Patchwork PPC: KVM: Introduce hypervisor call H_GET_TCE

login
register
mail settings
Submitter Laurent Dufour
Date Feb. 21, 2014, 3:31 p.m.
Message ID <20140221153110.8190.6271.stgit@nimbus>
Download mbox | patch
Permalink /patch/322925/
State New
Headers show

Comments

Laurent Dufour - Feb. 21, 2014, 3:31 p.m.
This fix introduces the H_GET_TCE hypervisor call which is basically the
reverse of H_PUT_TCE, as defined in the Power Architecture Platform
Requirements (PAPR).

The hcall H_GET_TCE is required by the kdump kernel which is calling it to
retrieve the TCE set up by the panicing kernel.

Signed-off-by: Laurent Dufour <ldufour@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/kvm_ppc.h      |    2 ++
 arch/powerpc/kvm/book3s_64_vio_hv.c     |   28 ++++++++++++++++++++++++++++
 arch/powerpc/kvm/book3s_hv_rmhandlers.S |    2 +-
 3 files changed, 31 insertions(+), 1 deletion(-)


--
To unsubscribe from this list: send the line "unsubscribe kvm-ppc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Alexander Graf - Feb. 21, 2014, 3:57 p.m.
On 21.02.2014, at 16:31, Laurent Dufour <ldufour@linux.vnet.ibm.com> wrote:

> This fix introduces the H_GET_TCE hypervisor call which is basically the
> reverse of H_PUT_TCE, as defined in the Power Architecture Platform
> Requirements (PAPR).
> 
> The hcall H_GET_TCE is required by the kdump kernel which is calling it to
> retrieve the TCE set up by the panicing kernel.
> 
> Signed-off-by: Laurent Dufour <ldufour@linux.vnet.ibm.com>

Thanks, applied to kvm-ppc-queue. Btw, why exactly are we using struct page pointers and alloc_page rather than __get_free_page() and simple page start pointers?


Alex

--
To unsubscribe from this list: send the line "unsubscribe kvm-ppc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Benjamin Herrenschmidt - Feb. 21, 2014, 7:23 p.m.
On Fri, 2014-02-21 at 16:31 +0100, Laurent Dufour wrote:
> This fix introduces the H_GET_TCE hypervisor call which is basically the
> reverse of H_PUT_TCE, as defined in the Power Architecture Platform
> Requirements (PAPR).
> 
> The hcall H_GET_TCE is required by the kdump kernel which is calling it to
> retrieve the TCE set up by the panicing kernel.

Alexey, will that work for VFIO ? Or are those patches *still* not
upstream ?

> Signed-off-by: Laurent Dufour <ldufour@linux.vnet.ibm.com>
> ---
>  arch/powerpc/include/asm/kvm_ppc.h      |    2 ++
>  arch/powerpc/kvm/book3s_64_vio_hv.c     |   28 ++++++++++++++++++++++++++++
>  arch/powerpc/kvm/book3s_hv_rmhandlers.S |    2 +-
>  3 files changed, 31 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
> index fcd53f0..4096f16 100644
> --- a/arch/powerpc/include/asm/kvm_ppc.h
> +++ b/arch/powerpc/include/asm/kvm_ppc.h
> @@ -129,6 +129,8 @@ extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
>  				struct kvm_create_spapr_tce *args);
>  extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>  			     unsigned long ioba, unsigned long tce);
> +extern long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
> +			     unsigned long ioba);
>  extern struct kvm_rma_info *kvm_alloc_rma(void);
>  extern void kvm_release_rma(struct kvm_rma_info *ri);
>  extern struct page *kvm_alloc_hpt(unsigned long nr_pages);
> diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
> index 2c25f54..89e96b3 100644
> --- a/arch/powerpc/kvm/book3s_64_vio_hv.c
> +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
> @@ -75,3 +75,31 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>  	return H_TOO_HARD;
>  }
>  EXPORT_SYMBOL_GPL(kvmppc_h_put_tce);
> +
> +long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
> +		      unsigned long ioba)
> +{
> +	struct kvm *kvm = vcpu->kvm;
> +	struct kvmppc_spapr_tce_table *stt;
> +
> +	list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
> +		if (stt->liobn == liobn) {
> +			unsigned long idx = ioba >> SPAPR_TCE_SHIFT;
> +			struct page *page;
> +			u64 *tbl;
> +
> +			if (ioba >= stt->window_size)
> +				return H_PARAMETER;
> +
> +			page = stt->pages[idx / TCES_PER_PAGE];
> +			tbl = (u64 *)page_address(page);
> +
> +			vcpu->arch.gpr[4] = tbl[idx % TCES_PER_PAGE];
> +			return H_SUCCESS;
> +		}
> +	}
> +
> +	/* Didn't find the liobn, punt it to userspace */
> +	return H_TOO_HARD;
> +}
> +EXPORT_SYMBOL_GPL(kvmppc_h_get_tce);
> diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
> index e66d4ec..7d4fe2a 100644
> --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
> +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
> @@ -1758,7 +1758,7 @@ hcall_real_table:
>  	.long	0		/* 0x10 - H_CLEAR_MOD */
>  	.long	0		/* 0x14 - H_CLEAR_REF */
>  	.long	.kvmppc_h_protect - hcall_real_table
> -	.long	0		/* 0x1c - H_GET_TCE */
> +	.long	.kvmppc_h_get_tce - hcall_real_table
>  	.long	.kvmppc_h_put_tce - hcall_real_table
>  	.long	0		/* 0x24 - H_SET_SPRG0 */
>  	.long	.kvmppc_h_set_dabr - hcall_real_table


--
To unsubscribe from this list: send the line "unsubscribe kvm-ppc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Alexey Kardashevskiy - Feb. 22, 2014, 12:28 a.m.
On 02/22/2014 06:23 AM, Benjamin Herrenschmidt wrote:
> On Fri, 2014-02-21 at 16:31 +0100, Laurent Dufour wrote:
>> This fix introduces the H_GET_TCE hypervisor call which is basically the
>> reverse of H_PUT_TCE, as defined in the Power Architecture Platform
>> Requirements (PAPR).
>>
>> The hcall H_GET_TCE is required by the kdump kernel which is calling it to
>> retrieve the TCE set up by the panicing kernel.
> 
> Alexey, will that work for VFIO ?

Yes.

> Or are those patches *still* not
> upstream ?

Yes.


> 
>> Signed-off-by: Laurent Dufour <ldufour@linux.vnet.ibm.com>
>> ---
>>  arch/powerpc/include/asm/kvm_ppc.h      |    2 ++
>>  arch/powerpc/kvm/book3s_64_vio_hv.c     |   28 ++++++++++++++++++++++++++++
>>  arch/powerpc/kvm/book3s_hv_rmhandlers.S |    2 +-
>>  3 files changed, 31 insertions(+), 1 deletion(-)
>>
>> diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
>> index fcd53f0..4096f16 100644
>> --- a/arch/powerpc/include/asm/kvm_ppc.h
>> +++ b/arch/powerpc/include/asm/kvm_ppc.h
>> @@ -129,6 +129,8 @@ extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
>>  				struct kvm_create_spapr_tce *args);
>>  extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>>  			     unsigned long ioba, unsigned long tce);
>> +extern long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>> +			     unsigned long ioba);
>>  extern struct kvm_rma_info *kvm_alloc_rma(void);
>>  extern void kvm_release_rma(struct kvm_rma_info *ri);
>>  extern struct page *kvm_alloc_hpt(unsigned long nr_pages);
>> diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
>> index 2c25f54..89e96b3 100644
>> --- a/arch/powerpc/kvm/book3s_64_vio_hv.c
>> +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
>> @@ -75,3 +75,31 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>>  	return H_TOO_HARD;
>>  }
>>  EXPORT_SYMBOL_GPL(kvmppc_h_put_tce);
>> +
>> +long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>> +		      unsigned long ioba)
>> +{
>> +	struct kvm *kvm = vcpu->kvm;
>> +	struct kvmppc_spapr_tce_table *stt;
>> +
>> +	list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
>> +		if (stt->liobn == liobn) {
>> +			unsigned long idx = ioba >> SPAPR_TCE_SHIFT;
>> +			struct page *page;
>> +			u64 *tbl;
>> +
>> +			if (ioba >= stt->window_size)
>> +				return H_PARAMETER;
>> +
>> +			page = stt->pages[idx / TCES_PER_PAGE];
>> +			tbl = (u64 *)page_address(page);
>> +
>> +			vcpu->arch.gpr[4] = tbl[idx % TCES_PER_PAGE];
>> +			return H_SUCCESS;
>> +		}
>> +	}
>> +
>> +	/* Didn't find the liobn, punt it to userspace */
>> +	return H_TOO_HARD;
>> +}
>> +EXPORT_SYMBOL_GPL(kvmppc_h_get_tce);
>> diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
>> index e66d4ec..7d4fe2a 100644
>> --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
>> +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
>> @@ -1758,7 +1758,7 @@ hcall_real_table:
>>  	.long	0		/* 0x10 - H_CLEAR_MOD */
>>  	.long	0		/* 0x14 - H_CLEAR_REF */
>>  	.long	.kvmppc_h_protect - hcall_real_table
>> -	.long	0		/* 0x1c - H_GET_TCE */
>> +	.long	.kvmppc_h_get_tce - hcall_real_table
>>  	.long	.kvmppc_h_put_tce - hcall_real_table
>>  	.long	0		/* 0x24 - H_SET_SPRG0 */
>>  	.long	.kvmppc_h_set_dabr - hcall_real_table
> 
> 
> _______________________________________________
> Linuxppc-dev mailing list
> Linuxppc-dev@lists.ozlabs.org
> https://lists.ozlabs.org/listinfo/linuxppc-dev
>
Alexey Kardashevskiy - Feb. 22, 2014, 12:48 a.m.
On 02/22/2014 11:28 AM, Alexey Kardashevskiy wrote:
> On 02/22/2014 06:23 AM, Benjamin Herrenschmidt wrote:
>> On Fri, 2014-02-21 at 16:31 +0100, Laurent Dufour wrote:
>>> This fix introduces the H_GET_TCE hypervisor call which is basically the
>>> reverse of H_PUT_TCE, as defined in the Power Architecture Platform
>>> Requirements (PAPR).
>>>
>>> The hcall H_GET_TCE is required by the kdump kernel which is calling it to
>>> retrieve the TCE set up by the panicing kernel.
>>
>> Alexey, will that work for VFIO ?
> 
> Yes.


Oh! My bad, this is _G_et. Not, this won't support VFIO but this should not
break the current "slow" VFIO support in upstream.


>> Or are those patches *still* not
>> upstream ?
> 
> Yes.

This part is still true. I cannot get Alex Graf attention even on much
simpler things for several months.



> 
> 
>>
>>> Signed-off-by: Laurent Dufour <ldufour@linux.vnet.ibm.com>
>>> ---
>>>  arch/powerpc/include/asm/kvm_ppc.h      |    2 ++
>>>  arch/powerpc/kvm/book3s_64_vio_hv.c     |   28 ++++++++++++++++++++++++++++
>>>  arch/powerpc/kvm/book3s_hv_rmhandlers.S |    2 +-
>>>  3 files changed, 31 insertions(+), 1 deletion(-)
>>>
>>> diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
>>> index fcd53f0..4096f16 100644
>>> --- a/arch/powerpc/include/asm/kvm_ppc.h
>>> +++ b/arch/powerpc/include/asm/kvm_ppc.h
>>> @@ -129,6 +129,8 @@ extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
>>>  				struct kvm_create_spapr_tce *args);
>>>  extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>>>  			     unsigned long ioba, unsigned long tce);
>>> +extern long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>>> +			     unsigned long ioba);
>>>  extern struct kvm_rma_info *kvm_alloc_rma(void);
>>>  extern void kvm_release_rma(struct kvm_rma_info *ri);
>>>  extern struct page *kvm_alloc_hpt(unsigned long nr_pages);
>>> diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
>>> index 2c25f54..89e96b3 100644
>>> --- a/arch/powerpc/kvm/book3s_64_vio_hv.c
>>> +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
>>> @@ -75,3 +75,31 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>>>  	return H_TOO_HARD;
>>>  }
>>>  EXPORT_SYMBOL_GPL(kvmppc_h_put_tce);
>>> +
>>> +long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
>>> +		      unsigned long ioba)
>>> +{
>>> +	struct kvm *kvm = vcpu->kvm;
>>> +	struct kvmppc_spapr_tce_table *stt;
>>> +
>>> +	list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
>>> +		if (stt->liobn == liobn) {
>>> +			unsigned long idx = ioba >> SPAPR_TCE_SHIFT;
>>> +			struct page *page;
>>> +			u64 *tbl;
>>> +
>>> +			if (ioba >= stt->window_size)
>>> +				return H_PARAMETER;
>>> +
>>> +			page = stt->pages[idx / TCES_PER_PAGE];
>>> +			tbl = (u64 *)page_address(page);
>>> +
>>> +			vcpu->arch.gpr[4] = tbl[idx % TCES_PER_PAGE];
>>> +			return H_SUCCESS;
>>> +		}
>>> +	}
>>> +
>>> +	/* Didn't find the liobn, punt it to userspace */
>>> +	return H_TOO_HARD;
>>> +}
>>> +EXPORT_SYMBOL_GPL(kvmppc_h_get_tce);
>>> diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
>>> index e66d4ec..7d4fe2a 100644
>>> --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
>>> +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
>>> @@ -1758,7 +1758,7 @@ hcall_real_table:
>>>  	.long	0		/* 0x10 - H_CLEAR_MOD */
>>>  	.long	0		/* 0x14 - H_CLEAR_REF */
>>>  	.long	.kvmppc_h_protect - hcall_real_table
>>> -	.long	0		/* 0x1c - H_GET_TCE */
>>> +	.long	.kvmppc_h_get_tce - hcall_real_table
>>>  	.long	.kvmppc_h_put_tce - hcall_real_table
>>>  	.long	0		/* 0x24 - H_SET_SPRG0 */
>>>  	.long	.kvmppc_h_set_dabr - hcall_real_table
>>
>>
>> _______________________________________________
>> Linuxppc-dev mailing list
>> Linuxppc-dev@lists.ozlabs.org
>> https://lists.ozlabs.org/listinfo/linuxppc-dev
>>
> 
>
Laurent Dufour - Feb. 25, 2014, 4 p.m.
On 21/02/2014 16:57, Alexander Graf wrote:
> 
> On 21.02.2014, at 16:31, Laurent Dufour <ldufour@linux.vnet.ibm.com> wrote:
> 
>> This fix introduces the H_GET_TCE hypervisor call which is basically the
>> reverse of H_PUT_TCE, as defined in the Power Architecture Platform
>> Requirements (PAPR).
>>
>> The hcall H_GET_TCE is required by the kdump kernel which is calling it to
>> retrieve the TCE set up by the panicing kernel.
>>
>> Signed-off-by: Laurent Dufour <ldufour@linux.vnet.ibm.com>
> 
> Thanks, applied to kvm-ppc-queue. Btw, why exactly are we using struct page pointers and alloc_page rather than __get_free_page() and simple page start pointers?

FWIW, I'm not so familiar with that part of code, it seems that this is
due to the page fault handler (kvm_spapr_tce_fault) which is part of the
mmap file operation handlers associated to the fd returned by
kvm_vm_ioctl_create_spapr_tce. Underlying vma's operation requires the
page fault handler to return a struct page value in the vm_fault structure.

Cheers,
Laurent.

--
To unsubscribe from this list: send the line "unsubscribe kvm-ppc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index fcd53f0..4096f16 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -129,6 +129,8 @@  extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 				struct kvm_create_spapr_tce *args);
 extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 			     unsigned long ioba, unsigned long tce);
+extern long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
+			     unsigned long ioba);
 extern struct kvm_rma_info *kvm_alloc_rma(void);
 extern void kvm_release_rma(struct kvm_rma_info *ri);
 extern struct page *kvm_alloc_hpt(unsigned long nr_pages);
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 2c25f54..89e96b3 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -75,3 +75,31 @@  long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	return H_TOO_HARD;
 }
 EXPORT_SYMBOL_GPL(kvmppc_h_put_tce);
+
+long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
+		      unsigned long ioba)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvmppc_spapr_tce_table *stt;
+
+	list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
+		if (stt->liobn == liobn) {
+			unsigned long idx = ioba >> SPAPR_TCE_SHIFT;
+			struct page *page;
+			u64 *tbl;
+
+			if (ioba >= stt->window_size)
+				return H_PARAMETER;
+
+			page = stt->pages[idx / TCES_PER_PAGE];
+			tbl = (u64 *)page_address(page);
+
+			vcpu->arch.gpr[4] = tbl[idx % TCES_PER_PAGE];
+			return H_SUCCESS;
+		}
+	}
+
+	/* Didn't find the liobn, punt it to userspace */
+	return H_TOO_HARD;
+}
+EXPORT_SYMBOL_GPL(kvmppc_h_get_tce);
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index e66d4ec..7d4fe2a 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1758,7 +1758,7 @@  hcall_real_table:
 	.long	0		/* 0x10 - H_CLEAR_MOD */
 	.long	0		/* 0x14 - H_CLEAR_REF */
 	.long	.kvmppc_h_protect - hcall_real_table
-	.long	0		/* 0x1c - H_GET_TCE */
+	.long	.kvmppc_h_get_tce - hcall_real_table
 	.long	.kvmppc_h_put_tce - hcall_real_table
 	.long	0		/* 0x24 - H_SET_SPRG0 */
 	.long	.kvmppc_h_set_dabr - hcall_real_table