[PATCH kernel v10 00/10] powerpc/kvm/vfio: Enable in-kernel acceleration

[PATCH kernel v10 00/10] powerpc/kvm/vfio: Enable in-kernel acceleration

[Alexey Kardashevskiy]

This is my current queue of patches to add acceleration of TCE
updates in KVM.

This is based on Linus'es tree sha1 d528ae0d3dfe.

Please comment. Thanks.

Changes:
v10:
* fixed bugs in 10/10
* fixed 04/10 to avoid iommu_table get/put race in 10/10

v9:
* renamed few exported symbols in 04/10
* reforked various objects reference counting in 10/10

v8:
* kept fixing oddities with error handling in 10/10

v7:
* added realmode's WARN_ON_ONCE_RM in arch/powerpc/kvm/book3s_64_vio_hv.c

v6:
* reworked the last patch in terms of error handling and parameters checking

v5:
* replaced "KVM: PPC: Separate TCE validation from update" with
"KVM: PPC: iommu: Unify TCE checking"
* changed already reviewed "powerpc/iommu/vfio_spapr_tce: Cleanup iommu_table disposal"
* reworked "KVM: PPC: VFIO: Add in-kernel acceleration for VFIO"
* more details in individual commit logs

v4:
* addressed comments from v3
* updated subject lines with correct component names
* regrouped the patchset in order:
	- powerpc fixes;
	- vfio_spapr_tce driver fixes;
	- KVM/PPC fixes;
	- KVM+PPC+VFIO;
* everything except last 2 patches have "Reviewed-By: David"

v3:
* there was no full repost, only last patch was posted

v2:
* 11/11 reworked to use new notifiers, it is rather RFC as it still has
a issue;
* got 09/11, 10/11 to use notifiers in 11/11;
* added rb: David to most of patches and added a comment in 05/11.


Alexey Kardashevskiy (10):
  powerpc/mmu: Add real mode support for IOMMU preregistered memory
  powerpc/powernv/iommu: Add real mode version of
    iommu_table_ops::exchange()
  powerpc/iommu/vfio_spapr_tce: Cleanup iommu_table disposal
  powerpc/vfio_spapr_tce: Add reference counting to iommu_table
  KVM: PPC: Reserve KVM_CAP_SPAPR_TCE_VFIO capability number
  KVM: PPC: Enable IOMMU_API for KVM_BOOK3S_64 permanently
  KVM: PPC: Pass kvm* to kvmppc_find_table()
  KVM: PPC: Use preregistered memory API to access TCE list
  KVM: PPC: iommu: Unify TCE checking
  KVM: PPC: VFIO: Add in-kernel acceleration for VFIO

 Documentation/virtual/kvm/devices/vfio.txt |  18 +-
 arch/powerpc/include/asm/iommu.h           |  32 ++-
 arch/powerpc/include/asm/kvm_host.h        |   8 +
 arch/powerpc/include/asm/kvm_ppc.h         |  12 +-
 arch/powerpc/include/asm/mmu_context.h     |   4 +
 include/uapi/linux/kvm.h                   |   7 +
 arch/powerpc/kernel/iommu.c                |  89 ++++++---
 arch/powerpc/kvm/book3s_64_vio.c           | 308 ++++++++++++++++++++++++++++-
 arch/powerpc/kvm/book3s_64_vio_hv.c        | 303 +++++++++++++++++++++++-----
 arch/powerpc/kvm/powerpc.c                 |   2 +
 arch/powerpc/mm/mmu_context_iommu.c        |  39 ++++
 arch/powerpc/platforms/powernv/pci-ioda.c  |  46 +++--
 arch/powerpc/platforms/powernv/pci.c       |   1 +
 arch/powerpc/platforms/pseries/iommu.c     |   3 +-
 arch/powerpc/platforms/pseries/vio.c       |   2 +-
 drivers/vfio/vfio_iommu_spapr_tce.c        |   2 +-
 virt/kvm/vfio.c                            | 104 ++++++++++
 arch/powerpc/kvm/Kconfig                   |   1 +
 18 files changed, 874 insertions(+), 107 deletions(-)

-- 
2.11.0

[PATCH kernel v10 00/10] powerpc/kvm/vfio: Enable in-kernel acceleration

[Alexey Kardashevskiy]

This is my current queue of patches to add acceleration of TCE
updates in KVM.

This is based on Linus'es tree sha1 d528ae0d3dfe.

Please comment. Thanks.

Changes:
v10:
* fixed bugs in 10/10
* fixed 04/10 to avoid iommu_table get/put race in 10/10

v9:
* renamed few exported symbols in 04/10
* reforked various objects reference counting in 10/10

v8:
* kept fixing oddities with error handling in 10/10

v7:
* added realmode's WARN_ON_ONCE_RM in arch/powerpc/kvm/book3s_64_vio_hv.c

v6:
* reworked the last patch in terms of error handling and parameters checking

v5:
* replaced "KVM: PPC: Separate TCE validation from update" with
"KVM: PPC: iommu: Unify TCE checking"
* changed already reviewed "powerpc/iommu/vfio_spapr_tce: Cleanup iommu_table disposal"
* reworked "KVM: PPC: VFIO: Add in-kernel acceleration for VFIO"
* more details in individual commit logs

v4:
* addressed comments from v3
* updated subject lines with correct component names
* regrouped the patchset in order:
	- powerpc fixes;
	- vfio_spapr_tce driver fixes;
	- KVM/PPC fixes;
	- KVM+PPC+VFIO;
* everything except last 2 patches have "Reviewed-By: David"

v3:
* there was no full repost, only last patch was posted

v2:
* 11/11 reworked to use new notifiers, it is rather RFC as it still has
a issue;
* got 09/11, 10/11 to use notifiers in 11/11;
* added rb: David to most of patches and added a comment in 05/11.


Alexey Kardashevskiy (10):
  powerpc/mmu: Add real mode support for IOMMU preregistered memory
  powerpc/powernv/iommu: Add real mode version of
    iommu_table_ops::exchange()
  powerpc/iommu/vfio_spapr_tce: Cleanup iommu_table disposal
  powerpc/vfio_spapr_tce: Add reference counting to iommu_table
  KVM: PPC: Reserve KVM_CAP_SPAPR_TCE_VFIO capability number
  KVM: PPC: Enable IOMMU_API for KVM_BOOK3S_64 permanently
  KVM: PPC: Pass kvm* to kvmppc_find_table()
  KVM: PPC: Use preregistered memory API to access TCE list
  KVM: PPC: iommu: Unify TCE checking
  KVM: PPC: VFIO: Add in-kernel acceleration for VFIO

 Documentation/virtual/kvm/devices/vfio.txt |  18 +-
 arch/powerpc/include/asm/iommu.h           |  32 ++-
 arch/powerpc/include/asm/kvm_host.h        |   8 +
 arch/powerpc/include/asm/kvm_ppc.h         |  12 +-
 arch/powerpc/include/asm/mmu_context.h     |   4 +
 include/uapi/linux/kvm.h                   |   7 +
 arch/powerpc/kernel/iommu.c                |  89 ++++++---
 arch/powerpc/kvm/book3s_64_vio.c           | 308 ++++++++++++++++++++++++++++-
 arch/powerpc/kvm/book3s_64_vio_hv.c        | 303 +++++++++++++++++++++++-----
 arch/powerpc/kvm/powerpc.c                 |   2 +
 arch/powerpc/mm/mmu_context_iommu.c        |  39 ++++
 arch/powerpc/platforms/powernv/pci-ioda.c  |  46 +++--
 arch/powerpc/platforms/powernv/pci.c       |   1 +
 arch/powerpc/platforms/pseries/iommu.c     |   3 +-
 arch/powerpc/platforms/pseries/vio.c       |   2 +-
 drivers/vfio/vfio_iommu_spapr_tce.c        |   2 +-
 virt/kvm/vfio.c                            | 104 ++++++++++
 arch/powerpc/kvm/Kconfig                   |   1 +
 18 files changed, 874 insertions(+), 107 deletions(-)

-- 
2.11.0

[PATCH kernel v10 01/10] powerpc/mmu: Add real mode support for IOMMU preregistered memory

[Alexey Kardashevskiy]

This makes mm_iommu_lookup() able to work in realmode by replacing
list_for_each_entry_rcu() (which can do debug stuff which can fail in
real mode) with list_for_each_entry_lockless().

This adds realmode version of mm_iommu_ua_to_hpa() which adds
explicit vmalloc'd-to-linear address conversion.
Unlike mm_iommu_ua_to_hpa(), mm_iommu_ua_to_hpa_rm() can fail.

This changes mm_iommu_preregistered() to receive @mm as in real mode
@current does not always have a correct pointer.

This adds realmode version of mm_iommu_lookup() which receives @mm
(for the same reason as for mm_iommu_preregistered()) and uses
lockless version of list_for_each_entry_rcu().

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
---
 arch/powerpc/include/asm/mmu_context.h |  4 ++++
 arch/powerpc/mm/mmu_context_iommu.c    | 39 ++++++++++++++++++++++++++++++++++
 2 files changed, 43 insertions(+)

diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index b9e3f0aca261..c70c8272523d 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -29,10 +29,14 @@ extern void mm_iommu_init(struct mm_struct *mm);
 extern void mm_iommu_cleanup(struct mm_struct *mm);
 extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm,
 		unsigned long ua, unsigned long size);
+extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(
+		struct mm_struct *mm, unsigned long ua, unsigned long size);
 extern struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
 		unsigned long ua, unsigned long entries);
 extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 		unsigned long ua, unsigned long *hpa);
+extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
+		unsigned long ua, unsigned long *hpa);
 extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);
 extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem);
 #endif
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index 497130c5c742..fc67bd766eaf 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -314,6 +314,25 @@ struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm,
 }
 EXPORT_SYMBOL_GPL(mm_iommu_lookup);
 
+struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(struct mm_struct *mm,
+		unsigned long ua, unsigned long size)
+{
+	struct mm_iommu_table_group_mem_t *mem, *ret = NULL;
+
+	list_for_each_entry_lockless(mem, &mm->context.iommu_group_mem_list,
+			next) {
+		if ((mem->ua <= ua) &&
+				(ua + size <= mem->ua +
+				 (mem->entries << PAGE_SHIFT))) {
+			ret = mem;
+			break;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_lookup_rm);
+
 struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
 		unsigned long ua, unsigned long entries)
 {
@@ -345,6 +364,26 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 }
 EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa);
 
+long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
+		unsigned long ua, unsigned long *hpa)
+{
+	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
+	void *va = &mem->hpas[entry];
+	unsigned long *pa;
+
+	if (entry >= mem->entries)
+		return -EFAULT;
+
+	pa = (void *) vmalloc_to_phys(va);
+	if (!pa)
+		return -EFAULT;
+
+	*hpa = *pa | (ua & ~PAGE_MASK);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa_rm);
+
 long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem)
 {
 	if (atomic64_inc_not_zero(&mem->mapped))
-- 
2.11.0

[PATCH kernel v10 01/10] powerpc/mmu: Add real mode support for IOMMU preregistered memory

[Alexey Kardashevskiy]

This makes mm_iommu_lookup() able to work in realmode by replacing
list_for_each_entry_rcu() (which can do debug stuff which can fail in
real mode) with list_for_each_entry_lockless().

This adds realmode version of mm_iommu_ua_to_hpa() which adds
explicit vmalloc'd-to-linear address conversion.
Unlike mm_iommu_ua_to_hpa(), mm_iommu_ua_to_hpa_rm() can fail.

This changes mm_iommu_preregistered() to receive @mm as in real mode
@current does not always have a correct pointer.

This adds realmode version of mm_iommu_lookup() which receives @mm
(for the same reason as for mm_iommu_preregistered()) and uses
lockless version of list_for_each_entry_rcu().

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
---
 arch/powerpc/include/asm/mmu_context.h |  4 ++++
 arch/powerpc/mm/mmu_context_iommu.c    | 39 ++++++++++++++++++++++++++++++++++
 2 files changed, 43 insertions(+)

diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index b9e3f0aca261..c70c8272523d 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -29,10 +29,14 @@ extern void mm_iommu_init(struct mm_struct *mm);
 extern void mm_iommu_cleanup(struct mm_struct *mm);
 extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm,
 		unsigned long ua, unsigned long size);
+extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(
+		struct mm_struct *mm, unsigned long ua, unsigned long size);
 extern struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
 		unsigned long ua, unsigned long entries);
 extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 		unsigned long ua, unsigned long *hpa);
+extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
+		unsigned long ua, unsigned long *hpa);
 extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);
 extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem);
 #endif
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index 497130c5c742..fc67bd766eaf 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -314,6 +314,25 @@ struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm,
 }
 EXPORT_SYMBOL_GPL(mm_iommu_lookup);
 
+struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(struct mm_struct *mm,
+		unsigned long ua, unsigned long size)
+{
+	struct mm_iommu_table_group_mem_t *mem, *ret = NULL;
+
+	list_for_each_entry_lockless(mem, &mm->context.iommu_group_mem_list,
+			next) {
+		if ((mem->ua <= ua) &&
+				(ua + size <= mem->ua +
+				 (mem->entries << PAGE_SHIFT))) {
+			ret = mem;
+			break;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_lookup_rm);
+
 struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
 		unsigned long ua, unsigned long entries)
 {
@@ -345,6 +364,26 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 }
 EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa);
 
+long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
+		unsigned long ua, unsigned long *hpa)
+{
+	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
+	void *va = &mem->hpas[entry];
+	unsigned long *pa;
+
+	if (entry >= mem->entries)
+		return -EFAULT;
+
+	pa = (void *) vmalloc_to_phys(va);
+	if (!pa)
+		return -EFAULT;
+
+	*hpa = *pa | (ua & ~PAGE_MASK);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa_rm);
+
 long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem)
 {
 	if (atomic64_inc_not_zero(&mem->mapped))
-- 
2.11.0

[PATCH kernel v10 02/10] powerpc/powernv/iommu: Add real mode version of iommu_table_ops::exchange()

[Alexey Kardashevskiy]

In real mode, TCE tables are invalidated using special
cache-inhibited store instructions which are not available in
virtual mode

This defines and implements exchange_rm() callback. This does not
define set_rm/clear_rm/flush_rm callbacks as there is no user for those -
exchange/exchange_rm are only to be used by KVM for VFIO.

The exchange_rm callback is defined for IODA1/IODA2 powernv platforms.

This replaces list_for_each_entry_rcu with its lockless version as
from now on pnv_pci_ioda2_tce_invalidate() can be called in
the real mode too.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
---
 arch/powerpc/include/asm/iommu.h          |  7 +++++++
 arch/powerpc/kernel/iommu.c               | 23 +++++++++++++++++++++++
 arch/powerpc/platforms/powernv/pci-ioda.c | 26 +++++++++++++++++++++++++-
 3 files changed, 55 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 2c1d50792944..4554699aec02 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -64,6 +64,11 @@ struct iommu_table_ops {
 			long index,
 			unsigned long *hpa,
 			enum dma_data_direction *direction);
+	/* Real mode */
+	int (*exchange_rm)(struct iommu_table *tbl,
+			long index,
+			unsigned long *hpa,
+			enum dma_data_direction *direction);
 #endif
 	void (*clear)(struct iommu_table *tbl,
 			long index, long npages);
@@ -208,6 +213,8 @@ extern void iommu_del_device(struct device *dev);
 extern int __init tce_iommu_bus_notifier_init(void);
 extern long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
 		unsigned long *hpa, enum dma_data_direction *direction);
+extern long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry,
+		unsigned long *hpa, enum dma_data_direction *direction);
 #else
 static inline void iommu_register_group(struct iommu_table_group *table_group,
 					int pci_domain_number,
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 5f202a566ec5..9bace5df05d5 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1004,6 +1004,29 @@ long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
 }
 EXPORT_SYMBOL_GPL(iommu_tce_xchg);
 
+long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry,
+		unsigned long *hpa, enum dma_data_direction *direction)
+{
+	long ret;
+
+	ret = tbl->it_ops->exchange_rm(tbl, entry, hpa, direction);
+
+	if (!ret && ((*direction == DMA_FROM_DEVICE) ||
+			(*direction == DMA_BIDIRECTIONAL))) {
+		struct page *pg = realmode_pfn_to_page(*hpa >> PAGE_SHIFT);
+
+		if (likely(pg)) {
+			SetPageDirty(pg);
+		} else {
+			tbl->it_ops->exchange_rm(tbl, entry, hpa, direction);
+			ret = -EFAULT;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_xchg_rm);
+
 int iommu_take_ownership(struct iommu_table *tbl)
 {
 	unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index e36738291c32..572e9c9f1ea0 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1860,6 +1860,17 @@ static int pnv_ioda1_tce_xchg(struct iommu_table *tbl, long index,
 
 	return ret;
 }
+
+static int pnv_ioda1_tce_xchg_rm(struct iommu_table *tbl, long index,
+		unsigned long *hpa, enum dma_data_direction *direction)
+{
+	long ret = pnv_tce_xchg(tbl, index, hpa, direction);
+
+	if (!ret)
+		pnv_pci_p7ioc_tce_invalidate(tbl, index, 1, true);
+
+	return ret;
+}
 #endif
 
 static void pnv_ioda1_tce_free(struct iommu_table *tbl, long index,
@@ -1874,6 +1885,7 @@ static struct iommu_table_ops pnv_ioda1_iommu_ops = {
 	.set = pnv_ioda1_tce_build,
 #ifdef CONFIG_IOMMU_API
 	.exchange = pnv_ioda1_tce_xchg,
+	.exchange_rm = pnv_ioda1_tce_xchg_rm,
 #endif
 	.clear = pnv_ioda1_tce_free,
 	.get = pnv_tce_get,
@@ -1948,7 +1960,7 @@ static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl,
 {
 	struct iommu_table_group_link *tgl;
 
-	list_for_each_entry_rcu(tgl, &tbl->it_group_list, next) {
+	list_for_each_entry_lockless(tgl, &tbl->it_group_list, next) {
 		struct pnv_ioda_pe *pe = container_of(tgl->table_group,
 				struct pnv_ioda_pe, table_group);
 		struct pnv_phb *phb = pe->phb;
@@ -2004,6 +2016,17 @@ static int pnv_ioda2_tce_xchg(struct iommu_table *tbl, long index,
 
 	return ret;
 }
+
+static int pnv_ioda2_tce_xchg_rm(struct iommu_table *tbl, long index,
+		unsigned long *hpa, enum dma_data_direction *direction)
+{
+	long ret = pnv_tce_xchg(tbl, index, hpa, direction);
+
+	if (!ret)
+		pnv_pci_ioda2_tce_invalidate(tbl, index, 1, true);
+
+	return ret;
+}
 #endif
 
 static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index,
@@ -2024,6 +2047,7 @@ static struct iommu_table_ops pnv_ioda2_iommu_ops = {
 	.set = pnv_ioda2_tce_build,
 #ifdef CONFIG_IOMMU_API
 	.exchange = pnv_ioda2_tce_xchg,
+	.exchange_rm = pnv_ioda2_tce_xchg_rm,
 #endif
 	.clear = pnv_ioda2_tce_free,
 	.get = pnv_tce_get,
-- 
2.11.0

[PATCH kernel v10 02/10] powerpc/powernv/iommu: Add real mode version of iommu_table_ops::exchange()

[Alexey Kardashevskiy]

In real mode, TCE tables are invalidated using special
cache-inhibited store instructions which are not available in
virtual mode

This defines and implements exchange_rm() callback. This does not
define set_rm/clear_rm/flush_rm callbacks as there is no user for those -
exchange/exchange_rm are only to be used by KVM for VFIO.

The exchange_rm callback is defined for IODA1/IODA2 powernv platforms.

This replaces list_for_each_entry_rcu with its lockless version as
from now on pnv_pci_ioda2_tce_invalidate() can be called in
the real mode too.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
---
 arch/powerpc/include/asm/iommu.h          |  7 +++++++
 arch/powerpc/kernel/iommu.c               | 23 +++++++++++++++++++++++
 arch/powerpc/platforms/powernv/pci-ioda.c | 26 +++++++++++++++++++++++++-
 3 files changed, 55 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 2c1d50792944..4554699aec02 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -64,6 +64,11 @@ struct iommu_table_ops {
 			long index,
 			unsigned long *hpa,
 			enum dma_data_direction *direction);
+	/* Real mode */
+	int (*exchange_rm)(struct iommu_table *tbl,
+			long index,
+			unsigned long *hpa,
+			enum dma_data_direction *direction);
 #endif
 	void (*clear)(struct iommu_table *tbl,
 			long index, long npages);
@@ -208,6 +213,8 @@ extern void iommu_del_device(struct device *dev);
 extern int __init tce_iommu_bus_notifier_init(void);
 extern long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
 		unsigned long *hpa, enum dma_data_direction *direction);
+extern long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry,
+		unsigned long *hpa, enum dma_data_direction *direction);
 #else
 static inline void iommu_register_group(struct iommu_table_group *table_group,
 					int pci_domain_number,
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 5f202a566ec5..9bace5df05d5 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1004,6 +1004,29 @@ long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
 }
 EXPORT_SYMBOL_GPL(iommu_tce_xchg);
 
+long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry,
+		unsigned long *hpa, enum dma_data_direction *direction)
+{
+	long ret;
+
+	ret = tbl->it_ops->exchange_rm(tbl, entry, hpa, direction);
+
+	if (!ret && ((*direction = DMA_FROM_DEVICE) ||
+			(*direction = DMA_BIDIRECTIONAL))) {
+		struct page *pg = realmode_pfn_to_page(*hpa >> PAGE_SHIFT);
+
+		if (likely(pg)) {
+			SetPageDirty(pg);
+		} else {
+			tbl->it_ops->exchange_rm(tbl, entry, hpa, direction);
+			ret = -EFAULT;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_xchg_rm);
+
 int iommu_take_ownership(struct iommu_table *tbl)
 {
 	unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index e36738291c32..572e9c9f1ea0 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1860,6 +1860,17 @@ static int pnv_ioda1_tce_xchg(struct iommu_table *tbl, long index,
 
 	return ret;
 }
+
+static int pnv_ioda1_tce_xchg_rm(struct iommu_table *tbl, long index,
+		unsigned long *hpa, enum dma_data_direction *direction)
+{
+	long ret = pnv_tce_xchg(tbl, index, hpa, direction);
+
+	if (!ret)
+		pnv_pci_p7ioc_tce_invalidate(tbl, index, 1, true);
+
+	return ret;
+}
 #endif
 
 static void pnv_ioda1_tce_free(struct iommu_table *tbl, long index,
@@ -1874,6 +1885,7 @@ static struct iommu_table_ops pnv_ioda1_iommu_ops = {
 	.set = pnv_ioda1_tce_build,
 #ifdef CONFIG_IOMMU_API
 	.exchange = pnv_ioda1_tce_xchg,
+	.exchange_rm = pnv_ioda1_tce_xchg_rm,
 #endif
 	.clear = pnv_ioda1_tce_free,
 	.get = pnv_tce_get,
@@ -1948,7 +1960,7 @@ static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl,
 {
 	struct iommu_table_group_link *tgl;
 
-	list_for_each_entry_rcu(tgl, &tbl->it_group_list, next) {
+	list_for_each_entry_lockless(tgl, &tbl->it_group_list, next) {
 		struct pnv_ioda_pe *pe = container_of(tgl->table_group,
 				struct pnv_ioda_pe, table_group);
 		struct pnv_phb *phb = pe->phb;
@@ -2004,6 +2016,17 @@ static int pnv_ioda2_tce_xchg(struct iommu_table *tbl, long index,
 
 	return ret;
 }
+
+static int pnv_ioda2_tce_xchg_rm(struct iommu_table *tbl, long index,
+		unsigned long *hpa, enum dma_data_direction *direction)
+{
+	long ret = pnv_tce_xchg(tbl, index, hpa, direction);
+
+	if (!ret)
+		pnv_pci_ioda2_tce_invalidate(tbl, index, 1, true);
+
+	return ret;
+}
 #endif
 
 static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index,
@@ -2024,6 +2047,7 @@ static struct iommu_table_ops pnv_ioda2_iommu_ops = {
 	.set = pnv_ioda2_tce_build,
 #ifdef CONFIG_IOMMU_API
 	.exchange = pnv_ioda2_tce_xchg,
+	.exchange_rm = pnv_ioda2_tce_xchg_rm,
 #endif
 	.clear = pnv_ioda2_tce_free,
 	.get = pnv_tce_get,
-- 
2.11.0

[PATCH kernel v10 03/10] powerpc/iommu/vfio_spapr_tce: Cleanup iommu_table disposal

[Alexey Kardashevskiy]

At the moment iommu_table can be disposed by either calling
iommu_table_free() directly or it_ops::free(); the only implementation
of free() is in IODA2 - pnv_ioda2_table_free() - and it calls
iommu_table_free() anyway.

As we are going to have reference counting on tables, we need an unified
way of disposing tables.

This moves it_ops::free() call into iommu_free_table() and makes use
of the latter. The free() callback now handles only platform-specific
data.

As from now on the iommu_free_table() calls it_ops->free(), we need
to have it_ops initialized before calling iommu_free_table() so this
moves this initialization in pnv_pci_ioda2_create_table().

This should cause no behavioral change.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
---
Changes:
v5:
* moved "tbl->it_ops = &pnv_ioda2_iommu_ops" earlier and updated
the commit log
---
 arch/powerpc/kernel/iommu.c               |  4 ++++
 arch/powerpc/platforms/powernv/pci-ioda.c | 10 ++++------
 drivers/vfio/vfio_iommu_spapr_tce.c       |  2 +-
 3 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 9bace5df05d5..bc142d87130f 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -719,6 +719,9 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
 	if (!tbl)
 		return;
 
+	if (tbl->it_ops->free)
+		tbl->it_ops->free(tbl);
+
 	if (!tbl->it_map) {
 		kfree(tbl);
 		return;
@@ -745,6 +748,7 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
 	/* free table */
 	kfree(tbl);
 }
+EXPORT_SYMBOL_GPL(iommu_free_table);
 
 /* Creates TCEs for a user provided buffer.  The user buffer must be
  * contiguous real kernel storage (not vmalloc).  The address passed here
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 572e9c9f1ea0..5dae54cb11e3 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1424,7 +1424,6 @@ static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe
 		iommu_group_put(pe->table_group.group);
 		BUG_ON(pe->table_group.group);
 	}
-	pnv_pci_ioda2_table_free_pages(tbl);
 	iommu_free_table(tbl, of_node_full_name(dev->dev.of_node));
 }
 
@@ -2040,7 +2039,6 @@ static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index,
 static void pnv_ioda2_table_free(struct iommu_table *tbl)
 {
 	pnv_pci_ioda2_table_free_pages(tbl);
-	iommu_free_table(tbl, "pnv");
 }
 
 static struct iommu_table_ops pnv_ioda2_iommu_ops = {
@@ -2317,6 +2315,8 @@ static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group,
 	if (!tbl)
 		return -ENOMEM;
 
+	tbl->it_ops = &pnv_ioda2_iommu_ops;
+
 	ret = pnv_pci_ioda2_table_alloc_pages(nid,
 			bus_offset, page_shift, window_size,
 			levels, tbl);
@@ -2325,8 +2325,6 @@ static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group,
 		return ret;
 	}
 
-	tbl->it_ops = &pnv_ioda2_iommu_ops;
-
 	*ptbl = tbl;
 
 	return 0;
@@ -2367,7 +2365,7 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
 	if (rc) {
 		pe_err(pe, "Failed to configure 32-bit TCE table, err %ld\n",
 				rc);
-		pnv_ioda2_table_free(tbl);
+		iommu_free_table(tbl, "");
 		return rc;
 	}
 
@@ -2455,7 +2453,7 @@ static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
 	pnv_pci_ioda2_unset_window(&pe->table_group, 0);
 	if (pe->pbus)
 		pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
-	pnv_ioda2_table_free(tbl);
+	iommu_free_table(tbl, "pnv");
 }
 
 static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group)
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index cf3de91fbfe7..fbec7348a7e5 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -680,7 +680,7 @@ static void tce_iommu_free_table(struct tce_container *container,
 	unsigned long pages = tbl->it_allocated_size >> PAGE_SHIFT;
 
 	tce_iommu_userspace_view_free(tbl, container->mm);
-	tbl->it_ops->free(tbl);
+	iommu_free_table(tbl, "");
 	decrement_locked_vm(container->mm, pages);
 }
 
-- 
2.11.0

[PATCH kernel v10 03/10] powerpc/iommu/vfio_spapr_tce: Cleanup iommu_table disposal

[Alexey Kardashevskiy]

At the moment iommu_table can be disposed by either calling
iommu_table_free() directly or it_ops::free(); the only implementation
of free() is in IODA2 - pnv_ioda2_table_free() - and it calls
iommu_table_free() anyway.

As we are going to have reference counting on tables, we need an unified
way of disposing tables.

This moves it_ops::free() call into iommu_free_table() and makes use
of the latter. The free() callback now handles only platform-specific
data.

As from now on the iommu_free_table() calls it_ops->free(), we need
to have it_ops initialized before calling iommu_free_table() so this
moves this initialization in pnv_pci_ioda2_create_table().

This should cause no behavioral change.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
---
Changes:
v5:
* moved "tbl->it_ops = &pnv_ioda2_iommu_ops" earlier and updated
the commit log
---
 arch/powerpc/kernel/iommu.c               |  4 ++++
 arch/powerpc/platforms/powernv/pci-ioda.c | 10 ++++------
 drivers/vfio/vfio_iommu_spapr_tce.c       |  2 +-
 3 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 9bace5df05d5..bc142d87130f 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -719,6 +719,9 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
 	if (!tbl)
 		return;
 
+	if (tbl->it_ops->free)
+		tbl->it_ops->free(tbl);
+
 	if (!tbl->it_map) {
 		kfree(tbl);
 		return;
@@ -745,6 +748,7 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
 	/* free table */
 	kfree(tbl);
 }
+EXPORT_SYMBOL_GPL(iommu_free_table);
 
 /* Creates TCEs for a user provided buffer.  The user buffer must be
  * contiguous real kernel storage (not vmalloc).  The address passed here
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 572e9c9f1ea0..5dae54cb11e3 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1424,7 +1424,6 @@ static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe
 		iommu_group_put(pe->table_group.group);
 		BUG_ON(pe->table_group.group);
 	}
-	pnv_pci_ioda2_table_free_pages(tbl);
 	iommu_free_table(tbl, of_node_full_name(dev->dev.of_node));
 }
 
@@ -2040,7 +2039,6 @@ static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index,
 static void pnv_ioda2_table_free(struct iommu_table *tbl)
 {
 	pnv_pci_ioda2_table_free_pages(tbl);
-	iommu_free_table(tbl, "pnv");
 }
 
 static struct iommu_table_ops pnv_ioda2_iommu_ops = {
@@ -2317,6 +2315,8 @@ static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group,
 	if (!tbl)
 		return -ENOMEM;
 
+	tbl->it_ops = &pnv_ioda2_iommu_ops;
+
 	ret = pnv_pci_ioda2_table_alloc_pages(nid,
 			bus_offset, page_shift, window_size,
 			levels, tbl);
@@ -2325,8 +2325,6 @@ static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group,
 		return ret;
 	}
 
-	tbl->it_ops = &pnv_ioda2_iommu_ops;
-
 	*ptbl = tbl;
 
 	return 0;
@@ -2367,7 +2365,7 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
 	if (rc) {
 		pe_err(pe, "Failed to configure 32-bit TCE table, err %ld\n",
 				rc);
-		pnv_ioda2_table_free(tbl);
+		iommu_free_table(tbl, "");
 		return rc;
 	}
 
@@ -2455,7 +2453,7 @@ static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
 	pnv_pci_ioda2_unset_window(&pe->table_group, 0);
 	if (pe->pbus)
 		pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
-	pnv_ioda2_table_free(tbl);
+	iommu_free_table(tbl, "pnv");
 }
 
 static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group)
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index cf3de91fbfe7..fbec7348a7e5 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -680,7 +680,7 @@ static void tce_iommu_free_table(struct tce_container *container,
 	unsigned long pages = tbl->it_allocated_size >> PAGE_SHIFT;
 
 	tce_iommu_userspace_view_free(tbl, container->mm);
-	tbl->it_ops->free(tbl);
+	iommu_free_table(tbl, "");
 	decrement_locked_vm(container->mm, pages);
 }
 
-- 
2.11.0

[PATCH kernel v10 04/10] powerpc/vfio_spapr_tce: Add reference counting to iommu_table

[Alexey Kardashevskiy]

So far iommu_table obejcts were only used in virtual mode and had
a single owner. We are going to change this by implementing in-kernel
acceleration of DMA mapping requests. The proposed acceleration
will handle requests in real mode and KVM will keep references to tables.

This adds a kref to iommu_table and defines new helpers to update it.
This replaces iommu_free_table() with iommu_tce_table_put() and makes
iommu_free_table() static. iommu_tce_table_get() is not used in this patch
but it will be in the following patch.

Since this touches prototypes, this also removes @node_name parameter as
it has never been really useful on powernv and carrying it for
the pseries platform code to iommu_free_table() seems to be quite
useless as well.

