Currently, tls_device_down synchronizes with tls_device_resync_rx using
RCU, however, the pointer to netdev is stored using WRITE_ONCE and
loaded using READ_ONCE.
Although such approach is technically correct (rcu_dereference is
essentially a READ_ONCE, and rcu_assign_pointer uses WRITE_ONCE to store
NULL), using special RCU helpers for pointers is more valid, as it
includes additional checks and might change the implementation
transparently to the callers.
Mark the netdev pointer as __rcu and use the correct RCU helpers to
access it. For non-concurrent access pass the right conditions that
guarantee safe access (locks taken, refcount value). Also use the
correct helper in mlx5e, where even READ_ONCE was missing.
The transition to RCU exposes existing issues, fixed by this commit:
1. bond_tls_device_xmit could read netdev twice, and it could become
NULL the second time, after the NULL check passed.
2. Drivers shouldn't stop processing the last packet if tls_device_down
just set netdev to NULL, before tls_dev_del was called. This prevents a
possible packet drop when transitioning to the fallback software mode.
Fixes: 89df6a8104 ("net/bonding: Implement TLS TX device offload")
Fixes: c55dcdd435 ("net/tls: Fix use-after-free after the TLS device goes down and up")
Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Link: https://lore.kernel.org/r/20220810081602.1435800-1-maximmi@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Another device offload bug, we use the length of the output
skb as an indication of how much data to copy. But that skb
is sized to offset + record length, and we start from offset.
So we end up double-counting the offset which leads to
skb_copy_bits() returning -EFAULT.
Reported-by: Tariq Toukan <tariqt@nvidia.com>
Fixes: 84c61fe1a7 ("tls: rx: do not use the standard strparser")
Tested-by: Ran Rozenstein <ranro@nvidia.com>
Link: https://lore.kernel.org/r/20220809175544.354343-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
We can't do skb_walk_frags() on the input skbs, because
the input skbs is really just a pointer to the tcp read
queue. We need to bound the "is decrypted" check by the
amount of data in the message.
Note that the walk in tls_device_reencrypt() is after a
CoW so the skb there is safe to walk. Actually in the
current implementation it can't have frags at all, but
whatever, maybe one day it will.
Reported-by: Tariq Toukan <tariqt@nvidia.com>
Fixes: 84c61fe1a7 ("tls: rx: do not use the standard strparser")
Tested-by: Ran Rozenstein <ranro@nvidia.com>
Link: https://lore.kernel.org/r/20220809175544.354343-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
destroy_workqueue() safely destroys the workqueue after draining it.
No need for the explicit call to flush_workqueue(). Remove it.
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/20220801112444.26175-1-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Multiple TLS device-offloaded contexts can be added in parallel via
concurrent calls to .tls_dev_add, while calls to .tls_dev_del are
sequential in tls_device_gc_task.
This is not a sustainable behavior. This creates a rate gap between add
and del operations (addition rate outperforms the deletion rate). When
running for enough time, the TLS device resources could get exhausted,
failing to offload new connections.
Replace the single-threaded garbage collector work with a per-context
alternative, so they can be handled on several cores in parallel. Use
a new dedicated destruct workqueue for this.
Tested with mlx5 device:
Before: 22141 add/sec, 103 del/sec
After: 11684 add/sec, 11684 del/sec
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
TLS context destructor can be run in atomic context. Cleanup operations
for device-offloaded contexts could require access and interaction with
the device callbacks, which might sleep. Hence, the cleanup of such
contexts must be deferred and completed inside an async work.
For all others, this is not necessary, as cleanup is atomic. Invoke
cleanup immediately for them, avoiding queueing redundant gc work.
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The return from the call to tls_rx_msg_size() is int, it can be
a negative error code, however this is being assigned to an
unsigned long variable 'sz', so making 'sz' an int.
