[PATCH] PCI: Apply quirk_amd_harvest_no_ats to all navi10 and 14 asics

linux-pci.vger.kernel.org archive mirror
 help / color / mirror / Atom feed

* [PATCH] PCI: Apply quirk_amd_harvest_no_ats to all navi10 and 14 asics
@ 2022-02-22 16:08 Alex Deucher
  2022-02-22 16:22 ` Christian König
                   ` (2 more replies)
  0 siblings, 3 replies; 4+ messages in thread
From: Alex Deucher @ 2022-02-22 16:08 UTC (permalink / raw)
  To: amd-gfx, bhelgaas, linux-pci; +Cc: Alex Deucher

There are enough vbios escapes without the proper workaround
that some users still hit this.  MS never productized ATS on
windows so OEM platforms that were windows only didn't always
validate ATS.

The advantages of ATS are not worth it compared to the potential
instabilities on harvested boards.  Just disable ATS on all navi10
and 14 boards.

Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1760
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/pci/quirks.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 003950c738d2..ea2de1616510 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -5341,11 +5341,6 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0422, quirk_no_ext_tags);
  */
 static void quirk_amd_harvest_no_ats(struct pci_dev *pdev)
 {
-	if ((pdev->device == 0x7312 && pdev->revision != 0x00) ||
-	    (pdev->device == 0x7340 && pdev->revision != 0xc5) ||
-	    (pdev->device == 0x7341 && pdev->revision != 0x00))
-		return;
-
 	if (pdev->device == 0x15d8) {
 		if (pdev->revision == 0xcf &&
 		    pdev->subsystem_vendor == 0xea50 &&
@@ -5367,10 +5362,19 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x98e4, quirk_amd_harvest_no_ats);
 /* AMD Iceland dGPU */
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6900, quirk_amd_harvest_no_ats);
 /* AMD Navi10 dGPU */
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7310, quirk_amd_harvest_no_ats);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7312, quirk_amd_harvest_no_ats);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7318, quirk_amd_harvest_no_ats);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7319, quirk_amd_harvest_no_ats);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x731a, quirk_amd_harvest_no_ats);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x731b, quirk_amd_harvest_no_ats);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x731e, quirk_amd_harvest_no_ats);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x731f, quirk_amd_harvest_no_ats);
 /* AMD Navi14 dGPU */
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7340, quirk_amd_harvest_no_ats);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7341, quirk_amd_harvest_no_ats);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7347, quirk_amd_harvest_no_ats);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x734f, quirk_amd_harvest_no_ats);
 /* AMD Raven platform iGPU */
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x15d8, quirk_amd_harvest_no_ats);
 #endif /* CONFIG_PCI_ATS */
-- 
2.35.1


^ permalink raw reply related	[flat|nested] 4+ messages in thread

* Re: [PATCH] PCI: Apply quirk_amd_harvest_no_ats to all navi10 and 14 asics
  2022-02-22 16:08 [PATCH] PCI: Apply quirk_amd_harvest_no_ats to all navi10 and 14 asics Alex Deucher
@ 2022-02-22 16:22 ` Christian König
  2022-02-23  2:37 ` Chen, Guchun
  2022-02-23 20:13 ` Bjorn Helgaas
  2 siblings, 0 replies; 4+ messages in thread
From: Christian König @ 2022-02-22 16:22 UTC (permalink / raw)
  To: Alex Deucher, amd-gfx, bhelgaas, linux-pci

Am 22.02.22 um 17:08 schrieb Alex Deucher:
> There are enough vbios escapes without the proper workaround
> that some users still hit this.  MS never productized ATS on
> windows so OEM platforms that were windows only didn't always
> validate ATS.
>
> The advantages of ATS are not worth it compared to the potential
> instabilities on harvested boards.  Just disable ATS on all navi10
> and 14 boards.
>
> Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1760
> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Acked-by: Christian König <christian.koenig@amd.com>

