Hi Joerg,
The following patches have been queued for v6.7. They aim to:
- Enable debugfs to dump domain attached to a pasid
- Remove an unnecessary inline function.
All patches are based on v6.6-rc5. The series is also available at:
https://github.com/LuBaolu/intel-iommu/commits/vtd-update-for-v6.7
Please consider them for v6.7.
Best regards,
Baolu
Jiapeng Chong (1):
iommu/vt-d: Remove unused function
Jingqi Liu (3):
iommu/vt-d: debugfs: Dump entry pointing to huge page
iommu/vt-d: debugfs: Create/remove debugfs file per {device, pasid}
iommu/vt-d: debugfs: Support dumping a specified page table
drivers/iommu/intel/iommu.h | 14 +++
drivers/iommu/intel/debugfs.c | 215 +++++++++++++++++++++++++++-------
drivers/iommu/intel/iommu.c | 7 ++
drivers/iommu/intel/pasid.c | 9 --
4 files changed, 195 insertions(+), 50 deletions(-)
--
2.34.1
From: Jiapeng Chong <[email protected]>
The function are defined in the pasid.c file, but not called
elsewhere, so delete the unused function.
drivers/iommu/intel/pasid.c:342:20: warning: unused function 'pasid_set_wpe'.
Reported-by: Abaci Robot <[email protected]>
Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=6185
Signed-off-by: Jiapeng Chong <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Lu Baolu <[email protected]>
---
drivers/iommu/intel/pasid.c | 9 ---------
1 file changed, 9 deletions(-)
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index 8f92b92f3d2a..06ddb3c927f5 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -335,15 +335,6 @@ static inline void pasid_set_fault_enable(struct pasid_entry *pe)
pasid_set_bits(&pe->val[0], 1 << 1, 0);
}
-/*
- * Setup the WPE(Write Protect Enable) field (Bit 132) of a
- * scalable mode PASID entry.
- */
-static inline void pasid_set_wpe(struct pasid_entry *pe)
-{
- pasid_set_bits(&pe->val[2], 1 << 4, 1 << 4);
-}
-
/*
* Setup the P(Present) field (Bit 0) of a scalable mode PASID
* entry.
--
2.34.1
From: Jingqi Liu <[email protected]>
For the page table entry pointing to a huge page, the data below the
level of the huge page is meaningless and does not need to be dumped.
Signed-off-by: Jingqi Liu <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Lu Baolu <[email protected]>
---
drivers/iommu/intel/debugfs.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/drivers/iommu/intel/debugfs.c b/drivers/iommu/intel/debugfs.c
index 1f925285104e..497c1561d3d2 100644
--- a/drivers/iommu/intel/debugfs.c
+++ b/drivers/iommu/intel/debugfs.c
@@ -311,9 +311,14 @@ static inline unsigned long level_to_directory_size(int level)
static inline void
dump_page_info(struct seq_file *m, unsigned long iova, u64 *path)
{
- seq_printf(m, "0x%013lx |\t0x%016llx\t0x%016llx\t0x%016llx\t0x%016llx\t0x%016llx\n",
- iova >> VTD_PAGE_SHIFT, path[5], path[4],
- path[3], path[2], path[1]);
+ seq_printf(m, "0x%013lx |\t0x%016llx\t0x%016llx\t0x%016llx",
+ iova >> VTD_PAGE_SHIFT, path[5], path[4], path[3]);
+ if (path[2]) {
+ seq_printf(m, "\t0x%016llx", path[2]);
+ if (path[1])
+ seq_printf(m, "\t0x%016llx", path[1]);
+ }
+ seq_putc(m, '\n');
}
static void pgtable_walk_level(struct seq_file *m, struct dma_pte *pde,
--
2.34.1
From: Jingqi Liu <[email protected]>
The original debugfs only dumps all page tables without pasid. With
pasid supported, the page table with pasid also needs to be dumped.
This patch supports dumping a specified page table in legacy mode or
scalable mode with or without a specified pasid.
For legacy mode, according to bus number and DEVFN, traverse the root
table and context table to get the pointer of page table in the
context table entry, then dump the specified page table.
For scalable mode, according to bus number, DEVFN and pasid, traverse
the root table, context table, pasid directory and pasid table to get
the pointer of page table in the pasid table entry, then dump the
specified page table..
Examples are as follows:
1) Dump the page table of device "0000:00:1f.0" that only supports
legacy mode.
