Allow the timestamp on the sk_buff holding the first DATA packet of a reply
to be queried. This can then be used as a base for the expiry time
calculation on the callback promise duration indicated by an operation
result.
Signed-off-by: David Howells <dhowells@redhat.com>
Push iov_iter up from rxrpc_kernel_recv_data() to its caller to allow
non-contiguous iovs to be passed down, thereby permitting file reading to
be simplified in the AFS filesystem in a future patch.
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Immediately flush any outstanding ACK on entry to rxrpc_recvmsg_data() -
which transfers data to the target buffers - if we previously had an Rx
underrun (ie. we returned -EAGAIN because we ran out of received data).
This lets the server know what we've managed to receive something.
Also flush any outstanding ACK after calling the function if it hit -EAGAIN
to let the server know we processed some data.
It might be better to send more ACKs, possibly on a time-based scheme, but
that needs some more consideration.
With this and some additional AFS patches, it is possible to get large
unencrypted O_DIRECT reads to be almost as fast as NFS over TCP. It looks
like it might be theoretically possible to improve performance yet more for
a server running a single operation as investigation of packet timestamps
indicates that the server keeps stalling.
The issue appears to be that rxrpc runs in to trouble with ACK packets
getting batched together (up to ~32 at a time) somewhere between the IP
transmit queue on the client and the ethernet receive queue on the server.
However, this case isn't too much of a worry as even a lightly loaded
server should be receiving sufficient packet flux to flush the ACK packets
to the UDP socket.
Signed-off-by: David Howells <dhowells@redhat.com>
The final ACK that closes out an rxrpc call needs to be transmitted by the
client unless we're going to follow up with a DATA packet for a new call on
the same channel (which implicitly ACK's the previous call, thereby saving
an ACK).
Currently, we don't do that, so if no follow on call is immediately
forthcoming, the server will resend the last DATA packet - at which point
rxrpc_conn_retransmit_call() will be triggered and will (re)send the final
ACK. But the server has to hold on to the last packet until the ACK is
received, thereby holding up its resources.
Fix the client side to propose a delayed final ACK, to be transmitted after
a short delay, assuming the call isn't superseded by a new one.
Signed-off-by: David Howells <dhowells@redhat.com>
The variable 'len' is being initialized with a value that is never
read and it is re-assigned later, hence the initialization is redundant
and can be removed.
Cleans up clang warning:
net/rxrpc/recvmsg.c:275:15: warning: Value stored to 'len' during its
initialization is never read
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Due to a check recently added to copy_to_user(), it's now not permitted to
copy from slab-held data to userspace unless the slab is whitelisted. This
affects rxrpc_recvmsg() when it attempts to place an RXRPC_USER_CALL_ID
control message in the userspace control message buffer. A warning is
generated by usercopy_warn() because the source is the copy of the
user_call_ID retained in the rxrpc_call struct.
Work around the issue by copying the user_call_ID to a variable on the
stack and passing that to put_cmsg().
The warning generated looks like:
Bad or missing usercopy whitelist? Kernel memory exposure attempt detected from SLUB object 'dmaengine-unmap-128' (offset 680, size 8)!
WARNING: CPU: 0 PID: 1401 at mm/usercopy.c:81 usercopy_warn+0x7e/0xa0
...
RIP: 0010:usercopy_warn+0x7e/0xa0
...
Call Trace:
__check_object_size+0x9c/0x1a0
put_cmsg+0x98/0x120
rxrpc_recvmsg+0x6fc/0x1010 [rxrpc]
? finish_wait+0x80/0x80
___sys_recvmsg+0xf8/0x240
? __clear_rsb+0x25/0x3d
? __clear_rsb+0x15/0x3d
? __clear_rsb+0x25/0x3d
? __clear_rsb+0x15/0x3d
? __clear_rsb+0x25/0x3d
? __clear_rsb+0x15/0x3d
? __clear_rsb+0x25/0x3d
? __clear_rsb+0x15/0x3d
? finish_task_switch+0xa6/0x2b0
? trace_hardirqs_on_caller+0xed/0x180
? _raw_spin_unlock_irq+0x29/0x40
? __sys_recvmsg+0x4e/0x90
__sys_recvmsg+0x4e/0x90
do_syscall_64+0x7a/0x220
entry_SYSCALL_64_after_hwframe+0x26/0x9b
Reported-by: Jonathan Billings <jsbillings@jsbillings.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Kees Cook <keescook@chromium.org>
Tested-by: Jonathan Billings <jsbillings@jsbillings.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add an extra timeout that is set/updated when we send a DATA packet that
has the request-ack flag set. This allows us to detect if we don't get an
ACK in response to the latest flagged packet.
The ACK packet is adjudged to have been lost if it doesn't turn up within
2*RTT of the transmission.
If the timeout occurs, we schedule the sending of a PING ACK to find out
the state of the other side. If a new DATA packet is ready to go sooner,
we cancel the sending of the ping and set the request-ack flag on that
instead.
If we get back a PING-RESPONSE ACK that indicates a lower tx_top than what
we had at the time of the ping transmission, we adjudge all the DATA
packets sent between the response tx_top and the ping-time tx_top to have
been lost and retransmit immediately.
Rather than sending a PING ACK, we could just pick a DATA packet and
speculatively retransmit that with request-ack set. It should result in
either a REQUESTED ACK or a DUPLICATE ACK which we can then use in lieu the
a PING-RESPONSE ACK mentioned above.