> ---
>   drivers/pci/quirks.c | 14 +++++++++-----
>   1 file changed, 9 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
> index 003950c738d2..ea2de1616510 100644
> --- a/drivers/pci/quirks.c
> +++ b/drivers/pci/quirks.c
> @@ -5341,11 +5341,6 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0422, quirk_no_ext_tags);
>    */
>   static void quirk_amd_harvest_no_ats(struct pci_dev *pdev)
>   {
> -	if ((pdev->device == 0x7312 && pdev->revision != 0x00) ||
> -	    (pdev->device == 0x7340 && pdev->revision != 0xc5) ||
> -	    (pdev->device == 0x7341 && pdev->revision != 0x00))
> -		return;
> -
>   	if (pdev->device == 0x15d8) {
>   		if (pdev->revision == 0xcf &&
>   		    pdev->subsystem_vendor == 0xea50 &&
> @@ -5367,10 +5362,19 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x98e4, quirk_amd_harvest_no_ats);
>   /* AMD Iceland dGPU */
>   DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6900, quirk_amd_harvest_no_ats);
>   /* AMD Navi10 dGPU */
> +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7310, quirk_amd_harvest_no_ats);
>   DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7312, quirk_amd_harvest_no_ats);
> +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7318, quirk_amd_harvest_no_ats);
> +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7319, quirk_amd_harvest_no_ats);
> +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x731a, quirk_amd_harvest_no_ats);
> +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x731b, quirk_amd_harvest_no_ats);
> +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x731e, quirk_amd_harvest_no_ats);
> +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x731f, quirk_amd_harvest_no_ats);
>   /* AMD Navi14 dGPU */
>   DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7340, quirk_amd_harvest_no_ats);
>   DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7341, quirk_amd_harvest_no_ats);
> +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7347, quirk_amd_harvest_no_ats);
> +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x734f, quirk_amd_harvest_no_ats);
>   /* AMD Raven platform iGPU */
>   DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x15d8, quirk_amd_harvest_no_ats);
>   #endif /* CONFIG_PCI_ATS */


^ permalink raw reply	[flat|nested] 4+ messages in thread

* RE: [PATCH] PCI: Apply quirk_amd_harvest_no_ats to all navi10 and 14 asics
  2022-02-22 16:08 [PATCH] PCI: Apply quirk_amd_harvest_no_ats to all navi10 and 14 asics Alex Deucher
  2022-02-22 16:22 ` Christian König
@ 2022-02-23  2:37 ` Chen, Guchun
  2022-02-23 20:13 ` Bjorn Helgaas
  2 siblings, 0 replies; 4+ messages in thread
From: Chen, Guchun @ 2022-02-23  2:37 UTC (permalink / raw)
  To: Deucher, Alexander, amd-gfx, bhelgaas, linux-pci; +Cc: Deucher, Alexander

Acked-by: Guchun Chen <guchun.chen@amd.com>

Regards,
Guchun

-----Original Message-----
From: amd-gfx <amd-gfx-bounces@lists.freedesktop.org> On Behalf Of Alex Deucher
Sent: Wednesday, February 23, 2022 12:08 AM
To: amd-gfx@lists.freedesktop.org; bhelgaas@google.com; linux-pci@vger.kernel.org
Cc: Deucher, Alexander <Alexander.Deucher@amd.com>
Subject: [PATCH] PCI: Apply quirk_amd_harvest_no_ats to all navi10 and 14 asics

There are enough vbios escapes without the proper workaround that some users still hit this.  MS never productized ATS on windows so OEM platforms that were windows only didn't always validate ATS.

The advantages of ATS are not worth it compared to the potential instabilities on harvested boards.  Just disable ATS on all navi10 and 14 boards.

Bug: https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgitlab.freedesktop.org%2Fdrm%2Famd%2F-%2Fissues%2F1760&amp;data=04%7C01%7Cguchun.chen%40amd.com%7C1f54cd26c00041e476d008d9f61d92e8%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637811429151667411%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&amp;sdata=1seVVxNb09HvAGelvuyN3WuHI%2BkCkfU%2F50Zzx4rifT4%3D&amp;reserved=0
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/pci/quirks.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 003950c738d2..ea2de1616510 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -5341,11 +5341,6 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0422, quirk_no_ext_tags);
  */
 static void quirk_amd_harvest_no_ats(struct pci_dev *pdev)  {
-	if ((pdev->device == 0x7312 && pdev->revision != 0x00) ||
-	    (pdev->device == 0x7340 && pdev->revision != 0xc5) ||
-	    (pdev->device == 0x7341 && pdev->revision != 0x00))
-		return;
-
 	if (pdev->device == 0x15d8) {
 		if (pdev->revision == 0xcf &&
 		    pdev->subsystem_vendor == 0xea50 && @@ -5367,10 +5362,19 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x98e4, quirk_amd_harvest_no_ats);
 /* AMD Iceland dGPU */
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6900, quirk_amd_harvest_no_ats);
 /* AMD Navi10 dGPU */
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7310, 
+quirk_amd_harvest_no_ats);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7312, quirk_amd_harvest_no_ats);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7318, 
+quirk_amd_harvest_no_ats); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 
+0x7319, quirk_amd_harvest_no_ats); 
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x731a, 
+quirk_amd_harvest_no_ats); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 
+0x731b, quirk_amd_harvest_no_ats); 
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x731e, 
+quirk_amd_harvest_no_ats); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 
+0x731f, quirk_amd_harvest_no_ats);
 /* AMD Navi14 dGPU */
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7340, quirk_amd_harvest_no_ats);  DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7341, quirk_amd_harvest_no_ats);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7347, 
+quirk_amd_harvest_no_ats); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 
+0x734f, quirk_amd_harvest_no_ats);
 /* AMD Raven platform iGPU */
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x15d8, quirk_amd_harvest_no_ats);  #endif /* CONFIG_PCI_ATS */
--
2.35.1


^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: [PATCH] PCI: Apply quirk_amd_harvest_no_ats to all navi10 and 14 asics
  2022-02-22 16:08 [PATCH] PCI: Apply quirk_amd_harvest_no_ats to all navi10 and 14 asics Alex Deucher
  2022-02-22 16:22 ` Christian König
  2022-02-23  2:37 ` Chen, Guchun
@ 2022-02-23 20:13 ` Bjorn Helgaas
  2 siblings, 0 replies; 4+ messages in thread
From: Bjorn Helgaas @ 2022-02-23 20:13 UTC (permalink / raw)
  To: Alex Deucher; +Cc: amd-gfx, bhelgaas, linux-pci

On Tue, Feb 22, 2022 at 11:08:01AM -0500, Alex Deucher wrote:
> There are enough vbios escapes without the proper workaround
> that some users still hit this.  MS never productized ATS on
> windows so OEM platforms that were windows only didn't always
> validate ATS.
> 
> The advantages of ATS are not worth it compared to the potential
> instabilities on harvested boards.  Just disable ATS on all navi10
> and 14 boards.
> 
> Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1760
> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Thanks, applied to for-linus for v5.17 with commit log:

    PCI: Mark all AMD Navi10 and Navi14 GPU ATS as broken
    
    There are enough VBIOS escapes without the proper workaround that some
    users still hit this.  Microsoft never productized ATS on Windows so OEM
    platforms that were Windows-only didn't always validate ATS.
    
    The advantages of ATS are not worth it compared to the potential
    instabilities on harvested boards.  Disable ATS on all Navi10 and Navi14
    boards.
    
    Symptoms include:
    
      amdgpu 0000:07:00.0: AMD-Vi: Event logged [IO_PAGE_FAULT domain=0x0007 address=0xffffc02000 flags=0x0000]
      AMD-Vi: Event logged [IO_PAGE_FAULT device=07:00.0 domain=0x0007 address=0xffffc02000 flags=0x0000]
      [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring sdma0 timeout, signaled seq=6047, emitted seq=6049
      amdgpu 0000:07:00.0: amdgpu: GPU reset begin!
      amdgpu 0000:07:00.0: amdgpu: GPU reset succeeded, trying to resume
      amdgpu 0000:07:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring sdma0 test failed (-110)
      [drm:amdgpu_device_ip_resume_phase2 [amdgpu]] *ERROR* resume of IP block <sdma_v4_0> failed -110
      amdgpu 0000:07:00.0: amdgpu: GPU reset(1) failed
    
    Related commits:
    
      e8946a53e2a6 ("PCI: Mark AMD Navi14 GPU ATS as broken")
      a2da5d8cc0b0 ("PCI: Mark AMD Raven iGPU ATS as broken in some platforms")
      45beb31d3afb ("PCI: Mark AMD Navi10 GPU rev 0x00 ATS as broken")
      5e89cd303e3a ("PCI: Mark AMD Navi14 GPU rev 0xc5 ATS as broken")
      d28ca864c493 ("PCI: Mark AMD Stoney Radeon R7 GPU ATS as broken")
      9b44b0b09dec ("PCI: Mark AMD Stoney GPU ATS as broken")
    
    [bhelgaas: add symptoms and related commits]
    Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1760
    Link: https://lore.kernel.org/r/20220222160801.841643-1-alexander.deucher@amd.com
    Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
    Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
    Acked-by: Christian König <christian.koenig@amd.com>
    Acked-by: Guchun Chen <guchun.chen@amd.com>

> ---
>  drivers/pci/quirks.c | 14 +++++++++-----
>  1 file changed, 9 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
> index 003950c738d2..ea2de1616510 100644
> --- a/drivers/pci/quirks.c
> +++ b/drivers/pci/quirks.c
> @@ -5341,11 +5341,6 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0422, quirk_no_ext_tags);
>   */
>  static void quirk_amd_harvest_no_ats(struct pci_dev *pdev)
>  {
> -	if ((pdev->device == 0x7312 && pdev->revision != 0x00) ||
> -	    (pdev->device == 0x7340 && pdev->revision != 0xc5) ||
> -	    (pdev->device == 0x7341 && pdev->revision != 0x00))
> -		return;
> -
>  	if (pdev->device == 0x15d8) {
>  		if (pdev->revision == 0xcf &&
>  		    pdev->subsystem_vendor == 0xea50 &&
> @@ -5367,10 +5362,19 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x98e4, quirk_amd_harvest_no_ats);
>  /* AMD Iceland dGPU */
>  DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6900, quirk_amd_harvest_no_ats);
>  /* AMD Navi10 dGPU */
> +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7310, quirk_amd_harvest_no_ats);
>  DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7312, quirk_amd_harvest_no_ats);
> +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7318, quirk_amd_harvest_no_ats);
> +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7319, quirk_amd_harvest_no_ats);
> +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x731a, quirk_amd_harvest_no_ats);
> +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x731b, quirk_amd_harvest_no_ats);
> +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x731e, quirk_amd_harvest_no_ats);
> +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x731f, quirk_amd_harvest_no_ats);
>  /* AMD Navi14 dGPU */
>  DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7340, quirk_amd_harvest_no_ats);
>  DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7341, quirk_amd_harvest_no_ats);
> +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7347, quirk_amd_harvest_no_ats);
> +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x734f, quirk_amd_harvest_no_ats);
>  /* AMD Raven platform iGPU */
>  DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x15d8, quirk_amd_harvest_no_ats);
>  #endif /* CONFIG_PCI_ATS */
> -- 
> 2.35.1
> 

^ permalink raw reply	[flat|nested] 4+ messages in thread

end of thread, other threads:[~2022-02-23 20:13 UTC | newest]

Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-02-22 16:08 [PATCH] PCI: Apply quirk_amd_harvest_no_ats to all navi10 and 14 asics Alex Deucher
2022-02-22 16:22 ` Christian König
2022-02-23  2:37 ` Chen, Guchun
2022-02-23 20:13 ` Bjorn Helgaas

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).