The VT-d spec requires (10.4.4 Global Command Register, TE field) that:
Hardware implementations supporting DMA draining must drain any in-flight DMA read/write requests queued within the Root-Complex before completing the translation enable command and reflecting the status of the command through the TES field in the Global Status register.
Unfortunately, some integrated graphic devices fail to do so after some kind of power state transition. As the result, the system might stuck in iommu_disable_translation(), waiting for the completion of TE transition.
This provides a quirk list for those devices and skips TE disabling if the qurik hits.
Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=208363 Tested-by: Koba Ko koba.ko@canonical.com Cc: Ashok Raj ashok.raj@intel.com Cc: stable@vger.kernel.org Signed-off-by: Lu Baolu baolu.lu@linux.intel.com --- drivers/iommu/intel/dmar.c | 1 + drivers/iommu/intel/iommu.c | 27 +++++++++++++++++++++++++++ include/linux/dmar.h | 1 + include/linux/intel-iommu.h | 2 ++ 4 files changed, 31 insertions(+)
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 683b812c5c47..16f47041f1bf 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -1102,6 +1102,7 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) }
drhd->iommu = iommu; + iommu->drhd = drhd;
return 0;
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 98390a6d8113..11418b14cc3f 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -356,6 +356,7 @@ static int intel_iommu_strict; static int intel_iommu_superpage = 1; static int iommu_identity_mapping; static int intel_no_bounce; +static int iommu_skip_te_disable;
#define IDENTMAP_GFX 2 #define IDENTMAP_AZALIA 4 @@ -1633,6 +1634,10 @@ static void iommu_disable_translation(struct intel_iommu *iommu) u32 sts; unsigned long flag;
+ if (iommu_skip_te_disable && iommu->drhd->gfx_dedicated && + (cap_read_drain(iommu->cap) || cap_write_drain(iommu->cap))) + return; + raw_spin_lock_irqsave(&iommu->register_lock, flag); iommu->gcmd &= ~DMA_GCMD_TE; writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG); @@ -4043,6 +4048,7 @@ static void __init init_no_remapping_devices(void)
/* This IOMMU has *only* gfx devices. Either bypass it or set the gfx_mapped flag, as appropriate */ + drhd->gfx_dedicated = 1; if (!dmar_map_gfx) { drhd->ignored = 1; for_each_active_dev_scope(drhd->devices, @@ -6160,6 +6166,27 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0044, quirk_calpella_no_shadow_g DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0062, quirk_calpella_no_shadow_gtt); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x006a, quirk_calpella_no_shadow_gtt);
+static void quirk_igfx_skip_te_disable(struct pci_dev *dev) +{ + unsigned short ver; + + if (!IS_GFX_DEVICE(dev)) + return; + + ver = (dev->device >> 8) & 0xff; + if (ver != 0x45 && ver != 0x46 && ver != 0x4c && + ver != 0x4e && ver != 0x8a && ver != 0x98 && + ver != 0x9a) + return; + + if (risky_device(dev)) + return; + + pci_info(dev, "Skip IOMMU disabling for graphics\n"); + iommu_skip_te_disable = 1; +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, quirk_igfx_skip_te_disable); + /* On Tylersburg chipsets, some BIOSes have been known to enable the ISOCH DMAR unit for the Azalia sound device, but not give it any TLB entries, which causes it to deadlock. Check for that. We do diff --git a/include/linux/dmar.h b/include/linux/dmar.h index d7bf029df737..65565820328a 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -48,6 +48,7 @@ struct dmar_drhd_unit { u16 segment; /* PCI domain */ u8 ignored:1; /* ignore drhd */ u8 include_all:1; + u8 gfx_dedicated:1; /* graphic dedicated */ struct intel_iommu *iommu; };
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index bf6009a344f5..329629e1e9de 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -600,6 +600,8 @@ struct intel_iommu { struct iommu_device iommu; /* IOMMU core code handle */ int node; u32 flags; /* Software defined flags */ + + struct dmar_drhd_unit *drhd; };
/* PCI domain-device relationship */
-----Original Message----- From: iommu iommu-bounces@lists.linux-foundation.org On Behalf Of Lu Baolu Sent: Monday, July 20, 2020 7:17 PM To: Joerg Roedel Cc: Ashok Raj; linux-kernel@vger.kernel.org; stable@vger.kernel.org; Koba Ko; iommu@lists.linux-foundation.org Subject: [PATCH 1/1] iommu/vt-d: Skip TE disabling on quirky gfx dedicated iommu
The VT-d spec requires (10.4.4 Global Command Register, TE field) that:
Hardware implementations supporting DMA draining must drain any in-flight DMA read/write requests queued within the Root-Complex before completing the translation enable command and reflecting the status of the command through the TES field in the Global Status register.
