From 85a06835f6f1ba79f0f00838ccd5ad840dd1eafb Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 26 Oct 2018 15:08:50 -0700 Subject: [PATCH] mm: mremap: downgrade mmap_sem to read when shrinking Other than munmap, mremap might be used to shrink memory mapping too. So, it may hold write mmap_sem for long time when shrinking large mapping, as what commit ("mm: mmap: zap pages with read mmap_sem in munmap") described. The mremap() will not manipulate vmas anymore after __do_munmap() call for the mapping shrink use case, so it is safe to downgrade to read mmap_sem. So, the same optimization, which downgrades mmap_sem to read for zapping pages, is also feasible and reasonable to this case. The period of holding exclusive mmap_sem for shrinking large mapping would be reduced significantly with this optimization. MREMAP_FIXED and MREMAP_MAYMOVE are more complicated to adopt this optimization since they need manipulate vmas after do_munmap(), downgrading mmap_sem may create race window. Simple mapping shrink is the low hanging fruit, and it may cover the most cases of unmap with munmap together. [akpm@linux-foundation.org: tweak comment] [yang.shi@linux.alibaba.com: fix unsigned compare against 0 issue] Link: http://lkml.kernel.org/r/1538687672-17795-2-git-send-email-yang.shi@linux.alibaba.com Link: http://lkml.kernel.org/r/1538067582-60038-1-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Acked-by: Vlastimil Babka Acked-by: Kirill A. Shutemov Cc: Michal Hocko Cc: Matthew Wilcox Cc: Laurent Dufour Cc: Colin Ian King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ mm/mmap.c | 4 ++-- mm/mremap.c | 20 ++++++++++++++++---- 3 files changed, 20 insertions(+), 6 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 33228a49d7d2..a023c5ce71fa 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2306,6 +2306,8 @@ 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); +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); diff --git a/mm/mmap.c b/mm/mmap.c index 58e323c92c8e..1bfd12032664 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2687,8 +2687,8 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, * work. This now handles partial unmappings. * Jeremy Fitzhardinge */ -static int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len, - struct list_head *uf, bool downgrade) +int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len, + struct list_head *uf, bool downgrade) { unsigned long end; struct vm_area_struct *vma, *prev, *last; diff --git a/mm/mremap.c b/mm/mremap.c index a9617e72e6b7..7f9f9180e401 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -521,6 +521,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, unsigned long ret = -EINVAL; unsigned long charged = 0; bool locked = false; + bool downgraded = false; struct vm_userfaultfd_ctx uf = NULL_VM_UFFD_CTX; LIST_HEAD(uf_unmap_early); LIST_HEAD(uf_unmap); @@ -557,12 +558,20 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, /* * Always allow a shrinking remap: that just unmaps * the unnecessary pages.. - * do_munmap does all the needed commit accounting + * __do_munmap does all the needed commit accounting, and + * downgrades mmap_sem to read if so directed. */ if (old_len >= new_len) { - ret = do_munmap(mm, addr+new_len, old_len - new_len, &uf_unmap); - if (ret && old_len != new_len) + int retval; + + retval = __do_munmap(mm, addr+new_len, old_len - new_len, + &uf_unmap, true); + if (retval < 0 && old_len != new_len) { + ret = retval; goto out; + /* Returning 1 indicates mmap_sem is downgraded to read. */ + } else if (retval == 1) + downgraded = true; ret = addr; goto out; } @@ -627,7 +636,10 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, vm_unacct_memory(charged); locked = 0; } - up_write(¤t->mm->mmap_sem); + if (downgraded) + up_read(¤t->mm->mmap_sem); + else + up_write(¤t->mm->mmap_sem); if (locked && new_len > old_len) mm_populate(new_addr + old_len, new_len - old_len); userfaultfd_unmap_complete(mm, &uf_unmap_early);