powerpc/powernv/iommu: Add real mode version of iommu_table_ops::exchange()

In real mode, TCE tables are invalidated using special
cache-inhibited store instructions which are not available in
virtual mode

This defines and implements exchange_rm() callback. This does not
define set_rm/clear_rm/flush_rm callbacks as there is no user for those -
exchange/exchange_rm are only to be used by KVM for VFIO.

The exchange_rm callback is defined for IODA1/IODA2 powernv platforms.

This replaces list_for_each_entry_rcu with its lockless version as
from now on pnv_pci_ioda2_tce_invalidate() can be called in
the real mode too.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

3 files changed, 57 insertions, 1 deletions

diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 2c1d50792944..4554699aec02 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -64,6 +64,11 @@ struct iommu_table_ops {
                         long index,
                         unsigned long *hpa,
                         enum dma_data_direction *direction);
+        /* Real mode */
+        int (*exchange_rm)(struct iommu_table *tbl,
+                        long index,
+                        unsigned long *hpa,
+                        enum dma_data_direction *direction);
 #endif
         void (*clear)(struct iommu_table *tbl,
                         long index, long npages);
@@ -208,6 +213,8 @@ extern void iommu_del_device(struct device *dev);
 extern int __init tce_iommu_bus_notifier_init(void);
 extern long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
                 unsigned long *hpa, enum dma_data_direction *direction);
+extern long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry,
+                unsigned long *hpa, enum dma_data_direction *direction);
 #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 5f202a566ec5..685a4767b722 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1004,6 +1004,31 @@ long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
 }
 EXPORT_SYMBOL_GPL(iommu_tce_xchg);
 
+#ifdef CONFIG_PPC_BOOK3S_64
+long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry,
+                unsigned long *hpa, enum dma_data_direction *direction)
+{
+        long ret;
+
+        ret = tbl->it_ops->exchange_rm(tbl, entry, hpa, direction);
+
+        if (!ret && ((*direction == DMA_FROM_DEVICE) ||
+                        (*direction == DMA_BIDIRECTIONAL))) {
+                struct page *pg = realmode_pfn_to_page(*hpa >> PAGE_SHIFT);
+
+                if (likely(pg)) {
+                        SetPageDirty(pg);
+                } else {
+                        tbl->it_ops->exchange_rm(tbl, entry, hpa, direction);
+                        ret = -EFAULT;
+                }
+        }
+
+        return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_xchg_rm);
+#endif
+
 int iommu_take_ownership(struct iommu_table *tbl)
 {
         unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index e36738291c32..572e9c9f1ea0 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1860,6 +1860,17 @@ static int pnv_ioda1_tce_xchg(struct iommu_table *tbl, long index,
 
         return ret;
 }
+
+static int pnv_ioda1_tce_xchg_rm(struct iommu_table *tbl, long index,
+                unsigned long *hpa, enum dma_data_direction *direction)
+{
+        long ret = pnv_tce_xchg(tbl, index, hpa, direction);
+
+        if (!ret)
+                pnv_pci_p7ioc_tce_invalidate(tbl, index, 1, true);
+
+        return ret;
+}
 #endif
 
 static void pnv_ioda1_tce_free(struct iommu_table *tbl, long index,
@@ -1874,6 +1885,7 @@ static struct iommu_table_ops pnv_ioda1_iommu_ops = {
         .set = pnv_ioda1_tce_build,
 #ifdef CONFIG_IOMMU_API
         .exchange = pnv_ioda1_tce_xchg,
+        .exchange_rm = pnv_ioda1_tce_xchg_rm,
 #endif
         .clear = pnv_ioda1_tce_free,
         .get = pnv_tce_get,
@@ -1948,7 +1960,7 @@ static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl,
 {
         struct iommu_table_group_link *tgl;
 
-        list_for_each_entry_rcu(tgl, &tbl->it_group_list, next) {
+        list_for_each_entry_lockless(tgl, &tbl->it_group_list, next) {
                 struct pnv_ioda_pe *pe = container_of(tgl->table_group,
                                 struct pnv_ioda_pe, table_group);
                 struct pnv_phb *phb = pe->phb;
@@ -2004,6 +2016,17 @@ static int pnv_ioda2_tce_xchg(struct iommu_table *tbl, long index,
 
         return ret;
 }
+
+static int pnv_ioda2_tce_xchg_rm(struct iommu_table *tbl, long index,
+                unsigned long *hpa, enum dma_data_direction *direction)
+{
+        long ret = pnv_tce_xchg(tbl, index, hpa, direction);
+
+        if (!ret)
+                pnv_pci_ioda2_tce_invalidate(tbl, index, 1, true);
+
+        return ret;
+}
 #endif
 
 static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index,
@@ -2024,6 +2047,7 @@ static struct iommu_table_ops pnv_ioda2_iommu_ops = {
         .set = pnv_ioda2_tce_build,
 #ifdef CONFIG_IOMMU_API
         .exchange = pnv_ioda2_tce_xchg,
+        .exchange_rm = pnv_ioda2_tce_xchg_rm,
 #endif
         .clear = pnv_ioda2_tce_free,
         .get = pnv_tce_get,