$ sudo cat
/sys/kernel/debug/iommu/intel/0000:00:1f.0/domain_translation_struct
2) Dump the page table of device "0000:00:0a.0" with PASID "1" that
supports scalable mode.
$ sudo cat
/sys/kernel/debug/iommu/intel/0000:00:0a.0/1/domain_translation_struct
Suggested-by: Kevin Tian <[email protected]>
Signed-off-by: Jingqi Liu <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Lu Baolu <[email protected]>
---
drivers/iommu/intel/debugfs.c | 153 ++++++++++++++++++++++++++--------
1 file changed, 119 insertions(+), 34 deletions(-)
diff --git a/drivers/iommu/intel/debugfs.c b/drivers/iommu/intel/debugfs.c
index 8a18a7be5215..dee61e513be6 100644
--- a/drivers/iommu/intel/debugfs.c
+++ b/drivers/iommu/intel/debugfs.c
@@ -347,58 +347,140 @@ static void pgtable_walk_level(struct seq_file *m, struct dma_pte *pde,
}
}
-static int __show_device_domain_translation(struct device *dev, void *data)
+static int domain_translation_struct_show(struct seq_file *m,
+ struct device_domain_info *info,
+ ioasid_t pasid)
{
- struct dmar_domain *domain;
- struct seq_file *m = data;
- u64 path[6] = { 0 };
+ bool scalable, found = false;
+ struct dmar_drhd_unit *drhd;
+ struct intel_iommu *iommu;
+ u16 devfn, bus, seg;
- domain = to_dmar_domain(iommu_get_domain_for_dev(dev));
- if (!domain)
- return 0;
+ bus = info->bus;
+ devfn = info->devfn;
+ seg = info->segment;
- seq_printf(m, "Device %s @0x%llx\n", dev_name(dev),
- (u64)virt_to_phys(domain->pgd));
- seq_puts(m, "IOVA_PFN\t\tPML5E\t\t\tPML4E\t\t\tPDPE\t\t\tPDE\t\t\tPTE\n");
+ rcu_read_lock();
+ for_each_active_iommu(iommu, drhd) {
+ struct context_entry *context;
+ u64 pgd, path[6] = { 0 };
+ u32 sts, agaw;
- pgtable_walk_level(m, domain->pgd, domain->agaw + 2, 0, path);
- seq_putc(m, '\n');
+ if (seg != iommu->segment)
+ continue;
- /* Don't iterate */
- return 1;
-}
+ sts = dmar_readl(iommu->reg + DMAR_GSTS_REG);
+ if (!(sts & DMA_GSTS_TES)) {
+ seq_printf(m, "DMA Remapping is not enabled on %s\n",
+ iommu->name);
+ continue;
+ }
+ if (dmar_readq(iommu->reg + DMAR_RTADDR_REG) & DMA_RTADDR_SMT)
+ scalable = true;
+ else
+ scalable = false;
-static int show_device_domain_translation(struct device *dev, void *data)
-{
- struct iommu_group *group;
-
- group = iommu_group_get(dev);
- if (group) {
/*
- * The group->mutex is held across the callback, which will
- * block calls to iommu_attach/detach_group/device. Hence,
+ * The iommu->lock is held across the callback, which will
+ * block calls to domain_attach/domain_detach. Hence,
* the domain of the device will not change during traversal.
*
- * All devices in an iommu group share a single domain, hence
- * we only dump the domain of the first device. Even though,
- * this code still possibly races with the iommu_unmap()
+ * Traversing page table possibly races with the iommu_unmap()
* interface. This could be solved by RCU-freeing the page
* table pages in the iommu_unmap() path.
*/
- iommu_group_for_each_dev(group, data,
- __show_device_domain_translation);
- iommu_group_put(group);
+ spin_lock(&iommu->lock);
+
+ context = iommu_context_addr(iommu, bus, devfn, 0);
+ if (!context || !context_present(context))
+ goto iommu_unlock;
+
+ if (scalable) { /* scalable mode */
+ struct pasid_entry *pasid_tbl, *pasid_tbl_entry;
+ struct pasid_dir_entry *dir_tbl, *dir_entry;
+ u16 dir_idx, tbl_idx, pgtt;
+ u64 pasid_dir_ptr;
+
+ pasid_dir_ptr = context->lo & VTD_PAGE_MASK;
+
+ /* Dump specified device domain mappings with PASID. */
+ dir_idx = pasid >> PASID_PDE_SHIFT;
+ tbl_idx = pasid & PASID_PTE_MASK;
+
+ dir_tbl = phys_to_virt(pasid_dir_ptr);
+ dir_entry = &dir_tbl[dir_idx];
+
+ pasid_tbl = get_pasid_table_from_pde(dir_entry);
+ if (!pasid_tbl)
+ goto iommu_unlock;
+
+ pasid_tbl_entry = &pasid_tbl[tbl_idx];
+ if (!pasid_pte_is_present(pasid_tbl_entry))
+ goto iommu_unlock;
+
+ /*
+ * According to PASID Granular Translation Type(PGTT),
+ * get the page table pointer.
+ */
+ pgtt = (u16)(pasid_tbl_entry->val[0] & GENMASK_ULL(8, 6)) >> 6;
+ agaw = (u8)(pasid_tbl_entry->val[0] & GENMASK_ULL(4, 2)) >> 2;
+
+ switch (pgtt) {
+ case PASID_ENTRY_PGTT_FL_ONLY:
+ pgd = pasid_tbl_entry->val[2];
+ break;
+ case PASID_ENTRY_PGTT_SL_ONLY:
+ case PASID_ENTRY_PGTT_NESTED:
+ pgd = pasid_tbl_entry->val[0];
+ break;
+ default:
+ goto iommu_unlock;
+ }
+ pgd &= VTD_PAGE_MASK;
+ } else { /* legacy mode */
+ pgd = context->lo & VTD_PAGE_MASK;
+ agaw = context->hi & 7;
+ }
+
+ seq_printf(m, "Device %04x:%02x:%02x.%x ",
+ iommu->segment, bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
+
+ if (scalable)
+ seq_printf(m, "with pasid %x @0x%llx\n", pasid, pgd);
+ else
+ seq_printf(m, "@0x%llx\n", pgd);
+
+ seq_printf(m, "%-17s\t%-18s\t%-18s\t%-18s\t%-18s\t%-s\n",
+ "IOVA_PFN", "PML5E", "PML4E", "PDPE", "PDE", "PTE");
+ pgtable_walk_level(m, phys_to_virt(pgd), agaw + 2, 0, path);
+
+ found = true;
+iommu_unlock:
+ spin_unlock(&iommu->lock);
+ if (found)
+ break;
}
+ rcu_read_unlock();
return 0;
}
-static int domain_translation_struct_show(struct seq_file *m, void *unused)
+static int dev_domain_translation_struct_show(struct seq_file *m, void *unused)
{
- return bus_for_each_dev(&pci_bus_type, NULL, m,
- show_device_domain_translation);
+ struct device_domain_info *info = (struct device_domain_info *)m->private;
+
+ return domain_translation_struct_show(m, info, IOMMU_NO_PASID);
}
-DEFINE_SHOW_ATTRIBUTE(domain_translation_struct);
+DEFINE_SHOW_ATTRIBUTE(dev_domain_translation_struct);
+
+static int pasid_domain_translation_struct_show(struct seq_file *m, void *unused)
+{
+ struct dev_pasid_info *dev_pasid = (struct dev_pasid_info *)m->private;
+ struct device_domain_info *info = dev_iommu_priv_get(dev_pasid->dev);
+
+ return domain_translation_struct_show(m, info, dev_pasid->pasid);
+}
+DEFINE_SHOW_ATTRIBUTE(pasid_domain_translation_struct);
static void invalidation_queue_entry_show(struct seq_file *m,
struct intel_iommu *iommu)
@@ -700,7 +782,7 @@ void intel_iommu_debugfs_create_dev(struct device_domain_info *info)
info->debugfs_dentry = debugfs_create_dir(dev_name(info->dev), intel_iommu_debug);
debugfs_create_file("domain_translation_struct", 0444, info->debugfs_dentry,
- NULL, &domain_translation_struct_fops);
+ info, &dev_domain_translation_struct_fops);
}
/* Remove the device debugfs directory. */
@@ -726,6 +808,9 @@ void intel_iommu_debugfs_create_dev_pasid(struct dev_pasid_info *dev_pasid)
sprintf(dir_name, "%x", dev_pasid->pasid);
dev_pasid->debugfs_dentry = debugfs_create_dir(dir_name, info->debugfs_dentry);
+
+ debugfs_create_file("domain_translation_struct", 0444, dev_pasid->debugfs_dentry,
+ dev_pasid, &pasid_domain_translation_struct_fops);
}
/* Remove the device pasid debugfs directory. */
--
2.34.1
From: Jingqi Liu <[email protected]>
Add a debugfs directory per pair of {device, pasid} if the mappings of
its page table are created and destroyed by the iommu_map/unmap()
interfaces. i.e. /sys/kernel/debug/iommu/intel/<device source id>/<pasid>.
