aboutsummaryrefslogtreecommitdiff
path: root/drivers
AgeCommit message (Collapse)Author
2007-07-18IB/mlx4: Factor out setting WQE data segment entriesRoland Dreier
Factor code to set data segment entries out of mlx4_ib_post_send() into set_data_seg(). This cleans up the code and lets the compiler do a better job -- on x86_64: add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-16 (-16) function old new delta mlx4_ib_post_send 1598 1582 -16 Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-18IB/mthca: Factor out setting WQE data segment entriesRoland Dreier
Factor code to set data segment entries out of the work request posting functions into inline functions mthca_set_data_seg() and mthca_set_data_seg_inval(). This makes the code more readable and also allows the compiler to do a better job -- on x86_64: add/remove: 0/0 grow/shrink: 0/6 up/down: 0/-69 (-69) function old new delta mthca_arbel_post_srq_recv 373 369 -4 mthca_arbel_post_receive 570 562 -8 mthca_tavor_post_srq_recv 520 508 -12 mthca_tavor_post_send 1344 1330 -14 mthca_arbel_post_send 1481 1467 -14 mthca_tavor_post_receive 792 775 -17 Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17IB/mlx4: Return receive queue sizes for userspace QPs from query QPRoland Dreier
Return the receive queue sizes for both userspace QPs and kernel Qps (not just kernel QPs) from mlx4_ib_query_qp(). Also zero the send queue sizes for userspace QPs to avoid a possible information leak, and set the max_inline_data for kernel QPs to 0 since inline sends are not supported for kernel QPs. Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17IB/mlx4: Increase max outstanding RDMA reads as targetJack Morgenstein
Change the maximum number of outstanding RDMA reads allowed as a target from 4 to 16 to per QP. This allows RDMA read operations to pipeline better. Pointed out by Dotan Barak and Sagi Rotem. Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17RDMA/cma: Remove local write permission from QP access flagsDotan Barak
Local write permission makes no sense as part of the QP access flags, since the access flags only control what the remote end of the connection is allowed to do. Remove the code in the RDMA CM that initializes qp_access_flags with IB_ACCESS_LOCAL_WRITE. Signed-off-by: Dotan Barak <dotanb@mellanox.co.il> Acked-by: Sean Hefty <sean.hefty@intel.com> Acked-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17IB/mthca: Use uninitialized_var() for f0Roland Dreier
Commit 9db48926 ("drivers/infiniband/hw/mthca/mthca_qp: kill uninit'd var warning") added "= 0" to the declarations of f0 to shut up gcc warnings. However, there's no point in making the code bigger by initializing f0 to a random value just to get rid of a warning; setting f0 to 0 is no safer than just using uninitialized_var(), which documents the situation better and gives smaller code too. For example, on x86_64: add/remove: 0/0 grow/shrink: 0/2 up/down: 0/-16 (-16) function old new delta mthca_tavor_post_send 1352 1344 -8 mthca_arbel_post_send 1489 1481 -8 Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17IB/cm: Make internal function cm_get_ack_delay() staticRoland Dreier
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17IB/ipath: Remove ipath_get_user_pages_nocopy()Roland Dreier
It has no callers and is completely dead code. Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17IB/ipath: Make a few functions staticRoland Dreier
Make some functions that are only used in a single .c file static. In addition to being a cleanup, this shrinks the generated code. On x86_64: add/remove: 1/3 grow/shrink: 2/1 up/down: 4777/-4956 (-179) function old new delta handle_errors - 3994 +3994 __verbs_timer 42 710 +668 ipath_do_ruc_send 2131 2246 +115 ipath_no_bufs_available 136 - -136 ipath_disarm_senderrbufs 639 - -639 ipath_ib_timer 658 - -658 ipath_intr 5878 2355 -3523 Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17mlx4_core: Reset device when internal error is detectedJack Morgenstein
Reset the device when an internal error is detected. Also, detect errors by polling the error buffer rather than using interrupts. This is more robust and doesn't depend on MSI-X. Remove the old interrupt handler entirely, since we don't want to support two mechanisms for detecting internal errors. Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17IB/iser: Make a couple of functions staticRoland Dreier
Make iser_conn_release() and iser_start_rdma_unaligned_sg() static, since they are only used in the .c file where they are defined. In addition to being a cleanup, this even shrinks the generated code by allowing the single call of iser_start_rdma_unaligned_sg() to be inlined into its callsite. On x86_64: add/remove: 0/1 grow/shrink: 1/0 up/down: 466/-533 (-67) function old new delta iser_reg_rdma_mem 1518 1984 +466 iser_start_rdma_unaligned_sg 533 - -533 Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17IB/mthca: Fix printk format used for firmware version in warningRoland Dreier
When warning about out-of-date firmware, current mthca code messes up the formatting of the version if the subminor doesn't have three digits. It doesn't fill the field with 0s so we end up with: ib_mthca 0000:0b:00.0: HCA FW version 1.1. 0 is old (1.2. 0 is current). Change the format from "%3d" to "%03d" to get the right thing printed. Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17IB/mthca: Schedule MSI support for removalRoland Dreier
The mthca driver supports both MSI and MSI-X. However, MSI-X works with all hardware that the driver handles, and provides a superset of what MSI does, so there's no point in having code for both. Schedule MSI support for removal in 2008 to give anyone who actually needs MSI and who can't use MSI time to speak up. Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17IB/ehca: Fix warnings issued by checkpatch.plHoang-Nam Nguyen
Run the existing ehca code through checkpatch.pl and clean up the worst of the coding style violations. Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17IB/ehca: Restructure ehca_set_pagebuf()Hoang-Nam Nguyen
Split ehca_set_pagebuf() into three functions depending on MR type (phys/user/fast) and remove superfluous ehca_set_pagebuf_1(). Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17IB/ehca: MR/MW structure refactoringHoang-Nam Nguyen
- Rename struct ehca_mr fields to clearly distinguish between kernel and HW page size. - Sort struct ehca_mr_pginfo into a common part and a union containing specific fields for physical, user and fast MR Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17IB/ehca: Use macro to calculate number of chunks in a mem blockHoang-Nam Nguyen
Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17IB/ehca: Use #define for "pages per register_rpage" instead of hardcoded valueHoang-Nam Nguyen
Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17IB/ehca: Use common error code mapping instead of specific onesHoang-Nam Nguyen
Instead of one error mapping function for each potential error source in ehca_mrmw.c, use a centralized function that handles all cases, saving a three-figure line count. Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17IB/ehca: Fix memory leak in error path of ehca_get_dma_mr()Hoang-Nam Nguyen
Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17IB/ehca: Fix HW level autodetectionJoachim Fenkes
Autodetection was missing a few HW revisions, causing certain eHCA1 revisions to be treated like eHCA2. Fixed. Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17IB/mlx4: Take sizeof the correct pointer in call to memset()Dotan Barak
When clearing the ib_ah_attr parameter in to_ib_ah_attr(), use sizeof *ib_ah_attr instead of sizeof *path. This is the same bug as was fixed for mthca in 99d4f22e ("IB/mthca: Use correct structure size in call to memset()"), but the code was cut and pasted into mlx4 before the fix was merged. Signed-off-by: Dotan Barak <dotanb@mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17IB/mlx4: Fix port returned from query QP for QPs in INIT stateJack Morgenstein
When a QP is in the INIT state, the sched_queue field hasn't been given to the firmware yet, so the firmware cannot return the value when the QP is queried. To handle this, use the port number that is saved in the driver's QP data structure. Found by Dotan Barak and Yaron Gepstein of Mellanox. Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17IB/mlx4: Fix flow label returned from query QPJack Morgenstein
Correct the mask used to get the flow label, since the field is 20 bits, not 24 bits. Found by Dotan Barak and Yaron Gepstein of Mellanox. Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17RDMA/cxgb3: Remove cm_id reference on listen failuresSteve Wise
Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2007-07-17Revert drivers/ide/ide.c scsi_cmd_ioctl() usage changesLinus Torvalds
The old IDE driver is not ready to take generic SCSI commands, even if it uses them for some specific issues (ie the tray open/close ioctls for IDE CD-ROM's). Pointed out by Bartlomiej. I'm sure we'll have it fixed properly soon enough, but for now we should not allow it to cause problems. Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17Make the "z/VM unit record device driver" depend on S390Linus Torvalds
I really don't see anybody else wanting to select it ;) Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17Merge branch 'for-linus' of git://git390.osdl.marist.edu/pub/scm/linux-2.6Linus Torvalds
* 'for-linus' of git://git390.osdl.marist.edu/pub/scm/linux-2.6: [S390] Fix broken logic, SIGA flags must be bitwise ORed [S390] cio: Dont print trailing \0 in modalias_show(). [S390] Simplify stack trace. [S390] z/VM unit record device driver [S390] vmcp cleanup [S390] qdio: output queue stall on FCP and network devices [S390] Fix disassembly of RX_URRD, SI_URD & PC-relative instructions. [S390] Update default configuration.
