summaryrefslogtreecommitdiffstats
path: root/drivers
Commit message (Collapse)AuthorAgeFilesLines
* sky2: don't clear phy power bitsStephen Hemminger2007-08-211-2/+2
| | | | | | | | | There are special PHY settings available on Yukon EC-U chip that should not get cleared. This should solve mysterious errors on some motherboards (like Gigabyte DS-3). Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* hisax: update hfc_usb driverMartin Bachem2007-08-212-445/+288
| | | | | | | | | | This fixes handling of USB ISO completion error -EXDEV and includes several other changes to current CVS version at isdn4linux.de (changes in debug flags, style of code remarks, etc) Signed-off-by: Martin Bachem <info@colognechip.com> Acked-by: Karsten Keil <kkeil@suse.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* Revert "USB: EHCI cpufreq fix"Linus Torvalds2007-08-205-215/+0
| | | | | | | | | | | | | This reverts commit 196705c9bbc03540429b0f7cf9ee35c2f928a534. It was reported to cause a regression by Daniel Exner, and Arjan van de Ven points out that we actually already have infrastructure in place for setting limits on acceptable DMA latency that would be the much more correct fix for the problem with some Broadcom EHCI controllers. Fixed up trivial conflicts due to the changes to support big-endian host controller descriptors in drivers/usb/host/{ehci-sched.c,ehci.h}. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* Merge git://git.kernel.org/pub/scm/linux/kernel/git/bart/ide-2.6Linus Torvalds2007-08-2012-72/+109
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * git://git.kernel.org/pub/scm/linux/kernel/git/bart/ide-2.6: ide-disk: workaround for buggy HPA support on ST340823A (take 3) hpt34x: fix CONFIG_HPT34X_AUTODMA=n handling triflex: add missing ->dma_base check pdc202xx_old: add missing ->dma_base check pdc202xx_new: add missing ->dma_base check cs5530: add missing ->dma_base check ide: ide_config_drive_speed() bugfixes ide: add cable detection for early UDMA66 devices (take 3) ide-pmac: fix drive->init_speed reporting ide: config_drive_for_dma() fixes ide-cris: fix ->set_pio_mode method to set transfer mode on the device ide: fix hidden dependencies on CONFIG_IDE_GENERIC ide: make CONFIG_IDE_GENERIC default to N
| * ide-disk: workaround for buggy HPA support on ST340823A (take 3)Bartlomiej Zolnierkiewicz2007-08-202-0/+20
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This disk reports total number of sectors instead of maximum sector address in response to READ_NATIVE_MAX_ADDRESS command and also happily accepts SET_MAX_ADDRESS command with the bogus value. This results in +1 sector capacity being used and errors on attempts to use the last sector. ... hdd: Host Protected Area detected.         current capacity is 78165360 sectors (40020 MB)         native  capacity is 78165361 sectors (40020 MB) hdd: Host Protected Area disabled. ... hdd: reading: block=78165360, sectors=1, buffer=0xc1e63000 hdd: dma_intr: status=0x51 { DriveReady SeekComplete Error } hdd: dma_intr: error=0x10 { SectorIdNotFound }, LBAsect=78165360, sector=78165360 ... Add hpa_list[] table and workaround the issue in idedisk_check_hpa(). v2: * Add missing export and improve patch description a bit. v3: * Add list termination. (From Mikko) Fixes kernel bugzilla bug #8816. Thanks to Mikko for investigating the issue and helping with this patch. Cc: Mikko Rapeli <mikko.rapeli@iki.fi> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
| * hpt34x: fix CONFIG_HPT34X_AUTODMA=n handlingBartlomiej Zolnierkiewicz2007-08-201-4/+2
| | | | | | | | | | | | | | | | | | | | | | Programming DMA mode may destroy current PIO mode setting so if CONFIG_HPT34X_AUTODMA=n (the default case) make ide_tune_dma() fail early by disabling all host DMA masks and re-tune PIO mode. This fix doesn't help with the driver being broken but is needed for some other changes. Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
| * triflex: add missing ->dma_base checkBartlomiej Zolnierkiewicz2007-08-201-0/+3
