From 6dc5ea16c86f753951f53085aa04df49cf17cb50 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Thu, 6 Aug 2020 23:19:51 -0700 Subject: mm, dump_page: do not crash with bad compound_mapcount() If a compound page is being split while dump_page() is being run on that page, we can end up calling compound_mapcount() on a page that is no longer compound. This leads to a crash (already seen at least once in the field), due to the VM_BUG_ON_PAGE() assertion inside compound_mapcount(). (The above is from Matthew Wilcox's analysis of Qian Cai's bug report.) A similar problem is possible, via compound_pincount() instead of compound_mapcount(). In order to avoid this kind of crash, make dump_page() slightly more robust, by providing a pair of simpler routines that don't contain assertions: head_mapcount() and head_pincount(). For debug tools, we don't want to go *too* far in this direction, but this is a simple small fix, and the crash has already been seen, so it's a good trade-off. Reported-by: Qian Cai Suggested-by: Matthew Wilcox Signed-off-by: John Hubbard Signed-off-by: Andrew Morton Acked-by: Vlastimil Babka Cc: Kirill A. Shutemov Cc: Mike Rapoport Cc: William Kucharski Link: http://lkml.kernel.org/r/20200804214807.169256-1-jhubbard@nvidia.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index dc7b87310c10..303a47a9769d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -779,6 +779,11 @@ static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) extern void kvfree(const void *addr); extern void kvfree_sensitive(const void *addr, size_t len); +static inline int head_mapcount(struct page *head) +{ + return atomic_read(compound_mapcount_ptr(head)) + 1; +} + /* * Mapcount of compound page as a whole, does not include mapped sub-pages. * @@ -788,7 +793,7 @@ static inline int compound_mapcount(struct page *page) { VM_BUG_ON_PAGE(!PageCompound(page), page); page = compound_head(page); - return atomic_read(compound_mapcount_ptr(page)) + 1; + return head_mapcount(page); } /* @@ -901,11 +906,16 @@ static inline bool hpage_pincount_available(struct page *page) return PageCompound(page) && compound_order(page) > 1; } +static inline int head_pincount(struct page *head) +{ + return atomic_read(compound_pincount_ptr(head)); +} + static inline int compound_pincount(struct page *page) { VM_BUG_ON_PAGE(!hpage_pincount_available(page), page); page = compound_head(page); - return atomic_read(compound_pincount_ptr(page)); + return head_pincount(page); } static inline void set_compound_order(struct page *page, unsigned int order) -- cgit From 2a681cfa5bb41e78e7bfafbb748b581374ce9b1d Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 6 Aug 2020 23:22:55 -0700 Subject: mm: move p?d_alloc_track to separate header file The functions are only used in two source files, so there is no need for them to be in the global header. Move them to the new header and include it only where needed. Signed-off-by: Joerg Roedel Signed-off-by: Andrew Morton Reviewed-by: Pekka Enberg Cc: Peter Zijlstra (Intel) Cc: Andy Lutomirski Cc: Abdul Haleem Cc: Satheesh Rajendran Cc: Stephen Rothwell Cc: Steven Rostedt (VMware) Cc: Mike Rapoport Cc: Christophe Leroy Cc: Arnd Bergmann Cc: Max Filippov Cc: Stafford Horne Cc: Geert Uytterhoeven Cc: Matthew Wilcox Link: http://lkml.kernel.org/r/20200609120533.25867-1-joro@8bytes.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 45 --------------------------------------------- 1 file changed, 45 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 303a47a9769d..2830f1c0fdc3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2103,51 +2103,11 @@ static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d, 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); -} - -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 @@ -2263,11 +2223,6 @@ 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 From 56f3547bfa4d361148aa748ccb86073bc57f5e6c Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Thu, 6 Aug 2020 23:23:15 -0700 Subject: mm: adjust vm_committed_as_batch according to vm overcommit policy When checking a performance