[PATCH 0/5 v2] VFIO PPC64: add VFIO support on POWERPC64

[PATCH 0/5 v2] VFIO PPC64: add VFIO support on POWERPC64

[Alexey Kardashevskiy]

The series adds support for VFIO on POWERPC in user space (such as QEMU).
The in-kernel real mode IOMMU support is added by another series posted
separately.

As the first and main aim of this series is the POWERNV platform support,
the "Enable on POWERNV platform" patch goes first and introduces an API
to be used by the VFIO IOMMU driver. The "Enable on pSeries platform" patch
simply registers PHBs in the IOMMU subsystem and expects the API to be present,
it enables VFIO support in fully emulated QEMU guests.

The main change is that this series was changed and tested against v3.10-rc1.
It also contains some bugfixes which are mentioned (if any) in the patch messages.

Alexey Kardashevskiy (3):
  powerpc/vfio: Enable on POWERNV platform
  powerpc/vfio: Implement IOMMU driver for VFIO
  powerpc/vfio: Enable on pSeries platform

 Documentation/vfio.txt                      |   63 +++++
 arch/powerpc/include/asm/iommu.h            |   26 ++
 arch/powerpc/kernel/iommu.c                 |  323 +++++++++++++++++++++++
 arch/powerpc/platforms/powernv/pci-ioda.c   |    1 +
 arch/powerpc/platforms/powernv/pci-p5ioc2.c |    5 +-
 arch/powerpc/platforms/powernv/pci.c        |    2 +
 arch/powerpc/platforms/pseries/iommu.c      |    4 +
 drivers/iommu/Kconfig                       |    8 +
 drivers/vfio/Kconfig                        |    6 +
 drivers/vfio/Makefile                       |    1 +
 drivers/vfio/vfio.c                         |    1 +
 drivers/vfio/vfio_iommu_spapr_tce.c         |  377 +++++++++++++++++++++++++++
 include/uapi/linux/vfio.h                   |   34 +++
 13 files changed, 850 insertions(+), 1 deletion(-)
 create mode 100644 drivers/vfio/vfio_iommu_spapr_tce.c

-- 
1.7.10.4

[PATCH 1/3] powerpc/vfio: Enable on POWERNV platform

[Alexey Kardashevskiy]

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>

---

Changes:
* the PCI devices are added to groups from subsys_initcall_sync (used to
be done via bus_notifier callback registered for PCI bus)
* fixed parameters checking (the very last page in the address space was
not handled correctly)
---
 arch/powerpc/include/asm/iommu.h            |   26 +++
 arch/powerpc/kernel/iommu.c                 |  323 +++++++++++++++++++++++++++
 arch/powerpc/platforms/powernv/pci-ioda.c   |    1 +
 arch/powerpc/platforms/powernv/pci-p5ioc2.c |    5 +-
 arch/powerpc/platforms/powernv/pci.c        |    2 +
 drivers/iommu/Kconfig                       |    8 +
 6 files changed, 364 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index cbfe678..98d1422 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 c0d0dbd..b20ff17 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 1da578b..cae2555 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -605,6 +605,7 @@ 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 92b37a0..5d378f2 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 55dfca844..bd69285 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>
@@ -408,6 +409,7 @@ 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 c332fb9..3f3abde 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
-- 
1.7.10.4

[PATCH 2/3] powerpc/vfio: Implement IOMMU driver for VFIO

[Alexey Kardashevskiy]

VFIO implements platform independent stuff such as
a PCI driver, BAR access (via read/write on a file descriptor
or direct mapping when possible) and IRQ signaling.

The platform dependent part includes IOMMU initialization
and handling.  This implements an IOMMU driver for VFIO
which does mapping/unmapping pages for the guest IO and
provides information about DMA window (required by a POWER
guest).

Cc: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 Documentation/vfio.txt              |   63 ++++++
 drivers/vfio/Kconfig                |    6 +
 drivers/vfio/Makefile               |    1 +
 drivers/vfio/vfio.c                 |    1 +
 drivers/vfio/vfio_iommu_spapr_tce.c |  377 +++++++++++++++++++++++++++++++++++
 include/uapi/linux/vfio.h           |   34 ++++
 6 files changed, 482 insertions(+)
 create mode 100644 drivers/vfio/vfio_iommu_spapr_tce.c

diff --git a/Documentation/vfio.txt b/Documentation/vfio.txt
index 8eda363..c55533c 100644
--- a/Documentation/vfio.txt
+++ b/Documentation/vfio.txt
@@ -283,6 +283,69 @@ a direct pass through for VFIO_DEVICE_* ioctls.  The read/write/mmap
 interfaces implement the device region access defined by the device's
 own VFIO_DEVICE_GET_REGION_INFO ioctl.
 
+
+PPC64 sPAPR implementation note
+-------------------------------------------------------------------------------
+
+This implementation has some specifics:
+
+1) Only one IOMMU group per container is supported as an IOMMU group
+represents the minimal entity which isolation can be guaranteed for and
+groups are allocated statically, one per a Partitionable Endpoint (PE)
+(PE is often a PCI domain but not always).
+
+2) The hardware supports so called DMA windows - the PCI address range
+within which DMA transfer is allowed, any attempt to access address space
+out of the window leads to the whole PE isolation.
+
+3) PPC64 guests are paravirtualized but not fully emulated. There is an API
+to map/unmap pages for DMA, and it normally maps 1..32 pages per call and
+currently there is no way to reduce the number of calls. In order to make things
+faster, the map/unmap handling has been implemented in real mode which provides
+an excellent performance which has limitations such as inability to do
+locked pages accounting in real time.
+
+So 3 additional ioctls have been added:
+
+	VFIO_IOMMU_SPAPR_TCE_GET_INFO - returns the size and the start
+		of the DMA window on the PCI bus.
+
+	VFIO_IOMMU_ENABLE - enables the container. The locked pages accounting
+		is done at this point. This lets user first to know what
+		the DMA window is and adjust rlimit before doing any real job.
+
+	VFIO_IOMMU_DISABLE - disables the container.
+
+
+The code flow from the example above should be slightly changed:
+
+	.....
+	/* Add the group to the container */
+	ioctl(group, VFIO_GROUP_SET_CONTAINER, &container);
+
+	/* Enable the IOMMU model we want */
+	ioctl(container, VFIO_SET_IOMMU, VFIO_SPAPR_TCE_IOMMU)
+
+	/* Get addition sPAPR IOMMU info */
+	vfio_iommu_spapr_tce_info spapr_iommu_info;
+	ioctl(container, VFIO_IOMMU_SPAPR_TCE_GET_INFO, &spapr_iommu_info);
+
+	if (ioctl(container, VFIO_IOMMU_ENABLE))
+		/* Cannot enable container, may be low rlimit */
+
+	/* Allocate some space and setup a DMA mapping */
+	dma_map.vaddr = mmap(0, 1024 * 1024, PROT_READ | PROT_WRITE,
+			     MAP_PRIVATE | MAP_ANONYMOUS, 0, 0);
+
+	dma_map.size = 1024 * 1024;
+	dma_map.iova = 0; /* 1MB starting at 0x0 from device view */
+	dma_map.flags = VFIO_DMA_MAP_FLAG_READ | VFIO_DMA_MAP_FLAG_WRITE;
+
+	/* Check here is .iova/.size are within DMA window from spapr_iommu_info */
+
+	ioctl(container, VFIO_IOMMU_MAP_DMA, &dma_map);
+	.....
+
 -------------------------------------------------------------------------------
 
 [1] VFIO was originally an acronym for "Virtual Function I/O" in its
diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
index 7cd5dec..b464687 100644
--- a/drivers/vfio/Kconfig
+++ b/drivers/vfio/Kconfig
@@ -3,10 +3,16 @@ config VFIO_IOMMU_TYPE1
 	depends on VFIO
 	default n
 
