The patches reimplement the iommu table_group_ops for pSeries
for VFIO SPAPR TCE sub-driver thereby bringing consistency with
PowerNV implementation and getting rid of limitations/bugs which
were emanating from these differences on the earlier approach on
pSeries.
Structure of the patchset:
-------------------------
The first and fifth patches just code movements.
Second patch takes care of collecting the TCE and DDW information
for the vfio_iommu_spapr_tce_ddw_info during probe.
Third patch fixes the convention of using table[1] for VFs on
pSeries when used by the host driver.
Fourth patch fixes the VFIO to call TCE clear before unset window.
The last patch has the API reimplementations, please find the
details on its commit description.
Testing:
-------
Tested with nested guest for NVME card, Mellanox multi-function
card by attaching them to nested kvm guest running on a pSeries
lpar.
Also vfio-test [2] by Alex Willamson, was forked and updated to
add support for pSeries guest and used to test these patches[3].
Limitations/Known Issues:
------------------------
* The DMA window restrictions with SRIOV VF scenarios of having
maximum 1 dma window is taken care in the current patches itself.
However, the necessary changes required in
vfio_iommu_spapr_tce_ddw_info to expose the default window being
a 64-bit one and the qemu changes handle the same will be taken
care in future versions.
References:
----------
[1] https://lore.kernel.org/linuxppc-dev/[email protected]/
[2] https://github.com/awilliam/tests
[3] https://github.com/nnmwebmin/vfio-ppc-tests/tree/vfio-ppc-ex
---
Changelog:
v2: https://lore.kernel.org/linuxppc-dev/[email protected]/
- Rebased to upstream. So, required the explicit vmalloc.h inclusion as its
removed from the system header io.h now.
- Fixed the DLPAR hotplugged device assignment case. The dma window
property is backed up before removal. That copy is restored when required.
- Cleaned up bit more. Removed leftover debug prints and dump_stack()s.
- The warning at remap_pfn_range_notrack() during kvm guest boot is no longer
seen after the rebase.
v1: https://lore.kernel.org/linuxppc-dev/[email protected]/
- Rewrite as to stop borrowing the DMA windows and implemented
the table_group_ops for pSeries.
- Cover letter and Patch 6 has more details as this was a rewrite.
Shivaprasad G Bhat (6):
powerpc/iommu: Move pSeries specific functions to pseries/iommu.c
powerpc/pseries/iommu: Fix the VFIO_IOMMU_SPAPR_TCE_GET_INFO ioctl output
powerpc/pseries/iommu: Use the iommu table[0] for IOV VF's DDW
vfio/spapr: Always clear TCEs before unsetting the window
powerpc/iommu: Move dev_has_iommu_table() to iommu.c
powerpc/iommu: Reimplement the iommu_table_group_ops for pSeries
arch/powerpc/include/asm/iommu.h | 9 +-
arch/powerpc/kernel/eeh.c | 16 -
arch/powerpc/kernel/iommu.c | 170 +-----
arch/powerpc/platforms/powernv/pci-ioda.c | 6 +-
arch/powerpc/platforms/pseries/iommu.c | 708 +++++++++++++++++++++-
drivers/vfio/vfio_iommu_spapr_tce.c | 13 +-
6 files changed, 717 insertions(+), 205 deletions(-)
--
Signature
The PowerNV specific table_group_ops are defined in powernv/pci-ioda.c.
The pSeries specific table_group_ops are sitting in the generic powerpc
file. Move it to where it actually belong(pseries/iommu.c).
Only code movement, no functional changes intended.
Signed-off-by: Shivaprasad G Bhat <[email protected]>
---
arch/powerpc/include/asm/iommu.h | 4 +
arch/powerpc/kernel/iommu.c | 149 --------------------------------
arch/powerpc/platforms/pseries/iommu.c | 144 +++++++++++++++++++++++++++++++
3 files changed, 149 insertions(+), 148 deletions(-)
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 026695943550..744cc5fc22d3 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -156,6 +156,9 @@ extern int iommu_tce_table_put(struct iommu_table *tbl);
extern struct iommu_table *iommu_init_table(struct iommu_table *tbl,
int nid, unsigned long res_start, unsigned long res_end);
bool iommu_table_in_use(struct iommu_table *tbl);
+extern void iommu_table_reserve_pages(struct iommu_table *tbl,
+ unsigned long res_start, unsigned long res_end);
+extern void iommu_table_clear(struct iommu_table *tbl);
#define IOMMU_TABLE_GROUP_MAX_TABLES 2
@@ -218,7 +221,6 @@ extern long iommu_tce_xchg_no_kill(struct mm_struct *mm,
extern void iommu_tce_kill(struct iommu_table *tbl,
unsigned long entry, unsigned long pages);
-extern struct iommu_table_group_ops spapr_tce_table_group_ops;
#else
static inline void iommu_register_group(struct iommu_table_group *table_group,
int pci_domain_number,
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index b70b4f93561f..b5febc6c7a5e 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -643,7 +643,7 @@ void ppc_iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
tbl->it_ops->flush(tbl);
}
-static void iommu_table_clear(struct iommu_table *tbl)
+void iommu_table_clear(struct iommu_table *tbl)
{
/*
* In case of firmware assisted dump system goes through clean
@@ -684,7 +684,7 @@ static void iommu_table_clear(struct iommu_table *tbl)
#endif
}
-static void iommu_table_reserve_pages(struct iommu_table *tbl,
+void iommu_table_reserve_pages(struct iommu_table *tbl,
unsigned long res_start, unsigned long res_end)
{
int i;
@@ -1102,59 +1102,6 @@ void iommu_tce_kill(struct iommu_table *tbl,
}
EXPORT_SYMBOL_GPL(iommu_tce_kill);
-#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
-static int iommu_take_ownership(struct iommu_table *tbl)
-{
- unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
- int ret = 0;
-
- /*
- * VFIO does not control TCE entries allocation and the guest
- * can write new TCEs on top of existing ones so iommu_tce_build()
- * must be able to release old pages. This functionality
- * requires exchange() callback defined so if it is not
- * implemented, we disallow taking ownership over the table.
- */
- if (!tbl->it_ops->xchg_no_kill)
- return -EINVAL;
-
- spin_lock_irqsave(&tbl->large_pool.lock, flags);
- for (i = 0; i < tbl->nr_pools; i++)
- spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock);
-
- if (iommu_table_in_use(tbl)) {
- pr_err("iommu_tce: it_map is not empty");
- ret = -EBUSY;
- } else {
- memset(tbl->it_map, 0xff, sz);
- }
-
- for (i = 0; i < tbl->nr_pools; i++)
- spin_unlock(&tbl->pools[i].lock);
- spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
-
- return ret;
-}
-
-static void iommu_release_ownership(struct iommu_table *tbl)
-{
- unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
-
- spin_lock_irqsave(&tbl->large_pool.lock, flags);
- for (i = 0; i < tbl->nr_pools; i++)
- spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock);
-
- memset(tbl->it_map, 0, sz);
-
- iommu_table_reserve_pages(tbl, tbl->it_reserved_start,
- tbl->it_reserved_end);
-
- for (i = 0; i < tbl->nr_pools; i++)
- spin_unlock(&tbl->pools[i].lock);
- spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
-}
-#endif
-
int iommu_add_device(struct iommu_table_group *table_group, struct device *dev)
{
/*
@@ -1186,98 +1133,6 @@ int iommu_add_device(struct iommu_table_group *table_group, struct device *dev)
EXPORT_SYMBOL_GPL(iommu_add_device);
#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
-/*
- * A simple iommu_table_group_ops which only allows reusing the existing
- * iommu_table. This handles VFIO for POWER7 or the nested KVM.
- * The ops does not allow creating windows and only allows reusing the existing
- * one if it matches table_group->tce32_start/tce32_size/page_shift.
- */
-static unsigned long spapr_tce_get_table_size(__u32 page_shift,
- __u64 window_size, __u32 levels)
-{
- unsigned long size;
-
- if (levels > 1)
- return ~0U;
- size = window_size >> (page_shift - 3);
- return size;
-}
-
-static long spapr_tce_create_table(struct iommu_table_group *table_group, int num,
- __u32 page_shift, __u64 window_size, __u32 levels,
- struct iommu_table **ptbl)
-{
- struct iommu_table *tbl = table_group->tables[0];
-
- if (num > 0)
- return -EPERM;
-
- if (tbl->it_page_shift != page_shift ||
- tbl->it_size != (window_size >> page_shift) ||
- tbl->it_indirect_levels != levels - 1)
- return -EINVAL;
-
- *ptbl = iommu_tce_table_get(tbl);
- return 0;
-}
-
-static long spapr_tce_set_window(struct iommu_table_group *table_group,
- int num, struct iommu_table *tbl)
-{
- return tbl == table_group->tables[num] ? 0 : -EPERM;
-}
-
-static long spapr_tce_unset_window(struct iommu_table_group *table_group, int num)
-{
- return 0;
-}
-
-static long spapr_tce_take_ownership(struct iommu_table_group *table_group)
-{
- int i, j, rc = 0;
-
- for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
- struct iommu_table *tbl = table_group->tables[i];
-
- if (!tbl || !tbl->it_map)
- continue;
-
- rc = iommu_take_ownership(tbl);
- if (!rc)
- continue;
-
- for (j = 0; j < i; ++j)
- iommu_release_ownership(table_group->tables[j]);
- return rc;
- }
- return 0;
-}
-
-static void spapr_tce_release_ownership(struct iommu_table_group *table_group)
-{
- int i;
-
- for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
- struct iommu_table *tbl = table_group->tables[i];
-
- if (!tbl)
- continue;
-
- iommu_table_clear(tbl);
- if (tbl->it_map)
- iommu_release_ownership(tbl);
- }
-}
-
-struct iommu_table_group_ops spapr_tce_table_group_ops = {
- .get_table_size = spapr_tce_get_table_size,
- .create_table = spapr_tce_create_table,
- .set_window = spapr_tce_set_window,
- .unset_window = spapr_tce_unset_window,
- .take_ownership = spapr_tce_take_ownership,
- .release_ownership = spapr_tce_release_ownership,
-};
-
/*
* A simple iommu_ops to allow less cruft in generic VFIO code.
