summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/platforms
diff options
context:
space:
mode:
authorAlexey Kardashevskiy <aik@ozlabs.ru>2015-06-05 16:35:12 +1000
committerMichael Ellerman <mpe@ellerman.id.au>2015-06-11 15:16:48 +1000
commit5780fb04263c16fdb9affd1012d5eb956e0cbcd9 (patch)
tree73f151d05b0759ec6eb5ae1e5b7738920012a4d3 /arch/powerpc/platforms
parentb82c75bfbeb5b4c7c23ee09dd6f295c7f06aeb25 (diff)
downloadop-kernel-dev-5780fb04263c16fdb9affd1012d5eb956e0cbcd9.zip
op-kernel-dev-5780fb04263c16fdb9affd1012d5eb956e0cbcd9.tar.gz
powerpc/powernv/ioda2: Move TCE kill register address to PE
At the moment the DMA setup code looks for the "ibm,opal-tce-kill" property which contains the TCE kill register address. Writing to this register invalidates TCE cache on IODA/IODA2 hub. This moves the register address from iommu_table to pnv_pnb as this register belongs to PHB and invalidates TCE cache for all tables of all attached PEs. This moves the property reading/remapping code to a helper which is called when DMA is being configured for PE and which does DMA setup for both IODA1 and IODA2. This adds a new pnv_pci_ioda2_tce_invalidate_entire() helper which invalidates cache for the entire table. It should be called after every call to opal_pci_map_pe_dma_window(). It was not required before because there was just a single TCE table and 64bit DMA was handled via bypass window (which has no table so no cache was used) but this is going to change with Dynamic DMA windows (DDW). Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Diffstat (limited to 'arch/powerpc/platforms')
-rw-r--r--arch/powerpc/platforms/powernv/pci-ioda.c66
-rw-r--r--arch/powerpc/platforms/powernv/pci.h7
2 files changed, 44 insertions, 29 deletions
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 17a7752..6bbb2bb 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1680,8 +1680,8 @@ static void pnv_pci_ioda1_tce_invalidate(struct iommu_table *tbl,
struct pnv_ioda_pe *pe = container_of(tgl->table_group,
struct pnv_ioda_pe, table_group);
__be64 __iomem *invalidate = rm ?
- (__be64 __iomem *)pe->tce_inval_reg_phys :
- (__be64 __iomem *)tbl->it_index;
+ (__be64 __iomem *)pe->phb->ioda.tce_inval_reg_phys :
+ pe->phb->ioda.tce_inval_reg;
unsigned long start, end, inc;
const unsigned shift = tbl->it_page_shift;
@@ -1752,6 +1752,19 @@ static struct iommu_table_ops pnv_ioda1_iommu_ops = {
.get = pnv_tce_get,
};
+static inline void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_ioda_pe *pe)
+{
+ /* 01xb - invalidate TCEs that match the specified PE# */
+ unsigned long val = (0x4ull << 60) | (pe->pe_number & 0xFF);
+ struct pnv_phb *phb = pe->phb;
+
+ if (!phb->ioda.tce_inval_reg)
+ return;
+
+ mb(); /* Ensure above stores are visible */
+ __raw_writeq(cpu_to_be64(val), phb->ioda.tce_inval_reg);
+}
+
static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl,
unsigned long index, unsigned long npages, bool rm)
{
@@ -1762,8 +1775,8 @@ static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl,
struct pnv_ioda_pe, table_group);
unsigned long start, end, inc;
__be64 __iomem *invalidate = rm ?
- (__be64 __iomem *)pe->tce_inval_reg_phys :
- (__be64 __iomem *)tbl->it_index;
+ (__be64 __iomem *)pe->phb->ioda.tce_inval_reg_phys :
+ pe->phb->ioda.tce_inval_reg;
const unsigned shift = tbl->it_page_shift;
/* We'll invalidate DMA address in PE scope */
@@ -1821,7 +1834,6 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
{
struct page *tce_mem = NULL;
- const __be64 *swinvp;
struct iommu_table *tbl;
unsigned int i;
int64_t rc;
@@ -1878,20 +1890,11 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
base << 28, IOMMU_PAGE_SHIFT_4K);
/* OPAL variant of P7IOC SW invalidated TCEs */
- swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL);
- if (swinvp) {
- /* We need a couple more fields -- an address and a data
- * to or. Since the bus is only printed out on table free
- * errors, and on the first pass the data will be a relative
- * bus number, print that out instead.
- */
- pe->tce_inval_reg_phys = be64_to_cpup(swinvp);
- tbl->it_index = (unsigned long)ioremap(pe->tce_inval_reg_phys,
- 8);
+ if (phb->ioda.tce_inval_reg)
tbl->it_type |= (TCE_PCI_SWINV_CREATE |
TCE_PCI_SWINV_FREE |
TCE_PCI_SWINV_PAIR);
- }
+
tbl->it_ops = &pnv_ioda1_iommu_ops;
iommu_init_table(tbl, phb->hose->node);
@@ -1972,12 +1975,24 @@ static struct iommu_table_group_ops pnv_pci_ioda2_ops = {
};
#endif
+static void pnv_pci_ioda_setup_opal_tce_kill(struct pnv_phb *phb)
+{
+ const __be64 *swinvp;
+
+ /* OPAL variant of PHB3 invalidated TCEs */
+ swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL);
+ if (!swinvp)
+ return;
+
+ phb->ioda.tce_inval_reg_phys = be64_to_cpup(swinvp);
+ phb->ioda.tce_inval_reg = ioremap(phb->ioda.tce_inval_reg_phys, 8);
+}
+
static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
struct pnv_ioda_pe *pe)
{
struct page *tce_mem = NULL;
void *addr;
- const __be64 *swinvp;
struct iommu_table *tbl;
unsigned int tce_table_size, end;
int64_t rc;
@@ -2024,23 +2039,16 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
goto fail;
}
+ pnv_pci_ioda2_tce_invalidate_entire(pe);
+
/* Setup linux iommu table */
pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, 0,
IOMMU_PAGE_SHIFT_4K);
/* OPAL variant of PHB3 invalidated TCEs */
- swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL);
- if (swinvp) {
- /* We need a couple more fields -- an address and a data
- * to or. Since the bus is only printed out on table free
- * errors, and on the first pass the data will be a relative
- * bus number, print that out instead.
- */
- pe->tce_inval_reg_phys = be64_to_cpup(swinvp);
- tbl->it_index = (unsigned long)ioremap(pe->tce_inval_reg_phys,
- 8);
+ if (phb->ioda.tce_inval_reg)
tbl->it_type |= (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE);
- }
+
tbl->it_ops = &pnv_ioda2_iommu_ops;
iommu_init_table(tbl, phb->hose->node);
#ifdef CONFIG_IOMMU_API
@@ -2096,6 +2104,8 @@ static void pnv_ioda_setup_dma(struct pnv_phb *phb)
pr_info("PCI: %d PE# for a total weight of %d\n",
phb->ioda.dma_pe_count, phb->ioda.dma_weight);
+ pnv_pci_ioda_setup_opal_tce_kill(phb);
+
/* Walk our PE list and configure their DMA segments, hand them
* out one base segment plus any residual segments based on
* weight
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index d37cb4d..792a723 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -58,7 +58,6 @@ struct pnv_ioda_pe {
int tce32_seg;
int tce32_segcount;
struct iommu_table_group table_group;
- phys_addr_t tce_inval_reg_phys;
/* 64-bit TCE bypass region */
bool tce_bypass_enabled;
@@ -184,6 +183,12 @@ struct pnv_phb {
* boot for resource allocation purposes
*/
struct list_head pe_dma_list;
+
+ /* TCE cache invalidate registers (physical and
+ * remapped)
+ */
+ phys_addr_t tce_inval_reg_phys;
+ __be64 __iomem *tce_inval_reg;
} ioda;
};
OpenPOWER on IntegriCloud