[PATCH v5 4/6] ivtv: use arch_phys_wc_add() and require PAT disabled

[PATCH v5 4/6] ivtv: use arch_phys_wc_add() and require PAT disabled

[Luis R. Rodriguez]

From: "Luis R. Rodriguez" <mcgrof@suse.com>

We are burrying direct access to MTRR code support on
x86 in order to take advantage of PAT. In the future we
also want to make the default behaviour of ioremap_nocache()
to use strong UC, use of mtrr_add() on those systems
would make write-combining void.

In order to help both enable us to later make strong
UC default and in order to phase out direct MTRR access
code port the driver over to arch_phys_wc_add() and
annotate that the device driver requires systems to
boot with PAT disabled, with the nopat kernel parameter.

This is a worthy comprmise given that the hardware is
really rare these days, and perhaps only some lost souls
in some third world country are expected to be using this
feature of the device driver.

Acked-by: Andy Walls <awalls@md.metrocast.net>
Cc: Andy Walls <awalls@md.metrocast.net>
Cc: Doug Ledford <dledford@redhat.com>
Cc: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Suresh Siddha <sbsiddha@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Juergen Gross <jgross@suse.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Dave Airlie <airlied@redhat.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Antonino Daplas <adaplas@gmail.com>
Cc: Jean-Christophe Plagniol-Villard <plagnioj@jcrosoft.com>
Cc: Tomi Valkeinen <tomi.valkeinen@ti.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Stefan Bader <stefan.bader@canonical.com>
Cc: Ville Syrjälä <syrjala@sci.fi>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Borislav Petkov <bp@suse.de>
Cc: Davidlohr Bueso <dbueso@suse.de>
Cc: konrad.wilk@oracle.com
Cc: ville.syrjala@linux.intel.com
Cc: david.vrabel@citrix.com
Cc: jbeulich@suse.com
Cc: toshi.kani@hp.com
Cc: Roger Pau Monné <roger.pau@citrix.com>
Cc: linux-fbdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: ivtv-devel@ivtvdriver.org
Cc: linux-media@vger.kernel.org
Cc: xen-devel@lists.xensource.com
Signed-off-by: Luis R. Rodriguez <mcgrof@suse.com>
---
 drivers/media/pci/ivtv/Kconfig  |  3 +++
 drivers/media/pci/ivtv/ivtvfb.c | 58 ++++++++++++++++-------------------------
 2 files changed, 26 insertions(+), 35 deletions(-)

diff --git a/drivers/media/pci/ivtv/Kconfig b/drivers/media/pci/ivtv/Kconfig
index dd6ee57e..b2a7f88 100644
--- a/drivers/media/pci/ivtv/Kconfig
+++ b/drivers/media/pci/ivtv/Kconfig
@@ -57,5 +57,8 @@ config VIDEO_FB_IVTV
 	  This is used in the Hauppauge PVR-350 card. There is a driver
 	  homepage at <http://www.ivtvdriver.org>.
 
+	  If you have this hardware you will need to boot with PAT disabled
+	  on your x86 systems, use the nopat kernel parameter.
+
 	  To compile this driver as a module, choose M here: the
 	  module will be called ivtvfb.
diff --git a/drivers/media/pci/ivtv/ivtvfb.c b/drivers/media/pci/ivtv/ivtvfb.c
index 9ff1230..7685ae3 100644
--- a/drivers/media/pci/ivtv/ivtvfb.c
+++ b/drivers/media/pci/ivtv/ivtvfb.c
@@ -44,8 +44,8 @@
 #include <linux/ivtvfb.h>
 #include <linux/slab.h>
 
-#ifdef CONFIG_MTRR
-#include <asm/mtrr.h>
+#ifdef CONFIG_X86_64
+#include <asm/pat.h>
 #endif
 
 #include "ivtv-driver.h"
@@ -155,12 +155,11 @@ struct osd_info {
 	/* Buffer size */
 	u32 video_buffer_size;
 