*/
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index b1e6d275cda9..330c69830660 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -54,6 +54,57 @@ enum {
DDW_EXT_QUERY_OUT_SIZE = 2
};
+static int iommu_take_ownership(struct iommu_table *tbl)
+{
+ unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
+ int ret = 0;
+
+ /*
+ * VFIO does not control TCE entries allocation and the guest
+ * can write new TCEs on top of existing ones so iommu_tce_build()
+ * must be able to release old pages. This functionality
+ * requires exchange() callback defined so if it is not
+ * implemented, we disallow taking ownership over the table.
+ */
+ if (!tbl->it_ops->xchg_no_kill)
+ return -EINVAL;
+
+ spin_lock_irqsave(&tbl->large_pool.lock, flags);
+ for (i = 0; i < tbl->nr_pools; i++)
+ spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock);
+
+ if (iommu_table_in_use(tbl)) {
+ pr_err("iommu_tce: it_map is not empty");
+ ret = -EBUSY;
+ } else {
+ memset(tbl->it_map, 0xff, sz);
+ }
+
+ for (i = 0; i < tbl->nr_pools; i++)
+ spin_unlock(&tbl->pools[i].lock);
+ spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
+
+ return ret;
+}
+
+static void iommu_release_ownership(struct iommu_table *tbl)
+{
+ unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
+
+ spin_lock_irqsave(&tbl->large_pool.lock, flags);
+ for (i = 0; i < tbl->nr_pools; i++)
+ spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock);
+
+ memset(tbl->it_map, 0, sz);
+
+ iommu_table_reserve_pages(tbl, tbl->it_reserved_start,
+ tbl->it_reserved_end);
+
+ for (i = 0; i < tbl->nr_pools; i++)
+ spin_unlock(&tbl->pools[i].lock);
+ spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
+}
+
static struct iommu_table *iommu_pseries_alloc_table(int node)
{
struct iommu_table *tbl;
@@ -67,6 +118,8 @@ static struct iommu_table *iommu_pseries_alloc_table(int node)
return tbl;
}
+struct iommu_table_group_ops spapr_tce_table_group_ops;
+
static struct iommu_table_group *iommu_pseries_alloc_group(int node)
{
struct iommu_table_group *table_group;
@@ -1651,6 +1704,97 @@ static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask)
return false;
}
+/*
+ * A simple iommu_table_group_ops which only allows reusing the existing
+ * iommu_table. This handles VFIO for POWER7 or the nested KVM.
+ * The ops does not allow creating windows and only allows reusing the existing
+ * one if it matches table_group->tce32_start/tce32_size/page_shift.
+ */
+static unsigned long spapr_tce_get_table_size(__u32 page_shift,
+ __u64 window_size, __u32 levels)
+{
+ unsigned long size;
+
+ if (levels > 1)
+ return ~0U;
+ size = window_size >> (page_shift - 3);
+ return size;
+}
+
+static long spapr_tce_create_table(struct iommu_table_group *table_group, int num,
+ __u32 page_shift, __u64 window_size, __u32 levels,
+ struct iommu_table **ptbl)
+{
+ struct iommu_table *tbl = table_group->tables[0];
+
+ if (num > 0)
+ return -EPERM;
+
+ if (tbl->it_page_shift != page_shift ||
+ tbl->it_size != (window_size >> page_shift) ||
+ tbl->it_indirect_levels != levels - 1)
+ return -EINVAL;
+
+ *ptbl = iommu_tce_table_get(tbl);
+ return 0;
+}
+
+static long spapr_tce_set_window(struct iommu_table_group *table_group,
+ int num, struct iommu_table *tbl)
+{
+ return tbl == table_group->tables[num] ? 0 : -EPERM;
+}
+
+static long spapr_tce_unset_window(struct iommu_table_group *table_group, int num)
+{
+ return 0;
+}
+
+static long spapr_tce_take_ownership(struct iommu_table_group *table_group)
+{
+ int i, j, rc = 0;
+
+ for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+ struct iommu_table *tbl = table_group->tables[i];
+
+ if (!tbl || !tbl->it_map)
+ continue;
+
+ rc = iommu_take_ownership(tbl);
+ if (!rc)
+ continue;
+
+ for (j = 0; j < i; ++j)
+ iommu_release_ownership(table_group->tables[j]);
+ return rc;
+ }
+ return 0;
+}
+
+static void spapr_tce_release_ownership(struct iommu_table_group *table_group)
+{
+ int i;
+
+ for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+ struct iommu_table *tbl = table_group->tables[i];
+
+ if (!tbl)
+ continue;
+
+ if (tbl->it_map)
+ iommu_release_ownership(tbl);
+ }
+}
+
+struct iommu_table_group_ops spapr_tce_table_group_ops = {
+ .get_table_size = spapr_tce_get_table_size,
+ .create_table = spapr_tce_create_table,
+ .set_window = spapr_tce_set_window,
+ .unset_window = spapr_tce_unset_window,
+ .take_ownership = spapr_tce_take_ownership,
+ .release_ownership = spapr_tce_release_ownership,
+};
+
static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action,
void *data)
{
This patch basically brings consistency with PowerNV approach
to use the first freely available iommu table when the default
window is removed.
The pSeries iommu code convention has been that the table[0] is
for the default 32 bit DMA window and the table[1] is for the
64 bit DDW.
With VFs having only 1 DMA window, the default has to be removed
for creating the larger DMA window. The existing code uses the
table[1] for that, while marking the table[0] as NULL. This is
fine as long as the host driver itself uses the device.
For the VFIO user, on pSeries there is no way to skip table[0]
as the VFIO subdriver uses the first freely available table.
The window 0, when created as 64-bit DDW in that context would
still be on table[0], as the maximum number of windows is 1.
This won't have any impact for the host driver as the table is
fetched from the device's iommu_table_base.
Signed-off-by: Shivaprasad G Bhat <[email protected]>
---
arch/powerpc/platforms/pseries/iommu.c | 12 +++++++-----
1 file changed, 7 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index eebb8296d431..cffa64cf60e7 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -155,7 +155,7 @@ static void iommu_pseries_free_group(struct iommu_table_group *table_group,
#endif
/* Default DMA window table is at index 0, while DDW at 1. SR-IOV
- * adapters only have table on index 1.
+ * adapters only have table on index 0(if not direct mapped).
*/
if (table_group->tables[0])
iommu_tce_table_put(table_group->tables[0]);
@@ -1527,6 +1527,11 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
clean_dma_window(pdn, win64->value);
goto out_del_list;
}
+ if (default_win_removed) {
+ iommu_tce_table_put(pci->table_group->tables[0]);
+ pci->table_group->tables[0] = NULL;
+ set_iommu_table_base(&dev->dev, NULL);
+ }
} else {
struct iommu_table *newtbl;
int i;
@@ -1556,15 +1561,12 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
1UL << len, page_shift, NULL, &iommu_table_lpar_multi_ops);
iommu_init_table(newtbl, pci->phb->node, start, end);
- pci->table_group->tables[1] = newtbl;
+ pci->table_group->tables[default_win_removed ? 0 : 1] = newtbl;
set_iommu_table_base(&dev->dev, newtbl);
}
if (default_win_removed) {
- iommu_tce_table_put(pci->table_group->tables[0]);
- pci->table_group->tables[0] = NULL;
-
/* default_win is valid here because default_win_removed == true */
of_remove_property(pdn, default_win);
dev_info(&dev->dev, "Removed default DMA window for %pOF\n", pdn);
The ioctl VFIO_IOMMU_SPAPR_TCE_GET_INFO is not reporting the
actuals on the platform as not all the details are correctly
collected during the platform probe/scan into the iommu_table_group.
Collect the information during the device setup time as the DMA
window property is already looked up on parent nodes anyway.
Signed-off-by: Shivaprasad G Bhat <[email protected]>
---
arch/powerpc/platforms/pseries/iommu.c | 81 ++++++++++++++++++++++++++------
1 file changed, 67 insertions(+), 14 deletions(-)
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 330c69830660..eebb8296d431 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -865,13 +865,6 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
be32_to_cpu(prop.tce_shift), NULL,
&iommu_table_lpar_multi_ops);
- /* Only for normal boot with default window. Doesn't matter even
- * if we set these with DDW which is 64bit during kdump, since
- * these will not be used during kdump.
- */
- ppci->table_group->tce32_start = be64_to_cpu(prop.dma_base);
- ppci->table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift);
-
if (!iommu_init_table(tbl, ppci->phb->node, 0, 0))
panic("Failed to initialize iommu table");
@@ -1623,6 +1616,71 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
return direct_mapping;
}
+static __u64 query_page_size_to_mask(u32 query_page_size)
+{
+ const long shift[] = {
+ (SZ_4K), (SZ_64K), (SZ_16M),
+ (SZ_32M), (SZ_64M), (SZ_128M),
+ (SZ_256M), (SZ_16G), (SZ_2M)
+ };
+ int i, ret = 0;
+
+ for (i = 0; i < ARRAY_SIZE(shift); i++) {
+ if (query_page_size & (1 << i))
+ ret |= shift[i];
+ }
+
+ return ret;
+}
+
+static void spapr_tce_init_table_group(struct pci_dev *pdev,
+ struct device_node *pdn,
+ struct dynamic_dma_window_prop prop)
+{
+ struct iommu_table_group *table_group = PCI_DN(pdn)->table_group;
+ u32 ddw_avail[DDW_APPLICABLE_SIZE];
+
+ struct ddw_query_response query;
+ int ret;
+
+ /* Only for normal boot with default window. Doesn't matter during
+ * kdump, since these will not be used during kdump.
+ */
+ if (is_kdump_kernel())
+ return;
+
+ if (table_group->max_dynamic_windows_supported != 0)
+ return; /* already initialized */
+
+ table_group->tce32_start = be64_to_cpu(prop.dma_base);
+ table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift);
+
+ if (!of_find_property(pdn, "ibm,dma-window", NULL))
+ dev_err(&pdev->dev, "default dma window missing!\n");
+
+ ret = of_property_read_u32_array(pdn, "ibm,ddw-applicable",
+ &ddw_avail[0], DDW_APPLICABLE_SIZE);
+ if (ret) {
+ table_group->max_dynamic_windows_supported = -1;
+ return;
+ }
+
+ ret = query_ddw(pdev, ddw_avail, &query, pdn);
+ if (ret) {
+ dev_err(&pdev->dev, "%s: query_ddw failed\n", __func__);
+ table_group->max_dynamic_windows_supported = -1;
+ return;
+ }
+
+ if (query.windows_available == 0)
+ table_group->max_dynamic_windows_supported = 1;
+ else
+ table_group->max_dynamic_windows_supported = IOMMU_TABLE_GROUP_MAX_TABLES;
+
+ table_group->max_levels = 1;
+ table_group->pgsizes |= query_page_size_to_mask(query.page_size);
+}
+
static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
{
struct device_node *pdn, *dn;
@@ -1662,13 +1720,6 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
be32_to_cpu(prop.tce_shift), NULL,
&iommu_table_lpar_multi_ops);
- /* Only for normal boot with default window. Doesn't matter even
- * if we set these with DDW which is 64bit during kdump, since
- * these will not be used during kdump.
- */
- pci->table_group->tce32_start = be64_to_cpu(prop.dma_base);
- pci->table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift);
-
iommu_init_table(tbl, pci->phb->node, 0, 0);
iommu_register_group(pci->table_group,
pci_domain_nr(pci->phb->bus), 0);
@@ -1677,6 +1728,8 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
pr_debug(" found DMA window, table: %p\n", pci->table_group);
}
+ spapr_tce_init_table_group(dev, pdn, prop);
+
set_iommu_table_base(&dev->dev, pci->table_group->tables[0]);
iommu_add_device(pci->table_group, &dev->dev);
}
Move function dev_has_iommu_table() to powerpc/kernel/iommu.c
as it is going to be used by machine specific iommu code as
well in subsequent patches.
Signed-off-by: Shivaprasad G Bhat <[email protected]>
---
arch/powerpc/include/asm/iommu.h | 1 +
arch/powerpc/kernel/eeh.c | 16 ----------------
arch/powerpc/kernel/iommu.c | 17 +++++++++++++++++
3 files changed, 18 insertions(+), 16 deletions(-)
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 744cc5fc22d3..784809e34abe 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -220,6 +220,7 @@ extern long iommu_tce_xchg_no_kill(struct mm_struct *mm,
enum dma_data_direction *direction);
extern void iommu_tce_kill(struct iommu_table *tbl,
unsigned long entry, unsigned long pages);
+int dev_has_iommu_table(struct device *dev, void *data);
#else
static inline void iommu_register_group(struct iommu_table_group *table_group,
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 6670063a7a6c..d03f17987fca 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -1273,22 +1273,6 @@ EXPORT_SYMBOL(eeh_dev_release);
#ifdef CONFIG_IOMMU_API
-static int dev_has_iommu_table(struct device *dev, void *data)
-{
- struct pci_dev *pdev = to_pci_dev(dev);
- struct pci_dev **ppdev = data;
-
- if (!dev)
- return 0;
-
- if (device_iommu_mapped(dev)) {
- *ppdev = pdev;
- return 1;
- }
-
- return 0;
-}
-
/**
* eeh_iommu_group_to_pe - Convert IOMMU group to EEH PE
* @group: IOMMU group
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index b5febc6c7a5e..ed8204cfa319 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -988,6 +988,23 @@ unsigned long iommu_direction_to_tce_perm(enum dma_data_direction dir)
EXPORT_SYMBOL_GPL(iommu_direction_to_tce_perm);
#ifdef CONFIG_IOMMU_API
+
+int dev_has_iommu_table(struct device *dev, void *data)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct pci_dev **ppdev = data;
+
+ if (!dev)
+ return 0;
+
+ if (device_iommu_mapped(dev)) {
+ *ppdev = pdev;
+ return 1;
+ }
+
+ return 0;
+}
+
/*
* SPAPR TCE API
*/
The PAPR expects the TCE table to have no entries at the time of
unset window(i.e. remove-pe). The TCE clear right now is done
before freeing the iommu table. On pSeries, the unset window
makes those entries inaccessible to the OS and the H_PUT/GET calls
fail on them with H_CONSTRAINED.
On PowerNV, this has no side effect as the TCE clear can be done
before the DMA window removal as well.
Signed-off-by: Shivaprasad G Bhat <[email protected]>
---
drivers/vfio/vfio_iommu_spapr_tce.c | 13 +++++++++----
1 file changed, 9 insertions(+), 4 deletions(-)
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index a94ec6225d31..5f9e7e477078 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -364,7 +364,6 @@ static void tce_iommu_release(void *iommu_data)
if (!tbl)
continue;
- tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
tce_iommu_free_table(container, tbl);
}
@@ -720,6 +719,8 @@ static long tce_iommu_remove_window(struct tce_container *container,
BUG_ON(!tbl->it_size);
+ tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
+
/* Detach groups from IOMMUs */
list_for_each_entry(tcegrp, &container->group_list, next) {
table_group = iommu_group_get_iommudata(tcegrp->grp);
@@ -738,7 +739,6 @@ static long tce_iommu_remove_window(struct tce_container *container,
}
/* Free table */
- tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
tce_iommu_free_table(container, tbl);
container->tables[num] = NULL;
@@ -1197,9 +1197,14 @@ static void tce_iommu_release_ownership(struct tce_container *container,
return;
}
- for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i)
- if (container->tables[i])
+ for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+ if (container->tables[i]) {
+ tce_iommu_clear(container, container->tables[i],
+ container->tables[i]->it_offset,
+ container->tables[i]->it_size);
table_group->ops->unset_window(table_group, i);
+ }
+ }
}
static long tce_iommu_take_ownership(struct tce_container *container,
PPC64 IOMMU API defines iommu_table_group_ops which handles DMA
windows for PEs, their ownership transfer, create/set/unset the TCE
tables for the Dynamic DMA wundows(DDW). VFIOS uses these APIs for
support on POWER.
The commit 9d67c9433509 ("powerpc/iommu: Add "borrowing"
iommu_table_group_ops") implemented partial support for this API with
"borrow" mechanism wherein the DMA windows if created already by the
host driver, they would be available for VFIO to use. Also, it didn't
have the support to control/modify the window size or the IO page
size.
The current patch implements all the necessary iommu_table_group_ops
APIs there by avoiding the "borrrowing". So, just the way it is on the
PowerNV platform, with this patch the iommu table group ownership is
transferred to the VFIO PPC subdriver, the iommu table, DMA windows
creation/deletion all driven through the APIs.
The pSeries uses the query-pe-dma-window, create-pe-dma-window and
reset-pe-dma-window RTAS calls for DMA window creation, deletion and
reset to defaul. The RTAs calls do show some minor differences to the
way things are to be handled on the pSeries which are listed below.
* On pSeries, the default DMA window size is "fixed" cannot be custom
sized as requested by the user. For non-SRIOV VFs, It is fixed at 2GB
and for SRIOV VFs, its variable sized based on the capacity assigned
to it during the VF assignment to the LPAR. So, for the default DMA
window alone the size if requested less than tce32_size, the smaller
size is enforced using the iommu table->it_size.
