summaryrefslogtreecommitdiff
path: root/drivers/net/cnic.c
AgeCommit message (Collapse)Author
2011-05-22Add appropriate <linux/prefetch.h> include for prefetch usersPaul Gortmaker
After discovering that wide use of prefetch on modern CPUs could be a net loss instead of a win, net drivers which were relying on the implicit inclusion of prefetch.h via the list headers showed up in the resulting cleanup fallout. Give them an explicit include via the following $0.02 script. ========================================= #!/bin/bash MANUAL="" for i in `git grep -l 'prefetch(.*)' .` ; do grep -q '<linux/prefetch.h>' $i if [ $? = 0 ] ; then continue fi ( echo '?^#include <linux/?a' echo '#include <linux/prefetch.h>' echo . echo w echo q ) | ed -s $i > /dev/null 2>&1 if [ $? != 0 ]; then echo $i needs manual fixup MANUAL="$i $MANUAL" fi done echo ------------------- 8\<---------------------- echo vi $MANUAL ========================================= Signed-off-by: Paul <paul.gortmaker@windriver.com> [ Fixed up some incorrect #include placements, and added some non-network drivers and the fib_trie.c case - Linus ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-04-08cnic: Fix rtnl deadlockMichael Chan
When cnic_stop_hw() -> cnic_cm_stop_bnx2x_hw() is called under rtnl_lock() from NETDEV_DOWN event, it waits for cnic_delete_task() to complete. It will deadlock when cnic_delete_task() takes rtnl_lock() before calling cnic_ulp_stop_one(). We fix it by removing the rtnl_lock() in cnic_delete_task(). cnic_ulp_stop_one() has mutex and atomic bit ops to prevent important operations from being done more than once, so it is not necessary to take rtnl_lock(). Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-03-31bnx2x, cnic: Disable iSCSI if DCBX negotiation is successfulDmitry Kravkov
With current bnx2x firmware 6.2.9, iSCSI is not supported in DCB network, so we need to disable it. Add cnic command to disconnect iSCSI connections and prevent future connections when DCBX negotiation succeeds. Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com> Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-03-12ipv6: Convert to use flowi6 where applicable.David S. Miller
Signed-off-by: David S. Miller <davem@davemloft.net>
2011-03-12net: Put flowi_* prefix on AF independent members of struct flowiDavid S. Miller
I intend to turn struct flowi into a union of AF specific flowi structs. There will be a common structure that each variant includes first, much like struct sock_common. This is the first step to move in that direction. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-03-12ipv4: Create and use route lookup helpers.David S. Miller
The idea here is this minimizes the number of places one has to edit in order to make changes to how flows are defined and used. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-03-03Merge branch 'master' of ↵David S. Miller
master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6 Conflicts: drivers/net/bnx2x/bnx2x.h
2011-03-02cnic: Fix lost interrupt on bnx2xMichael Chan
We service 2 queues (kcq1 and kcq2) in cnic_service_bnx2x_bh(). If the status block index has changed when servicing the kcq2, we must go back and check kcq1. The latest status block index will be used to acknowledge the interrupt, and without looping back to check kcq1, we may miss events on kcq1. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-03-02cnic: Prevent status block race conditions with hardwareMichael Chan
The status block index is used to acknowledge interrupt events and must be read before checking for the interrupt events, so we need to add rmb() to guarantee that. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-03-02ipv4: Make output route lookup return rtable directly.David S. Miller
Instead of on the stack. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-28net: use pci_dev->revision, againSergei Shtylyov
Several more network drivers that read the device's revision ID from the PCI configuration register were merged after the commit 44c10138fd4bbc4b6d6bff0873c24902f2a9da65 (PCI: Change all drivers to use pci_device->revision), so it's time to do another pass of conversion to using the 'revision' field of 'struct pci_dev'... Signed-off-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Acked-by: "John W. Linville" <linville@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-31bnx2x, cnic: Consolidate iSCSI/FCoE shared mem logic in bnx2xVladislav Zolotarov
Move all shared mem code to bnx2x to avoid code duplication. bnx2x now performs: - Read the FCoE and iSCSI max connection information. - Read the iSCSI and FCoE MACs from NPAR configuration in shmem. - Block the CNIC for the current function if there is neither FCoE nor iSCSI valid configuration by returning NULL from bnx2x_cnic_probe(). Signed-off-by: Vladislav Zolotarov <vladz@broadcom.com> Signed-off-by: Eilon Greenstein <eilong@broadcom.com> Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-27drivers/net: remove some rcu sparse warningsEric Dumazet
Add missing __rcu annotations and helpers. minor : Fix some rcu_dereference() calls in macvtap Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Acked-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-26cnic: Fix big endian bugMichael Chan
The chip's page tables did not set up properly on big endian machines, causing EEH errors on PPC machines. Reported-by: Breno Leitao <leitao@linux.vnet.ibm.com> Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-06cnic: Fix the type field in SPQ messagesMichael Chan
