From 73fb952d83717697910d981e27fe2c252f64662b Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 13 Oct 2020 16:49:18 -0700 Subject: resource: report parent to walk_iomem_res_desc() callback In support of detecting whether a resource might have been been claimed, report the parent to the walk_iomem_res_desc() callback. For example, the ACPI HMAT parser publishes "hmem" platform devices per target range. However, if the HMAT is disabled / missing a fallback driver can attach devices to the raw memory ranges as a fallback if it sees unclaimed / orphan "Soft Reserved" resources in the resource tree. Otherwise, find_next_iomem_res() returns a resource with garbage data from the stack allocation in __walk_iomem_res_desc() for the res->parent field. There are currently no users that expect ->child and ->sibling to be valid, and the resource_lock would be needed to traverse them. Use a compound literal to implicitly zero initialize the fields that are not being returned in addition to setting ->parent. Signed-off-by: Dan Williams Signed-off-by: Andrew Morton Cc: Jason Gunthorpe Cc: Dave Hansen Cc: Wei Yang Cc: Tom Lendacky Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Benjamin Herrenschmidt Cc: Ben Skeggs Cc: Borislav Petkov Cc: Brice Goglin Cc: Catalin Marinas Cc: Daniel Vetter Cc: Dave Jiang Cc: David Airlie Cc: David Hildenbrand Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Ira Weiny Cc: Jeff Moyer Cc: Jia He Cc: Joao Martins Cc: Jonathan Cameron Cc: Michael Ellerman Cc: Mike Rapoport Cc: Paul Mackerras Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Thomas Gleixner Cc: Vishal Verma Cc: Will Deacon Cc: Ard Biesheuvel Cc: Bjorn Helgaas Cc: Boris Ostrovsky Cc: Hulk Robot Cc: Jason Yan Cc: "Jérôme Glisse" Cc: Juergen Gross Cc: kernel test robot Cc: Randy Dunlap Cc: Stefano Stabellini Cc: Vivek Goyal Link: https://lkml.kernel.org/r/159643097166.4062302.11875688887228572793.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds --- kernel/resource.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/resource.c b/kernel/resource.c index 841737bbda9e..f1175ce93a1d 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -382,10 +382,13 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end, if (p) { /* copy data */ - res->start = max(start, p->start); - res->end = min(end, p->end); - res->flags = p->flags; - res->desc = p->desc; + *res = (struct resource) { + .start = max(start, p->start), + .end = min(end, p->end), + .flags = p->flags, + .desc = p->desc, + .parent = p->parent, + }; } read_unlock(&resource_lock); -- cgit v1.2.3 From cf508b58457cfe51b168d49ea6c79a221900d354 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Tue, 13 Oct 2020 16:54:10 -0700 Subject: mm: use helper function mapping_allow_writable() Commit 4bb5f5d9395b ("mm: allow drivers to prevent new writable mappings") changed i_mmap_writable from unsigned int to atomic_t and add the helper function mapping_allow_writable() to atomic_inc i_mmap_writable. But it forgot to use this helper function in dup_mmap() and __vma_link_file(). Signed-off-by: Miaohe Lin Signed-off-by: Andrew Morton Cc: Christian Brauner Cc: Ingo Molnar Cc: Peter Zijlstra Cc: "Eric W. Biederman" Cc: Christian Kellner Cc: Suren Baghdasaryan Cc: Adrian Reber Cc: Shakeel Butt Cc: Aleksa Sarai Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20200917112736.7789-1-linmiaohe@huawei.com Signed-off-by: Linus Torvalds --- kernel/fork.c | 2 +- mm/mmap.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index a3795aaaab5c..2dcb19a30650 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -559,7 +559,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, atomic_dec(&inode->i_writecount); i_mmap_lock_write(mapping); if (tmp->vm_flags & VM_SHARED) - atomic_inc(&mapping->i_mmap_writable); + mapping_allow_writable(mapping); flush_dcache_mmap_lock(mapping); /* insert tmp into the share list, just after mpnt */ vma_interval_tree_insert_after(tmp, mpnt, diff --git a/mm/mmap.c b/mm/mmap.c index 19cd69524837..7799a3f2e483 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -621,7 +621,7 @@ static void __vma_link_file(struct vm_area_struct *vma) if (vma->vm_flags & VM_DENYWRITE) atomic_dec(&file_inode(file)->i_writecount); if (vma->vm_flags & VM_SHARED) - atomic_inc(&mapping->i_mmap_writable); + mapping_allow_writable(mapping); flush_dcache_mmap_lock(mapping); vma_interval_tree_insert(vma, &mapping->i_mmap); -- cgit v1.2.3 From c78f463649d60f4ed12df97a32def4d77b583853 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Tue, 13 Oct 2020 16:54:21 -0700 Subject: mm: remove src/dst mm parameter in copy_page_range() Both of the mm pointers are not needed after commit 7a4830c380f3 ("mm/fork: Pass new vma pointer into copy_page_range()"). Jason Gunthorpe also reported that the ordering of copy_page_range() is odd. Since working at it, reorder the parameters to be logical, by (1) always put the dst_* fields to be before src_* fields, and (2) keep the same type of parameters together. [peterx@redhat.com: further reorder some parameters and line format, per Jason] Link: https://lkml.kernel.org/r/20201002192647.7161-1-peterx@redhat.com [peterx@redhat.com: fix warnings] Link: https://lkml.kernel.org/r/20201006200138.GA6026@xz-x1 Reported-by: Kirill A. Shutemov Signed-off-by: Peter Xu Signed-off-by: Andrew Morton Reviewed-by: Jason Gunthorpe Acked-by: Kirill A. Shutemov Link: https://lkml.kernel.org/r/20200930204950.6668-1-peterx@redhat.com Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 +- kernel/fork.c | 2 +- mm/memory.c | 141 +++++++++++++++++++++++++++-------------------------- 3 files changed, 76 insertions(+), 71 deletions(-) (limited to 'kernel') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5320e7ab843f..620961e4f32b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1653,8 +1653,8 @@ struct mmu_notifier_range; void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); -int copy_page_range(struct mm_struct *dst, struct mm_struct *src, - struct vm_area_struct *vma, struct vm_area_struct *new); +int +copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); int follow_pte_pmd(struct mm_struct *mm, unsigned long address, struct mmu_notifier_range *range, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp); diff --git a/kernel/fork.c b/kernel/fork.c index 2dcb19a30650..ede26e5a6097 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -590,7 +590,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, mm->map_count++; if (!(tmp->vm_flags & VM_WIPEONFORK)) - retval = copy_page_range(mm, oldmm, mpnt, tmp); + retval = copy_page_range(tmp, mpnt); if (tmp->vm_ops && tmp->vm_ops->open) tmp->vm_ops->open(tmp); diff --git a/mm/memory.c b/mm/memory.c index 5a1c4c9759dc..f482af8bc828 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -794,15 +794,14 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, * lock. */ static inline int -copy_present_page(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pte_t *dst_pte, pte_t *src_pte, - struct vm_area_struct *vma, struct vm_area_struct *new, - unsigned long addr, int *rss, struct page **prealloc, - pte_t pte, struct page *page) +copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, + struct page **prealloc, pte_t pte, struct page *page) { + struct mm_struct *src_mm = src_vma->vm_mm; struct page *new_page; - if (!is_cow_mapping(vma->vm_flags)) + if (!is_cow_mapping(src_vma->vm_flags)) return 1; /* @@ -832,16 +831,16 @@ copy_present_page(struct mm_struct *dst_mm, struct mm_struct *src_mm, * over and copy the page & arm it. */ *prealloc = NULL; - copy_user_highpage(new_page, page, addr, vma); + copy_user_highpage(new_page, page, addr, src_vma); __SetPageUptodate(new_page); - page_add_new_anon_rmap(new_page, new, addr, false); - lru_cache_add_inactive_or_unevictable(new_page, new); + page_add_new_anon_rmap(new_page, dst_vma, addr, false); + lru_cache_add_inactive_or_unevictable(new_page, dst_vma); rss[mm_counter(new_page)]++; /* All done, just insert the new page copy in the child */ - pte = mk_pte(new_page, new->vm_page_prot); - pte = maybe_mkwrite(pte_mkdirty(pte), new); - set_pte_at(dst_mm, addr, dst_pte, pte); + pte = mk_pte(new_page, dst_vma->vm_page_prot); + pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma); + set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); return 0; } @@ -850,24 +849,21 @@ copy_present_page(struct mm_struct *dst_mm, struct mm_struct *src_mm, * is required to copy this pte. */ static inline int -copy_present_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma, - struct vm_area_struct *new, - unsigned long addr, int *rss, struct page **prealloc) +copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, + struct page **prealloc) { - unsigned long vm_flags = vma->vm_flags; + struct mm_struct *src_mm = src_vma->vm_mm; + unsigned long vm_flags = src_vma->vm_flags; pte_t pte = *src_pte; struct page *page; - page = vm_normal_page(vma, addr, pte); + page = vm_normal_page(src_vma, addr, pte); if (page) { int retval; - retval = copy_present_page(dst_mm, src_mm, - dst_pte, src_pte, - vma, new, - addr, rss, prealloc, - pte, page); + retval = copy_present_page(dst_vma, src_vma, dst_pte, src_pte, + addr, rss, prealloc, pte, page); if (retval <= 0) return retval; @@ -901,7 +897,7 @@ copy_present_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (!(vm_flags & VM_UFFD_WP)) pte = pte_clear_uffd_wp(pte); - set_pte_at(dst_mm, addr, dst_pte, pte); + set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); return 0; } @@ -924,11 +920,13 @@ page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma, return new_page; } -static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma, - struct vm_area_struct *new, - unsigned long addr, unsigned long end) +static int +copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, + unsigned long end) { + struct mm_struct *dst_mm = dst_vma->vm_mm; + struct mm_struct *src_mm = src_vma->vm_mm; pte_t *orig_src_pte, *orig_dst_pte; pte_t *src_pte, *dst_pte; spinlock_t *src_ptl, *dst_ptl; @@ -971,15 +969,15 @@ again: if (unlikely(!pte_present(*src_pte))) { entry.val = copy_nonpresent_pte(dst_mm, src_mm, dst_pte, src_pte, - vma, addr, rss); + src_vma, addr, rss); if (entry.val) break; progress += 8; continue; } /* copy_present_pte() will clear `*prealloc' if consumed */ - ret = copy_present_pte(dst_mm, src_mm, dst_pte, src_pte, - vma, new, addr, rss, &prealloc); + ret = copy_present_pte(dst_vma, src_vma, dst_pte, src_pte, + addr, rss, &prealloc); /* * If we need a pre-allocated page for this pte, drop the * locks, allocate, and try again. @@ -1014,7 +1012,7 @@ again: entry.val = 0; } else if (ret) { WARN_ON_ONCE(ret != -EAGAIN); - prealloc = page_copy_prealloc(src_mm, vma, addr); + prealloc = page_copy_prealloc(src_mm, src_vma, addr); if (!prealloc) return -ENOMEM; /* We've captured and resolved the error. Reset, try again. */ @@ -1028,11 +1026,13 @@ out: return ret; } -static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma, - struct vm_area_struct *new, - unsigned long addr, unsigned long end) +static inline int +copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + pud_t *dst_pud, pud_t *src_pud, unsigned long addr, + unsigned long end) { + struct mm_struct *dst_mm = dst_vma->vm_mm; + struct mm_struct *src_mm = src_vma->vm_mm; pmd_t *src_pmd, *dst_pmd; unsigned long next; @@ -1045,9 +1045,9 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src if (is_swap_pmd(*src_pmd) || pmd_trans_huge(*src_pmd) || pmd_devmap(*src_pmd)) { int err; - VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, vma); + VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma); err = copy_huge_pmd(dst_mm, src_mm, - dst_pmd, src_pmd, addr, vma); + dst_pmd, src_pmd, addr, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) @@ -1056,18 +1056,20 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src } if (pmd_none_or_clear_bad(src_pmd)) continue; - if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd, - vma, new, addr, next)) + if (copy_pte_range(dst_vma, src_vma, dst_pmd, src_pmd, + addr, next)) return -ENOMEM; } while (dst_pmd++, src_pmd++, addr = next, addr != end); return 0; } -static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - p4d_t *dst_p4d, p4d_t *src_p4d, struct vm_area_struct *vma, - struct vm_area_struct *new, - unsigned long addr, unsigned long end) +static inline int +copy_pud_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + p4d_t *dst_p4d, p4d_t *src_p4d, unsigned long addr, + unsigned long end) { + struct mm_struct *dst_mm = dst_vma->vm_mm; + struct mm_struct *src_mm = src_vma->vm_mm; pud_t *src_pud, *dst_pud; unsigned long next; @@ -1080,9 +1082,9 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) { int err; - VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, vma); + VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, src_vma); err = copy_huge_pud(dst_mm, src_mm, - dst_pud, src_pud, addr, vma); + dst_pud, src_pud, addr, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) @@ -1091,18 +1093,19 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src } if (pud_none_or_clear_bad(src_pud)) continue; - if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud, - vma, new, addr, next)) + if (copy_pmd_range(dst_vma, src_vma, dst_pud, src_pud, + addr, next)) return -ENOMEM; } while (dst_pud++, src_pud++, addr = next, addr != end); return 0; } -static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma, - struct vm_area_struct *new, - unsigned long addr, unsigned long end) +static inline int +copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long addr, + unsigned long end) { + struct mm_struct *dst_mm = dst_vma->vm_mm; p4d_t *src_p4d, *dst_p4d; unsigned long next; @@ -1114,20 +1117,22 @@ static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(src_p4d)) continue; - if (copy_pud_range(dst_mm, src_mm, dst_p4d, src_p4d, - vma, new, addr, next)) + if (copy_pud_range(dst_vma, src_vma, dst_p4d, src_p4d, + addr, next)) return -ENOMEM; } while (dst_p4d++, src_p4d++, addr = next, addr != end); return 0; } -int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - struct vm_area_struct *vma, struct vm_area_struct *new) +int +copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { pgd_t *src_pgd, *dst_pgd; unsigned long next; - unsigned long addr = vma->vm_start; - unsigned long end = vma->vm_end; + unsigned long addr = src_vma->vm_start; + unsigned long end = src_vma->vm_end; + struct mm_struct *dst_mm = dst_vma->vm_mm; + struct mm_struct *src_mm = src_vma->vm_mm; struct mmu_notifier_range range; bool is_cow; int ret; @@ -1138,19 +1143,19 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, * readonly mappings. The tradeoff is that copy_page_range is more * efficient than faulting. */ - if (!(vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) && - !vma->anon_vma) + if (!(src_vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) && + !src_vma->anon_vma) return 0; - if (is_vm_hugetlb_page(vma)) - return copy_hugetlb_page_range(dst_mm, src_mm, vma); + if (is_vm_hugetlb_page(src_vma)) + return copy_hugetlb_page_range(dst_mm, src_mm, src_vma); - if (unlikely(vma->vm_flags & VM_PFNMAP)) { + if (unlikely(src_vma->vm_flags & VM_PFNMAP)) { /* * We do not free on error cases below as remove_vma * gets called on error from higher level routine */ - ret = track_pfn_copy(vma); + ret = track_pfn_copy(src_vma); if (ret) return ret; } @@ -1161,11 +1166,11 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, * parent mm. And a permission downgrade will only happen if * is_cow_mapping() returns true. */ - is_cow = is_cow_mapping(vma->vm_flags); + is_cow = is_cow_mapping(src_vma->vm_flags); if (is_cow) { mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, - 0, vma, src_mm, addr, end); + 0, src_vma, src_mm, addr, end); mmu_notifier_invalidate_range_start(&range); } @@ -1176,8 +1181,8 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(src_pgd)) continue; - if (unlikely(copy_p4d_range(dst_mm, src_mm, dst_pgd, src_pgd, - vma, new, addr, next))) { + if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd, + addr, next))) { ret = -ENOMEM; break; } -- cgit v1.2.3 From e9aa36ccbb4e845d043bb51de274ae877ae925a7 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 13 Oct 2020 16:57:22 -0700 Subject: dma-contiguous: simplify cma_early_percent_memory() The memory size calculation in cma_early_percent_memory() traverses memblock.memory rather than simply call