aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/DocBook/kernel-api.tmpl8
-rw-r--r--Documentation/networking/NAPI_HOWTO.txt766
-rw-r--r--Documentation/networking/netdevices.txt12
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib.h4
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_ib.c43
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_main.c11
-rw-r--r--drivers/net/8139cp.c41
-rw-r--r--drivers/net/8139too.c48
-rw-r--r--drivers/net/amd8111e.c30
-rw-r--r--drivers/net/amd8111e.h2
-rw-r--r--drivers/net/arm/ep93xx_eth.c72
-rw-r--r--drivers/net/b44.c48
-rw-r--r--drivers/net/b44.h2
-rw-r--r--drivers/net/bnx2.c47
-rw-r--r--drivers/net/bnx2.h2
-rw-r--r--drivers/net/cassini.c40
-rw-r--r--drivers/net/cassini.h2
-rw-r--r--drivers/net/chelsio/common.h1
-rw-r--r--drivers/net/chelsio/cxgb2.c9
-rw-r--r--drivers/net/chelsio/sge.c29
-rw-r--r--drivers/net/chelsio/sge.h2
-rw-r--r--drivers/net/cxgb3/adapter.h22
-rw-r--r--drivers/net/cxgb3/cxgb3_main.c96
-rw-r--r--drivers/net/cxgb3/sge.c170
-rw-r--r--drivers/net/e100.c37
-rw-r--r--drivers/net/e1000/e1000.h1
-rw-r--r--drivers/net/e1000/e1000_main.c45
-rw-r--r--drivers/net/ehea/ehea.h2
-rw-r--r--drivers/net/ehea/ehea_main.c129
-rw-r--r--drivers/net/epic100.c36
-rw-r--r--drivers/net/fec_8xx/fec_8xx.h2
-rw-r--r--drivers/net/fec_8xx/fec_main.c59
-rw-r--r--drivers/net/forcedeth.c69
-rw-r--r--drivers/net/fs_enet/fs_enet-main.c55
-rw-r--r--drivers/net/fs_enet/fs_enet.h1
-rw-r--r--drivers/net/gianfar.c47
-rw-r--r--drivers/net/gianfar.h3
-rw-r--r--drivers/net/ibmveth.c117
-rw-r--r--drivers/net/ibmveth.h1
-rw-r--r--drivers/net/ixgb/ixgb.h1
-rw-r--r--drivers/net/ixgb/ixgb_main.c29
-rw-r--r--drivers/net/ixp2000/ixpdev.c39
-rw-r--r--drivers/net/ixp2000/ixpdev.h2
-rw-r--r--drivers/net/macb.c40
-rw-r--r--drivers/net/macb.h1
-rw-r--r--drivers/net/mv643xx_eth.c48
-rw-r--r--drivers/net/mv643xx_eth.h2
-rw-r--r--drivers/net/myri10ge/myri10ge.c40
-rw-r--r--drivers/net/natsemi.c42
-rw-r--r--drivers/net/netxen/netxen_nic.h1
-rw-r--r--drivers/net/netxen/netxen_nic_main.c39
-rw-r--r--drivers/net/pasemi_mac.c36
-rw-r--r--drivers/net/pasemi_mac.h1
-rw-r--r--drivers/net/pcnet32.c82
-rw-r--r--drivers/net/ps3_gelic_net.c45
-rw-r--r--drivers/net/ps3_gelic_net.h1
-rwxr-xr-xdrivers/net/qla3xxx.c29
-rwxr-xr-xdrivers/net/qla3xxx.h2
-rw-r--r--drivers/net/r8169.c58
-rw-r--r--drivers/net/s2io.c35
-rw-r--r--drivers/net/s2io.h3
-rw-r--r--drivers/net/sb1250-mac.c47
-rw-r--r--drivers/net/sis190.c19
-rw-r--r--drivers/net/skge.c44
-rw-r--r--drivers/net/skge.h1
-rw-r--r--drivers/net/sky2.c94
-rw-r--r--drivers/net/sky2.h1
-rw-r--r--drivers/net/spider_net.c60
-rw-r--r--drivers/net/spider_net.h2
-rw-r--r--drivers/net/starfire.c51
-rw-r--r--drivers/net/sungem.c52
-rw-r--r--drivers/net/sungem.h1
-rw-r--r--drivers/net/tc35815.c49
