From: "Xie, Huawei" <huawei.xie@intel.com>
To: David Marchand <david.marchand@6wind.com>, "dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] [PATCH RFC 2/3] eal: don't call rte_eal_iopl_init unconditionnally
Date: Wed, 27 Aug 2014 17:26:59 +0000 [thread overview]
Message-ID: <C37D651A908B024F974696C65296B57B0F27E532@SHSMSX101.ccr.corp.intel.com> (raw)
In-Reply-To: <1409062300-17004-3-git-send-email-david.marchand@6wind.com>
Acked-by: Huawei Xie <huawei.xie@intel.com>
> -----Original Message-----
> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of David Marchand
> Sent: Tuesday, August 26, 2014 10:12 PM
> To: dev@dpdk.org
> Subject: [dpdk-dev] [PATCH RFC 2/3] eal: don't call rte_eal_iopl_init
> unconditionnally
>
> There is no need for ioport access for applications that won't use virtio pmds.
> Make rte_eal_iopl_init() non-static so that it is called from pmds that need it.
>
> Signed-off-by: David Marchand <david.marchand@6wind.com>
> ---
> lib/librte_eal/bsdapp/eal/eal.c | 5 +----
> lib/librte_eal/common/include/rte_eal.h | 14 +++++++++++---
> lib/librte_eal/linuxapp/eal/eal.c | 11 ++++-------
> lib/librte_pmd_virtio/virtio_ethdev.c | 15 ++++++++-------
> 4 files changed, 24 insertions(+), 21 deletions(-)
>
> diff --git a/lib/librte_eal/bsdapp/eal/eal.c b/lib/librte_eal/bsdapp/eal/eal.c
> index 0697b05..dad9e0c 100644
> --- a/lib/librte_eal/bsdapp/eal/eal.c
> +++ b/lib/librte_eal/bsdapp/eal/eal.c
> @@ -803,7 +803,7 @@ int rte_eal_has_hugepages(void)
> }
>
> /* Abstraction for port I/0 privilege */
> -static int
> +int
> rte_eal_iopl_init(void)
> {
> int fd = -1;
> @@ -864,9 +864,6 @@ rte_eal_init(int argc, char **argv)
>
> rte_config_init();
>
> - if (rte_eal_iopl_init() == 0)
> - rte_config.flags |= EAL_FLG_HIGH_IOPL;
> -
> if (rte_eal_cpu_init() < 0)
> rte_panic("Cannot detect lcores\n");
>
> diff --git a/lib/librte_eal/common/include/rte_eal.h
> b/lib/librte_eal/common/include/rte_eal.h
> index 273da9a..8d39cba 100644
> --- a/lib/librte_eal/common/include/rte_eal.h
> +++ b/lib/librte_eal/common/include/rte_eal.h
> @@ -88,9 +88,6 @@ struct rte_config {
> struct rte_mem_config *mem_config;
> } __attribute__((__packed__));
>
> -/* Flag definitions for rte_config flags */
> -#define EAL_FLG_HIGH_IOPL 1 /**< indicates high IO privilege in a linux env */
> -
> /**
> * Get the global configuration structure.
> *
> @@ -119,6 +116,17 @@ enum rte_lcore_role_t rte_eal_lcore_role(unsigned
> lcore_id);
> enum rte_proc_type_t rte_eal_process_type(void);
>
> /**
> + * Request iopl privilege for all RPL.
> + *
> + * This function should be called by pmds which need access to ioports.
> +
> + * @return
> + * - On success, returns 0.
> + * - On failure, returns -1.
> + */
> +int rte_eal_iopl_init(void);
> +
> +/**
> * Initialize the Environment Abstraction Layer (EAL).
> *
> * This function is to be executed on the MASTER lcore only, as soon
> diff --git a/lib/librte_eal/linuxapp/eal/eal.c b/lib/librte_eal/linuxapp/eal/eal.c
> index 2940e69..884aa9b 100644
> --- a/lib/librte_eal/linuxapp/eal/eal.c
> +++ b/lib/librte_eal/linuxapp/eal/eal.c
> @@ -107,8 +107,6 @@
>
> #define SOCKET_MEM_STRLEN (RTE_MAX_NUMA_NODES * 10)
>
> -#define HIGHEST_RPL 3
> -
> #define BITS_PER_HEX 4
>
> /* Allow the application to print its usage message too if set */
> @@ -1060,10 +1058,12 @@ rte_eal_mcfg_complete(void)
> /*
> * Request iopl privilege for all RPL, returns 0 on success
> */
> -static int
> +int
> rte_eal_iopl_init(void)
> {
> - return iopl(HIGHEST_RPL);
> + if (iopl(3) != 0)
> + return -1;
> + return 0;
> }
>
> /* Launch threads, called at application init(). */
> @@ -1125,9 +1125,6 @@ rte_eal_init(int argc, char **argv)
>
> rte_config_init();
>
> - if (rte_eal_iopl_init() == 0)
> - rte_config.flags |= EAL_FLG_HIGH_IOPL;
> -
> if (rte_eal_pci_init() < 0)
> rte_panic("Cannot init PCI\n");
>
> diff --git a/lib/librte_pmd_virtio/virtio_ethdev.c
> b/lib/librte_pmd_virtio/virtio_ethdev.c
> index 3344ffb..587b746 100644
> --- a/lib/librte_pmd_virtio/virtio_ethdev.c
> +++ b/lib/librte_pmd_virtio/virtio_ethdev.c
> @@ -736,12 +736,6 @@ eth_virtio_dev_init(__rte_unused struct eth_driver
> *eth_drv,
> return -1;
> }
>
> - if (!(rte_eal_get_configuration()->flags & EAL_FLG_HIGH_IOPL)) {
> - PMD_INIT_LOG(ERR,
> - "IOPL call failed in EAL init - cannot use virtio PMD
> driver\n");
> - return -1;
> - }
> -
> eth_dev->dev_ops = &virtio_eth_dev_ops;
> eth_dev->tx_pkt_burst = &virtio_xmit_pkts;
>
> @@ -896,8 +890,15 @@ static struct eth_driver rte_virtio_pmd = {
> * Returns 0 on success.
> */
> static int
> -rte_virtio_pmd_init(const char *name __rte_unused, const char *param
> __rte_unused)
> +rte_virtio_pmd_init(const char *name __rte_unused,
> + const char *param __rte_unused)
> {
> + if (rte_eal_iopl_init() != 0) {
> + PMD_INIT_LOG(ERR, "IOPL call failed - "
> + "cannot use virtio PMD driver\n");
> + return -1;
> + }
> +
> rte_eth_driver_register(&rte_virtio_pmd);
> return 0;
> }
> --
> 1.7.10.4
next prev parent reply other threads:[~2014-08-27 17:24 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-08-26 14:11 [dpdk-dev] [PATCH RFC 0/3] only call iopl when necessary David Marchand
2014-08-26 14:11 ` [dpdk-dev] [PATCH RFC 1/3] eal/bsd: fix fd leak David Marchand
2014-09-25 10:17 ` Thomas Monjalon
2014-08-26 14:11 ` [dpdk-dev] [PATCH RFC 2/3] eal: don't call rte_eal_iopl_init unconditionnally David Marchand
2014-08-27 17:26 ` Xie, Huawei [this message]
2014-08-26 14:11 ` [dpdk-dev] [PATCH RFC 3/3] eal: remove unused flags field David Marchand
2014-08-27 9:22 ` [dpdk-dev] [PATCH RFC 0/3] only call iopl when necessary Xie, Huawei
2014-08-27 9:34 ` David Marchand
2014-08-27 9:57 ` Xie, Huawei
2014-08-27 10:04 ` David Marchand
2014-08-27 10:09 ` Xie, Huawei
2014-08-27 10:24 ` Thomas Monjalon
2014-08-27 21:22 ` Patel, Rashmin N
2014-08-27 22:12 ` Stephen Hemminger
2014-09-29 12:44 ` Thomas Monjalon
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=C37D651A908B024F974696C65296B57B0F27E532@SHSMSX101.ccr.corp.intel.com \
--to=huawei.xie@intel.com \
--cc=david.marchand@6wind.com \
--cc=dev@dpdk.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).