From 710ec38b0f633ab3e2581f07a73442d809e28ab0 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 23 Sep 2019 15:32:59 -0700 Subject: mm: add dummy can_do_mlock() helper On kernels without CONFIG_MMU, we get a link error for the siw driver: drivers/infiniband/sw/siw/siw_mem.o: In function `siw_umem_get': siw_mem.c:(.text+0x4c8): undefined reference to `can_do_mlock' This is probably not the only driver that needs the function and could otherwise build correctly without CONFIG_MMU, so add a dummy variant that always returns false. Link: http://lkml.kernel.org/r/20190909204201.931830-1-arnd@arndb.de Fixes: 2251334dcac9 ("rdma/siw: application buffer management") Signed-off-by: Arnd Bergmann Suggested-by: Jason Gunthorpe Acked-by: Michal Hocko Cc: Bernard Metzler Cc: "Matthew Wilcox (Oracle)" Cc: "Kirill A. Shutemov" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7cf955feb823..6e79b3df1582 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1405,7 +1405,11 @@ extern void pagefault_out_of_memory(void); extern void show_free_areas(unsigned int flags, nodemask_t *nodemask); +#ifdef CONFIG_MMU extern bool can_do_mlock(void); +#else +static inline bool can_do_mlock(void) { return false; } +#endif extern int user_shm_lock(size_t, struct user_struct *); extern void user_shm_unlock(size_t, struct user_struct *); -- cgit v1.2.3 From a50b854e073cd3335bbbada8dcff83a857297dd7 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 23 Sep 2019 15:34:25 -0700 Subject: mm: introduce page_size() Patch series "Make working with compound pages easier", v2. These three patches add three helpers and convert the appropriate places to use them. This patch (of 3): It's unnecessarily hard to find out the size of a potentially huge page. Replace 'PAGE_SIZE << compound_order(page)' with page_size(page). Link: http://lkml.kernel.org/r/20190721104612.19120-2-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Michal Hocko Reviewed-by: Andrew Morton Reviewed-by: Ira Weiny Acked-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6e79b3df1582..d46d5585e2a2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -805,6 +805,12 @@ static inline void set_compound_order(struct page *page, unsigned int order) page[1].compound_order = order; } +/* Returns the number of bytes in this potentially compound page. */ +static inline unsigned long page_size(struct page *page) +{ + return PAGE_SIZE << compound_order(page); +} + void free_compound_page(struct page *page); #ifdef CONFIG_MMU -- cgit v1.2.3 From 94ad9338109fe9d0b8a4a16828719dd6dcaee4c2 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 23 Sep 2019 15:34:28 -0700 Subject: mm: introduce page_shift() Replace PAGE_SHIFT + compound_order(page) with the new page_shift() function. Minor improvements in readability. [akpm@linux-foundation.org: fix build in tce_page_is_contained()] Link: http://lkml.kernel.org/r/201907241853.yNQTrJWd%25lkp@intel.com Link: http://lkml.kernel.org/r/20190721104612.19120-3-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Andrew Morton Reviewed-by: Ira Weiny Acked-by: Kirill A. Shutemov Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index d46d5585e2a2..9238548bdec5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -811,6 +811,12 @@ static inline unsigned long page_size(struct page *page) return PAGE_SIZE << compound_order(page); } +/* Returns the number of bits needed for the number of bytes in a page */ +static inline unsigned int page_shift(struct page *page) +{ + return PAGE_SHIFT + compound_order(page); +} + void free_compound_page(struct page *page); #ifdef CONFIG_MMU -- cgit v1.2.3 From d8c6546b1aea843fbeb4d54a1202f1adda6504be Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 23 Sep 2019 15:34:30 -0700 Subject: mm: introduce compound_nr() Replace 1 << compound_order(page) with compound_nr(page). Minor improvements in readability. Link: http://lkml.kernel.org/r/20190721104612.19120-4-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Andrew Morton