This should cause no behavioral change.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
Changes:
v10:
* iommu_tce_table_get() can fail now if a table is being destroyed, will be
used in 10/10
* iommu_tce_table_put() returns what kref_put() returned
* iommu_tce_table_put() got WARN_ON(!tbl) as the callers already check
for it and do not call _put() when tbl==NULL

v9:
* s/iommu_table_get/iommu_tce_table_get/ and
s/iommu_table_put/iommu_tce_table_put/ -- so I removed r-b/a-b
---
 arch/powerpc/include/asm/iommu.h          |  5 +++--
 arch/powerpc/kernel/iommu.c               | 27 ++++++++++++++++++++++-----
 arch/powerpc/platforms/powernv/pci-ioda.c | 14 +++++++-------
 arch/powerpc/platforms/powernv/pci.c      |  1 +
 arch/powerpc/platforms/pseries/iommu.c    |  3 ++-
 arch/powerpc/platforms/pseries/vio.c      |  2 +-
 drivers/vfio/vfio_iommu_spapr_tce.c       |  2 +-
 7 files changed, 37 insertions(+), 17 deletions(-)

diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 4554699aec02..d96142572e6d 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -119,6 +119,7 @@ struct iommu_table {
 	struct list_head it_group_list;/* List of iommu_table_group_link */
 	unsigned long *it_userspace; /* userspace view of the table */
 	struct iommu_table_ops *it_ops;
+	struct kref    it_kref;
 };
 
 #define IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry) \
@@ -151,8 +152,8 @@ static inline void *get_iommu_table_base(struct device *dev)
 
 extern int dma_iommu_dma_supported(struct device *dev, u64 mask);
 
-/* Frees table for an individual device node */
-extern void iommu_free_table(struct iommu_table *tbl, const char *node_name);
+extern struct iommu_table *iommu_tce_table_get(struct iommu_table *tbl);
+extern int iommu_tce_table_put(struct iommu_table *tbl);
 
 /* Initializes an iommu_table based in values set in the passed-in
  * structure
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index bc142d87130f..af915da5e03a 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -711,13 +711,13 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
 	return tbl;
 }
 
-void iommu_free_table(struct iommu_table *tbl, const char *node_name)
+static void iommu_table_free(struct kref *kref)
 {
 	unsigned long bitmap_sz;
 	unsigned int order;
+	struct iommu_table *tbl;
 
-	if (!tbl)
-		return;
+	tbl = container_of(kref, struct iommu_table, it_kref);
 
 	if (tbl->it_ops->free)
 		tbl->it_ops->free(tbl);
@@ -736,7 +736,7 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
 
 	/* 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);
+		pr_warn("%s: Unexpected TCEs\n", __func__);
 
 	/* calculate bitmap size in bytes */
 	bitmap_sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long);
@@ -748,7 +748,24 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
 	/* free table */
 	kfree(tbl);
 }
-EXPORT_SYMBOL_GPL(iommu_free_table);
+
+struct iommu_table *iommu_tce_table_get(struct iommu_table *tbl)
+{
+	if (kref_get_unless_zero(&tbl->it_kref))
+		return tbl;
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_table_get);
+
+int iommu_tce_table_put(struct iommu_table *tbl)
+{
+	if (WARN_ON(!tbl))
+		return 0;
+
+	return kref_put(&tbl->it_kref, iommu_table_free);
+}
+EXPORT_SYMBOL_GPL(iommu_tce_table_put);
 
 /* Creates TCEs for a user provided buffer.  The user buffer must be
  * contiguous real kernel storage (not vmalloc).  The address passed here
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 5dae54cb11e3..ee4cdb5b893f 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1424,7 +1424,7 @@ static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe
 		iommu_group_put(pe->table_group.group);
 		BUG_ON(pe->table_group.group);
 	}
-	iommu_free_table(tbl, of_node_full_name(dev->dev.of_node));
+	iommu_tce_table_put(tbl);
 }
 
 static void pnv_ioda_release_vf_PE(struct pci_dev *pdev)
@@ -2225,7 +2225,7 @@ static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb,
 		__free_pages(tce_mem, get_order(tce32_segsz * segs));
 	if (tbl) {
 		pnv_pci_unlink_table_and_group(tbl, &pe->table_group);
-		iommu_free_table(tbl, "pnv");
+		iommu_tce_table_put(tbl);
 	}
 }
 
@@ -2321,7 +2321,7 @@ static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group,
 			bus_offset, page_shift, window_size,
 			levels, tbl);
 	if (ret) {
-		iommu_free_table(tbl, "pnv");
+		iommu_tce_table_put(tbl);
 		return ret;
 	}
 
@@ -2365,7 +2365,7 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
 	if (rc) {
 		pe_err(pe, "Failed to configure 32-bit TCE table, err %ld\n",
 				rc);
-		iommu_free_table(tbl, "");
+		iommu_tce_table_put(tbl);
 		return rc;
 	}
 
@@ -2453,7 +2453,7 @@ static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
 	pnv_pci_ioda2_unset_window(&pe->table_group, 0);
 	if (pe->pbus)
 		pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
-	iommu_free_table(tbl, "pnv");
+	iommu_tce_table_put(tbl);
 }
 
 static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group)
@@ -3428,7 +3428,7 @@ static void pnv_pci_ioda1_release_pe_dma(struct pnv_ioda_pe *pe)
 	}
 
 	free_pages(tbl->it_base, get_order(tbl->it_size << 3));
-	iommu_free_table(tbl, "pnv");
+	iommu_tce_table_put(tbl);
 }
 
 static void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe)
@@ -3455,7 +3455,7 @@ static void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe)
 	}
 
 	pnv_pci_ioda2_table_free_pages(tbl);
-	iommu_free_table(tbl, "pnv");
+	iommu_tce_table_put(tbl);
 }
 
 static void pnv_ioda_free_pe_seg(struct pnv_ioda_pe *pe,
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index eb835e977e33..204a829ff506 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -767,6 +767,7 @@ struct iommu_table *pnv_pci_table_alloc(int nid)
 
 	tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, nid);
 	INIT_LIST_HEAD_RCU(&tbl->it_group_list);
+	kref_init(&tbl->it_kref);
 
 	return tbl;
 }
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 4d757eaa46bf..7ce5db209abf 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -74,6 +74,7 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node)
 		goto fail_exit;
 
 	INIT_LIST_HEAD_RCU(&tbl->it_group_list);
+	kref_init(&tbl->it_kref);
 	tgl->table_group = table_group;
 	list_add_rcu(&tgl->next, &tbl->it_group_list);
 
@@ -115,7 +116,7 @@ static void iommu_pseries_free_group(struct iommu_table_group *table_group,
 		BUG_ON(table_group->group);
 	}
 #endif
-	iommu_free_table(tbl, node_name);
+	iommu_tce_table_put(tbl);
 
 	kfree(table_group);
 }
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 720493932486..28b09fd797ec 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -1318,7 +1318,7 @@ static void vio_dev_release(struct device *dev)
 	struct iommu_table *tbl = get_iommu_table_base(dev);
 
 	if (tbl)
-		iommu_free_table(tbl, of_node_full_name(dev->of_node));
+		iommu_tce_table_put(tbl);
 	of_node_put(dev->of_node);
 	kfree(to_vio_dev(dev));
 }
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index fbec7348a7e5..8031d3a55a17 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -680,7 +680,7 @@ static void tce_iommu_free_table(struct tce_container *container,
 	unsigned long pages = tbl->it_allocated_size >> PAGE_SHIFT;
 
 	tce_iommu_userspace_view_free(tbl, container->mm);
-	iommu_free_table(tbl, "");
+	iommu_tce_table_put(tbl);
 	decrement_locked_vm(container->mm, pages);
 }
 
-- 
2.11.0

[PATCH kernel v10 04/10] powerpc/vfio_spapr_tce: Add reference counting to iommu_table

[Alexey Kardashevskiy]

So far iommu_table obejcts were only used in virtual mode and had
a single owner. We are going to change this by implementing in-kernel
acceleration of DMA mapping requests. The proposed acceleration
will handle requests in real mode and KVM will keep references to tables.

This adds a kref to iommu_table and defines new helpers to update it.
This replaces iommu_free_table() with iommu_tce_table_put() and makes
iommu_free_table() static. iommu_tce_table_get() is not used in this patch
but it will be in the following patch.

Since this touches prototypes, this also removes @node_name parameter as
it has never been really useful on powernv and carrying it for
the pseries platform code to iommu_free_table() seems to be quite
useless as well.

This should cause no behavioral change.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
Changes:
v10:
* iommu_tce_table_get() can fail now if a table is being destroyed, will be
used in 10/10
* iommu_tce_table_put() returns what kref_put() returned
* iommu_tce_table_put() got WARN_ON(!tbl) as the callers already check
for it and do not call _put() when tbl=NULL

v9:
* s/iommu_table_get/iommu_tce_table_get/ and
s/iommu_table_put/iommu_tce_table_put/ -- so I removed r-b/a-b
---
 arch/powerpc/include/asm/iommu.h          |  5 +++--
 arch/powerpc/kernel/iommu.c               | 27 ++++++++++++++++++++++-----
 arch/powerpc/platforms/powernv/pci-ioda.c | 14 +++++++-------
 arch/powerpc/platforms/powernv/pci.c      |  1 +
 arch/powerpc/platforms/pseries/iommu.c    |  3 ++-
 arch/powerpc/platforms/pseries/vio.c      |  2 +-
 drivers/vfio/vfio_iommu_spapr_tce.c       |  2 +-
 7 files changed, 37 insertions(+), 17 deletions(-)

diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 4554699aec02..d96142572e6d 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -119,6 +119,7 @@ struct iommu_table {
 	struct list_head it_group_list;/* List of iommu_table_group_link */
 	unsigned long *it_userspace; /* userspace view of the table */
 	struct iommu_table_ops *it_ops;
+	struct kref    it_kref;
 };
 
 #define IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry) \
@@ -151,8 +152,8 @@ static inline void *get_iommu_table_base(struct device *dev)
 
 extern int dma_iommu_dma_supported(struct device *dev, u64 mask);
 
-/* Frees table for an individual device node */
-extern void iommu_free_table(struct iommu_table *tbl, const char *node_name);
+extern struct iommu_table *iommu_tce_table_get(struct iommu_table *tbl);
+extern int iommu_tce_table_put(struct iommu_table *tbl);
 
 /* Initializes an iommu_table based in values set in the passed-in
  * structure
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index bc142d87130f..af915da5e03a 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -711,13 +711,13 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
 	return tbl;
 }
 
-void iommu_free_table(struct iommu_table *tbl, const char *node_name)
+static void iommu_table_free(struct kref *kref)
 {
 	unsigned long bitmap_sz;
 	unsigned int order;
+	struct iommu_table *tbl;
 
-	if (!tbl)
-		return;
+	tbl = container_of(kref, struct iommu_table, it_kref);
 
 	if (tbl->it_ops->free)
 		tbl->it_ops->free(tbl);
@@ -736,7 +736,7 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
 
 	/* 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);
+		pr_warn("%s: Unexpected TCEs\n", __func__);
 
 	/* calculate bitmap size in bytes */
 	bitmap_sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long);
@@ -748,7 +748,24 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
 	/* free table */
 	kfree(tbl);
 }
-EXPORT_SYMBOL_GPL(iommu_free_table);
+
+struct iommu_table *iommu_tce_table_get(struct iommu_table *tbl)
+{
+	if (kref_get_unless_zero(&tbl->it_kref))
+		return tbl;
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_table_get);
+
+int iommu_tce_table_put(struct iommu_table *tbl)
+{
+	if (WARN_ON(!tbl))
+		return 0;
+
+	return kref_put(&tbl->it_kref, iommu_table_free);
+}
+EXPORT_SYMBOL_GPL(iommu_tce_table_put);
 
 /* Creates TCEs for a user provided buffer.  The user buffer must be
  * contiguous real kernel storage (not vmalloc).  The address passed here
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 5dae54cb11e3..ee4cdb5b893f 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1424,7 +1424,7 @@ static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe
 		iommu_group_put(pe->table_group.group);
 		BUG_ON(pe->table_group.group);
 	}
-	iommu_free_table(tbl, of_node_full_name(dev->dev.of_node));
+	iommu_tce_table_put(tbl);
 }
 
 static void pnv_ioda_release_vf_PE(struct pci_dev *pdev)
@@ -2225,7 +2225,7 @@ static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb,
 		__free_pages(tce_mem, get_order(tce32_segsz * segs));
 	if (tbl) {
 		pnv_pci_unlink_table_and_group(tbl, &pe->table_group);
-		iommu_free_table(tbl, "pnv");
+		iommu_tce_table_put(tbl);
 	}
 }
 
@@ -2321,7 +2321,7 @@ static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group,
 			bus_offset, page_shift, window_size,
 			levels, tbl);
 	if (ret) {
-		iommu_free_table(tbl, "pnv");
+		iommu_tce_table_put(tbl);
 		return ret;
 	}
 
@@ -2365,7 +2365,7 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
 	if (rc) {
 		pe_err(pe, "Failed to configure 32-bit TCE table, err %ld\n",
 				rc);
-		iommu_free_table(tbl, "");
+		iommu_tce_table_put(tbl);
 		return rc;
 	}
 
@@ -2453,7 +2453,7 @@ static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
 	pnv_pci_ioda2_unset_window(&pe->table_group, 0);
 	if (pe->pbus)
 		pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
-	iommu_free_table(tbl, "pnv");
+	iommu_tce_table_put(tbl);
 }
 
 static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group)
@@ -3428,7 +3428,7 @@ static void pnv_pci_ioda1_release_pe_dma(struct pnv_ioda_pe *pe)
 	}
 
 	free_pages(tbl->it_base, get_order(tbl->it_size << 3));
-	iommu_free_table(tbl, "pnv");
+	iommu_tce_table_put(tbl);
 }
 
 static void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe)
@@ -3455,7 +3455,7 @@ static void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe)
 	}
 
 	pnv_pci_ioda2_table_free_pages(tbl);
-	iommu_free_table(tbl, "pnv");
+	iommu_tce_table_put(tbl);
 }
 
 static void pnv_ioda_free_pe_seg(struct pnv_ioda_pe *pe,
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index eb835e977e33..204a829ff506 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -767,6 +767,7 @@ struct iommu_table *pnv_pci_table_alloc(int nid)
 
 	tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, nid);
 	INIT_LIST_HEAD_RCU(&tbl->it_group_list);
+	kref_init(&tbl->it_kref);
 
 	return tbl;
 }
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 4d757eaa46bf..7ce5db209abf 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -74,6 +74,7 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node)
 		goto fail_exit;
 
 	INIT_LIST_HEAD_RCU(&tbl->it_group_list);
+	kref_init(&tbl->it_kref);
 	tgl->table_group = table_group;
 	list_add_rcu(&tgl->next, &tbl->it_group_list);
 
@@ -115,7 +116,7 @@ static void iommu_pseries_free_group(struct iommu_table_group *table_group,
 		BUG_ON(table_group->group);
 	}
 #endif
-	iommu_free_table(tbl, node_name);
+	iommu_tce_table_put(tbl);
 
 	kfree(table_group);
 }
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 720493932486..28b09fd797ec 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -1318,7 +1318,7 @@ static void vio_dev_release(struct device *dev)
 	struct iommu_table *tbl = get_iommu_table_base(dev);
 
 	if (tbl)
-		iommu_free_table(tbl, of_node_full_name(dev->of_node));
+		iommu_tce_table_put(tbl);
 	of_node_put(dev->of_node);
 	kfree(to_vio_dev(dev));
 }
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index fbec7348a7e5..8031d3a55a17 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -680,7 +680,7 @@ static void tce_iommu_free_table(struct tce_container *container,
 	unsigned long pages = tbl->it_allocated_size >> PAGE_SHIFT;
 
 	tce_iommu_userspace_view_free(tbl, container->mm);
-	iommu_free_table(tbl, "");
+	iommu_tce_table_put(tbl);
 	decrement_locked_vm(container->mm, pages);
 }
 
-- 
2.11.0

Re: [PATCH kernel v10 04/10] powerpc/vfio_spapr_tce: Add reference counting to iommu_table

[David Gibson]

[-- Attachment #1: Type: text/plain, Size: 9905 bytes --]

On Fri, Mar 17, 2017 at 04:09:53PM +1100, Alexey Kardashevskiy wrote:
> So far iommu_table obejcts were only used in virtual mode and had
> a single owner. We are going to change this by implementing in-kernel
> acceleration of DMA mapping requests. The proposed acceleration
> will handle requests in real mode and KVM will keep references to tables.
> 
> This adds a kref to iommu_table and defines new helpers to update it.
> This replaces iommu_free_table() with iommu_tce_table_put() and makes
> iommu_free_table() static. iommu_tce_table_get() is not used in this patch
> but it will be in the following patch.
> 
> Since this touches prototypes, this also removes @node_name parameter as
> it has never been really useful on powernv and carrying it for
> the pseries platform code to iommu_free_table() seems to be quite
> useless as well.
> 
> This should cause no behavioral change.
> 
> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>

> ---
> Changes:
> v10:
> * iommu_tce_table_get() can fail now if a table is being destroyed, will be
> used in 10/10
> * iommu_tce_table_put() returns what kref_put() returned
> * iommu_tce_table_put() got WARN_ON(!tbl) as the callers already check
> for it and do not call _put() when tbl==NULL
> 
> v9:
> * s/iommu_table_get/iommu_tce_table_get/ and
> s/iommu_table_put/iommu_tce_table_put/ -- so I removed r-b/a-b
> ---
>  arch/powerpc/include/asm/iommu.h          |  5 +++--
>  arch/powerpc/kernel/iommu.c               | 27 ++++++++++++++++++++++-----
>  arch/powerpc/platforms/powernv/pci-ioda.c | 14 +++++++-------
>  arch/powerpc/platforms/powernv/pci.c      |  1 +
>  arch/powerpc/platforms/pseries/iommu.c    |  3 ++-
>  arch/powerpc/platforms/pseries/vio.c      |  2 +-
>  drivers/vfio/vfio_iommu_spapr_tce.c       |  2 +-
>  7 files changed, 37 insertions(+), 17 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
> index 4554699aec02..d96142572e6d 100644
> --- a/arch/powerpc/include/asm/iommu.h
> +++ b/arch/powerpc/include/asm/iommu.h
> @@ -119,6 +119,7 @@ struct iommu_table {
>  	struct list_head it_group_list;/* List of iommu_table_group_link */
>  	unsigned long *it_userspace; /* userspace view of the table */
>  	struct iommu_table_ops *it_ops;
> +	struct kref    it_kref;
>  };
>  
>  #define IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry) \
> @@ -151,8 +152,8 @@ static inline void *get_iommu_table_base(struct device *dev)
>  
>  extern int dma_iommu_dma_supported(struct device *dev, u64 mask);
>  
> -/* Frees table for an individual device node */
> -extern void iommu_free_table(struct iommu_table *tbl, const char *node_name);
> +extern struct iommu_table *iommu_tce_table_get(struct iommu_table *tbl);
> +extern int iommu_tce_table_put(struct iommu_table *tbl);
>  
>  /* Initializes an iommu_table based in values set in the passed-in
>   * structure
> diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
> index bc142d87130f..af915da5e03a 100644
> --- a/arch/powerpc/kernel/iommu.c
> +++ b/arch/powerpc/kernel/iommu.c
> @@ -711,13 +711,13 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
>  	return tbl;
>  }
>  
> -void iommu_free_table(struct iommu_table *tbl, const char *node_name)
> +static void iommu_table_free(struct kref *kref)
>  {
>  	unsigned long bitmap_sz;
>  	unsigned int order;
> +	struct iommu_table *tbl;
>  
> -	if (!tbl)
> -		return;
> +	tbl = container_of(kref, struct iommu_table, it_kref);
>  
>  	if (tbl->it_ops->free)
>  		tbl->it_ops->free(tbl);
> @@ -736,7 +736,7 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
>  
>  	/* 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);
> +		pr_warn("%s: Unexpected TCEs\n", __func__);
>  
>  	/* calculate bitmap size in bytes */
>  	bitmap_sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long);
> @@ -748,7 +748,24 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
>  	/* free table */
>  	kfree(tbl);
>  }
> -EXPORT_SYMBOL_GPL(iommu_free_table);
> +
> +struct iommu_table *iommu_tce_table_get(struct iommu_table *tbl)
> +{
> +	if (kref_get_unless_zero(&tbl->it_kref))
> +		return tbl;
> +
> +	return NULL;
> +}
> +EXPORT_SYMBOL_GPL(iommu_tce_table_get);
> +
> +int iommu_tce_table_put(struct iommu_table *tbl)
> +{
> +	if (WARN_ON(!tbl))
> +		return 0;
> +
> +	return kref_put(&tbl->it_kref, iommu_table_free);
> +}
> +EXPORT_SYMBOL_GPL(iommu_tce_table_put);
>  
>  /* Creates TCEs for a user provided buffer.  The user buffer must be
>   * contiguous real kernel storage (not vmalloc).  The address passed here
> diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
> index 5dae54cb11e3..ee4cdb5b893f 100644
> --- a/arch/powerpc/platforms/powernv/pci-ioda.c
> +++ b/arch/powerpc/platforms/powernv/pci-ioda.c
> @@ -1424,7 +1424,7 @@ static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe
>  		iommu_group_put(pe->table_group.group);
>  		BUG_ON(pe->table_group.group);
>  	}
> -	iommu_free_table(tbl, of_node_full_name(dev->dev.of_node));
> +	iommu_tce_table_put(tbl);
>  }
>  
>  static void pnv_ioda_release_vf_PE(struct pci_dev *pdev)
> @@ -2225,7 +2225,7 @@ static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb,
>  		__free_pages(tce_mem, get_order(tce32_segsz * segs));
>  	if (tbl) {
>  		pnv_pci_unlink_table_and_group(tbl, &pe->table_group);
> -		iommu_free_table(tbl, "pnv");
> +		iommu_tce_table_put(tbl);
>  	}
>  }
>  
> @@ -2321,7 +2321,7 @@ static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group,
>  			bus_offset, page_shift, window_size,
>  			levels, tbl);
>  	if (ret) {
> -		iommu_free_table(tbl, "pnv");
> +		iommu_tce_table_put(tbl);
>  		return ret;
>  	}
>  
> @@ -2365,7 +2365,7 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
>  	if (rc) {
>  		pe_err(pe, "Failed to configure 32-bit TCE table, err %ld\n",
>  				rc);
> -		iommu_free_table(tbl, "");
> +		iommu_tce_table_put(tbl);
>  		return rc;
>  	}
>  
> @@ -2453,7 +2453,7 @@ static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
>  	pnv_pci_ioda2_unset_window(&pe->table_group, 0);
>  	if (pe->pbus)
>  		pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
> -	iommu_free_table(tbl, "pnv");
> +	iommu_tce_table_put(tbl);
>  }
>  
>  static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group)
> @@ -3428,7 +3428,7 @@ static void pnv_pci_ioda1_release_pe_dma(struct pnv_ioda_pe *pe)
>  	}
>  
>  	free_pages(tbl->it_base, get_order(tbl->it_size << 3));
> -	iommu_free_table(tbl, "pnv");
> +	iommu_tce_table_put(tbl);
>  }
>  
>  static void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe)
> @@ -3455,7 +3455,7 @@ static void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe)
>  	}
>  
>  	pnv_pci_ioda2_table_free_pages(tbl);
> -	iommu_free_table(tbl, "pnv");
> +	iommu_tce_table_put(tbl);
>  }
>  
>  static void pnv_ioda_free_pe_seg(struct pnv_ioda_pe *pe,
> diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
> index eb835e977e33..204a829ff506 100644
> --- a/arch/powerpc/platforms/powernv/pci.c
> +++ b/arch/powerpc/platforms/powernv/pci.c
> @@ -767,6 +767,7 @@ struct iommu_table *pnv_pci_table_alloc(int nid)
>  
>  	tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, nid);
>  	INIT_LIST_HEAD_RCU(&tbl->it_group_list);
> +	kref_init(&tbl->it_kref);
>  
>  	return tbl;
>  }
> diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
> index 4d757eaa46bf..7ce5db209abf 100644
> --- a/arch/powerpc/platforms/pseries/iommu.c
> +++ b/arch/powerpc/platforms/pseries/iommu.c
> @@ -74,6 +74,7 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node)
>  		goto fail_exit;
>  
>  	INIT_LIST_HEAD_RCU(&tbl->it_group_list);
> +	kref_init(&tbl->it_kref);
>  	tgl->table_group = table_group;
>  	list_add_rcu(&tgl->next, &tbl->it_group_list);
>  
> @@ -115,7 +116,7 @@ static void iommu_pseries_free_group(struct iommu_table_group *table_group,
>  		BUG_ON(table_group->group);
>  	}
>  #endif
> -	iommu_free_table(tbl, node_name);
> +	iommu_tce_table_put(tbl);
>  
>  	kfree(table_group);
>  }
> diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
> index 720493932486..28b09fd797ec 100644
> --- a/arch/powerpc/platforms/pseries/vio.c
> +++ b/arch/powerpc/platforms/pseries/vio.c
> @@ -1318,7 +1318,7 @@ static void vio_dev_release(struct device *dev)
>  	struct iommu_table *tbl = get_iommu_table_base(dev);
>  
>  	if (tbl)
> -		iommu_free_table(tbl, of_node_full_name(dev->of_node));
> +		iommu_tce_table_put(tbl);
>  	of_node_put(dev->of_node);
>  	kfree(to_vio_dev(dev));
>  }
> diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
> index fbec7348a7e5..8031d3a55a17 100644
> --- a/drivers/vfio/vfio_iommu_spapr_tce.c
> +++ b/drivers/vfio/vfio_iommu_spapr_tce.c
> @@ -680,7 +680,7 @@ static void tce_iommu_free_table(struct tce_container *container,
>  	unsigned long pages = tbl->it_allocated_size >> PAGE_SHIFT;
>  
>  	tce_iommu_userspace_view_free(tbl, container->mm);
> -	iommu_free_table(tbl, "");
> +	iommu_tce_table_put(tbl);
>  	decrement_locked_vm(container->mm, pages);
>  }
>  

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 819 bytes --]

Re: [PATCH kernel v10 04/10] powerpc/vfio_spapr_tce: Add reference counting to iommu_table

[David Gibson]

[-- Attachment #1: Type: text/plain, Size: 9905 bytes --]

On Fri, Mar 17, 2017 at 04:09:53PM +1100, Alexey Kardashevskiy wrote:
> So far iommu_table obejcts were only used in virtual mode and had
> a single owner. We are going to change this by implementing in-kernel
> acceleration of DMA mapping requests. The proposed acceleration
> will handle requests in real mode and KVM will keep references to tables.
> 
> This adds a kref to iommu_table and defines new helpers to update it.
> This replaces iommu_free_table() with iommu_tce_table_put() and makes
> iommu_free_table() static. iommu_tce_table_get() is not used in this patch
> but it will be in the following patch.
> 
> Since this touches prototypes, this also removes @node_name parameter as
> it has never been really useful on powernv and carrying it for
> the pseries platform code to iommu_free_table() seems to be quite
> useless as well.
> 
> This should cause no behavioral change.
> 
> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>

> ---
> Changes:
> v10:
> * iommu_tce_table_get() can fail now if a table is being destroyed, will be
> used in 10/10
> * iommu_tce_table_put() returns what kref_put() returned
> * iommu_tce_table_put() got WARN_ON(!tbl) as the callers already check
> for it and do not call _put() when tbl==NULL
> 
> v9:
> * s/iommu_table_get/iommu_tce_table_get/ and
> s/iommu_table_put/iommu_tce_table_put/ -- so I removed r-b/a-b
> ---
>  arch/powerpc/include/asm/iommu.h          |  5 +++--
>  arch/powerpc/kernel/iommu.c               | 27 ++++++++++++++++++++++-----
>  arch/powerpc/platforms/powernv/pci-ioda.c | 14 +++++++-------
>  arch/powerpc/platforms/powernv/pci.c      |  1 +
>  arch/powerpc/platforms/pseries/iommu.c    |  3 ++-
>  arch/powerpc/platforms/pseries/vio.c      |  2 +-
>  drivers/vfio/vfio_iommu_spapr_tce.c       |  2 +-
>  7 files changed, 37 insertions(+), 17 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
> index 4554699aec02..d96142572e6d 100644
> --- a/arch/powerpc/include/asm/iommu.h
> +++ b/arch/powerpc/include/asm/iommu.h
> @@ -119,6 +119,7 @@ struct iommu_table {
>  	struct list_head it_group_list;/* List of iommu_table_group_link */
>  	unsigned long *it_userspace; /* userspace view of the table */
>  	struct iommu_table_ops *it_ops;
> +	struct kref    it_kref;
>  };
>  
>  #define IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry) \
> @@ -151,8 +152,8 @@ static inline void *get_iommu_table_base(struct device *dev)
>  
>  extern int dma_iommu_dma_supported(struct device *dev, u64 mask);
>  
> -/* Frees table for an individual device node */
> -extern void iommu_free_table(struct iommu_table *tbl, const char *node_name);
> +extern struct iommu_table *iommu_tce_table_get(struct iommu_table *tbl);
> +extern int iommu_tce_table_put(struct iommu_table *tbl);
>  
>  /* Initializes an iommu_table based in values set in the passed-in
>   * structure
> diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
> index bc142d87130f..af915da5e03a 100644
> --- a/arch/powerpc/kernel/iommu.c
> +++ b/arch/powerpc/kernel/iommu.c
> @@ -711,13 +711,13 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
>  	return tbl;
>  }
>  
> -void iommu_free_table(struct iommu_table *tbl, const char *node_name)
> +static void iommu_table_free(struct kref *kref)
>  {
>  	unsigned long bitmap_sz;
>  	unsigned int order;
> +	struct iommu_table *tbl;
>  
> -	if (!tbl)
> -		return;
> +	tbl = container_of(kref, struct iommu_table, it_kref);
>  
>  	if (tbl->it_ops->free)
>  		tbl->it_ops->free(tbl);
> @@ -736,7 +736,7 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
>  
>  	/* 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);
> +		pr_warn("%s: Unexpected TCEs\n", __func__);
>  
>  	/* calculate bitmap size in bytes */
>  	bitmap_sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long);
> @@ -748,7 +748,24 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
>  	/* free table */
>  	kfree(tbl);
>  }
> -EXPORT_SYMBOL_GPL(iommu_free_table);
> +
> +struct iommu_table *iommu_tce_table_get(struct iommu_table *tbl)
> +{
> +	if (kref_get_unless_zero(&tbl->it_kref))
> +		return tbl;
> +
> +	return NULL;
> +}
> +EXPORT_SYMBOL_GPL(iommu_tce_table_get);
> +
> +int iommu_tce_table_put(struct iommu_table *tbl)
> +{
> +	if (WARN_ON(!tbl))
> +		return 0;
> +
> +	return kref_put(&tbl->it_kref, iommu_table_free);
> +}
> +EXPORT_SYMBOL_GPL(iommu_tce_table_put);
>  
>  /* Creates TCEs for a user provided buffer.  The user buffer must be
>   * contiguous real kernel storage (not vmalloc).  The address passed here
> diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
> index 5dae54cb11e3..ee4cdb5b893f 100644
> --- a/arch/powerpc/platforms/powernv/pci-ioda.c
> +++ b/arch/powerpc/platforms/powernv/pci-ioda.c
> @@ -1424,7 +1424,7 @@ static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe
>  		iommu_group_put(pe->table_group.group);
>  		BUG_ON(pe->table_group.group);
>  	}
> -	iommu_free_table(tbl, of_node_full_name(dev->dev.of_node));
> +	iommu_tce_table_put(tbl);
>  }
>  
>  static void pnv_ioda_release_vf_PE(struct pci_dev *pdev)
> @@ -2225,7 +2225,7 @@ static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb,
>  		__free_pages(tce_mem, get_order(tce32_segsz * segs));
>  	if (tbl) {
>  		pnv_pci_unlink_table_and_group(tbl, &pe->table_group);
> -		iommu_free_table(tbl, "pnv");
> +		iommu_tce_table_put(tbl);
>  	}
>  }
>  
> @@ -2321,7 +2321,7 @@ static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group,
>  			bus_offset, page_shift, window_size,
>  			levels, tbl);
>  	if (ret) {
> -		iommu_free_table(tbl, "pnv");
> +		iommu_tce_table_put(tbl);
>  		return ret;
>  	}
>  
> @@ -2365,7 +2365,7 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
>  	if (rc) {
>  		pe_err(pe, "Failed to configure 32-bit TCE table, err %ld\n",
>  				rc);
> -		iommu_free_table(tbl, "");
> +		iommu_tce_table_put(tbl);
>  		return rc;
>  	}
>  
> @@ -2453,7 +2453,7 @@ static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
>  	pnv_pci_ioda2_unset_window(&pe->table_group, 0);
>  	if (pe->pbus)
>  		pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
> -	iommu_free_table(tbl, "pnv");
> +	iommu_tce_table_put(tbl);
>  }
>  
>  static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group)
> @@ -3428,7 +3428,7 @@ static void pnv_pci_ioda1_release_pe_dma(struct pnv_ioda_pe *pe)
>  	}
>  
>  	free_pages(tbl->it_base, get_order(tbl->it_size << 3));
> -	iommu_free_table(tbl, "pnv");
> +	iommu_tce_table_put(tbl);
>  }
>  
>  static void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe)
> @@ -3455,7 +3455,7 @@ static void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe)
>  	}
>  
>  	pnv_pci_ioda2_table_free_pages(tbl);
> -	iommu_free_table(tbl, "pnv");
> +	iommu_tce_table_put(tbl);
>  }
>  
>  static void pnv_ioda_free_pe_seg(struct pnv_ioda_pe *pe,
> diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
> index eb835e977e33..204a829ff506 100644
> --- a/arch/powerpc/platforms/powernv/pci.c
> +++ b/arch/powerpc/platforms/powernv/pci.c
> @@ -767,6 +767,7 @@ struct iommu_table *pnv_pci_table_alloc(int nid)
>  
>  	tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, nid);
>  	INIT_LIST_HEAD_RCU(&tbl->it_group_list);
> +	kref_init(&tbl->it_kref);
>  
>  	return tbl;
>  }
> diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
> index 4d757eaa46bf..7ce5db209abf 100644
> --- a/arch/powerpc/platforms/pseries/iommu.c
> +++ b/arch/powerpc/platforms/pseries/iommu.c
> @@ -74,6 +74,7 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node)
>  		goto fail_exit;
>  
>  	INIT_LIST_HEAD_RCU(&tbl->it_group_list);
> +	kref_init(&tbl->it_kref);
>  	tgl->table_group = table_group;
>  	list_add_rcu(&tgl->next, &tbl->it_group_list);
>  
> @@ -115,7 +116,7 @@ static void iommu_pseries_free_group(struct iommu_table_group *table_group,
>  		BUG_ON(table_group->group);
>  	}
>  #endif
> -	iommu_free_table(tbl, node_name);
> +	iommu_tce_table_put(tbl);
>  
>  	kfree(table_group);
>  }
> diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
> index 720493932486..28b09fd797ec 100644
> --- a/arch/powerpc/platforms/pseries/vio.c
> +++ b/arch/powerpc/platforms/pseries/vio.c
> @@ -1318,7 +1318,7 @@ static void vio_dev_release(struct device *dev)
>  	struct iommu_table *tbl = get_iommu_table_base(dev);
>  
>  	if (tbl)
> -		iommu_free_table(tbl, of_node_full_name(dev->of_node));
> +		iommu_tce_table_put(tbl);
>  	of_node_put(dev->of_node);
>  	kfree(to_vio_dev(dev));
>  }
> diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
> index fbec7348a7e5..8031d3a55a17 100644
> --- a/drivers/vfio/vfio_iommu_spapr_tce.c
> +++ b/drivers/vfio/vfio_iommu_spapr_tce.c
> @@ -680,7 +680,7 @@ static void tce_iommu_free_table(struct tce_container *container,
>  	unsigned long pages = tbl->it_allocated_size >> PAGE_SHIFT;
>  
>  	tce_iommu_userspace_view_free(tbl, container->mm);
> -	iommu_free_table(tbl, "");
> +	iommu_tce_table_put(tbl);
>  	decrement_locked_vm(container->mm, pages);
>  }
>  

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 819 bytes --]

[PATCH kernel v10 05/10] KVM: PPC: Reserve KVM_CAP_SPAPR_TCE_VFIO capability number

[Alexey Kardashevskiy]

This adds a capability number for in-kernel support for VFIO on
SPAPR platform.

