From cee9a0c4e84db024d692d6b5c18f65465eb06905 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 1 Jun 2020 21:46:07 -0700 Subject: mm: move readahead prototypes from mm.h Patch series "Change readahead API", v11. This series adds a readahead address_space operation to replace the readpages operation. The key difference is that pages are added to the page cache as they are allocated (and then looked up by the filesystem) instead of passing them on a list to the readpages operation and having the filesystem add them to the page cache. It's a net reduction in code for each implementation, more efficient than walking a list, and solves the direct-write vs buffered-read problem reported by yu kuai at http://lkml.kernel.org/r/20200116063601.39201-1-yukuai3@huawei.com The only unconverted filesystems are those which use fscache. Their conversion is pending Dave Howells' rewrite which will make the conversion substantially easier. This should be completed by the end of the year. I want to thank the reviewers/testers; Dave Chinner, John Hubbard, Eric Biggers, Johannes Thumshirn, Dave Sterba, Zi Yan, Christoph Hellwig and Miklos Szeredi have done a marvellous job of providing constructive criticism. These patches pass an xfstests run on ext4, xfs & btrfs with no regressions that I can tell (some of the tests seem a little flaky before and remain flaky afterwards). This patch (of 25): The readahead code is part of the page cache so should be found in the pagemap.h file. force_page_cache_readahead is only used within mm, so move it to mm/internal.h instead. Remove the parameter names where they add no value, and rename the ones which were actively misleading. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Reviewed-by: John Hubbard Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski Reviewed-by: Johannes Thumshirn Cc: Chao Yu Cc: Cong Wang Cc: Darrick J. Wong Cc: Dave Chinner Cc: Eric Biggers Cc: Gao Xiang Cc: Jaegeuk Kim Cc: Joseph Qi Cc: Junxiao Bi Cc: Michal Hocko Cc: Zi Yan Cc: Miklos Szeredi Link: http://lkml.kernel.org/r/20200414150233.24495-1-willy@infradead.org Link: http://lkml.kernel.org/r/20200414150233.24495-2-willy@infradead.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index f3fe7371855c..92704fde6475 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2612,25 +2612,6 @@ extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf); int __must_check write_one_page(struct page *page); void task_dirty_inc(struct task_struct *tsk); -/* readahead.c */ -#define VM_READAHEAD_PAGES (SZ_128K / PAGE_SIZE) - -int force_page_cache_readahead(struct address_space *mapping, struct file *filp, - pgoff_t offset, unsigned long nr_to_read); - -void page_cache_sync_readahead(struct address_space *mapping, - struct file_ra_state *ra, - struct file *filp, - pgoff_t offset, - unsigned long size); - -void page_cache_async_readahead(struct address_space *mapping, - struct file_ra_state *ra, - struct file *filp, - struct page *pg, - pgoff_t offset, - unsigned long size); - extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); -- cgit v1.2.3 From 91429023342789a89f4b6ae95b47a7df71ab6d95 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Mon, 1 Jun 2020 21:48:27 -0700 Subject: mm/gup: introduce pin_user_pages_unlocked Introduce pin_user_pages_unlocked(), which is nearly identical to the get_user_pages_unlocked() that it wraps, except that it sets FOLL_PIN and rejects FOLL_GET. Signed-off-by: John Hubbard Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Cc: Andy Walls Cc: Mauro Carvalho Chehab Link: http://lkml.kernel.org/r/20200518012157.1178336-2-jhubbard@nvidia.