Several devices have multiple independant RX queues per net
device, and some have a single interrupt doorbell for several
queues.
In either case, it's easier to support layouts like that if the
structure representing the poll is independant from the net
device itself.
The signature of the ->poll() call back goes from:
int foo_poll(struct net_device *dev, int *budget)
to
int foo_poll(struct napi_struct *napi, int budget)
The caller is returned the number of RX packets processed (or
the number of "NAPI credits" consumed if you want to get
abstract). The callee no longer messes around bumping
dev->quota, *budget, etc. because that is all handled in the
caller upon return.
The napi_struct is to be embedded in the device driver private data
structures.
Furthermore, it is the driver's responsibility to disable all NAPI
instances in it's ->stop() device close handler. Since the
napi_struct is privatized into the driver's private data structures,
only the driver knows how to get at all of the napi_struct instances
it may have per-device.
With lots of help and suggestions from Rusty Russell, Roland Dreier,
Michael Chan, Jeff Garzik, and Jamal Hadi Salim.
Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,
Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.
[ Ported to current tree and all drivers converted. Integrated
Stephen's follow-on kerneldoc additions, and restored poll_list
handling to the old style to fix mutual exclusion issues. -DaveM ]
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Update last_rx in registered device struct instead of
in the dummy device.
Signed-off-by: Jan-Bernd Themann <themann@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Introduces a module parameter to decide whether the physical
port link state is propagated to the network stack or not.
It makes sense not to take the physical port state into account
on machines with more logical partitions that communicate
with each other. This is always possible no matter what the physical
port state is. Thus eHEA can be considered as a switch there.
Signed-off-by: Jan-Bernd Themann <themann@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Includes hcp_epas_dtor in eq/cq/qp destructors to unmap
HW register.
Signed-off-by: Jan-Bernd Themann <themann@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Update the module parameter description of "use_mcs" to
show correct default value
Signed-off-by: Jan-Bernd Themann <themann@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Userspace DLPAR tool expects decimal numbers to be written to
and read from sysfs entries.
Signed-off-by: Jan-Bernd Themann <themann@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Use shorter method to determine whether adapter has configured ports
Signed-off-by: Thomas Klein <tklein@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
The driver didn't allow an interface's MAC address to be modified if the
respective interface wasn't setup - a failing Hcall was the result. Thus
bonding wasn't usable. The fix moves the failing Hcall which was registering
a MAC address for the reception of BC packets in firmware from the port up
and down functions to the port resources setup functions. Additionally the
missing update of the last_rx member of the netdev structure was added.
Signed-off-by: Thomas Klein <tklein@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch adds support for DLPAR memory add to the eHEA driver. To detect
whether memory was added the driver uses its own memory mapping table and
checks for kernel addresses whether they're located in already known memory
sections. If not the function ehea_rereg_mrs() is triggered which performs
a rebuild of the mapping table and a re-registration of the global memory
region.
Signed-off-by: Thomas Klein <tklein@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch introduces a capability flag that is used by the DLPAR userspace
tool to check which DLPAR features are supported by the eHEA driver.
Missing goto has been included.
Signed-off-by: Jan-Bernd Themann <themann@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch fixes a possible kernel panic due to not checking the vlan group
when processing received VLAN packets and a malfunction in VLAN/hypervisor
registration.
Signed-off-by: Thomas Klein <tklein@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Must access the respective queue's dummy netdev instead of the port's netdev.
Signed-off-by: Thomas Klein <tklein@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
* 'upstream-linus' of master.kernel.org:/pub/scm/linux/kernel/git/jgarzik/netdev-2.6: (40 commits)
[netdrvr] atl1: fix build
pasemi_mac: Use local-mac-address instead of mac-address if available
pasemi_mac: PHY support
pasemi_mac: Add msglevel support and "debug" module param
pasemi_mac: Logic cleanup / rx performance improvements
pasemi_mac: Minor cleanup / define fixes
pasemi_mac: Add SKB reuse / copy-break
pasemi_mac: Timer and interrupt fixes
pasemi_mac: Abstract and fix up interrupt restart routines
pasemi_mac: Move the IRQ mapping from the PCI layer to the driver
tc35815: Remove unnecessary skb->dev assignment
drivers/net/dm9000: Convert to generic boolean
AT91RM9200 Ethernet: Fix multicast addressing
AT91RM9200 Ethernet: Support additional PHYs
PCMCIA-NETDEV : xirc2ps_cs: bugfix of multicast code
sky2: re-enable 88E8056 for most motherboards
MIPS: Drop unnecessary CONFIG_ISA from RBTX49XX
ne: MIPS: Use platform_driver for ne on RBTX49XX
ne: Add NEEDS_PORTLIST to control ISA auto-probe
ne: Misc fixes for platform driver.
...
Fix conflict in drivers/net/pasemi_mac.c (get_property() got renamed to
of_get_property()) manually.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
These are all the remaining instances of get_property. Simple rename of
get_property to of_get_property.
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This is the last place that needs changing since get_property was changed
to return "const void *".
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Certain resources may only be allocated when first logical port is available,
and must be removed when last logical port has been removed.
Signed-off-by: Thomas Klein <tklein@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Create symbolic link from each logical port to ehea driver
Signed-off-by: Thomas Klein <tklein@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
strlcpy already accounts for the trailing zero in its length
computation, so there is no need to substract one to the buffer size.
Signed-off-by: Jean Delvare <khali@linux-fr.org>
Cc: Jan-Bernd Themann <themann@de.ibm.com>
Cc: Thomas Klein <osstklei@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch includes:
- code cleanup related to resource management
- extended error data gathering for resource management
- removing trailing whitespaces
Signed-off-by: Jan-Bernd Themann <themann@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
The patch fixes bugs related to the probe / remove adapter
functionality (handling of OFDT nodes)
Signed-off-by: Jan-Bernd Themann <themann@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch provides a functionality that allows parallel
RX processing on multiple RX queues by using dummy netdevices.
Signed-off-by: Jan-Bernd Themann <themann@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch introduces functionality to dynamically add / remove
ehea ports via an userspace DLPAR tool. It creates a subnode for
each logical port in the sysfs.
Signed-off-by: Jan-Bernd Themann <themann@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
To clearly state the intent of copying to 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@ghostprotocols.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>
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>
Error recovery for QP errors: Reset QPs and dump error information
Signed-off-by: Jan-Bernd Themann <themann@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch fixes the wrong query and logging of the per interface jumbo frames
enabled/disabled status.
Signed-off-by: Thomas Klein <tklein@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Fixed possible nullpointer access in event queue processing
Signed-off-by: Thomas Klein <tklein@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Added logging of error events associated with a specific queue pair
Signed-off-by: Thomas Klein <tklein@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Disabled dump of hcall regs on some permission issues and
fixed appropriate misleading logmessages
Signed-off-by: Thomas Klein <tklein@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Count OFDT nodes to determine the number of available ports
instead of using the possibly outdated value from the hypervisor
Signed-off-by: Thomas Klein <tklein@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Logical partitions are not allowed to (try to) set the autonegotiation status.
This patch removes the respective function call from the port setup function.
Signed-off-by: Thomas Klein <tklein@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Fix to use exactly one queue for incoming packets in all
firmware configurations
Signed-off-by: Thomas Klein <tklein@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Not only check the pointer against 0 but also the dereferenced value
Signed-off-by: Thomas Klein <tklein@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Conflicts:
drivers/ata/libata-scsi.c
include/linux/libata.h
Futher merge of Linus's head and compilation fixups.
Signed-Off-By: David Howells <dhowells@redhat.com>
This patch fixes 64k page support by using PAGE_MASK and appropriate pagesize defines in several places.
Signed-off-by: Thomas Klein <tklein@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Removed define H_CB_ALIGNMENT which is already defined in include/asm-powerpc/hvcall.h
Signed-off-by: Thomas Klein <tklein@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Fix: Must check for nullpointer before dereferencing it - not afterwards.
Signed-off-by: Thomas Klein <tklein@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This patch includes a bug fix for the port state notification
and fixes the default queue sizes.
Signed-off-by: Jan-Bernd Themann <themann@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
This eHEA patch covers required changes related to Anton Blanchard's new hvcall interface.
Signed-off-by: Jan-Bernd Themann <themann@de.ibm.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
Maintain a per-CPU global "struct pt_regs *" variable which can be used instead
of passing regs around manually through all ~1800 interrupt handlers in the
Linux kernel.
The regs pointer is used in few places, but it potentially costs both stack
space and code to pass it around. On the FRV arch, removing the regs parameter
from all the genirq function results in a 20% speed up of the IRQ exit path
(ie: from leaving timer_interrupt() to leaving do_IRQ()).
Where appropriate, an arch may override the generic storage facility and do
something different with the variable. On FRV, for instance, the address is
maintained in GR28 at all times inside the kernel as part of general exception
handling.
Having looked over the code, it appears that the parameter may be handed down
through up to twenty or so layers of functions. Consider a USB character
device attached to a USB hub, attached to a USB controller that posts its
interrupts through a cascaded auxiliary interrupt controller. A character
device driver may want to pass regs to the sysrq handler through the input
layer which adds another few layers of parameter passing.
I've build this code with allyesconfig for x86_64 and i386. I've runtested the
main part of the code on FRV and i386, though I can't test most of the drivers.
I've also done partial conversion for powerpc and MIPS - these at least compile
with minimal configurations.
This will affect all archs. Mostly the changes should be relatively easy.
Take do_IRQ(), store the regs pointer at the beginning, saving the old one:
struct pt_regs *old_regs = set_irq_regs(regs);
And put the old one back at the end:
set_irq_regs(old_regs);
Don't pass regs through to generic_handle_irq() or __do_IRQ().
In timer_interrupt(), this sort of change will be necessary:
- update_process_times(user_mode(regs));
- profile_tick(CPU_PROFILING, regs);
+ update_process_times(user_mode(get_irq_regs()));
+ profile_tick(CPU_PROFILING);
I'd like to move update_process_times()'s use of get_irq_regs() into itself,
except that i386, alone of the archs, uses something other than user_mode().
Some notes on the interrupt handling in the drivers:
(*) input_dev() is now gone entirely. The regs pointer is no longer stored in
the input_dev struct.
(*) finish_unlinks() in drivers/usb/host/ohci-q.c needs checking. It does
something different depending on whether it's been supplied with a regs
pointer or not.
(*) Various IRQ handler function pointers have been moved to type
irq_handler_t.
Signed-Off-By: David Howells <dhowells@redhat.com>
(cherry picked from 1b16e7ac850969f38b375e511e3fa2f474a33867 commit)
Hi Jeff,
sorry to bother you again. We figured out that the readq function we
included in the eHEA patch we sent yesterday to access eHEA registers
is defined as little endian on POWER. This collides with our adapter.
We talked to some PPC people who told us there is a discussion going
on about new access functions. We were told to use __raw_readq /
__raw_writeq for now.
This patch fixes this bug found by our internal tests today.
Please apply this small patch on the latest patch we sent you yesterday.
If it is easier for you I can also give you the entire eHEA patch again.
sorry and thanks a lot,
Jan-Bernd
Signed-off-by: Jan-Bernd Themann <themann@de.ibm.com>
drivers/net/ehea/ehea.h | 2 +-
drivers/net/ehea/ehea_hw.h | 11 ++++++++---
2 files changed, 9 insertions(+), 4 deletions(-)
Signed-off-by: Jeff Garzik <jeff@garzik.org>
