Re: [PATCH] vfio powerpc: implemented IOMMU driver for VFIO

2012-12-12 Thread Alex Williamson 
On Wed, 2012-12-12 at 17:59 +1100, Alexey Kardashevskiy wrote:
> On 08/12/12 04:01, Alex Williamson wrote:
> >> +  case VFIO_IOMMU_MAP_DMA: {
> >> +  vfio_iommu_spapr_tce_dma_map param;
> >> +  struct iommu_table *tbl = container->tbl;
> >> +  enum dma_data_direction direction;
> >> +  unsigned long locked, lock_limit;
> >> +
> >> +  if (WARN_ON(!tbl))
> >> +  return -ENXIO;
> >> +
> >> +  minsz = offsetofend(vfio_iommu_spapr_tce_dma_map, size);
> >> +
> >> +  if (copy_from_user(, (void __user *)arg, minsz))
> >> +  return -EFAULT;
> >> +
> >> +  if (param.argsz < minsz)
> >> +  return -EINVAL;
> >> +
> >> +  if ((param.flags & VFIO_DMA_MAP_FLAG_READ) &&
> >> +  (param.flags & VFIO_DMA_MAP_FLAG_WRITE))
> >> +  direction = DMA_BIDIRECTIONAL;
> >> +  else if (param.flags & VFIO_DMA_MAP_FLAG_READ)
> >> +  direction = DMA_TO_DEVICE;
> >> +  else if (param.flags & VFIO_DMA_MAP_FLAG_WRITE)
> >> +  direction = DMA_FROM_DEVICE;
> >> +  else
> >> +  return -EINVAL;
> >
> > flags needs to be sanitized too.  Return EINVAL if any unknown bit is
> > set or else sloppy users may make it very difficult to make use of those
> > flag bits later.
> 
> 
> It already returns -EINVAL on any bit set except READ/WRITE, no?

No.  I could pass flags ~0 through there to get a read/write mapping and
cause you problems if you later want to define another bit.  Thanks,

Alex

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[PATCH] vfio powerpc: implemented IOMMU driver for VFIO

2012-12-12 Thread 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 patch implements an IOMMU driver for VFIO
which does mapping/unmapping pages for the guest IO and
provides information about DMA window (required by a POWERPC
guest).

The counterpart in QEMU is required to support this functionality.

Cc: David Gibson 
Signed-off-by: Alexey Kardashevskiy 
---
 drivers/vfio/Kconfig|6 +
 drivers/vfio/Makefile   |1 +
 drivers/vfio/vfio_iommu_spapr_tce.c |  249 +++
 include/linux/vfio.h|   31 +
 4 files changed, 287 insertions(+)
 create mode 100644 drivers/vfio/vfio_iommu_spapr_tce.c

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_iommu_spapr_tce.c 
b/drivers/vfio/vfio_iommu_spapr_tce.c
new file mode 100644
index 000..714bf57
--- /dev/null
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -0,0 +1,249 @@
+/*
+ * VFIO: IOMMU DMA mapping support for TCE on POWER
+ *
+ * Copyright (C) 2012 IBM Corp.  All rights reserved.
+ * Author: Alexey Kardashevskiy 
+ *
+ * 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 
+ */
+
+#include 
+#include 
+#include 
+#include 
+#include 
+#include 
+#include 
+
+#define DRIVER_VERSION  "0.1"
+#define DRIVER_AUTHOR   "a...@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;
+};
+
+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(>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);
+   if (container->tbl && container->tbl->it_group)
+   tce_iommu_detach_group(iommu_data, container->tbl->it_group);
+
+   mutex_destroy(>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(, (void __user *)arg, minsz))
+   return -EFAULT;
+
+   if (info.argsz < minsz)
+

[PATCH] vfio powerpc: implemented IOMMU driver for VFIO

2012-12-12 Thread 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 patch implements an IOMMU driver for VFIO
which does mapping/unmapping pages for the guest IO and
provides information about DMA window (required by a POWERPC
guest).

The counterpart in QEMU is required to support this functionality.

Cc: David Gibson da...@gibson.dropbear.id.au
Signed-off-by: Alexey Kardashevskiy a...@ozlabs.ru
---
 drivers/vfio/Kconfig|6 +
 drivers/vfio/Makefile   |1 +
 drivers/vfio/vfio_iommu_spapr_tce.c |  249 +++
 include/linux/vfio.h|   31 +
 4 files changed, 287 insertions(+)
 create mode 100644 drivers/vfio/vfio_iommu_spapr_tce.c

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_iommu_spapr_tce.c 
b/drivers/vfio/vfio_iommu_spapr_tce.c
new file mode 100644
index 000..714bf57
--- /dev/null
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -0,0 +1,249 @@
+/*
+ * VFIO: IOMMU DMA mapping support for TCE on POWER
+ *
+ * Copyright (C) 2012 IBM Corp.  All rights reserved.
+ * Author: Alexey Kardashevskiy a...@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.william...@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
+
+#define DRIVER_VERSION  0.1
+#define DRIVER_AUTHOR   a...@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;
+};
+
+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);
+   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,
+

