[RFC,05/12] s390/cio: add protected virtualization support to cio
diff mbox series

Message ID 20190404231622.52531-6-pasic@linux.ibm.com
State New
Headers show
Series
  • s390: virtio: support protected virtualization
Related show

Commit Message

Halil Pasic April 4, 2019, 11:16 p.m. UTC
Virtio-ccw relies on cio mechanisms for bootstrapping the ccw device.
Thus we need to make sure any memory that is used for communication with
the hypervisor is shared.

Signed-off-by: Halil Pasic <pasic@linux.ibm.com>
---
 drivers/s390/cio/ccwreq.c        |  8 +++----
 drivers/s390/cio/device.c        | 46 +++++++++++++++++++++++++++++++---------
 drivers/s390/cio/device_fsm.c    | 40 +++++++++++++++++-----------------
 drivers/s390/cio/device_id.c     | 18 ++++++++--------
 drivers/s390/cio/device_ops.c    |  4 ++--
 drivers/s390/cio/device_pgid.c   | 20 ++++++++---------
 drivers/s390/cio/device_status.c | 24 ++++++++++-----------
 drivers/s390/cio/io_sch.h        | 19 ++++++++++++-----
 8 files changed, 107 insertions(+), 72 deletions(-)

Comments

Cornelia Huck April 9, 2019, 5:55 p.m. UTC | #1
On Fri,  5 Apr 2019 01:16:15 +0200
Halil Pasic <pasic@linux.ibm.com> wrote:

> Virtio-ccw relies on cio mechanisms for bootstrapping the ccw device.

Well, a ccw device is, by definition, using cio mechanisms ;)

Better say: "As virtio-ccw devices are channel devices, we need to use
the dma area for any communication with the hypervisor."
Or something like that.

> Thus we need to make sure any memory that is used for communication with
> the hypervisor is shared.

In this context, does 'hypervisor' always mean 'QEMU/KVM'? If Other
Hypervisors implement protected virtualization, we probably need to
make sure that all common I/O layer control blocks are in the dma area
(including e.g. QDIO), not just what virtio-ccw devices use.

> 
> Signed-off-by: Halil Pasic <pasic@linux.ibm.com>
> ---
>  drivers/s390/cio/ccwreq.c        |  8 +++----
>  drivers/s390/cio/device.c        | 46 +++++++++++++++++++++++++++++++---------
>  drivers/s390/cio/device_fsm.c    | 40 +++++++++++++++++-----------------
>  drivers/s390/cio/device_id.c     | 18 ++++++++--------
>  drivers/s390/cio/device_ops.c    |  4 ++--
>  drivers/s390/cio/device_pgid.c   | 20 ++++++++---------
>  drivers/s390/cio/device_status.c | 24 ++++++++++-----------
>  drivers/s390/cio/io_sch.h        | 19 ++++++++++++-----
>  8 files changed, 107 insertions(+), 72 deletions(-)
> 

(...)

(just looking at which fields are moved for now)

> diff --git a/drivers/s390/cio/io_sch.h b/drivers/s390/cio/io_sch.h
> index 90e4e3a7841b..fc3220fede0f 100644
> --- a/drivers/s390/cio/io_sch.h
> +++ b/drivers/s390/cio/io_sch.h
> @@ -9,15 +9,20 @@
>  #include "css.h"
>  #include "orb.h"
>  
> +
> +struct io_subchannel_dma_area {
> +	struct ccw1 sense_ccw;	/* static ccw for sense command */

The ccw makes sense.

> +};
> +
>  struct io_subchannel_private {
>  	union orb orb;		/* operation request block */
> -	struct ccw1 sense_ccw;	/* static ccw for sense command */
>  	struct ccw_device *cdev;/* pointer to the child ccw device */
>  	struct {
>  		unsigned int suspend:1;	/* allow suspend */
>  		unsigned int prefetch:1;/* deny prefetch */
>  		unsigned int inter:1;	/* suppress intermediate interrupts */
>  	} __packed options;
> +	struct io_subchannel_dma_area *dma_area;
>  } __aligned(8);
>  
>  #define to_io_private(n) ((struct io_subchannel_private *) \
> @@ -115,6 +120,13 @@ enum cdev_todo {
>  #define FAKE_CMD_IRB	1
>  #define FAKE_TM_IRB	2
>  
> +struct ccw_device_dma_area {
> +	struct senseid senseid;	/* SenseID info */
> +	struct ccw1 iccws[2];	/* ccws for SNID/SID/SPGID commands */
> +	struct irb irb;		/* device status */
> +	struct pgid pgid[8];	/* path group IDs per chpid*/

Again, ccws, and blocks that will be written by the hypervisor, which
makes sense as well.

> +};
> +
>  struct ccw_device_private {
>  	struct ccw_device *cdev;
>  	struct subchannel *sch;
> @@ -156,11 +168,7 @@ struct ccw_device_private {
>  	} __attribute__((packed)) flags;
>  	unsigned long intparm;	/* user interruption parameter */
>  	struct qdio_irq *qdio_data;
> -	struct irb irb;		/* device status */
>  	int async_kill_io_rc;
> -	struct senseid senseid;	/* SenseID info */
> -	struct pgid pgid[8];	/* path group IDs per chpid*/
> -	struct ccw1 iccws[2];	/* ccws for SNID/SID/SPGID commands */
>  	struct work_struct todo_work;
>  	enum cdev_todo todo;
>  	wait_queue_head_t wait_q;
> @@ -169,6 +177,7 @@ struct ccw_device_private {
>  	struct list_head cmb_list;	/* list of measured devices */
>  	u64 cmb_start_time;		/* clock value of cmb reset */
>  	void *cmb_wait;			/* deferred cmb enable/disable */
> +	struct ccw_device_dma_area *dma_area;
>  	enum interruption_class int_class;
>  };
>  

So, this leaves some things I'm not sure about, especially as I do not
know the architecture of this new feature.

