Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net

Documentation/kernel-parameters.txt

@@ -2680,6 +2680,27 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	vmpoff=		[KNL,S390] Perform z/VM CP command after power off.
 			Format: <command>
 
+	vsyscall=	[X86-64]
+			Controls the behavior of vsyscalls (i.e. calls to
+			fixed addresses of 0xffffffffff600x00 from legacy
+			code).  Most statically-linked binaries and older
+			versions of glibc use these calls.  Because these
+			functions are at fixed addresses, they make nice
+			targets for exploits that can control RIP.
+
+			emulate     [default] Vsyscalls turn into traps and are
+			            emulated reasonably safely.
+
+			native      Vsyscalls are native syscall instructions.
+			            This is a little bit faster than trapping
+			            and makes a few dynamic recompilers work
+			            better than they would in emulation mode.
+			            It also makes exploits much easier to write.
+
+			none        Vsyscalls don't work at all.  This makes
+			            them quite hard to use for exploits but
+			            might break your system.
+
 	vt.cur_default=	[VT] Default cursor shape.
 			Format: 0xCCBBAA, where AA, BB, and CC are the same as
 			the parameters of the <Esc>[?A;B;Cc escape sequence;

Documentation/networking/00-INDEX

@@ -1,13 +1,21 @@
 00-INDEX
 	- this file
+3c359.txt
+	- information on the 3Com TokenLink Velocity XL (3c5359) driver.
 3c505.txt
 	- information on the 3Com EtherLink Plus (3c505) driver.
+3c509.txt
+	- information on the 3Com Etherlink III Series Ethernet cards.
 6pack.txt
 	- info on the 6pack protocol, an alternative to KISS for AX.25
 DLINK.txt
 	- info on the D-Link DE-600/DE-620 parallel port pocket adapters
 PLIP.txt
 	- PLIP: The Parallel Line Internet Protocol device driver
+README.ipw2100
+	- README for the Intel PRO/Wireless 2100 driver.
+README.ipw2200
+	- README for the Intel PRO/Wireless 2915ABG and 2200BG driver.
 README.sb1000
 	- info on General Instrument/NextLevel SURFboard1000 cable modem.
 alias.txt
@@ -20,8 +28,12 @@ atm.txt
 	- info on where to get ATM programs and support for Linux.
 ax25.txt
 	- info on using AX.25 and NET/ROM code for Linux
+batman-adv.txt
+	- B.A.T.M.A.N routing protocol on top of layer 2 Ethernet Frames.
 baycom.txt
 	- info on the driver for Baycom style amateur radio modems
+bonding.txt
+	- Linux Ethernet Bonding Driver HOWTO: link aggregation in Linux.
 bridge.txt
 	- where to get user space programs for ethernet bridging with Linux.
 can.txt
@@ -34,32 +46,60 @@ cxacru.txt
 	- Conexant AccessRunner USB ADSL Modem
 cxacru-cf.py
 	- Conexant AccessRunner USB ADSL Modem configuration file parser
+cxgb.txt
+	- Release Notes for the Chelsio N210 Linux device driver.
+dccp.txt
+	- the Datagram Congestion Control Protocol (DCCP) (RFC 4340..42).
 de4x5.txt
 	- the Digital EtherWORKS DE4?? and DE5?? PCI Ethernet driver
 decnet.txt
 	- info on using the DECnet networking layer in Linux.
 depca.txt
 	- the Digital DEPCA/EtherWORKS DE1?? and DE2?? LANCE Ethernet driver
+dl2k.txt
+	- README for D-Link DL2000-based Gigabit Ethernet Adapters (dl2k.ko).
+dm9000.txt
+	- README for the Simtec DM9000 Network driver.
 dmfe.txt
 	- info on the Davicom DM9102(A)/DM9132/DM9801 fast ethernet driver.
+dns_resolver.txt
+	- The DNS resolver module allows kernel servies to make DNS queries.
+driver.txt
+	- Softnet driver issues.
 e100.txt
 	- info on Intel's EtherExpress PRO/100 line of 10/100 boards
 e1000.txt
 	- info on Intel's E1000 line of gigabit ethernet boards
+e1000e.txt
+	- README for the Intel Gigabit Ethernet Driver (e1000e).
 eql.txt
 	- serial IP load balancing
 ewrk3.txt
 	- the Digital EtherWORKS 3 DE203/4/5 Ethernet driver
+fib_trie.txt
+	- Level Compressed Trie (LC-trie) notes: a structure for routing.
 filter.txt
 	- Linux Socket Filtering
 fore200e.txt
 	- FORE Systems PCA-200E/SBA-200E ATM NIC driver info.
 framerelay.txt
 	- info on using Frame Relay/Data Link Connection Identifier (DLCI).
+gen_stats.txt
+	- Generic networking statistics for netlink users.
+generic_hdlc.txt
+	- The generic High Level Data Link Control (HDLC) layer.
 generic_netlink.txt
 	- info on Generic Netlink
+gianfar.txt
+	- Gianfar Ethernet Driver.
 ieee802154.txt
 	- Linux IEEE 802.15.4 implementation, API and drivers
+ifenslave.c
+	- Configure network interfaces for parallel routing (bonding).
+igb.txt
+	- README for the Intel Gigabit Ethernet Driver (igb).
+igbvf.txt
+	- README for the Intel Gigabit Ethernet Driver (igbvf).
 ip-sysctl.txt
 	- /proc/sys/net/ipv4/* variables
 ip_dynaddr.txt
@@ -68,41 +108,117 @@ ipddp.txt
 	- AppleTalk-IP Decapsulation and AppleTalk-IP Encapsulation
 iphase.txt
 	- Interphase PCI ATM (i)Chip IA Linux driver info.
+ipv6.txt
+	- Options to the ipv6 kernel module.
+ipvs-sysctl.txt
+	- Per-inode explanation of the /proc/sys/net/ipv4/vs interface.
 irda.txt
 	- where to get IrDA (infrared) utilities and info for Linux.
+ixgb.txt
+	- README for the Intel 10 Gigabit Ethernet Driver (ixgb).
+ixgbe.txt
+	- README for the Intel 10 Gigabit Ethernet Driver (ixgbe).
+ixgbevf.txt
+	- README for the Intel Virtual Function (VF) Driver (ixgbevf).
+l2tp.txt
+	- User guide to the L2TP tunnel protocol.
 lapb-module.txt
 	- programming information of the LAPB module.
 ltpc.txt
 	- the Apple or Farallon LocalTalk PC card driver
+mac80211-injection.txt
+	- HOWTO use packet injection with mac80211
 multicast.txt
 	- Behaviour of cards under Multicast
+multiqueue.txt
+	- HOWTO for multiqueue network device support.
+netconsole.txt
+	- The network console module netconsole.ko: configuration and notes.
+netdev-features.txt
+	- Network interface features API description.
 netdevices.txt
 	- info on network device driver functions exported to the kernel.
+netif-msg.txt
+	- Design of the network interface message level setting (NETIF_MSG_*).
+nfc.txt
+	- The Linux Near Field Communication (NFS) subsystem.
 olympic.txt
 	- IBM PCI Pit/Pit-Phy/Olympic Token Ring driver info.
+operstates.txt
+	- Overview of network interface operational states.
+packet_mmap.txt
+	- User guide to memory mapped packet socket rings (PACKET_[RT]X_RING).
+phonet.txt
+	- The Phonet packet protocol used in Nokia cellular modems.
+phy.txt
+	- The PHY abstraction layer.
+pktgen.txt
+	- User guide to the kernel packet generator (pktgen.ko).
 policy-routing.txt
 	- IP policy-based routing
+ppp_generic.txt
+	- Information about the generic PPP driver.
+proc_net_tcp.txt
+	- Per inode overview of the /proc/net/tcp and /proc/net/tcp6 interfaces.
+radiotap-headers.txt
+	- Background on radiotap headers.
 ray_cs.txt
 	- Raylink Wireless LAN card driver info.
+rds.txt
+	- Background on the reliable, ordered datagram delivery method RDS.
+regulatory.txt
+	- Overview of the Linux wireless regulatory infrastructure.
+rxrpc.txt
+	- Guide to the RxRPC protocol.
+s2io.txt
+	- Release notes for Neterion Xframe I/II 10GbE driver.
+scaling.txt
+	- Explanation of network scaling techniques: RSS, RPS, RFS, aRFS, XPS.
+sctp.txt
+	- Notes on the Linux kernel implementation of the SCTP protocol.
+secid.txt
+	- Explanation of the secid member in flow structures.
 skfp.txt
 	- SysKonnect FDDI (SK-5xxx, Compaq Netelligent) driver info.
 smc9.txt
 	- the driver for SMC's 9000 series of Ethernet cards
 smctr.txt
 	- SMC TokenCard TokenRing Linux driver info.
+spider-net.txt
+	- README for the Spidernet Driver (as found in PS3 / Cell BE).
+stmmac.txt
+	- README for the STMicro Synopsys Ethernet driver.
+tc-actions-env-rules.txt
+	- rules for traffic control (tc) actions.
+timestamping.txt
+	- overview of network packet timestamping variants.
 tcp.txt
 	- short blurb on how TCP output takes place.
+tcp-thin.txt
+	- kernel tuning options for low rate 'thin' TCP streams.
 tlan.txt
 	- ThunderLAN (Compaq Netelligent 10/100, Olicom OC-2xxx) driver info.
 tms380tr.txt
 	- SysKonnect Token Ring ISA/PCI adapter driver info.
+tproxy.txt
+	- Transparent proxy support user guide.
 tuntap.txt
 	- TUN/TAP device driver, allowing user space Rx/Tx of packets.
+udplite.txt
+	- UDP-Lite protocol (RFC 3828) introduction.
 vortex.txt
 	- info on using 3Com Vortex (3c590, 3c592, 3c595, 3c597) Ethernet cards.
+vxge.txt
+	- README for the Neterion X3100 PCIe Server Adapter.
 x25.txt
 	- general info on X.25 development.
 x25-iface.txt
 	- description of the X.25 Packet Layer to LAPB device interface.
+xfrm_proc.txt
+	- description of the statistics package for XFRM.
+xfrm_sync.txt
+	- sync patches for XFRM enable migration of an SA between hosts.
+xfrm_sysctl.txt
+	- description of the XFRM configuration options.
 z8530drv.txt
 	- info about Linux driver for Z8530 based HDLC cards for AX.25

Documentation/networking/scaling.txt

@@ -0,0 +1,378 @@
+Scaling in the Linux Networking Stack
+
+
+Introduction
+============
+
+This document describes a set of complementary techniques in the Linux
+networking stack to increase parallelism and improve performance for
+multi-processor systems.
+
+The following technologies are described:
+
+  RSS: Receive Side Scaling
+  RPS: Receive Packet Steering
+  RFS: Receive Flow Steering
+  Accelerated Receive Flow Steering
+  XPS: Transmit Packet Steering
+
+
+RSS: Receive Side Scaling
+=========================
+
+Contemporary NICs support multiple receive and transmit descriptor queues
+(multi-queue). On reception, a NIC can send different packets to different
+queues to distribute processing among CPUs. The NIC distributes packets by
+applying a filter to each packet that assigns it to one of a small number
+of logical flows. Packets for each flow are steered to a separate receive
+queue, which in turn can be processed by separate CPUs. This mechanism is
+generally known as “Receive-side Scaling” (RSS). The goal of RSS and
+the other scaling techniques to increase performance uniformly.
+Multi-queue distribution can also be used for traffic prioritization, but
+that is not the focus of these techniques.
+
+The filter used in RSS is typically a hash function over the network
+and/or transport layer headers-- for example, a 4-tuple hash over
+IP addresses and TCP ports of a packet. The most common hardware
+implementation of RSS uses a 128-entry indirection table where each entry
+stores a queue number. The receive queue for a packet is determined
+by masking out the low order seven bits of the computed hash for the
+packet (usually a Toeplitz hash), taking this number as a key into the
+indirection table and reading the corresponding value.
+
+Some advanced NICs allow steering packets to queues based on
+programmable filters. For example, webserver bound TCP port 80 packets
+can be directed to their own receive queue. Such “n-tuple” filters can
+be configured from ethtool (--config-ntuple).
+
+==== RSS Configuration
+
+The driver for a multi-queue capable NIC typically provides a kernel
+module parameter for specifying the number of hardware queues to
+configure. In the bnx2x driver, for instance, this parameter is called
+num_queues. A typical RSS configuration would be to have one receive queue
+for each CPU if the device supports enough queues, or otherwise at least
+one for each memory domain, where a memory domain is a set of CPUs that
+share a particular memory level (L1, L2, NUMA node, etc.).
+
+The indirection table of an RSS device, which resolves a queue by masked
+hash, is usually programmed by the driver at initialization. The
+default mapping is to distribute the queues evenly in the table, but the
+indirection table can be retrieved and modified at runtime using ethtool
+commands (--show-rxfh-indir and --set-rxfh-indir). Modifying the
+indirection table could be done to give different queues different
+relative weights.
+
+== RSS IRQ Configuration
+
+Each receive queue has a separate IRQ associated with it. The NIC triggers
+this to notify a CPU when new packets arrive on the given queue. The
+signaling path for PCIe devices uses message signaled interrupts (MSI-X),
+that can route each interrupt to a particular CPU. The active mapping
+of queues to IRQs can be determined from /proc/interrupts. By default,
+an IRQ may be handled on any CPU. Because a non-negligible part of packet
+processing takes place in receive interrupt handling, it is advantageous
+to spread receive interrupts between CPUs. To manually adjust the IRQ
+affinity of each interrupt see Documentation/IRQ-affinity. Some systems
+will be running irqbalance, a daemon that dynamically optimizes IRQ
+assignments and as a result may override any manual settings.
+
+== Suggested Configuration
+
+RSS should be enabled when latency is a concern or whenever receive
+interrupt processing forms a bottleneck. Spreading load between CPUs
+decreases queue length. For low latency networking, the optimal setting
+is to allocate as many queues as there are CPUs in the system (or the
+NIC maximum, if lower). The most efficient high-rate configuration
+is likely the one with the smallest number of receive queues where no
+receive queue overflows due to a saturated CPU, because in default
+mode with interrupt coalescing enabled, the aggregate number of
+interrupts (and thus work) grows with each additional queue.
+
+Per-cpu load can be observed using the mpstat utility, but note that on
+processors with hyperthreading (HT), each hyperthread is represented as
+a separate CPU. For interrupt handling, HT has shown no benefit in
+initial tests, so limit the number of queues to the number of CPU cores
+in the system.
+
+
+RPS: Receive Packet Steering
+============================
+
+Receive Packet Steering (RPS) is logically a software implementation of
+RSS. Being in software, it is necessarily called later in the datapath.
+Whereas RSS selects the queue and hence CPU that will run the hardware
+interrupt handler, RPS selects the CPU to perform protocol processing
+above the interrupt handler. This is accomplished by placing the packet
+on the desired CPU’s backlog queue and waking up the CPU for processing.
+RPS has some advantages over RSS: 1) it can be used with any NIC,
+2) software filters can easily be added to hash over new protocols,
+3) it does not increase hardware device interrupt rate (although it does
+introduce inter-processor interrupts (IPIs)).
+
+RPS is called during bottom half of the receive interrupt handler, when
+a driver sends a packet up the network stack with netif_rx() or
+netif_receive_skb(). These call the get_rps_cpu() function, which
+selects the queue that should process a packet.
+
+The first step in determining the target CPU for RPS is to calculate a
+flow hash over the packet’s addresses or ports (2-tuple or 4-tuple hash
+depending on the protocol). This serves as a consistent hash of the
+associated flow of the packet. The hash is either provided by hardware
+or will be computed in the stack. Capable hardware can pass the hash in
+the receive descriptor for the packet; this would usually be the same
+hash used for RSS (e.g. computed Toeplitz hash). The hash is saved in
+skb->rx_hash and can be used elsewhere in the stack as a hash of the
+packet’s flow.
+
+Each receive hardware queue has an associated list of CPUs to which
+RPS may enqueue packets for processing. For each received packet,
+an index into the list is computed from the flow hash modulo the size
+of the list. The indexed CPU is the target for processing the packet,
+and the packet is queued to the tail of that CPU’s backlog queue. At
+the end of the bottom half routine, IPIs are sent to any CPUs for which
+packets have been queued to their backlog queue. The IPI wakes backlog
+processing on the remote CPU, and any queued packets are then processed
+up the networking stack.
+
+==== RPS Configuration
+
+RPS requires a kernel compiled with the CONFIG_RPS kconfig symbol (on
+by default for SMP). Even when compiled in, RPS remains disabled until
+explicitly configured. The list of CPUs to which RPS may forward traffic
+can be configured for each receive queue using a sysfs file entry:
+
+ /sys/class/net/<dev>/queues/rx-<n>/rps_cpus
+
+This file implements a bitmap of CPUs. RPS is disabled when it is zero
+(the default), in which case packets are processed on the interrupting
+CPU. Documentation/IRQ-affinity.txt explains how CPUs are assigned to
+the bitmap.
+
+== Suggested Configuration
+
+For a single queue device, a typical RPS configuration would be to set
+the rps_cpus to the CPUs in the same memory domain of the interrupting
+CPU. If NUMA locality is not an issue, this could also be all CPUs in
+the system. At high interrupt rate, it might be wise to exclude the
+interrupting CPU from the map since that already performs much work.
+
+For a multi-queue system, if RSS is configured so that a hardware
+receive queue is mapped to each CPU, then RPS is probably redundant
+and unnecessary. If there are fewer hardware queues than CPUs, then
+RPS might be beneficial if the rps_cpus for each queue are the ones that
+share the same memory domain as the interrupting CPU for that queue.
+
+
+RFS: Receive Flow Steering
+==========================
+
+While RPS steers packets solely based on hash, and thus generally
+provides good load distribution, it does not take into account
+application locality. This is accomplished by Receive Flow Steering
+(RFS). The goal of RFS is to increase datacache hitrate by steering
+kernel processing of packets to the CPU where the application thread
+consuming the packet is running. RFS relies on the same RPS mechanisms
+to enqueue packets onto the backlog of another CPU and to wake up that
+CPU.
+
+In RFS, packets are not forwarded directly by the value of their hash,
+but the hash is used as index into a flow lookup table. This table maps
+flows to the CPUs where those flows are being processed. The flow hash
+(see RPS section above) is used to calculate the index into this table.
+The CPU recorded in each entry is the one which last processed the flow.
+If an entry does not hold a valid CPU, then packets mapped to that entry
+are steered using plain RPS. Multiple table entries may point to the
+same CPU. Indeed, with many flows and few CPUs, it is very likely that
+a single application thread handles flows with many different flow hashes.
+
+rps_sock_table is a global flow table that contains the *desired* CPU for
+flows: the CPU that is currently processing the flow in userspace. Each
+table value is a CPU index that is updated during calls to recvmsg and
+sendmsg (specifically, inet_recvmsg(), inet_sendmsg(), inet_sendpage()
+and tcp_splice_read()).
+
+When the scheduler moves a thread to a new CPU while it has outstanding
+receive packets on the old CPU, packets may arrive out of order. To
+avoid this, RFS uses a second flow table to track outstanding packets
+for each flow: rps_dev_flow_table is a table specific to each hardware
+receive queue of each device. Each table value stores a CPU index and a
+counter. The CPU index represents the *current* CPU onto which packets
+for this flow are enqueued for further kernel processing. Ideally, kernel
+and userspace processing occur on the same CPU, and hence the CPU index
+in both tables is identical. This is likely false if the scheduler has
+recently migrated a userspace thread while the kernel still has packets
+enqueued for kernel processing on the old CPU.
+
+The counter in rps_dev_flow_table values records the length of the current
+CPU's backlog when a packet in this flow was last enqueued. Each backlog
+queue has a head counter that is incremented on dequeue. A tail counter
+is computed as head counter + queue length. In other words, the counter
+in rps_dev_flow_table[i] records the last element in flow i that has
+been enqueued onto the currently designated CPU for flow i (of course,
+entry i is actually selected by hash and multiple flows may hash to the
+same entry i).
+
+And now the trick for avoiding out of order packets: when selecting the
+CPU for packet processing (from get_rps_cpu()) the rps_sock_flow table
+and the rps_dev_flow table of the queue that the packet was received on
+are compared. If the desired CPU for the flow (found in the
+rps_sock_flow table) matches the current CPU (found in the rps_dev_flow
+table), the packet is enqueued onto that CPU’s backlog. If they differ,
+the current CPU is updated to match the desired CPU if one of the
+following is true:
+
+- The current CPU's queue head counter >= the recorded tail counter
+  value in rps_dev_flow[i]
+- The current CPU is unset (equal to NR_CPUS)
+- The current CPU is offline
+
+After this check, the packet is sent to the (possibly updated) current
+CPU. These rules aim to ensure that a flow only moves to a new CPU when
+there are no packets outstanding on the old CPU, as the outstanding
+packets could arrive later than those about to be processed on the new
+CPU.
+
+==== RFS Configuration
+
+RFS is only available if the kconfig symbol CONFIG_RFS is enabled (on
+by default for SMP). The functionality remains disabled until explicitly
+configured. The number of entries in the global flow table is set through:
+
+ /proc/sys/net/core/rps_sock_flow_entries
+
+The number of entries in the per-queue flow table are set through:
+
+ /sys/class/net/<dev>/queues/tx-<n>/rps_flow_cnt
+
+== Suggested Configuration
+
+Both of these need to be set before RFS is enabled for a receive queue.
+Values for both are rounded up to the nearest power of two. The
+suggested flow count depends on the expected number of active connections
+at any given time, which may be significantly less than the number of open
+connections. We have found that a value of 32768 for rps_sock_flow_entries
+works fairly well on a moderately loaded server.
+
+For a single queue device, the rps_flow_cnt value for the single queue
+would normally be configured to the same value as rps_sock_flow_entries.
+For a multi-queue device, the rps_flow_cnt for each queue might be
+configured as rps_sock_flow_entries / N, where N is the number of
+queues. So for instance, if rps_flow_entries is set to 32768 and there
+are 16 configured receive queues, rps_flow_cnt for each queue might be
+configured as 2048.
+
+
+Accelerated RFS
+===============
+
+Accelerated RFS is to RFS what RSS is to RPS: a hardware-accelerated load
+balancing mechanism that uses soft state to steer flows based on where
+the application thread consuming the packets of each flow is running.
+Accelerated RFS should perform better than RFS since packets are sent
+directly to a CPU local to the thread consuming the data. The target CPU
+will either be the same CPU where the application runs, or at least a CPU
+which is local to the application thread’s CPU in the cache hierarchy.
+
+To enable accelerated RFS, the networking stack calls the
+ndo_rx_flow_steer driver function to communicate the desired hardware
+queue for packets matching a particular flow. The network stack
+automatically calls this function every time a flow entry in
+rps_dev_flow_table is updated. The driver in turn uses a device specific
+method to program the NIC to steer the packets.
+
+The hardware queue for a flow is derived from the CPU recorded in
+rps_dev_flow_table. The stack consults a CPU to hardware queue map which
+is maintained by the NIC driver. This is an auto-generated reverse map of
+the IRQ affinity table shown by /proc/interrupts. Drivers can use
+functions in the cpu_rmap (“CPU affinity reverse map”) kernel library
+to populate the map. For each CPU, the corresponding queue in the map is
+set to be one whose processing CPU is closest in cache locality.
+
+==== Accelerated RFS Configuration
+
+Accelerated RFS is only available if the kernel is compiled with
+CONFIG_RFS_ACCEL and support is provided by the NIC device and driver.
+It also requires that ntuple filtering is enabled via ethtool. The map
+of CPU to queues is automatically deduced from the IRQ affinities
+configured for each receive queue by the driver, so no additional
+configuration should be necessary.
+
+== Suggested Configuration
+
+This technique should be enabled whenever one wants to use RFS and the
+NIC supports hardware acceleration.
+
+XPS: Transmit Packet Steering
+=============================
+
+Transmit Packet Steering is a mechanism for intelligently selecting
+which transmit queue to use when transmitting a packet on a multi-queue
+device. To accomplish this, a mapping from CPU to hardware queue(s) is
+recorded. The goal of this mapping is usually to assign queues
+exclusively to a subset of CPUs, where the transmit completions for
+these queues are processed on a CPU within this set. This choice
+provides two benefits. First, contention on the device queue lock is
+significantly reduced since fewer CPUs contend for the same queue
+(contention can be eliminated completely if each CPU has its own
+transmit queue). Secondly, cache miss rate on transmit completion is
+reduced, in particular for data cache lines that hold the sk_buff
+structures.
+
+XPS is configured per transmit queue by setting a bitmap of CPUs that
+may use that queue to transmit. The reverse mapping, from CPUs to
+transmit queues, is computed and maintained for each network device.
+When transmitting the first packet in a flow, the function
+get_xps_queue() is called to select a queue. This function uses the ID
+of the running CPU as a key into the CPU-to-queue lookup table. If the
+ID matches a single queue, that is used for transmission. If multiple
+queues match, one is selected by using the flow hash to compute an index
+into the set.
+
+The queue chosen for transmitting a particular flow is saved in the
+corresponding socket structure for the flow (e.g. a TCP connection).
+This transmit queue is used for subsequent packets sent on the flow to
+prevent out of order (ooo) packets. The choice also amortizes the cost
+of calling get_xps_queues() over all packets in the flow. To avoid
+ooo packets, the queue for a flow can subsequently only be changed if
+skb->ooo_okay is set for a packet in the flow. This flag indicates that
+there are no outstanding packets in the flow, so the transmit queue can
+change without the risk of generating out of order packets. The
+transport layer is responsible for setting ooo_okay appropriately. TCP,
+for instance, sets the flag when all data for a connection has been
+acknowledged.
+
+==== XPS Configuration
+
+XPS is only available if the kconfig symbol CONFIG_XPS is enabled (on by
+default for SMP). The functionality remains disabled until explicitly
+configured. To enable XPS, the bitmap of CPUs that may use a transmit
+queue is configured using the sysfs file entry:
+
+/sys/class/net/<dev>/queues/tx-<n>/xps_cpus
+
+== Suggested Configuration
+
+For a network device with a single transmission queue, XPS configuration
+has no effect, since there is no choice in this case. In a multi-queue
+system, XPS is preferably configured so that each CPU maps onto one queue.
+If there are as many queues as there are CPUs in the system, then each
+queue can also map onto one CPU, resulting in exclusive pairings that
+experience no contention. If there are fewer queues than CPUs, then the
+best CPUs to share a given queue are probably those that share the cache
+with the CPU that processes transmit completions for that queue
+(transmit interrupts).
+
+
+Further Information
+===================
+RPS and RFS were introduced in kernel 2.6.35. XPS was incorporated into
+2.6.38. Original patches were submitted by Tom Herbert
+(therbert@google.com)
+
+Accelerated RFS was introduced in 2.6.35. Original patches were
+submitted by Ben Hutchings (bhutchings@solarflare.com)
+
+Authors:
+Tom Herbert (therbert@google.com)
+Willem de Bruijn (willemb@google.com)