The capability will tell the user space whether in-kernel handlers of
H_PUT_TCE can handle VFIO-targeted requests or not. If not, the user space
must not attempt allocating a TCE table in the host kernel via
the KVM_CREATE_SPAPR_TCE KVM ioctl because in that case TCE requests
will not be passed to the user space which is desired action in
the situation like that.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
---
 include/uapi/linux/kvm.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index f51d5082a377..f5a52ffb6b58 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -883,6 +883,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_PPC_MMU_RADIX 134
 #define KVM_CAP_PPC_MMU_HASH_V3 135
 #define KVM_CAP_IMMEDIATE_EXIT 136
+#define KVM_CAP_SPAPR_TCE_VFIO 137
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
2.11.0

[PATCH kernel v10 05/10] KVM: PPC: Reserve KVM_CAP_SPAPR_TCE_VFIO capability number

[Alexey Kardashevskiy]

This adds a capability number for in-kernel support for VFIO on
SPAPR platform.

The capability will tell the user space whether in-kernel handlers of
H_PUT_TCE can handle VFIO-targeted requests or not. If not, the user space
must not attempt allocating a TCE table in the host kernel via
the KVM_CREATE_SPAPR_TCE KVM ioctl because in that case TCE requests
will not be passed to the user space which is desired action in
the situation like that.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
---
 include/uapi/linux/kvm.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index f51d5082a377..f5a52ffb6b58 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -883,6 +883,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_PPC_MMU_RADIX 134
 #define KVM_CAP_PPC_MMU_HASH_V3 135
 #define KVM_CAP_IMMEDIATE_EXIT 136
+#define KVM_CAP_SPAPR_TCE_VFIO 137
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
2.11.0

[PATCH kernel v10 06/10] KVM: PPC: Enable IOMMU_API for KVM_BOOK3S_64 permanently

[Alexey Kardashevskiy]

It does not make much sense to have KVM in book3s-64 and
not to have IOMMU bits for PCI pass through support as it costs little
and allows VFIO to function on book3s KVM.

Having IOMMU_API always enabled makes it unnecessary to have a lot of
"#ifdef IOMMU_API" in arch/powerpc/kvm/book3s_64_vio*. With those
ifdef's we could have only user space emulated devices accelerated
(but not VFIO) which do not seem to be very useful.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
---
 arch/powerpc/kvm/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 029be26b5a17..65a471de96de 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -67,6 +67,7 @@ config KVM_BOOK3S_64
 	select KVM_BOOK3S_64_HANDLER
 	select KVM
 	select KVM_BOOK3S_PR_POSSIBLE if !KVM_BOOK3S_HV_POSSIBLE
+	select SPAPR_TCE_IOMMU if IOMMU_SUPPORT
 	---help---
 	  Support running unmodified book3s_64 and book3s_32 guest kernels
 	  in virtual machines on book3s_64 host processors.
-- 
2.11.0

[PATCH kernel v10 06/10] KVM: PPC: Enable IOMMU_API for KVM_BOOK3S_64 permanently

[Alexey Kardashevskiy]

It does not make much sense to have KVM in book3s-64 and
not to have IOMMU bits for PCI pass through support as it costs little
and allows VFIO to function on book3s KVM.

Having IOMMU_API always enabled makes it unnecessary to have a lot of
"#ifdef IOMMU_API" in arch/powerpc/kvm/book3s_64_vio*. With those
ifdef's we could have only user space emulated devices accelerated
(but not VFIO) which do not seem to be very useful.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
---
 arch/powerpc/kvm/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 029be26b5a17..65a471de96de 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -67,6 +67,7 @@ config KVM_BOOK3S_64
 	select KVM_BOOK3S_64_HANDLER
 	select KVM
 	select KVM_BOOK3S_PR_POSSIBLE if !KVM_BOOK3S_HV_POSSIBLE
+	select SPAPR_TCE_IOMMU if IOMMU_SUPPORT
 	---help---
 	  Support running unmodified book3s_64 and book3s_32 guest kernels
 	  in virtual machines on book3s_64 host processors.
-- 
2.11.0

[PATCH kernel v10 07/10] KVM: PPC: Pass kvm* to kvmppc_find_table()

[Alexey Kardashevskiy]

The guest view TCE tables are per KVM anyway (not per VCPU) so pass kvm*
there. This will be used in the following patches where we will be
attaching VFIO containers to LIOBNs via ioctl() to KVM (rather than
to VCPU).

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
---
 arch/powerpc/include/asm/kvm_ppc.h  |  2 +-
 arch/powerpc/kvm/book3s_64_vio.c    |  7 ++++---
 arch/powerpc/kvm/book3s_64_vio_hv.c | 13 +++++++------
 3 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index dd11c4c8c56a..eba8988d8443 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -168,7 +168,7 @@ extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
 extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 				struct kvm_create_spapr_tce_64 *args);
 extern struct kvmppc_spapr_tce_table *kvmppc_find_table(
-		struct kvm_vcpu *vcpu, unsigned long liobn);
+		struct kvm *kvm, unsigned long liobn);
 extern long kvmppc_ioba_validate(struct kvmppc_spapr_tce_table *stt,
 		unsigned long ioba, unsigned long npages);
 extern long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *tt,
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 3e26cd4979f9..e96a4590464c 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -214,12 +214,13 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		      unsigned long ioba, unsigned long tce)
 {
-	struct kvmppc_spapr_tce_table *stt = kvmppc_find_table(vcpu, liobn);
+	struct kvmppc_spapr_tce_table *stt;
 	long ret;
 
 	/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
 	/* 	    liobn, ioba, tce); */
 
+	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
 
@@ -247,7 +248,7 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	u64 __user *tces;
 	u64 tce;
 
-	stt = kvmppc_find_table(vcpu, liobn);
+	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
 
@@ -301,7 +302,7 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
 	struct kvmppc_spapr_tce_table *stt;
 	long i, ret;
 
-	stt = kvmppc_find_table(vcpu, liobn);
+	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
 
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index e4c4ea973e57..918af76ab2b6 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -48,10 +48,9 @@
  * WARNING: This will be called in real or virtual mode on HV KVM and virtual
  *          mode on PR KVM
  */
-struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm_vcpu *vcpu,
+struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm *kvm,
 		unsigned long liobn)
 {
-	struct kvm *kvm = vcpu->kvm;
 	struct kvmppc_spapr_tce_table *stt;
 
 	list_for_each_entry_lockless(stt, &kvm->arch.spapr_tce_tables, list)
@@ -182,12 +181,13 @@ EXPORT_SYMBOL_GPL(kvmppc_gpa_to_ua);
 long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		unsigned long ioba, unsigned long tce)
 {
-	struct kvmppc_spapr_tce_table *stt = kvmppc_find_table(vcpu, liobn);
+	struct kvmppc_spapr_tce_table *stt;
 	long ret;
 
 	/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
 	/* 	    liobn, ioba, tce); */
 
+	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
 
@@ -240,7 +240,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	unsigned long tces, entry, ua = 0;
 	unsigned long *rmap = NULL;
 
-	stt = kvmppc_find_table(vcpu, liobn);
+	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
 
@@ -301,7 +301,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 	struct kvmppc_spapr_tce_table *stt;
 	long i, ret;
 
-	stt = kvmppc_find_table(vcpu, liobn);
+	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
 
@@ -322,12 +322,13 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		      unsigned long ioba)
 {
-	struct kvmppc_spapr_tce_table *stt = kvmppc_find_table(vcpu, liobn);
+	struct kvmppc_spapr_tce_table *stt;
 	long ret;
 	unsigned long idx;
 	struct page *page;
 	u64 *tbl;
 
+	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
 
-- 
2.11.0

[PATCH kernel v10 07/10] KVM: PPC: Pass kvm* to kvmppc_find_table()

[Alexey Kardashevskiy]

The guest view TCE tables are per KVM anyway (not per VCPU) so pass kvm*
there. This will be used in the following patches where we will be
attaching VFIO containers to LIOBNs via ioctl() to KVM (rather than
to VCPU).

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
---
 arch/powerpc/include/asm/kvm_ppc.h  |  2 +-
 arch/powerpc/kvm/book3s_64_vio.c    |  7 ++++---
 arch/powerpc/kvm/book3s_64_vio_hv.c | 13 +++++++------
 3 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index dd11c4c8c56a..eba8988d8443 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -168,7 +168,7 @@ extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
 extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 				struct kvm_create_spapr_tce_64 *args);
 extern struct kvmppc_spapr_tce_table *kvmppc_find_table(
-		struct kvm_vcpu *vcpu, unsigned long liobn);
+		struct kvm *kvm, unsigned long liobn);
 extern long kvmppc_ioba_validate(struct kvmppc_spapr_tce_table *stt,
 		unsigned long ioba, unsigned long npages);
 extern long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *tt,
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 3e26cd4979f9..e96a4590464c 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -214,12 +214,13 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		      unsigned long ioba, unsigned long tce)
 {
-	struct kvmppc_spapr_tce_table *stt = kvmppc_find_table(vcpu, liobn);
+	struct kvmppc_spapr_tce_table *stt;
 	long ret;
 
 	/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
 	/* 	    liobn, ioba, tce); */
 
+	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
 
@@ -247,7 +248,7 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	u64 __user *tces;
 	u64 tce;
 
-	stt = kvmppc_find_table(vcpu, liobn);
+	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
 
@@ -301,7 +302,7 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
 	struct kvmppc_spapr_tce_table *stt;
 	long i, ret;
 
-	stt = kvmppc_find_table(vcpu, liobn);
+	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
 
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index e4c4ea973e57..918af76ab2b6 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -48,10 +48,9 @@
  * WARNING: This will be called in real or virtual mode on HV KVM and virtual
  *          mode on PR KVM
  */
-struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm_vcpu *vcpu,
+struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm *kvm,
 		unsigned long liobn)
 {
-	struct kvm *kvm = vcpu->kvm;
 	struct kvmppc_spapr_tce_table *stt;
 
 	list_for_each_entry_lockless(stt, &kvm->arch.spapr_tce_tables, list)
@@ -182,12 +181,13 @@ EXPORT_SYMBOL_GPL(kvmppc_gpa_to_ua);
 long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		unsigned long ioba, unsigned long tce)
 {
-	struct kvmppc_spapr_tce_table *stt = kvmppc_find_table(vcpu, liobn);
+	struct kvmppc_spapr_tce_table *stt;
 	long ret;
 
 	/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
 	/* 	    liobn, ioba, tce); */
 
+	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
 
@@ -240,7 +240,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	unsigned long tces, entry, ua = 0;
 	unsigned long *rmap = NULL;
 
-	stt = kvmppc_find_table(vcpu, liobn);
+	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
 
@@ -301,7 +301,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 	struct kvmppc_spapr_tce_table *stt;
 	long i, ret;
 
-	stt = kvmppc_find_table(vcpu, liobn);
+	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
 
@@ -322,12 +322,13 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		      unsigned long ioba)
 {
-	struct kvmppc_spapr_tce_table *stt = kvmppc_find_table(vcpu, liobn);
+	struct kvmppc_spapr_tce_table *stt;
 	long ret;
 	unsigned long idx;
 	struct page *page;
 	u64 *tbl;
 
+	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
 
-- 
2.11.0

[PATCH kernel v10 08/10] KVM: PPC: Use preregistered memory API to access TCE list

[Alexey Kardashevskiy]

VFIO on sPAPR already implements guest memory pre-registration
when the entire guest RAM gets pinned. This can be used to translate
the physical address of a guest page containing the TCE list
from H_PUT_TCE_INDIRECT.

This makes use of the pre-registrered memory API to access TCE list
pages in order to avoid unnecessary locking on the KVM memory
reverse map as we know that all of guest memory is pinned and
we have a flat array mapping GPA to HPA which makes it simpler and
quicker to index into that array (even with looking up the
kernel page tables in vmalloc_to_phys) than it is to find the memslot,
lock the rmap entry, look up the user page tables, and unlock the rmap
entry. Note that the rmap pointer is initialized to NULL
where declared (not in this patch).

If a requested chunk of memory has not been preregistered, this will
fall back to non-preregistered case and lock rmap.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
---
Changes:
v4:
* removed oneline inlines
* now falls back to locking rmap if TCE list is not in preregistered memory

v2:
* updated the commit log with David's comment
---
 arch/powerpc/kvm/book3s_64_vio_hv.c | 58 +++++++++++++++++++++++++++----------
 1 file changed, 42 insertions(+), 16 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 918af76ab2b6..0f145fc7a3a5 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -239,6 +239,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	long i, ret = H_SUCCESS;
 	unsigned long tces, entry, ua = 0;
 	unsigned long *rmap = NULL;
+	bool prereg = false;
 
 	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
@@ -259,23 +260,47 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	if (ret != H_SUCCESS)
 		return ret;
 
-	if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, &rmap))
-		return H_TOO_HARD;
+	if (mm_iommu_preregistered(vcpu->kvm->mm)) {
+		/*
+		 * We get here if guest memory was pre-registered which
+		 * is normally VFIO case and gpa->hpa translation does not
+		 * depend on hpt.
+		 */
+		struct mm_iommu_table_group_mem_t *mem;
 
-	rmap = (void *) vmalloc_to_phys(rmap);
+		if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, NULL))
+			return H_TOO_HARD;
 
-	/*
-	 * Synchronize with the MMU notifier callbacks in
-	 * book3s_64_mmu_hv.c (kvm_unmap_hva_hv etc.).
-	 * While we have the rmap lock, code running on other CPUs
-	 * cannot finish unmapping the host real page that backs
-	 * this guest real page, so we are OK to access the host
-	 * real page.
-	 */
-	lock_rmap(rmap);
-	if (kvmppc_rm_ua_to_hpa(vcpu, ua, &tces)) {
-		ret = H_TOO_HARD;
-		goto unlock_exit;
+		mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K);
+		if (mem)
+			prereg = mm_iommu_ua_to_hpa_rm(mem, ua, &tces) == 0;
+	}
+
+	if (!prereg) {
+		/*
+		 * This is usually a case of a guest with emulated devices only
+		 * when TCE list is not in preregistered memory.
+		 * We do not require memory to be preregistered in this case
+		 * so lock rmap and do __find_linux_pte_or_hugepte().
+		 */
+		if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, &rmap))
+			return H_TOO_HARD;
+
+		rmap = (void *) vmalloc_to_phys(rmap);
+
+		/*
+		 * Synchronize with the MMU notifier callbacks in
+		 * book3s_64_mmu_hv.c (kvm_unmap_hva_hv etc.).
+		 * While we have the rmap lock, code running on other CPUs
+		 * cannot finish unmapping the host real page that backs
+		 * this guest real page, so we are OK to access the host
+		 * real page.
+		 */
+		lock_rmap(rmap);
+		if (kvmppc_rm_ua_to_hpa(vcpu, ua, &tces)) {
+			ret = H_TOO_HARD;
+			goto unlock_exit;
+		}
 	}
 
 	for (i = 0; i < npages; ++i) {
@@ -289,7 +314,8 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	}
 
 unlock_exit:
-	unlock_rmap(rmap);
+	if (rmap)
+		unlock_rmap(rmap);
 
 	return ret;
 }
-- 
2.11.0

[PATCH kernel v10 08/10] KVM: PPC: Use preregistered memory API to access TCE list

[Alexey Kardashevskiy]

VFIO on sPAPR already implements guest memory pre-registration
when the entire guest RAM gets pinned. This can be used to translate
the physical address of a guest page containing the TCE list
from H_PUT_TCE_INDIRECT.

This makes use of the pre-registrered memory API to access TCE list
pages in order to avoid unnecessary locking on the KVM memory
reverse map as we know that all of guest memory is pinned and
we have a flat array mapping GPA to HPA which makes it simpler and
quicker to index into that array (even with looking up the
kernel page tables in vmalloc_to_phys) than it is to find the memslot,
lock the rmap entry, look up the user page tables, and unlock the rmap
entry. Note that the rmap pointer is initialized to NULL
where declared (not in this patch).

If a requested chunk of memory has not been preregistered, this will
fall back to non-preregistered case and lock rmap.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
---
Changes:
v4:
* removed oneline inlines
* now falls back to locking rmap if TCE list is not in preregistered memory

v2:
* updated the commit log with David's comment
---
 arch/powerpc/kvm/book3s_64_vio_hv.c | 58 +++++++++++++++++++++++++++----------
 1 file changed, 42 insertions(+), 16 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 918af76ab2b6..0f145fc7a3a5 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -239,6 +239,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	long i, ret = H_SUCCESS;
 	unsigned long tces, entry, ua = 0;
 	unsigned long *rmap = NULL;
+	bool prereg = false;
 
 	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
@@ -259,23 +260,47 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	if (ret != H_SUCCESS)
 		return ret;
 
-	if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, &rmap))
-		return H_TOO_HARD;
+	if (mm_iommu_preregistered(vcpu->kvm->mm)) {
+		/*
+		 * We get here if guest memory was pre-registered which
+		 * is normally VFIO case and gpa->hpa translation does not
+		 * depend on hpt.
+		 */
+		struct mm_iommu_table_group_mem_t *mem;
 
-	rmap = (void *) vmalloc_to_phys(rmap);
+		if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, NULL))
+			return H_TOO_HARD;
 
-	/*
-	 * Synchronize with the MMU notifier callbacks in
-	 * book3s_64_mmu_hv.c (kvm_unmap_hva_hv etc.).
-	 * While we have the rmap lock, code running on other CPUs
-	 * cannot finish unmapping the host real page that backs
-	 * this guest real page, so we are OK to access the host
-	 * real page.
-	 */
-	lock_rmap(rmap);
-	if (kvmppc_rm_ua_to_hpa(vcpu, ua, &tces)) {
-		ret = H_TOO_HARD;
-		goto unlock_exit;
+		mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K);
+		if (mem)
+			prereg = mm_iommu_ua_to_hpa_rm(mem, ua, &tces) = 0;
+	}
+
+	if (!prereg) {
+		/*
+		 * This is usually a case of a guest with emulated devices only
+		 * when TCE list is not in preregistered memory.
+		 * We do not require memory to be preregistered in this case
+		 * so lock rmap and do __find_linux_pte_or_hugepte().
+		 */
+		if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, &rmap))
+			return H_TOO_HARD;
+
+		rmap = (void *) vmalloc_to_phys(rmap);
+
+		/*
+		 * Synchronize with the MMU notifier callbacks in
+		 * book3s_64_mmu_hv.c (kvm_unmap_hva_hv etc.).
+		 * While we have the rmap lock, code running on other CPUs
+		 * cannot finish unmapping the host real page that backs
+		 * this guest real page, so we are OK to access the host
+		 * real page.
+		 */
+		lock_rmap(rmap);
+		if (kvmppc_rm_ua_to_hpa(vcpu, ua, &tces)) {
+			ret = H_TOO_HARD;
+			goto unlock_exit;
+		}
 	}
 
 	for (i = 0; i < npages; ++i) {
@@ -289,7 +314,8 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	}
 
 unlock_exit:
-	unlock_rmap(rmap);
+	if (rmap)
+		unlock_rmap(rmap);
 
 	return ret;
 }
-- 
2.11.0

[PATCH kernel v10 09/10] KVM: PPC: iommu: Unify TCE checking

[Alexey Kardashevskiy]

This reworks helpers for checking TCE update parameters in way they
can be used in KVM.

This should cause no behavioral change.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
---
Changes:
v6:
* s/tce/gpa/ as TCE without permission bits is a GPA and this is what is
passed everywhere
---
 arch/powerpc/include/asm/iommu.h    | 20 +++++++++++++++-----
 arch/powerpc/include/asm/kvm_ppc.h  |  6 ++++--
 arch/powerpc/kernel/iommu.c         | 37 +++++++++++++------------------------
 arch/powerpc/kvm/book3s_64_vio_hv.c | 31 +++++++------------------------
 4 files changed, 39 insertions(+), 55 deletions(-)

diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index d96142572e6d..8a8ce220d7d0 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -296,11 +296,21 @@ 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_check_ioba(unsigned long page_shift,
+		unsigned long offset, unsigned long size,
+		unsigned long ioba, unsigned long npages);
+extern int iommu_tce_check_gpa(unsigned long page_shift,
+		unsigned long gpa);
+
+#define iommu_tce_clear_param_check(tbl, ioba, tce_value, npages) \
+		(iommu_tce_check_ioba((tbl)->it_page_shift,       \
+				(tbl)->it_offset, (tbl)->it_size, \
+				(ioba), (npages)) || (tce_value))
+#define iommu_tce_put_param_check(tbl, ioba, gpa)                 \
+		(iommu_tce_check_ioba((tbl)->it_page_shift,       \
+				(tbl)->it_offset, (tbl)->it_size, \
+				(ioba), 1) ||                     \
+		iommu_tce_check_gpa((tbl)->it_page_shift, (gpa)))
 
 extern void iommu_flush_tce(struct iommu_table *tbl);
 extern int iommu_take_ownership(struct iommu_table *tbl);
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index eba8988d8443..72c2a155641f 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -169,8 +169,10 @@ extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 				struct kvm_create_spapr_tce_64 *args);
 extern struct kvmppc_spapr_tce_table *kvmppc_find_table(
 		struct kvm *kvm, unsigned long liobn);
-extern long kvmppc_ioba_validate(struct kvmppc_spapr_tce_table *stt,
-		unsigned long ioba, unsigned long npages);
+#define kvmppc_ioba_validate(stt, ioba, npages)                         \
+		(iommu_tce_check_ioba((stt)->page_shift, (stt)->offset, \
+				(stt)->size, (ioba), (npages)) ?        \
+				H_PARAMETER : H_SUCCESS)
 extern long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *tt,
 		unsigned long tce);
 extern long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index af915da5e03a..e73927352672 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -963,47 +963,36 @@ void iommu_flush_tce(struct iommu_table *tbl)
 }
 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)
+int iommu_tce_check_ioba(unsigned long page_shift,
+		unsigned long offset, unsigned long size,
+		unsigned long ioba, unsigned long npages)
 {
-	/* tbl->it_ops->clear() does not support any value but 0 */
-	if (tce_value)
-		return -EINVAL;
+	unsigned long mask = (1UL << page_shift) - 1;
 
-	if (ioba & ~IOMMU_PAGE_MASK(tbl))
+	if (ioba & mask)
 		return -EINVAL;
 
-	ioba >>= tbl->it_page_shift;
-	if (ioba < tbl->it_offset)
+	ioba >>= page_shift;
+	if (ioba < offset)
 		return -EINVAL;
 
-	if ((ioba + npages) > (tbl->it_offset + tbl->it_size))
+	if ((ioba + 1) > (offset + size))
 		return -EINVAL;
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(iommu_tce_clear_param_check);
+EXPORT_SYMBOL_GPL(iommu_tce_check_ioba);
 
-int iommu_tce_put_param_check(struct iommu_table *tbl,
-		unsigned long ioba, unsigned long tce)
+int iommu_tce_check_gpa(unsigned long page_shift, unsigned long gpa)
 {
-	if (tce & ~IOMMU_PAGE_MASK(tbl))
-		return -EINVAL;
-
-	if (ioba & ~IOMMU_PAGE_MASK(tbl))
-		return -EINVAL;
-
-	ioba >>= tbl->it_page_shift;
-	if (ioba < tbl->it_offset)
-		return -EINVAL;
+	unsigned long mask = (1UL << page_shift) - 1;
 
-	if ((ioba + 1) > (tbl->it_offset + tbl->it_size))
+	if (gpa & mask)
 		return -EINVAL;
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(iommu_tce_put_param_check);
+EXPORT_SYMBOL_GPL(iommu_tce_check_gpa);
 
 long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
 		unsigned long *hpa, enum dma_data_direction *direction)
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 0f145fc7a3a5..440d3ab5dc32 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -62,27 +62,6 @@ struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm *kvm,
 EXPORT_SYMBOL_GPL(kvmppc_find_table);
 
 /*
- * Validates IO address.
- *
- * WARNING: This will be called in real-mode on HV KVM and virtual
- *          mode on PR KVM
- */
-long kvmppc_ioba_validate(struct kvmppc_spapr_tce_table *stt,
-		unsigned long ioba, unsigned long npages)
-{
-	unsigned long mask = (1ULL << stt->page_shift) - 1;
-	unsigned long idx = ioba >> stt->page_shift;
-
-	if ((ioba & mask) || (idx < stt->offset) ||
-			(idx - stt->offset + npages > stt->size) ||
-			(idx + npages < idx))
-		return H_PARAMETER;
-
-	return H_SUCCESS;
-}
-EXPORT_SYMBOL_GPL(kvmppc_ioba_validate);
-
-/*
  * Validates TCE address.
  * At the moment flags and page mask are validated.
  * As the host kernel does not access those addresses (just puts them
@@ -95,10 +74,14 @@ EXPORT_SYMBOL_GPL(kvmppc_ioba_validate);
  */
 long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt, unsigned long tce)
 {
-	unsigned long page_mask = ~((1ULL << stt->page_shift) - 1);
-	unsigned long mask = ~(page_mask | TCE_PCI_WRITE | TCE_PCI_READ);
+	unsigned long gpa = tce & ~(TCE_PCI_READ | TCE_PCI_WRITE);
+	enum dma_data_direction dir = iommu_tce_direction(tce);
 
-	if (tce & mask)
+	/* Allow userspace to poison TCE table */
+	if (dir == DMA_NONE)
+		return H_SUCCESS;
+
+	if (iommu_tce_check_gpa(stt->page_shift, gpa))
 		return H_PARAMETER;
 
 	return H_SUCCESS;
-- 
2.11.0

[PATCH kernel v10 09/10] KVM: PPC: iommu: Unify TCE checking

[Alexey Kardashevskiy]

This reworks helpers for checking TCE update parameters in way they
can be used in KVM.

This should cause no behavioral change.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
---
Changes:
v6:
* s/tce/gpa/ as TCE without permission bits is a GPA and this is what is
passed everywhere
---
 arch/powerpc/include/asm/iommu.h    | 20 +++++++++++++++-----
 arch/powerpc/include/asm/kvm_ppc.h  |  6 ++++--
 arch/powerpc/kernel/iommu.c         | 37 +++++++++++++------------------------
 arch/powerpc/kvm/book3s_64_vio_hv.c | 31 +++++++------------------------
 4 files changed, 39 insertions(+), 55 deletions(-)

diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index d96142572e6d..8a8ce220d7d0 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -296,11 +296,21 @@ 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_check_ioba(unsigned long page_shift,
+		unsigned long offset, unsigned long size,
+		unsigned long ioba, unsigned long npages);
+extern int iommu_tce_check_gpa(unsigned long page_shift,
+		unsigned long gpa);
+
+#define iommu_tce_clear_param_check(tbl, ioba, tce_value, npages) \
+		(iommu_tce_check_ioba((tbl)->it_page_shift,       \
+				(tbl)->it_offset, (tbl)->it_size, \
+				(ioba), (npages)) || (tce_value))
+#define iommu_tce_put_param_check(tbl, ioba, gpa)                 \
+		(iommu_tce_check_ioba((tbl)->it_page_shift,       \
+				(tbl)->it_offset, (tbl)->it_size, \
+				(ioba), 1) ||                     \
+		iommu_tce_check_gpa((tbl)->it_page_shift, (gpa)))
 
 extern void iommu_flush_tce(struct iommu_table *tbl);
 extern int iommu_take_ownership(struct iommu_table *tbl);
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index eba8988d8443..72c2a155641f 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -169,8 +169,10 @@ extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 				struct kvm_create_spapr_tce_64 *args);
 extern struct kvmppc_spapr_tce_table *kvmppc_find_table(
 		struct kvm *kvm, unsigned long liobn);
-extern long kvmppc_ioba_validate(struct kvmppc_spapr_tce_table *stt,
-		unsigned long ioba, unsigned long npages);
+#define kvmppc_ioba_validate(stt, ioba, npages)                         \
+		(iommu_tce_check_ioba((stt)->page_shift, (stt)->offset, \
+				(stt)->size, (ioba), (npages)) ?        \
+				H_PARAMETER : H_SUCCESS)
 extern long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *tt,
 		unsigned long tce);
 extern long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index af915da5e03a..e73927352672 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -963,47 +963,36 @@ void iommu_flush_tce(struct iommu_table *tbl)
 }
 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)
+int iommu_tce_check_ioba(unsigned long page_shift,
+		unsigned long offset, unsigned long size,
+		unsigned long ioba, unsigned long npages)
 {
-	/* tbl->it_ops->clear() does not support any value but 0 */
-	if (tce_value)
-		return -EINVAL;
+	unsigned long mask = (1UL << page_shift) - 1;
 
-	if (ioba & ~IOMMU_PAGE_MASK(tbl))
+	if (ioba & mask)
 		return -EINVAL;
 
-	ioba >>= tbl->it_page_shift;
-	if (ioba < tbl->it_offset)
+	ioba >>= page_shift;
+	if (ioba < offset)
 		return -EINVAL;
 
-	if ((ioba + npages) > (tbl->it_offset + tbl->it_size))
+	if ((ioba + 1) > (offset + size))
 		return -EINVAL;
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(iommu_tce_clear_param_check);
+EXPORT_SYMBOL_GPL(iommu_tce_check_ioba);
 
-int iommu_tce_put_param_check(struct iommu_table *tbl,
-		unsigned long ioba, unsigned long tce)
+int iommu_tce_check_gpa(unsigned long page_shift, unsigned long gpa)
 {
-	if (tce & ~IOMMU_PAGE_MASK(tbl))
-		return -EINVAL;
-
-	if (ioba & ~IOMMU_PAGE_MASK(tbl))
-		return -EINVAL;
-
-	ioba >>= tbl->it_page_shift;
-	if (ioba < tbl->it_offset)
-		return -EINVAL;
+	unsigned long mask = (1UL << page_shift) - 1;
 
-	if ((ioba + 1) > (tbl->it_offset + tbl->it_size))
+	if (gpa & mask)
 		return -EINVAL;
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(iommu_tce_put_param_check);
+EXPORT_SYMBOL_GPL(iommu_tce_check_gpa);
 
 long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
 		unsigned long *hpa, enum dma_data_direction *direction)
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 0f145fc7a3a5..440d3ab5dc32 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -62,27 +62,6 @@ struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm *kvm,
 EXPORT_SYMBOL_GPL(kvmppc_find_table);
 
 /*
- * Validates IO address.
- *
- * WARNING: This will be called in real-mode on HV KVM and virtual
- *          mode on PR KVM
- */
-long kvmppc_ioba_validate(struct kvmppc_spapr_tce_table *stt,
-		unsigned long ioba, unsigned long npages)
-{
-	unsigned long mask = (1ULL << stt->page_shift) - 1;
-	unsigned long idx = ioba >> stt->page_shift;
-
-	if ((ioba & mask) || (idx < stt->offset) ||
-			(idx - stt->offset + npages > stt->size) ||
-			(idx + npages < idx))
-		return H_PARAMETER;
-
-	return H_SUCCESS;
-}
-EXPORT_SYMBOL_GPL(kvmppc_ioba_validate);
-
-/*
  * Validates TCE address.
  * At the moment flags and page mask are validated.
  * As the host kernel does not access those addresses (just puts them
@@ -95,10 +74,14 @@ EXPORT_SYMBOL_GPL(kvmppc_ioba_validate);
  */
 long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt, unsigned long tce)
 {
-	unsigned long page_mask = ~((1ULL << stt->page_shift) - 1);
-	unsigned long mask = ~(page_mask | TCE_PCI_WRITE | TCE_PCI_READ);
+	unsigned long gpa = tce & ~(TCE_PCI_READ | TCE_PCI_WRITE);
+	enum dma_data_direction dir = iommu_tce_direction(tce);
 
-	if (tce & mask)
+	/* Allow userspace to poison TCE table */
+	if (dir = DMA_NONE)
+		return H_SUCCESS;
+
+	if (iommu_tce_check_gpa(stt->page_shift, gpa))
 		return H_PARAMETER;
 
 	return H_SUCCESS;
-- 
2.11.0

[PATCH kernel v10 10/10] KVM: PPC: VFIO: Add in-kernel acceleration for VFIO

[Alexey Kardashevskiy]

This allows the host kernel to handle H_PUT_TCE, H_PUT_TCE_INDIRECT
and H_STUFF_TCE requests targeted an IOMMU TCE table used for VFIO
without passing them to user space which saves time on switching
to user space and back.

This adds H_PUT_TCE/H_PUT_TCE_INDIRECT/H_STUFF_TCE handlers to KVM.
KVM tries to handle a TCE request in the real mode, if failed
it passes the request to the virtual mode to complete the operation.
If it a virtual mode handler fails, the request is passed to
the user space; this is not expected to happen though.

To avoid dealing with page use counters (which is tricky in real mode),
this only accelerates SPAPR TCE IOMMU v2 clients which are required
to pre-register the userspace memory. The very first TCE request will
be handled in the VFIO SPAPR TCE driver anyway as the userspace view
of the TCE table (iommu_table::it_userspace) is not allocated till
the very first mapping happens and we cannot call vmalloc in real mode.

If we fail to update a hardware IOMMU table unexpected reason, we just
clear it and move on as there is nothing really we can do about it -
for example, if we hot plug a VFIO device to a guest, existing TCE tables
will be mirrored automatically to the hardware and there is no interface
to report to the guest about possible failures.

This adds new attribute - KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE - to
the VFIO KVM device. It takes a VFIO group fd and SPAPR TCE table fd
and associates a physical IOMMU table with the SPAPR TCE table (which
is a guest view of the hardware IOMMU table). The iommu_table object
is cached and referenced so we do not have to look up for it in real mode.

