| Commit message (Collapse) | Author | Age | Files | Lines |
| |
|
|
|
|
|
|
|
|
|
|
| |
Formerly, the request that was about to be received was looked up in
the receive queue without removing it, then the request payload was
received from the socket while the lock was not being held, and finally,
the lock was required again and the request removed from the queue.
This is dangrous as another thread can concurrently take the request
from the queue while the receive thread reads the payload from the
socket, leading to a double-free by calling blk_mq_end_request twice.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This change links the dnbd3-server with 'libatomic' to add support for
atomic operations not supported by hardware (especially 32-bit hardware
architectures, such as ARM). Thus the dnbd3-server can also run on a
Raspberry Pi 1 running Rasperry Pi OS.
Note that the dnbd3-server is still linked to the libatomic, even if the
hardware supports atomic operations. In this case, the compiler resolves
atomic operations and replaces them automatically with specific built-in
functions. This unnecessary linkage can be removed in the future if the
GCC supports an upcoming option called automatic linking of libatomic
(--enable-autolink-libatomic).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Previously disconnect was protected against concurrent calls, but connect
wasn't. It was easy to crash the kernel when calling connect and
disconnect IOCTLs in a tight loop concurrently.
A global lock was introduced to make sure only one caller can change the
connection state at a time. dev->connection_lock needs to be aquired
when calling dnbd3_net_connect or _disconnect.
This atomic_t based locking mechanism should be turned into a mutex in a
next step, relying on mutex_trylock for cases where we don't have the
cmpxchg-schedule() loop.
Along the way it was noticed that the send/receive timeouts don't apply
to kernel_connect, which might have been the case in older 3.x kernel
versions. A crude workaround using nonblocking connect has been
introduced to emulate this, but a clean solution for this is welcomed.
Also, devices are now properly closed on module unload.
|
|
|
|
|
|
|
| |
This patch replaces the __VA_OPT__ varadic macro for the C preprocessor
with a builtin GCC extension for optional varadic arguments. Based on
this change, the dnbd3 Linux kernel module can be also built with GCC
7.5 on a fresh Ubuntu 18.04 with Linux kernel version 4.19.x.
|
| |
|
| |
|
|
|
|
|
|
|
| |
With this change, the dnbd3-client is able to display the selected
server (choosen by the Linux kernel module) after successful probing.
Therefore, the ioctl call OPEN returns the selected server host as
index of the specified dnbd3-server hosts after successful probing.
|
|
|
|
|
|
| |
This patch adds the feature to manually switch the dnbd3-server to a
specified server. The switching is implemented by the use of the ioctl
call SWITCH.
|
|
|
|
|
|
|
|
|
|
| |
This patch completes the changes from the last commit [1] and protects
in addition the read-only access to the alternative list of new servers.
Otherwise a race condition between ioctl ADD_SRV/REM_SRV (process
context) and dnbd3 discover thread would be possible since the
'new_servers_num' field is changed in both contexts.
[1] - DNBD3 commit db5a93a43fea2aa3c3bbaf8c48d238e60d834676
|
|
|
|
|
|
| |
This patch locks the protecting spinlock of the DNBD3 device's new
server list. Otherwise a race condition between ioctl ADD_SRV/REM_SRV
(process context) and dnbd3 discover thread would be possible.
|
|
|
|
|
|
|
| |
This patch changes the probing logic to select the first available
dnbd3-server submitted by the ioctl OPEN call. All other specified
dnbd3-servers are added to the alternative server list and do not have
to be available.
|
|
|
|
|
|
|
|
|
|
| |
The ioctl OPEN call for DNBD3 devices exposed by the dnbd3 Linux kernel
module, is extended with a fixed array of dnbd3 hosts. The fixed array
allows the dnbd3-client to submit host information (IP address and port)
of multiple dnbd3-servers. This information is used to probe all
submitted dnbd3-servers and add them to the alternative dnbd3-server
list. If at least one dnbd3-server is not reachable, the OPEN ioctl call
will abort with an error code.
|
| |
|
| |
|
| |
|
| |
|
| |
|
|
|
|
|
|
|
|
|
| |
saveLoadAllCacheMaps() is called frequently, and a 'full' run can take
some time. If we only update the nextSave timestamp when we're done, we
might already have a concurrent call to the function, which will also do
a 'full' run, since the timestamp is not updated yet. This doesn't break
anything, but leads to even more disk activity, which is probably
already high, given that the previous run is not done yet.
|
|
|
|
|
| |
This patch sets the programming languages of each CMake project to C. With
this change, CMake does not search for an unused C++ compiler anymore.
|
| |
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
This patch adds the following CMake targets
- package
- source
to build bundeled packages. Those packages contain either all built
binary artifacts or all source files for source code distribution. Both
CMake targets are available in Release build configuration.
|
|
|
|
|
| |
The afl-fuzz support for the dnbd3-server requires an AFL C compiler
like afl-gcc and can be enabled with the CMake option DNBD3_SERVER_AFL.
|
| |
|
| |
|
|
|
|
|
|
|
|
|
|
| |
This change restructures the source code directories, separates shared
form non-shared application code and adds CMake dependencies. These
dependencies allow the tracking of changes and trigger a rebuild of
those build targets where changed files are involved.
WARNING: Note that the support of the DNBD3_SERVER_AFL build option is
not supported yet. Thus, the option should be never turned on.
|
|
|
|
|
|
|
|
|
| |
This patch implements the old time structures to support Linux kernels
prior to version 5.1.x.
WARNING: This change to the deprecated time structures does not solve
the Y2038 issue. Thus, the dnbd3 Linux kernel module can only run under
Linux kernels prior to version 5.1.x until the end of year 2037.
|
|
|
|
|
|
|
|
|
|
| |
This patch replaces the deprecated kernel_setsockopt() function with the
socket generic function sock_setsockopt() to set the send and receive
timeout for all used sockets in the kernel module. The timeout data type
is choosen according to the available kernel version, so that the dnbd3
kernel module supports the new y2038-problem-solving socket options.
With both changes, the kernel module runs on Linux kernel 5.4 LTS and
later (including Linux kernel 5.9).
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
This change converts all debug messages to support the Linux kernel's
dynamic debug feature. Debug messages can be enabled or disabled by
the debug feature if the
- kernel module is built in debug mode (EXTRA_CFLAGS=-g -DDEBUG)
- Linux kernel supports dynamic debug (CONFIG_DYNAMIC_DEBUG is set)
This patch removes outdated kernel compatibility macros (used for Linux
kernels in version 4.x) and cleans up the kernel module's code.
|
|
|
|
|
|
|
|
|
|
|
| |
This converts the dnbd3 kernel module driver to use the blk-mq
infrastructure, which allows the dnbd3 kernel module driver to be
compatible with Linux kernels in version 5.x or later. The conversion of
the implementation uses one hardware queue to preserve the existing
send/receive and load-balancing logic, but can be scaled up in the
future. In addition to that, time measurements in the implementation are
converted to ktime based accessors to replace the use of deprecated time
interfaces.
|
|
|
|
|
| |
There was a logic bug that would favor a remotely looked up image rid,
even if we already found a higher revision locally.
|
| |
|
|
|
|
|
|
| |
Greatly improves performance when reading from the local disk cache, and
additionally avoids having everything in the fs cache twice (disk view
and fuse view).
|
| |
|
| |
|
| |
|
| |
|
| |
|
|
|
|
|
| |
Still needs some cleanup and optimizations, variable naming sucks,
comments, etc.
|
|\ |
|
| |
| |
| |
| | |
Entries in _images array might ne NULL
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|