IOMMU Archive on lore.kernel.org
 help / color / Atom feed
* [PATCH v2] iommu/amd: Disable IOMMU on Stoney Ridge systems
@ 2019-11-29 14:21 Kai-Heng Feng
  2019-12-01 12:42 ` Lucas Stach
  2019-12-02 17:00 ` Christoph Hellwig
  0 siblings, 2 replies; 8+ messages in thread
From: Kai-Heng Feng @ 2019-11-29 14:21 UTC (permalink / raw)
  To: joro; +Cc: Alex Deucher, iommu, Kai-Heng Feng, linux-kernel

Serious screen flickering when Stoney Ridge outputs to a 4K monitor.

According to Alex Deucher, IOMMU isn't enabled on Windows, so let's do
the same here to avoid screen flickering on 4K monitor.

Cc: Alex Deucher <alexander.deucher@amd.com>
Bug: https://gitlab.freedesktop.org/drm/amd/issues/961
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
---
v2:
- Find Stoney graphics instead of host bridge.

 drivers/iommu/amd_iommu_init.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 568c52317757..139aa6fdadda 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -2516,6 +2516,7 @@ static int __init early_amd_iommu_init(void)
 	struct acpi_table_header *ivrs_base;
 	acpi_status status;
 	int i, remap_cache_sz, ret = 0;
+	u32 pci_id;
 
 	if (!amd_iommu_detected)
 		return -ENODEV;
@@ -2603,6 +2604,16 @@ static int __init early_amd_iommu_init(void)
 	if (ret)
 		goto out;
 
+	/* Disable IOMMU if there's Stoney Ridge graphics */
+	for (i = 0; i < 32; i++) {
+		pci_id = read_pci_config(0, i, 0, 0);
+		if ((pci_id & 0xffff) == 0x1002 && (pci_id >> 16) == 0x98e4) {
+			pr_info("Disable IOMMU on Stoney Ridge\n");
+			amd_iommu_disabled = true;
+			break;
+		}
+	}
+
 	/* Disable any previously enabled IOMMUs */
 	if (!is_kdump_kernel() || amd_iommu_disabled)
 		disable_iommus();
@@ -2711,7 +2722,7 @@ static int __init state_next(void)
 		ret = early_amd_iommu_init();
 		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_ACPI_FINISHED;
 		if (init_state == IOMMU_ACPI_FINISHED && amd_iommu_disabled) {
-			pr_info("AMD IOMMU disabled on kernel command-line\n");
+			pr_info("AMD IOMMU disabled\n");
 			init_state = IOMMU_CMDLINE_DISABLED;
 			ret = -EINVAL;
 		}
-- 
2.17.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: [PATCH v2] iommu/amd: Disable IOMMU on Stoney Ridge systems
  2019-11-29 14:21 [PATCH v2] iommu/amd: Disable IOMMU on Stoney Ridge systems Kai-Heng Feng
@ 2019-12-01 12:42 ` Lucas Stach
  2019-12-02 16:36   ` Deucher, Alexander
  2019-12-02 17:00 ` Christoph Hellwig
  1 sibling, 1 reply; 8+ messages in thread
From: Lucas Stach @ 2019-12-01 12:42 UTC (permalink / raw)
  To: Kai-Heng Feng, joro; +Cc: Alex Deucher, iommu, linux-kernel

Am Freitag, den 29.11.2019, 22:21 +0800 schrieb Kai-Heng Feng:
> Serious screen flickering when Stoney Ridge outputs to a 4K monitor.
> 
> According to Alex Deucher, IOMMU isn't enabled on Windows, so let's do
> the same here to avoid screen flickering on 4K monitor.

This doesn't seem like a good solution, especially if there isn't a
method for the user to opt-out.  Some users might prefer having the
IOMMU support to 4K display output.

But before using the big hammer of disabling or breaking one of those
features, we should take a look at what's the issue here. Screen
flickering caused by the IOMMU being active hints to the IOMMU not
being able to sustain the translation bandwidth required by the high-
bandwidth isochronous transfers caused by 4K scanout, most likely due
to insufficient TLB space.

As far as I know the framebuffer memory for the display buffers is
located in stolen RAM, and thus contigous in memory. I don't know the
details of the GPU integration on those APUs, but maybe there even is a
way to bypass the IOMMU for the stolen VRAM regions?

If there isn't and all GPU traffic passes through the IOMMU when
active, we should check if the stolen RAM is mapped with hugepages on
the IOMMU side. All the stolen RAM can most likely be mapped with a few
hugepage mappings, which should reduce IOMMU TLB demand by a large
margin.