The new firmware interface requires each Slow Path Queue (SPQ) message's type field to include the function number. The existing code does not do this consistently. We fix this by OR'ing in the function number into the type field centrally in cnic_submit_kwqe_16(). Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-04Merge branch 'master' of ↵David S. Miller
master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6
2011-01-03cnic: Do not call bnx2i when bnx2i is calling cnic_unregister_driver()Michael Chan
We should call bnx2i to send the iSCSI netlink message earlier in cnic_unregister_device(). By the time cnic_unregister_driver() is called, bnx2i may have freed data structures used by the upcalls. Update version to 2.2.12. Reviewed-by: Benjamin Li <benli@broadcom.com> Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-03cnic: Do not allow iSCSI and FCoE on bnx2x multi-function modeMichael Chan
Because the hardware does not yet support these in this mode. Reviewed-by: Benjamin Li <benli@broadcom.com> Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-12-31Broadcom CNIC core network driver: fix mem leak on allocation failures in ↵Jesper Juhl
cnic_alloc_uio_rings() We are leaking memory in drivers/net/cnic.c::cnic_alloc_uio_rings() if either of the calls to dma_alloc_coherent() fail. This patch fixes it by freeing both the memory allocated with kzalloc() and memory allocated with previous calls to dma_alloc_coherent() when there's a failure. Thanks to Joe Perches <joe@perches.com> for suggesting a better implementation than my initial version. Signed-off-by: Jesper Juhl <jj@chaosbits.net> Acked-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-12-23cnic: Add FCoE support on 57712Michael Chan
- Connection ID (cid) management - Slow-path command and response support - Update version to 2.2.11. Reviewed-by: Bhanu Prakash Gollapudi <bprakash@broadcom.com> Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-12-23cnic: Add kcq2 support on 57712Michael Chan
The kcq2 (2nd kernel work queue) is used by FCoE on 57712 devices. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-12-23cnic: Call cm_connect_complete() immediately on errorEddie Wai
If we get a path_resp error from userspace, call cm_connect_complete() immediately with error so that bnx2i can react to the error faster. Signed-off-by: Eddie Wai <waie@broadcom.com> Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-12-23cnic: Check device state before reading the kcq pointer in IRQMichael Chan
If the device is down, the kcq pointer may be NULL. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-12-23cnic: Support NIC Partition modeMichael Chan
Add a common function cnic_read_bnx2x_iscsi_mac() to read the iSCSI MAC address at any specified shared memory location. In NIC Partition mode, we need to get the MAC address from the MF_CFG area of shared memory. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-12-23cnic: Use proper client and connection IDs on iSCSI ringMichael Chan
Use the IDs specified by the bnx2x driver when initializing the ring. We don't have to make code changes when these IDs change in the future. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-12-23cnic: Improve ->iscsi_nl_msg_send()Michael Chan
1. Change first parameter from cnic_dev to ulp_handle which is the hba pointer. All other similar upcalls are using hba pointer. The callee can then directly reference the hba without conversion. 2. Change return value from void to int so that an error code can be passed back. This allows the operation to be retried. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-12-23cnic: Prevent "scheduling while atomic" when calling ->cnic_init()Michael Chan
cnic_dev_list is protected by rtnl_lock and cnic_dev_lock spin_lock during modifications. When looping on cnic_dev_list and calling ->cnic_init(), we should just hold rtnl_lock since ->cnic_init() may sleep. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-12-23cnic: Fix iSCSI TCP port endian order.Michael Chan
Pass the TCP port parameter for iSCSI connections to the firmware in proper endian order. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-11-15drivers/net/cnic.c: Remove unnecessary semicolonsJoe Perches
Signed-off-by: Joe Perches <joe@perches.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-14cnic: Add support for 57712 deviceMichael Chan
Add new interrupt ack functions and other hardware interface logic to support the new device. Update version to 2.2.6. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-14cnic: Decouple uio close from cnic shutdownMichael Chan
During cnic shutdown, the original driver code requires userspace to close the uio device within a few seconds. This doesn't always happen as the userapp may be hung or otherwise take a long time to close. The system may crash when this happens. We fix the problem by decoupling the uio structures from the cnic structures during cnic shutdown. We do not unregister the uio device until the cnic driver is unloaded. This eliminates the unreliable wait loop for uio to close. All uio structures are kept in a linked list. If the device is shutdown and later brought back up again, the uio strcture will be found in the linked list and coupled back to the cnic structures. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-14cnic: Add cnic_uio_dev structMichael Chan
and put all uio related structures and ring buffers in it. This allows uio operations to be done independent of the cnic device structures. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-14cnic: Add cnic_free_uio()Michael Chan
to free all UIO related structures. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-14cnic: Defer iscsi connection cleanupMichael Chan
The bnx2x devices require a 2 second quiet time before sending the last RAMROD command to destroy a connection. This sleep wait adds up to a long delay when iscsid is serially destroying maultiple connections. Create a workqueue to perform the final connection cleanup in the background to speed up the process. This significantly speeds up the process as the wait time can be done in parallel for multiple connections. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-14cnic: Add cnic_bnx2x_destroy_ramrod()Michael Chan
Refactoring code for the next patch to defer connection clean up. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-14cnic: Convert ctx_flags to bit fieldsMichael Chan
so that we can additional bit definitions without requiring a spinlock. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-14cnic: Add common cnic_request_irq()Michael Chan
to reduce some duplicate code. Also, use tasklet_kill() in cnic_free_irq() to wait for the cnic_irq_task to complete. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-06bnx2x, cnic: Fix SPQ return creditDmitry Kravkov
Return proper L2 and L5 SPQ (slow path queue) credits. Previously, all SPQ events were counted as L5 types. Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com> Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: Eilon Greenstein <eilong@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-06bnx2x, cnic, bnx2i: use new FW/HSIDmitry Kravkov
This is the new FW HSI blob and the relevant definitions without logic changes. It also included code adaptation for new HSI. New features are not enabled. New FW/HSI includes: - Support for 57712 HW - Future support for VF (not used) - Improvements in FW interrupts scheme - FW FCoE hooks (stubs for future usage) Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com> Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: Eilon Greenstein <eilong@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-06cnic: Fine-tune ring init code.Michael Chan
Initialize the rings only during cnic_uio_open() and shut them down during cnic_uio_close(). Check for the new bit CNIC_LCL_FL_RINGS_INITED before checking for ring interrupt. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-06cnic: Use pfid for internal memory offsets.Michael Chan
The pfid (physical function ID) is the same as PCI function on production devices. The pfid for future devices will be different and will be used for internal memory offsets. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-06cnic: Pass cp pointer to BNX2X_HW_CID.Michael Chan
Preparation work for upcoming firmware interface changes. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-08-17drivers/net: Convert unbounded kzalloc calls to kcallocJoe Perches
These changes may be slightly safer in some instances. There are other kzalloc calls with a multiply, but those calls are typically "small fixed #" * sizeof(some pointer)" and those are not converted. Signed-off-by: Joe Perches <joe@perches.com> Acked-by: Gertjan van Wingerde <gwingerde@gmail.com> Acked-by: Luciano Coelho <luciano.coelho@nokia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-07-27bnx2x: Create separate folder for bnx2x driverDmitry Kravkov
This commit includes files movement to newly created folder using git-mv command and fixes references in cnic and bnx2x code to each other. files moved using following: #!/bin/bash mkdir drivers/net/bnx2x/ list=$(cd drivers/net/ && ls bnx2x*.[ch]) for f in $list; do git mv -f drivers/net/$f drivers/net/bnx2x/$f done Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com> Signed-off-by: Eilon Greenstein <eilong@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-06-25cnic: Further unify kcq handling code.Michael Chan
This eliminates some of the duplicate code for the various devices that require the same basic kcq handling. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-06-25cnic: Restructure kcq processing.Michael Chan
By doing more work in the common function cnic_get_kcqes(), and making full use of the kcq_info structure. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-06-25cnic: Unify kcq allocation for all devices.Michael Chan
By creating a common data stucture kcq_info for all devices, the kcq (kernel completion queue) for all devices can be allocated by common code. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-06-25cnic: Unify IRQ code for all hardware types.Michael Chan
By creating a common cnic_doirq(). Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-06-25cnic: Fine-tune CID memory space calculation.Michael Chan
The current code makes assumptions about the CID (context ID) memory space and starting CID that may not be always correct when firmware changes. In particular, BNX2_ISCSI_START_CID may not always be fixed. We now calculate cp->max_cid_space and cp->iscsi_start_cid dynamically instead of using fixed constants. The unused cp->max_iscsi_conn is also eliminated. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-06-23Merge branch 'master' of ↵David S. Miller
master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6 Conflicts: net/ipv4/ip_output.c
generated by cgit v1.2.3 (git 2.0.4) at 2024-11-18 16:36:20 +0000