memblock_phys_mem_size(). The comment in that function suggests that at some point there should have been call to memblock_analyze() before memblock_phys_mem_size() could be used. As of now, there is no memblock_analyze() at all and memblock_phys_mem_size() can be used as soon as cold-plug memory is registered with memblock. Replace loop over memblock.memory with a call to memblock_phys_mem_size(). Signed-off-by: Mike Rapoport Signed-off-by: Andrew Morton Reviewed-by: Christoph Hellwig Reviewed-by: Baoquan He Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Daniel Axtens Cc: Dave Hansen Cc: Emil Renner Berthing Cc: Hari Bathini Cc: Ingo Molnar Cc: Ingo Molnar Cc: Jonathan Cameron Cc: Marek Szyprowski Cc: Max Filippov Cc: Michael Ellerman Cc: Michal Simek Cc: Miguel Ojeda Cc: Palmer Dabbelt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Russell King Cc: Stafford Horne Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Will Deacon Cc: Yoshinori Sato Link: https://lkml.kernel.org/r/20200818151634.14343-3-rppt@kernel.org Signed-off-by: Linus Torvalds --- kernel/dma/contiguous.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c index cff7e60968b9..0369fd5fda8f 100644 --- a/kernel/dma/contiguous.c +++ b/kernel/dma/contiguous.c @@ -73,16 +73,7 @@ early_param("cma", early_cma); static phys_addr_t __init __maybe_unused cma_early_percent_memory(void) { - struct memblock_region *reg; - unsigned long total_pages = 0; - - /* - * We cannot use memblock_phys_mem_size() here, because - * memblock_analyze() has not been called yet. - */ - for_each_memblock(memory, reg) - total_pages += memblock_region_memory_end_pfn(reg) - - memblock_region_memory_base_pfn(reg); + unsigned long total_pages = PHYS_PFN(memblock_phys_mem_size()); return (total_pages * CONFIG_CMA_SIZE_PERCENTAGE / 100) << PAGE_SHIFT; } -- cgit v1.2.3 From 67197a4f28d28d0b073ab0427b03cb2ee5382578 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Tue, 13 Oct 2020 16:58:35 -0700 Subject: mm, oom_adj: don't loop through tasks in __set_oom_adj when not necessary Currently __set_oom_adj loops through all processes in the system to keep oom_score_adj and oom_score_adj_min in sync between processes sharing their mm. This is done for any task with more that one mm_users, which includes processes with multiple threads (sharing mm and signals). However for such processes the loop is unnecessary because their signal structure is shared as well. Android updates oom_score_adj whenever a tasks changes its role (background/foreground/...) or binds to/unbinds from a service, making it more/less important. Such operation can happen frequently. We noticed that updates to oom_score_adj became more expensive and after further investigation found out that the patch mentioned in "Fixes" introduced a regression. Using Pixel 4 with a typical Android workload, write time to oom_score_adj increased from ~3.57us to ~362us. Moreover this regression linearly depends on the number of multi-threaded processes running on the system. Mark the mm with a new MMF_MULTIPROCESS flag bit when task is created with (CLONE_VM && !CLONE_THREAD && !CLONE_VFORK). Change __set_oom_adj to use MMF_MULTIPROCESS instead of mm_users to decide whether oom_score_adj update should be synchronized between multiple processes. To prevent races between clone() and __set_oom_adj(), when oom_score_adj of the process being cloned might be modified from userspace, we use oom_adj_mutex. Its scope is changed to global. The combination of (CLONE_VM && !CLONE_THREAD) is rarely used except for the case of vfork(). To prevent performance regressions of vfork(), we skip taking oom_adj_mutex and setting MMF_MULTIPROCESS when CLONE_VFORK is specified. Clearing the MMF_MULTIPROCESS flag (when the last process sharing the mm exits) is left out of this patch to keep it simple and because it is believed that this threading model is rare. Should there ever be a need for optimizing that case as well, it can be done by hooking into the exit path, likely following the mm_update_next_owner pattern. With the combination of (CLONE_VM && !CLONE_THREAD && !CLONE_VFORK) being