Signed-off-by: David Howells <dhowells@redhat.com>
Don't transmit a DELAY ACK immediately on proposal when the Rx window is
rotated, but rather defer it to the work function. This means that we have
a chance to queue/consume more received packets before we actually send the
DELAY ACK, or even cancel it entirely, thereby reducing the number of
packets transmitted.
We do, however, want to continue sending other types of packet immediately,
particularly REQUESTED ACKs, as they may be used for RTT calculation by the
other side.
Signed-off-by: David Howells <dhowells@redhat.com>
Fix the rxrpc call expiration timeouts and make them settable from
userspace. By analogy with other rx implementations, there should be three
timeouts:
(1) "Normal timeout"
This is set for all calls and is triggered if we haven't received any
packets from the peer in a while. It is measured from the last time
we received any packet on that call. This is not reset by any
connection packets (such as CHALLENGE/RESPONSE packets).
If a service operation takes a long time, the server should generate
PING ACKs at a duration that's substantially less than the normal
timeout so is to keep both sides alive. This is set at 1/6 of normal
timeout.
(2) "Idle timeout"
This is set only for a service call and is triggered if we stop
receiving the DATA packets that comprise the request data. It is
measured from the last time we received a DATA packet.
(3) "Hard timeout"
This can be set for a call and specified the maximum lifetime of that
call. It should not be specified by default. Some operations (such
as volume transfer) take a long time.
Allow userspace to set/change the timeouts on a call with sendmsg, using a
control message:
RXRPC_SET_CALL_TIMEOUTS
The data to the message is a number of 32-bit words, not all of which need
be given:
u32 hard_timeout; /* sec from first packet */
u32 idle_timeout; /* msec from packet Rx */
u32 normal_timeout; /* msec from data Rx */
This can be set in combination with any other sendmsg() that affects a
call.
Signed-off-by: David Howells <dhowells@redhat.com>
Delay terminal ACK transmission on a client call by deferring it to the
connection processor. This allows it to be skipped if we can send the next
call instead, the first DATA packet of which will implicitly ack this call.
Signed-off-by: David Howells <dhowells@redhat.com>
Place a spinlock around the invocation of call->notify_rx() for a kernel
service call and lock again when ending the call and replace the
notification pointer with a pointer to a dummy function.
This is required because it's possible for rxrpc_notify_socket() to be
called after the call has been ended by the kernel service if called from
the asynchronous work function rxrpc_process_call().
However, rxrpc_notify_socket() currently only holds the RCU read lock when
invoking ->notify_rx(), which means that the afs_call struct would need to
be disposed of by call_rcu() rather than by kfree().
But we shouldn't see any notifications from a call after calling
rxrpc_kernel_end_call(), so a lock is required in rxrpc code.
Without this, we may see the call wait queue as having a corrupt spinlock:
BUG: spinlock bad magic on CPU#0, kworker/0:2/1612
general protection fault: 0000 [#1] SMP
...
Workqueue: krxrpcd rxrpc_process_call
task: ffff88040b83c400 task.stack: ffff88040adfc000
RIP: 0010:spin_bug+0x161/0x18f
RSP: 0018:ffff88040adffcc0 EFLAGS: 00010002
RAX: 0000000000000032 RBX: 6b6b6b6b6b6b6b6b RCX: ffffffff81ab16cf
RDX: ffff88041fa14c01 RSI: ffff88041fa0ccb8 RDI: ffff88041fa0ccb8
RBP: ffff88040adffcd8 R08: 00000000ffffffff R09: 00000000ffffffff
R10: ffff88040adffc60 R11: 000000000000022c R12: ffff88040aca2208
R13: ffffffff81a58114 R14: 0000000000000000 R15: 0000000000000000
....
Call Trace:
do_raw_spin_lock+0x1d/0x89
_raw_spin_lock_irqsave+0x3d/0x49
? __wake_up_common_lock+0x4c/0xa7
__wake_up_common_lock+0x4c/0xa7
? __lock_is_held+0x47/0x7a
__wake_up+0xe/0x10
afs_wake_up_call_waiter+0x11b/0x122 [kafs]
rxrpc_notify_socket+0x12b/0x258
rxrpc_process_call+0x18e/0x7d0
process_one_work+0x298/0x4de
? rescuer_thread+0x280/0x280
worker_thread+0x1d1/0x2ae
? rescuer_thread+0x280/0x280
kthread+0x12c/0x134
? kthread_create_on_node+0x3a/0x3a
ret_from_fork+0x27/0x40
In this case, note the corrupt data in EBX. The address of the offending
afs_call is in R12, plus the offset to the spinlock.
Signed-off-by: David Howells <dhowells@redhat.com>
Provide support for a kernel service to make use of the service upgrade
facility. This involves:
(1) Pass an upgrade request flag to rxrpc_kernel_begin_call().
(2) Make rxrpc_kernel_recv_data() return the call's current service ID so
that the caller can detect service upgrade and see what the service
was upgraded to.
Signed-off-by: David Howells <dhowells@redhat.com>
Keep the rxrpc_connection struct's idea of the service ID that is exposed
in the protocol separate from the service ID that's used as a lookup key.
This allows the protocol service ID on a client connection to get upgraded
without making the connection unfindable for other client calls that also
would like to use the upgraded connection.
The connection's actual service ID is then returned through recvmsg() by
way of msg_name.
Whilst we're at it, we get rid of the last_service_id field from each
channel. The service ID is per-connection, not per-call and an entire
connection is upgraded in one go.
Signed-off-by: David Howells <dhowells@redhat.com>
Add a tracepoint (rxrpc_rx_proto) to record protocol errors in received
packets. The following changes are made:
(1) Add a function, __rxrpc_abort_eproto(), to note a protocol error on a
call and mark the call aborted. This is wrapped by
rxrpc_abort_eproto() that makes the why string usable in trace.
