Netdev List
 help / color / mirror / Atom feed
* Re: SR-IOV problem with Intel 82599EB (not enough MMIO resources for SR-IOV)
From: Yinghai Lu @ 2012-11-13 18:16 UTC (permalink / raw)
  To: Li, Sibai
  Cc: Jason Gao, bhelgaas@google.com, Rose, Gregory V,
	ddutile@redhat.com, Kirsher, Jeffrey T, linux-kernel, netdev, kvm,
	e1000-devel@lists.sourceforge.net, linux-pci@vger.kernel.org
In-Reply-To: <A3A921390EAE4044940E99EBF13D97321AE21E15@FMSMSX104.amr.corp.intel.com>

On Tue, Nov 13, 2012 at 8:04 AM, Li, Sibai <sibai.li@intel.com> wrote:
>
>>
>> Thank you very much,I try "pci=realloc" in Centos 6.3,and now it works for me.
>>
>> thank you Sibai,Our server "Dell R710",its BIOS version is just
>> v.6.3.0 and release date is 07/24/2012,and I also configured intel_iommu=on in
>> the grub.conf file,but I can't find these IOMMU options in "Device Drivers" in my
>> kernel(2.6.32-279) .config file , btw my os is Centos 6.3(RHEL6.3),although the
>> problem solved,I'd like to know what's your os version ,kernel version?
>
> I am using RHEL6.3 with unstable kernel 3.7.0-rc

that means that config has
CONFIG_PCI_REALLOC_ENABLE_AUTO=y

So you don't need to append "pci=realloc"

Yinghai

^ permalink raw reply

* [PATCH net-next 3/4] bridge: implement BPDU blocking
From: Stephen Hemminger @ 2012-11-13 17:53 UTC (permalink / raw)
  To: davem; +Cc: netdev
In-Reply-To: <20121113175304.628996029@vyatta.com>

[-- Attachment #1: bridge-bpdu-guard.patch --]
[-- Type: text/plain, Size: 4367 bytes --]

This is Linux bridge implementation of STP protection
(Cisco BPDU guard/Juniper BPDU block). BPDU block disables
the bridge port if a STP BPDU packet is received.

Why would you want to do this?
If running Spanning Tree on bridge, hostile devices on the network
may send BPDU and cause network failure. Enabling bpdu block
will detect and stop this.

How to recover the port?
The port will be restarted if link is brought down, or
removed and reattached.  For example:
 # ip li set dev eth0 down; ip li set dev eth0 up

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>

---
v2 - refresh for earlier changes related to generic bridge setlink

 include/uapi/linux/if_link.h |    1 +
 net/bridge/br_netlink.c      |    7 ++++++-
 net/bridge/br_private.h      |    1 +
 net/bridge/br_stp_bpdu.c     |    7 +++++++
 net/bridge/br_sysfs_if.c     |    2 ++
 5 files changed, 17 insertions(+), 1 deletion(-)

--- a/net/bridge/br_private.h	2012-11-12 07:58:45.000000000 -0800
+++ b/net/bridge/br_private.h	2012-11-12 13:52:51.858985336 -0800
@@ -135,6 +135,7 @@ struct net_bridge_port
 
 	unsigned long 			flags;
 #define BR_HAIRPIN_MODE		0x00000001
+#define BR_BPDU_GUARD           0x00000002
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 	u32				multicast_startup_queries_sent;
--- a/net/bridge/br_stp_bpdu.c	2012-11-12 07:58:35.000000000 -0800
+++ b/net/bridge/br_stp_bpdu.c	2012-11-12 13:52:51.858985336 -0800
@@ -170,6 +170,13 @@ void br_stp_rcv(const struct stp_proto *
 	if (!ether_addr_equal(dest, br->group_addr))
 		goto out;
 
+	if (p->flags & BR_BPDU_GUARD) {
+		br_notice(br, "BPDU received on blocked port %u(%s)\n",
+			  (unsigned int) p->port_no, p->dev->name);
+		br_stp_disable_port(p);
+		goto out;
+	}
+
 	buf = skb_pull(skb, 3);
 
 	if (buf[0] == BPDU_TYPE_CONFIG) {
--- a/net/bridge/br_sysfs_if.c	2012-11-12 13:52:42.000000000 -0800
+++ b/net/bridge/br_sysfs_if.c	2012-11-12 13:52:51.858985336 -0800
@@ -156,6 +156,7 @@ static int store_flush(struct net_bridge
 static BRPORT_ATTR(flush, S_IWUSR, NULL, store_flush);
 
 BRPORT_ATTR_FLAG(hairpin_mode, BR_HAIRPIN_MODE);
+BRPORT_ATTR_FLAG(bpdu_guard, BR_BPDU_GUARD);
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf)
@@ -189,6 +190,7 @@ static const struct brport_attribute *br
 	&brport_attr_hold_timer,
 	&brport_attr_flush,
 	&brport_attr_hairpin_mode,
+	&brport_attr_bpdu_guard,
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 	&brport_attr_multicast_router,
 #endif
--- a/include/uapi/linux/if_link.h	2012-11-12 13:33:53.000000000 -0800
+++ b/include/uapi/linux/if_link.h	2012-11-12 13:52:51.858985336 -0800
@@ -216,6 +216,7 @@ enum {
 	IFLA_BRPORT_PRIORITY,	/* "             priority  */
 	IFLA_BRPORT_COST,	/* "             cost      */
 	IFLA_BRPORT_MODE,	/* mode (hairpin)          */
+	IFLA_BRPORT_GUARD,	/* bpdu guard              */
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
--- a/net/bridge/br_netlink.c	2012-11-12 13:51:37.000000000 -0800
+++ b/net/bridge/br_netlink.c	2012-11-12 13:53:19.694706427 -0800
@@ -26,6 +26,7 @@ static inline size_t br_port_info_size(v
 		+ nla_total_size(2)	/* IFLA_BRPORT_PRIORITY */
 		+ nla_total_size(4)	/* IFLA_BRPORT_COST */
 		+ nla_total_size(1)	/* IFLA_BRPORT_MODE */
+		+ nla_total_size(1)	/* IFLA_BRPORT_GUARD */
 		+ 0;
 }
 
@@ -49,7 +50,8 @@ static int br_port_fill_attrs(struct sk_
 	if (nla_put_u8(skb, IFLA_BRPORT_STATE, p->state) ||
 	    nla_put_u16(skb, IFLA_BRPORT_PRIORITY, p->priority) ||
 	    nla_put_u32(skb, IFLA_BRPORT_COST, p->path_cost) ||
-	    nla_put_u8(skb, IFLA_BRPORT_MODE, mode))
+	    nla_put_u8(skb, IFLA_BRPORT_MODE, mode) ||
+	    nla_put_u8(skb, IFLA_BRPORT_GUARD, !!(p->flags & BR_BPDU_GUARD)))
 		return -EMSGSIZE;
 
 	return 0;
@@ -162,6 +164,7 @@ static const struct nla_policy ifla_brpo
 	[IFLA_BRPORT_COST]	= { .type = NLA_U32 },
 	[IFLA_BRPORT_PRIORITY]	= { .type = NLA_U16 },
 	[IFLA_BRPORT_MODE]	= { .type = NLA_U8 },
+	[IFLA_BRPORT_GUARD]	= { .type = NLA_U8 },
 };
 
 /* Change the state of the port and notify spanning tree */
@@ -203,6 +206,7 @@ static int br_setport(struct net_bridge_
 	int err;
 
 	br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE);
+	br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD);
 
 	if (tb[IFLA_BRPORT_COST]) {
 		err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST]));

^ permalink raw reply

* [PATCH net-next 4/4] bridge: add root port blocking
From: Stephen Hemminger @ 2012-11-13 17:53 UTC (permalink / raw)
  To: davem; +Cc: netdev
In-Reply-To: <20121113175304.628996029@vyatta.com>

[-- Attachment #1: bridge-root-block.patch --]
[-- Type: text/plain, Size: 4599 bytes --]

This is Linux bridge implementation of root port guard.
If BPDU is received from a leaf (edge) port, it should not
be elected as root port.

Why would you want to do this?
If using STP on a bridge and the downstream bridges are not fully
trusted; this prevents a hostile guest for rerouting traffic.

Why not just use netfilter?
Netfilter does not track of follow spanning tree decisions.
It would be difficult and error prone to try and mirror STP
resolution in netfilter module.

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>


---
 include/uapi/linux/if_link.h |    1 +
 net/bridge/br_netlink.c      |    6 +++++-
 net/bridge/br_private.h      |    1 +
 net/bridge/br_stp.c          |   22 +++++++++++++++++++++-
 net/bridge/br_sysfs_if.c     |    2 ++
 5 files changed, 30 insertions(+), 2 deletions(-)

--- a/net/bridge/br_private.h	2012-11-12 13:52:51.858985336 -0800
+++ b/net/bridge/br_private.h	2012-11-12 13:54:52.309778448 -0800
@@ -136,6 +136,7 @@ struct net_bridge_port
 	unsigned long 			flags;
 #define BR_HAIRPIN_MODE		0x00000001
 #define BR_BPDU_GUARD           0x00000002
+#define BR_ROOT_BLOCK		0x00000004
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 	u32				multicast_startup_queries_sent;
--- a/net/bridge/br_stp.c	2012-11-12 07:58:31.067183169 -0800
+++ b/net/bridge/br_stp.c	2012-11-12 13:53:27.254630683 -0800
@@ -100,6 +100,21 @@ static int br_should_become_root_port(co
 	return 0;
 }
 
+static void br_root_port_block(const struct net_bridge *br,
+			       struct net_bridge_port *p)
+{
+
+	br_notice(br, "port %u(%s) tried to become root port (blocked)",
+		  (unsigned int) p->port_no, p->dev->name);
+
+	p->state = BR_STATE_LISTENING;
+	br_log_state(p);
+	br_ifinfo_notify(RTM_NEWLINK, p);
+
+	if (br->forward_delay > 0)
+		mod_timer(&p->forward_delay_timer, jiffies + br->forward_delay);
+}
+
 /* called under bridge lock */
 static void br_root_selection(struct net_bridge *br)
 {
@@ -107,7 +122,12 @@ static void br_root_selection(struct net
 	u16 root_port = 0;
 
 	list_for_each_entry(p, &br->port_list, list) {
-		if (br_should_become_root_port(p, root_port))
+		if (!br_should_become_root_port(p, root_port))
+			continue;
+
+		if (p->flags & BR_ROOT_BLOCK)
+			br_root_port_block(br, p);
+		else
 			root_port = p->port_no;
 	}
 
--- a/net/bridge/br_sysfs_if.c	2012-11-12 13:52:51.858985336 -0800
+++ b/net/bridge/br_sysfs_if.c	2012-11-12 13:54:52.309778448 -0800
@@ -157,6 +157,7 @@ static BRPORT_ATTR(flush, S_IWUSR, NULL,
 
 BRPORT_ATTR_FLAG(hairpin_mode, BR_HAIRPIN_MODE);
 BRPORT_ATTR_FLAG(bpdu_guard, BR_BPDU_GUARD);
+BRPORT_ATTR_FLAG(root_block, BR_ROOT_BLOCK);
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf)
@@ -191,6 +192,7 @@ static const struct brport_attribute *br
 	&brport_attr_flush,
 	&brport_attr_hairpin_mode,
 	&brport_attr_bpdu_guard,
+	&brport_attr_root_block,
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 	&brport_attr_multicast_router,
 #endif
--- a/include/uapi/linux/if_link.h	2012-11-12 13:52:51.858985336 -0800
+++ b/include/uapi/linux/if_link.h	2012-11-12 13:54:52.309778448 -0800
@@ -217,6 +217,7 @@ enum {
 	IFLA_BRPORT_COST,	/* "             cost      */
 	IFLA_BRPORT_MODE,	/* mode (hairpin)          */
 	IFLA_BRPORT_GUARD,	/* bpdu guard              */
+	IFLA_BRPORT_PROTECT,	/* root port protection    */
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
--- a/net/bridge/br_netlink.c	2012-11-12 13:53:19.694706427 -0800
+++ b/net/bridge/br_netlink.c	2012-11-12 13:54:52.309778448 -0800
@@ -27,6 +27,7 @@ static inline size_t br_port_info_size(v
 		+ nla_total_size(4)	/* IFLA_BRPORT_COST */
 		+ nla_total_size(1)	/* IFLA_BRPORT_MODE */
 		+ nla_total_size(1)	/* IFLA_BRPORT_GUARD */
+		+ nla_total_size(1)	/* IFLA_BRPORT_PROTECT */
 		+ 0;
 }
 
@@ -51,7 +52,8 @@ static int br_port_fill_attrs(struct sk_
 	    nla_put_u16(skb, IFLA_BRPORT_PRIORITY, p->priority) ||
 	    nla_put_u32(skb, IFLA_BRPORT_COST, p->path_cost) ||
 	    nla_put_u8(skb, IFLA_BRPORT_MODE, mode) ||
-	    nla_put_u8(skb, IFLA_BRPORT_GUARD, !!(p->flags & BR_BPDU_GUARD)))
+	    nla_put_u8(skb, IFLA_BRPORT_GUARD, !!(p->flags & BR_BPDU_GUARD)) ||
+	    nla_put_u8(skb, IFLA_BRPORT_PROTECT, !!(p->flags & BR_ROOT_BLOCK)))
 		return -EMSGSIZE;
 
 	return 0;
@@ -165,6 +167,7 @@ static const struct nla_policy ifla_brpo
 	[IFLA_BRPORT_PRIORITY]	= { .type = NLA_U16 },
 	[IFLA_BRPORT_MODE]	= { .type = NLA_U8 },
 	[IFLA_BRPORT_GUARD]	= { .type = NLA_U8 },
+	[IFLA_BRPORT_PROTECT]	= { .type = NLA_U8 },
 };
 
 /* Change the state of the port and notify spanning tree */

^ permalink raw reply

* [PATCH net-next 0/4] New Bridge security features
From: Stephen Hemminger @ 2012-11-13 17:53 UTC (permalink / raw)
  To: davem; +Cc: netdev

New bridge API's and security features for protecting
Spanning Tree Protocol.  For more info, see KVM forum talk
  http://www.slideshare.net/shemminger/new-bridge
and BPDU guard explanation here:
  http://blog.ipexpert.com/2010/12/06/bpdu-filter-and-bpdu-guard/

^ permalink raw reply

* [PATCH net-next 2/4] bridge: add template for bridge port flags
From: Stephen Hemminger @ 2012-11-13 17:53 UTC (permalink / raw)
  To: davem; +Cc: netdev
In-Reply-To: <20121113175304.628996029@vyatta.com>

[-- Attachment #1: brport-flags-sysfs.patch --]
[-- Type: text/plain, Size: 1902 bytes --]

Provide macro to build sysfs data structures and functions
for accessing flag bits.  If flag bits change do netlink
notification.

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>


--- a/net/bridge/br_sysfs_if.c	2012-11-12 07:58:35.411139543 -0800
+++ b/net/bridge/br_sysfs_if.c	2012-11-12 13:52:42.319080923 -0800
@@ -34,6 +34,28 @@ const struct brport_attribute brport_att
 	.store	= _store,					\
 };
 
+#define BRPORT_ATTR_FLAG(_name, _mask)				\
+static ssize_t show_##_name(struct net_bridge_port *p, char *buf) \
+{								\
+	return sprintf(buf, "%d\n", !!(p->flags & _mask));	\
+}								\
+static int store_##_name(struct net_bridge_port *p, unsigned long v) \
+{								\
+	unsigned long flags = p->flags;				\
+	if (v)							\
+		flags |= _mask;					\
+	else							\
+		flags &= ~_mask;				\
+	if (flags != p->flags) {				\
+		p->flags = flags;				\
+		br_ifinfo_notify(RTM_NEWLINK, p);		\
+	}							\
+	return 0;						\
+}								\
+static BRPORT_ATTR(_name, S_IRUGO | S_IWUSR,			\
+		   show_##_name, store_##_name)
+
+
 static ssize_t show_path_cost(struct net_bridge_port *p, char *buf)
 {
 	return sprintf(buf, "%d\n", p->path_cost);
@@ -133,21 +155,7 @@ static int store_flush(struct net_bridge
 }
 static BRPORT_ATTR(flush, S_IWUSR, NULL, store_flush);
 
-static ssize_t show_hairpin_mode(struct net_bridge_port *p, char *buf)
-{
-	int hairpin_mode = (p->flags & BR_HAIRPIN_MODE) ? 1 : 0;
-	return sprintf(buf, "%d\n", hairpin_mode);
-}
-static int store_hairpin_mode(struct net_bridge_port *p, unsigned long v)
-{
-	if (v)
-		p->flags |= BR_HAIRPIN_MODE;
-	else
-		p->flags &= ~BR_HAIRPIN_MODE;
-	return 0;
-}
-static BRPORT_ATTR(hairpin_mode, S_IRUGO | S_IWUSR,
-		   show_hairpin_mode, store_hairpin_mode);
+BRPORT_ATTR_FLAG(hairpin_mode, BR_HAIRPIN_MODE);
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf)

^ permalink raw reply

* [PATCH net-next 1/4] bridge: bridge port parameters over netlink
From: Stephen Hemminger @ 2012-11-13 17:53 UTC (permalink / raw)
  To: davem; +Cc: netdev
In-Reply-To: <20121113175304.628996029@vyatta.com>

[-- Attachment #1: bridge-port-flags-netlink.patch --]
[-- Type: text/plain, Size: 7734 bytes --]

Expose bridge port parameter over netlink. By switching to a nested
message, this can be used for other bridge parameters.

This changes IFLA_PROTINFO attribute from one byte to a full nested
set of attributes. This is safe for application interface because the
old message used IFLA_PROTINFO and new one uses
 IFLA_PROTINFO | NLA_F_NESTED.

The code adapts to old format requests, and therefore stays
compatible with user mode RSTP daemon. Since the type field
for nested and unnested attributes are different, and the old
code in libnetlink doesn't do the mask, it is also safe to use
with old versions of bridge monitor command.

Note: although mode is only a boolean, treating it as a
full byte since in the future someone will probably want to add more
values (like macvlan has).

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>

---
v2 - adapt to new bridge generic setlink infrastructure
     fix cost/priority width in policy

 include/uapi/linux/if_link.h |   10 ++
 net/bridge/br_netlink.c      |  145 ++++++++++++++++++++++++++++++++-----------
 2 files changed, 119 insertions(+), 36 deletions(-)

--- a/include/uapi/linux/if_link.h	2012-11-12 07:58:35.000000000 -0800
+++ b/include/uapi/linux/if_link.h	2012-11-12 13:33:53.558390820 -0800
@@ -205,6 +205,21 @@ enum {
 
 #define IFLA_INET6_MAX	(__IFLA_INET6_MAX - 1)
 
+enum {
+	BRIDGE_MODE_UNSPEC,
+	BRIDGE_MODE_HAIRPIN,
+};
+
+enum {
+	IFLA_BRPORT_UNSPEC,
+	IFLA_BRPORT_STATE,	/* Spanning tree state     */
+	IFLA_BRPORT_PRIORITY,	/* "             priority  */
+	IFLA_BRPORT_COST,	/* "             cost      */
+	IFLA_BRPORT_MODE,	/* mode (hairpin)          */
+	__IFLA_BRPORT_MAX
+};
+#define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
+
 struct ifla_cacheinfo {
 	__u32	max_reasm_len;
 	__u32	tstamp;		/* ipv6InterfaceTable updated timestamp */
--- a/net/bridge/br_netlink.c	2012-11-12 07:58:45.000000000 -0800
+++ b/net/bridge/br_netlink.c	2012-11-12 13:51:24.367861973 -0800
@@ -20,16 +20,39 @@
 #include "br_private.h"
 #include "br_private_stp.h"
 
+static inline size_t br_port_info_size(void)
+{
+	return nla_total_size(1)	/* IFLA_BRPORT_STATE  */
+		+ nla_total_size(2)	/* IFLA_BRPORT_PRIORITY */
+		+ nla_total_size(4)	/* IFLA_BRPORT_COST */
+		+ nla_total_size(1)	/* IFLA_BRPORT_MODE */
+		+ 0;
+}
+
 static inline size_t br_nlmsg_size(void)
 {
 	return NLMSG_ALIGN(sizeof(struct ifinfomsg))
-	       + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */
-	       + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */
-	       + nla_total_size(4) /* IFLA_MASTER */
-	       + nla_total_size(4) /* IFLA_MTU */
-	       + nla_total_size(4) /* IFLA_LINK */
-	       + nla_total_size(1) /* IFLA_OPERSTATE */
-	       + nla_total_size(1); /* IFLA_PROTINFO */
+		+ nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */
+		+ nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */
+		+ nla_total_size(4) /* IFLA_MASTER */
+		+ nla_total_size(4) /* IFLA_MTU */
+		+ nla_total_size(4) /* IFLA_LINK */
+		+ nla_total_size(1) /* IFLA_OPERSTATE */
+		+ nla_total_size(br_port_info_size()); /* IFLA_PROTINFO */
+}
+
+static int br_port_fill_attrs(struct sk_buff *skb,
+			      const struct net_bridge_port *p)
+{
+	u8 mode = !!(p->flags & BR_HAIRPIN_MODE);
+
+	if (nla_put_u8(skb, IFLA_BRPORT_STATE, p->state) ||
+	    nla_put_u16(skb, IFLA_BRPORT_PRIORITY, p->priority) ||
+	    nla_put_u32(skb, IFLA_BRPORT_COST, p->path_cost) ||
+	    nla_put_u8(skb, IFLA_BRPORT_MODE, mode))
+		return -EMSGSIZE;
+
+	return 0;
 }
 
 /*
@@ -67,10 +90,18 @@ static int br_fill_ifinfo(struct sk_buff
 	    (dev->addr_len &&
 	     nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) ||
 	    (dev->ifindex != dev->iflink &&
-	     nla_put_u32(skb, IFLA_LINK, dev->iflink)) ||
-	    (event == RTM_NEWLINK &&
-	     nla_put_u8(skb, IFLA_PROTINFO, port->state)))
+	     nla_put_u32(skb, IFLA_LINK, dev->iflink)))
 		goto nla_put_failure;
+
+	if (event == RTM_NEWLINK) {
+		struct nlattr *nest
+			= nla_nest_start(skb, IFLA_PROTINFO | NLA_F_NESTED);
+
+		if (nest == NULL || br_port_fill_attrs(skb, port) < 0)
+			goto nla_put_failure;
+		nla_nest_end(skb, nest);
+	}
+
 	return nlmsg_end(skb, nlh);
 
 nla_put_failure:
@@ -126,49 +157,117 @@ out:
 	return err;
 }
 
-/*
- * Change state of port (ie from forwarding to blocking etc)
- * Used by spanning tree in user space.
- */
-int br_setlink(struct net_device *dev, struct nlmsghdr *nlh)
-{
-	struct ifinfomsg *ifm;
-	struct nlattr *protinfo;
-	struct net_bridge_port *p;
-	u8 new_state;
-
-	ifm = nlmsg_data(nlh);
+static const struct nla_policy ifla_brport_policy[IFLA_BRPORT_MAX + 1] = {
+	[IFLA_BRPORT_STATE]	= { .type = NLA_U8 },
+	[IFLA_BRPORT_COST]	= { .type = NLA_U32 },
+	[IFLA_BRPORT_PRIORITY]	= { .type = NLA_U16 },
+	[IFLA_BRPORT_MODE]	= { .type = NLA_U8 },
+};
 
-	protinfo = nlmsg_find_attr(nlh, sizeof(*ifm), IFLA_PROTINFO);
-	if (!protinfo || nla_len(protinfo) < sizeof(u8))
-		return -EINVAL;
-
-	new_state = nla_get_u8(protinfo);
-	if (new_state > BR_STATE_BLOCKING)
-		return -EINVAL;
-
-	p = br_port_get_rtnl(dev);
-	if (!p)
+/* Change the state of the port and notify spanning tree */
+static int br_set_port_state(struct net_bridge_port *p, u8 state)
+{
+	if (state > BR_STATE_BLOCKING)
 		return -EINVAL;
 
 	/* if kernel STP is running, don't allow changes */
 	if (p->br->stp_enabled == BR_KERNEL_STP)
 		return -EBUSY;
 
-	if (!netif_running(dev) ||
-	    (!netif_carrier_ok(dev) && new_state != BR_STATE_DISABLED))
+	if (!netif_running(p->dev) ||
+	    (!netif_carrier_ok(p->dev) && state != BR_STATE_DISABLED))
 		return -ENETDOWN;
 
-	p->state = new_state;
+	p->state = state;
 	br_log_state(p);
-
-	spin_lock_bh(&p->br->lock);
 	br_port_state_selection(p->br);
-	spin_unlock_bh(&p->br->lock);
+	return 0;
+}
+
+/* Set/clear or port flags based on attribute */
+static void br_set_port_flag(struct net_bridge_port *p, struct nlattr *tb[],
+			   int attrtype, unsigned long mask)
+{
+	if (tb[attrtype]) {
+		u8 flag = nla_get_u8(tb[attrtype]);
+		if (flag)
+			p->flags |= mask;
+		else
+			p->flags &= ~mask;
+	}
+}
+
+/* Process bridge protocol info on port */
+static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
+{
+	int err;
 
+	br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE);
+
+	if (tb[IFLA_BRPORT_COST]) {
+		err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST]));
+		if (err)
+			return err;
+	}
+
+	if (tb[IFLA_BRPORT_PRIORITY]) {
+		err = br_stp_set_port_priority(p, nla_get_u16(tb[IFLA_BRPORT_PRIORITY]));
+		if (err)
+			return err;
+	}
+
+	if (tb[IFLA_BRPORT_STATE]) {
+		err = br_set_port_state(p, nla_get_u8(tb[IFLA_BRPORT_STATE]));
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
+/* Change state and parameters on port. */
+int br_setlink(struct net_device *dev, struct nlmsghdr *nlh)
+{
+	struct ifinfomsg *ifm;
+	struct nlattr *protinfo;
+	struct net_bridge_port *p;
+	struct nlattr *tb[IFLA_BRPORT_MAX];
+	int err;
+
+	ifm = nlmsg_data(nlh);
+
+	protinfo = nlmsg_find_attr(nlh, sizeof(*ifm), IFLA_PROTINFO);
+	if (!protinfo)
+		return 0;
+
+ 	p = br_port_get_rtnl(dev);
+	if (!p)
+		return -EINVAL;
+
+	if (protinfo->nla_type & NLA_F_NESTED) {
+		err = nla_parse_nested(tb, IFLA_BRPORT_MAX,
+				       protinfo, ifla_brport_policy);
+		if (err)
+			return err;
+
+		spin_lock_bh(&p->br->lock);
+		err = br_setport(p, tb);
+		spin_unlock_bh(&p->br->lock);
+	} else {
+		/* Binary compatability with old RSTP */
+		if (nla_len(protinfo) < sizeof(u8))
+			return -EINVAL;
+
+		spin_lock_bh(&p->br->lock);
+		err = br_set_port_state(p, nla_get_u8(protinfo));
+		spin_unlock_bh(&p->br->lock);
+	}
+
+	if (err == 0)
+		br_ifinfo_notify(RTM_NEWLINK, p);
+
+	return err;
+}
+
 static int br_validate(struct nlattr *tb[], struct nlattr *data[])
 {
 	if (tb[IFLA_ADDRESS]) {

^ permalink raw reply

* Re: [PATCH 2/2] smsc95xx: set MII_BUSY bit to read/write PHY regs
From: Steve Glendinning @ 2012-11-13 17:44 UTC (permalink / raw)
  To: David Miller; +Cc: netdev
In-Reply-To: <20121109.160850.901809648224300452.davem@davemloft.net>

> Steve please let me know why you only submitted patch #2
> of an apparent 2 part series.

My bad being sloppy when formatting the patch for submission, sorry.
The first patch in my rebased tree was one you've already accepted
into net but hadn't pulled into net-next yet.  I just sent the second
one, and I forgot to remove the 2/2 from it.

They don't depend on each other, they're independent bugfixes.

Sorry again for the sloppyness.

^ permalink raw reply

* Re: [net-next 01/11] ixgbe: Do not use DCA to prefetch the entire packet into the cache
From: Alexander Duyck @ 2012-11-13 17:41 UTC (permalink / raw)
  To: Eric Dumazet; +Cc: Jeff Kirsher, davem, netdev, gospo, sassmann
In-Reply-To: <1352816011.6185.33.camel@edumazet-glaptop>

On 11/13/2012 06:13 AM, Eric Dumazet wrote:
> On Tue, 2012-11-13 at 06:03 -0800, Jeff Kirsher wrote:
>> From: Alexander Duyck <alexander.h.duyck@intel.com>
>>
>> The way the code was previously written it was causing DCA to prefetch the
>> entire packet into the cache when it was enabled.  That is excessive as we
>> only really need the headers.
>>
>> We are now prefetching the headers via software so doing this from DCA would
>> be redundant anyway.  So clear the bit that was causing us to prefetch the
>> packet data and instead only use DCA for the descriptor rings.
>>
>> Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
>> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
>> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
>> ---
> Excellent !
>
> My own ixgbe cards are moving so I cant test this, do you guys have some
> numbers to share ?
>
> Thanks

In my tests I saw no real change because of the DCA changes.  I kind of
suspected that would be the case as mentioned in the patch the prefetch
and DCA were both doing the same thing so by dropping the extra DCA
prefetch I am just polluting the case less.

I have a similar set of changes for the ixgbe transmit path that are
similar to the changes I made to igb in this patch set.  Those are a bit
more interesting as they actually decreased the ixgbe_xmit_frame_ring
function overhead for some of my tests by something like 15%.

Thanks,

Alex

^ permalink raw reply

* Re: [net-next PATCH v2 0/3] extend set/get netlink for embedded
From: John Fastabend @ 2012-11-13 17:16 UTC (permalink / raw)
  To: Ariel Elior
  Cc: shemminger@vyatta.com, buytenh@wantstofly.org,
	davem@davemloft.net, vyasevic@redhat.com, jhs@mojatatu.com,
	chrisw@redhat.com, krkumar2@in.ibm.com, samudrala@us.ibm.com,
	peter.p.waskiewicz.jr@intel.com, jeffrey.t.kirsher@intel.com,
	netdev@vger.kernel.org, bhutchings@solarflare.com,
	gregory.v.rose@intel.com, Eilon Greenstein
In-Reply-To: <6AE768456CEC4B4A9B2248CB6B87EB3E1BC95245@SJEXCHMB05.corp.ad.broadcom.com>

>
> This series looks fine from bnx2x point of view.
> The dynamic change from VEB to VEPA will require a firmware change,
> so we might arrive a little late for the party.
> Ariel
>

In the meantime you could enable just the get routines
so the upper layer could learn how your SR-IOV switching
is being done or not done.

My basic expectation is hardware defaults to VEB but
not sure if that is true in all cases.

.John

^ permalink raw reply

* [REGRESSION] r8169: jumbo fixes caused jumbo regressions!
From: Kirill Smelkov @ 2012-11-13 17:06 UTC (permalink / raw)
  To: Francois Romieu
  Cc: Realtek linux nic maintainers, Hayes Wang, David S. Miller,
	Greg Kroah-Hartman, netdev


Short description:

    I run net-next on my netbook with yukon2 ethernet controller and stable-3.0
    at work with pcie realtek network chips on several hosts. Upgrading from
    3.0.45 to 3.0.46 there revealed jumbo-related regression, because of

        r8169: jumbo fixes.

    which is

        cc669c37ba4a9c5c54c7842d0c9428aab64d62d7 at stable-3.0, and
        d58d46b5d85139d18eb939aa7279c160bab70484 upstream

    The problem is it is no longer possible to use 7200 mtu and tx checksum
    offload. Both features used to work without problems.


Details
-------

I have two machines with realtek chips in them. They are

    eth0: RTL8168cp/8111cp at 0xdffb8000, 00:18:7d:11:83:2b, XID 1cb00080 IRQ 16
    Ethernet controller: Realtek Semiconductor Co., Ltd. RTL8111/8168B PCI Express Gigabit Ethernet controller (rev 02)

and

    eth0: RTL8168c/8111c at 0xf8062000, 00:22:15:90:7e:c6, XID 1c4000c0 IRQ 17
    Ethernet controller: Realtek Semiconductor Co., Ltd. RTL8111/8168B PCI Express Gigabit Ethernet controller (rev 02)


Visually looking at chips, I can confirm that they are labelled as RTL8111CP
and RTL8111C accordingly.

I used to set mtu=7200 and turn tx checksum offload on on them and
transmit/receive almost gigabit traffic from/to either of them without a
problem. This worked fine until upgrade from 3.0.45 to 3.0.46 where
things broke - now for both devices r8169 driver says:

    eth0: jumbo features [frames: 6128 bytes, tx checksumming: ko]

i.e. only 6128 max mtu and no support for tx checksum offload.

Indeed, for one thing the patch says tx checksumming cannot work together with
jumbo frames:

commit cc669c37ba4a9c5c54c7842d0c9428aab64d62d7
Author:     Francois Romieu <romieu@fr.zoreil.com>
AuthorDate: Fri Oct 5 23:29:11 2012 +0200
Commit:     Greg Kroah-Hartman <gregkh@linuxfoundation.org>
CommitDate: Sat Oct 13 05:28:12 2012 +0900

    r8169: jumbo fixes.
    
    commit d58d46b5d85139d18eb939aa7279c160bab70484 upstream.
    
    - fix features : jumbo frames and checksumming can not be used at the
      same time.
    
    - introduce hw_jumbo_{enable / disable} helpers. Their content has been
      creatively extracted from Realtek's own drivers. As an illustration,
      it would be nice to know how/if the MaxTxPacketSize register operates
      when the device can work with a 9k jumbo frame as its documentation
      (8168c) can not be applied beyond ~7k.
    
    - rtl_tx_performance_tweak is moved forward. No change.
    
    Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
    Acked-by: David S. Miller <davem@davemloft.net>
    Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>


but again, I say that up till now I've used ~7K jumbos with tx checksum offload
just fine on those chips:

My test is to stream raw video from 8 PAL cameras to net - 4 for 720x576@25 and
4 for 360x288@25 which for YUYV format occupies ~ 860 Mbps of bandwidth. The
program to transmit/receive video is here: http://repo.or.cz/w/rawv.git

For video sources vivi.ko video driver is used with fps set to 25.  The
streams are generated with

    $ rawv -d /dev/video$X,720x576 -t 239.255.17.$X:1200$X  # X=1..4, 5834 eth framelen
    $ rawv -d /dev/video$X,360x288 -t 239.255.17.$X:1200$X  # X=5..8, 6554 eth framelen

(which is more than 6K jumbos for the second case), and also to come
close to 7K limit with

    $ rawv -d /dev/video$X,708x576 -t 239.255.17.$X:1200$X  # X=1..4, 7154 eth framelen
    $ rawv -d /dev/video$X,352x288 -t 239.255.17.$X:1200$X  # X=5..8, 7114 eth framelen

This used to work fine with mtu set to 7200 or 7152 (=7152+14+2 =7168 =1024*7
max eth framelen) and tx csum offload turned on via `ethtool -K eth0 tx on`.


Patching the driver to know "true xid"

diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c
index f7a56f4..247a238 100644
--- a/drivers/net/r8169.c
+++ b/drivers/net/r8169.c
@@ -1773,6 +1778,7 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp,
        reg = RTL_R32(TxConfig);
        while ((reg & p->mask) != p->val)
                p++;
+       dprintk("mac_version for 0x%08x (0x%08x): %i\n", reg, reg & 0x9cf0f8ff,p->mac_version);
        tp->mac_version = p->mac_version;
 
        if (tp->mac_version == RTL_GIGA_MAC_NONE) {


I've found that RTL_R32(TxConfig) is 0x3fb00080 and 0x3f4006c0 for my chips.
This gives RTL_GIGA_MAC_VER_24 and RTL_GIGA_MAC_VER_22 judging by table in
rtl8169_get_mac_version().

Then I'm now running 3.0.46 kernel with the following patch applied

diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c
index f7a56f4..247a238 100644
--- a/drivers/net/r8169.c
+++ b/drivers/net/r8169.c
@@ -210,11 +212,11 @@ static const struct {
        [RTL_GIGA_MAC_VER_21] =
                _R("RTL8168c/8111c",    RTL_TD_1, NULL, JUMBO_6K, false),
        [RTL_GIGA_MAC_VER_22] =
-               _R("RTL8168c/8111c",    RTL_TD_1, NULL, JUMBO_6K, false),
+               _R("RTL8168c/8111c",    RTL_TD_1, NULL, JUMBO_7K, true),
        [RTL_GIGA_MAC_VER_23] =
                _R("RTL8168cp/8111cp",  RTL_TD_1, NULL, JUMBO_6K, false),
        [RTL_GIGA_MAC_VER_24] =
-               _R("RTL8168cp/8111cp",  RTL_TD_1, NULL, JUMBO_6K, false),
+               _R("RTL8168cp/8111cp",  RTL_TD_1, NULL, JUMBO_7K, true),
        [RTL_GIGA_MAC_VER_25] =
                _R("RTL8168d/8111d",    RTL_TD_1, FIRMWARE_8168D_1,
                                                        JUMBO_9K, false),


and ~7K jumbos and tx csum offload work again.
(by the way, on atom system, without tx csum offload, half of cpu time
is spent only to calculate checksums...)


Now I wonder, where that 6K limit came from and why they say it is now
not possible to use jumbos together with tx csum offload? Is my testing
enough to justify raising the limits and allowing tx offload? If yes,
then how do we handle this regression?


Thanks,
Kirill


P.S. Just for info: I've also tried, but on both my chips 9K jumbos do
not work.

^ permalink raw reply related

* Re: SR-IOV problem with Intel 82599EB (not enough MMIO resources for SR-IOV)
From: Don Dutile @ 2012-11-13 16:40 UTC (permalink / raw)
  To: Li, Sibai
  Cc: Jason Gao, bhelgaas@google.com, Rose, Gregory V,
	Kirsher, Jeffrey T, linux-kernel, netdev, kvm,
	e1000-devel@lists.sourceforge.net, linux-pci@vger.kernel.org,
	Yinghai Lu
In-Reply-To: <A3A921390EAE4044940E99EBF13D97321AE21E15@FMSMSX104.amr.corp.intel.com>

On 11/13/2012 11:04 AM, Li, Sibai wrote:
>
>
>> -----Original Message-----
>> From: Jason Gao [mailto:pkill.2012@gmail.com]
>> Sent: Tuesday, November 13, 2012 5:38 AM
>> To: bhelgaas@google.com; Rose, Gregory V; Li, Sibai
>> Cc: ddutile@redhat.com; Kirsher, Jeffrey T; linux-kernel; netdev; kvm; e1000-
>> devel@lists.sourceforge.net; linux-pci@vger.kernel.org; Yinghai Lu
>> Subject: Re: SR-IOV problem with Intel 82599EB (not enough MMIO resources
>> for SR-IOV)
>>
>> I'm very sorry for delayed reply.now SR-IOV works for me in Centos 6.3,thank all
>> of you.
>>
>>
>> On Fri, Nov 9, 2012 at 11:26 PM, Bjorn Helgaas<bhelgaas@google.com>  wrote:
>>> Linux normally uses the resource assignments done by the BIOS, but it
>>> is possible for the kernel to reassign those.  We don't have good
>>> automatic support for that yet, but on a recent upstream kernel, you
>>> can try "pci=realloc".  I doubt this option is in CentOS 6.3, though
>>
>> Thank you very much,I try "pci=realloc" in Centos 6.3,and now it works for me.
>>
>>
>>
>> On Sat, Nov 10, 2012 at 2:08 AM, Li, Sibai<sibai.li@intel.com>  wrote:
>>> DellR710 with the latest BIOS should work fine for SR-IOV. My BIOS is
>>> v.6.3.0 and release date is 07/24/2012 Please check if you configured
>> intel_iommu=on in the grub.conf file.
>>> If you did, check your kernel .config file under Device Drivers->  IOMMU
>> Hardware support->enable Support for Intel IOMMU using DMA remapping
>> Devices, enable Intel DMA Remapping Devices by Default, enable Support for
>> Interrupt Remapping.
>>
>> thank you Sibai,Our server "Dell R710",its BIOS version is just
>> v.6.3.0 and release date is 07/24/2012,and I also configured intel_iommu=on in
>> the grub.conf file,but I can't find these IOMMU options in "Device Drivers" in my
Sibai is referring to kernel config options.  RHEL6.3 has the IOMMU options built into
the kernel, but not enabled by default -- have to add 'intel_iommu=on' to the kernel
cmdline to enable IOMMU. SRIOV support (CONFIG_IOV) is built into the RHEL6.3 kernel as well.