MAINTAINERS

@@ -3898,9 +3898,9 @@ F:	arch/powerpc/platforms/powermac/
 F:	drivers/macintosh/
 
 LINUX FOR POWERPC EMBEDDED MPC5XXX
-M:	Grant Likely <grant.likely@secretlab.ca>
+M:	Anatolij Gustschin <agust@denx.de>
 L:	linuxppc-dev@lists.ozlabs.org
-T:	git git://git.secretlab.ca/git/linux-2.6.git
+T:	git git://git.denx.de/linux-2.6-agust.git
 S:	Maintained
 F:	arch/powerpc/platforms/512x/
 F:	arch/powerpc/platforms/52xx/
@@ -7351,7 +7351,7 @@ THE REST
 M:	Linus Torvalds <torvalds@linux-foundation.org>
 L:	linux-kernel@vger.kernel.org
 Q:	http://patchwork.kernel.org/project/LKML/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
 S:	Buried alive in reporters
 F:	*
 F:	*/

Makefile

@@ -1,7 +1,7 @@
 VERSION = 3
-PATCHLEVEL = 0
+PATCHLEVEL = 1
 SUBLEVEL = 0
-EXTRAVERSION =
+EXTRAVERSION = -rc1
 NAME = Sneaky Weasel
 
 # *DOCUMENTATION*

arch/arm/Kconfig

@@ -195,8 +195,7 @@ config VECTORS_BASE
 	  The base address of exception vectors.
 
 config ARM_PATCH_PHYS_VIRT
-	bool "Patch physical to virtual translations at runtime (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	bool "Patch physical to virtual translations at runtime"
 	depends on !XIP_KERNEL && MMU
 	depends on !ARCH_REALVIEW || !SPARSEMEM
 	help

arch/arm/kernel/iwmmxt.S

@@ -195,10 +195,10 @@ ENTRY(iwmmxt_task_disable)
 
 	@ enable access to CP0 and CP1
 	XSC(mrc	p15, 0, r4, c15, c1, 0)
-	XSC(orr	r4, r4, #0xf)
+	XSC(orr	r4, r4, #0x3)
 	XSC(mcr	p15, 0, r4, c15, c1, 0)
 	PJ4(mrc p15, 0, r4, c1, c0, 2)
-	PJ4(orr	r4, r4, #0x3)
+	PJ4(orr	r4, r4, #0xf)
 	PJ4(mcr	p15, 0, r4, c1, c0, 2)
 
 	mov	r0, #0				@ nothing to load
@@ -313,7 +313,7 @@ ENTRY(iwmmxt_task_switch)
 	teq	r2, r3				@ next task owns it?
 	movne	pc, lr				@ no: leave Concan disabled
 
-1:	@ flip Conan access
+1:	@ flip Concan access
 	XSC(eor	r1, r1, #0x3)
 	XSC(mcr	p15, 0, r1, c15, c1, 0)
 	PJ4(eor r1, r1, #0xf)

arch/arm/kernel/module.c

@@ -323,7 +323,11 @@ int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs,
 #endif
 	s = find_mod_section(hdr, sechdrs, ".alt.smp.init");
 	if (s && !is_smp())
+#ifdef CONFIG_SMP_ON_UP
 		fixup_smp((void *)s->sh_addr, s->sh_size);
+#else
+		return -EINVAL;
+#endif
 	return 0;
 }
 

arch/arm/mach-imx/clock-imx25.c

@@ -331,6 +331,9 @@ int __init mx25_clocks_init(void)
 	__raw_writel(__raw_readl(CRM_BASE+0x64) | (1 << 7) | (1 << 0),
 			CRM_BASE + 0x64);
 
+	/* Clock source for gpt is ahb_div */
+	__raw_writel(__raw_readl(CRM_BASE+0x64) & ~(1 << 5), CRM_BASE + 0x64);
+
 	mxc_timer_init(&gpt_clk, MX25_IO_ADDRESS(MX25_GPT1_BASE_ADDR), 54);
 
 	return 0;

arch/arm/mach-imx/mach-imx27_visstrim_m10.c

@@ -30,6 +30,7 @@
 #include <linux/input.h>
 #include <linux/gpio.h>
 #include <linux/delay.h>
+#include <sound/tlv320aic32x4.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
@@ -196,6 +197,17 @@ static struct pca953x_platform_data visstrim_m10_pca9555_pdata = {
 	.invert = 0,
 };
 
+static struct aic32x4_pdata visstrim_m10_aic32x4_pdata = {
+	.power_cfg = AIC32X4_PWR_MICBIAS_2075_LDOIN |
+		     AIC32X4_PWR_AVDD_DVDD_WEAK_DISABLE |
+		     AIC32X4_PWR_AIC32X4_LDO_ENABLE |
+		     AIC32X4_PWR_CMMODE_LDOIN_RANGE_18_36 |
+		     AIC32X4_PWR_CMMODE_HP_LDOIN_POWERED,
+	.micpga_routing = AIC32X4_MICPGA_ROUTE_LMIC_IN2R_10K |
+			 AIC32X4_MICPGA_ROUTE_RMIC_IN1L_10K,
+	.swapdacs = false,
+};
+
 static struct i2c_board_info visstrim_m10_i2c_devices[] = {
 	{
 		I2C_BOARD_INFO("pca9555", 0x20),
@@ -203,6 +215,7 @@ static struct i2c_board_info visstrim_m10_i2c_devices[] = {
 	},
 	{
 		I2C_BOARD_INFO("tlv320aic32x4", 0x18),
+		.platform_data = &visstrim_m10_aic32x4_pdata,
 	}
 };
 

arch/arm/mach-imx/mach-mx31ads.c

@@ -468,7 +468,7 @@ static struct i2c_board_info __initdata mx31ads_i2c1_devices[] = {
 #endif
 };
 
-static void mxc_init_i2c(void)
+static void __init mxc_init_i2c(void)
 {
 	i2c_register_board_info(1, mx31ads_i2c1_devices,
 				ARRAY_SIZE(mx31ads_i2c1_devices));
@@ -486,7 +486,7 @@ static unsigned int ssi_pins[] = {
 	MX31_PIN_STXD5__STXD5,
 };
 
-static void mxc_init_audio(void)
+static void __init mxc_init_audio(void)
 {
 	imx31_add_imx_ssi(0, NULL);
 	mxc_iomux_setup_multiple_pins(ssi_pins, ARRAY_SIZE(ssi_pins), "ssi");

arch/arm/mach-imx/mach-mx31lilly.c

@@ -192,7 +192,7 @@ static struct mxc_usbh_platform_data usbh2_pdata __initdata = {
 	.portsc	= MXC_EHCI_MODE_ULPI | MXC_EHCI_UTMI_8BIT,
 };
 
-static void lilly1131_usb_init(void)
+static void __init lilly1131_usb_init(void)
 {
 	imx31_add_mxc_ehci_hs(1, &usbh1_pdata);
 

arch/arm/mach-mmp/gplugd.c

@@ -16,16 +16,18 @@
 #include <mach/gpio.h>
 #include <mach/pxa168.h>
 #include <mach/mfp-pxa168.h>
-#include <mach/mfp-gplugd.h>
 
 #include "common.h"
 
 static unsigned long gplugd_pin_config[] __initdata = {
 	/* UART3 */
-	GPIO8_UART3_SOUT,
-	GPIO9_UART3_SIN,
-	GPI1O_UART3_CTS,
-	GPI11_UART3_RTS,
+	GPIO8_UART3_TXD,
+	GPIO9_UART3_RXD,
+	GPIO1O_UART3_CTS,
+	GPIO11_UART3_RTS,
+
+	/* USB OTG PEN */
+	GPIO18_GPIO,
 
 	/* MMC2 */
 	GPIO28_MMC2_CMD,
@@ -109,6 +111,12 @@ static unsigned long gplugd_pin_config[] __initdata = {
 	GPIO105_CI2C_SDA,
 	GPIO106_CI2C_SCL,
 
+	/* SPI NOR Flash on SSP2 */
+	GPIO107_SSP2_RXD,
+	GPIO108_SSP2_TXD,
+	GPIO110_GPIO,     /* SPI_CSn */
+	GPIO111_SSP2_CLK,
+
 	/* Select JTAG */
 	GPIO109_GPIO,
 
@@ -154,7 +162,7 @@ static void __init select_disp_freq(void)
 				"frequency\n");
 	} else {
 		gpio_direction_output(35, 1);
-		gpio_free(104);
+		gpio_free(35);
 	}
 
 	if (unlikely(gpio_request(85, "DISP_FREQ_SEL_2"))) {
@@ -162,7 +170,7 @@ static void __init select_disp_freq(void)
 				"frequency\n");
 	} else {
 		gpio_direction_output(85, 0);
-		gpio_free(104);
+		gpio_free(85);
 	}
 }
 

arch/arm/mach-mmp/include/mach/mfp-gplugd.h

@@ -1,52 +0,0 @@
-/*
- * linux/arch/arm/mach-mmp/include/mach/mfp-gplugd.h
- *
- *   MFP definitions used in gplugD
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef __MACH_MFP_GPLUGD_H
-#define __MACH_MFP_GPLUGD_H
-
-#include <plat/mfp.h>
-#include <mach/mfp.h>
-
-/* UART3 */
-#define GPIO8_UART3_SOUT       MFP_CFG(GPIO8, AF2)
-#define GPIO9_UART3_SIN        MFP_CFG(GPIO9, AF2)
-#define GPI1O_UART3_CTS        MFP_CFG(GPIO10, AF2)
-#define GPI11_UART3_RTS        MFP_CFG(GPIO11, AF2)
-
-/* MMC2 */
-#define	GPIO28_MMC2_CMD		MFP_CFG_DRV(GPIO28, AF6, FAST)
-#define	GPIO29_MMC2_CLK		MFP_CFG_DRV(GPIO29, AF6, FAST)
-#define	GPIO30_MMC2_DAT0	MFP_CFG_DRV(GPIO30, AF6, FAST)
-#define	GPIO31_MMC2_DAT1	MFP_CFG_DRV(GPIO31, AF6, FAST)
-#define	GPIO32_MMC2_DAT2	MFP_CFG_DRV(GPIO32, AF6, FAST)
-#define	GPIO33_MMC2_DAT3	MFP_CFG_DRV(GPIO33, AF6, FAST)
-
-/* I2S */
-#undef GPIO114_I2S_FRM
-#undef GPIO115_I2S_BCLK
-
-#define GPIO114_I2S_FRM	        MFP_CFG_DRV(GPIO114, AF1, FAST)
-#define GPIO115_I2S_BCLK        MFP_CFG_DRV(GPIO115, AF1, FAST)
-#define GPIO116_I2S_TXD         MFP_CFG_DRV(GPIO116, AF1, FAST)
-
-/* MMC4 */
-#define GPIO125_MMC4_DAT3       MFP_CFG_DRV(GPIO125, AF7, FAST)
-#define GPIO126_MMC4_DAT2       MFP_CFG_DRV(GPIO126, AF7, FAST)
-#define GPIO127_MMC4_DAT1       MFP_CFG_DRV(GPIO127, AF7, FAST)
-#define GPIO0_2_MMC4_DAT0       MFP_CFG_DRV(GPIO0_2, AF7, FAST)
-#define GPIO1_2_MMC4_CMD        MFP_CFG_DRV(GPIO1_2, AF7, FAST)
-#define GPIO2_2_MMC4_CLK        MFP_CFG_DRV(GPIO2_2, AF7, FAST)
-
-/* OTG GPIO */
-#define GPIO_USB_OTG_PEN        18
-#define GPIO_USB_OIDIR          20
-
-/* Other GPIOs are 35, 84, 85 */
-#endif /* __MACH_MFP_GPLUGD_H */

arch/arm/mach-mmp/include/mach/mfp-pxa168.h

@@ -203,6 +203,10 @@
 #define GPIO33_CF_nCD2		MFP_CFG(GPIO33, AF3)
 
 /* UART */
+#define GPIO8_UART3_TXD		MFP_CFG(GPIO8, AF2)
+#define GPIO9_UART3_RXD		MFP_CFG(GPIO9, AF2)
+#define GPIO1O_UART3_CTS	MFP_CFG(GPIO10, AF2)
+#define GPIO11_UART3_RTS	MFP_CFG(GPIO11, AF2)
 #define GPIO88_UART2_TXD	MFP_CFG(GPIO88, AF2)
 #define GPIO89_UART2_RXD	MFP_CFG(GPIO89, AF2)
 #define GPIO107_UART1_TXD	MFP_CFG_DRV(GPIO107, AF1, FAST)
@@ -232,6 +236,22 @@
 #define GPIO53_MMC1_CD		MFP_CFG(GPIO53, AF1)
 #define GPIO46_MMC1_WP		MFP_CFG(GPIO46, AF1)
 
+/* MMC2 */
+#define	GPIO28_MMC2_CMD		MFP_CFG_DRV(GPIO28, AF6, FAST)
+#define	GPIO29_MMC2_CLK		MFP_CFG_DRV(GPIO29, AF6, FAST)
+#define	GPIO30_MMC2_DAT0	MFP_CFG_DRV(GPIO30, AF6, FAST)
+#define	GPIO31_MMC2_DAT1	MFP_CFG_DRV(GPIO31, AF6, FAST)
+#define	GPIO32_MMC2_DAT2	MFP_CFG_DRV(GPIO32, AF6, FAST)
+#define	GPIO33_MMC2_DAT3	MFP_CFG_DRV(GPIO33, AF6, FAST)
+
+/* MMC4 */
+#define GPIO125_MMC4_DAT3       MFP_CFG_DRV(GPIO125, AF7, FAST)
+#define GPIO126_MMC4_DAT2       MFP_CFG_DRV(GPIO126, AF7, FAST)
+#define GPIO127_MMC4_DAT1       MFP_CFG_DRV(GPIO127, AF7, FAST)
+#define GPIO0_2_MMC4_DAT0       MFP_CFG_DRV(GPIO0_2, AF7, FAST)
+#define GPIO1_2_MMC4_CMD        MFP_CFG_DRV(GPIO1_2, AF7, FAST)
+#define GPIO2_2_MMC4_CLK        MFP_CFG_DRV(GPIO2_2, AF7, FAST)
+
 /* LCD */
 #define GPIO84_LCD_CS		MFP_CFG(GPIO84, AF1)
 #define GPIO60_LCD_DD0		MFP_CFG(GPIO60, AF1)
@@ -269,11 +289,12 @@
 #define GPIO106_CI2C_SCL	MFP_CFG(GPIO106, AF1)
 
