powerpc/vfio: Enable on PowerNV platform

This initializes IOMMU groups based on the IOMMU configuration
discovered during the PCI scan on POWERNV (POWER non virtualized)
platform.  The IOMMU groups are to be used later by the VFIO driver,
which is used for PCI pass through.

It also implements an API for mapping/unmapping pages for
guest PCI drivers and providing DMA window properties.
This API is going to be used later by QEMU-VFIO to handle
h_put_tce hypercalls from the KVM guest.

The iommu_put_tce_user_mode() does only a single page mapping
as an API for adding many mappings at once is going to be
added later.

Although this driver has been tested only on the POWERNV
platform, it should work on any platform which supports
TCE tables.  As h_put_tce hypercall is received by the host
kernel and processed by the QEMU (what involves calling
the host kernel again), performance is not the best -
circa 220MB/s on 10Gb ethernet network.

To enable VFIO on POWER, enable SPAPR_TCE_IOMMU config
option and configure VFIO as required.

Cc: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

6 files changed, 364 insertions, 1 deletions

diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index cbfe678e3dbe..98d14229f893 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -76,6 +76,9 @@ struct iommu_table {
 	struct iommu_pool large_pool;
 	struct iommu_pool pools[IOMMU_NR_POOLS];
 	unsigned long *it_map;       /* A simple allocation bitmap for now */
+#ifdef CONFIG_IOMMU_API
+	struct iommu_group *it_group;
+#endif
 };
 
 struct scatterlist;
@@ -98,6 +101,8 @@ extern void iommu_free_table(struct iommu_table *tbl, const char *node_name);
  */
 extern struct iommu_table *iommu_init_table(struct iommu_table * tbl,
 					    int nid);
+extern void iommu_register_group(struct iommu_table *tbl,
+				 int pci_domain_number, unsigned long pe_num);
 
 extern int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 			struct scatterlist *sglist, int nelems,
@@ -147,5 +152,26 @@ static inline void iommu_restore(void)
 }
 #endif
 
+/* The API to support IOMMU operations for VFIO */
+extern int iommu_tce_clear_param_check(struct iommu_table *tbl,
+		unsigned long ioba, unsigned long tce_value,
+		unsigned long npages);
+extern int iommu_tce_put_param_check(struct iommu_table *tbl,
+		unsigned long ioba, unsigned long tce);
+extern int iommu_tce_build(struct iommu_table *tbl, unsigned long entry,
+		unsigned long hwaddr, enum dma_data_direction direction);
+extern unsigned long iommu_clear_tce(struct iommu_table *tbl,
+		unsigned long entry);
+extern int iommu_clear_tces_and_put_pages(struct iommu_table *tbl,
+		unsigned long entry, unsigned long pages);
+extern int iommu_put_tce_user_mode(struct iommu_table *tbl,
+		unsigned long entry, unsigned long tce);
+
+extern void iommu_flush_tce(struct iommu_table *tbl);
+extern int iommu_take_ownership(struct iommu_table *tbl);
+extern void iommu_release_ownership(struct iommu_table *tbl);
+
+extern enum dma_data_direction iommu_tce_direction(unsigned long tce);
+
 #endif /* __KERNEL__ */
 #endif /* _ASM_IOMMU_H */
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index c0d0dbddfba1..b20ff173a671 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -36,6 +36,8 @@
 #include <linux/hash.h>
 #include <linux/fault-inject.h>
 #include <linux/pci.h>
+#include <linux/iommu.h>
+#include <linux/sched.h>
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/iommu.h>
@@ -44,6 +46,7 @@
 #include <asm/kdump.h>
 #include <asm/fadump.h>
 #include <asm/vio.h>
+#include <asm/tce.h>
 
 #define DBG(...)
 
