* [PATCH net-next] ipv6: do not allow ipv6 module to be removed
From: Cong Wang @ 2013-09-21 3:12 UTC (permalink / raw)
To: netdev; +Cc: David S. Miller, Hideaki YOSHIFUJI, Stephen Hemminger, Cong Wang
From: Cong Wang <amwang@redhat.com>
There was some bug report on ipv6 module removal path before.
Also, as Stephen pointed out, after vxlan module gets ipv6 support,
the ipv6 stub it used is not safe against this module removal either.
So, let's just remove inet6_exit() so that ipv6 module will not be
able to be unloaded.
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Cong Wang <amwang@redhat.com>
---
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 7c96100..4966b12 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -1028,52 +1028,4 @@ out_unregister_tcp_proto:
}
module_init(inet6_init);
-static void __exit inet6_exit(void)
-{
- if (disable_ipv6_mod)
- return;
-
- /* First of all disallow new sockets creation. */
- sock_unregister(PF_INET6);
- /* Disallow any further netlink messages */
- rtnl_unregister_all(PF_INET6);
-
- udpv6_exit();
- udplitev6_exit();
- tcpv6_exit();
-
- /* Cleanup code parts. */
- ipv6_packet_cleanup();
- ipv6_frag_exit();
- ipv6_exthdrs_exit();
- addrconf_cleanup();
- ip6_flowlabel_cleanup();
- ndisc_late_cleanup();
- ip6_route_cleanup();
-#ifdef CONFIG_PROC_FS
-
- /* Cleanup code parts. */
- if6_proc_exit();
- ipv6_misc_proc_exit();
- udplite6_proc_exit();
- raw6_proc_exit();
-#endif
- ipv6_netfilter_fini();
- ipv6_stub = NULL;
- igmp6_cleanup();
- ndisc_cleanup();
- ip6_mr_cleanup();
- icmpv6_cleanup();
- rawv6_exit();
-
- unregister_pernet_subsys(&inet6_net_ops);
- proto_unregister(&rawv6_prot);
- proto_unregister(&udplitev6_prot);
- proto_unregister(&udpv6_prot);
- proto_unregister(&tcpv6_prot);
-
- rcu_barrier(); /* Wait for completion of call_rcu()'s */
-}
-module_exit(inet6_exit);
-
MODULE_ALIAS_NETPROTO(PF_INET6);
^ permalink raw reply related
* [RESEND PATCH iproute2] vxlan: add ipv6 support
From: Cong Wang @ 2013-09-21 2:35 UTC (permalink / raw)
To: netdev; +Cc: David S. Miller, Cong Wang, Stephen Hemminger
From: Cong Wang <amwang@redhat.com>
The kernel already supports it, so add the support
to iproute2 as well.
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Cong Wang <amwang@redhat.com>
---
include/linux/if_link.h | 2 +
ip/iplink_vxlan.c | 69 ++++++++++++++++++++++++++++++++++++++--------
2 files changed, 59 insertions(+), 12 deletions(-)
diff --git a/include/linux/if_link.h b/include/linux/if_link.h
index d07aeca..0c37561 100644
--- a/include/linux/if_link.h
+++ b/include/linux/if_link.h
@@ -311,6 +311,8 @@ enum {
IFLA_VXLAN_L2MISS,
IFLA_VXLAN_L3MISS,
IFLA_VXLAN_PORT, /* destination port */
+ IFLA_VXLAN_GROUP6,
+ IFLA_VXLAN_LOCAL6,
__IFLA_VXLAN_MAX
};
#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
diff --git a/ip/iplink_vxlan.c b/ip/iplink_vxlan.c
index 4304b0d..12e1c74 100644
--- a/ip/iplink_vxlan.c
+++ b/ip/iplink_vxlan.c
@@ -43,6 +43,9 @@ static int vxlan_parse_opt(struct link_util *lu, int argc, char **argv,
__u32 saddr = 0;
__u32 gaddr = 0;
__u32 daddr = 0;
+ struct in6_addr saddr6 = IN6ADDR_ANY_INIT;
+ struct in6_addr gaddr6 = IN6ADDR_ANY_INIT;
+ struct in6_addr daddr6 = IN6ADDR_ANY_INIT;
unsigned link = 0;
__u8 tos = 0;
__u8 ttl = 0;
@@ -66,21 +69,36 @@ static int vxlan_parse_opt(struct link_util *lu, int argc, char **argv,
vni_set = 1;
} else if (!matches(*argv, "group")) {
NEXT_ARG();
- gaddr = get_addr32(*argv);
-
- if (!IN_MULTICAST(ntohl(gaddr)))
- invarg("invalid group address", *argv);
+ if (!inet_pton(AF_INET, *argv, &gaddr)) {
+ if (!inet_pton(AF_INET6, *argv, &gaddr6)) {
+ fprintf(stderr, "Invalid address \"%s\"\n", *argv);
+ return -1;
+ } else if (!IN6_IS_ADDR_MULTICAST(&gaddr6))
+ invarg("invald group address", *argv);
+ } else if (!IN_MULTICAST(ntohl(gaddr)))
+ invarg("invald group address", *argv);
} else if (!matches(*argv, "remote")) {
NEXT_ARG();
- daddr = get_addr32(*argv);
-
- if (IN_MULTICAST(ntohl(daddr)))
- invarg("invalid remote address", *argv);
+ if (!inet_pton(AF_INET, *argv, &daddr)) {
+ if (!inet_pton(AF_INET6, *argv, &daddr6)) {
+ fprintf(stderr, "Invalid address \"%s\"\n", *argv);
+ return -1;
+ } else if (IN6_IS_ADDR_MULTICAST(&daddr6))
+ invarg("invald remote address", *argv);
+ } else if (IN_MULTICAST(ntohl(daddr)))
+ invarg("invald remote address", *argv);
} else if (!matches(*argv, "local")) {
NEXT_ARG();
- if (strcmp(*argv, "any"))
- saddr = get_addr32(*argv);
- if (IN_MULTICAST(ntohl(saddr)))
+ if (strcmp(*argv, "any")) {
+ if (!inet_pton(AF_INET, *argv, &saddr)) {
+ if (!inet_pton(AF_INET6, *argv, &saddr6)) {
+ fprintf(stderr, "Invalid address \"%s\"\n", *argv);
+ return -1;
+ }
+ }
+ }
+
+ if (IN_MULTICAST(ntohl(saddr)) || IN6_IS_ADDR_MULTICAST(&saddr6))
invarg("invalid local address", *argv);
} else if (!matches(*argv, "dev")) {
NEXT_ARG();
@@ -167,7 +185,9 @@ static int vxlan_parse_opt(struct link_util *lu, int argc, char **argv,
fprintf(stderr, "vxlan: missing virtual network identifier\n");
return -1;
}
- if (gaddr && daddr) {
+ if ((gaddr && daddr) ||
+ (memcmp(&gaddr6, &in6addr_any, sizeof(gaddr6)) &&
+ memcmp(&daddr6, &in6addr_any, sizeof(daddr6)))) {
fprintf(stderr, "vxlan: both group and remote cannot be specified\n");
return -1;
}
@@ -176,8 +196,16 @@ static int vxlan_parse_opt(struct link_util *lu, int argc, char **argv,
addattr_l(n, 1024, IFLA_VXLAN_GROUP, &gaddr, 4);
else if (daddr)
addattr_l(n, 1024, IFLA_VXLAN_GROUP, &daddr, 4);
+ if (memcmp(&gaddr6, &in6addr_any, sizeof(gaddr6)) != 0)
+ addattr_l(n, 1024, IFLA_VXLAN_GROUP6, &gaddr6, sizeof(struct in6_addr));
+ else if (memcmp(&daddr6, &in6addr_any, sizeof(daddr6)) != 0)
+ addattr_l(n, 1024, IFLA_VXLAN_GROUP6, &daddr6, sizeof(struct in6_addr));
+
if (saddr)
addattr_l(n, 1024, IFLA_VXLAN_LOCAL, &saddr, 4);
+ else if (memcmp(&saddr6, &in6addr_any, sizeof(saddr6)) != 0)
+ addattr_l(n, 1024, IFLA_VXLAN_LOCAL6, &saddr6, sizeof(struct in6_addr));
+
if (link)
addattr32(n, 1024, IFLA_VXLAN_LINK, link);
addattr8(n, 1024, IFLA_VXLAN_TTL, ttl);
@@ -229,6 +257,17 @@ static void vxlan_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
