* Re: [RFC PATCH v1.1 0/2] PTP related changes for fm10k
From: Richard Cochran @ 2014-09-20 21:52 UTC (permalink / raw)
To: Alexander Duyck; +Cc: netdev
In-Reply-To: <20140920170138.25490.40273.stgit@ahduyck-bv4.jf.intel.com>
Looks ok to me, and removing the timecounter stuff makes sense.
For these two patches,
Acked-by: Richard Cochran <richardcochran@gmail.com>
^ permalink raw reply
* [PATCH net-next 0/3] net: Eliminate gso_send_check
From: Tom Herbert @ 2014-09-20 21:52 UTC (permalink / raw)
To: davem, netdev
gso_send_check presents a lot of complexity for what it is being used
for. It seems that there are only two cases where it might be effective:
TCP and UFO paths. In these cases, the gso_send_check function
initializes the TCP or UDP checksum respectively to the pseudo header
checksum so that the checksum computation is appropriately offloaded or
computed in the gso_segment functions. The gso_send_check functions
are only called from dev.c in skb_mac_gso_segment when ip_summed !=
CHECKSUM_PARTIAL (which seems very unlikely in TCP case). We can move
the logic of this into the respective gso_segment functions where the
checksum is initialized if ip_summed != CHECKSUM_PARTIAL.
With the above cases handled, gso_send_check is no longer needed, so
we can remove all uses of it and the fields in the offload callbacks.
With this change, ip_summed in the skb should be preserved though all
the layers of gso_segment calls.
In follow-on patches, we may be able to remove the check setup code in
tcp_gso_segment if we can guarantee that ip_summed will always be
CHECKSUM_PARTIAL (verify all paths and probably add an assert in
tcp_gro_segment).
Tested these patches by:
- netperf TCP_STREAM test with GSO enabled
- Forced ip_summed != CHECKSUM_PARTIAL with above
- Ran UDP_RR with 10000 request size over GRE tunnel. This exercised
UFO path.
Tom Herbert (3):
tcp: move logic out of tcp_v[64]_gso_send_check
udp: move logic out of udp[46]_ufo_send_check
net: Remove gso_send_check as an offload callback
include/linux/netdevice.h | 1 -
net/core/dev.c | 10 ----------
net/ipv4/af_inet.c | 36 ------------------------------------
net/ipv4/gre_offload.c | 11 +++--------
net/ipv4/tcp_offload.c | 45 +++++++++++++++++++++++----------------------
net/ipv4/udp_offload.c | 43 +++++++++++++++----------------------------
net/ipv6/ip6_offload.c | 27 ---------------------------
net/ipv6/tcpv6_offload.c | 43 ++++++++++++++++++++++++-------------------
net/ipv6/udp_offload.c | 46 ++++++++++++++++++----------------------------
net/mpls/mpls_gso.c | 7 -------
10 files changed, 83 insertions(+), 186 deletions(-)
--
2.1.0.rc2.206.gedb03e5
^ permalink raw reply
* [PATCH net-next 1/3] tcp: move logic out of tcp_v[64]_gso_send_check
From: Tom Herbert @ 2014-09-20 21:52 UTC (permalink / raw)
To: davem, netdev
In-Reply-To: <1411249950-6795-1-git-send-email-therbert@google.com>
In tcp_v[46]_gso_send_check the TCP checksum is initialized to the
pseudo header checksum using __tcp_v[46]_send_check. We can move this
logic into new tcp[46]_gso_segment functions to be done when
ip_summed != CHECKSUM_PARTIAL (ip_summed == CHECKSUM_PARTIAL should be
the common case, possibly always true when taking GSO path). After this
change tcp_v[46]_gso_send_check is no-op.
Signed-off-by: Tom Herbert <therbert@google.com>
---
net/ipv4/tcp_offload.c | 39 +++++++++++++++++++++++----------------
net/ipv6/tcpv6_offload.c | 37 ++++++++++++++++++++++++-------------
2 files changed, 47 insertions(+), 29 deletions(-)
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 7291253..7cd12b0 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -29,6 +29,28 @@ static void tcp_gso_tstamp(struct sk_buff *skb, unsigned int ts_seq,
}
}
+struct sk_buff *tcp4_gso_segment(struct sk_buff *skb,
+ netdev_features_t features)
+{
+ if (!pskb_may_pull(skb, sizeof(struct tcphdr)))
+ return ERR_PTR(-EINVAL);
+
+ if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
+ const struct iphdr *iph = ip_hdr(skb);
+ struct tcphdr *th = tcp_hdr(skb);
+
+ /* Set up checksum pseudo header, usually expect stack to
+ * have done this already.
+ */
+
+ th->check = 0;
+ skb->ip_summed = CHECKSUM_PARTIAL;
+ __tcp_v4_send_check(skb, iph->saddr, iph->daddr);
+ }
+
+ return tcp_gso_segment(skb, features);
+}
+
struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
netdev_features_t features)
{
@@ -44,9 +66,6 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
__sum16 newcheck;
bool ooo_okay, copy_destructor;
- if (!pskb_may_pull(skb, sizeof(*th)))
- goto out;
-
th = tcp_hdr(skb);
thlen = th->doff * 4;
if (thlen < sizeof(*th))
@@ -271,18 +290,6 @@ EXPORT_SYMBOL(tcp_gro_complete);
static int tcp_v4_gso_send_check(struct sk_buff *skb)
{
- const struct iphdr *iph;
- struct tcphdr *th;
-
- if (!pskb_may_pull(skb, sizeof(*th)))
- return -EINVAL;
-
- iph = ip_hdr(skb);
- th = tcp_hdr(skb);
-
- th->check = 0;
- skb->ip_summed = CHECKSUM_PARTIAL;
- __tcp_v4_send_check(skb, iph->saddr, iph->daddr);
return 0;
}
@@ -314,7 +321,7 @@ static int tcp4_gro_complete(struct sk_buff *skb, int thoff)
static const struct net_offload tcpv4_offload = {
.callbacks = {
.gso_send_check = tcp_v4_gso_send_check,
- .gso_segment = tcp_gso_segment,
+ .gso_segment = tcp4_gso_segment,
.gro_receive = tcp4_gro_receive,
.gro_complete = tcp4_gro_complete,
},
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index dbb3d92..9625315 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -17,18 +17,6 @@
static int tcp_v6_gso_send_check(struct sk_buff *skb)
{
- const struct ipv6hdr *ipv6h;
- struct tcphdr *th;
-
- if (!pskb_may_pull(skb, sizeof(*th)))
- return -EINVAL;
-
- ipv6h = ipv6_hdr(skb);
- th = tcp_hdr(skb);
-
- th->check = 0;
- skb->ip_summed = CHECKSUM_PARTIAL;
- __tcp_v6_send_check(skb, &ipv6h->saddr, &ipv6h->daddr);
return 0;
}
@@ -58,10 +46,33 @@ static int tcp6_gro_complete(struct sk_buff *skb, int thoff)
return tcp_gro_complete(skb);
}
+struct sk_buff *tcp6_gso_segment(struct sk_buff *skb,
+ netdev_features_t features)
+{
+ struct tcphdr *th;
+
+ if (!pskb_may_pull(skb, sizeof(*th)))
+ return ERR_PTR(-EINVAL);
+
+ if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
+ const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+ struct tcphdr *th = tcp_hdr(skb);
+
+ /* Set up pseudo header, usually expect stack to have done
+ * this.
+ */
+
+ th->check = 0;
+ skb->ip_summed = CHECKSUM_PARTIAL;
+ __tcp_v6_send_check(skb, &ipv6h->saddr, &ipv6h->daddr);
+ }
+
+ return tcp_gso_segment(skb, features);
+}
static const struct net_offload tcpv6_offload = {
.callbacks = {
.gso_send_check = tcp_v6_gso_send_check,
- .gso_segment = tcp_gso_segment,
+ .gso_segment = tcp6_gso_segment,
.gro_receive = tcp6_gro_receive,
.gro_complete = tcp6_gro_complete,
},
--
2.1.0.rc2.206.gedb03e5
^ permalink raw reply related
* [PATCH net-next 2/3] udp: move logic out of udp[46]_ufo_send_check
From: Tom Herbert @ 2014-09-20 21:52 UTC (permalink / raw)
To: davem, netdev
In-Reply-To: <1411249950-6795-1-git-send-email-therbert@google.com>
In udp[46]_ufo_send_check the UDP checksum initialized to the pseudo
header checksum. We can move this logic into udp[46]_ufo_fragment.
After this change udp[64]_ufo_send_check is a no-op.
Signed-off-by: Tom Herbert <therbert@google.com>
---
net/ipv4/udp_offload.c | 37 +++++++++++++++----------------------
net/ipv6/udp_offload.c | 40 ++++++++++++++++++----------------------
2 files changed, 33 insertions(+), 44 deletions(-)
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index d7c43f7..2918cc9 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -27,23 +27,6 @@ struct udp_offload_priv {
static int udp4_ufo_send_check(struct sk_buff *skb)
{
- if (!pskb_may_pull(skb, sizeof(struct udphdr)))
- return -EINVAL;
-
- if (likely(!skb->encapsulation)) {
- const struct iphdr *iph;
- struct udphdr *uh;
-
- iph = ip_hdr(skb);
- uh = udp_hdr(skb);
-
- uh->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len,
- IPPROTO_UDP, 0);
- skb->csum_start = skb_transport_header(skb) - skb->head;
- skb->csum_offset = offsetof(struct udphdr, check);
- skb->ip_summed = CHECKSUM_PARTIAL;
- }
-
return 0;
}
@@ -128,8 +111,9 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
unsigned int mss;
- int offset;
__wsum csum;
+ struct udphdr *uh;
+ struct iphdr *iph;
if (skb->encapsulation &&
(skb_shinfo(skb)->gso_type &
@@ -138,6 +122,9 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
goto out;
}
+ if (!pskb_may_pull(skb, sizeof(struct udphdr)))
+ goto out;
+
mss = skb_shinfo(skb)->gso_size;
if (unlikely(skb->len <= mss))
goto out;
@@ -165,10 +152,16 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
* HW cannot do checksum of UDP packets sent as multiple
* IP fragments.
*/
- offset = skb_checksum_start_offset(skb);
- csum = skb_checksum(skb, offset, skb->len - offset, 0);
- offset += skb->csum_offset;
- *(__sum16 *)(skb->data + offset) = csum_fold(csum);
+
+ uh = udp_hdr(skb);
+ iph = ip_hdr(skb);
+
+ uh->check = 0;
+ csum = skb_checksum(skb, 0, skb->len, 0);
+ uh->check = udp_v4_check(skb->len, iph->saddr, iph->daddr, csum);
+ if (uh->check == 0)
+ uh->check = CSUM_MANGLED_0;
+
skb->ip_summed = CHECKSUM_NONE;
/* Fragment the skb. IP headers of the fragments are updated in
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index de85f80..e4af643 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -19,23 +19,6 @@
static int udp6_ufo_send_check(struct sk_buff *skb)
{
- const struct ipv6hdr *ipv6h;
- struct udphdr *uh;
-
- if (!pskb_may_pull(skb, sizeof(*uh)))
- return -EINVAL;
-
- if (likely(!skb->encapsulation)) {
- ipv6h = ipv6_hdr(skb);
- uh = udp_hdr(skb);
-
- uh->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len,
- IPPROTO_UDP, 0);
- skb->csum_start = skb_transport_header(skb) - skb->head;
- skb->csum_offset = offsetof(struct udphdr, check);
- skb->ip_summed = CHECKSUM_PARTIAL;
- }
-
return 0;
}
@@ -49,7 +32,6 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
u8 *packet_start, *prevhdr;
u8 nexthdr;
u8 frag_hdr_sz = sizeof(struct frag_hdr);
- int offset;
__wsum csum;
int tnl_hlen;
@@ -83,13 +65,27 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
(SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))
segs = skb_udp_tunnel_segment(skb, features);
else {
+ const struct ipv6hdr *ipv6h;
+ struct udphdr *uh;
+
+ if (!pskb_may_pull(skb, sizeof(struct udphdr)))
+ goto out;
+
/* Do software UFO. Complete and fill in the UDP checksum as HW cannot
* do checksum of UDP packets sent as multiple IP fragments.
*/
- offset = skb_checksum_start_offset(skb);
- csum = skb_checksum(skb, offset, skb->len - offset, 0);
- offset += skb->csum_offset;
- *(__sum16 *)(skb->data + offset) = csum_fold(csum);
+
+ uh = udp_hdr(skb);
+ ipv6h = ipv6_hdr(skb);
+
+ uh->check = 0;
+ csum = skb_checksum(skb, 0, skb->len, 0);
+ uh->check = udp_v6_check(skb->len, &ipv6h->saddr,
+ &ipv6h->daddr, csum);
+
+ if (uh->check == 0)
+ uh->check = CSUM_MANGLED_0;
+
skb->ip_summed = CHECKSUM_NONE;
/* Check if there is enough headroom to insert fragment header. */
--
2.1.0.rc2.206.gedb03e5
^ permalink raw reply related
* [PATCH net-next 3/3] net: Remove gso_send_check as an offload callback
From: Tom Herbert @ 2014-09-20 21:52 UTC (permalink / raw)
To: davem, netdev
In-Reply-To: <1411249950-6795-1-git-send-email-therbert@google.com>
The send_check logic was only interesting in cases of TCP offload and
UDP UFO where the checksum needed to be initialized to the pseudo
header checksum. Now we've moved that logic into the related
gso_segment functions so gso_send_check is no longer needed.
Signed-off-by: Tom Herbert <therbert@google.com>
---
include/linux/netdevice.h | 1 -
net/core/dev.c | 10 ----------
net/ipv4/af_inet.c | 36 ------------------------------------
net/ipv4/gre_offload.c | 11 +++--------
net/ipv4/tcp_offload.c | 6 ------
net/ipv4/udp_offload.c | 6 ------
net/ipv6/ip6_offload.c | 27 ---------------------------
net/ipv6/tcpv6_offload.c | 6 ------
net/ipv6/udp_offload.c | 6 ------
net/mpls/mpls_gso.c | 7 -------
10 files changed, 3 insertions(+), 113 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 4354b43..9f5d293 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1911,7 +1911,6 @@ struct packet_type {
struct offload_callbacks {
struct sk_buff *(*gso_segment)(struct sk_buff *skb,
netdev_features_t features);
- int (*gso_send_check)(struct sk_buff *skb);
struct sk_buff **(*gro_receive)(struct sk_buff **head,
struct sk_buff *skb);
int (*gro_complete)(struct sk_buff *skb, int nhoff);
diff --git a/net/core/dev.c b/net/core/dev.c
index e916ba8..734bca4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2422,16 +2422,6 @@ struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
rcu_read_lock();
list_for_each_entry_rcu(ptype, &offload_base, list) {
if (ptype->type == type && ptype->callbacks.gso_segment) {
- if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
- int err;
-
- err = ptype->callbacks.gso_send_check(skb);
- segs = ERR_PTR(err);
- if (err || skb_gso_ok(skb, features))
- break;
- __skb_push(skb, (skb->data -
- skb_network_header(skb)));
- }
segs = ptype->callbacks.gso_segment(skb, features);
break;
}
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 72011cc..28e589c 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1197,40 +1197,6 @@ int inet_sk_rebuild_header(struct sock *sk)
}
EXPORT_SYMBOL(inet_sk_rebuild_header);
-static int inet_gso_send_check(struct sk_buff *skb)
-{
- const struct net_offload *ops;
- const struct iphdr *iph;
- int proto;
- int ihl;
- int err = -EINVAL;
-
- if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
- goto out;
-
- iph = ip_hdr(skb);
- ihl = iph->ihl * 4;
- if (ihl < sizeof(*iph))
- goto out;
-
- proto = iph->protocol;
-
- /* Warning: after this point, iph might be no longer valid */
- if (unlikely(!pskb_may_pull(skb, ihl)))
- goto out;
- __skb_pull(skb, ihl);
-
- skb_reset_transport_header(skb);
- err = -EPROTONOSUPPORT;
-
- ops = rcu_dereference(inet_offloads[proto]);
- if (likely(ops && ops->callbacks.gso_send_check))
- err = ops->callbacks.gso_send_check(skb);
-
-out:
- return err;
-}
-
static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
netdev_features_t features)
{
@@ -1655,7 +1621,6 @@ static int ipv4_proc_init(void);
static struct packet_offload ip_packet_offload __read_mostly = {
.type = cpu_to_be16(ETH_P_IP),
.callbacks = {
- .gso_send_check = inet_gso_send_check,
.gso_segment = inet_gso_segment,
.gro_receive = inet_gro_receive,
.gro_complete = inet_gro_complete,
@@ -1664,7 +1629,6 @@ static struct packet_offload ip_packet_offload __read_mostly = {
static const struct net_offload ipip_offload = {
.callbacks = {
- .gso_send_check = inet_gso_send_check,
.gso_segment = inet_gso_segment,
.gro_receive = inet_gro_receive,
.gro_complete = inet_gro_complete,
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index d3fe2ac..a777295 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -15,13 +15,6 @@
#include <net/protocol.h>
#include <net/gre.h>
-static int gre_gso_send_check(struct sk_buff *skb)
-{
- if (!skb->encapsulation)
- return -EINVAL;
- return 0;
-}
-
static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
netdev_features_t features)
{
@@ -46,6 +39,9 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
SKB_GSO_IPIP)))
goto out;
+ if (!skb->encapsulation)
+ goto out;
+
if (unlikely(!pskb_may_pull(skb, sizeof(*greh))))
goto out;
@@ -256,7 +252,6 @@ static int gre_gro_complete(struct sk_buff *skb, int nhoff)
static const struct net_offload gre_offload = {
.callbacks = {
- .gso_send_check = gre_gso_send_check,
.gso_segment = gre_gso_segment,
.gro_receive = gre_gro_receive,
.gro_complete = gre_gro_complete,
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 7cd12b0..5b90f2f 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -288,11 +288,6 @@ int tcp_gro_complete(struct sk_buff *skb)
}
EXPORT_SYMBOL(tcp_gro_complete);
-static int tcp_v4_gso_send_check(struct sk_buff *skb)
-{
- return 0;
-}
-
static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
{
/* Don't bother verifying checksum if we're going to flush anyway. */
@@ -320,7 +315,6 @@ static int tcp4_gro_complete(struct sk_buff *skb, int thoff)
static const struct net_offload tcpv4_offload = {
.callbacks = {
- .gso_send_check = tcp_v4_gso_send_check,
.gso_segment = tcp4_gso_segment,
.gro_receive = tcp4_gro_receive,
.gro_complete = tcp4_gro_complete,
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 2918cc9..19ebe6a 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -25,11 +25,6 @@ struct udp_offload_priv {
struct udp_offload_priv __rcu *next;
};
-static int udp4_ufo_send_check(struct sk_buff *skb)
-{
- return 0;
-}
-
struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
netdev_features_t features)
{
@@ -346,7 +341,6 @@ static int udp4_gro_complete(struct sk_buff *skb, int nhoff)
static const struct net_offload udpv4_offload = {
.callbacks = {
- .gso_send_check = udp4_ufo_send_check,
.gso_segment = udp4_ufo_fragment,
.gro_receive = udp4_gro_receive,
.gro_complete = udp4_gro_complete,
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 9952f3f..9034f76 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -53,31 +53,6 @@ static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto)
return proto;
}
-static int ipv6_gso_send_check(struct sk_buff *skb)
-{
- const struct ipv6hdr *ipv6h;
- const struct net_offload *ops;
- int err = -EINVAL;
-
- if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
- goto out;
-
- ipv6h = ipv6_hdr(skb);
- __skb_pull(skb, sizeof(*ipv6h));
- err = -EPROTONOSUPPORT;
-
- ops = rcu_dereference(inet6_offloads[
- ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr)]);
-
- if (likely(ops && ops->callbacks.gso_send_check)) {
- skb_reset_transport_header(skb);
- err = ops->callbacks.gso_send_check(skb);
- }
-
-out:
- return err;
-}
-
static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
netdev_features_t features)
{
@@ -306,7 +281,6 @@ out_unlock:
static struct packet_offload ipv6_packet_offload __read_mostly = {
.type = cpu_to_be16(ETH_P_IPV6),
.callbacks = {
- .gso_send_check = ipv6_gso_send_check,
.gso_segment = ipv6_gso_segment,
.gro_receive = ipv6_gro_receive,
.gro_complete = ipv6_gro_complete,
@@ -315,7 +289,6 @@ static struct packet_offload ipv6_packet_offload __read_mostly = {
static const struct net_offload sit_offload = {
.callbacks = {
- .gso_send_check = ipv6_gso_send_check,
.gso_segment = ipv6_gso_segment,
.gro_receive = ipv6_gro_receive,
.gro_complete = ipv6_gro_complete,
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index 9625315..c1ab771 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -15,11 +15,6 @@
#include <net/ip6_checksum.h>
#include "ip6_offload.h"
-static int tcp_v6_gso_send_check(struct sk_buff *skb)
-{
- return 0;
-}
-
static struct sk_buff **tcp6_gro_receive(struct sk_buff **head,
struct sk_buff *skb)
{
@@ -71,7 +66,6 @@ struct sk_buff *tcp6_gso_segment(struct sk_buff *skb,
}
static const struct net_offload tcpv6_offload = {
.callbacks = {
- .gso_send_check = tcp_v6_gso_send_check,
.gso_segment = tcp6_gso_segment,
.gro_receive = tcp6_gro_receive,
.gro_complete = tcp6_gro_complete,
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index e4af643..212ebfc 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -17,11 +17,6 @@
#include <net/ip6_checksum.h>
#include "ip6_offload.h"
-static int udp6_ufo_send_check(struct sk_buff *skb)
-{
- return 0;
-}
-
static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
netdev_features_t features)
{
@@ -166,7 +161,6 @@ static int udp6_gro_complete(struct sk_buff *skb, int nhoff)
static const struct net_offload udpv6_offload = {
.callbacks = {
- .gso_send_check = udp6_ufo_send_check,
.gso_segment = udp6_ufo_fragment,
.gro_receive = udp6_gro_receive,
.gro_complete = udp6_gro_complete,
diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c
index 6b38d08..e28ed2e 100644
--- a/net/mpls/mpls_gso.c
+++ b/net/mpls/mpls_gso.c
@@ -65,15 +65,9 @@ out:
return segs;
}
-static int mpls_gso_send_check(struct sk_buff *skb)
-{
- return 0;
-}
-
static struct packet_offload mpls_mc_offload = {
.type = cpu_to_be16(ETH_P_MPLS_MC),
.callbacks = {
- .gso_send_check = mpls_gso_send_check,
.gso_segment = mpls_gso_segment,
},
};
@@ -81,7 +75,6 @@ static struct packet_offload mpls_mc_offload = {
static struct packet_offload mpls_uc_offload = {
.type = cpu_to_be16(ETH_P_MPLS_UC),
.callbacks = {
- .gso_send_check = mpls_gso_send_check,
.gso_segment = mpls_gso_segment,
},
};
--
2.1.0.rc2.206.gedb03e5
^ permalink raw reply related
* [PATCH net-next 0/8] ipv6: fib6: socket dst_entry improvments and cleanups
From: Hannes Frederic Sowa @ 2014-09-20 22:05 UTC (permalink / raw)
To: netdev; +Cc: eric.dumazet, vyasevich, nicolas.dichtel, kafai
Eric Dumazet noticed that rt6_nodes wich are neither RTF_NONEXTHOP nor
RTF_GATEWAY but DST_HOST ones cause major routing lookup churn because
their rt6_genid is never renewed, thus ip6_dst_check always considers
them outdated. This is a major problem, because these kind of routes
are normally used to in input handling.
Thus it does not make sense to use rt6i_genid anymore. This series
removes it.
The address deletion path is already covered and does not depend on
rt6i_genid. When we add a new address, we update the fn_sernums while
traversing the tree.
Because inet6_connect_socket depend on dst_check returning NULL also
for source address invalidation, we currently have to walk the whole
tree and update the fn_sernums manually when an address gets deleted.
This is a fairly expensive operation we currenlty have to do for address
deletion and xfrm policy changes. We currently do that for interface
mtu changes already.
I dropped the patch for updating the fn_sernum on deletion as it
showed some side effects with /proc/net/ipv6_route and we currently
don't need it. I stashed it away.
Thanks to Eric Dumazet for noticing the problem with rt6i_genid!
Hannes Frederic Sowa (8):
ipv6: support for fib6_clean_* to update fn_sernum
ipv6: a bit more typesafety
ipv6: only generate one new serial number during fib6_add()
ipv6: if no function for cleaner is specified only visit fib6_nodes
ipv6: new function fib6_flush_trees and use it instead of bumping
removed rt6_genid
ipv6: no need to bump rt_genid_ipv6 on address addition
ipv6: keep rt_sernum per namespace to reduce number of flushes
ipv6: switch rt_sernum to atomic_t and clean up types
include/net/ip6_fib.h | 16 ++++++--
include/net/net_namespace.h | 14 ++-----
include/net/netns/ipv6.h | 2 +-
net/ipv6/addrconf.c | 3 +-
net/ipv6/addrconf_core.c | 6 +++
net/ipv6/af_inet6.c | 2 +-
net/ipv6/ip6_fib.c | 90 +++++++++++++++++++++++++++------------------
net/ipv6/route.c | 4 --
8 files changed, 81 insertions(+), 56 deletions(-)
--
1.9.3
^ permalink raw reply
* [PATCH net-next 1/8] ipv6: support for fib6_clean_* to update fn_sernum
From: Hannes Frederic Sowa @ 2014-09-20 22:05 UTC (permalink / raw)
To: netdev; +Cc: eric.dumazet, vyasevich, nicolas.dichtel, kafai
In-Reply-To: <cover.1411249633.git.hannes@stressinduktion.org>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
---
include/net/ip6_fib.h | 2 +-
net/ipv6/ip6_fib.c | 29 +++++++++++++++++++----------
2 files changed, 20 insertions(+), 11 deletions(-)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 9bcb220..1cdd46e 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -64,7 +64,7 @@ struct fib6_node {
__u16 fn_bit; /* bit key */
__u16 fn_flags;
- __u32 fn_sernum;
+ u32 fn_sernum;
struct rt6_info *rr_ptr;
};
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 76b7f5e..559d03c 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -60,6 +60,7 @@ struct fib6_cleaner_t {
struct fib6_walker_t w;
struct net *net;
int (*func)(struct rt6_info *, void *arg);
+ u32 sernum;
void *arg;
};
@@ -71,7 +72,8 @@ static DEFINE_RWLOCK(fib6_walker_lock);
#define FWS_INIT FWS_L
#endif
-static void fib6_prune_clones(struct net *net, struct fib6_node *fn);
+static void fib6_prune_clones(struct net *net, struct fib6_node *fn,
+ u32 sernum);
static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn);
static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_node *fn);
static int fib6_walk(struct fib6_walker_t *w);
@@ -84,7 +86,7 @@ static int fib6_walk_continue(struct fib6_walker_t *w);
* result of redirects, path MTU changes, etc.
*/
-static __u32 rt_sernum;
+static u32 rt_sernum;
static void fib6_gc_timer_cb(unsigned long arg);
@@ -112,6 +114,8 @@ static __inline__ u32 fib6_new_sernum(void)
return n;
}
+#define FIB6_NO_SERNUM_CHANGE (0U)
+
/*
* Auxiliary address test functions for the radix tree.