change for will-it-scale scalability mmap test [1], we found very high lock contention for spinlock of percpu counter 'vm_committed_as': 94.14% 0.35% [kernel.kallsyms] [k] _raw_spin_lock_irqsave 48.21% _raw_spin_lock_irqsave;percpu_counter_add_batch;__vm_enough_memory;mmap_region;do_mmap; 45.91% _raw_spin_lock_irqsave;percpu_counter_add_batch;__do_munmap; Actually this heavy lock contention is not always necessary. The 'vm_committed_as' needs to be very precise when the strict OVERCOMMIT_NEVER policy is set, which requires a rather small batch number for the percpu counter. So keep 'batch' number unchanged for strict OVERCOMMIT_NEVER policy, and lift it to 64X for OVERCOMMIT_ALWAYS and OVERCOMMIT_GUESS policies. Also add a sysctl handler to adjust it when the policy is reconfigured. Benchmark with the same testcase in [1] shows 53% improvement on a 8C/16T desktop, and 2097%(20X) on a 4S/72C/144T server. We tested with test platforms in 0day (server, desktop and laptop), and 80%+ platforms shows improvements with that test. And whether it shows improvements depends on if the test mmap size is bigger than the batch number computed. And if the lift is 16X, 1/3 of the platforms will show improvements, though it should help the mmap/unmap usage generally, as Michal Hocko mentioned: : I believe that there are non-synthetic worklaods which would benefit from : a larger batch. E.g. large in memory databases which do large mmaps : during startups from multiple threads. [1] https://lore.kernel.org/lkml/20200305062138.GI5972@shao2-debian/ Signed-off-by: Feng Tang Signed-off-by: Andrew Morton Acked-by: Michal Hocko Cc: Matthew Wilcox (Oracle) Cc: Johannes Weiner Cc: Mel Gorman Cc: Qian Cai Cc: Kees Cook Cc: Andi Kleen Cc: Tim Chen Cc: Dave Hansen Cc: Huang Ying Cc: Christoph Lameter Cc: Dennis Zhou Cc: Haiyang Zhang Cc: kernel test robot Cc: "K. Y. Srinivasan" Cc: Tejun Heo Link: http://lkml.kernel.org/r/1589611660-89854-4-git-send-email-feng.tang@intel.com Link: http://lkml.kernel.org/r/1592725000-73486-4-git-send-email-feng.tang@intel.com Link: http://lkml.kernel.org/r/1594389708-60781-5-git-send-email-feng.tang@intel.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 2830f1c0fdc3..1c3470550395 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -206,6 +206,8 @@ int overcommit_ratio_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *, loff_t *); +int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *, + loff_t *); #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) -- cgit From 1d9cfee7535c213038a615f112c900c2d0ba8f54 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 6 Aug 2020 23:23:19 -0700 Subject: mm/sparsemem: enable vmem_altmap support in vmemmap_populate_basepages() Patch series "arm64: Enable vmemmap mapping from device memory", v4. This series enables vmemmap backing memory allocation from device memory ranges on arm64. But before that, it enables vmemmap_populate_basepages() and vmemmap_alloc_block_buf() to accommodate struct vmem_altmap based alocation requests. This patch (of 3): vmemmap_populate_basepages() is used across platforms to allocate backing memory for vmemmap mapping. This is used as a standard default choice or as a fallback when intended huge pages allocation fails. This just creates entire vmemmap mapping with base pages (PAGE_SIZE). On arm64 platforms, vmemmap_populate_basepages() is called instead of the platform specific vmemmap_populate() when ARM64_SWAPPER_USES_SECTION_MAPS is not enabled as in case for ARM64_16K_PAGES and ARM64_64K_PAGES configs. At present vmemmap_populate_basepages() does not support allocating from driver defined struct vmem_altmap while trying to create vmemmap mapping for a device memory range. It prevents ARM64_16K_PAGES and ARM64_64K_PAGES configs on arm64 from supporting device memory with vmemap_altmap request. This enables vmem_altmap support in vmemmap_populate_basepages() unlocking device memory allocation for vmemap mapping on arm64 platforms with 16K or 64K base page configs. Each architecture should evaluate and decide on subscribing device memory based