fprintf(f, "remote %s ",
format_host(AF_INET, 4, &addr, s1, sizeof(s1)));
}
+ } else if (tb[IFLA_VXLAN_GROUP6]) {
+ struct in6_addr addr;
+ memcpy(&addr, RTA_DATA(tb[IFLA_VXLAN_GROUP6]), sizeof(struct in6_addr));
+ if (memcmp(&addr, &in6addr_any, sizeof(addr)) != 0) {
+ if (IN6_IS_ADDR_MULTICAST(&addr))
+ fprintf(f, "group %s ",
+ format_host(AF_INET6, sizeof(struct in6_addr), &addr, s1, sizeof(s1)));
+ else
+ fprintf(f, "remote %s ",
+ format_host(AF_INET6, sizeof(struct in6_addr), &addr, s1, sizeof(s1)));
+ }
}
if (tb[IFLA_VXLAN_LOCAL]) {
@@ -236,6 +275,12 @@ static void vxlan_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
if (addr)
fprintf(f, "local %s ",
format_host(AF_INET, 4, &addr, s1, sizeof(s1)));
+ } else if (tb[IFLA_VXLAN_LOCAL6]) {
+ struct in6_addr addr;
+ memcpy(&addr, RTA_DATA(tb[IFLA_VXLAN_LOCAL6]), sizeof(struct in6_addr));
+ if (memcmp(&addr, &in6addr_any, sizeof(addr)) != 0)
+ fprintf(f, "local %s ",
+ format_host(AF_INET6, sizeof(struct in6_addr), &addr, s1, sizeof(s1)));
}
if (tb[IFLA_VXLAN_LINK] &&
--
1.7.7.6
^ permalink raw reply related
* Re: [PATCH 1/1] mrp: add periodictimer to allow retries when packets get lost
From: Ward, David - 0663 - MITLL @ 2013-09-21 1:32 UTC (permalink / raw)
To: David Miller
Cc: noel@burton-krahn.com, netdev@vger.kernel.org, joe@perches.com
In-Reply-To: <20130920.145903.1454447110808820874.davem@davemloft.net>
[-- Attachment #1: Type: text/plain, Size: 878 bytes --]
Noel, thanks for your patch. This timer was apparently not in the GARP
standard but added in the MRP standard and I missed it. Looks good to me.
Acked-by: David Ward <david.ward@ll.mit.edu>
On 09/20/2013 02:59 PM, David Miller wrote:
> Re: [PATCH 1/1] mrp: add periodictimer to allow retries when packets
> get lost
>
> From: Noel Burton-Krahn <noel@burton-krahn.com>
> Date: Wed, 18 Sep 2013 12:24:40 -0700
>
> > MRP doesn't implement the periodictimer in 802.1Q, so it never retries
> > if packets get lost. I ran into this problem when MRP sent a MVRP
> > JoinIn before the interface was fully up. The JoinIn was lost, MRP
> > didn't retry, and MVRP registration failed.
> >
> > Tested against Juniper QFabric switches
> >
> > Signed-off-by: Noel Burton-Krahn <noel@burton-krahn.com>
>
> David W., please review this patch.
>
> Thanks.
>
[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4571 bytes --]
^ permalink raw reply
* Re: [PATCH v4] net/hsr: Add support for the High-availability Seamless Redundancy protocol (HSRv0)
From: Arvid Brodin @ 2013-09-21 1:28 UTC (permalink / raw)
To: David Miller
Cc: Arvid Brodin, netdev, shemminger, joe, jboticario, balferreira,
elias.molina
In-Reply-To: <523CF077.8010607@xdin.com>
On 2013-09-21 03:03, Arvid Brodin wrote:
> On 2013-09-21 02:43, Arvid Brodin wrote:
>> It's weird though, the "len" bug doesn't show up in my practical tests -
>> scp of 16 MiB file (sha1sum compared afterwards) and ping with default
>> and 65 KB packets work just fine before and after this change - even
>> between one fixed system and one with the bug remaining. Could it be
>> that none of the network device drivers we use (e1000e and macb) make
>> use of nonlinear skbs?
>
> Forget about this, e1000e is running on an architecture with
> HAVE_EFFICIENT_UNALIGNED_ACCESS, and on macb it does affect things -
> with the "fix" nothing works. :-|
... and that is because I have already shortened the packet through the
call to strip_hsr_tag() a few lines above, which calls
skb_pull(..., HSR_TAGLEN) in turn. So ->len is already correct.
Moving both ->data and ->tail, and all data between them, HSR_TAGLEN bytes
lower, should not be a problem if
a) the space ahead of ->data is vacant (not part of the packet),
b) there is enough headroom,
c) it does not break 32-bit alignment, and
d) there are no references to headers etc in the data being moved.
Right?
--
Arvid Brodin | Consultant (Linux)
XDIN AB | Knarrarnäsgatan 7 | SE-164 40 Kista | Sweden | xdin.com
^ permalink raw reply
* Re: [PATCH v4] net/hsr: Add support for the High-availability Seamless Redundancy protocol (HSRv0)
From: Arvid Brodin @ 2013-09-21 1:03 UTC (permalink / raw)
To: David Miller
Cc: Arvid Brodin, netdev, shemminger, joe, jboticario, balferreira,
elias.molina
In-Reply-To: <523CEBCD.10808@xdin.com>
On 2013-09-21 02:43, Arvid Brodin wrote:
> It's weird though, the "len" bug doesn't show up in my practical tests -
> scp of 16 MiB file (sha1sum compared afterwards) and ping with default
> and 65 KB packets work just fine before and after this change - even
> between one fixed system and one with the bug remaining. Could it be
> that none of the network device drivers we use (e1000e and macb) make
> use of nonlinear skbs?
Forget about this, e1000e is running on an architecture with
HAVE_EFFICIENT_UNALIGNED_ACCESS, and on macb it does affect things -
with the "fix" nothing works. :-|
--
Arvid Brodin | Consultant (Linux)
XDIN AB | Knarrarnäsgatan 7 | SE-164 40 Kista | Sweden | xdin.com
^ permalink raw reply
* Re: [PATCH v4] net/hsr: Add support for the High-availability Seamless Redundancy protocol (HSRv0)
From: Arvid Brodin @ 2013-09-21 0:43 UTC (permalink / raw)
To: David Miller
Cc: netdev, shemminger, joe, jboticario, balferreira, elias.molina,
Arvid Brodin
In-Reply-To: <20130920.151017.2125552741552759738.davem@davemloft.net>
On 2013-09-20 21:10, David Miller wrote:
> From: Arvid Brodin <arvid.brodin@xdin.com>
> Date: Thu, 19 Sep 2013 03:11:58 +0200
>
>> +#if !defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
>> + /* We need to memmove the whole header to work around
>> + * alignment problems caused by the 6-byte HSR tag.
>> + */
>> + memmove(skb_deliver->data - HSR_TAGLEN, skb_deliver->data,
>> + skb_headlen(skb_deliver));
>> + skb_deliver->data -= HSR_TAGLEN;
>> + skb_deliver->tail -= HSR_TAGLEN;
>> +#endif
>
> You can't do this.
>
> First of all, you have no idea if subtracting skb->data a given amount
> will underflow the skb buffer start. You aren't even checking, all
> of the standard skb_*() data adjustment interfaces do.
