* [v2 PATCH 1/2 -mm] mm: mremap: dwongrade mmap_sem to read when shrinking
@ 2018-09-26 18:10 Yang Shi
2018-09-26 18:10 ` [v2 PATCH 2/2 -mm] mm: brk: " Yang Shi
` (2 more replies)
0 siblings, 3 replies; 10+ messages in thread
From: Yang Shi @ 2018-09-26 18:10 UTC (permalink / raw)
To: mhocko, kirill, willy, ldufour, vbabka, akpm
Cc: yang.shi, linux-mm, linux-kernel
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.
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Laurent Dufour <ldufour@linux.vnet.ibm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com>
---
v2: Rephrase the commit log per Michal
include/linux/mm.h | 2 ++
mm/mmap.c | 4 ++--
mm/mremap.c | 17 +++++++++++++----
3 files changed, 17 insertions(+), 6 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a61ebe8..3028028 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2286,6 +2286,8 @@ 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 847a17d..017bcfa 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 <jeremy@goop.org>
*/
-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 5c2e185..8f1ec2b 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -525,6 +525,7 @@ static int vma_expandable(struct vm_area_struct *vma, unsigned long delta)
unsigned long ret = -EINVAL;
unsigned long charged = 0;
bool locked = false;
+ bool downgrade = false;
struct vm_userfaultfd_ctx uf = NULL_VM_UFFD_CTX;
LIST_HEAD(uf_unmap_early);
LIST_HEAD(uf_unmap);
@@ -561,12 +562,17 @@ static int vma_expandable(struct vm_area_struct *vma, unsigned long delta)
/*
* 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
+ * downgrade mmap_sem to read.
*/
if (old_len >= new_len) {
- ret = do_munmap(mm, addr+new_len, old_len - new_len, &uf_unmap);
- if (ret && old_len != new_len)
+ ret = __do_munmap(mm, addr+new_len, old_len - new_len,
+ &uf_unmap, true);
+ if (ret < 0 && old_len != new_len)
goto out;
+ /* Returning 1 indicates mmap_sem is downgraded to read. */
+ else if (ret == 1)
+ downgrade = true;
ret = addr;
goto out;
}
@@ -631,7 +637,10 @@ static int vma_expandable(struct vm_area_struct *vma, unsigned long delta)
vm_unacct_memory(charged);
locked = 0;
}
- up_write(¤t->mm->mmap_sem);
+ if (downgrade)
+ 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);
--
1.8.3.1
^ permalink raw reply related [flat|nested] 10+ messages in thread
* [v2 PATCH 2/2 -mm] mm: brk: dwongrade mmap_sem to read when shrinking
2018-09-26 18:10 [v2 PATCH 1/2 -mm] mm: mremap: dwongrade mmap_sem to read when shrinking Yang Shi
@ 2018-09-26 18:10 ` Yang Shi
2018-09-27 12:14 ` Vlastimil Babka
2018-09-27 12:50 ` Kirill A. Shutemov
2018-09-27 11:50 ` [v2 PATCH 1/2 -mm] mm: mremap: " Vlastimil Babka
2018-09-27 12:46 ` Kirill A. Shutemov
2 siblings, 2 replies; 10+ messages in thread
From: Yang Shi @ 2018-09-26 18:10 UTC (permalink / raw)
To: mhocko, kirill, willy, ldufour, vbabka, akpm
Cc: yang.shi, linux-mm, linux-kernel
brk might be used to shinrk memory mapping too other than munmap().
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 brk() will not manipulate vmas anymore after __do_munmap() call for
the mapping shrink use case. But, it may set mm->brk after
__do_munmap(), which needs hold write mmap_sem.
However, a simple trick can workaround this by setting mm->brk before
__do_munmap(). Then restore the original value if __do_munmap() fails.
With this trick, 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.
