- Linux-kselftest-mirror - lists.linaro.org

[PATCH bpf-next v4 09/12] selftests: bpf: don't listen() on UDP sockets

by Lorenz Bauer

Most tests for TCP sockmap can be adapted to UDP sockmap if the listen call is skipped. Rename listen_loopback, etc. to socket_loopback and skip listen() for SOCK_DGRAM. Signed-off-by: Lorenz Bauer <lmb(a)cloudflare.com> Reviewed-by: Jakub Sitnicki <jakub(a)cloudflare.com> Acked-by: John Fastabend <john.fastabend(a)gmail.com> --- .../selftests/bpf/prog_tests/sockmap_listen.c | 47 ++++++++++--------- 1 file changed, 25 insertions(+), 22 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index b1b2acea0638..4ba41dd26d6b 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -230,7 +230,7 @@ static int enable_reuseport(int s, int progfd) return 0; } -static int listen_loopback_reuseport(int family, int sotype, int progfd) +static int socket_loopback_reuseport(int family, int sotype, int progfd) { struct sockaddr_storage addr; socklen_t len; @@ -249,6 +249,9 @@ static int listen_loopback_reuseport(int family, int sotype, int progfd) if (err) goto close; + if (sotype == SOCK_DGRAM) + return s; + err = xlisten(s, SOMAXCONN); if (err) goto close; @@ -259,9 +262,9 @@ static int listen_loopback_reuseport(int family, int sotype, int progfd) return -1; } -static int listen_loopback(int family, int sotype) +static int socket_loopback(int family, int sotype) { - return listen_loopback_reuseport(family, sotype, -1); + return socket_loopback_reuseport(family, sotype, -1); } static void test_insert_invalid(int family, int sotype, int mapfd) @@ -333,7 +336,7 @@ static void test_insert_listening(int family, int sotype, int mapfd) u32 key; int s; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -349,7 +352,7 @@ static void test_delete_after_insert(int family, int sotype, int mapfd) u32 key; int s; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -366,7 +369,7 @@ static void test_delete_after_close(int family, int sotype, int mapfd) u64 value; u32 key; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -390,7 +393,7 @@ static void test_lookup_after_insert(int family, int sotype, int mapfd) u32 key; int s; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -417,7 +420,7 @@ static void test_lookup_after_delete(int family, int sotype, int mapfd) u64 value; u32 key; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -439,7 +442,7 @@ static void test_lookup_32_bit_value(int family, int sotype, int mapfd) u32 key, value32; int err, s; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -470,11 +473,11 @@ static void test_update_listening(int family, int sotype, int mapfd) u64 value; u32 key; - s1 = listen_loopback(family, sotype); + s1 = socket_loopback(family, sotype); if (s1 < 0) return; - s2 = listen_loopback(family, sotype); + s2 = socket_loopback(family, sotype); if (s2 < 0) goto close_s1; @@ -500,7 +503,7 @@ static void test_destroy_orphan_child(int family, int sotype, int mapfd) u64 value; u32 key; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -534,7 +537,7 @@ static void test_clone_after_delete(int family, int sotype, int mapfd) u64 value; u32 key; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -570,7 +573,7 @@ static void test_accept_after_delete(int family, int sotype, int mapfd) socklen_t len; u64 value; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s == -1) return; @@ -624,7 +627,7 @@ static void test_accept_before_delete(int family, int sotype, int mapfd) socklen_t len; u64 value; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s == -1) return; @@ -735,7 +738,7 @@ static void test_syn_recv_insert_delete(int family, int sotype, int mapfd) int err, s; u64 value; - s = listen_loopback(family, sotype | SOCK_NONBLOCK); + s = socket_loopback(family, sotype | SOCK_NONBLOCK); if (s < 0) return; @@ -877,7 +880,7 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, zero_verdict_count(verd_mapfd); - s = listen_loopback(family, sotype | SOCK_NONBLOCK); + s = socket_loopback(family, sotype | SOCK_NONBLOCK); if (s < 0) return; @@ -1009,7 +1012,7 @@ static void redir_to_listening(int family, int sotype, int sock_mapfd, zero_verdict_count(verd_mapfd); - s = listen_loopback(family, sotype | SOCK_NONBLOCK); + s = socket_loopback(family, sotype | SOCK_NONBLOCK); if (s < 0) return; @@ -1120,7 +1123,7 @@ static void test_reuseport_select_listening(int family, int sotype, zero_verdict_count(verd_map); - s = listen_loopback_reuseport(family, sotype, reuseport_prog); + s = socket_loopback_reuseport(family, sotype, reuseport_prog); if (s < 0) return; @@ -1174,7 +1177,7 @@ static void test_reuseport_select_connected(int family, int sotype, zero_verdict_count(verd_map); - s = listen_loopback_reuseport(family, sotype, reuseport_prog); + s = socket_loopback_reuseport(family, sotype, reuseport_prog); if (s < 0) return; @@ -1249,11 +1252,11 @@ static void test_reuseport_mixed_groups(int family, int sotype, int sock_map, zero_verdict_count(verd_map); /* Create two listeners, each in its own reuseport group */ - s1 = listen_loopback_reuseport(family, sotype, reuseport_prog); + s1 = socket_loopback_reuseport(family, sotype, reuseport_prog); if (s1 < 0) return; - s2 = listen_loopback_reuseport(family, sotype, reuseport_prog); + s2 = socket_loopback_reuseport(family, sotype, reuseport_prog); if (s2 < 0) goto close_srv1; -- 2.20.1