>> kernel(2.6.32-279) .config file , btw my os is Centos 6.3(RHEL6.3),although the
>> problem solved,I'd like to know what's your os version ,kernel version?
>
> I am using RHEL6.3 with unstable kernel 3.7.0-rc
> --
> To unsubscribe from this list: send the line "unsubscribe linux-pci" 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: [PATCH 00/20] bnx2x: support SR-IOV
From: Ariel Elior @ 2012-11-13 16:20 UTC (permalink / raw)
  To: Ariel Elior, David Miller; +Cc: netdev
In-Reply-To: <1352823451-27042-1-git-send-email-ariele@broadcom.com>

> -----Original Message-----
> From: Ariel Elior [mailto:ariele@broadcom.com]
> Sent: Tuesday, November 13, 2012 6:17 PM
> To: David Miller
> Cc: netdev; Ariel Elior
> Subject: [PATCH 00/20] bnx2x: support SR-IOV
> 
> Please consider applying these patches.
To net-next, of course

^ permalink raw reply

* net, bluetooth: object debug warning in bt_host_release()
From: Sasha Levin @ 2012-11-13 16:18 UTC (permalink / raw)
  To: marcel, gustavo, Johan Hedberg, David S. Miller
  Cc: linux-bluetooth, netdev, linux-kernel@vger.kernel.org, Dave Jones

Hi all,

While fuzzing with trinity on a KVM tools (lkvm) guest running latest -next kernel I've
stumbled on the following:

[ 1434.201149] ------------[ cut here ]------------
[ 1434.204998] WARNING: at lib/debugobjects.c:261 debug_print_object+0x8e/0xb0()
[ 1434.208324] ODEBUG: free active (active state 0) object type: work_struct hint: hci_power_on+0x0/0x90
[ 1434.210386] Pid: 8564, comm: trinity-child25 Tainted: G        W    3.7.0-rc5-next-20121112-sasha-00018-g2f4ce0e #127
[ 1434.210760] Call Trace:
[ 1434.210760]  [<ffffffff819f3d6e>] ? debug_print_object+0x8e/0xb0
[ 1434.210760]  [<ffffffff8110b887>] warn_slowpath_common+0x87/0xb0
[ 1434.210760]  [<ffffffff8110b911>] warn_slowpath_fmt+0x41/0x50
[ 1434.210760]  [<ffffffff819f3d6e>] debug_print_object+0x8e/0xb0
[ 1434.210760]  [<ffffffff8376b750>] ? hci_dev_open+0x310/0x310
[ 1434.210760]  [<ffffffff83bf94e5>] ? _raw_spin_unlock_irqrestore+0x55/0xa0
[ 1434.210760]  [<ffffffff819f3ee5>] __debug_check_no_obj_freed+0xa5/0x230
[ 1434.210760]  [<ffffffff83785db0>] ? bt_host_release+0x10/0x20
[ 1434.210760]  [<ffffffff819f4d15>] debug_check_no_obj_freed+0x15/0x20
[ 1434.210760]  [<ffffffff8125eee7>] kfree+0x227/0x330
[ 1434.210760]  [<ffffffff83785db0>] bt_host_release+0x10/0x20
[ 1434.210760]  [<ffffffff81e539e5>] device_release+0x65/0xc0
[ 1434.210760]  [<ffffffff819d3975>] kobject_cleanup+0x145/0x190
[ 1434.210760]  [<ffffffff819d39cd>] kobject_release+0xd/0x10
[ 1434.210760]  [<ffffffff819d33cc>] kobject_put+0x4c/0x60
[ 1434.210760]  [<ffffffff81e548b2>] put_device+0x12/0x20
[ 1434.210760]  [<ffffffff8376a334>] hci_free_dev+0x24/0x30
[ 1434.210760]  [<ffffffff82fd8fe1>] vhci_release+0x31/0x60
[ 1434.210760]  [<ffffffff8127be12>] __fput+0x122/0x250
[ 1434.210760]  [<ffffffff811cab0d>] ? rcu_user_exit+0x9d/0xd0
[ 1434.210760]  [<ffffffff8127bf49>] ____fput+0x9/0x10
[ 1434.210760]  [<ffffffff81133402>] task_work_run+0xb2/0xf0
[ 1434.210760]  [<ffffffff8106cfa7>] do_notify_resume+0x77/0xa0
[ 1434.210760]  [<ffffffff83bfb0ea>] int_signal+0x12/0x17
[ 1434.210760] ---[ end trace a6d57fefbc8a8cc7 ]---

Not that the guest doesn't emulate anything that looks like a bluetooth device or
has bluetooth capabilities.


Thanks,
Sasha

^ permalink raw reply

* [PATCH 20/22] bnx2x: Support VF FLR
From: Ariel Elior @ 2012-11-13 16:17 UTC (permalink / raw)
  To: David Miller; +Cc: netdev, Ariel Elior, Eilon Greenstein
In-Reply-To: <1352823451-27042-1-git-send-email-ariele@broadcom.com>

The FLR indication arrives as an attention from the management processor.
Upon VF flr all FLRed function in the indication have already been
released by Firmware and now we basically need to free the resources
allocated to those VFs, and clean any remainders from the device
(FLR final cleanup).

Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x.h       |    6 +
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c  |   19 +-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h   |    1 +
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c |  295 ++++++++++++++++++++-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h |    7 +
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h  |    1 +
 6 files changed, 321 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 88dbf02..dfae9b0 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -1880,7 +1880,13 @@ void bnx2x_prep_dmae_with_comp(struct bnx2x *bp, struct dmae_command *dmae,
 int bnx2x_issue_dmae_with_comp(struct bnx2x *bp, struct dmae_command *dmae);
 void bnx2x_dp_dmae(struct bnx2x *bp, struct dmae_command *dmae, int msglvl);
 
+/* FLR related routines */
+u32 bnx2x_flr_clnup_poll_count(struct bnx2x *bp);
+void bnx2x_tx_hw_flushed(struct bnx2x *bp, u32 poll_count);
+int bnx2x_send_final_clnup(struct bnx2x *bp, u8 clnup_func, u32 poll_cnt);
 u8 bnx2x_is_pcie_pending(struct pci_dev *dev);
+int bnx2x_flr_clnup_poll_hw_counter(struct bnx2x *bp, u32 reg,
+				    char *msg, u32 poll_cnt);
 
 void bnx2x_calc_fc_adv(struct bnx2x *bp);
 int bnx2x_sp_post(struct bnx2x *bp, int command, int cid,
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 4418bc4..05aef19 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -1096,8 +1096,8 @@ static u32 bnx2x_flr_clnup_reg_poll(struct bnx2x *bp, u32 reg,
 	return val;
 }
 
-static int bnx2x_flr_clnup_poll_hw_counter(struct bnx2x *bp, u32 reg,
-					   char *msg, u32 poll_cnt)
+int bnx2x_flr_clnup_poll_hw_counter(struct bnx2x *bp, u32 reg,
+				    char *msg, u32 poll_cnt)
 {
 	u32 val = bnx2x_flr_clnup_reg_poll(bp, reg, 0, poll_cnt);
 	if (val != 0) {
@@ -1107,7 +1107,8 @@ static int bnx2x_flr_clnup_poll_hw_counter(struct bnx2x *bp, u32 reg,
 	return 0;
 }
 
-static u32 bnx2x_flr_clnup_poll_count(struct bnx2x *bp)
+/* Common routines with VF FLR cleanup */
+u32 bnx2x_flr_clnup_poll_count(struct bnx2x *bp)
 {
 	/* adjust polling timeout */
 	if (CHIP_REV_IS_EMUL(bp))
@@ -1119,7 +1120,7 @@ static u32 bnx2x_flr_clnup_poll_count(struct bnx2x *bp)
 	return FLR_POLL_CNT;
 }
 
-static void bnx2x_tx_hw_flushed(struct bnx2x *bp, u32 poll_count)
+void bnx2x_tx_hw_flushed(struct bnx2x *bp, u32 poll_count)
 {
 	struct pbf_pN_cmd_regs cmd_regs[] = {
 		{0, (CHIP_IS_E3B0(bp)) ?
@@ -1194,8 +1195,7 @@ static void bnx2x_tx_hw_flushed(struct bnx2x *bp, u32 poll_count)
 	(((index) << SDM_OP_GEN_AGG_VECT_IDX_SHIFT) & SDM_OP_GEN_AGG_VECT_IDX)
 
 
-static int bnx2x_send_final_clnup(struct bnx2x *bp, u8 clnup_func,
-					 u32 poll_cnt)
+int bnx2x_send_final_clnup(struct bnx2x *bp, u8 clnup_func, u32 poll_cnt)
 {
 	struct sdm_op_gen op_gen = {0};
 
@@ -1220,7 +1220,8 @@ static int bnx2x_send_final_clnup(struct bnx2x *bp, u8 clnup_func,
 		BNX2X_ERR("FW final cleanup did not succeed\n");
 		DP(BNX2X_MSG_SP, "At timeout completion address contained %x\n",
 		   (REG_RD(bp, comp_addr)));
-		ret = 1;
+		bnx2x_panic();
+		return 1;
 	}
 	/* Zero completion for nxt FLR */
 	REG_WR(bp, comp_addr, 0);
@@ -3884,6 +3885,10 @@ static void bnx2x_attn_int_deasserted3(struct bnx2x *bp, u32 attn)
 
 			if (val & DRV_STATUS_DRV_INFO_REQ)
 				bnx2x_handle_drv_info_req(bp);
+
+			if (val & DRV_STATUS_VF_DISABLED)
+				bnx2x_vf_handle_flr_event(bp);
+
 			if ((bp->port.pmf == 0) && (val & DRV_STATUS_PMF))
 				bnx2x_pmf_update(bp);
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
index 3997f63..823d1b6 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
@@ -876,6 +876,7 @@
 #define HC_CONFIG_0_REG_MSI_MSIX_INT_EN_0			 (0x1<<2)
 #define HC_CONFIG_0_REG_SINGLE_ISR_EN_0				 (0x1<<1)
 #define HC_CONFIG_1_REG_BLOCK_DISABLE_1				 (0x1<<0)
+#define DORQ_REG_VF_USAGE_CNT					 0x170320
 #define HC_REG_AGG_INT_0					 0x108050
 #define HC_REG_AGG_INT_1					 0x108054
 #define HC_REG_ATTN_BIT 					 0x108120
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index f083b5d..ee02374 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -137,6 +137,17 @@ enum bnx2x_vfop_mcast_state {
 	   BNX2X_VFOP_MCAST_ADD,
 	   BNX2X_VFOP_MCAST_CHK_DONE
 };
+enum bnx2x_vfop_qflr_state {
+	   BNX2X_VFOP_QFLR_CLR_VLAN,
+	   BNX2X_VFOP_QFLR_CLR_MAC,
+	   BNX2X_VFOP_QFLR_TERMINATE,
+	   BNX2X_VFOP_QFLR_DONE
+};
+
+enum bnx2x_vfop_flr_state {
+	   BNX2X_VFOP_FLR_QUEUES,
+	   BNX2X_VFOP_FLR_HW
+};
 
 enum bnx2x_vfop_close_state {
 	   BNX2X_VFOP_CLOSE_QUEUES,
@@ -974,6 +985,93 @@ int bnx2x_vfop_qsetup_cmd(struct bnx2x *bp,
 	return -ENOMEM;
 }
 
+/* VFOP queue FLR handling (clear vlans, clear macs, queue destructor) */
+static void bnx2x_vfop_qflr(struct bnx2x *bp, struct bnx2x_virtf *vf)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
+	int qid = vfop->args.qx.qid;
+	enum bnx2x_vfop_qflr_state state = vfop->state;
+	struct bnx2x_queue_state_params *qstate;
+	struct bnx2x_vfop_cmd cmd;
+
+	bnx2x_vfop_reset_wq(vf);
+
+	if (vfop->rc < 0)
+		goto op_err;
+
+	DP(BNX2X_MSG_IOV, "VF[%d] STATE: %d\n", vf->abs_vfid, state);
+
+	cmd.done = bnx2x_vfop_qflr;
+	cmd.block = false;
+
+	switch (state) {
+	case BNX2X_VFOP_QFLR_CLR_VLAN:
+		/* vlan-clear-all: driver-only, don't consume credit */
+		vfop->state = BNX2X_VFOP_QFLR_CLR_MAC;
+		vfop->rc = bnx2x_vfop_vlan_delall_cmd(bp, vf, &cmd, qid, true);
+		if (vfop->rc)
+			goto op_err;
+		return;
+
+	case BNX2X_VFOP_QFLR_CLR_MAC:
+		/* mac-clear-all: driver only consume credit */
+		vfop->state = BNX2X_VFOP_QFLR_TERMINATE;
+		vfop->rc = bnx2x_vfop_mac_delall_cmd(bp, vf, &cmd, qid, true);
+		DP(BNX2X_MSG_IOV,
+		   "VF[%d] vfop->rc after bnx2x_vfop_mac_delall_cmd was %d",
+		   vf->abs_vfid, vfop->rc);
+		if (vfop->rc)
+			goto op_err;
+		return;
+
+	case BNX2X_VFOP_QFLR_TERMINATE:
+		qstate = &vfop->op_p->qctor.qstate;
+		memset(qstate , 0, sizeof(*qstate));
+		qstate->q_obj = &bnx2x_vfq(vf, qid, sp_obj);
+		vfop->state = BNX2X_VFOP_QFLR_DONE;
+
+		DP(BNX2X_MSG_IOV, "VF[%d] qstate during flr was %d",
+		   vf->abs_vfid, qstate->q_obj->state);
+
+		if (qstate->q_obj->state != BNX2X_Q_STATE_RESET) {
+			qstate->q_obj->state = BNX2X_Q_STATE_STOPPED;
+			qstate->cmd = BNX2X_Q_CMD_TERMINATE;
+			vfop->rc = bnx2x_queue_state_change(bp, qstate);
+			bnx2x_vfop_finalize(vf, vfop->rc, VFOP_VERIFY_PEND);
+		} else {
+			goto op_done;
+		}
+
+op_err:
+	BNX2X_ERR("QFLR[%d:%d] error: rc %d\n",
+		  vf->abs_vfid, qid, vfop->rc);
+op_done:
+	case BNX2X_VFOP_QFLR_DONE:
+		bnx2x_vfop_end(bp, vf, vfop);
+		return;
+	default:
+		bnx2x_vfop_default(state);
+	}
+op_pending:
+	return;
+}
+
+static int bnx2x_vfop_qflr_cmd(struct bnx2x *bp,
+			       struct bnx2x_virtf *vf,
+			       struct bnx2x_vfop_cmd *cmd,
+			       int qid)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+
+	if (vfop) {
+		vfop->args.qx.qid = qid;
+		bnx2x_vfop_opset(BNX2X_VFOP_QFLR_CLR_VLAN,
+				 bnx2x_vfop_qflr, cmd->done);
+		return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_qflr,
+					     cmd->block);
+	}
+	return -ENOMEM;
+}
 
 /* VFOP multi-casts */
 static void bnx2x_vfop_mcast(struct bnx2x *bp, struct bnx2x_virtf *vf)
@@ -1433,8 +1531,203 @@ static void bnx2x_vf_free_resc(struct bnx2x *bp, struct bnx2x_virtf *vf)
 	vf->state = VF_FREE;
 }
 
-/* called by bnx2x_init_hw_func, returns the next ilt line */
+static void bnx2x_vf_flr_clnup_hw(struct bnx2x *bp, struct bnx2x_virtf *vf)
+{
+	u32 poll_cnt = bnx2x_flr_clnup_poll_count(bp);
+
+	/* DQ usage counter */
+	bnx2x_pretend_func(bp, HW_VF_HANDLE(bp, vf->abs_vfid));
+	bnx2x_flr_clnup_poll_hw_counter(bp, DORQ_REG_VF_USAGE_CNT,
+					"DQ VF usage counter timed out",
+					poll_cnt);
+	bnx2x_pretend_func(bp, BP_ABS_FUNC(bp));
+
+	/* FW cleanup command - poll for the results */
+	if (bnx2x_send_final_clnup(bp, (u8)FW_VF_HANDLE(vf->abs_vfid),
+				   poll_cnt))
+		BNX2X_ERR("VF[%d] Final cleanup timed-out\n", vf->abs_vfid);
+
+	/* ATC cleanup */
+
+	/* verify TX hw is flushed */
+	bnx2x_tx_hw_flushed(bp, poll_cnt);
+
+}
+
+static void bnx2x_vfop_flr(struct bnx2x *bp, struct bnx2x_virtf *vf)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
+	struct bnx2x_vfop_args_qx *qx = &vfop->args.qx;
+	enum bnx2x_vfop_flr_state state = vfop->state;
+	struct bnx2x_vfop_cmd cmd = {
+		.done = bnx2x_vfop_flr,
+		.block = false,
+	};
+
+	if (vfop->rc < 0)
+		goto op_err;
+
+	DP(BNX2X_MSG_IOV, "vf[%d] STATE: %d\n", vf->abs_vfid, state);
 
+	switch (state) {
+	case BNX2X_VFOP_FLR_QUEUES:
+		/* the cleanup operations are valid if and only if the VF
+		 * was first acquired.
+		 */
+		if (++(qx->qid) < vf_rxq_count(vf)) {
+			vfop->rc = bnx2x_vfop_qflr_cmd(bp, vf, &cmd,
+						       qx->qid);
+			if (vfop->rc)
+				goto op_err;
+			return;
+		}
+		/* remove multicasts */
+		vfop->state = BNX2X_VFOP_FLR_HW;
+		vfop->rc = bnx2x_vfop_mcast_cmd(bp, vf, &cmd, NULL,
+						0, true);
+		if (vfop->rc)
+			goto op_err;
+		return;
+	case BNX2X_VFOP_FLR_HW:
+
+		/* dispatch final cleanup and wait for HW queues to flush */
+		bnx2x_vf_flr_clnup_hw(bp, vf);
+
+		/* release VF resources */
+		bnx2x_vf_free_resc(bp, vf);
+
+		/* re-open the mailbox */
+		bnx2x_vf_enable_mbx(bp, vf->abs_vfid);
+
+		goto op_done;
+	default:
+		bnx2x_vfop_default(state);
+	}
+op_err:
+	BNX2X_ERR("VF[%d] FLR error: rc %d\n", vf->abs_vfid, vfop->rc);
+op_done:
+	vf->flr_clnup_stage = VF_FLR_ACK;
+	bnx2x_vfop_end(bp, vf, vfop);
+	bnx2x_unlock_vf_pf_channel(bp, vf, CHANNEL_TLV_FLR);
+}
+
+static int bnx2x_vfop_flr_cmd(struct bnx2x *bp,
+			      struct bnx2x_virtf *vf,
+			      vfop_handler_t done)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+	if (vfop) {
+		vfop->args.qx.qid = -1; /* loop */
+		bnx2x_vfop_opset(BNX2X_VFOP_FLR_QUEUES,
+				 bnx2x_vfop_flr, done);
+		return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_flr, false);
+	}
+	return -ENOMEM;
+}
+
+void bnx2x_vf_flr_clnup(struct bnx2x *bp, struct bnx2x_virtf *prev_vf)
+{
+	int i = prev_vf ? prev_vf->index + 1 : 0;
+	struct bnx2x_virtf *vf;
+
+	/* find next VF to cleanup */
+next_vf_to_clean:
+	for (;
+	     i < BNX2X_NR_VIRTFN(bp) &&
+	     (bnx2x_vf(bp, i, state) != VF_RESET ||
+	      bnx2x_vf(bp, i, flr_clnup_stage) != VF_FLR_CLN);
+	     i++)
+		;
+
+	DP(BNX2X_MSG_IOV, "next vf to cleanup: %d. num of vfs: %d\n", i,
+	   BNX2X_NR_VIRTFN(bp));
+
+	if (i < BNX2X_NR_VIRTFN(bp)) {
+		vf = BP_VF(bp, i);
+
+		/* lock the vf pf channel */
+		bnx2x_lock_vf_pf_channel(bp, vf, CHANNEL_TLV_FLR);
+
+		/* invoke the VF FLR SM */
+		if (bnx2x_vfop_flr_cmd(bp, vf, bnx2x_vf_flr_clnup)) {
+			BNX2X_ERR("VF[%d]: FLR cleanup failed -ENOMEM\n",
+				  vf->abs_vfid);
+
+			/* mark the VF to be ACKED and continue */
+			vf->flr_clnup_stage = VF_FLR_ACK;
+			goto next_vf_to_clean;
+		}
+		return;
+	}
+
+	/* we are done, update vf records */
+	for_each_vf(bp, i) {
+		vf = BP_VF(bp, i);
+
+		if (vf->flr_clnup_stage != VF_FLR_ACK)
+			continue;
+
+		vf->flr_clnup_stage = VF_FLR_EPILOG;
+	}
+
+	/* Acknowledge the handled VFs.
+	 * we are acknowledge all the vfs which an flr was requested for, even
+	 * if amongst them there are such that we never opened, since the mcp
+	 * will interrupt us immediately again if we only ack some of the bits,
+	 * resulting in an endless loop. This can happen for example in KVM
+	 * where an 'all ones' flr request is sometimes given by hyper visor
+	 */
+	DP(BNX2X_MSG_MCP, "DRV_STATUS_VF_DISABLED ACK for vfs 0x%x 0x%x\n",
+	   bp->vfdb->flrd_vfs[0], bp->vfdb->flrd_vfs[1]);
+	for (i = 0; i < FLRD_VFS_DWORDS; i++)
+		SHMEM2_WR(bp, drv_ack_vf_disabled[BP_FW_MB_IDX(bp)][i],
+			  bp->vfdb->flrd_vfs[i]);
+
+	bnx2x_fw_command(bp, DRV_MSG_CODE_VF_DISABLED_DONE, 0);
+
+	/* clear the acked bits - better yet if the MCP implemented
+	 * write to clear semantics
+	 */
+	for (i = 0; i < FLRD_VFS_DWORDS; i++)
+		SHMEM2_WR(bp, drv_ack_vf_disabled[BP_FW_MB_IDX(bp)][i], 0);
+}
+
+void bnx2x_vf_handle_flr_event(struct bnx2x *bp)
+{
+	int i;
+
+	/* Read FLR'd VFs */
+	for (i = 0; i < FLRD_VFS_DWORDS; i++)
+		bp->vfdb->flrd_vfs[i] = SHMEM2_RD(bp, mcp_vf_disabled[i]);
+
+	DP(BNX2X_MSG_MCP,
+	   "DRV_STATUS_VF_DISABLED received for vfs 0x%x 0x%x\n",
+	   bp->vfdb->flrd_vfs[0], bp->vfdb->flrd_vfs[1]);
+
+	for_each_vf(bp, i) {
+		struct bnx2x_virtf *vf = BP_VF(bp, i);
+		u32 reset = 0;
+
+		if (vf->abs_vfid < 32)
+			reset = bp->vfdb->flrd_vfs[0] & (1 << vf->abs_vfid);
+		else
+			reset = bp->vfdb->flrd_vfs[1] &
+				(1 << (vf->abs_vfid - 32));
+
+		if (reset) {
+			/* set as reset and ready for cleanup */
+			vf->state = VF_RESET;
+			vf->flr_clnup_stage = VF_FLR_CLN;
+
+			DP(BNX2X_MSG_IOV,
+			   "Initiating Final cleanup for VF %d\n",
+			   vf->abs_vfid);
+		}
+	}
+
+	/* do the FLR cleanup for all marked VFs*/
+	bnx2x_vf_flr_clnup(bp, NULL);
+}
 /* IOV global initialization routines  */
 void bnx2x_iov_init_dq(struct bnx2x *bp)
 {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
index 3815b20..b4efa79 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
@@ -697,9 +697,16 @@ int bnx2x_vfop_release_cmd(struct bnx2x *bp,
 void bnx2x_vf_release(struct bnx2x *bp, struct bnx2x_virtf *vf, bool block);
 int bnx2x_vf_idx_by_abs_fid(struct bnx2x *bp, u16 abs_vfid);
 u8 bnx2x_vf_max_queue_cnt(struct bnx2x *bp, struct bnx2x_virtf *vf);
+
+/* FLR routines */
+
 /* VF FLR helpers */
 int bnx2x_vf_flr_clnup_epilog(struct bnx2x *bp, u8 abs_vfid);
 void bnx2x_vf_enable_access(struct bnx2x *bp, u8 abs_vfid);
+
+/* Handles an FLR (or VF_DISABLE) notification form the MCP */
+void bnx2x_vf_handle_flr_event(struct bnx2x *bp);
+
 void bnx2x_add_tlv(struct bnx2x *bp, void *tlvs_list, u16 offset, u16 type,
 		   u16 length);
 void bnx2x_vfpf_prep(struct bnx2x *bp, struct vfpf_first_tlv *first_tlv,
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h
index 13c76df..0cf6e7f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h
@@ -307,6 +307,7 @@ enum channel_tlvs {
 	   CHANNEL_TLV_RELEASE,
 	   CHANNEL_TLV_PF_RELEASE_VF,
 	   CHANNEL_TLV_LIST_END,
+	   CHANNEL_TLV_FLR,
 	   CHANNEL_TLV_MAX
 };
 
-- 
1.7.9.GIT

^ permalink raw reply related

* [PATCH 18/22] bnx2x: Support of PF driver of a VF close request
From: Ariel Elior @ 2012-11-13 16:17 UTC (permalink / raw)
  To: David Miller; +Cc: netdev, Ariel Elior, Eilon Greenstein
In-Reply-To: <1352823451-27042-1-git-send-email-ariele@broadcom.com>

The 'close' command is the opposite of an init request. Here the
queues of the VF are closed (if any are opened) and released.
This flow applies the 'q_teardown' flow on all the queues.
The VF state is changed by this request.
Interrupts are disabled for the VF when closed.

Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c |   96 +++++++++++++++++++++
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h |    4 +
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c  |   27 ++++++
 3 files changed, 127 insertions(+), 0 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index 2c1945e..71640f3 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -138,6 +138,11 @@ enum bnx2x_vfop_mcast_state {
 	   BNX2X_VFOP_MCAST_CHK_DONE
 };
 
+enum bnx2x_vfop_close_state {
+	   BNX2X_VFOP_CLOSE_QUEUES,
+	   BNX2X_VFOP_CLOSE_HW
+};
+
 enum bnx2x_vfop_rxmode_state {
 	   BNX2X_VFOP_RXMODE_CONFIG,
 	   BNX2X_VFOP_RXMODE_DONE
@@ -2302,6 +2307,28 @@ static void bnx2x_vf_qtbl_set_q(struct bnx2x *bp, u8 abs_vfid, u8 qid,
 	REG_WR(bp, reg, val);
 }
 
+static void bnx2x_vf_clr_qtbl(struct bnx2x *bp, struct bnx2x_virtf *vf)
+{
+	int i;
+
+	for_each_vfq(vf, i)
+		bnx2x_vf_qtbl_set_q(bp, vf->abs_vfid,
+				    vfq_qzone_id(vf, vfq_get(vf, i)), false);
+}
+
+static void bnx2x_vf_igu_disable(struct bnx2x *bp, struct bnx2x_virtf *vf)
+{
+	u32 val;
+
+	/* clear the VF configuration - pretend */
+	bnx2x_pretend_func(bp, HW_VF_HANDLE(bp, vf->abs_vfid));
+	val = REG_RD(bp, IGU_REG_VF_CONFIGURATION);
+	val &= ~(IGU_VF_CONF_MSI_MSIX_EN | IGU_VF_CONF_SINGLE_ISR_EN |
+		 IGU_VF_CONF_FUNC_EN | IGU_VF_CONF_PARENT_MASK);
+	REG_WR(bp, IGU_REG_VF_CONFIGURATION, val);
+	bnx2x_pretend_func(bp, BP_ABS_FUNC(bp));
+}
+
 
 inline
 u8 bnx2x_vf_max_queue_cnt(struct bnx2x *bp, struct bnx2x_virtf *vf)
@@ -2475,6 +2502,75 @@ int bnx2x_vf_init(struct bnx2x *bp, struct bnx2x_virtf *vf, dma_addr_t *sb_map)
 	return 0;
 }
 
+/* VFOP close (teardown the queues, delete mcasts and close HW) */
+static void bnx2x_vfop_close(struct bnx2x *bp, struct bnx2x_virtf *vf)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
+	struct bnx2x_vfop_args_qx *qx = &vfop->args.qx;
+	enum bnx2x_vfop_close_state state = vfop->state;
+	struct bnx2x_vfop_cmd cmd = {
+		.done = bnx2x_vfop_close,
+		.block = false,
+	};
+
+	if (vfop->rc < 0)
+		goto op_err;
+
+	DP(BNX2X_MSG_IOV, "vf[%d] STATE: %d\n", vf->abs_vfid, state);
+
+	switch (state) {
+	case BNX2X_VFOP_CLOSE_QUEUES:
+
+		if (++(qx->qid) < vf_rxq_count(vf)) {
+			vfop->rc = bnx2x_vfop_qdown_cmd(bp, vf, &cmd, qx->qid);
+			if (vfop->rc)
+				goto op_err;
+			return;
+		}
+
+		/* remove multicasts */
+		vfop->state = BNX2X_VFOP_CLOSE_HW;
+		vfop->rc = bnx2x_vfop_mcast_cmd(bp, vf, &cmd, NULL, 0, false);
+		if (vfop->rc)
+			goto op_err;
+		return;
+
+	case BNX2X_VFOP_CLOSE_HW:
+
+		/* disable the interrupts */
+		DP(BNX2X_MSG_IOV, "disabling igu\n");
+		bnx2x_vf_igu_disable(bp, vf);
+
+		/* disable the VF */
+		DP(BNX2X_MSG_IOV, "clearing qtbl\n");
+		bnx2x_vf_clr_qtbl(bp, vf);
+
+		goto op_done;
+	default:
+		bnx2x_vfop_default(state);
+	}
+op_err:
+	BNX2X_ERR("VF[%d] CLOSE error: rc %d\n", vf->abs_vfid, vfop->rc);
+op_done:
+	vf->state = VF_ACQUIRED;
+	DP(BNX2X_MSG_IOV, "set state to acquired\n");
+	bnx2x_vfop_end(bp, vf, vfop);
+}
+
+int bnx2x_vfop_close_cmd(struct bnx2x *bp,
+			 struct bnx2x_virtf *vf,
+			 struct bnx2x_vfop_cmd *cmd)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+	if (vfop) {
+		vfop->args.qx.qid = -1; /* loop */
+		bnx2x_vfop_opset(BNX2X_VFOP_CLOSE_QUEUES,
+				 bnx2x_vfop_close, cmd->done);
+		return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_close,
+					     cmd->block);
+	}
+	return -ENOMEM;
+}
 void bnx2x_lock_vf_pf_channel(struct bnx2x *bp, struct bnx2x_virtf *vf,
 			      enum channel_tlvs tlv)
 {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
index 5c3e921..3c81029 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
@@ -667,6 +667,10 @@ int bnx2x_vfop_rxmode_cmd(struct bnx2x *bp,
 			  struct bnx2x_vfop_cmd *cmd,
 			  int qid, unsigned long accept_flags);
 
+int bnx2x_vfop_close_cmd(struct bnx2x *bp,
+			 struct bnx2x_virtf *vf,
+			 struct bnx2x_vfop_cmd *cmd);
+
 int bnx2x_vf_idx_by_abs_fid(struct bnx2x *bp, u16 abs_vfid);
 u8 bnx2x_vf_max_queue_cnt(struct bnx2x *bp, struct bnx2x_virtf *vf);
 /* VF FLR helpers */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index 20c929a..acf5f54 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -814,6 +814,30 @@ static void bnx2x_vf_mbx_teardown_q(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		bnx2x_vf_mbx_resp(bp, vf);
 }
 
+/* Done handler for 'close' operation: send response and reopen the
+ * channel.
+ */
+static void bnx2x_vf_mbx_close_done(struct bnx2x *bp, struct bnx2x_virtf *vf)
+{
+	bnx2x_vf_mbx_resp(bp, vf);
+	bnx2x_vf_enable_mbx(bp, vf->abs_vfid);
+}
+
+static void bnx2x_vf_mbx_close_vf(struct bnx2x *bp, struct bnx2x_virtf *vf,
+				  struct bnx2x_vf_mbx *mbx)
+{
+	struct bnx2x_vfop_cmd cmd = {
+		.done = bnx2x_vf_mbx_close_done,
+		.block = false,
+	};
+
+	DP(BNX2X_MSG_IOV, "VF[%d] VF_CLOSE\n", vf->abs_vfid);
+
+	vf->op_rc = bnx2x_vfop_close_cmd(bp, vf, &cmd);
+	if (vf->op_rc)
+		bnx2x_vf_mbx_close_done(bp, vf);
+}
+
 /* dispatch request */
 static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 				  struct bnx2x_vf_mbx *mbx)
@@ -845,6 +869,9 @@ static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		case CHANNEL_TLV_TEARDOWN_Q:
 			bnx2x_vf_mbx_teardown_q(bp, vf, mbx);
 			break;
+		case CHANNEL_TLV_CLOSE:
+			bnx2x_vf_mbx_close_vf(bp, vf, mbx);
+			break;
 		}
 
 	/* unknown TLV - this may belong to a VF driver from the future - a
-- 
1.7.9.GIT

^ permalink raw reply related

* [PATCH 15/22] bnx2x: Support of PF driver of a VF setup_q request
From: Ariel Elior @ 2012-11-13 16:17 UTC (permalink / raw)
  To: David Miller; +Cc: netdev, Ariel Elior, Eilon Greenstein
In-Reply-To: <1352823451-27042-1-git-send-email-ariele@broadcom.com>

Upon receiving a 'setup_q' request from the VF over the VF <-> PF
channel the PF driver will open a corresponding queue in the
device. The PF driver configures the queue with appropriate mac
address, vlan configuration, etc from the VF.

Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x.h       |    1 +
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c   |   19 +-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c |  899 +++++++++++++++++----
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h |  178 ++++
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c  |  145 ++++
 5 files changed, 1071 insertions(+), 171 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 4d89ef6..88dbf02 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -972,6 +972,7 @@ extern struct workqueue_struct *bnx2x_wq;
 #define BNX2X_MAX_NUM_OF_VFS	64
 #define BNX2X_VF_CID_WND	0
 #define BNX2X_CIDS_PER_VF	(1 << BNX2X_VF_CID_WND)
+#define BNX2X_CLIENTS_PER_VF	1
 #define BNX2X_FIRST_VF_CID	256
 #define BNX2X_VF_CIDS		(BNX2X_MAX_NUM_OF_VFS * BNX2X_CIDS_PER_VF)
 #define BNX2X_VF_ID_INVALID	0xFF
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 6483979..a7165e1 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -2019,7 +2019,7 @@ static void bnx2x_free_fw_stats_mem(struct bnx2x *bp)
 
 static int bnx2x_alloc_fw_stats_mem(struct bnx2x *bp)
 {
-	int num_groups;
+	int num_groups, vf_headroom = 0;
 	int is_fcoe_stats = NO_FCOE(bp) ? 0 : 1;
 
 	/* number of queues for statistics is number of eth queues + FCoE */
@@ -2031,18 +2031,27 @@ static int bnx2x_alloc_fw_stats_mem(struct bnx2x *bp)
 	 * for fcoe l2 queue if applicable)
 	 */
 	bp->fw_stats_num = 2 + is_fcoe_stats + num_queue_stats;
+
+	/* vf stats appear in the request list, but their data is allocated by
+	 * the VFs themselves. We don't include them in the bp->fw_stats_num as
+	 * it is used to determine where to place the vf stats queries in the
+	 * request struct
+	 */
+	if (IS_SRIOV(bp))
+		vf_headroom = bp->vfdb->sriov.nr_virtfn * BNX2X_CLIENTS_PER_VF;
+
 	/* Request is built from stats_query_header and an array of
 	 * stats_query_cmd_group each of which contains
 	 * STATS_QUERY_CMD_COUNT rules. The real number or requests is
 	 * configured in the stats_query_header.
 	 */
 	num_groups =
-		(((bp->fw_stats_num) / STATS_QUERY_CMD_COUNT) +
-		 (((bp->fw_stats_num) % STATS_QUERY_CMD_COUNT) ?
+		(((bp->fw_stats_num + vf_headroom) / STATS_QUERY_CMD_COUNT) +
+		 (((bp->fw_stats_num + vf_headroom) % STATS_QUERY_CMD_COUNT) ?
 		 1 : 0));
 
-	DP(BNX2X_MSG_SP, "stats fw_stats_num %d, num_groups %d",
-	   bp->fw_stats_num, num_groups);
+	DP(BNX2X_MSG_SP, "stats fw_stats_num %d, vf headroom %d, num_groups %d",
+	   bp->fw_stats_num, vf_headroom, num_groups);
 
 	bp->fw_stats_req_sz = sizeof(struct stats_query_header) +
 			num_groups * sizeof(struct stats_query_cmd_group);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index cec1dc0..2411f6c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -97,10 +97,236 @@ static void bnx2x_vf_igu_ack_sb(struct bnx2x *bp, struct bnx2x_virtf *vf,
 	REG_WR(bp, igu_addr_ctl, ctl);
 	mmiowb();
 	barrier();
+
 }
-static inline int bnx2x_ari_enabled(struct pci_dev *dev)
+/* VFOP - VF slow-path operation support */
+
+/* VFOP operations states */
+enum bnx2x_vfop_qctor_state {
+	   BNX2X_VFOP_QCTOR_INIT,
+	   BNX2X_VFOP_QCTOR_SETUP,
+	   BNX2X_VFOP_QCTOR_INT_EN
+};
+
+enum bnx2x_vfop_vlan_mac_state {
+	   BNX2X_VFOP_VLAN_MAC_CONFIG_SINGLE,
+	   BNX2X_VFOP_VLAN_MAC_CLEAR,
+	   BNX2X_VFOP_VLAN_MAC_CHK_DONE,
+	   BNX2X_VFOP_MAC_CONFIG_LIST,
+	   BNX2X_VFOP_VLAN_CONFIG_LIST,
+	   BNX2X_VFOP_VLAN_CONFIG_LIST_0
+};
+
+enum bnx2x_vfop_qsetup_state {
+	   BNX2X_VFOP_QSETUP_CTOR,
+	   BNX2X_VFOP_QSETUP_VLAN0,
+	   BNX2X_VFOP_QSETUP_DONE
+};
+
+#define bnx2x_vfop_reset_wq(vf)	atomic_set(&vf->op_in_progress, 0)
+
+void bnx2x_vfop_qctor_dump_tx(struct bnx2x *bp, struct bnx2x_virtf *vf,
+			      struct bnx2x_queue_init_params *init_params,
+			      struct bnx2x_queue_setup_params *setup_params,
+			      u16 q_idx, u16 sb_idx)
 {
-	return dev->bus->self && dev->bus->self->ari_enabled;
+	DP(BNX2X_MSG_IOV,
+	   "VF[%d] Q_SETUP: txq[%d]-- vfsb=%d, sb-index=%d, hc-rate=%d, flags=0x%lx, traffic-type=%d",
+	   vf->abs_vfid,
+	   q_idx,
+	   sb_idx,
+	   init_params->tx.sb_cq_index,
+	   init_params->tx.hc_rate,
+	   setup_params->flags,
+	   setup_params->txq_params.traffic_type);
+}
+
+void bnx2x_vfop_qctor_dump_rx(struct bnx2x *bp, struct bnx2x_virtf *vf,
+			    struct bnx2x_queue_init_params *init_params,
+			    struct bnx2x_queue_setup_params *setup_params,
+			    u16 q_idx, u16 sb_idx)
+{
+	struct bnx2x_rxq_setup_params *rxq_params = &setup_params->rxq_params;
+
+	DP(BNX2X_MSG_IOV, "VF[%d] Q_SETUP: rxq[%d]-- vfsb=%d, sb-index=%d, hc-rate=%d, mtu=%d, buf-size=%d\n"
+	   "sge-size=%d, max_sge_pkt=%d, tpa-agg-size=%d, flags=0x%lx, drop-flags=0x%x, cache-log=%d\n",
+	   vf->abs_vfid,
+	   q_idx,
+	   sb_idx,
+	   init_params->rx.sb_cq_index,
+	   init_params->rx.hc_rate,
+	   setup_params->gen_params.mtu,
+	   rxq_params->buf_sz,
+	   rxq_params->sge_buf_sz,
+	   rxq_params->max_sges_pkt,
+	   rxq_params->tpa_agg_sz,
+	   setup_params->flags,
+	   rxq_params->drop_flags,
+	   rxq_params->cache_line_log);
+}
+
+void bnx2x_vfop_qctor_prep(struct bnx2x *bp,
+			   struct bnx2x_virtf *vf,
+			   struct bnx2x_vf_queue *q,
+			   struct bnx2x_vfop_qctor_params *p,
+			   unsigned long q_type)
+{
+
+	struct bnx2x_queue_init_params *init_p = &p->qstate.params.init;
+	struct bnx2x_queue_setup_params *setup_p = &p->prep_qsetup;
+
+	/* INIT */
+
+	/* Enable host coalescing in the transition to INIT state */
+	if (test_bit(BNX2X_Q_FLG_HC, &init_p->rx.flags))
+		__set_bit(BNX2X_Q_FLG_HC_EN, &init_p->rx.flags);
+
+	if (test_bit(BNX2X_Q_FLG_HC, &init_p->tx.flags))
+		__set_bit(BNX2X_Q_FLG_HC_EN, &init_p->tx.flags);
+
+	/* FW SB ID */
+	init_p->rx.fw_sb_id = vf_igu_sb(vf, q->sb_idx);
+	init_p->tx.fw_sb_id = vf_igu_sb(vf, q->sb_idx);
+
+	/* context */
+	init_p->cxts[0] = q->cxt;
+
+	/* SETUP */
+
+	/* Setup-op general parameters */
+	setup_p->gen_params.spcl_id = vf->sp_cl_id;
+	setup_p->gen_params.stat_id = vfq_stat_id(vf, q);
+
+	/* Setup-op pause params:
+	 * Nothing to do, the pause thresholds are set by default to 0 which
+	 * effectively turns off the feature for this queue. We don't want
+	 * one queue (VF) to interfering with another queue (another VF)
+	 */
+	if (vf->cfg_flags & VF_CFG_FW_FC)
+		BNX2X_ERR("No support for pause to VFs (abs_vfid: %d)\n",
+			  vf->abs_vfid);
+	/* Setup-op flags:
+	 * collect statistics, zero statistics, local-switching, security,
+	 * OV for Flex10, RSS and MCAST for leading
+	 */
+	if (test_bit(BNX2X_Q_FLG_STATS, &setup_p->flags))
+		__set_bit(BNX2X_Q_FLG_ZERO_STATS, &setup_p->flags);
+
+	/* for VFs, enable tx switching, bd coherency, and mac address
+	 * anti-spoofing
+	 */
+	__set_bit(BNX2X_Q_FLG_TX_SWITCH, &setup_p->flags);
+	__set_bit(BNX2X_Q_FLG_TX_SEC, &setup_p->flags);
+	__set_bit(BNX2X_Q_FLG_ANTI_SPOOF, &setup_p->flags);
+
+	if (vfq_is_leading(q)) {
+		__set_bit(BNX2X_Q_FLG_LEADING_RSS, &setup_p->flags);
+		__set_bit(BNX2X_Q_FLG_MCAST, &setup_p->flags);
+	}
+
+	/* Setup-op rx parameters */
+	if (test_bit(BNX2X_Q_TYPE_HAS_RX, &q_type)) {
+		struct bnx2x_rxq_setup_params *rxq_p = &setup_p->rxq_params;
+
+		rxq_p->cl_qzone_id = vfq_qzone_id(vf, q);
+		rxq_p->fw_sb_id = vf_igu_sb(vf, q->sb_idx);
+		rxq_p->rss_engine_id = FW_VF_HANDLE(vf->abs_vfid);
+
+		if (test_bit(BNX2X_Q_FLG_TPA, &setup_p->flags))
+			rxq_p->max_tpa_queues = BNX2X_VF_MAX_TPA_AGG_QUEUES;
+	}
+
+	/* Setup-op tx parameters */
+	if (test_bit(BNX2X_Q_TYPE_HAS_TX, &q_type)) {
+		setup_p->txq_params.tss_leading_cl_id = vf->leading_rss;
+		setup_p->txq_params.fw_sb_id = vf_igu_sb(vf, q->sb_idx);
+	}
+}
+
+/* VFOP queue construction */
+static void bnx2x_vfop_qctor(struct bnx2x *bp, struct bnx2x_virtf *vf)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
+	struct bnx2x_vfop_args_qctor *args = &vfop->args.qctor;
+	struct bnx2x_queue_state_params *q_params = &vfop->op_p->qctor.qstate;
+	enum bnx2x_vfop_qctor_state state = vfop->state;
+
+	bnx2x_vfop_reset_wq(vf);
+
+	if (vfop->rc < 0)
+		goto op_err;
+
+	DP(BNX2X_MSG_IOV, "vf[%d] STATE: %d\n", vf->abs_vfid, state);
+
+	switch (state) {
+	case BNX2X_VFOP_QCTOR_INIT:
+
+		/* has this queue already been opened? */
+		if (bnx2x_get_q_logical_state(bp, q_params->q_obj) ==
+		    BNX2X_Q_LOGICAL_STATE_ACTIVE) {
+			DP(BNX2X_MSG_IOV,
+			   "Entered qctor but queue was already up. Aborting gracefully\n");
+			goto op_done;
+		}
+
+		/* next state */
+		vfop->state = BNX2X_VFOP_QCTOR_SETUP;
+
+		q_params->cmd = BNX2X_Q_CMD_INIT;
+		vfop->rc = bnx2x_queue_state_change(bp, q_params);
+
+		bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
+
+	case BNX2X_VFOP_QCTOR_SETUP:
+		/* next state */
+		vfop->state = BNX2X_VFOP_QCTOR_INT_EN;
+
+		/* copy pre-prepared setup params to the queue-state params */
+		vfop->op_p->qctor.qstate.params.setup =
+			vfop->op_p->qctor.prep_qsetup;
+
+		q_params->cmd = BNX2X_Q_CMD_SETUP;
+		vfop->rc = bnx2x_queue_state_change(bp, q_params);
+
+		bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
+
+	case BNX2X_VFOP_QCTOR_INT_EN:
+
+		/* enable interrupts */
+		bnx2x_vf_igu_ack_sb(bp, vf, vf_igu_sb(vf, args->sb_idx),
+				    USTORM_ID, 0, IGU_INT_ENABLE, 0);
+		goto op_done;
+	default:
+		bnx2x_vfop_default(state);
+	}
+op_err:
+	BNX2X_ERR("QCTOR[%d:%d] error: cmd %d, rc %d\n",
+		  vf->abs_vfid, args->qid, q_params->cmd, vfop->rc);
+op_done:
+	bnx2x_vfop_end(bp, vf, vfop);
+op_pending:
+	return;
+}
+
+static int bnx2x_vfop_qctor_cmd(struct bnx2x *bp,
+				struct bnx2x_virtf *vf,
+				struct bnx2x_vfop_cmd *cmd,
+				int qid)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+
+	if (vfop) {
+		vf->op_params.qctor.qstate.q_obj = &bnx2x_vfq(vf, qid, sp_obj);
+
+		vfop->args.qctor.qid = qid;
+		vfop->args.qctor.sb_idx = bnx2x_vfq(vf, qid, sb_idx);
+
+		bnx2x_vfop_opset(BNX2X_VFOP_QCTOR_INIT,
+				 bnx2x_vfop_qctor, cmd->done);
+		return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_qctor,
+					     cmd->block);
+	}
+	return -ENOMEM;
 }
 
 static inline void __devinit
@@ -111,221 +337,359 @@ bnx2x_vf_set_igu_info(struct bnx2x *bp, u8 igu_sb_id, u8 abs_vfid)
 		if (!vf_sb_count(vf))
 			vf->igu_base_id = igu_sb_id;
 		++vf_sb_count(vf);
-	 }
+	}
 }
 
