This series contains few clean up, minor bug fixes and
Convert get_user_pages() to pin_user_pages().
I'm compile tested this, but unable to run-time test,
so any testing help is much appriciated.
v2:
Addressed few review comments and compile issue.
Patch[1/2] from v1 split into 2 in v2.
Cc: John Hubbard <[email protected]>
Cc: Boris Ostrovsky <[email protected]>
Cc: Paul Durrant <[email protected]>
Souptick Joarder (3):
xen/privcmd: Corrected error handling path
xen/privcmd: Mark pages as dirty
xen/privcmd: Convert get_user_pages*() to pin_user_pages*()
drivers/xen/privcmd.c | 32 ++++++++++++++------------------
1 file changed, 14 insertions(+), 18 deletions(-)
--
1.9.1
Previously, if lock_pages() end up partially mapping pages, it used
to return -ERRNO due to which unlock_pages() have to go through
each pages[i] till *nr_pages* to validate them. This can be avoided
by passing correct number of partially mapped pages & -ERRNO separately,
while returning from lock_pages() due to error.
With this fix unlock_pages() doesn't need to validate pages[i] till
*nr_pages* for error scenario and few condition checks can be ignored.
Signed-off-by: Souptick Joarder <[email protected]>
Cc: John Hubbard <[email protected]>
Cc: Boris Ostrovsky <[email protected]>
Cc: Paul Durrant <[email protected]>
---
drivers/xen/privcmd.c | 31 +++++++++++++++----------------
1 file changed, 15 insertions(+), 16 deletions(-)
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index a250d11..33677ea 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -580,13 +580,13 @@ static long privcmd_ioctl_mmap_batch(
static int lock_pages(
struct privcmd_dm_op_buf kbufs[], unsigned int num,
- struct page *pages[], unsigned int nr_pages)
+ struct page *pages[], unsigned int nr_pages, unsigned int *pinned)
{
unsigned int i;
+ int page_count = 0;
for (i = 0; i < num; i++) {
unsigned int requested;
- int pinned;
requested = DIV_ROUND_UP(
offset_in_page(kbufs[i].uptr) + kbufs[i].size,
@@ -594,14 +594,15 @@ static int lock_pages(
if (requested > nr_pages)
return -ENOSPC;
- pinned = get_user_pages_fast(
+ page_count = get_user_pages_fast(
(unsigned long) kbufs[i].uptr,
requested, FOLL_WRITE, pages);
- if (pinned < 0)
- return pinned;
+ if (page_count < 0)
+ return page_count;
- nr_pages -= pinned;
- pages += pinned;
+ *pinned += page_count;
+ nr_pages -= page_count;
+ pages += page_count;
}
return 0;
@@ -611,13 +612,8 @@ static void unlock_pages(struct page *pages[], unsigned int nr_pages)
{
unsigned int i;
- if (!pages)
- return;
-
- for (i = 0; i < nr_pages; i++) {
- if (pages[i])
- put_page(pages[i]);
- }
+ for (i = 0; i < nr_pages; i++)
+ put_page(pages[i]);
}
static long privcmd_ioctl_dm_op(struct file *file, void __user *udata)
@@ -630,6 +626,7 @@ static long privcmd_ioctl_dm_op(struct file *file, void __user *udata)
struct xen_dm_op_buf *xbufs = NULL;
unsigned int i;
long rc;
+ unsigned int pinned = 0;
if (copy_from_user(&kdata, udata, sizeof(kdata)))
return -EFAULT;
@@ -683,9 +680,11 @@ static long privcmd_ioctl_dm_op(struct file *file, void __user *udata)
goto out;
}
- rc = lock_pages(kbufs, kdata.num, pages, nr_pages);
- if (rc)
+ rc = lock_pages(kbufs, kdata.num, pages, nr_pages, &pinned);
+ if (rc < 0) {
+ nr_pages = pinned;
goto out;
+ }
for (i = 0; i < kdata.num; i++) {
set_xen_guest_handle(xbufs[i].h, kbufs[i].uptr);
--
1.9.1
In 2019, we introduced pin_user_pages*() and now we are converting
get_user_pages*() to the new API as appropriate. [1] & [2] could
be referred for more information. This is case 5 as per document [1].