- This applies only to asynchronously handled things, it seems? So
  things like control blocks modified by stsch/msch/etc does not need
  special treatment?
- What about channel measurements? Or are they not supported?
- What about CHSCs? Or would only asynchronous commands (which we
  currently don't implement in QEMU) need special treatment?
Halil Pasic April 10, 2019, 12:10 a.m. UTC | #2
On Tue, 9 Apr 2019 19:55:48 +0200
Cornelia Huck <cohuck@redhat.com> wrote:

> On Fri,  5 Apr 2019 01:16:15 +0200
> Halil Pasic <pasic@linux.ibm.com> wrote:
> 
> > Virtio-ccw relies on cio mechanisms for bootstrapping the ccw device.
> 
> Well, a ccw device is, by definition, using cio mechanisms ;)

Right, this was supposed to explain to the non-virtio guys why do I
have to deal with this stuff in cio in a series that is about virtio. I
was chiefly alluding to the SENSE stuff.

> 
> Better say: "As virtio-ccw devices are channel devices, we need to use
> the dma area for any communication with the hypervisor."
> Or something like that.

Sure we can come up with a better commit message. Your sentence is
already better than mine ;).

> 
> > Thus we need to make sure any memory that is used for communication with
> > the hypervisor is shared.
> 
> In this context, does 'hypervisor' always mean 'QEMU/KVM'? If Other
> Hypervisors implement protected virtualization, we probably need to
> make sure that all common I/O layer control blocks are in the dma area
> (including e.g. QDIO), not just what virtio-ccw devices use.
> 

Hypervisor could theoretically be something different than QEMU/KVM. Yet,
as stated before, this series is about getting virtio-ccw working
(modulo the TODOs). 

[..]

> >  
> 
> So, this leaves some things I'm not sure about, especially as I do not
> know the architecture of this new feature.
> 
> - This applies only to asynchronously handled things, it seems? So
>   things like control blocks modified by stsch/msch/etc does not need
>   special treatment?

I had a feeble attempt at explaining this in the cover letter:

* make sure that virtio-ccw specific stuff uses shared memory when
  talking to the hypervisor (except communication blocks like ORB, these
  are handled by the hypervisor)

Unfortunately the last 'hypervisor' was supposed to be 'ultravisor'.

I.e. the ultravisor will take care of exposing the control blocks
to the hypervisor (and of changes as well).

> - What about channel measurements? Or are they not supported?

For virtio-ccw channel measurements are not very relevant. I think
it should work as it used to, but I will give it another look later.

> - What about CHSCs? Or would only asynchronous commands (which we
>   currently don't implement in QEMU) need special treatment?
> 

CHSC is special. AFAIR the code of Vasily and Janosch is handling
what needs to be handled. But I will double-check this as well.

Regards,
Halil
Cornelia Huck April 10, 2019, 8:25 a.m. UTC | #3
On Wed, 10 Apr 2019 02:10:44 +0200
Halil Pasic <pasic@linux.ibm.com> wrote:

> On Tue, 9 Apr 2019 19:55:48 +0200
> Cornelia Huck <cohuck@redhat.com> wrote:
> 
> > On Fri,  5 Apr 2019 01:16:15 +0200
> > Halil Pasic <pasic@linux.ibm.com> wrote:

> > > Thus we need to make sure any memory that is used for communication with
> > > the hypervisor is shared.  
> > 
> > In this context, does 'hypervisor' always mean 'QEMU/KVM'? If Other
> > Hypervisors implement protected virtualization, we probably need to
> > make sure that all common I/O layer control blocks are in the dma area
> > (including e.g. QDIO), not just what virtio-ccw devices use.
> >   
> 
> Hypervisor could theoretically be something different than QEMU/KVM. Yet,
> as stated before, this series is about getting virtio-ccw working
> (modulo the TODOs). 

Sure, just wanted to point it out. If this is "enable the common I/O
layer, except for QDIO" or so, that would sound fine to me :)

> 
> [..]
> 
> > >    
> > 
> > So, this leaves some things I'm not sure about, especially as I do not
> > know the architecture of this new feature.
> > 
> > - This applies only to asynchronously handled things, it seems? So
> >   things like control blocks modified by stsch/msch/etc does not need
> >   special treatment?  
> 
> I had a feeble attempt at explaining this in the cover letter:
> 
> * make sure that virtio-ccw specific stuff uses shared memory when
>   talking to the hypervisor (except communication blocks like ORB, these
>   are handled by the hypervisor)
> 
> Unfortunately the last 'hypervisor' was supposed to be 'ultravisor'.
> 
> I.e. the ultravisor will take care of exposing the control blocks
> to the hypervisor (and of changes as well).

Yeah, that "control blocks" or "communication blocks" leaves me a bit
fuzzy :)

So, what is a high-level summary of areas that need the treatment?
What I get from looking at the patches so far, it's:
- stuff that is written by the hypervisor's interrupt injection code:
  IRB, indicators, etc.
- buffers that are filled by a channel program: sense, sense id, etc.
- ccws themselves (because of translation?)
Halil Pasic April 10, 2019, 1:02 p.m. UTC | #4
On Wed, 10 Apr 2019 10:25:57 +0200
Cornelia Huck <cohuck@redhat.com> wrote:

> On Wed, 10 Apr 2019 02:10:44 +0200
> Halil Pasic <pasic@linux.ibm.com> wrote:
> 
> > On Tue, 9 Apr 2019 19:55:48 +0200
> > Cornelia Huck <cohuck@redhat.com> wrote:
> > 
> > > On Fri,  5 Apr 2019 01:16:15 +0200
> > > Halil Pasic <pasic@linux.ibm.com> wrote:
> 
> > > > Thus we need to make sure any memory that is used for communication with
> > > > the hypervisor is shared.  
> > > 
> > > In this context, does 'hypervisor' always mean 'QEMU/KVM'? If Other
> > > Hypervisors implement protected virtualization, we probably need to
> > > make sure that all common I/O layer control blocks are in the dma area
> > > (including e.g. QDIO), not just what virtio-ccw devices use.
> > >   
> > 
> > Hypervisor could theoretically be something different than QEMU/KVM. Yet,
> > as stated before, this series is about getting virtio-ccw working
> > (modulo the TODOs). 
> 
> Sure, just wanted to point it out. If this is "enable the common I/O
> layer, except for QDIO" or so, that would sound fine to me :)
> 

Right except QDIO. Series cares only about the bits relevant for
virtio-ccw. I guess I should make that clearer in the commit message.