Regards,
Lucas

> Cc: Alex Deucher <alexander.deucher@amd.com>
> Bug: https://gitlab.freedesktop.org/drm/amd/issues/961
> Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
> ---
> v2:
> - Find Stoney graphics instead of host bridge.
> 
>  drivers/iommu/amd_iommu_init.c | 13 ++++++++++++-
>  1 file changed, 12 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
> index 568c52317757..139aa6fdadda 100644
> --- a/drivers/iommu/amd_iommu_init.c
> +++ b/drivers/iommu/amd_iommu_init.c
> @@ -2516,6 +2516,7 @@ static int __init early_amd_iommu_init(void)
>  	struct acpi_table_header *ivrs_base;
>  	acpi_status status;
>  	int i, remap_cache_sz, ret = 0;
> +	u32 pci_id;
>  
>  	if (!amd_iommu_detected)
>  		return -ENODEV;
> @@ -2603,6 +2604,16 @@ static int __init early_amd_iommu_init(void)
>  	if (ret)
>  		goto out;
>  
> +	/* Disable IOMMU if there's Stoney Ridge graphics */
> +	for (i = 0; i < 32; i++) {
> +		pci_id = read_pci_config(0, i, 0, 0);
> +		if ((pci_id & 0xffff) == 0x1002 && (pci_id >> 16) == 0x98e4) {
> +			pr_info("Disable IOMMU on Stoney Ridge\n");
> +			amd_iommu_disabled = true;
> +			break;
> +		}
> +	}
> +
>  	/* Disable any previously enabled IOMMUs */
>  	if (!is_kdump_kernel() || amd_iommu_disabled)
>  		disable_iommus();
> @@ -2711,7 +2722,7 @@ static int __init state_next(void)
>  		ret = early_amd_iommu_init();
>  		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_ACPI_FINISHED;
>  		if (init_state == IOMMU_ACPI_FINISHED && amd_iommu_disabled) {
> -			pr_info("AMD IOMMU disabled on kernel command-line\n");
> +			pr_info("AMD IOMMU disabled\n");
>  			init_state = IOMMU_CMDLINE_DISABLED;
>  			ret = -EINVAL;
>  		}

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

^ permalink raw reply	[flat|nested] 8+ messages in thread

* RE: [PATCH v2] iommu/amd: Disable IOMMU on Stoney Ridge systems
  2019-12-01 12:42 ` Lucas Stach
@ 2019-12-02 16:36   ` Deucher, Alexander
  2019-12-04 16:08     ` Deucher, Alexander
  0 siblings, 1 reply; 8+ messages in thread
From: Deucher, Alexander @ 2019-12-02 16:36 UTC (permalink / raw)
  To: Lucas Stach, Kai-Heng Feng, joro, Koenig, Christian; +Cc: iommu, linux-kernel

> -----Original Message-----
> From: Lucas Stach <dev@lynxeye.de>
> Sent: Sunday, December 1, 2019 7:43 AM
> To: Kai-Heng Feng <kai.heng.feng@canonical.com>; joro@8bytes.org
> Cc: Deucher, Alexander <Alexander.Deucher@amd.com>;
> iommu@lists.linux-foundation.org; linux-kernel@vger.kernel.org
> Subject: Re: [PATCH v2] iommu/amd: Disable IOMMU on Stoney Ridge
> systems
> 
> Am Freitag, den 29.11.2019, 22:21 +0800 schrieb Kai-Heng Feng:
> > Serious screen flickering when Stoney Ridge outputs to a 4K monitor.
> >
> > According to Alex Deucher, IOMMU isn't enabled on Windows, so let's do
> > the same here to avoid screen flickering on 4K monitor.
> 
> This doesn't seem like a good solution, especially if there isn't a method for
> the user to opt-out.  Some users might prefer having the IOMMU support to
> 4K display output.
> 
> But before using the big hammer of disabling or breaking one of those
> features, we should take a look at what's the issue here. Screen flickering
> caused by the IOMMU being active hints to the IOMMU not being able to
> sustain the translation bandwidth required by the high- bandwidth
> isochronous transfers caused by 4K scanout, most likely due to insufficient
> TLB space.
> 
> As far as I know the framebuffer memory for the display buffers is located in
> stolen RAM, and thus contigous in memory. I don't know the details of the
> GPU integration on those APUs, but maybe there even is a way to bypass the
> IOMMU for the stolen VRAM regions?
> 
> If there isn't and all GPU traffic passes through the IOMMU when active, we
> should check if the stolen RAM is mapped with hugepages on the IOMMU
> side. All the stolen RAM can most likely be mapped with a few hugepage
> mappings, which should reduce IOMMU TLB demand by a large margin.

The is no issue when we scan out of the carve out region.  The issue occurs when we scan out of regular system memory (scatter/gather).  Many newer laptops have very small carve out regions (e.g., 32 MB), so we have to use regular system pages to support multiple high resolution displays.  The problem is, the latency gets too high at some point when the IOMMU is involved.  Huge pages would probably help in this case, but I'm not sure if there is any way to guarantee that we get huge pages for system memory.  I guess we could use CMA or something like that.