| | | | | | | | | | | | | | | | If ->dma_base is not set (== PCI BAR4 cannot be reserved) then DMA hooks shouldn't be initialized or bad things will happen. Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
| * pdc202xx_old: add missing ->dma_base checkBartlomiej Zolnierkiewicz2007-08-201-3/+6
| | | | | | | | | | | | | | | | If ->dma_base is not set (== PCI BAR4 cannot be reserved) then DMA hooks shouldn't be initialized or bad things will happen. Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
| * pdc202xx_new: add missing ->dma_base checkBartlomiej Zolnierkiewicz2007-08-201-2/+8
| | | | | | | | | | | | | | | | | | | | If ->dma_base is not set (== PCI BAR4 cannot be reserved) then DMA hooks shouldn't be initialized or bad things will happen. Also this host driver requires valid PCI BAR4 for normal operation so check it in ->init_chipset and fail initialization if not set. Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
| * cs5530: add missing ->dma_base checkBartlomiej Zolnierkiewicz2007-08-201-1/+7
| | | | | | | | | | | | | | | | | | | | If ->dma_base is not set (== PCI BAR4 cannot be reserved) then DMA hooks shouldn't be initialized or bad things will happen. Also this host driver requires valid PCI BAR4 for normal operation so check it in ->init_chipset and fail initialization if not set. Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
| * ide: ide_config_drive_speed() bugfixesBartlomiej Zolnierkiewicz2007-08-201-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | * Use ->OUTBSYNC instead of ->OUTB when writing command register (needed for scc_pata and pmac host drivers). * Don't check DRDY bit of the status register on ATAPI devices (ATAPI devices are free to ignore DRDY bit). Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Kou Ishizaki <kou.ishizaki@toshiba.co.jp> Cc: Akira Iguchi <akira2.iguchi@toshiba.co.jp> Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
| * ide: add cable detection for early UDMA66 devices (take 3)Bartlomiej Zolnierkiewicz2007-08-202-22/+36
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * Move ide_in_drive_list() from ide-dma.c to ide-iops.c. * Add ivb_list[] table for listening early UDMA66 devices which don't conform to ATA4 standard wrt cable detection (bit14 is zero, only bit13 is valid) and use only device side cable detection for them since host side cable detection may be unreliable. * Add model "QUANTUM FIREBALLlct10 05" with firwmare "A03.0900" to the list (from Craig's bugreport). v2: * Improve kernel message basing on suggestion from Sergei. v3: * Don't print kernel message when no device side cable detection is done, plus some minor fixes. (Noticed by Sergei) Thanks to Craig for testing this patch. Cc: Craig Block <chblock3@yahoo.com> Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
| * ide-pmac: fix drive->init_speed reportingBartlomiej Zolnierkiewicz2007-08-201-11/+3
| | | | | | | | | | | | | | | | | | | | pmac_ide_tune_chipset() don't set drive->init_speed. Fix it by setting drive->{current,init}_speed in pmac_ide_do_setfeature() and clean up pmac_ide_{tune_chipset,mdma_enable,udma_enable}(). Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
| * ide: config_drive_for_dma() fixesBartlomiej Zolnierkiewicz2007-08-202-25/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | * Add DMA blacklist checking (->ide_dma_on check probably can go now). * Add ->atapi_dma flag checking and remove no longer needed ns87415_ide_dma_check() from ns87415 host driver. * Remove now needless __ide_dma_check() wrapper and symbol export. * Check drive->autodma instead of hwif->autodma (there should be no changes in behavior as all users of config_drive_for_dma() set both ->autodma flags). Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
| * ide-cris: fix ->set_pio_mode method to set transfer mode on the deviceBartlomiej Zolnierkiewicz2007-08-201-0/+2
| | | | | | | | | | Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
| * ide: fix hidden dependencies on CONFIG_IDE_GENERICBartlomiej Zolnierkiewicz2007-08-201-0/+9
| | | | | | | | | | | | | | | | | | Some host drivers depend on CONFIG_IDE_GENERIC to do the probing but their config options lack explicit dependencies on IDE_GENERIC. In the long-term these host drivers should be fixed to do the probing themselves but for now fix them by making their config options select CONFIG_IDE_GENERIC. Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
| * ide: make CONFIG_IDE_GENERIC default to NTejun Heo2007-08-201-2/+1
| | | | | | | | | | | | | | | | | | | | | | These days, CONFIG_IDE_GENERIC causes more confusion and misconfiguration than it helps. Especially so because libata is linked after the generic driver. Default to N. Signed-off-by: Tejun Heo <htejun@gmail.com> Acked-by: Jeff Garzik <jeff@garzik.org> Cc: "P.C.Chan" <pc.chan@alcatel-lucent.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* | Merge branch 'master' of ↵Linus Torvalds2007-08-204-6/+39
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/v4l-dvb * 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/v4l-dvb: V4L/DVB (6028): Turn an unnecessary mdelay() into msleep(). V4L/DVB (6027): Get rid of an ill-behaved msleep in i2c write V4L/DVB (6026): Avoid powering up the camera on resume V4L/DVB (6016): get_dvb_firmware: update script for new location of tda10046 firmware V4L/DVB (5991): dvb-pll: Set minimum and maximum frequency properly V4L/DVB (5969): ivtv: report ivtv version in status log V4L/DVB (5967): ivtv: fix VIDIOC_S_FBUF:new OSD values where never set V4L/DVB (5968): videodev2.h: remove superfluous FBUF GLOBAL_INV_ALPHA support
| * | V4L/DVB (6028): Turn an unnecessary mdelay() into msleep().Marcelo Tosatti2007-08-201-1/+1
| | | | | | | | | | | | | | | Signed-off-by: Jonathan Corbet <corbet@lwn.net> Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
| * | V4L/DVB (6027): Get rid of an ill-behaved msleep in i2c writeJonathan Corbet2007-08-202-2/+25
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Configuring the OLPC camera requires something over 150 register writes. Unfortunately, querying the CAFE i2c controller too soon after a write causes the hardware to flake. The problem had been "solved" with an msleep() call, but, between the number of registers and how msleep() behaves, that resulted in a 3-second delay on camera initialization. Instead, we hand-code a wait for the completion interrupt which avoids reading the status registers. Signed-off-by: Jonathan Corbet <corbet@lwn.net> Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
| * | V4L/DVB (6026): Avoid powering up the camera on resumeChris Ball2007-08-201-1/+10
| | | | | | | | | | | | | | | | | | Signed-off-by: Chris Ball <cjb@laptop.org> Signed-off-by: Jonathan Corbet <corbet@lwn.net> Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
| * | V4L/DVB (5991): dvb-pll: Set minimum and maximum frequency properlyTrent Piepho2007-08-201-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The tuner maximum frequency wasn't being set, while the minimum frequency was set to what the maximum should have been. If a future patch were to enforce these limits, dvb-pll would be effectively broken. Signed-off-by: Trent Piepho <xyzzy@speakeasy.org> Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
| * | V4L/DVB (5969): ivtv: report ivtv version in status logHans Verkuil2007-08-201-1/+1
| | | | | | | | | | | | | | | Signed-off-by: Hans Verkuil <hverkuil@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
| * | V4L/DVB (5967): ivtv: fix VIDIOC_S_FBUF:new OSD values where never setHans Verkuil2007-08-201-0/+1
| |/ | | | | | | | | | | | | | | | | | | ivtv: fix VIDIOC_S_FBUF support: new OSD values where never actually set. The values set with VIDIOC_S_FBUF were not actually used until the next VIDIOC_S_FMT. Fixed. Signed-off-by: Hans Verkuil <hverkuil@xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab@infradead.org>
* | KVM: Avoid calling smp_call_function_single() with interrupts disabledAvi Kivity2007-08-191-0/+4