> > 
> > [..]
> > 
> > > >    
> > > 
> > > So, this leaves some things I'm not sure about, especially as I do not
> > > know the architecture of this new feature.
> > > 
> > > - This applies only to asynchronously handled things, it seems? So
> > >   things like control blocks modified by stsch/msch/etc does not need
> > >   special treatment?  
> > 
> > I had a feeble attempt at explaining this in the cover letter:
> > 
> > * make sure that virtio-ccw specific stuff uses shared memory when
> >   talking to the hypervisor (except communication blocks like ORB, these
> >   are handled by the hypervisor)
> > 
> > Unfortunately the last 'hypervisor' was supposed to be 'ultravisor'.
> > 
> > I.e. the ultravisor will take care of exposing the control blocks
> > to the hypervisor (and of changes as well).
> 
> Yeah, that "control blocks" or "communication blocks" leaves me a bit
> fuzzy :)

Yeah. I don't know if there is an official name for the stuff. For
the ORB of SSCH control block seems quite fitting. For the SCHIB of
STSCH communication seems a better fit.

> 
> So, what is a high-level summary of areas that need the treatment?
> What I get from looking at the patches so far, it's:
> - stuff that is written by the hypervisor's interrupt injection code:
>   IRB, indicators, etc.

In interrupt context IRB behaves like a control block. We don't have
to make it shared.

I moved IRB because of snse:


@@ -329,9 +329,9 @@ ccw_device_do_sense(struct ccw_device *cdev, struct
irb *irb) /*
         * We have ending status but no sense information. Do a basic
sense. */
-       sense_ccw = &to_io_private(sch)->sense_ccw;
+       sense_ccw = &to_io_private(sch)->dma_area->sense_ccw;
        sense_ccw->cmd_code = CCW_CMD_BASIC_SENSE;
-       sense_ccw->cda = (__u32) __pa(cdev->private->irb.ecw);
+       sense_ccw->cda = (__u32) __pa(cdev->private->dma_area->irb.ecw);

as the irb.ecw is used as channel program data. And that needs to be
shared.

> - buffers that are filled by a channel program: sense, sense id, etc.
> - ccws themselves (because of translation?)
> 

Right. The idea is: smallish, basically fixed size a readily available
control blocks (specified as a ) are copied back and forth by the
ultravisor (via SIE SD).

Regards,
Halil
Cornelia Huck April 10, 2019, 4:16 p.m. UTC | #5
On Wed, 10 Apr 2019 15:02:25 +0200
Halil Pasic <pasic@linux.ibm.com> wrote:

> On Wed, 10 Apr 2019 10:25:57 +0200
> Cornelia Huck <cohuck@redhat.com> wrote:

> > So, what is a high-level summary of areas that need the treatment?
> > What I get from looking at the patches so far, it's:
> > - stuff that is written by the hypervisor's interrupt injection code:
> >   IRB, indicators, etc.  
> 
> In interrupt context IRB behaves like a control block. We don't have
> to make it shared.
> 
> I moved IRB because of snse:
> 
> 
> @@ -329,9 +329,9 @@ ccw_device_do_sense(struct ccw_device *cdev, struct
> irb *irb) /*
>          * We have ending status but no sense information. Do a basic
> sense. */
> -       sense_ccw = &to_io_private(sch)->sense_ccw;
> +       sense_ccw = &to_io_private(sch)->dma_area->sense_ccw;
>         sense_ccw->cmd_code = CCW_CMD_BASIC_SENSE;
> -       sense_ccw->cda = (__u32) __pa(cdev->private->irb.ecw);
> +       sense_ccw->cda = (__u32) __pa(cdev->private->dma_area->irb.ecw);
> 
> as the irb.ecw is used as channel program data. And that needs to be
> shared.

Ah, I see. So it's more "guest points to some memory where the
hypervisor needs to write data"?

> 
> > - buffers that are filled by a channel program: sense, sense id, etc.
> > - ccws themselves (because of translation?)
> >   
> 
> Right. The idea is: smallish, basically fixed size a readily available
> control blocks (specified as a ) are copied back and forth by the

As a what? :)

> ultravisor (via SIE SD).

Ok. It's really hard to be sure from the outside what falls into which
category :(
Sebastian Ott April 11, 2019, 2:15 p.m. UTC | #6
On Fri, 5 Apr 2019, Halil Pasic wrote:
> @@ -1593,20 +1609,29 @@ struct ccw_device * __init ccw_device_create_console(struct ccw_driver *drv)
>  		return ERR_CAST(sch);
>  
>  	io_priv = kzalloc(sizeof(*io_priv), GFP_KERNEL | GFP_DMA);
> -	if (!io_priv) {
> -		put_device(&sch->dev);
> -		return ERR_PTR(-ENOMEM);
> -	}
> +	if (!io_priv)
> +		goto err_priv;
> +	io_priv->dma_area = cio_dma_zalloc(sizeof(*io_priv->dma_area));

This is called very early - the dma pool is not yet initialized.
Halil Pasic April 12, 2019, 11:29 a.m. UTC | #7
On Thu, 11 Apr 2019 16:15:02 +0200 (CEST)
Sebastian Ott <sebott@linux.ibm.com> wrote:

> On Fri, 5 Apr 2019, Halil Pasic wrote:
> > @@ -1593,20 +1609,29 @@ struct ccw_device * __init ccw_device_create_console(struct ccw_driver *drv)
> >  		return ERR_CAST(sch);
> >  
> >  	io_priv = kzalloc(sizeof(*io_priv), GFP_KERNEL | GFP_DMA);
> > -	if (!io_priv) {
> > -		put_device(&sch->dev);
> > -		return ERR_PTR(-ENOMEM);
> > -	}
> > +	if (!io_priv)
> > +		goto err_priv;
> > +	io_priv->dma_area = cio_dma_zalloc(sizeof(*io_priv->dma_area));
> 
> This is called very early - the dma pool is not yet initialized.
> 

Hm, I will have to have better look into this. I kind of assumed we
can't/don't create any ccw_device instances before we have a
channel_subsystem, as naive as I am.

Thank you very much for spotting this! Looking forward to more
review ;)

Regards,
Halil

Patch
diff mbox series

diff --git a/drivers/s390/cio/ccwreq.c b/drivers/s390/cio/ccwreq.c
index 603268a33ea1..dafbceb311b3 100644
--- a/drivers/s390/cio/ccwreq.c
+++ b/drivers/s390/cio/ccwreq.c
@@ -63,7 +63,7 @@  static void ccwreq_stop(struct ccw_device *cdev, int rc)
 		return;
 	req->done = 1;
 	ccw_device_set_timeout(cdev, 0);
-	memset(&cdev->private->irb, 0, sizeof(struct irb));
+	memset(&cdev->private->dma_area->irb, 0, sizeof(struct irb));
 	if (rc && rc != -ENODEV && req->drc)
 		rc = req->drc;
 	req->callback(cdev, req->data, rc);
@@ -86,7 +86,7 @@  static void ccwreq_do(struct ccw_device *cdev)
 			continue;
 		}
 		/* Perform start function. */
-		memset(&cdev->private->irb, 0, sizeof(struct irb));
+		memset(&cdev->private->dma_area->irb, 0, sizeof(struct irb));
 		rc = cio_start(sch, cp, (u8) req->mask);
 		if (rc == 0) {
 			/* I/O started successfully. */
@@ -169,7 +169,7 @@  int ccw_request_cancel(struct ccw_device *cdev)
  */
 static enum io_status ccwreq_status(struct ccw_device *cdev, struct irb *lcirb)
 {
-	struct irb *irb = &cdev->private->irb;
+	struct irb *irb = &cdev->private->dma_area->irb;
 	struct cmd_scsw *scsw = &irb->scsw.cmd;
 	enum uc_todo todo;
 
@@ -187,7 +187,7 @@  static enum io_status ccwreq_status(struct ccw_device *cdev, struct irb *lcirb)
 		CIO_TRACE_EVENT(2, "sensedata");
 		CIO_HEX_EVENT(2, &cdev->private->dev_id,
 			      sizeof(struct ccw_dev_id));
-		CIO_HEX_EVENT(2, &cdev->private->irb.ecw, SENSE_MAX_COUNT);
+		CIO_HEX_EVENT(2, &cdev->private->dma_area->irb.ecw, SENSE_MAX_COUNT);
 		/* Check for command reject. */
 		if (irb->ecw[0] & SNS0_CMD_REJECT)
 			return IO_REJECTED;
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index 1540229a37bb..62f50e288740 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -689,6 +689,7 @@  ccw_device_release(struct device *dev)
 	cdev = to_ccwdev(dev);
 	/* Release reference of parent subchannel. */
 	put_device(cdev->dev.parent);
+	cio_dma_free(cdev->private->dma_area, sizeof(*cdev->private->dma_area));
 	kfree(cdev->private);
 	kfree(cdev);
 }
@@ -698,13 +699,22 @@  static struct ccw_device * io_subchannel_allocate_dev(struct subchannel *sch)
 	struct ccw_device *cdev;
 
 	cdev  = kzalloc(sizeof(*cdev), GFP_KERNEL);
-	if (cdev) {
-		cdev->private = kzalloc(sizeof(struct ccw_device_private),
-					GFP_KERNEL | GFP_DMA);
-		if (cdev->private)
-			return cdev;
-	}
+	if (!cdev)
+		goto err_cdev;
+	cdev->private = kzalloc(sizeof(struct ccw_device_private),
+				GFP_KERNEL | GFP_DMA);
+	if (!cdev->private)
+		goto err_priv;
+	cdev->private->dma_area = cio_dma_zalloc(
+					sizeof(*cdev->private->dma_area));
+	if (!cdev->private->dma_area)
+		goto err_dma_area;
+	return cdev;
+err_dma_area:
+	kfree(cdev->private);
+err_priv:
 	kfree(cdev);
+err_cdev:
 	return ERR_PTR(-ENOMEM);
 }
 
@@ -1061,6 +1071,11 @@  static int io_subchannel_probe(struct subchannel *sch)
 	io_priv = kzalloc(sizeof(*io_priv), GFP_KERNEL | GFP_DMA);
 	if (!io_priv)
 		goto out_schedule;
+	io_priv->dma_area = cio_dma_zalloc(sizeof(*io_priv->dma_area));
+	if (!io_priv->dma_area) {
+		kfree(io_priv);
+		goto out_schedule;
+	}
 
 	set_io_private(sch, io_priv);
 	css_schedule_eval(sch->schid);
@@ -1088,6 +1103,7 @@  static int io_subchannel_remove(struct subchannel *sch)
 	set_io_private(sch, NULL);
 	spin_unlock_irq(sch->lock);
 out_free:
+	cio_dma_free(io_priv->dma_area, sizeof(*io_priv->dma_area));
 	kfree(io_priv);
 	sysfs_remove_group(&sch->dev.kobj, &io_subchannel_attr_group);
 	return 0;
@@ -1593,20 +1609,29 @@  struct ccw_device * __init ccw_device_create_console(struct ccw_driver *drv)
 		return ERR_CAST(sch);
 
 	io_priv = kzalloc(sizeof(*io_priv), GFP_KERNEL | GFP_DMA);
-	if (!io_priv) {
-		put_device(&sch->dev);
-		return ERR_PTR(-ENOMEM);
-	}
+	if (!io_priv)
+		goto err_priv;
+	io_priv->dma_area = cio_dma_zalloc(sizeof(*io_priv->dma_area));
+	if (!io_priv->dma_area)
+		goto err_dma_area;
 	set_io_private(sch, io_priv);
 	cdev = io_subchannel_create_ccwdev(sch);
 	if (IS_ERR(cdev)) {
 		put_device(&sch->dev);
+		cio_dma_free(io_priv->dma_area, sizeof(*io_priv->dma_area));
 		kfree(io_priv);
 		return cdev;
 	}
 	cdev->drv = drv;
 	ccw_device_set_int_class(cdev);
 	return cdev;
+
+err_dma_area:
+		kfree(io_priv);
+err_priv:
+	put_device(&sch->dev);
+	return ERR_PTR(-ENOMEM);
+
 }
 