+config VFIO_IOMMU_SPAPR_TCE
+	tristate
+	depends on VFIO && SPAPR_TCE_IOMMU
+	default n
+
 menuconfig VFIO
 	tristate "VFIO Non-Privileged userspace driver framework"
 	depends on IOMMU_API
 	select VFIO_IOMMU_TYPE1 if X86
+	select VFIO_IOMMU_SPAPR_TCE if PPC_POWERNV
 	help
 	  VFIO provides a framework for secure userspace device drivers.
 	  See Documentation/vfio.txt for more details.
diff --git a/drivers/vfio/Makefile b/drivers/vfio/Makefile
index 2398d4a..72bfabc 100644
--- a/drivers/vfio/Makefile
+++ b/drivers/vfio/Makefile
@@ -1,3 +1,4 @@
 obj-$(CONFIG_VFIO) += vfio.o
 obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o
+obj-$(CONFIG_VFIO_IOMMU_SPAPR_TCE) += vfio_iommu_spapr_tce.o
 obj-$(CONFIG_VFIO_PCI) += pci/
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 295c48f..a819604 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -1428,6 +1428,7 @@ static int __init vfio_init(void)
 	 * drivers.
 	 */
 	request_module_nowait("vfio_iommu_type1");
+	request_module_nowait("vfio_iommu_spapr_tce");
 
 	return 0;
 
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
new file mode 100644
index 0000000..bdae7a0
--- /dev/null
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -0,0 +1,377 @@
+/*
+ * VFIO: IOMMU DMA mapping support for TCE on POWER
+ *
+ * Copyright (C) 2013 IBM Corp.  All rights reserved.
+ *     Author: Alexey Kardashevskiy <aik@ozlabs.ru>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Derived from original vfio_iommu_type1.c:
+ * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
+ *     Author: Alex Williamson <alex.williamson@redhat.com>
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/err.h>
+#include <linux/vfio.h>
+#include <asm/iommu.h>
+#include <asm/tce.h>
+
+#define DRIVER_VERSION  "0.1"
+#define DRIVER_AUTHOR   "aik@ozlabs.ru"
+#define DRIVER_DESC     "VFIO IOMMU SPAPR TCE"
+
+static void tce_iommu_detach_group(void *iommu_data,
+		struct iommu_group *iommu_group);
+
+/*
+ * VFIO IOMMU fd for SPAPR_TCE IOMMU implementation
+ *
+ * This code handles mapping and unmapping of user data buffers
+ * into DMA'ble space using the IOMMU
+ */
+
+/*
+ * The container descriptor supports only a single group per container.
+ * Required by the API as the container is not supplied with the IOMMU group
+ * at the moment of initialization.
+ */
+struct tce_container {
+	struct mutex lock;
+	struct iommu_table *tbl;
+	bool enabled;
+};
+
+static int tce_iommu_enable(struct tce_container *container)
+{
+	int ret = 0;
+	unsigned long locked, lock_limit, npages;
+	struct iommu_table *tbl = container->tbl;
+
+	if (!container->tbl)
+		return -ENXIO;
+
+	if (!current->mm)
+		return -ESRCH; /* process exited */
+
+	if (container->enabled)
+		return -EBUSY;
+
+	/*
+	 * When userspace pages are mapped into the IOMMU, they are effectively
+	 * locked memory, so, theoretically, we need to update the accounting
+	 * of locked pages on each map and unmap.  For powerpc, the map unmap
+	 * paths can be very hot, though, and the accounting would kill
+	 * performance, especially since it would be difficult to impossible
+	 * to handle the accounting in real mode only.
+	 *
+	 * To address that, rather than precisely accounting every page, we
+	 * instead account for a worst case on locked memory when the iommu is
+	 * enabled and disabled.  The worst case upper bound on locked memory
+	 * is the size of the whole iommu window, which is usually relatively
+	 * small (compared to total memory sizes) on POWER hardware.
+	 *
+	 * Also we don't have a nice way to fail on H_PUT_TCE due to ulimits,
+	 * that would effectively kill the guest at random points, much better
+	 * enforcing the limit based on the max that the guest can map.
+	 */
+	down_write(&current->mm->mmap_sem);
+	npages = (tbl->it_size << IOMMU_PAGE_SHIFT) >> PAGE_SHIFT;
+	locked = current->mm->locked_vm + npages;
+	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+	if (locked > lock_limit && !capable(CAP_IPC_LOCK)) {
+		pr_warn("RLIMIT_MEMLOCK (%ld) exceeded\n",
+				rlimit(RLIMIT_MEMLOCK));
+		ret = -ENOMEM;
+	} else {
+
+		current->mm->locked_vm += npages;
+		container->enabled = true;
+	}
+	up_write(&current->mm->mmap_sem);
+
+	return ret;
+}
+
+static void tce_iommu_disable(struct tce_container *container)
+{
+	if (!container->enabled)
+		return;
+
+	container->enabled = false;
+
+	if (!container->tbl || !current->mm)
+		return;
+
+	down_write(&current->mm->mmap_sem);
+	current->mm->locked_vm -= (container->tbl->it_size <<
+			IOMMU_PAGE_SHIFT) >> PAGE_SHIFT;
+	up_write(&current->mm->mmap_sem);
+}
+
+static void *tce_iommu_open(unsigned long arg)
+{
+	struct tce_container *container;
+
+	if (arg != VFIO_SPAPR_TCE_IOMMU) {
+		pr_err("tce_vfio: Wrong IOMMU type\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	container = kzalloc(sizeof(*container), GFP_KERNEL);
+	if (!container)
+		return ERR_PTR(-ENOMEM);
+
+	mutex_init(&container->lock);
+
+	return container;
+}
+
+static void tce_iommu_release(void *iommu_data)
+{
+	struct tce_container *container = iommu_data;
+
+	WARN_ON(container->tbl && !container->tbl->it_group);
+	tce_iommu_disable(container);
+
+	if (container->tbl && container->tbl->it_group)
+		tce_iommu_detach_group(iommu_data, container->tbl->it_group);
+
+	mutex_destroy(&container->lock);
+
+	kfree(container);
+}
+
+static long tce_iommu_ioctl(void *iommu_data,
+				 unsigned int cmd, unsigned long arg)
+{
+	struct tce_container *container = iommu_data;
+	unsigned long minsz;
+	long ret;
+
+	switch (cmd) {
+	case VFIO_CHECK_EXTENSION:
+		return (arg == VFIO_SPAPR_TCE_IOMMU) ? 1 : 0;
+
+	case VFIO_IOMMU_SPAPR_TCE_GET_INFO: {
+		struct vfio_iommu_spapr_tce_info info;
+		struct iommu_table *tbl = container->tbl;
+
+		if (WARN_ON(!tbl))
+			return -ENXIO;
+
+		minsz = offsetofend(struct vfio_iommu_spapr_tce_info,
+				dma32_window_size);
+
+		if (copy_from_user(&info, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (info.argsz < minsz)
+			return -EINVAL;
+
+		info.dma32_window_start = tbl->it_offset << IOMMU_PAGE_SHIFT;
+		info.dma32_window_size = tbl->it_size << IOMMU_PAGE_SHIFT;
+		info.flags = 0;
+
+		if (copy_to_user((void __user *)arg, &info, minsz))
+			return -EFAULT;
+
+		return 0;
+	}
+	case VFIO_IOMMU_MAP_DMA: {
+		struct vfio_iommu_type1_dma_map param;
+		struct iommu_table *tbl = container->tbl;
+		unsigned long tce, i;
+
+		if (!tbl)
+			return -ENXIO;
+
+		BUG_ON(!tbl->it_group);
+
+		minsz = offsetofend(struct vfio_iommu_type1_dma_map, size);
+
+		if (copy_from_user(&param, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (param.argsz < minsz)
+			return -EINVAL;
+
+		if (param.flags & ~(VFIO_DMA_MAP_FLAG_READ |
+				VFIO_DMA_MAP_FLAG_WRITE))
+			return -EINVAL;
+
+		if ((param.size & ~IOMMU_PAGE_MASK) ||
+				(param.vaddr & ~IOMMU_PAGE_MASK))
+			return -EINVAL;
+
+		/* iova is checked by the IOMMU API */
+		tce = param.vaddr;
+		if (param.flags & VFIO_DMA_MAP_FLAG_READ)
+			tce |= TCE_PCI_READ;
+		if (param.flags & VFIO_DMA_MAP_FLAG_WRITE)
+			tce |= TCE_PCI_WRITE;
+
+		ret = iommu_tce_put_param_check(tbl, param.iova, tce);
+		if (ret)
+			return ret;
+
+		for (i = 0; i < (param.size >> IOMMU_PAGE_SHIFT); ++i) {
+			ret = iommu_put_tce_user_mode(tbl,
+					(param.iova >> IOMMU_PAGE_SHIFT) + i,
+					tce);
+			if (ret)
+				break;
+			tce += IOMMU_PAGE_SIZE;
+		}
+		if (ret)
+			iommu_clear_tces_and_put_pages(tbl,
+					param.iova >> IOMMU_PAGE_SHIFT,	i);
+
+		iommu_flush_tce(tbl);
+
+		return ret;
+	}
+	case VFIO_IOMMU_UNMAP_DMA: {
+		struct vfio_iommu_type1_dma_unmap param;
+		struct iommu_table *tbl = container->tbl;
+
+		if (WARN_ON(!tbl))
+			return -ENXIO;
+
+		minsz = offsetofend(struct vfio_iommu_type1_dma_unmap,
+				size);
+
+		if (copy_from_user(&param, (void __user *)arg, minsz))
+			return -EFAULT;
+
+		if (param.argsz < minsz)
+			return -EINVAL;
+
+		/* No flag is supported now */
+		if (param.flags)
+			return -EINVAL;
+
+		if (param.size & ~IOMMU_PAGE_MASK)
+			return -EINVAL;
+
+		ret = iommu_tce_clear_param_check(tbl, param.iova, 0,
+				param.size >> IOMMU_PAGE_SHIFT);
+		if (ret)
+			return ret;
+
+		ret = iommu_clear_tces_and_put_pages(tbl,
+				param.iova >> IOMMU_PAGE_SHIFT,
+				param.size >> IOMMU_PAGE_SHIFT);
+		iommu_flush_tce(tbl);
+
+		return ret;
+	}
+	case VFIO_IOMMU_ENABLE:
+		mutex_lock(&container->lock);
+		ret = tce_iommu_enable(container);
+		mutex_unlock(&container->lock);
+		return ret;
+
+
+	case VFIO_IOMMU_DISABLE:
+		mutex_lock(&container->lock);
+		tce_iommu_disable(container);
+		mutex_unlock(&container->lock);
+		return 0;
+	}
+
+	return -ENOTTY;
+}
+
+static int tce_iommu_attach_group(void *iommu_data,
+		struct iommu_group *iommu_group)
+{
+	int ret;
+	struct tce_container *container = iommu_data;
+	struct iommu_table *tbl = iommu_group_get_iommudata(iommu_group);
+
+	BUG_ON(!tbl);
+	mutex_lock(&container->lock);
+
+	/* pr_debug("tce_vfio: Attaching group #%u to iommu %p\n",
+			iommu_group_id(iommu_group), iommu_group); */
+	if (container->tbl) {
+		pr_warn("tce_vfio: Only one group per IOMMU container is allowed, existing id=%d, attaching id=%d\n",
+				iommu_group_id(container->tbl->it_group),
+				iommu_group_id(iommu_group));
+		ret = -EBUSY;
+	} else if (container->enabled) {
+		pr_err("tce_vfio: attaching group #%u to enabled container\n",
+				iommu_group_id(iommu_group));
+		ret = -EBUSY;
+	} else {
+		ret = iommu_take_ownership(tbl);
+		if (!ret)
+			container->tbl = tbl;
+	}
+
+	mutex_unlock(&container->lock);
+
+	return ret;
+}
+
+static void tce_iommu_detach_group(void *iommu_data,
+		struct iommu_group *iommu_group)
+{
+	struct tce_container *container = iommu_data;
+	struct iommu_table *tbl = iommu_group_get_iommudata(iommu_group);
+
+	BUG_ON(!tbl);
+	mutex_lock(&container->lock);
+	if (tbl != container->tbl) {
+		pr_warn("tce_vfio: detaching group #%u, expected group is #%u\n",
+				iommu_group_id(iommu_group),
+				iommu_group_id(tbl->it_group));
+	} else {
+		if (container->enabled) {
+			pr_warn("tce_vfio: detaching group #%u from enabled container, forcing disable\n",
+					iommu_group_id(tbl->it_group));
+			tce_iommu_disable(container);
+		}
+
+		/* pr_debug("tce_vfio: detaching group #%u from iommu %p\n",
+				iommu_group_id(iommu_group), iommu_group); */
+		container->tbl = NULL;
+		iommu_release_ownership(tbl);
+	}
+	mutex_unlock(&container->lock);
+}
+
+const struct vfio_iommu_driver_ops tce_iommu_driver_ops = {
+	.name		= "iommu-vfio-powerpc",
+	.owner		= THIS_MODULE,
+	.open		= tce_iommu_open,
+	.release	= tce_iommu_release,
+	.ioctl		= tce_iommu_ioctl,
+	.attach_group	= tce_iommu_attach_group,
+	.detach_group	= tce_iommu_detach_group,
+};
+
+static int __init tce_iommu_init(void)
+{
+	return vfio_register_iommu_driver(&tce_iommu_driver_ops);
+}
+
+static void __exit tce_iommu_cleanup(void)
+{
+	vfio_unregister_iommu_driver(&tce_iommu_driver_ops);
+}
+
+module_init(tce_iommu_init);
+module_exit(tce_iommu_cleanup);
+
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 284ff24..87ee4f4 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -22,6 +22,7 @@
 /* Extensions */
 