(2) Add trace_rxrpc_rx_proto() or rxrpc_abort_eproto() to protocol error
generation points, replacing rxrpc_abort_call() with the latter.
(3) Only send an abort packet in rxkad_verify_packet*() if we actually
managed to abort the call.
Note that a trace event is also emitted if a kernel user (e.g. afs) tries
to send data through a call when it's not in the transmission phase, though
it's not technically a receive event.
Signed-off-by: David Howells <dhowells@redhat.com>
Use negative error codes in struct rxrpc_call::error because that's what
the kernel normally deals with and to make the code consistent. We only
turn them positive when transcribing into a cmsg for userspace recvmsg.
Signed-off-by: David Howells <dhowells@redhat.com>
The call state may be changed at any time by the data-ready routine in
response to received packets, so if the call state is to be read and acted
upon several times in a function, READ_ONCE() must be used unless the call
state lock is held.
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull networking fixes from David Miller:
1) Fix double-free in batman-adv, from Sven Eckelmann.
2) Fix packet stats for fast-RX path, from Joannes Berg.
3) Netfilter's ip_route_me_harder() doesn't handle request sockets
properly, fix from Florian Westphal.
4) Fix sendmsg deadlock in rxrpc, from David Howells.
5) Add missing RCU locking to transport hashtable scan, from Xin Long.
6) Fix potential packet loss in mlxsw driver, from Ido Schimmel.
7) Fix race in NAPI handling between poll handlers and busy polling,
from Eric Dumazet.
8) TX path in vxlan and geneve need proper RCU locking, from Jakub
Kicinski.
9) SYN processing in DCCP and TCP need to disable BH, from Eric
Dumazet.
10) Properly handle net_enable_timestamp() being invoked from IRQ
context, also from Eric Dumazet.
11) Fix crash on device-tree systems in xgene driver, from Alban Bedel.
12) Do not call sk_free() on a locked socket, from Arnaldo Carvalho de
Melo.
13) Fix use-after-free in netvsc driver, from Dexuan Cui.
14) Fix max MTU setting in bonding driver, from WANG Cong.
15) xen-netback hash table can be allocated from softirq context, so use
GFP_ATOMIC. From Anoob Soman.
16) Fix MAC address change bug in bgmac driver, from Hari Vyas.
17) strparser needs to destroy strp_wq on module exit, from WANG Cong.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (69 commits)
strparser: destroy workqueue on module exit
sfc: fix IPID endianness in TSOv2
sfc: avoid max() in array size
rds: remove unnecessary returned value check
rxrpc: Fix potential NULL-pointer exception
nfp: correct DMA direction in XDP DMA sync
nfp: don't tell FW about the reserved buffer space
net: ethernet: bgmac: mac address change bug
net: ethernet: bgmac: init sequence bug
xen-netback: don't vfree() queues under spinlock
xen-netback: keep a local pointer for vif in backend_disconnect()
netfilter: nf_tables: don't call nfnetlink_set_err() if nfnetlink_send() fails
netfilter: nft_set_rbtree: incorrect assumption on lower interval lookups
netfilter: nf_conntrack_sip: fix wrong memory initialisation
can: flexcan: fix typo in comment
can: usb_8dev: Fix memory leak of priv->cmd_msg_buffer
can: gs_usb: fix coding style
can: gs_usb: Don't use stack memory for USB transfers
ixgbe: Limit use of 2K buffers on architectures with 256B or larger cache lines
ixgbe: update the rss key on h/w, when ethtool ask for it
...
Fix up affected files that include this signal functionality via sched.h.
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
All the routines by which rxrpc is accessed from the outside are serialised
by means of the socket lock (sendmsg, recvmsg, bind,
rxrpc_kernel_begin_call(), ...) and this presents a problem:
(1) If a number of calls on the same socket are in the process of
connection to the same peer, a maximum of four concurrent live calls
are permitted before further calls need to wait for a slot.
(2) If a call is waiting for a slot, it is deep inside sendmsg() or
rxrpc_kernel_begin_call() and the entry function is holding the socket
lock.
(3) sendmsg() and recvmsg() or the in-kernel equivalents are prevented
from servicing the other calls as they need to take the socket lock to
do so.
(4) The socket is stuck until a call is aborted and makes its slot
available to the waiter.
Fix this by:
(1) Provide each call with a mutex ('user_mutex') that arbitrates access
by the users of rxrpc separately for each specific call.
(2) Make rxrpc_sendmsg() and rxrpc_recvmsg() unlock the socket as soon as
they've got a call and taken its mutex.
Note that I'm returning EWOULDBLOCK from recvmsg() if MSG_DONTWAIT is
set but someone else has the lock. Should I instead only return
EWOULDBLOCK if there's nothing currently to be done on a socket, and
sleep in this particular instance because there is something to be
done, but we appear to be blocked by the interrupt handler doing its
ping?
(3) Make rxrpc_new_client_call() unlock the socket after allocating a new
call, locking its user mutex and adding it to the socket's call tree.
The call is returned locked so that sendmsg() can add data to it
immediately.
From the moment the call is in the socket tree, it is subject to
access by sendmsg() and recvmsg() - even if it isn't connected yet.
(4) Lock new service calls in the UDP data_ready handler (in
rxrpc_new_incoming_call()) because they may already be in the socket's
tree and the data_ready handler makes them live immediately if a user
ID has already been preassigned.
