aboutsummaryrefslogtreecommitdiff
path: root/drivers
AgeCommit message (Collapse)Author
2008-01-26swarm: set hwif->chipsetBartlomiej Zolnierkiewicz
hwif->chipset should be set if the hwif is claimed by host driver. Cc: Maciej W. Rozycki <macro@linux-mips.org> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-01-26rapide: set hwif->chipsetBartlomiej Zolnierkiewicz
hwif->chipset should be set if the hwif is claimed by host driver. Cc: Russell King <rmk@arm.linux.org.uk> Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-01-26ide: fix probing for hosts with serialized or IRQ sharing interfacesBartlomiej Zolnierkiewicz
After hwif_register_devices() IDE devices are ready to be used so the way in which ide_device_add() works currently is racy for hosts with serialized / IRQ sharing interfaces. Fix ide_device_add() by looping over interfaces for probe_hwif(), hwif_init() and hwif_register_devices() operations. Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-01-26ide: kill probe_hwif_init()Bartlomiej Zolnierkiewicz
There should be no functionality changes caused by this patch. Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-01-26ide: don't try to unregister interfaces if 'initializing' in ide_register_hw()Bartlomiej Zolnierkiewicz
Host drivers using ide_register_hw() and 'initializing == 1': * ide-pnp - depends on ISA * ide_arm - ARM arch specific - initialized before all other host drivers * ide-cris - CRIS arch specific => IDE_ARCH_OBSOLETE_INIT is not defined - broken * ide-h8300 - H8300 arch specific => IDE_ARCH_OBSOLETE_INIT is not defined, no PCI * buddha/q40/gayle/macide/falconide - M68K arch specific => IDE_ARCH_OBSOLETE_INIT is not defined, no PCI Since the only host drivers which probe interfaces before the above ones are: * ali14xx/dtc2278/ht6560b/qd65xx/umc8672 - depend on ISA - require IDE_ARCH_OBSOLETE_INIT=y to work * PCI ones - depend on PCI don't try to unregister interfaces if 'initializing == 1' in ide_register_hw() (it is possible that built-in host drivers will claim all IDE interfaces but later ide-pnp host driver will try to unregister them - this change fixes it). Also skip hwif->hold check if 'initializing == 1' since it is set only by: * pmac - PPC && PMAC specific => no ISA * au1xxx-ide - MIPS && SOC_AU1200 specific => no ISA and use ide_find_port() helper to find free ide_hwifs[] slot. Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-01-26ide: merge ->fixup and ->quirkproc methodsBartlomiej Zolnierkiewicz
* Assign drive->quirk_list in ->quirkproc implementations: - hpt366.c::hpt3xx_quirkproc() - pdc202xx_new.c::pdcnew_quirkproc() - pdc202xx_old.c::pdc202xx_quirkproc() * Make ->quirkproc void. * Move calling ->quirkproc from do_identify() to probe_hwif(). * Convert it821x_fixups() to it821x_quirkproc() in it821x.c. * Convert siimage_fixup() to sil_quirkproc() in siimage.c, also remove no longer needed drive->present check from is_dev_seagate_sata(). * Convert ide_undecoded_slave() to accept 'drive' instead of 'hwif' as an argument. Then convert ide_register_hw() to accept 'quirkproc' argument instead of 'fixup' one. * Remove no longer needed ->fixup method. Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-01-26ide: dump taskfile HOB registers in ide_tf_load() (if DEBUG is defined)Bartlomiej Zolnierkiewicz
* Dump taskfile HOB registers in ide_tf_load() (if DEBUG is defined). * Remove no longer needed DEBUG code from __ide_do_rw_disk(). Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-01-26ide: merge ->dma_host_{on,off} methods into ->dma_host_set methodBartlomiej Zolnierkiewicz
Merge ->dma_host_{on,off} methods into ->dma_host_set method which takes 'int on' argument. There should be no functionality changes caused by this patch. Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-01-26ide: move drive->using_dma check to callers of ->dma_host_on methodBartlomiej Zolnierkiewicz
Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-01-26atiixp: remove ->dma_host_on and ->dma_host_off methodsBartlomiej Zolnierkiewicz
* Enable/disable UDMA in atiixp_set_dma_mode(). * Remove no longer needed atiixp_dma_host_{on,off}() and save_mdma_mode[]. * Bump driver version. Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-01-26ide-cris: fix DMA methodsBartlomiej Zolnierkiewicz
