* [PATCH 1/5] iommu/vt-d: Setup scalable mode context entry in probe path
2023-11-20 11:29 [PATCH 0/5] iommu/vt-d: Convert to use static identity domain Lu Baolu
@ 2023-11-20 11:29 ` Lu Baolu
2023-11-20 11:29 ` [PATCH 2/5] iommu/vt-d: Remove scalable mode context entry setup from attach_dev Lu Baolu
` (3 subsequent siblings)
4 siblings, 0 replies; 9+ messages in thread
From: Lu Baolu @ 2023-11-20 11:29 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Robin Murphy, Jason Gunthorpe, Kevin Tian
Cc: iommu, linux-kernel, Lu Baolu
In contrast to legacy mode, the DMA translation table is configured in
the PASID table entry instead of the context entry for scalable mode.
For this reason, it is more appropriate to set up the scalable mode
context entry in the device_probe callback and direct it to the
appropriate PASID table.
The iommu domain attach/detach operations only affect the PASID table
entry. Therefore, there is no need to modify the context entry when
configuring the translation type and page table.
The only exception is the kdump case, where context entry setup is
postponed until the device driver invokes the first DMA interface.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
drivers/iommu/intel/pasid.h | 1 +
drivers/iommu/intel/iommu.c | 17 +++-
drivers/iommu/intel/pasid.c | 180 ++++++++++++++++++++++++++++++++++++
3 files changed, 195 insertions(+), 3 deletions(-)
diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h
index 8d40d4c66e31..58d7049081b9 100644
--- a/drivers/iommu/intel/pasid.h
+++ b/drivers/iommu/intel/pasid.h
@@ -319,4 +319,5 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
bool fault_ignore);
void intel_pasid_setup_page_snoop_control(struct intel_iommu *iommu,
struct device *dev, u32 pasid);
+int intel_pasid_setup_sm_context(struct device *dev, bool deferred);
#endif /* __INTEL_PASID_H */
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 5092330f6a10..e34a32cd2b9a 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -4270,15 +4270,26 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
ret = intel_pasid_alloc_table(dev);
if (ret) {
dev_err(dev, "PASID table allocation failed\n");
- dev_iommu_priv_set(dev, NULL);
- kfree(info);
- return ERR_PTR(ret);
+ goto err_clear_priv;
+ }
+
+ ret = intel_pasid_setup_sm_context(dev, false);
+ if (ret) {
+ dev_err(dev, "Scalable context entry setup failed\n");
+ goto err_free_table;
}
}
intel_iommu_debugfs_create_dev(info);
return &iommu->iommu;
+err_free_table:
+ intel_pasid_free_table(dev);
+err_clear_priv:
+ dev_iommu_priv_set(dev, NULL);
+ kfree(info);
+
+return ERR_PTR(ret);
}
static void intel_iommu_release_device(struct device *dev)
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index 3239cefa4c33..9e505060617a 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -304,6 +304,11 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu,
return -EINVAL;
}
+ if (intel_pasid_setup_sm_context(dev, true)) {
+ dev_err(dev, "Context entry is not configured\n");
+ return -ENODEV;
+ }
+
spin_lock(&iommu->lock);
pte = intel_pasid_get_entry(dev, pasid);
if (!pte) {
@@ -384,6 +389,11 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
return -EINVAL;
}
+ if (intel_pasid_setup_sm_context(dev, true)) {
+ dev_err(dev, "Context entry is not configured\n");
+ return -ENODEV;
+ }
+
pgd = domain->pgd;
agaw = iommu_skip_agaw(domain, iommu, &pgd);
if (agaw < 0) {
@@ -505,6 +515,11 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
u16 did = FLPT_DEFAULT_DID;
struct pasid_entry *pte;
+ if (intel_pasid_setup_sm_context(dev, true)) {
+ dev_err(dev, "Context entry is not configured\n");
+ return -ENODEV;
+ }
+
spin_lock(&iommu->lock);
pte = intel_pasid_get_entry(dev, pasid);
if (!pte) {
@@ -623,6 +638,11 @@ int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
return -EINVAL;
}
+ if (intel_pasid_setup_sm_context(dev, true)) {
+ dev_err_ratelimited(dev, "Context entry is not configured\n");
+ return -ENODEV;
+ }
+
spin_lock(&iommu->lock);
pte = intel_pasid_get_entry(dev, pasid);
if (!pte) {
@@ -666,3 +686,163 @@ int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
return 0;
}
+
+/*
+ * Interface to set a pasid table to the scalable mode context table entry:
+ */
+
+/*
+ * Get the PASID directory size for scalable mode context entry.
+ * Value of X in the PDTS field of a scalable mode context entry
+ * indicates PASID directory with 2^(X + 7) entries.
+ */
+static unsigned long context_get_sm_pds(struct pasid_table *table)
+{
+ unsigned long pds, max_pde;
+
+ max_pde = table->max_pasid >> PASID_PDE_SHIFT;
+ pds = find_first_bit(&max_pde, MAX_NR_PASID_BITS);
+ if (pds < 7)
+ return 0;
+
+ return pds - 7;
+}
+
+static int context_entry_set_pasid_table(struct context_entry *context,
+ struct device *dev)
+{
+ struct device_domain_info *info = dev_iommu_priv_get(dev);
+ struct pasid_table *table = info->pasid_table;
+ struct intel_iommu *iommu = info->iommu;
+ unsigned long pds;
+
+ context_clear_entry(context);
+
+ pds = context_get_sm_pds(table);
+ context->lo = (u64)virt_to_phys(table->table) | context_pdts(pds);
+ context_set_sm_rid2pasid(context, IOMMU_NO_PASID);
+
+ if (info->ats_supported)
+ context_set_sm_dte(context);
+ if (info->pri_supported)
+ context_set_sm_pre(context);
+ if (info->pasid_supported)
+ context_set_pasid(context);
+
+ context_set_fault_enable(context);
+ context_set_present(context);
+ if (!ecap_coherent(iommu->ecap))
+ clflush_cache_range(context, sizeof(*context));
+
+ return 0;
+}
+
+static int device_pasid_table_setup(struct device *dev, u8 bus, u8 devfn)
+{
+ struct device_domain_info *info = dev_iommu_priv_get(dev);
+ struct intel_iommu *iommu = info->iommu;
+ struct context_entry *context;
+ int ret = 0;
+
+ spin_lock(&iommu->lock);
+ context = iommu_context_addr(iommu, bus, devfn, true);
+ if (!context) {
+ ret = -ENOMEM;
+ goto out_unlock;
+ }
+
+ if (context_present(context) && !context_copied(iommu, bus, devfn))
+ goto out_unlock;
+
+ /*
+ * Cache invalidation for changes to a scalable-mode context table
+ * entry.