5 years, 3 months

1
0
0 0

[PATCH 0/3] riscv: add support for restartable sequence

by Vincent Chen

Add RSEQ, restartable sequence, support and related selftest to RISCV. The Kconfig option HAVE_REGS_AND_STACK_ACCESS_API is also required by RSEQ because RSEQ will modify the content of pt_regs.sepc through instruction_pointer_set() during the fixup procedure. In order to select the config HAVE_REGS_AND_STACK_ACCESS_API, the missing APIs for accessing pt_regs are also added in this patch set. The relevant RSEQ tests in kselftest require the Binutils patch "RISC-V: Fix linker problems with TLS copy relocs" to avoid placing PREINIT_ARRAY and TLS variable of librseq.so at the same address. https://sourceware.org/git/gitweb.cgi?p=binutils-gdb.git;a=commit;h=3e7bd7f… A segmental fault will happen if the Binutils misses this patch. Vincent Chen (3): riscv: add required functions to enable HAVE_REGS_AND_STACK_ACCESS_API riscv: Add support for restartable sequence rseq/selftests: Add support for riscv arch/riscv/Kconfig | 2 + arch/riscv/include/asm/ptrace.h | 29 +- arch/riscv/kernel/entry.S | 4 + arch/riscv/kernel/ptrace.c | 99 +++++ arch/riscv/kernel/signal.c | 3 + tools/testing/selftests/rseq/param_test.c | 23 ++ tools/testing/selftests/rseq/rseq-riscv.h | 622 ++++++++++++++++++++++++++++++ tools/testing/selftests/rseq/rseq.h | 2 + 8 files changed, 783 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/rseq/rseq-riscv.h -- 2.7.4

5 years, 3 months

3
8
0 0

kselftest selftest issues and clarifications

by Bird, Tim

> -----Original Message----- > From: Shuah Khan > > On 2/28/20 10:50 AM, Bird, Tim wrote: > > > > > >> -----Original Message----- > >> From: Shuah Khan > >> > >> Integrating Kselftest into Kernel CI rings depends on Kselftest build > >> and install framework to support Kernel CI use-cases. I am kicking off > >> an effort to support Kselftest runs in Kernel CI rings. Running these > >> tests in Kernel CI rings will help quality of kernel releases, both > >> stable and mainline. > >> > >> What is required for full support? > >> > >> 1. Cross-compilation & relocatable build support > >> 2. Generates objects in objdir/kselftest without cluttering main objdir > >> 3. Leave source directory clean > >> 4. Installs correctly in objdir/kselftest/kselftest_install and adds > >> itself to run_kselftest.sh script generated during install. > >> > >> Note that install step is necessary for all files to be installed for > >> run time support. > >> > >> I looked into the current status and identified problems. The work is > >> minimal to add full support. Out of 80+ tests, 7 fail to cross-build > >> and 1 fails to install correctly. > >> > >> List is below: > >> > >> Tests fails to build: bpf, capabilities, kvm, memfd, mqueue, timens, vm > >> Tests fail to install: android (partial failure) > >> Leaves source directory dirty: bpf, seccomp > >> > >> I have patches ready for the following issues: > >> > >> Kselftest objects (test dirs) clutter top level object directory. > >> seccomp_bpf generates objects in the source directory. > >> > >> I created a topic branch to collect all the patches: > >> > >> https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git/?… > >> > >> I am going to start working on build problems. If anybody is > >> interested in helping me with this effort, don't hesitate to > >> contact me. I first priority is fixing build and install and > >> then look into tests that leave the source directory dirty. > > > > I'm interested in this. I'd like the same cleanups in order to run > > kselftest in Fuego, and I can try it with additional toolchains > > and boards. Unfortunately, in terms of running tests, almost all > > the boards in my lab are running old kernels. So the tests results > > aren't useful for upstream work. But I can still test > > compilation and install issues, for the kselftest tests themselves. > > > > Testing compilation and install issues is very valuable. This is one > area that hasn't been test coverage compared to running tests. So it > great if you can help with build/install on linux-next to catch > problems in new tests. I am finding that older tests have been stable > and as new tests come in, we tend to miss catching these types of > problems. > > Especially cross-builds and installs on arm64 and others. OK. I've got 2 different arm64 compilers, with wildly different SDK setups, so hopefully this will be useful. > >> > >> Detailed report can be found here: > >> > >> https://drive.google.com/file/d/11nnWOKIzzOrE4EiucZBn423lzSU_eNNv/view?usp=… > > > > Is there anything you'd like me to look at specifically? Do you want me to start > > at the bottom of the list and work up? I could look at 'vm' or 'timens'. > > > > Yes you can start with vm and timens. I wrote a test for Fuego and ran into a few interesting issues. Also, I have a question about the best place to start, and your preference for reporting results. Your feedback on any of this would be appreciated: Here are some issues and questions I ran into: 1) overwriting of CC in lib.mk This line in tools/testing/selftests/lib.mk caused me some grief: CC := $(CROSS_COMPILE)gcc One of my toolchains pre-defines CC with a bunch of extra flags, so this didn't work for that tolchain. I'm still debugging this. I'm not sure why the weird definition of CC works for the rest of the kernel but not with kselftest. But I may submit some kind of patch to make this CC assignment conditional (that is, only do the assignment if it's not already defined) Let me know what you think. 2) ability to get list of targets would be nice It would be nice if there were a mechanism to get the list of default targets from kselftest. I added the following for my own tests, so that I don't have to hard-code my loop over the individual selftests: diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 63430e2..9955e71 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -246,4 +246,7 @@ clean: $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\ done; +show_targets: + @echo $(TARGETS) + .PHONY: khdr all run_tests hotplug run_hotplug clean_hotplug run_pstore_crash install clean This is pretty simple. I can submit this as a proper patch, if you're willing to take something like it, and we can discuss details if you'd rather see this done another way. 3) different ways to invoke kselftest There are a number of different ways to invoke kselftest. I'm currently using the '-C' method for both building and installing. make ARCH=$ARCHITECTURE TARGETS="$target" -C tools/testing/selftests make ARCH=$ARCHITECTURE TARGETS="$target" -C tools/testing/selftests install I think, there there are now targets for kselftest in the top-level Makefile. Do you have a preferred method you'd like me to test? Or would you like me to run my tests with multiple methods? And I'm using a KBUILD_OUTPUT environment variable, rather than O=. Let me know if you'd like me to build a matrix of these different build methods. 4) what tree(s) would you like me to test? I think you mentioned that you'd like to see the tests against 'linux-next'. Right now I've been doing tests against the 'torvalds' mainline tree, and the 'linux-kselftest' tree, master branch. Let me know if there are other branches or trees you like me to test. 5) where would you like test results? In the short term, I'm testing the compile and install of the tests and working on the ones that fail for me (I'm getting 17 or 18 failures, depending on the toolchain I'm using, for some of my boards). However, I'm still debugging my setup, I hope I can drop that down to the same one's you are seeing shortly. Longer-term I plan to set up a CI loop for these tests for Fuego, and publish some kind of matrix results and reports on my own server (https://birdcloud.org/) I'm generating HTML tables now that work with Fuego's Jenkins configuration, but I could send the data elsewhere if desired. This is still under construction. Would you like me to publish results also to kcidb, or some other repository? I might be able to publish my results to Kernelci, but I'll end up with a customized report for kselftest, that will allow drilling down to see output for individual compile or install failures. I'm not sure how much of that would be supported in the KernelCI interface. But I recognize you'd probably not like to have to go to multiple places to see results. Also, in terms of periodic results do you want any e-mails sent to the Linux-kselftest list? I thought I'd hold off for now, and wait for the compile/install fixes to settle down, so that future e-mails would only report regressions or issues with new tests. We can discuss this later, as I don't plan to do this quite yet (and would only do an e-mail after checking with you anyway). Thanks for any feedback you can provide. -- Tim P.S. Also, please let me know who is working on this on the KernelCI side (if it's not Kevin), so I can CC them on future discussions.

5 years, 3 months

3
3
0 0

[GIT PULL] Kselftest kunit update for Linux 5.6-rc5

by Shuah Khan

Hi Linus, Please pull the following Keselftest update for Linux 5.6-rc5. This Kselftest update for Linux 5.6-rc5 consists of a cleanup patch to undo changes to global .gitignore that added selftests/lkdtm objects and add them to a local selftests/lkdtm/.gitignore. Summary of Linus's comments on local vs. global gitignore scope: - Keep local gitignore patterns in local files. - Put only global gitignore patterns in the top-level gitignore file. Local scope keeps things much better separated. It also incidentally means that if a directory gets renamed, the gitignore file continues to work unless in the case of renaming the actual files themselves that are named in the gitignore. Diff is attached. I took the liberty to include summary of your comments on local vs global gitignore scope in the commit message. thanks, -- Shuah ---------------------------------------------------------------- The following changes since commit ef89d0545132d685f73da6f58b7e7fe002536f91: selftests/rseq: Fix out-of-tree compilation (2020-02-20 08:57:12 -0700) are available in the Git repository at: git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest tags/linux-kselftest-5.6-rc5 for you to fetch changes up to f3a60268f5cec7dae0e9713f5fc65aecc3734c09: selftest/lkdtm: Use local .gitignore (2020-03-02 08:39:39 -0700) ---------------------------------------------------------------- linux-kselftest-5.6-rc5 This Kselftest update for Linux 5.6-rc5 consists of a cleanup patch to undo changes to global .gitignore that added selftests/lkdtm objects and add them to a local selftests/lkdtm/.gitignore. Summary of Linus's comments on local vs. global gitignore scope: - Keep local gitignore patterns in local files. - Put only global gitignore patterns in the top-level gitignore file. Local scope keeps things much better separated. It also incidentally means that if a directory gets renamed, the gitignore file continues to work unless in the case of renaming the actual files themselves that are named in the gitignore. ---------------------------------------------------------------- Christophe Leroy (1): selftest/lkdtm: Use local .gitignore .gitignore | 4 ---- tools/testing/selftests/lkdtm/.gitignore | 2 ++ 2 files changed, 2 insertions(+), 4 deletions(-) create mode 100644 tools/testing/selftests/lkdtm/.gitignore ----------------------------------------------------------------