quite rare, the regression is gone after the change is applied. [surenb@google.com: v3] Link: https://lkml.kernel.org/r/20200902012558.2335613-1-surenb@google.com Fixes: 44a70adec910 ("mm, oom_adj: make sure processes sharing mm have same view of oom_score_adj") Reported-by: Tim Murray Suggested-by: Michal Hocko Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton Acked-by: Christian Brauner Acked-by: Michal Hocko Acked-by: Oleg Nesterov Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Eugene Syromiatnikov Cc: Christian Kellner Cc: Adrian Reber Cc: Shakeel Butt Cc: Aleksa Sarai Cc: Alexey Dobriyan Cc: "Eric W. Biederman" Cc: Alexey Gladkov Cc: Michel Lespinasse Cc: Daniel Jordan Cc: Andrei Vagin Cc: Bernd Edlinger Cc: John Johansen Cc: Yafang Shao Link: https://lkml.kernel.org/r/20200824153036.3201505-1-surenb@google.com Debugged-by: Minchan Kim Signed-off-by: Linus Torvalds --- fs/proc/base.c | 3 +-- include/linux/oom.h | 1 + include/linux/sched/coredump.h | 1 + kernel/fork.c | 21 +++++++++++++++++++++ mm/oom_kill.c | 2 ++ 5 files changed, 26 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/fs/proc/base.c b/fs/proc/base.c index 617db4e0faa0..aa69c35d904c 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1055,7 +1055,6 @@ static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count, static int __set_oom_adj(struct file *file, int oom_adj, bool legacy) { - static DEFINE_MUTEX(oom_adj_mutex); struct mm_struct *mm = NULL; struct task_struct *task; int err = 0; @@ -1095,7 +1094,7 @@ static int __set_oom_adj(struct file *file, int oom_adj, bool legacy) struct task_struct *p = find_lock_task_mm(task); if (p) { - if (atomic_read(&p->mm->mm_users) > 1) { + if (test_bit(MMF_MULTIPROCESS, &p->mm->flags)) { mm = p->mm; mmgrab(mm); } diff --git a/include/linux/oom.h b/include/linux/oom.h index f022f581ac29..2db9a1432511 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -55,6 +55,7 @@ struct oom_control { }; extern struct mutex oom_lock; +extern struct mutex oom_adj_mutex; static inline void set_current_oom_origin(void) { diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index ecdc6542070f..dfd82eab2902 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -72,6 +72,7 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ #define MMF_OOM_VICTIM 25 /* mm is the oom victim */ #define MMF_OOM_REAP_QUEUED 26 /* mm was queued for oom_reaper */ +#define MMF_MULTIPROCESS 27 /* mm is shared between processes */ #define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ diff --git a/kernel/fork.c b/kernel/fork.c index ede26e5a6097..50c90d368117 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1812,6 +1812,25 @@ static __always_inline void delayed_free_task(struct task_struct *tsk) free_task(tsk); } +static void copy_oom_score_adj(u64 clone_flags, struct task_struct *tsk) +{ + /* Skip if kernel thread */ + if (!tsk->mm) + return; + + /* Skip if spawning a thread or using vfork */ + if ((clone_flags & (CLONE_VM | CLONE_THREAD | CLONE_VFORK)) != CLONE_VM) + return; + + /* We need to synchronize with __set_oom_adj */ + mutex_lock(&oom_adj_mutex); + set_bit(MMF_MULTIPROCESS, &tsk->mm->flags); + /* Update the values in case they were changed after copy_signal */ + tsk->signal->oom_score_adj = current->signal->oom_score_adj; + tsk->signal->oom_score_adj_min = current->signal->oom_score_adj_min; + mutex_unlock(&oom_adj_mutex); +} + /* * This creates a new process as a copy of the old one, * but does not actually start it yet. @@ -2288,6 +2307,8 @@ static __latent_entropy struct task_struct *copy_process( trace_task_newtask(p, clone_flags); uprobe_copy_process(p, clone_flags); + copy_oom_score_adj(clone_flags, p); + return p; bad_fork_cancel_cgroup: diff --git a/mm/oom_kill.c b/mm/oom_kill.c index e90f25d6385d..8b84661a6410 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -64,6 +64,8 @@ int sysctl_oom_dump_tasks = 1; * and mark_oom_victim */ DEFINE_MUTEX(oom_lock); +/* Serializes oom_score_adj and oom_score_adj_min updates */ +DEFINE_MUTEX(oom_adj_mutex); static inline bool is_memcg_oom(struct oom_control *oc) { -- cgit v1.2.3