+ *
+ * Section 6.5.3.3 of the VT-d spec:
+ * - Device-selective context-cache invalidation;
+ * - Domain-selective PASID-cache invalidation to affected domains
+ * (can be skipped if all PASID entries were not-present);
+ * - Domain-selective IOTLB invalidation to affected domains;
+ * - Global Device-TLB invalidation to affected functions.
+ *
+ * For kdump cases, old valid entries may be cached due to the
+ * in-flight DMA and copied pgtable, but there is no unmapping
+ * behaviour for them, thus we need explicit cache flushes for all
+ * affected domain IDs and PASIDs used in the copied PASID table.
+ * Given that we have no idea about which domain IDs and PASIDs were
+ * used in the copied tables, upgrade them to global PASID and IOTLB
+ * cache invalidation.
+ *
+ * For kdump case, at this point, the device is supposed to finish
+ * reset at its driver probe stage, so no in-flight DMA will exist,
+ * and we don't need to worry anymore hereafter.
+ */
+ if (context_copied(iommu, bus, devfn)) {
+ context_clear_entry(context);
+ clear_context_copied(iommu, bus, devfn);
+ iommu->flush.flush_context(iommu, 0,
+ (((u16)bus) << 8) | devfn,
+ DMA_CCMD_MASK_NOBIT,
+ DMA_CCMD_DEVICE_INVL);
+ qi_flush_pasid_cache(iommu, 0, QI_PC_GLOBAL, 0);
+ iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
+ devtlb_invalidation_with_pasid(iommu, dev, IOMMU_NO_PASID);
+ }
+
+ context_entry_set_pasid_table(context, dev);
+
+ /*
+ * It's a non-present to present mapping. If hardware doesn't cache
+ * non-present entry we only need to flush the write-buffer. If the
+ * _does_ cache non-present entries, then it does so in the special
+ * domain ID #0, which we have to flush:
+ */
+ if (cap_caching_mode(iommu->cap)) {
+ iommu->flush.flush_context(iommu, 0,
+ (((u16)bus) << 8) | devfn,
+ DMA_CCMD_MASK_NOBIT,
+ DMA_CCMD_DEVICE_INVL);
+ iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
+ } else {
+ iommu_flush_write_buffer(iommu);
+ }
+
+out_unlock:
+ spin_unlock(&iommu->lock);
+ return ret;
+}
+
+static int pci_pasid_table_setup(struct pci_dev *pdev, u16 alias, void *data)
+{
+ struct device *dev = data;
+
+ if (dev != &pdev->dev)
+ return 0;
+
+ return device_pasid_table_setup(dev, PCI_BUS_NUM(alias), alias & 0xff);
+}
+
+/*
+ * Set the device's PASID table to its context table entry.
+ *
+ * The PASID table is set to the context entries of both device itself
+ * and its alias requester ID for DMA. If it is called in domain attach
+ * paths, set @deferred to true, false in other cases.
+ */
+int intel_pasid_setup_sm_context(struct device *dev, bool deferred)
+{
+ struct device_domain_info *info = dev_iommu_priv_get(dev);
+ struct intel_iommu *iommu = info->iommu;
+
+ /*
+ * Skip pasid table setting up if context entry is copied and
+ * function is not called in deferred attachment context.
+ */
+ if (deferred ^ context_copied(iommu, info->bus, info->devfn))
+ return 0;
+
+ if (!dev_is_pci(dev))
+ return device_pasid_table_setup(dev, info->bus, info->devfn);
+
+ return pci_for_each_dma_alias(to_pci_dev(dev), pci_pasid_table_setup, dev);
+}
--
2.34.1
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH 2/5] iommu/vt-d: Remove scalable mode context entry setup from attach_dev
2023-11-20 11:29 [PATCH 0/5] iommu/vt-d: Convert to use static identity domain Lu Baolu
2023-11-20 11:29 ` [PATCH 1/5] iommu/vt-d: Setup scalable mode context entry in probe path Lu Baolu
@ 2023-11-20 11:29 ` Lu Baolu
2023-11-20 11:29 ` [PATCH 3/5] iommu/vt-d: Refactor domain_context_mapping_one() to be reusable Lu Baolu
` (2 subsequent siblings)
4 siblings, 0 replies; 9+ messages in thread
From: Lu Baolu @ 2023-11-20 11:29 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Robin Murphy, Jason Gunthorpe, Kevin Tian
Cc: iommu, linux-kernel, Lu Baolu
The scalable mode context entry is now setup in the probe_device path,
eliminating the need to configure it in the attach_dev path. Removes the
redundant code from the attach_dev path to avoid dead code.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
drivers/iommu/intel/iommu.c | 156 ++++++++++--------------------------
1 file changed, 44 insertions(+), 112 deletions(-)
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index e34a32cd2b9a..77769ad4706e 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1727,34 +1727,17 @@ static void domain_exit(struct dmar_domain *domain)
kfree(domain);
}
-/*
- * Get the PASID directory size for scalable mode context entry.
- * Value of X in the PDTS field of a scalable mode context entry
- * indicates PASID directory with 2^(X + 7) entries.
- */
-static unsigned long context_get_sm_pds(struct pasid_table *table)
-{
- unsigned long pds, max_pde;
-
- max_pde = table->max_pasid >> PASID_PDE_SHIFT;
- pds = find_first_bit(&max_pde, MAX_NR_PASID_BITS);
- if (pds < 7)
- return 0;
-
- return pds - 7;
-}
-
static int domain_context_mapping_one(struct dmar_domain *domain,
struct intel_iommu *iommu,
- struct pasid_table *table,
u8 bus, u8 devfn)
{
struct device_domain_info *info =
domain_lookup_dev_info(domain, iommu, bus, devfn);
u16 did = domain_id_iommu(domain, iommu);
int translation = CONTEXT_TT_MULTI_LEVEL;
+ struct dma_pte *pgd = domain->pgd;
struct context_entry *context;
- int ret;
+ int agaw, ret;
if (hw_pass_through && domain_type_is_si(domain))
translation = CONTEXT_TT_PASS_THROUGH;
@@ -1797,65 +1780,37 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
}
context_clear_entry(context);
+ context_set_domain_id(context, did);
- if (sm_supported(iommu)) {
- unsigned long pds;
-
- /* Setup the PASID DIR pointer: */
- pds = context_get_sm_pds(table);
- context->lo = (u64)virt_to_phys(table->table) |
- context_pdts(pds);
-
- /* Setup the RID_PASID field: */
- context_set_sm_rid2pasid(context, IOMMU_NO_PASID);
-
+ if (translation != CONTEXT_TT_PASS_THROUGH) {
/*
- * Setup the Device-TLB enable bit and Page request
- * Enable bit:
+ * Skip top levels of page tables for iommu which has
+ * less agaw than default. Unnecessary for PT mode.