This does not implement the UNSET counterpart as there is no use for it -
once the acceleration is enabled, the existing userspace won't
disable it unless a VFIO container is destroyed; this adds necessary
cleanup to the KVM_DEV_VFIO_GROUP_DEL handler.

This advertises the new KVM_CAP_SPAPR_TCE_VFIO capability to the user
space.

This adds real mode version of WARN_ON_ONCE() as the generic version
causes problems with rcu_sched. Since we testing what vmalloc_to_phys()
returns in the code, this also adds a check for already existing
vmalloc_to_phys() call in kvmppc_rm_h_put_tce_indirect().

This finally makes use of vfio_external_user_iommu_id() which was
introduced quite some time ago and was considered for removal.

Tests show that this patch increases transmission speed from 220MB/s
to 750..1020MB/s on 10Gb network (Chelsea CXGB3 10Gb ethernet card).

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
Changes:
v10:
* fixed leaking references in virt/kvm/vfio.c
* moved code to helpers - kvm_vfio_group_get_iommu_group, kvm_spapr_tce_release_vfio_group
* fixed possible race between referencing table and destroying it via
VFIO add/remove window ioctls()

v9:
* removed referencing a group in KVM, only referencing iommu_table's now
* fixed a reference leak in KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE handler
* fixed typo in vfio.txt
* removed @argsz and @flags from struct kvm_vfio_spapr_tce

v8:
* changed all (!pua) checks to return H_TOO_HARD as ioctl() is supposed
to handle them
* changed vmalloc_to_phys() callers to return H_HARDWARE
* changed real mode iommu_tce_xchg_rm() callers to return H_TOO_HARD
and added a comment about this in the code
* changed virtual mode iommu_tce_xchg() callers to return H_HARDWARE
and do WARN_ON
* added WARN_ON_ONCE_RM(!rmap) in kvmppc_rm_h_put_tce_indirect() to
have all vmalloc_to_phys() callsites covered

v7:
* added realmode-friendly WARN_ON_ONCE_RM

v6:
* changed handling of errors returned by kvmppc_(rm_)tce_iommu_(un)map()
* moved kvmppc_gpa_to_ua() to TCE validation

v5:
* changed error codes in multiple places
* added bunch of WARN_ON() in places which should not really happen
* adde a check that an iommu table is not attached already to LIOBN
* dropped explicit calls to iommu_tce_clear_param_check/
iommu_tce_put_param_check as kvmppc_tce_validate/kvmppc_ioba_validate
call them anyway (since the previous patch)
* if we fail to update a hardware IOMMU table for unexpected reason,
this just clears the entry

v4:
* added note to the commit log about allowing multiple updates of
the same IOMMU table;
* instead of checking for if any memory was preregistered, this
returns H_TOO_HARD if a specific page was not;
* fixed comments from v3 about error handling in many places;
* simplified TCE handlers and merged IOMMU parts inline - for example,
there used to be kvmppc_h_put_tce_iommu(), now it is merged into
kvmppc_h_put_tce(); this allows to check IOBA boundaries against
the first attached table only (makes the code simpler);

v3:
* simplified not to use VFIO group notifiers
* reworked cleanup, should be cleaner/simpler now

v2:
* reworked to use new VFIO notifiers
* now same iommu_table may appear in the list several times, to be fixed later
---
 Documentation/virtual/kvm/devices/vfio.txt |  18 +-
 arch/powerpc/include/asm/kvm_host.h        |   8 +
 arch/powerpc/include/asm/kvm_ppc.h         |   4 +
 include/uapi/linux/kvm.h                   |   6 +
 arch/powerpc/kvm/book3s_64_vio.c           | 301 ++++++++++++++++++++++++++++-
 arch/powerpc/kvm/book3s_64_vio_hv.c        | 201 ++++++++++++++++++-
 arch/powerpc/kvm/powerpc.c                 |   2 +
 virt/kvm/vfio.c                            | 104 ++++++++++
 8 files changed, 639 insertions(+), 5 deletions(-)

diff --git a/Documentation/virtual/kvm/devices/vfio.txt b/Documentation/virtual/kvm/devices/vfio.txt
index ef51740c67ca..528c77c8022c 100644
--- a/Documentation/virtual/kvm/devices/vfio.txt
+++ b/Documentation/virtual/kvm/devices/vfio.txt
@@ -16,7 +16,21 @@ Groups:
 
 KVM_DEV_VFIO_GROUP attributes:
   KVM_DEV_VFIO_GROUP_ADD: Add a VFIO group to VFIO-KVM device tracking
+	kvm_device_attr.addr points to an int32_t file descriptor
+	for the VFIO group.
   KVM_DEV_VFIO_GROUP_DEL: Remove a VFIO group from VFIO-KVM device tracking
+	kvm_device_attr.addr points to an int32_t file descriptor
+	for the VFIO group.
+  KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: attaches a guest visible TCE table
+	allocated by sPAPR KVM.
+	kvm_device_attr.addr points to a struct:
 
-For each, kvm_device_attr.addr points to an int32_t file descriptor
-for the VFIO group.
+	struct kvm_vfio_spapr_tce {
+		__s32	groupfd;
+		__s32	tablefd;
+	};
+
+	where
+	@groupfd is a file descriptor for a VFIO group;
+	@tablefd is a file descriptor for a TCE table allocated via
+		KVM_CREATE_SPAPR_TCE.
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 7bba8f415627..178074e643e5 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -191,6 +191,13 @@ struct kvmppc_pginfo {
 	atomic_t refcnt;
 };
 
+struct kvmppc_spapr_tce_iommu_table {
+	struct rcu_head rcu;
+	struct list_head next;
+	struct iommu_table *tbl;
+	struct kref kref;
+};
+
 struct kvmppc_spapr_tce_table {
 	struct list_head list;
 	struct kvm *kvm;
@@ -199,6 +206,7 @@ struct kvmppc_spapr_tce_table {
 	u32 page_shift;
 	u64 offset;		/* in pages */
 	u64 size;		/* window size in pages */
+	struct list_head iommu_tables;
 	struct page *pages[0];
 };
 
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 72c2a155641f..cfd45714189e 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -164,6 +164,10 @@ extern long kvmppc_prepare_vrma(struct kvm *kvm,
 extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu,
 			struct kvm_memory_slot *memslot, unsigned long porder);
 extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
+extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
+		struct iommu_group *grp);
+extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
+		struct iommu_group *grp);
 
 extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 				struct kvm_create_spapr_tce_64 *args);
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index f5a52ffb6b58..0f8a5e6528aa 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1088,6 +1088,7 @@ struct kvm_device_attr {
 #define  KVM_DEV_VFIO_GROUP			1
 #define   KVM_DEV_VFIO_GROUP_ADD			1
 #define   KVM_DEV_VFIO_GROUP_DEL			2
+#define   KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE		3
 
 enum kvm_device_type {
 	KVM_DEV_TYPE_FSL_MPIC_20	= 1,
@@ -1109,6 +1110,11 @@ enum kvm_device_type {
 	KVM_DEV_TYPE_MAX,
 };
 
+struct kvm_vfio_spapr_tce {
+	__s32	groupfd;
+	__s32	tablefd;
+};
+
 /*
  * ioctls for VM fds
  */
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index e96a4590464c..22c67a47eaab 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -28,6 +28,8 @@
 #include <linux/hugetlb.h>
 #include <linux/list.h>
 #include <linux/anon_inodes.h>
+#include <linux/iommu.h>
+#include <linux/file.h>
 
 #include <asm/tlbflush.h>
 #include <asm/kvm_ppc.h>
@@ -40,6 +42,7 @@
 #include <asm/udbg.h>
 #include <asm/iommu.h>
 #include <asm/tce.h>
+#include <asm/mmu_context.h>
 
 static unsigned long kvmppc_tce_pages(unsigned long iommu_pages)
 {
@@ -91,6 +94,132 @@ static long kvmppc_account_memlimit(unsigned long stt_pages, bool inc)
 	return ret;
 }
 
+static void kvm_spapr_tce_iommu_table_free(struct rcu_head *head)
+{
+	struct kvmppc_spapr_tce_iommu_table *stit = container_of(head,
+			struct kvmppc_spapr_tce_iommu_table, rcu);
+
+	iommu_tce_table_put(stit->tbl);
+
+	kfree(stit);
+}
+
+static void kvm_spapr_tce_liobn_put(struct kref *kref)
+{
+	struct kvmppc_spapr_tce_iommu_table *stit = container_of(kref,
+			struct kvmppc_spapr_tce_iommu_table, kref);
+
+	list_del_rcu(&stit->next);
+
+	call_rcu(&stit->rcu, kvm_spapr_tce_iommu_table_free);
+}
+
+extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
+		struct iommu_group *grp)
+{
+	int i;
+	struct kvmppc_spapr_tce_table *stt;
+	struct kvmppc_spapr_tce_iommu_table *stit, *tmp;
+	struct iommu_table_group *table_group = NULL;
+
+	list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) {
+
+		table_group = iommu_group_get_iommudata(grp);
+		if (WARN_ON(!table_group))
+			continue;
+
+		list_for_each_entry_safe(stit, tmp, &stt->iommu_tables, next) {
+			for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+				if (table_group->tables[i] != stit->tbl)
+					continue;
+
+				kref_put(&stit->kref, kvm_spapr_tce_liobn_put);
+				return;
+			}
+		}
+	}
+}
+
+extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
+		struct iommu_group *grp)
+{
+	struct kvmppc_spapr_tce_table *stt = NULL;
+	bool found = false;
+	struct iommu_table *tbl = NULL;
+	struct iommu_table_group *table_group;
+	long i;
+	struct kvmppc_spapr_tce_iommu_table *stit;
+	struct fd f;
+
+	f = fdget(tablefd);
+	if (!f.file)
+		return -EBADF;
+
+	list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) {
+		if (stt == f.file->private_data) {
+			found = true;
+			break;
+		}
+	}
+
+	fdput(f);
+
+	if (!found)
+		return -EINVAL;
+
+	table_group = iommu_group_get_iommudata(grp);
+	if (WARN_ON(!table_group))
+		return -EFAULT;
+
+	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+		struct iommu_table *tbltmp = table_group->tables[i];
+
+		if (!tbltmp)
+			continue;
+		/*
+		 * Make sure hardware table parameters are exactly the same;
+		 * this is used in the TCE handlers where boundary checks
+		 * use only the first attached table.
+		 */
+		if ((tbltmp->it_page_shift == stt->page_shift) &&
+				(tbltmp->it_offset == stt->offset) &&
+				(tbltmp->it_size == stt->size)) {
+			/*
+			 * Reference the table to avoid races with
+			 * add/remove DMA windows.
+			 */
+			tbl = iommu_tce_table_get(tbltmp);
+			break;
+		}
+	}
+	if (!tbl)
+		return -EINVAL;
+
+	list_for_each_entry_rcu(stit, &stt->iommu_tables, next) {
+		if (tbl != stit->tbl)
+			continue;
+
+		if (!kref_get_unless_zero(&stit->kref)) {
+			/* stit is being destroyed */
+			iommu_tce_table_put(tbl);
+			return -ENOTTY;
+		}
+		/*
+		 * The table is already known to this KVM, we just increased
+		 * its KVM reference counter and can return.
+		 */
+		return 0;
+	}
+
+	stit = kzalloc(sizeof(*stit), GFP_KERNEL);
+	stit->tbl = tbl;
+	kref_init(&stit->kref);
+
+	list_add_rcu(&stit->next, &stt->iommu_tables);
+
+	return 0;
+}
+
 static void release_spapr_tce_table(struct rcu_head *head)
 {
 	struct kvmppc_spapr_tce_table *stt = container_of(head,
@@ -130,9 +259,18 @@ static int kvm_spapr_tce_mmap(struct file *file, struct vm_area_struct *vma)
 static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
 {
 	struct kvmppc_spapr_tce_table *stt = filp->private_data;
+	struct kvmppc_spapr_tce_iommu_table *stit, *tmp;
 
 	list_del_rcu(&stt->list);
 
+	list_for_each_entry_safe(stit, tmp, &stt->iommu_tables, next) {
+		WARN_ON(!kref_read(&stit->kref));
+		while (1) {
+			if (kref_put(&stit->kref, kvm_spapr_tce_liobn_put))
+				break;
+		}
+	}
+
 	kvm_put_kvm(stt->kvm);
 
 	kvmppc_account_memlimit(
@@ -183,6 +321,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 	stt->offset = args->offset;
 	stt->size = size;
 	stt->kvm = kvm;
+	INIT_LIST_HEAD_RCU(&stt->iommu_tables);
 
 	for (i = 0; i < npages; i++) {
 		stt->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
@@ -211,11 +350,101 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 	return ret;
 }
 
+static void kvmppc_clear_tce(struct iommu_table *tbl, unsigned long entry)
+{
+	unsigned long hpa = 0;
+	enum dma_data_direction dir = DMA_NONE;
+
+	iommu_tce_xchg(tbl, entry, &hpa, &dir);
+}
+
+static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm,
+		struct iommu_table *tbl, unsigned long entry)
+{
+	struct mm_iommu_table_group_mem_t *mem = NULL;
+	const unsigned long pgsize = 1ULL << tbl->it_page_shift;
+	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+
+	if (!pua)
+		/* it_userspace allocation might be delayed */
+		return H_TOO_HARD;
+
+	mem = mm_iommu_lookup(kvm->mm, *pua, pgsize);
+	if (!mem)
+		return H_TOO_HARD;
+
+	mm_iommu_mapped_dec(mem);
+
+	*pua = 0;
+
+	return H_SUCCESS;
+}
+
+static long kvmppc_tce_iommu_unmap(struct kvm *kvm,
+		struct iommu_table *tbl, unsigned long entry)
+{
+	enum dma_data_direction dir = DMA_NONE;
+	unsigned long hpa = 0;
+	long ret;
+
+	if (WARN_ON_ONCE(iommu_tce_xchg(tbl, entry, &hpa, &dir)))
+		return H_HARDWARE;
+
+	if (dir == DMA_NONE)
+		return H_SUCCESS;
+
+	ret = kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry);
+	if (ret != H_SUCCESS)
+		iommu_tce_xchg(tbl, entry, &hpa, &dir);
+
+	return ret;
+}
+
+long kvmppc_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
+		unsigned long entry, unsigned long ua,
+		enum dma_data_direction dir)
+{
+	long ret;
+	unsigned long hpa, *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+	struct mm_iommu_table_group_mem_t *mem;
+
+	if (!pua)
+		/* it_userspace allocation might be delayed */
+		return H_TOO_HARD;
+
+	mem = mm_iommu_lookup(kvm->mm, ua, 1ULL << tbl->it_page_shift);
+	if (!mem)
+		/* This only handles v2 IOMMU type, v1 is handled via ioctl() */
+		return H_TOO_HARD;
+
+	if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, &hpa)))
+		return H_HARDWARE;
+
+	if (mm_iommu_mapped_inc(mem))
+		return H_CLOSED;
+
+	ret = iommu_tce_xchg(tbl, entry, &hpa, &dir);
+	if (WARN_ON_ONCE(ret)) {
+		mm_iommu_mapped_dec(mem);
+		return H_HARDWARE;
+	}
+
+	if (dir != DMA_NONE)
+		kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry);
+
+	*pua = ua;
+
+	return 0;
+}
+
 long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		      unsigned long ioba, unsigned long tce)
 {
 	struct kvmppc_spapr_tce_table *stt;
-	long ret;
+	long ret, idx;
+	struct kvmppc_spapr_tce_iommu_table *stit;
+	unsigned long entry, ua = 0;
+	enum dma_data_direction dir;
 
 	/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
 	/* 	    liobn, ioba, tce); */
@@ -232,7 +461,35 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	if (ret != H_SUCCESS)
 		return ret;
 
-	kvmppc_tce_put(stt, ioba >> stt->page_shift, tce);
+	dir = iommu_tce_direction(tce);
+	if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm,
+			tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL))
+		return H_PARAMETER;
+
+	entry = ioba >> stt->page_shift;
+
+	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+		if (dir == DMA_NONE) {
+			ret = kvmppc_tce_iommu_unmap(vcpu->kvm,
+					stit->tbl, entry);
+		} else {
+			idx = srcu_read_lock(&vcpu->kvm->srcu);
+			ret = kvmppc_tce_iommu_map(vcpu->kvm, stit->tbl,
+					entry, ua, dir);
+			srcu_read_unlock(&vcpu->kvm->srcu, idx);
+		}
+
+		if (ret == H_SUCCESS)
+			continue;
+
+		if (ret == H_TOO_HARD)
+			return ret;
+
+		WARN_ON_ONCE(1);
+		kvmppc_clear_tce(stit->tbl, entry);
+	}
+
+	kvmppc_tce_put(stt, entry, tce);
 
 	return H_SUCCESS;
 }
@@ -247,6 +504,7 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	unsigned long entry, ua = 0;
 	u64 __user *tces;
 	u64 tce;
+	struct kvmppc_spapr_tce_iommu_table *stit;
 
 	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
@@ -285,6 +543,26 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		if (ret != H_SUCCESS)
 			goto unlock_exit;
 
+		if (kvmppc_gpa_to_ua(vcpu->kvm,
+				tce & ~(TCE_PCI_READ | TCE_PCI_WRITE),
+				&ua, NULL))
+			return H_PARAMETER;
+
+		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+			ret = kvmppc_tce_iommu_map(vcpu->kvm,
+					stit->tbl, entry + i, ua,
+					iommu_tce_direction(tce));
+
+			if (ret == H_SUCCESS)
+				continue;
+
+			if (ret == H_TOO_HARD)
+				goto unlock_exit;
+
+			WARN_ON_ONCE(1);
+			kvmppc_clear_tce(stit->tbl, entry);
+		}
+
 		kvmppc_tce_put(stt, entry + i, tce);
 	}
 
@@ -301,6 +579,7 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
 {
 	struct kvmppc_spapr_tce_table *stt;
 	long i, ret;
+	struct kvmppc_spapr_tce_iommu_table *stit;
 
 	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
@@ -314,6 +593,24 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
 	if (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ))
 		return H_PARAMETER;
 
+	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+		unsigned long entry = ioba >> stit->tbl->it_page_shift;
+
+		for (i = 0; i < npages; ++i) {
+			ret = kvmppc_tce_iommu_unmap(vcpu->kvm,
+					stit->tbl, entry + i);
+
+			if (ret == H_SUCCESS)
+				continue;
+
+			if (ret == H_TOO_HARD)
+				return ret;
+
+			WARN_ON_ONCE(1);
+			kvmppc_clear_tce(stit->tbl, entry);
+		}
+	}
+
 	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
 		kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
 
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 440d3ab5dc32..eda0a8f6fae8 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -40,6 +40,31 @@
 #include <asm/iommu.h>
 #include <asm/tce.h>
 
+#ifdef CONFIG_BUG
+
+#define WARN_ON_ONCE_RM(condition)	({			\
+	static bool __section(.data.unlikely) __warned;		\
+	int __ret_warn_once = !!(condition);			\
+								\
+	if (unlikely(__ret_warn_once && !__warned)) {		\
+		__warned = true;				\
+		pr_err("WARN_ON_ONCE_RM: (%s) at %s:%u\n",	\
+				__stringify(condition),		\
+				__func__, __LINE__);		\
+		dump_stack();					\
+	}							\
+	unlikely(__ret_warn_once);				\
+})
+
+#else
+
+#define WARN_ON_ONCE_RM(condition) ({				\
+	int __ret_warn_on = !!(condition);			\
+	unlikely(__ret_warn_on);				\
+})
+
+#endif
+
 #define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
 
 /*
@@ -161,11 +186,117 @@ long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
 EXPORT_SYMBOL_GPL(kvmppc_gpa_to_ua);
 
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+static void kvmppc_rm_clear_tce(struct iommu_table *tbl, unsigned long entry)
+{
+	unsigned long hpa = 0;
+	enum dma_data_direction dir = DMA_NONE;
+
+	iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
+}
+
+static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm,
+		struct iommu_table *tbl, unsigned long entry)
+{
+	struct mm_iommu_table_group_mem_t *mem = NULL;
+	const unsigned long pgsize = 1ULL << tbl->it_page_shift;
+	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+
+	if (!pua)
+		/* it_userspace allocation might be delayed */
+		return H_TOO_HARD;
+
+	pua = (void *) vmalloc_to_phys(pua);
+	if (WARN_ON_ONCE_RM(!pua))
+		return H_HARDWARE;
+
+	mem = mm_iommu_lookup_rm(kvm->mm, *pua, pgsize);
+	if (!mem)
+		return H_TOO_HARD;
+
+	mm_iommu_mapped_dec(mem);
+
+	*pua = 0;
+
+	return H_SUCCESS;
+}
+
+static long kvmppc_rm_tce_iommu_unmap(struct kvm *kvm,
+		struct iommu_table *tbl, unsigned long entry)
+{
+	enum dma_data_direction dir = DMA_NONE;
+	unsigned long hpa = 0;
+	long ret;
+
+	if (iommu_tce_xchg_rm(tbl, entry, &hpa, &dir))
+		/*
+		 * real mode xchg can fail if struct page crosses
+		 * a page boundary
+		 */
+		return H_TOO_HARD;
+
+	if (dir == DMA_NONE)
+		return H_SUCCESS;
+
+	ret = kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);
+	if (ret)
+		iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
+
+	return ret;
+}
+
+static long kvmppc_rm_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
+		unsigned long entry, unsigned long ua,
+		enum dma_data_direction dir)
+{
+	long ret;
+	unsigned long hpa = 0;
+	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+	struct mm_iommu_table_group_mem_t *mem;
+
+	if (!pua)
+		/* it_userspace allocation might be delayed */
+		return H_TOO_HARD;
+
+	mem = mm_iommu_lookup_rm(kvm->mm, ua, 1ULL << tbl->it_page_shift);
+	if (!mem)
+		return H_TOO_HARD;
+
+	if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, &hpa)))
+		return H_HARDWARE;
+
+	pua = (void *) vmalloc_to_phys(pua);
+	if (WARN_ON_ONCE_RM(!pua))
+		return H_HARDWARE;
+
+	if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem)))
+		return H_CLOSED;
+
+	ret = iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
+	if (ret) {
+		mm_iommu_mapped_dec(mem);
+		/*
+		 * real mode xchg can fail if struct page crosses
+		 * a page boundary
+		 */
+		return H_TOO_HARD;
+	}
+
+	if (dir != DMA_NONE)
+		kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);
+
+	*pua = ua;
+
+	return 0;
+}
+
 long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		unsigned long ioba, unsigned long tce)
 {
 	struct kvmppc_spapr_tce_table *stt;
 	long ret;
+	struct kvmppc_spapr_tce_iommu_table *stit;
+	unsigned long entry, ua = 0;
+	enum dma_data_direction dir;
 
 	/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
 	/* 	    liobn, ioba, tce); */
@@ -182,7 +313,32 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	if (ret != H_SUCCESS)
 		return ret;
 
-	kvmppc_tce_put(stt, ioba >> stt->page_shift, tce);
+	dir = iommu_tce_direction(tce);
+	if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm,
+			tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL))
+		return H_PARAMETER;
+
+	entry = ioba >> stt->page_shift;
+
+	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+		if (dir == DMA_NONE)
+			ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm,
+					stit->tbl, entry);
+		else
+			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm,
+					stit->tbl, entry, ua, dir);
+
+		if (ret == H_SUCCESS)
+			continue;
+
+		if (ret == H_TOO_HARD)
+			return ret;
+
+		WARN_ON_ONCE_RM(1);
+		kvmppc_rm_clear_tce(stit->tbl, entry);
+	}
+
+	kvmppc_tce_put(stt, entry, tce);
 
 	return H_SUCCESS;
 }
@@ -223,6 +379,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	unsigned long tces, entry, ua = 0;
 	unsigned long *rmap = NULL;
 	bool prereg = false;
+	struct kvmppc_spapr_tce_iommu_table *stit;
 
 	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
@@ -270,6 +427,8 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 			return H_TOO_HARD;
 
 		rmap = (void *) vmalloc_to_phys(rmap);
+		if (WARN_ON_ONCE_RM(!rmap))
+			return H_HARDWARE;
 
 		/*
 		 * Synchronize with the MMU notifier callbacks in
@@ -293,6 +452,27 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		if (ret != H_SUCCESS)
 			goto unlock_exit;
 
+		ua = 0;
+		if (kvmppc_gpa_to_ua(vcpu->kvm,
+				tce & ~(TCE_PCI_READ | TCE_PCI_WRITE),
+				&ua, NULL))
+			return H_PARAMETER;
+
+		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm,
+					stit->tbl, entry + i, ua,
+					iommu_tce_direction(tce));
+
+			if (ret == H_SUCCESS)
+				continue;
+
+			if (ret == H_TOO_HARD)
+				goto unlock_exit;
+
+			WARN_ON_ONCE_RM(1);
+			kvmppc_rm_clear_tce(stit->tbl, entry);
+		}
+
 		kvmppc_tce_put(stt, entry + i, tce);
 	}
 
@@ -309,6 +489,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 {
 	struct kvmppc_spapr_tce_table *stt;
 	long i, ret;
+	struct kvmppc_spapr_tce_iommu_table *stit;
 
 	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
@@ -322,6 +503,24 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 	if (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ))
 		return H_PARAMETER;
 
+	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+		unsigned long entry = ioba >> stit->tbl->it_page_shift;
+
+		for (i = 0; i < npages; ++i) {
+			ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm,
+					stit->tbl, entry + i);
+
+			if (ret == H_SUCCESS)
+				continue;
+
+			if (ret == H_TOO_HARD)
+				return ret;
+
+			WARN_ON_ONCE_RM(1);
+			kvmppc_rm_clear_tce(stit->tbl, entry);
+		}
+	}
+
 	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
 		kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 95c91a9de351..62bdd6c48107 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -538,6 +538,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 #ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_CAP_SPAPR_TCE:
 	case KVM_CAP_SPAPR_TCE_64:
+		/* fallthrough */
+	case KVM_CAP_SPAPR_TCE_VFIO:
 	case KVM_CAP_PPC_RTAS:
 	case KVM_CAP_PPC_FIXUP_HCALL:
 	case KVM_CAP_PPC_ENABLE_HCALL:
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index d32f239eb471..d438818e2681 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -20,6 +20,10 @@
 #include <linux/vfio.h>
 #include "vfio.h"
 
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+#include <asm/kvm_ppc.h>
+#endif
+
 struct kvm_vfio_group {
 	struct list_head node;
 	struct vfio_group *vfio_group;
@@ -89,6 +93,47 @@ static bool kvm_vfio_group_is_coherent(struct vfio_group *vfio_group)
 	return ret > 0;
 }
 
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+static int kvm_vfio_external_user_iommu_id(struct vfio_group *vfio_group)
+{
+	int (*fn)(struct vfio_group *);
+	int ret = -EINVAL;
+
+	fn = symbol_get(vfio_external_user_iommu_id);
+	if (!fn)
+		return ret;
+
+	ret = fn(vfio_group);
+
+	symbol_put(vfio_external_user_iommu_id);
+
+	return ret;
+}
+
+static struct iommu_group *kvm_vfio_group_get_iommu_group(
+		struct vfio_group *group)
+{
+	int group_id = kvm_vfio_external_user_iommu_id(group);
+
+	if (group_id < 0)
+		return NULL;
+
+	return iommu_group_get_by_id(group_id);
+}
+
+static void kvm_spapr_tce_release_vfio_group(struct kvm *kvm,
+		struct vfio_group *vfio_group)
+{
+	struct iommu_group *grp = kvm_vfio_group_get_iommu_group(vfio_group);
+
+	if (WARN_ON_ONCE(!grp))
+		return;
+
+	kvm_spapr_tce_release_iommu_group(kvm, grp);
+	iommu_group_put(grp);
+}
+#endif
+
 /*
  * Groups can use the same or different IOMMU domains.  If the same then
  * adding a new group may change the coherency of groups we've previously
@@ -211,6 +256,9 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
 
 		mutex_unlock(&kv->lock);
 
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+		kvm_spapr_tce_release_vfio_group(dev->kvm, vfio_group);
+#endif
 		kvm_vfio_group_set_kvm(vfio_group, NULL);
 
 		kvm_vfio_group_put_external_user(vfio_group);
@@ -218,6 +266,56 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
 		kvm_vfio_update_coherency(dev);
 
 		return ret;
+
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+	case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: {
+		struct kvm_vfio_spapr_tce param;
+		struct kvm_vfio *kv = dev->private;
+		struct vfio_group *vfio_group;
+		struct kvm_vfio_group *kvg;
+		struct fd f;
+		struct iommu_group *grp;
+
+		if (copy_from_user(&param, (void __user *)arg,
+				sizeof(struct kvm_vfio_spapr_tce)))
+			return -EFAULT;
+
+		f = fdget(param.groupfd);
+		if (!f.file)
+			return -EBADF;
+
+		vfio_group = kvm_vfio_group_get_external_user(f.file);
+		fdput(f);
+
+		if (IS_ERR(vfio_group))
+			return PTR_ERR(vfio_group);
+
+		grp = kvm_vfio_group_get_iommu_group(vfio_group);
+		if (WARN_ON_ONCE(!grp))
+			return -EIO;
+
+		ret = -ENOENT;
+
+		mutex_lock(&kv->lock);
+
+		list_for_each_entry(kvg, &kv->group_list, node) {
+			if (kvg->vfio_group != vfio_group)
+				continue;
+
+			ret = kvm_spapr_tce_attach_iommu_group(dev->kvm,
+					param.tablefd, grp);
+
+			break;
+		}
+
+		mutex_unlock(&kv->lock);
+
+		iommu_group_put(grp);
+		kvm_vfio_group_put_external_user(vfio_group);
+
+		return ret;
+	}
+#endif /* CONFIG_SPAPR_TCE_IOMMU */
 	}
 
 	return -ENXIO;
@@ -242,6 +340,9 @@ static int kvm_vfio_has_attr(struct kvm_device *dev,
 		switch (attr->attr) {
 		case KVM_DEV_VFIO_GROUP_ADD:
 		case KVM_DEV_VFIO_GROUP_DEL:
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+		case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE:
+#endif
 			return 0;
 		}
 
@@ -257,6 +358,9 @@ static void kvm_vfio_destroy(struct kvm_device *dev)
 	struct kvm_vfio_group *kvg, *tmp;
 
 	list_for_each_entry_safe(kvg, tmp, &kv->group_list, node) {
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+		kvm_spapr_tce_release_vfio_group(dev->kvm, kvg->vfio_group);
+#endif
 		kvm_vfio_group_set_kvm(kvg->vfio_group, NULL);
 		kvm_vfio_group_put_external_user(kvg->vfio_group);
 		list_del(&kvg->node);
-- 
2.11.0

[PATCH kernel v10 10/10] KVM: PPC: VFIO: Add in-kernel acceleration for VFIO

[Alexey Kardashevskiy]

This allows the host kernel to handle H_PUT_TCE, H_PUT_TCE_INDIRECT
and H_STUFF_TCE requests targeted an IOMMU TCE table used for VFIO
without passing them to user space which saves time on switching
to user space and back.

This adds H_PUT_TCE/H_PUT_TCE_INDIRECT/H_STUFF_TCE handlers to KVM.
KVM tries to handle a TCE request in the real mode, if failed
it passes the request to the virtual mode to complete the operation.
If it a virtual mode handler fails, the request is passed to
the user space; this is not expected to happen though.

To avoid dealing with page use counters (which is tricky in real mode),
this only accelerates SPAPR TCE IOMMU v2 clients which are required
to pre-register the userspace memory. The very first TCE request will
be handled in the VFIO SPAPR TCE driver anyway as the userspace view
of the TCE table (iommu_table::it_userspace) is not allocated till
the very first mapping happens and we cannot call vmalloc in real mode.

If we fail to update a hardware IOMMU table unexpected reason, we just
clear it and move on as there is nothing really we can do about it -
for example, if we hot plug a VFIO device to a guest, existing TCE tables
will be mirrored automatically to the hardware and there is no interface
to report to the guest about possible failures.

This adds new attribute - KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE - to
the VFIO KVM device. It takes a VFIO group fd and SPAPR TCE table fd
and associates a physical IOMMU table with the SPAPR TCE table (which
is a guest view of the hardware IOMMU table). The iommu_table object
is cached and referenced so we do not have to look up for it in real mode.

This does not implement the UNSET counterpart as there is no use for it -
once the acceleration is enabled, the existing userspace won't
disable it unless a VFIO container is destroyed; this adds necessary
cleanup to the KVM_DEV_VFIO_GROUP_DEL handler.

This advertises the new KVM_CAP_SPAPR_TCE_VFIO capability to the user
space.

This adds real mode version of WARN_ON_ONCE() as the generic version
causes problems with rcu_sched. Since we testing what vmalloc_to_phys()
returns in the code, this also adds a check for already existing
vmalloc_to_phys() call in kvmppc_rm_h_put_tce_indirect().

This finally makes use of vfio_external_user_iommu_id() which was
introduced quite some time ago and was considered for removal.

Tests show that this patch increases transmission speed from 220MB/s
to 750..1020MB/s on 10Gb network (Chelsea CXGB3 10Gb ethernet card).

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
Changes:
v10:
* fixed leaking references in virt/kvm/vfio.c
* moved code to helpers - kvm_vfio_group_get_iommu_group, kvm_spapr_tce_release_vfio_group
* fixed possible race between referencing table and destroying it via
VFIO add/remove window ioctls()

v9:
* removed referencing a group in KVM, only referencing iommu_table's now
* fixed a reference leak in KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE handler
* fixed typo in vfio.txt
* removed @argsz and @flags from struct kvm_vfio_spapr_tce

v8:
* changed all (!pua) checks to return H_TOO_HARD as ioctl() is supposed
to handle them
* changed vmalloc_to_phys() callers to return H_HARDWARE
* changed real mode iommu_tce_xchg_rm() callers to return H_TOO_HARD
and added a comment about this in the code
* changed virtual mode iommu_tce_xchg() callers to return H_HARDWARE
and do WARN_ON
* added WARN_ON_ONCE_RM(!rmap) in kvmppc_rm_h_put_tce_indirect() to
have all vmalloc_to_phys() callsites covered

v7:
* added realmode-friendly WARN_ON_ONCE_RM

v6:
* changed handling of errors returned by kvmppc_(rm_)tce_iommu_(un)map()
* moved kvmppc_gpa_to_ua() to TCE validation

v5:
* changed error codes in multiple places
* added bunch of WARN_ON() in places which should not really happen
* adde a check that an iommu table is not attached already to LIOBN
* dropped explicit calls to iommu_tce_clear_param_check/
iommu_tce_put_param_check as kvmppc_tce_validate/kvmppc_ioba_validate
call them anyway (since the previous patch)
* if we fail to update a hardware IOMMU table for unexpected reason,
this just clears the entry

v4:
* added note to the commit log about allowing multiple updates of
the same IOMMU table;
* instead of checking for if any memory was preregistered, this
returns H_TOO_HARD if a specific page was not;
* fixed comments from v3 about error handling in many places;
* simplified TCE handlers and merged IOMMU parts inline - for example,
there used to be kvmppc_h_put_tce_iommu(), now it is merged into
kvmppc_h_put_tce(); this allows to check IOBA boundaries against
the first attached table only (makes the code simpler);

v3:
* simplified not to use VFIO group notifiers
* reworked cleanup, should be cleaner/simpler now

v2:
* reworked to use new VFIO notifiers
* now same iommu_table may appear in the list several times, to be fixed later
---
 Documentation/virtual/kvm/devices/vfio.txt |  18 +-
 arch/powerpc/include/asm/kvm_host.h        |   8 +
 arch/powerpc/include/asm/kvm_ppc.h         |   4 +
 include/uapi/linux/kvm.h                   |   6 +
 arch/powerpc/kvm/book3s_64_vio.c           | 301 ++++++++++++++++++++++++++++-
 arch/powerpc/kvm/book3s_64_vio_hv.c        | 201 ++++++++++++++++++-
 arch/powerpc/kvm/powerpc.c                 |   2 +
 virt/kvm/vfio.c                            | 104 ++++++++++
 8 files changed, 639 insertions(+), 5 deletions(-)

diff --git a/Documentation/virtual/kvm/devices/vfio.txt b/Documentation/virtual/kvm/devices/vfio.txt
index ef51740c67ca..528c77c8022c 100644
--- a/Documentation/virtual/kvm/devices/vfio.txt
+++ b/Documentation/virtual/kvm/devices/vfio.txt
@@ -16,7 +16,21 @@ Groups:
 
 KVM_DEV_VFIO_GROUP attributes:
   KVM_DEV_VFIO_GROUP_ADD: Add a VFIO group to VFIO-KVM device tracking
+	kvm_device_attr.addr points to an int32_t file descriptor
+	for the VFIO group.
   KVM_DEV_VFIO_GROUP_DEL: Remove a VFIO group from VFIO-KVM device tracking
+	kvm_device_attr.addr points to an int32_t file descriptor
+	for the VFIO group.
+  KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: attaches a guest visible TCE table
+	allocated by sPAPR KVM.
+	kvm_device_attr.addr points to a struct:
 
-For each, kvm_device_attr.addr points to an int32_t file descriptor
-for the VFIO group.
+	struct kvm_vfio_spapr_tce {
+		__s32	groupfd;
+		__s32	tablefd;
+	};
+
+	where
+	@groupfd is a file descriptor for a VFIO group;
+	@tablefd is a file descriptor for a TCE table allocated via
+		KVM_CREATE_SPAPR_TCE.
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 7bba8f415627..178074e643e5 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -191,6 +191,13 @@ struct kvmppc_pginfo {
 	atomic_t refcnt;
 };
 
+struct kvmppc_spapr_tce_iommu_table {
+	struct rcu_head rcu;
+	struct list_head next;
+	struct iommu_table *tbl;
+	struct kref kref;
+};
+
 struct kvmppc_spapr_tce_table {
 	struct list_head list;
 	struct kvm *kvm;
@@ -199,6 +206,7 @@ struct kvmppc_spapr_tce_table {
 	u32 page_shift;
 	u64 offset;		/* in pages */
 	u64 size;		/* window size in pages */
+	struct list_head iommu_tables;
 	struct page *pages[0];
 };
 
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 72c2a155641f..cfd45714189e 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -164,6 +164,10 @@ extern long kvmppc_prepare_vrma(struct kvm *kvm,
 extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu,
 			struct kvm_memory_slot *memslot, unsigned long porder);
 extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
+extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
+		struct iommu_group *grp);
+extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
+		struct iommu_group *grp);
 
 extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 				struct kvm_create_spapr_tce_64 *args);
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index f5a52ffb6b58..0f8a5e6528aa 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1088,6 +1088,7 @@ struct kvm_device_attr {
 #define  KVM_DEV_VFIO_GROUP			1
 #define   KVM_DEV_VFIO_GROUP_ADD			1
 #define   KVM_DEV_VFIO_GROUP_DEL			2
+#define   KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE		3
 
 enum kvm_device_type {
 	KVM_DEV_TYPE_FSL_MPIC_20	= 1,
@@ -1109,6 +1110,11 @@ enum kvm_device_type {
 	KVM_DEV_TYPE_MAX,
 };
 
+struct kvm_vfio_spapr_tce {
+	__s32	groupfd;
+	__s32	tablefd;
+};
+
 /*
  * ioctls for VM fds
  */
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index e96a4590464c..22c67a47eaab 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -28,6 +28,8 @@
 #include <linux/hugetlb.h>
 #include <linux/list.h>
 #include <linux/anon_inodes.h>
+#include <linux/iommu.h>
+#include <linux/file.h>
 
 #include <asm/tlbflush.h>
 #include <asm/kvm_ppc.h>
@@ -40,6 +42,7 @@
 #include <asm/udbg.h>
 #include <asm/iommu.h>
 #include <asm/tce.h>
+#include <asm/mmu_context.h>
 
 static unsigned long kvmppc_tce_pages(unsigned long iommu_pages)
 {
@@ -91,6 +94,132 @@ static long kvmppc_account_memlimit(unsigned long stt_pages, bool inc)
 	return ret;
 }
 
+static void kvm_spapr_tce_iommu_table_free(struct rcu_head *head)
+{
+	struct kvmppc_spapr_tce_iommu_table *stit = container_of(head,
+			struct kvmppc_spapr_tce_iommu_table, rcu);
+
+	iommu_tce_table_put(stit->tbl);
+
+	kfree(stit);
+}
+
+static void kvm_spapr_tce_liobn_put(struct kref *kref)
+{
+	struct kvmppc_spapr_tce_iommu_table *stit = container_of(kref,
+			struct kvmppc_spapr_tce_iommu_table, kref);
+
+	list_del_rcu(&stit->next);
+
+	call_rcu(&stit->rcu, kvm_spapr_tce_iommu_table_free);
+}
+
+extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
+		struct iommu_group *grp)
+{
+	int i;
+	struct kvmppc_spapr_tce_table *stt;
+	struct kvmppc_spapr_tce_iommu_table *stit, *tmp;
+	struct iommu_table_group *table_group = NULL;
+
+	list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) {
+
+		table_group = iommu_group_get_iommudata(grp);
+		if (WARN_ON(!table_group))
+			continue;
+
+		list_for_each_entry_safe(stit, tmp, &stt->iommu_tables, next) {
+			for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+				if (table_group->tables[i] != stit->tbl)
+					continue;
+
+				kref_put(&stit->kref, kvm_spapr_tce_liobn_put);
+				return;
+			}
+		}
+	}
+}
+
+extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
+		struct iommu_group *grp)
+{
+	struct kvmppc_spapr_tce_table *stt = NULL;
+	bool found = false;
+	struct iommu_table *tbl = NULL;
+	struct iommu_table_group *table_group;
+	long i;
+	struct kvmppc_spapr_tce_iommu_table *stit;
+	struct fd f;
+
+	f = fdget(tablefd);
+	if (!f.file)
+		return -EBADF;
+
+	list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) {
+		if (stt = f.file->private_data) {
+			found = true;
+			break;
+		}
+	}
+
+	fdput(f);
+
+	if (!found)
+		return -EINVAL;
+
+	table_group = iommu_group_get_iommudata(grp);
+	if (WARN_ON(!table_group))
+		return -EFAULT;
+
+	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+		struct iommu_table *tbltmp = table_group->tables[i];
+
+		if (!tbltmp)
+			continue;
+		/*
+		 * Make sure hardware table parameters are exactly the same;
+		 * this is used in the TCE handlers where boundary checks
+		 * use only the first attached table.
+		 */
+		if ((tbltmp->it_page_shift = stt->page_shift) &&
+				(tbltmp->it_offset = stt->offset) &&
+				(tbltmp->it_size = stt->size)) {
+			/*
+			 * Reference the table to avoid races with
+			 * add/remove DMA windows.
+			 */
+			tbl = iommu_tce_table_get(tbltmp);
+			break;
+		}
+	}
+	if (!tbl)
+		return -EINVAL;
+
+	list_for_each_entry_rcu(stit, &stt->iommu_tables, next) {
+		if (tbl != stit->tbl)
+			continue;
+
+		if (!kref_get_unless_zero(&stit->kref)) {
+			/* stit is being destroyed */
+			iommu_tce_table_put(tbl);
+			return -ENOTTY;
+		}
+		/*
+		 * The table is already known to this KVM, we just increased
+		 * its KVM reference counter and can return.
+		 */
+		return 0;
+	}
+
+	stit = kzalloc(sizeof(*stit), GFP_KERNEL);
+	stit->tbl = tbl;
+	kref_init(&stit->kref);
+
+	list_add_rcu(&stit->next, &stt->iommu_tables);
+
+	return 0;
+}
+
 static void release_spapr_tce_table(struct rcu_head *head)
 {
 	struct kvmppc_spapr_tce_table *stt = container_of(head,
@@ -130,9 +259,18 @@ static int kvm_spapr_tce_mmap(struct file *file, struct vm_area_struct *vma)
 static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
 {
 	struct kvmppc_spapr_tce_table *stt = filp->private_data;
+	struct kvmppc_spapr_tce_iommu_table *stit, *tmp;
 
 	list_del_rcu(&stt->list);
 
+	list_for_each_entry_safe(stit, tmp, &stt->iommu_tables, next) {
+		WARN_ON(!kref_read(&stit->kref));
+		while (1) {
+			if (kref_put(&stit->kref, kvm_spapr_tce_liobn_put))
+				break;
+		}
+	}
+
 	kvm_put_kvm(stt->kvm);
 
 	kvmppc_account_memlimit(
@@ -183,6 +321,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 	stt->offset = args->offset;
 	stt->size = size;
 	stt->kvm = kvm;
+	INIT_LIST_HEAD_RCU(&stt->iommu_tables);
 
 	for (i = 0; i < npages; i++) {
 		stt->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
@@ -211,11 +350,101 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 	return ret;
 }
 
+static void kvmppc_clear_tce(struct iommu_table *tbl, unsigned long entry)
+{
+	unsigned long hpa = 0;
+	enum dma_data_direction dir = DMA_NONE;
+
+	iommu_tce_xchg(tbl, entry, &hpa, &dir);
+}
+
+static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm,
+		struct iommu_table *tbl, unsigned long entry)
+{
+	struct mm_iommu_table_group_mem_t *mem = NULL;
+	const unsigned long pgsize = 1ULL << tbl->it_page_shift;
+	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+
+	if (!pua)
+		/* it_userspace allocation might be delayed */
+		return H_TOO_HARD;
+
+	mem = mm_iommu_lookup(kvm->mm, *pua, pgsize);
+	if (!mem)
+		return H_TOO_HARD;
+
+	mm_iommu_mapped_dec(mem);
+
+	*pua = 0;
+
+	return H_SUCCESS;
+}
+
+static long kvmppc_tce_iommu_unmap(struct kvm *kvm,
+		struct iommu_table *tbl, unsigned long entry)
+{
+	enum dma_data_direction dir = DMA_NONE;
+	unsigned long hpa = 0;
+	long ret;
+
+	if (WARN_ON_ONCE(iommu_tce_xchg(tbl, entry, &hpa, &dir)))
+		return H_HARDWARE;
+
+	if (dir = DMA_NONE)
+		return H_SUCCESS;
+
+	ret = kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry);
+	if (ret != H_SUCCESS)
+		iommu_tce_xchg(tbl, entry, &hpa, &dir);
+
+	return ret;
+}
+
+long kvmppc_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
+		unsigned long entry, unsigned long ua,
+		enum dma_data_direction dir)
+{
+	long ret;
+	unsigned long hpa, *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+	struct mm_iommu_table_group_mem_t *mem;
+
+	if (!pua)
+		/* it_userspace allocation might be delayed */
+		return H_TOO_HARD;
+
+	mem = mm_iommu_lookup(kvm->mm, ua, 1ULL << tbl->it_page_shift);
+	if (!mem)
+		/* This only handles v2 IOMMU type, v1 is handled via ioctl() */
+		return H_TOO_HARD;
+
+	if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, &hpa)))
+		return H_HARDWARE;
+
+	if (mm_iommu_mapped_inc(mem))
+		return H_CLOSED;
+
+	ret = iommu_tce_xchg(tbl, entry, &hpa, &dir);
+	if (WARN_ON_ONCE(ret)) {
+		mm_iommu_mapped_dec(mem);
+		return H_HARDWARE;
+	}
+
+	if (dir != DMA_NONE)
+		kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry);
+
+	*pua = ua;
+
+	return 0;
+}
+
 long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		      unsigned long ioba, unsigned long tce)
 {
 	struct kvmppc_spapr_tce_table *stt;
-	long ret;
+	long ret, idx;
+	struct kvmppc_spapr_tce_iommu_table *stit;
+	unsigned long entry, ua = 0;
+	enum dma_data_direction dir;
 
 	/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
 	/* 	    liobn, ioba, tce); */
@@ -232,7 +461,35 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	if (ret != H_SUCCESS)
 		return ret;
 
-	kvmppc_tce_put(stt, ioba >> stt->page_shift, tce);
+	dir = iommu_tce_direction(tce);
+	if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm,
+			tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL))
+		return H_PARAMETER;
+
+	entry = ioba >> stt->page_shift;
+
+	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+		if (dir = DMA_NONE) {
+			ret = kvmppc_tce_iommu_unmap(vcpu->kvm,
+					stit->tbl, entry);
+		} else {
+			idx = srcu_read_lock(&vcpu->kvm->srcu);
+			ret = kvmppc_tce_iommu_map(vcpu->kvm, stit->tbl,
+					entry, ua, dir);
+			srcu_read_unlock(&vcpu->kvm->srcu, idx);
+		}
+
+		if (ret = H_SUCCESS)
+			continue;
+
+		if (ret = H_TOO_HARD)
+			return ret;
+
+		WARN_ON_ONCE(1);
+		kvmppc_clear_tce(stit->tbl, entry);
+	}
+
+	kvmppc_tce_put(stt, entry, tce);
 
 	return H_SUCCESS;
 }
@@ -247,6 +504,7 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	unsigned long entry, ua = 0;
 	u64 __user *tces;
 	u64 tce;
+	struct kvmppc_spapr_tce_iommu_table *stit;
 
 	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
@@ -285,6 +543,26 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		if (ret != H_SUCCESS)
 			goto unlock_exit;
 
+		if (kvmppc_gpa_to_ua(vcpu->kvm,
+				tce & ~(TCE_PCI_READ | TCE_PCI_WRITE),
+				&ua, NULL))
+			return H_PARAMETER;
+
+		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+			ret = kvmppc_tce_iommu_map(vcpu->kvm,
+					stit->tbl, entry + i, ua,
+					iommu_tce_direction(tce));
+
+			if (ret = H_SUCCESS)
+				continue;
+
+			if (ret = H_TOO_HARD)
+				goto unlock_exit;
+
+			WARN_ON_ONCE(1);
+			kvmppc_clear_tce(stit->tbl, entry);
+		}
+
 		kvmppc_tce_put(stt, entry + i, tce);
 	}
 
@@ -301,6 +579,7 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
 {
 	struct kvmppc_spapr_tce_table *stt;
 	long i, ret;
+	struct kvmppc_spapr_tce_iommu_table *stit;
 
 	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
@@ -314,6 +593,24 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
 	if (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ))
 		return H_PARAMETER;
 
+	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+		unsigned long entry = ioba >> stit->tbl->it_page_shift;
+
+		for (i = 0; i < npages; ++i) {
+			ret = kvmppc_tce_iommu_unmap(vcpu->kvm,
+					stit->tbl, entry + i);
+
+			if (ret = H_SUCCESS)
+				continue;
+
+			if (ret = H_TOO_HARD)
+				return ret;
+
+			WARN_ON_ONCE(1);
+			kvmppc_clear_tce(stit->tbl, entry);
+		}
+	}
+
 	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
 		kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
 
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 440d3ab5dc32..eda0a8f6fae8 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -40,6 +40,31 @@
 #include <asm/iommu.h>
 #include <asm/tce.h>
 
+#ifdef CONFIG_BUG
+
+#define WARN_ON_ONCE_RM(condition)	({			\
+	static bool __section(.data.unlikely) __warned;		\
+	int __ret_warn_once = !!(condition);			\
+								\
+	if (unlikely(__ret_warn_once && !__warned)) {		\
+		__warned = true;				\
+		pr_err("WARN_ON_ONCE_RM: (%s) at %s:%u\n",	\
+				__stringify(condition),		\
+				__func__, __LINE__);		\
+		dump_stack();					\
+	}							\
+	unlikely(__ret_warn_once);				\
+})
+
+#else
+
+#define WARN_ON_ONCE_RM(condition) ({				\
+	int __ret_warn_on = !!(condition);			\
+	unlikely(__ret_warn_on);				\
+})
+
+#endif
+
 #define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
 
 /*
@@ -161,11 +186,117 @@ long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
 EXPORT_SYMBOL_GPL(kvmppc_gpa_to_ua);
 
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+static void kvmppc_rm_clear_tce(struct iommu_table *tbl, unsigned long entry)
+{
+	unsigned long hpa = 0;
+	enum dma_data_direction dir = DMA_NONE;
+
+	iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
+}
+
+static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm,
+		struct iommu_table *tbl, unsigned long entry)
+{
+	struct mm_iommu_table_group_mem_t *mem = NULL;
+	const unsigned long pgsize = 1ULL << tbl->it_page_shift;
+	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+
+	if (!pua)
+		/* it_userspace allocation might be delayed */
+		return H_TOO_HARD;
+
+	pua = (void *) vmalloc_to_phys(pua);
+	if (WARN_ON_ONCE_RM(!pua))
+		return H_HARDWARE;
+
+	mem = mm_iommu_lookup_rm(kvm->mm, *pua, pgsize);
+	if (!mem)
+		return H_TOO_HARD;
+
+	mm_iommu_mapped_dec(mem);
+
+	*pua = 0;
+
+	return H_SUCCESS;
+}
+
+static long kvmppc_rm_tce_iommu_unmap(struct kvm *kvm,
+		struct iommu_table *tbl, unsigned long entry)
+{
+	enum dma_data_direction dir = DMA_NONE;
+	unsigned long hpa = 0;
+	long ret;
+
+	if (iommu_tce_xchg_rm(tbl, entry, &hpa, &dir))
+		/*
+		 * real mode xchg can fail if struct page crosses
+		 * a page boundary
+		 */
+		return H_TOO_HARD;
+
+	if (dir = DMA_NONE)
+		return H_SUCCESS;
+
+	ret = kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);
+	if (ret)
+		iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
+
+	return ret;
+}
+
+static long kvmppc_rm_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
+		unsigned long entry, unsigned long ua,
+		enum dma_data_direction dir)
+{
+	long ret;
+	unsigned long hpa = 0;
+	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+	struct mm_iommu_table_group_mem_t *mem;
+
+	if (!pua)
+		/* it_userspace allocation might be delayed */
+		return H_TOO_HARD;
+
+	mem = mm_iommu_lookup_rm(kvm->mm, ua, 1ULL << tbl->it_page_shift);
+	if (!mem)
+		return H_TOO_HARD;
+
+	if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, &hpa)))
+		return H_HARDWARE;
+
+	pua = (void *) vmalloc_to_phys(pua);
+	if (WARN_ON_ONCE_RM(!pua))
+		return H_HARDWARE;
+
+	if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem)))
+		return H_CLOSED;
+
+	ret = iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
+	if (ret) {
+		mm_iommu_mapped_dec(mem);
+		/*
+		 * real mode xchg can fail if struct page crosses
+		 * a page boundary
+		 */
+		return H_TOO_HARD;
+	}
+
+	if (dir != DMA_NONE)
+		kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);
+
+	*pua = ua;
+
+	return 0;
+}
+
 long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		unsigned long ioba, unsigned long tce)
 {
 	struct kvmppc_spapr_tce_table *stt;
 	long ret;
+	struct kvmppc_spapr_tce_iommu_table *stit;
+	unsigned long entry, ua = 0;
+	enum dma_data_direction dir;
 
 	/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
 	/* 	    liobn, ioba, tce); */
@@ -182,7 +313,32 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	if (ret != H_SUCCESS)
 		return ret;
 
-	kvmppc_tce_put(stt, ioba >> stt->page_shift, tce);
+	dir = iommu_tce_direction(tce);
+	if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm,
+			tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL))
+		return H_PARAMETER;
+
+	entry = ioba >> stt->page_shift;
+
+	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+		if (dir = DMA_NONE)
+			ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm,
+					stit->tbl, entry);
+		else
+			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm,
+					stit->tbl, entry, ua, dir);
+
+		if (ret = H_SUCCESS)
+			continue;
+
+		if (ret = H_TOO_HARD)
+			return ret;
+
+		WARN_ON_ONCE_RM(1);
+		kvmppc_rm_clear_tce(stit->tbl, entry);
+	}
+
+	kvmppc_tce_put(stt, entry, tce);
 
 	return H_SUCCESS;
 }
@@ -223,6 +379,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	unsigned long tces, entry, ua = 0;
 	unsigned long *rmap = NULL;
 	bool prereg = false;
+	struct kvmppc_spapr_tce_iommu_table *stit;
 
 	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
@@ -270,6 +427,8 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 			return H_TOO_HARD;
 
 		rmap = (void *) vmalloc_to_phys(rmap);
+		if (WARN_ON_ONCE_RM(!rmap))
+			return H_HARDWARE;
 
 		/*
 		 * Synchronize with the MMU notifier callbacks in
@@ -293,6 +452,27 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		if (ret != H_SUCCESS)
 			goto unlock_exit;
 
+		ua = 0;
+		if (kvmppc_gpa_to_ua(vcpu->kvm,
+				tce & ~(TCE_PCI_READ | TCE_PCI_WRITE),
+				&ua, NULL))
+			return H_PARAMETER;
+
+		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm,
+					stit->tbl, entry + i, ua,
+					iommu_tce_direction(tce));
+
+			if (ret = H_SUCCESS)
+				continue;
+
+			if (ret = H_TOO_HARD)
+				goto unlock_exit;
+
+			WARN_ON_ONCE_RM(1);
+			kvmppc_rm_clear_tce(stit->tbl, entry);
+		}
+
 		kvmppc_tce_put(stt, entry + i, tce);
 	}
 
@@ -309,6 +489,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 {
 	struct kvmppc_spapr_tce_table *stt;
 	long i, ret;
+	struct kvmppc_spapr_tce_iommu_table *stit;
 
 	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
@@ -322,6 +503,24 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 	if (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ))
 		return H_PARAMETER;
 
+	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+		unsigned long entry = ioba >> stit->tbl->it_page_shift;
+
+		for (i = 0; i < npages; ++i) {
+			ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm,
+					stit->tbl, entry + i);
+
+			if (ret = H_SUCCESS)
+				continue;
+
+			if (ret = H_TOO_HARD)
+				return ret;
+
+			WARN_ON_ONCE_RM(1);
+			kvmppc_rm_clear_tce(stit->tbl, entry);
+		}
+	}
+
 	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
 		kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 95c91a9de351..62bdd6c48107 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -538,6 +538,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 #ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_CAP_SPAPR_TCE:
 	case KVM_CAP_SPAPR_TCE_64:
+		/* fallthrough */
+	case KVM_CAP_SPAPR_TCE_VFIO:
 	case KVM_CAP_PPC_RTAS:
 	case KVM_CAP_PPC_FIXUP_HCALL:
 	case KVM_CAP_PPC_ENABLE_HCALL:
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index d32f239eb471..d438818e2681 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -20,6 +20,10 @@
 #include <linux/vfio.h>
 #include "vfio.h"
 
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+#include <asm/kvm_ppc.h>
+#endif
+
 struct kvm_vfio_group {
 	struct list_head node;
 	struct vfio_group *vfio_group;
@@ -89,6 +93,47 @@ static bool kvm_vfio_group_is_coherent(struct vfio_group *vfio_group)
 	return ret > 0;
 }
 
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+static int kvm_vfio_external_user_iommu_id(struct vfio_group *vfio_group)
+{
+	int (*fn)(struct vfio_group *);
+	int ret = -EINVAL;
+
+	fn = symbol_get(vfio_external_user_iommu_id);
+	if (!fn)
+		return ret;
+
+	ret = fn(vfio_group);
+
+	symbol_put(vfio_external_user_iommu_id);
+
+	return ret;
+}
+
+static struct iommu_group *kvm_vfio_group_get_iommu_group(
+		struct vfio_group *group)
+{
+	int group_id = kvm_vfio_external_user_iommu_id(group);
+
+	if (group_id < 0)
+		return NULL;
+
+	return iommu_group_get_by_id(group_id);
+}
+
+static void kvm_spapr_tce_release_vfio_group(struct kvm *kvm,
+		struct vfio_group *vfio_group)
+{
+	struct iommu_group *grp = kvm_vfio_group_get_iommu_group(vfio_group);
+
+	if (WARN_ON_ONCE(!grp))
+		return;
+
+	kvm_spapr_tce_release_iommu_group(kvm, grp);
+	iommu_group_put(grp);
+}
+#endif
+
 /*
  * Groups can use the same or different IOMMU domains.  If the same then
  * adding a new group may change the coherency of groups we've previously
@@ -211,6 +256,9 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
 
 		mutex_unlock(&kv->lock);
 
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+		kvm_spapr_tce_release_vfio_group(dev->kvm, vfio_group);
+#endif
 		kvm_vfio_group_set_kvm(vfio_group, NULL);
 
 		kvm_vfio_group_put_external_user(vfio_group);
@@ -218,6 +266,56 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
 		kvm_vfio_update_coherency(dev);
 
 		return ret;
+
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+	case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: {
+		struct kvm_vfio_spapr_tce param;
+		struct kvm_vfio *kv = dev->private;
+		struct vfio_group *vfio_group;
+		struct kvm_vfio_group *kvg;
+		struct fd f;
+		struct iommu_group *grp;
+
+		if (copy_from_user(&param, (void __user *)arg,
+				sizeof(struct kvm_vfio_spapr_tce)))
+			return -EFAULT;
+
+		f = fdget(param.groupfd);
+		if (!f.file)
+			return -EBADF;
+
+		vfio_group = kvm_vfio_group_get_external_user(f.file);
+		fdput(f);
+
+		if (IS_ERR(vfio_group))
+			return PTR_ERR(vfio_group);
+
+		grp = kvm_vfio_group_get_iommu_group(vfio_group);
+		if (WARN_ON_ONCE(!grp))
+			return -EIO;
+
+		ret = -ENOENT;
+
+		mutex_lock(&kv->lock);
+
+		list_for_each_entry(kvg, &kv->group_list, node) {
+			if (kvg->vfio_group != vfio_group)
+				continue;
+
+			ret = kvm_spapr_tce_attach_iommu_group(dev->kvm,
+					param.tablefd, grp);
+
+			break;
+		}
+
+		mutex_unlock(&kv->lock);
+
+		iommu_group_put(grp);
+		kvm_vfio_group_put_external_user(vfio_group);
+
+		return ret;
+	}
+#endif /* CONFIG_SPAPR_TCE_IOMMU */
 	}
 
 	return -ENXIO;
@@ -242,6 +340,9 @@ static int kvm_vfio_has_attr(struct kvm_device *dev,
 		switch (attr->attr) {
 		case KVM_DEV_VFIO_GROUP_ADD:
 		case KVM_DEV_VFIO_GROUP_DEL:
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+		case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE:
+#endif
 			return 0;
 		}
 
@@ -257,6 +358,9 @@ static void kvm_vfio_destroy(struct kvm_device *dev)
 	struct kvm_vfio_group *kvg, *tmp;
 
 	list_for_each_entry_safe(kvg, tmp, &kv->group_list, node) {
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+		kvm_spapr_tce_release_vfio_group(dev->kvm, kvg->vfio_group);
+#endif
 		kvm_vfio_group_set_kvm(kvg->vfio_group, NULL);
 		kvm_vfio_group_put_external_user(kvg->vfio_group);
 		list_del(&kvg->node);
-- 
2.11.0

Re: [PATCH kernel v10 10/10] KVM: PPC: VFIO: Add in-kernel acceleration for VFIO

[Alex Williamson]

On Fri, 17 Mar 2017 16:09:59 +1100
Alexey Kardashevskiy <aik@ozlabs.ru> wrote:

> This allows the host kernel to handle H_PUT_TCE, H_PUT_TCE_INDIRECT
> and H_STUFF_TCE requests targeted an IOMMU TCE table used for VFIO
> without passing them to user space which saves time on switching
> to user space and back.
> 
> This adds H_PUT_TCE/H_PUT_TCE_INDIRECT/H_STUFF_TCE handlers to KVM.
> KVM tries to handle a TCE request in the real mode, if failed
> it passes the request to the virtual mode to complete the operation.
> If it a virtual mode handler fails, the request is passed to
> the user space; this is not expected to happen though.
> 
> To avoid dealing with page use counters (which is tricky in real mode),
> this only accelerates SPAPR TCE IOMMU v2 clients which are required
> to pre-register the userspace memory. The very first TCE request will
> be handled in the VFIO SPAPR TCE driver anyway as the userspace view
> of the TCE table (iommu_table::it_userspace) is not allocated till
> the very first mapping happens and we cannot call vmalloc in real mode.
> 
> If we fail to update a hardware IOMMU table unexpected reason, we just
> clear it and move on as there is nothing really we can do about it -
> for example, if we hot plug a VFIO device to a guest, existing TCE tables
> will be mirrored automatically to the hardware and there is no interface
> to report to the guest about possible failures.
> 
> This adds new attribute - KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE - to
> the VFIO KVM device. It takes a VFIO group fd and SPAPR TCE table fd
> and associates a physical IOMMU table with the SPAPR TCE table (which
> is a guest view of the hardware IOMMU table). The iommu_table object
> is cached and referenced so we do not have to look up for it in real mode.
> 
> This does not implement the UNSET counterpart as there is no use for it -
> once the acceleration is enabled, the existing userspace won't
> disable it unless a VFIO container is destroyed; this adds necessary
> cleanup to the KVM_DEV_VFIO_GROUP_DEL handler.
> 
> This advertises the new KVM_CAP_SPAPR_TCE_VFIO capability to the user
> space.
> 
> This adds real mode version of WARN_ON_ONCE() as the generic version
> causes problems with rcu_sched. Since we testing what vmalloc_to_phys()
> returns in the code, this also adds a check for already existing
> vmalloc_to_phys() call in kvmppc_rm_h_put_tce_indirect().
> 
> This finally makes use of vfio_external_user_iommu_id() which was
> introduced quite some time ago and was considered for removal.
> 
> Tests show that this patch increases transmission speed from 220MB/s
> to 750..1020MB/s on 10Gb network (Chelsea CXGB3 10Gb ethernet card).
> 
> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
> ---
> Changes:
> v10:
> * fixed leaking references in virt/kvm/vfio.c
> * moved code to helpers - kvm_vfio_group_get_iommu_group, kvm_spapr_tce_release_vfio_group
> * fixed possible race between referencing table and destroying it via
> VFIO add/remove window ioctls()
> 
> v9:
> * removed referencing a group in KVM, only referencing iommu_table's now
> * fixed a reference leak in KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE handler
> * fixed typo in vfio.txt
> * removed @argsz and @flags from struct kvm_vfio_spapr_tce
> 
> v8:
> * changed all (!pua) checks to return H_TOO_HARD as ioctl() is supposed
> to handle them
> * changed vmalloc_to_phys() callers to return H_HARDWARE
> * changed real mode iommu_tce_xchg_rm() callers to return H_TOO_HARD
> and added a comment about this in the code
> * changed virtual mode iommu_tce_xchg() callers to return H_HARDWARE
> and do WARN_ON
> * added WARN_ON_ONCE_RM(!rmap) in kvmppc_rm_h_put_tce_indirect() to
> have all vmalloc_to_phys() callsites covered
> 
> v7:
> * added realmode-friendly WARN_ON_ONCE_RM
> 
> v6:
> * changed handling of errors returned by kvmppc_(rm_)tce_iommu_(un)map()
> * moved kvmppc_gpa_to_ua() to TCE validation
> 
> v5:
> * changed error codes in multiple places
> * added bunch of WARN_ON() in places which should not really happen
> * adde a check that an iommu table is not attached already to LIOBN
> * dropped explicit calls to iommu_tce_clear_param_check/
> iommu_tce_put_param_check as kvmppc_tce_validate/kvmppc_ioba_validate
> call them anyway (since the previous patch)
> * if we fail to update a hardware IOMMU table for unexpected reason,
> this just clears the entry
> 
> v4:
> * added note to the commit log about allowing multiple updates of
> the same IOMMU table;
> * instead of checking for if any memory was preregistered, this
> returns H_TOO_HARD if a specific page was not;
> * fixed comments from v3 about error handling in many places;
> * simplified TCE handlers and merged IOMMU parts inline - for example,
> there used to be kvmppc_h_put_tce_iommu(), now it is merged into
> kvmppc_h_put_tce(); this allows to check IOBA boundaries against
> the first attached table only (makes the code simpler);
> 
> v3:
> * simplified not to use VFIO group notifiers
> * reworked cleanup, should be cleaner/simpler now
> 
> v2:
> * reworked to use new VFIO notifiers
> * now same iommu_table may appear in the list several times, to be fixed later
> ---
>  Documentation/virtual/kvm/devices/vfio.txt |  18 +-
>  arch/powerpc/include/asm/kvm_host.h        |   8 +
>  arch/powerpc/include/asm/kvm_ppc.h         |   4 +
>  include/uapi/linux/kvm.h                   |   6 +
>  arch/powerpc/kvm/book3s_64_vio.c           | 301 ++++++++++++++++++++++++++++-
>  arch/powerpc/kvm/book3s_64_vio_hv.c        | 201 ++++++++++++++++++-
>  arch/powerpc/kvm/powerpc.c                 |   2 +
>  virt/kvm/vfio.c                            | 104 ++++++++++
>  8 files changed, 639 insertions(+), 5 deletions(-)
> 
> diff --git a/Documentation/virtual/kvm/devices/vfio.txt b/Documentation/virtual/kvm/devices/vfio.txt
> index ef51740c67ca..528c77c8022c 100644
> --- a/Documentation/virtual/kvm/devices/vfio.txt
> +++ b/Documentation/virtual/kvm/devices/vfio.txt
> @@ -16,7 +16,21 @@ Groups:
>  
>  KVM_DEV_VFIO_GROUP attributes:
>    KVM_DEV_VFIO_GROUP_ADD: Add a VFIO group to VFIO-KVM device tracking
> +	kvm_device_attr.addr points to an int32_t file descriptor
> +	for the VFIO group.
>    KVM_DEV_VFIO_GROUP_DEL: Remove a VFIO group from VFIO-KVM device tracking
> +	kvm_device_attr.addr points to an int32_t file descriptor
> +	for the VFIO group.
> +  KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: attaches a guest visible TCE table
> +	allocated by sPAPR KVM.
> +	kvm_device_attr.addr points to a struct:
>  
> -For each, kvm_device_attr.addr points to an int32_t file descriptor
> -for the VFIO group.
> +	struct kvm_vfio_spapr_tce {
> +		__s32	groupfd;
> +		__s32	tablefd;
> +	};
> +
> +	where
> +	@groupfd is a file descriptor for a VFIO group;
> +	@tablefd is a file descriptor for a TCE table allocated via
> +		KVM_CREATE_SPAPR_TCE.
> diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
> index 7bba8f415627..178074e643e5 100644
> --- a/arch/powerpc/include/asm/kvm_host.h
> +++ b/arch/powerpc/include/asm/kvm_host.h
> @@ -191,6 +191,13 @@ struct kvmppc_pginfo {
>  	atomic_t refcnt;
>  };
>  
> +struct kvmppc_spapr_tce_iommu_table {
> +	struct rcu_head rcu;
> +	struct list_head next;
> +	struct iommu_table *tbl;
> +	struct kref kref;
> +};
> +
>  struct kvmppc_spapr_tce_table {
>  	struct list_head list;
>  	struct kvm *kvm;
> @@ -199,6 +206,7 @@ struct kvmppc_spapr_tce_table {
>  	u32 page_shift;
>  	u64 offset;		/* in pages */
>  	u64 size;		/* window size in pages */
> +	struct list_head iommu_tables;
>  	struct page *pages[0];
>  };
>  
> diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
> index 72c2a155641f..cfd45714189e 100644
> --- a/arch/powerpc/include/asm/kvm_ppc.h
> +++ b/arch/powerpc/include/asm/kvm_ppc.h
> @@ -164,6 +164,10 @@ extern long kvmppc_prepare_vrma(struct kvm *kvm,
>  extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu,
>  			struct kvm_memory_slot *memslot, unsigned long porder);
>  extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
> +extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
> +		struct iommu_group *grp);
> +extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
> +		struct iommu_group *grp);
>  
>  extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
>  				struct kvm_create_spapr_tce_64 *args);
> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> index f5a52ffb6b58..0f8a5e6528aa 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -1088,6 +1088,7 @@ struct kvm_device_attr {
>  #define  KVM_DEV_VFIO_GROUP			1
>  #define   KVM_DEV_VFIO_GROUP_ADD			1
>  #define   KVM_DEV_VFIO_GROUP_DEL			2
> +#define   KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE		3
>  
>  enum kvm_device_type {
>  	KVM_DEV_TYPE_FSL_MPIC_20	= 1,
> @@ -1109,6 +1110,11 @@ enum kvm_device_type {
>  	KVM_DEV_TYPE_MAX,
>  };
>  
> +struct kvm_vfio_spapr_tce {
> +	__s32	groupfd;
> +	__s32	tablefd;
> +};
> +
>  /*
>   * ioctls for VM fds
>   */
> diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
> index e96a4590464c..22c67a47eaab 100644
> --- a/arch/powerpc/kvm/book3s_64_vio.c
> +++ b/arch/powerpc/kvm/book3s_64_vio.c
> @@ -28,6 +28,8 @@
>  #include <linux/hugetlb.h>
>  #include <linux/list.h>
>  #include <linux/anon_inodes.h>
> +#include <linux/iommu.h>
> +#include <linux/file.h>
>  
>  #include <asm/tlbflush.h>
>  #include <asm/kvm_ppc.h>
> @@ -40,6 +42,7 @@
>  #include <asm/udbg.h>
>  #include <asm/iommu.h>
>  #include <asm/tce.h>
> +#include <asm/mmu_context.h>
>  
>  static unsigned long kvmppc_tce_pages(unsigned long iommu_pages)
>  {
> @@ -91,6 +94,132 @@ static long kvmppc_account_memlimit(unsigned long stt_pages, bool inc)
>  	return ret;
>  }
>  
> +static void kvm_spapr_tce_iommu_table_free(struct rcu_head *head)
> +{
> +	struct kvmppc_spapr_tce_iommu_table *stit = container_of(head,
> +			struct kvmppc_spapr_tce_iommu_table, rcu);
> +
> +	iommu_tce_table_put(stit->tbl);
> +
> +	kfree(stit);
> +}
> +
> +static void kvm_spapr_tce_liobn_put(struct kref *kref)
> +{
> +	struct kvmppc_spapr_tce_iommu_table *stit = container_of(kref,
> +			struct kvmppc_spapr_tce_iommu_table, kref);
> +
> +	list_del_rcu(&stit->next);
> +
> +	call_rcu(&stit->rcu, kvm_spapr_tce_iommu_table_free);
> +}
> +
> +extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
> +		struct iommu_group *grp)
> +{
> +	int i;
> +	struct kvmppc_spapr_tce_table *stt;
> +	struct kvmppc_spapr_tce_iommu_table *stit, *tmp;
> +	struct iommu_table_group *table_group = NULL;
> +
> +	list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) {
> +
> +		table_group = iommu_group_get_iommudata(grp);
> +		if (WARN_ON(!table_group))
> +			continue;
> +
> +		list_for_each_entry_safe(stit, tmp, &stt->iommu_tables, next) {
> +			for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
> +				if (table_group->tables[i] != stit->tbl)
> +					continue;
> +
> +				kref_put(&stit->kref, kvm_spapr_tce_liobn_put);
> +				return;
> +			}
> +		}
> +	}
> +}
> +
> +extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
> +		struct iommu_group *grp)
> +{
> +	struct kvmppc_spapr_tce_table *stt = NULL;
> +	bool found = false;
> +	struct iommu_table *tbl = NULL;
> +	struct iommu_table_group *table_group;
> +	long i;
> +	struct kvmppc_spapr_tce_iommu_table *stit;
> +	struct fd f;
> +
> +	f = fdget(tablefd);
> +	if (!f.file)
> +		return -EBADF;
> +
> +	list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) {
> +		if (stt == f.file->private_data) {
> +			found = true;
> +			break;
> +		}
> +	}
> +
> +	fdput(f);
> +
> +	if (!found)
> +		return -EINVAL;
> +
> +	table_group = iommu_group_get_iommudata(grp);
> +	if (WARN_ON(!table_group))
> +		return -EFAULT;
> +
> +	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
> +		struct iommu_table *tbltmp = table_group->tables[i];
> +
> +		if (!tbltmp)
> +			continue;
> +		/*
> +		 * Make sure hardware table parameters are exactly the same;
> +		 * this is used in the TCE handlers where boundary checks
> +		 * use only the first attached table.
> +		 */
> +		if ((tbltmp->it_page_shift == stt->page_shift) &&
> +				(tbltmp->it_offset == stt->offset) &&
> +				(tbltmp->it_size == stt->size)) {
> +			/*
> +			 * Reference the table to avoid races with
> +			 * add/remove DMA windows.
> +			 */
> +			tbl = iommu_tce_table_get(tbltmp);
> +			break;
> +		}
> +	}
> +	if (!tbl)
> +		return -EINVAL;
> +
> +	list_for_each_entry_rcu(stit, &stt->iommu_tables, next) {
> +		if (tbl != stit->tbl)
> +			continue;
> +
> +		if (!kref_get_unless_zero(&stit->kref)) {
> +			/* stit is being destroyed */
> +			iommu_tce_table_put(tbl);
> +			return -ENOTTY;
> +		}
> +		/*
> +		 * The table is already known to this KVM, we just increased
> +		 * its KVM reference counter and can return.
> +		 */
> +		return 0;
> +	}
> +
> +	stit = kzalloc(sizeof(*stit), GFP_KERNEL);
> +	stit->tbl = tbl;
> +	kref_init(&stit->kref);
> +
> +	list_add_rcu(&stit->next, &stt->iommu_tables);
> +
> +	return 0;
> +}
> +
>  static void release_spapr_tce_table(struct rcu_head *head)
>  {
>  	struct kvmppc_spapr_tce_table *stt = container_of(head,
> @@ -130,9 +259,18 @@ static int kvm_spapr_tce_mmap(struct file *file, struct vm_area_struct *vma)
>  static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
>  {
>  	struct kvmppc_spapr_tce_table *stt = filp->private_data;
> +	struct kvmppc_spapr_tce_iommu_table *stit, *tmp;
>  
>  	list_del_rcu(&stt->list);
>  
> +	list_for_each_entry_safe(stit, tmp, &stt->iommu_tables, next) {
> +		WARN_ON(!kref_read(&stit->kref));
> +		while (1) {
> +			if (kref_put(&stit->kref, kvm_spapr_tce_liobn_put))
> +				break;
> +		}
> +	}
> +
>  	kvm_put_kvm(stt->kvm);
>  
>  	kvmppc_account_memlimit(
> @@ -183,6 +321,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
>  	stt->offset = args->offset;
>  	stt->size = size;
>  	stt->kvm = kvm;
> +	INIT_LIST_HEAD_RCU(&stt->iommu_tables);
>  
>  	for (i = 0; i < npages; i++) {
>  		stt->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
> @@ -211,11 +350,101 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
>  	return ret;
>  }
>  
> +static void kvmppc_clear_tce(struct iommu_table *tbl, unsigned long entry)
> +{
> +	unsigned long hpa = 0;
> +	enum dma_data_direction dir = DMA_NONE;
> +
> +	iommu_tce_xchg(tbl, entry, &hpa, &dir);
> +}
> +
> +static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm,
> +		struct iommu_table *tbl, unsigned long entry)
> +{
> +	struct mm_iommu_table_group_mem_t *mem = NULL;
> +	const unsigned long pgsize = 1ULL << tbl->it_page_shift;
> +	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
> +
> +	if (!pua)
> +		/* it_userspace allocation might be delayed */
> +		return H_TOO_HARD;
> +
> +	mem = mm_iommu_lookup(kvm->mm, *pua, pgsize);
> +	if (!mem)
> +		return H_TOO_HARD;
> +
> +	mm_iommu_mapped_dec(mem);
> +
> +	*pua = 0;
> +
> +	return H_SUCCESS;
> +}
> +
> +static long kvmppc_tce_iommu_unmap(struct kvm *kvm,
> +		struct iommu_table *tbl, unsigned long entry)
> +{
> +	enum dma_data_direction dir = DMA_NONE;
> +	unsigned long hpa = 0;
> +	long ret;
> +
> +	if (WARN_ON_ONCE(iommu_tce_xchg(tbl, entry, &hpa, &dir)))
> +		return H_HARDWARE;
> +
> +	if (dir == DMA_NONE)
> +		return H_SUCCESS;
> +
> +	ret = kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry);
> +	if (ret != H_SUCCESS)
> +		iommu_tce_xchg(tbl, entry, &hpa, &dir);
> +
> +	return ret;
> +}
> +
> +long kvmppc_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
> +		unsigned long entry, unsigned long ua,
> +		enum dma_data_direction dir)
> +{
> +	long ret;
> +	unsigned long hpa, *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
> +	struct mm_iommu_table_group_mem_t *mem;
> +
> +	if (!pua)
> +		/* it_userspace allocation might be delayed */
> +		return H_TOO_HARD;
> +
> +	mem = mm_iommu_lookup(kvm->mm, ua, 1ULL << tbl->it_page_shift);
> +	if (!mem)
> +		/* This only handles v2 IOMMU type, v1 is handled via ioctl() */
> +		return H_TOO_HARD;
> +
> +	if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, &hpa)))
> +		return H_HARDWARE;
> +
> +	if (mm_iommu_mapped_inc(mem))
> +		return H_CLOSED;
> +
> +	ret = iommu_tce_xchg(tbl, entry, &hpa, &dir);
> +	if (WARN_ON_ONCE(ret)) {
> +		mm_iommu_mapped_dec(mem);
> +		return H_HARDWARE;
> +	}
> +
> +	if (dir != DMA_NONE)
> +		kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry);
> +
> +	*pua = ua;
> +
> +	return 0;
> +}
> +
>  long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>  		      unsigned long ioba, unsigned long tce)
>  {
>  	struct kvmppc_spapr_tce_table *stt;
> -	long ret;
> +	long ret, idx;
> +	struct kvmppc_spapr_tce_iommu_table *stit;
> +	unsigned long entry, ua = 0;
> +	enum dma_data_direction dir;
>  
>  	/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
>  	/* 	    liobn, ioba, tce); */
> @@ -232,7 +461,35 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>  	if (ret != H_SUCCESS)
>  		return ret;
>  
> -	kvmppc_tce_put(stt, ioba >> stt->page_shift, tce);
> +	dir = iommu_tce_direction(tce);
> +	if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm,
> +			tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL))
> +		return H_PARAMETER;
> +
> +	entry = ioba >> stt->page_shift;
> +
> +	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
> +		if (dir == DMA_NONE) {
> +			ret = kvmppc_tce_iommu_unmap(vcpu->kvm,
> +					stit->tbl, entry);
> +		} else {
> +			idx = srcu_read_lock(&vcpu->kvm->srcu);
> +			ret = kvmppc_tce_iommu_map(vcpu->kvm, stit->tbl,
> +					entry, ua, dir);
> +			srcu_read_unlock(&vcpu->kvm->srcu, idx);
> +		}
> +
> +		if (ret == H_SUCCESS)
> +			continue;
> +
> +		if (ret == H_TOO_HARD)
> +			return ret;
> +
> +		WARN_ON_ONCE(1);
> +		kvmppc_clear_tce(stit->tbl, entry);
> +	}
> +
> +	kvmppc_tce_put(stt, entry, tce);
>  
>  	return H_SUCCESS;
>  }
> @@ -247,6 +504,7 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
>  	unsigned long entry, ua = 0;
>  	u64 __user *tces;
>  	u64 tce;
> +	struct kvmppc_spapr_tce_iommu_table *stit;
>  
>  	stt = kvmppc_find_table(vcpu->kvm, liobn);
>  	if (!stt)
> @@ -285,6 +543,26 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
>  		if (ret != H_SUCCESS)
>  			goto unlock_exit;
>  
> +		if (kvmppc_gpa_to_ua(vcpu->kvm,
> +				tce & ~(TCE_PCI_READ | TCE_PCI_WRITE),
> +				&ua, NULL))
> +			return H_PARAMETER;
> +
> +		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
> +			ret = kvmppc_tce_iommu_map(vcpu->kvm,
> +					stit->tbl, entry + i, ua,
> +					iommu_tce_direction(tce));
> +
> +			if (ret == H_SUCCESS)
> +				continue;
> +
> +			if (ret == H_TOO_HARD)
> +				goto unlock_exit;
> +
> +			WARN_ON_ONCE(1);
> +			kvmppc_clear_tce(stit->tbl, entry);
> +		}
> +
>  		kvmppc_tce_put(stt, entry + i, tce);
>  	}
>  
> @@ -301,6 +579,7 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
>  {
>  	struct kvmppc_spapr_tce_table *stt;
>  	long i, ret;
> +	struct kvmppc_spapr_tce_iommu_table *stit;
>  
>  	stt = kvmppc_find_table(vcpu->kvm, liobn);
>  	if (!stt)
> @@ -314,6 +593,24 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
>  	if (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ))
>  		return H_PARAMETER;
>  
> +	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
> +		unsigned long entry = ioba >> stit->tbl->it_page_shift;
> +
> +		for (i = 0; i < npages; ++i) {
> +			ret = kvmppc_tce_iommu_unmap(vcpu->kvm,
> +					stit->tbl, entry + i);
> +
> +			if (ret == H_SUCCESS)
> +				continue;
> +
> +			if (ret == H_TOO_HARD)
> +				return ret;
> +
> +			WARN_ON_ONCE(1);
> +			kvmppc_clear_tce(stit->tbl, entry);
> +		}
> +	}
> +
>  	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
>  		kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
>  
> diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
> index 440d3ab5dc32..eda0a8f6fae8 100644
> --- a/arch/powerpc/kvm/book3s_64_vio_hv.c
> +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
> @@ -40,6 +40,31 @@
>  #include <asm/iommu.h>
>  #include <asm/tce.h>
>  
> +#ifdef CONFIG_BUG
> +
> +#define WARN_ON_ONCE_RM(condition)	({			\
> +	static bool __section(.data.unlikely) __warned;		\
> +	int __ret_warn_once = !!(condition);			\
> +								\
> +	if (unlikely(__ret_warn_once && !__warned)) {		\
> +		__warned = true;				\
> +		pr_err("WARN_ON_ONCE_RM: (%s) at %s:%u\n",	\
> +				__stringify(condition),		\
> +				__func__, __LINE__);		\
> +		dump_stack();					\
> +	}							\
> +	unlikely(__ret_warn_once);				\
> +})
> +
> +#else
> +
> +#define WARN_ON_ONCE_RM(condition) ({				\
> +	int __ret_warn_on = !!(condition);			\
> +	unlikely(__ret_warn_on);				\
> +})
> +
> +#endif
> +
>  #define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
>  
>  /*
> @@ -161,11 +186,117 @@ long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
>  EXPORT_SYMBOL_GPL(kvmppc_gpa_to_ua);
>  
>  #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
> +static void kvmppc_rm_clear_tce(struct iommu_table *tbl, unsigned long entry)
> +{
> +	unsigned long hpa = 0;
> +	enum dma_data_direction dir = DMA_NONE;
> +
> +	iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
> +}
> +
> +static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm,
> +		struct iommu_table *tbl, unsigned long entry)
> +{
> +	struct mm_iommu_table_group_mem_t *mem = NULL;
> +	const unsigned long pgsize = 1ULL << tbl->it_page_shift;
> +	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
> +
> +	if (!pua)
> +		/* it_userspace allocation might be delayed */
> +		return H_TOO_HARD;
> +
> +	pua = (void *) vmalloc_to_phys(pua);
> +	if (WARN_ON_ONCE_RM(!pua))
> +		return H_HARDWARE;
> +
> +	mem = mm_iommu_lookup_rm(kvm->mm, *pua, pgsize);
> +	if (!mem)
> +		return H_TOO_HARD;
> +
> +	mm_iommu_mapped_dec(mem);
> +
> +	*pua = 0;
> +
> +	return H_SUCCESS;
> +}
> +
> +static long kvmppc_rm_tce_iommu_unmap(struct kvm *kvm,
> +		struct iommu_table *tbl, unsigned long entry)
> +{
> +	enum dma_data_direction dir = DMA_NONE;
> +	unsigned long hpa = 0;
> +	long ret;
> +
> +	if (iommu_tce_xchg_rm(tbl, entry, &hpa, &dir))
> +		/*
> +		 * real mode xchg can fail if struct page crosses
> +		 * a page boundary
> +		 */
> +		return H_TOO_HARD;
> +
> +	if (dir == DMA_NONE)
> +		return H_SUCCESS;
> +
> +	ret = kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);
> +	if (ret)
> +		iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
> +
> +	return ret;
> +}
> +
> +static long kvmppc_rm_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
> +		unsigned long entry, unsigned long ua,
> +		enum dma_data_direction dir)
> +{
> +	long ret;
> +	unsigned long hpa = 0;
> +	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
> +	struct mm_iommu_table_group_mem_t *mem;
> +
> +	if (!pua)
> +		/* it_userspace allocation might be delayed */
> +		return H_TOO_HARD;
> +
> +	mem = mm_iommu_lookup_rm(kvm->mm, ua, 1ULL << tbl->it_page_shift);
> +	if (!mem)
> +		return H_TOO_HARD;
> +
> +	if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, &hpa)))
> +		return H_HARDWARE;
> +
> +	pua = (void *) vmalloc_to_phys(pua);
> +	if (WARN_ON_ONCE_RM(!pua))
> +		return H_HARDWARE;
> +
> +	if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem)))
> +		return H_CLOSED;
> +
> +	ret = iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
> +	if (ret) {
> +		mm_iommu_mapped_dec(mem);
> +		/*
> +		 * real mode xchg can fail if struct page crosses
> +		 * a page boundary
> +		 */
> +		return H_TOO_HARD;
> +	}
> +
> +	if (dir != DMA_NONE)
> +		kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);
> +
> +	*pua = ua;
> +
> +	return 0;
> +}
> +
>  long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>  		unsigned long ioba, unsigned long tce)
>  {
>  	struct kvmppc_spapr_tce_table *stt;
>  	long ret;
> +	struct kvmppc_spapr_tce_iommu_table *stit;
> +	unsigned long entry, ua = 0;
> +	enum dma_data_direction dir;
>  
>  	/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
>  	/* 	    liobn, ioba, tce); */
> @@ -182,7 +313,32 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>  	if (ret != H_SUCCESS)
>  		return ret;
>  
> -	kvmppc_tce_put(stt, ioba >> stt->page_shift, tce);
> +	dir = iommu_tce_direction(tce);
> +	if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm,
> +			tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL))
> +		return H_PARAMETER;
> +
> +	entry = ioba >> stt->page_shift;
> +
> +	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
> +		if (dir == DMA_NONE)
> +			ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm,
> +					stit->tbl, entry);
> +		else
> +			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm,
> +					stit->tbl, entry, ua, dir);
> +
> +		if (ret == H_SUCCESS)
> +			continue;
> +
> +		if (ret == H_TOO_HARD)
> +			return ret;
> +
> +		WARN_ON_ONCE_RM(1);
> +		kvmppc_rm_clear_tce(stit->tbl, entry);
> +	}
> +
> +	kvmppc_tce_put(stt, entry, tce);
>  
>  	return H_SUCCESS;
>  }
> @@ -223,6 +379,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
>  	unsigned long tces, entry, ua = 0;
>  	unsigned long *rmap = NULL;
>  	bool prereg = false;
> +	struct kvmppc_spapr_tce_iommu_table *stit;
>  
>  	stt = kvmppc_find_table(vcpu->kvm, liobn);
>  	if (!stt)
> @@ -270,6 +427,8 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
>  			return H_TOO_HARD;
>  
>  		rmap = (void *) vmalloc_to_phys(rmap);
> +		if (WARN_ON_ONCE_RM(!rmap))
> +			return H_HARDWARE;
>  
>  		/*
>  		 * Synchronize with the MMU notifier callbacks in
> @@ -293,6 +452,27 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
>  		if (ret != H_SUCCESS)
>  			goto unlock_exit;
>  
> +		ua = 0;
> +		if (kvmppc_gpa_to_ua(vcpu->kvm,
> +				tce & ~(TCE_PCI_READ | TCE_PCI_WRITE),
> +				&ua, NULL))
> +			return H_PARAMETER;
> +
> +		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
> +			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm,
> +					stit->tbl, entry + i, ua,
> +					iommu_tce_direction(tce));
> +
> +			if (ret == H_SUCCESS)
> +				continue;
> +
> +			if (ret == H_TOO_HARD)
> +				goto unlock_exit;
> +
> +			WARN_ON_ONCE_RM(1);
> +			kvmppc_rm_clear_tce(stit->tbl, entry);
> +		}
> +
>  		kvmppc_tce_put(stt, entry + i, tce);
>  	}
>  
> @@ -309,6 +489,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
>  {
>  	struct kvmppc_spapr_tce_table *stt;
>  	long i, ret;
> +	struct kvmppc_spapr_tce_iommu_table *stit;
>  
>  	stt = kvmppc_find_table(vcpu->kvm, liobn);
>  	if (!stt)
> @@ -322,6 +503,24 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
>  	if (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ))
>  		return H_PARAMETER;
>  
> +	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
> +		unsigned long entry = ioba >> stit->tbl->it_page_shift;
> +
> +		for (i = 0; i < npages; ++i) {
> +			ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm,
> +					stit->tbl, entry + i);
> +
> +			if (ret == H_SUCCESS)
> +				continue;
> +
> +			if (ret == H_TOO_HARD)
> +				return ret;
> +
> +			WARN_ON_ONCE_RM(1);
> +			kvmppc_rm_clear_tce(stit->tbl, entry);
> +		}
> +	}
> +
>  	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
>  		kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
>  
> diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
> index 95c91a9de351..62bdd6c48107 100644
> --- a/arch/powerpc/kvm/powerpc.c
> +++ b/arch/powerpc/kvm/powerpc.c
> @@ -538,6 +538,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
>  #ifdef CONFIG_PPC_BOOK3S_64
>  	case KVM_CAP_SPAPR_TCE:
>  	case KVM_CAP_SPAPR_TCE_64:
> +		/* fallthrough */
> +	case KVM_CAP_SPAPR_TCE_VFIO:
>  	case KVM_CAP_PPC_RTAS:
>  	case KVM_CAP_PPC_FIXUP_HCALL:
>  	case KVM_CAP_PPC_ENABLE_HCALL:
> diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
> index d32f239eb471..d438818e2681 100644
> --- a/virt/kvm/vfio.c
> +++ b/virt/kvm/vfio.c
> @@ -20,6 +20,10 @@
>  #include <linux/vfio.h>
>  #include "vfio.h"
>  
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> +#include <asm/kvm_ppc.h>
> +#endif
> +
>  struct kvm_vfio_group {
>  	struct list_head node;
>  	struct vfio_group *vfio_group;
> @@ -89,6 +93,47 @@ static bool kvm_vfio_group_is_coherent(struct vfio_group *vfio_group)
>  	return ret > 0;
>  }
>  
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> +static int kvm_vfio_external_user_iommu_id(struct vfio_group *vfio_group)
> +{
> +	int (*fn)(struct vfio_group *);
> +	int ret = -EINVAL;
> +
> +	fn = symbol_get(vfio_external_user_iommu_id);
> +	if (!fn)
> +		return ret;
> +
> +	ret = fn(vfio_group);
> +
> +	symbol_put(vfio_external_user_iommu_id);
> +
> +	return ret;
> +}
> +
> +static struct iommu_group *kvm_vfio_group_get_iommu_group(
> +		struct vfio_group *group)
> +{
> +	int group_id = kvm_vfio_external_user_iommu_id(group);
> +
> +	if (group_id < 0)
> +		return NULL;
> +
> +	return iommu_group_get_by_id(group_id);
> +}
> +
> +static void kvm_spapr_tce_release_vfio_group(struct kvm *kvm,
> +		struct vfio_group *vfio_group)
> +{
> +	struct iommu_group *grp = kvm_vfio_group_get_iommu_group(vfio_group);
> +
> +	if (WARN_ON_ONCE(!grp))
> +		return;
> +
> +	kvm_spapr_tce_release_iommu_group(kvm, grp);
> +	iommu_group_put(grp);
> +}
> +#endif
> +
>  /*
>   * Groups can use the same or different IOMMU domains.  If the same then
>   * adding a new group may change the coherency of groups we've previously
> @@ -211,6 +256,9 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
>  
>  		mutex_unlock(&kv->lock);
>  
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> +		kvm_spapr_tce_release_vfio_group(dev->kvm, vfio_group);
> +#endif
>  		kvm_vfio_group_set_kvm(vfio_group, NULL);
>  
>  		kvm_vfio_group_put_external_user(vfio_group);
> @@ -218,6 +266,56 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
>  		kvm_vfio_update_coherency(dev);
>  
>  		return ret;
> +
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> +	case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: {
> +		struct kvm_vfio_spapr_tce param;
> +		struct kvm_vfio *kv = dev->private;
> +		struct vfio_group *vfio_group;
> +		struct kvm_vfio_group *kvg;
> +		struct fd f;
> +		struct iommu_group *grp;
> +
> +		if (copy_from_user(&param, (void __user *)arg,
> +				sizeof(struct kvm_vfio_spapr_tce)))
> +			return -EFAULT;
> +
> +		f = fdget(param.groupfd);
> +		if (!f.file)
> +			return -EBADF;
> +
> +		vfio_group = kvm_vfio_group_get_external_user(f.file);
> +		fdput(f);
> +
> +		if (IS_ERR(vfio_group))
> +			return PTR_ERR(vfio_group);
> +
> +		grp = kvm_vfio_group_get_iommu_group(vfio_group);
> +		if (WARN_ON_ONCE(!grp))

vfio_group leaked

> +			return -EIO;
> +
> +		ret = -ENOENT;
> +
> +		mutex_lock(&kv->lock);
> +
> +		list_for_each_entry(kvg, &kv->group_list, node) {
> +			if (kvg->vfio_group != vfio_group)
> +				continue;
> +
> +			ret = kvm_spapr_tce_attach_iommu_group(dev->kvm,
> +					param.tablefd, grp);
> +
> +			break;
> +		}
> +
> +		mutex_unlock(&kv->lock);
> +
> +		iommu_group_put(grp);
> +		kvm_vfio_group_put_external_user(vfio_group);
> +
> +		return ret;
> +	}
> +#endif /* CONFIG_SPAPR_TCE_IOMMU */
>  	}
>  
>  	return -ENXIO;
> @@ -242,6 +340,9 @@ static int kvm_vfio_has_attr(struct kvm_device *dev,
>  		switch (attr->attr) {
>  		case KVM_DEV_VFIO_GROUP_ADD:
>  		case KVM_DEV_VFIO_GROUP_DEL:
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> +		case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE:
> +#endif
>  			return 0;
>  		}
>  
> @@ -257,6 +358,9 @@ static void kvm_vfio_destroy(struct kvm_device *dev)
>  	struct kvm_vfio_group *kvg, *tmp;
>  
>  	list_for_each_entry_safe(kvg, tmp, &kv->group_list, node) {
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> +		kvm_spapr_tce_release_vfio_group(dev->kvm, kvg->vfio_group);
> +#endif
>  		kvm_vfio_group_set_kvm(kvg->vfio_group, NULL);
>  		kvm_vfio_group_put_external_user(kvg->vfio_group);
>  		list_del(&kvg->node);

Re: [PATCH kernel v10 10/10] KVM: PPC: VFIO: Add in-kernel acceleration for VFIO

[Alex Williamson]

On Fri, 17 Mar 2017 16:09:59 +1100
Alexey Kardashevskiy <aik@ozlabs.ru> wrote:

> This allows the host kernel to handle H_PUT_TCE, H_PUT_TCE_INDIRECT
> and H_STUFF_TCE requests targeted an IOMMU TCE table used for VFIO
> without passing them to user space which saves time on switching
> to user space and back.
> 
> This adds H_PUT_TCE/H_PUT_TCE_INDIRECT/H_STUFF_TCE handlers to KVM.
> KVM tries to handle a TCE request in the real mode, if failed
> it passes the request to the virtual mode to complete the operation.
> If it a virtual mode handler fails, the request is passed to
> the user space; this is not expected to happen though.
> 
> To avoid dealing with page use counters (which is tricky in real mode),
> this only accelerates SPAPR TCE IOMMU v2 clients which are required
> to pre-register the userspace memory. The very first TCE request will
> be handled in the VFIO SPAPR TCE driver anyway as the userspace view
> of the TCE table (iommu_table::it_userspace) is not allocated till
> the very first mapping happens and we cannot call vmalloc in real mode.
> 
> If we fail to update a hardware IOMMU table unexpected reason, we just
> clear it and move on as there is nothing really we can do about it -
> for example, if we hot plug a VFIO device to a guest, existing TCE tables
> will be mirrored automatically to the hardware and there is no interface
> to report to the guest about possible failures.
> 
> This adds new attribute - KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE - to
> the VFIO KVM device. It takes a VFIO group fd and SPAPR TCE table fd
> and associates a physical IOMMU table with the SPAPR TCE table (which
> is a guest view of the hardware IOMMU table). The iommu_table object
> is cached and referenced so we do not have to look up for it in real mode.
> 
> This does not implement the UNSET counterpart as there is no use for it -
> once the acceleration is enabled, the existing userspace won't
> disable it unless a VFIO container is destroyed; this adds necessary
> cleanup to the KVM_DEV_VFIO_GROUP_DEL handler.
> 
> This advertises the new KVM_CAP_SPAPR_TCE_VFIO capability to the user
> space.
> 
> This adds real mode version of WARN_ON_ONCE() as the generic version
> causes problems with rcu_sched. Since we testing what vmalloc_to_phys()
> returns in the code, this also adds a check for already existing
> vmalloc_to_phys() call in kvmppc_rm_h_put_tce_indirect().
> 
> This finally makes use of vfio_external_user_iommu_id() which was
> introduced quite some time ago and was considered for removal.
> 
> Tests show that this patch increases transmission speed from 220MB/s
> to 750..1020MB/s on 10Gb network (Chelsea CXGB3 10Gb ethernet card).
> 
> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
> ---
> Changes:
> v10:
> * fixed leaking references in virt/kvm/vfio.c
> * moved code to helpers - kvm_vfio_group_get_iommu_group, kvm_spapr_tce_release_vfio_group
> * fixed possible race between referencing table and destroying it via
> VFIO add/remove window ioctls()
> 
> v9:
> * removed referencing a group in KVM, only referencing iommu_table's now
> * fixed a reference leak in KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE handler
> * fixed typo in vfio.txt
> * removed @argsz and @flags from struct kvm_vfio_spapr_tce
> 
> v8:
> * changed all (!pua) checks to return H_TOO_HARD as ioctl() is supposed
> to handle them
> * changed vmalloc_to_phys() callers to return H_HARDWARE
> * changed real mode iommu_tce_xchg_rm() callers to return H_TOO_HARD
> and added a comment about this in the code
> * changed virtual mode iommu_tce_xchg() callers to return H_HARDWARE
> and do WARN_ON
> * added WARN_ON_ONCE_RM(!rmap) in kvmppc_rm_h_put_tce_indirect() to
> have all vmalloc_to_phys() callsites covered
> 
> v7:
> * added realmode-friendly WARN_ON_ONCE_RM
> 
> v6:
> * changed handling of errors returned by kvmppc_(rm_)tce_iommu_(un)map()
> * moved kvmppc_gpa_to_ua() to TCE validation
> 
> v5:
> * changed error codes in multiple places
> * added bunch of WARN_ON() in places which should not really happen
> * adde a check that an iommu table is not attached already to LIOBN
> * dropped explicit calls to iommu_tce_clear_param_check/
> iommu_tce_put_param_check as kvmppc_tce_validate/kvmppc_ioba_validate
> call them anyway (since the previous patch)
> * if we fail to update a hardware IOMMU table for unexpected reason,
> this just clears the entry
> 
> v4:
> * added note to the commit log about allowing multiple updates of
> the same IOMMU table;
> * instead of checking for if any memory was preregistered, this
> returns H_TOO_HARD if a specific page was not;
> * fixed comments from v3 about error handling in many places;
> * simplified TCE handlers and merged IOMMU parts inline - for example,
> there used to be kvmppc_h_put_tce_iommu(), now it is merged into
> kvmppc_h_put_tce(); this allows to check IOBA boundaries against
> the first attached table only (makes the code simpler);
> 
> v3:
> * simplified not to use VFIO group notifiers
> * reworked cleanup, should be cleaner/simpler now
> 
> v2:
> * reworked to use new VFIO notifiers
> * now same iommu_table may appear in the list several times, to be fixed later
> ---
>  Documentation/virtual/kvm/devices/vfio.txt |  18 +-
>  arch/powerpc/include/asm/kvm_host.h        |   8 +
>  arch/powerpc/include/asm/kvm_ppc.h         |   4 +
>  include/uapi/linux/kvm.h                   |   6 +
>  arch/powerpc/kvm/book3s_64_vio.c           | 301 ++++++++++++++++++++++++++++-
>  arch/powerpc/kvm/book3s_64_vio_hv.c        | 201 ++++++++++++++++++-
>  arch/powerpc/kvm/powerpc.c                 |   2 +
>  virt/kvm/vfio.c                            | 104 ++++++++++
>  8 files changed, 639 insertions(+), 5 deletions(-)
> 
> diff --git a/Documentation/virtual/kvm/devices/vfio.txt b/Documentation/virtual/kvm/devices/vfio.txt
> index ef51740c67ca..528c77c8022c 100644
> --- a/Documentation/virtual/kvm/devices/vfio.txt
> +++ b/Documentation/virtual/kvm/devices/vfio.txt
> @@ -16,7 +16,21 @@ Groups:
>  
>  KVM_DEV_VFIO_GROUP attributes:
>    KVM_DEV_VFIO_GROUP_ADD: Add a VFIO group to VFIO-KVM device tracking
> +	kvm_device_attr.addr points to an int32_t file descriptor
> +	for the VFIO group.
>    KVM_DEV_VFIO_GROUP_DEL: Remove a VFIO group from VFIO-KVM device tracking
> +	kvm_device_attr.addr points to an int32_t file descriptor
> +	for the VFIO group.
> +  KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: attaches a guest visible TCE table
> +	allocated by sPAPR KVM.
> +	kvm_device_attr.addr points to a struct:
>  
> -For each, kvm_device_attr.addr points to an int32_t file descriptor
> -for the VFIO group.
> +	struct kvm_vfio_spapr_tce {
> +		__s32	groupfd;
> +		__s32	tablefd;
> +	};
> +
> +	where
> +	@groupfd is a file descriptor for a VFIO group;
> +	@tablefd is a file descriptor for a TCE table allocated via
> +		KVM_CREATE_SPAPR_TCE.
> diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
> index 7bba8f415627..178074e643e5 100644
> --- a/arch/powerpc/include/asm/kvm_host.h
> +++ b/arch/powerpc/include/asm/kvm_host.h
> @@ -191,6 +191,13 @@ struct kvmppc_pginfo {
>  	atomic_t refcnt;
>  };
>  
> +struct kvmppc_spapr_tce_iommu_table {
> +	struct rcu_head rcu;
> +	struct list_head next;
> +	struct iommu_table *tbl;
> +	struct kref kref;
> +};
> +
>  struct kvmppc_spapr_tce_table {
>  	struct list_head list;
>  	struct kvm *kvm;
> @@ -199,6 +206,7 @@ struct kvmppc_spapr_tce_table {
>  	u32 page_shift;
>  	u64 offset;		/* in pages */
>  	u64 size;		/* window size in pages */
> +	struct list_head iommu_tables;
>  	struct page *pages[0];
>  };
>  
> diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
> index 72c2a155641f..cfd45714189e 100644
> --- a/arch/powerpc/include/asm/kvm_ppc.h
> +++ b/arch/powerpc/include/asm/kvm_ppc.h
> @@ -164,6 +164,10 @@ extern long kvmppc_prepare_vrma(struct kvm *kvm,
>  extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu,
>  			struct kvm_memory_slot *memslot, unsigned long porder);
>  extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
> +extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
> +		struct iommu_group *grp);
> +extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
> +		struct iommu_group *grp);
>  
>  extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
>  				struct kvm_create_spapr_tce_64 *args);
> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> index f5a52ffb6b58..0f8a5e6528aa 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -1088,6 +1088,7 @@ struct kvm_device_attr {
>  #define  KVM_DEV_VFIO_GROUP			1
>  #define   KVM_DEV_VFIO_GROUP_ADD			1
>  #define   KVM_DEV_VFIO_GROUP_DEL			2
> +#define   KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE		3
>  
>  enum kvm_device_type {
>  	KVM_DEV_TYPE_FSL_MPIC_20	= 1,
> @@ -1109,6 +1110,11 @@ enum kvm_device_type {
>  	KVM_DEV_TYPE_MAX,
>  };
>  
> +struct kvm_vfio_spapr_tce {
> +	__s32	groupfd;
> +	__s32	tablefd;
> +};
> +
>  /*
>   * ioctls for VM fds
>   */
> diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
> index e96a4590464c..22c67a47eaab 100644
> --- a/arch/powerpc/kvm/book3s_64_vio.c
> +++ b/arch/powerpc/kvm/book3s_64_vio.c
> @@ -28,6 +28,8 @@
>  #include <linux/hugetlb.h>
>  #include <linux/list.h>
>  #include <linux/anon_inodes.h>
> +#include <linux/iommu.h>
> +#include <linux/file.h>
>  
>  #include <asm/tlbflush.h>
>  #include <asm/kvm_ppc.h>
> @@ -40,6 +42,7 @@
>  #include <asm/udbg.h>
>  #include <asm/iommu.h>
>  #include <asm/tce.h>
> +#include <asm/mmu_context.h>
>  
>  static unsigned long kvmppc_tce_pages(unsigned long iommu_pages)
>  {
> @@ -91,6 +94,132 @@ static long kvmppc_account_memlimit(unsigned long stt_pages, bool inc)
>  	return ret;
>  }
>  
> +static void kvm_spapr_tce_iommu_table_free(struct rcu_head *head)
> +{
> +	struct kvmppc_spapr_tce_iommu_table *stit = container_of(head,
> +			struct kvmppc_spapr_tce_iommu_table, rcu);
> +
> +	iommu_tce_table_put(stit->tbl);
> +
> +	kfree(stit);
> +}
> +
> +static void kvm_spapr_tce_liobn_put(struct kref *kref)
> +{
> +	struct kvmppc_spapr_tce_iommu_table *stit = container_of(kref,
> +			struct kvmppc_spapr_tce_iommu_table, kref);
> +
> +	list_del_rcu(&stit->next);
> +
> +	call_rcu(&stit->rcu, kvm_spapr_tce_iommu_table_free);
> +}
> +
> +extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
> +		struct iommu_group *grp)
> +{
> +	int i;
> +	struct kvmppc_spapr_tce_table *stt;
> +	struct kvmppc_spapr_tce_iommu_table *stit, *tmp;
> +	struct iommu_table_group *table_group = NULL;
> +
> +	list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) {
> +
> +		table_group = iommu_group_get_iommudata(grp);
> +		if (WARN_ON(!table_group))
> +			continue;
> +
> +		list_for_each_entry_safe(stit, tmp, &stt->iommu_tables, next) {
> +			for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
> +				if (table_group->tables[i] != stit->tbl)
> +					continue;
> +
> +				kref_put(&stit->kref, kvm_spapr_tce_liobn_put);
> +				return;
> +			}
> +		}
> +	}
> +}
> +
> +extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
> +		struct iommu_group *grp)
> +{
> +	struct kvmppc_spapr_tce_table *stt = NULL;
> +	bool found = false;
> +	struct iommu_table *tbl = NULL;
> +	struct iommu_table_group *table_group;
> +	long i;
> +	struct kvmppc_spapr_tce_iommu_table *stit;
> +	struct fd f;
> +
> +	f = fdget(tablefd);
> +	if (!f.file)
> +		return -EBADF;
> +
> +	list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) {
> +		if (stt = f.file->private_data) {
> +			found = true;
> +			break;
> +		}
> +	}
> +
> +	fdput(f);
> +
> +	if (!found)
> +		return -EINVAL;
> +
> +	table_group = iommu_group_get_iommudata(grp);
> +	if (WARN_ON(!table_group))
> +		return -EFAULT;
> +
> +	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
> +		struct iommu_table *tbltmp = table_group->tables[i];
> +
> +		if (!tbltmp)
> +			continue;
> +		/*
> +		 * Make sure hardware table parameters are exactly the same;
> +		 * this is used in the TCE handlers where boundary checks
> +		 * use only the first attached table.
> +		 */
> +		if ((tbltmp->it_page_shift = stt->page_shift) &&
> +				(tbltmp->it_offset = stt->offset) &&
> +				(tbltmp->it_size = stt->size)) {
> +			/*
> +			 * Reference the table to avoid races with
> +			 * add/remove DMA windows.
> +			 */
> +			tbl = iommu_tce_table_get(tbltmp);
> +			break;
> +		}
> +	}
> +	if (!tbl)
> +		return -EINVAL;
> +
> +	list_for_each_entry_rcu(stit, &stt->iommu_tables, next) {
> +		if (tbl != stit->tbl)
> +			continue;
> +
> +		if (!kref_get_unless_zero(&stit->kref)) {
> +			/* stit is being destroyed */
> +			iommu_tce_table_put(tbl);
> +			return -ENOTTY;
> +		}
> +		/*
> +		 * The table is already known to this KVM, we just increased
> +		 * its KVM reference counter and can return.
> +		 */
> +		return 0;
> +	}
> +
> +	stit = kzalloc(sizeof(*stit), GFP_KERNEL);
> +	stit->tbl = tbl;
> +	kref_init(&stit->kref);
> +
> +	list_add_rcu(&stit->next, &stt->iommu_tables);
> +
> +	return 0;
> +}
> +
>  static void release_spapr_tce_table(struct rcu_head *head)
>  {
>  	struct kvmppc_spapr_tce_table *stt = container_of(head,
> @@ -130,9 +259,18 @@ static int kvm_spapr_tce_mmap(struct file *file, struct vm_area_struct *vma)
>  static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
>  {
>  	struct kvmppc_spapr_tce_table *stt = filp->private_data;
> +	struct kvmppc_spapr_tce_iommu_table *stit, *tmp;
>  
>  	list_del_rcu(&stt->list);
>  
> +	list_for_each_entry_safe(stit, tmp, &stt->iommu_tables, next) {
> +		WARN_ON(!kref_read(&stit->kref));
> +		while (1) {
> +			if (kref_put(&stit->kref, kvm_spapr_tce_liobn_put))
> +				break;
> +		}
> +	}
> +
>  	kvm_put_kvm(stt->kvm);
>  
>  	kvmppc_account_memlimit(
> @@ -183,6 +321,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
>  	stt->offset = args->offset;
>  	stt->size = size;
>  	stt->kvm = kvm;
> +	INIT_LIST_HEAD_RCU(&stt->iommu_tables);
>  
>  	for (i = 0; i < npages; i++) {
>  		stt->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
> @@ -211,11 +350,101 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
>  	return ret;
>  }
>  
> +static void kvmppc_clear_tce(struct iommu_table *tbl, unsigned long entry)
> +{
> +	unsigned long hpa = 0;
> +	enum dma_data_direction dir = DMA_NONE;
> +
> +	iommu_tce_xchg(tbl, entry, &hpa, &dir);
> +}
> +
> +static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm,
> +		struct iommu_table *tbl, unsigned long entry)
> +{
> +	struct mm_iommu_table_group_mem_t *mem = NULL;
> +	const unsigned long pgsize = 1ULL << tbl->it_page_shift;
> +	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
> +
> +	if (!pua)
> +		/* it_userspace allocation might be delayed */
> +		return H_TOO_HARD;
> +
> +	mem = mm_iommu_lookup(kvm->mm, *pua, pgsize);
> +	if (!mem)
> +		return H_TOO_HARD;
> +
> +	mm_iommu_mapped_dec(mem);
> +
> +	*pua = 0;
> +
> +	return H_SUCCESS;
> +}
> +
> +static long kvmppc_tce_iommu_unmap(struct kvm *kvm,
> +		struct iommu_table *tbl, unsigned long entry)
> +{
> +	enum dma_data_direction dir = DMA_NONE;
> +	unsigned long hpa = 0;
> +	long ret;
> +
> +	if (WARN_ON_ONCE(iommu_tce_xchg(tbl, entry, &hpa, &dir)))
> +		return H_HARDWARE;
> +
> +	if (dir = DMA_NONE)
> +		return H_SUCCESS;
> +
> +	ret = kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry);
> +	if (ret != H_SUCCESS)
> +		iommu_tce_xchg(tbl, entry, &hpa, &dir);
> +
> +	return ret;
> +}
> +
> +long kvmppc_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
> +		unsigned long entry, unsigned long ua,
> +		enum dma_data_direction dir)
> +{
> +	long ret;
> +	unsigned long hpa, *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
> +	struct mm_iommu_table_group_mem_t *mem;
> +
> +	if (!pua)
> +		/* it_userspace allocation might be delayed */
> +		return H_TOO_HARD;
> +
> +	mem = mm_iommu_lookup(kvm->mm, ua, 1ULL << tbl->it_page_shift);
> +	if (!mem)
> +		/* This only handles v2 IOMMU type, v1 is handled via ioctl() */
> +		return H_TOO_HARD;
> +
> +	if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, &hpa)))
> +		return H_HARDWARE;
> +
> +	if (mm_iommu_mapped_inc(mem))
> +		return H_CLOSED;
> +
> +	ret = iommu_tce_xchg(tbl, entry, &hpa, &dir);
> +	if (WARN_ON_ONCE(ret)) {
> +		mm_iommu_mapped_dec(mem);
> +		return H_HARDWARE;
> +	}
> +
> +	if (dir != DMA_NONE)
> +		kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry);
> +
> +	*pua = ua;
> +
> +	return 0;
> +}
> +
>  long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>  		      unsigned long ioba, unsigned long tce)
>  {
>  	struct kvmppc_spapr_tce_table *stt;
> -	long ret;
> +	long ret, idx;
> +	struct kvmppc_spapr_tce_iommu_table *stit;
> +	unsigned long entry, ua = 0;
> +	enum dma_data_direction dir;
>  
>  	/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
>  	/* 	    liobn, ioba, tce); */
> @@ -232,7 +461,35 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>  	if (ret != H_SUCCESS)
>  		return ret;
>  
> -	kvmppc_tce_put(stt, ioba >> stt->page_shift, tce);
> +	dir = iommu_tce_direction(tce);
> +	if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm,
> +			tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL))
> +		return H_PARAMETER;
> +
> +	entry = ioba >> stt->page_shift;
> +
> +	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
> +		if (dir = DMA_NONE) {
> +			ret = kvmppc_tce_iommu_unmap(vcpu->kvm,
> +					stit->tbl, entry);
> +		} else {
> +			idx = srcu_read_lock(&vcpu->kvm->srcu);
> +			ret = kvmppc_tce_iommu_map(vcpu->kvm, stit->tbl,
> +					entry, ua, dir);
> +			srcu_read_unlock(&vcpu->kvm->srcu, idx);
> +		}
> +
> +		if (ret = H_SUCCESS)
> +			continue;
> +
> +		if (ret = H_TOO_HARD)
> +			return ret;
> +
> +		WARN_ON_ONCE(1);
> +		kvmppc_clear_tce(stit->tbl, entry);
> +	}
> +
> +	kvmppc_tce_put(stt, entry, tce);
>  
>  	return H_SUCCESS;
>  }
> @@ -247,6 +504,7 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
>  	unsigned long entry, ua = 0;
>  	u64 __user *tces;
>  	u64 tce;
> +	struct kvmppc_spapr_tce_iommu_table *stit;
>  
>  	stt = kvmppc_find_table(vcpu->kvm, liobn);
>  	if (!stt)
> @@ -285,6 +543,26 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
>  		if (ret != H_SUCCESS)
>  			goto unlock_exit;
>  
> +		if (kvmppc_gpa_to_ua(vcpu->kvm,
> +				tce & ~(TCE_PCI_READ | TCE_PCI_WRITE),
> +				&ua, NULL))
> +			return H_PARAMETER;
> +
> +		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
> +			ret = kvmppc_tce_iommu_map(vcpu->kvm,
> +					stit->tbl, entry + i, ua,
> +					iommu_tce_direction(tce));
> +
> +			if (ret = H_SUCCESS)
> +				continue;
> +
> +			if (ret = H_TOO_HARD)
> +				goto unlock_exit;
> +
> +			WARN_ON_ONCE(1);
> +			kvmppc_clear_tce(stit->tbl, entry);
> +		}
> +
>  		kvmppc_tce_put(stt, entry + i, tce);
>  	}
>  
> @@ -301,6 +579,7 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
>  {
>  	struct kvmppc_spapr_tce_table *stt;
>  	long i, ret;
> +	struct kvmppc_spapr_tce_iommu_table *stit;
>  
>  	stt = kvmppc_find_table(vcpu->kvm, liobn);
>  	if (!stt)
> @@ -314,6 +593,24 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
>  	if (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ))
>  		return H_PARAMETER;
>  
> +	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
> +		unsigned long entry = ioba >> stit->tbl->it_page_shift;
> +
> +		for (i = 0; i < npages; ++i) {
> +			ret = kvmppc_tce_iommu_unmap(vcpu->kvm,
> +					stit->tbl, entry + i);
> +
> +			if (ret = H_SUCCESS)
> +				continue;
> +
> +			if (ret = H_TOO_HARD)
> +				return ret;
> +
> +			WARN_ON_ONCE(1);
> +			kvmppc_clear_tce(stit->tbl, entry);
> +		}
> +	}
> +
>  	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
>  		kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
>  
> diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
> index 440d3ab5dc32..eda0a8f6fae8 100644
> --- a/arch/powerpc/kvm/book3s_64_vio_hv.c
> +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
> @@ -40,6 +40,31 @@
>  #include <asm/iommu.h>
>  #include <asm/tce.h>
>  
> +#ifdef CONFIG_BUG
> +
> +#define WARN_ON_ONCE_RM(condition)	({			\
> +	static bool __section(.data.unlikely) __warned;		\
> +	int __ret_warn_once = !!(condition);			\
> +								\
> +	if (unlikely(__ret_warn_once && !__warned)) {		\
> +		__warned = true;				\
> +		pr_err("WARN_ON_ONCE_RM: (%s) at %s:%u\n",	\
> +				__stringify(condition),		\
> +				__func__, __LINE__);		\
> +		dump_stack();					\
> +	}							\
> +	unlikely(__ret_warn_once);				\
> +})
> +
> +#else
> +
> +#define WARN_ON_ONCE_RM(condition) ({				\
> +	int __ret_warn_on = !!(condition);			\
> +	unlikely(__ret_warn_on);				\
> +})
> +
> +#endif
> +
>  #define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
>  
>  /*
> @@ -161,11 +186,117 @@ long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
>  EXPORT_SYMBOL_GPL(kvmppc_gpa_to_ua);
>  
>  #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
> +static void kvmppc_rm_clear_tce(struct iommu_table *tbl, unsigned long entry)
> +{
> +	unsigned long hpa = 0;
> +	enum dma_data_direction dir = DMA_NONE;
> +
> +	iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
> +}
> +
> +static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm,
> +		struct iommu_table *tbl, unsigned long entry)
> +{
> +	struct mm_iommu_table_group_mem_t *mem = NULL;
> +	const unsigned long pgsize = 1ULL << tbl->it_page_shift;
> +	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
> +
> +	if (!pua)
> +		/* it_userspace allocation might be delayed */
> +		return H_TOO_HARD;
> +
> +	pua = (void *) vmalloc_to_phys(pua);
> +	if (WARN_ON_ONCE_RM(!pua))
> +		return H_HARDWARE;
> +
> +	mem = mm_iommu_lookup_rm(kvm->mm, *pua, pgsize);
> +	if (!mem)
> +		return H_TOO_HARD;
> +
> +	mm_iommu_mapped_dec(mem);
> +
> +	*pua = 0;
> +
> +	return H_SUCCESS;
> +}
> +
> +static long kvmppc_rm_tce_iommu_unmap(struct kvm *kvm,
> +		struct iommu_table *tbl, unsigned long entry)
> +{
> +	enum dma_data_direction dir = DMA_NONE;
> +	unsigned long hpa = 0;
> +	long ret;
> +
> +	if (iommu_tce_xchg_rm(tbl, entry, &hpa, &dir))
> +		/*
> +		 * real mode xchg can fail if struct page crosses
> +		 * a page boundary
> +		 */
> +		return H_TOO_HARD;
> +
> +	if (dir = DMA_NONE)
> +		return H_SUCCESS;
> +
> +	ret = kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);
> +	if (ret)
> +		iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
> +
> +	return ret;
> +}
> +
> +static long kvmppc_rm_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
> +		unsigned long entry, unsigned long ua,
> +		enum dma_data_direction dir)
> +{
> +	long ret;
> +	unsigned long hpa = 0;
> +	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
> +	struct mm_iommu_table_group_mem_t *mem;
> +
> +	if (!pua)
> +		/* it_userspace allocation might be delayed */
> +		return H_TOO_HARD;
> +
> +	mem = mm_iommu_lookup_rm(kvm->mm, ua, 1ULL << tbl->it_page_shift);
> +	if (!mem)
> +		return H_TOO_HARD;
> +
> +	if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, &hpa)))
> +		return H_HARDWARE;
> +
> +	pua = (void *) vmalloc_to_phys(pua);
> +	if (WARN_ON_ONCE_RM(!pua))
> +		return H_HARDWARE;
> +
> +	if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem)))
> +		return H_CLOSED;
> +
> +	ret = iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
> +	if (ret) {
> +		mm_iommu_mapped_dec(mem);
> +		/*
> +		 * real mode xchg can fail if struct page crosses
> +		 * a page boundary
> +		 */
> +		return H_TOO_HARD;
> +	}
> +
> +	if (dir != DMA_NONE)
> +		kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);
> +
> +	*pua = ua;
> +
> +	return 0;
> +}
> +
>  long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>  		unsigned long ioba, unsigned long tce)
>  {
>  	struct kvmppc_spapr_tce_table *stt;
>  	long ret;
> +	struct kvmppc_spapr_tce_iommu_table *stit;
> +	unsigned long entry, ua = 0;
> +	enum dma_data_direction dir;
>  
>  	/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
>  	/* 	    liobn, ioba, tce); */
> @@ -182,7 +313,32 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>  	if (ret != H_SUCCESS)
>  		return ret;
>  
> -	kvmppc_tce_put(stt, ioba >> stt->page_shift, tce);
> +	dir = iommu_tce_direction(tce);
> +	if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm,
> +			tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL))
> +		return H_PARAMETER;
> +
> +	entry = ioba >> stt->page_shift;
> +
> +	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
> +		if (dir = DMA_NONE)
> +			ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm,
> +					stit->tbl, entry);
> +		else
> +			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm,
> +					stit->tbl, entry, ua, dir);
> +
> +		if (ret = H_SUCCESS)
> +			continue;
> +
> +		if (ret = H_TOO_HARD)
> +			return ret;
> +
> +		WARN_ON_ONCE_RM(1);
> +		kvmppc_rm_clear_tce(stit->tbl, entry);
> +	}
> +
> +	kvmppc_tce_put(stt, entry, tce);
>  
>  	return H_SUCCESS;
>  }
> @@ -223,6 +379,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
>  	unsigned long tces, entry, ua = 0;
>  	unsigned long *rmap = NULL;
>  	bool prereg = false;
> +	struct kvmppc_spapr_tce_iommu_table *stit;
>  
>  	stt = kvmppc_find_table(vcpu->kvm, liobn);
>  	if (!stt)
> @@ -270,6 +427,8 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
>  			return H_TOO_HARD;
>  
>  		rmap = (void *) vmalloc_to_phys(rmap);
> +		if (WARN_ON_ONCE_RM(!rmap))
> +			return H_HARDWARE;
>  
>  		/*
>  		 * Synchronize with the MMU notifier callbacks in
> @@ -293,6 +452,27 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
>  		if (ret != H_SUCCESS)
>  			goto unlock_exit;
>  
> +		ua = 0;
> +		if (kvmppc_gpa_to_ua(vcpu->kvm,
> +				tce & ~(TCE_PCI_READ | TCE_PCI_WRITE),
> +				&ua, NULL))
> +			return H_PARAMETER;
> +
> +		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
> +			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm,
> +					stit->tbl, entry + i, ua,
> +					iommu_tce_direction(tce));
> +
> +			if (ret = H_SUCCESS)
> +				continue;
> +
> +			if (ret = H_TOO_HARD)
> +				goto unlock_exit;
> +
> +			WARN_ON_ONCE_RM(1);
> +			kvmppc_rm_clear_tce(stit->tbl, entry);
> +		}
> +
>  		kvmppc_tce_put(stt, entry + i, tce);
>  	}
>  
> @@ -309,6 +489,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
>  {
>  	struct kvmppc_spapr_tce_table *stt;
>  	long i, ret;
> +	struct kvmppc_spapr_tce_iommu_table *stit;
>  
>  	stt = kvmppc_find_table(vcpu->kvm, liobn);
>  	if (!stt)
> @@ -322,6 +503,24 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
>  	if (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ))
>  		return H_PARAMETER;
>  
> +	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
> +		unsigned long entry = ioba >> stit->tbl->it_page_shift;
> +
> +		for (i = 0; i < npages; ++i) {
> +			ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm,
> +					stit->tbl, entry + i);
> +
> +			if (ret = H_SUCCESS)
> +				continue;
> +
> +			if (ret = H_TOO_HARD)
> +				return ret;
> +
> +			WARN_ON_ONCE_RM(1);
> +			kvmppc_rm_clear_tce(stit->tbl, entry);
> +		}
> +	}
> +
>  	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
>  		kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
>  
> diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
> index 95c91a9de351..62bdd6c48107 100644
> --- a/arch/powerpc/kvm/powerpc.c
> +++ b/arch/powerpc/kvm/powerpc.c
> @@ -538,6 +538,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
>  #ifdef CONFIG_PPC_BOOK3S_64
>  	case KVM_CAP_SPAPR_TCE:
>  	case KVM_CAP_SPAPR_TCE_64:
> +		/* fallthrough */
> +	case KVM_CAP_SPAPR_TCE_VFIO:
>  	case KVM_CAP_PPC_RTAS:
>  	case KVM_CAP_PPC_FIXUP_HCALL:
>  	case KVM_CAP_PPC_ENABLE_HCALL:
> diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
> index d32f239eb471..d438818e2681 100644
> --- a/virt/kvm/vfio.c
> +++ b/virt/kvm/vfio.c
> @@ -20,6 +20,10 @@
>  #include <linux/vfio.h>
>  #include "vfio.h"
>  
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> +#include <asm/kvm_ppc.h>
> +#endif
> +
>  struct kvm_vfio_group {
>  	struct list_head node;
>  	struct vfio_group *vfio_group;
> @@ -89,6 +93,47 @@ static bool kvm_vfio_group_is_coherent(struct vfio_group *vfio_group)
>  	return ret > 0;
>  }
>  
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> +static int kvm_vfio_external_user_iommu_id(struct vfio_group *vfio_group)
> +{
> +	int (*fn)(struct vfio_group *);
> +	int ret = -EINVAL;
> +
> +	fn = symbol_get(vfio_external_user_iommu_id);
> +	if (!fn)
> +		return ret;
> +
> +	ret = fn(vfio_group);
> +
> +	symbol_put(vfio_external_user_iommu_id);
> +
> +	return ret;
> +}
> +
> +static struct iommu_group *kvm_vfio_group_get_iommu_group(
> +		struct vfio_group *group)
> +{
> +	int group_id = kvm_vfio_external_user_iommu_id(group);
> +
> +	if (group_id < 0)
> +		return NULL;
> +
> +	return iommu_group_get_by_id(group_id);
> +}
> +
> +static void kvm_spapr_tce_release_vfio_group(struct kvm *kvm,
> +		struct vfio_group *vfio_group)
> +{
> +	struct iommu_group *grp = kvm_vfio_group_get_iommu_group(vfio_group);
> +
> +	if (WARN_ON_ONCE(!grp))
> +		return;
> +
> +	kvm_spapr_tce_release_iommu_group(kvm, grp);
> +	iommu_group_put(grp);
> +}
> +#endif
> +
>  /*
>   * Groups can use the same or different IOMMU domains.  If the same then
>   * adding a new group may change the coherency of groups we've previously
> @@ -211,6 +256,9 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
>  
>  		mutex_unlock(&kv->lock);
>  
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> +		kvm_spapr_tce_release_vfio_group(dev->kvm, vfio_group);
> +#endif
>  		kvm_vfio_group_set_kvm(vfio_group, NULL);
>  
>  		kvm_vfio_group_put_external_user(vfio_group);
> @@ -218,6 +266,56 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
>  		kvm_vfio_update_coherency(dev);
>  
>  		return ret;
> +
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> +	case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: {
> +		struct kvm_vfio_spapr_tce param;
> +		struct kvm_vfio *kv = dev->private;
> +		struct vfio_group *vfio_group;
> +		struct kvm_vfio_group *kvg;
> +		struct fd f;
> +		struct iommu_group *grp;
> +
> +		if (copy_from_user(&param, (void __user *)arg,
> +				sizeof(struct kvm_vfio_spapr_tce)))
> +			return -EFAULT;
> +
> +		f = fdget(param.groupfd);
> +		if (!f.file)
> +			return -EBADF;
> +
> +		vfio_group = kvm_vfio_group_get_external_user(f.file);
> +		fdput(f);
> +
> +		if (IS_ERR(vfio_group))
> +			return PTR_ERR(vfio_group);
> +
> +		grp = kvm_vfio_group_get_iommu_group(vfio_group);
> +		if (WARN_ON_ONCE(!grp))

vfio_group leaked

> +			return -EIO;
> +
> +		ret = -ENOENT;
> +
> +		mutex_lock(&kv->lock);
> +
> +		list_for_each_entry(kvg, &kv->group_list, node) {
> +			if (kvg->vfio_group != vfio_group)
> +				continue;
> +
> +			ret = kvm_spapr_tce_attach_iommu_group(dev->kvm,
> +					param.tablefd, grp);
> +
> +			break;
> +		}
> +
> +		mutex_unlock(&kv->lock);
> +
> +		iommu_group_put(grp);
> +		kvm_vfio_group_put_external_user(vfio_group);
> +
> +		return ret;
> +	}
> +#endif /* CONFIG_SPAPR_TCE_IOMMU */
>  	}
>  
>  	return -ENXIO;
> @@ -242,6 +340,9 @@ static int kvm_vfio_has_attr(struct kvm_device *dev,
>  		switch (attr->attr) {
>  		case KVM_DEV_VFIO_GROUP_ADD:
>  		case KVM_DEV_VFIO_GROUP_DEL:
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> +		case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE:
> +#endif
>  			return 0;
>  		}
>  
> @@ -257,6 +358,9 @@ static void kvm_vfio_destroy(struct kvm_device *dev)
>  	struct kvm_vfio_group *kvg, *tmp;
>  
>  	list_for_each_entry_safe(kvg, tmp, &kv->group_list, node) {
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> +		kvm_spapr_tce_release_vfio_group(dev->kvm, kvg->vfio_group);
> +#endif
>  		kvm_vfio_group_set_kvm(kvg->vfio_group, NULL);
>  		kvm_vfio_group_put_external_user(kvg->vfio_group);
>  		list_del(&kvg->node);

Re: [PATCH kernel v10 10/10] KVM: PPC: VFIO: Add in-kernel acceleration for VFIO

[Alex Williamson]

On Fri, 17 Mar 2017 16:09:59 +1100
Alexey Kardashevskiy <aik@ozlabs.ru> wrote:

> This allows the host kernel to handle H_PUT_TCE, H_PUT_TCE_INDIRECT
> and H_STUFF_TCE requests targeted an IOMMU TCE table used for VFIO
> without passing them to user space which saves time on switching
> to user space and back.
> 
> This adds H_PUT_TCE/H_PUT_TCE_INDIRECT/H_STUFF_TCE handlers to KVM.
> KVM tries to handle a TCE request in the real mode, if failed
> it passes the request to the virtual mode to complete the operation.
> If it a virtual mode handler fails, the request is passed to
> the user space; this is not expected to happen though.
> 
> To avoid dealing with page use counters (which is tricky in real mode),
> this only accelerates SPAPR TCE IOMMU v2 clients which are required
> to pre-register the userspace memory. The very first TCE request will
> be handled in the VFIO SPAPR TCE driver anyway as the userspace view
> of the TCE table (iommu_table::it_userspace) is not allocated till
> the very first mapping happens and we cannot call vmalloc in real mode.
> 
> If we fail to update a hardware IOMMU table unexpected reason, we just
> clear it and move on as there is nothing really we can do about it -
> for example, if we hot plug a VFIO device to a guest, existing TCE tables
> will be mirrored automatically to the hardware and there is no interface
> to report to the guest about possible failures.
> 
> This adds new attribute - KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE - to
> the VFIO KVM device. It takes a VFIO group fd and SPAPR TCE table fd
> and associates a physical IOMMU table with the SPAPR TCE table (which
> is a guest view of the hardware IOMMU table). The iommu_table object
> is cached and referenced so we do not have to look up for it in real mode.
> 
> This does not implement the UNSET counterpart as there is no use for it -
> once the acceleration is enabled, the existing userspace won't
> disable it unless a VFIO container is destroyed; this adds necessary
> cleanup to the KVM_DEV_VFIO_GROUP_DEL handler.
> 
> This advertises the new KVM_CAP_SPAPR_TCE_VFIO capability to the user
> space.
> 
> This adds real mode version of WARN_ON_ONCE() as the generic version
> causes problems with rcu_sched. Since we testing what vmalloc_to_phys()
> returns in the code, this also adds a check for already existing
> vmalloc_to_phys() call in kvmppc_rm_h_put_tce_indirect().
> 
> This finally makes use of vfio_external_user_iommu_id() which was
> introduced quite some time ago and was considered for removal.
> 
> Tests show that this patch increases transmission speed from 220MB/s
> to 750..1020MB/s on 10Gb network (Chelsea CXGB3 10Gb ethernet card).
> 
> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
> ---
> Changes:
> v10:
> * fixed leaking references in virt/kvm/vfio.c
> * moved code to helpers - kvm_vfio_group_get_iommu_group, kvm_spapr_tce_release_vfio_group
> * fixed possible race between referencing table and destroying it via
> VFIO add/remove window ioctls()
> 
> v9:
> * removed referencing a group in KVM, only referencing iommu_table's now
> * fixed a reference leak in KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE handler
> * fixed typo in vfio.txt
> * removed @argsz and @flags from struct kvm_vfio_spapr_tce
> 
> v8:
> * changed all (!pua) checks to return H_TOO_HARD as ioctl() is supposed
> to handle them
> * changed vmalloc_to_phys() callers to return H_HARDWARE
> * changed real mode iommu_tce_xchg_rm() callers to return H_TOO_HARD
> and added a comment about this in the code
> * changed virtual mode iommu_tce_xchg() callers to return H_HARDWARE
> and do WARN_ON
> * added WARN_ON_ONCE_RM(!rmap) in kvmppc_rm_h_put_tce_indirect() to
> have all vmalloc_to_phys() callsites covered
> 
> v7:
> * added realmode-friendly WARN_ON_ONCE_RM
> 
> v6:
> * changed handling of errors returned by kvmppc_(rm_)tce_iommu_(un)map()
> * moved kvmppc_gpa_to_ua() to TCE validation
> 
> v5:
> * changed error codes in multiple places
> * added bunch of WARN_ON() in places which should not really happen
> * adde a check that an iommu table is not attached already to LIOBN
> * dropped explicit calls to iommu_tce_clear_param_check/
> iommu_tce_put_param_check as kvmppc_tce_validate/kvmppc_ioba_validate
> call them anyway (since the previous patch)
> * if we fail to update a hardware IOMMU table for unexpected reason,
> this just clears the entry
> 
> v4:
> * added note to the commit log about allowing multiple updates of
> the same IOMMU table;
> * instead of checking for if any memory was preregistered, this
> returns H_TOO_HARD if a specific page was not;
> * fixed comments from v3 about error handling in many places;
> * simplified TCE handlers and merged IOMMU parts inline - for example,
> there used to be kvmppc_h_put_tce_iommu(), now it is merged into
> kvmppc_h_put_tce(); this allows to check IOBA boundaries against
> the first attached table only (makes the code simpler);
> 
> v3:
> * simplified not to use VFIO group notifiers
> * reworked cleanup, should be cleaner/simpler now
> 
> v2:
> * reworked to use new VFIO notifiers
> * now same iommu_table may appear in the list several times, to be fixed later
> ---
>  Documentation/virtual/kvm/devices/vfio.txt |  18 +-
>  arch/powerpc/include/asm/kvm_host.h        |   8 +
>  arch/powerpc/include/asm/kvm_ppc.h         |   4 +
>  include/uapi/linux/kvm.h                   |   6 +
>  arch/powerpc/kvm/book3s_64_vio.c           | 301 ++++++++++++++++++++++++++++-
>  arch/powerpc/kvm/book3s_64_vio_hv.c        | 201 ++++++++++++++++++-
>  arch/powerpc/kvm/powerpc.c                 |   2 +
>  virt/kvm/vfio.c                            | 104 ++++++++++
>  8 files changed, 639 insertions(+), 5 deletions(-)
> 
> diff --git a/Documentation/virtual/kvm/devices/vfio.txt b/Documentation/virtual/kvm/devices/vfio.txt
> index ef51740c67ca..528c77c8022c 100644
> --- a/Documentation/virtual/kvm/devices/vfio.txt
> +++ b/Documentation/virtual/kvm/devices/vfio.txt
> @@ -16,7 +16,21 @@ Groups:
>  
>  KVM_DEV_VFIO_GROUP attributes:
>    KVM_DEV_VFIO_GROUP_ADD: Add a VFIO group to VFIO-KVM device tracking
> +	kvm_device_attr.addr points to an int32_t file descriptor
> +	for the VFIO group.
>    KVM_DEV_VFIO_GROUP_DEL: Remove a VFIO group from VFIO-KVM device tracking
> +	kvm_device_attr.addr points to an int32_t file descriptor
> +	for the VFIO group.
> +  KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: attaches a guest visible TCE table
> +	allocated by sPAPR KVM.
> +	kvm_device_attr.addr points to a struct:
>  
> -For each, kvm_device_attr.addr points to an int32_t file descriptor
> -for the VFIO group.
> +	struct kvm_vfio_spapr_tce {
> +		__s32	groupfd;
> +		__s32	tablefd;
> +	};
> +
> +	where
> +	@groupfd is a file descriptor for a VFIO group;
> +	@tablefd is a file descriptor for a TCE table allocated via
> +		KVM_CREATE_SPAPR_TCE.
> diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
> index 7bba8f415627..178074e643e5 100644
> --- a/arch/powerpc/include/asm/kvm_host.h
> +++ b/arch/powerpc/include/asm/kvm_host.h
> @@ -191,6 +191,13 @@ struct kvmppc_pginfo {
>  	atomic_t refcnt;
>  };
>  
> +struct kvmppc_spapr_tce_iommu_table {
> +	struct rcu_head rcu;
> +	struct list_head next;
> +	struct iommu_table *tbl;
> +	struct kref kref;
> +};
> +
>  struct kvmppc_spapr_tce_table {
>  	struct list_head list;
>  	struct kvm *kvm;
> @@ -199,6 +206,7 @@ struct kvmppc_spapr_tce_table {
>  	u32 page_shift;
>  	u64 offset;		/* in pages */
>  	u64 size;		/* window size in pages */
> +	struct list_head iommu_tables;
>  	struct page *pages[0];
>  };
>  
> diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
> index 72c2a155641f..cfd45714189e 100644
> --- a/arch/powerpc/include/asm/kvm_ppc.h
> +++ b/arch/powerpc/include/asm/kvm_ppc.h
> @@ -164,6 +164,10 @@ extern long kvmppc_prepare_vrma(struct kvm *kvm,
>  extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu,
>  			struct kvm_memory_slot *memslot, unsigned long porder);
>  extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
> +extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
> +		struct iommu_group *grp);
> +extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
> +		struct iommu_group *grp);
>  
>  extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
>  				struct kvm_create_spapr_tce_64 *args);
> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> index f5a52ffb6b58..0f8a5e6528aa 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -1088,6 +1088,7 @@ struct kvm_device_attr {
>  #define  KVM_DEV_VFIO_GROUP			1
>  #define   KVM_DEV_VFIO_GROUP_ADD			1
>  #define   KVM_DEV_VFIO_GROUP_DEL			2
> +#define   KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE		3
>  
>  enum kvm_device_type {
>  	KVM_DEV_TYPE_FSL_MPIC_20	= 1,
> @@ -1109,6 +1110,11 @@ enum kvm_device_type {
>  	KVM_DEV_TYPE_MAX,
>  };
>  
> +struct kvm_vfio_spapr_tce {
> +	__s32	groupfd;
> +	__s32	tablefd;
> +};
> +
>  /*
>   * ioctls for VM fds
>   */
> diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
> index e96a4590464c..22c67a47eaab 100644
> --- a/arch/powerpc/kvm/book3s_64_vio.c
> +++ b/arch/powerpc/kvm/book3s_64_vio.c
> @@ -28,6 +28,8 @@
>  #include <linux/hugetlb.h>
>  #include <linux/list.h>
>  #include <linux/anon_inodes.h>
> +#include <linux/iommu.h>
> +#include <linux/file.h>
>  
>  #include <asm/tlbflush.h>
>  #include <asm/kvm_ppc.h>
> @@ -40,6 +42,7 @@
>  #include <asm/udbg.h>
>  #include <asm/iommu.h>
>  #include <asm/tce.h>
> +#include <asm/mmu_context.h>
>  
>  static unsigned long kvmppc_tce_pages(unsigned long iommu_pages)
>  {
> @@ -91,6 +94,132 @@ static long kvmppc_account_memlimit(unsigned long stt_pages, bool inc)
>  	return ret;
>  }
>  
> +static void kvm_spapr_tce_iommu_table_free(struct rcu_head *head)
> +{
> +	struct kvmppc_spapr_tce_iommu_table *stit = container_of(head,
> +			struct kvmppc_spapr_tce_iommu_table, rcu);
> +
> +	iommu_tce_table_put(stit->tbl);
> +
> +	kfree(stit);
> +}
> +
> +static void kvm_spapr_tce_liobn_put(struct kref *kref)
> +{
> +	struct kvmppc_spapr_tce_iommu_table *stit = container_of(kref,
> +			struct kvmppc_spapr_tce_iommu_table, kref);
> +
> +	list_del_rcu(&stit->next);
> +
> +	call_rcu(&stit->rcu, kvm_spapr_tce_iommu_table_free);
> +}
> +
> +extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
> +		struct iommu_group *grp)
> +{
> +	int i;
> +	struct kvmppc_spapr_tce_table *stt;
> +	struct kvmppc_spapr_tce_iommu_table *stit, *tmp;
> +	struct iommu_table_group *table_group = NULL;
> +
> +	list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) {
> +
> +		table_group = iommu_group_get_iommudata(grp);
> +		if (WARN_ON(!table_group))
> +			continue;
> +
> +		list_for_each_entry_safe(stit, tmp, &stt->iommu_tables, next) {
> +			for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
> +				if (table_group->tables[i] != stit->tbl)
> +					continue;
> +
> +				kref_put(&stit->kref, kvm_spapr_tce_liobn_put);
> +				return;
> +			}
> +		}
> +	}
> +}
> +
> +extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
> +		struct iommu_group *grp)
> +{
> +	struct kvmppc_spapr_tce_table *stt = NULL;
> +	bool found = false;
> +	struct iommu_table *tbl = NULL;
> +	struct iommu_table_group *table_group;
> +	long i;
> +	struct kvmppc_spapr_tce_iommu_table *stit;
> +	struct fd f;
> +
> +	f = fdget(tablefd);
> +	if (!f.file)
> +		return -EBADF;
> +
> +	list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) {
> +		if (stt == f.file->private_data) {
> +			found = true;
> +			break;
> +		}
> +	}
> +
> +	fdput(f);
> +
> +	if (!found)
> +		return -EINVAL;
> +
> +	table_group = iommu_group_get_iommudata(grp);
> +	if (WARN_ON(!table_group))
> +		return -EFAULT;
> +
> +	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
> +		struct iommu_table *tbltmp = table_group->tables[i];
> +
> +		if (!tbltmp)
> +			continue;
> +		/*
> +		 * Make sure hardware table parameters are exactly the same;
> +		 * this is used in the TCE handlers where boundary checks
> +		 * use only the first attached table.
> +		 */
> +		if ((tbltmp->it_page_shift == stt->page_shift) &&
> +				(tbltmp->it_offset == stt->offset) &&
> +				(tbltmp->it_size == stt->size)) {
> +			/*
> +			 * Reference the table to avoid races with
> +			 * add/remove DMA windows.
> +			 */
> +			tbl = iommu_tce_table_get(tbltmp);
> +			break;
> +		}
> +	}
> +	if (!tbl)
> +		return -EINVAL;
> +
> +	list_for_each_entry_rcu(stit, &stt->iommu_tables, next) {
> +		if (tbl != stit->tbl)
> +			continue;
> +
> +		if (!kref_get_unless_zero(&stit->kref)) {
> +			/* stit is being destroyed */
> +			iommu_tce_table_put(tbl);
> +			return -ENOTTY;
> +		}
> +		/*
> +		 * The table is already known to this KVM, we just increased
> +		 * its KVM reference counter and can return.
> +		 */
> +		return 0;
> +	}
> +
> +	stit = kzalloc(sizeof(*stit), GFP_KERNEL);
> +	stit->tbl = tbl;
> +	kref_init(&stit->kref);
> +
> +	list_add_rcu(&stit->next, &stt->iommu_tables);
> +
> +	return 0;
> +}
> +
>  static void release_spapr_tce_table(struct rcu_head *head)
>  {
>  	struct kvmppc_spapr_tce_table *stt = container_of(head,
> @@ -130,9 +259,18 @@ static int kvm_spapr_tce_mmap(struct file *file, struct vm_area_struct *vma)
>  static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
>  {
>  	struct kvmppc_spapr_tce_table *stt = filp->private_data;
> +	struct kvmppc_spapr_tce_iommu_table *stit, *tmp;
>  
>  	list_del_rcu(&stt->list);
>  
> +	list_for_each_entry_safe(stit, tmp, &stt->iommu_tables, next) {
> +		WARN_ON(!kref_read(&stit->kref));
> +		while (1) {
> +			if (kref_put(&stit->kref, kvm_spapr_tce_liobn_put))
> +				break;
> +		}
> +	}
> +
>  	kvm_put_kvm(stt->kvm);
>  
>  	kvmppc_account_memlimit(
> @@ -183,6 +321,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
>  	stt->offset = args->offset;
>  	stt->size = size;
>  	stt->kvm = kvm;
> +	INIT_LIST_HEAD_RCU(&stt->iommu_tables);
>  
>  	for (i = 0; i < npages; i++) {
>  		stt->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
> @@ -211,11 +350,101 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
>  	return ret;
>  }
>  
> +static void kvmppc_clear_tce(struct iommu_table *tbl, unsigned long entry)
> +{
> +	unsigned long hpa = 0;
> +	enum dma_data_direction dir = DMA_NONE;
> +
> +	iommu_tce_xchg(tbl, entry, &hpa, &dir);
> +}
> +
> +static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm,
> +		struct iommu_table *tbl, unsigned long entry)
> +{
> +	struct mm_iommu_table_group_mem_t *mem = NULL;
> +	const unsigned long pgsize = 1ULL << tbl->it_page_shift;
> +	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
> +
> +	if (!pua)
> +		/* it_userspace allocation might be delayed */
> +		return H_TOO_HARD;
> +
> +	mem = mm_iommu_lookup(kvm->mm, *pua, pgsize);
> +	if (!mem)
> +		return H_TOO_HARD;
> +
> +	mm_iommu_mapped_dec(mem);
> +
> +	*pua = 0;
> +
> +	return H_SUCCESS;
> +}
> +
> +static long kvmppc_tce_iommu_unmap(struct kvm *kvm,
> +		struct iommu_table *tbl, unsigned long entry)
> +{
> +	enum dma_data_direction dir = DMA_NONE;
> +	unsigned long hpa = 0;
> +	long ret;
> +
> +	if (WARN_ON_ONCE(iommu_tce_xchg(tbl, entry, &hpa, &dir)))
> +		return H_HARDWARE;
> +
> +	if (dir == DMA_NONE)
> +		return H_SUCCESS;
> +
> +	ret = kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry);
> +	if (ret != H_SUCCESS)
> +		iommu_tce_xchg(tbl, entry, &hpa, &dir);
> +
> +	return ret;
> +}
> +
> +long kvmppc_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
> +		unsigned long entry, unsigned long ua,
> +		enum dma_data_direction dir)
> +{
> +	long ret;
> +	unsigned long hpa, *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
> +	struct mm_iommu_table_group_mem_t *mem;
> +
> +	if (!pua)
> +		/* it_userspace allocation might be delayed */
> +		return H_TOO_HARD;
> +
> +	mem = mm_iommu_lookup(kvm->mm, ua, 1ULL << tbl->it_page_shift);
> +	if (!mem)
> +		/* This only handles v2 IOMMU type, v1 is handled via ioctl() */
> +		return H_TOO_HARD;
> +
> +	if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, &hpa)))
> +		return H_HARDWARE;
> +
> +	if (mm_iommu_mapped_inc(mem))
> +		return H_CLOSED;
> +
> +	ret = iommu_tce_xchg(tbl, entry, &hpa, &dir);
> +	if (WARN_ON_ONCE(ret)) {
> +		mm_iommu_mapped_dec(mem);
> +		return H_HARDWARE;
> +	}
> +
> +	if (dir != DMA_NONE)
> +		kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry);
> +
> +	*pua = ua;
> +
> +	return 0;
> +}
> +
>  long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>  		      unsigned long ioba, unsigned long tce)
>  {
>  	struct kvmppc_spapr_tce_table *stt;
> -	long ret;
> +	long ret, idx;
> +	struct kvmppc_spapr_tce_iommu_table *stit;
> +	unsigned long entry, ua = 0;
> +	enum dma_data_direction dir;
>  
>  	/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
>  	/* 	    liobn, ioba, tce); */
> @@ -232,7 +461,35 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>  	if (ret != H_SUCCESS)
>  		return ret;
>  
> -	kvmppc_tce_put(stt, ioba >> stt->page_shift, tce);
> +	dir = iommu_tce_direction(tce);
> +	if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm,
> +			tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL))
> +		return H_PARAMETER;
> +
> +	entry = ioba >> stt->page_shift;
> +
> +	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
> +		if (dir == DMA_NONE) {
> +			ret = kvmppc_tce_iommu_unmap(vcpu->kvm,
> +					stit->tbl, entry);
> +		} else {
> +			idx = srcu_read_lock(&vcpu->kvm->srcu);
> +			ret = kvmppc_tce_iommu_map(vcpu->kvm, stit->tbl,
> +					entry, ua, dir);
> +			srcu_read_unlock(&vcpu->kvm->srcu, idx);
> +		}
> +
> +		if (ret == H_SUCCESS)
> +			continue;
> +
> +		if (ret == H_TOO_HARD)
> +			return ret;
> +
> +		WARN_ON_ONCE(1);
> +		kvmppc_clear_tce(stit->tbl, entry);
> +	}
> +
> +	kvmppc_tce_put(stt, entry, tce);
>  
>  	return H_SUCCESS;
>  }
> @@ -247,6 +504,7 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
>  	unsigned long entry, ua = 0;
>  	u64 __user *tces;
>  	u64 tce;
> +	struct kvmppc_spapr_tce_iommu_table *stit;
>  
>  	stt = kvmppc_find_table(vcpu->kvm, liobn);
>  	if (!stt)
> @@ -285,6 +543,26 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
>  		if (ret != H_SUCCESS)
>  			goto unlock_exit;
>  
> +		if (kvmppc_gpa_to_ua(vcpu->kvm,
> +				tce & ~(TCE_PCI_READ | TCE_PCI_WRITE),
> +				&ua, NULL))
> +			return H_PARAMETER;
> +
> +		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
> +			ret = kvmppc_tce_iommu_map(vcpu->kvm,
> +					stit->tbl, entry + i, ua,
> +					iommu_tce_direction(tce));
> +
> +			if (ret == H_SUCCESS)
> +				continue;
> +
> +			if (ret == H_TOO_HARD)
> +				goto unlock_exit;
> +
> +			WARN_ON_ONCE(1);
> +			kvmppc_clear_tce(stit->tbl, entry);
> +		}
> +
>  		kvmppc_tce_put(stt, entry + i, tce);
>  	}
>  
> @@ -301,6 +579,7 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
>  {
>  	struct kvmppc_spapr_tce_table *stt;
>  	long i, ret;
> +	struct kvmppc_spapr_tce_iommu_table *stit;
>  
>  	stt = kvmppc_find_table(vcpu->kvm, liobn);
>  	if (!stt)
> @@ -314,6 +593,24 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
>  	if (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ))
>  		return H_PARAMETER;
>  
> +	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
> +		unsigned long entry = ioba >> stit->tbl->it_page_shift;
> +
> +		for (i = 0; i < npages; ++i) {
> +			ret = kvmppc_tce_iommu_unmap(vcpu->kvm,
> +					stit->tbl, entry + i);
> +
> +			if (ret == H_SUCCESS)
> +				continue;
> +
> +			if (ret == H_TOO_HARD)
> +				return ret;
> +
> +			WARN_ON_ONCE(1);
> +			kvmppc_clear_tce(stit->tbl, entry);
> +		}
> +	}
> +
>  	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
>  		kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
>  
> diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
> index 440d3ab5dc32..eda0a8f6fae8 100644
> --- a/arch/powerpc/kvm/book3s_64_vio_hv.c
> +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
> @@ -40,6 +40,31 @@
>  #include <asm/iommu.h>
>  #include <asm/tce.h>
>  
> +#ifdef CONFIG_BUG
> +
> +#define WARN_ON_ONCE_RM(condition)	({			\
> +	static bool __section(.data.unlikely) __warned;		\
> +	int __ret_warn_once = !!(condition);			\
> +								\
> +	if (unlikely(__ret_warn_once && !__warned)) {		\
> +		__warned = true;				\
> +		pr_err("WARN_ON_ONCE_RM: (%s) at %s:%u\n",	\
> +				__stringify(condition),		\
> +				__func__, __LINE__);		\
> +		dump_stack();					\
> +	}							\
> +	unlikely(__ret_warn_once);				\
> +})
> +
> +#else
> +
> +#define WARN_ON_ONCE_RM(condition) ({				\
> +	int __ret_warn_on = !!(condition);			\
> +	unlikely(__ret_warn_on);				\
> +})
> +
> +#endif
> +
>  #define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
>  
>  /*
> @@ -161,11 +186,117 @@ long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
>  EXPORT_SYMBOL_GPL(kvmppc_gpa_to_ua);
>  
>  #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
> +static void kvmppc_rm_clear_tce(struct iommu_table *tbl, unsigned long entry)
> +{
> +	unsigned long hpa = 0;
> +	enum dma_data_direction dir = DMA_NONE;
> +
> +	iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
> +}
> +
> +static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm,
> +		struct iommu_table *tbl, unsigned long entry)
> +{
> +	struct mm_iommu_table_group_mem_t *mem = NULL;
> +	const unsigned long pgsize = 1ULL << tbl->it_page_shift;
> +	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
> +
> +	if (!pua)
> +		/* it_userspace allocation might be delayed */
> +		return H_TOO_HARD;
> +
> +	pua = (void *) vmalloc_to_phys(pua);
> +	if (WARN_ON_ONCE_RM(!pua))
> +		return H_HARDWARE;
> +
> +	mem = mm_iommu_lookup_rm(kvm->mm, *pua, pgsize);
> +	if (!mem)
> +		return H_TOO_HARD;
> +
> +	mm_iommu_mapped_dec(mem);
> +
> +	*pua = 0;
> +
> +	return H_SUCCESS;
> +}
> +
> +static long kvmppc_rm_tce_iommu_unmap(struct kvm *kvm,
> +		struct iommu_table *tbl, unsigned long entry)
> +{
> +	enum dma_data_direction dir = DMA_NONE;
> +	unsigned long hpa = 0;
> +	long ret;
> +
> +	if (iommu_tce_xchg_rm(tbl, entry, &hpa, &dir))
> +		/*
> +		 * real mode xchg can fail if struct page crosses
> +		 * a page boundary
> +		 */
> +		return H_TOO_HARD;
> +
> +	if (dir == DMA_NONE)
> +		return H_SUCCESS;
> +
> +	ret = kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);
> +	if (ret)
> +		iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
> +
> +	return ret;
> +}
> +
> +static long kvmppc_rm_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
> +		unsigned long entry, unsigned long ua,
> +		enum dma_data_direction dir)
> +{
> +	long ret;
> +	unsigned long hpa = 0;
> +	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
> +	struct mm_iommu_table_group_mem_t *mem;
> +
> +	if (!pua)
> +		/* it_userspace allocation might be delayed */
> +		return H_TOO_HARD;
> +
> +	mem = mm_iommu_lookup_rm(kvm->mm, ua, 1ULL << tbl->it_page_shift);
> +	if (!mem)
> +		return H_TOO_HARD;
> +
> +	if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, &hpa)))
> +		return H_HARDWARE;
> +
> +	pua = (void *) vmalloc_to_phys(pua);
> +	if (WARN_ON_ONCE_RM(!pua))
> +		return H_HARDWARE;
> +
> +	if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem)))
> +		return H_CLOSED;
> +
> +	ret = iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
> +	if (ret) {
> +		mm_iommu_mapped_dec(mem);
> +		/*
> +		 * real mode xchg can fail if struct page crosses
> +		 * a page boundary
> +		 */
> +		return H_TOO_HARD;
> +	}
> +
> +	if (dir != DMA_NONE)
> +		kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);
> +
> +	*pua = ua;
> +
> +	return 0;
> +}
> +
>  long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>  		unsigned long ioba, unsigned long tce)
>  {
>  	struct kvmppc_spapr_tce_table *stt;
>  	long ret;
> +	struct kvmppc_spapr_tce_iommu_table *stit;
> +	unsigned long entry, ua = 0;
> +	enum dma_data_direction dir;
>  
>  	/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
>  	/* 	    liobn, ioba, tce); */
> @@ -182,7 +313,32 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>  	if (ret != H_SUCCESS)
>  		return ret;
>  
> -	kvmppc_tce_put(stt, ioba >> stt->page_shift, tce);
> +	dir = iommu_tce_direction(tce);
> +	if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm,
> +			tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL))
> +		return H_PARAMETER;
> +
> +	entry = ioba >> stt->page_shift;
> +
> +	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
> +		if (dir == DMA_NONE)
> +			ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm,
> +					stit->tbl, entry);
> +		else
> +			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm,
> +					stit->tbl, entry, ua, dir);
> +
> +		if (ret == H_SUCCESS)
> +			continue;
> +
> +		if (ret == H_TOO_HARD)
> +			return ret;
> +
> +		WARN_ON_ONCE_RM(1);
> +		kvmppc_rm_clear_tce(stit->tbl, entry);
> +	}
> +
> +	kvmppc_tce_put(stt, entry, tce);
>  
>  	return H_SUCCESS;
>  }
> @@ -223,6 +379,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
>  	unsigned long tces, entry, ua = 0;
>  	unsigned long *rmap = NULL;
>  	bool prereg = false;
> +	struct kvmppc_spapr_tce_iommu_table *stit;
>  
>  	stt = kvmppc_find_table(vcpu->kvm, liobn);
>  	if (!stt)
> @@ -270,6 +427,8 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
>  			return H_TOO_HARD;
>  
>  		rmap = (void *) vmalloc_to_phys(rmap);
> +		if (WARN_ON_ONCE_RM(!rmap))
> +			return H_HARDWARE;
>  
>  		/*
>  		 * Synchronize with the MMU notifier callbacks in
> @@ -293,6 +452,27 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
>  		if (ret != H_SUCCESS)
>  			goto unlock_exit;
>  
> +		ua = 0;
> +		if (kvmppc_gpa_to_ua(vcpu->kvm,
> +				tce & ~(TCE_PCI_READ | TCE_PCI_WRITE),
> +				&ua, NULL))
> +			return H_PARAMETER;
> +
> +		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
> +			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm,
> +					stit->tbl, entry + i, ua,
> +					iommu_tce_direction(tce));
> +
> +			if (ret == H_SUCCESS)
> +				continue;
> +
> +			if (ret == H_TOO_HARD)
> +				goto unlock_exit;
> +
> +			WARN_ON_ONCE_RM(1);
> +			kvmppc_rm_clear_tce(stit->tbl, entry);
> +		}
> +
>  		kvmppc_tce_put(stt, entry + i, tce);
>  	}
>  
> @@ -309,6 +489,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
>  {
>  	struct kvmppc_spapr_tce_table *stt;
>  	long i, ret;
> +	struct kvmppc_spapr_tce_iommu_table *stit;
>  
>  	stt = kvmppc_find_table(vcpu->kvm, liobn);
>  	if (!stt)
> @@ -322,6 +503,24 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
>  	if (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ))
>  		return H_PARAMETER;
>  
> +	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
> +		unsigned long entry = ioba >> stit->tbl->it_page_shift;
> +
> +		for (i = 0; i < npages; ++i) {
> +			ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm,
> +					stit->tbl, entry + i);
> +
> +			if (ret == H_SUCCESS)
> +				continue;
> +
> +			if (ret == H_TOO_HARD)
> +				return ret;
> +
> +			WARN_ON_ONCE_RM(1);
> +			kvmppc_rm_clear_tce(stit->tbl, entry);
> +		}
> +	}
> +
>  	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
>  		kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
>  
> diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
> index 95c91a9de351..62bdd6c48107 100644
> --- a/arch/powerpc/kvm/powerpc.c
> +++ b/arch/powerpc/kvm/powerpc.c
> @@ -538,6 +538,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
>  #ifdef CONFIG_PPC_BOOK3S_64
>  	case KVM_CAP_SPAPR_TCE:
>  	case KVM_CAP_SPAPR_TCE_64:
> +		/* fallthrough */
> +	case KVM_CAP_SPAPR_TCE_VFIO:
>  	case KVM_CAP_PPC_RTAS:
>  	case KVM_CAP_PPC_FIXUP_HCALL:
>  	case KVM_CAP_PPC_ENABLE_HCALL:
> diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
> index d32f239eb471..d438818e2681 100644
> --- a/virt/kvm/vfio.c
> +++ b/virt/kvm/vfio.c
> @@ -20,6 +20,10 @@
>  #include <linux/vfio.h>
>  #include "vfio.h"
>  
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> +#include <asm/kvm_ppc.h>
> +#endif
> +
>  struct kvm_vfio_group {
>  	struct list_head node;
>  	struct vfio_group *vfio_group;
> @@ -89,6 +93,47 @@ static bool kvm_vfio_group_is_coherent(struct vfio_group *vfio_group)
>  	return ret > 0;
>  }
>  
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> +static int kvm_vfio_external_user_iommu_id(struct vfio_group *vfio_group)
> +{
> +	int (*fn)(struct vfio_group *);
> +	int ret = -EINVAL;
> +
> +	fn = symbol_get(vfio_external_user_iommu_id);
> +	if (!fn)
> +		return ret;
> +
> +	ret = fn(vfio_group);
> +
> +	symbol_put(vfio_external_user_iommu_id);
> +
> +	return ret;
> +}
> +
> +static struct iommu_group *kvm_vfio_group_get_iommu_group(
> +		struct vfio_group *group)
> +{
> +	int group_id = kvm_vfio_external_user_iommu_id(group);
> +
> +	if (group_id < 0)
> +		return NULL;
> +
> +	return iommu_group_get_by_id(group_id);
> +}
> +
> +static void kvm_spapr_tce_release_vfio_group(struct kvm *kvm,
> +		struct vfio_group *vfio_group)
> +{
> +	struct iommu_group *grp = kvm_vfio_group_get_iommu_group(vfio_group);
> +
> +	if (WARN_ON_ONCE(!grp))
> +		return;
> +
> +	kvm_spapr_tce_release_iommu_group(kvm, grp);
> +	iommu_group_put(grp);
> +}
> +#endif
> +
>  /*
>   * Groups can use the same or different IOMMU domains.  If the same then
>   * adding a new group may change the coherency of groups we've previously
> @@ -211,6 +256,9 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
>  
>  		mutex_unlock(&kv->lock);
>  
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> +		kvm_spapr_tce_release_vfio_group(dev->kvm, vfio_group);
> +#endif
>  		kvm_vfio_group_set_kvm(vfio_group, NULL);
>  
>  		kvm_vfio_group_put_external_user(vfio_group);
> @@ -218,6 +266,56 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
>  		kvm_vfio_update_coherency(dev);
>  
>  		return ret;
> +
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> +	case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: {
> +		struct kvm_vfio_spapr_tce param;
> +		struct kvm_vfio *kv = dev->private;
> +		struct vfio_group *vfio_group;
> +		struct kvm_vfio_group *kvg;
> +		struct fd f;
> +		struct iommu_group *grp;
> +
> +		if (copy_from_user(&param, (void __user *)arg,
> +				sizeof(struct kvm_vfio_spapr_tce)))
> +			return -EFAULT;
> +
> +		f = fdget(param.groupfd);
> +		if (!f.file)
> +			return -EBADF;
> +
> +		vfio_group = kvm_vfio_group_get_external_user(f.file);
> +		fdput(f);
> +
> +		if (IS_ERR(vfio_group))
> +			return PTR_ERR(vfio_group);
> +
> +		grp = kvm_vfio_group_get_iommu_group(vfio_group);
> +		if (WARN_ON_ONCE(!grp))

vfio_group leaked

> +			return -EIO;
> +
> +		ret = -ENOENT;
> +
> +		mutex_lock(&kv->lock);
> +
> +		list_for_each_entry(kvg, &kv->group_list, node) {
> +			if (kvg->vfio_group != vfio_group)
> +				continue;
> +
> +			ret = kvm_spapr_tce_attach_iommu_group(dev->kvm,
> +					param.tablefd, grp);
> +
> +			break;
> +		}
> +
> +		mutex_unlock(&kv->lock);
> +
> +		iommu_group_put(grp);
> +		kvm_vfio_group_put_external_user(vfio_group);
> +
> +		return ret;
> +	}
> +#endif /* CONFIG_SPAPR_TCE_IOMMU */
>  	}
>  
>  	return -ENXIO;
> @@ -242,6 +340,9 @@ static int kvm_vfio_has_attr(struct kvm_device *dev,
>  		switch (attr->attr) {
>  		case KVM_DEV_VFIO_GROUP_ADD:
>  		case KVM_DEV_VFIO_GROUP_DEL:
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> +		case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE:
> +#endif
>  			return 0;
>  		}
>  
> @@ -257,6 +358,9 @@ static void kvm_vfio_destroy(struct kvm_device *dev)
>  	struct kvm_vfio_group *kvg, *tmp;
>  
>  	list_for_each_entry_safe(kvg, tmp, &kv->group_list, node) {
> +#ifdef CONFIG_SPAPR_TCE_IOMMU
> +		kvm_spapr_tce_release_vfio_group(dev->kvm, kvg->vfio_group);
> +#endif
>  		kvm_vfio_group_set_kvm(kvg->vfio_group, NULL);
>  		kvm_vfio_group_put_external_user(kvg->vfio_group);
>  		list_del(&kvg->node);