Skip to content

L
linux
Switch branch/tag
  1. 11 Sep, 2014 5 commits
  3. 09 Sep, 2014 32 commits
  5. 08 Sep, 2014 3 commits
    • Johan Hedberg's avatar
      Bluetooth: Fix dereferencing conn variable before NULL check · c68b7f12
      Johan Hedberg authored 
      This patch fixes the following type of static analyzer warning (and
probably a real bug as well as the NULL check should be there for a
reason):

net/bluetooth/smp.c:1182 smp_conn_security() warn: variable dereferenced before check 'conn' (see line 1174)
Signed-off-by: default avatarJohan Hedberg <johan.hedberg@intel.com>
Signed-off-by: default avatarMarcel Holtmann <marcel@holtmann.org>
      c68b7f12
    • Behan Webster's avatar
      Bluetooth: LLVMLinux: Remove VLAIS from bluetooth/amp.c · 9f06a8d6
      Behan Webster authored 
      Replaced the use of a Variable Length Array In Struct (VLAIS) with a C99
compliant equivalent. This patch allocates the appropriate amount of memory
using an char array.

The new code can be compiled with both gcc and clang.

struct shash_desc contains a flexible array member member ctx declared with
CRYPTO_MINALIGN_ATTR, so sizeof(struct shash_desc) aligns the beginning
of the array declared after struct shash_desc with long long.

No trailing padding is required because it is not a struct type that can
be used in an array.

The CRYPTO_MINALIGN_ATTR is required so that desc is aligned with long long
as would be the case for a struct containing a member with
CRYPTO_MINALIGN_ATTR.
Signed-off-by: default avatarBehan Webster <behanw@converseincode.com>
Signed-off-by: default avatarMark Charlebois <charlebm@gmail.com>
Signed-off-by: default avatarJan-Simon Möller <dl9pf@gmx.de>
Signed-off-by: default avatarMarcel Holtmann <marcel@holtmann.org>
      9f06a8d6
    • Johan Hedberg's avatar
      Bluetooth: Add strict checks for allowed SMP PDUs · b28b4943
      Johan Hedberg authored 
      SMP defines quite clearly when certain PDUs are to be expected/allowed
and when not, but doesn't have any explicit request/response definition.
So far the code has relied on each PDU handler to behave correctly if
receiving PDUs at an unexpected moment, however this requires many
different checks and is prone to errors.

This patch introduces a generic way to keep track of allowed PDUs and
thereby reduces the responsibility & load on individual command
handlers. The tracking is implemented using a simple bit-mask where each
opcode maps to its own bit. If the bit is set the corresponding PDU is
allow and if the bit is not set the PDU is not allowed.

As a simple example, when we send the Pairing Request we'd set the bit
for Pairing Response, and when we receive the Pairing Response we'd
clear the bit for Pairing Response.

Since the disallowed PDU rejection is now done in a single central place
we need to be a bit careful of which action makes most sense to all
cases. Previously some, such as Security Request, have been simply
ignored whereas others have caused an explicit disconnect.

The only PDU rejection action that keeps good interoperability and can
be used for all the applicable use cases is to drop the data. This may
raise some concerns of us now being more lenient for misbehaving (and
potentially malicious) devices, but the policy of simply dropping data
has been a successful one for many years e.g. in L2CAP (where this is
the *only* policy for such cases - we never request disconnection in
l2cap_core.c because of bad data). Furthermore, we cannot prevent
connected devices from creating the SMP context (through a Security or
Pairing Request), and once the context exists looking up the
corresponding bit for the received opcode and deciding to reject it is
essentially an equally lightweight operation as the kind of rejection
that l2cap_core.c already successfully does.
Signed-off-by: default avatarJohan Hedberg <johan.hedberg@intel.com>
Signed-off-by: default avatarMarcel Holtmann <marcel@holtmann.org>
      b28b4943
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7