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 92704fde6475..ebbb0acbeee2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1713,6 +1713,8 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); +long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, + struct page **pages, unsigned int gup_flags); int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); -- cgit v1.2.3 From d8626138009ba58ae2c22356966c2edaa1f1c3b5 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 1 Jun 2020 21:52:18 -0700 Subject: mm: add functions to track page directory modifications Patch series "mm: Get rid of vmalloc_sync_(un)mappings()", v3. After the recent issue with vmalloc and tracing code[1] on x86 and a long history of previous issues related to the vmalloc_sync_mappings() interface, I thought the time has come to remove it. Please see [2], [3], and [4] for some other issues in the past. The patches add tracking of page-table directory changes to the vmalloc and ioremap code. Depending on which page-table levels changes have been made, a new per-arch function is called: arch_sync_kernel_mappings(). On x86-64 with 4-level paging, this function will not be called more than 64 times in a systems runtime (because vmalloc-space takes 64 PGD entries which are only populated, but never cleared). As a side effect this also allows to get rid of vmalloc faults on x86, making it safe to touch vmalloc'ed memory in the page-fault handler. Note that this potentially includes per-cpu memory. This patch (of 7): Add page-table allocation functions which will keep track of changed directory entries. They are needed for new PGD, P4D, PUD, and PMD entries and will be used in vmalloc and ioremap code to decide whether any changes in the kernel mappings need to be synchronized between page-tables in the system. Signed-off-by: Joerg Roedel Signed-off-by: Andrew Morton Acked-by: Andy Lutomirski Acked-by: Peter Zijlstra (Intel) Cc: "H . Peter Anvin" Cc: Dave Hansen Cc: "Rafael J. Wysocki" Cc: Arnd Bergmann Cc: Steven Rostedt (VMware) Cc: Vlastimil Babka Cc: Michal Hocko Cc: Matthew Wilcox (Oracle) Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Christoph Hellwig Link: http://lkml.kernel.org/r/20200515140023.25469-1-joro@8bytes.org Link: http://lkml.kernel.org/r/20200515140023.25469-2-joro@8bytes.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index ebbb0acbeee2..fda41eb7f1c8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2091,13 +2091,54 @@ static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d, return (unlikely(p4d_none(*p4d)) && __pud_alloc(mm, p4d, address)) ? NULL : pud_offset(p4d, address); } + +static inline p4d_t *p4d_alloc_track(struct mm_struct *mm, pgd_t *pgd, + unsigned long address, + pgtbl_mod_mask *mod_mask) + +{ + if (unlikely(pgd_none(*pgd))) { + if (__p4d_alloc(mm, pgd, address)) + return NULL; + *mod_mask |= PGTBL_PGD_MODIFIED; + } + + return p4d_offset(pgd, address); +} + #endif /* !__ARCH_HAS_5LEVEL_HACK */ +static inline pud_t *pud_alloc_track(struct mm_struct *mm, p4d_t *p4d, + unsigned long address, + pgtbl_mod_mask *mod_mask) +{ + if (unlikely(p4d_none(*p4d))) { + if (__pud_alloc(mm, p4d, address)) + return NULL; + *mod_mask |= PGTBL_P4D_MODIFIED; + } + + return pud_offset(p4d, address); +} + static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))? NULL: pmd_offset(pud, address); } + +static inline pmd_t *pmd_alloc_track(struct mm_struct *mm, pud_t *pud, + unsigned long address, + pgtbl_mod_mask *mod_mask) +{ + if (unlikely(pud_none(*pud))) { + if (__pmd_alloc(mm, pud, address)) + return NULL; + *mod_mask |= PGTBL_PUD_MODIFIED; + } + + return pmd_offset(pud, address); +} #endif /* CONFIG_MMU */ #if USE_SPLIT_PTE_PTLOCKS @@ -2213,6 +2254,11 @@ static inline void pgtable_pte_page_dtor(struct page *page) ((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd))? \ NULL: pte_offset_kernel(pmd, address)) +#define pte_alloc_kernel_track(pmd, address, mask) \ + ((unlikely(pmd_none(*(pmd))) && \ + (__pte_alloc_kernel(pmd) || ({*(mask)|=PGTBL_PMD_MODIFIED;0;})))?\ + NULL: pte_offset_kernel(pmd, address)) + #if USE_SPLIT_PMD_PTLOCKS static struct page *pmd_to_page(pmd_t *pmd) -- cgit v1.2.3