A hardware bug was revealed after a recent PCI MSI patch was made to
always disable legacy INTX when enabling MSI. The 5714/5780 chips
will not generate MSI when INTX is disabled, causing MSI failure
messages to be reported, and another patch was made to workaround the
problem by disabling MSI on ServerWorks HT1000 bridge chips commonly
found with the 5714.
We workaround this chip bug by enabling INTX after we enable MSI and
after we resume from suspend.
Update version to 3.81.
This problem was discovered by David Miller.
Signed-off-by: Michael Chan <mchan@broadcom.com>
Acked-by: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Joachim Deguara <joachim.deguara@amd.com> reported that tg3 devices
would not resume properly if the device was shutdown before the system
was suspended. In such scenario where the netif_running state is 0,
tg3_suspend() would not save the PCI state and so the memory enable bit
and bus master enable bit would be lost.
We fix this by always saving and restoring the PCI state in
tg3_suspend() and tg3_resume() regardless of netif_running() state.
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
All drivers implement ethtool get_perm_addr the same way -- by calling
the generic function. So we can inline the generic function into the
caller and avoid going through the drivers.
Signed-off-by: Matthew Wilcox <matthew@wil.cx>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tina Yang <tina.yang@oracle.com> discovered an MSI related problem
when doing kdump. The problem is that the kexec kernel is booted
without going through system reset, and as a result, MSI may already
be enabled when tg3_init_one() is called. tg3_init_one() calls
pci_save_state() which will save the stale MSI state. Later on in
tg3_open(), we call pci_enable_msi() to reconfigure MSI on the chip
before we reset the chip. After chip reset, we call
pci_restore_state() which will put the stale MSI address/data back
onto the chip.
This is no longer a problem in the latest kernel because
pci_restore_state() has been changed to restore MSI state from
internal data structures which will guarantee restoring the proper
MSI state.
But I think we should still fix it. Our save and restore sequence
can still cause very subtle problems down the road. The fix is to
have our own functions save and restore precisely what we need. We
also change it to save and restore state inside tg3_chip_reset() in a
more straight forward way.
Thanks to Tina for helping to test and debug the problem.
[ Bump driver version and release date. -DaveM ]
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add ethtool utility function to set or clear IPV6_CSUM feature flag.
Modify tg3.c and bnx2.c to use this function when doing ethtool -K
to change tx checksum.
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds a missing NVRAM strapping for 5755 devices.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds automatic MDI crossover support when autonegotiation is
turned off. Automatic MDI crossover allows link to be established
without the use of a crossover cable.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For most pre-5705 devices, multiple link interrupts were being generated
for a single physical link change. The source of the interrupts was
determined to be unnecessary toggling of the MAC link polarity bit.
This patch changes the way the link polarity bit gets configured. Where
possible, code that dynamically configures the bit in response to link
changes has been replaced by code that configures the bit once during
initialization time and then leaves the bit alone.
For correctness, this patch also limits the use of the bit to those
devices where it is defined, namely devices before the 5705. This patch
also corrects the link polarity configurations for 5700 devices when
paired against a bcm5411 phy.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Gagan Arneja <gaagaan@gmail.com> pointed out that tg3_reset_task()
could potentially race with another thread calling tg3_full_lock()
such as the ethtool_set_xxx() functions. This may trigger the
BUG_ON() in tg3_irq_quiesce() or cause the irq_sync flag to be out-
of-sync.
I think the easiest way to fix this is to get the tp->lock first
before setting the irq_sync flag. This is safe to do because the
tp->lock is never grabbed by the irq handler. This change will
guarantee that the irq_sync flag updates will be serialized. We also
have to change one spot to call tg3_netif_start() (which clears the
irq_sync flag) before releasing the tp->lock.
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of all drivers reading pci config space to get the revision
ID, they can now use the pci_device->revision member.
This exposes some issues where drivers where reading a word or a dword
for the revision number, and adding useless error-handling around the
read. Some drivers even just read it for no purpose of all.
In devices where the revision ID is being copied over and used in what
appears to be the equivalent of hotpath, I have left the copy code
and the cached copy as not to influence the driver's performance.
Compile tested with make all{yes,mod}config on x86_64 and i386.
Signed-off-by: Auke Kok <auke-jan.h.kok@intel.com>
Acked-by: Dave Jones <davej@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
The existing model for checksum offload does not correctly handle
devices that can offload IPV4 and IPV6 only. The NETIF_F_HW_CSUM flag
implies device can do any arbitrary protocol.
This patch:
* adds NETIF_F_IPV6_CSUM for those devices
* fixes bnx2 and tg3 devices that need it
* add NETIF_F_IPV6_CSUM to ipv6 output (incl GSO)
* fixes assumptions about NETIF_F_ALL_CSUM in nat
* adjusts bridge union of checksumming computation
Signed-off-by: David S. Miller <davem@davemloft.net>
The bug is caused by code that always set
(TG3_FLAG_USE_MI_INTERRUPT | TG3_FLAG_USE_LINKCHG_REG) on all Dell's
onboard devices. With these 2 flags set, the link status is polled
by tg3_timer() and will only work when the PHY is set up to interrupt
the MAC on link changes. This breaks 5906 because the 5906 PHY does
not support TG3_FLAG_USE_MI_INTERRUPT the same as other PHYs.
For correctness, only Dell's onboard 5701 needs these 2 flags to be
set. This change will fix the 5906 problem and will change other
Dell devices except 5700 and 5701 to use the more efficient
interrupt-driven link changes.
Update version to 3.77.
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Many drivers had code that did kill_vid, but they weren't doing vlan
filtering. With new API the stub is unneeded unless device sets
NETIF_F_HW_VLAN_FILTER.
Bad habit: I couldn't resist fixing a couple of nearby style things
in acenic, and forcedeth.
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
flush_work(wq, work) doesn't need the first parameter, we can use cwq->wq
(this was possible from the very beginnig, I missed this). So we can unify
flush_work_keventd and flush_work.
Also, rename flush_work() to cancel_work_sync() and fix all callers.
Perhaps this is not the best name, but "flush_work" is really bad.
(akpm: this is why the earlier patches bypassed maintainers)
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Jeff Garzik <jeff@garzik.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Tejun Heo <htejun@gmail.com>
Cc: Auke Kok <auke-jan.h.kok@intel.com>,
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Convert tg3 over to flush_work_keventd(). Remove nasty now-unneeded deadlock
avoidance logic.
(akpm: bypassed maintainers, sorry. There are other patches which depend on
this)
Cc: "Maciej W. Rozycki" <macro@linux-mips.org>
Cc: David Howells <dhowells@redhat.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Michael Chan <mchan@broadcom.com>
Cc: Jeff Garzik <jeff@garzik.org>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Spurious interrupts are often encountered especially on systems
using the 8259 PIC mode. This is because the I/O write to deassert
the interrupt is posted and won't get to the chip immediately. As
a result, the IRQ may remain asserted after the IRQ handler exits,
causing spurious interrupts.
Flush the interrupt mailbox in non-MSI handlers to de-assert the
IRQ immediately. This seems to be the most straight forward approach
after discussion with Jeff Garzik and David Miller.
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds workaround to fix performance problems caused by slow
PCIE L1->L0 transitions on ICH8 platforms.
Changed all magic numbers to constants as suggested by Jeff Garzik.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
And fix up the code to always allow MSI on 5714 A2.
Call tg3_find_peer() earlier because we need that information before
we can determine whether we can set TG3_FLAG_SUPPORT_MSI or not.
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch removes the use of the TG3_FLAG_5701_REG_WRITE_BUG flag.
It's logic is only used to set a function pointer and thus the
logic can be collapsed and the flag removed.
[ Comment tidy by Christoph Hellwig. -DaveM ]
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
The reset was added a while back so that ASF could re-init whatever
MAC address it wanted to use after the MAC address was changed.
Instead of resetting, we can just keep MAC address 1 unchanged during
MAC address changes if MAC address 1 is different from MAC address 0.
This fixes 2 problems:
1. Bonding calls set_mac_address in contexts that cannot sleep.
It no longer sleeps with the chip reset removed.
2. When ASF shares the same MAC address as the NIC, it needs to
always do that even when the MAC address is changed.
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Change TG3_FLAG_SERDES_WOL_CAP to TG3_FLAG_WOL_CAP to make it easier
to manage WoL. This flag is now used consistently during ethtool WoL
setup and power setting changes.
Signed-off-by: Gary Zambrano <zambrano@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The GPIO settings may change during reset and so the stored values in
tp->grc_local_ctrl should be cleared first.
Signed-off-by: Gary Zambrano <zambrano@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch changes the NVRAM sizing procedure so that the driver can
take advantage of devices with 1:1 NVRAM strapping configurations. This
is useful in cases where the traditional NVRAM sizing method fails. In
the event that the flash size cannot be determined, the largest known
NVRAM size is used. The patch also removes support for 5755 NVRAM
devices that are not supported by Broadcom and adds explicit sizing for
this device.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
1. Remove the check for skb->len greater than MTU when doing TSO.
When the destination has a smaller MSS than the source, a TSO packet
may be smaller than the MTU and we still need to process it as a TSO
packet.
2. On 5705A3 devices with TSO enabled, the DMA engine can hang due to a
hardware bug. This patch avoids the hanging condition by reducing the
DMA burst size.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The only unfortunate bit here is that the name field of struct map_info
is not const, so for now we put a cast on the assignment of it.
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
To clearly state the intent of copying from linear sk_buffs, _offset being a
overly long variant but interesting for the sake of saving some bytes.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The ip_hdrlen() buddy, created to reduce the number of skb->h.th-> uses and to
avoid the longer, open coded equivalent.
Ditched a no-op in bnx2 in the process.
I wonder if we should have a BUG_ON(skb->h.th->doff < 5) in tcp_optlen()...
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For the common sequence "skb->nh.iph->ihl * 4", removing a good number of open
coded skb->nh.iph uses, now to go after the rest...
Just out of curiosity, here are the idioms found to get the same result:
skb->nh.iph->ihl << 2
skb->nh.iph->ihl<<2
skb->nh.iph->ihl * 4
skb->nh.iph->ihl*4
(skb->nh.iph)->ihl * sizeof(u32)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The driver will crash when the chip has been initialized by EFI before
tg3_init_one(). In this case, the driver will call tg3_chip_reset()
before allocating consistent memory.
The bug is fixed by checking for tp->hw_status before accessing it
during tg3_chip_reset().
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
On most tg3 chips, the memory enable bit in the PCI command register
gets cleared during chip reset and must be restored before accessing
PCI registers using memory cycles. The chip does not generate
interrupt during chip reset, but the irq handler can still be called
because of irq sharing or irqpoll. Reading a register in the irq
handler can cause a master abort in this scenario and may result in a
crash on some architectures.
Use the TG3_FLAG_CHIP_RESETTING flag to tell the irq handler to exit
without touching any registers. The checking of the flag is in the
"slow" path of the irq handler and will not affect normal performance.
The msi handler is not shared and therefore does not require checking
the flag.
Thanks to Bernhard Walle <bwalle@suse.de> for reporting the problem.
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This flag to support multiple PCIX split completions was never used
because of hardware bugs. This will make room for a new flag.
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch splits the vlan_group struct into a multi-allocated struct. On
x86_64, the size of the original struct is a little more than 32KB, causing
a 4-order allocation, which is prune to problems caused by buddy-system
external fragmentation conditions.
I couldn't just use vmalloc() because vfree() cannot be called in the
softirq context of the RCU callback.
Signed-off-by: Dan Aloni <da-x@monatomic.org>
Acked-by: Jeff Garzik <jeff@garzik.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
1. Add race condition check after netif_stop_queue(). tg3_tx() runs
without netif_tx_lock and can race with tg3_start_xmit_dma_bug() ->
tg3_tso_bug().
2. Firmware TSO in 5703/5704/5705 also have the same TSO limitation,
i.e. they cannot handle TSO headers bigger than 80 bytes. Rename
TG3_FL2_HW_TSO_1_BUG to TG3_FL2_TSO_BUG and set this flag on
these chips as well.
3. Update version to 3.74.
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Print the most useful information during tx timeout to help debug.
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Set DMA read watermark to 4 on 5703 in PCIX mode. This is needed to
prevent some tx timeouts.
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This fixes the following problem:
http://bugzilla.kernel.org/show_bug.cgi?id=7969
The MSI state needs to be saved during suspend. PCI state saved
during tg3_init_one() does not contain valid MSI state because
MSI hasn't been enabled.
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
During an oprofile session of linux-2.6.20 on a dual opteron system, I noticed
an expensive divide was done in tg3_poll().
I am using gcc-4.1.1, so the following comment from drivers/net/tg3.c seems
over-optimistic :
/* Do not place this n-ring entries value into the tp struct itself,
* we really want to expose these constants to GCC so that modulo et
* al. operations are done with shifts and masks instead of with
* hw multiply/modulo instructions. Another solution would be to
* replace things like '% foo' with '& (foo - 1)'.
*/
#define TG3_RX_RCB_RING_SIZE(tp) \
((tp->tg3_flags2 & TG3_FLG2_5705_PLUS) ? 512 : 1024)
Assembly code before patch :
(oprofile results included)
6434 0.0088 :ffffffff803684b9: mov 0x6f0(%r15),%eax
587 8.0e-04 :ffffffff803684c0: and $0x40000,%eax
2170 0.0030 :ffffffff803684c5: cmp $0x1,%eax
:ffffffff803684c8: lea 0x1(%r13),%eax
:ffffffff803684cc: sbb %ecx,%ecx
2051 0.0028 :ffffffff803684ce: xor %edx,%edx
:ffffffff803684d0: and $0x200,%ecx
20 2.7e-05 :ffffffff803684d6: add $0x200,%ecx
1986 0.0027 :ffffffff803684dc: div %ecx
103427 0.1410 :ffffffff803684de: cmp %edx,0xffffffffffffff7c(%rbp)
Assembly code after the suggested patch :
ffffffff803684b9: mov 0x6f0(%r15),%eax
ffffffff803684c0: and $0x40000,%eax
ffffffff803684c5: cmp $0x1,%eax
ffffffff803684c8: sbb %eax,%eax
ffffffff803684ca: inc %r13d
ffffffff803684cd: and $0x200,%eax
ffffffff803684d2: add $0x1ff,%eax
ffffffff803684d7: and %eax,%r13d
ffffffff803684da: cmp %r13d,0xffffffffffffff7c(%rbp)
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Acked-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Michael Chan