A connection that is closed will no longer be connecting. So
clear the CONNECTING state bit in ceph_con_close(). Similarly,
if the socket has been closed we no longer are in connecting
state (a new connect sequence will need to be initiated).
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
In con_close_socket(), a connection's SOCK_CLOSED flag gets set and
then cleared while its shutdown method is called and its reference
gets dropped.
Previously, that flag got set only if it had not already been set,
so setting it in con_close_socket() might have prevented additional
processing being done on a socket being shut down. We no longer set
SOCK_CLOSED in the socket event routine conditionally, so setting
that bit here no longer provides whatever benefit it might have
provided before.
A race condition could still leave the SOCK_CLOSED bit set even
after we've issued the call to con_close_socket(), so we still clear
that bit after shutting the socket down. Add a comment explaining
the reason for this.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
When a TCP_CLOSE or TCP_CLOSE_WAIT event occurs, the SOCK_CLOSED
connection flag bit is set, and if it had not been previously set
queue_con() is called to ensure con_work() will get a chance to
handle the changed state.
con_work() atomically checks--and if set, clears--the SOCK_CLOSED
bit if it was set. This means that even if the bit were set
repeatedly, the related processing in con_work() only gets called
once per transition of the bit from 0 to 1.
What's important then is that we ensure con_work() gets called *at
least* once when a socket close event occurs, not that it gets
called *exactly* once.
The work queue mechanism already takes care of queueing work
only if it is not already queued, so there's no need for us
to call queue_con() conditionally.
So this patch just makes it so the SOCK_CLOSED flag gets set
unconditionally in ceph_sock_state_change().
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Currently the socket state change event handler records an error
message on a connection to distinguish a close while connecting from
a close while a connection was already established.
Changing connection information during handling of a socket event is
not very clean, so instead move this assignment inside con_work(),
where it can be done during normal connection-level processing (and
under protection of the connection mutex as well).
Move the handling of a socket closed event up to the top of the
processing loop in con_work(); there's no point in handling backoff
etc. if we have a newly-closed socket to take care of.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Recently a bug was fixed in which the bio_iter field in a ceph
message was not being properly re-initialized when a message got
re-transmitted:
commit 43643528cce60ca184fe8197efa8e8da7c89a037
Author: Yan, Zheng <zheng.z.yan@intel.com>
rbd: Clear ceph_msg->bio_iter for retransmitted message
We are now only initializing the bio_iter field when we are about to
start to write message data (in prepare_write_message_data()),
rather than every time we are attempting to write any portion of the
message data (in write_partial_msg_pages()). This means we no
longer need to use the msg->bio_iter field as a flag.
So just don't do that any more. Trust prepare_write_message_data()
to ensure msg->bio_iter is properly initialized, every time we are
about to begin writing (or re-writing) a message's bio data.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
If a message has a non-null bio pointer, its bio_iter field is
initialized in write_partial_msg_pages() if this has not been done
already. This is really a one-time setup operation for sending a
message's (bio) data, so move that initialization code into
prepare_write_message_data() which serves that purpose.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This is a nit, but prepare_write_message() sets the FOOTER_COMPLETE
flag before the CRC for the data portion (recorded in the footer)
has been completely computed. Hold off setting the complete flag
until we've decided it's ready to send.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
In write_partial_msg_pages(), once all the data from a page has been
sent we advance to the next one. Put the code that takes care of
this into its own function.
While modifying write_partial_msg_pages(), make its local variable
"in_trail" be Boolean, and use the local variable "msg" (which is
just the connection's current out_msg pointer) consistently.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Once we call ->connect(), we are racing against the actual
connection, and a subsequent transition from CONNECTING ->
CONNECTED. Set the state to CONNECTING before that, under the
protection of the mutex, to avoid the race.
On 32-bit systems, a large `pglen' would overflow `pglen*sizeof(u32)'
and bypass the check ceph_decode_need(p, end, pglen*sizeof(u32), bad).
It would also overflow the subsequent kmalloc() size, leading to
out-of-bounds write.