*
@@ -430,7 +434,7 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root,
struct rt6key *key;
int bit;
__be32 dir = 0;
- __u32 sernum = fib6_new_sernum();
+ u32 sernum = fib6_new_sernum();
RT6_TRACE("fib6_add_1\n");
@@ -940,7 +944,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
if (!err) {
fib6_start_gc(info->nl_net, rt);
if (!(rt->rt6i_flags & RTF_CACHE))
- fib6_prune_clones(info->nl_net, pn);
+ fib6_prune_clones(info->nl_net, pn,
+ FIB6_NO_SERNUM_CHANGE);
}
out:
@@ -1374,7 +1379,7 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info)
pn = pn->parent;
}
#endif
- fib6_prune_clones(info->nl_net, pn);
+ fib6_prune_clones(info->nl_net, pn, FIB6_NO_SERNUM_CHANGE);
}
/*
@@ -1521,6 +1526,9 @@ static int fib6_clean_node(struct fib6_walker_t *w)
.nl_net = c->net,
};
+ if (c->sernum != FIB6_NO_SERNUM_CHANGE)
+ c->w.node->fn_sernum = c->sernum;
+
for (rt = w->leaf; rt; rt = rt->dst.rt6_next) {
res = c->func(rt, c->arg);
if (res < 0) {
@@ -1554,7 +1562,7 @@ static int fib6_clean_node(struct fib6_walker_t *w)
static void fib6_clean_tree(struct net *net, struct fib6_node *root,
int (*func)(struct rt6_info *, void *arg),
- int prune, void *arg)
+ int prune, u32 sernum, void *arg)
{
struct fib6_cleaner_t c;
@@ -1564,6 +1572,7 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root,
c.w.count = 0;
c.w.skip = 0;
c.func = func;
+ c.sernum = sernum;
c.arg = arg;
c.net = net;
@@ -1583,7 +1592,7 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
hlist_for_each_entry_rcu(table, head, tb6_hlist) {
write_lock_bh(&table->tb6_lock);
fib6_clean_tree(net, &table->tb6_root,
- func, 0, arg);
+ func, 0, FIB6_NO_SERNUM_CHANGE, arg);
write_unlock_bh(&table->tb6_lock);
}
}
@@ -1600,9 +1609,9 @@ static int fib6_prune_clone(struct rt6_info *rt, void *arg)
return 0;
}
-static void fib6_prune_clones(struct net *net, struct fib6_node *fn)
+static void fib6_prune_clones(struct net *net, struct fib6_node *fn, u32 sernum)
{
- fib6_clean_tree(net, fn, fib6_prune_clone, 1, NULL);
+ fib6_clean_tree(net, fn, fib6_prune_clone, 1, sernum, NULL);
}
/*
@@ -1811,7 +1820,7 @@ struct ipv6_route_iter {
struct fib6_walker_t w;
loff_t skip;
struct fib6_table *tbl;
- __u32 sernum;
+ u32 sernum;
};
static int ipv6_route_seq_show(struct seq_file *seq, void *v)
--
1.9.3
^ permalink raw reply related
* [PATCH net-next 2/8] ipv6: a bit more typesafety
From: Hannes Frederic Sowa @ 2014-09-20 22:05 UTC (permalink / raw)
To: netdev; +Cc: eric.dumazet, vyasevich, nicolas.dichtel, kafai
In-Reply-To: <cover.1411249633.git.hannes@stressinduktion.org>
Convert bool to bool and fib6_walker_t.state to the already existing enum.
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
---
include/net/ip6_fib.h | 14 ++++++++++++--
net/ipv6/ip6_fib.c | 17 ++++-------------
2 files changed, 16 insertions(+), 15 deletions(-)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 1cdd46e..a09e554 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -205,12 +205,22 @@ static inline void ip6_rt_put(struct rt6_info *rt)
dst_release(&rt->dst);
}
+enum fib_walk_state_t {
+#ifdef CONFIG_IPV6_SUBTREES
+ FWS_S,
+#endif
+ FWS_L,
+ FWS_R,
+ FWS_C,
+ FWS_U
+};
+
struct fib6_walker_t {
struct list_head lh;
struct fib6_node *root, *node;
struct rt6_info *leaf;
- unsigned char state;
- unsigned char prune;
+ enum fib_walk_state_t state;
+ bool prune;
unsigned int skip;
unsigned int count;
int (*func)(struct fib6_walker_t *);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 559d03c..c5e7e04 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -46,16 +46,6 @@
static struct kmem_cache *fib6_node_kmem __read_mostly;
-enum fib_walk_state_t {
-#ifdef CONFIG_IPV6_SUBTREES
- FWS_S,
-#endif
- FWS_L,
- FWS_R,
- FWS_C,
- FWS_U
-};
-
struct fib6_cleaner_t {
struct fib6_walker_t w;
struct net *net;
@@ -1562,7 +1552,7 @@ static int fib6_clean_node(struct fib6_walker_t *w)
static void fib6_clean_tree(struct net *net, struct fib6_node *root,
int (*func)(struct rt6_info *, void *arg),
- int prune, u32 sernum, void *arg)
+ bool prune, u32 sernum, void *arg)
{
struct fib6_cleaner_t c;
@@ -1592,7 +1582,8 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
hlist_for_each_entry_rcu(table, head, tb6_hlist) {
write_lock_bh(&table->tb6_lock);
fib6_clean_tree(net, &table->tb6_root,
- func, 0, FIB6_NO_SERNUM_CHANGE, arg);
+ func, false, FIB6_NO_SERNUM_CHANGE,
+ arg);
write_unlock_bh(&table->tb6_lock);
}
}
@@ -1611,7 +1602,7 @@ static int fib6_prune_clone(struct rt6_info *rt, void *arg)
static void fib6_prune_clones(struct net *net, struct fib6_node *fn, u32 sernum)
{
- fib6_clean_tree(net, fn, fib6_prune_clone, 1, sernum, NULL);
+ fib6_clean_tree(net, fn, fib6_prune_clone, true, sernum, NULL);
}
/*
--
1.9.3
^ permalink raw reply related
* [PATCH net-next 3/8] ipv6: only generate one new serial number during fib6_add()
From: Hannes Frederic Sowa @ 2014-09-20 22:05 UTC (permalink / raw)
To: netdev; +Cc: eric.dumazet, vyasevich, nicolas.dichtel, kafai
In-Reply-To: <cover.1411249633.git.hannes@stressinduktion.org>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
---
net/ipv6/ip6_fib.c | 19 +++++++++----------
1 file changed, 9 insertions(+), 10 deletions(-)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index c5e7e04..0725fc1 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -415,16 +415,15 @@ out:
*/
static struct fib6_node *fib6_add_1(struct fib6_node *root,
- struct in6_addr *addr, int plen,
- int offset, int allow_create,
- int replace_required)
+ struct in6_addr *addr, int plen,
+ int offset, int allow_create,
+ int replace_required, u32 sernum)
{
struct fib6_node *fn, *in, *ln;
struct fib6_node *pn = NULL;
struct rt6key *key;
int bit;
__be32 dir = 0;
- u32 sernum = fib6_new_sernum();
RT6_TRACE("fib6_add_1\n");
@@ -842,6 +841,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
int err = -ENOMEM;
int allow_create = 1;
int replace_required = 0;
+ u32 sernum = fib6_new_sernum();
if (info->nlh) {
if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
@@ -854,7 +854,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
fn = fib6_add_1(root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen,
offsetof(struct rt6_info, rt6i_dst), allow_create,
- replace_required);
+ replace_required, sernum);
if (IS_ERR(fn)) {
err = PTR_ERR(fn);
fn = NULL;
@@ -888,14 +888,14 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
sfn->leaf = info->nl_net->ipv6.ip6_null_entry;
atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref);
sfn->fn_flags = RTN_ROOT;
- sfn->fn_sernum = fib6_new_sernum();
+ sfn->fn_sernum = sernum;
/* Now add the first leaf node to new subtree */
sn = fib6_add_1(sfn, &rt->rt6i_src.addr,
rt->rt6i_src.plen,
offsetof(struct rt6_info, rt6i_src),
- allow_create, replace_required);
+ allow_create, replace_required, sernum);
if (IS_ERR(sn)) {
/* If it is failed, discard just allocated
@@ -914,7 +914,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr,
rt->rt6i_src.plen,
offsetof(struct rt6_info, rt6i_src),
- allow_create, replace_required);
+ allow_create, replace_required, sernum);
if (IS_ERR(sn)) {
err = PTR_ERR(sn);
@@ -934,8 +934,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
if (!err) {
fib6_start_gc(info->nl_net, rt);
if (!(rt->rt6i_flags & RTF_CACHE))
- fib6_prune_clones(info->nl_net, pn,
- FIB6_NO_SERNUM_CHANGE);
+ fib6_prune_clones(info->nl_net, pn, sernum);
}
out:
--
1.9.3
^ permalink raw reply related
* [PATCH net-next 4/8] ipv6: if no function for cleaner is specified only visit fib6_nodes
From: Hannes Frederic Sowa @ 2014-09-20 22:05 UTC (permalink / raw)
To: netdev; +Cc: eric.dumazet, vyasevich, nicolas.dichtel, kafai
In-Reply-To: <cover.1411249633.git.hannes@stressinduktion.org>
We now allow NULL rt6_info walker functions to we only visit nodes.
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
---
net/ipv6/ip6_fib.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 0725fc1..8db8b1c 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1518,6 +1518,12 @@ static int fib6_clean_node(struct fib6_walker_t *w)
if (c->sernum != FIB6_NO_SERNUM_CHANGE)
c->w.node->fn_sernum = c->sernum;
+ if (!c->func) {
+ WARN_ON_ONCE(c->sernum == FIB6_NO_SERNUM_CHANGE);
+ w->leaf = NULL;
+ return 0;
+ }
+
for (rt = w->leaf; rt; rt = rt->dst.rt6_next) {
res = c->func(rt, c->arg);
if (res < 0) {
--
1.9.3
^ permalink raw reply related
* [PATCH net-next 5/8] ipv6: new function fib6_flush_trees and use it instead of bumping removed rt6_genid
From: Hannes Frederic Sowa @ 2014-09-20 22:05 UTC (permalink / raw)
To: netdev; +Cc: eric.dumazet, vyasevich, nicolas.dichtel, kafai
In-Reply-To: <cover.1411249633.git.hannes@stressinduktion.org>
fib6_flush_trees is still a very costly operation but now is only called
by xfrm code when a policy changes or ipv6 addresses are added/removed.
fib6_flush_tree must walk all ipv6 routing tables and modify fn_sernum,
so all sockets relookup their dst_entries. Use a NULL callback, so we
only walk the nodes without looking at the rt6_infos.
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
---
include/net/net_namespace.h | 14 +++-----------
include/net/netns/ipv6.h | 1 -
net/ipv6/addrconf_core.c | 6 ++++++
net/ipv6/af_inet6.c | 1 -
net/ipv6/ip6_fib.c | 21 +++++++++++++++++----
net/ipv6/route.c | 4 ----
6 files changed, 26 insertions(+), 21 deletions(-)
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 361d260..61aad36 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -353,21 +353,13 @@ static inline void rt_genid_bump_ipv4(struct net *net)
}
#if IS_ENABLED(CONFIG_IPV6)
-static inline int rt_genid_ipv6(struct net *net)
-{
- return atomic_read(&net->ipv6.rt_genid);
-}
-
+extern void (*__fib6_flush_trees)(struct net *);
static inline void rt_genid_bump_ipv6(struct net *net)
{
- atomic_inc(&net->ipv6.rt_genid);
+ if (__fib6_flush_trees)
+ __fib6_flush_trees(net);
}
#else
-static inline int rt_genid_ipv6(struct net *net)
-{
- return 0;
-}
-
static inline void rt_genid_bump_ipv6(struct net *net)
{
}
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index eade27a..3291ba6 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -76,7 +76,6 @@ struct netns_ipv6 {
#endif
#endif
atomic_t dev_addr_genid;
- atomic_t rt_genid;
};
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index e696045..8b2d99a 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -10,6 +10,12 @@
#define IPV6_ADDR_SCOPE_TYPE(scope) ((scope) << 16)
+/* if ipv6 module registers this function is used by xfrm to force
+ * all sockets to relookup their nodes - this is fairly expensive
+ */
+void (*__fib6_flush_trees)(struct net *);
+EXPORT_SYMBOL(__fib6_flush_trees);
+
static inline unsigned int ipv6_addr_scope2type(unsigned int scope)
{
switch (scope) {
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index e4865a3..2189d2d 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -766,7 +766,6 @@ static int __net_init inet6_net_init(struct net *net)
net->ipv6.sysctl.icmpv6_time = 1*HZ;
net->ipv6.sysctl.flowlabel_consistency = 1;
net->ipv6.sysctl.auto_flowlabels = 0;
- atomic_set(&net->ipv6.rt_genid, 0);
err = ipv6_init_mibs(net);
if (err)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 8db8b1c..0fe9241 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1574,8 +1574,9 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root,
fib6_walk(&c.w);
}
-void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
- void *arg)
+void __fib6_clean_all(struct net *net,
+ int (*func)(struct rt6_info *, void *arg),
+ u32 sernum, void *arg)
{
struct fib6_table *table;
struct hlist_head *head;
@@ -1587,14 +1588,24 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
hlist_for_each_entry_rcu(table, head, tb6_hlist) {
write_lock_bh(&table->tb6_lock);
fib6_clean_tree(net, &table->tb6_root,
- func, false, FIB6_NO_SERNUM_CHANGE,
- arg);
+ func, false, sernum, arg);
write_unlock_bh(&table->tb6_lock);
}
}
rcu_read_unlock();
}
+void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
+ void *arg)
+{
+ __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg);
+}
+
+static void fib6_flush_trees(struct net *net)
+{
+ __fib6_clean_all(net, NULL, fib6_new_sernum(), NULL);
+}
+
static int fib6_prune_clone(struct rt6_info *rt, void *arg)
{
if (rt->rt6i_flags & RTF_CACHE) {
@@ -1793,6 +1804,8 @@ int __init fib6_init(void)
NULL);
if (ret)
goto out_unregister_subsys;
+
+ __fib6_flush_trees = fib6_flush_trees;
out:
return ret;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index f74b041..a318dd89 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -314,7 +314,6 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net,
memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst));
rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers);
- rt->rt6i_genid = rt_genid_ipv6(net);
INIT_LIST_HEAD(&rt->rt6i_siblings);
}
return rt;
@@ -1096,9 +1095,6 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
* DST_OBSOLETE_FORCE_CHK which forces validation calls down
* into this function always.
*/
- if (rt->rt6i_genid != rt_genid_ipv6(dev_net(rt->dst.dev)))
- return NULL;
-
if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie))
return NULL;
--
1.9.3
^ permalink raw reply related
* [PATCH net-next 6/8] ipv6: no need to bump rt_genid_ipv6 on address addition
From: Hannes Frederic Sowa @ 2014-09-20 22:05 UTC (permalink / raw)
To: netdev; +Cc: eric.dumazet, vyasevich, nicolas.dichtel, kafai
In-Reply-To: <cover.1411249633.git.hannes@stressinduktion.org>
fn_sernum takes care that on address insertion the sockets throw away
their cached dst_entries and do a relookup.
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
---
net/ipv6/addrconf.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 39d3335..a2d2626 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4781,10 +4781,11 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
if (ip6_del_rt(ifp->rt))
dst_free(&ifp->rt->dst);
+
+ rt_genid_bump_ipv6(net);
break;
}
atomic_inc(&net->ipv6.dev_addr_genid);
- rt_genid_bump_ipv6(net);
}
static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
--
1.9.3
^ permalink raw reply related
* [PATCH net-next 7/8] ipv6: keep rt_sernum per namespace to reduce number of flushes
From: Hannes Frederic Sowa @ 2014-09-20 22:05 UTC (permalink / raw)
To: netdev; +Cc: eric.dumazet, vyasevich, nicolas.dichtel, kafai
In-Reply-To: <cover.1411249633.git.hannes@stressinduktion.org>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
---
include/net/netns/ipv6.h | 1 +
net/ipv6/af_inet6.c | 1 +
net/ipv6/ip6_fib.c | 19 ++++++++++---------
3 files changed, 12 insertions(+), 9 deletions(-)
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 3291ba6..2319949 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -76,6 +76,7 @@ struct netns_ipv6 {
#endif
#endif
atomic_t dev_addr_genid;
+ u32 rt_sernum;
};
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 2189d2d..7ff8996 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -766,6 +766,7 @@ static int __net_init inet6_net_init(struct net *net)
net->ipv6.sysctl.icmpv6_time = 1*HZ;
net->ipv6.sysctl.flowlabel_consistency = 1;
net->ipv6.sysctl.auto_flowlabels = 0;
+ net->ipv6.rt_sernum = 1;
err = ipv6_init_mibs(net);
if (err)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 0fe9241..9f973e4 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -76,8 +76,6 @@ static int fib6_walk_continue(struct fib6_walker_t *w);
* result of redirects, path MTU changes, etc.
*/
-static u32 rt_sernum;
-
static void fib6_gc_timer_cb(unsigned long arg);
static LIST_HEAD(fib6_walkers);
@@ -96,12 +94,15 @@ static inline void fib6_walker_unlink(struct fib6_walker_t *w)
list_del(&w->lh);
write_unlock_bh(&fib6_walker_lock);
}
-static __inline__ u32 fib6_new_sernum(void)
+
+static u32 fib6_new_sernum(struct net *net)
{
- u32 n = ++rt_sernum;
- if ((__s32)n <= 0)
- rt_sernum = n = 1;
- return n;
+ int *n = &net->ipv6.rt_sernum;
+
+ ++*n;
+ if ((s32)*n <= 0)
+ *n = 1;
+ return *n;
}
#define FIB6_NO_SERNUM_CHANGE (0U)
@@ -841,7 +842,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
int err = -ENOMEM;
int allow_create = 1;
int replace_required = 0;
- u32 sernum = fib6_new_sernum();
+ u32 sernum = fib6_new_sernum(dev_net(rt->dst.dev));
if (info->nlh) {
if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
@@ -1603,7 +1604,7 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
static void fib6_flush_trees(struct net *net)
{
- __fib6_clean_all(net, NULL, fib6_new_sernum(), NULL);
+ __fib6_clean_all(net, NULL, fib6_new_sernum(net), NULL);
}
static int fib6_prune_clone(struct rt6_info *rt, void *arg)
--
1.9.3
^ permalink raw reply related
* [PATCH net-next 8/8] ipv6: switch rt_sernum to atomic_t and clean up types
From: Hannes Frederic Sowa @ 2014-09-20 22:05 UTC (permalink / raw)
To: netdev; +Cc: eric.dumazet, vyasevich, nicolas.dichtel, kafai
In-Reply-To: <cover.1411249633.git.hannes@stressinduktion.org>
Switch rt_sernum to atomic_t, make it concurrency safe (the old scheme
looked broken to me) and switch from u32 to int types for the fn_sernum.
(fib6_new_sernum only gets used with table locks, but different tables
can get mutated at the same time.)
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
---
include/net/ip6_fib.h | 2 +-
include/net/netns/ipv6.h | 2 +-
net/ipv6/af_inet6.c | 2 +-
net/ipv6/ip6_fib.c | 29 +++++++++++++++--------------
4 files changed, 18 insertions(+), 17 deletions(-)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index a09e554..5440f99 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -64,7 +64,7 @@ struct fib6_node {
__u16 fn_bit; /* bit key */
__u16 fn_flags;
- u32 fn_sernum;
+ int fn_sernum;
struct rt6_info *rr_ptr;
};
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 2319949..7dee21b 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -76,7 +76,7 @@ struct netns_ipv6 {
#endif
#endif
atomic_t dev_addr_genid;
- u32 rt_sernum;
+ atomic_t rt_sernum;
};
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 7ff8996..6cde9b4 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -766,7 +766,7 @@ static int __net_init inet6_net_init(struct net *net)
net->ipv6.sysctl.icmpv6_time = 1*HZ;
net->ipv6.sysctl.flowlabel_consistency = 1;
net->ipv6.sysctl.auto_flowlabels = 0;
- net->ipv6.rt_sernum = 1;
+ atomic_set(&net->ipv6.rt_sernum, 1);
err = ipv6_init_mibs(net);
if (err)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 9f973e4..ae87d0c 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -50,7 +50,7 @@ struct fib6_cleaner_t {
struct fib6_walker_t w;
struct net *net;
int (*func)(struct rt6_info *, void *arg);
- u32 sernum;
+ int sernum;
void *arg;
};
@@ -63,7 +63,7 @@ static DEFINE_RWLOCK(fib6_walker_lock);
#endif
static void fib6_prune_clones(struct net *net, struct fib6_node *fn,
- u32 sernum);
+ int sernum);
static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn);
static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_node *fn);
static int fib6_walk(struct fib6_walker_t *w);
@@ -97,15 +97,16 @@ static inline void fib6_walker_unlink(struct fib6_walker_t *w)
static u32 fib6_new_sernum(struct net *net)
{
- int *n = &net->ipv6.rt_sernum;
+ int old, new;
- ++*n;
- if ((s32)*n <= 0)
- *n = 1;
- return *n;
+ do {
+ old = atomic_read(&net->ipv6.rt_sernum);
+ new = old < INT_MAX ? old + 1 : 1;
+ } while (atomic_cmpxchg(&net->ipv6.rt_sernum, old, new) != old);
+ return new;
}
-#define FIB6_NO_SERNUM_CHANGE (0U)
+#define FIB6_NO_SERNUM_CHANGE (0)
/*
* Auxiliary address test functions for the radix tree.
@@ -418,7 +419,7 @@ out:
static struct fib6_node *fib6_add_1(struct fib6_node *root,
struct in6_addr *addr, int plen,
int offset, int allow_create,
- int replace_required, u32 sernum)
+ int replace_required, int sernum)
{
struct fib6_node *fn, *in, *ln;
struct fib6_node *pn = NULL;
@@ -842,7 +843,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
int err = -ENOMEM;
int allow_create = 1;
int replace_required = 0;
- u32 sernum = fib6_new_sernum(dev_net(rt->dst.dev));
+ int sernum = fib6_new_sernum(dev_net(rt->dst.dev));
if (info->nlh) {
if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
@@ -1558,7 +1559,7 @@ static int fib6_clean_node(struct fib6_walker_t *w)
static void fib6_clean_tree(struct net *net, struct fib6_node *root,
int (*func)(struct rt6_info *, void *arg),
- bool prune, u32 sernum, void *arg)
+ bool prune, int sernum, void *arg)
{
struct fib6_cleaner_t c;
@@ -1577,7 +1578,7 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root,
void __fib6_clean_all(struct net *net,
int (*func)(struct rt6_info *, void *arg),
- u32 sernum, void *arg)
+ int sernum, void *arg)
{
struct fib6_table *table;
struct hlist_head *head;
@@ -1617,7 +1618,7 @@ static int fib6_prune_clone(struct rt6_info *rt, void *arg)
return 0;
}
-static void fib6_prune_clones(struct net *net, struct fib6_node *fn, u32 sernum)
+static void fib6_prune_clones(struct net *net, struct fib6_node *fn, int sernum)
{
fib6_clean_tree(net, fn, fib6_prune_clone, true, sernum, NULL);
}
@@ -1830,7 +1831,7 @@ struct ipv6_route_iter {
struct fib6_walker_t w;
loff_t skip;
struct fib6_table *tbl;
- u32 sernum;
+ int sernum;
};
static int ipv6_route_seq_show(struct seq_file *seq, void *v)
--
1.9.3
^ permalink raw reply related
* Re: [patch net-next v2 8/9] switchdev: introduce Netlink API
From: Alexei Starovoitov @ 2014-09-20 22:50 UTC (permalink / raw)
To: Thomas Graf
Cc: Jiri Pirko, John Fastabend, Jamal Hadi Salim,
netdev@vger.kernel.org, David S. Miller, Neil Horman,
Andy Gospodarek, Daniel Borkmann, Or Gerlitz, Jesse Gross,
Pravin Shelar, Andy Zhou, ben, Stephen Hemminger,
jeffrey.t.kirsher, Vladislav Yasevich, Cong Wang, Eric Dumazet,
Scott Feldman, Florian Fainelli, Roopa Prabhu, John Linville,
dev@openvswitch.org
In-Reply-To: <20140920105354.GA29419@casper.infradead.org>
On Sat, Sep 20, 2014 at 3:53 AM, Thomas Graf <tgraf@suug.ch> wrote:
> On 09/20/14 at 10:14am, Jiri Pirko wrote:
>> Sat, Sep 20, 2014 at 12:12:12AM CEST, john.r.fastabend@intel.com wrote:
>> >I was considering a slightly different approach where the
>> >device would report via netlink the fields/actions it
>> >supported rather than creating pre-defined enums for every
>> >possible key.
>> >
>> >I already need to have an API to report fields/matches
>> >that are being supported why not have the device report
>> >the headers as header fields (len, offset) and the
>> >associated parse graph the hardware uses? Vendors should
>> >have this already to describe/design their real hardware.
>>
>> Hmm, let me think about this a bit more. I will try to figure out how to
>> handle that. Sound logic though. Will try to incorporate the idea in the
>> patchset.
>
> I think this is the right track.
I agree with John and Thomas here.
I think HW should not be limited by SW abstractions whether
these abstractions are called flows, n-tuples, bridge or else.
Really looking forward to see "device reporting the headers as
header fields (len, offset) and the associated parse graph"
as the first step.
Another topic that this discussion didn't cover yet is how this
all connects to tunnels and what is 'tunnel offloading'.
imo flow offloading by itself serves only academic interest.
^ permalink raw reply
* [PATCH] brcmfmac: Fix off by one bug in brcmf_count_20mhz_channels()
From: Emil Goode @ 2014-09-20 22:58 UTC (permalink / raw)
To: Arend van Spriel, Brett Rudley, Franky (Zhenhui) Lin,
Hante Meuleman, John W. Linville, Pieter-Paul Giesberts,
Daniel Kim
Cc: linux-wireless-u79uwXL29TY76Z2rM5mHXA,
brcm80211-dev-list-dY08KVG/lbpWk0Htik3J/w,
netdev-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
kernel-janitors-u79uwXL29TY76Z2rM5mHXA, Emil Goode
In the brcmf_count_20mhz_channels function we are looping through a list
of channels received from firmware. Since the index of the first channel
is 0 the condition leads to an off by one bug. This is causing us to hit
the WARN_ON_ONCE(1) calls in the brcmu_d11n_decchspec function, which is
how I discovered the bug.
Introduced by:
commit b48d891676f756d48b4d0ee131e4a7a5d43ca417
("brcmfmac: rework wiphy structure setup")
Signed-off-by: Emil Goode <emilgoode-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
---
drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
index 02fe706..93b5dd9 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
@@ -4918,7 +4918,7 @@ static void brcmf_count_20mhz_channels(struct brcmf_cfg80211_info *cfg,
struct brcmu_chan ch;
int i;
- for (i = 0; i <= total; i++) {
+ for (i = 0; i < total; i++) {
ch.chspec = (u16)le32_to_cpu(chlist->element[i]);
cfg->d11inf.decchspec(&ch);
--
2.1.0
--
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 related
* Re: [net-next] udp_tunnel: Only build ip6_udp_tunnel.c when IPV6 is selected
From: Tom Herbert @ 2014-09-20 23:14 UTC (permalink / raw)
To: David Miller; +Cc: Andy Zhou, Linux Netdev List
In-Reply-To: <20140919.220620.557633612726378260.davem@davemloft.net>
On Fri, Sep 19, 2014 at 7:06 PM, David Miller <davem@davemloft.net> wrote:
> From: Andy Zhou <azhou@nicira.com>
> Date: Fri, 19 Sep 2014 18:02:53 -0700
>
>> Functions supplied in ip6_udp_tunnel.c are only needed when IPV6 is
>> selected. When IPV6 is not selected, those functions are stubbed out
>> in udp_tunnel.h.
>>
>> ==================================================================
>> net/ipv6/ip6_udp_tunnel.c:15:5: error: redefinition of 'udp_sock_create6'
>> int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
>> In file included from net/ipv6/ip6_udp_tunnel.c:9:0:
>> include/net/udp_tunnel.h:36:19: note: previous definition of 'udp_sock_create6' was here
>> static inline int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
>> ==================================================================
>>
>> Fixes: fd384412e udp_tunnel: Seperate ipv6 functions into its own file
>> Reported-by: kbuild test robot <fengguang.wu@intel.com>
>> Signed-off-by: Andy Zhou <azhou@nicira.com>
>
> Applied, thanks Andy.
