We dereference "con->in_msg" on the line after it was set to NULL.
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: NAlex Elder <elder@inktank.com>

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.

This was introduced in 928443cd,
with the original socket state code.
Signed-off-by: NSage Weil <sage@inktank.com>
Reviewed-by: NAlex Elder <elder@inktank.com>

The bug can cause NULL pointer dereference in write_partial_msg_pages
Signed-off-by: NZheng Yan <zheng.z.yan@intel.com>
Reviewed-by: NAlex Elder <elder@inktank.com>

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: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

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: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

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: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

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: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

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: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

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: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

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: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

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.

    --------
    | NEW* |  transient initial state
    --------
        | con_sock_state_init()
        v
    ----------
    | CLOSED |  initialized, but no socket (and no
    ----------  TCP connection)
     ^      \
     |       \ con_sock_state_connecting()
     |        ----------------------
     |                              \
     + con_sock_state_closed()       \
     |\                               \
     | \                               \
     |  -----------                     \
     |  | CLOSING |  socket event;       \
     |  -----------  await close          \
     |       ^                            |
     |       |                            |
     |       + con_sock_state_closing()   |
     |      / \                           |
     |     /   ---------------            |
     |    /                   \           v
     |   /                    --------------
     |  /    -----------------| CONNECTING |  socket created, TCP
     |  |   /                 --------------  connect initiated
     |  |   | con_sock_state_connected()
     |  |   v
    -------------
    | CONNECTED |  TCP connection established
    -------------

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.
Signed-off-by: NAlex Elder <elder@inktank.com>
Reviewed-by: Sage Weil<sage@inktank.com>

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.
Signed-off-by: NAlex Elder <elder@inktank.com>
Reviewed-by: Sage Weil<sage@inktank.com>

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: NAlex Elder <elder@inktank.com>
Reviewed-by: NYehuda Sadeh <yehuda@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

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: NAlex Elder <elder@inktank.com>
Reviewed-by: NYehuda Sadeh <yehuda@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

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: NAlex Elder <elder@inktank.com>
Reviewed-by: NYehuda Sadeh <yehuda@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

No code sets a bad_proto method in its ceph connection operations
vector, so just get rid of it.
Signed-off-by: NAlex Elder <elder@inktank.com>
Reviewed-by: NYehuda Sadeh <yehuda@inktank.com>

The ceph connection state "DEAD" is never set and is therefore not
needed.  Eliminate it.
Signed-off-by: NAlex Elder <elder@inktank.com>
Reviewed-by: NYehuda Sadeh <yehuda@inktank.com>

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/2424Signed-off-by: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

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: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

Change prepare_connect_authorizer() so it returns a pointer (or
pointer-coded error).
Signed-off-by: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

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: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

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: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

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: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

Change prepare_connect_authorizer() so it returns without dropping
the connection mutex if the connection has no get_authorizer method.

Use the symbolic CEPH_AUTH_UNKNOWN instead of 0 when assigning
authorization protocols.
Signed-off-by: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

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: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

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.

Partially addresses http://tracker.newdream.net/issues/2424Signed-off-by: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

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: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

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: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

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: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

Move the kvec reset for a connection out of prepare_write_banner and
into its only caller.
Signed-off-by: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

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: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

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: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

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: NAlex Elder <elder@inktank.com>
Reviewed-by: NSage Weil <sage@inktank.com>

Use of "unsigned int" is preferred to bare "unsigned" in net tree.
Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In write_partial_msg_pages(), every case now does an identical call
to kmap(page).  Instead, just call it once inside the CRC-computing
block where it's needed.  Move the definition of kaddr inside that
block, and make it a (char *) to ensure portable pointer arithmetic.

We still don't kunmap() it until after the sendpage() call, in case
that also ends up needing to use the mapping.
Signed-off-by: NAlex Elder <elder@dreamhost.com>
Reviewed-by: NSage Weil <sage@newdream.net>

In write_partial_msg_pages() there is a local variable used to
track the starting offset within a bio segment to use.  Its name,
"page_shift" defies the Linux convention of using that name for
log-base-2(page size).

Since it's only used in the bio case rename it "bio_offset".  Use it
along with the page_pos field to compute the memory offset when
computing CRC's in that function.  This makes the bio case match the
others more closely.
Signed-off-by: NAlex Elder <elder@dreamhost.com>
Reviewed-by: NSage Weil <sage@newdream.net>

There's not a lot of benefit to zero_page_address, which basically
holds a mapping of the zero page through the life of the messenger
module.  Even with our own mapping, the sendpage interface where
it's used may need to kmap() it again.  It's almost certain to
be in low memory anyway.

So stop treating the zero page specially in write_partial_msg_pages()
and just get rid of zero_page_address entirely.
Signed-off-by: NAlex Elder <elder@dreamhost.com>
Reviewed-by: NSage Weil <sage@newdream.net>

Make ceph_tcp_sendpage() be the only place kernel_sendpage() is
used, by using this helper in write_partial_msg_pages().
Signed-off-by: NAlex Elder <elder@dreamhost.com>
Reviewed-by: NSage Weil <sage@newdream.net>

If a message queued for send gets revoked, zeroes are sent over the
wire instead of any unsent data.  This is done by constructing a
message and passing it to kernel_sendmsg() via ceph_tcp_sendmsg().

Since we are already working with a page in this case we can use
the sendpage interface instead.  Create a new ceph_tcp_sendpage()
helper that sets up flags to match the way ceph_tcp_sendmsg()
does now.
Signed-off-by: NAlex Elder <elder@dreamhost.com>
Reviewed-by: NSage Weil <sage@newdream.net>

CRC's are computed for all messages between ceph entities.  The CRC
computation for the data portion of message can optionally be
disabled using the "nocrc" (common) ceph option.  The default is
for CRC computation for the data portion to be enabled.

Unfortunately, the code that implements this feature interprets the
feature flag wrong, meaning that by default the CRC's have *not*
been computed (or checked) for the data portion of messages unless
the "nocrc" option was supplied.

Fix this, in write_partial_msg_pages() and read_partial_message().
Also change the flag variable in write_partial_msg_pages() to be
"no_datacrc" to match the usage elsewhere in the file.

This fixes http://tracker.newdream.net/issues/2064Signed-off-by: NAlex Elder <elder@dreamhost.com>
Reviewed-by: NSage Weil <sage@newdream.net>