* The DMA start address for 32-bit window is 0, and for the 64-bit
window in case of PowerNV is hardcoded to TVE select (bit 59) at 512PiB
offset. This address is returned at the time of create_table() API call
(even before the window is created), the subsequent set_window() call
actually opens the DMA window. On pSeries, the DMA start address for
32-bit window is known from the 'ibm,dma-window' DT property. However,
the 64-bit window start address is not known until the create-pe-dma
RTAS call is made. So, the create_table() which returns the DMA window
start address actually opens the DMA window and returns the DMA start
address as returned by the Hypervisor for the create-pe-dma RTAS call.
* The reset-pe-dma RTAS call resets the DMA windows and restores the
default DMA window, however it does not clear the TCE table entries
if there are any. In case of ownership transfer from platform domain
which used direct mapping, the patch chooses remove-pe-dma instead of
reset-pe for the 64-bit window intentionally so that the
clear_dma_window() is called.
Other than the DMA window management changes mentioned above, the
patch also brings back the userspace view for the single level TCE
as it existed before commit 090bad39b237a ("powerpc/powernv: Add
indirect levels to it_userspace") along with the relavent
refactoring.
Signed-off-by: Shivaprasad G Bhat <[email protected]>
---
arch/powerpc/include/asm/iommu.h | 4
arch/powerpc/kernel/iommu.c | 4
arch/powerpc/platforms/powernv/pci-ioda.c | 6
arch/powerpc/platforms/pseries/iommu.c | 631 +++++++++++++++++++++++++----
4 files changed, 547 insertions(+), 98 deletions(-)
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 784809e34abe..1e0c2b2882c2 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -181,9 +181,9 @@ struct iommu_table_group_ops {
long (*unset_window)(struct iommu_table_group *table_group,
int num);
/* Switch ownership from platform code to external user (e.g. VFIO) */
- long (*take_ownership)(struct iommu_table_group *table_group);
+ long (*take_ownership)(struct iommu_table_group *table_group, struct device *dev);
/* Switch ownership from external user (e.g. VFIO) back to core */
- void (*release_ownership)(struct iommu_table_group *table_group);
+ void (*release_ownership)(struct iommu_table_group *table_group, struct device *dev);
};
struct iommu_table_group_link {
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index ed8204cfa319..76381e14e800 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1171,7 +1171,7 @@ spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain,
* The domain being set to PLATFORM from earlier
* BLOCKED. The table_group ownership has to be released.
*/
- table_group->ops->release_ownership(table_group);
+ table_group->ops->release_ownership(table_group, dev);
iommu_group_put(grp);
return 0;
@@ -1199,7 +1199,7 @@ spapr_tce_blocked_iommu_attach_dev(struct iommu_domain *platform_domain,
* also sets the dma_api ops
*/
table_group = iommu_group_get_iommudata(grp);
- ret = table_group->ops->take_ownership(table_group);
+ ret = table_group->ops->take_ownership(table_group, dev);
iommu_group_put(grp);
return ret;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 23f5b5093ec1..b0a14e48175c 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1537,7 +1537,8 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
}
}
-static long pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
+static long pnv_ioda2_take_ownership(struct iommu_table_group *table_group,
+ struct device *dev __maybe_unused)
{
struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
table_group);
@@ -1562,7 +1563,8 @@ static long pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
return 0;
}
-static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group)
+static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group,
+ struct device *dev __maybe_unused)
{
struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
table_group);
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index cffa64cf60e7..29211944565a 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -21,6 +21,7 @@
#include <linux/dma-mapping.h>
#include <linux/crash_dump.h>
#include <linux/memory.h>
+#include <linux/vmalloc.h>
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/iommu.h>
@@ -54,57 +55,6 @@ enum {
DDW_EXT_QUERY_OUT_SIZE = 2
};
-static int iommu_take_ownership(struct iommu_table *tbl)
-{
- unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
- int ret = 0;
-
- /*
- * VFIO does not control TCE entries allocation and the guest
- * can write new TCEs on top of existing ones so iommu_tce_build()
- * must be able to release old pages. This functionality
- * requires exchange() callback defined so if it is not
- * implemented, we disallow taking ownership over the table.
- */
- if (!tbl->it_ops->xchg_no_kill)
- return -EINVAL;
-
- spin_lock_irqsave(&tbl->large_pool.lock, flags);
- for (i = 0; i < tbl->nr_pools; i++)
- spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock);
-
- if (iommu_table_in_use(tbl)) {
- pr_err("iommu_tce: it_map is not empty");
- ret = -EBUSY;
- } else {
- memset(tbl->it_map, 0xff, sz);
- }
-
- for (i = 0; i < tbl->nr_pools; i++)
- spin_unlock(&tbl->pools[i].lock);
- spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
-
- return ret;
-}
-
-static void iommu_release_ownership(struct iommu_table *tbl)
-{
- unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
-
- spin_lock_irqsave(&tbl->large_pool.lock, flags);
- for (i = 0; i < tbl->nr_pools; i++)
- spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock);
-
- memset(tbl->it_map, 0, sz);
-
- iommu_table_reserve_pages(tbl, tbl->it_reserved_start,
- tbl->it_reserved_end);
-
- for (i = 0; i < tbl->nr_pools; i++)
- spin_unlock(&tbl->pools[i].lock);
- spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
-}
-
static struct iommu_table *iommu_pseries_alloc_table(int node)
{
struct iommu_table *tbl;
@@ -196,7 +146,7 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index,
}
-static void tce_free_pSeries(struct iommu_table *tbl, long index, long npages)
+static void tce_clear_pSeries(struct iommu_table *tbl, long index, long npages)
{
__be64 *tcep;
@@ -215,6 +165,37 @@ static unsigned long tce_get_pseries(struct iommu_table *tbl, long index)
return be64_to_cpu(*tcep);
}
+static long pseries_tce_iommu_userspace_view_alloc(struct iommu_table *tbl)
+{
+ unsigned long cb = ALIGN(sizeof(tbl->it_userspace[0]) * tbl->it_size, PAGE_SIZE);
+ unsigned long *uas;
+
+ if (tbl->it_indirect_levels) /* Impossible */
+ return -EPERM;
+
+ WARN_ON(tbl->it_userspace);
+
+ uas = vzalloc(cb);
+ if (!uas)
+ return -ENOMEM;
+
+ tbl->it_userspace = (__be64 *) uas;
+
+ return 0;
+}
+
+static void tce_iommu_userspace_view_free(struct iommu_table *tbl)
+{
+ vfree(tbl->it_userspace);
+ tbl->it_userspace = NULL;
+}
+
+static void tce_free_pSeries(struct iommu_table *tbl)
+{
+ if (!tbl->it_userspace)
+ tce_iommu_userspace_view_free(tbl);
+}
+
static void tce_free_pSeriesLP(unsigned long liobn, long, long, long);
static void tce_freemulti_pSeriesLP(struct iommu_table*, long, long);
@@ -629,7 +610,7 @@ struct iommu_table_ops iommu_table_lpar_multi_ops;
struct iommu_table_ops iommu_table_pseries_ops = {
.set = tce_build_pSeries,
- .clear = tce_free_pSeries,
+ .clear = tce_clear_pSeries,
.get = tce_get_pseries
};
@@ -738,17 +719,45 @@ static int tce_exchange_pseries(struct iommu_table *tbl, long index, unsigned
return rc;
}
+
+static __be64 *tce_useraddr_pSeriesLP(struct iommu_table *tbl, long index,
+ bool __always_unused alloc)
+{
+ return tbl->it_userspace ? &tbl->it_userspace[index - tbl->it_offset] : NULL;
+}
#endif
struct iommu_table_ops iommu_table_lpar_multi_ops = {
.set = tce_buildmulti_pSeriesLP,
#ifdef CONFIG_IOMMU_API
.xchg_no_kill = tce_exchange_pseries,
+ .useraddrptr = tce_useraddr_pSeriesLP,
#endif
.clear = tce_freemulti_pSeriesLP,
- .get = tce_get_pSeriesLP
+ .get = tce_get_pSeriesLP,
+ .free = tce_free_pSeries
};
+/*
+ * When the DMA window properties might have been removed,
+ * the parent node has the table_group setup on it.
+ */
+static struct device_node *pci_dma_find_parent_node(struct pci_dev *dev,
+ struct iommu_table_group *table_group)
+{
+ struct device_node *dn = pci_device_to_OF_node(dev);
+ struct pci_dn *rpdn;
+
+ for (; dn && PCI_DN(dn); dn = dn->parent) {
+ rpdn = PCI_DN(dn);
+
+ if (table_group == rpdn->table_group)
+ return dn;
+ }
+
+ return NULL;
+}
+
/*
* Find nearest ibm,dma-window (default DMA window) or direct DMA window or
* dynamic 64bit DMA window, walking up the device tree.
