(finfo.path); /* Cleanup from previous failed tests */ printf("Creating %s for collapse%s...", finfo.path, @@ -414,7 +413,7 @@ static void *file_setup_area_common(int success("OK"); printf("Opening %s %s for collapse...", finfo.path, - setup == FILE_SETUP_READ_ONLY_FS ? "read only" : + setup == FILE_SETUP_READ_ONLY_FS ? "read-only" : setup == FILE_SETUP_READ_WRITE_FS_READ_DATA ? "read-write (read)" : "read-write (write)"); @@ -423,8 +422,7 @@ static void *file_setup_area_common(int perror("open()"); exit(EXIT_FAILURE); } - p = mmap(BASE_ADDR, size, mmap_prot, - mmap_opt, finfo.fd, 0); + p = mmap(BASE_ADDR, size, mmap_prot, MAP_SHARED, finfo.fd, 0); if (p == MAP_FAILED || p != BASE_ADDR) { perror("mmap()"); exit(EXIT_FAILURE); @@ -458,27 +456,17 @@ static void file_cleanup_area(void *p, u unlink(finfo.path); } -static void file_fault_common(void *p, unsigned long start, unsigned long end, - int madv_ops) +static void file_fault_read(void *p, unsigned long start, unsigned long end) { - if (madvise(((char *)p) + start, end - start, madv_ops)) { - if (madv_ops == MADV_POPULATE_READ) - perror("madvise(MADV_POPULATE_READ"); - else if (madv_ops == MADV_POPULATE_WRITE) - perror("madvise(MADV_POPULATE_WRITE"); + if (madvise(((char *)p) + start, end - start, MADV_POPULATE_READ)) { + perror("madvise(MADV_POPULATE_READ)"); exit(EXIT_FAILURE); } } -static void file_fault_read(void *p, unsigned long start, unsigned long end) -{ - file_fault_common(p, start, end, MADV_POPULATE_READ); -} - static void file_fault_read_and_flush(void *p, unsigned long start, unsigned long end) { - file_fault_common(p, start, end, MADV_POPULATE_READ); - + file_fault_read(p, start, end); /* * make folio clean, since dirty folios from read&write file are * rejected and not flushed @@ -488,7 +476,10 @@ static void file_fault_read_and_flush(vo static void file_fault_write(void *p, unsigned long start, unsigned long end) { - file_fault_common(p, start, end, MADV_POPULATE_WRITE); + if (madvise(((char *)p) + start, end - start, MADV_POPULATE_WRITE)) { + perror("madvise(MADV_POPULATE_WRITE)"); + exit(EXIT_FAILURE); + } } static bool file_check_huge(void *addr, int nr_hpages) @@ -1191,7 +1182,7 @@ static void usage(void) fprintf(stderr, "\t<mem_type>\t: [all|anon|file|shmem]\n"); fprintf(stderr, "\n\t\"file,all\" mem_type requires [dir] argument\n"); fprintf(stderr, "\n\t\"file,all\" mem_type requires a file system\n"); - fprintf(stderr, "\twith large folio support (order >= PMD order)\n"); + fprintf(stderr, "\twith PMD-sized large folio support\n"); fprintf(stderr, "\n\tif [dir] is a (sub)directory of a tmpfs mount, tmpfs must be\n"); fprintf(stderr, "\tmounted with huge=advise option for khugepaged tests to work\n"); fprintf(stderr, "\n\tSupported Options:\n"); _