Eliminate the following coccicheck warning:
./net/tls/tls_strp.c:211:6-8: WARNING: Unsigned expression compared with zero: sz < 0
Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Link: https://lore.kernel.org/r/20220728031019.32838-1-yang.lee@linux.alibaba.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
I went too far in the accessor conversion, we can't use tls_strp_msg()
after decryption because the message may not be ready. What we care
about on this path is that the output skb is detached, i.e. we didn't
somehow just turn around and used the input skb with its TCP data
still attached. So look at the anchor directly.
Fixes: 84c61fe1a7 ("tls: rx: do not use the standard strparser")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Paolo points out that there seems to be no strong reason strparser
users a single threaded workqueue. Perhaps there were some performance
or pinning considerations? Since we don't know (and it's the slow path)
let's default to the most natural, multi-threaded choice.
Also rename the workqueue to "tls-".
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Eric indicates that restarting rcvtimeo on every wait may be fine.
I thought that we should consider it cumulative, and made
tls_rx_reader_lock() return the remaining timeo after acquiring
the reader lock.
tls_rx_rec_wait() gets its timeout passed in by value so it
does not keep track of time previously spent.
Make the lock waiting consistent with tls_rx_rec_wait() - don't
keep track of time spent.
Read the timeo fresh in tls_rx_rec_wait().
It's unclear to me why callers are supposed to cache the value.
Link: https://lore.kernel.org/all/CANn89iKcmSfWgvZjzNGbsrndmCch2HC_EPZ7qmGboDNaWoviNQ@mail.gmail.com/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
TLS is a relatively poor fit for strparser. We pause the input
every time a message is received, wait for a read which will
decrypt the message, start the parser, repeat. strparser is
built to delineate the messages, wrap them in individual skbs
and let them float off into the stack or a different socket.
TLS wants the data pages and nothing else. There's no need
for TLS to keep cloning (and occasionally skb_unclone()'ing)
the TCP rx queue.
This patch uses a pre-allocated skb and attaches the skbs
from the TCP rx queue to it as frags. TLS is careful never
to modify the input skb without CoW'ing / detaching it first.
Since we call TCP rx queue cleanup directly we also get back
the benefit of skb deferred free.
Overall this results in a 6% gain in my benchmarks.
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Wrap the remaining skb_cow_data() into a helper, so it's easier
to replace down the lane. The new version will change the skb
so make sure relevant pointers get reloaded after the call.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The non-zero-copy path assumes a full skb with decrypted contents.
This means the device offload would have to CoW the data. Try
to keep the zero-copy status instead, copy the data to user space.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In the future we'll want to reuse the input skb in case of
zero-copy so we shouldn't always free darg.skb. Move the
freeing of darg.skb into the non-zc cases. All cases will
now free ctx->recv_pkt (inside let tls_rx_rec_done()).
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
After recent changes the SW side of tls_rx_one_record() can
be nicely encapsulated in its own function. Move the pad handling
as well. This will be useful for ->zc handling in tls_decrypt_device().
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
To allow for the logic to change later wrap accesses
which interrogate the input skb in helper functions.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
tls_device_down takes a reference on all contexts it's going to move to
the degraded state (software fallback). If sk_destruct runs afterwards,
it can reduce the reference counter back to 1 and return early without
destroying the context. Then tls_device_down will release the reference
it took and call tls_device_free_ctx. However, the context will still
stay in tls_device_down_list forever. The list will contain an item,
memory for which is released, making a memory corruption possible.
Fix the above bug by properly removing the context from all lists before
any call to tls_device_free_ctx.
Fixes: 3740651bf7 ("tls: Fix context leak on tls_device_down")
Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric reports we should release the socket lock if the entire
"grab reader lock" operation has failed. The callers assume
they don't have to release it or otherwise unwind.
Reported-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot+16e72110feb2b653ef27@syzkaller.appspotmail.com
Fixes: 4cbc325ed6 ("tls: rx: allow only one reader at a time")
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20220720203701.2179034-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Socket destruction flow and tls_device_down function sync against each
other using tls_device_lock and the context refcount, to guarantee the
device resources are freed via tls_dev_del() by the end of
tls_device_down.
In the following unfortunate flow, this won't happen:
- refcount is decreased to zero in tls_device_sk_destruct.
- tls_device_down starts, skips the context as refcount is zero, going
all the way until it flushes the gc work, and returns without freeing
the device resources.
- only then, tls_device_queue_ctx_destruction is called, queues the gc
work and frees the context's device resources.
Solve it by decreasing the refcount in the socket's destruction flow
under the tls_device_lock, for perfect synchronization. This does not
slow down the common likely destructor flow, in which both the refcount
is decreased and the spinlock is acquired, anyway.
Fixes: e8f6979981 ("net/tls: Add generic NIC offload infrastructure")
Reviewed-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
We currently CoW Rx skbs whenever we can't decrypt to a user
space buffer. The skbs can be enormous (64kB) and CoW does
a linear alloc which has a strong chance of failing under
memory pressure. Or even without, skb_cow_data() assumes
GFP_ATOMIC.
Allocate a new frag'd skb and decrypt into it. We finally
take advantage of the decrypted skb getting returned via
darg.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The "zero-copy" path in SW TLS will engage either for no skbs or
for all but last. If the recvmsg parameters are right and the
socket can do ZC we'll ZC until the iterator can't fit a full
record at which point we'll decrypt one more record and copy
over the necessary bits to fill up the request.
The only reason we hold onto the ZC skbs which went thru the async
path until the end of recvmsg() is to count bytes. We need an accurate
count of zc'ed bytes so that we can calculate how much of the non-zc'd
data to copy. To allow freeing input skbs on the ZC path count only
how much of the list we'll need to consume.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Async crypto currently benefits from the fact that we decrypt
in place. When we allow input and output to be different skbs
we will have to hang onto the input while we move to the next
record. Clone the inputs and keep them on a list.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Async crypto TLS Rx currently waits for crypto to be done
in order to strip the TLS header and tailer. Simplify
the code by moving the pointers immediately, since only
TLS 1.2 is supported here there is no message padding.
This simplifies the decryption into a new skb in the next
patch as we don't have to worry about input vs output
skb in the decrypt_done() handler any more.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of using ctx->recv_pkt after decryption read the skb
from darg.skb. This moves the decision of what the "output skb"
is to the decrypt handlers. For now after decrypt handler returns
successfully ctx->recv_pkt is simply moved to darg.skb, but it
will change soon.
Note that tls_decrypt_sg() cannot clear the ctx->recv_pkt
because it gets called to re-encrypt (i.e. by the device offload).
So we need an awkward temporary if() in tls_rx_one_record().
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Callers always pass ctx->recv_pkt into decrypt_skb_update(),
and it propagates it to its callees. This may give someone
the false impression that those functions can accept any valid
skb containing a TLS record. That's not the case, the record
sequence number is read from the context, and they can only
take the next record coming out of the strp.
Let the functions get the skb from the context instead of
passing it in. This will also make it cleaner to return
a different skb than ctx->recv_pkt as the decrypted one
later on.
Since we're touching the definition of decrypt_skb_update()
use this as an opportunity to rename it.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
I already forgot to transform darg from input to output
semantics once on the NIC inline crypto fastpath. To
avoid this happening again create a device equivalent
of decrypt_internal(). A function responsible for decryption
and transforming darg.
While at it rename decrypt_internal() to a hopefully slightly
more meaningful name.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
We no longer allow a decrypted skb to remain linked to ctx->recv_pkt.
Anything on the list is decrypted, anything on ctx->recv_pkt needs
to be decrypted.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Detach the skb from ctx->recv_pkt after decryption is done,
even if we can't consume it.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
I thought that having the skb either always on the ctx->rx_list
or ctx->recv_pkt will simplify the handling, as we would not
have to remember to flip it from one to the other on exit paths.
This became a little harder to justify with the fix for BPF
sockmaps. Subsequent changes will make the situation even worse.
Queue the skbs only when really needed.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
recvmsg() in TLS gets data from the skb list (rx_list) or fresh
skbs we read from TCP via strparser. The former holds skbs which were
already decrypted for peek or decrypted and partially consumed.
tls_wait_data() only notices appearance of fresh skbs coming out
of TCP (or psock). It is possible, if there is a concurrent call
to peek() and recv() that the peek() will move the data from input
to rx_list without recv() noticing. recv() will then read data out
of order or never wake up.
This is not a practical use case/concern, but it makes the self
tests less reliable. This patch solves the problem by allowing
only one reader in.
Because having multiple processes calling read()/peek() is not
normal avoid adding a lock and try to fast-path the single reader
case.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
As discussed with Maxim add a counter for true NoPad violations.
This should help deployments catch unexpected padded records vs
just control records which always need re-encryption.
https: //lore.kernel.org/all/b111828e6ac34baad9f4e783127eba8344ac252d.camel@nvidia.com/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
tls_wait_data() sets the return code as an output parameter
and always returns ctx->recv_pkt on success.
Return the error code directly and let the caller read the skb
from the context. Use positive return code to indicate ctx->recv_pkt
is ready.
While touching the definition of the function rename it.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
include/net/tls.h is getting a little long, and is probably hard
for driver authors to navigate. Split out the internals into a
header which will live under net/tls/. While at it move some
static inlines with a single user into the source files, add
a few tls_ prefixes and fix spelling of 'proccess'.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The max size of iv + aad + tail is 22B. That's smaller
than a single sg entry (32B). Don't bother with the
memory packing, just create a struct which holds the
max size of those members.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
AAD size is either 5 or 13. Really no point complicating
the code for the 8B of difference. This will also let us
turn the chunked up buffer into a sane struct.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This reverts commit 284b4d93da.
When using TLS device offload and coming from tls_device_reencrypt()
flow, -EBADMSG error in tls_do_decryption() should not be counted
towards the TLSTlsDecryptError counter.
Move the counter increase back to the decrypt_internal() call site in
decrypt_skb_update().
This also fixes an issue where:
if (n_sgin < 1)
return -EBADMSG;
Errors in decrypt_internal() were not counted after the cited patch.
Fixes: 284b4d93da ("tls: rx: move counting TlsDecryptErrors for sync")
Cc: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
We continuously hold the socket lock during large reads and writes.
This may inflate RTT and negatively impact TCP performance.
Flush the backlog periodically. I tried to pick a flush period (128kB)
which gives significant benefit but the max Bps rate is not yet visibly
impacted.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since optimisitic decrypt may add extra load in case of retries
require socket owner to explicitly opt-in.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
We currently don't support decrypt to user buffer with TLS 1.3
because we don't know the record type and how much padding
record contains before decryption. In practice data records
are by far most common and padding gets used rarely so
we can assume data record, no padding, and if we find out
that wasn't the case - retry the crypto in place (decrypt
to skb).
To safeguard from user overwriting content type and padding
before we can check it attach a 1B sg entry where last byte
of the record will land.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
To make future patches easier to review make data_len
contain the length of the data, without the tail.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Most drivers use "skb_transport_offset(skb) + tcp_hdrlen(skb)"
to compute headers length for a TCP packet, but others
use more convoluted (but equivalent) ways.
Add skb_tcp_all_headers() and skb_inner_tcp_all_headers()
helpers to harmonize this a bit.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 8a59f9d1e3 ("sock: Introduce sk->sk_prot->psock_update_sk_prot()")
has moved the inet_csk_has_ulp(sk) check from sk_psock_init() to
the new tcp_bpf_update_proto() function. I'm guessing that this
was done to allow creating psocks for non-inet sockets.
Unfortunately the destruction path for psock includes the ULP
unwind, so we need to fail the sk_psock_init() itself.
Otherwise if ULP is already present we'll notice that later,
and call tcp_update_ulp() with the sk_proto of the ULP
itself, which will most likely result in the ULP looping
its callbacks.
Fixes: 8a59f9d1e3 ("sock: Introduce sk->sk_prot->psock_update_sk_prot()")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: John Fastabend <john.fastabend@gmail.com>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Tested-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/r/20220620191353.1184629-2-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