Signed-off-by: Xi Wang <xi.wang@gmail.com> Reviewed-by: Alex Elder <elder@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
On 32-bit systems, a large `n' would overflow `n * sizeof(u32)' and bypass
the check ceph_decode_need(p, end, n * sizeof(u32), bad). It would also
overflow the subsequent kmalloc() size, leading to out-of-bounds write.
Signed-off-by: Xi Wang <xi.wang@gmail.com> Reviewed-by: Alex Elder <elder@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
`len' is read from network and thus needs validation. Otherwise a
large `len' would cause out-of-bounds access via the memcpy() call.
In addition, len = 0xffffffff would overflow the kmalloc() size,
leading to out-of-bounds write.
This patch adds a check of `len' via ceph_decode_need(). Also use
kstrndup rather than kmalloc/memcpy.
[elder@inktank.com: added -ENOMEM return for null kstrndup() result]
Signed-off-by: Xi Wang <xi.wang@gmail.com> Reviewed-by: Alex Elder <elder@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
ceph_con_revoke_message() is passed both a message and a ceph
connection. A ceph_msg allocated for incoming messages on a
connection always has a pointer to that connection, so there's no
need to provide the connection when revoking such a message.
Note that the existing logic does not preclude the message supplied
being a null/bogus message pointer. The only user of this interface
is the OSD client, and the only value an osd client passes is a
request's r_reply field. That is always non-null (except briefly in
an error path in ceph_osdc_alloc_request(), and that drops the
only reference so the request won't ever have a reply to revoke).
So we can safely assume the passed-in message is non-null, but add a
BUG_ON() to make it very obvious we are imposing this restriction.
Rename the function ceph_msg_revoke_incoming() to reflect that it is
really an operation on an incoming message.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
ceph_con_revoke() is passed both a message and a ceph connection.
Now that any message associated with a connection holds a pointer
to that connection, there's no need to provide the connection when
revoking a message.
This has the added benefit of precluding the possibility of the
providing the wrong connection pointer. If the message's connection
pointer is null, it is not being tracked by any connection, so
revoking it is a no-op. This is supported as a convenience for
upper layers, so they can revoke a message that is not actually
"in flight."
Rename the function ceph_msg_revoke() to reflect that it is really
an operation on a message, not a connection.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
There are essentially two types of ceph messages: incoming and
outgoing. Outgoing messages are always allocated via ceph_msg_new(),
and at the time of their allocation they are not associated with any
particular connection. Incoming messages are always allocated via
ceph_con_in_msg_alloc(), and they are initially associated with the
connection from which incoming data will be placed into the message.
When an outgoing message gets sent, it becomes associated with a
connection and remains that way until the message is successfully
sent. The association of an incoming message goes away at the point
it is sent to an upper layer via a con->ops->dispatch method.
This patch implements reference counting for all ceph messages, such
that every message holds a reference (and a pointer) to a connection
if and only if it is associated with that connection (as described
above).
For background, here is an explanation of the ceph message
lifecycle, emphasizing when an association exists between a message
and a connection.
Outgoing Messages
An outgoing message is "owned" by its allocator, from the time it is
allocated in ceph_msg_new() up to the point it gets queued for
sending in ceph_con_send(). Prior to that point the message's
msg->con pointer is null; at the point it is queued for sending its
message pointer is assigned to refer to the connection. At that
time the message is inserted into a connection's out_queue list.
When a message on the out_queue list has been sent to the socket
layer to be put on the wire, it is transferred out of that list and
into the connection's out_sent list. At that point it is still owned
by the connection, and will remain so until an acknowledgement is
received from the recipient that indicates the message was
successfully transferred. When such an acknowledgement is received
(in process_ack()), the message is removed from its list (in
ceph_msg_remove()), at which point it is no longer associated with
the connection.
So basically, any time a message is on one of a connection's lists,
it is associated with that connection. Reference counting outgoing
messages can thus be done at the points a message is added to the
out_queue (in ceph_con_send()) and the point it is removed from
either its two lists (in ceph_msg_remove())--at which point its
connection pointer becomes null.
Incoming Messages
When an incoming message on a connection is getting read (in
read_partial_message()) and there is no message in con->in_msg,
a new one is allocated using ceph_con_in_msg_alloc(). At that
point the message is associated with the connection. Once that
message has been completely and successfully read, it is passed to
upper layer code using the connection's con->ops->dispatch method.
At that point the association between the message and the connection
no longer exists.
Reference counting of connections for incoming messages can be done
by taking a reference to the connection when the message gets
allocated, and releasing that reference when it gets handed off
using the dispatch method.
We should never fail to get a connection reference for a
message--the since the caller should already hold one.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
When a ceph message is queued for sending it is placed on a list of
pending messages (ceph_connection->out_queue). When they are
actually sent over the wire, they are moved from that list to
another (ceph_connection->out_sent). When acknowledgement for the
message is received, it is removed from the sent messages list.
During that entire time the message is "in the possession" of a
single ceph connection. Keep track of that connection in the
message. This will be used in the next patch (and is a helpful
bit of information for debugging anyway).
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The function ceph_alloc_msg() is only used to allocate a message
that will be assigned to a connection's in_msg pointer. Rename the
function so this implied usage is more clear.
In addition, make that assignment inside the function (again, since
that's precisely what it's intended to be used for). This allows us
to return what is now provided via the passed-in address of a "skip"
variable. The return type is now Boolean to be explicit that there
are only two possible outcomes.
Make sure the result of an ->alloc_msg method call always sets the
value of *skip properly.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Move the initialization of a ceph connection's private pointer,
operations vector pointer, and peer name information into
ceph_con_init(). Rearrange the arguments so the connection pointer
is first. Hide the byte-swapping of the peer entity number inside
ceph_con_init()
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
All references to the embedded ceph_connection come from the msgr
workqueue, which is drained prior to mon_client destruction. That
means we can ignore con refcounting entirely.
Signed-off-by: Sage Weil <sage@newdream.net> Reviewed-by: Alex Elder <elder@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
A monitor client has a pointer to a ceph connection structure in it.
This is the only one of the three ceph client types that do it this
way; the OSD and MDS clients embed the connection into their main
structures. There is always exactly one ceph connection for a
monitor client, so there is no need to allocate it separate from the
monitor client structure.
So switch the ceph_mon_client structure to embed its
ceph_connection structure.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Once a connection is fully initialized, it is really in a CLOSED
state, so make that explicit by setting the bit in its state field.
It is possible for a connection in NEGOTIATING state to get a
failure, leading to ceph_fault() and ultimately ceph_con_close().
Clear that bits if it is set in that case, to reflect that the
connection truly is closed and is no longer participating in a
connect sequence.
Issue a warning if ceph_con_open() is called on a connection that
is not in CLOSED state.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Start explicitly keeping track of the state of a ceph connection's
socket, separate from the state of the connection itself. Create
placeholder functions to encapsulate the state transitions.
Make the socket state an atomic variable, reinforcing that it's a
distinct transtion with no possible "intermediate/both" states.
This is almost certainly overkill at this point, though the
transitions into CONNECTED and CLOSING state do get called via
socket callback (the rest of the transitions occur with the
connection mutex held). We can back out the atomicity later.
A ceph_connection holds a mixture of connection state (as in "state
machine" state) and connection flags in a single "state" field. To
make the distinction more clear, define a new "flags" field and use
it rather than the "state" field to hold Boolean flag values.
A ceph client has a pointer to a ceph messenger structure in it.
There is always exactly one ceph messenger for a ceph client, so
there is no need to allocate it separate from the ceph client
structure.
Switch the ceph_client structure to embed its ceph_messenger
structure.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Yehuda Sadeh <yehuda@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The functions ceph_con_out_kvec_reset() and ceph_con_out_kvec_add()
are entirely private functions, so drop the "ceph_" prefix in their
name to make them slightly more wieldy.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Yehuda Sadeh <yehuda@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Change the names of the three socket callback functions to make it
more obvious they're specifically associated with a connection's
socket (not the ceph connection that uses it).
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Yehuda Sadeh <yehuda@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
I got lots of NULL pointer dereference Oops when compiling kernel on ceph.
The bug is because the kernel page migration routine replaces some pages
in the page cache with new pages, these new pages' private can be non-zero.