@@ -963,7 +972,7 @@ static void __remove_dma_window(struct device_node *np, u32 *ddw_avail, u64 liob
}
static void remove_dma_window(struct device_node *np, u32 *ddw_avail,
- struct property *win)
+ struct property *win, bool cleanup)
{
struct dynamic_dma_window_prop *dwp;
u64 liobn;
@@ -971,11 +980,44 @@ static void remove_dma_window(struct device_node *np, u32 *ddw_avail,
dwp = win->value;
liobn = (u64)be32_to_cpu(dwp->liobn);
- clean_dma_window(np, dwp);
+ if (cleanup)
+ clean_dma_window(np, dwp);
__remove_dma_window(np, ddw_avail, liobn);
}
-static int remove_ddw(struct device_node *np, bool remove_prop, const char *win_name)
+static void copy_property(struct device_node *pdn, const char *from, const char *to)
+{
+ struct property *src, *dst;
+
+ src = of_find_property(pdn, from, NULL);
+ if (!src)
+ return;
+
+ dst = kzalloc(sizeof(*dst), GFP_KERNEL);
+ if (!dst)
+ return;
+
+ dst->name = kstrdup(to, GFP_KERNEL);
+ dst->value = kmemdup(src->value, src->length, GFP_KERNEL);
+ dst->length = src->length;
+ if (!dst->name || !dst->value)
+ return;
+
+ if (of_add_property(pdn, dst)) {
+ pr_err("Unable to add DMA window property for %pOF", pdn);
+ goto free_prop;
+ }
+
+ return;
+
+free_prop:
+ kfree(dst->name);
+ kfree(dst->value);
+ kfree(dst);
+}
+
+static int remove_dma_window_named(struct device_node *np, bool remove_prop, const char *win_name,
+ bool cleanup)
{
struct property *win;
u32 ddw_avail[DDW_APPLICABLE_SIZE];
@@ -990,13 +1032,20 @@ static int remove_ddw(struct device_node *np, bool remove_prop, const char *win_
if (ret)
return 0;
-
if (win->length >= sizeof(struct dynamic_dma_window_prop))
- remove_dma_window(np, ddw_avail, win);
+ remove_dma_window(np, ddw_avail, win, cleanup);
if (!remove_prop)
return 0;
+ /* Default window property if removed is lost as reset-pe doesn't restore it.
+ * Though FDT has a copy of it, the DLPAR hotplugged devices will not have a
+ * node on FDT until next reboot. So, back it up.
+ */
+ if ((strcmp(win_name, "ibm,dma-window") == 0) &&
+ !of_find_property(np, "ibm,dma-window-saved", NULL))
+ copy_property(np, win_name, "ibm,dma-window-saved");
+
ret = of_remove_property(np, win);
if (ret)
pr_warn("%pOF: failed to remove DMA window property: %d\n",
@@ -1054,7 +1103,7 @@ static void find_existing_ddw_windows_named(const char *name)
for_each_node_with_property(pdn, name) {
dma64 = of_get_property(pdn, name, &len);
if (!dma64 || len < sizeof(*dma64)) {
- remove_ddw(pdn, true, name);
+ remove_dma_window_named(pdn, true, name, true);
continue;
}
@@ -1431,7 +1480,7 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
if (reset_win_ext)
goto out_failed;
- remove_dma_window(pdn, ddw_avail, default_win);
+ remove_dma_window(pdn, ddw_avail, default_win, true);
default_win_removed = true;
/* Query again, to check if the window is available */
@@ -1568,6 +1617,8 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
if (default_win_removed) {
/* default_win is valid here because default_win_removed == true */
+ if (!of_find_property(pdn, "ibm,dma-window-saved", NULL))
+ copy_property(pdn, "ibm,dma-window", "ibm,dma-window-saved");
of_remove_property(pdn, default_win);
dev_info(&dev->dev, "Removed default DMA window for %pOF\n", pdn);
}
@@ -1776,24 +1827,328 @@ static unsigned long spapr_tce_get_table_size(__u32 page_shift,
return size;
}
+static struct pci_dev *iommu_group_get_first_pci_dev(struct iommu_group *group)
+{
+ struct pci_dev *pdev = NULL;
+ int ret;
+
+ /* No IOMMU group ? */
+ if (!group)
+ return NULL;
+
+ ret = iommu_group_for_each_dev(group, &pdev, dev_has_iommu_table);
+ if (!ret || !pdev)
+ return NULL;
+ return pdev;
+}
+
+static void restore_default_dma_window(struct pci_dev *pdev, struct device_node *pdn)
+{
+ reset_dma_window(pdev, pdn);
+ copy_property(pdn, "ibm,dma-window-saved", "ibm,dma-window");
+}
+
+static long remove_dynamic_dma_windows(struct pci_dev *pdev, struct device_node *pdn)
+{
+ struct pci_dn *pci = PCI_DN(pdn);
+ struct dma_win *window;
+ bool direct_mapping;
+ int len;
+
+ if (find_existing_ddw(pdn, &pdev->dev.archdata.dma_offset, &len, &direct_mapping)) {
+ remove_dma_window_named(pdn, true, direct_mapping ?
+ DIRECT64_PROPNAME : DMA64_PROPNAME, true);
+ if (!direct_mapping) {
+ WARN_ON(!pci->table_group->tables[0] && !pci->table_group->tables[1]);
+
+ if (pci->table_group->tables[1]) {
+ iommu_tce_table_put(pci->table_group->tables[1]);
+ pci->table_group->tables[1] = NULL;
+ } else if (pci->table_group->tables[0]) {
+ /* Default window was removed and only the DDW exists */
+ iommu_tce_table_put(pci->table_group->tables[0]);
+ pci->table_group->tables[0] = NULL;
+ }
+ }
+ spin_lock(&dma_win_list_lock);
+ list_for_each_entry(window, &dma_win_list, list) {
+ if (window->device == pdn) {
+ list_del(&window->list);
+ kfree(window);
+ break;
+ }
+ }
+ spin_unlock(&dma_win_list_lock);
+ }
+
+ return 0;
+}
+
+static long pseries_setup_default_iommu_config(struct iommu_table_group *table_group,
+ struct device *dev)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ const __be32 *default_prop;
+ long liobn, offset, size;
+ struct device_node *pdn;
+ struct iommu_table *tbl;
+ struct pci_dn *pci;
+
+ pdn = pci_dma_find_parent_node(pdev, table_group);
+ if (!pdn || !PCI_DN(pdn)) {
+ dev_warn(&pdev->dev, "No table_group configured for the node %pOF\n", pdn);
+ return -1;
+ }
+ pci = PCI_DN(pdn);
+
+ /* The default window is restored if not present already on removal of DDW.
+ * However, if used by VFIO SPAPR sub driver, the user's order of removal of
+ * windows might have been different to not leading to auto restoration,
+ * suppose the DDW was removed first followed by the default one.
+ * So, restore the default window with reset-pe-dma call explicitly.