Alex

> 
> Regards,
> Lucas
> 
> > Cc: Alex Deucher <alexander.deucher@amd.com>
> > Bug:
> > https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgitl
> >
> ab.freedesktop.org%2Fdrm%2Famd%2Fissues%2F961&amp;data=02%7C01%
> 7Calexa
> >
> nder.deucher%40amd.com%7C30540b2bf2be417c4d9508d7765bf07f%7C3dd
> 8961fe4
> >
> 884e608e11a82d994e183d%7C0%7C0%7C637108010075463266&amp;sdata=1
> ZIZUWos
> > cPiB4auOY10jlGzoFeWszYMDBQG0CtrrOO8%3D&amp;reserved=0
> > Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
> > ---
> > v2:
> > - Find Stoney graphics instead of host bridge.
> >
> >  drivers/iommu/amd_iommu_init.c | 13 ++++++++++++-
> >  1 file changed, 12 insertions(+), 1 deletion(-)
> >
> > diff --git a/drivers/iommu/amd_iommu_init.c
> > b/drivers/iommu/amd_iommu_init.c index 568c52317757..139aa6fdadda
> > 100644
> > --- a/drivers/iommu/amd_iommu_init.c
> > +++ b/drivers/iommu/amd_iommu_init.c
> > @@ -2516,6 +2516,7 @@ static int __init early_amd_iommu_init(void)
> >  	struct acpi_table_header *ivrs_base;
> >  	acpi_status status;
> >  	int i, remap_cache_sz, ret = 0;
> > +	u32 pci_id;
> >
> >  	if (!amd_iommu_detected)
> >  		return -ENODEV;
> > @@ -2603,6 +2604,16 @@ static int __init early_amd_iommu_init(void)
> >  	if (ret)
> >  		goto out;
> >
> > +	/* Disable IOMMU if there's Stoney Ridge graphics */
> > +	for (i = 0; i < 32; i++) {
> > +		pci_id = read_pci_config(0, i, 0, 0);
> > +		if ((pci_id & 0xffff) == 0x1002 && (pci_id >> 16) == 0x98e4) {
> > +			pr_info("Disable IOMMU on Stoney Ridge\n");
> > +			amd_iommu_disabled = true;
> > +			break;
> > +		}
> > +	}
> > +
> >  	/* Disable any previously enabled IOMMUs */
> >  	if (!is_kdump_kernel() || amd_iommu_disabled)
> >  		disable_iommus();
> > @@ -2711,7 +2722,7 @@ static int __init state_next(void)
> >  		ret = early_amd_iommu_init();
> >  		init_state = ret ? IOMMU_INIT_ERROR :
> IOMMU_ACPI_FINISHED;
> >  		if (init_state == IOMMU_ACPI_FINISHED &&
> amd_iommu_disabled) {
> > -			pr_info("AMD IOMMU disabled on kernel command-
> line\n");
> > +			pr_info("AMD IOMMU disabled\n");
> >  			init_state = IOMMU_CMDLINE_DISABLED;
> >  			ret = -EINVAL;
> >  		}

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: [PATCH v2] iommu/amd: Disable IOMMU on Stoney Ridge systems
  2019-11-29 14:21 [PATCH v2] iommu/amd: Disable IOMMU on Stoney Ridge systems Kai-Heng Feng
  2019-12-01 12:42 ` Lucas Stach
@ 2019-12-02 17:00 ` Christoph Hellwig
  2019-12-06  5:57   ` Kai-Heng Feng
  1 sibling, 1 reply; 8+ messages in thread
From: Christoph Hellwig @ 2019-12-02 17:00 UTC (permalink / raw)
  To: Kai-Heng Feng; +Cc: Alex Deucher, iommu, linux-kernel

On Fri, Nov 29, 2019 at 10:21:54PM +0800, Kai-Heng Feng wrote:
> Serious screen flickering when Stoney Ridge outputs to a 4K monitor.
> 
> According to Alex Deucher, IOMMU isn't enabled on Windows, so let's do
> the same here to avoid screen flickering on 4K monitor.

Disabling the IOMMU entirely seem pretty severe.  Isn't it enough to
identity map the GPU device?
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

^ permalink raw reply	[flat|nested] 8+ messages in thread

* RE: [PATCH v2] iommu/amd: Disable IOMMU on Stoney Ridge systems
  2019-12-02 16:36   ` Deucher, Alexander
@ 2019-12-04 16:08     ` Deucher, Alexander
  2019-12-06  5:59       ` Kai-Heng Feng
  2019-12-06  8:57       ` Christian König
  0 siblings, 2 replies; 8+ messages in thread
From: Deucher, Alexander @ 2019-12-04 16:08 UTC (permalink / raw)
  To: Lucas Stach, Kai-Heng Feng, joro, Koenig, Christian; +Cc: iommu, linux-kernel

