1 files changed, 195 insertions, 47 deletions

diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 6d47b4a3ce39..e4198700ed1a 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -39,6 +39,20 @@
 
 #include "pseries.h"
 
+enum {
+	DDW_QUERY_PE_DMA_WIN  = 0,
+	DDW_CREATE_PE_DMA_WIN = 1,
+	DDW_REMOVE_PE_DMA_WIN = 2,
+
+	DDW_APPLICABLE_SIZE
+};
+
+enum {
+	DDW_EXT_SIZE = 0,
+	DDW_EXT_RESET_DMA_WIN = 1,
+	DDW_EXT_QUERY_OUT_SIZE = 2
+};
+
 static struct iommu_table_group *iommu_pseries_alloc_group(int node)
 {
 	struct iommu_table_group *table_group;
@@ -334,7 +348,7 @@ struct direct_window {
 /* Dynamic DMA Window support */
 struct ddw_query_response {
 	u32 windows_available;
-	u32 largest_available_block;
+	u64 largest_available_block;
 	u32 page_size;
 	u32 migration_capable;
 };
@@ -767,25 +781,14 @@ static int __init disable_ddw_setup(char *str)
 
 early_param("disable_ddw", disable_ddw_setup);
 
-static void remove_ddw(struct device_node *np, bool remove_prop)
+static void remove_dma_window(struct device_node *np, u32 *ddw_avail,
+			      struct property *win)
 {
 	struct dynamic_dma_window_prop *dwp;
-	struct property *win64;
-	u32 ddw_avail[3];
 	u64 liobn;
-	int ret = 0;
-
-	ret = of_property_read_u32_array(np, "ibm,ddw-applicable",
-					 &ddw_avail[0], 3);
-
-	win64 = of_find_property(np, DIRECT64_PROPNAME, NULL);
-	if (!win64)
-		return;
-
-	if (ret || win64->length < sizeof(*dwp))
-		goto delprop;
+	int ret;
 
-	dwp = win64->value;
+	dwp = win->value;
 	liobn = (u64)be32_to_cpu(dwp->liobn);
 
 	/* clear the whole window, note the arg is in kernel pages */
@@ -798,19 +801,39 @@ static void remove_ddw(struct device_node *np, bool remove_prop)
 		pr_debug("%pOF successfully cleared tces in window.\n",
 			 np);
 
-	ret = rtas_call(ddw_avail[2], 1, 1, NULL, liobn);
+	ret = rtas_call(ddw_avail[DDW_REMOVE_PE_DMA_WIN], 1, 1, NULL, liobn);
 	if (ret)
 		pr_warn("%pOF: failed to remove direct window: rtas returned "
 			"%d to ibm,remove-pe-dma-window(%x) %llx\n",
-			np, ret, ddw_avail[2], liobn);
+			np, ret, ddw_avail[DDW_REMOVE_PE_DMA_WIN], liobn);
 	else
 		pr_debug("%pOF: successfully removed direct window: rtas returned "
 			"%d to ibm,remove-pe-dma-window(%x) %llx\n",
-			np, ret, ddw_avail[2], liobn);
+			np, ret, ddw_avail[DDW_REMOVE_PE_DMA_WIN], liobn);
+}
+
+static void remove_ddw(struct device_node *np, bool remove_prop)
+{
+	struct property *win;
+	u32 ddw_avail[DDW_APPLICABLE_SIZE];
+	int ret = 0;
 
-delprop:
-	if (remove_prop)
-		ret = of_remove_property(np, win64);
+	ret = of_property_read_u32_array(np, "ibm,ddw-applicable",
+					 &ddw_avail[0], DDW_APPLICABLE_SIZE);
+	if (ret)
+		return;
+
+	win = of_find_property(np, DIRECT64_PROPNAME, NULL);
+	if (!win)
+		return;
+
+	if (win->length >= sizeof(struct dynamic_dma_window_prop))
+		remove_dma_window(np, ddw_avail, win);
+
+	if (!remove_prop)
+		return;
+
+	ret = of_remove_property(np, win);
 	if (ret)
 		pr_warn("%pOF: failed to remove direct window property: %d\n",
 			np, ret);
@@ -869,14 +892,62 @@ static int find_existing_ddw_windows(void)
 }
 machine_arch_initcall(pseries, find_existing_ddw_windows);
 
+/**
+ * ddw_read_ext - Get the value of an DDW extension
+ * @np:		device node from which the extension value is to be read.
+ * @extnum:	index number of the extension.
+ * @value:	pointer to return value, modified when extension is available.
+ *
+ * Checks if "ibm,ddw-extensions" exists for this node, and get the value
+ * on index 'extnum'.
+ * It can be used only to check if a property exists, passing value == NULL.
+ *
+ * Returns:
+ *	0 if extension successfully read
+ *	-EINVAL if the "ibm,ddw-extensions" does not exist,
+ *	-ENODATA if "ibm,ddw-extensions" does not have a value, and
+ *	-EOVERFLOW if "ibm,ddw-extensions" does not contain this extension.
+ */
+static inline int ddw_read_ext(const struct device_node *np, int extnum,
+			       u32 *value)
+{
+	static const char propname[] = "ibm,ddw-extensions";
+	u32 count;
+	int ret;
+
+	ret = of_property_read_u32_index(np, propname, DDW_EXT_SIZE, &count);
+	if (ret)
+		return ret;
+
+	if (count < extnum)
+		return -EOVERFLOW;
+
+	if (!value)
+		value = &count;
+
+	return of_property_read_u32_index(np, propname, extnum, value);
+}
+
 static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail,
-			struct ddw_query_response *query)
+		     struct ddw_query_response *query,
+		     struct device_node *parent)
 {
 	struct device_node *dn;
 	struct pci_dn *pdn;
-	u32 cfg_addr;
+	u32 cfg_addr, ext_query, query_out[5];
 	u64 buid;
-	int ret;
+	int ret, out_sz;
+
+	/*
+	 * From LoPAR level 2.8, "ibm,ddw-extensions" index 3 can rule how many
+	 * output parameters ibm,query-pe-dma-windows will have, ranging from
+	 * 5 to 6.
+	 */
+	ret = ddw_read_ext(parent, DDW_EXT_QUERY_OUT_SIZE, &ext_query);
+	if (!ret && ext_query == 1)
+		out_sz = 6;
+	else
+		out_sz = 5;
 
 	/*
 	 * Get the config address and phb buid of the PE window.
@@ -889,11 +960,28 @@ static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail,
 	buid = pdn->phb->buid;
 	cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8));
 
-	ret = rtas_call(ddw_avail[0], 3, 5, (u32 *)query,
-		  cfg_addr, BUID_HI(buid), BUID_LO(buid));
-	dev_info(&dev->dev, "ibm,query-pe-dma-windows(%x) %x %x %x"
-		" returned %d\n", ddw_avail[0], cfg_addr, BUID_HI(buid),
-		BUID_LO(buid), ret);
+	ret = rtas_call(ddw_avail[DDW_QUERY_PE_DMA_WIN], 3, out_sz, query_out,
+			cfg_addr, BUID_HI(buid), BUID_LO(buid));
+	dev_info(&dev->dev, "ibm,query-pe-dma-windows(%x) %x %x %x returned %d\n",
+		 ddw_avail[DDW_QUERY_PE_DMA_WIN], cfg_addr, BUID_HI(buid),
+		 BUID_LO(buid), ret);
+
+	switch (out_sz) {
+	case 5:
+		query->windows_available = query_out[0];
+		query->largest_available_block = query_out[1];
+		query->page_size = query_out[2];
+		query->migration_capable = query_out[3];
+		break;
+	case 6:
+		query->windows_available = query_out[0];
+		query->largest_available_block = ((u64)query_out[1] << 32) |
+						 query_out[2];
+		query->page_size = query_out[3];
+		query->migration_capable = query_out[4];
+		break;
+	}
+
 	return ret;
 }
 
@@ -920,15 +1008,16 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail,
 
 	do {
 		/* extra outputs are LIOBN and dma-addr (hi, lo) */
-		ret = rtas_call(ddw_avail[1], 5, 4, (u32 *)create,
-				cfg_addr, BUID_HI(buid), BUID_LO(buid),
-				page_shift, window_shift);
+		ret = rtas_call(ddw_avail[DDW_CREATE_PE_DMA_WIN], 5, 4,
+				(u32 *)create, cfg_addr, BUID_HI(buid),
+				BUID_LO(buid), page_shift, window_shift);
 	} while (rtas_busy_delay(ret));
 	dev_info(&dev->dev,
 		"ibm,create-pe-dma-window(%x) %x %x %x %x %x returned %d "
-		"(liobn = 0x%x starting addr = %x %x)\n", ddw_avail[1],
-		 cfg_addr, BUID_HI(buid), BUID_LO(buid), page_shift,
-		 window_shift, ret, create->liobn, create->addr_hi, create->addr_lo);
+		"(liobn = 0x%x starting addr = %x %x)\n",
+		 ddw_avail[DDW_CREATE_PE_DMA_WIN], cfg_addr, BUID_HI(buid),
+		 BUID_LO(buid), page_shift, window_shift, ret, create->liobn,
+		 create->addr_hi, create->addr_lo);
 
 	return ret;
 }
@@ -978,6 +1067,38 @@ static phys_addr_t ddw_memory_hotplug_max(void)
 }
 
 /*
+ * Platforms supporting the DDW option starting with LoPAR level 2.7 implement
+ * ibm,ddw-extensions, which carries the rtas token for
+ * ibm,reset-pe-dma-windows.
+ * That rtas-call can be used to restore the default DMA window for the device.
+ */
+static void reset_dma_window(struct pci_dev *dev, struct device_node *par_dn)
+{
+	int ret;
+	u32 cfg_addr, reset_dma_win;
+	u64 buid;
+	struct device_node *dn;
+	struct pci_dn *pdn;
+
+	ret = ddw_read_ext(par_dn, DDW_EXT_RESET_DMA_WIN, &reset_dma_win);
+	if (ret)
+		return;
+
+	dn = pci_device_to_OF_node(dev);
+	pdn = PCI_DN(dn);
+	buid = pdn->phb->buid;
+	cfg_addr = (pdn->busno << 16) | (pdn->devfn << 8);
+
+	ret = rtas_call(reset_dma_win, 3, 1, NULL, cfg_addr, BUID_HI(buid),
+			BUID_LO(buid));
+	if (ret)
+		dev_info(&dev->dev,
+			 "ibm,reset-pe-dma-windows(%x) %x %x %x returned %d ",
+			 reset_dma_win, cfg_addr, BUID_HI(buid), BUID_LO(buid),
+			 ret);
+}
+
+/*
  * If the PE supports dynamic dma windows, and there is space for a table
  * that can map all pages in a linear offset, then setup such a table,
  * and record the dma-offset in the struct device.
@@ -996,11 +1117,12 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	int page_shift;
 	u64 dma_addr, max_addr;
 	struct device_node *dn;
-	u32 ddw_avail[3];
+	u32 ddw_avail[DDW_APPLICABLE_SIZE];
 	struct direct_window *window;
 	struct property *win64;
 	struct dynamic_dma_window_prop *ddwprop;
 	struct failed_ddw_pdn *fpdn;
+	bool default_win_removed = false;
 
 	mutex_lock(&direct_window_init_mutex);
 
@@ -1029,7 +1151,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	 * the property is actually in the parent, not the PE
 	 */
 	ret = of_property_read_u32_array(pdn, "ibm,ddw-applicable",
-					 &ddw_avail[0], 3);
+					 &ddw_avail[0], DDW_APPLICABLE_SIZE);
 	if (ret)
 		goto out_failed;
 
@@ -1040,18 +1162,42 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	 * of page sizes: supported and supported for migrate-dma.
 	 */
 	dn = pci_device_to_OF_node(dev);
-	ret = query_ddw(dev, ddw_avail, &query);
+	ret = query_ddw(dev, ddw_avail, &query, pdn);
 	if (ret != 0)
 		goto out_failed;
 
+	/*
+	 * If there is no window available, remove the default DMA window,
+	 * if it's present. This will make all the resources available to the
+	 * new DDW window.
+	 * If anything fails after this, we need to restore it, so also check
+	 * for extensions presence.
+	 */
 	if (query.windows_available == 0) {
-		/*
-		 * no additional windows are available for this device.
-		 * We might be able to reallocate the existing window,
-		 * trading in for a larger page size.
-		 */
-		dev_dbg(&dev->dev, "no free dynamic windows");
-		goto out_failed;
+		struct property *default_win;
+		int reset_win_ext;
+
+		default_win = of_find_property(pdn, "ibm,dma-window", NULL);
+		if (!default_win)
+			goto out_failed;
+
+		reset_win_ext = ddw_read_ext(pdn, DDW_EXT_RESET_DMA_WIN, NULL);
+		if (reset_win_ext)
+			goto out_failed;
+
+		remove_dma_window(pdn, ddw_avail, default_win);
+		default_win_removed = true;
+
+		/* Query again, to check if the window is available */
+		ret = query_ddw(dev, ddw_avail, &query, pdn);
+		if (ret != 0)
+			goto out_failed;
+
+		if (query.windows_available == 0) {
+			/* no windows are available for this device. */
+			dev_dbg(&dev->dev, "no free dynamic windows");
+			goto out_failed;
+		}
 	}
 	if (query.page_size & 4) {
 		page_shift = 24; /* 16MB */
@@ -1068,7 +1214,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	/* check largest block * page size > max memory hotplug addr */
 	max_addr = ddw_memory_hotplug_max();
 	if (query.largest_available_block < (max_addr >> page_shift)) {
-		dev_dbg(&dev->dev, "can't map partition max 0x%llx with %u "
+		dev_dbg(&dev->dev, "can't map partition max 0x%llx with %llu "
 			  "%llu-sized pages\n", max_addr,  query.largest_available_block,
 			  1ULL << page_shift);
 		goto out_failed;
@@ -1142,6 +1288,8 @@ out_free_prop:
 	kfree(win64);
 
 out_failed:
+	if (default_win_removed)
+		reset_dma_window(dev, pdn);
 
 	fpdn = kzalloc(sizeof(*fpdn), GFP_KERNEL);
 	if (!fpdn)