linux-stable/drivers/infiniband/ulp/ipoib/ipoib_ib.c

1083 lines
27 KiB
C
Raw Normal View History

/*
* Copyright (c) 2004, 2005 Topspin Communications. All rights reserved.
* Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
* Copyright (c) 2005 Mellanox Technologies. All rights reserved.
* Copyright (c) 2004, 2005 Voltaire, Inc. All rights reserved.
*
* This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU
* General Public License (GPL) Version 2, available from the file
* COPYING in the main directory of this source tree, or the
* OpenIB.org BSD license below:
*
* Redistribution and use in source and binary forms, with or
* without modification, are permitted provided that the following
* conditions are met:
*
* - Redistributions of source code must retain the above
* copyright notice, this list of conditions and the following
* disclaimer.
*
* - Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following
* disclaimer in the documentation and/or other materials
* provided with the distribution.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
#include <linux/delay.h>
#include <linux/moduleparam.h>
#include <linux/dma-mapping.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include "ipoib.h"
#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG_DATA
static int data_debug_level;
module_param(data_debug_level, int, 0644);
MODULE_PARM_DESC(data_debug_level,
"Enable data path debug tracing if > 0");
#endif
static DEFINE_MUTEX(pkey_mutex);
struct ipoib_ah *ipoib_create_ah(struct net_device *dev,
struct ib_pd *pd, struct ib_ah_attr *attr)
{
struct ipoib_ah *ah;
ah = kmalloc(sizeof *ah, GFP_KERNEL);
if (!ah)
return NULL;
ah->dev = dev;
ah->last_send = 0;
kref_init(&ah->ref);
ah->ah = ib_create_ah(pd, attr);
if (IS_ERR(ah->ah)) {
kfree(ah);
ah = NULL;
} else
ipoib_dbg(netdev_priv(dev), "Created ah %p\n", ah->ah);
return ah;
}
void ipoib_free_ah(struct kref *kref)
{
struct ipoib_ah *ah = container_of(kref, struct ipoib_ah, ref);
struct ipoib_dev_priv *priv = netdev_priv(ah->dev);
unsigned long flags;
spin_lock_irqsave(&priv->lock, flags);
list_add_tail(&ah->list, &priv->dead_ahs);
spin_unlock_irqrestore(&priv->lock, flags);
}
static void ipoib_ud_dma_unmap_rx(struct ipoib_dev_priv *priv,
u64 mapping[IPOIB_UD_RX_SG])
{
if (ipoib_ud_need_sg(priv->max_ib_mtu)) {
ib_dma_unmap_single(priv->ca, mapping[0], IPOIB_UD_HEAD_SIZE,
DMA_FROM_DEVICE);
ib_dma_unmap_page(priv->ca, mapping[1], PAGE_SIZE,
DMA_FROM_DEVICE);
} else
ib_dma_unmap_single(priv->ca, mapping[0],
IPOIB_UD_BUF_SIZE(priv->max_ib_mtu),
DMA_FROM_DEVICE);
}
static void ipoib_ud_skb_put_frags(struct ipoib_dev_priv *priv,
struct sk_buff *skb,
unsigned int length)
{
if (ipoib_ud_need_sg(priv->max_ib_mtu)) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[0];
unsigned int size;
/*
* There is only two buffers needed for max_payload = 4K,
* first buf size is IPOIB_UD_HEAD_SIZE
*/
skb->tail += IPOIB_UD_HEAD_SIZE;
skb->len += length;
size = length - IPOIB_UD_HEAD_SIZE;
skb_frag_size_set(frag, size);
skb->data_len += size;
skb->truesize += size;
} else
skb_put(skb, length);
}
static int ipoib_ib_post_receive(struct net_device *dev, int id)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ib_recv_wr *bad_wr;
int ret;
priv->rx_wr.wr_id = id | IPOIB_OP_RECV;
priv->rx_sge[0].addr = priv->rx_ring[id].mapping[0];
priv->rx_sge[1].addr = priv->rx_ring[id].mapping[1];
ret = ib_post_recv(priv->qp, &priv->rx_wr, &bad_wr);
if (unlikely(ret)) {
ipoib_warn(priv, "receive failed for buf %d (%d)\n", id, ret);
ipoib_ud_dma_unmap_rx(priv, priv->rx_ring[id].mapping);
dev_kfree_skb_any(priv->rx_ring[id].skb);
priv->rx_ring[id].skb = NULL;
}
return ret;
}
static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct sk_buff *skb;
int buf_size;
u64 *mapping;
if (ipoib_ud_need_sg(priv->max_ib_mtu))
buf_size = IPOIB_UD_HEAD_SIZE;
else
buf_size = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu);
skb = dev_alloc_skb(buf_size + 4);
if (unlikely(!skb))
return NULL;
/*
* IB will leave a 40 byte gap for a GRH and IPoIB adds a 4 byte
* header. So we need 4 more bytes to get to 48 and align the
* IP header to a multiple of 16.
*/
skb_reserve(skb, 4);
mapping = priv->rx_ring[id].mapping;
mapping[0] = ib_dma_map_single(priv->ca, skb->data, buf_size,
DMA_FROM_DEVICE);
if (unlikely(ib_dma_mapping_error(priv->ca, mapping[0])))
goto error;
if (ipoib_ud_need_sg(priv->max_ib_mtu)) {
struct page *page = alloc_page(GFP_ATOMIC);
if (!page)
goto partial_error;
skb_fill_page_desc(skb, 0, page, 0, PAGE_SIZE);
mapping[1] =
ib_dma_map_page(priv->ca, page,
0, PAGE_SIZE, DMA_FROM_DEVICE);
if (unlikely(ib_dma_mapping_error(priv->ca, mapping[1])))
goto partial_error;
}
priv->rx_ring[id].skb = skb;
return skb;
partial_error:
ib_dma_unmap_single(priv->ca, mapping[0], buf_size, DMA_FROM_DEVICE);
error:
dev_kfree_skb_any(skb);
return NULL;
}
static int ipoib_ib_post_receives(struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
int i;
for (i = 0; i < ipoib_recvq_size; ++i) {
if (!ipoib_alloc_rx_skb(dev, i)) {
ipoib_warn(priv, "failed to allocate receive buffer %d\n", i);
return -ENOMEM;
}
if (ipoib_ib_post_receive(dev, i)) {
ipoib_warn(priv, "ipoib_ib_post_receive failed for buf %d\n", i);
return -EIO;
}
}
return 0;
}
static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
unsigned int wr_id = wc->wr_id & ~IPOIB_OP_RECV;
struct sk_buff *skb;
u64 mapping[IPOIB_UD_RX_SG];
union ib_gid *dgid;
ipoib_dbg_data(priv, "recv completion: id %d, status: %d\n",
wr_id, wc->status);
if (unlikely(wr_id >= ipoib_recvq_size)) {
ipoib_warn(priv, "recv completion event with wrid %d (> %d)\n",
wr_id, ipoib_recvq_size);
return;
}
skb = priv->rx_ring[wr_id].skb;
if (unlikely(wc->status != IB_WC_SUCCESS)) {
if (wc->status != IB_WC_WR_FLUSH_ERR)
ipoib_warn(priv, "failed recv event "
"(status=%d, wrid=%d vend_err %x)\n",
wc->status, wr_id, wc->vendor_err);
ipoib_ud_dma_unmap_rx(priv, priv->rx_ring[wr_id].mapping);
dev_kfree_skb_any(skb);
priv->rx_ring[wr_id].skb = NULL;
return;
}
/*
* Drop packets that this interface sent, ie multicast packets
* that the HCA has replicated.
*/
if (wc->slid == priv->local_lid && wc->src_qp == priv->qp->qp_num)
goto repost;
memcpy(mapping, priv->rx_ring[wr_id].mapping,
IPOIB_UD_RX_SG * sizeof *mapping);
/*
* If we can't allocate a new RX buffer, dump
* this packet and reuse the old buffer.
*/
if (unlikely(!ipoib_alloc_rx_skb(dev, wr_id))) {
++dev->stats.rx_dropped;
goto repost;
}
ipoib_dbg_data(priv, "received %d bytes, SLID 0x%04x\n",
wc->byte_len, wc->slid);
ipoib_ud_dma_unmap_rx(priv, mapping);
ipoib_ud_skb_put_frags(priv, skb, wc->byte_len);
/* First byte of dgid signals multicast when 0xff */
dgid = &((struct ib_grh *)skb->data)->dgid;
if (!(wc->wc_flags & IB_WC_GRH) || dgid->raw[0] != 0xff)
skb->pkt_type = PACKET_HOST;
else if (memcmp(dgid, dev->broadcast + 4, sizeof(union ib_gid)) == 0)
skb->pkt_type = PACKET_BROADCAST;
else
skb->pkt_type = PACKET_MULTICAST;
skb_pull(skb, IB_GRH_BYTES);
skb->protocol = ((struct ipoib_header *) skb->data)->proto;
skb_reset_mac_header(skb);
skb_pull(skb, IPOIB_ENCAP_LEN);
++dev->stats.rx_packets;
dev->stats.rx_bytes += skb->len;
skb->dev = dev;
if ((dev->features & NETIF_F_RXCSUM) && likely(wc->csum_ok))
skb->ip_summed = CHECKSUM_UNNECESSARY;
napi_gro_receive(&priv->napi, skb);
repost:
if (unlikely(ipoib_ib_post_receive(dev, wr_id)))
ipoib_warn(priv, "ipoib_ib_post_receive failed "
"for buf %d\n", wr_id);
}
static int ipoib_dma_map_tx(struct ib_device *ca,
struct ipoib_tx_buf *tx_req)
{
struct sk_buff *skb = tx_req->skb;
u64 *mapping = tx_req->mapping;
int i;
int off;
if (skb_headlen(skb)) {
mapping[0] = ib_dma_map_single(ca, skb->data, skb_headlen(skb),
DMA_TO_DEVICE);
if (unlikely(ib_dma_mapping_error(ca, mapping[0])))
return -EIO;
off = 1;
} else
off = 0;
for (i = 0; i < skb_shinfo(skb)->nr_frags; ++i) {
const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
mapping[i + off] = ib_dma_map_page(ca,
skb_frag_page(frag),
frag->page_offset, skb_frag_size(frag),
DMA_TO_DEVICE);
if (unlikely(ib_dma_mapping_error(ca, mapping[i + off])))
goto partial_error;
}
return 0;
partial_error:
for (; i > 0; --i) {
const skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1];
ib_dma_unmap_page(ca, mapping[i - !off], skb_frag_size(frag), DMA_TO_DEVICE);
}
if (off)
ib_dma_unmap_single(ca, mapping[0], skb_headlen(skb), DMA_TO_DEVICE);
return -EIO;
}
static void ipoib_dma_unmap_tx(struct ib_device *ca,
struct ipoib_tx_buf *tx_req)
{
struct sk_buff *skb = tx_req->skb;
u64 *mapping = tx_req->mapping;
int i;
int off;
if (skb_headlen(skb)) {
ib_dma_unmap_single(ca, mapping[0], skb_headlen(skb), DMA_TO_DEVICE);
off = 1;
} else
off = 0;
for (i = 0; i < skb_shinfo(skb)->nr_frags; ++i) {
const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
ib_dma_unmap_page(ca, mapping[i + off], skb_frag_size(frag),
DMA_TO_DEVICE);
}
}
static void ipoib_ib_handle_tx_wc(struct net_device *dev, struct ib_wc *wc)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
unsigned int wr_id = wc->wr_id;
struct ipoib_tx_buf *tx_req;
ipoib_dbg_data(priv, "send completion: id %d, status: %d\n",
wr_id, wc->status);
if (unlikely(wr_id >= ipoib_sendq_size)) {
ipoib_warn(priv, "send completion event with wrid %d (> %d)\n",
wr_id, ipoib_sendq_size);
return;
}
tx_req = &priv->tx_ring[wr_id];
ipoib_dma_unmap_tx(priv->ca, tx_req);
++dev->stats.tx_packets;
dev->stats.tx_bytes += tx_req->skb->len;
dev_kfree_skb_any(tx_req->skb);
++priv->tx_tail;
if (unlikely(--priv->tx_outstanding == ipoib_sendq_size >> 1) &&
netif_queue_stopped(dev) &&
test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))
netif_wake_queue(dev);
if (wc->status != IB_WC_SUCCESS &&
wc->status != IB_WC_WR_FLUSH_ERR)
ipoib_warn(priv, "failed send event "
"(status=%d, wrid=%d vend_err %x)\n",
wc->status, wr_id, wc->vendor_err);
}
static int poll_tx(struct ipoib_dev_priv *priv)
{
int n, i;
n = ib_poll_cq(priv->send_cq, MAX_SEND_CQE, priv->send_wc);
for (i = 0; i < n; ++i)
ipoib_ib_handle_tx_wc(priv->dev, priv->send_wc + i);
return n == MAX_SEND_CQE;
}
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-03 23:41:36 +00:00
int ipoib_poll(struct napi_struct *napi, int budget)
{
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-03 23:41:36 +00:00
struct ipoib_dev_priv *priv = container_of(napi, struct ipoib_dev_priv, napi);
struct net_device *dev = priv->dev;
int done;
int t;
int n, i;
done = 0;
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-03 23:41:36 +00:00
poll_more:
while (done < budget) {
int max = (budget - done);
t = min(IPOIB_NUM_WC, max);
n = ib_poll_cq(priv->recv_cq, t, priv->ibwc);
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-03 23:41:36 +00:00
for (i = 0; i < n; i++) {
struct ib_wc *wc = priv->ibwc + i;
if (wc->wr_id & IPOIB_OP_RECV) {
++done;
if (wc->wr_id & IPOIB_OP_CM)
ipoib_cm_handle_rx_wc(dev, wc);
else
ipoib_ib_handle_rx_wc(dev, wc);
} else
ipoib_cm_handle_tx_wc(priv->dev, wc);
}
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-03 23:41:36 +00:00
if (n != t)
break;
}
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-03 23:41:36 +00:00
if (done < budget) {
napi_complete(napi);
if (unlikely(ib_req_notify_cq(priv->recv_cq,
IB_CQ_NEXT_COMP |
IB_CQ_REPORT_MISSED_EVENTS)) &&
napi_reschedule(napi))
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-03 23:41:36 +00:00
goto poll_more;
}
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-03 23:41:36 +00:00
return done;
}
void ipoib_ib_completion(struct ib_cq *cq, void *dev_ptr)
{
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-03 23:41:36 +00:00
struct net_device *dev = dev_ptr;
struct ipoib_dev_priv *priv = netdev_priv(dev);
napi_schedule(&priv->napi);
}
static void drain_tx_cq(struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
netif_tx_lock(dev);
while (poll_tx(priv))
; /* nothing */
if (netif_queue_stopped(dev))
mod_timer(&priv->poll_timer, jiffies + 1);
netif_tx_unlock(dev);
}
void ipoib_send_comp_handler(struct ib_cq *cq, void *dev_ptr)
{
struct ipoib_dev_priv *priv = netdev_priv(dev_ptr);
mod_timer(&priv->poll_timer, jiffies);
}
static inline int post_send(struct ipoib_dev_priv *priv,
unsigned int wr_id,
struct ib_ah *address, u32 qpn,
struct ipoib_tx_buf *tx_req,
void *head, int hlen)
{
struct ib_send_wr *bad_wr;
int i, off;
struct sk_buff *skb = tx_req->skb;
skb_frag_t *frags = skb_shinfo(skb)->frags;
int nr_frags = skb_shinfo(skb)->nr_frags;
u64 *mapping = tx_req->mapping;
if (skb_headlen(skb)) {
priv->tx_sge[0].addr = mapping[0];
priv->tx_sge[0].length = skb_headlen(skb);
off = 1;
} else
off = 0;
for (i = 0; i < nr_frags; ++i) {
priv->tx_sge[i + off].addr = mapping[i + off];
priv->tx_sge[i + off].length = skb_frag_size(&frags[i]);
}
priv->tx_wr.num_sge = nr_frags + off;
priv->tx_wr.wr_id = wr_id;
priv->tx_wr.wr.ud.remote_qpn = qpn;
priv->tx_wr.wr.ud.ah = address;
if (head) {
priv->tx_wr.wr.ud.mss = skb_shinfo(skb)->gso_size;
priv->tx_wr.wr.ud.header = head;
priv->tx_wr.wr.ud.hlen = hlen;
priv->tx_wr.opcode = IB_WR_LSO;
} else
priv->tx_wr.opcode = IB_WR_SEND;
return ib_post_send(priv->qp, &priv->tx_wr, &bad_wr);
}
void ipoib_send(struct net_device *dev, struct sk_buff *skb,
struct ipoib_ah *address, u32 qpn)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ipoib_tx_buf *tx_req;
int hlen, rc;
void *phead;
if (skb_is_gso(skb)) {
hlen = skb_transport_offset(skb) + tcp_hdrlen(skb);
phead = skb->data;
if (unlikely(!skb_pull(skb, hlen))) {
ipoib_warn(priv, "linear data too small\n");
++dev->stats.tx_dropped;
++dev->stats.tx_errors;
dev_kfree_skb_any(skb);
return;
}
} else {
if (unlikely(skb->len > priv->mcast_mtu + IPOIB_ENCAP_LEN)) {
ipoib_warn(priv, "packet len %d (> %d) too long to send, dropping\n",
skb->len, priv->mcast_mtu + IPOIB_ENCAP_LEN);
++dev->stats.tx_dropped;
++dev->stats.tx_errors;
ipoib_cm_skb_too_long(dev, skb, priv->mcast_mtu);
return;
}
phead = NULL;
hlen = 0;
}
ipoib_dbg_data(priv, "sending packet, length=%d address=%p qpn=0x%06x\n",
skb->len, address, qpn);
/*
* We put the skb into the tx_ring _before_ we call post_send()
* because it's entirely possible that the completion handler will
* run before we execute anything after the post_send(). That
* means we have to make sure everything is properly recorded and
* our state is consistent before we call post_send().
*/
tx_req = &priv->tx_ring[priv->tx_head & (ipoib_sendq_size - 1)];
tx_req->skb = skb;
if (unlikely(ipoib_dma_map_tx(priv->ca, tx_req))) {
++dev->stats.tx_errors;
dev_kfree_skb_any(skb);
return;
}
if (skb->ip_summed == CHECKSUM_PARTIAL)
priv->tx_wr.send_flags |= IB_SEND_IP_CSUM;
else
priv->tx_wr.send_flags &= ~IB_SEND_IP_CSUM;
if (++priv->tx_outstanding == ipoib_sendq_size) {
ipoib_dbg(priv, "TX ring full, stopping kernel net queue\n");
if (ib_req_notify_cq(priv->send_cq, IB_CQ_NEXT_COMP))
ipoib_warn(priv, "request notify on send CQ failed\n");
netif_stop_queue(dev);
}
rc = post_send(priv, priv->tx_head & (ipoib_sendq_size - 1),
address->ah, qpn, tx_req, phead, hlen);
if (unlikely(rc)) {
ipoib_warn(priv, "post_send failed, error %d\n", rc);
++dev->stats.tx_errors;
--priv->tx_outstanding;
ipoib_dma_unmap_tx(priv->ca, tx_req);
dev_kfree_skb_any(skb);
if (netif_queue_stopped(dev))
netif_wake_queue(dev);
} else {
dev->trans_start = jiffies;
address->last_send = priv->tx_head;
++priv->tx_head;
skb_orphan(skb);
}
if (unlikely(priv->tx_outstanding > MAX_SEND_CQE))
while (poll_tx(priv))
; /* nothing */
}
static void __ipoib_reap_ah(struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ipoib_ah *ah, *tah;
LIST_HEAD(remove_list);
unsigned long flags;
netif_tx_lock_bh(dev);
spin_lock_irqsave(&priv->lock, flags);
list_for_each_entry_safe(ah, tah, &priv->dead_ahs, list)
if ((int) priv->tx_tail - (int) ah->last_send >= 0) {
list_del(&ah->list);
ib_destroy_ah(ah->ah);
kfree(ah);
}
spin_unlock_irqrestore(&priv->lock, flags);
netif_tx_unlock_bh(dev);
}
void ipoib_reap_ah(struct work_struct *work)
{
struct ipoib_dev_priv *priv =
container_of(work, struct ipoib_dev_priv, ah_reap_task.work);
struct net_device *dev = priv->dev;
__ipoib_reap_ah(dev);
if (!test_bit(IPOIB_STOP_REAPER, &priv->flags))
queue_delayed_work(ipoib_workqueue, &priv->ah_reap_task,
round_jiffies_relative(HZ));
}
static void ipoib_ib_tx_timer_func(unsigned long ctx)
{
drain_tx_cq((struct net_device *)ctx);
}
int ipoib_ib_dev_open(struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
int ret;
if (ib_find_pkey(priv->ca, priv->port, priv->pkey, &priv->pkey_index)) {
ipoib_warn(priv, "P_Key 0x%04x not found\n", priv->pkey);
clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
return -1;
}
set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
ret = ipoib_init_qp(dev);
if (ret) {
ipoib_warn(priv, "ipoib_init_qp returned %d\n", ret);
return -1;
}
ret = ipoib_ib_post_receives(dev);
if (ret) {
ipoib_warn(priv, "ipoib_ib_post_receives returned %d\n", ret);
ipoib_ib_dev_stop(dev, 1);
return -1;
}
ret = ipoib_cm_dev_open(dev);
if (ret) {
ipoib_warn(priv, "ipoib_cm_dev_open returned %d\n", ret);
ipoib_ib_dev_stop(dev, 1);
return -1;
}
clear_bit(IPOIB_STOP_REAPER, &priv->flags);
queue_delayed_work(ipoib_workqueue, &priv->ah_reap_task,
round_jiffies_relative(HZ));
if (!test_and_set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
napi_enable(&priv->napi);
return 0;
}
static void ipoib_pkey_dev_check_presence(struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
u16 pkey_index = 0;
if (ib_find_pkey(priv->ca, priv->port, priv->pkey, &pkey_index))
clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
else
set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
}
int ipoib_ib_dev_up(struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
ipoib_pkey_dev_check_presence(dev);
if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) {
ipoib_dbg(priv, "PKEY is not assigned.\n");
return 0;
}
set_bit(IPOIB_FLAG_OPER_UP, &priv->flags);
return ipoib_mcast_start_thread(dev);
}
int ipoib_ib_dev_down(struct net_device *dev, int flush)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
ipoib_dbg(priv, "downing ib_dev\n");
clear_bit(IPOIB_FLAG_OPER_UP, &priv->flags);
netif_carrier_off(dev);
/* Shutdown the P_Key thread if still active */
if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) {
mutex_lock(&pkey_mutex);
set_bit(IPOIB_PKEY_STOP, &priv->flags);
cancel_delayed_work(&priv->pkey_poll_task);
mutex_unlock(&pkey_mutex);
if (flush)
flush_workqueue(ipoib_workqueue);
}
ipoib_mcast_stop_thread(dev, flush);
ipoib_mcast_dev_flush(dev);
ipoib_flush_paths(dev);
return 0;
}
static int recvs_pending(struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
int pending = 0;
int i;
for (i = 0; i < ipoib_recvq_size; ++i)
if (priv->rx_ring[i].skb)
++pending;
return pending;
}
void ipoib_drain_cq(struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
int i, n;
/*
* We call completion handling routines that expect to be
* called from the BH-disabled NAPI poll context, so disable
* BHs here too.
*/
local_bh_disable();
do {
n = ib_poll_cq(priv->recv_cq, IPOIB_NUM_WC, priv->ibwc);
for (i = 0; i < n; ++i) {
/*
* Convert any successful completions to flush
* errors to avoid passing packets up the
* stack after bringing the device down.
*/
if (priv->ibwc[i].status == IB_WC_SUCCESS)
priv->ibwc[i].status = IB_WC_WR_FLUSH_ERR;
if (priv->ibwc[i].wr_id & IPOIB_OP_RECV) {
if (priv->ibwc[i].wr_id & IPOIB_OP_CM)
ipoib_cm_handle_rx_wc(dev, priv->ibwc + i);
else
ipoib_ib_handle_rx_wc(dev, priv->ibwc + i);
} else
ipoib_cm_handle_tx_wc(dev, priv->ibwc + i);
}
} while (n == IPOIB_NUM_WC);
while (poll_tx(priv))
; /* nothing */
local_bh_enable();
}
int ipoib_ib_dev_stop(struct net_device *dev, int flush)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ib_qp_attr qp_attr;
unsigned long begin;
struct ipoib_tx_buf *tx_req;
int i;
if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
napi_disable(&priv->napi);
ipoib_cm_dev_stop(dev);
/*
* Move our QP to the error state and then reinitialize in
* when all work requests have completed or have been flushed.
*/
qp_attr.qp_state = IB_QPS_ERR;
if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE))
ipoib_warn(priv, "Failed to modify QP to ERROR state\n");
/* Wait for all sends and receives to complete */
begin = jiffies;
while (priv->tx_head != priv->tx_tail || recvs_pending(dev)) {
if (time_after(jiffies, begin + 5 * HZ)) {
ipoib_warn(priv, "timing out; %d sends %d receives not completed\n",
priv->tx_head - priv->tx_tail, recvs_pending(dev));
/*
* assume the HW is wedged and just free up
* all our pending work requests.
*/
while ((int) priv->tx_tail - (int) priv->tx_head < 0) {
tx_req = &priv->tx_ring[priv->tx_tail &
(ipoib_sendq_size - 1)];
ipoib_dma_unmap_tx(priv->ca, tx_req);
dev_kfree_skb_any(tx_req->skb);
++priv->tx_tail;
--priv->tx_outstanding;
}
for (i = 0; i < ipoib_recvq_size; ++i) {
struct ipoib_rx_buf *rx_req;
rx_req = &priv->rx_ring[i];
if (!rx_req->skb)
continue;
ipoib_ud_dma_unmap_rx(priv,
priv->rx_ring[i].mapping);
dev_kfree_skb_any(rx_req->skb);
rx_req->skb = NULL;
}
goto timeout;
}
ipoib_drain_cq(dev);
msleep(1);
}
ipoib_dbg(priv, "All sends and receives done.\n");
timeout:
del_timer_sync(&priv->poll_timer);
qp_attr.qp_state = IB_QPS_RESET;
if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE))
ipoib_warn(priv, "Failed to modify QP to RESET state\n");
/* Wait for all AHs to be reaped */
set_bit(IPOIB_STOP_REAPER, &priv->flags);
cancel_delayed_work(&priv->ah_reap_task);
if (flush)
flush_workqueue(ipoib_workqueue);
begin = jiffies;
while (!list_empty(&priv->dead_ahs)) {
__ipoib_reap_ah(dev);
if (time_after(jiffies, begin + HZ)) {
ipoib_warn(priv, "timing out; will leak address handles\n");
break;
}
msleep(1);
}
ib_req_notify_cq(priv->recv_cq, IB_CQ_NEXT_COMP);
return 0;
}
int ipoib_ib_dev_init(struct net_device *dev, struct ib_device *ca, int port)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
priv->ca = ca;
priv->port = port;
priv->qp = NULL;
if (ipoib_transport_dev_init(dev, ca)) {
printk(KERN_WARNING "%s: ipoib_transport_dev_init failed\n", ca->name);
return -ENODEV;
}
setup_timer(&priv->poll_timer, ipoib_ib_tx_timer_func,
(unsigned long) dev);
if (dev->flags & IFF_UP) {
if (ipoib_ib_dev_open(dev)) {
ipoib_transport_dev_cleanup(dev);
return -ENODEV;
}
}
return 0;
}
static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
enum ipoib_flush_level level)
{
struct ipoib_dev_priv *cpriv;
struct net_device *dev = priv->dev;
u16 new_index;
mutex_lock(&priv->vlan_mutex);
/*
* Flush any child interfaces too -- they might be up even if
* the parent is down.
*/
list_for_each_entry(cpriv, &priv->child_intfs, list)
__ipoib_ib_dev_flush(cpriv, level);
mutex_unlock(&priv->vlan_mutex);
if (!test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) {
ipoib_dbg(priv, "Not flushing - IPOIB_FLAG_INITIALIZED not set.\n");
return;
}
if (!test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) {
ipoib_dbg(priv, "Not flushing - IPOIB_FLAG_ADMIN_UP not set.\n");
return;
}
if (level == IPOIB_FLUSH_HEAVY) {
if (ib_find_pkey(priv->ca, priv->port, priv->pkey, &new_index)) {
clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
ipoib_ib_dev_down(dev, 0);
ipoib_ib_dev_stop(dev, 0);
if (ipoib_pkey_dev_delay_open(dev))
return;
}
/* restart QP only if P_Key index is changed */
if (test_and_set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags) &&
new_index == priv->pkey_index) {
ipoib_dbg(priv, "Not flushing - P_Key index not changed.\n");
return;
}
priv->pkey_index = new_index;
}
if (level == IPOIB_FLUSH_LIGHT) {
ipoib_mark_paths_invalid(dev);
ipoib_mcast_dev_flush(dev);
}
if (level >= IPOIB_FLUSH_NORMAL)
ipoib_ib_dev_down(dev, 0);
if (level == IPOIB_FLUSH_HEAVY) {
ipoib_ib_dev_stop(dev, 0);
ipoib_ib_dev_open(dev);
}
/*
* The device could have been brought down between the start and when
* we get here, don't bring it back up if it's not configured up
*/
if (test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) {
if (level >= IPOIB_FLUSH_NORMAL)
ipoib_ib_dev_up(dev);
ipoib_mcast_restart_task(&priv->restart_task);
}
}
void ipoib_ib_dev_flush_light(struct work_struct *work)
{
struct ipoib_dev_priv *priv =
container_of(work, struct ipoib_dev_priv, flush_light);
__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_LIGHT);
}
void ipoib_ib_dev_flush_normal(struct work_struct *work)
{
struct ipoib_dev_priv *priv =
container_of(work, struct ipoib_dev_priv, flush_normal);
__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_NORMAL);
}
void ipoib_ib_dev_flush_heavy(struct work_struct *work)
{
struct ipoib_dev_priv *priv =
container_of(work, struct ipoib_dev_priv, flush_heavy);
__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_HEAVY);
}
void ipoib_ib_dev_cleanup(struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
ipoib_dbg(priv, "cleaning up ib_dev\n");
ipoib_mcast_stop_thread(dev, 1);
ipoib_mcast_dev_flush(dev);
ipoib_transport_dev_cleanup(dev);
}
/*
* Delayed P_Key Assigment Interim Support
*
* The following is initial implementation of delayed P_Key assigment
* mechanism. It is using the same approach implemented for the multicast
* group join. The single goal of this implementation is to quickly address
* Bug #2507. This implementation will probably be removed when the P_Key
* change async notification is available.
*/
void ipoib_pkey_poll(struct work_struct *work)
{
struct ipoib_dev_priv *priv =
container_of(work, struct ipoib_dev_priv, pkey_poll_task.work);
struct net_device *dev = priv->dev;
ipoib_pkey_dev_check_presence(dev);
if (test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags))
ipoib_open(dev);
else {
mutex_lock(&pkey_mutex);
if (!test_bit(IPOIB_PKEY_STOP, &priv->flags))
queue_delayed_work(ipoib_workqueue,
&priv->pkey_poll_task,
HZ);
mutex_unlock(&pkey_mutex);
}
}
int ipoib_pkey_dev_delay_open(struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
/* Look for the interface pkey value in the IB Port P_Key table and */
/* set the interface pkey assigment flag */
ipoib_pkey_dev_check_presence(dev);
/* P_Key value not assigned yet - start polling */
if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) {
mutex_lock(&pkey_mutex);
clear_bit(IPOIB_PKEY_STOP, &priv->flags);
queue_delayed_work(ipoib_workqueue,
&priv->pkey_poll_task,
HZ);
mutex_unlock(&pkey_mutex);
return 1;
}
return 0;
}