[dpdk-dev,v2,05/11] eal/linux: add intr api to report multi-vector capability
Commit Message
VFIO allows multiple MSI-X vector, others doesn't, but maybe will allow it in the future.
Device drivers need to be aware of the capability.
It's better to avoid condition check on interrupt type(VFIO) everywhere, instead
a capability api is more flexible for the condition change.
Signed-off-by: Cunming Liang <cunming.liang@intel.com>
---
lib/librte_eal/linuxapp/eal/eal_interrupts.c | 9 +++++++++
lib/librte_eal/linuxapp/eal/include/exec-env/rte_interrupts.h | 10 ++++++++++
lib/librte_eal/linuxapp/eal/rte_eal_version.map | 7 +++++++
3 files changed, 26 insertions(+)
\ No newline at end of file
Comments
> -----Original Message-----
> From: Liang, Cunming
> Sent: Friday, October 30, 2015 1:28 PM
> To: dev@dpdk.org
> Cc: Zhang, Helin; He, Shaopeng; Wu, Jingjing; Liang, Cunming
> Subject: [PATCH v2 05/11] eal/linux: add intr api to report multi-vector
> capability
>
> VFIO allows multiple MSI-X vector, others doesn't, but maybe will allow it in
> the future.
> Device drivers need to be aware of the capability.
> It's better to avoid condition check on interrupt type(VFIO) everywhere,
> instead
> a capability api is more flexible for the condition change.
>
> Signed-off-by: Cunming Liang <cunming.liang@intel.com>
Acked-by: Shaopeng He <shaopeng.he@intel.com>
On Fri, Oct 30, 2015 at 6:27 AM, Cunming Liang <cunming.liang@intel.com>
wrote:
> VFIO allows multiple MSI-X vector, others doesn't, but maybe will allow it
> in the future.
> Device drivers need to be aware of the capability.
> It's better to avoid condition check on interrupt type(VFIO) everywhere,
> instead
> a capability api is more flexible for the condition change.
>
> Signed-off-by: Cunming Liang <cunming.liang@intel.com>
> ---
> lib/librte_eal/linuxapp/eal/eal_interrupts.c | 9
> +++++++++
> lib/librte_eal/linuxapp/eal/include/exec-env/rte_interrupts.h | 10
> ++++++++++
> lib/librte_eal/linuxapp/eal/rte_eal_version.map | 7 +++++++
> 3 files changed, 26 insertions(+)
>
>
BSD has wrappers for the rest of this api, please add one for this too.
Hi David,
On 11/2/2015 11:59 PM, David Marchand wrote:
> On Fri, Oct 30, 2015 at 6:27 AM, Cunming Liang <cunming.liang@intel.com>
> wrote:
>
>> VFIO allows multiple MSI-X vector, others doesn't, but maybe will allow it
>> in the future.
>> Device drivers need to be aware of the capability.
>> It's better to avoid condition check on interrupt type(VFIO) everywhere,
>> instead
>> a capability api is more flexible for the condition change.
>>
>> Signed-off-by: Cunming Liang <cunming.liang@intel.com>
>> ---
>> lib/librte_eal/linuxapp/eal/eal_interrupts.c | 9
>> +++++++++
>> lib/librte_eal/linuxapp/eal/include/exec-env/rte_interrupts.h | 10
>> ++++++++++
>> lib/librte_eal/linuxapp/eal/rte_eal_version.map | 7 +++++++
>> 3 files changed, 26 insertions(+)
>>
>>
> BSD has wrappers for the rest of this api, please add one for this too.
Yes, you're right. Thanks.
>
@@ -1196,3 +1196,12 @@ rte_intr_allow_others(struct rte_intr_handle *intr_handle)
else
return !!(intr_handle->max_intr - intr_handle->nb_efd);
}
+
+int
+rte_intr_cap_multiple(struct rte_intr_handle *intr_handle)
+{
+ if (intr_handle->type == RTE_INTR_HANDLE_VFIO_MSIX)
+ return 1;
+
+ return 0;
+}
@@ -215,4 +215,14 @@ rte_intr_dp_is_en(struct rte_intr_handle *intr_handle);
int
rte_intr_allow_others(struct rte_intr_handle *intr_handle);
+/**
+ * The multiple interrupt vector capability of interrupt handle instance.
+ * It returns zero if no multiple interrupt vector support.
+ *
+ * @param intr_handle
+ * Pointer to the interrupt handle.
+ */
+int
+rte_intr_cap_multiple(struct rte_intr_handle *intr_handle);
+
#endif /* _RTE_LINUXAPP_INTERRUPTS_H_ */
@@ -128,3 +128,10 @@ DPDK_2.1 {
rte_memzone_free;
} DPDK_2.0;
+
+DPDK_2.2 {
+ global:
+
+ rte_intr_cap_multiple;
+
+} DPDK_2.1;