5 years, 3 months

2
1
0 0

[PATCH v3 0/4] Implement FUTEX_WAIT_MULTIPLE operation

by André Almeida

Hello, This patchset implements a new futex operation, called FUTEX_WAIT_MULTIPLE, which allows a thread to wait on several futexes at the same time, and be awoken by any of them. The use case lies in the Wine implementation of the Windows NT interface WaitMultipleObjects. This Windows API function allows a thread to sleep waiting on the first of a set of event sources (mutexes, timers, signal, console input, etc) to signal. Considering this is a primitive synchronization operation for Windows applications, being able to quickly signal events on the producer side, and quickly go to sleep on the consumer side is essential for good performance of those running over Wine. Since this API exposes a mechanism to wait on multiple objects, and we might have multiple waiters for each of these events, a M->N relationship, the current Linux interfaces fell short on performance evaluation of large M,N scenarios. We experimented, for instance, with eventfd, which has performance problems discussed below, but we also experimented with userspace solutions, like making each consumer wait on a condition variable guarding the entire list of objects, and then waking up multiple variables on the producer side, but this is prohibitively expensive since we either need to signal many condition variables or share that condition variable among multiple waiters, and then verify for the event being signaled in userspace, which means dealing with often false positive wakes ups. The natural interface to implement the behavior we want, also considering that one of the waitable objects is a mutex itself, would be the futex interface. Therefore, this patchset proposes a mechanism for a thread to wait on multiple futexes at once, and wake up on the first futex that was awaken. In particular, using futexes in our Wine use case reduced the CPU utilization by 4% for the game Beat Saber and by 1.5% for the game Shadow of Tomb Raider, both running over Proton (a Wine based solution for Windows emulation), when compared to the eventfd interface. This implementation also doesn't rely of file descriptors, so it doesn't risk overflowing the resource. In time, we are also proposing modifications to glibc and libpthread to make this feature available for Linux native multithreaded applications using libpthread, which can benefit from the behavior of waiting on any of a group of futexes. Technically, the existing FUTEX_WAIT implementation can be easily reworked by using futex_wait_multiple() with a count of one, and I have a patch showing how it works. I'm not proposing it, since futex is such a tricky code, that I'd be more comfortable to have FUTEX_WAIT_MULTIPLE running upstream for a couple development cycles, before considering modifying FUTEX_WAIT. The patch series includes an extensive set of kselftests validating the behavior of the interface. We also implemented support[1] on Syzkaller and survived the fuzzy testing. Finally, if you'd rather pull directly a branch with this set you can find it here: https://gitlab.collabora.com/tonyk/linux/commits/futex-dev-v3 The RFC for this patch can be found here: https://lkml.org/lkml/2019/7/30/1399 === Performance of eventfd === Polling on several eventfd contexts with semaphore semantics would provide us with the exact semantics we are looking for. However, as shown below, in a scenario with sufficient producers and consumers, the eventfd interface itself becomes a bottleneck, in particular because each thread will compete to acquire a sequence of waitqueue locks for each eventfd context in the poll list. In addition, in the uncontended case, where the producer is ready for consumption, eventfd still requires going into the kernel on the consumer side. When a write or a read operation in an eventfd file succeeds, it will try to wake up all threads that are waiting to perform some operation to the file. The lock (ctx->wqh.lock) that hold the access to the file value (ctx->count) is the same lock used to control access the waitqueue. When all those those thread woke, they will compete to get this lock. Along with that, the poll() also manipulates the waitqueue and need to hold this same lock. This lock is specially hard to acquire when poll() calls poll_freewait(), where it tries to free all waitqueues associated with this poll. While doing that, it will compete with a lot of read and write operations that have been waken. In our use case, with a huge number of parallel reads, writes and polls, this lock is a bottleneck and hurts the performance of applications. Our implementation of futex, however, decrease the calls of spin lock by more than 80% in some user applications. Finally, eventfd operates on file descriptors, which is a limited resource that has shown its limitation in our use cases. Despite the Windows interface not waiting on more than 64 objects at once, we still have multiple waiters at the same time, and we were easily able to exhaust the FD limits on applications like games. Thanks, André [1] https://github.com/andrealmeid/syzkaller/tree/futex-wait-multiple Gabriel Krisman Bertazi (4): futex: Implement mechanism to wait on any of several futexes selftests: futex: Add FUTEX_WAIT_MULTIPLE timeout test selftests: futex: Add FUTEX_WAIT_MULTIPLE wouldblock test selftests: futex: Add FUTEX_WAIT_MULTIPLE wake up test include/uapi/linux/futex.h | 20 + kernel/futex.c | 358 +++++++++++++++++- .../selftests/futex/functional/.gitignore | 1 + .../selftests/futex/functional/Makefile | 3 +- .../futex/functional/futex_wait_multiple.c | 173 +++++++++ .../futex/functional/futex_wait_timeout.c | 38 +- .../futex/functional/futex_wait_wouldblock.c | 28 +- .../testing/selftests/futex/functional/run.sh | 3 + .../selftests/futex/include/futextest.h | 22 ++ 9 files changed, 639 insertions(+), 7 deletions(-) create mode 100644 tools/testing/selftests/futex/functional/futex_wait_multiple.c -- 2.25.0

5 years, 3 months

7
20
0 0

[PATCH bpf-next v3 11/12] selftests: bpf: enable UDP sockmap reuseport tests

by Lorenz Bauer

Remove the guard that disables UDP tests now that sockmap has support for them. Signed-off-by: Lorenz Bauer <lmb(a)cloudflare.com> --- tools/testing/selftests/bpf/prog_tests/select_reuseport.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c index a1dd13b34d4b..821b4146b7b6 100644 --- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c +++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c @@ -805,12 +805,6 @@ static void test_config(int sotype, sa_family_t family, bool inany) char s[MAX_TEST_NAME]; const struct test *t; - /* SOCKMAP/SOCKHASH don't support UDP yet */ - if (sotype == SOCK_DGRAM && - (inner_map_type == BPF_MAP_TYPE_SOCKMAP || - inner_map_type == BPF_MAP_TYPE_SOCKHASH)) - return; - for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { if (t->need_sotype && t->need_sotype != sotype) continue; /* test not compatible with socket type */ -- 2.20.1

5 years, 3 months

3
2
0 0

[PATCH bpf-next v3 10/12] selftests: bpf: add tests for UDP sockets in sockmap

by Lorenz Bauer

Expand the TCP sockmap test suite to also check UDP sockets. Signed-off-by: Jakub Sitnicki <jakub(a)cloudflare.com> Signed-off-by: Lorenz Bauer <lmb(a)cloudflare.com> --- .../selftests/bpf/prog_tests/sockmap_listen.c | 157 ++++++++++++++---- 1 file changed, 127 insertions(+), 30 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 4ba41dd26d6b..52aa468bdccd 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -108,6 +108,22 @@ __ret; \ }) +#define xsend(fd, buf, len, flags) \ + ({ \ + ssize_t __ret = send((fd), (buf), (len), (flags)); \ + if (__ret == -1) \ + FAIL_ERRNO("send"); \ + __ret; \ + }) + +#define xrecv(fd, buf, len, flags) \ + ({ \ + ssize_t __ret = recv((fd), (buf), (len), (flags)); \ + if (__ret == -1) \ + FAIL_ERRNO("recv"); \ + __ret; \ + }) + #define xsocket(family, sotype, flags) \ ({ \ int __ret = socket(family, sotype, flags); \ @@ -330,7 +346,7 @@ static void test_insert_bound(int family, int sotype, int mapfd) xclose(s); } -static void test_insert_listening(int family, int sotype, int mapfd) +static void test_insert(int family, int sotype, int mapfd) { u64 value; u32 key; @@ -467,7 +483,7 @@ static void test_lookup_32_bit_value(int family, int sotype, int mapfd) xclose(s); } -static void test_update_listening(int family, int sotype, int mapfd) +static void test_update_existing(int family, int sotype, int mapfd) { int s1, s2; u64 value; @@ -1116,7 +1132,7 @@ static void test_reuseport_select_listening(int family, int sotype, { struct sockaddr_storage addr; unsigned int pass; - int s, c, p, err; + int s, c, err; socklen_t len; u64 value; u32 key; @@ -1145,19 +1161,33 @@ static void test_reuseport_select_listening(int family, int sotype, if (err) goto close_cli; - p = xaccept(s, NULL, NULL); - if (p < 0) - goto close_cli; + if (sotype == SOCK_STREAM) { + int p; + + p = xaccept(s, NULL, NULL); + if (p < 0) + goto close_cli; + xclose(p); + } else { + char b = 'a'; + ssize_t n; + + n = xsend(c, &b, sizeof(b), 0); + if (n == -1) + goto close_cli; + + n = xrecv(s, &b, sizeof(b), 0); + if (n == -1) + goto close_cli; + } key = SK_PASS; err = xbpf_map_lookup_elem(verd_map, &key, &pass); if (err) - goto close_peer; + goto close_cli; if (pass != 1) FAIL("want pass count 1, have %d", pass); -close_peer: - xclose(p); close_cli: xclose(c); close_srv: @@ -1201,9 +1231,24 @@ static void test_reuseport_select_connected(int family, int sotype, if (err) goto close_cli0; - p0 = xaccept(s, NULL, NULL); - if (err) - goto close_cli0; + if (sotype == SOCK_STREAM) { + p0 = xaccept(s, NULL, NULL); + if (p0 < 0) + goto close_cli0; + } else { + p0 = xsocket(family, sotype, 0); + if (p0 < 0) + goto close_cli0; + + len = sizeof(addr); + err = xgetsockname(c0, sockaddr(&addr), &len); + if (err) + goto close_cli0; + + err = xconnect(p0, sockaddr(&addr), len); + if (err) + goto close_cli0; + } /* Update sock_map[0] to redirect to a connected socket */ key = 0; @@ -1216,8 +1261,24 @@ static void test_reuseport_select_connected(int family, int sotype, if (c1 < 0) goto close_peer0; + len = sizeof(addr); + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + goto close_srv; + errno = 0; err = connect(c1, sockaddr(&addr), len); + if (sotype == SOCK_DGRAM) { + char b = 'a'; + ssize_t n; + + n = xsend(c1, &b, sizeof(b), 0); + if (n == -1) + goto close_cli1; + + n = recv(c1, &b, sizeof(b), 0); + err = n == -1; + } if (!err || errno != ECONNREFUSED) FAIL_ERRNO("connect: expected ECONNREFUSED"); @@ -1281,7 +1342,18 @@ static void test_reuseport_mixed_groups(int family, int sotype, int sock_map, goto close_srv2; err = connect(c, sockaddr(&addr), len); - if (err && errno != ECONNREFUSED) { + if (sotype == SOCK_DGRAM) { + char b = 'a'; + ssize_t n; + + n = xsend(c, &b, sizeof(b), 0); + if (n == -1) + goto close_cli; + + n = recv(c, &b, sizeof(b), 0); + err = n == -1; + } + if (!err || errno != ECONNREFUSED) { FAIL_ERRNO("connect: expected ECONNREFUSED"); goto close_cli; } @@ -1302,9 +1374,9 @@ static void test_reuseport_mixed_groups(int family, int sotype, int sock_map, xclose(s1); } -#define TEST(fn) \ +#define TEST(fn, ...) \ { \ - fn, #fn \ + fn, #fn, __VA_ARGS__ \ } static void test_ops_cleanup(const struct bpf_map *map) @@ -1353,18 +1425,31 @@ static const char *map_type_str(const struct bpf_map *map) } } +static const char *sotype_str(int sotype) +{ + switch (sotype) { + case SOCK_DGRAM: + return "UDP"; + case SOCK_STREAM: + return "TCP"; + default: + return "unknown"; + } +} + static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map, int family, int sotype) { const struct op_test { void (*fn)(int family, int sotype, int mapfd); const char *name; + int sotype; } tests[] = { /* insert */ TEST(test_insert_invalid), TEST(test_insert_opened), - TEST(test_insert_bound), - TEST(test_insert_listening), + TEST(test_insert_bound, SOCK_STREAM), + TEST(test_insert), /* delete */ TEST(test_delete_after_insert), TEST(test_delete_after_close), @@ -1373,28 +1458,32 @@ static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map, TEST(test_lookup_after_delete), TEST(test_lookup_32_bit_value), /* update */ - TEST(test_update_listening), + TEST(test_update_existing), /* races with insert/delete */ - TEST(test_destroy_orphan_child), - TEST(test_syn_recv_insert_delete), - TEST(test_race_insert_listen), + TEST(test_destroy_orphan_child, SOCK_STREAM), + TEST(test_syn_recv_insert_delete, SOCK_STREAM), + TEST(test_race_insert_listen, SOCK_STREAM), /* child clone */ - TEST(test_clone_after_delete), - TEST(test_accept_after_delete), - TEST(test_accept_before_delete), + TEST(test_clone_after_delete, SOCK_STREAM), + TEST(test_accept_after_delete, SOCK_STREAM), + TEST(test_accept_before_delete, SOCK_STREAM), }; - const char *family_name, *map_name; + const char *family_name, *map_name, *sotype_name; const struct op_test *t; char s[MAX_TEST_NAME]; int map_fd; family_name = family_str(family); map_name = map_type_str(map); + sotype_name = sotype_str(sotype); map_fd = bpf_map__fd(map); for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { - snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, - t->name); + snprintf(s, sizeof(s), "%s %s %s %s", map_name, family_name, + sotype_name, t->name); + + if (t->sotype != 0 && t->sotype != sotype) + continue; if (!test__start_subtest(s)) continue; @@ -1427,6 +1516,7 @@ static void test_redir(struct test_sockmap_listen *skel, struct bpf_map *map, for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, t->name); + if (!test__start_subtest(s)) continue; @@ -1441,26 +1531,31 @@ static void test_reuseport(struct test_sockmap_listen *skel, void (*fn)(int family, int sotype, int socket_map, int verdict_map, int reuseport_prog); const char *name; + int sotype; } tests[] = { TEST(test_reuseport_select_listening), TEST(test_reuseport_select_connected), TEST(test_reuseport_mixed_groups), }; int socket_map, verdict_map, reuseport_prog; - const char *family_name, *map_name; + const char *family_name, *map_name, *sotype_name; const struct reuseport_test *t; char s[MAX_TEST_NAME]; family_name = family_str(family); map_name = map_type_str(map); + sotype_name = sotype_str(sotype); socket_map = bpf_map__fd(map); verdict_map = bpf_map__fd(skel->maps.verdict_map); reuseport_prog = bpf_program__fd(skel->progs.prog_reuseport); for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { - snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, - t->name); + snprintf(s, sizeof(s), "%s %s %s %s", map_name, family_name, + sotype_name, t->name); + + if (t->sotype != 0 && t->sotype != sotype) + continue; if (!test__start_subtest(s)) continue; @@ -1473,8 +1568,10 @@ static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map, int family) { test_ops(skel, map, family, SOCK_STREAM); + test_ops(skel, map, family, SOCK_DGRAM); test_redir(skel, map, family, SOCK_STREAM); test_reuseport(skel, map, family, SOCK_STREAM); + test_reuseport(skel, map, family, SOCK_DGRAM); } void test_sockmap_listen(void) -- 2.20.1

5 years, 3 months

2
1
0 0

[PATCH bpf-next v3 09/12] selftests: bpf: don't listen() on UDP sockets

by Lorenz Bauer

Most tests for TCP sockmap can be adapted to UDP sockmap if the listen call is skipped. Rename listen_loopback, etc. to socket_loopback and skip listen() for SOCK_DGRAM. Signed-off-by: Lorenz Bauer <lmb(a)cloudflare.com> --- .../selftests/bpf/prog_tests/sockmap_listen.c | 47 ++++++++++--------- 1 file changed, 25 insertions(+), 22 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index b1b2acea0638..4ba41dd26d6b 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -230,7 +230,7 @@ static int enable_reuseport(int s, int progfd) return 0; } -static int listen_loopback_reuseport(int family, int sotype, int progfd) +static int socket_loopback_reuseport(int family, int sotype, int progfd) { struct sockaddr_storage addr; socklen_t len; @@ -249,6 +249,9 @@ static int listen_loopback_reuseport(int family, int sotype, int progfd) if (err) goto close; + if (sotype == SOCK_DGRAM) + return s; + err = xlisten(s, SOMAXCONN); if (err) goto close; @@ -259,9 +262,9 @@ static int listen_loopback_reuseport(int family, int sotype, int progfd) return -1; } -static int listen_loopback(int family, int sotype) +static int socket_loopback(int family, int sotype) { - return listen_loopback_reuseport(family, sotype, -1); + return socket_loopback_reuseport(family, sotype, -1); } static void test_insert_invalid(int family, int sotype, int mapfd) @@ -333,7 +336,7 @@ static void test_insert_listening(int family, int sotype, int mapfd) u32 key; int s; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -349,7 +352,7 @@ static void test_delete_after_insert(int family, int sotype, int mapfd) u32 key; int s; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -366,7 +369,7 @@ static void test_delete_after_close(int family, int sotype, int mapfd) u64 value; u32 key; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -390,7 +393,7 @@ static void test_lookup_after_insert(int family, int sotype, int mapfd) u32 key; int s; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -417,7 +420,7 @@ static void test_lookup_after_delete(int family, int sotype, int mapfd) u64 value; u32 key; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -439,7 +442,7 @@ static void test_lookup_32_bit_value(int family, int sotype, int mapfd) u32 key, value32; int err, s; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -470,11 +473,11 @@ static void test_update_listening(int family, int sotype, int mapfd) u64 value; u32 key; - s1 = listen_loopback(family, sotype); + s1 = socket_loopback(family, sotype); if (s1 < 0) return; - s2 = listen_loopback(family, sotype); + s2 = socket_loopback(family, sotype); if (s2 < 0) goto close_s1; @@ -500,7 +503,7 @@ static void test_destroy_orphan_child(int family, int sotype, int mapfd) u64 value; u32 key; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -534,7 +537,7 @@ static void test_clone_after_delete(int family, int sotype, int mapfd) u64 value; u32 key; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s < 0) return; @@ -570,7 +573,7 @@ static void test_accept_after_delete(int family, int sotype, int mapfd) socklen_t len; u64 value; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s == -1) return; @@ -624,7 +627,7 @@ static void test_accept_before_delete(int family, int sotype, int mapfd) socklen_t len; u64 value; - s = listen_loopback(family, sotype); + s = socket_loopback(family, sotype); if (s == -1) return; @@ -735,7 +738,7 @@ static void test_syn_recv_insert_delete(int family, int sotype, int mapfd) int err, s; u64 value; - s = listen_loopback(family, sotype | SOCK_NONBLOCK); + s = socket_loopback(family, sotype | SOCK_NONBLOCK); if (s < 0) return; @@ -877,7 +880,7 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, zero_verdict_count(verd_mapfd); - s = listen_loopback(family, sotype | SOCK_NONBLOCK); + s = socket_loopback(family, sotype | SOCK_NONBLOCK); if (s < 0) return; @@ -1009,7 +1012,7 @@ static void redir_to_listening(int family, int sotype, int sock_mapfd, zero_verdict_count(verd_mapfd); - s = listen_loopback(family, sotype | SOCK_NONBLOCK); + s = socket_loopback(family, sotype | SOCK_NONBLOCK); if (s < 0) return; @@ -1120,7 +1123,7 @@ static void test_reuseport_select_listening(int family, int sotype, zero_verdict_count(verd_map); - s = listen_loopback_reuseport(family, sotype, reuseport_prog); + s = socket_loopback_reuseport(family, sotype, reuseport_prog); if (s < 0) return; @@ -1174,7 +1177,7 @@ static void test_reuseport_select_connected(int family, int sotype, zero_verdict_count(verd_map); - s = listen_loopback_reuseport(family, sotype, reuseport_prog); + s = socket_loopback_reuseport(family, sotype, reuseport_prog); if (s < 0) return; @@ -1249,11 +1252,11 @@ static void test_reuseport_mixed_groups(int family, int sotype, int sock_map, zero_verdict_count(verd_map); /* Create two listeners, each in its own reuseport group */ - s1 = listen_loopback_reuseport(family, sotype, reuseport_prog); + s1 = socket_loopback_reuseport(family, sotype, reuseport_prog); if (s1 < 0) return; - s2 = listen_loopback_reuseport(family, sotype, reuseport_prog); + s2 = socket_loopback_reuseport(family, sotype, reuseport_prog); if (s2 < 0) goto close_srv1; -- 2.20.1

5 years, 3 months

3
2
0 0

[PATCH -next] selftests/timens: Remove duplicated include <time.h>

by YueHaibing

Remove duplicated include. Signed-off-by: YueHaibing <yuehaibing(a)huawei.com> --- tools/testing/selftests/timens/exec.c | 1 - tools/testing/selftests/timens/procfs.c | 1 - tools/testing/selftests/timens/timens.c | 1 - tools/testing/selftests/timens/timer.c | 1 - 4 files changed, 4 deletions(-) diff --git a/tools/testing/selftests/timens/exec.c b/tools/testing/selftests/timens/exec.c index 87b47b5..e40dc5b 100644 --- a/tools/testing/selftests/timens/exec.c +++ b/tools/testing/selftests/timens/exec.c @@ -11,7 +11,6 @@ #include <sys/wait.h> #include <time.h> #include <unistd.h> -#include <time.h> #include <string.h> #include "log.h" diff --git a/tools/testing/selftests/timens/procfs.c b/tools/testing/selftests/timens/procfs.c index 43d93f4..7f14f0f 100644 --- a/tools/testing/selftests/timens/procfs.c +++ b/tools/testing/selftests/timens/procfs.c @@ -12,7 +12,6 @@ #include <sys/types.h> #include <time.h> #include <unistd.h> -#include <time.h> #include "log.h" #include "timens.h" diff --git a/tools/testing/selftests/timens/timens.c b/tools/testing/selftests/timens/timens.c index 559d26e..098be7c 100644 --- a/tools/testing/selftests/timens/timens.c +++ b/tools/testing/selftests/timens/timens.c @@ -10,7 +10,6 @@ #include <sys/types.h> #include <time.h> #include <unistd.h> -#include <time.h> #include <string.h> #include "log.h" diff --git a/tools/testing/selftests/timens/timer.c b/tools/testing/selftests/timens/timer.c index 0cca7aa..96dba11 100644 --- a/tools/testing/selftests/timens/timer.c +++ b/tools/testing/selftests/timens/timer.c @@ -11,7 +11,6 @@ #include <stdio.h> #include <stdint.h> #include <signal.h> -#include <time.h> #include "log.h" #include "timens.h" -- 2.7.4

5 years, 3 months

2
1
0 0

[PATCH bpf 1/2] bpf, x32: fix bug with JMP32 JSET BPF_X checking upper bits

by Luke Nelson

The current x32 BPF JIT is incorrect for JMP32 JSET BPF_X when the upper 32 bits of operand registers are non-zero in certain situations. The problem is in the following code: case BPF_JMP | BPF_JSET | BPF_X: case BPF_JMP32 | BPF_JSET | BPF_X: ... /* and dreg_lo,sreg_lo */ EMIT2(0x23, add_2reg(0xC0, sreg_lo, dreg_lo)); /* and dreg_hi,sreg_hi */ EMIT2(0x23, add_2reg(0xC0, sreg_hi, dreg_hi)); /* or dreg_lo,dreg_hi */ EMIT2(0x09, add_2reg(0xC0, dreg_lo, dreg_hi)); This code checks the upper bits of the operand registers regardless if the BPF instruction is BPF_JMP32 or BPF_JMP64. Registers dreg_hi and dreg_lo are not loaded from the stack for BPF_JMP32, however, they can still be polluted with values from previous instructions. The following BPF program demonstrates the bug. The jset64 instruction loads the temporary registers and performs the jump, since ((u64)r7 & (u64)r8) is non-zero. The jset32 should _not_ be taken, as the lower 32 bits are all zero, however, the current JIT will take the branch due the pollution of temporary registers from the earlier jset64. mov64 r0, 0 ld64 r7, 0x8000000000000000 ld64 r8, 0x8000000000000000 jset64 r7, r8, 1 exit jset32 r7, r8, 1 mov64 r0, 2 exit The expected return value of this program is 2; under the buggy x32 JIT it returns 0. The fix is to skip using the upper 32 bits for jset32 and compare the upper 32 bits for jset64 only. All tests in test_bpf.ko and selftests/bpf/test_verifier continue to pass with this change. We found this bug using our automated verification tool, Serval. Fixes: 69f827eb6e14 ("x32: bpf: implement jitting of JMP32") Co-developed-by: Xi Wang <xi.wang(a)gmail.com> Signed-off-by: Xi Wang <xi.wang(a)gmail.com> Signed-off-by: Luke Nelson <luke.r.nels(a)gmail.com> --- arch/x86/net/bpf_jit_comp32.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 393d251798c0..4d2a7a764602 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -2039,10 +2039,12 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, } /* and dreg_lo,sreg_lo */ EMIT2(0x23, add_2reg(0xC0, sreg_lo, dreg_lo)); - /* and dreg_hi,sreg_hi */ - EMIT2(0x23, add_2reg(0xC0, sreg_hi, dreg_hi)); - /* or dreg_lo,dreg_hi */ - EMIT2(0x09, add_2reg(0xC0, dreg_lo, dreg_hi)); + if (is_jmp64) { + /* and dreg_hi,sreg_hi */ + EMIT2(0x23, add_2reg(0xC0, sreg_hi, dreg_hi)); + /* or dreg_lo,dreg_hi */ + EMIT2(0x09, add_2reg(0xC0, dreg_lo, dreg_hi)); + } goto emit_cond_jmp; } case BPF_JMP | BPF_JSET | BPF_K: -- 2.20.1

5 years, 3 months

2
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror