* [PATCH net-next 5/5] qlcnic: Bumped up driver version to 5.0.12
From: Anirban Chakraborty @ 2010-11-17 0:09 UTC (permalink / raw)
To: David Miller, netdev@vger.kernel.org; +Cc: Dept_NX_Linux_NIC_Driver
Signed-off-by: Anirban Chakraborty <anirban.chakraborty@qlogic.com>
---
drivers/net/qlcnic/qlcnic.h | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/qlcnic/qlcnic.h b/drivers/net/qlcnic/qlcnic.h
index 1375981..56f54ff 100644
--- a/drivers/net/qlcnic/qlcnic.h
+++ b/drivers/net/qlcnic/qlcnic.h
@@ -51,8 +51,8 @@
#define _QLCNIC_LINUX_MAJOR 5
#define _QLCNIC_LINUX_MINOR 0
-#define _QLCNIC_LINUX_SUBVERSION 11
-#define QLCNIC_LINUX_VERSIONID "5.0.11"
+#define _QLCNIC_LINUX_SUBVERSION 12
+#define QLCNIC_LINUX_VERSIONID "5.0.12"
#define QLCNIC_DRV_IDC_VER 0x01
#define QLCNIC_DRIVER_VERSION ((_QLCNIC_LINUX_MAJOR << 16) |\
(_QLCNIC_LINUX_MINOR << 8) | (_QLCNIC_LINUX_SUBVERSION))
--
1.5.4.5
^ permalink raw reply related
* [PATCH v3] filter: Optimize instruction revalidation code.
From: Tetsuo Handa @ 2010-11-17 1:19 UTC (permalink / raw)
To: mjt, davem, drosenberg, hagen, xiaosuo; +Cc: netdev
In-Reply-To: <1289925055.5372.484.camel@edumazet-laptop>
Eric Dumazet wrote:
> I dont understand the problem...
> Once translated, you have to test the translated code, not the original
> one ;)
I moved the test to after translation.
> why u16 ?
>
> You store translated instructions, so u8 is OK
I chose u16 because type of filter->code is __u16.
But I changed to use u8 as you suggested that translated code fits in u8.
> Also fix the indentation at the end of sk_chk_filter()
>
> You have 3 extra tabulations :
Fixed.
Hagen Paul Pfeifer wrote:
> Maybe I don't get it, but you increment the opcode by one, but you never
> increment the opcode in sk_run_filter() - do I miss something? Did you test
> the your patch (a trivial tcpdump rule should be sufficient)?
I added a comment line.
Changli Gao wrote:
> > + struct sock_filter *ftest = &filter[pc];
>
> Why move the define here?
To suppress compiler's warning about mixed declaration.
> > + u16 code = ftest->code;
> >
> > + if (code >= ARRAY_SIZE(codes))
> > + return 0;
>
> return -EINVAL;
Fixed in v2. Thanks.
> But how about this:
>
> enum {
> BPF_S_RET_K = 1,
If BPF_S_* are only for kernel internal use, I think we don't need to translate
from the beginning because only net/core/filter.c uses BPF_S_*.
BPF_S_* are exposed to userspace via /usr/include/linux/filter.h since 2.6.36.
Is it no problem to change?
Filesize change (x86_32) by this patch:
gcc 3.3.5: 7184 -> 5060
gcc 4.4.3: 7972 -> 5588
----------------------------------------
>From b8777ab64bc31dbbe499eb62c2ffd29add7e79c8 Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Wed, 17 Nov 2010 09:46:33 +0900
Subject: [PATCH v3] filter: Optimize instruction revalidation code.
Since repeating u16 value to u8 value conversion using switch() clause's
case statement is wasteful, this patch introduces u16 to u8 mapping table
and removes most of case statements. As a result, the size of net/core/filter.o
is reduced by about 29% on x86.
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
---
net/core/filter.c | 231 +++++++++++++++++------------------------------------
1 files changed, 72 insertions(+), 159 deletions(-)
diff --git a/net/core/filter.c b/net/core/filter.c
index 23e9b2a..03dc071 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -383,7 +383,57 @@ EXPORT_SYMBOL(sk_run_filter);
*/
int sk_chk_filter(struct sock_filter *filter, int flen)
{
- struct sock_filter *ftest;
+ /*
+ * Valid instructions are initialized to non-0.
+ * Invalid instructions are initialized to 0.
+ */
+ static const u8 codes[] = {
+ [BPF_ALU|BPF_ADD|BPF_K] = BPF_S_ALU_ADD_K + 1,
+ [BPF_ALU|BPF_ADD|BPF_X] = BPF_S_ALU_ADD_X + 1,
+ [BPF_ALU|BPF_SUB|BPF_K] = BPF_S_ALU_SUB_K + 1,
+ [BPF_ALU|BPF_SUB|BPF_X] = BPF_S_ALU_SUB_X + 1,
+ [BPF_ALU|BPF_MUL|BPF_K] = BPF_S_ALU_MUL_K + 1,
+ [BPF_ALU|BPF_MUL|BPF_X] = BPF_S_ALU_MUL_X + 1,
+ [BPF_ALU|BPF_DIV|BPF_X] = BPF_S_ALU_DIV_X + 1,
+ [BPF_ALU|BPF_AND|BPF_K] = BPF_S_ALU_AND_K + 1,
+ [BPF_ALU|BPF_AND|BPF_X] = BPF_S_ALU_AND_X + 1,
+ [BPF_ALU|BPF_OR|BPF_K] = BPF_S_ALU_OR_K + 1,
+ [BPF_ALU|BPF_OR|BPF_X] = BPF_S_ALU_OR_X + 1,
+ [BPF_ALU|BPF_LSH|BPF_K] = BPF_S_ALU_LSH_K + 1,
+ [BPF_ALU|BPF_LSH|BPF_X] = BPF_S_ALU_LSH_X + 1,
+ [BPF_ALU|BPF_RSH|BPF_K] = BPF_S_ALU_RSH_K + 1,
+ [BPF_ALU|BPF_RSH|BPF_X] = BPF_S_ALU_RSH_X + 1,
+ [BPF_ALU|BPF_NEG] = BPF_S_ALU_NEG + 1,
+ [BPF_LD|BPF_W|BPF_ABS] = BPF_S_LD_W_ABS + 1,
+ [BPF_LD|BPF_H|BPF_ABS] = BPF_S_LD_H_ABS + 1,
+ [BPF_LD|BPF_B|BPF_ABS] = BPF_S_LD_B_ABS + 1,
+ [BPF_LD|BPF_W|BPF_LEN] = BPF_S_LD_W_LEN + 1,
+ [BPF_LD|BPF_W|BPF_IND] = BPF_S_LD_W_IND + 1,
+ [BPF_LD|BPF_H|BPF_IND] = BPF_S_LD_H_IND + 1,
+ [BPF_LD|BPF_B|BPF_IND] = BPF_S_LD_B_IND + 1,
+ [BPF_LD|BPF_IMM] = BPF_S_LD_IMM + 1,
+ [BPF_LDX|BPF_W|BPF_LEN] = BPF_S_LDX_W_LEN + 1,
+ [BPF_LDX|BPF_B|BPF_MSH] = BPF_S_LDX_B_MSH + 1,
+ [BPF_LDX|BPF_IMM] = BPF_S_LDX_IMM + 1,
+ [BPF_MISC|BPF_TAX] = BPF_S_MISC_TAX + 1,
+ [BPF_MISC|BPF_TXA] = BPF_S_MISC_TXA + 1,
+ [BPF_RET|BPF_K] = BPF_S_RET_K + 1,
+ [BPF_RET|BPF_A] = BPF_S_RET_A + 1,
+ [BPF_ALU|BPF_DIV|BPF_K] = BPF_S_ALU_DIV_K + 1,
+ [BPF_LD|BPF_MEM] = BPF_S_LD_MEM + 1,
+ [BPF_LDX|BPF_MEM] = BPF_S_LDX_MEM + 1,
+ [BPF_ST] = BPF_S_ST + 1,
+ [BPF_STX] = BPF_S_STX + 1,
+ [BPF_JMP|BPF_JA] = BPF_S_JMP_JA + 1,
+ [BPF_JMP|BPF_JEQ|BPF_K] = BPF_S_JMP_JEQ_K + 1,
+ [BPF_JMP|BPF_JEQ|BPF_X] = BPF_S_JMP_JEQ_X + 1,
+ [BPF_JMP|BPF_JGE|BPF_K] = BPF_S_JMP_JGE_K + 1,
+ [BPF_JMP|BPF_JGE|BPF_X] = BPF_S_JMP_JGE_X + 1,
+ [BPF_JMP|BPF_JGT|BPF_K] = BPF_S_JMP_JGT_K + 1,
+ [BPF_JMP|BPF_JGT|BPF_X] = BPF_S_JMP_JGT_X + 1,
+ [BPF_JMP|BPF_JSET|BPF_K] = BPF_S_JMP_JSET_K + 1,
+ [BPF_JMP|BPF_JSET|BPF_X] = BPF_S_JMP_JSET_X + 1,
+ };
int pc;
if (flen == 0 || flen > BPF_MAXINSNS)
@@ -391,136 +441,31 @@ int sk_chk_filter(struct sock_filter *filter, int flen)
/* check the filter code now */
for (pc = 0; pc < flen; pc++) {
- ftest = &filter[pc];
-
- /* Only allow valid instructions */
- switch (ftest->code) {
- case BPF_ALU|BPF_ADD|BPF_K:
- ftest->code = BPF_S_ALU_ADD_K;
- break;
- case BPF_ALU|BPF_ADD|BPF_X:
- ftest->code = BPF_S_ALU_ADD_X;
- break;
- case BPF_ALU|BPF_SUB|BPF_K:
- ftest->code = BPF_S_ALU_SUB_K;
- break;
- case BPF_ALU|BPF_SUB|BPF_X:
- ftest->code = BPF_S_ALU_SUB_X;
- break;
- case BPF_ALU|BPF_MUL|BPF_K:
- ftest->code = BPF_S_ALU_MUL_K;
- break;
- case BPF_ALU|BPF_MUL|BPF_X:
- ftest->code = BPF_S_ALU_MUL_X;
- break;
- case BPF_ALU|BPF_DIV|BPF_X:
- ftest->code = BPF_S_ALU_DIV_X;
- break;
- case BPF_ALU|BPF_AND|BPF_K:
- ftest->code = BPF_S_ALU_AND_K;
- break;
- case BPF_ALU|BPF_AND|BPF_X:
- ftest->code = BPF_S_ALU_AND_X;
- break;
- case BPF_ALU|BPF_OR|BPF_K:
- ftest->code = BPF_S_ALU_OR_K;
- break;
- case BPF_ALU|BPF_OR|BPF_X:
- ftest->code = BPF_S_ALU_OR_X;
- break;
- case BPF_ALU|BPF_LSH|BPF_K:
- ftest->code = BPF_S_ALU_LSH_K;
- break;
- case BPF_ALU|BPF_LSH|BPF_X:
- ftest->code = BPF_S_ALU_LSH_X;
- break;
- case BPF_ALU|BPF_RSH|BPF_K:
- ftest->code = BPF_S_ALU_RSH_K;
- break;
- case BPF_ALU|BPF_RSH|BPF_X:
- ftest->code = BPF_S_ALU_RSH_X;
- break;
- case BPF_ALU|BPF_NEG:
- ftest->code = BPF_S_ALU_NEG;
- break;
- case BPF_LD|BPF_W|BPF_ABS:
- ftest->code = BPF_S_LD_W_ABS;
- break;
- case BPF_LD|BPF_H|BPF_ABS:
- ftest->code = BPF_S_LD_H_ABS;
- break;
- case BPF_LD|BPF_B|BPF_ABS:
- ftest->code = BPF_S_LD_B_ABS;
- break;
- case BPF_LD|BPF_W|BPF_LEN:
- ftest->code = BPF_S_LD_W_LEN;
- break;
- case BPF_LD|BPF_W|BPF_IND:
- ftest->code = BPF_S_LD_W_IND;
- break;
- case BPF_LD|BPF_H|BPF_IND:
- ftest->code = BPF_S_LD_H_IND;
- break;
- case BPF_LD|BPF_B|BPF_IND:
- ftest->code = BPF_S_LD_B_IND;
- break;
- case BPF_LD|BPF_IMM:
- ftest->code = BPF_S_LD_IMM;
- break;
- case BPF_LDX|BPF_W|BPF_LEN:
- ftest->code = BPF_S_LDX_W_LEN;
- break;
- case BPF_LDX|BPF_B|BPF_MSH:
- ftest->code = BPF_S_LDX_B_MSH;
- break;
- case BPF_LDX|BPF_IMM:
- ftest->code = BPF_S_LDX_IMM;
- break;
- case BPF_MISC|BPF_TAX:
- ftest->code = BPF_S_MISC_TAX;
- break;
- case BPF_MISC|BPF_TXA:
- ftest->code = BPF_S_MISC_TXA;
- break;
- case BPF_RET|BPF_K:
- ftest->code = BPF_S_RET_K;
- break;
- case BPF_RET|BPF_A:
- ftest->code = BPF_S_RET_A;
- break;
+ struct sock_filter *ftest = &filter[pc];
+ u16 code = ftest->code;
+ if (code >= ARRAY_SIZE(codes))
+ return -EINVAL;
+ code = codes[code];
+ /* Undo the '+ 1' in codes[] after validation. */
+ if (!code--)
+ return -EINVAL;
/* Some instructions need special checks */
-
+ switch (code) {
+ case BPF_S_ALU_DIV_K:
/* check for division by zero */
- case BPF_ALU|BPF_DIV|BPF_K:
if (ftest->k == 0)
return -EINVAL;
- ftest->code = BPF_S_ALU_DIV_K;
break;
-
- /* check for invalid memory addresses */
- case BPF_LD|BPF_MEM:
- if (ftest->k >= BPF_MEMWORDS)
- return -EINVAL;
- ftest->code = BPF_S_LD_MEM;
- break;
- case BPF_LDX|BPF_MEM:
- if (ftest->k >= BPF_MEMWORDS)
- return -EINVAL;
- ftest->code = BPF_S_LDX_MEM;
- break;
- case BPF_ST:
- if (ftest->k >= BPF_MEMWORDS)
- return -EINVAL;
- ftest->code = BPF_S_ST;
- break;
- case BPF_STX:
+ case BPF_S_LD_MEM:
+ case BPF_S_LDX_MEM:
+ case BPF_S_ST:
+ case BPF_S_STX:
+ /* check for invalid memory addresses */
if (ftest->k >= BPF_MEMWORDS)
return -EINVAL;
- ftest->code = BPF_S_STX;
break;
-
- case BPF_JMP|BPF_JA:
+ case BPF_S_JMP_JA:
/*
* Note, the large ftest->k might cause loops.
* Compare this with conditional jumps below,
@@ -528,40 +473,7 @@ int sk_chk_filter(struct sock_filter *filter, int flen)
*/
if (ftest->k >= (unsigned)(flen-pc-1))
return -EINVAL;
- ftest->code = BPF_S_JMP_JA;
- break;
-
- case BPF_JMP|BPF_JEQ|BPF_K:
- ftest->code = BPF_S_JMP_JEQ_K;
- break;
- case BPF_JMP|BPF_JEQ|BPF_X:
- ftest->code = BPF_S_JMP_JEQ_X;
break;
- case BPF_JMP|BPF_JGE|BPF_K:
- ftest->code = BPF_S_JMP_JGE_K;
- break;
- case BPF_JMP|BPF_JGE|BPF_X:
- ftest->code = BPF_S_JMP_JGE_X;
- break;
- case BPF_JMP|BPF_JGT|BPF_K:
- ftest->code = BPF_S_JMP_JGT_K;
- break;
- case BPF_JMP|BPF_JGT|BPF_X:
- ftest->code = BPF_S_JMP_JGT_X;
- break;
- case BPF_JMP|BPF_JSET|BPF_K:
- ftest->code = BPF_S_JMP_JSET_K;
- break;
- case BPF_JMP|BPF_JSET|BPF_X:
- ftest->code = BPF_S_JMP_JSET_X;
- break;
-
- default:
- return -EINVAL;
- }
-
- /* for conditionals both must be safe */
- switch (ftest->code) {
case BPF_S_JMP_JEQ_K:
case BPF_S_JMP_JEQ_X:
case BPF_S_JMP_JGE_K:
@@ -570,10 +482,13 @@ int sk_chk_filter(struct sock_filter *filter, int flen)
case BPF_S_JMP_JGT_X:
case BPF_S_JMP_JSET_X:
case BPF_S_JMP_JSET_K:
+ /* for conditionals both must be safe */
if (pc + ftest->jt + 1 >= flen ||
pc + ftest->jf + 1 >= flen)
return -EINVAL;
+ break;
}
+ ftest->code = code;
}
/* last instruction must be a RET code */
@@ -581,10 +496,8 @@ int sk_chk_filter(struct sock_filter *filter, int flen)
case BPF_S_RET_K:
case BPF_S_RET_A:
return 0;
- break;
- default:
- return -EINVAL;
- }
+ }
+ return -EINVAL;
}
EXPORT_SYMBOL(sk_chk_filter);
--
1.7.1
^ permalink raw reply related
* Re: Kernel rwlock design, Multicore and IGMP
From: Cypher Wu @ 2010-11-17 1:30 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Chris Metcalf, Américo Wang, linux-kernel, netdev
In-Reply-To: <1289820672.2607.10.camel@edumazet-laptop>
On Mon, Nov 15, 2010 at 7:31 PM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
> Le lundi 15 novembre 2010 à 19:18 +0800, Cypher Wu a écrit :
>> In that post I want to confirm another thing: if we join/leave on
>> different cores that every call will start the timer for IGMP message
>> using the same in_dev->mc_list, could that be optimized?
>>
>
> Which timer exactly ? Is it a real scalability problem ?
>
> I believe RTNL would be the blocking point actually...
>
>
>
>
struct in_device::mr_ifc_timer. Every time when a process join/leave a
MC group, igmp_ifc_event() -> igmp_ifc_start_timer() will start the
timer on the core that the system call issued, and
igmp_ifc_timer_expire() will be called on that core in the bottem halt
of timer interrupt.
If we call join/leave on mutlicores that timers will run on all these
cores, but it seems only one or two will generate IGMP message, others
will only lock the list and loop throught it with nothing generated.
--
Cyberman Wu
http://www.meganovo.com
^ permalink raw reply
* Re: [PATCH] 3c59x: fix build failure on !CONFIG_PCI
From: Namhyung Kim @ 2010-11-17 2:22 UTC (permalink / raw)
To: Randy Dunlap; +Cc: Steffen Klassert, netdev, linux-kernel
In-Reply-To: <20101116091408.abd36ec8.randy.dunlap@oracle.com>
2010-11-16 (화), 09:14 -0800, Randy Dunlap:
> Hi,
>
Hi, Randy
> Interesting patch. I have reported this build error and looked
> into fixing it, but did not come up with this solution.
>
> Looking at it more: if CONFIG_PCI is not enabled, DEVICE_PCI() is NULL.
> That makes VORTEX_PCI() (with or without your patch) have a value of NULL.
>
> Is the line with the reported syntax error (3211) executed in
> function acpi_set_WOL() ? If so, let's assume that vp->enable_wol is true.
> Then what happens on line 3211 (or 3213 after your patch)?
>
> if (VORTEX_PCI(vp)->current_state < PCI_D3hot)
> return;
>
> or if I am really confuzed this morning, please tell me how it works.
>
At first glance, I've noticed that the code above could make a NULL
dereference so I added NULL check prior to the line.
But after reading more code I realized that other pci-functions called
in acpi_set_WOL() would not work with NULL pci_dev pointer also. And I
found all callers of the acpi_set_WOL() already checked NULL pointer
before the call. Finally I could remove the NULL check and leave the
code as is. That's how it works. :)
Thanks.
--
Regards,
Namhyung Kim
^ permalink raw reply
* Re: [Bugme-new] [Bug 22962] New: building (e)glibc against 2.6.37-rc1 headers fails
From: David Miller @ 2010-11-17 2:33 UTC (permalink / raw)
To: akpm; +Cc: stephan, bugzilla-daemon, bugme-daemon, eric.dumazet, netdev
In-Reply-To: <20101116143349.2fbb6ed8.akpm@linux-foundation.org>
From: Andrew Morton <akpm@linux-foundation.org>
Date: Tue, 16 Nov 2010 14:33:49 -0800
> Maybe we need some __KERNEL__ guards in if.h.
Already fixed in net-2.6:
From 3b42a96dc7870c53d20b419185737d3b8f7a7b74 Mon Sep 17 00:00:00 2001
From: Andy Whitcroft <apw@canonical.com>
Date: Mon, 15 Nov 2010 06:01:59 +0000
Subject: [PATCH 1/3] net: rtnetlink.h -- only include linux/netdevice.h when used by the kernel
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The commit below added a new helper dev_ingress_queue to cleanly obtain the
ingress queue pointer. This necessitated including 'linux/netdevice.h':
commit 24824a09e35402b8d58dcc5be803a5ad3937bdba
Author: Eric Dumazet <eric.dumazet@gmail.com>
Date: Sat Oct 2 06:11:55 2010 +0000
net: dynamic ingress_queue allocation
However this include triggers issues for applications in userspace
which use the rtnetlink interfaces. Commonly this requires they include
'net/if.h' and 'linux/rtnetlink.h' leading to a compiler error as below:
In file included from /usr/include/linux/netdevice.h:28:0,
from /usr/include/linux/rtnetlink.h:9,
from t.c:2:
/usr/include/linux/if.h:135:8: error: redefinition of ‘struct ifmap’
/usr/include/net/if.h:112:8: note: originally defined here
/usr/include/linux/if.h:169:8: error: redefinition of ‘struct ifreq’
/usr/include/net/if.h:127:8: note: originally defined here
/usr/include/linux/if.h:218:8: error: redefinition of ‘struct ifconf’
/usr/include/net/if.h:177:8: note: originally defined here
The new helper is only defined for the kernel and protected by __KERNEL__
therefore we can simply pull the include down into the same protected
section.
Signed-off-by: Andy Whitcroft <apw@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/linux/rtnetlink.h | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index d42f2744..bbad657 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -6,7 +6,6 @@
#include <linux/if_link.h>
#include <linux/if_addr.h>
#include <linux/neighbour.h>
-#include <linux/netdevice.h>
/* rtnetlink families. Values up to 127 are reserved for real address
* families, values above 128 may be used arbitrarily.
@@ -606,6 +605,7 @@ struct tcamsg {
#ifdef __KERNEL__
#include <linux/mutex.h>
+#include <linux/netdevice.h>
static __inline__ int rtattr_strcmp(const struct rtattr *rta, const char *str)
{
--
1.7.3.2
^ permalink raw reply related
* Re: [PATCH net-next-2.6 v4] can: Topcliff: PCH_CAN driver: Add Flow control/Fix Endianess issue/Separate IF register/Enumerate LEC macro/Move MSI processing/Use BIT(X)/Change Message Object index/Add prefix PCH_
From: Tomoya MORINAGA @ 2010-11-17 3:00 UTC (permalink / raw)
To: w.sang-bIcnvbaLZ9MEGnE8C9+IrQ, David Miller,
wg-5Yr1BZd7O62+XT7JhA+gdA
Cc: andrew.chih.howe.khor-ral2JQCrhuEAvxtiuMwx3w,
sameo-VuQAYsv1563Yd54FQh9/CA,
margie.foster-ral2JQCrhuEAvxtiuMwx3w,
netdev-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
yong.y.wang-ral2JQCrhuEAvxtiuMwx3w,
socketcan-core-0fE9KPoRgkgATYTw5x5z8w,
kok.howg.ewe-ral2JQCrhuEAvxtiuMwx3w, chripell-VaTbYqLCNhc,
joel.clark-ral2JQCrhuEAvxtiuMwx3w, qi.wang-ral2JQCrhuEAvxtiuMwx3w
In-Reply-To: <20101116.131008.212663108.davem@davemloft.net>
Hi David Miller,
I see, I just have to obey your saying.
I will split our patch per issue/indicated item and re-submit to you.
Thanks,
Tomoya MORINAGA
OKI SEMICONDUCTOR CO., LTD.
----- Original Message -----
From: "David Miller" <davem-fT/PcQaiUtIeIZ0/mPfg9Q@public.gmane.org>
To: <w.sang-bIcnvbaLZ9MEGnE8C9+IrQ@public.gmane.org>
Cc: <wg-5Yr1BZd7O62+XT7JhA+gdA@public.gmane.org>; <tomoya-linux-ECg8zkTtlr0C6LszWs/t0g@public.gmane.org>; <andrew.chih.howe.khor-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>; <masa-korg-ECg8zkTtlr0C6LszWs/t0g@public.gmane.org>;
<sameo-VuQAYsv1563Yd54FQh9/CA@public.gmane.org>; <margie.foster-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>; <netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>; <linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>;
<socketcan-core-0fE9KPoRgkgATYTw5x5z8w@public.gmane.org>; <kok.howg.ewe-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>; <joel.clark-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>; <yong.y.wang-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>;
<chripell-VaTbYqLCNhc@public.gmane.org>; <qi.wang-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Sent: Wednesday, November 17, 2010 6:10 AM
Subject: Re: [PATCH net-next-2.6 v4] can: Topcliff: PCH_CAN driver: Add Flow control/Fix Endianess issue/Separate IF
register/Enumerate LEC macro/Move MSI processing/Use BIT(X)/Change Message Object index/Add prefix PCH_
> From: Wolfram Sang <w.sang-bIcnvbaLZ9MEGnE8C9+IrQ@public.gmane.org>
> Date: Tue, 16 Nov 2010 22:07:16 +0100
>
> > On Tue, Nov 16, 2010 at 12:43:25PM -0800, David Miller wrote:
> >> From: Wolfgang Grandegger <wg-5Yr1BZd7O62+XT7JhA+gdA@public.gmane.org>
> >> Date: Tue, 16 Nov 2010 21:39:47 +0100
> >>
> >> > Please take into account that this patch got accepted by accident
> >> > (because the maintainer did not respond properly in time). At that time
> >> > the driver was incomplete, not ready for mainline and did not even work
> >> > properly. Therefore it makes little sense to debug or even bisec these
> >> > changes. Just for that reason I made an exemption and added my
> >> > "Acked-by". Hope you can share my arguments.
> >>
> >> You don't put stupid on top of stupid and justify the latter using
> >> the former.
> >
> > Is reverting the incomplete driver an option?
>
> I told everyone that the plan was that we had several months
> to fix this, and that's what we should do.
>
> But yes if people are going to be maximally difficult about this and
> refuse to split up the bug fixes, I will have to regrettably revert
> the driver.
>
> But let's avoid that if we can.
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
>
^ permalink raw reply
* Re: [PATCH net-next-2.6] vlan: remove ndo_select_queue() logic
From: John Fastabend @ 2010-11-17 4:12 UTC (permalink / raw)
To: Eric Dumazet
Cc: David Miller, jesse@nicira.com, netdev@vger.kernel.org,
kaber@trash.net
In-Reply-To: <1289937251.2732.4.camel@edumazet-laptop>
On 11/16/2010 11:54 AM, Eric Dumazet wrote:
> Le mardi 16 novembre 2010 à 11:24 -0800, David Miller a écrit :
>> From: Eric Dumazet <eric.dumazet@gmail.com>
>> Date: Thu, 11 Nov 2010 20:42:45 +0100
>>
>>> [PATCH] vlan: remove ndo_select_queue() logic
>>>
>>> Now vlan are lockless, we dont need special ndo_select_queue() logic.
>>> dev_pick_tx() will do the multiqueue stuff on the real device transmit.
>>>
>>> Suggested-by: Jesse Gross <jesse@nicira.com>
>>> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
>>
>> Also applied, but again there were conflicts I had to resolve,
>> please check that I got it right.
>>
>
> Both patches seem fine to me.
>
> I am going to test them.
>
> Thanks !
>
>
Everything seems in order as far as I can tell. I've had io running over 50 VLANs for a few hours now.
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: Kernel rwlock design, Multicore and IGMP
From: Eric Dumazet @ 2010-11-17 4:43 UTC (permalink / raw)
To: Cypher Wu; +Cc: Chris Metcalf, Américo Wang, linux-kernel, netdev
In-Reply-To: <AANLkTimA3mnPQHYWVb_fzONXMz40WGTaWpf83uZTsYQ2@mail.gmail.com>
Le mercredi 17 novembre 2010 à 09:30 +0800, Cypher Wu a écrit :
> O
> struct in_device::mr_ifc_timer. Every time when a process join/leave a
> MC group, igmp_ifc_event() -> igmp_ifc_start_timer() will start the
> timer on the core that the system call issued, and
> igmp_ifc_timer_expire() will be called on that core in the bottem halt
> of timer interrupt.
> If we call join/leave on mutlicores that timers will run on all these
> cores, but it seems only one or two will generate IGMP message, others
> will only lock the list and loop throught it with nothing generated.
>
>
Problem would not be timer being restarted on different cores (very
small impact), but scanning a list in igmpv3_send_cr() with many items
in it and expensive things, under timer handler (softirq), so adding
spikes of latency.
IGMP_Unsolicited_Report_Interval is 10 seconds, so we start timer in a 5
second average.
I am not sure there is a need to join/leave thousand of groups per
second anyway...
^ permalink raw reply
* [net-next pull-request] Intel Wired LAN Driver Updates
From: Jeff Kirsher @ 2010-11-17 4:59 UTC (permalink / raw)
To: David Miller; +Cc: netdev@vger.kernel.org
Here is a batch of fixes/cleanups intended for 2.6.38. In the mix is added
support for x540 10GbE MAC. A large part of the changes are ixgbe cleanup
patches by Alex.
Please let me know if there are problems.
Cheers,
Jeff
The following changes since commit b178bb3dfc30d9555bdd2401e95af98e23e83e10:
net: reorder struct sock fields
are available in the git repository at:
master.kernel.org:/pub/scm/linux/kernel/git/jkirsher/net-next-2.6.git master
Alexander Duyck (29):
ixgbe: remove unnecessary re-init of adapter on Rx-csum change
ixgbe: move GSO segments and byte count processing into ixgbe_tx_map
ixgbe: cleanup ixgbe_alloc_rx_buffers
ixgbe: drop ring->head, make ring->tail a pointer instead of offset
ixgbe: move device pointer into the ring structure
ixgbe: combine some stats into a union to allow for Tx/Rx stats
overlap
ixgbe: add a netdev pointer to the ring structure
ixgbe: move ixgbe_clear_interrupt_scheme to before pci_save_state
ixgbe: remove residual code left over from earlier combining of
TXDCTL
ixgbe: move adapter into pci_dev driver data instead of netdev
ixgbe: move CPU variable from ring into q_vector, add ring->q_vector
ixgbe: add a state flags to ring
ixgbe: cleanup race conditions in link setup
ixgbe: Disable RSC when ITR setting is too high to allow RSC
ixgbe: reorder Tx cleanup so that if adapter will reset we don't
rearm
ixgbe: change vector numbering so that queues end up on correct CPUs
ixgbe: cleanup ixgbe_clean_rx_irq
ixgbe: cleanup ATR filter setup function
ixgbe: cleanup use of ixgbe_rsc_count and RSC_CB
ixgbe: change mac_type if statements to switch statements
ixgbe: cleanup ixgbe_set_tx_csum ethtool flags configuration
ixgbe: add WOL support for backplane adapters
ixgbe: Cleanup DCB logic, whitespace, and comments in ixgbe_ethtool.c
ixgbe: cleanup unnecessary return value in ixgbe_cache_ring_rss
ixgbe: cleanup unclear references to reg_idx
ixgbe: simplify math and improve stack use of ixgbe_set_itr functions
ixgbe: cleanup ixgbe_map_rings_to_vectors
ixgbe: populate the ring->q_vector pointer during ring mapping
ixgbe: Resolve null function pointer accesses on 82598 w/ multi-speed
fiber
Bruce Allan (2):
e1000e: 82571 SerDes link handle null code word from partner
e1000e: 82574 intermittently fails to initialize with manageability
f/w
Don Skidmore (3):
ixgbe: make silicon specific functions generic
ixgbe: add MAC and PHY support for x540
ixgbe: add support for x540 MAC
Dongdong Deng (1):
e1000e: add netpoll support for MSI/MSI-X IRQ modes
Eric Dumazet (2):
ixgbe: delay rx_ring freeing
ixgbe: refactor ixgbe_alloc_queues()
Greg Rose (4):
ixgbevf: Update Version String and Copyright Notice
ixgbevf: Fix Oops
igbvf: Update version and Copyright
Remove extra struct page member from the buffer info structure
John Fastabend (3):
ixgbe: DCB set PFC high and low water marks per data sheet specs
ixgbe: DCB: credit max only needs to be gt TSO size for 82598
ixgbe: rework Tx hang detection to fix reoccurring false Tx hangs
Julian Stecklina (1):
igbvf: Remove some dead code in igbvf
Yi Zou (3):
ixgbe: avoid doing FCoE DDP when adapter is DOWN or RESETTING
ixgbe: invalidate FCoE DDP context when no error status is available
ixgbe: make sure FCoE DDP user buffers are really released by the HW
drivers/net/e1000e/82571.c | 143 +++-
drivers/net/e1000e/defines.h | 1 +
drivers/net/e1000e/netdev.c | 49 +-
drivers/net/igbvf/Makefile | 2 +-
drivers/net/igbvf/defines.h | 2 +-
drivers/net/igbvf/ethtool.c | 2 +-
drivers/net/igbvf/igbvf.h | 3 +-
drivers/net/igbvf/mbx.c | 2 +-
drivers/net/igbvf/mbx.h | 2 +-
drivers/net/igbvf/netdev.c | 11 +-
drivers/net/igbvf/regs.h | 2 +-
drivers/net/igbvf/vf.c | 2 +-
drivers/net/igbvf/vf.h | 2 +-
drivers/net/ixgbe/Makefile | 2 +-
drivers/net/ixgbe/ixgbe.h | 122 ++-
drivers/net/ixgbe/ixgbe_82598.c | 58 +-
drivers/net/ixgbe/ixgbe_82599.c | 94 +--
drivers/net/ixgbe/ixgbe_common.c | 98 ++-
drivers/net/ixgbe/ixgbe_common.h | 5 +-
drivers/net/ixgbe/ixgbe_dcb.c | 17 +-
drivers/net/ixgbe/ixgbe_dcb.h | 3 +-
drivers/net/ixgbe/ixgbe_dcb_82598.c | 12 +-
drivers/net/ixgbe/ixgbe_dcb_82599.c | 12 +-
drivers/net/ixgbe/ixgbe_dcb_nl.c | 55 +-
drivers/net/ixgbe/ixgbe_ethtool.c | 255 +++--
drivers/net/ixgbe/ixgbe_fcoe.c | 15 +-
drivers/net/ixgbe/ixgbe_main.c | 1991 ++++++++++++++++++++---------------
drivers/net/ixgbe/ixgbe_mbx.c | 40 +-
drivers/net/ixgbe/ixgbe_mbx.h | 2 +-
drivers/net/ixgbe/ixgbe_phy.c | 52 +
drivers/net/ixgbe/ixgbe_phy.h | 5 +
drivers/net/ixgbe/ixgbe_sriov.c | 3 +-
drivers/net/ixgbe/ixgbe_type.h | 20 +
drivers/net/ixgbe/ixgbe_x540.c | 722 +++++++++++++
drivers/net/ixgbevf/Makefile | 2 +-
drivers/net/ixgbevf/defines.h | 2 +-
drivers/net/ixgbevf/ixgbevf.h | 2 +-
drivers/net/ixgbevf/ixgbevf_main.c | 13 +-
drivers/net/ixgbevf/mbx.c | 2 +-
drivers/net/ixgbevf/mbx.h | 2 +-
drivers/net/ixgbevf/regs.h | 2 +-
drivers/net/ixgbevf/vf.c | 2 +-
drivers/net/ixgbevf/vf.h | 2 +-
43 files changed, 2571 insertions(+), 1264 deletions(-)
create mode 100644 drivers/net/ixgbe/ixgbe_x540.c
diff --git a/drivers/net/e1000e/82571.c b/drivers/net/e1000e/82571.c
index 7236f1a..9333921 100644
--- a/drivers/net/e1000e/82571.c
+++ b/drivers/net/e1000e/82571.c
@@ -74,6 +74,9 @@ static bool e1000_check_mng_mode_82574(struct e1000_hw *hw);
static s32 e1000_led_on_82574(struct e1000_hw *hw);
static void e1000_put_hw_semaphore_82571(struct e1000_hw *hw);
static void e1000_power_down_phy_copper_82571(struct e1000_hw *hw);
+static void e1000_put_hw_semaphore_82573(struct e1000_hw *hw);
+static s32 e1000_get_hw_semaphore_82574(struct e1000_hw *hw);
+static void e1000_put_hw_semaphore_82574(struct e1000_hw *hw);
/**
* e1000_init_phy_params_82571 - Init PHY func ptrs.
@@ -107,6 +110,8 @@ static s32 e1000_init_phy_params_82571(struct e1000_hw *hw)
case e1000_82574:
case e1000_82583:
phy->type = e1000_phy_bm;
+ phy->ops.acquire = e1000_get_hw_semaphore_82574;
+ phy->ops.release = e1000_put_hw_semaphore_82574;
break;
default:
return -E1000_ERR_PHY;
@@ -200,6 +205,17 @@ static s32 e1000_init_nvm_params_82571(struct e1000_hw *hw)
break;
}
+ /* Function Pointers */
+ switch (hw->mac.type) {
+ case e1000_82574:
+ case e1000_82583:
+ nvm->ops.acquire = e1000_get_hw_semaphore_82574;
+ nvm->ops.release = e1000_put_hw_semaphore_82574;
+ break;
+ default:
+ break;
+ }
+
return 0;
}
@@ -542,6 +558,94 @@ static void e1000_put_hw_semaphore_82571(struct e1000_hw *hw)
swsm &= ~(E1000_SWSM_SMBI | E1000_SWSM_SWESMBI);
ew32(SWSM, swsm);
}
+/**
+ * e1000_get_hw_semaphore_82573 - Acquire hardware semaphore
+ * @hw: pointer to the HW structure
+ *
+ * Acquire the HW semaphore during reset.
+ *
+ **/
+static s32 e1000_get_hw_semaphore_82573(struct e1000_hw *hw)
+{
+ u32 extcnf_ctrl;
+ s32 ret_val = 0;
+ s32 i = 0;
+
+ extcnf_ctrl = er32(EXTCNF_CTRL);
+ extcnf_ctrl |= E1000_EXTCNF_CTRL_MDIO_SW_OWNERSHIP;
+ do {
+ ew32(EXTCNF_CTRL, extcnf_ctrl);
+ extcnf_ctrl = er32(EXTCNF_CTRL);
+
+ if (extcnf_ctrl & E1000_EXTCNF_CTRL_MDIO_SW_OWNERSHIP)
+ break;
+
+ extcnf_ctrl |= E1000_EXTCNF_CTRL_MDIO_SW_OWNERSHIP;
+
+ msleep(2);
+ i++;
+ } while (i < MDIO_OWNERSHIP_TIMEOUT);
+
+ if (i == MDIO_OWNERSHIP_TIMEOUT) {
+ /* Release semaphores */
+ e1000_put_hw_semaphore_82573(hw);
+ e_dbg("Driver can't access the PHY\n");
+ ret_val = -E1000_ERR_PHY;
+ goto out;
+ }
+
+out:
+ return ret_val;
+}
+
+/**
+ * e1000_put_hw_semaphore_82573 - Release hardware semaphore
+ * @hw: pointer to the HW structure
+ *
+ * Release hardware semaphore used during reset.
+ *
+ **/
+static void e1000_put_hw_semaphore_82573(struct e1000_hw *hw)
+{
+ u32 extcnf_ctrl;
+
+ extcnf_ctrl = er32(EXTCNF_CTRL);
+ extcnf_ctrl &= ~E1000_EXTCNF_CTRL_MDIO_SW_OWNERSHIP;
+ ew32(EXTCNF_CTRL, extcnf_ctrl);
+}
+
+static DEFINE_MUTEX(swflag_mutex);
+
+/**
+ * e1000_get_hw_semaphore_82574 - Acquire hardware semaphore
+ * @hw: pointer to the HW structure
+ *
+ * Acquire the HW semaphore to access the PHY or NVM.
+ *
+ **/
+static s32 e1000_get_hw_semaphore_82574(struct e1000_hw *hw)
+{
+ s32 ret_val;
+
+ mutex_lock(&swflag_mutex);
+ ret_val = e1000_get_hw_semaphore_82573(hw);
+ if (ret_val)
+ mutex_unlock(&swflag_mutex);
+ return ret_val;
+}
+
+/**
+ * e1000_put_hw_semaphore_82574 - Release hardware semaphore
+ * @hw: pointer to the HW structure
+ *
+ * Release hardware semaphore used to access the PHY or NVM
+ *
+ **/
+static void e1000_put_hw_semaphore_82574(struct e1000_hw *hw)
+{
+ e1000_put_hw_semaphore_82573(hw);
+ mutex_unlock(&swflag_mutex);
+}
/**
* e1000_acquire_nvm_82571 - Request for access to the EEPROM
@@ -562,8 +666,6 @@ static s32 e1000_acquire_nvm_82571(struct e1000_hw *hw)
switch (hw->mac.type) {
case e1000_82573:
- case e1000_82574:
- case e1000_82583:
break;
default:
ret_val = e1000e_acquire_nvm(hw);
@@ -853,9 +955,8 @@ static s32 e1000_set_d0_lplu_state_82571(struct e1000_hw *hw, bool active)
**/
static s32 e1000_reset_hw_82571(struct e1000_hw *hw)
{
- u32 ctrl, extcnf_ctrl, ctrl_ext, icr;
+ u32 ctrl, ctrl_ext, icr;
s32 ret_val;
- u16 i = 0;
/*
* Prevent the PCI-E bus from sticking if there is no TLP connection
@@ -880,33 +981,33 @@ static s32 e1000_reset_hw_82571(struct e1000_hw *hw)
*/
switch (hw->mac.type) {
case e1000_82573:
+ ret_val = e1000_get_hw_semaphore_82573(hw);
+ break;
case e1000_82574:
case e1000_82583:
- extcnf_ctrl = er32(EXTCNF_CTRL);
- extcnf_ctrl |= E1000_EXTCNF_CTRL_MDIO_SW_OWNERSHIP;
-
- do {
- ew32(EXTCNF_CTRL, extcnf_ctrl);
- extcnf_ctrl = er32(EXTCNF_CTRL);
-
- if (extcnf_ctrl & E1000_EXTCNF_CTRL_MDIO_SW_OWNERSHIP)
- break;
-
- extcnf_ctrl |= E1000_EXTCNF_CTRL_MDIO_SW_OWNERSHIP;
-
- msleep(2);
- i++;
- } while (i < MDIO_OWNERSHIP_TIMEOUT);
+ ret_val = e1000_get_hw_semaphore_82574(hw);
break;
default:
break;
}
+ if (ret_val)
+ e_dbg("Cannot acquire MDIO ownership\n");
ctrl = er32(CTRL);
e_dbg("Issuing a global reset to MAC\n");
ew32(CTRL, ctrl | E1000_CTRL_RST);
+ /* Must release MDIO ownership and mutex after MAC reset. */
+ switch (hw->mac.type) {
+ case e1000_82574:
+ case e1000_82583:
+ e1000_put_hw_semaphore_82574(hw);
+ break;
+ default:
+ break;
+ }
+
if (hw->nvm.type == e1000_nvm_flash_hw) {
udelay(10);
ctrl_ext = er32(CTRL_EXT);
@@ -1431,8 +1532,10 @@ static s32 e1000_check_for_serdes_link_82571(struct e1000_hw *hw)
* auto-negotiation in the TXCW register and disable
* forced link in the Device Control register in an
* attempt to auto-negotiate with our link partner.
+ * If the partner code word is null, stop forcing
+ * and restart auto negotiation.
*/
- if (rxcw & E1000_RXCW_C) {
+ if ((rxcw & E1000_RXCW_C) || !(rxcw & E1000_RXCW_CW)) {
/* Enable autoneg, and unforce link up */
ew32(TXCW, mac->txcw);
ew32(CTRL, (ctrl & ~E1000_CTRL_SLU));
diff --git a/drivers/net/e1000e/defines.h b/drivers/net/e1000e/defines.h
index d3f7a9c..016ea38 100644
--- a/drivers/net/e1000e/defines.h
+++ b/drivers/net/e1000e/defines.h
@@ -516,6 +516,7 @@
#define E1000_TXCW_ANE 0x80000000 /* Auto-neg enable */
/* Receive Configuration Word */
+#define E1000_RXCW_CW 0x0000ffff /* RxConfigWord mask */
#define E1000_RXCW_IV 0x08000000 /* Receive config invalid */
#define E1000_RXCW_C 0x20000000 /* Receive config */
#define E1000_RXCW_SYNCH 0x40000000 /* Receive config synch */
diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c
index a6d54e4..9b3f0a9 100644
--- a/drivers/net/e1000e/netdev.c
+++ b/drivers/net/e1000e/netdev.c
@@ -5465,6 +5465,36 @@ static void e1000_shutdown(struct pci_dev *pdev)
}
#ifdef CONFIG_NET_POLL_CONTROLLER
+
+static irqreturn_t e1000_intr_msix(int irq, void *data)
+{
+ struct net_device *netdev = data;
+ struct e1000_adapter *adapter = netdev_priv(netdev);
+ int vector, msix_irq;
+
+ if (adapter->msix_entries) {
+ vector = 0;
+ msix_irq = adapter->msix_entries[vector].vector;
+ disable_irq(msix_irq);
+ e1000_intr_msix_rx(msix_irq, netdev);
+ enable_irq(msix_irq);
+
+ vector++;
+ msix_irq = adapter->msix_entries[vector].vector;
+ disable_irq(msix_irq);
+ e1000_intr_msix_tx(msix_irq, netdev);
+ enable_irq(msix_irq);
+
+ vector++;
+ msix_irq = adapter->msix_entries[vector].vector;
+ disable_irq(msix_irq);
+ e1000_msix_other(msix_irq, netdev);
+ enable_irq(msix_irq);
+ }
+
+ return IRQ_HANDLED;
+}
+
/*
* Polling 'interrupt' - used by things like netconsole to send skbs
* without having to re-enable interrupts. It's not called while
@@ -5474,10 +5504,21 @@ static void e1000_netpoll(struct net_device *netdev)
{
struct e1000_adapter *adapter = netdev_priv(netdev);
- disable_irq(adapter->pdev->irq);
- e1000_intr(adapter->pdev->irq, netdev);
-
- enable_irq(adapter->pdev->irq);
+ switch (adapter->int_mode) {
+ case E1000E_INT_MODE_MSIX:
+ e1000_intr_msix(adapter->pdev->irq, netdev);
+ break;
+ case E1000E_INT_MODE_MSI:
+ disable_irq(adapter->pdev->irq);
+ e1000_intr_msi(adapter->pdev->irq, netdev);
+ enable_irq(adapter->pdev->irq);
+ break;
+ default: /* E1000E_INT_MODE_LEGACY */
+ disable_irq(adapter->pdev->irq);
+ e1000_intr(adapter->pdev->irq, netdev);
+ enable_irq(adapter->pdev->irq);
+ break;
+ }
}
#endif
diff --git a/drivers/net/igbvf/Makefile b/drivers/net/igbvf/Makefile
index c2f150d..0fa3db3 100644
--- a/drivers/net/igbvf/Makefile
+++ b/drivers/net/igbvf/Makefile
@@ -1,7 +1,7 @@
################################################################################
#
# Intel(R) 82576 Virtual Function Linux driver
-# Copyright(c) 2009 Intel Corporation.
+# Copyright(c) 2009 - 2010 Intel Corporation.
#
# This program is free software; you can redistribute it and/or modify it
# under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/igbvf/defines.h b/drivers/net/igbvf/defines.h
index 88a4753..79f2604 100644
--- a/drivers/net/igbvf/defines.h
+++ b/drivers/net/igbvf/defines.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) 82576 Virtual Function Linux driver
- Copyright(c) 1999 - 2009 Intel Corporation.
+ Copyright(c) 1999 - 2010 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/igbvf/ethtool.c b/drivers/net/igbvf/ethtool.c
index 33add70..abb3606 100644
--- a/drivers/net/igbvf/ethtool.c
+++ b/drivers/net/igbvf/ethtool.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) 82576 Virtual Function Linux driver
- Copyright(c) 2009 Intel Corporation.
+ Copyright(c) 2009 - 2010 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/igbvf/igbvf.h b/drivers/net/igbvf/igbvf.h
index debeee2..9d4d63e 100644
--- a/drivers/net/igbvf/igbvf.h
+++ b/drivers/net/igbvf/igbvf.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) 82576 Virtual Function Linux driver
- Copyright(c) 2009 Intel Corporation.
+ Copyright(c) 2009 - 2010 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -126,7 +126,6 @@ struct igbvf_buffer {
unsigned int page_offset;
};
};
- struct page *page;
};
union igbvf_desc {
diff --git a/drivers/net/igbvf/mbx.c b/drivers/net/igbvf/mbx.c
index 819a8ec..3d6f4cc 100644
--- a/drivers/net/igbvf/mbx.c
+++ b/drivers/net/igbvf/mbx.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) 82576 Virtual Function Linux driver
- Copyright(c) 2009 Intel Corporation.
+ Copyright(c) 2009 - 2010 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/igbvf/mbx.h b/drivers/net/igbvf/mbx.h
index 4938609..c2883c4 100644
--- a/drivers/net/igbvf/mbx.h
+++ b/drivers/net/igbvf/mbx.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) 82576 Virtual Function Linux driver
- Copyright(c) 1999 - 2009 Intel Corporation.
+ Copyright(c) 1999 - 2010 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/igbvf/netdev.c b/drivers/net/igbvf/netdev.c
index 28af019..4c998b7 100644
--- a/drivers/net/igbvf/netdev.c
+++ b/drivers/net/igbvf/netdev.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) 82576 Virtual Function Linux driver
- Copyright(c) 2009 Intel Corporation.
+ Copyright(c) 2009 - 2010 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -44,12 +44,13 @@
#include "igbvf.h"
-#define DRV_VERSION "1.0.0-k0"
+#define DRV_VERSION "1.0.8-k0"
char igbvf_driver_name[] = "igbvf";
const char igbvf_driver_version[] = DRV_VERSION;
static const char igbvf_driver_string[] =
"Intel(R) Virtual Function Network Driver";
-static const char igbvf_copyright[] = "Copyright (c) 2009 Intel Corporation.";
+static const char igbvf_copyright[] =
+ "Copyright (c) 2009 - 2010 Intel Corporation.";
static int igbvf_poll(struct napi_struct *napi, int budget);
static void igbvf_reset(struct igbvf_adapter *);
@@ -1851,8 +1852,6 @@ static void igbvf_watchdog_task(struct work_struct *work)
if (link) {
if (!netif_carrier_ok(netdev)) {
- bool txb2b = 1;
-
mac->ops.get_link_up_info(&adapter->hw,
&adapter->link_speed,
&adapter->link_duplex);
@@ -1862,11 +1861,9 @@ static void igbvf_watchdog_task(struct work_struct *work)
adapter->tx_timeout_factor = 1;
switch (adapter->link_speed) {
case SPEED_10:
- txb2b = 0;
adapter->tx_timeout_factor = 16;
break;
case SPEED_100:
- txb2b = 0;
/* maybe add some timeout factor ? */
break;
}
diff --git a/drivers/net/igbvf/regs.h b/drivers/net/igbvf/regs.h
index b9e24ed..77e18d3 100644
--- a/drivers/net/igbvf/regs.h
+++ b/drivers/net/igbvf/regs.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) 82576 Virtual Function Linux driver
- Copyright(c) 2009 Intel Corporation.
+ Copyright(c) 2009 - 2010 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/igbvf/vf.c b/drivers/net/igbvf/vf.c
index a9a61ef..0cc13c6 100644
--- a/drivers/net/igbvf/vf.c
+++ b/drivers/net/igbvf/vf.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) 82576 Virtual Function Linux driver
- Copyright(c) 2009 Intel Corporation.
+ Copyright(c) 2009 - 2010 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/igbvf/vf.h b/drivers/net/igbvf/vf.h
index 1e8ce37..c36ea21 100644
--- a/drivers/net/igbvf/vf.h
+++ b/drivers/net/igbvf/vf.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel(R) 82576 Virtual Function Linux driver
- Copyright(c) 2009 Intel Corporation.
+ Copyright(c) 2009 - 2010 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ixgbe/Makefile b/drivers/net/ixgbe/Makefile
index 8f81efb..7d7387f 100644
--- a/drivers/net/ixgbe/Makefile
+++ b/drivers/net/ixgbe/Makefile
@@ -34,7 +34,7 @@ obj-$(CONFIG_IXGBE) += ixgbe.o
ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \
ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \
- ixgbe_mbx.o
+ ixgbe_mbx.o ixgbe_x540.o
ixgbe-$(CONFIG_IXGBE_DCB) += ixgbe_dcb.o ixgbe_dcb_82598.o \
ixgbe_dcb_82599.o ixgbe_dcb_nl.o
diff --git a/drivers/net/ixgbe/ixgbe.h b/drivers/net/ixgbe/ixgbe.h
index ed8703c..3ae30b8 100644
--- a/drivers/net/ixgbe/ixgbe.h
+++ b/drivers/net/ixgbe/ixgbe.h
@@ -61,10 +61,8 @@
#define IXGBE_MIN_RXD 64
/* flow control */
-#define IXGBE_DEFAULT_FCRTL 0x10000
#define IXGBE_MIN_FCRTL 0x40
#define IXGBE_MAX_FCRTL 0x7FF80
-#define IXGBE_DEFAULT_FCRTH 0x20000
#define IXGBE_MIN_FCRTH 0x600
#define IXGBE_MAX_FCRTH 0x7FFF0
#define IXGBE_DEFAULT_FCPAUSE 0xFFFF
@@ -130,7 +128,9 @@ struct ixgbe_tx_buffer {
unsigned long time_stamp;
u16 length;
u16 next_to_watch;
- u16 mapped_as_page;
+ unsigned int bytecount;
+ u16 gso_segs;
+ u8 mapped_as_page;
};
struct ixgbe_rx_buffer {
@@ -146,12 +146,56 @@ struct ixgbe_queue_stats {
u64 bytes;
};
+struct ixgbe_tx_queue_stats {
+ u64 restart_queue;
+ u64 tx_busy;
+ u64 completed;
+ u64 tx_done_old;
+};
+
+struct ixgbe_rx_queue_stats {
+ u64 rsc_count;
+ u64 rsc_flush;
+ u64 non_eop_descs;
+ u64 alloc_rx_page_failed;
+ u64 alloc_rx_buff_failed;
+};
+
+enum ixbge_ring_state_t {
+ __IXGBE_TX_FDIR_INIT_DONE,
+ __IXGBE_TX_DETECT_HANG,
+ __IXGBE_HANG_CHECK_ARMED,
+ __IXGBE_RX_PS_ENABLED,
+ __IXGBE_RX_RSC_ENABLED,
+};
+
+#define ring_is_ps_enabled(ring) \
+ test_bit(__IXGBE_RX_PS_ENABLED, &(ring)->state)
+#define set_ring_ps_enabled(ring) \
+ set_bit(__IXGBE_RX_PS_ENABLED, &(ring)->state)
+#define clear_ring_ps_enabled(ring) \
+ clear_bit(__IXGBE_RX_PS_ENABLED, &(ring)->state)
+#define check_for_tx_hang(ring) \
+ test_bit(__IXGBE_TX_DETECT_HANG, &(ring)->state)
+#define set_check_for_tx_hang(ring) \
+ set_bit(__IXGBE_TX_DETECT_HANG, &(ring)->state)
+#define clear_check_for_tx_hang(ring) \
+ clear_bit(__IXGBE_TX_DETECT_HANG, &(ring)->state)
+#define ring_is_rsc_enabled(ring) \
+ test_bit(__IXGBE_RX_RSC_ENABLED, &(ring)->state)
+#define set_ring_rsc_enabled(ring) \
+ set_bit(__IXGBE_RX_RSC_ENABLED, &(ring)->state)
+#define clear_ring_rsc_enabled(ring) \
+ clear_bit(__IXGBE_RX_RSC_ENABLED, &(ring)->state)
struct ixgbe_ring {
void *desc; /* descriptor ring memory */
+ struct device *dev; /* device for DMA mapping */
+ struct net_device *netdev; /* netdev ring belongs to */
union {
struct ixgbe_tx_buffer *tx_buffer_info;
struct ixgbe_rx_buffer *rx_buffer_info;
};
+ unsigned long state;
u8 atr_sample_rate;
u8 atr_count;
u16 count; /* amount of descriptors */
@@ -160,38 +204,30 @@ struct ixgbe_ring {
u16 next_to_clean;
u8 queue_index; /* needed for multiqueue queue management */
-
-#define IXGBE_RING_RX_PS_ENABLED (u8)(1)
- u8 flags; /* per ring feature flags */
- u16 head;
- u16 tail;
-
- unsigned int total_bytes;
- unsigned int total_packets;
-
-#ifdef CONFIG_IXGBE_DCA
- /* cpu for tx queue */
- int cpu;
-#endif
-
- u16 work_limit; /* max work per interrupt */
- u16 reg_idx; /* holds the special value that gets
+ u8 reg_idx; /* holds the special value that gets
* the hardware register offset
* associated with this ring, which is
* different for DCB and RSS modes
*/
+ u16 work_limit; /* max work per interrupt */
+
+ u8 __iomem *tail;
+
+ unsigned int total_bytes;
+ unsigned int total_packets;
+
struct ixgbe_queue_stats stats;
struct u64_stats_sync syncp;
+ union {
+ struct ixgbe_tx_queue_stats tx_stats;
+ struct ixgbe_rx_queue_stats rx_stats;
+ };
int numa_node;
- unsigned long reinit_state;
- u64 rsc_count; /* stat for coalesced packets */
- u64 rsc_flush; /* stats for flushed packets */
- u32 restart_queue; /* track tx queue restarts */
- u32 non_eop_descs; /* track hardware descriptor chaining */
-
unsigned int size; /* length in bytes */
dma_addr_t dma; /* phys. address of descriptor ring */
+ struct rcu_head rcu;
+ struct ixgbe_q_vector *q_vector; /* back-pointer to host q_vector */
} ____cacheline_internodealigned_in_smp;
enum ixgbe_ring_f_enum {
@@ -237,6 +273,9 @@ struct ixgbe_q_vector {
unsigned int v_idx; /* index of q_vector within array, also used for
* finding the bit in EICR and friends that
* represents the vector for this ring */
+#ifdef CONFIG_IXGBE_DCA
+ int cpu; /* CPU for DCA */
+#endif
struct napi_struct napi;
DECLARE_BITMAP(rxr_idx, MAX_RX_QUEUES); /* Rx ring indices */
DECLARE_BITMAP(txr_idx, MAX_TX_QUEUES); /* Tx ring indices */
@@ -246,6 +285,7 @@ struct ixgbe_q_vector {
u8 rx_itr;
u32 eitr;
cpumask_var_t affinity_mask;
+ char name[IFNAMSIZ + 9];
};
/* Helper macros to switch between ints/sec and what the register uses.