 #define VFIO_TYPE1_IOMMU		1
+#define VFIO_SPAPR_TCE_IOMMU		2
 
 /*
  * The IOCTL interface is designed for extensibility by embedding the
@@ -375,4 +376,37 @@ struct vfio_iommu_type1_dma_unmap {
 
 #define VFIO_IOMMU_UNMAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 14)
 
+/*
+ * IOCTLs to enable/disable IOMMU container usage.
+ * No parameters are supported.
+ */
+#define VFIO_IOMMU_ENABLE	_IO(VFIO_TYPE, VFIO_BASE + 15)
+#define VFIO_IOMMU_DISABLE	_IO(VFIO_TYPE, VFIO_BASE + 16)
+
+/* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
+
+/*
+ * The SPAPR TCE info struct provides the information about the PCI bus
+ * address ranges available for DMA, these values are programmed into
+ * the hardware so the guest has to know that information.
+ *
+ * The DMA 32 bit window start is an absolute PCI bus address.
+ * The IOVA address passed via map/unmap ioctls are absolute PCI bus
+ * addresses too so the window works as a filter rather than an offset
+ * for IOVA addresses.
+ *
+ * A flag will need to be added if other page sizes are supported,
+ * so as defined here, it is always 4k.
+ */
+struct vfio_iommu_spapr_tce_info {
+	__u32 argsz;
+	__u32 flags;			/* reserved for future use */
+	__u32 dma32_window_start;	/* 32 bit window start (bytes) */
+	__u32 dma32_window_size;	/* 32 bit window size (bytes) */
+};
+
+#define VFIO_IOMMU_SPAPR_TCE_GET_INFO	_IO(VFIO_TYPE, VFIO_BASE + 12)
+
+/* ***************************************************************** */
+
 #endif /* _UAPIVFIO_H */
-- 
1.7.10.4

[PATCH 3/3] powerpc/vfio: Enable on pSeries platform

[Alexey Kardashevskiy]