 /* I2S */
-#define GPIO113_I2S_MCLK	MFP_CFG(GPIO113,AF6)
-#define GPIO114_I2S_FRM		MFP_CFG(GPIO114,AF1)
-#define GPIO115_I2S_BCLK	MFP_CFG(GPIO115,AF1)
-#define GPIO116_I2S_RXD		MFP_CFG(GPIO116,AF2)
-#define GPIO117_I2S_TXD		MFP_CFG(GPIO117,AF2)
+#define GPIO113_I2S_MCLK	MFP_CFG(GPIO113, AF6)
+#define GPIO114_I2S_FRM		MFP_CFG(GPIO114, AF1)
+#define GPIO115_I2S_BCLK	MFP_CFG(GPIO115, AF1)
+#define GPIO116_I2S_RXD		MFP_CFG(GPIO116, AF2)
+#define GPIO116_I2S_TXD         MFP_CFG(GPIO116, AF1)
+#define GPIO117_I2S_TXD		MFP_CFG(GPIO117, AF2)
 
 /* PWM */
 #define GPIO96_PWM3_OUT		MFP_CFG(GPIO96, AF1)
@@ -324,4 +345,10 @@
 #define GPIO101_MII_MDIO	MFP_CFG(GPIO101, AF5)
 #define GPIO103_RX_DV		MFP_CFG(GPIO103, AF5)
 
+/* SSP2 */
+#define GPIO107_SSP2_RXD	MFP_CFG(GPIO107, AF4)
+#define GPIO108_SSP2_TXD	MFP_CFG(GPIO108, AF4)
+#define GPIO111_SSP2_CLK	MFP_CFG(GPIO111, AF4)
+#define GPIO112_SSP2_FRM	MFP_CFG(GPIO112, AF4)
+
 #endif /* __ASM_MACH_MFP_PXA168_H */

arch/arm/mach-mmp/time.c

@@ -51,12 +51,12 @@ static inline uint32_t timer_read(void)
 {
 	int delay = 100;
 
-	__raw_writel(1, TIMERS_VIRT_BASE + TMR_CVWR(0));
+	__raw_writel(1, TIMERS_VIRT_BASE + TMR_CVWR(1));
 
 	while (delay--)
 		cpu_relax();
 
-	return __raw_readl(TIMERS_VIRT_BASE + TMR_CVWR(0));
+	return __raw_readl(TIMERS_VIRT_BASE + TMR_CVWR(1));
 }
 
 unsigned long long notrace sched_clock(void)
@@ -75,28 +75,51 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id)
 {
 	struct clock_event_device *c = dev_id;
 
-	/* disable and clear pending interrupt status */
-	__raw_writel(0x0, TIMERS_VIRT_BASE + TMR_IER(0));
-	__raw_writel(0x1, TIMERS_VIRT_BASE + TMR_ICR(0));
+	/*
+	 * Clear pending interrupt status.
+	 */
+	__raw_writel(0x01, TIMERS_VIRT_BASE + TMR_ICR(0));
+
+	/*
+	 * Disable timer 0.
+	 */
+	__raw_writel(0x02, TIMERS_VIRT_BASE + TMR_CER);
+
 	c->event_handler(c);
+
 	return IRQ_HANDLED;
 }
 
 static int timer_set_next_event(unsigned long delta,
 				struct clock_event_device *dev)
 {
-	unsigned long flags, next;
+	unsigned long flags;
 
 	local_irq_save(flags);
 
-	/* clear pending interrupt status and enable */
+	/*
+	 * Disable timer 0.
+	 */
+	__raw_writel(0x02, TIMERS_VIRT_BASE + TMR_CER);
+
+	/*
+	 * Clear and enable timer match 0 interrupt.
+	 */
 	__raw_writel(0x01, TIMERS_VIRT_BASE + TMR_ICR(0));
 	__raw_writel(0x01, TIMERS_VIRT_BASE + TMR_IER(0));
 
-	next = timer_read() + delta;
-	__raw_writel(next, TIMERS_VIRT_BASE + TMR_TN_MM(0, 0));
+	/*
+	 * Setup new clockevent timer value.
+	 */
+	__raw_writel(delta - 1, TIMERS_VIRT_BASE + TMR_TN_MM(0, 0));
+
+	/*
+	 * Enable timer 0.
+	 */
+	__raw_writel(0x03, TIMERS_VIRT_BASE + TMR_CER);
 
 	local_irq_restore(flags);
+
 	return 0;
 }
 
@@ -145,23 +168,26 @@ static struct clocksource cksrc = {
 static void __init timer_config(void)
 {
 	uint32_t ccr = __raw_readl(TIMERS_VIRT_BASE + TMR_CCR);
-	uint32_t cer = __raw_readl(TIMERS_VIRT_BASE + TMR_CER);
-	uint32_t cmr = __raw_readl(TIMERS_VIRT_BASE + TMR_CMR);
 
-	__raw_writel(cer & ~0x1, TIMERS_VIRT_BASE + TMR_CER); /* disable */
+	__raw_writel(0x0, TIMERS_VIRT_BASE + TMR_CER); /* disable */
 
-	ccr &= (cpu_is_mmp2()) ? TMR_CCR_CS_0(0) : TMR_CCR_CS_0(3);
+	ccr &= (cpu_is_mmp2()) ? (TMR_CCR_CS_0(0) | TMR_CCR_CS_1(0)) :
+		(TMR_CCR_CS_0(3) | TMR_CCR_CS_1(3));
 	__raw_writel(ccr, TIMERS_VIRT_BASE + TMR_CCR);
 
-	/* free-running mode */
-	__raw_writel(cmr | 0x01, TIMERS_VIRT_BASE + TMR_CMR);
+	/* set timer 0 to periodic mode, and timer 1 to free-running mode */
+	__raw_writel(0x2, TIMERS_VIRT_BASE + TMR_CMR);
 
-	__raw_writel(0x0, TIMERS_VIRT_BASE + TMR_PLCR(0)); /* free-running */
+	__raw_writel(0x1, TIMERS_VIRT_BASE + TMR_PLCR(0)); /* periodic */
 	__raw_writel(0x7, TIMERS_VIRT_BASE + TMR_ICR(0));  /* clear status */
 	__raw_writel(0x0, TIMERS_VIRT_BASE + TMR_IER(0));
 
-	/* enable timer counter */
-	__raw_writel(cer | 0x01, TIMERS_VIRT_BASE + TMR_CER);
+	__raw_writel(0x0, TIMERS_VIRT_BASE + TMR_PLCR(1)); /* free-running */
+	__raw_writel(0x7, TIMERS_VIRT_BASE + TMR_ICR(1));  /* clear status */
+	__raw_writel(0x0, TIMERS_VIRT_BASE + TMR_IER(1));
+
+	/* enable timer 1 counter */
+	__raw_writel(0x2, TIMERS_VIRT_BASE + TMR_CER);
 }
 
 static struct irqaction timer_irq = {

arch/arm/mach-mx5/board-cpuimx51.c

@@ -81,7 +81,7 @@ static struct plat_serial8250_port serial_platform_data[] = {
 		.flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_IOREMAP,
 	}, {
 		.mapbase = (unsigned long)(MX51_CS1_BASE_ADDR + 0x2000000),
-		.irq = irq_to_gpio(CPUIMX51_QUARTD_GPIO),
+		.irq = gpio_to_irq(CPUIMX51_QUARTD_GPIO),
 		.irqflags = IRQF_TRIGGER_HIGH,
 		.uartclk = CPUIMX51_QUART_XTAL,
 		.regshift = CPUIMX51_QUART_REGSHIFT,

arch/arm/mach-mx5/board-mx51_babbage.c

@@ -369,7 +369,7 @@ static void __init mx51_babbage_init(void)
 					ARRAY_SIZE(mx51babbage_pads));
 
 	imx51_add_imx_uart(0, &uart_pdata);
-	imx51_add_imx_uart(1, &uart_pdata);
+	imx51_add_imx_uart(1, NULL);
 	imx51_add_imx_uart(2, &uart_pdata);
 
 	babbage_fec_reset();

arch/arm/mach-mx5/board-mx51_efikamx.c

@@ -108,9 +108,9 @@ static void __init mx51_efikamx_board_id(void)
 	gpio_request(EFIKAMX_PCBID2, "pcbid2");
 	gpio_direction_input(EFIKAMX_PCBID2);
 
-	id = gpio_get_value(EFIKAMX_PCBID0);
-	id |= gpio_get_value(EFIKAMX_PCBID1) << 1;
-	id |= gpio_get_value(EFIKAMX_PCBID2) << 2;
+	id = gpio_get_value(EFIKAMX_PCBID0) ? 1 : 0;
+	id |= (gpio_get_value(EFIKAMX_PCBID1) ? 1 : 0) << 1;
+	id |= (gpio_get_value(EFIKAMX_PCBID2) ? 1 : 0) << 2;
 
 	switch (id) {
 	case 7:

arch/arm/mach-mx5/board-mx51_efikasb.c

@@ -156,23 +156,24 @@ static struct gpio_keys_button mx51_efikasb_keys[] = {
 	{
 		.code = KEY_POWER,
 		.gpio = EFIKASB_PWRKEY,
-		.type = EV_PWR,
+		.type = EV_KEY,
 		.desc = "Power Button",
 		.wakeup = 1,
-		.debounce_interval = 10, /* ms */
+		.active_low = 1,
 	},
 	{
 		.code = SW_LID,
 		.gpio = EFIKASB_LID,
 		.type = EV_SW,
 		.desc = "Lid Switch",
+		.active_low = 1,
 	},
 	{
-		/* SW_RFKILLALL vs KEY_RFKILL ? */
-		.code = SW_RFKILL_ALL,
+		.code = KEY_RFKILL,
 		.gpio = EFIKASB_RFKILL,
-		.type = EV_SW,
+		.type = EV_KEY,
 		.desc = "rfkill",
+		.active_low = 1,
 	},
 };
 
@@ -224,8 +225,8 @@ static void __init mx51_efikasb_board_id(void)
 	gpio_request(EFIKASB_PCBID1, "pcb id1");
 	gpio_direction_input(EFIKASB_PCBID1);
 
-	id = gpio_get_value(EFIKASB_PCBID0);
-	id |= gpio_get_value(EFIKASB_PCBID1) << 1;
+	id = gpio_get_value(EFIKASB_PCBID0) ? 1 : 0;
+	id |= (gpio_get_value(EFIKASB_PCBID1) ? 1 : 0) << 1;
 
 	switch (id) {
 	default:

arch/arm/mach-mx5/clock-mx51-mx53.c

@@ -271,7 +271,11 @@ static int _clk_pll_enable(struct clk *clk)
 	int i = 0;
 
 	pllbase = _get_pll_base(clk);
-	reg = __raw_readl(pllbase + MXC_PLL_DP_CTL) | MXC_PLL_DP_CTL_UPEN;
+	reg = __raw_readl(pllbase + MXC_PLL_DP_CTL);
+	if (reg & MXC_PLL_DP_CTL_UPEN)
+		return 0;
+
+	reg |= MXC_PLL_DP_CTL_UPEN;
 	__raw_writel(reg, pllbase + MXC_PLL_DP_CTL);
 
 	/* Wait for lock */

arch/arm/mach-mx5/mx51_efika.c

@@ -186,7 +186,7 @@ static int initialize_usbh1_port(struct platform_device *pdev)
 
 	mdelay(10);
 
-	return mx51_initialize_usb_hw(0, MXC_EHCI_ITC_NO_THRESHOLD);
+	return mx51_initialize_usb_hw(pdev->id, MXC_EHCI_ITC_NO_THRESHOLD);
 }
 
 static struct mxc_usbh_platform_data usbh1_config = {

arch/arm/mach-omap2/Kconfig

@@ -7,7 +7,6 @@ config ARCH_OMAP2PLUS_TYPICAL
 	default y
 	select AEABI
 	select REGULATOR
-	select PM
 	select PM_RUNTIME
 	select VFP
 	select NEON if ARCH_OMAP3 || ARCH_OMAP4

arch/arm/mach-omap2/board-am3517crane.c

@@ -45,8 +45,6 @@ static struct omap_board_config_kernel am3517_crane_config[] __initdata = {
 static struct omap_board_mux board_mux[] __initdata = {
 	{ .reg_offset = OMAP_MUX_TERMINATOR },
 };
-#else
-#define board_mux	NULL
 #endif
 
 static void __init am3517_crane_init_early(void)

arch/arm/mach-omap2/board-omap3beagle.c

@@ -491,23 +491,22 @@ static void __init beagle_opp_init(void)
 
 	/* Custom OPP enabled for all xM versions */
 	if (cpu_is_omap3630()) {
-		struct omap_hwmod *mh = omap_hwmod_lookup("mpu");
-		struct omap_hwmod *dh = omap_hwmod_lookup("iva");
-		struct device *dev;
+		struct device *mpu_dev, *iva_dev;
 
-		if (!mh || !dh) {
+		mpu_dev = omap2_get_mpuss_device();
+		iva_dev = omap2_get_iva_device();
+
+		if (!mpu_dev || !iva_dev) {
 			pr_err("%s: Aiee.. no mpu/dsp devices? %p %p\n",
-				__func__, mh, dh);
+				__func__, mpu_dev, iva_dev);
 			return;
 		}
 		/* Enable MPU 1GHz and lower opps */
-		dev = &mh->od->pdev.dev;
-		r = opp_enable(dev, 800000000);
+		r = opp_enable(mpu_dev, 800000000);
 		/* TODO: MPU 1GHz needs SR and ABB */
 
 		/* Enable IVA 800MHz and lower opps */
-		dev = &dh->od->pdev.dev;
-		r |= opp_enable(dev, 660000000);
+		r |= opp_enable(iva_dev, 660000000);
 		/* TODO: DSP 800MHz needs SR and ABB */
 		if (r) {
 			pr_err("%s: failed to enable higher opp %d\n",
@@ -516,10 +515,8 @@ static void __init beagle_opp_init(void)
 			 * Cleanup - disable the higher freqs - we dont care
 			 * about the results
 			 */
-			dev = &mh->od->pdev.dev;
-			opp_disable(dev, 800000000);
-			dev = &dh->od->pdev.dev;
-			opp_disable(dev, 660000000);
+			opp_disable(mpu_dev, 800000000);
+			opp_disable(iva_dev, 660000000);
 		}
 	}
 	return;

arch/arm/mach-omap2/cminst44xx.h

@@ -18,13 +18,36 @@ extern void omap4_cminst_clkdm_force_sleep(u8 part, s16 inst, u16 cdoffs);
 extern void omap4_cminst_clkdm_force_wakeup(u8 part, s16 inst, u16 cdoffs);
 
 extern int omap4_cminst_wait_module_ready(u8 part, u16 inst, s16 cdoffs, u16 clkctrl_offs);
-extern int omap4_cminst_wait_module_idle(u8 part, u16 inst, s16 cdoffs, u16 clkctrl_offs);
+
+# ifdef CONFIG_ARCH_OMAP4
+extern int omap4_cminst_wait_module_idle(u8 part, u16 inst, s16 cdoffs,
+					 u16 clkctrl_offs);
 
 extern void omap4_cminst_module_enable(u8 mode, u8 part, u16 inst, s16 cdoffs,
 				       u16 clkctrl_offs);
 extern void omap4_cminst_module_disable(u8 part, u16 inst, s16 cdoffs,
 					u16 clkctrl_offs);
 
+# else
+
+static inline int omap4_cminst_wait_module_idle(u8 part, u16 inst, s16 cdoffs,
+					u16 clkctrl_offs)
+{
+	return 0;
+}
+
+static inline void omap4_cminst_module_enable(u8 mode, u8 part, u16 inst,
+				s16 cdoffs, u16 clkctrl_offs)
+{
+}
+
+static inline void omap4_cminst_module_disable(u8 part, u16 inst, s16 cdoffs,
+				 u16 clkctrl_offs)
+{
+}
+
+# endif
+
 /*
  * In an ideal world, we would not export these low-level functions,
  * but this will probably take some time to fix properly

arch/arm/mach-omap2/mux.c

@@ -821,11 +821,10 @@ static void __init omap_mux_set_cmdline_signals(void)
 	if (!omap_mux_options)
 		return;
 
-	options = kmalloc(strlen(omap_mux_options) + 1, GFP_KERNEL);
+	options = kstrdup(omap_mux_options, GFP_KERNEL);
 	if (!options)
 		return;
 
-	strcpy(options, omap_mux_options);
 	next_opt = options;
 
 	while ((token = strsep(&next_opt, ",")) != NULL) {
@@ -855,24 +854,19 @@ static int __init omap_mux_copy_names(struct omap_mux *src,
 
 	for (i = 0; i < OMAP_MUX_NR_MODES; i++) {
 		if (src->muxnames[i]) {
-			dst->muxnames[i] =
-				kmalloc(strlen(src->muxnames[i]) + 1,
-					GFP_KERNEL);
+			dst->muxnames[i] = kstrdup(src->muxnames[i],
+						   GFP_KERNEL);
 			if (!dst->muxnames[i])
 				goto free;
-			strcpy(dst->muxnames[i], src->muxnames[i]);
 		}
 	}
 
 #ifdef CONFIG_DEBUG_FS
 	for (i = 0; i < OMAP_MUX_NR_SIDES; i++) {
 		if (src->balls[i]) {
-			dst->balls[i] =
-				kmalloc(strlen(src->balls[i]) + 1,
-					GFP_KERNEL);
+			dst->balls[i] = kstrdup(src->balls[i], GFP_KERNEL);
 			if (!dst->balls[i])
 				goto free;
-			strcpy(dst->balls[i], src->balls[i]);
 		}
 	}
 #endif

arch/arm/mach-omap2/smartreflex.c

@@ -621,7 +621,7 @@ void sr_disable(struct voltagedomain *voltdm)
 			sr_v2_disable(sr);
 	}
 
-	pm_runtime_put_sync(&sr->pdev->dev);
+	pm_runtime_put_sync_suspend(&sr->pdev->dev);
 }
 
 /**
@@ -860,6 +860,7 @@ static int __init omap_sr_probe(struct platform_device *pdev)
 	irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 
 	pm_runtime_enable(&pdev->dev);
+	pm_runtime_irq_safe(&pdev->dev);
 
 	sr_info->pdev = pdev;
 	sr_info->srid = pdev->id;

arch/arm/mach-omap2/timer.c

@@ -293,7 +293,8 @@ static void __init omap2_gp_clocksource_init(int gptimer_id,
 	pr_info("OMAP clocksource: GPTIMER%d at %lu Hz\n",
 		gptimer_id, clksrc.rate);
 
-	__omap_dm_timer_load_start(clksrc.io_base, OMAP_TIMER_CTRL_ST, 0, 1);
+	__omap_dm_timer_load_start(clksrc.io_base,
+			OMAP_TIMER_CTRL_ST | OMAP_TIMER_CTRL_AR, 0, 1);
 	init_sched_clock(&cd, dmtimer_update_sched_clock, 32, clksrc.rate);
 
 	if (clocksource_register_hz(&clocksource_gpt, clksrc.rate))

arch/arm/mach-omap2/twl-common.c

@@ -48,14 +48,7 @@ void __init omap_pmic_init(int bus, u32 clkrate,
 	omap_register_i2c_bus(bus, clkrate, &pmic_i2c_board_info, 1);
 }
 
-static struct twl4030_usb_data omap4_usb_pdata = {
-	.phy_init	= omap4430_phy_init,
-	.phy_exit	= omap4430_phy_exit,
-	.phy_power	= omap4430_phy_power,
-	.phy_set_clock	= omap4430_phy_set_clk,
-	.phy_suspend	= omap4430_phy_suspend,
-};
-
+#if defined(CONFIG_ARCH_OMAP3)
 static struct twl4030_usb_data omap3_usb_pdata = {
 	.usb_mode	= T2_USB_MODE_ULPI,
 };
@@ -122,6 +115,45 @@ static struct regulator_init_data omap3_vpll2_idata = {
 	.consumer_supplies		= omap3_vpll2_supplies,
 };
 