@@ -294,7 +334,6 @@ struct ixgbe_adapter {
u16 bd_number;
struct work_struct reset_task;
struct ixgbe_q_vector *q_vector[MAX_MSIX_Q_VECTORS];
- char name[MAX_MSIX_COUNT][IFNAMSIZ + 9];
struct ixgbe_dcb_config dcb_cfg;
struct ixgbe_dcb_config temp_dcb_cfg;
u8 dcb_set_bitmap;
@@ -417,6 +456,7 @@ struct ixgbe_adapter {
int node;
struct work_struct check_overtemp_task;
u32 interrupt_event;
+ char lsc_int_name[IFNAMSIZ + 9];
/* SR-IOV */
DECLARE_BITMAP(active_vfs, IXGBE_MAX_VF_FUNCTIONS);
@@ -428,17 +468,25 @@ enum ixbge_state_t {
__IXGBE_TESTING,
__IXGBE_RESETTING,
__IXGBE_DOWN,
- __IXGBE_FDIR_INIT_DONE,
__IXGBE_SFP_MODULE_NOT_FOUND
};
+struct ixgbe_rsc_cb {
+ dma_addr_t dma;
+ u16 skb_cnt;
+ bool delay_unmap;
+};
+#define IXGBE_RSC_CB(skb) ((struct ixgbe_rsc_cb *)(skb)->cb)
+
enum ixgbe_boards {
board_82598,
board_82599,
+ board_X540,
};
extern struct ixgbe_info ixgbe_82598_info;
extern struct ixgbe_info ixgbe_82599_info;
+extern struct ixgbe_info ixgbe_X540_info;
#ifdef CONFIG_IXGBE_DCB
extern const struct dcbnl_rtnl_ops dcbnl_ops;
extern int ixgbe_copy_dcb_cfg(struct ixgbe_dcb_config *src_dcb_cfg,
@@ -454,26 +502,24 @@ extern void ixgbe_down(struct ixgbe_adapter *adapter);
extern void ixgbe_reinit_locked(struct ixgbe_adapter *adapter);
extern void ixgbe_reset(struct ixgbe_adapter *adapter);
extern void ixgbe_set_ethtool_ops(struct net_device *netdev);
-extern int ixgbe_setup_rx_resources(struct ixgbe_adapter *, struct ixgbe_ring *);
-extern int ixgbe_setup_tx_resources(struct ixgbe_adapter *, struct ixgbe_ring *);
-extern void ixgbe_free_rx_resources(struct ixgbe_adapter *, struct ixgbe_ring *);
-extern void ixgbe_free_tx_resources(struct ixgbe_adapter *, struct ixgbe_ring *);
+extern int ixgbe_setup_rx_resources(struct ixgbe_ring *);
+extern int ixgbe_setup_tx_resources(struct ixgbe_ring *);
+extern void ixgbe_free_rx_resources(struct ixgbe_ring *);
+extern void ixgbe_free_tx_resources(struct ixgbe_ring *);
extern void ixgbe_configure_rx_ring(struct ixgbe_adapter *,struct ixgbe_ring *);
extern void ixgbe_configure_tx_ring(struct ixgbe_adapter *,struct ixgbe_ring *);
extern void ixgbe_update_stats(struct ixgbe_adapter *adapter);
extern int ixgbe_init_interrupt_scheme(struct ixgbe_adapter *adapter);
extern void ixgbe_clear_interrupt_scheme(struct ixgbe_adapter *adapter);
extern netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *,
- struct net_device *,
struct ixgbe_adapter *,
struct ixgbe_ring *);
-extern void ixgbe_unmap_and_free_tx_resource(struct ixgbe_adapter *,
+extern void ixgbe_unmap_and_free_tx_resource(struct ixgbe_ring *,
struct ixgbe_tx_buffer *);
-extern void ixgbe_alloc_rx_buffers(struct ixgbe_adapter *adapter,
- struct ixgbe_ring *rx_ring,
- int cleaned_count);
+extern void ixgbe_alloc_rx_buffers(struct ixgbe_ring *, u16);
extern void ixgbe_write_eitr(struct ixgbe_q_vector *);
extern int ethtool_ioctl(struct ifreq *ifr);
+extern u8 ixgbe_dcb_txq_to_tc(struct ixgbe_adapter *adapter, u8 index);
extern s32 ixgbe_reinit_fdir_tables_82599(struct ixgbe_hw *hw);
extern s32 ixgbe_init_fdir_signature_82599(struct ixgbe_hw *hw, u32 pballoc);
extern s32 ixgbe_init_fdir_perfect_82599(struct ixgbe_hw *hw, u32 pballoc);
@@ -498,6 +544,10 @@ extern s32 ixgbe_atr_set_flex_byte_82599(struct ixgbe_atr_input *input,
u16 flex_byte);
extern s32 ixgbe_atr_set_l4type_82599(struct ixgbe_atr_input *input,
u8 l4type);
+extern void ixgbe_configure_rscctl(struct ixgbe_adapter *adapter,
+ struct ixgbe_ring *ring);
+extern void ixgbe_clear_rscctl(struct ixgbe_adapter *adapter,
+ struct ixgbe_ring *ring);
extern void ixgbe_set_rx_mode(struct net_device *netdev);
#ifdef IXGBE_FCOE
extern void ixgbe_configure_fcoe(struct ixgbe_adapter *adapter);
diff --git a/drivers/net/ixgbe/ixgbe_82598.c b/drivers/net/ixgbe/ixgbe_82598.c
index 9c02d60..d0f1d9d 100644
--- a/drivers/net/ixgbe/ixgbe_82598.c
+++ b/drivers/net/ixgbe/ixgbe_82598.c
@@ -38,9 +38,6 @@
#define IXGBE_82598_MC_TBL_SIZE 128
#define IXGBE_82598_VFT_TBL_SIZE 128
-static s32 ixgbe_get_copper_link_capabilities_82598(struct ixgbe_hw *hw,
- ixgbe_link_speed *speed,
- bool *autoneg);
static s32 ixgbe_setup_copper_link_82598(struct ixgbe_hw *hw,
ixgbe_link_speed speed,
bool autoneg,
@@ -156,7 +153,7 @@ static s32 ixgbe_init_phy_ops_82598(struct ixgbe_hw *hw)
if (mac->ops.get_media_type(hw) == ixgbe_media_type_copper) {
mac->ops.setup_link = &ixgbe_setup_copper_link_82598;
mac->ops.get_link_capabilities =
- &ixgbe_get_copper_link_capabilities_82598;
+ &ixgbe_get_copper_link_capabilities_generic;
}
switch (hw->phy.type) {
@@ -274,37 +271,6 @@ static s32 ixgbe_get_link_capabilities_82598(struct ixgbe_hw *hw,
}
/**
- * ixgbe_get_copper_link_capabilities_82598 - Determines link capabilities
- * @hw: pointer to hardware structure
- * @speed: pointer to link speed
- * @autoneg: boolean auto-negotiation value
- *
- * Determines the link capabilities by reading the AUTOC register.
- **/
-static s32 ixgbe_get_copper_link_capabilities_82598(struct ixgbe_hw *hw,
- ixgbe_link_speed *speed,
- bool *autoneg)
-{
- s32 status = IXGBE_ERR_LINK_SETUP;
- u16 speed_ability;
-
- *speed = 0;
- *autoneg = true;
-
- status = hw->phy.ops.read_reg(hw, MDIO_SPEED, MDIO_MMD_PMAPMD,
- &speed_ability);
-
- if (status == 0) {
- if (speed_ability & MDIO_SPEED_10G)
- *speed |= IXGBE_LINK_SPEED_10GB_FULL;
- if (speed_ability & MDIO_PMA_SPEED_1000)
- *speed |= IXGBE_LINK_SPEED_1GB_FULL;
- }
-
- return status;
-}
-
-/**
* ixgbe_get_media_type_82598 - Determines media type
* @hw: pointer to hardware structure
*
@@ -357,6 +323,7 @@ static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw, s32 packetbuf_num)
u32 fctrl_reg;
u32 rmcs_reg;
u32 reg;
+ u32 rx_pba_size;
u32 link_speed = 0;
bool link_up;
@@ -459,16 +426,18 @@ static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw, s32 packetbuf_num)
/* Set up and enable Rx high/low water mark thresholds, enable XON. */
if (hw->fc.current_mode & ixgbe_fc_tx_pause) {
- if (hw->fc.send_xon) {
- IXGBE_WRITE_REG(hw, IXGBE_FCRTL(packetbuf_num),
- (hw->fc.low_water | IXGBE_FCRTL_XONE));
- } else {
- IXGBE_WRITE_REG(hw, IXGBE_FCRTL(packetbuf_num),
- hw->fc.low_water);
- }
+ rx_pba_size = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(packetbuf_num));
+ rx_pba_size >>= IXGBE_RXPBSIZE_SHIFT;
+
+ reg = (rx_pba_size - hw->fc.low_water) << 6;
+ if (hw->fc.send_xon)
+ reg |= IXGBE_FCRTL_XONE;
+ IXGBE_WRITE_REG(hw, IXGBE_FCRTL(packetbuf_num), reg);
+
+ reg = (rx_pba_size - hw->fc.high_water) << 10;
+ reg |= IXGBE_FCRTH_FCEN;
- IXGBE_WRITE_REG(hw, IXGBE_FCRTH(packetbuf_num),
- (hw->fc.high_water | IXGBE_FCRTH_FCEN));
+ IXGBE_WRITE_REG(hw, IXGBE_FCRTH(packetbuf_num), reg);
}
/* Configure pause time (2 TCs per register) */
@@ -1222,6 +1191,7 @@ static struct ixgbe_mac_operations mac_ops_82598 = {
static struct ixgbe_eeprom_operations eeprom_ops_82598 = {
.init_params = &ixgbe_init_eeprom_params_generic,
.read = &ixgbe_read_eerd_generic,
+ .calc_checksum = &ixgbe_calc_eeprom_checksum_generic,
.validate_checksum = &ixgbe_validate_eeprom_checksum_generic,
.update_checksum = &ixgbe_update_eeprom_checksum_generic,
};
diff --git a/drivers/net/ixgbe/ixgbe_82599.c b/drivers/net/ixgbe/ixgbe_82599.c
index 0bd8fbb..e34643e 100644
--- a/drivers/net/ixgbe/ixgbe_82599.c
+++ b/drivers/net/ixgbe/ixgbe_82599.c
@@ -56,9 +56,6 @@ static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw,
ixgbe_link_speed speed,
bool autoneg,
bool autoneg_wait_to_complete);
-static s32 ixgbe_get_copper_link_capabilities_82599(struct ixgbe_hw *hw,
- ixgbe_link_speed *speed,
- bool *autoneg);
static s32 ixgbe_setup_copper_link_82599(struct ixgbe_hw *hw,
ixgbe_link_speed speed,
bool autoneg,
@@ -174,7 +171,7 @@ static s32 ixgbe_init_phy_ops_82599(struct ixgbe_hw *hw)
if (mac->ops.get_media_type(hw) == ixgbe_media_type_copper) {
mac->ops.setup_link = &ixgbe_setup_copper_link_82599;
mac->ops.get_link_capabilities =
- &ixgbe_get_copper_link_capabilities_82599;
+ &ixgbe_get_copper_link_capabilities_generic;
}
/* Set necessary function pointers based on phy type */
@@ -184,6 +181,10 @@ static s32 ixgbe_init_phy_ops_82599(struct ixgbe_hw *hw)
phy->ops.get_firmware_version =
&ixgbe_get_phy_firmware_version_tnx;
break;
+ case ixgbe_phy_aq:
+ phy->ops.get_firmware_version =
+ &ixgbe_get_phy_firmware_version_generic;
+ break;
default:
break;
}
@@ -290,37 +291,6 @@ out:
}
/**
- * ixgbe_get_copper_link_capabilities_82599 - Determines link capabilities
- * @hw: pointer to hardware structure
- * @speed: pointer to link speed
- * @autoneg: boolean auto-negotiation value
- *
- * Determines the link capabilities by reading the AUTOC register.
- **/
-static s32 ixgbe_get_copper_link_capabilities_82599(struct ixgbe_hw *hw,
- ixgbe_link_speed *speed,
- bool *autoneg)
-{
- s32 status = IXGBE_ERR_LINK_SETUP;
- u16 speed_ability;
-
- *speed = 0;
- *autoneg = true;
-
- status = hw->phy.ops.read_reg(hw, MDIO_SPEED, MDIO_MMD_PMAPMD,
- &speed_ability);
-
- if (status == 0) {
- if (speed_ability & MDIO_SPEED_10G)
- *speed |= IXGBE_LINK_SPEED_10GB_FULL;
- if (speed_ability & MDIO_PMA_SPEED_1000)
- *speed |= IXGBE_LINK_SPEED_1GB_FULL;
- }
-
- return status;
-}
-
-/**
* ixgbe_get_media_type_82599 - Get media type
* @hw: pointer to hardware structure
*
@@ -332,7 +302,8 @@ static enum ixgbe_media_type ixgbe_get_media_type_82599(struct ixgbe_hw *hw)
/* Detect if there is a copper PHY attached. */
if (hw->phy.type == ixgbe_phy_cu_unknown ||
- hw->phy.type == ixgbe_phy_tn) {
+ hw->phy.type == ixgbe_phy_tn ||
+ hw->phy.type == ixgbe_phy_aq) {
media_type = ixgbe_media_type_copper;
goto out;
}
@@ -1924,6 +1895,7 @@ static u32 ixgbe_get_supported_physical_layer_82599(struct ixgbe_hw *hw)
hw->phy.ops.identify(hw);
if (hw->phy.type == ixgbe_phy_tn ||
+ hw->phy.type == ixgbe_phy_aq ||
hw->phy.type == ixgbe_phy_cu_unknown) {
hw->phy.ops.read_reg(hw, MDIO_PMA_EXTABLE, MDIO_MMD_PMAPMD,
&ext_ability);
@@ -2125,51 +2097,6 @@ fw_version_out:
return status;
}
-/**
- * ixgbe_get_wwn_prefix_82599 - Get alternative WWNN/WWPN prefix from
- * the EEPROM
- * @hw: pointer to hardware structure
- * @wwnn_prefix: the alternative WWNN prefix
- * @wwpn_prefix: the alternative WWPN prefix
- *
- * This function will read the EEPROM from the alternative SAN MAC address
- * block to check the support for the alternative WWNN/WWPN prefix support.
- **/
-static s32 ixgbe_get_wwn_prefix_82599(struct ixgbe_hw *hw, u16 *wwnn_prefix,
- u16 *wwpn_prefix)
-{
- u16 offset, caps;
- u16 alt_san_mac_blk_offset;
-
- /* clear output first */
- *wwnn_prefix = 0xFFFF;
- *wwpn_prefix = 0xFFFF;
-
- /* check if alternative SAN MAC is supported */
- hw->eeprom.ops.read(hw, IXGBE_ALT_SAN_MAC_ADDR_BLK_PTR,
- &alt_san_mac_blk_offset);
-
- if ((alt_san_mac_blk_offset == 0) ||
- (alt_san_mac_blk_offset == 0xFFFF))
- goto wwn_prefix_out;
-
- /* check capability in alternative san mac address block */
- offset = alt_san_mac_blk_offset + IXGBE_ALT_SAN_MAC_ADDR_CAPS_OFFSET;
- hw->eeprom.ops.read(hw, offset, &caps);
- if (!(caps & IXGBE_ALT_SAN_MAC_ADDR_CAPS_ALTWWN))
- goto wwn_prefix_out;
-
- /* get the corresponding prefix for WWNN/WWPN */
- offset = alt_san_mac_blk_offset + IXGBE_ALT_SAN_MAC_ADDR_WWNN_OFFSET;
- hw->eeprom.ops.read(hw, offset, wwnn_prefix);
-
- offset = alt_san_mac_blk_offset + IXGBE_ALT_SAN_MAC_ADDR_WWPN_OFFSET;
- hw->eeprom.ops.read(hw, offset, wwpn_prefix);
-
-wwn_prefix_out:
- return 0;
-}
-
static struct ixgbe_mac_operations mac_ops_82599 = {
.init_hw = &ixgbe_init_hw_generic,
.reset_hw = &ixgbe_reset_hw_82599,
@@ -2181,7 +2108,7 @@ static struct ixgbe_mac_operations mac_ops_82599 = {
.get_mac_addr = &ixgbe_get_mac_addr_generic,
.get_san_mac_addr = &ixgbe_get_san_mac_addr_generic,
.get_device_caps = &ixgbe_get_device_caps_82599,
- .get_wwn_prefix = &ixgbe_get_wwn_prefix_82599,
+ .get_wwn_prefix = &ixgbe_get_wwn_prefix_generic,
.stop_adapter = &ixgbe_stop_adapter_generic,
.get_bus_info = &ixgbe_get_bus_info_generic,
.set_lan_id = &ixgbe_set_lan_id_multi_port_pcie,
@@ -2214,6 +2141,7 @@ static struct ixgbe_eeprom_operations eeprom_ops_82599 = {
.init_params = &ixgbe_init_eeprom_params_generic,
.read = &ixgbe_read_eerd_generic,
.write = &ixgbe_write_eeprom_generic,
+ .calc_checksum = &ixgbe_calc_eeprom_checksum_generic,
.validate_checksum = &ixgbe_validate_eeprom_checksum_generic,
.update_checksum = &ixgbe_update_eeprom_checksum_generic,
};
@@ -2240,5 +2168,5 @@ struct ixgbe_info ixgbe_82599_info = {
.mac_ops = &mac_ops_82599,
.eeprom_ops = &eeprom_ops_82599,
.phy_ops = &phy_ops_82599,
- .mbx_ops = &mbx_ops_82599,
+ .mbx_ops = &mbx_ops_generic,
};
diff --git a/drivers/net/ixgbe/ixgbe_common.c b/drivers/net/ixgbe/ixgbe_common.c
index e3eca13..5605257 100644
--- a/drivers/net/ixgbe/ixgbe_common.c
+++ b/drivers/net/ixgbe/ixgbe_common.c
@@ -45,14 +45,12 @@ static u16 ixgbe_shift_in_eeprom_bits(struct ixgbe_hw *hw, u16 count);
static void ixgbe_raise_eeprom_clk(struct ixgbe_hw *hw, u32 *eec);
static void ixgbe_lower_eeprom_clk(struct ixgbe_hw *hw, u32 *eec);
static void ixgbe_release_eeprom(struct ixgbe_hw *hw);
-static u16 ixgbe_calc_eeprom_checksum(struct ixgbe_hw *hw);
static void ixgbe_enable_rar(struct ixgbe_hw *hw, u32 index);
static void ixgbe_disable_rar(struct ixgbe_hw *hw, u32 index);
static s32 ixgbe_mta_vector(struct ixgbe_hw *hw, u8 *mc_addr);
static void ixgbe_add_uc_addr(struct ixgbe_hw *hw, u8 *addr, u32 vmdq);
static s32 ixgbe_setup_fc(struct ixgbe_hw *hw, s32 packetbuf_num);
-static s32 ixgbe_poll_eerd_eewr_done(struct ixgbe_hw *hw, u32 ee_reg);
/**
* ixgbe_start_hw_generic - Prepare hardware for Tx/Rx
@@ -638,7 +636,7 @@ out:
* Polls the status bit (bit 1) of the EERD or EEWR to determine when the
* read or write is done respectively.
**/
-static s32 ixgbe_poll_eerd_eewr_done(struct ixgbe_hw *hw, u32 ee_reg)
+s32 ixgbe_poll_eerd_eewr_done(struct ixgbe_hw *hw, u32 ee_reg)
{
u32 i;
u32 reg;
@@ -1009,7 +1007,7 @@ static void ixgbe_release_eeprom(struct ixgbe_hw *hw)
* ixgbe_calc_eeprom_checksum - Calculates and returns the checksum
* @hw: pointer to hardware structure
**/
-static u16 ixgbe_calc_eeprom_checksum(struct ixgbe_hw *hw)
+u16 ixgbe_calc_eeprom_checksum_generic(struct ixgbe_hw *hw)
{
u16 i;
u16 j;
@@ -1072,7 +1070,7 @@ s32 ixgbe_validate_eeprom_checksum_generic(struct ixgbe_hw *hw,
status = hw->eeprom.ops.read(hw, 0, &checksum);
if (status == 0) {
- checksum = ixgbe_calc_eeprom_checksum(hw);
+ checksum = hw->eeprom.ops.calc_checksum(hw);
hw->eeprom.ops.read(hw, IXGBE_EEPROM_CHECKSUM, &read_checksum);
@@ -1110,7 +1108,7 @@ s32 ixgbe_update_eeprom_checksum_generic(struct ixgbe_hw *hw)
status = hw->eeprom.ops.read(hw, 0, &checksum);
if (status == 0) {
- checksum = ixgbe_calc_eeprom_checksum(hw);
+ checksum = hw->eeprom.ops.calc_checksum(hw);
status = hw->eeprom.ops.write(hw, IXGBE_EEPROM_CHECKSUM,
checksum);
} else {
@@ -1595,6 +1593,7 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw, s32 packetbuf_num)
u32 mflcn_reg, fccfg_reg;
u32 reg;
u32 rx_pba_size;
+ u32 fcrtl, fcrth;
#ifdef CONFIG_DCB
if (hw->fc.requested_mode == ixgbe_fc_pfc)
@@ -1671,41 +1670,21 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw, s32 packetbuf_num)
IXGBE_WRITE_REG(hw, IXGBE_MFLCN, mflcn_reg);
IXGBE_WRITE_REG(hw, IXGBE_FCCFG, fccfg_reg);
- reg = IXGBE_READ_REG(hw, IXGBE_MTQC);
- /* Thresholds are different for link flow control when in DCB mode */
- if (reg & IXGBE_MTQC_RT_ENA) {
- rx_pba_size = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(packetbuf_num));
+ rx_pba_size = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(packetbuf_num));
+ rx_pba_size >>= IXGBE_RXPBSIZE_SHIFT;
- /* Always disable XON for LFC when in DCB mode */
- reg = (rx_pba_size >> 5) & 0xFFE0;
- IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(packetbuf_num), reg);
+ fcrth = (rx_pba_size - hw->fc.high_water) << 10;
+ fcrtl = (rx_pba_size - hw->fc.low_water) << 10;
- reg = (rx_pba_size >> 2) & 0xFFE0;
- if (hw->fc.current_mode & ixgbe_fc_tx_pause)
- reg |= IXGBE_FCRTH_FCEN;
- IXGBE_WRITE_REG(hw, IXGBE_FCRTH_82599(packetbuf_num), reg);
- } else {
- /*
- * Set up and enable Rx high/low water mark thresholds,
- * enable XON.
- */
- if (hw->fc.current_mode & ixgbe_fc_tx_pause) {
- if (hw->fc.send_xon) {
- IXGBE_WRITE_REG(hw,
- IXGBE_FCRTL_82599(packetbuf_num),
- (hw->fc.low_water |
- IXGBE_FCRTL_XONE));
- } else {
- IXGBE_WRITE_REG(hw,
- IXGBE_FCRTL_82599(packetbuf_num),
- hw->fc.low_water);
- }
-
- IXGBE_WRITE_REG(hw, IXGBE_FCRTH_82599(packetbuf_num),
- (hw->fc.high_water | IXGBE_FCRTH_FCEN));
- }
+ if (hw->fc.current_mode & ixgbe_fc_tx_pause) {
+ fcrth |= IXGBE_FCRTH_FCEN;
+ if (hw->fc.send_xon)
+ fcrtl |= IXGBE_FCRTL_XONE;
}
+ IXGBE_WRITE_REG(hw, IXGBE_FCRTH_82599(packetbuf_num), fcrth);
+ IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(packetbuf_num), fcrtl);
+
/* Configure pause time (2 TCs per register) */
reg = IXGBE_READ_REG(hw, IXGBE_FCTTV(packetbuf_num / 2));
if ((packetbuf_num & 1) == 0)
@@ -2705,3 +2684,48 @@ s32 ixgbe_check_mac_link_generic(struct ixgbe_hw *hw, ixgbe_link_speed *speed,
return 0;
}
+
+/**
+ * ixgbe_get_wwn_prefix_generic Get alternative WWNN/WWPN prefix from
+ * the EEPROM
+ * @hw: pointer to hardware structure
+ * @wwnn_prefix: the alternative WWNN prefix
+ * @wwpn_prefix: the alternative WWPN prefix
+ *
+ * This function will read the EEPROM from the alternative SAN MAC address
+ * block to check the support for the alternative WWNN/WWPN prefix support.
+ **/
+s32 ixgbe_get_wwn_prefix_generic(struct ixgbe_hw *hw, u16 *wwnn_prefix,
+ u16 *wwpn_prefix)
+{
+ u16 offset, caps;
+ u16 alt_san_mac_blk_offset;
+
+ /* clear output first */
+ *wwnn_prefix = 0xFFFF;
+ *wwpn_prefix = 0xFFFF;
+
+ /* check if alternative SAN MAC is supported */
+ hw->eeprom.ops.read(hw, IXGBE_ALT_SAN_MAC_ADDR_BLK_PTR,
+ &alt_san_mac_blk_offset);
+
+ if ((alt_san_mac_blk_offset == 0) ||
+ (alt_san_mac_blk_offset == 0xFFFF))
+ goto wwn_prefix_out;
+
+ /* check capability in alternative san mac address block */
+ offset = alt_san_mac_blk_offset + IXGBE_ALT_SAN_MAC_ADDR_CAPS_OFFSET;
+ hw->eeprom.ops.read(hw, offset, &caps);
+ if (!(caps & IXGBE_ALT_SAN_MAC_ADDR_CAPS_ALTWWN))
+ goto wwn_prefix_out;
+
+ /* get the corresponding prefix for WWNN/WWPN */
+ offset = alt_san_mac_blk_offset + IXGBE_ALT_SAN_MAC_ADDR_WWNN_OFFSET;
+ hw->eeprom.ops.read(hw, offset, wwnn_prefix);
+
+ offset = alt_san_mac_blk_offset + IXGBE_ALT_SAN_MAC_ADDR_WWPN_OFFSET;
+ hw->eeprom.ops.read(hw, offset, wwpn_prefix);
+
+wwn_prefix_out:
+ return 0;
+}
diff --git a/drivers/net/ixgbe/ixgbe_common.h b/drivers/net/ixgbe/ixgbe_common.h
index 424c223..341ca51 100644
--- a/drivers/net/ixgbe/ixgbe_common.h
+++ b/drivers/net/ixgbe/ixgbe_common.h
@@ -49,9 +49,11 @@ s32 ixgbe_write_eeprom_generic(struct ixgbe_hw *hw, u16 offset, u16 data);
s32 ixgbe_read_eerd_generic(struct ixgbe_hw *hw, u16 offset, u16 *data);
s32 ixgbe_read_eeprom_bit_bang_generic(struct ixgbe_hw *hw, u16 offset,
u16 *data);
+u16 ixgbe_calc_eeprom_checksum_generic(struct ixgbe_hw *hw);
s32 ixgbe_validate_eeprom_checksum_generic(struct ixgbe_hw *hw,
u16 *checksum_val);
s32 ixgbe_update_eeprom_checksum_generic(struct ixgbe_hw *hw);
+s32 ixgbe_poll_eerd_eewr_done(struct ixgbe_hw *hw, u32 ee_reg);
s32 ixgbe_set_rar_generic(struct ixgbe_hw *hw, u32 index, u8 *addr, u32 vmdq,
u32 enable_addr);
@@ -81,7 +83,8 @@ s32 ixgbe_clear_vfta_generic(struct ixgbe_hw *hw);
s32 ixgbe_check_mac_link_generic(struct ixgbe_hw *hw,
ixgbe_link_speed *speed,
bool *link_up, bool link_up_wait_to_complete);
-
+s32 ixgbe_get_wwn_prefix_generic(struct ixgbe_hw *hw, u16 *wwnn_prefix,
+ u16 *wwpn_prefix);
s32 ixgbe_blink_led_start_generic(struct ixgbe_hw *hw, u32 index);
s32 ixgbe_blink_led_stop_generic(struct ixgbe_hw *hw, u32 index);
diff --git a/drivers/net/ixgbe/ixgbe_dcb.c b/drivers/net/ixgbe/ixgbe_dcb.c
index 0d44c64..d16c260 100644
--- a/drivers/net/ixgbe/ixgbe_dcb.c
+++ b/drivers/net/ixgbe/ixgbe_dcb.c
@@ -42,7 +42,8 @@
* It should be called only after the rules are checked by
* ixgbe_dcb_check_config().
*/
-s32 ixgbe_dcb_calculate_tc_credits(struct ixgbe_dcb_config *dcb_config,
+s32 ixgbe_dcb_calculate_tc_credits(struct ixgbe_hw *hw,
+ struct ixgbe_dcb_config *dcb_config,
int max_frame, u8 direction)
{
struct tc_bw_alloc *p;
@@ -124,7 +125,8 @@ s32 ixgbe_dcb_calculate_tc_credits(struct ixgbe_dcb_config *dcb_config,
* credit may not be enough to send out a TSO
* packet in descriptor plane arbitration.
*/
- if (credit_max &&
+ if ((hw->mac.type == ixgbe_mac_82598EB) &&
+ credit_max &&
(credit_max < MINIMUM_CREDIT_FOR_TSO))
credit_max = MINIMUM_CREDIT_FOR_TSO;
@@ -150,10 +152,17 @@ s32 ixgbe_dcb_hw_config(struct ixgbe_hw *hw,
struct ixgbe_dcb_config *dcb_config)
{
s32 ret = 0;
- if (hw->mac.type == ixgbe_mac_82598EB)
+ switch (hw->mac.type) {
+ case ixgbe_mac_82598EB:
ret = ixgbe_dcb_hw_config_82598(hw, dcb_config);
- else if (hw->mac.type == ixgbe_mac_82599EB)
+ break;
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
ret = ixgbe_dcb_hw_config_82599(hw, dcb_config);
+ break;
+ default:
+ break;
+ }
return ret;
}
diff --git a/drivers/net/ixgbe/ixgbe_dcb.h b/drivers/net/ixgbe/ixgbe_dcb.h
index 0208a87..1cfe38e 100644
--- a/drivers/net/ixgbe/ixgbe_dcb.h
+++ b/drivers/net/ixgbe/ixgbe_dcb.h
@@ -150,7 +150,8 @@ struct ixgbe_dcb_config {
/* DCB driver APIs */
/* DCB credits calculation */
-s32 ixgbe_dcb_calculate_tc_credits(struct ixgbe_dcb_config *, int, u8);
+s32 ixgbe_dcb_calculate_tc_credits(struct ixgbe_hw *,
+ struct ixgbe_dcb_config *, int, u8);
/* DCB hw initialization */
s32 ixgbe_dcb_hw_config(struct ixgbe_hw *, struct ixgbe_dcb_config *);
diff --git a/drivers/net/ixgbe/ixgbe_dcb_82598.c b/drivers/net/ixgbe/ixgbe_dcb_82598.c
index 50288bc..9a5e89c 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_82598.c
+++ b/drivers/net/ixgbe/ixgbe_dcb_82598.c
@@ -256,21 +256,17 @@ s32 ixgbe_dcb_config_pfc_82598(struct ixgbe_hw *hw,
* for each traffic class.
*/
for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
- if (dcb_config->rx_pba_cfg == pba_equal) {
- rx_pba_size = IXGBE_RXPBSIZE_64KB;
- } else {
- rx_pba_size = (i < 4) ? IXGBE_RXPBSIZE_80KB
- : IXGBE_RXPBSIZE_48KB;
- }
+ rx_pba_size = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(i));
+ rx_pba_size >>= IXGBE_RXPBSIZE_SHIFT;
+ reg = (rx_pba_size - hw->fc.low_water) << 10;
- reg = ((rx_pba_size >> 5) & 0xFFF0);
if (dcb_config->tc_config[i].dcb_pfc == pfc_enabled_tx ||
dcb_config->tc_config[i].dcb_pfc == pfc_enabled_full)
reg |= IXGBE_FCRTL_XONE;
IXGBE_WRITE_REG(hw, IXGBE_FCRTL(i), reg);
- reg = ((rx_pba_size >> 2) & 0xFFF0);
+ reg = (rx_pba_size - hw->fc.high_water) << 10;
if (dcb_config->tc_config[i].dcb_pfc == pfc_enabled_tx ||
dcb_config->tc_config[i].dcb_pfc == pfc_enabled_full)
reg |= IXGBE_FCRTH_FCEN;
diff --git a/drivers/net/ixgbe/ixgbe_dcb_82599.c b/drivers/net/ixgbe/ixgbe_dcb_82599.c
index 05f2247..374e1f7 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_82599.c
+++ b/drivers/net/ixgbe/ixgbe_dcb_82599.c
@@ -251,19 +251,17 @@ s32 ixgbe_dcb_config_pfc_82599(struct ixgbe_hw *hw,
/* Configure PFC Tx thresholds per TC */
for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
- if (dcb_config->rx_pba_cfg == pba_equal)
- rx_pba_size = IXGBE_RXPBSIZE_64KB;
- else
- rx_pba_size = (i < 4) ? IXGBE_RXPBSIZE_80KB
- : IXGBE_RXPBSIZE_48KB;
+ rx_pba_size = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(i));
+ rx_pba_size >>= IXGBE_RXPBSIZE_SHIFT;
+
+ reg = (rx_pba_size - hw->fc.low_water) << 10;
- reg = ((rx_pba_size >> 5) & 0xFFE0);
if (dcb_config->tc_config[i].dcb_pfc == pfc_enabled_full ||
dcb_config->tc_config[i].dcb_pfc == pfc_enabled_tx)
reg |= IXGBE_FCRTL_XONE;
IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(i), reg);
- reg = ((rx_pba_size >> 2) & 0xFFE0);
+ reg = (rx_pba_size - hw->fc.high_water) << 10;
if (dcb_config->tc_config[i].dcb_pfc == pfc_enabled_full ||
dcb_config->tc_config[i].dcb_pfc == pfc_enabled_tx)
reg |= IXGBE_FCRTH_FCEN;
diff --git a/drivers/net/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ixgbe/ixgbe_dcb_nl.c
index b53b465..bf566e8 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ixgbe/ixgbe_dcb_nl.c
@@ -130,15 +130,21 @@ static u8 ixgbe_dcbnl_set_state(struct net_device *netdev, u8 state)
netdev->netdev_ops->ndo_stop(netdev);
ixgbe_clear_interrupt_scheme(adapter);
- if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
+ adapter->flags &= ~IXGBE_FLAG_RSS_ENABLED;
+ switch (adapter->hw.mac.type) {
+ case ixgbe_mac_82598EB:
adapter->last_lfc_mode = adapter->hw.fc.current_mode;
adapter->hw.fc.requested_mode = ixgbe_fc_none;
- }
- adapter->flags &= ~IXGBE_FLAG_RSS_ENABLED;
- if (adapter->hw.mac.type == ixgbe_mac_82599EB) {
+ break;
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE;
adapter->flags &= ~IXGBE_FLAG_FDIR_PERFECT_CAPABLE;
+ break;
+ default:
+ break;
}
+
adapter->flags |= IXGBE_FLAG_DCB_ENABLED;
ixgbe_init_interrupt_scheme(adapter);
if (netif_running(netdev))
@@ -155,8 +161,14 @@ static u8 ixgbe_dcbnl_set_state(struct net_device *netdev, u8 state)
adapter->dcb_cfg.pfc_mode_enable = false;
adapter->flags &= ~IXGBE_FLAG_DCB_ENABLED;
adapter->flags |= IXGBE_FLAG_RSS_ENABLED;
- if (adapter->hw.mac.type == ixgbe_mac_82599EB)
+ switch (adapter->hw.mac.type) {
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
adapter->flags |= IXGBE_FLAG_FDIR_HASH_CAPABLE;
+ break;
+ default:
+ break;
+ }
ixgbe_init_interrupt_scheme(adapter);
if (netif_running(netdev))
@@ -178,9 +190,14 @@ static void ixgbe_dcbnl_get_perm_hw_addr(struct net_device *netdev,
for (i = 0; i < netdev->addr_len; i++)
perm_addr[i] = adapter->hw.mac.perm_addr[i];
- if (adapter->hw.mac.type == ixgbe_mac_82599EB) {
+ switch (adapter->hw.mac.type) {
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
for (j = 0; j < netdev->addr_len; j++, i++)
perm_addr[i] = adapter->hw.mac.san_addr[j];
+ break;
+ default:
+ break;
}
}
@@ -366,15 +383,29 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
}
if (adapter->dcb_cfg.pfc_mode_enable) {
- if ((adapter->hw.mac.type != ixgbe_mac_82598EB) &&
- (adapter->hw.fc.current_mode != ixgbe_fc_pfc))
- adapter->last_lfc_mode = adapter->hw.fc.current_mode;
+ switch (adapter->hw.mac.type) {
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
+ if (adapter->hw.fc.current_mode != ixgbe_fc_pfc)
+ adapter->last_lfc_mode =
+ adapter->hw.fc.current_mode;
+ break;
+ default:
+ break;
+ }
adapter->hw.fc.requested_mode = ixgbe_fc_pfc;
} else {
- if (adapter->hw.mac.type != ixgbe_mac_82598EB)
- adapter->hw.fc.requested_mode = adapter->last_lfc_mode;
- else
+ switch (adapter->hw.mac.type) {
+ case ixgbe_mac_82598EB:
adapter->hw.fc.requested_mode = ixgbe_fc_none;
+ break;
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
+ adapter->hw.fc.requested_mode = adapter->last_lfc_mode;
+ break;
+ default:
+ break;
+ }
}
if (adapter->dcb_set_bitmap & BIT_RESETLINK) {
diff --git a/drivers/net/ixgbe/ixgbe_ethtool.c b/drivers/net/ixgbe/ixgbe_ethtool.c
index 3dc731c..f9b5839 100644
--- a/drivers/net/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ixgbe/ixgbe_ethtool.c
@@ -185,6 +185,16 @@ static int ixgbe_get_settings(struct net_device *netdev,
ADVERTISED_FIBRE);
ecmd->port = PORT_FIBRE;
ecmd->autoneg = AUTONEG_DISABLE;
+ } else if ((hw->device_id == IXGBE_DEV_ID_82599_COMBO_BACKPLANE) ||
+ (hw->device_id == IXGBE_DEV_ID_82599_KX4_MEZZ)) {
+ ecmd->supported |= (SUPPORTED_1000baseT_Full |
+ SUPPORTED_Autoneg |
+ SUPPORTED_FIBRE);
+ ecmd->advertising = (ADVERTISED_10000baseT_Full |
+ ADVERTISED_1000baseT_Full |
+ ADVERTISED_Autoneg |
+ ADVERTISED_FIBRE);
+ ecmd->port = PORT_FIBRE;
} else {
ecmd->supported |= (SUPPORTED_1000baseT_Full |
SUPPORTED_FIBRE);
@@ -204,6 +214,7 @@ static int ixgbe_get_settings(struct net_device *netdev,
/* Get PHY type */
switch (adapter->hw.phy.type) {
case ixgbe_phy_tn:
+ case ixgbe_phy_aq:
case ixgbe_phy_cu_unknown:
/* Copper 10G-BASET */
ecmd->port = PORT_TP;
@@ -332,13 +343,6 @@ static void ixgbe_get_pauseparam(struct net_device *netdev,
else
pause->autoneg = 1;
-#ifdef CONFIG_DCB
- if (hw->fc.current_mode == ixgbe_fc_pfc) {
- pause->rx_pause = 0;
- pause->tx_pause = 0;
- }
-
-#endif
if (hw->fc.current_mode == ixgbe_fc_rx_pause) {
pause->rx_pause = 1;
} else if (hw->fc.current_mode == ixgbe_fc_tx_pause) {
@@ -346,6 +350,11 @@ static void ixgbe_get_pauseparam(struct net_device *netdev,
} else if (hw->fc.current_mode == ixgbe_fc_full) {
pause->rx_pause = 1;
pause->tx_pause = 1;
+#ifdef CONFIG_DCB
+ } else if (hw->fc.current_mode == ixgbe_fc_pfc) {
+ pause->rx_pause = 0;
+ pause->tx_pause = 0;
+#endif
}
}
@@ -363,7 +372,6 @@ static int ixgbe_set_pauseparam(struct net_device *netdev,
return -EINVAL;
#endif
-
fc = hw->fc;
if (pause->autoneg != AUTONEG_ENABLE)
@@ -412,11 +420,6 @@ static int ixgbe_set_rx_csum(struct net_device *netdev, u32 data)
else
adapter->flags &= ~IXGBE_FLAG_RX_CSUM_ENABLED;
- if (netif_running(netdev))
- ixgbe_reinit_locked(adapter);
- else
- ixgbe_reset(adapter);
-
return 0;
}
@@ -428,16 +431,21 @@ static u32 ixgbe_get_tx_csum(struct net_device *netdev)
static int ixgbe_set_tx_csum(struct net_device *netdev, u32 data)
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
+ u32 feature_list;
- if (data) {
- netdev->features |= (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
- if (adapter->hw.mac.type == ixgbe_mac_82599EB)
- netdev->features |= NETIF_F_SCTP_CSUM;
- } else {
- netdev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
- if (adapter->hw.mac.type == ixgbe_mac_82599EB)
- netdev->features &= ~NETIF_F_SCTP_CSUM;
+ feature_list = (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
+ switch (adapter->hw.mac.type) {
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
+ feature_list |= NETIF_F_SCTP_CSUM;
+ break;
+ default:
+ break;
}
+ if (data)
+ netdev->features |= feature_list;
+ else
+ netdev->features &= ~feature_list;
return 0;
}
@@ -530,10 +538,20 @@ static void ixgbe_get_regs(struct net_device *netdev,
regs_buff[32] = IXGBE_READ_REG(hw, IXGBE_FCTTV(1));
regs_buff[33] = IXGBE_READ_REG(hw, IXGBE_FCTTV(2));
regs_buff[34] = IXGBE_READ_REG(hw, IXGBE_FCTTV(3));
- for (i = 0; i < 8; i++)
- regs_buff[35 + i] = IXGBE_READ_REG(hw, IXGBE_FCRTL(i));
- for (i = 0; i < 8; i++)
- regs_buff[43 + i] = IXGBE_READ_REG(hw, IXGBE_FCRTH(i));
+ for (i = 0; i < 8; i++) {
+ switch (hw->mac.type) {
+ case ixgbe_mac_82598EB:
+ regs_buff[35 + i] = IXGBE_READ_REG(hw, IXGBE_FCRTL(i));
+ regs_buff[43 + i] = IXGBE_READ_REG(hw, IXGBE_FCRTH(i));
+ break;
+ case ixgbe_mac_82599EB:
+ regs_buff[35 + i] = IXGBE_READ_REG(hw, IXGBE_FCRTL_82599(i));
+ regs_buff[43 + i] = IXGBE_READ_REG(hw, IXGBE_FCRTH_82599(i));
+ break;
+ default:
+ break;
+ }
+ }
regs_buff[51] = IXGBE_READ_REG(hw, IXGBE_FCRTV);
regs_buff[52] = IXGBE_READ_REG(hw, IXGBE_TFCS);
@@ -615,6 +633,7 @@ static void ixgbe_get_regs(struct net_device *netdev,
regs_buff[827] = IXGBE_READ_REG(hw, IXGBE_WUPM);
regs_buff[828] = IXGBE_READ_REG(hw, IXGBE_FHFT(0));
+ /* DCB */
regs_buff[829] = IXGBE_READ_REG(hw, IXGBE_RMCS);
regs_buff[830] = IXGBE_READ_REG(hw, IXGBE_DPMCS);
regs_buff[831] = IXGBE_READ_REG(hw, IXGBE_PDPMCS);
@@ -905,13 +924,11 @@ static int ixgbe_set_ringparam(struct net_device *netdev,
memcpy(&temp_tx_ring[i], adapter->tx_ring[i],
sizeof(struct ixgbe_ring));
temp_tx_ring[i].count = new_tx_count;
- err = ixgbe_setup_tx_resources(adapter,
- &temp_tx_ring[i]);
+ err = ixgbe_setup_tx_resources(&temp_tx_ring[i]);
if (err) {
while (i) {
i--;
- ixgbe_free_tx_resources(adapter,
- &temp_tx_ring[i]);
+ ixgbe_free_tx_resources(&temp_tx_ring[i]);
}
goto clear_reset;
}
@@ -930,13 +947,11 @@ static int ixgbe_set_ringparam(struct net_device *netdev,
memcpy(&temp_rx_ring[i], adapter->rx_ring[i],
sizeof(struct ixgbe_ring));
temp_rx_ring[i].count = new_rx_count;
- err = ixgbe_setup_rx_resources(adapter,
- &temp_rx_ring[i]);
+ err = ixgbe_setup_rx_resources(&temp_rx_ring[i]);
if (err) {
while (i) {
i--;
- ixgbe_free_rx_resources(adapter,
- &temp_rx_ring[i]);
+ ixgbe_free_rx_resources(&temp_rx_ring[i]);
}
goto err_setup;
}
@@ -951,8 +966,7 @@ static int ixgbe_set_ringparam(struct net_device *netdev,
/* tx */
if (new_tx_count != adapter->tx_ring_count) {
for (i = 0; i < adapter->num_tx_queues; i++) {
- ixgbe_free_tx_resources(adapter,
- adapter->tx_ring[i]);
+ ixgbe_free_tx_resources(adapter->tx_ring[i]);
memcpy(adapter->tx_ring[i], &temp_tx_ring[i],
sizeof(struct ixgbe_ring));
}
@@ -962,8 +976,7 @@ static int ixgbe_set_ringparam(struct net_device *netdev,
/* rx */
if (new_rx_count != adapter->rx_ring_count) {
for (i = 0; i < adapter->num_rx_queues; i++) {
- ixgbe_free_rx_resources(adapter,
- adapter->rx_ring[i]);
+ ixgbe_free_rx_resources(adapter->rx_ring[i]);
memcpy(adapter->rx_ring[i], &temp_rx_ring[i],
sizeof(struct ixgbe_ring));
}
@@ -1237,12 +1250,20 @@ static int ixgbe_reg_test(struct ixgbe_adapter *adapter, u64 *data)
u32 value, before, after;
u32 i, toggle;
- if (adapter->hw.mac.type == ixgbe_mac_82599EB) {
- toggle = 0x7FFFF30F;
- test = reg_test_82599;
- } else {
+ switch (adapter->hw.mac.type) {
+ case ixgbe_mac_82598EB:
toggle = 0x7FFFF3FF;
test = reg_test_82598;
+ break;
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
+ toggle = 0x7FFFF30F;
+ test = reg_test_82599;
+ break;
+ default:
+ *data = 1;
+ return 1;
+ break;
}
/*
@@ -1460,16 +1481,21 @@ static void ixgbe_free_desc_rings(struct ixgbe_adapter *adapter)
reg_ctl &= ~IXGBE_TXDCTL_ENABLE;
IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(tx_ring->reg_idx), reg_ctl);
- if (hw->mac.type == ixgbe_mac_82599EB) {
+ switch (hw->mac.type) {
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
reg_ctl = IXGBE_READ_REG(hw, IXGBE_DMATXCTL);
reg_ctl &= ~IXGBE_DMATXCTL_TE;
IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL, reg_ctl);
+ break;
+ default:
+ break;
}
ixgbe_reset(adapter);
- ixgbe_free_tx_resources(adapter, &adapter->test_tx_ring);
- ixgbe_free_rx_resources(adapter, &adapter->test_rx_ring);
+ ixgbe_free_tx_resources(&adapter->test_tx_ring);
+ ixgbe_free_rx_resources(&adapter->test_rx_ring);
}
static int ixgbe_setup_desc_rings(struct ixgbe_adapter *adapter)
@@ -1483,17 +1509,24 @@ static int ixgbe_setup_desc_rings(struct ixgbe_adapter *adapter)
/* Setup Tx descriptor ring and Tx buffers */
tx_ring->count = IXGBE_DEFAULT_TXD;
tx_ring->queue_index = 0;
+ tx_ring->dev = &adapter->pdev->dev;
+ tx_ring->netdev = adapter->netdev;
tx_ring->reg_idx = adapter->tx_ring[0]->reg_idx;
tx_ring->numa_node = adapter->node;
- err = ixgbe_setup_tx_resources(adapter, tx_ring);
+ err = ixgbe_setup_tx_resources(tx_ring);
if (err)
return 1;
- if (adapter->hw.mac.type == ixgbe_mac_82599EB) {
+ switch (adapter->hw.mac.type) {
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
reg_data = IXGBE_READ_REG(&adapter->hw, IXGBE_DMATXCTL);
reg_data |= IXGBE_DMATXCTL_TE;
IXGBE_WRITE_REG(&adapter->hw, IXGBE_DMATXCTL, reg_data);
+ break;
+ default:
+ break;
}
ixgbe_configure_tx_ring(adapter, tx_ring);
@@ -1501,11 +1534,13 @@ static int ixgbe_setup_desc_rings(struct ixgbe_adapter *adapter)
/* Setup Rx Descriptor ring and Rx buffers */
rx_ring->count = IXGBE_DEFAULT_RXD;
rx_ring->queue_index = 0;
+ rx_ring->dev = &adapter->pdev->dev;
+ rx_ring->netdev = adapter->netdev;
rx_ring->reg_idx = adapter->rx_ring[0]->reg_idx;
rx_ring->rx_buf_len = IXGBE_RXBUFFER_2048;
rx_ring->numa_node = adapter->node;
- err = ixgbe_setup_rx_resources(adapter, rx_ring);
+ err = ixgbe_setup_rx_resources(rx_ring);
if (err) {
ret_val = 4;
goto err_nomem;
@@ -1604,8 +1639,7 @@ static int ixgbe_check_lbtest_frame(struct sk_buff *skb,
return 13;
}
-static u16 ixgbe_clean_test_rings(struct ixgbe_adapter *adapter,
- struct ixgbe_ring *rx_ring,
+static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring,
struct ixgbe_ring *tx_ring,
unsigned int size)
{
@@ -1627,7 +1661,7 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_adapter *adapter,
rx_buffer_info = &rx_ring->rx_buffer_info[rx_ntc];
/* unmap Rx buffer, will be remapped by alloc_rx_buffers */
- dma_unmap_single(&adapter->pdev->dev,
+ dma_unmap_single(rx_ring->dev,
rx_buffer_info->dma,
bufsz,
DMA_FROM_DEVICE);
@@ -1639,7 +1673,7 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_adapter *adapter,
/* unmap buffer on Tx side */
tx_buffer_info = &tx_ring->tx_buffer_info[tx_ntc];
- ixgbe_unmap_and_free_tx_resource(adapter, tx_buffer_info);
+ ixgbe_unmap_and_free_tx_resource(tx_ring, tx_buffer_info);
/* increment Rx/Tx next to clean counters */
rx_ntc++;
@@ -1655,7 +1689,7 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_adapter *adapter,
}
/* re-map buffers to ring, store next to clean values */
- ixgbe_alloc_rx_buffers(adapter, rx_ring, count);
+ ixgbe_alloc_rx_buffers(rx_ring, count);
rx_ring->next_to_clean = rx_ntc;
tx_ring->next_to_clean = tx_ntc;
@@ -1699,7 +1733,6 @@ static int ixgbe_run_loopback_test(struct ixgbe_adapter *adapter)
for (i = 0; i < 64; i++) {
skb_get(skb);
tx_ret_val = ixgbe_xmit_frame_ring(skb,
- adapter->netdev,
adapter,
tx_ring);
if (tx_ret_val == NETDEV_TX_OK)
@@ -1714,8 +1747,7 @@ static int ixgbe_run_loopback_test(struct ixgbe_adapter *adapter)
/* allow 200 milliseconds for packets to go from Tx to Rx */
msleep(200);
- good_cnt = ixgbe_clean_test_rings(adapter, rx_ring,
- tx_ring, size);
+ good_cnt = ixgbe_clean_test_rings(rx_ring, tx_ring, size);
if (good_cnt != 64) {
ret_val = 13;
break;
@@ -1848,6 +1880,13 @@ static int ixgbe_wol_exclusion(struct ixgbe_adapter *adapter,
int retval = 1;
switch(hw->device_id) {
+ case IXGBE_DEV_ID_82599_COMBO_BACKPLANE:
+ /* All except this subdevice support WOL */
+ if (hw->subsystem_device_id ==
+ IXGBE_SUBDEV_ID_82599_KX4_KR_MEZZ) {
+ wol->supported = 0;
+ break;
+ }
case IXGBE_DEV_ID_82599_KX4:
retval = 0;
break;
@@ -1985,6 +2024,41 @@ static int ixgbe_get_coalesce(struct net_device *netdev,
return 0;
}
+/*
+ * this function must be called before setting the new value of
+ * rx_itr_setting
+ */
+static bool ixgbe_update_rsc(struct ixgbe_adapter *adapter,
+ struct ethtool_coalesce *ec)
+{
+ struct net_device *netdev = adapter->netdev;
+
+ if (!(adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE))
+ return false;
+
+ /* if interrupt rate is too high then disable RSC */
+ if (ec->rx_coalesce_usecs != 1 &&
+ ec->rx_coalesce_usecs <= 1000000/IXGBE_MAX_RSC_INT_RATE) {
+ if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) {
+ e_info(probe, "rx-usecs set too low, "
+ "disabling RSC\n");
+ adapter->flags2 &= ~IXGBE_FLAG2_RSC_ENABLED;
+ return true;
+ }
+ } else {
+ /* check the feature flag value and enable RSC if necessary */
+ if ((netdev->features & NETIF_F_LRO) &&
+ !(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)) {
+ e_info(probe, "rx-usecs set to %d, "
+ "re-enabling RSC\n",
+ ec->rx_coalesce_usecs);
+ adapter->flags2 |= IXGBE_FLAG2_RSC_ENABLED;
+ return true;
+ }
+ }
+ return false;
+}
+
static int ixgbe_set_coalesce(struct net_device *netdev,
struct ethtool_coalesce *ec)
{
@@ -2002,17 +2076,14 @@ static int ixgbe_set_coalesce(struct net_device *netdev,
adapter->tx_ring[0]->work_limit = ec->tx_max_coalesced_frames_irq;
if (ec->rx_coalesce_usecs > 1) {
- u32 max_int;
- if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)
- max_int = IXGBE_MAX_RSC_INT_RATE;
- else
- max_int = IXGBE_MAX_INT_RATE;
-
/* check the limits */
- if ((1000000/ec->rx_coalesce_usecs > max_int) ||
+ if ((1000000/ec->rx_coalesce_usecs > IXGBE_MAX_INT_RATE) ||
(1000000/ec->rx_coalesce_usecs < IXGBE_MIN_INT_RATE))
return -EINVAL;
+ /* check the old value and enable RSC if necessary */
+ need_reset = ixgbe_update_rsc(adapter, ec);
+
/* store the value in ints/second */
adapter->rx_eitr_param = 1000000/ec->rx_coalesce_usecs;
@@ -2021,32 +2092,21 @@ static int ixgbe_set_coalesce(struct net_device *netdev,
/* clear the lower bit as its used for dynamic state */
adapter->rx_itr_setting &= ~1;
} else if (ec->rx_coalesce_usecs == 1) {
+ /* check the old value and enable RSC if necessary */
+ need_reset = ixgbe_update_rsc(adapter, ec);
+
/* 1 means dynamic mode */
adapter->rx_eitr_param = 20000;
adapter->rx_itr_setting = 1;
} else {
+ /* check the old value and enable RSC if necessary */
+ need_reset = ixgbe_update_rsc(adapter, ec);
/*
* any other value means disable eitr, which is best
* served by setting the interrupt rate very high
*/
adapter->rx_eitr_param = IXGBE_MAX_INT_RATE;
adapter->rx_itr_setting = 0;
-
- /*
- * if hardware RSC is enabled, disable it when
- * setting low latency mode, to avoid errata, assuming
- * that when the user set low latency mode they want
- * it at the cost of anything else
- */
- if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) {
- adapter->flags2 &= ~IXGBE_FLAG2_RSC_ENABLED;
- if (netdev->features & NETIF_F_LRO) {
- netdev->features &= ~NETIF_F_LRO;
- e_info(probe, "rx-usecs set to 0, "
- "disabling RSC\n");
- }
- need_reset = true;
- }
}
if (ec->tx_coalesce_usecs > 1) {
@@ -2133,28 +2193,39 @@ static int ixgbe_set_flags(struct net_device *netdev, u32 data)
return rc;
/* if state changes we need to update adapter->flags and reset */
- if (adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE) {
- /*
- * cast both to bool and verify if they are set the same
- * but only enable RSC if itr is non-zero, as
- * itr=0 and RSC are mutually exclusive
- */
- if (((!!(data & ETH_FLAG_LRO)) !=
- (!!(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED))) &&
- adapter->rx_itr_setting) {
+ if ((adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE) &&
+ (!!(data & ETH_FLAG_LRO) !=
+ !!(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED))) {
+ if ((data & ETH_FLAG_LRO) &&
+ (!adapter->rx_itr_setting ||
+ (adapter->rx_itr_setting > IXGBE_MAX_RSC_INT_RATE))) {
+ e_info(probe, "rx-usecs set too low, "
+ "not enabling RSC.\n");
+ } else {
adapter->flags2 ^= IXGBE_FLAG2_RSC_ENABLED;
switch (adapter->hw.mac.type) {
case ixgbe_mac_82599EB:
need_reset = true;
break;
+ case ixgbe_mac_X540: {
+ int i;
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ struct ixgbe_ring *ring =
+ adapter->rx_ring[i];
+ if (adapter->flags2 &
+ IXGBE_FLAG2_RSC_ENABLED) {
+ ixgbe_configure_rscctl(adapter,
+ ring);
+ } else {
+ ixgbe_clear_rscctl(adapter,
+ ring);
+ }
+ }
+ }
+ break;
default:
break;
}
- } else if (!adapter->rx_itr_setting) {
- netdev->features &= ~NETIF_F_LRO;
- if (data & ETH_FLAG_LRO)
- e_info(probe, "rx-usecs set to 0, "
- "LRO/RSC cannot be enabled.\n");
}
}
diff --git a/drivers/net/ixgbe/ixgbe_fcoe.c b/drivers/net/ixgbe/ixgbe_fcoe.c
index 05efa6a..6342d48 100644
--- a/drivers/net/ixgbe/ixgbe_fcoe.c
+++ b/drivers/net/ixgbe/ixgbe_fcoe.c
@@ -68,7 +68,7 @@ static inline bool ixgbe_rx_is_fcoe(union ixgbe_adv_rx_desc *rx_desc)
static inline void ixgbe_fcoe_clear_ddp(struct ixgbe_fcoe_ddp *ddp)
{
ddp->len = 0;
- ddp->err = 0;
+ ddp->err = 1;
ddp->udl = NULL;
ddp->udp = 0UL;
ddp->sgl = NULL;
@@ -92,6 +92,7 @@ int ixgbe_fcoe_ddp_put(struct net_device *netdev, u16 xid)
struct ixgbe_fcoe *fcoe;
struct ixgbe_adapter *adapter;
struct ixgbe_fcoe_ddp *ddp;
+ u32 fcbuff;
if (!netdev)
goto out_ddp_put;
@@ -115,7 +116,14 @@ int ixgbe_fcoe_ddp_put(struct net_device *netdev, u16 xid)
IXGBE_WRITE_REG(&adapter->hw, IXGBE_FCBUFF, 0);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_FCDMARW,
(xid | IXGBE_FCDMARW_WE));
+
+ /* guaranteed to be invalidated after 100us */
+ IXGBE_WRITE_REG(&adapter->hw, IXGBE_FCDMARW,
+ (xid | IXGBE_FCDMARW_RE));
+ fcbuff = IXGBE_READ_REG(&adapter->hw, IXGBE_FCBUFF);
spin_unlock_bh(&fcoe->lock);
+ if (fcbuff & IXGBE_FCBUFF_VALID)
+ udelay(100);
}
if (ddp->sgl)
pci_unmap_sg(adapter->pdev, ddp->sgl, ddp->sgc,
@@ -168,6 +176,11 @@ int ixgbe_fcoe_ddp_get(struct net_device *netdev, u16 xid,
return 0;
}
+ /* no DDP if we are already down or resetting */
+ if (test_bit(__IXGBE_DOWN, &adapter->state) ||
+ test_bit(__IXGBE_RESETTING, &adapter->state))
+ return 0;
+
fcoe = &adapter->fcoe;
if (!fcoe->pool) {
e_warn(drv, "xid=0x%x no ddp pool for fcoe\n", xid);
diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index fbad4d8..5409af3 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -59,6 +59,7 @@ static char ixgbe_copyright[] = "Copyright (c) 1999-2010 Intel Corporation.";
static const struct ixgbe_info *ixgbe_info_tbl[] = {
[board_82598] = &ixgbe_82598_info,
[board_82599] = &ixgbe_82599_info,
+ [board_X540] = &ixgbe_X540_info,
};
/* ixgbe_pci_tbl - PCI Device ID Table
@@ -112,6 +113,8 @@ static DEFINE_PCI_DEVICE_TABLE(ixgbe_pci_tbl) = {
board_82599 },
{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_COMBO_BACKPLANE),
board_82599 },
+ {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540T),
+ board_82599 },
/* required last entry */
{0, }
@@ -560,6 +563,7 @@ static void ixgbe_set_ivar(struct ixgbe_adapter *adapter, s8 direction,
IXGBE_WRITE_REG(hw, IXGBE_IVAR(index), ivar);
break;
case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
if (direction == -1) {
/* other causes */
msix_vector |= IXGBE_IVAR_ALLOC_VAL;
@@ -589,29 +593,34 @@ static inline void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter,
{
u32 mask;
- if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
+ switch (adapter->hw.mac.type) {
+ case ixgbe_mac_82598EB:
mask = (IXGBE_EIMS_RTX_QUEUE & qmask);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS, mask);
- } else {
+ break;
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
mask = (qmask & 0xFFFFFFFF);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS_EX(0), mask);
mask = (qmask >> 32);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS_EX(1), mask);
+ break;
+ default:
+ break;
}
}
-void ixgbe_unmap_and_free_tx_resource(struct ixgbe_adapter *adapter,
- struct ixgbe_tx_buffer
- *tx_buffer_info)
+void ixgbe_unmap_and_free_tx_resource(struct ixgbe_ring *tx_ring,
+ struct ixgbe_tx_buffer *tx_buffer_info)
{
if (tx_buffer_info->dma) {
if (tx_buffer_info->mapped_as_page)
- dma_unmap_page(&adapter->pdev->dev,
+ dma_unmap_page(tx_ring->dev,
tx_buffer_info->dma,
tx_buffer_info->length,
DMA_TO_DEVICE);
else
- dma_unmap_single(&adapter->pdev->dev,
+ dma_unmap_single(tx_ring->dev,
tx_buffer_info->dma,
tx_buffer_info->length,
DMA_TO_DEVICE);
@@ -626,92 +635,166 @@ void ixgbe_unmap_and_free_tx_resource(struct ixgbe_adapter *adapter,
}
/**
- * ixgbe_tx_xon_state - check the tx ring xon state
- * @adapter: the ixgbe adapter
- * @tx_ring: the corresponding tx_ring
+ * ixgbe_dcb_txq_to_tc - convert a reg index to a traffic class
+ * @adapter: driver private struct
+ * @index: reg idx of queue to query (0-127)
*
- * If not in DCB mode, checks TFCS.TXOFF, otherwise, find out the
- * corresponding TC of this tx_ring when checking TFCS.
+ * Helper function to determine the traffic index for a paticular
+ * register index.
*
- * Returns : true if in xon state (currently not paused)
+ * Returns : a tc index for use in range 0-7, or 0-3
*/
-static inline bool ixgbe_tx_xon_state(struct ixgbe_adapter *adapter,
- struct ixgbe_ring *tx_ring)
+u8 ixgbe_dcb_txq_to_tc(struct ixgbe_adapter *adapter, u8 reg_idx)
{
- u32 txoff = IXGBE_TFCS_TXOFF;
+ int tc = -1;
+ int dcb_i = adapter->ring_feature[RING_F_DCB].indices;
-#ifdef CONFIG_IXGBE_DCB
- if (adapter->dcb_cfg.pfc_mode_enable) {
- int tc;
- int reg_idx = tx_ring->reg_idx;
- int dcb_i = adapter->ring_feature[RING_F_DCB].indices;
+ /* if DCB is not enabled the queues have no TC */
+ if (!(adapter->flags & IXGBE_FLAG_DCB_ENABLED))
+ return tc;
+
+ /* check valid range */
+ if (reg_idx >= adapter->hw.mac.max_tx_queues)
+ return tc;
+
+ switch (adapter->hw.mac.type) {
+ case ixgbe_mac_82598EB:
+ tc = reg_idx >> 2;
+ break;
+ default:
+ if (dcb_i != 4 && dcb_i != 8)
+ break;
+
+ /* if VMDq is enabled the lowest order bits determine TC */
+ if (adapter->flags & (IXGBE_FLAG_SRIOV_ENABLED |
+ IXGBE_FLAG_VMDQ_ENABLED)) {
+ tc = reg_idx & (dcb_i - 1);
+ break;
+ }
+
+ /*
+ * Convert the reg_idx into the correct TC. This bitmask
+ * targets the last full 32 ring traffic class and assigns
+ * it a value of 1. From there the rest of the rings are
+ * based on shifting the mask further up to include the
+ * reg_idx / 16 and then reg_idx / 8. It assumes dcB_i
+ * will only ever be 8 or 4 and that reg_idx will never
+ * be greater then 128. The code without the power of 2
+ * optimizations would be:
+ * (((reg_idx % 32) + 32) * dcb_i) >> (9 - reg_idx / 32)
+ */
+ tc = ((reg_idx & 0X1F) + 0x20) * dcb_i;
+ tc >>= 9 - (reg_idx >> 5);
+ }
+
+ return tc;
+}
- switch (adapter->hw.mac.type) {
+static void ixgbe_update_xoff_received(struct ixgbe_adapter *adapter)
+{
+ struct ixgbe_hw *hw = &adapter->hw;
+ struct ixgbe_hw_stats *hwstats = &adapter->stats;
+ u32 data = 0;
+ u32 xoff[8] = {0};
+ int i;
+
+ if ((hw->fc.current_mode == ixgbe_fc_full) ||
+ (hw->fc.current_mode == ixgbe_fc_rx_pause)) {
+ switch (hw->mac.type) {
case ixgbe_mac_82598EB:
- tc = reg_idx >> 2;
- txoff = IXGBE_TFCS_TXOFF0;
+ data = IXGBE_READ_REG(hw, IXGBE_LXOFFRXC);
break;
- case ixgbe_mac_82599EB:
- tc = 0;
- txoff = IXGBE_TFCS_TXOFF;
- if (dcb_i == 8) {
- /* TC0, TC1 */
- tc = reg_idx >> 5;
- if (tc == 2) /* TC2, TC3 */
- tc += (reg_idx - 64) >> 4;
- else if (tc == 3) /* TC4, TC5, TC6, TC7 */
- tc += 1 + ((reg_idx - 96) >> 3);
- } else if (dcb_i == 4) {
- /* TC0, TC1 */
- tc = reg_idx >> 6;
- if (tc == 1) {
- tc += (reg_idx - 64) >> 5;
- if (tc == 2) /* TC2, TC3 */
- tc += (reg_idx - 96) >> 4;
- }
- }
+ default:
+ data = IXGBE_READ_REG(hw, IXGBE_LXOFFRXCNT);
+ }
+ hwstats->lxoffrxc += data;
+
+ /* refill credits (no tx hang) if we received xoff */
+ if (!data)
+ return;
+
+ for (i = 0; i < adapter->num_tx_queues; i++)
+ clear_bit(__IXGBE_HANG_CHECK_ARMED,
+ &adapter->tx_ring[i]->state);
+ return;
+ } else if (!(adapter->dcb_cfg.pfc_mode_enable))
+ return;
+
+ /* update stats for each tc, only valid with PFC enabled */
+ for (i = 0; i < MAX_TX_PACKET_BUFFERS; i++) {
+ switch (hw->mac.type) {
+ case ixgbe_mac_82598EB:
+ xoff[i] = IXGBE_READ_REG(hw, IXGBE_PXOFFRXC(i));
break;
default:
- tc = 0;
+ xoff[i] = IXGBE_READ_REG(hw, IXGBE_PXOFFRXCNT(i));
}
- txoff <<= tc;
+ hwstats->pxoffrxc[i] += xoff[i];
+ }
+
+ /* disarm tx queues that have received xoff frames */
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ struct ixgbe_ring *tx_ring = adapter->tx_ring[i];
+ u32 tc = ixgbe_dcb_txq_to_tc(adapter, tx_ring->reg_idx);
+
+ if (xoff[tc])
+ clear_bit(__IXGBE_HANG_CHECK_ARMED, &tx_ring->state);
}
-#endif
- return IXGBE_READ_REG(&adapter->hw, IXGBE_TFCS) & txoff;
}
-static inline bool ixgbe_check_tx_hang(struct ixgbe_adapter *adapter,
- struct ixgbe_ring *tx_ring,
- unsigned int eop)
+static u64 ixgbe_get_tx_completed(struct ixgbe_ring *ring)
{
+ return ring->tx_stats.completed;
+}
+
+static u64 ixgbe_get_tx_pending(struct ixgbe_ring *ring)
+{
+ struct ixgbe_adapter *adapter = netdev_priv(ring->netdev);
struct ixgbe_hw *hw = &adapter->hw;
- /* Detect a transmit hang in hardware, this serializes the
- * check with the clearing of time_stamp and movement of eop */
- adapter->detect_tx_hung = false;
- if (tx_ring->tx_buffer_info[eop].time_stamp &&
- time_after(jiffies, tx_ring->tx_buffer_info[eop].time_stamp + HZ) &&
- ixgbe_tx_xon_state(adapter, tx_ring)) {
- /* detected Tx unit hang */
- union ixgbe_adv_tx_desc *tx_desc;
- tx_desc = IXGBE_TX_DESC_ADV(tx_ring, eop);
- e_err(drv, "Detected Tx Unit Hang\n"
- " Tx Queue <%d>\n"
- " TDH, TDT <%x>, <%x>\n"
- " next_to_use <%x>\n"
- " next_to_clean <%x>\n"
- "tx_buffer_info[next_to_clean]\n"
- " time_stamp <%lx>\n"
- " jiffies <%lx>\n",
- tx_ring->queue_index,
- IXGBE_READ_REG(hw, tx_ring->head),
- IXGBE_READ_REG(hw, tx_ring->tail),
- tx_ring->next_to_use, eop,
- tx_ring->tx_buffer_info[eop].time_stamp, jiffies);
- return true;
+ u32 head = IXGBE_READ_REG(hw, IXGBE_TDH(ring->reg_idx));
+ u32 tail = IXGBE_READ_REG(hw, IXGBE_TDT(ring->reg_idx));
+
+ if (head != tail)
+ return (head < tail) ?
+ tail - head : (tail + ring->count - head);
+
+ return 0;
+}
+
+static inline bool ixgbe_check_tx_hang(struct ixgbe_ring *tx_ring)
+{
+ u32 tx_done = ixgbe_get_tx_completed(tx_ring);
+ u32 tx_done_old = tx_ring->tx_stats.tx_done_old;
+ u32 tx_pending = ixgbe_get_tx_pending(tx_ring);
+ bool ret = false;
+
+ clear_check_for_tx_hang(tx_ring);
+
+ /*
+ * Check for a hung queue, but be thorough. This verifies
+ * that a transmit has been completed since the previous
+ * check AND there is at least one packet pending. The
+ * ARMED bit is set to indicate a potential hang. The
+ * bit is cleared if a pause frame is received to remove
+ * false hang detection due to PFC or 802.3x frames. By
+ * requiring this to fail twice we avoid races with
+ * pfc clearing the ARMED bit and conditions where we
+ * run the check_tx_hang logic with a transmit completion
+ * pending but without time to complete it yet.
+ */
+ if ((tx_done_old == tx_done) && tx_pending) {
+ /* make sure it is true for two checks in a row */
+ ret = test_and_set_bit(__IXGBE_HANG_CHECK_ARMED,
+ &tx_ring->state);
+ } else {
+ /* update completed stats and continue */
+ tx_ring->tx_stats.tx_done_old = tx_done;
+ /* reset the countdown */
+ clear_bit(__IXGBE_HANG_CHECK_ARMED, &tx_ring->state);
}
- return false;
+ return ret;
}
#define IXGBE_MAX_TXD_PWR 14
@@ -734,11 +817,10 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
struct ixgbe_ring *tx_ring)
{
struct ixgbe_adapter *adapter = q_vector->adapter;
- struct net_device *netdev = adapter->netdev;
union ixgbe_adv_tx_desc *tx_desc, *eop_desc;
struct ixgbe_tx_buffer *tx_buffer_info;
- unsigned int i, eop, count = 0;
unsigned int total_bytes = 0, total_packets = 0;
+ u16 i, eop, count = 0;
i = tx_ring->next_to_clean;
eop = tx_ring->tx_buffer_info[i].next_to_watch;
@@ -749,148 +831,182 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
bool cleaned = false;
rmb(); /* read buffer_info after eop_desc */
for ( ; !cleaned; count++) {
- struct sk_buff *skb;
tx_desc = IXGBE_TX_DESC_ADV(tx_ring, i);
tx_buffer_info = &tx_ring->tx_buffer_info[i];
- cleaned = (i == eop);
- skb = tx_buffer_info->skb;
-
- if (cleaned && skb) {
- unsigned int segs, bytecount;
- unsigned int hlen = skb_headlen(skb);
-
- /* gso_segs is currently only valid for tcp */
- segs = skb_shinfo(skb)->gso_segs ?: 1;
-#ifdef IXGBE_FCOE
- /* adjust for FCoE Sequence Offload */
- if ((adapter->flags & IXGBE_FLAG_FCOE_ENABLED)
- && skb_is_gso(skb)
- && vlan_get_protocol(skb) ==
- htons(ETH_P_FCOE)) {
- hlen = skb_transport_offset(skb) +
- sizeof(struct fc_frame_header) +
- sizeof(struct fcoe_crc_eof);
- segs = DIV_ROUND_UP(skb->len - hlen,
- skb_shinfo(skb)->gso_size);
- }
-#endif /* IXGBE_FCOE */
- /* multiply data chunks by size of headers */
- bytecount = ((segs - 1) * hlen) + skb->len;
- total_packets += segs;
- total_bytes += bytecount;
- }
-
- ixgbe_unmap_and_free_tx_resource(adapter,
- tx_buffer_info);
tx_desc->wb.status = 0;
+ cleaned = (i == eop);
i++;
if (i == tx_ring->count)
i = 0;
+
+ if (cleaned && tx_buffer_info->skb) {
+ total_bytes += tx_buffer_info->bytecount;
+ total_packets += tx_buffer_info->gso_segs;
+ }
+
+ ixgbe_unmap_and_free_tx_resource(tx_ring,
+ tx_buffer_info);
}
+ tx_ring->tx_stats.completed++;
eop = tx_ring->tx_buffer_info[i].next_to_watch;
eop_desc = IXGBE_TX_DESC_ADV(tx_ring, eop);
}
tx_ring->next_to_clean = i;
+ tx_ring->total_bytes += total_bytes;
+ tx_ring->total_packets += total_packets;
+ u64_stats_update_begin(&tx_ring->syncp);
+ tx_ring->stats.packets += total_packets;
+ tx_ring->stats.bytes += total_bytes;
+ u64_stats_update_end(&tx_ring->syncp);
+
+ if (check_for_tx_hang(tx_ring) && ixgbe_check_tx_hang(tx_ring)) {
+ /* schedule immediate reset if we believe we hung */
+ struct ixgbe_hw *hw = &adapter->hw;
+ tx_desc = IXGBE_TX_DESC_ADV(tx_ring, eop);
+ e_err(drv, "Detected Tx Unit Hang\n"
+ " Tx Queue <%d>\n"
+ " TDH, TDT <%x>, <%x>\n"
+ " next_to_use <%x>\n"
+ " next_to_clean <%x>\n"
+ "tx_buffer_info[next_to_clean]\n"
+ " time_stamp <%lx>\n"
+ " jiffies <%lx>\n",
+ tx_ring->queue_index,
+ IXGBE_READ_REG(hw, IXGBE_TDH(tx_ring->reg_idx)),
+ IXGBE_READ_REG(hw, IXGBE_TDT(tx_ring->reg_idx)),
+ tx_ring->next_to_use, eop,
+ tx_ring->tx_buffer_info[eop].time_stamp, jiffies);
+
+ netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
+
+ e_info(probe,
+ "tx hang %d detected on queue %d, resetting adapter\n",
+ adapter->tx_timeout_count + 1, tx_ring->queue_index);
+
+ /* schedule immediate reset if we believe we hung */
+ ixgbe_tx_timeout(adapter->netdev);
+
+ /* the adapter is about to reset, no point in enabling stuff */
+ return true;
+ }
#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2)
- if (unlikely(count && netif_carrier_ok(netdev) &&
+ if (unlikely(count && netif_carrier_ok(tx_ring->netdev) &&
(IXGBE_DESC_UNUSED(tx_ring) >= TX_WAKE_THRESHOLD))) {
/* Make sure that anybody stopping the queue after this
* sees the new next_to_clean.
*/
smp_mb();
- if (__netif_subqueue_stopped(netdev, tx_ring->queue_index) &&
+ if (__netif_subqueue_stopped(tx_ring->netdev, tx_ring->queue_index) &&
!test_bit(__IXGBE_DOWN, &adapter->state)) {
- netif_wake_subqueue(netdev, tx_ring->queue_index);
- ++tx_ring->restart_queue;
- }
- }
-
- if (adapter->detect_tx_hung) {
- if (ixgbe_check_tx_hang(adapter, tx_ring, i)) {
- /* schedule immediate reset if we believe we hung */
- e_info(probe, "tx hang %d detected, resetting "
- "adapter\n", adapter->tx_timeout_count + 1);
- ixgbe_tx_timeout(adapter->netdev);
+ netif_wake_subqueue(tx_ring->netdev, tx_ring->queue_index);
+ ++tx_ring->tx_stats.restart_queue;
}
}
- /* re-arm the interrupt */
- if (count >= tx_ring->work_limit)
- ixgbe_irq_rearm_queues(adapter, ((u64)1 << q_vector->v_idx));
-
- tx_ring->total_bytes += total_bytes;
- tx_ring->total_packets += total_packets;
- u64_stats_update_begin(&tx_ring->syncp);
- tx_ring->stats.packets += total_packets;
- tx_ring->stats.bytes += total_bytes;
- u64_stats_update_end(&tx_ring->syncp);
return count < tx_ring->work_limit;
}
#ifdef CONFIG_IXGBE_DCA
static void ixgbe_update_rx_dca(struct ixgbe_adapter *adapter,
- struct ixgbe_ring *rx_ring)
+ struct ixgbe_ring *rx_ring,
+ int cpu)
{
+ struct ixgbe_hw *hw = &adapter->hw;
u32 rxctrl;
- int cpu = get_cpu();
- int q = rx_ring->reg_idx;
-
- if (rx_ring->cpu != cpu) {
- rxctrl = IXGBE_READ_REG(&adapter->hw, IXGBE_DCA_RXCTRL(q));
- if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
- rxctrl &= ~IXGBE_DCA_RXCTRL_CPUID_MASK;
- rxctrl |= dca3_get_tag(&adapter->pdev->dev, cpu);
- } else if (adapter->hw.mac.type == ixgbe_mac_82599EB) {
- rxctrl &= ~IXGBE_DCA_RXCTRL_CPUID_MASK_82599;
- rxctrl |= (dca3_get_tag(&adapter->pdev->dev, cpu) <<
- IXGBE_DCA_RXCTRL_CPUID_SHIFT_82599);
- }
- rxctrl |= IXGBE_DCA_RXCTRL_DESC_DCA_EN;
- rxctrl |= IXGBE_DCA_RXCTRL_HEAD_DCA_EN;
- rxctrl &= ~(IXGBE_DCA_RXCTRL_DESC_RRO_EN);
- rxctrl &= ~(IXGBE_DCA_RXCTRL_DESC_WRO_EN |
- IXGBE_DCA_RXCTRL_DESC_HSRO_EN);
- IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_RXCTRL(q), rxctrl);
- rx_ring->cpu = cpu;
+ u8 reg_idx = rx_ring->reg_idx;
+
+ rxctrl = IXGBE_READ_REG(hw, IXGBE_DCA_RXCTRL(reg_idx));
+ switch (hw->mac.type) {
+ case ixgbe_mac_82598EB:
+ rxctrl &= ~IXGBE_DCA_RXCTRL_CPUID_MASK;
+ rxctrl |= dca3_get_tag(&adapter->pdev->dev, cpu);
+ break;
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
+ rxctrl &= ~IXGBE_DCA_RXCTRL_CPUID_MASK_82599;
+ rxctrl |= (dca3_get_tag(&adapter->pdev->dev, cpu) <<
+ IXGBE_DCA_RXCTRL_CPUID_SHIFT_82599);
+ break;
+ default:
+ break;
}
- put_cpu();
+ rxctrl |= IXGBE_DCA_RXCTRL_DESC_DCA_EN;
+ rxctrl |= IXGBE_DCA_RXCTRL_HEAD_DCA_EN;
+ rxctrl &= ~(IXGBE_DCA_RXCTRL_DESC_RRO_EN);
+ rxctrl &= ~(IXGBE_DCA_RXCTRL_DESC_WRO_EN |
+ IXGBE_DCA_RXCTRL_DESC_HSRO_EN);
+ IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(reg_idx), rxctrl);
}
static void ixgbe_update_tx_dca(struct ixgbe_adapter *adapter,
- struct ixgbe_ring *tx_ring)
+ struct ixgbe_ring *tx_ring,
+ int cpu)
{
+ struct ixgbe_hw *hw = &adapter->hw;
u32 txctrl;
+ u8 reg_idx = tx_ring->reg_idx;
+
+ switch (hw->mac.type) {
+ case ixgbe_mac_82598EB:
+ txctrl = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL(reg_idx));
+ txctrl &= ~IXGBE_DCA_TXCTRL_CPUID_MASK;
+ txctrl |= dca3_get_tag(&adapter->pdev->dev, cpu);
+ txctrl |= IXGBE_DCA_TXCTRL_DESC_DCA_EN;
+ txctrl &= ~IXGBE_DCA_TXCTRL_TX_WB_RO_EN;
+ IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL(reg_idx), txctrl);
+ break;
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
+ txctrl = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL_82599(reg_idx));
+ txctrl &= ~IXGBE_DCA_TXCTRL_CPUID_MASK_82599;
+ txctrl |= (dca3_get_tag(&adapter->pdev->dev, cpu) <<
+ IXGBE_DCA_TXCTRL_CPUID_SHIFT_82599);
+ txctrl |= IXGBE_DCA_TXCTRL_DESC_DCA_EN;
+ txctrl &= ~IXGBE_DCA_TXCTRL_TX_WB_RO_EN;
+ IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL_82599(reg_idx), txctrl);
+ break;
+ default:
+ break;
+ }
+}
+
+static void ixgbe_update_dca(struct ixgbe_q_vector *q_vector)
+{
+ struct ixgbe_adapter *adapter = q_vector->adapter;
int cpu = get_cpu();
- int q = tx_ring->reg_idx;
- struct ixgbe_hw *hw = &adapter->hw;
+ long r_idx;
+ int i;
- if (tx_ring->cpu != cpu) {
- if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
- txctrl = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL(q));
- txctrl &= ~IXGBE_DCA_TXCTRL_CPUID_MASK;
- txctrl |= dca3_get_tag(&adapter->pdev->dev, cpu);
- txctrl |= IXGBE_DCA_TXCTRL_DESC_DCA_EN;
- IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL(q), txctrl);
- } else if (adapter->hw.mac.type == ixgbe_mac_82599EB) {
- txctrl = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL_82599(q));
- txctrl &= ~IXGBE_DCA_TXCTRL_CPUID_MASK_82599;
- txctrl |= (dca3_get_tag(&adapter->pdev->dev, cpu) <<
- IXGBE_DCA_TXCTRL_CPUID_SHIFT_82599);
- txctrl |= IXGBE_DCA_TXCTRL_DESC_DCA_EN;
- IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL_82599(q), txctrl);
- }
- tx_ring->cpu = cpu;
+ if (q_vector->cpu == cpu)
+ goto out_no_update;
+
+ r_idx = find_first_bit(q_vector->txr_idx, adapter->num_tx_queues);
+ for (i = 0; i < q_vector->txr_count; i++) {
+ ixgbe_update_tx_dca(adapter, adapter->tx_ring[r_idx], cpu);
+ r_idx = find_next_bit(q_vector->txr_idx, adapter->num_tx_queues,
+ r_idx + 1);
+ }
+
+ r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues);
+ for (i = 0; i < q_vector->rxr_count; i++) {
+ ixgbe_update_rx_dca(adapter, adapter->rx_ring[r_idx], cpu);
+ r_idx = find_next_bit(q_vector->rxr_idx, adapter->num_rx_queues,
+ r_idx + 1);
}
+
+ q_vector->cpu = cpu;
+out_no_update:
put_cpu();
}
static void ixgbe_setup_dca(struct ixgbe_adapter *adapter)
{
+ int num_q_vectors;
int i;
if (!(adapter->flags & IXGBE_FLAG_DCA_ENABLED))
@@ -899,22 +1015,25 @@ static void ixgbe_setup_dca(struct ixgbe_adapter *adapter)
/* always use CB2 mode, difference is masked in the CB driver */
IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL, 2);
- for (i = 0; i < adapter->num_tx_queues; i++) {
- adapter->tx_ring[i]->cpu = -1;
- ixgbe_update_tx_dca(adapter, adapter->tx_ring[i]);
- }
- for (i = 0; i < adapter->num_rx_queues; i++) {
- adapter->rx_ring[i]->cpu = -1;
- ixgbe_update_rx_dca(adapter, adapter->rx_ring[i]);
+ if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED)
+ num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
+ else
+ num_q_vectors = 1;
+
+ for (i = 0; i < num_q_vectors; i++) {
+ adapter->q_vector[i]->cpu = -1;
+ ixgbe_update_dca(adapter->q_vector[i]);
}
}
static int __ixgbe_notify_dca(struct device *dev, void *data)
{
- struct net_device *netdev = dev_get_drvdata(dev);
- struct ixgbe_adapter *adapter = netdev_priv(netdev);
+ struct ixgbe_adapter *adapter = dev_get_drvdata(dev);
unsigned long event = *(unsigned long *)data;
+ if (!(adapter->flags & IXGBE_FLAG_DCA_ENABLED))
+ return 0;
+
switch (event) {
case DCA_PROVIDER_ADD:
/* if we're already enabled, don't do it again */
@@ -1013,8 +1132,7 @@ static inline void ixgbe_rx_checksum(struct ixgbe_adapter *adapter,
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
-static inline void ixgbe_release_rx_desc(struct ixgbe_hw *hw,
- struct ixgbe_ring *rx_ring, u32 val)
+static inline void ixgbe_release_rx_desc(struct ixgbe_ring *rx_ring, u32 val)
{
/*
* Force memory writes to complete before letting h/w
@@ -1023,72 +1141,81 @@ static inline void ixgbe_release_rx_desc(struct ixgbe_hw *hw,
* such as IA-64).
*/
wmb();
- IXGBE_WRITE_REG(hw, IXGBE_RDT(rx_ring->reg_idx), val);
+ writel(val, rx_ring->tail);
}
/**
* ixgbe_alloc_rx_buffers - Replace used receive buffers; packet split
- * @adapter: address of board private structure
+ * @rx_ring: ring to place buffers on
+ * @cleaned_count: number of buffers to replace
**/
-void ixgbe_alloc_rx_buffers(struct ixgbe_adapter *adapter,
- struct ixgbe_ring *rx_ring,
- int cleaned_count)
+void ixgbe_alloc_rx_buffers(struct ixgbe_ring *rx_ring, u16 cleaned_count)
{
- struct net_device *netdev = adapter->netdev;
- struct pci_dev *pdev = adapter->pdev;
union ixgbe_adv_rx_desc *rx_desc;
struct ixgbe_rx_buffer *bi;
- unsigned int i;
- unsigned int bufsz = rx_ring->rx_buf_len;
+ struct sk_buff *skb;
+ u16 i = rx_ring->next_to_use;
- i = rx_ring->next_to_use;
- bi = &rx_ring->rx_buffer_info[i];
+ /* do nothing if no valid netdev defined */
+ if (!rx_ring->netdev)
+ return;
while (cleaned_count--) {
rx_desc = IXGBE_RX_DESC_ADV(rx_ring, i);
+ bi = &rx_ring->rx_buffer_info[i];
+ skb = bi->skb;
- if (!bi->page_dma &&
- (rx_ring->flags & IXGBE_RING_RX_PS_ENABLED)) {
- if (!bi->page) {
- bi->page = netdev_alloc_page(netdev);
- if (!bi->page) {
- adapter->alloc_rx_page_failed++;
- goto no_buffers;
- }
- bi->page_offset = 0;
- } else {
- /* use a half page if we're re-using */
- bi->page_offset ^= (PAGE_SIZE / 2);
- }
-
- bi->page_dma = dma_map_page(&pdev->dev, bi->page,
- bi->page_offset,
- (PAGE_SIZE / 2),
- DMA_FROM_DEVICE);
- }
-
- if (!bi->skb) {
- struct sk_buff *skb = netdev_alloc_skb_ip_align(netdev,
- bufsz);
- bi->skb = skb;
-
+ if (!skb) {
+ skb = netdev_alloc_skb_ip_align(rx_ring->netdev,
+ rx_ring->rx_buf_len);
if (!skb) {
- adapter->alloc_rx_buff_failed++;
+ rx_ring->rx_stats.alloc_rx_buff_failed++;
goto no_buffers;
}
/* initialize queue mapping */
skb_record_rx_queue(skb, rx_ring->queue_index);
+ bi->skb = skb;
}
if (!bi->dma) {
- bi->dma = dma_map_single(&pdev->dev,
- bi->skb->data,
+ bi->dma = dma_map_single(rx_ring->dev,
+ skb->data,
rx_ring->rx_buf_len,
DMA_FROM_DEVICE);
+ if (dma_mapping_error(rx_ring->dev, bi->dma)) {
+ rx_ring->rx_stats.alloc_rx_buff_failed++;
+ bi->dma = 0;
+ goto no_buffers;
+ }
}
- /* Refresh the desc even if buffer_addrs didn't change because
- * each write-back erases this info. */
- if (rx_ring->flags & IXGBE_RING_RX_PS_ENABLED) {
+
+ if (ring_is_ps_enabled(rx_ring)) {
+ if (!bi->page) {
+ bi->page = netdev_alloc_page(rx_ring->netdev);
+ if (!bi->page) {
+ rx_ring->rx_stats.alloc_rx_page_failed++;
+ goto no_buffers;
+ }
+ }
+
+ if (!bi->page_dma) {
+ /* use a half page if we're re-using */
+ bi->page_offset ^= PAGE_SIZE / 2;
+ bi->page_dma = dma_map_page(rx_ring->dev,
+ bi->page,
+ bi->page_offset,
+ PAGE_SIZE / 2,
+ DMA_FROM_DEVICE);
+ if (dma_mapping_error(rx_ring->dev,
+ bi->page_dma)) {
+ rx_ring->rx_stats.alloc_rx_page_failed++;
+ bi->page_dma = 0;
+ goto no_buffers;
+ }
+ }
+
+ /* Refresh the desc even if buffer_addrs didn't change
+ * because each write-back erases this info. */
rx_desc->read.pkt_addr = cpu_to_le64(bi->page_dma);
rx_desc->read.hdr_addr = cpu_to_le64(bi->dma);
} else {
@@ -1099,56 +1226,48 @@ void ixgbe_alloc_rx_buffers(struct ixgbe_adapter *adapter,
i++;
if (i == rx_ring->count)
i = 0;
- bi = &rx_ring->rx_buffer_info[i];
}
no_buffers:
if (rx_ring->next_to_use != i) {
rx_ring->next_to_use = i;
- if (i-- == 0)
- i = (rx_ring->count - 1);
-
- ixgbe_release_rx_desc(&adapter->hw, rx_ring, i);
+ ixgbe_release_rx_desc(rx_ring, i);
}
}
-static inline u16 ixgbe_get_hdr_info(union ixgbe_adv_rx_desc *rx_desc)
+static inline u16 ixgbe_get_hlen(union ixgbe_adv_rx_desc *rx_desc)
{
- return rx_desc->wb.lower.lo_dword.hs_rss.hdr_info;
-}
-
-static inline u16 ixgbe_get_pkt_info(union ixgbe_adv_rx_desc *rx_desc)
-{
- return rx_desc->wb.lower.lo_dword.hs_rss.pkt_info;
-}
-
-static inline u32 ixgbe_get_rsc_count(union ixgbe_adv_rx_desc *rx_desc)
-{
- return (le32_to_cpu(rx_desc->wb.lower.lo_dword.data) &
- IXGBE_RXDADV_RSCCNT_MASK) >>
- IXGBE_RXDADV_RSCCNT_SHIFT;
+ /* HW will not DMA in data larger than the given buffer, even if it
+ * parses the (NFS, of course) header to be larger. In that case, it
+ * fills the header buffer and spills the rest into the page.
+ */
+ u16 hdr_info = le16_to_cpu(rx_desc->wb.lower.lo_dword.hs_rss.hdr_info);
+ u16 hlen = (hdr_info & IXGBE_RXDADV_HDRBUFLEN_MASK) >>
+ IXGBE_RXDADV_HDRBUFLEN_SHIFT;
+ if (hlen > IXGBE_RX_HDR_SIZE)
+ hlen = IXGBE_RX_HDR_SIZE;
+ return hlen;
}
/**
* ixgbe_transform_rsc_queue - change rsc queue into a full packet
* @skb: pointer to the last skb in the rsc queue
- * @count: pointer to number of packets coalesced in this context
*
* This function changes a queue full of hw rsc buffers into a completed
* packet. It uses the ->prev pointers to find the first packet and then
* turns it into the frag list owner.
**/
-static inline struct sk_buff *ixgbe_transform_rsc_queue(struct sk_buff *skb,
- u64 *count)
+static inline struct sk_buff *ixgbe_transform_rsc_queue(struct sk_buff *skb)
{
unsigned int frag_list_size = 0;
+ unsigned int skb_cnt = 1;
while (skb->prev) {
struct sk_buff *prev = skb->prev;
frag_list_size += skb->len;
skb->prev = NULL;
skb = prev;
- *count += 1;
+ skb_cnt++;
}
skb_shinfo(skb)->frag_list = skb->next;
@@ -1156,68 +1275,59 @@ static inline struct sk_buff *ixgbe_transform_rsc_queue(struct sk_buff *skb,
skb->len += frag_list_size;
skb->data_len += frag_list_size;
skb->truesize += frag_list_size;
+ IXGBE_RSC_CB(skb)->skb_cnt = skb_cnt;
+
return skb;
}
-struct ixgbe_rsc_cb {
- dma_addr_t dma;
- bool delay_unmap;
-};
-
-#define IXGBE_RSC_CB(skb) ((struct ixgbe_rsc_cb *)(skb)->cb)
+static inline bool ixgbe_get_rsc_state(union ixgbe_adv_rx_desc *rx_desc)
+{
+ return !!(le32_to_cpu(rx_desc->wb.lower.lo_dword.data) &
+ IXGBE_RXDADV_RSCCNT_MASK);
+}
-static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
+static void ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
struct ixgbe_ring *rx_ring,
int *work_done, int work_to_do)
{
struct ixgbe_adapter *adapter = q_vector->adapter;
- struct pci_dev *pdev = adapter->pdev;
union ixgbe_adv_rx_desc *rx_desc, *next_rxd;
struct ixgbe_rx_buffer *rx_buffer_info, *next_buffer;
struct sk_buff *skb;
- unsigned int i, rsc_count = 0;
- u32 len, staterr;
- u16 hdr_info;
- bool cleaned = false;
- int cleaned_count = 0;
unsigned int total_rx_bytes = 0, total_rx_packets = 0;
+ const int current_node = numa_node_id();
#ifdef IXGBE_FCOE
int ddp_bytes = 0;
#endif /* IXGBE_FCOE */
+ u32 staterr;
+ u16 i;
+ u16 cleaned_count = 0;
+ bool pkt_is_rsc = false;
i = rx_ring->next_to_clean;
rx_desc = IXGBE_RX_DESC_ADV(rx_ring, i);
staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
- rx_buffer_info = &rx_ring->rx_buffer_info[i];
while (staterr & IXGBE_RXD_STAT_DD) {
u32 upper_len = 0;
- if (*work_done >= work_to_do)
- break;
- (*work_done)++;
rmb(); /* read descriptor and rx_buffer_info after status DD */
- if (rx_ring->flags & IXGBE_RING_RX_PS_ENABLED) {
- hdr_info = le16_to_cpu(ixgbe_get_hdr_info(rx_desc));
- len = (hdr_info & IXGBE_RXDADV_HDRBUFLEN_MASK) >>
- IXGBE_RXDADV_HDRBUFLEN_SHIFT;
- upper_len = le16_to_cpu(rx_desc->wb.upper.length);
- if ((len > IXGBE_RX_HDR_SIZE) ||
- (upper_len && !(hdr_info & IXGBE_RXDADV_SPH)))
- len = IXGBE_RX_HDR_SIZE;
- } else {
- len = le16_to_cpu(rx_desc->wb.upper.length);
- }
- cleaned = true;
+ rx_buffer_info = &rx_ring->rx_buffer_info[i];
+
skb = rx_buffer_info->skb;
- prefetch(skb->data);
rx_buffer_info->skb = NULL;
+ prefetch(skb->data);
+
+ if (ring_is_rsc_enabled(rx_ring))
+ pkt_is_rsc = ixgbe_get_rsc_state(rx_desc);
+ /* if this is a skb from previous receive DMA will be 0 */
if (rx_buffer_info->dma) {
- if ((adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) &&
- (!(staterr & IXGBE_RXD_STAT_EOP)) &&
- (!(skb->prev))) {
+ u16 hlen;
+ if (pkt_is_rsc &&
+ !(staterr & IXGBE_RXD_STAT_EOP) &&
+ !skb->prev) {
/*
* When HWRSC is enabled, delay unmapping
* of the first packet. It carries the
@@ -1228,29 +1338,42 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
IXGBE_RSC_CB(skb)->delay_unmap = true;
IXGBE_RSC_CB(skb)->dma = rx_buffer_info->dma;
} else {
- dma_unmap_single(&pdev->dev,
+ dma_unmap_single(rx_ring->dev,
rx_buffer_info->dma,
rx_ring->rx_buf_len,
DMA_FROM_DEVICE);
}
rx_buffer_info->dma = 0;
- skb_put(skb, len);
+
+ if (ring_is_ps_enabled(rx_ring)) {
+ hlen = ixgbe_get_hlen(rx_desc);
+ upper_len = le16_to_cpu(rx_desc->wb.upper.length);
+ } else {
+ hlen = le16_to_cpu(rx_desc->wb.upper.length);
+ }
+
+ skb_put(skb, hlen);
+ } else {
+ /* assume packet split since header is unmapped */
+ upper_len = le16_to_cpu(rx_desc->wb.upper.length);
}
if (upper_len) {
- dma_unmap_page(&pdev->dev, rx_buffer_info->page_dma,
- PAGE_SIZE / 2, DMA_FROM_DEVICE);
+ dma_unmap_page(rx_ring->dev,
+ rx_buffer_info->page_dma,
+ PAGE_SIZE / 2,
+ DMA_FROM_DEVICE);
rx_buffer_info->page_dma = 0;
skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags,
rx_buffer_info->page,
rx_buffer_info->page_offset,
upper_len);
- if ((rx_ring->rx_buf_len > (PAGE_SIZE / 2)) ||
- (page_count(rx_buffer_info->page) != 1))
- rx_buffer_info->page = NULL;
- else
+ if ((page_count(rx_buffer_info->page) == 1) &&
+ (page_to_nid(rx_buffer_info->page) == current_node))
get_page(rx_buffer_info->page);
+ else
+ rx_buffer_info->page = NULL;
skb->len += upper_len;
skb->data_len += upper_len;
@@ -1265,10 +1388,7 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
prefetch(next_rxd);
cleaned_count++;
- if (adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE)
- rsc_count = ixgbe_get_rsc_count(rx_desc);
-
- if (rsc_count) {
+ if (pkt_is_rsc) {
u32 nextp = (staterr & IXGBE_RXDADV_NEXTP_MASK) >>
IXGBE_RXDADV_NEXTP_SHIFT;
next_buffer = &rx_ring->rx_buffer_info[nextp];
@@ -1276,32 +1396,8 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
next_buffer = &rx_ring->rx_buffer_info[i];
}
- if (staterr & IXGBE_RXD_STAT_EOP) {
- if (skb->prev)
- skb = ixgbe_transform_rsc_queue(skb,
- &(rx_ring->rsc_count));
- if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) {
- if (IXGBE_RSC_CB(skb)->delay_unmap) {
- dma_unmap_single(&pdev->dev,
- IXGBE_RSC_CB(skb)->dma,
- rx_ring->rx_buf_len,
- DMA_FROM_DEVICE);
- IXGBE_RSC_CB(skb)->dma = 0;
- IXGBE_RSC_CB(skb)->delay_unmap = false;
- }
- if (rx_ring->flags & IXGBE_RING_RX_PS_ENABLED)
- rx_ring->rsc_count +=
- skb_shinfo(skb)->nr_frags;
- else
- rx_ring->rsc_count++;
- rx_ring->rsc_flush++;
- }
- u64_stats_update_begin(&rx_ring->syncp);
- rx_ring->stats.packets++;
- rx_ring->stats.bytes += skb->len;
- u64_stats_update_end(&rx_ring->syncp);
- } else {
- if (rx_ring->flags & IXGBE_RING_RX_PS_ENABLED) {
+ if (!(staterr & IXGBE_RXD_STAT_EOP)) {
+ if (ring_is_ps_enabled(rx_ring)) {
rx_buffer_info->skb = next_buffer->skb;
rx_buffer_info->dma = next_buffer->dma;
next_buffer->skb = skb;
@@ -1310,12 +1406,45 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
skb->next = next_buffer->skb;
skb->next->prev = skb;
}
- rx_ring->non_eop_descs++;
+ rx_ring->rx_stats.non_eop_descs++;
goto next_desc;
}
+ if (skb->prev) {
+ skb = ixgbe_transform_rsc_queue(skb);
+ /* if we got here without RSC the packet is invalid */
+ if (!pkt_is_rsc) {
+ __pskb_trim(skb, 0);
+ rx_buffer_info->skb = skb;
+ goto next_desc;
+ }
+ }
+
+ if (ring_is_rsc_enabled(rx_ring)) {
+ if (IXGBE_RSC_CB(skb)->delay_unmap) {
+ dma_unmap_single(rx_ring->dev,
+ IXGBE_RSC_CB(skb)->dma,
+ rx_ring->rx_buf_len,
+ DMA_FROM_DEVICE);
+ IXGBE_RSC_CB(skb)->dma = 0;
+ IXGBE_RSC_CB(skb)->delay_unmap = false;
+ }
+ }
+ if (pkt_is_rsc) {
+ if (ring_is_ps_enabled(rx_ring))
+ rx_ring->rx_stats.rsc_count +=
+ skb_shinfo(skb)->nr_frags;
+ else
+ rx_ring->rx_stats.rsc_count +=
+ IXGBE_RSC_CB(skb)->skb_cnt;
+ rx_ring->rx_stats.rsc_flush++;
+ }
+
+ /* ERR_MASK will only have valid bits if EOP set */
if (staterr & IXGBE_RXDADV_ERR_FRAME_ERR_MASK) {
- dev_kfree_skb_irq(skb);
+ /* trim packet back to size 0 and recycle it */
+ __pskb_trim(skb, 0);
+ rx_buffer_info->skb = skb;
goto next_desc;
}
@@ -1325,7 +1454,7 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
total_rx_bytes += skb->len;
total_rx_packets++;
- skb->protocol = eth_type_trans(skb, adapter->netdev);
+ skb->protocol = eth_type_trans(skb, rx_ring->netdev);
#ifdef IXGBE_FCOE
/* if ddp, not passing to ULD unless for FCP_RSP or error */
if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) {
@@ -1339,16 +1468,18 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
next_desc:
rx_desc->wb.upper.status_error = 0;
+ (*work_done)++;
+ if (*work_done >= work_to_do)
+ break;
+
/* return some buffers to hardware, one at a time is too slow */
if (cleaned_count >= IXGBE_RX_BUFFER_WRITE) {
- ixgbe_alloc_rx_buffers(adapter, rx_ring, cleaned_count);
+ ixgbe_alloc_rx_buffers(rx_ring, cleaned_count);
cleaned_count = 0;
}
/* use prefetched values */
rx_desc = next_rxd;
- rx_buffer_info = &rx_ring->rx_buffer_info[i];
-
staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
}
@@ -1356,14 +1487,14 @@ next_desc:
cleaned_count = IXGBE_DESC_UNUSED(rx_ring);
if (cleaned_count)
- ixgbe_alloc_rx_buffers(adapter, rx_ring, cleaned_count);
+ ixgbe_alloc_rx_buffers(rx_ring, cleaned_count);
#ifdef IXGBE_FCOE
/* include DDPed FCoE data */
if (ddp_bytes > 0) {
unsigned int mss;
- mss = adapter->netdev->mtu - sizeof(struct fcoe_hdr) -
+ mss = rx_ring->netdev->mtu - sizeof(struct fcoe_hdr) -
sizeof(struct fc_frame_header) -
sizeof(struct fcoe_crc_eof);
if (mss > 512)
@@ -1375,8 +1506,10 @@ next_desc:
rx_ring->total_packets += total_rx_packets;
rx_ring->total_bytes += total_rx_bytes;
-
- return cleaned;
+ u64_stats_update_begin(&rx_ring->syncp);
+ rx_ring->stats.packets += total_rx_packets;
+ rx_ring->stats.bytes += total_rx_bytes;
+ u64_stats_update_end(&rx_ring->syncp);
}
static int ixgbe_clean_rxonly(struct napi_struct *, int);
@@ -1390,7 +1523,7 @@ static int ixgbe_clean_rxonly(struct napi_struct *, int);
static void ixgbe_configure_msix(struct ixgbe_adapter *adapter)
{
struct ixgbe_q_vector *q_vector;
- int i, j, q_vectors, v_idx, r_idx;
+ int i, q_vectors, v_idx, r_idx;
u32 mask;
q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
@@ -1406,8 +1539,8 @@ static void ixgbe_configure_msix(struct ixgbe_adapter *adapter)
adapter->num_rx_queues);
for (i = 0; i < q_vector->rxr_count; i++) {
- j = adapter->rx_ring[r_idx]->reg_idx;
- ixgbe_set_ivar(adapter, 0, j, v_idx);
+ u8 reg_idx = adapter->rx_ring[r_idx]->reg_idx;
+ ixgbe_set_ivar(adapter, 0, reg_idx, v_idx);
r_idx = find_next_bit(q_vector->rxr_idx,
adapter->num_rx_queues,
r_idx + 1);
@@ -1416,8 +1549,8 @@ static void ixgbe_configure_msix(struct ixgbe_adapter *adapter)
adapter->num_tx_queues);
for (i = 0; i < q_vector->txr_count; i++) {
- j = adapter->tx_ring[r_idx]->reg_idx;
- ixgbe_set_ivar(adapter, 1, j, v_idx);
+ u8 reg_idx = adapter->tx_ring[r_idx]->reg_idx;
+ ixgbe_set_ivar(adapter, 1, reg_idx, v_idx);
r_idx = find_next_bit(q_vector->txr_idx,
adapter->num_tx_queues,
r_idx + 1);
@@ -1448,11 +1581,19 @@ static void ixgbe_configure_msix(struct ixgbe_adapter *adapter)
}
}
- if (adapter->hw.mac.type == ixgbe_mac_82598EB)
+ switch (adapter->hw.mac.type) {
+ case ixgbe_mac_82598EB:
ixgbe_set_ivar(adapter, -1, IXGBE_IVAR_OTHER_CAUSES_INDEX,
v_idx);
- else if (adapter->hw.mac.type == ixgbe_mac_82599EB)
+ break;
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
ixgbe_set_ivar(adapter, -1, 1, v_idx);
+ break;
+
+ default:
+ break;
+ }
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EITR(v_idx), 1950);
/* set up to autoclear timer, and the vectors */
@@ -1548,12 +1689,15 @@ void ixgbe_write_eitr(struct ixgbe_q_vector *q_vector)
int v_idx = q_vector->v_idx;
u32 itr_reg = EITR_INTS_PER_SEC_TO_REG(q_vector->eitr);
- if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
+ switch (adapter->hw.mac.type) {
+ case ixgbe_mac_82598EB:
/* must write high and low 16 bits to reset counter */
itr_reg |= (itr_reg << 16);
- } else if (adapter->hw.mac.type == ixgbe_mac_82599EB) {
+ break;
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
/*
- * 82599 can support a value of zero, so allow it for
+ * 82599 and X540 can support a value of zero, so allow it for
* max interrupt rate, but there is an errata where it can
* not be zero with RSC
*/
@@ -1566,6 +1710,9 @@ void ixgbe_write_eitr(struct ixgbe_q_vector *q_vector)
* immediate assertion of the interrupt
*/
itr_reg |= IXGBE_EITR_CNT_WDIS;
+ break;
+ default:
+ break;
}
IXGBE_WRITE_REG(hw, IXGBE_EITR(v_idx), itr_reg);
}
@@ -1573,14 +1720,13 @@ void ixgbe_write_eitr(struct ixgbe_q_vector *q_vector)
static void ixgbe_set_itr_msix(struct ixgbe_q_vector *q_vector)
{
struct ixgbe_adapter *adapter = q_vector->adapter;
+ int i, r_idx;
u32 new_itr;
u8 current_itr, ret_itr;
- int i, r_idx;
- struct ixgbe_ring *rx_ring, *tx_ring;
r_idx = find_first_bit(q_vector->txr_idx, adapter->num_tx_queues);
for (i = 0; i < q_vector->txr_count; i++) {
- tx_ring = adapter->tx_ring[r_idx];
+ struct ixgbe_ring *tx_ring = adapter->tx_ring[r_idx];
ret_itr = ixgbe_update_itr(adapter, q_vector->eitr,
q_vector->tx_itr,
tx_ring->total_packets,
@@ -1595,7 +1741,7 @@ static void ixgbe_set_itr_msix(struct ixgbe_q_vector *q_vector)
r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues);
for (i = 0; i < q_vector->rxr_count; i++) {
- rx_ring = adapter->rx_ring[r_idx];
+ struct ixgbe_ring *rx_ring = adapter->rx_ring[r_idx];
ret_itr = ixgbe_update_itr(adapter, q_vector->eitr,
q_vector->rx_itr,
rx_ring->total_packets,
@@ -1626,7 +1772,7 @@ static void ixgbe_set_itr_msix(struct ixgbe_q_vector *q_vector)
if (new_itr != q_vector->eitr) {
/* do an exponential smoothing */
- new_itr = ((q_vector->eitr * 90)/100) + ((new_itr * 10)/100);
+ new_itr = ((q_vector->eitr * 9) + new_itr)/10;
/* save the algorithm value here, not the smoothed one */
q_vector->eitr = new_itr;
@@ -1694,17 +1840,18 @@ static void ixgbe_check_sfp_event(struct ixgbe_adapter *adapter, u32 eicr)
{
struct ixgbe_hw *hw = &adapter->hw;
+ if (eicr & IXGBE_EICR_GPI_SDP2) {
+ /* Clear the interrupt */
+ IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP2);
+ if (!test_bit(__IXGBE_DOWN, &adapter->state))
+ schedule_work(&adapter->sfp_config_module_task);
+ }
+
if (eicr & IXGBE_EICR_GPI_SDP1) {
/* Clear the interrupt */
IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP1);
- schedule_work(&adapter->multispeed_fiber_task);
- } else if (eicr & IXGBE_EICR_GPI_SDP2) {
- /* Clear the interrupt */
- IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP2);
- schedule_work(&adapter->sfp_config_module_task);
- } else {
- /* Interrupt isn't for us... */
- return;
+ if (!test_bit(__IXGBE_DOWN, &adapter->state))
+ schedule_work(&adapter->multispeed_fiber_task);
}
}
@@ -1744,16 +1891,9 @@ static irqreturn_t ixgbe_msix_lsc(int irq, void *data)
if (eicr & IXGBE_EICR_MAILBOX)
ixgbe_msg_task(adapter);
- if (hw->mac.type == ixgbe_mac_82598EB)
- ixgbe_check_fan_failure(adapter, eicr);
-
- if (hw->mac.type == ixgbe_mac_82599EB) {
- ixgbe_check_sfp_event(adapter, eicr);
- adapter->interrupt_event = eicr;
- if ((adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE) &&
- ((eicr & IXGBE_EICR_GPI_SDP0) || (eicr & IXGBE_EICR_LSC)))
- schedule_work(&adapter->check_overtemp_task);
-
+ switch (hw->mac.type) {
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
/* Handle Flow Director Full threshold interrupt */
if (eicr & IXGBE_EICR_FLOW_DIR) {
int i;
@@ -1763,12 +1903,24 @@ static irqreturn_t ixgbe_msix_lsc(int irq, void *data)
for (i = 0; i < adapter->num_tx_queues; i++) {
struct ixgbe_ring *tx_ring =
adapter->tx_ring[i];
- if (test_and_clear_bit(__IXGBE_FDIR_INIT_DONE,
- &tx_ring->reinit_state))
+ if (test_and_clear_bit(__IXGBE_TX_FDIR_INIT_DONE,
+ &tx_ring->state))
schedule_work(&adapter->fdir_reinit_task);
}
}
+ ixgbe_check_sfp_event(adapter, eicr);
+ if ((adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE) &&
+ ((eicr & IXGBE_EICR_GPI_SDP0) || (eicr & IXGBE_EICR_LSC))) {
+ adapter->interrupt_event = eicr;
+ schedule_work(&adapter->check_overtemp_task);
+ }
+ break;
+ default:
+ break;
}
+
+ ixgbe_check_fan_failure(adapter, eicr);
+
if (!test_bit(__IXGBE_DOWN, &adapter->state))
IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_OTHER);
@@ -1779,15 +1931,24 @@ static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter,
u64 qmask)
{
u32 mask;
+ struct ixgbe_hw *hw = &adapter->hw;
- if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
+ switch (hw->mac.type) {
+ case ixgbe_mac_82598EB:
mask = (IXGBE_EIMS_RTX_QUEUE & qmask);
- IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMS, mask);
- } else {
+ IXGBE_WRITE_REG(hw, IXGBE_EIMS, mask);
+ break;
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
mask = (qmask & 0xFFFFFFFF);
- IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMS_EX(0), mask);
+ if (mask)
+ IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(0), mask);
mask = (qmask >> 32);
- IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMS_EX(1), mask);
+ if (mask)
+ IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(1), mask);
+ break;
+ default:
+ break;
}
/* skip the flush */
}
@@ -1796,15 +1957,24 @@ static inline void ixgbe_irq_disable_queues(struct ixgbe_adapter *adapter,
u64 qmask)
{
u32 mask;
+ struct ixgbe_hw *hw = &adapter->hw;
- if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
+ switch (hw->mac.type) {
+ case ixgbe_mac_82598EB:
mask = (IXGBE_EIMS_RTX_QUEUE & qmask);
- IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, mask);
- } else {
+ IXGBE_WRITE_REG(hw, IXGBE_EIMC, mask);
+ break;
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
mask = (qmask & 0xFFFFFFFF);
- IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(0), mask);
+ if (mask)
+ IXGBE_WRITE_REG(hw, IXGBE_EIMC_EX(0), mask);
mask = (qmask >> 32);
- IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(1), mask);
+ if (mask)
+ IXGBE_WRITE_REG(hw, IXGBE_EIMC_EX(1), mask);
+ break;
+ default:
+ break;
}
/* skip the flush */
}
@@ -1847,8 +2017,13 @@ static irqreturn_t ixgbe_msix_clean_rx(int irq, void *data)
int r_idx;
int i;
+#ifdef CONFIG_IXGBE_DCA
+ if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
+ ixgbe_update_dca(q_vector);
+#endif
+
r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues);
- for (i = 0; i < q_vector->rxr_count; i++) {
+ for (i = 0; i < q_vector->rxr_count; i++) {
rx_ring = adapter->rx_ring[r_idx];
rx_ring->total_bytes = 0;
rx_ring->total_packets = 0;
@@ -1859,7 +2034,6 @@ static irqreturn_t ixgbe_msix_clean_rx(int irq, void *data)
if (!q_vector->rxr_count)
return IRQ_HANDLED;
- /* disable interrupts on this vector only */
/* EIAM disabled interrupts (on this vector) for us */
napi_schedule(&q_vector->napi);
@@ -1918,13 +2092,14 @@ static int ixgbe_clean_rxonly(struct napi_struct *napi, int budget)
int work_done = 0;
long r_idx;
- r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues);
- rx_ring = adapter->rx_ring[r_idx];
#ifdef CONFIG_IXGBE_DCA
if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
- ixgbe_update_rx_dca(adapter, rx_ring);
+ ixgbe_update_dca(q_vector);
#endif
+ r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues);
+ rx_ring = adapter->rx_ring[r_idx];
+
ixgbe_clean_rx_irq(q_vector, rx_ring, &work_done, budget);
/* If all Rx work done, exit the polling mode */
@@ -1958,13 +2133,14 @@ static int ixgbe_clean_rxtx_many(struct napi_struct *napi, int budget)
long r_idx;
bool tx_clean_complete = true;
+#ifdef CONFIG_IXGBE_DCA
+ if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
+ ixgbe_update_dca(q_vector);
+#endif
+
r_idx = find_first_bit(q_vector->txr_idx, adapter->num_tx_queues);
for (i = 0; i < q_vector->txr_count; i++) {
ring = adapter->tx_ring[r_idx];
-#ifdef CONFIG_IXGBE_DCA
- if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
- ixgbe_update_tx_dca(adapter, ring);
-#endif
tx_clean_complete &= ixgbe_clean_tx_irq(q_vector, ring);
r_idx = find_next_bit(q_vector->txr_idx, adapter->num_tx_queues,
r_idx + 1);
@@ -1977,10 +2153,6 @@ static int ixgbe_clean_rxtx_many(struct napi_struct *napi, int budget)
r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues);
for (i = 0; i < q_vector->rxr_count; i++) {
ring = adapter->rx_ring[r_idx];
-#ifdef CONFIG_IXGBE_DCA
- if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
- ixgbe_update_rx_dca(adapter, ring);
-#endif
ixgbe_clean_rx_irq(q_vector, ring, &work_done, budget);
r_idx = find_next_bit(q_vector->rxr_idx, adapter->num_rx_queues,
r_idx + 1);
@@ -2019,13 +2191,14 @@ static int ixgbe_clean_txonly(struct napi_struct *napi, int budget)
int work_done = 0;
long r_idx;
- r_idx = find_first_bit(q_vector->txr_idx, adapter->num_tx_queues);
- tx_ring = adapter->tx_ring[r_idx];
#ifdef CONFIG_IXGBE_DCA
if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
- ixgbe_update_tx_dca(adapter, tx_ring);
+ ixgbe_update_dca(q_vector);
#endif
+ r_idx = find_first_bit(q_vector->txr_idx, adapter->num_tx_queues);
+ tx_ring = adapter->tx_ring[r_idx];
+
if (!ixgbe_clean_tx_irq(q_vector, tx_ring))
work_done = budget;
@@ -2046,24 +2219,27 @@ static inline void map_vector_to_rxq(struct ixgbe_adapter *a, int v_idx,
int r_idx)
{
struct ixgbe_q_vector *q_vector = a->q_vector[v_idx];
+ struct ixgbe_ring *rx_ring = a->rx_ring[r_idx];
set_bit(r_idx, q_vector->rxr_idx);
q_vector->rxr_count++;
+ rx_ring->q_vector = q_vector;
}
static inline void map_vector_to_txq(struct ixgbe_adapter *a, int v_idx,
int t_idx)
{
struct ixgbe_q_vector *q_vector = a->q_vector[v_idx];
+ struct ixgbe_ring *tx_ring = a->tx_ring[t_idx];
set_bit(t_idx, q_vector->txr_idx);
q_vector->txr_count++;
+ tx_ring->q_vector = q_vector;
}
/**
* ixgbe_map_rings_to_vectors - Maps descriptor rings to vectors
* @adapter: board private structure to initialize
- * @vectors: allotted vector count for descriptor rings
*
* This function maps descriptor rings to the queue-specific vectors
* we were allotted through the MSI-X enabling code. Ideally, we'd have
@@ -2071,9 +2247,9 @@ static inline void map_vector_to_txq(struct ixgbe_adapter *a, int v_idx,
* group the rings as "efficiently" as possible. You would add new
* mapping configurations in here.
**/
-static int ixgbe_map_rings_to_vectors(struct ixgbe_adapter *adapter,
- int vectors)
+static int ixgbe_map_rings_to_vectors(struct ixgbe_adapter *adapter)
{
+ int q_vectors;
int v_start = 0;
int rxr_idx = 0, txr_idx = 0;
int rxr_remaining = adapter->num_rx_queues;
@@ -2086,11 +2262,13 @@ static int ixgbe_map_rings_to_vectors(struct ixgbe_adapter *adapter,
if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED))
goto out;
+ q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
+
/*
* The ideal configuration...
* We have enough vectors to map one per queue.
*/
- if (vectors == adapter->num_rx_queues + adapter->num_tx_queues) {
+ if (q_vectors == adapter->num_rx_queues + adapter->num_tx_queues) {
for (; rxr_idx < rxr_remaining; v_start++, rxr_idx++)
map_vector_to_rxq(adapter, v_start, rxr_idx);
@@ -2106,23 +2284,20 @@ static int ixgbe_map_rings_to_vectors(struct ixgbe_adapter *adapter,
* multiple queues per vector.
*/
/* Re-adjusting *qpv takes care of the remainder. */
- for (i = v_start; i < vectors; i++) {
- rqpv = DIV_ROUND_UP(rxr_remaining, vectors - i);
+ for (i = v_start; i < q_vectors; i++) {
+ rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - i);
for (j = 0; j < rqpv; j++) {
map_vector_to_rxq(adapter, i, rxr_idx);
rxr_idx++;
rxr_remaining--;
}
- }
- for (i = v_start; i < vectors; i++) {
- tqpv = DIV_ROUND_UP(txr_remaining, vectors - i);
+ tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - i);
for (j = 0; j < tqpv; j++) {
map_vector_to_txq(adapter, i, txr_idx);
txr_idx++;
txr_remaining--;
}
}
-
out:
return err;
}
@@ -2144,30 +2319,36 @@ static int ixgbe_request_msix_irqs(struct ixgbe_adapter *adapter)
/* Decrement for Other and TCP Timer vectors */
q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
- /* Map the Tx/Rx rings to the vectors we were allotted. */
- err = ixgbe_map_rings_to_vectors(adapter, q_vectors);
+ err = ixgbe_map_rings_to_vectors(adapter);
if (err)
- goto out;
+ return err;
-#define SET_HANDLER(_v) ((!(_v)->rxr_count) ? &ixgbe_msix_clean_tx : \
- (!(_v)->txr_count) ? &ixgbe_msix_clean_rx : \
- &ixgbe_msix_clean_many)
+#define SET_HANDLER(_v) (((_v)->rxr_count && (_v)->txr_count) \
+ ? &ixgbe_msix_clean_many : \
+ (_v)->rxr_count ? &ixgbe_msix_clean_rx : \
+ (_v)->txr_count ? &ixgbe_msix_clean_tx : \
+ NULL)
for (vector = 0; vector < q_vectors; vector++) {
- handler = SET_HANDLER(adapter->q_vector[vector]);
+ struct ixgbe_q_vector *q_vector = adapter->q_vector[vector];
+ handler = SET_HANDLER(q_vector);
if (handler == &ixgbe_msix_clean_rx) {
- sprintf(adapter->name[vector], "%s-%s-%d",
+ sprintf(q_vector->name, "%s-%s-%d",
netdev->name, "rx", ri++);
} else if (handler == &ixgbe_msix_clean_tx) {
- sprintf(adapter->name[vector], "%s-%s-%d",
+ sprintf(q_vector->name, "%s-%s-%d",
netdev->name, "tx", ti++);
- } else
- sprintf(adapter->name[vector], "%s-%s-%d",
- netdev->name, "TxRx", vector);
-
+ } else if (handler == &ixgbe_msix_clean_many) {
+ sprintf(q_vector->name, "%s-%s-%d",
+ netdev->name, "TxRx", ri++);
+ ti++;
+ } else {
+ /* skip this unused q_vector */
+ continue;
+ }
err = request_irq(adapter->msix_entries[vector].vector,
- handler, 0, adapter->name[vector],
- adapter->q_vector[vector]);
+ handler, 0, q_vector->name,
+ q_vector);
if (err) {
e_err(probe, "request_irq failed for MSIX interrupt "
"Error: %d\n", err);
@@ -2175,9 +2356,9 @@ static int ixgbe_request_msix_irqs(struct ixgbe_adapter *adapter)
}
}
- sprintf(adapter->name[vector], "%s:lsc", netdev->name);
+ sprintf(adapter->lsc_int_name, "%s:lsc", netdev->name);
err = request_irq(adapter->msix_entries[vector].vector,
- ixgbe_msix_lsc, 0, adapter->name[vector], netdev);
+ ixgbe_msix_lsc, 0, adapter->lsc_int_name, netdev);
if (err) {
e_err(probe, "request_irq for msix_lsc failed: %d\n", err);
goto free_queue_irqs;
@@ -2193,17 +2374,16 @@ free_queue_irqs:
pci_disable_msix(adapter->pdev);
kfree(adapter->msix_entries);
adapter->msix_entries = NULL;
-out:
return err;
}
static void ixgbe_set_itr(struct ixgbe_adapter *adapter)
{
struct ixgbe_q_vector *q_vector = adapter->q_vector[0];
- u8 current_itr;
- u32 new_itr = q_vector->eitr;
struct ixgbe_ring *rx_ring = adapter->rx_ring[0];
struct ixgbe_ring *tx_ring = adapter->tx_ring[0];
+ u32 new_itr = q_vector->eitr;
+ u8 current_itr;
q_vector->tx_itr = ixgbe_update_itr(adapter, new_itr,
q_vector->tx_itr,
@@ -2233,9 +2413,9 @@ static void ixgbe_set_itr(struct ixgbe_adapter *adapter)
if (new_itr != q_vector->eitr) {
/* do an exponential smoothing */
- new_itr = ((q_vector->eitr * 90)/100) + ((new_itr * 10)/100);
+ new_itr = ((q_vector->eitr * 9) + new_itr)/10;
- /* save the algorithm value here, not the smoothed one */
+ /* save the algorithm value here */
q_vector->eitr = new_itr;
ixgbe_write_eitr(q_vector);
@@ -2256,12 +2436,17 @@ static inline void ixgbe_irq_enable(struct ixgbe_adapter *adapter, bool queues,
mask |= IXGBE_EIMS_GPI_SDP0;
if (adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE)
mask |= IXGBE_EIMS_GPI_SDP1;
- if (adapter->hw.mac.type == ixgbe_mac_82599EB) {
+ switch (adapter->hw.mac.type) {
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
mask |= IXGBE_EIMS_ECC;
mask |= IXGBE_EIMS_GPI_SDP1;
mask |= IXGBE_EIMS_GPI_SDP2;
if (adapter->num_vfs)
mask |= IXGBE_EIMS_MAILBOX;
+ break;
+ default:
+ break;
}
if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE ||
adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE)
@@ -2317,13 +2502,21 @@ static irqreturn_t ixgbe_intr(int irq, void *data)
if (eicr & IXGBE_EICR_LSC)
ixgbe_check_lsc(adapter);
- if (hw->mac.type == ixgbe_mac_82599EB)
+ switch (hw->mac.type) {
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
ixgbe_check_sfp_event(adapter, eicr);
+ if ((adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE) &&
+ ((eicr & IXGBE_EICR_GPI_SDP0) || (eicr & IXGBE_EICR_LSC))) {
+ adapter->interrupt_event = eicr;
+ schedule_work(&adapter->check_overtemp_task);
+ }
+ break;
+ default:
+ break;
+ }
ixgbe_check_fan_failure(adapter, eicr);
- if ((adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE) &&
- ((eicr & IXGBE_EICR_GPI_SDP0) || (eicr & IXGBE_EICR_LSC)))
- schedule_work(&adapter->check_overtemp_task);
if (napi_schedule_prep(&(q_vector->napi))) {
adapter->tx_ring[0]->total_packets = 0;
@@ -2416,14 +2609,20 @@ static void ixgbe_free_irq(struct ixgbe_adapter *adapter)
**/
static inline void ixgbe_irq_disable(struct ixgbe_adapter *adapter)
{
- if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
+ switch (adapter->hw.mac.type) {
+ case ixgbe_mac_82598EB:
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, ~0);
- } else {
+ break;
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, 0xFFFF0000);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(0), ~0);
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(1), ~0);
if (adapter->num_vfs > 32)
IXGBE_WRITE_REG(&adapter->hw, IXGBE_EITRSEL, 0);
+ break;
+ default:
+ break;
}
IXGBE_WRITE_FLUSH(&adapter->hw);
if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) {
@@ -2469,7 +2668,7 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter,
u64 tdba = ring->dma;
int wait_loop = 10;
u32 txdctl;
- u16 reg_idx = ring->reg_idx;
+ u8 reg_idx = ring->reg_idx;
/* disable queue to avoid issues while updating state */
txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx));
@@ -2484,8 +2683,7 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter,
ring->count * sizeof(union ixgbe_adv_tx_desc));
IXGBE_WRITE_REG(hw, IXGBE_TDH(reg_idx), 0);
IXGBE_WRITE_REG(hw, IXGBE_TDT(reg_idx), 0);
- ring->head = IXGBE_TDH(reg_idx);
- ring->tail = IXGBE_TDT(reg_idx);
+ ring->tail = hw->hw_addr + IXGBE_TDT(reg_idx);
/* configure fetching thresholds */
if (adapter->rx_itr_setting == 0) {
@@ -2501,7 +2699,16 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter,
}
/* reinitialize flowdirector state */
- set_bit(__IXGBE_FDIR_INIT_DONE, &ring->reinit_state);
+ if ((adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) &&
+ adapter->atr_sample_rate) {
+ ring->atr_sample_rate = adapter->atr_sample_rate;
+ ring->atr_count = 0;
+ set_bit(__IXGBE_TX_FDIR_INIT_DONE, &ring->state);
+ } else {
+ ring->atr_sample_rate = 0;
+ }
+
+ clear_bit(__IXGBE_HANG_CHECK_ARMED, &ring->state);
/* enable queue */
txdctl |= IXGBE_TXDCTL_ENABLE;
@@ -2592,16 +2799,22 @@ static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter,
struct ixgbe_ring *rx_ring)
{
u32 srrctl;
- int index;
- struct ixgbe_ring_feature *feature = adapter->ring_feature;
+ u8 reg_idx = rx_ring->reg_idx;
- index = rx_ring->reg_idx;
- if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
- unsigned long mask;
- mask = (unsigned long) feature[RING_F_RSS].mask;
- index = index & mask;
+ switch (adapter->hw.mac.type) {
+ case ixgbe_mac_82598EB: {
+ struct ixgbe_ring_feature *feature = adapter->ring_feature;
+ const int mask = feature[RING_F_RSS].mask;
+ reg_idx = reg_idx & mask;
+ }
+ break;
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
+ default:
+ break;
}
- srrctl = IXGBE_READ_REG(&adapter->hw, IXGBE_SRRCTL(index));
+
+ srrctl = IXGBE_READ_REG(&adapter->hw, IXGBE_SRRCTL(reg_idx));
srrctl &= ~IXGBE_SRRCTL_BSIZEHDR_MASK;
srrctl &= ~IXGBE_SRRCTL_BSIZEPKT_MASK;
@@ -2611,7 +2824,7 @@ static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter,
srrctl |= (IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT) &
IXGBE_SRRCTL_BSIZEHDR_MASK;
- if (rx_ring->flags & IXGBE_RING_RX_PS_ENABLED) {
+ if (ring_is_ps_enabled(rx_ring)) {
#if (PAGE_SIZE / 2) > IXGBE_MAX_RXBUFFER
srrctl |= IXGBE_MAX_RXBUFFER >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
#else
@@ -2624,7 +2837,7 @@ static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter,
srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF;
}
- IXGBE_WRITE_REG(&adapter->hw, IXGBE_SRRCTL(index), srrctl);
+ IXGBE_WRITE_REG(&adapter->hw, IXGBE_SRRCTL(reg_idx), srrctl);
}
static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter)
@@ -2694,19 +2907,36 @@ static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter)
}
/**
+ * ixgbe_clear_rscctl - disable RSC for the indicated ring
+ * @adapter: address of board private structure
+ * @ring: structure containing ring specific data
+ **/
+void ixgbe_clear_rscctl(struct ixgbe_adapter *adapter,
+ struct ixgbe_ring *ring)
+{
+ struct ixgbe_hw *hw = &adapter->hw;
+ u32 rscctrl;
+ u8 reg_idx = ring->reg_idx;
+
+ rscctrl = IXGBE_READ_REG(hw, IXGBE_RSCCTL(reg_idx));
+ rscctrl &= ~IXGBE_RSCCTL_RSCEN;
+ IXGBE_WRITE_REG(hw, IXGBE_RSCCTL(reg_idx), rscctrl);
+}
+
+/**
* ixgbe_configure_rscctl - enable RSC for the indicated ring
* @adapter: address of board private structure
* @index: index of ring to set
**/
-static void ixgbe_configure_rscctl(struct ixgbe_adapter *adapter,
+void ixgbe_configure_rscctl(struct ixgbe_adapter *adapter,
struct ixgbe_ring *ring)
{
struct ixgbe_hw *hw = &adapter->hw;
u32 rscctrl;
int rx_buf_len;
- u16 reg_idx = ring->reg_idx;
+ u8 reg_idx = ring->reg_idx;
- if (!(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED))
+ if (!ring_is_rsc_enabled(ring))
return;
rx_buf_len = ring->rx_buf_len;
@@ -2717,7 +2947,7 @@ static void ixgbe_configure_rscctl(struct ixgbe_adapter *adapter,
* total size of max desc * buf_len is not greater
* than 65535
*/
- if (ring->flags & IXGBE_RING_RX_PS_ENABLED) {
+ if (ring_is_ps_enabled(ring)) {
#if (MAX_SKB_FRAGS > 16)
rscctrl |= IXGBE_RSCCTL_MAXDESC_16;
#elif (MAX_SKB_FRAGS > 8)
@@ -2770,9 +3000,9 @@ static void ixgbe_rx_desc_queue_enable(struct ixgbe_adapter *adapter,
struct ixgbe_ring *ring)
{
struct ixgbe_hw *hw = &adapter->hw;
- int reg_idx = ring->reg_idx;
int wait_loop = IXGBE_MAX_RX_DESC_POLL;
u32 rxdctl;
+ u8 reg_idx = ring->reg_idx;
/* RXDCTL.EN will return 0 on 82598 if link is down, so skip it */
if (hw->mac.type == ixgbe_mac_82598EB &&
@@ -2796,7 +3026,7 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
struct ixgbe_hw *hw = &adapter->hw;
u64 rdba = ring->dma;
u32 rxdctl;
- u16 reg_idx = ring->reg_idx;
+ u8 reg_idx = ring->reg_idx;
/* disable queue to avoid issues while updating state */
rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
@@ -2810,8 +3040,7 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
ring->count * sizeof(union ixgbe_adv_rx_desc));
IXGBE_WRITE_REG(hw, IXGBE_RDH(reg_idx), 0);
IXGBE_WRITE_REG(hw, IXGBE_RDT(reg_idx), 0);
- ring->head = IXGBE_RDH(reg_idx);
- ring->tail = IXGBE_RDT(reg_idx);
+ ring->tail = hw->hw_addr + IXGBE_RDT(reg_idx);
ixgbe_configure_srrctl(adapter, ring);
ixgbe_configure_rscctl(adapter, ring);
@@ -2833,7 +3062,7 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl);
ixgbe_rx_desc_queue_enable(adapter, ring);
- ixgbe_alloc_rx_buffers(adapter, ring, IXGBE_DESC_UNUSED(ring));
+ ixgbe_alloc_rx_buffers(ring, IXGBE_DESC_UNUSED(ring));
}
static void ixgbe_setup_psrtype(struct ixgbe_adapter *adapter)
@@ -2956,24 +3185,32 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter)
rx_ring->rx_buf_len = rx_buf_len;
if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED)
- rx_ring->flags |= IXGBE_RING_RX_PS_ENABLED;
+ set_ring_ps_enabled(rx_ring);
+ else
+ clear_ring_ps_enabled(rx_ring);
+
+ if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)
+ set_ring_rsc_enabled(rx_ring);
else
- rx_ring->flags &= ~IXGBE_RING_RX_PS_ENABLED;
+ clear_ring_rsc_enabled(rx_ring);
#ifdef IXGBE_FCOE
if (netdev->features & NETIF_F_FCOE_MTU) {
struct ixgbe_ring_feature *f;
f = &adapter->ring_feature[RING_F_FCOE];
if ((i >= f->mask) && (i < f->mask + f->indices)) {
- rx_ring->flags &= ~IXGBE_RING_RX_PS_ENABLED;
+ clear_ring_ps_enabled(rx_ring);
if (rx_buf_len < IXGBE_FCOE_JUMBO_FRAME_SIZE)
rx_ring->rx_buf_len =
IXGBE_FCOE_JUMBO_FRAME_SIZE;
+ } else if (!ring_is_rsc_enabled(rx_ring) &&
+ !ring_is_ps_enabled(rx_ring)) {
+ rx_ring->rx_buf_len =
+ IXGBE_FCOE_JUMBO_FRAME_SIZE;
}
}
#endif /* IXGBE_FCOE */
}
-
}
static void ixgbe_setup_rdrxctl(struct ixgbe_adapter *adapter)
@@ -2996,6 +3233,7 @@ static void ixgbe_setup_rdrxctl(struct ixgbe_adapter *adapter)
rdrxctl |= IXGBE_RDRXCTL_MVMEN;
break;
case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
/* Disable RSC for ACK packets */
IXGBE_WRITE_REG(hw, IXGBE_RSCDBU,
(IXGBE_RSCDBU_RSCACKDIS | IXGBE_READ_REG(hw, IXGBE_RSCDBU)));
@@ -3123,6 +3361,7 @@ static void ixgbe_vlan_strip_disable(struct ixgbe_adapter *adapter)
IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
break;
case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
for (i = 0; i < adapter->num_rx_queues; i++) {
j = adapter->rx_ring[i]->reg_idx;
vlnctrl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(j));
@@ -3152,6 +3391,7 @@ static void ixgbe_vlan_strip_enable(struct ixgbe_adapter *adapter)
IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
break;
case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
for (i = 0; i < adapter->num_rx_queues; i++) {
j = adapter->rx_ring[i]->reg_idx;
vlnctrl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(j));
@@ -3349,8 +3589,6 @@ static void ixgbe_configure_dcb(struct ixgbe_adapter *adapter)
{
struct ixgbe_hw *hw = &adapter->hw;
int max_frame = adapter->netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
- u32 txdctl;
- int i, j;
if (!(adapter->flags & IXGBE_FLAG_DCB_ENABLED)) {
if (hw->mac.type == ixgbe_mac_82598EB)
@@ -3366,25 +3604,18 @@ static void ixgbe_configure_dcb(struct ixgbe_adapter *adapter)
max_frame = max(max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE);
#endif
- ixgbe_dcb_calculate_tc_credits(&adapter->dcb_cfg, max_frame,
+ ixgbe_dcb_calculate_tc_credits(hw, &adapter->dcb_cfg, max_frame,
DCB_TX_CONFIG);
- ixgbe_dcb_calculate_tc_credits(&adapter->dcb_cfg, max_frame,
+ ixgbe_dcb_calculate_tc_credits(hw, &adapter->dcb_cfg, max_frame,
DCB_RX_CONFIG);
- /* reconfigure the hardware */
- ixgbe_dcb_hw_config(&adapter->hw, &adapter->dcb_cfg);
-
- for (i = 0; i < adapter->num_tx_queues; i++) {
- j = adapter->tx_ring[i]->reg_idx;
- txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(j));
- /* PThresh workaround for Tx hang with DFP enabled. */
- txdctl |= 32;
- IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(j), txdctl);
- }
/* Enable VLAN tag insert/strip */
adapter->netdev->features |= NETIF_F_HW_VLAN_RX;
hw->mac.ops.set_vfta(&adapter->hw, 0, 0, true);
+
+ /* reconfigure the hardware */
+ ixgbe_dcb_hw_config(hw, &adapter->dcb_cfg);
}
#endif
@@ -3516,8 +3747,9 @@ static void ixgbe_setup_gpie(struct ixgbe_adapter *adapter)
case ixgbe_mac_82598EB:
IXGBE_WRITE_REG(hw, IXGBE_EIAM, IXGBE_EICS_RTX_QUEUE);
break;
- default:
case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
+ default:
IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(0), 0xFFFFFFFF);
IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(1), 0xFFFFFFFF);
break;
@@ -3562,12 +3794,20 @@ static int ixgbe_up_complete(struct ixgbe_adapter *adapter)
ixgbe_configure_msi_and_legacy(adapter);
/* enable the optics */
- if (hw->phy.multispeed_fiber)
+ if (hw->phy.multispeed_fiber && hw->mac.ops.enable_tx_laser)
hw->mac.ops.enable_tx_laser(hw);
clear_bit(__IXGBE_DOWN, &adapter->state);
ixgbe_napi_enable_all(adapter);
+ if (ixgbe_is_sfp(hw)) {
+ ixgbe_sfp_link_config(adapter);
+ } else {
+ err = ixgbe_non_sfp_link_config(hw);
+ if (err)
+ e_err(probe, "link_config FAILED %d\n", err);
+ }
+
/* clear any pending interrupts, may auto mask */
IXGBE_READ_REG(hw, IXGBE_EICR);
ixgbe_irq_enable(adapter, true, true);
@@ -3590,26 +3830,8 @@ static int ixgbe_up_complete(struct ixgbe_adapter *adapter)
* If we're not hot-pluggable SFP+, we just need to configure link
* and bring it up.
*/
- if (hw->phy.type == ixgbe_phy_unknown) {
- err = hw->phy.ops.identify(hw);
- if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) {
- /*
- * Take the device down and schedule the sfp tasklet
- * which will unregister_netdev and log it.
- */
- ixgbe_down(adapter);
- schedule_work(&adapter->sfp_config_module_task);
- return err;
- }
- }
-
- if (ixgbe_is_sfp(hw)) {
- ixgbe_sfp_link_config(adapter);
- } else {
- err = ixgbe_non_sfp_link_config(hw);
- if (err)
- e_err(probe, "link_config FAILED %d\n", err);
- }
+ if (hw->phy.type == ixgbe_phy_unknown)
+ schedule_work(&adapter->sfp_config_module_task);
/* enable transmits */
netif_tx_start_all_queues(adapter->netdev);
@@ -3687,15 +3909,13 @@ void ixgbe_reset(struct ixgbe_adapter *adapter)
/**
* ixgbe_clean_rx_ring - Free Rx Buffers per Queue
- * @adapter: board private structure
* @rx_ring: ring to free buffers from
**/
-static void ixgbe_clean_rx_ring(struct ixgbe_adapter *adapter,
- struct ixgbe_ring *rx_ring)
+static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring)
{
- struct pci_dev *pdev = adapter->pdev;
+ struct device *dev = rx_ring->dev;
unsigned long size;
- unsigned int i;
+ u16 i;
/* ring already cleared, nothing to do */
if (!rx_ring->rx_buffer_info)
@@ -3707,7 +3927,7 @@ static void ixgbe_clean_rx_ring(struct ixgbe_adapter *adapter,
rx_buffer_info = &rx_ring->rx_buffer_info[i];
if (rx_buffer_info->dma) {
- dma_unmap_single(&pdev->dev, rx_buffer_info->dma,
+ dma_unmap_single(rx_ring->dev, rx_buffer_info->dma,
rx_ring->rx_buf_len,
DMA_FROM_DEVICE);
rx_buffer_info->dma = 0;
@@ -3718,7 +3938,7 @@ static void ixgbe_clean_rx_ring(struct ixgbe_adapter *adapter,
do {
struct sk_buff *this = skb;
if (IXGBE_RSC_CB(this)->delay_unmap) {
- dma_unmap_single(&pdev->dev,
+ dma_unmap_single(dev,
IXGBE_RSC_CB(this)->dma,
rx_ring->rx_buf_len,
DMA_FROM_DEVICE);
@@ -3732,7 +3952,7 @@ static void ixgbe_clean_rx_ring(struct ixgbe_adapter *adapter,
if (!rx_buffer_info->page)
continue;
if (rx_buffer_info->page_dma) {
- dma_unmap_page(&pdev->dev, rx_buffer_info->page_dma,
+ dma_unmap_page(dev, rx_buffer_info->page_dma,
PAGE_SIZE / 2, DMA_FROM_DEVICE);
rx_buffer_info->page_dma = 0;
}
@@ -3749,24 +3969,17 @@ static void ixgbe_clean_rx_ring(struct ixgbe_adapter *adapter,
rx_ring->next_to_clean = 0;
rx_ring->next_to_use = 0;
-
- if (rx_ring->head)
- writel(0, adapter->hw.hw_addr + rx_ring->head);
- if (rx_ring->tail)
- writel(0, adapter->hw.hw_addr + rx_ring->tail);
}
/**
* ixgbe_clean_tx_ring - Free Tx Buffers
- * @adapter: board private structure
* @tx_ring: ring to be cleaned
**/
-static void ixgbe_clean_tx_ring(struct ixgbe_adapter *adapter,
- struct ixgbe_ring *tx_ring)
+static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring)
{
struct ixgbe_tx_buffer *tx_buffer_info;
unsigned long size;
- unsigned int i;
+ u16 i;
/* ring already cleared, nothing to do */
if (!tx_ring->tx_buffer_info)
@@ -3775,7 +3988,7 @@ static void ixgbe_clean_tx_ring(struct ixgbe_adapter *adapter,
/* Free all the Tx ring sk_buffs */
for (i = 0; i < tx_ring->count; i++) {
tx_buffer_info = &tx_ring->tx_buffer_info[i];
- ixgbe_unmap_and_free_tx_resource(adapter, tx_buffer_info);
+ ixgbe_unmap_and_free_tx_resource(tx_ring, tx_buffer_info);
}
size = sizeof(struct ixgbe_tx_buffer) * tx_ring->count;
@@ -3786,11 +3999,6 @@ static void ixgbe_clean_tx_ring(struct ixgbe_adapter *adapter,
tx_ring->next_to_use = 0;
tx_ring->next_to_clean = 0;
-
- if (tx_ring->head)
- writel(0, adapter->hw.hw_addr + tx_ring->head);
- if (tx_ring->tail)
- writel(0, adapter->hw.hw_addr + tx_ring->tail);
}
/**
@@ -3802,7 +4010,7 @@ static void ixgbe_clean_all_rx_rings(struct ixgbe_adapter *adapter)
int i;
for (i = 0; i < adapter->num_rx_queues; i++)
- ixgbe_clean_rx_ring(adapter, adapter->rx_ring[i]);
+ ixgbe_clean_rx_ring(adapter->rx_ring[i]);
}
/**
@@ -3814,7 +4022,7 @@ static void ixgbe_clean_all_tx_rings(struct ixgbe_adapter *adapter)
int i;
for (i = 0; i < adapter->num_tx_queues; i++)
- ixgbe_clean_tx_ring(adapter, adapter->tx_ring[i]);
+ ixgbe_clean_tx_ring(adapter->tx_ring[i]);
}
void ixgbe_down(struct ixgbe_adapter *adapter)
@@ -3823,7 +4031,7 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
struct ixgbe_hw *hw = &adapter->hw;
u32 rxctrl;
u32 txdctl;
- int i, j;
+ int i;
int num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS;
/* signal that we are down to the interrupt handler */
@@ -3881,19 +4089,25 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
/* disable transmits in the hardware now that interrupts are off */
for (i = 0; i < adapter->num_tx_queues; i++) {
- j = adapter->tx_ring[i]->reg_idx;
- txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(j));
- IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(j),
+ u8 reg_idx = adapter->tx_ring[i]->reg_idx;
+ txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx));
+ IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx),
(txdctl & ~IXGBE_TXDCTL_ENABLE));
}
/* Disable the Tx DMA engine on 82599 */
- if (hw->mac.type == ixgbe_mac_82599EB)
+ switch (hw->mac.type) {
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL,
(IXGBE_READ_REG(hw, IXGBE_DMATXCTL) &
~IXGBE_DMATXCTL_TE));
+ break;
+ default:
+ break;
+ }
/* power down the optics */
- if (hw->phy.multispeed_fiber)
+ if (hw->phy.multispeed_fiber && hw->mac.ops.disable_tx_laser)
hw->mac.ops.disable_tx_laser(hw);
/* clear n-tuple filters that are cached */
@@ -3925,10 +4139,8 @@ static int ixgbe_poll(struct napi_struct *napi, int budget)
int tx_clean_complete, work_done = 0;
#ifdef CONFIG_IXGBE_DCA
- if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) {
- ixgbe_update_tx_dca(adapter, adapter->tx_ring[0]);
- ixgbe_update_rx_dca(adapter, adapter->rx_ring[0]);
- }
+ if (adapter->flags & IXGBE_FLAG_DCA_ENABLED)
+ ixgbe_update_dca(q_vector);
#endif
tx_clean_complete = ixgbe_clean_tx_irq(q_vector, adapter->tx_ring[0]);
@@ -3956,6 +4168,8 @@ static void ixgbe_tx_timeout(struct net_device *netdev)
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
+ adapter->tx_timeout_count++;
+
/* Do the reset outside of interrupt context */
schedule_work(&adapter->reset_task);
}
@@ -3970,8 +4184,6 @@ static void ixgbe_reset_task(struct work_struct *work)
test_bit(__IXGBE_RESETTING, &adapter->state))
return;
- adapter->tx_timeout_count++;
-
ixgbe_dump(adapter);
netdev_err(adapter->netdev, "Reset adapter\n");
ixgbe_reinit_locked(adapter);
@@ -4221,19 +4433,16 @@ static void ixgbe_acquire_msix_vectors(struct ixgbe_adapter *adapter,
static inline bool ixgbe_cache_ring_rss(struct ixgbe_adapter *adapter)
{
int i;
- bool ret = false;
- if (adapter->flags & IXGBE_FLAG_RSS_ENABLED) {
- for (i = 0; i < adapter->num_rx_queues; i++)
- adapter->rx_ring[i]->reg_idx = i;
- for (i = 0; i < adapter->num_tx_queues; i++)
- adapter->tx_ring[i]->reg_idx = i;
- ret = true;
- } else {
- ret = false;
- }
+ if (!(adapter->flags & IXGBE_FLAG_RSS_ENABLED))
+ return false;
- return ret;
+ for (i = 0; i < adapter->num_rx_queues; i++)
+ adapter->rx_ring[i]->reg_idx = i;
+ for (i = 0; i < adapter->num_tx_queues; i++)
+ adapter->tx_ring[i]->reg_idx = i;
+
+ return true;
}
#ifdef CONFIG_IXGBE_DCB
@@ -4250,71 +4459,67 @@ static inline bool ixgbe_cache_ring_dcb(struct ixgbe_adapter *adapter)
bool ret = false;
int dcb_i = adapter->ring_feature[RING_F_DCB].indices;
- if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) {
- if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
- /* the number of queues is assumed to be symmetric */
- for (i = 0; i < dcb_i; i++) {
- adapter->rx_ring[i]->reg_idx = i << 3;
- adapter->tx_ring[i]->reg_idx = i << 2;
- }
- ret = true;
- } else if (adapter->hw.mac.type == ixgbe_mac_82599EB) {
- if (dcb_i == 8) {
- /*
- * Tx TC0 starts at: descriptor queue 0
- * Tx TC1 starts at: descriptor queue 32
- * Tx TC2 starts at: descriptor queue 64
- * Tx TC3 starts at: descriptor queue 80
- * Tx TC4 starts at: descriptor queue 96
- * Tx TC5 starts at: descriptor queue 104
- * Tx TC6 starts at: descriptor queue 112
- * Tx TC7 starts at: descriptor queue 120
- *
- * Rx TC0-TC7 are offset by 16 queues each
- */
- for (i = 0; i < 3; i++) {
- adapter->tx_ring[i]->reg_idx = i << 5;
- adapter->rx_ring[i]->reg_idx = i << 4;
- }
- for ( ; i < 5; i++) {
- adapter->tx_ring[i]->reg_idx =
- ((i + 2) << 4);
- adapter->rx_ring[i]->reg_idx = i << 4;
- }
- for ( ; i < dcb_i; i++) {
- adapter->tx_ring[i]->reg_idx =
- ((i + 8) << 3);
- adapter->rx_ring[i]->reg_idx = i << 4;
- }
+ if (!(adapter->flags & IXGBE_FLAG_DCB_ENABLED))
+ return false;
- ret = true;
- } else if (dcb_i == 4) {
- /*
- * Tx TC0 starts at: descriptor queue 0
- * Tx TC1 starts at: descriptor queue 64
- * Tx TC2 starts at: descriptor queue 96
- * Tx TC3 starts at: descriptor queue 112
- *
- * Rx TC0-TC3 are offset by 32 queues each
- */
- adapter->tx_ring[0]->reg_idx = 0;
- adapter->tx_ring[1]->reg_idx = 64;
- adapter->tx_ring[2]->reg_idx = 96;
- adapter->tx_ring[3]->reg_idx = 112;
- for (i = 0 ; i < dcb_i; i++)
- adapter->rx_ring[i]->reg_idx = i << 5;
-
- ret = true;
- } else {
- ret = false;
+ /* the number of queues is assumed to be symmetric */
+ switch (adapter->hw.mac.type) {
+ case ixgbe_mac_82598EB:
+ for (i = 0; i < dcb_i; i++) {
+ adapter->rx_ring[i]->reg_idx = i << 3;
+ adapter->tx_ring[i]->reg_idx = i << 2;
+ }
+ ret = true;
+ break;
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
+ if (dcb_i == 8) {
+ /*
+ * Tx TC0 starts at: descriptor queue 0
+ * Tx TC1 starts at: descriptor queue 32
+ * Tx TC2 starts at: descriptor queue 64
+ * Tx TC3 starts at: descriptor queue 80
+ * Tx TC4 starts at: descriptor queue 96
+ * Tx TC5 starts at: descriptor queue 104
+ * Tx TC6 starts at: descriptor queue 112
+ * Tx TC7 starts at: descriptor queue 120
+ *
+ * Rx TC0-TC7 are offset by 16 queues each
+ */
+ for (i = 0; i < 3; i++) {
+ adapter->tx_ring[i]->reg_idx = i << 5;
+ adapter->rx_ring[i]->reg_idx = i << 4;
}
- } else {
- ret = false;
+ for ( ; i < 5; i++) {
+ adapter->tx_ring[i]->reg_idx = ((i + 2) << 4);
+ adapter->rx_ring[i]->reg_idx = i << 4;
+ }
+ for ( ; i < dcb_i; i++) {
+ adapter->tx_ring[i]->reg_idx = ((i + 8) << 3);
+ adapter->rx_ring[i]->reg_idx = i << 4;
+ }
+ ret = true;
+ } else if (dcb_i == 4) {
+ /*
+ * Tx TC0 starts at: descriptor queue 0
+ * Tx TC1 starts at: descriptor queue 64
+ * Tx TC2 starts at: descriptor queue 96
+ * Tx TC3 starts at: descriptor queue 112
+ *
+ * Rx TC0-TC3 are offset by 32 queues each
+ */
+ adapter->tx_ring[0]->reg_idx = 0;
+ adapter->tx_ring[1]->reg_idx = 64;
+ adapter->tx_ring[2]->reg_idx = 96;
+ adapter->tx_ring[3]->reg_idx = 112;
+ for (i = 0 ; i < dcb_i; i++)
+ adapter->rx_ring[i]->reg_idx = i << 5;
+ ret = true;
}
- } else {
- ret = false;
+ break;
+ default:
+ break;
}
-
return ret;
}
#endif
@@ -4354,55 +4559,55 @@ static inline bool ixgbe_cache_ring_fdir(struct ixgbe_adapter *adapter)
*/
static inline bool ixgbe_cache_ring_fcoe(struct ixgbe_adapter *adapter)
{
- int i, fcoe_rx_i = 0, fcoe_tx_i = 0;
- bool ret = false;
struct ixgbe_ring_feature *f = &adapter->ring_feature[RING_F_FCOE];
+ int i;
+ u8 fcoe_rx_i = 0, fcoe_tx_i = 0;
+
+ if (!(adapter->flags & IXGBE_FLAG_FCOE_ENABLED))
+ return false;
- if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) {
#ifdef CONFIG_IXGBE_DCB
- if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) {
- struct ixgbe_fcoe *fcoe = &adapter->fcoe;
+ if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) {
+ struct ixgbe_fcoe *fcoe = &adapter->fcoe;
- ixgbe_cache_ring_dcb(adapter);
- /* find out queues in TC for FCoE */
- fcoe_rx_i = adapter->rx_ring[fcoe->tc]->reg_idx + 1;
- fcoe_tx_i = adapter->tx_ring[fcoe->tc]->reg_idx + 1;
- /*
- * In 82599, the number of Tx queues for each traffic
- * class for both 8-TC and 4-TC modes are:
- * TCs : TC0 TC1 TC2 TC3 TC4 TC5 TC6 TC7
- * 8 TCs: 32 32 16 16 8 8 8 8
- * 4 TCs: 64 64 32 32
- * We have max 8 queues for FCoE, where 8 the is
- * FCoE redirection table size. If TC for FCoE is
- * less than or equal to TC3, we have enough queues
- * to add max of 8 queues for FCoE, so we start FCoE
- * tx descriptor from the next one, i.e., reg_idx + 1.
- * If TC for FCoE is above TC3, implying 8 TC mode,
- * and we need 8 for FCoE, we have to take all queues
- * in that traffic class for FCoE.
- */
- if ((f->indices == IXGBE_FCRETA_SIZE) && (fcoe->tc > 3))
- fcoe_tx_i--;
- }
+ ixgbe_cache_ring_dcb(adapter);
+ /* find out queues in TC for FCoE */
+ fcoe_rx_i = adapter->rx_ring[fcoe->tc]->reg_idx + 1;
+ fcoe_tx_i = adapter->tx_ring[fcoe->tc]->reg_idx + 1;
+ /*
+ * In 82599, the number of Tx queues for each traffic
+ * class for both 8-TC and 4-TC modes are:
+ * TCs : TC0 TC1 TC2 TC3 TC4 TC5 TC6 TC7
+ * 8 TCs: 32 32 16 16 8 8 8 8
+ * 4 TCs: 64 64 32 32
+ * We have max 8 queues for FCoE, where 8 the is
+ * FCoE redirection table size. If TC for FCoE is
+ * less than or equal to TC3, we have enough queues
+ * to add max of 8 queues for FCoE, so we start FCoE
+ * Tx queue from the next one, i.e., reg_idx + 1.
+ * If TC for FCoE is above TC3, implying 8 TC mode,
+ * and we need 8 for FCoE, we have to take all queues
+ * in that traffic class for FCoE.
+ */
+ if ((f->indices == IXGBE_FCRETA_SIZE) && (fcoe->tc > 3))
+ fcoe_tx_i--;
+ }
#endif /* CONFIG_IXGBE_DCB */
- if (adapter->flags & IXGBE_FLAG_RSS_ENABLED) {
- if ((adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) ||
- (adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE))
- ixgbe_cache_ring_fdir(adapter);
- else
- ixgbe_cache_ring_rss(adapter);
+ if (adapter->flags & IXGBE_FLAG_RSS_ENABLED) {
+ if ((adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) ||
+ (adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE))
+ ixgbe_cache_ring_fdir(adapter);
+ else
+ ixgbe_cache_ring_rss(adapter);
- fcoe_rx_i = f->mask;
- fcoe_tx_i = f->mask;
- }
- for (i = 0; i < f->indices; i++, fcoe_rx_i++, fcoe_tx_i++) {
- adapter->rx_ring[f->mask + i]->reg_idx = fcoe_rx_i;
- adapter->tx_ring[f->mask + i]->reg_idx = fcoe_tx_i;
- }
- ret = true;
+ fcoe_rx_i = f->mask;
+ fcoe_tx_i = f->mask;
}
- return ret;
+ for (i = 0; i < f->indices; i++, fcoe_rx_i++, fcoe_tx_i++) {
+ adapter->rx_ring[f->mask + i]->reg_idx = fcoe_rx_i;
+ adapter->tx_ring[f->mask + i]->reg_idx = fcoe_tx_i;
+ }
+ return true;
}
#endif /* IXGBE_FCOE */
@@ -4471,65 +4676,55 @@ static void ixgbe_cache_ring_register(struct ixgbe_adapter *adapter)
**/
static int ixgbe_alloc_queues(struct ixgbe_adapter *adapter)
{
- int i;
- int orig_node = adapter->node;
+ int rx = 0, tx = 0, nid = adapter->node;
- for (i = 0; i < adapter->num_tx_queues; i++) {
- struct ixgbe_ring *ring = adapter->tx_ring[i];
- if (orig_node == -1) {
- int cur_node = next_online_node(adapter->node);
- if (cur_node == MAX_NUMNODES)
- cur_node = first_online_node;
- adapter->node = cur_node;
- }
- ring = kzalloc_node(sizeof(struct ixgbe_ring), GFP_KERNEL,
- adapter->node);
+ if (nid < 0 || !node_online(nid))
+ nid = first_online_node;
+
+ for (; tx < adapter->num_tx_queues; tx++) {
+ struct ixgbe_ring *ring;
+
+ ring = kzalloc_node(sizeof(*ring), GFP_KERNEL, nid);
if (!ring)
- ring = kzalloc(sizeof(struct ixgbe_ring), GFP_KERNEL);
+ ring = kzalloc(sizeof(*ring), GFP_KERNEL);
if (!ring)
- goto err_tx_ring_allocation;
+ goto err_allocation;
ring->count = adapter->tx_ring_count;
- ring->queue_index = i;
- ring->numa_node = adapter->node;
+ ring->queue_index = tx;
+ ring->numa_node = nid;
+ ring->dev = &adapter->pdev->dev;
+ ring->netdev = adapter->netdev;
- adapter->tx_ring[i] = ring;
+ adapter->tx_ring[tx] = ring;
}
- /* Restore the adapter's original node */
- adapter->node = orig_node;
+ for (; rx < adapter->num_rx_queues; rx++) {
+ struct ixgbe_ring *ring;
- for (i = 0; i < adapter->num_rx_queues; i++) {
- struct ixgbe_ring *ring = adapter->rx_ring[i];
- if (orig_node == -1) {
- int cur_node = next_online_node(adapter->node);
- if (cur_node == MAX_NUMNODES)
- cur_node = first_online_node;
- adapter->node = cur_node;
- }
- ring = kzalloc_node(sizeof(struct ixgbe_ring), GFP_KERNEL,
- adapter->node);
+ ring = kzalloc_node(sizeof(*ring), GFP_KERNEL, nid);
if (!ring)
- ring = kzalloc(sizeof(struct ixgbe_ring), GFP_KERNEL);
+ ring = kzalloc(sizeof(*ring), GFP_KERNEL);
if (!ring)
- goto err_rx_ring_allocation;
+ goto err_allocation;
ring->count = adapter->rx_ring_count;
- ring->queue_index = i;
- ring->numa_node = adapter->node;
+ ring->queue_index = rx;
+ ring->numa_node = nid;
+ ring->dev = &adapter->pdev->dev;
+ ring->netdev = adapter->netdev;
- adapter->rx_ring[i] = ring;
+ adapter->rx_ring[rx] = ring;
}
- /* Restore the adapter's original node */
- adapter->node = orig_node;
-
ixgbe_cache_ring_register(adapter);
return 0;
-err_rx_ring_allocation:
- for (i = 0; i < adapter->num_tx_queues; i++)
- kfree(adapter->tx_ring[i]);
-err_tx_ring_allocation:
+err_allocation:
+ while (tx)
+ kfree(adapter->tx_ring[--tx]);
+
+ while (rx)
+ kfree(adapter->rx_ring[--rx]);
return -ENOMEM;
}
@@ -4751,6 +4946,11 @@ err_set_interrupt:
return err;
}
+static void ring_free_rcu(struct rcu_head *head)
+{
+ kfree(container_of(head, struct ixgbe_ring, rcu));
+}
+
/**
* ixgbe_clear_interrupt_scheme - Clear the current interrupt scheme settings
* @adapter: board private structure to clear interrupt scheme on
@@ -4767,7 +4967,12 @@ void ixgbe_clear_interrupt_scheme(struct ixgbe_adapter *adapter)
adapter->tx_ring[i] = NULL;
}
for (i = 0; i < adapter->num_rx_queues; i++) {
- kfree(adapter->rx_ring[i]);
+ struct ixgbe_ring *ring = adapter->rx_ring[i];
+
+ /* ixgbe_get_stats64() might access this ring, we must wait
+ * a grace period before freeing it.
+ */
+ call_rcu(&ring->rcu, ring_free_rcu);
adapter->rx_ring[i] = NULL;
}
@@ -4844,6 +5049,7 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter)
int j;
struct tc_configuration *tc;
#endif
+ int max_frame = dev->mtu + ETH_HLEN + ETH_FCS_LEN;
/* PCI config space info */
@@ -4858,11 +5064,14 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter)
adapter->ring_feature[RING_F_RSS].indices = rss;
adapter->flags |= IXGBE_FLAG_RSS_ENABLED;
adapter->ring_feature[RING_F_DCB].indices = IXGBE_MAX_DCB_INDICES;
- if (hw->mac.type == ixgbe_mac_82598EB) {
+ switch (hw->mac.type) {
+ case ixgbe_mac_82598EB:
if (hw->device_id == IXGBE_DEV_ID_82598AT)
adapter->flags |= IXGBE_FLAG_FAN_FAIL_CAPABLE;
adapter->max_msix_q_vectors = MAX_MSIX_Q_VECTORS_82598;
- } else if (hw->mac.type == ixgbe_mac_82599EB) {
+ break;
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
adapter->max_msix_q_vectors = MAX_MSIX_Q_VECTORS_82599;
adapter->flags2 |= IXGBE_FLAG2_RSC_CAPABLE;
adapter->flags2 |= IXGBE_FLAG2_RSC_ENABLED;
@@ -4891,6 +5100,9 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter)
adapter->fcoe.up = IXGBE_FCOE_DEFTC;
#endif
#endif /* IXGBE_FCOE */
+ break;
+ default:
+ break;
}
#ifdef CONFIG_IXGBE_DCB
@@ -4920,8 +5132,8 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter)
#ifdef CONFIG_DCB
adapter->last_lfc_mode = hw->fc.current_mode;
#endif
- hw->fc.high_water = IXGBE_DEFAULT_FCRTH;
- hw->fc.low_water = IXGBE_DEFAULT_FCRTL;
+ hw->fc.high_water = FC_HIGH_WATER(max_frame);
+ hw->fc.low_water = FC_LOW_WATER(max_frame);
hw->fc.pause_time = IXGBE_DEFAULT_FCPAUSE;
hw->fc.send_xon = true;
hw->fc.disable_fc_autoneg = false;
@@ -4959,15 +5171,13 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter)
/**
* ixgbe_setup_tx_resources - allocate Tx resources (Descriptors)
- * @adapter: board private structure
* @tx_ring: tx descriptor ring (for a specific queue) to setup
*
* Return 0 on success, negative on failure
**/
-int ixgbe_setup_tx_resources(struct ixgbe_adapter *adapter,
- struct ixgbe_ring *tx_ring)
+int ixgbe_setup_tx_resources(struct ixgbe_ring *tx_ring)
{
- struct pci_dev *pdev = adapter->pdev;
+ struct device *dev = tx_ring->dev;
int size;
size = sizeof(struct ixgbe_tx_buffer) * tx_ring->count;
@@ -4982,7 +5192,7 @@ int ixgbe_setup_tx_resources(struct ixgbe_adapter *adapter,
tx_ring->size = tx_ring->count * sizeof(union ixgbe_adv_tx_desc);
tx_ring->size = ALIGN(tx_ring->size, 4096);
- tx_ring->desc = dma_alloc_coherent(&pdev->dev, tx_ring->size,
+ tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size,
&tx_ring->dma, GFP_KERNEL);
if (!tx_ring->desc)
goto err;
@@ -4995,7 +5205,7 @@ int ixgbe_setup_tx_resources(struct ixgbe_adapter *adapter,
err:
vfree(tx_ring->tx_buffer_info);
tx_ring->tx_buffer_info = NULL;
- e_err(probe, "Unable to allocate memory for the Tx descriptor ring\n");
+ dev_err(dev, "Unable to allocate memory for the Tx descriptor ring\n");
return -ENOMEM;
}
@@ -5014,7 +5224,7 @@ static int ixgbe_setup_all_tx_resources(struct ixgbe_adapter *adapter)
int i, err = 0;
for (i = 0; i < adapter->num_tx_queues; i++) {
- err = ixgbe_setup_tx_resources(adapter, adapter->tx_ring[i]);
+ err = ixgbe_setup_tx_resources(adapter->tx_ring[i]);
if (!err)
continue;
e_err(probe, "Allocation for Tx Queue %u failed\n", i);
@@ -5026,48 +5236,41 @@ static int ixgbe_setup_all_tx_resources(struct ixgbe_adapter *adapter)
/**
* ixgbe_setup_rx_resources - allocate Rx resources (Descriptors)
- * @adapter: board private structure
* @rx_ring: rx descriptor ring (for a specific queue) to setup
*
* Returns 0 on success, negative on failure
**/
-int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter,
- struct ixgbe_ring *rx_ring)
+int ixgbe_setup_rx_resources(struct ixgbe_ring *rx_ring)
{
- struct pci_dev *pdev = adapter->pdev;
+ struct device *dev = rx_ring->dev;
int size;
size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count;
- rx_ring->rx_buffer_info = vmalloc_node(size, adapter->node);
+ rx_ring->rx_buffer_info = vmalloc_node(size, rx_ring->numa_node);
if (!rx_ring->rx_buffer_info)
rx_ring->rx_buffer_info = vmalloc(size);
- if (!rx_ring->rx_buffer_info) {
- e_err(probe, "vmalloc allocation failed for the Rx "
- "descriptor ring\n");
- goto alloc_failed;
- }
+ if (!rx_ring->rx_buffer_info)
+ goto err;
memset(rx_ring->rx_buffer_info, 0, size);
/* Round up to nearest 4K */
rx_ring->size = rx_ring->count * sizeof(union ixgbe_adv_rx_desc);
rx_ring->size = ALIGN(rx_ring->size, 4096);
- rx_ring->desc = dma_alloc_coherent(&pdev->dev, rx_ring->size,
+ rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size,
&rx_ring->dma, GFP_KERNEL);
- if (!rx_ring->desc) {
- e_err(probe, "Memory allocation failed for the Rx "
- "descriptor ring\n");
- vfree(rx_ring->rx_buffer_info);
- goto alloc_failed;
- }
+ if (!rx_ring->desc)
+ goto err;
rx_ring->next_to_clean = 0;
rx_ring->next_to_use = 0;
return 0;
-
-alloc_failed:
+err:
+ vfree(rx_ring->rx_buffer_info);
+ rx_ring->rx_buffer_info = NULL;
+ dev_err(dev, "Unable to allocate memory for the Rx descriptor ring\n");
return -ENOMEM;
}
@@ -5081,13 +5284,12 @@ alloc_failed:
*
* Return 0 on success, negative on failure
**/
-
static int ixgbe_setup_all_rx_resources(struct ixgbe_adapter *adapter)
{
int i, err = 0;
for (i = 0; i < adapter->num_rx_queues; i++) {
- err = ixgbe_setup_rx_resources(adapter, adapter->rx_ring[i]);
+ err = ixgbe_setup_rx_resources(adapter->rx_ring[i]);
if (!err)
continue;
e_err(probe, "Allocation for Rx Queue %u failed\n", i);
@@ -5099,23 +5301,23 @@ static int ixgbe_setup_all_rx_resources(struct ixgbe_adapter *adapter)
/**
* ixgbe_free_tx_resources - Free Tx Resources per Queue
- * @adapter: board private structure
* @tx_ring: Tx descriptor ring for a specific queue
*
* Free all transmit software resources
**/
-void ixgbe_free_tx_resources(struct ixgbe_adapter *adapter,
- struct ixgbe_ring *tx_ring)
+void ixgbe_free_tx_resources(struct ixgbe_ring *tx_ring)
{
- struct pci_dev *pdev = adapter->pdev;
-
- ixgbe_clean_tx_ring(adapter, tx_ring);
+ ixgbe_clean_tx_ring(tx_ring);
vfree(tx_ring->tx_buffer_info);
tx_ring->tx_buffer_info = NULL;
- dma_free_coherent(&pdev->dev, tx_ring->size, tx_ring->desc,
- tx_ring->dma);
+ /* if not set, then don't free */
+ if (!tx_ring->desc)
+ return;
+
+ dma_free_coherent(tx_ring->dev, tx_ring->size,
+ tx_ring->desc, tx_ring->dma);
tx_ring->desc = NULL;
}
@@ -5132,28 +5334,28 @@ static void ixgbe_free_all_tx_resources(struct ixgbe_adapter *adapter)
for (i = 0; i < adapter->num_tx_queues; i++)
if (adapter->tx_ring[i]->desc)
- ixgbe_free_tx_resources(adapter, adapter->tx_ring[i]);
+ ixgbe_free_tx_resources(adapter->tx_ring[i]);
}
/**
* ixgbe_free_rx_resources - Free Rx Resources
- * @adapter: board private structure
* @rx_ring: ring to clean the resources from
*
* Free all receive software resources
**/
-void ixgbe_free_rx_resources(struct ixgbe_adapter *adapter,
- struct ixgbe_ring *rx_ring)
+void ixgbe_free_rx_resources(struct ixgbe_ring *rx_ring)
{
- struct pci_dev *pdev = adapter->pdev;
-
- ixgbe_clean_rx_ring(adapter, rx_ring);
+ ixgbe_clean_rx_ring(rx_ring);
vfree(rx_ring->rx_buffer_info);
rx_ring->rx_buffer_info = NULL;
- dma_free_coherent(&pdev->dev, rx_ring->size, rx_ring->desc,
- rx_ring->dma);
+ /* if not set, then don't free */
+ if (!rx_ring->desc)
+ return;
+
+ dma_free_coherent(rx_ring->dev, rx_ring->size,
+ rx_ring->desc, rx_ring->dma);
rx_ring->desc = NULL;
}
@@ -5170,7 +5372,7 @@ static void ixgbe_free_all_rx_resources(struct ixgbe_adapter *adapter)
for (i = 0; i < adapter->num_rx_queues; i++)
if (adapter->rx_ring[i]->desc)
- ixgbe_free_rx_resources(adapter, adapter->rx_ring[i]);
+ ixgbe_free_rx_resources(adapter->rx_ring[i]);
}
/**
@@ -5183,6 +5385,7 @@ static void ixgbe_free_all_rx_resources(struct ixgbe_adapter *adapter)
static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu)
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
+ struct ixgbe_hw *hw = &adapter->hw;
int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN;
/* MTU < 68 is an error and causes problems on some kernels */
@@ -5193,6 +5396,9 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu)
/* must set new MTU before calling down or up */
netdev->mtu = new_mtu;
+ hw->fc.high_water = FC_HIGH_WATER(max_frame);
+ hw->fc.low_water = FC_LOW_WATER(max_frame);
+
if (netif_running(netdev))
ixgbe_reinit_locked(adapter);
@@ -5288,8 +5494,8 @@ static int ixgbe_close(struct net_device *netdev)
#ifdef CONFIG_PM
static int ixgbe_resume(struct pci_dev *pdev)
{
- struct net_device *netdev = pci_get_drvdata(pdev);
- struct ixgbe_adapter *adapter = netdev_priv(netdev);
+ struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
+ struct net_device *netdev = adapter->netdev;
u32 err;
pci_set_power_state(pdev, PCI_D0);
@@ -5320,7 +5526,7 @@ static int ixgbe_resume(struct pci_dev *pdev)
IXGBE_WRITE_REG(&adapter->hw, IXGBE_WUS, ~0);
if (netif_running(netdev)) {
- err = ixgbe_open(adapter->netdev);
+ err = ixgbe_open(netdev);
if (err)
return err;
}
@@ -5333,8 +5539,8 @@ static int ixgbe_resume(struct pci_dev *pdev)
static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake)
{
- struct net_device *netdev = pci_get_drvdata(pdev);
- struct ixgbe_adapter *adapter = netdev_priv(netdev);
+ struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
+ struct net_device *netdev = adapter->netdev;
struct ixgbe_hw *hw = &adapter->hw;
u32 ctrl, fctrl;
u32 wufc = adapter->wol;
@@ -5351,6 +5557,8 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake)
ixgbe_free_all_rx_resources(adapter);
}
+ ixgbe_clear_interrupt_scheme(adapter);
+
#ifdef CONFIG_PM
retval = pci_save_state(pdev);
if (retval)
@@ -5377,15 +5585,20 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake)
IXGBE_WRITE_REG(hw, IXGBE_WUFC, 0);
}
- if (wufc && hw->mac.type == ixgbe_mac_82599EB)
- pci_wake_from_d3(pdev, true);
- else
+ switch (hw->mac.type) {
+ case ixgbe_mac_82598EB:
pci_wake_from_d3(pdev, false);
+ break;
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
+ pci_wake_from_d3(pdev, !!wufc);
+ break;
+ default:
+ break;
+ }
*enable_wake = !!wufc;
- ixgbe_clear_interrupt_scheme(adapter);
-
ixgbe_release_hw_control(adapter);
pci_disable_device(pdev);
@@ -5434,10 +5647,12 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
struct ixgbe_hw *hw = &adapter->hw;
+ struct ixgbe_hw_stats *hwstats = &adapter->stats;
u64 total_mpc = 0;
u32 i, missed_rx = 0, mpc, bprc, lxon, lxoff, xon_off_tot;
- u64 non_eop_descs = 0, restart_queue = 0;
- struct ixgbe_hw_stats *hwstats = &adapter->stats;
+ u64 non_eop_descs = 0, restart_queue = 0, tx_busy = 0;
+ u64 alloc_rx_page_failed = 0, alloc_rx_buff_failed = 0;
+ u64 bytes = 0, packets = 0;
if (test_bit(__IXGBE_DOWN, &adapter->state) ||
test_bit(__IXGBE_RESETTING, &adapter->state))
@@ -5450,21 +5665,41 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
adapter->hw_rx_no_dma_resources +=
IXGBE_READ_REG(hw, IXGBE_QPRDC(i));
for (i = 0; i < adapter->num_rx_queues; i++) {
- rsc_count += adapter->rx_ring[i]->rsc_count;
- rsc_flush += adapter->rx_ring[i]->rsc_flush;
+ rsc_count += adapter->rx_ring[i]->rx_stats.rsc_count;
+ rsc_flush += adapter->rx_ring[i]->rx_stats.rsc_flush;
}
adapter->rsc_total_count = rsc_count;
adapter->rsc_total_flush = rsc_flush;
}
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ struct ixgbe_ring *rx_ring = adapter->rx_ring[i];
+ non_eop_descs += rx_ring->rx_stats.non_eop_descs;
+ alloc_rx_page_failed += rx_ring->rx_stats.alloc_rx_page_failed;
+ alloc_rx_buff_failed += rx_ring->rx_stats.alloc_rx_buff_failed;
+ bytes += rx_ring->stats.bytes;
+ packets += rx_ring->stats.packets;
+ }
+ adapter->non_eop_descs = non_eop_descs;
+ adapter->alloc_rx_page_failed = alloc_rx_page_failed;
+ adapter->alloc_rx_buff_failed = alloc_rx_buff_failed;
+ netdev->stats.rx_bytes = bytes;
+ netdev->stats.rx_packets = packets;
+
+ bytes = 0;
+ packets = 0;
/* gather some stats to the adapter struct that are per queue */
- for (i = 0; i < adapter->num_tx_queues; i++)
- restart_queue += adapter->tx_ring[i]->restart_queue;
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ struct ixgbe_ring *tx_ring = adapter->tx_ring[i];
+ restart_queue += tx_ring->tx_stats.restart_queue;
+ tx_busy += tx_ring->tx_stats.tx_busy;
+ bytes += tx_ring->stats.bytes;
+ packets += tx_ring->stats.packets;
+ }
adapter->restart_queue = restart_queue;
-
- for (i = 0; i < adapter->num_rx_queues; i++)
- non_eop_descs += adapter->rx_ring[i]->non_eop_descs;
- adapter->non_eop_descs = non_eop_descs;
+ adapter->tx_busy = tx_busy;
+ netdev->stats.tx_bytes = bytes;
+ netdev->stats.tx_packets = packets;
hwstats->crcerrs += IXGBE_READ_REG(hw, IXGBE_CRCERRS);
for (i = 0; i < 8; i++) {
@@ -5479,17 +5714,18 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
hwstats->qbtc[i] += IXGBE_READ_REG(hw, IXGBE_QBTC(i));
hwstats->qprc[i] += IXGBE_READ_REG(hw, IXGBE_QPRC(i));
hwstats->qbrc[i] += IXGBE_READ_REG(hw, IXGBE_QBRC(i));
- if (hw->mac.type == ixgbe_mac_82599EB) {
- hwstats->pxonrxc[i] +=
- IXGBE_READ_REG(hw, IXGBE_PXONRXCNT(i));
- hwstats->pxoffrxc[i] +=
- IXGBE_READ_REG(hw, IXGBE_PXOFFRXCNT(i));
- hwstats->qprdc[i] += IXGBE_READ_REG(hw, IXGBE_QPRDC(i));
- } else {
+ switch (hw->mac.type) {
+ case ixgbe_mac_82598EB:
hwstats->pxonrxc[i] +=
IXGBE_READ_REG(hw, IXGBE_PXONRXC(i));
- hwstats->pxoffrxc[i] +=
- IXGBE_READ_REG(hw, IXGBE_PXOFFRXC(i));
+ break;
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
+ hwstats->pxonrxc[i] +=
+ IXGBE_READ_REG(hw, IXGBE_PXONRXCNT(i));
+ break;
+ default:
+ break;
}
hwstats->pxontxc[i] += IXGBE_READ_REG(hw, IXGBE_PXONTXC(i));
hwstats->pxofftxc[i] += IXGBE_READ_REG(hw, IXGBE_PXOFFTXC(i));
@@ -5498,21 +5734,25 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
/* work around hardware counting issue */
hwstats->gprc -= missed_rx;
+ ixgbe_update_xoff_received(adapter);
+
/* 82598 hardware only has a 32 bit counter in the high register */
- if (hw->mac.type == ixgbe_mac_82599EB) {
- u64 tmp;
+ switch (hw->mac.type) {
+ case ixgbe_mac_82598EB:
+ hwstats->lxonrxc += IXGBE_READ_REG(hw, IXGBE_LXONRXC);
+ hwstats->gorc += IXGBE_READ_REG(hw, IXGBE_GORCH);
+ hwstats->gotc += IXGBE_READ_REG(hw, IXGBE_GOTCH);
+ hwstats->tor += IXGBE_READ_REG(hw, IXGBE_TORH);
+ break;
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
hwstats->gorc += IXGBE_READ_REG(hw, IXGBE_GORCL);
- tmp = IXGBE_READ_REG(hw, IXGBE_GORCH) & 0xF;
- /* 4 high bits of GORC */
- hwstats->gorc += (tmp << 32);
+ IXGBE_READ_REG(hw, IXGBE_GORCH); /* to clear */
hwstats->gotc += IXGBE_READ_REG(hw, IXGBE_GOTCL);
- tmp = IXGBE_READ_REG(hw, IXGBE_GOTCH) & 0xF;
- /* 4 high bits of GOTC */
- hwstats->gotc += (tmp << 32);
+ IXGBE_READ_REG(hw, IXGBE_GOTCH); /* to clear */
hwstats->tor += IXGBE_READ_REG(hw, IXGBE_TORL);
- IXGBE_READ_REG(hw, IXGBE_TORH); /* to clear */
+ IXGBE_READ_REG(hw, IXGBE_TORH); /* to clear */
hwstats->lxonrxc += IXGBE_READ_REG(hw, IXGBE_LXONRXCNT);
- hwstats->lxoffrxc += IXGBE_READ_REG(hw, IXGBE_LXOFFRXCNT);
hwstats->fdirmatch += IXGBE_READ_REG(hw, IXGBE_FDIRMATCH);
hwstats->fdirmiss += IXGBE_READ_REG(hw, IXGBE_FDIRMISS);
#ifdef IXGBE_FCOE
@@ -5523,12 +5763,9 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
hwstats->fcoedwrc += IXGBE_READ_REG(hw, IXGBE_FCOEDWRC);
hwstats->fcoedwtc += IXGBE_READ_REG(hw, IXGBE_FCOEDWTC);
#endif /* IXGBE_FCOE */
- } else {
- hwstats->lxonrxc += IXGBE_READ_REG(hw, IXGBE_LXONRXC);
- hwstats->lxoffrxc += IXGBE_READ_REG(hw, IXGBE_LXOFFRXC);
- hwstats->gorc += IXGBE_READ_REG(hw, IXGBE_GORCH);
- hwstats->gotc += IXGBE_READ_REG(hw, IXGBE_GOTCH);
- hwstats->tor += IXGBE_READ_REG(hw, IXGBE_TORH);
+ break;
+ default:
+ break;
}
bprc = IXGBE_READ_REG(hw, IXGBE_BPRC);
hwstats->bprc += bprc;
@@ -5701,8 +5938,8 @@ static void ixgbe_fdir_reinit_task(struct work_struct *work)
if (ixgbe_reinit_fdir_tables_82599(hw) == 0) {
for (i = 0; i < adapter->num_tx_queues; i++)
- set_bit(__IXGBE_FDIR_INIT_DONE,
- &(adapter->tx_ring[i]->reinit_state));
+ set_bit(__IXGBE_TX_FDIR_INIT_DONE,
+ &(adapter->tx_ring[i]->state));
} else {
e_err(probe, "failed to finish FDIR re-initialization, "
"ignored adding FDIR ATR filters\n");
@@ -5764,17 +6001,27 @@ static void ixgbe_watchdog_task(struct work_struct *work)
if (!netif_carrier_ok(netdev)) {
bool flow_rx, flow_tx;
- if (hw->mac.type == ixgbe_mac_82599EB) {
- u32 mflcn = IXGBE_READ_REG(hw, IXGBE_MFLCN);
- u32 fccfg = IXGBE_READ_REG(hw, IXGBE_FCCFG);
- flow_rx = !!(mflcn & IXGBE_MFLCN_RFCE);
- flow_tx = !!(fccfg & IXGBE_FCCFG_TFCE_802_3X);
- } else {
+ switch (hw->mac.type) {
+ case ixgbe_mac_82598EB: {
u32 frctl = IXGBE_READ_REG(hw, IXGBE_FCTRL);
u32 rmcs = IXGBE_READ_REG(hw, IXGBE_RMCS);
flow_rx = !!(frctl & IXGBE_FCTRL_RFCE);
flow_tx = !!(rmcs & IXGBE_RMCS_TFCE_802_3X);
}
+ break;
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540: {
+ u32 mflcn = IXGBE_READ_REG(hw, IXGBE_MFLCN);
+ u32 fccfg = IXGBE_READ_REG(hw, IXGBE_FCCFG);
+ flow_rx = !!(mflcn & IXGBE_MFLCN_RFCE);
+ flow_tx = !!(fccfg & IXGBE_FCCFG_TFCE_802_3X);
+ }
+ break;
+ default:
+ flow_tx = false;
+ flow_rx = false;
+ break;
+ }
e_info(drv, "NIC Link is Up %s, Flow Control: %s\n",
(link_speed == IXGBE_LINK_SPEED_10GB_FULL ?