* Rename cris_dma_{on,off}() to cris_dma_host_{on,off}(). * Remove no longer needed ->dma_off_quietly (IDE core has the needed code now). * Make cris_dma_host_on() void. I left fixing ide-cris after "kill dma_on/dma_off_quietly() methods" patch because: * Currently this driver is broken: cris_dma_on() (returns 'int') is assigned to hwif->dma_host_on (returns 'void') so the driver won't build. * ->ide_dma_on method was missing so the driver OOPS-es on attempt to enable DMA. * drive->using_dma was never set/cleared so DMA wouldn't be used anyway. Unfortunately it seems that ide-cris stays broken even after this patch: * V10: <asm/arch-v10/ide.h> needs fixing - ide_init_default_hwifs() should be removed (IDE core no longer uses it) - same for ide_init_hwif_ports() and ide_default_{irq,io_base}() (they shouldn't be needed for ide-cris host driver) * V32: I'm unable to find a place which defines ETRAX_ARCH_V32 but I'm leaving fixing this to CRIS gurus. :) Cc: Mikael Starvik <starvik@axis.com> Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-01-26ide: remove ->ide_dma_on and ->dma_off_quietly methods from ide_hwif_tBartlomiej Zolnierkiewicz
* Make ide_dma_off_quietly() and __ide_dma_on() always available. * Drop "__" prefix from __ide_dma_on(). * Check for presence of ->dma_host_on instead of ->ide_dma_on. * Convert all users of ->ide_dma_on and ->dma_off_quietly methods to use ide_dma_on() and ide_dma_off_quietly() instead. * Remove no longer needed ->ide_dma_on and ->dma_off_quietly methods from ide_hwif_t. * Make ide_dma_on() void. There should be no functionality changes caused by this patch. Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-01-26au1xxx-ide: add ide_toggle_bounce() callsBartlomiej Zolnierkiewicz
Add ide_toggle_bounce() call to ->ide_dma_on/->dma_off_quietly methods so they match generic __ide_dma_on()/ide_dma_off_quietly(). Since there is no PCI device there should be no functionality changes caused by this patch. Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-01-26icside: add ide_toggle_bounce() callsBartlomiej Zolnierkiewicz
Add ide_toggle_bounce() call to ->ide_dma_on/->dma_off_quietly methods so they match generic __ide_dma_on()/ide_dma_off_quietly(). Since there is no PCI device there should be no functionality changes caused by this patch. Cc: Russell King <rmk@arm.linux.org.uk> Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-01-26sgiioc4: add ide_toggle_bounce() callsBartlomiej Zolnierkiewicz
Add ide_toggle_bounce() call to ->ide_dma_on/->dma_off_quietly methods so they match generic __ide_dma_on()/ide_dma_off_quietly(). Tested on Altix by Jeremy. Acked-by: Jeremy Higdon <jeremy@sgi.com> Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-01-26cy82c693: add ->set_dma_mode methodBartlomiej Zolnierkiewicz
* Fix SWDMA/MWDMA masks in cy82c693_chipset. * Add IDE_HFLAG_CY82C693 host flag and use it in ide_tune_dma() to check whether the DMA should be enabled even if ide_max_dma_mode() fails. * Convert cy82c693_dma_enable() to become cy82c693_set_dma_mode() and remove no longer needed cy82c693_ide_dma_on(). Then set IDE_HFLAG_CY82C693 instead of IDE_HFLAG_TRUST_BIOS_FOR_DMA in cy82c693_chipset. * Bump driver version. As a result of this patch cy82c693 driver will configure and use DMA on all SWDMA0-2 and MWDMA0-2 capable ATA devices instead of relying on BIOS. Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-01-26cy82c693: correct DMA modes clippingBartlomiej Zolnierkiewicz
* Mask device DMA masks by ATA_{S,M}WDMA2 in cy82c693_ide_dma_on(). * Remove clipping of DMA modes by id->tDMA in cy82c693_dma_enable(): - id->tDMA may not be defined on newer devices - id->vendor6/id->tDMA word is in LE endianness (cy82c693 seems to be Alpha specific though) * Bump driver version. Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-01-26ide: (hopefully) fix VDMA for CS5520Bartlomiej Zolnierkiewicz
* Set the correct hwif->dma_base for the second channel in ide_get_or_set_dma_base(). * Remove DMA enable code from cs5520_set_pio_mode(), this can be handled by the generic ->dma_host_on method now. * Add VDMA check to ide_config_drive_speed(). * drive->using_dma was never enabled since cs5520 host driver's ->ide_dma_on method overrided the generic ->ide_dma_on (so __ide_dma_on() was never called, drive->using_dma was never set and VDMA was never used since it depends on drive->using_dma). Fix it by using ->dma_host_on method instead of ->ide_dma_on (also add matching ->dma_host_off method). Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-01-26ide-disk: add idedisk_set_doorlock() helperBartlomiej Zolnierkiewicz
There should be no functionality changes caused by this patch. Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-01-26serverworks: cleanup ->set_dma_mode methodBartlomiej Zolnierkiewicz
IDE core guarantees that ->set_dma_mode will be called only for DMA modes set in SWDMA/MWDMA/UDMA masks. There should be no functionality changes caused by this patch. Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-01-26sl82c105: remove no longer needed ->selectproc methodBartlomiej Zolnierkiewicz
* Program register 0x40 in sl82c105_resetproc(). * Remove no longer needed sl82c105_selectproc() and pci_set_drvdata() calls. Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-01-26sl82c105: program DMA/PIO timings in ->dma_start/->ide_dma_endBartlomiej Zolnierkiewicz
* Program DMA timings in sl82c105_dma_start() (->dma_start method) before starting DMA transfer. * Add sl82c105_dma_end() (->ide_dma_end method) to switch back to PIO timings when DMA transfer is complete. * In sl82c105_set_pio_mode() program timings regardless of ->using_dma setting and in sl82c105_set_dma_mode() only cache the new timings. * Remove no longer needed sl82c105_{ide_dma_on,off_quietly}(). Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
2008-01-25Merge git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6Linus Torvalds
* git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6: (200 commits) [SCSI] usbstorage: use last_sector_bug flag universally [SCSI] libsas: abstract STP task status into a function [SCSI] ultrastor: clean up inline asm warnings [SCSI] aic7xxx: fix firmware build [SCSI] aacraid: fib context lock for management ioctls [SCSI] ch: remove forward declarations [SCSI] ch: fix device minor number management bug [SCSI] ch: handle class_device_create failure properly [SCSI] NCR5380: fix section mismatch [SCSI] sg: fix /proc/scsi/sg/devices when no SCSI devices [SCSI] IB/iSER: add logical unit reset support [SCSI] don't use __GFP_DMA for sense buffers if not required [SCSI] use dynamically allocated sense buffer [SCSI] scsi.h: add macro for enclosure bit of inquiry data [SCSI] sd: add fix for devices with last sector access problems [SCSI] fix pcmcia compile problem [SCSI] aacraid: add Voodoo Lite class of cards. [SCSI] aacraid: add new driver features flags [SCSI] qla2xxx: Update version number to 8.02.00-k7. [SCSI] qla2xxx: Issue correct MBC_INITIALIZE_FIRMWARE command. ...
2008-01-25Merge git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6Linus Torvalds
* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: [CRYPTO] hifn795x: Disallow built-in hifn795x when HW_RANDOM is m
2008-01-25Merge branch 'upstream-linus' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/jgarzik/libata-dev * 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jgarzik/libata-dev: (67 commits) fix drivers/ata/sata_fsl.c double-decl [libata] Prefer SCSI_SENSE_BUFFERSIZE to sizeof() pata_legacy: Merge winbond support ata_generic: Cenatek support pata_winbond: error return pata_serverworks: Fix cable types and cosmetics pata_mpc52xx: remove un-needed assignment libata: fix off-by-one in error categorization ahci: factor out AHCI enabling and enable AHCI before reading CAP ata_piix: implement SIDPR SCR access ata_piix: convert to prepare - activate initialization libata: factor out ata_pci_activate_sff_host() from ata_pci_one() [libata] Prefer SCSI_SENSE_BUFFERSIZE to sizeof() pata_legacy: resychronize with upstream changes and resubmit [libata] pata_legacy: typo fix [libata] pata_winbond: update for new ->data_xfer hook pata_pcmcia: convert to new data_xfer prototype libata annotations and fixes libata: use dev_driver_string() instead of "libata" in libata-sff.c ata_piix: kill unused constants and flags ...
2008-01-25[SCSI] usbstorage: use last_sector_bug flag universallyHans de Goede
This patch sets the last_sector_bug flag to 1 for all USB disks. This is needed to makes the cardreader on various HP multifunction printers work. Since the performance impact is negible we set this flag for all USB disks to avoid an unusual_devs.h nightmare. Signed-off-by: Hans de Goede <j.w.r.degoede@hhs.nl> Acked-by: Matthew Dharm <mdharm-usb@one-eyed-alien.net> Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
2008-01-26[CRYPTO] hifn795x: Disallow built-in hifn795x when HW_RANDOM is mHerbert Xu
Currently it is possible to select HW_RANDOM as a module and have hifn795x built-in. This causes a build problem because hifn795x will then call hwrng_register which isn't built-in. This patch introduces a new config option to control the hifn795x RNG which lets us avoid this problem. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2008-01-25Merge branch 'for-linus' of ↵Linus Torvalds
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: (81 commits) RDMA/cxgb3: Fix the T3A workaround checks IB/ipath: Remove unnecessary cast IPoIB: Constify seq_operations function pointer tables RDMA/cxgb3: Mark QP as privileged based on user capabilities RDMA/cxgb3: Fix page shift calculation in build_phys_page_list() RDMA/cxgb3: Flush the receive queue when closing IB/ipath: Trivial simplification of ipath_make_ud_req() IB/mthca: Update latest "native Arbel" firmware revision IPoIB: Remove redundant check of netif_queue_stopped() in xmit handler IB/ipath: Add mappings from HW register to PortInfo port physical state IB/ipath: Changes to support PIO bandwidth check on IBA7220 IB/ipath: Minor cleanup of unused fields and chip-specific errors IB/ipath: New sysfs entries to control 7220 features IB/ipath: Add new chip-specific functions to older chips, consistent init IB/ipath: Remove unused MDIO interface code IB/ehca: Prevent RDMA-related connection failures on some eHCA2 hardware IB/ehca: Add "port connection autodetect mode" IB/ehca: Define array to store SMI/GSI QPs IB/ehca: Remove CQ-QP-link before destroying QP in error path of create_qp() IB/iser: Add change_queue_depth method ...
2008-01-25RDMA/cxgb3: Fix the T3A workaround checksSteve Wise
Correctly work around T3A issues by checking "hwtype != T3A" instead of "hwtype == T3B". This will be needed for new hardware types. Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-01-25IB/ipath: Remove unnecessary castJan Engelhardt
Signed-off-by: Jan Engelhardt <jengelh@computergmbh.de> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-01-25IPoIB: Constify seq_operations function pointer tablesJan Engelhardt
Signed-off-by: Jan Engelhardt <jengelh@computergmbh.de> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-01-25RDMA/cxgb3: Mark QP as privileged based on user capabilitiesSteve Wise
This is needed to support zero-stag properly. Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-01-25RDMA/cxgb3: Fix page shift calculation in build_phys_page_list()Steve Wise
The existing logic incorrectly maps this buffer list: 0: addr 0x10001000, size 0x1000 1: addr 0x10002000, size 0x1000 To this bogus page list: 0: 0x10000000 1: 0x10002000 The shift calculation must also take into account the address of the first entry masked by the page_mask as well as the last address+size rounded up to the next page size. Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-01-25RDMA/cxgb3: Flush the receive queue when closingSteve Wise
- for kernel mode cqs, call event notification handler when flushing. - flush QP when moving from RTS -> CLOSING. - fix logic to identify a kernel mode qp. Signed-off-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-01-25IB/ipath: Trivial simplification of ipath_make_ud_req()Ralph Campbell
Move the increment of s_hdrwords into the existing if block that tests if we're doing a send with immediate, to save one test of the opcode. Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-01-25IB/mthca: Update latest "native Arbel" firmware revisionRoland Dreier
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-01-25IPoIB: Remove redundant check of netif_queue_stopped() in xmit handlerKrishna Kumar
qdisc_run() now tests for queue_stopped() before calling __qdisc_run(), and the same check is done in every iteration of __qdisc_run(), so another check is not required in the driver xmit. This means that ipoib_start_xmit() no longer needs to test netif_queue_stopped(); the test was added to fix earlier kernels, where the networking stack did not guarantee that the xmit method of an LLTX driver would not be called after the queue was stopped, but current kernels do provide this guarantee. To validate, I put a debug in the TX_BUSY path which never hit with 64 threads running overnight exercising this code a few 100 million times. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-01-25IB/ipath: Add mappings from HW register to PortInfo port physical stateRalph Campbell
Add new mappings from port physical state (a HW register value) to the IB SubnGet(PortInfo) port physical state. Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-01-25IB/ipath: Changes to support PIO bandwidth check on IBA7220Dave Olson
The IBA7220 uses a count-based triggering mechanism, and therefore can't use the same bandwidth verification mechanism as older chips. To support the 7220, allow enabling and disabling armlaunch errors on application request. Minor robustness improvements as well. Signed-off-by: Dave Olson <dave.olson@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-01-25IB/ipath: Minor cleanup of unused fields and chip-specific errorsDave Olson
Clean up some unused header fields, minor related cleanup. Signed-off-by: Dave Olson <dave.olson@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-01-25IB/ipath: New sysfs entries to control 7220 featuresMichael Albaugh
IBA7220 includes many more configurable IB settings. Getting/setting these is now grouped into a pair of chip specific functions accessed via function pointers. Provide sysfs access to these settings. Signed-off-by: Michael Albaugh <michael.albaugh@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-01-25IB/ipath: Add new chip-specific functions to older chips, consistent initDave Olson
This adds the new (sometimes empty) chip-specific functions to the older chips, and makes the initialization and related functions consistent across all 3 chips. Signed-off-by: Dave Olson <dave.olson@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-01-25IB/ipath: Remove unused MDIO interface codeDave Olson
This code has been unused for some time, but still had leftovers from when it was used. Signed-off-by: Dave Olson <dave.olson@qlogic.com Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-01-25IB/ehca: Prevent RDMA-related connection failures on some eHCA2 hardwareJoachim Fenkes
Some HW revisions of eHCA2 may cause an RC connection to break if they received RDMA Reads over that connection before. This can be prevented by assuring that, after the first RDMA Read, the QP receives a new RDMA Read every few million link packets. Include code into the driver that inserts an empty (size 0) RDMA Read into the message stream every now and then if the consumer doesn't post them frequently enough. Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-01-25IB/ehca: Add "port connection autodetect mode"Hoang-Nam Nguyen
This patch enhances ehca with a capability to "autodetect" the ports being connected physically. In order to utilize that function the module option nr_ports must be set to -1 (default is 2 - two ports). This feature is experimental and will made the default later. More detail: If the user connects only one port to the switch, current code requires 1) port one to be connected and 2) module option nr_ports=1 to be given. If autodetect is enabled, ehca will not wait at creation of the GSI QP for the respective port to become active. Since firmware does not accept modify_qp() while the port is down at initialization, we need to cache all calls to modify_qp() for the SMI/GSI QP and just return a good return code. When a port is activated and we get a PORT_ACTIVE event, we replay the cached modify-qp() parms and re-trigger any posted recv WRs. Only then do we forward the PORT_ACTIVE event to registered clients. The result of this autodetect patch is that all ports will be accessible by the users. Depending on their respective cabling only those ports that are connected properly will become operable. If a user tries to modify a regular QP of a non-connected port, modify_qp() will fail. Furthermore, ibv_devinfo should show the port state accordingly. Note that this patch primarily improves the loading behaviour of ehca. If the cable is removed while the driver is operating and plugged in again, firmware will handle that properly by sending an appropriate async event. Signed-off-by: Hoang-Nam Nguyen <hnguyen@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-01-25IB/ehca: Define array to store SMI/GSI QPsHoang-Nam Nguyen
Signed-off-by: Hoang-Nam Nguyen <hnguyen@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-01-25IB/ehca: Remove CQ-QP-link before destroying QP in error path of create_qp()Hoang-Nam Nguyen
Signed-off-by: Hoang-Nam Nguyen <hnguyen@de.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-01-25IB/iser: Add change_queue_depth methodErez Zilber
Add a .change_queue_depth handler to the scsi_host_template in the iSER driver. iscsi_change_queue_depth was added to iscsi_tcp in order to solve the problem of queue depth which was too high for some targets. It is also applicable for iSER. Signed-off-by: Erez Zilber <erezz@voltaire.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-01-25IB/iser: Print information about unhandled RDMA CM eventsErez Zilber
Some RDMA CM events are not supported or not handled in iSER. This patch adds some info (printk) for the user about them. Signed-off-by: Erez Zilber <erezz@voltaire.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
2008-01-25IB/fmr_pool: ib_fmr_pool_flush() should flush all dirty FMRsOlaf Kirch
When a FMR is released via ib_fmr_pool_unmap(), the FMR usually ends up on the free_list rather than the dirty_list (because we allow a certain number of remappings before actually requiring a flush). However, ib_fmr_batch_release() only looks at dirty_list when flushing out old mappings. This means that when ib_fmr_pool_flush() is used to force a flush of the FMR pool, some dirty FMRs that have not reached their maximum remap count will not actually be flushed. Fix this by flushing all FMRs that have been used at least once in ib_fmr_batch_release(). Signed-off-by: Olaf Kirch <olaf.kirch@oracle.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-05 05:08:28 +0000