Create a debugfs file in the directory for users to dump the page
table corresponding to {device, pasid}. e.g.
/sys/kernel/debug/iommu/intel/0000:00:02.0/1/domain_translation_struct.
For the default domain without pasid, it creates a debugfs file in the
debugfs device directory for users to dump its page table. e.g.
/sys/kernel/debug/iommu/intel/0000:00:02.0/domain_translation_struct.
When setting a domain to a PASID of device, create a debugfs file in
the pasid debugfs directory for users to dump the page table of the
specified pasid. Remove the debugfs device directory of the device
when releasing a device. e.g.
/sys/kernel/debug/iommu/intel/0000:00:01.0
Signed-off-by: Jingqi Liu <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Lu Baolu <[email protected]>
---
drivers/iommu/intel/iommu.h | 14 +++++++++
drivers/iommu/intel/debugfs.c | 53 +++++++++++++++++++++++++++++++----
drivers/iommu/intel/iommu.c | 7 +++++
3 files changed, 69 insertions(+), 5 deletions(-)
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index 7dac94f62b4e..f9c1dd1ccff8 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -716,12 +716,18 @@ struct device_domain_info {
struct intel_iommu *iommu; /* IOMMU used by this device */
struct dmar_domain *domain; /* pointer to domain */
struct pasid_table *pasid_table; /* pasid table */
+#ifdef CONFIG_INTEL_IOMMU_DEBUGFS
+ struct dentry *debugfs_dentry; /* pointer to device directory dentry */
+#endif
};
struct dev_pasid_info {
struct list_head link_domain; /* link to domain siblings */
struct device *dev;
ioasid_t pasid;
+#ifdef CONFIG_INTEL_IOMMU_DEBUGFS
+ struct dentry *debugfs_dentry; /* pointer to pasid directory dentry */
+#endif
};
static inline void __iommu_flush_cache(
@@ -883,8 +889,16 @@ static inline void intel_svm_remove_dev_pasid(struct device *dev, ioasid_t pasid
#ifdef CONFIG_INTEL_IOMMU_DEBUGFS
void intel_iommu_debugfs_init(void);
+void intel_iommu_debugfs_create_dev(struct device_domain_info *info);
+void intel_iommu_debugfs_remove_dev(struct device_domain_info *info);
+void intel_iommu_debugfs_create_dev_pasid(struct dev_pasid_info *dev_pasid);
+void intel_iommu_debugfs_remove_dev_pasid(struct dev_pasid_info *dev_pasid);
#else
static inline void intel_iommu_debugfs_init(void) {}
+static inline void intel_iommu_debugfs_create_dev(struct device_domain_info *info) {}
+static inline void intel_iommu_debugfs_remove_dev(struct device_domain_info *info) {}
+static inline void intel_iommu_debugfs_create_dev_pasid(struct dev_pasid_info *dev_pasid) {}
+static inline void intel_iommu_debugfs_remove_dev_pasid(struct dev_pasid_info *dev_pasid) {}
#endif /* CONFIG_INTEL_IOMMU_DEBUGFS */
extern const struct attribute_group *intel_iommu_groups[];
diff --git a/drivers/iommu/intel/debugfs.c b/drivers/iommu/intel/debugfs.c
index 497c1561d3d2..8a18a7be5215 100644
--- a/drivers/iommu/intel/debugfs.c
+++ b/drivers/iommu/intel/debugfs.c
@@ -111,6 +111,8 @@ static const struct iommu_regset iommu_regs_64[] = {
IOMMU_REGSET_ENTRY(VCRSP),
};
+static struct dentry *intel_iommu_debug;
+
static int iommu_regset_show(struct seq_file *m, void *unused)
{
struct dmar_drhd_unit *drhd;
@@ -671,16 +673,12 @@ static const struct file_operations dmar_perf_latency_fops = {
void __init intel_iommu_debugfs_init(void)
{
- struct dentry *intel_iommu_debug = debugfs_create_dir("intel",
- iommu_debugfs_dir);
+ intel_iommu_debug = debugfs_create_dir("intel", iommu_debugfs_dir);
debugfs_create_file("iommu_regset", 0444, intel_iommu_debug, NULL,
&iommu_regset_fops);
debugfs_create_file("dmar_translation_struct", 0444, intel_iommu_debug,
NULL, &dmar_translation_struct_fops);
- debugfs_create_file("domain_translation_struct", 0444,
- intel_iommu_debug, NULL,
- &domain_translation_struct_fops);
debugfs_create_file("invalidation_queue", 0444, intel_iommu_debug,
NULL, &invalidation_queue_fops);
#ifdef CONFIG_IRQ_REMAP
@@ -690,3 +688,48 @@ void __init intel_iommu_debugfs_init(void)
debugfs_create_file("dmar_perf_latency", 0644, intel_iommu_debug,
NULL, &dmar_perf_latency_fops);
}
+
+/*
+ * Create a debugfs directory for each device, and then create a
+ * debugfs file in this directory for users to dump the page table
+ * of the default domain. e.g.