-static void __devinit
-bnx2x_get_vf_igu_cam_info(struct bnx2x *bp)
+/* VFOP MAC/VLAN helpers */
+static inline void bnx2x_vfop_credit(struct bnx2x *bp,
+				     struct bnx2x_vfop *vfop,
+				     struct bnx2x_vlan_mac_obj *obj)
 {
-	int sb_id;
-	u32 val;
-	u8 fid;
+	struct bnx2x_vfop_args_filters *args = &vfop->args.filters;
 
-	/* IGU in normal mode - read CAM */
-	for (sb_id = 0; sb_id < IGU_REG_MAPPING_MEMORY_SIZE; sb_id++) {
-		val = REG_RD(bp, IGU_REG_MAPPING_MEMORY + sb_id * 4);
-		if (!(val & IGU_REG_MAPPING_MEMORY_VALID))
-			continue;
-		fid = GET_FIELD((val), IGU_REG_MAPPING_MEMORY_FID);
-		if (!(fid & IGU_FID_ENCODE_IS_PF))
-			bnx2x_vf_set_igu_info(bp, sb_id,
-					      (fid & IGU_FID_VF_NUM_MASK));
+	/* update credit only if there is no error
+	 * and a valid credit counter
+	 */
+	if (!vfop->rc && args->credit) {
+		int cnt = 0;
+		struct list_head *pos;
 
-		DP(BNX2X_MSG_IOV, "%s[%d], igu_sb_id=%d, msix=%d\n",
-		   ((fid & IGU_FID_ENCODE_IS_PF) ? "PF" : "VF"),
-		   ((fid & IGU_FID_ENCODE_IS_PF) ? (fid & IGU_FID_PF_NUM_MASK) :
-		   (fid & IGU_FID_VF_NUM_MASK)), sb_id,
-		   GET_FIELD((val), IGU_REG_MAPPING_MEMORY_VECTOR));
+		list_for_each(pos, &obj->head)
+			cnt++;
+
+		atomic_set(args->credit, cnt);
 	}
 }
 
-static void __bnx2x_iov_free_vfdb(struct bnx2x *bp)
+static int bnx2x_vfop_set_user_req(struct bnx2x *bp,
+				    struct bnx2x_vfop_filter *pos,
+				    struct bnx2x_vlan_mac_data *user_req)
 {
-	if (bp->vfdb) {
-		kfree(bp->vfdb->vfqs);
-		kfree(bp->vfdb->vfs);
-		kfree(bp->vfdb);
+	user_req->cmd = pos->add ? BNX2X_VLAN_MAC_ADD :
+		BNX2X_VLAN_MAC_DEL;
+
+	switch (pos->type) {
+	case BNX2X_VFOP_FILTER_MAC:
+		memcpy(user_req->u.mac.mac, pos->mac, ETH_ALEN);
+		break;
+	case BNX2X_VFOP_FILTER_VLAN:
+		user_req->u.vlan.vlan = pos->vid;
+		break;
+	default:
+		BNX2X_ERR("Invalid filter type, skipping\n");
+		return 1;
 	}
-	bp->vfdb = NULL;
+	return 0;
 }
 
-static int bnx2x_sriov_pci_cfg_info(struct bnx2x *bp, struct bnx2x_sriov *iov)
+static inline int
+bnx2x_vfop_config_vlan0(struct bnx2x *bp,
+			struct bnx2x_vlan_mac_ramrod_params *vlan_mac,
+			bool add)
 {
-	int pos;
-	struct pci_dev *dev = bp->pdev;
-
-	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_SRIOV);
-	if (!pos) {
-		BNX2X_ERR("failed to find SRIOV capability in device\n");
-		return -ENODEV;
-	}
+	int rc;
 
-	iov->pos = pos;
-	DP(BNX2X_MSG_IOV, "sriov ext pos %d\n", pos);
-	pci_read_config_word(dev, pos + PCI_SRIOV_CTRL, &iov->ctrl);
-	pci_read_config_word(dev, pos + PCI_SRIOV_TOTAL_VF, &iov->total);
-	pci_read_config_word(dev, pos + PCI_SRIOV_INITIAL_VF, &iov->initial);
-	pci_read_config_word(dev, pos + PCI_SRIOV_VF_OFFSET, &iov->offset);
-	pci_read_config_word(dev, pos + PCI_SRIOV_VF_STRIDE, &iov->stride);
-	pci_read_config_dword(dev, pos + PCI_SRIOV_SUP_PGSIZE, &iov->pgsz);
-	pci_read_config_dword(dev, pos + PCI_SRIOV_CAP, &iov->cap);
-	pci_read_config_byte(dev, pos + PCI_SRIOV_FUNC_LINK, &iov->link);
+	vlan_mac->user_req.cmd = add ? BNX2X_VLAN_MAC_ADD :
+		BNX2X_VLAN_MAC_DEL;
+	vlan_mac->user_req.u.vlan.vlan = 0;
 
-	return 0;
+	rc = bnx2x_config_vlan_mac(bp, vlan_mac);
+	if (rc == -EEXIST)
+		rc = 0;
+	return rc;
 }
 
-static int bnx2x_sriov_info(struct bnx2x *bp, struct bnx2x_sriov *iov)
+static int bnx2x_vfop_config_list(struct bnx2x *bp,
+				  struct bnx2x_vfop_filters *filters,
+				  struct bnx2x_vlan_mac_ramrod_params *vlan_mac)
 {
-	u32 val;
+	struct bnx2x_vfop_filter *pos, *tmp;
+	struct list_head rollback_list, *filters_list = &filters->head;
+	struct bnx2x_vlan_mac_data *user_req = &vlan_mac->user_req;
+	int rc = 0, cnt = 0;
 
-	/* read the SRIOV capability structure
-	 * The fields can be read via configuration read or
-	 * directly from the device (starting at offset PCICFG_OFFSET)
-	 */
-	if (bnx2x_sriov_pci_cfg_info(bp, iov))
-		return -ENODEV;
-
-	/* get the number of SRIOV bars */
-	iov->nres = 0;
+	INIT_LIST_HEAD(&rollback_list);
 
-	/* read the first_vfid */
-	val = REG_RD(bp, PCICFG_OFFSET + GRC_CONFIG_REG_PF_INIT_VF);
-	iov->first_vf_in_pf = ((val & GRC_CR_PF_INIT_VF_PF_FIRST_VF_NUM_MASK)
-			       * 8) - (BNX2X_MAX_NUM_OF_VFS * BP_PATH(bp));
+	list_for_each_entry_safe(pos, tmp, filters_list, link) {
+		if (bnx2x_vfop_set_user_req(bp, pos, user_req))
+			continue;
 
-	DP(BNX2X_MSG_IOV,
-	   "IOV info[%d]: first vf %d, nres %d, cap 0x%x, ctrl 0x%x, total %d, initial %d, num vfs %d, offset %d, stride %d, page size 0x%x\n",
-	   BP_FUNC(bp),
-	   iov->first_vf_in_pf, iov->nres, iov->cap, iov->ctrl, iov->total,
-	   iov->initial, iov->nr_virtfn, iov->offset, iov->stride, iov->pgsz);
+		rc = bnx2x_config_vlan_mac(bp, vlan_mac);
+		if (rc >= 0) {
+			cnt += pos->add ? 1 : -1;
+			list_del(&pos->link);
+			list_add(&pos->link, &rollback_list);
+			rc = 0;
+		} else if (rc == -EEXIST) {
+			rc = 0;
+		} else {
+			BNX2X_ERR("Failed to add a new vlan_mac command\n");
+			break;
+		}
+	}
 
-	return 0;
+	/* rollback if error or too many rules added */
+	if (rc || cnt > filters->add_cnt) {
+		BNX2X_ERR("error or too many rules added. Performing rollback\n");
+		list_for_each_entry_safe(pos, tmp, &rollback_list, link) {
+			pos->add = !pos->add;	/* reverse op */
+			bnx2x_vfop_set_user_req(bp, pos, user_req);
+			bnx2x_config_vlan_mac(bp, vlan_mac);
+			list_del(&pos->link);
+		}
+		cnt = 0;
+		if (!rc)
+			rc = -EINVAL;
+	}
+	filters->add_cnt = cnt;
+	return rc;
 }
 
-static u8 bnx2x_iov_get_max_queue_count(struct bnx2x *bp)
+/* VFOP set VLAN/MAC */
+static void bnx2x_vfop_vlan_mac(struct bnx2x *bp, struct bnx2x_virtf *vf)
 {
-	int i;
-	u8 queue_count = 0;
+	struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
+	struct bnx2x_vlan_mac_ramrod_params *vlan_mac = &vfop->op_p->vlan_mac;
+	struct bnx2x_vlan_mac_obj *obj = vlan_mac->vlan_mac_obj;
+	struct bnx2x_vfop_filters *filters = vfop->args.filters.multi_filter;
 
-	if (IS_SRIOV(bp))
-		for_each_vf(bp, i)
-			queue_count += bnx2x_vf(bp, i, alloc_resc.num_sbs);
+	enum bnx2x_vfop_vlan_mac_state state = vfop->state;
 
-	return queue_count;
-}
+	if (vfop->rc < 0)
+		goto op_err;
 
-/* must be called after PF bars are mapped */
-int __devinit bnx2x_iov_init_one(struct bnx2x *bp, int int_mode_param,
-				 int num_vfs_param)
-{
-	int err, i, qcount;
-	struct bnx2x_sriov *iov;
-	struct pci_dev *dev = bp->pdev;
+	DP(BNX2X_MSG_IOV, "vf[%d] STATE: %d\n", vf->abs_vfid, state);
 
-	bp->vfdb = NULL;
+	bnx2x_vfop_reset_wq(vf);
 
-	/* verify sriov capability is present in configuration space */
-	if (!pci_find_ext_capability(dev, PCI_EXT_CAP_ID_SRIOV))
-		return 0;
+	switch (state) {
+	case BNX2X_VFOP_VLAN_MAC_CLEAR:
+		/* next state */
+		vfop->state = BNX2X_VFOP_VLAN_MAC_CHK_DONE;
 
-	/* verify is pf */
-	if (IS_VF(bp))
-		return 0;
+		/* do delete */
+		vfop->rc = obj->delete_all(bp, obj,
+					   &vlan_mac->user_req.vlan_mac_flags,
+					   &vlan_mac->ramrod_flags);
 
-	/* verify chip revision */
-	if (CHIP_IS_E1x(bp))
-		return 0;
+		bnx2x_vfop_finalize(vf, vfop->rc, VFOP_DONE);
 
-	/* check if SRIOV support is turned off */
-	if (!num_vfs_param)
-		return 0;
+	case BNX2X_VFOP_VLAN_MAC_CONFIG_SINGLE:
+		/* next state */
+		vfop->state = BNX2X_VFOP_VLAN_MAC_CHK_DONE;
 
-	/* SRIOV assumes that num of PF CIDs < BNX2X_FIRST_VF_CID */
-	if (BNX2X_L2_MAX_CID(bp) >= BNX2X_FIRST_VF_CID) {
-		BNX2X_ERR("PF cids %d are overspilling into vf space (starts at %d). Abort SRIOV",
-			  BNX2X_L2_MAX_CID(bp), BNX2X_FIRST_VF_CID);
-		return 0;
-	}
+		/* do config */
+		vfop->rc = bnx2x_config_vlan_mac(bp, vlan_mac);
+		if (vfop->rc == -EEXIST)
+			vfop->rc = 0;
 
-	/* SRIOV can be enabled only with MSIX */
-	if (int_mode_param == BNX2X_INT_MODE_MSI ||
-	    int_mode_param == BNX2X_INT_MODE_INTX)
-		BNX2X_ERR("Forced MSI/INTx mode is incompatible with SRIOV\n");
+		bnx2x_vfop_finalize(vf, vfop->rc, VFOP_DONE);
 
-	err = -EIO;
-	/* verify ari is enabled */
-	if (!bnx2x_ari_enabled(bp->pdev)) {
-		BNX2X_ERR("ARI not supported, SRIOV can not be enabled\n");
-		return err;
-	}
+	case BNX2X_VFOP_VLAN_MAC_CHK_DONE:
+		vfop->rc = !!obj->raw.check_pending(&obj->raw);
+		bnx2x_vfop_finalize(vf, vfop->rc, VFOP_DONE);
 
-	/* verify igu is in normal mode */
-	if (CHIP_INT_MODE_IS_BC(bp)) {
-		BNX2X_ERR("IGU not normal mode,  SRIOV can not be enabled\n");
-		return err;
-	}
+	case BNX2X_VFOP_MAC_CONFIG_LIST:
+		/* next state */
+		vfop->state = BNX2X_VFOP_VLAN_MAC_CHK_DONE;
 
-	/* allocate the vfs database */
-	bp->vfdb = kzalloc(sizeof(*(bp->vfdb)), GFP_KERNEL);
-	if (!bp->vfdb) {
-		BNX2X_ERR("failed to allocate vf database\n");
-		err = -ENOMEM;
-		goto failed;
+		/* do list config */
+		vfop->rc = bnx2x_vfop_config_list(bp, filters, vlan_mac);
+		if (vfop->rc)
+			goto op_err;
+
+		set_bit(RAMROD_CONT, &vlan_mac->ramrod_flags);
+		vfop->rc = bnx2x_config_vlan_mac(bp, vlan_mac);
+		bnx2x_vfop_finalize(vf, vfop->rc, VFOP_DONE);
+
+	case BNX2X_VFOP_VLAN_CONFIG_LIST:
+		/* next state */
+		vfop->state = BNX2X_VFOP_VLAN_CONFIG_LIST_0;
+
+		/* remove vlan0 - could be no-op */
+		vfop->rc = bnx2x_vfop_config_vlan0(bp, vlan_mac, false);
+		if (vfop->rc)
+			goto op_err;
+
+		/* Do vlan list config. if this operation fails we try to
+		 * restore vlan0 to keep the queue is working order
+		 */
+		vfop->rc = bnx2x_vfop_config_list(bp, filters, vlan_mac);
+		if (!vfop->rc) {
+			set_bit(RAMROD_CONT, &vlan_mac->ramrod_flags);
+			vfop->rc = bnx2x_config_vlan_mac(bp, vlan_mac);
+		}
+		bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT); /* fall-through */
+
+	case BNX2X_VFOP_VLAN_CONFIG_LIST_0:
+		/* next state */
+		vfop->state = BNX2X_VFOP_VLAN_MAC_CHK_DONE;
+
+		if (list_empty(&obj->head))
+			/* add vlan0 */
+			vfop->rc = bnx2x_vfop_config_vlan0(bp, vlan_mac, true);
+		bnx2x_vfop_finalize(vf, vfop->rc, VFOP_DONE);
+
+	default:
+		bnx2x_vfop_default(state);
 	}
+op_err:
+	BNX2X_ERR("VLAN-MAC error: rc %d\n", vfop->rc);
+op_done:
+	kfree(filters);
+	bnx2x_vfop_credit(bp, vfop, obj);
+	bnx2x_vfop_end(bp, vf, vfop);
+op_pending:
+	return;
+}
 
-	/* get the sriov info - Linux already collected all the pertinent
-	 * information, however the sriov structure is for the private use
-	 * of the pci module. Also we want this information regardless
-	 *  of the hyper-visor.
-	 */
-	iov = &(bp->vfdb->sriov);
-	err = bnx2x_sriov_info(bp, iov);
-	if (err)
-		goto failed;
+struct bnx2x_vfop_vlan_mac_flags {
+	bool drv_only;
+	bool dont_consume;
+	bool single_cmd;
+	bool add;
+};
 
-	/* calcuate the actual number of VFs */
-	iov->nr_virtfn = min_t(u16, iov->total, (u16)num_vfs_param);
+static inline void
+bnx2x_vfop_vlan_mac_prep_ramrod(struct bnx2x_vlan_mac_ramrod_params *ramrod,
+				struct bnx2x_vfop_vlan_mac_flags *flags)
+{
+	struct bnx2x_vlan_mac_data *ureq = &ramrod->user_req;
 
-	/* allcate the vf array */
-	bp->vfdb->vfs = kzalloc(sizeof(struct bnx2x_virtf) *
-				BNX2X_NR_VIRTFN(bp), GFP_KERNEL);
-	if (!bp->vfdb->vfs) {
-		BNX2X_ERR("failed to allocate vf array\n");
-		err = -ENOMEM;
-		goto failed;
+	memset(ramrod, 0, sizeof(*ramrod));
+
+	/* ramrod flags */
+	if (flags->drv_only)
+		set_bit(RAMROD_DRV_CLR_ONLY, &ramrod->ramrod_flags);
+	if (flags->single_cmd)
+		set_bit(RAMROD_EXEC, &ramrod->ramrod_flags);
+
+	/* mac_vlan flags */
+	if (flags->dont_consume)
+		set_bit(BNX2X_DONT_CONSUME_CAM_CREDIT, &ureq->vlan_mac_flags);
+
+	/* cmd */
+	ureq->cmd = flags->add ? BNX2X_VLAN_MAC_ADD : BNX2X_VLAN_MAC_DEL;
+}
+
+
+int bnx2x_vfop_vlan_set_cmd(struct bnx2x *bp,
+			    struct bnx2x_virtf *vf,
+			    struct bnx2x_vfop_cmd *cmd,
+			    int qid, u16 vid, bool add)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+
+	if (vfop) {
+		struct bnx2x_vfop_args_filters filters = {
+			.multi_filter = NULL, /* single command */
+			.credit = &bnx2x_vfq(vf, qid, vlan_count),
+		};
+		struct bnx2x_vfop_vlan_mac_flags flags = {
+			.drv_only = false,
+			.dont_consume = (filters.credit != NULL),
+			.single_cmd = true,
+			.add = add,
+		};
+		struct bnx2x_vlan_mac_ramrod_params *ramrod =
+			&vf->op_params.vlan_mac;
+
+		/* set ramrod params */
+		bnx2x_vfop_vlan_mac_prep_ramrod(ramrod, &flags);
+		ramrod->user_req.u.vlan.vlan = vid;
+
+		/* set object */
+		ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, vlan_obj);
+
+		/* set extra args */
+		vfop->args.filters = filters;
+
+		bnx2x_vfop_opset(BNX2X_VFOP_VLAN_MAC_CONFIG_SINGLE,
+				 bnx2x_vfop_vlan_mac, cmd->done);
+		return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_vlan_mac,
+					     cmd->block);
 	}
+	return -ENOMEM;
+}
 
-	/* Initial VF init - index and abs_vfid - nr_virtfn must be set */
-	for_each_vf(bp, i) {
-		bnx2x_vf(bp, i, index) = i;
-		bnx2x_vf(bp, i, abs_vfid) = iov->first_vf_in_pf + i;
-		bnx2x_vf(bp, i, state) = VF_FREE;
-		INIT_LIST_HEAD(&bnx2x_vf(bp, i, op_list_head));
-		mutex_init(&bnx2x_vf(bp, i, op_mutex));
-		bnx2x_vf(bp, i, op_current) = CHANNEL_TLV_NONE;
+/* VFOP queue setup (queue constructor + set vlan 0) */
+static void bnx2x_vfop_qsetup(struct bnx2x *bp, struct bnx2x_virtf *vf)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
+	int qid = vfop->args.qctor.qid;
+	enum bnx2x_vfop_qsetup_state state = vfop->state;
+	struct bnx2x_vfop_cmd cmd = {
+		.done = bnx2x_vfop_qsetup,
+		.block = false,
+	};
+
+	if (vfop->rc < 0)
+		goto op_err;
+
+	DP(BNX2X_MSG_IOV, "vf[%d] STATE: %d\n", vf->abs_vfid, state);
+
+	switch (state) {
+	case BNX2X_VFOP_QSETUP_CTOR:
+		/* init the queue ctor command */
+		vfop->state = BNX2X_VFOP_QSETUP_VLAN0;
+		vfop->rc = bnx2x_vfop_qctor_cmd(bp, vf, &cmd, qid);
+		if (vfop->rc)
+			goto op_err;
+		return;
+
+	case BNX2X_VFOP_QSETUP_VLAN0:
+		/* skip if non-leading or FPGA/EMU*/
+		if (qid || CHIP_REV_IS_SLOW(bp))
+			goto op_done;
+
+		/* init the queue set-vlan command (for vlan 0) */
+		vfop->state = BNX2X_VFOP_QSETUP_DONE;
+		vfop->rc = bnx2x_vfop_vlan_set_cmd(bp, vf, &cmd, qid, 0, true);
+		if (vfop->rc)
+			goto op_err;
+		return;
+op_err:
+	BNX2X_ERR("QSETUP[%d:%d] error: rc %d\n", vf->abs_vfid, qid, vfop->rc);
+op_done:
+	case BNX2X_VFOP_QSETUP_DONE:
+		bnx2x_vfop_end(bp, vf, vfop);
+		return;
+	default:
+		bnx2x_vfop_default(state);
 	}
+}
 
-	/* re-read the IGU CAM for VFs - index and abs_vfid must be set */
-	bnx2x_get_vf_igu_cam_info(bp);
+int bnx2x_vfop_qsetup_cmd(struct bnx2x *bp,
+			  struct bnx2x_virtf *vf,
+			  struct bnx2x_vfop_cmd *cmd,
+			  int qid)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
 
-	/* get the total queue count and allocate the global queue arrays */
-	qcount = bnx2x_iov_get_max_queue_count(bp);
+	if (vfop) {
+		vfop->args.qctor.qid = qid;
 
-	/* allocate the queue arrays for all VFs */
-	bp->vfdb->vfqs = kzalloc(qcount * sizeof(struct bnx2x_vf_queue),
-				 GFP_KERNEL);
-	if (!bp->vfdb->vfqs) {
-		BNX2X_ERR("failed to allocate vf queue array\n");
-		err = -ENOMEM;
-		goto failed;
+		bnx2x_vfop_opset(BNX2X_VFOP_QSETUP_CTOR,
+				 bnx2x_vfop_qsetup, cmd->done);
+		return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_qsetup,
+					     cmd->block);
 	}
+	return -ENOMEM;
+}
 
-	return 0;
-failed:
-	DP(BNX2X_MSG_IOV, "Failed err=%d\n", err);
-	__bnx2x_iov_free_vfdb(bp);
-	return err;
+
+static u8 bnx2x_iov_get_max_queue_count(struct bnx2x *bp)
+{
+	int i;
+	u8 queue_count = 0;
+
+	if (IS_SRIOV(bp))
+		for_each_vf(bp, i)
+			queue_count += bnx2x_vf(bp, i, alloc_resc.num_sbs);
+
+	return queue_count;
 }
+
 /* VF enable primitives
  *
  * when pretend is required the caller is responsible
@@ -601,6 +965,209 @@ static void bnx2x_vf_set_bars(struct bnx2x *bp, struct bnx2x_virtf *vf)
 	}
 }
 
+static inline int bnx2x_ari_enabled(struct pci_dev *dev)
+{
+	return dev->bus->self && dev->bus->self->ari_enabled;
+}
+
+static void __devinit
+bnx2x_get_vf_igu_cam_info(struct bnx2x *bp)
+{
+	int sb_id;
+	u32 val;
+	u8 fid;
+
+	/* IGU in normal mode - read CAM */
+	for (sb_id = 0; sb_id < IGU_REG_MAPPING_MEMORY_SIZE; sb_id++) {
+		val = REG_RD(bp, IGU_REG_MAPPING_MEMORY + sb_id * 4);
+		if (!(val & IGU_REG_MAPPING_MEMORY_VALID))
+			continue;
+		fid = GET_FIELD((val), IGU_REG_MAPPING_MEMORY_FID);
+		if (!(fid & IGU_FID_ENCODE_IS_PF))
+			bnx2x_vf_set_igu_info(bp, sb_id,
+					      (fid & IGU_FID_VF_NUM_MASK));
+
+		DP(BNX2X_MSG_IOV, "%s[%d], igu_sb_id=%d, msix=%d\n",
+		   ((fid & IGU_FID_ENCODE_IS_PF) ? "PF" : "VF"),
+		   ((fid & IGU_FID_ENCODE_IS_PF) ? (fid & IGU_FID_PF_NUM_MASK) :
+		   (fid & IGU_FID_VF_NUM_MASK)), sb_id,
+		   GET_FIELD((val), IGU_REG_MAPPING_MEMORY_VECTOR));
+	}
+}
+
+static void __bnx2x_iov_free_vfdb(struct bnx2x *bp)
+{
+	if (bp->vfdb) {
+		kfree(bp->vfdb->vfqs);
+		kfree(bp->vfdb->vfs);
+		kfree(bp->vfdb);
+	}
+	bp->vfdb = NULL;
+}
+
+static int bnx2x_sriov_pci_cfg_info(struct bnx2x *bp, struct bnx2x_sriov *iov)
+{
+	int pos;
+	struct pci_dev *dev = bp->pdev;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_SRIOV);
+	if (!pos) {
+		BNX2X_ERR("failed to find SRIOV capability in device\n");
+		return -ENODEV;
+	}
+
+	iov->pos = pos;
+	DP(BNX2X_MSG_IOV, "sriov ext pos %d\n", pos);
+	pci_read_config_word(dev, pos + PCI_SRIOV_CTRL, &iov->ctrl);
+	pci_read_config_word(dev, pos + PCI_SRIOV_TOTAL_VF, &iov->total);
+	pci_read_config_word(dev, pos + PCI_SRIOV_INITIAL_VF, &iov->initial);
+	pci_read_config_word(dev, pos + PCI_SRIOV_VF_OFFSET, &iov->offset);
+	pci_read_config_word(dev, pos + PCI_SRIOV_VF_STRIDE, &iov->stride);
+	pci_read_config_dword(dev, pos + PCI_SRIOV_SUP_PGSIZE, &iov->pgsz);
+	pci_read_config_dword(dev, pos + PCI_SRIOV_CAP, &iov->cap);
+	pci_read_config_byte(dev, pos + PCI_SRIOV_FUNC_LINK, &iov->link);
+
+	return 0;
+}
+static int bnx2x_sriov_info(struct bnx2x *bp, struct bnx2x_sriov *iov)
+{
+	u32 val;
+
+	/* read the SRIOV capability structure
+	 * The fields can be read via configuration read or
+	 * directly from the device (starting at offset PCICFG_OFFSET)
+	 */
+	if (bnx2x_sriov_pci_cfg_info(bp, iov))
+		return -ENODEV;
+
+	/* get the number of SRIOV bars */
+	iov->nres = 0;
+
+	/* read the first_vfid */
+	val = REG_RD(bp, PCICFG_OFFSET + GRC_CONFIG_REG_PF_INIT_VF);
+	iov->first_vf_in_pf = ((val & GRC_CR_PF_INIT_VF_PF_FIRST_VF_NUM_MASK)
+			       * 8) - (BNX2X_MAX_NUM_OF_VFS * BP_PATH(bp));
+
+	DP(BNX2X_MSG_IOV,
+	   "IOV info[%d]: first vf %d, nres %d, cap 0x%x, ctrl 0x%x, total %d, initial %d, num vfs %d, offset %d, stride %d, page size 0x%x\n",
+	   BP_FUNC(bp),
+	   iov->first_vf_in_pf, iov->nres, iov->cap, iov->ctrl, iov->total,
+	   iov->initial, iov->nr_virtfn, iov->offset, iov->stride, iov->pgsz);
+
+	return 0;
+}
+/* must be called after PF bars are mapped */
+int __devinit bnx2x_iov_init_one(struct bnx2x *bp, int int_mode_param,
+				 int num_vfs_param)
+{
+	int err, i, qcount;
+	struct bnx2x_sriov *iov;
+	struct pci_dev *dev = bp->pdev;
+
+	bp->vfdb = NULL;
+
+	/* verify is pf */
+	if (IS_VF(bp))
+		return 0;
+
+	/* verify sriov capability is present in configuration space */
+	if (!pci_find_ext_capability(dev, PCI_EXT_CAP_ID_SRIOV))
+		return 0;
+
+	/* verify chip revision */
+	if (CHIP_IS_E1x(bp))
+		return 0;
+
+	/* check if SRIOV support is turned off */
+	if (!num_vfs_param)
+		return 0;
+
+	/* SRIOV assumes that num of PF CIDs < BNX2X_FIRST_VF_CID */
+	if (BNX2X_L2_MAX_CID(bp) >= BNX2X_FIRST_VF_CID) {
+		BNX2X_ERR("PF cids %d are overspilling into vf space (starts at %d). Abort SRIOV",
+			  BNX2X_L2_MAX_CID(bp), BNX2X_FIRST_VF_CID);
+		return 0;
+	}
+
+	/* SRIOV can be enabled only with MSIX */
+	if (int_mode_param == BNX2X_INT_MODE_MSI ||
+	    int_mode_param == BNX2X_INT_MODE_INTX)
+		BNX2X_ERR("Forced MSI/INTx mode is incompatible with SRIOV\n");
+
+	err = -EIO;
+	/* verify ari is enabled */
+	if (!bnx2x_ari_enabled(bp->pdev)) {
+		BNX2X_ERR("ARI not supported, SRIOV can not be enabled\n");
+		return err;
+	}
+
+	/* verify igu is in normal mode */
+	if (CHIP_INT_MODE_IS_BC(bp)) {
+		BNX2X_ERR("IGU not normal mode,  SRIOV can not be enabled\n");
+		return err;
+	}
+
+	/* allocate the vfs database */
+	bp->vfdb = kzalloc(sizeof(*(bp->vfdb)), GFP_KERNEL);
+	if (!bp->vfdb) {
+		BNX2X_ERR("failed to allocate vf database\n");
+		err = -ENOMEM;
+		goto failed;
+	}
+
+	/* get the sriov info - Linux already collected all the pertinent
+	 * information, however the sriov structure is for the private use
+	 * of the pci module. Also we want this information regardless
+	 * of the hyper-visor.
+	 */
+	iov = &(bp->vfdb->sriov);
+	err = bnx2x_sriov_info(bp, iov);
+	if (err)
+		goto failed;
+
+	/* calculate the actual number of VFs */
+	iov->nr_virtfn = min_t(u16, iov->total, (u16)num_vfs_param);
+
+	/* allocate the vf array */
+	bp->vfdb->vfs = kzalloc(sizeof(struct bnx2x_virtf) *
+				BNX2X_NR_VIRTFN(bp), GFP_KERNEL);
+	if (!bp->vfdb->vfs) {
+		BNX2X_ERR("failed to allocate vf array\n");
+		err = -ENOMEM;
+		goto failed;
+	}
+
+	/* Initial VF init - index and abs_vfid - nr_virtfn must be set */
+	for_each_vf(bp, i) {
+		bnx2x_vf(bp, i, index) = i;
+		bnx2x_vf(bp, i, abs_vfid) = iov->first_vf_in_pf + i;
+		bnx2x_vf(bp, i, state) = VF_FREE;
+		INIT_LIST_HEAD(&bnx2x_vf(bp, i, op_list_head));
+		mutex_init(&bnx2x_vf(bp, i, op_mutex));
+		bnx2x_vf(bp, i, op_current) = CHANNEL_TLV_NONE;
+	}
+
+	/* re-read the IGU CAM for VFs - index and abs_vfid must be set */
+	bnx2x_get_vf_igu_cam_info(bp);
+
+	/* get the total queue count and allocate the global queue arrays */
+	qcount = bnx2x_iov_get_max_queue_count(bp);
+
+	/* allocate the queue arrays for all VFs */
+	bp->vfdb->vfqs = kzalloc(qcount * sizeof(struct bnx2x_vf_queue),
+				 GFP_KERNEL);
+	if (!bp->vfdb->vfqs) {
+		BNX2X_ERR("failed to allocate vf queue array\n");
+		err = -ENOMEM;
+		goto failed;
+	}
+
+	return 0;
+failed:
+	DP(BNX2X_MSG_IOV, "Failed err=%d\n", err);
+	__bnx2x_iov_free_vfdb(bp);
+	return err;
+}
 void __devexit bnx2x_iov_remove_one(struct bnx2x *bp)
 {
 	/* if SRIOV is not enabled there's nothing to do */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
index 583ac13..64b0c1d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
@@ -26,6 +26,8 @@
  * The VF array is indexed by the relative vfid.
  */
 #define BNX2X_VF_MAX_QUEUES		16
+#define BNX2X_VF_MAX_TPA_AGG_QUEUES	8
+
 struct bnx2x_sriov {
 	u32 first_vf_in_pf;
 
@@ -92,6 +94,11 @@ struct bnx2x_virtf;
 /* VFOP definitions */
 typedef void (*vfop_handler_t)(struct bnx2x *bp, struct bnx2x_virtf *vf);
 
+struct bnx2x_vfop_cmd {
+	vfop_handler_t done;
+	bool block;
+};
+
 /* VFOP queue filters command additional arguments */
 struct bnx2x_vfop_filter {
 	struct list_head link;
@@ -411,6 +418,10 @@ static inline u8 vfq_cl_id(struct bnx2x_virtf *vf, struct bnx2x_vf_queue *q)
 {
 	return vf->igu_base_id + q->index;
 }
+static inline u8 vfq_stat_id(struct bnx2x_virtf *vf, struct bnx2x_vf_queue *q)
+{
+	return vfq_cl_id(vf, q);
+}
 static inline u8 vfq_qzone_id(struct bnx2x_virtf *vf, struct bnx2x_vf_queue *q)
 {
 	return vfq_cl_id(vf, q);
@@ -444,6 +455,45 @@ int bnx2x_vf_init(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		  dma_addr_t *sb_map);
 
 
+/* VFOP generic helpers */
+#define bnx2x_vfop_default(state) do {				\
+		BNX2X_ERR("Bad state %d\n", (state));		\
+		vfop->rc = -EINVAL;				\
+		goto op_err;					\
+	} while (0)
+
+
+enum {
+	VFOP_DONE,
+	VFOP_CONT,
+	VFOP_VERIFY_PEND,
+};
+
+#define bnx2x_vfop_finalize(vf, rc, next) do {				\
+		if ((rc) < 0)						\
+			goto op_err;					\
+		else if ((rc) > 0)					\
+			goto op_pending;				\
+		else if ((next) == VFOP_DONE)				\
+			goto op_done;					\
+		else if ((next) == VFOP_VERIFY_PEND)			\
+			BNX2X_ERR("expected pending");			\
+		else {							\
+			DP(BNX2X_MSG_IOV, "no ramrod. scheduling");	\
+			atomic_set(&vf->op_in_progress, 1);		\
+			queue_delayed_work(bnx2x_wq, &bp->sp_task, 0);  \
+			return;						\
+		}							\
+	} while (0)
+
+#define bnx2x_vfop_opset(first_state, trans_hndlr, done_hndlr)		\
+	do {								\
+		vfop->state = first_state;				\
+		vfop->op_p = &vf->op_params;				\
+		vfop->transition = trans_hndlr;				\
+		vfop->done = done_hndlr;				\
+	} while (0)
+
 static inline struct bnx2x_vfop *bnx2x_vfop_cur(struct bnx2x *bp,
 						struct bnx2x_virtf *vf)
 {
@@ -452,6 +502,134 @@ static inline struct bnx2x_vfop *bnx2x_vfop_cur(struct bnx2x *bp,
 	return list_first_entry(&vf->op_list_head, struct bnx2x_vfop, link);
 }
 