The enables VFIO on the pSeries platform, enabling user space
programs to access PCI devices directly.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Cc: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/platforms/pseries/iommu.c |    4 ++++
 drivers/iommu/Kconfig                  |    2 +-
 drivers/vfio/Kconfig                   |    2 +-
 3 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 86ae364..23fc1dc 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -614,6 +614,7 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
 
 	iommu_table_setparms(pci->phb, dn, tbl);
 	pci->iommu_table = iommu_init_table(tbl, pci->phb->node);
+	iommu_register_group(tbl, pci_domain_nr(bus), 0);
 
 	/* Divide the rest (1.75GB) among the children */
 	pci->phb->dma_window_size = 0x80000000ul;
@@ -658,6 +659,7 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 				   ppci->phb->node);
 		iommu_table_setparms_lpar(ppci->phb, pdn, tbl, dma_window);
 		ppci->iommu_table = iommu_init_table(tbl, ppci->phb->node);
+		iommu_register_group(tbl, pci_domain_nr(bus), 0);
 		pr_debug("  created table: %p\n", ppci->iommu_table);
 	}
 }
@@ -684,6 +686,7 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
 				   phb->node);
 		iommu_table_setparms(phb, dn, tbl);
 		PCI_DN(dn)->iommu_table = iommu_init_table(tbl, phb->node);
+		iommu_register_group(tbl, pci_domain_nr(phb->bus), 0);
 		set_iommu_table_base(&dev->dev, PCI_DN(dn)->iommu_table);
 		return;
 	}
@@ -1184,6 +1187,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 				   pci->phb->node);
 		iommu_table_setparms_lpar(pci->phb, pdn, tbl, dma_window);
 		pci->iommu_table = iommu_init_table(tbl, pci->phb->node);
+		iommu_register_group(tbl, pci_domain_nr(pci->phb->bus), 0);
 		pr_debug("  created table: %p\n", pci->iommu_table);
 	} else {
 		pr_debug("  found DMA window, table: %p\n", pci->iommu_table);
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 3f3abde..01730b2 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -263,7 +263,7 @@ config SHMOBILE_IOMMU_L1SIZE
 
 config SPAPR_TCE_IOMMU
 	bool "sPAPR TCE IOMMU Support"
-	depends on PPC_POWERNV
+	depends on PPC_POWERNV || PPC_PSERIES
 	select IOMMU_API
 	help
 	  Enables bits of IOMMU API required by VFIO. The iommu_ops
diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
index b464687..26b3d9d 100644
--- a/drivers/vfio/Kconfig
+++ b/drivers/vfio/Kconfig
@@ -12,7 +12,7 @@ menuconfig VFIO
 	tristate "VFIO Non-Privileged userspace driver framework"
 	depends on IOMMU_API
 	select VFIO_IOMMU_TYPE1 if X86
-	select VFIO_IOMMU_SPAPR_TCE if PPC_POWERNV
+	select VFIO_IOMMU_SPAPR_TCE if (PPC_POWERNV || PPC_PSERIES)
 	help
 	  VFIO provides a framework for secure userspace device drivers.
 	  See Documentation/vfio.txt for more details.
-- 
1.7.10.4

Re: [PATCH 0/5 v2] VFIO PPC64: add VFIO support on POWERPC64

[Alexey Kardashevskiy]

Oops, wrong subject (cut-n-paste) :)
There are 3 patches, not 5.


On 05/21/2013 01:33 PM, Alexey Kardashevskiy wrote:
> The series adds support for VFIO on POWERPC in user space (such as QEMU).
> The in-kernel real mode IOMMU support is added by another series posted
> separately.
> 
> As the first and main aim of this series is the POWERNV platform support,
> the "Enable on POWERNV platform" patch goes first and introduces an API
> to be used by the VFIO IOMMU driver. The "Enable on pSeries platform" patch
> simply registers PHBs in the IOMMU subsystem and expects the API to be present,
> it enables VFIO support in fully emulated QEMU guests.
> 
> The main change is that this series was changed and tested against v3.10-rc1.
> It also contains some bugfixes which are mentioned (if any) in the patch messages.
> 
> Alexey Kardashevskiy (3):
>   powerpc/vfio: Enable on POWERNV platform
>   powerpc/vfio: Implement IOMMU driver for VFIO
>   powerpc/vfio: Enable on pSeries platform


-- 
Alexey

Re: [PATCH 0/5 v2] VFIO PPC64: add VFIO support on POWERPC64

[Alex Williamson]

On Tue, 2013-05-21 at 13:33 +1000, Alexey Kardashevskiy wrote:
> The series adds support for VFIO on POWERPC in user space (such as QEMU).
> The in-kernel real mode IOMMU support is added by another series posted
> separately.
> 
> As the first and main aim of this series is the POWERNV platform support,
> the "Enable on POWERNV platform" patch goes first and introduces an API
> to be used by the VFIO IOMMU driver. The "Enable on pSeries platform" patch
> simply registers PHBs in the IOMMU subsystem and expects the API to be present,
> it enables VFIO support in fully emulated QEMU guests.
> 
> The main change is that this series was changed and tested against v3.10-rc1.
> It also contains some bugfixes which are mentioned (if any) in the patch messages.
> 
> Alexey Kardashevskiy (3):
>   powerpc/vfio: Enable on POWERNV platform
>   powerpc/vfio: Implement IOMMU driver for VFIO
>   powerpc/vfio: Enable on pSeries platform
> 
>  Documentation/vfio.txt                      |   63 +++++
>  arch/powerpc/include/asm/iommu.h            |   26 ++
>  arch/powerpc/kernel/iommu.c                 |  323 +++++++++++++++++++++++
>  arch/powerpc/platforms/powernv/pci-ioda.c   |    1 +
>  arch/powerpc/platforms/powernv/pci-p5ioc2.c |    5 +-
>  arch/powerpc/platforms/powernv/pci.c        |    2 +
>  arch/powerpc/platforms/pseries/iommu.c      |    4 +
>  drivers/iommu/Kconfig                       |    8 +
>  drivers/vfio/Kconfig                        |    6 +
>  drivers/vfio/Makefile                       |    1 +
>  drivers/vfio/vfio.c                         |    1 +
>  drivers/vfio/vfio_iommu_spapr_tce.c         |  377 +++++++++++++++++++++++++++
>  include/uapi/linux/vfio.h                   |   34 +++
>  13 files changed, 850 insertions(+), 1 deletion(-)
>  create mode 100644 drivers/vfio/vfio_iommu_spapr_tce.c
> 

These look ok to me, how do you want to integrate them?  Should I
provide Acks on patches 2 & 3 and let them get pushed through the ppc
tree or should I wait for patch 1 then push 2 & 3 through my tree?
Thanks,

Alex

Re: [PATCH 0/5 v2] VFIO PPC64: add VFIO support on POWERPC64

[Alexey Kardashevskiy]

