* [PATCH net-next v2 1/2] enic: implement frag allocator
From: Govindarajulu Varadarajan @ 2015-02-11 12:59 UTC (permalink / raw)
To: davem, netdev; +Cc: benve, ssujith, Govindarajulu Varadarajan
In-Reply-To: <1423659558-32523-1-git-send-email-_govind@gmx.com>
This patch implements frag allocator for rq buffer. This is based on
__alloc_page_frag & __page_frag_refill implementation in net/core/skbuff.c
In addition to frag allocation from order(3) page in __alloc_page_frag,
we also maintain dma address of the page. While allocating a frag for rx buffer
we return va + offset for virtual address of the frag, and pa + offset for
dma address of the frag. This reduces the number of calls to dma_map()
by 1/3 for 9k mtu and by 1/20 for 1500 mtu.
__alloc_page_frag is limited to max buffer size of PAGE_SIZE, i.e 4096 in most
of the cases. So 9k buffer allocation goes through kmalloc which return
page of order 2, 16k. We waste 7k bytes for every 9k buffer.
we maintain dma_count variable which is incremented when we allocate a frag.
enic_unmap_dma will decrement the dma_count and unmap it when there is no user
of that page in rx ring.
This reduces the memory utilization for 9k mtu by 33%.
Signed-off-by: Govindarajulu Varadarajan <_govind@gmx.com>
---
drivers/net/ethernet/cisco/enic/enic.h | 15 +++
drivers/net/ethernet/cisco/enic/enic_main.c | 155 +++++++++++++++++++++++-----
drivers/net/ethernet/cisco/enic/vnic_rq.c | 13 +++
drivers/net/ethernet/cisco/enic/vnic_rq.h | 2 +
4 files changed, 161 insertions(+), 24 deletions(-)
diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h
index 84b6a2b..0f3b6327 100644
--- a/drivers/net/ethernet/cisco/enic/enic.h
+++ b/drivers/net/ethernet/cisco/enic/enic.h
@@ -20,6 +20,11 @@
#ifndef _ENIC_H_
#define _ENIC_H_
+#include <linux/if.h>
+#include <linux/if_link.h>
+#include <linux/if_ether.h>
+#include <linux/netdevice.h>
+
#include "vnic_enet.h"
#include "vnic_dev.h"
#include "vnic_wq.h"
@@ -191,6 +196,16 @@ struct enic {
struct vnic_gen_stats gen_stats;
};
+#define ENIC_ALLOC_ORDER PAGE_ALLOC_COSTLY_ORDER
+
+struct enic_alloc_cache {
+ struct page_frag frag;
+ unsigned int pagecnt_bias;
+ int dma_count;
+ void *va;
+ dma_addr_t pa;
+};
+
static inline struct device *enic_get_dev(struct enic *enic)
{
return &(enic->pdev->dev);
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 9cbe038..841571f 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -950,6 +950,105 @@ nla_put_failure:
return -EMSGSIZE;
}
+struct enic_alloc_cache *enic_page_refill(struct enic *enic, size_t sz,
+ gfp_t gfp)
+{
+ struct enic_alloc_cache *ec;
+ gfp_t gfp_comp = gfp | __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY;
+ u8 order = ENIC_ALLOC_ORDER;
+
+ ec = kzalloc(sizeof(*ec), GFP_ATOMIC);
+ if (unlikely(!ec))
+ goto no_ec;
+ ec->frag.page = alloc_pages_node(NUMA_NO_NODE, gfp_comp, order);
+ if (unlikely(!ec->frag.page)) {
+ order = get_order(sz);
+ ec->frag.page = alloc_pages_node(NUMA_NO_NODE, gfp, order);
+ if (!ec->frag.page)
+ goto free_ec;
+ }
+
+ ec->frag.size = (PAGE_SIZE << order);
+ ec->va = page_address(ec->frag.page);
+ ec->pa = pci_map_single(enic->pdev, ec->va, ec->frag.size,
+ PCI_DMA_FROMDEVICE);
+ if (unlikely(enic_dma_map_check(enic, ec->pa)))
+ goto free_page;
+ atomic_add(ec->frag.size - 1, &ec->frag.page->_count);
+ ec->pagecnt_bias = ec->frag.size;
+ ec->frag.offset = ec->frag.size;
+
+ return ec;
+
+free_page:
+ __free_pages(ec->frag.page, order);
+free_ec:
+ kfree(ec);
+no_ec:
+ return NULL;
+}
+
+struct enic_alloc_cache *enic_alloc_frag(struct vnic_rq *rq, size_t sz)
+{
+ struct enic *enic = vnic_dev_priv(rq->vdev);
+ struct enic_alloc_cache *ec = rq->ec;
+ int offset;
+
+ if (unlikely(!ec)) {
+refill:
+ ec = enic_page_refill(enic, sz, GFP_ATOMIC);
+ rq->ec = ec;
+
+ if (unlikely(!ec))
+ return NULL;
+ }
+
+ offset = ec->frag.offset - sz;
+ if (offset < 0) {
+ if (!atomic_sub_and_test(ec->pagecnt_bias,
+ &ec->frag.page->_count)) {
+ /* rq cleanup service has processed all the frags
+ * belonging to this page. Since page->_count is not 0
+ * and ec->dma_count is 0 these frags should be in
+ * stack. We should unmap the page here.
+ */
+ if (!ec->dma_count) {
+ pci_unmap_single(enic->pdev, ec->pa,
+ ec->frag.size,
+ PCI_DMA_FROMDEVICE);
+ kfree(ec);
+ } else {
+ /* frags from this page are still in rx queue. Let the
+ * rx cleanup service unmap the page in enic_unmap_dma.
+ */
+ ec->pagecnt_bias = 0;
+ }
+ goto refill;
+ }
+ WARN_ON(ec->dma_count);
+ atomic_set(&ec->frag.page->_count, ec->frag.size);
+ ec->pagecnt_bias = ec->frag.size;
+ offset = ec->frag.size - sz;
+ }
+ ec->pagecnt_bias--;
+ ec->dma_count++;
+ ec->frag.offset = offset;
+
+ return ec;
+}
+
+void enic_unmap_dma(struct enic *enic, struct enic_alloc_cache *ec)
+{
+ /* enic_alloc_frag is done using this page. We should be free to unmap
+ * the page if there are no pending frags in the queue.
+ */
+ if (!--ec->dma_count && !ec->pagecnt_bias) {
+ pci_unmap_single(enic->pdev, ec->pa, ec->frag.size,
+ PCI_DMA_FROMDEVICE);
+ kfree(ec);
+ }
+}
+
static void enic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf)
{
struct enic *enic = vnic_dev_priv(rq->vdev);
@@ -957,8 +1056,7 @@ static void enic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf)
if (!buf->os_buf)
return;
- pci_unmap_single(enic->pdev, buf->dma_addr,
- buf->len, PCI_DMA_FROMDEVICE);
+ enic_unmap_dma(enic, buf->ec);
dev_kfree_skb_any(buf->os_buf);
buf->os_buf = NULL;
}
@@ -968,10 +1066,12 @@ static int enic_rq_alloc_buf(struct vnic_rq *rq)
struct enic *enic = vnic_dev_priv(rq->vdev);
struct net_device *netdev = enic->netdev;
struct sk_buff *skb;
- unsigned int len = netdev->mtu + VLAN_ETH_HLEN;
+ unsigned int len;
unsigned int os_buf_index = 0;
dma_addr_t dma_addr;
struct vnic_rq_buf *buf = rq->to_use;
+ struct enic_alloc_cache *ec;
+ void *va;
if (buf->os_buf) {
enic_queue_rq_desc(rq, buf->os_buf, os_buf_index, buf->dma_addr,
@@ -979,21 +1079,33 @@ static int enic_rq_alloc_buf(struct vnic_rq *rq)
return 0;
}
- skb = netdev_alloc_skb_ip_align(netdev, len);
- if (!skb)
- return -ENOMEM;
- dma_addr = pci_map_single(enic->pdev, skb->data, len,
- PCI_DMA_FROMDEVICE);
- if (unlikely(enic_dma_map_check(enic, dma_addr))) {
- dev_kfree_skb(skb);
- return -ENOMEM;
- }
+ len = netdev->mtu + VLAN_ETH_HLEN + NET_IP_ALIGN + NET_SKB_PAD;
+ len = SKB_DATA_ALIGN(len) +
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
- enic_queue_rq_desc(rq, skb, os_buf_index,
- dma_addr, len);
+ ec = enic_alloc_frag(rq, len);
+ if (unlikely(!ec))
+ goto alloc_fail;
+ va = ec->va + ec->frag.offset;
+ skb = build_skb(va, len);
+ if (unlikely(!skb)) {
+ ec->pagecnt_bias++;
+ ec->frag.offset += len;
+ ec->dma_count--;
+
+ goto alloc_fail;
+ }
+ skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
+ dma_addr = ec->pa + ec->frag.offset + NET_SKB_PAD + NET_IP_ALIGN;
+ buf->ec = ec;
+ enic_queue_rq_desc(rq, skb, os_buf_index, dma_addr,
+ netdev->mtu + VLAN_ETH_HLEN);
return 0;
+
+alloc_fail:
+ return -ENOMEM;
}
static void enic_intr_update_pkt_size(struct vnic_rx_bytes_counter *pkt_size,
@@ -1016,8 +1128,6 @@ static bool enic_rxcopybreak(struct net_device *netdev, struct sk_buff **skb,
new_skb = netdev_alloc_skb_ip_align(netdev, len);
if (!new_skb)
return false;
- pci_dma_sync_single_for_cpu(enic->pdev, buf->dma_addr, len,
- DMA_FROM_DEVICE);
memcpy(new_skb->data, (*skb)->data, len);
*skb = new_skb;
@@ -1065,8 +1175,7 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq,
enic->rq_truncated_pkts++;
}
- pci_unmap_single(enic->pdev, buf->dma_addr, buf->len,
- PCI_DMA_FROMDEVICE);
+ enic_unmap_dma(enic, buf->ec);
dev_kfree_skb_any(skb);
buf->os_buf = NULL;
@@ -1077,11 +1186,11 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq,
/* Good receive
*/
-
+ pci_dma_sync_single_for_cpu(enic->pdev, buf->dma_addr,
+ bytes_written, DMA_FROM_DEVICE);
if (!enic_rxcopybreak(netdev, &skb, buf, bytes_written)) {
buf->os_buf = NULL;
- pci_unmap_single(enic->pdev, buf->dma_addr, buf->len,
- PCI_DMA_FROMDEVICE);
+ enic_unmap_dma(enic, buf->ec);
}
prefetch(skb->data - NET_IP_ALIGN);
@@ -1122,9 +1231,7 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq,
/* Buffer overflow
*/
-
- pci_unmap_single(enic->pdev, buf->dma_addr, buf->len,
- PCI_DMA_FROMDEVICE);
+ enic_unmap_dma(enic, buf->ec);
dev_kfree_skb_any(skb);
buf->os_buf = NULL;
}
diff --git a/drivers/net/ethernet/cisco/enic/vnic_rq.c b/drivers/net/ethernet/cisco/enic/vnic_rq.c
index 36a2ed6..c31669f 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_rq.c
+++ b/drivers/net/ethernet/cisco/enic/vnic_rq.c
@@ -26,6 +26,7 @@
#include "vnic_dev.h"
#include "vnic_rq.h"
+#include "enic.h"
static int vnic_rq_alloc_bufs(struct vnic_rq *rq)
{
@@ -199,6 +200,18 @@ void vnic_rq_clean(struct vnic_rq *rq,
rq->ring.desc_avail++;
}
+ if (rq->ec) {
+ struct enic *enic = vnic_dev_priv(rq->vdev);
+ struct enic_alloc_cache *ec = rq->ec;
+
+ WARN_ON(ec->dma_count);
+ pci_unmap_single(enic->pdev, ec->pa, ec->frag.size,
+ PCI_DMA_FROMDEVICE);
+ atomic_sub(ec->pagecnt_bias - 1, &ec->frag.page->_count);
+ __free_pages(ec->frag.page, get_order(ec->frag.size));
+ kfree(ec);
+ rq->ec = NULL;
+ }
/* Use current fetch_index as the ring starting point */
fetch_index = ioread32(&rq->ctrl->fetch_index);
diff --git a/drivers/net/ethernet/cisco/enic/vnic_rq.h b/drivers/net/ethernet/cisco/enic/vnic_rq.h
index 8111d52..2e4815a 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_rq.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_rq.h
@@ -73,6 +73,7 @@ struct vnic_rq_buf {
unsigned int index;
void *desc;
uint64_t wr_id;
+ struct enic_alloc_cache *ec;
};
struct vnic_rq {
@@ -100,6 +101,7 @@ struct vnic_rq {
unsigned int bpoll_state;
spinlock_t bpoll_lock;
#endif /* CONFIG_NET_RX_BUSY_POLL */
+ struct enic_alloc_cache *ec;
};
static inline unsigned int vnic_rq_desc_avail(struct vnic_rq *rq)
--
2.3.0
^ permalink raw reply related
* [PATCH net-next v2 2/2] enic: Add rq allocation failure stats
From: Govindarajulu Varadarajan @ 2015-02-11 12:59 UTC (permalink / raw)
To: davem, netdev; +Cc: benve, ssujith, Govindarajulu Varadarajan
In-Reply-To: <1423659558-32523-1-git-send-email-_govind@gmx.com>
This patch adds rq buff allocation failure stats.
cache_alloc_err: incremented when higher order page allocation fails.
enic_rq_alloc_buf: incremented rq buff fails. Either due to page alloc
failure or build_skb.
Signed-off-by: Govindarajulu Varadarajan <_govind@gmx.com>
---
drivers/net/ethernet/cisco/enic/enic_ethtool.c | 2 ++
drivers/net/ethernet/cisco/enic/enic_main.c | 3 +++
drivers/net/ethernet/cisco/enic/vnic_stats.h | 2 ++
3 files changed, 7 insertions(+)
diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
index 28d9ca6..c804e6c 100644
--- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c
+++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
@@ -86,6 +86,8 @@ static const struct enic_stat enic_rx_stats[] = {
static const struct enic_stat enic_gen_stats[] = {
ENIC_GEN_STAT(dma_map_error),
+ ENIC_GEN_STAT(cache_alloc_err),
+ ENIC_GEN_STAT(rq_alloc_err),
};
static const unsigned int enic_n_tx_stats = ARRAY_SIZE(enic_tx_stats);
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 841571f..b92bfe4 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -962,6 +962,7 @@ struct enic_alloc_cache *enic_page_refill(struct enic *enic, size_t sz,
goto no_ec;
ec->frag.page = alloc_pages_node(NUMA_NO_NODE, gfp_comp, order);
if (unlikely(!ec->frag.page)) {
+ enic->gen_stats.cache_alloc_err++;
order = get_order(sz);
ec->frag.page = alloc_pages_node(NUMA_NO_NODE, gfp, order);
if (!ec->frag.page)
@@ -1105,6 +1106,8 @@ static int enic_rq_alloc_buf(struct vnic_rq *rq)
return 0;
alloc_fail:
+ enic->gen_stats.rq_alloc_err++;
+
return -ENOMEM;
}
diff --git a/drivers/net/ethernet/cisco/enic/vnic_stats.h b/drivers/net/ethernet/cisco/enic/vnic_stats.h
index 74c81ed..b2a4528 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_stats.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_stats.h
@@ -65,6 +65,8 @@ struct vnic_rx_stats {
/* Generic statistics */
struct vnic_gen_stats {
u64 dma_map_error;
+ u64 cache_alloc_err; /* alloc_pages(enic->order) failures */
+ u64 rq_alloc_err; /* rq buf + skb alloc failures */
};
struct vnic_stats {
--
2.3.0
^ permalink raw reply related
* [PATCH] ipv6: fix possible deadlock in ip6_fl_purge / ip6_fl_gc
From: Jan Stancek @ 2015-02-11 13:06 UTC (permalink / raw)
To: netdev; +Cc: linux-kernel, jstancek
Use spin_lock_bh in ip6_fl_purge() to prevent following potentially
deadlock scenario between ip6_fl_purge() and ip6_fl_gc() timer.
=================================
[ INFO: inconsistent lock state ]
3.19.0 #1 Not tainted
---------------------------------
inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
swapper/5/0 [HC0[0]:SC1[1]:HE1:SE0] takes:
(ip6_fl_lock){+.?...}, at: [<ffffffff8171155d>] ip6_fl_gc+0x2d/0x180
{SOFTIRQ-ON-W} state was registered at:
[<ffffffff810ee9a0>] __lock_acquire+0x4a0/0x10b0
[<ffffffff810efd54>] lock_acquire+0xc4/0x2b0
[<ffffffff81751d2d>] _raw_spin_lock+0x3d/0x80
[<ffffffff81711798>] ip6_flowlabel_net_exit+0x28/0x110
[<ffffffff815f9759>] ops_exit_list.isra.1+0x39/0x60
[<ffffffff815fa320>] cleanup_net+0x100/0x1e0
[<ffffffff810ad80a>] process_one_work+0x20a/0x830
[<ffffffff810adf4b>] worker_thread+0x11b/0x460
[<ffffffff810b42f4>] kthread+0x104/0x120
[<ffffffff81752bfc>] ret_from_fork+0x7c/0xb0
irq event stamp: 84640
hardirqs last enabled at (84640): [<ffffffff81752080>] _raw_spin_unlock_irq+0x30/0x50
hardirqs last disabled at (84639): [<ffffffff81751eff>] _raw_spin_lock_irq+0x1f/0x80
softirqs last enabled at (84628): [<ffffffff81091ad1>] _local_bh_enable+0x21/0x50
softirqs last disabled at (84629): [<ffffffff81093b7d>] irq_exit+0x12d/0x150
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(ip6_fl_lock);
<Interrupt>
lock(ip6_fl_lock);
*** DEADLOCK ***
Signed-off-by: Jan Stancek <jstancek@redhat.com>
---
net/ipv6/ip6_flowlabel.c | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 2f780cb..f45d6db 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -172,7 +172,7 @@ static void __net_exit ip6_fl_purge(struct net *net)
{
int i;
- spin_lock(&ip6_fl_lock);
+ spin_lock_bh(&ip6_fl_lock);
for (i = 0; i <= FL_HASH_MASK; i++) {
struct ip6_flowlabel *fl;
struct ip6_flowlabel __rcu **flp;
@@ -190,7 +190,7 @@ static void __net_exit ip6_fl_purge(struct net *net)
flp = &fl->next;
}
}
- spin_unlock(&ip6_fl_lock);
+ spin_unlock_bh(&ip6_fl_lock);
}
static struct ip6_flowlabel *fl_intern(struct net *net,
--
1.7.1
^ permalink raw reply related
* Re: Throughput regression with `tcp: refine TSO autosizing`
From: Eric Dumazet @ 2015-02-11 13:17 UTC (permalink / raw)
To: Michal Kazior
Cc: Neal Cardwell, linux-wireless, Network Development, Eyal Perry
In-Reply-To: <CA+BoTQkRp38nttSJgKs4dzQrn-TXpPbh4i-01YCF0BJQWrFi=Q@mail.gmail.com>
On Wed, 2015-02-11 at 09:33 +0100, Michal Kazior wrote:
> If I set tcp_limit_output_bytes to 700K+ I can get ath10k w/ cushion
> w/ aggregation to reach 600mbps on a single flow.
You know, there is a reason this sysctl exists in the first place ;)
The first suggestion I made to you was to raise it.
The default setting must stay as is as long default Qdisc is pfifo_fast.
I believe I already mentioned skb->truesize tricks for drivers willing
to adjust the TSQ given their constraints.
--
To unsubscribe from this list: send the line "unsubscribe linux-wireless" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH net-next] sunvnet: don't change gso data on clones
From: David L Stevens @ 2015-02-11 13:20 UTC (permalink / raw)
To: David Miller; +Cc: netdev
This patch unclones an skb for the case where the sunvnet driver needs to
change the segmentation size so that it doesn't interfere with TCP SACK's
use of them.
Signed-off-by: David L Stevens <david.stevens@oracle.com>
---
drivers/net/ethernet/sun/sunvnet.c | 23 ++++++++++-------------
1 files changed, 10 insertions(+), 13 deletions(-)
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index 2b10b85..22e0cad 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -1192,23 +1192,16 @@ static int vnet_handle_offloads(struct vnet_port *port, struct sk_buff *skb)
skb_pull(skb, maclen);
if (port->tso && gso_size < datalen) {
+ if (skb_unclone(skb, GFP_ATOMIC))
+ goto out_dropped;
+
/* segment to TSO size */
skb_shinfo(skb)->gso_size = datalen;
skb_shinfo(skb)->gso_segs = gso_segs;
-
- segs = skb_gso_segment(skb, dev->features & ~NETIF_F_TSO);
-
- /* restore gso_size & gso_segs */
- skb_shinfo(skb)->gso_size = gso_size;
- skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len - hlen,
- gso_size);
- } else
- segs = skb_gso_segment(skb, dev->features & ~NETIF_F_TSO);
- if (IS_ERR(segs)) {
- dev->stats.tx_dropped++;
- dev_kfree_skb_any(skb);
- return NETDEV_TX_OK;
}
+ segs = skb_gso_segment(skb, dev->features & ~NETIF_F_TSO);
+ if (IS_ERR(segs))
+ goto out_dropped;
skb_push(skb, maclen);
skb_reset_mac_header(skb);
@@ -1246,6 +1239,10 @@ static int vnet_handle_offloads(struct vnet_port *port, struct sk_buff *skb)
if (!(status & NETDEV_TX_MASK))
dev_kfree_skb_any(skb);
return status;
+out_dropped:
+ dev->stats.tx_dropped++;
+ dev_kfree_skb_any(skb);
+ return NETDEV_TX_OK;
}
static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev)
--
1.7.1
^ permalink raw reply related
* Re: [PATCH net-next 1/3] r8152: separate USB_RX_EARLY_AGG
From: Sergei Shtylyov @ 2015-02-11 13:52 UTC (permalink / raw)
To: Hayes Wang, netdev-u79uwXL29TY76Z2rM5mHXA
Cc: nic_swsd-Rasf1IRRPZFBDgjK7y7TUQ,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
linux-usb-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <1394712342-15778-138-Taiwan-albertk-Rasf1IRRPZFBDgjK7y7TUQ@public.gmane.org>
Hello.
On 2/11/2015 9:46 AM, Hayes Wang wrote:
> Separate USB_RX_EARLY_AGG into USB_RX_EARLY_TIMEOUT and USB_RX_EARLY_SIZE.
> Replace r8153_set_rx_agg() with r8153_set_rx_early_timeout() and
> r8153_set_rx_early_size().
> Set the default timeout value according to the USB speed.
> Signed-off-by: Hayes Wang <hayeswang-Rasf1IRRPZFBDgjK7y7TUQ@public.gmane.org>
> ---
> drivers/net/usb/r8152.c | 55 ++++++++++++++++++++++++++-----------------------
> 1 file changed, 29 insertions(+), 26 deletions(-)
> diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
> index 5980ac6..b043c7f 100644
> --- a/drivers/net/usb/r8152.c
> +++ b/drivers/net/usb/r8152.c
[...]
> @@ -2114,28 +2116,21 @@ static int rtl8152_enable(struct r8152 *tp)
> return rtl_enable(tp);
> }
>
> -static void r8153_set_rx_agg(struct r8152 *tp)
> +static void r8153_set_rx_early_timeout(struct r8152 *tp)
> {
> - u8 speed;
> + u32 ocp_data;
>
[...]
> + ocp_data = tp->coalesce / 8;
Why not do it in the initializer?
> + ocp_write_word(tp, MCU_TYPE_USB, USB_RX_EARLY_TIMEOUT, ocp_data);
> +}
> +
> +static void r8153_set_rx_early_size(struct r8152 *tp)
> +{
> + struct net_device *dev = tp->netdev;
Not sure you actually need this variable.
> + u32 ocp_data;
> +
> + ocp_data = (agg_buf_sz - dev->mtu - VLAN_ETH_HLEN - VLAN_HLEN) / 4;
Why not in initializer?
> + ocp_write_word(tp, MCU_TYPE_USB, USB_RX_EARLY_SIZE, ocp_data);
> }
[...]
> @@ -3911,6 +3907,13 @@ static int rtl8152_probe(struct usb_interface *intf,
> tp->mii.reg_num_mask = 0x1f;
> tp->mii.phy_id = R8152_PHY_ID;
>
> + if (udev->speed == USB_SPEED_SUPER)
> + tp->coalesce = COALESCE_SUPER;
> + else if (udev->speed == USB_SPEED_HIGH)
> + tp->coalesce = COALESCE_HIGH;
> + else
> + tp->coalesce = COALESCE_SLOW;
This is asking to be a *switch* statement.
[...]
WBR, Sergei
--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH net-next] sunvnet: don't change gso data on clones
From: Eric Dumazet @ 2015-02-11 13:56 UTC (permalink / raw)
To: David L Stevens; +Cc: David Miller, netdev
In-Reply-To: <54DB5711.3040705@oracle.com>
On Wed, 2015-02-11 at 08:20 -0500, David L Stevens wrote:
> This patch unclones an skb for the case where the sunvnet driver needs to
> change the segmentation size so that it doesn't interfere with TCP SACK's
> use of them.
>
> Signed-off-by: David L Stevens <david.stevens@oracle.com>
> ---
Hmm... this would point to a TCP bug ?
What happens if not GSO is needed, TCP corrupts data currently
read/processed by NIC/driver ?
TCP should have required skb_unclone() where needed.
^ permalink raw reply
* Re: [GIT] Networking
From: Al Viro @ 2015-02-11 14:00 UTC (permalink / raw)
To: Linus Torvalds
Cc: David Miller, Andrew Morton, Network Development,
Linux Kernel Mailing List
In-Reply-To: <CA+55aFyyMXWH1cfyB+fUX8jwngjzemiAgoZdKJogs_Pae9m+Xw@mail.gmail.com>
On Tue, Feb 10, 2015 at 08:09:29PM -0800, Linus Torvalds wrote:
> On Tue, Feb 10, 2015 at 8:02 PM, Al Viro <viro@zeniv.linux.org.uk> wrote:
> >
> > Anyway, what userland do you have?
>
> I have regular Fedora 21, nothing special.
>
> I'm *assuming* that the thing that triggers this is that I use disk
> encryption on this machine, as that's the only even remotely unusual
> thing that isn't just a bog-standard "default install"). The kernel
> oops happens basically immediately after I've typed in my decryption
> key.
Hmm... Fedora image I've got here has been upgraded from F20, and it's
definitely not configured for disk encryption. Ought to try fresh
install and throw that thing into the "test on those" pile as well.
Thanks...
^ permalink raw reply
* Re: [GIT] Networking
From: David Miller @ 2015-02-11 14:01 UTC (permalink / raw)
To: torvalds; +Cc: viro, akpm, netdev, linux-kernel
In-Reply-To: <CA+55aFyU2nxQ=8c7CdRo4EUOBwf0R2sFJ243qF94O4JSrA0nrw@mail.gmail.com>
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Tue, 10 Feb 2015 21:54:35 -0800
> Btw, I like your summaries for the networking pulls, but they don't
> tend to mention a lot of the stuff that I assume you pull from others.
> For example, there seems to have been a lot of bluetooth stuff this
> round and obviously there's just a ton of network driver work, but
> those tend to not be mentioned in your summary - presumablty because
> most of that is a few people removed. I'm wondering if you could add
> *some* mention of things like that to the summaries too?
Will do.
^ permalink raw reply
* (unknown)
From: Families Need Support @ 2015-02-11 14:04 UTC (permalink / raw)
In-Reply-To: <105649434.1938158.1423663368208.JavaMail.yahoo@mail.yahoo.com>
[-- Attachment #1: Type: text/plain, Size: 141 bytes --]
Plz this is my family help is very urgent i need your quick response.
+27731055945
Regards
Mrs. Maureen M Staker
dannystaker@gmail.com
[-- Attachment #2: Maureen Mwanawasa Staker.doc --]
[-- Type: application/msword, Size: 363520 bytes --]
^ permalink raw reply
* (unknown)
From: Families Need Support @ 2015-02-11 14:05 UTC (permalink / raw)
In-Reply-To: <227571021.1933835.1423663444450.JavaMail.yahoo@mail.yahoo.com>
[-- Attachment #1: Type: text/plain, Size: 141 bytes --]
Plz this is my family help is very urgent i need your quick response.
+27731055945
Regards
Mrs. Maureen M Staker
dannystaker@gmail.com
[-- Attachment #2: Maureen Mwanawasa Staker.doc --]
[-- Type: application/msword, Size: 363520 bytes --]
^ permalink raw reply
* Re: [PATCH] netfilter: ipset: fix boolreturn.cocci warnings
From: Pablo Neira Ayuso @ 2015-02-11 14:40 UTC (permalink / raw)
To: Jozsef Kadlecsik
Cc: kbuild-all, kbuild test robot, Patrick McHardy, netfilter-devel,
coreteam, netdev, linux-kernel
In-Reply-To: <20150211123305.GA32347@waimea>
On Wed, Feb 11, 2015 at 08:33:05PM +0800, kbuild test robot wrote:
> net/netfilter/xt_set.c:196:9-10: WARNING: return of 0/1 in function 'set_match_v3' with return type bool
> net/netfilter/xt_set.c:242:9-10: WARNING: return of 0/1 in function 'set_match_v4' with return type bool
>
> Return statements in functions returning bool should use
> true/false instead of 1/0.
> Generated by: scripts/coccinelle/misc/boolreturn.cocci
Jozsef, unless you have any objection, I'm going to apply this.
Thanks.
> CC: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
> Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
> ---
>
> xt_set.c | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> --- a/net/netfilter/xt_set.c
> +++ b/net/netfilter/xt_set.c
> @@ -193,7 +193,7 @@ set_match_v3(const struct sk_buff *skb,
> return ret;
>
> if (!match_counter0(opt.ext.packets, &info->packets))
> - return 0;
> + return false;
> return match_counter0(opt.ext.bytes, &info->bytes);
> }
>
> @@ -239,7 +239,7 @@ set_match_v4(const struct sk_buff *skb,
> return ret;
>
> if (!match_counter(opt.ext.packets, &info->packets))
> - return 0;
> + return false;
> return match_counter(opt.ext.bytes, &info->bytes);
> }
>
^ permalink raw reply
* [PATCH net] net/mlx5_core: Fix configuration of log_uar_page_sz
From: Eli Cohen @ 2015-02-11 14:40 UTC (permalink / raw)
To: davem; +Cc: netdev, clsoto, ogerlitz
The current code failed to configure the page size for architectures with page
size different than 4K - PPC for example.
Signed-off-by: Carol L Soto <clsoto@us.ibm.com>
Signed-off-by: Eli Cohen <eli@mellanox.com>
---
Hi Dave,
this patch fixes a problem in powerpc with 64K page size
Eli
drivers/net/ethernet/mellanox/mlx5/core/main.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 3a85904932e7..52d3afd6d548 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -290,6 +290,7 @@ static void copy_rw_fields(void *to, struct mlx5_caps *from)
MLX5_SET(cmd_hca_cap, to, log_max_ra_req_dc, from->gen.log_max_ra_req_dc);
MLX5_SET(cmd_hca_cap, to, log_max_ra_res_dc, from->gen.log_max_ra_res_dc);
MLX5_SET(cmd_hca_cap, to, pkey_table_size, to_fw_pkey_sz(from->gen.pkey_table_size));
+ MLX5_SET(cmd_hca_cap, to, log_uar_page_sz, PAGE_SHIFT - 12);
v64 = from->gen.flags & MLX5_CAP_BITS_RW_MASK;
*flags_off = cpu_to_be64(v64);
}
--
2.3.0
^ permalink raw reply related
* Re: [PATCH] netfilter: ipset: fix boolreturn.cocci warnings
From: Jozsef Kadlecsik @ 2015-02-11 14:50 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: kbuild-all, kbuild test robot, Patrick McHardy, netfilter-devel,
coreteam, netdev, linux-kernel
In-Reply-To: <20150211144016.GB3919@salvia>
On Wed, 11 Feb 2015, Pablo Neira Ayuso wrote:
> On Wed, Feb 11, 2015 at 08:33:05PM +0800, kbuild test robot wrote:
> > net/netfilter/xt_set.c:196:9-10: WARNING: return of 0/1 in function 'set_match_v3' with return type bool
> > net/netfilter/xt_set.c:242:9-10: WARNING: return of 0/1 in function 'set_match_v4' with return type bool
> >
> > Return statements in functions returning bool should use
> > true/false instead of 1/0.
> > Generated by: scripts/coccinelle/misc/boolreturn.cocci
>
> Jozsef, unless you have any objection, I'm going to apply this.
No objection, just go ahead.
Acked-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Best regards,
Jozsef
> > CC: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
> > Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
> > ---
> >
> > xt_set.c | 4 ++--
> > 1 file changed, 2 insertions(+), 2 deletions(-)
> >
> > --- a/net/netfilter/xt_set.c
> > +++ b/net/netfilter/xt_set.c
> > @@ -193,7 +193,7 @@ set_match_v3(const struct sk_buff *skb,
> > return ret;
> >
> > if (!match_counter0(opt.ext.packets, &info->packets))
> > - return 0;
> > + return false;
> > return match_counter0(opt.ext.bytes, &info->bytes);
> > }
> >
> > @@ -239,7 +239,7 @@ set_match_v4(const struct sk_buff *skb,
> > return ret;
> >
> > if (!match_counter(opt.ext.packets, &info->packets))
> > - return 0;
> > + return false;
> > return match_counter(opt.ext.bytes, &info->bytes);
> > }
> >
>
-
E-mail : kadlec@blackhole.kfki.hu, kadlecsik.jozsef@wigner.mta.hu
PGP key : http://www.kfki.hu/~kadlec/pgp_public_key.txt
Address : Wigner Research Centre for Physics, Hungarian Academy of Sciences
H-1525 Budapest 114, POB. 49, Hungary
^ permalink raw reply
* [PATCH v1 03/10] IB/core: Find the network namespace matching connection parameters
From: Shachar Raindel @ 2015-02-11 15:06 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A, sean.hefty-ral2JQCrhuEAvxtiuMwx3w
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, netdev-u79uwXL29TY76Z2rM5mHXA,
liranl-VPRAkNaXOzVWk0Htik3J/w, guysh-VPRAkNaXOzVWk0Htik3J/w,
haggaie-VPRAkNaXOzVWk0Htik3J/w, yotamke-VPRAkNaXOzVWk0Htik3J/w,
raindel-VPRAkNaXOzVWk0Htik3J/w
In-Reply-To: <1423667204-8807-1-git-send-email-raindel-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
From: Yotam Kenneth <yotamke-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
In the case of IPoIB, and maybe in other cases, the network device is
managed by an upper-layer protocol (ULP). In order to expose this
network device to other users of the IB device, let ULPs implement
a callback that returns network device according to connection parameters.
The IB device and port, together with the P_Key and the IP address should be
enough to uniquely identify the ULP net device.
This function is passed to ib_core as part of the ib_client
registration.
Using this functionality, add a way to get the network namespace
corresponding to a work completion. This is needed so that responses to CM
requests can be sent from the same network namespace as the request.
Signed-off-by: Haggai Eran <haggaie-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Yotam Kenneth <yotamke-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Shachar Raindel <raindel-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Guy Shapiro <guysh-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/infiniband/core/device.c | 57 ++++++++++++++++++++++++++++++++++++++++
include/rdma/ib_verbs.h | 29 ++++++++++++++++++++
2 files changed, 86 insertions(+)
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 18c1ece..2f06be5 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -38,6 +38,7 @@
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/mutex.h>
+#include <linux/netdevice.h>
#include <rdma/rdma_netlink.h>
#include "core_priv.h"
@@ -733,6 +734,62 @@ int ib_find_pkey(struct ib_device *device,
}
EXPORT_SYMBOL(ib_find_pkey);
+static struct net_device *ib_get_net_dev_by_port_pkey_ip(struct ib_device *dev,
+ u8 port,
+ u16 pkey,
+ struct sockaddr *addr)
+{
+ struct net_device *ret = NULL;
+ struct ib_client *client;
+
+ mutex_lock(&device_mutex);
+ list_for_each_entry(client, &client_list, list)
+ if (client->get_net_device_by_port_pkey_ip) {
+ ret = client->get_net_device_by_port_pkey_ip(dev, port,
+ pkey,
+ addr);
+ if (ret)
+ break;
+ }
+
+ mutex_unlock(&device_mutex);
+ return ret;
+}
+
+struct net *ib_get_net_ns_by_port_pkey_ip(struct ib_device *dev,
+ u8 port,
+ u16 pkey,
+ struct sockaddr *addr)
+{
+ struct net_device *ndev = NULL;
+ struct net *ns;
+
+ switch (rdma_port_get_link_layer(dev, port)) {
+ case IB_LINK_LAYER_INFINIBAND:
+ if (!addr)
+ goto not_found;
+ ndev = ib_get_net_dev_by_port_pkey_ip(dev, port, pkey, addr);
+ break;
+ default:
+ goto not_found;
+ }
+
+ if (!ndev)
+ goto not_found;
+
+ rcu_read_lock();
+ ns = maybe_get_net(dev_net(ndev));
+ dev_put(ndev);
+ rcu_read_unlock();
+ if (!ns)
+ goto not_found;
+ return ns;
+
+not_found:
+ return get_net(&init_net);
+}
+EXPORT_SYMBOL(ib_get_net_ns_by_port_pkey_ip);
+
static int __init ib_core_init(void)
{
int ret;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index f4a85de..74b2394 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1683,6 +1683,21 @@ struct ib_client {
void (*add) (struct ib_device *);
void (*remove)(struct ib_device *);
+ /* Returns the net_dev belonging to this ib_client and matching the
+ * given parameters.
+ * @dev: An RDMA device that the net_dev use for communication.
+ * @port: A physical port number on the RDMA device.
+ * @pkey: P_Key that the net_dev uses if applicable.
+ * @addr: An IP address the net_dev is configured with.
+ *
+ * An ib_client that implements a net_dev on top of RDMA devices
+ * (such as IP over IB) should implement this callback, allowing the
+ * rdma_cm module to find the right net_dev for a given request. */
+ struct net_device *(*get_net_device_by_port_pkey_ip)(
+ struct ib_device *dev,
+ u8 port,
+ u16 pkey,
+ struct sockaddr *addr);
struct list_head list;
};
@@ -2679,4 +2694,18 @@ static inline int ib_check_mr_access(int flags)
int ib_check_mr_status(struct ib_mr *mr, u32 check_mask,
struct ib_mr_status *mr_status);
+/**
+ * ib_get_net_ns_by_port_pkey_ip() - Return the appropriate net namespace
+ * for a received CM request
+ * @dev: An RDMA device on which the request has been received.
+ * @port: Port number on the RDMA device.
+ * @pkey: The Pkey the request came on.
+ * @addr: Contains the IP address that the request specified as its
+ * destination.
+ */
+struct net *ib_get_net_ns_by_port_pkey_ip(struct ib_device *dev,
+ u8 port,
+ u16 pkey,
+ struct sockaddr *addr);
+
#endif /* IB_VERBS_H */
--
1.7.11.2
--
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
^ permalink raw reply related
* [PATCH v1 09/10] IB/ucma: Take the network namespace from the process
From: Shachar Raindel @ 2015-02-11 15:06 UTC (permalink / raw)
To: roland-DgEjT+Ai2ygdnm+yROfE0A, sean.hefty-ral2JQCrhuEAvxtiuMwx3w
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA, netdev-u79uwXL29TY76Z2rM5mHXA,
liranl-VPRAkNaXOzVWk0Htik3J/w, guysh-VPRAkNaXOzVWk0Htik3J/w,
haggaie-VPRAkNaXOzVWk0Htik3J/w, yotamke-VPRAkNaXOzVWk0Htik3J/w,
raindel-VPRAkNaXOzVWk0Htik3J/w
In-Reply-To: <1423667204-8807-1-git-send-email-raindel-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
From: Guy Shapiro <guysh-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Add support for network namespaces from user space. This is done by passing
the network namespace of the process instead of init_net.
Signed-off-by: Haggai Eran <haggaie-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Yotam Kenneth <yotamke-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Shachar Raindel <raindel-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Guy Shapiro <guysh-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
drivers/infiniband/core/ucma.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index de755f2..d25a209 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -42,6 +42,7 @@
#include <linux/slab.h>
#include <linux/sysctl.h>
#include <linux/module.h>
+#include <linux/nsproxy.h>
#include <rdma/rdma_user_cm.h>
#include <rdma/ib_marshall.h>
@@ -392,7 +393,7 @@ static ssize_t ucma_create_id(struct ucma_file *file, const char __user *inbuf,
ctx->uid = cmd.uid;
ctx->cm_id = rdma_create_id(ucma_event_handler, ctx, cmd.ps, qp_type,
- &init_net);
+ current->nsproxy->net_ns);
if (IS_ERR(ctx->cm_id)) {
ret = PTR_ERR(ctx->cm_id);
goto err1;
--
1.7.11.2
--
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
^ permalink raw reply related
* Re: [GIT PULL nf-next] IPVS Enhancements for v3.20
From: Pablo Neira Ayuso @ 2015-02-11 15:10 UTC (permalink / raw)
To: Simon Horman
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov
In-Reply-To: <1423549929-25064-1-git-send-email-horms@verge.net.au>
On Tue, Feb 10, 2015 at 03:32:08PM +0900, Simon Horman wrote:
> Hi Pablo,
>
> please consider this enhancement for v3.20.
>
> It adds support for 64-bit rates in IPVS statistics.
>
>
> The following changes since commit 4c1017aa80c95a74703139bb95c4ce0d130efe4d:
>
> netfilter: nft_lookup: add missing attribute validation for NFTA_LOOKUP_SET_ID (2015-01-30 19:08:20 +0100)
>
> are available in the git repository at:
>
> https://git.kernel.org/pub/scm/linux/kernel/git/horms/ipvs-next.git tags/ipvs-for-v3.20
Pulled, thanks.
If merge window closes (I still have a little pending request), I'll
keep this in nf-next until it reopens again for the next round.
^ permalink raw reply
* [PATCH v1 02/10] IB/core: Pass network namespace as a parameter to relevant functions
From: Shachar Raindel @ 2015-02-11 15:06 UTC (permalink / raw)
To: roland, sean.hefty
Cc: linux-rdma, netdev, liranl, guysh, haggaie, yotamke, raindel
In-Reply-To: <1423667204-8807-1-git-send-email-raindel@mellanox.com>
From: Guy Shapiro <guysh@mellanox.com>
Add network namespace parameters for the address related ib_core
functions. The parameter is passed to lower level function, instead of
&init_net, so things are done in the correct namespace.
For now pass &init_net on every caller.
Callers that will pass &init_net permanently are marked with an
appropriate comment.
Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Yotam Kenneth <yotamke@mellanox.com>
Signed-off-by: Shachar Raindel <raindel@mellanox.com>
Signed-off-by: Guy Shapiro <guysh@mellanox.com>
---
drivers/infiniband/core/agent.c | 4 +++-
drivers/infiniband/core/cm.c | 9 +++++++--
drivers/infiniband/core/mad_rmpp.c | 10 ++++++++--
drivers/infiniband/core/user_mad.c | 4 +++-
drivers/infiniband/core/verbs.c | 10 ++++++----
drivers/infiniband/ulp/srpt/ib_srpt.c | 3 ++-
include/rdma/ib_verbs.h | 15 +++++++++++++--
7 files changed, 42 insertions(+), 13 deletions(-)
diff --git a/drivers/infiniband/core/agent.c b/drivers/infiniband/core/agent.c
index f6d2961..539378d 100644
--- a/drivers/infiniband/core/agent.c
+++ b/drivers/infiniband/core/agent.c
@@ -99,7 +99,9 @@ void agent_send_response(struct ib_mad *mad, struct ib_grh *grh,
}
agent = port_priv->agent[qpn];
- ah = ib_create_ah_from_wc(agent->qp->pd, wc, grh, port_num);
+ /* Physical devices (and their MAD replies) always reside in the host
+ * network namespace */
+ ah = ib_create_ah_from_wc(agent->qp->pd, wc, grh, port_num, &init_net);
if (IS_ERR(ah)) {
dev_err(&device->dev, "ib_create_ah_from_wc error %ld\n",
PTR_ERR(ah));
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index e28a494..5a45cb7 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -290,8 +290,13 @@ static int cm_alloc_response_msg(struct cm_port *port,
struct ib_mad_send_buf *m;
struct ib_ah *ah;
+ /* For IB, the network namespace doesn't affect the created address
+ * handle, so we use &init_net. In the future, RoCE support will
+ * require finding a specific network namespace to send the response
+ * from. */
ah = ib_create_ah_from_wc(port->mad_agent->qp->pd, mad_recv_wc->wc,
- mad_recv_wc->recv_buf.grh, port->port_num);
+ mad_recv_wc->recv_buf.grh, port->port_num,
+ &init_net);
if (IS_ERR(ah))
return PTR_ERR(ah);
@@ -346,7 +351,7 @@ static void cm_init_av_for_response(struct cm_port *port, struct ib_wc *wc,
av->port = port;
av->pkey_index = wc->pkey_index;
ib_init_ah_from_wc(port->cm_dev->ib_device, port->port_num, wc,
- grh, &av->ah_attr);
+ grh, &av->ah_attr, &init_net);
}
static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av)
diff --git a/drivers/infiniband/core/mad_rmpp.c b/drivers/infiniband/core/mad_rmpp.c
index f37878c..6c15762 100644
--- a/drivers/infiniband/core/mad_rmpp.c
+++ b/drivers/infiniband/core/mad_rmpp.c
@@ -157,8 +157,11 @@ static struct ib_mad_send_buf *alloc_response_msg(struct ib_mad_agent *agent,
struct ib_ah *ah;
int hdr_len;
+ /* Physical devices (and their MAD replies) always reside in the host
+ * network namespace */
ah = ib_create_ah_from_wc(agent->qp->pd, recv_wc->wc,
- recv_wc->recv_buf.grh, agent->port_num);
+ recv_wc->recv_buf.grh, agent->port_num,
+ &init_net);
if (IS_ERR(ah))
return (void *) ah;
@@ -287,10 +290,13 @@ create_rmpp_recv(struct ib_mad_agent_private *agent,
if (!rmpp_recv)
return NULL;
+ /* Physical devices (and their MAD replies) always reside in the host
+ * network namespace */
rmpp_recv->ah = ib_create_ah_from_wc(agent->agent.qp->pd,
mad_recv_wc->wc,
mad_recv_wc->recv_buf.grh,
- agent->agent.port_num);
+ agent->agent.port_num,
+ &init_net);
if (IS_ERR(rmpp_recv->ah))
goto error;
diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c
index 928cdd2..f34c607 100644
--- a/drivers/infiniband/core/user_mad.c
+++ b/drivers/infiniband/core/user_mad.c
@@ -239,7 +239,9 @@ static void recv_handler(struct ib_mad_agent *agent,
ib_init_ah_from_wc(agent->device, agent->port_num,
mad_recv_wc->wc, mad_recv_wc->recv_buf.grh,
- &ah_attr);
+ &ah_attr, &init_net);
+ /* Note that network namespace seperation isn't supported on
+ * umad yet. */
packet->mad.hdr.gid_index = ah_attr.grh.sgid_index;
packet->mad.hdr.hop_limit = ah_attr.grh.hop_limit;
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index ca5c4dd..a51d5d6 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -193,7 +193,8 @@ struct ib_ah *ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr)
EXPORT_SYMBOL(ib_create_ah);
int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, struct ib_wc *wc,
- struct ib_grh *grh, struct ib_ah_attr *ah_attr)
+ struct ib_grh *grh, struct ib_ah_attr *ah_attr,
+ struct net *net)
{
u32 flow_class;
u16 gid_index;
@@ -214,7 +215,7 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, struct ib_wc *wc,
ret = rdma_addr_find_dmac_by_grh(&grh->dgid, &grh->sgid,
ah_attr->dmac,
&ah_attr->vlan_id,
- &init_net);
+ net);
if (ret)
return ret;
}
@@ -247,12 +248,13 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, struct ib_wc *wc,
EXPORT_SYMBOL(ib_init_ah_from_wc);
struct ib_ah *ib_create_ah_from_wc(struct ib_pd *pd, struct ib_wc *wc,
- struct ib_grh *grh, u8 port_num)
+ struct ib_grh *grh, u8 port_num,
+ struct net *net)
{
struct ib_ah_attr ah_attr;
int ret;
- ret = ib_init_ah_from_wc(pd->device, port_num, wc, grh, &ah_attr);
+ ret = ib_init_ah_from_wc(pd->device, port_num, wc, grh, &ah_attr, net);
if (ret)
return ERR_PTR(ret);
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index eb694dd..7867bd5 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -468,7 +468,8 @@ static void srpt_mad_recv_handler(struct ib_mad_agent *mad_agent,
return;
ah = ib_create_ah_from_wc(mad_agent->qp->pd, mad_wc->wc,
- mad_wc->recv_buf.grh, mad_agent->port_num);
+ mad_wc->recv_buf.grh, mad_agent->port_num,
+ &init_net);
if (IS_ERR(ah))
goto err;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 65994a1..f4a85de 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -48,6 +48,7 @@
#include <linux/rwsem.h>
#include <linux/scatterlist.h>
#include <linux/workqueue.h>
+#include <net/net_namespace.h>
#include <uapi/linux/if_ether.h>
#include <linux/atomic.h>
@@ -1798,9 +1799,14 @@ struct ib_ah *ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr);
* ignored unless the work completion indicates that the GRH is valid.
* @ah_attr: Returned attributes that can be used when creating an address
* handle for replying to the message.
+ * @net: The network namespace to use for address resolution.
+ *
+ * It is the caller's responsibility to make sure the network namespace is
+ * alive until the function returns.
*/
int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, struct ib_wc *wc,
- struct ib_grh *grh, struct ib_ah_attr *ah_attr);
+ struct ib_grh *grh, struct ib_ah_attr *ah_attr,
+ struct net *net);
/**
* ib_create_ah_from_wc - Creates an address handle associated with the
@@ -1810,12 +1816,17 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, struct ib_wc *wc,
* @grh: References the received global route header. This parameter is
* ignored unless the work completion indicates that the GRH is valid.
* @port_num: The outbound port number to associate with the address.
+ * @net: The network namespace to use for address resolution.
*
* The address handle is used to reference a local or global destination
* in all UD QP post sends.
+ *
+ * It is the caller's responsibility to make sure the network namespace is
+ * alive until the function returns.
*/
struct ib_ah *ib_create_ah_from_wc(struct ib_pd *pd, struct ib_wc *wc,
- struct ib_grh *grh, u8 port_num);
+ struct ib_grh *grh, u8 port_num,
+ struct net *net);
/**
* ib_modify_ah - Modifies the address vector associated with an address
--
1.7.11.2
^ permalink raw reply related
* [PATCH v1 01/10] IB/addr: Pass network namespace as a parameter
From: Shachar Raindel @ 2015-02-11 15:06 UTC (permalink / raw)
To: roland, sean.hefty
Cc: linux-rdma, netdev, liranl, guysh, haggaie, yotamke, raindel
In-Reply-To: <1423667204-8807-1-git-send-email-raindel@mellanox.com>
From: Guy Shapiro <guysh@mellanox.com>
Add network namespace support to the ib_addr module. For that, all the address
resolution and matching should be done using the appropriate namespace instead
of init_net.
This is achieved by:
1. Adding an explicit network namespace argument to exported function that
require a namespace.
2. Saving the namespace in the rdma_addr_client structure.
3. Using it when calling networking functions.
In order to preserve the behavior of calling modules, &init_net is
passed as the parameter in calls from other modules. This is modified as
namespace support is added on more levels.
Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Yotam Kenneth <yotamke@mellanox.com>
Signed-off-by: Shachar Raindel <raindel@mellanox.com>
Signed-off-by: Guy Shapiro <guysh@mellanox.com>
---
drivers/infiniband/core/addr.c | 31 ++++++++++++----------
drivers/infiniband/core/cma.c | 4 ++-
drivers/infiniband/core/verbs.c | 14 +++++++---
drivers/infiniband/hw/ocrdma/ocrdma_ah.c | 3 ++-
include/rdma/ib_addr.h | 44 ++++++++++++++++++++++++++++----
5 files changed, 72 insertions(+), 24 deletions(-)
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index f80da50..95beaef 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -128,7 +128,7 @@ int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr,
int ret = -EADDRNOTAVAIL;
if (dev_addr->bound_dev_if) {
- dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if);
+ dev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if);
if (!dev)
return -ENODEV;
ret = rdma_copy_addr(dev_addr, dev, NULL);
@@ -137,9 +137,10 @@ int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr,
}
switch (addr->sa_family) {
- case AF_INET:
- dev = ip_dev_find(&init_net,
- ((struct sockaddr_in *) addr)->sin_addr.s_addr);
+ case AF_INET: {
+ struct sockaddr_in *addr_in = (struct sockaddr_in *)addr;
+
+ dev = ip_dev_find(dev_addr->net, addr_in->sin_addr.s_addr);
if (!dev)
return ret;
@@ -149,12 +150,12 @@ int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr,
*vlan_id = rdma_vlan_dev_vlan_id(dev);
dev_put(dev);
break;
-
+ }
#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
rcu_read_lock();
- for_each_netdev_rcu(&init_net, dev) {
- if (ipv6_chk_addr(&init_net,
+ for_each_netdev_rcu(dev_addr->net, dev) {
+ if (ipv6_chk_addr(dev_addr->net,
&((struct sockaddr_in6 *) addr)->sin6_addr,
dev, 1)) {
ret = rdma_copy_addr(dev_addr, dev, NULL);
@@ -236,7 +237,7 @@ static int addr4_resolve(struct sockaddr_in *src_in,
fl4.daddr = dst_ip;
fl4.saddr = src_ip;
fl4.flowi4_oif = addr->bound_dev_if;
- rt = ip_route_output_key(&init_net, &fl4);
+ rt = ip_route_output_key(addr->net, &fl4);
if (IS_ERR(rt)) {
ret = PTR_ERR(rt);
goto out;
@@ -278,12 +279,13 @@ static int addr6_resolve(struct sockaddr_in6 *src_in,
fl6.saddr = src_in->sin6_addr;
fl6.flowi6_oif = addr->bound_dev_if;
- dst = ip6_route_output(&init_net, NULL, &fl6);
+ dst = ip6_route_output(addr->net, NULL, &fl6);
if ((ret = dst->error))
goto put;
if (ipv6_addr_any(&fl6.saddr)) {
- ret = ipv6_dev_get_saddr(&init_net, ip6_dst_idev(dst)->dev,
+ ret = ipv6_dev_get_saddr(addr->net,
+ ip6_dst_idev(dst)->dev,
&fl6.daddr, 0, &fl6.saddr);
if (ret)
goto put;
@@ -458,7 +460,7 @@ static void resolve_cb(int status, struct sockaddr *src_addr,
}
int rdma_addr_find_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *dmac,
- u16 *vlan_id)
+ u16 *vlan_id, struct net *net)
{
int ret = 0;
struct rdma_dev_addr dev_addr;
@@ -481,6 +483,7 @@ int rdma_addr_find_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *dmac,
return ret;
memset(&dev_addr, 0, sizeof(dev_addr));
+ dev_addr.net = net;
ctx.addr = &dev_addr;
init_completion(&ctx.comp);
@@ -492,7 +495,7 @@ int rdma_addr_find_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *dmac,
wait_for_completion(&ctx.comp);
memcpy(dmac, dev_addr.dst_dev_addr, ETH_ALEN);
- dev = dev_get_by_index(&init_net, dev_addr.bound_dev_if);
+ dev = dev_get_by_index(net, dev_addr.bound_dev_if);
if (!dev)
return -ENODEV;
if (vlan_id)
@@ -502,7 +505,8 @@ int rdma_addr_find_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *dmac,
}
EXPORT_SYMBOL(rdma_addr_find_dmac_by_grh);
-int rdma_addr_find_smac_by_sgid(union ib_gid *sgid, u8 *smac, u16 *vlan_id)
+int rdma_addr_find_smac_by_sgid(union ib_gid *sgid, u8 *smac, u16 *vlan_id,
+ struct net *net)
{
int ret = 0;
struct rdma_dev_addr dev_addr;
@@ -517,6 +521,7 @@ int rdma_addr_find_smac_by_sgid(union ib_gid *sgid, u8 *smac, u16 *vlan_id)
if (ret)
return ret;
memset(&dev_addr, 0, sizeof(dev_addr));
+ dev_addr.net = net;
ret = rdma_translate_ip(&gid_addr._sockaddr, &dev_addr, vlan_id);
if (ret)
return ret;
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 6e5e11c..aeb2417 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -512,6 +512,7 @@ struct rdma_cm_id *rdma_create_id(rdma_cm_event_handler event_handler,
INIT_LIST_HEAD(&id_priv->listen_list);
INIT_LIST_HEAD(&id_priv->mc_list);
get_random_bytes(&id_priv->seq_num, sizeof id_priv->seq_num);
+ id_priv->id.route.addr.dev_addr.net = &init_net;
return &id_priv->id;
}
@@ -637,7 +638,8 @@ static int cma_modify_qp_rtr(struct rdma_id_private *id_priv,
== RDMA_TRANSPORT_IB &&
rdma_port_get_link_layer(id_priv->id.device, id_priv->id.port_num)
== IB_LINK_LAYER_ETHERNET) {
- ret = rdma_addr_find_smac_by_sgid(&sgid, qp_attr.smac, NULL);
+ ret = rdma_addr_find_smac_by_sgid(&sgid, qp_attr.smac, NULL,
+ &init_net);
if (ret)
goto out;
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index f93eb8d..ca5c4dd 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -212,7 +212,9 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, struct ib_wc *wc,
ah_attr->vlan_id = wc->vlan_id;
} else {
ret = rdma_addr_find_dmac_by_grh(&grh->dgid, &grh->sgid,
- ah_attr->dmac, &ah_attr->vlan_id);
+ ah_attr->dmac,
+ &ah_attr->vlan_id,
+ &init_net);
if (ret)
return ret;
}
@@ -882,11 +884,15 @@ int ib_resolve_eth_l2_attrs(struct ib_qp *qp,
if (!(*qp_attr_mask & IB_QP_VID))
qp_attr->vlan_id = rdma_get_vlan_id(&sgid);
} else {
- ret = rdma_addr_find_dmac_by_grh(&sgid, &qp_attr->ah_attr.grh.dgid,
- qp_attr->ah_attr.dmac, &qp_attr->vlan_id);
+ ret = rdma_addr_find_dmac_by_grh(
+ &sgid,
+ &qp_attr->ah_attr.grh.dgid,
+ qp_attr->ah_attr.dmac, &qp_attr->vlan_id,
+ &init_net);
if (ret)
goto out;
- ret = rdma_addr_find_smac_by_sgid(&sgid, qp_attr->smac, NULL);
+ ret = rdma_addr_find_smac_by_sgid(&sgid, qp_attr->smac,
+ NULL, &init_net);
if (ret)
goto out;
}
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
index f3cc8c9..debaac2 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
@@ -119,7 +119,8 @@ struct ib_ah *ocrdma_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *attr)
if (pd->uctx) {
status = rdma_addr_find_dmac_by_grh(&sgid, &attr->grh.dgid,
- attr->dmac, &attr->vlan_id);
+ attr->dmac, &attr->vlan_id,
+ &init_net);
if (status) {
pr_err("%s(): Failed to resolve dmac from gid."
"status = %d\n", __func__, status);
diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h
index ce55906..40ccf8b 100644
--- a/include/rdma/ib_addr.h
+++ b/include/rdma/ib_addr.h
@@ -47,6 +47,7 @@
#include <rdma/ib_verbs.h>
#include <rdma/ib_pack.h>
#include <net/ipv6.h>
+#include <net/net_namespace.h>
struct rdma_addr_client {
atomic_t refcount;
@@ -64,6 +65,16 @@ void rdma_addr_register_client(struct rdma_addr_client *client);
*/
void rdma_addr_unregister_client(struct rdma_addr_client *client);
+/**
+ * struct rdma_dev_addr - Contains resolved RDMA hardware addresses
+ * @src_dev_addr: Source MAC address.
+ * @dst_dev_addr: Destination MAC address.
+ * @broadcast: Broadcast address of the device.
+ * @dev_type: The interface hardware type of the device.
+ * @bound_dev_if: An optional device interface index.
+ * @transport: The transport type used.
+ * @net: Network namespace containing the bound_dev_if net_dev.
+ */
struct rdma_dev_addr {
unsigned char src_dev_addr[MAX_ADDR_LEN];
unsigned char dst_dev_addr[MAX_ADDR_LEN];
@@ -71,11 +82,14 @@ struct rdma_dev_addr {
unsigned short dev_type;
int bound_dev_if;
enum rdma_transport_type transport;
+ struct net *net;
};
/**
* rdma_translate_ip - Translate a local IP address to an RDMA hardware
* address.
+ *
+ * The dev_addr->net field must be initialized.
*/
int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr,
u16 *vlan_id);
@@ -90,7 +104,7 @@ int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr,
* @dst_addr: The destination address to resolve.
* @addr: A reference to a data location that will receive the resolved
* addresses. The data location must remain valid until the callback has
- * been invoked.
+ * been invoked. The net field of the addr struct must be valid.
* @timeout_ms: Amount of time to wait for the address resolution to complete.
* @callback: Call invoked once address resolution has completed, timed out,
* or been canceled. A status of 0 indicates success.
@@ -110,9 +124,29 @@ int rdma_copy_addr(struct rdma_dev_addr *dev_addr, struct net_device *dev,
int rdma_addr_size(struct sockaddr *addr);
-int rdma_addr_find_smac_by_sgid(union ib_gid *sgid, u8 *smac, u16 *vlan_id);
-int rdma_addr_find_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *smac,
- u16 *vlan_id);
+/** rdma_addr_find_smac_by_sgid() - Find the src MAC and VLAN ID for a src GID
+ * @sgid: Source GID to find the MAC and VLAN for.
+ * @smac: A buffer to contain the resulting MAC address.
+ * @vlan_id: Will contain the resulting VLAN ID.
+ * @net: Network namespace to use for the address resolution.
+ *
+ * It is the caller's responsibility to keep the network namespace alive until
+ * the function returns.
+ */
+int rdma_addr_find_smac_by_sgid(union ib_gid *sgid, u8 *smac, u16 *vlan_id,
+ struct net *net);
+/** rdma_addr_find_dmac_by_grh() - Find the dst MAC and VLAN ID for a GID pair
+ * @sgid: Source GID to use for the search.
+ * @dgid: Destination GID to find the details for.
+ * @dmac: Contains the resulting destination MAC address.
+ * @vlan_id: Contains the resulting VLAN ID.
+ * @net: Network namespace to use for the address resolution.
+ *
+ * It is the caller's responsibility to keep the network namespace alive until
+ * the function returns.
+ */
+int rdma_addr_find_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *dmac,
+ u16 *vlan_id, struct net *net);
static inline u16 ib_addr_get_pkey(struct rdma_dev_addr *dev_addr)
{
@@ -182,7 +216,7 @@ static inline void iboe_addr_get_sgid(struct rdma_dev_addr *dev_addr,
struct net_device *dev;
struct in_device *ip4;
- dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if);
+ dev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if);
if (dev) {
ip4 = (struct in_device *)dev->ip_ptr;
if (ip4 && ip4->ifa_list && ip4->ifa_list->ifa_address)
--
1.7.11.2
^ permalink raw reply related
* [PATCH v1 04/10] IB/ipoib: Return IPoIB devices as possible matches to get_net_device_by_port_pkey_ip
From: Shachar Raindel @ 2015-02-11 15:06 UTC (permalink / raw)
To: roland, sean.hefty
Cc: linux-rdma, netdev, liranl, guysh, haggaie, yotamke, raindel
In-Reply-To: <1423667204-8807-1-git-send-email-raindel@mellanox.com>
From: Guy Shapiro <guysh@mellanox.com>
Implement callback that returns network device to ib_core according to
connection parameters. Check the ipoib device and iterate over all child
devices to look for a match.
For each ipoib device we iterate through all upper devices when searching for
a matching IP, in order to support bonding.
Signed-off-by: Guy Shapiro <guysh@mellanox.com>
Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Yotam Kenneth <yotamke@mellanox.com>
Signed-off-by: Shachar Raindel <raindel@mellanox.com>
---
drivers/infiniband/ulp/ipoib/ipoib_main.c | 122 +++++++++++++++++++++++++++++-
1 file changed, 121 insertions(+), 1 deletion(-)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 58b5aa3..63119ff 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -48,6 +48,9 @@
#include <linux/jhash.h>
#include <net/arp.h>
+#include <net/addrconf.h>
+#include <linux/inetdevice.h>
+#include <rdma/ib_cache.h>
#define DRV_VERSION "1.0.0"
@@ -91,11 +94,15 @@ struct ib_sa_client ipoib_sa_client;
static void ipoib_add_one(struct ib_device *device);
static void ipoib_remove_one(struct ib_device *device);
static void ipoib_neigh_reclaim(struct rcu_head *rp);
+static struct net_device *ipoib_get_net_device_by_port_pkey_ip(
+ struct ib_device *dev, u8 port, u16 pkey,
+ struct sockaddr *addr);
static struct ib_client ipoib_client = {
.name = "ipoib",
.add = ipoib_add_one,
- .remove = ipoib_remove_one
+ .remove = ipoib_remove_one,
+ .get_net_device_by_port_pkey_ip = ipoib_get_net_device_by_port_pkey_ip,
};
int ipoib_open(struct net_device *dev)
@@ -222,6 +229,119 @@ static int ipoib_change_mtu(struct net_device *dev, int new_mtu)
return 0;
}
+static bool ipoib_is_dev_match_addr(struct sockaddr *addr,
+ struct net_device *dev)
+{
+ struct net *net = dev_net(dev);
+
+ if (addr->sa_family == AF_INET) {
+ struct in_device *in_dev = in_dev_get(dev);
+ struct sockaddr_in *addr_in = (struct sockaddr_in *)addr;
+ __be32 ret_addr;
+
+ if (!in_dev)
+ return false;
+
+ ret_addr = inet_confirm_addr(net, in_dev, 0,
+ addr_in->sin_addr.s_addr,
+ RT_SCOPE_HOST);
+ in_dev_put(in_dev);
+ if (ret_addr)
+ return true;
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ else if (addr->sa_family == AF_INET6) {
+ struct sockaddr_in6 *addr_in6 = (struct sockaddr_in6 *)addr;
+
+ if (ipv6_chk_addr(net, &addr_in6->sin6_addr, dev, 1))
+ return true;
+ }
+#endif
+ return false;
+}
+
+/**
+ * Find a net_device matching the given address, which is an upper device of
+ * the given net_device.
+ * @addr: IP address to look for.
+ * @dev: base IPoIB net_device
+ *
+ * If found, returns the net_device with a reference held. Otherwise return
+ * NULL.
+ */
+static struct net_device *ipoib_get_net_dev_match_addr(struct sockaddr *addr,
+ struct net_device *dev)
+{
+ struct net_device *upper,
+ *result = NULL;
+ struct list_head *iter;
+
+ if (ipoib_is_dev_match_addr(addr, dev)) {
+ dev_hold(dev);
+ return dev;
+ }
+
+ rcu_read_lock();
+ netdev_for_each_all_upper_dev_rcu(dev, upper, iter) {
+ if (ipoib_is_dev_match_addr(addr, upper)) {
+ dev_hold(upper);
+ result = upper;
+ break;
+ }
+ }
+ rcu_read_unlock();
+ return result;
+}
+
+static struct net_device *ipoib_get_net_device_by_port_pkey_ip(
+ struct ib_device *dev, u8 port, u16 pkey, struct sockaddr *addr)
+{
+ struct ipoib_dev_priv *priv;
+ struct list_head *dev_list;
+ u16 pkey_index;
+
+ ib_find_cached_pkey(dev, port, pkey, &pkey_index);
+ if (pkey_index == (u16)-1)
+ return NULL;
+
+ if (rdma_node_get_transport(dev->node_type) != RDMA_TRANSPORT_IB)
+ return NULL;
+
+ dev_list = ib_get_client_data(dev, &ipoib_client);
+ if (!dev_list)
+ return NULL;
+
+ list_for_each_entry(priv, dev_list, list) {
+ struct net_device *net_dev = NULL;
+ struct ipoib_dev_priv *child_priv;
+
+ if (priv->port != port)
+ continue;
+
+ if (priv->pkey_index == pkey_index) {
+ net_dev = ipoib_get_net_dev_match_addr(addr, priv->dev);
+ if (net_dev)
+ return net_dev;
+ }
+
+ down_read(&priv->vlan_rwsem);
+ list_for_each_entry(child_priv,
+ &priv->child_intfs, list) {
+ if (child_priv->pkey_index != pkey_index)
+ continue;
+
+ net_dev = ipoib_get_net_dev_match_addr(
+ addr, child_priv->dev);
+ if (net_dev)
+ break;
+ }
+ up_read(&priv->vlan_rwsem);
+ if (net_dev)
+ return net_dev;
+ }
+ return NULL;
+}
+
int ipoib_set_mode(struct net_device *dev, const char *buf)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
--
1.7.11.2
^ permalink raw reply related
* [PATCH v1 00/10] Add network namespace support in the RDMA-CM
From: Shachar Raindel @ 2015-02-11 15:06 UTC (permalink / raw)
To: roland, sean.hefty
Cc: linux-rdma, netdev, liranl, guysh, haggaie, yotamke, raindel
RDMA-CM uses IP based addressing and routing to setup RDMA connections between
hosts. Currently, all of the IP interfaces and addresses used by the RDMA-CM
must reside in the init_net namespace. This restricts the usage of containers
with RDMA to only work with host network namespace (aka the kernel init_net NS
instance).
This patchset allows using network namespaces with the RDMA-CM.
Each RDMA-CM and CM id is keeping a reference to a network namespace.
This reference is based on the process network namespace at the time of the
creation of the object or inherited from the listener.
This network namespace is used to perform all IP and network related
operations. Specifically, the local device lookup, as well as the remote GID
address resolution are done in the context of the RDMA-CM object's namespace.
This allows outgoing connections to reach the right target, even if the same
IP address exists in multiple network namespaces. This can happen if each
network namespace resides on a different pkey.
Additionally, the network namespace is used to split the listener service ID
table. From the user point of view, each network namespace has a unique,
completely independent table of service IDs. This allows running multiple
instances of a single service on the same machine, using containers. To
implement this, the CM layer now parses the IP address from the CM connect
requests, and searches for the matching networking device. The namespace of
the device found is used when looking up the service ID in the listener table.
The functionnality introduced by this series would come into play when the
transport is InfiniBand and IPoIB interfaces are assigned to each namespace.
Multiple IPoIB interfaces can be created and assigned to different RDMA-CM
capable containers, for example using pipework [1].
Full support for RoCE will be introduced in a later stage.
The patches apply against kernel v3.19-rc5, with the patch "RDMA/CMA: Mark
IPv4 addresses correctly when the listener is IPv6" [2] applied.
The patchset is structured as follows:
Patches 1 and 2 are relatively trivial API extensions, requiring the callers
of certain ib_addr and ib_core functions to provide a network namespace, as
needed.
Patches 3 and 4 adds the ability to lookup a network namespace according to
the IP address, device and pkey. It finds the matching IPoIB interfaces, and
safely takes a reference on the network namespace before returning to the
caller.
Patch 5 moves the logic that extracts the IP address from a connect request
into the CM layer. This is needed for the upcoming listener lookup by
namespace.
Patch 6 adds support for network namespaces in the CM layer. All callers are
still passing init_net as the namespace, to maintain backward compatibility.
For incoming requests, the namespace of the relevant IPoIB device is used.
Patches 7 and 8 add proper namespace support to the RDMA-CM module.
Patches 9 and 10 add namespace support to the relevant user facing modules in
the IB stack.
[1] https://github.com/jpetazzo/pipework/pull/108
[2] https://patchwork.kernel.org/patch/5298971/
Change-log:
V0 -> V1:
- Fix code review comments by Yann
- Rebase on top of linux-3.19
Guy Shapiro (7):
IB/addr: Pass network namespace as a parameter
IB/core: Pass network namespace as a parameter to relevant functions
IB/ipoib: Return IPoIB devices as possible matches to
get_net_device_by_port_pkey_ip
IB/cm,cma: Move RDMA IP CM private-data parsing code from ib_cma to
ib_cm
IB/cm: Add network namespace support
IB/cma: Add support for network namespaces
IB/ucma: Take the network namespace from the process
Shachar Raindel (1):
IB/ucm: Add partial support for network namespaces
Yotam Kenneth (2):
IB/core: Find the network namespace matching connection parameters
IB/cma: Separate port allocation to network namespaces
drivers/infiniband/core/addr.c | 31 +-
drivers/infiniband/core/agent.c | 4 +-
drivers/infiniband/core/cm.c | 287 ++++++++++++++++--
drivers/infiniband/core/cma.c | 332 +++++++++------------
drivers/infiniband/core/device.c | 57 ++++
drivers/infiniband/core/mad_rmpp.c | 10 +-
drivers/infiniband/core/ucm.c | 4 +-
drivers/infiniband/core/ucma.c | 4 +-
drivers/infiniband/core/user_mad.c | 4 +-
drivers/infiniband/core/verbs.c | 22 +-
drivers/infiniband/hw/ocrdma/ocrdma_ah.c | 3 +-
drivers/infiniband/ulp/ipoib/ipoib_cm.c | 21 +-
drivers/infiniband/ulp/ipoib/ipoib_main.c | 122 +++++++-
drivers/infiniband/ulp/iser/iser_verbs.c | 2 +-
drivers/infiniband/ulp/isert/ib_isert.c | 2 +-
drivers/infiniband/ulp/srp/ib_srp.c | 2 +-
drivers/infiniband/ulp/srpt/ib_srpt.c | 5 +-
.../staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h | 4 +-
include/rdma/ib_addr.h | 44 ++-
include/rdma/ib_cm.h | 63 +++-
include/rdma/ib_verbs.h | 44 ++-
include/rdma/rdma_cm.h | 6 +-
net/9p/trans_rdma.c | 2 +-
net/rds/ib.c | 2 +-
net/rds/ib_cm.c | 2 +-
net/rds/iw.c | 2 +-
net/rds/iw_cm.c | 2 +-
net/rds/rdma_transport.c | 2 +-
net/sunrpc/xprtrdma/svc_rdma_transport.c | 2 +-
net/sunrpc/xprtrdma/verbs.c | 3 +-
30 files changed, 822 insertions(+), 268 deletions(-)
--
1.7.11.2
^ permalink raw reply
* [PATCH v1 06/10] IB/cm: Add network namespace support
From: Shachar Raindel @ 2015-02-11 15:06 UTC (permalink / raw)
To: roland, sean.hefty
Cc: linux-rdma, netdev, liranl, guysh, haggaie, yotamke, raindel
In-Reply-To: <1423667204-8807-1-git-send-email-raindel@mellanox.com>
From: Guy Shapiro <guysh@mellanox.com>
Add namespace support to the IB-CM layer.
- Each CM-ID now has a network namespace it is associated with, assigned at
creation. This namespace is used as needed during subsequent action on the
CM-ID or related objects.
- All of the relevant calls to ib_addr and ib_core were updated to use the
namespace from the CM-ID. External APIs were extended as needed to allow
specifying the namespace where relevant.
- The listening service ID table is now also indexed by the CM-ID namespace.
- For incoming connection requests, we use the connection parameters to select
namespace. The namespace is matched when looking for listening service ID.
To preserve current behavior pass init_net to ib_cm wherever network namespace
function parameters were added.
The ib_cm_create_id interface now takes a reference to the relevant network
namespace. CM-IDs created by accepting a connection for a listening CM-ID will
also take a reference to the namespace. When the ID is destroyed, the
namespace reference is released.
Signed-off-by: Guy Shapiro <guysh@mellanox.com>
Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Yotam Kenneth <yotamke@mellanox.com>
Signed-off-by: Shachar Raindel <raindel@mellanox.com>
---
drivers/infiniband/core/cm.c | 124 ++++++++++++++++++++++++--------
drivers/infiniband/core/cma.c | 8 ++-
drivers/infiniband/core/ucm.c | 3 +-
drivers/infiniband/ulp/ipoib/ipoib_cm.c | 21 +++++-
drivers/infiniband/ulp/srp/ib_srp.c | 2 +-
drivers/infiniband/ulp/srpt/ib_srpt.c | 2 +-
include/rdma/ib_cm.h | 7 +-
7 files changed, 130 insertions(+), 37 deletions(-)
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index efc5cff..75c6ac9 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -241,6 +241,8 @@ struct cm_id_private {
u8 service_timeout;
u8 target_ack_delay;
+ struct net *net; /* A network namespace that the ID belongs to */
+
struct list_head work_list;
atomic_t work_count;
};
@@ -347,12 +349,13 @@ static void cm_set_private_data(struct cm_id_private *cm_id_priv,
}
static void cm_init_av_for_response(struct cm_port *port, struct ib_wc *wc,
- struct ib_grh *grh, struct cm_av *av)
+ struct ib_grh *grh, struct cm_av *av,
+ struct net *net)
{
av->port = port;
av->pkey_index = wc->pkey_index;
ib_init_ah_from_wc(port->cm_dev->ib_device, port->port_num, wc,
- grh, &av->ah_attr, &init_net);
+ grh, &av->ah_attr, net);
}
static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av)
@@ -521,10 +524,15 @@ static struct cm_id_private * cm_insert_listen(struct cm_id_private *cm_id_priv)
if ((cur_cm_id_priv->id.service_mask & service_id) ==
(service_mask & cur_cm_id_priv->id.service_id) &&
(cm_id_priv->id.device == cur_cm_id_priv->id.device) &&
- !data_cmp)
+ !data_cmp &&
+ net_eq(cm_id_priv->net, cur_cm_id_priv->net))
return cur_cm_id_priv;
- if (cm_id_priv->id.device < cur_cm_id_priv->id.device)
+ if (cm_id_priv->net < cur_cm_id_priv->net)
+ link = &(*link)->rb_left;
+ else if (cm_id_priv->net > cur_cm_id_priv->net)
+ link = &(*link)->rb_right;
+ else if (cm_id_priv->id.device < cur_cm_id_priv->id.device)
link = &(*link)->rb_left;
else if (cm_id_priv->id.device > cur_cm_id_priv->id.device)
link = &(*link)->rb_right;
@@ -544,7 +552,8 @@ static struct cm_id_private * cm_insert_listen(struct cm_id_private *cm_id_priv)
static struct cm_id_private * cm_find_listen(struct ib_device *device,
__be64 service_id,
- u8 *private_data)
+ u8 *private_data,
+ struct net *net)
{
struct rb_node *node = cm.listen_service_table.rb_node;
struct cm_id_private *cm_id_priv;
@@ -556,10 +565,14 @@ static struct cm_id_private * cm_find_listen(struct ib_device *device,
cm_id_priv->compare_data);
if ((cm_id_priv->id.service_mask & service_id) ==
cm_id_priv->id.service_id &&
- (cm_id_priv->id.device == device) && !data_cmp)
+ (cm_id_priv->id.device == device) && !data_cmp &&
+ net_eq(cm_id_priv->net, net))
return cm_id_priv;
-
- if (device < cm_id_priv->id.device)
+ if (net < cm_id_priv->net)
+ node = node->rb_left;
+ else if (net > cm_id_priv->net)
+ node = node->rb_right;
+ else if (device < cm_id_priv->id.device)
node = node->rb_left;
else if (device > cm_id_priv->id.device)
node = node->rb_right;
@@ -857,7 +870,8 @@ EXPORT_SYMBOL(cm_save_net_info);
struct ib_cm_id *ib_create_cm_id(struct ib_device *device,
ib_cm_handler cm_handler,
- void *context)
+ void *context,
+ struct net *net)
{
struct cm_id_private *cm_id_priv;
int ret;
@@ -875,6 +889,8 @@ struct ib_cm_id *ib_create_cm_id(struct ib_device *device,
if (ret)
goto error;
+ cm_id_priv->net = get_net(net);
+
spin_lock_init(&cm_id_priv->lock);
init_completion(&cm_id_priv->comp);
INIT_LIST_HEAD(&cm_id_priv->work_list);
@@ -1078,6 +1094,7 @@ retest:
cm_free_work(work);
kfree(cm_id_priv->compare_data);
kfree(cm_id_priv->private_data);
+ put_net(cm_id_priv->net);
kfree(cm_id_priv);
}
@@ -1597,7 +1614,8 @@ free: cm_free_msg(msg);
}
static struct cm_id_private * cm_match_req(struct cm_work *work,
- struct cm_id_private *cm_id_priv)
+ struct cm_id_private *cm_id_priv,
+ struct net *net)
{
struct cm_id_private *listen_cm_id_priv, *cur_cm_id_priv;
struct cm_timewait_info *timewait_info;
@@ -1633,7 +1651,8 @@ static struct cm_id_private * cm_match_req(struct cm_work *work,
/* Find matching listen request. */
listen_cm_id_priv = cm_find_listen(cm_id_priv->id.device,
req_msg->service_id,
- req_msg->private_data);
+ req_msg->private_data,
+ net);
if (!listen_cm_id_priv) {
cm_cleanup_timewait(cm_id_priv->timewait_info);
spin_unlock_irq(&cm.lock);
@@ -1679,24 +1698,58 @@ static void cm_process_routed_req(struct cm_req_msg *req_msg, struct ib_wc *wc)
}
}
+static int cm_is_cma_service_id(__be64 service_id)
+{
+ return (IB_CMA_SERVICE_ID_MASK & service_id) == IB_CMA_SERVICE_ID;
+}
+
+static struct net *cm_get_net_ns(struct cm_work *work, __be64 service_id,
+ __be16 pkey)
+{
+ struct sockaddr_storage addr_storage;
+ struct sockaddr *listen_addr;
+
+ if (cm_is_cma_service_id(service_id)) {
+ listen_addr = (struct sockaddr *)&addr_storage;
+ cm_save_ip_info(listen_addr, NULL, work);
+ } else {
+ /* On RoCE we could extend this branch to determine the
+ * destination IP from the incoming packet headers, and add
+ * support for services that are not RDMA IP CM compliant. */
+ listen_addr = NULL;
+ }
+
+ return ib_get_net_ns_by_port_pkey_ip(work->port->cm_dev->ib_device,
+ work->port->port_num,
+ be16_to_cpu(pkey),
+ listen_addr);
+}
static int cm_req_handler(struct cm_work *work)
{
struct ib_cm_id *cm_id;
struct cm_id_private *cm_id_priv, *listen_cm_id_priv;
struct cm_req_msg *req_msg;
+ struct net *net;
int ret;
req_msg = (struct cm_req_msg *)work->mad_recv_wc->recv_buf.mad;
+ work->cm_event.private_data = req_msg->private_data;
- cm_id = ib_create_cm_id(work->port->cm_dev->ib_device, NULL, NULL);
- if (IS_ERR(cm_id))
- return PTR_ERR(cm_id);
+ net = cm_get_net_ns(work, req_msg->service_id, req_msg->pkey);
+
+ cm_id = ib_create_cm_id(work->port->cm_dev->ib_device, NULL, NULL, net);
+ /* cm_id took a reference to net, so no need to hold it anymore */
+ put_net(net);
+ if (IS_ERR(cm_id)) {
+ ret = PTR_ERR(cm_id);
+ goto out;
+ }
cm_id_priv = container_of(cm_id, struct cm_id_private, id);
cm_id_priv->id.remote_id = req_msg->local_comm_id;
cm_init_av_for_response(work->port, work->mad_recv_wc->wc,
work->mad_recv_wc->recv_buf.grh,
- &cm_id_priv->av);
+ &cm_id_priv->av, net);
cm_id_priv->timewait_info = cm_create_timewait_info(cm_id_priv->
id.local_id);
if (IS_ERR(cm_id_priv->timewait_info)) {
@@ -1707,7 +1760,7 @@ static int cm_req_handler(struct cm_work *work)
cm_id_priv->timewait_info->remote_ca_guid = req_msg->local_ca_guid;
cm_id_priv->timewait_info->remote_qpn = cm_req_get_local_qpn(req_msg);
- listen_cm_id_priv = cm_match_req(work, cm_id_priv);
+ listen_cm_id_priv = cm_match_req(work, cm_id_priv, net);
if (!listen_cm_id_priv) {
ret = -EINVAL;
kfree(cm_id_priv->timewait_info);
@@ -1766,6 +1819,7 @@ rejected:
cm_deref_id(listen_cm_id_priv);
destroy:
ib_destroy_cm_id(cm_id);
+out:
return ret;
}
@@ -2900,7 +2954,7 @@ static int cm_lap_handler(struct cm_work *work)
cm_id_priv->tid = lap_msg->hdr.tid;
cm_init_av_for_response(work->port, work->mad_recv_wc->wc,
work->mad_recv_wc->recv_buf.grh,
- &cm_id_priv->av);
+ &cm_id_priv->av, cm_id_priv->net);
cm_init_av_by_path(param->alternate_path, &cm_id_priv->alt_av);
ret = atomic_inc_and_test(&cm_id_priv->work_count);
if (!ret)
@@ -3150,21 +3204,31 @@ static int cm_sidr_req_handler(struct cm_work *work)
struct cm_id_private *cm_id_priv, *cur_cm_id_priv;
struct cm_sidr_req_msg *sidr_req_msg;
struct ib_wc *wc;
+ struct net *net;
+ int retval;
+
+ sidr_req_msg = (struct cm_sidr_req_msg *)
+ work->mad_recv_wc->recv_buf.mad;
+ work->cm_event.private_data = sidr_req_msg->private_data;
+
+ net = cm_get_net_ns(work, sidr_req_msg->service_id, sidr_req_msg->pkey);
- cm_id = ib_create_cm_id(work->port->cm_dev->ib_device, NULL, NULL);
- if (IS_ERR(cm_id))
- return PTR_ERR(cm_id);
+ cm_id = ib_create_cm_id(work->port->cm_dev->ib_device, NULL, NULL, net);
+ /* cm_id took a reference to net, so no need to hold it anymore */
+ put_net(net);
+ if (IS_ERR(cm_id)) {
+ retval = PTR_ERR(cm_id);
+ goto out;
+ }
cm_id_priv = container_of(cm_id, struct cm_id_private, id);
/* Record SGID/SLID and request ID for lookup. */
- sidr_req_msg = (struct cm_sidr_req_msg *)
- work->mad_recv_wc->recv_buf.mad;
wc = work->mad_recv_wc->wc;
cm_id_priv->av.dgid.global.subnet_prefix = cpu_to_be64(wc->slid);
cm_id_priv->av.dgid.global.interface_id = 0;
cm_init_av_for_response(work->port, work->mad_recv_wc->wc,
work->mad_recv_wc->recv_buf.grh,
- &cm_id_priv->av);
+ &cm_id_priv->av, net);
cm_id_priv->id.remote_id = sidr_req_msg->request_id;
cm_id_priv->tid = sidr_req_msg->hdr.tid;
atomic_inc(&cm_id_priv->work_count);
@@ -3175,16 +3239,19 @@ static int cm_sidr_req_handler(struct cm_work *work)
spin_unlock_irq(&cm.lock);
atomic_long_inc(&work->port->counter_group[CM_RECV_DUPLICATES].
counter[CM_SIDR_REQ_COUNTER]);
- goto out; /* Duplicate message. */
+ retval = -EINVAL; /* Duplicate message. */
+ goto out_id;
}
cm_id_priv->id.state = IB_CM_SIDR_REQ_RCVD;
cur_cm_id_priv = cm_find_listen(cm_id->device,
sidr_req_msg->service_id,
- sidr_req_msg->private_data);
+ sidr_req_msg->private_data,
+ net);
if (!cur_cm_id_priv) {
spin_unlock_irq(&cm.lock);
cm_reject_sidr_req(cm_id_priv, IB_SIDR_UNSUPPORTED);
- goto out; /* No match. */
+ retval = -EINVAL; /* No match. */
+ goto out_id;
}
atomic_inc(&cur_cm_id_priv->refcount);
atomic_inc(&cm_id_priv->refcount);
@@ -3199,9 +3266,10 @@ static int cm_sidr_req_handler(struct cm_work *work)
cm_process_work(cm_id_priv, work);
cm_deref_id(cur_cm_id_priv);
return 0;
-out:
+out_id:
ib_destroy_cm_id(&cm_id_priv->id);
- return -EINVAL;
+out:
+ return retval;
}
static void cm_format_sidr_rep(struct cm_sidr_rep_msg *sidr_rep_msg,
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 9f6faeb..1ce84a0 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1456,7 +1456,8 @@ static int cma_ib_listen(struct rdma_id_private *id_priv)
__be64 svc_id;
int ret;
- id = ib_create_cm_id(id_priv->id.device, cma_req_handler, id_priv);
+ id = ib_create_cm_id(id_priv->id.device, cma_req_handler, id_priv,
+ &init_net);
if (IS_ERR(id))
return PTR_ERR(id);
@@ -2606,7 +2607,7 @@ static int cma_resolve_ib_udp(struct rdma_id_private *id_priv,
}
id = ib_create_cm_id(id_priv->id.device, cma_sidr_rep_handler,
- id_priv);
+ id_priv, &init_net);
if (IS_ERR(id)) {
ret = PTR_ERR(id);
goto out;
@@ -2655,7 +2656,8 @@ static int cma_connect_ib(struct rdma_id_private *id_priv,
memcpy(private_data + offset, conn_param->private_data,
conn_param->private_data_len);
- id = ib_create_cm_id(id_priv->id.device, cma_ib_handler, id_priv);
+ id = ib_create_cm_id(id_priv->id.device, cma_ib_handler, id_priv,
+ &init_net);
if (IS_ERR(id)) {
ret = PTR_ERR(id);
goto out;
diff --git a/drivers/infiniband/core/ucm.c b/drivers/infiniband/core/ucm.c
index f2f6393..9604ab0 100644
--- a/drivers/infiniband/core/ucm.c
+++ b/drivers/infiniband/core/ucm.c
@@ -489,7 +489,8 @@ static ssize_t ib_ucm_create_id(struct ib_ucm_file *file,
ctx->uid = cmd.uid;
ctx->cm_id = ib_create_cm_id(file->device->ib_dev,
- ib_ucm_event_handler, ctx);
+ ib_ucm_event_handler, ctx,
+ &init_net);
if (IS_ERR(ctx->cm_id)) {
result = PTR_ERR(ctx->cm_id);
goto err1;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 933efce..749b65b 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -846,7 +846,15 @@ int ipoib_cm_dev_open(struct net_device *dev)
if (!IPOIB_CM_SUPPORTED(dev->dev_addr))
return 0;
- priv->cm.id = ib_create_cm_id(priv->ca, ipoib_cm_rx_handler, dev);
+ /*
+ * The IPoIB CM ID should always be in the init_net namespace.
+ * It is using a service ID which is not in the RDMA IP CM
+ * range. Furthermore, it is guaranteed that this service ID
+ * will be unique in the machine, as it is based on the UD QP
+ * number.
+ */
+ priv->cm.id = ib_create_cm_id(priv->ca, ipoib_cm_rx_handler, dev,
+ &init_net);
if (IS_ERR(priv->cm.id)) {
printk(KERN_WARNING "%s: failed to create CM ID\n", priv->ca->name);
ret = PTR_ERR(priv->cm.id);
@@ -1130,7 +1138,16 @@ static int ipoib_cm_tx_init(struct ipoib_cm_tx *p, u32 qpn,
goto err_qp;
}
- p->id = ib_create_cm_id(priv->ca, ipoib_cm_tx_handler, p);
+ /*
+ * The IPoIB CM ID should always be in the init_net namespace.
+ *
+ * The target for connection is specified by an explicit GID,
+ * which is machine global and not specific for the namespace
+ * the device resides at. The service ID is also guaranteed to
+ * be per machine unique, and therefore init_net is the right
+ * namespace.
+ */
+ p->id = ib_create_cm_id(priv->ca, ipoib_cm_tx_handler, p, &init_net);
if (IS_ERR(p->id)) {
ret = PTR_ERR(p->id);
ipoib_warn(priv, "failed to create tx cm id: %d\n", ret);
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 0747c05..3b418be 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -294,7 +294,7 @@ static int srp_new_cm_id(struct srp_rdma_ch *ch)
struct ib_cm_id *new_cm_id;
new_cm_id = ib_create_cm_id(target->srp_host->srp_dev->dev,
- srp_cm_handler, ch);
+ srp_cm_handler, ch, &init_net);
if (IS_ERR(new_cm_id))
return PTR_ERR(new_cm_id);
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 7867bd5..c0a1de3 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -3247,7 +3247,7 @@ static void srpt_add_one(struct ib_device *device)
if (!srpt_service_guid)
srpt_service_guid = be64_to_cpu(device->node_guid);
- sdev->cm_id = ib_create_cm_id(device, srpt_cm_handler, sdev);
+ sdev->cm_id = ib_create_cm_id(device, srpt_cm_handler, sdev, &init_net);
if (IS_ERR(sdev->cm_id))
goto err_srq;
diff --git a/include/rdma/ib_cm.h b/include/rdma/ib_cm.h
index 0e49933..a22ffa3 100644
--- a/include/rdma/ib_cm.h
+++ b/include/rdma/ib_cm.h
@@ -369,13 +369,18 @@ struct ib_cm_id {
* @cm_handler: Callback invoked to notify the user of CM events.
* @context: User specified context associated with the communication
* identifier.
+ * @net: Network namespace associated with the cm_id.
*
* Communication identifiers are used to track connection states, service
* ID resolution requests, and listen requests.
+ *
+ * The created CM ID will hold a reference on the network namespace until its
+ * destruction.
*/
struct ib_cm_id *ib_create_cm_id(struct ib_device *device,
ib_cm_handler cm_handler,
- void *context);
+ void *context,
+ struct net *net);
/**
* ib_destroy_cm_id - Destroy a connection identifier.
--
1.7.11.2
^ permalink raw reply related
* [PATCH v1 07/10] IB/cma: Separate port allocation to network namespaces
From: Shachar Raindel @ 2015-02-11 15:06 UTC (permalink / raw)
To: roland, sean.hefty
Cc: linux-rdma, netdev, liranl, guysh, haggaie, yotamke, raindel
In-Reply-To: <1423667204-8807-1-git-send-email-raindel@mellanox.com>
From: Yotam Kenneth <yotamke@mellanox.com>
Keep a radix-tree for the network namespaces we support for each port-space.
Dynamically allocate idr for network namespace upon first bind request for a
port in the (ps, net) tuple.
Destroy the idr when the (ps, net) tuple does not contain any bounded ports.
This patch is internal infrastructure work for the following patch. In
this patch, init_net is statically used as the network namespace for
the new port-space API.
The radix-tree is protected under the same locking that protects the
rest of the port space data. This locking is practically a big, static
mutex lock for the entire module.
Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Yotam Kenneth <yotamke@mellanox.com>
Signed-off-by: Shachar Raindel <raindel@mellanox.com>
Signed-off-by: Guy Shapiro <guysh@mellanox.com>
---
drivers/infiniband/core/cma.c | 122 ++++++++++++++++++++++++++++++++++--------
1 file changed, 99 insertions(+), 23 deletions(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 1ce84a0..022b0d0 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -39,11 +39,13 @@
#include <linux/mutex.h>
#include <linux/random.h>
#include <linux/idr.h>
+#include <linux/radix-tree.h>
#include <linux/inetdevice.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <net/route.h>
+#include <net/netns/hash.h>
#include <net/tcp.h>
#include <net/ipv6.h>
@@ -80,10 +82,83 @@ static LIST_HEAD(dev_list);
static LIST_HEAD(listen_any_list);
static DEFINE_MUTEX(lock);
static struct workqueue_struct *cma_wq;
-static DEFINE_IDR(tcp_ps);
-static DEFINE_IDR(udp_ps);
-static DEFINE_IDR(ipoib_ps);
-static DEFINE_IDR(ib_ps);
+static RADIX_TREE(tcp_ps, GFP_KERNEL);
+static RADIX_TREE(udp_ps, GFP_KERNEL);
+static RADIX_TREE(ipoib_ps, GFP_KERNEL);
+static RADIX_TREE(ib_ps, GFP_KERNEL);
+
+static LIST_HEAD(idrs_list);
+
+struct idr_ll {
+ unsigned net_val;
+ struct net *net;
+ struct radix_tree_root *ps;
+ struct idr idr;
+};
+
+static void zap_ps_idr(struct idr_ll *idr_ll)
+{
+ radix_tree_delete(idr_ll->ps, idr_ll->net_val);
+ idr_destroy(&idr_ll->idr);
+ kfree(idr_ll);
+}
+
+static int cma_ps_alloc(struct radix_tree_root *ps, struct net *net, void *ptr,
+ int snum)
+{
+ struct idr_ll *idr_ll;
+ int err;
+ int res;
+
+ idr_ll = radix_tree_lookup(ps, net_hash_mix(net));
+ if (!idr_ll) {
+ idr_ll = kmalloc(sizeof(*idr_ll), GFP_KERNEL);
+ if (!idr_ll)
+ return -ENOMEM;
+ idr_init(&idr_ll->idr);
+ idr_ll->net_val = net_hash_mix(net);
+ idr_ll->net = net;
+ idr_ll->ps = ps;
+ err = radix_tree_insert(ps, idr_ll->net_val, idr_ll);
+ if (err) {
+ idr_destroy(&idr_ll->idr);
+ kfree(idr_ll);
+ return err;
+ }
+ }
+ res = idr_alloc(&idr_ll->idr, ptr, snum, snum + 1, GFP_KERNEL);
+ if (unlikely((res < 0) && idr_is_empty(&idr_ll->idr))) {
+ zap_ps_idr(idr_ll);
+ return res;
+ }
+ return res;
+}
+
+static void *cma_ps_find(struct radix_tree_root *ps, struct net *net, int snum)
+{
+ struct idr_ll *idr_ll;
+
+ idr_ll = radix_tree_lookup(ps, net_hash_mix(net));
+ if (!idr_ll)
+ return NULL;
+ return idr_find(&idr_ll->idr, snum);
+}
+
+static void cma_ps_remove(struct radix_tree_root *ps, struct net *net, int snum)
+{
+ struct idr_ll *idr_ll;
+
+ idr_ll = radix_tree_lookup(ps, net_hash_mix(net));
+ if (unlikely(!idr_ll)) {
+ WARN(1, "cma_ps_removed can't find expected net ns 0x%lx\n",
+ (unsigned long)net);
+ return;
+ }
+ idr_remove(&idr_ll->idr, snum);
+ if (idr_is_empty(&idr_ll->idr)) {
+ zap_ps_idr(idr_ll);
+ }
+}
struct cma_device {
struct list_head list;
@@ -94,9 +169,9 @@ struct cma_device {
};
struct rdma_bind_list {
- struct idr *ps;
- struct hlist_head owners;
- unsigned short port;
+ struct radix_tree_root *ps;
+ struct hlist_head owners;
+ unsigned short port;
};
enum {
@@ -885,7 +960,7 @@ static void cma_release_port(struct rdma_id_private *id_priv)
mutex_lock(&lock);
hlist_del(&id_priv->node);
if (hlist_empty(&bind_list->owners)) {
- idr_remove(bind_list->ps, bind_list->port);
+ cma_ps_remove(bind_list->ps, &init_net, bind_list->port);
kfree(bind_list);
}
mutex_unlock(&lock);
@@ -2198,8 +2273,8 @@ static void cma_bind_port(struct rdma_bind_list *bind_list,
hlist_add_head(&id_priv->node, &bind_list->owners);
}
-static int cma_alloc_port(struct idr *ps, struct rdma_id_private *id_priv,
- unsigned short snum)
+static int cma_alloc_port(struct radix_tree_root *ps,
+ struct rdma_id_private *id_priv, unsigned short snum)
{
struct rdma_bind_list *bind_list;
int ret;
@@ -2208,7 +2283,7 @@ static int cma_alloc_port(struct idr *ps, struct rdma_id_private *id_priv,
if (!bind_list)
return -ENOMEM;
- ret = idr_alloc(ps, bind_list, snum, snum + 1, GFP_KERNEL);
+ ret = cma_ps_alloc(ps, &init_net, bind_list, snum);
if (ret < 0)
goto err;
@@ -2221,7 +2296,8 @@ err:
return ret == -ENOSPC ? -EADDRNOTAVAIL : ret;
}
-static int cma_alloc_any_port(struct idr *ps, struct rdma_id_private *id_priv)
+static int cma_alloc_any_port(struct radix_tree_root *ps,
+ struct rdma_id_private *id_priv)
{
static unsigned int last_used_port;
int low, high, remaining;
@@ -2232,7 +2308,7 @@ static int cma_alloc_any_port(struct idr *ps, struct rdma_id_private *id_priv)
rover = prandom_u32() % remaining + low;
retry:
if (last_used_port != rover &&
- !idr_find(ps, (unsigned short) rover)) {
+ !cma_ps_find(ps, &init_net, (unsigned short)rover)) {
int ret = cma_alloc_port(ps, id_priv, rover);
/*
* Remember previously used port number in order to avoid
@@ -2257,6 +2333,8 @@ retry:
* bind to a specific port, or when trying to listen on a bound port. In
* the latter case, the provided id_priv may already be on the bind_list, but
* we still need to check that it's okay to start listening.
+ *
+ * Assume the bind_list contains only services from the correct name space.
*/
static int cma_check_port(struct rdma_bind_list *bind_list,
struct rdma_id_private *id_priv, uint8_t reuseaddr)
@@ -2287,7 +2365,8 @@ static int cma_check_port(struct rdma_bind_list *bind_list,
return 0;
}
-static int cma_use_port(struct idr *ps, struct rdma_id_private *id_priv)
+static int cma_use_port(struct radix_tree_root *ps,
+ struct rdma_id_private *id_priv)
{
struct rdma_bind_list *bind_list;
unsigned short snum;
@@ -2297,7 +2376,7 @@ static int cma_use_port(struct idr *ps, struct rdma_id_private *id_priv)
if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
return -EACCES;
- bind_list = idr_find(ps, snum);
+ bind_list = cma_ps_find(ps, &init_net, snum);
if (!bind_list) {
ret = cma_alloc_port(ps, id_priv, snum);
} else {
@@ -2320,7 +2399,8 @@ static int cma_bind_listen(struct rdma_id_private *id_priv)
return ret;
}
-static struct idr *cma_select_inet_ps(struct rdma_id_private *id_priv)
+static struct radix_tree_root *cma_select_inet_ps(
+ struct rdma_id_private *id_priv)
{
switch (id_priv->id.ps) {
case RDMA_PS_TCP:
@@ -2336,9 +2416,9 @@ static struct idr *cma_select_inet_ps(struct rdma_id_private *id_priv)
}
}
-static struct idr *cma_select_ib_ps(struct rdma_id_private *id_priv)
+static struct radix_tree_root *cma_select_ib_ps(struct rdma_id_private *id_priv)
{
- struct idr *ps = NULL;
+ struct radix_tree_root *ps = NULL;
struct sockaddr_ib *sib;
u64 sid_ps, mask, sid;
@@ -2369,7 +2449,7 @@ static struct idr *cma_select_ib_ps(struct rdma_id_private *id_priv)
static int cma_get_port(struct rdma_id_private *id_priv)
{
- struct idr *ps;
+ struct radix_tree_root *ps;
int ret;
if (cma_family(id_priv) != AF_IB)
@@ -3567,10 +3647,6 @@ static void __exit cma_cleanup(void)
rdma_addr_unregister_client(&addr_client);
ib_sa_unregister_client(&sa_client);
destroy_workqueue(cma_wq);
- idr_destroy(&tcp_ps);
- idr_destroy(&udp_ps);
- idr_destroy(&ipoib_ps);
- idr_destroy(&ib_ps);
}
module_init(cma_init);
--
1.7.11.2
^ permalink raw reply related
* [PATCH v1 08/10] IB/cma: Add support for network namespaces
From: Shachar Raindel @ 2015-02-11 15:06 UTC (permalink / raw)
To: roland, sean.hefty
Cc: linux-rdma, netdev, liranl, guysh, haggaie, yotamke, raindel
In-Reply-To: <1423667204-8807-1-git-send-email-raindel@mellanox.com>
From: Guy Shapiro <guysh@mellanox.com>
Add support for network namespaces in the ib_cma module. This is
accomplished by:
1. Adding network namespace parameter for rdma_create_id. This parameter is used
to populate the network namespace field in rdma_id_private. rdma_create_id
keeps a reference on the network namespace.
2. Using the network namespace from the rdma_id instead of init_net inside of
ib_cma.
3. Decrementing the reference count for the appropriate network namespace when
calling rdma_destroy_id.
In order to preserve the current behavior init_net is passed when calling from
other modules.
Signed-off-by: Guy Shapiro <guysh@mellanox.com>
Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Yotam Kenneth <yotamke@mellanox.com>
Signed-off-by: Shachar Raindel <raindel@mellanox.com>
---
drivers/infiniband/core/cma.c | 52 +++++++++++++---------
drivers/infiniband/core/ucma.c | 3 +-
drivers/infiniband/ulp/iser/iser_verbs.c | 2 +-
drivers/infiniband/ulp/isert/ib_isert.c | 2 +-
.../staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h | 4 +-
include/rdma/rdma_cm.h | 6 ++-
net/9p/trans_rdma.c | 2 +-
net/rds/ib.c | 2 +-
net/rds/ib_cm.c | 2 +-
net/rds/iw.c | 2 +-
net/rds/iw_cm.c | 2 +-
net/rds/rdma_transport.c | 2 +-
net/sunrpc/xprtrdma/svc_rdma_transport.c | 2 +-
net/sunrpc/xprtrdma/verbs.c | 3 +-
14 files changed, 52 insertions(+), 34 deletions(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 022b0d0..9ea42fe 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -540,7 +540,8 @@ static int cma_disable_callback(struct rdma_id_private *id_priv,
struct rdma_cm_id *rdma_create_id(rdma_cm_event_handler event_handler,
void *context, enum rdma_port_space ps,
- enum ib_qp_type qp_type)
+ enum ib_qp_type qp_type,
+ struct net *net)
{
struct rdma_id_private *id_priv;
@@ -562,7 +563,7 @@ struct rdma_cm_id *rdma_create_id(rdma_cm_event_handler event_handler,
INIT_LIST_HEAD(&id_priv->listen_list);
INIT_LIST_HEAD(&id_priv->mc_list);
get_random_bytes(&id_priv->seq_num, sizeof id_priv->seq_num);
- id_priv->id.route.addr.dev_addr.net = &init_net;
+ id_priv->id.route.addr.dev_addr.net = get_net(net);
return &id_priv->id;
}
@@ -689,7 +690,7 @@ static int cma_modify_qp_rtr(struct rdma_id_private *id_priv,
rdma_port_get_link_layer(id_priv->id.device, id_priv->id.port_num)
== IB_LINK_LAYER_ETHERNET) {
ret = rdma_addr_find_smac_by_sgid(&sgid, qp_attr.smac, NULL,
- &init_net);
+ id_priv->id.route.addr.dev_addr.net);
if (ret)
goto out;
@@ -953,6 +954,7 @@ static void cma_cancel_operation(struct rdma_id_private *id_priv,
static void cma_release_port(struct rdma_id_private *id_priv)
{
struct rdma_bind_list *bind_list = id_priv->bind_list;
+ struct net *net = id_priv->id.route.addr.dev_addr.net;
if (!bind_list)
return;
@@ -960,7 +962,7 @@ static void cma_release_port(struct rdma_id_private *id_priv)
mutex_lock(&lock);
hlist_del(&id_priv->node);
if (hlist_empty(&bind_list->owners)) {
- cma_ps_remove(bind_list->ps, &init_net, bind_list->port);
+ cma_ps_remove(bind_list->ps, net, bind_list->port);
kfree(bind_list);
}
mutex_unlock(&lock);
@@ -1029,6 +1031,7 @@ void rdma_destroy_id(struct rdma_cm_id *id)
cma_deref_id(id_priv->id.context);
kfree(id_priv->id.route.path_rec);
+ put_net(id_priv->id.route.addr.dev_addr.net);
kfree(id_priv);
}
EXPORT_SYMBOL(rdma_destroy_id);
@@ -1156,7 +1159,8 @@ static struct rdma_id_private *cma_new_conn_id(struct rdma_cm_id *listen_id,
int ret;
id = rdma_create_id(listen_id->event_handler, listen_id->context,
- listen_id->ps, ib_event->param.req_rcvd.qp_type);
+ listen_id->ps, ib_event->param.req_rcvd.qp_type,
+ listen_id->route.addr.dev_addr.net);
if (IS_ERR(id))
return NULL;
@@ -1201,10 +1205,11 @@ static struct rdma_id_private *cma_new_udp_id(struct rdma_cm_id *listen_id,
{
struct rdma_id_private *id_priv;
struct rdma_cm_id *id;
+ struct net *net = listen_id->route.addr.dev_addr.net;
int ret;
id = rdma_create_id(listen_id->event_handler, listen_id->context,
- listen_id->ps, IB_QPT_UD);
+ listen_id->ps, IB_QPT_UD, net);
if (IS_ERR(id))
return NULL;
@@ -1455,7 +1460,8 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id,
/* Create a new RDMA id for the new IW CM ID */
new_cm_id = rdma_create_id(listen_id->id.event_handler,
listen_id->id.context,
- RDMA_PS_TCP, IB_QPT_RC);
+ RDMA_PS_TCP, IB_QPT_RC,
+ listen_id->id.route.addr.dev_addr.net);
if (IS_ERR(new_cm_id)) {
ret = -ENOMEM;
goto out;
@@ -1528,11 +1534,11 @@ static int cma_ib_listen(struct rdma_id_private *id_priv)
struct ib_cm_compare_data compare_data;
struct sockaddr *addr;
struct ib_cm_id *id;
+ struct net *net = id_priv->id.route.addr.dev_addr.net;
__be64 svc_id;
int ret;
- id = ib_create_cm_id(id_priv->id.device, cma_req_handler, id_priv,
- &init_net);
+ id = ib_create_cm_id(id_priv->id.device, cma_req_handler, id_priv, net);
if (IS_ERR(id))
return PTR_ERR(id);
@@ -1596,6 +1602,7 @@ static void cma_listen_on_dev(struct rdma_id_private *id_priv,
{
struct rdma_id_private *dev_id_priv;
struct rdma_cm_id *id;
+ struct net *net = id_priv->id.route.addr.dev_addr.net;
int ret;
if (cma_family(id_priv) == AF_IB &&
@@ -1603,7 +1610,7 @@ static void cma_listen_on_dev(struct rdma_id_private *id_priv,
return;
id = rdma_create_id(cma_listen_handler, id_priv, id_priv->id.ps,
- id_priv->id.qp_type);
+ id_priv->id.qp_type, net);
if (IS_ERR(id))
return;
@@ -2283,7 +2290,8 @@ static int cma_alloc_port(struct radix_tree_root *ps,
if (!bind_list)
return -ENOMEM;
- ret = cma_ps_alloc(ps, &init_net, bind_list, snum);
+ ret = cma_ps_alloc(ps, id_priv->id.route.addr.dev_addr.net, bind_list,
+ snum);
if (ret < 0)
goto err;
@@ -2302,13 +2310,14 @@ static int cma_alloc_any_port(struct radix_tree_root *ps,
static unsigned int last_used_port;
int low, high, remaining;
unsigned int rover;
+ struct net *net = id_priv->id.route.addr.dev_addr.net;
- inet_get_local_port_range(&init_net, &low, &high);
+ inet_get_local_port_range(net, &low, &high);
remaining = (high - low) + 1;
rover = prandom_u32() % remaining + low;
retry:
if (last_used_port != rover &&
- !cma_ps_find(ps, &init_net, (unsigned short)rover)) {
+ !cma_ps_find(ps, net, (unsigned short)rover)) {
int ret = cma_alloc_port(ps, id_priv, rover);
/*
* Remember previously used port number in order to avoid
@@ -2376,7 +2385,7 @@ static int cma_use_port(struct radix_tree_root *ps,
if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
return -EACCES;
- bind_list = cma_ps_find(ps, &init_net, snum);
+ bind_list = cma_ps_find(ps, id_priv->id.route.addr.dev_addr.net, snum);
if (!bind_list) {
ret = cma_alloc_port(ps, id_priv, snum);
} else {
@@ -2573,8 +2582,11 @@ int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr)
if (addr->sa_family == AF_INET)
id_priv->afonly = 1;
#if IS_ENABLED(CONFIG_IPV6)
- else if (addr->sa_family == AF_INET6)
- id_priv->afonly = init_net.ipv6.sysctl.bindv6only;
+ else if (addr->sa_family == AF_INET6) {
+ struct net *net = id_priv->id.route.addr.dev_addr.net;
+
+ id_priv->afonly = net->ipv6.sysctl.bindv6only;
+ }
#endif
}
ret = cma_get_port(id_priv);
@@ -2687,7 +2699,7 @@ static int cma_resolve_ib_udp(struct rdma_id_private *id_priv,
}
id = ib_create_cm_id(id_priv->id.device, cma_sidr_rep_handler,
- id_priv, &init_net);
+ id_priv, id_priv->id.route.addr.dev_addr.net);
if (IS_ERR(id)) {
ret = PTR_ERR(id);
goto out;
@@ -2737,7 +2749,7 @@ static int cma_connect_ib(struct rdma_id_private *id_priv,
conn_param->private_data_len);
id = ib_create_cm_id(id_priv->id.device, cma_ib_handler, id_priv,
- &init_net);
+ id_priv->id.route.addr.dev_addr.net);
if (IS_ERR(id)) {
ret = PTR_ERR(id);
goto out;
@@ -3387,6 +3399,7 @@ static int cma_netdev_change(struct net_device *ndev, struct rdma_id_private *id
dev_addr = &id_priv->id.route.addr.dev_addr;
if ((dev_addr->bound_dev_if == ndev->ifindex) &&
+ (net_eq(dev_net(ndev), dev_addr->net)) &&
memcmp(dev_addr->src_dev_addr, ndev->dev_addr, ndev->addr_len)) {
printk(KERN_INFO "RDMA CM addr change for ndev %s used by id %p\n",
ndev->name, &id_priv->id);
@@ -3412,9 +3425,6 @@ static int cma_netdev_callback(struct notifier_block *self, unsigned long event,
struct rdma_id_private *id_priv;
int ret = NOTIFY_DONE;
- if (dev_net(ndev) != &init_net)
- return NOTIFY_DONE;
-
if (event != NETDEV_BONDING_FAILOVER)
return NOTIFY_DONE;
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 56a4b7c..de755f2 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -391,7 +391,8 @@ static ssize_t ucma_create_id(struct ucma_file *file, const char __user *inbuf,
return -ENOMEM;
ctx->uid = cmd.uid;
- ctx->cm_id = rdma_create_id(ucma_event_handler, ctx, cmd.ps, qp_type);
+ ctx->cm_id = rdma_create_id(ucma_event_handler, ctx, cmd.ps, qp_type,
+ &init_net);
if (IS_ERR(ctx->cm_id)) {
ret = PTR_ERR(ctx->cm_id);
goto err1;
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index 695a270..d4e9c63 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -949,7 +949,7 @@ int iser_connect(struct iser_conn *iser_conn,
ib_conn->cma_id = rdma_create_id(iser_cma_handler,
(void *)iser_conn,
- RDMA_PS_TCP, IB_QPT_RC);
+ RDMA_PS_TCP, IB_QPT_RC, &init_net);
if (IS_ERR(ib_conn->cma_id)) {
err = PTR_ERR(ib_conn->cma_id);
iser_err("rdma_create_id failed: %d\n", err);
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index dafb3c5..44a6fff 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -2960,7 +2960,7 @@ isert_setup_id(struct isert_np *isert_np)
isert_dbg("ksockaddr: %p, sa: %p\n", &np->np_sockaddr, sa);
id = rdma_create_id(isert_cma_handler, isert_np,
- RDMA_PS_TCP, IB_QPT_RC);
+ RDMA_PS_TCP, IB_QPT_RC, &init_net);
if (IS_ERR(id)) {
isert_err("rdma_create_id() failed: %ld\n", PTR_ERR(id));
ret = PTR_ERR(id);
diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h
index b02b4ec..128de4e 100644
--- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h
+++ b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h
@@ -125,7 +125,9 @@ extern kib_tunables_t kiblnd_tunables;
IBLND_CREDIT_HIGHWATER_V1 : \
*kiblnd_tunables.kib_peercredits_hiw) /* when eagerly to return credits */
-#define kiblnd_rdma_create_id(cb, dev, ps, qpt) rdma_create_id(cb, dev, ps, qpt)
+#define kiblnd_rdma_create_id(cb, dev, ps, qpt) rdma_create_id(cb, dev, \
+ ps, qpt, \
+ &init_net)
static inline int
kiblnd_concurrent_sends_v1(void)
diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h
index 1ed2088..3953e9c 100644
--- a/include/rdma/rdma_cm.h
+++ b/include/rdma/rdma_cm.h
@@ -163,10 +163,14 @@ struct rdma_cm_id {
* @context: User specified context associated with the id.
* @ps: RDMA port space.
* @qp_type: type of queue pair associated with the id.
+ * @net: The network namespace in which to create the new id.
+ *
+ * The id holds a reference on the network namespace until it is destroyed.
*/
struct rdma_cm_id *rdma_create_id(rdma_cm_event_handler event_handler,
void *context, enum rdma_port_space ps,
- enum ib_qp_type qp_type);
+ enum ib_qp_type qp_type,
+ struct net *net);
/**
* rdma_destroy_id - Destroys an RDMA identifier.
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index 14ad43b..577fd31 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -635,7 +635,7 @@ rdma_create_trans(struct p9_client *client, const char *addr, char *args)
/* Create the RDMA CM ID */
rdma->cm_id = rdma_create_id(p9_cm_event_handler, client, RDMA_PS_TCP,
- IB_QPT_RC);
+ IB_QPT_RC, &init_net);
if (IS_ERR(rdma->cm_id))
goto error;
diff --git a/net/rds/ib.c b/net/rds/ib.c
index ba2dffe..cc137f5 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -326,7 +326,7 @@ static int rds_ib_laddr_check(__be32 addr)
/* Create a CMA ID and try to bind it. This catches both
* IB and iWARP capable NICs.
*/
- cm_id = rdma_create_id(NULL, NULL, RDMA_PS_TCP, IB_QPT_RC);
+ cm_id = rdma_create_id(NULL, NULL, RDMA_PS_TCP, IB_QPT_RC, &init_net);
if (IS_ERR(cm_id))
return PTR_ERR(cm_id);
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 31b74f5..d19b912 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -584,7 +584,7 @@ int rds_ib_conn_connect(struct rds_connection *conn)
/* XXX I wonder what affect the port space has */
/* delegate cm event handler to rdma_transport */
ic->i_cm_id = rdma_create_id(rds_rdma_cm_event_handler, conn,
- RDMA_PS_TCP, IB_QPT_RC);
+ RDMA_PS_TCP, IB_QPT_RC, &init_net);
if (IS_ERR(ic->i_cm_id)) {
ret = PTR_ERR(ic->i_cm_id);
ic->i_cm_id = NULL;
diff --git a/net/rds/iw.c b/net/rds/iw.c
index 5899356..8501b73 100644
--- a/net/rds/iw.c
+++ b/net/rds/iw.c
@@ -227,7 +227,7 @@ static int rds_iw_laddr_check(__be32 addr)
/* Create a CMA ID and try to bind it. This catches both
* IB and iWARP capable NICs.
*/
- cm_id = rdma_create_id(NULL, NULL, RDMA_PS_TCP, IB_QPT_RC);
+ cm_id = rdma_create_id(NULL, NULL, RDMA_PS_TCP, IB_QPT_RC, &init_net);
if (IS_ERR(cm_id))
return PTR_ERR(cm_id);
diff --git a/net/rds/iw_cm.c b/net/rds/iw_cm.c
index a91e1db..e5ee2d56 100644
--- a/net/rds/iw_cm.c
+++ b/net/rds/iw_cm.c
@@ -521,7 +521,7 @@ int rds_iw_conn_connect(struct rds_connection *conn)
/* XXX I wonder what affect the port space has */
/* delegate cm event handler to rdma_transport */
ic->i_cm_id = rdma_create_id(rds_rdma_cm_event_handler, conn,
- RDMA_PS_TCP, IB_QPT_RC);
+ RDMA_PS_TCP, IB_QPT_RC, &init_net);
if (IS_ERR(ic->i_cm_id)) {
ret = PTR_ERR(ic->i_cm_id);
ic->i_cm_id = NULL;
diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c
index 6cd9d1d..066b60b 100644
--- a/net/rds/rdma_transport.c
+++ b/net/rds/rdma_transport.c
@@ -160,7 +160,7 @@ static int rds_rdma_listen_init(void)
int ret;
cm_id = rdma_create_id(rds_rdma_cm_event_handler, NULL, RDMA_PS_TCP,
- IB_QPT_RC);
+ IB_QPT_RC, &init_net);
if (IS_ERR(cm_id)) {
ret = PTR_ERR(cm_id);
printk(KERN_ERR "RDS/RDMA: failed to setup listener, "
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 4e61880..e3b246e 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -701,7 +701,7 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
xprt = &cma_xprt->sc_xprt;
listen_id = rdma_create_id(rdma_listen_handler, cma_xprt, RDMA_PS_TCP,
- IB_QPT_RC);
+ IB_QPT_RC, &init_net);
if (IS_ERR(listen_id)) {
ret = PTR_ERR(listen_id);
dprintk("svcrdma: rdma_create_id failed = %d\n", ret);
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index c98e406..f574e77 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -483,7 +483,8 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt,
init_completion(&ia->ri_done);
- id = rdma_create_id(rpcrdma_conn_upcall, xprt, RDMA_PS_TCP, IB_QPT_RC);
+ id = rdma_create_id(rpcrdma_conn_upcall, xprt, RDMA_PS_TCP, IB_QPT_RC,
+ &init_net);
if (IS_ERR(id)) {
rc = PTR_ERR(id);
dprintk("RPC: %s: rdma_create_id() failed %i\n",
--
1.7.11.2
^ permalink raw reply related
* [PATCH v1 10/10] IB/ucm: Add partial support for network namespaces
From: Shachar Raindel @ 2015-02-11 15:06 UTC (permalink / raw)
To: roland, sean.hefty
Cc: linux-rdma, netdev, liranl, guysh, haggaie, yotamke, raindel
In-Reply-To: <1423667204-8807-1-git-send-email-raindel@mellanox.com>
It is impossible to completely support network namespaces for UCM, as
we cannot identify the target IPoIB device. However, we add support
which will work if the user is following the IB-Spec Annex 11 (RDMA IP
CM Services) with the service ID and private data formatting.
Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Yotam Kenneth <yotamke@mellanox.com>
Signed-off-by: Shachar Raindel <raindel@mellanox.com>
Signed-off-by: Guy Shapiro <guysh@mellanox.com>
---
drivers/infiniband/core/ucm.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/infiniband/core/ucm.c b/drivers/infiniband/core/ucm.c
index 9604ab0..4244210 100644
--- a/drivers/infiniband/core/ucm.c
+++ b/drivers/infiniband/core/ucm.c
@@ -45,6 +45,7 @@
#include <linux/idr.h>
#include <linux/mutex.h>
#include <linux/slab.h>
+#include <linux/nsproxy.h>
#include <asm/uaccess.h>
@@ -490,7 +491,7 @@ static ssize_t ib_ucm_create_id(struct ib_ucm_file *file,
ctx->uid = cmd.uid;
ctx->cm_id = ib_create_cm_id(file->device->ib_dev,
ib_ucm_event_handler, ctx,
- &init_net);
+ current->nsproxy->net_ns);
if (IS_ERR(ctx->cm_id)) {
result = PTR_ERR(ctx->cm_id);
goto err1;
--
1.7.11.2
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox