1. 28 Oct, 2008 22 commits
    • Linus Torvalds's avatar
      Merge branch 'for-linus' of git://git390.osdl.marist.edu/pub/scm/linux-2.6 · b30fc14c
      Linus Torvalds authored
      * 'for-linus' of git://git390.osdl.marist.edu/pub/scm/linux-2.6:
        [S390] s390: Fix build for !CONFIG_S390_GUEST + CONFIG_VIRTIO_CONSOLE
        [S390] No more 4kb stacks.
        [S390] Change default IPL method to IPL_VM.
        [S390] tape: disable interrupts in tape_open and tape_release
        [S390] appldata: unsigned ops->size cannot be negative
        [S390] tape block: complete request with correct locking
        [S390] Fix sysdev class file creation.
        [S390] pgtables: Fix race in enable_sie vs. page table ops
        [S390] qdio: remove incorrect memset
        [S390] qdio: prevent double qdio shutdown in case of I/O errors
      b30fc14c
    • Linus Torvalds's avatar
      Merge branch 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jgarzik/libata-dev · 3c136f29
      Linus Torvalds authored
      * 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jgarzik/libata-dev:
        libata: ahci enclosure management bit mask
        libata: ahci enclosure management led sync
        pata_ninja32: suspend/resume support
        libata: Fix LBA48 on pata_it821x RAID volumes.
        libata: clear saved xfer_mode and ncq_enabled on device detach
        sata_sil24: configure max read request size to 4k
        libata: add missing kernel-doc
        libata: fix device iteration bugs
        ahci: Add support for Promise PDC42819
        ata: Switch all my stuff to a common address
      3c136f29
    • Christian Borntraeger's avatar
      [S390] s390: Fix build for !CONFIG_S390_GUEST + CONFIG_VIRTIO_CONSOLE · ea4bfdf5
      Christian Borntraeger authored
      The s390 kernel does not compile if virtio console is enabled, but guest
      support is disabled:
      
        LD      .tmp_vmlinux1
      arch/s390/kernel/built-in.o: In function `setup_arch':
      /space/linux-2.5/arch/s390/kernel/setup.c:773: undefined reference to
      `s390_virtio_console_init'
      
      The fix is related to
      commit 99e65c92
      Author: Christian Borntraeger <borntraeger@de.ibm.com>
      Date:   Fri Jul 25 15:50:04 2008 +0200
          KVM: s390: Fix guest kconfig
      
      Which changed the build process to build kvm_virtio.c only if CONFIG_S390_GUEST
      is set. We must ifdef the prototype in the header file accordingly.
      Reported-by: default avatarHeiko Carstens <heiko.carstens@de.ibm.com>
      Signed-off-by: default avatarChristian Borntraeger <borntraeger@de.ibm.com>
      Signed-off-by: default avatarMartin Schwidefsky <schwidefsky@de.ibm.com>
      ea4bfdf5
    • Heiko Carstens's avatar
      [S390] No more 4kb stacks. · 7f5a8ba6
      Heiko Carstens authored
      We got a stack overflow with a small stack configuration on a 32 bit
      system. It just looks like as 4kb isn't enough and too dangerous.
      So lets get rid of 4kb stacks on 32 bit.
      
      But one thing I completely dislike about the call trace below is that
      just for debugging or tracing purposes sprintf gets called (cio_start_key):
      
      	/* process condition code */
      	sprintf(dbf_txt, "ccode:%d", ccode);
      	CIO_TRACE_EVENT(4, dbf_txt);
      
      But maybe its just me who thinks that this could be done better.
      
          <4>Kernel stack overflow.
          <4>Modules linked in: dm_multipath sunrpc bonding qeth_l2 dm_mod qeth ccwgroup vmur
          <4>CPU: 1 Not tainted 2.6.27-30.x.20081015-s390default #1
          <4>Process httpd (pid: 3807, task: 20ae2df8, ksp: 1666fb78)
          <4>Krnl PSW : 040c0000 8027098a (number+0xe/0x348)
          <4>           R:0 T:1 IO:0 EX:0 Key:0 M:1 W:0 P:0 AS:0 CC:0 PM:0
          <4>Krnl GPRS: 00d43318 0027097c 1666f277 9666f270
          <4>           00000000 00000000 0000000a ffffffff
          <4>           9666f270 1666f228 1666f277 1666f098
          <4>           00000002 80270982 80271016 1666f098
          <4>Krnl Code: 8027097e: f0340dd0a7f1	srp	3536(4,%r0),2033(%r10),4
          <4>           80270984: 0f00		clcl	%r0,%r0
          <4>           80270986: a7840001		brc	8,80270988
          <4>          >8027098a: 18ef		lr	%r14,%r15
          <4>           8027098c: a7faff68		ahi	%r15,-152
          <4>           80270990: 18bf		lr	%r11,%r15
          <4>           80270992: 18a2		lr	%r10,%r2
          <4>           80270994: 1893		lr	%r9,%r3
      
      Modified calltrace with annotated stackframe size of each function:
      
      stackframe size
          |
       0 304 vsnprintf+850 [0x271016]
       1  72 sprintf+74 [0x271522]
       2  56 cio_start_key+262 [0x2d4c16]
       3  56 ccw_device_start_key+222 [0x2dfe92]
       4  56 ccw_device_start+40 [0x2dff28]
       5  48 raw3215_start_io+104 [0x30b0f8]
       6  56 raw3215_write+494 [0x30ba0a]
       7  40 con3215_write+68 [0x30bafc]
       8  40 __call_console_drivers+146 [0x12b0fa]
       9  32 _call_console_drivers+102 [0x12b192]
      10  64 release_console_sem+268 [0x12b614]
      11 168 vprintk+462 [0x12bca6]
      12  72 printk+68 [0x12bfd0]
      13 256 __print_symbol+50 [0x15a882]
      14  56 __show_trace+162 [0x103d06]
      15  32 show_trace+224 [0x103e70]
      16  48 show_stack+152 [0x103f20]
      17  56 dump_stack+126 [0x104612]
      18  96 __alloc_pages_internal+592 [0x175004]
      19  80 cache_alloc_refill+776 [0x196f3c]
      20  40 __kmalloc+258 [0x1972ae]
      21  40 __alloc_skb+94 [0x328086]
      22  32 pskb_copy+50 [0x328252]
      23  32 skb_realloc_headroom+110 [0x328a72]
      24 104 qeth_l2_hard_start_xmit+378 [0x7803bfde]
      25  56 dev_hard_start_xmit+450 [0x32ef6e]
      26  56 __qdisc_run+390 [0x3425d6]
      27  48 dev_queue_xmit+410 [0x331e06]
      28  40 ip_finish_output+308 [0x354ac8]
      29  56 ip_output+218 [0x355b6e]
      30  24 ip_local_out+56 [0x354584]
      31 120 ip_queue_xmit+300 [0x355cec]
      32  96 tcp_transmit_skb+812 [0x367da8]
      33  40 tcp_push_one+158 [0x369fda]
      34 112 tcp_sendmsg+852 [0x35d5a0]
      35 240 sock_sendmsg+164 [0x32035c]
      36  56 kernel_sendmsg+86 [0x32064a]
      37  88 sock_no_sendpage+98 [0x322b22]
      38 104 tcp_sendpage+70 [0x35cc1e]
      39  48 sock_sendpage+74 [0x31eb66]
      40  64 pipe_to_sendpage+102 [0x1c4b2e]
      41  64 __splice_from_pipe+120 [0x1c5340]
      42  72 splice_from_pipe+90 [0x1c57e6]
      43  56 generic_splice_sendpage+38 [0x1c5832]
      44  48 do_splice_from+104 [0x1c4c38]
      45  48 direct_splice_actor+52 [0x1c4c88]
      46  80 splice_direct_to_actor+180 [0x1c4f80]
      47  72 do_splice_direct+70 [0x1c5112]
      48  64 do_sendfile+360 [0x19de18]
      49  72 sys_sendfile64+126 [0x19df32]
      50 336 sysc_do_restart+18 [0x111a1a]
      Signed-off-by: default avatarHeiko Carstens <heiko.carstens@de.ibm.com>
      Signed-off-by: default avatarMartin Schwidefsky <schwidefsky@de.ibm.com>
      7f5a8ba6
    • Heiko Carstens's avatar
      [S390] Change default IPL method to IPL_VM. · 46e7951f
      Heiko Carstens authored
      allyesconfig and allmodconfig built kernels have a tape IPL record.
      A the vmreader record makes much more sense, since hardly anybody will
      ever IPL a kernel from tape. So change the default.
      As I side effect I can test these kernels without fiddling around with
      the kernel config ;)
      Signed-off-by: default avatarHeiko Carstens <heiko.carstens@de.ibm.com>
      Signed-off-by: default avatarMartin Schwidefsky <schwidefsky@de.ibm.com>
      46e7951f
    • Frank Munzert's avatar
      [S390] tape: disable interrupts in tape_open and tape_release · b3c21e49
      Frank Munzert authored
      Get tape device lock with interrupts disabled. Otherwise lockdep will issue a
      warning similar to:
      
      =================================
      [ INFO: inconsistent lock state ]
      2.6.27 #1
      ---------------------------------
      inconsistent {in-hardirq-W} -> {hardirq-on-W} usage.
      vol_id/2903 [HC0[0]:SC0[0]:HE1:SE1] takes:
       (sch->lock){++..}, at: [<000003e00004c7a2>] tape_open+0x42/0x1a4 [tape]
      {in-hardirq-W} state was registered at:
        [<000000000007ce5c>] __lock_acquire+0x894/0xa74
        [<000000000007d0ce>] lock_acquire+0x92/0xb8
        [<0000000000345154>] _spin_lock+0x5c/0x9c
        [<0000000000202264>] do_IRQ+0x124/0x1f0
        [<0000000000026610>] io_return+0x0/0x8
      
      irq event stamp: 847
      hardirqs last  enabled at (847): [<000000000007aca6>] trace_hardirqs_on+0x2a/0x38
      hardirqs last disabled at (846): [<0000000000076ca2>] trace_hardirqs_off+0x2a/0x38
      softirqs last  enabled at (0): [<000000000004909e>] copy_process+0x43e/0x11f4
      softirqs last disabled at (0): [<0000000000000000>] 0x0
      
      other info that might help us debug this:
      1 lock held by vol_id/2903:
       #0:  (&bdev->bd_mutex){--..}, at: [<000000000010e0f4>] do_open+0x78/0x358
      
      stack backtrace:
      CPU: 1 Not tainted 2.6.27 #1},
      Process vol_id (pid: 2903, task: 000000003d4c0000, ksp: 000000003d4e3b10)
      0400000000000000 000000003d4e3830 0000000000000002 0000000000000000
             000000003d4e38d0 000000003d4e3848 000000003d4e3848 00000000000168a8
             0000000000000000 000000003d4e3b10 0000000000000000 0000000000000000
             000000003d4e3830 000000000000000c 000000003d4e3830 000000003d4e38a0
             000000000034aa98 00000000000168a8 000000003d4e3830 000000003d4e3880
      Call Trace:
      ([<000000000001681c>] show_trace+0x138/0x158)
       [<0000000000016902>] show_stack+0xc6/0xf8
       [<00000000000170d4>] dump_stack+0xb0/0xc0
       [<0000000000078810>] print_usage_bug+0x1e8/0x228
       [<000000000007a71c>] mark_lock+0xb14/0xd24
       [<000000000007cd5a>] __lock_acquire+0x792/0xa74
       [<000000000007d0ce>] lock_acquire+0x92/0xb8
       [<0000000000345154>] _spin_lock+0x5c/0x9c
       [<000003e00004c7a2>] tape_open+0x42/0x1a4 [tape]
       [<000003e00005185c>] tapeblock_open+0x98/0xd0 [tape]
      Signed-off-by: default avatarFrank Munzert <munzert@de.ibm.com>
      Signed-off-by: default avatarMartin Schwidefsky <schwidefsky@de.ibm.com>
      b3c21e49
    • Roel Kluin's avatar
      [S390] appldata: unsigned ops->size cannot be negative · 13f8b7c5
      Roel Kluin authored
      unsigned ops->size cannot be negative
      Signed-off-by: default avatarRoel Kluin <roel.kluin@gmail.com>
      Signed-off-by: default avatarMartin Schwidefsky <schwidefsky@de.ibm.com>
      13f8b7c5
    • Frank Munzert's avatar
      [S390] tape block: complete request with correct locking · 7a4a1ccd
      Frank Munzert authored
      __blk_end_request must be called with request queue lock held. We need to use
      blk_end_request rather than  __blk_end_request.
      Signed-off-by: default avatarFrank Munzert <munzert@de.ibm.com>
      Signed-off-by: default avatarMartin Schwidefsky <schwidefsky@de.ibm.com>
      7a4a1ccd
    • Heiko Carstens's avatar
      [S390] Fix sysdev class file creation. · da5aae70
      Heiko Carstens authored
      Use sysdev_class_create_file() to create create sysdev class attributes
      instead of sysfs_create_file(). Using sysfs_create_file() wasn't a very
      good idea since the show and store functions have a different amount of
      parameters for sysfs files and sysdev class files.
      In particular the pointer to the buffer is the last argument and
      therefore accesses to random memory regions happened.
      Still worked surprisingly well until we got a kernel panic.
      
      Cc: stable@kernel.org
      Signed-off-by: default avatarHeiko Carstens <heiko.carstens@de.ibm.com>
      Signed-off-by: default avatarMartin Schwidefsky <schwidefsky@de.ibm.com>
      da5aae70
    • Christian Borntraeger's avatar
      [S390] pgtables: Fix race in enable_sie vs. page table ops · 250cf776
      Christian Borntraeger authored
      The current enable_sie code sets the mm->context.pgstes bit to tell
      dup_mm that the new mm should have extended page tables. This bit is also
      used by the s390 specific page table primitives to decide about the page
      table layout - which means context.pgstes has two meanings. This can cause
      any kind of bugs. For example  - e.g. shrink_zone can call
      ptep_clear_flush_young while enable_sie is running. ptep_clear_flush_young
      will test for context.pgstes. Since enable_sie changed that value of the old
      struct mm without changing the page table layout ptep_clear_flush_young will
      do the wrong thing.
      The solution is to split pgstes into two bits
      - one for the allocation
      - one for the current state
      Signed-off-by: default avatarChristian Borntraeger <borntraeger@de.ibm.com>
      Signed-off-by: default avatarMartin Schwidefsky <schwidefsky@de.ibm.com>
      250cf776
    • Jan Glauber's avatar
      [S390] qdio: remove incorrect memset · 2c780914
      Jan Glauber authored
      Remove the memset since zeroing the string is not needed and use
      snprintf instead of sprintf.
      Signed-off-by: default avatarJan Glauber <jang@linux.vnet.ibm.com>
      Signed-off-by: default avatarMartin Schwidefsky <schwidefsky@de.ibm.com>
      2c780914
    • Jan Glauber's avatar
      [S390] qdio: prevent double qdio shutdown in case of I/O errors · 7c045aa2
      Jan Glauber authored
      In case of I/O errors on a qdio subchannel qdio_shutdown may be
      called twice by the qdio driver and by zfcp. Remove the
      superfluous shutdown from qdio and let the upper layer driver
      handle the error condition.
      Signed-off-by: default avatarJan Glauber <jang@linux.vnet.ibm.com>
      Signed-off-by: default avatarMartin Schwidefsky <schwidefsky@de.ibm.com>
      7c045aa2
    • David Milburn's avatar
      libata: ahci enclosure management bit mask · 87943acf
      David Milburn authored
      Enclosure management bit mask definitions.
      Signed-off-by: default avatarDavid Milburn <dmilburn@redhat.com>
      Signed-off-by: default avatarJeff Garzik <jgarzik@redhat.com>
      87943acf
    • David Milburn's avatar
      libata: ahci enclosure management led sync · eb40963c
      David Milburn authored
      Synchronize ahci_sw_activity and ahci_sw_activity_blink with ata_port lock.
      Signed-off-by: default avatarDavid Milburn <dmilburn@redhat.com>
      Signed-off-by: default avatarJeff Garzik <jgarzik@redhat.com>
      eb40963c
    • Alan Cox's avatar
      pata_ninja32: suspend/resume support · e7c0d217
      Alan Cox authored
      I had assumed that the standard recovery would be sufficient for this
      hardware but it isn't. Fix up the other registers on resume as needed. See
      bug #11735
      Signed-off-by: default avatarAlan Cox <alan@redhat.com>
      Signed-off-by: default avatarJeff Garzik <jgarzik@redhat.com>
      e7c0d217
    • Ondrej Zary's avatar
    • Tejun Heo's avatar
      libata: clear saved xfer_mode and ncq_enabled on device detach · 90484ebf
      Tejun Heo authored
      libata EH saves xfer_mode and ncq_enabled at start to later set
      DUBIOUS_XFER flag if it has changed.  These values need to be cleared
      on device detach such that hot device swap doesn't accidentally miss
      DUBIOUS_XFER.
      Signed-off-by: default avatarTejun Heo <tj@kernel.org>
      Signed-off-by: default avatarJeff Garzik <jgarzik@redhat.com>
      90484ebf
    • Tejun Heo's avatar
      sata_sil24: configure max read request size to 4k · e8b3b5e9
      Tejun Heo authored
      Due to request posting limitations, bandwidth of sil3132 is limited to
      around 120MB/s with the minimum pci-e payload size (128bytes) which is
      used by most consumer systems.  However, write throughput can be
      slightly (~3%) increased by increasing the max read requeset size.
      Configure it to 4k which is the maximum supported.  This optimization
      is also done by SIMG's windows driver.
      Signed-off-by: default avatarTejun Heo <tj@kernel.org>
      Signed-off-by: default avatarJeff Garzik <jgarzik@redhat.com>
      e8b3b5e9
    • Randy Dunlap's avatar
      libata: add missing kernel-doc · 3cd8ddbd
      Randy Dunlap authored
      Fix libata missing kernel-doc:
      
      Warning(lin2628-rc2//drivers/ata/libata-core.c:4562): No description
      found for parameter 'tag'
      Signed-off-by: default avatarRandy Dunlap <randy.dunlap@oracle.com>
      Signed-off-by: default avatarJeff Garzik <jgarzik@redhat.com>
      3cd8ddbd
    • Tejun Heo's avatar
      libata: fix device iteration bugs · 4a9c7b33
      Tejun Heo authored
      There were several places where only enabled devices should be
      iterated over but device enabledness wasn't checked.
      
      * IDENTIFY data 40 wire check in cable_is_40wire()
      * xfer_mode/ncq_enabled saving in ata_scsi_error()
      * DUBIOUS_XFER handling in ata_set_mode()
      
      While at it, reformat comments in cable_is_40wire().
      Signed-off-by: default avatarTejun Heo <tj@kernel.org>
      Signed-off-by: default avatarJeff Garzik <jgarzik@redhat.com>
      4a9c7b33
    • Mark Nelson's avatar
      ahci: Add support for Promise PDC42819 · c77a036b
      Mark Nelson authored
      Add an appropriate entry for the Promise PDC42819 controller. It has an
      AHCI mode and so far works correctly with board_ahci.
      
      This chip is found on Promise's FastTrak TX2650 (2 port) and TX4650 (4 port)
      software-based RAID cards (for which there is a binary driver, t3sas) and
      can be found on some motherboards, for example the MSI K9A2 Platinum,
      which calls the chip a Promise T3 controller.
      
      Although this controller also supports SAS devices, its default bootup mode
      is AHCI and the binary driver has to do some magic to get the chip into the
      appropriate mode to drive SAS disks.
      
      Seeing as no documentation is provided by Promise, adding this entry to the
      ahci driver allows the controller to be useful to people as a SATA
      controller (with no ill effects on the system if a SAS disk is connected -
      probing of the port just times out with "link online but device
      misclassified"), without having to resort to using the binary driver. Users
      who require SAS or the proprietary software raid can get this functionality
      using the binary driver.
      Signed-off-by: default avatarMark Nelson <mdnelson8@gmail.com>
      Signed-off-by: default avatarJeff Garzik <jgarzik@redhat.com>
      c77a036b
    • Alan Cox's avatar
      ata: Switch all my stuff to a common address · ab771630
      Alan Cox authored
      Signed-off-by: default avatarJeff Garzik <jgarzik@redhat.com>
      ab771630
  2. 27 Oct, 2008 18 commits