 void __init ccw_device_destroy_console(struct ccw_device *cdev)
@@ -1617,6 +1642,7 @@  void __init ccw_device_destroy_console(struct ccw_device *cdev)
 	set_io_private(sch, NULL);
 	put_device(&sch->dev);
 	put_device(&cdev->dev);
+	cio_dma_free(io_priv->dma_area, sizeof(*io_priv->dma_area));
 	kfree(io_priv);
 }
 
diff --git a/drivers/s390/cio/device_fsm.c b/drivers/s390/cio/device_fsm.c
index 9169af7dbb43..fea23b44795b 100644
--- a/drivers/s390/cio/device_fsm.c
+++ b/drivers/s390/cio/device_fsm.c
@@ -67,8 +67,8 @@  static void ccw_timeout_log(struct ccw_device *cdev)
 			       sizeof(struct tcw), 0);
 	} else {
 		printk(KERN_WARNING "cio: orb indicates command mode\n");
-		if ((void *)(addr_t)orb->cmd.cpa == &private->sense_ccw ||
-		    (void *)(addr_t)orb->cmd.cpa == cdev->private->iccws)
+		if ((void *)(addr_t)orb->cmd.cpa == &private->dma_area->sense_ccw ||
+		    (void *)(addr_t)orb->cmd.cpa == cdev->private->dma_area->iccws)
 			printk(KERN_WARNING "cio: last channel program "
 			       "(intern):\n");
 		else
@@ -143,18 +143,18 @@  ccw_device_cancel_halt_clear(struct ccw_device *cdev)
 void ccw_device_update_sense_data(struct ccw_device *cdev)
 {
 	memset(&cdev->id, 0, sizeof(cdev->id));
-	cdev->id.cu_type   = cdev->private->senseid.cu_type;
-	cdev->id.cu_model  = cdev->private->senseid.cu_model;
-	cdev->id.dev_type  = cdev->private->senseid.dev_type;
-	cdev->id.dev_model = cdev->private->senseid.dev_model;
+	cdev->id.cu_type   = cdev->private->dma_area->senseid.cu_type;
+	cdev->id.cu_model  = cdev->private->dma_area->senseid.cu_model;
+	cdev->id.dev_type  = cdev->private->dma_area->senseid.dev_type;
+	cdev->id.dev_model = cdev->private->dma_area->senseid.dev_model;
 }
 
 int ccw_device_test_sense_data(struct ccw_device *cdev)
 {
-	return cdev->id.cu_type == cdev->private->senseid.cu_type &&
-		cdev->id.cu_model == cdev->private->senseid.cu_model &&
-		cdev->id.dev_type == cdev->private->senseid.dev_type &&
-		cdev->id.dev_model == cdev->private->senseid.dev_model;
+	return cdev->id.cu_type == cdev->private->dma_area->senseid.cu_type &&
+		cdev->id.cu_model == cdev->private->dma_area->senseid.cu_model &&
+		cdev->id.dev_type == cdev->private->dma_area->senseid.dev_type &&
+		cdev->id.dev_model == cdev->private->dma_area->senseid.dev_model;
 }
 
 /*
@@ -342,7 +342,7 @@  ccw_device_done(struct ccw_device *cdev, int state)
 		cio_disable_subchannel(sch);
 
 	/* Reset device status. */
-	memset(&cdev->private->irb, 0, sizeof(struct irb));
+	memset(&cdev->private->dma_area->irb, 0, sizeof(struct irb));
 
 	cdev->private->state = state;
 
@@ -509,13 +509,13 @@  void ccw_device_verify_done(struct ccw_device *cdev, int err)
 		ccw_device_done(cdev, DEV_STATE_ONLINE);
 		/* Deliver fake irb to device driver, if needed. */
 		if (cdev->private->flags.fake_irb) {
-			create_fake_irb(&cdev->private->irb,
+			create_fake_irb(&cdev->private->dma_area->irb,
 					cdev->private->flags.fake_irb);
 			cdev->private->flags.fake_irb = 0;
 			if (cdev->handler)
 				cdev->handler(cdev, cdev->private->intparm,
-					      &cdev->private->irb);
-			memset(&cdev->private->irb, 0, sizeof(struct irb));
+					      &cdev->private->dma_area->irb);
+			memset(&cdev->private->dma_area->irb, 0, sizeof(struct irb));
 		}
 		ccw_device_report_path_events(cdev);
 		ccw_device_handle_broken_paths(cdev);
@@ -672,7 +672,7 @@  ccw_device_online_verify(struct ccw_device *cdev, enum dev_event dev_event)
 
 	if (scsw_actl(&sch->schib.scsw) != 0 ||
 	    (scsw_stctl(&sch->schib.scsw) & SCSW_STCTL_STATUS_PEND) ||
-	    (scsw_stctl(&cdev->private->irb.scsw) & SCSW_STCTL_STATUS_PEND)) {
+	    (scsw_stctl(&cdev->private->dma_area->irb.scsw) & SCSW_STCTL_STATUS_PEND)) {
 		/*
 		 * No final status yet or final status not yet delivered
 		 * to the device driver. Can't do path verification now,
@@ -719,7 +719,7 @@  static int ccw_device_call_handler(struct ccw_device *cdev)
 	 *  - fast notification was requested (primary status)
 	 *  - unsolicited interrupts
 	 */
-	stctl = scsw_stctl(&cdev->private->irb.scsw);
+	stctl = scsw_stctl(&cdev->private->dma_area->irb.scsw);
 	ending_status = (stctl & SCSW_STCTL_SEC_STATUS) ||
 		(stctl == (SCSW_STCTL_ALERT_STATUS | SCSW_STCTL_STATUS_PEND)) ||
 		(stctl == SCSW_STCTL_STATUS_PEND);
@@ -735,9 +735,9 @@  static int ccw_device_call_handler(struct ccw_device *cdev)
 
 	if (cdev->handler)
 		cdev->handler(cdev, cdev->private->intparm,
-			      &cdev->private->irb);
+			      &cdev->private->dma_area->irb);
 
-	memset(&cdev->private->irb, 0, sizeof(struct irb));
+	memset(&cdev->private->dma_area->irb, 0, sizeof(struct irb));
 	return 1;
 }
 
@@ -759,7 +759,7 @@  ccw_device_irq(struct ccw_device *cdev, enum dev_event dev_event)
 			/* Unit check but no sense data. Need basic sense. */
 			if (ccw_device_do_sense(cdev, irb) != 0)
 				goto call_handler_unsol;
-			memcpy(&cdev->private->irb, irb, sizeof(struct irb));
+			memcpy(&cdev->private->dma_area->irb, irb, sizeof(struct irb));
 			cdev->private->state = DEV_STATE_W4SENSE;
 			cdev->private->intparm = 0;
 			return;
@@ -842,7 +842,7 @@  ccw_device_w4sense(struct ccw_device *cdev, enum dev_event dev_event)
 	if (scsw_fctl(&irb->scsw) &
 	    (SCSW_FCTL_CLEAR_FUNC | SCSW_FCTL_HALT_FUNC)) {
 		cdev->private->flags.dosense = 0;
-		memset(&cdev->private->irb, 0, sizeof(struct irb));
+		memset(&cdev->private->dma_area->irb, 0, sizeof(struct irb));
 		ccw_device_accumulate_irb(cdev, irb);
 		goto call_handler;
 	}
diff --git a/drivers/s390/cio/device_id.c b/drivers/s390/cio/device_id.c
index f6df83a9dfbb..ea8a0fc6c0b6 100644
--- a/drivers/s390/cio/device_id.c
+++ b/drivers/s390/cio/device_id.c
@@ -99,7 +99,7 @@  static int diag210_to_senseid(struct senseid *senseid, struct diag210 *diag)
 static int diag210_get_dev_info(struct ccw_device *cdev)
 {
 	struct ccw_dev_id *dev_id = &cdev->private->dev_id;
-	struct senseid *senseid = &cdev->private->senseid;
+	struct senseid *senseid = &cdev->private->dma_area->senseid;
 	struct diag210 diag_data;
 	int rc;
 
@@ -134,8 +134,8 @@  static int diag210_get_dev_info(struct ccw_device *cdev)
 static void snsid_init(struct ccw_device *cdev)
 {
 	cdev->private->flags.esid = 0;
-	memset(&cdev->private->senseid, 0, sizeof(cdev->private->senseid));
-	cdev->private->senseid.cu_type = 0xffff;
+	memset(&cdev->private->dma_area->senseid, 0, sizeof(cdev->private->dma_area->senseid));
+	cdev->private->dma_area->senseid.cu_type = 0xffff;
 }
 
 /*
@@ -143,16 +143,16 @@  static void snsid_init(struct ccw_device *cdev)
  */
 static int snsid_check(struct ccw_device *cdev, void *data)
 {
-	struct cmd_scsw *scsw = &cdev->private->irb.scsw.cmd;
+	struct cmd_scsw *scsw = &cdev->private->dma_area->irb.scsw.cmd;
 	int len = sizeof(struct senseid) - scsw->count;
 
 	/* Check for incomplete SENSE ID data. */
 	if (len < SENSE_ID_MIN_LEN)
 		goto out_restart;
-	if (cdev->private->senseid.cu_type == 0xffff)
+	if (cdev->private->dma_area->senseid.cu_type == 0xffff)
 		goto out_restart;
 	/* Check for incompatible SENSE ID data. */
-	if (cdev->private->senseid.reserved != 0xff)
+	if (cdev->private->dma_area->senseid.reserved != 0xff)
 		return -EOPNOTSUPP;
 	/* Check for extended-identification information. */
 	if (len > SENSE_ID_BASIC_LEN)
@@ -170,7 +170,7 @@  static int snsid_check(struct ccw_device *cdev, void *data)
 static void snsid_callback(struct ccw_device *cdev, void *data, int rc)
 {
 	struct ccw_dev_id *id = &cdev->private->dev_id;
-	struct senseid *senseid = &cdev->private->senseid;
+	struct senseid *senseid = &cdev->private->dma_area->senseid;
 	int vm = 0;
 
 	if (rc && MACHINE_IS_VM) {
@@ -200,7 +200,7 @@  void ccw_device_sense_id_start(struct ccw_device *cdev)
 {
 	struct subchannel *sch = to_subchannel(cdev->dev.parent);
 	struct ccw_request *req = &cdev->private->req;
-	struct ccw1 *cp = cdev->private->iccws;
+	struct ccw1 *cp = cdev->private->dma_area->iccws;
 
 	CIO_TRACE_EVENT(4, "snsid");
 	CIO_HEX_EVENT(4, &cdev->private->dev_id, sizeof(cdev->private->dev_id));
@@ -208,7 +208,7 @@  void ccw_device_sense_id_start(struct ccw_device *cdev)
 	snsid_init(cdev);
 	/* Channel program setup. */
 	cp->cmd_code	= CCW_CMD_SENSE_ID;
-	cp->cda		= (u32) (addr_t) &cdev->private->senseid;
+	cp->cda		= (u32) (addr_t) &cdev->private->dma_area->senseid;
 	cp->count	= sizeof(struct senseid);
 	cp->flags	= CCW_FLAG_SLI;
 	/* Request setup. */
diff --git a/drivers/s390/cio/device_ops.c b/drivers/s390/cio/device_ops.c
index 4435ae0b3027..8c3ccb8768a0 100644
--- a/drivers/s390/cio/device_ops.c
+++ b/drivers/s390/cio/device_ops.c
@@ -429,8 +429,8 @@  struct ciw *ccw_device_get_ciw(struct ccw_device *cdev, __u32 ct)
 	if (cdev->private->flags.esid == 0)
 		return NULL;
 	for (ciw_cnt = 0; ciw_cnt < MAX_CIWS; ciw_cnt++)
-		if (cdev->private->senseid.ciw[ciw_cnt].ct == ct)
-			return cdev->private->senseid.ciw + ciw_cnt;
+		if (cdev->private->dma_area->senseid.ciw[ciw_cnt].ct == ct)
+			return cdev->private->dma_area->senseid.ciw + ciw_cnt;
 	return NULL;
 }
 
diff --git a/drivers/s390/cio/device_pgid.c b/drivers/s390/cio/device_pgid.c
index d30a3babf176..e97baa89cbf8 100644
--- a/drivers/s390/cio/device_pgid.c
+++ b/drivers/s390/cio/device_pgid.c
@@ -57,7 +57,7 @@  static void verify_done(struct ccw_device *cdev, int rc)
 static void nop_build_cp(struct ccw_device *cdev)
 {
 	struct ccw_request *req = &cdev->private->req;
-	struct ccw1 *cp = cdev->private->iccws;
+	struct ccw1 *cp = cdev->private->dma_area->iccws;
 
 	cp->cmd_code	= CCW_CMD_NOOP;
 	cp->cda		= 0;
@@ -134,9 +134,9 @@  static void nop_callback(struct ccw_device *cdev, void *data, int rc)
 static void spid_build_cp(struct ccw_device *cdev, u8 fn)
 {
 	struct ccw_request *req = &cdev->private->req;
-	struct ccw1 *cp = cdev->private->iccws;
+	struct ccw1 *cp = cdev->private->dma_area->iccws;
 	int i = pathmask_to_pos(req->lpm);
-	struct pgid *pgid = &cdev->private->pgid[i];
+	struct pgid *pgid = &cdev->private->dma_area->pgid[i];
 
 	pgid->inf.fc	= fn;
 	cp->cmd_code	= CCW_CMD_SET_PGID;
@@ -300,7 +300,7 @@  static int pgid_cmp(struct pgid *p1, struct pgid *p2)
 static void pgid_analyze(struct ccw_device *cdev, struct pgid **p,
 			 int *mismatch, u8 *reserved, u8 *reset)
 {
-	struct pgid *pgid = &cdev->private->pgid[0];
+	struct pgid *pgid = &cdev->private->dma_area->pgid[0];
 	struct pgid *first = NULL;
 	int lpm;
 	int i;
@@ -342,7 +342,7 @@  static u8 pgid_to_donepm(struct ccw_device *cdev)
 		lpm = 0x80 >> i;
 		if ((cdev->private->pgid_valid_mask & lpm) == 0)
 			continue;
-		pgid = &cdev->private->pgid[i];
+		pgid = &cdev->private->dma_area->pgid[i];
 		if (sch->opm & lpm) {
 			if (pgid->inf.ps.state1 != SNID_STATE1_GROUPED)
 				continue;
@@ -368,7 +368,7 @@  static void pgid_fill(struct ccw_device *cdev, struct pgid *pgid)
 	int i;
 
 	for (i = 0; i < 8; i++)
-		memcpy(&cdev->private->pgid[i], pgid, sizeof(struct pgid));
+		memcpy(&cdev->private->dma_area->pgid[i], pgid, sizeof(struct pgid));
 }
 
 /*
@@ -435,12 +435,12 @@  static void snid_done(struct ccw_device *cdev, int rc)
 static void snid_build_cp(struct ccw_device *cdev)
 {
 	struct ccw_request *req = &cdev->private->req;
-	struct ccw1 *cp = cdev->private->iccws;
+	struct ccw1 *cp = cdev->private->dma_area->iccws;
 	int i = pathmask_to_pos(req->lpm);
 
 	/* Channel program setup. */
 	cp->cmd_code	= CCW_CMD_SENSE_PGID;
-	cp->cda		= (u32) (addr_t) &cdev->private->pgid[i];
+	cp->cda		= (u32) (addr_t) &cdev->private->dma_area->pgid[i];
 	cp->count	= sizeof(struct pgid);
 	cp->flags	= CCW_FLAG_SLI;
 	req->cp		= cp;
@@ -516,7 +516,7 @@  static void verify_start(struct ccw_device *cdev)
 	sch->lpm = sch->schib.pmcw.pam;
 
 	/* Initialize PGID data. */
-	memset(cdev->private->pgid, 0, sizeof(cdev->private->pgid));
+	memset(cdev->private->dma_area->pgid, 0, sizeof(cdev->private->dma_area->pgid));
 	cdev->private->pgid_valid_mask = 0;
 	cdev->private->pgid_todo_mask = sch->schib.pmcw.pam;
 	cdev->private->path_notoper_mask = 0;
@@ -626,7 +626,7 @@  struct stlck_data {
 static void stlck_build_cp(struct ccw_device *cdev, void *buf1, void *buf2)
 {
 	struct ccw_request *req = &cdev->private->req;
-	struct ccw1 *cp = cdev->private->iccws;
+	struct ccw1 *cp = cdev->private->dma_area->iccws;
 
 	cp[0].cmd_code = CCW_CMD_STLCK;
 	cp[0].cda = (u32) (addr_t) buf1;
diff --git a/drivers/s390/cio/device_status.c b/drivers/s390/cio/device_status.c
index 7d5c7892b2c4..a9aabde604f4 100644
--- a/drivers/s390/cio/device_status.c
+++ b/drivers/s390/cio/device_status.c
@@ -79,15 +79,15 @@  ccw_device_accumulate_ecw(struct ccw_device *cdev, struct irb *irb)
 	 * are condition that have to be met for the extended control
 	 * bit to have meaning. Sick.
 	 */
-	cdev->private->irb.scsw.cmd.ectl = 0;
+	cdev->private->dma_area->irb.scsw.cmd.ectl = 0;
 	if ((irb->scsw.cmd.stctl & SCSW_STCTL_ALERT_STATUS) &&
 	    !(irb->scsw.cmd.stctl & SCSW_STCTL_INTER_STATUS))
-		cdev->private->irb.scsw.cmd.ectl = irb->scsw.cmd.ectl;
+		cdev->private->dma_area->irb.scsw.cmd.ectl = irb->scsw.cmd.ectl;
 	/* Check if extended control word is valid. */
-	if (!cdev->private->irb.scsw.cmd.ectl)
+	if (!cdev->private->dma_area->irb.scsw.cmd.ectl)
 		return;
 	/* Copy concurrent sense / model dependent information. */
-	memcpy (&cdev->private->irb.ecw, irb->ecw, sizeof (irb->ecw));
+	memcpy (&cdev->private->dma_area->irb.ecw, irb->ecw, sizeof (irb->ecw));
 }
 
 /*
@@ -118,7 +118,7 @@  ccw_device_accumulate_esw(struct ccw_device *cdev, struct irb *irb)
 	if (!ccw_device_accumulate_esw_valid(irb))
 		return;
 
-	cdev_irb = &cdev->private->irb;
+	cdev_irb = &cdev->private->dma_area->irb;
 
 	/* Copy last path used mask. */
 	cdev_irb->esw.esw1.lpum = irb->esw.esw1.lpum;
@@ -210,7 +210,7 @@  ccw_device_accumulate_irb(struct ccw_device *cdev, struct irb *irb)
 		ccw_device_path_notoper(cdev);
 	/* No irb accumulation for transport mode irbs. */
 	if (scsw_is_tm(&irb->scsw)) {
-		memcpy(&cdev->private->irb, irb, sizeof(struct irb));
+		memcpy(&cdev->private->dma_area->irb, irb, sizeof(struct irb));
 		return;
 	}
 	/*
@@ -219,7 +219,7 @@  ccw_device_accumulate_irb(struct ccw_device *cdev, struct irb *irb)
 	if (!scsw_is_solicited(&irb->scsw))
 		return;
 
-	cdev_irb = &cdev->private->irb;
+	cdev_irb = &cdev->private->dma_area->irb;
 
 	/*
 	 * If the clear function had been performed, all formerly pending
@@ -227,7 +227,7 @@  ccw_device_accumulate_irb(struct ccw_device *cdev, struct irb *irb)
 	 * intermediate accumulated status to the device driver.
 	 */
 	if (irb->scsw.cmd.fctl & SCSW_FCTL_CLEAR_FUNC)
-		memset(&cdev->private->irb, 0, sizeof(struct irb));
+		memset(&cdev->private->dma_area->irb, 0, sizeof(struct irb));
 
 	/* Copy bits which are valid only for the start function. */
 	if (irb->scsw.cmd.fctl & SCSW_FCTL_START_FUNC) {
@@ -329,9 +329,9 @@  ccw_device_do_sense(struct ccw_device *cdev, struct irb *irb)
 	/*
 	 * We have ending status but no sense information. Do a basic sense.
 	 */
-	sense_ccw = &to_io_private(sch)->sense_ccw;
+	sense_ccw = &to_io_private(sch)->dma_area->sense_ccw;
 	sense_ccw->cmd_code = CCW_CMD_BASIC_SENSE;
-	sense_ccw->cda = (__u32) __pa(cdev->private->irb.ecw);
+	sense_ccw->cda = (__u32) __pa(cdev->private->dma_area->irb.ecw);
 	sense_ccw->count = SENSE_MAX_COUNT;
 	sense_ccw->flags = CCW_FLAG_SLI;
 
@@ -364,7 +364,7 @@  ccw_device_accumulate_basic_sense(struct ccw_device *cdev, struct irb *irb)
 
 	if (!(irb->scsw.cmd.dstat & DEV_STAT_UNIT_CHECK) &&
 	    (irb->scsw.cmd.dstat & DEV_STAT_CHN_END)) {
-		cdev->private->irb.esw.esw0.erw.cons = 1;
+		cdev->private->dma_area->irb.esw.esw0.erw.cons = 1;
 		cdev->private->flags.dosense = 0;
 	}
 	/* Check if path verification is required. */
@@ -386,7 +386,7 @@  ccw_device_accumulate_and_sense(struct ccw_device *cdev, struct irb *irb)
 	/* Check for basic sense. */
 	if (cdev->private->flags.dosense &&
 	    !(irb->scsw.cmd.dstat & DEV_STAT_UNIT_CHECK)) {
-		cdev->private->irb.esw.esw0.erw.cons = 1;
+		cdev->private->dma_area->irb.esw.esw0.erw.cons = 1;
 		cdev->private->flags.dosense = 0;
 		return 0;
 	}
diff --git a/drivers/s390/cio/io_sch.h b/drivers/s390/cio/io_sch.h
index 90e4e3a7841b..fc3220fede0f 100644
--- a/drivers/s390/cio/io_sch.h
+++ b/drivers/s390/cio/io_sch.h
@@ -9,15 +9,20 @@ 
 #include "css.h"
 #include "orb.h"
 
+
+struct io_subchannel_dma_area {
+	struct ccw1 sense_ccw;	/* static ccw for sense command */
+};
+
 struct io_subchannel_private {
 	union orb orb;		/* operation request block */
-	struct ccw1 sense_ccw;	/* static ccw for sense command */
 	struct ccw_device *cdev;/* pointer to the child ccw device */
 	struct {
 		unsigned int suspend:1;	/* allow suspend */
 		unsigned int prefetch:1;/* deny prefetch */
 		unsigned int inter:1;	/* suppress intermediate interrupts */
 	} __packed options;
+	struct io_subchannel_dma_area *dma_area;
 } __aligned(8);
 
 #define to_io_private(n) ((struct io_subchannel_private *) \
@@ -115,6 +120,13 @@  enum cdev_todo {
 #define FAKE_CMD_IRB	1
 #define FAKE_TM_IRB	2
 
+struct ccw_device_dma_area {
+	struct senseid senseid;	/* SenseID info */
+	struct ccw1 iccws[2];	/* ccws for SNID/SID/SPGID commands */
+	struct irb irb;		/* device status */
+	struct pgid pgid[8];	/* path group IDs per chpid*/
+};
+
 struct ccw_device_private {
 	struct ccw_device *cdev;
 	struct subchannel *sch;
@@ -156,11 +168,7 @@  struct ccw_device_private {
 	} __attribute__((packed)) flags;
 	unsigned long intparm;	/* user interruption parameter */
 	struct qdio_irq *qdio_data;
-	struct irb irb;		/* device status */
 	int async_kill_io_rc;
-	struct senseid senseid;	/* SenseID info */
-	struct pgid pgid[8];	/* path group IDs per chpid*/
-	struct ccw1 iccws[2];	/* ccws for SNID/SID/SPGID commands */
 	struct work_struct todo_work;
 	enum cdev_todo todo;
 	wait_queue_head_t wait_q;
@@ -169,6 +177,7 @@  struct ccw_device_private {
 	struct list_head cmb_list;	/* list of measured devices */
 	u64 cmb_start_time;		/* clock value of cmb reset */
 	void *cmb_wait;			/* deferred cmb enable/disable */
+	struct ccw_device_dma_area *dma_area;
 	enum interruption_class int_class;
 };