Signed-off-by: Zheng Yan <zheng.z.yan@intel.com> Signed-off-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
When a device was open at a snapshot, and snapshots were deleted or
added, data from the wrong snapshot could be read. Instead of
assuming the snap context is constant, store the actual snap id when
the device is initialized, and rely on the OSDs to signal an error
if we try reading from a snapshot that was deleted.
A recent change made changes to the rbd_client_list be protected by
a spinlock. Unfortunately in rbd_put_client(), the lock is taken
before possibly dropping the last reference to an rbd_client, and on
the last reference that eventually calls flush_workqueue() which can
sleep.
The problem was flagged by a debug spinlock warning:
BUG: spinlock wrong CPU on CPU#3, rbd/27814
The solution is to move the spinlock acquisition and release inside
rbd_client_release(), which is the spot where it's really needed for
protecting the removal of the rbd_client from the client list.
Signed-off-by: Alex Elder <elder@dreamhost.com> Reviewed-by: Sage Weil <sage@newdream.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
In ancient times, the messenger could both initiate and accept connections.
An artifact if that was data structures to store/process an incoming
ceph_msg_connect request and send an outgoing ceph_msg_connect_reply.
Sadly, the negotiation code was referencing those structures and ignoring
important information (like the peer's connect_seq) from the correct ones.
Among other things, this fixes tight reconnect loops where the server sends
RETRY_SESSION and we (the client) retries with the same connect_seq as last
time. This bug pretty easily triggered by injecting socket failures on the
MDS and running some fs workload like workunits/direct_io/test_sync_io.
Signed-off-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
We need to flush the msgr workqueue during mon_client shutdown to
ensure that any work affecting our embedded ceph_connection is
finished so that we can be safely destroyed.
Previously, we were flushing the work queue after osd_client
shutdown and before mon_client shutdown to ensure that any osd
connection refs to authorizers are flushed. Remove the redundant
flush, and document in the comment that the mon_client flush is
needed to cover that case as well.
Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Alex Elder <elder@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
There were a few direct calls to ceph_con_{get,put}() instead of the con
ops from osd_client.c. This is a bug since those ops aren't defined to
be ceph_con_get/put.
This breaks refcounting on the ceph_osd structs that contain the
ceph_connections, and could lead to all manner of strangeness.
The purpose of the ->get and ->put methods in a ceph connection are
to allow the connection to indicate it has a reference to something
external to the messaging system, *not* to indicate something
external has a reference to the connection.
[elder@inktank.com: added that last sentence]
Signed-off-by: Sage Weil <sage@newdream.net> Reviewed-by: Alex Elder <elder@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
(cherry picked from commit 88ed6ea0b295f8e2383d599a04027ec596cdf97b)
In ceph_osdc_release_request(), a reference to the r_reply message
is dropped. But just after that, that same message is revoked if it
was in use to receive an incoming reply. Reorder these so we are
sure we hold a reference until we're actually done with the message.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
(cherry picked from commit 680584fab05efff732b5ae16ad601ba994d7b505)
Usually, we are adding pg_temp entries or removing them. Occasionally they
update. In that case, osdmap_apply_incremental() was failing because the
rbtree entry already exists.
Fix by removing the existing entry before inserting a new one.
Fixes http://tracker.newdream.net/issues/2446
Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Alex Elder <elder@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
There is a race between two __unregister_request() callers: the
reply path and the ceph_osdc_wait_request(). If we get a reply
*and* the timeout expires at roughly the same time, both callers
will try to unregister the request, and the second one will do bad
things.
Simply check if the request is still already unregistered; if so,
return immediately and do nothing.
Fixes http://tracker.newdream.net/issues/2420
Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Alex Elder <elder@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Move the addition of the authorizer buffer to a connection's
out_kvec out of get_connect_authorizer() and into its caller. This
way, the caller--prepare_write_connect()--can avoid adding the
connect header to out_kvec before it has been fully initialized.
Prior to this patch, it was possible for a connect header to be
sent over the wire before the authorizer protocol or buffer length
fields were initialized. An authorizer buffer associated with that
header could also be queued to send only after the connection header
that describes it was on the wire.
Fixes http://tracker.newdream.net/issues/2424
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Change the name of prepare_connect_authorizer(). The next
patch is going to make this function no longer add anything to the
connection's out_kvec, so it will no longer fit the pattern of
the rest of the prepare_connect_*() functions.
In addition, pass the address of a variable that will hold the
authorization protocol to use. Move the assignment of that to the
connection's out_connect structure into prepare_write_connect().
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Rather than passing a bunch of arguments to be filled in with the
content of the ceph_auth_handshake buffer now returned by the
get_authorizer method, just use the returned information in the
caller, and drop the unnecessary arguments.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Have the get_authorizer auth_client method return a ceph_auth
pointer rather than an integer, pointer-encoding any returned
error value. This is to pave the way for making use of the
returned value in an upcoming patch.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
In the create_authorizer method for both the mds and osd clients,
the auth_client->ops pointer is blindly dereferenced. There is no
obvious guarantee that this pointer has been assigned. And
furthermore, even if the ops pointer is non-null there is definitely
no guarantee that the create_authorizer or destroy_authorizer
methods are defined.
Add checks in both routines to make sure they are defined (non-null)
before use. Add similar checks in a few other spots in these files
while we're at it.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Make use of the new ceph_auth_handshake structure in order to reduce
the number of arguments passed to the create_authorizor method in
ceph_auth_client_ops. Use a local variable of that type as a
shorthand in the get_authorizer method definitions.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The definitions for the ceph_mds_session and ceph_osd both contain
five fields related only to "authorizers." Encapsulate those fields
into their own struct type, allowing for better isolation in some
upcoming patches.
Fix the #includes in "linux/ceph/osd_client.h" to lay out their more
complete canonical path.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
In prepare_connect_authorizer(), a connection's get_authorizer
method is called but ignores its return value. This function can
return an error, so check for it and return it if that ever occurs.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
prepare_write_connect() can return an error, but only one of its
callers checks for it. All the rest are in functions that already
return errors, so it should be fine to return the error if one
gets returned.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
prepare_write_connect() prepares a connect message, then sets
WRITE_PENDING on the connection. Then *after* this, it calls
prepare_connect_authorizer(), which updates the content of the
connection buffer already queued for sending. It's also possible it
will result in prepare_write_connect() returning -EAGAIN despite the
WRITE_PENDING big getting set.
Fix this by preparing the connect authorizer first, setting the
WRITE_PENDING bit only after that is done.
In all cases, the value passed as the msgr argument to
prepare_write_connect() is just con->msgr. Just get the msgr
value from the ceph connection and drop the unneeded argument.
The only msgr passed to prepare_write_banner() is also therefore
just the one from con->msgr, so change that function to drop the
msgr argument as well.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
prepare_write_connect() has an argument indicating whether a banner
should be sent out before sending out a connection message. It's
only ever set in one of its callers, so move the code that arranges
to send the banner into that caller and drop the "include_banner"
argument from prepare_write_connect().
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reset a connection's kvec fields in the caller rather than in
prepare_write_connect(). This ends up repeating a few lines of
code but it's improving the separation between distinct operations
on the connection, which we can take advantage of later.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Make the second argument to read_partial() be the ending input byte
position rather than the beginning offset it now represents. This
amounts to moving the addition "to + size" into the caller.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
read_partial() always increases whatever "to" value is supplied by
adding the requested size to it, and that's the only thing it does
with that pointed-to value.
Do that pointer advance in the caller (and then only when the
updated value will be subsequently used), and change the "to"
parameter to be an in-only and non-pointer value.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
There are two blocks of code in read_partial_message()--those that
read the header and footer of the message--that can be replaced by a
call to read_partial(). Do that.
Signed-off-by: Alex Elder <elder@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Al Viro noticed that we were using a non-cpu-encoded value in
a switch statement in osd_req_encode_op(). The result would
clearly not work correctly on a big-endian machine.
Signed-off-by: Alex Elder <elder@dreamhost.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This small adjustment reflects a change that was made in ceph.git commit af6a9f30696c900a2a8bd7ae24e8ed15fb4964bb, about 6 months ago. An N-1
search is not exhaustive. Fixed ceph.git bug #1594.
Reviewed-by: Alex Elder <elder@inktank.com> Signed-off-by: Sage Weil <sage@inktank.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This patch below does what Paul McKenney suggested in the previous thread.
Signed-off-by: Dave Jones <davej@redhat.com> Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Paul Moore <paul@paul-moore.com> Cc: Eric Paris <eparis@parisplace.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: James Morris <james.l.morris@oracle.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Calls into reiserfs journalling code and reiserfs_get_block() need to
be protected with write lock. We remove write lock around calls to high
level quota code in the next patch so these paths would suddently become
unprotected.
Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Calls into highlevel quota code cannot happen under the write lock. These
calls take dqio_mutex which ranks above write lock. So drop write lock
before calling back into quota code.
Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
In reiserfs_quota_on() we do quite some work - for example unpacking
tail of a quota file. Thus we have to hold write lock until a moment
we call back into the quota code.
Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
When remounting reiserfs dquot_suspend() or dquot_resume() can be called.
These functions take dqonoff_mutex which ranks above write lock so we have
to drop it before calling into quota code.
Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Currently, we will schedule session recovery and then return to the
caller of nfs4_handle_exception. This works for most cases, but causes
a hang on the following test case:
Client Server
------ ------
Open file over NFS v4.1
Write to file
Expire client
Try to lock file
The server will return NFS4ERR_BADSESSION, prompting the client to
schedule recovery. However, the client will continue placing lock
attempts and the open recovery never seems to be scheduled. The
simplest solution is to wait for session recovery to run before retrying
the lock.
The overlay on the i830M has a peculiar failure mode: It works the
first time around after boot-up, but consistenly hangs the second time
it's used.
Chris Wilson has dug out a nice errata:
"1.5.12 Clock Gating Disable for Display Register
Address Offset: 06200h–06203h
"Bit 3
Ovrunit Clock Gating Disable.
0 = Clock gating controlled by unit enabling logic
1 = Disable clock gating function
DevALM Errata ALM049: Overlay Clock Gating Must be Disabled: Overlay
& L2 Cache clock gating must be disabled in order to prevent device
hangs when turning off overlay.SW must turn off Ovrunit clock gating
(6200h) and L2 Cache clock gating (C8h)."
Now I've nowhere found that 0xc8 register and hence couldn't apply the
l2 cache workaround. But I've remembered that part of the magic that
the OVERLAY_ON/OFF commands are supposed to do is to rearrange cache
allocations so that the overlay scaler has some scratch space.
And while pondering how that could explain the hang the 2nd time we
enable the overlay, I've remembered that the old ums overlay code did
_not_ issue the OVERLAY_OFF cmd.
And indeed, disabling the OFF cmd results in the overlay working
flawlessly, so I guess we can workaround the lack of the above
workaround by simply never disabling the overlay engine once it's
enabled.
Note that we have the first part of the above w/a already implemented
in i830_init_clock_gating - leave that as-is to avoid surprises.
v2: Add a comment in the code.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=47827 Tested-by: Rhys <rhyspuk@gmail.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
[bwh: Backported to 3.2:
- Adjust context
- s/intel_ring_emit(ring, /OUT_RING(/] Signed-off-by: Ben Hutchings <ben@decadent.org.uk> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
If user space is running in primary mode it can switch to secondary
or access register mode, this is used e.g. in the clock_gettime code
of the vdso. If a signal is delivered to the user space process while
it has been running in access register mode the signal handler is
executed in access register mode as well which will result in a crash
most of the time.
Set the address space control bits in the PSW to the default for the
execution of the signal handler and make sure that the previous
address space control is restored on signal return. Take care
that user space can not switch to the kernel address space by
modifying the registers in the signal frame.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Mirko Lindner <mlindner@marvell.com> Signed-off-by: David S. Miller <davem@davemloft.net> Cc: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The issue occurs when eCryptfs is mounted with a cipher supported by
the crypto subsystem but not by eCryptfs. The mount succeeds and an
error does not occur until a write. This change checks for eCryptfs
cipher support at mount time.
Resolves Launchpad issue #338914, reported by Tyler Hicks in 03/2009.
https://bugs.launchpad.net/ecryptfs/+bug/338914
Signed-off-by: Tim Sally <tsally@atomicpeace.com> Signed-off-by: Tyler Hicks <tyhicks@canonical.com> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
When the eCryptfs mount options do not include '-o acl', but the lower
filesystem's mount options do include 'acl', the MS_POSIXACL flag is not
flipped on in the eCryptfs super block flags. This flag is what the VFS
checks in do_last() when deciding if the current umask should be applied
to a newly created inode's mode or not. When a default POSIX ACL mask is
set on a directory, the current umask is incorrectly applied to new
inodes created in the directory. This patch ignores the MS_POSIXACL flag
passed into ecryptfs_mount() and sets the flag on the eCryptfs super
block depending on the flag's presence on the lower super block.
Additionally, it is incorrect to allow a writeable eCryptfs mount on top
of a read-only lower mount. This missing check did not allow writes to
the read-only lower mount because permissions checks are still performed
on the lower filesystem's objects but it is best to simply not allow a
rw mount on top of ro mount. However, a ro eCryptfs mount on top of a rw
mount is valid and still allowed.
The use of kfree(serial) in error cases of usb_serial_probe
was invalid - usb_serial structure allocated in create_serial()
gets reference of usb_device that needs to be put, so we need
to use usb_serial_put() instead of simple kfree().
Signed-off-by: Jan Safrata <jan.nikitenko@gmail.com> Acked-by: Johan Hovold <jhovold@gmail.com> Cc: Richard Retanubun <richardretanubun@ruggedcom.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
ICMP tuples have id in src and type/code in dst.
So comparing src.u.all with dst.u.all will always fail here
and ip_xfrm_me_harder() is called for every ICMP packet,
even if there was no NAT.
RTL_GIGA_MAC_VER_35 includes no multicast hardware filter.
Signed-off-by: Nathan Walp <faceprint@faceprint.com> Suggested-by: Hayes Wang <hayeswang@realtek.com> Acked-by: Francois Romieu <romieu@fr.zoreil.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This regression was spotted between Debian squeeze and Debian wheezy
kernels (respectively based on 2.6.32 and 3.2). More info about
Wake-on-LAN issues with Realtek's 816x chipsets can be found in the
following thread: http://marc.info/?t=132079219400004
exit_idle() should be called after irq_enter(), otherwise it throws:
[ INFO: suspicious RCU usage. ]
3.6.5 #1 Not tainted
-------------------------------
include/linux/rcupdate.h:725 rcu_read_lock() used illegally while idle!
other info that might help us debug this:
RCU used illegally from idle CPU!
rcu_scheduler_active = 1, debug_locks = 1
RCU used illegally from extended quiescent state!
1 lock held by swapper/0/0:
#0: (rcu_read_lock){......}, at: [<ffffffff810e9fe0>] __atomic_notifier_call_chain+0x0/0x140
The r8169 driver currently limits the DMA burst for TX to 1024 bytes. I have
a box where this prevents the interface from using the gigabit line to its full
potential. This patch solves the problem by setting TX_DMA_BURST to unlimited.
The box has an ASRock B75M motherboard with on-board RTL8168evl/8111evl
(XID 0c900880). TSO is enabled.
I used netperf (TCP_STREAM test) to measure the dependency of TX throughput
on MTU. I did it for three different values of TX_DMA_BURST ('5'=512, '6'=1024,
'7'=unlimited). This chart shows the results:
http://michich.fedorapeople.org/r8169/r8169-effects-of-TX_DMA_BURST.png
Interesting points:
- With the current DMA burst limit (1024):
- at the default MTU=1500 I get only 842 Mbit/s.
- when going from small MTU, the performance rises monotonically with
increasing MTU only up to a peak at MTU=1076 (908 MBit/s). Then there's
a sudden drop to 762 MBit/s from which the throughput rises monotonically
again with further MTU increases.
- With a smaller DMA burst limit (512):
- there's a similar peak at MTU=1076 and another one at MTU=564.
- With unlimited DMA burst:
- at the default MTU=1500 I get nice 940 Mbit/s.
- the throughput rises monotonically with increasing MTU with no strange
peaks.
Notice that the peaks occur at MTU sizes that are multiples of the DMA burst
limit plus 52. Why 52? Because:
20 (IP header) + 20 (TCP header) + 12 (TCP options) = 52
The Realtek-provided r8168 driver (v8.032.00) uses unlimited TX DMA burst too,
except for CFG_METHOD_1 where the TX DMA burst is set to 512 bytes.
CFG_METHOD_1 appears to be the oldest MAC version of "RTL8168B/8111B",
i.e. RTL_GIGA_MAC_VER_11 in r8169. Not sure if this MAC version really needs
the smaller burst limit, or if any other versions have similar requirements.
Signed-off-by: Michal Schmidt <mschmidt@redhat.com> Acked-by: Francois Romieu <romieu@fr.zoreil.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Under a particular load on one machine, I have hit shmem_evict_inode()'s
BUG_ON(inode->i_blocks), enough times to narrow it down to a particular
race between swapout and eviction.
It comes from the "if (freed > 0)" asymmetry in shmem_recalc_inode(),
and the lack of coherent locking between mapping's nrpages and shmem's
swapped count. There's a window in shmem_writepage(), between lowering
nrpages in shmem_delete_from_page_cache() and then raising swapped
count, when the freed count appears to be +1 when it should be 0, and
then the asymmetry stops it from being corrected with -1 before hitting
the BUG.
One answer is coherent locking: using tree_lock throughout, without
info->lock; reasonable, but the raw_spin_lock in percpu_counter_add() on
used_blocks makes that messier than expected. Another answer may be a
further effort to eliminate the weird shmem_recalc_inode() altogether,
but previous attempts at that failed.
So far undecided, but for now change the BUG_ON to WARN_ON: in usual
circumstances it remains a useful consistency check.
In commit c445477d74ab3779 which adds aRFS to the kernel, the CPU
selected for RFS is not set correctly when CPU is changing.
This is causing OOO packets and probably other issues.
Signed-off-by: Tom Herbert <therbert@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Acked-by: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Check (ha->addr == dev->dev_addr) is always true because dev_addr_init()
sets this. Correct the check to behave properly on addr removal.
Signed-off-by: Jiri Pirko <jiri@resnulli.us> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
(1<<optname) is undefined behavior in C with a negative optname or
optname larger than 31. In those cases the result of the shift is
not necessarily zero (e.g., on x86).
This patch simplifies the code with a switch statement on optname.
It also allows the compiler to generate better code (e.g., using a
64-bit mask).
Signed-off-by: Xi Wang <xi.wang@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The sigaddset/sigdelset/sigismember functions that are implemented with
bitfield insn cannot allow the sigset argument to be placed in a data
register since the sigset is wider than 32 bits. Remove the "d"
constraint from the asm statements.
The effect of the bug is that sending RT signals does not work, the signal
number is truncated modulo 32.
When in world roaming mode, allow 40 MHz to be used
on channels 12 and 13 so that an AP that is, e.g.,
using HT40+ on channel 9 (in the UK) can be used.
Reported-by: Eddie Chapman <eddie@ehuk.net> Tested-by: Eddie Chapman <eddie@ehuk.net> Acked-by: Luis R. Rodriguez <mcgrof@qca.qualcomm.com> Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
oom_badness() takes a totalpages argument which says how many pages are
available and it uses it as a base for the score calculation. The value
is calculated by mem_cgroup_get_limit which considers both limit and
total_swap_pages (resp. memsw portion of it).
This is usually correct but since fe35004fbf9e ("mm: avoid swapping out
with swappiness==0") we do not swap when swappiness is 0 which means
that we cannot really use up all the totalpages pages. This in turn
confuses oom score calculation if the memcg limit is much smaller than
the available swap because the used memory (capped by the limit) is
negligible comparing to totalpages so the resulting score is too small
if adj!=0 (typically task with CAP_SYS_ADMIN or non zero oom_score_adj).
A wrong process might be selected as result.
The problem can be worked around by checking mem_cgroup_swappiness==0
and not considering swap at all in such a case.
Signed-off-by: Michal Hocko <mhocko@suse.cz> Acked-by: David Rientjes <rientjes@google.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
projects / karo-tx-linux.git / log