Re: [PATCH kernel 9/9] KVM: PPC: Add support for multiple-TCE hcalls

2015-12-21 Thread Alexey Kardashevskiy 

On 12/08/2015 04:48 PM, David Gibson wrote:

On Tue, Sep 15, 2015 at 08:49:39PM +1000, Alexey Kardashevskiy wrote:

This adds real and virtual mode handlers for the H_PUT_TCE_INDIRECT and
H_STUFF_TCE hypercalls for user space emulated devices such as IBMVIO
devices or emulated PCI.  These calls allow adding multiple entries
(up to 512) into the TCE table in one call which saves time on
transition between kernel and user space.

This implements the KVM_CAP_PPC_MULTITCE capability. When present,
the kernel will try handling H_PUT_TCE_INDIRECT and H_STUFF_TCE.
If they can not be handled by the kernel, they are passed on to
the user space. The user space still has to have an implementation
for these.

Both HV and PR-syle KVM are supported.

Signed-off-by: Alexey Kardashevskiy 
---
  Documentation/virtual/kvm/api.txt   |  25 ++
  arch/powerpc/include/asm/kvm_ppc.h  |  12 +++
  arch/powerpc/kvm/book3s_64_vio.c| 111 +++-
  arch/powerpc/kvm/book3s_64_vio_hv.c | 145 ++--
  arch/powerpc/kvm/book3s_hv.c|  26 +-
  arch/powerpc/kvm/book3s_hv_rmhandlers.S |   6 +-
  arch/powerpc/kvm/book3s_pr_papr.c   |  35 
  arch/powerpc/kvm/powerpc.c  |   3 +
  8 files changed, 350 insertions(+), 13 deletions(-)

diff --git a/Documentation/virtual/kvm/api.txt 
b/Documentation/virtual/kvm/api.txt
index d86d831..593c62a 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -3019,6 +3019,31 @@ Returns: 0 on success, -1 on error

  Queues an SMI on the thread's vcpu.

+4.97 KVM_CAP_PPC_MULTITCE
+
+Capability: KVM_CAP_PPC_MULTITCE
+Architectures: ppc
+Type: vm
+
+This capability means the kernel is capable of handling hypercalls
+H_PUT_TCE_INDIRECT and H_STUFF_TCE without passing those into the user
+space. This significantly accelerates DMA operations for PPC KVM guests.
+User space should expect that its handlers for these hypercalls
+are not going to be called if user space previously registered LIOBN
+in KVM (via KVM_CREATE_SPAPR_TCE or similar calls).
+
+In order to enable H_PUT_TCE_INDIRECT and H_STUFF_TCE use in the guest,
+user space might have to advertise it for the guest. For example,
+IBM pSeries (sPAPR) guest starts using them if "hcall-multi-tce" is
+present in the "ibm,hypertas-functions" device-tree property.
+
+The hypercalls mentioned above may or may not be processed successfully
+in the kernel based fast path. If they can not be handled by the kernel,
+they will get passed on to user space. So user space still has to have
+an implementation for these despite the in kernel acceleration.
+
+This capability is always enabled.
+
  5. The kvm_run structure
  

diff --git a/arch/powerpc/include/asm/kvm_ppc.h 
b/arch/powerpc/include/asm/kvm_ppc.h
index fcde896..e5b968e 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -166,12 +166,24 @@ 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 *args);
+extern struct kvmppc_spapr_tce_table *kvmppc_find_table(
+   struct kvm_vcpu *vcpu, 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,
unsigned long tce);
+extern long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
+   unsigned long *ua, unsigned long **prmap);
+extern void kvmppc_tce_put(struct kvmppc_spapr_tce_table *tt,
+   unsigned long idx, unsigned long tce);
  extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 unsigned long ioba, unsigned long tce);
+extern long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
+   unsigned long liobn, unsigned long ioba,
+   unsigned long tce_list, unsigned long npages);
+extern long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
+   unsigned long liobn, unsigned long ioba,
+   unsigned long tce_value, unsigned long npages);
  extern long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 unsigned long ioba);
  extern struct page *kvm_alloc_hpt(unsigned long nr_pages);
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index e347856..d3fc732 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -14,6 +14,7 @@
   *
   * Copyright 2010 Paul Mackerras, IBM Corp. 
   * Copyright 2011 David Gibson, IBM Corporation 
+ * Copyright 2013 Alexey Kardashevskiy, IBM Corporation 
   */

  #include 
@@ -37,8 +38,7 @@
  #include 
  #include 
  #include 
-
-#define TCES_PER_PAGE

Re: [PATCH kernel 9/9] KVM: PPC: Add support for multiple-TCE hcalls

2015-12-21 Thread Alexey Kardashevskiy 

On 12/08/2015 04:48 PM, David Gibson wrote:

On Tue, Sep 15, 2015 at 08:49:39PM +1000, Alexey Kardashevskiy wrote:

This adds real and virtual mode handlers for the H_PUT_TCE_INDIRECT and
H_STUFF_TCE hypercalls for user space emulated devices such as IBMVIO
devices or emulated PCI.  These calls allow adding multiple entries
(up to 512) into the TCE table in one call which saves time on
transition between kernel and user space.

This implements the KVM_CAP_PPC_MULTITCE capability. When present,
the kernel will try handling H_PUT_TCE_INDIRECT and H_STUFF_TCE.
If they can not be handled by the kernel, they are passed on to
the user space. The user space still has to have an implementation
for these.

Both HV and PR-syle KVM are supported.

Signed-off-by: Alexey Kardashevskiy 
---
  Documentation/virtual/kvm/api.txt   |  25 ++
  arch/powerpc/include/asm/kvm_ppc.h  |  12 +++
  arch/powerpc/kvm/book3s_64_vio.c| 111 +++-
  arch/powerpc/kvm/book3s_64_vio_hv.c | 145 ++--
  arch/powerpc/kvm/book3s_hv.c|  26 +-
  arch/powerpc/kvm/book3s_hv_rmhandlers.S |   6 +-
  arch/powerpc/kvm/book3s_pr_papr.c   |  35 
  arch/powerpc/kvm/powerpc.c  |   3 +
  8 files changed, 350 insertions(+), 13 deletions(-)

diff --git a/Documentation/virtual/kvm/api.txt 
b/Documentation/virtual/kvm/api.txt
index d86d831..593c62a 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -3019,6 +3019,31 @@ Returns: 0 on success, -1 on error

  Queues an SMI on the thread's vcpu.

+4.97 KVM_CAP_PPC_MULTITCE
+
+Capability: KVM_CAP_PPC_MULTITCE
+Architectures: ppc
+Type: vm
+
+This capability means the kernel is capable of handling hypercalls
+H_PUT_TCE_INDIRECT and H_STUFF_TCE without passing those into the user
+space. This significantly accelerates DMA operations for PPC KVM guests.
+User space should expect that its handlers for these hypercalls
+are not going to be called if user space previously registered LIOBN
+in KVM (via KVM_CREATE_SPAPR_TCE or similar calls).
+
+In order to enable H_PUT_TCE_INDIRECT and H_STUFF_TCE use in the guest,
+user space might have to advertise it for the guest. For example,
+IBM pSeries (sPAPR) guest starts using them if "hcall-multi-tce" is
+present in the "ibm,hypertas-functions" device-tree property.
+
+The hypercalls mentioned above may or may not be processed successfully
+in the kernel based fast path. If they can not be handled by the kernel,
+they will get passed on to user space. So user space still has to have
+an implementation for these despite the in kernel acceleration.
+
+This capability is always enabled.
+
  5. The kvm_run structure
  

diff --git a/arch/powerpc/include/asm/kvm_ppc.h 
b/arch/powerpc/include/asm/kvm_ppc.h
index fcde896..e5b968e 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -166,12 +166,24 @@ 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 *args);
+extern struct kvmppc_spapr_tce_table *kvmppc_find_table(
+   struct kvm_vcpu *vcpu, 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,
unsigned long tce);
+extern long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
+   unsigned long *ua, unsigned long **prmap);
+extern void kvmppc_tce_put(struct kvmppc_spapr_tce_table *tt,
+   unsigned long idx, unsigned long tce);
  extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 unsigned long ioba, unsigned long tce);
+extern long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
+   unsigned long liobn, unsigned long ioba,
+   unsigned long tce_list, unsigned long npages);
+extern long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
+   unsigned long liobn, unsigned long ioba,
+   unsigned long tce_value, unsigned long npages);
  extern long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 unsigned long ioba);
  extern struct page *kvm_alloc_hpt(unsigned long nr_pages);
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index e347856..d3fc732 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -14,6 +14,7 @@
   *
   * Copyright 2010 Paul Mackerras, IBM Corp. 
   * Copyright 2011 David Gibson, IBM Corporation 
+ * Copyright 2013 Alexey Kardashevskiy, IBM Corporation 
   */

  #include 
@@ -37,8 +38,7 @@
  #include 
  #include 
  #include 
-
-#define TCES_PER_PAGE

Re: [PATCH kernel 9/9] KVM: PPC: Add support for multiple-TCE hcalls

2015-12-08 Thread David Gibson 
On Tue, Sep 15, 2015 at 08:49:39PM +1000, Alexey Kardashevskiy wrote:
> This adds real and virtual mode handlers for the H_PUT_TCE_INDIRECT and
> H_STUFF_TCE hypercalls for user space emulated devices such as IBMVIO
> devices or emulated PCI.  These calls allow adding multiple entries
> (up to 512) into the TCE table in one call which saves time on
> transition between kernel and user space.
> 
> This implements the KVM_CAP_PPC_MULTITCE capability. When present,
> the kernel will try handling H_PUT_TCE_INDIRECT and H_STUFF_TCE.
> If they can not be handled by the kernel, they are passed on to
> the user space. The user space still has to have an implementation
> for these.
> 
> Both HV and PR-syle KVM are supported.
> 
> Signed-off-by: Alexey Kardashevskiy 
> ---
>  Documentation/virtual/kvm/api.txt   |  25 ++
>  arch/powerpc/include/asm/kvm_ppc.h  |  12 +++
>  arch/powerpc/kvm/book3s_64_vio.c| 111 +++-
>  arch/powerpc/kvm/book3s_64_vio_hv.c | 145 
> ++--
>  arch/powerpc/kvm/book3s_hv.c|  26 +-
>  arch/powerpc/kvm/book3s_hv_rmhandlers.S |   6 +-
>  arch/powerpc/kvm/book3s_pr_papr.c   |  35 
>  arch/powerpc/kvm/powerpc.c  |   3 +
>  8 files changed, 350 insertions(+), 13 deletions(-)
> 
> diff --git a/Documentation/virtual/kvm/api.txt 
> b/Documentation/virtual/kvm/api.txt
> index d86d831..593c62a 100644
> --- a/Documentation/virtual/kvm/api.txt
> +++ b/Documentation/virtual/kvm/api.txt
> @@ -3019,6 +3019,31 @@ Returns: 0 on success, -1 on error
>  
>  Queues an SMI on the thread's vcpu.
>  
> +4.97 KVM_CAP_PPC_MULTITCE
> +
> +Capability: KVM_CAP_PPC_MULTITCE
> +Architectures: ppc
> +Type: vm
> +
> +This capability means the kernel is capable of handling hypercalls
> +H_PUT_TCE_INDIRECT and H_STUFF_TCE without passing those into the user
> +space. This significantly accelerates DMA operations for PPC KVM guests.
> +User space should expect that its handlers for these hypercalls
> +are not going to be called if user space previously registered LIOBN
> +in KVM (via KVM_CREATE_SPAPR_TCE or similar calls).
> +
> +In order to enable H_PUT_TCE_INDIRECT and H_STUFF_TCE use in the guest,
> +user space might have to advertise it for the guest. For example,
> +IBM pSeries (sPAPR) guest starts using them if "hcall-multi-tce" is
> +present in the "ibm,hypertas-functions" device-tree property.
> +
> +The hypercalls mentioned above may or may not be processed successfully
> +in the kernel based fast path. If they can not be handled by the kernel,
> +they will get passed on to user space. So user space still has to have
> +an implementation for these despite the in kernel acceleration.
> +
> +This capability is always enabled.
> +
>  5. The kvm_run structure
>  
>  
> diff --git a/arch/powerpc/include/asm/kvm_ppc.h 
> b/arch/powerpc/include/asm/kvm_ppc.h
> index fcde896..e5b968e 100644
> --- a/arch/powerpc/include/asm/kvm_ppc.h
> +++ b/arch/powerpc/include/asm/kvm_ppc.h
> @@ -166,12 +166,24 @@ 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 *args);
> +extern struct kvmppc_spapr_tce_table *kvmppc_find_table(
> + struct kvm_vcpu *vcpu, 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,
>   unsigned long tce);
> +extern long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
> + unsigned long *ua, unsigned long **prmap);
> +extern void kvmppc_tce_put(struct kvmppc_spapr_tce_table *tt,
> + unsigned long idx, unsigned long tce);
>  extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>unsigned long ioba, unsigned long tce);
> +extern long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
> + unsigned long liobn, unsigned long ioba,
> + unsigned long tce_list, unsigned long npages);
> +extern long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
> + unsigned long liobn, unsigned long ioba,
> + unsigned long tce_value, unsigned long npages);
>  extern long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>unsigned long ioba);
>  extern struct page *kvm_alloc_hpt(unsigned long nr_pages);
> diff --git a/arch/powerpc/kvm/book3s_64_vio.c 
> b/arch/powerpc/kvm/book3s_64_vio.c
> index e347856..d3fc732 100644
> --- a/arch/powerpc/kvm/book3s_64_vio.c
> +++ b/arch/powerpc/kvm/book3s_64_vio.c
> @@ -14,6 +14,7 @@
>   *
>   * Copyright 2010 Paul Mackerras, IBM Corp. 
>   * Copyright 2011 David Gibson, IBM Corporation 
> + * Copyright 2013 Alexey Kardashevskiy, IBM

Re: [PATCH kernel 9/9] KVM: PPC: Add support for multiple-TCE hcalls

2015-12-08 Thread David Gibson 
On Tue, Sep 15, 2015 at 08:49:39PM +1000, Alexey Kardashevskiy wrote:
> This adds real and virtual mode handlers for the H_PUT_TCE_INDIRECT and
> H_STUFF_TCE hypercalls for user space emulated devices such as IBMVIO
> devices or emulated PCI.  These calls allow adding multiple entries
> (up to 512) into the TCE table in one call which saves time on
> transition between kernel and user space.
> 
> This implements the KVM_CAP_PPC_MULTITCE capability. When present,
> the kernel will try handling H_PUT_TCE_INDIRECT and H_STUFF_TCE.
> If they can not be handled by the kernel, they are passed on to
> the user space. The user space still has to have an implementation
> for these.
> 
> Both HV and PR-syle KVM are supported.
> 
> Signed-off-by: Alexey Kardashevskiy 
> ---
>  Documentation/virtual/kvm/api.txt   |  25 ++
>  arch/powerpc/include/asm/kvm_ppc.h  |  12 +++
>  arch/powerpc/kvm/book3s_64_vio.c| 111 +++-
>  arch/powerpc/kvm/book3s_64_vio_hv.c | 145 
> ++--
>  arch/powerpc/kvm/book3s_hv.c|  26 +-
>  arch/powerpc/kvm/book3s_hv_rmhandlers.S |   6 +-
>  arch/powerpc/kvm/book3s_pr_papr.c   |  35 
>  arch/powerpc/kvm/powerpc.c  |   3 +
>  8 files changed, 350 insertions(+), 13 deletions(-)
> 
> diff --git a/Documentation/virtual/kvm/api.txt 
> b/Documentation/virtual/kvm/api.txt
> index d86d831..593c62a 100644
> --- a/Documentation/virtual/kvm/api.txt
> +++ b/Documentation/virtual/kvm/api.txt
> @@ -3019,6 +3019,31 @@ Returns: 0 on success, -1 on error
>  
>  Queues an SMI on the thread's vcpu.
>  
> +4.97 KVM_CAP_PPC_MULTITCE
> +
> +Capability: KVM_CAP_PPC_MULTITCE
> +Architectures: ppc
> +Type: vm
> +
> +This capability means the kernel is capable of handling hypercalls
> +H_PUT_TCE_INDIRECT and H_STUFF_TCE without passing those into the user
> +space. This significantly accelerates DMA operations for PPC KVM guests.
> +User space should expect that its handlers for these hypercalls
> +are not going to be called if user space previously registered LIOBN
> +in KVM (via KVM_CREATE_SPAPR_TCE or similar calls).
> +
> +In order to enable H_PUT_TCE_INDIRECT and H_STUFF_TCE use in the guest,
> +user space might have to advertise it for the guest. For example,
> +IBM pSeries (sPAPR) guest starts using them if "hcall-multi-tce" is
> +present in the "ibm,hypertas-functions" device-tree property.
> +
> +The hypercalls mentioned above may or may not be processed successfully
> +in the kernel based fast path. If they can not be handled by the kernel,
> +they will get passed on to user space. So user space still has to have
> +an implementation for these despite the in kernel acceleration.
> +
> +This capability is always enabled.
> +
>  5. The kvm_run structure
>  
>  
> diff --git a/arch/powerpc/include/asm/kvm_ppc.h 
> b/arch/powerpc/include/asm/kvm_ppc.h
> index fcde896..e5b968e 100644
> --- a/arch/powerpc/include/asm/kvm_ppc.h
> +++ b/arch/powerpc/include/asm/kvm_ppc.h
> @@ -166,12 +166,24 @@ 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 *args);
> +extern struct kvmppc_spapr_tce_table *kvmppc_find_table(
> + struct kvm_vcpu *vcpu, 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,
>   unsigned long tce);
> +extern long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
> + unsigned long *ua, unsigned long **prmap);
> +extern void kvmppc_tce_put(struct kvmppc_spapr_tce_table *tt,
> + unsigned long idx, unsigned long tce);
>  extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>unsigned long ioba, unsigned long tce);
> +extern long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
> + unsigned long liobn, unsigned long ioba,
> + unsigned long tce_list, unsigned long npages);
> +extern long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
> + unsigned long liobn, unsigned long ioba,
> + unsigned long tce_value, unsigned long npages);
>  extern long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>unsigned long ioba);
>  extern struct page *kvm_alloc_hpt(unsigned long nr_pages);
> diff --git a/arch/powerpc/kvm/book3s_64_vio.c 
> b/arch/powerpc/kvm/book3s_64_vio.c
> index e347856..d3fc732 100644
> --- a/arch/powerpc/kvm/book3s_64_vio.c
> +++ b/arch/powerpc/kvm/book3s_64_vio.c
> @@ -14,6 +14,7 @@
>   *
>   * Copyright 2010 Paul Mackerras, IBM Corp. 
>   * Copyright 2011 David Gibson, IBM Corporation 
> + * Copyright 2013 Alexey Kardashevskiy, IBM

[PATCH kernel 9/9] KVM: PPC: Add support for multiple-TCE hcalls

2015-09-15 Thread Alexey Kardashevskiy 
This adds real and virtual mode handlers for the H_PUT_TCE_INDIRECT and
H_STUFF_TCE hypercalls for user space emulated devices such as IBMVIO
devices or emulated PCI.  These calls allow adding multiple entries
(up to 512) into the TCE table in one call which saves time on
transition between kernel and user space.

This implements the KVM_CAP_PPC_MULTITCE capability. When present,
the kernel will try handling H_PUT_TCE_INDIRECT and H_STUFF_TCE.
If they can not be handled by the kernel, they are passed on to
the user space. The user space still has to have an implementation
for these.

Both HV and PR-syle KVM are supported.

Signed-off-by: Alexey Kardashevskiy 
---
 Documentation/virtual/kvm/api.txt   |  25 ++
 arch/powerpc/include/asm/kvm_ppc.h  |  12 +++
 arch/powerpc/kvm/book3s_64_vio.c| 111 +++-
 arch/powerpc/kvm/book3s_64_vio_hv.c | 145 ++--
 arch/powerpc/kvm/book3s_hv.c|  26 +-
 arch/powerpc/kvm/book3s_hv_rmhandlers.S |   6 +-
 arch/powerpc/kvm/book3s_pr_papr.c   |  35 
 arch/powerpc/kvm/powerpc.c  |   3 +
 8 files changed, 350 insertions(+), 13 deletions(-)

diff --git a/Documentation/virtual/kvm/api.txt 
b/Documentation/virtual/kvm/api.txt
index d86d831..593c62a 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -3019,6 +3019,31 @@ Returns: 0 on success, -1 on error
 
 Queues an SMI on the thread's vcpu.
 
+4.97 KVM_CAP_PPC_MULTITCE
+
+Capability: KVM_CAP_PPC_MULTITCE
+Architectures: ppc
+Type: vm
+
+This capability means the kernel is capable of handling hypercalls
+H_PUT_TCE_INDIRECT and H_STUFF_TCE without passing those into the user
+space. This significantly accelerates DMA operations for PPC KVM guests.
+User space should expect that its handlers for these hypercalls
+are not going to be called if user space previously registered LIOBN
+in KVM (via KVM_CREATE_SPAPR_TCE or similar calls).
+
+In order to enable H_PUT_TCE_INDIRECT and H_STUFF_TCE use in the guest,
+user space might have to advertise it for the guest. For example,
+IBM pSeries (sPAPR) guest starts using them if "hcall-multi-tce" is
+present in the "ibm,hypertas-functions" device-tree property.
+
+The hypercalls mentioned above may or may not be processed successfully
+in the kernel based fast path. If they can not be handled by the kernel,
+they will get passed on to user space. So user space still has to have
+an implementation for these despite the in kernel acceleration.
+
+This capability is always enabled.
+
 5. The kvm_run structure
 
 
diff --git a/arch/powerpc/include/asm/kvm_ppc.h 
b/arch/powerpc/include/asm/kvm_ppc.h
index fcde896..e5b968e 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -166,12 +166,24 @@ 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 *args);
+extern struct kvmppc_spapr_tce_table *kvmppc_find_table(
+   struct kvm_vcpu *vcpu, 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,
unsigned long tce);
+extern long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
+   unsigned long *ua, unsigned long **prmap);
+extern void kvmppc_tce_put(struct kvmppc_spapr_tce_table *tt,
+   unsigned long idx, unsigned long tce);
 extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 unsigned long ioba, unsigned long tce);
+extern long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
+   unsigned long liobn, unsigned long ioba,
+   unsigned long tce_list, unsigned long npages);
+extern long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
+   unsigned long liobn, unsigned long ioba,
+   unsigned long tce_value, unsigned long npages);
 extern long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 unsigned long ioba);
 extern struct page *kvm_alloc_hpt(unsigned long nr_pages);
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index e347856..d3fc732 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -14,6 +14,7 @@
  *
  * Copyright 2010 Paul Mackerras, IBM Corp. 
  * Copyright 2011 David Gibson, IBM Corporation 
+ * Copyright 2013 Alexey Kardashevskiy, IBM Corporation 
  */
 
 #include 
@@ -37,8 +38,7 @@
 #include 
 #include 
 #include 
-
-#define TCES_PER_PAGE  (PAGE_SIZE / sizeof(u64))
+#include 
 
 static long kvmppc_stt_npages(unsigned long window_size)
 {
@@ -200,3 +200,110 @@ fail:
}

[PATCH kernel 9/9] KVM: PPC: Add support for multiple-TCE hcalls

2015-09-15 Thread Alexey Kardashevskiy 
This adds real and virtual mode handlers for the H_PUT_TCE_INDIRECT and
H_STUFF_TCE hypercalls for user space emulated devices such as IBMVIO
devices or emulated PCI.  These calls allow adding multiple entries
(up to 512) into the TCE table in one call which saves time on
transition between kernel and user space.

This implements the KVM_CAP_PPC_MULTITCE capability. When present,
the kernel will try handling H_PUT_TCE_INDIRECT and H_STUFF_TCE.
If they can not be handled by the kernel, they are passed on to
the user space. The user space still has to have an implementation
for these.

Both HV and PR-syle KVM are supported.

Signed-off-by: Alexey Kardashevskiy 
---
 Documentation/virtual/kvm/api.txt   |  25 ++
 arch/powerpc/include/asm/kvm_ppc.h  |  12 +++
 arch/powerpc/kvm/book3s_64_vio.c| 111 +++-
 arch/powerpc/kvm/book3s_64_vio_hv.c | 145 ++--
 arch/powerpc/kvm/book3s_hv.c|  26 +-
 arch/powerpc/kvm/book3s_hv_rmhandlers.S |   6 +-
 arch/powerpc/kvm/book3s_pr_papr.c   |  35 
 arch/powerpc/kvm/powerpc.c  |   3 +
 8 files changed, 350 insertions(+), 13 deletions(-)

diff --git a/Documentation/virtual/kvm/api.txt 
b/Documentation/virtual/kvm/api.txt
index d86d831..593c62a 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -3019,6 +3019,31 @@ Returns: 0 on success, -1 on error
 
 Queues an SMI on the thread's vcpu.
 
+4.97 KVM_CAP_PPC_MULTITCE
+
+Capability: KVM_CAP_PPC_MULTITCE
+Architectures: ppc
+Type: vm
+
+This capability means the kernel is capable of handling hypercalls
+H_PUT_TCE_INDIRECT and H_STUFF_TCE without passing those into the user
+space. This significantly accelerates DMA operations for PPC KVM guests.
+User space should expect that its handlers for these hypercalls
+are not going to be called if user space previously registered LIOBN
+in KVM (via KVM_CREATE_SPAPR_TCE or similar calls).
+
+In order to enable H_PUT_TCE_INDIRECT and H_STUFF_TCE use in the guest,
+user space might have to advertise it for the guest. For example,
+IBM pSeries (sPAPR) guest starts using them if "hcall-multi-tce" is
+present in the "ibm,hypertas-functions" device-tree property.
+
+The hypercalls mentioned above may or may not be processed successfully
+in the kernel based fast path. If they can not be handled by the kernel,
+they will get passed on to user space. So user space still has to have
+an implementation for these despite the in kernel acceleration.
+
+This capability is always enabled.
+
 5. The kvm_run structure
 
 
diff --git a/arch/powerpc/include/asm/kvm_ppc.h 
b/arch/powerpc/include/asm/kvm_ppc.h
index fcde896..e5b968e 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -166,12 +166,24 @@ 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 *args);
+extern struct kvmppc_spapr_tce_table *kvmppc_find_table(
+   struct kvm_vcpu *vcpu, 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,
unsigned long tce);
+extern long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
+   unsigned long *ua, unsigned long **prmap);
+extern void kvmppc_tce_put(struct kvmppc_spapr_tce_table *tt,
+   unsigned long idx, unsigned long tce);
 extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 unsigned long ioba, unsigned long tce);
+extern long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
+   unsigned long liobn, unsigned long ioba,
+   unsigned long tce_list, unsigned long npages);
+extern long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
+   unsigned long liobn, unsigned long ioba,
+   unsigned long tce_value, unsigned long npages);
 extern long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 unsigned long ioba);
 extern struct page *kvm_alloc_hpt(unsigned long nr_pages);
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index e347856..d3fc732 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -14,6 +14,7 @@
  *
  * Copyright 2010 Paul Mackerras, IBM Corp. 
  * Copyright 2011 David Gibson, IBM Corporation 
+ * Copyright 2013 Alexey Kardashevskiy, IBM Corporation 
  */
 
 #include 
@@ -37,8 +38,7 @@
 #include 
 #include 
 #include 
-
-#define TCES_PER_PAGE  (PAGE_SIZE / sizeof(u64))
+#include 
 
 static long kvmppc_stt_npages(unsigned long window_size)
 {
@@ -200,3 +200,110 @@ fail:
}