+ */
+ restore_default_dma_window(pdev, pdn);
+
+ default_prop = of_get_property(pdn, "ibm,dma-window", NULL);
+ of_parse_dma_window(pdn, default_prop, &liobn, &offset, &size);
+ tbl = iommu_pseries_alloc_table(pci->phb->node);
+ if (!tbl) {
+ dev_err(&pdev->dev, "couldn't create new IOMMU table\n");
+ return -1;
+ }
+
+ iommu_table_setparms_common(tbl, pci->phb->bus->number, liobn, offset,
+ size, IOMMU_PAGE_SHIFT_4K, NULL,
+ &iommu_table_lpar_multi_ops);
+ iommu_init_table(tbl, pci->phb->node, 0, 0);
+
+ pci->table_group->tables[0] = tbl;
+ set_iommu_table_base(&pdev->dev, tbl);
+
+ return 0;
+}
+
+static bool is_default_window_request(struct iommu_table_group *table_group, __u32 page_shift,
+ __u64 window_size)
+{
+ if ((window_size <= table_group->tce32_size) &&
+ (page_shift == IOMMU_PAGE_SHIFT_4K))
+ return true;
+
+ return false;
+}
+
static long spapr_tce_create_table(struct iommu_table_group *table_group, int num,
__u32 page_shift, __u64 window_size, __u32 levels,
struct iommu_table **ptbl)
{
- struct iommu_table *tbl = table_group->tables[0];
-
- if (num > 0)
- return -EPERM;
+ struct pci_dev *pdev = iommu_group_get_first_pci_dev(table_group->group);
+ u32 ddw_avail[DDW_APPLICABLE_SIZE];
+ struct ddw_create_response create;
+ unsigned long liobn, offset, size;
+ unsigned long start = 0, end = 0;
+ struct ddw_query_response query;
+ const __be32 *default_prop;
+ struct failed_ddw_pdn *fpdn;
+ unsigned int entries_shift;
+ unsigned int window_shift;
+ struct device_node *pdn;
+ struct iommu_table *tbl;
+ struct dma_win *window;
+ struct property *win64;
+ struct pci_dn *pci;
+ u64 win_addr;
+ int len, i;
+ long ret;
- if (tbl->it_page_shift != page_shift ||
- tbl->it_size != (window_size >> page_shift) ||
- tbl->it_indirect_levels != levels - 1)
+ if (!is_power_of_2(window_size) || levels > 1)
return -EINVAL;
+ window_shift = order_base_2(window_size);
+ entries_shift = window_shift - page_shift;
+
+ mutex_lock(&dma_win_init_mutex);
+
+ ret = -ENODEV;
+
+ pdn = pci_dma_find_parent_node(pdev, table_group);
+ if (!pdn || !PCI_DN(pdn)) { /* Niether of 32s|64-bit exist! */
+ dev_warn(&pdev->dev, "No dma-windows exist for the node %pOF\n", pdn);
+ goto out_failed;
+ }
+ pci = PCI_DN(pdn);
+
+ /* If the enable DDW failed for the pdn, dont retry! */
+ list_for_each_entry(fpdn, &failed_ddw_pdn_list, list) {
+ if (fpdn->pdn == pdn) {
+ dev_info(&pdev->dev, "%pOF in failed DDW device list\n", pdn);
+ goto out_unlock;
+ }
+ }
+
+ tbl = iommu_pseries_alloc_table(pci->phb->node);
+ if (!tbl) {
+ dev_dbg(&pdev->dev, "couldn't create new IOMMU table\n");
+ goto out_unlock;
+ }
+
+ if (num == 0) {
+ bool direct_mapping;
+ /* The request is not for default window? Ensure there is no DDW window already */
+ if (!is_default_window_request(table_group, page_shift, window_size)) {
+ if (find_existing_ddw(pdn, &pdev->dev.archdata.dma_offset, &len,
+ &direct_mapping)) {
+ dev_warn(&pdev->dev, "%pOF: 64-bit window already present.", pdn);
+ ret = -EPERM;
+ goto out_unlock;
+ }
+ } else {
+ /* Request is for Default window, ensure there is no DDW if there is a
+ * need to reset. reset-pe otherwise removes the DDW also
+ */
+ default_prop = of_get_property(pdn, "ibm,dma-window", NULL);
+ if (!default_prop) {
+ if (find_existing_ddw(pdn, &pdev->dev.archdata.dma_offset, &len,
+ &direct_mapping)) {
+ dev_warn(&pdev->dev, "%pOF: Attempt to create window#0 when 64-bit window is present. Preventing the attempt as that would destroy the 64-bit window",
+ pdn);
+ ret = -EPERM;
+ goto out_unlock;
+ }
+
+ restore_default_dma_window(pdev, pdn);
+
+ default_prop = of_get_property(pdn, "ibm,dma-window", NULL);
+ of_parse_dma_window(pdn, default_prop, &liobn, &offset, &size);
+ /* Limit the default window size to window_size */
+ iommu_table_setparms_common(tbl, pci->phb->bus->number, liobn,
+ offset, 1UL << window_shift,
+ IOMMU_PAGE_SHIFT_4K, NULL,
+ &iommu_table_lpar_multi_ops);
+ iommu_init_table(tbl, pci->phb->node, start, end);
+
+ table_group->tables[0] = tbl;
+
+ mutex_unlock(&dma_win_init_mutex);
+
+ goto exit;
+ }
+ }
+ }
+
+ ret = of_property_read_u32_array(pdn, "ibm,ddw-applicable",
+ &ddw_avail[0], DDW_APPLICABLE_SIZE);
+ if (ret) {
+ dev_info(&pdev->dev, "ibm,ddw-applicable not found\n");
+ goto out_failed;
+ }
+ ret = -ENODEV;
+
+ pr_err("%s: Calling query %pOF\n", __func__, pdn);
+ ret = query_ddw(pdev, ddw_avail, &query, pdn);
+ if (ret)
+ goto out_failed;
+ ret = -ENODEV;
+
+ len = window_shift;
+ if (query.largest_available_block < (1ULL << (len - page_shift))) {
+ dev_dbg(&pdev->dev, "can't map window 0x%llx with %llu %llu-sized pages\n",
+ 1ULL << len, query.largest_available_block,
+ 1ULL << page_shift);
+ ret = -EINVAL; /* Retry with smaller window size */
+ goto out_unlock;
+ }
+
+ if (create_ddw(pdev, ddw_avail, &create, page_shift, len)) {
+ pr_err("%s: Create ddw failed %pOF\n", __func__, pdn);
+ goto out_failed;
+ }
+
+ win_addr = ((u64)create.addr_hi << 32) | create.addr_lo;
+ win64 = ddw_property_create(DMA64_PROPNAME, create.liobn, win_addr, page_shift, len);
+ if (!win64)
+ goto remove_window;
+
+ ret = of_add_property(pdn, win64);
+ if (ret) {
+ dev_err(&pdev->dev, "unable to add DMA window property for %pOF: %ld", pdn, ret);
+ goto free_property;
+ }
+ ret = -ENODEV;
+
+ window = ddw_list_new_entry(pdn, win64->value);
+ if (!window)
+ goto remove_property;
+
+ window->direct = false;
+
+ for (i = 0; i < ARRAY_SIZE(pci->phb->mem_resources); i++) {
+ const unsigned long mask = IORESOURCE_MEM_64 | IORESOURCE_MEM;
+
+ /* Look for MMIO32 */
+ if ((pci->phb->mem_resources[i].flags & mask) == IORESOURCE_MEM) {
+ start = pci->phb->mem_resources[i].start;
+ end = pci->phb->mem_resources[i].end;
+ break;
+ }
+ }
+
+ /* New table for using DDW instead of the default DMA window */
+ iommu_table_setparms_common(tbl, pci->phb->bus->number, create.liobn, win_addr,
+ 1UL << len, page_shift, NULL, &iommu_table_lpar_multi_ops);
+ iommu_init_table(tbl, pci->phb->node, start, end);
+
+ pci->table_group->tables[num] = tbl;
+ set_iommu_table_base(&pdev->dev, tbl);
+ pdev->dev.archdata.dma_offset = win_addr;
+
+ spin_lock(&dma_win_list_lock);
+ list_add(&window->list, &dma_win_list);
+ spin_unlock(&dma_win_list_lock);
+
+ mutex_unlock(&dma_win_init_mutex);
+
+ goto exit;
+
+remove_property:
+ of_remove_property(pdn, win64);
+free_property:
+ kfree(win64->name);
+ kfree(win64->value);
+ kfree(win64);
+remove_window:
+ __remove_dma_window(pdn, ddw_avail, create.liobn);
+
+out_failed:
+ fpdn = kzalloc(sizeof(*fpdn), GFP_KERNEL);
+ if (!fpdn)
+ goto out_unlock;
+ fpdn->pdn = pdn;
+ list_add(&fpdn->list, &failed_ddw_pdn_list);
+
+out_unlock:
+ mutex_unlock(&dma_win_init_mutex);
+
+ return ret;
+exit:
+ /* Allocate the userspace view */
+ pseries_tce_iommu_userspace_view_alloc(tbl);
+ tbl->it_allocated_size = spapr_tce_get_table_size(page_shift, window_size, levels);
+
*ptbl = iommu_tce_table_get(tbl);
+
return 0;
}
+static bool is_default_window_table(struct iommu_table_group *table_group, struct iommu_table *tbl)
+{
+ if (((tbl->it_size << tbl->it_page_shift) <= table_group->tce32_size) &&
+ (tbl->it_page_shift == IOMMU_PAGE_SHIFT_4K))
+ return true;
+
+ return false;
+}
+
static long spapr_tce_set_window(struct iommu_table_group *table_group,
int num, struct iommu_table *tbl)
{
@@ -1802,43 +2157,135 @@ static long spapr_tce_set_window(struct iommu_table_group *table_group,
static long spapr_tce_unset_window(struct iommu_table_group *table_group, int num)
{
- return 0;
+ struct pci_dev *pdev = iommu_group_get_first_pci_dev(table_group->group);
+ struct device_node *dn = pci_device_to_OF_node(pdev), *pdn;
+ struct iommu_table *tbl = table_group->tables[num];
+ struct failed_ddw_pdn *fpdn;
+ struct dma_win *window;
+ const char *win_name;
+ struct pci_dn *pci;
+ int ret = -ENODEV;
+
+ mutex_lock(&dma_win_init_mutex);
+
+ if ((num == 0) && is_default_window_table(table_group, tbl))
+ win_name = "ibm,dma-window";
+ else
+ win_name = DMA64_PROPNAME;
+
+ pdn = pci_dma_find(dn, NULL);
+ if (!pdn || !PCI_DN(pdn)) { /* Niether of 32s|64-bit exist! */
+ dev_warn(&pdev->dev, "No dma-windows exist for the node %pOF\n", pdn);
+ goto out_failed;
+ }
+ pci = PCI_DN(pdn);
+
+ /* Dont clear the TCEs, User should have done it */
+ if (remove_dma_window_named(pdn, true, win_name, false)) {
+ pr_err("%s: The existing DDW removal failed for node %pOF\n", __func__, pdn);
+ goto out_failed; /* Could not remove it either! */
+ }
+
+ if (strcmp(win_name, DMA64_PROPNAME) == 0) {
+ spin_lock(&dma_win_list_lock);
+ list_for_each_entry(window, &dma_win_list, list) {
+ if (window->device == pdn) {
+ list_del(&window->list);
+ kfree(window);
+ break;
+ }
+ }
+ spin_unlock(&dma_win_list_lock);
+ }
+
+ iommu_tce_table_put(table_group->tables[num]);
+ table_group->tables[num] = NULL;
+
+ ret = 0;
+
+ goto out_unlock;
+
+out_failed:
+ fpdn = kzalloc(sizeof(*fpdn), GFP_KERNEL);
+ if (!fpdn)
+ goto out_unlock;
+ fpdn->pdn = pdn;
+ list_add(&fpdn->list, &failed_ddw_pdn_list);
+
+out_unlock:
+ mutex_unlock(&dma_win_init_mutex);
+
+ return ret;
}
-static long spapr_tce_take_ownership(struct iommu_table_group *table_group)
+static long spapr_tce_take_ownership(struct iommu_table_group *table_group, struct device *dev)
{
- int i, j, rc = 0;
+ struct iommu_table *tbl = table_group->tables[0];
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct device_node *dn = pci_device_to_OF_node(pdev);
+ struct device_node *pdn;
- for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
- struct iommu_table *tbl = table_group->tables[i];
+ /* SRIOV VFs using direct map by the host driver OR multifunction devices
+ * where the ownership was taken on the attempt by the first function
+ */
+ if (!tbl && (table_group->max_dynamic_windows_supported != 1))
+ return 0;
- if (!tbl || !tbl->it_map)
- continue;
+ mutex_lock(&dma_win_init_mutex);
- rc = iommu_take_ownership(tbl);
- if (!rc)
- continue;
+ pdn = pci_dma_find(dn, NULL);
+ if (!pdn || !PCI_DN(pdn)) { /* Niether of 32s|64-bit exist! */
+ dev_warn(&pdev->dev, "No dma-windows exist for the node %pOF\n", pdn);
+ mutex_unlock(&dma_win_init_mutex);
+ return -1;
+ }
- for (j = 0; j < i; ++j)
- iommu_release_ownership(table_group->tables[j]);
- return rc;
+ /*
+ * Though rtas call reset-pe removes the DDW, it doesn't clear the entries on the table
+ * if there are any. In case of direct map, the entries will be left over, which
+ * is fine for PEs with 2 DMA windows where the second window is created with create-pe
+ * at which point the table is cleared. However, on VFs having only one DMA window, the
+ * default window would end up seeing the entries left over from the direct map done
+ * on the second window. So, remove the ddw explicitly so that clean_dma_window()
+ * cleans up the entries if any.
+ */
+ if (remove_dynamic_dma_windows(pdev, pdn)) {
+ dev_warn(&pdev->dev, "The existing DDW removal failed for node %pOF\n", pdn);
+ mutex_unlock(&dma_win_init_mutex);
+ return -1;
}
+
+ /* The table_group->tables[0] is not null now, it must be the default window
+ * Remove it, let the userspace create it as it needs.
+ */
+ if (table_group->tables[0]) {
+ remove_dma_window_named(pdn, true, "ibm,dma-window", true);
+ iommu_tce_table_put(tbl);
+ table_group->tables[0] = NULL;
+ }
+ set_iommu_table_base(dev, NULL);
+
+ mutex_unlock(&dma_win_init_mutex);
+
return 0;
}
-static void spapr_tce_release_ownership(struct iommu_table_group *table_group)
+static void spapr_tce_release_ownership(struct iommu_table_group *table_group, struct device *dev)
{
- int i;
+ struct iommu_table *tbl = table_group->tables[0];
- for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
- struct iommu_table *tbl = table_group->tables[i];
+ if (tbl) { /* Default window already restored */
+ return;
+ }
- if (!tbl)
- continue;
+ mutex_lock(&dma_win_init_mutex);
- if (tbl->it_map)
- iommu_release_ownership(tbl);
- }
+ /* Restore the default window */
+ pseries_setup_default_iommu_config(table_group, dev);
+
+ mutex_unlock(&dma_win_init_mutex);
+
+ return;
}
struct iommu_table_group_ops spapr_tce_table_group_ops = {
@@ -1911,8 +2358,8 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti
* we have to remove the property when releasing
* the device node.
*/
- if (remove_ddw(np, false, DIRECT64_PROPNAME))
- remove_ddw(np, false, DMA64_PROPNAME);
+ if (remove_dma_window_named(np, false, DIRECT64_PROPNAME, true))
+ remove_dma_window_named(np, false, DMA64_PROPNAME, true);
if (pci && pci->table_group)
iommu_pseries_free_group(pci->table_group,
Hi Shivaprasad,
kernel test robot noticed the following build warnings:
[auto build test WARNING on powerpc/fixes]
[also build test WARNING on awilliam-vfio/next awilliam-vfio/for-linus linus/master v6.10-rc3]
[cannot apply to powerpc/next next-20240612]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Shivaprasad-G-Bhat/powerpc-iommu-Move-pSeries-specific-functions-to-pseries-iommu-c/20240611-203313
base: https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git fixes
patch link: https://lore.kernel.org/r/171810901192.1721.18057294492426295643.stgit%40linux.ibm.com
patch subject: [PATCH v3 6/6] powerpc/iommu: Reimplement the iommu_table_group_ops for pSeries
config: powerpc64-randconfig-001-20240612 (https://download.01.org/0day-ci/archive/20240612/[email protected]/config)
compiler: powerpc64-linux-gcc (GCC) 13.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240612/[email protected]/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
All warnings (new ones prefixed by >>):
arch/powerpc/platforms/pseries/iommu.c: In function 'spapr_tce_create_table':
>> arch/powerpc/platforms/pseries/iommu.c:1953:22: warning: variable 'entries_shift' set but not used [-Wunused-but-set-variable]
1953 | unsigned int entries_shift;
| ^~~~~~~~~~~~~
arch/powerpc/platforms/pseries/iommu.c: In function 'spapr_tce_unset_window':
>> arch/powerpc/platforms/pseries/iommu.c:2166:24: warning: variable 'pci' set but not used [-Wunused-but-set-variable]
2166 | struct pci_dn *pci;
| ^~~
vim +/entries_shift +1953 arch/powerpc/platforms/pseries/iommu.c
1940
1941 static long spapr_tce_create_table(struct iommu_table_group *table_group, int num,
1942 __u32 page_shift, __u64 window_size, __u32 levels,
1943 struct iommu_table **ptbl)
1944 {
1945 struct pci_dev *pdev = iommu_group_get_first_pci_dev(table_group->group);
1946 u32 ddw_avail[DDW_APPLICABLE_SIZE];
1947 struct ddw_create_response create;
1948 unsigned long liobn, offset, size;
1949 unsigned long start = 0, end = 0;
1950 struct ddw_query_response query;
1951 const __be32 *default_prop;
1952 struct failed_ddw_pdn *fpdn;
> 1953 unsigned int entries_shift;
1954 unsigned int window_shift;
1955 struct device_node *pdn;
1956 struct iommu_table *tbl;
1957 struct dma_win *window;
1958 struct property *win64;
1959 struct pci_dn *pci;
1960 u64 win_addr;
1961 int len, i;
1962 long ret;
1963
1964 if (!is_power_of_2(window_size) || levels > 1)
1965 return -EINVAL;
1966
1967 window_shift = order_base_2(window_size);
1968 entries_shift = window_shift - page_shift;
1969
1970 mutex_lock(&dma_win_init_mutex);
1971
1972 ret = -ENODEV;
1973
1974 pdn = pci_dma_find_parent_node(pdev, table_group);
1975 if (!pdn || !PCI_DN(pdn)) { /* Niether of 32s|64-bit exist! */
1976 dev_warn(&pdev->dev, "No dma-windows exist for the node %pOF\n", pdn);
1977 goto out_failed;
1978 }
1979 pci = PCI_DN(pdn);
1980
1981 /* If the enable DDW failed for the pdn, dont retry! */
1982 list_for_each_entry(fpdn, &failed_ddw_pdn_list, list) {
1983 if (fpdn->pdn == pdn) {
1984 dev_info(&pdev->dev, "%pOF in failed DDW device list\n", pdn);
1985 goto out_unlock;
1986 }
1987 }
1988
1989 tbl = iommu_pseries_alloc_table(pci->phb->node);
1990 if (!tbl) {
1991 dev_dbg(&pdev->dev, "couldn't create new IOMMU table\n");
1992 goto out_unlock;
1993 }
1994
1995 if (num == 0) {
1996 bool direct_mapping;
1997 /* The request is not for default window? Ensure there is no DDW window already */
1998 if (!is_default_window_request(table_group, page_shift, window_size)) {
1999 if (find_existing_ddw(pdn, &pdev->dev.archdata.dma_offset, &len,
2000 &direct_mapping)) {
2001 dev_warn(&pdev->dev, "%pOF: 64-bit window already present.", pdn);
2002 ret = -EPERM;
2003 goto out_unlock;
2004 }
2005 } else {
2006 /* Request is for Default window, ensure there is no DDW if there is a
2007 * need to reset. reset-pe otherwise removes the DDW also
2008 */
2009 default_prop = of_get_property(pdn, "ibm,dma-window", NULL);
2010 if (!default_prop) {
2011 if (find_existing_ddw(pdn, &pdev->dev.archdata.dma_offset, &len,
2012 &direct_mapping)) {
2013 dev_warn(&pdev->dev, "%pOF: Attempt to create window#0 when 64-bit window is present. Preventing the attempt as that would destroy the 64-bit window",
2014 pdn);
2015 ret = -EPERM;
2016 goto out_unlock;
2017 }
2018
2019 restore_default_dma_window(pdev, pdn);
2020
2021 default_prop = of_get_property(pdn, "ibm,dma-window", NULL);
2022 of_parse_dma_window(pdn, default_prop, &liobn, &offset, &size);
2023 /* Limit the default window size to window_size */
2024 iommu_table_setparms_common(tbl, pci->phb->bus->number, liobn,
2025 offset, 1UL << window_shift,
2026 IOMMU_PAGE_SHIFT_4K, NULL,
2027 &iommu_table_lpar_multi_ops);
2028 iommu_init_table(tbl, pci->phb->node, start, end);
2029
2030 table_group->tables[0] = tbl;
2031
2032 mutex_unlock(&dma_win_init_mutex);
2033
2034 goto exit;
2035 }
2036 }
2037 }
2038
2039 ret = of_property_read_u32_array(pdn, "ibm,ddw-applicable",
2040 &ddw_avail[0], DDW_APPLICABLE_SIZE);