@@ -724,6 +727,13 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
 	if (tbl->it_offset == 0)
 		clear_bit(0, tbl->it_map);
 
+#ifdef CONFIG_IOMMU_API
+	if (tbl->it_group) {
+		iommu_group_put(tbl->it_group);
+		BUG_ON(tbl->it_group);
+	}
+#endif
+
 	/* verify that table contains no entries */
 	if (!bitmap_empty(tbl->it_map, tbl->it_size))
 		pr_warn("%s: Unexpected TCEs for %s\n", __func__, node_name);
@@ -860,3 +870,316 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size,
 		free_pages((unsigned long)vaddr, get_order(size));
 	}
 }
+
+#ifdef CONFIG_IOMMU_API
+/*
+ * SPAPR TCE API
+ */
+static void group_release(void *iommu_data)
+{
+	struct iommu_table *tbl = iommu_data;
+	tbl->it_group = NULL;
+}
+
+void iommu_register_group(struct iommu_table *tbl,
+		int pci_domain_number, unsigned long pe_num)
+{
+	struct iommu_group *grp;
+	char *name;
+
+	grp = iommu_group_alloc();
+	if (IS_ERR(grp)) {
+		pr_warn("powerpc iommu api: cannot create new group, err=%ld\n",
+				PTR_ERR(grp));
+		return;
+	}
+	tbl->it_group = grp;
+	iommu_group_set_iommudata(grp, tbl, group_release);
+	name = kasprintf(GFP_KERNEL, "domain%d-pe%lx",
+			pci_domain_number, pe_num);
+	if (!name)
+		return;
+	iommu_group_set_name(grp, name);
+	kfree(name);
+}
+
+enum dma_data_direction iommu_tce_direction(unsigned long tce)
+{
+	if ((tce & TCE_PCI_READ) && (tce & TCE_PCI_WRITE))
+		return DMA_BIDIRECTIONAL;
+	else if (tce & TCE_PCI_READ)
+		return DMA_TO_DEVICE;
+	else if (tce & TCE_PCI_WRITE)
+		return DMA_FROM_DEVICE;
+	else
+		return DMA_NONE;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_direction);
+
+void iommu_flush_tce(struct iommu_table *tbl)
+{
+	/* Flush/invalidate TLB caches if necessary */
+	if (ppc_md.tce_flush)
+		ppc_md.tce_flush(tbl);
+
+	/* Make sure updates are seen by hardware */
+	mb();
+}
+EXPORT_SYMBOL_GPL(iommu_flush_tce);
+
+int iommu_tce_clear_param_check(struct iommu_table *tbl,
+		unsigned long ioba, unsigned long tce_value,
+		unsigned long npages)
+{
+	/* ppc_md.tce_free() does not support any value but 0 */
+	if (tce_value)
+		return -EINVAL;
+
+	if (ioba & ~IOMMU_PAGE_MASK)
+		return -EINVAL;
+
+	ioba >>= IOMMU_PAGE_SHIFT;
+	if (ioba < tbl->it_offset)
+		return -EINVAL;
+
+	if ((ioba + npages) > (tbl->it_offset + tbl->it_size))
+		return -EINVAL;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_clear_param_check);
+
+int iommu_tce_put_param_check(struct iommu_table *tbl,
+		unsigned long ioba, unsigned long tce)
+{
+	if (!(tce & (TCE_PCI_WRITE | TCE_PCI_READ)))
+		return -EINVAL;
+
+	if (tce & ~(IOMMU_PAGE_MASK | TCE_PCI_WRITE | TCE_PCI_READ))
+		return -EINVAL;
+
+	if (ioba & ~IOMMU_PAGE_MASK)
+		return -EINVAL;
+
+	ioba >>= IOMMU_PAGE_SHIFT;
+	if (ioba < tbl->it_offset)
+		return -EINVAL;
+
+	if ((ioba + 1) > (tbl->it_offset + tbl->it_size))
+		return -EINVAL;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_put_param_check);
+
+unsigned long iommu_clear_tce(struct iommu_table *tbl, unsigned long entry)
+{
+	unsigned long oldtce;
+	struct iommu_pool *pool = get_pool(tbl, entry);
+
+	spin_lock(&(pool->lock));
+
+	oldtce = ppc_md.tce_get(tbl, entry);
+	if (oldtce & (TCE_PCI_WRITE | TCE_PCI_READ))
+		ppc_md.tce_free(tbl, entry, 1);
+	else
+		oldtce = 0;
+
+	spin_unlock(&(pool->lock));
+
+	return oldtce;
+}
+EXPORT_SYMBOL_GPL(iommu_clear_tce);
+
+int iommu_clear_tces_and_put_pages(struct iommu_table *tbl,
+		unsigned long entry, unsigned long pages)
+{
+	unsigned long oldtce;
+	struct page *page;
+
+	for ( ; pages; --pages, ++entry) {
+		oldtce = iommu_clear_tce(tbl, entry);
+		if (!oldtce)
+			continue;
+
+		page = pfn_to_page(oldtce >> PAGE_SHIFT);
+		WARN_ON(!page);
+		if (page) {
+			if (oldtce & TCE_PCI_WRITE)
+				SetPageDirty(page);
+			put_page(page);
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_clear_tces_and_put_pages);
+
+/*
+ * hwaddr is a kernel virtual address here (0xc... bazillion),
+ * tce_build converts it to a physical address.
+ */
+int iommu_tce_build(struct iommu_table *tbl, unsigned long entry,
+		unsigned long hwaddr, enum dma_data_direction direction)
+{
+	int ret = -EBUSY;
+	unsigned long oldtce;
+	struct iommu_pool *pool = get_pool(tbl, entry);
+
+	spin_lock(&(pool->lock));
+
+	oldtce = ppc_md.tce_get(tbl, entry);
+	/* Add new entry if it is not busy */
+	if (!(oldtce & (TCE_PCI_WRITE | TCE_PCI_READ)))
+		ret = ppc_md.tce_build(tbl, entry, 1, hwaddr, direction, NULL);
+
+	spin_unlock(&(pool->lock));
+
+	/* if (unlikely(ret))
+		pr_err("iommu_tce: %s failed on hwaddr=%lx ioba=%lx kva=%lx ret=%d\n",
+				__func__, hwaddr, entry << IOMMU_PAGE_SHIFT,
+				hwaddr, ret); */
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_build);
+
+int iommu_put_tce_user_mode(struct iommu_table *tbl, unsigned long entry,
+		unsigned long tce)
+{
+	int ret;
+	struct page *page = NULL;
+	unsigned long hwaddr, offset = tce & IOMMU_PAGE_MASK & ~PAGE_MASK;
+	enum dma_data_direction direction = iommu_tce_direction(tce);
+
+	ret = get_user_pages_fast(tce & PAGE_MASK, 1,
+			direction != DMA_TO_DEVICE, &page);
+	if (unlikely(ret != 1)) {
+		/* pr_err("iommu_tce: get_user_pages_fast failed tce=%lx ioba=%lx ret=%d\n",
+				tce, entry << IOMMU_PAGE_SHIFT, ret); */
+		return -EFAULT;
+	}
+	hwaddr = (unsigned long) page_address(page) + offset;
+
+	ret = iommu_tce_build(tbl, entry, hwaddr, direction);
+	if (ret)
+		put_page(page);
+
+	if (ret < 0)
+		pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%d\n",
+				__func__, entry << IOMMU_PAGE_SHIFT, tce, ret);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_put_tce_user_mode);
+
+int iommu_take_ownership(struct iommu_table *tbl)
+{
+	unsigned long sz = (tbl->it_size + 7) >> 3;
+
+	if (tbl->it_offset == 0)
+		clear_bit(0, tbl->it_map);
+
+	if (!bitmap_empty(tbl->it_map, tbl->it_size)) {
+		pr_err("iommu_tce: it_map is not empty");
+		return -EBUSY;
+	}
+
+	memset(tbl->it_map, 0xff, sz);
+	iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_take_ownership);
+
+void iommu_release_ownership(struct iommu_table *tbl)
+{
+	unsigned long sz = (tbl->it_size + 7) >> 3;
+
+	iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size);
+	memset(tbl->it_map, 0, sz);
+
+	/* Restore bit#0 set by iommu_init_table() */
+	if (tbl->it_offset == 0)
+		set_bit(0, tbl->it_map);
+}
+EXPORT_SYMBOL_GPL(iommu_release_ownership);
+
+static int iommu_add_device(struct device *dev)
+{
+	struct iommu_table *tbl;
+	int ret = 0;
+
+	if (WARN_ON(dev->iommu_group)) {
+		pr_warn("iommu_tce: device %s is already in iommu group %d, skipping\n",
+				dev_name(dev),
+				iommu_group_id(dev->iommu_group));
+		return -EBUSY;
+	}
+
+	tbl = get_iommu_table_base(dev);
+	if (!tbl || !tbl->it_group) {
+		pr_debug("iommu_tce: skipping device %s with no tbl\n",
+				dev_name(dev));
+		return 0;
+	}
+
+	pr_debug("iommu_tce: adding %s to iommu group %d\n",
+			dev_name(dev), iommu_group_id(tbl->it_group));
+
+	ret = iommu_group_add_device(tbl->it_group, dev);
+	if (ret < 0)
+		pr_err("iommu_tce: %s has not been added, ret=%d\n",
+				dev_name(dev), ret);
+
+	return ret;
+}
+
+static void iommu_del_device(struct device *dev)
+{
+	iommu_group_remove_device(dev);
+}
+
+static int iommu_bus_notifier(struct notifier_block *nb,
+			      unsigned long action, void *data)
+{
+	struct device *dev = data;
+
+	switch (action) {
+	case BUS_NOTIFY_ADD_DEVICE:
+		return iommu_add_device(dev);
+	case BUS_NOTIFY_DEL_DEVICE:
+		iommu_del_device(dev);
+		return 0;
+	default:
+		return 0;
+	}
+}
+
+static struct notifier_block tce_iommu_bus_nb = {
+	.notifier_call = iommu_bus_notifier,
+};
+
+static int __init tce_iommu_init(void)
+{
+	struct pci_dev *pdev = NULL;
+
+	BUILD_BUG_ON(PAGE_SIZE < IOMMU_PAGE_SIZE);
+
+	for_each_pci_dev(pdev)
+		iommu_add_device(&pdev->dev);
+
+	bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb);
+	return 0;
+}
+
+subsys_initcall_sync(tce_iommu_init);
+
+#else
+
+void iommu_register_group(struct iommu_table *tbl,
+		int pci_domain_number, unsigned long pe_num)
+{
+}
+
+#endif /* CONFIG_IOMMU_API */
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 9c9d15e4cdf2..2931d97baa56 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -595,6 +595,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 			       TCE_PCI_SWINV_PAIR;
 	}
 	iommu_init_table(tbl, phb->hose->node);
+	iommu_register_group(tbl, pci_domain_nr(pe->pbus), pe->pe_number);
 
 	return;
  fail:
diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
index 92b37a0186c9..5d378f2d9e26 100644
--- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c
+++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
@@ -86,8 +86,11 @@ static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) { }
 static void pnv_pci_p5ioc2_dma_dev_setup(struct pnv_phb *phb,
 					 struct pci_dev *pdev)
 {
-	if (phb->p5ioc2.iommu_table.it_map == NULL)
+	if (phb->p5ioc2.iommu_table.it_map == NULL) {
 		iommu_init_table(&phb->p5ioc2.iommu_table, phb->hose->node);
+		iommu_register_group(&phb->p5ioc2.iommu_table,
+				pci_domain_nr(phb->hose->bus), phb->opal_id);
+	}
 
 	set_iommu_table_base(&pdev->dev, &phb->p5ioc2.iommu_table);
 }
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 277343cc6a3d..e16b729f46f9 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -20,6 +20,7 @@
 #include <linux/irq.h>
 #include <linux/io.h>
 #include <linux/msi.h>
+#include <linux/iommu.h>
 
 #include <asm/sections.h>
 #include <asm/io.h>
@@ -412,6 +413,7 @@ static struct iommu_table *pnv_pci_setup_bml_iommu(struct pci_controller *hose)
 	pnv_pci_setup_iommu_table(tbl, __va(be64_to_cpup(basep)),
 				  be32_to_cpup(sizep), 0);
 	iommu_init_table(tbl, hose->node);
+	iommu_register_group(tbl, pci_domain_nr(hose->bus), 0);
 
 	/* Deal with SW invalidated TCEs when needed (BML way) */
 	swinvp = of_get_property(hose->dn, "linux,tce-sw-invalidate-info",
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index c332fb98480d..3f3abde8a7f9 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -261,4 +261,12 @@ config SHMOBILE_IOMMU_L1SIZE
 	default 256 if SHMOBILE_IOMMU_ADDRSIZE_64MB
 	default 128 if SHMOBILE_IOMMU_ADDRSIZE_32MB
 
+config SPAPR_TCE_IOMMU
+	bool "sPAPR TCE IOMMU Support"
+	depends on PPC_POWERNV
+	select IOMMU_API
+	help
+	  Enables bits of IOMMU API required by VFIO. The iommu_ops
+	  is not implemented as it is not necessary for VFIO.
+
 endif # IOMMU_SUPPORT