Unfortunately, some integrated graphic devices fail to do so after some kind of power state transition. As the result, the system might stuck in iommu_disable_translation(), waiting for the completion of TE transition.
This provides a quirk list for those devices and skips TE disabling if the qurik hits.
That one is for TGL.
I think you also want to add this one for ICL: Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=206571
Tested-by: Koba Ko koba.ko@canonical.com Cc: Ashok Raj ashok.raj@intel.com Cc: stable@vger.kernel.org Signed-off-by: Lu Baolu baolu.lu@linux.intel.com
drivers/iommu/intel/dmar.c | 1 + drivers/iommu/intel/iommu.c | 27 +++++++++++++++++++++++++++ include/linux/dmar.h | 1 + include/linux/intel-iommu.h | 2 ++ 4 files changed, 31 insertions(+)
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 683b812c5c47..16f47041f1bf 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -1102,6 +1102,7 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) }
drhd->iommu = iommu;
iommu->drhd = drhd;
return 0;
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 98390a6d8113..11418b14cc3f 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -356,6 +356,7 @@ static int intel_iommu_strict; static int intel_iommu_superpage = 1; static int iommu_identity_mapping; static int intel_no_bounce; +static int iommu_skip_te_disable;
#define IDENTMAP_GFX 2 #define IDENTMAP_AZALIA 4 @@ -1633,6 +1634,10 @@ static void iommu_disable_translation(struct intel_iommu *iommu) u32 sts; unsigned long flag;
- if (iommu_skip_te_disable && iommu->drhd->gfx_dedicated &&
(cap_read_drain(iommu->cap) || cap_write_drain(iommu->cap)))
return;
- raw_spin_lock_irqsave(&iommu->register_lock, flag); iommu->gcmd &= ~DMA_GCMD_TE; writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
@@ -4043,6 +4048,7 @@ static void __init init_no_remapping_devices(void)
/* This IOMMU has *only* gfx devices. Either bypass it or set the gfx_mapped flag, as appropriate */
if (!dmar_map_gfx) { drhd->ignored = 1; for_each_active_dev_scope(drhd->devices,drhd->gfx_dedicated = 1;
@@ -6160,6 +6166,27 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0044, quirk_calpella_no_shadow_g DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0062, quirk_calpella_no_shadow_gtt); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x006a, quirk_calpella_no_shadow_gtt);
+static void quirk_igfx_skip_te_disable(struct pci_dev *dev) +{
- unsigned short ver;
- if (!IS_GFX_DEVICE(dev))
return;
- ver = (dev->device >> 8) & 0xff;
- if (ver != 0x45 && ver != 0x46 && ver != 0x4c &&
ver != 0x4e && ver != 0x8a && ver != 0x98 &&
ver != 0x9a)
return;
- if (risky_device(dev))
return;
- pci_info(dev, "Skip IOMMU disabling for graphics\n");
- iommu_skip_te_disable = 1;
+} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, quirk_igfx_skip_te_disable);
/* On Tylersburg chipsets, some BIOSes have been known to enable the ISOCH DMAR unit for the Azalia sound device, but not give it any TLB entries, which causes it to deadlock. Check for that. We do diff --git a/include/linux/dmar.h b/include/linux/dmar.h index d7bf029df737..65565820328a 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -48,6 +48,7 @@ struct dmar_drhd_unit { u16 segment; /* PCI domain */ u8 ignored:1; /* ignore drhd */ u8 include_all:1;
- u8 gfx_dedicated:1; /* graphic dedicated */ struct intel_iommu *iommu;
};
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index bf6009a344f5..329629e1e9de 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -600,6 +600,8 @@ struct intel_iommu { struct iommu_device iommu; /* IOMMU core code handle */ int node; u32 flags; /* Software defined flags */
- struct dmar_drhd_unit *drhd;
};
/* PCI domain-device relationship */
2.17.1
iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
Hi Limonciello,
On 7/21/20 10:44 PM, Limonciello, Mario wrote:
-----Original Message----- From: iommuiommu-bounces@lists.linux-foundation.org On Behalf Of Lu Baolu Sent: Monday, July 20, 2020 7:17 PM To: Joerg Roedel Cc: Ashok Raj;linux-kernel@vger.kernel.org;stable@vger.kernel.org; Koba Ko;iommu@lists.linux-foundation.org Subject: [PATCH 1/1] iommu/vt-d: Skip TE disabling on quirky gfx dedicated iommu
The VT-d spec requires (10.4.4 Global Command Register, TE field) that:
Hardware implementations supporting DMA draining must drain any in-flight DMA read/write requests queued within the Root-Complex before completing the translation enable command and reflecting the status of the command through the TES field in the Global Status register.
