@@ -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,
@@ -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.
*/
@@ -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)
{
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 <sbhat@linux.ibm.com> --- 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(-)