On 05/24/2013 12:56 AM, Alex Williamson wrote:
> On Tue, 2013-05-21 at 13:33 +1000, Alexey Kardashevskiy wrote:
>> The series adds support for VFIO on POWERPC in user space (such as QEMU).
>> The in-kernel real mode IOMMU support is added by another series posted
>> separately.
>>
>> As the first and main aim of this series is the POWERNV platform support,
>> the "Enable on POWERNV platform" patch goes first and introduces an API
>> to be used by the VFIO IOMMU driver. The "Enable on pSeries platform" patch
>> simply registers PHBs in the IOMMU subsystem and expects the API to be present,
>> it enables VFIO support in fully emulated QEMU guests.
>>
>> The main change is that this series was changed and tested against v3.10-rc1.
>> It also contains some bugfixes which are mentioned (if any) in the patch messages.
>>
>> Alexey Kardashevskiy (3):
>>   powerpc/vfio: Enable on POWERNV platform
>>   powerpc/vfio: Implement IOMMU driver for VFIO
>>   powerpc/vfio: Enable on pSeries platform
>>
>>  Documentation/vfio.txt                      |   63 +++++
>>  arch/powerpc/include/asm/iommu.h            |   26 ++
>>  arch/powerpc/kernel/iommu.c                 |  323 +++++++++++++++++++++++
>>  arch/powerpc/platforms/powernv/pci-ioda.c   |    1 +
>>  arch/powerpc/platforms/powernv/pci-p5ioc2.c |    5 +-
>>  arch/powerpc/platforms/powernv/pci.c        |    2 +
>>  arch/powerpc/platforms/pseries/iommu.c      |    4 +
>>  drivers/iommu/Kconfig                       |    8 +
>>  drivers/vfio/Kconfig                        |    6 +
>>  drivers/vfio/Makefile                       |    1 +
>>  drivers/vfio/vfio.c                         |    1 +
>>  drivers/vfio/vfio_iommu_spapr_tce.c         |  377 +++++++++++++++++++++++++++
>>  include/uapi/linux/vfio.h                   |   34 +++
>>  13 files changed, 850 insertions(+), 1 deletion(-)
>>  create mode 100644 drivers/vfio/vfio_iommu_spapr_tce.c
>>
> 
> These look ok to me, how do you want to integrate them?  Should I
> provide Acks on patches 2 & 3 and let them get pushed through the ppc
> tree or should I wait for patch 1 then push 2 & 3 through my tree?

Please ack on 2 & 3 and Ben will merge all three into his tree. Thanks!



-- 
Alexey

Re: [PATCH 2/3] powerpc/vfio: Implement IOMMU driver for VFIO

[Alex Williamson]

On Tue, 2013-05-21 at 13:33 +1000, Alexey Kardashevskiy wrote:
> VFIO implements platform independent stuff such as
> a PCI driver, BAR access (via read/write on a file descriptor
> or direct mapping when possible) and IRQ signaling.
> 
> The platform dependent part includes IOMMU initialization
> and handling.  This implements an IOMMU driver for VFIO
> which does mapping/unmapping pages for the guest IO and
> provides information about DMA window (required by a POWER
> guest).
> 
> Cc: David Gibson <david@gibson.dropbear.id.au>
> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
> Signed-off-by: Paul Mackerras <paulus@samba.org>