+void __init omap3_pmic_get_config(struct twl4030_platform_data *pmic_data,
+				  u32 pdata_flags, u32 regulators_flags)
+{
+	if (!pmic_data->irq_base)
+		pmic_data->irq_base = TWL4030_IRQ_BASE;
+	if (!pmic_data->irq_end)
+		pmic_data->irq_end = TWL4030_IRQ_END;
+
+	/* Common platform data configurations */
+	if (pdata_flags & TWL_COMMON_PDATA_USB && !pmic_data->usb)
+		pmic_data->usb = &omap3_usb_pdata;
+
+	if (pdata_flags & TWL_COMMON_PDATA_BCI && !pmic_data->bci)
+		pmic_data->bci = &omap3_bci_pdata;
+
+	if (pdata_flags & TWL_COMMON_PDATA_MADC && !pmic_data->madc)
+		pmic_data->madc = &omap3_madc_pdata;
+
+	if (pdata_flags & TWL_COMMON_PDATA_AUDIO && !pmic_data->audio)
+		pmic_data->audio = &omap3_audio_pdata;
+
+	/* Common regulator configurations */
+	if (regulators_flags & TWL_COMMON_REGULATOR_VDAC && !pmic_data->vdac)
+		pmic_data->vdac = &omap3_vdac_idata;
+
+	if (regulators_flags & TWL_COMMON_REGULATOR_VPLL2 && !pmic_data->vpll2)
+		pmic_data->vpll2 = &omap3_vpll2_idata;
+}
+#endif /* CONFIG_ARCH_OMAP3 */
+
+#if defined(CONFIG_ARCH_OMAP4)
+static struct twl4030_usb_data omap4_usb_pdata = {
+	.phy_init	= omap4430_phy_init,
+	.phy_exit	= omap4430_phy_exit,
+	.phy_power	= omap4430_phy_power,
+	.phy_set_clock	= omap4430_phy_set_clk,
+	.phy_suspend	= omap4430_phy_suspend,
+};
+
 static struct regulator_init_data omap4_vdac_idata = {
 	.constraints = {
 		.min_uV			= 1800000,
@@ -273,32 +305,4 @@ void __init omap4_pmic_get_config(struct twl4030_platform_data *pmic_data,
 	    !pmic_data->clk32kg)
 		pmic_data->clk32kg = &omap4_clk32kg_idata;
 }
-
-void __init omap3_pmic_get_config(struct twl4030_platform_data *pmic_data,
-				  u32 pdata_flags, u32 regulators_flags)
-{
-	if (!pmic_data->irq_base)
-		pmic_data->irq_base = TWL4030_IRQ_BASE;
-	if (!pmic_data->irq_end)
-		pmic_data->irq_end = TWL4030_IRQ_END;
-
-	/* Common platform data configurations */
-	if (pdata_flags & TWL_COMMON_PDATA_USB && !pmic_data->usb)
-		pmic_data->usb = &omap3_usb_pdata;
-
-	if (pdata_flags & TWL_COMMON_PDATA_BCI && !pmic_data->bci)
-		pmic_data->bci = &omap3_bci_pdata;
-
-	if (pdata_flags & TWL_COMMON_PDATA_MADC && !pmic_data->madc)
-		pmic_data->madc = &omap3_madc_pdata;
-
-	if (pdata_flags & TWL_COMMON_PDATA_AUDIO && !pmic_data->audio)
-		pmic_data->audio = &omap3_audio_pdata;
-
-	/* Common regulator configurations */
-	if (regulators_flags & TWL_COMMON_REGULATOR_VDAC && !pmic_data->vdac)
-		pmic_data->vdac = &omap3_vdac_idata;
-
-	if (regulators_flags & TWL_COMMON_REGULATOR_VPLL2 && !pmic_data->vpll2)
-		pmic_data->vpll2 = &omap3_vpll2_idata;
-}
+#endif /* CONFIG_ARCH_OMAP4 */

arch/arm/mach-s3c64xx/mach-crag6410.c

@@ -65,7 +65,7 @@
 #include <plat/iic.h>
 #include <plat/pm.h>
 
-#include <sound/wm8915.h>
+#include <sound/wm8996.h>
 #include <sound/wm8962.h>
 #include <sound/wm9081.h>
 
@@ -614,7 +614,7 @@ static struct wm831x_pdata glenfarclas_pmic_pdata __initdata = {
 	.disable_touch = true,
 };
 
-static struct wm8915_retune_mobile_config wm8915_retune[] = {
+static struct wm8996_retune_mobile_config wm8996_retune[] = {
 	{
 		.name = "Sub LPF",
 		.rate = 48000,
@@ -635,12 +635,12 @@ static struct wm8915_retune_mobile_config wm8915_retune[] = {
 	},
 };
 
-static struct wm8915_pdata wm8915_pdata __initdata = {
+static struct wm8996_pdata wm8996_pdata __initdata = {
 	.ldo_ena = S3C64XX_GPN(7),
 	.gpio_base = CODEC_GPIO_BASE,
 	.micdet_def = 1,
-	.inl_mode = WM8915_DIFFERRENTIAL_1,
-	.inr_mode = WM8915_DIFFERRENTIAL_1,
+	.inl_mode = WM8996_DIFFERRENTIAL_1,
+	.inr_mode = WM8996_DIFFERRENTIAL_1,
 
 	.irq_flags = IRQF_TRIGGER_RISING,
 
@@ -652,8 +652,8 @@ static struct wm8915_pdata wm8915_pdata __initdata = {
 		0x020e, /* GPIO5 == CLKOUT */
 	},
 
-	.retune_mobile_cfgs = wm8915_retune,
-	.num_retune_mobile_cfgs = ARRAY_SIZE(wm8915_retune),
+	.retune_mobile_cfgs = wm8996_retune,
+	.num_retune_mobile_cfgs = ARRAY_SIZE(wm8996_retune),
 };
 
 static struct wm8962_pdata wm8962_pdata __initdata = {
@@ -679,8 +679,8 @@ static struct i2c_board_info i2c_devs1[] __initdata = {
 	  .platform_data = &glenfarclas_pmic_pdata },
 
 	{ I2C_BOARD_INFO("wm1250-ev1", 0x27) },
-	{ I2C_BOARD_INFO("wm8915", 0x1a),
-	  .platform_data = &wm8915_pdata,
+	{ I2C_BOARD_INFO("wm8996", 0x1a),
+	  .platform_data = &wm8996_pdata,
 	  .irq = GLENFARCLAS_PMIC_IRQ_BASE + WM831X_IRQ_GPIO_2,
 	},
 	{ I2C_BOARD_INFO("wm9081", 0x6c),

arch/arm/mach-sa1100/pci-nanoengine.c

@@ -28,6 +28,7 @@
 #include <asm/mach-types.h>
 
 #include <mach/nanoengine.h>
+#include <mach/hardware.h>
 
 static DEFINE_SPINLOCK(nano_lock);
 

arch/arm/mm/alignment.c

@@ -22,6 +22,7 @@
 #include <linux/sched.h>
 #include <linux/uaccess.h>
 
+#include <asm/system.h>
 #include <asm/unaligned.h>
 
 #include "fault.h"
@@ -95,6 +96,33 @@ static const char *usermode_action[] = {
 	"signal+warn"
 };
 
+/* Return true if and only if the ARMv6 unaligned access model is in use. */
+static bool cpu_is_v6_unaligned(void)
+{
+	return cpu_architecture() >= CPU_ARCH_ARMv6 && (cr_alignment & CR_U);
+}
+
+static int safe_usermode(int new_usermode, bool warn)
+{
+	/*
+	 * ARMv6 and later CPUs can perform unaligned accesses for
+	 * most single load and store instructions up to word size.
+	 * LDM, STM, LDRD and STRD still need to be handled.
+	 *
+	 * Ignoring the alignment fault is not an option on these
+	 * CPUs since we spin re-faulting the instruction without
+	 * making any progress.
+	 */
+	if (cpu_is_v6_unaligned() && !(new_usermode & (UM_FIXUP | UM_SIGNAL))) {
+		new_usermode |= UM_FIXUP;
+
+		if (warn)
+			printk(KERN_WARNING "alignment: ignoring faults is unsafe on this CPU.  Defaulting to fixup mode.\n");
+	}
+
+	return new_usermode;
+}
+
 static int alignment_proc_show(struct seq_file *m, void *v)
 {
 	seq_printf(m, "User:\t\t%lu\n", ai_user);
@@ -125,7 +153,7 @@ static ssize_t alignment_proc_write(struct file *file, const char __user *buffer
 		if (get_user(mode, buffer))
 			return -EFAULT;
 		if (mode >= '0' && mode <= '5')
-			ai_usermode = mode - '0';
+			ai_usermode = safe_usermode(mode - '0', true);
 	}
 	return count;
 }
@@ -886,9 +914,16 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	if (ai_usermode & UM_FIXUP)
 		goto fixup;
 
-	if (ai_usermode & UM_SIGNAL)
-		force_sig(SIGBUS, current);
-	else {
+	if (ai_usermode & UM_SIGNAL) {
+		siginfo_t si;
+
+		si.si_signo = SIGBUS;
+		si.si_errno = 0;
+		si.si_code = BUS_ADRALN;
+		si.si_addr = (void __user *)addr;
+
+		force_sig_info(si.si_signo, &si, current);
+	} else {
 		/*
 		 * We're about to disable the alignment trap and return to
 		 * user space.  But if an interrupt occurs before actually
@@ -926,20 +961,11 @@ static int __init alignment_init(void)
 		return -ENOMEM;
 #endif
 
-	/*
-	 * ARMv6 and later CPUs can perform unaligned accesses for
-	 * most single load and store instructions up to word size.
-	 * LDM, STM, LDRD and STRD still need to be handled.
-	 *
-	 * Ignoring the alignment fault is not an option on these
-	 * CPUs since we spin re-faulting the instruction without
-	 * making any progress.
-	 */
-	if (cpu_architecture() >= CPU_ARCH_ARMv6 && (cr_alignment & CR_U)) {
+	if (cpu_is_v6_unaligned()) {
 		cr_alignment &= ~CR_A;
 		cr_no_alignment &= ~CR_A;
 		set_cr(cr_alignment);
-		ai_usermode = UM_FIXUP;
+		ai_usermode = safe_usermode(ai_usermode, false);
 	}
 
 	hook_fault_code(1, do_alignment, SIGBUS, BUS_ADRALN,

arch/arm/mm/init.c

@@ -441,7 +441,7 @@ static inline int free_area(unsigned long pfn, unsigned long end, char *s)
 static inline void poison_init_mem(void *s, size_t count)
 {
 	u32 *p = (u32 *)s;
-	while ((count = count - 4))
+	for (; count != 0; count -= 4)
 		*p++ = 0xe7fddef0;
 }
 

arch/arm/mm/proc-arm946.S

@@ -410,6 +410,7 @@ __arm946_proc_info:
 	.long	0x41009460
 	.long	0xff00fff0
 	.long	0
+	.long	0
 	b	__arm946_setup
 	.long	cpu_arch_name
 	.long	cpu_elf_name
@@ -418,6 +419,6 @@ __arm946_proc_info:
 	.long	arm946_processor_functions
 	.long	0
 	.long	0
-	.long	arm940_cache_fns
+	.long	arm946_cache_fns
 	.size	__arm946_proc_info, . - __arm946_proc_info
 

arch/arm/plat-mxc/include/mach/debug-macro.S

@@ -44,6 +44,14 @@
 #define UART_PADDR	MX51_UART1_BASE_ADDR
 #endif
 
+/* iMX50/53 have same addresses, but not iMX51 */
+#if defined(CONFIG_SOC_IMX50) || defined(CONFIG_SOC_IMX53)
+#ifdef UART_PADDR
+#error "CONFIG_DEBUG_LL is incompatible with multiple archs"
+#endif
+#define UART_PADDR	MX53_UART1_BASE_ADDR
+#endif
+
 #define UART_VADDR	IMX_IO_ADDRESS(UART_PADDR)
 
 		.macro	addruart, rp, rv

arch/arm/plat-mxc/include/mach/iomux-mx53.h

@@ -30,6 +30,9 @@
 #define MX53_SDHC_PAD_CTRL 	(PAD_CTL_HYS | PAD_CTL_PKE | PAD_CTL_PUE | \
 				PAD_CTL_PUS_47K_UP | PAD_CTL_DSE_HIGH | \
 				PAD_CTL_SRE_FAST)
+#define PAD_CTRL_I2C	(PAD_CTL_SRE_FAST | PAD_CTL_ODE | PAD_CTL_PKE | \
+			PAD_CTL_PUE | PAD_CTL_DSE_HIGH | PAD_CTL_PUS_100K_UP \
+			| PAD_CTL_HYS)
 
 #define _MX53_PAD_GPIO_19__KPP_COL_5		IOMUX_PAD(0x348, 0x20, 0, 0x840, 0, 0)
 #define _MX53_PAD_GPIO_19__GPIO4_5		IOMUX_PAD(0x348, 0x20, 1, 0x0, 0, 0)
@@ -1256,7 +1259,7 @@
 #define MX53_PAD_KEY_COL3__GPIO4_12		(_MX53_PAD_KEY_COL3__GPIO4_12 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_KEY_COL3__USBOH3_H2_DP		(_MX53_PAD_KEY_COL3__USBOH3_H2_DP | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_KEY_COL3__SPDIF_IN1		(_MX53_PAD_KEY_COL3__SPDIF_IN1 | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_KEY_COL3__I2C2_SCL		(_MX53_PAD_KEY_COL3__I2C2_SCL | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_KEY_COL3__I2C2_SCL		(_MX53_PAD_KEY_COL3__I2C2_SCL | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_KEY_COL3__ECSPI1_SS3		(_MX53_PAD_KEY_COL3__ECSPI1_SS3 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_KEY_COL3__FEC_CRS		(_MX53_PAD_KEY_COL3__FEC_CRS | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_KEY_COL3__USBPHY1_SIECLOCK		(_MX53_PAD_KEY_COL3__USBPHY1_SIECLOCK | MUX_PAD_CTRL(NO_PAD_CTRL))
@@ -1264,7 +1267,7 @@
 #define MX53_PAD_KEY_ROW3__GPIO4_13		(_MX53_PAD_KEY_ROW3__GPIO4_13 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_KEY_ROW3__USBOH3_H2_DM		(_MX53_PAD_KEY_ROW3__USBOH3_H2_DM | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_KEY_ROW3__CCM_ASRC_EXT_CLK		(_MX53_PAD_KEY_ROW3__CCM_ASRC_EXT_CLK | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_KEY_ROW3__I2C2_SDA		(_MX53_PAD_KEY_ROW3__I2C2_SDA | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_KEY_ROW3__I2C2_SDA		(_MX53_PAD_KEY_ROW3__I2C2_SDA | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_KEY_ROW3__OSC32K_32K_OUT		(_MX53_PAD_KEY_ROW3__OSC32K_32K_OUT | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_KEY_ROW3__CCM_PLL4_BYP		(_MX53_PAD_KEY_ROW3__CCM_PLL4_BYP | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_KEY_ROW3__USBPHY1_LINESTATE_0		(_MX53_PAD_KEY_ROW3__USBPHY1_LINESTATE_0 | MUX_PAD_CTRL(NO_PAD_CTRL))
@@ -1536,7 +1539,7 @@
 #define MX53_PAD_CSI0_DAT8__KPP_COL_7		(_MX53_PAD_CSI0_DAT8__KPP_COL_7 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_CSI0_DAT8__ECSPI2_SCLK		(_MX53_PAD_CSI0_DAT8__ECSPI2_SCLK | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_CSI0_DAT8__USBOH3_USBH3_OC		(_MX53_PAD_CSI0_DAT8__USBOH3_USBH3_OC | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_CSI0_DAT8__I2C1_SDA		(_MX53_PAD_CSI0_DAT8__I2C1_SDA | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_CSI0_DAT8__I2C1_SDA		(_MX53_PAD_CSI0_DAT8__I2C1_SDA | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_CSI0_DAT8__EMI_EMI_DEBUG_37		(_MX53_PAD_CSI0_DAT8__EMI_EMI_DEBUG_37 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_CSI0_DAT8__TPIU_TRACE_5		(_MX53_PAD_CSI0_DAT8__TPIU_TRACE_5 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_CSI0_DAT9__IPU_CSI0_D_9		(_MX53_PAD_CSI0_DAT9__IPU_CSI0_D_9 | MUX_PAD_CTRL(NO_PAD_CTRL))
@@ -1544,7 +1547,7 @@
 #define MX53_PAD_CSI0_DAT9__KPP_ROW_7		(_MX53_PAD_CSI0_DAT9__KPP_ROW_7 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_CSI0_DAT9__ECSPI2_MOSI		(_MX53_PAD_CSI0_DAT9__ECSPI2_MOSI | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_CSI0_DAT9__USBOH3_USBH3_PWR		(_MX53_PAD_CSI0_DAT9__USBOH3_USBH3_PWR | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_CSI0_DAT9__I2C1_SCL		(_MX53_PAD_CSI0_DAT9__I2C1_SCL | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_CSI0_DAT9__I2C1_SCL		(_MX53_PAD_CSI0_DAT9__I2C1_SCL | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_CSI0_DAT9__EMI_EMI_DEBUG_38		(_MX53_PAD_CSI0_DAT9__EMI_EMI_DEBUG_38 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_CSI0_DAT9__TPIU_TRACE_6		(_MX53_PAD_CSI0_DAT9__TPIU_TRACE_6 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_CSI0_DAT10__IPU_CSI0_D_10		(_MX53_PAD_CSI0_DAT10__IPU_CSI0_D_10 | MUX_PAD_CTRL(NO_PAD_CTRL))
@@ -1631,25 +1634,25 @@
 #define MX53_PAD_EIM_EB2__CCM_DI1_EXT_CLK		(_MX53_PAD_EIM_EB2__CCM_DI1_EXT_CLK | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_EB2__IPU_SER_DISP1_CS		(_MX53_PAD_EIM_EB2__IPU_SER_DISP1_CS | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_EB2__ECSPI1_SS0		(_MX53_PAD_EIM_EB2__ECSPI1_SS0 | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_EIM_EB2__I2C2_SCL		(_MX53_PAD_EIM_EB2__I2C2_SCL | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_EIM_EB2__I2C2_SCL		(_MX53_PAD_EIM_EB2__I2C2_SCL | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_EIM_D16__EMI_WEIM_D_16		(_MX53_PAD_EIM_D16__EMI_WEIM_D_16 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D16__GPIO3_16		(_MX53_PAD_EIM_D16__GPIO3_16 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D16__IPU_DI0_PIN5		(_MX53_PAD_EIM_D16__IPU_DI0_PIN5 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D16__IPU_DISPB1_SER_CLK		(_MX53_PAD_EIM_D16__IPU_DISPB1_SER_CLK | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D16__ECSPI1_SCLK		(_MX53_PAD_EIM_D16__ECSPI1_SCLK | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_EIM_D16__I2C2_SDA		(_MX53_PAD_EIM_D16__I2C2_SDA | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_EIM_D16__I2C2_SDA		(_MX53_PAD_EIM_D16__I2C2_SDA | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_EIM_D17__EMI_WEIM_D_17		(_MX53_PAD_EIM_D17__EMI_WEIM_D_17 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D17__GPIO3_17		(_MX53_PAD_EIM_D17__GPIO3_17 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D17__IPU_DI0_PIN6		(_MX53_PAD_EIM_D17__IPU_DI0_PIN6 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D17__IPU_DISPB1_SER_DIN		(_MX53_PAD_EIM_D17__IPU_DISPB1_SER_DIN | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D17__ECSPI1_MISO		(_MX53_PAD_EIM_D17__ECSPI1_MISO | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_EIM_D17__I2C3_SCL		(_MX53_PAD_EIM_D17__I2C3_SCL | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_EIM_D17__I2C3_SCL		(_MX53_PAD_EIM_D17__I2C3_SCL | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_EIM_D18__EMI_WEIM_D_18		(_MX53_PAD_EIM_D18__EMI_WEIM_D_18 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D18__GPIO3_18		(_MX53_PAD_EIM_D18__GPIO3_18 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D18__IPU_DI0_PIN7		(_MX53_PAD_EIM_D18__IPU_DI0_PIN7 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D18__IPU_DISPB1_SER_DIO		(_MX53_PAD_EIM_D18__IPU_DISPB1_SER_DIO | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D18__ECSPI1_MOSI		(_MX53_PAD_EIM_D18__ECSPI1_MOSI | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_EIM_D18__I2C3_SDA		(_MX53_PAD_EIM_D18__I2C3_SDA | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_EIM_D18__I2C3_SDA		(_MX53_PAD_EIM_D18__I2C3_SDA | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_EIM_D18__IPU_DI1_D0_CS		(_MX53_PAD_EIM_D18__IPU_DI1_D0_CS | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D19__EMI_WEIM_D_19		(_MX53_PAD_EIM_D19__EMI_WEIM_D_19 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D19__GPIO3_19		(_MX53_PAD_EIM_D19__GPIO3_19 | MUX_PAD_CTRL(NO_PAD_CTRL))
@@ -1672,7 +1675,7 @@
 #define MX53_PAD_EIM_D21__IPU_DI0_PIN17		(_MX53_PAD_EIM_D21__IPU_DI0_PIN17 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D21__IPU_DISPB0_SER_CLK		(_MX53_PAD_EIM_D21__IPU_DISPB0_SER_CLK | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D21__CSPI_SCLK		(_MX53_PAD_EIM_D21__CSPI_SCLK | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_EIM_D21__I2C1_SCL		(_MX53_PAD_EIM_D21__I2C1_SCL | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_EIM_D21__I2C1_SCL		(_MX53_PAD_EIM_D21__I2C1_SCL | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_EIM_D21__USBOH3_USBOTG_OC		(_MX53_PAD_EIM_D21__USBOH3_USBOTG_OC | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D22__EMI_WEIM_D_22		(_MX53_PAD_EIM_D22__EMI_WEIM_D_22 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D22__GPIO3_22		(_MX53_PAD_EIM_D22__GPIO3_22 | MUX_PAD_CTRL(NO_PAD_CTRL))
@@ -1732,7 +1735,7 @@
 #define MX53_PAD_EIM_D28__UART2_CTS		(_MX53_PAD_EIM_D28__UART2_CTS | MUX_PAD_CTRL(MX53_UART_PAD_CTRL))
 #define MX53_PAD_EIM_D28__IPU_DISPB0_SER_DIO		(_MX53_PAD_EIM_D28__IPU_DISPB0_SER_DIO | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D28__CSPI_MOSI		(_MX53_PAD_EIM_D28__CSPI_MOSI | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_EIM_D28__I2C1_SDA		(_MX53_PAD_EIM_D28__I2C1_SDA | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_EIM_D28__I2C1_SDA		(_MX53_PAD_EIM_D28__I2C1_SDA | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_EIM_D28__IPU_EXT_TRIG		(_MX53_PAD_EIM_D28__IPU_EXT_TRIG | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D28__IPU_DI0_PIN13		(_MX53_PAD_EIM_D28__IPU_DI0_PIN13 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_EIM_D29__EMI_WEIM_D_29		(_MX53_PAD_EIM_D29__EMI_WEIM_D_29 | MUX_PAD_CTRL(NO_PAD_CTRL))
@@ -2297,7 +2300,7 @@
 #define MX53_PAD_GPIO_9__SCC_FAIL_STATE		(_MX53_PAD_GPIO_9__SCC_FAIL_STATE | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_3__ESAI1_HCKR		(_MX53_PAD_GPIO_3__ESAI1_HCKR | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_3__GPIO1_3		(_MX53_PAD_GPIO_3__GPIO1_3 | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_GPIO_3__I2C3_SCL		(_MX53_PAD_GPIO_3__I2C3_SCL | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_GPIO_3__I2C3_SCL		(_MX53_PAD_GPIO_3__I2C3_SCL | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_GPIO_3__DPLLIP1_TOG_EN		(_MX53_PAD_GPIO_3__DPLLIP1_TOG_EN | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_3__CCM_CLKO2		(_MX53_PAD_GPIO_3__CCM_CLKO2 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_3__OBSERVE_MUX_OBSRV_INT_OUT0		(_MX53_PAD_GPIO_3__OBSERVE_MUX_OBSRV_INT_OUT0 | MUX_PAD_CTRL(NO_PAD_CTRL))
@@ -2305,7 +2308,7 @@
 #define MX53_PAD_GPIO_3__MLB_MLBCLK		(_MX53_PAD_GPIO_3__MLB_MLBCLK | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_6__ESAI1_SCKT		(_MX53_PAD_GPIO_6__ESAI1_SCKT | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_6__GPIO1_6		(_MX53_PAD_GPIO_6__GPIO1_6 | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_GPIO_6__I2C3_SDA		(_MX53_PAD_GPIO_6__I2C3_SDA | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_GPIO_6__I2C3_SDA		(_MX53_PAD_GPIO_6__I2C3_SDA | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_GPIO_6__CCM_CCM_OUT_0		(_MX53_PAD_GPIO_6__CCM_CCM_OUT_0 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_6__CSU_CSU_INT_DEB		(_MX53_PAD_GPIO_6__CSU_CSU_INT_DEB | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_6__OBSERVE_MUX_OBSRV_INT_OUT1		(_MX53_PAD_GPIO_6__OBSERVE_MUX_OBSRV_INT_OUT1 | MUX_PAD_CTRL(NO_PAD_CTRL))
@@ -2333,7 +2336,7 @@
 #define MX53_PAD_GPIO_5__CCM_CLKO		(_MX53_PAD_GPIO_5__CCM_CLKO | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_5__CSU_CSU_ALARM_AUT_2		(_MX53_PAD_GPIO_5__CSU_CSU_ALARM_AUT_2 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_5__OBSERVE_MUX_OBSRV_INT_OUT4		(_MX53_PAD_GPIO_5__OBSERVE_MUX_OBSRV_INT_OUT4 | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_GPIO_5__I2C3_SCL		(_MX53_PAD_GPIO_5__I2C3_SCL | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_GPIO_5__I2C3_SCL		(_MX53_PAD_GPIO_5__I2C3_SCL | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_GPIO_5__CCM_PLL1_BYP		(_MX53_PAD_GPIO_5__CCM_PLL1_BYP | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_7__ESAI1_TX4_RX1		(_MX53_PAD_GPIO_7__ESAI1_TX4_RX1 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_7__GPIO1_7		(_MX53_PAD_GPIO_7__GPIO1_7 | MUX_PAD_CTRL(NO_PAD_CTRL))
@@ -2356,7 +2359,7 @@
 #define MX53_PAD_GPIO_16__TZIC_PWRFAIL_INT		(_MX53_PAD_GPIO_16__TZIC_PWRFAIL_INT | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_16__RTC_CE_RTC_EXT_TRIG1		(_MX53_PAD_GPIO_16__RTC_CE_RTC_EXT_TRIG1 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_16__SPDIF_IN1		(_MX53_PAD_GPIO_16__SPDIF_IN1 | MUX_PAD_CTRL(NO_PAD_CTRL))
-#define MX53_PAD_GPIO_16__I2C3_SDA		(_MX53_PAD_GPIO_16__I2C3_SDA | MUX_PAD_CTRL(NO_PAD_CTRL))
+#define MX53_PAD_GPIO_16__I2C3_SDA		(_MX53_PAD_GPIO_16__I2C3_SDA | MUX_PAD_CTRL(PAD_CTRL_I2C))
 #define MX53_PAD_GPIO_16__SJC_DE_B		(_MX53_PAD_GPIO_16__SJC_DE_B | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_17__ESAI1_TX0		(_MX53_PAD_GPIO_17__ESAI1_TX0 | MUX_PAD_CTRL(NO_PAD_CTRL))
 #define MX53_PAD_GPIO_17__GPIO7_12		(_MX53_PAD_GPIO_17__GPIO7_12 | MUX_PAD_CTRL(NO_PAD_CTRL))

