Merge branch 'next-sriov' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc into next

Merge Richard's work to support SR-IOV on PowerNV. All generic PCI
patches acked by Bjorn.

Some minor conflicts with Daniel's pci_controller_ops work.

Conflicts:
	arch/powerpc/include/asm/machdep.h
	arch/powerpc/platforms/powernv/pci-ioda.c

3 files changed, 195 insertions, 57 deletions

diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 4b3a4eaad996..ee0ebff103a4 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -19,16 +19,59 @@
 
 #define VIRTFN_ID_LEN	16
 
-static inline u8 virtfn_bus(struct pci_dev *dev, int id)
+int pci_iov_virtfn_bus(struct pci_dev *dev, int vf_id)
 {
+	if (!dev->is_physfn)
+		return -EINVAL;
 	return dev->bus->number + ((dev->devfn + dev->sriov->offset +
-				    dev->sriov->stride * id) >> 8);
+				    dev->sriov->stride * vf_id) >> 8);
 }
 
-static inline u8 virtfn_devfn(struct pci_dev *dev, int id)
+int pci_iov_virtfn_devfn(struct pci_dev *dev, int vf_id)
 {
+	if (!dev->is_physfn)
+		return -EINVAL;
 	return (dev->devfn + dev->sriov->offset +
-		dev->sriov->stride * id) & 0xff;
+		dev->sriov->stride * vf_id) & 0xff;
+}
+
+/*
+ * Per SR-IOV spec sec 3.3.10 and 3.3.11, First VF Offset and VF Stride may
+ * change when NumVFs changes.
+ *
+ * Update iov->offset and iov->stride when NumVFs is written.
+ */
+static inline void pci_iov_set_numvfs(struct pci_dev *dev, int nr_virtfn)
+{
+	struct pci_sriov *iov = dev->sriov;
+
+	pci_write_config_word(dev, iov->pos + PCI_SRIOV_NUM_VF, nr_virtfn);
+	pci_read_config_word(dev, iov->pos + PCI_SRIOV_VF_OFFSET, &iov->offset);
+	pci_read_config_word(dev, iov->pos + PCI_SRIOV_VF_STRIDE, &iov->stride);
+}
+
+/*
+ * The PF consumes one bus number.  NumVFs, First VF Offset, and VF Stride
+ * determine how many additional bus numbers will be consumed by VFs.
+ *
+ * Iterate over all valid NumVFs and calculate the maximum number of bus
+ * numbers that could ever be required.
+ */
+static inline u8 virtfn_max_buses(struct pci_dev *dev)
+{
+	struct pci_sriov *iov = dev->sriov;
+	int nr_virtfn;
+	u8 max = 0;
+	int busnr;
+
+	for (nr_virtfn = 1; nr_virtfn <= iov->total_VFs; nr_virtfn++) {
+		pci_iov_set_numvfs(dev, nr_virtfn);
+		busnr = pci_iov_virtfn_bus(dev, nr_virtfn - 1);
+		if (busnr > max)
+			max = busnr;
+	}
+
+	return max;
 }
 
 static struct pci_bus *virtfn_add_bus(struct pci_bus *bus, int busnr)
@@ -57,6 +100,14 @@ static void virtfn_remove_bus(struct pci_bus *physbus, struct pci_bus *virtbus)
 		pci_remove_bus(virtbus);
 }
 
+resource_size_t pci_iov_resource_size(struct pci_dev *dev, int resno)
+{
+	if (!dev->is_physfn)
+		return 0;
+
+	return dev->sriov->barsz[resno - PCI_IOV_RESOURCES];
+}
+
 static int virtfn_add(struct pci_dev *dev, int id, int reset)
 {
 	int i;
@@ -69,7 +120,7 @@ static int virtfn_add(struct pci_dev *dev, int id, int reset)
 	struct pci_bus *bus;
 
 	mutex_lock(&iov->dev->sriov->lock);
-	bus = virtfn_add_bus(dev->bus, virtfn_bus(dev, id));
+	bus = virtfn_add_bus(dev->bus, pci_iov_virtfn_bus(dev, id));
 	if (!bus)
 		goto failed;
 
@@ -77,7 +128,7 @@ static int virtfn_add(struct pci_dev *dev, int id, int reset)
 	if (!virtfn)
 		goto failed0;
 
-	virtfn->devfn = virtfn_devfn(dev, id);
+	virtfn->devfn = pci_iov_virtfn_devfn(dev, id);
 	virtfn->vendor = dev->vendor;
 	pci_read_config_word(dev, iov->pos + PCI_SRIOV_VF_DID, &virtfn->device);
 	pci_setup_device(virtfn);
@@ -87,13 +138,12 @@ static int virtfn_add(struct pci_dev *dev, int id, int reset)
 	virtfn->multifunction = 0;
 