-#ifdef CONFIG_MTRR
 	/* video_base rounded down as required by hardware MTRRs */
 	unsigned long fb_start_aligned_physaddr;
 	/* video_base rounded up as required by hardware MTRRs */
 	unsigned long fb_end_aligned_physaddr;
-#endif
+	int wc_cookie;
 
 	/* Store the buffer offset */
 	int set_osd_coords_x;
@@ -1099,6 +1098,8 @@ static int ivtvfb_init_vidmode(struct ivtv *itv)
 static int ivtvfb_init_io(struct ivtv *itv)
 {
 	struct osd_info *oi = itv->osd_info;
+	/* Find the largest power of two that maps the whole buffer */
+	int size_shift = 31;
 
 	mutex_lock(&itv->serialize_lock);
 	if (ivtv_init_on_first_open(itv)) {
@@ -1132,29 +1133,16 @@ static int ivtvfb_init_io(struct ivtv *itv)
 			oi->video_pbase, oi->video_vbase,
 			oi->video_buffer_size / 1024);
 
-#ifdef CONFIG_MTRR
-	{
-		/* Find the largest power of two that maps the whole buffer */
-		int size_shift = 31;
-
-		while (!(oi->video_buffer_size & (1 << size_shift))) {
-			size_shift--;
-		}
-		size_shift++;
-		oi->fb_start_aligned_physaddr = oi->video_pbase & ~((1 << size_shift) - 1);
-		oi->fb_end_aligned_physaddr = oi->video_pbase + oi->video_buffer_size;
-		oi->fb_end_aligned_physaddr += (1 << size_shift) - 1;
-		oi->fb_end_aligned_physaddr &= ~((1 << size_shift) - 1);
-		if (mtrr_add(oi->fb_start_aligned_physaddr,
-			oi->fb_end_aligned_physaddr - oi->fb_start_aligned_physaddr,
-			     MTRR_TYPE_WRCOMB, 1) < 0) {
-			IVTVFB_INFO("disabled mttr\n");
-			oi->fb_start_aligned_physaddr = 0;
-			oi->fb_end_aligned_physaddr = 0;
-		}
-	}
-#endif
-
+	while (!(oi->video_buffer_size & (1 << size_shift)))
+		size_shift--;
+	size_shift++;
+	oi->fb_start_aligned_physaddr = oi->video_pbase & ~((1 << size_shift) - 1);
+	oi->fb_end_aligned_physaddr = oi->video_pbase + oi->video_buffer_size;
+	oi->fb_end_aligned_physaddr += (1 << size_shift) - 1;
+	oi->fb_end_aligned_physaddr &= ~((1 << size_shift) - 1);
+	oi->wc_cookie = arch_phys_wc_add(oi->fb_start_aligned_physaddr,
+					 oi->fb_end_aligned_physaddr -
+					 oi->fb_start_aligned_physaddr);
 	/* Blank the entire osd. */
 	memset_io(oi->video_vbase, 0, oi->video_buffer_size);
 
@@ -1172,14 +1160,7 @@ static void ivtvfb_release_buffers (struct ivtv *itv)
 
 	/* Release pseudo palette */
 	kfree(oi->ivtvfb_info.pseudo_palette);
-
-#ifdef CONFIG_MTRR
-	if (oi->fb_end_aligned_physaddr) {
-		mtrr_del(-1, oi->fb_start_aligned_physaddr,
-			oi->fb_end_aligned_physaddr - oi->fb_start_aligned_physaddr);
-	}
-#endif
-
+	arch_phys_wc_del(oi->wc_cookie);
 	kfree(oi);
 	itv->osd_info = NULL;
 }
@@ -1284,6 +1265,13 @@ static int __init ivtvfb_init(void)
 	int registered = 0;
 	int err;
 
+#ifdef CONFIG_X86_64
+	if (WARN(pat_enabled(),
+		 "ivtvfb needs PAT disabled, boot with nopat kernel parameter\n")) {
+		return EINVAL;
+	}
+#endif
+
 	if (ivtvfb_card_id < -1 || ivtvfb_card_id >= IVTV_MAX_CARDS) {
 		printk(KERN_ERR "ivtvfb:  ivtvfb_card_id parameter is out of range (valid range: -1 - %d)\n",
 		     IVTV_MAX_CARDS - 1);
-- 
2.3.2.209.gd67f9d5.dirty

[PATCH v5 5/6] IB/ipath: add counting for MTRR

[Luis R. Rodriguez]

From: "Luis R. Rodriguez" <mcgrof@suse.com>

There is no good reason not to, we eventually delete it as well.