|/ | | | | | | | | | | | | | When taking a cpu down, we need to hardware_disable() it. Unfortunately, the CPU_DYING notifier is called with interrupts disabled, which means we can't use smp_call_function_single(). Fortunately, the CPU_DYING notifier is always called on the dying cpu, so we don't need to use the function at all and can simply call hardware_disable() directly. Tested-by: Paolo Ornati <ornati@fastwebnet.it> Signed-off-by: Avi Kivity <avi@qumranet.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* Merge master.kernel.org:/home/rmk/linux-2.6-armLinus Torvalds2007-08-181-1/+1
|\ | | | | | | | | | | | | * master.kernel.org:/home/rmk/linux-2.6-arm: [ARM] 4549/1: KS8695: Fix build errors [ARM] 4546/1: s3c2410: fix architecture typo for s3c2442 [ARM] 4544/1: arm: fix section mismatch in pxa fb
| * [ARM] 4544/1: arm: fix section mismatch in pxa fbSam Ravnborg2007-08-111-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | Fix following section mismatch warning: WARNING: drivers/built-in.o(.text+0x73d0): Section mismatch: reference to .init.data: (between 'pxafb_setup' and 'pxafb_init') The warning are caused by __devinit pxafb_setup() that refers to a variable marked __initdata. In a hotplug scenario we would have a reference to the freed .init.data section. Fix this by declaring g_options __devinitdata. Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* | fix random hang in forcedeth driver when using netconsoleTimo Jantunen2007-08-181-5/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If the forcedeth driver receives too much work in an interrupt, it assumes it has a broken hardware with stuck IRQ. It works around the problem by disabling interrupts on the nic but makes a printk while holding device spinlog - which isn't smart thing to do if you have netconsole on the same nic. This patch moves the printk's out of the spinlock protected area. Without this patch the machine hangs hard. With this patch everything still works even when there is significant increase on CPU usage while using the nic. Signed-off-by: Timo Jantunen <jeti@iki.fi> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* | Add some help texts to recently-introduced kconfig itemsJan Engelhardt2007-08-1810-0/+59
| | | | | | | | | | | | Signed-off-by: Jan Engelhardt <jengelh@gmx.de> Signed-off-by: Stefan Richter <stefanr@s5r6.in-berlin.de> (edited MACINTOSH_DRIVERS per Geert Uytterhoeven's remark) Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* | Enable partitions for lguest block deviceRusty Russell2007-08-181-3/+6
| | | | | | | | | | | | | | | | | | | | The lguest block device only requests one minor, which means partitions don't work (eg "root=/dev/lgba1"). Let's follow the crowd and ask for 16. Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* | Merge branch 'release' of git://lm-sensors.org/kernel/mhoffman/hwmon-2.6Linus Torvalds2007-08-183-26/+36
|\ \ | | | | | | | | | | | | | | | | | | | | | * 'release' of git://lm-sensors.org/kernel/mhoffman/hwmon-2.6: hwmon: (smsc47m1) restore missing name attribute hwmon: (w83627ehf) don't assume bank 0 hwmon: (w83627ehf) read fan_div values during probe hwmon: fix w83781d temp sensor type setting
| * | hwmon: (smsc47m1) restore missing name attributeJean Delvare2007-08-121-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The smsc47m1 driver no longer creates the name attribute used by libsensors to identify chip types. It was lost during the conversion to a platform driver. I was fooled by the fact that we do have a group with all attributes, but only to delete them all at once. The group is not used to create the attributes, so we have to explicitly create the name attribute. This fixes lm-sensors ticket #2236: http://lm-sensors.org/ticket/2236 Signed-off-by: Jean Delvare <khali@linux-fr.org> Signed-off-by: Mark M. Hoffman <mhoffman@lightlink.com>
| * | hwmon: (w83627ehf) don't assume bank 0Jean Delvare2007-08-121-5/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Don't assume that the default bank is 0. For one thing, we don't even set it to 0 when the driver is loaded, so the initial state might be different. For another, something (say, the BIOS) might access the chip and leave with the bank set to something different, so assuming that the bank value is 0 is not safe. Signed-off-by: Jean Delvare <khali@linux-fr.org> Signed-off-by: Mark M. Hoffman <mhoffman@lightlink.com>
| * | hwmon: (w83627ehf) read fan_div values during probeMark M. Hoffman2007-08-121-19/+29
| | | | | | | | | | | | | | | | | | | | | | | | This patch forces the driver to read the fan divider values during early init. Otherwise, a call to store_fan_min() could access uninitialized variables. Signed-off-by: Mark M. Hoffman <mhoffman@lightlink.com> Signed-off-by: Jean Delvare <khali@linux-fr.org>
| * | hwmon: fix w83781d temp sensor type settingMark M. Hoffman2007-08-111-2/+2
| |/ | | | | | | | | | | | | | | Commit 348753379a7704087603dad403603e825422fd9a introduced a regression that caused temp2 and temp3 sensor type settings to be written to temp1 instead. The result is that temp sensor readings could be way off. Signed-off-by: Mark M. Hoffman <mhoffman@lightlink.com>
* | Merge branch 'for-linus' of ↵Linus Torvalds2007-08-1813-56/+73
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: IB/mlx4: Incorrect semicolon after if statement mlx4_core: Wait 1 second after reset before accessing device IPoIB: Fix leak in ipoib_transport_dev_init() error path IB/mlx4: Fix opcode returned in RDMA read completion IB/srp: Add OUI for new Cisco targets IB/srp: Wrap OUI checking for workarounds in helper functions RDMA/cxgb3: Always call low level send function via cxgb3_ofld_send() IB: Move the macro IB_UMEM_MAX_PAGE_CHUNK() to umem.c IB: Include <linux/list.h> and <linux/rwsem.h> from <rdma/ib_verbs.h> IB: Include <linux/list.h> from <rdma/ib_mad.h> IB/mad: Fix address handle leak in mad_rmpp IB/mad: agent_send_response() should be void IB/mad: Fix memory leak in switch handling in ib_mad_recv_done_handler() IB/mad: Fix error path if response alloc fails in ib_mad_recv_done_handler() IB/sa: Don't need to check for default P_Key twice IB/core: Ignore membership bit in ib_find_pkey()
| * | IB/mlx4: Incorrect semicolon after if statementIlpo Järvinen2007-08-151-1/+1
| | | | | | | | | | | | | | | | | | | | | A stray semicolon makes us inadvertently ignore the value of err. Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: Roland Dreier <rolandd@cisco.com>
| * | mlx4_core: Wait 1 second after reset before accessing deviceEli Cohen2007-08-131-0/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | Put a 1000 msec delay after resetting the device before attempting to do config cycles on it. Not waiting causes system hangs on some chipsets, e.g. Intel E7520, when the driver is loaded. Signed-off-by: Eli Cohen <eli@mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com>
| * | IPoIB: Fix leak in ipoib_transport_dev_init() error pathJack Morgenstein2007-08-071-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ipoib_transport_dev_init() calls ipoib_cm_dev_init(), so it needs to call ipoib_cm_dev_cleanup() to unwind that on the error path. Found by Dotan Barak of Mellanox. Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com>
| * | IB/mlx4: Fix opcode returned in RDMA read completionVu Pham2007-08-031-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | Current code has a cut-and-paste error and returns IB_WC_SEND when it should return IB_WC_RDMA_READ. Signed-off-by: Vu Pham <vu@mellanox.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
| * | IB/srp: Add OUI for new Cisco targetsRaghava Kondapalli2007-08-031-1/+3
| | | | | | | | | | | | | | | | | | | | | New Cisco IB SRP targets use the Cisco OUI 00-1b-0d but still need the Topspin workarounds. Add this OUI to srp_target_is_topspin(). Signed-off-by: Roland Dreier <rolandd@cisco.com>
| * | IB/srp: Wrap OUI checking for workarounds in helper functionsRoland Dreier2007-08-031-9/+20
| | | | | | | | | | | | | | | | | | | | | | | | | | | Wrap the checking for Mellanox and Topspin OUIs to decide whether to use a workaround into helper functions. This will make it cleaner to add a new OUI to check (as we need to do now that some targets with a Cisco OUI still need the Topspin workarounds). Signed-off-by: Roland Dreier <rolandd@cisco.com>
| * | RDMA/cxgb3: Always call low level send function via cxgb3_ofld_send()Steve Wise2007-08-031-8/+8
| | | | | | | | | | | | | | | | | | | | | This avoids deadlocks. Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
| * | IB: Move the macro IB_UMEM_MAX_PAGE_CHUNK() to umem.cDotan Barak2007-08-031-0/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | After moving the definition of struct ib_umem_chunk from ib_verbs.h to ib_umem.h there isn't any reason for the macro IB_UMEM_MAX_PAGE_CHUNK to stay in ib_verbs.h. Move the macro to umem.c, the only place where it is used. Signed-off-by: Dotan Barak <dotanb@dev.mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com>
| * | IB/mad: Fix address handle leak in mad_rmppSean Hefty2007-08-031-4/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The address handle associated with dual-sided RMPP direction switch ACKs is never destroyed. Free the AH for ACKs which fall into this category. Problem was reported by Dotan Barak <dotanb@dev.mellanox.co.il>. Signed-off-by: Sean Hefty <sean.hefty@intel.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
| * | IB/mad: agent_send_response() should be voidHal Rosenstock2007-08-032-17/+13
| | | | | | | | | | | | | | | | | | | | | | | | Nothing looks at the return value of agent_send_response(), so there's no point in returning anything. Signed-off-by: Hal Rosenstock <hal.rosenstock@gmail.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
| * | IB/mad: Fix memory leak in switch handling in ib_mad_recv_done_handler()Hal Rosenstock2007-08-031-6/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If agent_send_response() returns an error, we shouldn't do anything differently than if it succeeds; setting response to NULL just means that the response buffer gets leaked. Signed-off-by: Suresh Shelvapille <suri@baymicrosystems.com> Signed-off-by: Hal Rosenstock <hal.rosenstock@gmail.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
| * | IB/mad: Fix error path if response alloc fails in ib_mad_recv_done_handler()Hal Rosenstock2007-08-031-6/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If ib_mad_recv_done_handler() fails to allocate response, then it just printed a warning and continued, which leads to an oops if the MAD is being handled for a switch device, because the switch code uses response without checking for NULL. Fix this by bailing out of the function if the allocation fails. Signed-off-by: Suresh Shelvapille <suri@baymicrosystems.com> Signed-off-by: Hal Rosenstock <hal.rosenstock@gmail.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
| * | IB/sa: Don't need to check for default P_Key twiceRoland Dreier2007-08-031-3/+1
| | | | | | | | | | | | | | | | | | | | | Now that ib_find_pkey() ignores the membership bit of P_Keys, there's no need for ib_sa to look for both 0x7fff and 0xffff in a port's P_Key table. Signed-off-by: Roland Dreier <rolandd@cisco.com>
| * | IB/core: Ignore membership bit in ib_find_pkey()Moni Shoua2007-08-031-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ib_find_pkey() is used as a replacement for ib_find_cached_pkey(), and the original function ignored the membership bit when searching for a P_Key, so ib_find_pkey() should ignore the bit too. In particular, IPoIB turns on the P_Key membership bit of limited membership P_Keys when creating a child interface and looks for the full membership P_key. This broke if a port was a partial member of a partition when IPoIB switched from ib_find_cached_pkey() to ib_find_pkey(), and this change fixes things again. Signed-off-by: Moni Shoua <monis@voltaire.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
OpenPOWER on IntegriCloud