base page allocation through vmemmap_populate_basepages(). Hence lets keep it disabled on all archs in order to preserve the existing semantics. A subsequent patch enables it on arm64. Signed-off-by: Anshuman Khandual Signed-off-by: Andrew Morton Tested-by: Jia He Reviewed-by: David Hildenbrand Acked-by: Will Deacon Acked-by: Catalin Marinas Cc: Mark Rutland Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Tony Luck Cc: Fenghua Yu Cc: Dave Hansen Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Mike Rapoport Cc: Michal Hocko Cc: "Matthew Wilcox (Oracle)" Cc: "Kirill A. Shutemov" Cc: Dan Williams Cc: Pavel Tatashin Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Hsin-Yi Wang Cc: Jonathan Corbet Cc: Michael Ellerman Cc: Paul Mackerras Cc: Robin Murphy Cc: Steve Capper Cc: Yu Zhao Link: http://lkml.kernel.org/r/1594004178-8861-1-git-send-email-anshuman.khandual@arm.com Link: http://lkml.kernel.org/r/1594004178-8861-2-git-send-email-anshuman.khandual@arm.com 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 1c3470550395..a7ff98738126 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2978,14 +2978,15 @@ pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); -pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node); +pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, + struct vmem_altmap *altmap); void *vmemmap_alloc_block(unsigned long size, int node); struct vmem_altmap; void *vmemmap_alloc_block_buf(unsigned long size, int node); void *altmap_alloc_block_buf(unsigned long size, struct vmem_altmap *altmap); void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); int vmemmap_populate_basepages(unsigned long start, unsigned long end, - int node); + int node, struct vmem_altmap *altmap); int vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); void vmemmap_populate_print_last(void); -- cgit From 56993b4e147e9f2ba91ac15ef9ae5ee0626a6850 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 6 Aug 2020 23:23:24 -0700 Subject: mm/sparsemem: enable vmem_altmap support in vmemmap_alloc_block_buf() There are many instances where vmemap allocation is often switched between regular memory and device memory just based on whether altmap is available or not. vmemmap_alloc_block_buf() is used in various platforms to allocate vmemmap mappings. Lets also enable it to handle altmap based device memory allocation along with existing regular memory allocations. This will help in avoiding the altmap based allocation switch in many places. To summarize there are two different methods to call vmemmap_alloc_block_buf(). vmemmap_alloc_block_buf(size, node, NULL) /* Allocate from system RAM */ vmemmap_alloc_block_buf(size, node, altmap) /* Allocate from altmap */ This converts altmap_alloc_block_buf() into a static function, drops it's entry from the header and updates Documentation/vm/memory-model.rst. Suggested-by: Robin Murphy Signed-off-by: Anshuman Khandual Signed-off-by: Andrew Morton Tested-by: Jia He Reviewed-by: Catalin Marinas Cc: Jonathan Corbet Cc: Will Deacon Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Dave Hansen Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Dan Williams Cc: David Hildenbrand Cc: Fenghua Yu Cc: Hsin-Yi Wang Cc: "Kirill A. Shutemov" Cc: Mark Rutland Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Rapoport Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Pavel Tatashin Cc: Steve Capper Cc: Tony Luck Cc: Yu Zhao Link: http://lkml.kernel.org/r/1594004178-8861-3-git-send-email-anshuman.khandual@arm.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index a7ff98738126..98e35df8d88e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2982,8 +2982,8 @@ pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, struct vmem_altmap *altmap); void *vmemmap_alloc_block(unsigned long size, int node); struct vmem_altmap; -void *vmemmap_alloc_block_buf(unsigned long size, int node); -void *altmap_alloc_block_buf(unsigned long size, struct vmem_altmap *altmap); +void *vmemmap_alloc_block_buf(unsigned long size, int node, + struct vmem_altmap *altmap); void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); int vmemmap_populate_basepages(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); -- cgit From 45e55300f11495ed58c53427da7f0d958800a30f Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Thu, 6 Aug 2020 23:23:37 -0700 Subject: mm: remove unnecessary wrapper function do_mmap_pgoff() The current split between do_mmap() and do_mmap_pgoff() was introduced in commit 1fcfd8db7f82 ("mm, mpx: add "vm_flags_t vm_flags" arg to do_mmap_pgoff()") to support MPX. The wrapper function do_mmap_pgoff() always passed 0 as the value of the vm_flags argument to do_mmap(). However, MPX support has subsequently been removed from the kernel and there were no more direct callers of do_mmap(); all calls were going via do_mmap_pgoff(). Simplify the code by removing do_mmap_pgoff() and changing all callers to directly call do_mmap(), which now no longer takes a vm_flags argument. Signed-off-by: Peter Collingbourne Signed-off-by: Andrew Morton Reviewed-by: Andrew Morton Reviewed-by: David Hildenbrand Link: http://lkml.kernel.org/r/20200727194109.1371462-1-pcc@google.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 98e35df8d88e..cf7e4605ff3f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2546,23 +2546,13 @@ extern unsigned long mmap_region(struct file *file, unsigned long addr, struct list_head *uf); extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, - vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate, - struct list_head *uf); + unsigned long pgoff, unsigned long *populate, struct list_head *uf); extern int __do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf, bool downgrade); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); extern int do_madvise(unsigned long start, size_t len_in, int behavior); -static inline unsigned long -do_mmap_pgoff(struct file *file, unsigned long addr, - unsigned long len, unsigned long prot, unsigned long flags, - unsigned long pgoff, unsigned long *populate, - struct list_head *uf) -{ - return do_mmap(file, addr, len, prot, flags, 0, pgoff, populate, uf); -} - #ifdef CONFIG_MMU extern int __mm_populate(unsigned long addr, unsigned long len, int ignore_errors); -- cgit From c89ab04febf97d2db8ca4ef8e2866fadc474351b Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Thu, 6 Aug 2020 23:24:02 -0700 Subject: mm/sparse: cleanup the code surrounding memory_present() After removal of CONFIG_HAVE_MEMBLOCK_NODE_MAP we have two equivalent functions that call memory_present() for each region in memblock.memory: sparse_memory_present_with_active_regions() and membocks_present(). Moreover, all architectures have a call to either of these functions preceding the call to sparse_init() and in the most cases they are called one after the other. Mark the regions from memblock.memory as present during sparce_init() by making sparse_init() call memblocks_present(), make memblocks_present() and memory_present() functions static and remove redundant sparse_memory_present_with_active_regions() function. Also remove no longer required HAVE_MEMORY_PRESENT configuration option. Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Link: http://lkml.kernel.org/r/20200712083130.22919-1-rppt@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index cf7e4605ff3f..392016ce5878 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2382,9 +2382,6 @@ static inline unsigned long get_num_physpages(void) * for_each_valid_physical_page_range() * memblock_add_node(base, size, nid) * free_area_init(max_zone_pfns); - * - * sparse_memory_present_with_active_regions() calls memory_present() for - * each range when SPARSEMEM is enabled. */ void free_area_init(unsigned long *max_zone_pfn); unsigned long node_map_pfn_alignment(void); @@ -2395,7 +2392,6 @@ extern unsigned long absent_pages_in_range(unsigned long start_pfn, extern void get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn); extern unsigned long find_min_pfn_with_active_regions(void); -extern void sparse_memory_present_with_active_regions(int nid); #ifndef CONFIG_NEED_MULTIPLE_NODES static inline int early_pfn_to_nid(unsigned long pfn) -- cgit