 	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
-		res = dev->resource + PCI_IOV_RESOURCES + i;
+		res = &dev->resource[i + PCI_IOV_RESOURCES];
 		if (!res->parent)
 			continue;
 		virtfn->resource[i].name = pci_name(virtfn);
 		virtfn->resource[i].flags = res->flags;
-		size = resource_size(res);
-		do_div(size, iov->total_VFs);
+		size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES);
 		virtfn->resource[i].start = res->start + size * id;
 		virtfn->resource[i].end = virtfn->resource[i].start + size - 1;
 		rc = request_resource(res, &virtfn->resource[i]);
@@ -140,8 +190,8 @@ static void virtfn_remove(struct pci_dev *dev, int id, int reset)
 	struct pci_sriov *iov = dev->sriov;
 
 	virtfn = pci_get_domain_bus_and_slot(pci_domain_nr(dev->bus),
-					     virtfn_bus(dev, id),
-					     virtfn_devfn(dev, id));
+					     pci_iov_virtfn_bus(dev, id),
+					     pci_iov_virtfn_devfn(dev, id));
 	if (!virtfn)
 		return;
 
@@ -170,6 +220,11 @@ static void virtfn_remove(struct pci_dev *dev, int id, int reset)
 	pci_dev_put(dev);
 }
 
+int __weak pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
+{
+       return 0;
+}
+
 static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
 {
 	int rc;
@@ -180,6 +235,8 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
 	struct pci_dev *pdev;
 	struct pci_sriov *iov = dev->sriov;
 	int bars = 0;
+	int bus;
+	int retval;
 
 	if (!nr_virtfn)
 		return 0;
@@ -204,7 +261,7 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
 	nres = 0;
 	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
 		bars |= (1 << (i + PCI_IOV_RESOURCES));
-		res = dev->resource + PCI_IOV_RESOURCES + i;
+		res = &dev->resource[i + PCI_IOV_RESOURCES];
 		if (res->parent)
 			nres++;
 	}
@@ -216,8 +273,10 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
 	iov->offset = offset;
 	iov->stride = stride;
 
-	if (virtfn_bus(dev, nr_virtfn - 1) > dev->bus->busn_res.end) {
-		dev_err(&dev->dev, "SR-IOV: bus number out of range\n");
+	bus = pci_iov_virtfn_bus(dev, nr_virtfn - 1);
+	if (bus > dev->bus->busn_res.end) {
+		dev_err(&dev->dev, "can't enable %d VFs (bus %02x out of range of %pR)\n",
+			nr_virtfn, bus, &dev->bus->busn_res);
 		return -ENOMEM;
 	}
 
@@ -243,7 +302,7 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
 			return rc;
 	}
 
-	pci_write_config_word(dev, iov->pos + PCI_SRIOV_NUM_VF, nr_virtfn);
+	pci_iov_set_numvfs(dev, nr_virtfn);
 	iov->ctrl |= PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE;
 	pci_cfg_access_lock(dev);
 	pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
@@ -254,6 +313,12 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
 	if (nr_virtfn < initial)
 		initial = nr_virtfn;
 
+	if ((retval = pcibios_sriov_enable(dev, initial))) {
+		dev_err(&dev->dev, "failure %d from pcibios_sriov_enable()\n",
+			retval);
+		return retval;
+	}
+
 	for (i = 0; i < initial; i++) {
 		rc = virtfn_add(dev, i, 0);
 		if (rc)
@@ -272,7 +337,7 @@ failed:
 	iov->ctrl &= ~(PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE);
 	pci_cfg_access_lock(dev);
 	pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
-	pci_write_config_word(dev, iov->pos + PCI_SRIOV_NUM_VF, 0);
+	pci_iov_set_numvfs(dev, 0);
 	ssleep(1);
 	pci_cfg_access_unlock(dev);
 
@@ -282,6 +347,11 @@ failed:
 	return rc;
 }
 
+int __weak pcibios_sriov_disable(struct pci_dev *pdev)
+{
+       return 0;
+}
+
 static void sriov_disable(struct pci_dev *dev)
 {
 	int i;
@@ -293,6 +363,8 @@ static void sriov_disable(struct pci_dev *dev)
 	for (i = 0; i < iov->num_VFs; i++)
 		virtfn_remove(dev, i, 0);
 
+	pcibios_sriov_disable(dev);
+
 	iov->ctrl &= ~(PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE);
 	pci_cfg_access_lock(dev);
 	pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
@@ -303,12 +375,12 @@ static void sriov_disable(struct pci_dev *dev)
 		sysfs_remove_link(&dev->dev.kobj, "dep_link");
 
 	iov->num_VFs = 0;
-	pci_write_config_word(dev, iov->pos + PCI_SRIOV_NUM_VF, 0);
+	pci_iov_set_numvfs(dev, 0);
 }
 
 static int sriov_init(struct pci_dev *dev, int pos)
 {
-	int i;
+	int i, bar64;
 	int rc;
 	int nres;
 	u32 pgsz;
@@ -357,27 +429,29 @@ found:
 	pgsz &= ~(pgsz - 1);
 	pci_write_config_dword(dev, pos + PCI_SRIOV_SYS_PGSIZE, pgsz);
 
+	iov = kzalloc(sizeof(*iov), GFP_KERNEL);
+	if (!iov)
+		return -ENOMEM;
+
 	nres = 0;
 	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
-		res = dev->resource + PCI_IOV_RESOURCES + i;
-		i += __pci_read_base(dev, pci_bar_unknown, res,
-				     pos + PCI_SRIOV_BAR + i * 4);
+		res = &dev->resource[i + PCI_IOV_RESOURCES];
+		bar64 = __pci_read_base(dev, pci_bar_unknown, res,
+					pos + PCI_SRIOV_BAR + i * 4);
 		if (!res->flags)
 			continue;
 		if (resource_size(res) & (PAGE_SIZE - 1)) {
 			rc = -EIO;
 			goto failed;
 		}
+		iov->barsz[i] = resource_size(res);
 		res->end = res->start + resource_size(res) * total - 1;
+		dev_info(&dev->dev, "VF(n) BAR%d space: %pR (contains BAR%d for %d VFs)\n",
+			 i, res, i, total);
+		i += bar64;
 		nres++;
 	}
 
-	iov = kzalloc(sizeof(*iov), GFP_KERNEL);
-	if (!iov) {
-		rc = -ENOMEM;
-		goto failed;
-	}
-
 	iov->pos = pos;
 	iov->nres = nres;
 	iov->ctrl = ctrl;
@@ -400,15 +474,17 @@ found:
 
 	dev->sriov = iov;
 	dev->is_physfn = 1;
+	iov->max_VF_buses = virtfn_max_buses(dev);
 
 	return 0;
 
 failed:
 	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
-		res = dev->resource + PCI_IOV_RESOURCES + i;
+		res = &dev->resource[i + PCI_IOV_RESOURCES];
 		res->flags = 0;
 	}
 
+	kfree(iov);
 	return rc;
 }
 
@@ -439,7 +515,7 @@ static void sriov_restore_state(struct pci_dev *dev)
 		pci_update_resource(dev, i);
 
 	pci_write_config_dword(dev, iov->pos + PCI_SRIOV_SYS_PGSIZE, iov->pgsz);
-	pci_write_config_word(dev, iov->pos + PCI_SRIOV_NUM_VF, iov->num_VFs);
+	pci_iov_set_numvfs(dev, iov->num_VFs);
 	pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
 	if (iov->ctrl & PCI_SRIOV_CTRL_VFE)
 		msleep(100);
@@ -493,6 +569,12 @@ int pci_iov_resource_bar(struct pci_dev *dev, int resno)
 		4 * (resno - PCI_IOV_RESOURCES);
 }
 
+resource_size_t __weak pcibios_iov_resource_alignment(struct pci_dev *dev,
+						      int resno)
+{
+	return pci_iov_resource_size(dev, resno);
+}
+
 /**
  * pci_sriov_resource_alignment - get resource alignment for VF BAR
  * @dev: the PCI device
@@ -505,14 +587,7 @@ int pci_iov_resource_bar(struct pci_dev *dev, int resno)
  */
 resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno)
 {
-	struct resource tmp;
-	int reg = pci_iov_resource_bar(dev, resno);
-
-	if (!reg)
-		return 0;
-
-	 __pci_read_base(dev, pci_bar_unknown, &tmp, reg);
-	return resource_alignment(&tmp);
+	return pcibios_iov_resource_alignment(dev, resno);
 }
 
 /**
@@ -535,15 +610,13 @@ void pci_restore_iov_state(struct pci_dev *dev)
 int pci_iov_bus_range(struct pci_bus *bus)
 {
 	int max = 0;
-	u8 busnr;
 	struct pci_dev *dev;
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		if (!dev->is_physfn)
 			continue;
-		busnr = virtfn_bus(dev, dev->sriov->total_VFs - 1);
-		if (busnr > max)
-			max = busnr;
+		if (dev->sriov->max_VF_buses > max)
+			max = dev->sriov->max_VF_buses;
 	}
 
 	return max ? max - bus->number : 0;
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 4091f82239cd..bae593c04541 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -243,10 +243,12 @@ struct pci_sriov {
 	u16 stride;		/* following VF stride */
 	u32 pgsz;		/* page size for BAR alignment */
 	u8 link;		/* Function Dependency Link */
+	u8 max_VF_buses;	/* max buses consumed by VFs */
 	u16 driver_max_VFs;	/* max num VFs driver supports */
 	struct pci_dev *dev;	/* lowest numbered PF */
 	struct pci_dev *self;	/* this PF */
 	struct mutex lock;	/* lock for VF bus */
+	resource_size_t barsz[PCI_SRIOV_NUM_BARS];	/* VF BAR size */
 };
 
 #ifdef CONFIG_PCI_ATS
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index e3e17f3c0f0f..6603d401bb7c 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -99,8 +99,8 @@ static void remove_from_list(struct list_head *head,
 	}
 }
 
-static resource_size_t get_res_add_size(struct list_head *head,
-					struct resource *res)
+static struct pci_dev_resource *res_to_dev_res(struct list_head *head,
+					       struct resource *res)
 {
 	struct pci_dev_resource *dev_res;
 
@@ -109,17 +109,37 @@ static resource_size_t get_res_add_size(struct list_head *head,
 			int idx = res - &dev_res->dev->resource[0];
 
 			dev_printk(KERN_DEBUG, &dev_res->dev->dev,
-				 "res[%d]=%pR get_res_add_size add_size %llx\n",
+				 "res[%d]=%pR res_to_dev_res add_size %llx min_align %llx\n",
 				 idx, dev_res->res,
-				 (unsigned long long)dev_res->add_size);
+				 (unsigned long long)dev_res->add_size,
+				 (unsigned long long)dev_res->min_align);
 
-			return dev_res->add_size;
+			return dev_res;
 		}
 	}
 
-	return 0;
+	return NULL;
 }
 
+static resource_size_t get_res_add_size(struct list_head *head,
+					struct resource *res)
+{
+	struct pci_dev_resource *dev_res;
+
+	dev_res = res_to_dev_res(head, res);
+	return dev_res ? dev_res->add_size : 0;
+}
+
+static resource_size_t get_res_add_align(struct list_head *head,
+					 struct resource *res)
+{
+	struct pci_dev_resource *dev_res;
+
+	dev_res = res_to_dev_res(head, res);
+	return dev_res ? dev_res->min_align : 0;
+}
+
+
 /* Sort resources by alignment */
 static void pdev_sort_resources(struct pci_dev *dev, struct list_head *head)
 {
@@ -215,7 +235,7 @@ static void reassign_resources_sorted(struct list_head *realloc_head,
 	struct resource *res;
 	struct pci_dev_resource *add_res, *tmp;
 	struct pci_dev_resource *dev_res;
-	resource_size_t add_size;
+	resource_size_t add_size, align;
 	int idx;
 
 	list_for_each_entry_safe(add_res, tmp, realloc_head, list) {
@@ -238,13 +258,13 @@ static void reassign_resources_sorted(struct list_head *realloc_head,
 
 		idx = res - &add_res->dev->resource[0];
 		add_size = add_res->add_size;
+		align = add_res->min_align;
 		if (!resource_size(res)) {
-			res->start = add_res->start;
+			res->start = align;
 			res->end = res->start + add_size - 1;
 			if (pci_assign_resource(add_res->dev, idx))
 				reset_resource(res);
 		} else {
-			resource_size_t align = add_res->min_align;
 			res->flags |= add_res->flags &
 				 (IORESOURCE_STARTALIGN|IORESOURCE_SIZEALIGN);
 			if (pci_reassign_resource(add_res->dev, idx,
@@ -368,8 +388,9 @@ static void __assign_resources_sorted(struct list_head *head,
 	LIST_HEAD(save_head);
 	LIST_HEAD(local_fail_head);
 	struct pci_dev_resource *save_res;
-	struct pci_dev_resource *dev_res, *tmp_res;
+	struct pci_dev_resource *dev_res, *tmp_res, *dev_res2;
 	unsigned long fail_type;
+	resource_size_t add_align, align;
 
 	/* Check if optional add_size is there */
 	if (!realloc_head || list_empty(realloc_head))
@@ -384,10 +405,44 @@ static void __assign_resources_sorted(struct list_head *head,
 	}
 
 	/* Update res in head list with add_size in realloc_head list */
-	list_for_each_entry(dev_res, head, list)
+	list_for_each_entry_safe(dev_res, tmp_res, head, list) {
 		dev_res->res->end += get_res_add_size(realloc_head,
 							dev_res->res);
 
+		/*
+		 * There are two kinds of additional resources in the list:
+		 * 1. bridge resource  -- IORESOURCE_STARTALIGN
+		 * 2. SR-IOV resource   -- IORESOURCE_SIZEALIGN
+		 * Here just fix the additional alignment for bridge
+		 */
+		if (!(dev_res->res->flags & IORESOURCE_STARTALIGN))
+			continue;
+
+		add_align = get_res_add_align(realloc_head, dev_res->res);
+
+		/*
+		 * The "head" list is sorted by the alignment to make sure
+		 * resources with bigger alignment will be assigned first.
+		 * After we change the alignment of a dev_res in "head" list,
+		 * we need to reorder the list by alignment to make it
+		 * consistent.
+		 */
+		if (add_align > dev_res->res->start) {
+			dev_res->res->start = add_align;
+			dev_res->res->end = add_align +
+				            resource_size(dev_res->res);
+
+			list_for_each_entry(dev_res2, head, list) {
+				align = pci_resource_alignment(dev_res2->dev,
+							       dev_res2->res);
+				if (add_align > align)
+					list_move_tail(&dev_res->list,
+						       &dev_res2->list);
+			}
+               }
+
+	}
+
 	/* Try updated head list with add_size added */
 	assign_requested_resources_sorted(head, &local_fail_head);
 
@@ -962,6 +1017,8 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
 	struct resource *b_res = find_free_bus_resource(bus,
 					mask | IORESOURCE_PREFETCH, type);
 	resource_size_t children_add_size = 0;
+	resource_size_t children_add_align = 0;
+	resource_size_t add_align = 0;
 
 	if (!b_res)
 		return -ENOSPC;
@@ -986,6 +1043,7 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
 			/* put SRIOV requested res to the optional list */
 			if (realloc_head && i >= PCI_IOV_RESOURCES &&
 					i <= PCI_IOV_RESOURCE_END) {
+				add_align = max(pci_resource_alignment(dev, r), add_align);
 				r->end = r->start - 1;
 				add_to_list(realloc_head, dev, r, r_size, 0/* don't care */);
 				children_add_size += r_size;
@@ -1016,19 +1074,23 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
 			if (order > max_order)
 				max_order = order;
 
-			if (realloc_head)
+			if (realloc_head) {
 				children_add_size += get_res_add_size(realloc_head, r);
+				children_add_align = get_res_add_align(realloc_head, r);
+				add_align = max(add_align, children_add_align);
+			}
 		}
 	}
 
 	min_align = calculate_mem_align(aligns, max_order);
 	min_align = max(min_align, window_alignment(bus, b_res->flags));
 	size0 = calculate_memsize(size, min_size, 0, resource_size(b_res), min_align);
+	add_align = max(min_align, add_align);
 	if (children_add_size > add_size)
 		add_size = children_add_size;
 	size1 = (!realloc_head || (realloc_head && !add_size)) ? size0 :
 		calculate_memsize(size, min_size, add_size,
-				resource_size(b_res), min_align);
+				resource_size(b_res), add_align);
 	if (!size0 && !size1) {
 		if (b_res->start || b_res->end)
 			dev_info(&bus->self->dev, "disabling bridge window %pR to %pR (unused)\n",
@@ -1040,10 +1102,11 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
 	b_res->end = size0 + min_align - 1;
 	b_res->flags |= IORESOURCE_STARTALIGN;
 	if (size1 > size0 && realloc_head) {
-		add_to_list(realloc_head, bus->self, b_res, size1-size0, min_align);
-		dev_printk(KERN_DEBUG, &bus->self->dev, "bridge window %pR to %pR add_size %llx\n",
+		add_to_list(realloc_head, bus->self, b_res, size1-size0, add_align);
+		dev_printk(KERN_DEBUG, &bus->self->dev, "bridge window %pR to %pR add_size %llx add_align %llx\n",
 			   b_res, &bus->busn_res,
-			   (unsigned long long)size1-size0);
+			   (unsigned long long) (size1 - size0),
+			   (unsigned long long) add_align);
 	}
 	return 0;
 }