Unfortunately, some integrated graphic devices fail to do so after some kind of power state transition. As the result, the system might stuck in iommu_disable_translation(), waiting for the completion of TE transition.
This provides a quirk list for those devices and skips TE disabling if the qurik hits.
That one is for TGL.
I think you also want to add this one for ICL: Fixes:https://bugzilla.kernel.org/show_bug.cgi?id=206571
Do you mean someone have tested that this patch also fixes the problem described in 206571?
Best regards, baolu
-----Original Message----- From: Lu Baolu baolu.lu@linux.intel.com Sent: Tuesday, July 21, 2020 6:07 PM To: Limonciello, Mario; Joerg Roedel Cc: baolu.lu@linux.intel.com; Ashok Raj; linux-kernel@vger.kernel.org; stable@vger.kernel.org; Koba Ko; iommu@lists.linux-foundation.org Subject: Re: [PATCH 1/1] iommu/vt-d: Skip TE disabling on quirky gfx dedicated iommu
[EXTERNAL EMAIL]
Hi Limonciello,
On 7/21/20 10:44 PM, Limonciello, Mario wrote:
-----Original Message----- From: iommuiommu-bounces@lists.linux-foundation.org On Behalf Of Lu Baolu Sent: Monday, July 20, 2020 7:17 PM To: Joerg Roedel Cc: Ashok Raj;linux-kernel@vger.kernel.org;stable@vger.kernel.org; Koba Ko;iommu@lists.linux-foundation.org Subject: [PATCH 1/1] iommu/vt-d: Skip TE disabling on quirky gfx dedicated iommu
The VT-d spec requires (10.4.4 Global Command Register, TE field) that:
Hardware implementations supporting DMA draining must drain any in-flight DMA read/write requests queued within the Root-Complex before completing the translation enable command and reflecting the status of the command through the TES field in the Global Status register.
Unfortunately, some integrated graphic devices fail to do so after some kind of power state transition. As the result, the system might stuck in iommu_disable_translation(), waiting for the completion of TE transition.
This provides a quirk list for those devices and skips TE disabling if the qurik hits.
That one is for TGL.
I think you also want to add this one for ICL: Fixes:https://bugzilla.kernel.org/show_bug.cgi?id=206571
Do you mean someone have tested that this patch also fixes the problem described in 206571?
Yes, confusingly https://bugzilla.kernel.org/show_bug.cgi?id=208363#c31 actually is the XPS 9300 ICL system and issue.
I also have a private confirmation from another person that it resolves it for them on another ICL platform.
Christian, maybe you can add a tested by clause for the ICL testing.
On 7/22/20 7:45 AM, Limonciello, Mario wrote:
-----Original Message----- From: Lu Baolu baolu.lu@linux.intel.com Sent: Tuesday, July 21, 2020 6:07 PM To: Limonciello, Mario; Joerg Roedel Cc: baolu.lu@linux.intel.com; Ashok Raj; linux-kernel@vger.kernel.org; stable@vger.kernel.org; Koba Ko; iommu@lists.linux-foundation.org Subject: Re: [PATCH 1/1] iommu/vt-d: Skip TE disabling on quirky gfx dedicated iommu
[EXTERNAL EMAIL]
Hi Limonciello,
On 7/21/20 10:44 PM, Limonciello, Mario wrote:
-----Original Message----- From: iommuiommu-bounces@lists.linux-foundation.org On Behalf Of Lu Baolu Sent: Monday, July 20, 2020 7:17 PM To: Joerg Roedel Cc: Ashok Raj;linux-kernel@vger.kernel.org;stable@vger.kernel.org; Koba Ko;iommu@lists.linux-foundation.org Subject: [PATCH 1/1] iommu/vt-d: Skip TE disabling on quirky gfx dedicated iommu
The VT-d spec requires (10.4.4 Global Command Register, TE field) that:
Hardware implementations supporting DMA draining must drain any in-flight DMA read/write requests queued within the Root-Complex before completing the translation enable command and reflecting the status of the command through the TES field in the Global Status register.