@@ -5788,7 +6035,10 @@ static void ixgbe_watchdog_task(struct work_struct *work)
netif_carrier_on(netdev);
} else {
/* Force detection of hung controller */
- adapter->detect_tx_hung = true;
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ tx_ring = adapter->tx_ring[i];
+ set_check_for_tx_hang(tx_ring);
+ }
}
} else {
adapter->link_up = false;
@@ -6000,15 +6250,17 @@ static bool ixgbe_tx_csum(struct ixgbe_adapter *adapter,
static int ixgbe_tx_map(struct ixgbe_adapter *adapter,
struct ixgbe_ring *tx_ring,
struct sk_buff *skb, u32 tx_flags,
- unsigned int first)
+ unsigned int first, const u8 hdr_len)
{
- struct pci_dev *pdev = adapter->pdev;
+ struct device *dev = tx_ring->dev;
struct ixgbe_tx_buffer *tx_buffer_info;
unsigned int len;
unsigned int total = skb->len;
unsigned int offset = 0, size, count = 0, i;
unsigned int nr_frags = skb_shinfo(skb)->nr_frags;
unsigned int f;
+ unsigned int bytecount = skb->len;
+ u16 gso_segs = 1;
i = tx_ring->next_to_use;
@@ -6023,10 +6275,10 @@ static int ixgbe_tx_map(struct ixgbe_adapter *adapter,
tx_buffer_info->length = size;
tx_buffer_info->mapped_as_page = false;
- tx_buffer_info->dma = dma_map_single(&pdev->dev,
+ tx_buffer_info->dma = dma_map_single(dev,
skb->data + offset,
size, DMA_TO_DEVICE);
- if (dma_mapping_error(&pdev->dev, tx_buffer_info->dma))
+ if (dma_mapping_error(dev, tx_buffer_info->dma))
goto dma_error;
tx_buffer_info->time_stamp = jiffies;
tx_buffer_info->next_to_watch = i;
@@ -6059,12 +6311,12 @@ static int ixgbe_tx_map(struct ixgbe_adapter *adapter,
size = min(len, (uint)IXGBE_MAX_DATA_PER_TXD);
tx_buffer_info->length = size;
- tx_buffer_info->dma = dma_map_page(&adapter->pdev->dev,
+ tx_buffer_info->dma = dma_map_page(dev,
frag->page,
offset, size,
DMA_TO_DEVICE);
tx_buffer_info->mapped_as_page = true;
- if (dma_mapping_error(&pdev->dev, tx_buffer_info->dma))
+ if (dma_mapping_error(dev, tx_buffer_info->dma))
goto dma_error;
tx_buffer_info->time_stamp = jiffies;
tx_buffer_info->next_to_watch = i;
@@ -6078,6 +6330,19 @@ static int ixgbe_tx_map(struct ixgbe_adapter *adapter,
break;
}
+ if (tx_flags & IXGBE_TX_FLAGS_TSO)
+ gso_segs = skb_shinfo(skb)->gso_segs;
+#ifdef IXGBE_FCOE
+ /* adjust for FCoE Sequence Offload */
+ else if (tx_flags & IXGBE_TX_FLAGS_FSO)
+ gso_segs = DIV_ROUND_UP(skb->len - hdr_len,
+ skb_shinfo(skb)->gso_size);
+#endif /* IXGBE_FCOE */
+ bytecount += (gso_segs - 1) * hdr_len;
+
+ /* multiply data chunks by size of headers */
+ tx_ring->tx_buffer_info[i].bytecount = bytecount;
+ tx_ring->tx_buffer_info[i].gso_segs = gso_segs;
tx_ring->tx_buffer_info[i].skb = skb;
tx_ring->tx_buffer_info[first].next_to_watch = i;
@@ -6099,14 +6364,13 @@ dma_error:
i += tx_ring->count;
i--;
tx_buffer_info = &tx_ring->tx_buffer_info[i];
- ixgbe_unmap_and_free_tx_resource(adapter, tx_buffer_info);
+ ixgbe_unmap_and_free_tx_resource(tx_ring, tx_buffer_info);
}
return 0;
}
-static void ixgbe_tx_queue(struct ixgbe_adapter *adapter,
- struct ixgbe_ring *tx_ring,
+static void ixgbe_tx_queue(struct ixgbe_ring *tx_ring,
int tx_flags, int count, u32 paylen, u8 hdr_len)
{
union ixgbe_adv_tx_desc *tx_desc = NULL;
@@ -6171,60 +6435,46 @@ static void ixgbe_tx_queue(struct ixgbe_adapter *adapter,
wmb();
tx_ring->next_to_use = i;
- writel(i, adapter->hw.hw_addr + tx_ring->tail);
+ writel(i, tx_ring->tail);
}
static void ixgbe_atr(struct ixgbe_adapter *adapter, struct sk_buff *skb,
- int queue, u32 tx_flags, __be16 protocol)
+ u8 queue, u32 tx_flags, __be16 protocol)
{
struct ixgbe_atr_input atr_input;
- struct tcphdr *th;
struct iphdr *iph = ip_hdr(skb);
struct ethhdr *eth = (struct ethhdr *)skb->data;
- u16 vlan_id, src_port, dst_port, flex_bytes;
- u32 src_ipv4_addr, dst_ipv4_addr;
- u8 l4type = 0;
+ struct tcphdr *th;
+ u16 vlan_id;
- /* Right now, we support IPv4 only */
- if (protocol != htons(ETH_P_IP))
- return;
- /* check if we're UDP or TCP */
- if (iph->protocol == IPPROTO_TCP) {
- th = tcp_hdr(skb);
- src_port = th->source;
- dst_port = th->dest;
- l4type |= IXGBE_ATR_L4TYPE_TCP;
- /* l4type IPv4 type is 0, no need to assign */
- } else {
- /* Unsupported L4 header, just bail here */
+ /* Right now, we support IPv4 w/ TCP only */
+ if (protocol != htons(ETH_P_IP) ||
+ iph->protocol != IPPROTO_TCP)
return;
- }
memset(&atr_input, 0, sizeof(struct ixgbe_atr_input));
vlan_id = (tx_flags & IXGBE_TX_FLAGS_VLAN_MASK) >>
IXGBE_TX_FLAGS_VLAN_SHIFT;
- src_ipv4_addr = iph->saddr;
- dst_ipv4_addr = iph->daddr;
- flex_bytes = eth->h_proto;
+
+ th = tcp_hdr(skb);
ixgbe_atr_set_vlan_id_82599(&atr_input, vlan_id);
- ixgbe_atr_set_src_port_82599(&atr_input, dst_port);
- ixgbe_atr_set_dst_port_82599(&atr_input, src_port);
- ixgbe_atr_set_flex_byte_82599(&atr_input, flex_bytes);
- ixgbe_atr_set_l4type_82599(&atr_input, l4type);
+ ixgbe_atr_set_src_port_82599(&atr_input, th->dest);
+ ixgbe_atr_set_dst_port_82599(&atr_input, th->source);
+ ixgbe_atr_set_flex_byte_82599(&atr_input, eth->h_proto);
+ ixgbe_atr_set_l4type_82599(&atr_input, IXGBE_ATR_L4TYPE_TCP);
/* src and dst are inverted, think how the receiver sees them */
- ixgbe_atr_set_src_ipv4_82599(&atr_input, dst_ipv4_addr);
- ixgbe_atr_set_dst_ipv4_82599(&atr_input, src_ipv4_addr);
+ ixgbe_atr_set_src_ipv4_82599(&atr_input, iph->daddr);
+ ixgbe_atr_set_dst_ipv4_82599(&atr_input, iph->saddr);
/* This assumes the Rx queue and Tx queue are bound to the same CPU */
ixgbe_fdir_add_signature_filter_82599(&adapter->hw, &atr_input, queue);
}
-static int __ixgbe_maybe_stop_tx(struct net_device *netdev,
- struct ixgbe_ring *tx_ring, int size)
+static int __ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, int size)
{
- netif_stop_subqueue(netdev, tx_ring->queue_index);
+ netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
/* Herbert's original patch had:
* smp_mb__after_netif_stop_queue();
* but since that doesn't exist yet, just open code it. */
@@ -6236,17 +6486,16 @@ static int __ixgbe_maybe_stop_tx(struct net_device *netdev,
return -EBUSY;
/* A reprieve! - use start_queue because it doesn't call schedule */
- netif_start_subqueue(netdev, tx_ring->queue_index);
- ++tx_ring->restart_queue;
+ netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index);
+ ++tx_ring->tx_stats.restart_queue;
return 0;
}
-static int ixgbe_maybe_stop_tx(struct net_device *netdev,
- struct ixgbe_ring *tx_ring, int size)
+static int ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, int size)
{
if (likely(IXGBE_DESC_UNUSED(tx_ring) >= size))
return 0;
- return __ixgbe_maybe_stop_tx(netdev, tx_ring, size);
+ return __ixgbe_maybe_stop_tx(tx_ring, size);
}
static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb)
@@ -6291,10 +6540,11 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb)
return skb_tx_hash(dev, skb);
}
-netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, struct net_device *netdev,
+netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
struct ixgbe_adapter *adapter,
struct ixgbe_ring *tx_ring)
{
+ struct net_device *netdev = tx_ring->netdev;
struct netdev_queue *txq;
unsigned int first;
unsigned int tx_flags = 0;
@@ -6352,8 +6602,8 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, struct net_device *netdev
for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size);
- if (ixgbe_maybe_stop_tx(netdev, tx_ring, count)) {
- adapter->tx_busy++;
+ if (ixgbe_maybe_stop_tx(tx_ring, count)) {
+ tx_ring->tx_stats.tx_busy++;
return NETDEV_TX_BUSY;
}
@@ -6387,14 +6637,14 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, struct net_device *netdev
tx_flags |= IXGBE_TX_FLAGS_CSUM;
}
- count = ixgbe_tx_map(adapter, tx_ring, skb, tx_flags, first);
+ count = ixgbe_tx_map(adapter, tx_ring, skb, tx_flags, first, hdr_len);
if (count) {
/* add the ATR filter if ATR is on */
if (tx_ring->atr_sample_rate) {
++tx_ring->atr_count;
if ((tx_ring->atr_count >= tx_ring->atr_sample_rate) &&
- test_bit(__IXGBE_FDIR_INIT_DONE,
- &tx_ring->reinit_state)) {
+ test_bit(__IXGBE_TX_FDIR_INIT_DONE,
+ &tx_ring->state)) {
ixgbe_atr(adapter, skb, tx_ring->queue_index,
tx_flags, protocol);
tx_ring->atr_count = 0;
@@ -6403,9 +6653,8 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, struct net_device *netdev
txq = netdev_get_tx_queue(netdev, tx_ring->queue_index);
txq->tx_bytes += skb->len;
txq->tx_packets++;
- ixgbe_tx_queue(adapter, tx_ring, tx_flags, count, skb->len,
- hdr_len);
- ixgbe_maybe_stop_tx(netdev, tx_ring, DESC_NEEDED);
+ ixgbe_tx_queue(tx_ring, tx_flags, count, skb->len, hdr_len);
+ ixgbe_maybe_stop_tx(tx_ring, DESC_NEEDED);
} else {
dev_kfree_skb_any(skb);
@@ -6422,7 +6671,7 @@ static netdev_tx_t ixgbe_xmit_frame(struct sk_buff *skb, struct net_device *netd
struct ixgbe_ring *tx_ring;
tx_ring = adapter->tx_ring[skb->queue_mapping];
- return ixgbe_xmit_frame_ring(skb, netdev, adapter, tx_ring);
+ return ixgbe_xmit_frame_ring(skb, adapter, tx_ring);
}
/**
@@ -6563,20 +6812,23 @@ static struct rtnl_link_stats64 *ixgbe_get_stats64(struct net_device *netdev,
/* accurate rx/tx bytes/packets stats */
dev_txq_stats_fold(netdev, stats);
+ rcu_read_lock();
for (i = 0; i < adapter->num_rx_queues; i++) {
- struct ixgbe_ring *ring = adapter->rx_ring[i];
+ struct ixgbe_ring *ring = ACCESS_ONCE(adapter->rx_ring[i]);
u64 bytes, packets;
unsigned int start;
- do {
- start = u64_stats_fetch_begin_bh(&ring->syncp);
- packets = ring->stats.packets;
- bytes = ring->stats.bytes;
- } while (u64_stats_fetch_retry_bh(&ring->syncp, start));
- stats->rx_packets += packets;
- stats->rx_bytes += bytes;
+ if (ring) {
+ do {
+ start = u64_stats_fetch_begin_bh(&ring->syncp);
+ packets = ring->stats.packets;
+ bytes = ring->stats.bytes;
+ } while (u64_stats_fetch_retry_bh(&ring->syncp, start));
+ stats->rx_packets += packets;
+ stats->rx_bytes += bytes;
+ }
}
-
+ rcu_read_unlock();
/* following stats updated by ixgbe_watchdog_task() */
stats->multicast = netdev->stats.multicast;
stats->rx_errors = netdev->stats.rx_errors;
@@ -6758,8 +7010,8 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev,
SET_NETDEV_DEV(netdev, &pdev->dev);
- pci_set_drvdata(pdev, netdev);
adapter = netdev_priv(netdev);
+ pci_set_drvdata(pdev, adapter);
adapter->netdev = netdev;
adapter->pdev = pdev;
@@ -6832,8 +7084,14 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev,
goto err_sw_init;
/* Make it possible the adapter to be woken up via WOL */
- if (adapter->hw.mac.type == ixgbe_mac_82599EB)
+ switch (adapter->hw.mac.type) {
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
IXGBE_WRITE_REG(&adapter->hw, IXGBE_WUS, ~0);
+ break;
+ default:
+ break;
+ }
/*
* If there is a fan on this device and it has failed log the
@@ -6942,7 +7200,7 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev,
}
/* power down the optics */
- if (hw->phy.multispeed_fiber)
+ if (hw->phy.multispeed_fiber && hw->mac.ops.disable_tx_laser)
hw->mac.ops.disable_tx_laser(hw);
init_timer(&adapter->watchdog_timer);
@@ -6957,6 +7215,13 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev,
goto err_sw_init;
switch (pdev->device) {
+ case IXGBE_DEV_ID_82599_COMBO_BACKPLANE:
+ /* All except this subdevice support WOL */
+ if (pdev->subsystem_device ==
+ IXGBE_SUBDEV_ID_82599_KX4_KR_MEZZ) {
+ adapter->wol = 0;
+ break;
+ }
case IXGBE_DEV_ID_82599_KX4:
adapter->wol = (IXGBE_WUFC_MAG | IXGBE_WUFC_EX |
IXGBE_WUFC_MC | IXGBE_WUFC_BC);
@@ -7082,8 +7347,8 @@ err_dma:
**/
static void __devexit ixgbe_remove(struct pci_dev *pdev)
{
- struct net_device *netdev = pci_get_drvdata(pdev);
- struct ixgbe_adapter *adapter = netdev_priv(netdev);
+ struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
+ struct net_device *netdev = adapter->netdev;
set_bit(__IXGBE_DOWN, &adapter->state);
/* clear the module not found bit to make sure the worker won't
@@ -7153,8 +7418,8 @@ static void __devexit ixgbe_remove(struct pci_dev *pdev)
static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev,
pci_channel_state_t state)
{
- struct net_device *netdev = pci_get_drvdata(pdev);
- struct ixgbe_adapter *adapter = netdev_priv(netdev);
+ struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
+ struct net_device *netdev = adapter->netdev;
netif_device_detach(netdev);
@@ -7177,8 +7442,7 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev,
*/
static pci_ers_result_t ixgbe_io_slot_reset(struct pci_dev *pdev)
{
- struct net_device *netdev = pci_get_drvdata(pdev);
- struct ixgbe_adapter *adapter = netdev_priv(netdev);
+ struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
pci_ers_result_t result;
int err;
@@ -7216,8 +7480,8 @@ static pci_ers_result_t ixgbe_io_slot_reset(struct pci_dev *pdev)
*/
static void ixgbe_io_resume(struct pci_dev *pdev)
{
- struct net_device *netdev = pci_get_drvdata(pdev);
- struct ixgbe_adapter *adapter = netdev_priv(netdev);
+ struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
+ struct net_device *netdev = adapter->netdev;
if (netif_running(netdev)) {
if (ixgbe_up(adapter)) {
@@ -7282,6 +7546,7 @@ static void __exit ixgbe_exit_module(void)
dca_unregister_notify(&dca_notifier);
#endif
pci_unregister_driver(&ixgbe_driver);
+ rcu_barrier(); /* Wait for completion of call_rcu()'s */
}
#ifdef CONFIG_IXGBE_DCA
diff --git a/drivers/net/ixgbe/ixgbe_mbx.c b/drivers/net/ixgbe/ixgbe_mbx.c
index 471f0f2..027c628 100644
--- a/drivers/net/ixgbe/ixgbe_mbx.c
+++ b/drivers/net/ixgbe/ixgbe_mbx.c
@@ -319,8 +319,14 @@ static s32 ixgbe_check_for_rst_pf(struct ixgbe_hw *hw, u16 vf_number)
u32 vflre = 0;
s32 ret_val = IXGBE_ERR_MBX;
- if (hw->mac.type == ixgbe_mac_82599EB)
+ switch (hw->mac.type) {
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
vflre = IXGBE_READ_REG(hw, IXGBE_VFLRE(reg_offset));
+ break;
+ default:
+ break;
+ }
if (vflre & (1 << vf_shift)) {
ret_val = 0;
@@ -439,22 +445,26 @@ void ixgbe_init_mbx_params_pf(struct ixgbe_hw *hw)
{
struct ixgbe_mbx_info *mbx = &hw->mbx;
- if (hw->mac.type != ixgbe_mac_82599EB)
- return;
-
- mbx->timeout = 0;
- mbx->usec_delay = 0;
-
- mbx->size = IXGBE_VFMAILBOX_SIZE;
-
- mbx->stats.msgs_tx = 0;
- mbx->stats.msgs_rx = 0;
- mbx->stats.reqs = 0;
- mbx->stats.acks = 0;
- mbx->stats.rsts = 0;
+ switch (hw->mac.type) {
+ case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
+ mbx->timeout = 0;
+ mbx->usec_delay = 0;
+
+ mbx->size = IXGBE_VFMAILBOX_SIZE;
+
+ mbx->stats.msgs_tx = 0;
+ mbx->stats.msgs_rx = 0;
+ mbx->stats.reqs = 0;
+ mbx->stats.acks = 0;
+ mbx->stats.rsts = 0;
+ break;
+ default:
+ break;
+ }
}
-struct ixgbe_mbx_operations mbx_ops_82599 = {
+struct ixgbe_mbx_operations mbx_ops_generic = {
.read = ixgbe_read_mbx_pf,
.write = ixgbe_write_mbx_pf,
.read_posted = ixgbe_read_posted_mbx,
diff --git a/drivers/net/ixgbe/ixgbe_mbx.h b/drivers/net/ixgbe/ixgbe_mbx.h
index 7e0d08f..3df9b15 100644
--- a/drivers/net/ixgbe/ixgbe_mbx.h
+++ b/drivers/net/ixgbe/ixgbe_mbx.h
@@ -88,6 +88,6 @@ s32 ixgbe_check_for_ack(struct ixgbe_hw *, u16);
s32 ixgbe_check_for_rst(struct ixgbe_hw *, u16);
void ixgbe_init_mbx_params_pf(struct ixgbe_hw *);
-extern struct ixgbe_mbx_operations mbx_ops_82599;
+extern struct ixgbe_mbx_operations mbx_ops_generic;
#endif /* _IXGBE_MBX_H_ */
diff --git a/drivers/net/ixgbe/ixgbe_phy.c b/drivers/net/ixgbe/ixgbe_phy.c
index 6c0d42e..c445fbc 100644
--- a/drivers/net/ixgbe/ixgbe_phy.c
+++ b/drivers/net/ixgbe/ixgbe_phy.c
@@ -115,6 +115,9 @@ static enum ixgbe_phy_type ixgbe_get_phy_type_from_id(u32 phy_id)
case TN1010_PHY_ID:
phy_type = ixgbe_phy_tn;
break;
+ case AQ1202_PHY_ID:
+ phy_type = ixgbe_phy_aq;
+ break;
case QT2022_PHY_ID:
phy_type = ixgbe_phy_qt;
break;
@@ -425,6 +428,39 @@ s32 ixgbe_setup_phy_link_speed_generic(struct ixgbe_hw *hw,
}
/**
+ * ixgbe_get_copper_link_capabilities_generic - Determines link capabilities
+ * @hw: pointer to hardware structure
+ * @speed: pointer to link speed
+ * @autoneg: boolean auto-negotiation value
+ *
+ * Determines the link capabilities by reading the AUTOC register.
+ */
+s32 ixgbe_get_copper_link_capabilities_generic(struct ixgbe_hw *hw,
+ ixgbe_link_speed *speed,
+ bool *autoneg)
+{
+ s32 status = IXGBE_ERR_LINK_SETUP;
+ u16 speed_ability;
+
+ *speed = 0;
+ *autoneg = true;
+
+ status = hw->phy.ops.read_reg(hw, MDIO_SPEED, MDIO_MMD_PMAPMD,
+ &speed_ability);
+
+ if (status == 0) {
+ if (speed_ability & MDIO_SPEED_10G)
+ *speed |= IXGBE_LINK_SPEED_10GB_FULL;
+ if (speed_ability & MDIO_PMA_SPEED_1000)
+ *speed |= IXGBE_LINK_SPEED_1GB_FULL;
+ if (speed_ability & MDIO_PMA_SPEED_100)
+ *speed |= IXGBE_LINK_SPEED_100_FULL;
+ }
+
+ return status;
+}
+
+/**
* ixgbe_reset_phy_nl - Performs a PHY reset
* @hw: pointer to hardware structure
**/
@@ -1378,6 +1414,22 @@ s32 ixgbe_get_phy_firmware_version_tnx(struct ixgbe_hw *hw,
}
/**
+ * ixgbe_get_phy_firmware_version_generic - Gets the PHY Firmware Version
+ * @hw: pointer to hardware structure
+ * @firmware_version: pointer to the PHY Firmware Version
+**/
+s32 ixgbe_get_phy_firmware_version_generic(struct ixgbe_hw *hw,
+ u16 *firmware_version)
+{
+ s32 status = 0;
+
+ status = hw->phy.ops.read_reg(hw, AQ_FW_REV, MDIO_MMD_VEND1,
+ firmware_version);
+
+ return status;
+}
+
+/**
* ixgbe_tn_check_overtemp - Checks if an overtemp occured.
* @hw: pointer to hardware structure
*
diff --git a/drivers/net/ixgbe/ixgbe_phy.h b/drivers/net/ixgbe/ixgbe_phy.h
index fb3898f..e2c6b7e 100644
--- a/drivers/net/ixgbe/ixgbe_phy.h
+++ b/drivers/net/ixgbe/ixgbe_phy.h
@@ -96,6 +96,9 @@ s32 ixgbe_setup_phy_link_speed_generic(struct ixgbe_hw *hw,
ixgbe_link_speed speed,
bool autoneg,
bool autoneg_wait_to_complete);
+s32 ixgbe_get_copper_link_capabilities_generic(struct ixgbe_hw *hw,
+ ixgbe_link_speed *speed,
+ bool *autoneg);
/* PHY specific */
s32 ixgbe_check_phy_link_tnx(struct ixgbe_hw *hw,
@@ -103,6 +106,8 @@ s32 ixgbe_check_phy_link_tnx(struct ixgbe_hw *hw,
bool *link_up);
s32 ixgbe_get_phy_firmware_version_tnx(struct ixgbe_hw *hw,
u16 *firmware_version);
+s32 ixgbe_get_phy_firmware_version_generic(struct ixgbe_hw *hw,
+ u16 *firmware_version);
s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw);
s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw);
diff --git a/drivers/net/ixgbe/ixgbe_sriov.c b/drivers/net/ixgbe/ixgbe_sriov.c
index 93f40bc..6e3e94b 100644
--- a/drivers/net/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ixgbe/ixgbe_sriov.c
@@ -178,8 +178,7 @@ static int ixgbe_set_vf_mac(struct ixgbe_adapter *adapter,
int ixgbe_vf_configuration(struct pci_dev *pdev, unsigned int event_mask)
{
unsigned char vf_mac_addr[6];
- struct net_device *netdev = pci_get_drvdata(pdev);
- struct ixgbe_adapter *adapter = netdev_priv(netdev);
+ struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
unsigned int vfn = (event_mask & 0x3f);
bool enable = ((event_mask & 0x10000000U) != 0);
diff --git a/drivers/net/ixgbe/ixgbe_type.h b/drivers/net/ixgbe/ixgbe_type.h
index d3cc6ce..42c6073 100644
--- a/drivers/net/ixgbe/ixgbe_type.h
+++ b/drivers/net/ixgbe/ixgbe_type.h
@@ -57,6 +57,8 @@
#define IXGBE_DEV_ID_82599_SFP_EM 0x1507
#define IXGBE_DEV_ID_82599_XAUI_LOM 0x10FC
#define IXGBE_DEV_ID_82599_COMBO_BACKPLANE 0x10F8
+#define IXGBE_SUBDEV_ID_82599_KX4_KR_MEZZ 0x000C
+#define IXGBE_DEV_ID_X540T 0x1528
/* General Registers */
#define IXGBE_CTRL 0x00000
@@ -994,8 +996,10 @@
/* PHY IDs*/
#define TN1010_PHY_ID 0x00A19410
#define TNX_FW_REV 0xB
+#define AQ1202_PHY_ID 0x03A1B440
#define QT2022_PHY_ID 0x0043A400
#define ATH_PHY_ID 0x03429050
+#define AQ_FW_REV 0x20
/* PHY Types */
#define IXGBE_M88E1145_E_PHY_ID 0x01410CD0
@@ -1491,6 +1495,7 @@
#define IXGBE_EEC_PRES 0x00000100 /* EEPROM Present */
#define IXGBE_EEC_ARD 0x00000200 /* EEPROM Auto Read Done */
#define IXGBE_EEC_FLUP 0x00800000 /* Flash update command */
+#define IXGBE_EEC_SEC1VAL 0x02000000 /* Sector 1 Valid */
#define IXGBE_EEC_FLUDONE 0x04000000 /* Flash update done */
/* EEPROM Addressing bits based on type (0-small, 1-large) */
#define IXGBE_EEC_ADDR_SIZE 0x00000400
@@ -1505,7 +1510,9 @@
#define IXGBE_EEPROM_SUM 0xBABA
#define IXGBE_PCIE_ANALOG_PTR 0x03
#define IXGBE_ATLAS0_CONFIG_PTR 0x04
+#define IXGBE_PHY_PTR 0x04
#define IXGBE_ATLAS1_CONFIG_PTR 0x05
+#define IXGBE_OPTION_ROM_PTR 0x05
#define IXGBE_PCIE_GENERAL_PTR 0x06
#define IXGBE_PCIE_CONFIG0_PTR 0x07
#define IXGBE_PCIE_CONFIG1_PTR 0x08
@@ -2113,6 +2120,14 @@ typedef u32 ixgbe_physical_layer;
#define IXGBE_PHYSICAL_LAYER_10GBASE_XAUI 0x1000
#define IXGBE_PHYSICAL_LAYER_SFP_ACTIVE_DA 0x2000
+/* Flow Control Macros */
+#define PAUSE_RTT 8
+#define PAUSE_MTU(MTU) ((MTU + 1024 - 1) / 1024)
+
+#define FC_HIGH_WATER(MTU) ((((PAUSE_RTT + PAUSE_MTU(MTU)) * 144) + 99) / 100 +\
+ PAUSE_MTU(MTU))
+#define FC_LOW_WATER(MTU) (2 * (2 * PAUSE_MTU(MTU) + PAUSE_RTT))
+
/* Software ATR hash keys */
#define IXGBE_ATR_BUCKET_HASH_KEY 0xE214AD3D
#define IXGBE_ATR_SIGNATURE_HASH_KEY 0x14364D17
@@ -2164,6 +2179,7 @@ struct ixgbe_atr_input_masks {
enum ixgbe_eeprom_type {
ixgbe_eeprom_uninitialized = 0,
ixgbe_eeprom_spi,
+ ixgbe_flash,
ixgbe_eeprom_none /* No NVM support */
};
@@ -2171,12 +2187,14 @@ enum ixgbe_mac_type {
ixgbe_mac_unknown = 0,
ixgbe_mac_82598EB,
ixgbe_mac_82599EB,
+ ixgbe_mac_X540,
ixgbe_num_macs
};
enum ixgbe_phy_type {
ixgbe_phy_unknown = 0,
ixgbe_phy_tn,
+ ixgbe_phy_aq,
ixgbe_phy_cu_unknown,
ixgbe_phy_qt,
ixgbe_phy_xaui,
@@ -2405,6 +2423,7 @@ struct ixgbe_eeprom_operations {
s32 (*write)(struct ixgbe_hw *, u16, u16);
s32 (*validate_checksum)(struct ixgbe_hw *, u16 *);
s32 (*update_checksum)(struct ixgbe_hw *);
+ u16 (*calc_checksum)(struct ixgbe_hw *);
};
struct ixgbe_mac_operations {
@@ -2574,6 +2593,7 @@ struct ixgbe_hw {
u16 subsystem_vendor_id;
u8 revision_id;
bool adapter_stopped;
+ bool force_full_reset;
};
struct ixgbe_info {
diff --git a/drivers/net/ixgbe/ixgbe_x540.c b/drivers/net/ixgbe/ixgbe_x540.c
new file mode 100644
index 0000000..9649fa7
--- /dev/null
+++ b/drivers/net/ixgbe/ixgbe_x540.c
@@ -0,0 +1,722 @@
+/*******************************************************************************
+
+ Intel 10 Gigabit PCI Express Linux driver
+ Copyright(c) 1999 - 2010 Intel Corporation.
+
+ This program is free software; you can redistribute it and/or modify it
+ under the terms and conditions of the GNU General Public License,
+ version 2, as published by the Free Software Foundation.
+
+ This program is distributed in the hope it will be useful, but WITHOUT
+ ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ more details.
+
+ You should have received a copy of the GNU General Public License along with
+ this program; if not, write to the Free Software Foundation, Inc.,
+ 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+
+ The full GNU General Public License is included in this distribution in
+ the file called "COPYING".
+
+ Contact Information:
+ e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+
+*******************************************************************************/
+
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/sched.h>
+
+#include "ixgbe.h"
+#include "ixgbe_phy.h"
+//#include "ixgbe_mbx.h"
+
+#define IXGBE_X540_MAX_TX_QUEUES 128
+#define IXGBE_X540_MAX_RX_QUEUES 128
+#define IXGBE_X540_RAR_ENTRIES 128
+#define IXGBE_X540_MC_TBL_SIZE 128
+#define IXGBE_X540_VFT_TBL_SIZE 128
+
+static s32 ixgbe_update_flash_X540(struct ixgbe_hw *hw);
+static s32 ixgbe_poll_flash_update_done_X540(struct ixgbe_hw *hw);
+static s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u16 mask);
+static void ixgbe_release_swfw_sync_X540(struct ixgbe_hw *hw, u16 mask);
+static s32 ixgbe_get_swfw_sync_semaphore(struct ixgbe_hw *hw);
+static void ixgbe_release_swfw_sync_semaphore(struct ixgbe_hw *hw);
+
+static enum ixgbe_media_type ixgbe_get_media_type_X540(struct ixgbe_hw *hw)
+{
+ return ixgbe_media_type_copper;
+}
+
+static s32 ixgbe_get_invariants_X540(struct ixgbe_hw *hw)
+{
+ struct ixgbe_mac_info *mac = &hw->mac;
+
+ /* Call PHY identify routine to get the phy type */
+ ixgbe_identify_phy_generic(hw);
+
+ mac->mcft_size = IXGBE_X540_MC_TBL_SIZE;
+ mac->vft_size = IXGBE_X540_VFT_TBL_SIZE;
+ mac->num_rar_entries = IXGBE_X540_RAR_ENTRIES;
+ mac->max_rx_queues = IXGBE_X540_MAX_RX_QUEUES;
+ mac->max_tx_queues = IXGBE_X540_MAX_TX_QUEUES;
+ mac->max_msix_vectors = ixgbe_get_pcie_msix_count_generic(hw);
+
+ return 0;
+}
+
+/**
+ * ixgbe_setup_mac_link_X540 - Set the auto advertised capabilitires
+ * @hw: pointer to hardware structure
+ * @speed: new link speed
+ * @autoneg: true if autonegotiation enabled
+ * @autoneg_wait_to_complete: true when waiting for completion is needed
+ **/
+static s32 ixgbe_setup_mac_link_X540(struct ixgbe_hw *hw,
+ ixgbe_link_speed speed, bool autoneg,
+ bool autoneg_wait_to_complete)
+{
+ return hw->phy.ops.setup_link_speed(hw, speed, autoneg,
+ autoneg_wait_to_complete);
+}
+
+/**
+ * ixgbe_reset_hw_X540 - Perform hardware reset
+ * @hw: pointer to hardware structure
+ *
+ * Resets the hardware by resetting the transmit and receive units, masks
+ * and clears all interrupts, perform a PHY reset, and perform a link (MAC)
+ * reset.
+ **/
+static s32 ixgbe_reset_hw_X540(struct ixgbe_hw *hw)
+{
+ ixgbe_link_speed link_speed;
+ s32 status = 0;
+ u32 ctrl;
+ u32 ctrl_ext;
+ u32 reset_bit;
+ u32 i;
+ u32 autoc;
+ u32 autoc2;
+ bool link_up = false;
+
+ /* Call adapter stop to disable tx/rx and clear interrupts */
+ hw->mac.ops.stop_adapter(hw);
+
+ /*
+ * Prevent the PCI-E bus from from hanging by disabling PCI-E master
+ * access and verify no pending requests before reset
+ */
+ status = ixgbe_disable_pcie_master(hw);
+ if (status != 0) {
+ status = IXGBE_ERR_MASTER_REQUESTS_PENDING;
+ hw_dbg(hw, "PCI-E Master disable polling has failed.\n");
+ }
+
+ /*
+ * Issue global reset to the MAC. Needs to be SW reset if link is up.
+ * If link reset is used when link is up, it might reset the PHY when
+ * mng is using it. If link is down or the flag to force full link
+ * reset is set, then perform link reset.
+ */
+ if (hw->force_full_reset) {
+ reset_bit = IXGBE_CTRL_LNK_RST;
+ } else {
+ hw->mac.ops.check_link(hw, &link_speed, &link_up, false);
+ if (!link_up)
+ reset_bit = IXGBE_CTRL_LNK_RST;
+ else
+ reset_bit = IXGBE_CTRL_RST;
+ }
+
+ ctrl = IXGBE_READ_REG(hw, IXGBE_CTRL);
+ IXGBE_WRITE_REG(hw, IXGBE_CTRL, (ctrl | IXGBE_CTRL_RST));
+ IXGBE_WRITE_FLUSH(hw);
+
+ /* Poll for reset bit to self-clear indicating reset is complete */
+ for (i = 0; i < 10; i++) {
+ udelay(1);
+ ctrl = IXGBE_READ_REG(hw, IXGBE_CTRL);
+ if (!(ctrl & IXGBE_CTRL_RST))
+ break;
+ }
+ if (ctrl & IXGBE_CTRL_RST) {
+ status = IXGBE_ERR_RESET_FAILED;
+ hw_dbg(hw, "Reset polling failed to complete.\n");
+ }
+
+ /* Clear PF Reset Done bit so PF/VF Mail Ops can work */
+ ctrl_ext = IXGBE_READ_REG(hw, IXGBE_CTRL_EXT);
+ ctrl_ext |= IXGBE_CTRL_EXT_PFRSTD;
+ IXGBE_WRITE_REG(hw, IXGBE_CTRL_EXT, ctrl_ext);
+
+ msleep(50);
+
+ /* Set the Rx packet buffer size. */
+ IXGBE_WRITE_REG(hw, IXGBE_RXPBSIZE(0), 384 << IXGBE_RXPBSIZE_SHIFT);
+
+ /* Store the permanent mac address */
+ hw->mac.ops.get_mac_addr(hw, hw->mac.perm_addr);
+
+ /*
+ * Store the original AUTOC/AUTOC2 values if they have not been
+ * stored off yet. Otherwise restore the stored original
+ * values since the reset operation sets back to defaults.
+ */
+ autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC);
+ autoc2 = IXGBE_READ_REG(hw, IXGBE_AUTOC2);
+ if (hw->mac.orig_link_settings_stored == false) {
+ hw->mac.orig_autoc = autoc;
+ hw->mac.orig_autoc2 = autoc2;
+ hw->mac.orig_link_settings_stored = true;
+ } else {
+ if (autoc != hw->mac.orig_autoc)
+ IXGBE_WRITE_REG(hw, IXGBE_AUTOC, (hw->mac.orig_autoc |
+ IXGBE_AUTOC_AN_RESTART));
+
+ if ((autoc2 & IXGBE_AUTOC2_UPPER_MASK) !=
+ (hw->mac.orig_autoc2 & IXGBE_AUTOC2_UPPER_MASK)) {
+ autoc2 &= ~IXGBE_AUTOC2_UPPER_MASK;
+ autoc2 |= (hw->mac.orig_autoc2 &
+ IXGBE_AUTOC2_UPPER_MASK);
+ IXGBE_WRITE_REG(hw, IXGBE_AUTOC2, autoc2);
+ }
+ }
+
+ /*
+ * Store MAC address from RAR0, clear receive address registers, and
+ * clear the multicast table. Also reset num_rar_entries to 128,
+ * since we modify this value when programming the SAN MAC address.
+ */
+ hw->mac.num_rar_entries = 128;
+ hw->mac.ops.init_rx_addrs(hw);
+
+ /* Store the permanent mac address */
+ hw->mac.ops.get_mac_addr(hw, hw->mac.perm_addr);
+
+ /* Store the permanent SAN mac address */
+ hw->mac.ops.get_san_mac_addr(hw, hw->mac.san_addr);
+
+ /* Add the SAN MAC address to the RAR only if it's a valid address */
+ if (ixgbe_validate_mac_addr(hw->mac.san_addr) == 0) {
+ hw->mac.ops.set_rar(hw, hw->mac.num_rar_entries - 1,
+ hw->mac.san_addr, 0, IXGBE_RAH_AV);
+
+ /* Reserve the last RAR for the SAN MAC address */
+ hw->mac.num_rar_entries--;
+ }
+
+ /* Store the alternative WWNN/WWPN prefix */
+ hw->mac.ops.get_wwn_prefix(hw, &hw->mac.wwnn_prefix,
+ &hw->mac.wwpn_prefix);
+
+ return status;
+}
+
+/**
+ * ixgbe_get_supported_physical_layer_X540 - Returns physical layer type
+ * @hw: pointer to hardware structure
+ *
+ * Determines physical layer capabilities of the current configuration.
+ **/
+static u32 ixgbe_get_supported_physical_layer_X540(struct ixgbe_hw *hw)
+{
+ u32 physical_layer = IXGBE_PHYSICAL_LAYER_UNKNOWN;
+ u16 ext_ability = 0;
+
+ hw->phy.ops.identify(hw);
+
+ hw->phy.ops.read_reg(hw, MDIO_PMA_EXTABLE, MDIO_MMD_PMAPMD,
+ &ext_ability);
+ if (ext_ability & MDIO_PMA_EXTABLE_10GBT)
+ physical_layer |= IXGBE_PHYSICAL_LAYER_10GBASE_T;
+ if (ext_ability & MDIO_PMA_EXTABLE_1000BT)
+ physical_layer |= IXGBE_PHYSICAL_LAYER_1000BASE_T;
+ if (ext_ability & MDIO_PMA_EXTABLE_100BTX)
+ physical_layer |= IXGBE_PHYSICAL_LAYER_100BASE_TX;
+
+ return physical_layer;
+}
+
+/**
+ * ixgbe_init_eeprom_params_X540 - Initialize EEPROM params
+ * @hw: pointer to hardware structure
+ **/
+static s32 ixgbe_init_eeprom_params_X540(struct ixgbe_hw *hw)
+{
+ struct ixgbe_eeprom_info *eeprom = &hw->eeprom;
+ u32 eec;
+ u16 eeprom_size;
+
+ if (eeprom->type == ixgbe_eeprom_uninitialized) {
+ eeprom->semaphore_delay = 10;
+ eeprom->type = ixgbe_flash;
+
+ eec = IXGBE_READ_REG(hw, IXGBE_EEC);
+ eeprom_size = (u16)((eec & IXGBE_EEC_SIZE) >>
+ IXGBE_EEC_SIZE_SHIFT);
+ eeprom->word_size = 1 << (eeprom_size +
+ IXGBE_EEPROM_WORD_SIZE_SHIFT);
+
+ hw_dbg(hw, "Eeprom params: type = %d, size = %d\n",
+ eeprom->type, eeprom->word_size);
+ }
+
+ return 0;
+}
+
+/**
+ * ixgbe_read_eerd_X540 - Read EEPROM word using EERD
+ * @hw: pointer to hardware structure
+ * @offset: offset of word in the EEPROM to read
+ * @data: word read from the EERPOM
+ **/
+static s32 ixgbe_read_eerd_X540(struct ixgbe_hw *hw, u16 offset, u16 *data)
+{
+ s32 status;
+
+ if (ixgbe_acquire_swfw_sync_X540(hw, IXGBE_GSSR_EEP_SM))
+ status = ixgbe_read_eerd_generic(hw, offset, data);
+ else
+ status = IXGBE_ERR_SWFW_SYNC;
+
+ ixgbe_release_swfw_sync_X540(hw, IXGBE_GSSR_EEP_SM);
+ return status;
+}
+
+/**
+ * ixgbe_write_eewr_X540 - Write EEPROM word using EEWR
+ * @hw: pointer to hardware structure
+ * @offset: offset of word in the EEPROM to write
+ * @data: word write to the EEPROM
+ *
+ * Write a 16 bit word to the EEPROM using the EEWR register.
+ **/
+static s32 ixgbe_write_eewr_X540(struct ixgbe_hw *hw, u16 offset, u16 data)
+{
+ u32 eewr;
+ s32 status;
+
+ hw->eeprom.ops.init_params(hw);
+
+ if (offset >= hw->eeprom.word_size) {
+ status = IXGBE_ERR_EEPROM;
+ goto out;
+ }
+
+ eewr = (offset << IXGBE_EEPROM_RW_ADDR_SHIFT) |
+ (data << IXGBE_EEPROM_RW_REG_DATA) |
+ IXGBE_EEPROM_RW_REG_START;
+
+ if (ixgbe_acquire_swfw_sync_X540(hw, IXGBE_GSSR_EEP_SM)) {
+ status = ixgbe_poll_eerd_eewr_done(hw, IXGBE_NVM_POLL_WRITE);
+ if (status != 0) {
+ hw_dbg(hw, "Eeprom write EEWR timed out\n");
+ goto out;
+ }
+
+ IXGBE_WRITE_REG(hw, IXGBE_EEWR, eewr);
+
+ status = ixgbe_poll_eerd_eewr_done(hw, IXGBE_NVM_POLL_WRITE);
+ if (status != 0) {
+ hw_dbg(hw, "Eeprom write EEWR timed out\n");
+ goto out;
+ }
+ } else {
+ status = IXGBE_ERR_SWFW_SYNC;
+ }
+
+out:
+ ixgbe_release_swfw_sync_X540(hw, IXGBE_GSSR_EEP_SM);
+ return status;
+}
+
+/**
+ * ixgbe_calc_eeprom_checksum_X540 - Calculates and returns the checksum
+ * @hw: pointer to hardware structure
+ **/
+static u16 ixgbe_calc_eeprom_checksum_X540(struct ixgbe_hw *hw)
+{
+ u16 i;
+ u16 j;
+ u16 checksum = 0;
+ u16 length = 0;
+ u16 pointer = 0;
+ u16 word = 0;
+
+ /* Include 0x0-0x3F in the checksum */
+ for (i = 0; i < IXGBE_EEPROM_CHECKSUM; i++) {
+ if (hw->eeprom.ops.read(hw, i, &word) != 0) {
+ hw_dbg(hw, "EEPROM read failed\n");
+ break;
+ }
+ checksum += word;
+ }
+
+ /*
+ * Include all data from pointers 0x3, 0x6-0xE. This excludes the
+ * FW, PHY module, and PCIe Expansion/Option ROM pointers.
+ */
+ for (i = IXGBE_PCIE_ANALOG_PTR; i < IXGBE_FW_PTR; i++) {
+ if (i == IXGBE_PHY_PTR || i == IXGBE_OPTION_ROM_PTR)
+ continue;
+
+ if (hw->eeprom.ops.read(hw, i, &pointer) != 0) {
+ hw_dbg(hw, "EEPROM read failed\n");
+ break;
+ }
+
+ /* Skip pointer section if the pointer is invalid. */
+ if (pointer == 0xFFFF || pointer == 0 ||
+ pointer >= hw->eeprom.word_size)
+ continue;
+
+ if (hw->eeprom.ops.read(hw, pointer, &length) != 0) {
+ hw_dbg(hw, "EEPROM read failed\n");
+ break;
+ }
+
+ /* Skip pointer section if length is invalid. */
+ if (length == 0xFFFF || length == 0 ||
+ (pointer + length) >= hw->eeprom.word_size)
+ continue;
+
+ for (j = pointer+1; j <= pointer+length; j++) {
+ if (hw->eeprom.ops.read(hw, j, &word) != 0) {
+ hw_dbg(hw, "EEPROM read failed\n");
+ break;
+ }
+ checksum += word;
+ }
+ }
+
+ checksum = (u16)IXGBE_EEPROM_SUM - checksum;
+
+ return checksum;
+}
+
+/**
+ * ixgbe_update_eeprom_checksum_X540 - Updates the EEPROM checksum and flash
+ * @hw: pointer to hardware structure
+ *
+ * After writing EEPROM to shadow RAM using EEWR register, software calculates
+ * checksum and updates the EEPROM and instructs the hardware to update
+ * the flash.
+ **/
+static s32 ixgbe_update_eeprom_checksum_X540(struct ixgbe_hw *hw)
+{
+ s32 status;
+
+ status = ixgbe_update_eeprom_checksum_generic(hw);
+
+ if (status)
+ status = ixgbe_update_flash_X540(hw);
+
+ return status;
+}
+
+/**
+ * ixgbe_update_flash_X540 - Instruct HW to copy EEPROM to Flash device
+ * @hw: pointer to hardware structure
+ *
+ * Set FLUP (bit 23) of the EEC register to instruct Hardware to copy
+ * EEPROM from shadow RAM to the flash device.
+ **/
+static s32 ixgbe_update_flash_X540(struct ixgbe_hw *hw)
+{
+ u32 flup;
+ s32 status = IXGBE_ERR_EEPROM;
+
+ status = ixgbe_poll_flash_update_done_X540(hw);
+ if (status == IXGBE_ERR_EEPROM) {
+ hw_dbg(hw, "Flash update time out\n");
+ goto out;
+ }
+
+ flup = IXGBE_READ_REG(hw, IXGBE_EEC) | IXGBE_EEC_FLUP;
+ IXGBE_WRITE_REG(hw, IXGBE_EEC, flup);
+
+ status = ixgbe_poll_flash_update_done_X540(hw);
+ if (status)
+ hw_dbg(hw, "Flash update complete\n");
+ else
+ hw_dbg(hw, "Flash update time out\n");
+
+ if (hw->revision_id == 0) {
+ flup = IXGBE_READ_REG(hw, IXGBE_EEC);
+
+ if (flup & IXGBE_EEC_SEC1VAL) {
+ flup |= IXGBE_EEC_FLUP;
+ IXGBE_WRITE_REG(hw, IXGBE_EEC, flup);
+ }
+
+ status = ixgbe_poll_flash_update_done_X540(hw);
+ if (status)
+ hw_dbg(hw, "Flash update complete\n");
+ else
+ hw_dbg(hw, "Flash update time out\n");
+
+ }
+out:
+ return status;
+}
+
+/**
+ * ixgbe_poll_flash_update_done_X540 - Poll flash update status
+ * @hw: pointer to hardware structure
+ *
+ * Polls the FLUDONE (bit 26) of the EEC Register to determine when the
+ * flash update is done.
+ **/
+static s32 ixgbe_poll_flash_update_done_X540(struct ixgbe_hw *hw)
+{
+ u32 i;
+ u32 reg;
+ s32 status = IXGBE_ERR_EEPROM;
+
+ for (i = 0; i < IXGBE_FLUDONE_ATTEMPTS; i++) {
+ reg = IXGBE_READ_REG(hw, IXGBE_EEC);
+ if (reg & IXGBE_EEC_FLUDONE) {
+ status = 0;
+ break;
+ }
+ udelay(5);
+ }
+ return status;
+}
+
+/**
+ * ixgbe_acquire_swfw_sync_X540 - Acquire SWFW semaphore
+ * @hw: pointer to hardware structure
+ * @mask: Mask to specify which semaphore to acquire
+ *
+ * Acquires the SWFW semaphore thought the SW_FW_SYNC register for
+ * the specified function (CSR, PHY0, PHY1, NVM, Flash)
+ **/
+static s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u16 mask)
+{
+ u32 swfw_sync;
+ u32 swmask = mask;
+ u32 fwmask = mask << 5;
+ u32 hwmask = 0;
+ u32 timeout = 200;
+ u32 i;
+
+ if (swmask == IXGBE_GSSR_EEP_SM)
+ hwmask = IXGBE_GSSR_FLASH_SM;
+
+ for (i = 0; i < timeout; i++) {
+ /*
+ * SW NVM semaphore bit is used for access to all
+ * SW_FW_SYNC bits (not just NVM)
+ */
+ if (ixgbe_get_swfw_sync_semaphore(hw))
+ return IXGBE_ERR_SWFW_SYNC;
+
+ swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC);
+ if (!(swfw_sync & (fwmask | swmask | hwmask))) {
+ swfw_sync |= swmask;
+ IXGBE_WRITE_REG(hw, IXGBE_SWFW_SYNC, swfw_sync);
+ ixgbe_release_swfw_sync_semaphore(hw);
+ break;
+ } else {
+ /*
+ * Firmware currently using resource (fwmask),
+ * hardware currently using resource (hwmask),
+ * or other software thread currently using
+ * resource (swmask)
+ */
+ ixgbe_release_swfw_sync_semaphore(hw);
+ msleep(5);
+ }
+ }
+
+ /*
+ * If the resource is not released by the FW/HW the SW can assume that
+ * the FW/HW malfunctions. In that case the SW should sets the
+ * SW bit(s) of the requested resource(s) while ignoring the
+ * corresponding FW/HW bits in the SW_FW_SYNC register.
+ */
+ if (i >= timeout) {
+ swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC);
+ if (swfw_sync & (fwmask | hwmask)) {
+ if (ixgbe_get_swfw_sync_semaphore(hw))
+ return IXGBE_ERR_SWFW_SYNC;
+
+ swfw_sync |= swmask;
+ IXGBE_WRITE_REG(hw, IXGBE_SWFW_SYNC, swfw_sync);
+ ixgbe_release_swfw_sync_semaphore(hw);
+ }
+ }
+
+ msleep(5);
+ return 0;
+}
+
+/**
+ * ixgbe_release_swfw_sync_X540 - Release SWFW semaphore
+ * @hw: pointer to hardware structure
+ * @mask: Mask to specify which semaphore to release
+ *
+ * Releases the SWFW semaphore throught the SW_FW_SYNC register
+ * for the specified function (CSR, PHY0, PHY1, EVM, Flash)
+ **/
+static void ixgbe_release_swfw_sync_X540(struct ixgbe_hw *hw, u16 mask)
+{
+ u32 swfw_sync;
+ u32 swmask = mask;
+
+ ixgbe_get_swfw_sync_semaphore(hw);
+
+ swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC);
+ swfw_sync &= ~swmask;
+ IXGBE_WRITE_REG(hw, IXGBE_SWFW_SYNC, swfw_sync);
+
+ ixgbe_release_swfw_sync_semaphore(hw);
+ msleep(5);
+}
+
+/**
+ * ixgbe_get_nvm_semaphore - Get hardware semaphore
+ * @hw: pointer to hardware structure
+ *
+ * Sets the hardware semaphores so SW/FW can gain control of shared resources
+ **/
+static s32 ixgbe_get_swfw_sync_semaphore(struct ixgbe_hw *hw)
+{
+ s32 status = IXGBE_ERR_EEPROM;
+ u32 timeout = 2000;
+ u32 i;
+ u32 swsm;
+
+ /* Get SMBI software semaphore between device drivers first */
+ for (i = 0; i < timeout; i++) {
+ /*
+ * If the SMBI bit is 0 when we read it, then the bit will be
+ * set and we have the semaphore
+ */
+ swsm = IXGBE_READ_REG(hw, IXGBE_SWSM);
+ if (!(swsm & IXGBE_SWSM_SMBI)) {
+ status = 0;
+ break;
+ }
+ udelay(50);
+ }
+
+ /* Now get the semaphore between SW/FW through the REGSMP bit */
+ if (status) {
+ for (i = 0; i < timeout; i++) {
+ swsm = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC);
+ if (!(swsm & IXGBE_SWFW_REGSMP))
+ break;
+
+ udelay(50);
+ }
+ } else {
+ hw_dbg(hw, "Software semaphore SMBI between device drivers "
+ "not granted.\n");
+ }
+
+ return status;
+}
+
+/**
+ * ixgbe_release_nvm_semaphore - Release hardware semaphore
+ * @hw: pointer to hardware structure
+ *
+ * This function clears hardware semaphore bits.
+ **/
+static void ixgbe_release_swfw_sync_semaphore(struct ixgbe_hw *hw)
+{
+ u32 swsm;
+
+ /* Release both semaphores by writing 0 to the bits REGSMP and SMBI */
+
+ swsm = IXGBE_READ_REG(hw, IXGBE_SWSM);
+ swsm &= ~IXGBE_SWSM_SMBI;
+ IXGBE_WRITE_REG(hw, IXGBE_SWSM, swsm);
+
+ swsm = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC);
+ swsm &= ~IXGBE_SWFW_REGSMP;
+ IXGBE_WRITE_REG(hw, IXGBE_SWFW_SYNC, swsm);
+
+ IXGBE_WRITE_FLUSH(hw);
+}
+
+static struct ixgbe_mac_operations mac_ops_X540 = {
+ .init_hw = &ixgbe_init_hw_generic,
+ .reset_hw = &ixgbe_reset_hw_X540,
+ .start_hw = &ixgbe_start_hw_generic,
+ .clear_hw_cntrs = &ixgbe_clear_hw_cntrs_generic,
+ .get_media_type = &ixgbe_get_media_type_X540,
+ .get_supported_physical_layer =
+ &ixgbe_get_supported_physical_layer_X540,
+ .enable_rx_dma = &ixgbe_enable_rx_dma_generic,
+ .get_mac_addr = &ixgbe_get_mac_addr_generic,
+ .get_san_mac_addr = &ixgbe_get_san_mac_addr_generic,
+ .get_device_caps = NULL,
+ .get_wwn_prefix = &ixgbe_get_wwn_prefix_generic,
+ .stop_adapter = &ixgbe_stop_adapter_generic,
+ .get_bus_info = &ixgbe_get_bus_info_generic,
+ .set_lan_id = &ixgbe_set_lan_id_multi_port_pcie,
+ .read_analog_reg8 = NULL,
+ .write_analog_reg8 = NULL,
+ .setup_link = &ixgbe_setup_mac_link_X540,
+ .check_link = &ixgbe_check_mac_link_generic,
+ .get_link_capabilities = &ixgbe_get_copper_link_capabilities_generic,
+ .led_on = &ixgbe_led_on_generic,
+ .led_off = &ixgbe_led_off_generic,
+ .blink_led_start = &ixgbe_blink_led_start_generic,
+ .blink_led_stop = &ixgbe_blink_led_stop_generic,
+ .set_rar = &ixgbe_set_rar_generic,
+ .clear_rar = &ixgbe_clear_rar_generic,
+ .set_vmdq = &ixgbe_set_vmdq_generic,
+ .clear_vmdq = &ixgbe_clear_vmdq_generic,
+ .init_rx_addrs = &ixgbe_init_rx_addrs_generic,
+ .update_uc_addr_list = &ixgbe_update_uc_addr_list_generic,
+ .update_mc_addr_list = &ixgbe_update_mc_addr_list_generic,
+ .enable_mc = &ixgbe_enable_mc_generic,
+ .disable_mc = &ixgbe_disable_mc_generic,
+ .clear_vfta = &ixgbe_clear_vfta_generic,
+ .set_vfta = &ixgbe_set_vfta_generic,
+ .fc_enable = &ixgbe_fc_enable_generic,
+ .init_uta_tables = &ixgbe_init_uta_tables_generic,
+ .setup_sfp = NULL,
+};
+
+static struct ixgbe_eeprom_operations eeprom_ops_X540 = {
+ .init_params = &ixgbe_init_eeprom_params_X540,
+ .read = &ixgbe_read_eerd_X540,
+ .write = &ixgbe_write_eewr_X540,
+ .calc_checksum = &ixgbe_calc_eeprom_checksum_X540,
+ .validate_checksum = &ixgbe_validate_eeprom_checksum_generic,
+ .update_checksum = &ixgbe_update_eeprom_checksum_X540,
+};
+
+static struct ixgbe_phy_operations phy_ops_X540 = {
+ .identify = &ixgbe_identify_phy_generic,
+ .identify_sfp = &ixgbe_identify_sfp_module_generic,
+ .init = NULL,
+ .reset = &ixgbe_reset_phy_generic,
+ .read_reg = &ixgbe_read_phy_reg_generic,
+ .write_reg = &ixgbe_write_phy_reg_generic,
+ .setup_link = &ixgbe_setup_phy_link_generic,
+ .setup_link_speed = &ixgbe_setup_phy_link_speed_generic,
+ .read_i2c_byte = &ixgbe_read_i2c_byte_generic,
+ .write_i2c_byte = &ixgbe_write_i2c_byte_generic,
+ .read_i2c_eeprom = &ixgbe_read_i2c_eeprom_generic,
+ .write_i2c_eeprom = &ixgbe_write_i2c_eeprom_generic,
+ .check_overtemp = &ixgbe_tn_check_overtemp,
+};
+
+struct ixgbe_info ixgbe_X540_info = {
+ .mac = ixgbe_mac_X540,
+ .get_invariants = &ixgbe_get_invariants_X540,
+ .mac_ops = &mac_ops_X540,
+ .eeprom_ops = &eeprom_ops_X540,
+ .phy_ops = &phy_ops_X540,
+ .mbx_ops = &mbx_ops_generic,
+};
diff --git a/drivers/net/ixgbevf/Makefile b/drivers/net/ixgbevf/Makefile
index dd4e0d2..1f35d22 100644
--- a/drivers/net/ixgbevf/Makefile
+++ b/drivers/net/ixgbevf/Makefile
@@ -1,7 +1,7 @@
################################################################################
#
# Intel 82599 Virtual Function driver
-# Copyright(c) 1999 - 2009 Intel Corporation.
+# Copyright(c) 1999 - 2010 Intel Corporation.
#
# This program is free software; you can redistribute it and/or modify it
# under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ixgbevf/defines.h b/drivers/net/ixgbevf/defines.h
index ca2c81f..f8a807d 100644
--- a/drivers/net/ixgbevf/defines.h
+++ b/drivers/net/ixgbevf/defines.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel 82599 Virtual Function driver
- Copyright(c) 1999 - 2009 Intel Corporation.
+ Copyright(c) 1999 - 2010 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ixgbevf/ixgbevf.h b/drivers/net/ixgbevf/ixgbevf.h
index da4033c..0cd6abc 100644
--- a/drivers/net/ixgbevf/ixgbevf.h
+++ b/drivers/net/ixgbevf/ixgbevf.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel 82599 Virtual Function driver
- Copyright(c) 1999 - 2009 Intel Corporation.
+ Copyright(c) 1999 - 2010 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ixgbevf/ixgbevf_main.c b/drivers/net/ixgbevf/ixgbevf_main.c
index dc03c96..5b8063c 100644
--- a/drivers/net/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ixgbevf/ixgbevf_main.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel 82599 Virtual Function driver
- Copyright(c) 1999 - 2009 Intel Corporation.
+ Copyright(c) 1999 - 2010 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
@@ -51,9 +51,10 @@ char ixgbevf_driver_name[] = "ixgbevf";
static const char ixgbevf_driver_string[] =
"Intel(R) 82599 Virtual Function";
-#define DRV_VERSION "1.0.0-k0"
+#define DRV_VERSION "1.0.12-k0"
const char ixgbevf_driver_version[] = DRV_VERSION;
-static char ixgbevf_copyright[] = "Copyright (c) 2009 Intel Corporation.";
+static char ixgbevf_copyright[] =
+ "Copyright (c) 2009 - 2010 Intel Corporation.";
static const struct ixgbevf_info *ixgbevf_info_tbl[] = {
[board_82599_vf] = &ixgbevf_vf_info,
@@ -3424,10 +3425,6 @@ static int __devinit ixgbevf_probe(struct pci_dev *pdev,
if (hw->mac.ops.get_bus_info)
hw->mac.ops.get_bus_info(hw);
-
- netif_carrier_off(netdev);
- netif_tx_stop_all_queues(netdev);
-
strcpy(netdev->name, "eth%d");
err = register_netdev(netdev);
@@ -3436,6 +3433,8 @@ static int __devinit ixgbevf_probe(struct pci_dev *pdev,
adapter->netdev_registered = true;
+ netif_carrier_off(netdev);
+
ixgbevf_init_last_counter_stats(adapter);
/* print the MAC address */
diff --git a/drivers/net/ixgbevf/mbx.c b/drivers/net/ixgbevf/mbx.c
index 84ac486..7a88331 100644
--- a/drivers/net/ixgbevf/mbx.c
+++ b/drivers/net/ixgbevf/mbx.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel 82599 Virtual Function driver
- Copyright(c) 1999 - 2009 Intel Corporation.
