- add a comment to the device structure that the device_busy field
is now protected by the request_queue->queue_lock
- null out sdev->request_queue after the queue is released to trap
any (and there shouldn't be any) use after the queue is freed.
Signed-off-by: James Bottomley <[email protected]>
The current problem seen is that the queue lock is actually in the
SCSI device structure, so when that structure is freed on device
release, we go boom if the queue tries to access the lock again.
The fix here is to move the lock from the scsi_device to the queue.
Signed-off-by: James Bottomley <[email protected]>
This driver has had it's own different infrastructure for doing this for
ages, but it's time it used the common one.
Signed-off-by: James Bottomley <[email protected]>
The attachment combines the most recent patch from
Yum Rayan <[email protected]> (to reduce sg stack
usage), Adrian Bunk <[email protected]> (to fix check
after use) and me (fix elapsed time calculation
(duration) on ia64 machines).
I have modified the patch from Yum Rayan so kmalloc()
in sg_read() is only called for the (rare) code paths
that need them.
Changelog:
- reduce stack usage in sg_ioctl() and sg_read()
- fix check after use in sg_mmap()
- hold duration internally in milliseconds and
check current time later than held time
Signed-off-by: Douglas Gilbert <[email protected]>
Signed-off-by: James Bottomley <[email protected]>
The conditions that cause these calls to MD_BUG are not kernel bugs, just
oddities in what userspace is asking for.
Also convert analyze_sbs to return void, and the value it returned was
always 0.
Signed-off-by: Neil Brown <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
There is a tiny race when de-registering an MD thread, in that the thread
could disappear before it is set a SIGKILL, causing send_sig to have
problems.
This is most easily closed by holding tasklist_lock between enabling the
thread to exit (setting ->run to NULL) and telling it to exit.
(akpm: ick. Needs to use kthread API and stop using signals)
Signed-off-by: Neil Brown <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
This patch does the long overdue updates to MAINTAINERS file for aty128fb
and radeonfb.
Signed-off-by: Benjamin Herrenschmidt <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Fix the formatting of some comments in 8250.c, and add a note that the
register_serial / unregister_serial shouldn't be used in new code.
We do this here in preference to adding to linux/serial.h, since that is used
by a number of non-8250 drivers which pretend to be 8250. It is not known
whether it would be appropriate to do so.
Signed-off-by: Russell King <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
We were failing to close on an error path, resulting in a leak of struct files
which could take a v4 server down fairly quickly.... So call
nfs4_close_delegation instead of just open-coding parts of it.
Simplify the cleanup on delegation failure while we're at it.
Signed-off-by: J. Bruce Fields <[email protected]>
Signed-off-by: Neil Brown <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Fixes the error "RPC: failed to contact portmap (errno -512)." when the server
later tries to unregister from the portmapper.
Signed-off-by: Trond Myklebust <[email protected]>
Signed-off-by: J. Bruce Fields <[email protected]>
Signed-off-by: Neil Brown <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
This fixes the lots-of-fsx-linux-instances-cause-a-slow-leak bug.
It's been there since 2.6.6, caused by:
ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.5/2.6.5-mm4/broken-out/jbd-move-locked-buffers.patch
That patch moves under-writeout ordered-data buffers onto a separate journal
list during commit. It took out the old code which was based on a single
list.
The old code (necessarily) had logic which would restart I/O against buffers
which had been redirtied while they were on the committing transaction's
t_sync_datalist list. The new code only writes buffers once, ignoring
redirtyings by a later transaction, which is good.
But over on the truncate side of things, in journal_unmap_buffer(), we're
treating buffers on the t_locked_list as inviolable things which belong to the
committing transaction, and we just leave them alone during concurrent
truncate-vs-commit.
The net effect is that when truncate tries to invalidate a page whose buffers
are on t_locked_list and have been redirtied, journal_unmap_buffer() just
leaves those buffers alone. truncate will remove the page from its mapping
and we end up with an anonymous clean page with dirty buffers, which is an
illegal state for a page. The JBD commit will not clean those buffers as they
are removed from t_locked_list. The VM (try_to_free_buffers) cannot reclaim
these pages.
The patch teaches journal_unmap_buffer() about buffers which are on the
committing transaction's t_locked_list. These buffers have been written and
I/O has completed. We can take them off the transaction and undirty them
within the context of journal_invalidatepage()->journal_unmap_buffer().
Acked-by: "Stephen C. Tweedie" <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Decouple table of HCA features from exact HCA device type. Add a current FW
version field so we can warn when someone is using old FW. Add support for
new MT25204 HCA.
Remove the warning about mem-free support, since it should be pretty solid at
this point.
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Fix RDMA in mem-free mode: we need to make sure that the RDMA context memory
is mapped for the HCA.
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Update initialization of receive queue to match new documentation. This
change is required to support new MT25204 HCA.
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Clean up mem-free mode support by introducing mthca_is_memfree() function,
which encapsulates the logic of deciding if a device is mem-free.
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Minor tweaks to firmware command handling: kill off an unused get of a value,
and add a little more info to debug output.
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Implement fast memory regions (FMRs), where the driver writes directly into
the HCA's translation tables rather than requiring a firmware command. For
Tavor, MTTs for FMR are separate from regular MTTs, and are reserved at driver
initialization. This is done to limit the amount of virtual memory needed to
map the MTTs. For Arbel, there's no such limitation, and all MTTs and MPTs
may be used for FMR or for regular MR.
Signed-off-by: Michael S. Tsirkin <[email protected]>
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Split Tavor and Arbel/mem-free index<->hw key munging routines, so that FMR
implementation can call correct implementation without testing HCA type (which
it already knows).
Signed-off-by: Michael S. Tsirkin <[email protected]>
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Add mthca_table_find() function, which returns the lowmem address of an entry
in a mem-free HCA's context tables. This will be used by the FMR
implementation.
Signed-off-by: Michael S. Tsirkin <[email protected]>
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Add code for SYNC_TPT firmware command, which will be used by FMR
implementation.
Signed-off-by: Michael S. Tsirkin <[email protected]>
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Add mthca_write64_raw() function, which will be used to write FMR entries that
are in ioremapped PCI memory.
Signed-off-by: Michael S. Tsirkin <[email protected]>
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Encapsulate the buddy allocator used for MTT segments. This cleans up the
code and also gets us ready to add FMR support.
Signed-off-by: Michael S. Tsirkin <[email protected]>
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Fix bug in MTT allocation in mem-free mode.
I misunderstood the MTT size value returned by the firmware -- it is really
the size of a single MTT entry, since mem-free mode does not segment the MTT
as the original firmware did. This meant that our MTT addresses ended up
being off by a factor of 8. This meant that our MTT allocations might
overlap, and so we could overwrite and corrupt earlier memory regions when
writing new MTT entries.
We fix this by always using our 64-byte MTT segment size. This allows some
simplification of the code as well, since there's no reason to put the MTT
segment size in a variable -- we can always use our enum value directly.
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Add code to support RDMA and atomic send work requests in mem-free mode.
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
CQ numbers are only 24 bits, so only print 6 hex digits and mask off reserved
part when reporting a CQ event.
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
On error path, only free doorbell records if we're in mem-free mode.
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Print IRQ number when NOP command interrupt test fails to help debugging.
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Fix error handling in MR allocation for mem-free mode: mthca_free must get an
MR index, not a key.
Signed-off-by: Michael S. Tsirkin <[email protected]>
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Doorbell record pages are allocated in HCA page size chunks (always 4096
bytes), so we need to divide by 4096 and not PAGE_SIZE when figuring out how
many pages we'll need space for.
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
It's cleaner to kfree mthca_mr, and not rely on the fact that ib_mr is the
first field in mthca_mr.
Signed-off-by: Michael S. Tsirkin <[email protected]>
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
The first buffer of a memory region is not required to be page-aligned, so
don't return an error if it's not.
Signed-off-by: Michael S. Tsirkin <[email protected]>
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
When posting a work request with immediate data, put the immediate data in the
immediate data field of the hardware's work request (rather than overwriting
the flags field).
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Fix calculation of rdb_shift by using original number of QPs, not
their slot in profile[] (which will be rearranged when we sort it).
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
In mem-free mode, when allocating memory regions, make sure that the HCA has
context memory mapped to cover the virtual space used for the MPT and MTTs
being used.
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Fix handling of MAD agent registrations with mgmt_class == 0. In this case
ib_umad should pass a NULL registration request to the MAD core rather than a
request with mgmt_class set to 0.
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Mask bits correctly from jhash result in ib_fmr_hash() so that the
computed bucket index is within our hash table. This fixes an SDP
crash.
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Replace the *wc field in ib_mad_recv_wc from pointing to a structure on the
stack to one allocated with the received MAD buffer. This allows a client to
access the *wc field after their receive completion handler has returned.
Signed-off-by: Sean Hefty <[email protected]>
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Update IPoIB documentation now that multicast debugging files have moved from
ipoibdebugfs to debugfs.
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Convert IPoIB to use debugfs instead of its own custom debugging filesystem.
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Correct and simplify calculation of static rate. We need to round up the
quotient of (local_rate - path_rate) / path_rate. To round up we add
(path_rate - 1) to the numerator, so the quotient simplifies to (local_rate -
1) / path_rate.
No idea how I came up with the old formula.
Signed-off-by: Roland Dreier <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