Note that the new call is locked before any notifications are sent
that it is live, so doing mutex_trylock() *ought* to always succeed.
Userspace is prevented from doing sendmsg() on calls that are in a
too-early state in rxrpc_do_sendmsg().
(5) Make rxrpc_new_incoming_call() return the call with the user mutex
held so that a ping can be scheduled immediately under it.
Note that it might be worth moving the ping call into
rxrpc_new_incoming_call() and then we can drop the mutex there.
(6) Make rxrpc_accept_call() take the lock on the call it is accepting and
release the socket after adding the call to the socket's tree. This
is slightly tricky as we've dequeued the call by that point and have
to requeue it.
Note that requeuing emits a trace event.
(7) Make rxrpc_kernel_send_data() and rxrpc_kernel_recv_data() take the
new mutex immediately and don't bother with the socket mutex at all.
This patch has the nice bonus that calls on the same socket are now to some
extent parallelisable.
Note that we might want to move rxrpc_service_prealloc() calls out from the
socket lock and give it its own lock, so that we don't hang progress in
other calls because we're waiting for the allocator.
We probably also want to avoid calling rxrpc_notify_socket() from within
the socket lock (rxrpc_accept_call()).
Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Marc Dionne <marc.c.dionne@auristor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Calls made through the in-kernel interface can end up getting stuck because
of a missed variable update in a loop in rxrpc_recvmsg_data(). The problem
is like this:
(1) A new packet comes in and doesn't cause a notification to be given to
the client as there's still another packet in the ring - the
assumption being that if the client will keep drawing off data until
the ring is empty.
(2) The client is in rxrpc_recvmsg_data(), inside the big while loop that
iterates through the packets. This copies the window pointers into
variables rather than using the information in the call struct
because:
(a) MSG_PEEK might be in effect;
(b) we need a barrier after reading call->rx_top to pair with the
barrier in the softirq routine that loads the buffer.
(3) The reading of call->rx_top is done outside of the loop, and top is
never updated whilst we're in the loop. This means that even through
there's a new packet available, we don't see it and may return -EFAULT
to the caller - who will happily return to the scheduler and await the
next notification.
(4) No further notifications are forthcoming until there's an abort as the
ring isn't empty.
The fix is to move the read of call->rx_top inside the loop - but it needs
to be done before the condition is checked.
Reported-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We need to generate a DELAY ACK from the service end of an operation if we
start doing the actual operation work and it takes longer than expected.
This will hard-ACK the request data and allow the client to release its
resources.
To make this work:
(1) We have to set the ack timer and propose an ACK when the call moves to
the RXRPC_CALL_SERVER_ACK_REQUEST and clear the pending ACK and cancel
the timer when we start transmitting the reply (the first DATA packet
of the reply implicitly ACKs the request phase).
(2) It must be possible to set the timer when the caller is holding
call->state_lock, so split the lock-getting part of the timer function
out.
(3) Add trace notes for the ACK we're requesting and the timer we clear.
Signed-off-by: David Howells <dhowells@redhat.com>
In rxrpc_kernel_recv_data(), when we return the error number incurred by a
failed call, we must negate it before returning it as it's stored as
positive (that's what we have to pass back to userspace).
Signed-off-by: David Howells <dhowells@redhat.com>
Separate the output of PING ACKs from the output of other sorts of ACK so
that if we receive a PING ACK and schedule transmission of a PING RESPONSE
ACK, the response doesn't get cancelled by a PING ACK we happen to be
scheduling transmission of at the same time.
If a PING RESPONSE gets lost, the other side might just sit there waiting
for it and refuse to proceed otherwise.
Signed-off-by: David Howells <dhowells@redhat.com>
Split rxrpc_send_data_packet() to separate ACK generation (which is more
complicated) from ABORT generation. This simplifies the code a bit and
fixes the following warning:
In file included from ../net/rxrpc/output.c:20:0:
net/rxrpc/output.c: In function 'rxrpc_send_call_packet':
net/rxrpc/ar-internal.h:1187:27: error: 'top' may be used uninitialized in this function [-Werror=maybe-uninitialized]
net/rxrpc/output.c:103:24: note: 'top' was declared here
net/rxrpc/output.c:225:25: error: 'hard_ack' may be used uninitialized in this function [-Werror=maybe-uninitialized]
Reported-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David Howells <dhowells@redhat.com>
Send an ACK if we haven't sent one for the last two packets we've received.
This keeps the other end apprised of where we've got to - which is
important if they're doing slow-start.
We do this in recvmsg so that we can dispatch a packet directly without the
need to wake up the background thread.
This should possibly be made configurable in future.
Signed-off-by: David Howells <dhowells@redhat.com>
Add a tracepoint to log proposed ACKs, including whether the proposal is
used to update a pending ACK or is discarded in favour of an easlier,
higher priority ACK.
Whilst we're at it, get rid of the rxrpc_acks() function and access the
name array directly. We do, however, need to validate the ACK reason
number given to trace_rxrpc_rx_ack() to make sure we don't overrun the
array.
Signed-off-by: David Howells <dhowells@redhat.com>
Don't send an IDLE ACK at the end of the transmission of the response to a
service call. The service end resends DATA packets until the client sends an
ACK that hard-acks all the send data. At that point, the call is complete.
Signed-off-by: David Howells <dhowells@redhat.com>
Improve sk_buff tracing within AF_RXRPC by the following means:
(1) Use an enum to note the event type rather than plain integers and use
an array of event names rather than a big multi ?: list.
(2) Distinguish Rx from Tx packets and account them separately. This
requires the call phase to be tracked so that we know what we might
find in rxtx_buffer[].
