[PATCH v4 0/2] VMD MSI Remapping Bypass
The Intel Volume Management Device acts similar to a PCI-to-PCI bridge in that it changes downstream devices' requester-ids to its own. As VMD supports PCIe devices, it has its own MSI-X table and transmits child device MSI-X by remapping child device MSI-X and handling like a demultiplexer. Some newer VMD devices (Icelake Server) have an option to bypass the VMD MSI-X remapping table. This allows for better performance scaling as the child device MSI-X won't be limited by VMD's MSI-X count and IRQ handler. V3->V4: Integrated wording suggestions; no functional changes V2->V3: Trivial comment fixes Added acks V1->V2: Updated for 5.12-next Moved IRQ allocation and remapping enable/disable to a more logical location V1 patches 1-4 were already merged V1, 5/6: https://patchwork.kernel.org/project/linux-pci/patch/20200728194945.14126-6-jonathan.derr...@intel.com/ V1, 6/6: https://patchwork.kernel.org/project/linux-pci/patch/20200728194945.14126-7-jonathan.derr...@intel.com/ Jon Derrick (2): iommu/vt-d: Use Real PCI DMA device for IRTE PCI: vmd: Disable MSI-X remapping when possible drivers/iommu/intel/irq_remapping.c | 3 +- drivers/pci/controller/vmd.c| 63 +++-- 2 files changed, 53 insertions(+), 13 deletions(-) -- 2.27.0 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v4 2/2] PCI: vmd: Disable MSI-X remapping when possible
VMD will retransmit child device MSI-X using its own MSI-X table and
requester-id. This limits the number of MSI-X available to the whole
child device domain to the number of VMD MSI-X interrupts.
Some VMD devices have a mode where this remapping can be disabled,
allowing child device interrupts to bypass processing with the VMD MSI-X
domain interrupt handler and going straight the child device interrupt
handler, allowing for better performance and scaling. The requester-id
still gets changed to the VMD endpoint's requester-id, and the interrupt
remapping handlers have been updated to properly set IRTE for child
device interrupts to the VMD endpoint's context.
Some VMD platforms have existing production BIOS which rely on MSI-X
remapping and won't explicitly program the MSI-X remapping bit. This
re-enables MSI-X remapping on unload.
Acked-by: Joerg Roedel
Reviewed-by: Krzysztof Wilczyński
Signed-off-by: Jon Derrick
---
drivers/pci/controller/vmd.c | 63 +---
1 file changed, 51 insertions(+), 12 deletions(-)
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 5e80f28f0119..e3fcdfec58b3 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -28,6 +28,7 @@
#define BUS_RESTRICT_CAP(vmcap)(vmcap & 0x1)
#define PCI_REG_VMCONFIG 0x44
#define BUS_RESTRICT_CFG(vmcfg)((vmcfg >> 8) & 0x3)
+#define VMCONFIG_MSI_REMAP 0x2
#define PCI_REG_VMLOCK 0x70
#define MB2_SHADOW_EN(vmlock) (vmlock & 0x2)
@@ -59,6 +60,13 @@ enum vmd_features {
* be used for MSI remapping
*/
VMD_FEAT_OFFSET_FIRST_VECTOR= (1 << 3),
+
+ /*
+* Device can bypass remapping MSI-X transactions into its MSI-X table,
+* avoiding the requirement of a VMD MSI domain for child device
+* interrupt handling.
+*/
+ VMD_FEAT_CAN_BYPASS_MSI_REMAP = (1 << 4),
};
/*
@@ -306,6 +314,16 @@ static struct msi_domain_info vmd_msi_domain_info = {
.chip = _msi_controller,
};
+static void vmd_set_msi_remapping(struct vmd_dev *vmd, bool enable)
+{
+ u16 reg;
+
+ pci_read_config_word(vmd->dev, PCI_REG_VMCONFIG, );
+ reg = enable ? (reg & ~VMCONFIG_MSI_REMAP) :
+ (reg | VMCONFIG_MSI_REMAP);
+ pci_write_config_word(vmd->dev, PCI_REG_VMCONFIG, reg);
+}
+
static int vmd_create_irq_domain(struct vmd_dev *vmd)
{
struct fwnode_handle *fn;
@@ -325,6 +343,13 @@ static int vmd_create_irq_domain(struct vmd_dev *vmd)
static void vmd_remove_irq_domain(struct vmd_dev *vmd)
{
+ /*
+* Some production BIOS won't enable remapping between soft reboots.
+* Ensure remapping is restored before unloading the driver.
+*/
+ if (!vmd->msix_count)
+ vmd_set_msi_remapping(vmd, true);
+
if (vmd->irq_domain) {
struct fwnode_handle *fn = vmd->irq_domain->fwnode;
@@ -679,15 +704,32 @@ static int vmd_enable_domain(struct vmd_dev *vmd,
unsigned long features)
sd->node = pcibus_to_node(vmd->dev->bus);
- ret = vmd_create_irq_domain(vmd);
- if (ret)
- return ret;
-
/*
-* Override the irq domain bus token so the domain can be distinguished
-* from a regular PCI/MSI domain.
+* Currently MSI remapping must be enabled in guest passthrough mode
+* due to some missing interrupt remapping plumbing. This is probably
+* acceptable because the guest is usually CPU-limited and MSI
+* remapping doesn't become a performance bottleneck.
*/
- irq_domain_update_bus_token(vmd->irq_domain, DOMAIN_BUS_VMD_MSI);
+ if (!(features & VMD_FEAT_CAN_BYPASS_MSI_REMAP) ||
+ offset[0] || offset[1]) {
+ ret = vmd_alloc_irqs(vmd);
+ if (ret)
+ return ret;
+
+ vmd_set_msi_remapping(vmd, true);
+
+ ret = vmd_create_irq_domain(vmd);
+ if (ret)
+ return ret;
+
+ /*
+* Override the IRQ domain bus token so the domain can be
+* distinguished from a regular PCI/MSI domain.
+*/
+ irq_domain_update_bus_token(vmd->irq_domain,
DOMAIN_BUS_VMD_MSI);
+ } else {
+ vmd_set_msi_remapping(vmd, false);
+ }
pci_add_resource(, >resources[0]);
pci_add_resource_offset(, >resources[1], offset[0]);
@@ -753,10 +795,6 @@ static int vmd_probe(struct pci_dev *dev, const struct
pci_device_id *id)
if (features & VMD_FEAT_OFFSET_FIRST_VECTOR)
vmd->first_vec = 1;
- err = vmd_alloc_irqs(vmd);
- if (err)
- return err;
-
spin_lock_init(>cfg_lock);
pci_set_drvdata(dev, vmd);
err =
[PATCH v4 1/2] iommu/vt-d: Use Real PCI DMA device for IRTE
VMD retransmits child device MSI-X with the VMD endpoint's requester-id. In order to support direct interrupt remapping of VMD child devices, ensure that the IRTE is programmed with the VMD endpoint's requester-id using pci_real_dma_dev(). Acked-by: Lu Baolu Acked-by: Joerg Roedel Signed-off-by: Jon Derrick --- drivers/iommu/intel/irq_remapping.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index 685200a5cff0..1939e070eec8 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers/iommu/intel/irq_remapping.c @@ -1276,7 +1276,8 @@ static void intel_irq_remapping_prepare_irte(struct intel_ir_data *data, break; case X86_IRQ_ALLOC_TYPE_PCI_MSI: case X86_IRQ_ALLOC_TYPE_PCI_MSIX: - set_msi_sid(irte, msi_desc_to_pci_dev(info->desc)); + set_msi_sid(irte, + pci_real_dma_dev(msi_desc_to_pci_dev(info->desc))); break; default: BUG_ON(1); -- 2.27.0 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v3 2/2] PCI: vmd: Disable MSI-X remapping when possible
VMD will retransmit child device MSI-X using its own MSI-X table and
requester-id. This limits the number of MSI-X available to the whole
child device domain to the number of VMD MSI-X interrupts.
Some VMD devices have a mode where this remapping can be disabled,
allowing child device interrupts to bypass processing with the VMD MSI-X
domain interrupt handler and going straight the child device interrupt
handler, allowing for better performance and scaling. The requester-id
still gets changed to the VMD endpoint's requester-id, and the interrupt
remapping handlers have been updated to properly set IRTE for child
device interrupts to the VMD endpoint's context.
Some VMD platforms have existing production BIOS which rely on MSI-X
remapping and won't explicitly program the MSI-X remapping bit. This
re-enables MSI-X remapping on unload.
Acked-by: Joerg Roedel
Signed-off-by: Jon Derrick
---
drivers/pci/controller/vmd.c | 61 +---
1 file changed, 49 insertions(+), 12 deletions(-)
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 5e80f28f0119..2a585d1b3349 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -28,6 +28,7 @@
#define BUS_RESTRICT_CAP(vmcap)(vmcap & 0x1)
#define PCI_REG_VMCONFIG 0x44
#define BUS_RESTRICT_CFG(vmcfg)((vmcfg >> 8) & 0x3)
+#define VMCFG_MSI_RMP_DIS 0x2
#define PCI_REG_VMLOCK 0x70
#define MB2_SHADOW_EN(vmlock) (vmlock & 0x2)
@@ -59,6 +60,13 @@ enum vmd_features {
* be used for MSI remapping
*/
VMD_FEAT_OFFSET_FIRST_VECTOR= (1 << 3),
+
+ /*
+* Device can bypass remapping MSI-X transactions into its MSI-X table,
+* avoiding the requirement of a VMD MSI domain for child device
+* interrupt handling.
+*/
+ VMD_FEAT_BYPASS_MSI_REMAP = (1 << 4),
};
/*
@@ -306,6 +314,15 @@ static struct msi_domain_info vmd_msi_domain_info = {
.chip = _msi_controller,
};
+static void vmd_enable_msi_remapping(struct vmd_dev *vmd, bool enable)
+{
+ u16 reg;
+
+ pci_read_config_word(vmd->dev, PCI_REG_VMCONFIG, );
+ reg = enable ? (reg & ~VMCFG_MSI_RMP_DIS) : (reg | VMCFG_MSI_RMP_DIS);
+ pci_write_config_word(vmd->dev, PCI_REG_VMCONFIG, reg);
+}
+
static int vmd_create_irq_domain(struct vmd_dev *vmd)
{
struct fwnode_handle *fn;
@@ -325,6 +342,13 @@ static int vmd_create_irq_domain(struct vmd_dev *vmd)
static void vmd_remove_irq_domain(struct vmd_dev *vmd)
{
+ /*
+* Some production BIOS won't enable remapping between soft reboots.
+* Ensure remapping is restored before unloading the driver.
+*/
+ if (!vmd->msix_count)
+ vmd_enable_msi_remapping(vmd, true);
+
if (vmd->irq_domain) {
struct fwnode_handle *fn = vmd->irq_domain->fwnode;
@@ -679,15 +703,31 @@ static int vmd_enable_domain(struct vmd_dev *vmd,
unsigned long features)
sd->node = pcibus_to_node(vmd->dev->bus);
- ret = vmd_create_irq_domain(vmd);
- if (ret)
- return ret;
-
/*
-* Override the irq domain bus token so the domain can be distinguished
-* from a regular PCI/MSI domain.
+* Currently MSI remapping must be enabled in guest passthrough mode
+* due to some missing interrupt remapping plumbing. This is probably
+* acceptable because the guest is usually CPU-limited and MSI
+* remapping doesn't become a performance bottleneck.
*/
- irq_domain_update_bus_token(vmd->irq_domain, DOMAIN_BUS_VMD_MSI);
+ if (!(features & VMD_FEAT_BYPASS_MSI_REMAP) || offset[0] || offset[1]) {
+ ret = vmd_alloc_irqs(vmd);
+ if (ret)
+ return ret;
+
+ vmd_enable_msi_remapping(vmd, true);
+
+ ret = vmd_create_irq_domain(vmd);
+ if (ret)
+ return ret;
+
+ /*
+* Override the irq domain bus token so the domain can be
+* distinguished from a regular PCI/MSI domain.
+*/
+ irq_domain_update_bus_token(vmd->irq_domain,
DOMAIN_BUS_VMD_MSI);
+ } else {
+ vmd_enable_msi_remapping(vmd, false);
+ }
pci_add_resource(, >resources[0]);
pci_add_resource_offset(, >resources[1], offset[0]);
@@ -753,10 +793,6 @@ static int vmd_probe(struct pci_dev *dev, const struct
pci_device_id *id)
if (features & VMD_FEAT_OFFSET_FIRST_VECTOR)
vmd->first_vec = 1;
- err = vmd_alloc_irqs(vmd);
- if (err)
- return err;
-
spin_lock_init(>cfg_lock);
pci_set_drvdata(dev, vmd);
err = vmd_enable_domain(vmd, features);
@@ -825,7
[PATCH v3 0/2] VMD MSI Remapping Bypass
The Intel Volume Management Device acts similar to a PCI-to-PCI bridge in that it changes downstream devices' requester-ids to its own. As VMD supports PCIe devices, it has its own MSI-X table and transmits child device MSI-X by remapping child device MSI-X and handling like a demultiplexer. Some newer VMD devices (Icelake Server) have an option to bypass the VMD MSI-X remapping table. This allows for better performance scaling as the child device MSI-X won't be limited by VMD's MSI-X count and IRQ handler. V2->V3: Trivial comment fixes Added acks V1->V2: Updated for 5.12-next Moved IRQ allocation and remapping enable/disable to a more logical location V1 patches 1-4 were already merged V1, 5/6: https://patchwork.kernel.org/project/linux-pci/patch/20200728194945.14126-6-jonathan.derr...@intel.com/ V1, 6/6: https://patchwork.kernel.org/project/linux-pci/patch/20200728194945.14126-7-jonathan.derr...@intel.com/ Jon Derrick (2): iommu/vt-d: Use Real PCI DMA device for IRTE PCI: vmd: Disable MSI-X remapping when possible drivers/iommu/intel/irq_remapping.c | 3 +- drivers/pci/controller/vmd.c| 61 +++-- 2 files changed, 51 insertions(+), 13 deletions(-) -- 2.27.0 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v3 1/2] iommu/vt-d: Use Real PCI DMA device for IRTE
VMD retransmits child device MSI-X with the VMD endpoint's requester-id. In order to support direct interrupt remapping of VMD child devices, ensure that the IRTE is programmed with the VMD endpoint's requester-id using pci_real_dma_dev(). Acked-by: Lu Baolu Acked-by: Joerg Roedel Signed-off-by: Jon Derrick --- drivers/iommu/intel/irq_remapping.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index 685200a5cff0..1939e070eec8 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers/iommu/intel/irq_remapping.c @@ -1276,7 +1276,8 @@ static void intel_irq_remapping_prepare_irte(struct intel_ir_data *data, break; case X86_IRQ_ALLOC_TYPE_PCI_MSI: case X86_IRQ_ALLOC_TYPE_PCI_MSIX: - set_msi_sid(irte, msi_desc_to_pci_dev(info->desc)); + set_msi_sid(irte, + pci_real_dma_dev(msi_desc_to_pci_dev(info->desc))); break; default: BUG_ON(1); -- 2.27.0 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v2 1/2] iommu/vt-d: Use Real PCI DMA device for IRTE
VMD retransmits child device MSI/X with the VMD endpoint's requester-id. In order to support direct interrupt remapping of VMD child devices, ensure that the IRTE is programmed with the VMD endpoint's requester-id using pci_real_dma_dev(). Signed-off-by: Jon Derrick --- drivers/iommu/intel/irq_remapping.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index 685200a5cff0..1939e070eec8 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers/iommu/intel/irq_remapping.c @@ -1276,7 +1276,8 @@ static void intel_irq_remapping_prepare_irte(struct intel_ir_data *data, break; case X86_IRQ_ALLOC_TYPE_PCI_MSI: case X86_IRQ_ALLOC_TYPE_PCI_MSIX: - set_msi_sid(irte, msi_desc_to_pci_dev(info->desc)); + set_msi_sid(irte, + pci_real_dma_dev(msi_desc_to_pci_dev(info->desc))); break; default: BUG_ON(1); -- 2.27.0 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v2 2/2] PCI: vmd: Disable MSI/X remapping when possible
VMD will retransmit child device MSI/X using its own MSI/X table and
requester-id. This limits the number of MSI/X available to the whole
child device domain to the number of VMD MSI/X interrupts.
Some VMD devices have a mode where this remapping can be disabled,
allowing child device interrupts to bypass processing with the VMD MSI/X
domain interrupt handler and going straight the child device interrupt
handler, allowing for better performance and scaling. The requester-id
still gets changed to the VMD endpoint's requester-id, and the interrupt
remapping handlers have been updated to properly set IRTE for child
device interrupts to the VMD endpoint's context.
Some VMD platforms have existing production BIOS which rely on MSI/X
remapping and won't explicitly program the MSI/X remapping bit. This
re-enables MSI/X remapping on unload.
Signed-off-by: Jon Derrick
---
drivers/pci/controller/vmd.c | 60
1 file changed, 48 insertions(+), 12 deletions(-)
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 5e80f28f0119..a319ce49645b 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -59,6 +59,13 @@ enum vmd_features {
* be used for MSI remapping
*/
VMD_FEAT_OFFSET_FIRST_VECTOR= (1 << 3),
+
+ /*
+* Device can bypass remapping MSI/X transactions into its MSI/X table,
+* avoding the requirement of a VMD MSI domain for child device
+* interrupt handling
+*/
+ VMD_FEAT_BYPASS_MSI_REMAP = (1 << 4),
};
/*
@@ -306,6 +313,15 @@ static struct msi_domain_info vmd_msi_domain_info = {
.chip = _msi_controller,
};
+static void vmd_enable_msi_remapping(struct vmd_dev *vmd, bool enable)
+{
+ u16 reg;
+
+ pci_read_config_word(vmd->dev, PCI_REG_VMCONFIG, );
+ reg = enable ? (reg & ~0x2) : (reg | 0x2);
+ pci_write_config_word(vmd->dev, PCI_REG_VMCONFIG, reg);
+}
+
static int vmd_create_irq_domain(struct vmd_dev *vmd)
{
struct fwnode_handle *fn;
@@ -325,6 +341,13 @@ static int vmd_create_irq_domain(struct vmd_dev *vmd)
static void vmd_remove_irq_domain(struct vmd_dev *vmd)
{
+ /*
+* Some production BIOS won't enable remapping between soft reboots.
+* Ensure remapping is restored before unloading the driver.
+*/
+ if (!vmd->msix_count)
+ vmd_enable_msi_remapping(vmd, true);
+
if (vmd->irq_domain) {
struct fwnode_handle *fn = vmd->irq_domain->fwnode;
@@ -679,15 +702,31 @@ static int vmd_enable_domain(struct vmd_dev *vmd,
unsigned long features)
sd->node = pcibus_to_node(vmd->dev->bus);
- ret = vmd_create_irq_domain(vmd);
- if (ret)
- return ret;
-
/*
-* Override the irq domain bus token so the domain can be distinguished
-* from a regular PCI/MSI domain.
+* Currently MSI remapping must be enabled in guest passthrough mode
+* due to some missing interrupt remapping plumbing. This is probably
+* acceptable because the guest is usually CPU-limited and MSI
+* remapping doesn't become a performance bottleneck.
*/
- irq_domain_update_bus_token(vmd->irq_domain, DOMAIN_BUS_VMD_MSI);
+ if (!(features & VMD_FEAT_BYPASS_MSI_REMAP) || offset[0] || offset[1]) {
+ ret = vmd_alloc_irqs(vmd);
+ if (ret)
+ return ret;
+
+ vmd_enable_msi_remapping(vmd, true);
+
+ ret = vmd_create_irq_domain(vmd);
+ if (ret)
+ return ret;
+
+ /*
+* Override the irq domain bus token so the domain can be
+* distinguished from a regular PCI/MSI domain.
+*/
+ irq_domain_update_bus_token(vmd->irq_domain,
DOMAIN_BUS_VMD_MSI);
+ } else {
+ vmd_enable_msi_remapping(vmd, false);
+ }
pci_add_resource(, >resources[0]);
pci_add_resource_offset(, >resources[1], offset[0]);
@@ -753,10 +792,6 @@ static int vmd_probe(struct pci_dev *dev, const struct
pci_device_id *id)
if (features & VMD_FEAT_OFFSET_FIRST_VECTOR)
vmd->first_vec = 1;
- err = vmd_alloc_irqs(vmd);
- if (err)
- return err;
-
spin_lock_init(>cfg_lock);
pci_set_drvdata(dev, vmd);
err = vmd_enable_domain(vmd, features);
@@ -825,7 +860,8 @@ static const struct pci_device_id vmd_ids[] = {
.driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP,},
{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_28C0),
.driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW |
- VMD_FEAT_HAS_BUS_RESTRICTIONS,},
+ VMD_FEAT_HAS_BUS_RES
[PATCH v2 0/2] VMD MSI Remapping Bypass
The Intel Volume Management Device acts similar to a PCI-to-PCI bridge in that it changes downstream devices' requester-ids to its own. As VMD supports PCIe devices, it has its own MSI/X table and transmits child device MSI/X by remapping child device MSI/X and handling like a demultiplexer. Some newer VMD devices (Icelake Server) have an option to bypass the VMD MSI/X remapping table. This allows for better performance scaling as the child device MSI/X won't be limited by VMD's MSI/X count and IRQ handler. V1->V2: Updated for 5.12-next Moved IRQ allocation and remapping enable/disable to a more logical location V1 patches 1-4 were already merged V1, 5/6: https://patchwork.kernel.org/project/linux-pci/patch/20200728194945.14126-6-jonathan.derr...@intel.com/ V1, 6/6: https://patchwork.kernel.org/project/linux-pci/patch/20200728194945.14126-7-jonathan.derr...@intel.com/ Jon Derrick (2): iommu/vt-d: Use Real PCI DMA device for IRTE PCI: vmd: Disable MSI/X remapping when possible drivers/iommu/intel/irq_remapping.c | 3 +- drivers/pci/controller/vmd.c| 60 +++-- 2 files changed, 50 insertions(+), 13 deletions(-) -- 2.27.0 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v1 0/3] iommu/vt-d: real DMA sub-device info allocation
This set adds the support for real DMA sub-devices to have device_domain_info,
leading to the correct domain type being used.
This applies on Joerg's origin/next. This also applies against v5.6.12
and v5.7-rc7 with some API modifications, making it a stable candidate
that fixes the issue reported in [1].
For v5.6.12 and v5.7-rc7, identity_mapping() would return 0 for real DMA
sub-devices due to not having valid device_domain_info, leading to
__intel_map_single() paths. This is a problem if the real DMA device
started in IDENTITY, leading to a NULL Pointer Dereference:
__intel_map_single()
domain = find_domain(dev);
dev = _real_dma_dev(to_pci_dev(dev))->dev;
info = dev->archdata.iommu;
return info->domain;
iommu = domain_get_iommu(domain)
if (WARN_ON(domain->domain.type != IOMMU_DOMAIN_DMA))
return NULL;
cap_zlr(iommu->cap) <-- NULL Pointer Deref
This issue was also fixed by 6fc7020cf298 ("iommu/vt-d: Apply per-device
dma_ops") due to removing identity_mapping() paths.
[1] https://bugzilla.kernel.org/show_bug.cgi?id=207575
Jon Derrick (3):
iommu/vt-d: Only clear real DMA device's context entries
iommu/vt-d: Allocate domain info for real DMA sub-devices
iommu/vt-d: Remove real DMA lookup in find_domain
drivers/iommu/intel-iommu.c | 31 +++
include/linux/intel-iommu.h | 1 +
2 files changed, 24 insertions(+), 8 deletions(-)
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v1 3/3] iommu/vt-d: Remove real DMA lookup in find_domain
By removing the real DMA indirection in find_domain(), we can allow
sub-devices of a real DMA device to have their own valid
device_domain_info. The dmar lookup and context entry removal paths have
been fixed to account for sub-devices.
Fixes: 2b0140c69637 ("iommu/vt-d: Use pci_real_dma_dev() for mapping")
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=207575
Signed-off-by: Jon Derrick
---
drivers/iommu/intel-iommu.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 6d39b9b..5767882 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -2436,9 +2436,6 @@ struct dmar_domain *find_domain(struct device *dev)
if (unlikely(attach_deferred(dev) || iommu_dummy(dev)))
return NULL;
- if (dev_is_pci(dev))
- dev = _real_dma_dev(to_pci_dev(dev))->dev;
-
/* No lock here, assumes no domain exit in normal case */
info = get_domain_info(dev);
if (likely(info))
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v1 2/3] iommu/vt-d: Allocate domain info for real DMA sub-devices
Sub-devices of a real DMA device might exist on a separate segment than
the real DMA device and its IOMMU. These devices should still have a
valid device_domain_info, but the current dma alias model won't
allocate info for the subdevice.
This patch adds a segment member to struct device_domain_info and uses
the sub-device's BDF so that these sub-devices won't alias to other
devices.
Signed-off-by: Jon Derrick
---
drivers/iommu/intel-iommu.c | 19 +++
include/linux/intel-iommu.h | 1 +
2 files changed, 16 insertions(+), 4 deletions(-)
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 1ff45b2..6d39b9b 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -2463,7 +2463,7 @@ static void do_deferred_attach(struct device *dev)
struct device_domain_info *info;
list_for_each_entry(info, _domain_list, global)
- if (info->iommu->segment == segment && info->bus == bus &&
+ if (info->segment == segment && info->bus == bus &&
info->devfn == devfn)
return info;
@@ -2520,8 +2520,18 @@ static struct dmar_domain
*dmar_insert_one_dev_info(struct intel_iommu *iommu,
if (!info)
return NULL;
- info->bus = bus;
- info->devfn = devfn;
+ if (!dev_is_real_dma_subdevice(dev)) {
+ info->bus = bus;
+ info->devfn = devfn;
+ info->segment = iommu->segment;
+ } else {
+ struct pci_dev *pdev = to_pci_dev(dev);
+
+ info->bus = pdev->bus->number;
+ info->devfn = pdev->devfn;
+ info->segment = pci_domain_nr(pdev->bus);
+ }
+
info->ats_supported = info->pasid_supported = info->pri_supported = 0;
info->ats_enabled = info->pasid_enabled = info->pri_enabled = 0;
info->ats_qdep = 0;
@@ -2561,7 +2571,8 @@ static struct dmar_domain
*dmar_insert_one_dev_info(struct intel_iommu *iommu,
if (!found) {
struct device_domain_info *info2;
- info2 = dmar_search_domain_by_dev_info(iommu->segment, bus,
devfn);
+ info2 = dmar_search_domain_by_dev_info(info->segment, info->bus,
+ info->devfn);
if (info2) {
found = info2->domain;
info2->dev = dev;
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 21633ce..4100bd2 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -609,6 +609,7 @@ struct device_domain_info {
struct list_head auxiliary_domains; /* auxiliary domains
* attached to this device
*/
+ u32 segment;/* PCI segment number */
u8 bus; /* PCI bus number */
u8 devfn; /* PCI devfn number */
u16 pfsid; /* SRIOV physical function source ID */
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v1 1/3] iommu/vt-d: Only clear real DMA device's context entries
Domain context mapping can encounter issues with sub-devices of a real
DMA device. A sub-device cannot have a valid context entry due to it
potentially aliasing another device's 16-bit ID. It's expected that
sub-devices of the real DMA device uses the real DMA device's requester
when context mapping.
This is an issue when a sub-device is removed where the context entry is
cleared for all aliases. Other sub-devices are still valid, resulting in
those sub-devices being stranded without valid context entries.
The correct approach is to use the real DMA device when programming the
context entries. The insertion path is correct because device_to_iommu()
will return the bus and devfn of the real DMA device. The removal path
needs to only operate on the real DMA device, otherwise the entire
context entry would be cleared for all sub-devices of the real DMA
device.
This patch also adds a helper to determine if a struct device is a
sub-device of a real DMA device.
Signed-off-by: Jon Derrick
---
drivers/iommu/intel-iommu.c | 9 -
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index ff5a30a..1ff45b2 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -2500,6 +2500,12 @@ static int domain_setup_first_level(struct intel_iommu
*iommu,
flags);
}
+static bool dev_is_real_dma_subdevice(struct device *dev)
+{
+ return dev && dev_is_pci(dev) &&
+ pci_real_dma_dev(to_pci_dev(dev)) != to_pci_dev(dev);
+}
+
static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
int bus, int devfn,
struct device *dev,
@@ -4975,7 +4981,8 @@ static void __dmar_remove_one_dev_info(struct
device_domain_info *info)
PASID_RID2PASID, false);
iommu_disable_dev_iotlb(info);
- domain_context_clear(iommu, info->dev);
+ if (!dev_is_real_dma_subdevice(info->dev))
+ domain_context_clear(iommu, info->dev);
intel_pasid_free_table(info->dev);
}
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH 0/1] Real DMA dev DMA domain patch
Sorry for the late patch here, but I hit the issue Baolu and Daniel pointed out could occur, and requires this fix (or iommu=nopt). Hoping to get it into an rc Jon Derrick (1): iommu/vt-d: use DMA domain for real DMA devices and subdevices drivers/iommu/intel-iommu.c | 56 - 1 file changed, 43 insertions(+), 13 deletions(-) -- 2.18.1 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH 1/1] iommu/vt-d: use DMA domain for real DMA devices and subdevices
The PCI devices handled by intel-iommu may have a DMA requester on another bus,
such as VMD subdevices needing to use the VMD endpoint.
The real DMA device is now used for the DMA mapping, but one case was missed
earlier: if the VMD device (and hence subdevices too) are under
IOMMU_DOMAIN_IDENTITY, mappings do not work.
Codepaths like intel_map_page() handle the IOMMU_DOMAIN_DMA case by creating an
iommu DMA mapping, and fall back on dma_direct_map_page() for the
IOMMU_DOMAIN_IDENTITY case. However, handling of the IDENTITY case is broken
when intel_page_page() handles a subdevice.
We observe that at iommu attach time, dmar_insert_one_dev_info() for the
subdevices will never set dev->archdata.iommu. This is because that function
uses find_domain() to check if there is already an IOMMU for the device, and
find_domain() then defers to the real DMA device which does have one. Thus
dmar_insert_one_dev_info() returns without assigning dev->archdata.iommu.
Then, later:
1. intel_map_page() checks if an IOMMU mapping is needed by calling
iommu_need_mapping() on the subdevice. identity_mapping() returns
false because dev->archdata.iommu is NULL, so this function
returns false indicating that mapping is needed.
2. __intel_map_single() is called to create the mapping.
3. __intel_map_single() calls find_domain(). This function now returns
the IDENTITY domain corresponding to the real DMA device.
4. __intel_map_single() calls domain_get_iommu() on this "real" domain.
A failure is hit and the entire operation is aborted, because this
codepath is not intended to handle IDENTITY mappings:
if (WARN_ON(domain->domain.type != IOMMU_DOMAIN_DMA))
return NULL;
This becomes problematic if the real DMA device and the subdevices have
different addressing capabilities and some require translation. Instead we can
put the real DMA dev and any subdevices on the DMA domain. This change assigns
subdevices to the DMA domain, and moves the real DMA device to the DMA domain
if necessary.
Reported-by: Daniel Drake
Fixes: b0140c69637e ("iommu/vt-d: Use pci_real_dma_dev() for mapping")
Signed-off-by: Jon Derrick
Signed-off-by: Daniel Drake
---
drivers/iommu/intel-iommu.c | 56 -
1 file changed, 43 insertions(+), 13 deletions(-)
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index ef0a5246700e..b4844a502499 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -3049,6 +3049,9 @@ static int device_def_domain_type(struct device *dev)
if ((iommu_identity_mapping & IDENTMAP_GFX) &&
IS_GFX_DEVICE(pdev))
return IOMMU_DOMAIN_IDENTITY;
+ if (pci_real_dma_dev(pdev) != pdev)
+ return IOMMU_DOMAIN_DMA;
+
/*
* We want to start off with all devices in the 1:1 domain, and
* take them out later if we find they can't access all of
memory.
@@ -5781,12 +5784,32 @@ static bool intel_iommu_capable(enum iommu_cap cap)
return false;
}
+static int intel_iommu_request_dma_domain_for_dev(struct device *dev,
+ struct dmar_domain *domain)
+{
+ int ret;
+
+ ret = iommu_request_dma_domain_for_dev(dev);
+ if (ret) {
+ dmar_remove_one_dev_info(dev);
+ domain->flags |= DOMAIN_FLAG_LOSE_CHILDREN;
+ if (!get_private_domain_for_dev(dev)) {
+ dev_warn(dev,
+"Failed to get a private domain.\n");
+ return -ENOMEM;
+ }
+ }
+
+ return 0;
+}
+
static int intel_iommu_add_device(struct device *dev)
{
struct dmar_domain *dmar_domain;
struct iommu_domain *domain;
struct intel_iommu *iommu;
struct iommu_group *group;
+ struct device *real_dev = dev;
u8 bus, devfn;
int ret;
@@ -5810,6 +5833,21 @@ static int intel_iommu_add_device(struct device *dev)
domain = iommu_get_domain_for_dev(dev);
dmar_domain = to_dmar_domain(domain);
+
+ if (dev_is_pci(dev))
+ real_dev = _real_dma_dev(to_pci_dev(dev))->dev;
+
+ if (real_dev != dev) {
+ domain = iommu_get_domain_for_dev(real_dev);
+ if (domain->type != IOMMU_DOMAIN_DMA) {
+ dmar_remove_one_dev_info(real_dev);
+
+ ret = intel_iommu_request_dma_domain_for_dev(real_dev,
dmar_domain);
+ if (ret)
+ goto unlink;
+ }
+ }
+
if (domain->type == IOMMU_DOMAIN_DMA) {
if (device_def_domain_type(dev) == IOMMU_DOMAIN_IDENTITY) {
ret = iommu_request_dm_for_dev(dev);
@@ -5823,20 +5861,12 @@ static int intel_iom
[PATCH v5 7/7] x86/PCI: Remove X86_DEV_DMA_OPS
From: Christoph Hellwig
There are no users of X86_DEV_DMA_OPS left, so remove the code.
Reviewed-by: Jon Derrick
Signed-off-by: Christoph Hellwig
---
arch/x86/Kconfig | 3 ---
arch/x86/include/asm/device.h | 10 --
arch/x86/pci/common.c | 38 --
3 files changed, 51 deletions(-)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5e89499..77f9426 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2955,9 +2955,6 @@ config HAVE_ATOMIC_IOMAP
def_bool y
depends on X86_32
-config X86_DEV_DMA_OPS
- bool
-
source "drivers/firmware/Kconfig"
source "arch/x86/kvm/Kconfig"
diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h
index 5e12c63..7e31f7f 100644
--- a/arch/x86/include/asm/device.h
+++ b/arch/x86/include/asm/device.h
@@ -8,16 +8,6 @@ struct dev_archdata {
#endif
};
-#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS)
-struct dma_domain {
- struct list_head node;
- const struct dma_map_ops *dma_ops;
- int domain_nr;
-};
-void add_dma_domain(struct dma_domain *domain);
-void del_dma_domain(struct dma_domain *domain);
-#endif
-
struct pdev_archdata {
};
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index fe21a5c..df1d959 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -625,43 +625,6 @@ unsigned int pcibios_assign_all_busses(void)
return (pci_probe & PCI_ASSIGN_ALL_BUSSES) ? 1 : 0;
}
-#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS)
-static LIST_HEAD(dma_domain_list);
-static DEFINE_SPINLOCK(dma_domain_list_lock);
-
-void add_dma_domain(struct dma_domain *domain)
-{
- spin_lock(_domain_list_lock);
- list_add(>node, _domain_list);
- spin_unlock(_domain_list_lock);
-}
-EXPORT_SYMBOL_GPL(add_dma_domain);
-
-void del_dma_domain(struct dma_domain *domain)
-{
- spin_lock(_domain_list_lock);
- list_del(>node);
- spin_unlock(_domain_list_lock);
-}
-EXPORT_SYMBOL_GPL(del_dma_domain);
-
-static void set_dma_domain_ops(struct pci_dev *pdev)
-{
- struct dma_domain *domain;
-
- spin_lock(_domain_list_lock);
- list_for_each_entry(domain, _domain_list, node) {
- if (pci_domain_nr(pdev->bus) == domain->domain_nr) {
- pdev->dev.dma_ops = domain->dma_ops;
- break;
- }
- }
- spin_unlock(_domain_list_lock);
-}
-#else
-static void set_dma_domain_ops(struct pci_dev *pdev) {}
-#endif
-
static void set_dev_domain_options(struct pci_dev *pdev)
{
if (is_vmd(pdev->bus))
@@ -697,7 +660,6 @@ int pcibios_add_device(struct pci_dev *dev)
pa_data = data->next;
memunmap(data);
}
- set_dma_domain_ops(dev);
set_dev_domain_options(dev);
return 0;
}
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v5 0/7] Clean up VMD DMA Map Ops
v4 Set: https://lore.kernel.org/linux-pci/20200120110220.gb17...@e121166-lin.cambridge.arm.com/T/#t v3 Set: https://lore.kernel.org/linux-iommu/20200113181742.ga27...@e121166-lin.cambridge.arm.com/T/#t v2 Set: https://lore.kernel.org/linux-iommu/1578580256-3483-1-git-send-email-jonathan.derr...@intel.com/T/#t v1 Set: https://lore.kernel.org/linux-iommu/20200107134125.gd30...@8bytes.org/T/#t VMD currently works with VT-d enabled by pointing DMA and IOMMU actions at the VMD endpoint. The problem with this approach is that the VMD endpoint's device-specific attributes, such as the DMA Mask Bits, are used instead of the child device's attributes. This set cleans up VMD by removing the override that redirects DMA map operations to the VMD endpoint. Instead it introduces a new DMA alias mechanism into the existing DMA alias infrastructure. This new DMA alias mechanism allows an architecture-specific pci_real_dma_dev() function to provide a pointer from a pci_dev to its PCI DMA device, where by default it returns the original pci_dev. In addition, this set removes the sanity check that was added to prevent assigning VMD child devices. By using the DMA alias mechanism, all child devices are assigned the same IOMMU group as the VMD endpoint. This removes the need for restricting VMD child devices from assignment, as the whole group would have to be assigned, requiring unbinding the VMD driver and removing the child device domain. v1 added a pointer in struct pci_dev that pointed to the DMA alias' struct pci_dev and did the necessary DMA alias and IOMMU modifications. v2 introduced a new weak function to reference the 'Direct DMA Alias', and removed the need to add a pointer in struct device or pci_dev. Weak functions are generally frowned upon when it's a single architecture implementation, so I am open to alternatives. v3 referenced the pci_dev rather than the struct device for the PCI 'Direct DMA Alias' (pci_direct_dma_alias()). This revision also allowed pci_for_each_dma_alias() to call any DMA aliases for the Direct DMA alias device, though I don't expect the VMD endpoint to need intra-bus DMA aliases. v4 changes the 'Direct DMA Alias' to instead refer to the 'Real DMA Dev', which either returns the PCI device itself or the PCI DMA device. v5 Fixes a bad call argument to pci_real_dma_dev that would have broken bisection. This revision also changes one of the calls to a one-liner, and assembles the same on my system. Changes from v4: Fix pci_real_dma_dev() call in 4/7. Change other pci_real_dma_dev() call in 4/7 to one-liner. Changes from v3: Uses pci_real_dma_dev() instead of pci_direct_dma_alias() Split IOMMU enabling, IOMMU VMD sanity check and VMD dma_map_ops cleanup into three patches Changes from v2: Uses struct pci_dev for PCI Device 'Direct DMA aliasing' (pci_direct_dma_alias) Allows pci_for_each_dma_alias to iterate over the alias mask of the 'Direct DMA alias' Changes from v1: Removed 1/5 & 2/5 misc fix patches that were merged Uses Christoph's staging/cleanup patches Introduce weak function rather than including pointer in struct device or pci_dev. Based on Bjorn's next: https://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci.git/log/?h=next Christoph Hellwig (2): x86/PCI: Add a to_pci_sysdata helper x86/PCI: Remove X86_DEV_DMA_OPS Jon Derrick (5): x86/PCI: Expose VMD's PCI Device in pci_sysdata PCI: Introduce pci_real_dma_dev() iommu/vt-d: Use pci_real_dma_dev() for mapping iommu/vt-d: Remove VMD child device sanity check PCI: vmd: Stop overriding dma_map_ops arch/x86/Kconfig | 3 - arch/x86/include/asm/device.h | 10 --- arch/x86/include/asm/pci.h | 31 - arch/x86/pci/common.c | 48 +++-- drivers/iommu/intel-iommu.c| 11 ++- drivers/pci/controller/Kconfig | 1 - drivers/pci/controller/vmd.c | 152 + drivers/pci/pci.c | 19 +- drivers/pci/search.c | 6 ++ include/linux/pci.h| 1 + 10 files changed, 54 insertions(+), 228 deletions(-) -- 1.8.3.1 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v5 5/7] iommu/vt-d: Remove VMD child device sanity check
This removes the sanity check required for VMD child devices. The new
pci_real_dma_dev() DMA alias mechanism places them in the same IOMMU
group as the VMD endpoint. Assignment of the group would require
assigning the VMD endpoint, where unbinding the VMD endpoint removes the
child device domain from the hierarchy.
Signed-off-by: Jon Derrick
---
drivers/iommu/intel-iommu.c | 10 +-
1 file changed, 1 insertion(+), 9 deletions(-)
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 72f26e8..7e2c492f 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -774,15 +774,7 @@ static struct intel_iommu *device_to_iommu(struct device
*dev, u8 *bus, u8 *devf
if (dev_is_pci(dev)) {
struct pci_dev *pf_pdev;
- pdev = to_pci_dev(dev);
-
-#ifdef CONFIG_X86
- /* VMD child devices currently cannot be handled individually */
- if (is_vmd(pdev->bus))
- return NULL;
-#endif
-
- pdev = pci_real_dma_dev(pdev);
+ pdev = pci_real_dma_dev(to_pci_dev(dev));
/* VFs aren't listed in scope tables; we need to look up
* the PF instead to find the IOMMU. */
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v5 2/7] x86/PCI: Expose VMD's PCI Device in pci_sysdata
To be used by Intel-IOMMU code to find the correct domain.
CC: Christoph Hellwig
Signed-off-by: Jon Derrick
---
arch/x86/include/asm/pci.h | 4 ++--
drivers/pci/controller/vmd.c | 2 +-
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index a4e09db60..6512c54 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -25,7 +25,7 @@ struct pci_sysdata {
void*fwnode;/* IRQ domain for MSI assignment */
#endif
#if IS_ENABLED(CONFIG_VMD)
- bool vmd_domain;/* True if in Intel VMD domain */
+ struct pci_dev *vmd_dev; /* VMD Device if in Intel VMD domain */
#endif
};
@@ -64,7 +64,7 @@ static inline void *_pci_root_bus_fwnode(struct pci_bus *bus)
#if IS_ENABLED(CONFIG_VMD)
static inline bool is_vmd(struct pci_bus *bus)
{
- return to_pci_sysdata(bus)->vmd_domain;
+ return to_pci_sysdata(bus)->vmd_dev != NULL;
}
#else
#define is_vmd(bus)false
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 2128422..d67ad56 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -679,7 +679,7 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned
long features)
.parent = res,
};
- sd->vmd_domain = true;
+ sd->vmd_dev = vmd->dev;
sd->domain = vmd_find_free_domain();
if (sd->domain < 0)
return sd->domain;
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v5 3/7] PCI: Introduce pci_real_dma_dev()
The current DMA alias implementation requires the aliased device be on
the same PCI bus as the requester ID. This introduces an arch-specific
mechanism to point to another PCI device when doing mapping and
PCI DMA alias search. The default case returns the actual device.
CC: Christoph Hellwig
Signed-off-by: Jon Derrick
---
arch/x86/pci/common.c | 10 ++
drivers/pci/pci.c | 19 ++-
drivers/pci/search.c | 6 ++
include/linux/pci.h | 1 +
4 files changed, 35 insertions(+), 1 deletion(-)
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 1e59df0..fe21a5c 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -736,3 +736,13 @@ int pci_ext_cfg_avail(void)
else
return 0;
}
+
+#if IS_ENABLED(CONFIG_VMD)
+struct pci_dev *pci_real_dma_dev(struct pci_dev *dev)
+{
+ if (is_vmd(dev->bus))
+ return to_pci_sysdata(dev->bus)->vmd_dev;
+
+ return dev;
+}
+#endif
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 581b177..36d24f2 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -6048,7 +6048,9 @@ bool pci_devs_are_dma_aliases(struct pci_dev *dev1,
struct pci_dev *dev2)
return (dev1->dma_alias_mask &&
test_bit(dev2->devfn, dev1->dma_alias_mask)) ||
(dev2->dma_alias_mask &&
- test_bit(dev1->devfn, dev2->dma_alias_mask));
+ test_bit(dev1->devfn, dev2->dma_alias_mask)) ||
+ pci_real_dma_dev(dev1) == dev2 ||
+ pci_real_dma_dev(dev2) == dev1;
}
bool pci_device_is_present(struct pci_dev *pdev)
@@ -6072,6 +6074,21 @@ void pci_ignore_hotplug(struct pci_dev *dev)
}
EXPORT_SYMBOL_GPL(pci_ignore_hotplug);
+/**
+ * pci_real_dma_dev - Get PCI DMA device for PCI device
+ * @dev: the PCI device that may have a PCI DMA alias
+ *
+ * Permits the platform to provide architecture-specific functionality to
+ * devices needing to alias DMA to another PCI device on another PCI bus. If
+ * the PCI device is on the same bus, it is recommended to use
+ * pci_add_dma_alias(). This is the default implementation. Architecture
+ * implementations can override this.
+ */
+struct pci_dev __weak *pci_real_dma_dev(struct pci_dev *dev)
+{
+ return dev;
+}
+
resource_size_t __weak pcibios_default_alignment(void)
{
return 0;
diff --git a/drivers/pci/search.c b/drivers/pci/search.c
index e4dbdef..2061672 100644
--- a/drivers/pci/search.c
+++ b/drivers/pci/search.c
@@ -32,6 +32,12 @@ int pci_for_each_dma_alias(struct pci_dev *pdev,
struct pci_bus *bus;
int ret;
+ /*
+* The device may have an explicit alias requester ID for DMA where the
+* requester is on another PCI bus.
+*/
+ pdev = pci_real_dma_dev(pdev);
+
ret = fn(pdev, pci_dev_id(pdev), data);
if (ret)
return ret;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 930fab2..3840a54 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1202,6 +1202,7 @@ u32 pcie_bandwidth_available(struct pci_dev *dev, struct
pci_dev **limiting_dev,
int pci_select_bars(struct pci_dev *dev, unsigned long flags);
bool pci_device_is_present(struct pci_dev *pdev);
void pci_ignore_hotplug(struct pci_dev *dev);
+struct pci_dev *pci_real_dma_dev(struct pci_dev *dev);
int __printf(6, 7) pci_request_irq(struct pci_dev *dev, unsigned int nr,
irq_handler_t handler, irq_handler_t thread_fn, void *dev_id,
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v5 6/7] PCI: vmd: Stop overriding dma_map_ops
Devices on the VMD domain use the VMD endpoint's requester ID and have
been relying on the VMD endpoint's DMA operations. The problem with this
was that VMD domain devices would use the VMD endpoint's attributes when
doing DMA and IOMMU mapping. We can be smarter about this by only using
the VMD endpoint when mapping and providing the correct child device's
attributes during DMA operations.
This patch removes the dma_map_ops redirect.
Signed-off-by: Jon Derrick
---
drivers/pci/controller/Kconfig | 1 -
drivers/pci/controller/vmd.c | 150 -
2 files changed, 151 deletions(-)
diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig
index 918e283..20bf00f 100644
--- a/drivers/pci/controller/Kconfig
+++ b/drivers/pci/controller/Kconfig
@@ -239,7 +239,6 @@ config PCIE_TANGO_SMP8759
config VMD
depends on PCI_MSI && X86_64 && SRCU
- select X86_DEV_DMA_OPS
tristate "Intel Volume Management Device Driver"
---help---
Adds support for the Intel Volume Management Device (VMD). VMD is a
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index d67ad56..fe1acb0 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -98,9 +98,6 @@ struct vmd_dev {
struct irq_domain *irq_domain;
struct pci_bus *bus;
u8 busn_start;
-
- struct dma_map_ops dma_ops;
- struct dma_domain dma_domain;
};
static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus)
@@ -295,151 +292,6 @@ static void vmd_set_desc(msi_alloc_info_t *arg, struct
msi_desc *desc)
.chip = _msi_controller,
};
-/*
- * VMD replaces the requester ID with its own. DMA mappings for devices in a
- * VMD domain need to be mapped for the VMD, not the device requiring
- * the mapping.
- */
-static struct device *to_vmd_dev(struct device *dev)
-{
- struct pci_dev *pdev = to_pci_dev(dev);
- struct vmd_dev *vmd = vmd_from_bus(pdev->bus);
-
- return >dev->dev;
-}
-
-static void *vmd_alloc(struct device *dev, size_t size, dma_addr_t *addr,
- gfp_t flag, unsigned long attrs)
-{
- return dma_alloc_attrs(to_vmd_dev(dev), size, addr, flag, attrs);
-}
-
-static void vmd_free(struct device *dev, size_t size, void *vaddr,
-dma_addr_t addr, unsigned long attrs)
-{
- return dma_free_attrs(to_vmd_dev(dev), size, vaddr, addr, attrs);
-}
-
-static int vmd_mmap(struct device *dev, struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t addr, size_t size,
- unsigned long attrs)
-{
- return dma_mmap_attrs(to_vmd_dev(dev), vma, cpu_addr, addr, size,
- attrs);
-}
-
-static int vmd_get_sgtable(struct device *dev, struct sg_table *sgt,
- void *cpu_addr, dma_addr_t addr, size_t size,
- unsigned long attrs)
-{
- return dma_get_sgtable_attrs(to_vmd_dev(dev), sgt, cpu_addr, addr, size,
- attrs);
-}
-
-static dma_addr_t vmd_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir,
- unsigned long attrs)
-{
- return dma_map_page_attrs(to_vmd_dev(dev), page, offset, size, dir,
- attrs);
-}
-
-static void vmd_unmap_page(struct device *dev, dma_addr_t addr, size_t size,
- enum dma_data_direction dir, unsigned long attrs)
-{
- dma_unmap_page_attrs(to_vmd_dev(dev), addr, size, dir, attrs);
-}
-
-static int vmd_map_sg(struct device *dev, struct scatterlist *sg, int nents,
- enum dma_data_direction dir, unsigned long attrs)
-{
- return dma_map_sg_attrs(to_vmd_dev(dev), sg, nents, dir, attrs);
-}
-
-static void vmd_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
-enum dma_data_direction dir, unsigned long attrs)
-{
- dma_unmap_sg_attrs(to_vmd_dev(dev), sg, nents, dir, attrs);
-}
-
-static void vmd_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
- size_t size, enum dma_data_direction dir)
-{
- dma_sync_single_for_cpu(to_vmd_dev(dev), addr, size, dir);
-}
-
-static void vmd_sync_single_for_device(struct device *dev, dma_addr_t addr,
- size_t size, enum dma_data_direction dir)
-{
- dma_sync_single_for_device(to_vmd_dev(dev), addr, size, dir);
-}
-
-static void vmd_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
- int nents, enum dma_data_direction dir)
-{
- dma_sync_sg_for_cpu(to_vmd_dev(dev), sg, nents, dir);
-}
-
-static void vmd_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-
[PATCH v5 4/7] iommu/vt-d: Use pci_real_dma_dev() for mapping
The PCI device may have a DMA requester on another bus, such as VMD subdevices needing to use the VMD endpoint. This case requires the real DMA device when mapping to IOMMU. Signed-off-by: Jon Derrick --- drivers/iommu/intel-iommu.c | 5 + 1 file changed, 5 insertions(+) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 0c8d81f..72f26e8 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -782,6 +782,8 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf return NULL; #endif + pdev = pci_real_dma_dev(pdev); + /* VFs aren't listed in scope tables; we need to look up * the PF instead to find the IOMMU. */ pf_pdev = pci_physfn(pdev); @@ -2428,6 +2430,9 @@ static struct dmar_domain *find_domain(struct device *dev) dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO)) return NULL; + if (dev_is_pci(dev)) + dev = _real_dma_dev(to_pci_dev(dev))->dev; + /* No lock here, assumes no domain exit in normal case */ info = dev->archdata.iommu; if (likely(info)) -- 1.8.3.1 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v5 1/7] x86/PCI: Add a to_pci_sysdata helper
From: Christoph Hellwig
Various helpers need the pci_sysdata just to dereference a single field
in it. Add a little helper that returns the properly typed sysdata
pointer to require a little less boilerplate code.
Signed-off-by: Christoph Hellwig
[jonathan.derrick: to_pci_sysdata const argument]
Signed-off-by: Jon Derrick
---
arch/x86/include/asm/pci.h | 29 +
1 file changed, 13 insertions(+), 16 deletions(-)
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 90d0731..a4e09db60 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -35,12 +35,15 @@ struct pci_sysdata {
#ifdef CONFIG_PCI
+static inline struct pci_sysdata *to_pci_sysdata(const struct pci_bus *bus)
+{
+ return bus->sysdata;
+}
+
#ifdef CONFIG_PCI_DOMAINS
static inline int pci_domain_nr(struct pci_bus *bus)
{
- struct pci_sysdata *sd = bus->sysdata;
-
- return sd->domain;
+ return to_pci_sysdata(bus)->domain;
}
static inline int pci_proc_domain(struct pci_bus *bus)
@@ -52,24 +55,20 @@ static inline int pci_proc_domain(struct pci_bus *bus)
#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
static inline void *_pci_root_bus_fwnode(struct pci_bus *bus)
{
- struct pci_sysdata *sd = bus->sysdata;
-
- return sd->fwnode;
+ return to_pci_sysdata(bus)->fwnode;
}
#define pci_root_bus_fwnode_pci_root_bus_fwnode
#endif
+#if IS_ENABLED(CONFIG_VMD)
static inline bool is_vmd(struct pci_bus *bus)
{
-#if IS_ENABLED(CONFIG_VMD)
- struct pci_sysdata *sd = bus->sysdata;
-
- return sd->vmd_domain;
-#else
- return false;
-#endif
+ return to_pci_sysdata(bus)->vmd_domain;
}
+#else
+#define is_vmd(bus)false
+#endif /* CONFIG_VMD */
/* Can be used to override the logic in pci_scan_bus for skipping
already-configured bus numbers - to be used for buggy BIOSes
@@ -124,9 +123,7 @@ static inline void early_quirks(void) { }
/* Returns the node based on pci bus */
static inline int __pcibus_to_node(const struct pci_bus *bus)
{
- const struct pci_sysdata *sd = bus->sysdata;
-
- return sd->node;
+ return to_pci_sysdata(bus)->node;
}
static inline const struct cpumask *
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v4 5/7] iommu/vt-d: Remove VMD child device sanity check
This removes the sanity check required for VMD child devices. The new
pci_real_dma_dev() DMA alias mechanism places them in the same IOMMU
group as the VMD endpoint. Assignment of the group would require
assigning the VMD endpoint, where unbinding the VMD endpoint removes the
child device domain from the hierarchy.
Signed-off-by: Jon Derrick
---
drivers/iommu/intel-iommu.c | 10 +-
1 file changed, 1 insertion(+), 9 deletions(-)
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 01a1b0f..c055699 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -774,15 +774,7 @@ static struct intel_iommu *device_to_iommu(struct device
*dev, u8 *bus, u8 *devf
if (dev_is_pci(dev)) {
struct pci_dev *pf_pdev;
- pdev = to_pci_dev(dev);
-
-#ifdef CONFIG_X86
- /* VMD child devices currently cannot be handled individually */
- if (is_vmd(pdev->bus))
- return NULL;
-#endif
-
- pdev = pci_real_dma_dev(dev);
+ pdev = pci_real_dma_dev(to_pci_dev(dev));
/* VFs aren't listed in scope tables; we need to look up
* the PF instead to find the IOMMU. */
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v4 4/7] iommu/vt-d: Use pci_real_dma_dev() for mapping
The PCI device may have a DMA requester on another bus, such as VMD
subdevices needing to use the VMD endpoint. This case requires the real
DMA device when mapping to IOMMU.
Signed-off-by: Jon Derrick
---
drivers/iommu/intel-iommu.c | 9 +
1 file changed, 9 insertions(+)
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 0c8d81f..01a1b0f 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -782,6 +782,8 @@ static struct intel_iommu *device_to_iommu(struct device
*dev, u8 *bus, u8 *devf
return NULL;
#endif
+ pdev = pci_real_dma_dev(dev);
+
/* VFs aren't listed in scope tables; we need to look up
* the PF instead to find the IOMMU. */
pf_pdev = pci_physfn(pdev);
@@ -2428,6 +2430,13 @@ static struct dmar_domain *find_domain(struct device
*dev)
dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO))
return NULL;
+ if (dev_is_pci(dev)) {
+ struct pci_dev *pdev;
+
+ pdev = pci_real_dma_dev(to_pci_dev(dev));
+ dev = >dev;
+ }
+
/* No lock here, assumes no domain exit in normal case */
info = dev->archdata.iommu;
if (likely(info))
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v4 2/7] x86/PCI: Expose VMD's PCI Device in pci_sysdata
To be used by Intel-IOMMU code to find the correct domain.
CC: Christoph Hellwig
Signed-off-by: Jon Derrick
---
arch/x86/include/asm/pci.h | 4 ++--
drivers/pci/controller/vmd.c | 2 +-
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index a4e09db60..6512c54 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -25,7 +25,7 @@ struct pci_sysdata {
void*fwnode;/* IRQ domain for MSI assignment */
#endif
#if IS_ENABLED(CONFIG_VMD)
- bool vmd_domain;/* True if in Intel VMD domain */
+ struct pci_dev *vmd_dev; /* VMD Device if in Intel VMD domain */
#endif
};
@@ -64,7 +64,7 @@ static inline void *_pci_root_bus_fwnode(struct pci_bus *bus)
#if IS_ENABLED(CONFIG_VMD)
static inline bool is_vmd(struct pci_bus *bus)
{
- return to_pci_sysdata(bus)->vmd_domain;
+ return to_pci_sysdata(bus)->vmd_dev != NULL;
}
#else
#define is_vmd(bus)false
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 2128422..d67ad56 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -679,7 +679,7 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned
long features)
.parent = res,
};
- sd->vmd_domain = true;
+ sd->vmd_dev = vmd->dev;
sd->domain = vmd_find_free_domain();
if (sd->domain < 0)
return sd->domain;
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v4 1/7] x86/PCI: Add a to_pci_sysdata helper
From: Christoph Hellwig
Various helpers need the pci_sysdata just to dereference a single field
in it. Add a little helper that returns the properly typed sysdata
pointer to require a little less boilerplate code.
Signed-off-by: Christoph Hellwig
[jonathan.derrick: to_pci_sysdata const argument]
Signed-off-by: Jon Derrick
---
arch/x86/include/asm/pci.h | 29 +
1 file changed, 13 insertions(+), 16 deletions(-)
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 90d0731..a4e09db60 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -35,12 +35,15 @@ struct pci_sysdata {
#ifdef CONFIG_PCI
+static inline struct pci_sysdata *to_pci_sysdata(const struct pci_bus *bus)
+{
+ return bus->sysdata;
+}
+
#ifdef CONFIG_PCI_DOMAINS
static inline int pci_domain_nr(struct pci_bus *bus)
{
- struct pci_sysdata *sd = bus->sysdata;
-
- return sd->domain;
+ return to_pci_sysdata(bus)->domain;
}
static inline int pci_proc_domain(struct pci_bus *bus)
@@ -52,24 +55,20 @@ static inline int pci_proc_domain(struct pci_bus *bus)
#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
static inline void *_pci_root_bus_fwnode(struct pci_bus *bus)
{
- struct pci_sysdata *sd = bus->sysdata;
-
- return sd->fwnode;
+ return to_pci_sysdata(bus)->fwnode;
}
#define pci_root_bus_fwnode_pci_root_bus_fwnode
#endif
+#if IS_ENABLED(CONFIG_VMD)
static inline bool is_vmd(struct pci_bus *bus)
{
-#if IS_ENABLED(CONFIG_VMD)
- struct pci_sysdata *sd = bus->sysdata;
-
- return sd->vmd_domain;
-#else
- return false;
-#endif
+ return to_pci_sysdata(bus)->vmd_domain;
}
+#else
+#define is_vmd(bus)false
+#endif /* CONFIG_VMD */
/* Can be used to override the logic in pci_scan_bus for skipping
already-configured bus numbers - to be used for buggy BIOSes
@@ -124,9 +123,7 @@ static inline void early_quirks(void) { }
/* Returns the node based on pci bus */
static inline int __pcibus_to_node(const struct pci_bus *bus)
{
- const struct pci_sysdata *sd = bus->sysdata;
-
- return sd->node;
+ return to_pci_sysdata(bus)->node;
}
static inline const struct cpumask *
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v4 3/7] PCI: Introduce pci_real_dma_dev()
The current DMA alias implementation requires the aliased device be on
the same PCI bus as the requester ID. This introduces an arch-specific
mechanism to point to another PCI device when doing mapping and
PCI DMA alias search. The default case returns the actual device.
CC: Christoph Hellwig
Signed-off-by: Jon Derrick
---
arch/x86/pci/common.c | 10 ++
drivers/pci/pci.c | 19 ++-
drivers/pci/search.c | 6 ++
include/linux/pci.h | 1 +
4 files changed, 35 insertions(+), 1 deletion(-)
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 1e59df0..fe21a5c 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -736,3 +736,13 @@ int pci_ext_cfg_avail(void)
else
return 0;
}
+
+#if IS_ENABLED(CONFIG_VMD)
+struct pci_dev *pci_real_dma_dev(struct pci_dev *dev)
+{
+ if (is_vmd(dev->bus))
+ return to_pci_sysdata(dev->bus)->vmd_dev;
+
+ return dev;
+}
+#endif
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 581b177..36d24f2 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -6048,7 +6048,9 @@ bool pci_devs_are_dma_aliases(struct pci_dev *dev1,
struct pci_dev *dev2)
return (dev1->dma_alias_mask &&
test_bit(dev2->devfn, dev1->dma_alias_mask)) ||
(dev2->dma_alias_mask &&
- test_bit(dev1->devfn, dev2->dma_alias_mask));
+ test_bit(dev1->devfn, dev2->dma_alias_mask)) ||
+ pci_real_dma_dev(dev1) == dev2 ||
+ pci_real_dma_dev(dev2) == dev1;
}
bool pci_device_is_present(struct pci_dev *pdev)
@@ -6072,6 +6074,21 @@ void pci_ignore_hotplug(struct pci_dev *dev)
}
EXPORT_SYMBOL_GPL(pci_ignore_hotplug);
+/**
+ * pci_real_dma_dev - Get PCI DMA device for PCI device
+ * @dev: the PCI device that may have a PCI DMA alias
+ *
+ * Permits the platform to provide architecture-specific functionality to
+ * devices needing to alias DMA to another PCI device on another PCI bus. If
+ * the PCI device is on the same bus, it is recommended to use
+ * pci_add_dma_alias(). This is the default implementation. Architecture
+ * implementations can override this.
+ */
+struct pci_dev __weak *pci_real_dma_dev(struct pci_dev *dev)
+{
+ return dev;
+}
+
resource_size_t __weak pcibios_default_alignment(void)
{
return 0;
diff --git a/drivers/pci/search.c b/drivers/pci/search.c
index e4dbdef..2061672 100644
--- a/drivers/pci/search.c
+++ b/drivers/pci/search.c
@@ -32,6 +32,12 @@ int pci_for_each_dma_alias(struct pci_dev *pdev,
struct pci_bus *bus;
int ret;
+ /*
+* The device may have an explicit alias requester ID for DMA where the
+* requester is on another PCI bus.
+*/
+ pdev = pci_real_dma_dev(pdev);
+
ret = fn(pdev, pci_dev_id(pdev), data);
if (ret)
return ret;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 930fab2..3840a54 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1202,6 +1202,7 @@ u32 pcie_bandwidth_available(struct pci_dev *dev, struct
pci_dev **limiting_dev,
int pci_select_bars(struct pci_dev *dev, unsigned long flags);
bool pci_device_is_present(struct pci_dev *pdev);
void pci_ignore_hotplug(struct pci_dev *dev);
+struct pci_dev *pci_real_dma_dev(struct pci_dev *dev);
int __printf(6, 7) pci_request_irq(struct pci_dev *dev, unsigned int nr,
irq_handler_t handler, irq_handler_t thread_fn, void *dev_id,
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v4 7/7] x86/PCI: Remove X86_DEV_DMA_OPS
From: Christoph Hellwig
There are no users of X86_DEV_DMA_OPS left, so remove the code.
Reviewed-by: Jon Derrick
Signed-off-by: Christoph Hellwig
---
arch/x86/Kconfig | 3 ---
arch/x86/include/asm/device.h | 10 --
arch/x86/pci/common.c | 38 --
3 files changed, 51 deletions(-)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5e89499..77f9426 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2955,9 +2955,6 @@ config HAVE_ATOMIC_IOMAP
def_bool y
depends on X86_32
-config X86_DEV_DMA_OPS
- bool
-
source "drivers/firmware/Kconfig"
source "arch/x86/kvm/Kconfig"
diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h
index 5e12c63..7e31f7f 100644
--- a/arch/x86/include/asm/device.h
+++ b/arch/x86/include/asm/device.h
@@ -8,16 +8,6 @@ struct dev_archdata {
#endif
};
-#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS)
-struct dma_domain {
- struct list_head node;
- const struct dma_map_ops *dma_ops;
- int domain_nr;
-};
-void add_dma_domain(struct dma_domain *domain);
-void del_dma_domain(struct dma_domain *domain);
-#endif
-
struct pdev_archdata {
};
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index fe21a5c..df1d959 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -625,43 +625,6 @@ unsigned int pcibios_assign_all_busses(void)
return (pci_probe & PCI_ASSIGN_ALL_BUSSES) ? 1 : 0;
}
-#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS)
-static LIST_HEAD(dma_domain_list);
-static DEFINE_SPINLOCK(dma_domain_list_lock);
-
-void add_dma_domain(struct dma_domain *domain)
-{
- spin_lock(_domain_list_lock);
- list_add(>node, _domain_list);
- spin_unlock(_domain_list_lock);
-}
-EXPORT_SYMBOL_GPL(add_dma_domain);
-
-void del_dma_domain(struct dma_domain *domain)
-{
- spin_lock(_domain_list_lock);
- list_del(>node);
- spin_unlock(_domain_list_lock);
-}
-EXPORT_SYMBOL_GPL(del_dma_domain);
-
-static void set_dma_domain_ops(struct pci_dev *pdev)
-{
- struct dma_domain *domain;
-
- spin_lock(_domain_list_lock);
- list_for_each_entry(domain, _domain_list, node) {
- if (pci_domain_nr(pdev->bus) == domain->domain_nr) {
- pdev->dev.dma_ops = domain->dma_ops;
- break;
- }
- }
- spin_unlock(_domain_list_lock);
-}
-#else
-static void set_dma_domain_ops(struct pci_dev *pdev) {}
-#endif
-
static void set_dev_domain_options(struct pci_dev *pdev)
{
if (is_vmd(pdev->bus))
@@ -697,7 +660,6 @@ int pcibios_add_device(struct pci_dev *dev)
pa_data = data->next;
memunmap(data);
}
- set_dma_domain_ops(dev);
set_dev_domain_options(dev);
return 0;
}
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v4 0/7] Clean up VMD DMA Map Ops
v3 Set: https://lore.kernel.org/linux-iommu/20200113181742.ga27...@e121166-lin.cambridge.arm.com/T/#t v2 Set: https://lore.kernel.org/linux-iommu/1578580256-3483-1-git-send-email-jonathan.derr...@intel.com/T/#t v1 Set: https://lore.kernel.org/linux-iommu/20200107134125.gd30...@8bytes.org/T/#t VMD currently works with VT-d enabled by pointing DMA and IOMMU actions at the VMD endpoint. The problem with this approach is that the VMD endpoint's device-specific attributes, such as the DMA Mask Bits, are used instead of the child device's attributes. This set cleans up VMD by removing the override that redirects DMA map operations to the VMD endpoint. Instead it introduces a new DMA alias mechanism into the existing DMA alias infrastructure. This new DMA alias mechanism allows an architecture-specific pci_real_dma_dev() function to provide a pointer from a pci_dev to its PCI DMA device, where by default it returns the original pci_dev. In addition, this set removes the sanity check that was added to prevent assigning VMD child devices. By using the DMA alias mechanism, all child devices are assigned the same IOMMU group as the VMD endpoint. This removes the need for restricting VMD child devices from assignment, as the whole group would have to be assigned, requiring unbinding the VMD driver and removing the child device domain. v1 added a pointer in struct pci_dev that pointed to the DMA alias' struct pci_dev and did the necessary DMA alias and IOMMU modifications. v2 introduced a new weak function to reference the 'Direct DMA Alias', and removed the need to add a pointer in struct device or pci_dev. Weak functions are generally frowned upon when it's a single architecture implementation, so I am open to alternatives. v3 referenced the pci_dev rather than the struct device for the PCI 'Direct DMA Alias' (pci_direct_dma_alias()). This revision also allowed pci_for_each_dma_alias() to call any DMA aliases for the Direct DMA alias device, though I don't expect the VMD endpoint to need intra-bus DMA aliases. v4 changes the 'Direct DMA Alias' to instead refer to the 'Real DMA Dev', which either returns the PCI device itself or the PCI DMA device. Changes from v3: Uses pci_real_dma_dev() instead of pci_direct_dma_alias() Split IOMMU enabling, IOMMU VMD sanity check and VMD dma_map_ops cleanup into three patches Changes from v2: Uses struct pci_dev for PCI Device 'Direct DMA aliasing' (pci_direct_dma_alias) Allows pci_for_each_dma_alias to iterate over the alias mask of the 'Direct DMA alias' Changes from v1: Removed 1/5 & 2/5 misc fix patches that were merged Uses Christoph's staging/cleanup patches Introduce weak function rather than including pointer in struct device or pci_dev. Based on Bjorn's next: https://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci.git/log/?h=next Christoph Hellwig (2): x86/PCI: Add a to_pci_sysdata helper x86/PCI: Remove X86_DEV_DMA_OPS Jon Derrick (5): x86/PCI: Expose VMD's PCI Device in pci_sysdata PCI: Introduce pci_real_dma_dev() iommu/vt-d: Use pci_real_dma_dev() for mapping iommu/vt-d: Remove VMD child device sanity check PCI: vmd: Stop overriding dma_map_ops arch/x86/Kconfig | 3 - arch/x86/include/asm/device.h | 10 --- arch/x86/include/asm/pci.h | 31 - arch/x86/pci/common.c | 48 +++-- drivers/iommu/intel-iommu.c| 15 ++-- drivers/pci/controller/Kconfig | 1 - drivers/pci/controller/vmd.c | 152 + drivers/pci/pci.c | 19 +- drivers/pci/search.c | 6 ++ include/linux/pci.h| 1 + 10 files changed, 58 insertions(+), 228 deletions(-) -- 1.8.3.1 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v4 6/7] PCI: vmd: Stop overriding dma_map_ops
Devices on the VMD domain use the VMD endpoint's requester ID and have
been relying on the VMD endpoint's DMA operations. The problem with this
was that VMD domain devices would use the VMD endpoint's attributes when
doing DMA and IOMMU mapping. We can be smarter about this by only using
the VMD endpoint when mapping and providing the correct child device's
attributes during DMA operations.
This patch removes the dma_map_ops redirect.
Signed-off-by: Jon Derrick
---
drivers/pci/controller/Kconfig | 1 -
drivers/pci/controller/vmd.c | 150 -
2 files changed, 151 deletions(-)
diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig
index 918e283..20bf00f 100644
--- a/drivers/pci/controller/Kconfig
+++ b/drivers/pci/controller/Kconfig
@@ -239,7 +239,6 @@ config PCIE_TANGO_SMP8759
config VMD
depends on PCI_MSI && X86_64 && SRCU
- select X86_DEV_DMA_OPS
tristate "Intel Volume Management Device Driver"
---help---
Adds support for the Intel Volume Management Device (VMD). VMD is a
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index d67ad56..fe1acb0 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -98,9 +98,6 @@ struct vmd_dev {
struct irq_domain *irq_domain;
struct pci_bus *bus;
u8 busn_start;
-
- struct dma_map_ops dma_ops;
- struct dma_domain dma_domain;
};
static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus)
@@ -295,151 +292,6 @@ static void vmd_set_desc(msi_alloc_info_t *arg, struct
msi_desc *desc)
.chip = _msi_controller,
};
-/*
- * VMD replaces the requester ID with its own. DMA mappings for devices in a
- * VMD domain need to be mapped for the VMD, not the device requiring
- * the mapping.
- */
-static struct device *to_vmd_dev(struct device *dev)
-{
- struct pci_dev *pdev = to_pci_dev(dev);
- struct vmd_dev *vmd = vmd_from_bus(pdev->bus);
-
- return >dev->dev;
-}
-
-static void *vmd_alloc(struct device *dev, size_t size, dma_addr_t *addr,
- gfp_t flag, unsigned long attrs)
-{
- return dma_alloc_attrs(to_vmd_dev(dev), size, addr, flag, attrs);
-}
-
-static void vmd_free(struct device *dev, size_t size, void *vaddr,
-dma_addr_t addr, unsigned long attrs)
-{
- return dma_free_attrs(to_vmd_dev(dev), size, vaddr, addr, attrs);
-}
-
-static int vmd_mmap(struct device *dev, struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t addr, size_t size,
- unsigned long attrs)
-{
- return dma_mmap_attrs(to_vmd_dev(dev), vma, cpu_addr, addr, size,
- attrs);
-}
-
-static int vmd_get_sgtable(struct device *dev, struct sg_table *sgt,
- void *cpu_addr, dma_addr_t addr, size_t size,
- unsigned long attrs)
-{
- return dma_get_sgtable_attrs(to_vmd_dev(dev), sgt, cpu_addr, addr, size,
- attrs);
-}
-
-static dma_addr_t vmd_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir,
- unsigned long attrs)
-{
- return dma_map_page_attrs(to_vmd_dev(dev), page, offset, size, dir,
- attrs);
-}
-
-static void vmd_unmap_page(struct device *dev, dma_addr_t addr, size_t size,
- enum dma_data_direction dir, unsigned long attrs)
-{
- dma_unmap_page_attrs(to_vmd_dev(dev), addr, size, dir, attrs);
-}
-
-static int vmd_map_sg(struct device *dev, struct scatterlist *sg, int nents,
- enum dma_data_direction dir, unsigned long attrs)
-{
- return dma_map_sg_attrs(to_vmd_dev(dev), sg, nents, dir, attrs);
-}
-
-static void vmd_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
-enum dma_data_direction dir, unsigned long attrs)
-{
- dma_unmap_sg_attrs(to_vmd_dev(dev), sg, nents, dir, attrs);
-}
-
-static void vmd_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
- size_t size, enum dma_data_direction dir)
-{
- dma_sync_single_for_cpu(to_vmd_dev(dev), addr, size, dir);
-}
-
-static void vmd_sync_single_for_device(struct device *dev, dma_addr_t addr,
- size_t size, enum dma_data_direction dir)
-{
- dma_sync_single_for_device(to_vmd_dev(dev), addr, size, dir);
-}
-
-static void vmd_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
- int nents, enum dma_data_direction dir)
-{
- dma_sync_sg_for_cpu(to_vmd_dev(dev), sg, nents, dir);
-}
-
-static void vmd_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-
[PATCH v3 3/5] PCI: Introduce pci_direct_dma_alias()
The current DMA alias implementation requires the aliased device be on
the same PCI bus as the requester ID. This introduces an arch-specific
mechanism to point to another PCI device when doing mapping and
PCI DMA alias search.
Signed-off-by: Jon Derrick
---
arch/x86/pci/common.c | 7 +++
drivers/pci/pci.c | 19 ++-
drivers/pci/search.c | 7 +++
include/linux/pci.h | 1 +
4 files changed, 33 insertions(+), 1 deletion(-)
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 1e59df0..83334a5 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -736,3 +736,10 @@ int pci_ext_cfg_avail(void)
else
return 0;
}
+
+#if IS_ENABLED(CONFIG_VMD)
+struct pci_dev *pci_direct_dma_alias(struct pci_dev *dev)
+{
+ return to_pci_sysdata(dev->bus)->vmd_dev;
+}
+#endif
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index ad746d9..1362694 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -6034,7 +6034,9 @@ bool pci_devs_are_dma_aliases(struct pci_dev *dev1,
struct pci_dev *dev2)
return (dev1->dma_alias_mask &&
test_bit(dev2->devfn, dev1->dma_alias_mask)) ||
(dev2->dma_alias_mask &&
- test_bit(dev1->devfn, dev2->dma_alias_mask));
+ test_bit(dev1->devfn, dev2->dma_alias_mask)) ||
+ (pci_direct_dma_alias(dev1) == dev2) ||
+ (pci_direct_dma_alias(dev2) == dev1);
}
bool pci_device_is_present(struct pci_dev *pdev)
@@ -6058,6 +6060,21 @@ void pci_ignore_hotplug(struct pci_dev *dev)
}
EXPORT_SYMBOL_GPL(pci_ignore_hotplug);
+/**
+ * pci_direct_dma_alias - Get PCI DMA alias for PCI device
+ * @dev: the PCI device that may have a PCI DMA alias
+ *
+ * Permits the platform to provide architecture-specific functionality to
+ * devices needing to alias DMA to another PCI device on another PCI bus. If
+ * the PCI device is on the same bus, it is recommended to use
+ * pci_add_dma_alias(). This is the default implementation. Architecture
+ * implementations can override this.
+ */
+struct pci_dev __weak *pci_direct_dma_alias(struct pci_dev *dev)
+{
+ return NULL;
+}
+
resource_size_t __weak pcibios_default_alignment(void)
{
return 0;
diff --git a/drivers/pci/search.c b/drivers/pci/search.c
index bade140..12811b3 100644
--- a/drivers/pci/search.c
+++ b/drivers/pci/search.c
@@ -32,6 +32,13 @@ int pci_for_each_dma_alias(struct pci_dev *pdev,
struct pci_bus *bus;
int ret;
+ /*
+* The device may have an explicit alias requester ID for DMA where the
+* requester is on another PCI bus.
+*/
+ if (unlikely(pci_direct_dma_alias(pdev)))
+ pdev = pci_direct_dma_alias(pdev);
+
ret = fn(pdev, pci_dev_id(pdev), data);
if (ret)
return ret;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index c393dff..cb6677b 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1202,6 +1202,7 @@ u32 pcie_bandwidth_available(struct pci_dev *dev, struct
pci_dev **limiting_dev,
int pci_select_bars(struct pci_dev *dev, unsigned long flags);
bool pci_device_is_present(struct pci_dev *pdev);
void pci_ignore_hotplug(struct pci_dev *dev);
+struct pci_dev *pci_direct_dma_alias(struct pci_dev *dev);
int __printf(6, 7) pci_request_irq(struct pci_dev *dev, unsigned int nr,
irq_handler_t handler, irq_handler_t thread_fn, void *dev_id,
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v3 1/5] x86/pci: Add a to_pci_sysdata helper
From: Christoph Hellwig
Various helpers need the pci_sysdata just to dereference a single field
in it. Add a little helper that returns the properly typed sysdata
pointer to require a little less boilerplate code.
Signed-off-by: Christoph Hellwig
[jonathan.derrick: added un-const cast]
Signed-off-by: Jon Derrick
---
arch/x86/include/asm/pci.h | 28 +---
1 file changed, 13 insertions(+), 15 deletions(-)
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 90d0731..cf680c5 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -35,12 +35,15 @@ struct pci_sysdata {
#ifdef CONFIG_PCI
+static inline struct pci_sysdata *to_pci_sysdata(struct pci_bus *bus)
+{
+ return bus->sysdata;
+}
+
#ifdef CONFIG_PCI_DOMAINS
static inline int pci_domain_nr(struct pci_bus *bus)
{
- struct pci_sysdata *sd = bus->sysdata;
-
- return sd->domain;
+ return to_pci_sysdata(bus)->domain;
}
static inline int pci_proc_domain(struct pci_bus *bus)
@@ -52,23 +55,20 @@ static inline int pci_proc_domain(struct pci_bus *bus)
#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
static inline void *_pci_root_bus_fwnode(struct pci_bus *bus)
{
- struct pci_sysdata *sd = bus->sysdata;
-
- return sd->fwnode;
+ return to_pci_sysdata(bus)->fwnode;
}
#define pci_root_bus_fwnode_pci_root_bus_fwnode
#endif
+#if IS_ENABLED(CONFIG_VMD)
static inline bool is_vmd(struct pci_bus *bus)
{
-#if IS_ENABLED(CONFIG_VMD)
- struct pci_sysdata *sd = bus->sysdata;
-
- return sd->vmd_domain;
+ return to_pci_sysdata(bus)->vmd_domain;
+}
#else
- return false;
-#endif
+#define is_vmd(bus)false
+#endif /* CONFIG_VMD */
}
/* Can be used to override the logic in pci_scan_bus for skipping
@@ -124,9 +124,7 @@ static inline void early_quirks(void) { }
/* Returns the node based on pci bus */
static inline int __pcibus_to_node(const struct pci_bus *bus)
{
- const struct pci_sysdata *sd = bus->sysdata;
-
- return sd->node;
+ return to_pci_sysdata((struct pci_bus *) bus)->node;
}
static inline const struct cpumask *
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v3 4/5] PCI: vmd: Stop overriding dma_map_ops
Devices on the VMD domain use the VMD endpoint's requester ID and have
been relying on the VMD endpoint's DMA operations. The problem with this
was that VMD domain devices would use the VMD endpoint's attributes when
doing DMA and IOMMU mapping. We can be smarter about this by only using
the VMD endpoint when mapping and providing the correct child device's
attributes during DMA operations.
This patch modifies Intel-IOMMU to check for a 'Direct DMA Alias' and
refer to it for mapping.
Signed-off-by: Jon Derrick
---
drivers/iommu/intel-iommu.c| 18 +++--
drivers/pci/controller/Kconfig | 1 -
drivers/pci/controller/vmd.c | 150 -
3 files changed, 13 insertions(+), 156 deletions(-)
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 716347e2..7ca807a 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -804,14 +804,14 @@ static struct intel_iommu *device_to_iommu(struct device
*dev, u8 *bus, u8 *devf
if (dev_is_pci(dev)) {
struct pci_dev *pf_pdev;
+ struct pci_dev *dma_alias;
pdev = to_pci_dev(dev);
-#ifdef CONFIG_X86
- /* VMD child devices currently cannot be handled individually */
- if (is_vmd(pdev->bus))
- return NULL;
-#endif
+ /* DMA aliased devices use the DMA alias's IOMMU */
+ dma_alias = pci_direct_dma_alias(pdev);
+ if (dma_alias)
+ pdev = dma_alias;
/* VFs aren't listed in scope tables; we need to look up
* the PF instead to find the IOMMU. */
@@ -2521,6 +2521,14 @@ struct dmar_domain *find_domain(struct device *dev)
dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO))
return NULL;
+ if (dev_is_pci(dev)) {
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct pci_dev *dma_alias = pci_direct_dma_alias(pdev);
+
+ if (dma_alias)
+ dev = _alias->dev;
+ }
+
/* No lock here, assumes no domain exit in normal case */
info = dev->archdata.iommu;
if (likely(info))
diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig
index c77069c..55671429 100644
--- a/drivers/pci/controller/Kconfig
+++ b/drivers/pci/controller/Kconfig
@@ -239,7 +239,6 @@ config PCIE_TANGO_SMP8759
config VMD
depends on PCI_MSI && X86_64 && SRCU
- select X86_DEV_DMA_OPS
tristate "Intel Volume Management Device Driver"
---help---
Adds support for the Intel Volume Management Device (VMD). VMD is a
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index d67ad56..fe1acb0 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -98,9 +98,6 @@ struct vmd_dev {
struct irq_domain *irq_domain;
struct pci_bus *bus;
u8 busn_start;
-
- struct dma_map_ops dma_ops;
- struct dma_domain dma_domain;
};
static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus)
@@ -295,151 +292,6 @@ static void vmd_set_desc(msi_alloc_info_t *arg, struct
msi_desc *desc)
.chip = _msi_controller,
};
-/*
- * VMD replaces the requester ID with its own. DMA mappings for devices in a
- * VMD domain need to be mapped for the VMD, not the device requiring
- * the mapping.
- */
-static struct device *to_vmd_dev(struct device *dev)
-{
- struct pci_dev *pdev = to_pci_dev(dev);
- struct vmd_dev *vmd = vmd_from_bus(pdev->bus);
-
- return >dev->dev;
-}
-
-static void *vmd_alloc(struct device *dev, size_t size, dma_addr_t *addr,
- gfp_t flag, unsigned long attrs)
-{
- return dma_alloc_attrs(to_vmd_dev(dev), size, addr, flag, attrs);
-}
-
-static void vmd_free(struct device *dev, size_t size, void *vaddr,
-dma_addr_t addr, unsigned long attrs)
-{
- return dma_free_attrs(to_vmd_dev(dev), size, vaddr, addr, attrs);
-}
-
-static int vmd_mmap(struct device *dev, struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t addr, size_t size,
- unsigned long attrs)
-{
- return dma_mmap_attrs(to_vmd_dev(dev), vma, cpu_addr, addr, size,
- attrs);
-}
-
-static int vmd_get_sgtable(struct device *dev, struct sg_table *sgt,
- void *cpu_addr, dma_addr_t addr, size_t size,
- unsigned long attrs)
-{
- return dma_get_sgtable_attrs(to_vmd_dev(dev), sgt, cpu_addr, addr, size,
- attrs);
-}
-
-static dma_addr_t vmd_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir,
-
[PATCH v3 0/5] Clean up VMD DMA Map Ops
v2 Set: https://lore.kernel.org/linux-iommu/1578580256-3483-1-git-send-email-jonathan.derr...@intel.com/T/#t v1 Set: https://lore.kernel.org/linux-iommu/20200107134125.gd30...@8bytes.org/T/#t VMD currently works with VT-d enabled by pointing DMA and IOMMU actions at the VMD endpoint. The problem with this approach is that the VMD endpoint's device-specific attributes, such as the DMA Mask Bits, are used instead. This set cleans up VMD by removing the override that redirects DMA map operations to the VMD endpoint. Instead it introduces a new DMA alias mechanism into the existing DMA alias infrastructure. v1 added a pointer in struct pci_dev that pointed to the DMA alias' struct pci_dev and did the necessary DMA alias and IOMMU modifications. v2 introduced a new weak function to reference the 'Direct DMA Alias', and removed the need to add a pointer in struct device or pci_dev. Weak functions are generally frowned upon when it's a single architecture implementation, so I am open to alternatives. v3 references the pci_dev rather than the struct device for the PCI 'Direct DMA Alias' (pci_direct_dma_alias()). This revision also allows pci_for_each_dma_alias() to call any DMA aliases for the Direct DMA alias device, though I don't expect the VMD endpoint to need intra-bus DMA aliases. Changes from v2: Uses struct pci_dev for PCI Device 'Direct DMA aliasing' (pci_direct_dma_alias) Allows pci_for_each_dma_alias to iterate over the alias mask of the 'Direct DMA alias' Changes from v1: Removed 1/5 & 2/5 misc fix patches that were merged Uses Christoph's staging/cleanup patches Introduce weak function rather than including pointer in struct device or pci_dev. Based on Joerg's next: https://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git/ Jon Derrick (5): x86/pci: Add a to_pci_sysdata helper x86/PCI: Expose VMD's PCI Device in pci_sysdata PCI: Introduce pci_direct_dma_alias() PCI: vmd: Stop overriding dma_map_ops x86/pci: Remove X86_DEV_DMA_OPS arch/x86/Kconfig | 3 - arch/x86/include/asm/device.h | 10 --- arch/x86/include/asm/pci.h | 31 - arch/x86/pci/common.c | 45 ++-- drivers/iommu/intel-iommu.c| 18 +++-- drivers/pci/controller/Kconfig | 1 - drivers/pci/controller/vmd.c | 152 + drivers/pci/pci.c | 19 +- drivers/pci/search.c | 7 ++ include/linux/pci.h| 1 + 10 files changed, 61 insertions(+), 226 deletions(-) -- 1.8.3.1 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v3 2/5] x86/PCI: Expose VMD's PCI Device in pci_sysdata
To be used by Intel-IOMMU code to find the correct domain.
CC: Christoph Hellwig
Signed-off-by: Jon Derrick
---
arch/x86/include/asm/pci.h | 5 ++---
drivers/pci/controller/vmd.c | 2 +-
2 files changed, 3 insertions(+), 4 deletions(-)
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index cf680c5..b982d9c 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -25,7 +25,7 @@ struct pci_sysdata {
void*fwnode;/* IRQ domain for MSI assignment */
#endif
#if IS_ENABLED(CONFIG_VMD)
- bool vmd_domain;/* True if in Intel VMD domain */
+ struct pci_dev *vmd_dev; /* VMD Device if in Intel VMD domain */
#endif
};
@@ -64,12 +64,11 @@ static inline void *_pci_root_bus_fwnode(struct pci_bus
*bus)
#if IS_ENABLED(CONFIG_VMD)
static inline bool is_vmd(struct pci_bus *bus)
{
- return to_pci_sysdata(bus)->vmd_domain;
+ return to_pci_sysdata(bus)->vmd_dev != NULL;
}
#else
#define is_vmd(bus)false
#endif /* CONFIG_VMD */
-}
/* Can be used to override the logic in pci_scan_bus for skipping
already-configured bus numbers - to be used for buggy BIOSes
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 2128422..d67ad56 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -679,7 +679,7 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned
long features)
.parent = res,
};
- sd->vmd_domain = true;
+ sd->vmd_dev = vmd->dev;
sd->domain = vmd_find_free_domain();
if (sd->domain < 0)
return sd->domain;
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v3 5/5] x86/pci: Remove X86_DEV_DMA_OPS
From: Christoph Hellwig
There are no users of X86_DEV_DMA_OPS left, so remove the code.
Reviewed-by: Jon Derrick
Signed-off-by: Christoph Hellwig
---
arch/x86/Kconfig | 3 ---
arch/x86/include/asm/device.h | 10 --
arch/x86/pci/common.c | 38 --
3 files changed, 51 deletions(-)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5e89499..77f9426 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2955,9 +2955,6 @@ config HAVE_ATOMIC_IOMAP
def_bool y
depends on X86_32
-config X86_DEV_DMA_OPS
- bool
-
source "drivers/firmware/Kconfig"
source "arch/x86/kvm/Kconfig"
diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h
index 5e12c63..7e31f7f 100644
--- a/arch/x86/include/asm/device.h
+++ b/arch/x86/include/asm/device.h
@@ -8,16 +8,6 @@ struct dev_archdata {
#endif
};
-#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS)
-struct dma_domain {
- struct list_head node;
- const struct dma_map_ops *dma_ops;
- int domain_nr;
-};
-void add_dma_domain(struct dma_domain *domain);
-void del_dma_domain(struct dma_domain *domain);
-#endif
-
struct pdev_archdata {
};
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 83334a5..8f60d52 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -625,43 +625,6 @@ unsigned int pcibios_assign_all_busses(void)
return (pci_probe & PCI_ASSIGN_ALL_BUSSES) ? 1 : 0;
}
-#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS)
-static LIST_HEAD(dma_domain_list);
-static DEFINE_SPINLOCK(dma_domain_list_lock);
-
-void add_dma_domain(struct dma_domain *domain)
-{
- spin_lock(_domain_list_lock);
- list_add(>node, _domain_list);
- spin_unlock(_domain_list_lock);
-}
-EXPORT_SYMBOL_GPL(add_dma_domain);
-
-void del_dma_domain(struct dma_domain *domain)
-{
- spin_lock(_domain_list_lock);
- list_del(>node);
- spin_unlock(_domain_list_lock);
-}
-EXPORT_SYMBOL_GPL(del_dma_domain);
-
-static void set_dma_domain_ops(struct pci_dev *pdev)
-{
- struct dma_domain *domain;
-
- spin_lock(_domain_list_lock);
- list_for_each_entry(domain, _domain_list, node) {
- if (pci_domain_nr(pdev->bus) == domain->domain_nr) {
- pdev->dev.dma_ops = domain->dma_ops;
- break;
- }
- }
- spin_unlock(_domain_list_lock);
-}
-#else
-static void set_dma_domain_ops(struct pci_dev *pdev) {}
-#endif
-
static void set_dev_domain_options(struct pci_dev *pdev)
{
if (is_vmd(pdev->bus))
@@ -697,7 +660,6 @@ int pcibios_add_device(struct pci_dev *dev)
pa_data = data->next;
memunmap(data);
}
- set_dma_domain_ops(dev);
set_dev_domain_options(dev);
return 0;
}
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v2 1/5] x86/pci: Add a to_pci_sysdata helper
From: Christoph Hellwig
From: Christoph Hellwig
Various helpers need the pci_sysdata just to dereference a single field
in it. Add a little helper that returns the properly typed sysdata
pointer to require a little less boilerplate code.
Signed-off-by: Christoph Hellwig
[jonathan.derrick: added un-const cast]
Signed-off-by: Jon Derrick
---
arch/x86/include/asm/pci.h | 28 +---
1 file changed, 13 insertions(+), 15 deletions(-)
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 90d0731..cf680c5 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -35,12 +35,15 @@ struct pci_sysdata {
#ifdef CONFIG_PCI
+static inline struct pci_sysdata *to_pci_sysdata(struct pci_bus *bus)
+{
+ return bus->sysdata;
+}
+
#ifdef CONFIG_PCI_DOMAINS
static inline int pci_domain_nr(struct pci_bus *bus)
{
- struct pci_sysdata *sd = bus->sysdata;
-
- return sd->domain;
+ return to_pci_sysdata(bus)->domain;
}
static inline int pci_proc_domain(struct pci_bus *bus)
@@ -52,23 +55,20 @@ static inline int pci_proc_domain(struct pci_bus *bus)
#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
static inline void *_pci_root_bus_fwnode(struct pci_bus *bus)
{
- struct pci_sysdata *sd = bus->sysdata;
-
- return sd->fwnode;
+ return to_pci_sysdata(bus)->fwnode;
}
#define pci_root_bus_fwnode_pci_root_bus_fwnode
#endif
+#if IS_ENABLED(CONFIG_VMD)
static inline bool is_vmd(struct pci_bus *bus)
{
-#if IS_ENABLED(CONFIG_VMD)
- struct pci_sysdata *sd = bus->sysdata;
-
- return sd->vmd_domain;
+ return to_pci_sysdata(bus)->vmd_domain;
+}
#else
- return false;
-#endif
+#define is_vmd(bus)false
+#endif /* CONFIG_VMD */
}
/* Can be used to override the logic in pci_scan_bus for skipping
@@ -124,9 +124,7 @@ static inline void early_quirks(void) { }
/* Returns the node based on pci bus */
static inline int __pcibus_to_node(const struct pci_bus *bus)
{
- const struct pci_sysdata *sd = bus->sysdata;
-
- return sd->node;
+ return to_pci_sysdata((struct pci_bus *) bus)->node;
}
static inline const struct cpumask *
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v2 4/5] PCI: vmd: Stop overriding dma_map_ops
Devices on the VMD domain use the VMD endpoint's requester-id and have
been relying on the VMD endpoint's dma operations. The downside of this
was that VMD domain devices would use the VMD endpoint's attributes when
doing DMA and IOMMU mapping. We can be smarter about this by only using
the VMD endpoint when mapping and providing the correct child device's
attributes during dma operations.
This patch modifies intel-iommu to check for a 'direct dma alias' and
refer to it for mapping.
Signed-off-by: Jon Derrick
---
drivers/iommu/intel-iommu.c| 17 +++--
drivers/pci/controller/Kconfig | 1 -
drivers/pci/controller/vmd.c | 150 -
3 files changed, 12 insertions(+), 156 deletions(-)
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index b2526a4..c812594 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -773,14 +773,13 @@ static struct intel_iommu *device_to_iommu(struct device
*dev, u8 *bus, u8 *devf
if (dev_is_pci(dev)) {
struct pci_dev *pf_pdev;
+ struct device *dma_alias;
pdev = to_pci_dev(dev);
-#ifdef CONFIG_X86
- /* VMD child devices currently cannot be handled individually */
- if (is_vmd(pdev->bus))
- return NULL;
-#endif
+ dma_alias = pci_direct_dma_alias(pdev);
+ if (dma_alias && dev_is_pci(dma_alias))
+ pdev = to_pci_dev(dma_alias);
/* VFs aren't listed in scope tables; we need to look up
* the PF instead to find the IOMMU. */
@@ -2428,6 +2427,14 @@ static struct dmar_domain *find_domain(struct device
*dev)
dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO))
return NULL;
+ if (dev_is_pci(dev)) {
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct device *dma_alias = pci_direct_dma_alias(pdev);
+
+ if (dma_alias)
+ dev = dma_alias;
+ }
+
/* No lock here, assumes no domain exit in normal case */
info = dev->archdata.iommu;
if (likely(info))
diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig
index c77069c..55671429 100644
--- a/drivers/pci/controller/Kconfig
+++ b/drivers/pci/controller/Kconfig
@@ -239,7 +239,6 @@ config PCIE_TANGO_SMP8759
config VMD
depends on PCI_MSI && X86_64 && SRCU
- select X86_DEV_DMA_OPS
tristate "Intel Volume Management Device Driver"
---help---
Adds support for the Intel Volume Management Device (VMD). VMD is a
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 907b5bd..5824a39 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -98,9 +98,6 @@ struct vmd_dev {
struct irq_domain *irq_domain;
struct pci_bus *bus;
u8 busn_start;
-
- struct dma_map_ops dma_ops;
- struct dma_domain dma_domain;
};
static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus)
@@ -295,151 +292,6 @@ static void vmd_set_desc(msi_alloc_info_t *arg, struct
msi_desc *desc)
.chip = _msi_controller,
};
-/*
- * VMD replaces the requester ID with its own. DMA mappings for devices in a
- * VMD domain need to be mapped for the VMD, not the device requiring
- * the mapping.
- */
-static struct device *to_vmd_dev(struct device *dev)
-{
- struct pci_dev *pdev = to_pci_dev(dev);
- struct vmd_dev *vmd = vmd_from_bus(pdev->bus);
-
- return >dev->dev;
-}
-
-static void *vmd_alloc(struct device *dev, size_t size, dma_addr_t *addr,
- gfp_t flag, unsigned long attrs)
-{
- return dma_alloc_attrs(to_vmd_dev(dev), size, addr, flag, attrs);
-}
-
-static void vmd_free(struct device *dev, size_t size, void *vaddr,
-dma_addr_t addr, unsigned long attrs)
-{
- return dma_free_attrs(to_vmd_dev(dev), size, vaddr, addr, attrs);
-}
-
-static int vmd_mmap(struct device *dev, struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t addr, size_t size,
- unsigned long attrs)
-{
- return dma_mmap_attrs(to_vmd_dev(dev), vma, cpu_addr, addr, size,
- attrs);
-}
-
-static int vmd_get_sgtable(struct device *dev, struct sg_table *sgt,
- void *cpu_addr, dma_addr_t addr, size_t size,
- unsigned long attrs)
-{
- return dma_get_sgtable_attrs(to_vmd_dev(dev), sgt, cpu_addr, addr, size,
- attrs);
-}
-
-static dma_addr_t vmd_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir,
- unsig
[PATCH v2 0/5] Clean up VMD DMA Map Ops
v1 Set: https://lore.kernel.org/linux-iommu/20200107134125.gd30...@8bytes.org/T/#t This revision introduces a new weak function to reference the dma alias, as well as using the struct device rather than the pci_dev. By using the weak function in this manner, we remove the need to add a pointer in struct device or pci_dev. Weak functions are generally frowned upon when it's a single architecture implementation, so I am open to alternatives. v1 Blurb: VMD currently works with VT-d enabled by pointing DMA and IOMMU actions at the VMD endpoint. The problem with this approach is that the VMD endpoint's device-specific attributes, such as the dma mask, are used instead. This set cleans up VMD by removing the override that redirects dma map operations to the VMD endpoint. Instead it introduces a new dma alias mechanism into the existing dma alias infrastructure. Changes from v1: Removed 1/5 & 2/5 misc fix patches that were merged Uses Christoph's staging/cleanup patches Introduce weak function rather than including pointer in struct device or pci_dev. Based on Joerg's next: https://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git/ Christoph Hellwig (2): x86/pci: Add a to_pci_sysdata helper x86/pci: Replace the vmd_domain field with a vmd_dev pointer Jon Derrick (3): PCI: Introduce direct dma alias PCI: vmd: Stop overriding dma_map_ops x86/pci: Remove X86_DEV_DMA_OPS arch/x86/Kconfig | 3 - arch/x86/include/asm/device.h | 10 --- arch/x86/include/asm/pci.h | 31 - arch/x86/pci/common.c | 45 ++-- drivers/iommu/intel-iommu.c| 17 +++-- drivers/pci/controller/Kconfig | 1 - drivers/pci/controller/vmd.c | 152 + drivers/pci/pci.c | 17 - drivers/pci/search.c | 9 +++ include/linux/pci.h| 1 + 10 files changed, 60 insertions(+), 226 deletions(-) -- 1.8.3.1 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v2 2/5] x86/pci: Replace the vmd_domain field with a vmd_dev pointer
From: Christoph Hellwig
From: Christoph Hellwig
Store the actual VMD device in struct pci_sysdata, so that we can later
use it directly for DMA mappings.
Reviewed-by: Jon Derrick
Signed-off-by: Christoph Hellwig
---
arch/x86/include/asm/pci.h | 5 ++---
drivers/pci/controller/vmd.c | 2 +-
2 files changed, 3 insertions(+), 4 deletions(-)
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index cf680c5..7c6c7d7 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -25,7 +25,7 @@ struct pci_sysdata {
void*fwnode;/* IRQ domain for MSI assignment */
#endif
#if IS_ENABLED(CONFIG_VMD)
- bool vmd_domain;/* True if in Intel VMD domain */
+ struct device *vmd_dev; /* Main device if in Intel VMD domain */
#endif
};
@@ -64,12 +64,11 @@ static inline void *_pci_root_bus_fwnode(struct pci_bus
*bus)
#if IS_ENABLED(CONFIG_VMD)
static inline bool is_vmd(struct pci_bus *bus)
{
- return to_pci_sysdata(bus)->vmd_domain;
+ return to_pci_sysdata(bus)->vmd_dev != NULL;
}
#else
#define is_vmd(bus)false
#endif /* CONFIG_VMD */
-}
/* Can be used to override the logic in pci_scan_bus for skipping
already-configured bus numbers - to be used for buggy BIOSes
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 2128422..907b5bd 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -679,7 +679,7 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned
long features)
.parent = res,
};
- sd->vmd_domain = true;
+ sd->vmd_dev = >dev->dev;
sd->domain = vmd_find_free_domain();
if (sd->domain < 0)
return sd->domain;
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v2 5/5] x86/pci: Remove X86_DEV_DMA_OPS
From: Christoph Hellwig
There are no users of X86_DEV_DMA_OPS left, so remove the code.
Reviewed-by: Jon Derrick
Signed-off-by: Christoph Hellwig
---
arch/x86/Kconfig | 3 ---
arch/x86/include/asm/device.h | 10 --
arch/x86/pci/common.c | 38 --
3 files changed, 51 deletions(-)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5e89499..77f9426 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2955,9 +2955,6 @@ config HAVE_ATOMIC_IOMAP
def_bool y
depends on X86_32
-config X86_DEV_DMA_OPS
- bool
-
source "drivers/firmware/Kconfig"
source "arch/x86/kvm/Kconfig"
diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h
index 5e12c63..7e31f7f 100644
--- a/arch/x86/include/asm/device.h
+++ b/arch/x86/include/asm/device.h
@@ -8,16 +8,6 @@ struct dev_archdata {
#endif
};
-#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS)
-struct dma_domain {
- struct list_head node;
- const struct dma_map_ops *dma_ops;
- int domain_nr;
-};
-void add_dma_domain(struct dma_domain *domain);
-void del_dma_domain(struct dma_domain *domain);
-#endif
-
struct pdev_archdata {
};
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 565cc17..5a9fb00 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -625,43 +625,6 @@ unsigned int pcibios_assign_all_busses(void)
return (pci_probe & PCI_ASSIGN_ALL_BUSSES) ? 1 : 0;
}
-#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS)
-static LIST_HEAD(dma_domain_list);
-static DEFINE_SPINLOCK(dma_domain_list_lock);
-
-void add_dma_domain(struct dma_domain *domain)
-{
- spin_lock(_domain_list_lock);
- list_add(>node, _domain_list);
- spin_unlock(_domain_list_lock);
-}
-EXPORT_SYMBOL_GPL(add_dma_domain);
-
-void del_dma_domain(struct dma_domain *domain)
-{
- spin_lock(_domain_list_lock);
- list_del(>node);
- spin_unlock(_domain_list_lock);
-}
-EXPORT_SYMBOL_GPL(del_dma_domain);
-
-static void set_dma_domain_ops(struct pci_dev *pdev)
-{
- struct dma_domain *domain;
-
- spin_lock(_domain_list_lock);
- list_for_each_entry(domain, _domain_list, node) {
- if (pci_domain_nr(pdev->bus) == domain->domain_nr) {
- pdev->dev.dma_ops = domain->dma_ops;
- break;
- }
- }
- spin_unlock(_domain_list_lock);
-}
-#else
-static void set_dma_domain_ops(struct pci_dev *pdev) {}
-#endif
-
static void set_dev_domain_options(struct pci_dev *pdev)
{
if (is_vmd(pdev->bus))
@@ -697,7 +660,6 @@ int pcibios_add_device(struct pci_dev *dev)
pa_data = data->next;
memunmap(data);
}
- set_dma_domain_ops(dev);
set_dev_domain_options(dev);
return 0;
}
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v2 3/5] PCI: Introduce direct dma alias
The current dma alias implementation requires the aliased device be on
the same bus as the dma parent. This introduces an arch-specific
mechanism to point to an arbitrary struct device when doing mapping and
pci alias search.
Signed-off-by: Jon Derrick
---
arch/x86/pci/common.c | 7 +++
drivers/pci/pci.c | 17 -
drivers/pci/search.c | 9 +
include/linux/pci.h | 1 +
4 files changed, 33 insertions(+), 1 deletion(-)
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 1e59df0..565cc17 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -736,3 +736,10 @@ int pci_ext_cfg_avail(void)
else
return 0;
}
+
+#if IS_ENABLED(CONFIG_VMD)
+struct device *pci_direct_dma_alias(struct pci_dev *dev)
+{
+ return to_pci_sysdata(dev->bus)->vmd_dev;
+}
+#endif
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index ad746d9..e4269e9 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -6034,7 +6034,9 @@ bool pci_devs_are_dma_aliases(struct pci_dev *dev1,
struct pci_dev *dev2)
return (dev1->dma_alias_mask &&
test_bit(dev2->devfn, dev1->dma_alias_mask)) ||
(dev2->dma_alias_mask &&
- test_bit(dev1->devfn, dev2->dma_alias_mask));
+ test_bit(dev1->devfn, dev2->dma_alias_mask)) ||
+ (pci_direct_dma_alias(dev1) == >dev) ||
+ (pci_direct_dma_alias(dev2) == >dev);
}
bool pci_device_is_present(struct pci_dev *pdev)
@@ -6058,6 +6060,19 @@ void pci_ignore_hotplug(struct pci_dev *dev)
}
EXPORT_SYMBOL_GPL(pci_ignore_hotplug);
+/**
+ * pci_direct_dma_alias - Get dma alias for pci device
+ * @dev: the PCI device that may have a dma alias
+ *
+ * Permits the platform to provide architecture-specific functionality to
+ * devices needing to alias dma to another device. This is the default
+ * implementation. Architecture implementations can override this.
+ */
+struct device __weak *pci_direct_dma_alias(struct pci_dev *dev)
+{
+ return NULL;
+}
+
resource_size_t __weak pcibios_default_alignment(void)
{
return 0;
diff --git a/drivers/pci/search.c b/drivers/pci/search.c
index bade140..6d61209 100644
--- a/drivers/pci/search.c
+++ b/drivers/pci/search.c
@@ -32,6 +32,15 @@ int pci_for_each_dma_alias(struct pci_dev *pdev,
struct pci_bus *bus;
int ret;
+ if (unlikely(pci_direct_dma_alias(pdev))) {
+ struct device *dev = pci_direct_dma_alias(pdev);
+
+ if (dev_is_pci(dev))
+ pdev = to_pci_dev(dev);
+ return fn(pdev, PCI_DEVID(pdev->bus->number, pdev->devfn),
+ data);
+ }
+
ret = fn(pdev, pci_dev_id(pdev), data);
if (ret)
return ret;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index c393dff..82494d3 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1202,6 +1202,7 @@ u32 pcie_bandwidth_available(struct pci_dev *dev, struct
pci_dev **limiting_dev,
int pci_select_bars(struct pci_dev *dev, unsigned long flags);
bool pci_device_is_present(struct pci_dev *pdev);
void pci_ignore_hotplug(struct pci_dev *dev);
+struct device *pci_direct_dma_alias(struct pci_dev *dev);
int __printf(6, 7) pci_request_irq(struct pci_dev *dev, unsigned int nr,
irq_handler_t handler, irq_handler_t thread_fn, void *dev_id,
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[RFC 5/5] x86/PCI: Remove unused X86_DEV_DMA_OPS
VMD was the only user of device dma operations. Now that the IOMMU has
been made aware of direct DMA aliases, VMD domain devices can reference
the VMD endpoint directly and the VMD device dma operations has been
made obsolete.
Signed-off-by: Jon Derrick
---
arch/x86/Kconfig | 3 ---
arch/x86/include/asm/device.h | 10 --
arch/x86/pci/common.c | 38 --
3 files changed, 51 deletions(-)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5e89499..77f9426 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2955,9 +2955,6 @@ config HAVE_ATOMIC_IOMAP
def_bool y
depends on X86_32
-config X86_DEV_DMA_OPS
- bool
-
source "drivers/firmware/Kconfig"
source "arch/x86/kvm/Kconfig"
diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h
index 5e12c63..7e31f7f 100644
--- a/arch/x86/include/asm/device.h
+++ b/arch/x86/include/asm/device.h
@@ -8,16 +8,6 @@ struct dev_archdata {
#endif
};
-#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS)
-struct dma_domain {
- struct list_head node;
- const struct dma_map_ops *dma_ops;
- int domain_nr;
-};
-void add_dma_domain(struct dma_domain *domain);
-void del_dma_domain(struct dma_domain *domain);
-#endif
-
struct pdev_archdata {
};
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 4022609..fcf03da 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -625,43 +625,6 @@ unsigned int pcibios_assign_all_busses(void)
return (pci_probe & PCI_ASSIGN_ALL_BUSSES) ? 1 : 0;
}
-#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS)
-static LIST_HEAD(dma_domain_list);
-static DEFINE_SPINLOCK(dma_domain_list_lock);
-
-void add_dma_domain(struct dma_domain *domain)
-{
- spin_lock(_domain_list_lock);
- list_add(>node, _domain_list);
- spin_unlock(_domain_list_lock);
-}
-EXPORT_SYMBOL_GPL(add_dma_domain);
-
-void del_dma_domain(struct dma_domain *domain)
-{
- spin_lock(_domain_list_lock);
- list_del(>node);
- spin_unlock(_domain_list_lock);
-}
-EXPORT_SYMBOL_GPL(del_dma_domain);
-
-static void set_dma_domain_ops(struct pci_dev *pdev)
-{
- struct dma_domain *domain;
-
- spin_lock(_domain_list_lock);
- list_for_each_entry(domain, _domain_list, node) {
- if (pci_domain_nr(pdev->bus) == domain->domain_nr) {
- pdev->dev.dma_ops = domain->dma_ops;
- break;
- }
- }
- spin_unlock(_domain_list_lock);
-}
-#else
-static void set_dma_domain_ops(struct pci_dev *pdev) {}
-#endif
-
static void set_dev_domain_options(struct pci_dev *pdev)
{
if (is_vmd(pdev->bus)) {
@@ -701,7 +664,6 @@ int pcibios_add_device(struct pci_dev *dev)
pa_data = data->next;
memunmap(data);
}
- set_dma_domain_ops(dev);
set_dev_domain_options(dev);
return 0;
}
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[RFC 2/5] iommu/vt-d: Unlink device if failed to add to group
If the device fails to be added to the group, make sure to unlink the
reference before returning.
Signed-off-by: Jon Derrick
---
drivers/iommu/intel-iommu.c | 13 ++---
1 file changed, 10 insertions(+), 3 deletions(-)
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index b2526a4..978d502 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -5625,8 +5625,10 @@ static int intel_iommu_add_device(struct device *dev)
group = iommu_group_get_for_dev(dev);
- if (IS_ERR(group))
- return PTR_ERR(group);
+ if (IS_ERR(group)) {
+ ret = PTR_ERR(group);
+ goto unlink;
+ }
iommu_group_put(group);
@@ -5652,7 +5654,8 @@ static int intel_iommu_add_device(struct device *dev)
if (!get_private_domain_for_dev(dev)) {
dev_warn(dev,
"Failed to get a private
domain.\n");
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto unlink;
}
dev_info(dev,
@@ -5667,6 +5670,10 @@ static int intel_iommu_add_device(struct device *dev)
}
return 0;
+
+unlink:
+ iommu_device_unlink(>iommu, dev);
+ return ret;
}
static void intel_iommu_remove_device(struct device *dev)
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[RFC 3/5] x86/PCI: Expose VMD's device in pci_sysdata
To be used by intel-iommu code to find the correct domain.
Signed-off-by: Jon Derrick
---
arch/x86/include/asm/pci.h | 4 ++--
drivers/pci/controller/vmd.c | 2 +-
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 90d0731..7656807 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -25,7 +25,7 @@ struct pci_sysdata {
void*fwnode;/* IRQ domain for MSI assignment */
#endif
#if IS_ENABLED(CONFIG_VMD)
- bool vmd_domain;/* True if in Intel VMD domain */
+ struct device *vmd_dev; /* Non-null if in Intel VMD domain */
#endif
};
@@ -65,7 +65,7 @@ static inline bool is_vmd(struct pci_bus *bus)
#if IS_ENABLED(CONFIG_VMD)
struct pci_sysdata *sd = bus->sysdata;
- return sd->vmd_domain;
+ return !!sd->vmd_dev;
#else
return false;
#endif
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 2128422..907b5bd 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -679,7 +679,7 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned
long features)
.parent = res,
};
- sd->vmd_domain = true;
+ sd->vmd_dev = >dev->dev;
sd->domain = vmd_find_free_domain();
if (sd->domain < 0)
return sd->domain;
--
1.8.3.1
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[RFC 1/5] iommu: Remove device link to group on failure
This adds the missing teardown step that removes the device link from the group when the device addition fails. Signed-off-by: Jon Derrick --- drivers/iommu/iommu.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index d5174f0..3e35284 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -768,6 +768,7 @@ int iommu_group_add_device(struct iommu_group *group, struct device *dev) mutex_unlock(>mutex); dev->iommu_group = NULL; kobject_put(group->devices_kobj); + sysfs_remove_link(group->devices_kobj, device->name); err_free_name: kfree(device->name); err_remove_link: -- 1.8.3.1 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[RFC 0/5] Clean up VMD DMA Map Ops
Inspired by Christoph's last set: https://lkml.org/lkml/2019/8/28/667 VMD currently works with VT-d enabled by pointing DMA and IOMMU actions at the VMD endpoint. The problem with this approach is that the VMD endpoint's device-specific attributes, such as the dma mask, are used instead. This set cleans up VMD by removing the override that redirects dma map operations to the VMD endpoint. Instead it introduces a new dma alias mechanism into the existing dma alias infrastructure. Patch 1 and 2 are miscellaneous fixes discovered during development. Patch 1 is ready, but 2 likely doesn't go far enough for proper teardown on addition failure. Jon Derrick (5): iommu: Remove device link to group on failure iommu/vt-d: Unlink device if failed to add to group x86/PCI: Expose VMD's device in pci_sysdata PCI: vmd: Stop overriding dma_map_ops x86/PCI: Remove unused X86_DEV_DMA_OPS arch/x86/Kconfig | 3 - arch/x86/include/asm/device.h | 10 --- arch/x86/include/asm/pci.h | 4 +- arch/x86/pci/common.c | 44 ++-- drivers/iommu/intel-iommu.c| 26 --- drivers/iommu/iommu.c | 1 + drivers/pci/controller/Kconfig | 1 - drivers/pci/controller/vmd.c | 152 + drivers/pci/pci.c | 4 +- drivers/pci/search.c | 6 ++ include/linux/pci.h| 1 + 11 files changed, 37 insertions(+), 215 deletions(-) -- 1.8.3.1 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[RFC 4/5] PCI: vmd: Stop overriding dma_map_ops
Devices on the VMD domain use the VMD endpoint's requester-id and have
been relying on the VMD endpoint's dma operations. The downside of this
was that VMD domain devices would use the VMD endpoint's attributes when
doing DMA and IOMMU mapping. We can be smarter about this by only using
the VMD endpoint when mapping and providing the correct child device's
attributes during dma operations.
This patch adds a new dma alias mechanism by adding a hint to a pci_dev
to point to a singular DMA requester's pci_dev. This integrates into the
existing dma alias infrastructure to reduce the impact of the changes
required to support this mode.
Signed-off-by: Jon Derrick
---
arch/x86/pci/common.c | 6 +-
drivers/iommu/intel-iommu.c| 13 ++--
drivers/pci/controller/Kconfig | 1 -
drivers/pci/controller/vmd.c | 150 -
drivers/pci/pci.c | 4 +-
drivers/pci/search.c | 6 ++
include/linux/pci.h| 1 +
7 files changed, 23 insertions(+), 158 deletions(-)
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 1e59df0..4022609 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -664,8 +664,12 @@ static void set_dma_domain_ops(struct pci_dev *pdev) {}
static void set_dev_domain_options(struct pci_dev *pdev)
{
- if (is_vmd(pdev->bus))
+ if (is_vmd(pdev->bus)) {
+ struct pci_sysdata *sd = pdev->bus->sysdata;
+
+ pdev->dma_parent = to_pci_dev(sd->vmd_dev);
pdev->hotplug_user_indicators = 1;
+ }
}
int pcibios_add_device(struct pci_dev *dev)
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 978d502..5aee648 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -776,11 +776,8 @@ static struct intel_iommu *device_to_iommu(struct device
*dev, u8 *bus, u8 *devf
pdev = to_pci_dev(dev);
-#ifdef CONFIG_X86
- /* VMD child devices currently cannot be handled individually */
- if (is_vmd(pdev->bus))
- return NULL;
-#endif
+ if (pdev->dma_parent)
+ pdev = pdev->dma_parent;
/* VFs aren't listed in scope tables; we need to look up
* the PF instead to find the IOMMU. */
@@ -2428,6 +2425,12 @@ static struct dmar_domain *find_domain(struct device
*dev)
dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO))
return NULL;
+ if (dev_is_pci(dev)) {
+ struct pci_dev *pdev = to_pci_dev(dev);
+ if (pdev->dma_parent)
+ dev = >dma_parent->dev;
+ }
+
/* No lock here, assumes no domain exit in normal case */
info = dev->archdata.iommu;
if (likely(info))
diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig
index c77069c..55671429 100644
--- a/drivers/pci/controller/Kconfig
+++ b/drivers/pci/controller/Kconfig
@@ -239,7 +239,6 @@ config PCIE_TANGO_SMP8759
config VMD
depends on PCI_MSI && X86_64 && SRCU
- select X86_DEV_DMA_OPS
tristate "Intel Volume Management Device Driver"
---help---
Adds support for the Intel Volume Management Device (VMD). VMD is a
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 907b5bd..5824a39 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -98,9 +98,6 @@ struct vmd_dev {
struct irq_domain *irq_domain;
struct pci_bus *bus;
u8 busn_start;
-
- struct dma_map_ops dma_ops;
- struct dma_domain dma_domain;
};
static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus)
@@ -295,151 +292,6 @@ static void vmd_set_desc(msi_alloc_info_t *arg, struct
msi_desc *desc)
.chip = _msi_controller,
};
-/*
- * VMD replaces the requester ID with its own. DMA mappings for devices in a
- * VMD domain need to be mapped for the VMD, not the device requiring
- * the mapping.