+ * /sys/kernel/debug/iommu/intel/0000:00:01.0/domain_translation_struct
+ */
+void intel_iommu_debugfs_create_dev(struct device_domain_info *info)
+{
+ info->debugfs_dentry = debugfs_create_dir(dev_name(info->dev), intel_iommu_debug);
+
+ debugfs_create_file("domain_translation_struct", 0444, info->debugfs_dentry,
+ NULL, &domain_translation_struct_fops);
+}
+
+/* Remove the device debugfs directory. */
+void intel_iommu_debugfs_remove_dev(struct device_domain_info *info)
+{
+ debugfs_remove_recursive(info->debugfs_dentry);
+}
+
+/*
+ * Create a debugfs directory per pair of {device, pasid}, then create the
+ * corresponding debugfs file in this directory for users to dump its page
+ * table. e.g.
+ * /sys/kernel/debug/iommu/intel/0000:00:01.0/1/domain_translation_struct
+ *
+ * The debugfs only dumps the page tables whose mappings are created and
+ * destroyed by the iommu_map/unmap() interfaces. Check the mapping type
+ * of the domain before creating debugfs directory.
+ */
+void intel_iommu_debugfs_create_dev_pasid(struct dev_pasid_info *dev_pasid)
+{
+ struct device_domain_info *info = dev_iommu_priv_get(dev_pasid->dev);
+ char dir_name[10];
+
+ sprintf(dir_name, "%x", dev_pasid->pasid);
+ dev_pasid->debugfs_dentry = debugfs_create_dir(dir_name, info->debugfs_dentry);
+}
+
+/* Remove the device pasid debugfs directory. */
+void intel_iommu_debugfs_remove_dev_pasid(struct dev_pasid_info *dev_pasid)
+{
+ debugfs_remove_recursive(dev_pasid->debugfs_dentry);
+}
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 3685ba90ec88..d77d60bc418f 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -4409,6 +4409,8 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
}
}
+ intel_iommu_debugfs_create_dev(info);
+
return &iommu->iommu;
}
@@ -4418,6 +4420,7 @@ static void intel_iommu_release_device(struct device *dev)
dmar_remove_one_dev_info(dev);
intel_pasid_free_table(dev);
+ intel_iommu_debugfs_remove_dev(info);
dev_iommu_priv_set(dev, NULL);
kfree(info);
set_dma_ops(dev, NULL);
@@ -4710,6 +4713,7 @@ static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid)
spin_unlock_irqrestore(&dmar_domain->lock, flags);
domain_detach_iommu(dmar_domain, iommu);
+ intel_iommu_debugfs_remove_dev_pasid(dev_pasid);
kfree(dev_pasid);
out_tear_down:
intel_pasid_tear_down_entry(iommu, dev, pasid, false);
@@ -4762,6 +4766,9 @@ static int intel_iommu_set_dev_pasid(struct iommu_domain *domain,
list_add(&dev_pasid->link_domain, &dmar_domain->dev_pasids);
spin_unlock_irqrestore(&dmar_domain->lock, flags);
+ if (domain->type & __IOMMU_DOMAIN_PAGING)
+ intel_iommu_debugfs_create_dev_pasid(dev_pasid);
+
return 0;
out_detach_iommu:
domain_detach_iommu(dmar_domain, iommu);
--
2.34.1
On Mon, Oct 16, 2023 at 11:28:26AM +0800, Lu Baolu wrote:
> Jiapeng Chong (1):
> iommu/vt-d: Remove unused function
>
> Jingqi Liu (3):
> iommu/vt-d: debugfs: Dump entry pointing to huge page
> iommu/vt-d: debugfs: Create/remove debugfs file per {device, pasid}
> iommu/vt-d: debugfs: Support dumping a specified page table
Applied, thanks Baolu.