Isn't it reasonable to assume that skb points to an sk_buff with a
valid Ethernet header, and with skb->data pointing to the end of that
header, at the start of ETH_P_... protocol handlers?
> Secondly, everything after the header is now at the wrong offset from
> the beginning of the packet.
>
> You will have to memmove() the entire packet if you want to realign
> where it starts.
Are you saying packet data may contain offsets from itself to the mac
header? Or are you talking about fragments? This being the Ethernet
protocol handler, e.g. skb->network_header and skb->transport_header
should not have been set yet.
Anyway, I should do
skb_deliver->len -= HSR_TAGLEN;
here! (I'm removing 6 bytes after the mac header from the packet, not
just realigning it.)
Given all this, and looking at e.g. __pskb_pull_tail(), it should be
correct to memmove() only the linear part of the packet after the removed
bytes - any fragments will just be appended directly after the end of the
(shortened) linear part on use?
It's weird though, the "len" bug doesn't show up in my practical tests -
scp of 16 MiB file (sha1sum compared afterwards) and ping with default
and 65 KB packets work just fine before and after this change - even
between one fixed system and one with the bug remaining. Could it be
that none of the network device drivers we use (e1000e and macb) make
use of nonlinear skbs?
--
Arvid Brodin | Consultant (Linux)
XDIN AB | Knarrarnäsgatan 7 | SE-164 40 Kista | Sweden | xdin.com
^ permalink raw reply
* Re: [PATCH] sh_eth: call phy_scan_fixups() after PHY reset
From: Sergei Shtylyov @ 2013-09-21 0:39 UTC (permalink / raw)
To: David Miller, nobuhiro.iwamatsu.yj
Cc: netdev, linux-sh, laurent.pinchart+renesas
In-Reply-To: <20130917.154446.554384673039269498.davem@davemloft.net>
Hello.
On 09/17/2013 11:44 PM, David Miller wrote:
>> Sometimes the PHY reset that sh_eth_phy_start() does effects the PHY registers
>> registers values of which are vital for the correct functioning of the driver.
>> Unfortunately, the existing PHY platform fixup mechanism doesn't help here as
>> it only hooks PHY resets done by ioctl() calls. Calling phy_scan_fixups() from
>> the driver helps here. With a proper platform fixup, this fixes NFS timeouts on
>> the SH-Mobile Lager board.
"And sets the PHY LED pins to the desired mode", I should have added.
>> Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
> The PHY layer is designed to naturally already take care of this kind of
> thing. I think that part of the problem is that you're fighting the
> natural control flow the PHY layer provides.
> When the phy_connect() is performed, what we end up doing is calling
> phy_attach_direct() which invokes the ->probe() method of the driver
> and then afterwards we do phy_init_hw() which takes care of doing
> the fixup calls.
Yes, I have studied the code paths beforehand.
> So if you really need to do a BMCR reset then run the fixups I'd like
> you to look into making that happen within the provided control
> flow rather than with an exceptional explicit call to run the fixups.
That could change the behavior of many Ethernet drivers in sometimes
unpredictable ways I think (due to extended registers the PHYs sometimes have,
like in this case) if you meant including the PHY reset into phylib control
flows. Anyway, that would have required more complex patches only good for
merging at the merge window time while I aimed at a quick fix for a problem at
hand (which is NFS timeout/slowdown and LED mode mismatch to what was designed
for the board).
Some other drivers also do reset the PHYs but usually that's accompanied
by a loop polling for reset completion, so a naive code like that one on the
phylib's ioctl() path couldn't have helped if I wanted to hook reset writes in
the same fashion in phy_write(). In my case reset seems just quick enough for
the extended PHY register reads/writes to work correctly without polling the
reset bit first...
That's why I took an easy way and used already exported phy_scan_fixups()
to undo what the PHY reset did to some of the PHY's registers. The question is
why it was exported in the first place? It doesn't seem to be used by anything
but phylib internally...
> I'm willing to be convinced that this is a better or necessary approach
> but you'll need to explain it to me.
Well, I didn't write this driver, so I'm probably not the best person to
be asked about its design (maybe Iwamatsu-san could add something here). I
don't know about the purpose of the explicit PHY reset in the driver more than
the accompanying comment says (and it doesn't say much other than that it
takes the PHY out of power-down). Perhaps we could just painlessly remove it,
who knows?
> Thanks.
WBR, Sergei
^ permalink raw reply
* Re: [PATCH 1/2] remove all uses of printf's %n
From: Tetsuo Handa @ 2013-09-21 0:28 UTC (permalink / raw)
To: keescook, jslaby
Cc: viro, xemul, remi.denis-courmont, linux-kernel, netdev,
linux-sctp, linux, akpm, dan.carpenter, geert, JBeulich, joe,
kosaki.motohiro
In-Reply-To: <CAGXu5jLENb+x6b9XOY7-pWMT7GsFgnLr0=A8VNFLkqMi0BX4=w@mail.gmail.com>
Kees Cook wrote:
> >> - seq_printf(seq, "%*s\n", 127 - len, "");
> >> + seq_pad(seq, '\n');
> >
> > Hmm, seq_pad is unintuitive. I would say it pads the string by '\n'. Of
> > course it does not, but...
>
> I don't think this is a very serious problem. Currently, the padding
> character is always ' ' for all existing callers, so it only makes
> sense to make the trailing character an argument.
If you want, we can rename seq_pad() to seq_pad_and_putc(). Also we can pass
both the padding character (e.g. ' ') and the trailing character (e.g. '\n')
like seq_pad_and_putc((' ' << 8) | '\n'), though I wonder someone wants to
use '\0', '\t', '\n' etc. as the padding character...
^ permalink raw reply
* [PATCH net-next 6/8] tg3: Appropriately classify interrupts during request_irq
From: Nithin Nayak Sujir @ 2013-09-20 23:47 UTC (permalink / raw)
To: davem; +Cc: netdev, Nithin Nayak Sujir, Michael Chan
In-Reply-To: <1379720822-6500-1-git-send-email-nsujir@broadcom.com>
Distinguish between tx, rx and txrx interrupts.
Signed-off-by: Nithin Nayak Sujir <nsujir@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
---
drivers/net/ethernet/broadcom/tg3.c | 13 ++++++++++++-
1 file changed, 12 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index e56e4f8..b0dd391 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -11038,7 +11038,18 @@ static int tg3_request_irq(struct tg3 *tp, int irq_num)
name = tp->dev->name;
else {
name = &tnapi->irq_lbl[0];
- snprintf(name, IFNAMSIZ, "%s-%d", tp->dev->name, irq_num);
+ if (tnapi->tx_buffers && tnapi->rx_rcb)
+ snprintf(name, IFNAMSIZ,
+ "%s-txrx-%d", tp->dev->name, irq_num);
+ else if (tnapi->tx_buffers)
+ snprintf(name, IFNAMSIZ,
+ "%s-tx-%d", tp->dev->name, irq_num);
+ else if (tnapi->rx_rcb)
+ snprintf(name, IFNAMSIZ,
+ "%s-rx-%d", tp->dev->name, irq_num);
+ else
+ snprintf(name, IFNAMSIZ,
+ "%s-%d", tp->dev->name, irq_num);
name[IFNAMSIZ-1] = 0;
}
--
1.8.1.4
^ permalink raw reply related
* [PATCH net-next 1/8] tg3: Add function tg3_phy_shdw_write()
From: Nithin Nayak Sujir @ 2013-09-20 23:46 UTC (permalink / raw)
To: davem; +Cc: netdev, Nithin Nayak Sujir, Michael Chan
In-Reply-To: <1379720822-6500-1-git-send-email-nsujir@broadcom.com>
For consistency with other register access functions, add shadow
register access function of the type (register/val).