arch/arm/plat-omap/Kconfig

@@ -13,6 +13,7 @@ config ARCH_OMAP1
 	bool "TI OMAP1"
 	select CLKDEV_LOOKUP
 	select CLKSRC_MMIO
+	select GENERIC_IRQ_CHIP
 	help
 	  "Systems based on omap7xx, omap15xx or omap16xx"
 

arch/arm/plat-omap/include/plat/dma.h

@@ -195,6 +195,11 @@
 
 #define OMAP36XX_DMA_UART4_TX		81	/* S_DMA_80 */
 #define OMAP36XX_DMA_UART4_RX		82	/* S_DMA_81 */
+
+/* Only for AM35xx */
+#define AM35XX_DMA_UART4_TX		54
+#define AM35XX_DMA_UART4_RX		55
+
 /*----------------------------------------------------------------------------*/
 
 #define OMAP1_DMA_TOUT_IRQ		(1 << 0)

arch/arm/plat-omap/include/plat/irqs.h

@@ -357,6 +357,7 @@
 #define INT_35XX_EMAC_C0_TX_PULSE_IRQ	69
 #define INT_35XX_EMAC_C0_MISC_PULSE_IRQ	70
 #define INT_35XX_USBOTG_IRQ		71
+#define INT_35XX_UART4			84
 #define INT_35XX_CCDC_VD0_IRQ		88
 #define INT_35XX_CCDC_VD1_IRQ		92
 #define INT_35XX_CCDC_VD2_IRQ		93

arch/arm/plat-omap/include/plat/serial.h

@@ -56,6 +56,9 @@
 #define TI816X_UART2_BASE	0x48022000
 #define TI816X_UART3_BASE	0x48024000
 
+/* AM3505/3517 UART4 */
+#define AM35XX_UART4_BASE	0x4809E000	/* Only on AM3505/3517 */
+
 /* External port on Zoom2/3 */
 #define ZOOM_UART_BASE		0x10000000
 #define ZOOM_UART_VIRT		0xfa400000

arch/arm/plat-omap/iovmm.c

@@ -423,9 +423,6 @@ static void sgtable_fill_kmalloc(struct sg_table *sgt, u32 pa, u32 da,
 {
 	unsigned int i;
 	struct scatterlist *sg;
-	void *va;
-
-	va = phys_to_virt(pa);
 
 	for_each_sg(sgt->sgl, sg, sgt->nents, i) {
 		unsigned bytes;

arch/arm/tools/mach-types

@@ -910,7 +910,7 @@ omapl138_case_a3	MACH_OMAPL138_CASE_A3	OMAPL138_CASE_A3	3280
 uemd			MACH_UEMD		UEMD			3281
 ccwmx51mut		MACH_CCWMX51MUT		CCWMX51MUT		3282
 rockhopper		MACH_ROCKHOPPER		ROCKHOPPER		3283
-nookcolor		MACH_NOOKCOLOR		NOOKCOLOR		3284
+encore			MACH_ENCORE		ENCORE			3284
 hkdkc100		MACH_HKDKC100		HKDKC100		3285
 ts42xx			MACH_TS42XX		TS42XX			3286
 aebl			MACH_AEBL		AEBL			3287

arch/powerpc/include/asm/jump_label.h

@@ -22,7 +22,6 @@ static __always_inline bool arch_static_branch(struct jump_label_key *key)
 	asm goto("1:\n\t"
 		 "nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
-		 ".align 4\n\t"
 		 JUMP_ENTRY_TYPE "1b, %l[l_yes], %c0\n\t"
 		 ".popsection \n\t"
 		 : :  "i" (key) : : l_yes);
@@ -41,7 +40,6 @@ struct jump_entry {
 	jump_label_t code;
 	jump_label_t target;
 	jump_label_t key;
-	jump_label_t pad;
 };
 
 #endif /* _ASM_POWERPC_JUMP_LABEL_H */

arch/powerpc/include/asm/kdump.h

@@ -3,17 +3,7 @@
 
 #include <asm/page.h>
 
-/*
- * If CONFIG_RELOCATABLE is enabled we can place the kdump kernel anywhere.
- * To keep enough space in the RMO for the first stage kernel on 64bit, we
- * place it at 64MB. If CONFIG_RELOCATABLE is not enabled we must place
- * the second stage at 32MB.
- */
-#if defined(CONFIG_RELOCATABLE) && defined(CONFIG_PPC64)
-#define KDUMP_KERNELBASE	0x4000000
-#else
 #define KDUMP_KERNELBASE	0x2000000
-#endif
 
 /* How many bytes to reserve at zero for kdump. The reserve limit should
  * be greater or equal to the trampoline's end address.

arch/powerpc/include/asm/reg.h

@@ -1003,7 +1003,6 @@
 #define PV_970		0x0039
 #define PV_POWER5	0x003A
 #define PV_POWER5p	0x003B
-#define PV_POWER7	0x003F
 #define PV_970FX	0x003C
 #define PV_POWER6	0x003E
 #define PV_POWER7	0x003F
@@ -1024,13 +1023,16 @@
 #define mtmsrd(v)	__mtmsrd((v), 0)
 #define mtmsr(v)	mtmsrd(v)
 #else
-#define mtmsr(v)	asm volatile("mtmsr %0" : : "r" (v) : "memory")
+#define mtmsr(v)	asm volatile("mtmsr %0" : \
+				     : "r" ((unsigned long)(v)) \
+				     : "memory")
 #endif
 
 #define mfspr(rn)	({unsigned long rval; \
 			asm volatile("mfspr %0," __stringify(rn) \
 				: "=r" (rval)); rval;})
-#define mtspr(rn, v)	asm volatile("mtspr " __stringify(rn) ",%0" : : "r" (v)\
+#define mtspr(rn, v)	asm volatile("mtspr " __stringify(rn) ",%0" : \
+				     : "r" ((unsigned long)(v)) \
 				     : "memory")
 
 #ifdef __powerpc64__

arch/powerpc/kernel/cputable.c

@@ -2051,7 +2051,8 @@ static struct cpu_spec __initdata cpu_specs[] = {
 
 static struct cpu_spec the_cpu_spec;
 
-static void __init setup_cpu_spec(unsigned long offset, struct cpu_spec *s)
+static struct cpu_spec * __init setup_cpu_spec(unsigned long offset,
+					       struct cpu_spec *s)
 {
 	struct cpu_spec *t = &the_cpu_spec;
 	struct cpu_spec old;
@@ -2114,6 +2115,8 @@ static void __init setup_cpu_spec(unsigned long offset, struct cpu_spec *s)
 		t->cpu_setup(offset, t);
 	}
 #endif /* CONFIG_PPC64 || CONFIG_BOOKE */
+
+	return t;
 }
 
 struct cpu_spec * __init identify_cpu(unsigned long offset, unsigned int pvr)
@@ -2124,10 +2127,8 @@ struct cpu_spec * __init identify_cpu(unsigned long offset, unsigned int pvr)
 	s = PTRRELOC(s);
 
 	for (i = 0; i < ARRAY_SIZE(cpu_specs); i++,s++) {
-		if ((pvr & s->pvr_mask) == s->pvr_value) {
-			setup_cpu_spec(offset, s);
-			return s;
-		}
+		if ((pvr & s->pvr_mask) == s->pvr_value)
+			return setup_cpu_spec(offset, s);
 	}
 
 	BUG();

arch/powerpc/kernel/iomap.c

@@ -117,6 +117,7 @@ void ioport_unmap(void __iomem *addr)
 EXPORT_SYMBOL(ioport_map);
 EXPORT_SYMBOL(ioport_unmap);
 
+#ifdef CONFIG_PCI
 void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max)
 {
 	resource_size_t start = pci_resource_start(dev, bar);
@@ -146,3 +147,4 @@ void pci_iounmap(struct pci_dev *dev, void __iomem *addr)
 
 EXPORT_SYMBOL(pci_iomap);
 EXPORT_SYMBOL(pci_iounmap);
+#endif /* CONFIG_PCI */

arch/powerpc/kernel/machine_kexec.c

@@ -136,12 +136,16 @@ void __init reserve_crashkernel(void)
 	crashk_res.start = KDUMP_KERNELBASE;
 #else
 	if (!crashk_res.start) {
+#ifdef CONFIG_PPC64
 		/*
-		 * unspecified address, choose a region of specified size
-		 * can overlap with initrd (ignoring corruption when retained)
-		 * ppc64 requires kernel and some stacks to be in first segemnt
+		 * On 64bit we split the RMO in half but cap it at half of
+		 * a small SLB (128MB) since the crash kernel needs to place
+		 * itself and some stacks to be in the first segment.
 		 */
+		crashk_res.start = min(0x80000000ULL, (ppc64_rma_size / 2));
+#else
 		crashk_res.start = KDUMP_KERNELBASE;
+#endif
 	}
 
 	crash_base = PAGE_ALIGN(crashk_res.start);

arch/powerpc/kernel/perf_callchain.c

@@ -154,8 +154,12 @@ static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret)
 	    ((unsigned long)ptr & 7))
 		return -EFAULT;
 
-	if (!__get_user_inatomic(*ret, ptr))
+	pagefault_disable();
+	if (!__get_user_inatomic(*ret, ptr)) {
+		pagefault_enable();
 		return 0;
+	}
+	pagefault_enable();
 
 	return read_user_stack_slow(ptr, ret, 8);
 }
@@ -166,8 +170,12 @@ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
 	    ((unsigned long)ptr & 3))
 		return -EFAULT;
 
-	if (!__get_user_inatomic(*ret, ptr))
+	pagefault_disable();
+	if (!__get_user_inatomic(*ret, ptr)) {
+		pagefault_enable();
 		return 0;
+	}
+	pagefault_enable();
 
 	return read_user_stack_slow(ptr, ret, 4);
 }
@@ -294,11 +302,17 @@ static inline int current_is_64bit(void)
  */
 static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
 {
+	int rc;
+
 	if ((unsigned long)ptr > TASK_SIZE - sizeof(unsigned int) ||
 	    ((unsigned long)ptr & 3))
 		return -EFAULT;
 
-	return __get_user_inatomic(*ret, ptr);
+	pagefault_disable();
+	rc = __get_user_inatomic(*ret, ptr);
+	pagefault_enable();
+
+	return rc;
 }
 
 static inline void perf_callchain_user_64(struct perf_callchain_entry *entry,

arch/powerpc/kernel/prom_init.c

@@ -1020,7 +1020,7 @@ static unsigned long __init alloc_up(unsigned long size, unsigned long align)
 	}
 	if (addr == 0)
 		return 0;
-	RELOC(alloc_bottom) = addr;
+	RELOC(alloc_bottom) = addr + size;
 
 	prom_debug(" -> %x\n", addr);
 	prom_debug("  alloc_bottom : %x\n", RELOC(alloc_bottom));
@@ -1830,11 +1830,13 @@ static void __init *make_room(unsigned long *mem_start, unsigned long *mem_end,
 		if (room > DEVTREE_CHUNK_SIZE)
 			room = DEVTREE_CHUNK_SIZE;
 		if (room < PAGE_SIZE)
-			prom_panic("No memory for flatten_device_tree (no room)");
+			prom_panic("No memory for flatten_device_tree "
+				   "(no room)\n");
 		chunk = alloc_up(room, 0);
 		if (chunk == 0)
-			prom_panic("No memory for flatten_device_tree (claim failed)");
-		*mem_end = RELOC(alloc_top);
+			prom_panic("No memory for flatten_device_tree "
+				   "(claim failed)\n");
+		*mem_end = chunk + room;
 	}
 
 	ret = (void *)*mem_start;
@@ -2042,7 +2044,7 @@ static void __init flatten_device_tree(void)
 
 	/*
 	 * Check how much room we have between alloc top & bottom (+/- a
-	 * few pages), crop to 4Mb, as this is our "chuck" size
+	 * few pages), crop to 1MB, as this is our "chunk" size
 	 */
 	room = RELOC(alloc_top) - RELOC(alloc_bottom) - 0x4000;
 	if (room > DEVTREE_CHUNK_SIZE)
@@ -2053,7 +2055,7 @@ static void __init flatten_device_tree(void)
 	mem_start = (unsigned long)alloc_up(room, PAGE_SIZE);
 	if (mem_start == 0)
 		prom_panic("Can't allocate initial device-tree chunk\n");
-	mem_end = RELOC(alloc_top);
+	mem_end = mem_start + room;
 
 	/* Get root of tree */
 	root = call_prom("peer", 1, 1, (phandle)0);

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -1251,7 +1251,7 @@ BEGIN_FTR_SECTION
 	reg = 0
 	.rept	32
 	li	r6,reg*16+VCPU_VSRS
-	stxvd2x	reg,r6,r3
+	STXVD2X(reg,r6,r3)
 	reg = reg + 1
 	.endr
 FTR_SECTION_ELSE
@@ -1313,7 +1313,7 @@ BEGIN_FTR_SECTION
 	reg = 0
 	.rept	32
 	li	r7,reg*16+VCPU_VSRS
-	lxvd2x	reg,r7,r4
+	LXVD2X(reg,r7,r4)
 	reg = reg + 1
 	.endr
 FTR_SECTION_ELSE

arch/powerpc/platforms/Kconfig

@@ -24,7 +24,7 @@ source "arch/powerpc/platforms/wsp/Kconfig"
 
 config KVM_GUEST
 	bool "KVM Guest support"
-	default y
+	default n
 	---help---
 	  This option enables various optimizations for running under the KVM
 	  hypervisor. Overhead for the kernel when not running inside KVM should

arch/powerpc/platforms/pseries/dtl.c

@@ -181,7 +181,7 @@ static void dtl_stop(struct dtl *dtl)
 
 	lppaca_of(dtl->cpu).dtl_enable_mask = 0x0;
 
-	unregister_dtl(hwcpu, __pa(dtl->buf));
+	unregister_dtl(hwcpu);
 }
 
 static u64 dtl_current_index(struct dtl *dtl)

arch/powerpc/platforms/pseries/hotplug-cpu.c

@@ -135,7 +135,7 @@ static void pseries_mach_cpu_die(void)
 		get_lppaca()->idle = 0;
 
 		if (get_preferred_offline_state(cpu) == CPU_STATE_ONLINE) {
-			unregister_slb_shadow(hwcpu, __pa(get_slb_shadow()));
+			unregister_slb_shadow(hwcpu);
 
