From 4b6e1e37026ec7dae9b23d78ffcebdd5ddb1bfa1 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Mon, 8 Oct 2012 16:28:40 -0700 Subject: [PATCH] mm: kill vma flag VM_INSERTPAGE Merge VM_INSERTPAGE into VM_MIXEDMAP. VM_MIXEDMAP VMA can mix pure-pfn ptes, special ptes and normal ptes. Now copy_page_range() always copies VM_MIXEDMAP VMA on fork like VM_PFNMAP. If driver populates whole VMA at mmap() it probably not expects page-faults. This patch removes special check from vma_wants_writenotify() which disables pages write tracking for VMA populated via vm_instert_page(). BDI below mapped file should not use dirty-accounting, moreover do_wp_page() can handle this. vm_insert_page() still marks vma after first usage. Usually it is called from f_op->mmap() handler under mm->mmap_sem write-lock, so it able to change vma->vm_flags. Caller must set VM_MIXEDMAP at mmap time if it wants to call this function from other places, for example from page-fault handler. Signed-off-by: Konstantin Khlebnikov Cc: Alexander Viro Cc: Carsten Otte Cc: Chris Metcalf Cc: Cyrill Gorcunov Cc: Eric Paris Cc: H. Peter Anvin Cc: Hugh Dickins Cc: Ingo Molnar Cc: James Morris Cc: Jason Baron Cc: Kentaro Takeda Cc: Matt Helsley Cc: Nick Piggin Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Robert Richter Cc: Suresh Siddha Cc: Tetsuo Handa Cc: Venkatesh Pallipadi Acked-by: Linus Torvalds Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 - mm/huge_memory.c | 3 +-- mm/ksm.c | 2 +- mm/memory.c | 14 ++++++++++++-- mm/mmap.c | 2 +- 5 files changed, 15 insertions(+), 7 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 9c039f84b63c..fb0685b17914 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -103,7 +103,6 @@ extern unsigned int kobjsize(const void *objp); #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */ #define VM_ARCH_1 0x01000000 /* Architecture-specific flag */ -#define VM_INSERTPAGE 0x02000000 /* The vma has had "vm_insert_page()" done on it */ #define VM_NODUMP 0x04000000 /* Do not include in the core dump */ #define VM_CAN_NONLINEAR 0x08000000 /* Has ->fault & does nonlinear pages */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 47206692cf88..9b72d1270519 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1491,8 +1491,7 @@ out: return ret; } -#define VM_NO_THP (VM_SPECIAL|VM_INSERTPAGE|VM_MIXEDMAP| \ - VM_HUGETLB|VM_SHARED|VM_MAYSHARE) +#define VM_NO_THP (VM_SPECIAL|VM_MIXEDMAP|VM_HUGETLB|VM_SHARED|VM_MAYSHARE) int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) diff --git a/mm/ksm.c b/mm/ksm.c index d1cbe2aa6b3a..f9ccb16559ee 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -1469,7 +1469,7 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start, */ if (*vm_flags & (VM_MERGEABLE | VM_SHARED | VM_MAYSHARE | VM_PFNMAP | VM_IO | VM_DONTEXPAND | - VM_RESERVED | VM_HUGETLB | VM_INSERTPAGE | + VM_RESERVED | VM_HUGETLB | VM_NONLINEAR | VM_MIXEDMAP)) return 0; /* just ignore the advice */ diff --git a/mm/memory.c b/mm/memory.c index 655e1429388a..7b1e4feaec06 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1047,7 +1047,8 @@ 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_NONLINEAR|VM_PFNMAP|VM_INSERTPAGE))) { + if (!(vma->vm_flags & (VM_HUGETLB | VM_NONLINEAR | + VM_PFNMAP | VM_MIXEDMAP))) { if (!vma->anon_vma) return 0; } @@ -2085,6 +2086,11 @@ out: * ask for a shared writable mapping! * * The page does not need to be reserved. + * + * Usually this function is called from f_op->mmap() handler + * under mm->mmap_sem write-lock, so it can change vma->vm_flags. + * Caller must set VM_MIXEDMAP on vma if it wants to call this + * function from other places, for example from page-fault handler. */ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) @@ -2093,7 +2099,11 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, return -EFAULT; if (!page_count(page)) return -EINVAL; - vma->vm_flags |= VM_INSERTPAGE; + if (!(vma->vm_flags & VM_MIXEDMAP)) { + BUG_ON(down_read_trylock(&vma->vm_mm->mmap_sem)); + BUG_ON(vma->vm_flags & VM_PFNMAP); + vma->vm_flags |= VM_MIXEDMAP; + } return insert_page(vma, addr, page, vma->vm_page_prot); } EXPORT_SYMBOL(vm_insert_page); diff --git a/mm/mmap.c b/mm/mmap.c index 872441e81914..b0989f4d4f09 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1190,7 +1190,7 @@ int vma_wants_writenotify(struct vm_area_struct *vma) return 0; /* Specialty mapping? */ - if (vm_flags & (VM_PFNMAP|VM_INSERTPAGE)) + if (vm_flags & VM_PFNMAP) return 0; /* Can the mapping track the dirty pages? */