Permalink
Switch branches/tags
Nothing to show
Commits on Jun 12, 2011
  1. If an application specifies zero-copy read-buffers to read the data into

    for a read10 call, the application might have specified too few buffers
    for the full I/O.
    For example if the application tries to read just 512 bytes off a MMC device.
    
    In this case we wopuld run out of buffers and fail with a SEGV.
    
    Instead of failing like this, return NULL from the function to locate a suitable buffer and read the remaining data from the command into the callback buffer instead, just like when no read-buffer at all has been specified.
    sahlberg committed Jun 12, 2011
Commits on Apr 23, 2011
Commits on Apr 22, 2011
  1. Fix typo in a printed string

    sahlberg committed Apr 22, 2011
Commits on Apr 21, 2011
  1. Qemu patch. Update the qemu patch to provide task management abort task

    when the qemu cancels an i/o.
    
    Update the patch to use FUA on all writes when qemu is in writethrough
    mode.
    
    Update to apply and compile against current master for qemu
    sahlberg committed Apr 21, 2011
  2. Fix documentation of how to use 'zero-copy' reads.

    The function to specify the read buffers is called
    scsi_task_add_data_in_buffer, not scsi_task_add_data_buffer
    
    Signed-off-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
    sahlberg committed Apr 21, 2011
Commits on Apr 19, 2011
  1. Add 'zero-copy' in libiscsi for reads.

    It is not real zero-copy since the data is still copied in the kernel,
    but it avoids copying the data inside libiscsi as well as in the callback.
    
    For SCSI tasks that will return data from the target, the application can now
    specify application buffers for libiscsi to read the data directly into.
    This is done by calling scsi_task_add_data_in_buffer(task, ...
    
    These buffers need not be linear, you can specify different areas to read into
    by calling this function several times.
    
    See examples/iscsiclient.c for an example.
    sahlberg committed Apr 19, 2011
Commits on Apr 18, 2011
Commits on Apr 16, 2011
  1. Add a few more tests of READ10 with a mismatch between the amount of …

    …data
    
    specified in the CDB XFERLENGTH and the iSCSI EDTL
    sahlberg committed Apr 16, 2011
  2. Add a simple SCSI test tool.

    For now focused on SBC but should be enhanced to cover other commandsets too
    sahlberg committed Apr 16, 2011
  3. In iscsi_scsi_response_cb()

    dont pick task up from the argument, since this callback can be invoked
    from places where we dont have/know the task strucutre and it is thus NULL.
    
    Instead pick it up from scsi_cbstruct.
    
    This prevents a SEGV when processing REJECT to SCSI commands.
    (the scsi command callback dereferences the task pointer)
    sahlberg committed Apr 16, 2011
Commits on Apr 15, 2011
  1. Add support for READ6

    sahlberg committed Apr 15, 2011
Commits on Apr 13, 2011
  1. TCP KEEPALIVE support

    Add tcp keeplaive support on platforms that support these socket options.
    Set default to fail the socket after 120 seconds
    sahlberg committed Apr 13, 2011
Commits on Apr 10, 2011
  1. Target initiated NOP:

    Initial support to try to respond to target initiated NOPs.
    sahlberg committed Apr 10, 2011
Commits on Apr 9, 2011
  1. Add RESERVATION CONFLICT

    From Richard Sharpe,  add support to handle when a target responds with
    RESERVATION CONFLICT to a scsi i/o
    sahlberg committed Apr 9, 2011
Commits on Apr 6, 2011
Commits on Apr 5, 2011
Commits on Apr 4, 2011
  1. READ10: only set R flag in iscsi if we are reading >0 blocks.

    If we are reading 0 blocks, the R flag should be clear
    sahlberg committed Apr 4, 2011
Commits on Apr 2, 2011
  1. Use ioctl(FIONREAD) to determine how many bytes are readable in the s…

    …ocket
    
    and make sure we dont try to read mor than that.
    sahlberg committed Apr 2, 2011
Commits on Mar 27, 2011
  1. From Richard Sharpe

    Add a mechanism where residual overflow/underflow can be reportad back to
    the application
    
    We probably need somethinf for bidir residuals at some stage too
    sahlberg committed Mar 27, 2011