Hi Pablo,
On 1/10/2018 6:17 PM, De Lara Guarch, Pablo wrote:
Hi Akhil,
-----Original Message-----
From: Akhil Goyal [mailto:akhil.go...@nxp.com]
Sent: Thursday, December 14, 2017 6:52 AM
To: dev@dpdk.org
Cc: De Lara Guarch, Pablo <pablo.de.lara.gua...@intel.com>;
hemant.agra...@nxp.com; Gonzalez Monroy, Sergio
<sergio.gonzalez.mon...@intel.com>; Nicolau, Radu
<radu.nico...@intel.com>; Akhil Goyal <akhil.go...@nxp.com>
Subject: [PATCH] examples/ipsec-secgw: add cryptodev mask option
Previously, ipsec-secgw application did not give user the flexibility to decide
which crypto device(s) will be used.
In this patch, a new cryptodev_mask option is added to the application.
Same as portmask, the cryptodev_mask avails the user to mask out the
unwanted crypto devices in the system.
This patch is similar to the support added in l2fwd-crypto
(d2797f51cc63: examples/l2fwd-crypto: add cryptodev mask option)
Signed-off-by: Akhil Goyal <akhil.go...@nxp.com>
---
...
Not sure if you should change the order of the crypto devices that was set
previously
(starting from the end and not from the beginning). Shouldn't we keep it as it
was?
Actually as per the current code base there is no fix order of the
devices to be available. In bus scan, all(pci,fslmc,vdev) have same
priority(110), which means whatever is first recognized/linked will come
first.
So the assumption that last cdev_id is HW doesn't seem to be correct.
I just wanted to make the code similar to l2fwd-crypto and the behavior
of cryptodev_mask similar to what l2fwd-crypto understands.
Please let me know if my understanding is not correct.
idx = 0;
- /* Start from last cdev id to give HW priority */
- for (cdev_id = rte_cryptodev_count() - 1; cdev_id >= 0; cdev_id--) {
+ for (cdev_id = 0; cdev_id < rte_cryptodev_count(); cdev_id++) {
struct rte_cryptodev_info cdev_info;
+ if (check_cryptodev_mask((uint8_t)cdev_id))
+ continue;
+
rte_cryptodev_info_get(cdev_id, &cdev_info);
if (nb_lcore_params > cdev_info.max_nb_queue_pairs)
--
2.9.3
For the rest, I don't have other objections, so apart from the comment above:
Acked-by: Pablo de Lara <pablo.de.lara.gua...@intel.com>
Thanks,
Akhil