Acked-by: Alex Williamson <alex.williamson@redhat.com>

> ---
>  Documentation/vfio.txt              |   63 ++++++
>  drivers/vfio/Kconfig                |    6 +
>  drivers/vfio/Makefile               |    1 +
>  drivers/vfio/vfio.c                 |    1 +
>  drivers/vfio/vfio_iommu_spapr_tce.c |  377 +++++++++++++++++++++++++++++++++++
>  include/uapi/linux/vfio.h           |   34 ++++
>  6 files changed, 482 insertions(+)
>  create mode 100644 drivers/vfio/vfio_iommu_spapr_tce.c
> 
> diff --git a/Documentation/vfio.txt b/Documentation/vfio.txt
> index 8eda363..c55533c 100644
> --- a/Documentation/vfio.txt
> +++ b/Documentation/vfio.txt
> @@ -283,6 +283,69 @@ a direct pass through for VFIO_DEVICE_* ioctls.  The read/write/mmap
>  interfaces implement the device region access defined by the device's
>  own VFIO_DEVICE_GET_REGION_INFO ioctl.
>  
> +
> +PPC64 sPAPR implementation note
> +-------------------------------------------------------------------------------
> +
> +This implementation has some specifics:
> +
> +1) Only one IOMMU group per container is supported as an IOMMU group
> +represents the minimal entity which isolation can be guaranteed for and
> +groups are allocated statically, one per a Partitionable Endpoint (PE)
> +(PE is often a PCI domain but not always).
> +
> +2) The hardware supports so called DMA windows - the PCI address range
> +within which DMA transfer is allowed, any attempt to access address space
> +out of the window leads to the whole PE isolation.
> +
> +3) PPC64 guests are paravirtualized but not fully emulated. There is an API
> +to map/unmap pages for DMA, and it normally maps 1..32 pages per call and
> +currently there is no way to reduce the number of calls. In order to make things
> +faster, the map/unmap handling has been implemented in real mode which provides
> +an excellent performance which has limitations such as inability to do
> +locked pages accounting in real time.
> +
> +So 3 additional ioctls have been added:
> +
> +	VFIO_IOMMU_SPAPR_TCE_GET_INFO - returns the size and the start
> +		of the DMA window on the PCI bus.
> +
> +	VFIO_IOMMU_ENABLE - enables the container. The locked pages accounting
> +		is done at this point. This lets user first to know what
> +		the DMA window is and adjust rlimit before doing any real job.
> +
> +	VFIO_IOMMU_DISABLE - disables the container.
> +
> +
> +The code flow from the example above should be slightly changed:
> +
> +	.....
> +	/* Add the group to the container */
> +	ioctl(group, VFIO_GROUP_SET_CONTAINER, &container);
> +
> +	/* Enable the IOMMU model we want */
> +	ioctl(container, VFIO_SET_IOMMU, VFIO_SPAPR_TCE_IOMMU)
> +
> +	/* Get addition sPAPR IOMMU info */
> +	vfio_iommu_spapr_tce_info spapr_iommu_info;
> +	ioctl(container, VFIO_IOMMU_SPAPR_TCE_GET_INFO, &spapr_iommu_info);
> +
> +	if (ioctl(container, VFIO_IOMMU_ENABLE))
> +		/* Cannot enable container, may be low rlimit */
> +
> +	/* Allocate some space and setup a DMA mapping */
> +	dma_map.vaddr = mmap(0, 1024 * 1024, PROT_READ | PROT_WRITE,
> +			     MAP_PRIVATE | MAP_ANONYMOUS, 0, 0);
> +
> +	dma_map.size = 1024 * 1024;
> +	dma_map.iova = 0; /* 1MB starting at 0x0 from device view */
> +	dma_map.flags = VFIO_DMA_MAP_FLAG_READ | VFIO_DMA_MAP_FLAG_WRITE;
> +
> +	/* Check here is .iova/.size are within DMA window from spapr_iommu_info */
> +
> +	ioctl(container, VFIO_IOMMU_MAP_DMA, &dma_map);
> +	.....
> +
>  -------------------------------------------------------------------------------
>  
>  [1] VFIO was originally an acronym for "Virtual Function I/O" in its
> diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
> index 7cd5dec..b464687 100644
> --- a/drivers/vfio/Kconfig
> +++ b/drivers/vfio/Kconfig
> @@ -3,10 +3,16 @@ config VFIO_IOMMU_TYPE1
>  	depends on VFIO
>  	default n
>  
> +config VFIO_IOMMU_SPAPR_TCE
> +	tristate
> +	depends on VFIO && SPAPR_TCE_IOMMU
> +	default n
> +
>  menuconfig VFIO
>  	tristate "VFIO Non-Privileged userspace driver framework"
>  	depends on IOMMU_API
>  	select VFIO_IOMMU_TYPE1 if X86
> +	select VFIO_IOMMU_SPAPR_TCE if PPC_POWERNV
>  	help
>  	  VFIO provides a framework for secure userspace device drivers.
>  	  See Documentation/vfio.txt for more details.
> diff --git a/drivers/vfio/Makefile b/drivers/vfio/Makefile
> index 2398d4a..72bfabc 100644
> --- a/drivers/vfio/Makefile
> +++ b/drivers/vfio/Makefile
> @@ -1,3 +1,4 @@
>  obj-$(CONFIG_VFIO) += vfio.o
>  obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o
> +obj-$(CONFIG_VFIO_IOMMU_SPAPR_TCE) += vfio_iommu_spapr_tce.o
>  obj-$(CONFIG_VFIO_PCI) += pci/
> diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
> index 295c48f..a819604 100644
> --- a/drivers/vfio/vfio.c
> +++ b/drivers/vfio/vfio.c
> @@ -1428,6 +1428,7 @@ static int __init vfio_init(void)
>  	 * drivers.
>  	 */
>  	request_module_nowait("vfio_iommu_type1");
> +	request_module_nowait("vfio_iommu_spapr_tce");
>  
>  	return 0;
>  
> diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
> new file mode 100644
> index 0000000..bdae7a0
> --- /dev/null
> +++ b/drivers/vfio/vfio_iommu_spapr_tce.c
> @@ -0,0 +1,377 @@
> +/*
> + * VFIO: IOMMU DMA mapping support for TCE on POWER
> + *
> + * Copyright (C) 2013 IBM Corp.  All rights reserved.
> + *     Author: Alexey Kardashevskiy <aik@ozlabs.ru>
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License version 2 as
> + * published by the Free Software Foundation.
> + *
> + * Derived from original vfio_iommu_type1.c:
> + * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
> + *     Author: Alex Williamson <alex.williamson@redhat.com>
> + */
> +
> +#include <linux/module.h>
> +#include <linux/pci.h>
> +#include <linux/slab.h>
> +#include <linux/uaccess.h>
> +#include <linux/err.h>
> +#include <linux/vfio.h>
> +#include <asm/iommu.h>
> +#include <asm/tce.h>
> +
> +#define DRIVER_VERSION  "0.1"
> +#define DRIVER_AUTHOR   "aik@ozlabs.ru"
> +#define DRIVER_DESC     "VFIO IOMMU SPAPR TCE"
> +
> +static void tce_iommu_detach_group(void *iommu_data,
> +		struct iommu_group *iommu_group);
> +
> +/*
> + * VFIO IOMMU fd for SPAPR_TCE IOMMU implementation
> + *
> + * This code handles mapping and unmapping of user data buffers
> + * into DMA'ble space using the IOMMU
> + */
> +
> +/*
> + * The container descriptor supports only a single group per container.
> + * Required by the API as the container is not supplied with the IOMMU group
> + * at the moment of initialization.
> + */
> +struct tce_container {
> +	struct mutex lock;
> +	struct iommu_table *tbl;
> +	bool enabled;
> +};
> +
> +static int tce_iommu_enable(struct tce_container *container)
> +{
> +	int ret = 0;
> +	unsigned long locked, lock_limit, npages;
> +	struct iommu_table *tbl = container->tbl;
> +
> +	if (!container->tbl)
> +		return -ENXIO;
> +
> +	if (!current->mm)
> +		return -ESRCH; /* process exited */
> +
> +	if (container->enabled)
> +		return -EBUSY;
> +
> +	/*
> +	 * When userspace pages are mapped into the IOMMU, they are effectively
> +	 * locked memory, so, theoretically, we need to update the accounting
> +	 * of locked pages on each map and unmap.  For powerpc, the map unmap
> +	 * paths can be very hot, though, and the accounting would kill
> +	 * performance, especially since it would be difficult to impossible
> +	 * to handle the accounting in real mode only.
> +	 *
> +	 * To address that, rather than precisely accounting every page, we
> +	 * instead account for a worst case on locked memory when the iommu is
> +	 * enabled and disabled.  The worst case upper bound on locked memory
> +	 * is the size of the whole iommu window, which is usually relatively
> +	 * small (compared to total memory sizes) on POWER hardware.
> +	 *
> +	 * Also we don't have a nice way to fail on H_PUT_TCE due to ulimits,
> +	 * that would effectively kill the guest at random points, much better
> +	 * enforcing the limit based on the max that the guest can map.
> +	 */
> +	down_write(&current->mm->mmap_sem);
> +	npages = (tbl->it_size << IOMMU_PAGE_SHIFT) >> PAGE_SHIFT;
> +	locked = current->mm->locked_vm + npages;
> +	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
> +	if (locked > lock_limit && !capable(CAP_IPC_LOCK)) {
> +		pr_warn("RLIMIT_MEMLOCK (%ld) exceeded\n",
> +				rlimit(RLIMIT_MEMLOCK));
> +		ret = -ENOMEM;
> +	} else {
> +
> +		current->mm->locked_vm += npages;
> +		container->enabled = true;
> +	}
> +	up_write(&current->mm->mmap_sem);
> +
> +	return ret;
> +}
> +
> +static void tce_iommu_disable(struct tce_container *container)
> +{
> +	if (!container->enabled)
> +		return;
> +
> +	container->enabled = false;
> +
> +	if (!container->tbl || !current->mm)
> +		return;
> +
> +	down_write(&current->mm->mmap_sem);
> +	current->mm->locked_vm -= (container->tbl->it_size <<
> +			IOMMU_PAGE_SHIFT) >> PAGE_SHIFT;