Cc: Toshi Kani <toshi.kani@hp.com>
Cc: Roland Dreier <roland@kernel.org>
Cc: Sean Hefty <sean.hefty@intel.com>
Cc: Hal Rosenstock <hal.rosenstock@gmail.com>
Cc: Suresh Siddha <sbsiddha@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Juergen Gross <jgross@suse.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Airlie <airlied@redhat.com>
Cc: Antonino Daplas <adaplas@gmail.com>
Cc: Jean-Christophe Plagniol-Villard <plagnioj@jcrosoft.com>
Cc: Tomi Valkeinen <tomi.valkeinen@ti.com>
Cc: infinipath@intel.com
Cc: linux-rdma@vger.kernel.org
Cc: linux-fbdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Luis R. Rodriguez <mcgrof@suse.com>
---
 drivers/infiniband/hw/ipath/ipath_wc_x86_64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/ipath/ipath_wc_x86_64.c b/drivers/infiniband/hw/ipath/ipath_wc_x86_64.c
index 4ad0b93..70c1f3a 100644
--- a/drivers/infiniband/hw/ipath/ipath_wc_x86_64.c
+++ b/drivers/infiniband/hw/ipath/ipath_wc_x86_64.c
@@ -127,7 +127,7 @@ int ipath_enable_wc(struct ipath_devdata *dd)
 			   "(addr %llx, len=0x%llx)\n",
 			   (unsigned long long) pioaddr,
 			   (unsigned long long) piolen);
-		cookie = mtrr_add(pioaddr, piolen, MTRR_TYPE_WRCOMB, 0);
+		cookie = mtrr_add(pioaddr, piolen, MTRR_TYPE_WRCOMB, 1);
 		if (cookie < 0) {
 			{
 				dev_info(&dd->pcidev->dev,
-- 
2.3.2.209.gd67f9d5.dirty

[PATCH v5 6/6] IB/ipath: use arch_phys_wc_add() and require PAT disabled

[Luis R. Rodriguez]

From: "Luis R. Rodriguez" <mcgrof@suse.com>

We are burrying direct access to MTRR code support on
x86 in order to take advantage of PAT. In the future we
also want to make the default behaviour of ioremap_nocache()
to use strong UC, use of mtrr_add() on those systems
would make write-combining void.

In order to help both enable us to later make strong
UC default and in order to phase out direct MTRR access
code port the driver over to arch_phys_wc_add() and
annotate that the device driver requires systems to
boot with PAT disabled, with the nopat kernel parameter.

This is a worthy compromise given that the ipath device
driver powers the old HTX bus cards that only work in
AMD systems, while the newer IB/qib device driver
powers all PCI-e cards. The ipath device driver is
obsolete, hardware hard to find and because of this
this its a reasonable compromise to make to require
users of ipath to boot with nopat.

Acked-by: Doug Ledford <dledford@redhat.com>
Cc: Doug Ledford <dledford@redhat.com>
Cc: Andy Walls <awalls@md.metrocast.net>
Cc: Hal Rosenstock <hal.rosenstock@gmail.com>
Cc: Sean Hefty <sean.hefty@intel.com>
Cc: Suresh Siddha <sbsiddha@gmail.com>
Cc: Rickard Strandqvist <rickard_strandqvist@spectrumdigital.se>
Cc: Mike Marciniszyn <mike.marciniszyn@intel.com>
Cc: Roland Dreier <roland@purestorage.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Juergen Gross <jgross@suse.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Dave Airlie <airlied@redhat.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Antonino Daplas <adaplas@gmail.com>
Cc: Jean-Christophe Plagniol-Villard <plagnioj@jcrosoft.com>
Cc: Tomi Valkeinen <tomi.valkeinen@ti.com>
Cc: Ville Syrjälä <syrjala@sci.fi>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Borislav Petkov <bp@suse.de>
Cc: Davidlohr Bueso <dbueso@suse.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Stefan Bader <stefan.bader@canonical.com>
Cc: konrad.wilk@oracle.com
Cc: ville.syrjala@linux.intel.com
Cc: david.vrabel@citrix.com
Cc: jbeulich@suse.com
Cc: toshi.kani@hp.com
Cc: Roger Pau Monné <roger.pau@citrix.com>
Cc: infinipath@intel.com
Cc: linux-rdma@vger.kernel.org
Cc: linux-fbdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: xen-devel@lists.xensource.com
Signed-off-by: Luis R. Rodriguez <mcgrof@suse.com>
---
 drivers/infiniband/hw/ipath/Kconfig           |  3 ++
 drivers/infiniband/hw/ipath/ipath_driver.c    | 18 +++++++----
 drivers/infiniband/hw/ipath/ipath_kernel.h    |  4 +--
 drivers/infiniband/hw/ipath/ipath_wc_x86_64.c | 43 ++++++---------------------
 4 files changed, 26 insertions(+), 42 deletions(-)

diff --git a/drivers/infiniband/hw/ipath/Kconfig b/drivers/infiniband/hw/ipath/Kconfig
index 1d9bb11..8fe54ff 100644
--- a/drivers/infiniband/hw/ipath/Kconfig
+++ b/drivers/infiniband/hw/ipath/Kconfig
@@ -9,3 +9,6 @@ config INFINIBAND_IPATH
 	as IP-over-InfiniBand as well as with userspace applications
 	(in conjunction with InfiniBand userspace access).
 	For QLogic PCIe QLE based cards, use the QIB driver instead.
+
+	If you have this hardware you will need to boot with PAT disabled
+	on your x86-64 systems, use the nopat kernel parameter.
diff --git a/drivers/infiniband/hw/ipath/ipath_driver.c b/drivers/infiniband/hw/ipath/ipath_driver.c
index bd0caed..441cfe5 100644
--- a/drivers/infiniband/hw/ipath/ipath_driver.c
+++ b/drivers/infiniband/hw/ipath/ipath_driver.c
@@ -42,6 +42,9 @@
 #include <linux/bitmap.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#ifdef CONFIG_X86_64
+#include <asm/pat.h>
+#endif
 
 #include "ipath_kernel.h"
 #include "ipath_verbs.h"
@@ -395,6 +398,14 @@ static int ipath_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	unsigned long long addr;
 	u32 bar0 = 0, bar1 = 0;
 
+#ifdef CONFIG_X86_64
+	if (WARN(pat_enabled(),
+		 "ipath needs PAT disabled, boot with nopat kernel parameter\n")) {
+		ret = EINVAL;
+		goto bail;
+	}
+#endif
+
 	dd = ipath_alloc_devdata(pdev);
 	if (IS_ERR(dd)) {
 		ret = PTR_ERR(dd);
@@ -542,6 +553,7 @@ static int ipath_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dd->ipath_kregbase = __ioremap(addr, len,
 		(_PAGE_NO_CACHE|_PAGE_WRITETHRU));
 #else
+	/* XXX: split this properly to enable on PAT */
 	dd->ipath_kregbase = ioremap_nocache(addr, len);
 #endif
 
@@ -587,12 +599,8 @@ static int ipath_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	ret = ipath_enable_wc(dd);
 