2041 if (ret) {
2042 dev_info(&pdev->dev, "ibm,ddw-applicable not found\n");
2043 goto out_failed;
2044 }
2045 ret = -ENODEV;
2046
2047 pr_err("%s: Calling query %pOF\n", __func__, pdn);
2048 ret = query_ddw(pdev, ddw_avail, &query, pdn);
2049 if (ret)
2050 goto out_failed;
2051 ret = -ENODEV;
2052
2053 len = window_shift;
2054 if (query.largest_available_block < (1ULL << (len - page_shift))) {
2055 dev_dbg(&pdev->dev, "can't map window 0x%llx with %llu %llu-sized pages\n",
2056 1ULL << len, query.largest_available_block,
2057 1ULL << page_shift);
2058 ret = -EINVAL; /* Retry with smaller window size */
2059 goto out_unlock;
2060 }
2061
2062 if (create_ddw(pdev, ddw_avail, &create, page_shift, len)) {
2063 pr_err("%s: Create ddw failed %pOF\n", __func__, pdn);
2064 goto out_failed;
2065 }
2066
2067 win_addr = ((u64)create.addr_hi << 32) | create.addr_lo;
2068 win64 = ddw_property_create(DMA64_PROPNAME, create.liobn, win_addr, page_shift, len);
2069 if (!win64)
2070 goto remove_window;
2071
2072 ret = of_add_property(pdn, win64);
2073 if (ret) {
2074 dev_err(&pdev->dev, "unable to add DMA window property for %pOF: %ld", pdn, ret);
2075 goto free_property;
2076 }
2077 ret = -ENODEV;
2078
2079 window = ddw_list_new_entry(pdn, win64->value);
2080 if (!window)
2081 goto remove_property;
2082
2083 window->direct = false;
2084
2085 for (i = 0; i < ARRAY_SIZE(pci->phb->mem_resources); i++) {
2086 const unsigned long mask = IORESOURCE_MEM_64 | IORESOURCE_MEM;
2087
2088 /* Look for MMIO32 */
2089 if ((pci->phb->mem_resources[i].flags & mask) == IORESOURCE_MEM) {
2090 start = pci->phb->mem_resources[i].start;
2091 end = pci->phb->mem_resources[i].end;
2092 break;
2093 }
2094 }
2095
2096 /* New table for using DDW instead of the default DMA window */
2097 iommu_table_setparms_common(tbl, pci->phb->bus->number, create.liobn, win_addr,
2098 1UL << len, page_shift, NULL, &iommu_table_lpar_multi_ops);
2099 iommu_init_table(tbl, pci->phb->node, start, end);
2100
2101 pci->table_group->tables[num] = tbl;
2102 set_iommu_table_base(&pdev->dev, tbl);
2103 pdev->dev.archdata.dma_offset = win_addr;
2104
2105 spin_lock(&dma_win_list_lock);
2106 list_add(&window->list, &dma_win_list);
2107 spin_unlock(&dma_win_list_lock);
2108
2109 mutex_unlock(&dma_win_init_mutex);
2110
2111 goto exit;
2112
2113 remove_property:
2114 of_remove_property(pdn, win64);
2115 free_property:
2116 kfree(win64->name);
2117 kfree(win64->value);
2118 kfree(win64);
2119 remove_window:
2120 __remove_dma_window(pdn, ddw_avail, create.liobn);
2121
2122 out_failed:
2123 fpdn = kzalloc(sizeof(*fpdn), GFP_KERNEL);
2124 if (!fpdn)
2125 goto out_unlock;
2126 fpdn->pdn = pdn;
2127 list_add(&fpdn->list, &failed_ddw_pdn_list);
2128
2129 out_unlock:
2130 mutex_unlock(&dma_win_init_mutex);
2131
2132 return ret;
2133 exit:
2134 /* Allocate the userspace view */
2135 pseries_tce_iommu_userspace_view_alloc(tbl);
2136 tbl->it_allocated_size = spapr_tce_get_table_size(page_shift, window_size, levels);
2137
2138 *ptbl = iommu_tce_table_get(tbl);
2139
2140 return 0;
2141 }
2142
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
Hi Shivaprasad,
kernel test robot noticed the following build errors:
[auto build test ERROR on powerpc/fixes]
[also build test ERROR on awilliam-vfio/next awilliam-vfio/for-linus linus/master v6.10-rc3]
[cannot apply to powerpc/next next-20240613]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]
url: https://github.com/intel-lab-lkp/linux/commits/Shivaprasad-G-Bhat/powerpc-iommu-Move-pSeries-specific-functions-to-pseries-iommu-c/20240611-203313
base: https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git fixes
patch link: https://lore.kernel.org/r/171810901192.1721.18057294492426295643.stgit%40linux.ibm.com
patch subject: [PATCH v3 6/6] powerpc/iommu: Reimplement the iommu_table_group_ops for pSeries
config: powerpc64-randconfig-r133-20240614 (https://download.01.org/0day-ci/archive/20240614/[email protected]/config)
compiler: clang version 19.0.0git (https://github.com/llvm/llvm-project 78ee473784e5ef6f0b19ce4cb111fb6e4d23c6b2)
reproduce: (https://download.01.org/0day-ci/archive/20240614/[email protected]/reproduce)
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
All errors (new ones prefixed by >>):
In file included from arch/powerpc/platforms/pseries/iommu.c:16:
In file included from include/linux/mm.h:2253:
include/linux/vmstat.h:500:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
500 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
| ~~~~~~~~~~~~~~~~~~~~~ ^
501 | item];
| ~~~~
include/linux/vmstat.h:507:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
507 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
| ~~~~~~~~~~~~~~~~~~~~~ ^
508 | NR_VM_NUMA_EVENT_ITEMS +
| ~~~~~~~~~~~~~~~~~~~~~~
include/linux/vmstat.h:514:36: warning: arithmetic between different enumeration types ('enum node_stat_item' and 'enum lru_list') [-Wenum-enum-conversion]
514 | return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_"
| ~~~~~~~~~~~ ^ ~~~
include/linux/vmstat.h:519:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
519 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
| ~~~~~~~~~~~~~~~~~~~~~ ^
520 | NR_VM_NUMA_EVENT_ITEMS +
| ~~~~~~~~~~~~~~~~~~~~~~
include/linux/vmstat.h:528:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
528 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
| ~~~~~~~~~~~~~~~~~~~~~ ^
529 | NR_VM_NUMA_EVENT_ITEMS +
| ~~~~~~~~~~~~~~~~~~~~~~
>> arch/powerpc/platforms/pseries/iommu.c:1839:47: error: use of undeclared identifier 'dev_has_iommu_table'; did you mean 'device_iommu_capable'?
1839 | ret = iommu_group_for_each_dev(group, &pdev, dev_has_iommu_table);
| ^~~~~~~~~~~~~~~~~~~
| device_iommu_capable
include/linux/iommu.h:1079:20: note: 'device_iommu_capable' declared here
1079 | static inline bool device_iommu_capable(struct device *dev, enum iommu_cap cap)
| ^
arch/powerpc/platforms/pseries/iommu.c:1953:15: warning: variable 'entries_shift' set but not used [-Wunused-but-set-variable]
1953 | unsigned int entries_shift;
| ^
arch/powerpc/platforms/pseries/iommu.c:2166:17: warning: variable 'pci' set but not used [-Wunused-but-set-variable]
2166 | struct pci_dn *pci;
| ^
7 warnings and 1 error generated.
vim +1839 arch/powerpc/platforms/pseries/iommu.c
1829
1830 static struct pci_dev *iommu_group_get_first_pci_dev(struct iommu_group *group)
1831 {
1832 struct pci_dev *pdev = NULL;
1833 int ret;
1834
1835 /* No IOMMU group ? */
1836 if (!group)
1837 return NULL;
1838
> 1839 ret = iommu_group_for_each_dev(group, &pdev, dev_has_iommu_table);
1840 if (!ret || !pdev)
1841 return NULL;
1842 return pdev;
1843 }
1844
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki