From: dykmanj@linux.vnet.ibm.com
To: netdev@vger.kernel.org
Cc: Jim Dykman <dykmanj@linux.vnet.ibm.com>
Subject: [PATCH v4 00/27] HFI: minimal device driver/ip driver
Date: Mon, 25 Apr 2011 17:23:40 -0400 [thread overview]
Message-ID: <1303766647-30156-1-git-send-email-dykmanj@linux.vnet.ibm.com> (raw)
From: Jim Dykman <dykmanj@linux.vnet.ibm.com>
The HFI ("Host Fabric Interface") network interface is the internal cluster
fabric of IBM's PERCS supercomputer. The hardware design is under US export
control, so we cannot release hardware specs. There is a writeup of
publically available information about the system available here:
http://sourceforge.net/projects/hfidevicedriver/files/docs/hfi_general_desc_v2.1.txt
hfi_core contains the resource management to set up communications paths for
network traffic. Calls are provided for kernel drivers, and also for setting
up direct user-space access to HFI windows.
hfi_ip contains the kernel network driver.
The driver has been running in the lab for several months. The full patch is
around 22000 lines, so we've split out a minimal device/network driver that
can send and receive through the simplest path. Once that much gets accepted
we'll start adding on to it.
Patches are against net-next-2.6.
Jim Dykman
Changelog:
----------
v4: Don't include <linux/vermagic.h>
v3: Don't include <linux/version.h>
hfidd_mod_init: return -1; --> return rc;
hfidd_alloc_adapter: pass snprintf xiHFI_DEVICE_NAME_MAX,
not HFI_DEVICE_NAME_MAX -1
change HFI_DEVICE_NAME_MAX from 64 to 8
v2:
Remove return; at the end of void funcs
hfidd_free_adapter: p_acs = NULL unneccesssary, remove
remove net_stats, and use netdev->stats, remove hf_get_stats
rename network driver to hfi_ip
hf_inet_event: NETDEV_UP needs to check event is for us, check
netdev->netdev_ops == ours
change printk()s to netdev_err() and friends
hf_net_close: remove redundant CLOSE check
hf_change_mtu: minimum mtu should be 68
remove NETIF_F_SG flag
hf_init_netdev: Use ERR_PTR
hf_init_module: %ld / formatting
pass up return code from failed call
use unsigned int instead of u32 for bit fields <32 bits
use struct ethhdr instead of hf_hwhdr
hf_get_sset_count: default return -EINVAL not -EOPNOTSUPP
Remove "hfidd_callback_event: enter" message that printed on every
recv interrupt
hfidd_destroy_devices: hfidd_rmdev() after hfidd_free_adapter() so
dev_printk doesn't oops on rmmod
next reply other threads:[~2011-04-25 21:24 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-04-25 21:23 dykmanj [this message]
2011-04-25 21:23 ` [PATCH v4 01/27] HFI: skeleton driver dykmanj
2011-05-20 18:37 ` Brian King
2011-04-25 21:23 ` [PATCH v4 02/27] HFI: Add HFI adapter control structure dykmanj
2011-04-25 21:23 ` [PATCH v4 03/27] HFI: Add device_create/device_destroy calls for HFI devices dykmanj
2011-04-25 21:23 ` [PATCH v4 04/27] HFI: Find HFI devices in the device tree dykmanj
2011-04-25 21:23 ` [PATCH v4 05/27] HFI: The first few HFI-specific hypervisor calls dykmanj
2011-04-25 21:23 ` [PATCH v4 06/27] HFI: Add DD calls to START/STOP INTERFACE HCALLs dykmanj
2011-04-25 21:23 ` [PATCH v4 07/27] HFI: Add nMMU start/stop hypervisor calls dykmanj
2011-04-25 21:23 ` [PATCH v4 08/27] HFI: DD request framework and first HFI DD request dykmanj
2011-04-25 21:23 ` [PATCH v4 09/27] HFI: Add HFI window resource tracking dykmanj
2011-04-25 21:23 ` [PATCH v4 10/27] HFI: HFIDD_REQ_OPEN_WINDOW request dykmanj
2011-04-25 21:23 ` [PATCH v4 11/27] HFI: Check window number/assign window number dykmanj
2011-04-25 21:23 ` [PATCH v4 12/27] HFI: Sanity check send and receive fifo parameters dykmanj
2011-04-25 21:23 ` [PATCH v4 13/27] HFI: Send and receive fifo address translation dykmanj
2011-04-25 21:23 ` [PATCH v4 14/27] HFI: Add hypercalls to create/modify/free page tables in the nMMU dykmanj
2011-04-25 21:23 ` [PATCH v4 15/27] HFI: Set up nMMU page tables for the send and receive fifos dykmanj
2011-04-25 21:23 ` [PATCH v4 16/27] HFI: Add window open hypervisor call dykmanj
2011-04-25 21:23 ` [PATCH v4 17/27] HFI: Set up and call the open window hypercall dykmanj
2011-04-25 21:23 ` [PATCH v4 18/27] HFI: Map window registers into user process dykmanj
2011-04-25 21:23 ` [PATCH v4 19/27] HFI: Add window close request dykmanj
2011-04-25 21:24 ` [PATCH v4 20/27] HFI: Close window hypervisor call dykmanj
2011-04-25 21:24 ` [PATCH v4 21/27] HFI: Add send and receive interrupts dykmanj
2011-04-25 21:24 ` [PATCH v4 22/27] HFI: Add event notifications dykmanj
2011-04-25 21:24 ` [PATCH v4 23/27] HFI: Define packet header formats and window register offsets dykmanj
2011-04-25 21:24 ` [PATCH v4 24/27] HFI: hfi_ip network driver dykmanj
2011-04-25 21:24 ` [PATCH v4 25/27] HFI: hfi_ip fifo transmit paths dykmanj
2011-04-25 21:24 ` [PATCH v4 26/27] HFI: hfi_ip fifo receive path dykmanj
2011-04-25 21:24 ` [PATCH v4 27/27] HFI: hfi_ip ethtool support dykmanj
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=1303766647-30156-1-git-send-email-dykmanj@linux.vnet.ibm.com \
--to=dykmanj@linux.vnet.ibm.com \
--cc=netdev@vger.kernel.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).