+static inline struct bnx2x_vfop *bnx2x_vfop_add(struct bnx2x *bp,
+						struct bnx2x_virtf *vf)
+{
+	struct bnx2x_vfop *vfop = kzalloc(sizeof(*vfop), GFP_KERNEL);
+
+	WARN(!mutex_is_locked(&vf->op_mutex), "about to access vf op linked list but mutex was not locked!");
+	if (vfop) {
+		INIT_LIST_HEAD(&vfop->link);
+		list_add(&vfop->link, &vf->op_list_head);
+	}
+	return vfop;
+}
+
+
+static inline void bnx2x_vfop_end(struct bnx2x *bp, struct bnx2x_virtf *vf,
+				  struct bnx2x_vfop *vfop)
+{
+	/* rc < 0 - error, otherwise set to 0 */
+	DP(BNX2X_MSG_IOV, "rc was %d\n", vfop->rc);
+	if (vfop->rc >= 0)
+		vfop->rc = 0;
+	DP(BNX2X_MSG_IOV, "rc is now %d\n", vfop->rc);
+
+	/* unlink the current op context and propagate error code
+	 * must be done before invoking the 'done()' handler
+	 */
+	WARN(!mutex_is_locked(&vf->op_mutex), "about to access vf op linked list but mutex was not locked!");
+	list_del(&vfop->link);
+
+	if (list_empty(&vf->op_list_head)) {
+		DP(BNX2X_MSG_IOV, "list was empty %d\n", vfop->rc);
+		vf->op_rc = vfop->rc;
+		DP(BNX2X_MSG_IOV, "copying rc vf->op_rc %d,  vfop->rc %d\n",
+		   vf->op_rc, vfop->rc);
+	} else {
+		struct bnx2x_vfop *cur_vfop;
+		DP(BNX2X_MSG_IOV, "list not empty %d\n", vfop->rc);
+		cur_vfop = bnx2x_vfop_cur(bp, vf);
+		cur_vfop->rc = vfop->rc;
+		DP(BNX2X_MSG_IOV, "copying rc vf->op_rc %d, vfop->rc %d\n",
+		   vf->op_rc, vfop->rc);
+	}
+
+	/* invoke done handler */
+	if (vfop->done) {
+		DP(BNX2X_MSG_IOV, "calling done handler\n");
+		vfop->done(bp, vf);
+	}
+
+	DP(BNX2X_MSG_IOV, "done handler complete. vf->op_rc %d, vfop->rc %d\n",
+	   vf->op_rc, vfop->rc);
+
+	/* if this is the last nested op reset the wait_blocking flag
+	 * to release any blocking wrappers, only after 'done()' is invoked
+	 */
+	if (list_empty(&vf->op_list_head)) {
+		DP(BNX2X_MSG_IOV, "list was empty after done %d\n", vfop->rc);
+		vf->op_wait_blocking = false;
+	}
+
+	kfree(vfop);
+}
+
+static inline int bnx2x_vfop_wait_blocking(struct bnx2x *bp,
+					   struct bnx2x_virtf *vf)
+{
+	/* can take a while if any port is running */
+	int cnt = 5000;
+
+	if (CHIP_REV_IS_EMUL(bp))
+		cnt *= 20;
+
+	might_sleep();
+	while (cnt--) {
+		if (vf->op_wait_blocking == false) {
+#ifdef BNX2X_STOP_ON_ERROR
+			DP(BNX2X_MSG_IOV, "exit  (cnt %d)\n", 5000 - cnt);
+#endif
+			return 0;
+		}
+		usleep_range(1000, 2000);
+
+		if (bp->panic)
+			return -EIO;
+	}
+
+	/* timeout! */
+#ifdef BNX2X_STOP_ON_ERROR
+	bnx2x_panic();
+#endif
+
+	return -EBUSY;
+}
+
+static inline int bnx2x_vfop_transition(struct bnx2x *bp,
+					struct bnx2x_virtf *vf,
+					vfop_handler_t transition,
+					bool block)
+{
+	if (block)
+		vf->op_wait_blocking = true;
+	transition(bp, vf);
+	if (block)
+		return bnx2x_vfop_wait_blocking(bp, vf);
+	return 0;
+}
+
+/* VFOP queue construction helpers */
+void bnx2x_vfop_qctor_dump_tx(struct bnx2x *bp, struct bnx2x_virtf *vf,
+			    struct bnx2x_queue_init_params *init_params,
+			    struct bnx2x_queue_setup_params *setup_params,
+			    u16 q_idx, u16 sb_idx);
+
+void bnx2x_vfop_qctor_dump_rx(struct bnx2x *bp, struct bnx2x_virtf *vf,
+			    struct bnx2x_queue_init_params *init_params,
+			    struct bnx2x_queue_setup_params *setup_params,
+			    u16 q_idx, u16 sb_idx);
+
+void bnx2x_vfop_qctor_prep(struct bnx2x *bp,
+			   struct bnx2x_virtf *vf,
+			   struct bnx2x_vf_queue *q,
+			   struct bnx2x_vfop_qctor_params *p,
+			   unsigned long q_type);
+int bnx2x_vfop_qsetup_cmd(struct bnx2x *bp,
+			  struct bnx2x_virtf *vf,
+			  struct bnx2x_vfop_cmd *cmd,
+			  int qid);
+
 int bnx2x_vf_idx_by_abs_fid(struct bnx2x *bp, u16 abs_vfid);
 u8 bnx2x_vf_max_queue_cnt(struct bnx2x *bp, struct bnx2x_virtf *vf);
 /* VF FLR helpers */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index 4fcd974..3f02cf7 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -378,6 +378,148 @@ static void bnx2x_vf_mbx_init_vf(struct bnx2x *bp, struct bnx2x_virtf *vf,
 	bnx2x_vf_mbx_resp(bp, vf);
 }
 
+/* convert MBX queue-flags to standard SP queue-flags */
+static void bnx2x_vf_mbx_set_q_flags(u32 mbx_q_flags,
+				     unsigned long *sp_q_flags)
+{
+	if (mbx_q_flags & VFPF_QUEUE_FLG_TPA)
+		__set_bit(BNX2X_Q_FLG_TPA, sp_q_flags);
+	if (mbx_q_flags & VFPF_QUEUE_FLG_TPA_IPV6)
+		__set_bit(BNX2X_Q_FLG_TPA_IPV6, sp_q_flags);
+	if (mbx_q_flags & VFPF_QUEUE_FLG_TPA_GRO)
+		__set_bit(BNX2X_Q_FLG_TPA_GRO, sp_q_flags);
+	if (mbx_q_flags & VFPF_QUEUE_FLG_STATS)
+		__set_bit(BNX2X_Q_FLG_STATS, sp_q_flags);
+	if (mbx_q_flags & VFPF_QUEUE_FLG_OV)
+		__set_bit(BNX2X_Q_FLG_OV, sp_q_flags);
+	if (mbx_q_flags & VFPF_QUEUE_FLG_VLAN)
+		__set_bit(BNX2X_Q_FLG_VLAN, sp_q_flags);
+	if (mbx_q_flags & VFPF_QUEUE_FLG_COS)
+		__set_bit(BNX2X_Q_FLG_COS, sp_q_flags);
+	if (mbx_q_flags & VFPF_QUEUE_FLG_HC)
+		__set_bit(BNX2X_Q_FLG_HC, sp_q_flags);
+	if (mbx_q_flags & VFPF_QUEUE_FLG_DHC)
+		__set_bit(BNX2X_Q_FLG_DHC, sp_q_flags);
+}
+
+static void bnx2x_vf_mbx_setup_q(struct bnx2x *bp, struct bnx2x_virtf *vf,
+				 struct bnx2x_vf_mbx *mbx)
+{
+	struct vfpf_setup_q_tlv *setup_q = &mbx->msg->req.setup_q;
+	struct bnx2x_vfop_cmd cmd = {
+		.done = bnx2x_vf_mbx_resp,
+		.block = false,
+	};
+
+	/* verify vf_qid */
+	if (setup_q->vf_qid >= vf_rxq_count(vf)) {
+		BNX2X_ERR("vf_qid %d invalid, max queue count is %d\n",
+			  setup_q->vf_qid, vf_rxq_count(vf));
+		vf->op_rc = -EINVAL;
+		goto response;
+	}
+
+	/* tx queues must be setup alongside rx queues thus if the rx queue
+	 * is not marked as valid there's nothing to do.
+	 */
+	if (setup_q->param_valid & (VFPF_RXQ_VALID|VFPF_TXQ_VALID)) {
+		struct bnx2x_vf_queue *q = vfq_get(vf, setup_q->vf_qid);
+		unsigned long q_type = 0;
+
+		struct bnx2x_queue_init_params *init_p;
+		struct bnx2x_queue_setup_params *setup_p;
+
+		/* reinit the VF operation context */
+		memset(&vf->op_params.qctor, 0 , sizeof(vf->op_params.qctor));
+		setup_p = &vf->op_params.qctor.prep_qsetup;
+		init_p =  &vf->op_params.qctor.qstate.params.init;
+
+		/* activate immediateely */
+		__set_bit(BNX2X_Q_FLG_ACTIVE, &setup_p->flags);
+
+		if (setup_q->param_valid & VFPF_TXQ_VALID) {
+			struct bnx2x_txq_setup_params *txq_params =
+				&setup_p->txq_params;
+
+			__set_bit(BNX2X_Q_TYPE_HAS_TX, &q_type);
+
+			/* save sb resource index */
+			q->sb_idx = setup_q->txq.vf_sb;
+
+			/* tx init */
+			init_p->tx.hc_rate = setup_q->txq.hc_rate;
+			init_p->tx.sb_cq_index = setup_q->txq.sb_index;
+
+			bnx2x_vf_mbx_set_q_flags(setup_q->txq.flags,
+						 &init_p->tx.flags);
+
+			/* tx setup - flags */
+			bnx2x_vf_mbx_set_q_flags(setup_q->txq.flags,
+						 &setup_p->flags);
+
+			/* tx setup - general, nothing */
+
+			/* tx setup - tx */
+			txq_params->dscr_map = setup_q->txq.txq_addr;
+			txq_params->sb_cq_index = setup_q->txq.sb_index;
+			txq_params->traffic_type = setup_q->txq.traffic_type;
+
+			bnx2x_vfop_qctor_dump_tx(bp, vf, init_p, setup_p,
+						 q->index, q->sb_idx);
+		}
+
+		if (setup_q->param_valid & VFPF_RXQ_VALID) {
+			struct bnx2x_rxq_setup_params *rxq_params =
+							&setup_p->rxq_params;
+
+			__set_bit(BNX2X_Q_TYPE_HAS_RX, &q_type);
+
+			/* Note: there is no support for different SBs
+			 * for TX and RX
+			 */
+			q->sb_idx = setup_q->rxq.vf_sb;
+
+			/* rx init */
+			init_p->rx.hc_rate = setup_q->rxq.hc_rate;
+			init_p->rx.sb_cq_index = setup_q->rxq.sb_index;
+			bnx2x_vf_mbx_set_q_flags(setup_q->rxq.flags,
+						 &init_p->rx.flags);
+
+			/* rx setup - flags */
+			bnx2x_vf_mbx_set_q_flags(setup_q->rxq.flags,
+						 &setup_p->flags);
+
+			/* rx setup - general */
+			setup_p->gen_params.mtu = setup_q->rxq.mtu;
+
+			/* rx setup - rx */
+			rxq_params->drop_flags = setup_q->rxq.drop_flags;
+			rxq_params->dscr_map = setup_q->rxq.rxq_addr;
+			rxq_params->sge_map = setup_q->rxq.sge_addr;
+			rxq_params->rcq_map = setup_q->rxq.rcq_addr;
+			rxq_params->rcq_np_map = setup_q->rxq.rcq_np_addr;
+			rxq_params->buf_sz = setup_q->rxq.buf_sz;
+			rxq_params->tpa_agg_sz = setup_q->rxq.tpa_agg_sz;
+			rxq_params->max_sges_pkt = setup_q->rxq.max_sge_pkt;
+			rxq_params->sge_buf_sz = setup_q->rxq.sge_buf_sz;
+			rxq_params->cache_line_log =
+				setup_q->rxq.cache_line_log;
+			rxq_params->sb_cq_index = setup_q->rxq.sb_index;
+
+			bnx2x_vfop_qctor_dump_rx(bp, vf, init_p, setup_p,
+						 q->index, q->sb_idx);
+		}
+		/* complete the preparations */
+		bnx2x_vfop_qctor_prep(bp, vf, q, &vf->op_params.qctor, q_type);
+
+		vf->op_rc = bnx2x_vfop_qsetup_cmd(bp, vf, &cmd, q->index);
+		if (vf->op_rc)
+			goto response;
+		return;
+	}
+response:
+	bnx2x_vf_mbx_resp(bp, vf);
+}
 /* dispatch request */
 static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 				  struct bnx2x_vf_mbx *mbx)
@@ -400,6 +542,9 @@ static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		case CHANNEL_TLV_INIT:
 			bnx2x_vf_mbx_init_vf(bp, vf, mbx);
 			break;
+		case CHANNEL_TLV_SETUP_Q:
+			bnx2x_vf_mbx_setup_q(bp, vf, mbx);
+			break;
 		}
 
 	/* unknown TLV - this may belong to a VF driver from the future - a
-- 
1.7.9.GIT

^ permalink raw reply related

* [PATCH 06/22] bnx2x: Add teardown_q and close to VF <-> PF channel
From: Ariel Elior @ 2012-11-13 16:17 UTC (permalink / raw)
  To: David Miller; +Cc: netdev, Ariel Elior, Eilon Greenstein
In-Reply-To: <1352823451-27042-1-git-send-email-ariele@broadcom.com>

When a VF is being closed its queues are released via
the 'teardown_q' and the VF itself is closed with
'close'. These are essentially the unload counterparts of
'init' and 'setup_q' from the load flow.

Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x.h      |    2 +
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c  |   12 +++-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c |   86 ++++++++++++++++++++++
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h |   19 +++++
 4 files changed, 117 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 860b0ce..de6b9d4 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -2227,7 +2227,9 @@ int bnx2x_send_msg2pf(struct bnx2x *bp, u8 *done, dma_addr_t msg_mapping);
 int __devinit bnx2x_vfpf_acquire(struct bnx2x *bp, u8 tx_count, u8 rx_count);
 int __devexit bnx2x_vfpf_release(struct bnx2x *bp);
 int bnx2x_vfpf_init(struct bnx2x *bp);
+void bnx2x_vfpf_close_vf(struct bnx2x *bp);
 int bnx2x_vfpf_setup_q(struct bnx2x *bp, int fp_idx);
+int bnx2x_vfpf_teardown_queue(struct bnx2x *bp, int qidx);
 int bnx2x_vfpf_set_mac(struct bnx2x *bp);
 int bnx2x_nic_load_analyze_req(struct bnx2x *bp, u32 load_code);
 /* Congestion management fairness mode */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 0642c28..9196389 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -2784,9 +2784,17 @@ int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode, bool keep_link)
 	/* wait till consumers catch up with producers in all queues */
 	bnx2x_drain_tx_queues(bp);
 
-	/* Cleanup the chip if needed */
-	if (unload_mode != UNLOAD_RECOVERY)
+	/* if VF indicate to PF this function is going down (PF will delete sp
+	 * elsements and clear initializations
+	 */
+	if (IS_VF(bp))
+		bnx2x_vfpf_close_vf(bp);
+
+	/* if this is a normal/close unload need to clean up chip*/
+	else if (unload_mode != UNLOAD_RECOVERY)
 		bnx2x_chip_cleanup(bp, unload_mode, keep_link);
+
+	/* recovery */
 	else {
 		/* Send the UNLOAD_REQUEST to the MCP */
 		bnx2x_send_unload_req(bp, unload_mode);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index ba152e6..fe7e5ab 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -13399,6 +13399,56 @@ int bnx2x_vfpf_init(struct bnx2x *bp)
 
 	return 0;
 }
+
+/* CLOSE VF - opposite to INIT_VF */
+void bnx2x_vfpf_close_vf(struct bnx2x *bp)
+{
+	struct vfpf_close_tlv *req = &bp->vf2pf_mbox->req.close;
+	struct pfvf_general_resp_tlv *resp = &bp->vf2pf_mbox->resp.general_resp;
+	int i, rc;
+	u32 vf_id;
+
+	/* If we haven't got a valid VF id, there is no sense to
+	 * continue with sending messages
+	 */
+	if (bnx2x_get_vf_id(bp, &vf_id))
+		goto free_irq;
+
+	/* Close the queues */
+	for_each_queue(bp, i)
+		bnx2x_vfpf_teardown_queue(bp, i);
+
+	/* clear mailbox and prep first tlv */
+	bnx2x_vfpf_prep(bp, &req->first_tlv, CHANNEL_TLV_CLOSE, sizeof(*req));
+
+	req->vf_id = vf_id;
+
+	/* add list termination tlv */
+	bnx2x_add_tlv(bp, req, req->first_tlv.tl.length, CHANNEL_TLV_LIST_END,
+		      sizeof(struct channel_list_end_tlv));
+
+	/* output tlvs list */
+	bnx2x_dp_tlv_list(bp, req);
+
+	rc = bnx2x_send_msg2pf(bp, &resp->hdr.status, bp->vf2pf_mbox_mapping);
+
+	if (rc)
+		BNX2X_ERR("Sending CLOSE failed. rc was: %d\n", rc);
+
+	else if (resp->hdr.status != PFVF_STATUS_SUCCESS)
+		BNX2X_ERR("Sending CLOSE failed: pf response was %d\n",
+			  resp->hdr.status);
+
+free_irq:
+	/* Disable HW interrupts, NAPI */
+	bnx2x_netif_stop(bp, 0);
+	/* Delete all NAPI objects */
+	bnx2x_del_all_napi(bp);
+
+	/* Release IRQs */
+	bnx2x_free_irq(bp);
+}
+
 /* ask the pf to open a queue for the vf */
 int bnx2x_vfpf_setup_q(struct bnx2x *bp, int fp_idx)
 {
@@ -13482,6 +13532,42 @@ int bnx2x_vfpf_setup_q(struct bnx2x *bp, int fp_idx)
 	return rc;
 }
 
+int bnx2x_vfpf_teardown_queue(struct bnx2x *bp, int qidx)
+{
+	struct vfpf_q_op_tlv *req = &bp->vf2pf_mbox->req.q_op;
+	struct pfvf_general_resp_tlv *resp = &bp->vf2pf_mbox->resp.general_resp;
+	int rc;
+
+	/* clear mailbox and prep first tlv */
+	bnx2x_vfpf_prep(bp, &req->first_tlv, CHANNEL_TLV_TEARDOWN_Q,
+			sizeof(*req));
+
+	req->vf_qid = qidx;
+
+	/* add list termination tlv */
+	bnx2x_add_tlv(bp, req, req->first_tlv.tl.length, CHANNEL_TLV_LIST_END,
+		      sizeof(struct channel_list_end_tlv));
+
+	/* output tlvs list */
+	bnx2x_dp_tlv_list(bp, req);
+
+	rc = bnx2x_send_msg2pf(bp, &resp->hdr.status, bp->vf2pf_mbox_mapping);
+
+	if (rc) {
+		BNX2X_ERR("Sending TEARDOWN for queue %d failed: %d\n", qidx,
+			  rc);
+		return rc;
+	}
+
+	if (resp->hdr.status != PFVF_STATUS_SUCCESS) {
+		BNX2X_ERR("TEARDOWN for queue %d failed: %d\n", qidx,
+			  resp->hdr.status);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /* request pf to add a mac for the vf */
 int bnx2x_vfpf_set_mac(struct bnx2x *bp)
 {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h
index a4c1ad9..a482d69 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h
@@ -109,6 +109,13 @@ struct vfpf_acquire_tlv {
 	aligned_u64 bulletin_addr;
 };
 
+/* simple operation request on queue */
+struct vfpf_q_op_tlv {
+	struct vfpf_first_tlv	first_tlv;
+	u8 vf_qid;
+	u8 padding[3];
+};
+
 /* acquire response tlv - carries the allocated resources */
 struct pfvf_acquire_resp_tlv {
 	struct pfvf_tlv hdr;
@@ -245,6 +252,14 @@ struct vfpf_set_q_filters_tlv {
 	u32 rx_mask;	/* see mask constants at the top of the file */
 };
 
+
+/* close VF (disable VF) */
+struct vfpf_close_tlv {
+	struct vfpf_first_tlv	first_tlv;
+	u16			vf_id;  /* for debug */
+	u8 padding[2];
+};
+
 /* release the VF's acquired resources */
 struct vfpf_release_tlv {
 	struct vfpf_first_tlv   first_tlv;
@@ -259,6 +274,8 @@ union vfpf_tlvs {
 	struct vfpf_first_tlv		first_tlv;
 	struct vfpf_acquire_tlv		acquire;
 	struct vfpf_init_tlv		init;
+	struct vfpf_close_tlv		close;
+	struct vfpf_q_op_tlv		q_op;
 	struct vfpf_setup_q_tlv		setup_q;
 	struct vfpf_set_q_filters_tlv	set_q_filters;
 	struct vfpf_release_tlv		release;
@@ -278,6 +295,8 @@ enum channel_tlvs {
 	   CHANNEL_TLV_INIT,
 	   CHANNEL_TLV_SETUP_Q,
 	   CHANNEL_TLV_SET_Q_FILTERS,
+	   CHANNEL_TLV_TEARDOWN_Q,
+	   CHANNEL_TLV_CLOSE,
 	   CHANNEL_TLV_RELEASE,
 	   CHANNEL_TLV_LIST_END,
 	   CHANNEL_TLV_MAX
-- 
1.7.9.GIT

^ permalink raw reply related

* [PATCH 22/22] bnx2x: Add VF device ids and enable feature
From: Ariel Elior @ 2012-11-13 16:17 UTC (permalink / raw)
  To: David Miller; +Cc: netdev, Ariel Elior, Eilon Greenstein
In-Reply-To: <1352823451-27042-1-git-send-email-ariele@broadcom.com>

Add the various VF device ids (of all supported hardware)
Add the calls to enable_sriov and disable_sriov to enable the
SR-IOV feature.

Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x.h       |   22 +++++-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c  |   86 +++++++++++++++++++--
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c |    4 +
 3 files changed, 102 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 91beeaf..df9979d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -26,8 +26,8 @@
  * (you will need to reboot afterwards) */
 /* #define BNX2X_STOP_ON_ERROR */
 
-#define DRV_MODULE_VERSION      "1.78.00-0"
-#define DRV_MODULE_RELDATE      "2012/09/27"
+#define DRV_MODULE_VERSION      "1.78.01-0"
+#define DRV_MODULE_RELDATE      "2012/10/30"
 #define BNX2X_BC_VER            0x040200
 
 #if defined(CONFIG_DCB)
@@ -805,36 +805,46 @@ struct bnx2x_common {
 #define CHIP_NUM_57711E			0x1650
 #define CHIP_NUM_57712			0x1662
 #define CHIP_NUM_57712_MF		0x1663
+#define CHIP_NUM_57712_VF		0x166f
 #define CHIP_NUM_57713			0x1651
 #define CHIP_NUM_57713E			0x1652
 #define CHIP_NUM_57800			0x168a
 #define CHIP_NUM_57800_MF		0x16a5
+#define CHIP_NUM_57800_VF		0x16a9
 #define CHIP_NUM_57810			0x168e
 #define CHIP_NUM_57810_MF		0x16ae
+#define CHIP_NUM_57810_VF		0x16af
 #define CHIP_NUM_57811			0x163d
 #define CHIP_NUM_57811_MF		0x163e
+#define CHIP_NUM_57811_VF		0x163f
 #define CHIP_NUM_57840_OBSOLETE	0x168d
 #define CHIP_NUM_57840_MF_OBSOLETE	0x16ab
 #define CHIP_NUM_57840_4_10		0x16a1
 #define CHIP_NUM_57840_2_20		0x16a2
 #define CHIP_NUM_57840_MF		0x16a4
+#define CHIP_NUM_57840_VF		0x16ad
 #define CHIP_IS_E1(bp)			(CHIP_NUM(bp) == CHIP_NUM_57710)
 #define CHIP_IS_57711(bp)		(CHIP_NUM(bp) == CHIP_NUM_57711)
 #define CHIP_IS_57711E(bp)		(CHIP_NUM(bp) == CHIP_NUM_57711E)
 #define CHIP_IS_57712(bp)		(CHIP_NUM(bp) == CHIP_NUM_57712)
+#define CHIP_IS_57712_VF(bp)		(CHIP_NUM(bp) == CHIP_NUM_57712_VF)
 #define CHIP_IS_57712_MF(bp)		(CHIP_NUM(bp) == CHIP_NUM_57712_MF)
 #define CHIP_IS_57800(bp)		(CHIP_NUM(bp) == CHIP_NUM_57800)
 #define CHIP_IS_57800_MF(bp)		(CHIP_NUM(bp) == CHIP_NUM_57800_MF)
+#define CHIP_IS_57800_VF(bp)		(CHIP_NUM(bp) == CHIP_NUM_57800_VF)
 #define CHIP_IS_57810(bp)		(CHIP_NUM(bp) == CHIP_NUM_57810)
 #define CHIP_IS_57810_MF(bp)		(CHIP_NUM(bp) == CHIP_NUM_57810_MF)
+#define CHIP_IS_57810_VF(bp)		(CHIP_NUM(bp) == CHIP_NUM_57810_VF)
 #define CHIP_IS_57811(bp)		(CHIP_NUM(bp) == CHIP_NUM_57811)
 #define CHIP_IS_57811_MF(bp)		(CHIP_NUM(bp) == CHIP_NUM_57811_MF)
+#define CHIP_IS_57811_VF(bp)		(CHIP_NUM(bp) == CHIP_NUM_57811_VF)
 #define CHIP_IS_57840(bp)		\
 		((CHIP_NUM(bp) == CHIP_NUM_57840_4_10) || \
 		 (CHIP_NUM(bp) == CHIP_NUM_57840_2_20) || \
 		 (CHIP_NUM(bp) == CHIP_NUM_57840_OBSOLETE))
 #define CHIP_IS_57840_MF(bp)	((CHIP_NUM(bp) == CHIP_NUM_57840_MF) || \
 				 (CHIP_NUM(bp) == CHIP_NUM_57840_MF_OBSOLETE))
+#define CHIP_IS_57840_VF(bp)		(CHIP_NUM(bp) == CHIP_NUM_57840_VF)
 #define CHIP_IS_E1H(bp)			(CHIP_IS_57711(bp) || \
 					 CHIP_IS_57711E(bp))
 #define CHIP_IS_E2(bp)			(CHIP_IS_57712(bp) || \
@@ -843,10 +853,13 @@ struct bnx2x_common {
 					 CHIP_IS_57800_MF(bp) || \
 					 CHIP_IS_57810(bp) || \
 					 CHIP_IS_57810_MF(bp) || \
+					 CHIP_IS_57810_VF(bp) || \
 					 CHIP_IS_57811(bp) || \
 					 CHIP_IS_57811_MF(bp) || \
+					 CHIP_IS_57811_VF(bp) || \
 					 CHIP_IS_57840(bp) || \
-					 CHIP_IS_57840_MF(bp))
+					 CHIP_IS_57840_MF(bp) || \
+					 CHIP_IS_57840_VF(bp))
 #define CHIP_IS_E1x(bp)			(CHIP_IS_E1((bp)) || CHIP_IS_E1H((bp)))
 #define USES_WARPCORE(bp)		(CHIP_IS_E3(bp))
 #define IS_E1H_OFFSET			(!CHIP_IS_E1(bp))
@@ -1198,8 +1211,9 @@ struct bnx2x_fw_stats_data {
 enum {
 	BNX2X_SP_RTNL_SETUP_TC,
 	BNX2X_SP_RTNL_TX_TIMEOUT,
-	BNX2X_SP_RTNL_AFEX_F_UPDATE,
 	BNX2X_SP_RTNL_FAN_FAILURE,
+	BNX2X_SP_RTNL_AFEX_F_UPDATE,
+	BNX2X_SP_RTNL_ENABLE_SRIOV,
 	BNX2X_SP_RTNL_VFPF_MCAST,
 	BNX2X_SP_RTNL_VFPF_STORM_RX_MODE,
 };
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 22da522..6d278a0 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -193,12 +193,18 @@ static struct {
 #ifndef PCI_DEVICE_ID_NX2_57712_MF
 #define PCI_DEVICE_ID_NX2_57712_MF	CHIP_NUM_57712_MF
 #endif
+#ifndef PCI_DEVICE_ID_NX2_57712_VF
+#define PCI_DEVICE_ID_NX2_57712_VF	CHIP_NUM_57712_VF
+#endif
 #ifndef PCI_DEVICE_ID_NX2_57800
 #define PCI_DEVICE_ID_NX2_57800		CHIP_NUM_57800
 #endif
 #ifndef PCI_DEVICE_ID_NX2_57800_MF
 #define PCI_DEVICE_ID_NX2_57800_MF	CHIP_NUM_57800_MF
 #endif
+#ifndef PCI_DEVICE_ID_NX2_57800_VF
+#define PCI_DEVICE_ID_NX2_57800_VF	CHIP_NUM_57800_VF
+#endif
 #ifndef PCI_DEVICE_ID_NX2_57810
 #define PCI_DEVICE_ID_NX2_57810		CHIP_NUM_57810
 #endif
@@ -208,6 +214,9 @@ static struct {
 #ifndef PCI_DEVICE_ID_NX2_57840_O
 #define PCI_DEVICE_ID_NX2_57840_O	CHIP_NUM_57840_OBSOLETE
 #endif
+#ifndef PCI_DEVICE_ID_NX2_57810_VF
+#define PCI_DEVICE_ID_NX2_57810_VF	CHIP_NUM_57810_VF
+#endif
 #ifndef PCI_DEVICE_ID_NX2_57840_4_10
 #define PCI_DEVICE_ID_NX2_57840_4_10	CHIP_NUM_57840_4_10
 #endif
@@ -220,29 +229,42 @@ static struct {
 #ifndef PCI_DEVICE_ID_NX2_57840_MF
 #define PCI_DEVICE_ID_NX2_57840_MF	CHIP_NUM_57840_MF
 #endif
+#ifndef PCI_DEVICE_ID_NX2_57840_VF
+#define PCI_DEVICE_ID_NX2_57840_VF	CHIP_NUM_57840_VF
+#endif
 #ifndef PCI_DEVICE_ID_NX2_57811
 #define PCI_DEVICE_ID_NX2_57811		CHIP_NUM_57811
 #endif
 #ifndef PCI_DEVICE_ID_NX2_57811_MF
 #define PCI_DEVICE_ID_NX2_57811_MF	CHIP_NUM_57811_MF
 #endif
+#ifndef PCI_DEVICE_ID_NX2_57811_VF
+#define PCI_DEVICE_ID_NX2_57811_VF	CHIP_NUM_57811_VF
+#endif
+
+
 static DEFINE_PCI_DEVICE_TABLE(bnx2x_pci_tbl) = {
 	{ PCI_VDEVICE(BROADCOM, PCI_DEVICE_ID_NX2_57710), BCM57710 },
 	{ PCI_VDEVICE(BROADCOM, PCI_DEVICE_ID_NX2_57711), BCM57711 },
 	{ PCI_VDEVICE(BROADCOM, PCI_DEVICE_ID_NX2_57711E), BCM57711E },
 	{ PCI_VDEVICE(BROADCOM, PCI_DEVICE_ID_NX2_57712), BCM57712 },
 	{ PCI_VDEVICE(BROADCOM, PCI_DEVICE_ID_NX2_57712_MF), BCM57712_MF },
+	{ PCI_VDEVICE(BROADCOM, PCI_DEVICE_ID_NX2_57712_VF), BCM57712_VF },
 	{ PCI_VDEVICE(BROADCOM, PCI_DEVICE_ID_NX2_57800), BCM57800 },
 	{ PCI_VDEVICE(BROADCOM, PCI_DEVICE_ID_NX2_57800_MF), BCM57800_MF },
+	{ PCI_VDEVICE(BROADCOM, PCI_DEVICE_ID_NX2_57800_VF), BCM57800_VF },
 	{ PCI_VDEVICE(BROADCOM, PCI_DEVICE_ID_NX2_57810), BCM57810 },
 	{ PCI_VDEVICE(BROADCOM, PCI_DEVICE_ID_NX2_57810_MF), BCM57810_MF },
 	{ PCI_VDEVICE(BROADCOM, PCI_DEVICE_ID_NX2_57840_O), BCM57840_O },
 	{ PCI_VDEVICE(BROADCOM, PCI_DEVICE_ID_NX2_57840_4_10), BCM57840_4_10 },
 	{ PCI_VDEVICE(BROADCOM, PCI_DEVICE_ID_NX2_57840_2_20), BCM57840_2_20 },
+	{ PCI_VDEVICE(BROADCOM, PCI_DEVICE_ID_NX2_57810_VF), BCM57810_VF },
 	{ PCI_VDEVICE(BROADCOM, PCI_DEVICE_ID_NX2_57840_MFO), BCM57840_MFO },
 	{ PCI_VDEVICE(BROADCOM, PCI_DEVICE_ID_NX2_57840_MF), BCM57840_MF },
+	{ PCI_VDEVICE(BROADCOM, PCI_DEVICE_ID_NX2_57840_VF), BCM57840_VF },
 	{ PCI_VDEVICE(BROADCOM, PCI_DEVICE_ID_NX2_57811), BCM57811 },
 	{ PCI_VDEVICE(BROADCOM, PCI_DEVICE_ID_NX2_57811_MF), BCM57811_MF },
+	{ PCI_VDEVICE(BROADCOM, PCI_DEVICE_ID_NX2_57811_VF), BCM57811_VF },
 	{ 0 }
 };
 
@@ -9407,8 +9429,10 @@ static void bnx2x_sp_rtnl_task(struct work_struct *work)
 
 	rtnl_lock();
 
-	if (!netif_running(bp->dev))
-		goto sp_rtnl_exit;
+	if (!netif_running(bp->dev)) {
+		rtnl_unlock();
+		return;
+	}
 
 	/* if stop on error is defined no recovery flows should be executed */
 #ifdef BNX2X_STOP_ON_ERROR
@@ -9427,7 +9451,8 @@ static void bnx2x_sp_rtnl_task(struct work_struct *work)
 
 		bnx2x_parity_recover(bp);
 
-		goto sp_rtnl_exit;
+		rtnl_unlock();
+		return;
 	}
 
 	if (test_and_clear_bit(BNX2X_SP_RTNL_TX_TIMEOUT, &bp->sp_rtnl_state)) {
@@ -9441,7 +9466,8 @@ static void bnx2x_sp_rtnl_task(struct work_struct *work)
 		bnx2x_nic_unload(bp, UNLOAD_NORMAL, true);
 		bnx2x_nic_load(bp, LOAD_NORMAL);
 
-		goto sp_rtnl_exit;
+		rtnl_unlock();
+		return;
 	}
 #ifdef BNX2X_STOP_ON_ERROR
 sp_rtnl_not_reset:
@@ -9459,6 +9485,8 @@ sp_rtnl_not_reset:
 		DP(NETIF_MSG_HW, "fan failure detected. Unloading driver\n");
 		netif_device_detach(bp->dev);
 		bnx2x_close(bp->dev);
+		rtnl_unlock();
+		return;
 	}
 
 	if (test_and_clear_bit(BNX2X_SP_RTNL_VFPF_MCAST, &bp->sp_rtnl_state)) {
@@ -9474,8 +9502,28 @@ sp_rtnl_not_reset:
 		bnx2x_vfpf_storm_rx_mode(bp);
 	}
 
-sp_rtnl_exit:
+	/* work which needs rtnl lock not-taken (as it takes the lock itself and
+	 * can be called from other contexts as well)
+	 */
+
 	rtnl_unlock();
+
+	if (IS_SRIOV(bp) && test_and_clear_bit(BNX2X_SP_RTNL_ENABLE_SRIOV,
+					       &bp->sp_rtnl_state)) {
+		int rc = 0;
+
+		/* disbale sriov in case it is still enabled */
+		pci_disable_sriov(bp->pdev);
+		DP(BNX2X_MSG_IOV, "sriov disabled");
+
+		/* enable sriov */
+		DP(BNX2X_MSG_IOV, "vf num (%d)\n", (bp->vfdb->sriov.nr_virtfn));
+		rc = pci_enable_sriov(bp->pdev, (bp->vfdb->sriov.nr_virtfn));
+		if (rc)
+			BNX2X_ERR("pci_enable_sriov failed with %d\n", rc);
+		else
+			DP(BNX2X_MSG_IOV, "sriov enabled");
+	}
 }
 
 /* end of nic load/unload */
@@ -11274,6 +11322,26 @@ static int __devinit bnx2x_init_bp(struct bnx2x *bp)
  * net_device service functions
  */
 
+static int bnx2x_open_epilog(struct bnx2x *bp)
+{
+	/* Enable sriov via delayed work. This must be done via delayed work
+	 * because it causes the probe of the vf devices to be run, which invoke
+	 * register_netdevice which must have rtnl lock taken. As we are holding
+	 * the lock right now, that could only work if the probe would not take
+	 * the lock. However, as the probe of the vf may be called from other
+	 * contexts as well (such as passthrough to vm failes) it can't assume
+	 * the lock is being held for it. Using delayed work here allows the
+	 * probe code to simply take the lock (i.e. wait for it to be released
+	 * if it is being held).
+	 */
+	smp_mb__before_clear_bit();
+	set_bit(BNX2X_SP_RTNL_ENABLE_SRIOV, &bp->sp_rtnl_state);
+	smp_mb__after_clear_bit();
+	schedule_delayed_work(&bp->sp_rtnl_task, 0);
+
+	return 0;
+}
+
 /* called with rtnl_lock */
 static int bnx2x_open(struct net_device *dev)
 {
@@ -11281,6 +11349,7 @@ static int bnx2x_open(struct net_device *dev)
 	bool global = false;
 	int other_engine = BP_PATH(bp) ? 0 : 1;
 	bool other_load_status, load_status;
+	int rc;
 
 	bp->stats_init = true;
 
@@ -11338,7 +11407,12 @@ static int bnx2x_open(struct net_device *dev)
 		} while (0);
 
 	bp->recovery_state = BNX2X_RECOVERY_DONE;
-	return bnx2x_nic_load(bp, LOAD_OPEN);
+
+	rc = bnx2x_nic_load(bp, LOAD_OPEN);
+	if (rc)
+		return rc;
+
+	return bnx2x_open_epilog(bp);
 }
 
 /* called with rtnl_lock */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index a4b5f48..c5001ee 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -2031,6 +2031,10 @@ void __devexit bnx2x_iov_remove_one(struct bnx2x *bp)
 	if (!IS_SRIOV(bp))
 		return;
 
+	DP(BNX2X_MSG_IOV, "about to call disable sriov");
+	pci_disable_sriov(bp->pdev);
+	DP(BNX2X_MSG_IOV, "sriov disabled");
+
 
 	/* free vf database */
 	__bnx2x_iov_free_vfdb(bp);
-- 
1.7.9.GIT

^ permalink raw reply related

* [PATCH 21/22] bnx2x: Support PF <-> VF Bulletin Board
From: Ariel Elior @ 2012-11-13 16:17 UTC (permalink / raw)
  To: David Miller; +Cc: netdev, Ariel Elior, Eilon Greenstein
In-Reply-To: <1352823451-27042-1-git-send-email-ariele@broadcom.com>

The PF <-> VF Bulletin Board is a simple interface between the
PF and the VF. The VF publishes at 'acquire' stage the GPA of a
Bulletin Board structure it has allocated. The PF notes this GPA
in the VF database. The VF samples the Bulletin Board periodically
for new messages. The latest version of the BB is always used.

Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x.h       |    6 ++
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c   |   89 +++++++++++++++++++
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h   |    2 +
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c  |   94 ++++++++++++++++++++-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c |   12 +++
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h |   17 ++++
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c  |   67 +++++++++++++++
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h  |   38 ++++++++
 8 files changed, 324 insertions(+), 1 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index dfae9b0..91beeaf 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -1261,6 +1261,12 @@ struct bnx2x {
 	/* we set aside a copy of the acquire response */
 	struct pfvf_acquire_resp_tlv acquire_resp;
 
+	/* bulletin board for messages from pf to vf*/
+	union pf_vf_bulletin   *pf2vf_bulletin;
+	dma_addr_t		pf2vf_bulletin_mapping;
+
+	struct pf_vf_bulletin_content	old_bulletin;
+
 	struct net_device	*dev;
 	struct pci_dev		*pdev;
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index a7165e1..f89728e 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -3793,6 +3793,95 @@ int bnx2x_setup_tc(struct net_device *dev, u8 num_tc)
 	return 0;
 }
 
+/* New mac for VF. Consider these cases:
+ * 1. VF hasn't been acquired yet - save the mac in local bulletin board and
+ *    supply at acquire.
+ * 2. VF has already been acquired but has not yet initialized - store in local
+ *    bulletin board. mac will be posted on VF bulletin board after VF init. VF
+ *    will configure this mac when it is ready.
+ * 3. VF has already initialized but has not yet setup a queue - post the new
+ *    mac on VF's bulletin board right now. VF will configure this mac when it
+ *    is ready.
+ * 4. VF has already set a queue - delete any macs already configured for this
+ *    queue and manually config the new mac.
+ * In any event, once this function has been called refuse any attempts by the
+ * VF to configure any mac for itself except for this mac. In case of a race
+ * where the VF fails to see the new post on its bulletin board before sending a
+ * mac configuration request, the PF will simply fail the request and VF can try
+ * again after consulting its bulletin board
+ */
+int bnx2x_set_vf_mac(struct net_device *dev, int queue, u8 *mac)
+{
+
+	struct bnx2x *bp = netdev_priv(dev);
+	int rc, q_logical_state, vfidx = queue;
+	struct bnx2x_virtf *vf = BP_VF(bp, vfidx);
+	struct pf_vf_bulletin_content *bulletin = BP_VF_BULLETIN(bp, vfidx);
+
+	/* if SRIOV is disabled there is nothing to do (and somewhere, someone
+	 * has erred).
+	 */
+	if (!IS_SRIOV(bp)) {
+		BNX2X_ERR("bnx2x_set_vf_mac called though sriov is disabled\n");
+		return -EINVAL;
+	}
+
+	if (!is_valid_ether_addr(mac)) {
+		BNX2X_ERR("mac address invalid\n");
+		return -EINVAL;
+	}
+
+	/* update PF's copy of the VF's bulletin. will no longer accept mac
+	 * configuration requests from vf unless match this mac
+	 */
+	bulletin->valid_bitmap |= 1 << MAC_ADDR_VALID;
+	memcpy(bulletin->mac, mac, ETH_ALEN);
+
+	/* Post update on VF's bulletin board */
+	rc = bnx2x_post_vf_bulletin(bp, vfidx);
+	if (rc) {
+		BNX2X_ERR("failed to update VF[%d] bulletin", vfidx);
+		return rc;
+	}
+
+	/* is vf initialized and queue set up? */
+	q_logical_state =
+		bnx2x_get_q_logical_state(bp, &bnx2x_vfq(vf, 0, sp_obj));
+	if (vf->state == VF_ENABLED &&
+	    q_logical_state == BNX2X_Q_LOGICAL_STATE_ACTIVE) {
+
+		/* configure the mac in device on this vf's queue */
+		unsigned long flags = 0;
+		struct bnx2x_vlan_mac_obj *mac_obj = &bnx2x_vfq(vf, 0, mac_obj);
+
+		/* must lock vfpf channel to protect against vf flows */
+		bnx2x_lock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_SET_MAC);
+
+		/* remove existing eth macs */
+		rc = bnx2x_del_all_macs(bp, mac_obj, BNX2X_ETH_MAC, true);
+		if (rc) {
+			BNX2X_ERR("failed to delete eth macs\n");
+			return -EINVAL;
+		}
+
+		/* remove existing uc list macs */
+		rc = bnx2x_del_all_macs(bp, mac_obj, BNX2X_UC_LIST_MAC, true);
+		if (rc) {
+			BNX2X_ERR("failed to delete uc_list macs\n");
+			return -EINVAL;
+		}
+
+		/* configure the new mac to device */
+		__set_bit(RAMROD_COMP_WAIT, &flags);
+		bnx2x_set_mac_one(bp, (u8 *)&bulletin->mac, mac_obj, true,
+				  BNX2X_ETH_MAC, &flags);
+
+		bnx2x_unlock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_SET_MAC);
+	}
+
+	return rc;
+}
+
 /* called with rtnl_lock */
 int bnx2x_change_mac_addr(struct net_device *dev, void *p)
 {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index 2dfde45..b80c456 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -496,6 +496,8 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev);
 /* setup_tc callback */
 int bnx2x_setup_tc(struct net_device *dev, u8 num_tc);
 
+int bnx2x_set_vf_mac(struct net_device *dev, int queue, u8 *mac);
+
 /* select_queue callback */
 u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb);
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 05aef19..22da522 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -5230,6 +5230,62 @@ void bnx2x_drv_pulse(struct bnx2x *bp)
 		 bp->fw_drv_pulse_wr_seq);
 }
 
+/* crc is the first field in the bulletin board. compute the crc over the
+ * entire bulletin board excluding the crc field itself */
+u32 bnx2x_crc_vf_bulletin(struct bnx2x *bp,
+			  struct pf_vf_bulletin_content *bulletin)
+{
+	return crc32(BULLETIN_CRC_SEED,
+		 ((u8 *)bulletin) + sizeof(bulletin->crc),
+		 BULLETIN_CONTENT_SIZE - sizeof(bulletin->crc));
+}
+
+/* Check for new posts on the bulletin board */
+enum sample_bulletin_result bnx2x_sample_bulletin(struct bnx2x *bp)
+{
+	struct pf_vf_bulletin_content bulletin = bp->pf2vf_bulletin->content;
+	int attempts;
+
+	/* bulletin board hasn't changed since last sample */
+	if (bp->old_bulletin.version == bulletin.version)
+		return PFVF_BULLETIN_UNCHANGED;
+
+	/* validate crc of new bulletin board */
+	if (bp->old_bulletin.version != bp->pf2vf_bulletin->content.version) {
+
+		/* sampling structure in mid post may result with corrupted data
+		 * validate crc to ensure coherency.
+		 */
+		for (attempts = 0; attempts < BULLETIN_ATTEMPTS; attempts++) {
+			bulletin = bp->pf2vf_bulletin->content;
+			if (bulletin.crc == bnx2x_crc_vf_bulletin(bp,
+								  &bulletin))
+				break;
+
+			BNX2X_ERR("bad crc on bulletin board. contained %x computed %x\n",
+				  bulletin.crc,
+				  bnx2x_crc_vf_bulletin(bp, &bulletin));
+		}
+		if (attempts >= BULLETIN_ATTEMPTS) {
+			BNX2X_ERR("pf to vf bulletin board crc was wrong %d consecutive times. Aborting\n",
+				  attempts);
+			return PFVF_BULLETIN_CRC_ERR;
+		}
+	}
+
+	/* the mac address in bulletin board is valid and is new */
+	if (bulletin.valid_bitmap & 1 << MAC_ADDR_VALID &&
+	    memcmp(bulletin.mac, bp->old_bulletin.mac, ETH_ALEN)) {
+
+		/* update new mac to net device */
+		memcpy(bp->dev->dev_addr, bulletin.mac, ETH_ALEN);
+	}
+
+	/* copy new bulletin board to bp */
+	bp->old_bulletin = bulletin;
+
+	return PFVF_BULLETIN_UPDATED;
+}
 
 static void bnx2x_timer(unsigned long data)
 {
@@ -5267,6 +5323,10 @@ static void bnx2x_timer(unsigned long data)
 	if (bp->state == BNX2X_STATE_OPEN)
 		bnx2x_stats_handle(bp, STATS_EVENT_UPDATE);
 
+	/* sample pf vf bulletin board for new posts from pf */
+	if (IS_VF(bp))
+		bnx2x_sample_bulletin(bp);
+
 	mod_timer(&bp->timer, jiffies + bp->current_interval);
 }
 
@@ -11581,7 +11641,7 @@ static const struct net_device_ops bnx2x_netdev_ops = {
 	.ndo_poll_controller	= poll_bnx2x,
 #endif
 	.ndo_setup_tc		= bnx2x_setup_tc,
-
+	.ndo_set_vf_mac		= bnx2x_set_vf_mac,
 #ifdef NETDEV_FCOE_WWNN
 	.ndo_fcoe_get_wwn	= bnx2x_fcoe_get_wwn,
 #endif
@@ -12246,6 +12306,11 @@ static int __devinit bnx2x_init_one(struct pci_dev *pdev,
 		/* allocate vf2pf mailbox for vf to pf channel */
 		BNX2X_PCI_ALLOC(bp->vf2pf_mbox, &bp->vf2pf_mbox_mapping,
 				sizeof(struct bnx2x_vf_mbx_msg));
+
+		/* allocate pf 2 vf bulletin board */
+		BNX2X_PCI_ALLOC(bp->pf2vf_bulletin, &bp->pf2vf_bulletin_mapping,
+				sizeof(union pf_vf_bulletin));
+
 	} else {
 		doorbell_size = BNX2X_L2_MAX_CID(bp) * (1 << BNX2X_DB_SHIFT);
 		if (doorbell_size > pci_resource_len(pdev, 2)) {
@@ -13304,6 +13369,9 @@ int __devinit bnx2x_vfpf_acquire(struct bnx2x *bp, u8 tx_count,
 	req->resc_request.num_mac_filters = VF_ACQUIRE_MAC_FILTERS;
 	req->resc_request.num_mc_filters = VF_ACQUIRE_MC_FILTERS;
 
+	/* pf 2 vf bulletin board address */
+	req->bulletin_addr = bp->pf2vf_bulletin_mapping;
+
 	/* add list termination tlv */
 	bnx2x_add_tlv(bp, req, req->first_tlv.tl.length, CHANNEL_TLV_LIST_END,
 		      sizeof(struct channel_list_end_tlv));
@@ -13660,6 +13728,9 @@ int bnx2x_vfpf_set_mac(struct bnx2x *bp)
 	req->filters[0].flags =
 		VFPF_Q_FILTER_DEST_MAC_VALID | VFPF_Q_FILTER_SET_MAC;
 
+	/* sample bulletin board for new mac */
+	bnx2x_sample_bulletin(bp);
+
 	/* copy mac from device to request */
 	memcpy(req->filters[0].mac, bp->dev->dev_addr, ETH_ALEN);
 
@@ -13677,6 +13748,27 @@ int bnx2x_vfpf_set_mac(struct bnx2x *bp)
 		return rc;
 	}
 
+	/* failure may mean PF was configured with a new mac for us */
+	while (resp->hdr.status == PFVF_STATUS_FAILURE) {
+
+		DP(BNX2X_MSG_IOV,
+		   "vfpf SET MAC failed. Check bulletin board for new posts\n");
+
+		/* check if bulletin board was updated */
+		if (bnx2x_sample_bulletin(bp) == PFVF_BULLETIN_UPDATED) {
+
+			/* copy mac from device to request */
+			memcpy(req->filters[0].mac, bp->dev->dev_addr,
+			       ETH_ALEN);
+
+			/* send message to pf */
+			rc = bnx2x_send_msg2pf(bp, &resp->hdr.status,
+					       bp->vf2pf_mbox_mapping);
+		} else {
+			/* no new info in bulletin */
+			break;
+		}
+	}
 
 	if (resp->hdr.status != PFVF_STATUS_SUCCESS) {
 		BNX2X_ERR("vfpf SET MAC failed: %d\n", resp->hdr.status);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index ee02374..a4b5f48 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -2056,6 +2056,10 @@ void bnx2x_iov_free_mem(struct bnx2x *bp)
 	BNX2X_PCI_FREE(BP_VF_MBX_DMA(bp)->addr,
 		       BP_VF_MBX_DMA(bp)->mapping,
 		       BP_VF_MBX_DMA(bp)->size);
+
+	BNX2X_PCI_FREE(BP_VF_BULLETIN_DMA(bp)->addr,
+		       BP_VF_BULLETIN_DMA(bp)->mapping,
+		       BP_VF_BULLETIN_DMA(bp)->size);
 }
 
 
@@ -2096,6 +2100,11 @@ int bnx2x_iov_alloc_mem(struct bnx2x *bp)
 			tot_size);
 	BP_VF_MBX_DMA(bp)->size = tot_size;
 
+	/* allocate local bulletin boards */
+	tot_size = BNX2X_NR_VIRTFN(bp) * BULLETIN_CONTENT_SIZE;
+	BNX2X_PCI_ALLOC(BP_VF_BULLETIN_DMA(bp)->addr,
+			&BP_VF_BULLETIN_DMA(bp)->mapping, tot_size);
+	BP_VF_BULLETIN_DMA(bp)->size = tot_size;
 
 	return 0;
 
@@ -2817,6 +2826,9 @@ int bnx2x_vf_init(struct bnx2x *bp, struct bnx2x_virtf *vf, dma_addr_t *sb_map)
 
 	vf->state = VF_ENABLED;
 
+	/* update vf bulletin board */
+	bnx2x_post_vf_bulletin(bp, vf->index);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
index b4efa79..49fa10f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
@@ -387,6 +387,11 @@ struct bnx2x_vfdb {
 	struct bnx2x_vf_mbx	mbxs[BNX2X_MAX_NUM_OF_VFS];
 #define BP_VF_MBX(bp, vfid)	(&((bp)->vfdb->mbxs[(vfid)]))
 
+	struct hw_dma		bulletin_dma;
+#define BP_VF_BULLETIN_DMA(bp)	(&((bp)->vfdb->bulletin_dma))
+#define	BP_VF_BULLETIN(bp, vf) \
+	(((struct pf_vf_bulletin_content *)(BP_VF_BULLETIN_DMA(bp)->addr)) + vf)
+
 	struct hw_dma		sp_dma;
 #define bnx2x_vf_sp(bp, vf, field) ((bp)->vfdb->sp_dma.addr +		\
 		(vf)->index * sizeof(struct bnx2x_vf_sp) +		\
@@ -715,4 +720,16 @@ void bnx2x_dp_tlv_list(struct bnx2x *bp, void *tlvs_list);
 
 bool bnx2x_tlv_supported(u16 tlvtype);
 
+u32 bnx2x_crc_vf_bulletin(struct bnx2x *bp,
+			  struct pf_vf_bulletin_content *bulletin);
+int bnx2x_post_vf_bulletin(struct bnx2x *bp, int vf);
+
+enum sample_bulletin_result {
+	   PFVF_BULLETIN_UNCHANGED,
+	   PFVF_BULLETIN_UPDATED,
+	   PFVF_BULLETIN_CRC_ERR
+};
+
+enum sample_bulletin_result bnx2x_sample_bulletin(struct bnx2x *bp);
+
 #endif /* bnx2x_sriov.h */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index f7a63d2..ba1fe18 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -304,6 +304,10 @@ static void bnx2x_vf_mbx_acquire_resp(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		resc->num_mc_filters = 0;
 
 		if (status == PFVF_STATUS_SUCCESS) {
+			/* fill in the allocated resources */
+			struct pf_vf_bulletin_content *bulletin =
+				BP_VF_BULLETIN(bp, vf->index);
+
 			for_each_vfq(vf, i)
 				resc->hw_qid[i] =
 					vfq_qzone_id(vf, vfq_get(vf, i));
@@ -312,6 +316,12 @@ static void bnx2x_vf_mbx_acquire_resp(struct bnx2x *bp, struct bnx2x_virtf *vf,
 				resc->hw_sbs[i].hw_sb_id = vf_igu_sb(vf, i);
 				resc->hw_sbs[i].sb_qid = vf_hc_qzone(vf, i);
 			}
+
+			/* if a mac has been set for this vf, supply it */
+			if (bulletin->valid_bitmap & 1 << MAC_ADDR_VALID) {
+				memcpy(resc->current_mac_addr, bulletin->mac,
+				       ETH_ALEN);
+			}
 		}
 	}
 
@@ -363,6 +373,9 @@ static void bnx2x_vf_mbx_acquire(struct bnx2x *bp, struct bnx2x_virtf *vf,
 	/* acquire the resources */
 	rc = bnx2x_vf_acquire(bp, vf, &acquire->resc_request);
 
+	/* store address of vf's bulletin board */
+	vf->bulletin_map = acquire->bulletin_addr;
+
 	/* response */
 	bnx2x_vf_mbx_acquire_resp(bp, vf, mbx, rc);
 }
@@ -776,11 +789,39 @@ static void bnx2x_vf_mbx_set_q_filters(struct bnx2x *bp,
 				       struct bnx2x_vf_mbx *mbx)
 {
 	struct vfpf_set_q_filters_tlv *filters = &mbx->msg->req.set_q_filters;
+	struct pf_vf_bulletin_content *bulletin = BP_VF_BULLETIN(bp, vf->index);
 	struct bnx2x_vfop_cmd cmd = {
 		.done = bnx2x_vf_mbx_resp,
 		.block = false,
 	};
 
+	/* if a mac was already set for this VF via the set vf mac ndo, we only
+	 * accept mac configurations of that mac. Why accept them at all?
+	 * because PF may have been unable to configure the mac at the time
+	 * since queue was not set up.
+	 */
+	if (bulletin->valid_bitmap & 1 << MAC_ADDR_VALID) {
+
+		/* once a mac was set by ndo can only accept a single mac... */
+		if (filters->n_mac_vlan_filters > 1) {
+			BNX2X_ERR("VF[%d] requested the addition of multiple macs after set_vf_mac ndo was called\n",
+				  vf->abs_vfid);
+			vf->op_rc = -EPERM;
+			goto response;
+		}
+
+		/* ...and only the mac set by the ndo */
+		if (filters->n_mac_vlan_filters == 1 &&
+		    memcmp(filters->filters->mac, bulletin->mac, ETH_ALEN)) {
+
+			BNX2X_ERR("VF[%d] requested the addition of a mac address not matching the one configured by set_vf_mac ndo\n",
+				  vf->abs_vfid);
+
+
+			vf->op_rc = -EPERM;
+			goto response;
+		}
+	}
 
 	/* verify vf_qid */
 	if (filters->vf_qid > vf_rxq_count(vf))
@@ -994,3 +1035,29 @@ mbx_error:
 mbx_done:
 	return;
 }
+
+/* propagate local bulletin board to vf */
+int bnx2x_post_vf_bulletin(struct bnx2x *bp, int vf)
+{
+	struct pf_vf_bulletin_content *bulletin = BP_VF_BULLETIN(bp, vf);
+	dma_addr_t pf_addr = BP_VF_BULLETIN_DMA(bp)->mapping +
+		vf * BULLETIN_CONTENT_SIZE;
+	dma_addr_t vf_addr = bnx2x_vf(bp, vf, bulletin_map);
+	u32 len = BULLETIN_CONTENT_SIZE;
+	int rc;
+
+	/* can only update vf after init took place */
+	if (bnx2x_vf(bp, vf, state) != VF_ENABLED &&
+	    bnx2x_vf(bp, vf, state) != VF_ACQUIRED)
+		return 0;
+
+	/* increment bulletin board version and compute crc */
+	bulletin->version++;
+	bulletin->crc = bnx2x_crc_vf_bulletin(bp, bulletin);
+
+	/* propagate bulletin board via dmae to vm memory */
+	rc = bnx2x_copy32_vf_dmae(bp, false, pf_addr,
+				  bnx2x_vf(bp, vf, abs_vfid), U64_HI(vf_addr),
+				  U64_LO(vf_addr), len/4);
+	return rc;
+}
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h
index 0cf6e7f..21dda5a 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h
@@ -36,6 +36,7 @@ struct hw_sb_info {
  * A.K.A VF-PF mailbox
  */
 #define TLV_BUFFER_SIZE			1024
+#define PF_VF_BULLETIN_SIZE		512
 
 #define VFPF_QUEUE_FLG_TPA		0x0001
 #define VFPF_QUEUE_FLG_TPA_IPV6		0x0002
@@ -59,6 +60,9 @@ struct hw_sb_info {
 #define VFPF_RX_MASK_ACCEPT_ALL_UNICAST		0x00000004
 #define VFPF_RX_MASK_ACCEPT_ALL_MULTICAST	0x00000008
 #define VFPF_RX_MASK_ACCEPT_BROADCAST		0x00000010
+#define BULLETIN_CONTENT_SIZE		(sizeof(struct pf_vf_bulletin_content))
+#define BULLETIN_ATTEMPTS	5 /* crc failures before throwing towel */
+#define BULLETIN_CRC_SEED	0
 
 enum {
 	PFVF_STATUS_WAITING = 0,
@@ -296,6 +300,39 @@ union pfvf_tlvs {
 	struct channel_list_end_tlv	list_end;
 	struct tlv_buffer_size		tlv_buf_size;
 };
+
+/* This is a structure which is allocated in the VF, which the PF may update
+ * when it deems it necessary to do so. The bulletin board is sampled
+ * periodically by the VF. A copy per VF is maintained in the PF (to prevent
+ * loss of data upon multiple updates (or the need for read modify write)).
+ */
+struct pf_vf_bulletin_size {
+	u8 size[PF_VF_BULLETIN_SIZE];
+};
+
+struct pf_vf_bulletin_content {
+	u32 crc;			/* crc of structure to ensure is not in
+					 * mid-update
+					 */
+	u32 version;
+
+	aligned_u64 valid_bitmap;	/* bitmap indicating which fields
+					 * hold valid values
+					 */
+
+#define MAC_ADDR_VALID		0	/* alert the vf that a new mac address
+					 * is available for it
+					 */
+
+	u8 mac[ETH_ALEN];
+	u8 padding[2];
+};
+
+union pf_vf_bulletin {
+	struct pf_vf_bulletin_content content;
+	struct pf_vf_bulletin_size size;
+};
+
 enum channel_tlvs {
 	   CHANNEL_TLV_NONE, /* ends tlv sequence */
 	   CHANNEL_TLV_ACQUIRE,
@@ -308,6 +345,7 @@ enum channel_tlvs {
 	   CHANNEL_TLV_PF_RELEASE_VF,
 	   CHANNEL_TLV_LIST_END,
 	   CHANNEL_TLV_FLR,
+	   CHANNEL_TLV_PF_SET_MAC,
 	   CHANNEL_TLV_MAX
 };
 
-- 
1.7.9.GIT

^ permalink raw reply related

* [PATCH 19/22] bnx2x: Support of PF driver of a VF release request
From: Ariel Elior @ 2012-11-13 16:17 UTC (permalink / raw)
  To: David Miller; +Cc: netdev, Ariel Elior, Eilon Greenstein
In-Reply-To: <1352823451-27042-1-git-send-email-ariele@broadcom.com>

The 'release' request is the opposite of the 'acquire' request.
At release, all the resources allocated to the VF are reclaimed.
The release flow applies the close flow if applicable.
Note that there are actually two types of release:
1. The VF has been removed, and so issued a 'release' request
over the VF <-> PF Channel.
2. The PF is going down and so has to release all of it's VFs.

Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c  |    1 +
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c |  126 +++++++++++++++++++++
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h |   24 ++++
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c  |   25 ++++-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h  |    1 +
 5 files changed, 176 insertions(+), 1 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index bc40081..4418bc4 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -8611,6 +8611,7 @@ void bnx2x_chip_cleanup(struct bnx2x *bp, int unload_mode, bool keep_link)
 
 	netif_addr_unlock_bh(bp->dev);
 
+	bnx2x_iov_chip_cleanup(bp);
 
 
 	/*
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index 71640f3..f083b5d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -1425,6 +1425,14 @@ bnx2x_iov_static_resc(struct bnx2x *bp, struct vf_pf_resc_request *resc)
 	/* num_sbs already set */
 }
 
+/* FLR routines: */
+static void bnx2x_vf_free_resc(struct bnx2x *bp, struct bnx2x_virtf *vf)
+{
+	/* reset the state variables */
+	bnx2x_iov_static_resc(bp, &vf->alloc_resc);
+	vf->state = VF_FREE;
+}
+
 /* called by bnx2x_init_hw_func, returns the next ilt line */
 
 /* IOV global initialization routines  */
@@ -1950,6 +1958,23 @@ int bnx2x_iov_nic_init(struct bnx2x *bp)
 	return 0;
 }
 
+/* called by bnx2x_chip_cleanup */
+int bnx2x_iov_chip_cleanup(struct bnx2x *bp)
+{
+	int i;
+
+	if (!IS_SRIOV(bp))
+		return 0;
+
+	/* release all the VFs */
+	for_each_vf(bp, i)
+		bnx2x_vf_release(bp, BP_VF(bp, i), true); /* blocking */
+
+	return 0;
+}
+
+
+/* called by bnx2x_init_hw_func, returns the next ilt line */
 int bnx2x_iov_init_ilt(struct bnx2x *bp, u16 line)
 {
 	int i;
@@ -2571,6 +2596,107 @@ int bnx2x_vfop_close_cmd(struct bnx2x *bp,
 	}
 	return -ENOMEM;
 }
+
+
+/* VF release can be called either: 1. the VF was acquired but
+ * not enabled 2. the vf was enabled or in the process of being
+ * enabled
+ */
+static void bnx2x_vfop_release(struct bnx2x *bp, struct bnx2x_virtf *vf)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
+	struct bnx2x_vfop_cmd cmd = {
+		.done = bnx2x_vfop_release,
+		.block = false,
+	};
+
+	DP(BNX2X_MSG_IOV, "vfop->rc %d\n", vfop->rc);
+
+	if (vfop->rc < 0)
+		goto op_err;
+
+	DP(BNX2X_MSG_IOV, "VF[%d] STATE: %s\n", vf->abs_vfid,
+	   vf->state == VF_FREE ? "Free" :
+	   vf->state == VF_ACQUIRED ? "Acquired" :
+	   vf->state == VF_ENABLED ? "Enabled" :
+	   vf->state == VF_RESET ? "Reset" :
+	   "Unknown");
+
+	switch (vf->state) {
+	case VF_ENABLED:
+		vfop->rc = bnx2x_vfop_close_cmd(bp, vf, &cmd);
+		if (vfop->rc)
+			goto op_err;
+		return;
+
+	case VF_ACQUIRED:
+		DP(BNX2X_MSG_IOV, "about to free resources\n");
+		bnx2x_vf_free_resc(bp, vf);
+		DP(BNX2X_MSG_IOV, "vfop->rc %d\n", vfop->rc);
+		goto op_done;
+
+	case VF_FREE:
+	case VF_RESET:
+		/* do nothing */
+		goto op_done;
+	default:
+		bnx2x_vfop_default(vf->state);
+	}
+op_err:
+	BNX2X_ERR("VF[%d] RELEASE error: rc %d\n", vf->abs_vfid, vfop->rc);
+op_done:
+	bnx2x_vfop_end(bp, vf, vfop);
+}
+
+int bnx2x_vfop_release_cmd(struct bnx2x *bp,
+			   struct bnx2x_virtf *vf,
+			   struct bnx2x_vfop_cmd *cmd)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+	if (vfop) {
+		bnx2x_vfop_opset(-1, /* use vf->state */
+				 bnx2x_vfop_release, cmd->done);
+		return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_release,
+					     cmd->block);
+	}
+	return -ENOMEM;
+}
+
+
+/* VF release ~ VF close + VF release-resources
+ * Release is the ultimate SW shutdown and is called whenever an
+ * irrecoverable error is encountered.
+ */
+void bnx2x_vf_release(struct bnx2x *bp, struct bnx2x_virtf *vf, bool block)
+{
+	struct bnx2x_vfop_cmd cmd = {
+		.done = NULL,
+		.block = block,
+	};
+	int rc;
+	bnx2x_lock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_RELEASE_VF);
+	rc = bnx2x_vfop_release_cmd(bp, vf, &cmd);
+	if (rc)
+		WARN(rc,
+		     "VF[%d] Failed to allocate resources for release op- rc=%d\n",
+		     vf->abs_vfid, rc);
+}
+
+inline void bnx2x_vf_get_sbdf(struct bnx2x *bp,
+			      struct bnx2x_virtf *vf, u32 *sbdf)
+{
+	*sbdf = vf->devfn | (vf->bus << 8);
+}
+
+inline void bnx2x_vf_get_bars(struct bnx2x *bp, struct bnx2x_virtf *vf,
+		       struct bnx2x_vf_bar_info *bar_info)
+{
+	int n;
+	bar_info->nr_bars = bp->vfdb->sriov.nres;
+	for (n = 0; n < bar_info->nr_bars; n++)
+		bar_info->bars[n] = vf->bars[n];
+}
+
 void bnx2x_lock_vf_pf_channel(struct bnx2x *bp, struct bnx2x_virtf *vf,
 			      enum channel_tlvs tlv)
 {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
index 3c81029..3815b20 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
@@ -49,6 +49,13 @@ struct bnx2x_vf_bar {
 	u64 bar;
 	u32 size;
 };
+
+struct bnx2x_vf_bar_info {
+	struct bnx2x_vf_bar bars[PCI_SRIOV_NUM_BARS];
+	u8 nr_bars;
+};
+
+
 /* vf queue (used both for rx or tx) */
 struct bnx2x_vf_queue {
 	struct eth_context		*cxt;
@@ -434,6 +441,7 @@ void __devexit bnx2x_iov_remove_one(struct bnx2x *bp);
 void bnx2x_iov_free_mem(struct bnx2x *bp);
 int bnx2x_iov_alloc_mem(struct bnx2x *bp);
 int bnx2x_iov_nic_init(struct bnx2x *bp);
+int bnx2x_iov_chip_cleanup(struct bnx2x *bp);
 void bnx2x_iov_init_dq(struct bnx2x *bp);
 void bnx2x_iov_init_dmae(struct bnx2x *bp);
 void bnx2x_iov_set_queue_sp_obj(struct bnx2x *bp, int vf_cid,
@@ -553,6 +561,11 @@ static inline void bnx2x_vfop_end(struct bnx2x *bp, struct bnx2x_virtf *vf,
 	if (vfop->done) {
 		DP(BNX2X_MSG_IOV, "calling done handler\n");
 		vfop->done(bp, vf);
+	} else {
+		/* there is no done handler for the operation to unlock
+		 * the mutex. Must have gotten here from PF initiated VF RELEASE
+		 */
+		bnx2x_unlock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_RELEASE_VF);
 	}
 
 	DP(BNX2X_MSG_IOV, "done handler complete. vf->op_rc %d, vfop->rc %d\n",
@@ -671,6 +684,17 @@ int bnx2x_vfop_close_cmd(struct bnx2x *bp,
 			 struct bnx2x_virtf *vf,
 			 struct bnx2x_vfop_cmd *cmd);
 
+int bnx2x_vfop_release_cmd(struct bnx2x *bp,
+			   struct bnx2x_virtf *vf,
+			   struct bnx2x_vfop_cmd *cmd);
+
+/**
+ * VF release ~ VF close + VF release-resources
+ *
+ * Release is the ultimate SW shutdown and is called whenever an
+ * irrecoverable error is encountered.
+ */
+void bnx2x_vf_release(struct bnx2x *bp, struct bnx2x_virtf *vf, bool block);
 int bnx2x_vf_idx_by_abs_fid(struct bnx2x *bp, u16 abs_vfid);
 u8 bnx2x_vf_max_queue_cnt(struct bnx2x *bp, struct bnx2x_virtf *vf);
 /* VF FLR helpers */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index acf5f54..f7a63d2 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -234,7 +234,7 @@ static void bnx2x_vf_mbx_resp(struct bnx2x *bp, struct bnx2x_virtf *vf)
 		if (rc) {
 			BNX2X_ERR("Failed to copy response body to VF %d\n",
 				  vf->abs_vfid);
-			return;
+			goto mbx_error;
 		}
 		vf_addr -= sizeof(u64);
 		pf_addr -= sizeof(u64);
@@ -261,8 +261,12 @@ static void bnx2x_vf_mbx_resp(struct bnx2x *bp, struct bnx2x_virtf *vf)
 	if (rc) {
 		BNX2X_ERR("Failed to copy response status to VF %d\n",
 			  vf->abs_vfid);
+		goto mbx_error;
 	}
 	return;
+
+mbx_error:
+	bnx2x_vf_release(bp, vf, false); /* non blocking */
 }
 
 static void bnx2x_vf_mbx_acquire_resp(struct bnx2x *bp, struct bnx2x_virtf *vf,
@@ -838,6 +842,21 @@ static void bnx2x_vf_mbx_close_vf(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		bnx2x_vf_mbx_close_done(bp, vf);
 }
 
+static void bnx2x_vf_mbx_release_vf(struct bnx2x *bp, struct bnx2x_virtf *vf,
+				    struct bnx2x_vf_mbx *mbx)
+{
+	struct bnx2x_vfop_cmd cmd = {
+		.done = bnx2x_vf_mbx_resp,
+		.block = false,
+	};
+
+	DP(BNX2X_MSG_IOV, "VF[%d] VF_RELEASE\n", vf->abs_vfid);
+
+	vf->op_rc = bnx2x_vfop_release_cmd(bp, vf, &cmd);
+	if (vf->op_rc)
+		bnx2x_vf_mbx_resp(bp, vf);
+}
+
 /* dispatch request */
 static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 				  struct bnx2x_vf_mbx *mbx)
@@ -872,6 +891,9 @@ static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		case CHANNEL_TLV_CLOSE:
 			bnx2x_vf_mbx_close_vf(bp, vf, mbx);
 			break;
+		case CHANNEL_TLV_RELEASE:
+			bnx2x_vf_mbx_release_vf(bp, vf, mbx);
+			break;
 		}
 
 	/* unknown TLV - this may belong to a VF driver from the future - a
@@ -968,6 +990,7 @@ void bnx2x_vf_mbx(struct bnx2x *bp, struct vf_pf_event_data *vfpf_event)
 	goto mbx_done;
 
 mbx_error:
+	bnx2x_vf_release(bp, vf, false); /* non blocking */
 mbx_done:
 	return;
 }
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h
index 7fe5b83..13c76df 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h
@@ -305,6 +305,7 @@ enum channel_tlvs {
 	   CHANNEL_TLV_TEARDOWN_Q,
 	   CHANNEL_TLV_CLOSE,
 	   CHANNEL_TLV_RELEASE,
+	   CHANNEL_TLV_PF_RELEASE_VF,
 	   CHANNEL_TLV_LIST_END,
 	   CHANNEL_TLV_MAX
 };
-- 
1.7.9.GIT

^ permalink raw reply related

* [PATCH 16/22] bnx2x: Support of PF driver of a VF q_filters request
From: Ariel Elior @ 2012-11-13 16:17 UTC (permalink / raw)
  To: David Miller; +Cc: netdev, Ariel Elior, Eilon Greenstein
In-Reply-To: <1352823451-27042-1-git-send-email-ariele@broadcom.com>

The VF driver uses the 'q_filters' message on the VF <-> PF channel
for configuring an open queue, for example when the rxmode changes.

Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c |  298 ++++++++++++++++++++-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h |   32 +++
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c  |  280 +++++++++++++++++++
 3 files changed, 603 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index 2411f6c..55082cc 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -101,6 +101,8 @@ static void bnx2x_vf_igu_ack_sb(struct bnx2x *bp, struct bnx2x_virtf *vf,
 }
 /* VFOP - VF slow-path operation support */
 
+#define BNX2X_VFOP_FILTER_ADD_CNT_MAX		0x10000
+
 /* VFOP operations states */
 enum bnx2x_vfop_qctor_state {
 	   BNX2X_VFOP_QCTOR_INIT,
@@ -123,6 +125,18 @@ enum bnx2x_vfop_qsetup_state {
 	   BNX2X_VFOP_QSETUP_DONE
 };
 
+enum bnx2x_vfop_mcast_state {
+	   BNX2X_VFOP_MCAST_DEL,
+	   BNX2X_VFOP_MCAST_ADD,
+	   BNX2X_VFOP_MCAST_CHK_DONE
+};
+
+enum bnx2x_vfop_rxmode_state {
+	   BNX2X_VFOP_RXMODE_CONFIG,
+	   BNX2X_VFOP_RXMODE_DONE
+};
+
+
 #define bnx2x_vfop_reset_wq(vf)	atomic_set(&vf->op_in_progress, 0)
 
 void bnx2x_vfop_qctor_dump_tx(struct bnx2x *bp, struct bnx2x_virtf *vf,
@@ -550,7 +564,7 @@ struct bnx2x_vfop_vlan_mac_flags {
 	bool add;
 };
 
-static inline void
+static void
 bnx2x_vfop_vlan_mac_prep_ramrod(struct bnx2x_vlan_mac_ramrod_params *ramrod,
 				struct bnx2x_vfop_vlan_mac_flags *flags)
 {
@@ -572,6 +586,56 @@ bnx2x_vfop_vlan_mac_prep_ramrod(struct bnx2x_vlan_mac_ramrod_params *ramrod,
 	ureq->cmd = flags->add ? BNX2X_VLAN_MAC_ADD : BNX2X_VLAN_MAC_DEL;
 }
 
+static inline void
+bnx2x_vfop_mac_prep_ramrod(struct bnx2x_vlan_mac_ramrod_params *ramrod,
+			   struct bnx2x_vfop_vlan_mac_flags *flags)
+{
+	bnx2x_vfop_vlan_mac_prep_ramrod(ramrod, flags);
+	set_bit(BNX2X_ETH_MAC, &ramrod->user_req.vlan_mac_flags);
+}
+
+int bnx2x_vfop_mac_list_cmd(struct bnx2x *bp,
+			    struct bnx2x_virtf *vf,
+			    struct bnx2x_vfop_cmd *cmd,
+			    struct bnx2x_vfop_filters *macs,
+			    int qid, bool drv_only)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+
+	if (vfop) {
+		struct bnx2x_vfop_args_filters filters = {
+			.multi_filter = macs,
+			.credit = NULL,		/* consume credit */
+		};
+		struct bnx2x_vfop_vlan_mac_flags flags = {
+			.drv_only = drv_only,
+			.dont_consume = (filters.credit != NULL),
+			.single_cmd = false,
+			.add = false, /* don't care since only the items in the
+				       * filters list affect the sp operation,
+				       * not the list itself
+				       */
+		};
+		struct bnx2x_vlan_mac_ramrod_params *ramrod =
+			&vf->op_params.vlan_mac;
+
+		/* set ramrod params */
+		bnx2x_vfop_mac_prep_ramrod(ramrod, &flags);
+
+		/* set object */
+		ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, mac_obj);
+
+		/* set extra args */
+		filters.multi_filter->add_cnt = BNX2X_VFOP_FILTER_ADD_CNT_MAX;
+		vfop->args.filters = filters;
+
+		bnx2x_vfop_opset(BNX2X_VFOP_MAC_CONFIG_LIST,
+				 bnx2x_vfop_vlan_mac, cmd->done);
+		return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_vlan_mac,
+					     cmd->block);
+	}
+	return -ENOMEM;
+}
 
 int bnx2x_vfop_vlan_set_cmd(struct bnx2x *bp,
 			    struct bnx2x_virtf *vf,
@@ -612,6 +676,48 @@ int bnx2x_vfop_vlan_set_cmd(struct bnx2x *bp,
 	return -ENOMEM;
 }
 
+int bnx2x_vfop_vlan_list_cmd(struct bnx2x *bp,
+			     struct bnx2x_virtf *vf,
+			     struct bnx2x_vfop_cmd *cmd,
+			     struct bnx2x_vfop_filters *vlans,
+			     int qid, bool drv_only)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+
+	if (vfop) {
+		struct bnx2x_vfop_args_filters filters = {
+			.multi_filter = vlans,
+			.credit = &bnx2x_vfq(vf, qid, vlan_count),
+		};
+		struct bnx2x_vfop_vlan_mac_flags flags = {
+			.drv_only = drv_only,
+			.dont_consume = (filters.credit != NULL),
+			.single_cmd = false,
+			.add = false, /* don't care */
+		};
+		struct bnx2x_vlan_mac_ramrod_params *ramrod =
+			&vf->op_params.vlan_mac;
+
+		/* set ramrod params */
+		bnx2x_vfop_vlan_mac_prep_ramrod(ramrod, &flags);
+
+		/* set object */
+		ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, vlan_obj);
+
+		/* set extra args */
+		filters.multi_filter->add_cnt = vf_vlan_rules_cnt(vf) -
+			atomic_read(filters.credit);
+
+		vfop->args.filters = filters;
+
+		bnx2x_vfop_opset(BNX2X_VFOP_VLAN_CONFIG_LIST,
+				 bnx2x_vfop_vlan_mac, cmd->done);
+		return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_vlan_mac,
+					     cmd->block);
+	}
+	return -ENOMEM;
+}
+
 /* VFOP queue setup (queue constructor + set vlan 0) */
 static void bnx2x_vfop_qsetup(struct bnx2x *bp, struct bnx2x_virtf *vf)
 {
@@ -678,16 +784,181 @@ int bnx2x_vfop_qsetup_cmd(struct bnx2x *bp,
 }
 
 
-static u8 bnx2x_iov_get_max_queue_count(struct bnx2x *bp)
+/* VFOP multi-casts */
+static void bnx2x_vfop_mcast(struct bnx2x *bp, struct bnx2x_virtf *vf)
 {
+	struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
+	struct bnx2x_mcast_ramrod_params *mcast = &vfop->op_p->mcast;
+	struct bnx2x_raw_obj *raw = &mcast->mcast_obj->raw;
+	struct bnx2x_vfop_args_mcast *args = &vfop->args.mc_list;
+	enum bnx2x_vfop_mcast_state state = vfop->state;
 	int i;
-	u8 queue_count = 0;
 