Reviewed-by: Ira Weiny Acked-by: Kirill A. Shutemov Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9238548bdec5..69b7314c8d24 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -805,6 +805,12 @@ static inline void set_compound_order(struct page *page, unsigned int order) page[1].compound_order = order; } +/* Returns the number of pages in this potentially compound page. */ +static inline unsigned long compound_nr(struct page *page) +{ + return 1UL << compound_order(page); +} + /* Returns the number of bytes in this potentially compound page. */ static inline unsigned long page_size(struct page *page) { -- cgit v1.2.3 From 2d15eb31b50a1b93927bdb7cc5d9960b90f7c1e4 Mon Sep 17 00:00:00 2001 From: "akpm@linux-foundation.org" Date: Mon, 23 Sep 2019 15:35:04 -0700 Subject: mm/gup: add make_dirty arg to put_user_pages_dirty_lock() [11~From: John Hubbard Subject: mm/gup: add make_dirty arg to put_user_pages_dirty_lock() Patch series "mm/gup: add make_dirty arg to put_user_pages_dirty_lock()", v3. There are about 50+ patches in my tree [2], and I'll be sending out the remaining ones in a few more groups: * The block/bio related changes (Jerome mostly wrote those, but I've had to move stuff around extensively, and add a little code) * mm/ changes * other subsystem patches * an RFC that shows the current state of the tracking patch set. That can only be applied after all call sites are converted, but it's good to get an early look at it. This is part a tree-wide conversion, as described in fc1d8e7cca2d ("mm: introduce put_user_page*(), placeholder versions"). This patch (of 3): Provide more capable variation of put_user_pages_dirty_lock(), and delete put_user_pages_dirty(). This is based on the following: 1. Lots of call sites become simpler if a bool is passed into put_user_page*(), instead of making the call site choose which put_user_page*() variant to call. 2. Christoph Hellwig's observation that set_page_dirty_lock() is usually correct, and set_page_dirty() is usually a bug, or at least questionable, within a put_user_page*() calling chain. This leads to the following API choices: * put_user_pages_dirty_lock(page, npages, make_dirty) * There is no put_user_pages_dirty(). You have to hand code that, in the rare case that it's required. [jhubbard@nvidia.com: remove unused variable in siw_free_plist()] Link: http://lkml.kernel.org/r/20190729074306.10368-1-jhubbard@nvidia.com Link: http://lkml.kernel.org/r/20190724044537.10458-2-jhubbard@nvidia.com Signed-off-by: John Hubbard Cc: Matthew Wilcox Cc: Jan Kara Cc: Christoph Hellwig Cc: Ira Weiny Cc: Jason Gunthorpe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 69b7314c8d24..57a9fa34f159 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1075,8 +1075,9 @@ static inline void put_user_page(struct page *page) put_page(page); } -void put_user_pages_dirty(struct page **pages, unsigned long npages); -void put_user_pages_dirty_lock(struct page **pages, unsigned long npages); +void put_user_pages_dirty_lock(struct page **pages, unsigned long npages, + bool make_dirty); + void put_user_pages(struct page **pages, unsigned long npages); #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) -- cgit v1.2.3 From 010c164a5fa7e169deab0a4d8211611f1930c1cd Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 23 Sep 2019 15:38:19 -0700 Subject: mm: move memcmp_pages() and pages_identical() Patch series "THP aware uprobe", v13. This patchset makes uprobe aware of THPs. Currently, when uprobe is attached to text on THP, the page is split by FOLL_SPLIT. As a result, uprobe eliminates the performance benefit of THP. This set makes uprobe THP-aware. Instead of FOLL_SPLIT, we introduces FOLL_SPLIT_PMD, which only split PMD for uprobe. After all uprobes within the THP are removed, the PTE-mapped pages are regrouped as huge PMD. This set (plus a few THP patches) is also available at https://github.com/liu-song-6/linux/tree/uprobe-thp This patch (of 6): Move memcmp_pages() to mm/util.c and