David, what branch did you apply this to? I pulled from your net-next
but don't see this patch...
Thanks,
Tom
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [net-next PATCH 29/29] fm10k: Add support for PTP
From: Alexander Duyck @ 2014-09-20 23:36 UTC (permalink / raw)
To: Richard Cochran, Alexander Duyck
Cc: davem, nhorman, netdev, john.fastabend, matthew.vick,
jeffrey.t.kirsher, sassmann
In-Reply-To: <20140920211647.GB5258@netboy>
On 09/20/2014 02:16 PM, Richard Cochran wrote:
> On Fri, Sep 19, 2014 at 11:32:24AM -0700, Alexander Duyck wrote:
>> Because the value cannot be adjusted directly. The timesource for the
>> switch is shared by all ports and host interfaces. As such we have to
>> maintain a software offset per host to avoid corrupting the other clocks.
> So any host can set the time, but only one may adjust the frequency?
Yes. Essentially the one who should be adjusting the frequency should
be the host interface that is providing traffic for the control plane
processor. That way the control plane processor can act as a boundary
clock and can adjust the frequency to match the port it has decided to
be a slave on.
In the case of the ordinary clock host interfaces they will be slaves to
the boundary clock and since they share the same clock source anyway
they shouldn't need any frequency adjustments, or at least that is how
it is supposed to work. The other reason for using the software offset
is that it can be very time intensive as you have to stop the clock,
update the staring value for each host interface and the Ethernet ports,
and then you can resume the clock. It can be a rather time consuming
process doing it that way versus just maintaining an offset in software.
Tx timestamps from the host interface are actually identical to the Rx
timestamps on the receiving host interface in the case of traffic going
between two fm10k host interfaces on the same switch. So what you end
up with is that any two hosts should be able to perfectly synchronize
their clocks with just the follow-up to the first sync message. I've
done some testing for this with an FPGA and actually it has proven out
as ptp4l did one offset adjustment on the follow-up and then indicated 0
adjustments from there forward. It is one of the reasons why I believe
we should be able to disable the frequency adjustment for interfaces
configured as ordinary clocks.
> Regarding the overflow, probably you can remove the daily check, since
> you only need a single clock read every 300 years, and that is
> reasonable to expect in any case.
Yeah, I figured that out after I recalled that the overflow check is
only really necessary if the mask is less than 64 bits.
Thanks,
Alex
^ permalink raw reply
* [net-next PATCH v2 00/29] Add support for the Intel FM10000 Ethernet Switch Host Interface
From: Alexander Duyck @ 2014-09-20 23:45 UTC (permalink / raw)
To: davem
Cc: nhorman, netdev, john.fastabend, matthew.vick, jeffrey.t.kirsher,
sassmann
This patch series adds support for the FM10000 Ethernet switch host
interface. The Intel FM10000 Ethernet Switch is a 48-port Ethernet switch
supporting both Ethernet ports and PCI Express host interfaces. The fm10k
driver provides support for the host interface portion of the switch, both
PF and VF.
As the host interfaces are directly connected to the switch this results in
some significant differences versus a standard network driver. For example
there is no PHY or MII on the device. Since packets are delivered directly
from the switch to the host interface these are unnecessary. Otherwise most
of the functionality is very similar to our other network drivers such as
ixgbe or igb. For example we support all the standard network offloads,
jumbo frames, SR-IOV (64 VFS), PTP, and some VXLAN and NVGRE offloads.
---
Alexander Duyck (29):
fm10k: Add skeletal frame for Intel(R) FM10000 Ethernet Switch Host Interface Driver
fm10k: Add register defines and basic structures
fm10k: Add support for TLV message parsing and generation
fm10k: Add support for basic interaction with hardware
fm10k: Add support for mailbox
fm10k: Implement PF <-> SM mailbox operations
fm10k: Add support for PF
fm10k: Add support for configuring PF interface
fm10k: Add netdev
fm10k: Add support for L2 filtering
fm10k: Add support for ndo_open/stop
fm10k: Add interrupt support
fm10k: add support for Tx/Rx rings
fm10k: Add service task to handle delayed events
fm10k: Add Tx/Rx hardware ring bring-up/tear-down
fm10k: Add transmit and receive fastpath and interrupt handlers
fm10k: Add ethtool support
fm10k: Add support for PCI power management and error handling
fm10k: Add support for multiple queues
fm10k: Add support for netdev offloads
fm10k: Add support for MACVLAN acceleration
fm10k: Add support for PF <-> VF mailbox
fm10k: Add support for VF
fm10k: Add support for SR-IOV to PF core files
fm10k: Add support for SR-IOV to driver
fm10k: Add support for IEEE DCBx
fm10k: Add support for debugfs
fm10k: Add support for ptp to hw specific files
fm10k: Add support for PTP
drivers/net/ethernet/intel/Kconfig | 19
drivers/net/ethernet/intel/Makefile | 1
drivers/net/ethernet/intel/fm10k/Makefile | 33
drivers/net/ethernet/intel/fm10k/fm10k.h | 534 +++++
drivers/net/ethernet/intel/fm10k/fm10k_common.c | 534 +++++
drivers/net/ethernet/intel/fm10k/fm10k_common.h | 65 +
drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c | 174 ++
drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c | 259 +++
drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c | 1069 +++++++++++
drivers/net/ethernet/intel/fm10k/fm10k_iov.c | 536 +++++
drivers/net/ethernet/intel/fm10k/fm10k_main.c | 1978 ++++++++++++++++++++
drivers/net/ethernet/intel/fm10k/fm10k_mbx.c | 2125 ++++++++++++++++++++++
drivers/net/ethernet/intel/fm10k/fm10k_mbx.h | 307 +++
drivers/net/ethernet/intel/fm10k/fm10k_netdev.c | 1430 +++++++++++++++
drivers/net/ethernet/intel/fm10k/fm10k_pci.c | 2166 ++++++++++++++++++++++
drivers/net/ethernet/intel/fm10k/fm10k_pf.c | 1880 +++++++++++++++++++
drivers/net/ethernet/intel/fm10k/fm10k_pf.h | 135 +
drivers/net/ethernet/intel/fm10k/fm10k_ptp.c | 463 +++++
drivers/net/ethernet/intel/fm10k/fm10k_tlv.c | 863 +++++++++
drivers/net/ethernet/intel/fm10k/fm10k_tlv.h | 186 ++
drivers/net/ethernet/intel/fm10k/fm10k_type.h | 770 ++++++++
drivers/net/ethernet/intel/fm10k/fm10k_vf.c | 578 ++++++
drivers/net/ethernet/intel/fm10k/fm10k_vf.h | 78 +
23 files changed, 16183 insertions(+)
create mode 100644 drivers/net/ethernet/intel/fm10k/Makefile
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k.h
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_common.c
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_common.h
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_iov.c
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_main.c
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_mbx.c
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_mbx.h
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_pci.c
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_pf.c
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_pf.h
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_ptp.c
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_tlv.c
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_tlv.h
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_type.h
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_vf.c
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_vf.h
--
^ permalink raw reply
* [net-next PATCH v2 01/29] fm10k: Add skeletal frame for Intel(R) FM10000 Ethernet Switch Host Interface Driver
From: Alexander Duyck @ 2014-09-20 23:46 UTC (permalink / raw)
To: davem
Cc: nhorman, netdev, john.fastabend, matthew.vick, jeffrey.t.kirsher,
sassmann
In-Reply-To: <20140920234342.2977.21667.stgit@ahduyck-bv4.jf.intel.com>
This patch adds the beginning framework onto which I am going to add the
fm10k driver which supports the Intel(R) FM10000 Ethernet Switch Host
Interface.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
---
drivers/net/ethernet/intel/Kconfig | 19 +++
drivers/net/ethernet/intel/Makefile | 1
drivers/net/ethernet/intel/fm10k/Makefile | 30 +++++
drivers/net/ethernet/intel/fm10k/fm10k.h | 39 +++++++
drivers/net/ethernet/intel/fm10k/fm10k_main.c | 67 ++++++++++++
drivers/net/ethernet/intel/fm10k/fm10k_pci.c | 145 +++++++++++++++++++++++++
drivers/net/ethernet/intel/fm10k/fm10k_type.h | 27 +++++
7 files changed, 328 insertions(+)
create mode 100644 drivers/net/ethernet/intel/fm10k/Makefile
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k.h
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_main.c
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_pci.c
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_type.h
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index bb9f0ba..6a6d5ee 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -300,4 +300,23 @@ config I40EVF
will be called i40evf. MSI-X interrupt support is required
for this driver to work correctly.
+config FM10K
+ tristate "Intel(R) FM10000 Ethernet Switch Host Interface Support"
+ default n
+ depends on PCI_MSI
+ ---help---
+ This driver supports Intel(R) FM10000 Ethernet Switch Host
+ Interface. For more information on how to identify your adapter,
+ go to the Adapter & Driver ID Guide at:
+
+ <http://support.intel.com/support/network/sb/CS-008441.htm>
+
+ For general information and support, go to the Intel support
+ website at:
+
+ <http://support.intel.com>
+
+ To compile this driver as a module, choose M here. The module
+ will be called fm10k. MSI-X interrupt support is required
+
endif # NET_VENDOR_INTEL
diff --git a/drivers/net/ethernet/intel/Makefile b/drivers/net/ethernet/intel/Makefile
index cdbbca8..5ea764d 100644
--- a/drivers/net/ethernet/intel/Makefile
+++ b/drivers/net/ethernet/intel/Makefile
@@ -12,3 +12,4 @@ obj-$(CONFIG_IXGBEVF) += ixgbevf/
obj-$(CONFIG_I40E) += i40e/
obj-$(CONFIG_IXGB) += ixgb/
obj-$(CONFIG_I40EVF) += i40evf/
+obj-$(CONFIG_FM10K) += fm10k/
diff --git a/drivers/net/ethernet/intel/fm10k/Makefile b/drivers/net/ethernet/intel/fm10k/Makefile
new file mode 100644
index 0000000..ddc0eb7
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/Makefile
@@ -0,0 +1,30 @@
+################################################################################
+#
+# Intel Ethernet Switch Host Interface Driver
+# Copyright(c) 2013 - 2014 Intel Corporation.
+#
+# This program is free software; you can redistribute it and/or modify it
+# under the terms and conditions of the GNU General Public License,
+# version 2, as published by the Free Software Foundation.
+#
+# This program is distributed in the hope it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+# more details.
+#
+# The full GNU General Public License is included in this distribution in
+# the file called "COPYING".
+#
+# Contact Information:
+# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+#
+################################################################################
+
+#
+# Makefile for the Intel(R) FM10000 Ethernet Switch Host Interface driver
+#
+
+obj-$(CONFIG_FM10K) += fm10k.o
+
+fm10k-objs := fm10k_main.o fm10k_pci.o
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h
new file mode 100644
index 0000000..2e27bd9
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k.h
@@ -0,0 +1,39 @@
+/* Intel Ethernet Switch Host Interface Driver
+ * Copyright(c) 2013 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
+
+#ifndef _FM10K_H_
+#define _FM10K_H_
+
+#include <linux/types.h>
+#include <linux/etherdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/if_vlan.h>
+#include <linux/pci.h>
+
+#include "fm10k_type.h"
+
+/* main */
+extern char fm10k_driver_name[];
+extern const char fm10k_driver_version[];
+
+/* PCI */
+int fm10k_register_pci_driver(void);
+void fm10k_unregister_pci_driver(void);
+#endif /* _FM10K_H_ */
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
new file mode 100644
index 0000000..a7822b8
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -0,0 +1,67 @@
+/* Intel Ethernet Switch Host Interface Driver
+ * Copyright(c) 2013 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <net/ipv6.h>
+#include <net/ip.h>
+#include <net/tcp.h>
+#include <linux/if_macvlan.h>
+
+#include "fm10k.h"
+
+#define DRV_VERSION "0.12.2-k"
+const char fm10k_driver_version[] = DRV_VERSION;
+char fm10k_driver_name[] = "fm10k";
+static const char fm10k_driver_string[] =
+ "Intel(R) Ethernet Switch Host Interface Driver";
+static const char fm10k_copyright[] =
+ "Copyright (c) 2013 Intel Corporation.";
+
+MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
+MODULE_DESCRIPTION("Intel(R) Ethernet Switch Host Interface Driver");
+MODULE_LICENSE("GPL");
+MODULE_VERSION(DRV_VERSION);
+
+/** fm10k_init_module - Driver Registration Routine
+ *
+ * fm10k_init_module is the first routine called when the driver is
+ * loaded. All it does is register with the PCI subsystem.
+ **/
+static int __init fm10k_init_module(void)
+{
+ pr_info("%s - version %s\n", fm10k_driver_string, fm10k_driver_version);
+ pr_info("%s\n", fm10k_copyright);
+
+ return fm10k_register_pci_driver();
+}
+module_init(fm10k_init_module);
+
+/**
+ * fm10k_exit_module - Driver Exit Cleanup Routine
+ *
+ * fm10k_exit_module is called just before the driver is removed
+ * from memory.
+ **/
+static void __exit fm10k_exit_module(void)
+{
+ fm10k_unregister_pci_driver();
+}
+module_exit(fm10k_exit_module);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
new file mode 100644
index 0000000..12089ce
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
@@ -0,0 +1,145 @@
+/* Intel Ethernet Switch Host Interface Driver
+ * Copyright(c) 2013 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
+
+#include <linux/module.h>
+
+#include "fm10k.h"
+
+/**
+ * fm10k_pci_tbl - PCI Device ID Table
+ *
+ * Wildcard entries (PCI_ANY_ID) should come last
+ * Last entry must be all 0s
+ *
+ * { Vendor ID, Device ID, SubVendor ID, SubDevice ID,
+ * Class, Class Mask, private data (not used) }
+ */
+static const struct pci_device_id fm10k_pci_tbl[] = {
+ { PCI_VDEVICE(INTEL, FM10K_DEV_ID_PF) },
+ /* required last entry */
+ { 0, }
+};
+MODULE_DEVICE_TABLE(pci, fm10k_pci_tbl);
+
+/**
+ * fm10k_probe - Device Initialization Routine
+ * @pdev: PCI device information struct
+ * @ent: entry in fm10k_pci_tbl
+ *
+ * Returns 0 on success, negative on failure
+ *
+ * fm10k_probe initializes an interface identified by a pci_dev structure.
+ * The OS initialization, configuring of the interface private structure,
+ * and a hardware reset occur.
+ **/
+static int fm10k_probe(struct pci_dev *pdev,
+ const struct pci_device_id *ent)
+{
+ int err;
+ u64 dma_mask;
+
+ err = pci_enable_device_mem(pdev);
+ if (err)
+ return err;
+
+ /* By default fm10k only supports a 48 bit DMA mask */
+ dma_mask = DMA_BIT_MASK(48) | dma_get_required_mask(&pdev->dev);
+
+ if ((dma_mask <= DMA_BIT_MASK(32)) ||
+ dma_set_mask_and_coherent(&pdev->dev, dma_mask)) {
+ dma_mask &= DMA_BIT_MASK(32);
+
+ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+ err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
+ if (err) {
+ err = dma_set_coherent_mask(&pdev->dev,
+ DMA_BIT_MASK(32));
+ if (err) {
+ dev_err(&pdev->dev,
+ "No usable DMA configuration, aborting\n");
+ goto err_dma;
+ }
+ }
+ }
+
+ err = pci_request_selected_regions(pdev,
+ pci_select_bars(pdev,
+ IORESOURCE_MEM),
+ fm10k_driver_name);
+ if (err) {
+ dev_err(&pdev->dev,
+ "pci_request_selected_regions failed 0x%x\n", err);
+ goto err_pci_reg;
+ }
+
+ pci_set_master(pdev);
+ pci_save_state(pdev);
+
+ return 0;
+
+err_pci_reg:
+err_dma:
+ pci_disable_device(pdev);
+ return err;
+}
+
+/**
+ * fm10k_remove - Device Removal Routine
+ * @pdev: PCI device information struct
+ *
+ * fm10k_remove is called by the PCI subsystem to alert the driver
+ * that it should release a PCI device. The could be caused by a
+ * Hot-Plug event, or because the driver is going to be removed from
+ * memory.
+ **/
+static void fm10k_remove(struct pci_dev *pdev)
+{
+ pci_release_selected_regions(pdev,
+ pci_select_bars(pdev, IORESOURCE_MEM));
+
+ pci_disable_device(pdev);
+}
+
+static struct pci_driver fm10k_driver = {
+ .name = fm10k_driver_name,
+ .id_table = fm10k_pci_tbl,
+ .probe = fm10k_probe,
+ .remove = fm10k_remove,
+};
+
+/**
+ * fm10k_register_pci_driver - register driver interface
+ *
+ * This funciton is called on module load in order to register the driver.
+ **/
+int fm10k_register_pci_driver(void)
+{
+ return pci_register_driver(&fm10k_driver);
+}
+
+/**
+ * fm10k_unregister_pci_driver - unregister driver interface
+ *
+ * This funciton is called on module unload in order to remove the driver.
+ **/
+void fm10k_unregister_pci_driver(void)
+{
+ pci_unregister_driver(&fm10k_driver);
+}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_type.h b/drivers/net/ethernet/intel/fm10k/fm10k_type.h
new file mode 100644
index 0000000..2c06f02
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_type.h
@@ -0,0 +1,27 @@
+/* Intel Ethernet Switch Host Interface Driver
+ * Copyright(c) 2013 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
+
+#ifndef _FM10K_TYPE_H_
+#define _FM10K_TYPE_H_
+
+#define FM10K_DEV_ID_PF 0x15A4
+#define FM10K_DEV_ID_VF 0x15A5
+
+#endif /* _FM10K_TYPE_H */
^ permalink raw reply related
* [net-next PATCH v2 02/29] fm10k: Add register defines and basic structures
From: Alexander Duyck @ 2014-09-20 23:46 UTC (permalink / raw)
To: davem
Cc: nhorman, netdev, john.fastabend, matthew.vick, jeffrey.t.kirsher,
sassmann
In-Reply-To: <20140920234342.2977.21667.stgit@ahduyck-bv4.jf.intel.com>
This patch adds the basic defines and structures needed by the PF for
operation.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
---
drivers/net/ethernet/intel/fm10k/fm10k_main.c | 3
drivers/net/ethernet/intel/fm10k/fm10k_type.h | 659 +++++++++++++++++++++++++
2 files changed, 661 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index a7822b8..6ca0614 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -40,7 +40,8 @@ MODULE_DESCRIPTION("Intel(R) Ethernet Switch Host Interface Driver");
MODULE_LICENSE("GPL");
MODULE_VERSION(DRV_VERSION);
-/** fm10k_init_module - Driver Registration Routine
+/**
+ * fm10k_init_module - Driver Registration Routine
*
* fm10k_init_module is the first routine called when the driver is
* loaded. All it does is register with the PCI subsystem.
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_type.h b/drivers/net/ethernet/intel/fm10k/fm10k_type.h
index 2c06f02..1606805 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_type.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_type.h
@@ -21,7 +21,666 @@
#ifndef _FM10K_TYPE_H_
#define _FM10K_TYPE_H_
+/* forward declaration */
+struct fm10k_hw;
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+#include <linux/etherdevice.h>
+
#define FM10K_DEV_ID_PF 0x15A4
#define FM10K_DEV_ID_VF 0x15A5
+#define FM10K_MAX_QUEUES 256
+#define FM10K_MAX_QUEUES_PF 128
+#define FM10K_MAX_QUEUES_POOL 16
+
+#define FM10K_48_BIT_MASK 0x0000FFFFFFFFFFFFull
+#define FM10K_STAT_VALID 0x80000000
+
+/* PCI Bus Info */
+#define FM10K_PCIE_LINK_CAP 0x7C
+#define FM10K_PCIE_LINK_STATUS 0x82
+#define FM10K_PCIE_LINK_WIDTH 0x3F0
+#define FM10K_PCIE_LINK_WIDTH_1 0x10
+#define FM10K_PCIE_LINK_WIDTH_2 0x20
+#define FM10K_PCIE_LINK_WIDTH_4 0x40
+#define FM10K_PCIE_LINK_WIDTH_8 0x80
+#define FM10K_PCIE_LINK_SPEED 0xF
+#define FM10K_PCIE_LINK_SPEED_2500 0x1
+#define FM10K_PCIE_LINK_SPEED_5000 0x2
+#define FM10K_PCIE_LINK_SPEED_8000 0x3
+
+/* PCIe payload size */
+#define FM10K_PCIE_DEV_CAP 0x74
+#define FM10K_PCIE_DEV_CAP_PAYLOAD 0x07
+#define FM10K_PCIE_DEV_CAP_PAYLOAD_128 0x00
+#define FM10K_PCIE_DEV_CAP_PAYLOAD_256 0x01
+#define FM10K_PCIE_DEV_CAP_PAYLOAD_512 0x02
+#define FM10K_PCIE_DEV_CTRL 0x78
+#define FM10K_PCIE_DEV_CTRL_PAYLOAD 0xE0
+#define FM10K_PCIE_DEV_CTRL_PAYLOAD_128 0x00
+#define FM10K_PCIE_DEV_CTRL_PAYLOAD_256 0x20
+#define FM10K_PCIE_DEV_CTRL_PAYLOAD_512 0x40
+
+/* PCIe MSI-X Capability info */
+#define FM10K_PCI_MSIX_MSG_CTRL 0xB2
+#define FM10K_PCI_MSIX_MSG_CTRL_TBL_SZ_MASK 0x7FF
+#define FM10K_MAX_MSIX_VECTORS 256
+#define FM10K_MAX_VECTORS_PF 256
+#define FM10K_MAX_VECTORS_POOL 32
+
+/* PCIe SR-IOV Info */
+#define FM10K_PCIE_SRIOV_CTRL 0x190
+#define FM10K_PCIE_SRIOV_CTRL_VFARI 0x10
+
+#define FM10K_ERR_PARAM -2
+#define FM10K_ERR_REQUESTS_PENDING -4
+#define FM10K_ERR_RESET_REQUESTED -5
+#define FM10K_ERR_DMA_PENDING -6
+#define FM10K_ERR_RESET_FAILED -7
+#define FM10K_ERR_INVALID_MAC_ADDR -8
+#define FM10K_ERR_INVALID_VALUE -9
+#define FM10K_NOT_IMPLEMENTED 0x7FFFFFFF
+
+/* Start of PF registers */
+#define FM10K_CTRL 0x0000
+#define FM10K_CTRL_BAR4_ALLOWED 0x00000004
+
+#define FM10K_CTRL_EXT 0x0001
+#define FM10K_GCR 0x0003
+#define FM10K_GCR_EXT 0x0005
+
+/* Interrupt control registers */
+#define FM10K_EICR 0x0006
+#define FM10K_EICR_FAULT_MASK 0x0000003F
+#define FM10K_EICR_MAILBOX 0x00000040
+#define FM10K_EICR_SWITCHREADY 0x00000080
+#define FM10K_EICR_SWITCHNOTREADY 0x00000100
+#define FM10K_EICR_SWITCHINTERRUPT 0x00000200
+#define FM10K_EICR_VFLR 0x00000800
+#define FM10K_EICR_MAXHOLDTIME 0x00001000
+#define FM10K_EIMR 0x0007
+#define FM10K_EIMR_PCA_FAULT 0x00000001
+#define FM10K_EIMR_THI_FAULT 0x00000010
+#define FM10K_EIMR_FUM_FAULT 0x00000400
+#define FM10K_EIMR_MAILBOX 0x00001000
+#define FM10K_EIMR_SWITCHREADY 0x00004000
+#define FM10K_EIMR_SWITCHNOTREADY 0x00010000
+#define FM10K_EIMR_SWITCHINTERRUPT 0x00040000
+#define FM10K_EIMR_SRAMERROR 0x00100000
+#define FM10K_EIMR_VFLR 0x00400000
+#define FM10K_EIMR_MAXHOLDTIME 0x01000000
+#define FM10K_EIMR_ALL 0x55555555
+#define FM10K_EIMR_DISABLE(NAME) ((FM10K_EIMR_ ## NAME) << 0)
+#define FM10K_EIMR_ENABLE(NAME) ((FM10K_EIMR_ ## NAME) << 1)
+#define FM10K_FAULT_ADDR_LO 0x0
+#define FM10K_FAULT_ADDR_HI 0x1
+#define FM10K_FAULT_SPECINFO 0x2
+#define FM10K_FAULT_FUNC 0x3
+#define FM10K_FAULT_SIZE 0x4
+#define FM10K_FAULT_FUNC_VALID 0x00008000
+#define FM10K_FAULT_FUNC_PF 0x00004000
+#define FM10K_FAULT_FUNC_VF_MASK 0x00003F00
+#define FM10K_FAULT_FUNC_VF_SHIFT 8
+#define FM10K_FAULT_FUNC_TYPE_MASK 0x000000FF
+
+#define FM10K_PCA_FAULT 0x0008
+#define FM10K_THI_FAULT 0x0010
+#define FM10K_FUM_FAULT 0x001C
+
+/* Rx queue timeout indicator */
+#define FM10K_MAXHOLDQ(_n) ((_n) + 0x0020)
+
+/* Switch Manager info */
+#define FM10K_SM_AREA(_n) ((_n) + 0x0028)
+
+/* GLORT mapping registers */
+#define FM10K_DGLORTMAP(_n) ((_n) + 0x0030)
+#define FM10K_DGLORT_COUNT 8
+#define FM10K_DGLORTMAP_MASK_SHIFT 16
+#define FM10K_DGLORTMAP_ANY 0x00000000
+#define FM10K_DGLORTMAP_NONE 0x0000FFFF
+#define FM10K_DGLORTMAP_ZERO 0xFFFF0000
+#define FM10K_DGLORTDEC(_n) ((_n) + 0x0038)
+#define FM10K_DGLORTDEC_VSILENGTH_SHIFT 4
+#define FM10K_DGLORTDEC_VSIBASE_SHIFT 7
+#define FM10K_DGLORTDEC_PCLENGTH_SHIFT 14
+#define FM10K_DGLORTDEC_QBASE_SHIFT 16
+#define FM10K_DGLORTDEC_RSSLENGTH_SHIFT 24
+#define FM10K_DGLORTDEC_INNERRSS_ENABLE 0x08000000
+#define FM10K_TUNNEL_CFG 0x0040
+#define FM10K_TUNNEL_CFG_NVGRE_SHIFT 16
+#define FM10K_SWPRI_MAP(_n) ((_n) + 0x0050)
+#define FM10K_SWPRI_MAX 16
+#define FM10K_RSSRK(_n, _m) (((_n) * 0x10) + (_m) + 0x0800)
+#define FM10K_RSSRK_SIZE 10
+#define FM10K_RSSRK_ENTRIES_PER_REG 4
+#define FM10K_RETA(_n, _m) (((_n) * 0x20) + (_m) + 0x1000)
+#define FM10K_RETA_SIZE 32
+#define FM10K_RETA_ENTRIES_PER_REG 4
+#define FM10K_MAX_RSS_INDICES 128
+
+/* Rate limiting registers */
+#define FM10K_TC_CREDIT(_n) ((_n) + 0x2000)
+#define FM10K_TC_CREDIT_CREDIT_MASK 0x001FFFFF
+#define FM10K_TC_MAXCREDIT(_n) ((_n) + 0x2040)
+#define FM10K_TC_MAXCREDIT_64K 0x00010000
+#define FM10K_TC_RATE(_n) ((_n) + 0x2080)
+#define FM10K_TC_RATE_QUANTA_MASK 0x0000FFFF
+#define FM10K_TC_RATE_INTERVAL_4US_GEN1 0x00020000
+#define FM10K_TC_RATE_INTERVAL_4US_GEN2 0x00040000
+#define FM10K_TC_RATE_INTERVAL_4US_GEN3 0x00080000
+
+/* DMA control registers */
+#define FM10K_DMA_CTRL 0x20C3
+#define FM10K_DMA_CTRL_TX_ENABLE 0x00000001
+#define FM10K_DMA_CTRL_TX_ACTIVE 0x00000008
+#define FM10K_DMA_CTRL_RX_ENABLE 0x00000010
+#define FM10K_DMA_CTRL_RX_ACTIVE 0x00000080
+#define FM10K_DMA_CTRL_RX_DESC_SIZE 0x00000100
+#define FM10K_DMA_CTRL_MINMSS_64 0x00008000
+#define FM10K_DMA_CTRL_MAX_HOLD_1US_GEN3 0x04800000
+#define FM10K_DMA_CTRL_MAX_HOLD_1US_GEN2 0x04000000
+#define FM10K_DMA_CTRL_MAX_HOLD_1US_GEN1 0x03800000
+#define FM10K_DMA_CTRL_DATAPATH_RESET 0x20000000
+#define FM10K_DMA_CTRL_32_DESC 0x00000000
+
+#define FM10K_DMA_CTRL2 0x20C4
+#define FM10K_DMA_CTRL2_SWITCH_READY 0x00002000
+
+/* TSO flags configuration
+ * First packet contains all flags except for fin and psh
+ * Middle packet contains only urg and ack
+ * Last packet contains urg, ack, fin, and psh
+ */
+#define FM10K_TSO_FLAGS_LOW 0x00300FF6
+#define FM10K_TSO_FLAGS_HI 0x00000039
+#define FM10K_DTXTCPFLGL 0x20C5
+#define FM10K_DTXTCPFLGH 0x20C6
+
+#define FM10K_TPH_CTRL 0x20C7
+#define FM10K_MRQC(_n) ((_n) + 0x2100)
+#define FM10K_MRQC_TCP_IPV4 0x00000001
+#define FM10K_MRQC_IPV4 0x00000002
+#define FM10K_MRQC_IPV6 0x00000010
+#define FM10K_MRQC_TCP_IPV6 0x00000020
+#define FM10K_MRQC_UDP_IPV4 0x00000040
+#define FM10K_MRQC_UDP_IPV6 0x00000080
+
+#define FM10K_TQMAP(_n) ((_n) + 0x2800)
+#define FM10K_TQMAP_TABLE_SIZE 2048
+#define FM10K_RQMAP(_n) ((_n) + 0x3000)
+
+/* Hardware Statistics */
+#define FM10K_STATS_TIMEOUT 0x3800
+#define FM10K_STATS_UR 0x3801
+#define FM10K_STATS_CA 0x3802
+#define FM10K_STATS_UM 0x3803
+#define FM10K_STATS_XEC 0x3804
+#define FM10K_STATS_VLAN_DROP 0x3805
+#define FM10K_STATS_LOOPBACK_DROP 0x3806
+#define FM10K_STATS_NODESC_DROP 0x3807
+
+/* PCIe state registers */
+#define FM10K_PHYADDR 0x381C
+
+/* Rx ring registers */
+#define FM10K_RDBAL(_n) ((0x40 * (_n)) + 0x4000)
+#define FM10K_RDBAH(_n) ((0x40 * (_n)) + 0x4001)
+#define FM10K_RDLEN(_n) ((0x40 * (_n)) + 0x4002)
+#define FM10K_TPH_RXCTRL(_n) ((0x40 * (_n)) + 0x4003)
+#define FM10K_TPH_RXCTRL_DESC_TPHEN 0x00000020
+#define FM10K_TPH_RXCTRL_DESC_RROEN 0x00000200
+#define FM10K_TPH_RXCTRL_DATA_WROEN 0x00002000
+#define FM10K_TPH_RXCTRL_HDR_WROEN 0x00008000
+#define FM10K_RDH(_n) ((0x40 * (_n)) + 0x4004)
+#define FM10K_RDT(_n) ((0x40 * (_n)) + 0x4005)
+#define FM10K_RXQCTL(_n) ((0x40 * (_n)) + 0x4006)
+#define FM10K_RXQCTL_ENABLE 0x00000001
+#define FM10K_RXQCTL_PF 0x000000FC
+#define FM10K_RXQCTL_VF_SHIFT 2
+#define FM10K_RXQCTL_VF 0x00000100
+#define FM10K_RXQCTL_ID_MASK (FM10K_RXQCTL_PF | FM10K_RXQCTL_VF)
+#define FM10K_RXDCTL(_n) ((0x40 * (_n)) + 0x4007)
+#define FM10K_RXDCTL_WRITE_BACK_MIN_DELAY 0x00000001
+#define FM10K_RXDCTL_DROP_ON_EMPTY 0x00000200
+#define FM10K_RXINT(_n) ((0x40 * (_n)) + 0x4008)
+#define FM10K_SRRCTL(_n) ((0x40 * (_n)) + 0x4009)
+#define FM10K_SRRCTL_BSIZEPKT_SHIFT 8 /* shift _right_ */
+#define FM10K_SRRCTL_LOOPBACK_SUPPRESS 0x40000000
+#define FM10K_SRRCTL_BUFFER_CHAINING_EN 0x80000000
+
+/* Rx Statistics */
+#define FM10K_QPRC(_n) ((0x40 * (_n)) + 0x400A)
+#define FM10K_QPRDC(_n) ((0x40 * (_n)) + 0x400B)
+#define FM10K_QBRC_L(_n) ((0x40 * (_n)) + 0x400C)
+#define FM10K_QBRC_H(_n) ((0x40 * (_n)) + 0x400D)
+
+/* Rx GLORT register */
+#define FM10K_RX_SGLORT(_n) ((0x40 * (_n)) + 0x400E)
+
+/* Tx ring registers */
+#define FM10K_TDBAL(_n) ((0x40 * (_n)) + 0x8000)
+#define FM10K_TDBAH(_n) ((0x40 * (_n)) + 0x8001)
+#define FM10K_TDLEN(_n) ((0x40 * (_n)) + 0x8002)
+#define FM10K_TPH_TXCTRL(_n) ((0x40 * (_n)) + 0x8003)
+#define FM10K_TPH_TXCTRL_DESC_TPHEN 0x00000020
+#define FM10K_TPH_TXCTRL_DESC_RROEN 0x00000200
+#define FM10K_TPH_TXCTRL_DESC_WROEN 0x00000800
+#define FM10K_TPH_TXCTRL_DATA_RROEN 0x00002000
+#define FM10K_TDH(_n) ((0x40 * (_n)) + 0x8004)
+#define FM10K_TDT(_n) ((0x40 * (_n)) + 0x8005)
+#define FM10K_TXDCTL(_n) ((0x40 * (_n)) + 0x8006)
+#define FM10K_TXDCTL_ENABLE 0x00004000
+#define FM10K_TXDCTL_MAX_TIME_SHIFT 16
+#define FM10K_TXQCTL(_n) ((0x40 * (_n)) + 0x8007)
+#define FM10K_TXQCTL_PF 0x0000003F
+#define FM10K_TXQCTL_VF 0x00000040
+#define FM10K_TXQCTL_ID_MASK (FM10K_TXQCTL_PF | FM10K_TXQCTL_VF)
+#define FM10K_TXQCTL_PC_SHIFT 7
+#define FM10K_TXQCTL_PC_MASK 0x00000380
+#define FM10K_TXQCTL_TC_SHIFT 10
+#define FM10K_TXQCTL_VID_SHIFT 16
+#define FM10K_TXQCTL_VID_MASK 0x0FFF0000
+#define FM10K_TXQCTL_UNLIMITED_BW 0x10000000
+#define FM10K_TXINT(_n) ((0x40 * (_n)) + 0x8008)
+
+/* Tx Statistics */
+#define FM10K_QPTC(_n) ((0x40 * (_n)) + 0x8009)
+#define FM10K_QBTC_L(_n) ((0x40 * (_n)) + 0x800A)
+#define FM10K_QBTC_H(_n) ((0x40 * (_n)) + 0x800B)
+
+/* Tx Push registers */
+#define FM10K_TQDLOC(_n) ((0x40 * (_n)) + 0x800C)
+#define FM10K_TQDLOC_BASE_32_DESC 0x08
+#define FM10K_TQDLOC_SIZE_32_DESC 0x00050000
+
+/* Tx GLORT registers */
+#define FM10K_TX_SGLORT(_n) ((0x40 * (_n)) + 0x800D)
+#define FM10K_PFVTCTL(_n) ((0x40 * (_n)) + 0x800E)
+#define FM10K_PFVTCTL_FTAG_DESC_ENABLE 0x00000001
+
+/* Interrupt moderation and control registers */
+#define FM10K_INT_MAP(_n) ((_n) + 0x10080)
+#define FM10K_INT_MAP_TIMER0 0x00000000
+#define FM10K_INT_MAP_TIMER1 0x00000100
+#define FM10K_INT_MAP_IMMEDIATE 0x00000200
+#define FM10K_INT_MAP_DISABLE 0x00000300
+#define FM10K_MSIX_VECTOR_MASK(_n) ((0x4 * (_n)) + 0x11003)
+#define FM10K_INT_CTRL 0x12000
+#define FM10K_INT_CTRL_ENABLEMODERATOR 0x00000400
+#define FM10K_ITR(_n) ((_n) + 0x12400)
+#define FM10K_ITR_INTERVAL1_SHIFT 12
+#define FM10K_ITR_PENDING2 0x10000000
+#define FM10K_ITR_AUTOMASK 0x20000000
+#define FM10K_ITR_MASK_SET 0x40000000
+#define FM10K_ITR_MASK_CLEAR 0x80000000
+#define FM10K_ITR2(_n) ((0x2 * (_n)) + 0x12800)
+#define FM10K_ITR_REG_COUNT 768
+#define FM10K_ITR_REG_COUNT_PF 256
+
+/* Switch manager interrupt registers */
+#define FM10K_IP 0x13000
+#define FM10K_IP_NOTINRESET 0x00000100
+
+/* VLAN registers */
+#define FM10K_VLAN_TABLE(_n, _m) ((0x80 * (_n)) + (_m) + 0x14000)
+#define FM10K_VLAN_TABLE_SIZE 128
+
+/* VLAN specific message offsets */
+#define FM10K_VLAN_TABLE_VID_MAX 4096
+#define FM10K_VLAN_TABLE_VSI_MAX 64
+#define FM10K_VLAN_LENGTH_SHIFT 16
+#define FM10K_VLAN_CLEAR (1 << 15)
+#define FM10K_VLAN_ALL \
+ ((FM10K_VLAN_TABLE_VID_MAX - 1) << FM10K_VLAN_LENGTH_SHIFT)
+
+/* VF FLR event notification registers */
+#define FM10K_PFVFLRE(_n) ((0x1 * (_n)) + 0x18844)
+#define FM10K_PFVFLREC(_n) ((0x1 * (_n)) + 0x18846)
+
+/* Defines for size of uncacheable memories */
+#define FM10K_UC_ADDR_START 0x000000 /* start of standard regs */
+#define FM10K_UC_ADDR_END 0x100000 /* end of standard regs */
+#define FM10K_UC_ADDR_SIZE (FM10K_UC_ADDR_END - FM10K_UC_ADDR_START)
+
+/* Define timeouts for resets and disables */
+#define FM10K_QUEUE_DISABLE_TIMEOUT 100
+#define FM10K_RESET_TIMEOUT 100
+
+enum fm10k_int_source {
+ fm10k_int_Mailbox = 0,
+ fm10k_int_PCIeFault = 1,
+ fm10k_int_SwitchUpDown = 2,
+ fm10k_int_SwitchEvent = 3,
+ fm10k_int_SRAM = 4,
+ fm10k_int_VFLR = 5,
+ fm10k_int_MaxHoldTime = 6,
+ fm10k_int_sources_max_pf
+};
+
+/* PCIe bus speeds */
+enum fm10k_bus_speed {
+ fm10k_bus_speed_unknown = 0,
+ fm10k_bus_speed_2500 = 2500,
+ fm10k_bus_speed_5000 = 5000,
+ fm10k_bus_speed_8000 = 8000,
+ fm10k_bus_speed_reserved
+};
+
+/* PCIe bus widths */
+enum fm10k_bus_width {
+ fm10k_bus_width_unknown = 0,
+ fm10k_bus_width_pcie_x1 = 1,
+ fm10k_bus_width_pcie_x2 = 2,
+ fm10k_bus_width_pcie_x4 = 4,
+ fm10k_bus_width_pcie_x8 = 8,
+ fm10k_bus_width_reserved
+};
+
+/* PCIe payload sizes */
+enum fm10k_bus_payload {
+ fm10k_bus_payload_unknown = 0,
+ fm10k_bus_payload_128 = 1,
+ fm10k_bus_payload_256 = 2,
+ fm10k_bus_payload_512 = 3,
+ fm10k_bus_payload_reserved
+};
+
+/* Bus parameters */
+struct fm10k_bus_info {
+ enum fm10k_bus_speed speed;
+ enum fm10k_bus_width width;
+ enum fm10k_bus_payload payload;
+};
+
+/* Statistics related declarations */
+struct fm10k_hw_stat {
+ u64 count;
+ u32 base_l;
+ u32 base_h;
+};
+
+struct fm10k_hw_stats_q {
+ struct fm10k_hw_stat tx_bytes;
+ struct fm10k_hw_stat tx_packets;
+#define tx_stats_idx tx_packets.base_h
+ struct fm10k_hw_stat rx_bytes;
+ struct fm10k_hw_stat rx_packets;
+#define rx_stats_idx rx_packets.base_h
+ struct fm10k_hw_stat rx_drops;
+};
+
+struct fm10k_hw_stats {
+ struct fm10k_hw_stat timeout;
+#define stats_idx timeout.base_h
+ struct fm10k_hw_stat ur;
+ struct fm10k_hw_stat ca;
+ struct fm10k_hw_stat um;
+ struct fm10k_hw_stat xec;
+ struct fm10k_hw_stat vlan_drop;
+ struct fm10k_hw_stat loopback_drop;
+ struct fm10k_hw_stat nodesc_drop;
+ struct fm10k_hw_stats_q q[FM10K_MAX_QUEUES_PF];
+};
+
+/* Establish DGLORT feature priority */
+enum fm10k_dglortdec_idx {
+ fm10k_dglort_default = 0,
+ fm10k_dglort_vf_rsvd0 = 1,
+ fm10k_dglort_vf_rss = 2,
+ fm10k_dglort_pf_rsvd0 = 3,
+ fm10k_dglort_pf_queue = 4,
+ fm10k_dglort_pf_vsi = 5,
+ fm10k_dglort_pf_rsvd1 = 6,
+ fm10k_dglort_pf_rss = 7
+};
+
+struct fm10k_dglort_cfg {
+ u16 glort; /* GLORT base */
+ u16 queue_b; /* Base value for queue */
+ u8 vsi_b; /* Base value for VSI */
+ u8 idx; /* index of DGLORTDEC entry */
+ u8 rss_l; /* RSS indices */
+ u8 pc_l; /* Priority Class indices */
+ u8 vsi_l; /* Number of bits from GLORT used to determine VSI */
+ u8 queue_l; /* Number of bits from GLORT used to determine queue */
+ u8 shared_l; /* Ignored bits from GLORT resulting in shared VSI */
+ u8 inner_rss; /* Boolean value if inner header is used for RSS */
+};
+
+enum fm10k_pca_fault {
+ PCA_NO_FAULT,
+ PCA_UNMAPPED_ADDR,
+ PCA_BAD_QACCESS_PF,
+ PCA_BAD_QACCESS_VF,
+ PCA_MALICIOUS_REQ,
+ PCA_POISONED_TLP,
+ PCA_TLP_ABORT,
+ __PCA_MAX
+};
+
+enum fm10k_thi_fault {
+ THI_NO_FAULT,
+ THI_MAL_DIS_Q_FAULT,
+ __THI_MAX
+};
+
+enum fm10k_fum_fault {
+ FUM_NO_FAULT,
+ FUM_UNMAPPED_ADDR,
+ FUM_POISONED_TLP,
+ FUM_BAD_VF_QACCESS,
+ FUM_ADD_DECODE_ERR,
+ FUM_RO_ERROR,
+ FUM_QPRC_CRC_ERROR,
+ FUM_CSR_TIMEOUT,
+ FUM_INVALID_TYPE,
+ FUM_INVALID_LENGTH,
+ FUM_INVALID_BE,
+ FUM_INVALID_ALIGN,
+ __FUM_MAX
+};
+
+struct fm10k_fault {
+ u64 address; /* Address at the time fault was detected */
+ u32 specinfo; /* Extra info on this fault (fault dependent) */
+ u8 type; /* Fault value dependent on subunit */
+ u8 func; /* Function number of the fault */
+};
+
+struct fm10k_mac_ops {
+ /* basic bring-up and tear-down */
+ s32 (*reset_hw)(struct fm10k_hw *);
+ s32 (*init_hw)(struct fm10k_hw *);
+ s32 (*start_hw)(struct fm10k_hw *);
+ s32 (*stop_hw)(struct fm10k_hw *);
+ s32 (*get_bus_info)(struct fm10k_hw *);
+ s32 (*get_host_state)(struct fm10k_hw *, bool *);
+ bool (*is_slot_appropriate)(struct fm10k_hw *);
+ s32 (*update_vlan)(struct fm10k_hw *, u32, u8, bool);
+ s32 (*read_mac_addr)(struct fm10k_hw *);
+ s32 (*update_uc_addr)(struct fm10k_hw *, u16, const u8 *,
+ u16, bool, u8);
+ s32 (*update_mc_addr)(struct fm10k_hw *, u16, const u8 *, u16, bool);
+ s32 (*update_xcast_mode)(struct fm10k_hw *, u16, u8);
+ void (*update_int_moderator)(struct fm10k_hw *);
+ s32 (*update_lport_state)(struct fm10k_hw *, u16, u16, bool);
+ void (*update_hw_stats)(struct fm10k_hw *, struct fm10k_hw_stats *);
+ void (*rebind_hw_stats)(struct fm10k_hw *, struct fm10k_hw_stats *);
+ s32 (*configure_dglort_map)(struct fm10k_hw *,
+ struct fm10k_dglort_cfg *);
+ void (*set_dma_mask)(struct fm10k_hw *, u64);
+ s32 (*get_fault)(struct fm10k_hw *, int, struct fm10k_fault *);
+ void (*request_lport_map)(struct fm10k_hw *);
+ s32 (*adjust_systime)(struct fm10k_hw *, s32 ppb);
+};
+
+enum fm10k_mac_type {
+ fm10k_mac_unknown = 0,
+ fm10k_mac_pf,
+ fm10k_num_macs
+};
+
+struct fm10k_mac_info {
+ struct fm10k_mac_ops ops;
+ enum fm10k_mac_type type;
+ u8 addr[ETH_ALEN];
+ u8 perm_addr[ETH_ALEN];
+ u16 default_vid;
+ u16 max_msix_vectors;
+ u16 max_queues;
+ bool vlan_override;
+ bool get_host_state;
+ bool tx_ready;
+ u32 dglort_map;
+};
+
+struct fm10k_swapi_table_info {
+ u32 used;
+ u32 avail;
+};
+
+struct fm10k_swapi_info {
+ u32 status;
+ struct fm10k_swapi_table_info mac;
+ struct fm10k_swapi_table_info nexthop;
+ struct fm10k_swapi_table_info ffu;
+};
+
+enum fm10k_xcast_modes {
+ FM10K_XCAST_MODE_ALLMULTI = 0,
+ FM10K_XCAST_MODE_MULTI = 1,
+ FM10K_XCAST_MODE_PROMISC = 2,
+ FM10K_XCAST_MODE_NONE = 3,
+ FM10K_XCAST_MODE_DISABLE = 4
+};
+
+enum fm10k_devices {
+ fm10k_device_pf,
+};
+
+struct fm10k_info {
+ enum fm10k_mac_type mac;
+ s32 (*get_invariants)(struct fm10k_hw *);
+ struct fm10k_mac_ops *mac_ops;
+};
+
+struct fm10k_hw {
+ u32 __iomem *hw_addr;
+ void *back;
+ struct fm10k_mac_info mac;
+ struct fm10k_bus_info bus;
+ struct fm10k_bus_info bus_caps;
+ struct fm10k_swapi_info swapi;
+ u16 device_id;
+ u16 vendor_id;
+ u16 subsystem_device_id;
+ u16 subsystem_vendor_id;
+ u8 revision_id;
+};
+
+/* Number of Transmit and Receive Descriptors must be a multiple of 8 */
+#define FM10K_REQ_TX_DESCRIPTOR_MULTIPLE 8
+#define FM10K_REQ_RX_DESCRIPTOR_MULTIPLE 8
+
+/* Transmit Descriptor */
+struct fm10k_tx_desc {
+ __le64 buffer_addr; /* Address of the descriptor's data buffer */
+ __le16 buflen; /* Length of data to be DMAed */
+ __le16 vlan; /* VLAN_ID and VPRI to be inserted in FTAG */
+ __le16 mss; /* MSS for segmentation offload */
+ u8 hdrlen; /* Header size for segmentation offload */
+ u8 flags; /* Status and offload request flags */
+};
+
+/* Transmit Descriptor Cache Structure */
+struct fm10k_tx_desc_cache {
+ struct fm10k_tx_desc tx_desc[256];
+};
+
+#define FM10K_TXD_FLAG_INT 0x01
+#define FM10K_TXD_FLAG_TIME 0x02
+#define FM10K_TXD_FLAG_CSUM 0x04
+#define FM10K_TXD_FLAG_FTAG 0x10
+#define FM10K_TXD_FLAG_RS 0x20
+#define FM10K_TXD_FLAG_LAST 0x40
+#define FM10K_TXD_FLAG_DONE 0x80
+
+/* These macros are meant to enable optimal placement of the RS and INT
+ * bits. It will point us to the last descriptor in the cache for either the
+ * start of the packet, or the end of the packet. If the index is actually
+ * at the start of the FIFO it will point to the offset for the last index
+ * in the FIFO to prevent an unnecessary write.
+ */
+#define FM10K_TXD_WB_FIFO_SIZE 4
+
+/* Receive Descriptor - 32B */
+union fm10k_rx_desc {
+ struct {
+ __le64 pkt_addr; /* Packet buffer address */
+ __le64 hdr_addr; /* Header buffer address */
+ __le64 reserved; /* Empty space, RSS hash */
+ __le64 timestamp;
+ } q; /* Read, Writeback, 64b quad-words */
+ struct {
+ __le32 data; /* RSS and header data */
+ __le32 rss; /* RSS Hash */
+ __le32 staterr;
+ __le32 vlan_len;
+ __le32 glort; /* sglort/dglort */
+ } d; /* Writeback, 32b double-words */
+ struct {
+ __le16 pkt_info; /* RSS, Pkt type */
+ __le16 hdr_info; /* Splithdr, hdrlen, xC */
+ __le16 rss_lower;
+ __le16 rss_upper;
+ __le16 status; /* status/error */
+ __le16 csum_err; /* checksum or extended error value */
+ __le16 length; /* Packet length */
+ __le16 vlan; /* VLAN tag */
+ __le16 dglort;
+ __le16 sglort;
+ } w; /* Writeback, 16b words */
+};
+
+#define FM10K_RXD_RSSTYPE_MASK 0x000F
+enum fm10k_rdesc_rss_type {
+ FM10K_RSSTYPE_NONE = 0x0,
+ FM10K_RSSTYPE_IPV4_TCP = 0x1,
+ FM10K_RSSTYPE_IPV4 = 0x2,
+ FM10K_RSSTYPE_IPV6_TCP = 0x3,
+ /* Reserved 0x4 */
+ FM10K_RSSTYPE_IPV6 = 0x5,
+ /* Reserved 0x6 */
+ FM10K_RSSTYPE_IPV4_UDP = 0x7,
+ FM10K_RSSTYPE_IPV6_UDP = 0x8
+ /* Reserved 0x9 - 0xF */
+};
+
+#define FM10K_RXD_HDR_INFO_XC_MASK 0x0006
+enum fm10k_rxdesc_xc {
+ FM10K_XC_UNICAST = 0x0,
+ FM10K_XC_MULTICAST = 0x4,
+ FM10K_XC_BROADCAST = 0x6
+};
+
+#define FM10K_RXD_STATUS_DD 0x0001 /* Descriptor done */
+#define FM10K_RXD_STATUS_EOP 0x0002 /* End of packet */
+#define FM10K_RXD_STATUS_L4CS 0x0010 /* Indicates an L4 csum */
+#define FM10K_RXD_STATUS_L4CS2 0x0040 /* Inner header L4 csum */
+#define FM10K_RXD_STATUS_L4E2 0x0800 /* Inner header L4 csum err */
+#define FM10K_RXD_STATUS_IPE2 0x1000 /* Inner header IPv4 csum err */
+#define FM10K_RXD_STATUS_RXE 0x2000 /* Generic Rx error */
+#define FM10K_RXD_STATUS_L4E 0x4000 /* L4 csum error */
+#define FM10K_RXD_STATUS_IPE 0x8000 /* IPv4 csum error */
+
+struct fm10k_ftag {
+ __be16 swpri_type_user;
+ __be16 vlan;
+ __be16 sglort;
+ __be16 dglort;
+};
+
#endif /* _FM10K_TYPE_H */
^ permalink raw reply related
* [net-next PATCH v2 03/29] fm10k: Add support for TLV message parsing and generation
From: Alexander Duyck @ 2014-09-20 23:46 UTC (permalink / raw)
To: davem
Cc: nhorman, netdev, john.fastabend, matthew.vick, jeffrey.t.kirsher,
sassmann
In-Reply-To: <20140920234342.2977.21667.stgit@ahduyck-bv4.jf.intel.com>
This patch adds support for the TVL message formats supported by the PF,
VF, and Switch Management entity.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
---
drivers/net/ethernet/intel/fm10k/Makefile | 3
drivers/net/ethernet/intel/fm10k/fm10k_tlv.c | 543 ++++++++++++++++++++++++++
drivers/net/ethernet/intel/fm10k/fm10k_tlv.h | 141 +++++++
3 files changed, 686 insertions(+), 1 deletion(-)
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_tlv.c
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_tlv.h
diff --git a/drivers/net/ethernet/intel/fm10k/Makefile b/drivers/net/ethernet/intel/fm10k/Makefile
index ddc0eb7..1052808 100644
--- a/drivers/net/ethernet/intel/fm10k/Makefile
+++ b/drivers/net/ethernet/intel/fm10k/Makefile
@@ -27,4 +27,5 @@
obj-$(CONFIG_FM10K) += fm10k.o
-fm10k-objs := fm10k_main.o fm10k_pci.o
+fm10k-objs := fm10k_main.o fm10k_pci.o \
+ fm10k_tlv.o
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c
new file mode 100644
index 0000000..f1fc709
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c
@@ -0,0 +1,543 @@
+/* Intel Ethernet Switch Host Interface Driver
+ * Copyright(c) 2013 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
+
+#include "fm10k_tlv.h"
+
+/**
+ * fm10k_tlv_msg_init - Initialize message block for TLV data storage
+ * @msg: Pointer to message block
+ * @msg_id: Message ID indicating message type
+ *
+ * This function return success if provided with a valid message pointer
+ **/
+s32 fm10k_tlv_msg_init(u32 *msg, u16 msg_id)
+{
+ /* verify pointer is not NULL */
+ if (!msg)
+ return FM10K_ERR_PARAM;
+
+ *msg = (FM10K_TLV_FLAGS_MSG << FM10K_TLV_FLAGS_SHIFT) | msg_id;
+
+ return 0;
+}
+
+/**
+ * fm10k_tlv_attr_put_null_string - Place null terminated string on message
+ * @msg: Pointer to message block
+ * @attr_id: Attribute ID
+ * @string: Pointer to string to be stored in attribute
+ *
+ * This function will reorder a string to be CPU endian and store it in
+ * the attribute buffer. It will return success if provided with a valid
+ * pointers.
+ **/
+s32 fm10k_tlv_attr_put_null_string(u32 *msg, u16 attr_id,
+ const unsigned char *string)
+{
+ u32 attr_data = 0, len = 0;
+ u32 *attr;
+
+ /* verify pointers are not NULL */
+ if (!string || !msg)
+ return FM10K_ERR_PARAM;
+
+ attr = &msg[FM10K_TLV_DWORD_LEN(*msg)];
+
+ /* copy string into local variable and then write to msg */
+ do {
+ /* write data to message */
+ if (len && !(len % 4)) {
+ attr[len / 4] = attr_data;
+ attr_data = 0;
+ }
+
+ /* record character to offset location */
+ attr_data |= (u32)(*string) << (8 * (len % 4));
+ len++;
+
+ /* test for NULL and then increment */
+ } while (*(string++));
+
+ /* write last piece of data to message */
+ attr[(len + 3) / 4] = attr_data;
+
+ /* record attribute header, update message length */
+ len <<= FM10K_TLV_LEN_SHIFT;
+ attr[0] = len | attr_id;
+
+ /* add header length to length */
+ len += FM10K_TLV_HDR_LEN << FM10K_TLV_LEN_SHIFT;
+ *msg += FM10K_TLV_LEN_ALIGN(len);
+
+ return 0;
+}
+
+/**
+ * fm10k_tlv_attr_get_null_string - Get null terminated string from attribute
+ * @attr: Pointer to attribute
+ * @string: Pointer to location of destination string
+ *
+ * This function pulls the string back out of the attribute and will place
+ * it in the array pointed by by string. It will return success if provided
+ * with a valid pointers.
+ **/
+s32 fm10k_tlv_attr_get_null_string(u32 *attr, unsigned char *string)
+{
+ u32 len;
+
+ /* verify pointers are not NULL */
+ if (!string || !attr)
+ return FM10K_ERR_PARAM;
+
+ len = *attr >> FM10K_TLV_LEN_SHIFT;
+ attr++;
+
+ while (len--)
+ string[len] = (u8)(attr[len / 4] >> (8 * (len % 4)));
+
+ return 0;
+}
+
+/**
+ * fm10k_tlv_attr_put_mac_vlan - Store MAC/VLAN attribute in message
+ * @msg: Pointer to message block
+ * @attr_id: Attribute ID
+ * @mac_addr: MAC address to be stored
+ *
+ * This function will reorder a MAC address to be CPU endian and store it
+ * in the attribute buffer. It will return success if provided with a
+ * valid pointers.
+ **/
+s32 fm10k_tlv_attr_put_mac_vlan(u32 *msg, u16 attr_id,
+ const u8 *mac_addr, u16 vlan)
+{
+ u32 len = ETH_ALEN << FM10K_TLV_LEN_SHIFT;
+ u32 *attr;
+
+ /* verify pointers are not NULL */
+ if (!msg || !mac_addr)
+ return FM10K_ERR_PARAM;
+
+ attr = &msg[FM10K_TLV_DWORD_LEN(*msg)];
+
+ /* record attribute header, update message length */
+ attr[0] = len | attr_id;
+
+ /* copy value into local variable and then write to msg */
+ attr[1] = le32_to_cpu(*(const __le32 *)&mac_addr[0]);
+ attr[2] = le16_to_cpu(*(const __le16 *)&mac_addr[4]);
+ attr[2] |= (u32)vlan << 16;
+
+ /* add header length to length */
+ len += FM10K_TLV_HDR_LEN << FM10K_TLV_LEN_SHIFT;
+ *msg += FM10K_TLV_LEN_ALIGN(len);
+
+ return 0;
+}
+
+/**
+ * fm10k_tlv_attr_get_mac_vlan - Get MAC/VLAN stored in attribute
+ * @attr: Pointer to attribute
+ * @attr_id: Attribute ID
+ * @mac_addr: location of buffer to store MAC address
+ *
+ * This function pulls the MAC address back out of the attribute and will
+ * place it in the array pointed by by mac_addr. It will return success
+ * if provided with a valid pointers.
+ **/
+s32 fm10k_tlv_attr_get_mac_vlan(u32 *attr, u8 *mac_addr, u16 *vlan)
+{
+ /* verify pointers are not NULL */
+ if (!mac_addr || !attr)
+ return FM10K_ERR_PARAM;
+
+ *(__le32 *)&mac_addr[0] = cpu_to_le32(attr[1]);
+ *(__le16 *)&mac_addr[4] = cpu_to_le16((u16)(attr[2]));
+ *vlan = (u16)(attr[2] >> 16);
+
+ return 0;
+}
+
+/**
+ * fm10k_tlv_attr_put_bool - Add header indicating value "true"
+ * @msg: Pointer to message block
+ * @attr_id: Attribute ID
+ *
+ * This function will simply add an attribute header, the fact
+ * that the header is here means the attribute value is true, else
+ * it is false. The function will return success if provided with a
+ * valid pointers.
+ **/
+s32 fm10k_tlv_attr_put_bool(u32 *msg, u16 attr_id)
+{
+ /* verify pointers are not NULL */
+ if (!msg)
+ return FM10K_ERR_PARAM;
+
+ /* record attribute header */
+ msg[FM10K_TLV_DWORD_LEN(*msg)] = attr_id;
+
+ /* add header length to length */
+ *msg += FM10K_TLV_HDR_LEN << FM10K_TLV_LEN_SHIFT;
+
+ return 0;
+}
+
+/**
+ * fm10k_tlv_attr_put_value - Store integer value attribute in message
+ * @msg: Pointer to message block
+ * @attr_id: Attribute ID
+ * @value: Value to be written
+ * @len: Size of value
+ *
+ * This function will place an integer value of up to 8 bytes in size
+ * in a message attribute. The function will return success provided
+ * that msg is a valid pointer, and len is 1, 2, 4, or 8.
+ **/
+s32 fm10k_tlv_attr_put_value(u32 *msg, u16 attr_id, s64 value, u32 len)
+{
+ u32 *attr;
+
+ /* verify non-null msg and len is 1, 2, 4, or 8 */
+ if (!msg || !len || len > 8 || (len & (len - 1)))
+ return FM10K_ERR_PARAM;
+
+ attr = &msg[FM10K_TLV_DWORD_LEN(*msg)];
+
+ if (len < 4) {
+ attr[1] = (u32)value & ((0x1ul << (8 * len)) - 1);
+ } else {
+ attr[1] = (u32)value;
+ if (len > 4)
+ attr[2] = (u32)(value >> 32);
+ }
+
+ /* record attribute header, update message length */
+ len <<= FM10K_TLV_LEN_SHIFT;
+ attr[0] = len | attr_id;
+
+ /* add header length to length */
+ len += FM10K_TLV_HDR_LEN << FM10K_TLV_LEN_SHIFT;
+ *msg += FM10K_TLV_LEN_ALIGN(len);
+
+ return 0;
+}
+
+/**
+ * fm10k_tlv_attr_get_value - Get integer value stored in attribute
+ * @attr: Pointer to attribute
+ * @value: Pointer to destination buffer
+ * @len: Size of value
+ *
+ * This function will place an integer value of up to 8 bytes in size
+ * in the offset pointed to by value. The function will return success
+ * provided that pointers are valid and the len value matches the
+ * attribute length.
+ **/
+s32 fm10k_tlv_attr_get_value(u32 *attr, void *value, u32 len)
+{
+ /* verify pointers are not NULL */
+ if (!attr || !value)
+ return FM10K_ERR_PARAM;
+
+ if ((*attr >> FM10K_TLV_LEN_SHIFT) != len)
+ return FM10K_ERR_PARAM;
+
+ if (len == 8)
+ *(u64 *)value = ((u64)attr[2] << 32) | attr[1];
+ else if (len == 4)
+ *(u32 *)value = attr[1];
+ else if (len == 2)
+ *(u16 *)value = (u16)attr[1];
+ else
+ *(u8 *)value = (u8)attr[1];
+
+ return 0;
+}
+
+/**
+ * fm10k_tlv_attr_put_le_struct - Store little endian structure in message
+ * @msg: Pointer to message block
+ * @attr_id: Attribute ID
+ * @le_struct: Pointer to structure to be written
+ * @len: Size of le_struct
+ *
+ * This function will place a little endian structure value in a message
+ * attribute. The function will return success provided that all pointers
+ * are valid and length is a non-zero multiple of 4.
+ **/
+s32 fm10k_tlv_attr_put_le_struct(u32 *msg, u16 attr_id,
+ const void *le_struct, u32 len)
+{
+ const __le32 *le32_ptr = (const __le32 *)le_struct;
+ u32 *attr;
+ u32 i;
+
+ /* verify non-null msg and len is in 32 bit words */
+ if (!msg || !len || (len % 4))
+ return FM10K_ERR_PARAM;
+
+ attr = &msg[FM10K_TLV_DWORD_LEN(*msg)];
+
+ /* copy le32 structure into host byte order at 32b boundaries */
+ for (i = 0; i < (len / 4); i++)
+ attr[i + 1] = le32_to_cpu(le32_ptr[i]);
+
+ /* record attribute header, update message length */
+ len <<= FM10K_TLV_LEN_SHIFT;
+ attr[0] = len | attr_id;
+
+ /* add header length to length */
+ len += FM10K_TLV_HDR_LEN << FM10K_TLV_LEN_SHIFT;
+ *msg += FM10K_TLV_LEN_ALIGN(len);
+
+ return 0;
+}
+
+/**
+ * fm10k_tlv_attr_get_le_struct - Get little endian struct form attribute
+ * @attr: Pointer to attribute
+ * @le_struct: Pointer to structure to be written
+ * @len: Size of structure
+ *
+ * This function will place a little endian structure in the buffer
+ * pointed to by le_struct. The function will return success
+ * provided that pointers are valid and the len value matches the
+ * attribute length.
+ **/
+s32 fm10k_tlv_attr_get_le_struct(u32 *attr, void *le_struct, u32 len)
+{
+ __le32 *le32_ptr = (__le32 *)le_struct;
+ u32 i;
+
+ /* verify pointers are not NULL */
+ if (!le_struct || !attr)
+ return FM10K_ERR_PARAM;
+
+ if ((*attr >> FM10K_TLV_LEN_SHIFT) != len)
+ return FM10K_ERR_PARAM;
+
+ attr++;
+
+ for (i = 0; len; i++, len -= 4)
+ le32_ptr[i] = cpu_to_le32(attr[i]);
+
+ return 0;
+}
+
+/**
+ * fm10k_tlv_attr_nest_start - Start a set of nested attributes
+ * @msg: Pointer to message block
+ * @attr_id: Attribute ID
+ *
+ * This function will mark off a new nested region for encapsulating
+ * a given set of attributes. The idea is if you wish to place a secondary
+ * structure within the message this mechanism allows for that. The
+ * function will return NULL on failure, and a pointer to the start
+ * of the nested attributes on success.
+ **/
+u32 *fm10k_tlv_attr_nest_start(u32 *msg, u16 attr_id)
+{
+ u32 *attr;
+
+ /* verify pointer is not NULL */
+ if (!msg)
+ return NULL;
+
+ attr = &msg[FM10K_TLV_DWORD_LEN(*msg)];
+
+ attr[0] = attr_id;
+
+ /* return pointer to nest header */
+ return attr;
+}
+
+/**
+ * fm10k_tlv_attr_nest_start - Start a set of nested attributes
+ * @msg: Pointer to message block
+ *
+ * This function closes off an existing set of nested attributes. The
+ * message pointer should be pointing to the parent of the nest. So in
+ * the case of a nest within the nest this would be the outer nest pointer.
+ * This function will return success provided all pointers are valid.
+ **/
+s32 fm10k_tlv_attr_nest_stop(u32 *msg)
+{
+ u32 *attr;
+ u32 len;
+
+ /* verify pointer is not NULL */
+ if (!msg)
+ return FM10K_ERR_PARAM;
+
+ /* locate the nested header and retrieve its length */
+ attr = &msg[FM10K_TLV_DWORD_LEN(*msg)];
+ len = (attr[0] >> FM10K_TLV_LEN_SHIFT) << FM10K_TLV_LEN_SHIFT;
+
+ /* only include nest if data was added to it */
+ if (len) {
+ len += FM10K_TLV_HDR_LEN << FM10K_TLV_LEN_SHIFT;
+ *msg += len;
+ }
+
+ return 0;
+}
+
+/**
+ * fm10k_tlv_attr_validate - Validate attribute metadata
+ * @attr: Pointer to attribute
+ * @tlv_attr: Type and length info for attribute
+ *
+ * This function does some basic validation of the input TLV. It
+ * verifies the length, and in the case of null terminated strings
+ * it verifies that the last byte is null. The function will
+ * return FM10K_ERR_PARAM if any attribute is malformed, otherwise
+ * it returns 0.
+ **/
+static s32 fm10k_tlv_attr_validate(u32 *attr,
+ const struct fm10k_tlv_attr *tlv_attr)
+{
+ u32 attr_id = *attr & FM10K_TLV_ID_MASK;
+ u16 len = *attr >> FM10K_TLV_LEN_SHIFT;
+
+ /* verify this is an attribute and not a message */
+ if (*attr & (FM10K_TLV_FLAGS_MSG << FM10K_TLV_FLAGS_SHIFT))
+ return FM10K_ERR_PARAM;
+
+ /* search through the list of attributes to find a matching ID */
+ while (tlv_attr->id < attr_id)
+ tlv_attr++;
+
+ /* if didn't find a match then we should exit */
+ if (tlv_attr->id != attr_id)
+ return FM10K_NOT_IMPLEMENTED;
+
+ /* move to start of attribute data */
+ attr++;
+
+ switch (tlv_attr->type) {
+ case FM10K_TLV_NULL_STRING:
+ if (!len ||
+ (attr[(len - 1) / 4] & (0xFF << (8 * ((len - 1) % 4)))))
+ return FM10K_ERR_PARAM;
+ if (len > tlv_attr->len)
+ return FM10K_ERR_PARAM;
+ break;
+ case FM10K_TLV_MAC_ADDR:
+ if (len != ETH_ALEN)
+ return FM10K_ERR_PARAM;
+ break;
+ case FM10K_TLV_BOOL:
+ if (len)
+ return FM10K_ERR_PARAM;
+ break;
+ case FM10K_TLV_UNSIGNED:
+ case FM10K_TLV_SIGNED:
+ if (len != tlv_attr->len)
+ return FM10K_ERR_PARAM;
+ break;
+ case FM10K_TLV_LE_STRUCT:
+ /* struct must be 4 byte aligned */
+ if ((len % 4) || len != tlv_attr->len)
+ return FM10K_ERR_PARAM;
+ break;
+ case FM10K_TLV_NESTED:
+ /* nested attributes must be 4 byte aligned */
+ if (len % 4)
+ return FM10K_ERR_PARAM;
+ break;
+ default:
+ /* attribute id is mapped to bad value */
+ return FM10K_ERR_PARAM;
+ }
+
+ return 0;
+}
+
+/**
+ * fm10k_tlv_attr_parse - Parses stream of attribute data
+ * @attr: Pointer to attribute list
+ * @results: Pointer array to store pointers to attributes
+ * @tlv_attr: Type and length info for attributes
+ *
+ * This function validates a stream of attributes and parses them
+ * up into an array of pointers stored in results. The function will
+ * return FM10K_ERR_PARAM on any input or message error,
+ * FM10K_NOT_IMPLEMENTED for any attribute that is outside of the array
+ * and 0 on success.
+ **/
+s32 fm10k_tlv_attr_parse(u32 *attr, u32 **results,
+ const struct fm10k_tlv_attr *tlv_attr)
+{
+ u32 i, attr_id, offset = 0;
+ s32 err = 0;
+ u16 len;
+
+ /* verify pointers are not NULL */
+ if (!attr || !results)
+ return FM10K_ERR_PARAM;
+
+ /* initialize results to NULL */
+ for (i = 0; i < FM10K_TLV_RESULTS_MAX; i++)
+ results[i] = NULL;
+
+ /* pull length from the message header */
+ len = *attr >> FM10K_TLV_LEN_SHIFT;
+
+ /* no attributes to parse if there is no length */
+ if (!len)
+ return 0;
+
+ /* no attributes to parse, just raw data, message becomes attribute */
+ if (!tlv_attr) {
+ results[0] = attr;
+ return 0;
+ }
+
+ /* move to start of attribute data */
+ attr++;
+
+ /* run through list parsing all attributes */
+ while (offset < len) {
+ attr_id = *attr & FM10K_TLV_ID_MASK;
+
+ if (attr_id < FM10K_TLV_RESULTS_MAX)
+ err = fm10k_tlv_attr_validate(attr, tlv_attr);
+ else
+ err = FM10K_NOT_IMPLEMENTED;
+
+ if (err < 0)
+ return err;
+ if (!err)
+ results[attr_id] = attr;
+
+ /* update offset */
+ offset += FM10K_TLV_DWORD_LEN(*attr) * 4;
+
+ /* move to next attribute */
+ attr = &attr[FM10K_TLV_DWORD_LEN(*attr)];
+ }
+
+ /* we should find ourselves at the end of the list */
+ if (offset != len)
+ return FM10K_ERR_PARAM;
+
+ return 0;
+}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.h b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.h
new file mode 100644
index 0000000..6d22db6
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.h
@@ -0,0 +1,141 @@
+/* Intel Ethernet Switch Host Interface Driver
+ * Copyright(c) 2013 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
+
+#ifndef _FM10K_TLV_H_
+#define _FM10K_TLV_H_
+
+#include "fm10k_type.h"
+
+/* Message / Argument header format
+ * 3 2 1 0
+ * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Length | Flags | Type / ID |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * The message header format described here is used for messages that are
+ * passed between the PF and the VF. To allow for messages larger then
+ * mailbox size we will provide a message with the above header and it
+ * will be segmented and transported to the mailbox to the other side where
+ * it is reassembled. It contains the following fields:
+ * Len: Length of the message in bytes excluding the message header
+ * Flags: TBD
+ * Rule: These will be the message/argument types we pass
+ */
+/* message data header */
+#define FM10K_TLV_ID_SHIFT 0
+#define FM10K_TLV_ID_SIZE 16
+#define FM10K_TLV_ID_MASK ((1u << FM10K_TLV_ID_SIZE) - 1)
+#define FM10K_TLV_FLAGS_SHIFT 16
+#define FM10K_TLV_FLAGS_MSG 0x1
+#define FM10K_TLV_FLAGS_SIZE 4
+#define FM10K_TLV_LEN_SHIFT 20
+#define FM10K_TLV_LEN_SIZE 12
+
+#define FM10K_TLV_HDR_LEN 4ul
+#define FM10K_TLV_LEN_ALIGN_MASK \
+ ((FM10K_TLV_HDR_LEN - 1) << FM10K_TLV_LEN_SHIFT)
+#define FM10K_TLV_LEN_ALIGN(tlv) \
+ (((tlv) + FM10K_TLV_LEN_ALIGN_MASK) & ~FM10K_TLV_LEN_ALIGN_MASK)
+#define FM10K_TLV_DWORD_LEN(tlv) \
+ ((u16)((FM10K_TLV_LEN_ALIGN(tlv)) >> (FM10K_TLV_LEN_SHIFT + 2)) + 1)
+
+#define FM10K_TLV_RESULTS_MAX 32
+
+enum fm10k_tlv_type {
+ FM10K_TLV_NULL_STRING,
+ FM10K_TLV_MAC_ADDR,
+ FM10K_TLV_BOOL,
+ FM10K_TLV_UNSIGNED,
+ FM10K_TLV_SIGNED,
+ FM10K_TLV_LE_STRUCT,
+ FM10K_TLV_NESTED,
+ FM10K_TLV_MAX_TYPE
+};
+
+#define FM10K_TLV_ERROR (~0u)
+
+struct fm10k_tlv_attr {
+ unsigned int id;
+ enum fm10k_tlv_type type;
+ u16 len;
+};
+
+#define FM10K_TLV_ATTR_NULL_STRING(id, len) { id, FM10K_TLV_NULL_STRING, len }
+#define FM10K_TLV_ATTR_MAC_ADDR(id) { id, FM10K_TLV_MAC_ADDR, 6 }
+#define FM10K_TLV_ATTR_BOOL(id) { id, FM10K_TLV_BOOL, 0 }
+#define FM10K_TLV_ATTR_U8(id) { id, FM10K_TLV_UNSIGNED, 1 }
+#define FM10K_TLV_ATTR_U16(id) { id, FM10K_TLV_UNSIGNED, 2 }
+#define FM10K_TLV_ATTR_U32(id) { id, FM10K_TLV_UNSIGNED, 4 }
+#define FM10K_TLV_ATTR_U64(id) { id, FM10K_TLV_UNSIGNED, 8 }
+#define FM10K_TLV_ATTR_S8(id) { id, FM10K_TLV_SIGNED, 1 }
+#define FM10K_TLV_ATTR_S16(id) { id, FM10K_TLV_SIGNED, 2 }
+#define FM10K_TLV_ATTR_S32(id) { id, FM10K_TLV_SIGNED, 4 }
+#define FM10K_TLV_ATTR_S64(id) { id, FM10K_TLV_SIGNED, 8 }
+#define FM10K_TLV_ATTR_LE_STRUCT(id, len) { id, FM10K_TLV_LE_STRUCT, len }
+#define FM10K_TLV_ATTR_NESTED(id) { id, FM10K_TLV_NESTED }
+#define FM10K_TLV_ATTR_LAST { FM10K_TLV_ERROR }
+
+s32 fm10k_tlv_msg_init(u32 *, u16);
+s32 fm10k_tlv_attr_put_null_string(u32 *, u16, const unsigned char *);
+s32 fm10k_tlv_attr_get_null_string(u32 *, unsigned char *);
+s32 fm10k_tlv_attr_put_mac_vlan(u32 *, u16, const u8 *, u16);
+s32 fm10k_tlv_attr_get_mac_vlan(u32 *, u8 *, u16 *);
+s32 fm10k_tlv_attr_put_bool(u32 *, u16);
+s32 fm10k_tlv_attr_put_value(u32 *, u16, s64, u32);
+#define fm10k_tlv_attr_put_u8(msg, attr_id, val) \
+ fm10k_tlv_attr_put_value(msg, attr_id, val, 1)
+#define fm10k_tlv_attr_put_u16(msg, attr_id, val) \
+ fm10k_tlv_attr_put_value(msg, attr_id, val, 2)
+#define fm10k_tlv_attr_put_u32(msg, attr_id, val) \
+ fm10k_tlv_attr_put_value(msg, attr_id, val, 4)
+#define fm10k_tlv_attr_put_u64(msg, attr_id, val) \
+ fm10k_tlv_attr_put_value(msg, attr_id, val, 8)
+#define fm10k_tlv_attr_put_s8(msg, attr_id, val) \
+ fm10k_tlv_attr_put_value(msg, attr_id, val, 1)
+#define fm10k_tlv_attr_put_s16(msg, attr_id, val) \
+ fm10k_tlv_attr_put_value(msg, attr_id, val, 2)
+#define fm10k_tlv_attr_put_s32(msg, attr_id, val) \
+ fm10k_tlv_attr_put_value(msg, attr_id, val, 4)
+#define fm10k_tlv_attr_put_s64(msg, attr_id, val) \
+ fm10k_tlv_attr_put_value(msg, attr_id, val, 8)
+s32 fm10k_tlv_attr_get_value(u32 *, void *, u32);
+#define fm10k_tlv_attr_get_u8(attr, ptr) \
+ fm10k_tlv_attr_get_value(attr, ptr, sizeof(u8))
+#define fm10k_tlv_attr_get_u16(attr, ptr) \
+ fm10k_tlv_attr_get_value(attr, ptr, sizeof(u16))
+#define fm10k_tlv_attr_get_u32(attr, ptr) \
+ fm10k_tlv_attr_get_value(attr, ptr, sizeof(u32))
+#define fm10k_tlv_attr_get_u64(attr, ptr) \
+ fm10k_tlv_attr_get_value(attr, ptr, sizeof(u64))
+#define fm10k_tlv_attr_get_s8(attr, ptr) \
+ fm10k_tlv_attr_get_value(attr, ptr, sizeof(s8))
+#define fm10k_tlv_attr_get_s16(attr, ptr) \
+ fm10k_tlv_attr_get_value(attr, ptr, sizeof(s16))
+#define fm10k_tlv_attr_get_s32(attr, ptr) \
+ fm10k_tlv_attr_get_value(attr, ptr, sizeof(s32))
+#define fm10k_tlv_attr_get_s64(attr, ptr) \
+ fm10k_tlv_attr_get_value(attr, ptr, sizeof(s64))
+s32 fm10k_tlv_attr_put_le_struct(u32 *, u16, const void *, u32);
+s32 fm10k_tlv_attr_get_le_struct(u32 *, void *, u32);
+u32 *fm10k_tlv_attr_nest_start(u32 *, u16);
+s32 fm10k_tlv_attr_nest_stop(u32 *);
+s32 fm10k_tlv_attr_parse(u32 *, u32 **, const struct fm10k_tlv_attr *);
+#endif /* _FM10K_MSG_H_ */
^ permalink raw reply related
* [net-next PATCH v2 04/29] fm10k: Add support for basic interaction with hardware
From: Alexander Duyck @ 2014-09-20 23:46 UTC (permalink / raw)
To: davem
Cc: nhorman, netdev, john.fastabend, matthew.vick, jeffrey.t.kirsher,
sassmann
In-Reply-To: <20140920234342.2977.21667.stgit@ahduyck-bv4.jf.intel.com>
This patch adds the basic read/write operations for accessing the hardware.
In addition to read read functionality the read functions also provide
surprise remove detection in the event that the device either loses power
or is removed.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
---
drivers/net/ethernet/intel/fm10k/fm10k.h | 9 ++++-
drivers/net/ethernet/intel/fm10k/fm10k_common.h | 44 +++++++++++++++++++++++
drivers/net/ethernet/intel/fm10k/fm10k_pci.c | 30 ++++++++++++++++
3 files changed, 82 insertions(+), 1 deletion(-)
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_common.h
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h
index 2e27bd9..3da3a99 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k.h
@@ -27,7 +27,14 @@
#include <linux/if_vlan.h>
#include <linux/pci.h>
-#include "fm10k_type.h"
+#include "fm10k_common.h"
+
+struct fm10k_intfc {
+ struct pci_dev *pdev;
+
+ struct fm10k_hw hw;
+ u32 __iomem *uc_addr;
+};
/* main */
extern char fm10k_driver_name[];
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_common.h b/drivers/net/ethernet/intel/fm10k/fm10k_common.h
new file mode 100644
index 0000000..2b214a6
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_common.h
@@ -0,0 +1,44 @@
+/* Intel Ethernet Switch Host Interface Driver
+ * Copyright(c) 2013 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
+
+#ifndef _FM10K_COMMON_H_
+#define _FM10K_COMMON_H_
+
+#include "fm10k_type.h"
+
+#define FM10K_REMOVED(hw_addr) unlikely(!(hw_addr))
+
+/* PCI configuration read */
+u16 fm10k_read_pci_cfg_word(struct fm10k_hw *hw, u32 reg);
+
+/* read operations, indexed using DWORDS */
+u32 fm10k_read_reg(struct fm10k_hw *hw, int reg);
+
+/* write operations, indexed using DWORDS */
+#define fm10k_write_reg(hw, reg, val) \
+do { \
+ u32 __iomem *hw_addr = ACCESS_ONCE((hw)->hw_addr); \
+ if (!FM10K_REMOVED(hw_addr)) \
+ writel((val), &hw_addr[(reg)]); \
+} while (0)
+
+/* read ctrl register which has no clear on read fields as PCIe flush */
+#define fm10k_write_flush(hw) fm10k_read_reg((hw), FM10K_CTRL)
+#endif /* _FM10K_COMMON_H_ */
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
index 12089ce..6d5e33c 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
@@ -38,6 +38,36 @@ static const struct pci_device_id fm10k_pci_tbl[] = {
};
MODULE_DEVICE_TABLE(pci, fm10k_pci_tbl);
+u16 fm10k_read_pci_cfg_word(struct fm10k_hw *hw, u32 reg)
+{
+ struct fm10k_intfc *interface = hw->back;
+ u16 value = 0;
+
+ if (FM10K_REMOVED(hw->hw_addr))
+ return ~value;
+
+ pci_read_config_word(interface->pdev, reg, &value);
+ if (value == 0xFFFF)
+ fm10k_write_flush(hw);
+
+ return value;
+}
+
+u32 fm10k_read_reg(struct fm10k_hw *hw, int reg)
+{
+ u32 __iomem *hw_addr = ACCESS_ONCE(hw->hw_addr);
+ u32 value = 0;
+
+ if (FM10K_REMOVED(hw_addr))
+ return ~value;
+
+ value = readl(&hw_addr[reg]);
+ if (!(~value) && (!reg || !(~readl(hw_addr))))
+ hw->hw_addr = NULL;
+
+ return value;
+}
+
/**
* fm10k_probe - Device Initialization Routine
* @pdev: PCI device information struct
^ permalink raw reply related
* [net-next PATCH v2 05/29] fm10k: Add support for mailbox
From: Alexander Duyck @ 2014-09-20 23:47 UTC (permalink / raw)
To: davem
Cc: nhorman, netdev, john.fastabend, matthew.vick, jeffrey.t.kirsher,
sassmann
In-Reply-To: <20140920234342.2977.21667.stgit@ahduyck-bv4.jf.intel.com>
This patch adds generic mailbox support. The general idea of the mailboxes
is to use a pair of ring buffers, one for request, one for response to send
data between the local driver and some remote entity be it the PF of the
Switch Manager.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
---
v2: Removed stray define for unused register
drivers/net/ethernet/intel/fm10k/fm10k_mbx.h | 240 +++++++++++++++++++
drivers/net/ethernet/intel/fm10k/fm10k_tlv.c | 320 +++++++++++++++++++++++++
drivers/net/ethernet/intel/fm10k/fm10k_tlv.h | 45 ++++
drivers/net/ethernet/intel/fm10k/fm10k_type.h | 3
4 files changed, 608 insertions(+)
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_mbx.h
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.h b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.h
new file mode 100644
index 0000000..cb7aa4a
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.h
@@ -0,0 +1,240 @@
+/* Intel Ethernet Switch Host Interface Driver
+ * Copyright(c) 2013 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
+
+#ifndef _FM10K_MBX_H_
+#define _FM10K_MBX_H_
+
+/* forward declaration */
+struct fm10k_mbx_info;
+
+#include "fm10k_type.h"
+#include "fm10k_tlv.h"
+
+/* PF Mailbox Registers */
+#define FM10K_MBMEM(_n) ((_n) + 0x18000)
+#define FM10K_MBMEM_VF(_n, _m) (((_n) * 0x10) + (_m) + 0x18000)
+#define FM10K_MBMEM_SM(_n) ((_n) + 0x18400)
+#define FM10K_MBMEM_PF(_n) ((_n) + 0x18600)
+/* XOR provides means of switching from Tx to Rx FIFO */
+#define FM10K_MBMEM_PF_XOR (FM10K_MBMEM_SM(0) ^ FM10K_MBMEM_PF(0))
+#define FM10K_MBX(_n) ((_n) + 0x18800)
+#define FM10K_MBX_REQ 0x00000002
+#define FM10K_MBX_ACK 0x00000004
+#define FM10K_MBX_REQ_INTERRUPT 0x00000008
+#define FM10K_MBX_ACK_INTERRUPT 0x00000010
+#define FM10K_MBX_INTERRUPT_ENABLE 0x00000020
+#define FM10K_MBX_INTERRUPT_DISABLE 0x00000040
+#define FM10K_MBICR(_n) ((_n) + 0x18840)
+#define FM10K_GMBX 0x18842
+
+/* VF Mailbox Registers */
+#define FM10K_VFMBX 0x00010
+#define FM10K_VFMBMEM(_n) ((_n) + 0x00020)
+#define FM10K_VFMBMEM_LEN 16
+#define FM10K_VFMBMEM_VF_XOR (FM10K_VFMBMEM_LEN / 2)
+
+/* Delays/timeouts */
+#define FM10K_MBX_DISCONNECT_TIMEOUT 500
+#define FM10K_MBX_POLL_DELAY 19
+#define FM10K_MBX_INT_DELAY 20
+
+/* PF/VF Mailbox state machine
+ *
+ * +----------+ connect() +----------+
+ * | CLOSED | --------------> | CONNECT |
+ * +----------+ +----------+
+ * ^ ^ |
+ * | rcv: rcv: | | rcv:
+ * | Connect Disconnect | | Connect
+ * | Disconnect Error | | Data
+ * | | |
+ * | | V
+ * +----------+ disconnect() +----------+
+ * |DISCONNECT| <-------------- | OPEN |
+ * +----------+ +----------+
+ *
+ * The diagram above describes the PF/VF mailbox state machine. There
+ * are four main states to this machine.
+ * Closed: This state represents a mailbox that is in a standby state
+ * with interrupts disabled. In this state the mailbox should not
+ * read the mailbox or write any data. The only means of exiting
+ * this state is for the system to make the connect() call for the
+ * mailbox, it will then transition to the connect state.
+ * Connect: In this state the mailbox is seeking a connection. It will
+ * post a connect message with no specified destination and will
+ * wait for a reply from the other side of the mailbox. This state
+ * is exited when either a connect with the local mailbox as the
+ * destination is received or when a data message is received with
+ * a valid sequence number.
+ * Open: In this state the mailbox is able to transfer data between the local
+ * entity and the remote. It will fall back to connect in the event of
+ * receiving either an error message, or a disconnect message. It will
+ * transition to disconnect on a call to disconnect();
+ * Disconnect: In this state the mailbox is attempting to gracefully terminate
+ * the connection. It will do so at the first point where it knows
+ * that the remote endpoint is either done sending, or when the
+ * remote endpoint has fallen back into connect.
+ */
+enum fm10k_mbx_state {
+ FM10K_STATE_CLOSED,
+ FM10K_STATE_CONNECT,
+ FM10K_STATE_OPEN,
+ FM10K_STATE_DISCONNECT,
+};
+
+/* macros for retriving and setting header values */
+#define FM10K_MSG_HDR_MASK(name) \
+ ((0x1u << FM10K_MSG_##name##_SIZE) - 1)
+#define FM10K_MSG_HDR_FIELD_SET(value, name) \
+ (((u32)(value) & FM10K_MSG_HDR_MASK(name)) << FM10K_MSG_##name##_SHIFT)
+#define FM10K_MSG_HDR_FIELD_GET(value, name) \
+ ((u16)((value) >> FM10K_MSG_##name##_SHIFT) & FM10K_MSG_HDR_MASK(name))
+
+/* HNI/SM Mailbox FIFO format
+ * 3 2 1 0
+ * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
+ * +-------+-----------------------+-------+-----------------------+
+ * | Error | Remote Head |Version| Local Tail |
+ * +-------+-----------------------+-------+-----------------------+
+ * | |
+ * . Local FIFO Data .
+ * . .
+ * +-------+-----------------------+-------+-----------------------+
+ *
+ * The layout above describes the format for the FIFOs used by the host
+ * network interface and the switch manager to communicate messages back
+ * and forth. Both the HNI and the switch maintain one such FIFO. The
+ * layout in memory has the switch manager FIFO followed immediately by
+ * the HNI FIFO. For this reason I am using just the pointer to the
+ * HNI FIFO in the mailbox ops as the offset between the two is fixed.
+ *
+ * The header for the FIFO is broken out into the following fields:
+ * Local Tail: Offset into FIFO region for next DWORD to write.
+ * Version: Version info for mailbox, only values of 0/1 are supported.
+ * Remote Head: Offset into remote FIFO to indicate how much we have read.
+ * Error: Error indication, values TBD.
+ */
+
+/* version number for switch manager mailboxes */
+#define FM10K_SM_MBX_VERSION 1
+#define FM10K_SM_MBX_FIFO_LEN (FM10K_MBMEM_PF_XOR - 1)
+
+/* offsets shared between all SM FIFO headers */
+#define FM10K_MSG_SM_TAIL_SHIFT 0
+#define FM10K_MSG_SM_TAIL_SIZE 12
+#define FM10K_MSG_SM_VER_SHIFT 12
+#define FM10K_MSG_SM_VER_SIZE 4
+#define FM10K_MSG_SM_HEAD_SHIFT 16
+#define FM10K_MSG_SM_HEAD_SIZE 12
+#define FM10K_MSG_SM_ERR_SHIFT 28
+#define FM10K_MSG_SM_ERR_SIZE 4
+
+/* All error messages returned by mailbox functions
+ * The value -511 is 0xFE01 in hex. The idea is to order the errors
+ * from 0xFE01 - 0xFEFF so error codes are easily visible in the mailbox
+ * messages. This also helps to avoid error number collisions as Linux
+ * doesn't appear to use error numbers 256 - 511.
+ */
+#define FM10K_MBX_ERR(_n) ((_n) - 512)
+#define FM10K_MBX_ERR_NO_MBX FM10K_MBX_ERR(0x01)
+#define FM10K_MBX_ERR_NO_SPACE FM10K_MBX_ERR(0x03)
+#define FM10K_MBX_ERR_TAIL FM10K_MBX_ERR(0x05)
+#define FM10K_MBX_ERR_HEAD FM10K_MBX_ERR(0x06)
+#define FM10K_MBX_ERR_SRC FM10K_MBX_ERR(0x08)
+#define FM10K_MBX_ERR_TYPE FM10K_MBX_ERR(0x09)
+#define FM10K_MBX_ERR_SIZE FM10K_MBX_ERR(0x0B)
+#define FM10K_MBX_ERR_BUSY FM10K_MBX_ERR(0x0C)
+#define FM10K_MBX_ERR_RSVD0 FM10K_MBX_ERR(0x0E)
+#define FM10K_MBX_ERR_CRC FM10K_MBX_ERR(0x0F)
+
+#define FM10K_MBX_CRC_SEED 0xFFFF
+
+struct fm10k_mbx_ops {
+ s32 (*connect)(struct fm10k_hw *, struct fm10k_mbx_info *);
+ void (*disconnect)(struct fm10k_hw *, struct fm10k_mbx_info *);
+ bool (*rx_ready)(struct fm10k_mbx_info *);
+ bool (*tx_ready)(struct fm10k_mbx_info *, u16);
+ bool (*tx_complete)(struct fm10k_mbx_info *);
+ s32 (*enqueue_tx)(struct fm10k_hw *, struct fm10k_mbx_info *,
+ const u32 *);
+ s32 (*process)(struct fm10k_hw *, struct fm10k_mbx_info *);
+ s32 (*register_handlers)(struct fm10k_mbx_info *,
+ const struct fm10k_msg_data *);
+};
+
+struct fm10k_mbx_fifo {
+ u32 *buffer;
+ u16 head;
+ u16 tail;
+ u16 size;
+};
+
+/* size of buffer to be stored in mailbox for FIFOs */
+#define FM10K_MBX_TX_BUFFER_SIZE 512
+#define FM10K_MBX_RX_BUFFER_SIZE 128
+#define FM10K_MBX_BUFFER_SIZE \
+ (FM10K_MBX_TX_BUFFER_SIZE + FM10K_MBX_RX_BUFFER_SIZE)
+
+/* minimum and maximum message size in dwords */
+#define FM10K_MBX_MSG_MAX_SIZE \
+ ((FM10K_MBX_TX_BUFFER_SIZE - 1) & (FM10K_MBX_RX_BUFFER_SIZE - 1))
+#define FM10K_VFMBX_MSG_MTU ((FM10K_VFMBMEM_LEN / 2) - 1)
+
+#define FM10K_MBX_INIT_TIMEOUT 2000 /* number of retries on mailbox */
+#define FM10K_MBX_INIT_DELAY 500 /* microseconds between retries */
+
+struct fm10k_mbx_info {
+ /* function pointers for mailbox operations */
+ struct fm10k_mbx_ops ops;
+ const struct fm10k_msg_data *msg_data;
+
+ /* message FIFOs */
+ struct fm10k_mbx_fifo rx;
+ struct fm10k_mbx_fifo tx;
+
+ /* delay for handling timeouts */
+ u32 timeout;
+ u32 udelay;
+
+ /* mailbox state info */
+ u32 mbx_reg, mbmem_reg, mbx_lock, mbx_hdr;
+ u16 max_size, mbmem_len;
+ u16 tail, tail_len, pulled;
+ u16 head, head_len, pushed;
+ u16 local, remote;
+ enum fm10k_mbx_state state;
+
+ /* result of last mailbox test */
+ s32 test_result;
+
+ /* statistics */
+ u64 tx_busy;
+ u64 tx_dropped;
+ u64 tx_messages;
+ u64 tx_dwords;
+ u64 rx_messages;
+ u64 rx_dwords;
+ u64 rx_parse_err;
+
+ /* Buffer to store messages */
+ u32 buffer[FM10K_MBX_BUFFER_SIZE];
+};
+
+#endif /* _FM10K_MBX_H_ */
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c
index f1fc709..fd0a05f 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c
@@ -541,3 +541,323 @@ s32 fm10k_tlv_attr_parse(u32 *attr, u32 **results,
return 0;
}
+
+/**
+ * fm10k_tlv_msg_parse - Parses message header and calls function handler
+ * @hw: Pointer to hardware structure
+ * @msg: Pointer to message
+ * @mbx: Pointer to mailbox information structure
+ * @func: Function array containing list of message handling functions
+ *
+ * This function should be the first function called upon receiving a
+ * message. The handler will identify the message type and call the correct
+ * handler for the given message. It will return the value from the function
+ * call on a recognized message type, otherwise it will return
+ * FM10K_NOT_IMPLEMENTED on an unrecognized type.
+ **/
+s32 fm10k_tlv_msg_parse(struct fm10k_hw *hw, u32 *msg,
+ struct fm10k_mbx_info *mbx,
+ const struct fm10k_msg_data *data)
+{
+ u32 *results[FM10K_TLV_RESULTS_MAX];
+ u32 msg_id;
+ s32 err;
+
+ /* verify pointer is not NULL */
+ if (!msg || !data)
+ return FM10K_ERR_PARAM;
+
+ /* verify this is a message and not an attribute */
+ if (!(*msg & (FM10K_TLV_FLAGS_MSG << FM10K_TLV_FLAGS_SHIFT)))
+ return FM10K_ERR_PARAM;
+
+ /* grab message ID */
+ msg_id = *msg & FM10K_TLV_ID_MASK;
+
+ while (data->id < msg_id)
+ data++;
+
+ /* if we didn't find it then pass it up as an error */
+ if (data->id != msg_id) {
+ while (data->id != FM10K_TLV_ERROR)
+ data++;
+ }
+
+ /* parse the attributes into the results list */
+ err = fm10k_tlv_attr_parse(msg, results, data->attr);
+ if (err < 0)
+ return err;
+
+ return data->func(hw, results, mbx);
+}
+
+/**
+ * fm10k_tlv_msg_error - Default handler for unrecognized TLV message IDs
+ * @hw: Pointer to hardware structure
+ * @results: Pointer array to message, results[0] is pointer to message
+ * @mbx: Unused mailbox pointer
+ *
+ * This function is a default handler for unrecognized messages. At a
+ * a minimum it just indicates that the message requested was
+ * unimplemented.
+ **/
+s32 fm10k_tlv_msg_error(struct fm10k_hw *hw, u32 **results,
+ struct fm10k_mbx_info *mbx)
+{
+ return FM10K_NOT_IMPLEMENTED;
+}
+
+static const unsigned char test_str[] = "fm10k";
+static const unsigned char test_mac[ETH_ALEN] = { 0x12, 0x34, 0x56,
+ 0x78, 0x9a, 0xbc };
+static const u16 test_vlan = 0x0FED;
+static const u64 test_u64 = 0xfedcba9876543210ull;
+static const u32 test_u32 = 0x87654321;
+static const u16 test_u16 = 0x8765;
+static const u8 test_u8 = 0x87;
+static const s64 test_s64 = -0x123456789abcdef0ll;
+static const s32 test_s32 = -0x1235678;
+static const s16 test_s16 = -0x1234;
+static const s8 test_s8 = -0x12;
+static const __le32 test_le[2] = { cpu_to_le32(0x12345678),
+ cpu_to_le32(0x9abcdef0)};
+
+/* The message below is meant to be used as a test message to demonstrate
+ * how to use the TLV interface and to test the types. Normally this code
+ * be compiled out by stripping the code wrapped in FM10K_TLV_TEST_MSG
+ */
+const struct fm10k_tlv_attr fm10k_tlv_msg_test_attr[] = {
+ FM10K_TLV_ATTR_NULL_STRING(FM10K_TEST_MSG_STRING, 80),
+ FM10K_TLV_ATTR_MAC_ADDR(FM10K_TEST_MSG_MAC_ADDR),
+ FM10K_TLV_ATTR_U8(FM10K_TEST_MSG_U8),
+ FM10K_TLV_ATTR_U16(FM10K_TEST_MSG_U16),
+ FM10K_TLV_ATTR_U32(FM10K_TEST_MSG_U32),
+ FM10K_TLV_ATTR_U64(FM10K_TEST_MSG_U64),
+ FM10K_TLV_ATTR_S8(FM10K_TEST_MSG_S8),
+ FM10K_TLV_ATTR_S16(FM10K_TEST_MSG_S16),
+ FM10K_TLV_ATTR_S32(FM10K_TEST_MSG_S32),
+ FM10K_TLV_ATTR_S64(FM10K_TEST_MSG_S64),
+ FM10K_TLV_ATTR_LE_STRUCT(FM10K_TEST_MSG_LE_STRUCT, 8),
+ FM10K_TLV_ATTR_NESTED(FM10K_TEST_MSG_NESTED),
+ FM10K_TLV_ATTR_S32(FM10K_TEST_MSG_RESULT),
+ FM10K_TLV_ATTR_LAST
+};
+
+/**
+ * fm10k_tlv_msg_test_generate_data - Stuff message with data
+ * @msg: Pointer to message
+ * @attr_flags: List of flags indicating what attributes to add
+ *
+ * This function is meant to load a message buffer with attribute data
+ **/
+static void fm10k_tlv_msg_test_generate_data(u32 *msg, u32 attr_flags)
+{
+ if (attr_flags & (1 << FM10K_TEST_MSG_STRING))
+ fm10k_tlv_attr_put_null_string(msg, FM10K_TEST_MSG_STRING,
+ test_str);
+ if (attr_flags & (1 << FM10K_TEST_MSG_MAC_ADDR))
+ fm10k_tlv_attr_put_mac_vlan(msg, FM10K_TEST_MSG_MAC_ADDR,
+ test_mac, test_vlan);
+ if (attr_flags & (1 << FM10K_TEST_MSG_U8))
+ fm10k_tlv_attr_put_u8(msg, FM10K_TEST_MSG_U8, test_u8);
+ if (attr_flags & (1 << FM10K_TEST_MSG_U16))
+ fm10k_tlv_attr_put_u16(msg, FM10K_TEST_MSG_U16, test_u16);
+ if (attr_flags & (1 << FM10K_TEST_MSG_U32))
+ fm10k_tlv_attr_put_u32(msg, FM10K_TEST_MSG_U32, test_u32);
+ if (attr_flags & (1 << FM10K_TEST_MSG_U64))
+ fm10k_tlv_attr_put_u64(msg, FM10K_TEST_MSG_U64, test_u64);
+ if (attr_flags & (1 << FM10K_TEST_MSG_S8))
+ fm10k_tlv_attr_put_s8(msg, FM10K_TEST_MSG_S8, test_s8);
+ if (attr_flags & (1 << FM10K_TEST_MSG_S16))
+ fm10k_tlv_attr_put_s16(msg, FM10K_TEST_MSG_S16, test_s16);
+ if (attr_flags & (1 << FM10K_TEST_MSG_S32))
+ fm10k_tlv_attr_put_s32(msg, FM10K_TEST_MSG_S32, test_s32);
+ if (attr_flags & (1 << FM10K_TEST_MSG_S64))
+ fm10k_tlv_attr_put_s64(msg, FM10K_TEST_MSG_S64, test_s64);
+ if (attr_flags & (1 << FM10K_TEST_MSG_LE_STRUCT))
+ fm10k_tlv_attr_put_le_struct(msg, FM10K_TEST_MSG_LE_STRUCT,
+ test_le, 8);
+}
+
+/**
+ * fm10k_tlv_msg_test_create - Create a test message testing all attributes
+ * @msg: Pointer to message
+ * @attr_flags: List of flags indicating what attributes to add
+ *
+ * This function is meant to load a message buffer with all attribute types
+ * including a nested attribute.
+ **/
+void fm10k_tlv_msg_test_create(u32 *msg, u32 attr_flags)
+{
+ u32 *nest = NULL;
+
+ fm10k_tlv_msg_init(msg, FM10K_TLV_MSG_ID_TEST);
+
+ fm10k_tlv_msg_test_generate_data(msg, attr_flags);
+
+ /* check for nested attributes */
+ attr_flags >>= FM10K_TEST_MSG_NESTED;
+
+ if (attr_flags) {
+ nest = fm10k_tlv_attr_nest_start(msg, FM10K_TEST_MSG_NESTED);
+
+ fm10k_tlv_msg_test_generate_data(nest, attr_flags);
+
+ fm10k_tlv_attr_nest_stop(msg);
+ }
+}
+
+/**
+ * fm10k_tlv_msg_test - Validate all results on test message receive
+ * @hw: Pointer to hardware structure
+ * @results: Pointer array to attributes in the mesage
+ * @mbx: Pointer to mailbox information structure
+ *
+ * This function does a check to verify all attributes match what the test
+ * message placed in the message buffer. It is the default handler
+ * for TLV test messages.
+ **/
+s32 fm10k_tlv_msg_test(struct fm10k_hw *hw, u32 **results,
+ struct fm10k_mbx_info *mbx)
+{
+ u32 *nest_results[FM10K_TLV_RESULTS_MAX];
+ unsigned char result_str[80];
+ unsigned char result_mac[ETH_ALEN];
+ s32 err = 0;
+ __le32 result_le[2];
+ u16 result_vlan;
+ u64 result_u64;
+ u32 result_u32;
+ u16 result_u16;
+ u8 result_u8;
+ s64 result_s64;
+ s32 result_s32;
+ s16 result_s16;
+ s8 result_s8;
+ u32 reply[3];
+
+ /* retrieve results of a previous test */
+ if (!!results[FM10K_TEST_MSG_RESULT])
+ return fm10k_tlv_attr_get_s32(results[FM10K_TEST_MSG_RESULT],
+ &mbx->test_result);
+
+parse_nested:
+ if (!!results[FM10K_TEST_MSG_STRING]) {
+ err = fm10k_tlv_attr_get_null_string(
+ results[FM10K_TEST_MSG_STRING],
+ result_str);
+ if (!err && memcmp(test_str, result_str, sizeof(test_str)))
+ err = FM10K_ERR_INVALID_VALUE;
+ if (err)
+ goto report_result;
+ }
+ if (!!results[FM10K_TEST_MSG_MAC_ADDR]) {
+ err = fm10k_tlv_attr_get_mac_vlan(
+ results[FM10K_TEST_MSG_MAC_ADDR],
+ result_mac, &result_vlan);
+ if (!err && memcmp(test_mac, result_mac, ETH_ALEN))
+ err = FM10K_ERR_INVALID_VALUE;
+ if (!err && test_vlan != result_vlan)
+ err = FM10K_ERR_INVALID_VALUE;
+ if (err)
+ goto report_result;
+ }
+ if (!!results[FM10K_TEST_MSG_U8]) {
+ err = fm10k_tlv_attr_get_u8(results[FM10K_TEST_MSG_U8],
+ &result_u8);
+ if (!err && test_u8 != result_u8)
+ err = FM10K_ERR_INVALID_VALUE;
+ if (err)
+ goto report_result;
+ }
+ if (!!results[FM10K_TEST_MSG_U16]) {
+ err = fm10k_tlv_attr_get_u16(results[FM10K_TEST_MSG_U16],
+ &result_u16);
+ if (!err && test_u16 != result_u16)
+ err = FM10K_ERR_INVALID_VALUE;
+ if (err)
+ goto report_result;
+ }
+ if (!!results[FM10K_TEST_MSG_U32]) {
+ err = fm10k_tlv_attr_get_u32(results[FM10K_TEST_MSG_U32],
+ &result_u32);
+ if (!err && test_u32 != result_u32)
+ err = FM10K_ERR_INVALID_VALUE;
+ if (err)
+ goto report_result;
+ }
+ if (!!results[FM10K_TEST_MSG_U64]) {
+ err = fm10k_tlv_attr_get_u64(results[FM10K_TEST_MSG_U64],
+ &result_u64);
+ if (!err && test_u64 != result_u64)
+ err = FM10K_ERR_INVALID_VALUE;
+ if (err)
+ goto report_result;
+ }
+ if (!!results[FM10K_TEST_MSG_S8]) {
+ err = fm10k_tlv_attr_get_s8(results[FM10K_TEST_MSG_S8],
+ &result_s8);
+ if (!err && test_s8 != result_s8)
+ err = FM10K_ERR_INVALID_VALUE;
+ if (err)
+ goto report_result;
+ }
+ if (!!results[FM10K_TEST_MSG_S16]) {
+ err = fm10k_tlv_attr_get_s16(results[FM10K_TEST_MSG_S16],
+ &result_s16);
+ if (!err && test_s16 != result_s16)
+ err = FM10K_ERR_INVALID_VALUE;
+ if (err)
+ goto report_result;
+ }
+ if (!!results[FM10K_TEST_MSG_S32]) {
+ err = fm10k_tlv_attr_get_s32(results[FM10K_TEST_MSG_S32],
+ &result_s32);
+ if (!err && test_s32 != result_s32)
+ err = FM10K_ERR_INVALID_VALUE;
+ if (err)
+ goto report_result;
+ }
+ if (!!results[FM10K_TEST_MSG_S64]) {
+ err = fm10k_tlv_attr_get_s64(results[FM10K_TEST_MSG_S64],
+ &result_s64);
+ if (!err && test_s64 != result_s64)
+ err = FM10K_ERR_INVALID_VALUE;
+ if (err)
+ goto report_result;
+ }
+ if (!!results[FM10K_TEST_MSG_LE_STRUCT]) {
+ err = fm10k_tlv_attr_get_le_struct(
+ results[FM10K_TEST_MSG_LE_STRUCT],
+ result_le,
+ sizeof(result_le));
+ if (!err && memcmp(test_le, result_le, sizeof(test_le)))
+ err = FM10K_ERR_INVALID_VALUE;
+ if (err)
+ goto report_result;
+ }
+
+ if (!!results[FM10K_TEST_MSG_NESTED]) {
+ /* clear any pointers */
+ memset(nest_results, 0, sizeof(nest_results));
+
+ /* parse the nested attributes into the nest results list */
+ err = fm10k_tlv_attr_parse(results[FM10K_TEST_MSG_NESTED],
+ nest_results,
+ fm10k_tlv_msg_test_attr);
+ if (err)
+ goto report_result;
+
+ /* loop back through to the start */
+ results = nest_results;
+ goto parse_nested;
+ }
+
+report_result:
+ /* generate reply with test result */
+ fm10k_tlv_msg_init(reply, FM10K_TLV_MSG_ID_TEST);
+ fm10k_tlv_attr_put_s32(reply, FM10K_TEST_MSG_RESULT, err);
+
+ /* load onto outgoing mailbox */
+ return mbx->ops.enqueue_tx(hw, mbx, reply);
+}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.h b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.h
index 6d22db6..7e045e8 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.h
@@ -21,6 +21,9 @@
#ifndef _FM10K_TLV_H_
#define _FM10K_TLV_H_
+/* forward declaration */
+struct fm10k_msg_data;
+
#include "fm10k_type.h"
/* Message / Argument header format
@@ -93,6 +96,15 @@ struct fm10k_tlv_attr {
#define FM10K_TLV_ATTR_NESTED(id) { id, FM10K_TLV_NESTED }
#define FM10K_TLV_ATTR_LAST { FM10K_TLV_ERROR }
+struct fm10k_msg_data {
+ unsigned int id;
+ const struct fm10k_tlv_attr *attr;
+ s32 (*func)(struct fm10k_hw *, u32 **,
+ struct fm10k_mbx_info *);
+};
+
+#define FM10K_MSG_HANDLER(id, attr, func) { id, attr, func }
+
s32 fm10k_tlv_msg_init(u32 *, u16);
s32 fm10k_tlv_attr_put_null_string(u32 *, u16, const unsigned char *);
s32 fm10k_tlv_attr_get_null_string(u32 *, unsigned char *);
@@ -138,4 +150,37 @@ s32 fm10k_tlv_attr_get_le_struct(u32 *, void *, u32);
u32 *fm10k_tlv_attr_nest_start(u32 *, u16);
s32 fm10k_tlv_attr_nest_stop(u32 *);
s32 fm10k_tlv_attr_parse(u32 *, u32 **, const struct fm10k_tlv_attr *);
+s32 fm10k_tlv_msg_parse(struct fm10k_hw *, u32 *, struct fm10k_mbx_info *,
+ const struct fm10k_msg_data *);
+s32 fm10k_tlv_msg_error(struct fm10k_hw *hw, u32 **results,
+ struct fm10k_mbx_info *);
+
+#define FM10K_TLV_MSG_ID_TEST 0
+
+enum fm10k_tlv_test_attr_id {
+ FM10K_TEST_MSG_UNSET,
+ FM10K_TEST_MSG_STRING,
+ FM10K_TEST_MSG_MAC_ADDR,
+ FM10K_TEST_MSG_U8,
+ FM10K_TEST_MSG_U16,
+ FM10K_TEST_MSG_U32,
+ FM10K_TEST_MSG_U64,
+ FM10K_TEST_MSG_S8,
+ FM10K_TEST_MSG_S16,
+ FM10K_TEST_MSG_S32,
+ FM10K_TEST_MSG_S64,
+ FM10K_TEST_MSG_LE_STRUCT,
+ FM10K_TEST_MSG_NESTED,
+ FM10K_TEST_MSG_RESULT,
+ FM10K_TEST_MSG_MAX
+};
+
+extern const struct fm10k_tlv_attr fm10k_tlv_msg_test_attr[];
+void fm10k_tlv_msg_test_create(u32 *, u32);
+s32 fm10k_tlv_msg_test(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *);
+
+#define FM10K_TLV_MSG_TEST_HANDLER(func) \
+ FM10K_MSG_HANDLER(FM10K_TLV_MSG_ID_TEST, fm10k_tlv_msg_test_attr, func)
+#define FM10K_TLV_MSG_ERROR_HANDLER(func) \
+ FM10K_MSG_HANDLER(FM10K_TLV_ERROR, NULL, func)
#endif /* _FM10K_MSG_H_ */
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_type.h b/drivers/net/ethernet/intel/fm10k/fm10k_type.h
index 1606805..eda0c7c 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_type.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_type.h
@@ -28,6 +28,8 @@ struct fm10k_hw;
#include <asm/byteorder.h>
#include <linux/etherdevice.h>
+#include "fm10k_mbx.h"
+
#define FM10K_DEV_ID_PF 0x15A4
#define FM10K_DEV_ID_VF 0x15A5
@@ -573,6 +575,7 @@ struct fm10k_hw {
struct fm10k_mac_info mac;
struct fm10k_bus_info bus;
struct fm10k_bus_info bus_caps;
+ struct fm10k_mbx_info mbx;
struct fm10k_swapi_info swapi;
u16 device_id;
u16 vendor_id;
^ permalink raw reply related
* [net-next PATCH v2 06/29] fm10k: Implement PF <-> SM mailbox operations
From: Alexander Duyck @ 2014-09-20 23:47 UTC (permalink / raw)
To: davem
Cc: nhorman, netdev, john.fastabend, matthew.vick, jeffrey.t.kirsher,
sassmann
In-Reply-To: <20140920234342.2977.21667.stgit@ahduyck-bv4.jf.intel.com>
This patch adds support for the mailbox that connects the PF to the Switch
Management entity. This mailbox will pass TLV formatted messages between
the two entities by using a pair of shared ring buffers.
The primary use of the mailbox is to configure L2 forwarding addresses,
VLANs, and general resource allocation from the switch.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
---
v2: Stray define removal moved to previous patch so it was never added
drivers/net/ethernet/intel/fm10k/Makefile | 2
drivers/net/ethernet/intel/fm10k/fm10k_mbx.c | 1351 ++++++++++++++++++++++++++
drivers/net/ethernet/intel/fm10k/fm10k_mbx.h | 3
3 files changed, 1355 insertions(+), 1 deletion(-)
create mode 100644 drivers/net/ethernet/intel/fm10k/fm10k_mbx.c
diff --git a/drivers/net/ethernet/intel/fm10k/Makefile b/drivers/net/ethernet/intel/fm10k/Makefile
index 1052808..6642611 100644
--- a/drivers/net/ethernet/intel/fm10k/Makefile
+++ b/drivers/net/ethernet/intel/fm10k/Makefile
@@ -28,4 +28,4 @@
obj-$(CONFIG_FM10K) += fm10k.o
fm10k-objs := fm10k_main.o fm10k_pci.o \
- fm10k_tlv.o
+ fm10k_mbx.o fm10k_tlv.o
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c
new file mode 100644
index 0000000..2609847
--- /dev/null
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c
@@ -0,0 +1,1351 @@
+/* Intel Ethernet Switch Host Interface Driver
+ * Copyright(c) 2013 - 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
+
+#include "fm10k_common.h"
+
+/**
+ * fm10k_fifo_init - Initialize a message FIFO
+ * @fifo: pointer to FIFO
+ * @buffer: pointer to memory to be used to store FIFO
+ * @size: maximum message size to store in FIFO, must be 2^n - 1
+ **/
+static void fm10k_fifo_init(struct fm10k_mbx_fifo *fifo, u32 *buffer, u16 size)
+{
+ fifo->buffer = buffer;
+ fifo->size = size;
+ fifo->head = 0;
+ fifo->tail = 0;
+}
+
+/**
+ * fm10k_fifo_used - Retrieve used space in FIFO
+ * @fifo: pointer to FIFO
+ *
+ * This function returns the number of DWORDs used in the FIFO
+ **/
+static u16 fm10k_fifo_used(struct fm10k_mbx_fifo *fifo)
+{
+ return fifo->tail - fifo->head;
+}
+
+/**
+ * fm10k_fifo_unused - Retrieve unused space in FIFO
+ * @fifo: pointer to FIFO
+ *
+ * This function returns the number of unused DWORDs in the FIFO
+ **/
+static u16 fm10k_fifo_unused(struct fm10k_mbx_fifo *fifo)
+{
+ return fifo->size + fifo->head - fifo->tail;
+}
+
+/**
+ * fm10k_fifo_empty - Test to verify if fifo is empty
+ * @fifo: pointer to FIFO
+ *
+ * This function returns true if the FIFO is empty, else false
+ **/
+static bool fm10k_fifo_empty(struct fm10k_mbx_fifo *fifo)
+{
+ return fifo->head == fifo->tail;
+}
+
+/**
+ * fm10k_fifo_head_offset - returns indices of head with given offset
+ * @fifo: pointer to FIFO
+ * @offset: offset to add to head
+ *
+ * This function returns the indicies into the fifo based on head + offset
+ **/
+static u16 fm10k_fifo_head_offset(struct fm10k_mbx_fifo *fifo, u16 offset)
+{
+ return (fifo->head + offset) & (fifo->size - 1);
+}
+
+/**
+ * fm10k_fifo_tail_offset - returns indices of tail with given offset
+ * @fifo: pointer to FIFO
+ * @offset: offset to add to tail
+ *
+ * This function returns the indicies into the fifo based on tail + offset
+ **/
+static u16 fm10k_fifo_tail_offset(struct fm10k_mbx_fifo *fifo, u16 offset)
+{
+ return (fifo->tail + offset) & (fifo->size - 1);
+}
+
+/**
+ * fm10k_fifo_head_len - Retrieve length of first message in FIFO
+ * @fifo: pointer to FIFO
+ *
+ * This function returns the size of the first message in the FIFO
+ **/
+static u16 fm10k_fifo_head_len(struct fm10k_mbx_fifo *fifo)
+{
+ u32 *head = fifo->buffer + fm10k_fifo_head_offset(fifo, 0);
+
+ /* verify there is at least 1 DWORD in the fifo so *head is valid */
+ if (fm10k_fifo_empty(fifo))
+ return 0;
+
+ /* retieve the message length */
+ return FM10K_TLV_DWORD_LEN(*head);
+}
+
+/**
+ * fm10k_fifo_head_drop - Drop the first message in FIFO
+ * @fifo: pointer to FIFO
+ *
+ * This function returns the size of the message dropped from the FIFO
+ **/
+static u16 fm10k_fifo_head_drop(struct fm10k_mbx_fifo *fifo)
+{
+ u16 len = fm10k_fifo_head_len(fifo);
+
+ /* update head so it is at the start of next frame */
+ fifo->head += len;
+
+ return len;
+}
+
+/**
+ * fm10k_mbx_index_len - Convert a head/tail index into a length value
+ * @mbx: pointer to mailbox
+ * @head: head index
+ * @tail: head index
+ *
+ * This function takes the head and tail index and determines the length
+ * of the data indicated by this pair.
+ **/
+static u16 fm10k_mbx_index_len(struct fm10k_mbx_info *mbx, u16 head, u16 tail)
+{
+ u16 len = tail - head;
+
+ /* we wrapped so subtract 2, one for index 0, one for all 1s index */
+ if (len > tail)
+ len -= 2;
+
+ return len & ((mbx->mbmem_len << 1) - 1);
+}
+
+/**
+ * fm10k_mbx_tail_add - Determine new tail value with added offset
+ * @mbx: pointer to mailbox
+ * @offset: length to add to head offset
+ *
+ * This function takes the local tail index and recomputes it for
+ * a given length added as an offset.
+ **/
+static u16 fm10k_mbx_tail_add(struct fm10k_mbx_info *mbx, u16 offset)
+{
+ u16 tail = (mbx->tail + offset + 1) & ((mbx->mbmem_len << 1) - 1);
+
+ /* add/sub 1 because we cannot have offset 0 or all 1s */
+ return (tail > mbx->tail) ? --tail : ++tail;
+}
+
+/**
+ * fm10k_mbx_tail_sub - Determine new tail value with subtracted offset
+ * @mbx: pointer to mailbox
+ * @offset: length to add to head offset
+ *
+ * This function takes the local tail index and recomputes it for
+ * a given length added as an offset.
+ **/
+static u16 fm10k_mbx_tail_sub(struct fm10k_mbx_info *mbx, u16 offset)
+{
+ u16 tail = (mbx->tail - offset - 1) & ((mbx->mbmem_len << 1) - 1);
+
+ /* sub/add 1 because we cannot have offset 0 or all 1s */
+ return (tail < mbx->tail) ? ++tail : --tail;
+}
+
+/**
+ * fm10k_mbx_head_add - Determine new head value with added offset
+ * @mbx: pointer to mailbox
+ * @offset: length to add to head offset
+ *
+ * This function takes the local head index and recomputes it for
+ * a given length added as an offset.
+ **/
+static u16 fm10k_mbx_head_add(struct fm10k_mbx_info *mbx, u16 offset)
+{
+ u16 head = (mbx->head + offset + 1) & ((mbx->mbmem_len << 1) - 1);
+
+ /* add/sub 1 because we cannot have offset 0 or all 1s */
+ return (head > mbx->head) ? --head : ++head;
+}
+
+/**
+ * fm10k_mbx_head_sub - Determine new head value with subtracted offset
+ * @mbx: pointer to mailbox
+ * @offset: length to add to head offset
+ *
+ * This function takes the local head index and recomputes it for
+ * a given length added as an offset.
+ **/
+static u16 fm10k_mbx_head_sub(struct fm10k_mbx_info *mbx, u16 offset)
+{
+ u16 head = (mbx->head - offset - 1) & ((mbx->mbmem_len << 1) - 1);
+
+ /* sub/add 1 because we cannot have offset 0 or all 1s */
+ return (head < mbx->head) ? ++head : --head;
+}
+
+/**
+ * fm10k_mbx_pushed_tail_len - Retrieve the length of message being pushed
+ * @mbx: pointer to mailbox
+ *
+ * This function will return the length of the message currently being
+ * pushed onto the tail of the Rx queue.
+ **/
+static u16 fm10k_mbx_pushed_tail_len(struct fm10k_mbx_info *mbx)
+{
+ u32 *tail = mbx->rx.buffer + fm10k_fifo_tail_offset(&mbx->rx, 0);
+
+ /* pushed tail is only valid if pushed is set */
+ if (!mbx->pushed)
+ return 0;
+
+ return FM10K_TLV_DWORD_LEN(*tail);
+}
+
+/**
+ * fm10k_fifo_write_copy - pulls data off of msg and places it in fifo
+ * @fifo: pointer to FIFO
+ * @msg: message array to populate
+ * @tail_offset: additional offset to add to tail pointer
+ * @len: length of FIFO to copy into message header
+ *
+ * This function will take a message and copy it into a section of the
+ * FIFO. In order to get something into a location other than just
+ * the tail you can use tail_offset to adjust the pointer.
+ **/
+static void fm10k_fifo_write_copy(struct fm10k_mbx_fifo *fifo,
+ const u32 *msg, u16 tail_offset, u16 len)
+{
+ u16 end = fm10k_fifo_tail_offset(fifo, tail_offset);
+ u32 *tail = fifo->buffer + end;
+
+ /* track when we should cross the end of the FIFO */
+ end = fifo->size - end;
+
+ /* copy end of message before start of message */
+ if (end < len)
+ memcpy(fifo->buffer, msg + end, (len - end) << 2);
+ else
+ end = len;
+
+ /* Copy remaining message into Tx FIFO */
+ memcpy(tail, msg, end << 2);
+}
+
+/**
+ * fm10k_fifo_enqueue - Enqueues the message to the tail of the FIFO
+ * @fifo: pointer to FIFO
+ * @msg: message array to read
+ *
+ * This function enqueues a message up to the size specified by the length
+ * contained in the first DWORD of the message and will place at the tail
+ * of the FIFO. It will return 0 on success, or a negative value on error.
+ **/
+static s32 fm10k_fifo_enqueue(struct fm10k_mbx_fifo *fifo, const u32 *msg)
+{
+ u16 len = FM10K_TLV_DWORD_LEN(*msg);
+
+ /* verify parameters */
+ if (len > fifo->size)
+ return FM10K_MBX_ERR_SIZE;
+
+ /* verify there is room for the message */
+ if (len > fm10k_fifo_unused(fifo))
+ return FM10K_MBX_ERR_NO_SPACE;
+
+ /* Copy message into FIFO */
+ fm10k_fifo_write_copy(fifo, msg, 0, len);
+
+ /* memory barrier to guarantee FIFO is written before tail update */
+ wmb();
+
+ /* Update Tx FIFO tail */
+ fifo->tail += len;
+
+ return 0;
+}
+
+/**
+ * fm10k_mbx_validate_msg_size - Validate incoming message based on size
+ * @mbx: pointer to mailbox
+ * @len: length of data pushed onto buffer
+ *
+ * This function analyzes the frame and will return a non-zero value when
+ * the start of a message larger than the mailbox is detected.
+ **/
+static u16 fm10k_mbx_validate_msg_size(struct fm10k_mbx_info *mbx, u16 len)
+{
+ struct fm10k_mbx_fifo *fifo = &mbx->rx;
+ u16 total_len = 0, msg_len;
+ u32 *msg;
+
+ /* length should include previous amounts pushed */
+ len += mbx->pushed;
+
+ /* offset in message is based off of current message size */
+ do {
+ msg = fifo->buffer + fm10k_fifo_tail_offset(fifo, total_len);
+ msg_len = FM10K_TLV_DWORD_LEN(*msg);
+ total_len += msg_len;
+ } while (total_len < len);
+
+ /* message extends out of pushed section, but fits in FIFO */
+ if ((len < total_len) && (msg_len <= mbx->rx.size))
+ return 0;
+
+ /* return length of invalid section */
+ return (len < total_len) ? len : (len - total_len);
+}
+
+/**
+ * fm10k_mbx_write_copy - pulls data off of Tx FIFO and places it in mbmem
+ * @mbx: pointer to mailbox
+ *
+ * This function will take a seciton of the Rx FIFO and copy it into the
+ mbx->tail--;
+ * mailbox memory. The offset in mbmem is based on the lower bits of the
+ * tail and len determines the length to copy.
+ **/
+static void fm10k_mbx_write_copy(struct fm10k_hw *hw,
+ struct fm10k_mbx_info *mbx)
+{
+ struct fm10k_mbx_fifo *fifo = &mbx->tx;
+ u32 mbmem = mbx->mbmem_reg;
+ u32 *head = fifo->buffer;
+ u16 end, len, tail, mask;
+
+ if (!mbx->tail_len)
+ return;
+
+ /* determine data length and mbmem tail index */
+ mask = mbx->mbmem_len - 1;
+ len = mbx->tail_len;
+ tail = fm10k_mbx_tail_sub(mbx, len);
+ if (tail > mask)
+ tail++;
+
+ /* determine offset in the ring */
+ end = fm10k_fifo_head_offset(fifo, mbx->pulled);
+ head += end;
+
+ /* memory barrier to guarantee data is ready to be read */
+ rmb();
+
+ /* Copy message from Tx FIFO */
+ for (end = fifo->size - end; len; head = fifo->buffer) {
+ do {
+ /* adjust tail to match offset for FIFO */
+ tail &= mask;
+ if (!tail)
+ tail++;
+
+ /* write message to hardware FIFO */
+ fm10k_write_reg(hw, mbmem + tail++, *(head++));
+ } while (--len && --end);
+ }
+}
+
+/**
+ * fm10k_mbx_pull_head - Pulls data off of head of Tx FIFO
+ * @hw: pointer to hardware structure
+ * @mbx: pointer to mailbox
+ * @head: acknowledgement number last received
+ *
+ * This function will push the tail index forward based on the remote
+ * head index. It will then pull up to mbmem_len DWORDs off of the
+ * head of the FIFO and will place it in the MBMEM registers
+ * associated with the mailbox.
+ **/
+static void fm10k_mbx_pull_head(struct fm10k_hw *hw,
+ struct fm10k_mbx_info *mbx, u16 head)
+{
+ u16 mbmem_len, len, ack = fm10k_mbx_index_len(mbx, head, mbx->tail);
+ struct fm10k_mbx_fifo *fifo = &mbx->tx;
+
+ /* update number of bytes pulled and update bytes in transit */
+ mbx->pulled += mbx->tail_len - ack;
+
+ /* determine length of data to pull, reserve space for mbmem header */
+ mbmem_len = mbx->mbmem_len - 1;
+ len = fm10k_fifo_used(fifo) - mbx->pulled;
+ if (len > mbmem_len)
+ len = mbmem_len;
+
+ /* update tail and record number of bytes in transit */
+ mbx->tail = fm10k_mbx_tail_add(mbx, len - ack);
+ mbx->tail_len = len;
+
+ /* drop pulled messages from the FIFO */
+ for (len = fm10k_fifo_head_len(fifo);
+ len && (mbx->pulled >= len);
+ len = fm10k_fifo_head_len(fifo)) {
+ mbx->pulled -= fm10k_fifo_head_drop(fifo);
+ mbx->tx_messages++;
+ mbx->tx_dwords += len;
+ }
+
+ /* Copy message out from the Tx FIFO */
+ fm10k_mbx_write_copy(hw, mbx);
+}
+
+/**
+ * fm10k_mbx_read_copy - pulls data off of mbmem and places it in Rx FIFO
+ * @hw: pointer to hardware structure
+ * @mbx: pointer to mailbox
+ *
+ * This function will take a seciton of the mailbox memory and copy it
+ * into the Rx FIFO. The offset is based on the lower bits of the
+ * head and len determines the length to copy.
+ **/
+static void fm10k_mbx_read_copy(struct fm10k_hw *hw,
+ struct fm10k_mbx_info *mbx)
+{
+ struct fm10k_mbx_fifo *fifo = &mbx->rx;
+ u32 mbmem = mbx->mbmem_reg ^ mbx->mbmem_len;
+ u32 *tail = fifo->buffer;
+ u16 end, len, head;
+
+ /* determine data length and mbmem head index */
+ len = mbx->head_len;
+ head = fm10k_mbx_head_sub(mbx, len);
+ if (head >= mbx->mbmem_len)
+ head++;
+
+ /* determine offset in the ring */
+ end = fm10k_fifo_tail_offset(fifo, mbx->pushed);
+ tail += end;
+
+ /* Copy message into Rx FIFO */
+ for (end = fifo->size - end; len; tail = fifo->buffer) {
+ do {
+ /* adjust head to match offset for FIFO */
+ head &= mbx->mbmem_len - 1;
+ if (!head)
+ head++;
+
+ /* read message from hardware FIFO */
+ *(tail++) = fm10k_read_reg(hw, mbmem + head++);
+ } while (--len && --end);
+ }
+
+ /* memory barrier to guarantee FIFO is written before tail update */
+ wmb();
+}
+
+/**
+ * fm10k_mbx_push_tail - Pushes up to 15 DWORDs on to tail of FIFO
+ * @hw: pointer to hardware structure
+ * @mbx: pointer to mailbox
+ * @tail: tail index of message
+ *
+ * This function will first validate the tail index and size for the
+ * incoming message. It then updates the acknowlegment number and
+ * copies the data into the FIFO. It will return the number of messages
+ * dequeued on success and a negative value on error.
+ **/
+static s32 fm10k_mbx_push_tail(struct fm10k_hw *hw,
+ struct fm10k_mbx_info *mbx,
+ u16 tail)
+{
+ struct fm10k_mbx_fifo *fifo = &mbx->rx;
+ u16 len, seq = fm10k_mbx_index_len(mbx, mbx->head, tail);
+
+ /* determine length of data to push */
+ len = fm10k_fifo_unused(fifo) - mbx->pushed;
+ if (len > seq)
+ len = seq;
+
+ /* update head and record bytes received */
+ mbx->head = fm10k_mbx_head_add(mbx, len);
+ mbx->head_len = len;
+
+ /* nothing to do if there is no data */
+ if (!len)
+ return 0;
+
+ /* Copy msg into Rx FIFO */
+ fm10k_mbx_read_copy(hw, mbx);
+
+ /* determine if there are any invalid lengths in message */
+ if (fm10k_mbx_validate_msg_size(mbx, len))
+ return FM10K_MBX_ERR_SIZE;
+
+ /* Update pushed */
+ mbx->pushed += len;
+
+ /* flush any completed messages */
+ for (len = fm10k_mbx_pushed_tail_len(mbx);
+ len && (mbx->pushed >= len);
+ len = fm10k_mbx_pushed_tail_len(mbx)) {
+ fifo->tail += len;
+ mbx->pushed -= len;
+ mbx->rx_messages++;
+ mbx->rx_dwords += len;
+ }
+
+ return 0;
+}
+
+/**
+ * fm10k_mbx_rx_ready - Indicates that a message is ready in the Rx FIFO
+ * @mbx: pointer to mailbox
+ *
+ * This function returns true if there is a message in the Rx FIFO to dequeue.
+ **/
+static bool fm10k_mbx_rx_ready(struct fm10k_mbx_info *mbx)
+{
+ u16 msg_size = fm10k_fifo_head_len(&mbx->rx);
+
+ return msg_size && (fm10k_fifo_used(&mbx->rx) >= msg_size);
+}
+
+/**
+ * fm10k_mbx_tx_ready - Indicates that the mailbox is in state ready for Tx
+ * @mbx: pointer to mailbox
+ * @len: verify free space is >= this value
+ *
+ * This function returns true if the mailbox is in a state ready to transmit.
+ **/
+static bool fm10k_mbx_tx_ready(struct fm10k_mbx_info *mbx, u16 len)
+{
+ u16 fifo_unused = fm10k_fifo_unused(&mbx->tx);
+
+ return (mbx->state == FM10K_STATE_OPEN) && (fifo_unused >= len);
+}
+
+/**
+ * fm10k_mbx_tx_complete - Indicates that the Tx FIFO has been emptied
+ * @mbx: pointer to mailbox
+ *
+ * This function returns true if the Tx FIFO is empty.
+ **/
+static bool fm10k_mbx_tx_complete(struct fm10k_mbx_info *mbx)
+{
+ return fm10k_fifo_empty(&mbx->tx);
+}
+
+/**
+ * fm10k_mbx_deqeueue_rx - Dequeues the message from the head in the Rx FIFO
+ * @hw: pointer to hardware structure
+ * @mbx: pointer to mailbox
+ *
+ * This function dequeues messages and hands them off to the tlv parser.
+ * It will return the number of messages processed when called.
+ **/
+static u16 fm10k_mbx_dequeue_rx(struct fm10k_hw *hw,
+ struct fm10k_mbx_info *mbx)
+{
+ struct fm10k_mbx_fifo *fifo = &mbx->rx;
+ s32 err;
+ u16 cnt;
+
+ /* parse Rx messages out of the Rx FIFO to empty it */
+ for (cnt = 0; !fm10k_fifo_empty(fifo); cnt++) {
+ err = fm10k_tlv_msg_parse(hw, fifo->buffer + fifo->head,
+ mbx, mbx->msg_data);
+ if (err < 0)
+ mbx->rx_parse_err++;
+
+ fm10k_fifo_head_drop(fifo);
+ }
+
+ /* shift remaining bytes back to start of FIFO */
+ memmove(fifo->buffer, fifo->buffer + fifo->tail, mbx->pushed << 2);
+
+ /* shift head and tail based on the memory we moved */
+ fifo->tail -= fifo->head;
+ fifo->head = 0;
+
+ return cnt;
+}
+
+/**
+ * fm10k_mbx_enqueue_tx - Enqueues the message to the tail of the Tx FIFO
+ * @hw: pointer to hardware structure
+ * @mbx: pointer to mailbox
+ * @msg: message array to read
+ *
+ * This function enqueues a message up to the size specified by the length
+ * contained in the first DWORD of the message and will place at the tail
+ * of the FIFO. It will return 0 on success, or a negative value on error.
+ **/
+static s32 fm10k_mbx_enqueue_tx(struct fm10k_hw *hw,
+ struct fm10k_mbx_info *mbx, const u32 *msg)
+{
+ u32 countdown = mbx->timeout;
+ s32 err;
+
+ switch (mbx->state) {
+ case FM10K_STATE_CLOSED:
+ case FM10K_STATE_DISCONNECT:
+ return FM10K_MBX_ERR_NO_MBX;
+ default:
+ break;
+ }
+
+ /* enqueue the message on the Tx FIFO */
+ err = fm10k_fifo_enqueue(&mbx->tx, msg);
+
+ /* if it failed give the FIFO a chance to drain */
+ while (err && countdown) {
+ countdown--;
+ udelay(mbx->udelay);
+ mbx->ops.process(hw, mbx);
+ err = fm10k_fifo_enqueue(&mbx->tx, msg);
+ }
+
+ /* if we failed trhead the error */
+ if (err) {
+ mbx->timeout = 0;
+ mbx->tx_busy++;
+ }
+
+ /* begin processing message, ignore errors as this is just meant
+ * to start the mailbox flow so we are not concerned if there
+ * is a bad error, or the mailbox is already busy with a request
+ */
+ if (!mbx->tail_len)
+ mbx->ops.process(hw, mbx);
+
+ return 0;
+}
+
+/**
+ * fm10k_mbx_read - Copies the mbmem to local message buffer
+ * @hw: pointer to hardware structure
+ * @mbx: pointer to mailbox
+ *
+ * This function copies the message from the mbmem to the message array
+ **/
+static s32 fm10k_mbx_read(struct fm10k_hw *hw, struct fm10k_mbx_info *mbx)
+{
+ /* only allow one reader in here at a time */
+ if (mbx->mbx_hdr)
+ return FM10K_MBX_ERR_BUSY;
+
+ /* read to capture initial interrupt bits */
+ if (fm10k_read_reg(hw, mbx->mbx_reg) & FM10K_MBX_REQ_INTERRUPT)
+ mbx->mbx_lock = FM10K_MBX_ACK;
+
+ /* write back interrupt bits to clear */
+ fm10k_write_reg(hw, mbx->mbx_reg,
+ FM10K_MBX_REQ_INTERRUPT | FM10K_MBX_ACK_INTERRUPT);
+
+ /* read remote header */
+ mbx->mbx_hdr = fm10k_read_reg(hw, mbx->mbmem_reg ^ mbx->mbmem_len);
+
+ return 0;
+}
+
+/**
+ * fm10k_mbx_write - Copies the local message buffer to mbmem
+ * @hw: pointer to hardware structure
+ * @mbx: pointer to mailbox
+ *
+ * This function copies the message from the the message array to mbmem
+ **/
+static void fm10k_mbx_write(struct fm10k_hw *hw, struct fm10k_mbx_info *mbx)
+{
+ u32 mbmem = mbx->mbmem_reg;
+
+ /* write new msg header to notify recepient of change */
+ fm10k_write_reg(hw, mbmem, mbx->mbx_hdr);
+
+ /* write mailbox to sent interrupt */
+ if (mbx->mbx_lock)
+ fm10k_write_reg(hw, mbx->mbx_reg, mbx->mbx_lock);
+
+ /* we no longer are using the header so free it */
+ mbx->mbx_hdr = 0;
+ mbx->mbx_lock = 0;
+}
+
+/**
+ * fm10k_mbx_reset_work- Reset internal pointers for any pending work
+ * @mbx: pointer to mailbox
+ *
+ * This function will reset all internal pointers so any work in progress
+ * is dropped. This call should occur every time we transition from the
+ * open state to the connect state.
+ **/
+static void fm10k_mbx_reset_work(struct fm10k_mbx_info *mbx)
+{
+ /* reset our outgoing max size back to Rx limits */
+ mbx->max_size = mbx->rx.size - 1;
+
+ /* just do a quick resysnc to start of message */
+ mbx->pushed = 0;
+ mbx->pulled = 0;
+ mbx->tail_len = 0;
+ mbx->head_len = 0;
+ mbx->rx.tail = 0;
+ mbx->rx.head = 0;
+}
+
+/**
+ * fm10k_mbx_update_max_size - Update the max_size and drop any large messages
+ * @mbx: pointer to mailbox
+ * @size: new value for max_size
+ *
+ * This function will update the max_size value and drop any outgoing messages
+ * from the head of the Tx FIFO that are larger than max_size.
+ **/
+static void fm10k_mbx_update_max_size(struct fm10k_mbx_info *mbx, u16 size)
+{
+ u16 len;
+
+ mbx->max_size = size;
+
+ /* flush any oversized messages from the queue */
+ for (len = fm10k_fifo_head_len(&mbx->tx);
+ len > size;
+ len = fm10k_fifo_head_len(&mbx->tx)) {
+ fm10k_fifo_head_drop(&mbx->tx);
+ mbx->tx_dropped++;
+ }
+}
+
+/**
+ * fm10k_mbx_validate_handlers - Validate layout of message parsing data
+ * @msg_data: handlers for mailbox events
+ *
+ * This function validates the layout of the message parsing data. This
+ * should be mostly static, but it is important to catch any errors that
+ * are made when constructing the parsers.
+ **/
+static s32 fm10k_mbx_validate_handlers(const struct fm10k_msg_data *msg_data)
+{
+ const struct fm10k_tlv_attr *attr;
+ unsigned int id;
+
+ /* Allow NULL mailboxes that transmit but don't receive */
+ if (!msg_data)
+ return 0;
+
+ while (msg_data->id != FM10K_TLV_ERROR) {
+ /* all messages should have a function handler */
+ if (!msg_data->func)
+ return FM10K_ERR_PARAM;
+
+ /* parser is optional */
+ attr = msg_data->attr;
+ if (attr) {
+ while (attr->id != FM10K_TLV_ERROR) {
+ id = attr->id;
+ attr++;
+ /* ID should always be increasing */
+ if (id >= attr->id)
+ return FM10K_ERR_PARAM;
+ /* ID should fit in results array */
+ if (id >= FM10K_TLV_RESULTS_MAX)
+ return FM10K_ERR_PARAM;
+ }
+
+ /* verify terminator is in the list */
+ if (attr->id != FM10K_TLV_ERROR)
+ return FM10K_ERR_PARAM;
+ }
+
+ id = msg_data->id;
+ msg_data++;
+ /* ID should always be increasing */
+ if (id >= msg_data->id)
+ return FM10K_ERR_PARAM;
+ }
+
+ /* verify terminator is in the list */
+ if ((msg_data->id != FM10K_TLV_ERROR) || !msg_data->func)
+ return FM10K_ERR_PARAM;
+
+ return 0;
+}
+
+/**
+ * fm10k_mbx_register_handlers - Register a set of handler ops for mailbox
+ * @mbx: pointer to mailbox
+ * @msg_data: handlers for mailbox events
+ *
+ * This function associates a set of message handling ops with a mailbox.
+ **/
+static s32 fm10k_mbx_register_handlers(struct fm10k_mbx_info *mbx,
+ const struct fm10k_msg_data *msg_data)
+{
+ /* validate layout of handlers before assigning them */
+ if (fm10k_mbx_validate_handlers(msg_data))
+ return FM10K_ERR_PARAM;
+
+ /* initialize the message handlers */
+ mbx->msg_data = msg_data;
+
+ return 0;
+}
+
+/**
+ * fm10k_sm_mbx_create_data_hdr - Generate a mailbox header for local FIFO
+ * @mbx: pointer to mailbox
+ *
+ * This function returns a connection mailbox header
+ **/
+static void fm10k_sm_mbx_create_data_hdr(struct fm10k_mbx_info *mbx)
+{
+ if (mbx->tail_len)
+ mbx->mbx_lock |= FM10K_MBX_REQ;
+
+ mbx->mbx_hdr = FM10K_MSG_HDR_FIELD_SET(mbx->tail, SM_TAIL) |
+ FM10K_MSG_HDR_FIELD_SET(mbx->remote, SM_VER) |
+ FM10K_MSG_HDR_FIELD_SET(mbx->head, SM_HEAD);
+}
+
+/**
+ * fm10k_sm_mbx_create_connect_hdr - Generate a mailbox header for local FIFO
+ * @mbx: pointer to mailbox
+ * @err: error flags to report if any
+ *
+ * This function returns a connection mailbox header
+ **/
+static void fm10k_sm_mbx_create_connect_hdr(struct fm10k_mbx_info *mbx, u8 err)
+{
+ if (mbx->local)
+ mbx->mbx_lock |= FM10K_MBX_REQ;
+
+ mbx->mbx_hdr = FM10K_MSG_HDR_FIELD_SET(mbx->tail, SM_TAIL) |
+ FM10K_MSG_HDR_FIELD_SET(mbx->remote, SM_VER) |
+ FM10K_MSG_HDR_FIELD_SET(mbx->head, SM_HEAD) |
+ FM10K_MSG_HDR_FIELD_SET(err, SM_ERR);
+}
+
+/**
+ * fm10k_sm_mbx_connect_reset - Reset following request for reset
+ * @mbx: pointer to mailbox
+ *
+ * This function resets the mailbox to a just connected state
+ **/
+static void fm10k_sm_mbx_connect_reset(struct fm10k_mbx_info *mbx)
+{
+ /* flush any uncompleted work */
+ fm10k_mbx_reset_work(mbx);
+
+ /* set local version to max and remote version to 0 */
+ mbx->local = FM10K_SM_MBX_VERSION;
+ mbx->remote = 0;
+
+ /* initalize tail and head */
+ mbx->tail = 1;
+ mbx->head = 1;
+
+ /* reset state back to connect */
+ mbx->state = FM10K_STATE_CONNECT;
+}
+
+/**
+ * fm10k_sm_mbx_connect - Start switch manager mailbox connection
+ * @hw: pointer to hardware structure
+ * @mbx: pointer to mailbox
+ *
+ * This function will initiate a mailbox connection with the switch
+ * manager. To do this it will first disconnect the mailbox, and then
+ * reconnect it in order to complete a reset of the mailbox.
+ *
+ * This function will return an error if the mailbox has not been initiated
+ * or is currently in use.
+ **/
+static s32 fm10k_sm_mbx_connect(struct fm10k_hw *hw, struct fm10k_mbx_info *mbx)
+{
+ /* we cannot connect an uninitialized mailbox */
+ if (!mbx->rx.buffer)
+ return FM10K_MBX_ERR_NO_SPACE;
+
+ /* we cannot connect an already connected mailbox */
+ if (mbx->state != FM10K_STATE_CLOSED)
+ return FM10K_MBX_ERR_BUSY;
+
+ /* mailbox timeout can now become active */
+ mbx->timeout = FM10K_MBX_INIT_TIMEOUT;
+
+ /* Place mbx in ready to connect state */
+ mbx->state = FM10K_STATE_CONNECT;
+ mbx->max_size = FM10K_MBX_MSG_MAX_SIZE;
+
+ /* reset interface back to connect */
+ fm10k_sm_mbx_connect_reset(mbx);
+
+ /* enable interrupt and notify other party of new message */
+ mbx->mbx_lock = FM10K_MBX_REQ_INTERRUPT | FM10K_MBX_ACK_INTERRUPT |
+ FM10K_MBX_INTERRUPT_ENABLE;
+
+ /* generate and load connect header into mailbox */
+ fm10k_sm_mbx_create_connect_hdr(mbx, 0);
+ fm10k_mbx_write(hw, mbx);
+
+ /* enable interrupt and notify other party of new message */
+
+ return 0;
+}
+
+/**
+ * fm10k_sm_mbx_disconnect - Shutdown mailbox connection
+ * @hw: pointer to hardware structure
+ * @mbx: pointer to mailbox
+ *
+ * This function will shut down the mailbox. It places the mailbox first
+ * in the disconnect state, it then allows up to a predefined timeout for
+ * the mailbox to transition to close on its own. If this does not occur
+ * then the mailbox will be forced into the closed state.
+ *
+ * Any mailbox transactions not completed before calling this function
+ * are not guaranteed to complete and may be dropped.
+ **/
+static void fm10k_sm_mbx_disconnect(struct fm10k_hw *hw,
+ struct fm10k_mbx_info *mbx)
+{
+ int timeout = mbx->timeout ? FM10K_MBX_DISCONNECT_TIMEOUT : 0;
+
+ /* Place mbx in ready to disconnect state */
+ mbx->state = FM10K_STATE_DISCONNECT;
+
+ /* trigger interrupt to start shutdown process */
+ fm10k_write_reg(hw, mbx->mbx_reg, FM10K_MBX_REQ |
+ FM10K_MBX_INTERRUPT_DISABLE);
+ do {
+ udelay(FM10K_MBX_POLL_DELAY);
+ mbx->ops.process(hw, mbx);
+ timeout -= FM10K_MBX_POLL_DELAY;
+ } while ((timeout > 0) && (mbx->state != FM10K_STATE_CLOSED));
+
+ /* in case we didn't close just force the mailbox into shutdown */
+ mbx->state = FM10K_STATE_CLOSED;
+ mbx->remote = 0;
+ fm10k_mbx_reset_work(mbx);
+ fm10k_mbx_update_max_size(mbx, 0);
+
+ fm10k_write_reg(hw, mbx->mbmem_reg, 0);
+}
+
+/**
+ * fm10k_mbx_validate_fifo_hdr - Validate fields in the remote FIFO header
+ * @mbx: pointer to mailbox
+ *
+ * This function will parse up the fields in the mailbox header and return
+ * an error if the header contains any of a number of invalid configurations
+ * including unrecognized offsets or version numbers.
+ **/
+static s32 fm10k_sm_mbx_validate_fifo_hdr(struct fm10k_mbx_info *mbx)
+{
+ const u32 *hdr = &mbx->mbx_hdr;
+ u16 tail, head, ver;
+
+ tail = FM10K_MSG_HDR_FIELD_GET(*hdr, SM_TAIL);
+ ver = FM10K_MSG_HDR_FIELD_GET(*hdr, SM_VER);
+ head = FM10K_MSG_HDR_FIELD_GET(*hdr, SM_HEAD);
+
+ switch (ver) {
+ case 0:
+ break;
+ case FM10K_SM_MBX_VERSION:
+ if (!head || head > FM10K_SM_MBX_FIFO_LEN)
+ return FM10K_MBX_ERR_HEAD;
+ if (!tail || tail > FM10K_SM_MBX_FIFO_LEN)
+ return FM10K_MBX_ERR_TAIL;
+ if (mbx->tail < head)
+ head += mbx->mbmem_len - 1;
+ if (tail < mbx->head)
+ tail += mbx->mbmem_len - 1;
+ if (fm10k_mbx_index_len(mbx, head, mbx->tail) > mbx->tail_len)
+ return FM10K_MBX_ERR_HEAD;
+ if (fm10k_mbx_index_len(mbx, mbx->head, tail) < mbx->mbmem_len)
+ break;
+ return FM10K_MBX_ERR_TAIL;
+ default:
+ return FM10K_MBX_ERR_SRC;
+ }
+
+ return 0;
+}
+
+/**
+ * fm10k_sm_mbx_process_error - Process header with error flag set
+ * @mbx: pointer to mailbox
+ *
+ * This function is meant to respond to a request where the error flag
+ * is set. As a result we will terminate a connection if one is present
+ * and fall back into the reset state with a connection header of version
+ * 0 (RESET).
+ **/
+static void fm10k_sm_mbx_process_error(struct fm10k_mbx_info *mbx)
+{
+ const enum fm10k_mbx_state state = mbx->state;
+
+ switch (state) {
+ case FM10K_STATE_DISCONNECT:
+ /* if there is an error just disconnect */
+ mbx->remote = 0;
+ break;
+ case FM10K_STATE_OPEN:
+ /* flush any uncompleted work */
+ fm10k_sm_mbx_connect_reset(mbx);
+ break;
+ case FM10K_STATE_CONNECT:
+ /* try connnecting at lower version */
+ if (mbx->remote) {
+ while (mbx->local > 1)
+ mbx->local--;
+ mbx->remote = 0;
+ }
+ break;
+ default:
+ break;
+ }
+
+ fm10k_sm_mbx_create_connect_hdr(mbx, 0);
+}
+
+/**
+ * fm10k_sm_mbx_create_error_message - Process an error in FIFO hdr
+ * @mbx: pointer to mailbox
+ * @err: local error encountered
+ *
+ * This function will interpret the error provided by err, and based on
+ * that it may set the error bit in the local message header
+ **/
+static void fm10k_sm_mbx_create_error_msg(struct fm10k_mbx_info *mbx, s32 err)
+{
+ /* only generate an error message for these types */
+ switch (err) {
+ case FM10K_MBX_ERR_TAIL:
+ case FM10K_MBX_ERR_HEAD:
+ case FM10K_MBX_ERR_SRC:
+ case FM10K_MBX_ERR_SIZE:
+ case FM10K_MBX_ERR_RSVD0:
+ break;
+ default:
+ return;
+ }
+
+ /* process it as though we received an error, and send error reply */
+ fm10k_sm_mbx_process_error(mbx);
+ fm10k_sm_mbx_create_connect_hdr(mbx, 1);
+}
+
+/**
+ * fm10k_sm_mbx_receive - Take message from Rx mailbox FIFO and put it in Rx
+ * @hw: pointer to hardware structure
+ * @mbx: pointer to mailbox
+ *
+ * This function will dequeue one message from the Rx switch manager mailbox
+ * FIFO and place it in the Rx mailbox FIFO for processing by software.
+ **/
+static s32 fm10k_sm_mbx_receive(struct fm10k_hw *hw,
+ struct fm10k_mbx_info *mbx,
+ u16 tail)
+{
+ /* reduce length by 1 to convert to a mask */
+ u16 mbmem_len = mbx->mbmem_len - 1;
+ s32 err;
+
+ /* push tail in front of head */
+ if (tail < mbx->head)
+ tail += mbmem_len;
+
+ /* copy data to the Rx FIFO */
+ err = fm10k_mbx_push_tail(hw, mbx, tail);
+ if (err < 0)
+ return err;
+
+ /* process messages if we have received any */
+ fm10k_mbx_dequeue_rx(hw, mbx);
+
+ /* guarantee head aligns with the end of the last message */
+ mbx->head = fm10k_mbx_head_sub(mbx, mbx->pushed);
+ mbx->pushed = 0;
+
+ /* clear any extra bits left over since index adds 1 extra bit */
+ if (mbx->head > mbmem_len)
+ mbx->head -= mbmem_len;
+
+ return err;
+}
+
+/**
+ * fm10k_sm_mbx_transmit - Take message from Tx and put it in Tx mailbox FIFO
+ * @hw: pointer to hardware structure
+ * @mbx: pointer to mailbox
+ *
+ * This function will dequeue one message from the Tx mailbox FIFO and place
+ * it in the Tx switch manager mailbox FIFO for processing by hardware.
+ **/
+static void fm10k_sm_mbx_transmit(struct fm10k_hw *hw,
+ struct fm10k_mbx_info *mbx, u16 head)
+{
+ struct fm10k_mbx_fifo *fifo = &mbx->tx;
+ /* reduce length by 1 to convert to a mask */
+ u16 mbmem_len = mbx->mbmem_len - 1;
+ u16 tail_len, len = 0;
+ u32 *msg;
+
+ /* push head behind tail */
+ if (mbx->tail < head)
+ head += mbmem_len;
+
+ fm10k_mbx_pull_head(hw, mbx, head);
+
+ /* determine msg aligned offset for end of buffer */
+ do {
+ msg = fifo->buffer + fm10k_fifo_head_offset(fifo, len);
+ tail_len = len;
+ len += FM10K_TLV_DWORD_LEN(*msg);
+ } while ((len <= mbx->tail_len) && (len < mbmem_len));
+
+ /* guarantee we stop on a message boundary */
+ if (mbx->tail_len > tail_len) {
+ mbx->tail = fm10k_mbx_tail_sub(mbx, mbx->tail_len - tail_len);
+ mbx->tail_len = tail_len;
+ }
+
+ /* clear any extra bits left over since index adds 1 extra bit */
+ if (mbx->tail > mbmem_len)
+ mbx->tail -= mbmem_len;
+}
+
+/**
+ * fm10k_sm_mbx_create_reply - Generate reply based on state and remote head
+ * @mbx: pointer to mailbox
+ * @head: acknowledgement number
+ *
+ * This function will generate an outgoing message based on the current
+ * mailbox state and the remote fifo head. It will return the length
+ * of the outgoing message excluding header on success, and a negative value
+ * on error.
+ **/
+static void fm10k_sm_mbx_create_reply(struct fm10k_hw *hw,
+ struct fm10k_mbx_info *mbx, u16 head)
+{
+ switch (mbx->state) {
+ case FM10K_STATE_OPEN:
+ case FM10K_STATE_DISCONNECT:
+ /* flush out Tx data */
+ fm10k_sm_mbx_transmit(hw, mbx, head);
+
+ /* generate new header based on data */
+ if (mbx->tail_len || (mbx->state == FM10K_STATE_OPEN)) {
+ fm10k_sm_mbx_create_data_hdr(mbx);
+ } else {
+ mbx->remote = 0;
+ fm10k_sm_mbx_create_connect_hdr(mbx, 0);
+ }
+ break;
+ case FM10K_STATE_CONNECT:
+ case FM10K_STATE_CLOSED:
+ fm10k_sm_mbx_create_connect_hdr(mbx, 0);
+ break;
+ default:
+ break;
+ }
+}
+
+/**
+ * fm10k_sm_mbx_process_reset - Process header with version == 0 (RESET)
+ * @hw: pointer to hardware structure
+ * @mbx: pointer to mailbox
+ *
+ * This function is meant to respond to a request where the version data
+ * is set to 0. As such we will either terminate the connection or go
+ * into the connect state in order to re-establish the connection. This
+ * function can also be used to respond to an error as the connection
+ * resetting would also be a means of dealing with errors.
+ **/
+static void fm10k_sm_mbx_process_reset(struct fm10k_hw *hw,
+ struct fm10k_mbx_info *mbx)
+{
+ const enum fm10k_mbx_state state = mbx->state;
+
+ switch (state) {
+ case FM10K_STATE_DISCONNECT:
+ /* drop remote connections and disconnect */
+ mbx->state = FM10K_STATE_CLOSED;
+ mbx->remote = 0;
+ mbx->local = 0;
+ break;
+ case FM10K_STATE_OPEN:
+ /* flush any incomplete work */
+ fm10k_sm_mbx_connect_reset(mbx);
+ break;
+ case FM10K_STATE_CONNECT:
+ /* Update remote value to match local value */
+ mbx->remote = mbx->local;
+ default:
+ break;
+ }
+
+ fm10k_sm_mbx_create_reply(hw, mbx, mbx->tail);
+}
+
+/**
+ * fm10k_sm_mbx_process_version_1 - Process header with version == 1
+ * @hw: pointer to hardware structure
+ * @mbx: pointer to mailbox
+ *
+ * This function is meant to process messages received when the remote
+ * mailbox is active.
+ **/
+static s32 fm10k_sm_mbx_process_version_1(struct fm10k_hw *hw,
+ struct fm10k_mbx_info *mbx)
+{
+ const u32 *hdr = &mbx->mbx_hdr;
+ u16 head, tail;
+ s32 len;
+
+ /* pull all fields needed for verification */
+ tail = FM10K_MSG_HDR_FIELD_GET(*hdr, SM_TAIL);
+ head = FM10K_MSG_HDR_FIELD_GET(*hdr, SM_HEAD);
+
+ /* if we are in connect and wanting version 1 then start up and go */
+ if (mbx->state == FM10K_STATE_CONNECT) {
+ if (!mbx->remote)
+ goto send_reply;
+ if (mbx->remote != 1)
+ return FM10K_MBX_ERR_SRC;
+
+ mbx->state = FM10K_STATE_OPEN;
+ }
+
+ do {
+ /* abort on message size errors */
+ len = fm10k_sm_mbx_receive(hw, mbx, tail);
+ if (len < 0)
+ return len;
+
+ /* continue until we have flushed the Rx FIFO */
+ } while (len);
+
+send_reply:
+ fm10k_sm_mbx_create_reply(hw, mbx, head);
+
+ return 0;
+}
+
+/**
+ * fm10k_sm_mbx_process - Process mailbox switch mailbox interrupt
+ * @hw: pointer to hardware structure
+ * @mbx: pointer to mailbox
+ *
+ * This function will process incoming mailbox events and generate mailbox
+ * replies. It will return a value indicating the number of DWORDs
+ * transmitted excluding header on success or a negative value on error.
+ **/
+static s32 fm10k_sm_mbx_process(struct fm10k_hw *hw,
+ struct fm10k_mbx_info *mbx)
+{
+ s32 err;
+
+ /* we do not read mailbox if closed */
+ if (mbx->state == FM10K_STATE_CLOSED)
+ return 0;
+
+ /* retrieve data from switch manager */
+ err = fm10k_mbx_read(hw, mbx);
+ if (err)
+ return err;
+
+ err = fm10k_sm_mbx_validate_fifo_hdr(mbx);
+ if (err < 0)
+ goto fifo_err;
+
+ if (FM10K_MSG_HDR_FIELD_GET(mbx->mbx_hdr, SM_ERR)) {
+ fm10k_sm_mbx_process_error(mbx);
+ goto fifo_err;
+ }
+
+ switch (FM10K_MSG_HDR_FIELD_GET(mbx->mbx_hdr, SM_VER)) {
+ case 0:
+ fm10k_sm_mbx_process_reset(hw, mbx);
+ break;
+ case FM10K_SM_MBX_VERSION:
+ err = fm10k_sm_mbx_process_version_1(hw, mbx);
+ break;
+ }
+
+fifo_err:
+ if (err < 0)
+ fm10k_sm_mbx_create_error_msg(mbx, err);
+
+ /* report data to switch manager */
+ fm10k_mbx_write(hw, mbx);
+
+ return err;
+}
+
+/**
+ * fm10k_sm_mbx_init - Initialize mailbox memory for PF/SM mailbox
+ * @hw: pointer to hardware structure
+ * @mbx: pointer to mailbox
+ * @msg_data: handlers for mailbox events
+ *
+ * This function for now is used to stub out the PF/SM mailbox
+ **/
+s32 fm10k_sm_mbx_init(struct fm10k_hw *hw, struct fm10k_mbx_info *mbx,
+ const struct fm10k_msg_data *msg_data)
+{
+ mbx->mbx_reg = FM10K_GMBX;
+ mbx->mbmem_reg = FM10K_MBMEM_PF(0);
+ /* start out in closed state */
+ mbx->state = FM10K_STATE_CLOSED;
+
+ /* validate layout of handlers before assigning them */
+ if (fm10k_mbx_validate_handlers(msg_data))
+ return FM10K_ERR_PARAM;
+
+ /* initialize the message handlers */
+ mbx->msg_data = msg_data;
+
+ /* start mailbox as timed out and let the reset_hw call
+ * set the timeout value to begin communications
+ */
+ mbx->timeout = 0;
+ mbx->udelay = FM10K_MBX_INIT_DELAY;
+
+ /* Split buffer for use by Tx/Rx FIFOs */
+ mbx->max_size = FM10K_MBX_MSG_MAX_SIZE;
+ mbx->mbmem_len = FM10K_MBMEM_PF_XOR;
+
+ /* initialize the FIFOs, sizes are in 4 byte increments */
+ fm10k_fifo_init(&mbx->tx, mbx->buffer, FM10K_MBX_TX_BUFFER_SIZE);
+ fm10k_fifo_init(&mbx->rx, &mbx->buffer[FM10K_MBX_TX_BUFFER_SIZE],
+ FM10K_MBX_RX_BUFFER_SIZE);
+
+ /* initialize function pointers */
+ mbx->ops.connect = fm10k_sm_mbx_connect;
+ mbx->ops.disconnect = fm10k_sm_mbx_disconnect;
+ mbx->ops.rx_ready = fm10k_mbx_rx_ready;
+ mbx->ops.tx_ready = fm10k_mbx_tx_ready;
+ mbx->ops.tx_complete = fm10k_mbx_tx_complete;
+ mbx->ops.enqueue_tx = fm10k_mbx_enqueue_tx;
+ mbx->ops.process = fm10k_sm_mbx_process;
+ mbx->ops.register_handlers = fm10k_mbx_register_handlers;
+
+ return 0;
+}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.h b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.h
index cb7aa4a..f5ba86f 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.h
@@ -237,4 +237,7 @@ struct fm10k_mbx_info {
u32 buffer[FM10K_MBX_BUFFER_SIZE];
};
+s32 fm10k_sm_mbx_init(struct fm10k_hw *, struct fm10k_mbx_info *,
+ const struct fm10k_msg_data *);
+
#endif /* _FM10K_MBX_H_ */
^ 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