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Laurent Dufour <ldufour@linux.vnet.ibm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com>
---
v2: Rephrase the commit per Michal
mm/mmap.c | 40 ++++++++++++++++++++++++++++++----------
1 file changed, 30 insertions(+), 10 deletions(-)
diff --git a/mm/mmap.c b/mm/mmap.c
index 017bcfa..0d2fae1 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -193,9 +193,11 @@ static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long
unsigned long retval;
unsigned long newbrk, oldbrk;
struct mm_struct *mm = current->mm;
+ unsigned long origbrk = mm->brk;
struct vm_area_struct *next;
unsigned long min_brk;
bool populate;
+ bool downgrade = false;
LIST_HEAD(uf);
if (down_write_killable(&mm->mmap_sem))
@@ -229,14 +231,29 @@ static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long
newbrk = PAGE_ALIGN(brk);
oldbrk = PAGE_ALIGN(mm->brk);
- if (oldbrk == newbrk)
- goto set_brk;
+ if (oldbrk == newbrk) {
+ mm->brk = brk;
+ goto success;
+ }
- /* Always allow shrinking brk. */
+ /*
+ * Always allow shrinking brk.
+ * __do_munmap() may downgrade mmap_sem to read.
+ */
if (brk <= mm->brk) {
- if (!do_munmap(mm, newbrk, oldbrk-newbrk, &uf))
- goto set_brk;
- goto out;
+ /*
+ * mm->brk need to be protected by write mmap_sem, update it
+ * before downgrading mmap_sem.
+ * When __do_munmap fail, it will be restored from origbrk.
+ */
+ mm->brk = brk;
+ retval = __do_munmap(mm, newbrk, oldbrk-newbrk, &uf, true);
+ if (retval < 0) {
+ mm->brk = origbrk;
+ goto out;
+ } else if (retval == 1)
+ downgrade = true;
+ goto success;
}
/* Check against existing mmap mappings. */
@@ -247,18 +264,21 @@ static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long
/* Ok, looks good - let it rip. */
if (do_brk_flags(oldbrk, newbrk-oldbrk, 0, &uf) < 0)
goto out;
-
-set_brk:
mm->brk = brk;
+
+success:
populate = newbrk > oldbrk && (mm->def_flags & VM_LOCKED) != 0;
- up_write(&mm->mmap_sem);
+ if (downgrade)
+ up_read(&mm->mmap_sem);
+ else
+ up_write(&mm->mmap_sem);
userfaultfd_unmap_complete(mm, &uf);
if (populate)
mm_populate(oldbrk, newbrk - oldbrk);
return brk;
out:
- retval = mm->brk;
+ retval = origbrk;
up_write(&mm->mmap_sem);
return retval;
}
--
1.8.3.1
^ permalink raw reply related [flat|nested] 10+ messages in thread
* Re: [v2 PATCH 1/2 -mm] mm: mremap: dwongrade mmap_sem to read when shrinking
2018-09-26 18:10 [v2 PATCH 1/2 -mm] mm: mremap: dwongrade mmap_sem to read when shrinking Yang Shi
2018-09-26 18:10 ` [v2 PATCH 2/2 -mm] mm: brk: " Yang Shi
@ 2018-09-27 11:50 ` Vlastimil Babka
2018-09-27 16:04 ` Yang Shi
2018-09-27 12:46 ` Kirill A. Shutemov
2 siblings, 1 reply; 10+ messages in thread
From: Vlastimil Babka @ 2018-09-27 11:50 UTC (permalink / raw)
To: Yang Shi, mhocko, kirill, willy, ldufour, akpm; +Cc: linux-mm, linux-kernel
On 9/26/18 8:10 PM, Yang Shi wrote:
> Subject: [v2 PATCH 1/2 -mm] mm: mremap: dwongrade mmap_sem to read
when shrinking
"downgrade" in the subject
> 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.
>
> Cc: Michal Hocko <mhocko@kernel.org>
> Cc: Kirill A. Shutemov <kirill@shutemov.name>
> Cc: Matthew Wilcox <willy@infradead.org>
> Cc: Laurent Dufour <ldufour@linux.vnet.ibm.com>
> Cc: Vlastimil Babka <vbabka@suse.cz>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com>
Looks fine,
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Nit:
> --- 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 <jeremy@goop.org>
> */
> -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 5c2e185..8f1ec2b 100644
> --- a/mm/mremap.c
> +++ b/mm/mremap.c
> @@ -525,6 +525,7 @@ static int vma_expandable(struct vm_area_struct *vma, unsigned long delta)
> unsigned long ret = -EINVAL;
> unsigned long charged = 0;
> bool locked = false;
> + bool downgrade = false;
Maybe "downgraded" is more accurate here, or even "downgraded_mmap_sem".
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [v2 PATCH 2/2 -mm] mm: brk: dwongrade mmap_sem to read when shrinking
2018-09-26 18:10 ` [v2 PATCH 2/2 -mm] mm: brk: " Yang Shi
@ 2018-09-27 12:14 ` Vlastimil Babka
2018-09-27 16:05 ` Yang Shi
2018-09-27 12:50 ` Kirill A. Shutemov
1 sibling, 1 reply; 10+ messages in thread
From: Vlastimil Babka @ 2018-09-27 12:14 UTC (permalink / raw)
To: Yang Shi, mhocko, kirill, willy, ldufour, akpm; +Cc: linux-mm, linux-kernel
On 9/26/18 8:10 PM, Yang Shi wrote:
Again, "downgrade" in the subject
> brk might be used to shinrk memory mapping too other than munmap().
^ shrink
> 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 brk() will not manipulate vmas anymore after __do_munmap() call for
> the mapping shrink use case. But, it may set mm->brk after
> __do_munmap(), which needs hold write mmap_sem.
>
> However, a simple trick can workaround this by setting mm->brk before
> __do_munmap(). Then restore the original value if __do_munmap() fails.
> With this trick, 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.
>
> Cc: Michal Hocko <mhocko@kernel.org>
> Cc: Kirill A. Shutemov <kirill@shutemov.name>
> Cc: Matthew Wilcox <willy@infradead.org>
> Cc: Laurent Dufour <ldufour@linux.vnet.ibm.com>
> Cc: Vlastimil Babka <vbabka@suse.cz>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Same nit for the "bool downgrade" name as for patch 1/2.
Thanks,
Vlastimil
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [v2 PATCH 1/2 -mm] mm: mremap: dwongrade mmap_sem to read when shrinking
2018-09-26 18:10 [v2 PATCH 1/2 -mm] mm: mremap: dwongrade mmap_sem to read when shrinking Yang Shi
2018-09-26 18:10 ` [v2 PATCH 2/2 -mm] mm: brk: " Yang Shi
2018-09-27 11:50 ` [v2 PATCH 1/2 -mm] mm: mremap: " Vlastimil Babka
@ 2018-09-27 12:46 ` Kirill A. Shutemov
2 siblings, 0 replies; 10+ messages in thread
From: Kirill A. Shutemov @ 2018-09-27 12:46 UTC (permalink / raw)
To: Yang Shi; +Cc: mhocko, willy, ldufour, vbabka, akpm, linux-mm, linux-kernel
On Thu, Sep 27, 2018 at 02:10:33AM +0800, Yang Shi wrote:
> 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.
>
> Cc: Michal Hocko <mhocko@kernel.org>
> Cc: Kirill A. Shutemov <kirill@shutemov.name>
> Cc: Matthew Wilcox <willy@infradead.org>
> Cc: Laurent Dufour <ldufour@linux.vnet.ibm.com>
> Cc: Vlastimil Babka <vbabka@suse.cz>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com>
> ---
> v2: Rephrase the commit log per Michal
>
> include/linux/mm.h | 2 ++
> mm/mmap.c | 4 ++--
> mm/mremap.c | 17 +++++++++++++----
> 3 files changed, 17 insertions(+), 6 deletions(-)
>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index a61ebe8..3028028 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -2286,6 +2286,8 @@ 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 847a17d..017bcfa 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 <jeremy@goop.org>
> */
> -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 5c2e185..8f1ec2b 100644
> --- a/mm/mremap.c
> +++ b/mm/mremap.c
> @@ -525,6 +525,7 @@ static int vma_expandable(struct vm_area_struct *vma, unsigned long delta)
> unsigned long ret = -EINVAL;
> unsigned long charged = 0;
> bool locked = false;
> + bool downgrade = false;
s/downgrade/downgraded/ ?
Otherwise looks good to me:
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
--
Kirill A. Shutemov
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [v2 PATCH 2/2 -mm] mm: brk: dwongrade mmap_sem to read when shrinking
2018-09-26 18:10 ` [v2 PATCH 2/2 -mm] mm: brk: " Yang Shi
2018-09-27 12:14 ` Vlastimil Babka
@ 2018-09-27 12:50 ` Kirill A. Shutemov
2018-09-27 13:21 ` Vlastimil Babka
2018-09-27 16:06 ` Yang Shi
1 sibling, 2 replies; 10+ messages in thread
From: Kirill A. Shutemov @ 2018-09-27 12:50 UTC (permalink / raw)
To: Yang Shi; +Cc: mhocko, willy, ldufour, vbabka, akpm, linux-mm, linux-kernel
On Thu, Sep 27, 2018 at 02:10:34AM +0800, Yang Shi wrote:
> brk might be used to shinrk memory mapping too other than munmap().
s/shinrk/shrink/
> 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 brk() will not manipulate vmas anymore after __do_munmap() call for
> the mapping shrink use case. But, it may set mm->brk after
> __do_munmap(), which needs hold write mmap_sem.
>
> However, a simple trick can workaround this by setting mm->brk before
> __do_munmap(). Then restore the original value if __do_munmap() fails.
> With this trick, 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.
>
> Cc: Michal Hocko <mhocko@kernel.org>
> Cc: Kirill A. Shutemov <kirill@shutemov.name>
> Cc: Matthew Wilcox <willy@infradead.org>
> Cc: Laurent Dufour <ldufour@linux.vnet.ibm.com>
> Cc: Vlastimil Babka <vbabka@suse.cz>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com>
> ---
> v2: Rephrase the commit per Michal
>
> mm/mmap.c | 40 ++++++++++++++++++++++++++++++----------
> 1 file changed, 30 insertions(+), 10 deletions(-)
>
> diff --git a/mm/mmap.c b/mm/mmap.c
> index 017bcfa..0d2fae1 100644
> --- a/mm/mmap.c
> +++ b/mm/mmap.c
> @@ -193,9 +193,11 @@ static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long
> unsigned long retval;
> unsigned long newbrk, oldbrk;
> struct mm_struct *mm = current->mm;
> + unsigned long origbrk = mm->brk;
Is it safe to read mm->brk outside the lock?
> struct vm_area_struct *next;
> unsigned long min_brk;
> bool populate;
> + bool downgrade = false;
Again,
s/downgrade/downgraded/ ?
> LIST_HEAD(uf);
>
> if (down_write_killable(&mm->mmap_sem))
> @@ -229,14 +231,29 @@ static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long
>
> newbrk = PAGE_ALIGN(brk);
> oldbrk = PAGE_ALIGN(mm->brk);
> - if (oldbrk == newbrk)
> - goto set_brk;
> + if (oldbrk == newbrk) {
> + mm->brk = brk;
> + goto success;
> + }
>
> - /* Always allow shrinking brk. */
> + /*
> + * Always allow shrinking brk.
> + * __do_munmap() may downgrade mmap_sem to read.
> + */
> if (brk <= mm->brk) {
> - if (!do_munmap(mm, newbrk, oldbrk-newbrk, &uf))
> - goto set_brk;
> - goto out;
> + /*
> + * mm->brk need to be protected by write mmap_sem, update it
> + * before downgrading mmap_sem.
> + * When __do_munmap fail, it will be restored from origbrk.
> + */
> + mm->brk = brk;
> + retval = __do_munmap(mm, newbrk, oldbrk-newbrk, &uf, true);
> + if (retval < 0) {
> + mm->brk = origbrk;
> + goto out;
> + } else if (retval == 1)
> + downgrade = true;
> + goto success;
> }
>
> /* Check against existing mmap mappings. */
> @@ -247,18 +264,21 @@ static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long
> /* Ok, looks good - let it rip. */
> if (do_brk_flags(oldbrk, newbrk-oldbrk, 0, &uf) < 0)
> goto out;
> -
> -set_brk:
> mm->brk = brk;
> +
> +success:
> populate = newbrk > oldbrk && (mm->def_flags & VM_LOCKED) != 0;
> - up_write(&mm->mmap_sem);
> + if (downgrade)
> + up_read(&mm->mmap_sem);
> + else
> + up_write(&mm->mmap_sem);
> userfaultfd_unmap_complete(mm, &uf);
> if (populate)
> mm_populate(oldbrk, newbrk - oldbrk);
> return brk;
>
> out:
> - retval = mm->brk;
> + retval = origbrk;
> up_write(&mm->mmap_sem);
> return retval;
> }
> --
> 1.8.3.1
>
--
Kirill A. Shutemov
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [v2 PATCH 2/2 -mm] mm: brk: dwongrade mmap_sem to read when shrinking
2018-09-27 12:50 ` Kirill A. Shutemov
@ 2018-09-27 13:21 ` Vlastimil Babka
2018-09-27 16:06 ` Yang Shi
1 sibling, 0 replies; 10+ messages in thread
From: Vlastimil Babka @ 2018-09-27 13:21 UTC (permalink / raw)
To: Kirill A. Shutemov, Yang Shi
Cc: mhocko, willy, ldufour, akpm, linux-mm, linux-kernel
On 9/27/18 2:50 PM, Kirill A. Shutemov wrote:
>> diff --git a/mm/mmap.c b/mm/mmap.c
>> index 017bcfa..0d2fae1 100644
>> --- a/mm/mmap.c
>> +++ b/mm/mmap.c
>> @@ -193,9 +193,11 @@ static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long
>> unsigned long retval;
>> unsigned long newbrk, oldbrk;
>> struct mm_struct *mm = current->mm;
>> + unsigned long origbrk = mm->brk;
>
> Is it safe to read mm->brk outside the lock?
Good catch! I guess not, parallel brk()'s could then race.
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [v2 PATCH 1/2 -mm] mm: mremap: dwongrade mmap_sem to read when shrinking
2018-09-27 11:50 ` [v2 PATCH 1/2 -mm] mm: mremap: " Vlastimil Babka
@ 2018-09-27 16:04 ` Yang Shi
0 siblings, 0 replies; 10+ messages in thread
From: Yang Shi @ 2018-09-27 16:04 UTC (permalink / raw)
To: Vlastimil Babka, mhocko, kirill, willy, ldufour, akpm
Cc: linux-mm, linux-kernel
On 9/27/18 4:50 AM, Vlastimil Babka wrote:
> On 9/26/18 8:10 PM, Yang Shi wrote:
>> Subject: [v2 PATCH 1/2 -mm] mm: mremap: dwongrade mmap_sem to read
> when shrinking
>
> "downgrade" in the subject
Will fix in the next version.
Thanks,
Yang
>
>> 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.
>>
>> Cc: Michal Hocko <mhocko@kernel.org>
>> Cc: Kirill A. Shutemov <kirill@shutemov.name>
>> Cc: Matthew Wilcox <willy@infradead.org>
>> Cc: Laurent Dufour <ldufour@linux.vnet.ibm.com>
>> Cc: Vlastimil Babka <vbabka@suse.cz>
>> Cc: Andrew Morton <akpm@linux-foundation.org>
>> Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com>
> Looks fine,
>
> Acked-by: Vlastimil Babka <vbabka@suse.cz>
>
> Nit:
>
>> --- 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 <jeremy@goop.org>
>> */
>> -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 5c2e185..8f1ec2b 100644
>> --- a/mm/mremap.c
>> +++ b/mm/mremap.c
>> @@ -525,6 +525,7 @@ static int vma_expandable(struct vm_area_struct *vma, unsigned long delta)
>> unsigned long ret = -EINVAL;
>> unsigned long charged = 0;
>> bool locked = false;
>> + bool downgrade = false;
> Maybe "downgraded" is more accurate here, or even "downgraded_mmap_sem".
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [v2 PATCH 2/2 -mm] mm: brk: dwongrade mmap_sem to read when shrinking
2018-09-27 12:14 ` Vlastimil Babka
@ 2018-09-27 16:05 ` Yang Shi
0 siblings, 0 replies; 10+ messages in thread
From: Yang Shi @ 2018-09-27 16:05 UTC (permalink / raw)
To: Vlastimil Babka, mhocko, kirill, willy, ldufour, akpm
Cc: linux-mm, linux-kernel
On 9/27/18 5:14 AM, Vlastimil Babka wrote:
> On 9/26/18 8:10 PM, Yang Shi wrote:
>
> Again, "downgrade" in the subject
>
>> brk might be used to shinrk memory mapping too other than munmap().
> ^ shrink
>
>> 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 brk() will not manipulate vmas anymore after __do_munmap() call for
>> the mapping shrink use case. But, it may set mm->brk after
>> __do_munmap(), which needs hold write mmap_sem.
>>
>> However, a simple trick can workaround this by setting mm->brk before
>> __do_munmap(). Then restore the original value if __do_munmap() fails.
>> With this trick, 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.
>>
>> Cc: Michal Hocko <mhocko@kernel.org>
>> Cc: Kirill A. Shutemov <kirill@shutemov.name>
>> Cc: Matthew Wilcox <willy@infradead.org>
>> Cc: Laurent Dufour <ldufour@linux.vnet.ibm.com>
>> Cc: Vlastimil Babka <vbabka@suse.cz>
>> Cc: Andrew Morton <akpm@linux-foundation.org>
>> Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com>
> Acked-by: Vlastimil Babka <vbabka@suse.cz>
>
> Same nit for the "bool downgrade" name as for patch 1/2.
Will solve in next version.
Thanks,
Yang
>
> Thanks,
> Vlastimil
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [v2 PATCH 2/2 -mm] mm: brk: dwongrade mmap_sem to read when shrinking
2018-09-27 12:50 ` Kirill A. Shutemov
2018-09-27 13:21 ` Vlastimil Babka
@ 2018-09-27 16:06 ` Yang Shi
1 sibling, 0 replies; 10+ messages in thread
From: Yang Shi @ 2018-09-27 16:06 UTC (permalink / raw)
To: Kirill A. Shutemov
Cc: mhocko, willy, ldufour, vbabka, akpm, linux-mm, linux-kernel
On 9/27/18 5:50 AM, Kirill A. Shutemov wrote:
> On Thu, Sep 27, 2018 at 02:10:34AM +0800, Yang Shi wrote:
>> brk might be used to shinrk memory mapping too other than munmap().
> s/shinrk/shrink/
>
>> 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 brk() will not manipulate vmas anymore after __do_munmap() call for
>> the mapping shrink use case. But, it may set mm->brk after
>> __do_munmap(), which needs hold write mmap_sem.
>>
>> However, a simple trick can workaround this by setting mm->brk before
>> __do_munmap(). Then restore the original value if __do_munmap() fails.
>> With this trick, 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.
>>
>> Cc: Michal Hocko <mhocko@kernel.org>
>> Cc: Kirill A. Shutemov <kirill@shutemov.name>
>> Cc: Matthew Wilcox <willy@infradead.org>
>> Cc: Laurent Dufour <ldufour@linux.vnet.ibm.com>
>> Cc: Vlastimil Babka <vbabka@suse.cz>
>> Cc: Andrew Morton <akpm@linux-foundation.org>
>> Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com>
>> ---
>> v2: Rephrase the commit per Michal
>>
>> mm/mmap.c | 40 ++++++++++++++++++++++++++++++----------
>> 1 file changed, 30 insertions(+), 10 deletions(-)
>>
>> diff --git a/mm/mmap.c b/mm/mmap.c
>> index 017bcfa..0d2fae1 100644
>> --- a/mm/mmap.c
>> +++ b/mm/mmap.c
>> @@ -193,9 +193,11 @@ static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long
>> unsigned long retval;
>> unsigned long newbrk, oldbrk;
>> struct mm_struct *mm = current->mm;
>> + unsigned long origbrk = mm->brk;
> Is it safe to read mm->brk outside the lock?
Aha, thanks for catching this. It can be moved inside down_write().
Will solve in the next version.
Thanks,
Yang
>
>> struct vm_area_struct *next;
>> unsigned long min_brk;
>> bool populate;
>> + bool downgrade = false;
> Again,
>
> s/downgrade/downgraded/ ?
>
>> LIST_HEAD(uf);
>>
>> if (down_write_killable(&mm->mmap_sem))
>> @@ -229,14 +231,29 @@ static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long
>>
>> newbrk = PAGE_ALIGN(brk);
>> oldbrk = PAGE_ALIGN(mm->brk);
>> - if (oldbrk == newbrk)
>> - goto set_brk;
>> + if (oldbrk == newbrk) {
>> + mm->brk = brk;
>> + goto success;
>> + }
>>
>> - /* Always allow shrinking brk. */
>> + /*
>> + * Always allow shrinking brk.
>> + * __do_munmap() may downgrade mmap_sem to read.
>> + */
>> if (brk <= mm->brk) {
>> - if (!do_munmap(mm, newbrk, oldbrk-newbrk, &uf))
>> - goto set_brk;
>> - goto out;
>> + /*
>> + * mm->brk need to be protected by write mmap_sem, update it
>> + * before downgrading mmap_sem.
>> + * When __do_munmap fail, it will be restored from origbrk.
>> + */
>> + mm->brk = brk;
>> + retval = __do_munmap(mm, newbrk, oldbrk-newbrk, &uf, true);
>> + if (retval < 0) {
>> + mm->brk = origbrk;
>> + goto out;
>> + } else if (retval == 1)
>> + downgrade = true;
>> + goto success;
>> }
>>
>> /* Check against existing mmap mappings. */
>> @@ -247,18 +264,21 @@ static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long
>> /* Ok, looks good - let it rip. */
>> if (do_brk_flags(oldbrk, newbrk-oldbrk, 0, &uf) < 0)
>> goto out;
>> -
>> -set_brk:
>> mm->brk = brk;
>> +
>> +success:
>> populate = newbrk > oldbrk && (mm->def_flags & VM_LOCKED) != 0;
>> - up_write(&mm->mmap_sem);
>> + if (downgrade)
>> + up_read(&mm->mmap_sem);
>> + else
>> + up_write(&mm->mmap_sem);
>> userfaultfd_unmap_complete(mm, &uf);
>> if (populate)
>> mm_populate(oldbrk, newbrk - oldbrk);
>> return brk;
>>
>> out:
>> - retval = mm->brk;
>> + retval = origbrk;
>> up_write(&mm->mmap_sem);
>> return retval;
>> }
>> --
>> 1.8.3.1
>>
^ permalink raw reply [flat|nested] 10+ messages in thread
end of thread, other threads:[~2018-09-27 16:06 UTC | newest]
Thread overview: 10+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-09-26 18:10 [v2 PATCH 1/2 -mm] mm: mremap: dwongrade mmap_sem to read when shrinking Yang Shi
2018-09-26 18:10 ` [v2 PATCH 2/2 -mm] mm: brk: " Yang Shi
2018-09-27 12:14 ` Vlastimil Babka
2018-09-27 16:05 ` Yang Shi
2018-09-27 12:50 ` Kirill A. Shutemov
2018-09-27 13:21 ` Vlastimil Babka
2018-09-27 16:06 ` Yang Shi
2018-09-27 11:50 ` [v2 PATCH 1/2 -mm] mm: mremap: " Vlastimil Babka
2018-09-27 16:04 ` Yang Shi
2018-09-27 12:46 ` Kirill A. Shutemov
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).