pages_identical() to mm.h, so that we can use them in other files. Link: http://lkml.kernel.org/r/20190815164525.1848545-2-songliubraving@fb.com Signed-off-by: Song Liu Acked-by: Kirill A. Shutemov Reviewed-by: Oleg Nesterov Cc: Johannes Weiner Cc: Matthew Wilcox Cc: William Kucharski Cc: Srikar Dronamraju Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 57a9fa34f159..0ac87d9ee9d8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2868,5 +2868,12 @@ void __init setup_nr_node_ids(void); static inline void setup_nr_node_ids(void) {} #endif +extern int memcmp_pages(struct page *page1, struct page *page2); + +static inline int pages_identical(struct page *page1, struct page *page2) +{ + return !memcmp_pages(page1, page2); +} + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ -- cgit v1.2.3 From bfe7b00de6d1e25fee08484c4fbf1c1ed175be78 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 23 Sep 2019 15:38:25 -0700 Subject: mm, thp: introduce FOLL_SPLIT_PMD Introduce a new foll_flag: FOLL_SPLIT_PMD. As the name says FOLL_SPLIT_PMD splits huge pmd for given mm_struct, the underlining huge page stays as-is. FOLL_SPLIT_PMD is useful for cases where we need to use regular pages, but would switch back to huge page and huge pmd on. One of such example is uprobe. The following patches use FOLL_SPLIT_PMD in uprobe. Link: http://lkml.kernel.org/r/20190815164525.1848545-4-songliubraving@fb.com Signed-off-by: Song Liu Reviewed-by: Oleg Nesterov Acked-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0ac87d9ee9d8..233ad11938db 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2591,6 +2591,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #define FOLL_COW 0x4000 /* internal GUP flag */ #define FOLL_ANON 0x8000 /* don't do file mappings */ #define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */ +#define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */ /* * NOTE on FOLL_LONGTERM: -- cgit v1.2.3 From 649775be63c8b2e0b56ecc5bbc96d38205ec5259 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Mon, 23 Sep 2019 15:38:37 -0700 Subject: mm, fs: move randomize_stack_top from fs to mm Patch series "Provide generic top-down mmap layout functions", v6. This series introduces generic functions to make top-down mmap layout easily accessible to architectures, in particular riscv which was the initial goal of this series. The generic implementation was taken from arm64 and used successively by arm, mips and finally riscv. Note that in addition the series fixes 2 issues: - stack randomization was taken into account even if not necessary. - [1] fixed an issue with mmap base which did not take into account randomization but did not report it to arm and mips, so by moving arm64 into a generic library, this problem is now fixed for both architectures. This work is an effort to factorize architecture functions to avoid code duplication and oversights as in [1]. [1]: https://www.mail-archive.com/linux-kernel@vger.kernel.org/msg1429066.html This patch (of 14): This preparatory commit moves this function so that further introduction of generic topdown mmap layout is contained only in mm/util.c. Link: http://lkml.kernel.org/r/20190730055113.23635-2-alex@ghiti.fr Signed-off-by: Alexandre Ghiti Acked-by: Kees Cook Reviewed-by: Christoph Hellwig Reviewed-by: Luis Chamberlain Cc: Russell King Cc: Catalin Marinas Cc: Will Deacon Cc: Ralf Baechle Cc: Paul Burton Cc: James Hogan Cc: Palmer Dabbelt Cc: Albert Ou Cc: Alexander Viro Cc: Christoph Hellwig Signed-off-by: Andrew Morton 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 233ad11938db..294a67b94147 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2328,6 +2328,8 @@ extern int install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long flags, struct page **pages); +unsigned long randomize_stack_top(unsigned long stack_top); + extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); extern unsigned long mmap_region(struct file *file, unsigned long addr, -- cgit v1.2.3