- */
-static struct device *to_vmd_dev(struct device *dev)
-{
- struct pci_dev *pdev = to_pci_dev(dev);
- struct vmd_dev *vmd = vmd_from_bus(pdev->bus);
-
- return >dev->dev;
-}
-
-static void *vmd_alloc(struct device *dev, size_t size, dma_addr_t *addr,
- gfp_t flag, unsigned long attrs)
-{
- return dma_alloc_attrs(to_vmd_dev(dev), size, addr, flag, attrs);
-}
-
-static void vmd_free(struct device *dev, size_t size, void *vaddr,
-dma_addr_t addr, unsigned long attrs)
-{
- return dma_free_attrs(to_vmd_dev(dev), size, vaddr, addr, attrs);
-}
-
-static int vmd_mmap(struct device *dev, struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t addr, size_t size,
- unsigned l
[PATCH v3] iommu: Prevent VMD child devices from being remapping targets
VMD child devices must use the VMD endpoint's ID as the requester. Because of this, there needs to be a way to link the parent VMD endpoint's iommu group and associated mappings to the VMD child devices such that attaching and detaching child devices modify the endpoint's mappings, while preventing early detaching on a singular device removal or unbinding. The reassignment of individual VMD child devices devices to VMs is outside the scope of VMD, but may be implemented in the future. For now it is best to prevent any such attempts. This patch prevents VMD child devices from returning an IOMMU, which prevents it from exposing an iommu_group sysfs directories and allowing subsequent binding by userspace-access drivers such as VFIO. Signed-off-by: Jon Derrick <jonathan.derr...@intel.com> --- v2->3, wrapped in x86 ifdef to avoid ia64 compilation errors drivers/iommu/intel-iommu.c | 7 +++ 1 file changed, 7 insertions(+) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 687f18f..2800a6e 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -901,6 +901,13 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf struct pci_dev *pf_pdev; pdev = to_pci_dev(dev); + +#ifdef CONFIG_X86 + /* VMD child devices currently cannot be handled individually */ + if (is_vmd(pdev->bus)) + return NULL; +#endif + /* VFs aren't listed in scope tables; we need to look up * the PF instead to find the IOMMU. */ pf_pdev = pci_physfn(pdev); -- 1.8.3.1 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v2 4/4] iommu: Prevent VMD child devices from being remapping targets
VMD child devices must use the VMD endpoint's ID as the requester. Because of this, there needs to be a way to link the parent VMD endpoint's iommu group and associated mappings to the VMD child devices such that attaching and detaching child devices modify the endpoint's mappings, while preventing early detaching on a singular device removal or unbinding. The reassignment of individual VMD child devices devices to VMs is outside the scope of VMD, but may be implemented in the future. For now it is best to prevent any such attempts. This patch prevents VMD child devices from returning an IOMMU, which prevents it from exposing an iommu_group sysfs directories and allowing subsequent binding by userspace-access drivers such as VFIO. Signed-off-by: Jon Derrick <jonathan.derr...@intel.com> --- drivers/iommu/intel-iommu.c | 5 + 1 file changed, 5 insertions(+) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 687f18f..94353a6e 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -901,6 +901,11 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf struct pci_dev *pf_pdev; pdev = to_pci_dev(dev); + + /* VMD child devices currently cannot be handled individually */ + if (is_vmd(pdev->bus)) + return NULL; + /* VFs aren't listed in scope tables; we need to look up * the PF instead to find the IOMMU. */ pf_pdev = pci_physfn(pdev); -- 2.9.4 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v2 0/4] VMD fixups
Mostly just cleanup in this revision, eg, trying to limit scope of vmd code to x86 Previous: https://patchwork.kernel.org/patch/9886095/ https://patchwork.kernel.org/patch/9886097/ https://patchwork.kernel.org/patch/9886101/ Jon Derrick (4): MAINTAINERS: Add Jonathan Derrick as VMD maintainer pci/x86: Move VMD quirks to x86 fixups x86/PCI: Use is_vmd rather than relying on the domain number iommu: Prevent VMD child devices from being remapping targets MAINTAINERS | 1 + arch/x86/pci/fixup.c| 18 ++ drivers/iommu/intel-iommu.c | 5 + drivers/pci/quirks.c| 17 - 4 files changed, 24 insertions(+), 17 deletions(-) -- 2.9.4 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v2 3/4] x86/PCI: Use is_vmd rather than relying on the domain number
Signed-off-by: Jon Derrick <jonathan.derr...@intel.com>
---
arch/x86/pci/fixup.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index ca4b02e5..1ed2fbf 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -628,7 +628,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8c10,
quirk_apple_mbp_poweroff);
static void quirk_no_aersid(struct pci_dev *pdev)
{
/* VMD Domain */
- if (pdev->bus->sysdata && pci_domain_nr(pdev->bus) >= 0x1)
+ if (is_vmd(pdev->bus))
pdev->bus->bus_flags |= PCI_BUS_FLAGS_NO_AERSID;
}
DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2030, quirk_no_aersid);
--
2.9.4
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v2 2/4] pci/x86: Move VMD quirks to x86 fixups
VMD currently only exists for Intel x86 products
Signed-off-by: Jon Derrick <jonathan.derr...@intel.com>
---
arch/x86/pci/fixup.c | 18 ++
drivers/pci/quirks.c | 17 -
2 files changed, 18 insertions(+), 17 deletions(-)
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index 11e4074..ca4b02e5 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -618,3 +618,21 @@ static void quirk_apple_mbp_poweroff(struct pci_dev *pdev)
dev_info(dev, "can't work around MacBook Pro poweroff issue\n");
}
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8c10,
quirk_apple_mbp_poweroff);
+
+/*
+ * VMD-enabled root ports will change the source ID for all messages
+ * to the VMD device. Rather than doing device matching with the source
+ * ID, the AER driver should traverse the child device tree, reading
+ * AER registers to find the faulting device.
+ */
+static void quirk_no_aersid(struct pci_dev *pdev)
+{
+ /* VMD Domain */
+ if (pdev->bus->sysdata && pci_domain_nr(pdev->bus) >= 0x1)
+ pdev->bus->bus_flags |= PCI_BUS_FLAGS_NO_AERSID;
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2030, quirk_no_aersid);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2031, quirk_no_aersid);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2032, quirk_no_aersid);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2033, quirk_no_aersid);
+
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index f1c9852..073baba 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -4671,23 +4671,6 @@ static void quirk_intel_qat_vf_cap(struct pci_dev *pdev)
}
DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x443, quirk_intel_qat_vf_cap);
-/*
- * VMD-enabled root ports will change the source ID for all messages
- * to the VMD device. Rather than doing device matching with the source
- * ID, the AER driver should traverse the child device tree, reading
- * AER registers to find the faulting device.
- */
-static void quirk_no_aersid(struct pci_dev *pdev)
-{
- /* VMD Domain */
- if (pdev->bus->sysdata && pci_domain_nr(pdev->bus) >= 0x1)
- pdev->bus->bus_flags |= PCI_BUS_FLAGS_NO_AERSID;
-}
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2030, quirk_no_aersid);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2031, quirk_no_aersid);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2032, quirk_no_aersid);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2033, quirk_no_aersid);
-
/* FLR may cause some 82579 devices to hang. */
static void quirk_intel_no_flr(struct pci_dev *dev)
{
--
2.9.4
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v2 1/4] MAINTAINERS: Add Jonathan Derrick as VMD maintainer
Add myself as VMD maintainer Signed-off-by: Jon Derrick <jonathan.derr...@intel.com> Acked-by: Keith Busch <keith.bu...@intel.com> --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index f66488d..3ec39df 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10090,6 +10090,7 @@ F: drivers/pci/dwc/*imx6* PCI DRIVER FOR INTEL VOLUME MANAGEMENT DEVICE (VMD) M: Keith Busch <keith.bu...@intel.com> +M: Jonathan Derrick <jonathan.derr...@intel.com> L: linux-...@vger.kernel.org S: Supported F: drivers/pci/host/vmd.c -- 2.9.4 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
Re: [PATCH 3/3] iommu: prevent VMD child devices from being remapping targets
Hi Robin, thanks for the reply. On 08/11/2017 12:25 PM, Robin Murphy wrote: > On 07/08/17 20:57, Jon Derrick wrote: >> VMD child devices must use the VMD endpoint's ID as the DMA source. >> Because of this, there needs to be a way to link the parent VMD >> endpoint's DMAR domain to the VMD child devices' DMAR domain such that >> attaching and detaching child devices modify the endpoint's DMAR mapping >> and prevents early detaching. > > That sounds like either pci_device_group() needs modifying, or perhaps > that intel-iommu needs its own extended iommu_ops::device_group > implementation, to ensure that VMD child devices get put in the same > group as their parent - if they share requester IDs they can't feasibly > be attached to different domains anyway. > > Robin. Yes it seems like that to me too. I have a high-level understanding of the changes required but not too much in the nitty-gritty details. It's a bit more complicated anyways because VMD emerges a set of root ports, and AFAICT, PCI ACS end at the root ports and iommu groups rely on ACS to group devices. Either way it's not within the scope of VMD. ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
Re: [PATCH 2/3] pci: Generalize is_vmd behavior
On 08/11/2017 11:03 AM, Bjorn Helgaas wrote:
> On Mon, Aug 07, 2017 at 01:57:12PM -0600, Jon Derrick wrote:
>> Generalize is_vmd behavior to remove dependency on domain number
>> checking in pci quirks.
>>
>> Signed-off-by: Jon Derrick <jonathan.derr...@intel.com>
>> ---
>> arch/x86/include/asm/pci.h | 8 +++-
>> arch/x86/pci/common.c | 2 +-
>> drivers/pci/quirks.c | 2 +-
>> include/linux/pci.h| 4
>> 4 files changed, 9 insertions(+), 7 deletions(-)
>>
>> diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
>> index 473a729..5c5d54a 100644
>> --- a/arch/x86/include/asm/pci.h
>> +++ b/arch/x86/include/asm/pci.h
>> @@ -60,16 +60,14 @@ static inline void *_pci_root_bus_fwnode(struct pci_bus
>> *bus)
>> #define pci_root_bus_fwnode _pci_root_bus_fwnode
>> #endif
>>
>> -static inline bool is_vmd(struct pci_bus *bus)
>> -{
>> #if IS_ENABLED(CONFIG_VMD)
>> +static inline bool pci_bus_is_vmd(struct pci_bus *bus)
>> +{
>> struct pci_sysdata *sd = bus->sysdata;
>>
>> return sd->vmd_domain;
>> -#else
>> -return false;
>> -#endif
>> }
>> +#endif
>>
>> /* Can be used to override the logic in pci_scan_bus for skipping
>> already-configured bus numbers - to be used for buggy BIOSes
>> diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
>> index dbe2132..18b2277 100644
>> --- a/arch/x86/pci/common.c
>> +++ b/arch/x86/pci/common.c
>> @@ -662,7 +662,7 @@ static void set_dma_domain_ops(struct pci_dev *pdev) {}
>>
>> static void set_dev_domain_options(struct pci_dev *pdev)
>> {
>> -if (is_vmd(pdev->bus))
>> +if (pci_bus_is_vmd(pdev->bus))
>> pdev->hotplug_user_indicators = 1;
>> }
>>
>> diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
>> index 6967c6b..ba47995 100644
>> --- a/drivers/pci/quirks.c
>> +++ b/drivers/pci/quirks.c
>> @@ -4666,7 +4666,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x443,
>> quirk_intel_qat_vf_cap);
>> static void quirk_no_aersid(struct pci_dev *pdev)
>> {
>> /* VMD Domain */
>> -if (pdev->bus->sysdata && pci_domain_nr(pdev->bus) >= 0x1)
>> +if (pci_bus_is_vmd(pdev->bus))
>
> I like this part ...
>
>> pdev->bus->bus_flags |= PCI_BUS_FLAGS_NO_AERSID;
>> }
>> DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2030, quirk_no_aersid);
>> diff --git a/include/linux/pci.h b/include/linux/pci.h
>> index 4869e66..0299d8b 100644
>> --- a/include/linux/pci.h
>> +++ b/include/linux/pci.h
>> @@ -1471,6 +1471,10 @@ static inline int pci_proc_domain(struct pci_bus
>> *bus) { return 0; }
>> static inline int pci_get_new_domain_nr(void) { return -ENOSYS; }
>> #endif /* CONFIG_PCI_DOMAINS */
>>
>> +#if !IS_ENABLED(CONFIG_VMD)
>> +static inline bool pci_bus_is_vmd(struct pci_bus *bus) { return false; }
>> +#endif
>
> But not so much this part. VMD is (AFAIK) still fundamentally an
> x86-only thing, so I'd like it better if this could all be within
> arch/x86. Could this be done by moving quirk_no_aersid() to
> arch/x86/pci/fixup.c?
>
Thanks for pointing this out. I'll think of something different and
localize it to the x86 code domain.
> BTW, CONFIG_VMD in drivers/pci/host/Kconfig is currently "depends on
> SRCU". I'm not a Kconfig expert, but that doesn't seem like an
> intuitive connection. And it's the only such dependency on SRCU in
> the tree -- most other places use "select SRCU", which makes more
> sense to me.
I agree - most places use select SRCU. I'll add that to v2.
>
>> /*
>> * Generic implementation for PCI domain support. If your
>> * architecture does not need custom management of PCI
>> --
>> 2.9.4
>>
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH 3/3] iommu: prevent VMD child devices from being remapping targets
VMD child devices must use the VMD endpoint's ID as the DMA source. Because of this, there needs to be a way to link the parent VMD endpoint's DMAR domain to the VMD child devices' DMAR domain such that attaching and detaching child devices modify the endpoint's DMAR mapping and prevents early detaching. This is outside the scope of VMD, so disable binding child devices to prevent unforeseen issues. This functionality may be implemented in the future. This patch prevents VMD child devices from returning an IOMMU, which prevents it from exposing iommu_group sysfs directories and subsequent binding by userspace-access drivers such as VFIO. Signed-off-by: Jon Derrick <jonathan.derr...@intel.com> --- drivers/iommu/intel-iommu.c | 5 + 1 file changed, 5 insertions(+) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 687f18f..651a6cd 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -905,6 +905,11 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf * the PF instead to find the IOMMU. */ pf_pdev = pci_physfn(pdev); dev = _pdev->dev; + + /* VMD child devices currently cannot be handled individually */ + if (pci_bus_is_vmd(pdev->bus)) + return NULL; + segment = pci_domain_nr(pdev->bus); } else if (has_acpi_companion(dev)) dev = _COMPANION(dev)->dev; -- 2.9.4 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH 1/3] MAINTAINERS: Add Jonathan Derrick as VMD maintainer
Add myself as VMD maintainer Signed-off-by: Jon Derrick <jonathan.derr...@intel.com> --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index f66488d..3ec39df 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10090,6 +10090,7 @@ F: drivers/pci/dwc/*imx6* PCI DRIVER FOR INTEL VOLUME MANAGEMENT DEVICE (VMD) M: Keith Busch <keith.bu...@intel.com> +M: Jonathan Derrick <jonathan.derr...@intel.com> L: linux-...@vger.kernel.org S: Supported F: drivers/pci/host/vmd.c -- 2.9.4 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH 2/3] pci: Generalize is_vmd behavior
Generalize is_vmd behavior to remove dependency on domain number
checking in pci quirks.
Signed-off-by: Jon Derrick <jonathan.derr...@intel.com>
---
arch/x86/include/asm/pci.h | 8 +++-
arch/x86/pci/common.c | 2 +-
drivers/pci/quirks.c | 2 +-
include/linux/pci.h| 4
4 files changed, 9 insertions(+), 7 deletions(-)
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 473a729..5c5d54a 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -60,16 +60,14 @@ static inline void *_pci_root_bus_fwnode(struct pci_bus
*bus)
#define pci_root_bus_fwnode_pci_root_bus_fwnode
#endif
-static inline bool is_vmd(struct pci_bus *bus)
-{
#if IS_ENABLED(CONFIG_VMD)
+static inline bool pci_bus_is_vmd(struct pci_bus *bus)
+{
struct pci_sysdata *sd = bus->sysdata;
return sd->vmd_domain;
-#else
- return false;
-#endif
}
+#endif
/* Can be used to override the logic in pci_scan_bus for skipping
already-configured bus numbers - to be used for buggy BIOSes
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index dbe2132..18b2277 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -662,7 +662,7 @@ static void set_dma_domain_ops(struct pci_dev *pdev) {}
static void set_dev_domain_options(struct pci_dev *pdev)
{
- if (is_vmd(pdev->bus))
+ if (pci_bus_is_vmd(pdev->bus))
pdev->hotplug_user_indicators = 1;
}
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 6967c6b..ba47995 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -4666,7 +4666,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x443,
quirk_intel_qat_vf_cap);
static void quirk_no_aersid(struct pci_dev *pdev)
{
/* VMD Domain */
- if (pdev->bus->sysdata && pci_domain_nr(pdev->bus) >= 0x1)
+ if (pci_bus_is_vmd(pdev->bus))
pdev->bus->bus_flags |= PCI_BUS_FLAGS_NO_AERSID;
}
DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2030, quirk_no_aersid);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 4869e66..0299d8b 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1471,6 +1471,10 @@ static inline int pci_proc_domain(struct pci_bus *bus) {
return 0; }
static inline int pci_get_new_domain_nr(void) { return -ENOSYS; }
#endif /* CONFIG_PCI_DOMAINS */
+#if !IS_ENABLED(CONFIG_VMD)
+static inline bool pci_bus_is_vmd(struct pci_bus *bus) { return false; }
+#endif
+
/*
* Generic implementation for PCI domain support. If your
* architecture does not need custom management of PCI
--
2.9.4
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