Unfortunately, some integrated graphic devices fail to do so after some kind of power state transition. As the result, the system might stuck in iommu_disable_translation(), waiting for the completion of TE transition.
This provides a quirk list for those devices and skips TE disabling if the qurik hits.
That one is for TGL.
I think you also want to add this one for ICL: Fixes:https://bugzilla.kernel.org/show_bug.cgi?id=206571
Do you mean someone have tested that this patch also fixes the problem described in 206571?
Yes, confusingly https://bugzilla.kernel.org/show_bug.cgi?id=208363#c31 actually is the XPS 9300 ICL system and issue.
I also have a private confirmation from another person that it resolves it for them on another ICL platform.
Okay! Thank you very much! I just posted v2 with this tag added.
Best regards, baolu
Hi
[This is an automated email]
This commit has been processed because it contains a "Fixes:" tag fixing commit: .
The bot has tested the following trees: v5.7.9, v5.4.52, v4.19.133, v4.14.188, v4.9.230, v4.4.230.
v5.7.9: Failed to apply! Possible dependencies: Unable to calculate
v5.4.52: Failed to apply! Possible dependencies: Unable to calculate
v4.19.133: Failed to apply! Possible dependencies: e5e04d051979d ("iommu/vt-d: Check whether device requires bounce buffer")
v4.14.188: Failed to apply! Possible dependencies: 85319dcc8955f ("iommu/vt-d: Add for_each_device_domain() helper") 9ddbfb42138d8 ("iommu/vt-d: Move device_domain_info to header") e5e04d051979d ("iommu/vt-d: Check whether device requires bounce buffer")
v4.9.230: Failed to apply! Possible dependencies: 161b28aae1651 ("iommu/vt-d: Make sure IOMMUs are off when intel_iommu=off") 61012985eb132 ("iommu/vt-d: Use lo_hi_readq() / lo_hi_writeq()") 85319dcc8955f ("iommu/vt-d: Add for_each_device_domain() helper") 9ddbfb42138d8 ("iommu/vt-d: Move device_domain_info to header") a7fdb6e648fb1 ("iommu/vt-d: Fix crash when accessing VT-d sysfs entries") b0119e870837d ("iommu: Introduce new 'struct iommu_device'") b316d02a13c3a ("iommu/vt-d: Unwrap __get_valid_domain_for_dev()") bfd20f1cc8501 ("x86, iommu/vt-d: Add an option to disable Intel IOMMU force on") e5e04d051979d ("iommu/vt-d: Check whether device requires bounce buffer")
v4.4.230: Failed to apply! Possible dependencies: 0824c5920b16f ("iommu/vt-d: avoid dev iotlb logic for domains with no dev iotlbs") 161b28aae1651 ("iommu/vt-d: Make sure IOMMUs are off when intel_iommu=off") 314f1dc140844 ("iommu/vt-d: refactoring of deferred flush entries") 53c92d793395f ("iommu: of: enforce const-ness of struct iommu_ops") 57f98d2f61e19 ("iommu: Introduce iommu_fwspec") 592033790e827 ("iommu/vt-d: Check the return value of iommu_device_create()") 85319dcc8955f ("iommu/vt-d: Add for_each_device_domain() helper") 8d54d6c8b8f3e ("iommu/amd: Implement apply_dm_region call-back") 9ddbfb42138d8 ("iommu/vt-d: Move device_domain_info to header") a7fdb6e648fb1 ("iommu/vt-d: Fix crash when accessing VT-d sysfs entries") aa4732406e129 ("iommu/vt-d: per-cpu deferred invalidation queues") b0119e870837d ("iommu: Introduce new 'struct iommu_device'") b996444cf35e7 ("iommu/of: Handle iommu-map property for PCI") bc8474549e94e ("iommu/vt-d: Fix up error handling in alloc_iommu") bfd20f1cc8501 ("x86, iommu/vt-d: Add an option to disable Intel IOMMU force on") e5e04d051979d ("iommu/vt-d: Check whether device requires bounce buffer")
NOTE: The patch will not be queued to stable trees until it is upstream.
How should we proceed with this patch?
linux-stable-mirror@lists.linaro.org