> -----Original Message-----
> From: Deucher, Alexander
> Sent: Monday, December 2, 2019 11:37 AM
> To: Lucas Stach <dev@lynxeye.de>; Kai-Heng Feng
> <kai.heng.feng@canonical.com>; joro@8bytes.org; Koenig, Christian
> (Christian.Koenig@amd.com) <Christian.Koenig@amd.com>
> Cc: iommu@lists.linux-foundation.org; linux-kernel@vger.kernel.org
> Subject: RE: [PATCH v2] iommu/amd: Disable IOMMU on Stoney Ridge
> systems
> 
> > -----Original Message-----
> > From: Lucas Stach <dev@lynxeye.de>
> > Sent: Sunday, December 1, 2019 7:43 AM
> > To: Kai-Heng Feng <kai.heng.feng@canonical.com>; joro@8bytes.org
> > Cc: Deucher, Alexander <Alexander.Deucher@amd.com>;
> > iommu@lists.linux-foundation.org; linux-kernel@vger.kernel.org
> > Subject: Re: [PATCH v2] iommu/amd: Disable IOMMU on Stoney Ridge
> > systems
> >
> > Am Freitag, den 29.11.2019, 22:21 +0800 schrieb Kai-Heng Feng:
> > > Serious screen flickering when Stoney Ridge outputs to a 4K monitor.
> > >
> > > According to Alex Deucher, IOMMU isn't enabled on Windows, so let's
> > > do the same here to avoid screen flickering on 4K monitor.
> >
> > This doesn't seem like a good solution, especially if there isn't a
> > method for the user to opt-out.  Some users might prefer having the
> > IOMMU support to 4K display output.
> >
> > But before using the big hammer of disabling or breaking one of those
> > features, we should take a look at what's the issue here. Screen
> > flickering caused by the IOMMU being active hints to the IOMMU not
> > being able to sustain the translation bandwidth required by the high-
> > bandwidth isochronous transfers caused by 4K scanout, most likely due
> > to insufficient TLB space.
> >
> > As far as I know the framebuffer memory for the display buffers is
> > located in stolen RAM, and thus contigous in memory. I don't know the
> > details of the GPU integration on those APUs, but maybe there even is
> > a way to bypass the IOMMU for the stolen VRAM regions?
> >
> > If there isn't and all GPU traffic passes through the IOMMU when
> > active, we should check if the stolen RAM is mapped with hugepages on
> > the IOMMU side. All the stolen RAM can most likely be mapped with a
> > few hugepage mappings, which should reduce IOMMU TLB demand by a
> large margin.
> 
> The is no issue when we scan out of the carve out region.  The issue occurs
> when we scan out of regular system memory (scatter/gather).  Many newer
> laptops have very small carve out regions (e.g., 32 MB), so we have to use
> regular system pages to support multiple high resolution displays.  The
> problem is, the latency gets too high at some point when the IOMMU is
> involved.  Huge pages would probably help in this case, but I'm not sure if
> there is any way to guarantee that we get huge pages for system memory.  I
> guess we could use CMA or something like that.

Thomas recently sent out a patch set to add huge page support to ttm:
https://patchwork.freedesktop.org/series/70090/
We'd still need a way to guarantee huge pages for the display buffer.