 			/*
 			 * Call to start_secondary_resume() will not return.
@@ -150,7 +150,7 @@ static void pseries_mach_cpu_die(void)
 	WARN_ON(get_preferred_offline_state(cpu) != CPU_STATE_OFFLINE);
 
 	set_cpu_current_state(cpu, CPU_STATE_OFFLINE);
-	unregister_slb_shadow(hwcpu, __pa(get_slb_shadow()));
+	unregister_slb_shadow(hwcpu);
 	rtas_stop_self();
 
 	/* Should never get here... */

arch/powerpc/platforms/pseries/io_event_irq.c

@@ -212,17 +212,15 @@ static int __init ioei_init(void)
 	struct device_node *np;
 
 	ioei_check_exception_token = rtas_token("check-exception");
-	if (ioei_check_exception_token == RTAS_UNKNOWN_SERVICE) {
-		pr_warning("IO Event IRQ not supported on this system !\n");
+	if (ioei_check_exception_token == RTAS_UNKNOWN_SERVICE)
 		return -ENODEV;
-	}
+
 	np = of_find_node_by_path("/event-sources/ibm,io-events");
 	if (np) {
 		request_event_sources_irqs(np, ioei_interrupt, "IO_EVENT");
+		pr_info("IBM I/O event interrupts enabled\n");
 		of_node_put(np);
 	} else {
-		pr_err("io_event_irq: No ibm,io-events on system! "
-		       "IO Event interrupt disabled.\n");
 		return -ENODEV;
 	}
 	return 0;

arch/powerpc/platforms/pseries/kexec.c

@@ -25,20 +25,30 @@ static void pseries_kexec_cpu_down(int crash_shutdown, int secondary)
 {
 	/* Don't risk a hypervisor call if we're crashing */
 	if (firmware_has_feature(FW_FEATURE_SPLPAR) && !crash_shutdown) {
-		unsigned long addr;
+		int ret;
+		int cpu = smp_processor_id();
+		int hwcpu = hard_smp_processor_id();
 
-		addr = __pa(get_slb_shadow());
-		if (unregister_slb_shadow(hard_smp_processor_id(), addr))
-			printk("SLB shadow buffer deregistration of "
-			       "cpu %u (hw_cpu_id %d) failed\n",
-			       smp_processor_id(),
-			       hard_smp_processor_id());
+		if (get_lppaca()->dtl_enable_mask) {
+			ret = unregister_dtl(hwcpu);
+			if (ret) {
+				pr_err("WARNING: DTL deregistration for cpu "
+				       "%d (hw %d) failed with %d\n",
+				       cpu, hwcpu, ret);
+			}
+		}
+
+		ret = unregister_slb_shadow(hwcpu);
+		if (ret) {
+			pr_err("WARNING: SLB shadow buffer deregistration "
+			       "for cpu %d (hw %d) failed with %d\n",
+			       cpu, hwcpu, ret);
+		}
 
-		addr = __pa(get_lppaca());
-		if (unregister_vpa(hard_smp_processor_id(), addr)) {
-			printk("VPA deregistration of cpu %u (hw_cpu_id %d) "
-					"failed\n", smp_processor_id(),
-					hard_smp_processor_id());
+		ret = unregister_vpa(hwcpu);
+		if (ret) {
+			pr_err("WARNING: VPA deregistration for cpu %d "
+			       "(hw %d) failed with %d\n", cpu, hwcpu, ret);
 		}
 	}
 }

arch/powerpc/platforms/pseries/lpar.c

@@ -67,9 +67,8 @@ void vpa_init(int cpu)
 	ret = register_vpa(hwcpu, addr);
 
 	if (ret) {
-		printk(KERN_ERR "WARNING: vpa_init: VPA registration for "
-				"cpu %d (hw %d) of area %lx returns %ld\n",
-				cpu, hwcpu, addr, ret);
+		pr_err("WARNING: VPA registration for cpu %d (hw %d) of area "
+		       "%lx failed with %ld\n", cpu, hwcpu, addr, ret);
 		return;
 	}
 	/*
@@ -80,10 +79,9 @@ void vpa_init(int cpu)
 	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
 		ret = register_slb_shadow(hwcpu, addr);
 		if (ret)
-			printk(KERN_ERR
-			       "WARNING: vpa_init: SLB shadow buffer "
-			       "registration for cpu %d (hw %d) of area %lx "
-			       "returns %ld\n", cpu, hwcpu, addr, ret);
+			pr_err("WARNING: SLB shadow buffer registration for "
+			       "cpu %d (hw %d) of area %lx failed with %ld\n",
+			       cpu, hwcpu, addr, ret);
 	}
 
 	/*
@@ -100,8 +98,9 @@ void vpa_init(int cpu)
 		dtl->enqueue_to_dispatch_time = DISPATCH_LOG_BYTES;
 		ret = register_dtl(hwcpu, __pa(dtl));
 		if (ret)
-			pr_warn("DTL registration failed for cpu %d (%ld)\n",
-				cpu, ret);
+			pr_err("WARNING: DTL registration of cpu %d (hw %d) "
+			       "failed with %ld\n", smp_processor_id(),
+			       hwcpu, ret);
 		lppaca_of(cpu).dtl_enable_mask = 2;
 	}
 }
@@ -204,7 +203,7 @@ static void pSeries_lpar_hptab_clear(void)
 		unsigned long ptel;
 	} ptes[4];
 	long lpar_rc;
-	int i, j;
+	unsigned long i, j;
 
 	/* Read in batches of 4,
 	 * invalidate only valid entries not in the VRMA

arch/powerpc/platforms/pseries/plpar_wrappers.h

@@ -53,9 +53,9 @@ static inline long vpa_call(unsigned long flags, unsigned long cpu,
 	return plpar_hcall_norets(H_REGISTER_VPA, flags, cpu, vpa);
 }
 
-static inline long unregister_vpa(unsigned long cpu, unsigned long vpa)
+static inline long unregister_vpa(unsigned long cpu)
 {
-	return vpa_call(0x5, cpu, vpa);
+	return vpa_call(0x5, cpu, 0);
 }
 
 static inline long register_vpa(unsigned long cpu, unsigned long vpa)
@@ -63,9 +63,9 @@ static inline long register_vpa(unsigned long cpu, unsigned long vpa)
 	return vpa_call(0x1, cpu, vpa);
 }
 
-static inline long unregister_slb_shadow(unsigned long cpu, unsigned long vpa)
+static inline long unregister_slb_shadow(unsigned long cpu)
 {
-	return vpa_call(0x7, cpu, vpa);
+	return vpa_call(0x7, cpu, 0);
 }
 
 static inline long register_slb_shadow(unsigned long cpu, unsigned long vpa)
@@ -73,9 +73,9 @@ static inline long register_slb_shadow(unsigned long cpu, unsigned long vpa)
 	return vpa_call(0x3, cpu, vpa);
 }
 
-static inline long unregister_dtl(unsigned long cpu, unsigned long vpa)
+static inline long unregister_dtl(unsigned long cpu)
 {
-	return vpa_call(0x6, cpu, vpa);
+	return vpa_call(0x6, cpu, 0);
 }
 
 static inline long register_dtl(unsigned long cpu, unsigned long vpa)

arch/powerpc/platforms/pseries/setup.c

@@ -324,8 +324,9 @@ static int alloc_dispatch_logs(void)
 	dtl->enqueue_to_dispatch_time = DISPATCH_LOG_BYTES;
 	ret = register_dtl(hard_smp_processor_id(), __pa(dtl));
 	if (ret)
-		pr_warn("DTL registration failed for boot cpu %d (%d)\n",
-			smp_processor_id(), ret);
+		pr_err("WARNING: DTL registration of cpu %d (hw %d) failed "
+		       "with %d\n", smp_processor_id(),
+		       hard_smp_processor_id(), ret);
 	get_paca()->lppaca_ptr->dtl_enable_mask = 2;
 
 	return 0;

arch/powerpc/sysdev/ppc4xx_pci.c

@@ -655,8 +655,6 @@ struct ppc4xx_pciex_hwops
 
 static struct ppc4xx_pciex_hwops *ppc4xx_pciex_hwops;
 
-#ifdef CONFIG_44x
-
 static int __init ppc4xx_pciex_wait_on_sdr(struct ppc4xx_pciex_port *port,
 					   unsigned int sdr_offset,
 					   unsigned int mask,
@@ -688,6 +686,7 @@ static int __init ppc4xx_pciex_port_reset_sdr(struct ppc4xx_pciex_port *port)
 	return 0;
 }
 
+
 static void __init ppc4xx_pciex_check_link_sdr(struct ppc4xx_pciex_port *port)
 {
 	printk(KERN_INFO "PCIE%d: Checking link...\n", port->index);
@@ -718,6 +717,8 @@ static void __init ppc4xx_pciex_check_link_sdr(struct ppc4xx_pciex_port *port)
 		printk(KERN_INFO "PCIE%d: No device detected.\n", port->index);
 }
 
+#ifdef CONFIG_44x
+
 /* Check various reset bits of the 440SPe PCIe core */
 static int __init ppc440spe_pciex_check_reset(struct device_node *np)
 {

arch/sparc/kernel/ds.c

@@ -1256,13 +1256,14 @@ static int __init ds_init(void)
 {
 	unsigned long hv_ret, major, minor;
 
-	hv_ret = sun4v_get_version(HV_GRP_REBOOT_DATA, &major, &minor);
-	if (hv_ret == HV_EOK) {
-		pr_info("SUN4V: Reboot data supported (maj=%lu,min=%lu).\n",
-			major, minor);
-		reboot_data_supported = 1;
+	if (tlb_type == hypervisor) {
+		hv_ret = sun4v_get_version(HV_GRP_REBOOT_DATA, &major, &minor);
+		if (hv_ret == HV_EOK) {
+			pr_info("SUN4V: Reboot data supported (maj=%lu,min=%lu).\n",
+				major, minor);
+			reboot_data_supported = 1;
+		}
 	}
-
 	kthread_run(ds_thread, NULL, "kldomd");
 
 	return vio_register_driver(&ds_driver);

arch/x86/include/asm/desc.h

@@ -27,8 +27,8 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in
 
 	desc->base2		= (info->base_addr & 0xff000000) >> 24;
 	/*
-	 * Don't allow setting of the lm bit. It is useless anyway
-	 * because 64bit system calls require __USER_CS:
+	 * Don't allow setting of the lm bit. It would confuse
+	 * user_64bit_mode and would get overridden by sysret anyway.
 	 */
 	desc->l			= 0;
 }

arch/x86/include/asm/irq_vectors.h

@@ -17,7 +17,6 @@
  *  Vectors   0 ...  31 : system traps and exceptions - hardcoded events
  *  Vectors  32 ... 127 : device interrupts
  *  Vector  128         : legacy int80 syscall interface
- *  Vector  204         : legacy x86_64 vsyscall emulation
  *  Vectors 129 ... INVALIDATE_TLB_VECTOR_START-1 except 204 : device interrupts
  *  Vectors INVALIDATE_TLB_VECTOR_START ... 255 : special interrupts
  *
@@ -51,9 +50,6 @@
 #ifdef CONFIG_X86_32
 # define SYSCALL_VECTOR			0x80
 #endif
-#ifdef CONFIG_X86_64
-# define VSYSCALL_EMU_VECTOR		0xcc
-#endif
 
 /*
  * Vectors 0x30-0x3f are used for ISA interrupts.

arch/x86/include/asm/paravirt_types.h

@@ -41,6 +41,7 @@
 
 #include <asm/desc_defs.h>
 #include <asm/kmap_types.h>
+#include <asm/pgtable_types.h>
 
 struct page;
 struct thread_struct;
@@ -63,6 +64,11 @@ struct paravirt_callee_save {
 struct pv_info {
 	unsigned int kernel_rpl;
 	int shared_kernel_pmd;
+
+#ifdef CONFIG_X86_64
+	u16 extra_user_64bit_cs;  /* __USER_CS if none */
+#endif
+
 	int paravirt_enabled;
 	const char *name;
 };

arch/x86/include/asm/ptrace.h

@@ -131,6 +131,9 @@ struct pt_regs {
 #ifdef __KERNEL__
 
 #include <linux/init.h>
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt_types.h>
+#endif
 
 struct cpuinfo_x86;
 struct task_struct;
@@ -187,6 +190,22 @@ static inline int v8086_mode(struct pt_regs *regs)
 #endif
 }
 
+#ifdef CONFIG_X86_64
+static inline bool user_64bit_mode(struct pt_regs *regs)
+{
+#ifndef CONFIG_PARAVIRT
+	/*
+	 * On non-paravirt systems, this is the only long mode CPL 3
+	 * selector.  We do not allow long mode selectors in the LDT.
+	 */
+	return regs->cs == __USER_CS;
+#else
+	/* Headers are too twisted for this to go in paravirt.h. */
+	return regs->cs == __USER_CS || regs->cs == pv_info.extra_user_64bit_cs;
+#endif
+}
+#endif
+
 /*
  * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode
  * when it traps.  The previous stack will be directly underneath the saved

arch/x86/include/asm/traps.h

@@ -40,7 +40,6 @@ asmlinkage void alignment_check(void);
 asmlinkage void machine_check(void);
 #endif /* CONFIG_X86_MCE */
 asmlinkage void simd_coprocessor_error(void);
-asmlinkage void emulate_vsyscall(void);
 
 dotraplinkage void do_divide_error(struct pt_regs *, long);
 dotraplinkage void do_debug(struct pt_regs *, long);
@@ -67,7 +66,6 @@ dotraplinkage void do_alignment_check(struct pt_regs *, long);
 dotraplinkage void do_machine_check(struct pt_regs *, long);
 #endif
 dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long);
-dotraplinkage void do_emulate_vsyscall(struct pt_regs *, long);
 #ifdef CONFIG_X86_32
 dotraplinkage void do_iret_error(struct pt_regs *, long);
 #endif

arch/x86/include/asm/unistd_64.h

@@ -681,6 +681,8 @@ __SYSCALL(__NR_syncfs, sys_syncfs)
 __SYSCALL(__NR_sendmmsg, sys_sendmmsg)
 #define __NR_setns				308
 __SYSCALL(__NR_setns, sys_setns)
+#define __NR_getcpu				309
+__SYSCALL(__NR_getcpu, sys_getcpu)
 
 #ifndef __NO_STUBS
 #define __ARCH_WANT_OLD_READDIR

arch/x86/include/asm/vsyscall.h

@@ -27,6 +27,12 @@ extern struct timezone sys_tz;
 
 extern void map_vsyscall(void);
 
+/*
+ * Called on instruction fetch fault in vsyscall page.
+ * Returns true if handled.
+ */
+extern bool emulate_vsyscall(struct pt_regs *regs, unsigned long address);
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_VSYSCALL_H */

arch/x86/kernel/Makefile

@@ -17,19 +17,6 @@ CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_early_printk.o = -pg
 endif
 
-#
-# vsyscalls (which work on the user stack) should have
-# no stack-protector checks:
-#
-nostackp := $(call cc-option, -fno-stack-protector)
-CFLAGS_vsyscall_64.o	:= $(PROFILING) -g0 $(nostackp)
-CFLAGS_hpet.o		:= $(nostackp)
-CFLAGS_paravirt.o	:= $(nostackp)
-GCOV_PROFILE_vsyscall_64.o	:= n
-GCOV_PROFILE_hpet.o		:= n
-GCOV_PROFILE_tsc.o		:= n
-GCOV_PROFILE_paravirt.o		:= n
-
 obj-y			:= process_$(BITS).o signal.o entry_$(BITS).o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
 obj-y			+= time.o ioport.o ldt.o dumpstack.o

arch/x86/kernel/cpu/perf_event_intel.c

@@ -1590,6 +1590,7 @@ static __init int intel_pmu_init(void)
 		break;
 
 	case 42: /* SandyBridge */
+	case 45: /* SandyBridge, "Romely-EP" */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 

arch/x86/kernel/entry_64.S

@@ -1111,7 +1111,6 @@ zeroentry spurious_interrupt_bug do_spurious_interrupt_bug
 zeroentry coprocessor_error do_coprocessor_error
 errorentry alignment_check do_alignment_check
 zeroentry simd_coprocessor_error do_simd_coprocessor_error
-zeroentry emulate_vsyscall do_emulate_vsyscall
 
 
 	/* Reload gs selector with exception handling */

arch/x86/kernel/paravirt.c

@@ -307,6 +307,10 @@ struct pv_info pv_info = {
 	.paravirt_enabled = 0,
 	.kernel_rpl = 0,
 	.shared_kernel_pmd = 1,	/* Only used when CONFIG_X86_PAE is set */
+
+#ifdef CONFIG_X86_64
+	.extra_user_64bit_cs = __USER_CS,
+#endif
 };
 
 struct pv_init_ops pv_init_ops = {

arch/x86/kernel/step.c

@@ -74,7 +74,7 @@ static int is_setting_trap_flag(struct task_struct *child, struct pt_regs *regs)
 
 #ifdef CONFIG_X86_64
 		case 0x40 ... 0x4f:
-			if (regs->cs != __USER_CS)
+			if (!user_64bit_mode(regs))
 				/* 32-bit mode: register increment */
 				return 0;
 			/* 64-bit mode: REX prefix */

arch/x86/kernel/traps.c

@@ -872,12 +872,6 @@ void __init trap_init(void)
 	set_bit(SYSCALL_VECTOR, used_vectors);
 #endif
 
-#ifdef CONFIG_X86_64
-	BUG_ON(test_bit(VSYSCALL_EMU_VECTOR, used_vectors));
-	set_system_intr_gate(VSYSCALL_EMU_VECTOR, &emulate_vsyscall);
-	set_bit(VSYSCALL_EMU_VECTOR, used_vectors);
-#endif
-
 	/*
 	 * Should be a barrier for any external CPU state:
 	 */

arch/x86/kernel/vmlinux.lds.S

@@ -71,7 +71,6 @@ PHDRS {
 	text PT_LOAD FLAGS(5);          /* R_E */
 	data PT_LOAD FLAGS(6);          /* RW_ */
 #ifdef CONFIG_X86_64
-	user PT_LOAD FLAGS(5);          /* R_E */
 #ifdef CONFIG_SMP
 	percpu PT_LOAD FLAGS(6);        /* RW_ */
 #endif
@@ -154,44 +153,16 @@ SECTIONS
 
 #ifdef CONFIG_X86_64
 
-#define VSYSCALL_ADDR (-10*1024*1024)
-
-#define VLOAD_OFFSET (VSYSCALL_ADDR - __vsyscall_0 + LOAD_OFFSET)
-#define VLOAD(x) (ADDR(x) - VLOAD_OFFSET)
-
-#define VVIRT_OFFSET (VSYSCALL_ADDR - __vsyscall_0)
-#define VVIRT(x) (ADDR(x) - VVIRT_OFFSET)
-
-	. = ALIGN(4096);
-	__vsyscall_0 = .;
-
-	. = VSYSCALL_ADDR;
-	.vsyscall : AT(VLOAD(.vsyscall)) {
-		*(.vsyscall_0)
-
-		. = 1024;
-		*(.vsyscall_1)
-
-		. = 2048;
-		*(.vsyscall_2)
-
-		. = 4096;  /* Pad the whole page. */
-	} :user =0xcc
-	. = ALIGN(__vsyscall_0 + PAGE_SIZE, PAGE_SIZE);
-
-#undef VSYSCALL_ADDR
-#undef VLOAD_OFFSET
-#undef VLOAD
-#undef VVIRT_OFFSET
-#undef VVIRT
-
+	. = ALIGN(PAGE_SIZE);
 	__vvar_page = .;
 
 	.vvar : AT(ADDR(.vvar) - LOAD_OFFSET) {
+		/* work around gold bug 13023 */
+		__vvar_beginning_hack = .;
 
-	      /* Place all vvars at the offsets in asm/vvar.h. */
-#define EMIT_VVAR(name, offset) 		\
-		. = offset;		\
+		/* Place all vvars at the offsets in asm/vvar.h. */
+#define EMIT_VVAR(name, offset) 			\
+		. = __vvar_beginning_hack + offset;	\
 		*(.vvar_ ## name)
 #define __VVAR_KERNEL_LDS
 #include <asm/vvar.h>

arch/x86/kernel/vsyscall_64.c

@@ -18,9 +18,6 @@
  *  use the vDSO.
  */
 
-/* Disable profiling for userspace code: */
-#define DISABLE_BRANCH_PROFILING
-
 #include <linux/time.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -50,12 +47,36 @@
 #include <asm/vgtod.h>
 #include <asm/traps.h>
 