-	if (IS_SRIOV(bp))
-		for_each_vf(bp, i)
-			queue_count += bnx2x_vf(bp, i, alloc_resc.num_sbs);
+	bnx2x_vfop_reset_wq(vf);
+
+	if (vfop->rc < 0)
+		goto op_err;
+
+	DP(BNX2X_MSG_IOV, "vf[%d] STATE: %d\n", vf->abs_vfid, state);
+
+	switch (state) {
+	case BNX2X_VFOP_MCAST_DEL:
+		/* clear existing mcasts */
+		vfop->state = BNX2X_VFOP_MCAST_ADD;
+		vfop->rc = bnx2x_config_mcast(bp, mcast, BNX2X_MCAST_CMD_DEL);
+		bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
+
+	case BNX2X_VFOP_MCAST_ADD:
+		if (raw->check_pending(raw))
+			goto op_pending;
+
+		if (args->mc_num) {
+			/* update mcast list on the ramrod params */
+			INIT_LIST_HEAD(&mcast->mcast_list);
+			for (i = 0; i < args->mc_num; i++)
+				list_add_tail(&(args->mc[i].link),
+					      &mcast->mcast_list);
+			/* add new mcasts */
+			vfop->state = BNX2X_VFOP_MCAST_CHK_DONE;
+			vfop->rc = bnx2x_config_mcast(bp, mcast,
+						      BNX2X_MCAST_CMD_ADD);
+		}
+		bnx2x_vfop_finalize(vf, vfop->rc, VFOP_DONE);
+
+	case BNX2X_VFOP_MCAST_CHK_DONE:
+		vfop->rc = raw->check_pending(raw) ? 1 : 0;
+		bnx2x_vfop_finalize(vf, vfop->rc, VFOP_DONE);
+	default:
+		bnx2x_vfop_default(state);
+	}
+op_err:
+	BNX2X_ERR("MCAST CONFIG error: rc %d\n", vfop->rc);
+op_done:
+	kfree(args->mc);
+	bnx2x_vfop_end(bp, vf, vfop);
+op_pending:
+	return;
+}
+
+int bnx2x_vfop_mcast_cmd(struct bnx2x *bp,
+			 struct bnx2x_virtf *vf,
+			 struct bnx2x_vfop_cmd *cmd,
+			 bnx2x_mac_addr_t *mcasts,
+			 int mcast_num, bool drv_only)
+{
+	struct bnx2x_vfop *vfop = NULL;
+	size_t mc_sz = mcast_num * sizeof(struct bnx2x_mcast_list_elem);
+	struct bnx2x_mcast_list_elem *mc = mc_sz ? kzalloc(mc_sz, GFP_KERNEL) :
+		NULL;
+
+	if (!mc_sz || mc) {
+		vfop = bnx2x_vfop_add(bp, vf);
+		if (vfop) {
+			int i;
+			struct bnx2x_mcast_ramrod_params *ramrod =
+				&vf->op_params.mcast;
+
+			/* set ramrod params */
+			memset(ramrod, 0, sizeof(*ramrod));
+			ramrod->mcast_obj = &vf->mcast_obj;
+			if (drv_only)
+				set_bit(RAMROD_DRV_CLR_ONLY,
+					&ramrod->ramrod_flags);
+
+			/* copy mcasts pointers */
+			vfop->args.mc_list.mc_num = mcast_num;
+			vfop->args.mc_list.mc = mc;
+			for (i = 0; i < mcast_num; i++)
+				mc[i].mac = mcasts[i];
+
+			bnx2x_vfop_opset(BNX2X_VFOP_MCAST_DEL,
+					 bnx2x_vfop_mcast, cmd->done);
+			return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_mcast,
+						     cmd->block);
+		} else {
+			kfree(mc);
+		}
+	}
+	return -ENOMEM;
+}
+
+/* VFOP rx-mode */
+static void bnx2x_vfop_rxmode(struct bnx2x *bp, struct bnx2x_virtf *vf)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
+	struct bnx2x_rx_mode_ramrod_params *ramrod = &vfop->op_p->rx_mode;
+	enum bnx2x_vfop_rxmode_state state = vfop->state;
+
+	bnx2x_vfop_reset_wq(vf);
+
+	if (vfop->rc < 0)
+		goto op_err;
+
+	DP(BNX2X_MSG_IOV, "vf[%d] STATE: %d\n", vf->abs_vfid, state);
+
+	switch (state) {
+	case BNX2X_VFOP_RXMODE_CONFIG:
+		/* next state */
+		vfop->state = BNX2X_VFOP_RXMODE_DONE;
+
+		vfop->rc = bnx2x_config_rx_mode(bp, ramrod);
+		bnx2x_vfop_finalize(vf, vfop->rc, VFOP_DONE);
+op_err:
+	BNX2X_ERR("RXMODE error: rc %d\n", vfop->rc);
+op_done:
+	case BNX2X_VFOP_RXMODE_DONE:
+		bnx2x_vfop_end(bp, vf, vfop);
+		return;
+	default:
+		bnx2x_vfop_default(state);
+	}
+op_pending:
+	return;
+}
+
+
+int bnx2x_vfop_rxmode_cmd(struct bnx2x *bp,
+			  struct bnx2x_virtf *vf,
+			  struct bnx2x_vfop_cmd *cmd,
+			  int qid, unsigned long accept_flags)
+{
+
+	struct bnx2x_vf_queue *vfq = vfq_get(vf, qid);
+	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+
+	if (vfop) {
+		struct bnx2x_rx_mode_ramrod_params *ramrod =
+			&vf->op_params.rx_mode;
+
+		memset(ramrod, 0, sizeof(*ramrod));
+
+		/* Prepare ramrod parameters */
+		ramrod->cid = vfq->cid;
+		ramrod->cl_id = vfq_cl_id(vf, vfq);
+		ramrod->rx_mode_obj = &bp->rx_mode_obj;
+		ramrod->func_id = FW_VF_HANDLE(vf->abs_vfid);
+
+		ramrod->rx_accept_flags = accept_flags;
+		ramrod->tx_accept_flags = accept_flags;
+		ramrod->pstate = &vf->filter_state;
+		ramrod->state = BNX2X_FILTER_RX_MODE_PENDING;
+
+		set_bit(BNX2X_FILTER_RX_MODE_PENDING, &vf->filter_state);
+		set_bit(RAMROD_RX, &ramrod->ramrod_flags);
+		set_bit(RAMROD_TX, &ramrod->ramrod_flags);
+
+		ramrod->rdata =
+			bnx2x_vf_sp(bp, vf, rx_mode_rdata.e2);
+		ramrod->rdata_mapping =
+			bnx2x_vf_sp_map(bp, vf, rx_mode_rdata.e2);
+
+		bnx2x_vfop_opset(BNX2X_VFOP_RXMODE_CONFIG,
+				 bnx2x_vfop_rxmode, cmd->done);
+		return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_rxmode,
+					     cmd->block);
+	}
+	return -ENOMEM;
 
-	return queue_count;
 }
 
 /* VF enable primitives
@@ -1056,6 +1327,19 @@ static int bnx2x_sriov_info(struct bnx2x *bp, struct bnx2x_sriov *iov)
 
 	return 0;
 }
+
+static u8 bnx2x_iov_get_max_queue_count(struct bnx2x *bp)
+{
+	int i;
+	u8 queue_count = 0;
+
+	if (IS_SRIOV(bp))
+		for_each_vf(bp, i)
+			queue_count += bnx2x_vf(bp, i, alloc_resc.num_sbs);
+
+	return queue_count;
+}
+
 /* must be called after PF bars are mapped */
 int __devinit bnx2x_iov_init_one(struct bnx2x *bp, int int_mode_param,
 				 int num_vfs_param)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
index 64b0c1d..c3be848 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
@@ -446,6 +446,10 @@ void bnx2x_iov_sp_task(struct bnx2x *bp);
 /* global vf mailbox routines */
 void bnx2x_vf_mbx(struct bnx2x *bp, struct vf_pf_event_data *vfpf_event);
 void bnx2x_vf_enable_mbx(struct bnx2x *bp, u8 abs_vfid);
+
+/* CORE VF API */
+typedef u8 bnx2x_mac_addr_t[ETH_ALEN];
+
 /* acquire */
 int bnx2x_vf_acquire(struct bnx2x *bp, struct bnx2x_virtf *vf,
 			  struct vf_pf_resc_request *resc);
@@ -625,11 +629,39 @@ void bnx2x_vfop_qctor_prep(struct bnx2x *bp,
 			   struct bnx2x_vf_queue *q,
 			   struct bnx2x_vfop_qctor_params *p,
 			   unsigned long q_type);
+int bnx2x_vfop_mac_list_cmd(struct bnx2x *bp,
+			    struct bnx2x_virtf *vf,
+			    struct bnx2x_vfop_cmd *cmd,
+			    struct bnx2x_vfop_filters *macs,
+			    int qid, bool drv_only);
+
+int bnx2x_vfop_vlan_set_cmd(struct bnx2x *bp,
+			    struct bnx2x_virtf *vf,
+			    struct bnx2x_vfop_cmd *cmd,
+			    int qid, u16 vid, bool add);
+
+int bnx2x_vfop_vlan_list_cmd(struct bnx2x *bp,
+			     struct bnx2x_virtf *vf,
+			     struct bnx2x_vfop_cmd *cmd,
+			     struct bnx2x_vfop_filters *vlans,
+			     int qid, bool drv_only);
+
 int bnx2x_vfop_qsetup_cmd(struct bnx2x *bp,
 			  struct bnx2x_virtf *vf,
 			  struct bnx2x_vfop_cmd *cmd,
 			  int qid);
 
+int bnx2x_vfop_mcast_cmd(struct bnx2x *bp,
+			 struct bnx2x_virtf *vf,
+			 struct bnx2x_vfop_cmd *cmd,
+			 bnx2x_mac_addr_t *mcasts,
+			 int mcast_num, bool drv_only);
+
+int bnx2x_vfop_rxmode_cmd(struct bnx2x *bp,
+			  struct bnx2x_virtf *vf,
+			  struct bnx2x_vfop_cmd *cmd,
+			  int qid, unsigned long accept_flags);
+
 int bnx2x_vf_idx_by_abs_fid(struct bnx2x *bp, u16 abs_vfid);
 u8 bnx2x_vf_max_queue_cnt(struct bnx2x *bp, struct bnx2x_virtf *vf);
 /* VF FLR helpers */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index 3f02cf7..39862a2 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -520,6 +520,283 @@ static void bnx2x_vf_mbx_setup_q(struct bnx2x *bp, struct bnx2x_virtf *vf,
 response:
 	bnx2x_vf_mbx_resp(bp, vf);
 }
+
+enum bnx2x_vfop_filters_state {
+	   BNX2X_VFOP_MBX_Q_FILTERS_MACS,
+	   BNX2X_VFOP_MBX_Q_FILTERS_VLANS,
+	   BNX2X_VFOP_MBX_Q_FILTERS_RXMODE,
+	   BNX2X_VFOP_MBX_Q_FILTERS_MCAST,
+	   BNX2X_VFOP_MBX_Q_FILTERS_DONE
+};
+
+static int bnx2x_vf_mbx_macvlan_list(struct bnx2x *bp,
+				     struct bnx2x_virtf *vf,
+				     struct vfpf_set_q_filters_tlv *tlv,
+				     struct bnx2x_vfop_filters **pfl,
+				     u32 type_flag)
+{
+	int i, j;
+	struct bnx2x_vfop_filters *fl = NULL;
+	size_t fsz;
+
+	fsz = tlv->n_mac_vlan_filters * sizeof(struct bnx2x_vfop_filter) +
+		sizeof(struct bnx2x_vfop_filters);
+
+	fl = kzalloc(fsz, GFP_KERNEL);
+	if (!fl)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&fl->head);
+
+	for (i = 0, j = 0; i < tlv->n_mac_vlan_filters; i++) {
+		struct vfpf_q_mac_vlan_filter *msg_filter = &tlv->filters[i];
+
+		if ((msg_filter->flags & type_flag) != type_flag)
+			continue;
+		if (type_flag == VFPF_Q_FILTER_DEST_MAC_VALID) {
+			fl->filters[j].mac = msg_filter->mac;
+			fl->filters[j].type = BNX2X_VFOP_FILTER_MAC;
+		} else {
+			fl->filters[j].vid = msg_filter->vlan_tag;
+			fl->filters[j].type = BNX2X_VFOP_FILTER_VLAN;
+		}
+		fl->filters[j].add =
+			(msg_filter->flags & VFPF_Q_FILTER_SET_MAC) ?
+			true : false;
+		list_add_tail(&fl->filters[j++].link, &fl->head);
+	}
+	if (list_empty(&fl->head))
+		kfree(fl);
+	else
+		*pfl = fl;
+
+	return 0;
+}
+
+static void bnx2x_vf_mbx_dp_q_filter(struct bnx2x *bp, int msglvl, int idx,
+				       struct vfpf_q_mac_vlan_filter *filter)
+{
+	DP(msglvl, "MAC-VLAN[%d] -- flags=0x%x", idx, filter->flags);
+	if (filter->flags & VFPF_Q_FILTER_VLAN_TAG_VALID)
+		DP_CONT(msglvl, ", vlan=%d", filter->vlan_tag);
+	if (filter->flags & VFPF_Q_FILTER_DEST_MAC_VALID)
+		DP_CONT(msglvl, ", MAC=%pM", filter->mac);
+	DP_CONT(msglvl, "\n");
+}
+
+static void bnx2x_vf_mbx_dp_q_filters(struct bnx2x *bp, int msglvl,
+				       struct vfpf_set_q_filters_tlv *filters)
+{
+	int i;
+
+	if (filters->flags & VFPF_SET_Q_FILTERS_MAC_VLAN_CHANGED)
+		for (i = 0; i < filters->n_mac_vlan_filters; i++)
+			bnx2x_vf_mbx_dp_q_filter(bp, msglvl, i,
+						 &filters->filters[i]);
+
+	if (filters->flags & VFPF_SET_Q_FILTERS_RX_MASK_CHANGED)
+		DP(msglvl, "RX-MASK=0x%x\n", filters->rx_mask);
+
+	if (filters->flags & VFPF_SET_Q_FILTERS_MULTICAST_CHANGED)
+		for (i = 0; i < filters->n_multicast; i++)
+			DP(msglvl, "MULTICAST=%pM\n", filters->multicast[i]);
+}
+
+
+#define VFPF_MAC_FILTER		VFPF_Q_FILTER_DEST_MAC_VALID
+#define VFPF_VLAN_FILTER	VFPF_Q_FILTER_VLAN_TAG_VALID
+
+static void bnx2x_vfop_mbx_qfilters(struct bnx2x *bp, struct bnx2x_virtf *vf)
+{
+	int rc;
+
+	struct vfpf_set_q_filters_tlv *msg =
+		&BP_VF_MBX(bp, vf->index)->msg->req.set_q_filters;
+
+	struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
+	enum bnx2x_vfop_filters_state state = vfop->state;
+
+	struct bnx2x_vfop_cmd cmd = {
+		.done = bnx2x_vfop_mbx_qfilters,
+		.block = false,
+	};
+
+
+	DP(BNX2X_MSG_IOV, "STATE: %d\n", state);
+
+	if (vfop->rc < 0)
+		goto op_err;
+
+	switch (state) {
+	case BNX2X_VFOP_MBX_Q_FILTERS_MACS:
+		/* next state */
+		vfop->state = BNX2X_VFOP_MBX_Q_FILTERS_VLANS;
+
+		/* check for any vlan/mac changes */
+		if (msg->flags & VFPF_SET_Q_FILTERS_MAC_VLAN_CHANGED) {
+
+			/* build mac list */
+			struct bnx2x_vfop_filters *fl = NULL;
+			vfop->rc = bnx2x_vf_mbx_macvlan_list(bp, vf, msg, &fl,
+							     VFPF_MAC_FILTER);
+			if (vfop->rc)
+				goto op_err;
+
+			if (fl) {
+				/* set mac list */
+				rc = bnx2x_vfop_mac_list_cmd(bp, vf, &cmd, fl,
+							     msg->vf_qid,
+							     false);
+				if (rc) {
+					vfop->rc = rc;
+					goto op_err;
+				}
+				return;
+			}
+		}
+		/* fall through */
+
+	case BNX2X_VFOP_MBX_Q_FILTERS_VLANS:
+		/* next state */
+		vfop->state = BNX2X_VFOP_MBX_Q_FILTERS_RXMODE;
+
+		/* check for any vlan/mac changes */
+		if (msg->flags & VFPF_SET_Q_FILTERS_MAC_VLAN_CHANGED) {
+
+			/* build vlan list */
+			struct bnx2x_vfop_filters *fl = NULL;
+			vfop->rc = bnx2x_vf_mbx_macvlan_list(bp, vf, msg, &fl,
+							     VFPF_VLAN_FILTER);
+			if (vfop->rc)
+				goto op_err;
+
+			if (fl) {
+				/* set vlan list */
+				rc = bnx2x_vfop_vlan_list_cmd(bp, vf, &cmd, fl,
+							      msg->vf_qid,
+							      false);
+				if (rc) {
+					vfop->rc = rc;
+					goto op_err;
+				}
+				return;
+			}
+		}
+		/* fall through */
+
+	case BNX2X_VFOP_MBX_Q_FILTERS_RXMODE:
+		/* next state */
+		vfop->state = BNX2X_VFOP_MBX_Q_FILTERS_MCAST;
+
+		if (msg->flags & VFPF_SET_Q_FILTERS_RX_MASK_CHANGED) {
+			unsigned long accept = 0;
+
+			/* covert VF-PF if mask to bnx2x accept flags */
+			if (msg->rx_mask & VFPF_RX_MASK_ACCEPT_MATCHED_UNICAST)
+				__set_bit(BNX2X_ACCEPT_UNICAST, &accept);
+
+			if (msg->rx_mask &
+					VFPF_RX_MASK_ACCEPT_MATCHED_MULTICAST)
+				__set_bit(BNX2X_ACCEPT_MULTICAST, &accept);
+
+			if (msg->rx_mask & VFPF_RX_MASK_ACCEPT_ALL_UNICAST)
+				__set_bit(BNX2X_ACCEPT_ALL_UNICAST, &accept);
+
+			if (msg->rx_mask & VFPF_RX_MASK_ACCEPT_ALL_MULTICAST)
+				__set_bit(BNX2X_ACCEPT_ALL_MULTICAST, &accept);
+
+			if (msg->rx_mask & VFPF_RX_MASK_ACCEPT_BROADCAST)
+				__set_bit(BNX2X_ACCEPT_BROADCAST, &accept);
+
+			/* A packet arriving the vf's mac should be accepted
+			 * with any vlan
+			 */
+			__set_bit(BNX2X_ACCEPT_ANY_VLAN, &accept);
+
+			/* set rx-mode */
+			rc = bnx2x_vfop_rxmode_cmd(bp, vf, &cmd,
+						   msg->vf_qid, accept);
+			if (rc) {
+				vfop->rc = rc;
+				goto op_err;
+			}
+			return;
+		}
+		/* fall through */
+
+	case BNX2X_VFOP_MBX_Q_FILTERS_MCAST:
+		/* next state */
+		vfop->state = BNX2X_VFOP_MBX_Q_FILTERS_DONE;
+
+		if (msg->flags & VFPF_SET_Q_FILTERS_MULTICAST_CHANGED) {
+			/* set mcasts */
+			rc = bnx2x_vfop_mcast_cmd(bp, vf, &cmd, msg->multicast,
+						  msg->n_multicast, false);
+			if (rc) {
+				vfop->rc = rc;
+				goto op_err;
+			}
+			return;
+		}
+		/* fall through */
+op_done:
+	case BNX2X_VFOP_MBX_Q_FILTERS_DONE:
+		bnx2x_vfop_end(bp, vf, vfop);
+		return;
+op_err:
+	BNX2X_ERR("QFILTERS[%d:%d] error: rc %d\n",
+		  vf->abs_vfid, msg->vf_qid, vfop->rc);
+	goto op_done;
+
+	default:
+		bnx2x_vfop_default(state);
+	}
+}
+
+static int bnx2x_vfop_mbx_qfilters_cmd(struct bnx2x *bp,
+					struct bnx2x_virtf *vf,
+					struct bnx2x_vfop_cmd *cmd)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+	if (vfop) {
+		bnx2x_vfop_opset(BNX2X_VFOP_MBX_Q_FILTERS_MACS,
+				 bnx2x_vfop_mbx_qfilters, cmd->done);
+		return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_mbx_qfilters,
+					     cmd->block);
+	}
+	return -ENOMEM;
+}
+
+static void bnx2x_vf_mbx_set_q_filters(struct bnx2x *bp,
+				       struct bnx2x_virtf *vf,
+				       struct bnx2x_vf_mbx *mbx)
+{
+	struct vfpf_set_q_filters_tlv *filters = &mbx->msg->req.set_q_filters;
+	struct bnx2x_vfop_cmd cmd = {
+		.done = bnx2x_vf_mbx_resp,
+		.block = false,
+	};
+
+
+	/* verify vf_qid */
+	if (filters->vf_qid > vf_rxq_count(vf))
+		goto response;
+
+	DP(BNX2X_MSG_IOV, "VF[%d] Q_FILTERS: queue[%d]\n",
+	   vf->abs_vfid,
+	   filters->vf_qid);
+
+	/* print q_filter message */
+	bnx2x_vf_mbx_dp_q_filters(bp, BNX2X_MSG_IOV, filters);
+
+	vf->op_rc = bnx2x_vfop_mbx_qfilters_cmd(bp, vf, &cmd);
+	if (vf->op_rc)
+		goto response;
+	return;
+
+response:
+	bnx2x_vf_mbx_resp(bp, vf);
+}
 /* dispatch request */
 static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 				  struct bnx2x_vf_mbx *mbx)
@@ -545,6 +822,9 @@ static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		case CHANNEL_TLV_SETUP_Q:
 			bnx2x_vf_mbx_setup_q(bp, vf, mbx);
 			break;
+		case CHANNEL_TLV_SET_Q_FILTERS:
+			bnx2x_vf_mbx_set_q_filters(bp, vf, mbx);
+			break;
 		}
 
 	/* unknown TLV - this may belong to a VF driver from the future - a
-- 
1.7.9.GIT

^ permalink raw reply related

* [PATCH 17/22] bnx2x: Support of PF driver of a VF q_teardown request
From: Ariel Elior @ 2012-11-13 16:17 UTC (permalink / raw)
  To: David Miller; +Cc: netdev, Ariel Elior, Eilon Greenstein
In-Reply-To: <1352823451-27042-1-git-send-email-ariele@broadcom.com>

The 'q_teardown' request is basically the opposite of the 'q_setup'.
Here the PF driver removes from the device the queue it opened against
the VF fastpath ring at 'setup_q' stage, along with all related
rx_mode info.

Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c |  267 +++++++++++++++++++++
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h |    5 +
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c  |   20 ++
 3 files changed, 292 insertions(+), 0 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index 55082cc..2c1945e 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -110,6 +110,13 @@ enum bnx2x_vfop_qctor_state {
 	   BNX2X_VFOP_QCTOR_INT_EN
 };
 
+enum bnx2x_vfop_qdtor_state {
+	   BNX2X_VFOP_QDTOR_HALT,
+	   BNX2X_VFOP_QDTOR_TERMINATE,
+	   BNX2X_VFOP_QDTOR_CFCDEL,
+	   BNX2X_VFOP_QDTOR_DONE
+};
+
 enum bnx2x_vfop_vlan_mac_state {
 	   BNX2X_VFOP_VLAN_MAC_CONFIG_SINGLE,
 	   BNX2X_VFOP_VLAN_MAC_CLEAR,
@@ -136,6 +143,13 @@ enum bnx2x_vfop_rxmode_state {
 	   BNX2X_VFOP_RXMODE_DONE
 };
 
+enum bnx2x_vfop_qteardown_state {
+	   BNX2X_VFOP_QTEARDOWN_RXMODE,
+	   BNX2X_VFOP_QTEARDOWN_CLR_VLAN,
+	   BNX2X_VFOP_QTEARDOWN_CLR_MAC,
+	   BNX2X_VFOP_QTEARDOWN_QDTOR,
+	   BNX2X_VFOP_QTEARDOWN_DONE
+};
 
 #define bnx2x_vfop_reset_wq(vf)	atomic_set(&vf->op_in_progress, 0)
 
@@ -343,6 +357,102 @@ static int bnx2x_vfop_qctor_cmd(struct bnx2x *bp,
 	return -ENOMEM;
 }
 
+/* VFOP queue destruction */
+static void bnx2x_vfop_qdtor(struct bnx2x *bp, struct bnx2x_virtf *vf)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
+	struct bnx2x_vfop_args_qdtor *qdtor = &vfop->args.qdtor;
+	struct bnx2x_queue_state_params *q_params = &vfop->op_p->qctor.qstate;
+	enum bnx2x_vfop_qdtor_state state = vfop->state;
+
+	bnx2x_vfop_reset_wq(vf);
+
+	if (vfop->rc < 0)
+		goto op_err;
+
+	DP(BNX2X_MSG_IOV, "vf[%d] STATE: %d\n", vf->abs_vfid, state);
+
+	switch (state) {
+	case BNX2X_VFOP_QDTOR_HALT:
+
+		/* has this queue already been stopped? */
+		if (bnx2x_get_q_logical_state(bp, q_params->q_obj) ==
+		    BNX2X_Q_LOGICAL_STATE_STOPPED) {
+			DP(BNX2X_MSG_IOV,
+			   "Entered qdtor but queue was already stopped. Aborting gracefully\n");
+			goto op_done;
+		}
+
+		/* next state */
+		vfop->state = BNX2X_VFOP_QDTOR_TERMINATE;
+
+		q_params->cmd = BNX2X_Q_CMD_HALT;
+		vfop->rc = bnx2x_queue_state_change(bp, q_params);
+
+		bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
+
+	case BNX2X_VFOP_QDTOR_TERMINATE:
+		/* next state */
+		vfop->state = BNX2X_VFOP_QDTOR_CFCDEL;
+
+		q_params->cmd = BNX2X_Q_CMD_TERMINATE;
+		vfop->rc = bnx2x_queue_state_change(bp, q_params);
+
+		bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
+
+	case BNX2X_VFOP_QDTOR_CFCDEL:
+		/* next state */
+		vfop->state = BNX2X_VFOP_QDTOR_DONE;
+
+		q_params->cmd = BNX2X_Q_CMD_CFC_DEL;
+		vfop->rc = bnx2x_queue_state_change(bp, q_params);
+
+		bnx2x_vfop_finalize(vf, vfop->rc, VFOP_DONE);
+op_err:
+	BNX2X_ERR("QDTOR[%d:%d] error: cmd %d, rc %d\n",
+		  vf->abs_vfid, qdtor->qid, q_params->cmd, vfop->rc);
+op_done:
+	case BNX2X_VFOP_QDTOR_DONE:
+		/* invalidate the context */
+		qdtor->cxt->ustorm_ag_context.cdu_usage = 0;
+		qdtor->cxt->xstorm_ag_context.cdu_reserved = 0;
+		bnx2x_vfop_end(bp, vf, vfop);
+		return;
+	default:
+		bnx2x_vfop_default(state);
+	}
+op_pending:
+	return;
+}
+
+static int bnx2x_vfop_qdtor_cmd(struct bnx2x *bp,
+				struct bnx2x_virtf *vf,
+				struct bnx2x_vfop_cmd *cmd,
+				int qid)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+
+
+	if (vfop) {
+		struct bnx2x_queue_state_params *qstate =
+			&vf->op_params.qctor.qstate;
+
+		memset(qstate, 0, sizeof(*qstate));
+		qstate->q_obj = &bnx2x_vfq(vf, qid, sp_obj);
+
+		vfop->args.qdtor.qid = qid;
+		vfop->args.qdtor.cxt = bnx2x_vfq(vf, qid, cxt);
+
+		bnx2x_vfop_opset(BNX2X_VFOP_QDTOR_HALT,
+				 bnx2x_vfop_qdtor, cmd->done);
+		return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_qdtor,
+					     cmd->block);
+	}
+	DP(BNX2X_MSG_IOV, "VF[%d] failed to add a vfop. rc %d\n",
+	   vf->abs_vfid, vfop->rc);
+	return -ENOMEM;
+}
+
 static inline void __devinit
 bnx2x_vf_set_igu_info(struct bnx2x *bp, u8 igu_sb_id, u8 abs_vfid)
 {
@@ -594,6 +704,44 @@ bnx2x_vfop_mac_prep_ramrod(struct bnx2x_vlan_mac_ramrod_params *ramrod,
 	set_bit(BNX2X_ETH_MAC, &ramrod->user_req.vlan_mac_flags);
 }
 
+static int bnx2x_vfop_mac_delall_cmd(struct bnx2x *bp,
+				     struct bnx2x_virtf *vf,
+				     struct bnx2x_vfop_cmd *cmd,
+				     int qid, bool drv_only)
+{
+
+	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+
+	if (vfop) {
+		struct bnx2x_vfop_args_filters filters = {
+			.multi_filter = NULL,	/* single */
+			.credit = NULL,		/* consume credit */
+		};
+		struct bnx2x_vfop_vlan_mac_flags flags = {
+			.drv_only = drv_only,
+			.dont_consume = (filters.credit != NULL),
+			.single_cmd = true,
+			.add = false /* don't care */,
+		};
+		struct bnx2x_vlan_mac_ramrod_params *ramrod =
+			&vf->op_params.vlan_mac;
+
+		/* set ramrod params */
+		bnx2x_vfop_mac_prep_ramrod(ramrod, &flags);
+
+		/* set object */
+		ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, mac_obj);
+
+		/* set extra args */
+		vfop->args.filters = filters;
+
+		bnx2x_vfop_opset(BNX2X_VFOP_VLAN_MAC_CLEAR,
+				 bnx2x_vfop_vlan_mac, cmd->done);
+		return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_vlan_mac,
+					     cmd->block);
+	}
+	return -ENOMEM;
+}
 int bnx2x_vfop_mac_list_cmd(struct bnx2x *bp,
 			    struct bnx2x_virtf *vf,
 			    struct bnx2x_vfop_cmd *cmd,
@@ -676,6 +824,44 @@ int bnx2x_vfop_vlan_set_cmd(struct bnx2x *bp,
 	return -ENOMEM;
 }
 
+static int bnx2x_vfop_vlan_delall_cmd(struct bnx2x *bp,
+			       struct bnx2x_virtf *vf,
+			       struct bnx2x_vfop_cmd *cmd,
+			       int qid, bool drv_only)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+
+	if (vfop) {
+		struct bnx2x_vfop_args_filters filters = {
+			.multi_filter = NULL, /* single command */
+			.credit = &bnx2x_vfq(vf, qid, vlan_count),
+		};
+		struct bnx2x_vfop_vlan_mac_flags flags = {
+			.drv_only = drv_only,
+			.dont_consume = (filters.credit != NULL),
+			.single_cmd = true,
+			.add = false, /* don't care */
+		};
+		struct bnx2x_vlan_mac_ramrod_params *ramrod =
+			&vf->op_params.vlan_mac;
+
+		/* set ramrod params */
+		bnx2x_vfop_vlan_mac_prep_ramrod(ramrod, &flags);
+
+		/* set object */
+		ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, vlan_obj);
+
+		/* set extra args */
+		vfop->args.filters = filters;
+
+		bnx2x_vfop_opset(BNX2X_VFOP_VLAN_MAC_CLEAR,
+				 bnx2x_vfop_vlan_mac, cmd->done);
+		return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_vlan_mac,
+					     cmd->block);
+	}
+	return -ENOMEM;
+}
+
 int bnx2x_vfop_vlan_list_cmd(struct bnx2x *bp,
 			     struct bnx2x_virtf *vf,
 			     struct bnx2x_vfop_cmd *cmd,
@@ -961,6 +1147,87 @@ int bnx2x_vfop_rxmode_cmd(struct bnx2x *bp,
 
 }
 
+/* VFOP queue tear-down ('drop all' rx-mode, clear vlans, clear macs,
+ * queue destructor)
+ */
+static void bnx2x_vfop_qdown(struct bnx2x *bp, struct bnx2x_virtf *vf)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
+	int qid = vfop->args.qx.qid;
+	enum bnx2x_vfop_qteardown_state state = vfop->state;
+	struct bnx2x_vfop_cmd cmd;
+
+	if (vfop->rc < 0)
+		goto op_err;
+
+	DP(BNX2X_MSG_IOV, "vf[%d] STATE: %d\n", vf->abs_vfid, state);
+
+	cmd.done = bnx2x_vfop_qdown;
+	cmd.block = false;
+
+	switch (state) {
+	case BNX2X_VFOP_QTEARDOWN_RXMODE:
+		/* Drop all */
+		vfop->state = BNX2X_VFOP_QTEARDOWN_CLR_VLAN;
+		vfop->rc = bnx2x_vfop_rxmode_cmd(bp, vf, &cmd, qid, 0);
+		if (vfop->rc)
+			goto op_err;
+		return;
+
+	case BNX2X_VFOP_QTEARDOWN_CLR_VLAN:
+		/* vlan-clear-all: don't consume credit */
+		vfop->state = BNX2X_VFOP_QTEARDOWN_CLR_MAC;
+		vfop->rc = bnx2x_vfop_vlan_delall_cmd(bp, vf, &cmd, qid, false);
+		if (vfop->rc)
+			goto op_err;
+		return;
+
+	case BNX2X_VFOP_QTEARDOWN_CLR_MAC:
+		/* mac-clear-all: consume credit */
+		vfop->state = BNX2X_VFOP_QTEARDOWN_QDTOR;
+		vfop->rc = bnx2x_vfop_mac_delall_cmd(bp, vf, &cmd, qid, false);
+		if (vfop->rc)
+			goto op_err;
+		return;
+
+	case BNX2X_VFOP_QTEARDOWN_QDTOR:
+		/* run the queue destruction flow */
+		DP(BNX2X_MSG_IOV, "case: BNX2X_VFOP_QTEARDOWN_QDTOR\n");
+		vfop->state = BNX2X_VFOP_QTEARDOWN_DONE;
+		DP(BNX2X_MSG_IOV, "new state: BNX2X_VFOP_QTEARDOWN_DONE\n");
+		vfop->rc = bnx2x_vfop_qdtor_cmd(bp, vf, &cmd, qid);
+		DP(BNX2X_MSG_IOV, "returned from cmd");
+		if (vfop->rc)
+			goto op_err;
+		return;
+op_err:
+	BNX2X_ERR("QTEARDOWN[%d:%d] error: rc %d\n",
+		  vf->abs_vfid, qid, vfop->rc);
+
+	case BNX2X_VFOP_QTEARDOWN_DONE:
+		bnx2x_vfop_end(bp, vf, vfop);
+		return;
+	default:
+		bnx2x_vfop_default(state);
+	}
+}
+
+int bnx2x_vfop_qdown_cmd(struct bnx2x *bp,
+			 struct bnx2x_virtf *vf,
+			 struct bnx2x_vfop_cmd *cmd,
+			 int qid)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+
+	if (vfop) {
+		vfop->args.qx.qid = qid;
+		bnx2x_vfop_opset(BNX2X_VFOP_QTEARDOWN_RXMODE,
+				 bnx2x_vfop_qdown, cmd->done);
+		return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_qdown,
+					     cmd->block);
+	}
+	return -ENOMEM;
+}
 /* VF enable primitives
  *
  * when pretend is required the caller is responsible
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
index c3be848..5c3e921 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
@@ -651,6 +651,11 @@ int bnx2x_vfop_qsetup_cmd(struct bnx2x *bp,
 			  struct bnx2x_vfop_cmd *cmd,
 			  int qid);
 
+int bnx2x_vfop_qdown_cmd(struct bnx2x *bp,
+			 struct bnx2x_virtf *vf,
+			 struct bnx2x_vfop_cmd *cmd,
+			 int qid);
+
 int bnx2x_vfop_mcast_cmd(struct bnx2x *bp,
 			 struct bnx2x_virtf *vf,
 			 struct bnx2x_vfop_cmd *cmd,
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index 39862a2..20c929a 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -797,6 +797,23 @@ static void bnx2x_vf_mbx_set_q_filters(struct bnx2x *bp,
 response:
 	bnx2x_vf_mbx_resp(bp, vf);
 }
+static void bnx2x_vf_mbx_teardown_q(struct bnx2x *bp, struct bnx2x_virtf *vf,
+				    struct bnx2x_vf_mbx *mbx)
+{
+	int qid = mbx->msg->req.q_op.vf_qid;
+	struct bnx2x_vfop_cmd cmd = {
+		.done = bnx2x_vf_mbx_resp,
+		.block = false,
+	};
+
+	DP(BNX2X_MSG_IOV, "VF[%d] Q_TEARDOWN: vf_qid=%d\n",
+	   vf->abs_vfid, qid);
+
+	vf->op_rc = bnx2x_vfop_qdown_cmd(bp, vf, &cmd, qid);
+	if (vf->op_rc)
+		bnx2x_vf_mbx_resp(bp, vf);
+}
+
 /* dispatch request */
 static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 				  struct bnx2x_vf_mbx *mbx)
@@ -825,6 +842,9 @@ static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		case CHANNEL_TLV_SET_Q_FILTERS:
 			bnx2x_vf_mbx_set_q_filters(bp, vf, mbx);
 			break;
+		case CHANNEL_TLV_TEARDOWN_Q:
+			bnx2x_vf_mbx_teardown_q(bp, vf, mbx);
+			break;
 		}
 
 	/* unknown TLV - this may belong to a VF driver from the future - a
-- 
1.7.9.GIT

^ permalink raw reply related

* [PATCH 14/22] bnx2x: Support statistics collection for VFs by the PF
From: Ariel Elior @ 2012-11-13 16:17 UTC (permalink / raw)
  To: David Miller; +Cc: netdev, Ariel Elior, Eilon Greenstein
In-Reply-To: <1352823451-27042-1-git-send-email-ariele@broadcom.com>

Statistics are collected by the PF driver. The collection is
performed via a query sent to the device which is basically an array
of 3-tuples of the form (statistics client, function, DMAE address).
In this patch the PF driver adds to the ramrod, on top of the
statistics clients it is maintaining for itself (rss queues, storage,
etc), the 3-tuples for the VFs it is maintaining. The addresses used
are the GPAs of the statistics buffers supplied by the VF in the
init message on the VF <-> PF channel. The function parameter
ensures that the iommu will translate the GPA to the correct physical
address.

Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c  |   78 +--------------
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c    |   21 ++++
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h    |   11 ++
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c |   94 ++++++++++++++++++
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h |    2 +
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c |  108 +++++++++++++++++----
 6 files changed, 223 insertions(+), 91 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index def50d2..bc40081 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -5233,7 +5233,9 @@ static void bnx2x_timer(unsigned long data)
 	if (!netif_running(bp->dev))
 		return;
 
-	if (!BP_NOMCP(bp)) {
+
+	if (IS_PF(bp) &&
+	    !BP_NOMCP(bp)) {
 		int mb_idx = BP_FW_MB_IDX(bp);
 		u32 drv_pulse;
 		u32 mcp_pulse;
@@ -7654,66 +7656,6 @@ void bnx2x_free_mem(struct bnx2x *bp)
 		       BCM_PAGE_SIZE * NUM_EQ_PAGES);
 }
 
-static int bnx2x_alloc_fw_stats_mem(struct bnx2x *bp)
-{
-	int num_groups;
-	int is_fcoe_stats = NO_FCOE(bp) ? 0 : 1;
-
-	/* number of queues for statistics is number of eth queues + FCoE */
-	u8 num_queue_stats = BNX2X_NUM_ETH_QUEUES(bp) + is_fcoe_stats;
-
-	/* Total number of FW statistics requests =
-	 * 1 for port stats + 1 for PF stats + potential 1 for FCoE stats +
-	 * num of queues
-	 */
-	bp->fw_stats_num = 2 + is_fcoe_stats + num_queue_stats;
-
-
-	/* Request is built from stats_query_header and an array of
-	 * stats_query_cmd_group each of which contains
-	 * STATS_QUERY_CMD_COUNT rules. The real number or requests is
-	 * configured in the stats_query_header.
-	 */
-	num_groups = ((bp->fw_stats_num) / STATS_QUERY_CMD_COUNT) +
-		     (((bp->fw_stats_num) % STATS_QUERY_CMD_COUNT) ? 1 : 0);
-
-	bp->fw_stats_req_sz = sizeof(struct stats_query_header) +
-			num_groups * sizeof(struct stats_query_cmd_group);
-
-	/* Data for statistics requests + stats_conter
-	 *
-	 * stats_counter holds per-STORM counters that are incremented
-	 * when STORM has finished with the current request.
-	 *
-	 * memory for FCoE offloaded statistics are counted anyway,
-	 * even if they will not be sent.
-	 */
-	bp->fw_stats_data_sz = sizeof(struct per_port_stats) +
-		sizeof(struct per_pf_stats) +
-		sizeof(struct fcoe_statistics_params) +
-		sizeof(struct per_queue_stats) * num_queue_stats +
-		sizeof(struct stats_counter);
-
-	BNX2X_PCI_ALLOC(bp->fw_stats, &bp->fw_stats_mapping,
-			bp->fw_stats_data_sz + bp->fw_stats_req_sz);
-
-	/* Set shortcuts */
-	bp->fw_stats_req = (struct bnx2x_fw_stats_req *)bp->fw_stats;
-	bp->fw_stats_req_mapping = bp->fw_stats_mapping;
-
-	bp->fw_stats_data = (struct bnx2x_fw_stats_data *)
-		((u8 *)bp->fw_stats + bp->fw_stats_req_sz);
-
-	bp->fw_stats_data_mapping = bp->fw_stats_mapping +
-				   bp->fw_stats_req_sz;
-	return 0;
-
-alloc_mem_err:
-	BNX2X_PCI_FREE(bp->fw_stats, bp->fw_stats_mapping,
-		       bp->fw_stats_data_sz + bp->fw_stats_req_sz);
-	BNX2X_ERR("Can't allocate memory\n");
-	return -ENOMEM;
-}
 
 int bnx2x_alloc_mem_cnic(struct bnx2x *bp)
 {
@@ -7760,10 +7702,6 @@ int bnx2x_alloc_mem(struct bnx2x *bp)
 	BNX2X_PCI_ALLOC(bp->slowpath, &bp->slowpath_mapping,
 			sizeof(struct bnx2x_slowpath));
 
-	/* Allocated memory for FW statistics  */
-	if (bnx2x_alloc_fw_stats_mem(bp))
-		goto alloc_mem_err;
-
 	/* Allocate memory for CDU context:
 	 * This memory is allocated separately and not in the generic ILT
 	 * functions because CDU differs in few aspects:
@@ -7792,6 +7730,9 @@ int bnx2x_alloc_mem(struct bnx2x *bp)
 	if (bnx2x_ilt_mem_op(bp, ILT_MEMOP_ALLOC))
 		goto alloc_mem_err;
 
+	if (bnx2x_iov_alloc_mem(bp))
+		goto alloc_mem_err;
+
 	/* Slow path ring */
 	BNX2X_PCI_ALLOC(bp->spq, &bp->spq_mapping, BCM_PAGE_SIZE);
 
@@ -7799,13 +7740,6 @@ int bnx2x_alloc_mem(struct bnx2x *bp)
 	BNX2X_PCI_ALLOC(bp->eq_ring, &bp->eq_mapping,
 			BCM_PAGE_SIZE * NUM_EQ_PAGES);
 
-
-	/* fastpath */
-	/* need to be done at the end, since it's self adjusting to amount
-	 * of memory available for RSS queues
-	 */
-	if (bnx2x_alloc_fp_mem(bp))
-		goto alloc_mem_err;
 	return 0;
 
 alloc_mem_err:
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index b8b4b74..1eb92b8 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -5199,6 +5199,27 @@ void bnx2x_init_queue_obj(struct bnx2x *bp,
 	obj->set_pending = bnx2x_queue_set_pending;
 }
 
+/* return a queue object's logical state*/
+int bnx2x_get_q_logical_state(struct bnx2x *bp,
+			       struct bnx2x_queue_sp_obj *obj)
+{
+	switch (obj->state) {
+	case BNX2X_Q_STATE_ACTIVE:
+	case BNX2X_Q_STATE_MULTI_COS:
+		return BNX2X_Q_LOGICAL_STATE_ACTIVE;
+	case BNX2X_Q_STATE_RESET:
+	case BNX2X_Q_STATE_INITIALIZED:
+	case BNX2X_Q_STATE_MCOS_TERMINATED:
+	case BNX2X_Q_STATE_INACTIVE:
+	case BNX2X_Q_STATE_STOPPED:
+	case BNX2X_Q_STATE_TERMINATED:
+	case BNX2X_Q_STATE_FLRED:
+		return BNX2X_Q_LOGICAL_STATE_STOPPED;
+	default:
+		return -EINVAL;
+	}
+}
+
 /********************** Function state object *********************************/
 enum bnx2x_func_state bnx2x_func_get_state(struct bnx2x *bp,
 					   struct bnx2x_func_sp_obj *o)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
index adbd91b..157fc4f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
@@ -776,6 +776,13 @@ enum bnx2x_q_state {
 	BNX2X_Q_STATE_MAX,
 };
 