Alex

> 
> Alex
> 
> >
> > Regards,
> > Lucas
> >
> > > Cc: Alex Deucher <alexander.deucher@amd.com>
> > > Bug:
> > >
> https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgi
> > > tl
> > >
> >
> ab.freedesktop.org%2Fdrm%2Famd%2Fissues%2F961&amp;data=02%7C01%
> > 7Calexa
> > >
> >
> nder.deucher%40amd.com%7C30540b2bf2be417c4d9508d7765bf07f%7C3dd
> > 8961fe4
> > >
> >
> 884e608e11a82d994e183d%7C0%7C0%7C637108010075463266&amp;sdata=1
> > ZIZUWos
> > > cPiB4auOY10jlGzoFeWszYMDBQG0CtrrOO8%3D&amp;reserved=0
> > > Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
> > > ---
> > > v2:
> > > - Find Stoney graphics instead of host bridge.
> > >
> > >  drivers/iommu/amd_iommu_init.c | 13 ++++++++++++-
> > >  1 file changed, 12 insertions(+), 1 deletion(-)
> > >
> > > diff --git a/drivers/iommu/amd_iommu_init.c
> > > b/drivers/iommu/amd_iommu_init.c index 568c52317757..139aa6fdadda
> > > 100644
> > > --- a/drivers/iommu/amd_iommu_init.c
> > > +++ b/drivers/iommu/amd_iommu_init.c
> > > @@ -2516,6 +2516,7 @@ static int __init early_amd_iommu_init(void)
> > >  	struct acpi_table_header *ivrs_base;
> > >  	acpi_status status;
> > >  	int i, remap_cache_sz, ret = 0;
> > > +	u32 pci_id;
> > >
> > >  	if (!amd_iommu_detected)
> > >  		return -ENODEV;
> > > @@ -2603,6 +2604,16 @@ static int __init early_amd_iommu_init(void)
> > >  	if (ret)
> > >  		goto out;
> > >
> > > +	/* Disable IOMMU if there's Stoney Ridge graphics */
> > > +	for (i = 0; i < 32; i++) {
> > > +		pci_id = read_pci_config(0, i, 0, 0);
> > > +		if ((pci_id & 0xffff) == 0x1002 && (pci_id >> 16) == 0x98e4) {
> > > +			pr_info("Disable IOMMU on Stoney Ridge\n");
> > > +			amd_iommu_disabled = true;
> > > +			break;
> > > +		}
> > > +	}
> > > +
> > >  	/* Disable any previously enabled IOMMUs */
> > >  	if (!is_kdump_kernel() || amd_iommu_disabled)
> > >  		disable_iommus();
> > > @@ -2711,7 +2722,7 @@ static int __init state_next(void)
> > >  		ret = early_amd_iommu_init();
> > >  		init_state = ret ? IOMMU_INIT_ERROR :
> > IOMMU_ACPI_FINISHED;
> > >  		if (init_state == IOMMU_ACPI_FINISHED &&
> > amd_iommu_disabled) {
> > > -			pr_info("AMD IOMMU disabled on kernel command-
> > line\n");
> > > +			pr_info("AMD IOMMU disabled\n");
> > >  			init_state = IOMMU_CMDLINE_DISABLED;
> > >  			ret = -EINVAL;
> > >  		}

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: [PATCH v2] iommu/amd: Disable IOMMU on Stoney Ridge systems
  2019-12-02 17:00 ` Christoph Hellwig
@ 2019-12-06  5:57   ` Kai-Heng Feng
  0 siblings, 0 replies; 8+ messages in thread
From: Kai-Heng Feng @ 2019-12-06  5:57 UTC (permalink / raw)
  To: Joerg Roedel; +Cc: Alex Deucher, iommu, Kernel development list

Hi Joerg,

> On Dec 3, 2019, at 01:00, Christoph Hellwig <hch@infradead.org> wrote:
> 
> On Fri, Nov 29, 2019 at 10:21:54PM +0800, Kai-Heng Feng wrote:
>> Serious screen flickering when Stoney Ridge outputs to a 4K monitor.
>> 
>> According to Alex Deucher, IOMMU isn't enabled on Windows, so let's do
>> the same here to avoid screen flickering on 4K monitor.
> 
> Disabling the IOMMU entirely seem pretty severe.  Isn't it enough to
> identity map the GPU device?

Ok, there's set_device_exclusion_range() to exclude the device from IOMMU.
However I don't know how to generate range_start and range_length, which are read from ACPI.

Can you please give me some advice here?

Kai-Henge
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: [PATCH v2] iommu/amd: Disable IOMMU on Stoney Ridge systems
  2019-12-04 16:08     ` Deucher, Alexander
@ 2019-12-06  5:59       ` Kai-Heng Feng
  2019-12-06  8:57       ` Christian König
  1 sibling, 0 replies; 8+ messages in thread
From: Kai-Heng Feng @ 2019-12-06  5:59 UTC (permalink / raw)
  To: Deucher, Alexander; +Cc: Koenig, Christian, iommu, linux-kernel