(3) Add a parameter to rxrpc_{new,see,get,free}_skb() to indicate the
event type.
(4) A pair of 'rotate' events are added to indicate packets that are about
to be rotated out of the Rx and Tx windows.
(5) A pair of 'lost' events are added, along with rxrpc_lose_skb() for
packet loss injection recording.
Signed-off-by: David Howells <dhowells@redhat.com>
Remove _enter/_debug/_leave calls from rxrpc_recvmsg_data() of which one
uses an uninitialised variable.
Signed-off-by: David Howells <dhowells@redhat.com>
The code for determining the last packet in rxrpc_recvmsg_data() has been
using the RXRPC_CALL_RX_LAST flag to determine if the rx_top pointer points
to the last packet or not. This isn't a good idea, however, as the input
code may be running simultaneously on another CPU and that sets the flag
*before* updating the top pointer.
Fix this by the following means:
(1) Restrict the use of RXRPC_CALL_RX_LAST to the input routines only.
There's otherwise a synchronisation problem between detecting the flag
and checking tx_top. This could probably be dealt with by appropriate
application of memory barriers, but there's a simpler way.
(2) Set RXRPC_CALL_RX_LAST after setting rx_top.
(3) Make rxrpc_rotate_rx_window() consult the flags header field of the
DATA packet it's about to discard to see if that was the last packet.
Use this as the basis for ending the Rx phase. This shouldn't be a
problem because the recvmsg side of things is guaranteed to see the
packets in order.
(4) Make rxrpc_recvmsg_data() return 1 to indicate the end of the data if:
(a) the packet it has just processed is marked as RXRPC_LAST_PACKET
(b) the call's Rx phase has been ended.
Signed-off-by: David Howells <dhowells@redhat.com>
Move the check of rx_pkt_offset from rxrpc_locate_data() to the caller,
rxrpc_recvmsg_data(), so that it's more clear what's going on there.
Signed-off-by: David Howells <dhowells@redhat.com>
The preallocated call buffer holds a ref on the calls within that buffer.
The ref was being released in the wrong place - it worked okay for incoming
calls to the AFS cache manager service, but doesn't work right for incoming
calls to a userspace service.
Instead of releasing an extra ref service calls in rxrpc_release_call(),
the ref needs to be released during the acceptance/rejectance process. To
this end:
(1) The prealloc ref is now normally released during
rxrpc_new_incoming_call().
(2) For preallocated kernel API calls, the kernel API's ref needs to be
released when the call is discarded on socket close.
(3) We shouldn't take a second ref in rxrpc_accept_call().
(4) rxrpc_recvmsg_new_call() needs to get a ref of its own when it adds
the call to the to_be_accepted socket queue.
In doing (4) above, we would prefer not to put the call's refcount down to
0 as that entails doing cleanup in softirq context, but it's unlikely as
there are several refs held elsewhere, at least one of which must be put by
someone in process context calling rxrpc_release_call(). However, it's not
a problem if we do have to do that.
Signed-off-by: David Howells <dhowells@redhat.com>
rxrpc_recvmsg() needs to make sure that the call it has just been
processing gets requeued for further attention if the buffer has been
filled and there's more data to be consumed. The softirq producer only
queues the call and wakes the socket if it fills the first slot in the
window, so userspace might end up sleeping forever otherwise, despite there
being data available.
This is not a problem provided the userspace buffer is big enough or it
empties the buffer completely before more data comes in.
Signed-off-by: David Howells <dhowells@redhat.com>
Rewrite the data and ack handling code such that:
(1) Parsing of received ACK and ABORT packets and the distribution and the
filing of DATA packets happens entirely within the data_ready context
called from the UDP socket. This allows us to process and discard ACK
and ABORT packets much more quickly (they're no longer stashed on a
queue for a background thread to process).
(2) We avoid calling skb_clone(), pskb_pull() and pskb_trim(). We instead
keep track of the offset and length of the content of each packet in
the sk_buff metadata. This means we don't do any allocation in the
receive path.
(3) Jumbo DATA packet parsing is now done in data_ready context. Rather
than cloning the packet once for each subpacket and pulling/trimming
it, we file the packet multiple times with an annotation for each
indicating which subpacket is there. From that we can directly
calculate the offset and length.
(4) A call's receive queue can be accessed without taking locks (memory
barriers do have to be used, though).
(5) Incoming calls are set up from preallocated resources and immediately
made live. They can than have packets queued upon them and ACKs
generated. If insufficient resources exist, DATA packet #1 is given a
BUSY reply and other DATA packets are discarded).
(6) sk_buffs no longer take a ref on their parent call.
To make this work, the following changes are made:
(1) Each call's receive buffer is now a circular buffer of sk_buff
pointers (rxtx_buffer) rather than a number of sk_buff_heads spread
between the call and the socket. This permits each sk_buff to be in
the buffer multiple times. The receive buffer is reused for the
transmit buffer.
(2) A circular buffer of annotations (rxtx_annotations) is kept parallel
to the data buffer. Transmission phase annotations indicate whether a
buffered packet has been ACK'd or not and whether it needs
retransmission.
Receive phase annotations indicate whether a slot holds a whole packet
or a jumbo subpacket and, if the latter, which subpacket. They also
note whether the packet has been decrypted in place.
(3) DATA packet window tracking is much simplified. Each phase has just
two numbers representing the window (rx_hard_ack/rx_top and
tx_hard_ack/tx_top).
The hard_ack number is the sequence number before base of the window,
representing the last packet the other side says it has consumed.
hard_ack starts from 0 and the first packet is sequence number 1.
The top number is the sequence number of the highest-numbered packet
residing in the buffer. Packets between hard_ack+1 and top are
soft-ACK'd to indicate they've been received, but not yet consumed.
Four macros, before(), before_eq(), after() and after_eq() are added
to compare sequence numbers within the window. This allows for the
top of the window to wrap when the hard-ack sequence number gets close
to the limit.
Two flags, RXRPC_CALL_RX_LAST and RXRPC_CALL_TX_LAST, are added also
to indicate when rx_top and tx_top point at the packets with the
LAST_PACKET bit set, indicating the end of the phase.
(4) Calls are queued on the socket 'receive queue' rather than packets.
This means that we don't need have to invent dummy packets to queue to
indicate abnormal/terminal states and we don't have to keep metadata
packets (such as ABORTs) around
(5) The offset and length of a (sub)packet's content are now passed to
the verify_packet security op. This is currently expected to decrypt
the packet in place and validate it.
However, there's now nowhere to store the revised offset and length of
the actual data within the decrypted blob (there may be a header and
padding to skip) because an sk_buff may represent multiple packets, so
a locate_data security op is added to retrieve these details from the
sk_buff content when needed.
(6) recvmsg() now has to handle jumbo subpackets, where each subpacket is
individually secured and needs to be individually decrypted. The code
to do this is broken out into rxrpc_recvmsg_data() and shared with the
kernel API. It now iterates over the call's receive buffer rather
than walking the socket receive queue.
Additional changes:
(1) The timers are condensed to a single timer that is set for the soonest
of three timeouts (delayed ACK generation, DATA retransmission and
call lifespan).
(2) Transmission of ACK and ABORT packets is effected immediately from
process-context socket ops/kernel API calls that cause them instead of
them being punted off to a background work item. The data_ready
handler still has to defer to the background, though.
(3) A shutdown op is added to the AF_RXRPC socket so that the AFS
filesystem can shut down the socket and flush its own work items
before closing the socket to deal with any in-progress service calls.
Future additional changes that will need to be considered:
(1) Make sure that a call doesn't hog the front of the queue by receiving
data from the network as fast as userspace is consuming it to the
exclusion of other calls.
(2) Transmit delayed ACKs from within recvmsg() when we've consumed
sufficiently more packets to avoid the background work item needing to
run.
Signed-off-by: David Howells <dhowells@redhat.com>
rxrpc calls shouldn't hold refs on the sock struct. This was done so that
the socket wouldn't go away whilst the call was in progress, such that the
call could reach the socket's queues.
However, we can mark the socket as requiring an RCU release and rely on the
RCU read lock.
To make this work, we do:
(1) rxrpc_release_call() removes the call's call user ID. This is now
only called from socket operations and not from the call processor:
rxrpc_accept_call() / rxrpc_kernel_accept_call()
rxrpc_reject_call() / rxrpc_kernel_reject_call()
rxrpc_kernel_end_call()
rxrpc_release_calls_on_socket()
rxrpc_recvmsg()
Though it is also called in the cleanup path of
rxrpc_accept_incoming_call() before we assign a user ID.
(2) Pass the socket pointer into rxrpc_release_call() rather than getting
it from the call so that we can get rid of uninitialised calls.
(3) Fix call processor queueing to pass a ref to the work queue and to
release that ref at the end of the processor function (or to pass it
back to the work queue if we have to requeue).
(4) Skip out of the call processor function asap if the call is complete
and don't requeue it if the call is complete.
(5) Clean up the call immediately that the refcount reaches 0 rather than
trying to defer it. Actual deallocation is deferred to RCU, however.
(6) Don't hold socket refs for allocated calls.
(7) Use the RCU read lock when queueing a message on a socket and treat
the call's socket pointer according to RCU rules and check it for
NULL.
We also need to use the RCU read lock when viewing a call through
procfs.
(8) Transmit the final ACK/ABORT to a client call in rxrpc_release_call()
if this hasn't been done yet so that we can then disconnect the call.
Once the call is disconnected, it won't have any access to the
connection struct and the UDP socket for the call work processor to be
able to send the ACK. Terminal retransmission will be handled by the
connection processor.
(9) Release all calls immediately on the closing of a socket rather than
trying to defer this. Incomplete calls will be aborted.
The call refcount model is much simplified. Refs are held on the call by:
(1) A socket's user ID tree.
(2) A socket's incoming call secureq and acceptq.
(3) A kernel service that has a call in progress.
(4) A queued call work processor. We have to take care to put any call
that we failed to queue.
(5) sk_buffs on a socket's receive queue. A future patch will get rid of
this.
Whilst we're at it, we can do:
(1) Get rid of the RXRPC_CALL_EV_RELEASE event. Release is now done
entirely from the socket routines and never from the call's processor.
(2) Get rid of the RXRPC_CALL_DEAD state. Calls now end in the
RXRPC_CALL_COMPLETE state.
(3) Get rid of the rxrpc_call::destroyer work item. Calls are now torn
down when their refcount reaches 0 and then handed over to RCU for
final cleanup.
(4) Get rid of the rxrpc_call::deadspan timer. Calls are cleaned up
immediately they're finished with and don't hang around.
Post-completion retransmission is handled by the connection processor
once the call is disconnected.
(5) Get rid of the dead call expiry setting as there's no longer a timer
to set.
(6) rxrpc_destroy_all_calls() can just check that the call list is empty.
Signed-off-by: David Howells <dhowells@redhat.com>
Improve the call tracking tracepoint by showing more differentiation
between some of the put and get events, including:
(1) Getting and putting refs for the socket call user ID tree.
(2) Getting and putting refs for queueing and failing to queue the call
processor work item.
Note that these aren't necessarily used in this patch, but will be taken
advantage of in future patches.
An enum is added for the event subtype numbers rather than coding them
directly as decimal numbers and a table of 3-letter strings is provided
rather than a sequence of ?: operators.
Signed-off-by: David Howells <dhowells@redhat.com>
Don't expose skbs to in-kernel users, such as the AFS filesystem, but
instead provide a notification hook the indicates that a call needs
attention and another that indicates that there's a new call to be
collected.
This makes the following possibilities more achievable:
(1) Call refcounting can be made simpler if skbs don't hold refs to calls.
(2) skbs referring to non-data events will be able to be freed much sooner
rather than being queued for AFS to pick up as rxrpc_kernel_recv_data
will be able to consult the call state.
(3) We can shortcut the receive phase when a call is remotely aborted
because we don't have to go through all the packets to get to the one
cancelling the operation.
(4) It makes it easier to do encryption/decryption directly between AFS's
buffers and sk_buffs.
(5) Encryption/decryption can more easily be done in the AFS's thread
contexts - usually that of the userspace process that issued a syscall
- rather than in one of rxrpc's background threads on a workqueue.
(6) AFS will be able to wait synchronously on a call inside AF_RXRPC.
To make this work, the following interface function has been added:
int rxrpc_kernel_recv_data(
struct socket *sock, struct rxrpc_call *call,
void *buffer, size_t bufsize, size_t *_offset,
bool want_more, u32 *_abort_code);
This is the recvmsg equivalent. It allows the caller to find out about the
state of a specific call and to transfer received data into a buffer
piecemeal.
afs_extract_data() and rxrpc_kernel_recv_data() now do all the extraction
logic between them. They don't wait synchronously yet because the socket
lock needs to be dealt with.
Five interface functions have been removed:
rxrpc_kernel_is_data_last()
rxrpc_kernel_get_abort_code()
rxrpc_kernel_get_error_number()
rxrpc_kernel_free_skb()
rxrpc_kernel_data_consumed()
As a temporary hack, sk_buffs going to an in-kernel call are queued on the
rxrpc_call struct (->knlrecv_queue) rather than being handed over to the
in-kernel user. To process the queue internally, a temporary function,
temp_deliver_data() has been added. This will be replaced with common code
between the rxrpc_recvmsg() path and the kernel_rxrpc_recv_data() path in a
future patch.
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Condense the terminal states of a call state machine to a single state,
plus a separate completion type value. The value is then set, along with
error and abort code values, only when the call is transitioned to the
completion state.
Helpers are provided to simplify this.
Signed-off-by: David Howells <dhowells@redhat.com>
Inside the kafs filesystem it is possible to occasionally have a call
processed and terminated before we've had a chance to check whether we need
to clean up the rx queue for that call because afs_send_simple_reply() ends
the call when it is done, but this is done in a workqueue item that might
happen to run to completion before afs_deliver_to_call() completes.
Further, it is possible for rxrpc_kernel_send_data() to be called to send a
reply before the last request-phase data skb is released. The rxrpc skb
destructor is where the ACK processing is done and the call state is
advanced upon release of the last skb. ACK generation is also deferred to
a work item because it's possible that the skb destructor is not called in
a context where kernel_sendmsg() can be invoked.
To this end, the following changes are made:
(1) kernel_rxrpc_data_consumed() is added. This should be called whenever
an skb is emptied so as to crank the ACK and call states. This does
not release the skb, however. kernel_rxrpc_free_skb() must now be
called to achieve that. These together replace
rxrpc_kernel_data_delivered().
(2) kernel_rxrpc_data_consumed() is wrapped by afs_data_consumed().
This makes afs_deliver_to_call() easier to work as the skb can simply
be discarded unconditionally here without trying to work out what the
return value of the ->deliver() function means.
The ->deliver() functions can, via afs_data_complete(),
afs_transfer_reply() and afs_extract_data() mark that an skb has been
consumed (thereby cranking the state) without the need to
conditionally free the skb to make sure the state is correct on an
incoming call for when the call processor tries to send the reply.
(3) rxrpc_recvmsg() now has to call kernel_rxrpc_data_consumed() when it
has finished with a packet and MSG_PEEK isn't set.
(4) rxrpc_packet_destructor() no longer calls rxrpc_hard_ACK_data().
Because of this, we no longer need to clear the destructor and put the
call before we free the skb in cases where we don't want the ACK/call
state to be cranked.
(5) The ->deliver() call-type callbacks are made to return -EAGAIN rather
than 0 if they expect more data (afs_extract_data() returns -EAGAIN to
the delivery function already), and the caller is now responsible for
producing an abort if that was the last packet.
(6) There are many bits of unmarshalling code where:
ret = afs_extract_data(call, skb, last, ...);
switch (ret) {
case 0: break;
case -EAGAIN: return 0;
default: return ret;
}
is to be found. As -EAGAIN can now be passed back to the caller, we
now just return if ret < 0:
ret = afs_extract_data(call, skb, last, ...);
if (ret < 0)
return ret;
(7) Checks for trailing data and empty final data packets has been
consolidated as afs_data_complete(). So:
if (skb->len > 0)
return -EBADMSG;
if (!last)
return 0;
becomes:
ret = afs_data_complete(call, skb, last);
if (ret < 0)
return ret;
(8) afs_transfer_reply() now checks the amount of data it has against the
amount of data desired and the amount of data in the skb and returns
an error to induce an abort if we don't get exactly what we want.
Without these changes, the following oops can occasionally be observed,
particularly if some printks are inserted into the delivery path:
general protection fault: 0000 [#1] SMP
Modules linked in: kafs(E) af_rxrpc(E) [last unloaded: af_rxrpc]
CPU: 0 PID: 1305 Comm: kworker/u8:3 Tainted: G E 4.7.0-fsdevel+ #1303
Hardware name: ASUS All Series/H97-PLUS, BIOS 2306 10/09/2014
Workqueue: kafsd afs_async_workfn [kafs]
task: ffff88040be041c0 ti: ffff88040c070000 task.ti: ffff88040c070000
RIP: 0010:[<ffffffff8108fd3c>] [<ffffffff8108fd3c>] __lock_acquire+0xcf/0x15a1
RSP: 0018:ffff88040c073bc0 EFLAGS: 00010002
RAX: 6b6b6b6b6b6b6b6b RBX: 0000000000000000 RCX: ffff88040d29a710
RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88040d29a710
RBP: ffff88040c073c70 R08: 0000000000000001 R09: 0000000000000001
R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: ffff88040be041c0 R15: ffffffff814c928f
FS: 0000000000000000(0000) GS:ffff88041fa00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fa4595f4750 CR3: 0000000001c14000 CR4: 00000000001406f0
Stack:
0000000000000006 000000000be04930 0000000000000000 ffff880400000000
ffff880400000000 ffffffff8108f847 ffff88040be041c0 ffffffff81050446
ffff8803fc08a920 ffff8803fc08a958 ffff88040be041c0 ffff88040c073c38
Call Trace:
[<ffffffff8108f847>] ? mark_held_locks+0x5e/0x74
[<ffffffff81050446>] ? __local_bh_enable_ip+0x9b/0xa1
[<ffffffff8108f9ca>] ? trace_hardirqs_on_caller+0x16d/0x189
[<ffffffff810915f4>] lock_acquire+0x122/0x1b6
[<ffffffff810915f4>] ? lock_acquire+0x122/0x1b6
[<ffffffff814c928f>] ? skb_dequeue+0x18/0x61
[<ffffffff81609dbf>] _raw_spin_lock_irqsave+0x35/0x49
[<ffffffff814c928f>] ? skb_dequeue+0x18/0x61
[<ffffffff814c928f>] skb_dequeue+0x18/0x61
[<ffffffffa009aa92>] afs_deliver_to_call+0x344/0x39d [kafs]
[<ffffffffa009ab37>] afs_process_async_call+0x4c/0xd5 [kafs]
[<ffffffffa0099e9c>] afs_async_workfn+0xe/0x10 [kafs]
[<ffffffff81063a3a>] process_one_work+0x29d/0x57c
[<ffffffff81064ac2>] worker_thread+0x24a/0x385
[<ffffffff81064878>] ? rescuer_thread+0x2d0/0x2d0
[<ffffffff810696f5>] kthread+0xf3/0xfb
[<ffffffff8160a6ff>] ret_from_fork+0x1f/0x40
[<ffffffff81069602>] ? kthread_create_on_node+0x1cf/0x1cf
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Replace accesses of conn->trans->{local,peer} with
conn->params.{local,peer} thus making it easier for a future commit to
remove the rxrpc_transport struct.
This also reduces the number of memory accesses involved.
Signed-off-by: David Howells <dhowells@redhat.com>
Define and use a structure to hold connection parameters. This makes it
easier to pass multiple connection parameters around.
Define and use a structure to hold protocol information used to hash a
connection for lookup on incoming packet. Most of these fields will be
disposed of eventually, including the duplicate local pointer.
Whilst we're at it rename "proto" to "family" when referring to a protocol
family.
Signed-off-by: David Howells <dhowells@redhat.com>
Rename files matching net/rxrpc/ar-*.c to get rid of the "ar-" prefix.
This will aid splitting those files by making easier to come up with new
names.
Note that the not all files are simply renamed from ar-X.c to X.c. The
following exceptions are made:
(*) ar-call.c -> call_object.c
ar-ack.c -> call_event.c
call_object.c is going to contain the core of the call object
handling. Call event handling is all going to be in call_event.c.
(*) ar-accept.c -> call_accept.c
Incoming call handling is going to be here.
(*) ar-connection.c -> conn_object.c
ar-connevent.c -> conn_event.c
The former file is going to have the basic connection object handling,
but there will likely be some differentiation between client
connections and service connections in additional files later. The
latter file will have all the connection-level event handling.
(*) ar-local.c -> local_object.c
This will have the local endpoint object handling code. The local
endpoint event handling code will later be split out into
local_event.c.
(*) ar-peer.c -> peer_object.c
This will have the peer endpoint object handling code. Peer event
handling code will be placed in peer_event.c (for the moment, there is
none).
(*) ar-error.c -> peer_event.c
This will become the peer event handling code, though for the moment
it's actually driven from the local endpoint's perspective.
Note that I haven't renamed ar-transport.c to transport_object.c as the
intention is to delete it when the rxrpc_transport struct is excised.
The only file that actually has its contents changed is net/rxrpc/Makefile.
net/rxrpc/ar-internal.h will need its section marker comments updating, but
I'll do that in a separate patch to make it easier for git to follow the
history across the rename. I may also want to rename ar-internal.h at some
point - but that would mean updating all the #includes and I'd rather do
that in a separate step.
Signed-off-by: David Howells <dhowells@redhat.com.
Eric Dumazet