Message-ID: <20200214142857.kcmjiequhfl3sot2@box>
Date:   Fri, 14 Feb 2020 17:28:57 +0300
From:   "Kirill A. Shutemov" <kirill@...temov.name>
To:     Brian Geffon <bgeffon@...gle.com>
Cc:     Andrew Morton <akpm@...ux-foundation.org>,
        "Michael S . Tsirkin" <mst@...hat.com>,
        Arnd Bergmann <arnd@...db.de>, linux-kernel@...r.kernel.org,
        linux-mm@...ck.org, linux-api@...r.kernel.org,
        Andy Lutomirski <luto@...capital.net>,
        Will Deacon <will@...nel.org>,
        Andrea Arcangeli <aarcange@...hat.com>,
        Sonny Rao <sonnyrao@...gle.com>,
        Minchan Kim <minchan@...nel.org>,
        Joel Fernandes <joel@...lfernandes.org>,
        Yu Zhao <yuzhao@...gle.com>,
        Jesse Barnes <jsbarnes@...gle.com>,
        Nathan Chancellor <natechancellor@...il.com>,
        Florian Weimer <fweimer@...hat.com>
Subject: Re: [PATCH v5 1/2] mm: Add MREMAP_DONTUNMAP to mremap().

On Thu, Feb 13, 2020 at 08:09:51PM -0800, Brian Geffon wrote:
> When remapping an anonymous, private mapping, if MREMAP_DONTUNMAP is
> set, the source mapping will not be removed. The remap operation
> will be performed as it would have been normally by moving over the
> page tables to the new mapping. The old vma will have any locked
> flags cleared, have no pagetables, and any userfaultfds that were
> watching that range will continue watching it.
> 
> For a mapping that is shared or not anonymous, MREMAP_DONTUNMAP will cause
> the mremap() call to fail. Because MREMAP_DONTUNMAP always results in moving
> a VMA you MUST use the MREMAP_MAYMOVE flag. The final result is two
> equally sized VMAs where the destination contains the PTEs of the source.
> 
> We hope to use this in Chrome OS where with userfaultfd we could write
> an anonymous mapping to disk without having to STOP the process or worry
> about VMA permission changes.
> 
> This feature also has a use case in Android, Lokesh Gidra has said
> that "As part of using userfaultfd for GC, We'll have to move the physical
> pages of the java heap to a separate location. For this purpose mremap
> will be used. Without the MREMAP_DONTUNMAP flag, when I mremap the java
> heap, its virtual mapping will be removed as well. Therefore, we'll
> require performing mmap immediately after. This is not only time consuming
> but also opens a time window where a native thread may call mmap and
> reserve the java heap's address range for its own usage. This flag
> solves the problem."
> 
>   v4 -> v5:
>     - Correct commit message to more accurately reflect the behavior.
>     - Clear VM_LOCKED and VM_LOCKEDONFAULT on the old vma.
>            
> Signed-off-by: Brian Geffon <bgeffon@...gle.com>
> 
> ---
>  include/uapi/linux/mman.h |   5 +-
>  mm/mremap.c               | 106 ++++++++++++++++++++++++++++++--------
>  2 files changed, 88 insertions(+), 23 deletions(-)
> 
> diff --git a/include/uapi/linux/mman.h b/include/uapi/linux/mman.h
> index fc1a64c3447b..923cc162609c 100644
> --- a/include/uapi/linux/mman.h
> +++ b/include/uapi/linux/mman.h
> @@ -5,8 +5,9 @@
>  #include <asm/mman.h>
>  #include <asm-generic/hugetlb_encode.h>
>  
> -#define MREMAP_MAYMOVE	1
> -#define MREMAP_FIXED	2
> +#define MREMAP_MAYMOVE		1
> +#define MREMAP_FIXED		2
> +#define MREMAP_DONTUNMAP	4
>  
>  #define OVERCOMMIT_GUESS		0
>  #define OVERCOMMIT_ALWAYS		1
> diff --git a/mm/mremap.c b/mm/mremap.c
> index 1fc8a29fbe3f..a2a792fdbc64 100644
> --- a/mm/mremap.c
> +++ b/mm/mremap.c
> @@ -318,8 +318,8 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
>  static unsigned long move_vma(struct vm_area_struct *vma,
>  		unsigned long old_addr, unsigned long old_len,
>  		unsigned long new_len, unsigned long new_addr,
> -		bool *locked, struct vm_userfaultfd_ctx *uf,
> -		struct list_head *uf_unmap)
> +		bool *locked, unsigned long flags,
> +		struct vm_userfaultfd_ctx *uf, struct list_head *uf_unmap)
>  {
>  	struct mm_struct *mm = vma->vm_mm;
>  	struct vm_area_struct *new_vma;
> @@ -408,11 +408,49 @@ static unsigned long move_vma(struct vm_area_struct *vma,
>  	if (unlikely(vma->vm_flags & VM_PFNMAP))
>  		untrack_pfn_moved(vma);
>  
> +	if (unlikely(!err && (flags & MREMAP_DONTUNMAP))) {
> +		if (vm_flags & VM_ACCOUNT) {
> +			/* Always put back VM_ACCOUNT since we won't unmap */
> +			vma->vm_flags |= VM_ACCOUNT;
> +
> +			vm_acct_memory(vma_pages(new_vma));
> +		}
> +
> +		/*
> +		 * locked_vm accounting: if the mapping remained the same size
> +		 * it will have just moved and we don't need to touch locked_vm
> +		 * because we skip the do_unmap. If the mapping shrunk before
> +		 * being moved then the do_unmap on that portion will have
> +		 * adjusted vm_locked. Only if the mapping grows do we need to
> +		 * do something special; the reason is locked_vm only accounts
> +		 * for old_len, but we're now adding new_len - old_len locked
> +		 * bytes to the new mapping.
> +		 */
> +		if (vm_flags & VM_LOCKED) {
> +			/* We always clear VM_LOCKED[ONFAULT] on the old vma */
> +			vma->vm_flags &= VM_LOCKED_CLEAR_MASK;
> +
> +			if (new_len > old_len) {
> +				mm->locked_vm +=
> +					(new_len - old_len) >> PAGE_SHIFT;
> +				*locked = true;

This level of code indentation suggests that code restructuring is
required.

> +			}
> +		}
> +
> +		goto out;
> +	}
> +
>  	if (do_munmap(mm, old_addr, old_len, uf_unmap) < 0) {
>  		/* OOM: unable to split vma, just get accounts right */
>  		vm_unacct_memory(excess >> PAGE_SHIFT);
>  		excess = 0;
>  	}
> +
> +	if (vm_flags & VM_LOCKED) {
> +		mm->locked_vm += new_len >> PAGE_SHIFT;
> +		*locked = true;
> +	}

I don't follow why this is required.

> +out:
>  	mm->hiwater_vm = hiwater_vm;
>  
>  	/* Restore VM_ACCOUNT if one or two pieces of vma left */
> @@ -422,16 +460,12 @@ static unsigned long move_vma(struct vm_area_struct *vma,
>  			vma->vm_next->vm_flags |= VM_ACCOUNT;
>  	}
>  
> -	if (vm_flags & VM_LOCKED) {
> -		mm->locked_vm += new_len >> PAGE_SHIFT;
> -		*locked = true;
> -	}
> -

Ah. You moved this piece. Why?

>  	return new_addr;
>  }
>  
>  static struct vm_area_struct *vma_to_resize(unsigned long addr,
> -	unsigned long old_len, unsigned long new_len, unsigned long *p)
> +	unsigned long old_len, unsigned long new_len, unsigned long flags,
> +	unsigned long *p)
>  {
>  	struct mm_struct *mm = current->mm;
>  	struct vm_area_struct *vma = find_vma(mm, addr);
> @@ -453,6 +487,10 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr,
>  		return ERR_PTR(-EINVAL);
>  	}
>  
> +	if (flags & MREMAP_DONTUNMAP && (!vma_is_anonymous(vma) ||
> +			vma->vm_flags & VM_SHARED))
> +		return ERR_PTR(-EINVAL);
> +
>  	if (is_vm_hugetlb_page(vma))
>  		return ERR_PTR(-EINVAL);
>  
> @@ -497,7 +535,7 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr,
>  
>  static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
>  		unsigned long new_addr, unsigned long new_len, bool *locked,
> -		struct vm_userfaultfd_ctx *uf,
> +		unsigned long flags, struct vm_userfaultfd_ctx *uf,
>  		struct list_head *uf_unmap_early,
>  		struct list_head *uf_unmap)
>  {
> @@ -505,7 +543,7 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
>  	struct vm_area_struct *vma;
>  	unsigned long ret = -EINVAL;
>  	unsigned long charged = 0;
> -	unsigned long map_flags;
> +	unsigned long map_flags = 0;
>  
>  	if (offset_in_page(new_addr))
>  		goto out;
> @@ -534,9 +572,11 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
>  	if ((mm->map_count + 2) >= sysctl_max_map_count - 3)
>  		return -ENOMEM;
>  
> -	ret = do_munmap(mm, new_addr, new_len, uf_unmap_early);
> -	if (ret)
> -		goto out;
> +	if (flags & MREMAP_FIXED) {

I think it has to be

	if (!(flags & MREMAP_DONTUNMAP)) {

No?


> +		ret = do_munmap(mm, new_addr, new_len, uf_unmap_early);
> +		if (ret)
> +			goto out;
> +	}
>  
>  	if (old_len >= new_len) {
>  		ret = do_munmap(mm, addr+new_len, old_len - new_len, uf_unmap);
> @@ -545,13 +585,26 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
>  		old_len = new_len;
>  	}
>  
> -	vma = vma_to_resize(addr, old_len, new_len, &charged);
> +	vma = vma_to_resize(addr, old_len, new_len, flags, &charged);
>  	if (IS_ERR(vma)) {
>  		ret = PTR_ERR(vma);
>  		goto out;
>  	}
>  
> -	map_flags = MAP_FIXED;
> +	/*
> +	 * MREMAP_DONTUNMAP expands by new_len - (new_len - old_len), we will
> +	 * check that we can expand by new_len and vma_to_resize will handle
> +	 * the vma growing which is (new_len - old_len).
> +	 */
> +	if (flags & MREMAP_DONTUNMAP &&
> +		!may_expand_vm(mm, vma->vm_flags, new_len >> PAGE_SHIFT)) {
> +		ret = -ENOMEM;
> +		goto out;
> +	}
> +
> +	if (flags & MREMAP_FIXED)
> +		map_flags |= MAP_FIXED;
> +
>  	if (vma->vm_flags & VM_MAYSHARE)
>  		map_flags |= MAP_SHARED;
>  
> @@ -561,10 +614,16 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
>  	if (offset_in_page(ret))
>  		goto out1;
>  
> -	ret = move_vma(vma, addr, old_len, new_len, new_addr, locked, uf,
> +	/* We got a new mapping */
> +	if (!(flags & MREMAP_FIXED))
> +		new_addr = ret;
> +
> +	ret = move_vma(vma, addr, old_len, new_len, new_addr, locked, flags, uf,
>  		       uf_unmap);
> +
>  	if (!(offset_in_page(ret)))
>  		goto out;
> +
>  out1:
>  	vm_unacct_memory(charged);
>  
> @@ -609,12 +668,16 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
>  	addr = untagged_addr(addr);
>  	new_addr = untagged_addr(new_addr);
>  
> -	if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
> +	if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE | MREMAP_DONTUNMAP))
>  		return ret;
>  
>  	if (flags & MREMAP_FIXED && !(flags & MREMAP_MAYMOVE))
>  		return ret;
>  
> +	/* MREMAP_DONTUNMAP is always a move */
> +	if (flags & MREMAP_DONTUNMAP && !(flags & MREMAP_MAYMOVE))
> +		return ret;
> +
>  	if (offset_in_page(addr))
>  		return ret;
>  
> @@ -632,9 +695,10 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
>  	if (down_write_killable(&current->mm->mmap_sem))
>  		return -EINTR;
>  
> -	if (flags & MREMAP_FIXED) {
> +	if (flags & MREMAP_FIXED || flags & MREMAP_DONTUNMAP) {

	if (flags & (MREMAP_FIXED | MREMAP_DONTUNMAP)) {

>  		ret = mremap_to(addr, old_len, new_addr, new_len,
> -				&locked, &uf, &uf_unmap_early, &uf_unmap);
> +				&locked, flags, &uf, &uf_unmap_early,
> +				&uf_unmap);
>  		goto out;
>  	}
>  
> @@ -662,7 +726,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
>  	/*
>  	 * Ok, we need to grow..
>  	 */
> -	vma = vma_to_resize(addr, old_len, new_len, &charged);
> +	vma = vma_to_resize(addr, old_len, new_len, flags, &charged);
>  	if (IS_ERR(vma)) {
>  		ret = PTR_ERR(vma);
>  		goto out;
> @@ -712,7 +776,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
>  		}
>  
>  		ret = move_vma(vma, addr, old_len, new_len, new_addr,
> -			       &locked, &uf, &uf_unmap);
> +			       &locked, flags, &uf, &uf_unmap);
>  	}
>  out:
>  	if (offset_in_page(ret)) {
> -- 
> 2.25.0.265.gbab2e86ba0-goog
> 

-- 
 Kirill A. Shutemov

Powered by blists - more mailing lists