[PATCH 4.4 85/91] powerpc/pseries: Allow not having ibm, hypertas-functions::hcall-multi-tce for DDW

[Greg Kroah-Hartman]

From: Alexey Kardashevskiy <aik@xxxxxxxxx>

commit 7559d3d295f3365ea7ac0c0274c05e633fe4f594 upstream.

By default a pseries guest supports a H_PUT_TCE hypercall which maps
a single IOMMU page in a DMA window. Additionally the hypervisor may
support H_PUT_TCE_INDIRECT/H_STUFF_TCE which update multiple TCEs at once;
this is advertised via the device tree /rtas/ibm,hypertas-functions
property which Linux converts to FW_FEATURE_MULTITCE.

FW_FEATURE_MULTITCE is checked when dma_iommu_ops is used; however
the code managing the huge DMA window (DDW) ignores it and calls
H_PUT_TCE_INDIRECT even if it is explicitly disabled via
the "multitce=off" kernel command line parameter.

This adds FW_FEATURE_MULTITCE checking to the DDW code path.

This changes tce_build_pSeriesLP to take liobn and page size as
the huge window does not have iommu_table descriptor which usually
the place to store these numbers.

Fixes: 4e8b0cf46b25 ("powerpc/pseries: Add support for dynamic dma windows")
Signed-off-by: Alexey Kardashevskiy <aik@xxxxxxxxx>
Reviewed-by: Thiago Jung Bauermann <bauerman@xxxxxxxxxxxxx>
Tested-by: Thiago Jung Bauermann <bauerman@xxxxxxxxxxxxx>
Signed-off-by: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20191216041924.42318-3-aik@xxxxxxxxx
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
 arch/powerpc/platforms/pseries/iommu.c |   43 ++++++++++++++++++++++-----------
 1 file changed, 29 insertions(+), 14 deletions(-)

--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -202,10 +202,10 @@ static unsigned long tce_get_pseries(str
 	return be64_to_cpu(*tcep);
 }
 
-static void tce_free_pSeriesLP(struct iommu_table*, long, long);
+static void tce_free_pSeriesLP(unsigned long liobn, long, long);
 static void tce_freemulti_pSeriesLP(struct iommu_table*, long, long);
 
-static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
+static int tce_build_pSeriesLP(unsigned long liobn, long tcenum, long tceshift,
 				long npages, unsigned long uaddr,
 				enum dma_data_direction direction,
 				struct dma_attrs *attrs)
@@ -216,25 +216,25 @@ static int tce_build_pSeriesLP(struct io
 	int ret = 0;
 	long tcenum_start = tcenum, npages_start = npages;
 
-	rpn = __pa(uaddr) >> TCE_SHIFT;
+	rpn = __pa(uaddr) >> tceshift;
 	proto_tce = TCE_PCI_READ;
 	if (direction != DMA_TO_DEVICE)
 		proto_tce |= TCE_PCI_WRITE;
 
 	while (npages--) {
-		tce = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT;
-		rc = plpar_tce_put((u64)tbl->it_index, (u64)tcenum << 12, tce);
+		tce = proto_tce | (rpn & TCE_RPN_MASK) << tceshift;
+		rc = plpar_tce_put((u64)liobn, (u64)tcenum << tceshift, tce);
 
 		if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) {
 			ret = (int)rc;
-			tce_free_pSeriesLP(tbl, tcenum_start,
+			tce_free_pSeriesLP(liobn, tcenum_start,
 			                   (npages_start - (npages + 1)));
 			break;
 		}
 
 		if (rc && printk_ratelimit()) {
 			printk("tce_build_pSeriesLP: plpar_tce_put failed. rc=%lld\n", rc);
-			printk("\tindex   = 0x%llx\n", (u64)tbl->it_index);
+			printk("\tindex   = 0x%llx\n", (u64)liobn);
 			printk("\ttcenum  = 0x%llx\n", (u64)tcenum);
 			printk("\ttce val = 0x%llx\n", tce );
 			dump_stack();
@@ -263,7 +263,8 @@ static int tce_buildmulti_pSeriesLP(stru
 	unsigned long flags;
 
 	if ((npages == 1) || !firmware_has_feature(FW_FEATURE_MULTITCE)) {
-		return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
+		return tce_build_pSeriesLP(tbl->it_index, tcenum,
+					   tbl->it_page_shift, npages, uaddr,
 		                           direction, attrs);
 	}
 
@@ -279,8 +280,9 @@ static int tce_buildmulti_pSeriesLP(stru
 		/* If allocation fails, fall back to the loop implementation */
 		if (!tcep) {
 			local_irq_restore(flags);
-			return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
-					    direction, attrs);
+			return tce_build_pSeriesLP(tbl->it_index, tcenum,
+					tbl->it_page_shift,
+					npages, uaddr, direction, attrs);
 		}
 		__this_cpu_write(tce_page, tcep);
 	}
@@ -331,16 +333,16 @@ static int tce_buildmulti_pSeriesLP(stru
 	return ret;
 }
 
-static void tce_free_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages)
+static void tce_free_pSeriesLP(unsigned long liobn, long tcenum, long npages)
 {
 	u64 rc;
 
 	while (npages--) {
-		rc = plpar_tce_put((u64)tbl->it_index, (u64)tcenum << 12, 0);
+		rc = plpar_tce_put((u64)liobn, (u64)tcenum << 12, 0);
 
 		if (rc && printk_ratelimit()) {
 			printk("tce_free_pSeriesLP: plpar_tce_put failed. rc=%lld\n", rc);
-			printk("\tindex   = 0x%llx\n", (u64)tbl->it_index);
+			printk("\tindex   = 0x%llx\n", (u64)liobn);
 			printk("\ttcenum  = 0x%llx\n", (u64)tcenum);
 			dump_stack();
 		}
@@ -355,7 +357,7 @@ static void tce_freemulti_pSeriesLP(stru
 	u64 rc;
 
 	if (!firmware_has_feature(FW_FEATURE_MULTITCE))
-		return tce_free_pSeriesLP(tbl, tcenum, npages);
+		return tce_free_pSeriesLP(tbl->it_index, tcenum, npages);
 
 	rc = plpar_tce_stuff((u64)tbl->it_index, (u64)tcenum << 12, 0, npages);
 
@@ -470,6 +472,19 @@ static int tce_setrange_multi_pSeriesLP(
 	u64 rc = 0;
 	long l, limit;
 
+	if (!firmware_has_feature(FW_FEATURE_MULTITCE)) {
+		unsigned long tceshift = be32_to_cpu(maprange->tce_shift);
+		unsigned long dmastart = (start_pfn << PAGE_SHIFT) +
+				be64_to_cpu(maprange->dma_base);
+		unsigned long tcenum = dmastart >> tceshift;
+		unsigned long npages = num_pfn << PAGE_SHIFT >> tceshift;
+		void *uaddr = __va(start_pfn << PAGE_SHIFT);
+
+		return tce_build_pSeriesLP(be32_to_cpu(maprange->liobn),
+				tcenum, tceshift, npages, (unsigned long) uaddr,
+				DMA_BIDIRECTIONAL, 0);
+	}
+
 	local_irq_disable();	/* to protect tcep and the page behind it */
 	tcep = __this_cpu_read(tce_page);