Signed-off-by: Nithin Nayak Sujir <nsujir@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
---
drivers/net/ethernet/broadcom/tg3.c | 18 ++++++++++--------
1 file changed, 10 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 5701f3d..d2bc391 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -1326,6 +1326,12 @@ static int tg3_phy_toggle_auxctl_smdsp(struct tg3 *tp, bool enable)
return err;
}
+static int tg3_phy_shdw_write(struct tg3 *tp, int reg, u32 val)
+{
+ return tg3_writephy(tp, MII_TG3_MISC_SHDW,
+ reg | val | MII_TG3_MISC_SHDW_WREN);
+}
+
static int tg3_bmcr_reset(struct tg3 *tp)
{
u32 phy_control;
@@ -2218,25 +2224,21 @@ static void tg3_phy_toggle_apd(struct tg3 *tp, bool enable)
return;
}
- reg = MII_TG3_MISC_SHDW_WREN |
- MII_TG3_MISC_SHDW_SCR5_SEL |
- MII_TG3_MISC_SHDW_SCR5_LPED |
+ reg = MII_TG3_MISC_SHDW_SCR5_LPED |
MII_TG3_MISC_SHDW_SCR5_DLPTLM |
MII_TG3_MISC_SHDW_SCR5_SDTL |
MII_TG3_MISC_SHDW_SCR5_C125OE;
if (tg3_asic_rev(tp) != ASIC_REV_5784 || !enable)
reg |= MII_TG3_MISC_SHDW_SCR5_DLLAPD;
- tg3_writephy(tp, MII_TG3_MISC_SHDW, reg);
+ tg3_phy_shdw_write(tp, MII_TG3_MISC_SHDW_SCR5_SEL, reg);
- reg = MII_TG3_MISC_SHDW_WREN |
- MII_TG3_MISC_SHDW_APD_SEL |
- MII_TG3_MISC_SHDW_APD_WKTM_84MS;
+ reg = MII_TG3_MISC_SHDW_APD_WKTM_84MS;
if (enable)
reg |= MII_TG3_MISC_SHDW_APD_ENABLE;
- tg3_writephy(tp, MII_TG3_MISC_SHDW, reg);
+ tg3_phy_shdw_write(tp, MII_TG3_MISC_SHDW_APD_SEL, reg);
}
static void tg3_phy_toggle_automdix(struct tg3 *tp, bool enable)
--
1.8.1.4
^ permalink raw reply related
* [PATCH net-next 0/8] tg3: Misc cleanups and fixes.
From: Nithin Nayak Sujir @ 2013-09-20 23:46 UTC (permalink / raw)
To: davem; +Cc: netdev, Nithin Nayak Sujir
Nithin Nayak Sujir (8):
tg3: Add function tg3_phy_shdw_write()
tg3: Add support for new 577xx device ids
tg3: LED in shared mode does not blink during traffic
tg3: Remove if 0'd code
tg3: Remove redundant if check
tg3: Appropriately classify interrupts during request_irq
tg3: Remove unnecessary spinlock
tg3: Update version to 3.134
drivers/net/ethernet/broadcom/tg3.c | 81 ++++++++++++++++++++-----------------
drivers/net/ethernet/broadcom/tg3.h | 3 ++
2 files changed, 47 insertions(+), 37 deletions(-)
--
1.8.1.4
^ permalink raw reply
* [PATCH net-next 8/8] tg3: Update version to 3.134
From: Nithin Nayak Sujir @ 2013-09-20 23:47 UTC (permalink / raw)
To: davem; +Cc: netdev, Nithin Nayak Sujir, Michael Chan
In-Reply-To: <1379720822-6500-1-git-send-email-nsujir@broadcom.com>
Signed-off-by: Nithin Nayak Sujir <nsujir@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
---
drivers/net/ethernet/broadcom/tg3.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index f3312cf..20d570d 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -94,10 +94,10 @@ static inline void _tg3_flag_clear(enum TG3_FLAGS flag, unsigned long *bits)
#define DRV_MODULE_NAME "tg3"
#define TG3_MAJ_NUM 3
-#define TG3_MIN_NUM 133
+#define TG3_MIN_NUM 134
#define DRV_MODULE_VERSION \
__stringify(TG3_MAJ_NUM) "." __stringify(TG3_MIN_NUM)
-#define DRV_MODULE_RELDATE "Jul 29, 2013"
+#define DRV_MODULE_RELDATE "Sep 16, 2013"
#define RESET_KIND_SHUTDOWN 0
#define RESET_KIND_INIT 1
--
1.8.1.4
^ permalink raw reply related
* [PATCH net-next 7/8] tg3: Remove unnecessary spinlock
From: Nithin Nayak Sujir @ 2013-09-20 23:47 UTC (permalink / raw)
To: davem; +Cc: netdev, Nithin Nayak Sujir, Michael Chan
In-Reply-To: <1379720822-6500-1-git-send-email-nsujir@broadcom.com>
The spinlock is not needed after conversion of tg3_flags from array to
set_bit().
Signed-off-by: Nithin Nayak Sujir <nsujir@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
---
drivers/net/ethernet/broadcom/tg3.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index b0dd391..f3312cf 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -12107,12 +12107,10 @@ static int tg3_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
device_set_wakeup_enable(dp, wol->wolopts & WAKE_MAGIC);
- spin_lock_bh(&tp->lock);
if (device_may_wakeup(dp))
tg3_flag_set(tp, WOL_ENABLE);
else
tg3_flag_clear(tp, WOL_ENABLE);
- spin_unlock_bh(&tp->lock);
return 0;
}
--
1.8.1.4
^ permalink raw reply related
* [PATCH net-next 4/8] tg3: Remove if 0'd code
From: Nithin Nayak Sujir @ 2013-09-20 23:46 UTC (permalink / raw)
To: davem; +Cc: netdev, Nithin Nayak Sujir, Michael Chan
In-Reply-To: <1379720822-6500-1-git-send-email-nsujir@broadcom.com>
Signed-off-by: Nithin Nayak Sujir <nsujir@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
---
drivers/net/ethernet/broadcom/tg3.c | 18 ------------------
1 file changed, 18 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 34cd0f5..01aa405 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -17067,10 +17067,6 @@ static int tg3_test_dma(struct tg3 *tp)
tw32(TG3PCI_DMA_RW_CTRL, tp->dma_rwctrl);
-#if 0
- /* Unneeded, already done by tg3_get_invariants. */
- tg3_switch_clocks(tp);
-#endif
if (tg3_asic_rev(tp) != ASIC_REV_5700 &&
tg3_asic_rev(tp) != ASIC_REV_5701)
@@ -17098,20 +17094,6 @@ static int tg3_test_dma(struct tg3 *tp)
break;
}
-#if 0
- /* validate data reached card RAM correctly. */
- for (i = 0; i < TEST_BUFFER_SIZE / sizeof(u32); i++) {
- u32 val;
- tg3_read_mem(tp, 0x2100 + (i*4), &val);
- if (le32_to_cpu(val) != p[i]) {
- dev_err(&tp->pdev->dev,
- "%s: Buffer corrupted on device! "
- "(%d != %d)\n", __func__, val, i);
- /* ret = -ENODEV here? */
- }
- p[i] = 0;
- }
-#endif
/* Now read it back. */
ret = tg3_do_test_dma(tp, buf, buf_dma, TEST_BUFFER_SIZE, false);
if (ret) {
--
1.8.1.4
^ permalink raw reply related
* [PATCH net-next 5/8] tg3: Remove redundant if check
From: Nithin Nayak Sujir @ 2013-09-20 23:46 UTC (permalink / raw)
To: davem; +Cc: netdev, Nithin Nayak Sujir, Michael Chan
In-Reply-To: <1379720822-6500-1-git-send-email-nsujir@broadcom.com>
Signed-off-by: Nithin Nayak Sujir <nsujir@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
---
drivers/net/ethernet/broadcom/tg3.c | 5 +----
1 file changed, 1 insertion(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 01aa405..e56e4f8 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -9202,10 +9202,7 @@ static int tg3_halt(struct tg3 *tp, int kind, bool silent)
memset(tp->hw_stats, 0, sizeof(struct tg3_hw_stats));
}
- if (err)
- return err;
-
- return 0;
+ return err;
}
static int tg3_set_mac_addr(struct net_device *dev, void *p)
--
1.8.1.4
^ permalink raw reply related
* [PATCH net-next 3/8] tg3: LED in shared mode does not blink during traffic
From: Nithin Nayak Sujir @ 2013-09-20 23:46 UTC (permalink / raw)
To: davem; +Cc: netdev, Nithin Nayak Sujir, Michael Chan
In-Reply-To: <1379720822-6500-1-git-send-email-nsujir@broadcom.com>
On the 5717, 5719, 5720 and 5762 devices, in shared link/activity mode,
the blink rate must be overridden with all bits set.
Signed-off-by: Nithin Nayak Sujir <nsujir@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
---
drivers/net/ethernet/broadcom/tg3.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 0155ac3..34cd0f5 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -14927,6 +14927,12 @@ static void tg3_get_eeprom_hw_cfg(struct tg3 *tp)
tg3_chip_rev_id(tp) != CHIPREV_ID_5750_A1)
tp->led_ctrl |= (LED_CTRL_MODE_PHY_1 |
LED_CTRL_MODE_PHY_2);
+
+ if (tg3_flag(tp, 5717_PLUS) ||
+ tg3_asic_rev(tp) == ASIC_REV_5762)
+ tp->led_ctrl |= LED_CTRL_BLINK_RATE_OVERRIDE |
+ LED_CTRL_BLINK_RATE_MASK;
+
break;
case SHASTA_EXT_LED_MAC:
--
1.8.1.4
^ permalink raw reply related
* [PATCH net-next 2/8] tg3: Add support for new 577xx device ids
From: Nithin Nayak Sujir @ 2013-09-20 23:46 UTC (permalink / raw)
To: davem; +Cc: netdev, Nithin Nayak Sujir, Michael Chan
In-Reply-To: <1379720822-6500-1-git-send-email-nsujir@broadcom.com>
This patch adds support for 57764, 57765, 57787, 57782 and 57786
devices.
Signed-off-by: Nithin Nayak Sujir <nsujir@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
---
drivers/net/ethernet/broadcom/tg3.c | 15 +++++++++++++--
drivers/net/ethernet/broadcom/tg3.h | 3 +++
2 files changed, 16 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index d2bc391..0155ac3 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -337,6 +337,11 @@ static DEFINE_PCI_DEVICE_TABLE(tg3_pci_tbl) = {
{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_5762)},
{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_5725)},
{PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_5727)},
+ {PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_57764)},
+ {PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_57767)},
+ {PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_57787)},
+ {PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_57782)},
+ {PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_57786)},
{PCI_DEVICE(PCI_VENDOR_ID_SYSKONNECT, PCI_DEVICE_ID_SYSKONNECT_9DXX)},
{PCI_DEVICE(PCI_VENDOR_ID_SYSKONNECT, PCI_DEVICE_ID_SYSKONNECT_9MXX)},
{PCI_DEVICE(PCI_VENDOR_ID_ALTIMA, PCI_DEVICE_ID_ALTIMA_AC1000)},
@@ -15760,9 +15765,12 @@ static void tg3_detect_asic_rev(struct tg3 *tp, u32 misc_ctrl_reg)
tp->pdev->device == TG3PCI_DEVICE_TIGON3_5718 ||
tp->pdev->device == TG3PCI_DEVICE_TIGON3_5719 ||
tp->pdev->device == TG3PCI_DEVICE_TIGON3_5720 ||
+ tp->pdev->device == TG3PCI_DEVICE_TIGON3_57767 ||
+ tp->pdev->device == TG3PCI_DEVICE_TIGON3_57764 ||
tp->pdev->device == TG3PCI_DEVICE_TIGON3_5762 ||
tp->pdev->device == TG3PCI_DEVICE_TIGON3_5725 ||
- tp->pdev->device == TG3PCI_DEVICE_TIGON3_5727)
+ tp->pdev->device == TG3PCI_DEVICE_TIGON3_5727 ||
+ tp->pdev->device == TG3PCI_DEVICE_TIGON3_57787)
reg = TG3PCI_GEN2_PRODID_ASICREV;
else if (tp->pdev->device == TG3PCI_DEVICE_TIGON3_57781 ||
tp->pdev->device == TG3PCI_DEVICE_TIGON3_57785 ||
@@ -17411,9 +17419,12 @@ static int tg3_init_one(struct pci_dev *pdev,
tp->pdev->device == TG3PCI_DEVICE_TIGON3_5718 ||
tp->pdev->device == TG3PCI_DEVICE_TIGON3_5719 ||
tp->pdev->device == TG3PCI_DEVICE_TIGON3_5720 ||
+ tp->pdev->device == TG3PCI_DEVICE_TIGON3_57767 ||
+ tp->pdev->device == TG3PCI_DEVICE_TIGON3_57764 ||
tp->pdev->device == TG3PCI_DEVICE_TIGON3_5762 ||
tp->pdev->device == TG3PCI_DEVICE_TIGON3_5725 ||
- tp->pdev->device == TG3PCI_DEVICE_TIGON3_5727) {
+ tp->pdev->device == TG3PCI_DEVICE_TIGON3_5727 ||
+ tp->pdev->device == TG3PCI_DEVICE_TIGON3_57787) {
tg3_flag_set(tp, ENABLE_APE);
tp->aperegs = pci_ioremap_bar(pdev, BAR_2);
if (!tp->aperegs) {
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index ddb8be1..e5249f8 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -68,6 +68,9 @@
#define TG3PCI_DEVICE_TIGON3_5762 0x1687
#define TG3PCI_DEVICE_TIGON3_5725 0x1643
#define TG3PCI_DEVICE_TIGON3_5727 0x16f3
+#define TG3PCI_DEVICE_TIGON3_57764 0x1642
+#define TG3PCI_DEVICE_TIGON3_57767 0x1683
+#define TG3PCI_DEVICE_TIGON3_57787 0x1641
/* 0x04 --> 0x2c unused */
#define TG3PCI_SUBVENDOR_ID_BROADCOM PCI_VENDOR_ID_BROADCOM
#define TG3PCI_SUBDEVICE_ID_BROADCOM_95700A6 0x1644
--
1.8.1.4
^ permalink raw reply related
* Re: [RFC PATCH 3/4] net: VSI: Add virtual station interface support
From: Neil Horman @ 2013-09-20 23:12 UTC (permalink / raw)
To: netdev; +Cc: John Fastabend
In-Reply-To: <20130911184718.26914.98366.stgit@nitbit.x32>
John-
Sorry for not copying your orgional patch into your email, but I apparently
erased this email prior to fully reading it. At any rate, as we discussed the
other day, I think this idea is great, but it would benefit from being
implemented using macvlans rather than a new link type. If we can set a
hardware flag in the underlying driver to indicate support for hardware
forwarding, we can skip the macvlan soft forwarding, and just transmit directly.
It should save us needing to create a whole new link type that is so simmilar to
one we already have.
I'm back home now, so I can start looking at this if you like on monday.