2007-07-17Merge git://git.kernel.org/pub/scm/linux/kernel/git/wim/linux-2.6-watchdogLinus Torvalds
* git://git.kernel.org/pub/scm/linux/kernel/git/wim/linux-2.6-watchdog: (21 commits) [WATCHDOG] at32ap700x_wdt.c - Fix compilation warnings [WATCHDOG] at32ap700x_wdt.c - Add spinlock support [WATCHDOG] at32ap700x_wdt.c - Add nowayout + MAGICCLOSE features [WATCHDOG] at32ap700x_wdt.c - timeout module parameter patch [WATCHDOG] at32ap700x_wdt.c - checkpatch.pl-0.05 clean-up's [WATCHDOG] change s3c2410_wdt to using dev_() macros for output [WATCHDOG] s3c2410_wdt announce initialisation [WATCHDOG] at32ap700x-wdt: add iounmap if probe function fails [WATCHDOG] at32ap700x-wdt: add missing iounmap in _remove [WATCHDOG] watchdog-driver-for-at32ap700x-devices-fix-2 [WATCHDOG] watchdog-driver-for-at32ap700x-devices-fix [WATCHDOG] Watchdog driver for AT32AP700X devices [WATCHDOG] Mixcom Watchdog - CodingStyle clean-up [WATCHDOG] Mixcom Watchdog - clean-up printk's [WATCHDOG] Mixcom Watchdog - clean-up printk's [WATCHDOG] Mixcom Watchdog - checkcard part 2 [WATCHDOG] Mixcom Watchdog - checkcard [WATCHDOG] Mixcom Watchdog - get rid of port offset's [WATCHDOG] Mixcom Watchdog - update "Documentation" [WATCHDOG] Remove the redundant check for pwrite() in EP93XXX watchdog. ...
2007-07-17Merge branch 'isdn-cleanup' of ↵Linus Torvalds
master.kernel.org:/pub/scm/linux/kernel/git/jgarzik/misc-2.6 * 'isdn-cleanup' of master.kernel.org:/pub/scm/linux/kernel/git/jgarzik/misc-2.6: [ISDN] HiSax hfc_pci: minor cleanups [ISDN] HiSax bkm_a4t: split setup into two smaller functions [ISDN] HiSax enternow: split setup into 3 smaller functions [ISDN] HiSax netjet_u: split setup into 3 smaller functions [ISDN] HiSax netjet_s: code movement, prep for hotplug [ISDN] HiSax: move card state alloc/setup code into separate functions [ISDN] HiSax: move card setup into separate function
2007-07-17Merge branch 'uninit-var' of ↵Linus Torvalds
master.kernel.org:/pub/scm/linux/kernel/git/jgarzik/misc-2.6 * 'uninit-var' of master.kernel.org:/pub/scm/linux/kernel/git/jgarzik/misc-2.6: arch/i386/* fs/* ipc/*: mark variables with uninitialized_var() drivers/*: mark variables with uninitialized_var()
2007-07-17Merge branch 'warnings' of ↵Linus Torvalds
master.kernel.org:/pub/scm/linux/kernel/git/jgarzik/misc-2.6 * 'warnings' of master.kernel.org:/pub/scm/linux/kernel/git/jgarzik/misc-2.6: drivers/atm/ambassador: kill uninit'd var warning, and fix bug [libata] sata_mv: use pci_try_set_mwi() drivers/infiniband/hw/mthca/mthca_qp: kill uninit'd var warning drivers/net/wan/sbni: kill uninit'd var warning drivers/mtd/ubi/eba: minor cleanup: tighten scope of a local var drivers/telephony/ixj: cleanup and fix gcc warning drivers/net/wan/pc300_drv: fix bug caught by gcc warning drivers/usb/misc/auerswald: fix status check, remove redundant check [netdrvr] eepro100, ne2k-pci: abort resume if pci_enable_device() fails [netdrvr] natsemi: Fix device removal bug kernel/auditfilter: kill bogus uninit'd-var compiler warning
2007-07-17[ISDN] HiSax hfc_pci: minor cleanupsJeff Garzik
* trim trailing whitespace * remove CONFIG_PCI ifdefs, this driver is always PCI (Kconfig enforced) * remove return statements at the tail of a function * remove indentation levels by returning an error code immediately. Makes the code much more readable, and easier to update to PCI hotplug API. Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-17[ISDN] HiSax bkm_a4t: split setup into two smaller functionsJeff Garzik
No behavior changes, just code movement. Prep for PCI hotplug API. Well, CONFIG_PCI useless ifdef was removed. Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-17[ISDN] HiSax enternow: split setup into 3 smaller functionsJeff Garzik
No behavior changes, just code movement. Prep for PCI hotplug API. Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-17[ISDN] HiSax netjet_u: split setup into 3 smaller functionsJeff Garzik
No behavior changes, just code movement. Prep for PCI hotplug API. Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-17[ISDN] HiSax netjet_s: code movement, prep for hotplugJeff Garzik
1) Remove CONFIG_PCI ifdefs. PCI is required in Kconfig. 2) Break up setup_netjet_s() into three separate internal functions. This helps facilitate upcoming use of PCI hotplug API, and in addition makes the code much easier to follow. No code is changed, just moved around. I even kept the out-of-favor "return(0)" style used in the current source code. Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-17[ISDN] HiSax: move card state alloc/setup code into separate functionsJeff Garzik
Just code movement. No code changes or cleanups besides that which is required to call the new functions from the old code site. Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-17[ISDN] HiSax: move card setup into separate functionJeff Garzik
No behavior changes, just code movement. Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-17hppb: Add missing dma-mapping.h includeFrank Lichtenheld
This fixes the following build-error: CC drivers/parisc/hppb.o drivers/parisc/hppb.c: In function ‘hppb_probe’: drivers/parisc/hppb.c:73: error: implicit declaration of function ‘ccio_request_resource’ Signed-off-by: Frank Lichtenheld <frank@lichtenheld.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17drivers/*: mark variables with uninitialized_var()Jeff Garzik
Mark variables in drivers/* with uninitialized_var() if such a warning appears, and analysis proves that the var is initialized properly on all paths it is used. Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-17drivers/atm/ambassador: kill uninit'd var warning, and fix bugJeff Garzik
An uninitialized variable warning illuminated an area where indeed the variable was being used without initialization. Unfortunately, after verifying all such paths were fixed, the warning still appears. So we follow the initialization practice of other variables in this function. Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-17[libata] sata_mv: use pci_try_set_mwi()Jeff Garzik
Because sometimes in life, it's ok to fail. Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-17drivers/infiniband/hw/mthca/mthca_qp: kill uninit'd var warningJeff Garzik
drivers/infiniband/hw/mthca/mthca_qp.c: In function ‘mthca_tavor_post_send’: drivers/infiniband/hw/mthca/mthca_qp.c:1594: warning: ‘f0’ may be used uninitialized in this function drivers/infiniband/hw/mthca/mthca_qp.c: In function ‘mthca_arbel_post_send’: drivers/infiniband/hw/mthca/mthca_qp.c:1949: warning: ‘f0’ may be used uninitialized in this function Initializing 'f0' is not strictly necessary in either case, AFAICS. I was considering use of uninitialized_var(), but looking at the complex flow of control in each function, I feel it is wiser and safer to simply zero the var and be certain of ourselves. Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-17drivers/net/wan/sbni: kill uninit'd var warningJeff Garzik
It's actually convenient in the code to initialize this and a sister variable to zero. Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-17drivers/mtd/ubi/eba: minor cleanup: tighten scope of a local varJeff Garzik
Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-17drivers/telephony/ixj: cleanup and fix gcc warningJeff Garzik
1) Fix gcc uninit'd var warnings by adding 'default' switch stmt labels in two cases. It was lightning-strikes unlikely that a problem would ever arise, but not impossible. 2) Tighten the scope of 'blankword' in two cases. Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-17drivers/net/wan/pc300_drv: fix bug caught by gcc warningJeff Garzik
The warning drivers/net/wan/pc300_drv.c: In function ‘cpc_open’: drivers/net/wan/pc300_drv.c:2942: warning: ‘br’ may be used uninitialized in this function was valid. Ensure 'br' is initialized in all cases. Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-17drivers/usb/misc/auerswald: fix status check, remove redundant checkJeff Garzik
1) We should only set 'actual_length' output variable if usb length is known to be good. 2) No need to check actual_length for NULL. The only caller always passes non-NULL value. Signed-off-by: Jeff Garzik <jeff@garzik.org>
2007-07-17[netdrvr] eepro100, ne2k-pci: abort resume if pci_enable_device() failsJeff Garzik
Signed-off-by: Jeff Garzik <jeff@garzik.org>
generated by cgit v1.2.3 (git 2.25.1) at 2024-10-23 20:48:16 +0000