-	if (ret) {
-		ipath_dev_err(dd, "Write combining not enabled "
-			      "(err %d): performance may be poor\n",
-			      -ret);
+	if (ret)
 		ret = 0;
-	}
 
 	ipath_verify_pioperf(dd);
 
diff --git a/drivers/infiniband/hw/ipath/ipath_kernel.h b/drivers/infiniband/hw/ipath/ipath_kernel.h
index e08db70..f0f9471 100644
--- a/drivers/infiniband/hw/ipath/ipath_kernel.h
+++ b/drivers/infiniband/hw/ipath/ipath_kernel.h
@@ -463,9 +463,7 @@ struct ipath_devdata {
 	/* offset in HT config space of slave/primary interface block */
 	u8 ipath_ht_slave_off;
 	/* for write combining settings */
-	unsigned long ipath_wc_cookie;
-	unsigned long ipath_wc_base;
-	unsigned long ipath_wc_len;
+	int wc_cookie;
 	/* ref count for each pkey */
 	atomic_t ipath_pkeyrefs[4];
 	/* shadow copy of struct page *'s for exp tid pages */
diff --git a/drivers/infiniband/hw/ipath/ipath_wc_x86_64.c b/drivers/infiniband/hw/ipath/ipath_wc_x86_64.c
index 70c1f3a..7b6e4c8 100644
--- a/drivers/infiniband/hw/ipath/ipath_wc_x86_64.c
+++ b/drivers/infiniband/hw/ipath/ipath_wc_x86_64.c
@@ -37,7 +37,6 @@
  */
 
 #include <linux/pci.h>
-#include <asm/mtrr.h>
 #include <asm/processor.h>
 
 #include "ipath_kernel.h"
@@ -122,27 +121,14 @@ int ipath_enable_wc(struct ipath_devdata *dd)
 	}
 
 	if (!ret) {
-		int cookie;
-		ipath_cdbg(VERBOSE, "Setting mtrr for chip to WC "
-			   "(addr %llx, len=0x%llx)\n",
-			   (unsigned long long) pioaddr,
-			   (unsigned long long) piolen);
-		cookie = mtrr_add(pioaddr, piolen, MTRR_TYPE_WRCOMB, 1);
-		if (cookie < 0) {
-			{
-				dev_info(&dd->pcidev->dev,
-					 "mtrr_add()  WC for PIO bufs "
-					 "failed (%d)\n",
-					 cookie);
-				ret = -EINVAL;
-			}
-		} else {
-			ipath_cdbg(VERBOSE, "Set mtrr for chip to WC, "
-				   "cookie is %d\n", cookie);
-			dd->ipath_wc_cookie = cookie;
-			dd->ipath_wc_base = (unsigned long) pioaddr;
-			dd->ipath_wc_len = (unsigned long) piolen;
-		}
+		dd->wc_cookie = arch_phys_wc_add(pioaddr, piolen);
+		if (dd->wc_cookie < 0) {
+			ipath_dev_err(dd, "Seting mtrr failed on PIO buffers\n");
+			ret = -ENODEV;
+		} else if (dd->wc_cookie = 0)
+			ipath_cdbg(VERBOSE, "Set mtrr for chip to WC not needed\n");
+		else
+			ipath_cdbg(VERBOSE, "Set mtrr for chip to WC\n");
 	}
 
 	return ret;
@@ -154,16 +140,5 @@ int ipath_enable_wc(struct ipath_devdata *dd)
  */
 void ipath_disable_wc(struct ipath_devdata *dd)
 {
-	if (dd->ipath_wc_cookie) {
-		int r;
-		ipath_cdbg(VERBOSE, "undoing WCCOMB on pio buffers\n");
-		r = mtrr_del(dd->ipath_wc_cookie, dd->ipath_wc_base,
-			     dd->ipath_wc_len);
-		if (r < 0)
-			dev_info(&dd->pcidev->dev,
-				 "mtrr_del(%lx, %lx, %lx) failed: %d\n",
-				 dd->ipath_wc_cookie, dd->ipath_wc_base,
-				 dd->ipath_wc_len, r);
-		dd->ipath_wc_cookie = 0; /* even on failure */
-	}
+	arch_phys_wc_del(dd->wc_cookie);
 }
-- 
2.3.2.209.gd67f9d5.dirty