+ Copyright(c) 1999 - 2010 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ixgbevf/mbx.h b/drivers/net/ixgbevf/mbx.h
index 8c063be..b2b5bf5 100644
--- a/drivers/net/ixgbevf/mbx.h
+++ b/drivers/net/ixgbevf/mbx.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel 82599 Virtual Function driver
- Copyright(c) 1999 - 2009 Intel Corporation.
+ Copyright(c) 1999 - 2010 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ixgbevf/regs.h b/drivers/net/ixgbevf/regs.h
index 12f7596..fb80ca1 100644
--- a/drivers/net/ixgbevf/regs.h
+++ b/drivers/net/ixgbevf/regs.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel 82599 Virtual Function driver
- Copyright(c) 1999 - 2009 Intel Corporation.
+ Copyright(c) 1999 - 2010 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ixgbevf/vf.c b/drivers/net/ixgbevf/vf.c
index bfe42c1..971019d 100644
--- a/drivers/net/ixgbevf/vf.c
+++ b/drivers/net/ixgbevf/vf.c
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel 82599 Virtual Function driver
- Copyright(c) 1999 - 2009 Intel Corporation.
+ Copyright(c) 1999 - 2010 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ixgbevf/vf.h b/drivers/net/ixgbevf/vf.h
index 61f9dc8..144c99d 100644
--- a/drivers/net/ixgbevf/vf.h
+++ b/drivers/net/ixgbevf/vf.h
@@ -1,7 +1,7 @@
/*******************************************************************************
Intel 82599 Virtual Function driver
- Copyright(c) 1999 - 2009 Intel Corporation.
+ Copyright(c) 1999 - 2010 Intel Corporation.
This program is free software; you can redistribute it and/or modify it
under the terms and conditions of the GNU General Public License,
^ permalink raw reply related
* [PATCH net-next-2.6 ] can: EG20T PCH: add prefix to macro
From: Tomoya MORINAGA @ 2010-11-17 5:13 UTC (permalink / raw)
To: Wolfgang Grandegger, David S. Miller, Wolfram Sang,
Christian Pellegrin, Barry Song
Cc: qi.wang, yong.y.wang, andrew.chih.howe.khor, joel.clark,
kok.howg.ewe, margie.foster
For easy to readable/identifiable, add prefix "PCH_" to all of #define macros.
Signed-off-by: Tomoya MORINAGA <tomoya-linux@dsn.okisemi.com>
---
drivers/net/can/pch_can.c | 392 ++++++++++++++++++++++-----------------------
1 files changed, 190 insertions(+), 202 deletions(-)
diff --git a/drivers/net/can/pch_can.c b/drivers/net/can/pch_can.c
index 6727182..b4bb775 100644
--- a/drivers/net/can/pch_can.c
+++ b/drivers/net/can/pch_can.c
@@ -32,49 +32,48 @@
#include <linux/can/dev.h>
#include <linux/can/error.h>
-#define MAX_MSG_OBJ 32
-#define MSG_OBJ_RX 0 /* The receive message object flag. */
-#define MSG_OBJ_TX 1 /* The transmit message object flag. */
-
-#define ENABLE 1 /* The enable flag */
-#define DISABLE 0 /* The disable flag */
-#define CAN_CTRL_INIT 0x0001 /* The INIT bit of CANCONT register. */
-#define CAN_CTRL_IE 0x0002 /* The IE bit of CAN control register */
-#define CAN_CTRL_IE_SIE_EIE 0x000e
-#define CAN_CTRL_CCE 0x0040
-#define CAN_CTRL_OPT 0x0080 /* The OPT bit of CANCONT register. */
-#define CAN_OPT_SILENT 0x0008 /* The Silent bit of CANOPT reg. */
-#define CAN_OPT_LBACK 0x0010 /* The LoopBack bit of CANOPT reg. */
-#define CAN_CMASK_RX_TX_SET 0x00f3
-#define CAN_CMASK_RX_TX_GET 0x0073
-#define CAN_CMASK_ALL 0xff
-#define CAN_CMASK_RDWR 0x80
-#define CAN_CMASK_ARB 0x20
-#define CAN_CMASK_CTRL 0x10
-#define CAN_CMASK_MASK 0x40
-#define CAN_CMASK_NEWDAT 0x04
-#define CAN_CMASK_CLRINTPND 0x08
-
-#define CAN_IF_MCONT_NEWDAT 0x8000
-#define CAN_IF_MCONT_INTPND 0x2000
-#define CAN_IF_MCONT_UMASK 0x1000
-#define CAN_IF_MCONT_TXIE 0x0800
-#define CAN_IF_MCONT_RXIE 0x0400
-#define CAN_IF_MCONT_RMTEN 0x0200
-#define CAN_IF_MCONT_TXRQXT 0x0100
-#define CAN_IF_MCONT_EOB 0x0080
-#define CAN_IF_MCONT_DLC 0x000f
-#define CAN_IF_MCONT_MSGLOST 0x4000
-#define CAN_MASK2_MDIR_MXTD 0xc000
-#define CAN_ID2_DIR 0x2000
-#define CAN_ID_MSGVAL 0x8000
-
-#define CAN_STATUS_INT 0x8000
-#define CAN_IF_CREQ_BUSY 0x8000
-#define CAN_ID2_XTD 0x4000
-
-#define CAN_REC 0x00007f00
-#define CAN_TEC 0x000000ff
+#define PCH_MAX_MSG_OBJ 32
+#define PCH_MSG_OBJ_RX 0 /* The receive message object flag. */
+#define PCH_MSG_OBJ_TX 1 /* The transmit message object flag. */
+
+#define PCH_ENABLE 1 /* The enable flag */
+#define PCH_DISABLE 0 /* The disable flag */
+#define PCH_CTRL_INIT 0x0001 /* The INIT bit of CANCONT register. */
+#define PCH_CTRL_IE 0x0002 /* The IE bit of CAN control register */
+#define PCH_CTRL_IE_SIE_EIE 0x000e
+#define PCH_CTRL_CCE 0x0040
+#define PCH_CTRL_OPT 0x0080 /* The OPT bit of CANCONT register. */
+#define PCH_OPT_SILENT 0x0008 /* The Silent bit of CANOPT reg. */
+#define PCH_OPT_LBACK 0x0010 /* The LoopBack bit of CANOPT reg. */
+#define PCH_CMASK_RX_TX_SET 0x00f3
+#define PCH_CMASK_RX_TX_GET 0x0073
+#define PCH_CMASK_ALL 0xff
+#define PCH_CMASK_RDWR 0x80
+#define PCH_CMASK_ARB 0x20
+#define PCH_CMASK_CTRL 0x10
+#define PCH_CMASK_MASK 0x40
+#define PCH_CMASK_NEWDAT 0x04
+#define PCH_CMASK_CLRINTPND 0x08
+#define PCH_IF_MCONT_NEWDAT 0x8000
+#define PCH_IF_MCONT_INTPND 0x2000
+#define PCH_IF_MCONT_UMASK 0x1000
+#define PCH_IF_MCONT_TXIE 0x0800
+#define PCH_IF_MCONT_RXIE 0x0400
+#define PCH_IF_MCONT_RMTEN 0x0200
+#define PCH_IF_MCONT_TXRQXT 0x0100
+#define PCH_IF_MCONT_EOB 0x0080
+#define PCH_IF_MCONT_DLC 0x000f
+#define PCH_IF_MCONT_MSGLOST 0x4000
+#define PCH_MASK2_MDIR_MXTD 0xc000
+#define PCH_ID2_DIR 0x2000
+#define PCH_ID2_XTD 0x4000
+#define PCH_ID_MSGVAL 0x8000
+#define PCH_IF_CREQ_BUSY 0x8000
+
+#define PCH_STATUS_INT 0x8000
+#define PCH_REC 0x00007f00
+#define PCH_TEC 0x000000ff
+
#define PCH_RX_OK 0x00000010
#define PCH_TX_OK 0x00000008
@@ -93,26 +92,15 @@
#define PCH_CRC_ERR (PCH_LEC1 | PCH_LEC2)
/* bit position of certain controller bits. */
-#define BIT_BITT_BRP 0
-#define BIT_BITT_SJW 6
-#define BIT_BITT_TSEG1 8
-#define BIT_BITT_TSEG2 12
-#define BIT_IF1_MCONT_RXIE 10
-#define BIT_IF2_MCONT_TXIE 11
-#define BIT_BRPE_BRPE 6
-#define BIT_ES_TXERRCNT 0
-#define BIT_ES_RXERRCNT 8
-#define MSK_BITT_BRP 0x3f
-#define MSK_BITT_SJW 0xc0
-#define MSK_BITT_TSEG1 0xf00
-#define MSK_BITT_TSEG2 0x7000
-#define MSK_BRPE_BRPE 0x3c0
-#define MSK_BRPE_GET 0x0f
-#define MSK_CTRL_IE_SIE_EIE 0x07
-#define MSK_MCONT_TXIE 0x08
-#define MSK_MCONT_RXIE 0x10
-#define PCH_CAN_NO_TX_BUFF 1
-#define COUNTER_LIMIT 10
+#define PCH_BIT_BRP 0
+#define PCH_BIT_SJW 6
+#define PCH_BIT_TSEG1 8
+#define PCH_BIT_TSEG2 12
+#define PCH_BIT_BRPE_BRPE 6
+#define PCH_MSK_BITT_BRP 0x3f
+#define PCH_MSK_BRPE_BRPE 0x3c0
+#define PCH_MSK_CTRL_IE_SIE_EIE 0x07
+#define PCH_COUNTER_LIMIT 10
#define PCH_CAN_CLK 50000000 /* 50MHz */
@@ -181,14 +169,14 @@ struct pch_can_priv {
struct can_priv can;
unsigned int can_num;
struct pci_dev *dev;
- unsigned int tx_enable[MAX_MSG_OBJ];
- unsigned int rx_enable[MAX_MSG_OBJ];
- unsigned int rx_link[MAX_MSG_OBJ];
+ unsigned int tx_enable[PCH_MAX_MSG_OBJ];
+ unsigned int rx_enable[PCH_MAX_MSG_OBJ];
+ unsigned int rx_link[PCH_MAX_MSG_OBJ];
unsigned int int_enables;
unsigned int int_stat;
struct net_device *ndev;
spinlock_t msgif_reg_lock; /* Message Interface Registers Access Lock*/
- unsigned int msg_obj[MAX_MSG_OBJ];
+ unsigned int msg_obj[PCH_MAX_MSG_OBJ];
struct pch_can_regs __iomem *regs;
struct napi_struct napi;
unsigned int tx_obj; /* Point next Tx Obj index */
@@ -228,11 +216,11 @@ static void pch_can_set_run_mode(struct pch_can_priv *priv,
{
switch (mode) {
case PCH_CAN_RUN:
- pch_can_bit_clear(&priv->regs->cont, CAN_CTRL_INIT);
+ pch_can_bit_clear(&priv->regs->cont, PCH_CTRL_INIT);
break;
case PCH_CAN_STOP:
- pch_can_bit_set(&priv->regs->cont, CAN_CTRL_INIT);
+ pch_can_bit_set(&priv->regs->cont, PCH_CTRL_INIT);
break;
default:
@@ -246,30 +234,30 @@ static void pch_can_set_optmode(struct pch_can_priv *priv)
u32 reg_val = ioread32(&priv->regs->opt);
if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
- reg_val |= CAN_OPT_SILENT;
+ reg_val |= PCH_OPT_SILENT;
if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK)
- reg_val |= CAN_OPT_LBACK;
+ reg_val |= PCH_OPT_LBACK;
- pch_can_bit_set(&priv->regs->cont, CAN_CTRL_OPT);
+ pch_can_bit_set(&priv->regs->cont, PCH_CTRL_OPT);
iowrite32(reg_val, &priv->regs->opt);
}
static void pch_can_set_int_custom(struct pch_can_priv *priv)
{
/* Clearing the IE, SIE and EIE bits of Can control register. */
- pch_can_bit_clear(&priv->regs->cont, CAN_CTRL_IE_SIE_EIE);
+ pch_can_bit_clear(&priv->regs->cont, PCH_CTRL_IE_SIE_EIE);
/* Appropriately setting them. */
pch_can_bit_set(&priv->regs->cont,
- ((priv->int_enables & MSK_CTRL_IE_SIE_EIE) << 1));
+ ((priv->int_enables & PCH_MSK_CTRL_IE_SIE_EIE) << 1));
}
/* This function retrieves interrupt enabled for the CAN device. */
static void pch_can_get_int_enables(struct pch_can_priv *priv, u32 *enables)
{
/* Obtaining the status of IE, SIE and EIE interrupt bits. */
- *enables = ((ioread32(&priv->regs->cont) & CAN_CTRL_IE_SIE_EIE) >> 1);
+ *enables = ((ioread32(&priv->regs->cont) & PCH_CTRL_IE_SIE_EIE) >> 1);
}
static void pch_can_set_int_enables(struct pch_can_priv *priv,
@@ -277,19 +265,19 @@ static void pch_can_set_int_enables(struct pch_can_priv *priv,
{
switch (interrupt_no) {
case PCH_CAN_ENABLE:
- pch_can_bit_set(&priv->regs->cont, CAN_CTRL_IE);
+ pch_can_bit_set(&priv->regs->cont, PCH_CTRL_IE);
break;
case PCH_CAN_DISABLE:
- pch_can_bit_clear(&priv->regs->cont, CAN_CTRL_IE);
+ pch_can_bit_clear(&priv->regs->cont, PCH_CTRL_IE);
break;
case PCH_CAN_ALL:
- pch_can_bit_set(&priv->regs->cont, CAN_CTRL_IE_SIE_EIE);
+ pch_can_bit_set(&priv->regs->cont, PCH_CTRL_IE_SIE_EIE);
break;
case PCH_CAN_NONE:
- pch_can_bit_clear(&priv->regs->cont, CAN_CTRL_IE_SIE_EIE);
+ pch_can_bit_clear(&priv->regs->cont, PCH_CTRL_IE_SIE_EIE);
break;
default:
@@ -300,12 +288,12 @@ static void pch_can_set_int_enables(struct pch_can_priv *priv,
static void pch_can_check_if_busy(u32 __iomem *creq_addr, u32 num)
{
- u32 counter = COUNTER_LIMIT;
+ u32 counter = PCH_COUNTER_LIMIT;
u32 ifx_creq;
iowrite32(num, creq_addr);
while (counter) {
- ifx_creq = ioread32(creq_addr) & CAN_IF_CREQ_BUSY;
+ ifx_creq = ioread32(creq_addr) & PCH_IF_CREQ_BUSY;
if (!ifx_creq)
break;
counter--;
@@ -322,22 +310,22 @@ static void pch_can_set_rx_enable(struct pch_can_priv *priv, u32 buff_num,
spin_lock_irqsave(&priv->msgif_reg_lock, flags);
/* Reading the receive buffer data from RAM to Interface1 registers */
- iowrite32(CAN_CMASK_RX_TX_GET, &priv->regs->if1_cmask);
+ iowrite32(PCH_CMASK_RX_TX_GET, &priv->regs->if1_cmask);
pch_can_check_if_busy(&priv->regs->if1_creq, buff_num);
/* Setting the IF1MASK1 register to access MsgVal and RxIE bits */
- iowrite32(CAN_CMASK_RDWR | CAN_CMASK_ARB | CAN_CMASK_CTRL,
+ iowrite32(PCH_CMASK_RDWR | PCH_CMASK_ARB | PCH_CMASK_CTRL,
&priv->regs->if1_cmask);
- if (set == ENABLE) {
+ if (set == PCH_ENABLE) {
/* Setting the MsgVal and RxIE bits */
- pch_can_bit_set(&priv->regs->if1_mcont, CAN_IF_MCONT_RXIE);
- pch_can_bit_set(&priv->regs->if1_id2, CAN_ID_MSGVAL);
+ pch_can_bit_set(&priv->regs->if1_mcont, PCH_IF_MCONT_RXIE);
+ pch_can_bit_set(&priv->regs->if1_id2, PCH_ID_MSGVAL);
- } else if (set == DISABLE) {
+ } else if (set == PCH_DISABLE) {
/* Resetting the MsgVal and RxIE bits */
- pch_can_bit_clear(&priv->regs->if1_mcont, CAN_IF_MCONT_RXIE);
- pch_can_bit_clear(&priv->regs->if1_id2, CAN_ID_MSGVAL);
+ pch_can_bit_clear(&priv->regs->if1_mcont, PCH_IF_MCONT_RXIE);
+ pch_can_bit_clear(&priv->regs->if1_id2, PCH_ID_MSGVAL);
}
pch_can_check_if_busy(&priv->regs->if1_creq, buff_num);
@@ -350,8 +338,8 @@ static void pch_can_rx_enable_all(struct pch_can_priv *priv)
/* Traversing to obtain the object configured as receivers. */
for (i = 0; i < PCH_OBJ_NUM; i++) {
- if (priv->msg_obj[i] == MSG_OBJ_RX)
- pch_can_set_rx_enable(priv, i + 1, ENABLE);
+ if (priv->msg_obj[i] == PCH_MSG_OBJ_RX)
+ pch_can_set_rx_enable(priv, i + 1, PCH_ENABLE);
}
}
@@ -361,8 +349,8 @@ static void pch_can_rx_disable_all(struct pch_can_priv *priv)
/* Traversing to obtain the object configured as receivers. */
for (i = 0; i < PCH_OBJ_NUM; i++) {
- if (priv->msg_obj[i] == MSG_OBJ_RX)
- pch_can_set_rx_enable(priv, i + 1, DISABLE);
+ if (priv->msg_obj[i] == PCH_MSG_OBJ_RX)
+ pch_can_set_rx_enable(priv, i + 1, PCH_DISABLE);
}
}
@@ -373,22 +361,22 @@ static void pch_can_set_tx_enable(struct pch_can_priv *priv, u32 buff_num,
spin_lock_irqsave(&priv->msgif_reg_lock, flags);
/* Reading the Msg buffer from Message RAM to Interface2 registers. */
- iowrite32(CAN_CMASK_RX_TX_GET, &priv->regs->if2_cmask);
+ iowrite32(PCH_CMASK_RX_TX_GET, &priv->regs->if2_cmask);
pch_can_check_if_busy(&priv->regs->if2_creq, buff_num);
/* Setting the IF2CMASK register for accessing the
MsgVal and TxIE bits */
- iowrite32(CAN_CMASK_RDWR | CAN_CMASK_ARB | CAN_CMASK_CTRL,
+ iowrite32(PCH_CMASK_RDWR | PCH_CMASK_ARB | PCH_CMASK_CTRL,
&priv->regs->if2_cmask);
- if (set == ENABLE) {
+ if (set == PCH_ENABLE) {
/* Setting the MsgVal and TxIE bits */
- pch_can_bit_set(&priv->regs->if2_mcont, CAN_IF_MCONT_TXIE);
- pch_can_bit_set(&priv->regs->if2_id2, CAN_ID_MSGVAL);
- } else if (set == DISABLE) {
+ pch_can_bit_set(&priv->regs->if2_mcont, PCH_IF_MCONT_TXIE);
+ pch_can_bit_set(&priv->regs->if2_id2, PCH_ID_MSGVAL);
+ } else if (set == PCH_DISABLE) {
/* Resetting the MsgVal and TxIE bits. */
- pch_can_bit_clear(&priv->regs->if2_mcont, CAN_IF_MCONT_TXIE);
- pch_can_bit_clear(&priv->regs->if2_id2, CAN_ID_MSGVAL);
+ pch_can_bit_clear(&priv->regs->if2_mcont, PCH_IF_MCONT_TXIE);
+ pch_can_bit_clear(&priv->regs->if2_id2, PCH_ID_MSGVAL);
}
pch_can_check_if_busy(&priv->regs->if2_creq, buff_num);
@@ -401,8 +389,8 @@ static void pch_can_tx_enable_all(struct pch_can_priv *priv)
/* Traversing to obtain the object configured as transmit object. */
for (i = 0; i < PCH_OBJ_NUM; i++) {
- if (priv->msg_obj[i] == MSG_OBJ_TX)
- pch_can_set_tx_enable(priv, i + 1, ENABLE);
+ if (priv->msg_obj[i] == PCH_MSG_OBJ_TX)
+ pch_can_set_tx_enable(priv, i + 1, PCH_ENABLE);
}
}
@@ -412,8 +400,8 @@ static void pch_can_tx_disable_all(struct pch_can_priv *priv)
/* Traversing to obtain the object configured as transmit object. */
for (i = 0; i < PCH_OBJ_NUM; i++) {
- if (priv->msg_obj[i] == MSG_OBJ_TX)
- pch_can_set_tx_enable(priv, i + 1, DISABLE);
+ if (priv->msg_obj[i] == PCH_MSG_OBJ_TX)
+ pch_can_set_tx_enable(priv, i + 1, PCH_DISABLE);
}
}
@@ -423,15 +411,15 @@ static void pch_can_get_rx_enable(struct pch_can_priv *priv, u32 buff_num,
unsigned long flags;
spin_lock_irqsave(&priv->msgif_reg_lock, flags);
- iowrite32(CAN_CMASK_RX_TX_GET, &priv->regs->if1_cmask);
+ iowrite32(PCH_CMASK_RX_TX_GET, &priv->regs->if1_cmask);
pch_can_check_if_busy(&priv->regs->if1_creq, buff_num);
- if (((ioread32(&priv->regs->if1_id2)) & CAN_ID_MSGVAL) &&
+ if (((ioread32(&priv->regs->if1_id2)) & PCH_ID_MSGVAL) &&
((ioread32(&priv->regs->if1_mcont)) &
- CAN_IF_MCONT_RXIE))
- *enable = ENABLE;
+ PCH_IF_MCONT_RXIE))
+ *enable = PCH_ENABLE;
else
- *enable = DISABLE;
+ *enable = PCH_DISABLE;
spin_unlock_irqrestore(&priv->msgif_reg_lock, flags);
}
@@ -441,15 +429,15 @@ static void pch_can_get_tx_enable(struct pch_can_priv *priv, u32 buff_num,
unsigned long flags;
spin_lock_irqsave(&priv->msgif_reg_lock, flags);
- iowrite32(CAN_CMASK_RX_TX_GET, &priv->regs->if2_cmask);
+ iowrite32(PCH_CMASK_RX_TX_GET, &priv->regs->if2_cmask);
pch_can_check_if_busy(&priv->regs->if2_creq, buff_num);
- if (((ioread32(&priv->regs->if2_id2)) & CAN_ID_MSGVAL) &&
+ if (((ioread32(&priv->regs->if2_id2)) & PCH_ID_MSGVAL) &&
((ioread32(&priv->regs->if2_mcont)) &
- CAN_IF_MCONT_TXIE)) {
- *enable = ENABLE;
+ PCH_IF_MCONT_TXIE)) {
+ *enable = PCH_ENABLE;
} else {
- *enable = DISABLE;
+ *enable = PCH_DISABLE;
}
spin_unlock_irqrestore(&priv->msgif_reg_lock, flags);
}
@@ -465,13 +453,13 @@ static void pch_can_set_rx_buffer_link(struct pch_can_priv *priv,
unsigned long flags;
spin_lock_irqsave(&priv->msgif_reg_lock, flags);
- iowrite32(CAN_CMASK_RX_TX_GET, &priv->regs->if1_cmask);
+ iowrite32(PCH_CMASK_RX_TX_GET, &priv->regs->if1_cmask);
pch_can_check_if_busy(&priv->regs->if1_creq, buffer_num);
- iowrite32(CAN_CMASK_RDWR | CAN_CMASK_CTRL, &priv->regs->if1_cmask);
- if (set == ENABLE)
- pch_can_bit_clear(&priv->regs->if1_mcont, CAN_IF_MCONT_EOB);
+ iowrite32(PCH_CMASK_RDWR | PCH_CMASK_CTRL, &priv->regs->if1_cmask);
+ if (set == PCH_ENABLE)
+ pch_can_bit_clear(&priv->regs->if1_mcont, PCH_IF_MCONT_EOB);
else
- pch_can_bit_set(&priv->regs->if1_mcont, CAN_IF_MCONT_EOB);
+ pch_can_bit_set(&priv->regs->if1_mcont, PCH_IF_MCONT_EOB);
pch_can_check_if_busy(&priv->regs->if1_creq, buffer_num);
spin_unlock_irqrestore(&priv->msgif_reg_lock, flags);
@@ -483,13 +471,13 @@ static void pch_can_get_rx_buffer_link(struct pch_can_priv *priv,
unsigned long flags;
spin_lock_irqsave(&priv->msgif_reg_lock, flags);
- iowrite32(CAN_CMASK_RX_TX_GET, &priv->regs->if1_cmask);
+ iowrite32(PCH_CMASK_RX_TX_GET, &priv->regs->if1_cmask);
pch_can_check_if_busy(&priv->regs->if1_creq, buffer_num);
- if (ioread32(&priv->regs->if1_mcont) & CAN_IF_MCONT_EOB)
- *link = DISABLE;
+ if (ioread32(&priv->regs->if1_mcont) & PCH_IF_MCONT_EOB)
+ *link = PCH_DISABLE;
else
- *link = ENABLE;
+ *link = PCH_ENABLE;
spin_unlock_irqrestore(&priv->msgif_reg_lock, flags);
}
@@ -498,7 +486,7 @@ static void pch_can_clear_buffers(struct pch_can_priv *priv)
int i;
for (i = 0; i < PCH_RX_OBJ_NUM; i++) {
- iowrite32(CAN_CMASK_RX_TX_SET, &priv->regs->if1_cmask);
+ iowrite32(PCH_CMASK_RX_TX_SET, &priv->regs->if1_cmask);
iowrite32(0xffff, &priv->regs->if1_mask1);
iowrite32(0xffff, &priv->regs->if1_mask2);
iowrite32(0x0, &priv->regs->if1_id1);
@@ -508,14 +496,14 @@ static void pch_can_clear_buffers(struct pch_can_priv *priv)
iowrite32(0x0, &priv->regs->if1_dataa2);
iowrite32(0x0, &priv->regs->if1_datab1);
iowrite32(0x0, &priv->regs->if1_datab2);
- iowrite32(CAN_CMASK_RDWR | CAN_CMASK_MASK |
- CAN_CMASK_ARB | CAN_CMASK_CTRL,
+ iowrite32(PCH_CMASK_RDWR | PCH_CMASK_MASK |
+ PCH_CMASK_ARB | PCH_CMASK_CTRL,
&priv->regs->if1_cmask);
pch_can_check_if_busy(&priv->regs->if1_creq, i+1);
}
for (i = i; i < PCH_OBJ_NUM; i++) {
- iowrite32(CAN_CMASK_RX_TX_SET, &priv->regs->if2_cmask);
+ iowrite32(PCH_CMASK_RX_TX_SET, &priv->regs->if2_cmask);
iowrite32(0xffff, &priv->regs->if2_mask1);
iowrite32(0xffff, &priv->regs->if2_mask2);
iowrite32(0x0, &priv->regs->if2_id1);
@@ -525,8 +513,8 @@ static void pch_can_clear_buffers(struct pch_can_priv *priv)
iowrite32(0x0, &priv->regs->if2_dataa2);
iowrite32(0x0, &priv->regs->if2_datab1);
iowrite32(0x0, &priv->regs->if2_datab2);
- iowrite32(CAN_CMASK_RDWR | CAN_CMASK_MASK |
- CAN_CMASK_ARB | CAN_CMASK_CTRL,
+ iowrite32(PCH_CMASK_RDWR | PCH_CMASK_MASK |
+ PCH_CMASK_ARB | PCH_CMASK_CTRL,
&priv->regs->if2_cmask);
pch_can_check_if_busy(&priv->regs->if2_creq, i+1);
}
@@ -540,8 +528,8 @@ static void pch_can_config_rx_tx_buffers(struct pch_can_priv *priv)
spin_lock_irqsave(&priv->msgif_reg_lock, flags);
for (i = 0; i < PCH_OBJ_NUM; i++) {
- if (priv->msg_obj[i] == MSG_OBJ_RX) {
- iowrite32(CAN_CMASK_RX_TX_GET,
+ if (priv->msg_obj[i] == PCH_MSG_OBJ_RX) {
+ iowrite32(PCH_CMASK_RX_TX_GET,
&priv->regs->if1_cmask);
pch_can_check_if_busy(&priv->regs->if1_creq, i+1);
@@ -549,48 +537,48 @@ static void pch_can_config_rx_tx_buffers(struct pch_can_priv *priv)
iowrite32(0x0, &priv->regs->if1_id2);
pch_can_bit_set(&priv->regs->if1_mcont,
- CAN_IF_MCONT_UMASK);
+ PCH_IF_MCONT_UMASK);
/* Set FIFO mode set to 0 except last Rx Obj*/
pch_can_bit_clear(&priv->regs->if1_mcont,
- CAN_IF_MCONT_EOB);
+ PCH_IF_MCONT_EOB);
/* In case FIFO mode, Last EoB of Rx Obj must be 1 */
if (i == (PCH_RX_OBJ_NUM - 1))
pch_can_bit_set(&priv->regs->if1_mcont,
- CAN_IF_MCONT_EOB);
+ PCH_IF_MCONT_EOB);
iowrite32(0, &priv->regs->if1_mask1);
pch_can_bit_clear(&priv->regs->if1_mask2,
- 0x1fff | CAN_MASK2_MDIR_MXTD);
+ 0x1fff | PCH_MASK2_MDIR_MXTD);
/* Setting CMASK for writing */
- iowrite32(CAN_CMASK_RDWR | CAN_CMASK_MASK |
- CAN_CMASK_ARB | CAN_CMASK_CTRL,
+ iowrite32(PCH_CMASK_RDWR | PCH_CMASK_MASK |
+ PCH_CMASK_ARB | PCH_CMASK_CTRL,
&priv->regs->if1_cmask);
pch_can_check_if_busy(&priv->regs->if1_creq, i+1);
- } else if (priv->msg_obj[i] == MSG_OBJ_TX) {
- iowrite32(CAN_CMASK_RX_TX_GET,
+ } else if (priv->msg_obj[i] == PCH_MSG_OBJ_TX) {
+ iowrite32(PCH_CMASK_RX_TX_GET,
&priv->regs->if2_cmask);
pch_can_check_if_busy(&priv->regs->if2_creq, i+1);
/* Resetting DIR bit for reception */
iowrite32(0x0, &priv->regs->if2_id1);
iowrite32(0x0, &priv->regs->if2_id2);
- pch_can_bit_set(&priv->regs->if2_id2, CAN_ID2_DIR);
+ pch_can_bit_set(&priv->regs->if2_id2, PCH_ID2_DIR);
/* Setting EOB bit for transmitter */
- iowrite32(CAN_IF_MCONT_EOB, &priv->regs->if2_mcont);
+ iowrite32(PCH_IF_MCONT_EOB, &priv->regs->if2_mcont);
pch_can_bit_set(&priv->regs->if2_mcont,
- CAN_IF_MCONT_UMASK);
+ PCH_IF_MCONT_UMASK);
iowrite32(0, &priv->regs->if2_mask1);
pch_can_bit_clear(&priv->regs->if2_mask2, 0x1fff);
/* Setting CMASK for writing */
- iowrite32(CAN_CMASK_RDWR | CAN_CMASK_MASK |
- CAN_CMASK_ARB | CAN_CMASK_CTRL,
+ iowrite32(PCH_CMASK_RDWR | PCH_CMASK_MASK |
+ PCH_CMASK_ARB | PCH_CMASK_CTRL,
&priv->regs->if2_cmask);
pch_can_check_if_busy(&priv->regs->if2_creq, i+1);
@@ -632,39 +620,39 @@ static void pch_can_release(struct pch_can_priv *priv)
/* This function clears interrupt(s) from the CAN device. */
static void pch_can_int_clr(struct pch_can_priv *priv, u32 mask)
{
- if (mask == CAN_STATUS_INT) {
+ if (mask == PCH_STATUS_INT) {
ioread32(&priv->regs->stat);
return;
}
/* Clear interrupt for transmit object */
- if (priv->msg_obj[mask - 1] == MSG_OBJ_TX) {
+ if (priv->msg_obj[mask - 1] == PCH_MSG_OBJ_TX) {
/* Setting CMASK for clearing interrupts for
frame transmission. */
- iowrite32(CAN_CMASK_RDWR | CAN_CMASK_CTRL | CAN_CMASK_ARB,
+ iowrite32(PCH_CMASK_RDWR | PCH_CMASK_CTRL | PCH_CMASK_ARB,
&priv->regs->if2_cmask);
/* Resetting the ID registers. */
pch_can_bit_set(&priv->regs->if2_id2,
- CAN_ID2_DIR | (0x7ff << 2));
+ PCH_ID2_DIR | (0x7ff << 2));
iowrite32(0x0, &priv->regs->if2_id1);
/* Claring NewDat, TxRqst & IntPnd */
pch_can_bit_clear(&priv->regs->if2_mcont,
- CAN_IF_MCONT_NEWDAT | CAN_IF_MCONT_INTPND |
- CAN_IF_MCONT_TXRQXT);
+ PCH_IF_MCONT_NEWDAT | PCH_IF_MCONT_INTPND |
+ PCH_IF_MCONT_TXRQXT);
pch_can_check_if_busy(&priv->regs->if2_creq, mask);
- } else if (priv->msg_obj[mask - 1] == MSG_OBJ_RX) {
+ } else if (priv->msg_obj[mask - 1] == PCH_MSG_OBJ_RX) {
/* Setting CMASK for clearing the reception interrupts. */
- iowrite32(CAN_CMASK_RDWR | CAN_CMASK_CTRL | CAN_CMASK_ARB,
+ iowrite32(PCH_CMASK_RDWR | PCH_CMASK_CTRL | PCH_CMASK_ARB,
&priv->regs->if1_cmask);
/* Clearing the Dir bit. */
- pch_can_bit_clear(&priv->regs->if1_id2, CAN_ID2_DIR);
+ pch_can_bit_clear(&priv->regs->if1_id2, PCH_ID2_DIR);
/* Clearing NewDat & IntPnd */
pch_can_bit_clear(&priv->regs->if1_mcont,
- CAN_IF_MCONT_NEWDAT | CAN_IF_MCONT_INTPND);
+ PCH_IF_MCONT_NEWDAT | PCH_IF_MCONT_INTPND);
pch_can_check_if_busy(&priv->regs->if1_creq, mask);
}
@@ -712,9 +700,9 @@ static void pch_can_error(struct net_device *ndev, u32 status)
priv->can.can_stats.error_warning++;
cf->can_id |= CAN_ERR_CRTL;
errc = ioread32(&priv->regs->errc);
- if (((errc & CAN_REC) >> 8) > 96)
+ if (((errc & PCH_REC) >> 8) > 96)
cf->data[1] |= CAN_ERR_CRTL_RX_WARNING;
- if ((errc & CAN_TEC) > 96)
+ if ((errc & PCH_TEC) > 96)
cf->data[1] |= CAN_ERR_CRTL_TX_WARNING;
dev_warn(&ndev->dev,
"%s -> Error Counter is more than 96.\n", __func__);
@@ -725,9 +713,9 @@ static void pch_can_error(struct net_device *ndev, u32 status)
state = CAN_STATE_ERROR_PASSIVE;
cf->can_id |= CAN_ERR_CRTL;
errc = ioread32(&priv->regs->errc);
- if (((errc & CAN_REC) >> 8) > 127)
+ if (((errc & PCH_REC) >> 8) > 127)
cf->data[1] |= CAN_ERR_CRTL_RX_PASSIVE;
- if ((errc & CAN_TEC) > 127)
+ if ((errc & PCH_TEC) > 127)
cf->data[1] |= CAN_ERR_CRTL_TX_PASSIVE;
dev_err(&ndev->dev,
"%s -> CAN controller is ERROR PASSIVE .\n", __func__);
@@ -795,20 +783,20 @@ static int pch_can_rx_normal(struct net_device *ndev, u32 int_stat)
struct net_device_stats *stats = &(priv->ndev->stats);
/* Reading the messsage object from the Message RAM */
- iowrite32(CAN_CMASK_RX_TX_GET, &priv->regs->if1_cmask);
+ iowrite32(PCH_CMASK_RX_TX_GET, &priv->regs->if1_cmask);
pch_can_check_if_busy(&priv->regs->if1_creq, int_stat);
/* Reading the MCONT register. */
reg = ioread32(&priv->regs->if1_mcont);
reg &= 0xffff;
- for (k = int_stat; !(reg & CAN_IF_MCONT_EOB); k++) {
+ for (k = int_stat; !(reg & PCH_IF_MCONT_EOB); k++) {
/* If MsgLost bit set. */
- if (reg & CAN_IF_MCONT_MSGLOST) {
+ if (reg & PCH_IF_MCONT_MSGLOST) {
dev_err(&priv->ndev->dev, "Msg Obj is overwritten.\n");
pch_can_bit_clear(&priv->regs->if1_mcont,
- CAN_IF_MCONT_MSGLOST);
- iowrite32(CAN_CMASK_RDWR | CAN_CMASK_CTRL,
+ PCH_IF_MCONT_MSGLOST);
+ iowrite32(PCH_CMASK_RDWR | PCH_CMASK_CTRL,
&priv->regs->if1_cmask);
pch_can_check_if_busy(&priv->regs->if1_creq, k);
@@ -828,7 +816,7 @@ static int pch_can_rx_normal(struct net_device *ndev, u32 int_stat)
rcv_pkts++;
goto RX_NEXT;
}
- if (!(reg & CAN_IF_MCONT_NEWDAT))
+ if (!(reg & PCH_IF_MCONT_NEWDAT))
goto RX_NEXT;
skb = alloc_can_skb(priv->ndev, &cf);
@@ -836,7 +824,7 @@ static int pch_can_rx_normal(struct net_device *ndev, u32 int_stat)
return -ENOMEM;
/* Get Received data */
- ide = ((ioread32(&priv->regs->if1_id2)) & CAN_ID2_XTD) >> 14;
+ ide = ((ioread32(&priv->regs->if1_id2)) & PCH_ID2_XTD) >> 14;
if (ide) {
id = (ioread32(&priv->regs->if1_id1) & 0xffff);
id |= (((ioread32(&priv->regs->if1_id2)) &
@@ -848,7 +836,7 @@ static int pch_can_rx_normal(struct net_device *ndev, u32 int_stat)
cf->can_id = (id & CAN_SFF_MASK);
}
- rtr = (ioread32(&priv->regs->if1_id2) & CAN_ID2_DIR);
+ rtr = (ioread32(&priv->regs->if1_id2) & PCH_ID2_DIR);
if (rtr) {
cf->can_dlc = 0;
cf->can_id |= CAN_RTR_FLAG;
@@ -871,15 +859,15 @@ static int pch_can_rx_normal(struct net_device *ndev, u32 int_stat)
stats->rx_bytes += cf->can_dlc;
if (k < PCH_FIFO_THRESH) {
- iowrite32(CAN_CMASK_RDWR | CAN_CMASK_CTRL |
- CAN_CMASK_ARB, &priv->regs->if1_cmask);
+ iowrite32(PCH_CMASK_RDWR | PCH_CMASK_CTRL |
+ PCH_CMASK_ARB, &priv->regs->if1_cmask);
/* Clearing the Dir bit. */
- pch_can_bit_clear(&priv->regs->if1_id2, CAN_ID2_DIR);
+ pch_can_bit_clear(&priv->regs->if1_id2, PCH_ID2_DIR);
/* Clearing NewDat & IntPnd */
pch_can_bit_clear(&priv->regs->if1_mcont,
- CAN_IF_MCONT_INTPND);
+ PCH_IF_MCONT_INTPND);
pch_can_check_if_busy(&priv->regs->if1_creq, k);
} else if (k > PCH_FIFO_THRESH) {
pch_can_int_clr(priv, k);
@@ -890,7 +878,7 @@ static int pch_can_rx_normal(struct net_device *ndev, u32 int_stat)
}
RX_NEXT:
/* Reading the messsage object from the Message RAM */
- iowrite32(CAN_CMASK_RX_TX_GET, &priv->regs->if1_cmask);
+ iowrite32(PCH_CMASK_RX_TX_GET, &priv->regs->if1_cmask);
pch_can_check_if_busy(&priv->regs->if1_creq, k + 1);
reg = ioread32(&priv->regs->if1_mcont);
}
@@ -913,7 +901,7 @@ static int pch_can_rx_poll(struct napi_struct *napi, int quota)
return 0;
INT_STAT:
- if (int_stat == CAN_STATUS_INT) {
+ if (int_stat == PCH_STATUS_INT) {
reg_stat = ioread32(&priv->regs->stat);
if (reg_stat & (PCH_BUS_OFF | PCH_LEC_ALL)) {
if ((reg_stat & PCH_LEC_ALL) != PCH_LEC_ALL)
@@ -922,7 +910,7 @@ INT_STAT:
if (reg_stat & PCH_TX_OK) {
spin_lock_irqsave(&priv->msgif_reg_lock, flags);
- iowrite32(CAN_CMASK_RX_TX_GET, &priv->regs->if2_cmask);
+ iowrite32(PCH_CMASK_RX_TX_GET, &priv->regs->if2_cmask);
pch_can_check_if_busy(&priv->regs->if2_creq,
ioread32(&priv->regs->intr));
spin_unlock_irqrestore(&priv->msgif_reg_lock, flags);
@@ -933,7 +921,7 @@ INT_STAT:
pch_can_bit_clear(&priv->regs->stat, PCH_RX_OK);
int_stat = pch_can_int_pending(priv);
- if (int_stat == CAN_STATUS_INT)
+ if (int_stat == PCH_STATUS_INT)
goto INT_STAT;
}
@@ -945,14 +933,14 @@ MSG_OBJ:
if (rcv_pkts < 0)
return 0;
} else if ((int_stat > PCH_RX_OBJ_NUM) && (int_stat <= PCH_OBJ_NUM)) {
- if (priv->msg_obj[int_stat - 1] == MSG_OBJ_TX) {
+ if (priv->msg_obj[int_stat - 1] == PCH_MSG_OBJ_TX) {
/* Handle transmission interrupt */
can_get_echo_skb(ndev, int_stat - PCH_RX_OBJ_NUM - 1);
spin_lock_irqsave(&priv->msgif_reg_lock, flags);
- iowrite32(CAN_CMASK_RX_TX_GET | CAN_CMASK_CLRINTPND,
+ iowrite32(PCH_CMASK_RX_TX_GET | PCH_CMASK_CLRINTPND,
&priv->regs->if2_cmask);
dlc = ioread32(&priv->regs->if2_mcont) &
- CAN_IF_MCONT_DLC;
+ PCH_IF_MCONT_DLC;
pch_can_check_if_busy(&priv->regs->if2_creq, int_stat);
spin_unlock_irqrestore(&priv->msgif_reg_lock, flags);
if (dlc > 8)
@@ -963,7 +951,7 @@ MSG_OBJ:
}
int_stat = pch_can_int_pending(priv);
- if (int_stat == CAN_STATUS_INT)
+ if (int_stat == PCH_STATUS_INT)
goto INT_STAT;
else if (int_stat >= 1 && int_stat <= 32)
goto MSG_OBJ;
@@ -983,17 +971,17 @@ static int pch_set_bittiming(struct net_device *ndev)
u32 brp;
/* Setting the CCE bit for accessing the Can Timing register. */
- pch_can_bit_set(&priv->regs->cont, CAN_CTRL_CCE);
+ pch_can_bit_set(&priv->regs->cont, PCH_CTRL_CCE);
brp = (bt->tq) / (1000000000/PCH_CAN_CLK) - 1;
- canbit = brp & MSK_BITT_BRP;
- canbit |= (bt->sjw - 1) << BIT_BITT_SJW;
- canbit |= (bt->phase_seg1 + bt->prop_seg - 1) << BIT_BITT_TSEG1;
- canbit |= (bt->phase_seg2 - 1) << BIT_BITT_TSEG2;
- bepe = (brp & MSK_BRPE_BRPE) >> BIT_BRPE_BRPE;
+ canbit = brp & PCH_MSK_BITT_BRP;
+ canbit |= (bt->sjw - 1) << PCH_BIT_SJW;
+ canbit |= (bt->phase_seg1 + bt->prop_seg - 1) << PCH_BIT_TSEG1;
+ canbit |= (bt->phase_seg2 - 1) << PCH_BIT_TSEG2;
+ bepe = (brp & PCH_MSK_BRPE_BRPE) >> PCH_BIT_BRPE_BRPE;
iowrite32(canbit, &priv->regs->bitt);
iowrite32(bepe, &priv->regs->brpe);
- pch_can_bit_clear(&priv->regs->cont, CAN_CTRL_CCE);
+ pch_can_bit_clear(&priv->regs->cont, PCH_CTRL_CCE);
return 0;
}
@@ -1137,19 +1125,19 @@ static netdev_tx_t pch_xmit(struct sk_buff *skb, struct net_device *ndev)
spin_lock_irqsave(&priv->msgif_reg_lock, flags);
/* Reading the Msg Obj from the Msg RAM to the Interface register. */
- iowrite32(CAN_CMASK_RX_TX_GET, &priv->regs->if2_cmask);
+ iowrite32(PCH_CMASK_RX_TX_GET, &priv->regs->if2_cmask);
pch_can_check_if_busy(&priv->regs->if2_creq, tx_buffer_avail);
/* Setting the CMASK register. */
- pch_can_bit_set(&priv->regs->if2_cmask, CAN_CMASK_ALL);
+ pch_can_bit_set(&priv->regs->if2_cmask, PCH_CMASK_ALL);
/* If ID extended is set. */
pch_can_bit_clear(&priv->regs->if2_id1, 0xffff);
- pch_can_bit_clear(&priv->regs->if2_id2, 0x1fff | CAN_ID2_XTD);
+ pch_can_bit_clear(&priv->regs->if2_id2, 0x1fff | PCH_ID2_XTD);
if (cf->can_id & CAN_EFF_FLAG) {
pch_can_bit_set(&priv->regs->if2_id1, cf->can_id & 0xffff);
pch_can_bit_set(&priv->regs->if2_id2,
- ((cf->can_id >> 16) & 0x1fff) | CAN_ID2_XTD);
+ ((cf->can_id >> 16) & 0x1fff) | PCH_ID2_XTD);
} else {
pch_can_bit_set(&priv->regs->if2_id1, 0);
pch_can_bit_set(&priv->regs->if2_id2,
@@ -1158,7 +1146,7 @@ static netdev_tx_t pch_xmit(struct sk_buff *skb, struct net_device *ndev)
/* If remote frame has to be transmitted.. */
if (cf->can_id & CAN_RTR_FLAG)
- pch_can_bit_clear(&priv->regs->if2_id2, CAN_ID2_DIR);
+ pch_can_bit_clear(&priv->regs->if2_id2, PCH_ID2_DIR);
for (i = 0, j = 0; i < cf->can_dlc; j++) {
iowrite32(le32_to_cpu(cf->data[i++]),
@@ -1177,12 +1165,12 @@ static netdev_tx_t pch_xmit(struct sk_buff *skb, struct net_device *ndev)
/* Clearing IntPend, NewDat & TxRqst */
pch_can_bit_clear(&priv->regs->if2_mcont,
- CAN_IF_MCONT_NEWDAT | CAN_IF_MCONT_INTPND |
- CAN_IF_MCONT_TXRQXT);
+ PCH_IF_MCONT_NEWDAT | PCH_IF_MCONT_INTPND |
+ PCH_IF_MCONT_TXRQXT);
/* Setting NewDat, TxRqst bits */
pch_can_bit_set(&priv->regs->if2_mcont,
- CAN_IF_MCONT_NEWDAT | CAN_IF_MCONT_TXRQXT);
+ PCH_IF_MCONT_NEWDAT | PCH_IF_MCONT_TXRQXT);
pch_can_check_if_busy(&priv->regs->if2_creq, tx_buffer_avail);
@@ -1245,7 +1233,7 @@ static int pch_can_suspend(struct pci_dev *pdev, pm_message_t state)
/* Save Tx buffer enable state */
for (i = 0; i < PCH_OBJ_NUM; i++) {
- if (priv->msg_obj[i] == MSG_OBJ_TX)
+ if (priv->msg_obj[i] == PCH_MSG_OBJ_TX)
pch_can_get_tx_enable(priv, i + 1,
&(priv->tx_enable[i]));
}
@@ -1255,7 +1243,7 @@ static int pch_can_suspend(struct pci_dev *pdev, pm_message_t state)
/* Save Rx buffer enable state */
for (i = 0; i < PCH_OBJ_NUM; i++) {
- if (priv->msg_obj[i] == MSG_OBJ_RX) {
+ if (priv->msg_obj[i] == PCH_MSG_OBJ_RX) {
pch_can_get_rx_enable(priv, i + 1,
&(priv->rx_enable[i]));
pch_can_get_rx_buffer_link(priv, i + 1,
@@ -1313,7 +1301,7 @@ static int pch_can_resume(struct pci_dev *pdev)
/* Enabling the transmit buffer. */
for (i = 0; i < PCH_OBJ_NUM; i++) {
- if (priv->msg_obj[i] == MSG_OBJ_TX) {
+ if (priv->msg_obj[i] == PCH_MSG_OBJ_TX) {
pch_can_set_tx_enable(priv, i + 1,
priv->tx_enable[i]);
}
@@ -1321,7 +1309,7 @@ static int pch_can_resume(struct pci_dev *pdev)
/* Configuring the receive buffer and enabling them. */
for (i = 0; i < PCH_OBJ_NUM; i++) {
- if (priv->msg_obj[i] == MSG_OBJ_RX) {
+ if (priv->msg_obj[i] == PCH_MSG_OBJ_RX) {
/* Restore buffer link */
pch_can_set_rx_buffer_link(priv, i + 1,
priv->rx_link[i]);
@@ -1349,8 +1337,8 @@ static int pch_can_get_berr_counter(const struct net_device *dev,
{
struct pch_can_priv *priv = netdev_priv(dev);
- bec->txerr = ioread32(&priv->regs->errc) & CAN_TEC;
- bec->rxerr = (ioread32(&priv->regs->errc) & CAN_REC) >> 8;
+ bec->txerr = ioread32(&priv->regs->errc) & PCH_TEC;
+ bec->rxerr = (ioread32(&priv->regs->errc) & PCH_REC) >> 8;
return 0;
}
@@ -1410,10 +1398,10 @@ static int __devinit pch_can_probe(struct pci_dev *pdev,
priv->can.clock.freq = PCH_CAN_CLK; /* Hz */
for (index = 0; index < PCH_RX_OBJ_NUM;)
- priv->msg_obj[index++] = MSG_OBJ_RX;
+ priv->msg_obj[index++] = PCH_MSG_OBJ_RX;
for (index = index; index < PCH_OBJ_NUM;)
- priv->msg_obj[index++] = MSG_OBJ_TX;
+ priv->msg_obj[index++] = PCH_MSG_OBJ_TX;
netif_napi_add(ndev, &priv->napi, pch_can_rx_poll, PCH_RX_OBJ_NUM);
--
1.6.0.6
^ permalink raw reply related
* Re: [PATCH 2.6.37-rc1] net-next: Add multiqueue support to vmxnet3 driver v3
From: Shreyas Bhatewara @ 2010-11-17 5:14 UTC (permalink / raw)
To: David Miller
Cc: bhutchings@solarflare.com, shemminger@vyatta.com,
netdev@vger.kernel.org, pv-drivers@vmware.com,
linux-kernel@vger.kernel.org
In-Reply-To: <alpine.LRH.2.00.1011101426410.816@sbhatewara-dev1.eng.vmware.com>
From: Shreyas Bhatewara <sbhatewara@vmware.com>
Add multiqueue support to vmxnet3 driver
This change adds Multiqueue and thus receive side scaling support
to vmxnet3 device driver. Number of rx queues is limited to 1 in cases
where
MSI is not configured or
One MSIx vector is not available per rx queue
By default multiqueue capability is turned off and hence only 1 tx and 1
rx queue will be initialized.
Signed-off-by: Shreyas Bhatewara <sbhatewara@vmware.com>
Reviwed-by: Bhavesh Davda <bhavesh@vmware.com>
---
Thanks for your reply David.
> Two things:
>
> 1) Do not quote the entire patch when asking for feedback,
> that adds needless scrolling for people trying to read
> through either the thread on an archive site or me trying
> to skim through the feedback in the patchwork entry.
Sorry about quoting the entire patch. My motive was to have the patch
handy for the reviewers. I see how that went south.
>
> You are not adding any new information at all by quoting
> the entire patch, and in fact you are making it more difficult
> for the very people you want replies from.
>
> 2) You're still adding driver specific module option knobs
> which we have consistently stated are not to be added to
> any driver. Instead create generic facilities that any
> driver, not just your's, can make use of.
>
> For now I would simply rip out the module option knobs and
> submit the simplest patch possible which always turns on
> multiqueue and never acts conditionally.
>
> You can add the knobs via a kernel wide facility later.
Okay. I am resending the patch with no module params what-so-ever. The default
is no-multiqueue though. Single queue code has matured and is optimized for
performance. Multiqueue code has got relatively lesser performance tuning. Since
there is no way to switch between the two modes as of now, it only makes sense
to keep the best known as default. When configuration knobs are introduced
later, multiqueue can be made default.
Thanks.
Shreyas
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 21314e0..6f3f905 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -44,6 +44,9 @@ MODULE_DEVICE_TABLE(pci, vmxnet3_pciid_table);
static atomic_t devices_found;
+#define VMXNET3_MAX_DEVICES 10
+static int enable_mq;
+static int irq_share_mode;
/*
* Enable/Disable the given intr
@@ -107,7 +110,7 @@ static void
vmxnet3_tq_start(struct vmxnet3_tx_queue *tq, struct vmxnet3_adapter *adapter)
{
tq->stopped = false;
- netif_start_queue(adapter->netdev);
+ netif_start_subqueue(adapter->netdev, tq - adapter->tx_queue);
}
@@ -115,7 +118,7 @@ static void
vmxnet3_tq_wake(struct vmxnet3_tx_queue *tq, struct vmxnet3_adapter *adapter)
{
tq->stopped = false;
- netif_wake_queue(adapter->netdev);
+ netif_wake_subqueue(adapter->netdev, (tq - adapter->tx_queue));
}
@@ -124,7 +127,7 @@ vmxnet3_tq_stop(struct vmxnet3_tx_queue *tq, struct vmxnet3_adapter *adapter)
{
tq->stopped = true;
tq->num_stop++;
- netif_stop_queue(adapter->netdev);
+ netif_stop_subqueue(adapter->netdev, (tq - adapter->tx_queue));
}
@@ -135,6 +138,7 @@ static void
vmxnet3_check_link(struct vmxnet3_adapter *adapter, bool affectTxQueue)
{
u32 ret;
+ int i;
VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_LINK);
ret = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD);
@@ -145,22 +149,28 @@ vmxnet3_check_link(struct vmxnet3_adapter *adapter, bool affectTxQueue)
if (!netif_carrier_ok(adapter->netdev))
netif_carrier_on(adapter->netdev);
- if (affectTxQueue)
- vmxnet3_tq_start(&adapter->tx_queue, adapter);
+ if (affectTxQueue) {
+ for (i = 0; i < adapter->num_tx_queues; i++)
+ vmxnet3_tq_start(&adapter->tx_queue[i],
+ adapter);
+ }
} else {
printk(KERN_INFO "%s: NIC Link is Down\n",
adapter->netdev->name);
if (netif_carrier_ok(adapter->netdev))
netif_carrier_off(adapter->netdev);
- if (affectTxQueue)
- vmxnet3_tq_stop(&adapter->tx_queue, adapter);
+ if (affectTxQueue) {
+ for (i = 0; i < adapter->num_tx_queues; i++)
+ vmxnet3_tq_stop(&adapter->tx_queue[i], adapter);
+ }
}
}
static void
vmxnet3_process_events(struct vmxnet3_adapter *adapter)
{
+ int i;
u32 events = le32_to_cpu(adapter->shared->ecr);
if (!events)
return;
@@ -176,16 +186,18 @@ vmxnet3_process_events(struct vmxnet3_adapter *adapter)
VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
VMXNET3_CMD_GET_QUEUE_STATUS);
- if (adapter->tqd_start->status.stopped) {
- printk(KERN_ERR "%s: tq error 0x%x\n",
- adapter->netdev->name,
- le32_to_cpu(adapter->tqd_start->status.error));
- }
- if (adapter->rqd_start->status.stopped) {
- printk(KERN_ERR "%s: rq error 0x%x\n",
- adapter->netdev->name,
- adapter->rqd_start->status.error);
- }
+ for (i = 0; i < adapter->num_tx_queues; i++)
+ if (adapter->tqd_start[i].status.stopped)
+ dev_dbg(&adapter->netdev->dev,
+ "%s: tq[%d] error 0x%x\n",
+ adapter->netdev->name, i, le32_to_cpu(
+ adapter->tqd_start[i].status.error));
+ for (i = 0; i < adapter->num_rx_queues; i++)
+ if (adapter->rqd_start[i].status.stopped)
+ dev_dbg(&adapter->netdev->dev,
+ "%s: rq[%d] error 0x%x\n",
+ adapter->netdev->name, i,
+ adapter->rqd_start[i].status.error);
schedule_work(&adapter->work);
}
@@ -410,7 +422,7 @@ vmxnet3_tq_cleanup(struct vmxnet3_tx_queue *tq,
}
-void
+static void
vmxnet3_tq_destroy(struct vmxnet3_tx_queue *tq,
struct vmxnet3_adapter *adapter)
{
@@ -437,6 +449,17 @@ vmxnet3_tq_destroy(struct vmxnet3_tx_queue *tq,
}
+/* Destroy all tx queues */
+void
+vmxnet3_tq_destroy_all(struct vmxnet3_adapter *adapter)
+{
+ int i;
+
+ for (i = 0; i < adapter->num_tx_queues; i++)
+ vmxnet3_tq_destroy(&adapter->tx_queue[i], adapter);
+}
+
+
static void
vmxnet3_tq_init(struct vmxnet3_tx_queue *tq,
struct vmxnet3_adapter *adapter)
@@ -518,6 +541,14 @@ err:
return -ENOMEM;
}
+static void
+vmxnet3_tq_cleanup_all(struct vmxnet3_adapter *adapter)
+{
+ int i;
+
+ for (i = 0; i < adapter->num_tx_queues; i++)
+ vmxnet3_tq_cleanup(&adapter->tx_queue[i], adapter);
+}
/*
* starting from ring->next2fill, allocate rx buffers for the given ring
@@ -732,6 +763,17 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
}
+/* Init all tx queues */
+static void
+vmxnet3_tq_init_all(struct vmxnet3_adapter *adapter)
+{
+ int i;
+
+ for (i = 0; i < adapter->num_tx_queues; i++)
+ vmxnet3_tq_init(&adapter->tx_queue[i], adapter);
+}
+
+
/*
* parse and copy relevant protocol headers:
* For a tso pkt, relevant headers are L2/3/4 including options
@@ -1000,8 +1042,8 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
if (le32_to_cpu(tq->shared->txNumDeferred) >=
le32_to_cpu(tq->shared->txThreshold)) {
tq->shared->txNumDeferred = 0;
- VMXNET3_WRITE_BAR0_REG(adapter, VMXNET3_REG_TXPROD,
- tq->tx_ring.next2fill);
+ VMXNET3_WRITE_BAR0_REG(adapter, (VMXNET3_REG_TXPROD +
+ tq->qid * 8), tq->tx_ring.next2fill);
}
return NETDEV_TX_OK;
@@ -1020,7 +1062,10 @@ vmxnet3_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
{
struct vmxnet3_adapter *adapter = netdev_priv(netdev);
- return vmxnet3_tq_xmit(skb, &adapter->tx_queue, adapter, netdev);
+ BUG_ON(skb->queue_mapping > adapter->num_tx_queues);
+ return vmxnet3_tq_xmit(skb,
+ &adapter->tx_queue[skb->queue_mapping],
+ adapter, netdev);
}
@@ -1106,9 +1151,9 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
break;
}
num_rxd++;
-
+ BUG_ON(rcd->rqID != rq->qid && rcd->rqID != rq->qid2);
idx = rcd->rxdIdx;
- ring_idx = rcd->rqID == rq->qid ? 0 : 1;
+ ring_idx = rcd->rqID < adapter->num_rx_queues ? 0 : 1;
vmxnet3_getRxDesc(rxd, &rq->rx_ring[ring_idx].base[idx].rxd,
&rxCmdDesc);
rbi = rq->buf_info[ring_idx] + idx;
@@ -1260,6 +1305,16 @@ vmxnet3_rq_cleanup(struct vmxnet3_rx_queue *rq,
}
+static void
+vmxnet3_rq_cleanup_all(struct vmxnet3_adapter *adapter)
+{
+ int i;
+
+ for (i = 0; i < adapter->num_rx_queues; i++)
+ vmxnet3_rq_cleanup(&adapter->rx_queue[i], adapter);
+}
+
+
void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq,
struct vmxnet3_adapter *adapter)
{
@@ -1351,6 +1406,25 @@ vmxnet3_rq_init(struct vmxnet3_rx_queue *rq,
static int
+vmxnet3_rq_init_all(struct vmxnet3_adapter *adapter)
+{
+ int i, err = 0;
+
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ err = vmxnet3_rq_init(&adapter->rx_queue[i], adapter);
+ if (unlikely(err)) {
+ dev_err(&adapter->netdev->dev, "%s: failed to "
+ "initialize rx queue%i\n",
+ adapter->netdev->name, i);
+ break;
+ }
+ }
+ return err;
+
+}
+
+
+static int
vmxnet3_rq_create(struct vmxnet3_rx_queue *rq, struct vmxnet3_adapter *adapter)
{
int i;
@@ -1398,33 +1472,177 @@ err:
static int
+vmxnet3_rq_create_all(struct vmxnet3_adapter *adapter)
+{
+ int i, err = 0;
+
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ err = vmxnet3_rq_create(&adapter->rx_queue[i], adapter);
+ if (unlikely(err)) {
+ dev_err(&adapter->netdev->dev,
+ "%s: failed to create rx queue%i\n",
+ adapter->netdev->name, i);
+ goto err_out;
+ }
+ }
+ return err;
+err_out:
+ vmxnet3_rq_destroy_all(adapter);
+ return err;
+
+}
+
+/* Multiple queue aware polling function for tx and rx */
+
+static int
vmxnet3_do_poll(struct vmxnet3_adapter *adapter, int budget)
{
+ int rcd_done = 0, i;
if (unlikely(adapter->shared->ecr))
vmxnet3_process_events(adapter);
+ for (i = 0; i < adapter->num_tx_queues; i++)
+ vmxnet3_tq_tx_complete(&adapter->tx_queue[i], adapter);
- vmxnet3_tq_tx_complete(&adapter->tx_queue, adapter);
- return vmxnet3_rq_rx_complete(&adapter->rx_queue, adapter, budget);
+ for (i = 0; i < adapter->num_rx_queues; i++)
+ rcd_done += vmxnet3_rq_rx_complete(&adapter->rx_queue[i],
+ adapter, budget);
+ return rcd_done;
}
static int
vmxnet3_poll(struct napi_struct *napi, int budget)
{
- struct vmxnet3_adapter *adapter = container_of(napi,
- struct vmxnet3_adapter, napi);
+ struct vmxnet3_rx_queue *rx_queue = container_of(napi,
+ struct vmxnet3_rx_queue, napi);
+ int rxd_done;
+
+ rxd_done = vmxnet3_do_poll(rx_queue->adapter, budget);
+
+ if (rxd_done < budget) {
+ napi_complete(napi);
+ vmxnet3_enable_all_intrs(rx_queue->adapter);
+ }
+ return rxd_done;
+}
+
+/*
+ * NAPI polling function for MSI-X mode with multiple Rx queues
+ * Returns the # of the NAPI credit consumed (# of rx descriptors processed)
+ */
+
+static int
+vmxnet3_poll_rx_only(struct napi_struct *napi, int budget)
+{
+ struct vmxnet3_rx_queue *rq = container_of(napi,
+ struct vmxnet3_rx_queue, napi);
+ struct vmxnet3_adapter *adapter = rq->adapter;
int rxd_done;
- rxd_done = vmxnet3_do_poll(adapter, budget);
+ /* When sharing interrupt with corresponding tx queue, process
+ * tx completions in that queue as well
+ */
+ if (adapter->share_intr == VMXNET3_INTR_BUDDYSHARE) {
+ struct vmxnet3_tx_queue *tq =
+ &adapter->tx_queue[rq - adapter->rx_queue];
+ vmxnet3_tq_tx_complete(tq, adapter);
+ }
+
+ rxd_done = vmxnet3_rq_rx_complete(rq, adapter, budget);
if (rxd_done < budget) {
napi_complete(napi);
- vmxnet3_enable_intr(adapter, 0);
+ vmxnet3_enable_intr(adapter, rq->comp_ring.intr_idx);
}
return rxd_done;
}
+#ifdef CONFIG_PCI_MSI
+
+/*
+ * Handle completion interrupts on tx queues
+ * Returns whether or not the intr is handled
+ */
+
+static irqreturn_t
+vmxnet3_msix_tx(int irq, void *data)
+{
+ struct vmxnet3_tx_queue *tq = data;
+ struct vmxnet3_adapter *adapter = tq->adapter;
+
+ if (adapter->intr.mask_mode == VMXNET3_IMM_ACTIVE)
+ vmxnet3_disable_intr(adapter, tq->comp_ring.intr_idx);
+
+ /* Handle the case where only one irq is allocate for all tx queues */
+ if (adapter->share_intr == VMXNET3_INTR_TXSHARE) {
+ int i;
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ struct vmxnet3_tx_queue *txq = &adapter->tx_queue[i];
+ vmxnet3_tq_tx_complete(txq, adapter);
+ }
+ } else {
+ vmxnet3_tq_tx_complete(tq, adapter);
+ }
+ vmxnet3_enable_intr(adapter, tq->comp_ring.intr_idx);
+
+ return IRQ_HANDLED;
+}
+
+
+/*
+ * Handle completion interrupts on rx queues. Returns whether or not the
+ * intr is handled
+ */
+
+static irqreturn_t
+vmxnet3_msix_rx(int irq, void *data)
+{
+ struct vmxnet3_rx_queue *rq = data;
+ struct vmxnet3_adapter *adapter = rq->adapter;
+
+ /* disable intr if needed */
+ if (adapter->intr.mask_mode == VMXNET3_IMM_ACTIVE)
+ vmxnet3_disable_intr(adapter, rq->comp_ring.intr_idx);
+ napi_schedule(&rq->napi);
+
+ return IRQ_HANDLED;
+}
+
+/*
+ *----------------------------------------------------------------------------
+ *
+ * vmxnet3_msix_event --
+ *
+ * vmxnet3 msix event intr handler
+ *
+ * Result:
+ * whether or not the intr is handled
+ *
+ *----------------------------------------------------------------------------
+ */
+
+static irqreturn_t
+vmxnet3_msix_event(int irq, void *data)
+{
+ struct net_device *dev = data;
+ struct vmxnet3_adapter *adapter = netdev_priv(dev);
+
+ /* disable intr if needed */
+ if (adapter->intr.mask_mode == VMXNET3_IMM_ACTIVE)
+ vmxnet3_disable_intr(adapter, adapter->intr.event_intr_idx);
+
+ if (adapter->shared->ecr)
+ vmxnet3_process_events(adapter);
+
+ vmxnet3_enable_intr(adapter, adapter->intr.event_intr_idx);
+
+ return IRQ_HANDLED;
+}
+
+#endif /* CONFIG_PCI_MSI */
+
+
/* Interrupt handler for vmxnet3 */
static irqreturn_t
vmxnet3_intr(int irq, void *dev_id)
@@ -1432,7 +1650,7 @@ vmxnet3_intr(int irq, void *dev_id)
struct net_device *dev = dev_id;
struct vmxnet3_adapter *adapter = netdev_priv(dev);
- if (unlikely(adapter->intr.type == VMXNET3_IT_INTX)) {
+ if (adapter->intr.type == VMXNET3_IT_INTX) {
u32 icr = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_ICR);
if (unlikely(icr == 0))
/* not ours */
@@ -1442,77 +1660,136 @@ vmxnet3_intr(int irq, void *dev_id)
/* disable intr if needed */
if (adapter->intr.mask_mode == VMXNET3_IMM_ACTIVE)
- vmxnet3_disable_intr(adapter, 0);
+ vmxnet3_disable_all_intrs(adapter);
- napi_schedule(&adapter->napi);
+ napi_schedule(&adapter->rx_queue[0].napi);
return IRQ_HANDLED;
}
#ifdef CONFIG_NET_POLL_CONTROLLER
-
/* netpoll callback. */
static void
vmxnet3_netpoll(struct net_device *netdev)
{
struct vmxnet3_adapter *adapter = netdev_priv(netdev);
- int irq;
-#ifdef CONFIG_PCI_MSI
- if (adapter->intr.type == VMXNET3_IT_MSIX)
- irq = adapter->intr.msix_entries[0].vector;
- else
-#endif
- irq = adapter->pdev->irq;
+ if (adapter->intr.mask_mode == VMXNET3_IMM_ACTIVE)
+ vmxnet3_disable_all_intrs(adapter);
+
+ vmxnet3_do_poll(adapter, adapter->rx_queue[0].rx_ring[0].size);
+ vmxnet3_enable_all_intrs(adapter);
- disable_irq(irq);
- vmxnet3_intr(irq, netdev);
- enable_irq(irq);
}
-#endif
+#endif /* CONFIG_NET_POLL_CONTROLLER */
static int
vmxnet3_request_irqs(struct vmxnet3_adapter *adapter)
{
- int err;
+ struct vmxnet3_intr *intr = &adapter->intr;
+ int err = 0, i;
+ int vector = 0;
#ifdef CONFIG_PCI_MSI
if (adapter->intr.type == VMXNET3_IT_MSIX) {
- /* we only use 1 MSI-X vector */
- err = request_irq(adapter->intr.msix_entries[0].vector,
- vmxnet3_intr, 0, adapter->netdev->name,
- adapter->netdev);
- } else if (adapter->intr.type == VMXNET3_IT_MSI) {
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ sprintf(adapter->tx_queue[i].name, "%s:v%d-%s",
+ adapter->netdev->name, vector, "Tx");
+ if (adapter->share_intr != VMXNET3_INTR_BUDDYSHARE)
+ err = request_irq(
+ intr->msix_entries[vector].vector,
+ vmxnet3_msix_tx, 0,
+ adapter->tx_queue[i].name,
+ &adapter->tx_queue[i]);
+ if (err) {
+ dev_err(&adapter->netdev->dev,
+ "Failed to request irq for MSIX, %s, "
+ "error %d\n",
+ adapter->tx_queue[i].name, err);
+ return err;
+ }
+
+ /* Handle the case where only 1 MSIx was allocated for
+ * all tx queues */
+ if (adapter->share_intr == VMXNET3_INTR_TXSHARE) {
+ for (; i < adapter->num_tx_queues; i++)
+ adapter->tx_queue[i].comp_ring.intr_idx
+ = vector;
+ vector++;
+ break;
+ } else {
+ adapter->tx_queue[i].comp_ring.intr_idx
+ = vector++;
+ }
+ }
+ if (adapter->share_intr == VMXNET3_INTR_BUDDYSHARE)
+ vector = 0;
+
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ sprintf(adapter->rx_queue[i].name, "%s:v%d-%s",
+ adapter->netdev->name, vector, "Rx");
+ err = request_irq(intr->msix_entries[vector].vector,
+ vmxnet3_msix_rx, 0,
+ adapter->rx_queue[i].name,
+ &(adapter->rx_queue[i]));
+ if (err) {
+ printk(KERN_ERR "Failed to request irq for MSIX"
+ ", %s, error %d\n",
+ adapter->rx_queue[i].name, err);
+ return err;
+ }
+
+ adapter->rx_queue[i].comp_ring.intr_idx = vector++;
+ }
+
+ sprintf(intr->event_msi_vector_name, "%s:v%d-event",
+ adapter->netdev->name, vector);
+ err = request_irq(intr->msix_entries[vector].vector,
+ vmxnet3_msix_event, 0,
+ intr->event_msi_vector_name, adapter->netdev);
+ intr->event_intr_idx = vector;
+
+ } else if (intr->type == VMXNET3_IT_MSI) {
+ adapter->num_rx_queues = 1;
err = request_irq(adapter->pdev->irq, vmxnet3_intr, 0,
adapter->netdev->name, adapter->netdev);
- } else
+ } else {
#endif
- {
+ adapter->num_rx_queues = 1;
err = request_irq(adapter->pdev->irq, vmxnet3_intr,
IRQF_SHARED, adapter->netdev->name,
adapter->netdev);
+#ifdef CONFIG_PCI_MSI
}
-
- if (err)
+#endif
+ intr->num_intrs = vector + 1;
+ if (err) {
printk(KERN_ERR "Failed to request irq %s (intr type:%d), error"
- ":%d\n", adapter->netdev->name, adapter->intr.type, err);
+ ":%d\n", adapter->netdev->name, intr->type, err);
+ } else {
+ /* Number of rx queues will not change after this */
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i];
+ rq->qid = i;
+ rq->qid2 = i + adapter->num_rx_queues;
+ }
- if (!err) {
- int i;
- /* init our intr settings */
- for (i = 0; i < adapter->intr.num_intrs; i++)
- adapter->intr.mod_levels[i] = UPT1_IML_ADAPTIVE;
- /* next setup intr index for all intr sources */
- adapter->tx_queue.comp_ring.intr_idx = 0;
- adapter->rx_queue.comp_ring.intr_idx = 0;
- adapter->intr.event_intr_idx = 0;
+ /* init our intr settings */
+ for (i = 0; i < intr->num_intrs; i++)
+ intr->mod_levels[i] = UPT1_IML_ADAPTIVE;
+ if (adapter->intr.type != VMXNET3_IT_MSIX) {
+ adapter->intr.event_intr_idx = 0;
+ for (i = 0; i < adapter->num_tx_queues; i++)
+ adapter->tx_queue[i].comp_ring.intr_idx = 0;
+ adapter->rx_queue[0].comp_ring.intr_idx = 0;
+ }
printk(KERN_INFO "%s: intr type %u, mode %u, %u vectors "
- "allocated\n", adapter->netdev->name, adapter->intr.type,
- adapter->intr.mask_mode, adapter->intr.num_intrs);
+ "allocated\n", adapter->netdev->name, intr->type,
+ intr->mask_mode, intr->num_intrs);
}
return err;
@@ -1522,18 +1799,32 @@ vmxnet3_request_irqs(struct vmxnet3_adapter *adapter)
static void
vmxnet3_free_irqs(struct vmxnet3_adapter *adapter)
{
- BUG_ON(adapter->intr.type == VMXNET3_IT_AUTO ||
- adapter->intr.num_intrs <= 0);
+ struct vmxnet3_intr *intr = &adapter->intr;
+ BUG_ON(intr->type == VMXNET3_IT_AUTO || intr->num_intrs <= 0);
- switch (adapter->intr.type) {
+ switch (intr->type) {
#ifdef CONFIG_PCI_MSI
case VMXNET3_IT_MSIX:
{
- int i;
+ int i, vector = 0;
+
+ if (adapter->share_intr != VMXNET3_INTR_BUDDYSHARE) {
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ free_irq(intr->msix_entries[vector++].vector,
+ &(adapter->tx_queue[i]));
+ if (adapter->share_intr == VMXNET3_INTR_TXSHARE)
+ break;
+ }
+ }
+
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ free_irq(intr->msix_entries[vector++].vector,
+ &(adapter->rx_queue[i]));
+ }
- for (i = 0; i < adapter->intr.num_intrs; i++)
- free_irq(adapter->intr.msix_entries[i].vector,
- adapter->netdev);
+ free_irq(intr->msix_entries[vector].vector,
+ adapter->netdev);
+ BUG_ON(vector >= intr->num_intrs);
break;
}
#endif
@@ -1727,6 +2018,15 @@ vmxnet3_set_mc(struct net_device *netdev)
kfree(new_table);
}
+void
+vmxnet3_rq_destroy_all(struct vmxnet3_adapter *adapter)
+{
+ int i;
+
+ for (i = 0; i < adapter->num_rx_queues; i++)
+ vmxnet3_rq_destroy(&adapter->rx_queue[i], adapter);
+}
+
/*
* Set up driver_shared based on settings in adapter.
@@ -1774,40 +2074,72 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter)
devRead->misc.mtu = cpu_to_le32(adapter->netdev->mtu);
devRead->misc.queueDescPA = cpu_to_le64(adapter->queue_desc_pa);
devRead->misc.queueDescLen = cpu_to_le32(
- sizeof(struct Vmxnet3_TxQueueDesc) +
- sizeof(struct Vmxnet3_RxQueueDesc));
+ adapter->num_tx_queues * sizeof(struct Vmxnet3_TxQueueDesc) +
+ adapter->num_rx_queues * sizeof(struct Vmxnet3_RxQueueDesc));
/* tx queue settings */
- BUG_ON(adapter->tx_queue.tx_ring.base == NULL);
-
- devRead->misc.numTxQueues = 1;
- tqc = &adapter->tqd_start->conf;
- tqc->txRingBasePA = cpu_to_le64(adapter->tx_queue.tx_ring.basePA);
- tqc->dataRingBasePA = cpu_to_le64(adapter->tx_queue.data_ring.basePA);
- tqc->compRingBasePA = cpu_to_le64(adapter->tx_queue.comp_ring.basePA);
- tqc->ddPA = cpu_to_le64(virt_to_phys(
- adapter->tx_queue.buf_info));
- tqc->txRingSize = cpu_to_le32(adapter->tx_queue.tx_ring.size);
- tqc->dataRingSize = cpu_to_le32(adapter->tx_queue.data_ring.size);
- tqc->compRingSize = cpu_to_le32(adapter->tx_queue.comp_ring.size);
- tqc->ddLen = cpu_to_le32(sizeof(struct vmxnet3_tx_buf_info) *
- tqc->txRingSize);
- tqc->intrIdx = adapter->tx_queue.comp_ring.intr_idx;
+ devRead->misc.numTxQueues = adapter->num_tx_queues;
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ struct vmxnet3_tx_queue *tq = &adapter->tx_queue[i];
+ BUG_ON(adapter->tx_queue[i].tx_ring.base == NULL);
+ tqc = &adapter->tqd_start[i].conf;
+ tqc->txRingBasePA = cpu_to_le64(tq->tx_ring.basePA);
+ tqc->dataRingBasePA = cpu_to_le64(tq->data_ring.basePA);
+ tqc->compRingBasePA = cpu_to_le64(tq->comp_ring.basePA);
+ tqc->ddPA = cpu_to_le64(virt_to_phys(tq->buf_info));
+ tqc->txRingSize = cpu_to_le32(tq->tx_ring.size);
+ tqc->dataRingSize = cpu_to_le32(tq->data_ring.size);
+ tqc->compRingSize = cpu_to_le32(tq->comp_ring.size);
+ tqc->ddLen = cpu_to_le32(
+ sizeof(struct vmxnet3_tx_buf_info) *
+ tqc->txRingSize);
+ tqc->intrIdx = tq->comp_ring.intr_idx;
+ }
/* rx queue settings */
- devRead->misc.numRxQueues = 1;
- rqc = &adapter->rqd_start->conf;
- rqc->rxRingBasePA[0] = cpu_to_le64(adapter->rx_queue.rx_ring[0].basePA);
- rqc->rxRingBasePA[1] = cpu_to_le64(adapter->rx_queue.rx_ring[1].basePA);
- rqc->compRingBasePA = cpu_to_le64(adapter->rx_queue.comp_ring.basePA);
- rqc->ddPA = cpu_to_le64(virt_to_phys(
- adapter->rx_queue.buf_info));
- rqc->rxRingSize[0] = cpu_to_le32(adapter->rx_queue.rx_ring[0].size);
- rqc->rxRingSize[1] = cpu_to_le32(adapter->rx_queue.rx_ring[1].size);
- rqc->compRingSize = cpu_to_le32(adapter->rx_queue.comp_ring.size);
- rqc->ddLen = cpu_to_le32(sizeof(struct vmxnet3_rx_buf_info) *
- (rqc->rxRingSize[0] + rqc->rxRingSize[1]));
- rqc->intrIdx = adapter->rx_queue.comp_ring.intr_idx;
+ devRead->misc.numRxQueues = adapter->num_rx_queues;
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i];
+ rqc = &adapter->rqd_start[i].conf;
+ rqc->rxRingBasePA[0] = cpu_to_le64(rq->rx_ring[0].basePA);
+ rqc->rxRingBasePA[1] = cpu_to_le64(rq->rx_ring[1].basePA);
+ rqc->compRingBasePA = cpu_to_le64(rq->comp_ring.basePA);
+ rqc->ddPA = cpu_to_le64(virt_to_phys(
+ rq->buf_info));
+ rqc->rxRingSize[0] = cpu_to_le32(rq->rx_ring[0].size);
+ rqc->rxRingSize[1] = cpu_to_le32(rq->rx_ring[1].size);
+ rqc->compRingSize = cpu_to_le32(rq->comp_ring.size);
+ rqc->ddLen = cpu_to_le32(
+ sizeof(struct vmxnet3_rx_buf_info) *
+ (rqc->rxRingSize[0] +
+ rqc->rxRingSize[1]));
+ rqc->intrIdx = rq->comp_ring.intr_idx;
+ }
+
+#ifdef VMXNET3_RSS
+ memset(adapter->rss_conf, 0, sizeof(*adapter->rss_conf));
+
+ if (adapter->rss) {
+ struct UPT1_RSSConf *rssConf = adapter->rss_conf;
+ devRead->misc.uptFeatures |= UPT1_F_RSS;
+ devRead->misc.numRxQueues = adapter->num_rx_queues;
+ rssConf->hashType = UPT1_RSS_HASH_TYPE_TCP_IPV4 |
+ UPT1_RSS_HASH_TYPE_IPV4 |
+ UPT1_RSS_HASH_TYPE_TCP_IPV6 |
+ UPT1_RSS_HASH_TYPE_IPV6;
+ rssConf->hashFunc = UPT1_RSS_HASH_FUNC_TOEPLITZ;
+ rssConf->hashKeySize = UPT1_RSS_MAX_KEY_SIZE;
+ rssConf->indTableSize = VMXNET3_RSS_IND_TABLE_SIZE;
+ get_random_bytes(&rssConf->hashKey[0], rssConf->hashKeySize);
+ for (i = 0; i < rssConf->indTableSize; i++)
+ rssConf->indTable[i] = i % adapter->num_rx_queues;
+
+ devRead->rssConfDesc.confVer = 1;
+ devRead->rssConfDesc.confLen = sizeof(*rssConf);
+ devRead->rssConfDesc.confPA = virt_to_phys(rssConf);
+ }
+
+#endif /* VMXNET3_RSS */
/* intr settings */
devRead->intrConf.autoMask = adapter->intr.mask_mode ==
@@ -1829,18 +2161,18 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter)
int
vmxnet3_activate_dev(struct vmxnet3_adapter *adapter)
{
- int err;
+ int err, i;
u32 ret;
- dev_dbg(&adapter->netdev->dev,
- "%s: skb_buf_size %d, rx_buf_per_pkt %d, ring sizes"
- " %u %u %u\n", adapter->netdev->name, adapter->skb_buf_size,
- adapter->rx_buf_per_pkt, adapter->tx_queue.tx_ring.size,
- adapter->rx_queue.rx_ring[0].size,
- adapter->rx_queue.rx_ring[1].size);
-
- vmxnet3_tq_init(&adapter->tx_queue, adapter);
- err = vmxnet3_rq_init(&adapter->rx_queue, adapter);
+ dev_dbg(&adapter->netdev->dev, "%s: skb_buf_size %d, rx_buf_per_pkt %d,"
+ " ring sizes %u %u %u\n", adapter->netdev->name,
+ adapter->skb_buf_size, adapter->rx_buf_per_pkt,
+ adapter->tx_queue[0].tx_ring.size,
+ adapter->rx_queue[0].rx_ring[0].size,
+ adapter->rx_queue[0].rx_ring[1].size);
+
+ vmxnet3_tq_init_all(adapter);
+ err = vmxnet3_rq_init_all(adapter);
if (err) {
printk(KERN_ERR "Failed to init rx queue for %s: error %d\n",
adapter->netdev->name, err);
@@ -1870,10 +2202,15 @@ vmxnet3_activate_dev(struct vmxnet3_adapter *adapter)
err = -EINVAL;
goto activate_err;
}
- VMXNET3_WRITE_BAR0_REG(adapter, VMXNET3_REG_RXPROD,
- adapter->rx_queue.rx_ring[0].next2fill);
- VMXNET3_WRITE_BAR0_REG(adapter, VMXNET3_REG_RXPROD2,
- adapter->rx_queue.rx_ring[1].next2fill);
+
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ VMXNET3_WRITE_BAR0_REG(adapter, (VMXNET3_REG_RXPROD +
+ (i * VMXNET3_REG_ALIGN)),
+ adapter->rx_queue[i].rx_ring[0].next2fill);
+ VMXNET3_WRITE_BAR0_REG(adapter, (VMXNET3_REG_RXPROD2 +
+ (i * VMXNET3_REG_ALIGN)),
+ adapter->rx_queue[i].rx_ring[1].next2fill);
+ }
/* Apply the rx filter settins last. */
vmxnet3_set_mc(adapter->netdev);
@@ -1883,8 +2220,8 @@ vmxnet3_activate_dev(struct vmxnet3_adapter *adapter)
* tx queue if the link is up.
*/
vmxnet3_check_link(adapter, true);
-
- napi_enable(&adapter->napi);
+ for (i = 0; i < adapter->num_rx_queues; i++)
+ napi_enable(&adapter->rx_queue[i].napi);
vmxnet3_enable_all_intrs(adapter);
clear_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state);
return 0;
@@ -1896,7 +2233,7 @@ activate_err:
irq_err:
rq_err:
/* free up buffers we allocated */
- vmxnet3_rq_cleanup(&adapter->rx_queue, adapter);
+ vmxnet3_rq_cleanup_all(adapter);
return err;
}
@@ -1911,6 +2248,7 @@ vmxnet3_reset_dev(struct vmxnet3_adapter *adapter)
int
vmxnet3_quiesce_dev(struct vmxnet3_adapter *adapter)
{
+ int i;
if (test_and_set_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state))
return 0;
@@ -1919,13 +2257,14 @@ vmxnet3_quiesce_dev(struct vmxnet3_adapter *adapter)
VMXNET3_CMD_QUIESCE_DEV);
vmxnet3_disable_all_intrs(adapter);
- napi_disable(&adapter->napi);
+ for (i = 0; i < adapter->num_rx_queues; i++)
+ napi_disable(&adapter->rx_queue[i].napi);
netif_tx_disable(adapter->netdev);
adapter->link_speed = 0;
netif_carrier_off(adapter->netdev);
- vmxnet3_tq_cleanup(&adapter->tx_queue, adapter);
- vmxnet3_rq_cleanup(&adapter->rx_queue, adapter);
+ vmxnet3_tq_cleanup_all(adapter);
+ vmxnet3_rq_cleanup_all(adapter);
vmxnet3_free_irqs(adapter);
return 0;
}
@@ -2047,7 +2386,9 @@ vmxnet3_free_pci_resources(struct vmxnet3_adapter *adapter)
static void
vmxnet3_adjust_rx_ring_size(struct vmxnet3_adapter *adapter)
{
- size_t sz;
+ size_t sz, i, ring0_size, ring1_size, comp_size;
+ struct vmxnet3_rx_queue *rq = &adapter->rx_queue[0];
+
if (adapter->netdev->mtu <= VMXNET3_MAX_SKB_BUF_SIZE -
VMXNET3_MAX_ETH_HDR_SIZE) {
@@ -2069,11 +2410,19 @@ vmxnet3_adjust_rx_ring_size(struct vmxnet3_adapter *adapter)
* rx_buf_per_pkt * VMXNET3_RING_SIZE_ALIGN
*/
sz = adapter->rx_buf_per_pkt * VMXNET3_RING_SIZE_ALIGN;
- adapter->rx_queue.rx_ring[0].size = (adapter->rx_queue.rx_ring[0].size +
- sz - 1) / sz * sz;
- adapter->rx_queue.rx_ring[0].size = min_t(u32,
- adapter->rx_queue.rx_ring[0].size,
- VMXNET3_RX_RING_MAX_SIZE / sz * sz);
+ ring0_size = adapter->rx_queue[0].rx_ring[0].size;
+ ring0_size = (ring0_size + sz - 1) / sz * sz;
+ ring0_size = min_t(u32, rq->rx_ring[0].size, VMXNET3_RX_RING_MAX_SIZE /
+ sz * sz);
+ ring1_size = adapter->rx_queue[0].rx_ring[1].size;
+ comp_size = ring0_size + ring1_size;
+
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ rq = &adapter->rx_queue[i];
+ rq->rx_ring[0].size = ring0_size;
+ rq->rx_ring[1].size = ring1_size;
+ rq->comp_ring.size = comp_size;
+ }
}
@@ -2081,29 +2430,53 @@ int
vmxnet3_create_queues(struct vmxnet3_adapter *adapter, u32 tx_ring_size,
u32 rx_ring_size, u32 rx_ring2_size)
{
- int err;
-
- adapter->tx_queue.tx_ring.size = tx_ring_size;
- adapter->tx_queue.data_ring.size = tx_ring_size;
- adapter->tx_queue.comp_ring.size = tx_ring_size;
- adapter->tx_queue.shared = &adapter->tqd_start->ctrl;
- adapter->tx_queue.stopped = true;
- err = vmxnet3_tq_create(&adapter->tx_queue, adapter);
- if (err)
- return err;
+ int err = 0, i;
+
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ struct vmxnet3_tx_queue *tq = &adapter->tx_queue[i];
+ tq->tx_ring.size = tx_ring_size;
+ tq->data_ring.size = tx_ring_size;
+ tq->comp_ring.size = tx_ring_size;
+ tq->shared = &adapter->tqd_start[i].ctrl;
+ tq->stopped = true;
+ tq->adapter = adapter;
+ tq->qid = i;
+ err = vmxnet3_tq_create(tq, adapter);
+ /*
+ * Too late to change num_tx_queues. We cannot do away with
+ * lesser number of queues than what we asked for
+ */
+ if (err)
+ goto queue_err;
+ }
- adapter->rx_queue.rx_ring[0].size = rx_ring_size;
- adapter->rx_queue.rx_ring[1].size = rx_ring2_size;
+ adapter->rx_queue[0].rx_ring[0].size = rx_ring_size;
+ adapter->rx_queue[0].rx_ring[1].size = rx_ring2_size;
vmxnet3_adjust_rx_ring_size(adapter);
- adapter->rx_queue.comp_ring.size = adapter->rx_queue.rx_ring[0].size +
- adapter->rx_queue.rx_ring[1].size;
- adapter->rx_queue.qid = 0;
- adapter->rx_queue.qid2 = 1;
- adapter->rx_queue.shared = &adapter->rqd_start->ctrl;
- err = vmxnet3_rq_create(&adapter->rx_queue, adapter);
- if (err)
- vmxnet3_tq_destroy(&adapter->tx_queue, adapter);
-
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i];
+ /* qid and qid2 for rx queues will be assigned later when num
+ * of rx queues is finalized after allocating intrs */
+ rq->shared = &adapter->rqd_start[i].ctrl;
+ rq->adapter = adapter;
+ err = vmxnet3_rq_create(rq, adapter);
+ if (err) {
+ if (i == 0) {
+ printk(KERN_ERR "Could not allocate any rx"
+ "queues. Aborting.\n");
+ goto queue_err;
+ } else {
+ printk(KERN_INFO "Number of rx queues changed "
+ "to : %d.\n", i);
+ adapter->num_rx_queues = i;
+ err = 0;
+ break;
+ }
+ }
+ }
+ return err;
+queue_err:
+ vmxnet3_tq_destroy_all(adapter);
return err;
}
@@ -2111,11 +2484,12 @@ static int
vmxnet3_open(struct net_device *netdev)
{
struct vmxnet3_adapter *adapter;
- int err;
+ int err, i;
adapter = netdev_priv(netdev);
- spin_lock_init(&adapter->tx_queue.tx_lock);
+ for (i = 0; i < adapter->num_tx_queues; i++)
+ spin_lock_init(&adapter->tx_queue[i].tx_lock);
err = vmxnet3_create_queues(adapter, VMXNET3_DEF_TX_RING_SIZE,
VMXNET3_DEF_RX_RING_SIZE,
@@ -2130,8 +2504,8 @@ vmxnet3_open(struct net_device *netdev)
return 0;
activate_err:
- vmxnet3_rq_destroy(&adapter->rx_queue, adapter);
- vmxnet3_tq_destroy(&adapter->tx_queue, adapter);
+ vmxnet3_rq_destroy_all(adapter);
+ vmxnet3_tq_destroy_all(adapter);
queue_err:
return err;
}
@@ -2151,8 +2525,8 @@ vmxnet3_close(struct net_device *netdev)
vmxnet3_quiesce_dev(adapter);
- vmxnet3_rq_destroy(&adapter->rx_queue, adapter);
- vmxnet3_tq_destroy(&adapter->tx_queue, adapter);
+ vmxnet3_rq_destroy_all(adapter);
+ vmxnet3_tq_destroy_all(adapter);
clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state);
@@ -2164,6 +2538,8 @@ vmxnet3_close(struct net_device *netdev)
void
vmxnet3_force_close(struct vmxnet3_adapter *adapter)
{
+ int i;
+
/*
* we must clear VMXNET3_STATE_BIT_RESETTING, otherwise
* vmxnet3_close() will deadlock.
@@ -2171,7 +2547,8 @@ vmxnet3_force_close(struct vmxnet3_adapter *adapter)
BUG_ON(test_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state));
/* we need to enable NAPI, otherwise dev_close will deadlock */
- napi_enable(&adapter->napi);
+ for (i = 0; i < adapter->num_rx_queues; i++)
+ napi_enable(&adapter->rx_queue[i].napi);
dev_close(adapter->netdev);
}
@@ -2202,14 +2579,11 @@ vmxnet3_change_mtu(struct net_device *netdev, int new_mtu)
vmxnet3_reset_dev(adapter);
/* we need to re-create the rx queue based on the new mtu */
- vmxnet3_rq_destroy(&adapter->rx_queue, adapter);
+ vmxnet3_rq_destroy_all(adapter);
vmxnet3_adjust_rx_ring_size(adapter);
- adapter->rx_queue.comp_ring.size =
- adapter->rx_queue.rx_ring[0].size +
- adapter->rx_queue.rx_ring[1].size;
- err = vmxnet3_rq_create(&adapter->rx_queue, adapter);
+ err = vmxnet3_rq_create_all(adapter);
if (err) {
- printk(KERN_ERR "%s: failed to re-create rx queue,"
+ printk(KERN_ERR "%s: failed to re-create rx queues,"
" error %d. Closing it.\n", netdev->name, err);
goto out;
}
@@ -2274,6 +2648,55 @@ vmxnet3_read_mac_addr(struct vmxnet3_adapter *adapter, u8 *mac)
mac[5] = (tmp >> 8) & 0xff;
}
+#ifdef CONFIG_PCI_MSI
+
+/*
+ * Enable MSIx vectors.
+ * Returns :
+ * 0 on successful enabling of required vectors,
+ * VMXNET3_LINUX_MIN_MSIX_VECT when only minumum number of vectors required
+ * could be enabled.
+ * number of vectors which can be enabled otherwise (this number is smaller
+ * than VMXNET3_LINUX_MIN_MSIX_VECT)
+ */
+
+static int
+vmxnet3_acquire_msix_vectors(struct vmxnet3_adapter *adapter,
+ int vectors)
+{
+ int err = 0, vector_threshold;
+ vector_threshold = VMXNET3_LINUX_MIN_MSIX_VECT;
+
+ while (vectors >= vector_threshold) {
+ err = pci_enable_msix(adapter->pdev, adapter->intr.msix_entries,
+ vectors);
+ if (!err) {
+ adapter->intr.num_intrs = vectors;
+ return 0;
+ } else if (err < 0) {
+ printk(KERN_ERR "Failed to enable MSI-X for %s, error"
+ " %d\n", adapter->netdev->name, err);
+ vectors = 0;
+ } else if (err < vector_threshold) {
+ break;
+ } else {
+ /* If fails to enable required number of MSI-x vectors
+ * try enabling 3 of them. One each for rx, tx and event
+ */
+ vectors = vector_threshold;
+ printk(KERN_ERR "Failed to enable %d MSI-X for %s, try"
+ " %d instead\n", vectors, adapter->netdev->name,
+ vector_threshold);
+ }
+ }
+
+ printk(KERN_INFO "Number of MSI-X interrupts which can be allocatedi"
+ " are lower than min threshold required.\n");
+ return err;
+}
+
+
+#endif /* CONFIG_PCI_MSI */
static void
vmxnet3_alloc_intr_resources(struct vmxnet3_adapter *adapter)
@@ -2293,16 +2716,47 @@ vmxnet3_alloc_intr_resources(struct vmxnet3_adapter *adapter)
#ifdef CONFIG_PCI_MSI
if (adapter->intr.type == VMXNET3_IT_MSIX) {
- int err;
-
- adapter->intr.msix_entries[0].entry = 0;
- err = pci_enable_msix(adapter->pdev, adapter->intr.msix_entries,
- VMXNET3_LINUX_MAX_MSIX_VECT);
- if (!err) {
- adapter->intr.num_intrs = 1;
- adapter->intr.type = VMXNET3_IT_MSIX;
+ int vector, err = 0;
+
+ adapter->intr.num_intrs = (adapter->share_intr ==
+ VMXNET3_INTR_TXSHARE) ? 1 :
+ adapter->num_tx_queues;
+ adapter->intr.num_intrs += (adapter->share_intr ==
+ VMXNET3_INTR_BUDDYSHARE) ? 0 :
+ adapter->num_rx_queues;
+ adapter->intr.num_intrs += 1; /* for link event */
+
+ adapter->intr.num_intrs = (adapter->intr.num_intrs >
+ VMXNET3_LINUX_MIN_MSIX_VECT
+ ? adapter->intr.num_intrs :
+ VMXNET3_LINUX_MIN_MSIX_VECT);
+
+ for (vector = 0; vector < adapter->intr.num_intrs; vector++)
+ adapter->intr.msix_entries[vector].entry = vector;
+
+ err = vmxnet3_acquire_msix_vectors(adapter,
+ adapter->intr.num_intrs);
+ /* If we cannot allocate one MSIx vector per queue
+ * then limit the number of rx queues to 1
+ */
+ if (err == VMXNET3_LINUX_MIN_MSIX_VECT) {
+ if (adapter->share_intr != VMXNET3_INTR_BUDDYSHARE
+ || adapter->num_rx_queues != 2) {
+ adapter->share_intr = VMXNET3_INTR_TXSHARE;
+ printk(KERN_ERR "Number of rx queues : 1\n");
+ adapter->num_rx_queues = 1;
+ adapter->intr.num_intrs =
+ VMXNET3_LINUX_MIN_MSIX_VECT;
+ }
return;
}
+ if (!err)
+ return;
+
+ /* If we cannot allocate MSIx vectors use only one rx queue */
+ printk(KERN_INFO "Failed to enable MSI-X for %s, error %d."
+ "#rx queues : 1, try MSI\n", adapter->netdev->name, err);
+
adapter->intr.type = VMXNET3_IT_MSI;
}
@@ -2310,12 +2764,15 @@ vmxnet3_alloc_intr_resources(struct vmxnet3_adapter *adapter)
int err;
err = pci_enable_msi(adapter->pdev);
if (!err) {
+ adapter->num_rx_queues = 1;
adapter->intr.num_intrs = 1;
return;
}
}
#endif /* CONFIG_PCI_MSI */
+ adapter->num_rx_queues = 1;
+ printk(KERN_INFO "Using INTx interrupt, #Rx queues: 1.\n");
adapter->intr.type = VMXNET3_IT_INTX;
/* INT-X related setting */
@@ -2343,6 +2800,7 @@ vmxnet3_tx_timeout(struct net_device *netdev)
printk(KERN_ERR "%s: tx hang\n", adapter->netdev->name);
schedule_work(&adapter->work);
+ netif_wake_queue(adapter->netdev);
}
@@ -2399,8 +2857,32 @@ vmxnet3_probe_device(struct pci_dev *pdev,
struct net_device *netdev;
struct vmxnet3_adapter *adapter;
u8 mac[ETH_ALEN];
+ int size;
+ int num_tx_queues = enable_mq == 0 ? 1 : 0;
+ int num_rx_queues = enable_mq == 0 ? 1 : 0;
+
+#ifdef VMXNET3_RSS
+ if (num_rx_queues == 0)
+ num_rx_queues = min(VMXNET3_DEVICE_MAX_RX_QUEUES,
+ (int)num_online_cpus());
+ else
+ num_rx_queues = min(VMXNET3_DEVICE_MAX_RX_QUEUES,
+ num_rx_queues);
+#else
+ num_rx_queues = 1;
+#endif
+
+ if (num_tx_queues <= 0)
+ num_tx_queues = min(VMXNET3_DEVICE_MAX_TX_QUEUES,
+ (int)num_online_cpus());
+ else
+ num_tx_queues = min(VMXNET3_DEVICE_MAX_TX_QUEUES,
+ num_tx_queues);
+ netdev = alloc_etherdev_mq(sizeof(struct vmxnet3_adapter),
+ num_tx_queues);
+ printk(KERN_INFO "# of Tx queues : %d, # of Rx queues : %d\n",
+ num_tx_queues, num_rx_queues);
- netdev = alloc_etherdev(sizeof(struct vmxnet3_adapter));
if (!netdev) {
printk(KERN_ERR "Failed to alloc ethernet device for adapter "
"%s\n", pci_name(pdev));
@@ -2422,9 +2904,12 @@ vmxnet3_probe_device(struct pci_dev *pdev,
goto err_alloc_shared;
}
- adapter->tqd_start = pci_alloc_consistent(adapter->pdev,
- sizeof(struct Vmxnet3_TxQueueDesc) +
- sizeof(struct Vmxnet3_RxQueueDesc),
+ adapter->num_rx_queues = num_rx_queues;
+ adapter->num_tx_queues = num_tx_queues;
+
+ size = sizeof(struct Vmxnet3_TxQueueDesc) * adapter->num_tx_queues;
+ size += sizeof(struct Vmxnet3_RxQueueDesc) * adapter->num_rx_queues;
+ adapter->tqd_start = pci_alloc_consistent(adapter->pdev, size,
&adapter->queue_desc_pa);
if (!adapter->tqd_start) {
@@ -2433,8 +2918,8 @@ vmxnet3_probe_device(struct pci_dev *pdev,
err = -ENOMEM;
goto err_alloc_queue_desc;
}
- adapter->rqd_start = (struct Vmxnet3_RxQueueDesc *)(adapter->tqd_start
- + 1);
+ adapter->rqd_start = (struct Vmxnet3_RxQueueDesc *)(adapter->tqd_start +
+ adapter->num_tx_queues);
adapter->pm_conf = kmalloc(sizeof(struct Vmxnet3_PMConf), GFP_KERNEL);
if (adapter->pm_conf == NULL) {
@@ -2444,6 +2929,17 @@ vmxnet3_probe_device(struct pci_dev *pdev,
goto err_alloc_pm;
}
+#ifdef VMXNET3_RSS
+
+ adapter->rss_conf = kmalloc(sizeof(struct UPT1_RSSConf), GFP_KERNEL);
+ if (adapter->rss_conf == NULL) {
+ printk(KERN_ERR "Failed to allocate memory for %s\n",
+ pci_name(pdev));
+ err = -ENOMEM;
+ goto err_alloc_rss;
+ }
+#endif /* VMXNET3_RSS */
+
err = vmxnet3_alloc_pci_resources(adapter, &dma64);
if (err < 0)
goto err_alloc_pci;
@@ -2471,8 +2967,24 @@ vmxnet3_probe_device(struct pci_dev *pdev,
vmxnet3_declare_features(adapter, dma64);
adapter->dev_number = atomic_read(&devices_found);
+
+ adapter->share_intr = irq_share_mode;
+ if (adapter->share_intr == VMXNET3_INTR_BUDDYSHARE &&
+ adapter->num_tx_queues != adapter->num_rx_queues)
+ adapter->share_intr = VMXNET3_INTR_DONTSHARE;
+
vmxnet3_alloc_intr_resources(adapter);
+#ifdef VMXNET3_RSS
+ if (adapter->num_rx_queues > 1 &&
+ adapter->intr.type == VMXNET3_IT_MSIX) {
+ adapter->rss = true;
+ printk(KERN_INFO "RSS is enabled.\n");
+ } else {
+ adapter->rss = false;
+ }
+#endif
+
vmxnet3_read_mac_addr(adapter, mac);
memcpy(netdev->dev_addr, mac, netdev->addr_len);
@@ -2482,7 +2994,18 @@ vmxnet3_probe_device(struct pci_dev *pdev,
INIT_WORK(&adapter->work, vmxnet3_reset_work);
- netif_napi_add(netdev, &adapter->napi, vmxnet3_poll, 64);
+ if (adapter->intr.type == VMXNET3_IT_MSIX) {
+ int i;
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ netif_napi_add(adapter->netdev,
+ &adapter->rx_queue[i].napi,
+ vmxnet3_poll_rx_only, 64);
+ }
+ } else {
+ netif_napi_add(adapter->netdev, &adapter->rx_queue[0].napi,
+ vmxnet3_poll, 64);
+ }
+
SET_NETDEV_DEV(netdev, &pdev->dev);
err = register_netdev(netdev);
@@ -2502,11 +3025,14 @@ err_register:
err_ver:
vmxnet3_free_pci_resources(adapter);
err_alloc_pci:
+#ifdef VMXNET3_RSS
+ kfree(adapter->rss_conf);
+err_alloc_rss:
+#endif
kfree(adapter->pm_conf);
err_alloc_pm:
- pci_free_consistent(adapter->pdev, sizeof(struct Vmxnet3_TxQueueDesc) +
- sizeof(struct Vmxnet3_RxQueueDesc),
- adapter->tqd_start, adapter->queue_desc_pa);
+ pci_free_consistent(adapter->pdev, size, adapter->tqd_start,
+ adapter->queue_desc_pa);
err_alloc_queue_desc:
pci_free_consistent(adapter->pdev, sizeof(struct Vmxnet3_DriverShared),
adapter->shared, adapter->shared_pa);
@@ -2522,6 +3048,19 @@ vmxnet3_remove_device(struct pci_dev *pdev)
{
struct net_device *netdev = pci_get_drvdata(pdev);
struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+ int size = 0;
+ int num_rx_queues = enable_mq == 0 ? 1 : 0;
+
+#ifdef VMXNET3_RSS
+ if (num_rx_queues <= 0)
+ num_rx_queues = min(VMXNET3_DEVICE_MAX_RX_QUEUES,
+ (int)num_online_cpus());
+ else
+ num_rx_queues = min(VMXNET3_DEVICE_MAX_RX_QUEUES,
+ num_rx_queues);
+#else
+ num_rx_queues = 1;
+#endif
flush_scheduled_work();
@@ -2529,10 +3068,15 @@ vmxnet3_remove_device(struct pci_dev *pdev)
vmxnet3_free_intr_resources(adapter);
vmxnet3_free_pci_resources(adapter);
+#ifdef VMXNET3_RSS
+ kfree(adapter->rss_conf);
+#endif
kfree(adapter->pm_conf);
- pci_free_consistent(adapter->pdev, sizeof(struct Vmxnet3_TxQueueDesc) +
- sizeof(struct Vmxnet3_RxQueueDesc),
- adapter->tqd_start, adapter->queue_desc_pa);
+
+ size = sizeof(struct Vmxnet3_TxQueueDesc) * adapter->num_tx_queues;
+ size += sizeof(struct Vmxnet3_RxQueueDesc) * num_rx_queues;
+ pci_free_consistent(adapter->pdev, size, adapter->tqd_start,
+ adapter->queue_desc_pa);
pci_free_consistent(adapter->pdev, sizeof(struct Vmxnet3_DriverShared),
adapter->shared, adapter->shared_pa);
free_netdev(netdev);
@@ -2563,7 +3107,7 @@ vmxnet3_suspend(struct device *device)
vmxnet3_free_intr_resources(adapter);
netif_device_detach(netdev);
- netif_stop_queue(netdev);
+ netif_tx_stop_all_queues(netdev);
/* Create wake-up filters. */
pmConf = adapter->pm_conf;
@@ -2708,6 +3252,7 @@ vmxnet3_init_module(void)
{
printk(KERN_INFO "%s - version %s\n", VMXNET3_DRIVER_DESC,
VMXNET3_DRIVER_VERSION_REPORT);
+ atomic_set(&devices_found, 0);
return pci_register_driver(&vmxnet3_driver);
}
@@ -2726,3 +3271,5 @@ MODULE_AUTHOR("VMware, Inc.");
MODULE_DESCRIPTION(VMXNET3_DRIVER_DESC);
MODULE_LICENSE("GPL v2");
MODULE_VERSION(VMXNET3_DRIVER_VERSION_STRING);
+
+
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index b79070b..9a80106 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -151,44 +151,42 @@ vmxnet3_get_stats(struct net_device *netdev)
struct UPT1_TxStats *devTxStats;
struct UPT1_RxStats *devRxStats;
struct net_device_stats *net_stats = &netdev->stats;
+ int i;
adapter = netdev_priv(netdev);
/* Collect the dev stats into the shared area */
VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_STATS);
- /* Assuming that we have a single queue device */
- devTxStats = &adapter->tqd_start->stats;
- devRxStats = &adapter->rqd_start->stats;
-
- /* Get access to the driver stats per queue */
- drvTxStats = &adapter->tx_queue.stats;
- drvRxStats = &adapter->rx_queue.stats;
-
memset(net_stats, 0, sizeof(*net_stats));
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ devTxStats = &adapter->tqd_start[i].stats;
+ drvTxStats = &adapter->tx_queue[i].stats;
+ net_stats->tx_packets += devTxStats->ucastPktsTxOK +
+ devTxStats->mcastPktsTxOK +
+ devTxStats->bcastPktsTxOK;
+ net_stats->tx_bytes += devTxStats->ucastBytesTxOK +
+ devTxStats->mcastBytesTxOK +
+ devTxStats->bcastBytesTxOK;
+ net_stats->tx_errors += devTxStats->pktsTxError;
+ net_stats->tx_dropped += drvTxStats->drop_total;
+ }
- net_stats->rx_packets = devRxStats->ucastPktsRxOK +
- devRxStats->mcastPktsRxOK +
- devRxStats->bcastPktsRxOK;
-
- net_stats->tx_packets = devTxStats->ucastPktsTxOK +
- devTxStats->mcastPktsTxOK +
- devTxStats->bcastPktsTxOK;
-
- net_stats->rx_bytes = devRxStats->ucastBytesRxOK +
- devRxStats->mcastBytesRxOK +
- devRxStats->bcastBytesRxOK;
-
- net_stats->tx_bytes = devTxStats->ucastBytesTxOK +
- devTxStats->mcastBytesTxOK +
- devTxStats->bcastBytesTxOK;
+ for (i = 0; i < adapter->num_rx_queues; i++) {
+ devRxStats = &adapter->rqd_start[i].stats;
+ drvRxStats = &adapter->rx_queue[i].stats;
+ net_stats->rx_packets += devRxStats->ucastPktsRxOK +
+ devRxStats->mcastPktsRxOK +
+ devRxStats->bcastPktsRxOK;
- net_stats->rx_errors = devRxStats->pktsRxError;
- net_stats->tx_errors = devTxStats->pktsTxError;
- net_stats->rx_dropped = drvRxStats->drop_total;
- net_stats->tx_dropped = drvTxStats->drop_total;
- net_stats->multicast = devRxStats->mcastPktsRxOK;
+ net_stats->rx_bytes += devRxStats->ucastBytesRxOK +
+ devRxStats->mcastBytesRxOK +
+ devRxStats->bcastBytesRxOK;
+ net_stats->rx_errors += devRxStats->pktsRxError;
+ net_stats->rx_dropped += drvRxStats->drop_total;
+ net_stats->multicast += devRxStats->mcastPktsRxOK;
+ }
return net_stats;
}
@@ -307,24 +305,26 @@ vmxnet3_get_ethtool_stats(struct net_device *netdev,
struct vmxnet3_adapter *adapter = netdev_priv(netdev);
u8 *base;
int i;
+ int j = 0;
VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_STATS);
/* this does assume each counter is 64-bit wide */
+/* TODO change this for multiple queues */
- base = (u8 *)&adapter->tqd_start->stats;
+ base = (u8 *)&adapter->tqd_start[j].stats;
for (i = 0; i < ARRAY_SIZE(vmxnet3_tq_dev_stats); i++)
*buf++ = *(u64 *)(base + vmxnet3_tq_dev_stats[i].offset);
- base = (u8 *)&adapter->tx_queue.stats;
+ base = (u8 *)&adapter->tx_queue[j].stats;
for (i = 0; i < ARRAY_SIZE(vmxnet3_tq_driver_stats); i++)
*buf++ = *(u64 *)(base + vmxnet3_tq_driver_stats[i].offset);
- base = (u8 *)&adapter->rqd_start->stats;
+ base = (u8 *)&adapter->rqd_start[j].stats;
for (i = 0; i < ARRAY_SIZE(vmxnet3_rq_dev_stats); i++)
*buf++ = *(u64 *)(base + vmxnet3_rq_dev_stats[i].offset);
- base = (u8 *)&adapter->rx_queue.stats;
+ base = (u8 *)&adapter->rx_queue[j].stats;
for (i = 0; i < ARRAY_SIZE(vmxnet3_rq_driver_stats); i++)
*buf++ = *(u64 *)(base + vmxnet3_rq_driver_stats[i].offset);
@@ -339,6 +339,7 @@ vmxnet3_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p)
{
struct vmxnet3_adapter *adapter = netdev_priv(netdev);
u32 *buf = p;
+ int i = 0;
memset(p, 0, vmxnet3_get_regs_len(netdev));
@@ -347,28 +348,29 @@ vmxnet3_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p)
/* Update vmxnet3_get_regs_len if we want to dump more registers */
/* make each ring use multiple of 16 bytes */
- buf[0] = adapter->tx_queue.tx_ring.next2fill;
- buf[1] = adapter->tx_queue.tx_ring.next2comp;
- buf[2] = adapter->tx_queue.tx_ring.gen;
+/* TODO change this for multiple queues */
+ buf[0] = adapter->tx_queue[i].tx_ring.next2fill;
+ buf[1] = adapter->tx_queue[i].tx_ring.next2comp;
+ buf[2] = adapter->tx_queue[i].tx_ring.gen;
buf[3] = 0;
- buf[4] = adapter->tx_queue.comp_ring.next2proc;
- buf[5] = adapter->tx_queue.comp_ring.gen;
- buf[6] = adapter->tx_queue.stopped;
+ buf[4] = adapter->tx_queue[i].comp_ring.next2proc;
+ buf[5] = adapter->tx_queue[i].comp_ring.gen;
+ buf[6] = adapter->tx_queue[i].stopped;
buf[7] = 0;
- buf[8] = adapter->rx_queue.rx_ring[0].next2fill;
- buf[9] = adapter->rx_queue.rx_ring[0].next2comp;
- buf[10] = adapter->rx_queue.rx_ring[0].gen;
+ buf[8] = adapter->rx_queue[i].rx_ring[0].next2fill;
+ buf[9] = adapter->rx_queue[i].rx_ring[0].next2comp;
+ buf[10] = adapter->rx_queue[i].rx_ring[0].gen;
buf[11] = 0;
- buf[12] = adapter->rx_queue.rx_ring[1].next2fill;
- buf[13] = adapter->rx_queue.rx_ring[1].next2comp;
- buf[14] = adapter->rx_queue.rx_ring[1].gen;
+ buf[12] = adapter->rx_queue[i].rx_ring[1].next2fill;
+ buf[13] = adapter->rx_queue[i].rx_ring[1].next2comp;
+ buf[14] = adapter->rx_queue[i].rx_ring[1].gen;
buf[15] = 0;
- buf[16] = adapter->rx_queue.comp_ring.next2proc;
- buf[17] = adapter->rx_queue.comp_ring.gen;
+ buf[16] = adapter->rx_queue[i].comp_ring.next2proc;
+ buf[17] = adapter->rx_queue[i].comp_ring.gen;
buf[18] = 0;
buf[19] = 0;
}
@@ -435,8 +437,10 @@ vmxnet3_get_ringparam(struct net_device *netdev,
param->rx_mini_max_pending = 0;
param->rx_jumbo_max_pending = 0;
- param->rx_pending = adapter->rx_queue.rx_ring[0].size;
- param->tx_pending = adapter->tx_queue.tx_ring.size;
+ param->rx_pending = adapter->rx_queue[0].rx_ring[0].size *
+ adapter->num_rx_queues;
+ param->tx_pending = adapter->tx_queue[0].tx_ring.size *
+ adapter->num_tx_queues;
param->rx_mini_pending = 0;
param->rx_jumbo_pending = 0;
}
@@ -480,8 +484,8 @@ vmxnet3_set_ringparam(struct net_device *netdev,
sz) != 0)
return -EINVAL;
- if (new_tx_ring_size == adapter->tx_queue.tx_ring.size &&
- new_rx_ring_size == adapter->rx_queue.rx_ring[0].size) {
+ if (new_tx_ring_size == adapter->tx_queue[0].tx_ring.size &&
+ new_rx_ring_size == adapter->rx_queue[0].rx_ring[0].size) {
return 0;
}
@@ -498,11 +502,12 @@ vmxnet3_set_ringparam(struct net_device *netdev,
/* recreate the rx queue and the tx queue based on the
* new sizes */
- vmxnet3_tq_destroy(&adapter->tx_queue, adapter);
- vmxnet3_rq_destroy(&adapter->rx_queue, adapter);
+ vmxnet3_tq_destroy_all(adapter);
+ vmxnet3_rq_destroy_all(adapter);
err = vmxnet3_create_queues(adapter, new_tx_ring_size,
new_rx_ring_size, VMXNET3_DEF_RX_RING_SIZE);
+
if (err) {
/* failed, most likely because of OOM, try default
* size */
@@ -535,6 +540,59 @@ out:
}
+static int
+vmxnet3_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *info,
+ void *rules)
+{
+ struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+ switch (info->cmd) {
+ case ETHTOOL_GRXRINGS:
+ info->data = adapter->num_rx_queues;
+ return 0;
+ }
+ return -EOPNOTSUPP;
+}
+
+
+static int
+vmxnet3_get_rss_indir(struct net_device *netdev,
+ struct ethtool_rxfh_indir *p)
+{
+ struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+ struct UPT1_RSSConf *rssConf = adapter->rss_conf;
+ unsigned int n = min_t(unsigned int, p->size, rssConf->indTableSize);
+
+ p->size = rssConf->indTableSize;
+ while (n--)
+ p->ring_index[n] = rssConf->indTable[n];
+ return 0;
+
+}
+
+static int
+vmxnet3_set_rss_indir(struct net_device *netdev,
+ const struct ethtool_rxfh_indir *p)
+{
+ unsigned int i;
+ struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+ struct UPT1_RSSConf *rssConf = adapter->rss_conf;
+
+ if (p->size != rssConf->indTableSize)
+ return -EINVAL;
+ for (i = 0; i < rssConf->indTableSize; i++) {
+ if (p->ring_index[i] >= 0 && p->ring_index[i] <
+ adapter->num_rx_queues)
+ rssConf->indTable[i] = p->ring_index[i];
+ else
+ rssConf->indTable[i] = i % adapter->num_rx_queues;
+ }
+ VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+ VMXNET3_CMD_UPDATE_RSSIDT);
+
+ return 0;
+
+}
+
static struct ethtool_ops vmxnet3_ethtool_ops = {
.get_settings = vmxnet3_get_settings,
.get_drvinfo = vmxnet3_get_drvinfo,
@@ -558,6 +616,9 @@ static struct ethtool_ops vmxnet3_ethtool_ops = {
.get_ethtool_stats = vmxnet3_get_ethtool_stats,
.get_ringparam = vmxnet3_get_ringparam,
.set_ringparam = vmxnet3_set_ringparam,
+ .get_rxnfc = vmxnet3_get_rxnfc,
+ .get_rxfh_indir = vmxnet3_get_rss_indir,
+ .set_rxfh_indir = vmxnet3_set_rss_indir,
};
void vmxnet3_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index edf2288..7fadeed 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -68,11 +68,15 @@
/*
* Version numbers
*/
-#define VMXNET3_DRIVER_VERSION_STRING "1.0.14.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING "1.0.16.0-k"
/* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */
-#define VMXNET3_DRIVER_VERSION_NUM 0x01000E00
+#define VMXNET3_DRIVER_VERSION_NUM 0x01001000
+#if defined(CONFIG_PCI_MSI)
+ /* RSS only makes sense if MSI-X is supported. */
+ #define VMXNET3_RSS
+#endif
/*
* Capabilities
@@ -218,16 +222,19 @@ struct vmxnet3_tx_ctx {
};
struct vmxnet3_tx_queue {
+ char name[IFNAMSIZ+8]; /* To identify interrupt */
+ struct vmxnet3_adapter *adapter;
spinlock_t tx_lock;
struct vmxnet3_cmd_ring tx_ring;
- struct vmxnet3_tx_buf_info *buf_info;
+ struct vmxnet3_tx_buf_info *buf_info;
struct vmxnet3_tx_data_ring data_ring;
struct vmxnet3_comp_ring comp_ring;
- struct Vmxnet3_TxQueueCtrl *shared;
+ struct Vmxnet3_TxQueueCtrl *shared;
struct vmxnet3_tq_driver_stats stats;
bool stopped;
int num_stop; /* # of times the queue is
* stopped */
+ int qid;
} __attribute__((__aligned__(SMP_CACHE_BYTES)));
enum vmxnet3_rx_buf_type {
@@ -259,6 +266,9 @@ struct vmxnet3_rq_driver_stats {
};
struct vmxnet3_rx_queue {
+ char name[IFNAMSIZ + 8]; /* To identify interrupt */
+ struct vmxnet3_adapter *adapter;
+ struct napi_struct napi;
struct vmxnet3_cmd_ring rx_ring[2];
struct vmxnet3_comp_ring comp_ring;
struct vmxnet3_rx_ctx rx_ctx;
@@ -271,7 +281,16 @@ struct vmxnet3_rx_queue {
struct vmxnet3_rq_driver_stats stats;
} __attribute__((__aligned__(SMP_CACHE_BYTES)));
-#define VMXNET3_LINUX_MAX_MSIX_VECT 1
+#define VMXNET3_DEVICE_MAX_TX_QUEUES 8
+#define VMXNET3_DEVICE_MAX_RX_QUEUES 8 /* Keep this value as a power of 2 */
+
+/* Should be less than UPT1_RSS_MAX_IND_TABLE_SIZE */
+#define VMXNET3_RSS_IND_TABLE_SIZE (VMXNET3_DEVICE_MAX_RX_QUEUES * 4)
+
+#define VMXNET3_LINUX_MAX_MSIX_VECT (VMXNET3_DEVICE_MAX_TX_QUEUES + \
+ VMXNET3_DEVICE_MAX_RX_QUEUES + 1)
+#define VMXNET3_LINUX_MIN_MSIX_VECT 3 /* 1 for each : tx, rx and event */
+
struct vmxnet3_intr {
enum vmxnet3_intr_mask_mode mask_mode;
@@ -279,27 +298,32 @@ struct vmxnet3_intr {
u8 num_intrs; /* # of intr vectors */
u8 event_intr_idx; /* idx of the intr vector for event */
u8 mod_levels[VMXNET3_LINUX_MAX_MSIX_VECT]; /* moderation level */
+ char event_msi_vector_name[IFNAMSIZ+11];
#ifdef CONFIG_PCI_MSI
struct msix_entry msix_entries[VMXNET3_LINUX_MAX_MSIX_VECT];
#endif
};
+/* Interrupt sharing schemes, share_intr */
+#define VMXNET3_INTR_BUDDYSHARE 0 /* Corresponding tx,rx queues share irq */
+#define VMXNET3_INTR_TXSHARE 1 /* All tx queues share one irq */
+#define VMXNET3_INTR_DONTSHARE 2 /* each queue has its own irq */
+
+
#define VMXNET3_STATE_BIT_RESETTING 0
#define VMXNET3_STATE_BIT_QUIESCED 1
struct vmxnet3_adapter {
- struct vmxnet3_tx_queue tx_queue;
- struct vmxnet3_rx_queue rx_queue;
- struct napi_struct napi;
- struct vlan_group *vlan_grp;
-
- struct vmxnet3_intr intr;
-
- struct Vmxnet3_DriverShared *shared;
- struct Vmxnet3_PMConf *pm_conf;
- struct Vmxnet3_TxQueueDesc *tqd_start; /* first tx queue desc */
- struct Vmxnet3_RxQueueDesc *rqd_start; /* first rx queue desc */
- struct net_device *netdev;
- struct pci_dev *pdev;
+ struct vmxnet3_tx_queue tx_queue[VMXNET3_DEVICE_MAX_TX_QUEUES];
+ struct vmxnet3_rx_queue rx_queue[VMXNET3_DEVICE_MAX_RX_QUEUES];
+ struct vlan_group *vlan_grp;
+ struct vmxnet3_intr intr;
+ struct Vmxnet3_DriverShared *shared;
+ struct Vmxnet3_PMConf *pm_conf;
+ struct Vmxnet3_TxQueueDesc *tqd_start; /* all tx queue desc */
+ struct Vmxnet3_RxQueueDesc *rqd_start; /* all rx queue desc */
+ struct net_device *netdev;
+ struct net_device_stats net_stats;
+ struct pci_dev *pdev;
u8 __iomem *hw_addr0; /* for BAR 0 */
u8 __iomem *hw_addr1; /* for BAR 1 */
@@ -308,6 +332,12 @@ struct vmxnet3_adapter {
bool rxcsum;
bool lro;
bool jumbo_frame;
+#ifdef VMXNET3_RSS
+ struct UPT1_RSSConf *rss_conf;
+ bool rss;
+#endif
+ u32 num_rx_queues;
+ u32 num_tx_queues;
/* rx buffer related */
unsigned skb_buf_size;
@@ -327,6 +357,7 @@ struct vmxnet3_adapter {
unsigned long state; /* VMXNET3_STATE_BIT_xxx */
int dev_number;
+ int share_intr;
};
#define VMXNET3_WRITE_BAR0_REG(adapter, reg, val) \
@@ -366,12 +397,10 @@ void
vmxnet3_reset_dev(struct vmxnet3_adapter *adapter);
void
-vmxnet3_tq_destroy(struct vmxnet3_tx_queue *tq,
- struct vmxnet3_adapter *adapter);
+vmxnet3_tq_destroy_all(struct vmxnet3_adapter *adapter);
void
-vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq,
- struct vmxnet3_adapter *adapter);
+vmxnet3_rq_destroy_all(struct vmxnet3_adapter *adapter);
int
vmxnet3_create_queues(struct vmxnet3_adapter *adapter,
^ permalink raw reply related
* [net-next-2.6 PATCH] net: add priority field to pktgen
From: John Fastabend @ 2010-11-17 5:12 UTC (permalink / raw)
To: davem; +Cc: john.r.fastabend, netdev
Add option to set skb priority to pktgen. Useful for testing
QOS features. Also by running pktgen on the vlan device the
qdisc on the real device can be tested.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
---
net/core/pktgen.c | 20 ++++++++++++++++++++
1 files changed, 20 insertions(+), 0 deletions(-)
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 33bc382..52fc1e0 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -378,6 +378,7 @@ struct pktgen_dev {
u16 queue_map_min;
u16 queue_map_max;
+ __u32 skb_priority; /* skb priority field */
int node; /* Memory node */
#ifdef CONFIG_XFRM
@@ -547,6 +548,10 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
pkt_dev->queue_map_min,
pkt_dev->queue_map_max);
+ if (pkt_dev->skb_priority)
+ seq_printf(seq, " skb_priority: %u\n",
+ pkt_dev->skb_priority);
+
if (pkt_dev->flags & F_IPV6) {
char b1[128], b2[128], b3[128];
fmt_ip6(b1, pkt_dev->in6_saddr.s6_addr);
@@ -1711,6 +1716,18 @@ static ssize_t pktgen_if_write(struct file *file,
return count;
}
+ if (!strcmp(name, "skb_priority")) {
+ len = num_arg(&user_buffer[i], 9, &value);
+ if (len < 0)
+ return len;
+
+ i += len;
+ pkt_dev->skb_priority = value;
+ sprintf(pg_result, "OK: skb_priority=%i",
+ pkt_dev->skb_priority);
+ return count;
+ }
+
sprintf(pkt_dev->result, "No such parameter \"%s\"", name);
return -EINVAL;
}
@@ -2671,6 +2688,8 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
skb->transport_header = skb->network_header + sizeof(struct iphdr);
skb_put(skb, sizeof(struct iphdr) + sizeof(struct udphdr));
skb_set_queue_mapping(skb, queue_map);
+ skb->priority = pkt_dev->skb_priority;
+
iph = ip_hdr(skb);
udph = udp_hdr(skb);
@@ -3016,6 +3035,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
skb->transport_header = skb->network_header + sizeof(struct ipv6hdr);
skb_put(skb, sizeof(struct ipv6hdr) + sizeof(struct udphdr));
skb_set_queue_mapping(skb, queue_map);
+ skb->priority = pkt_dev->skb_priority;
iph = ipv6_hdr(skb);
udph = udp_hdr(skb);
^ permalink raw reply related
* [RFC PATCH v1 1/2] net: implement mechanism for HW based QOS
From: John Fastabend @ 2010-11-17 5:15 UTC (permalink / raw)
To: netdev; +Cc: john.r.fastabend, nhorman, davem
This patch provides a mechanism for lower layer devices to
steer traffic using skb->priority to tx queues. This allows
for hardware based QOS schemes to use the default qdisc without
incurring the penalties related to global state and the qdisc
lock. While reliably receiving skbs on the correct tx ring
to avoid head of line blocking resulting from shuffling in
the LLD. Finally, all the goodness from txq caching and xps/rps
can still be leveraged.
Many drivers and hardware exist with the ability to implement
QOS schemes in the hardware but currently these drivers tend
to rely on firmware to reroute specific traffic, a driver
specific select_queue or the queue_mapping action in the
qdisc.
None of these solutions are ideal or generic so we end up
with driver specific solutions that one-off traffic types
for example FCoE traffic is steered in ixgbe with the
queue_select routine. By using select_queue for this drivers
need to be updated for each and every traffic type and we
loose the goodness of much of the upstream work. For example
txq caching.
Firmware solutions are inherently inflexible. And finally if
admins are expected to build a qdisc and filter rules to steer
traffic this requires knowledge of how the hardware is currently
configured. The number of tx queues and the queue offsets may
change depending on resources. Also this approach incurs all the
overhead of a qdisc with filters.
With this mechanism users can set skb priority using expected
methods either socket options or the stack can set this directly.
Then the skb will be steered to the correct tx queues aligned
with hardware QOS traffic classes. In the normal case with a
single traffic class and all queues in this class every thing
works as is until the LLD enables multiple tcs.
To steer the skb we mask out the lower 8 bits of the priority
and allow the hardware to configure upto 15 distinct classes
of traffic. This is expected to be sufficient for most applications
at any rate it is more then the 8021Q spec designates and is
equal to the number of prio bands currently implemented in
the default qdisc.
This in conjunction with a userspace application such as
lldpad can be used to implement 8021Q transmission selection
algorithms one of these algorithms being the extended transmission
selection algorithm currently being used for DCB.
If this approach seems reasonable I'll go ahead and finish
this up. The priority to tc mapping should probably be exposed
to userspace either through sysfs or rtnetlink. Any thoughts?
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
---
include/linux/netdevice.h | 47 +++++++++++++++++++++++++++++++++++++++++++++
net/core/dev.c | 43 ++++++++++++++++++++++++++++++++++++++++-
2 files changed, 89 insertions(+), 1 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b45c1b8..8a2adeb 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1092,6 +1092,12 @@ struct net_device {
/* Data Center Bridging netlink ops */
const struct dcbnl_rtnl_ops *dcbnl_ops;
#endif
+ u8 max_tcs;
+ u8 num_tcs;
+ unsigned int *_tc_txqcount;
+ unsigned int *_tc_txqoffset;
+ u64 prio_tc_map;
+
#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
/* max exchange id for FCoE LRO by ddp */
@@ -1108,6 +1114,44 @@ struct net_device {
#define NETDEV_ALIGN 32
static inline
+int netdev_get_prio_tc_map(const struct net_device *dev, u32 prio)
+{
+ return (dev->prio_tc_map >> (4 * (prio & 0xF))) & 0xF;
+}
+
+static inline
+void netdev_set_prio_tc_map(struct net_device *dev, u8 prio, u8 tc)
+{
+ u64 mask = ~(-1 & (0xF << (4 * prio)));
+ /* Zero the 4 bit prio map and set traffic class */
+ dev->prio_tc_map &= mask;
+ dev->prio_tc_map |= tc << (4 * prio);
+}
+
+static inline
+void netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset)
+{
+ dev->_tc_txqcount[tc] = count;
+ dev->_tc_txqoffset[tc] = offset;
+}
+
+static inline
+int netdev_set_num_tc(struct net_device *dev, u8 num_tc)
+{
+ if (num_tc > dev->max_tcs)
+ return -EINVAL;
+
+ dev->num_tcs = num_tc;
+ return 0;
+}
+
+static inline
+u8 netdev_get_num_tc(struct net_device *dev)
+{
+ return dev->num_tcs;
+}
+
+static inline
struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev,
unsigned int index)
{
@@ -1332,6 +1376,9 @@ static inline void unregister_netdevice(struct net_device *dev)
unregister_netdevice_queue(dev, NULL);
}
+extern int netdev_alloc_max_tcs(struct net_device *dev, u8 tcs);
+extern void netdev_free_tcs(struct net_device *dev);
+
extern int netdev_refcnt_read(const struct net_device *dev);
extern void free_netdev(struct net_device *dev);
extern void synchronize_net(void);
diff --git a/net/core/dev.c b/net/core/dev.c
index 4a587b3..4565afc 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2111,6 +2111,8 @@ static u32 hashrnd __read_mostly;
u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb)
{
u32 hash;
+ u16 qoffset = 0;
+ u16 qcount = dev->real_num_tx_queues;
if (skb_rx_queue_recorded(skb)) {
hash = skb_get_rx_queue(skb);
@@ -2119,13 +2121,20 @@ u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb)
return hash;
}
+ if (dev->num_tcs) {
+ u8 tc;
+ tc = netdev_get_prio_tc_map(dev, skb->priority);
+ qoffset = dev->_tc_txqoffset[tc];
+ qcount = dev->_tc_txqcount[tc];
+ }
+
if (skb->sk && skb->sk->sk_hash)
hash = skb->sk->sk_hash;
else
hash = (__force u16) skb->protocol ^ skb->rxhash;
hash = jhash_1word(hash, hashrnd);
- return (u16) (((u64) hash * dev->real_num_tx_queues) >> 32);
+ return (u16) ((((u64) hash * qcount)) >> 32) + qoffset;
}
EXPORT_SYMBOL(skb_tx_hash);
@@ -5037,6 +5046,37 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev,
}
EXPORT_SYMBOL(netif_stacked_transfer_operstate);
+int netdev_alloc_max_tcs(struct net_device *dev, u8 tcs)
+{
+ unsigned int *count, *offset;
+ count = kcalloc(tcs, sizeof(unsigned int), GFP_KERNEL);
+ if (!count)
+ return -ENOMEM;
+ offset = kcalloc(tcs, sizeof(unsigned int), GFP_KERNEL);
+ if (!offset) {
+ kfree(count);
+ return -ENOMEM;
+ }
+
+ dev->_tc_txqcount = count;
+ dev->_tc_txqoffset = offset;
+ dev->max_tcs = tcs;
+ return tcs;
+}
+EXPORT_SYMBOL(netdev_alloc_max_tcs);
+
+void netdev_free_tcs(struct net_device *dev)
+{
+ dev->max_tcs = 0;
+ dev->num_tcs = 0;
+ dev->prio_tc_map = 0;
+ kfree(dev->_tc_txqcount);
+ kfree(dev->_tc_txqoffset);
+ dev->_tc_txqcount = NULL;
+ dev->_tc_txqoffset = NULL;
+}
+EXPORT_SYMBOL(netdev_free_tcs);
+
static int netif_alloc_rx_queues(struct net_device *dev)
{
#ifdef CONFIG_RPS
@@ -5641,6 +5681,7 @@ void free_netdev(struct net_device *dev)
#ifdef CONFIG_RPS
kfree(dev->_rx);
#endif
+ netdev_free_tcs(dev);
kfree(rcu_dereference_raw(dev->ingress_queue));
^ permalink raw reply related
* [RFC PATCH v1 2/2] ixgbe: add multiple txqs per tc
From: John Fastabend @ 2010-11-17 5:15 UTC (permalink / raw)
To: netdev; +Cc: john.r.fastabend, nhorman, davem
In-Reply-To: <20101117051544.19800.97654.stgit@jf-dev1-dcblab>
This is sample code to illustrate the usage model for hardware
QOS offloading. It needs some polishing, but should be good
enough to illustrate how the API can be used.
Currently, DCB only enables a single queue per tc. Due to
complications with how to map tc filter rules to traffic classes
when multiple queues are enabled. And previously there was no
mechanism to map flows to multiple queues by priority.
Using the above mentioned API we allocate multiple queues per
tc and configure the stack to hash across these queues. The
hardware then offloads the DCB extended transmission selection
algorithm. Sockets can set the priority using the SO_PRIORITY
socket option.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
---
drivers/net/ixgbe/ixgbe.h | 5 -
drivers/net/ixgbe/ixgbe_dcb_nl.c | 3
drivers/net/ixgbe/ixgbe_main.c | 254 +++++++++++++++-----------------------
3 files changed, 105 insertions(+), 157 deletions(-)
diff --git a/drivers/net/ixgbe/ixgbe.h b/drivers/net/ixgbe/ixgbe.h
index ed8703c..2ac7bf7 100644
--- a/drivers/net/ixgbe/ixgbe.h
+++ b/drivers/net/ixgbe/ixgbe.h
@@ -207,11 +207,12 @@ enum ixgbe_ring_f_enum {
RING_F_ARRAY_SIZE /* must be last in enum set */
};
-#define IXGBE_MAX_DCB_INDICES 8
+#define IXGBE_MAX_DCB_INDICES 64
#define IXGBE_MAX_RSS_INDICES 16
#define IXGBE_MAX_VMDQ_INDICES 64
#define IXGBE_MAX_FDIR_INDICES 64
-#ifdef IXGBE_FCOE
+
+#if defined(IXGBE_FCOE)
#define IXGBE_MAX_FCOE_INDICES 8
#define MAX_RX_QUEUES (IXGBE_MAX_FDIR_INDICES + IXGBE_MAX_FCOE_INDICES)
#define MAX_TX_QUEUES (IXGBE_MAX_FDIR_INDICES + IXGBE_MAX_FCOE_INDICES)
diff --git a/drivers/net/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ixgbe/ixgbe_dcb_nl.c
index b53b465..7c85f3c 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ixgbe/ixgbe_dcb_nl.c
@@ -140,6 +140,7 @@ static u8 ixgbe_dcbnl_set_state(struct net_device *netdev, u8 state)
adapter->flags &= ~IXGBE_FLAG_FDIR_PERFECT_CAPABLE;
}
adapter->flags |= IXGBE_FLAG_DCB_ENABLED;
+
ixgbe_init_interrupt_scheme(adapter);
if (netif_running(netdev))
netdev->netdev_ops->ndo_open(netdev);
@@ -342,7 +343,7 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
return DCB_NO_HW_CHG;
ret = ixgbe_copy_dcb_cfg(&adapter->temp_dcb_cfg, &adapter->dcb_cfg,
- adapter->ring_feature[RING_F_DCB].indices);
+ netdev->num_tcs);
if (ret)
return DCB_NO_HW_CHG;
diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index fbad4d8..2c0cfb8 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -644,7 +644,7 @@ static inline bool ixgbe_tx_xon_state(struct ixgbe_adapter *adapter,
if (adapter->dcb_cfg.pfc_mode_enable) {
int tc;
int reg_idx = tx_ring->reg_idx;
- int dcb_i = adapter->ring_feature[RING_F_DCB].indices;
+ int dcb_i = MAX_TRAFFIC_CLASS;
switch (adapter->hw.mac.type) {
case ixgbe_mac_82598EB:
@@ -3978,14 +3978,64 @@ static void ixgbe_reset_task(struct work_struct *work)
}
#ifdef CONFIG_IXGBE_DCB
+/*
+ * Queue to TC Mapping Layout 82599:
+ *
+ * Tx TC0 starts at: descriptor queue 0
+ * Tx TC1 starts at: descriptor queue 32
+ * Tx TC2 starts at: descriptor queue 64
+ * Tx TC3 starts at: descriptor queue 80
+ * Tx TC4 starts at: descriptor queue 96
+ * Tx TC5 starts at: descriptor queue 104
+ * Tx TC6 starts at: descriptor queue 112
+ * Tx TC7 starts at: descriptor queue 120
+ *
+ * Rx TC0-TC7 are offset by 16 queues each
+ *
+ * Queue to TC Mapping Layout 82598:
+ *
+ * TX TC0-TC7 are offset by 4 queues each
+ * RX TC0-TC7 are offset by 4 queues each
+ */
+static unsigned int Q_TC8_82599[] = {0, 32, 64, 80, 96, 104, 112, 120, 128};
+static unsigned int Q_TC4_82599[] = {0, 64, 96, 104, 128};
+static unsigned int Q_TC8_82598[] = {0, 4, 8, 12, 16, 20, 24, 28, 32};
+
+#define MAX_Q_PER_TC 4
+
static inline bool ixgbe_set_dcb_queues(struct ixgbe_adapter *adapter)
{
bool ret = false;
struct ixgbe_ring_feature *f = &adapter->ring_feature[RING_F_DCB];
+ int num_tcs;
+ unsigned int *__tc;
+ int i, q;
if (!(adapter->flags & IXGBE_FLAG_DCB_ENABLED))
return ret;
+ if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
+ num_tcs = 4;
+ __tc = Q_TC8_82598;
+ } else {
+ num_tcs = 8;
+ if (num_tcs == 8)
+ __tc = Q_TC8_82599;
+ else
+ __tc = Q_TC4_82599;
+ }
+
+ netdev_set_num_tc(adapter->netdev, num_tcs);
+
+ f->indices = 0;
+ for (i = 0; i < num_tcs; i++) {
+ q = min((unsigned int)num_online_cpus(), __tc[i+1] - __tc[i]);
+ q = min(q, MAX_Q_PER_TC);
+ netdev_set_prio_tc_map(adapter->netdev, i, i);
+ netdev_set_tc_queue(adapter->netdev, i, q, f->indices);
+ f->indices += q;
+ }
+
f->mask = 0x7 << 3;
adapter->num_rx_queues = f->indices;
adapter->num_tx_queues = f->indices;
@@ -4072,12 +4122,7 @@ static inline bool ixgbe_set_fcoe_queues(struct ixgbe_adapter *adapter)
if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) {
adapter->num_rx_queues = 1;
adapter->num_tx_queues = 1;
-#ifdef CONFIG_IXGBE_DCB
- if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) {
- e_info(probe, "FCoE enabled with DCB\n");
- ixgbe_set_dcb_queues(adapter);
- }
-#endif
+
if (adapter->flags & IXGBE_FLAG_RSS_ENABLED) {
e_info(probe, "FCoE enabled with RSS\n");
if ((adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) ||
@@ -4133,16 +4178,16 @@ static int ixgbe_set_num_queues(struct ixgbe_adapter *adapter)
if (ixgbe_set_sriov_queues(adapter))
goto done;
+#ifdef CONFIG_IXGBE_DCB
+ if (ixgbe_set_dcb_queues(adapter))
+ goto done;
+#endif
+
#ifdef IXGBE_FCOE
if (ixgbe_set_fcoe_queues(adapter))
goto done;
#endif /* IXGBE_FCOE */
-#ifdef CONFIG_IXGBE_DCB
- if (ixgbe_set_dcb_queues(adapter))
- goto done;
-
-#endif
if (ixgbe_set_fdir_queues(adapter))
goto done;
@@ -4246,73 +4291,35 @@ static inline bool ixgbe_cache_ring_rss(struct ixgbe_adapter *adapter)
**/
static inline bool ixgbe_cache_ring_dcb(struct ixgbe_adapter *adapter)
{
- int i;
+ struct net_device *dev = adapter->netdev;
+ int i, j, rx_off, qcount, index;
bool ret = false;
- int dcb_i = adapter->ring_feature[RING_F_DCB].indices;
+ u8 num_tcs = netdev_get_num_tc(dev);
+ unsigned int *__tc;
if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) {
if (adapter->hw.mac.type == ixgbe_mac_82598EB) {
- /* the number of queues is assumed to be symmetric */
- for (i = 0; i < dcb_i; i++) {
- adapter->rx_ring[i]->reg_idx = i << 3;
- adapter->tx_ring[i]->reg_idx = i << 2;
+ rx_off = 2;
+ __tc = Q_TC8_82598;
+ } else {
+ if (num_tcs == 8) {
+ rx_off = 4;
+ __tc = Q_TC8_82599;
+ } else if (num_tcs == 4) {
+ rx_off = 5;
+ __tc = Q_TC4_82599;
}
- ret = true;
- } else if (adapter->hw.mac.type == ixgbe_mac_82599EB) {
- if (dcb_i == 8) {
- /*
- * Tx TC0 starts at: descriptor queue 0
- * Tx TC1 starts at: descriptor queue 32
- * Tx TC2 starts at: descriptor queue 64
- * Tx TC3 starts at: descriptor queue 80
- * Tx TC4 starts at: descriptor queue 96
- * Tx TC5 starts at: descriptor queue 104
- * Tx TC6 starts at: descriptor queue 112
- * Tx TC7 starts at: descriptor queue 120
- *
- * Rx TC0-TC7 are offset by 16 queues each
- */
- for (i = 0; i < 3; i++) {
- adapter->tx_ring[i]->reg_idx = i << 5;
- adapter->rx_ring[i]->reg_idx = i << 4;
- }
- for ( ; i < 5; i++) {
- adapter->tx_ring[i]->reg_idx =
- ((i + 2) << 4);
- adapter->rx_ring[i]->reg_idx = i << 4;
- }
- for ( ; i < dcb_i; i++) {
- adapter->tx_ring[i]->reg_idx =
- ((i + 8) << 3);
- adapter->rx_ring[i]->reg_idx = i << 4;
- }
+ }
- ret = true;
- } else if (dcb_i == 4) {
- /*
- * Tx TC0 starts at: descriptor queue 0
- * Tx TC1 starts at: descriptor queue 64
- * Tx TC2 starts at: descriptor queue 96
- * Tx TC3 starts at: descriptor queue 112
- *
- * Rx TC0-TC3 are offset by 32 queues each
- */
- adapter->tx_ring[0]->reg_idx = 0;
- adapter->tx_ring[1]->reg_idx = 64;
- adapter->tx_ring[2]->reg_idx = 96;
- adapter->tx_ring[3]->reg_idx = 112;
- for (i = 0 ; i < dcb_i; i++)
- adapter->rx_ring[i]->reg_idx = i << 5;
-
- ret = true;
- } else {
- ret = false;
+ for (i = 0, index = 0; i < num_tcs; i++) {
+ qcount = dev->_tc_txqcount[i];
+ for (j = 0; j < qcount; j++, index++) {
+ adapter->tx_ring[index]->reg_idx = __tc[i] + j;
+ adapter->rx_ring[index]->reg_idx =
+ (i << (rx_off + (num_tcs == 4))) + j;
}
- } else {
- ret = false;
}
- } else {
- ret = false;
+ ret = true;
}
return ret;
@@ -4359,33 +4366,6 @@ static inline bool ixgbe_cache_ring_fcoe(struct ixgbe_adapter *adapter)
struct ixgbe_ring_feature *f = &adapter->ring_feature[RING_F_FCOE];
if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) {
-#ifdef CONFIG_IXGBE_DCB
- if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) {
- struct ixgbe_fcoe *fcoe = &adapter->fcoe;
-
- ixgbe_cache_ring_dcb(adapter);
- /* find out queues in TC for FCoE */
- fcoe_rx_i = adapter->rx_ring[fcoe->tc]->reg_idx + 1;
- fcoe_tx_i = adapter->tx_ring[fcoe->tc]->reg_idx + 1;
- /*
- * In 82599, the number of Tx queues for each traffic
- * class for both 8-TC and 4-TC modes are:
- * TCs : TC0 TC1 TC2 TC3 TC4 TC5 TC6 TC7
- * 8 TCs: 32 32 16 16 8 8 8 8
- * 4 TCs: 64 64 32 32
- * We have max 8 queues for FCoE, where 8 the is
- * FCoE redirection table size. If TC for FCoE is
- * less than or equal to TC3, we have enough queues
- * to add max of 8 queues for FCoE, so we start FCoE
- * tx descriptor from the next one, i.e., reg_idx + 1.
- * If TC for FCoE is above TC3, implying 8 TC mode,
- * and we need 8 for FCoE, we have to take all queues
- * in that traffic class for FCoE.
- */
- if ((f->indices == IXGBE_FCRETA_SIZE) && (fcoe->tc > 3))
- fcoe_tx_i--;
- }
-#endif /* CONFIG_IXGBE_DCB */
if (adapter->flags & IXGBE_FLAG_RSS_ENABLED) {
if ((adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) ||
(adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE))
@@ -4443,17 +4423,15 @@ static void ixgbe_cache_ring_register(struct ixgbe_adapter *adapter)
if (ixgbe_cache_ring_sriov(adapter))
return;
-
+#ifdef CONFIG_IXGBE_DCB
+ if (ixgbe_cache_ring_dcb(adapter))
+ return;
+#endif /* IXGBE_DCB */
#ifdef IXGBE_FCOE
if (ixgbe_cache_ring_fcoe(adapter))
return;
#endif /* IXGBE_FCOE */
-#ifdef CONFIG_IXGBE_DCB
- if (ixgbe_cache_ring_dcb(adapter))
- return;
-
-#endif
if (ixgbe_cache_ring_fdir(adapter))
return;
@@ -4910,7 +4888,7 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter)
adapter->dcb_cfg.round_robin_enable = false;
adapter->dcb_set_bitmap = 0x00;
ixgbe_copy_dcb_cfg(&adapter->dcb_cfg, &adapter->temp_dcb_cfg,
- adapter->ring_feature[RING_F_DCB].indices);
+ MAX_TRAFFIC_CLASS);
#endif
@@ -6253,25 +6231,6 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb)
{
struct ixgbe_adapter *adapter = netdev_priv(dev);
int txq = smp_processor_id();
-#ifdef IXGBE_FCOE
- __be16 protocol;
-
- protocol = vlan_get_protocol(skb);
-
- if ((protocol == htons(ETH_P_FCOE)) ||
- (protocol == htons(ETH_P_FIP))) {
- if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) {
- txq &= (adapter->ring_feature[RING_F_FCOE].indices - 1);
- txq += adapter->ring_feature[RING_F_FCOE].mask;
- return txq;
-#ifdef CONFIG_IXGBE_DCB
- } else if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) {
- txq = adapter->fcoe.up;
- return txq;
-#endif
- }
- }
-#endif
if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) {
while (unlikely(txq >= dev->real_num_tx_queues))
@@ -6279,14 +6238,20 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb)
return txq;
}
- if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) {
- if (skb->priority == TC_PRIO_CONTROL)
- txq = adapter->ring_feature[RING_F_DCB].indices-1;
- else
- txq = (skb->vlan_tci & IXGBE_TX_FLAGS_VLAN_PRIO_MASK)
- >> 13;
+#ifdef IXGBE_FCOE
+ /*
+ * If DCB is not enabled to assign FCoE a priority mapping
+ * we need to steer the skb to FCoE enabled tx rings.
+ */
+ if ((adapter->flags & IXGBE_FLAG_FCOE_ENABLED) &&
+ !(adapter->flags & IXGBE_FLAG_DCB_ENABLED) &&
+ ((skb->protocol == htons(ETH_P_FCOE)) ||
+ (skb->protocol == htons(ETH_P_FIP)))) {
+ txq &= (adapter->ring_feature[RING_F_FCOE].indices - 1);
+ txq += adapter->ring_feature[RING_F_FCOE].mask;
return txq;
}
+#endif
return skb_tx_hash(dev, skb);
}
@@ -6308,33 +6273,12 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, struct net_device *netdev
if (vlan_tx_tag_present(skb)) {
tx_flags |= vlan_tx_tag_get(skb);
- if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) {
- tx_flags &= ~IXGBE_TX_FLAGS_VLAN_PRIO_MASK;
- tx_flags |= ((skb->queue_mapping & 0x7) << 13);
- }
- tx_flags <<= IXGBE_TX_FLAGS_VLAN_SHIFT;
- tx_flags |= IXGBE_TX_FLAGS_VLAN;
- } else if (adapter->flags & IXGBE_FLAG_DCB_ENABLED &&
- skb->priority != TC_PRIO_CONTROL) {
- tx_flags |= ((skb->queue_mapping & 0x7) << 13);
tx_flags <<= IXGBE_TX_FLAGS_VLAN_SHIFT;
tx_flags |= IXGBE_TX_FLAGS_VLAN;
}
#ifdef IXGBE_FCOE
- /* for FCoE with DCB, we force the priority to what
- * was specified by the switch */
- if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED &&
- (protocol == htons(ETH_P_FCOE) ||
- protocol == htons(ETH_P_FIP))) {
-#ifdef CONFIG_IXGBE_DCB
- if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) {
- tx_flags &= ~(IXGBE_TX_FLAGS_VLAN_PRIO_MASK
- << IXGBE_TX_FLAGS_VLAN_SHIFT);
- tx_flags |= ((adapter->fcoe.up << 13)
- << IXGBE_TX_FLAGS_VLAN_SHIFT);
- }
-#endif
+ if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) {
/* flag for FCoE offloads */
if (protocol == htons(ETH_P_FCOE))
tx_flags |= IXGBE_TX_FLAGS_FCOE;
@@ -6744,9 +6688,9 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev,
indices = min_t(unsigned int, indices, IXGBE_MAX_RSS_INDICES);
else
indices = min_t(unsigned int, indices, IXGBE_MAX_FDIR_INDICES);
-
+#if defined(CONFIG_IXGBE_DCB)
indices = max_t(unsigned int, indices, IXGBE_MAX_DCB_INDICES);
-#ifdef IXGBE_FCOE
+#elif defined(IXGBE_FCOE)
indices += min_t(unsigned int, num_possible_cpus(),
IXGBE_MAX_FCOE_INDICES);
#endif
@@ -6901,6 +6845,7 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev,
#ifdef CONFIG_IXGBE_DCB
netdev->dcbnl_ops = &dcbnl_ops;
+ netdev_alloc_max_tcs(netdev, MAX_TRAFFIC_CLASS);
#endif
#ifdef IXGBE_FCOE
@@ -7043,6 +6988,7 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev,
/* add san mac addr to netdev */
ixgbe_add_sanmac_netdev(netdev);
+
e_dev_info("Intel(R) 10 Gigabit Network Connection\n");
cards_found++;
return 0;
^ permalink raw reply related
* Re: [net-next-2.6 PATCH] net: add priority field to pktgen
From: Eric Dumazet @ 2010-11-17 5:27 UTC (permalink / raw)
To: John Fastabend; +Cc: davem, netdev
In-Reply-To: <20101117051228.19479.8267.stgit@jf-dev1-dcblab>
Le mardi 16 novembre 2010 à 21:12 -0800, John Fastabend a écrit :
> Add option to set skb priority to pktgen. Useful for testing
> QOS features. Also by running pktgen on the vlan device the
> qdisc on the real device can be tested.
>
> Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
> ---
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
^ permalink raw reply
* [net-2.6 PATCH v2] net: zero kobject in rx_queue_release
From: John Fastabend @ 2010-11-17 5:42 UTC (permalink / raw)
To: davem; +Cc: john.r.fastabend, eric.dumazet, therbert, netdev
netif_set_real_num_rx_queues() can decrement and increment
the number of rx queues. For example ixgbe does this as
features and offloads are toggled. Presumably this could
also happen across down/up on most devices if the available
resources changed (cpu offlined).
The kobject needs to be zero'd in this case so that the
state is not preserved across kobject_put()/kobject_init_and_add().
This resolves the following error report.
ixgbe 0000:03:00.0: eth2: NIC Link is Up 10 Gbps, Flow Control: RX/TX
kobject (ffff880324b83210): tried to init an initialized object, something is seriously wrong.
Pid: 1972, comm: lldpad Not tainted 2.6.37-rc18021qaz+ #169
Call Trace:
[<ffffffff8121c940>] kobject_init+0x3a/0x83
[<ffffffff8121cf77>] kobject_init_and_add+0x23/0x57
[<ffffffff8107b800>] ? mark_lock+0x21/0x267
[<ffffffff813c6d11>] net_rx_queue_update_kobjects+0x63/0xc6
[<ffffffff813b5e0e>] netif_set_real_num_rx_queues+0x5f/0x78
[<ffffffffa0261d49>] ixgbe_set_num_queues+0x1c6/0x1ca [ixgbe]
[<ffffffffa0262509>] ixgbe_init_interrupt_scheme+0x1e/0x79c [ixgbe]
[<ffffffffa0274596>] ixgbe_dcbnl_set_state+0x167/0x189 [ixgbe]
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
---
net/core/net-sysfs.c | 10 ++++++++--
1 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index a5ff5a8..7f902ca 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -712,15 +712,21 @@ static void rx_queue_release(struct kobject *kobj)
map = rcu_dereference_raw(queue->rps_map);
- if (map)
+ if (map) {
+ RCU_INIT_POINTER(queue->rps_map, NULL);
call_rcu(&map->rcu, rps_map_release);
+ }
flow_table = rcu_dereference_raw(queue->rps_flow_table);
- if (flow_table)
+ if (flow_table) {
+ RCU_INIT_POINTER(queue->rps_flow_table, NULL);
call_rcu(&flow_table->rcu, rps_dev_flow_table_release);
+ }
if (atomic_dec_and_test(&first->count))
kfree(first);
+ else
+ memset(kobj, 0, sizeof(*kobj));
}
static struct kobj_type rx_queue_ktype = {
^ permalink raw reply related
* Re: [net-2.6 PATCH v2] net: zero kobject in rx_queue_release
From: Eric Dumazet @ 2010-11-17 5:51 UTC (permalink / raw)
To: John Fastabend; +Cc: davem, therbert, netdev
In-Reply-To: <20101117054253.8714.24548.stgit@jf-dev1-dcblab>
Le mardi 16 novembre 2010 à 21:42 -0800, John Fastabend a écrit :
> netif_set_real_num_rx_queues() can decrement and increment
> the number of rx queues. For example ixgbe does this as
> features and offloads are toggled. Presumably this could
> also happen across down/up on most devices if the available
> resources changed (cpu offlined).
>
> The kobject needs to be zero'd in this case so that the
> state is not preserved across kobject_put()/kobject_init_and_add().
>
> This resolves the following error report.
>
> ixgbe 0000:03:00.0: eth2: NIC Link is Up 10 Gbps, Flow Control: RX/TX
> kobject (ffff880324b83210): tried to init an initialized object, something is seriously wrong.
> Pid: 1972, comm: lldpad Not tainted 2.6.37-rc18021qaz+ #169
> Call Trace:
> [<ffffffff8121c940>] kobject_init+0x3a/0x83
> [<ffffffff8121cf77>] kobject_init_and_add+0x23/0x57
> [<ffffffff8107b800>] ? mark_lock+0x21/0x267
> [<ffffffff813c6d11>] net_rx_queue_update_kobjects+0x63/0xc6
> [<ffffffff813b5e0e>] netif_set_real_num_rx_queues+0x5f/0x78
> [<ffffffffa0261d49>] ixgbe_set_num_queues+0x1c6/0x1ca [ixgbe]
> [<ffffffffa0262509>] ixgbe_init_interrupt_scheme+0x1e/0x79c [ixgbe]
> [<ffffffffa0274596>] ixgbe_dcbnl_set_state+0x167/0x189 [ixgbe]
>
> Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
> ---
I am not sure why you resent it, anyway, I ack it
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Thanks
^ permalink raw reply
* Re: [net-2.6 PATCH v2] net: zero kobject in rx_queue_release
From: John Fastabend @ 2010-11-17 6:01 UTC (permalink / raw)
To: Eric Dumazet
Cc: davem@davemloft.net, therbert@google.com, netdev@vger.kernel.org
In-Reply-To: <1289973119.2732.104.camel@edumazet-laptop>
On 11/16/2010 9:51 PM, Eric Dumazet wrote:
> Le mardi 16 novembre 2010 à 21:42 -0800, John Fastabend a écrit :
>> netif_set_real_num_rx_queues() can decrement and increment
>> the number of rx queues. For example ixgbe does this as
>> features and offloads are toggled. Presumably this could
>> also happen across down/up on most devices if the available
>> resources changed (cpu offlined).
>>
>> The kobject needs to be zero'd in this case so that the
>> state is not preserved across kobject_put()/kobject_init_and_add().
>>
>> This resolves the following error report.
>>
>> ixgbe 0000:03:00.0: eth2: NIC Link is Up 10 Gbps, Flow Control: RX/TX
>> kobject (ffff880324b83210): tried to init an initialized object, something is seriously wrong.
>> Pid: 1972, comm: lldpad Not tainted 2.6.37-rc18021qaz+ #169
>> Call Trace:
>> [<ffffffff8121c940>] kobject_init+0x3a/0x83
>> [<ffffffff8121cf77>] kobject_init_and_add+0x23/0x57
>> [<ffffffff8107b800>] ? mark_lock+0x21/0x267
>> [<ffffffff813c6d11>] net_rx_queue_update_kobjects+0x63/0xc6
>> [<ffffffff813b5e0e>] netif_set_real_num_rx_queues+0x5f/0x78
>> [<ffffffffa0261d49>] ixgbe_set_num_queues+0x1c6/0x1ca [ixgbe]
>> [<ffffffffa0262509>] ixgbe_init_interrupt_scheme+0x1e/0x79c [ixgbe]
>> [<ffffffffa0274596>] ixgbe_dcbnl_set_state+0x167/0x189 [ixgbe]
>>
>> Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
>> ---
>
> I am not sure why you resent it, anyway, I ack it
>
> Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
>
> Thanks
>
>
net-next has Tom's changes for queue allocation and freeing. So the net-2.6 patch and net-next-2.6 patches are slightly different. I wanted to get the RCU_INIT_POINTER update in both and thought it would be easiest for Dave if they applied cleanly on both tree's. Let me know if there is a better way to indicate that here I just used the prefix net and net-next.
Thanks,
John.
^ permalink raw reply
* [PATCH] net: move definitions of BPF_S_* to net/core/filter.c
From: Changli Gao @ 2010-11-17 6:28 UTC (permalink / raw)
To: David S. Miller
Cc: Tetsuo Handa, Hagen Paul Pfeifer, Eric Dumazet, netdev,
Changli Gao
BPF_S_* are used internally, should not be exposed to the others.
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
---
include/linux/filter.h | 48 ------------------------------------------------
net/core/filter.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 48 insertions(+), 48 deletions(-)
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 69b43db..151f5d7 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -91,54 +91,6 @@ struct sock_fprog { /* Required for SO_ATTACH_FILTER. */
#define BPF_TAX 0x00
#define BPF_TXA 0x80
-enum {
- BPF_S_RET_K = 0,
- BPF_S_RET_A,
- BPF_S_ALU_ADD_K,
- BPF_S_ALU_ADD_X,
- BPF_S_ALU_SUB_K,
- BPF_S_ALU_SUB_X,
- BPF_S_ALU_MUL_K,
- BPF_S_ALU_MUL_X,
- BPF_S_ALU_DIV_X,
- BPF_S_ALU_AND_K,
- BPF_S_ALU_AND_X,
- BPF_S_ALU_OR_K,
- BPF_S_ALU_OR_X,
- BPF_S_ALU_LSH_K,
- BPF_S_ALU_LSH_X,
- BPF_S_ALU_RSH_K,
- BPF_S_ALU_RSH_X,
- BPF_S_ALU_NEG,
- BPF_S_LD_W_ABS,
- BPF_S_LD_H_ABS,
- BPF_S_LD_B_ABS,
- BPF_S_LD_W_LEN,
- BPF_S_LD_W_IND,
- BPF_S_LD_H_IND,
- BPF_S_LD_B_IND,
- BPF_S_LD_IMM,
- BPF_S_LDX_W_LEN,
- BPF_S_LDX_B_MSH,
- BPF_S_LDX_IMM,
- BPF_S_MISC_TAX,
- BPF_S_MISC_TXA,
- BPF_S_ALU_DIV_K,
- BPF_S_LD_MEM,
- BPF_S_LDX_MEM,
- BPF_S_ST,
- BPF_S_STX,
- BPF_S_JMP_JA,
- BPF_S_JMP_JEQ_K,
- BPF_S_JMP_JEQ_X,
- BPF_S_JMP_JGE_K,
- BPF_S_JMP_JGE_X,
- BPF_S_JMP_JGT_K,
- BPF_S_JMP_JGT_X,
- BPF_S_JMP_JSET_K,
- BPF_S_JMP_JSET_X,
-};
-
#ifndef BPF_MAXINSNS
#define BPF_MAXINSNS 4096
#endif
diff --git a/net/core/filter.c b/net/core/filter.c
index 23e9b2a..ceb36ea 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -38,6 +38,54 @@
#include <asm/unaligned.h>
#include <linux/filter.h>
+enum {
+ BPF_S_RET_K = 0,
+ BPF_S_RET_A,
+ BPF_S_ALU_ADD_K,
+ BPF_S_ALU_ADD_X,
+ BPF_S_ALU_SUB_K,
+ BPF_S_ALU_SUB_X,
+ BPF_S_ALU_MUL_K,
+ BPF_S_ALU_MUL_X,
+ BPF_S_ALU_DIV_X,
+ BPF_S_ALU_AND_K,
+ BPF_S_ALU_AND_X,
+ BPF_S_ALU_OR_K,
+ BPF_S_ALU_OR_X,
+ BPF_S_ALU_LSH_K,
+ BPF_S_ALU_LSH_X,
+ BPF_S_ALU_RSH_K,
+ BPF_S_ALU_RSH_X,
+ BPF_S_ALU_NEG,
+ BPF_S_LD_W_ABS,
+ BPF_S_LD_H_ABS,
+ BPF_S_LD_B_ABS,
+ BPF_S_LD_W_LEN,
+ BPF_S_LD_W_IND,
+ BPF_S_LD_H_IND,
+ BPF_S_LD_B_IND,
+ BPF_S_LD_IMM,
+ BPF_S_LDX_W_LEN,
+ BPF_S_LDX_B_MSH,
+ BPF_S_LDX_IMM,
+ BPF_S_MISC_TAX,
+ BPF_S_MISC_TXA,
+ BPF_S_ALU_DIV_K,
+ BPF_S_LD_MEM,
+ BPF_S_LDX_MEM,
+ BPF_S_ST,
+ BPF_S_STX,
+ BPF_S_JMP_JA,
+ BPF_S_JMP_JEQ_K,
+ BPF_S_JMP_JEQ_X,
+ BPF_S_JMP_JGE_K,
+ BPF_S_JMP_JGE_X,
+ BPF_S_JMP_JGT_K,
+ BPF_S_JMP_JGT_X,
+ BPF_S_JMP_JSET_K,
+ BPF_S_JMP_JSET_X,
+};
+
/* No hurry in this branch */
static void *__load_pointer(struct sk_buff *skb, int k)
{
^ permalink raw reply related
* [PATCH net-next-2.6] igmp: refine skb allocations
From: Eric Dumazet @ 2010-11-17 6:36 UTC (permalink / raw)
To: David Miller; +Cc: netdev
IGMP allocates MTU sized skbs. This may fail for large MTU (order-2
allocations), so add a fallback to try lower sizes.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
---
net/ipv4/igmp.c | 17 +++++++++++++----
1 file changed, 13 insertions(+), 4 deletions(-)
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index a1bf2f4..caff2fc 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -300,6 +300,8 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted)
return scount;
}
+#define igmp_skb_size(skb) (*(unsigned int *)((skb)->cb))
+
static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
{
struct sk_buff *skb;
@@ -308,9 +310,16 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
struct igmpv3_report *pig;
struct net *net = dev_net(dev);
- skb = alloc_skb(size + LL_ALLOCATED_SPACE(dev), GFP_ATOMIC);
- if (skb == NULL)
- return NULL;
+ while (1) {
+ skb = alloc_skb(size + LL_ALLOCATED_SPACE(dev),
+ GFP_ATOMIC | __GFP_NOWARN);
+ if (skb)
+ break;
+ size >>= 1;
+ if (size < 256)
+ return NULL;
+ }
+ igmp_skb_size(skb) = size;
{
struct flowi fl = { .oif = dev->ifindex,
@@ -400,7 +409,7 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc,
return skb;
}
-#define AVAILABLE(skb) ((skb) ? ((skb)->dev ? (skb)->dev->mtu - (skb)->len : \
+#define AVAILABLE(skb) ((skb) ? ((skb)->dev ? igmp_skb_size(skb) - (skb)->len : \
skb_tailroom(skb)) : 0)
static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
^ permalink raw reply related
* Re: [PATCH] net: move definitions of BPF_S_* to net/core/filter.c
From: Eric Dumazet @ 2010-11-17 6:38 UTC (permalink / raw)
To: Changli Gao; +Cc: David S. Miller, Tetsuo Handa, Hagen Paul Pfeifer, netdev
In-Reply-To: <1289975304-19796-1-git-send-email-xiaosuo@gmail.com>
Le mercredi 17 novembre 2010 à 14:28 +0800, Changli Gao a écrit :
> BPF_S_* are used internally, should not be exposed to the others.
>
> Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
^ permalink raw reply
* Re: [RFC PATCH v1 1/2] net: implement mechanism for HW based QOS
From: Eric Dumazet @ 2010-11-17 6:56 UTC (permalink / raw)
To: John Fastabend; +Cc: netdev, nhorman, davem
In-Reply-To: <20101117051544.19800.97654.stgit@jf-dev1-dcblab>
Le mardi 16 novembre 2010 à 21:15 -0800, John Fastabend a écrit :
> This patch provides a mechanism for lower layer devices to
> steer traffic using skb->priority to tx queues. This allows
> for hardware based QOS schemes to use the default qdisc without
> incurring the penalties related to global state and the qdisc
> lock. While reliably receiving skbs on the correct tx ring
> to avoid head of line blocking resulting from shuffling in
> the LLD. Finally, all the goodness from txq caching and xps/rps
> can still be leveraged.
>
> Many drivers and hardware exist with the ability to implement
> QOS schemes in the hardware but currently these drivers tend
> to rely on firmware to reroute specific traffic, a driver
> specific select_queue or the queue_mapping action in the
> qdisc.
>
> None of these solutions are ideal or generic so we end up
> with driver specific solutions that one-off traffic types
> for example FCoE traffic is steered in ixgbe with the
> queue_select routine. By using select_queue for this drivers
> need to be updated for each and every traffic type and we
> loose the goodness of much of the upstream work. For example
> txq caching.
>
> Firmware solutions are inherently inflexible. And finally if
> admins are expected to build a qdisc and filter rules to steer
> traffic this requires knowledge of how the hardware is currently
> configured. The number of tx queues and the queue offsets may
> change depending on resources. Also this approach incurs all the
> overhead of a qdisc with filters.
>
> With this mechanism users can set skb priority using expected
> methods either socket options or the stack can set this directly.
> Then the skb will be steered to the correct tx queues aligned
> with hardware QOS traffic classes. In the normal case with a
> single traffic class and all queues in this class every thing
> works as is until the LLD enables multiple tcs.
>
> To steer the skb we mask out the lower 8 bits of the priority
> and allow the hardware to configure upto 15 distinct classes
> of traffic. This is expected to be sufficient for most applications
> at any rate it is more then the 8021Q spec designates and is
> equal to the number of prio bands currently implemented in
> the default qdisc.
>
> This in conjunction with a userspace application such as
> lldpad can be used to implement 8021Q transmission selection
> algorithms one of these algorithms being the extended transmission
> selection algorithm currently being used for DCB.
>
> If this approach seems reasonable I'll go ahead and finish
> this up. The priority to tc mapping should probably be exposed
> to userspace either through sysfs or rtnetlink. Any thoughts?
>
> Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
> ---
>
> include/linux/netdevice.h | 47 +++++++++++++++++++++++++++++++++++++++++++++
> net/core/dev.c | 43 ++++++++++++++++++++++++++++++++++++++++-
> 2 files changed, 89 insertions(+), 1 deletions(-)
>
> diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
> index b45c1b8..8a2adeb 100644
> --- a/include/linux/netdevice.h
> +++ b/include/linux/netdevice.h
> @@ -1092,6 +1092,12 @@ struct net_device {
> /* Data Center Bridging netlink ops */
> const struct dcbnl_rtnl_ops *dcbnl_ops;
> #endif
> + u8 max_tcs;
> + u8 num_tcs;
> + unsigned int *_tc_txqcount;
> + unsigned int *_tc_txqoffset;
This seems wrong to use two different pointers, this is a waste of cache
memory. Also, I am not sure we need 32 bits, I believe we have a 16bit
limit for queue numbers.
Use a struct {
u16 count;
u16 offset;
};
> + u64 prio_tc_map;
Seems wrong too on 32bit arches
Please use : (even if using 16 bytes instead of 8)
u8 prio_tc_map[16];
> +
>
> #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
> /* max exchange id for FCoE LRO by ddp */
> @@ -1108,6 +1114,44 @@ struct net_device {
> #define NETDEV_ALIGN 32
>
> static inline
> +int netdev_get_prio_tc_map(const struct net_device *dev, u32 prio)
> +{
> + return (dev->prio_tc_map >> (4 * (prio & 0xF))) & 0xF;
return dev->prio_tc_map[prio & 15];
> +}
> +
> +static inline
> +void netdev_set_prio_tc_map(struct net_device *dev, u8 prio, u8 tc)
> +{
> + u64 mask = ~(-1 & (0xF << (4 * prio)));
> + /* Zero the 4 bit prio map and set traffic class */
> + dev->prio_tc_map &= mask;
> + dev->prio_tc_map |= tc << (4 * prio);
dev->prio_tc_map[prio & 15] = tc & 15;
> +}
> +
> +static inline
> +void netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset)
> +{
> + dev->_tc_txqcount[tc] = count;
> + dev->_tc_txqoffset[tc] = offset;
> +}
> +
> +static inline
> +int netdev_set_num_tc(struct net_device *dev, u8 num_tc)
> +{
> + if (num_tc > dev->max_tcs)
> + return -EINVAL;
> +
> + dev->num_tcs = num_tc;
> + return 0;
> +}
> +
> +static inline
> +u8 netdev_get_num_tc(struct net_device *dev)
> +{
> + return dev->num_tcs;
> +}
> +
> +static inline
> struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev,
> unsigned int index)
> {
> @@ -1332,6 +1376,9 @@ static inline void unregister_netdevice(struct net_device *dev)
> unregister_netdevice_queue(dev, NULL);
> }
>
> +extern int netdev_alloc_max_tcs(struct net_device *dev, u8 tcs);
> +extern void netdev_free_tcs(struct net_device *dev);
> +
> extern int netdev_refcnt_read(const struct net_device *dev);
> extern void free_netdev(struct net_device *dev);
> extern void synchronize_net(void);
> diff --git a/net/core/dev.c b/net/core/dev.c
> index 4a587b3..4565afc 100644
> --- a/net/core/dev.c
> +++ b/net/core/dev.c
> @@ -2111,6 +2111,8 @@ static u32 hashrnd __read_mostly;
> u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb)
> {
> u32 hash;
> + u16 qoffset = 0;
> + u16 qcount = dev->real_num_tx_queues;
>
> if (skb_rx_queue_recorded(skb)) {
> hash = skb_get_rx_queue(skb);
> @@ -2119,13 +2121,20 @@ u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb)
> return hash;
> }
>
> + if (dev->num_tcs) {
> + u8 tc;
> + tc = netdev_get_prio_tc_map(dev, skb->priority);
> + qoffset = dev->_tc_txqoffset[tc];
> + qcount = dev->_tc_txqcount[tc];
Here, two cache lines accessed... with one pointer, only one cache
line.
> + }
> +
> if (skb->sk && skb->sk->sk_hash)
> hash = skb->sk->sk_hash;
> else
> hash = (__force u16) skb->protocol ^ skb->rxhash;
> hash = jhash_1word(hash, hashrnd);
>
> - return (u16) (((u64) hash * dev->real_num_tx_queues) >> 32);
> + return (u16) ((((u64) hash * qcount)) >> 32) + qoffset;
> }
> EXPORT_SYMBOL(skb_tx_hash);
>
> @@ -5037,6 +5046,37 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev,
> }
> EXPORT_SYMBOL(netif_stacked_transfer_operstate);
>
> +int netdev_alloc_max_tcs(struct net_device *dev, u8 tcs)
> +{
> + unsigned int *count, *offset;
> + count = kcalloc(tcs, sizeof(unsigned int), GFP_KERNEL);
for small tcs, you could get half a cache line, the other one might be
used elsewhere in the kernel, giving false sharing.
> + if (!count)
> + return -ENOMEM;
> + offset = kcalloc(tcs, sizeof(unsigned int), GFP_KERNEL);
One allocation only ;)
> + if (!offset) {
> + kfree(count);
> + return -ENOMEM;
> + }
> +
> + dev->_tc_txqcount = count;
> + dev->_tc_txqoffset = offset;
> + dev->max_tcs = tcs;
> + return tcs;
> +}
> +EXPORT_SYMBOL(netdev_alloc_max_tcs);
> +
> +void netdev_free_tcs(struct net_device *dev)
> +{
> + dev->max_tcs = 0;
> + dev->num_tcs = 0;
> + dev->prio_tc_map = 0;
> + kfree(dev->_tc_txqcount);
> + kfree(dev->_tc_txqoffset);
> + dev->_tc_txqcount = NULL;
> + dev->_tc_txqoffset = NULL;
> +}
> +EXPORT_SYMBOL(netdev_free_tcs);
> +
> static int netif_alloc_rx_queues(struct net_device *dev)
> {
> #ifdef CONFIG_RPS
> @@ -5641,6 +5681,7 @@ void free_netdev(struct net_device *dev)
> #ifdef CONFIG_RPS
> kfree(dev->_rx);
> #endif
> + netdev_free_tcs(dev);
>
> kfree(rcu_dereference_raw(dev->ingress_queue));
>
>
^ permalink raw reply
* Re: [PATCH v3] filter: Optimize instruction revalidation code.
From: Eric Dumazet @ 2010-11-17 7:48 UTC (permalink / raw)
To: Tetsuo Handa; +Cc: mjt, davem, drosenberg, hagen, xiaosuo, netdev
In-Reply-To: <201011170119.oAH1JpES011121@www262.sakura.ne.jp>
Le mercredi 17 novembre 2010 à 10:19 +0900, Tetsuo Handa a écrit :
> Eric Dumazet wrote:
> > I dont understand the problem...
> > Once translated, you have to test the translated code, not the original
> > one ;)
>
> I moved the test to after translation.
>
> > why u16 ?
> >
> > You store translated instructions, so u8 is OK
>
> I chose u16 because type of filter->code is __u16.
> But I changed to use u8 as you suggested that translated code fits in u8.
>
> > Also fix the indentation at the end of sk_chk_filter()
> >
> > You have 3 extra tabulations :
>
> Fixed.
>
> Hagen Paul Pfeifer wrote:
> > Maybe I don't get it, but you increment the opcode by one, but you never
> > increment the opcode in sk_run_filter() - do I miss something? Did you test
> > the your patch (a trivial tcpdump rule should be sufficient)?
>
> I added a comment line.
>
> Changli Gao wrote:
> > > + struct sock_filter *ftest = &filter[pc];
> >
> > Why move the define here?
>
> To suppress compiler's warning about mixed declaration.
>
> > > + u16 code = ftest->code;
> > >
> > > + if (code >= ARRAY_SIZE(codes))
> > > + return 0;
> >
> > return -EINVAL;
>
> Fixed in v2. Thanks.
>
> > But how about this:
> >
> > enum {
> > BPF_S_RET_K = 1,
>
> If BPF_S_* are only for kernel internal use, I think we don't need to translate
> from the beginning because only net/core/filter.c uses BPF_S_*.
>
> BPF_S_* are exposed to userspace via /usr/include/linux/filter.h since 2.6.36.
> Is it no problem to change?
No problem, and Changli posted patch to move them to net/core/filter.c
anyway.
>
> Filesize change (x86_32) by this patch:
> gcc 3.3.5: 7184 -> 5060
> gcc 4.4.3: 7972 -> 5588
> ----------------------------------------
> From b8777ab64bc31dbbe499eb62c2ffd29add7e79c8 Mon Sep 17 00:00:00 2001
> From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
> Date: Wed, 17 Nov 2010 09:46:33 +0900
> Subject: [PATCH v3] filter: Optimize instruction revalidation code.
>
> Since repeating u16 value to u8 value conversion using switch() clause's
> case statement is wasteful, this patch introduces u16 to u8 mapping table
> and removes most of case statements. As a result, the size of net/core/filter.o
> is reduced by about 29% on x86.
>
> Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
> ---
> net/core/filter.c | 231 +++++++++++++++++------------------------------------
> 1 files changed, 72 insertions(+), 159 deletions(-)
>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Please repost it when Changli patch is accepted by David
(if accepted :)), to get rid of the "+ 1"
^ permalink raw reply
* Re: [PATCH v3] filter: Optimize instruction revalidation code.
From: Changli Gao @ 2010-11-17 7:54 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Tetsuo Handa, mjt, davem, drosenberg, hagen, netdev
In-Reply-To: <1289980137.2732.280.camel@edumazet-laptop>
On Wed, Nov 17, 2010 at 3:48 PM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
>
> Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
>
> Please repost it when Changli patch is accepted by David
> (if accepted :)), to get rid of the "+ 1"
>
Oh. No need, if David accepts this patch first, otherwise, there is
just some offset, and patch can handle it. :)
--
Regards,
Changli Gao(xiaosuo@gmail.com)
^ permalink raw reply
* Re: [PATCH v3] filter: Optimize instruction revalidation code.
From: Tetsuo Handa @ 2010-11-17 8:06 UTC (permalink / raw)
To: eric.dumazet; +Cc: mjt, davem, drosenberg, hagen, xiaosuo, netdev
In-Reply-To: <1289980137.2732.280.camel@edumazet-laptop>
Eric Dumazet wrote:
> > > But how about this:
> > >
> > > enum {
> > > BPF_S_RET_K = 1,
> >
> > If BPF_S_* are only for kernel internal use, I think we don't need to translate
> > from the beginning because only net/core/filter.c uses BPF_S_*.
> >
> > BPF_S_* are exposed to userspace via /usr/include/linux/filter.h since 2.6.36.
> > Is it no problem to change?
>
> No problem, and Changli posted patch to move them to net/core/filter.c
> anyway.
> Please repost it when Changli patch is accepted by David
> (if accepted :)), to get rid of the "+ 1"
But if Changli's patch is accepted, we can remove BPF_S_* like below.
switch (fentry->code) {
- case BPF_S_ALU_ADD_X:
+ case BPF_ALU|BPF_ADD|BPF_X: /* BPF_S_ALU_ADD_X */
A += X;
continue;
- case BPF_S_ALU_ADD_K:
+ case BPF_ALU|BPF_ADD|BPF_K: /* BPF_S_ALU_ADD_K */
A += f_k;
continue;
- case BPF_S_ALU_SUB_X:
+ case BPF_ALU|BPF_SUB|BPF_X: /* BPF_S_ALU_SUB_X */
A -= X;
continue;
- case BPF_S_ALU_SUB_K:
+ case BPF_ALU|BPF_SUB|BPF_K: /* BPF_S_ALU_SUB_K */
A -= f_k;
continue;
If compilers can generate better code for continuous case values
than discontinuous case values, then keeping BPF_S_* makes sense.
^ 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