> +	up_write(&current->mm->mmap_sem);
> +}
> +
> +static void *tce_iommu_open(unsigned long arg)
> +{
> +	struct tce_container *container;
> +
> +	if (arg != VFIO_SPAPR_TCE_IOMMU) {
> +		pr_err("tce_vfio: Wrong IOMMU type\n");
> +		return ERR_PTR(-EINVAL);
> +	}
> +
> +	container = kzalloc(sizeof(*container), GFP_KERNEL);
> +	if (!container)
> +		return ERR_PTR(-ENOMEM);
> +
> +	mutex_init(&container->lock);
> +
> +	return container;
> +}
> +
> +static void tce_iommu_release(void *iommu_data)
> +{
> +	struct tce_container *container = iommu_data;
> +
> +	WARN_ON(container->tbl && !container->tbl->it_group);
> +	tce_iommu_disable(container);
> +
> +	if (container->tbl && container->tbl->it_group)
> +		tce_iommu_detach_group(iommu_data, container->tbl->it_group);
> +
> +	mutex_destroy(&container->lock);
> +
> +	kfree(container);
> +}
> +
> +static long tce_iommu_ioctl(void *iommu_data,
> +				 unsigned int cmd, unsigned long arg)
> +{
> +	struct tce_container *container = iommu_data;
> +	unsigned long minsz;
> +	long ret;
> +
> +	switch (cmd) {
> +	case VFIO_CHECK_EXTENSION:
> +		return (arg == VFIO_SPAPR_TCE_IOMMU) ? 1 : 0;
> +
> +	case VFIO_IOMMU_SPAPR_TCE_GET_INFO: {
> +		struct vfio_iommu_spapr_tce_info info;
> +		struct iommu_table *tbl = container->tbl;
> +
> +		if (WARN_ON(!tbl))
> +			return -ENXIO;
> +
> +		minsz = offsetofend(struct vfio_iommu_spapr_tce_info,
> +				dma32_window_size);
> +
> +		if (copy_from_user(&info, (void __user *)arg, minsz))
> +			return -EFAULT;
> +
> +		if (info.argsz < minsz)
> +			return -EINVAL;
> +
> +		info.dma32_window_start = tbl->it_offset << IOMMU_PAGE_SHIFT;
> +		info.dma32_window_size = tbl->it_size << IOMMU_PAGE_SHIFT;
> +		info.flags = 0;
> +
> +		if (copy_to_user((void __user *)arg, &info, minsz))
> +			return -EFAULT;
> +
> +		return 0;
> +	}
> +	case VFIO_IOMMU_MAP_DMA: {
> +		struct vfio_iommu_type1_dma_map param;
> +		struct iommu_table *tbl = container->tbl;
> +		unsigned long tce, i;
> +
> +		if (!tbl)
> +			return -ENXIO;
> +
> +		BUG_ON(!tbl->it_group);
> +
> +		minsz = offsetofend(struct vfio_iommu_type1_dma_map, size);
> +
> +		if (copy_from_user(&param, (void __user *)arg, minsz))
> +			return -EFAULT;
> +
> +		if (param.argsz < minsz)
> +			return -EINVAL;
> +
> +		if (param.flags & ~(VFIO_DMA_MAP_FLAG_READ |
> +				VFIO_DMA_MAP_FLAG_WRITE))
> +			return -EINVAL;
> +
> +		if ((param.size & ~IOMMU_PAGE_MASK) ||
> +				(param.vaddr & ~IOMMU_PAGE_MASK))
> +			return -EINVAL;
> +
> +		/* iova is checked by the IOMMU API */
> +		tce = param.vaddr;
> +		if (param.flags & VFIO_DMA_MAP_FLAG_READ)
> +			tce |= TCE_PCI_READ;
> +		if (param.flags & VFIO_DMA_MAP_FLAG_WRITE)
> +			tce |= TCE_PCI_WRITE;
> +
> +		ret = iommu_tce_put_param_check(tbl, param.iova, tce);
> +		if (ret)
> +			return ret;
> +
> +		for (i = 0; i < (param.size >> IOMMU_PAGE_SHIFT); ++i) {
> +			ret = iommu_put_tce_user_mode(tbl,
> +					(param.iova >> IOMMU_PAGE_SHIFT) + i,
> +					tce);
> +			if (ret)
> +				break;
> +			tce += IOMMU_PAGE_SIZE;
> +		}
> +		if (ret)
> +			iommu_clear_tces_and_put_pages(tbl,
> +					param.iova >> IOMMU_PAGE_SHIFT,	i);
> +
> +		iommu_flush_tce(tbl);
> +
> +		return ret;
> +	}
> +	case VFIO_IOMMU_UNMAP_DMA: {
> +		struct vfio_iommu_type1_dma_unmap param;
> +		struct iommu_table *tbl = container->tbl;
> +
> +		if (WARN_ON(!tbl))
> +			return -ENXIO;
> +
> +		minsz = offsetofend(struct vfio_iommu_type1_dma_unmap,
> +				size);
> +
> +		if (copy_from_user(&param, (void __user *)arg, minsz))
> +			return -EFAULT;
> +
> +		if (param.argsz < minsz)
> +			return -EINVAL;
> +
> +		/* No flag is supported now */
> +		if (param.flags)
> +			return -EINVAL;
> +
> +		if (param.size & ~IOMMU_PAGE_MASK)
> +			return -EINVAL;
> +
> +		ret = iommu_tce_clear_param_check(tbl, param.iova, 0,
> +				param.size >> IOMMU_PAGE_SHIFT);
> +		if (ret)
> +			return ret;
> +
> +		ret = iommu_clear_tces_and_put_pages(tbl,
> +				param.iova >> IOMMU_PAGE_SHIFT,
> +				param.size >> IOMMU_PAGE_SHIFT);
> +		iommu_flush_tce(tbl);
> +
> +		return ret;
> +	}
> +	case VFIO_IOMMU_ENABLE:
> +		mutex_lock(&container->lock);
> +		ret = tce_iommu_enable(container);
> +		mutex_unlock(&container->lock);
> +		return ret;
> +
> +
> +	case VFIO_IOMMU_DISABLE:
> +		mutex_lock(&container->lock);
> +		tce_iommu_disable(container);
> +		mutex_unlock(&container->lock);
> +		return 0;
> +	}
> +
> +	return -ENOTTY;
> +}
> +
> +static int tce_iommu_attach_group(void *iommu_data,
> +		struct iommu_group *iommu_group)
> +{
> +	int ret;
> +	struct tce_container *container = iommu_data;
> +	struct iommu_table *tbl = iommu_group_get_iommudata(iommu_group);
> +
> +	BUG_ON(!tbl);
> +	mutex_lock(&container->lock);
> +
> +	/* pr_debug("tce_vfio: Attaching group #%u to iommu %p\n",
> +			iommu_group_id(iommu_group), iommu_group); */
> +	if (container->tbl) {
> +		pr_warn("tce_vfio: Only one group per IOMMU container is allowed, existing id=%d, attaching id=%d\n",
> +				iommu_group_id(container->tbl->it_group),
> +				iommu_group_id(iommu_group));
> +		ret = -EBUSY;
> +	} else if (container->enabled) {
> +		pr_err("tce_vfio: attaching group #%u to enabled container\n",
> +				iommu_group_id(iommu_group));
> +		ret = -EBUSY;
> +	} else {
> +		ret = iommu_take_ownership(tbl);
> +		if (!ret)
> +			container->tbl = tbl;
> +	}
> +
> +	mutex_unlock(&container->lock);
> +
> +	return ret;
> +}
> +
> +static void tce_iommu_detach_group(void *iommu_data,
> +		struct iommu_group *iommu_group)
> +{
> +	struct tce_container *container = iommu_data;
> +	struct iommu_table *tbl = iommu_group_get_iommudata(iommu_group);
> +
> +	BUG_ON(!tbl);
> +	mutex_lock(&container->lock);
> +	if (tbl != container->tbl) {
> +		pr_warn("tce_vfio: detaching group #%u, expected group is #%u\n",
> +				iommu_group_id(iommu_group),
> +				iommu_group_id(tbl->it_group));
> +	} else {
> +		if (container->enabled) {
> +			pr_warn("tce_vfio: detaching group #%u from enabled container, forcing disable\n",
> +					iommu_group_id(tbl->it_group));
> +			tce_iommu_disable(container);
> +		}
> +
> +		/* pr_debug("tce_vfio: detaching group #%u from iommu %p\n",
> +				iommu_group_id(iommu_group), iommu_group); */
> +		container->tbl = NULL;
> +		iommu_release_ownership(tbl);
> +	}
> +	mutex_unlock(&container->lock);
> +}
> +
> +const struct vfio_iommu_driver_ops tce_iommu_driver_ops = {
> +	.name		= "iommu-vfio-powerpc",
> +	.owner		= THIS_MODULE,
> +	.open		= tce_iommu_open,
> +	.release	= tce_iommu_release,
> +	.ioctl		= tce_iommu_ioctl,
> +	.attach_group	= tce_iommu_attach_group,
> +	.detach_group	= tce_iommu_detach_group,
> +};
> +
> +static int __init tce_iommu_init(void)
> +{
> +	return vfio_register_iommu_driver(&tce_iommu_driver_ops);
> +}
> +
> +static void __exit tce_iommu_cleanup(void)
> +{
> +	vfio_unregister_iommu_driver(&tce_iommu_driver_ops);
> +}
> +
> +module_init(tce_iommu_init);
> +module_exit(tce_iommu_cleanup);
> +
> +MODULE_VERSION(DRIVER_VERSION);
> +MODULE_LICENSE("GPL v2");
> +MODULE_AUTHOR(DRIVER_AUTHOR);
> +MODULE_DESCRIPTION(DRIVER_DESC);
> +
> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
> index 284ff24..87ee4f4 100644
> --- a/include/uapi/linux/vfio.h
> +++ b/include/uapi/linux/vfio.h
> @@ -22,6 +22,7 @@
>  /* Extensions */
>  
>  #define VFIO_TYPE1_IOMMU		1
> +#define VFIO_SPAPR_TCE_IOMMU		2
>  
>  /*
>   * The IOCTL interface is designed for extensibility by embedding the
> @@ -375,4 +376,37 @@ struct vfio_iommu_type1_dma_unmap {
>  
>  #define VFIO_IOMMU_UNMAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 14)
>  
> +/*
> + * IOCTLs to enable/disable IOMMU container usage.
> + * No parameters are supported.
> + */
> +#define VFIO_IOMMU_ENABLE	_IO(VFIO_TYPE, VFIO_BASE + 15)
> +#define VFIO_IOMMU_DISABLE	_IO(VFIO_TYPE, VFIO_BASE + 16)
> +
> +/* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
> +
> +/*
> + * The SPAPR TCE info struct provides the information about the PCI bus
> + * address ranges available for DMA, these values are programmed into
> + * the hardware so the guest has to know that information.
> + *
> + * The DMA 32 bit window start is an absolute PCI bus address.
> + * The IOVA address passed via map/unmap ioctls are absolute PCI bus
> + * addresses too so the window works as a filter rather than an offset
> + * for IOVA addresses.
> + *
> + * A flag will need to be added if other page sizes are supported,
> + * so as defined here, it is always 4k.
> + */
> +struct vfio_iommu_spapr_tce_info {
> +	__u32 argsz;
> +	__u32 flags;			/* reserved for future use */
> +	__u32 dma32_window_start;	/* 32 bit window start (bytes) */
> +	__u32 dma32_window_size;	/* 32 bit window size (bytes) */
> +};
> +
> +#define VFIO_IOMMU_SPAPR_TCE_GET_INFO	_IO(VFIO_TYPE, VFIO_BASE + 12)
> +
> +/* ***************************************************************** */
> +
>  #endif /* _UAPIVFIO_H */

Re: [PATCH 3/3] powerpc/vfio: Enable on pSeries platform

[Alex Williamson]

On Tue, 2013-05-21 at 13:33 +1000, Alexey Kardashevskiy wrote:
> The enables VFIO on the pSeries platform, enabling user space
> programs to access PCI devices directly.
> 
> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
> Cc: David Gibson <david@gibson.dropbear.id.au>
> Signed-off-by: Paul Mackerras <paulus@samba.org>

Acked-by: Alex Williamson <alex.williamson@redhat.com>

> ---
>  arch/powerpc/platforms/pseries/iommu.c |    4 ++++
>  drivers/iommu/Kconfig                  |    2 +-
>  drivers/vfio/Kconfig                   |    2 +-
>  3 files changed, 6 insertions(+), 2 deletions(-)
> 
> diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
> index 86ae364..23fc1dc 100644
> --- a/arch/powerpc/platforms/pseries/iommu.c
> +++ b/arch/powerpc/platforms/pseries/iommu.c
> @@ -614,6 +614,7 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
>  
>  	iommu_table_setparms(pci->phb, dn, tbl);
>  	pci->iommu_table = iommu_init_table(tbl, pci->phb->node);
> +	iommu_register_group(tbl, pci_domain_nr(bus), 0);
>  
>  	/* Divide the rest (1.75GB) among the children */
>  	pci->phb->dma_window_size = 0x80000000ul;
> @@ -658,6 +659,7 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
>  				   ppci->phb->node);
>  		iommu_table_setparms_lpar(ppci->phb, pdn, tbl, dma_window);
>  		ppci->iommu_table = iommu_init_table(tbl, ppci->phb->node);
> +		iommu_register_group(tbl, pci_domain_nr(bus), 0);
>  		pr_debug("  created table: %p\n", ppci->iommu_table);
>  	}
>  }
> @@ -684,6 +686,7 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
>  				   phb->node);
>  		iommu_table_setparms(phb, dn, tbl);
>  		PCI_DN(dn)->iommu_table = iommu_init_table(tbl, phb->node);
> +		iommu_register_group(tbl, pci_domain_nr(phb->bus), 0);
>  		set_iommu_table_base(&dev->dev, PCI_DN(dn)->iommu_table);
>  		return;
>  	}
> @@ -1184,6 +1187,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
>  				   pci->phb->node);
>  		iommu_table_setparms_lpar(pci->phb, pdn, tbl, dma_window);
>  		pci->iommu_table = iommu_init_table(tbl, pci->phb->node);
> +		iommu_register_group(tbl, pci_domain_nr(pci->phb->bus), 0);
>  		pr_debug("  created table: %p\n", pci->iommu_table);
>  	} else {
>  		pr_debug("  found DMA window, table: %p\n", pci->iommu_table);
> diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
> index 3f3abde..01730b2 100644
> --- a/drivers/iommu/Kconfig
> +++ b/drivers/iommu/Kconfig
> @@ -263,7 +263,7 @@ config SHMOBILE_IOMMU_L1SIZE
>  
>  config SPAPR_TCE_IOMMU
>  	bool "sPAPR TCE IOMMU Support"
> -	depends on PPC_POWERNV
> +	depends on PPC_POWERNV || PPC_PSERIES
>  	select IOMMU_API
>  	help
>  	  Enables bits of IOMMU API required by VFIO. The iommu_ops
> diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
> index b464687..26b3d9d 100644
> --- a/drivers/vfio/Kconfig
> +++ b/drivers/vfio/Kconfig
> @@ -12,7 +12,7 @@ menuconfig VFIO
>  	tristate "VFIO Non-Privileged userspace driver framework"
>  	depends on IOMMU_API
>  	select VFIO_IOMMU_TYPE1 if X86
> -	select VFIO_IOMMU_SPAPR_TCE if PPC_POWERNV
> +	select VFIO_IOMMU_SPAPR_TCE if (PPC_POWERNV || PPC_PSERIES)
>  	help
>  	  VFIO provides a framework for secure userspace device drivers.
>  	  See Documentation/vfio.txt for more details.

Re: [1/3] powerpc/vfio: Enable on POWERNV platform

[Scott Wood]

On Tue, May 21, 2013 at 01:33:09PM +1000, Alexey Kardashevskiy wrote:
> +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;
> +	}
[snip]
> +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);

This is missing a check to see whether the appropriate hardware is
present.  This file should also be renamed to something less generic, and
depend on a kconfig symbol more specific than CONFIG_PPC64.

When this is combined with CONFIG_FSL_PAMU on hardware with a PAMU, I get
a bunch of those "WARN_ON(dev->iommu_group)" dumps because PAMU already
got to them.  Presumably without PAMU it silently (or with just pr_debug)
bails out at some other point.

-Scott

Re: [1/3] powerpc/vfio: Enable on POWERNV platform

[Alexey Kardashevskiy]

On 12/13/2013 10:35 AM, Scott Wood wrote:
> On Tue, May 21, 2013 at 01:33:09PM +1000, Alexey Kardashevskiy wrote:
>> +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;
>> +	}
> [snip]
>> +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);
> 
> This is missing a check to see whether the appropriate hardware is
> present.  This file should also be renamed to something less generic, and
> depend on a kconfig symbol more specific than CONFIG_PPC64.
> 
> When this is combined with CONFIG_FSL_PAMU on hardware with a PAMU, I get
> a bunch of those "WARN_ON(dev->iommu_group)" dumps because PAMU already
> got to them.  Presumably without PAMU it silently (or with just pr_debug)
> bails out at some other point.


I posted (yet again) yesterday "[PATCH v11] PPC: POWERNV: move
iommu_add_device earlier" which should fix this. And Bharat asked many
times for this to get accepted :)



-- 
Alexey

Re: [1/3] powerpc/vfio: Enable on POWERNV platform

[Scott Wood]

On Fri, 2013-12-13 at 14:02 +1100, Alexey Kardashevskiy wrote:
> On 12/13/2013 10:35 AM, Scott Wood wrote:
> > On Tue, May 21, 2013 at 01:33:09PM +1000, Alexey Kardashevskiy wrote:
> >> +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;
> >> +	}
> > [snip]
> >> +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);
> > 
> > This is missing a check to see whether the appropriate hardware is
> > present.  This file should also be renamed to something less generic, and
> > depend on a kconfig symbol more specific than CONFIG_PPC64.
> > 
> > When this is combined with CONFIG_FSL_PAMU on hardware with a PAMU, I get
> > a bunch of those "WARN_ON(dev->iommu_group)" dumps because PAMU already
> > got to them.  Presumably without PAMU it silently (or with just pr_debug)
> > bails out at some other point.
> 
> 
> I posted (yet again) yesterday "[PATCH v11] PPC: POWERNV: move
> iommu_add_device earlier" which should fix this. And Bharat asked many
> times for this to get accepted :)

I still get the WARN_ONs even with that patch.  You're still registering
the bus notifier unconditionally.

-Scott

RE: [1/3] powerpc/vfio: Enable on POWERNV platform

[Bharat.Bhushan]
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==