[1] Documentation/core-api/pin_user_pages.rst
[2] "Explicit pinning of user-space pages":
https://lwn.net/Articles/807108/
Signed-off-by: Souptick Joarder <[email protected]>
Cc: John Hubbard <[email protected]>
Cc: Boris Ostrovsky <[email protected]>
Cc: Paul Durrant <[email protected]>
---
drivers/xen/privcmd.c | 10 ++--------
1 file changed, 2 insertions(+), 8 deletions(-)
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index f6c1543..5c5cd24 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -594,7 +594,7 @@ static int lock_pages(
if (requested > nr_pages)
return -ENOSPC;
- page_count = get_user_pages_fast(
+ page_count = pin_user_pages_fast(
(unsigned long) kbufs[i].uptr,
requested, FOLL_WRITE, pages);
if (page_count < 0)
@@ -610,13 +610,7 @@ static int lock_pages(
static void unlock_pages(struct page *pages[], unsigned int nr_pages)
{
- unsigned int i;
-
- for (i = 0; i < nr_pages; i++) {
- if (!PageDirty(pages[i]))
- set_page_dirty_lock(pages[i]);
- put_page(pages[i]);
- }
+ unpin_user_pages_dirty_lock(pages, nr_pages, true);
}
static long privcmd_ioctl_dm_op(struct file *file, void __user *udata)
--
1.9.1
On 06.07.20 20:16, Souptick Joarder wrote:
> Previously, if lock_pages() end up partially mapping pages, it used
> to return -ERRNO due to which unlock_pages() have to go through
> each pages[i] till *nr_pages* to validate them. This can be avoided
> by passing correct number of partially mapped pages & -ERRNO separately,
> while returning from lock_pages() due to error.
>
> With this fix unlock_pages() doesn't need to validate pages[i] till
> *nr_pages* for error scenario and few condition checks can be ignored.
>
> Signed-off-by: Souptick Joarder <[email protected]>
> Cc: John Hubbard <[email protected]>
> Cc: Boris Ostrovsky <[email protected]>
> Cc: Paul Durrant <[email protected]>
> ---
> drivers/xen/privcmd.c | 31 +++++++++++++++----------------
> 1 file changed, 15 insertions(+), 16 deletions(-)
>
> diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
> index a250d11..33677ea 100644
> --- a/drivers/xen/privcmd.c
> +++ b/drivers/xen/privcmd.c
> @@ -580,13 +580,13 @@ static long privcmd_ioctl_mmap_batch(
>
> static int lock_pages(
> struct privcmd_dm_op_buf kbufs[], unsigned int num,
> - struct page *pages[], unsigned int nr_pages)
> + struct page *pages[], unsigned int nr_pages, unsigned int *pinned)
> {
> unsigned int i;
> + int page_count = 0;
Initial value shouldn't be needed, and ...
>
> for (i = 0; i < num; i++) {
> unsigned int requested;
> - int pinned;
... you could move the declaration here.
With that done you can add my
Reviewed-by: Juergen Gross <[email protected]>
Juergen
On Tue, Jul 7, 2020 at 3:05 PM Jürgen Groß <[email protected]> wrote:
>
> On 06.07.20 20:16, Souptick Joarder wrote:
> > Previously, if lock_pages() end up partially mapping pages, it used
> > to return -ERRNO due to which unlock_pages() have to go through
> > each pages[i] till *nr_pages* to validate them. This can be avoided
> > by passing correct number of partially mapped pages & -ERRNO separately,
> > while returning from lock_pages() due to error.
> >
> > With this fix unlock_pages() doesn't need to validate pages[i] till
> > *nr_pages* for error scenario and few condition checks can be ignored.
> >
> > Signed-off-by: Souptick Joarder <[email protected]>
> > Cc: John Hubbard <[email protected]>
> > Cc: Boris Ostrovsky <[email protected]>
> > Cc: Paul Durrant <[email protected]>
> > ---
> > drivers/xen/privcmd.c | 31 +++++++++++++++----------------
> > 1 file changed, 15 insertions(+), 16 deletions(-)
> >
> > diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
> > index a250d11..33677ea 100644
> > --- a/drivers/xen/privcmd.c
> > +++ b/drivers/xen/privcmd.c
> > @@ -580,13 +580,13 @@ static long privcmd_ioctl_mmap_batch(
> >
> > static int lock_pages(
> > struct privcmd_dm_op_buf kbufs[], unsigned int num,
> > - struct page *pages[], unsigned int nr_pages)
> > + struct page *pages[], unsigned int nr_pages, unsigned int *pinned)
> > {
> > unsigned int i;
> > + int page_count = 0;
>
> Initial value shouldn't be needed, and ...
>
> >
> > for (i = 0; i < num; i++) {
> > unsigned int requested;
> > - int pinned;
>
> ... you could move the declaration here.
>
> With that done you can add my
>
> Reviewed-by: Juergen Gross <[email protected]>
Ok. But does it going make any difference other than limiting scope ?
>
>
> Juergen
On 07.07.20 13:40, Souptick Joarder wrote:
> On Tue, Jul 7, 2020 at 3:05 PM Jürgen Groß <[email protected]> wrote:
>>
>> On 06.07.20 20:16, Souptick Joarder wrote:
>>> Previously, if lock_pages() end up partially mapping pages, it used
>>> to return -ERRNO due to which unlock_pages() have to go through
>>> each pages[i] till *nr_pages* to validate them. This can be avoided
>>> by passing correct number of partially mapped pages & -ERRNO separately,
>>> while returning from lock_pages() due to error.
>>>
>>> With this fix unlock_pages() doesn't need to validate pages[i] till
>>> *nr_pages* for error scenario and few condition checks can be ignored.
>>>
>>> Signed-off-by: Souptick Joarder <[email protected]>
>>> Cc: John Hubbard <[email protected]>
>>> Cc: Boris Ostrovsky <[email protected]>
>>> Cc: Paul Durrant <[email protected]>
>>> ---
>>> drivers/xen/privcmd.c | 31 +++++++++++++++----------------
>>> 1 file changed, 15 insertions(+), 16 deletions(-)
>>>
>>> diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
>>> index a250d11..33677ea 100644
>>> --- a/drivers/xen/privcmd.c
>>> +++ b/drivers/xen/privcmd.c
>>> @@ -580,13 +580,13 @@ static long privcmd_ioctl_mmap_batch(
>>>
>>> static int lock_pages(
>>> struct privcmd_dm_op_buf kbufs[], unsigned int num,
>>> - struct page *pages[], unsigned int nr_pages)
>>> + struct page *pages[], unsigned int nr_pages, unsigned int *pinned)
>>> {
>>> unsigned int i;
>>> + int page_count = 0;
>>
>> Initial value shouldn't be needed, and ...
>>
>>>
>>> for (i = 0; i < num; i++) {
>>> unsigned int requested;
>>> - int pinned;
>>
>> ... you could move the declaration here.
>>
>> With that done you can add my
>>
>> Reviewed-by: Juergen Gross <[email protected]>
>
> Ok. But does it going make any difference other than limiting scope ?
Dropping the initializer surely does, and in the end page_count just
replaces the former pinned variable, so why would we want to widen the
scope with this patch?
Juergen
On 06.07.20 20:16, Souptick Joarder wrote:
> In 2019, we introduced pin_user_pages*() and now we are converting
> get_user_pages*() to the new API as appropriate. [1] & [2] could
> be referred for more information. This is case 5 as per document [1].
>
> [1] Documentation/core-api/pin_user_pages.rst
>
> [2] "Explicit pinning of user-space pages":
> https://lwn.net/Articles/807108/
>
> Signed-off-by: Souptick Joarder <[email protected]>
> Cc: John Hubbard <[email protected]>
> Cc: Boris Ostrovsky <[email protected]>
> Cc: Paul Durrant <[email protected]>
Reviewed-by: Juergen Gross <[email protected]>
Juergen
On Tue, Jul 7, 2020 at 5:15 PM Jürgen Groß <[email protected]> wrote:
>
> On 07.07.20 13:40, Souptick Joarder wrote:
> > On Tue, Jul 7, 2020 at 3:05 PM Jürgen Groß <[email protected]> wrote:
> >>
> >> On 06.07.20 20:16, Souptick Joarder wrote:
> >>> Previously, if lock_pages() end up partially mapping pages, it used
> >>> to return -ERRNO due to which unlock_pages() have to go through
> >>> each pages[i] till *nr_pages* to validate them. This can be avoided
> >>> by passing correct number of partially mapped pages & -ERRNO separately,
> >>> while returning from lock_pages() due to error.
> >>>
> >>> With this fix unlock_pages() doesn't need to validate pages[i] till
> >>> *nr_pages* for error scenario and few condition checks can be ignored.
> >>>
> >>> Signed-off-by: Souptick Joarder <[email protected]>
> >>> Cc: John Hubbard <[email protected]>
> >>> Cc: Boris Ostrovsky <[email protected]>
> >>> Cc: Paul Durrant <[email protected]>
> >>> ---
> >>> drivers/xen/privcmd.c | 31 +++++++++++++++----------------
> >>> 1 file changed, 15 insertions(+), 16 deletions(-)
> >>>
> >>> diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
> >>> index a250d11..33677ea 100644
> >>> --- a/drivers/xen/privcmd.c
> >>> +++ b/drivers/xen/privcmd.c
> >>> @@ -580,13 +580,13 @@ static long privcmd_ioctl_mmap_batch(
> >>>
> >>> static int lock_pages(
> >>> struct privcmd_dm_op_buf kbufs[], unsigned int num,
> >>> - struct page *pages[], unsigned int nr_pages)
> >>> + struct page *pages[], unsigned int nr_pages, unsigned int *pinned)
> >>> {
> >>> unsigned int i;
> >>> + int page_count = 0;
> >>
> >> Initial value shouldn't be needed, and ...
> >>
> >>>
> >>> for (i = 0; i < num; i++) {
> >>> unsigned int requested;
> >>> - int pinned;
> >>
> >> ... you could move the declaration here.
> >>
> >> With that done you can add my
> >>
> >> Reviewed-by: Juergen Gross <[email protected]>
> >
> > Ok. But does it going make any difference other than limiting scope ?
>
> Dropping the initializer surely does, and in the end page_count just
> replaces the former pinned variable, so why would we want to widen the
> scope with this patch?
Agree, no reason to move it up. Will change it in v3.
>
>
> Juergen