*/
+ for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
+ ret = -ENOMEM;
+ pgd = phys_to_virt(dma_pte_addr(pgd));
+ if (!dma_pte_present(pgd))
+ goto out_unlock;
+ }
+
if (info && info->ats_supported)
- context_set_sm_dte(context);
- if (info && info->pri_supported)
- context_set_sm_pre(context);
- if (info && info->pasid_supported)
- context_set_pasid(context);
+ translation = CONTEXT_TT_DEV_IOTLB;
+ else
+ translation = CONTEXT_TT_MULTI_LEVEL;
+
+ context_set_address_root(context, virt_to_phys(pgd));
+ context_set_address_width(context, agaw);
} else {
- struct dma_pte *pgd = domain->pgd;
- int agaw;
-
- context_set_domain_id(context, did);
-
- if (translation != CONTEXT_TT_PASS_THROUGH) {
- /*
- * Skip top levels of page tables for iommu which has
- * less agaw than default. Unnecessary for PT mode.
- */
- for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
- ret = -ENOMEM;
- pgd = phys_to_virt(dma_pte_addr(pgd));
- if (!dma_pte_present(pgd))
- goto out_unlock;
- }
-
- if (info && info->ats_supported)
- translation = CONTEXT_TT_DEV_IOTLB;
- else
- translation = CONTEXT_TT_MULTI_LEVEL;
-
- context_set_address_root(context, virt_to_phys(pgd));
- context_set_address_width(context, agaw);
- } else {
- /*
- * In pass through mode, AW must be programmed to
- * indicate the largest AGAW value supported by
- * hardware. And ASR is ignored by hardware.
- */
- context_set_address_width(context, iommu->msagaw);
- }
-
- context_set_translation_type(context, translation);
+ /*
+ * In pass through mode, AW must be programmed to
+ * indicate the largest AGAW value supported by
+ * hardware. And ASR is ignored by hardware.
+ */
+ context_set_address_width(context, iommu->msagaw);
}
+ context_set_translation_type(context, translation);
context_set_fault_enable(context);
context_set_present(context);
if (!ecap_coherent(iommu->ecap))
@@ -1885,43 +1840,29 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
return ret;
}
-struct domain_context_mapping_data {
- struct dmar_domain *domain;
- struct intel_iommu *iommu;
- struct pasid_table *table;
-};
-
static int domain_context_mapping_cb(struct pci_dev *pdev,
u16 alias, void *opaque)
{
- struct domain_context_mapping_data *data = opaque;
+ struct device_domain_info *info = dev_iommu_priv_get(&pdev->dev);
+ struct intel_iommu *iommu = info->iommu;
+ struct dmar_domain *domain = opaque;
- return domain_context_mapping_one(data->domain, data->iommu,
- data->table, PCI_BUS_NUM(alias),
- alias & 0xff);
+ return domain_context_mapping_one(domain, iommu,
+ PCI_BUS_NUM(alias), alias & 0xff);
}
static int
domain_context_mapping(struct dmar_domain *domain, struct device *dev)
{
struct device_domain_info *info = dev_iommu_priv_get(dev);
- struct domain_context_mapping_data data;
struct intel_iommu *iommu = info->iommu;
u8 bus = info->bus, devfn = info->devfn;
- struct pasid_table *table;
-
- table = intel_pasid_get_table(dev);
if (!dev_is_pci(dev))
- return domain_context_mapping_one(domain, iommu, table,
- bus, devfn);
-
- data.domain = domain;
- data.iommu = iommu;
- data.table = table;
+ return domain_context_mapping_one(domain, iommu, bus, devfn);
return pci_for_each_dma_alias(to_pci_dev(dev),
- &domain_context_mapping_cb, &data);
+ domain_context_mapping_cb, domain);
}
/* Returns a number of VTD pages, but aligned to MM page size */
@@ -2278,28 +2219,19 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
list_add(&info->link, &domain->devices);
spin_unlock_irqrestore(&domain->lock, flags);
- /* PASID table is mandatory for a PCI device in scalable mode. */
- if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) {
- /* Setup the PASID entry for requests without PASID: */
- if (hw_pass_through && domain_type_is_si(domain))
- ret = intel_pasid_setup_pass_through(iommu,
- dev, IOMMU_NO_PASID);
- else if (domain->use_first_level)
- ret = domain_setup_first_level(iommu, domain, dev,
- IOMMU_NO_PASID);
- else
- ret = intel_pasid_setup_second_level(iommu, domain,
- dev, IOMMU_NO_PASID);
- if (ret) {
- dev_err(dev, "Setup RID2PASID failed\n");
- device_block_translation(dev);
- return ret;
- }
- }
+ if (dev_is_real_dma_subdevice(dev))
+ return 0;
+
+ if (!sm_supported(iommu))
+ ret = domain_context_mapping(domain, dev);
+ else if (hw_pass_through && domain_type_is_si(domain))
+ ret = intel_pasid_setup_pass_through(iommu, dev, IOMMU_NO_PASID);
+ else if (domain->use_first_level)
+ ret = domain_setup_first_level(iommu, domain, dev, IOMMU_NO_PASID);
+ else
+ ret = intel_pasid_setup_second_level(iommu, domain, dev, IOMMU_NO_PASID);
- ret = domain_context_mapping(domain, dev);
if (ret) {
- dev_err(dev, "Domain context map failed\n");
device_block_translation(dev);
return ret;
}
--
2.34.1
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH 3/5] iommu/vt-d: Refactor domain_context_mapping_one() to be reusable
2023-11-20 11:29 [PATCH 0/5] iommu/vt-d: Convert to use static identity domain Lu Baolu
2023-11-20 11:29 ` [PATCH 1/5] iommu/vt-d: Setup scalable mode context entry in probe path Lu Baolu
2023-11-20 11:29 ` [PATCH 2/5] iommu/vt-d: Remove scalable mode context entry setup from attach_dev Lu Baolu
@ 2023-11-20 11:29 ` Lu Baolu
2023-11-20 11:29 ` [PATCH 4/5] iommu/vt-d: Add support for static identity domain Lu Baolu
2023-11-20 11:29 ` [PATCH 5/5] iommu/vt-d: Remove si_domain Lu Baolu
4 siblings, 0 replies; 9+ messages in thread
From: Lu Baolu @ 2023-11-20 11:29 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Robin Murphy, Jason Gunthorpe, Kevin Tian
Cc: iommu, linux-kernel, Lu Baolu
Extract common code from domain_context_mapping_one() into new functions,
making it reusable by other functions such as the upcoming identity domain
implementation. No intentional functional changes.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
drivers/iommu/intel/iommu.c | 99 ++++++++++++++++++++++---------------
1 file changed, 58 insertions(+), 41 deletions(-)
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 77769ad4706e..86339dc30243 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1727,6 +1727,61 @@ static void domain_exit(struct dmar_domain *domain)
kfree(domain);
}
+/*
+ * For kdump cases, old valid entries may be cached due to the
+ * in-flight DMA and copied pgtable, but there is no unmapping
+ * behaviour for them, thus we need an explicit cache flush for
+ * the newly-mapped device. For kdump, at this point, the device
+ * is supposed to finish reset at its driver probe stage, so no
+ * in-flight DMA will exist, and we don't need to worry anymore
+ * hereafter.