> On Dec 5, 2019, at 00:08, Deucher, Alexander <alexander.deucher@amd.com> wrote:
> 
>> -----Original Message-----
>> From: Deucher, Alexander
>> Sent: Monday, December 2, 2019 11:37 AM
>> To: Lucas Stach <dev@lynxeye.de>; Kai-Heng Feng
>> <kai.heng.feng@canonical.com>; joro@8bytes.org; Koenig, Christian
>> (Christian.Koenig@amd.com) <Christian.Koenig@amd.com>
>> Cc: iommu@lists.linux-foundation.org; linux-kernel@vger.kernel.org
>> Subject: RE: [PATCH v2] iommu/amd: Disable IOMMU on Stoney Ridge
>> systems
>> 
>>> -----Original Message-----
>>> From: Lucas Stach <dev@lynxeye.de>
>>> Sent: Sunday, December 1, 2019 7:43 AM
>>> To: Kai-Heng Feng <kai.heng.feng@canonical.com>; joro@8bytes.org
>>> Cc: Deucher, Alexander <Alexander.Deucher@amd.com>;
>>> iommu@lists.linux-foundation.org; linux-kernel@vger.kernel.org
>>> Subject: Re: [PATCH v2] iommu/amd: Disable IOMMU on Stoney Ridge
>>> systems
>>> 
>>> Am Freitag, den 29.11.2019, 22:21 +0800 schrieb Kai-Heng Feng:
>>>> Serious screen flickering when Stoney Ridge outputs to a 4K monitor.
>>>> 
>>>> According to Alex Deucher, IOMMU isn't enabled on Windows, so let's
>>>> do the same here to avoid screen flickering on 4K monitor.
>>> 
>>> This doesn't seem like a good solution, especially if there isn't a
>>> method for the user to opt-out.  Some users might prefer having the
>>> IOMMU support to 4K display output.
>>> 
>>> But before using the big hammer of disabling or breaking one of those
>>> features, we should take a look at what's the issue here. Screen
>>> flickering caused by the IOMMU being active hints to the IOMMU not
>>> being able to sustain the translation bandwidth required by the high-
>>> bandwidth isochronous transfers caused by 4K scanout, most likely due
>>> to insufficient TLB space.
>>> 
>>> As far as I know the framebuffer memory for the display buffers is
>>> located in stolen RAM, and thus contigous in memory. I don't know the
>>> details of the GPU integration on those APUs, but maybe there even is
>>> a way to bypass the IOMMU for the stolen VRAM regions?
>>> 
>>> If there isn't and all GPU traffic passes through the IOMMU when
>>> active, we should check if the stolen RAM is mapped with hugepages on
>>> the IOMMU side. All the stolen RAM can most likely be mapped with a
>>> few hugepage mappings, which should reduce IOMMU TLB demand by a
>> large margin.
>> 
>> The is no issue when we scan out of the carve out region.  The issue occurs
>> when we scan out of regular system memory (scatter/gather).  Many newer
>> laptops have very small carve out regions (e.g., 32 MB), so we have to use
>> regular system pages to support multiple high resolution displays.  The
>> problem is, the latency gets too high at some point when the IOMMU is
>> involved.  Huge pages would probably help in this case, but I'm not sure if
>> there is any way to guarantee that we get huge pages for system memory.  I
>> guess we could use CMA or something like that.
> 
> Thomas recently sent out a patch set to add huge page support to ttm:
> https://patchwork.freedesktop.org/series/70090/
> We'd still need a way to guarantee huge pages for the display buffer.

Is there an amdgpu counterpart to let me test out?

Kai-Heng

> 
> Alex
> 
>> 
>> Alex
>> 
>>> 
>>> Regards,
>>> Lucas
>>> 
>>>> Cc: Alex Deucher <alexander.deucher@amd.com>
>>>> Bug:
>>>> 
>> https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgi
>>>> tl
>>>> 
>>> 
>> ab.freedesktop.org%2Fdrm%2Famd%2Fissues%2F961&amp;data=02%7C01%
>>> 7Calexa
>>>> 
>>> 
>> nder.deucher%40amd.com%7C30540b2bf2be417c4d9508d7765bf07f%7C3dd
>>> 8961fe4
>>>> 
>>> 
>> 884e608e11a82d994e183d%7C0%7C0%7C637108010075463266&amp;sdata=1
>>> ZIZUWos
>>>> cPiB4auOY10jlGzoFeWszYMDBQG0CtrrOO8%3D&amp;reserved=0
>>>> Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
>>>> ---
>>>> v2:
>>>> - Find Stoney graphics instead of host bridge.
>>>> 
>>>> drivers/iommu/amd_iommu_init.c | 13 ++++++++++++-
>>>> 1 file changed, 12 insertions(+), 1 deletion(-)
>>>> 
>>>> diff --git a/drivers/iommu/amd_iommu_init.c
>>>> b/drivers/iommu/amd_iommu_init.c index 568c52317757..139aa6fdadda
>>>> 100644
>>>> --- a/drivers/iommu/amd_iommu_init.c
>>>> +++ b/drivers/iommu/amd_iommu_init.c
>>>> @@ -2516,6 +2516,7 @@ static int __init early_amd_iommu_init(void)
>>>> 	struct acpi_table_header *ivrs_base;
>>>> 	acpi_status status;
>>>> 	int i, remap_cache_sz, ret = 0;
>>>> +	u32 pci_id;
>>>> 
>>>> 	if (!amd_iommu_detected)
>>>> 		return -ENODEV;
>>>> @@ -2603,6 +2604,16 @@ static int __init early_amd_iommu_init(void)
>>>> 	if (ret)
>>>> 		goto out;
>>>> 
>>>> +	/* Disable IOMMU if there's Stoney Ridge graphics */
>>>> +	for (i = 0; i < 32; i++) {
>>>> +		pci_id = read_pci_config(0, i, 0, 0);
>>>> +		if ((pci_id & 0xffff) == 0x1002 && (pci_id >> 16) == 0x98e4) {
>>>> +			pr_info("Disable IOMMU on Stoney Ridge\n");
>>>> +			amd_iommu_disabled = true;
>>>> +			break;
>>>> +		}
>>>> +	}
>>>> +
>>>> 	/* Disable any previously enabled IOMMUs */
>>>> 	if (!is_kdump_kernel() || amd_iommu_disabled)
>>>> 		disable_iommus();
>>>> @@ -2711,7 +2722,7 @@ static int __init state_next(void)
>>>> 		ret = early_amd_iommu_init();
>>>> 		init_state = ret ? IOMMU_INIT_ERROR :
>>> IOMMU_ACPI_FINISHED;
>>>> 		if (init_state == IOMMU_ACPI_FINISHED &&
>>> amd_iommu_disabled) {
>>>> -			pr_info("AMD IOMMU disabled on kernel command-
>>> line\n");
>>>> +			pr_info("AMD IOMMU disabled\n");
>>>> 			init_state = IOMMU_CMDLINE_DISABLED;
>>>> 			ret = -EINVAL;
>>>> 		}