Re: [PATCH] vfio powerpc: implemented IOMMU driver for VFIO

2012-12-12 Thread Alex Williamson 
On Wed, 2012-12-12 at 17:59 +1100, Alexey Kardashevskiy wrote:
 On 08/12/12 04:01, Alex Williamson wrote:
  +  case VFIO_IOMMU_MAP_DMA: {
  +  vfio_iommu_spapr_tce_dma_map param;
  +  struct iommu_table *tbl = container-tbl;
  +  enum dma_data_direction direction;
  +  unsigned long locked, lock_limit;
  +
  +  if (WARN_ON(!tbl))
  +  return -ENXIO;
  +
  +  minsz = offsetofend(vfio_iommu_spapr_tce_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) 
  +  (param.flags  VFIO_DMA_MAP_FLAG_WRITE))
  +  direction = DMA_BIDIRECTIONAL;
  +  else if (param.flags  VFIO_DMA_MAP_FLAG_READ)
  +  direction = DMA_TO_DEVICE;
  +  else if (param.flags  VFIO_DMA_MAP_FLAG_WRITE)
  +  direction = DMA_FROM_DEVICE;
  +  else
  +  return -EINVAL;
 
  flags needs to be sanitized too.  Return EINVAL if any unknown bit is
  set or else sloppy users may make it very difficult to make use of those
  flag bits later.
 
 
 It already returns -EINVAL on any bit set except READ/WRITE, no?

No.  I could pass flags ~0 through there to get a read/write mapping and
cause you problems if you later want to define another bit.  Thanks,

Alex

--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Re: [PATCH] vfio powerpc: implemented IOMMU driver for VFIO

2012-12-11 Thread Alexey Kardashevskiy 

On 08/12/12 04:01, Alex Williamson wrote:

+   case VFIO_IOMMU_MAP_DMA: {
+   vfio_iommu_spapr_tce_dma_map param;
+   struct iommu_table *tbl = container->tbl;
+   enum dma_data_direction direction;
+   unsigned long locked, lock_limit;
+
+   if (WARN_ON(!tbl))
+   return -ENXIO;
+
+   minsz = offsetofend(vfio_iommu_spapr_tce_dma_map, size);
+
+   if (copy_from_user(, (void __user *)arg, minsz))
+   return -EFAULT;
+
+   if (param.argsz < minsz)
+   return -EINVAL;
+
+   if ((param.flags & VFIO_DMA_MAP_FLAG_READ) &&
+   (param.flags & VFIO_DMA_MAP_FLAG_WRITE))
+   direction = DMA_BIDIRECTIONAL;
+   else if (param.flags & VFIO_DMA_MAP_FLAG_READ)
+   direction = DMA_TO_DEVICE;
+   else if (param.flags & VFIO_DMA_MAP_FLAG_WRITE)
+   direction = DMA_FROM_DEVICE;
+   else
+   return -EINVAL;


flags needs to be sanitized too.  Return EINVAL if any unknown bit is
set or else sloppy users may make it very difficult to make use of those
flag bits later.



It already returns -EINVAL on any bit set except READ/WRITE, no?


--
Alexey
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Re: [PATCH] vfio powerpc: implemented IOMMU driver for VFIO

2012-12-11 Thread Alexey Kardashevskiy 

On 08/12/12 04:01, Alex Williamson wrote:

+   case VFIO_IOMMU_MAP_DMA: {
+   vfio_iommu_spapr_tce_dma_map param;
+   struct iommu_table *tbl = container-tbl;
+   enum dma_data_direction direction;
+   unsigned long locked, lock_limit;
+
+   if (WARN_ON(!tbl))
+   return -ENXIO;
+
+   minsz = offsetofend(vfio_iommu_spapr_tce_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) 
+   (param.flags  VFIO_DMA_MAP_FLAG_WRITE))
+   direction = DMA_BIDIRECTIONAL;
+   else if (param.flags  VFIO_DMA_MAP_FLAG_READ)
+   direction = DMA_TO_DEVICE;
+   else if (param.flags  VFIO_DMA_MAP_FLAG_WRITE)
+   direction = DMA_FROM_DEVICE;
+   else
+   return -EINVAL;


flags needs to be sanitized too.  Return EINVAL if any unknown bit is
set or else sloppy users may make it very difficult to make use of those
flag bits later.



It already returns -EINVAL on any bit set except READ/WRITE, no?


--
Alexey
--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Re: [PATCH] vfio powerpc: implemented IOMMU driver for VFIO

2012-12-07 Thread Alex Williamson 
On Fri, 2012-12-07 at 18:34 +1100, 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 patch implements an IOMMU driver for VFIO
> which does mapping/unmapping pages for the guest IO and
> provides information about DMA window (required by a POWERPC
> guest).
> 
> The counterpart in QEMU is required to support this functionality.
> 
> Cc: David Gibson 
> Signed-off-by: Alexey Kardashevskiy 
> ---
>  drivers/vfio/Kconfig|6 +
>  drivers/vfio/Makefile   |1 +
>  drivers/vfio/vfio_iommu_spapr_tce.c |  348 
> +++
>  include/linux/vfio.h|   30 +++
>  4 files changed, 385 insertions(+)
>  create mode 100644 drivers/vfio/vfio_iommu_spapr_tce.c
> 
> 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_iommu_spapr_tce.c 
> b/drivers/vfio/vfio_iommu_spapr_tce.c
> new file mode 100644
> index 000..b0f81fe
> --- /dev/null
> +++ b/drivers/vfio/vfio_iommu_spapr_tce.c
> @@ -0,0 +1,348 @@
> +/*
> + * VFIO: IOMMU DMA mapping support for TCE on POWER
> + *
> + * Copyright (C) 2012 IBM Corp.  All rights reserved.
> + * Author: Alexey Kardashevskiy 
> + *
> + * 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 
> + */
> +
> +#include 
> +#include 
> +#include 
> +#include 
> +#include 
> +#include 
> +#include 
> +
> +#define DRIVER_VERSION  "0.1"
> +#define DRIVER_AUTHOR   "a...@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
> + */
> +
> +#define NPAGE_TO_SIZE(npage) ((size_t)(npage) << PAGE_SHIFT)
> +
> +struct vwork {
> + struct mm_struct*mm;
> + longnpage;
> + struct work_struct  work;
> +};
> +
> +/* delayed decrement/increment for locked_vm */
> +static void lock_acct_bg(struct work_struct *work)
> +{
> + struct vwork *vwork = container_of(work, struct vwork, work);
> + struct mm_struct *mm;
> +
> + mm = vwork->mm;
> + down_write(>mmap_sem);
> + mm->locked_vm += vwork->npage;
> + up_write(>mmap_sem);
> + mmput(mm);
> + kfree(vwork);
> +}
> +
> +static void lock_acct(long npage)
> +{
> + struct vwork *vwork;
> + struct mm_struct *mm;
> +
> + if (!current->mm)
> + return; /* process exited */
> +
> + if (down_write_trylock(>mm->mmap_sem)) {
> + current->mm->locked_vm += npage;
> + up_write(>mm->mmap_sem);
> + return;
> + }
> +
> + /*
> +  * Couldn't get mmap_sem lock, so must setup to update
> +  * mm->locked_vm later. If locked_vm were atomic, we
> +  * wouldn't need this silliness
> +  */
> + vwork = kmalloc(sizeof(struct vwork), GFP_KERNEL);
> + if (!vwork)
> + return;
> + mm = get_task_mm(current);
> + if (!mm) {
> + kfree(vwork);
> + return;
> + }
> + INIT_WORK(>work, lock_acct_bg);
> + vwork->mm = mm;
> + vwork->npage = npage;
> + schedule_work(>work);
> +}
> +
> +/*
> + * 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.
> + */
>

Re: [PATCH] vfio powerpc: implemented IOMMU driver for VFIO

2012-12-07 Thread Alex Williamson 
On Fri, 2012-12-07 at 18:34 +1100, 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 patch implements an IOMMU driver for VFIO
 which does mapping/unmapping pages for the guest IO and
 provides information about DMA window (required by a POWERPC
 guest).
 
 The counterpart in QEMU is required to support this functionality.
 
 Cc: David Gibson da...@gibson.dropbear.id.au
 Signed-off-by: Alexey Kardashevskiy a...@ozlabs.ru
 ---
  drivers/vfio/Kconfig|6 +
  drivers/vfio/Makefile   |1 +
  drivers/vfio/vfio_iommu_spapr_tce.c |  348 
 +++
  include/linux/vfio.h|   30 +++
  4 files changed, 385 insertions(+)
  create mode 100644 drivers/vfio/vfio_iommu_spapr_tce.c
 
 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_iommu_spapr_tce.c 
 b/drivers/vfio/vfio_iommu_spapr_tce.c
 new file mode 100644
 index 000..b0f81fe
 --- /dev/null
 +++ b/drivers/vfio/vfio_iommu_spapr_tce.c
 @@ -0,0 +1,348 @@
 +/*
 + * VFIO: IOMMU DMA mapping support for TCE on POWER
 + *
 + * Copyright (C) 2012 IBM Corp.  All rights reserved.
 + * Author: Alexey Kardashevskiy a...@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.william...@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
 +
 +#define DRIVER_VERSION  0.1
 +#define DRIVER_AUTHOR   a...@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
 + */
 +
 +#define NPAGE_TO_SIZE(npage) ((size_t)(npage)  PAGE_SHIFT)
 +
 +struct vwork {
 + struct mm_struct*mm;
 + longnpage;
 + struct work_struct  work;
 +};
 +
 +/* delayed decrement/increment for locked_vm */
 +static void lock_acct_bg(struct work_struct *work)
 +{
 + struct vwork *vwork = container_of(work, struct vwork, work);
 + struct mm_struct *mm;
 +
 + mm = vwork-mm;
 + down_write(mm-mmap_sem);
 + mm-locked_vm += vwork-npage;
 + up_write(mm-mmap_sem);
 + mmput(mm);
 + kfree(vwork);
 +}
 +
 +static void lock_acct(long npage)
 +{
 + struct vwork *vwork;
 + struct mm_struct *mm;
 +
 + if (!current-mm)
 + return; /* process exited */
 +
 + if (down_write_trylock(current-mm-mmap_sem)) {
 + current-mm-locked_vm += npage;
 + up_write(current-mm-mmap_sem);
 + return;
 + }
 +
 + /*
 +  * Couldn't get mmap_sem lock, so must setup to update
 +  * mm-locked_vm later. If locked_vm were atomic, we
 +  * wouldn't need this silliness
 +  */
 + vwork = kmalloc(sizeof(struct vwork), GFP_KERNEL);
 + if (!vwork)
 + return;
 + mm = get_task_mm(current);
 + if (!mm) {
 + kfree(vwork);
 + return;
 + }
 + INIT_WORK(vwork-work, lock_acct_bg);
 + vwork-mm = mm;
 + vwork-npage = npage;
 + schedule_work(vwork-work);
 +}
 +
 +/*
 + * 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

[PATCH] vfio powerpc: implemented IOMMU driver for VFIO

2012-12-06 Thread 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 patch implements an IOMMU driver for VFIO
which does mapping/unmapping pages for the guest IO and
provides information about DMA window (required by a POWERPC
guest).

The counterpart in QEMU is required to support this functionality.

Cc: David Gibson 
Signed-off-by: Alexey Kardashevskiy 
---
 drivers/vfio/Kconfig|6 +
 drivers/vfio/Makefile   |1 +
 drivers/vfio/vfio_iommu_spapr_tce.c |  348 +++
 include/linux/vfio.h|   30 +++
 4 files changed, 385 insertions(+)
 create mode 100644 drivers/vfio/vfio_iommu_spapr_tce.c

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_iommu_spapr_tce.c 
b/drivers/vfio/vfio_iommu_spapr_tce.c
new file mode 100644
index 000..b0f81fe
--- /dev/null
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -0,0 +1,348 @@
+/*
+ * VFIO: IOMMU DMA mapping support for TCE on POWER
+ *
+ * Copyright (C) 2012 IBM Corp.  All rights reserved.
+ * Author: Alexey Kardashevskiy 
+ *
+ * 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 
+ */
+
+#include 
+#include 
+#include 
+#include 
+#include 
+#include 
+#include 
+
+#define DRIVER_VERSION  "0.1"
+#define DRIVER_AUTHOR   "a...@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
+ */
+
+#define NPAGE_TO_SIZE(npage)   ((size_t)(npage) << PAGE_SHIFT)
+
+struct vwork {
+   struct mm_struct*mm;
+   longnpage;
+   struct work_struct  work;
+};
+
+/* delayed decrement/increment for locked_vm */
+static void lock_acct_bg(struct work_struct *work)
+{
+   struct vwork *vwork = container_of(work, struct vwork, work);
+   struct mm_struct *mm;
+
+   mm = vwork->mm;
+   down_write(>mmap_sem);
+   mm->locked_vm += vwork->npage;
+   up_write(>mmap_sem);
+   mmput(mm);
+   kfree(vwork);
+}
+
+static void lock_acct(long npage)
+{
+   struct vwork *vwork;
+   struct mm_struct *mm;
+
+   if (!current->mm)
+   return; /* process exited */
+
+   if (down_write_trylock(>mm->mmap_sem)) {
+   current->mm->locked_vm += npage;
+   up_write(>mm->mmap_sem);
+   return;
+   }
+
+   /*
+* Couldn't get mmap_sem lock, so must setup to update
+* mm->locked_vm later. If locked_vm were atomic, we
+* wouldn't need this silliness
+*/
+   vwork = kmalloc(sizeof(struct vwork), GFP_KERNEL);
+   if (!vwork)
+   return;
+   mm = get_task_mm(current);
+   if (!mm) {
+   kfree(vwork);
+   return;
+   }
+   INIT_WORK(>work, lock_acct_bg);
+   vwork->mm = mm;
+   vwork->npage = npage;
+   schedule_work(>work);
+}
+
+/*
+ * 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;
+};
+
+static void *tce_iommu_open(unsigned long arg)
+{
+   struct tce_container *container;
+
+   if (arg != VFIO_SPAPR_TCE_IOMMU) {
+   pr_err("tce_vfio: Wrong IOMMU

[PATCH] vfio powerpc: implemented IOMMU driver for VFIO

2012-12-06 Thread 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 patch implements an IOMMU driver for VFIO
which does mapping/unmapping pages for the guest IO and
provides information about DMA window (required by a POWERPC
guest).

The counterpart in QEMU is required to support this functionality.

Cc: David Gibson da...@gibson.dropbear.id.au
Signed-off-by: Alexey Kardashevskiy a...@ozlabs.ru
---
 drivers/vfio/Kconfig|6 +
 drivers/vfio/Makefile   |1 +
 drivers/vfio/vfio_iommu_spapr_tce.c |  348 +++
 include/linux/vfio.h|   30 +++
 4 files changed, 385 insertions(+)
 create mode 100644 drivers/vfio/vfio_iommu_spapr_tce.c

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_iommu_spapr_tce.c 
b/drivers/vfio/vfio_iommu_spapr_tce.c
new file mode 100644
index 000..b0f81fe
--- /dev/null
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -0,0 +1,348 @@
+/*
+ * VFIO: IOMMU DMA mapping support for TCE on POWER
+ *
+ * Copyright (C) 2012 IBM Corp.  All rights reserved.
+ * Author: Alexey Kardashevskiy a...@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.william...@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
+
+#define DRIVER_VERSION  0.1
+#define DRIVER_AUTHOR   a...@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
+ */
+
+#define NPAGE_TO_SIZE(npage)   ((size_t)(npage)  PAGE_SHIFT)
+
+struct vwork {
+   struct mm_struct*mm;
+   longnpage;
+   struct work_struct  work;
+};
+
+/* delayed decrement/increment for locked_vm */
+static void lock_acct_bg(struct work_struct *work)
+{
+   struct vwork *vwork = container_of(work, struct vwork, work);
+   struct mm_struct *mm;
+
+   mm = vwork-mm;
+   down_write(mm-mmap_sem);
+   mm-locked_vm += vwork-npage;
+   up_write(mm-mmap_sem);
+   mmput(mm);
+   kfree(vwork);
+}
+
+static void lock_acct(long npage)
+{
+   struct vwork *vwork;
+   struct mm_struct *mm;
+
+   if (!current-mm)
+   return; /* process exited */
+
+   if (down_write_trylock(current-mm-mmap_sem)) {
+   current-mm-locked_vm += npage;
+   up_write(current-mm-mmap_sem);
+   return;
+   }
+
+   /*
+* Couldn't get mmap_sem lock, so must setup to update
+* mm-locked_vm later. If locked_vm were atomic, we
+* wouldn't need this silliness
+*/
+   vwork = kmalloc(sizeof(struct vwork), GFP_KERNEL);
+   if (!vwork)
+   return;
+   mm = get_task_mm(current);
+   if (!mm) {
+   kfree(vwork);
+   return;
+   }
+   INIT_WORK(vwork-work, lock_acct_bg);
+   vwork-mm = mm;
+   vwork-npage = npage;
+   schedule_work(vwork-work);
+}
+
+/*
+ * 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;
+};
+
+static void

Re: [PATCH] vfio powerpc: implemented IOMMU driver for VFIO

2012-11-28 Thread Alexey Kardashevskiy 

On 29/11/12 08:01, Alex Williamson wrote:

On Wed, 2012-11-28 at 18:21 +1100, 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 patch implements an IOMMU driver for VFIO
which does mapping/unmapping pages for the guest IO and
provides information about DMA window (required by a POWERPC
guest).

The counterpart in QEMU is required to support this functionality.

Cc: David Gibson 
Signed-off-by: Alexey Kardashevskiy 
---
  drivers/vfio/Kconfig|6 +
  drivers/vfio/Makefile   |1 +
  drivers/vfio/vfio_iommu_spapr_tce.c |  332 +++
  include/linux/vfio.h|   33 
  4 files changed, 372 insertions(+)
  create mode 100644 drivers/vfio/vfio_iommu_spapr_tce.c

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_iommu_spapr_tce.c 
b/drivers/vfio/vfio_iommu_spapr_tce.c
new file mode 100644
index 000..b98770e
--- /dev/null
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -0,0 +1,332 @@
+/*
+ * VFIO: IOMMU DMA mapping support for TCE on POWER
+ *
+ * Copyright (C) 2012 IBM Corp.  All rights reserved.
+ * Author: Alexey Kardashevskiy 
+ *
+ * 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 
+ */
+
+#include 
+#include 
+#include 
+#include 
+#include 
+#include 
+#include 
+
+#define DRIVER_VERSION  "0.1"
+#define DRIVER_AUTHOR   "a...@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
+ */
+
+#define NPAGE_TO_SIZE(npage)   ((size_t)(npage) << PAGE_SHIFT)
+
+struct vwork {
+   struct mm_struct*mm;
+   longnpage;
+   struct work_struct  work;
+};
+
+/* delayed decrement/increment for locked_vm */
+static void lock_acct_bg(struct work_struct *work)
+{
+   struct vwork *vwork = container_of(work, struct vwork, work);
+   struct mm_struct *mm;
+
+   mm = vwork->mm;
+   down_write(>mmap_sem);
+   mm->locked_vm += vwork->npage;
+   up_write(>mmap_sem);
+   mmput(mm);
+   kfree(vwork);
+}
+
+static void lock_acct(long npage)
+{
+   struct vwork *vwork;
+   struct mm_struct *mm;
+
+   if (!current->mm)
+   return; /* process exited */
+
+   if (down_write_trylock(>mm->mmap_sem)) {
+   current->mm->locked_vm += npage;
+   up_write(>mm->mmap_sem);
+   return;
+   }
+
+   /*
+* Couldn't get mmap_sem lock, so must setup to update
+* mm->locked_vm later. If locked_vm were atomic, we
+* wouldn't need this silliness
+*/
+   vwork = kmalloc(sizeof(struct vwork), GFP_KERNEL);
+   if (!vwork)
+   return;
+   mm = get_task_mm(current);
+   if (!mm) {
+   kfree(vwork);
+   return;
+   }
+   INIT_WORK(>work, lock_acct_bg);
+   vwork->mm = mm;
+   vwork->npage = npage;
+   schedule_work(>work);
+}


This looks familiar, should we split it out to a common file instead of
duplicating it?


It is simple cut-n-paste from type1 driver :)
Moving it to a separate file is up to you but it is quite small piece of 
code to move it somewhere, and I have not fixed rlimit handling yet, so 
wait a bit.




+
+/*
+ * The container descriptor supports only a single

Re: [PATCH] vfio powerpc: implemented IOMMU driver for VFIO

2012-11-28 Thread Alex Williamson 
On Wed, 2012-11-28 at 18:21 +1100, 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 patch implements an IOMMU driver for VFIO
> which does mapping/unmapping pages for the guest IO and
> provides information about DMA window (required by a POWERPC
> guest).
> 
> The counterpart in QEMU is required to support this functionality.
> 
> Cc: David Gibson 
> Signed-off-by: Alexey Kardashevskiy 
> ---
>  drivers/vfio/Kconfig|6 +
>  drivers/vfio/Makefile   |1 +
>  drivers/vfio/vfio_iommu_spapr_tce.c |  332 
> +++
>  include/linux/vfio.h|   33 
>  4 files changed, 372 insertions(+)
>  create mode 100644 drivers/vfio/vfio_iommu_spapr_tce.c
> 
> 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_iommu_spapr_tce.c 
> b/drivers/vfio/vfio_iommu_spapr_tce.c
> new file mode 100644
> index 000..b98770e
> --- /dev/null
> +++ b/drivers/vfio/vfio_iommu_spapr_tce.c
> @@ -0,0 +1,332 @@
> +/*
> + * VFIO: IOMMU DMA mapping support for TCE on POWER
> + *
> + * Copyright (C) 2012 IBM Corp.  All rights reserved.
> + * Author: Alexey Kardashevskiy 
> + *
> + * 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 
> + */
> +
> +#include 
> +#include 
> +#include 
> +#include 
> +#include 
> +#include 
> +#include 
> +
> +#define DRIVER_VERSION  "0.1"
> +#define DRIVER_AUTHOR   "a...@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
> + */
> +
> +#define NPAGE_TO_SIZE(npage) ((size_t)(npage) << PAGE_SHIFT)
> +
> +struct vwork {
> + struct mm_struct*mm;
> + longnpage;
> + struct work_struct  work;
> +};
> +
> +/* delayed decrement/increment for locked_vm */
> +static void lock_acct_bg(struct work_struct *work)
> +{
> + struct vwork *vwork = container_of(work, struct vwork, work);
> + struct mm_struct *mm;
> +
> + mm = vwork->mm;
> + down_write(>mmap_sem);
> + mm->locked_vm += vwork->npage;
> + up_write(>mmap_sem);
> + mmput(mm);
> + kfree(vwork);
> +}
> +
> +static void lock_acct(long npage)
> +{
> + struct vwork *vwork;
> + struct mm_struct *mm;
> +
> + if (!current->mm)
> + return; /* process exited */
> +
> + if (down_write_trylock(>mm->mmap_sem)) {
> + current->mm->locked_vm += npage;
> + up_write(>mm->mmap_sem);
> + return;
> + }
> +
> + /*
> +  * Couldn't get mmap_sem lock, so must setup to update
> +  * mm->locked_vm later. If locked_vm were atomic, we
> +  * wouldn't need this silliness
> +  */
> + vwork = kmalloc(sizeof(struct vwork), GFP_KERNEL);
> + if (!vwork)
> + return;
> + mm = get_task_mm(current);
> + if (!mm) {
> + kfree(vwork);
> + return;
> + }
> + INIT_WORK(>work, lock_acct_bg);
> + vwork->mm = mm;
> + vwork->npage = npage;
> + schedule_work(>work);
> +}

This looks familiar, should we split it out to a common file instead of
duplicating it?

> +
> +/*
> + * The container descriptor supports only a single group per container.
> + * Required by the API as the

Re: [PATCH] vfio powerpc: implemented IOMMU driver for VFIO

2012-11-28 Thread Alex Williamson 
On Wed, 2012-11-28 at 18:21 +1100, 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 patch implements an IOMMU driver for VFIO
 which does mapping/unmapping pages for the guest IO and
 provides information about DMA window (required by a POWERPC
 guest).
 
 The counterpart in QEMU is required to support this functionality.
 
 Cc: David Gibson da...@gibson.dropbear.id.au
 Signed-off-by: Alexey Kardashevskiy a...@ozlabs.ru
 ---
  drivers/vfio/Kconfig|6 +
  drivers/vfio/Makefile   |1 +
  drivers/vfio/vfio_iommu_spapr_tce.c |  332 
 +++
  include/linux/vfio.h|   33 
  4 files changed, 372 insertions(+)
  create mode 100644 drivers/vfio/vfio_iommu_spapr_tce.c
 
 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_iommu_spapr_tce.c 
 b/drivers/vfio/vfio_iommu_spapr_tce.c
 new file mode 100644
 index 000..b98770e
 --- /dev/null
 +++ b/drivers/vfio/vfio_iommu_spapr_tce.c
 @@ -0,0 +1,332 @@
 +/*
 + * VFIO: IOMMU DMA mapping support for TCE on POWER
 + *
 + * Copyright (C) 2012 IBM Corp.  All rights reserved.
 + * Author: Alexey Kardashevskiy a...@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.william...@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
 +
 +#define DRIVER_VERSION  0.1
 +#define DRIVER_AUTHOR   a...@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
 + */
 +
 +#define NPAGE_TO_SIZE(npage) ((size_t)(npage)  PAGE_SHIFT)
 +
 +struct vwork {
 + struct mm_struct*mm;
 + longnpage;
 + struct work_struct  work;
 +};
 +
 +/* delayed decrement/increment for locked_vm */
 +static void lock_acct_bg(struct work_struct *work)
 +{
 + struct vwork *vwork = container_of(work, struct vwork, work);
 + struct mm_struct *mm;
 +
 + mm = vwork-mm;
 + down_write(mm-mmap_sem);
 + mm-locked_vm += vwork-npage;
 + up_write(mm-mmap_sem);
 + mmput(mm);
 + kfree(vwork);
 +}
 +
 +static void lock_acct(long npage)
 +{
 + struct vwork *vwork;
 + struct mm_struct *mm;
 +
 + if (!current-mm)
 + return; /* process exited */
 +
 + if (down_write_trylock(current-mm-mmap_sem)) {
 + current-mm-locked_vm += npage;
 + up_write(current-mm-mmap_sem);
 + return;
 + }
 +
 + /*
 +  * Couldn't get mmap_sem lock, so must setup to update
 +  * mm-locked_vm later. If locked_vm were atomic, we
 +  * wouldn't need this silliness
 +  */
 + vwork = kmalloc(sizeof(struct vwork), GFP_KERNEL);
 + if (!vwork)
 + return;
 + mm = get_task_mm(current);
 + if (!mm) {
 + kfree(vwork);
 + return;
 + }
 + INIT_WORK(vwork-work, lock_acct_bg);
 + vwork-mm = mm;
 + vwork-npage = npage;
 + schedule_work(vwork-work);
 +}

