powerpc/pseries: Software invalidatation of TCEs

Some pseries IOMMUs cache TCEs but don't snoop when the TCEs are changed
in memory, hence we need manually invalidate in software.

This adds code to do the invalidate.  It keys off a device tree property
to say where the to do the MMIO for the invalidate and some information
on what the format of the invalidate including some magic routing info.

it_busno get overloaded with this magic routing info and it_index with
the MMIO address for the invalidate command.

This then gets hooked into the building and freeing of TCEs.

This is only useful on bare metal pseries.  pHyp takes care of this when
virtualised.

Based on patch from Milton with cleanups from Mikey.

Signed-off-by: Milton Miller <miltonm@bga.com>
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

diff --git a/arch/powerpc/include/asm/tce.h b/arch/powerpc/include/asm/tce.h
index f663634cccc9c89b8d87164d98387cc61e97773a..3dead82d597951ef90cb08bd445376d6e9e071d1 100644 (file)
--- a/arch/powerpc/include/asm/tce.h
+++ b/arch/powerpc/include/asm/tce.h
@@ -26,10 +26,12 @@
 
 /*
  * Tces come in two formats, one for the virtual bus and a different
- * format for PCI
+ * format for PCI.  PCI TCEs can have hardware or software maintianed
+ * coherency.
  */
-#define TCE_VB  0
-#define TCE_PCI 1
+#define TCE_VB                 0
+#define TCE_PCI                        1
+#define TCE_PCI_SW_INVAL       2
 
 /* TCE page size is 4096 bytes (1 << 12) */
 

diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index b719d9709730e577af3671a562f5ab415d7daacd..ea70667d4fc319d00fcb9f43adfeb6b9159004b3 100644 (file)
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -52,13 +52,42 @@
 #include "plpar_wrappers.h"
 
 
+static void tce_invalidate_pSeries_sw(struct iommu_table *tbl,
+                                     u64 *startp, u64 *endp)
+{
+       u64 __iomem *invalidate = (u64 __iomem *)tbl->it_index;
+       unsigned long start, end, inc;
+
+       start = __pa(startp);
+       end = __pa(endp);
+       inc = L1_CACHE_BYTES; /* invalidate a cacheline of TCEs at a time */
+
+       /* If this is non-zero, change the format.  We shift the
+        * address and or in the magic from the device tree. */
+       if (tbl->it_busno) {
+               start <<= 12;
+               end <<= 12;
+               inc <<= 12;
+               start |= tbl->it_busno;
+               end |= tbl->it_busno;
+       }
+
+       end |= inc - 1; /* round up end to be different than start */
+
+       mb(); /* Make sure TCEs in memory are written */
+       while (start <= end) {
+               out_be64(invalidate, start);
+               start += inc;
+       }
+}
+
 static int tce_build_pSeries(struct iommu_table *tbl, long index,
                              long npages, unsigned long uaddr,
                              enum dma_data_direction direction,
                              struct dma_attrs *attrs)
 {
        u64 proto_tce;
-       u64 *tcep;
+       u64 *tcep, *tces;
        u64 rpn;
 
        proto_tce = TCE_PCI_READ; // Read allowed
@@ -66,7 +95,7 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index,
        if (direction != DMA_TO_DEVICE)
                proto_tce |= TCE_PCI_WRITE;
 
-       tcep = ((u64 *)tbl->it_base) + index;
+       tces = tcep = ((u64 *)tbl->it_base) + index;
 
        while (npages--) {
                /* can't move this out since we might cross MEMBLOCK boundary */
@@ -76,18 +105,24 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index,
                uaddr += TCE_PAGE_SIZE;
                tcep++;
        }
+
+       if (tbl->it_type == TCE_PCI_SW_INVAL)
+               tce_invalidate_pSeries_sw(tbl, tces, tcep - 1);
        return 0;
 }
 
 
 static void tce_free_pSeries(struct iommu_table *tbl, long index, long npages)
 {
-       u64 *tcep;
+       u64 *tcep, *tces;
 
-       tcep = ((u64 *)tbl->it_base) + index;
+       tces = tcep = ((u64 *)tbl->it_base) + index;
 
        while (npages--)
                *(tcep++) = 0;
+
+       if (tbl->it_type == TCE_PCI_SW_INVAL)
+               tce_invalidate_pSeries_sw(tbl, tces, tcep - 1);
 }
 
 static unsigned long tce_get_pseries(struct iommu_table *tbl, long index)
@@ -425,7 +460,7 @@ static void iommu_table_setparms(struct pci_controller *phb,
                                 struct iommu_table *tbl)
 {
        struct device_node *node;
-       const unsigned long *basep;
+       const unsigned long *basep, *sw_inval;
        const u32 *sizep;
 
        node = phb->dn;
@@ -462,6 +497,22 @@ static void iommu_table_setparms(struct pci_controller *phb,
        tbl->it_index = 0;
        tbl->it_blocksize = 16;
        tbl->it_type = TCE_PCI;
+
+       sw_inval = of_get_property(node, "linux,tce-sw-invalidate-info", NULL);
+       if (sw_inval) {
+               /*
+                * This property contains information on how to
+                * invalidate the TCE entry.  The first property is
+                * the base MMIO address used to invalidate entries.
+                * The second property tells us the format of the TCE
+                * invalidate (whether it needs to be shifted) and
+                * some magic routing info to add to our invalidate
+                * command.
+                */
+               tbl->it_index = (unsigned long) ioremap(sw_inval[0], 8);
+               tbl->it_busno = sw_inval[1]; /* overload this with magic */
+               tbl->it_type = TCE_PCI_SW_INVAL;
+       }
 }
 
 /*