+/* Allowed Queue states */
+enum bnx2x_q_logical_state {
+	BNX2X_Q_LOGICAL_STATE_ACTIVE,
+	BNX2X_Q_LOGICAL_STATE_STOPPED,
+};
+
+
 /* Allowed commands */
 enum bnx2x_queue_cmd {
 	BNX2X_Q_CMD_INIT,
@@ -1261,6 +1268,10 @@ void bnx2x_init_queue_obj(struct bnx2x *bp,
 int bnx2x_queue_state_change(struct bnx2x *bp,
 			     struct bnx2x_queue_state_params *params);
 
+int bnx2x_get_q_logical_state(struct bnx2x *bp,
+			       struct bnx2x_queue_sp_obj *obj);
+
+
 /********************* VLAN-MAC ****************/
 void bnx2x_init_mac_obj(struct bnx2x *bp,
 			struct bnx2x_vlan_mac_obj *mac_obj,
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index 776d21d..cec1dc0 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -1062,6 +1062,82 @@ void bnx2x_iov_sp_event(struct bnx2x *bp, int vf_cid, bool queue_work)
 			queue_delayed_work(bnx2x_wq, &bp->sp_task, 0);
 	}
 }
+
+void bnx2x_iov_adjust_stats_req(struct bnx2x *bp)
+{
+	int i;
+	int first_queue_query_index, num_queues_req;
+	dma_addr_t cur_data_offset;
+	struct stats_query_entry *cur_query_entry;
+	u8 stats_count = 0;
+	bool is_fcoe = false;
+
+	if (!IS_SRIOV(bp))
+		return;
+
+	if (!NO_FCOE(bp))
+		is_fcoe = true;
+
+	/* fcoe adds one global request and one queue request */
+	num_queues_req = BNX2X_NUM_ETH_QUEUES(bp) + is_fcoe;
+
+	first_queue_query_index = BNX2X_FIRST_QUEUE_QUERY_IDX -
+		(is_fcoe ? 0 : 1);
+
+	DP(BNX2X_MSG_IOV,
+	   "BNX2X_NUM_ETH_QUEUES %d, is_fcoe %d, first_queue_query_index %d => determined the last non virtual statistics query index is %d. Will add queries on top of that\n",
+	   BNX2X_NUM_ETH_QUEUES(bp), is_fcoe, first_queue_query_index,
+	   first_queue_query_index + num_queues_req);
+
+	cur_data_offset = bp->fw_stats_data_mapping +
+		offsetof(struct bnx2x_fw_stats_data, queue_stats) +
+		num_queues_req * sizeof(struct per_queue_stats);
+
+	cur_query_entry = &bp->fw_stats_req->
+		query[first_queue_query_index + num_queues_req];
+
+	for_each_vf(bp, i) {
+		int j;
+		struct bnx2x_virtf *vf = BP_VF(bp, i);
+		if (vf->state != VF_ENABLED) {
+			DP(BNX2X_MSG_IOV,
+			   "vf %d not enabled so no stats for it\n",
+			   vf->abs_vfid);
+			continue;
+		}
+
+		DP(BNX2X_MSG_IOV, "add addresses for vf %d\n", vf->abs_vfid);
+
+		for_each_vfq(vf, j) {
+			struct bnx2x_vf_queue *rxq = vfq_get(vf, j);
+
+			/* collect stats fro active queues only */
+			if (bnx2x_get_q_logical_state(bp, &rxq->sp_obj) ==
+			    BNX2X_Q_LOGICAL_STATE_STOPPED)
+				continue;
+
+			/* create stats query entry for this queue */
+			cur_query_entry->kind = STATS_TYPE_QUEUE;
+			cur_query_entry->index = vfq_cl_id(vf, rxq);
+			cur_query_entry->funcID =
+				cpu_to_le16(FW_VF_HANDLE(vf->abs_vfid));
+			cur_query_entry->address.hi =
+				cpu_to_le32(U64_HI(vf->fw_stat_map));
+			cur_query_entry->address.lo =
+				cpu_to_le32(U64_LO(vf->fw_stat_map));
+			DP(BNX2X_MSG_IOV,
+			   "added address %x %x for vf %d queue %d client %d\n",
+			   cur_query_entry->address.hi,
+			   cur_query_entry->address.lo, cur_query_entry->funcID,
+			   j, cur_query_entry->index);
+			cur_query_entry++;
+			cur_data_offset += sizeof(struct per_queue_stats);
+			stats_count++;
+		}
+	}
+	bp->fw_stats_req->hdr.cmd_num = bp->fw_stats_num + stats_count;
+}
+
 void bnx2x_iov_sp_task(struct bnx2x *bp)
 {
 	int i;
@@ -1082,6 +1158,24 @@ void bnx2x_iov_sp_task(struct bnx2x *bp)
 		}
 	}
 }
+
+static inline
+struct bnx2x_virtf *__vf_from_stat_id(struct bnx2x *bp, u8 stat_id)
+{
+	int i;
+	struct bnx2x_virtf *vf = NULL;
+
+	for_each_vf(bp, i) {
+		vf = BP_VF(bp, i);
+		if (stat_id >= vf->igu_base_id &&
+		    stat_id < vf->igu_base_id + vf_sb_count(vf))
+			break;
+	}
+	return vf;
+
+}
+
+/* VF API helpers */
 static void bnx2x_vf_qtbl_set_q(struct bnx2x *bp, u8 abs_vfid, u8 qid,
 				u8 enable)
 {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
index ad3299e..583ac13 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
@@ -429,6 +429,8 @@ void bnx2x_iov_set_queue_sp_obj(struct bnx2x *bp, int vf_cid,
 				struct bnx2x_queue_sp_obj **q_obj);
 void bnx2x_iov_sp_event(struct bnx2x *bp, int vf_cid, bool queue_work);
 int bnx2x_iov_eq_sp_event(struct bnx2x *bp, union event_ring_elem *elem);
+void bnx2x_iov_adjust_stats_req(struct bnx2x *bp);
+void bnx2x_iov_storm_stats_update(struct bnx2x *bp);
 void bnx2x_iov_sp_task(struct bnx2x *bp);
 /* global vf mailbox routines */
 void bnx2x_vf_mbx(struct bnx2x *bp, struct vf_pf_event_data *vfpf_event);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
index 348ed02..cdd5abb 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
@@ -20,6 +20,8 @@
 #include "bnx2x_stats.h"
 #include "bnx2x_cmn.h"
 
+#include "bnx2x_sriov.h"
+
 
 /* Statistics */
 
@@ -79,6 +81,41 @@ static inline u16 bnx2x_get_port_stats_dma_len(struct bnx2x *bp)
  * Init service functions
  */
 
+static void bnx2x_dp_stats(struct bnx2x *bp)
+{
+	int i;
+	DP(BNX2X_MSG_STATS, "dumping stats:\n"
+	   "fw_stats_req\n"
+	   "    hdr\n"
+	   "        cmd_num %d\n"
+	   "        reserved0 %d\n"
+	   "        drv_stats_counter %d\n"
+	   "        reserved1 %d\n"
+	   "        stats_counters_addrs %x %x\n",
+	   bp->fw_stats_req->hdr.cmd_num,
+	   bp->fw_stats_req->hdr.reserved0,
+	   bp->fw_stats_req->hdr.drv_stats_counter,
+	   bp->fw_stats_req->hdr.reserved1,
+	   bp->fw_stats_req->hdr.stats_counters_addrs.hi,
+	   bp->fw_stats_req->hdr.stats_counters_addrs.lo);
+
+	for (i = 0; i < bp->fw_stats_req->hdr.cmd_num; i++) {
+		DP(BNX2X_MSG_STATS,
+		   "query[%d]\n"
+		   "              kind %d\n"
+		   "              index %d\n"
+		   "              funcID %d\n"
+		   "              reserved %d\n"
+		   "              address %x %x\n",
+		   i, bp->fw_stats_req->query[i].kind,
+		   bp->fw_stats_req->query[i].index,
+		   bp->fw_stats_req->query[i].funcID,
+		   bp->fw_stats_req->query[i].reserved,
+		   bp->fw_stats_req->query[i].address.hi,
+		   bp->fw_stats_req->query[i].address.lo);
+	}
+}
+
 /* Post the next statistics ramrod. Protect it with the spin in
  * order to ensure the strict order between statistics ramrods
  * (each ramrod has a sequence number passed in a
@@ -103,7 +140,10 @@ static void bnx2x_storm_stats_post(struct bnx2x *bp)
 		DP(BNX2X_MSG_STATS, "Sending statistics ramrod %d\n",
 			bp->fw_stats_req->hdr.drv_stats_counter);
 
+		/* adjust the ramrod to include VF queues statistics */
+		bnx2x_iov_adjust_stats_req(bp);
 
+		bnx2x_dp_stats(bp);
 
 		/* send FW stats ramrod */
 		rc = bnx2x_sp_post(bp, RAMROD_CMD_ID_COMMON_STAT_QUERY, 0,
@@ -482,6 +522,12 @@ static void bnx2x_func_stats_init(struct bnx2x *bp)
 
 static void bnx2x_stats_start(struct bnx2x *bp)
 {
+	/* vfs travel through here as part of the statistics FSM, but no action
+	 * is required
+	 */
+	if (IS_VF(bp))
+		return;
+
 	if (bp->port.pmf)
 		bnx2x_port_stats_init(bp);
 
@@ -501,6 +547,11 @@ static void bnx2x_stats_pmf_start(struct bnx2x *bp)
 
 static void bnx2x_stats_restart(struct bnx2x *bp)
 {
+	/* vfs travel through here as part of the statistics FSM, but no action
+	 * is required
+	 */
+	if (IS_VF(bp))
+		return;
 	bnx2x_stats_comp(bp);
 	bnx2x_stats_start(bp);
 }
@@ -832,19 +883,10 @@ static int bnx2x_hw_stats_update(struct bnx2x *bp)
 	return 0;
 }
 
-static int bnx2x_storm_stats_update(struct bnx2x *bp)
+static int bnx2x_storm_stats_validate_counters(struct bnx2x *bp)
 {
-	struct tstorm_per_port_stats *tport =
-				&bp->fw_stats_data->port.tstorm_port_statistics;
-	struct tstorm_per_pf_stats *tfunc =
-				&bp->fw_stats_data->pf.tstorm_pf_statistics;
-	struct host_func_stats *fstats = &bp->func_stats;
-	struct bnx2x_eth_stats *estats = &bp->eth_stats;
-	struct bnx2x_eth_stats_old *estats_old = &bp->eth_stats_old;
 	struct stats_counter *counters = &bp->fw_stats_data->storm_counters;
-	int i;
 	u16 cur_stats_counter;
-
 	/* Make sure we use the value of the counter
 	 * used for sending the last stats ramrod.
 	 */
@@ -880,6 +922,23 @@ static int bnx2x_storm_stats_update(struct bnx2x *bp)
 		   le16_to_cpu(counters->tstats_counter), bp->stats_counter);
 		return -EAGAIN;
 	}
+	return 0;
+}
+
+static int bnx2x_storm_stats_update(struct bnx2x *bp)
+{
+	struct tstorm_per_port_stats *tport =
+				&bp->fw_stats_data->port.tstorm_port_statistics;
+	struct tstorm_per_pf_stats *tfunc =
+				&bp->fw_stats_data->pf.tstorm_pf_statistics;
+	struct host_func_stats *fstats = &bp->func_stats;
+	struct bnx2x_eth_stats *estats = &bp->eth_stats;
+	struct bnx2x_eth_stats_old *estats_old = &bp->eth_stats_old;
+	int i;
+
+	/* vfs stat counter is managed by pf */
+	if (IS_PF(bp) && bnx2x_storm_stats_validate_counters(bp))
+		return -EAGAIN;
 
 	estats->error_bytes_received_hi = 0;
 	estats->error_bytes_received_lo = 0;
@@ -1173,23 +1232,34 @@ static void bnx2x_stats_update(struct bnx2x *bp)
 	if (bnx2x_edebug_stats_stopped(bp))
 		return;
 
-	if (*stats_comp != DMAE_COMP_VAL)
-		return;
+	if (IS_PF(bp)) {
+		if (*stats_comp != DMAE_COMP_VAL)
+			return;
 
-	if (bp->port.pmf)
-		bnx2x_hw_stats_update(bp);
+		if (bp->port.pmf)
+			bnx2x_hw_stats_update(bp);
 
-	if (bnx2x_storm_stats_update(bp)) {
-		if (bp->stats_pending++ == 3) {
-			BNX2X_ERR("storm stats were not updated for 3 times\n");
-			bnx2x_panic();
+		if (bnx2x_storm_stats_update(bp)) {
+			if (bp->stats_pending++ == 3) {
+				BNX2X_ERR("storm stats were not updated for 3 times\n");
+				bnx2x_panic();
+			}
+			return;
 		}
-		return;
+	} else {
+		/* vf doesn't collect HW statistics, and doesn't get completions
+		 * perform only update
+		 */
+		bnx2x_storm_stats_update(bp);
 	}
 
 	bnx2x_net_stats_update(bp);
 	bnx2x_drv_stats_update(bp);
 
+	/* vf is done */
+	if (IS_VF(bp))
+		return;
+
 	if (netif_msg_timer(bp)) {
 		struct bnx2x_eth_stats *estats = &bp->eth_stats;
 
-- 
1.7.9.GIT

^ permalink raw reply related

* [PATCH 12/22] bnx2x: Support of PF driver of a VF acquire request
From: Ariel Elior @ 2012-11-13 16:17 UTC (permalink / raw)
  To: David Miller; +Cc: netdev, Ariel Elior, Eilon Greenstein
In-Reply-To: <1352823451-27042-1-git-send-email-ariele@broadcom.com>

When a VF is probed by the VF driver, the VF driver sends an
'acquire' request over the VF <-> PF channel for the resources
it needs to operate (interrupts, queues, etc).
The PF driver either ratifies the request and allocates the resources,
responds with the maximum values it will allow the VF to acquire,
or fails the request entirely if there is a problem.

Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c    |   28 +++
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h    |   10 +
 .../net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c    |   13 +-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c  |  203 +++++++++++++++++++
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h  |   45 ++++-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c   |  204 ++++++++++++++++++++
 6 files changed, 490 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 13f1270..6483979 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -87,6 +87,34 @@ static inline void bnx2x_move_fp(struct bnx2x *bp, int from, int to)
 	to_fp->txdata_ptr[0] = &bp->bnx2x_txq[new_txdata_index];
 }
 
+/**
+ * bnx2x_fill_fw_str - move content of the fastpath structure.
+ *
+ * @bp:        driver handle
+ * @buf:       character buffer to fill with the fw name
+ * @buf_len:   length of the above buffer
+ *
+ */
+void bnx2x_fill_fw_str(struct bnx2x *bp, char *buf, size_t buf_len)
+{
+	if (IS_PF(bp)) {
+		u8 phy_fw_ver[PHY_FW_VER_LEN];
+
+		phy_fw_ver[0] = '\0';
+		bnx2x_get_ext_phy_fw_version(&bp->link_params,
+					     phy_fw_ver, PHY_FW_VER_LEN);
+		strlcpy(buf, bp->fw_ver, buf_len);
+		snprintf(buf + strlen(bp->fw_ver), 32 - strlen(bp->fw_ver),
+			 "bc %d.%d.%d%s%s",
+			 (bp->common.bc_ver & 0xff0000) >> 16,
+			 (bp->common.bc_ver & 0xff00) >> 8,
+			 (bp->common.bc_ver & 0xff),
+			 ((phy_fw_ver[0] != '\0') ? " phy " : ""), phy_fw_ver);
+	} else {
+		strlcpy(buf, bp->acquire_resp.pfdev_info.fw_ver, buf_len);
+	}
+}
+
 int load_count[2][3] = { {0} }; /* per-path: 0-common, 1-port0, 2-port1 */
 
 /* free skb in the packet ring at pos idx
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index f6e92ac..2dfde45 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -1401,4 +1401,14 @@ static inline bool bnx2x_is_valid_ether_addr(struct bnx2x *bp, u8 *addr)
 	return false;
 }
 
+
+/**
+ * bnx2x_fill_fw_str - Fill buffer with FW version string
+ *
+ * @bp:         driver handle
+ * @buf:	buffer to fill with FW string
+ * @buf_len:	length of buffer
+ *
+ */
+void bnx2x_fill_fw_str(struct bnx2x *bp, char *buf, size_t buf_len);
 #endif /* BNX2X_CMN_H */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index 252fce3..3854ad6 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -817,21 +817,12 @@ static void bnx2x_get_drvinfo(struct net_device *dev,
 			      struct ethtool_drvinfo *info)
 {
 	struct bnx2x *bp = netdev_priv(dev);
-	u8 phy_fw_ver[PHY_FW_VER_LEN];
 
 	strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
 	strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
 
-	phy_fw_ver[0] = '\0';
-	bnx2x_get_ext_phy_fw_version(&bp->link_params,
-				     phy_fw_ver, PHY_FW_VER_LEN);
-	strlcpy(info->fw_version, bp->fw_ver, sizeof(info->fw_version));
-	snprintf(info->fw_version + strlen(bp->fw_ver), 32 - strlen(bp->fw_ver),
-		 "bc %d.%d.%d%s%s",
-		 (bp->common.bc_ver & 0xff0000) >> 16,
-		 (bp->common.bc_ver & 0xff00) >> 8,
-		 (bp->common.bc_ver & 0xff),
-		 ((phy_fw_ver[0] != '\0') ? " phy " : ""), phy_fw_ver);
+	bnx2x_fill_fw_str(bp, info->fw_version, sizeof(info->fw_version));
+
 	strlcpy(info->bus_info, pci_name(bp->pdev), sizeof(info->bus_info));
 	info->n_stats = BNX2X_NUM_STATS;
 	info->testinfo_len = BNX2X_NUM_TESTS(bp);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index 1cd2176..f95bb9e 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -586,6 +586,66 @@ int bnx2x_iov_alloc_mem(struct bnx2x *bp)
 alloc_mem_err:
 	return -ENOMEM;
 }
+
+static void bnx2x_vfq_init(struct bnx2x *bp, struct bnx2x_virtf *vf,
+			   struct bnx2x_vf_queue *q)
+{
+	u8 cl_id = vfq_cl_id(vf, q);
+	u8 func_id = FW_VF_HANDLE(vf->abs_vfid);
+
+	unsigned long q_type = 0;
+	set_bit(BNX2X_Q_TYPE_HAS_TX, &q_type);
+	set_bit(BNX2X_Q_TYPE_HAS_RX, &q_type);
+
+	/* Queue State object */
+	bnx2x_init_queue_obj(bp, &q->sp_obj,
+			     cl_id, &q->cid, 1, func_id,
+			     bnx2x_vf_sp(bp, vf, q_data),
+			     bnx2x_vf_sp_map(bp, vf, q_data),
+			     q_type);
+
+	DP(BNX2X_MSG_IOV,
+	   "initialized vf %d's queue object. func id set to %d\n",
+	   vf->abs_vfid, q->sp_obj.func_id);
+
+
+	/* mac/vlan objects are per queue, but only those
+	 * that belong to the leading queue are initialized
+	 */
+	if (vfq_is_leading(q)) {
+
+		/* mac*/
+		bnx2x_init_mac_obj(bp, &q->mac_obj,
+				   cl_id, q->cid, func_id,
+				   bnx2x_vf_sp(bp, vf, mac_rdata),
+				   bnx2x_vf_sp_map(bp, vf, mac_rdata),
+				   BNX2X_FILTER_MAC_PENDING,
+				   &vf->filter_state,
+				   BNX2X_OBJ_TYPE_RX_TX,
+				   &bp->macs_pool);
+		/* vlan */
+		bnx2x_init_vlan_obj(bp, &q->vlan_obj,
+				    cl_id, q->cid, func_id,
+				    bnx2x_vf_sp(bp, vf, vlan_rdata),
+				    bnx2x_vf_sp_map(bp, vf, vlan_rdata),
+				    BNX2X_FILTER_VLAN_PENDING,
+				    &vf->filter_state,
+				    BNX2X_OBJ_TYPE_RX_TX,
+				    &bp->vlans_pool);
+
+		/* mcast */
+		bnx2x_init_mcast_obj(bp, &vf->mcast_obj, cl_id,
+				     q->cid, func_id, func_id,
+				     bnx2x_vf_sp(bp, vf, mcast_rdata),
+				     bnx2x_vf_sp_map(bp, vf, mcast_rdata),
+				     BNX2X_FILTER_MCAST_PENDING,
+				     &vf->filter_state,
+				     BNX2X_OBJ_TYPE_RX_TX);
+
+		vf->leading_rss = cl_id;
+	}
+}
+
 /* called by bnx2x_nic_load */
 int bnx2x_iov_nic_init(struct bnx2x *bp)
 {
@@ -930,3 +990,146 @@ void bnx2x_iov_sp_task(struct bnx2x *bp)
 		}
 	}
 }
+
+inline
+u8 bnx2x_vf_max_queue_cnt(struct bnx2x *bp, struct bnx2x_virtf *vf)
+{
+	return min_t(u8, min_t(u8, vf_sb_count(vf), BNX2X_CIDS_PER_VF),
+		     BNX2X_VF_MAX_QUEUES);
+}
+
+static inline
+int bnx2x_vf_chk_avail_resc(struct bnx2x *bp, struct bnx2x_virtf *vf,
+			    struct vf_pf_resc_request *req_resc)
+{
+	u8 rxq_cnt = vf_rxq_count(vf) ? : bnx2x_vf_max_queue_cnt(bp, vf);
+	u8 txq_cnt = vf_txq_count(vf) ? : bnx2x_vf_max_queue_cnt(bp, vf);
+
+	return ((req_resc->num_rxqs <= rxq_cnt) &&
+		(req_resc->num_txqs <= txq_cnt) &&
+		(req_resc->num_sbs <= vf_sb_count(vf))   &&
+		(req_resc->num_mac_filters <= vf_mac_rules_cnt(vf)) &&
+		(req_resc->num_vlan_filters <= vf_vlan_rules_cnt(vf)));
+}
+
+/* CORE VF API */
+int bnx2x_vf_acquire(struct bnx2x *bp, struct bnx2x_virtf *vf,
+		     struct vf_pf_resc_request *resc)
+{
+	int base_vf_cid = (BP_VFDB(bp)->sriov.first_vf_in_pf + vf->index) *
+		BNX2X_CIDS_PER_VF;
+
+	union cdu_context *base_cxt = (union cdu_context *)
+		BP_VF_CXT_PAGE(bp, base_vf_cid/ILT_PAGE_CIDS)->addr +
+		(base_vf_cid & (ILT_PAGE_CIDS-1));
+	int i;
+
+	/* if state is 'acquired' the VF was not released or FLR'd, in
+	 * this case the returned resources match the acquired already
+	 * acquired resources. Verify that the requested numbers do
+	 * not exceed the already acquired numbers.
+	 */
+	if (vf->state == VF_ACQUIRED) {
+		DP(BNX2X_MSG_IOV, "VF[%d] Trying to re-acquire resources (VF was not released or FLR'd)\n",
+		   vf->abs_vfid);
+
+		if (!bnx2x_vf_chk_avail_resc(bp, vf, resc)) {
+			BNX2X_ERR("VF[%d] When re-acquiring resources, requested numbers must be <= then previously acquired numbers\n",
+				  vf->abs_vfid);
+			return -EINVAL;
+		}
+		return 0;
+	}
+
+	/* Otherwise vf state must be 'free' or 'reset' */
+	if (vf->state != VF_FREE && vf->state != VF_RESET) {
+		BNX2X_ERR("VF[%d] Can not acquire a VF with state %d\n",
+			  vf->abs_vfid, vf->state);
+		return -EINVAL;
+	}
+
+	/* static allocation:
+	 * the global maximum number are fixed per VF. fail the request if
+	 * requested number exceed these globals
+	 */
+	if (!bnx2x_vf_chk_avail_resc(bp, vf, resc)) {
+		DP(BNX2X_MSG_IOV,
+		   "cannot fullfill vf resource request. Placing maximal available values in response");
+		/* set the max resource in the vf */
+		return -ENOMEM;
+	}
+
+	/* Set resources counters - 0 request means max available */
+	vf_sb_count(vf) = resc->num_sbs;
+	vf_rxq_count(vf) = resc->num_rxqs ? : bnx2x_vf_max_queue_cnt(bp, vf);
+	vf_txq_count(vf) = resc->num_txqs ? : bnx2x_vf_max_queue_cnt(bp, vf);
+	if (resc->num_mac_filters)
+		vf_mac_rules_cnt(vf) = resc->num_mac_filters;
+	if (resc->num_vlan_filters)
+		vf_vlan_rules_cnt(vf) = resc->num_vlan_filters;
+
+	DP(BNX2X_MSG_IOV,
+	   "Fullfilling vf request: sbount %d, tx_count %d, rx_count %d, mac_rules_count %d, vlan_rules_count %d\n",
+	   vf_sb_count(vf), vf_rxq_count(vf),
+	   vf_txq_count(vf), vf_mac_rules_cnt(vf),
+	   vf_vlan_rules_cnt(vf));
+
+	/* Initialize the queues */
+	if (!vf->vfqs) {
+		DP(BNX2X_MSG_IOV, "vf->vfqs was not allocated");
+		return -EINVAL;
+	}
+
+	for_each_vfq(vf, i) {
+		struct bnx2x_vf_queue *q = vfq_get(vf, i);
+
+		if (!q) {
+			DP(BNX2X_MSG_IOV, "q numer %d was not allocated", i);
+			return -EINVAL;
+		}
+
+		q->index = i;
+		q->cxt = &((base_cxt + i)->eth);
+		q->cid = BNX2X_FIRST_VF_CID + base_vf_cid + i;
+
+		DP(BNX2X_MSG_IOV, "VFQ[%d:%d]: index %d, cid 0x%x, cxt %p\n",
+		   vf->abs_vfid, i, q->index, q->cid, q->cxt);
+
+		/* init SP objects */
+		bnx2x_vfq_init(bp, vf, q);
+	}
+	vf->state = VF_ACQUIRED;
+	return 0;
+}
+
+void bnx2x_lock_vf_pf_channel(struct bnx2x *bp, struct bnx2x_virtf *vf,
+			      enum channel_tlvs tlv)
+{
+	/* lock the channel */
+	mutex_lock(&vf->op_mutex);
+
+	/* record the locking op */
+	vf->op_current = tlv;
+
+	/* log the lock */
+	DP(BNX2X_MSG_IOV, "VF[%d]: vf pf channel locked by %d\n",
+	   vf->abs_vfid, tlv);
+}
+
+void bnx2x_unlock_vf_pf_channel(struct bnx2x *bp, struct bnx2x_virtf *vf,
+				enum channel_tlvs expected_tlv)
+{
+	WARN(expected_tlv != vf->op_current,
+	     "lock mismatch: expected %d found %d", expected_tlv,
+	     vf->op_current);
+
+	/* lock the channel */
+	mutex_unlock(&vf->op_mutex);
+
+	/* log the unlock */
+	DP(BNX2X_MSG_IOV, "VF[%d]: vf pf channel unlocked by %d\n",
+	   vf->abs_vfid, vf->op_current);
+
+	/* record the locking op */
+	vf->op_current = CHANNEL_TLV_NONE;
+}
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
index 6fd3042..3375a1a 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
@@ -19,10 +19,13 @@
 #ifndef BNX2X_SRIOV_H
 #define BNX2X_SRIOV_H
 
-/*
- * The bnx2x device structure holds vfdb structure described below.
+#include "bnx2x_vfpf.h"
+#include "bnx2x_cmn.h"
+
+/* The bnx2x device structure holds vfdb structure described below.
  * The VF array is indexed by the relative vfid.
  */
+#define BNX2X_VF_MAX_QUEUES		16
 struct bnx2x_sriov {
 	u32 first_vf_in_pf;
 
@@ -264,6 +267,12 @@ struct bnx2x_virtf {
 #define for_each_vf(bp, var) \
 		for ((var) = 0; (var) < BNX2X_NR_VIRTFN(bp); (var)++)
 
+#define for_each_vfq(vf, var) \
+		for ((var) = 0; (var) < vf_rxq_count(vf); (var)++)
+
+#define for_each_vf_sb(vf, var) \
+		for ((var) = 0; (var) < vf_sb_count(vf); (var)++)
+
 #define HW_VF_HANDLE(bp, abs_vfid) \
 	(u16)(BP_ABS_FUNC((bp)) | (1<<3) |  ((u16)(abs_vfid) << 4))
 
@@ -272,6 +281,13 @@ struct bnx2x_virtf {
 #define FW_VF_HANDLE(abs_vfid)	\
 	(abs_vfid + FW_PF_MAX_HANDLE)
 
+/* locking and unlocking the channel mutex */
+void bnx2x_lock_vf_pf_channel(struct bnx2x *bp, struct bnx2x_virtf *vf,
+			      enum channel_tlvs tlv);
+
+void bnx2x_unlock_vf_pf_channel(struct bnx2x *bp, struct bnx2x_virtf *vf,
+				enum channel_tlvs expected_tlv);
+
 /* VF mail box (aka vf-pf channel) */
 
 /* a container for the bi-directional vf<-->pf messages.
@@ -373,11 +389,31 @@ static inline struct bnx2x_vf_queue *vfq_get(struct bnx2x_virtf *vf, u8 index)
 	return &(vf->vfqs[index]);
 }
 
+static inline bool vfq_is_leading(struct bnx2x_vf_queue *vfq)
+{
+	return (vfq->index == 0);
+}
+
+/* FW ids */
 static inline u8 vf_igu_sb(struct bnx2x_virtf *vf, u16 sb_idx)
 {
 	return vf->igu_base_id + sb_idx;
 }
 
+static inline u8 vf_hc_qzone(struct bnx2x_virtf *vf, u16 sb_idx)
+{
+	return vf_igu_sb(vf, sb_idx);
+}
+
+static inline u8 vfq_cl_id(struct bnx2x_virtf *vf, struct bnx2x_vf_queue *q)
+{
+	return vf->igu_base_id + q->index;
+}
+static inline u8 vfq_qzone_id(struct bnx2x_virtf *vf, struct bnx2x_vf_queue *q)
+{
+	return vfq_cl_id(vf, q);
+}
+
 /* global iov routines */
 int bnx2x_iov_init_ilt(struct bnx2x *bp, u16 line);
 int bnx2x_iov_init_one(struct bnx2x *bp, int int_mode_param, int num_vfs_param);
@@ -395,6 +431,10 @@ void bnx2x_iov_sp_task(struct bnx2x *bp);
 /* global vf mailbox routines */
 void bnx2x_vf_mbx(struct bnx2x *bp, struct vf_pf_event_data *vfpf_event);
 void bnx2x_vf_enable_mbx(struct bnx2x *bp, u8 abs_vfid);
+/* acquire */
+int bnx2x_vf_acquire(struct bnx2x *bp, struct bnx2x_virtf *vf,
+			  struct vf_pf_resc_request *resc);
+
 static inline struct bnx2x_vfop *bnx2x_vfop_cur(struct bnx2x *bp,
 						struct bnx2x_virtf *vf)
 {
@@ -404,6 +444,7 @@ static inline struct bnx2x_vfop *bnx2x_vfop_cur(struct bnx2x *bp,
 }
 
 int bnx2x_vf_idx_by_abs_fid(struct bnx2x *bp, u16 abs_vfid);
+u8 bnx2x_vf_max_queue_cnt(struct bnx2x *bp, struct bnx2x_virtf *vf);
 /* VF FLR helpers */
 int bnx2x_vf_flr_clnup_epilog(struct bnx2x *bp, u8 abs_vfid);
 void bnx2x_vf_enable_access(struct bnx2x *bp, u8 abs_vfid);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index a933442..ffe49d0 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -186,6 +186,181 @@ static int bnx2x_copy32_vf_dmae(struct bnx2x *bp, u8 from_vf,
 	/* issue the command and wait for completion */
 	return bnx2x_issue_dmae_with_comp(bp, &dmae);
 }
+
+static void bnx2x_vf_mbx_resp(struct bnx2x *bp, struct bnx2x_virtf *vf)
+{
+	struct bnx2x_vf_mbx *mbx = BP_VF_MBX(bp, vf->index);
+	u64 vf_addr;
+	dma_addr_t pf_addr;
+	u16 length, type;
+	int rc;
+
+	struct pfvf_general_resp_tlv *resp = &mbx->msg->resp.general_resp;
+
+	/* prepare response */
+	type = mbx->first_tlv.tl.type;
+	length = type == CHANNEL_TLV_ACQUIRE ?
+		sizeof(struct pfvf_acquire_resp_tlv) :
+		sizeof(struct pfvf_general_resp_tlv);
+	bnx2x_add_tlv(bp, resp, 0, type, length);
+	resp->hdr.status = bnx2x_pfvf_status_codes(vf->op_rc);
+	bnx2x_add_tlv(bp, resp, length, CHANNEL_TLV_LIST_END,
+		      sizeof(struct channel_list_end_tlv));
+	bnx2x_dp_tlv_list(bp, resp);
+
+	DP(BNX2X_MSG_IOV, "mailbox vf address hi 0x%x, lo 0x%x, offset 0x%x",
+	   mbx->vf_addr_hi, mbx->vf_addr_lo, mbx->first_tlv.resp_msg_offset);
+
+	/* send response */
+	vf_addr = HILO_U64(mbx->vf_addr_hi, mbx->vf_addr_lo) +
+		  mbx->first_tlv.resp_msg_offset;
+
+	pf_addr = mbx->msg_mapping +
+		offsetof(struct bnx2x_vf_mbx_msg, resp);
+
+	/* copy the response body, if there is one, before the header, as the vf
+	 * is sensitive to the header being written
+	 */
+	if (resp->hdr.tl.length > sizeof(u64)) {
+		length = resp->hdr.tl.length - sizeof(u64);
+		vf_addr += sizeof(u64);
+		pf_addr += sizeof(u64);
+		rc = bnx2x_copy32_vf_dmae(bp, false, pf_addr, vf->abs_vfid,
+					  U64_HI(vf_addr),
+					  U64_LO(vf_addr),
+					  length/4);
+		if (rc) {
+			BNX2X_ERR("Failed to copy response body to VF %d\n",
+				  vf->abs_vfid);
+			return;
+		}
+		vf_addr -= sizeof(u64);
+		pf_addr -= sizeof(u64);
+	}
+
+	/* ack the FW */
+	storm_memset_vf_mbx_ack(bp, vf->abs_vfid);
+	mmiowb();
+
+	/* initiate dmae to send the response */
+	mbx->flags &= ~VF_MSG_INPROCESS;
+
+	/* copy the response header including status-done field,
+	 * must be last dmae, must be after FW is acked
+	 */
+	rc = bnx2x_copy32_vf_dmae(bp, false, pf_addr, vf->abs_vfid,
+				  U64_HI(vf_addr),
+				  U64_LO(vf_addr),
+				  sizeof(u64)/4);
+
+	/* unlock channel mutex */
+	bnx2x_unlock_vf_pf_channel(bp, vf, mbx->first_tlv.tl.type);
+
+	if (rc) {
+		BNX2X_ERR("Failed to copy response status to VF %d\n",
+			  vf->abs_vfid);
+	}
+	return;
+}
+
+static void bnx2x_vf_mbx_acquire_resp(struct bnx2x *bp, struct bnx2x_virtf *vf,
+				      struct bnx2x_vf_mbx *mbx, int vfop_status)
+{
+	int i;
+	struct pfvf_acquire_resp_tlv *resp = &mbx->msg->resp.acquire_resp;
+	struct pf_vf_resc *resc = &resp->resc;
+	u8 status = bnx2x_pfvf_status_codes(vfop_status);
+
+	memset(resp, 0, sizeof(*resp));
+
+	/* fill in pfdev info */
+	resp->pfdev_info.chip_num = bp->common.chip_id;
+	resp->pfdev_info.db_size = (1 << BNX2X_DB_SHIFT);
+	resp->pfdev_info.indices_per_sb = HC_SB_MAX_INDICES_E2;
+	resp->pfdev_info.pf_cap = (PFVF_CAP_RSS |
+				   /* PFVF_CAP_DHC |*/ PFVF_CAP_TPA);
+	bnx2x_fill_fw_str(bp, resp->pfdev_info.fw_ver,
+			  sizeof(resp->pfdev_info.fw_ver));
+
+	if (status == PFVF_STATUS_NO_RESOURCE ||
+	    status == PFVF_STATUS_SUCCESS) {
+
+		/* set resources numbers, if status equals NO_RESOURCE these
+		 * are max possible numbers
+		 */
+		resc->num_rxqs = vf_rxq_count(vf) ? :
+			bnx2x_vf_max_queue_cnt(bp, vf);
+		resc->num_txqs = vf_txq_count(vf) ? :
+			bnx2x_vf_max_queue_cnt(bp, vf);
+		resc->num_sbs = vf_sb_count(vf);
+		resc->num_mac_filters = vf_mac_rules_cnt(vf);
+		resc->num_vlan_filters = vf_vlan_rules_cnt(vf);
+		resc->num_mc_filters = 0;
+
+		if (status == PFVF_STATUS_SUCCESS) {
+			for_each_vfq(vf, i)
+				resc->hw_qid[i] =
+					vfq_qzone_id(vf, vfq_get(vf, i));
+
+			for_each_vf_sb(vf, i) {
+				resc->hw_sbs[i].hw_sb_id = vf_igu_sb(vf, i);
+				resc->hw_sbs[i].sb_qid = vf_hc_qzone(vf, i);
+			}
+		}
+	}
+
+	DP(BNX2X_MSG_IOV, "VF[%d] ACQUIRE_RESPONSE: pfdev_info- chip_num=0x%x, db_size=%d, idx_per_sb=%d, pf_cap=0x%x\n"
+	   "resources- n_rxq-%d, n_txq-%d, n_sbs-%d, n_macs-%d, n_vlans-%d, n_mcs-%d, fw_ver: '%s'\n",
+	   vf->abs_vfid,
+	   resp->pfdev_info.chip_num,
+	   resp->pfdev_info.db_size,
+	   resp->pfdev_info.indices_per_sb,
+	   resp->pfdev_info.pf_cap,
+	   resc->num_rxqs,
+	   resc->num_txqs,
+	   resc->num_sbs,
+	   resc->num_mac_filters,
+	   resc->num_vlan_filters,
+	   resc->num_mc_filters,
+	   resp->pfdev_info.fw_ver);
+
+	DP_CONT(BNX2X_MSG_IOV, "hw_qids- [ ");
+	for (i = 0; i < vf_rxq_count(vf); i++)
+		DP_CONT(BNX2X_MSG_IOV, "%d ", resc->hw_qid[i]);
+	DP_CONT(BNX2X_MSG_IOV, "], sb_info- [ ");
+	for (i = 0; i < vf_sb_count(vf); i++)
+		DP_CONT(BNX2X_MSG_IOV, "%d:%d ",
+			resc->hw_sbs[i].hw_sb_id,
+			resc->hw_sbs[i].sb_qid);
+	DP_CONT(BNX2X_MSG_IOV, "]\n");
+
+	/* send the response */
+	vf->op_rc = vfop_status;
+	bnx2x_vf_mbx_resp(bp, vf);
+}
+
+static void bnx2x_vf_mbx_acquire(struct bnx2x *bp, struct bnx2x_virtf *vf,
+				 struct bnx2x_vf_mbx *mbx)
+{
+	int rc;
+	struct vfpf_acquire_tlv *acquire = &mbx->msg->req.acquire;
+
+	/* log vfdef info */
+	DP(BNX2X_MSG_IOV,
+	   "VF[%d] ACQUIRE: vfdev_info- vf_id %d, vf_os %d resources- n_rxq-%d, n_txq-%d, n_sbs-%d, n_macs-%d, n_vlans-%d, n_mcs-%d\n",
+	   vf->abs_vfid, acquire->vfdev_info.vf_id, acquire->vfdev_info.vf_os,
+	   acquire->resc_request.num_rxqs, acquire->resc_request.num_txqs,
+	   acquire->resc_request.num_sbs, acquire->resc_request.num_mac_filters,
+	   acquire->resc_request.num_vlan_filters,
+	   acquire->resc_request.num_mc_filters);
+
+	/* acquire the resources */
+	rc = bnx2x_vf_acquire(bp, vf, &acquire->resc_request);
+
+	/* response */
+	bnx2x_vf_mbx_acquire_resp(bp, vf, mbx, rc);
+}
+
 /* dispatch request */
 static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 				  struct bnx2x_vf_mbx *mbx)
@@ -195,8 +370,16 @@ static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 	/* check if tlv type is known */
 	if (bnx2x_tlv_supported(mbx->first_tlv.tl.type)) {
 
+		/* Lock the per vf op mutex and note the locker's identity.
+		 * The unlock will take place in mbx response.
+		 */
+		bnx2x_lock_vf_pf_channel(bp, vf, mbx->first_tlv.tl.type);
+
 		/* switch on the opcode */
 		switch (mbx->first_tlv.tl.type) {
+		case CHANNEL_TLV_ACQUIRE:
+			bnx2x_vf_mbx_acquire(bp, vf, mbx);
+			break;
 		}
 
 	/* unknown TLV - this may belong to a VF driver from the future - a
@@ -211,6 +394,27 @@ static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		for (i = 0; i < 20; i++)
 			DP_CONT(BNX2X_MSG_IOV, "%x ",
 				mbx->msg->req.tlv_buf_size.tlv_buffer[i]);
+
+		/* test whether we can respond to the VF (do we have an address
+		 * for it?)
+		 */
+		if (vf->state == VF_ACQUIRED) {
+
+			/* mbx_resp uses the op_rc of the VF */
+			vf->op_rc = PFVF_STATUS_NOT_SUPPORTED;
+
+			/* notify the VF that we do not support this request */
+			bnx2x_vf_mbx_resp(bp, vf);
+		} else {
+
+			/* can't send a response since this VF is unknown to us
+			 * just unlock the channel and be done with.
+			 */
+			bnx2x_unlock_vf_pf_channel(bp, vf,
+						   mbx->first_tlv.tl.type);
+		}
+
+
 	}
 }
 
-- 
1.7.9.GIT

^ permalink raw reply related

* [PATCH 11/22] bnx2x: Infrastructure for VF <-> PF request on PF side
From: Ariel Elior @ 2012-11-13 16:17 UTC (permalink / raw)
  To: David Miller; +Cc: netdev, Ariel Elior, Eilon Greenstein
In-Reply-To: <1352823451-27042-1-git-send-email-ariele@broadcom.com>

Support interrupt from device which indicates VF has placed
A request on the VF <-> PF channel.
The PF driver issues a DMAE to retrieve the request from the VM
memory (the Ghost Physical Address of the request is contained
in the interrupt. The PF driver uses the GPA in the DMAE request,
which is translated by the IOMMU to the correct physical address).
The request which arrives is examined to recognize the sending VF.
The PF driver allocates a workitem to handle the VF Operation (vfop).

Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x.h       |    6 +
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c  |  203 ++++++++++++++----
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c |  247 ++++++++++++++++++++-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h |  102 +++++++++
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c  |  158 +++++++++++++
 5 files changed, 671 insertions(+), 45 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index d0d1467..52012f2 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -1380,6 +1380,7 @@ struct bnx2x {
 	int			mrrs;
 
 	struct delayed_work	sp_task;
+	atomic_t		interrupt_occurred;
 	struct delayed_work	sp_rtnl_task;
 
 	struct delayed_work	period_task;
@@ -1871,6 +1872,11 @@ u32 bnx2x_dmae_opcode_clr_src_reset(u32 opcode);
 u32 bnx2x_dmae_opcode(struct bnx2x *bp, u8 src_type, u8 dst_type,
 		      bool with_comp, u8 comp_type);
 
+void bnx2x_prep_dmae_with_comp(struct bnx2x *bp, struct dmae_command *dmae,
+			       u8 src_type, u8 dst_type);
+int bnx2x_issue_dmae_with_comp(struct bnx2x *bp, struct dmae_command *dmae);
+void bnx2x_dp_dmae(struct bnx2x *bp, struct dmae_command *dmae, int msglvl);
+
 u8 bnx2x_is_pcie_pending(struct pci_dev *dev);
 
 void bnx2x_calc_fc_adv(struct bnx2x *bp);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 3f51700..1a7287b 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -345,6 +345,66 @@ static u32 bnx2x_reg_rd_ind(struct bnx2x *bp, u32 addr)
 #define DMAE_DP_DST_PCI		"pci dst_addr [%x:%08x]"
 #define DMAE_DP_DST_NONE	"dst_addr [none]"
 
+void bnx2x_dp_dmae(struct bnx2x *bp, struct dmae_command *dmae, int msglvl)
+{
+	u32 src_type = dmae->opcode & DMAE_COMMAND_SRC;
+
+	switch (dmae->opcode & DMAE_COMMAND_DST) {
+	case DMAE_CMD_DST_PCI:
+		if (src_type == DMAE_CMD_SRC_PCI)
+			DP(msglvl, "DMAE: opcode 0x%08x\n"
+			   "src [%x:%08x], len [%d*4], dst [%x:%08x]\n"
+			   "comp_addr [%x:%08x], comp_val 0x%08x\n",
+			   dmae->opcode, dmae->src_addr_hi, dmae->src_addr_lo,
+			   dmae->len, dmae->dst_addr_hi, dmae->dst_addr_lo,
+			   dmae->comp_addr_hi, dmae->comp_addr_lo,
+			   dmae->comp_val);
+		else
+			DP(msglvl, "DMAE: opcode 0x%08x\n"
+			   "src [%08x], len [%d*4], dst [%x:%08x]\n"
+			   "comp_addr [%x:%08x], comp_val 0x%08x\n",
+			   dmae->opcode, dmae->src_addr_lo >> 2,
+			   dmae->len, dmae->dst_addr_hi, dmae->dst_addr_lo,
+			   dmae->comp_addr_hi, dmae->comp_addr_lo,
+			   dmae->comp_val);
+		break;
+	case DMAE_CMD_DST_GRC:
+		if (src_type == DMAE_CMD_SRC_PCI)
+			DP(msglvl, "DMAE: opcode 0x%08x\n"
+			   "src [%x:%08x], len [%d*4], dst_addr [%08x]\n"
+			   "comp_addr [%x:%08x], comp_val 0x%08x\n",
+			   dmae->opcode, dmae->src_addr_hi, dmae->src_addr_lo,
+			   dmae->len, dmae->dst_addr_lo >> 2,
+			   dmae->comp_addr_hi, dmae->comp_addr_lo,
+			   dmae->comp_val);
+		else
+			DP(msglvl, "DMAE: opcode 0x%08x\n"
+			   "src [%08x], len [%d*4], dst [%08x]\n"
+			   "comp_addr [%x:%08x], comp_val 0x%08x\n",
+			   dmae->opcode, dmae->src_addr_lo >> 2,
+			   dmae->len, dmae->dst_addr_lo >> 2,
+			   dmae->comp_addr_hi, dmae->comp_addr_lo,
+			   dmae->comp_val);
+		break;
+	default:
+		if (src_type == DMAE_CMD_SRC_PCI)
+			DP(msglvl, "DMAE: opcode 0x%08x\n"
+			   "src_addr [%x:%08x]  len [%d * 4]  dst_addr [none]\n"
+			   "comp_addr [%x:%08x]  comp_val 0x%08x\n",
+			   dmae->opcode, dmae->src_addr_hi, dmae->src_addr_lo,
+			   dmae->len, dmae->comp_addr_hi, dmae->comp_addr_lo,
+			   dmae->comp_val);
+		else
+			DP(msglvl, "DMAE: opcode 0x%08x\n"
+			   "src_addr [%08x]  len [%d * 4]  dst_addr [none]\n"
+			   "comp_addr [%x:%08x]  comp_val 0x%08x\n",
+			   dmae->opcode, dmae->src_addr_lo >> 2,
+			   dmae->len, dmae->comp_addr_hi, dmae->comp_addr_lo,
+			   dmae->comp_val);
+		break;
+	}
+
+}
 
 /* copy command into DMAE command memory and set DMAE command go */
 void bnx2x_post_dmae(struct bnx2x *bp, struct dmae_command *dmae, int idx)
@@ -395,7 +455,7 @@ u32 bnx2x_dmae_opcode(struct bnx2x *bp, u8 src_type, u8 dst_type,
 	return opcode;
 }
 
-static void bnx2x_prep_dmae_with_comp(struct bnx2x *bp,
+void bnx2x_prep_dmae_with_comp(struct bnx2x *bp,
 				      struct dmae_command *dmae,
 				      u8 src_type, u8 dst_type)
 {
@@ -411,9 +471,8 @@ static void bnx2x_prep_dmae_with_comp(struct bnx2x *bp,
 	dmae->comp_val = DMAE_COMP_VAL;
 }
 
-/* issue a dmae command over the init-channel and wailt for completion */
-static int bnx2x_issue_dmae_with_comp(struct bnx2x *bp,
-				      struct dmae_command *dmae)
+/* issue a dmae command over the init-channel and wait for completion */
+int bnx2x_issue_dmae_with_comp(struct bnx2x *bp, struct dmae_command *dmae)
 {
 	u32 *wb_comp = bnx2x_sp(bp, wb_comp);
 	int cnt = CHIP_REV_IS_SLOW(bp) ? (400000) : 4000;
@@ -1598,6 +1657,24 @@ static bool bnx2x_trylock_leader_lock(struct bnx2x *bp)
 
 static void bnx2x_cnic_cfc_comp(struct bnx2x *bp, int cid, u8 err);
 
+/* schedule the sp task and mark that interrupt occurred (runs from ISR) */
+static inline int bnx2x_schedule_sp_task(struct bnx2x *bp)
+{
+	/* Set the interrupt occurred bit for the sp-task to recognize it
+	 * must ack the interrupt and transition according to the IGU
+	 * state machine.
+	 */
+	atomic_set(&bp->interrupt_occurred, 1);
+
+	/* The sp_task must execute only after this bit
+	 * is set, otherwise we will get out of sync and miss all
+	 * further interrupts. Hence, the barrier.
+	 */
+	smp_wmb();
+
+	/* schedule sp_task to workqueue */
+	return queue_delayed_work(bnx2x_wq, &bp->sp_task, 0);
+}
 
 void bnx2x_sp_event(struct bnx2x_fastpath *fp, union eth_rx_cqe *rr_cqe)
 {
@@ -1612,6 +1689,13 @@ void bnx2x_sp_event(struct bnx2x_fastpath *fp, union eth_rx_cqe *rr_cqe)
 	   fp->index, cid, command, bp->state,
 	   rr_cqe->ramrod_cqe.ramrod_type);
 
+	/* If cid is within VF range, replace the slowpath object with the
+	   one corresponding to this VF
+	 */
+	if (cid >= BNX2X_FIRST_VF_CID  &&
+	    cid < BNX2X_FIRST_VF_CID + BNX2X_VF_CIDS)
+		bnx2x_iov_set_queue_sp_obj(bp, cid, &q_obj);
+
 	switch (command) {
 	case (RAMROD_CMD_ID_ETH_CLIENT_UPDATE):
 		DP(BNX2X_MSG_SP, "got UPDATE ramrod. CID %d\n", cid);
@@ -1663,6 +1747,8 @@ void bnx2x_sp_event(struct bnx2x_fastpath *fp, union eth_rx_cqe *rr_cqe)
 #else
 		return;
 #endif
+	/* SRIOV: reschedule any 'in_progress' operations */
+	bnx2x_iov_sp_event(bp, cid, true);
 
 	smp_mb__before_atomic_inc();
 	atomic_inc(&bp->cq_spq_left);
@@ -1688,8 +1774,8 @@ void bnx2x_sp_event(struct bnx2x_fastpath *fp, union eth_rx_cqe *rr_cqe)
 		clear_bit(BNX2X_AFEX_FCOE_Q_UPDATE_PENDING, &bp->sp_state);
 		smp_mb__after_clear_bit();
 
-		/* schedule workqueue to send ack to MCP */
-		queue_delayed_work(bnx2x_wq, &bp->sp_task, 0);
+		/* schedule the sp task as mcp ack is required */
+		bnx2x_schedule_sp_task(bp);
 	}
 
 	return;
@@ -1749,7 +1835,11 @@ irqreturn_t bnx2x_interrupt(int irq, void *dev_instance)
 	}
 
 	if (unlikely(status & 0x1)) {
-		queue_delayed_work(bnx2x_wq, &bp->sp_task, 0);
+
+		/* schedule sp task to perform default status block work, ack
+		 * attentions and enable interrupts.
+		 */
+		bnx2x_schedule_sp_task(bp);
 
 		status &= ~0x1;
 		if (!status)
@@ -4812,7 +4902,7 @@ static void bnx2x_eq_int(struct bnx2x *bp)
 	u8 echo;
 	u32 cid;
 	u8 opcode;
-	int spqe_cnt = 0;
+	int rc, spqe_cnt = 0;
 	struct bnx2x_queue_sp_obj *q_obj;
 	struct bnx2x_func_sp_obj *f_obj = &bp->func_obj;
 	struct bnx2x_raw_obj *rss_raw = &bp->rss_conf_obj.raw;
@@ -4843,12 +4933,23 @@ static void bnx2x_eq_int(struct bnx2x *bp)
 
 		elem = &bp->eq_ring[EQ_DESC(sw_cons)];
 
+		rc = bnx2x_iov_eq_sp_event(bp, elem);
+		if (!rc) {
+			DP(BNX2X_MSG_IOV, "bnx2x_iov_eq_sp_event returned %d\n",
+			   rc);
+			goto next_spqe;
+		}
 		cid = SW_CID(elem->message.data.cfc_del_event.cid);
 		opcode = elem->message.opcode;
 
 
 		/* handle eq element */
 		switch (opcode) {
+		case EVENT_RING_OPCODE_VF_PF_CHANNEL:
+			DP(BNX2X_MSG_IOV, "vf pf channel element on eq");
+			bnx2x_vf_mbx(bp, &elem->message.data.vf_pf_event);
+			continue;
+
 		case EVENT_RING_OPCODE_STAT_QUERY:
 			DP(BNX2X_MSG_SP | BNX2X_MSG_STATS,
 			   "got statistics comp event %d\n",
@@ -5014,50 +5115,67 @@ next_spqe:
 static void bnx2x_sp_task(struct work_struct *work)
 {
 	struct bnx2x *bp = container_of(work, struct bnx2x, sp_task.work);
-	u16 status;
 
-	status = bnx2x_update_dsb_idx(bp);
-/*	if (status == 0)				     */
-/*		BNX2X_ERR("spurious slowpath interrupt!\n"); */
+	DP(BNX2X_MSG_SP, "sp task invoked\n");
 
-	DP(BNX2X_MSG_SP, "got a slowpath interrupt (status 0x%x)\n", status);
+	/* make sure the atomic interupt_occurred has bee written */
+	smp_rmb();
+	if (atomic_read(&bp->interrupt_occurred)) {
 
-	/* HW attentions */
-	if (status & BNX2X_DEF_SB_ATT_IDX) {
-		bnx2x_attn_int(bp);
-		status &= ~BNX2X_DEF_SB_ATT_IDX;
-	}
+		/* what work needs to be performed? */
+		u16 status = bnx2x_update_dsb_idx(bp);
+		DP(BNX2X_MSG_SP, "status %x\n", status);
 
-	/* SP events: STAT_QUERY and others */
-	if (status & BNX2X_DEF_SB_IDX) {
-		struct bnx2x_fastpath *fp = bnx2x_fcoe_fp(bp);
+		DP(BNX2X_MSG_SP, "setting interrupt_occurred to 0");
+		atomic_set(&bp->interrupt_occurred, 0);
+
+		/* HW attentions */
+		if (status & BNX2X_DEF_SB_ATT_IDX) {
+			bnx2x_attn_int(bp);
+			status &= ~BNX2X_DEF_SB_ATT_IDX;
+		}
+
+		/* SP events: STAT_QUERY and others */
+		if (status & BNX2X_DEF_SB_IDX) {
+			struct bnx2x_fastpath *fp = bnx2x_fcoe_fp(bp);
 
 		if (FCOE_INIT(bp) &&
-		    (bnx2x_has_rx_work(fp) || bnx2x_has_tx_work(fp))) {
-			/*
-			 * Prevent local bottom-halves from running as
-			 * we are going to change the local NAPI list.
-			 */
-			local_bh_disable();
-			napi_schedule(&bnx2x_fcoe(bp, napi));
-			local_bh_enable();
+			    (bnx2x_has_rx_work(fp) || bnx2x_has_tx_work(fp))) {
+				/*
+				 * Prevent local bottom-halves from running as
+				 * we are going to change the local NAPI list.
+				 */
+				local_bh_disable();
+				napi_schedule(&bnx2x_fcoe(bp, napi));
+				local_bh_enable();
+			}
+
+			/* Handle EQ completions */
+			bnx2x_eq_int(bp);
+
+			bnx2x_ack_sb(bp, bp->igu_dsb_id, USTORM_ID,
+				     le16_to_cpu(bp->def_idx), IGU_INT_NOP, 1);
+
+			status &= ~BNX2X_DEF_SB_IDX;
 		}
 
-		/* Handle EQ completions */
-		bnx2x_eq_int(bp);
+		/* if status is non zero then perhaps something went wrong */
+		if (unlikely(status))
+			DP(BNX2X_MSG_SP,
+			   "got an unknown interrupt! (status 0x%x)\n", status);
 
-		bnx2x_ack_sb(bp, bp->igu_dsb_id, USTORM_ID,
-			le16_to_cpu(bp->def_idx), IGU_INT_NOP, 1);
+		/* ack status block only if something was actually handled */
+		bnx2x_ack_sb(bp, bp->igu_dsb_id, ATTENTION_ID,
+			     le16_to_cpu(bp->def_att_idx), IGU_INT_ENABLE, 1);
 
-		status &= ~BNX2X_DEF_SB_IDX;
 	}
 
-	if (unlikely(status))
-		DP(BNX2X_MSG_SP, "got an unknown interrupt! (status 0x%x)\n",
-		   status);
-
-	bnx2x_ack_sb(bp, bp->igu_dsb_id, ATTENTION_ID,
-	     le16_to_cpu(bp->def_att_idx), IGU_INT_ENABLE, 1);
+	/* must be called after the EQ processing (since eq leads to sriov
+	 * ramrod completion flows).
+	 * This flow may have been scheduled by the arrival of a ramrod
+	 * completion, or by the sriov code rescheduling itself.
+	 */
+	bnx2x_iov_sp_task(bp);
 
 	/* afex - poll to check if VIFSET_ACK should be sent to MFW */
 	if (test_and_clear_bit(BNX2X_AFEX_PENDING_VIFSET_MCP_ACK,
@@ -5090,7 +5208,10 @@ irqreturn_t bnx2x_msix_sp_int(int irq, void *dev_instance)
 		rcu_read_unlock();
 	}
 
-	queue_delayed_work(bnx2x_wq, &bp->sp_task, 0);
+	/* schedule sp task to perform default status block work, ack
+	 * attentions and enable interrupts.
+	 */
+	bnx2x_schedule_sp_task(bp);
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index 22bae7f..1cd2176 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -509,6 +509,17 @@ static void bnx2x_vf_set_bars(struct bnx2x *bp, struct bnx2x_virtf *vf)
 	}
 }
 
+void __devexit bnx2x_iov_remove_one(struct bnx2x *bp)
+{
+	/* if SRIOV is not enabled there's nothing to do */
+	if (!IS_SRIOV(bp))
+		return;
+
+
+	/* free vf database */
+	__bnx2x_iov_free_vfdb(bp);
+}
+
 void bnx2x_iov_free_mem(struct bnx2x *bp)
 {
 	int i;
@@ -681,13 +692,241 @@ int bnx2x_iov_init_ilt(struct bnx2x *bp, u16 line)
 	}
 	return line+i;
 }
-void __devexit bnx2x_iov_remove_one(struct bnx2x *bp)
+
+static inline u8 bnx2x_iov_is_vf_cid(struct bnx2x *bp, u16 cid)
+{
+	return ((cid >= BNX2X_FIRST_VF_CID) &&
+		((cid - BNX2X_FIRST_VF_CID) < BNX2X_VF_CIDS));
+}
+
+static inline
+void bnx2x_vf_handle_classification_eqe(struct bnx2x *bp,
+					struct bnx2x_vf_queue *vfq,
+					union event_ring_elem *elem)
 {
-	/* if SRIOV is not eanbled there's nothing to do */
+	unsigned long ramrod_flags = 0;
+	int rc = 0;
+
+	/* Always push next commands out, don't wait here */
+	set_bit(RAMROD_CONT, &ramrod_flags);
+
+	switch (elem->message.data.eth_event.echo >> BNX2X_SWCID_SHIFT) {
+	case BNX2X_FILTER_MAC_PENDING:
+		rc = vfq->mac_obj.complete(bp, &vfq->mac_obj, elem,
+					   &ramrod_flags);
+		break;
+	case BNX2X_FILTER_VLAN_PENDING:
+		rc = vfq->vlan_obj.complete(bp, &vfq->vlan_obj, elem,
+					    &ramrod_flags);
+		break;
+	default:
+		BNX2X_ERR("Unsupported classification command: %d\n",
+			  elem->message.data.eth_event.echo);
+		return;
+	}
+	if (rc < 0)
+		BNX2X_ERR("Failed to schedule new commands: %d\n", rc);
+	else if (rc > 0)
+		DP(BNX2X_MSG_IOV, "Scheduled next pending commands...\n");
+}
+
+static inline
+void bnx2x_vf_handle_mcast_eqe(struct bnx2x *bp,
+			       struct bnx2x_virtf *vf)
+{
+	struct bnx2x_mcast_ramrod_params rparam = {NULL};
+	int rc;
+
+	rparam.mcast_obj = &vf->mcast_obj;
+
+	vf->mcast_obj.raw.clear_pending(&vf->mcast_obj.raw);
+
+	/* If there are pending mcast commands - send them */
+	if (vf->mcast_obj.check_pending(&vf->mcast_obj)) {
+		rc = bnx2x_config_mcast(bp, &rparam, BNX2X_MCAST_CMD_CONT);
+		if (rc < 0)
+			BNX2X_ERR("Failed to send pending mcast commands: %d\n",
+				  rc);
+	}
+}
+
+static inline
+void bnx2x_vf_handle_filters_eqe(struct bnx2x *bp,
+				 struct bnx2x_virtf *vf)
+{
+	smp_mb__before_clear_bit();
+	clear_bit(BNX2X_FILTER_RX_MODE_PENDING, &vf->filter_state);
+	smp_mb__after_clear_bit();
+}
+
+int bnx2x_iov_eq_sp_event(struct bnx2x *bp, union event_ring_elem *elem)
+{
+	struct bnx2x_virtf *vf;
+	int qidx = 0, abs_vfid;
+	u8 opcode;
+	u16 cid = 0xffff;
+
+	if (!IS_SRIOV(bp))
+		return 1;
+
+	/* first get the cid - the only events we handle here are cfc-delete
+	 * and set-mac completion
+	 */
+	opcode = elem->message.opcode;
+
+	switch (opcode) {
+	case EVENT_RING_OPCODE_CFC_DEL:
+		cid = SW_CID((__force __le32)
+			     elem->message.data.cfc_del_event.cid);
+		DP(BNX2X_MSG_IOV, "checking cfc-del comp cid=%d\n", cid);
+		break;
+	case EVENT_RING_OPCODE_CLASSIFICATION_RULES:
+	case EVENT_RING_OPCODE_MULTICAST_RULES:
+	case EVENT_RING_OPCODE_FILTERS_RULES:
+		cid = (elem->message.data.eth_event.echo &
+		       BNX2X_SWCID_MASK);
+		DP(BNX2X_MSG_IOV, "checking filtering comp cid=%d\n", cid);
+		break;
+	case EVENT_RING_OPCODE_VF_FLR:
+		abs_vfid = elem->message.data.vf_flr_event.vf_id;
+		DP(BNX2X_MSG_IOV, "Got VF FLR notification abs_vfid=%d\n", abs_vfid);
+		goto get_vf;
+	case EVENT_RING_OPCODE_MALICIOUS_VF:
+		abs_vfid = elem->message.data.malicious_vf_event.vf_id;
+		DP(BNX2X_MSG_IOV, "Got VF MALICIOUS notification abs_vfid=%d\n", abs_vfid);
+		goto get_vf;
+	default:
+		return 1;
+	}
+
+	/* check if the cid is the VF range */
+	if (!bnx2x_iov_is_vf_cid(bp, cid)) {
+		DP(BNX2X_MSG_IOV, "cid is outside vf range: %d\n", cid);
+		return 1;
+	}
+	/* extract vf and rxq index from vf_cid - relies on the following:
+	 * 1. vfid on cid reflects the true abs_vfid
+	 * 2. the max number of VFs (per path) is 64
+	 */
+	qidx = cid & ((1 << BNX2X_VF_CID_WND)-1);
+	abs_vfid = (cid >> BNX2X_VF_CID_WND) & (BNX2X_MAX_NUM_OF_VFS-1);
+get_vf:
+	vf = bnx2x_vf_by_abs_fid(bp, abs_vfid);
+
+	if (!vf) {
+		BNX2X_ERR("EQ completion for unknown VF, cid %d, abs_vfid %d\n",
+			  cid, abs_vfid);
+		return 0;
+	}
+
+	switch (opcode) {
+	case EVENT_RING_OPCODE_CFC_DEL:
+		DP(BNX2X_MSG_IOV, "got VF [%d:%d] cfc delete ramrod\n",
+		   vf->abs_vfid, qidx);
+		vfq_get(vf, qidx)->sp_obj.complete_cmd(bp,
+						       &vfq_get(vf,
+								qidx)->sp_obj,
+						       BNX2X_Q_CMD_CFC_DEL);
+		break;
+	case EVENT_RING_OPCODE_CLASSIFICATION_RULES:
+		DP(BNX2X_MSG_IOV, "got VF [%d:%d] set mac/vlan ramrod\n",
+		   vf->abs_vfid, qidx);
+		bnx2x_vf_handle_classification_eqe(bp, vfq_get(vf, qidx), elem);
+		break;
+	case EVENT_RING_OPCODE_MULTICAST_RULES:
+		DP(BNX2X_MSG_IOV, "got VF [%d:%d] set mcast ramrod\n",
+		   vf->abs_vfid, qidx);
+		bnx2x_vf_handle_mcast_eqe(bp, vf);
+		break;
+	case EVENT_RING_OPCODE_FILTERS_RULES:
+		DP(BNX2X_MSG_IOV, "got VF [%d:%d] set rx-mode ramrod\n",
+		   vf->abs_vfid, qidx);
+		bnx2x_vf_handle_filters_eqe(bp, vf);
+		break;
+	case EVENT_RING_OPCODE_VF_FLR:
+		DP(BNX2X_MSG_IOV, "got VF [%d] FLR notification\n",
+		   vf->abs_vfid);
+		/* Do nothing for now */
+		break;
+	case EVENT_RING_OPCODE_MALICIOUS_VF:
+		DP(BNX2X_MSG_IOV, "got VF [%d] MALICIOUS notification\n",
+		   vf->abs_vfid);
+		/* Do nothing for now */
+		break;
+	}
+	/* SRIOV: reschedule any 'in_progress' operations */
+	bnx2x_iov_sp_event(bp, cid, false);
+
+	return 0;
+}
+
+static inline struct bnx2x_virtf *bnx2x_vf_by_cid(struct bnx2x *bp, int vf_cid)
+{
+	/* extract the vf from vf_cid - relies on the following:
+	 * 1. vfid on cid reflects the true abs_vfid
+	 * 2. the max number of VFs (per path) is 64
+	 */
+	int abs_vfid = (vf_cid >> BNX2X_VF_CID_WND) & (BNX2X_MAX_NUM_OF_VFS-1);
+	return bnx2x_vf_by_abs_fid(bp, abs_vfid);
+}
+
+void bnx2x_iov_set_queue_sp_obj(struct bnx2x *bp, int vf_cid,
+				struct bnx2x_queue_sp_obj **q_obj)
+{
+	struct bnx2x_virtf *vf;
+
 	if (!IS_SRIOV(bp))
 		return;
 
+	vf = bnx2x_vf_by_cid(bp, vf_cid);
 
-	/* free vf database */
-	__bnx2x_iov_free_vfdb(bp);
+	if (vf) {
+		/**
+		 * extract queue index from vf_cid - relies on the following:
+		 * 1. vfid on cid reflects the true abs_vfid
+		 * 2. the max number of VFs (per path) is 64
+		 */
+		int q_index = vf_cid & ((1 << BNX2X_VF_CID_WND)-1);
+		*q_obj = &bnx2x_vfq(vf, q_index, sp_obj);
+	} else {
+		BNX2X_ERR("No vf matching cid %d\n", vf_cid);
+	}
+}
+
+void bnx2x_iov_sp_event(struct bnx2x *bp, int vf_cid, bool queue_work)
+{
+	struct bnx2x_virtf *vf;
+
+	/* check if the cid is the VF range */
+	if (!IS_SRIOV(bp) || !bnx2x_iov_is_vf_cid(bp, vf_cid))
+		return;
+
+	vf = bnx2x_vf_by_cid(bp, vf_cid);
+	if (vf) {
+
+		/* set in_progress flag */
+		atomic_set(&vf->op_in_progress, 1);
+		if (queue_work)
+			queue_delayed_work(bnx2x_wq, &bp->sp_task, 0);
+	}
+}
+void bnx2x_iov_sp_task(struct bnx2x *bp)
+{
+	int i;
+
+	if (!IS_SRIOV(bp))
+		return;
+	/* Iterate over all VFs and invoke state transition for VFs with
+	 * 'in-progress' slow-path operations
+	 */
+	DP(BNX2X_MSG_IOV, "searching for pending vf operations\n");
+	for_each_vf(bp, i) {
+		struct bnx2x_virtf *vf = BP_VF(bp, i);
+
+		if (!list_empty(&vf->op_list_head) &&
+		    atomic_read(&vf->op_in_progress)) {
+			DP(BNX2X_MSG_IOV, "running pending op for vf %d\n", i);
+			bnx2x_vfop_cur(bp, vf)->transition(bp, vf);
+		}
+	}
 }
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
index 6ac3dbd..6fd3042 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
@@ -85,6 +85,84 @@ union bnx2x_vfop_params {
 
 /* forward */
 struct bnx2x_virtf;
+
+/* VFOP definitions */
+typedef void (*vfop_handler_t)(struct bnx2x *bp, struct bnx2x_virtf *vf);
+
+/* VFOP queue filters command additional arguments */
+struct bnx2x_vfop_filter {
+	struct list_head link;
+	int type;
+#define BNX2X_VFOP_FILTER_MAC	1
+#define BNX2X_VFOP_FILTER_VLAN	2
+
+	bool add;
+	u8 *mac;
+	u16 vid;
+};
+
+struct bnx2x_vfop_filters {
+	int add_cnt;
+	struct list_head head;
+	struct bnx2x_vfop_filter filters[];
+};
+
+/* transient list allocated, built and saved until its
+ * passed to the SP-VERBs layer.
+ */
+struct bnx2x_vfop_args_mcast {
+	int mc_num;
+	struct bnx2x_mcast_list_elem *mc;
+};
+
+struct bnx2x_vfop_args_qctor {
+	int	qid;
+	u16	sb_idx;
+};
+
+struct bnx2x_vfop_args_qdtor {
+	int	qid;
+	struct eth_context *cxt;
+};
+
+struct bnx2x_vfop_args_defvlan {
+	int	qid;
+	bool	enable;
+	u16	vid;
+	u8	prio;
+};
+
+struct bnx2x_vfop_args_qx {
+	int	qid;
+	bool	en_add;
+};
+
+struct bnx2x_vfop_args_filters {
+	struct bnx2x_vfop_filters *multi_filter;
+	atomic_t *credit;	/* non NULL means 'don't consume credit' */
+};
+
+union bnx2x_vfop_args {
+	struct bnx2x_vfop_args_mcast	mc_list;
+	struct bnx2x_vfop_args_qctor	qctor;
+	struct bnx2x_vfop_args_qdtor	qdtor;
+	struct bnx2x_vfop_args_defvlan	defvlan;
+	struct bnx2x_vfop_args_qx	qx;
+	struct bnx2x_vfop_args_filters	filters;
+};
+
+struct bnx2x_vfop {
+	struct list_head link;
+	int			rc;		/* return code */
+	int			state;		/* next state */
+	union bnx2x_vfop_args	args;		/* extra arguments */
+	union bnx2x_vfop_params *op_p;		/* ramrod params */
+
+	/* state machine callbacks */
+	vfop_handler_t transition;
+	vfop_handler_t done;
+};
+
 /* vf context */
 struct bnx2x_virtf {
 	u16 cfg_flags;
@@ -289,6 +367,12 @@ struct bnx2x_vfdb {
 	u32 flrd_vfs[FLRD_VFS_DWORDS];
 };
 
+/* queue access */
+static inline struct bnx2x_vf_queue *vfq_get(struct bnx2x_virtf *vf, u8 index)
+{
+	return &(vf->vfqs[index]);
+}
+
 static inline u8 vf_igu_sb(struct bnx2x_virtf *vf, u16 sb_idx)
 {
 	return vf->igu_base_id + sb_idx;
@@ -303,7 +387,22 @@ int bnx2x_iov_alloc_mem(struct bnx2x *bp);
 int bnx2x_iov_nic_init(struct bnx2x *bp);
 void bnx2x_iov_init_dq(struct bnx2x *bp);
 void bnx2x_iov_init_dmae(struct bnx2x *bp);
+void bnx2x_iov_set_queue_sp_obj(struct bnx2x *bp, int vf_cid,
+				struct bnx2x_queue_sp_obj **q_obj);
+void bnx2x_iov_sp_event(struct bnx2x *bp, int vf_cid, bool queue_work);
+int bnx2x_iov_eq_sp_event(struct bnx2x *bp, union event_ring_elem *elem);
+void bnx2x_iov_sp_task(struct bnx2x *bp);
+/* global vf mailbox routines */
+void bnx2x_vf_mbx(struct bnx2x *bp, struct vf_pf_event_data *vfpf_event);
 void bnx2x_vf_enable_mbx(struct bnx2x *bp, u8 abs_vfid);
+static inline struct bnx2x_vfop *bnx2x_vfop_cur(struct bnx2x *bp,
+						struct bnx2x_virtf *vf)
+{
+	WARN(!mutex_is_locked(&vf->op_mutex), "about to access vf op linked list but mutex was not locked!");
+	WARN_ON(list_empty(&vf->op_list_head));
+	return list_first_entry(&vf->op_list_head, struct bnx2x_vfop, link);
+}
+
 int bnx2x_vf_idx_by_abs_fid(struct bnx2x *bp, u16 abs_vfid);
 /* VF FLR helpers */
 int bnx2x_vf_flr_clnup_epilog(struct bnx2x *bp, u8 abs_vfid);
@@ -313,4 +412,7 @@ void bnx2x_add_tlv(struct bnx2x *bp, void *tlvs_list, u16 offset, u16 type,
 void bnx2x_vfpf_prep(struct bnx2x *bp, struct vfpf_first_tlv *first_tlv,
 		     u16 type, u16 length);
 void bnx2x_dp_tlv_list(struct bnx2x *bp, void *tlvs_list);
+
+bool bnx2x_tlv_supported(u16 tlvtype);
+
 #endif /* bnx2x_sriov.h */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index f053b46..a933442 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -81,6 +81,24 @@ void bnx2x_dp_tlv_list(struct bnx2x *bp, void *tlvs_list)
 	   tlv->type, tlv->length);
 }
 
+/* test whether we support a tlv type */
+bool bnx2x_tlv_supported(u16 tlvtype)
+{
+	return CHANNEL_TLV_NONE < tlvtype && tlvtype < CHANNEL_TLV_MAX;
+}
+
+static inline int bnx2x_pfvf_status_codes(int rc)
+{
+	switch (rc) {
+	case 0:
+		return PFVF_STATUS_SUCCESS;
+	case -ENOMEM:
+		return PFVF_STATUS_NO_RESOURCE;
+	default:
+		return PFVF_STATUS_FAILURE;
+	}
+}
+
 /* General service functions */
 static inline void storm_memset_vf_mbx_ack(struct bnx2x *bp, u16 abs_fid)
 {
@@ -117,3 +135,143 @@ void bnx2x_vf_enable_mbx(struct bnx2x *bp, u8 abs_vfid)
 	/* enable the VF access to the mailbox */
 	bnx2x_vf_enable_access(bp, abs_vfid);
 }
+
+/* this works only on !E1h */
+static int bnx2x_copy32_vf_dmae(struct bnx2x *bp, u8 from_vf,
+				dma_addr_t pf_addr, u8 vfid, u32 vf_addr_hi,
+				u32 vf_addr_lo, u32 len32)
+{
+	struct dmae_command dmae;
+
+	if (CHIP_IS_E1x(bp)) {
+		BNX2X_ERR("Chip revision does not support VFs\n");
+		return DMAE_NOT_RDY;
+	}
+
+	if (!bp->dmae_ready) {
+		BNX2X_ERR("DMAE is not ready, can not copy\n");
+		return DMAE_NOT_RDY;
+	}
+
+	/* set opcode and fixed command fields */
+	bnx2x_prep_dmae_with_comp(bp, &dmae, DMAE_SRC_PCI, DMAE_DST_PCI);
+
+	if (from_vf) {
+		dmae.opcode_iov = (vfid << DMAE_COMMAND_SRC_VFID_SHIFT) |
+			(DMAE_SRC_VF << DMAE_COMMAND_SRC_VFPF_SHIFT) |
+			(DMAE_DST_PF << DMAE_COMMAND_DST_VFPF_SHIFT);
+
+		dmae.opcode |= (DMAE_C_DST << DMAE_COMMAND_C_FUNC_SHIFT);
+
+		dmae.src_addr_lo = vf_addr_lo;
+		dmae.src_addr_hi = vf_addr_hi;
+		dmae.dst_addr_lo = U64_LO(pf_addr);
+		dmae.dst_addr_hi = U64_HI(pf_addr);
+	} else {
+		dmae.opcode_iov = (vfid << DMAE_COMMAND_DST_VFID_SHIFT) |
+			(DMAE_DST_VF << DMAE_COMMAND_DST_VFPF_SHIFT) |
+			(DMAE_SRC_PF << DMAE_COMMAND_SRC_VFPF_SHIFT);
+
+		dmae.opcode |= (DMAE_C_SRC << DMAE_COMMAND_C_FUNC_SHIFT);
+
+		dmae.src_addr_lo = U64_LO(pf_addr);
+		dmae.src_addr_hi = U64_HI(pf_addr);
+		dmae.dst_addr_lo = vf_addr_lo;
+		dmae.dst_addr_hi = vf_addr_hi;
+	}
+	dmae.len = len32;
+
+	bnx2x_dp_dmae(bp, &dmae, BNX2X_MSG_DMAE);
+
+	/* issue the command and wait for completion */
+	return bnx2x_issue_dmae_with_comp(bp, &dmae);
+}
+/* dispatch request */
+static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
+				  struct bnx2x_vf_mbx *mbx)
+{
+	int i;
+
+	/* check if tlv type is known */
+	if (bnx2x_tlv_supported(mbx->first_tlv.tl.type)) {
+
+		/* switch on the opcode */
+		switch (mbx->first_tlv.tl.type) {
+		}
+
+	/* unknown TLV - this may belong to a VF driver from the future - a
+	 * version written after this PF driver was written, which supports
+	 * features unknown as of yet. Too bad since we don't support them.
+	 * Or this may be because someone wrote a crappy VF driver and is
+	 * sending garbage over the channel.
+	 */
+	} else {
+		BNX2X_ERR("unknown TLV. type %d length %d. first 20 bytes of mailbox buffer:\n",
+			  mbx->first_tlv.tl.type, mbx->first_tlv.tl.length);
+		for (i = 0; i < 20; i++)
+			DP_CONT(BNX2X_MSG_IOV, "%x ",
+				mbx->msg->req.tlv_buf_size.tlv_buffer[i]);
+	}
+}
+
+/* handle new vf-pf message */
+void bnx2x_vf_mbx(struct bnx2x *bp, struct vf_pf_event_data *vfpf_event)
+{
+	struct bnx2x_virtf *vf;
+	struct bnx2x_vf_mbx *mbx;
+	u8 vf_idx;
+	int rc;
+
+	DP(BNX2X_MSG_IOV,
+	   "vf pf event received: vfid %d, address_hi %x, address lo %x",
+	   vfpf_event->vf_id, vfpf_event->msg_addr_hi, vfpf_event->msg_addr_lo);
+	/* Sanity checks consider removing later */
+
+	/* check if the vf_id is valid */
+	if (vfpf_event->vf_id - BP_VFDB(bp)->sriov.first_vf_in_pf >
+	    BNX2X_NR_VIRTFN(bp)) {
+		BNX2X_ERR("Illegal vf_id %d max allowed: %d\n",
+			  vfpf_event->vf_id, BNX2X_NR_VIRTFN(bp));
+		goto mbx_done;
+	}
+	vf_idx = bnx2x_vf_idx_by_abs_fid(bp, vfpf_event->vf_id);
+
+	mbx = BP_VF_MBX(bp, vf_idx);
+
+	/* verify an event is not currently being processed -
+	 * debug failsafe only
+	 */
+	if (mbx->flags & VF_MSG_INPROCESS) {
+		BNX2X_ERR("Previous message is still being processed, vf_id %d\n",
+			  vfpf_event->vf_id);
+		goto mbx_done;
+	}
+
+	vf = BP_VF(bp, vf_idx);
+
+	/* save the VF message address */
+	mbx->vf_addr_hi = vfpf_event->msg_addr_hi;
+	mbx->vf_addr_lo = vfpf_event->msg_addr_lo;
+	DP(BNX2X_MSG_IOV, "mailbox vf address hi 0x%x, lo 0x%x, offset 0x%x",
+	   mbx->vf_addr_hi, mbx->vf_addr_lo, mbx->first_tlv.resp_msg_offset);
+
+	/* dmae to get the VF request */
+	rc = bnx2x_copy32_vf_dmae(bp, true, mbx->msg_mapping, vf->abs_vfid,
+				  mbx->vf_addr_hi, mbx->vf_addr_lo,
+				  sizeof(union vfpf_tlvs)/4);
+	if (rc) {
+		BNX2X_ERR("Failed to copy request VF %d\n", vf->abs_vfid);
+		goto mbx_error;
+	}
+
+	/* process the VF message header */
+	mbx->first_tlv = mbx->msg->req.first_tlv;
+
+	/* dispatch the request (will prepare the response) */
+	bnx2x_vf_mbx_request(bp, vf, mbx);
+	goto mbx_done;
+
+mbx_error:
+mbx_done:
+	return;
+}
-- 
1.7.9.GIT

^ permalink raw reply related


This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox