fixes surrounding PCIe enhanced error handling:

(1) We need to reject all request generated internaly inside the driver as well
as request arriving from the scsi mid layer when PCIe EEH is active. The fix is
to add a per adapter flag called pci_error_recovery which is checked thru out
the driver when request are generated.

(2) We don't need to call the pci_driver->remove directly from the PCIe
callbacks becuase its already called from the PCIe EEH code. In its place we are
shutting down the watchdog timer, and flushing back all pending IO.

(3) We need to save and restore the pci state across PCIe EEH handling.
Signed-off-by: NEric Moore <eric.moore@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

(1) driver was not setting the sense data size prior to sending SCSI_IO,
resulting in the 0x31190000 loginfo
(2) The driver needs to copy the sense data to local buffer prior
to releasing the request message frame.  If not, the sense buffer gets
overwritten by the next SCSI_IO request.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

In the driver mpt2sas_base_attach subroutine, we need to add
support to return the proper error code when there are memory allocation
failures, e.g. returning -ENOMEM.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Actual problem :
Driver  may receiving the top level expander
removal event prior to all the individual PD removal events, hence the
driver is breaking down all the PDs in advanced to the actaul PD UNHIDE
event. Driver sends multiple
Target Resets to the same volume handle for each individual PD removal.

FIX DESCRIPTION:
To fix this issue, the entire PD device handshake protocal has to be
moved to interrupt context so the breakdown occurs immediately after the
actual UNHIDE event arrives.  The driver will only issue one Target Reset to
the volume handle, occurring after the FAILED or MISSING volume status
event arrives from interrupt context. For the PD UNHIDE event, the driver
will issue target resets to the PD handles, followed by OP_REMOVE.  The
driver will set the "deteleted" flag during interrupt context.  A "pd_handle"
bitmask was introduced so the driver has a list of known pds during entire
life of the PD; this replaces the "hidden_raid_component" flag handle in
the sas_device object.  Each bit in the bitmask represents a device handle.
The bit in the bitmask would be toggled ON/OFF when the HIDE/UNHIDE
events arrive; also this pd_handle bitmask would bould be refreshed
across host resets.

Here we kept older behavior of sending target reset to volume when there is
a single drive pull, wait for the reply, then send target resets
to the PDs.  We kept this behavior so the driver will
behave the same for older versions of firmware.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Converting print level from  MPT2SAS_DEBUG_FMT  to MPT2SAS_INFO_FMT.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Added support so the diag ring buffer can be pulled via sysfs
Added three new shost attributes: host_trace_buffer,
host_trace_buffer_enable, and host_trace_buffer_size.  The
host_trace_buffer_enable attribute is used to either post or release
the trace buffers.   The host_trace_buffer_size attribute contains
the size of the trace buffer. The host_trace_buffer atttribute contains
a maximum 4KB window of the buffer. In order to read the entire host buffer,
you will need to write the offset to  host_trace_buffer prior to reading
it. release the host buffer, then write the entire host buffer contents to
a file.
In addition to this enhancement, we moved the automatic posting of host buffers
at driver load time to be called prior to port_enable, instead of after.
That way discovery is available in the host buffer.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Added a new sysfs shost attribute called ioc_reset_count. This will
keep count of host resets (both diagnostic and message unit).
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Added command line option called disable_discovery.  When enabled
on the command line, the driver will not send a port_enable when loaded
for the first time.   If port_enable is not called, then there is
no discovery of devices, as well as the sas topology.  Then later if one
desires to invoke discovery, then they will need to issue a diagnostic reset.
A diagnostic reset can be issued various ways. One of the way is throught
sysfs.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Driver should not allow multiple host reset when already host reset is in
progress. It is possible that host reset was sent by scsi mid layer while there was already an host reset active,
either issued via IOCTL interface or internaly, like a config page timeout.
Since there was a host reset active, the driver would return a FAILED response
to the scsi mid layer. The solution is make sure pending host resets will
wait for the active host reset to complete before returning control
back up the call stack.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

- C99 knows about USHRT_MAX/SHRT_MAX/SHRT_MIN, not
  USHORT_MAX/SHORT_MAX/SHORT_MIN.

- Make SHRT_MIN of type s16, not int, for consistency.

[akpm@linux-foundation.org: fix drivers/dma/timb_dma.c]
[akpm@linux-foundation.org: fix security/keys/keyring.c]
Signed-off-by: NAlexey Dobriyan <adobriyan@gmail.com>
Acked-by: NWANG Cong <xiyou.wangcong@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Added check before free_pages just to make sure ioc->scsi_lookup is not NULL.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Added support in the driver to support EEH and
PCIe Advanced Error Recovery. This involves adding new
pci_error_handler interface for recovering the controller from PCI Bus
errors, such as SERR and PERR. Some tools are available for simulating
PCI errors in order to validate this interface:
http://www.kernel.org/pub/linux/utils/pci/aer-injectSigned-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Copyright changes for year 2010.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Added proper return type values in case memory allocation failed.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

1. Fixes for little endian issues.
2. Now Debug info for Discovery event is more readable.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Aded checks for shost_recovery flag for early return from function.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

use the get_free_pages API for larger contigious physical memory chunk.
Also, the ioc->chain_depth need to be changed from
a 16bit to 32bit variable because the number of chains will exceed 64k
when the queue depth is large.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

incorrect timestamp on 32 bit platforms: The upper 32 bit of
the timestamp was getting truncated when converting seconds to
milliseconds, which was due to the variable being long. To fix the problem,
the variable needs to be u64. Also the microseconds conversion to
milliseconds was incorrect; it should be divide by 1000 instead of divide by
8.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

This patch replaces incorrect base address space flag with correct IO
resource flag.  Also, performs check of memory resource to validate
resource before using.
Signed-off-by: NRichard A Lary <rlary@linux.vnet.ibm.com>
Acked-by: N"Desai, Kashyap" <Kashyap.Desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Add the cancel_pending_work flag from the fw_event_work structure, and then to
set the flag during host reset, check the flag later from work threads
context and if cancel_pending_work_flag is set ingore those events.

Now Rescan after host reset is changed.
Added special task MPT2SAS_RESCAN_AFTER_HOST_RESET. This task will be queued
at the time of HBA reset. this task is treated as barrier. All work after
MPT2SAS_RESCAN_AFTER_HOST_RESET will be treated as new work and will be
server by callback handle. If host_recovery is going on while running RESCAN
task, it will wait for shos_recovery_done completion which will be called
from HBA reset DONE context.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Reviewed-by: NEric Moore <eric.moore@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

(1) change the formentioned string from logging_level to fwfault_debug
(2) set ioc->fwfault_debug to the command line option mpt2sas_fwfault_debug
setting at driver load time.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Reviewed-by: NEric Moore <eric.moore@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Use resource_size_t to define the type resource for the system interface
register set.
The existing implementation was using "unsigned long" which would be 32 bit
in 32 bit OS.  If 32 bit OS is using 64 bit physical
address space for the system interface register set, we need to shift to
using resource_size_t which takes care of physical address space.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Reviewed-by: NEric Moore <eric.moore@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Internal command scsih_cmds init is included in mpt2sas_base_attach.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Cc: Stable Tree <stable@kernel.org>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

(1) EEDP(End to End data protection) was not working. This was due to not
setting EEDP BlockSize and Flags to little endian format in the message
frame.
(2) Some expander sysfs attributes were not getting set properly.  The sas
format was not getting set due to endian issues with sas_format field in the
struct rep_manu_reply. Since sas_format was not set properly, the
component_vendor_id, component_revision_id, and component_id were not set.
(3) In _transport_smp_handler: we don't need to convert the smid from little
endian to cpu prior to calling mpt2sas_base_free_smid, because its allready
in cpu format. (4) Some loginfos and ioc status were not xonverted from
little endian to cpu.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NEric Moore <Eric.moore@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

cpu_to_le64 when calculating the physical dma address. This will properly
handle endianess on big endian systems.  The return value of this function
was changed from dma_addr_t to __le64. Remove the typecasting of u32 when
setting the SenseBufferLowAddress, since its already in __le32 format.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NEric Moore <Eric.moore@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

The driver needs to retrieve the ioc facts prior to putting the controller
into READY state. The current design is calling ioc facts after putting the
controller into READY state, which means the driver is sending a diag reset
instead of message unit reset becuase the capability information is not yet
available.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NEric Moore <Eric.moore@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Added support to set the TimeStamp when sending ioc_init.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NEric Moore <Eric.moore@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Added tests for registry entries of EXBuffSize, EXImmed, and EXType to
support the new Extended diag buffer type.  Modified code where necessary to
handle the new ExtendedType field in the F/W diagnostic Post and Release
messages.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NEric Moore <Eric.moore@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Added command line option diag_buffer_enable. When the command line option is
set, the driver will automatically post diag buffers at driver load time.
The command line option diag_buffer_enable is bitwise, so it's possible to
enable both and/or snapshot + trace buffers.  For trace, the driver will
allocate 1MB buffer, whereas for snapshot its 2MB. The purpose for this is
so the enduser doesn't have to manually use an application to setup diag
buffers for debugging firmware related issues.

Here is some examples
trace:
# insmod mpt2sas.ko diag_buffer_enable=1

snapshot:
# insmod mpt2sas.ko diag_buffer_enable=2

both trace and snapshot:
# insmod mpt2sas.ko diag_buffer_enable=3
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NEric Moore <Eric.moore@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Fixed some of the comments sections for some of the function so "@ioc:
pointer to scsi command object" was changed to "@ioc: per adapter object"
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NEric Moore <Eric.moore@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Added command line option and shost sysfs attribute called
mpt2sas_fwfault_debug. When enduser writes a "1" to this parameter, this
will enable support in the driver for debugging firmware timeout related
issues.  This handling was added in three areas (a) scsi error handling
callback called task_abort, (b) IOCTL interface, and (c) other timeouts that
result in diag resets, such as manufacturing config pages.  When this
support is enabled, the driver will provide dump_stack to console, halt
controller firmware, and panic driver. The end user probably would want to
setup serial console redirection so the dump stack can be seen.

Here are the three methods for enable this support:

(a) # insmod mpt2sas.ko mpt2sas_fwfault_debug=1
(b) # echo 1 > /sys/module/mpt2sas/parameters/mpt2sas_fwfault_debug
(c) # echo 1 > /sys/class/scsi_host/host#/fwfault_debug  (where # is
the host number)
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NEric Moore <Eric.moore@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Following a diag_reset, a request to send an ioc_init is timing out.  The
timeout occurred within the HANDSHAKE logic while waiting on firmware to
acknowledge that the driver had wrote to the doorbell register.  This was
root caused to a logic timeout in the firmware code.  The proposed solution
is for the driver to call the udelay instead of msleep API in function where
its looping reading the interrupt status.  In addition to this change, there
were two additional cases where we deleted the clearing interrupt status
outside handshake context.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Now driver call init_completion on a per request basis.  At some
point the wait_for_completion_timeout is not waiting for the timeout,
instead returning immediately, thus going into diag reset.  This fix will
address all request using the wait_for_completion_timeout API. The previous
implimentation was only calling init_completion at driver
load time.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

(1) Added three new functions to handle sending target resest and OP_REMOVE
from interrupt time, they are _scsih_tm_tr_send, _scsih_tm_tr_complete, and
_scsih_sas_control_complete.  This code will create a link list of pending
target resets if there is no more available request in the hipriority
request queue.  The list is stored in ioc->delayed_tr_list.

(2) All callback handler return type is changed from void to u8.
Now _base_interrupt will check for return type of callback handlers to
take decision of message frame is already freed or not.
In genral,
Return 1 meaning mf should be freed from _base_interrupt
       0 means the mf is freed from function.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

1) create a pool of high priority message frames in the region of memory
between message frames and chains.  The modifications are in
_base_allocate_memory_pools.  Also create a seperate pool of memory for
internal commands located near the same region of memory.  The pool of high
priority message frames is restriced by the facts->HighPriorityCredit.

2) Create additional API for accessing request message frames. New function
mpt2sas_base_get_smid_hpr is for highpriority request. New function
mpt2sas_base_get_smid_scsiio for SCSI_IO, passing in the scsi command
pointer.  The mpt2sas_base_get_smid function is for requesting internal
commands.

3) Added new function _base_get_cb_idx to obtain the callback
index from one of the three pools of request message frames.

4) Removed wrapper functions _scsih_scsi_lookup_set and
_scsih_scsi_lookup_getclear. These were removed because this handling was
moved into mpt2sas_base_get_smid_scsiio and mpt2sas_base_free_smid.

5) The function mpt2sas_base_free_smid is modified so the request message
frames are put back on one of the three pools of request message frames.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Update the copyright year to 2009 through out the code.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Drivers header are updated to the MPI2 REV K headers.
Renamed VF_ID to msix_index in all call back handlers.
VF_ID is removed from all request descriptor.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

Cleaned up base_interrupt routine to be more effiecent.

Deleted about a third of the config page API by moving redundant code from all
the calling functions to _config_request.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Reviewed-by: NEric Moore <Eric.moore@lsi.com>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

This patch modifies the slave_configure callback so the messages that get sent
to system log for RAID1E volumes contain the string "RAID10" instead of
"RAID1E". These messages contain information regarding what kind of scsi device
is being added. Certain OEMS can enable displaying the RAID10 string instead of
RAID1E via manufacturing page 10.   The driver will read this config page at
driver load time, then determine from the GenericFlags0 bits whether display
the RAID10 or RAID1E string, also even drive count is taken into consideration.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Reviewed-by: NEric Moore <Eric.moore@lsi.com>
Cc: Stable Tree <stable@kernel.org>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>

This patch renames the flag for indicating host reset from
ioc_reset_in_progress to shost_recovery. It also removes the spin locks
surrounding the setting of this flag, which are unnecessary.   Sanity checks on
the shost_recovery flag were added thru out the code so as to prevent sending
firmware commands during host reset.  Also, the setting of the shost state to
SHOST_RECOVERY was removed to prevent deadlocks, this is actually better
handled by the shost_recovery flag.
Signed-off-by: NKashyap Desai <kashyap.desai@lsi.com>
Reviewed-by: NEric Moore <Eric.moore@lsi.com>
Cc: Stable Tree <stable@kernel.org>
Signed-off-by: NJames Bottomley <James.Bottomley@suse.de>