-rw-r--r--drivers/net/tg3.c61
-rw-r--r--drivers/net/tg3.h1
-rw-r--r--drivers/net/tsi108_eth.c40
-rw-r--r--drivers/net/tulip/interrupt.c54
-rw-r--r--drivers/net/tulip/tulip.h3
-rw-r--r--drivers/net/tulip/tulip_core.c11
-rw-r--r--drivers/net/typhoon.c47
-rw-r--r--drivers/net/ucc_geth.c64
-rw-r--r--drivers/net/ucc_geth.h1
-rw-r--r--drivers/net/via-rhine.c42
-rw-r--r--drivers/net/xen-netfront.c33
-rw-r--r--include/linux/netdevice.h361
-rw-r--r--include/linux/netpoll.h55
-rw-r--r--net/core/dev.c180
-rw-r--r--net/core/net-sysfs.c15
-rw-r--r--net/core/netpoll.c39
-rw-r--r--net/core/rtnetlink.c6
-rw-r--r--net/sched/sch_generic.c12
91 files changed, 1758 insertions, 2375 deletions
diff --git a/Documentation/DocBook/kernel-api.tmpl b/Documentation/DocBook/kernel-api.tmpl
index b886f52a9aa..e5da4f2b7c2 100644
--- a/Documentation/DocBook/kernel-api.tmpl
+++ b/Documentation/DocBook/kernel-api.tmpl
@@ -240,17 +240,23 @@ X!Ilib/string.c
<sect1><title>Driver Support</title>
!Enet/core/dev.c
!Enet/ethernet/eth.c
+!Enet/sched/sch_generic.c
!Iinclude/linux/etherdevice.h
+!Iinclude/linux/netdevice.h
+ </sect1>
+ <sect1><title>PHY Support</title>
!Edrivers/net/phy/phy.c
!Idrivers/net/phy/phy.c
!Edrivers/net/phy/phy_device.c
!Idrivers/net/phy/phy_device.c
!Edrivers/net/phy/mdio_bus.c
!Idrivers/net/phy/mdio_bus.c
+ </sect1>
<!-- FIXME: Removed for now since no structured comments in source
+ <sect1><title>Wireless</title>
X!Enet/core/wireless.c
--->
</sect1>
+-->
<sect1><title>Synchronous PPP</title>
!Edrivers/net/wan/syncppp.c
</sect1>
diff --git a/Documentation/networking/NAPI_HOWTO.txt b/Documentation/networking/NAPI_HOWTO.txt
deleted file mode 100644
index 7907435a661..00000000000
--- a/Documentation/networking/NAPI_HOWTO.txt
+++ /dev/null
@@ -1,766 +0,0 @@
-HISTORY:
-February 16/2002 -- revision 0.2.1:
-COR typo corrected
-February 10/2002 -- revision 0.2:
-some spell checking ;->
-January 12/2002 -- revision 0.1
-This is still work in progress so may change.
-To keep up to date please watch this space.
-
-Introduction to NAPI
-====================
-
-NAPI is a proven (www.cyberus.ca/~hadi/usenix-paper.tgz) technique
-to improve network performance on Linux. For more details please
-read that paper.
-NAPI provides a "inherent mitigation" which is bound by system capacity
-as can be seen from the following data collected by Robert on Gigabit
-ethernet (e1000):
-
- Psize Ipps Tput Rxint Txint Done Ndone
- ---------------------------------------------------------------
- 60 890000 409362 17 27622 7 6823
- 128 758150 464364 21 9301 10 7738
- 256 445632 774646 42 15507 21 12906
- 512 232666 994445 241292 19147 241192 1062
- 1024 119061 1000003 872519 19258 872511 0
- 1440 85193 1000003 946576 19505 946569 0
-
-
-Legend:
-"Ipps" stands for input packets per second.
-"Tput" == packets out of total 1M that made it out.
-"txint" == transmit completion interrupts seen
-"Done" == The number of times that the poll() managed to pull all
-packets out of the rx ring. Note from this that the lower the
-load the more we could clean up the rxring
-"Ndone" == is the converse of "Done". Note again, that the higher
-the load the more times we couldn't clean up the rxring.
-
-Observe that:
-when the NIC receives 890Kpackets/sec only 17 rx interrupts are generated.
-The system cant handle the processing at 1 interrupt/packet at that load level.
-At lower rates on the other hand, rx interrupts go up and therefore the
-interrupt/packet ratio goes up (as observable from that table). So there is
-possibility that under low enough input, you get one poll call for each
-input packet caused by a single interrupt each time. And if the system
-cant handle interrupt per packet ratio of 1, then it will just have to
-chug along ....
-
-
-0) Prerequisites:
-==================
-A driver MAY continue using the old 2.4 technique for interfacing
-to the network stack and not benefit from the NAPI changes.
-NAPI additions to the kernel do not break backward compatibility.
-NAPI, however, requires the following features to be available:
-
-A) DMA ring or enough RAM to store packets in software devices.
-
-B) Ability to turn off interrupts or maybe events that send packets up
-the stack.
-
-NAPI processes packet events in what is known as dev->poll() method.
-Typically, only packet receive events are processed in dev->poll().
-The rest of the events MAY be processed by the regular interrupt handler
-to reduce processing latency (justified also because there are not that
-many of them).
-Note, however, NAPI does not enforce that dev->poll() only processes
-receive events.
-Tests with the tulip driver indicated slightly increased latency if
-all of the interrupt handler is moved to dev->poll(). Also MII handling
-gets a little trickier.
-The example used in this document is to move the receive processing only
-to dev->poll(); this is shown with the patch for the tulip driver.
-For an example of code that moves all the interrupt driver to
-dev->poll() look at the ported e1000 code.
-
-There are caveats that might force you to go with moving everything to
-dev->poll(). Different NICs work differently depending on their status/event
-acknowledgement setup.
-There are two types of event register ACK mechanisms.
- I) what is known as Clear-on-read (COR).
- when you read the status/event register, it clears everything!
- The natsemi and sunbmac NICs are known to do this.
- In this case your only choice is to move all to dev->poll()
-
- II) Clear-on-write (COW)
- i) you clear the status by writing a 1 in the bit-location you want.
- These are the majority of the NICs and work the best with NAPI.
- Put only receive events in dev->poll(); leave the rest in
- the old interrupt handler.
- ii) whatever you write in the status register clears every thing ;->
- Cant seem to find any supported by Linux which do this. If
- someone knows such a chip email us please.
- Move all to dev->poll()
-
-C) Ability to detect new work correctly.
-NAPI works by shutting down event interrupts when there's work and
-turning them on when there's none.
-New packets might show up in the small window while interrupts were being
-re-enabled (refer to appendix 2). A packet might sneak in during the period
-we are enabling interrupts. We only get to know about such a packet when the
-next new packet arrives and generates an interrupt.
-Essentially, there is a small window of opportunity for a race condition
-which for clarity we'll refer to as the "rotting packet".
-
-This is a very important topic and appendix 2 is dedicated for more
-discussion.
-
-Locking rules and environmental guarantees
-==========================================
-
--Guarantee: Only one CPU at any time can call dev->poll(); this is because
-only one CPU can pick the initial interrupt and hence the initial
-netif_rx_schedule(dev);
-- The core layer invokes devices to send packets in a round robin format.
-This implies receive is totally lockless because of the guarantee that only
-one CPU is executing it.
-- contention can only be the result of some other CPU accessing the rx
-ring. This happens only in close() and suspend() (when these methods
-try to clean the rx ring);
-****guarantee: driver authors need not worry about this; synchronization
-is taken care for them by the top net layer.
--local interrupts are enabled (if you dont move all to dev->poll()). For
-example link/MII and txcomplete continue functioning just same old way.
-This improves the latency of processing these events. It is also assumed that
-the receive interrupt is the largest cause of noise. Note this might not
-always be true.
-[according to Manfred Spraul, the winbond insists on sending one
-txmitcomplete interrupt for each packet (although this can be mitigated)].
-For these broken drivers, move all to dev->poll().
-
-For the rest of this text, we'll assume that dev->poll() only
-processes receive events.
-
-new methods introduce by NAPI
-=============================
-
-a) netif_rx_schedule(dev)
-Called by an IRQ handler to schedule a poll for device
-
-b) netif_rx_schedule_prep(dev)
-puts the device in a state which allows for it to be added to the
-CPU polling list if it is up and running. You can look at this as
-the first half of netif_rx_schedule(dev) above; the second half
-being c) below.
-
-c) __netif_rx_schedule(dev)
-Add device to the poll list for this CPU; assuming that _prep above
-has already been called and returned 1.
-
-d) netif_rx_reschedule(dev, undo)
-Called to reschedule polling for device specifically for some
-deficient hardware. Read Appendix 2 for more details.
-
-e) netif_rx_complete(dev)
-
-Remove interface from the CPU poll list: it must be in the poll list
-on current cpu. This primitive is called by dev->poll(), when
-it completes its work. The device cannot be out of poll list at this
-call, if it is then clearly it is a BUG(). You'll know ;->
-
-All of the above methods are used below, so keep reading for clarity.
-
-Device driver changes to be made when porting NAPI
-==================================================
-
-Below we describe what kind of changes are required for NAPI to work.
-
-1) introduction of dev->poll() method
-=====================================
-
-This is the method that is invoked by the network core when it requests
-for new packets from the driver. A driver is allowed to send upto
-dev->quota packets by the current CPU before yielding to the network
-subsystem (so other devices can also get opportunity to send to the stack).
-
-dev->poll() prototype looks as follows:
-int my_poll(struct net_device *dev, int *budget)
-
-budget is the remaining number of packets the network subsystem on the
-current CPU can send up the stack before yielding to other system tasks.
-*Each driver is responsible for decrementing budget by the total number of
-packets sent.
- Total number of packets cannot exceed dev->quota.
-
-dev->poll() method is invoked by the top layer, the driver just sends if it
-can to the stack the packet quantity requested.
-
-more on dev->poll() below after the interrupt changes are explained.
-
-2) registering dev->poll() method
-===================================
-
-dev->poll should be set in the dev->probe() method.
-e.g:
-dev->open = my_open;
-.
-.
-/* two new additions */
-/* first register my poll method */
-dev->poll = my_poll;
-/* next register my weight/quanta; can be overridden in /proc */
-dev->weight = 16;
-.
-.
-dev->stop = my_close;
-
-
-
-3) scheduling dev->poll()
-=============================
-This involves modifying the interrupt handler and the code
-path which takes the packet off the NIC and sends them to the
-stack.
-
-it's important at this point to introduce the classical D Becker
-interrupt processor:
-
-------------------
-static irqreturn_t
-netdevice_interrupt(int irq, void *dev_id, struct pt_regs *regs)
-{
-
- struct net_device *dev = (struct net_device *)dev_instance;
- struct my_private *tp = (struct my_private *)dev->priv;
-
- int work_count = my_work_count;
- status = read_interrupt_status_reg();
- if (status == 0)
- return IRQ_NONE; /* Shared IRQ: not us */
- if (status == 0xffff)
- return IRQ_HANDLED; /* Hot unplug */
- if (status & error)
- do_some_error_handling()
-
- do {
- acknowledge_ints_ASAP();
-
- if (status & link_interrupt) {
- spin_lock(&tp->link_lock);
- do_some_link_stat_stuff();
- spin_lock(&tp->link_lock);
- }
-
- if (status & rx_interrupt) {
- receive_packets(dev);
- }
-
- if (status & rx_nobufs) {
- make_rx_buffs_avail();
- }
-
- if (status & tx_related) {
- spin_lock(&tp->lock);
- tx_ring_free(dev);
- if (tx_died)
- restart_tx();