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: [PATCH v2] iommu/amd: Disable IOMMU on Stoney Ridge systems
  2019-12-04 16:08     ` Deucher, Alexander
  2019-12-06  5:59       ` Kai-Heng Feng
@ 2019-12-06  8:57       ` Christian König
  1 sibling, 0 replies; 8+ messages in thread
From: Christian König @ 2019-12-06  8:57 UTC (permalink / raw)
  To: Deucher, Alexander, Lucas Stach, Kai-Heng Feng, joro; +Cc: iommu, linux-kernel

Am 04.12.19 um 17:08 schrieb Deucher, Alexander:
>> -----Original Message-----
>> From: Deucher, Alexander
>> Sent: Monday, December 2, 2019 11:37 AM
>> To: Lucas Stach <dev@lynxeye.de>; Kai-Heng Feng
>> <kai.heng.feng@canonical.com>; joro@8bytes.org; Koenig, Christian
>> (Christian.Koenig@amd.com) <Christian.Koenig@amd.com>
>> Cc: iommu@lists.linux-foundation.org; linux-kernel@vger.kernel.org
>> Subject: RE: [PATCH v2] iommu/amd: Disable IOMMU on Stoney Ridge
>> systems
>>
>>> -----Original Message-----
>>> From: Lucas Stach <dev@lynxeye.de>
>>> Sent: Sunday, December 1, 2019 7:43 AM
>>> To: Kai-Heng Feng <kai.heng.feng@canonical.com>; joro@8bytes.org
>>> Cc: Deucher, Alexander <Alexander.Deucher@amd.com>;
>>> iommu@lists.linux-foundation.org; linux-kernel@vger.kernel.org
>>> Subject: Re: [PATCH v2] iommu/amd: Disable IOMMU on Stoney Ridge
>>> systems
>>>
>>> Am Freitag, den 29.11.2019, 22:21 +0800 schrieb Kai-Heng Feng:
>>>> Serious screen flickering when Stoney Ridge outputs to a 4K monitor.
>>>>
>>>> According to Alex Deucher, IOMMU isn't enabled on Windows, so let's
>>>> do the same here to avoid screen flickering on 4K monitor.
>>> This doesn't seem like a good solution, especially if there isn't a
>>> method for the user to opt-out.  Some users might prefer having the
>>> IOMMU support to 4K display output.
>>>
>>> But before using the big hammer of disabling or breaking one of those
>>> features, we should take a look at what's the issue here. Screen
>>> flickering caused by the IOMMU being active hints to the IOMMU not
>>> being able to sustain the translation bandwidth required by the high-
>>> bandwidth isochronous transfers caused by 4K scanout, most likely due
>>> to insufficient TLB space.
>>>
>>> As far as I know the framebuffer memory for the display buffers is
>>> located in stolen RAM, and thus contigous in memory. I don't know the
>>> details of the GPU integration on those APUs, but maybe there even is
>>> a way to bypass the IOMMU for the stolen VRAM regions?
>>>
>>> If there isn't and all GPU traffic passes through the IOMMU when
>>> active, we should check if the stolen RAM is mapped with hugepages on
>>> the IOMMU side. All the stolen RAM can most likely be mapped with a
>>> few hugepage mappings, which should reduce IOMMU TLB demand by a
>> large margin.
>>
>> The is no issue when we scan out of the carve out region.  The issue occurs
>> when we scan out of regular system memory (scatter/gather).  Many newer
>> laptops have very small carve out regions (e.g., 32 MB), so we have to use
>> regular system pages to support multiple high resolution displays.  The
>> problem is, the latency gets too high at some point when the IOMMU is
>> involved.  Huge pages would probably help in this case, but I'm not sure if
>> there is any way to guarantee that we get huge pages for system memory.  I
>> guess we could use CMA or something like that.
> Thomas recently sent out a patch set to add huge page support to ttm:
> https://patchwork.freedesktop.org/series/70090/
> We'd still need a way to guarantee huge pages for the display buffer.

That unfortunately won't help in this case since the TTM work Thomas is 
doing only affects the CPU page tables.

Additional to that we already allocate huge pages for the display buffer 
in a best effort manner and it doesn't seem to help.

If I understood the hardware guys correctly even transparent mode adds 
to much latency so that the display block might run into an underflow.

The only solution documented to work is to either disabling the IOMMU or 
not using scan-out from system memory.

Alex, we should probably kick of another internal discussion with the 
hardware guys about that.

Christian.

>
> Alex
>
>> Alex
>>
>>> Regards,
>>> Lucas
>>>
>>>> Cc: Alex Deucher <alexander.deucher@amd.com>
>>>> Bug:
>>>>
>> https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgi
>>>> tl
>>>>
>> ab.freedesktop.org%2Fdrm%2Famd%2Fissues%2F961&amp;data=02%7C01%
>>> 7Calexa
>> nder.deucher%40amd.com%7C30540b2bf2be417c4d9508d7765bf07f%7C3dd
>>> 8961fe4
>> 884e608e11a82d994e183d%7C0%7C0%7C637108010075463266&amp;sdata=1
>>> ZIZUWos
>>>> cPiB4auOY10jlGzoFeWszYMDBQG0CtrrOO8%3D&amp;reserved=0
>>>> Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
>>>> ---
>>>> v2:
>>>> - Find Stoney graphics instead of host bridge.
>>>>
>>>>   drivers/iommu/amd_iommu_init.c | 13 ++++++++++++-
>>>>   1 file changed, 12 insertions(+), 1 deletion(-)
>>>>
>>>> diff --git a/drivers/iommu/amd_iommu_init.c
>>>> b/drivers/iommu/amd_iommu_init.c index 568c52317757..139aa6fdadda
>>>> 100644
>>>> --- a/drivers/iommu/amd_iommu_init.c
>>>> +++ b/drivers/iommu/amd_iommu_init.c
>>>> @@ -2516,6 +2516,7 @@ static int __init early_amd_iommu_init(void)
>>>>   	struct acpi_table_header *ivrs_base;
>>>>   	acpi_status status;
>>>>   	int i, remap_cache_sz, ret = 0;
>>>> +	u32 pci_id;
>>>>
>>>>   	if (!amd_iommu_detected)
>>>>   		return -ENODEV;
>>>> @@ -2603,6 +2604,16 @@ static int __init early_amd_iommu_init(void)
>>>>   	if (ret)
>>>>   		goto out;
>>>>
>>>> +	/* Disable IOMMU if there's Stoney Ridge graphics */
>>>> +	for (i = 0; i < 32; i++) {
>>>> +		pci_id = read_pci_config(0, i, 0, 0);
>>>> +		if ((pci_id & 0xffff) == 0x1002 && (pci_id >> 16) == 0x98e4) {
>>>> +			pr_info("Disable IOMMU on Stoney Ridge\n");
>>>> +			amd_iommu_disabled = true;
>>>> +			break;
>>>> +		}
>>>> +	}
>>>> +
>>>>   	/* Disable any previously enabled IOMMUs */
>>>>   	if (!is_kdump_kernel() || amd_iommu_disabled)
>>>>   		disable_iommus();
>>>> @@ -2711,7 +2722,7 @@ static int __init state_next(void)
>>>>   		ret = early_amd_iommu_init();
>>>>   		init_state = ret ? IOMMU_INIT_ERROR :
>>> IOMMU_ACPI_FINISHED;
>>>>   		if (init_state == IOMMU_ACPI_FINISHED &&
>>> amd_iommu_disabled) {
>>>> -			pr_info("AMD IOMMU disabled on kernel command-
>>> line\n");
>>>> +			pr_info("AMD IOMMU disabled\n");
>>>>   			init_state = IOMMU_CMDLINE_DISABLED;
>>>>   			ret = -EINVAL;
>>>>   		}

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

^ permalink raw reply	[flat|nested] 8+ messages in thread

end of thread, back to index

Thread overview: 8+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-11-29 14:21 [PATCH v2] iommu/amd: Disable IOMMU on Stoney Ridge systems Kai-Heng Feng
2019-12-01 12:42 ` Lucas Stach
2019-12-02 16:36   ` Deucher, Alexander
2019-12-04 16:08     ` Deucher, Alexander
2019-12-06  5:59       ` Kai-Heng Feng
2019-12-06  8:57       ` Christian König
2019-12-02 17:00 ` Christoph Hellwig
2019-12-06  5:57   ` Kai-Heng Feng

IOMMU Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-iommu/0 linux-iommu/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-iommu linux-iommu/ https://lore.kernel.org/linux-iommu \
		iommu@lists.linux-foundation.org
	public-inbox-index linux-iommu

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.linux-foundation.lists.iommu


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git