+ */
+static void copied_context_tear_down(struct intel_iommu *iommu,
+ struct context_entry *context,
+ u8 bus, u8 devfn)
+{
+ u16 did_old;
+
+ if (!context_copied(iommu, bus, devfn))
+ return;
+
+ assert_spin_locked(&iommu->lock);
+
+ did_old = context_domain_id(context);
+ context_clear_entry(context);
+
+ if (did_old < cap_ndoms(iommu->cap)) {
+ iommu->flush.flush_context(iommu, did_old,
+ (((u16)bus) << 8) | devfn,
+ DMA_CCMD_MASK_NOBIT,
+ DMA_CCMD_DEVICE_INVL);
+ iommu->flush.flush_iotlb(iommu, did_old, 0, 0,
+ DMA_TLB_DSI_FLUSH);
+ }
+
+ clear_context_copied(iommu, bus, devfn);
+}
+
+/*
+ * It's a non-present to present mapping. If hardware doesn't cache
+ * non-present entry we only need to flush the write-buffer. If the
+ * _does_ cache non-present entries, then it does so in the special
+ * domain #0, which we have to flush:
+ */
+static void context_present_cache_flush(struct intel_iommu *iommu, u16 did,
+ u8 bus, u8 devfn)
+{
+ if (cap_caching_mode(iommu->cap)) {
+ iommu->flush.flush_context(iommu, 0,
+ (((u16)bus) << 8) | devfn,
+ DMA_CCMD_MASK_NOBIT,
+ DMA_CCMD_DEVICE_INVL);
+ iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH);
+ } else {
+ iommu_flush_write_buffer(iommu);
+ }
+}
+
static int domain_context_mapping_one(struct dmar_domain *domain,
struct intel_iommu *iommu,
u8 bus, u8 devfn)
@@ -1755,31 +1810,9 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
if (context_present(context) && !context_copied(iommu, bus, devfn))
goto out_unlock;
- /*
- * For kdump cases, old valid entries may be cached due to the
- * in-flight DMA and copied pgtable, but there is no unmapping
- * behaviour for them, thus we need an explicit cache flush for
- * the newly-mapped device. For kdump, at this point, the device
- * is supposed to finish reset at its driver probe stage, so no
- * in-flight DMA will exist, and we don't need to worry anymore
- * hereafter.
- */
- if (context_copied(iommu, bus, devfn)) {
- u16 did_old = context_domain_id(context);
-
- if (did_old < cap_ndoms(iommu->cap)) {
- iommu->flush.flush_context(iommu, did_old,
- (((u16)bus) << 8) | devfn,
- DMA_CCMD_MASK_NOBIT,
- DMA_CCMD_DEVICE_INVL);
- iommu->flush.flush_iotlb(iommu, did_old, 0, 0,
- DMA_TLB_DSI_FLUSH);
- }
-
- clear_context_copied(iommu, bus, devfn);
- }
-
+ copied_context_tear_down(iommu, context, bus, devfn);
context_clear_entry(context);
+
context_set_domain_id(context, did);
if (translation != CONTEXT_TT_PASS_THROUGH) {
@@ -1815,23 +1848,7 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
context_set_present(context);
if (!ecap_coherent(iommu->ecap))
clflush_cache_range(context, sizeof(*context));
-
- /*
- * It's a non-present to present mapping. If hardware doesn't cache
- * non-present entry we only need to flush the write-buffer. If the
- * _does_ cache non-present entries, then it does so in the special
- * domain #0, which we have to flush:
- */
- if (cap_caching_mode(iommu->cap)) {
- iommu->flush.flush_context(iommu, 0,
- (((u16)bus) << 8) | devfn,
- DMA_CCMD_MASK_NOBIT,
- DMA_CCMD_DEVICE_INVL);
- iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH);
- } else {
- iommu_flush_write_buffer(iommu);
- }
-
+ context_present_cache_flush(iommu, did, bus, devfn);
ret = 0;
out_unlock:
--
2.34.1
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH 4/5] iommu/vt-d: Add support for static identity domain
2023-11-20 11:29 [PATCH 0/5] iommu/vt-d: Convert to use static identity domain Lu Baolu
` (2 preceding siblings ...)
2023-11-20 11:29 ` [PATCH 3/5] iommu/vt-d: Refactor domain_context_mapping_one() to be reusable Lu Baolu
@ 2023-11-20 11:29 ` Lu Baolu
2023-11-29 20:26 ` Jason Gunthorpe
2023-11-20 11:29 ` [PATCH 5/5] iommu/vt-d: Remove si_domain Lu Baolu
4 siblings, 1 reply; 9+ messages in thread
From: Lu Baolu @ 2023-11-20 11:29 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Robin Murphy, Jason Gunthorpe, Kevin Tian
Cc: iommu, linux-kernel, Lu Baolu
Add a global static identity domain with guaranteed attach semantics.
Software determines VT-d hardware support for pass-through translation by
inspecting the capability register. If pass-through translation is not
supported, the device is instructed to use DMA domain for its default
domain. While most recent VT-d hardware implementations support pass-
through translation, this capability is only lacking in some early VT-d
implementations.
With the static identity domain in place, the domain field of per-device
iommu driver data can be either a pointer to a DMA translation domain, or
NULL, indicating that the static identity domain is attached. Refine some
code to accommodate this change.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
drivers/iommu/intel/iommu.c | 129 ++++++++++++++++++++++++++++++++++--
drivers/iommu/intel/svm.c | 2 +-
2 files changed, 125 insertions(+), 6 deletions(-)
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 86339dc30243..ad2e53821a05 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1282,7 +1282,8 @@ static void iommu_enable_pci_caps(struct device_domain_info *info)
if (info->ats_supported && pci_ats_page_aligned(pdev) &&
!pci_enable_ats(pdev, VTD_PAGE_SHIFT)) {
info->ats_enabled = 1;
- domain_update_iotlb(info->domain);
+ if (info->domain)
+ domain_update_iotlb(info->domain);
}
}
@@ -1298,7 +1299,8 @@ static void iommu_disable_pci_caps(struct device_domain_info *info)
if (info->ats_enabled) {
pci_disable_ats(pdev);
info->ats_enabled = 0;
- domain_update_iotlb(info->domain);
+ if (info->domain)
+ domain_update_iotlb(info->domain);
}
if (info->pasid_enabled) {
@@ -2301,6 +2303,9 @@ static bool device_rmrr_is_relaxable(struct device *dev)
*/
static int device_def_domain_type(struct device *dev)
{
+ struct device_domain_info *info = dev_iommu_priv_get(dev);
+ struct intel_iommu *iommu = info->iommu;
+
if (dev_is_pci(dev)) {
struct pci_dev *pdev = to_pci_dev(dev);
@@ -2311,6 +2316,13 @@ static int device_def_domain_type(struct device *dev)
return IOMMU_DOMAIN_IDENTITY;
}
+ /*
+ * Hardware does not support the passthrough translation mode.
+ * Always use a dynamaic mapping domain.
+ */
+ if (!ecap_pass_through(iommu->ecap))
+ return IOMMU_DOMAIN_DMA;
+
return 0;
}
@@ -3712,6 +3724,9 @@ static void dmar_remove_one_dev_info(struct device *dev)
domain_context_clear(info);
}
+ if (!domain)
+ return;
+
spin_lock_irqsave(&domain->lock, flags);
list_del(&info->link);
spin_unlock_irqrestore(&domain->lock, flags);
@@ -3920,11 +3935,9 @@ int prepare_domain_attach_device(struct iommu_domain *domain,
static int intel_iommu_attach_device(struct iommu_domain *domain,
struct device *dev)
{
- struct device_domain_info *info = dev_iommu_priv_get(dev);
int ret;
- if (info->domain)
- device_block_translation(dev);
+ device_block_translation(dev);
ret = prepare_domain_attach_device(domain, dev);
if (ret)
@@ -4529,6 +4542,9 @@ static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid)
goto out_tear_down;
}
+ if (domain->type == IOMMU_DOMAIN_IDENTITY)
+ goto out_tear_down;
+
dmar_domain = to_dmar_domain(domain);
spin_lock_irqsave(&dmar_domain->lock, flags);
list_for_each_entry(curr, &dmar_domain->dev_pasids, link_domain) {
@@ -4703,8 +4719,111 @@ const struct iommu_dirty_ops intel_dirty_ops = {
.read_and_clear_dirty = intel_iommu_read_and_clear_dirty,
};
+static int context_setup_pass_through(struct device *dev, u8 bus, u8 devfn)
+{
+ struct device_domain_info *info = dev_iommu_priv_get(dev);
+ struct intel_iommu *iommu = info->iommu;
+ struct context_entry *context;
+
+ spin_lock(&iommu->lock);
+ context = iommu_context_addr(iommu, bus, devfn, 1);
+ if (!context) {
+ spin_unlock(&iommu->lock);
+ return -ENOMEM;
+ }
+
+ if (context_present(context) && !context_copied(iommu, bus, devfn)) {
+ spin_unlock(&iommu->lock);
+ return 0;
+ }
+
+ copied_context_tear_down(iommu, context, bus, devfn);
+ context_clear_entry(context);
+ context_set_domain_id(context, FLPT_DEFAULT_DID);
+
+ /*
+ * In pass through mode, AW must be programmed to indicate the largest
+ * AGAW value supported by hardware. And ASR is ignored by hardware.
+ */
+ context_set_address_width(context, iommu->msagaw);
+ context_set_translation_type(context, CONTEXT_TT_PASS_THROUGH);
+ context_set_fault_enable(context);
+ context_set_present(context);
+ if (!ecap_coherent(iommu->ecap))
+ clflush_cache_range(context, sizeof(*context));
+ context_present_cache_flush(iommu, FLPT_DEFAULT_DID, bus, devfn);
+ spin_unlock(&iommu->lock);
+
+ return 0;
+}
+
+static int context_setup_pass_through_cb(struct pci_dev *pdev, u16 alias, void *data)
+{
+ struct device *dev = data;
+
+ if (dev != &pdev->dev)
+ return 0;
+
+ return context_setup_pass_through(dev, PCI_BUS_NUM(alias), alias & 0xff);
+}
+
+static int device_setup_pass_through(struct device *dev)
+{
+ struct device_domain_info *info = dev_iommu_priv_get(dev);
+
+ if (!dev_is_pci(dev))
+ return context_setup_pass_through(dev, info->bus, info->devfn);
+
+ return pci_for_each_dma_alias(to_pci_dev(dev),
+ context_setup_pass_through_cb, dev);
+}
+
+static int identity_domain_attach_dev(struct iommu_domain *domain,
+ struct device *dev)
+{
+ struct device_domain_info *info = dev_iommu_priv_get(dev);
+ struct intel_iommu *iommu = info->iommu;
+ int ret;
+
+ device_block_translation(dev);
+
+ if (dev_is_real_dma_subdevice(dev))
+ return 0;
+
+ if (sm_supported(iommu)) {
+ ret = intel_pasid_setup_pass_through(iommu, dev, IOMMU_NO_PASID);
+ if (!ret)
+ iommu_enable_pci_caps(info);
+ } else {
+ ret = device_setup_pass_through(dev);
+ }
+
+ return ret;
+}
+
+static int identity_domain_set_dev_pasid(struct iommu_domain *domain,
+ struct device *dev, ioasid_t pasid)
+{
+ struct device_domain_info *info = dev_iommu_priv_get(dev);
+ struct intel_iommu *iommu = info->iommu;
+
+ if (!pasid_supported(iommu) || dev_is_real_dma_subdevice(dev))
+ return -EOPNOTSUPP;
+
+ return intel_pasid_setup_pass_through(iommu, dev, pasid);
+}
+
+static struct iommu_domain identity_domain = {
+ .type = IOMMU_DOMAIN_IDENTITY,
+ .ops = &(const struct iommu_domain_ops) {
+ .attach_dev = identity_domain_attach_dev,
+ .set_dev_pasid = identity_domain_set_dev_pasid,
+ },
+};
+
const struct iommu_ops intel_iommu_ops = {
.blocked_domain = &blocking_domain,
+ .identity_domain = &identity_domain,
.capable = intel_iommu_capable,
.hw_info = intel_iommu_hw_info,
.domain_alloc = intel_iommu_domain_alloc,
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 64c02e6ab1b3..e744f7439e97 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -493,7 +493,7 @@ void intel_drain_pasid_prq(struct device *dev, u32 pasid)
domain = info->domain;
pdev = to_pci_dev(dev);
sid = PCI_DEVID(info->bus, info->devfn);
- did = domain_id_iommu(domain, iommu);
+ did = domain ? domain_id_iommu(domain, iommu) : FLPT_DEFAULT_DID;
qdep = pci_ats_queue_depth(pdev);
/*
--
2.34.1
^ permalink raw reply related [flat|nested] 9+ messages in thread* Re: [PATCH 4/5] iommu/vt-d: Add support for static identity domain
2023-11-20 11:29 ` [PATCH 4/5] iommu/vt-d: Add support for static identity domain Lu Baolu
@ 2023-11-29 20:26 ` Jason Gunthorpe
2023-11-29 20:28 ` Jason Gunthorpe
0 siblings, 1 reply; 9+ messages in thread
From: Jason Gunthorpe @ 2023-11-29 20:26 UTC (permalink / raw)
To: Lu Baolu
Cc: Joerg Roedel, Will Deacon, Robin Murphy, Kevin Tian, iommu, linux-kernel
On Mon, Nov 20, 2023 at 07:29:43PM +0800, Lu Baolu wrote:
> @@ -2311,6 +2316,13 @@ static int device_def_domain_type(struct device *dev)
> return IOMMU_DOMAIN_IDENTITY;
> }
>
> + /*
> + * Hardware does not support the passthrough translation mode.
> + * Always use a dynamaic mapping domain.
> + */
> + if (!ecap_pass_through(iommu->ecap))
> + return IOMMU_DOMAIN_DMA;
> +
Doesn't this return from def_domain_type completely prevent using an
identity domain?
I thought the point of this was to allow the identity domain but have
it be translating?
Jason
^ permalink raw reply [flat|nested] 9+ messages in thread
* Re: [PATCH 4/5] iommu/vt-d: Add support for static identity domain
2023-11-29 20:26 ` Jason Gunthorpe
@ 2023-11-29 20:28 ` Jason Gunthorpe
2023-11-30 6:09 ` Baolu Lu
0 siblings, 1 reply; 9+ messages in thread
From: Jason Gunthorpe @ 2023-11-29 20:28 UTC (permalink / raw)
To: Lu Baolu
Cc: Joerg Roedel, Will Deacon, Robin Murphy, Kevin Tian, iommu, linux-kernel
On Wed, Nov 29, 2023 at 04:26:15PM -0400, Jason Gunthorpe wrote:
> On Mon, Nov 20, 2023 at 07:29:43PM +0800, Lu Baolu wrote:
>
> > @@ -2311,6 +2316,13 @@ static int device_def_domain_type(struct device *dev)
> > return IOMMU_DOMAIN_IDENTITY;
> > }
> >
> > + /*
> > + * Hardware does not support the passthrough translation mode.
> > + * Always use a dynamaic mapping domain.
> > + */
> > + if (!ecap_pass_through(iommu->ecap))
> > + return IOMMU_DOMAIN_DMA;
> > +
>
> Doesn't this return from def_domain_type completely prevent using an
> identity domain?
>
> I thought the point of this was to allow the identity domain but have
> it be translating?
I suppose the answer is the next patch deletes that stuff.
I would probably have structured this in the other order, first add
this hunk and say that old HW is being de-supported. Remove all the
now-dead code creating the 1:1 page table, then refactor the remainder
to create the global static.
Jason
^ permalink raw reply [flat|nested] 9+ messages in thread
* Re: [PATCH 4/5] iommu/vt-d: Add support for static identity domain
2023-11-29 20:28 ` Jason Gunthorpe
@ 2023-11-30 6:09 ` Baolu Lu
0 siblings, 0 replies; 9+ messages in thread
From: Baolu Lu @ 2023-11-30 6:09 UTC (permalink / raw)
To: Jason Gunthorpe
Cc: baolu.lu, Joerg Roedel, Will Deacon, Robin Murphy, Kevin Tian,
iommu, linux-kernel
On 2023/11/30 4:28, Jason Gunthorpe wrote:
> On Wed, Nov 29, 2023 at 04:26:15PM -0400, Jason Gunthorpe wrote:
>> On Mon, Nov 20, 2023 at 07:29:43PM +0800, Lu Baolu wrote:
>>
>>> @@ -2311,6 +2316,13 @@ static int device_def_domain_type(struct device *dev)
>>> return IOMMU_DOMAIN_IDENTITY;
>>> }
>>>
>>> + /*
>>> + * Hardware does not support the passthrough translation mode.
>>> + * Always use a dynamaic mapping domain.
>>> + */
>>> + if (!ecap_pass_through(iommu->ecap))
>>> + return IOMMU_DOMAIN_DMA;
>>> +
>> Doesn't this return from def_domain_type completely prevent using an
>> identity domain?
>>
>> I thought the point of this was to allow the identity domain but have
>> it be translating?
> I suppose the answer is the next patch deletes that stuff.
>
> I would probably have structured this in the other order, first add
> this hunk and say that old HW is being de-supported. Remove all the
> now-dead code creating the 1:1 page table, then refactor the remainder
> to create the global static.
Okay, that would be more readable.
Best regards,
baolu
^ permalink raw reply [flat|nested] 9+ messages in thread
* [PATCH 5/5] iommu/vt-d: Remove si_domain
2023-11-20 11:29 [PATCH 0/5] iommu/vt-d: Convert to use static identity domain Lu Baolu
` (3 preceding siblings ...)
2023-11-20 11:29 ` [PATCH 4/5] iommu/vt-d: Add support for static identity domain Lu Baolu
@ 2023-11-20 11:29 ` Lu Baolu
4 siblings, 0 replies; 9+ messages in thread
From: Lu Baolu @ 2023-11-20 11:29 UTC (permalink / raw)
To: Joerg Roedel, Will Deacon, Robin Murphy, Jason Gunthorpe, Kevin Tian
Cc: iommu, linux-kernel, Lu Baolu
The static identity domain has been introduced, rendering the si_domain
obsolete. Remove si_domain and cleanup the code accordingly.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
drivers/iommu/intel/iommu.c | 226 ++++--------------------------------
1 file changed, 23 insertions(+), 203 deletions(-)
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index ad2e53821a05..90dd7f24beda 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -97,15 +97,6 @@ static phys_addr_t root_entry_uctp(struct root_entry *re)
return re->hi & VTD_PAGE_MASK;
}
-/*
- * This domain is a statically identity mapping domain.
- * 1. This domain creats a static 1:1 mapping to all usable memory.
- * 2. It maps to each iommu if successful.
- * 3. Each iommu mapps to this domain if successful.
- */
-static struct dmar_domain *si_domain;
-static int hw_pass_through = 1;
-
struct dmar_rmrr_unit {
struct list_head list; /* list of rmrr units */
struct acpi_dmar_header *hdr; /* ACPI header */
@@ -240,11 +231,6 @@ void free_pgtable_page(void *vaddr)
free_page((unsigned long)vaddr);
}
-static int domain_type_is_si(struct dmar_domain *domain)
-{
- return domain->domain.type == IOMMU_DOMAIN_IDENTITY;
-}
-
static int domain_pfn_supported(struct dmar_domain *domain, unsigned long pfn)
{
int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
@@ -1796,9 +1782,6 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
struct context_entry *context;
int agaw, ret;
- if (hw_pass_through && domain_type_is_si(domain))
- translation = CONTEXT_TT_PASS_THROUGH;
-
pr_debug("Set context mapping for %02x:%02x.%d\n",
bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
@@ -1817,34 +1800,24 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
context_set_domain_id(context, did);
- if (translation != CONTEXT_TT_PASS_THROUGH) {
- /*
- * Skip top levels of page tables for iommu which has
- * less agaw than default. Unnecessary for PT mode.
- */
- for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
- ret = -ENOMEM;
- pgd = phys_to_virt(dma_pte_addr(pgd));
- if (!dma_pte_present(pgd))
- goto out_unlock;
- }
-
- if (info && info->ats_supported)
- translation = CONTEXT_TT_DEV_IOTLB;
- else
- translation = CONTEXT_TT_MULTI_LEVEL;
-
- context_set_address_root(context, virt_to_phys(pgd));
- context_set_address_width(context, agaw);
- } else {
- /*
- * In pass through mode, AW must be programmed to
- * indicate the largest AGAW value supported by
- * hardware. And ASR is ignored by hardware.
- */
- context_set_address_width(context, iommu->msagaw);
+ /*
+ * Skip top levels of page tables for iommu which has
+ * less agaw than default. Unnecessary for PT mode.
+ */
+ for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
+ ret = -ENOMEM;
+ pgd = phys_to_virt(dma_pte_addr(pgd));
+ if (!dma_pte_present(pgd))
+ goto out_unlock;
}
+ if (info && info->ats_supported)
+ translation = CONTEXT_TT_DEV_IOTLB;
+ else
+ translation = CONTEXT_TT_MULTI_LEVEL;
+
+ context_set_address_root(context, virt_to_phys(pgd));
+ context_set_address_width(context, agaw);
context_set_translation_type(context, translation);
context_set_fault_enable(context);
context_set_present(context);
@@ -2078,14 +2051,10 @@ static void domain_context_clear_one(struct device_domain_info *info, u8 bus, u8
return;
}
- if (sm_supported(iommu)) {
- if (hw_pass_through && domain_type_is_si(info->domain))
- did_old = FLPT_DEFAULT_DID;
- else
- did_old = domain_id_iommu(info->domain, iommu);
- } else {
- did_old = context_domain_id(context);
- }
+ if (info->domain)
+ did_old = domain_id_iommu(info->domain, iommu);
+ else
+ did_old = FLPT_DEFAULT_DID;
context_clear_entry(context);
__iommu_flush_cache(iommu, context, sizeof(*context));
@@ -2148,80 +2117,6 @@ static bool dev_is_real_dma_subdevice(struct device *dev)
pci_real_dma_dev(to_pci_dev(dev)) != to_pci_dev(dev);
}
-static int iommu_domain_identity_map(struct dmar_domain *domain,
- unsigned long first_vpfn,
- unsigned long last_vpfn)
-{
- /*
- * RMRR range might have overlap with physical memory range,
- * clear it first
- */
- dma_pte_clear_range(domain, first_vpfn, last_vpfn);
-
- return __domain_mapping(domain, first_vpfn,
- first_vpfn, last_vpfn - first_vpfn + 1,
- DMA_PTE_READ|DMA_PTE_WRITE, GFP_KERNEL);
-}
-
-static int md_domain_init(struct dmar_domain *domain, int guest_width);
-
-static int __init si_domain_init(int hw)
-{
- struct dmar_rmrr_unit *rmrr;
- struct device *dev;
- int i, nid, ret;
-
- si_domain = alloc_domain(IOMMU_DOMAIN_IDENTITY);
- if (!si_domain)
- return -EFAULT;
-
- if (md_domain_init(si_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) {
- domain_exit(si_domain);
- si_domain = NULL;
- return -EFAULT;
- }
-
- if (hw)
- return 0;
-
- for_each_online_node(nid) {
- unsigned long start_pfn, end_pfn;
- int i;
-
- for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
- ret = iommu_domain_identity_map(si_domain,
- mm_to_dma_pfn_start(start_pfn),
- mm_to_dma_pfn_end(end_pfn));
- if (ret)
- return ret;
- }
- }
-
- /*
- * Identity map the RMRRs so that devices with RMRRs could also use
- * the si_domain.
- */
- for_each_rmrr_units(rmrr) {
- for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt,
- i, dev) {
- unsigned long long start = rmrr->base_address;
- unsigned long long end = rmrr->end_address;
-
- if (WARN_ON(end < start ||
- end >> agaw_to_width(si_domain->agaw)))
- continue;
-
- ret = iommu_domain_identity_map(si_domain,
- mm_to_dma_pfn_start(start >> PAGE_SHIFT),
- mm_to_dma_pfn_end(end >> PAGE_SHIFT));
- if (ret)
- return ret;
- }
- }
-
- return 0;
-}
-
static int dmar_domain_attach_device(struct dmar_domain *domain,
struct device *dev)
{
@@ -2243,8 +2138,6 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
if (!sm_supported(iommu))
ret = domain_context_mapping(domain, dev);
- else if (hw_pass_through && domain_type_is_si(domain))
- ret = intel_pasid_setup_pass_through(iommu, dev, IOMMU_NO_PASID);
else if (domain->use_first_level)
ret = domain_setup_first_level(iommu, domain, dev, IOMMU_NO_PASID);
else
@@ -2255,8 +2148,7 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
return ret;
}
- if (sm_supported(info->iommu) || !domain_type_is_si(info->domain))
- iommu_enable_pci_caps(info);
+ iommu_enable_pci_caps(info);
return 0;
}
@@ -2606,8 +2498,6 @@ static int __init init_dmars(void)
}
}
- if (!ecap_pass_through(iommu->ecap))
- hw_pass_through = 0;
intel_svm_check(iommu);
}
@@ -2630,10 +2520,6 @@ static int __init init_dmars(void)
check_tylersburg_isoch();
- ret = si_domain_init(hw_pass_through);
- if (ret)
- goto free_iommu;
-
/*
* for each drhd
* enable fault log
@@ -2679,10 +2565,6 @@ static int __init init_dmars(void)
disable_dmar_iommu(iommu);
free_dmar_iommu(iommu);
}
- if (si_domain) {
- domain_exit(si_domain);
- si_domain = NULL;
- }
return ret;
}
@@ -3057,12 +2939,6 @@ static int intel_iommu_add(struct dmar_drhd_unit *dmaru)
if (ret)
goto out;
- if (hw_pass_through && !ecap_pass_through(iommu->ecap)) {
- pr_warn("%s: Doesn't support hardware pass through.\n",
- iommu->name);
- return -ENXIO;
- }
-
sp = domain_update_iommu_superpage(NULL, iommu) - 1;
if (sp >= 0 && !(cap_super_page_val(iommu->cap) & (1 << sp))) {
pr_warn("%s: Doesn't support large page.\n",
@@ -3313,52 +3189,6 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
return 0;
}
-static int intel_iommu_memory_notifier(struct notifier_block *nb,
- unsigned long val, void *v)
-{
- struct memory_notify *mhp = v;
- unsigned long start_vpfn = mm_to_dma_pfn_start(mhp->start_pfn);
- unsigned long last_vpfn = mm_to_dma_pfn_end(mhp->start_pfn +
- mhp->nr_pages - 1);
-
- switch (val) {
- case MEM_GOING_ONLINE:
- if (iommu_domain_identity_map(si_domain,
- start_vpfn, last_vpfn)) {
- pr_warn("Failed to build identity map for [%lx-%lx]\n",
- start_vpfn, last_vpfn);
- return NOTIFY_BAD;
- }
- break;
-
- case MEM_OFFLINE:
- case MEM_CANCEL_ONLINE:
- {
- struct dmar_drhd_unit *drhd;
- struct intel_iommu *iommu;
- LIST_HEAD(freelist);
-
- domain_unmap(si_domain, start_vpfn, last_vpfn, &freelist);
-
- rcu_read_lock();
- for_each_active_iommu(iommu, drhd)
- iommu_flush_iotlb_psi(iommu, si_domain,
- start_vpfn, mhp->nr_pages,
- list_empty(&freelist), 0);
- rcu_read_unlock();
- put_pages_list(&freelist);
- }
- break;
- }
-
- return NOTIFY_OK;
-}
-
-static struct notifier_block intel_iommu_memory_nb = {
- .notifier_call = intel_iommu_memory_notifier,
- .priority = 0
-};
-
static void intel_disable_iommus(void)
{
struct intel_iommu *iommu = NULL;
@@ -3655,12 +3485,7 @@ int __init intel_iommu_init(void)
iommu_pmu_register(iommu);
}
- up_read(&dmar_global_lock);
- if (si_domain && !hw_pass_through)
- register_memory_notifier(&intel_iommu_memory_nb);
-
- down_read(&dmar_global_lock);
if (probe_acpi_namespace_devices())
pr_warn("ACPI name space devices didn't probe correctly\n");
@@ -3827,8 +3652,6 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type)
domain->geometry.force_aperture = true;
return domain;
- case IOMMU_DOMAIN_IDENTITY:
- return &si_domain->domain;
case IOMMU_DOMAIN_SVA:
return intel_svm_domain_alloc();
default:
@@ -3888,8 +3711,7 @@ intel_iommu_domain_alloc_user(struct device *dev, u32 flags,
static void intel_iommu_domain_free(struct iommu_domain *domain)
{
- if (domain != &si_domain->domain)
- domain_exit(to_dmar_domain(domain));
+ domain_exit(to_dmar_domain(domain));
}
int prepare_domain_attach_device(struct iommu_domain *domain,
@@ -4596,9 +4418,7 @@ static int intel_iommu_set_dev_pasid(struct iommu_domain *domain,
if (ret)
goto out_free;
- if (domain_type_is_si(dmar_domain))
- ret = intel_pasid_setup_pass_through(iommu, dev, pasid);
- else if (dmar_domain->use_first_level)
+ if (dmar_domain->use_first_level)
ret = domain_setup_first_level(iommu, dmar_domain,
dev, pasid);
else
--
2.34.1
^ permalink raw reply related [flat|nested] 9+ messages in thread