This looks familiar, should we split it out to a common file instead of
duplicating it?

 +
 +/*
 + * The container descriptor supports only a single group per container.
 + * Required by the

Re: [PATCH] vfio powerpc: implemented IOMMU driver for VFIO

2012-11-28 Thread Alexey Kardashevskiy 

On 29/11/12 08:01, Alex Williamson wrote:

On Wed, 2012-11-28 at 18:21 +1100, 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 patch implements an IOMMU driver for VFIO
which does mapping/unmapping pages for the guest IO and
provides information about DMA window (required by a POWERPC
guest).

The counterpart in QEMU is required to support this functionality.

Cc: David Gibson da...@gibson.dropbear.id.au
Signed-off-by: Alexey Kardashevskiy a...@ozlabs.ru
---
  drivers/vfio/Kconfig|6 +
  drivers/vfio/Makefile   |1 +
  drivers/vfio/vfio_iommu_spapr_tce.c |  332 +++
  include/linux/vfio.h|   33 
  4 files changed, 372 insertions(+)
  create mode 100644 drivers/vfio/vfio_iommu_spapr_tce.c

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_iommu_spapr_tce.c 
b/drivers/vfio/vfio_iommu_spapr_tce.c
new file mode 100644
index 000..b98770e
--- /dev/null
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -0,0 +1,332 @@
+/*
+ * VFIO: IOMMU DMA mapping support for TCE on POWER
+ *
+ * Copyright (C) 2012 IBM Corp.  All rights reserved.
+ * Author: Alexey Kardashevskiy a...@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.william...@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
+
+#define DRIVER_VERSION  0.1
+#define DRIVER_AUTHOR   a...@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
+ */
+
+#define NPAGE_TO_SIZE(npage)   ((size_t)(npage)  PAGE_SHIFT)
+
+struct vwork {
+   struct mm_struct*mm;
+   longnpage;
+   struct work_struct  work;
+};
+
+/* delayed decrement/increment for locked_vm */
+static void lock_acct_bg(struct work_struct *work)
+{
+   struct vwork *vwork = container_of(work, struct vwork, work);
+   struct mm_struct *mm;
+
+   mm = vwork-mm;
+   down_write(mm-mmap_sem);
+   mm-locked_vm += vwork-npage;
+   up_write(mm-mmap_sem);
+   mmput(mm);
+   kfree(vwork);
+}
+
+static void lock_acct(long npage)
+{
+   struct vwork *vwork;
+   struct mm_struct *mm;
+
+   if (!current-mm)
+   return; /* process exited */
+
+   if (down_write_trylock(current-mm-mmap_sem)) {
+   current-mm-locked_vm += npage;
+   up_write(current-mm-mmap_sem);
+   return;
+   }
+
+   /*
+* Couldn't get mmap_sem lock, so must setup to update
+* mm-locked_vm later. If locked_vm were atomic, we
+* wouldn't need this silliness
+*/
+   vwork = kmalloc(sizeof(struct vwork), GFP_KERNEL);
+   if (!vwork)
+   return;
+   mm = get_task_mm(current);
+   if (!mm) {
+   kfree(vwork);
+   return;
+   }
+   INIT_WORK(vwork-work, lock_acct_bg);
+   vwork-mm = mm;
+   vwork-npage = npage;
+   schedule_work(vwork-work);
+}


This looks familiar, should we split it out to a common file instead of
duplicating it?


It is simple cut-n-paste from type1 driver :)
Moving it to a separate file is up to you but it is

[PATCH] vfio powerpc: implemented IOMMU driver for VFIO

2012-11-27 Thread 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 patch implements an IOMMU driver for VFIO
which does mapping/unmapping pages for the guest IO and
provides information about DMA window (required by a POWERPC
guest).

The counterpart in QEMU is required to support this functionality.

Cc: David Gibson 
Signed-off-by: Alexey Kardashevskiy 
---
 drivers/vfio/Kconfig|6 +
 drivers/vfio/Makefile   |1 +
 drivers/vfio/vfio_iommu_spapr_tce.c |  332 +++
 include/linux/vfio.h|   33 
 4 files changed, 372 insertions(+)
 create mode 100644 drivers/vfio/vfio_iommu_spapr_tce.c

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_iommu_spapr_tce.c 
b/drivers/vfio/vfio_iommu_spapr_tce.c
new file mode 100644
index 000..b98770e
--- /dev/null
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -0,0 +1,332 @@
+/*
+ * VFIO: IOMMU DMA mapping support for TCE on POWER
+ *
+ * Copyright (C) 2012 IBM Corp.  All rights reserved.
+ * Author: Alexey Kardashevskiy 
+ *
+ * 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 
+ */
+
+#include 
+#include 
+#include 
+#include 
+#include 
+#include 
+#include 
+
+#define DRIVER_VERSION  "0.1"
+#define DRIVER_AUTHOR   "a...@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
+ */
+
+#define NPAGE_TO_SIZE(npage)   ((size_t)(npage) << PAGE_SHIFT)
+
+struct vwork {
+   struct mm_struct*mm;
+   longnpage;
+   struct work_struct  work;
+};
+
+/* delayed decrement/increment for locked_vm */
+static void lock_acct_bg(struct work_struct *work)
+{
+   struct vwork *vwork = container_of(work, struct vwork, work);
+   struct mm_struct *mm;
+
+   mm = vwork->mm;
+   down_write(>mmap_sem);
+   mm->locked_vm += vwork->npage;
+   up_write(>mmap_sem);
+   mmput(mm);
+   kfree(vwork);
+}
+
+static void lock_acct(long npage)
+{
+   struct vwork *vwork;
+   struct mm_struct *mm;
+
+   if (!current->mm)
+   return; /* process exited */
+
+   if (down_write_trylock(>mm->mmap_sem)) {
+   current->mm->locked_vm += npage;
+   up_write(>mm->mmap_sem);
+   return;
+   }
+
+   /*
+* Couldn't get mmap_sem lock, so must setup to update
+* mm->locked_vm later. If locked_vm were atomic, we
+* wouldn't need this silliness
+*/
+   vwork = kmalloc(sizeof(struct vwork), GFP_KERNEL);
+   if (!vwork)
+   return;
+   mm = get_task_mm(current);
+   if (!mm) {
+   kfree(vwork);
+   return;
+   }
+   INIT_WORK(>work, lock_acct_bg);
+   vwork->mm = mm;
+   vwork->npage = npage;
+   schedule_work(>work);
+}
+
+/*
+ * 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;
+};
+
+static void *tce_iommu_open(unsigned long arg)
+{
+   struct tce_container *container;
+
+   if (arg != VFIO_SPAPR_TCE_IOMMU) {
+   pr_err("tce_vfio: Wrong IOMMU

[PATCH] vfio powerpc: implemented IOMMU driver for VFIO

2012-11-27 Thread 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 patch implements an IOMMU driver for VFIO
which does mapping/unmapping pages for the guest IO and
provides information about DMA window (required by a POWERPC
guest).

The counterpart in QEMU is required to support this functionality.

Cc: David Gibson da...@gibson.dropbear.id.au
Signed-off-by: Alexey Kardashevskiy a...@ozlabs.ru
---
 drivers/vfio/Kconfig|6 +
 drivers/vfio/Makefile   |1 +
 drivers/vfio/vfio_iommu_spapr_tce.c |  332 +++
 include/linux/vfio.h|   33 
 4 files changed, 372 insertions(+)
 create mode 100644 drivers/vfio/vfio_iommu_spapr_tce.c

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_iommu_spapr_tce.c 
b/drivers/vfio/vfio_iommu_spapr_tce.c
new file mode 100644
index 000..b98770e
--- /dev/null
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -0,0 +1,332 @@
+/*
+ * VFIO: IOMMU DMA mapping support for TCE on POWER
+ *
+ * Copyright (C) 2012 IBM Corp.  All rights reserved.
+ * Author: Alexey Kardashevskiy a...@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.william...@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
+
+#define DRIVER_VERSION  0.1
+#define DRIVER_AUTHOR   a...@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
+ */
+
+#define NPAGE_TO_SIZE(npage)   ((size_t)(npage)  PAGE_SHIFT)
+
+struct vwork {
+   struct mm_struct*mm;
+   longnpage;
+   struct work_struct  work;
+};
+
+/* delayed decrement/increment for locked_vm */
+static void lock_acct_bg(struct work_struct *work)
+{
+   struct vwork *vwork = container_of(work, struct vwork, work);
+   struct mm_struct *mm;
+
+   mm = vwork-mm;
+   down_write(mm-mmap_sem);
+   mm-locked_vm += vwork-npage;
+   up_write(mm-mmap_sem);
+   mmput(mm);
+   kfree(vwork);
+}
+
+static void lock_acct(long npage)
+{
+   struct vwork *vwork;
+   struct mm_struct *mm;
+
+   if (!current-mm)
+   return; /* process exited */
+
+   if (down_write_trylock(current-mm-mmap_sem)) {
+   current-mm-locked_vm += npage;
+   up_write(current-mm-mmap_sem);
+   return;
+   }
+
+   /*
+* Couldn't get mmap_sem lock, so must setup to update
+* mm-locked_vm later. If locked_vm were atomic, we
+* wouldn't need this silliness
+*/
+   vwork = kmalloc(sizeof(struct vwork), GFP_KERNEL);
+   if (!vwork)
+   return;
+   mm = get_task_mm(current);
+   if (!mm) {
+   kfree(vwork);
+   return;
+   }
+   INIT_WORK(vwork-work, lock_acct_bg);
+   vwork-mm = mm;
+   vwork-npage = npage;
+   schedule_work(vwork-work);
+}
+
+/*
+ * 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;
+};
+
+static void