+#define CREATE_TRACE_POINTS
+#include "vsyscall_trace.h"
+
 DEFINE_VVAR(int, vgetcpu_mode);
 DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data) =
 {
 	.lock = __SEQLOCK_UNLOCKED(__vsyscall_gtod_data.lock),
 };
 
+static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE;
+
+static int __init vsyscall_setup(char *str)
+{
+	if (str) {
+		if (!strcmp("emulate", str))
+			vsyscall_mode = EMULATE;
+		else if (!strcmp("native", str))
+			vsyscall_mode = NATIVE;
+		else if (!strcmp("none", str))
+			vsyscall_mode = NONE;
+		else
+			return -EINVAL;
+
+		return 0;
+	}
+
+	return -EINVAL;
+}
+early_param("vsyscall", vsyscall_setup);
+
 void update_vsyscall_tz(void)
 {
 	unsigned long flags;
@@ -100,7 +121,7 @@ static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
 
 	printk("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
 	       level, tsk->comm, task_pid_nr(tsk),
-	       message, regs->ip - 2, regs->cs,
+	       message, regs->ip, regs->cs,
 	       regs->sp, regs->ax, regs->si, regs->di);
 }
 
@@ -118,46 +139,39 @@ static int addr_to_vsyscall_nr(unsigned long addr)
 	return nr;
 }
 
-void dotraplinkage do_emulate_vsyscall(struct pt_regs *regs, long error_code)
+bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 {
 	struct task_struct *tsk;
 	unsigned long caller;
 	int vsyscall_nr;
 	long ret;
 
-	local_irq_enable();
-
 	/*
-	 * Real 64-bit user mode code has cs == __USER_CS.  Anything else
-	 * is bogus.
+	 * No point in checking CS -- the only way to get here is a user mode
+	 * trap to a high address, which means that we're in 64-bit user code.
 	 */
-	if (regs->cs != __USER_CS) {
-		/*
-		 * If we trapped from kernel mode, we might as well OOPS now
-		 * instead of returning to some random address and OOPSing
-		 * then.
-		 */
-		BUG_ON(!user_mode(regs));
 
-		/* Compat mode and non-compat 32-bit CS should both segfault. */
-		warn_bad_vsyscall(KERN_WARNING, regs,
-				  "illegal int 0xcc from 32-bit mode");
-		goto sigsegv;
+	WARN_ON_ONCE(address != regs->ip);
+
+	if (vsyscall_mode == NONE) {
+		warn_bad_vsyscall(KERN_INFO, regs,
+				  "vsyscall attempted with vsyscall=none");
+		return false;
 	}
 
-	/*
-	 * x86-ism here: regs->ip points to the instruction after the int 0xcc,
-	 * and int 0xcc is two bytes long.
-	 */
-	vsyscall_nr = addr_to_vsyscall_nr(regs->ip - 2);
+	vsyscall_nr = addr_to_vsyscall_nr(address);
+
+	trace_emulate_vsyscall(vsyscall_nr);
+
 	if (vsyscall_nr < 0) {
 		warn_bad_vsyscall(KERN_WARNING, regs,
-				  "illegal int 0xcc (exploit attempt?)");
+				  "misaligned vsyscall (exploit attempt or buggy program) -- look up the vsyscall kernel parameter if you need a workaround");
 		goto sigsegv;
 	}
 
 	if (get_user(caller, (unsigned long __user *)regs->sp) != 0) {
-		warn_bad_vsyscall(KERN_WARNING, regs, "int 0xcc with bad stack (exploit attempt?)");
+		warn_bad_vsyscall(KERN_WARNING, regs,
+				  "vsyscall with bad stack (exploit attempt?)");
 		goto sigsegv;
 	}
 
@@ -202,13 +216,11 @@ void dotraplinkage do_emulate_vsyscall(struct pt_regs *regs, long error_code)
 	regs->ip = caller;
 	regs->sp += 8;
 
-	local_irq_disable();
-	return;
+	return true;
 
 sigsegv:
-	regs->ip -= 2;  /* The faulting instruction should be the int 0xcc. */
 	force_sig(SIGSEGV, current);
-	local_irq_disable();
+	return true;
 }
 
 /*
@@ -256,15 +268,21 @@ cpu_vsyscall_notifier(struct notifier_block *n, unsigned long action, void *arg)
 
 void __init map_vsyscall(void)
 {
-	extern char __vsyscall_0;
-	unsigned long physaddr_page0 = __pa_symbol(&__vsyscall_0);
+	extern char __vsyscall_page;
+	unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
 	extern char __vvar_page;
 	unsigned long physaddr_vvar_page = __pa_symbol(&__vvar_page);
 
-	/* Note that VSYSCALL_MAPPED_PAGES must agree with the code below. */
-	__set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_page0, PAGE_KERNEL_VSYSCALL);
+	__set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_vsyscall,
+		     vsyscall_mode == NATIVE
+		     ? PAGE_KERNEL_VSYSCALL
+		     : PAGE_KERNEL_VVAR);
+	BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_FIRST_PAGE) !=
+		     (unsigned long)VSYSCALL_START);
+
 	__set_fixmap(VVAR_PAGE, physaddr_vvar_page, PAGE_KERNEL_VVAR);
-	BUILD_BUG_ON((unsigned long)__fix_to_virt(VVAR_PAGE) != (unsigned long)VVAR_ADDRESS);
+	BUILD_BUG_ON((unsigned long)__fix_to_virt(VVAR_PAGE) !=
+		     (unsigned long)VVAR_ADDRESS);
 }
 
 static int __init vsyscall_init(void)

arch/x86/kernel/vsyscall_emu_64.S

@@ -7,21 +7,31 @@
  */
 
 #include <linux/linkage.h>
+
 #include <asm/irq_vectors.h>
+#include <asm/page_types.h>
+#include <asm/unistd_64.h>
+
+__PAGE_ALIGNED_DATA
+	.globl __vsyscall_page
+	.balign PAGE_SIZE, 0xcc
+	.type __vsyscall_page, @object
+__vsyscall_page:
+
+	mov $__NR_gettimeofday, %rax
+	syscall
+	ret
 
-/* The unused parts of the page are filled with 0xcc by the linker script. */
+	.balign 1024, 0xcc
+	mov $__NR_time, %rax
+	syscall
+	ret
 
-.section .vsyscall_0, "a"
-ENTRY(vsyscall_0)
-	int $VSYSCALL_EMU_VECTOR
-END(vsyscall_0)
+	.balign 1024, 0xcc
+	mov $__NR_getcpu, %rax
+	syscall
+	ret
 
-.section .vsyscall_1, "a"
-ENTRY(vsyscall_1)
-	int $VSYSCALL_EMU_VECTOR
-END(vsyscall_1)
+	.balign 4096, 0xcc
 
-.section .vsyscall_2, "a"
-ENTRY(vsyscall_2)
-	int $VSYSCALL_EMU_VECTOR
-END(vsyscall_2)
+	.size __vsyscall_page, 4096

arch/x86/kernel/vsyscall_trace.h

@@ -0,0 +1,29 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM vsyscall
+
+#if !defined(__VSYSCALL_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define __VSYSCALL_TRACE_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(emulate_vsyscall,
+
+	    TP_PROTO(int nr),
+
+	    TP_ARGS(nr),
+
+	    TP_STRUCT__entry(__field(int, nr)),
+
+	    TP_fast_assign(
+			   __entry->nr = nr;
+			   ),
+
+	    TP_printk("nr = %d", __entry->nr)
+);
+
+#endif
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH ../../arch/x86/kernel
+#define TRACE_INCLUDE_FILE vsyscall_trace
+#include <trace/define_trace.h>

arch/x86/mm/fault.c

@@ -105,7 +105,7 @@ check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr,
 		 * but for now it's good enough to assume that long
 		 * mode only uses well known segments or kernel.
 		 */
-		return (!user_mode(regs)) || (regs->cs == __USER_CS);
+		return (!user_mode(regs) || user_64bit_mode(regs));
 #endif
 	case 0x60:
 		/* 0x64 thru 0x67 are valid prefixes in all modes. */
@@ -720,6 +720,18 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 		if (is_errata100(regs, address))
 			return;
 
+#ifdef CONFIG_X86_64
+		/*
+		 * Instruction fetch faults in the vsyscall page might need
+		 * emulation.
+		 */
+		if (unlikely((error_code & PF_INSTR) &&
+			     ((address & ~0xfff) == VSYSCALL_START))) {
+			if (emulate_vsyscall(regs, address))
+				return;
+		}
+#endif
+
 		if (unlikely(show_unhandled_signals))
 			show_signal_msg(regs, error_code, address, tsk);
 

arch/x86/vdso/vdso.S

@@ -9,6 +9,7 @@ __PAGE_ALIGNED_DATA
 vdso_start:
 	.incbin "arch/x86/vdso/vdso.so"
 vdso_end:
+	.align PAGE_SIZE /* extra data here leaks to userspace. */
 
 .previous
 

arch/x86/xen/enlighten.c

@@ -951,6 +951,10 @@ static const struct pv_info xen_info __initconst = {
 	.paravirt_enabled = 1,
 	.shared_kernel_pmd = 0,
 
+#ifdef CONFIG_X86_64
+	.extra_user_64bit_cs = FLAT_USER_CS64,
+#endif
+
 	.name = "Xen",
 };
 

arch/x86/xen/mmu.c

@@ -1916,6 +1916,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 # endif
 #else
 	case VSYSCALL_LAST_PAGE ... VSYSCALL_FIRST_PAGE:
+	case VVAR_PAGE:
 #endif
 	case FIX_TEXT_POKE0:
 	case FIX_TEXT_POKE1:
@@ -1956,7 +1957,8 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #ifdef CONFIG_X86_64
 	/* Replicate changes to map the vsyscall page into the user
 	   pagetable vsyscall mapping. */
-	if (idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) {
+	if ((idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) ||
+	    idx == VVAR_PAGE) {
 		unsigned long vaddr = __fix_to_virt(idx);
 		set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte);
 	}

drivers/dma/amba-pl08x.c

@@ -80,6 +80,7 @@
 #include <linux/interrupt.h>
 #include <linux/slab.h>
 #include <linux/delay.h>
+#include <linux/dma-mapping.h>
 #include <linux/dmapool.h>
 #include <linux/dmaengine.h>
 #include <linux/amba/bus.h>

drivers/net/bonding/bond_main.c

@@ -3419,9 +3419,27 @@ static int bond_xmit_hash_policy_l2(struct sk_buff *skb, int count)
 static int bond_open(struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
+	struct slave *slave;
+	int i;
 
 	bond->kill_timers = 0;
 
+	/* reset slave->backup and slave->inactive */
+	read_lock(&bond->lock);
+	if (bond->slave_cnt > 0) {
+		read_lock(&bond->curr_slave_lock);
+		bond_for_each_slave(bond, slave, i) {
+			if ((bond->params.mode == BOND_MODE_ACTIVEBACKUP)
+				&& (slave != bond->curr_active_slave)) {
+				bond_set_slave_inactive_flags(slave);
+			} else {
+				bond_set_slave_active_flags(slave);
+			}
+		}
+		read_unlock(&bond->curr_slave_lock);
+	}
+	read_unlock(&bond->lock);
+
 	INIT_DELAYED_WORK(&bond->mcast_work, bond_resend_igmp_join_requests_delayed);
 
 	if (bond_is_lb(bond)) {

drivers/net/can/sja1000/plx_pci.c

@@ -408,7 +408,7 @@ static void plx_pci_del_card(struct pci_dev *pdev)
 	struct sja1000_priv *priv;
 	int i = 0;
 
-	for (i = 0; i < card->channels; i++) {
+	for (i = 0; i < PLX_PCI_MAX_CHAN; i++) {
 		dev = card->net_dev[i];
 		if (!dev)
 			continue;
@@ -536,7 +536,6 @@ static int __devinit plx_pci_add_card(struct pci_dev *pdev,
 			if (err) {
 				dev_err(&pdev->dev, "Registering device failed "
 					"(err=%d)\n", err);
-				free_sja1000dev(dev);
 				goto failure_cleanup;
 			}
 
@@ -549,6 +548,7 @@ static int __devinit plx_pci_add_card(struct pci_dev *pdev,
 			dev_err(&pdev->dev, "Channel #%d not detected\n",
 				i + 1);
 			free_sja1000dev(dev);
+			card->net_dev[i] = NULL;
 		}
 	}
 

drivers/net/can/slcan.c

@@ -197,7 +197,7 @@ static void slc_bump(struct slcan *sl)
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
 	memcpy(skb_put(skb, sizeof(struct can_frame)),
 	       &cf, sizeof(struct can_frame));
-	netif_rx(skb);
+	netif_rx_ni(skb);
 
 	sl->dev->stats.rx_packets++;
 	sl->dev->stats.rx_bytes += cf.can_dlc;

drivers/net/ethernet/amd/pcnet32.c

@@ -82,7 +82,7 @@ static int cards_found;
 /*
  * VLB I/O addresses
  */
-static unsigned int pcnet32_portlist[] __initdata =
+static unsigned int pcnet32_portlist[] =
     { 0x300, 0x320, 0x340, 0x360, 0 };
 
 static int pcnet32_debug;

drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c

@@ -65,8 +65,9 @@ static inline void bnx2x_bz_fp(struct bnx2x *bp, int index)
 	fp->disable_tpa = ((bp->flags & TPA_ENABLE_FLAG) == 0);
 
 #ifdef BCM_CNIC
-	/* We don't want TPA on FCoE, FWD and OOO L2 rings */
-	bnx2x_fcoe(bp, disable_tpa) = 1;
+	/* We don't want TPA on an FCoE L2 ring */
+	if (IS_FCOE_FP(fp))
+		fp->disable_tpa = 1;
 #endif
 }
 
@@ -1410,10 +1411,9 @@ void bnx2x_netif_stop(struct bnx2x *bp, int disable_hw)
 u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb)
 {
 	struct bnx2x *bp = netdev_priv(dev);
+
 #ifdef BCM_CNIC
-	if (NO_FCOE(bp))
-		return skb_tx_hash(dev, skb);
-	else {
+	if (!NO_FCOE(bp)) {
 		struct ethhdr *hdr = (struct ethhdr *)skb->data;
 		u16 ether_type = ntohs(hdr->h_proto);
 
@@ -1430,8 +1430,7 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb)
 			return bnx2x_fcoe_tx(bp, txq_index);
 	}
 #endif
-	/* Select a none-FCoE queue:  if FCoE is enabled, exclude FCoE L2 ring
-	 */
+	/* select a non-FCoE queue */
 	return __skb_tx_hash(dev, skb, BNX2X_NUM_ETH_QUEUES(bp));
 }
 
@@ -1454,6 +1453,28 @@ void bnx2x_set_num_queues(struct bnx2x *bp)
 	bp->num_queues += NON_ETH_CONTEXT_USE;
 }
 
+/**
+ * bnx2x_set_real_num_queues - configure netdev->real_num_[tx,rx]_queues
+ *
+ * @bp:		Driver handle
+ *
+ * We currently support for at most 16 Tx queues for each CoS thus we will
+ * allocate a multiple of 16 for ETH L2 rings according to the value of the
+ * bp->max_cos.
+ *
+ * If there is an FCoE L2 queue the appropriate Tx queue will have the next
+ * index after all ETH L2 indices.
+ *
+ * If the actual number of Tx queues (for each CoS) is less than 16 then there
+ * will be the holes at the end of each group of 16 ETh L2 indices (0..15,
+ * 16..31,...) with indicies that are not coupled with any real Tx queue.
+ *
+ * The proper configuration of skb->queue_mapping is handled by
+ * bnx2x_select_queue() and __skb_tx_hash().
+ *
+ * bnx2x_setup_tc() takes care of the proper TC mappings so that __skb_tx_hash()
+ * will return a proper Tx index if TC is enabled (netdev->num_tc > 0).
+ */
 static inline int bnx2x_set_real_num_queues(struct bnx2x *bp)
 {
 	int rc, tx, rx;

drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c

@@ -923,7 +923,7 @@ static void bnx2x_dcbx_admin_mib_updated_params(struct bnx2x *bp,
 
 void bnx2x_dcbx_set_state(struct bnx2x *bp, bool dcb_on, u32 dcbx_enabled)
 {
-	if (!CHIP_IS_E1x(bp)) {
+	if (!CHIP_IS_E1x(bp) && !CHIP_IS_E3(bp)) {
 		bp->dcb_state = dcb_on;
 		bp->dcbx_enabled = dcbx_enabled;
 	} else {

drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c

@@ -5794,6 +5794,12 @@ static int bnx2x_init_hw_common(struct bnx2x *bp)
 
 	DP(BNX2X_MSG_MCP, "starting common init  func %d\n", BP_ABS_FUNC(bp));
 
+	/*
+	 * take the UNDI lock to protect undi_unload flow from accessing
+	 * registers while we're resetting the chip
+	 */
+	bnx2x_acquire_hw_lock(bp, HW_LOCK_RESOURCE_UNDI);
+
 	bnx2x_reset_common(bp);
 	REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_1_SET, 0xffffffff);
 
@@ -5804,6 +5810,8 @@ static int bnx2x_init_hw_common(struct bnx2x *bp)
 	}
 	REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_2_SET, val);
 
+	bnx2x_release_hw_lock(bp, HW_LOCK_RESOURCE_UNDI);
+
 	bnx2x_init_block(bp, BLOCK_MISC, PHASE_COMMON);
 
 	if (!CHIP_IS_E1x(bp)) {
@@ -10245,10 +10253,17 @@ static int __devinit bnx2x_init_dev(struct pci_dev *pdev,
 	/* clean indirect addresses */
 	pci_write_config_dword(bp->pdev, PCICFG_GRC_ADDRESS,
 			       PCICFG_VENDOR_ID_OFFSET);
-	REG_WR(bp, PXP2_REG_PGL_ADDR_88_F0 + BP_PORT(bp)*16, 0);
-	REG_WR(bp, PXP2_REG_PGL_ADDR_8C_F0 + BP_PORT(bp)*16, 0);
-	REG_WR(bp, PXP2_REG_PGL_ADDR_90_F0 + BP_PORT(bp)*16, 0);
-	REG_WR(bp, PXP2_REG_PGL_ADDR_94_F0 + BP_PORT(bp)*16, 0);
+	/* Clean the following indirect addresses for all functions since it
+	 * is not used by the driver.
+	 */
+	REG_WR(bp, PXP2_REG_PGL_ADDR_88_F0, 0);
+	REG_WR(bp, PXP2_REG_PGL_ADDR_8C_F0, 0);
+	REG_WR(bp, PXP2_REG_PGL_ADDR_90_F0, 0);
+	REG_WR(bp, PXP2_REG_PGL_ADDR_94_F0, 0);
+	REG_WR(bp, PXP2_REG_PGL_ADDR_88_F1, 0);
+	REG_WR(bp, PXP2_REG_PGL_ADDR_8C_F1, 0);
+	REG_WR(bp, PXP2_REG_PGL_ADDR_90_F1, 0);
+	REG_WR(bp, PXP2_REG_PGL_ADDR_94_F1, 0);
 
 	/*
 	 * Enable internal target-read (in case we are probed after PF FLR).

drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h

@@ -3007,11 +3007,27 @@
 /* [R 6] Debug only: Number of used entries in the data FIFO */
 #define PXP2_REG_HST_DATA_FIFO_STATUS				 0x12047c
 /* [R 7] Debug only: Number of used entries in the header FIFO */
-#define PXP2_REG_HST_HEADER_FIFO_STATUS 			 0x120478
-#define PXP2_REG_PGL_ADDR_88_F0 				 0x120534
-#define PXP2_REG_PGL_ADDR_8C_F0 				 0x120538
-#define PXP2_REG_PGL_ADDR_90_F0 				 0x12053c
-#define PXP2_REG_PGL_ADDR_94_F0 				 0x120540
+#define PXP2_REG_HST_HEADER_FIFO_STATUS				 0x120478
+#define PXP2_REG_PGL_ADDR_88_F0					 0x120534
+/* [R 32] GRC address for configuration access to PCIE config address 0x88.
+ * any write to this PCIE address will cause a GRC write access to the
+ * address that's in t this register */
+#define PXP2_REG_PGL_ADDR_88_F1					 0x120544
+#define PXP2_REG_PGL_ADDR_8C_F0					 0x120538
+/* [R 32] GRC address for configuration access to PCIE config address 0x8c.
+ * any write to this PCIE address will cause a GRC write access to the
+ * address that's in t this register */
+#define PXP2_REG_PGL_ADDR_8C_F1					 0x120548
+#define PXP2_REG_PGL_ADDR_90_F0					 0x12053c
+/* [R 32] GRC address for configuration access to PCIE config address 0x90.
+ * any write to this PCIE address will cause a GRC write access to the
+ * address that's in t this register */
+#define PXP2_REG_PGL_ADDR_90_F1					 0x12054c
+#define PXP2_REG_PGL_ADDR_94_F0					 0x120540
+/* [R 32] GRC address for configuration access to PCIE config address 0x94.
+ * any write to this PCIE address will cause a GRC write access to the
+ * address that's in t this register */
+#define PXP2_REG_PGL_ADDR_94_F1					 0x120550
 #define PXP2_REG_PGL_CONTROL0					 0x120490
 #define PXP2_REG_PGL_CONTROL1					 0x120514
 #define PXP2_REG_PGL_DEBUG					 0x120520

drivers/net/ethernet/freescale/gianfar.c

@@ -2710,8 +2710,13 @@ static int gfar_process_frame(struct net_device *dev, struct sk_buff *skb,
 	/* Tell the skb what kind of packet this is */
 	skb->protocol = eth_type_trans(skb, dev);
 
-	/* Set vlan tag */
-	if (fcb->flags & RXFCB_VLN)
+	/*
+	 * There's need to check for NETIF_F_HW_VLAN_RX here.
+	 * Even if vlan rx accel is disabled, on some chips
+	 * RXFCB_VLN is pseudo randomly set.
+	 */
+	if (dev->features & NETIF_F_HW_VLAN_RX &&
+	    fcb->flags & RXFCB_VLN)
 		__vlan_hwaccel_put_tag(skb, fcb->vlctl);
 
 	/* Send the packet up the stack */

drivers/net/ethernet/freescale/gianfar_ethtool.c

@@ -686,10 +686,21 @@ static int gfar_ethflow_to_filer_table(struct gfar_private *priv, u64 ethflow, u
 {
 	unsigned int last_rule_idx = priv->cur_filer_idx;
 	unsigned int cmp_rqfpr;
-	unsigned int local_rqfpr[MAX_FILER_IDX + 1];
-	unsigned int local_rqfcr[MAX_FILER_IDX + 1];
+	unsigned int *local_rqfpr;
+	unsigned int *local_rqfcr;
 	int i = 0x0, k = 0x0;
 	int j = MAX_FILER_IDX, l = 0x0;
+	int ret = 1;
+
+	local_rqfpr = kmalloc(sizeof(unsigned int) * (MAX_FILER_IDX + 1),
+		GFP_KERNEL);
+	local_rqfcr = kmalloc(sizeof(unsigned int) * (MAX_FILER_IDX + 1),
+		GFP_KERNEL);
+	if (!local_rqfpr || !local_rqfcr) {
+		pr_err("Out of memory\n");
+		ret = 0;
+		goto err;
+	}
 
 	switch (class) {
 	case TCP_V4_FLOW:
@@ -706,7 +717,8 @@ static int gfar_ethflow_to_filer_table(struct gfar_private *priv, u64 ethflow, u
 		break;
 	default:
 		pr_err("Right now this class is not supported\n");
-		return 0;
+		ret = 0;
+		goto err;
 	}
 
 	for (i = 0; i < MAX_FILER_IDX + 1; i++) {
@@ -721,7 +733,8 @@ static int gfar_ethflow_to_filer_table(struct gfar_private *priv, u64 ethflow, u
 
 	if (i == MAX_FILER_IDX + 1) {
 		pr_err("No parse rule found, can't create hash rules\n");
-		return 0;
+		ret = 0;
+		goto err;
 	}
 
 	/* If a match was found, then it begins the starting of a cluster rule
@@ -765,7 +778,10 @@ static int gfar_ethflow_to_filer_table(struct gfar_private *priv, u64 ethflow, u
 		priv->cur_filer_idx = priv->cur_filer_idx - 1;
 	}
 
-	return 1;
+err:
+	kfree(local_rqfcr);
+	kfree(local_rqfpr);
+	return ret;
 }
 
 static int gfar_set_hash_opts(struct gfar_private *priv, struct ethtool_rxnfc *cmd)

drivers/net/ethernet/intel/e1000e/82571.c

@@ -2085,7 +2085,8 @@ struct e1000_info e1000_82574_info = {
 				  | FLAG_HAS_AMT
 				  | FLAG_HAS_CTRLEXT_ON_LOAD,
 	.flags2			  = FLAG2_CHECK_PHY_HANG
-				  | FLAG2_DISABLE_ASPM_L0S,
+				  | FLAG2_DISABLE_ASPM_L0S
+				  | FLAG2_NO_DISABLE_RX,
 	.pba			= 32,
 	.max_hw_frame_size	= DEFAULT_JUMBO,
 	.get_variants		= e1000_get_variants_82571,
@@ -2104,7 +2105,8 @@ struct e1000_info e1000_82583_info = {
 				  | FLAG_HAS_AMT
 				  | FLAG_HAS_JUMBO_FRAMES
 				  | FLAG_HAS_CTRLEXT_ON_LOAD,
-	.flags2			= FLAG2_DISABLE_ASPM_L0S,
+	.flags2			= FLAG2_DISABLE_ASPM_L0S
+				  | FLAG2_NO_DISABLE_RX,
 	.pba			= 32,
 	.max_hw_frame_size	= DEFAULT_JUMBO,
 	.get_variants		= e1000_get_variants_82571,

drivers/net/ethernet/intel/e1000e/e1000.h

@@ -155,6 +155,9 @@ struct e1000_info;
 #define HV_M_STATUS_SPEED_1000            0x0200
 #define HV_M_STATUS_LINK_UP               0x0040
 
+#define E1000_ICH_FWSM_PCIM2PCI		0x01000000 /* ME PCIm-to-PCI active */
+#define E1000_ICH_FWSM_PCIM2PCI_COUNT	2000
+
 /* Time to wait before putting the device into D3 if there's no link (in ms). */
 #define LINK_TIMEOUT		100
 
@@ -453,6 +456,8 @@ struct e1000_info {
 #define FLAG2_DISABLE_ASPM_L0S            (1 << 7)
 #define FLAG2_DISABLE_AIM                 (1 << 8)
 #define FLAG2_CHECK_PHY_HANG              (1 << 9)
+#define FLAG2_NO_DISABLE_RX               (1 << 10)
+#define FLAG2_PCIM2PCI_ARBITER_WA         (1 << 11)
 
 #define E1000_RX_DESC_PS(R, i)	    \
 	(&(((union e1000_rx_desc_packet_split *)((R).desc))[i]))

drivers/net/ethernet/intel/e1000e/ethtool.c

@@ -1206,7 +1206,8 @@ static int e1000_setup_desc_rings(struct e1000_adapter *adapter)
 	rx_ring->next_to_clean = 0;
 
 	rctl = er32(RCTL);
-	ew32(RCTL, rctl & ~E1000_RCTL_EN);
+	if (!(adapter->flags2 & FLAG2_NO_DISABLE_RX))
+		ew32(RCTL, rctl & ~E1000_RCTL_EN);
 	ew32(RDBAL, ((u64) rx_ring->dma & 0xFFFFFFFF));
 	ew32(RDBAH, ((u64) rx_ring->dma >> 32));
 	ew32(RDLEN, rx_ring->size);

drivers/net/ethernet/intel/e1000e/ich8lan.c

@@ -137,8 +137,9 @@
 #define HV_PM_CTRL		PHY_REG(770, 17)
 
 /* PHY Low Power Idle Control */
-#define I82579_LPI_CTRL			PHY_REG(772, 20)
-#define I82579_LPI_CTRL_ENABLE_MASK	0x6000
+#define I82579_LPI_CTRL				PHY_REG(772, 20)
+#define I82579_LPI_CTRL_ENABLE_MASK		0x6000
+#define I82579_LPI_CTRL_FORCE_PLL_LOCK_COUNT	0x80
 
 /* EMI Registers */
 #define I82579_EMI_ADDR         0x10
@@ -163,6 +164,11 @@
 #define HV_KMRN_MODE_CTRL      PHY_REG(769, 16)
 #define HV_KMRN_MDIO_SLOW      0x0400
 
+/* KMRN FIFO Control and Status */
+#define HV_KMRN_FIFO_CTRLSTA                  PHY_REG(770, 16)
+#define HV_KMRN_FIFO_CTRLSTA_PREAMBLE_MASK    0x7000
+#define HV_KMRN_FIFO_CTRLSTA_PREAMBLE_SHIFT   12
+
 /* ICH GbE Flash Hardware Sequencing Flash Status Register bit breakdown */
 /* Offset 04h HSFSTS */
 union ich8_hws_flash_status {
@@ -657,6 +663,7 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw)
 	struct e1000_mac_info *mac = &hw->mac;
 	s32 ret_val;
 	bool link;
+	u16 phy_reg;
 
 	/*
 	 * We only want to go out to the PHY registers to see if Auto-Neg
@@ -689,16 +696,35 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw)
 
 	mac->get_link_status = false;
 
-	if (hw->phy.type == e1000_phy_82578) {
-		ret_val = e1000_link_stall_workaround_hv(hw);
-		if (ret_val)
-			goto out;
-	}
-
-	if (hw->mac.type == e1000_pch2lan) {
+	switch (hw->mac.type) {
+	case e1000_pch2lan:
 		ret_val = e1000_k1_workaround_lv(hw);
 		if (ret_val)
 			goto out;
+		/* fall-thru */
+	case e1000_pchlan:
+		if (hw->phy.type == e1000_phy_82578) {
+			ret_val = e1000_link_stall_workaround_hv(hw);
+			if (ret_val)
+				goto out;
+		}
+
+		/*
+		 * Workaround for PCHx parts in half-duplex:
+		 * Set the number of preambles removed from the packet
+		 * when it is passed from the PHY to the MAC to prevent
+		 * the MAC from misinterpreting the packet type.
+		 */
+		e1e_rphy(hw, HV_KMRN_FIFO_CTRLSTA, &phy_reg);
+		phy_reg &= ~HV_KMRN_FIFO_CTRLSTA_PREAMBLE_MASK;
+
+		if ((er32(STATUS) & E1000_STATUS_FD) != E1000_STATUS_FD)
+			phy_reg |= (1 << HV_KMRN_FIFO_CTRLSTA_PREAMBLE_SHIFT);
+
+		e1e_wphy(hw, HV_KMRN_FIFO_CTRLSTA, phy_reg);
+		break;
+	default:
+		break;
 	}
 
 	/*
@@ -788,6 +814,11 @@ static s32 e1000_get_variants_ich8lan(struct e1000_adapter *adapter)
 	    (adapter->hw.phy.type == e1000_phy_igp_3))
 		adapter->flags |= FLAG_LSC_GIG_SPEED_DROP;
 
+	/* Enable workaround for 82579 w/ ME enabled */
+	if ((adapter->hw.mac.type == e1000_pch2lan) &&
+	    (er32(FWSM) & E1000_ICH_FWSM_FW_VALID))
+		adapter->flags2 |= FLAG2_PCIM2PCI_ARBITER_WA;
+
 	/* Disable EEE by default until IEEE802.3az spec is finalized */
 	if (adapter->flags2 & FLAG2_HAS_EEE)
 		adapter->hw.dev_spec.ich8lan.eee_disable = true;
@@ -1355,7 +1386,7 @@ static s32 e1000_hv_phy_workarounds_ich8lan(struct e1000_hw *hw)
 			return ret_val;
 
 		/* Preamble tuning for SSC */
-		ret_val = e1e_wphy(hw, PHY_REG(770, 16), 0xA204);
+		ret_val = e1e_wphy(hw, HV_KMRN_FIFO_CTRLSTA, 0xA204);
 		if (ret_val)
 			return ret_val;
 	}
@@ -1645,6 +1676,7 @@ static s32 e1000_k1_workaround_lv(struct e1000_hw *hw)
 	s32 ret_val = 0;
 	u16 status_reg = 0;
 	u32 mac_reg;
+	u16 phy_reg;
 
 	if (hw->mac.type != e1000_pch2lan)
 		goto out;
@@ -1659,12 +1691,19 @@ static s32 e1000_k1_workaround_lv(struct e1000_hw *hw)
 		mac_reg = er32(FEXTNVM4);
 		mac_reg &= ~E1000_FEXTNVM4_BEACON_DURATION_MASK;
 
-		if (status_reg & HV_M_STATUS_SPEED_1000)
+		ret_val = e1e_rphy(hw, I82579_LPI_CTRL, &phy_reg);
+		if (ret_val)
+			goto out;
+
+		if (status_reg & HV_M_STATUS_SPEED_1000) {
 			mac_reg |= E1000_FEXTNVM4_BEACON_DURATION_8USEC;
-		else
+			phy_reg &= ~I82579_LPI_CTRL_FORCE_PLL_LOCK_COUNT;
+		} else {
 			mac_reg |= E1000_FEXTNVM4_BEACON_DURATION_16USEC;
-
+			phy_reg |= I82579_LPI_CTRL_FORCE_PLL_LOCK_COUNT;
+		}
 		ew32(FEXTNVM4, mac_reg);
+		ret_val = e1e_wphy(hw, I82579_LPI_CTRL, phy_reg);
 	}
 
 out:

drivers/net/ethernet/intel/e1000e/lib.c

@@ -190,7 +190,8 @@ s32 e1000_check_alt_mac_addr_generic(struct e1000_hw *hw)
 	/* Check for LOM (vs. NIC) or one of two valid mezzanine cards */
 	if (!((nvm_data & NVM_COMPAT_LOM) ||
 	      (hw->adapter->pdev->device == E1000_DEV_ID_82571EB_SERDES_DUAL) ||
-	      (hw->adapter->pdev->device == E1000_DEV_ID_82571EB_SERDES_QUAD)))
+	      (hw->adapter->pdev->device == E1000_DEV_ID_82571EB_SERDES_QUAD) ||
+	      (hw->adapter->pdev->device == E1000_DEV_ID_82571EB_SERDES)))
 		goto out;
 
 	ret_val = e1000_read_nvm(hw, NVM_ALT_MAC_ADDR_PTR, 1,
@@ -200,10 +201,10 @@ s32 e1000_check_alt_mac_addr_generic(struct e1000_hw *hw)
 		goto out;
 	}
 
-	if (nvm_alt_mac_addr_offset == 0xFFFF) {
+	if ((nvm_alt_mac_addr_offset == 0xFFFF) ||
+	    (nvm_alt_mac_addr_offset == 0x0000))
 		/* There is no Alternate MAC Address */
 		goto out;
-	}
 
 	if (hw->bus.func == E1000_FUNC_1)
 		nvm_alt_mac_addr_offset += E1000_ALT_MAC_ADDRESS_OFFSET_LAN1;

drivers/net/ethernet/intel/e1000e/netdev.c

@@ -56,7 +56,7 @@
 
 #define DRV_EXTRAVERSION "-k"
 
-#define DRV_VERSION "1.3.16" DRV_EXTRAVERSION
+#define DRV_VERSION "1.4.4" DRV_EXTRAVERSION
 char e1000e_driver_name[] = "e1000e";
 const char e1000e_driver_version[] = DRV_VERSION;
 
@@ -518,6 +518,63 @@ static void e1000_rx_checksum(struct e1000_adapter *adapter, u32 status_err,
 	adapter->hw_csum_good++;
 }
 
+/**
+ * e1000e_update_tail_wa - helper function for e1000e_update_[rt]dt_wa()
+ * @hw: pointer to the HW structure
+ * @tail: address of tail descriptor register
+ * @i: value to write to tail descriptor register
+ *
+ * When updating the tail register, the ME could be accessing Host CSR
+ * registers at the same time.  Normally, this is handled in h/w by an
+ * arbiter but on some parts there is a bug that acknowledges Host accesses
+ * later than it should which could result in the descriptor register to
+ * have an incorrect value.  Workaround this by checking the FWSM register
+ * which has bit 24 set while ME is accessing Host CSR registers, wait
+ * if it is set and try again a number of times.
+ **/
+static inline s32 e1000e_update_tail_wa(struct e1000_hw *hw, u8 __iomem * tail,
+					unsigned int i)
+{
+	unsigned int j = 0;
+
+	while ((j++ < E1000_ICH_FWSM_PCIM2PCI_COUNT) &&
+	       (er32(FWSM) & E1000_ICH_FWSM_PCIM2PCI))
+		udelay(50);
+
+	writel(i, tail);
+
+	if ((j == E1000_ICH_FWSM_PCIM2PCI_COUNT) && (i != readl(tail)))
+		return E1000_ERR_SWFW_SYNC;
+
+	return 0;
+}
+
+static void e1000e_update_rdt_wa(struct e1000_adapter *adapter, unsigned int i)
+{
+	u8 __iomem *tail = (adapter->hw.hw_addr + adapter->rx_ring->tail);
+	struct e1000_hw *hw = &adapter->hw;
+
+	if (e1000e_update_tail_wa(hw, tail, i)) {
+		u32 rctl = er32(RCTL);
+		ew32(RCTL, rctl & ~E1000_RCTL_EN);
+		e_err("ME firmware caused invalid RDT - resetting\n");
+		schedule_work(&adapter->reset_task);
+	}
+}
+
+static void e1000e_update_tdt_wa(struct e1000_adapter *adapter, unsigned int i)
+{
+	u8 __iomem *tail = (adapter->hw.hw_addr + adapter->tx_ring->tail);
+	struct e1000_hw *hw = &adapter->hw;
+
+	if (e1000e_update_tail_wa(hw, tail, i)) {
+		u32 tctl = er32(TCTL);
+		ew32(TCTL, tctl & ~E1000_TCTL_EN);
+		e_err("ME firmware caused invalid TDT - resetting\n");
+		schedule_work(&adapter->reset_task);
+	}
+}
+
 /**
  * e1000_alloc_rx_buffers - Replace used receive buffers; legacy & extended
  * @adapter: address of board private structure
@@ -573,7 +630,10 @@ map_skb:
 			 * such as IA-64).
 			 */
 			wmb();
-			writel(i, adapter->hw.hw_addr + rx_ring->tail);
+			if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
+				e1000e_update_rdt_wa(adapter, i);
+			else
+				writel(i, adapter->hw.hw_addr + rx_ring->tail);
 		}
 		i++;
 		if (i == rx_ring->count)
@@ -673,7 +733,11 @@ static void e1000_alloc_rx_buffers_ps(struct e1000_adapter *adapter,
 			 * such as IA-64).
 			 */
 			wmb();
-			writel(i << 1, adapter->hw.hw_addr + rx_ring->tail);
+			if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
+				e1000e_update_rdt_wa(adapter, i << 1);
+			else
+				writel(i << 1,
+				       adapter->hw.hw_addr + rx_ring->tail);
 		}
 
 		i++;
@@ -756,7 +820,10 @@ check_page:
 		 * applicable for weak-ordered memory model archs,
 		 * such as IA-64). */
 		wmb();
-		writel(i, adapter->hw.hw_addr + rx_ring->tail);
+		if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
+			e1000e_update_rdt_wa(adapter, i);
+		else
+			writel(i, adapter->hw.hw_addr + rx_ring->tail);
 	}
 }
 
@@ -2915,7 +2982,8 @@ static void e1000_configure_rx(struct e1000_adapter *adapter)
 
 	/* disable receives while setting up the descriptors */
 	rctl = er32(RCTL);
-	ew32(RCTL, rctl & ~E1000_RCTL_EN);
+	if (!(adapter->flags2 & FLAG2_NO_DISABLE_RX))
+		ew32(RCTL, rctl & ~E1000_RCTL_EN);
 	e1e_flush();
 	usleep_range(10000, 20000);
 
@@ -3394,7 +3462,8 @@ void e1000e_down(struct e1000_adapter *adapter)
 
 	/* disable receives in the hardware */
 	rctl = er32(RCTL);
-	ew32(RCTL, rctl & ~E1000_RCTL_EN);
+	if (!(adapter->flags2 & FLAG2_NO_DISABLE_RX))
+		ew32(RCTL, rctl & ~E1000_RCTL_EN);
 	/* flush and sleep below */
 
 	netif_stop_queue(netdev);
@@ -3403,6 +3472,7 @@ void e1000e_down(struct e1000_adapter *adapter)
 	tctl = er32(TCTL);
 	tctl &= ~E1000_TCTL_EN;
 	ew32(TCTL, tctl);
+
 	/* flush both disables and wait for them to finish */
 	e1e_flush();
 	usleep_range(10000, 20000);
@@ -4686,7 +4756,12 @@ static void e1000_tx_queue(struct e1000_adapter *adapter,
 	wmb();
 
 	tx_ring->next_to_use = i;
-	writel(i, adapter->hw.hw_addr + tx_ring->tail);
+
+	if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
+		e1000e_update_tdt_wa(adapter, i);
+	else
+		writel(i, adapter->hw.hw_addr + tx_ring->tail);
+
 	/*
 	 * we need this if more than one processor can write to our tail
 	 * at a time, it synchronizes IO on IA64/Altix systems