Best
Neil
^ permalink raw reply
* Re: [PATCH 39/51] DMA-API: others: use dma_set_coherent_mask()
From: Tejun Heo @ 2013-09-20 22:20 UTC (permalink / raw)
To: Russell King - ARM Linux
Cc: alsa-devel, b43-dev, devel, devicetree, dri-devel, e1000-devel,
linux-arm-kernel, linux-crypto, linux-doc, linux-fbdev, linux-ide,
linux-media, linux-mmc, linux-nvme, linux-omap, linuxppc-dev,
linux-samsung-soc, linux-scsi, linux-tegra, linux-usb,
linux-wireless, netdev, Solarflare linux maintainers,
uclinux-dist-devel, Inki Dae, Joonyoung Shim, Seung-Woo Kim, Kyun
In-Reply-To: <20130920140018.GP25647@n2100.arm.linux.org.uk>
Hey,
On Fri, Sep 20, 2013 at 03:00:18PM +0100, Russell King - ARM Linux wrote:
> Another would be if subsystem maintainers are happy that I carry them,
> I can add the acks, and then later on towards the end of the cycle,
> provide a branch subsystem maintainers could pull.
>
> Or... if you can think of something easier...
I'm happy with the latter method and it's likely that you'll end up
carrying at least some of the patches through your tree anyway.
Please feel free to add my acks to all libata related patches and
carry them through your tree.
Thanks and have fun routing.
--
tejun
^ permalink raw reply
* Re: [PATCH] skge: fix broken driver
From: Francois Romieu @ 2013-09-20 21:38 UTC (permalink / raw)
To: Mikulas Patocka; +Cc: Igor Gnatenko, David Miller, stephen, netdev
In-Reply-To: <alpine.LRH.2.02.1309201030420.30821@file01.intranet.prod.int.rdu2.redhat.com>
Mikulas Patocka <mpatocka@redhat.com> :
> On Thu, 19 Sep 2013, Francois Romieu wrote:
[...]
> > Both patches don't behave exactly the same wrt pci_unmap_single.
[...]
> I see, my patch passes a wrong value to pci_unmap_single. So I made this
> change to make it pass the correct value. Do you agree with this patch ?
Yes. I did not report it. Igor did.
You may "struct skge_element ee = *e;" and save a line. Who cares about
the extra copy when netdev_alloc_skb_ip_align fails ?
Something less ugly for the longer term
- use netdev_alloc_skb_ip_align in skge_rx_fill
- have skge_rx_setup return previouly stored sk_buff * - NULL if it was so -
and ERR_PTR when it fails for whatever reason
- move netdev_alloc_skb_ip_align into skge_rx_setup
- pci_unmap in skge_rx_setup
- profit
Or isolate the struct sk_buff * + DEFINE_DMA_ part in skge_element then
save it as a whole in skge_rx_setup before initializing a new one as a
(netdev_alloc_skb_ip_align + pci_map).
Does someone volunteer to write it for net-next once the fix has been
merged and later pulled into net-next ?
--
Ueimor
^ permalink raw reply
* [PATCH v2] qlge: call ql_core_dump() only if dump memory was allocated.
From: Malahal Naineni @ 2013-09-20 21:21 UTC (permalink / raw)
To: netdev
Also changed a log message to indicate that memory was not allocated
instead of memory not available!
Signed-off-by: Malahal Naineni <malahal@us.ibm.com>
---
drivers/net/ethernet/qlogic/qlge/qlge_dbg.c | 4 ++--
drivers/net/ethernet/qlogic/qlge/qlge_mpi.c | 2 +-
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c b/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c
index 10093f0..6bc5db7 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c
@@ -740,8 +740,8 @@ int ql_core_dump(struct ql_adapter *qdev, struct ql_mpi_coredump *mpi_coredump)
int i;
if (!mpi_coredump) {
- netif_err(qdev, drv, qdev->ndev, "No memory available\n");
- return -ENOMEM;
+ netif_err(qdev, drv, qdev->ndev, "No memory allocated\n");
+ return -EINVAL;
}
/* Try to get the spinlock, but dont worry if
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_mpi.c b/drivers/net/ethernet/qlogic/qlge/qlge_mpi.c
index ff2bf8a..7ad1460 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_mpi.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_mpi.c
@@ -1274,7 +1274,7 @@ void ql_mpi_reset_work(struct work_struct *work)
return;
}
- if (!ql_core_dump(qdev, qdev->mpi_coredump)) {
+ if (qdev->mpi_coredump && !ql_core_dump(qdev, qdev->mpi_coredump)) {
netif_err(qdev, drv, qdev->ndev, "Core is dumped!\n");
qdev->core_is_dumped = 1;
queue_delayed_work(qdev->workqueue,
--
1.7.11.7
^ permalink raw reply related
* [PATCH net-next] tcp: fix dynamic right sizing
From: Eric Dumazet @ 2013-09-20 20:56 UTC (permalink / raw)
To: David Miller; +Cc: netdev, Neal Cardwell, Yuchung Cheng, Van Jacobson
Dynamic Right Sizing (DRS) is supposed to open TCP receive window
automatically, but suffers from two bugs, presented by order
of importance.
1) tcp_rcv_space_adjust() fix :
Using twice the last received amount is very pessimistic,
because it doesn't allow fast recovery or proper slow start
ramp up, if sender wants to increase cwin by 100% every RTT.
copied = bytes received in previous RTT
2*copied = bytes we expect to receive in next RTT
4*copied = bytes we need to advertise in rwin at end of next RTT
DRS is one RTT late, it needs a 4x factor.
If sender is not using ABC, and increases cwin by 50% every rtt,
then we needed 1.5*1.5 = 2.25 factor.
This is probably why this bug was not really noticed.
2) There is no window adjustment after first RTT. DRS triggers only
after the second RTT.
DRS needs two RTT to initialize, so tcp_fixup_rcvbuf() should setup
sk_rcvbuf to allow proper window grow for first two RTT.
This patch increases TCP efficiency particularly for large RTT flows
when autotuning is used at the receiver, and more particularly
in presence of packet losses.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Cc: Van Jacobson <vanj@google.com>
---
net/ipv4/tcp_input.c | 84 +++++++++++++++++++++++++----------------
1 file changed, 53 insertions(+), 31 deletions(-)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 25a89ea..5d08385 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -355,6 +355,12 @@ static void tcp_fixup_rcvbuf(struct sock *sk)
rcvmem = 2 * SKB_TRUESIZE(mss + MAX_TCP_HEADER) *
tcp_default_init_rwnd(mss);
+ /* Dynamic Right Sizing (DRS) has 2 to 3 RTT latency
+ * Allow enough cushion so that sender is not limited by our window
+ */
+ if (sysctl_tcp_moderate_rcvbuf)
+ rcvmem <<= 2;
+
if (sk->sk_rcvbuf < rcvmem)
sk->sk_rcvbuf = min(rcvmem, sysctl_tcp_rmem[2]);
}
@@ -373,6 +379,8 @@ void tcp_init_buffer_space(struct sock *sk)
tcp_fixup_sndbuf(sk);
tp->rcvq_space.space = tp->rcv_wnd;
+ tp->rcvq_space.time = tcp_time_stamp;
+ tp->rcvq_space.seq = tp->copied_seq;
maxwin = tcp_full_space(sk);
@@ -512,48 +520,62 @@ void tcp_rcv_space_adjust(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
int time;
- int space;
-
- if (tp->rcvq_space.time == 0)
- goto new_measure;
+ int copied;
time = tcp_time_stamp - tp->rcvq_space.time;
if (time < (tp->rcv_rtt_est.rtt >> 3) || tp->rcv_rtt_est.rtt == 0)
return;
- space = 2 * (tp->copied_seq - tp->rcvq_space.seq);
+ /* Number of bytes copied to user in last RTT */
+ copied = tp->copied_seq - tp->rcvq_space.seq;
+ if (copied <= tp->rcvq_space.space)
+ goto new_measure;
+
+ /* A bit of theory :
+ * copied = bytes received in previous RTT, our base window
+ * To cope with packet losses, we need a 2x factor
+ * To cope with slow start, and sender growing its cwin by 100 %
+ * every RTT, we need a 4x factor, because the ACK we are sending
+ * now is for the next RTT, not the current one :
+ * <prev RTT . ><current RTT .. ><next RTT .... >
+ */
+
+ if (sysctl_tcp_moderate_rcvbuf &&
+ !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
+ int rcvwin, rcvmem, rcvbuf;
- space = max(tp->rcvq_space.space, space);
+ /* minimal window to cope with packet losses, assuming
+ * steady state. Add some cushion because of small variations.
+ */
+ rcvwin = (copied << 1) + 16 * tp->advmss;
- if (tp->rcvq_space.space != space) {
- int rcvmem;
+ /* If rate increased by 25%,
+ * assume slow start, rcvwin = 3 * copied
+ * If rate increased by 50%,
+ * assume sender can use 2x growth, rcvwin = 4 * copied
+ */
+ if (copied >=
+ tp->rcvq_space.space + (tp->rcvq_space.space >> 2)) {
+ if (copied >=
+ tp->rcvq_space.space + (tp->rcvq_space.space >> 1))
+ rcvwin <<= 1;
+ else
+ rcvwin += (rcvwin >> 1);
+ }
- tp->rcvq_space.space = space;
+ rcvmem = SKB_TRUESIZE(tp->advmss + MAX_TCP_HEADER);
+ while (tcp_win_from_space(rcvmem) < tp->advmss)
+ rcvmem += 128;
- if (sysctl_tcp_moderate_rcvbuf &&
- !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
- int new_clamp = space;
+ rcvbuf = min(rcvwin / tp->advmss * rcvmem, sysctl_tcp_rmem[2]);
+ if (rcvbuf > sk->sk_rcvbuf) {
+ sk->sk_rcvbuf = rcvbuf;
- /* Receive space grows, normalize in order to
- * take into account packet headers and sk_buff
- * structure overhead.
- */
- space /= tp->advmss;
- if (!space)
- space = 1;
- rcvmem = SKB_TRUESIZE(tp->advmss + MAX_TCP_HEADER);
- while (tcp_win_from_space(rcvmem) < tp->advmss)
- rcvmem += 128;
- space *= rcvmem;
- space = min(space, sysctl_tcp_rmem[2]);
- if (space > sk->sk_rcvbuf) {
- sk->sk_rcvbuf = space;
-
- /* Make the window clamp follow along. */
- tp->window_clamp = new_clamp;
- }
+ /* Make the window clamp follow along. */
+ tp->window_clamp = rcvwin;
}
}
+ tp->rcvq_space.space = copied;
new_measure:
tp->rcvq_space.seq = tp->copied_seq;
@@ -5674,8 +5696,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
tcp_init_congestion_control(sk);
tcp_mtup_init(sk);
- tcp_init_buffer_space(sk);
tp->copied_seq = tp->rcv_nxt;
+ tcp_init_buffer_space(sk);
}
smp_mb();
tcp_set_state(sk, TCP_ESTABLISHED);
^ permalink raw reply related
* [PATCH v3 -next 2/2] tcp: syncookies: reduce mss table to four values
From: Florian Westphal @ 2013-09-20 20:32 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal
In-Reply-To: <1379709176-1625-1-git-send-email-fw@strlen.de>
Halve mss table size to make blind cookie guessing more difficult.
This is sad since the tables were already small, but there
is little alternative except perhaps adding more precise mss information
in the tcp timestamp. Timestamps are unfortunately not ubiquitous.
Guessing all possible cookie values still has 8-in 2**32 chance.
Reported-by: Jakob Lell <jakob@jakoblell.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
Changes since v2:
- add comment explaining mss choices for tcp6 cookies, too
Changes since v1:
- add comment explaining mss choices
net/ipv4/syncookies.c | 22 +++++++++++-----------
net/ipv6/syncookies.c | 15 +++++++++------
2 files changed, 20 insertions(+), 17 deletions(-)
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index b6ea297..15e0241 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -136,22 +136,22 @@ static __u32 check_tcp_syn_cookie(__u32 cookie, __be32 saddr, __be32 daddr,
}
/*
- * MSS Values are taken from the 2009 paper
- * 'Measuring TCP Maximum Segment Size' by S. Alcock and R. Nelson:
- * - values 1440 to 1460 accounted for 80% of observed mss values
- * - values outside the 536-1460 range are rare (<0.2%).
+ * MSS Values are chosen based on the 2011 paper
+ * 'An Analysis of TCP Maximum Segement Sizes' by S. Alcock and R. Nelson.
+ * Values ..
+ * .. lower than 536 are rare (< 0.2%)
+ * .. between 537 and 1299 account for less than < 1.5% of observed values
+ * .. in the 1300-1349 range account for about 15 to 20% of observed mss values
+ * .. exceeding 1460 are very rare (< 0.04%)
*
- * Table must be sorted.
+ * 1460 is the single most frequently announced mss value (30 to 46% depending
+ * on monitor location). Table must be sorted.
*/
static __u16 const msstab[] = {
- 64,
- 512,
536,
- 1024,
- 1440,
+ 1300,
+ 1440, /* 1440, 1452: PPPoE */
1460,
- 4312,
- 8960,
};
/*
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 13ca0a0..d703218 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -24,15 +24,18 @@
#define COOKIEBITS 24 /* Upper bits store count */
#define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
-/* Table must be sorted. */
+/* RFC 2460, Section 8.3:
+ * [ipv6 tcp] MSS must be computed as the maximum packet size minus 60 [..]
+ *
+ * Due to IPV6_MIN_MTU=1280 the lowest possible MSS is 1220, which allows
+ * using higher values than ipv4 tcp syncookies.
+ * The other values are chosen based on ethernet (1500 and 9k MTU), plus
+ * one that accounts for common encap (PPPoe) overhead. Table must be sorted.
+ */
static __u16 const msstab[] = {
- 64,
- 512,
- 536,
- 1280 - 60,
+ 1280 - 60, /* IPV6_MIN_MTU - 60 */
1480 - 60,
1500 - 60,
- 4460 - 60,
9000 - 60,
};
--
1.8.1.5
^ permalink raw reply related
* [PATCH v3 -next 1/2] tcp: syncookies: reduce cookie lifetime to 128 seconds
From: Florian Westphal @ 2013-09-20 20:32 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal
We currently accept cookies that were created less than 4 minutes ago
(ie, cookies with counter delta 0-3). Combined with the 8 mss table
values, this yields 32 possible values (out of 2**32) that will be valid.
Reducing the lifetime to < 2 minutes halves the guessing chance while
still providing a large enough period.
While at it, get rid of jiffies value -- they overflow too quickly on
32 bit platforms.
getnstimeofday is used to create a counter that increments every 64s.
perf shows getnstimeofday cost is negible compared to sha_transform;
normal tcp initial sequence number generation uses getnstimeofday, too.
Reported-by: Jakob Lell <jakob@jakoblell.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
No changes since v2.
Changes since v1:
- add comment explaining MAX_SYNCOOKIE_AGE value
- add sentence about 'getnstimeofday' cost to commit message
- rebase on net-next master
include/net/tcp.h | 18 ++++++++++++++++++
net/ipv4/syncookies.c | 31 ++++++++++---------------------
net/ipv6/syncookies.c | 24 +++++++-----------------
3 files changed, 35 insertions(+), 38 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index b1aa324..ebb98e3 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -482,6 +482,24 @@ extern int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
extern struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
struct ip_options *opt);
#ifdef CONFIG_SYN_COOKIES
+#include <linux/ktime.h>
+
+/* Syncookies use a monotonic timer which increments every 64 seconds.
+ * This counter is used both as a hash input and partially encoded into
+ * the cookie value. A cookie is only validated further if the delta
+ * between the current counter value and the encoded one is less than this,
+ * i.e. a sent cookie is valid only at most for 128 seconds (or less if
+ * the counter advances immediately after a cookie is generated).
+ */
+#define MAX_SYNCOOKIE_AGE 2
+
+static inline u32 tcp_cookie_time(void)
+{
+ struct timespec now;
+ getnstimeofday(&now);
+ return now.tv_sec >> 6; /* 64 seconds granularity */
+}
+
extern u32 __cookie_v4_init_sequence(const struct iphdr *iph,
const struct tcphdr *th, u16 *mssp);
extern __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb,
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 14a15c4..b6ea297 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -89,8 +89,7 @@ __u32 cookie_init_timestamp(struct request_sock *req)
static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport,
- __be16 dport, __u32 sseq, __u32 count,
- __u32 data)
+ __be16 dport, __u32 sseq, __u32 data)
{
/*
* Compute the secure sequence number.
@@ -102,7 +101,7 @@ static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport,
* As an extra hack, we add a small "data" value that encodes the
* MSS into the second hash value.
*/
-
+ u32 count = tcp_cookie_time();
return (cookie_hash(saddr, daddr, sport, dport, 0, 0) +
sseq + (count << COOKIEBITS) +
((cookie_hash(saddr, daddr, sport, dport, count, 1) + data)
@@ -114,22 +113,21 @@ static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport,
* If the syncookie is bad, the data returned will be out of
* range. This must be checked by the caller.
*
- * The count value used to generate the cookie must be within
- * "maxdiff" if the current (passed-in) "count". The return value
- * is (__u32)-1 if this test fails.
+ * The count value used to generate the cookie must be less than
+ * MAX_SYNCOOKIE_AGE minutes in the past.
+ * The return value (__u32)-1 if this test fails.
*/
static __u32 check_tcp_syn_cookie(__u32 cookie, __be32 saddr, __be32 daddr,
- __be16 sport, __be16 dport, __u32 sseq,
- __u32 count, __u32 maxdiff)
+ __be16 sport, __be16 dport, __u32 sseq)
{
- __u32 diff;
+ u32 diff, count = tcp_cookie_time();
/* Strip away the layers from the cookie */
cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq;
/* Cookie is now reduced to (count * 2^24) ^ (hash % 2^24) */
diff = (count - (cookie >> COOKIEBITS)) & ((__u32) - 1 >> COOKIEBITS);
- if (diff >= maxdiff)
+ if (diff >= MAX_SYNCOOKIE_AGE)
return (__u32)-1;
return (cookie -
@@ -173,7 +171,7 @@ u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th,
return secure_tcp_syn_cookie(iph->saddr, iph->daddr,
th->source, th->dest, ntohl(th->seq),
- jiffies / (HZ * 60), mssind);
+ mssind);
}
EXPORT_SYMBOL_GPL(__cookie_v4_init_sequence);
@@ -189,13 +187,6 @@ __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp)
}
/*
- * This (misnamed) value is the age of syncookie which is permitted.
- * Its ideal value should be dependent on TCP_TIMEOUT_INIT and
- * sysctl_tcp_retries1. It's a rather complicated formula (exponential
- * backoff) to compute at runtime so it's currently hardcoded here.
- */
-#define COUNTER_TRIES 4
-/*
* Check if a ack sequence number is a valid syncookie.
* Return the decoded mss if it is, or 0 if not.
*/
@@ -204,9 +195,7 @@ int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
{
__u32 seq = ntohl(th->seq) - 1;
__u32 mssind = check_tcp_syn_cookie(cookie, iph->saddr, iph->daddr,
- th->source, th->dest, seq,
- jiffies / (HZ * 60),
- COUNTER_TRIES);
+ th->source, th->dest, seq);
return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0;
}
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index bf63ac8..13ca0a0 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -36,14 +36,6 @@ static __u16 const msstab[] = {
9000 - 60,
};
-/*
- * This (misnamed) value is the age of syncookie which is permitted.
- * Its ideal value should be dependent on TCP_TIMEOUT_INIT and
- * sysctl_tcp_retries1. It's a rather complicated formula (exponential
- * backoff) to compute at runtime so it's currently hardcoded here.
- */
-#define COUNTER_TRIES 4
-
static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst)
@@ -86,8 +78,9 @@ static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *dadd
static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr,
const struct in6_addr *daddr,
__be16 sport, __be16 dport, __u32 sseq,
- __u32 count, __u32 data)
+ __u32 data)
{
+ u32 count = tcp_cookie_time();
return (cookie_hash(saddr, daddr, sport, dport, 0, 0) +
sseq + (count << COOKIEBITS) +
((cookie_hash(saddr, daddr, sport, dport, count, 1) + data)
@@ -96,15 +89,14 @@ static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr,
static __u32 check_tcp_syn_cookie(__u32 cookie, const struct in6_addr *saddr,
const struct in6_addr *daddr, __be16 sport,
- __be16 dport, __u32 sseq, __u32 count,
- __u32 maxdiff)
+ __be16 dport, __u32 sseq)
{
- __u32 diff;
+ __u32 diff, count = tcp_cookie_time();
cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq;
diff = (count - (cookie >> COOKIEBITS)) & ((__u32) -1 >> COOKIEBITS);
- if (diff >= maxdiff)
+ if (diff >= MAX_SYNCOOKIE_AGE)
return (__u32)-1;
return (cookie -
@@ -125,8 +117,7 @@ u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph,
*mssp = msstab[mssind];
return secure_tcp_syn_cookie(&iph->saddr, &iph->daddr, th->source,
- th->dest, ntohl(th->seq),
- jiffies / (HZ * 60), mssind);
+ th->dest, ntohl(th->seq), mssind);
}
EXPORT_SYMBOL_GPL(__cookie_v6_init_sequence);
@@ -146,8 +137,7 @@ int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th,
{
__u32 seq = ntohl(th->seq) - 1;
__u32 mssind = check_tcp_syn_cookie(cookie, &iph->saddr, &iph->daddr,
- th->source, th->dest, seq,
- jiffies / (HZ * 60), COUNTER_TRIES);
+ th->source, th->dest, seq);
return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0;
}
--
1.8.1.5
^ permalink raw reply related
* Re: [PATCH 08/51] DMA-API: net: intel/ixgbevf: fix 32-bit DMA mask handling
From: Jeff Kirsher @ 2013-09-20 19:51 UTC (permalink / raw)
To: Russell King
Cc: alsa-devel, linux-doc, linux-mmc, Peter P Waskiewicz Jr,
linux-fbdev, linux-nvme, linux-ide, Carolyn Wyborny, devel,
linux-samsung-soc, linux-scsi, e1000-devel, Don Skidmore,
Jesse Brandeburg, b43-dev, linux-media, Alex Duyck, devicetree,
Greg Rose, dri-devel, linux-tegra, linux-omap, linux-arm-kernel,
Solarflare linux maintainers, netdev, linux-usb
In-Reply-To: <E1VMlqN-0007fw-MQ@rmk-PC.arm.linux.org.uk>
[-- Attachment #1.1: Type: text/plain, Size: 1366 bytes --]
On Thu, 2013-09-19 at 22:32 +0100, Russell King wrote:
> The fallback to 32-bit DMA mask is rather odd:
> if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)) &&
> !dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64))) {
> pci_using_dac = 1;
> } else {
> err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
> if (err) {
> err = dma_set_coherent_mask(&pdev->dev,
> DMA_BIT_MASK(32));
> if (err) {
> dev_err(&pdev->dev, "No usable DMA "
> "configuration, aborting\n");
> goto err_dma;
> }
> }
> pci_using_dac = 0;
> }
> This means we only set the coherent DMA mask in the fallback path if
> the DMA mask set failed, which is silly. This fixes it to set the
> coherent DMA mask only if dma_set_mask() succeeded, and to error out
> if either fails.
>
> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
> ---
> drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 15
> +++++----------
> 1 files changed, 5 insertions(+), 10 deletions(-)
Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
[-- Attachment #1.2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 836 bytes --]
[-- Attachment #2: Type: text/plain, Size: 150 bytes --]
_______________________________________________
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox