From: "Eli Dorfman (Voltaire)" <dorfman.eli-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
To: Sasha Khapyorsky <sashak-smomgflXvOZWk0Htik3J/w@public.gmane.org>
Cc: linux-rdma <linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
Vladimir Koushnir
<vladimirk-smomgflXvOZWk0Htik3J/w@public.gmane.org>
Subject: Re: [PATCH v2] ibsim: allocate mft according to number of switch ports
Date: Tue, 4 Jan 2011 14:39:18 +0200 [thread overview]
Message-ID: <4D2314F6.1060902@gmail.com> (raw)
In-Reply-To: <4C90B424.4060104-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Sasha,
It seems that you've missed this patch.
Please apply.
Thanks,
Eli
Eli Dorfman (Voltaire) wrote:
> allocate mft according to number of switch ports
>
> calculate number of port masks according to number of switch ports
> and allocate MFT accordingly
>
> Signed-off-by: Eli Dorfman <elid-smomgflXvOZWk0Htik3J/w@public.gmane.org>
> ---
> ibsim/sim.h | 5 ++---
> ibsim/sim_mad.c | 5 +++--
> ibsim/sim_net.c | 5 +++--
> 3 files changed, 8 insertions(+), 7 deletions(-)
>
> diff --git a/ibsim/sim.h b/ibsim/sim.h
> index 30f5075..c4ee11f 100644
> --- a/ibsim/sim.h
> +++ b/ibsim/sim.h
> @@ -45,9 +45,7 @@
> #define MAXLINEARCAP (30*1024)
> #define MAXMCASTCAP 1024
> #define LASTBLOCK32 (MAXMCASTCAP/32-1)
> -// NUMBEROFPORTMASK means that 32port switches could only be build
> -#define NUMBEROFPORTMASK 2
> -#define LASTPORTMASK (NUMBEROFPORTMASK-1)
> +#define MCASTMASKSIZE 16
> // linkwidth == 4X - must be one width only 1,2 or 8
> #define LINKWIDTH_1x 1
> #define LINKWIDTH_4x 2
> @@ -229,6 +227,7 @@ struct Switch {
> int linearFDBtop;
> int portchange;
> int lifetime;
> + int numportmask;
> uint8_t switchinfo[64];
> Node *node;
> uint8_t *fdb;
> diff --git a/ibsim/sim_mad.c b/ibsim/sim_mad.c
> index 61d4866..3133bcf 100644
> --- a/ibsim/sim_mad.c
> +++ b/ibsim/sim_mad.c
> @@ -513,18 +513,19 @@ static int do_multicastforwtbl(Port * port, unsigned op, uint32_t mod,
> int blockposition;
>
> Switch *sw = port->node->sw;
> + int lastportmask = sw->numportmask + 1;
>
> if (!sw) // not a Switch?
> return ERR_ATTR_UNSUPPORTED;
>
> VERB("requested : Block32 %d PortMask %d", numBlock32, numPortMsk);
> - if (numBlock32 > LASTBLOCK32 || numPortMsk > LASTPORTMASK) {
> + if (numBlock32 > LASTBLOCK32 || numPortMsk > lastportmask) {
> int8_t zeroblock[64] = { 0 };
> mad_set_array(data, 0, IB_MULTICAST_FORW_TBL_F, zeroblock);
> return 0;
> }
>
> - blockposition = (numBlock32 * NUMBEROFPORTMASK + numPortMsk) * 64;
> + blockposition = (numBlock32 * sw->numportmask + numPortMsk) * 64;
> if (op == IB_MAD_METHOD_SET)
> mad_get_array(data, 0, IB_MULTICAST_FORW_TBL_F,
> sw->mfdb + blockposition);
> diff --git a/ibsim/sim_net.c b/ibsim/sim_net.c
> index 13c3b8c..f17f0b9 100644
> --- a/ibsim/sim_net.c
> +++ b/ibsim/sim_net.c
> @@ -245,6 +245,7 @@ static Switch *new_switch(Node * nd, int set_esp0)
> sw->node = nd;
> sw->linearcap = maxlinearcap; // assume identical val for all switches
> sw->multicastcap = maxmcastcap; // assume identical val for all switches
> + sw->numportmask = (nd->numports + MCASTMASKSIZE) / MCASTMASKSIZE;
> memcpy(sw->switchinfo, switchinfo, sizeof(sw->switchinfo));
> mad_set_field(sw->switchinfo, 0, IB_SW_LINEAR_FDB_CAP_F, sw->linearcap);
> mad_set_field(sw->switchinfo, 0, IB_SW_MCAST_FDB_CAP_F,
> @@ -253,13 +254,13 @@ static Switch *new_switch(Node * nd, int set_esp0)
> mad_set_field(sw->switchinfo, 0, IB_SW_ENHANCED_PORT0_F,
> set_esp0 > 0);
> sw->fdb = malloc(maxlinearcap*sizeof(sw->fdb[0]));
> - sw->mfdb = malloc(maxmcastcap*NUMBEROFPORTMASK*sizeof(uint16_t));
> + sw->mfdb = malloc(maxmcastcap * sw->numportmask * sizeof(uint16_t));
> if (!sw->fdb || !sw->mfdb) {
> IBPANIC("new_switch: no mem: %m");
> return NULL;
> }
> memset(sw->fdb, 0xff, maxlinearcap*sizeof(sw->fdb[0]));
> - memset(sw->mfdb, 0, maxmcastcap*NUMBEROFPORTMASK*sizeof(uint16_t));
> + memset(sw->mfdb, 0, maxmcastcap * sw->numportmask * sizeof(uint16_t));
>
> return sw;
> }
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
prev parent reply other threads:[~2011-01-04 12:39 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-09-13 12:09 [PATCH] ibsim: support MFT for switches with up to 48 ports Eli Dorfman (Voltaire)
[not found] ` <4C8E1470.8070106-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2010-09-15 11:55 ` [PATCH v2] ibsim: allocate mft according to number of switch ports Eli Dorfman (Voltaire)
[not found] ` <4C90B424.4060104-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2011-01-04 12:39 ` Eli Dorfman (Voltaire) [this message]
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=4D2314F6.1060902@gmail.com \
--to=dorfman.eli-re5jqeeqqe8avxtiumwx3w@public.gmane.org \
--cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=sashak-smomgflXvOZWk0Htik3J/w@public.gmane.org \
--cc=vladimirk-smomgflXvOZWk0Htik3J/w@public.gmane.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).