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

[PATCH v11 1/9] hugetlb_cgroup: Add hugetlb_cgroup reservation counter

by Mina Almasry

These counters will track hugetlb reservations rather than hugetlb memory faulted in. This patch only adds the counter, following patches add the charging and uncharging of the counter. This is patch 1 of an 9 patch series. Problem: Currently tasks attempting to reserve more hugetlb memory than is available get a failure at mmap/shmget time. This is thanks to Hugetlbfs Reservations [1]. However, if a task attempts to reserve more hugetlb memory than its hugetlb_cgroup limit allows, the kernel will allow the mmap/shmget call, but will SIGBUS the task when it attempts to fault in the excess memory. We have users hitting their hugetlb_cgroup limits and thus we've been looking at this failure mode. We'd like to improve this behavior such that users violating the hugetlb_cgroup limits get an error on mmap/shmget time, rather than getting SIGBUS'd when they try to fault the excess memory in. This gives the user an opportunity to fallback more gracefully to non-hugetlbfs memory for example. The underlying problem is that today's hugetlb_cgroup accounting happens at hugetlb memory *fault* time, rather than at *reservation* time. Thus, enforcing the hugetlb_cgroup limit only happens at fault time, and the offending task gets SIGBUS'd. Proposed Solution: A new page counter named 'hugetlb.xMB.rsvd.[limit|usage|max_usage]_in_bytes'. This counter has slightly different semantics than 'hugetlb.xMB.[limit|usage|max_usage]_in_bytes': - While usage_in_bytes tracks all *faulted* hugetlb memory, rsvd.usage_in_bytes tracks all *reserved* hugetlb memory and hugetlb memory faulted in without a prior reservation. - If a task attempts to reserve more memory than limit_in_bytes allows, the kernel will allow it to do so. But if a task attempts to reserve more memory than rsvd.limit_in_bytes, the kernel will fail this reservation. This proposal is implemented in this patch series, with tests to verify functionality and show the usage. Alternatives considered: 1. A new cgroup, instead of only a new page_counter attached to the existing hugetlb_cgroup. Adding a new cgroup seemed like a lot of code duplication with hugetlb_cgroup. Keeping hugetlb related page counters under hugetlb_cgroup seemed cleaner as well. 2. Instead of adding a new counter, we considered adding a sysctl that modifies the behavior of hugetlb.xMB.[limit|usage]_in_bytes, to do accounting at reservation time rather than fault time. Adding a new page_counter seems better as userspace could, if it wants, choose to enforce different cgroups differently: one via limit_in_bytes, and another via rsvd.limit_in_bytes. This could be very useful if you're transitioning how hugetlb memory is partitioned on your system one cgroup at a time, for example. Also, someone may find usage for both limit_in_bytes and rsvd.limit_in_bytes concurrently, and this approach gives them the option to do so. Testing: - Added tests passing. - Used libhugetlbfs for regression testing. [1]: https://www.kernel.org/doc/html/latest/vm/hugetlbfs_reserv.html Signed-off-by: Mina Almasry <almasrymina(a)google.com> Acked-by: David Rientjes <rientjes(a)google.com> --- Changes in v11: - Renamed resv.* or 'reservation' or 'reserved' to rsvd.* - Renamed hugetlb_cgroup_get_counter() to hugetlb_cgroup_counter_from_cgroup(). Changes in v10: - Renamed reservation_* to resv.* --- include/linux/hugetlb.h | 4 +- mm/hugetlb_cgroup.c | 116 +++++++++++++++++++++++++++++++++++----- 2 files changed, 105 insertions(+), 15 deletions(-) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 1e897e4168ac1..dea6143aa0685 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -432,8 +432,8 @@ struct hstate { unsigned int surplus_huge_pages_node[MAX_NUMNODES]; #ifdef CONFIG_CGROUP_HUGETLB /* cgroup control files */ - struct cftype cgroup_files_dfl[5]; - struct cftype cgroup_files_legacy[5]; + struct cftype cgroup_files_dfl[7]; + struct cftype cgroup_files_legacy[9]; #endif char name[HSTATE_NAME_LEN]; }; diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index e434b05416c68..cd1f44775259c 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -36,6 +36,11 @@ struct hugetlb_cgroup { */ struct page_counter hugepage[HUGE_MAX_HSTATE]; + /* + * the counter to account for hugepage reservations from hugetlb. + */ + struct page_counter rsvd_hugepage[HUGE_MAX_HSTATE]; + atomic_long_t events[HUGE_MAX_HSTATE][HUGETLB_NR_MEMORY_EVENTS]; atomic_long_t events_local[HUGE_MAX_HSTATE][HUGETLB_NR_MEMORY_EVENTS]; @@ -55,6 +60,15 @@ struct hugetlb_cgroup { static struct hugetlb_cgroup *root_h_cgroup __read_mostly; +static inline struct page_counter * +hugetlb_cgroup_counter_from_cgroup(struct hugetlb_cgroup *h_cg, int idx, + bool rsvd) +{ + if (rsvd) + return &h_cg->rsvd_hugepage[idx]; + return &h_cg->hugepage[idx]; +} + static inline struct hugetlb_cgroup *hugetlb_cgroup_from_css(struct cgroup_subsys_state *s) { @@ -295,28 +309,42 @@ void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, enum { RES_USAGE, + RES_RSVD_USAGE, RES_LIMIT, + RES_RSVD_LIMIT, RES_MAX_USAGE, + RES_RSVD_MAX_USAGE, RES_FAILCNT, + RES_RSVD_FAILCNT, }; static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) { struct page_counter *counter; + struct page_counter *rsvd_counter; struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); counter = &h_cg->hugepage[MEMFILE_IDX(cft->private)]; + rsvd_counter = &h_cg->rsvd_hugepage[MEMFILE_IDX(cft->private)]; switch (MEMFILE_ATTR(cft->private)) { case RES_USAGE: return (u64)page_counter_read(counter) * PAGE_SIZE; + case RES_RSVD_USAGE: + return (u64)page_counter_read(rsvd_counter) * PAGE_SIZE; case RES_LIMIT: return (u64)counter->max * PAGE_SIZE; + case RES_RSVD_LIMIT: + return (u64)rsvd_counter->max * PAGE_SIZE; case RES_MAX_USAGE: return (u64)counter->watermark * PAGE_SIZE; + case RES_RSVD_MAX_USAGE: + return (u64)rsvd_counter->watermark * PAGE_SIZE; case RES_FAILCNT: return counter->failcnt; + case RES_RSVD_FAILCNT: + return rsvd_counter->failcnt; default: BUG(); } @@ -338,10 +366,16 @@ static int hugetlb_cgroup_read_u64_max(struct seq_file *seq, void *v) 1 << huge_page_order(&hstates[idx])); switch (MEMFILE_ATTR(cft->private)) { + case RES_RSVD_USAGE: + counter = &h_cg->rsvd_hugepage[idx]; + /* Fall through. */ case RES_USAGE: val = (u64)page_counter_read(counter); seq_printf(seq, "%llu\n", val * PAGE_SIZE); break; + case RES_RSVD_LIMIT: + counter = &h_cg->rsvd_hugepage[idx]; + /* Fall through. */ case RES_LIMIT: val = (u64)counter->max; if (val == limit) @@ -365,6 +399,7 @@ static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of, int ret, idx; unsigned long nr_pages; struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of)); + bool rsvd = false; if (hugetlb_cgroup_is_root(h_cg)) /* Can't set limit on root */ return -EINVAL; @@ -378,9 +413,14 @@ static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of, nr_pages = round_down(nr_pages, 1 << huge_page_order(&hstates[idx])); switch (MEMFILE_ATTR(of_cft(of)->private)) { + case RES_RSVD_LIMIT: + rsvd = true; + /* Fall through. */ case RES_LIMIT: mutex_lock(&hugetlb_limit_mutex); - ret = page_counter_set_max(&h_cg->hugepage[idx], nr_pages); + ret = page_counter_set_max( + hugetlb_cgroup_counter_from_cgroup(h_cg, idx, rsvd), + nr_pages); mutex_unlock(&hugetlb_limit_mutex); break; default: @@ -406,18 +446,26 @@ static ssize_t hugetlb_cgroup_reset(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { int ret = 0; - struct page_counter *counter; + struct page_counter *counter, *rsvd_counter; struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of)); counter = &h_cg->hugepage[MEMFILE_IDX(of_cft(of)->private)]; + rsvd_counter = + &h_cg->rsvd_hugepage[MEMFILE_IDX(of_cft(of)->private)]; switch (MEMFILE_ATTR(of_cft(of)->private)) { case RES_MAX_USAGE: page_counter_reset_watermark(counter); break; + case RES_RSVD_MAX_USAGE: + page_counter_reset_watermark(rsvd_counter); + break; case RES_FAILCNT: counter->failcnt = 0; break; + case RES_RSVD_FAILCNT: + rsvd_counter->failcnt = 0; + break; default: ret = -EINVAL; break; @@ -472,7 +520,7 @@ static void __init __hugetlb_cgroup_file_dfl_init(int idx) struct hstate *h = &hstates[idx]; /* format the size */ - mem_fmt(buf, 32, huge_page_size(h)); + mem_fmt(buf, sizeof(buf), huge_page_size(h)); /* Add the limit file */ cft = &h->cgroup_files_dfl[0]; @@ -482,15 +530,30 @@ static void __init __hugetlb_cgroup_file_dfl_init(int idx) cft->write = hugetlb_cgroup_write_dfl; cft->flags = CFTYPE_NOT_ON_ROOT; - /* Add the current usage file */ + /* Add the reservation limit file */ cft = &h->cgroup_files_dfl[1]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.rsvd.max", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_RSVD_LIMIT); + cft->seq_show = hugetlb_cgroup_read_u64_max; + cft->write = hugetlb_cgroup_write_dfl; + cft->flags = CFTYPE_NOT_ON_ROOT; + + /* Add the current usage file */ + cft = &h->cgroup_files_dfl[2]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.current", buf); cft->private = MEMFILE_PRIVATE(idx, RES_USAGE); cft->seq_show = hugetlb_cgroup_read_u64_max; cft->flags = CFTYPE_NOT_ON_ROOT; + /* Add the current reservation usage file */ + cft = &h->cgroup_files_dfl[3]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.rsvd.current", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_RSVD_USAGE); + cft->seq_show = hugetlb_cgroup_read_u64_max; + cft->flags = CFTYPE_NOT_ON_ROOT; + /* Add the events file */ - cft = &h->cgroup_files_dfl[2]; + cft = &h->cgroup_files_dfl[4]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.events", buf); cft->private = MEMFILE_PRIVATE(idx, 0); cft->seq_show = hugetlb_events_show; @@ -498,7 +561,7 @@ static void __init __hugetlb_cgroup_file_dfl_init(int idx) cft->flags = CFTYPE_NOT_ON_ROOT; /* Add the events.local file */ - cft = &h->cgroup_files_dfl[3]; + cft = &h->cgroup_files_dfl[5]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.events.local", buf); cft->private = MEMFILE_PRIVATE(idx, 0); cft->seq_show = hugetlb_events_local_show; @@ -507,7 +570,7 @@ static void __init __hugetlb_cgroup_file_dfl_init(int idx) cft->flags = CFTYPE_NOT_ON_ROOT; /* NULL terminate the last cft */ - cft = &h->cgroup_files_dfl[4]; + cft = &h->cgroup_files_dfl[6]; memset(cft, 0, sizeof(*cft)); WARN_ON(cgroup_add_dfl_cftypes(&hugetlb_cgrp_subsys, @@ -521,7 +584,7 @@ static void __init __hugetlb_cgroup_file_legacy_init(int idx) struct hstate *h = &hstates[idx]; /* format the size */ - mem_fmt(buf, 32, huge_page_size(h)); + mem_fmt(buf, sizeof(buf), huge_page_size(h)); /* Add the limit file */ cft = &h->cgroup_files_legacy[0]; @@ -530,28 +593,55 @@ static void __init __hugetlb_cgroup_file_legacy_init(int idx) cft->read_u64 = hugetlb_cgroup_read_u64; cft->write = hugetlb_cgroup_write_legacy; - /* Add the usage file */ + /* Add the reservation limit file */ cft = &h->cgroup_files_legacy[1]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.rsvd.limit_in_bytes", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_RSVD_LIMIT); + cft->read_u64 = hugetlb_cgroup_read_u64; + cft->write = hugetlb_cgroup_write_legacy; + + /* Add the usage file */ + cft = &h->cgroup_files_legacy[2]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.usage_in_bytes", buf); cft->private = MEMFILE_PRIVATE(idx, RES_USAGE); cft->read_u64 = hugetlb_cgroup_read_u64; + /* Add the reservation usage file */ + cft = &h->cgroup_files_legacy[3]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.rsvd.usage_in_bytes", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_RSVD_USAGE); + cft->read_u64 = hugetlb_cgroup_read_u64; + /* Add the MAX usage file */ - cft = &h->cgroup_files_legacy[2]; + cft = &h->cgroup_files_legacy[4]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.max_usage_in_bytes", buf); cft->private = MEMFILE_PRIVATE(idx, RES_MAX_USAGE); cft->write = hugetlb_cgroup_reset; cft->read_u64 = hugetlb_cgroup_read_u64; + /* Add the MAX reservation usage file */ + cft = &h->cgroup_files_legacy[5]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.rsvd.max_usage_in_bytes", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_RSVD_MAX_USAGE); + cft->write = hugetlb_cgroup_reset; + cft->read_u64 = hugetlb_cgroup_read_u64; + /* Add the failcntfile */ - cft = &h->cgroup_files_legacy[3]; + cft = &h->cgroup_files_legacy[6]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.failcnt", buf); - cft->private = MEMFILE_PRIVATE(idx, RES_FAILCNT); + cft->private = MEMFILE_PRIVATE(idx, RES_FAILCNT); + cft->write = hugetlb_cgroup_reset; + cft->read_u64 = hugetlb_cgroup_read_u64; + + /* Add the reservation failcntfile */ + cft = &h->cgroup_files_legacy[7]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.rsvd.failcnt", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_RSVD_FAILCNT); cft->write = hugetlb_cgroup_reset; cft->read_u64 = hugetlb_cgroup_read_u64; /* NULL terminate the last cft */ - cft = &h->cgroup_files_legacy[4]; + cft = &h->cgroup_files_legacy[8]; memset(cft, 0, sizeof(*cft)); WARN_ON(cgroup_add_legacy_cftypes(&hugetlb_cgrp_subsys, -- 2.25.0.341.g760bfbb309-goog

5 years, 3 months

3
28
0 0

[PATCH] Documentation: kunit: Make the KUnit documentation less UML-specific

by David Gow

Remove some of the outmoded "Why KUnit" rationale -- which focuses significantly on UML -- and update the Getting Started guide to mention running tests without the kunit_tool wrapper. Signed-off-by: David Gow <davidgow(a)google.com> --- This is an attempt at resolving some of the issues with the KUnit documentation pointed out here: https://lore.kernel.org/linux-kselftest/CABVgOSkiLi0UNijH1xTSvmsJEE5+ocCZ7n… There's definitely room for further work on the KUnit documentation (e.g., adding more information around the environment tests run in), but this hopefully is better than nothing as a starting point. Documentation/dev-tools/kunit/index.rst | 60 ++++--------------- Documentation/dev-tools/kunit/start.rst | 80 +++++++++++++++++++++---- 2 files changed, 78 insertions(+), 62 deletions(-) diff --git a/Documentation/dev-tools/kunit/index.rst b/Documentation/dev-tools/kunit/index.rst index d16a4d2c3a41..6064cd14dfad 100644 --- a/Documentation/dev-tools/kunit/index.rst +++ b/Documentation/dev-tools/kunit/index.rst @@ -17,63 +17,23 @@ What is KUnit? ============== KUnit is a lightweight unit testing and mocking framework for the Linux kernel. -These tests are able to be run locally on a developer's workstation without a VM -or special hardware. KUnit is heavily inspired by JUnit, Python's unittest.mock, and Googletest/Googlemock for C++. KUnit provides facilities for defining unit test cases, grouping related test cases into test suites, providing common infrastructure for running tests, and much more. -Get started now: :doc:`start` - -Why KUnit? -========== - -A unit test is supposed to test a single unit of code in isolation, hence the -name. A unit test should be the finest granularity of testing and as such should -allow all possible code paths to be tested in the code under test; this is only -possible if the code under test is very small and does not have any external -dependencies outside of the test's control like hardware. - -Outside of KUnit, there are no testing frameworks currently -available for the kernel that do not require installing the kernel on a test -machine or in a VM and all require tests to be written in userspace running on -the kernel; this is true for Autotest, and kselftest, disqualifying -any of them from being considered unit testing frameworks. +KUnit consists of a kernel component, which provides a set of macros for easily +writing unit tests. Tests written against KUnit will run on kernel boot if +built-in, or when loaded if built as a module. These tests write out results to +the kernel log in `TAP <https://testanything.org/>`_ format. -KUnit addresses the problem of being able to run tests without needing a virtual -machine or actual hardware with User Mode Linux. User Mode Linux is a Linux -architecture, like ARM or x86; however, unlike other architectures it compiles -to a standalone program that can be run like any other program directly inside -of a host operating system; to be clear, it does not require any virtualization -support; it is just a regular program. +To make running these tests (and reading the results) easier, KUnit offsers +:doc:`kunit_tool <kunit-tool>`, which builds a `User Mode Linux +<http://user-mode-linux.sourceforge.net>`_ kernel, runs it, and parses the test +results. This provides a quick way of running KUnit tests during development. -Alternatively, kunit and kunit tests can be built as modules and tests will -run when the test module is loaded. - -KUnit is fast. Excluding build time, from invocation to completion KUnit can run -several dozen tests in only 10 to 20 seconds; this might not sound like a big -deal to some people, but having such fast and easy to run tests fundamentally -changes the way you go about testing and even writing code in the first place. -Linus himself said in his `git talk at Google -<https://gist.github.com/lorn/1272686/revisions#diff-53c65572127855f1b003db4…>`_: - - "... a lot of people seem to think that performance is about doing the - same thing, just doing it faster, and that is not true. That is not what - performance is all about. If you can do something really fast, really - well, people will start using it differently." - -In this context Linus was talking about branching and merging, -but this point also applies to testing. If your tests are slow, unreliable, are -difficult to write, and require a special setup or special hardware to run, -then you wait a lot longer to write tests, and you wait a lot longer to run -tests; this means that tests are likely to break, unlikely to test a lot of -things, and are unlikely to be rerun once they pass. If your tests are really -fast, you run them all the time, every time you make a change, and every time -someone sends you some code. Why trust that someone ran all their tests -correctly on every change when you can just run them yourself in less time than -it takes to read their test log? +Get started now: :doc:`start` How do I use it? ================ @@ -81,3 +41,5 @@ How do I use it? * :doc:`start` - for new users of KUnit * :doc:`usage` - for a more detailed explanation of KUnit features * :doc:`api/index` - for the list of KUnit APIs used for testing +* :doc:`kunit-tool` - for more information on the kunit_tool helper script +* :doc:`faq` - for answers to some common questions about KUnit diff --git a/Documentation/dev-tools/kunit/start.rst b/Documentation/dev-tools/kunit/start.rst index 4e1d24db6b13..e1c5ce80ce12 100644 --- a/Documentation/dev-tools/kunit/start.rst +++ b/Documentation/dev-tools/kunit/start.rst @@ -9,11 +9,10 @@ Installing dependencies KUnit has the same dependencies as the Linux kernel. As long as you can build the kernel, you can run KUnit. -KUnit Wrapper -============= -Included with KUnit is a simple Python wrapper that helps format the output to -easily use and read KUnit output. It handles building and running the kernel, as -well as formatting the output. +Running tests with the KUnit Wrapper +==================================== +Included with KUnit is a simple Python wrapper which runs tests under User Mode +Linux, and formats the test results. The wrapper can be run with: @@ -21,22 +20,42 @@ The wrapper can be run with: ./tools/testing/kunit/kunit.py run --defconfig -For more information on this wrapper (also called kunit_tool) checkout the +For more information on this wrapper (also called kunit_tool) check out the :doc:`kunit-tool` page. Creating a .kunitconfig -======================= -The Python script is a thin wrapper around Kbuild. As such, it needs to be -configured with a ``.kunitconfig`` file. This file essentially contains the -regular Kernel config, with the specific test targets as well. - +----------------------- +If you want to run a specific set of tests (rather than those listed in the +KUnit defconfig), you can provide Kconfig options in the ``.kunitconfig`` file. +This file essentially contains the regular Kernel config, with the specific +test targets as well. The ``.kunitconfig`` should also contain any other config +options required by the tests. + +A good starting point for a ``.kunitconfig`` is the KUnit defconfig: .. code-block:: bash cd $PATH_TO_LINUX_REPO cp arch/um/configs/kunit_defconfig .kunitconfig -Verifying KUnit Works ---------------------- +You can then add any other Kconfig options you wish, e.g.: +.. code-block:: none + + CONFIG_LIST_KUNIT_TEST=y + +:doc:`kunit_tool <kunit-tool>` will ensure that all config options set in +``.kunitconfig`` are set in the kernel ``.config`` before running the tests. +It'll warn you if you haven't included the dependencies of the options you're +using. + +.. note:: + Note that removing something from the ``.kunitconfig`` will not trigger a + rebuild of the ``.config`` file: the configuration is only updated if the + ``.kunitconfig`` is not a subset of ``.config``. This means that you can use + other tools (such as make menuconfig) to adjust other config options. + + +Running the tests +----------------- To make sure that everything is set up correctly, simply invoke the Python wrapper from your kernel repo: @@ -62,6 +81,41 @@ followed by a list of tests that are run. All of them should be passing. Because it is building a lot of sources for the first time, the ``Building KUnit kernel`` step may take a while. +Running tests without the KUnit Wrapper +======================================= + +If you'd rather not use the KUnit Wrapper (if, for example, you need to +integrate with other systems, or use an architecture other than UML), KUnit can +be included in any kernel, and the results read out and parsed manually. + +.. note:: + KUnit is not designed for use in a production system, and it's possible that + tests may reduce the stability or security of the system. + + + +Configuring the kernel +---------------------- + +In order to enable KUnit itself, you simply need to enable the ``CONFIG_KUNIT`` +Kconfig option (it's under Kernel Hacking/Kernel Testing and Coverage in +menuconfig). From there, you can enable any KUnit tests you want: they usually +have config options ending in ``_KUNIT_TEST``. + +KUnit and KUnit tests can be compiled as modules: in this case the tests in a +module will be run when the module is loaded. + +Running the tests +----------------- + +Build and run your kernel as usual. Test output will be written to the kernel +log in `TAP <https://testanything.org/>`_ format. + +.. note:: + It's possible that there will be other lines and/or data interspersed in the + TAP output. + + Writing your first test ======================= -- 2.25.0.341.g760bfbb309-goog

5 years, 3 months

3
2
0 0

[PATCH] Removing a duplicate condition.

by Isaac Young

Signed-off-by: Isaac Young <isaac.young5(a)gmail.com> --- tools/testing/selftests/bpf/prog_tests/select_reuseport.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c index 098bcae5f827..0954c7a8aa08 100644 --- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c +++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c @@ -823,7 +823,7 @@ void test_select_reuseport(void) saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL); saved_tcp_syncookie = read_int_sysctl(TCP_SYNCOOKIE_SYSCTL); - if (saved_tcp_syncookie < 0 || saved_tcp_syncookie < 0) + if (saved_tcp_syncookie < 0) goto out; if (enable_fastopen()) -- 2.24.1

5 years, 3 months

3
2
0 0

next-20200211 kselftest results

by ci_notify＠linaro.org

Summary ------------------------------------------------------------------------ kernel: 5.6.0-rc1 git repo: https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git git branch: master git commit: ac431e2d7b1be81bfe58163b9f81ba79bc987dc3 git describe: next-20200211 Test details: https://qa-reports.linaro.org/lkft/linux-next-oe/build/next-20200211 Regressions (compared to build next-20200117) ------------------------------------------------------------------------ No regressions Fixes (compared to build next-20200117) ------------------------------------------------------------------------ No fixes In total: ------------------------------------------------------------------------ Ran 0 total tests in the following environments and test suites. pass 0 fail 0 xfail 0 skip 0 Environments -------------- - dragonboard-410c - arm64 - hi6220-hikey - arm64 - i386 - juno-r2 - arm64 - x15 - arm - x86_64 Test Suites ----------- Failures ------------------------------------------------------------------------ juno-r2: x15: x86: i386: hi6220-hikey: dragonboard-410c: Skips ------------------------------------------------------------------------ No skips -- Linaro LKFT https://lkft.linaro.org

5 years, 3 months

1
0
0 0

[PATCH] Documentation: kunit: fix Sphinx directive warning

by Randy Dunlap

From: Randy Dunlap <rdunlap(a)infradead.org> Fix Documentation warning due to missing a blank line after a directive: linux/Documentation/dev-tools/kunit/usage.rst:553: WARNING: Error in "code-block" directive: maximum 1 argument(s) allowed, 3 supplied. .. code-block:: bash modprobe example-test Fixes: 6ae2bfd3df06 ("kunit: update documentation to describe module-based build") Signed-off-by: Randy Dunlap <rdunlap(a)infradead.org> Cc: Alan Maguire <alan.maguire(a)oracle.com> Cc: Knut Omang <knut.omang(a)oracle.com> Cc: Brendan Higgins <brendanhiggins(a)google.com> Cc: linux-kselftest(a)vger.kernel.org Cc: kunit-dev(a)googlegroups.com Cc: Shuah Khan <skhan(a)linuxfoundation.org> --- Documentation/dev-tools/kunit/usage.rst | 1 + 1 file changed, 1 insertion(+) --- lnx-56-rc1.orig/Documentation/dev-tools/kunit/usage.rst +++ lnx-56-rc1/Documentation/dev-tools/kunit/usage.rst @@ -551,6 +551,7 @@ options to your ``.config``: Once the kernel is built and installed, a simple .. code-block:: bash + modprobe example-test ...will run the tests.

5 years, 3 months

3
2
0 0

[RESEND PATCH v9 00/13] selftests/resctrl: Add resctrl selftest

by Fenghua Yu

[Resend the v9 patch set to Shuah Khan and linux-kselftest mailing list. No code and commit message change.] With more and more resctrl features are being added by Intel, AMD and ARM, a test tool is becoming more and more useful to validate that both hardware and software functionalities work as expected. We introduce resctrl selftest to cover resctrl features on X86, AMD and ARM architectures. It first implements MBM (Memory Bandwidth Monitoring), MBA (Memory Bandwidth Allocation), L3 CAT (Cache Allocation Technology), and CQM (Cache QoS Monitoring) tests. We will enhance the selftest tool to include more functionality tests in the future. The tool has been tested on Intel RDT, AMD QoS and ARM MPAM and is in tools/testing/selftests/resctrl in order to have generic test code base for all architectures. The selftest tool we are introducing here provides a convenient tool which does automatic resctrl testing, is easily available in kernel tree, and covers Intel RDT, AMD QoS and ARM MPAM. There is an existing resctrl test suite 'intel_cmt_cat'. But its major purpose is to test Intel RDT hardware via writing and reading MSR registers. It does access resctrl file system; but the functionalities are very limited. And it doesn't support automatic test and a lot of manual verifications are involved. Changelog: v9: - Per Boris suggestion, add Co-developed-by in each patch to make it clear who contributed to the patch set. v8: Update code per comments from Andre Przywara from ARM: - Change Makefile and remove inline assembly code to build and test the tool on ARM - Change the output to TAP format because the format is both readable by human and other test tools. - Detect resctrl feature from /proc/cpuinfo instead of dmesg to support generic detection on all architectures. - Fix a few coding issues. v7: - Fix a few warnings when compiling patches separately, pointed by Babu v6: - Fix a benchmark reading optimized out issue in newer GCC. - Fix a few coding style issues. - Re-arrange code among patches to make cleaner code. No change in patches structure. v5: - Based the v4 patches submitted by Fenghua Yu and added changes to support AMD. - Changed the function name get_sock_num to get_resource_id. Intel uses socket number for schemata and AMD uses l3 index id. To generalize, changed the function name to get_resource_id. - Added the code to detect vendor. - Disabled the few tests for AMD where the test results are not clear. Also AMD does not have IMC. - Fixed few compile issues. - Some cleanup to make each patch independent. - Tested the patches on AMD system. Fenghua, Need your help to test on Intel box. Please feel free to change and resubmit if something broken. v4: - address comments from Balu and Randy - Add CAT and CQM tests v3: - Change code based on comments from Babu Moger - Remove some unnessary code and use pipe to communicate b/w processes v2: - Change code based on comments from Babu Moger - Clean up other places. Babu Moger (3): selftests/resctrl: Add vendor detection mechanism selftests/resctrl: Use cache index3 id for AMD schemata masks selftests/resctrl: Disable MBA and MBM tests for AMD Fenghua Yu (6): selftests/resctrl: Add README for resctrl tests selftests/resctrl: Add MBM test selftests/resctrl: Add MBA test selftests/resctrl: Add Cache QoS Monitoring (CQM) selftest selftests/resctrl: Add Cache Allocation Technology (CAT) selftest selftests/resctrl: Add the test in MAINTAINERS Sai Praneeth Prakhya (4): selftests/resctrl: Add basic resctrl file system operations and data selftests/resctrl: Read memory bandwidth from perf IMC counter and from resctrl file system selftests/resctrl: Add callback to start a benchmark selftests/resctrl: Add built in benchmark MAINTAINERS | 1 + tools/testing/selftests/resctrl/Makefile | 17 + tools/testing/selftests/resctrl/README | 53 ++ tools/testing/selftests/resctrl/cache.c | 272 +++++++ tools/testing/selftests/resctrl/cat_test.c | 250 ++++++ tools/testing/selftests/resctrl/cqm_test.c | 176 +++++ tools/testing/selftests/resctrl/fill_buf.c | 213 +++++ tools/testing/selftests/resctrl/mba_test.c | 171 ++++ tools/testing/selftests/resctrl/mbm_test.c | 145 ++++ tools/testing/selftests/resctrl/resctrl.h | 107 +++ .../testing/selftests/resctrl/resctrl_tests.c | 202 +++++ tools/testing/selftests/resctrl/resctrl_val.c | 744 ++++++++++++++++++ tools/testing/selftests/resctrl/resctrlfs.c | 722 +++++++++++++++++ 13 files changed, 3073 insertions(+) create mode 100644 tools/testing/selftests/resctrl/Makefile create mode 100644 tools/testing/selftests/resctrl/README create mode 100644 tools/testing/selftests/resctrl/cache.c create mode 100644 tools/testing/selftests/resctrl/cat_test.c create mode 100644 tools/testing/selftests/resctrl/cqm_test.c create mode 100644 tools/testing/selftests/resctrl/fill_buf.c create mode 100644 tools/testing/selftests/resctrl/mba_test.c create mode 100644 tools/testing/selftests/resctrl/mbm_test.c create mode 100644 tools/testing/selftests/resctrl/resctrl.h create mode 100644 tools/testing/selftests/resctrl/resctrl_tests.c create mode 100644 tools/testing/selftests/resctrl/resctrl_val.c create mode 100644 tools/testing/selftests/resctrl/resctrlfs.c -- 2.19.1

5 years, 3 months

2
15
0 0

[PATCH v5 00/12] mm/gup: track FOLL_PIN pages

by John Hubbard

Hi, Here's another update after another round of reviews from Kirill and Jan. There is a git repo and branch, for convenience in reviewing: git@github.com:johnhubbard/linux.git track_user_pages_v5 ============================================================ Changes since v4: * Added documentation about the huge page behavior of the new /proc/vmstat items. * Added a missing mode_node_page_state() call to put_compound_head(). * Fixed a tracepoint call in page_ref_sub_return(). * Added a trailing underscore to a URL in pin_user_pages.rst, to fix a broken generated link. * Added ACKs and reviewed-by's from Jan Kara and Kirill Shutemov. * Rebased onto today's linux.git, and * I am experimenting here with "git format-patch --base=<commit>". This generated the "base-commit:" tag you'll see at the end of this cover letter. I was inspired to do so after trying out a new get-lore-mbox.py tool (it's very nice), mentioned in a recent LWN article (https://lwn.net/Articles/811528/ ). That tool relies on the base-commit tag for some things. ============================================================ Changes since v3: * Rebased onto latest linux.git * Added ACKs and reviewed-by's from Kirill Shutemov and Jan Kara. * /proc/vmstat: * Renamed items, after realizing that I hate the previous names: nr_foll_pin_requested --> nr_foll_pin_acquired nr_foll_pin_returned --> nr_foll_pin_released * Removed the CONFIG_DEBUG_VM guard, and collapsed away a wrapper routine: now just calls mod_node_page_state() directly. * Tweaked the WARN_ON_ONCE() statements in mm/hugetlb.c to be more informative, and added comments above them as well. * Fixed gup_benchmark: signed int --> unsigned long. * One or two minor formatting changes. ============================================================ Changes since v2: * Rebased onto linux.git, because the akpm tree for 5.6 has been merged. * Split the tracking patch into even more patches, as requested. * Merged Matthew Wilcox's dump_page() changes into mine, as part of the first patch. * Renamed: page_dma_pinned() --> page_maybe_dma_pinned(), in response to Kirill Shutemov's review. * Moved a WARN to the top of a routine, and fixed a typo in the commit description of patch #7, also as suggested by Kirill. ============================================================ Changes since v1: * Split the tracking patch into 6 smaller patches * Rebased onto today's linux-next/akpm (there weren't any conflicts). * Fixed an "unsigned int" vs. "int" problem in gup_benchmark, reported by Nathan Chancellor. (I don't see it in my local builds, probably because they use gcc, but an LLVM test found the mismatch.) * Fixed a huge page pincount problem (add/subtract vs. increment/decrement), spotted by Jan Kara. ============================================================ There is a reasonable case to be made for merging two of the patches (patches 7 and 8), given that patch 7 provides tracking that has upper limits on the number of pins that can be done with huge pages. Let me know if anyone wants those merged, but unless there is some weird chance of someone grabbing patch 7 and not patch 8, I don't really see the need. Meanwhile, it's easier to review in this form. Also, patch 3 has been revived. Earlier reviewers asked for it to be merged into the tracking patch (one cannot please everyone, heh), but now it's back out on it's own. This activates tracking of FOLL_PIN pages. This is in support of fixing the get_user_pages()+DMA problem described in [1]-[4]. FOLL_PIN support is now in the main linux tree. However, the patch to use FOLL_PIN to track pages was *not* submitted, because Leon saw an RDMA test suite failure that involved (I think) page refcount overflows when huge pages were used. This patch definitively solves that kind of overflow problem, by adding an exact pincount, for compound pages (of order > 1), in the 3rd struct page of a compound page. If available, that form of pincounting is used, instead of the GUP_PIN_COUNTING_BIAS approach. Thanks again to Jan Kara for that idea. Other interesting changes: * dump_page(): added one, or two new things to report for compound pages: head refcount (for all compound pages), and map_pincount (for compound pages of order > 1). * Documentation/core-api/pin_user_pages.rst: removed the "TODO" for the huge page refcount upper limit problems, and added notes about how it works now. Also added a note about the dump_page() enhancements. * Added some comments in gup.c and mm.h, to explain that there are two ways to count pinned pages: exact (for compound pages of order > 1) and fuzzy (GUP_PIN_COUNTING_BIAS: for all other pages). ============================================================ General notes about the tracking patch: This is a prerequisite to solving the problem of proper interactions between file-backed pages, and [R]DMA activities, as discussed in [1], [2], [3], [4] and in a remarkable number of email threads since about 2017. :) In contrast to earlier approaches, the page tracking can be incrementally applied to the kernel call sites that, until now, have been simply calling get_user_pages() ("gup"). In other words, opt-in by changing from this: get_user_pages() (sets FOLL_GET) put_page() to this: pin_user_pages() (sets FOLL_PIN) unpin_user_page() ============================================================ Next steps: * Convert more subsystems from get_user_pages() to pin_user_pages(). * Work with Ira and others to connect this all up with file system leases. [1] Some slow progress on get_user_pages() (Apr 2, 2019): https://lwn.net/Articles/784574/ [2] DMA and get_user_pages() (LPC: Dec 12, 2018): https://lwn.net/Articles/774411/ [3] The trouble with get_user_pages() (Apr 30, 2018): https://lwn.net/Articles/753027/ [4] LWN kernel index: get_user_pages() https://lwn.net/Kernel/Index/#Memory_management-get_user_pages John Hubbard (12): mm: dump_page(): better diagnostics for compound pages mm/gup: split get_user_pages_remote() into two routines mm/gup: pass a flags arg to __gup_device_* functions mm: introduce page_ref_sub_return() mm/gup: pass gup flags to two more routines mm/gup: require FOLL_GET for get_user_pages_fast() mm/gup: track FOLL_PIN pages mm/gup: page->hpage_pinned_refcount: exact pin counts for huge pages mm: dump_page(): better diagnostics for huge pinned pages mm/gup: /proc/vmstat: pin_user_pages (FOLL_PIN) reporting mm/gup_benchmark: support pin_user_pages() and related calls selftests/vm: run_vmtests: invoke gup_benchmark with basic FOLL_PIN coverage Documentation/core-api/pin_user_pages.rst | 86 ++-- include/linux/mm.h | 108 ++++- include/linux/mm_types.h | 7 +- include/linux/mmzone.h | 2 + include/linux/page_ref.h | 9 + mm/debug.c | 61 ++- mm/gup.c | 452 ++++++++++++++++----- mm/gup_benchmark.c | 71 +++- mm/huge_memory.c | 29 +- mm/hugetlb.c | 60 ++- mm/page_alloc.c | 2 + mm/rmap.c | 6 + mm/vmstat.c | 2 + tools/testing/selftests/vm/gup_benchmark.c | 15 +- tools/testing/selftests/vm/run_vmtests | 22 + 15 files changed, 752 insertions(+), 180 deletions(-) base-commit: 90568ecf561540fa330511e21fcd823b0c3829c6 -- 2.25.0

5 years, 3 months

4
19
0 0

Re: linux-5.6-rc1/tools/testing/selftests/bpf/prog_tests/select_reuseport.cc :826: possible cut-n-paste error ?

by Martin KaFai Lau

On Mon, Feb 10, 2020 at 01:42:45PM +0000, David Binderman wrote: > Hello there, > > saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL); > saved_tcp_syncookie = read_int_sysctl(TCP_SYNCOOKIE_SYSCTL); > if (saved_tcp_syncookie < 0 || saved_tcp_syncookie < 0) > goto out; > > Maybe better code > > saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL); > saved_tcp_syncookie = read_int_sysctl(TCP_SYNCOOKIE_SYSCTL); > if (saved_tcp_fo < 0 || saved_tcp_syncookie < 0) Thanks for the report. I will post a fix.

5 years, 3 months

1
0
0 0

[PATCH v26 20/22] selftests/x86: Add vDSO selftest for SGX

by Jarkko Sakkinen

Expand the selftest by invoking the enclave by using __vdso_sgx_enter_enclave() in addition to direct ENCLS[EENTER]. Cc: linux-kselftest(a)vger.kernel.org Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen(a)linux.intel.com> --- tools/testing/selftests/x86/sgx/main.c | 132 +++++++++++++++++++++ tools/testing/selftests/x86/sgx/sgx_call.S | 43 +++++++ tools/testing/selftests/x86/sgx/sgx_call.h | 3 + 3 files changed, 178 insertions(+) diff --git a/tools/testing/selftests/x86/sgx/main.c b/tools/testing/selftests/x86/sgx/main.c index 48ed5fdfb3cb..d97cc3cf0093 100644 --- a/tools/testing/selftests/x86/sgx/main.c +++ b/tools/testing/selftests/x86/sgx/main.c @@ -21,6 +21,109 @@ #define PAGE_SIZE 4096 static const uint64_t MAGIC = 0x1122334455667788ULL; +void *eenter; + +struct vdso_symtab { + Elf64_Sym *elf_symtab; + const char *elf_symstrtab; + Elf64_Word *elf_hashtab; +}; + +static void *vdso_get_base_addr(char *envp[]) +{ + Elf64_auxv_t *auxv; + int i; + + for (i = 0; envp[i]; i++) + ; + + auxv = (Elf64_auxv_t *)&envp[i + 1]; + + for (i = 0; auxv[i].a_type != AT_NULL; i++) { + if (auxv[i].a_type == AT_SYSINFO_EHDR) + return (void *)auxv[i].a_un.a_val; + } + + return NULL; +} + +static Elf64_Dyn *vdso_get_dyntab(void *addr) +{ + Elf64_Ehdr *ehdr = addr; + Elf64_Phdr *phdrtab = addr + ehdr->e_phoff; + int i; + + for (i = 0; i < ehdr->e_phnum; i++) + if (phdrtab[i].p_type == PT_DYNAMIC) + return addr + phdrtab[i].p_offset; + + return NULL; +} + +static void *vdso_get_dyn(void *addr, Elf64_Dyn *dyntab, Elf64_Sxword tag) +{ + int i; + + for (i = 0; dyntab[i].d_tag != DT_NULL; i++) + if (dyntab[i].d_tag == tag) + return addr + dyntab[i].d_un.d_ptr; + + return NULL; +} + +static bool vdso_get_symtab(void *addr, struct vdso_symtab *symtab) +{ + Elf64_Dyn *dyntab = vdso_get_dyntab(addr); + + symtab->elf_symtab = vdso_get_dyn(addr, dyntab, DT_SYMTAB); + if (!symtab->elf_symtab) + return false; + + symtab->elf_symstrtab = vdso_get_dyn(addr, dyntab, DT_STRTAB); + if (!symtab->elf_symstrtab) + return false; + + symtab->elf_hashtab = vdso_get_dyn(addr, dyntab, DT_HASH); + if (!symtab->elf_hashtab) + return false; + + return true; +} + +static unsigned long elf_sym_hash(const char *name) +{ + unsigned long h = 0, high; + + while (*name) { + h = (h << 4) + *name++; + high = h & 0xf0000000; + + if (high) + h ^= high >> 24; + + h &= ~high; + } + + return h; +} + +static Elf64_Sym *vdso_symtab_get(struct vdso_symtab *symtab, const char *name) +{ + Elf64_Word bucketnum = symtab->elf_hashtab[0]; + Elf64_Word *buckettab = &symtab->elf_hashtab[2]; + Elf64_Word *chaintab = &symtab->elf_hashtab[2 + bucketnum]; + Elf64_Sym *sym; + Elf64_Word i; + + for (i = buckettab[elf_sym_hash(name) % bucketnum]; i != STN_UNDEF; + i = chaintab[i]) { + sym = &symtab->elf_symtab[i]; + if (!strcmp(name, &symtab->elf_symstrtab[sym->st_name])) + return sym; + } + + return NULL; +} static bool encl_create(int dev_fd, unsigned long bin_size, struct sgx_secs *secs) @@ -218,10 +321,14 @@ bool load_sigstruct(const char *path, void *sigstruct) int main(int argc, char *argv[], char *envp[]) { + struct sgx_enclave_exception exception; struct sgx_sigstruct sigstruct; + struct vdso_symtab symtab; + Elf64_Sym *eenter_sym; struct sgx_secs secs; uint64_t result = 0; off_t bin_size; + void *addr; void *bin; if (!encl_data_map("encl.bin", &bin, &bin_size)) @@ -243,5 +350,30 @@ int main(int argc, char *argv[], char *envp[]) printf("Output: 0x%lx\n", result); + memset(&exception, 0, sizeof(exception)); + + addr = vdso_get_base_addr(envp); + if (!addr) + exit(1); + + if (!vdso_get_symtab(addr, &symtab)) + exit(1); + + eenter_sym = vdso_symtab_get(&symtab, "__vdso_sgx_enter_enclave"); + if (!eenter_sym) + exit(1); + eenter = addr + eenter_sym->st_value; + + printf("Input: 0x%lx\n", MAGIC); + + sgx_call_vdso((void *)&MAGIC, &result, 0, NULL, NULL, NULL, + (void *)secs.base, &exception, NULL); + if (result != MAGIC) { + fprintf(stderr, "0x%lx != 0x%lx\n", result, MAGIC); + exit(1); + } + + printf("Output: 0x%lx\n", result); + exit(0); } diff --git a/tools/testing/selftests/x86/sgx/sgx_call.S b/tools/testing/selftests/x86/sgx/sgx_call.S index ca4c7893f9d9..e71f44f7a995 100644 --- a/tools/testing/selftests/x86/sgx/sgx_call.S +++ b/tools/testing/selftests/x86/sgx/sgx_call.S @@ -21,3 +21,46 @@ sgx_async_exit: ENCLU pop %rbx ret + + .global sgx_call_vdso +sgx_call_vdso: + .cfi_startproc + push %r15 + .cfi_adjust_cfa_offset 8 + .cfi_rel_offset %r15, 0 + push %r14 + .cfi_adjust_cfa_offset 8 + .cfi_rel_offset %r14, 0 + push %r13 + .cfi_adjust_cfa_offset 8 + .cfi_rel_offset %r13, 0 + push %r12 + .cfi_adjust_cfa_offset 8 + .cfi_rel_offset %r12, 0 + push %rbx + .cfi_adjust_cfa_offset 8 + .cfi_rel_offset %rbx, 0 + push $0 + .cfi_adjust_cfa_offset 8 + push 0x48(%rsp) + .cfi_adjust_cfa_offset 8 + push 0x48(%rsp) + .cfi_adjust_cfa_offset 8 + push 0x48(%rsp) + .cfi_adjust_cfa_offset 8 + mov $2, %eax + call *eenter(%rip) + add $0x20, %rsp + .cfi_adjust_cfa_offset -0x20 + pop %rbx + .cfi_adjust_cfa_offset -8 + pop %r12 + .cfi_adjust_cfa_offset -8 + pop %r13 + .cfi_adjust_cfa_offset -8 + pop %r14 + .cfi_adjust_cfa_offset -8 + pop %r15 + .cfi_adjust_cfa_offset -8 + ret + .cfi_endproc diff --git a/tools/testing/selftests/x86/sgx/sgx_call.h b/tools/testing/selftests/x86/sgx/sgx_call.h index bf72068ada23..a4072c5ecce7 100644 --- a/tools/testing/selftests/x86/sgx/sgx_call.h +++ b/tools/testing/selftests/x86/sgx/sgx_call.h @@ -8,4 +8,7 @@ void sgx_call_eenter(void *rdi, void *rsi, void *entry); +int sgx_call_vdso(void *rdi, void *rsi, long rdx, void *rcx, void *r8, void *r9, + void *tcs, struct sgx_enclave_exception *ei, void *cb); + #endif /* SGX_CALL_H */ -- 2.20.1

5 years, 3 months

1
0
0 0

[PATCH v26 12/22] selftests/x86: Add a selftest for SGX

by Jarkko Sakkinen

Add a selftest for SGX. It is a trivial test where a simple enclave copies one 64-bit word of memory between two memory locations given to the enclave as arguments. Use ENCLS[EENTER] to invoke the enclave. Cc: linux-sgx(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen(a)linux.intel.com> --- tools/testing/selftests/x86/sgx/.gitignore | 3 + tools/testing/selftests/x86/sgx/Makefile | 48 ++ tools/testing/selftests/x86/sgx/defines.h | 17 + tools/testing/selftests/x86/sgx/encl.c | 20 + tools/testing/selftests/x86/sgx/encl.lds | 34 ++ .../selftests/x86/sgx/encl_bootstrap.S | 94 ++++ tools/testing/selftests/x86/sgx/main.c | 247 +++++++++ tools/testing/selftests/x86/sgx/sgx_call.S | 23 + tools/testing/selftests/x86/sgx/sgx_call.h | 11 + tools/testing/selftests/x86/sgx/sgxsign.c | 493 ++++++++++++++++++ .../testing/selftests/x86/sgx/signing_key.pem | 39 ++ 11 files changed, 1029 insertions(+) create mode 100644 tools/testing/selftests/x86/sgx/.gitignore create mode 100644 tools/testing/selftests/x86/sgx/Makefile create mode 100644 tools/testing/selftests/x86/sgx/defines.h create mode 100644 tools/testing/selftests/x86/sgx/encl.c create mode 100644 tools/testing/selftests/x86/sgx/encl.lds create mode 100644 tools/testing/selftests/x86/sgx/encl_bootstrap.S create mode 100644 tools/testing/selftests/x86/sgx/main.c create mode 100644 tools/testing/selftests/x86/sgx/sgx_call.S create mode 100644 tools/testing/selftests/x86/sgx/sgx_call.h create mode 100644 tools/testing/selftests/x86/sgx/sgxsign.c create mode 100644 tools/testing/selftests/x86/sgx/signing_key.pem diff --git a/tools/testing/selftests/x86/sgx/.gitignore b/tools/testing/selftests/x86/sgx/.gitignore new file mode 100644 index 000000000000..98eb2d439606 --- /dev/null +++ b/tools/testing/selftests/x86/sgx/.gitignore @@ -0,0 +1,3 @@ +encl.ss +sgxsign +test_sgx diff --git a/tools/testing/selftests/x86/sgx/Makefile b/tools/testing/selftests/x86/sgx/Makefile new file mode 100644 index 000000000000..f838700029e2 --- /dev/null +++ b/tools/testing/selftests/x86/sgx/Makefile @@ -0,0 +1,48 @@ +top_srcdir = ../../../../.. + +include ../../lib.mk + +ifndef OBJCOPY +OBJCOPY := $(CROSS_COMPILE)objcopy +endif + +INCLUDES := -I$(top_srcdir)/tools/include +HOST_CFLAGS := -Wall -Werror -g $(INCLUDES) -fPIC -z noexecstack +ENCL_CFLAGS := -Wall -Werror -static -nostdlib -nostartfiles -fPIC \ + -fno-stack-protector -mrdrnd $(INCLUDES) + +TEST_CUSTOM_PROGS := $(OUTPUT)/test_sgx $(OUTPUT)/encl.bin $(OUTPUT)/encl.ss + +all: $(TEST_CUSTOM_PROGS) + +$(OUTPUT)/test_sgx: $(OUTPUT)/main.o $(OUTPUT)/sgx_call.o + $(CC) $(HOST_CFLAGS) -o $@ $^ + +$(OUTPUT)/main.o: main.c + $(CC) $(HOST_CFLAGS) -c $< -o $@ + +$(OUTPUT)/sgx_call.o: sgx_call.S + $(CC) $(HOST_CFLAGS) -c $< -o $@ + +$(OUTPUT)/encl.bin: $(OUTPUT)/encl.elf $(OUTPUT)/sgxsign + $(OBJCOPY) -O binary $< $@ + +$(OUTPUT)/encl.elf: encl.lds encl.c encl_bootstrap.S + $(CC) $(ENCL_CFLAGS) -T $^ -o $@ + +$(OUTPUT)/encl.ss: $(OUTPUT)/encl.bin + $(OUTPUT)/sgxsign signing_key.pem $(OUTPUT)/encl.bin $(OUTPUT)/encl.ss + +$(OUTPUT)/sgxsign: sgxsign.c + $(CC) $(INCLUDES) -o $@ $< -lcrypto + +EXTRA_CLEAN := \ + $(OUTPUT)/encl.bin \ + $(OUTPUT)/encl.elf \ + $(OUTPUT)/encl.ss \ + $(OUTPUT)/sgx_call.o \ + $(OUTPUT)/sgxsign \ + $(OUTPUT)/test_sgx \ + $(OUTPUT)/test_sgx.o \ + +.PHONY: clean diff --git a/tools/testing/selftests/x86/sgx/defines.h b/tools/testing/selftests/x86/sgx/defines.h new file mode 100644 index 000000000000..87264f85cb9f --- /dev/null +++ b/tools/testing/selftests/x86/sgx/defines.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright(c) 2016-19 Intel Corporation. + */ + +#ifndef DEFINES_H +#define DEFINES_H + +#include <stdint.h> + +#define __aligned(x) __attribute__((__aligned__(x))) +#define __packed __attribute__((packed)) + +#include "../../../../../arch/x86/kernel/cpu/sgx/arch.h" +#include "../../../../../arch/x86/include/uapi/asm/sgx.h" + +#endif /* DEFINES_H */ diff --git a/tools/testing/selftests/x86/sgx/encl.c b/tools/testing/selftests/x86/sgx/encl.c new file mode 100644 index 000000000000..ede915399742 --- /dev/null +++ b/tools/testing/selftests/x86/sgx/encl.c @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) +// Copyright(c) 2016-18 Intel Corporation. + +#include <stddef.h> +#include "defines.h" + +static void *memcpy(void *dest, const void *src, size_t n) +{ + size_t i; + + for (i = 0; i < n; i++) + ((char *)dest)[i] = ((char *)src)[i]; + + return dest; +} + +void encl_body(void *rdi, void *rsi) +{ + memcpy(rsi, rdi, 8); +} diff --git a/tools/testing/selftests/x86/sgx/encl.lds b/tools/testing/selftests/x86/sgx/encl.lds new file mode 100644 index 000000000000..9a56d3064104 --- /dev/null +++ b/tools/testing/selftests/x86/sgx/encl.lds @@ -0,0 +1,34 @@ +OUTPUT_FORMAT(elf64-x86-64) + +SECTIONS +{ + . = 0; + .tcs : { + *(.tcs*) + } + + . = ALIGN(4096); + .text : { + *(.text*) + *(.rodata*) + } + + . = ALIGN(4096); + .data : { + *(.data*) + } + + /DISCARD/ : { + *(.data*) + *(.comment*) + *(.note*) + *(.debug*) + *(.eh_frame*) + } +} + +ASSERT(!DEFINED(.altinstructions), "ALTERNATIVES are not supported in enclaves") +ASSERT(!DEFINED(.altinstr_replacement), "ALTERNATIVES are not supported in enclaves") +ASSERT(!DEFINED(.discard.retpoline_safe), "RETPOLINE ALTERNATIVES are not supported in enclaves") +ASSERT(!DEFINED(.discard.nospec), "RETPOLINE ALTERNATIVES are not supported in enclaves") +ASSERT(!DEFINED(.got.plt), "Libcalls are not supported in enclaves") diff --git a/tools/testing/selftests/x86/sgx/encl_bootstrap.S b/tools/testing/selftests/x86/sgx/encl_bootstrap.S new file mode 100644 index 000000000000..d07f970ccdf9 --- /dev/null +++ b/tools/testing/selftests/x86/sgx/encl_bootstrap.S @@ -0,0 +1,94 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ +/* + * Copyright(c) 2016-18 Intel Corporation. + */ + + .macro ENCLU + .byte 0x0f, 0x01, 0xd7 + .endm + + .section ".tcs", "a" + .balign 4096 + + .fill 1, 8, 0 # STATE (set by CPU) + .fill 1, 8, 0 # FLAGS + .quad encl_ssa # OSSA + .fill 1, 4, 0 # CSSA (set by CPU) + .fill 1, 4, 1 # NSSA + .quad encl_entry # OENTRY + .fill 1, 8, 0 # AEP (set by EENTER and ERESUME) + .fill 1, 8, 0 # OFSBASE + .fill 1, 8, 0 # OGSBASE + .fill 1, 4, 0xFFFFFFFF # FSLIMIT + .fill 1, 4, 0xFFFFFFFF # GSLIMIT + .fill 4024, 1, 0 # Reserved + + .text + +encl_entry: + # RBX contains the base address for TCS, which is also the first address + # inside the enclave. By adding the value of le_stack_end to it, we get + # the absolute address for the stack. + lea (encl_stack)(%rbx), %rax + xchg %rsp, %rax + push %rax + + push %rcx # push the address after EENTER + push %rbx # push the enclave base address + + call encl_body + + pop %rbx # pop the enclave base address + + # Restore XSAVE registers to a synthetic state. + mov $0xFFFFFFFF, %rax + mov $0xFFFFFFFF, %rdx + lea (xsave_area)(%rbx), %rdi + fxrstor (%rdi) + + # Clear GPRs. + xor %rcx, %rcx + xor %rdx, %rdx + xor %rdi, %rdi + xor %rsi, %rsi + xor %r8, %r8 + xor %r9, %r9 + xor %r10, %r10 + xor %r11, %r11 + xor %r12, %r12 + xor %r13, %r13 + xor %r14, %r14 + xor %r15, %r15 + + # Reset status flags. + add %rdx, %rdx # OF = SF = AF = CF = 0; ZF = PF = 1 + + # Prepare EEXIT target by popping the address of the instruction after + # EENTER to RBX. + pop %rbx + + # Restore the caller stack. + pop %rax + mov %rax, %rsp + + # EEXIT + mov $4, %rax + enclu + + .section ".data", "aw" + +encl_ssa: + .space 4096 + +xsave_area: + .fill 1, 4, 0x037F # FCW + .fill 5, 4, 0 + .fill 1, 4, 0x1F80 # MXCSR + .fill 1, 4, 0xFFFF # MXCSR_MASK + .fill 123, 4, 0 + .fill 1, 4, 0x80000000 # XCOMP_BV[63] = 1, compaction mode + .fill 12, 4, 0 + + .balign 4096 + .space 8192 +encl_stack: diff --git a/tools/testing/selftests/x86/sgx/main.c b/tools/testing/selftests/x86/sgx/main.c new file mode 100644 index 000000000000..48ed5fdfb3cb --- /dev/null +++ b/tools/testing/selftests/x86/sgx/main.c @@ -0,0 +1,247 @@ +// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) +// Copyright(c) 2016-18 Intel Corporation. + +#include <elf.h> +#include <errno.h> +#include <fcntl.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdint.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <sys/stat.h> +#include <sys/time.h> +#include <sys/types.h> +#include "defines.h" +#include "sgx_call.h" + +#define PAGE_SIZE 4096 + +static const uint64_t MAGIC = 0x1122334455667788ULL; + +static bool encl_create(int dev_fd, unsigned long bin_size, + struct sgx_secs *secs) +{ + struct sgx_enclave_create ioc; + void *area; + int rc; + + memset(secs, 0, sizeof(*secs)); + secs->ssa_frame_size = 1; + secs->attributes = SGX_ATTR_MODE64BIT; + secs->xfrm = 3; + + for (secs->size = 4096; secs->size < bin_size; ) + secs->size <<= 1; + + area = mmap(NULL, secs->size * 2, PROT_NONE, MAP_SHARED, dev_fd, 0); + if (area == MAP_FAILED) { + perror("mmap"); + return false; + } + + secs->base = ((uint64_t)area + secs->size - 1) & ~(secs->size - 1); + + munmap(area, secs->base - (uint64_t)area); + munmap((void *)(secs->base + secs->size), + (uint64_t)area + secs->size - secs->base); + + ioc.src = (unsigned long)secs; + rc = ioctl(dev_fd, SGX_IOC_ENCLAVE_CREATE, &ioc); + if (rc) { + fprintf(stderr, "ECREATE failed rc=%d, err=%d.\n", rc, errno); + munmap((void *)secs->base, secs->size); + return false; + } + + return true; +} + +static bool encl_add_pages(int dev_fd, unsigned long offset, void *data, + unsigned long length, uint64_t flags) +{ + struct sgx_enclave_add_pages ioc; + struct sgx_secinfo secinfo; + int rc; + + memset(&secinfo, 0, sizeof(secinfo)); + secinfo.flags = flags; + + ioc.src = (uint64_t)data; + ioc.offset = offset; + ioc.length = length; + ioc.secinfo = (unsigned long)&secinfo; + ioc.flags = SGX_PAGE_MEASURE; + + rc = ioctl(dev_fd, SGX_IOC_ENCLAVE_ADD_PAGES, &ioc); + if (rc) { + fprintf(stderr, "EADD failed rc=%d.\n", rc); + return false; + } + + if (ioc.count != ioc.length) { + fprintf(stderr, "Partially processed, update the test.\n"); + return false; + } + + return true; +} + +#define SGX_REG_PAGE_FLAGS \ + (SGX_SECINFO_REG | SGX_SECINFO_R | SGX_SECINFO_W | SGX_SECINFO_X) + +static bool encl_build(struct sgx_secs *secs, void *bin, + unsigned long bin_size, struct sgx_sigstruct *sigstruct) +{ + struct sgx_enclave_init ioc; + void *addr; + int dev_fd; + int rc; + + dev_fd = open("/dev/sgx/enclave", O_RDWR); + if (dev_fd < 0) { + fprintf(stderr, "Unable to open /dev/sgx\n"); + return false; + } + + if (!encl_create(dev_fd, bin_size, secs)) + goto out_dev_fd; + + if (!encl_add_pages(dev_fd, 0, bin, PAGE_SIZE, SGX_SECINFO_TCS)) + goto out_dev_fd; + + if (!encl_add_pages(dev_fd, PAGE_SIZE, bin + PAGE_SIZE, + bin_size - PAGE_SIZE, SGX_REG_PAGE_FLAGS)) + goto out_dev_fd; + + ioc.sigstruct = (uint64_t)sigstruct; + rc = ioctl(dev_fd, SGX_IOC_ENCLAVE_INIT, &ioc); + if (rc) { + printf("EINIT failed rc=%d\n", rc); + goto out_map; + } + + addr = mmap((void *)secs->base, PAGE_SIZE, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_FIXED, dev_fd, 0); + if (addr == MAP_FAILED) { + fprintf(stderr, "mmap() failed on TCS, errno=%d.\n", errno); + return false; + } + + addr = mmap((void *)(secs->base + PAGE_SIZE), bin_size - PAGE_SIZE, + PROT_READ | PROT_WRITE | PROT_EXEC, + MAP_SHARED | MAP_FIXED, dev_fd, 0); + if (addr == MAP_FAILED) { + fprintf(stderr, "mmap() failed, errno=%d.\n", errno); + return false; + } + + close(dev_fd); + return true; +out_map: + munmap((void *)secs->base, secs->size); +out_dev_fd: + close(dev_fd); + return false; +} + +bool get_file_size(const char *path, off_t *bin_size) +{ + struct stat sb; + int ret; + + ret = stat(path, &sb); + if (ret) { + perror("stat"); + return false; + } + + if (!sb.st_size || sb.st_size & 0xfff) { + fprintf(stderr, "Invalid blob size %lu\n", sb.st_size); + return false; + } + + *bin_size = sb.st_size; + return true; +} + +bool encl_data_map(const char *path, void **bin, off_t *bin_size) +{ + int fd; + + fd = open(path, O_RDONLY); + if (fd == -1) { + fprintf(stderr, "open() %s failed, errno=%d.\n", path, errno); + return false; + } + + if (!get_file_size(path, bin_size)) + goto err_out; + + *bin = mmap(NULL, *bin_size, PROT_READ, MAP_PRIVATE, fd, 0); + if (*bin == MAP_FAILED) { + fprintf(stderr, "mmap() %s failed, errno=%d.\n", path, errno); + goto err_out; + } + + close(fd); + return true; + +err_out: + close(fd); + return false; +} + +bool load_sigstruct(const char *path, void *sigstruct) +{ + int fd; + + fd = open(path, O_RDONLY); + if (fd == -1) { + fprintf(stderr, "open() %s failed, errno=%d.\n", path, errno); + return false; + } + + if (read(fd, sigstruct, sizeof(struct sgx_sigstruct)) != + sizeof(struct sgx_sigstruct)) { + fprintf(stderr, "read() %s failed, errno=%d.\n", path, errno); + close(fd); + return false; + } + + close(fd); + return true; +} + +int main(int argc, char *argv[], char *envp[]) +{ + struct sgx_sigstruct sigstruct; + struct sgx_secs secs; + uint64_t result = 0; + off_t bin_size; + void *bin; + + if (!encl_data_map("encl.bin", &bin, &bin_size)) + exit(1); + + if (!load_sigstruct("encl.ss", &sigstruct)) + exit(1); + + if (!encl_build(&secs, bin, bin_size, &sigstruct)) + exit(1); + + printf("Input: 0x%lx\n", MAGIC); + + sgx_call_eenter((void *)&MAGIC, &result, (void *)secs.base); + if (result != MAGIC) { + fprintf(stderr, "0x%lx != 0x%lx\n", result, MAGIC); + exit(1); + } + + printf("Output: 0x%lx\n", result); + + exit(0); +} diff --git a/tools/testing/selftests/x86/sgx/sgx_call.S b/tools/testing/selftests/x86/sgx/sgx_call.S new file mode 100644 index 000000000000..ca4c7893f9d9 --- /dev/null +++ b/tools/testing/selftests/x86/sgx/sgx_call.S @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ +/** +* Copyright(c) 2016-18 Intel Corporation. +*/ + + .text + + .macro ENCLU + .byte 0x0f, 0x01, 0xd7 + .endm + + .text + + .global sgx_call_eenter +sgx_call_eenter: + push %rbx + mov $0x02, %rax + mov %rdx, %rbx + lea sgx_async_exit(%rip), %rcx +sgx_async_exit: + ENCLU + pop %rbx + ret diff --git a/tools/testing/selftests/x86/sgx/sgx_call.h b/tools/testing/selftests/x86/sgx/sgx_call.h new file mode 100644 index 000000000000..bf72068ada23 --- /dev/null +++ b/tools/testing/selftests/x86/sgx/sgx_call.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright(c) 2016-19 Intel Corporation. + */ + +#ifndef SGX_CALL_H +#define SGX_CALL_H + +void sgx_call_eenter(void *rdi, void *rsi, void *entry); + +#endif /* SGX_CALL_H */ diff --git a/tools/testing/selftests/x86/sgx/sgxsign.c b/tools/testing/selftests/x86/sgx/sgxsign.c new file mode 100644 index 000000000000..3d9007af40c9 --- /dev/null +++ b/tools/testing/selftests/x86/sgx/sgxsign.c @@ -0,0 +1,493 @@ +// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) +// Copyright(c) 2016-18 Intel Corporation. + +#define _GNU_SOURCE +#include <getopt.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> +#include <openssl/err.h> +#include <openssl/pem.h> +#include "defines.h" + +struct sgx_sigstruct_payload { + struct sgx_sigstruct_header header; + struct sgx_sigstruct_body body; +}; + +static bool check_crypto_errors(void) +{ + int err; + bool had_errors = false; + const char *filename; + int line; + char str[256]; + + for ( ; ; ) { + if (ERR_peek_error() == 0) + break; + + had_errors = true; + err = ERR_get_error_line(&filename, &line); + ERR_error_string_n(err, str, sizeof(str)); + fprintf(stderr, "crypto: %s: %s:%d\n", str, filename, line); + } + + return had_errors; +} + +static void exit_usage(const char *program) +{ + fprintf(stderr, + "Usage: %s/sign-le <key> <enclave> <sigstruct>\n", program); + exit(1); +} + +static inline const BIGNUM *get_modulus(RSA *key) +{ +#if OPENSSL_VERSION_NUMBER < 0x10100000L + return key->n; +#else + const BIGNUM *n; + + RSA_get0_key(key, &n, NULL, NULL); + return n; +#endif +} + +static RSA *load_sign_key(const char *path) +{ + FILE *f; + RSA *key; + + f = fopen(path, "rb"); + if (!f) { + fprintf(stderr, "Unable to open %s\n", path); + return NULL; + } + key = RSA_new(); + if (!PEM_read_RSAPrivateKey(f, &key, NULL, NULL)) + return NULL; + fclose(f); + + if (BN_num_bytes(get_modulus(key)) != SGX_MODULUS_SIZE) { + fprintf(stderr, "Invalid key size %d\n", + BN_num_bytes(get_modulus(key))); + RSA_free(key); + return NULL; + } + + return key; +} + +static void reverse_bytes(void *data, int length) +{ + int i = 0; + int j = length - 1; + uint8_t temp; + uint8_t *ptr = data; + + while (i < j) { + temp = ptr[i]; + ptr[i] = ptr[j]; + ptr[j] = temp; + i++; + j--; + } +} + +enum mrtags { + MRECREATE = 0x0045544145524345, + MREADD = 0x0000000044444145, + MREEXTEND = 0x00444E4554584545, +}; + +static bool mrenclave_update(EVP_MD_CTX *ctx, const void *data) +{ + if (!EVP_DigestUpdate(ctx, data, 64)) { + fprintf(stderr, "digest update failed\n"); + return false; + } + + return true; +} + +static bool mrenclave_commit(EVP_MD_CTX *ctx, uint8_t *mrenclave) +{ + unsigned int size; + + if (!EVP_DigestFinal_ex(ctx, (unsigned char *)mrenclave, &size)) { + fprintf(stderr, "digest commit failed\n"); + return false; + } + + if (size != 32) { + fprintf(stderr, "invalid digest size = %u\n", size); + return false; + } + + return true; +} + +struct mrecreate { + uint64_t tag; + uint32_t ssaframesize; + uint64_t size; + uint8_t reserved[44]; +} __attribute__((__packed__)); + + +static bool mrenclave_ecreate(EVP_MD_CTX *ctx, uint64_t blob_size) +{ + struct mrecreate mrecreate; + uint64_t encl_size; + + for (encl_size = 0x1000; encl_size < blob_size; ) + encl_size <<= 1; + + memset(&mrecreate, 0, sizeof(mrecreate)); + mrecreate.tag = MRECREATE; + mrecreate.ssaframesize = 1; + mrecreate.size = encl_size; + + if (!EVP_DigestInit_ex(ctx, EVP_sha256(), NULL)) + return false; + + return mrenclave_update(ctx, &mrecreate); +} + +struct mreadd { + uint64_t tag; + uint64_t offset; + uint64_t flags; /* SECINFO flags */ + uint8_t reserved[40]; +} __attribute__((__packed__)); + +static bool mrenclave_eadd(EVP_MD_CTX *ctx, uint64_t offset, uint64_t flags) +{ + struct mreadd mreadd; + + memset(&mreadd, 0, sizeof(mreadd)); + mreadd.tag = MREADD; + mreadd.offset = offset; + mreadd.flags = flags; + + return mrenclave_update(ctx, &mreadd); +} + +struct mreextend { + uint64_t tag; + uint64_t offset; + uint8_t reserved[48]; +} __attribute__((__packed__)); + +static bool mrenclave_eextend(EVP_MD_CTX *ctx, uint64_t offset, uint8_t *data) +{ + struct mreextend mreextend; + int i; + + for (i = 0; i < 0x1000; i += 0x100) { + memset(&mreextend, 0, sizeof(mreextend)); + mreextend.tag = MREEXTEND; + mreextend.offset = offset + i; + + if (!mrenclave_update(ctx, &mreextend)) + return false; + + if (!mrenclave_update(ctx, &data[i + 0x00])) + return false; + + if (!mrenclave_update(ctx, &data[i + 0x40])) + return false; + + if (!mrenclave_update(ctx, &data[i + 0x80])) + return false; + + if (!mrenclave_update(ctx, &data[i + 0xC0])) + return false; + } + + return true; +} + +/** + * measure_encl - measure enclave + * @path: path to the enclave + * @mrenclave: measurement + * + * Calculates MRENCLAVE. Assumes that the very first page is a TCS page and + * following pages are regular pages. Does not measure the contents of the + * enclave as the signing tool is used at the moment only for the launch + * enclave, which is pass-through (everything gets a token). + */ +static bool measure_encl(const char *path, uint8_t *mrenclave) +{ + FILE *file; + struct stat sb; + EVP_MD_CTX *ctx; + uint64_t flags; + uint64_t offset; + uint8_t data[0x1000]; + int rc; + + ctx = EVP_MD_CTX_create(); + if (!ctx) + return false; + + file = fopen(path, "rb"); + if (!file) { + perror("fopen"); + EVP_MD_CTX_destroy(ctx); + return false; + } + + rc = stat(path, &sb); + if (rc) { + perror("stat"); + goto out; + } + + if (!sb.st_size || sb.st_size & 0xfff) { + fprintf(stderr, "Invalid blob size %lu\n", sb.st_size); + goto out; + } + + if (!mrenclave_ecreate(ctx, sb.st_size)) + goto out; + + for (offset = 0; offset < sb.st_size; offset += 0x1000) { + if (!offset) + flags = SGX_SECINFO_TCS; + else + flags = SGX_SECINFO_REG | SGX_SECINFO_R | + SGX_SECINFO_W | SGX_SECINFO_X; + + if (!mrenclave_eadd(ctx, offset, flags)) + goto out; + + rc = fread(data, 1, 0x1000, file); + if (!rc) + break; + if (rc < 0x1000) + goto out; + + if (!mrenclave_eextend(ctx, offset, data)) + goto out; + } + + if (!mrenclave_commit(ctx, mrenclave)) + goto out; + + fclose(file); + EVP_MD_CTX_destroy(ctx); + return true; +out: + fclose(file); + EVP_MD_CTX_destroy(ctx); + return false; +} + +/** + * sign_encl - sign enclave + * @sigstruct: pointer to SIGSTRUCT + * @key: 3072-bit RSA key + * @signature: byte array for the signature + * + * Calculates EMSA-PKCSv1.5 signature for the given SIGSTRUCT. The result is + * stored in big-endian format so that it can be further passed to OpenSSL + * libcrypto functions. + */ +static bool sign_encl(const struct sgx_sigstruct *sigstruct, RSA *key, + uint8_t *signature) +{ + struct sgx_sigstruct_payload payload; + unsigned int siglen; + uint8_t digest[SHA256_DIGEST_LENGTH]; + bool ret; + + memcpy(&payload.header, &sigstruct->header, sizeof(sigstruct->header)); + memcpy(&payload.body, &sigstruct->body, sizeof(sigstruct->body)); + + SHA256((unsigned char *)&payload, sizeof(payload), digest); + + ret = RSA_sign(NID_sha256, digest, SHA256_DIGEST_LENGTH, signature, + &siglen, key); + + return ret; +} + +struct q1q2_ctx { + BN_CTX *bn_ctx; + BIGNUM *m; + BIGNUM *s; + BIGNUM *q1; + BIGNUM *qr; + BIGNUM *q2; +}; + +static void free_q1q2_ctx(struct q1q2_ctx *ctx) +{ + BN_CTX_free(ctx->bn_ctx); + BN_free(ctx->m); + BN_free(ctx->s); + BN_free(ctx->q1); + BN_free(ctx->qr); + BN_free(ctx->q2); +} + +static bool alloc_q1q2_ctx(const uint8_t *s, const uint8_t *m, + struct q1q2_ctx *ctx) +{ + ctx->bn_ctx = BN_CTX_new(); + ctx->s = BN_bin2bn(s, SGX_MODULUS_SIZE, NULL); + ctx->m = BN_bin2bn(m, SGX_MODULUS_SIZE, NULL); + ctx->q1 = BN_new(); + ctx->qr = BN_new(); + ctx->q2 = BN_new(); + + if (!ctx->bn_ctx || !ctx->s || !ctx->m || !ctx->q1 || !ctx->qr || + !ctx->q2) { + free_q1q2_ctx(ctx); + return false; + } + + return true; +} + +static bool calc_q1q2(const uint8_t *s, const uint8_t *m, uint8_t *q1, + uint8_t *q2) +{ + struct q1q2_ctx ctx; + + if (!alloc_q1q2_ctx(s, m, &ctx)) { + fprintf(stderr, "Not enough memory for Q1Q2 calculation\n"); + return false; + } + + if (!BN_mul(ctx.q1, ctx.s, ctx.s, ctx.bn_ctx)) + goto out; + + if (!BN_div(ctx.q1, ctx.qr, ctx.q1, ctx.m, ctx.bn_ctx)) + goto out; + + if (BN_num_bytes(ctx.q1) > SGX_MODULUS_SIZE) { + fprintf(stderr, "Too large Q1 %d bytes\n", + BN_num_bytes(ctx.q1)); + goto out; + } + + if (!BN_mul(ctx.q2, ctx.s, ctx.qr, ctx.bn_ctx)) + goto out; + + if (!BN_div(ctx.q2, NULL, ctx.q2, ctx.m, ctx.bn_ctx)) + goto out; + + if (BN_num_bytes(ctx.q2) > SGX_MODULUS_SIZE) { + fprintf(stderr, "Too large Q2 %d bytes\n", + BN_num_bytes(ctx.q2)); + goto out; + } + + BN_bn2bin(ctx.q1, q1); + BN_bn2bin(ctx.q2, q2); + + free_q1q2_ctx(&ctx); + return true; +out: + free_q1q2_ctx(&ctx); + return false; +} + +static bool save_sigstruct(const struct sgx_sigstruct *sigstruct, + const char *path) +{ + FILE *f = fopen(path, "wb"); + + if (!f) { + fprintf(stderr, "Unable to open %s\n", path); + return false; + } + + fwrite(sigstruct, sizeof(*sigstruct), 1, f); + fclose(f); + return true; +} + +int main(int argc, char **argv) +{ + uint64_t header1[2] = {0x000000E100000006, 0x0000000000010000}; + uint64_t header2[2] = {0x0000006000000101, 0x0000000100000060}; + struct sgx_sigstruct ss; + const char *program; + int opt; + RSA *sign_key; + + memset(&ss, 0, sizeof(ss)); + ss.header.header1[0] = header1[0]; + ss.header.header1[1] = header1[1]; + ss.header.header2[0] = header2[0]; + ss.header.header2[1] = header2[1]; + ss.exponent = 3; + +#ifndef CONFIG_EINITTOKENKEY + ss.body.attributes = SGX_ATTR_MODE64BIT; +#else + ss.body.attributes = SGX_ATTR_MODE64BIT | SGX_ATTR_EINITTOKENKEY; +#endif + ss.body.xfrm = 3, + + program = argv[0]; + + do { + opt = getopt(argc, argv, ""); + switch (opt) { + case -1: + break; + default: + exit_usage(program); + } + } while (opt != -1); + + argc -= optind; + argv += optind; + + if (argc < 3) + exit_usage(program); + + /* sanity check only */ + if (check_crypto_errors()) + exit(1); + + sign_key = load_sign_key(argv[0]); + if (!sign_key) + goto out; + + BN_bn2bin(get_modulus(sign_key), ss.modulus); + + if (!measure_encl(argv[1], ss.body.mrenclave)) + goto out; + + if (!sign_encl(&ss, sign_key, ss.signature)) + goto out; + + if (!calc_q1q2(ss.signature, ss.modulus, ss.q1, ss.q2)) + goto out; + + /* convert to little endian */ + reverse_bytes(ss.signature, SGX_MODULUS_SIZE); + reverse_bytes(ss.modulus, SGX_MODULUS_SIZE); + reverse_bytes(ss.q1, SGX_MODULUS_SIZE); + reverse_bytes(ss.q2, SGX_MODULUS_SIZE); + + if (!save_sigstruct(&ss, argv[2])) + goto out; + exit(0); +out: + check_crypto_errors(); + exit(1); +} diff --git a/tools/testing/selftests/x86/sgx/signing_key.pem b/tools/testing/selftests/x86/sgx/signing_key.pem new file mode 100644 index 000000000000..d76f21f19187 --- /dev/null +++ b/tools/testing/selftests/x86/sgx/signing_key.pem @@ -0,0 +1,39 @@ +-----BEGIN RSA PRIVATE KEY----- +MIIG4wIBAAKCAYEApalGbq7Q+usM91CPtksu3D+b0Prc8gAFL6grM3mg85A5Bx8V +cfMXPgtrw8EYFwQxDAvzZWwl+9VfOX0ECrFRBkOHcOiG0SnADN8+FLj1UiNUQwbp +S6OzhNWuRcSbGraSOyUlVlV0yMQSvewyzGklOaXBe30AJqzIBc8QfdSxKuP8rs0Z +ga6k/Bl73osrYKByILJTUUeZqjLERsE6GebsdzbWgKn8qVqng4ZS4yMNg6LeRlH3 ++9CIPgg4jwpSLHcp7dq2qTIB9a0tGe9ayp+5FbucpB6U7ePold0EeRN6RlJGDF9k +L93v8P5ykz5G5gYZ2g0K1X2sHIWV4huxPgv5PXgdyQYbK+6olqj0d5rjYuwX57Ul +k6SroPS1U6UbdCjG5txM+BNGU0VpD0ZhrIRw0leQdnNcCO9sTJuInZrgYacSVJ7u +mtB+uCt+uzUesc+l+xPRYA+9e14lLkZp7AAmo9FvL816XDI09deehJ3i/LmHKCRN +tuqC5TprRjFwUr6dAgEDAoIBgG5w2Z8fNfycs0+LCnmHdJLVEotR6KFVWMpwHMz7 +wKJgJgS/Y6FMuilc8oKAuroCy11dTO5IGVKOP3uorVx2NgQtBPXwWeDGgAiU1A3Q +o4wXjYIEm4fCd63jyYPYZ2ckYXzDbjmOTdstYdPyzIhGGNEZK6eoqsRzMAPfYFPj +IMdCqHSIu6vJw1K7p+myHOsVoWshjODaZnF3LYSA0WaZ8vokjwBxUxuRxQJZjJds +s60XPtmL+qfgWtQFewoG4XL6GuD8FcXccynRRtzrLtFNPIl9BQfWfjBBhTC1/Te1 +0Z6XbZvpdUTD9OfLB7SbR2OUFNpKQgriO0iYVdbW3cr7uu38Zwp4W1TX73DPjoi6 +KNooP6SGWd4mRJW2+dUmSYS4QNG8eVVZswKcploEIXlAKRsOe4kzJJ1iETugIe85 +uX8nd1WYEp65xwoRUg8hqng0MeyveVbXqNKuJG6tzNDt9kgFYo+hmC/oouAW2Dtc +T9jdRAwKJXqA2Eg6OkgXCEv+kwKBwQDYaQiFMlFhsmLlqI+EzCUh7c941/cL7m6U +7j98+8ngl0HgCEcrc10iJVCKakQW3YbPzAx3XkKTaGjWazvvrFarXIGlOud64B8a +iWyQ7VdlnmZnNEdk+C83tI91OQeaTKqRLDGzKh29Ry/jL8Pcbazt+kDgxa0H7qJp +roADUanLQuNkYubpbhFBh3xpa2EExaVq6rF7nIVsD8W9TrbmPKA4LgH7z0iy544D +kVCNYsTjYDdUWP+WiSor8kCnnpjnN9sCgcEAw/eNezUD1UDf6OYFC9+5JZJFn4Tg +mZMyN93JKIb199ffwnjtHUSjcyiWeesXucpzwtGbTcwQnDisSW4oneYKLSEBlBaq +scqiUugyGZZOthFSCbdXYXMViK2vHrKlkse7GxVlROKcEhM/pRBrmjaGO8eWR+D4 +FO2wCXzVs3KgV6j779frw0vC54oHOxc9+Lu1rSHp4i+600koyvL/zF6U/5tZXIvN +YW2yoiQJnjCmVA1pwbwV6KAUTPDTMnBK+YjnAoHBAJBGBa4hi5Z27JkbCliIGMFJ +NPs6pLKe9GNJf6in2+sPgUAFhMeiPhbDiwbxgrnpBIqICE+ULGJFmzmc0p/IOceT +ARjR76dAFLxbnbXzj5kURETNhO36yiUjCk4mBRGIcbYddndxaSjaH+zKgpLzyJ6m +1esuc1qfFvEfAAI2cTIsl5hB70ZJYNZaUvDyQK3ZGPHxy6e9rkgKg9OJz0QoatAe +q/002yHvtAJg4F5B2JeVejg7VQ8GHB1MKxppu0TP5wKBwQCCpQj8zgKOKz/wmViy +lSYZDC5qWJW7t3bP6TDFr06lOpUsUJ4TgxeiGw778g/RMaKB4RIz3WBoJcgw9BsT +7rFza1ZiucchMcGMmswRDt8kC4wGejpA92Owc8oUdxkMhSdnY5jYlxK2t3/DYEe8 +JFl9L7mFQKVjSSAGUzkiTGrlG1Kf5UfXh9dFBq98uilQfSPIwUaWynyM23CHTKqI +Pw3/vOY9sojrnncWwrEUIG7is5vWfWPwargzSzd29YdRBe8CgcEAuRVewK/YeNOX +B7ZG6gKKsfsvrGtY7FPETzLZAHjoVXYNea4LVZ2kn4hBXXlvw/4HD+YqcTt4wmif +5JQlDvjNobUiKJZpzy7hklVhF7wZFl4pCF7Yh43q9iQ7gKTaeUG7MiaK+G8Zz8aY +HW9rsiihbdZkccMvnPfO9334XMxl3HtBRzLstjUlbLB7Sdh+7tZ3JQidCOFNs5pE +XyWwnASPu4tKfDahH1UUTp1uJcq/6716CSWg080avYxFcn75qqsb +-----END RSA PRIVATE KEY----- -- 2.20.1

5 years, 3 months

1
0
0 0

[PATCH v2 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 === 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. The RFC for this patch can be found here: https://lkml.org/lkml/2019/7/30/1399 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 | 356 +++++++++++++++++- .../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, 635 insertions(+), 7 deletions(-) create mode 100644 tools/testing/selftests/futex/functional/futex_wait_multiple.c -- 2.25.0

5 years, 3 months

1
4
0 0

[PATCH] selftests: allow detection of build failures

by Jiri Benc

Commit 5f70bde26a48 ("selftests: fix build behaviour on targets' failures") added a logic to track failure of builds of individual targets. However, it does exactly the opposite of what a distro kernel needs: we create a RPM package with a selected set of selftests and we need the build to fail if build of any of the targets fail. Both use cases are valid. A distribution kernel is in control of what is included in the kernel and what is being built; any error needs to be flagged and acted upon. A CI system that tries to build as many tests as possible on the best effort basis is not really interested in a failure here and there. Support both use cases by introducing a FORCE_TARGETS variable. It is switched off by default to make life for CI systems easier, distributions can easily switch it on while building their packages. Reported-by: Yauheni Kaliuta <yauheni.kaliuta(a)redhat.com> Signed-off-by: Jiri Benc <jbenc(a)redhat.com> --- tools/testing/selftests/Makefile | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 5182d6078cbc..97fca70d2cd6 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -74,6 +74,12 @@ ifneq ($(SKIP_TARGETS),) override TARGETS := $(TMP) endif +# User can set FORCE_TARGETS to 1 to require all targets to be successfully +# built; make will fail if any of the targets cannot be built. If +# FORCE_TARGETS is not set (the default), make will succeed if at least one +# of the targets gets built. +FORCE_TARGETS ?= + # Clear LDFLAGS and MAKEFLAGS if called from main # Makefile to avoid test build failures when test # Makefile doesn't have explicit build rules. @@ -148,7 +154,8 @@ all: khdr for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ mkdir $$BUILD_TARGET -p; \ - $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET \ + $(if $(FORCE_TARGETS),|| exit); \ ret=$$((ret * $$?)); \ done; exit $$ret; @@ -202,7 +209,8 @@ ifdef INSTALL_PATH @ret=1; \ for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ - $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install \ + $(if $(FORCE_TARGETS),|| exit); \ ret=$$((ret * $$?)); \ done; exit $$ret; -- 2.18.1

5 years, 3 months

2
1
0 0

[PATCH] selftests/vm: Add missed tests in run_vmtests

by sj38.park＠gmail.com

From: SeongJae Park <sjpark(a)amazon.de> The commits introducing 'mlock-random-test'[1], 'map_fiex_noreplace'[2], and 'thuge-gen'[3] have not added those in the 'run_vmtests' script and thus the 'run_tests' command of kselftests doesn't run those. This commit adds those in the script. 'gup_benchmark' and 'transhuge-stress' are also not included in the 'run_vmtests', but this commit does not add those because those are for performance measurement rather than pass/fail tests. [1] commit 26b4224d9961 ("selftests: expanding more mlock selftest") [2] commit 91cbacc34512 ("tools/testing/selftests/vm/map_fixed_noreplace.c: add test for MAP_FIXED_NOREPLACE") [3] commit fcc1f2d5dd34 ("selftests: add a test program for variable huge page sizes in mmap/shmget") Signed-off-by: SeongJae Park <sjpark(a)amazon.de> --- tools/testing/selftests/vm/run_vmtests | 33 ++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests index a692ea828317..f33714843198 100755 --- a/tools/testing/selftests/vm/run_vmtests +++ b/tools/testing/selftests/vm/run_vmtests @@ -112,6 +112,17 @@ echo "NOTE: The above hugetlb tests provide minimal coverage. Use" echo " https://github.com/libhugetlbfs/libhugetlbfs.git for" echo " hugetlb regression testing." +echo "---------------------------" +echo "running map_fixed_noreplace" +echo "---------------------------" +./map_fixed_noreplace +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi + echo "-------------------" echo "running userfaultfd" echo "-------------------" @@ -186,6 +197,17 @@ else echo "[PASS]" fi +echo "-------------------------" +echo "running mlock-random-test" +echo "-------------------------" +./mlock-random-test +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi + echo "--------------------" echo "running mlock2-tests" echo "--------------------" @@ -197,6 +219,17 @@ else echo "[PASS]" fi +echo "-----------------" +echo "running thuge-gen" +echo "-----------------" +./thuge-gen +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi + if [ $VADDR64 -ne 0 ]; then echo "-----------------------------" echo "running virtual_address_range" base-commit: d5226fa6dbae0569ee43ecfc08bdcd6770fc4755 -- 2.17.1

5 years, 3 months

1
0
0 0

[PATCH] selftests: fix too long argument

by Jiri Benc

With some shells, the command construed for install of bpf selftests becomes too large due to long list of files: make[1]: execvp: /bin/sh: Argument list too long make[1]: *** [../lib.mk:73: install] Error 127 Currently, each of the file lists is replicated three times in the command: in the shell 'if' condition, in the 'echo' and in the 'rsync'. Reduce that by one instance by using make conditionals and separate the echo and rsync into two shell commands. (One would be inclined to just remove the '@' at the beginning of the rsync command and let 'make' echo it by itself; unfortunately, it appears that the '@' in the front of mkdir silences output also for the following commands.) Also, separate handling of each of the lists to its own shell command. The semantics of the makefile is unchanged before and after the patch. The ability of individual test directories to override INSTALL_RULE is retained. Reported-by: Yauheni Kaliuta <yauheni.kaliuta(a)redhat.com> Tested-by: Yauheni Kaliuta <yauheni.kaliuta(a)redhat.com> Signed-off-by: Jiri Benc <jbenc(a)redhat.com> --- tools/testing/selftests/lib.mk | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 1c8a1963d03f..3ed0134a764d 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -83,17 +83,20 @@ else $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS)) endif +define INSTALL_SINGLE_RULE + $(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH)) + $(if $(INSTALL_LIST),@echo rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/) + $(if $(INSTALL_LIST),@rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/) +endef + define INSTALL_RULE - @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \ - mkdir -p ${INSTALL_PATH}; \ - echo "rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/"; \ - rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/; \ - fi - @if [ "X$(TEST_GEN_PROGS)$(TEST_CUSTOM_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then \ - mkdir -p ${INSTALL_PATH}; \ - echo "rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/"; \ - rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/; \ - fi + $(eval INSTALL_LIST = $(TEST_PROGS)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_FILES)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_GEN_PROGS)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_CUSTOM_PROGS)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_GEN_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_GEN_FILES)) $(INSTALL_SINGLE_RULE) endef install: all -- 2.18.1

5 years, 3 months

1
0
0 0

[PATCH v4 00/12] mm/gup: track FOLL_PIN pages

by John Hubbard

Hi, Here's an update after the latest round of reviews from Kirill and Jan. There is a git repo and branch, for convenience in reviewing: git@github.com:johnhubbard/linux.git track_user_pages_v4 I'm particularly pleased that the /proc/vmstat items are now available in all configurations, seeing as how I was looking (in vain) for that information during a recent investigation of a remotely reported problem. ============================================================ Changes since v3: * Rebased onto latest linux.git * Added ACKs and reviewed-by's from Kirill Shutemov and Jan Kara. * /proc/vmstat: * Renamed items, after realizing that I hate the previous names: nr_foll_pin_requested --> nr_foll_pin_acquired nr_foll_pin_returned --> nr_foll_pin_released * Removed the CONFIG_DEBUG_VM guard, and collapsed away a wrapper routine: now just calls mod_node_page_state() directly. * Tweaked the WARN_ON_ONCE() statements in mm/hugetlb.c to be more informative, and added comments above them as well. * Fixed gup_benchmark: signed int --> unsigned long. * One or two minor formatting changes. ============================================================ Changes since v2: * Rebased onto linux.git, because the akpm tree for 5.6 has been merged. * Split the tracking patch into even more patches, as requested. * Merged Matthew Wilcox's dump_page() changes into mine, as part of the first patch. * Renamed: page_dma_pinned() --> page_maybe_dma_pinned(), in response to Kirill Shutemov's review. * Moved a WARN to the top of a routine, and fixed a typo in the commit description of patch #7, also as suggested by Kirill. ============================================================ Changes since v1: * Split the tracking patch into 6 smaller patches * Rebased onto today's linux-next/akpm (there weren't any conflicts). * Fixed an "unsigned int" vs. "int" problem in gup_benchmark, reported by Nathan Chancellor. (I don't see it in my local builds, probably because they use gcc, but an LLVM test found the mismatch.) * Fixed a huge page pincount problem (add/subtract vs. increment/decrement), spotted by Jan Kara. ============================================================ There is a reasonable case to be made for merging two of the patches (patches 7 and 8), given that patch 7 provides tracking that has upper limits on the number of pins that can be done with huge pages. Let me know if anyone wants those merged, but unless there is some weird chance of someone grabbing patch 7 and not patch 8, I don't really see the need. Meanwhile, it's easier to review in this form. Also, patch 3 has been revived. Earlier reviewers asked for it to be merged into the tracking patch (one cannot please everyone, heh), but now it's back out on it's own. This activates tracking of FOLL_PIN pages. This is in support of fixing the get_user_pages()+DMA problem described in [1]-[4]. FOLL_PIN support is now in the main linux tree. However, the patch to use FOLL_PIN to track pages was *not* submitted, because Leon saw an RDMA test suite failure that involved (I think) page refcount overflows when huge pages were used. This patch definitively solves that kind of overflow problem, by adding an exact pincount, for compound pages (of order > 1), in the 3rd struct page of a compound page. If available, that form of pincounting is used, instead of the GUP_PIN_COUNTING_BIAS approach. Thanks again to Jan Kara for that idea. Other interesting changes: * dump_page(): added one, or two new things to report for compound pages: head refcount (for all compound pages), and map_pincount (for compound pages of order > 1). * Documentation/core-api/pin_user_pages.rst: removed the "TODO" for the huge page refcount upper limit problems, and added notes about how it works now. Also added a note about the dump_page() enhancements. * Added some comments in gup.c and mm.h, to explain that there are two ways to count pinned pages: exact (for compound pages of order > 1) and fuzzy (GUP_PIN_COUNTING_BIAS: for all other pages). ============================================================ General notes about the tracking patch: This is a prerequisite to solving the problem of proper interactions between file-backed pages, and [R]DMA activities, as discussed in [1], [2], [3], [4] and in a remarkable number of email threads since about 2017. :) In contrast to earlier approaches, the page tracking can be incrementally applied to the kernel call sites that, until now, have been simply calling get_user_pages() ("gup"). In other words, opt-in by changing from this: get_user_pages() (sets FOLL_GET) put_page() to this: pin_user_pages() (sets FOLL_PIN) unpin_user_page() ============================================================ Next steps: * Convert more subsystems from get_user_pages() to pin_user_pages(). * Work with Ira and others to connect this all up with file system leases. [1] Some slow progress on get_user_pages() (Apr 2, 2019): https://lwn.net/Articles/784574/ [2] DMA and get_user_pages() (LPC: Dec 12, 2018): https://lwn.net/Articles/774411/ [3] The trouble with get_user_pages() (Apr 30, 2018): https://lwn.net/Articles/753027/ [4] LWN kernel index: get_user_pages() https://lwn.net/Kernel/Index/#Memory_management-get_user_pages John Hubbard (12): mm: dump_page(): better diagnostics for compound pages mm/gup: split get_user_pages_remote() into two routines mm/gup: pass a flags arg to __gup_device_* functions mm: introduce page_ref_sub_return() mm/gup: pass gup flags to two more routines mm/gup: require FOLL_GET for get_user_pages_fast() mm/gup: track FOLL_PIN pages mm/gup: page->hpage_pinned_refcount: exact pin counts for huge pages mm: dump_page(): better diagnostics for huge pinned pages mm/gup: /proc/vmstat: pin_user_pages (FOLL_PIN) reporting mm/gup_benchmark: support pin_user_pages() and related calls selftests/vm: run_vmtests: invoke gup_benchmark with basic FOLL_PIN coverage Documentation/core-api/pin_user_pages.rst | 59 ++- include/linux/mm.h | 108 ++++- include/linux/mm_types.h | 7 +- include/linux/mmzone.h | 2 + include/linux/page_ref.h | 9 + mm/debug.c | 61 ++- mm/gup.c | 448 ++++++++++++++++----- mm/gup_benchmark.c | 71 +++- mm/huge_memory.c | 29 +- mm/hugetlb.c | 60 ++- mm/page_alloc.c | 2 + mm/rmap.c | 6 + mm/vmstat.c | 2 + tools/testing/selftests/vm/gup_benchmark.c | 15 +- tools/testing/selftests/vm/run_vmtests | 22 + 15 files changed, 721 insertions(+), 180 deletions(-) -- 2.25.0

5 years, 3 months

3
20
0 0

[PATCH 1/3] kvm: mmu: Replace unsigned with unsigned int for PTE access

by Ben Gardon

There are several functions which pass an access permission mask for SPTEs as an unsigned. This works, but checkpatch complains about it. Switch the occurrences of unsigned to unsigned int to satisfy checkpatch. No functional change expected. Tested by running kvm-unit-tests on an Intel Haswell machine. This commit introduced no new failures. This commit can be viewed in Gerrit at: https://linux-review.googlesource.com/c/virt/kvm/kvm/+/2358 Signed-off-by: Ben Gardon <bgardon(a)google.com> Reviewed-by: Oliver Upton <oupton(a)google.com> --- arch/x86/kvm/mmu/mmu.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 84eeb61d06aa3..a9c593dec49bf 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -452,7 +452,7 @@ static u64 get_mmio_spte_generation(u64 spte) } static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, - unsigned access) + unsigned int access) { u64 gen = kvm_vcpu_memslots(vcpu)->generation & MMIO_SPTE_GEN_MASK; u64 mask = generation_mmio_spte_mask(gen); @@ -484,7 +484,7 @@ static unsigned get_mmio_spte_access(u64 spte) } static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, - kvm_pfn_t pfn, unsigned access) + kvm_pfn_t pfn, unsigned int access) { if (unlikely(is_noslot_pfn(pfn))) { mark_mmio_spte(vcpu, sptep, gfn, access); @@ -2475,7 +2475,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, gva_t gaddr, unsigned level, int direct, - unsigned access) + unsigned int access) { union kvm_mmu_page_role role; unsigned quadrant; @@ -2990,7 +2990,7 @@ static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) #define SET_SPTE_NEED_REMOTE_TLB_FLUSH BIT(1) static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, - unsigned pte_access, int level, + unsigned int pte_access, int level, gfn_t gfn, kvm_pfn_t pfn, bool speculative, bool can_unsync, bool host_writable) { @@ -3081,9 +3081,10 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, return ret; } -static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, - int write_fault, int level, gfn_t gfn, kvm_pfn_t pfn, - bool speculative, bool host_writable) +static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, + unsigned int pte_access, int write_fault, int level, + gfn_t gfn, kvm_pfn_t pfn, bool speculative, + bool host_writable) { int was_rmapped = 0; int rmap_count; @@ -3165,7 +3166,7 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, { struct page *pages[PTE_PREFETCH_NUM]; struct kvm_memory_slot *slot; - unsigned access = sp->role.access; + unsigned int access = sp->role.access; int i, ret; gfn_t gfn; @@ -3400,7 +3401,8 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) } static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, - kvm_pfn_t pfn, unsigned access, int *ret_val) + kvm_pfn_t pfn, unsigned int access, + int *ret_val) { /* The pfn is invalid, report the error! */ if (unlikely(is_error_pfn(pfn))) { @@ -4005,7 +4007,7 @@ static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct) if (is_mmio_spte(spte)) { gfn_t gfn = get_mmio_spte_gfn(spte); - unsigned access = get_mmio_spte_access(spte); + unsigned int access = get_mmio_spte_access(spte); if (!check_mmio_spte(vcpu, spte)) return RET_PF_INVALID; @@ -4349,7 +4351,7 @@ static void inject_page_fault(struct kvm_vcpu *vcpu, } static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, - unsigned access, int *nr_present) + unsigned int access, int *nr_present) { if (unlikely(is_mmio_spte(*sptep))) { if (gfn != get_mmio_spte_gfn(*sptep)) { -- 2.25.0.341.g760bfbb309-goog

5 years, 3 months

4
8
0 0

[PATCH v6 6/6] selftests/cgroup: add tests for cloning into cgroups

by Christian Brauner

Expand the cgroup test-suite to include tests for CLONE_INTO_CGROUP. This adds the following tests: - CLONE_INTO_CGROUP manages to clone a process directly into a correctly delegated cgroup - CLONE_INTO_CGROUP fails to clone a process into a cgroup that has been removed after we've opened an fd to it - CLONE_INTO_CGROUP fails to clone a process into an invalid domain cgroup - CLONE_INTO_CGROUP adheres to the no internal process constraint - CLONE_INTO_CGROUP works with the freezer feature Cc: Tejun Heo <tj(a)kernel.org> Cc: Shuah Khan <shuah(a)kernel.org> Cc: cgroups(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org Acked-by: Roman Gushchin <guro(a)fb.com> Signed-off-by: Christian Brauner <christian.brauner(a)ubuntu.com> --- /* v1 */ Link: https://lore.kernel.org/r/20191218173516.7875-4-christian.brauner@ubuntu.com /* v2 */ Link: https://lore.kernel.org/r/20191223061504.28716-4-christian.brauner@ubuntu.c… unchanged /* v3 */ Link: https://lore.kernel.org/r/20200117002143.15559-6-christian.brauner@ubuntu.c… unchanged /* v4 */ Link: https://lore.kernel.org/r/20200117181219.14542-7-christian.brauner@ubuntu.c… unchanged /* v5 */ Link: https://lore.kernel.org/r/20200121154844.411-7-christian.brauner@ubuntu.com unchanged - Christian Brauner <christian.brauner(a)ubuntu.com>: - add Acked-by: Roman Gushchin <guro(a)fb.com> /* v6 */ unchanged --- tools/testing/selftests/cgroup/Makefile | 6 +- tools/testing/selftests/cgroup/cgroup_util.c | 126 ++++++++++++++++++ tools/testing/selftests/cgroup/cgroup_util.h | 4 + tools/testing/selftests/cgroup/test_core.c | 64 +++++++++ .../selftests/clone3/clone3_selftests.h | 19 ++- 5 files changed, 214 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile index 66aafe1f5746..967f268fde74 100644 --- a/tools/testing/selftests/cgroup/Makefile +++ b/tools/testing/selftests/cgroup/Makefile @@ -11,6 +11,6 @@ TEST_GEN_PROGS += test_freezer include ../lib.mk -$(OUTPUT)/test_memcontrol: cgroup_util.c -$(OUTPUT)/test_core: cgroup_util.c -$(OUTPUT)/test_freezer: cgroup_util.c +$(OUTPUT)/test_memcontrol: cgroup_util.c ../clone3/clone3_selftests.h +$(OUTPUT)/test_core: cgroup_util.c ../clone3/clone3_selftests.h +$(OUTPUT)/test_freezer: cgroup_util.c ../clone3/clone3_selftests.h diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c index 8f7131dcf1ff..8a637ca7d73a 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.c +++ b/tools/testing/selftests/cgroup/cgroup_util.c @@ -15,6 +15,7 @@ #include <unistd.h> #include "cgroup_util.h" +#include "../clone3/clone3_selftests.h" static ssize_t read_text(const char *path, char *buf, size_t max_len) { @@ -331,12 +332,112 @@ int cg_run(const char *cgroup, } } +pid_t clone_into_cgroup(int cgroup_fd) +{ +#ifdef CLONE_ARGS_SIZE_VER2 + pid_t pid; + + struct clone_args args = { + .flags = CLONE_INTO_CGROUP, + .exit_signal = SIGCHLD, + .cgroup = cgroup_fd, + }; + + pid = sys_clone3(&args, sizeof(struct clone_args)); + /* + * Verify that this is a genuine test failure: + * ENOSYS -> clone3() not available + * E2BIG -> CLONE_INTO_CGROUP not available + */ + if (pid < 0 && (errno == ENOSYS || errno == E2BIG)) + goto pretend_enosys; + + return pid; + +pretend_enosys: +#endif + errno = ENOSYS; + return -ENOSYS; +} + +int clone_reap(pid_t pid, int options) +{ + int ret; + siginfo_t info = { + .si_signo = 0, + }; + +again: + ret = waitid(P_PID, pid, &info, options | __WALL | __WNOTHREAD); + if (ret < 0) { + if (errno == EINTR) + goto again; + return -1; + } + + if (options & WEXITED) { + if (WIFEXITED(info.si_status)) + return WEXITSTATUS(info.si_status); + } + + if (options & WSTOPPED) { + if (WIFSTOPPED(info.si_status)) + return WSTOPSIG(info.si_status); + } + + if (options & WCONTINUED) { + if (WIFCONTINUED(info.si_status)) + return 0; + } + + return -1; +} + +int dirfd_open_opath(const char *dir) +{ + return open(dir, O_DIRECTORY | O_CLOEXEC | O_NOFOLLOW | O_PATH); +} + +#define close_prot_errno(fd) \ + if (fd >= 0) { \ + int _e_ = errno; \ + close(fd); \ + errno = _e_; \ + } + +static int clone_into_cgroup_run_nowait(const char *cgroup, + int (*fn)(const char *cgroup, void *arg), + void *arg) +{ + int cgroup_fd; + pid_t pid; + + cgroup_fd = dirfd_open_opath(cgroup); + if (cgroup_fd < 0) + return -1; + + pid = clone_into_cgroup(cgroup_fd); + close_prot_errno(cgroup_fd); + if (pid == 0) + exit(fn(cgroup, arg)); + + return pid; +} + int cg_run_nowait(const char *cgroup, int (*fn)(const char *cgroup, void *arg), void *arg) { int pid; + pid = clone_into_cgroup_run_nowait(cgroup, fn, arg); + if (pid > 0) + return pid; + + /* Genuine test failure. */ + if (pid < 0 && errno != ENOSYS) + return -1; + pid = fork(); if (pid == 0) { char buf[64]; @@ -450,3 +551,28 @@ int proc_read_strstr(int pid, bool thread, const char *item, const char *needle) return strstr(buf, needle) ? 0 : -1; } + +int clone_into_cgroup_run_wait(const char *cgroup) +{ + int cgroup_fd; + pid_t pid; + + cgroup_fd = dirfd_open_opath(cgroup); + if (cgroup_fd < 0) + return -1; + + pid = clone_into_cgroup(cgroup_fd); + close_prot_errno(cgroup_fd); + if (pid < 0) + return -1; + + if (pid == 0) + exit(EXIT_SUCCESS); + + /* + * We don't care whether this fails. We only care whether the initial + * clone succeeded. + */ + (void)clone_reap(pid, WEXITED); + return 0; +} diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h index 49c54fbdb229..5a1305dd1f0b 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.h +++ b/tools/testing/selftests/cgroup/cgroup_util.h @@ -50,3 +50,7 @@ extern int cg_wait_for_proc_count(const char *cgroup, int count); extern int cg_killall(const char *cgroup); extern ssize_t proc_read_text(int pid, bool thread, const char *item, char *buf, size_t size); extern int proc_read_strstr(int pid, bool thread, const char *item, const char *needle); +extern pid_t clone_into_cgroup(int cgroup_fd); +extern int clone_reap(pid_t pid, int options); +extern int clone_into_cgroup_run_wait(const char *cgroup); +extern int dirfd_open_opath(const char *dir); diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c index c5ca669feb2b..96e016ccafe0 100644 --- a/tools/testing/selftests/cgroup/test_core.c +++ b/tools/testing/selftests/cgroup/test_core.c @@ -25,8 +25,11 @@ static int test_cgcore_populated(const char *root) { int ret = KSFT_FAIL; + int err; char *cg_test_a = NULL, *cg_test_b = NULL; char *cg_test_c = NULL, *cg_test_d = NULL; + int cgroup_fd = -EBADF; + pid_t pid; cg_test_a = cg_name(root, "cg_test_a"); cg_test_b = cg_name(root, "cg_test_a/cg_test_b"); @@ -78,6 +81,52 @@ static int test_cgcore_populated(const char *root) if (cg_read_strcmp(cg_test_d, "cgroup.events", "populated 0\n")) goto cleanup; + /* Test that we can directly clone into a new cgroup. */ + cgroup_fd = dirfd_open_opath(cg_test_d); + if (cgroup_fd < 0) + goto cleanup; + + pid = clone_into_cgroup(cgroup_fd); + if (pid < 0) { + if (errno == ENOSYS) + goto cleanup_pass; + goto cleanup; + } + + if (pid == 0) { + if (raise(SIGSTOP)) + exit(EXIT_FAILURE); + exit(EXIT_SUCCESS); + } + + err = cg_read_strcmp(cg_test_d, "cgroup.events", "populated 1\n"); + + (void)clone_reap(pid, WSTOPPED); + (void)kill(pid, SIGCONT); + (void)clone_reap(pid, WEXITED); + + if (err) + goto cleanup; + + if (cg_read_strcmp(cg_test_d, "cgroup.events", "populated 0\n")) + goto cleanup; + + /* Remove cgroup. */ + if (cg_test_d) { + cg_destroy(cg_test_d); + free(cg_test_d); + cg_test_d = NULL; + } + + pid = clone_into_cgroup(cgroup_fd); + if (pid < 0) + goto cleanup_pass; + if (pid == 0) + exit(EXIT_SUCCESS); + (void)clone_reap(pid, WEXITED); + goto cleanup; + +cleanup_pass: ret = KSFT_PASS; cleanup: @@ -93,6 +142,8 @@ static int test_cgcore_populated(const char *root) free(cg_test_c); free(cg_test_b); free(cg_test_a); + if (cgroup_fd >= 0) + close(cgroup_fd); return ret; } @@ -136,6 +187,16 @@ static int test_cgcore_invalid_domain(const char *root) if (errno != EOPNOTSUPP) goto cleanup; + if (!clone_into_cgroup_run_wait(child)) + goto cleanup; + + if (errno == ENOSYS) + goto cleanup_pass; + + if (errno != EOPNOTSUPP) + goto cleanup; + +cleanup_pass: ret = KSFT_PASS; cleanup: @@ -345,6 +406,9 @@ static int test_cgcore_internal_process_constraint(const char *root) if (!cg_enter_current(parent)) goto cleanup; + if (!clone_into_cgroup_run_wait(parent)) + goto cleanup; + ret = KSFT_PASS; cleanup: diff --git a/tools/testing/selftests/clone3/clone3_selftests.h b/tools/testing/selftests/clone3/clone3_selftests.h index a3f2c8ad8bcc..91c1a78ddb39 100644 --- a/tools/testing/selftests/clone3/clone3_selftests.h +++ b/tools/testing/selftests/clone3/clone3_selftests.h @@ -5,12 +5,24 @@ #define _GNU_SOURCE #include <sched.h> +#include <linux/sched.h> +#include <linux/types.h> #include <stdint.h> #include <syscall.h> -#include <linux/types.h> +#include <sys/wait.h> + +#include "../kselftest.h" #define ptr_to_u64(ptr) ((__u64)((uintptr_t)(ptr))) +#ifndef CLONE_INTO_CGROUP +#define CLONE_INTO_CGROUP 0x200000000ULL /* Clone into a specific cgroup given the right permissions. */ +#endif + +#ifndef CLONE_ARGS_SIZE_VER0 +#define CLONE_ARGS_SIZE_VER0 64 +#endif + #ifndef __NR_clone3 #define __NR_clone3 -1 struct clone_args { @@ -22,10 +34,13 @@ struct clone_args { __aligned_u64 stack; __aligned_u64 stack_size; __aligned_u64 tls; +#define CLONE_ARGS_SIZE_VER1 80 __aligned_u64 set_tid; __aligned_u64 set_tid_size; +#define CLONE_ARGS_SIZE_VER2 88 + __aligned_u64 cgroup; }; -#endif +#endif /* __NR_clone3 */ static pid_t sys_clone3(struct clone_args *args, size_t size) { -- 2.25.0

5 years, 3 months

1
0
0 0

[PATCH v25 20/21] selftests/x86: Add vDSO selftest for SGX

by Jarkko Sakkinen

Expand the selftest by invoking the enclave by using __vdso_sgx_enter_enclave() in addition to direct ENCLS[EENTER]. Cc: linux-kselftest(a)vger.kernel.org Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen(a)linux.intel.com> --- tools/testing/selftests/x86/sgx/main.c | 132 +++++++++++++++++++++ tools/testing/selftests/x86/sgx/sgx_call.S | 43 +++++++ tools/testing/selftests/x86/sgx/sgx_call.h | 3 + 3 files changed, 178 insertions(+) diff --git a/tools/testing/selftests/x86/sgx/main.c b/tools/testing/selftests/x86/sgx/main.c index 48ed5fdfb3cb..d97cc3cf0093 100644 --- a/tools/testing/selftests/x86/sgx/main.c +++ b/tools/testing/selftests/x86/sgx/main.c @@ -21,6 +21,109 @@ #define PAGE_SIZE 4096 static const uint64_t MAGIC = 0x1122334455667788ULL; +void *eenter; + +struct vdso_symtab { + Elf64_Sym *elf_symtab; + const char *elf_symstrtab; + Elf64_Word *elf_hashtab; +}; + +static void *vdso_get_base_addr(char *envp[]) +{ + Elf64_auxv_t *auxv; + int i; + + for (i = 0; envp[i]; i++) + ; + + auxv = (Elf64_auxv_t *)&envp[i + 1]; + + for (i = 0; auxv[i].a_type != AT_NULL; i++) { + if (auxv[i].a_type == AT_SYSINFO_EHDR) + return (void *)auxv[i].a_un.a_val; + } + + return NULL; +} + +static Elf64_Dyn *vdso_get_dyntab(void *addr) +{ + Elf64_Ehdr *ehdr = addr; + Elf64_Phdr *phdrtab = addr + ehdr->e_phoff; + int i; + + for (i = 0; i < ehdr->e_phnum; i++) + if (phdrtab[i].p_type == PT_DYNAMIC) + return addr + phdrtab[i].p_offset; + + return NULL; +} + +static void *vdso_get_dyn(void *addr, Elf64_Dyn *dyntab, Elf64_Sxword tag) +{ + int i; + + for (i = 0; dyntab[i].d_tag != DT_NULL; i++) + if (dyntab[i].d_tag == tag) + return addr + dyntab[i].d_un.d_ptr; + + return NULL; +} + +static bool vdso_get_symtab(void *addr, struct vdso_symtab *symtab) +{ + Elf64_Dyn *dyntab = vdso_get_dyntab(addr); + + symtab->elf_symtab = vdso_get_dyn(addr, dyntab, DT_SYMTAB); + if (!symtab->elf_symtab) + return false; + + symtab->elf_symstrtab = vdso_get_dyn(addr, dyntab, DT_STRTAB); + if (!symtab->elf_symstrtab) + return false; + + symtab->elf_hashtab = vdso_get_dyn(addr, dyntab, DT_HASH); + if (!symtab->elf_hashtab) + return false; + + return true; +} + +static unsigned long elf_sym_hash(const char *name) +{ + unsigned long h = 0, high; + + while (*name) { + h = (h << 4) + *name++; + high = h & 0xf0000000; + + if (high) + h ^= high >> 24; + + h &= ~high; + } + + return h; +} + +static Elf64_Sym *vdso_symtab_get(struct vdso_symtab *symtab, const char *name) +{ + Elf64_Word bucketnum = symtab->elf_hashtab[0]; + Elf64_Word *buckettab = &symtab->elf_hashtab[2]; + Elf64_Word *chaintab = &symtab->elf_hashtab[2 + bucketnum]; + Elf64_Sym *sym; + Elf64_Word i; + + for (i = buckettab[elf_sym_hash(name) % bucketnum]; i != STN_UNDEF; + i = chaintab[i]) { + sym = &symtab->elf_symtab[i]; + if (!strcmp(name, &symtab->elf_symstrtab[sym->st_name])) + return sym; + } + + return NULL; +} static bool encl_create(int dev_fd, unsigned long bin_size, struct sgx_secs *secs) @@ -218,10 +321,14 @@ bool load_sigstruct(const char *path, void *sigstruct) int main(int argc, char *argv[], char *envp[]) { + struct sgx_enclave_exception exception; struct sgx_sigstruct sigstruct; + struct vdso_symtab symtab; + Elf64_Sym *eenter_sym; struct sgx_secs secs; uint64_t result = 0; off_t bin_size; + void *addr; void *bin; if (!encl_data_map("encl.bin", &bin, &bin_size)) @@ -243,5 +350,30 @@ int main(int argc, char *argv[], char *envp[]) printf("Output: 0x%lx\n", result); + memset(&exception, 0, sizeof(exception)); + + addr = vdso_get_base_addr(envp); + if (!addr) + exit(1); + + if (!vdso_get_symtab(addr, &symtab)) + exit(1); + + eenter_sym = vdso_symtab_get(&symtab, "__vdso_sgx_enter_enclave"); + if (!eenter_sym) + exit(1); + eenter = addr + eenter_sym->st_value; + + printf("Input: 0x%lx\n", MAGIC); + + sgx_call_vdso((void *)&MAGIC, &result, 0, NULL, NULL, NULL, + (void *)secs.base, &exception, NULL); + if (result != MAGIC) { + fprintf(stderr, "0x%lx != 0x%lx\n", result, MAGIC); + exit(1); + } + + printf("Output: 0x%lx\n", result); + exit(0); } diff --git a/tools/testing/selftests/x86/sgx/sgx_call.S b/tools/testing/selftests/x86/sgx/sgx_call.S index ca4c7893f9d9..e71f44f7a995 100644 --- a/tools/testing/selftests/x86/sgx/sgx_call.S +++ b/tools/testing/selftests/x86/sgx/sgx_call.S @@ -21,3 +21,46 @@ sgx_async_exit: ENCLU pop %rbx ret + + .global sgx_call_vdso +sgx_call_vdso: + .cfi_startproc + push %r15 + .cfi_adjust_cfa_offset 8 + .cfi_rel_offset %r15, 0 + push %r14 + .cfi_adjust_cfa_offset 8 + .cfi_rel_offset %r14, 0 + push %r13 + .cfi_adjust_cfa_offset 8 + .cfi_rel_offset %r13, 0 + push %r12 + .cfi_adjust_cfa_offset 8 + .cfi_rel_offset %r12, 0 + push %rbx + .cfi_adjust_cfa_offset 8 + .cfi_rel_offset %rbx, 0 + push $0 + .cfi_adjust_cfa_offset 8 + push 0x48(%rsp) + .cfi_adjust_cfa_offset 8 + push 0x48(%rsp) + .cfi_adjust_cfa_offset 8 + push 0x48(%rsp) + .cfi_adjust_cfa_offset 8 + mov $2, %eax + call *eenter(%rip) + add $0x20, %rsp + .cfi_adjust_cfa_offset -0x20 + pop %rbx + .cfi_adjust_cfa_offset -8 + pop %r12 + .cfi_adjust_cfa_offset -8 + pop %r13 + .cfi_adjust_cfa_offset -8 + pop %r14 + .cfi_adjust_cfa_offset -8 + pop %r15 + .cfi_adjust_cfa_offset -8 + ret + .cfi_endproc diff --git a/tools/testing/selftests/x86/sgx/sgx_call.h b/tools/testing/selftests/x86/sgx/sgx_call.h index bf72068ada23..a4072c5ecce7 100644 --- a/tools/testing/selftests/x86/sgx/sgx_call.h +++ b/tools/testing/selftests/x86/sgx/sgx_call.h @@ -8,4 +8,7 @@ void sgx_call_eenter(void *rdi, void *rsi, void *entry); +int sgx_call_vdso(void *rdi, void *rsi, long rdx, void *rcx, void *r8, void *r9, + void *tcs, struct sgx_enclave_exception *ei, void *cb); + #endif /* SGX_CALL_H */ -- 2.20.1

5 years, 3 months

1
0
0 0

[PATCH v25 12/21] selftests/x86: Add a selftest for SGX

by Jarkko Sakkinen

Add a selftest for SGX. It is a trivial test where a simple enclave copies one 64-bit word of memory between two memory locations given to the enclave as arguments. Use ENCLS[EENTER] to invoke the enclave. Cc: linux-sgx(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen(a)linux.intel.com> --- tools/testing/selftests/x86/sgx/.gitignore | 3 + tools/testing/selftests/x86/sgx/Makefile | 48 ++ tools/testing/selftests/x86/sgx/defines.h | 17 + tools/testing/selftests/x86/sgx/encl.c | 20 + tools/testing/selftests/x86/sgx/encl.lds | 34 ++ .../selftests/x86/sgx/encl_bootstrap.S | 94 ++++ tools/testing/selftests/x86/sgx/main.c | 247 +++++++++ tools/testing/selftests/x86/sgx/sgx_call.S | 23 + tools/testing/selftests/x86/sgx/sgx_call.h | 11 + tools/testing/selftests/x86/sgx/sgxsign.c | 493 ++++++++++++++++++ .../testing/selftests/x86/sgx/signing_key.pem | 39 ++ 11 files changed, 1029 insertions(+) create mode 100644 tools/testing/selftests/x86/sgx/.gitignore create mode 100644 tools/testing/selftests/x86/sgx/Makefile create mode 100644 tools/testing/selftests/x86/sgx/defines.h create mode 100644 tools/testing/selftests/x86/sgx/encl.c create mode 100644 tools/testing/selftests/x86/sgx/encl.lds create mode 100644 tools/testing/selftests/x86/sgx/encl_bootstrap.S create mode 100644 tools/testing/selftests/x86/sgx/main.c create mode 100644 tools/testing/selftests/x86/sgx/sgx_call.S create mode 100644 tools/testing/selftests/x86/sgx/sgx_call.h create mode 100644 tools/testing/selftests/x86/sgx/sgxsign.c create mode 100644 tools/testing/selftests/x86/sgx/signing_key.pem diff --git a/tools/testing/selftests/x86/sgx/.gitignore b/tools/testing/selftests/x86/sgx/.gitignore new file mode 100644 index 000000000000..98eb2d439606 --- /dev/null +++ b/tools/testing/selftests/x86/sgx/.gitignore @@ -0,0 +1,3 @@ +encl.ss +sgxsign +test_sgx diff --git a/tools/testing/selftests/x86/sgx/Makefile b/tools/testing/selftests/x86/sgx/Makefile new file mode 100644 index 000000000000..f838700029e2 --- /dev/null +++ b/tools/testing/selftests/x86/sgx/Makefile @@ -0,0 +1,48 @@ +top_srcdir = ../../../../.. + +include ../../lib.mk + +ifndef OBJCOPY +OBJCOPY := $(CROSS_COMPILE)objcopy +endif + +INCLUDES := -I$(top_srcdir)/tools/include +HOST_CFLAGS := -Wall -Werror -g $(INCLUDES) -fPIC -z noexecstack +ENCL_CFLAGS := -Wall -Werror -static -nostdlib -nostartfiles -fPIC \ + -fno-stack-protector -mrdrnd $(INCLUDES) + +TEST_CUSTOM_PROGS := $(OUTPUT)/test_sgx $(OUTPUT)/encl.bin $(OUTPUT)/encl.ss + +all: $(TEST_CUSTOM_PROGS) + +$(OUTPUT)/test_sgx: $(OUTPUT)/main.o $(OUTPUT)/sgx_call.o + $(CC) $(HOST_CFLAGS) -o $@ $^ + +$(OUTPUT)/main.o: main.c + $(CC) $(HOST_CFLAGS) -c $< -o $@ + +$(OUTPUT)/sgx_call.o: sgx_call.S + $(CC) $(HOST_CFLAGS) -c $< -o $@ + +$(OUTPUT)/encl.bin: $(OUTPUT)/encl.elf $(OUTPUT)/sgxsign + $(OBJCOPY) -O binary $< $@ + +$(OUTPUT)/encl.elf: encl.lds encl.c encl_bootstrap.S + $(CC) $(ENCL_CFLAGS) -T $^ -o $@ + +$(OUTPUT)/encl.ss: $(OUTPUT)/encl.bin + $(OUTPUT)/sgxsign signing_key.pem $(OUTPUT)/encl.bin $(OUTPUT)/encl.ss + +$(OUTPUT)/sgxsign: sgxsign.c + $(CC) $(INCLUDES) -o $@ $< -lcrypto + +EXTRA_CLEAN := \ + $(OUTPUT)/encl.bin \ + $(OUTPUT)/encl.elf \ + $(OUTPUT)/encl.ss \ + $(OUTPUT)/sgx_call.o \ + $(OUTPUT)/sgxsign \ + $(OUTPUT)/test_sgx \ + $(OUTPUT)/test_sgx.o \ + +.PHONY: clean diff --git a/tools/testing/selftests/x86/sgx/defines.h b/tools/testing/selftests/x86/sgx/defines.h new file mode 100644 index 000000000000..87264f85cb9f --- /dev/null +++ b/tools/testing/selftests/x86/sgx/defines.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright(c) 2016-19 Intel Corporation. + */ + +#ifndef DEFINES_H +#define DEFINES_H + +#include <stdint.h> + +#define __aligned(x) __attribute__((__aligned__(x))) +#define __packed __attribute__((packed)) + +#include "../../../../../arch/x86/kernel/cpu/sgx/arch.h" +#include "../../../../../arch/x86/include/uapi/asm/sgx.h" + +#endif /* DEFINES_H */ diff --git a/tools/testing/selftests/x86/sgx/encl.c b/tools/testing/selftests/x86/sgx/encl.c new file mode 100644 index 000000000000..ede915399742 --- /dev/null +++ b/tools/testing/selftests/x86/sgx/encl.c @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) +// Copyright(c) 2016-18 Intel Corporation. + +#include <stddef.h> +#include "defines.h" + +static void *memcpy(void *dest, const void *src, size_t n) +{ + size_t i; + + for (i = 0; i < n; i++) + ((char *)dest)[i] = ((char *)src)[i]; + + return dest; +} + +void encl_body(void *rdi, void *rsi) +{ + memcpy(rsi, rdi, 8); +} diff --git a/tools/testing/selftests/x86/sgx/encl.lds b/tools/testing/selftests/x86/sgx/encl.lds new file mode 100644 index 000000000000..9a56d3064104 --- /dev/null +++ b/tools/testing/selftests/x86/sgx/encl.lds @@ -0,0 +1,34 @@ +OUTPUT_FORMAT(elf64-x86-64) + +SECTIONS +{ + . = 0; + .tcs : { + *(.tcs*) + } + + . = ALIGN(4096); + .text : { + *(.text*) + *(.rodata*) + } + + . = ALIGN(4096); + .data : { + *(.data*) + } + + /DISCARD/ : { + *(.data*) + *(.comment*) + *(.note*) + *(.debug*) + *(.eh_frame*) + } +} + +ASSERT(!DEFINED(.altinstructions), "ALTERNATIVES are not supported in enclaves") +ASSERT(!DEFINED(.altinstr_replacement), "ALTERNATIVES are not supported in enclaves") +ASSERT(!DEFINED(.discard.retpoline_safe), "RETPOLINE ALTERNATIVES are not supported in enclaves") +ASSERT(!DEFINED(.discard.nospec), "RETPOLINE ALTERNATIVES are not supported in enclaves") +ASSERT(!DEFINED(.got.plt), "Libcalls are not supported in enclaves") diff --git a/tools/testing/selftests/x86/sgx/encl_bootstrap.S b/tools/testing/selftests/x86/sgx/encl_bootstrap.S new file mode 100644 index 000000000000..d07f970ccdf9 --- /dev/null +++ b/tools/testing/selftests/x86/sgx/encl_bootstrap.S @@ -0,0 +1,94 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ +/* + * Copyright(c) 2016-18 Intel Corporation. + */ + + .macro ENCLU + .byte 0x0f, 0x01, 0xd7 + .endm + + .section ".tcs", "a" + .balign 4096 + + .fill 1, 8, 0 # STATE (set by CPU) + .fill 1, 8, 0 # FLAGS + .quad encl_ssa # OSSA + .fill 1, 4, 0 # CSSA (set by CPU) + .fill 1, 4, 1 # NSSA + .quad encl_entry # OENTRY + .fill 1, 8, 0 # AEP (set by EENTER and ERESUME) + .fill 1, 8, 0 # OFSBASE + .fill 1, 8, 0 # OGSBASE + .fill 1, 4, 0xFFFFFFFF # FSLIMIT + .fill 1, 4, 0xFFFFFFFF # GSLIMIT + .fill 4024, 1, 0 # Reserved + + .text + +encl_entry: + # RBX contains the base address for TCS, which is also the first address + # inside the enclave. By adding the value of le_stack_end to it, we get + # the absolute address for the stack. + lea (encl_stack)(%rbx), %rax + xchg %rsp, %rax + push %rax + + push %rcx # push the address after EENTER + push %rbx # push the enclave base address + + call encl_body + + pop %rbx # pop the enclave base address + + # Restore XSAVE registers to a synthetic state. + mov $0xFFFFFFFF, %rax + mov $0xFFFFFFFF, %rdx + lea (xsave_area)(%rbx), %rdi + fxrstor (%rdi) + + # Clear GPRs. + xor %rcx, %rcx + xor %rdx, %rdx + xor %rdi, %rdi + xor %rsi, %rsi + xor %r8, %r8 + xor %r9, %r9 + xor %r10, %r10 + xor %r11, %r11 + xor %r12, %r12 + xor %r13, %r13 + xor %r14, %r14 + xor %r15, %r15 + + # Reset status flags. + add %rdx, %rdx # OF = SF = AF = CF = 0; ZF = PF = 1 + + # Prepare EEXIT target by popping the address of the instruction after + # EENTER to RBX. + pop %rbx + + # Restore the caller stack. + pop %rax + mov %rax, %rsp + + # EEXIT + mov $4, %rax + enclu + + .section ".data", "aw" + +encl_ssa: + .space 4096 + +xsave_area: + .fill 1, 4, 0x037F # FCW + .fill 5, 4, 0 + .fill 1, 4, 0x1F80 # MXCSR + .fill 1, 4, 0xFFFF # MXCSR_MASK + .fill 123, 4, 0 + .fill 1, 4, 0x80000000 # XCOMP_BV[63] = 1, compaction mode + .fill 12, 4, 0 + + .balign 4096 + .space 8192 +encl_stack: diff --git a/tools/testing/selftests/x86/sgx/main.c b/tools/testing/selftests/x86/sgx/main.c new file mode 100644 index 000000000000..48ed5fdfb3cb --- /dev/null +++ b/tools/testing/selftests/x86/sgx/main.c @@ -0,0 +1,247 @@ +// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) +// Copyright(c) 2016-18 Intel Corporation. + +#include <elf.h> +#include <errno.h> +#include <fcntl.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdint.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <sys/stat.h> +#include <sys/time.h> +#include <sys/types.h> +#include "defines.h" +#include "sgx_call.h" + +#define PAGE_SIZE 4096 + +static const uint64_t MAGIC = 0x1122334455667788ULL; + +static bool encl_create(int dev_fd, unsigned long bin_size, + struct sgx_secs *secs) +{ + struct sgx_enclave_create ioc; + void *area; + int rc; + + memset(secs, 0, sizeof(*secs)); + secs->ssa_frame_size = 1; + secs->attributes = SGX_ATTR_MODE64BIT; + secs->xfrm = 3; + + for (secs->size = 4096; secs->size < bin_size; ) + secs->size <<= 1; + + area = mmap(NULL, secs->size * 2, PROT_NONE, MAP_SHARED, dev_fd, 0); + if (area == MAP_FAILED) { + perror("mmap"); + return false; + } + + secs->base = ((uint64_t)area + secs->size - 1) & ~(secs->size - 1); + + munmap(area, secs->base - (uint64_t)area); + munmap((void *)(secs->base + secs->size), + (uint64_t)area + secs->size - secs->base); + + ioc.src = (unsigned long)secs; + rc = ioctl(dev_fd, SGX_IOC_ENCLAVE_CREATE, &ioc); + if (rc) { + fprintf(stderr, "ECREATE failed rc=%d, err=%d.\n", rc, errno); + munmap((void *)secs->base, secs->size); + return false; + } + + return true; +} + +static bool encl_add_pages(int dev_fd, unsigned long offset, void *data, + unsigned long length, uint64_t flags) +{ + struct sgx_enclave_add_pages ioc; + struct sgx_secinfo secinfo; + int rc; + + memset(&secinfo, 0, sizeof(secinfo)); + secinfo.flags = flags; + + ioc.src = (uint64_t)data; + ioc.offset = offset; + ioc.length = length; + ioc.secinfo = (unsigned long)&secinfo; + ioc.flags = SGX_PAGE_MEASURE; + + rc = ioctl(dev_fd, SGX_IOC_ENCLAVE_ADD_PAGES, &ioc); + if (rc) { + fprintf(stderr, "EADD failed rc=%d.\n", rc); + return false; + } + + if (ioc.count != ioc.length) { + fprintf(stderr, "Partially processed, update the test.\n"); + return false; + } + + return true; +} + +#define SGX_REG_PAGE_FLAGS \ + (SGX_SECINFO_REG | SGX_SECINFO_R | SGX_SECINFO_W | SGX_SECINFO_X) + +static bool encl_build(struct sgx_secs *secs, void *bin, + unsigned long bin_size, struct sgx_sigstruct *sigstruct) +{ + struct sgx_enclave_init ioc; + void *addr; + int dev_fd; + int rc; + + dev_fd = open("/dev/sgx/enclave", O_RDWR); + if (dev_fd < 0) { + fprintf(stderr, "Unable to open /dev/sgx\n"); + return false; + } + + if (!encl_create(dev_fd, bin_size, secs)) + goto out_dev_fd; + + if (!encl_add_pages(dev_fd, 0, bin, PAGE_SIZE, SGX_SECINFO_TCS)) + goto out_dev_fd; + + if (!encl_add_pages(dev_fd, PAGE_SIZE, bin + PAGE_SIZE, + bin_size - PAGE_SIZE, SGX_REG_PAGE_FLAGS)) + goto out_dev_fd; + + ioc.sigstruct = (uint64_t)sigstruct; + rc = ioctl(dev_fd, SGX_IOC_ENCLAVE_INIT, &ioc); + if (rc) { + printf("EINIT failed rc=%d\n", rc); + goto out_map; + } + + addr = mmap((void *)secs->base, PAGE_SIZE, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_FIXED, dev_fd, 0); + if (addr == MAP_FAILED) { + fprintf(stderr, "mmap() failed on TCS, errno=%d.\n", errno); + return false; + } + + addr = mmap((void *)(secs->base + PAGE_SIZE), bin_size - PAGE_SIZE, + PROT_READ | PROT_WRITE | PROT_EXEC, + MAP_SHARED | MAP_FIXED, dev_fd, 0); + if (addr == MAP_FAILED) { + fprintf(stderr, "mmap() failed, errno=%d.\n", errno); + return false; + } + + close(dev_fd); + return true; +out_map: + munmap((void *)secs->base, secs->size); +out_dev_fd: + close(dev_fd); + return false; +} + +bool get_file_size(const char *path, off_t *bin_size) +{ + struct stat sb; + int ret; + + ret = stat(path, &sb); + if (ret) { + perror("stat"); + return false; + } + + if (!sb.st_size || sb.st_size & 0xfff) { + fprintf(stderr, "Invalid blob size %lu\n", sb.st_size); + return false; + } + + *bin_size = sb.st_size; + return true; +} + +bool encl_data_map(const char *path, void **bin, off_t *bin_size) +{ + int fd; + + fd = open(path, O_RDONLY); + if (fd == -1) { + fprintf(stderr, "open() %s failed, errno=%d.\n", path, errno); + return false; + } + + if (!get_file_size(path, bin_size)) + goto err_out; + + *bin = mmap(NULL, *bin_size, PROT_READ, MAP_PRIVATE, fd, 0); + if (*bin == MAP_FAILED) { + fprintf(stderr, "mmap() %s failed, errno=%d.\n", path, errno); + goto err_out; + } + + close(fd); + return true; + +err_out: + close(fd); + return false; +} + +bool load_sigstruct(const char *path, void *sigstruct) +{ + int fd; + + fd = open(path, O_RDONLY); + if (fd == -1) { + fprintf(stderr, "open() %s failed, errno=%d.\n", path, errno); + return false; + } + + if (read(fd, sigstruct, sizeof(struct sgx_sigstruct)) != + sizeof(struct sgx_sigstruct)) { + fprintf(stderr, "read() %s failed, errno=%d.\n", path, errno); + close(fd); + return false; + } + + close(fd); + return true; +} + +int main(int argc, char *argv[], char *envp[]) +{ + struct sgx_sigstruct sigstruct; + struct sgx_secs secs; + uint64_t result = 0; + off_t bin_size; + void *bin; + + if (!encl_data_map("encl.bin", &bin, &bin_size)) + exit(1); + + if (!load_sigstruct("encl.ss", &sigstruct)) + exit(1); + + if (!encl_build(&secs, bin, bin_size, &sigstruct)) + exit(1); + + printf("Input: 0x%lx\n", MAGIC); + + sgx_call_eenter((void *)&MAGIC, &result, (void *)secs.base); + if (result != MAGIC) { + fprintf(stderr, "0x%lx != 0x%lx\n", result, MAGIC); + exit(1); + } + + printf("Output: 0x%lx\n", result); + + exit(0); +} diff --git a/tools/testing/selftests/x86/sgx/sgx_call.S b/tools/testing/selftests/x86/sgx/sgx_call.S new file mode 100644 index 000000000000..ca4c7893f9d9 --- /dev/null +++ b/tools/testing/selftests/x86/sgx/sgx_call.S @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ +/** +* Copyright(c) 2016-18 Intel Corporation. +*/ + + .text + + .macro ENCLU + .byte 0x0f, 0x01, 0xd7 + .endm + + .text + + .global sgx_call_eenter +sgx_call_eenter: + push %rbx + mov $0x02, %rax + mov %rdx, %rbx + lea sgx_async_exit(%rip), %rcx +sgx_async_exit: + ENCLU + pop %rbx + ret diff --git a/tools/testing/selftests/x86/sgx/sgx_call.h b/tools/testing/selftests/x86/sgx/sgx_call.h new file mode 100644 index 000000000000..bf72068ada23 --- /dev/null +++ b/tools/testing/selftests/x86/sgx/sgx_call.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright(c) 2016-19 Intel Corporation. + */ + +#ifndef SGX_CALL_H +#define SGX_CALL_H + +void sgx_call_eenter(void *rdi, void *rsi, void *entry); + +#endif /* SGX_CALL_H */ diff --git a/tools/testing/selftests/x86/sgx/sgxsign.c b/tools/testing/selftests/x86/sgx/sgxsign.c new file mode 100644 index 000000000000..3d9007af40c9 --- /dev/null +++ b/tools/testing/selftests/x86/sgx/sgxsign.c @@ -0,0 +1,493 @@ +// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) +// Copyright(c) 2016-18 Intel Corporation. + +#define _GNU_SOURCE +#include <getopt.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> +#include <openssl/err.h> +#include <openssl/pem.h> +#include "defines.h" + +struct sgx_sigstruct_payload { + struct sgx_sigstruct_header header; + struct sgx_sigstruct_body body; +}; + +static bool check_crypto_errors(void) +{ + int err; + bool had_errors = false; + const char *filename; + int line; + char str[256]; + + for ( ; ; ) { + if (ERR_peek_error() == 0) + break; + + had_errors = true; + err = ERR_get_error_line(&filename, &line); + ERR_error_string_n(err, str, sizeof(str)); + fprintf(stderr, "crypto: %s: %s:%d\n", str, filename, line); + } + + return had_errors; +} + +static void exit_usage(const char *program) +{ + fprintf(stderr, + "Usage: %s/sign-le <key> <enclave> <sigstruct>\n", program); + exit(1); +} + +static inline const BIGNUM *get_modulus(RSA *key) +{ +#if OPENSSL_VERSION_NUMBER < 0x10100000L + return key->n; +#else + const BIGNUM *n; + + RSA_get0_key(key, &n, NULL, NULL); + return n; +#endif +} + +static RSA *load_sign_key(const char *path) +{ + FILE *f; + RSA *key; + + f = fopen(path, "rb"); + if (!f) { + fprintf(stderr, "Unable to open %s\n", path); + return NULL; + } + key = RSA_new(); + if (!PEM_read_RSAPrivateKey(f, &key, NULL, NULL)) + return NULL; + fclose(f); + + if (BN_num_bytes(get_modulus(key)) != SGX_MODULUS_SIZE) { + fprintf(stderr, "Invalid key size %d\n", + BN_num_bytes(get_modulus(key))); + RSA_free(key); + return NULL; + } + + return key; +} + +static void reverse_bytes(void *data, int length) +{ + int i = 0; + int j = length - 1; + uint8_t temp; + uint8_t *ptr = data; + + while (i < j) { + temp = ptr[i]; + ptr[i] = ptr[j]; + ptr[j] = temp; + i++; + j--; + } +} + +enum mrtags { + MRECREATE = 0x0045544145524345, + MREADD = 0x0000000044444145, + MREEXTEND = 0x00444E4554584545, +}; + +static bool mrenclave_update(EVP_MD_CTX *ctx, const void *data) +{ + if (!EVP_DigestUpdate(ctx, data, 64)) { + fprintf(stderr, "digest update failed\n"); + return false; + } + + return true; +} + +static bool mrenclave_commit(EVP_MD_CTX *ctx, uint8_t *mrenclave) +{ + unsigned int size; + + if (!EVP_DigestFinal_ex(ctx, (unsigned char *)mrenclave, &size)) { + fprintf(stderr, "digest commit failed\n"); + return false; + } + + if (size != 32) { + fprintf(stderr, "invalid digest size = %u\n", size); + return false; + } + + return true; +} + +struct mrecreate { + uint64_t tag; + uint32_t ssaframesize; + uint64_t size; + uint8_t reserved[44]; +} __attribute__((__packed__)); + + +static bool mrenclave_ecreate(EVP_MD_CTX *ctx, uint64_t blob_size) +{ + struct mrecreate mrecreate; + uint64_t encl_size; + + for (encl_size = 0x1000; encl_size < blob_size; ) + encl_size <<= 1; + + memset(&mrecreate, 0, sizeof(mrecreate)); + mrecreate.tag = MRECREATE; + mrecreate.ssaframesize = 1; + mrecreate.size = encl_size; + + if (!EVP_DigestInit_ex(ctx, EVP_sha256(), NULL)) + return false; + + return mrenclave_update(ctx, &mrecreate); +} + +struct mreadd { + uint64_t tag; + uint64_t offset; + uint64_t flags; /* SECINFO flags */ + uint8_t reserved[40]; +} __attribute__((__packed__)); + +static bool mrenclave_eadd(EVP_MD_CTX *ctx, uint64_t offset, uint64_t flags) +{ + struct mreadd mreadd; + + memset(&mreadd, 0, sizeof(mreadd)); + mreadd.tag = MREADD; + mreadd.offset = offset; + mreadd.flags = flags; + + return mrenclave_update(ctx, &mreadd); +} + +struct mreextend { + uint64_t tag; + uint64_t offset; + uint8_t reserved[48]; +} __attribute__((__packed__)); + +static bool mrenclave_eextend(EVP_MD_CTX *ctx, uint64_t offset, uint8_t *data) +{ + struct mreextend mreextend; + int i; + + for (i = 0; i < 0x1000; i += 0x100) { + memset(&mreextend, 0, sizeof(mreextend)); + mreextend.tag = MREEXTEND; + mreextend.offset = offset + i; + + if (!mrenclave_update(ctx, &mreextend)) + return false; + + if (!mrenclave_update(ctx, &data[i + 0x00])) + return false; + + if (!mrenclave_update(ctx, &data[i + 0x40])) + return false; + + if (!mrenclave_update(ctx, &data[i + 0x80])) + return false; + + if (!mrenclave_update(ctx, &data[i + 0xC0])) + return false; + } + + return true; +} + +/** + * measure_encl - measure enclave + * @path: path to the enclave + * @mrenclave: measurement + * + * Calculates MRENCLAVE. Assumes that the very first page is a TCS page and + * following pages are regular pages. Does not measure the contents of the + * enclave as the signing tool is used at the moment only for the launch + * enclave, which is pass-through (everything gets a token). + */ +static bool measure_encl(const char *path, uint8_t *mrenclave) +{ + FILE *file; + struct stat sb; + EVP_MD_CTX *ctx; + uint64_t flags; + uint64_t offset; + uint8_t data[0x1000]; + int rc; + + ctx = EVP_MD_CTX_create(); + if (!ctx) + return false; + + file = fopen(path, "rb"); + if (!file) { + perror("fopen"); + EVP_MD_CTX_destroy(ctx); + return false; + } + + rc = stat(path, &sb); + if (rc) { + perror("stat"); + goto out; + } + + if (!sb.st_size || sb.st_size & 0xfff) { + fprintf(stderr, "Invalid blob size %lu\n", sb.st_size); + goto out; + } + + if (!mrenclave_ecreate(ctx, sb.st_size)) + goto out; + + for (offset = 0; offset < sb.st_size; offset += 0x1000) { + if (!offset) + flags = SGX_SECINFO_TCS; + else + flags = SGX_SECINFO_REG | SGX_SECINFO_R | + SGX_SECINFO_W | SGX_SECINFO_X; + + if (!mrenclave_eadd(ctx, offset, flags)) + goto out; + + rc = fread(data, 1, 0x1000, file); + if (!rc) + break; + if (rc < 0x1000) + goto out; + + if (!mrenclave_eextend(ctx, offset, data)) + goto out; + } + + if (!mrenclave_commit(ctx, mrenclave)) + goto out; + + fclose(file); + EVP_MD_CTX_destroy(ctx); + return true; +out: + fclose(file); + EVP_MD_CTX_destroy(ctx); + return false; +} + +/** + * sign_encl - sign enclave + * @sigstruct: pointer to SIGSTRUCT + * @key: 3072-bit RSA key + * @signature: byte array for the signature + * + * Calculates EMSA-PKCSv1.5 signature for the given SIGSTRUCT. The result is + * stored in big-endian format so that it can be further passed to OpenSSL + * libcrypto functions. + */ +static bool sign_encl(const struct sgx_sigstruct *sigstruct, RSA *key, + uint8_t *signature) +{ + struct sgx_sigstruct_payload payload; + unsigned int siglen; + uint8_t digest[SHA256_DIGEST_LENGTH]; + bool ret; + + memcpy(&payload.header, &sigstruct->header, sizeof(sigstruct->header)); + memcpy(&payload.body, &sigstruct->body, sizeof(sigstruct->body)); + + SHA256((unsigned char *)&payload, sizeof(payload), digest); + + ret = RSA_sign(NID_sha256, digest, SHA256_DIGEST_LENGTH, signature, + &siglen, key); + + return ret; +} + +struct q1q2_ctx { + BN_CTX *bn_ctx; + BIGNUM *m; + BIGNUM *s; + BIGNUM *q1; + BIGNUM *qr; + BIGNUM *q2; +}; + +static void free_q1q2_ctx(struct q1q2_ctx *ctx) +{ + BN_CTX_free(ctx->bn_ctx); + BN_free(ctx->m); + BN_free(ctx->s); + BN_free(ctx->q1); + BN_free(ctx->qr); + BN_free(ctx->q2); +} + +static bool alloc_q1q2_ctx(const uint8_t *s, const uint8_t *m, + struct q1q2_ctx *ctx) +{ + ctx->bn_ctx = BN_CTX_new(); + ctx->s = BN_bin2bn(s, SGX_MODULUS_SIZE, NULL); + ctx->m = BN_bin2bn(m, SGX_MODULUS_SIZE, NULL); + ctx->q1 = BN_new(); + ctx->qr = BN_new(); + ctx->q2 = BN_new(); + + if (!ctx->bn_ctx || !ctx->s || !ctx->m || !ctx->q1 || !ctx->qr || + !ctx->q2) { + free_q1q2_ctx(ctx); + return false; + } + + return true; +} + +static bool calc_q1q2(const uint8_t *s, const uint8_t *m, uint8_t *q1, + uint8_t *q2) +{ + struct q1q2_ctx ctx; + + if (!alloc_q1q2_ctx(s, m, &ctx)) { + fprintf(stderr, "Not enough memory for Q1Q2 calculation\n"); + return false; + } + + if (!BN_mul(ctx.q1, ctx.s, ctx.s, ctx.bn_ctx)) + goto out; + + if (!BN_div(ctx.q1, ctx.qr, ctx.q1, ctx.m, ctx.bn_ctx)) + goto out; + + if (BN_num_bytes(ctx.q1) > SGX_MODULUS_SIZE) { + fprintf(stderr, "Too large Q1 %d bytes\n", + BN_num_bytes(ctx.q1)); + goto out; + } + + if (!BN_mul(ctx.q2, ctx.s, ctx.qr, ctx.bn_ctx)) + goto out; + + if (!BN_div(ctx.q2, NULL, ctx.q2, ctx.m, ctx.bn_ctx)) + goto out; + + if (BN_num_bytes(ctx.q2) > SGX_MODULUS_SIZE) { + fprintf(stderr, "Too large Q2 %d bytes\n", + BN_num_bytes(ctx.q2)); + goto out; + } + + BN_bn2bin(ctx.q1, q1); + BN_bn2bin(ctx.q2, q2); + + free_q1q2_ctx(&ctx); + return true; +out: + free_q1q2_ctx(&ctx); + return false; +} + +static bool save_sigstruct(const struct sgx_sigstruct *sigstruct, + const char *path) +{ + FILE *f = fopen(path, "wb"); + + if (!f) { + fprintf(stderr, "Unable to open %s\n", path); + return false; + } + + fwrite(sigstruct, sizeof(*sigstruct), 1, f); + fclose(f); + return true; +} + +int main(int argc, char **argv) +{ + uint64_t header1[2] = {0x000000E100000006, 0x0000000000010000}; + uint64_t header2[2] = {0x0000006000000101, 0x0000000100000060}; + struct sgx_sigstruct ss; + const char *program; + int opt; + RSA *sign_key; + + memset(&ss, 0, sizeof(ss)); + ss.header.header1[0] = header1[0]; + ss.header.header1[1] = header1[1]; + ss.header.header2[0] = header2[0]; + ss.header.header2[1] = header2[1]; + ss.exponent = 3; + +#ifndef CONFIG_EINITTOKENKEY + ss.body.attributes = SGX_ATTR_MODE64BIT; +#else + ss.body.attributes = SGX_ATTR_MODE64BIT | SGX_ATTR_EINITTOKENKEY; +#endif + ss.body.xfrm = 3, + + program = argv[0]; + + do { + opt = getopt(argc, argv, ""); + switch (opt) { + case -1: + break; + default: + exit_usage(program); + } + } while (opt != -1); + + argc -= optind; + argv += optind; + + if (argc < 3) + exit_usage(program); + + /* sanity check only */ + if (check_crypto_errors()) + exit(1); + + sign_key = load_sign_key(argv[0]); + if (!sign_key) + goto out; + + BN_bn2bin(get_modulus(sign_key), ss.modulus); + + if (!measure_encl(argv[1], ss.body.mrenclave)) + goto out; + + if (!sign_encl(&ss, sign_key, ss.signature)) + goto out; + + if (!calc_q1q2(ss.signature, ss.modulus, ss.q1, ss.q2)) + goto out; + + /* convert to little endian */ + reverse_bytes(ss.signature, SGX_MODULUS_SIZE); + reverse_bytes(ss.modulus, SGX_MODULUS_SIZE); + reverse_bytes(ss.q1, SGX_MODULUS_SIZE); + reverse_bytes(ss.q2, SGX_MODULUS_SIZE); + + if (!save_sigstruct(&ss, argv[2])) + goto out; + exit(0); +out: + check_crypto_errors(); + exit(1); +} diff --git a/tools/testing/selftests/x86/sgx/signing_key.pem b/tools/testing/selftests/x86/sgx/signing_key.pem new file mode 100644 index 000000000000..d76f21f19187 --- /dev/null +++ b/tools/testing/selftests/x86/sgx/signing_key.pem @@ -0,0 +1,39 @@ +-----BEGIN RSA PRIVATE KEY----- +MIIG4wIBAAKCAYEApalGbq7Q+usM91CPtksu3D+b0Prc8gAFL6grM3mg85A5Bx8V +cfMXPgtrw8EYFwQxDAvzZWwl+9VfOX0ECrFRBkOHcOiG0SnADN8+FLj1UiNUQwbp +S6OzhNWuRcSbGraSOyUlVlV0yMQSvewyzGklOaXBe30AJqzIBc8QfdSxKuP8rs0Z +ga6k/Bl73osrYKByILJTUUeZqjLERsE6GebsdzbWgKn8qVqng4ZS4yMNg6LeRlH3 ++9CIPgg4jwpSLHcp7dq2qTIB9a0tGe9ayp+5FbucpB6U7ePold0EeRN6RlJGDF9k +L93v8P5ykz5G5gYZ2g0K1X2sHIWV4huxPgv5PXgdyQYbK+6olqj0d5rjYuwX57Ul +k6SroPS1U6UbdCjG5txM+BNGU0VpD0ZhrIRw0leQdnNcCO9sTJuInZrgYacSVJ7u +mtB+uCt+uzUesc+l+xPRYA+9e14lLkZp7AAmo9FvL816XDI09deehJ3i/LmHKCRN +tuqC5TprRjFwUr6dAgEDAoIBgG5w2Z8fNfycs0+LCnmHdJLVEotR6KFVWMpwHMz7 +wKJgJgS/Y6FMuilc8oKAuroCy11dTO5IGVKOP3uorVx2NgQtBPXwWeDGgAiU1A3Q +o4wXjYIEm4fCd63jyYPYZ2ckYXzDbjmOTdstYdPyzIhGGNEZK6eoqsRzMAPfYFPj +IMdCqHSIu6vJw1K7p+myHOsVoWshjODaZnF3LYSA0WaZ8vokjwBxUxuRxQJZjJds +s60XPtmL+qfgWtQFewoG4XL6GuD8FcXccynRRtzrLtFNPIl9BQfWfjBBhTC1/Te1 +0Z6XbZvpdUTD9OfLB7SbR2OUFNpKQgriO0iYVdbW3cr7uu38Zwp4W1TX73DPjoi6 +KNooP6SGWd4mRJW2+dUmSYS4QNG8eVVZswKcploEIXlAKRsOe4kzJJ1iETugIe85 +uX8nd1WYEp65xwoRUg8hqng0MeyveVbXqNKuJG6tzNDt9kgFYo+hmC/oouAW2Dtc +T9jdRAwKJXqA2Eg6OkgXCEv+kwKBwQDYaQiFMlFhsmLlqI+EzCUh7c941/cL7m6U +7j98+8ngl0HgCEcrc10iJVCKakQW3YbPzAx3XkKTaGjWazvvrFarXIGlOud64B8a +iWyQ7VdlnmZnNEdk+C83tI91OQeaTKqRLDGzKh29Ry/jL8Pcbazt+kDgxa0H7qJp +roADUanLQuNkYubpbhFBh3xpa2EExaVq6rF7nIVsD8W9TrbmPKA4LgH7z0iy544D +kVCNYsTjYDdUWP+WiSor8kCnnpjnN9sCgcEAw/eNezUD1UDf6OYFC9+5JZJFn4Tg +mZMyN93JKIb199ffwnjtHUSjcyiWeesXucpzwtGbTcwQnDisSW4oneYKLSEBlBaq +scqiUugyGZZOthFSCbdXYXMViK2vHrKlkse7GxVlROKcEhM/pRBrmjaGO8eWR+D4 +FO2wCXzVs3KgV6j779frw0vC54oHOxc9+Lu1rSHp4i+600koyvL/zF6U/5tZXIvN +YW2yoiQJnjCmVA1pwbwV6KAUTPDTMnBK+YjnAoHBAJBGBa4hi5Z27JkbCliIGMFJ +NPs6pLKe9GNJf6in2+sPgUAFhMeiPhbDiwbxgrnpBIqICE+ULGJFmzmc0p/IOceT +ARjR76dAFLxbnbXzj5kURETNhO36yiUjCk4mBRGIcbYddndxaSjaH+zKgpLzyJ6m +1esuc1qfFvEfAAI2cTIsl5hB70ZJYNZaUvDyQK3ZGPHxy6e9rkgKg9OJz0QoatAe +q/002yHvtAJg4F5B2JeVejg7VQ8GHB1MKxppu0TP5wKBwQCCpQj8zgKOKz/wmViy +lSYZDC5qWJW7t3bP6TDFr06lOpUsUJ4TgxeiGw778g/RMaKB4RIz3WBoJcgw9BsT +7rFza1ZiucchMcGMmswRDt8kC4wGejpA92Owc8oUdxkMhSdnY5jYlxK2t3/DYEe8 +JFl9L7mFQKVjSSAGUzkiTGrlG1Kf5UfXh9dFBq98uilQfSPIwUaWynyM23CHTKqI +Pw3/vOY9sojrnncWwrEUIG7is5vWfWPwargzSzd29YdRBe8CgcEAuRVewK/YeNOX +B7ZG6gKKsfsvrGtY7FPETzLZAHjoVXYNea4LVZ2kn4hBXXlvw/4HD+YqcTt4wmif +5JQlDvjNobUiKJZpzy7hklVhF7wZFl4pCF7Yh43q9iQ7gKTaeUG7MiaK+G8Zz8aY +HW9rsiihbdZkccMvnPfO9334XMxl3HtBRzLstjUlbLB7Sdh+7tZ3JQidCOFNs5pE +XyWwnASPu4tKfDahH1UUTp1uJcq/6716CSWg080avYxFcn75qqsb +-----END RSA PRIVATE KEY----- -- 2.20.1

5 years, 3 months

1
0
0 0

[PATCH v3 00/12] mm/gup: track FOLL_PIN pages

by John Hubbard

Matthew, I've merged in your dump_page() ideas, and also factored things out into a new __dump_tail_page() routine, in order to save a few indentation levels, mainly. Kirill, thanks for your review comments. I've applied them, and I think splitting this up as you recommended really makes it a lot better, and easier to spot problems. ============================================================ Changes since v2: * Rebased onto linux.git, because the akpm tree for 5.6 has been merged. * Split the tracking patch into even more patches, as requested. * Merged Matthew Wilcox's dump_page() changes into mine, as part of the first patch. * Renamed: page_dma_pinned() --> page_maybe_dma_pinned(), in response to Kirill Shutemov's review. * Moved a WARN to the top of a routine, and fixed a typo in the commit description of patch #7, also as suggested by Kirill. ============================================================ Changes since v1: * Split the tracking patch into 6 smaller patches * Rebased onto today's linux-next/akpm (there weren't any conflicts). * Fixed an "unsigned int" vs. "int" problem in gup_benchmark, reported by Nathan Chancellor. (I don't see it in my local builds, probably because they use gcc, but an LLVM test found the mismatch.) * Fixed a huge page pincount problem (add/subtract vs. increment/decrement), spotted by Jan Kara. ============================================================ There is a reasonable case to be made for merging two of the patches (patches 4 and 5), given that patch 4 provides tracking that has upper limits on the number of pins that can be done with huge pages. Let me know if anyone wants those merged, but unless there is some weird chance of someone grabbing patch 4 and not patch 5, I don't really see the need. Meanwhile, it's easier to review in this form. Also, patch 3 has been revived. Earlier reviewers asked for it to be merged into the tracking patch (one cannot please everyone, heh), but now it's back out on it's own. This activates tracking of FOLL_PIN pages. This is in support of fixing the get_user_pages()+DMA problem described in [1]-[4]. It is based on today's (Jan 28) linux-next (branch: akpm), commit 280e9cb00b41 ("drivers/media/platform/sti/delta/delta-ipc.c: fix read buffer overflow") There is a git repo and branch, for convenience in reviewing: git@github.com:johnhubbard/linux.git track_user_pages_v2_linux-next_akpm_28Jan2020 FOLL_PIN support is (so far) in mmotm and linux-next. However, the patch to use FOLL_PIN to track pages was *not* submitted, because Leon saw an RDMA test suite failure that involved (I think) page refcount overflows when huge pages were used. This patch definitively solves that kind of overflow problem, by adding an exact pincount, for compound pages (of order > 1), in the 3rd struct page of a compound page. If available, that form of pincounting is used, instead of the GUP_PIN_COUNTING_BIAS approach. Thanks again to Jan Kara for that idea. Here's the last reviewed version of the tracking patch (v11): https://lore.kernel.org/r/20191216222537.491123-1-jhubbard@nvidia.com Jan Kara had provided a reviewed-by tag for that, but I've had to remove it (again) here, due to having changed the patch "a little bit", in order to add the feature described above. Other interesting changes: * dump_page(): added one, or two new things to report for compound pages: head refcount (for all compound pages), and map_pincount (for compound pages of order > 1). * Documentation/core-api/pin_user_pages.rst: removed the "TODO" for the huge page refcount upper limit problems, and added notes about how it works now. Also added a note about the dump_page() enhancements. * Added some comments in gup.c and mm.h, to explain that there are two ways to count pinned pages: exact (for compound pages of order > 1) and fuzzy (GUP_PIN_COUNTING_BIAS: for all other pages). ============================================================ General notes about the tracking patch: This is a prerequisite to solving the problem of proper interactions between file-backed pages, and [R]DMA activities, as discussed in [1], [2], [3], [4] and in a remarkable number of email threads since about 2017. :) In contrast to earlier approaches, the page tracking can be incrementally applied to the kernel call sites that, until now, have been simply calling get_user_pages() ("gup"). In other words, opt-in by changing from this: get_user_pages() (sets FOLL_GET) put_page() to this: pin_user_pages() (sets FOLL_PIN) unpin_user_page() ============================================================ Next steps: * Convert more subsystems from get_user_pages() to pin_user_pages(). * Work with Ira and others to connect this all up with file system leases. [1] Some slow progress on get_user_pages() (Apr 2, 2019): https://lwn.net/Articles/784574/ [2] DMA and get_user_pages() (LPC: Dec 12, 2018): https://lwn.net/Articles/774411/ [3] The trouble with get_user_pages() (Apr 30, 2018): https://lwn.net/Articles/753027/ [4] LWN kernel index: get_user_pages() https://lwn.net/Kernel/Index/#Memory_management-get_user_pages John Hubbard (12): mm: dump_page(): better diagnostics for compound pages mm/gup: split get_user_pages_remote() into two routines mm/gup: pass a flags arg to __gup_device_* functions mm: introduce page_ref_sub_return() mm/gup: pass gup flags to two more routines mm/gup: require FOLL_GET for get_user_pages_fast() mm/gup: track FOLL_PIN pages mm/gup: page->hpage_pinned_refcount: exact pin counts for huge pages mm: dump_page(): better diagnostics for huge pinned pages mm/gup: /proc/vmstat: pin_user_pages (FOLL_PIN) reporting mm/gup_benchmark: support pin_user_pages() and related calls selftests/vm: run_vmtests: invoke gup_benchmark with basic FOLL_PIN coverage Documentation/core-api/pin_user_pages.rst | 53 +-- include/linux/mm.h | 108 ++++- include/linux/mm_types.h | 7 +- include/linux/mmzone.h | 2 + include/linux/page_ref.h | 10 + mm/debug.c | 60 ++- mm/gup.c | 459 ++++++++++++++++----- mm/gup_benchmark.c | 71 +++- mm/huge_memory.c | 29 +- mm/hugetlb.c | 44 +- mm/page_alloc.c | 2 + mm/rmap.c | 6 + mm/vmstat.c | 2 + tools/testing/selftests/vm/gup_benchmark.c | 15 +- tools/testing/selftests/vm/run_vmtests | 22 + 15 files changed, 715 insertions(+), 175 deletions(-) -- 2.25.0

5 years, 3 months

3
42
0 0

[PATCH v10 1/8] hugetlb_cgroup: Add hugetlb_cgroup reservation counter

by Mina Almasry

These counters will track hugetlb reservations rather than hugetlb memory faulted in. This patch only adds the counter, following patches add the charging and uncharging of the counter. This is patch 1 of an 8 patch series. Problem: Currently tasks attempting to reserve more hugetlb memory than is available get a failure at mmap/shmget time. This is thanks to Hugetlbfs Reservations [1]. However, if a task attempts to reserve hugetlb memory only more than its hugetlb_cgroup limit allows, the kernel will allow the mmap/shmget call, but will SIGBUS the task when it attempts to fault the memory in. We have users hitting their hugetlb_cgroup limits and thus we've been looking at this failure mode. We'd like to improve this behavior such that users violating the hugetlb_cgroup limits get an error on mmap/shmget time, rather than getting SIGBUS'd when they try to fault the excess memory in. This gives the user an opportunity to fallback more gracefully to non-hugetlbfs memory for example. The underlying problem is that today's hugetlb_cgroup accounting happens at hugetlb memory *fault* time, rather than at *reservation* time. Thus, enforcing the hugetlb_cgroup limit only happens at fault time, and the offending task gets SIGBUS'd. Proposed Solution: A new page counter named 'hugetlb.xMB.reservation_[limit|usage|max_usage]_in_bytes'. This counter has slightly different semantics than 'hugetlb.xMB.[limit|usage|max_usage]_in_bytes': - While usage_in_bytes tracks all *faulted* hugetlb memory, reservation_usage_in_bytes tracks all *reserved* hugetlb memory and hugetlb memory faulted in without a prior reservation. - If a task attempts to reserve more memory than limit_in_bytes allows, the kernel will allow it to do so. But if a task attempts to reserve more memory than reservation_limit_in_bytes, the kernel will fail this reservation. This proposal is implemented in this patch series, with tests to verify functionality and show the usage. Alternatives considered: 1. A new cgroup, instead of only a new page_counter attached to the existing hugetlb_cgroup. Adding a new cgroup seemed like a lot of code duplication with hugetlb_cgroup. Keeping hugetlb related page counters under hugetlb_cgroup seemed cleaner as well. 2. Instead of adding a new counter, we considered adding a sysctl that modifies the behavior of hugetlb.xMB.[limit|usage]_in_bytes, to do accounting at reservation time rather than fault time. Adding a new page_counter seems better as userspace could, if it wants, choose to enforce different cgroups differently: one via limit_in_bytes, and another via reservation_limit_in_bytes. This could be very useful if you're transitioning how hugetlb memory is partitioned on your system one cgroup at a time, for example. Also, someone may find usage for both limit_in_bytes and reservation_limit_in_bytes concurrently, and this approach gives them the option to do so. Testing: - Added tests passing. - Used libhugetlbfs for regression testing. [1]: https://www.kernel.org/doc/html/latest/vm/hugetlbfs_reserv.html Signed-off-by: Mina Almasry <almasrymina(a)google.com> --- Changes in v10: - Renamed reservation_* to resv.* --- include/linux/hugetlb.h | 4 +- mm/hugetlb_cgroup.c | 115 +++++++++++++++++++++++++++++++++++----- 2 files changed, 104 insertions(+), 15 deletions(-) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 1e897e4168ac1..dea6143aa0685 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -432,8 +432,8 @@ struct hstate { unsigned int surplus_huge_pages_node[MAX_NUMNODES]; #ifdef CONFIG_CGROUP_HUGETLB /* cgroup control files */ - struct cftype cgroup_files_dfl[5]; - struct cftype cgroup_files_legacy[5]; + struct cftype cgroup_files_dfl[7]; + struct cftype cgroup_files_legacy[9]; #endif char name[HSTATE_NAME_LEN]; }; diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index e434b05416c68..209f9b9604d34 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -36,6 +36,11 @@ struct hugetlb_cgroup { */ struct page_counter hugepage[HUGE_MAX_HSTATE]; + /* + * the counter to account for hugepage reservations from hugetlb. + */ + struct page_counter reserved_hugepage[HUGE_MAX_HSTATE]; + atomic_long_t events[HUGE_MAX_HSTATE][HUGETLB_NR_MEMORY_EVENTS]; atomic_long_t events_local[HUGE_MAX_HSTATE][HUGETLB_NR_MEMORY_EVENTS]; @@ -55,6 +60,14 @@ struct hugetlb_cgroup { static struct hugetlb_cgroup *root_h_cgroup __read_mostly; +static inline struct page_counter * +hugetlb_cgroup_get_counter(struct hugetlb_cgroup *h_cg, int idx, bool reserved) +{ + if (reserved) + return &h_cg->reserved_hugepage[idx]; + return &h_cg->hugepage[idx]; +} + static inline struct hugetlb_cgroup *hugetlb_cgroup_from_css(struct cgroup_subsys_state *s) { @@ -295,28 +308,42 @@ void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, enum { RES_USAGE, + RES_RESERVATION_USAGE, RES_LIMIT, + RES_RESERVATION_LIMIT, RES_MAX_USAGE, + RES_RESERVATION_MAX_USAGE, RES_FAILCNT, + RES_RESERVATION_FAILCNT, }; static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) { struct page_counter *counter; + struct page_counter *reserved_counter; struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); counter = &h_cg->hugepage[MEMFILE_IDX(cft->private)]; + reserved_counter = &h_cg->reserved_hugepage[MEMFILE_IDX(cft->private)]; switch (MEMFILE_ATTR(cft->private)) { case RES_USAGE: return (u64)page_counter_read(counter) * PAGE_SIZE; + case RES_RESERVATION_USAGE: + return (u64)page_counter_read(reserved_counter) * PAGE_SIZE; case RES_LIMIT: return (u64)counter->max * PAGE_SIZE; + case RES_RESERVATION_LIMIT: + return (u64)reserved_counter->max * PAGE_SIZE; case RES_MAX_USAGE: return (u64)counter->watermark * PAGE_SIZE; + case RES_RESERVATION_MAX_USAGE: + return (u64)reserved_counter->watermark * PAGE_SIZE; case RES_FAILCNT: return counter->failcnt; + case RES_RESERVATION_FAILCNT: + return reserved_counter->failcnt; default: BUG(); } @@ -338,10 +365,16 @@ static int hugetlb_cgroup_read_u64_max(struct seq_file *seq, void *v) 1 << huge_page_order(&hstates[idx])); switch (MEMFILE_ATTR(cft->private)) { + case RES_RESERVATION_USAGE: + counter = &h_cg->reserved_hugepage[idx]; + /* Fall through. */ case RES_USAGE: val = (u64)page_counter_read(counter); seq_printf(seq, "%llu\n", val * PAGE_SIZE); break; + case RES_RESERVATION_LIMIT: + counter = &h_cg->reserved_hugepage[idx]; + /* Fall through. */ case RES_LIMIT: val = (u64)counter->max; if (val == limit) @@ -365,6 +398,7 @@ static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of, int ret, idx; unsigned long nr_pages; struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of)); + bool reserved = false; if (hugetlb_cgroup_is_root(h_cg)) /* Can't set limit on root */ return -EINVAL; @@ -378,9 +412,14 @@ static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of, nr_pages = round_down(nr_pages, 1 << huge_page_order(&hstates[idx])); switch (MEMFILE_ATTR(of_cft(of)->private)) { + case RES_RESERVATION_LIMIT: + reserved = true; + /* Fall through. */ case RES_LIMIT: mutex_lock(&hugetlb_limit_mutex); - ret = page_counter_set_max(&h_cg->hugepage[idx], nr_pages); + ret = page_counter_set_max(hugetlb_cgroup_get_counter(h_cg, idx, + reserved), + nr_pages); mutex_unlock(&hugetlb_limit_mutex); break; default: @@ -406,18 +445,26 @@ static ssize_t hugetlb_cgroup_reset(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { int ret = 0; - struct page_counter *counter; + struct page_counter *counter, *reserved_counter; struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of)); counter = &h_cg->hugepage[MEMFILE_IDX(of_cft(of)->private)]; + reserved_counter = + &h_cg->reserved_hugepage[MEMFILE_IDX(of_cft(of)->private)]; switch (MEMFILE_ATTR(of_cft(of)->private)) { case RES_MAX_USAGE: page_counter_reset_watermark(counter); break; + case RES_RESERVATION_MAX_USAGE: + page_counter_reset_watermark(reserved_counter); + break; case RES_FAILCNT: counter->failcnt = 0; break; + case RES_RESERVATION_FAILCNT: + reserved_counter->failcnt = 0; + break; default: ret = -EINVAL; break; @@ -472,7 +519,7 @@ static void __init __hugetlb_cgroup_file_dfl_init(int idx) struct hstate *h = &hstates[idx]; /* format the size */ - mem_fmt(buf, 32, huge_page_size(h)); + mem_fmt(buf, sizeof(buf), huge_page_size(h)); /* Add the limit file */ cft = &h->cgroup_files_dfl[0]; @@ -482,15 +529,30 @@ static void __init __hugetlb_cgroup_file_dfl_init(int idx) cft->write = hugetlb_cgroup_write_dfl; cft->flags = CFTYPE_NOT_ON_ROOT; - /* Add the current usage file */ + /* Add the reservation limit file */ cft = &h->cgroup_files_dfl[1]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.resv.max", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_RESERVATION_LIMIT); + cft->seq_show = hugetlb_cgroup_read_u64_max; + cft->write = hugetlb_cgroup_write_dfl; + cft->flags = CFTYPE_NOT_ON_ROOT; + + /* Add the current usage file */ + cft = &h->cgroup_files_dfl[2]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.current", buf); cft->private = MEMFILE_PRIVATE(idx, RES_USAGE); cft->seq_show = hugetlb_cgroup_read_u64_max; cft->flags = CFTYPE_NOT_ON_ROOT; + /* Add the current reservation usage file */ + cft = &h->cgroup_files_dfl[3]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.resv.current", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_RESERVATION_USAGE); + cft->seq_show = hugetlb_cgroup_read_u64_max; + cft->flags = CFTYPE_NOT_ON_ROOT; + /* Add the events file */ - cft = &h->cgroup_files_dfl[2]; + cft = &h->cgroup_files_dfl[4]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.events", buf); cft->private = MEMFILE_PRIVATE(idx, 0); cft->seq_show = hugetlb_events_show; @@ -498,7 +560,7 @@ static void __init __hugetlb_cgroup_file_dfl_init(int idx) cft->flags = CFTYPE_NOT_ON_ROOT; /* Add the events.local file */ - cft = &h->cgroup_files_dfl[3]; + cft = &h->cgroup_files_dfl[5]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.events.local", buf); cft->private = MEMFILE_PRIVATE(idx, 0); cft->seq_show = hugetlb_events_local_show; @@ -507,7 +569,7 @@ static void __init __hugetlb_cgroup_file_dfl_init(int idx) cft->flags = CFTYPE_NOT_ON_ROOT; /* NULL terminate the last cft */ - cft = &h->cgroup_files_dfl[4]; + cft = &h->cgroup_files_dfl[6]; memset(cft, 0, sizeof(*cft)); WARN_ON(cgroup_add_dfl_cftypes(&hugetlb_cgrp_subsys, @@ -521,7 +583,7 @@ static void __init __hugetlb_cgroup_file_legacy_init(int idx) struct hstate *h = &hstates[idx]; /* format the size */ - mem_fmt(buf, 32, huge_page_size(h)); + mem_fmt(buf, sizeof(buf), huge_page_size(h)); /* Add the limit file */ cft = &h->cgroup_files_legacy[0]; @@ -530,28 +592,55 @@ static void __init __hugetlb_cgroup_file_legacy_init(int idx) cft->read_u64 = hugetlb_cgroup_read_u64; cft->write = hugetlb_cgroup_write_legacy; - /* Add the usage file */ + /* Add the reservation limit file */ cft = &h->cgroup_files_legacy[1]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.resv.limit_in_bytes", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_RESERVATION_LIMIT); + cft->read_u64 = hugetlb_cgroup_read_u64; + cft->write = hugetlb_cgroup_write_legacy; + + /* Add the usage file */ + cft = &h->cgroup_files_legacy[2]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.usage_in_bytes", buf); cft->private = MEMFILE_PRIVATE(idx, RES_USAGE); cft->read_u64 = hugetlb_cgroup_read_u64; + /* Add the reservation usage file */ + cft = &h->cgroup_files_legacy[3]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.resv.usage_in_bytes", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_RESERVATION_USAGE); + cft->read_u64 = hugetlb_cgroup_read_u64; + /* Add the MAX usage file */ - cft = &h->cgroup_files_legacy[2]; + cft = &h->cgroup_files_legacy[4]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.max_usage_in_bytes", buf); cft->private = MEMFILE_PRIVATE(idx, RES_MAX_USAGE); cft->write = hugetlb_cgroup_reset; cft->read_u64 = hugetlb_cgroup_read_u64; + /* Add the MAX reservation usage file */ + cft = &h->cgroup_files_legacy[5]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.resv.max_usage_in_bytes", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_RESERVATION_MAX_USAGE); + cft->write = hugetlb_cgroup_reset; + cft->read_u64 = hugetlb_cgroup_read_u64; + /* Add the failcntfile */ - cft = &h->cgroup_files_legacy[3]; + cft = &h->cgroup_files_legacy[6]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.failcnt", buf); - cft->private = MEMFILE_PRIVATE(idx, RES_FAILCNT); + cft->private = MEMFILE_PRIVATE(idx, RES_FAILCNT); + cft->write = hugetlb_cgroup_reset; + cft->read_u64 = hugetlb_cgroup_read_u64; + + /* Add the reservation failcntfile */ + cft = &h->cgroup_files_legacy[7]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.resv.failcnt", buf); + cft->private = MEMFILE_PRIVATE(idx, RES_RESERVATION_FAILCNT); cft->write = hugetlb_cgroup_reset; cft->read_u64 = hugetlb_cgroup_read_u64; /* NULL terminate the last cft */ - cft = &h->cgroup_files_legacy[4]; + cft = &h->cgroup_files_legacy[8]; memset(cft, 0, sizeof(*cft)); WARN_ON(cgroup_add_legacy_cftypes(&hugetlb_cgrp_subsys, -- 2.25.0.rc1.283.g88dfdc4193-goog

5 years, 3 months

4
23
0 0

[PATCH 0/3] Fix reconnection latency caused by FIN/ACK handling race

by sjpark＠amazon.com

From: SeongJae Park <sjpark(a)amazon.de> When closing a connection, the two acks that required to change closing socket's status to FIN_WAIT_2 and then TIME_WAIT could be processed in reverse order. This is possible in RSS disabled environments such as a connection inside a host. For example, expected state transitions and required packets for the disconnection will be similar to below flow. 00 (Process A) (Process B) 01 ESTABLISHED ESTABLISHED 02 close() 03 FIN_WAIT_1 04 ---FIN--> 05 CLOSE_WAIT 06 <--ACK--- 07 FIN_WAIT_2 08 <--FIN/ACK--- 09 TIME_WAIT 10 ---ACK--> 11 LAST_ACK 12 CLOSED CLOSED The acks in lines 6 and 8 are the acks. If the line 8 packet is processed before the line 6 packet, it will be just ignored as it is not a expected packet, and the later process of the line 6 packet will change the status of Process A to FIN_WAIT_2, but as it has already handled line 8 packet, it will not go to TIME_WAIT and thus will not send the line 10 packet to Process B. Thus, Process B will left in CLOSE_WAIT status, as below. 00 (Process A) (Process B) 01 ESTABLISHED ESTABLISHED 02 close() 03 FIN_WAIT_1 04 ---FIN--> 05 CLOSE_WAIT 06 (<--ACK---) 07 (<--FIN/ACK---) 08 (fired in right order) 09 <--FIN/ACK--- 10 <--ACK--- 11 (processed in reverse order) 12 FIN_WAIT_2 Later, if the Process B sends SYN to Process A for reconnection using the same port, Process A will responds with an ACK for the last flow, which has no increased sequence number. Thus, Process A will send RST, wait for TIMEOUT_INIT (one second in default), and then try reconnection. If reconnections are frequent, the one second latency spikes can be a big problem. Below is a tcpdump results of the problem: 14.436259 IP 127.0.0.1.45150 > 127.0.0.1.4242: Flags [S], seq 2560603644 14.436266 IP 127.0.0.1.4242 > 127.0.0.1.45150: Flags [.], ack 5, win 512 14.436271 IP 127.0.0.1.45150 > 127.0.0.1.4242: Flags [R], seq 2541101298 /* ONE SECOND DELAY */ 15.464613 IP 127.0.0.1.45150 > 127.0.0.1.4242: Flags [S], seq 2560603644 Patchset Organization --------------------- The first patch fix a trivial nit. The second one fix the problem by adjusting the resend delay of the SYN in the case. Finally, the third patch adds a user space test to reproduce this problem. The patches are based on the v5.5. You can also clone the complete git tree: $ git clone git://github.com/sjp38/linux -b patches/finack_lat/v1 The web is also available: https://github.com/sjp38/linux/tree/patches/finack_lat/v1 SeongJae Park (3): net/ipv4/inet_timewait_sock: Fix inconsistent comments tcp: Reduce SYN resend delay if a suspicous ACK is received selftests: net: Add FIN_ACK processing order related latency spike test net/ipv4/inet_timewait_sock.c | 1 + net/ipv4/tcp_input.c | 6 +- tools/testing/selftests/net/.gitignore | 2 + tools/testing/selftests/net/Makefile | 2 + tools/testing/selftests/net/fin_ack_lat.sh | 42 ++++++++++ .../selftests/net/fin_ack_lat_accept.c | 49 +++++++++++ .../selftests/net/fin_ack_lat_connect.c | 81 +++++++++++++++++++ 7 files changed, 182 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/net/fin_ack_lat.sh create mode 100644 tools/testing/selftests/net/fin_ack_lat_accept.c create mode 100644 tools/testing/selftests/net/fin_ack_lat_connect.c -- 2.17.1

5 years, 3 months

6
24
0 0

[PATCH v3 0/2] Fix reconnection latency caused by FIN/ACK handling race

by sj38.park＠gmail.com

From: SeongJae Park <sjpark(a)amazon.de> When closing a connection, the two acks that required to change closing socket's status to FIN_WAIT_2 and then TIME_WAIT could be processed in reverse order. This is possible in RSS disabled environments such as a connection inside a host. For example, expected state transitions and required packets for the disconnection will be similar to below flow. 00 (Process A) (Process B) 01 ESTABLISHED ESTABLISHED 02 close() 03 FIN_WAIT_1 04 ---FIN--> 05 CLOSE_WAIT 06 <--ACK--- 07 FIN_WAIT_2 08 <--FIN/ACK--- 09 TIME_WAIT 10 ---ACK--> 11 LAST_ACK 12 CLOSED CLOSED In some cases such as LINGER option applied socket, the FIN and FIN/ACK will be substituted to RST and RST/ACK, but there is no difference in the main logic. The acks in lines 6 and 8 are the acks. If the line 8 packet is processed before the line 6 packet, it will be just ignored as it is not a expected packet, and the later process of the line 6 packet will change the status of Process A to FIN_WAIT_2, but as it has already handled line 8 packet, it will not go to TIME_WAIT and thus will not send the line 10 packet to Process B. Thus, Process B will left in CLOSE_WAIT status, as below. 00 (Process A) (Process B) 01 ESTABLISHED ESTABLISHED 02 close() 03 FIN_WAIT_1 04 ---FIN--> 05 CLOSE_WAIT 06 (<--ACK---) 07 (<--FIN/ACK---) 08 (fired in right order) 09 <--FIN/ACK--- 10 <--ACK--- 11 (processed in reverse order) 12 FIN_WAIT_2 Later, if the Process B sends SYN to Process A for reconnection using the same port, Process A will responds with an ACK for the last flow, which has no increased sequence number. Thus, Process A will send RST, wait for TIMEOUT_INIT (one second in default), and then try reconnection. If reconnections are frequent, the one second latency spikes can be a big problem. Below is a tcpdump results of the problem: 14.436259 IP 127.0.0.1.45150 > 127.0.0.1.4242: Flags [S], seq 2560603644 14.436266 IP 127.0.0.1.4242 > 127.0.0.1.45150: Flags [.], ack 5, win 512 14.436271 IP 127.0.0.1.45150 > 127.0.0.1.4242: Flags [R], seq 2541101298 /* ONE SECOND DELAY */ 15.464613 IP 127.0.0.1.45150 > 127.0.0.1.4242: Flags [S], seq 2560603644 Patchset Organization --------------------- The first patch fixes the problem by adjusting the first resend delay of the SYN in the case. The second one adds a user space test to reproduce this problem. The patches are based on the v5.5. You can also clone the complete git tree: $ git clone git://github.com/sjp38/linux -b patches/finack_lat/v3 The web is also available: https://github.com/sjp38/linux/tree/patches/finack_lat/v3 Patchset History ---------------- >From v2 (https://lore.kernel.org/linux-kselftest/20200201071859.4231-1-sj38.park@gma…) - Use TCP_TIMEOUT_MIN as reduced delay (Neal Cardwall) - Add Reviewed-by and Signed-off-by from Eric Dumazet >From v1 (https://lore.kernel.org/linux-kselftest/20200131122421.23286-1-sjpark@amazo…) - Drop the trivial comment fix patch (Eric Dumazet) - Limit the delay adjustment to only the first SYN resend (Eric Dumazet) - selftest: Avoid use of hard-coded port number (Eric Dumazet) - Explain RST/ACK and FIN/ACK has no big difference (Neal Cardwell) SeongJae Park (2): tcp: Reduce SYN resend delay if a suspicous ACK is received selftests: net: Add FIN_ACK processing order related latency spike test net/ipv4/tcp_input.c | 8 +- tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 2 + tools/testing/selftests/net/fin_ack_lat.c | 151 +++++++++++++++++++++ tools/testing/selftests/net/fin_ack_lat.sh | 35 +++++ 5 files changed, 196 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/net/fin_ack_lat.c create mode 100755 tools/testing/selftests/net/fin_ack_lat.sh -- 2.17.1

5 years, 3 months

3
4
0 0

[PATCH v2 0/2] Fix reconnection latency caused by FIN/ACK handling race

by sj38.park＠gmail.com

From: SeongJae Park <sjpark(a)amazon.de> When closing a connection, the two acks that required to change closing socket's status to FIN_WAIT_2 and then TIME_WAIT could be processed in reverse order. This is possible in RSS disabled environments such as a connection inside a host. For example, expected state transitions and required packets for the disconnection will be similar to below flow. 00 (Process A) (Process B) 01 ESTABLISHED ESTABLISHED 02 close() 03 FIN_WAIT_1 04 ---FIN--> 05 CLOSE_WAIT 06 <--ACK--- 07 FIN_WAIT_2 08 <--FIN/ACK--- 09 TIME_WAIT 10 ---ACK--> 11 LAST_ACK 12 CLOSED CLOSED In some cases such as LINGER option applied socket, the FIN and FIN/ACK will be substituted to RST and RST/ACK, but there is no difference in the main logic. The acks in lines 6 and 8 are the acks. If the line 8 packet is processed before the line 6 packet, it will be just ignored as it is not a expected packet, and the later process of the line 6 packet will change the status of Process A to FIN_WAIT_2, but as it has already handled line 8 packet, it will not go to TIME_WAIT and thus will not send the line 10 packet to Process B. Thus, Process B will left in CLOSE_WAIT status, as below. 00 (Process A) (Process B) 01 ESTABLISHED ESTABLISHED 02 close() 03 FIN_WAIT_1 04 ---FIN--> 05 CLOSE_WAIT 06 (<--ACK---) 07 (<--FIN/ACK---) 08 (fired in right order) 09 <--FIN/ACK--- 10 <--ACK--- 11 (processed in reverse order) 12 FIN_WAIT_2 Later, if the Process B sends SYN to Process A for reconnection using the same port, Process A will responds with an ACK for the last flow, which has no increased sequence number. Thus, Process A will send RST, wait for TIMEOUT_INIT (one second in default), and then try reconnection. If reconnections are frequent, the one second latency spikes can be a big problem. Below is a tcpdump results of the problem: 14.436259 IP 127.0.0.1.45150 > 127.0.0.1.4242: Flags [S], seq 2560603644 14.436266 IP 127.0.0.1.4242 > 127.0.0.1.45150: Flags [.], ack 5, win 512 14.436271 IP 127.0.0.1.45150 > 127.0.0.1.4242: Flags [R], seq 2541101298 /* ONE SECOND DELAY */ 15.464613 IP 127.0.0.1.45150 > 127.0.0.1.4242: Flags [S], seq 2560603644 Patchset Organization --------------------- The first patch fixes the problem by adjusting the first resend delay of the SYN in the case. The second one adds a user space test to reproduce this problem. The patches are based on the v5.5. You can also clone the complete git tree: $ git clone git://github.com/sjp38/linux -b patches/finack_lat/v2 The web is also available: https://github.com/sjp38/linux/tree/patches/finack_lat/v2 Patchset History ---------------- >From v1 (https://lore.kernel.org/linux-kselftest/20200131122421.23286-1-sjpark@amazo…) - Drop the trivial comment fix patch (Eric Dumazet) - Limit the delay adjustment to only the first SYN resend (Eric Dumazet) - selftest: Avoid use of hard-coded port number (Eric Dumazet) - Explain RST/ACK and FIN/ACK has no big difference (Neal Cardwell) SeongJae Park (2): tcp: Reduce SYN resend delay if a suspicous ACK is received selftests: net: Add FIN_ACK processing order related latency spike test net/ipv4/tcp_input.c | 8 +- tools/testing/selftests/net/.gitignore | 2 + tools/testing/selftests/net/Makefile | 2 + tools/testing/selftests/net/fin_ack_lat.c | 151 +++++++++++++++++++++ tools/testing/selftests/net/fin_ack_lat.sh | 35 +++++ 5 files changed, 197 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/net/fin_ack_lat.c create mode 100755 tools/testing/selftests/net/fin_ack_lat.sh -- 2.17.1

5 years, 3 months

4
8
0 0

[PATCH v1] Documentation: kunit: fixed sphinx error in code block

by Brendan Higgins

Fix a missing newline in a code block that was causing a warning: Documentation/dev-tools/kunit/usage.rst:553: WARNING: Error in "code-block" directive: maximum 1 argument(s) allowed, 3 supplied. .. code-block:: bash modprobe example-test Signed-off-by: Brendan Higgins <brendanhiggins(a)google.com> --- Documentation/dev-tools/kunit/usage.rst | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst index 7cd56a1993b14..607758a66a99c 100644 --- a/Documentation/dev-tools/kunit/usage.rst +++ b/Documentation/dev-tools/kunit/usage.rst @@ -551,6 +551,7 @@ options to your ``.config``: Once the kernel is built and installed, a simple .. code-block:: bash + modprobe example-test ...will run the tests. -- 2.25.0.341.g760bfbb309-goog

5 years, 3 months

2
1
0 0

[PATCH] Kernel selftests: tpm2: check for tpm support

by Nikita Sobolev

tpm2 tests set fails if there is no /dev/tpm0 and /dev/tpmrm0 supported. Check if these files exist before run and mark test as skipped in case of absence. Signed-off-by: Nikita Sobolev <Nikita.Sobolev(a)synopsys.com> --- tools/testing/selftests/tpm2/test_smoke.sh | 13 +++++++++++-- tools/testing/selftests/tpm2/test_space.sh | 9 ++++++++- 2 files changed, 19 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/tpm2/test_smoke.sh b/tools/testing/selftests/tpm2/test_smoke.sh index 8155c2ea7ccb..b630c7b5950a 100755 --- a/tools/testing/selftests/tpm2/test_smoke.sh +++ b/tools/testing/selftests/tpm2/test_smoke.sh @@ -1,8 +1,17 @@ #!/bin/bash # SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) +self.flags = flags -python -m unittest -v tpm2_tests.SmokeTest -python -m unittest -v tpm2_tests.AsyncTest +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + + +if [ -f /dev/tpm0 ] ; then + python -m unittest -v tpm2_tests.SmokeTest + python -m unittest -v tpm2_tests.AsyncTest +else + exit $ksft_skip +fi CLEAR_CMD=$(which tpm2_clear) if [ -n $CLEAR_CMD ]; then diff --git a/tools/testing/selftests/tpm2/test_space.sh b/tools/testing/selftests/tpm2/test_space.sh index a6f5e346635e..180b469c53b4 100755 --- a/tools/testing/selftests/tpm2/test_space.sh +++ b/tools/testing/selftests/tpm2/test_space.sh @@ -1,4 +1,11 @@ #!/bin/bash # SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) -python -m unittest -v tpm2_tests.SpaceTest +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +if [ -f /dev/tpmrm0 ] ; then + python -m unittest -v tpm2_tests.SpaceTest +else + exit $ksft_skip +fi -- 2.16.2

5 years, 3 months

1
0
0 0

[PATCH][RESEND] selftests/ftrace: Have pid filter test use instance flag

by Steven Rostedt

From: "Steven Rostedt (VMware)" <rostedt(a)goodmis.org> While running the ftracetests, the pid filter test failed because the instance "foo" existed, and it was using it to rerun the test under a instance named foo. The collision caused the test to fail as the mkdir failed as the name already existed. As of commit b5b77be812de7 ("selftests: ftrace: Allow some tests to be run in a tracing instance") all a selftest needs to do to be tested in an instance is to set the "instance" flag. There's no reason a selftest needs to create an instance to run its test in an instance directly. Remove the open coded testing in an instance for the pid filter test and have it set the "instance" flag instead. Signed-off-by: Steven Rostedt (VMware) <rostedt(a)goodmis.org> --- .../selftests/ftrace/test.d/ftrace/func-filter-pid.tc | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc index 64cfcc75e3c1..f2ee1e889e13 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc @@ -1,6 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: ftrace - function pid filters +# flags: instance # Make sure that function pid matching filter works. # Also test it on an instance directory @@ -96,13 +97,6 @@ do_test() { } do_test - -mkdir instances/foo -cd instances/foo -do_test -cd ../../ -rmdir instances/foo - do_reset exit 0 -- 2.20.1

5 years, 3 months

2
1
0 0

[PATCH v2 0/8] mm/gup: track FOLL_PIN pages (follow on from v12)

by John Hubbard

OK, as requested, I've split the tracking patch into 6 smaller patches, and it should be *much* easier to understand and review now. ============================================================ Changes since v1: * Split the tracking patch into 6 smaller patches * Rebased onto today's linux-next/akpm (there weren't any conflicts). * Fixed an "unsigned int" vs. "int" problem in gup_benchmark, reported by Nathan Chancellor. (I don't see it in my local builds, probably because they use gcc, but an LLVM test found the mismatch.) * Fixed a huge page pincount problem (add/subtract vs. increment/decrement), spotted by Jan Kara. ============================================================ There is a reasonable case to be made for merging two of the patches (patches 4 and 5), given that patch 4 provides tracking that has upper limits on the number of pins that can be done with huge pages. Let me know if anyone wants those merged, but unless there is some weird chance of someone grabbing patch 4 and not patch 5, I don't really see the need. Meanwhile, it's easier to review in this form. Also, patch 3 has been revived. Earlier reviewers asked for it to be merged into the tracking patch (one cannot please everyone, heh), but now it's back out on it's own. This activates tracking of FOLL_PIN pages. This is in support of fixing the get_user_pages()+DMA problem described in [1]-[4]. It is based on today's (Jan 28) linux-next (branch: akpm), commit 280e9cb00b41 ("drivers/media/platform/sti/delta/delta-ipc.c: fix read buffer overflow") There is a git repo and branch, for convenience in reviewing: git@github.com:johnhubbard/linux.git track_user_pages_v2_linux-next_akpm_28Jan2020 FOLL_PIN support is (so far) in mmotm and linux-next. However, the patch to use FOLL_PIN to track pages was *not* submitted, because Leon saw an RDMA test suite failure that involved (I think) page refcount overflows when huge pages were used. This patch definitively solves that kind of overflow problem, by adding an exact pincount, for compound pages (of order > 1), in the 3rd struct page of a compound page. If available, that form of pincounting is used, instead of the GUP_PIN_COUNTING_BIAS approach. Thanks again to Jan Kara for that idea. Here's the last reviewed version of the tracking patch (v11): https://lore.kernel.org/r/20191216222537.491123-1-jhubbard@nvidia.com Jan Kara had provided a reviewed-by tag for that, but I've had to remove it (again) here, due to having changed the patch "a little bit", in order to add the feature described above. Other interesting changes: * dump_page(): added one, or two new things to report for compound pages: head refcount (for all compound pages), and map_pincount (for compound pages of order > 1). * Documentation/core-api/pin_user_pages.rst: removed the "TODO" for the huge page refcount upper limit problems, and added notes about how it works now. Also added a note about the dump_page() enhancements. * Added some comments in gup.c and mm.h, to explain that there are two ways to count pinned pages: exact (for compound pages of order > 1) and fuzzy (GUP_PIN_COUNTING_BIAS: for all other pages). ============================================================ General notes about the tracking patch: This is a prerequisite to solving the problem of proper interactions between file-backed pages, and [R]DMA activities, as discussed in [1], [2], [3], [4] and in a remarkable number of email threads since about 2017. :) In contrast to earlier approaches, the page tracking can be incrementally applied to the kernel call sites that, until now, have been simply calling get_user_pages() ("gup"). In other words, opt-in by changing from this: get_user_pages() (sets FOLL_GET) put_page() to this: pin_user_pages() (sets FOLL_PIN) unpin_user_page() ============================================================ Next steps: * Convert more subsystems from get_user_pages() to pin_user_pages(). * Work with Ira and others to connect this all up with file system leases. [1] Some slow progress on get_user_pages() (Apr 2, 2019): https://lwn.net/Articles/784574/ [2] DMA and get_user_pages() (LPC: Dec 12, 2018): https://lwn.net/Articles/774411/ [3] The trouble with get_user_pages() (Apr 30, 2018): https://lwn.net/Articles/753027/ [4] LWN kernel index: get_user_pages() https://lwn.net/Kernel/Index/#Memory_management-get_user_pages John Hubbard (8): mm: dump_page: print head page's refcount, for compound pages mm/gup: split get_user_pages_remote() into two routines mm/gup: pass a flags arg to __gup_device_* functions mm/gup: track FOLL_PIN pages mm/gup: page->hpage_pinned_refcount: exact pin counts for huge pages mm/gup: /proc/vmstat: pin_user_pages (FOLL_PIN) reporting mm/gup_benchmark: support pin_user_pages() and related calls selftests/vm: run_vmtests: invoke gup_benchmark with basic FOLL_PIN coverage Documentation/core-api/pin_user_pages.rst | 47 +-- include/linux/mm.h | 109 ++++- include/linux/mm_types.h | 7 +- include/linux/mmzone.h | 2 + include/linux/page_ref.h | 10 + mm/debug.c | 22 +- mm/gup.c | 460 ++++++++++++++++----- mm/gup_benchmark.c | 71 +++- mm/huge_memory.c | 29 +- mm/hugetlb.c | 44 +- mm/page_alloc.c | 2 + mm/rmap.c | 6 + mm/vmstat.c | 2 + tools/testing/selftests/vm/gup_benchmark.c | 15 +- tools/testing/selftests/vm/run_vmtests | 22 + 15 files changed, 681 insertions(+), 167 deletions(-) -- 2.25.0

5 years, 3 months

3
17
0 0

[PATCH v2 kunit-next 0/3] kunit: add debugfs representation to show results/run tests

by Alan Maguire

When kunit tests are run on native (i.e. non-UML) environments, the results of test execution are often intermixed with dmesg output. This patch series attempts to solve this by providing a debugfs representation of the results of the last test run, available as /sys/kernel/debug/kunit/<testsuite>/results In addition, we provide a way to re-run the tests and show results via /sys/kernel/debug/kunit/<testsuite>/run Changes since v1: - trimmed unneeded include files in lib/kunit/debugfs.c (Greg) - renamed global debugfs functions to be prefixed with kunit_ (Greg) - removed error checking for debugfs operations (Greg) Alan Maguire (3): kunit: add debugfs /sys/kernel/debug/kunit/<suite>/results display kunit: add "run" debugfs file to run suites, display results kunit: update documentation to describe debugfs representation Documentation/dev-tools/kunit/usage.rst | 19 +++++ include/kunit/test.h | 21 +++-- lib/kunit/Makefile | 3 +- lib/kunit/debugfs.c | 137 ++++++++++++++++++++++++++++++++ lib/kunit/debugfs.h | 16 ++++ lib/kunit/test.c | 85 +++++++++++++++----- 6 files changed, 254 insertions(+), 27 deletions(-) create mode 100644 lib/kunit/debugfs.c create mode 100644 lib/kunit/debugfs.h -- 1.8.3.1

5 years, 3 months

2
7
0 0

[PATCH v1 0/7] kunit: create a centralized executor to dispatch all KUnit tests

by Brendan Higgins

## TL;DR This patchset adds a centralized executor to dispatch tests rather than relying on late_initcall to schedule each test suite separately along with a couple of new features that depend on it. ## What am I trying to do? Conceptually, I am trying to provide a mechanism by which test suites can be grouped together so that they can be reasoned about collectively. The last two of three patches in this series add features which depend on this: PATCH 5/7 Prints out a test plan right before KUnit tests are run[1]; this is valuable because it makes it possible for a test harness to detect whether the number of tests run matches the number of tests expected to be run, ensuring that no tests silently failed. PATCH 6/7 Add a new kernel command-line option which allows the user to specify that the kernel poweroff, halt, or reboot after completing all KUnit tests; this is very handy for running KUnit tests on UML or a VM so that the UML/VM process exits cleanly immediately after running all tests without needing a special initramfs. In addition, by dispatching tests from a single location, we can guarantee that all KUnit tests run after late_init is complete, which was a concern during the initial KUnit patchset review (this has not been a problem in practice, but resolving with certainty is nevertheless desirable). Other use cases for this exist, but the above features should provide an idea of the value that this could provide. Alan Maguire (1): kunit: test: create a single centralized executor for all tests Brendan Higgins (5): vmlinux.lds.h: add linker section for KUnit test suites arch: um: add linker section for KUnit test suites init: main: add KUnit to kernel init kunit: test: add test plan to KUnit TAP format Documentation: Add kunit_shutdown to kernel-parameters.txt David Gow (1): kunit: Add 'kunit_shutdown' option .../admin-guide/kernel-parameters.txt | 7 ++ arch/um/include/asm/common.lds.S | 4 + include/asm-generic/vmlinux.lds.h | 8 ++ include/kunit/test.h | 82 ++++++++++++------- init/main.c | 4 + lib/kunit/Makefile | 3 +- lib/kunit/executor.c | 71 ++++++++++++++++ lib/kunit/test.c | 11 --- tools/testing/kunit/kunit_kernel.py | 2 +- tools/testing/kunit/kunit_parser.py | 76 ++++++++++++++--- .../test_is_test_passed-all_passed.log | 1 + .../test_data/test_is_test_passed-crash.log | 1 + .../test_data/test_is_test_passed-failure.log | 1 + 13 files changed, 217 insertions(+), 54 deletions(-) create mode 100644 lib/kunit/executor.c -- 2.25.0.341.g760bfbb309-goog

5 years, 3 months

2
14
0 0

[PATCH] wireguard: selftests: Cleanup CONFIG_ENABLE_WARN_DEPRECATED

by Krzysztof Kozlowski

CONFIG_ENABLE_WARN_DEPRECATED is gone since commit 771c035372a0 ("deprecate the '__deprecated' attribute warnings entirely and for good"). Signed-off-by: Krzysztof Kozlowski <krzk(a)kernel.org> --- tools/testing/selftests/wireguard/qemu/debug.config | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config index b9c72706fe4d..5909e7ef2a5c 100644 --- a/tools/testing/selftests/wireguard/qemu/debug.config +++ b/tools/testing/selftests/wireguard/qemu/debug.config @@ -1,5 +1,4 @@ CONFIG_LOCALVERSION="-debug" -CONFIG_ENABLE_WARN_DEPRECATED=y CONFIG_ENABLE_MUST_CHECK=y CONFIG_FRAME_POINTER=y CONFIG_STACK_VALIDATION=y -- 2.17.1

5 years, 3 months

2
1
0 0

[PATCH v16 00/23] selftests, powerpc, x86: Memory Protection Keys

by Sandipan Das

Memory protection keys enables an application to protect its address space from inadvertent access by its own code. This feature is now enabled on powerpc and has been available since 4.16-rc1. The patches move the selftests to arch neutral directory and enhance their test coverage. Tested on powerpc64 and x86_64 (Skylake-SP). Link to development branch: https://github.com/sandip4n/linux/tree/pkey-selftests Changelog --------- Link to previous version (v16): https://patchwork.ozlabs.org/project/linuxppc-dev/list/?series=153824 v17: (1) Fixed issues with i386 builds when running on x86_64 based on feedback from Dave. (2) Replaced patch 6 from previous version with patch 7. This addresses u64 format specifier related concerns that Michael had raised in v15. v16: (1) Rebased on top of latest master. (2) Switched to u64 instead of using an arch-dependent pkey_reg_t type for references to the pkey register based on suggestions from Dave, Michal and Michael. (3) Removed build time determination of page size based on suggestion from Michael. (4) Fixed comment before the definition of __page_o_noops() from patch 13 ("selftests/vm/pkeys: Introduce powerpc support"). v15: (1) Rebased on top of latest master. (2) Addressed review comments from Dave Hansen. (3) Moved code for getting or setting pkey bits to new helpers. These changes replace patch 7 of v14. (4) Added a fix which ensures that the correct count of reserved keys is used across different platforms. (5) Added a fix which ensures that the correct page size is used as powerpc supports both 4K and 64K pages. v14: (1) Incorporated another round of comments from Dave Hansen. v13: (1) Incorporated comments for Dave Hansen. (2) Added one more test for correct pkey-0 behavior. v12: (1) Fixed the offset of pkey field in the siginfo structure for x86_64 and powerpc. And tries to use the actual field if the headers have it defined. v11: (1) Fixed a deadlock in the ptrace testcase. v10 and prior: (1) Moved the testcase to arch neutral directory. (2) Split the changes into incremental patches. Desnes A. Nunes do Rosario (1): selftests/vm/pkeys: Fix number of reserved powerpc pkeys Ram Pai (16): selftests/x86/pkeys: Move selftests to arch-neutral directory selftests/vm/pkeys: Rename all references to pkru to a generic name selftests/vm/pkeys: Move generic definitions to header file selftests/vm/pkeys: Fix pkey_disable_clear() selftests/vm/pkeys: Fix assertion in pkey_disable_set/clear() selftests/vm/pkeys: Fix alloc_random_pkey() to make it really random selftests/vm/pkeys: Introduce generic pkey abstractions selftests/vm/pkeys: Introduce powerpc support selftests/vm/pkeys: Fix assertion in test_pkey_alloc_exhaust() selftests/vm/pkeys: Improve checks to determine pkey support selftests/vm/pkeys: Associate key on a mapped page and detect access violation selftests/vm/pkeys: Associate key on a mapped page and detect write violation selftests/vm/pkeys: Detect write violation on a mapped access-denied-key page selftests/vm/pkeys: Introduce a sub-page allocator selftests/vm/pkeys: Test correct behaviour of pkey-0 selftests/vm/pkeys: Override access right definitions on powerpc Sandipan Das (5): selftests: vm: pkeys: Fix multilib builds for x86 selftests: vm: pkeys: Use sane types for pkey register selftests: vm: pkeys: Add helpers for pkey bits selftests: vm: pkeys: Use the correct huge page size selftests: vm: pkeys: Use the correct page size on powerpc Thiago Jung Bauermann (2): selftests/vm/pkeys: Move some definitions to arch-specific header selftests/vm/pkeys: Make gcc check arguments of sigsafe_printf() tools/testing/selftests/vm/.gitignore | 1 + tools/testing/selftests/vm/Makefile | 50 ++ tools/testing/selftests/vm/pkey-helpers.h | 225 ++++++ tools/testing/selftests/vm/pkey-powerpc.h | 136 ++++ tools/testing/selftests/vm/pkey-x86.h | 181 +++++ .../selftests/{x86 => vm}/protection_keys.c | 696 ++++++++++-------- tools/testing/selftests/x86/.gitignore | 1 - tools/testing/selftests/x86/Makefile | 2 +- tools/testing/selftests/x86/pkey-helpers.h | 219 ------ 9 files changed, 979 insertions(+), 532 deletions(-) create mode 100644 tools/testing/selftests/vm/pkey-helpers.h create mode 100644 tools/testing/selftests/vm/pkey-powerpc.h create mode 100644 tools/testing/selftests/vm/pkey-x86.h rename tools/testing/selftests/{x86 => vm}/protection_keys.c (74%) delete mode 100644 tools/testing/selftests/x86/pkey-helpers.h -- 2.17.1

5 years, 3 months

3
33
0 0

[GIT PULL] Kselftest kunit update for Linux 5.6-rc1

by Shuah Khan

Hi Linus, Please pull the following Kselftest kunit update for Linux 5.6-rc1 This kunit update for Linux 5.6-rc1 consists of: -- Support for building kunit as a module from Alan Maguire -- AppArmor KUnit tests for policy unpack from Mike Salvatore diff is attached. thanks, -- Shuah ---------------------------------------------------------------- The following changes since commit c79f46a282390e0f5b306007bf7b11a46d529538: Linux 5.5-rc5 (2020-01-05 14:23:27 -0800) are available in the Git repository at: git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest tags/linux-kselftest-5.6-rc1-kunit for you to fetch changes up to 35c57fc3f8eac81b38664a0fe160e267b908d8b8: kunit: building kunit as a module breaks allmodconfig (2020-01-10 14:36:37 -0700) ---------------------------------------------------------------- linux-kselftest-5.6-rc1-kunit This kunit update for Linux 5.6-rc1 consists of: -- Support for building kunit as a module from Alan Maguire -- AppArmor KUnit tests for policy unpack from Mike Salvatore ---------------------------------------------------------------- Alan Maguire (7): kunit: move string-stream.h to lib/kunit kunit: hide unexported try-catch interface in try-catch-impl.h kunit: allow kunit tests to be loaded as a module kunit: remove timeout dependence on sysctl_hung_task_timeout_seconds kunit: allow kunit to be loaded as a module kunit: update documentation to describe module-based build kunit: building kunit as a module breaks allmodconfig Mike Salvatore (1): apparmor: add AppArmor KUnit tests for policy unpack Documentation/dev-tools/kunit/faq.rst | 3 +- Documentation/dev-tools/kunit/index.rst | 3 + Documentation/dev-tools/kunit/usage.rst | 16 + drivers/base/Kconfig | 2 +- drivers/base/power/qos-test.c | 2 +- fs/ext4/Kconfig | 2 +- fs/ext4/Makefile | 3 +- fs/ext4/inode-test.c | 4 +- include/kunit/assert.h | 3 +- include/kunit/test.h | 37 +- include/kunit/try-catch.h | 10 - kernel/sysctl-test.c | 4 +- lib/Kconfig.debug | 4 +- lib/kunit/Kconfig | 6 +- lib/kunit/Makefile | 14 +- lib/kunit/assert.c | 10 + lib/kunit/{example-test.c => kunit-example-test.c} | 4 +- lib/kunit/{test-test.c => kunit-test.c} | 7 +- lib/kunit/string-stream-test.c | 5 +- lib/kunit/string-stream.c | 3 +- {include => lib}/kunit/string-stream.h | 0 lib/kunit/test.c | 25 +- lib/kunit/try-catch-impl.h | 27 + lib/kunit/try-catch.c | 37 +- lib/list-test.c | 4 +- security/apparmor/Kconfig | 16 + security/apparmor/policy_unpack.c | 4 + security/apparmor/policy_unpack_test.c | 607 +++++++++++++++++++++ 28 files changed, 788 insertions(+), 74 deletions(-) rename lib/kunit/{example-test.c => kunit-example-test.c} (97%) rename lib/kunit/{test-test.c => kunit-test.c} (98%) rename {include => lib}/kunit/string-stream.h (100%) create mode 100644 lib/kunit/try-catch-impl.h create mode 100644 security/apparmor/policy_unpack_test.c ----------------------------------------------------------------

5 years, 3 months

2
1
0 0

[GIT PULL] Kselftest update for Linux 5.6-rc1

by Shuah Khan

Hi Linus, Please pull the following Kselftest update for Linux 5.6-rc1 This Kselftest update for Linux 5.6-rc1 consists of several fixes to framework and individual tests. In addition, it enables LKDTM tests adding lkdtm target to kselftest Makefile. diff is attached. thanks, -- Shuah ---------------------------------------------------------------- The following changes since commit c79f46a282390e0f5b306007bf7b11a46d529538: Linux 5.5-rc5 (2020-01-05 14:23:27 -0800) are available in the Git repository at: git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest tags/linux-kselftest-5.6-rc1 for you to fetch changes up to af4ddd607dff7aabd466a4a878e01b9f592a75ab: selftests/ftrace: fix glob selftest (2020-01-28 13:36:48 -0700) ---------------------------------------------------------------- linux-kselftest-5.6-rc1 This Kselftest update for Linux 5.6-rc1 consists of several fixes to framework and individual tests. In addition, it enables LKDTM tests adding lkdtm target to kselftest Makefile. ---------------------------------------------------------------- Cristian Marussi (1): selftests: fix build behaviour on targets' failures Dan Carpenter (1): selftests: Uninitialized variable in test_cgcore_proc_migration() Kees Cook (1): selftests/lkdtm: Add tests for LKDTM targets Matthieu Baerts (1): selftests: settings: tests can be in subsubdirs Miroslav Benes (2): selftests/livepatch: Replace set_dynamic_debug() with setup_config() in README selftests/livepatch: Remove unused local variable in set_ftrace_enabled() Siddhesh Poyarekar (1): kselftest: Minimise dependency of get_size on C library interfaces Sven Schnelle (1): selftests/ftrace: fix glob selftest MAINTAINERS | 1 + tools/testing/selftests/Makefile | 19 +++-- tools/testing/selftests/cgroup/test_core.c | 2 +- .../ftrace/test.d/ftrace/func-filter-glob.tc | 2 +- tools/testing/selftests/kselftest/runner.sh | 2 +- tools/testing/selftests/livepatch/README | 2 +- tools/testing/selftests/livepatch/functions.sh | 1 - tools/testing/selftests/lkdtm/Makefile | 12 +++ tools/testing/selftests/lkdtm/config | 1 + tools/testing/selftests/lkdtm/run.sh | 92 ++++++++++++++++++++++ tools/testing/selftests/lkdtm/tests.txt | 71 +++++++++++++++++ tools/testing/selftests/size/get_size.c | 24 ++++-- 12 files changed, 211 insertions(+), 18 deletions(-) create mode 100644 tools/testing/selftests/lkdtm/Makefile create mode 100644 tools/testing/selftests/lkdtm/config create mode 100755 tools/testing/selftests/lkdtm/run.sh create mode 100644 tools/testing/selftests/lkdtm/tests.txt ----------------------------------------------------------------

5 years, 3 months

2
1
0 0

[PATCH 0/3] mm/gup: track FOLL_PIN pages (follow on from v12)

by John Hubbard

Leon Romanovsky: If you get a chance, I'd love to have this short series (or even just the first patch; the others are just selftests) run through your test suite that was previously choking on my earlier v11 patchset. The huge page pincount limitations are removed, so I'm expecting a perfect test run this time! Everyone: This activates tracking of FOLL_PIN pages. This is in support of fixing the get_user_pages()+DMA problem described in [1]-[4]. It is based on today's (Jan 24) mmotm. There is a git repo and branch, for convenience in reviewing: git@github.com:johnhubbard/linux.git track_user_pages_v1_mmotm_24Jan2020 FOLL_PIN support is (so far) in mmotm and linux-next. However, the patch to use FOLL_PIN to track pages was *not* submitted, because Leon saw an RDMA test suite failure that involved (I think) page refcount overflows when huge pages were used. This patch definitively solves that kind of overflow problem, by adding an exact pincount, for compound pages (of order > 1), in the 3rd struct page of a compound page. If available, that form of pincounting is used, instead of the GUP_PIN_COUNTING_BIAS approach. Thanks again to Jan Kara for that idea. Here's the last reviewed version of the tracking patch (v11): https://lore.kernel.org/r/20191216222537.491123-1-jhubbard@nvidia.com Jan Kara had provided a reviewed-by tag for that, but I've had to remove it (again) here, due to having changed the patch "a little bit", in order to add the feature described above. Other interesting changes: * dump_page(): added one, or two new things to report for compound pages: head refcount (for all compound pages), and map_pincount (for compound pages of order > 1). * Documentation/core-api/pin_user_pages.rst: removed the "TODO" for the huge page refcount upper limit problems, and added notes about how it works now. Also added a note about the dump_page() enhancements. * Added some comments in gup.c and mm.h, to explain that there are two ways to count pinned pages: exact (for compound pages of order > 1) and fuzzy (GUP_PIN_COUNTING_BIAS: for all other pages). ============================================================ General notes about the tracking patch: This is a prerequisite to solving the problem of proper interactions between file-backed pages, and [R]DMA activities, as discussed in [1], [2], [3], [4] and in a remarkable number of email threads since about 2017. :) In contrast to earlier approaches, the page tracking can be incrementally applied to the kernel call sites that, until now, have been simply calling get_user_pages() ("gup"). In other words, opt-in by changing from this: get_user_pages() (sets FOLL_GET) put_page() to this: pin_user_pages() (sets FOLL_PIN) unpin_user_page() ============================================================ Next steps: * Convert more subsystems from get_user_pages() to pin_user_pages(). * Work with Ira and others to connect this all up with file system leases. [1] Some slow progress on get_user_pages() (Apr 2, 2019): https://lwn.net/Articles/784574/ [2] DMA and get_user_pages() (LPC: Dec 12, 2018): https://lwn.net/Articles/774411/ [3] The trouble with get_user_pages() (Apr 30, 2018): https://lwn.net/Articles/753027/ [4] LWN kernel index: get_user_pages() https://lwn.net/Kernel/Index/#Memory_management-get_user_pages John Hubbard (3): mm/gup: track FOLL_PIN pages mm/gup_benchmark: support pin_user_pages() and related calls selftests/vm: run_vmtests: invoke gup_benchmark with basic FOLL_PIN coverage Documentation/core-api/pin_user_pages.rst | 48 ++- include/linux/mm.h | 109 ++++- include/linux/mm_types.h | 7 +- include/linux/mmzone.h | 2 + include/linux/page_ref.h | 10 + mm/debug.c | 22 +- mm/gup.c | 467 ++++++++++++++++----- mm/gup_benchmark.c | 70 ++- mm/huge_memory.c | 29 +- mm/hugetlb.c | 44 +- mm/page_alloc.c | 2 + mm/rmap.c | 6 + mm/vmstat.c | 2 + tools/testing/selftests/vm/gup_benchmark.c | 15 +- tools/testing/selftests/vm/run_vmtests | 22 + 15 files changed, 678 insertions(+), 177 deletions(-) -- 2.25.0

5 years, 3 months

5
12
0 0

Re: [PATCH v3] selftests/ftrace: fix glob selftest

by Shuah Khan

On Mon, Jan 27, 2020 at 6:23 AM Sven Schnelle <svens(a)linux.ibm.com> wrote: > > Hi Steve, > > On Wed, Jan 08, 2020 at 09:11:55AM -0500, Steven Rostedt wrote: > > > > Shuah, > > > > Want to take this through your tree? > > > > https://lore.kernel.org/r/20200108074043.21580-1-svens@linux.ibm.com > > > > Reviewed-by: Steven Rostedt (VMware) <rostedt(a)goodmis.org> > > As Shuah didn't reply, can you push that through your tree? > Hi Sven, Did you run getmaintainers of this patch? You didn't send this to my email address listed in the get maintainers file and also didn't cc linux-kselftest. I just happen to notice this now. Please resend with steve's Reviewed-by tag to the recipients suggested by get_maintainers.pl I will take this through ksleftest tree. thanks, -- Shuah

5 years, 3 months

2
1
0 0

[PATCH v4] selftests/ftrace: fix glob selftest

by Sven Schnelle

test.d/ftrace/func-filter-glob.tc is failing on s390 because it has ARCH_INLINE_SPIN_LOCK and friends set to 'y'. So the usual __raw_spin_lock symbol isn't in the ftrace function list. Change '*aw*lock' to '*spin*lock' which would hopefully match some of the locking functions on all platforms. Reviewed-by: Steven Rostedt (VMware) <rostedt(a)goodmis.org> Signed-off-by: Sven Schnelle <svens(a)linux.ibm.com> --- Changes in v4: - rebase to latest master Changes in v3: change '*spin*lock' to '*pin*lock' to not match the beginning Changes in v2: use '*spin*lock' instead of '*ktime*ns' .../testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc index 27a54a17da65..f4e92afab14b 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc @@ -30,7 +30,7 @@ ftrace_filter_check '*schedule*' '^.*schedule.*$' ftrace_filter_check 'schedule*' '^schedule.*$' # filter by *mid*end -ftrace_filter_check '*aw*lock' '.*aw.*lock$' +ftrace_filter_check '*pin*lock' '.*pin.*lock$' # filter by start*mid* ftrace_filter_check 'mutex*try*' '^mutex.*try.*' -- 2.17.1

5 years, 3 months

1
0
0 0

[PATCH] selftests: settings: tests can be in subsubdirs

by Matthieu Baerts

Commit 852c8cbf34d3 (selftests/kselftest/runner.sh: Add 45 second timeout per test) adds support for a new per-test-directory "settings" file. But this only works for tests not in a sub-subdirectories, e.g. - tools/testing/selftests/rtc (rtc) is OK, - tools/testing/selftests/net/mptcp (net/mptcp) is not. We have to increase the timeout for net/mptcp tests which are not upstreamed yet but this fix is valid for other tests if they need to add a "settings" file, see the full list with: tools/testing/selftests/*/*/**/Makefile Note that this patch changes the text header message printed at the end of the execution but this text is modified only for the tests that are in sub-subdirectories, e.g. ok 1 selftests: net/mptcp: mptcp_connect.sh Before we had: ok 1 selftests: mptcp: mptcp_connect.sh But showing the full target name is probably better, just in case a subsubdir has the same name as another one in another subdirectory. Fixes: 852c8cbf34d3 (selftests/kselftest/runner.sh: Add 45 second timeout per test) Signed-off-by: Matthieu Baerts <matthieu.baerts(a)tessares.net> --- tools/testing/selftests/kselftest/runner.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh index 84de7bc74f2c..0d7a89901ef7 100644 --- a/tools/testing/selftests/kselftest/runner.sh +++ b/tools/testing/selftests/kselftest/runner.sh @@ -90,7 +90,7 @@ run_one() run_many() { echo "TAP version 13" - DIR=$(basename "$PWD") + DIR="${PWD#${BASE_DIR}/}" test_num=0 total=$(echo "$@" | wc -w) echo "1..$total" -- 2.20.1

5 years, 3 months

3
5
0 0

[PATCH v4 00/10] Create a userfaultfd demand paging test

by Ben Gardon

When handling page faults for many vCPUs during demand paging, KVM's MMU lock becomes highly contended. This series creates a test with a naive userfaultfd based demand paging implementation to demonstrate that contention. This test serves both as a functional test of userfaultfd and a microbenchmark of demand paging performance with a variable number of vCPUs and memory per vCPU. The test creates N userfaultfd threads, N vCPUs, and a region of memory with M pages per vCPU. The N userfaultfd polling threads are each set up to serve faults on a region of memory corresponding to one of the vCPUs. Each of the vCPUs is then started, and touches each page of its disjoint memory region, sequentially. In response to faults, the userfaultfd threads copy a static buffer into the guest's memory. This creates a worst case for MMU lock contention as we have removed most of the contention between the userfaultfd threads and there is no time required to fetch the contents of guest memory. This test was run successfully on Intel Haswell, Broadwell, and Cascadelake hosts with a variety of vCPU counts and memory sizes. This test was adapted from the dirty_log_test. The series can also be viewed in Gerrit here: https://linux-review.googlesource.com/c/virt/kvm/kvm/+/1464 (Thanks to Dmitry Vyukov <dvyukov(a)google.com> for setting up the Gerrit instance) v4 (Responding to feedback from Andrew Jones, Peter Xu, and Peter Shier): - Tested this revision by running demand_paging_test at each commit in the series on an Intel Haswell machine. Ran demand_paging_test -u -v 8 -b 8M -d 10 on the same machine at the last commit in the series. - Readded partial aarch64 support, though aarch64 and s390 remain untested - Implemented pipefd polling to reduce UFFD thread exit latency - Added variable unit input for memory size so users can pass command line arguments of the form -b 24M instead of the raw number or bytes - Moved a missing break from a patch later in the series to an earlier one - Moved to syncing per-vCPU global variables to guest and looking up per-vcpu arguments based on a single CPU ID passed to each guest vCPU. This allows for future patches to pass more than the supported number of arguments for each arch to the vCPUs. - Implemented vcpu_args_set for s390 and aarch64 [UNTESTED] - Changed vm_create to always allocate memslot 0 at 4G instead of only when the number of pages required is large. - Changed vcpu_wss to vcpu_memory_size for clarity. Ben Gardon (10): KVM: selftests: Create a demand paging test KVM: selftests: Add demand paging content to the demand paging test KVM: selftests: Add configurable demand paging delay KVM: selftests: Add memory size parameter to the demand paging test KVM: selftests: Pass args to vCPU in global vCPU args struct KVM: selftests: Add support for vcpu_args_set to aarch64 and s390x KVM: selftests: Support multiple vCPUs in demand paging test KVM: selftests: Time guest demand paging KVM: selftests: Stop memslot creation in KVM internal memslot region KVM: selftests: Move memslot 0 above KVM internal memslots tools/testing/selftests/kvm/.gitignore | 1 + tools/testing/selftests/kvm/Makefile | 5 +- .../selftests/kvm/demand_paging_test.c | 680 ++++++++++++++++++ .../testing/selftests/kvm/include/test_util.h | 2 + .../selftests/kvm/lib/aarch64/processor.c | 33 + tools/testing/selftests/kvm/lib/kvm_util.c | 27 +- .../selftests/kvm/lib/s390x/processor.c | 35 + tools/testing/selftests/kvm/lib/test_util.c | 61 ++ 8 files changed, 839 insertions(+), 5 deletions(-) create mode 100644 tools/testing/selftests/kvm/demand_paging_test.c create mode 100644 tools/testing/selftests/kvm/lib/test_util.c -- 2.25.0.341.g760bfbb309-goog

5 years, 3 months

5
34
0 0

[PATCH] selftests/bpf: Elide a check for LLVM versions that can't compile it

by Palmer Dabbelt

The current stable LLVM BPF backend fails to compile the BPF selftests due to a compiler bug. The bug has been fixed in trunk, but that fix hasn't landed in the binary packages I'm using yet (Fedora arm64). Without this workaround the tests don't compile for me. This patch triggers a preprocessor warning on LLVM versions that definitely have the bug. The test may be conservative (ie, I'm not sure if 9.1 will have the fix), but it should at least make the current set of stable releases work together. See https://reviews.llvm.org/D69438 for more information on the fix. I obtained the workaround from https://lore.kernel.org/linux-kselftest/aed8eda7-df20-069b-ea14-f0662898456… Fixes: 20a9ad2e7136 ("selftests/bpf: add CO-RE relocs array tests") Signed-off-by: Palmer Dabbelt <palmerdabbelt(a)google.com> --- .../testing/selftests/bpf/progs/test_core_reloc_arrays.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c index 89951b684282..e5eafdab80a4 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c @@ -43,15 +43,23 @@ int test_core_arrays(void *ctx) /* in->a[2] */ if (CORE_READ(&out->a2, &in->a[2])) return 1; +#if defined(__clang__) && (__clang_major__ < 10) && (__clang_minor__ < 1) +# warning "clang 9.0 SEGVs on multidimensional arrays, see https://reviews.llvm.org/D69438" +#else /* in->b[1][2][3] */ if (CORE_READ(&out->b123, &in->b[1][2][3])) return 1; +#endif /* in->c[1].c */ if (CORE_READ(&out->c1c, &in->c[1].c)) return 1; +#if defined(__clang__) && (__clang_major__ < 10) && (__clang_minor__ < 1) +# warning "clang 9.0 SEGVs on multidimensional arrays, see https://reviews.llvm.org/D69438" +#else /* in->d[0][0].d */ if (CORE_READ(&out->d00d, &in->d[0][0].d)) return 1; +#endif return 0; } -- 2.25.0.341.g760bfbb309-goog

5 years, 3 months

3
2
0 0

[PATCH] Fix linked-list KUnit test when run multiple times

by David Gow

A few of the lists used in the linked-list KUnit tests (the for_each_entry{,_reverse} tests) are declared 'static', and so are not-reinitialised if the test runs multiple times. This was not a problem when KUnit tests were run once on startup, but when tests are able to be run manually (e.g. from debugfs[1]), this is no longer the case. Making these lists no longer 'static' causes the lists to be reinitialised, and the test passes each time it is run. While there may be some value in testing that initialising static lists works, the for_each_entry_* tests are unlikely to be the right place for it. Signed-off-by: David Gow <davidgow(a)google.com> --- lib/list-test.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/list-test.c b/lib/list-test.c index 76babb1df889..ee09505df16f 100644 --- a/lib/list-test.c +++ b/lib/list-test.c @@ -659,7 +659,7 @@ static void list_test_list_for_each_prev_safe(struct kunit *test) static void list_test_list_for_each_entry(struct kunit *test) { struct list_test_struct entries[5], *cur; - static LIST_HEAD(list); + LIST_HEAD(list); int i = 0; for (i = 0; i < 5; ++i) { @@ -680,7 +680,7 @@ static void list_test_list_for_each_entry(struct kunit *test) static void list_test_list_for_each_entry_reverse(struct kunit *test) { struct list_test_struct entries[5], *cur; - static LIST_HEAD(list); + LIST_HEAD(list); int i = 0; for (i = 0; i < 5; ++i) { -- 2.25.0.341.g760bfbb309-goog

5 years, 3 months

2
3
0 0

[PATCH bpf-next] bpf: add bpf_ct_lookup_{tcp,udp}() helpers

by Matthew Cover

Allow looking up an nf_conn. This allows eBPF programs to leverage nf_conntrack state for similar purposes to socket state use cases, as provided by the socket lookup helpers. This is particularly useful when nf_conntrack state is locally available, but socket state is not. Signed-off-by: Matthew Cover <matthew.cover(a)stackpath.com> --- include/linux/bpf.h | 28 +++ include/uapi/linux/bpf.h | 111 ++++++++- kernel/bpf/verifier.c | 105 +++++++- net/core/filter.c | 277 +++++++++++++++++++++ scripts/bpf_helpers_doc.py | 4 + tools/include/uapi/linux/bpf.h | 111 ++++++++- tools/testing/selftests/bpf/test_verifier.c | 18 ++ .../testing/selftests/bpf/verifier/ref_tracking.c | 48 ++++ 8 files changed, 694 insertions(+), 8 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8e3b8f4..28d35c3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -239,6 +239,7 @@ enum bpf_arg_type { ARG_PTR_TO_LONG, /* pointer to long */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ + ARG_PTR_TO_NF_CONN, /* pointer to bpf_nf_conn */ }; /* type of values returned from helper functions */ @@ -250,6 +251,7 @@ enum bpf_return_type { RET_PTR_TO_SOCKET_OR_NULL, /* returns a pointer to a socket or NULL */ RET_PTR_TO_TCP_SOCK_OR_NULL, /* returns a pointer to a tcp_sock or NULL */ RET_PTR_TO_SOCK_COMMON_OR_NULL, /* returns a pointer to a sock_common or NULL */ + RET_PTR_TO_NF_CONN_OR_NULL, /* returns a pointer to a nf_conn or NULL */ }; /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs @@ -316,6 +318,8 @@ enum bpf_reg_type { PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */ PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ PTR_TO_BTF_ID, /* reg points to kernel struct */ + PTR_TO_NF_CONN, /* reg points to struct nf_conn */ + PTR_TO_NF_CONN_OR_NULL, /* reg points to struct nf_conn or NULL */ }; /* The information passed from prog-specific *_is_valid_access @@ -1513,4 +1517,28 @@ enum bpf_text_poke_type { int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2); +#if IS_BUILTIN(CONFIG_NF_CONNTRACK) +bool bpf_nf_conn_is_valid_access(int off, int size, enum bpf_access_type type, + struct bpf_insn_access_aux *info); + +u32 bpf_nf_conn_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, u32 *target_size); +#else +bool bpf_nf_conn_is_valid_access(int off, int size, enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + return false; +} + +u32 bpf_nf_conn_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, u32 *target_size) +{ + return 0; +} +#endif /* CONFIG_NF_CONNTRACK */ + #endif /* _LINUX_BPF_H */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 033d90a..12e16ad 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2885,6 +2885,88 @@ struct bpf_stack_build_id { * **-EPERM** if no permission to send the *sig*. * * **-EAGAIN** if bpf program can try again. + * + * struct bpf_nf_conn *bpf_ct_lookup_tcp(void *ctx, struct bpf_nf_conntrack_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for TCP nf_conntrack entry matching *tuple*, optionally in + * a child network namespace *netns*. The return value must be + * checked, and if non-**NULL**, released via + * **bpf_ct_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or xdp_md (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 nf_conn. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 nf_conn. + * + * If the *netns* is a negative signed 32-bit integer, then the + * nf_conn lookup table in the netns associated with the *ctx* will + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For XDP hooks, this is the netns of the device in + * the xdp_md. If *netns* is any other signed 32-bit value greater + * than or equal to zero then it specifies the ID of the netns + * relative to the netns associated with the *ctx*. *netns* values + * beyond the range of 32-bit integers are reserved for future + * use. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NF_CONNTRACK=y** configuration option. + * Return + * Pointer to **struct bpf_nf_conn**, or **NULL** in case of + * failure. + * + * struct bpf_nf_conn *bpf_ct_lookup_udp(void *ctx, struct bpf_nf_conntrack_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for UDP nf_conntrack entry matching *tuple*, optionally in + * a child network namespace *netns*. The return value must be + * checked, and if non-**NULL**, released via + * **bpf_ct_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or xdp_md (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 nf_conn. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 nf_conn. + * + * If the *netns* is a negative signed 32-bit integer, then the + * nf_conn lookup table in the netns associated with the *ctx* will + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For XDP hooks, this is the netns of the device in + * the xdp_md. If *netns* is any other signed 32-bit value greater + * than or equal to zero then it specifies the ID of the netns + * relative to the netns associated with the *ctx*. *netns* values + * beyond the range of 32-bit integers are reserved for future + * use. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NF_CONNTRACK=y** configuration option. + * Return + * Pointer to **struct bpf_nf_conn**, or **NULL** in case of + * failure. + * + * int bpf_ct_release(struct bpf_nf_conn *ct) + * Description + * Release the reference held by *ct*. *ct* must be a + * non-**NULL** pointer that was returned from + * **bpf_ct_lookup_xxx**\ (). + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3004,7 +3086,10 @@ struct bpf_stack_build_id { FN(probe_read_user_str), \ FN(probe_read_kernel_str), \ FN(tcp_send_ack), \ - FN(send_signal_thread), + FN(send_signal_thread), \ + FN(ct_lookup_tcp), \ + FN(ct_lookup_udp), \ + FN(ct_release), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3278,6 +3363,30 @@ struct bpf_sock_tuple { }; }; +struct bpf_nf_conn { + __u32 cpu; + __u32 mark; + __u32 status; + __u32 timeout; +}; + +struct bpf_nf_conntrack_tuple { + union { + struct { + __be32 saddr; + __be32 daddr; + __be16 sport; + __be16 dport; + } ipv4; + struct { + __be32 saddr[4]; + __be32 daddr[4]; + __be16 sport; + __be16 dport; + } ipv6; + }; +}; + struct bpf_xdp_sock { __u32 queue_id; }; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ca17dccc..0ea0ee7 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -362,6 +362,11 @@ static const char *ltrim(const char *s) env->prev_linfo = linfo; } +static bool type_is_nf_ct_pointer(enum bpf_reg_type type) +{ + return type == PTR_TO_NF_CONN; +} + static bool type_is_pkt_pointer(enum bpf_reg_type type) { return type == PTR_TO_PACKET || @@ -381,7 +386,8 @@ static bool reg_type_may_be_null(enum bpf_reg_type type) return type == PTR_TO_MAP_VALUE_OR_NULL || type == PTR_TO_SOCKET_OR_NULL || type == PTR_TO_SOCK_COMMON_OR_NULL || - type == PTR_TO_TCP_SOCK_OR_NULL; + type == PTR_TO_TCP_SOCK_OR_NULL || + type == PTR_TO_NF_CONN_OR_NULL; } static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) @@ -395,12 +401,15 @@ static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type) return type == PTR_TO_SOCKET || type == PTR_TO_SOCKET_OR_NULL || type == PTR_TO_TCP_SOCK || - type == PTR_TO_TCP_SOCK_OR_NULL; + type == PTR_TO_TCP_SOCK_OR_NULL || + type == PTR_TO_NF_CONN || + type == PTR_TO_NF_CONN_OR_NULL; } static bool arg_type_may_be_refcounted(enum bpf_arg_type type) { - return type == ARG_PTR_TO_SOCK_COMMON; + return type == ARG_PTR_TO_SOCK_COMMON || + type == ARG_PTR_TO_NF_CONN; } /* Determine whether the function releases some resources allocated by another @@ -409,14 +418,17 @@ static bool arg_type_may_be_refcounted(enum bpf_arg_type type) */ static bool is_release_function(enum bpf_func_id func_id) { - return func_id == BPF_FUNC_sk_release; + return func_id == BPF_FUNC_sk_release || + func_id == BPF_FUNC_ct_release; } static bool is_acquire_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_sk_lookup_tcp || func_id == BPF_FUNC_sk_lookup_udp || - func_id == BPF_FUNC_skc_lookup_tcp; + func_id == BPF_FUNC_skc_lookup_tcp || + func_id == BPF_FUNC_ct_lookup_tcp || + func_id == BPF_FUNC_ct_lookup_udp; } static bool is_ptr_cast_function(enum bpf_func_id func_id) @@ -447,6 +459,8 @@ static bool is_ptr_cast_function(enum bpf_func_id func_id) [PTR_TO_TP_BUFFER] = "tp_buffer", [PTR_TO_XDP_SOCK] = "xdp_sock", [PTR_TO_BTF_ID] = "ptr_", + [PTR_TO_NF_CONN] = "nf_conn", + [PTR_TO_NF_CONN_OR_NULL] = "nf_conn_or_null", }; static char slot_type_char[] = { @@ -1913,6 +1927,8 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: case PTR_TO_BTF_ID: + case PTR_TO_NF_CONN: + case PTR_TO_NF_CONN_OR_NULL: return true; default: return false; @@ -2440,6 +2456,35 @@ static int check_flow_keys_access(struct bpf_verifier_env *env, int off, return 0; } +static int check_nf_ct_access(struct bpf_verifier_env *env, int insn_idx, + u32 regno, int off, int size, + enum bpf_access_type t) +{ + struct bpf_reg_state *regs = cur_regs(env); + struct bpf_reg_state *reg = &regs[regno]; + struct bpf_insn_access_aux info = {}; + bool valid; + + switch (reg->type) { + case PTR_TO_NF_CONN: + valid = bpf_nf_conn_is_valid_access(off, size, t, &info); + break; + default: + valid = false; + } + + if (valid) { + env->insn_aux_data[insn_idx].ctx_field_size = + info.ctx_field_size; + return 0; + } + + verbose(env, "R%d invalid %s access off=%d size=%d\n", + regno, reg_type_str[reg->type], off, size); + + return -EACCES; +} + static int check_sock_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, int off, int size, enum bpf_access_type t) @@ -2511,6 +2556,13 @@ static bool is_ctx_reg(struct bpf_verifier_env *env, int regno) return reg->type == PTR_TO_CTX; } +static bool is_nf_ct_reg(struct bpf_verifier_env *env, int regno) +{ + const struct bpf_reg_state *reg = reg_state(env, regno); + + return type_is_nf_ct_pointer(reg->type); +} + static bool is_sk_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = reg_state(env, regno); @@ -2635,6 +2687,9 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, case PTR_TO_XDP_SOCK: pointer_desc = "xdp_sock "; break; + case PTR_TO_NF_CONN: + pointer_desc = "nf_conn "; + break; default: break; } @@ -3050,6 +3105,15 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_sock_access(env, insn_idx, regno, off, size, t); if (!err && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); + } else if (type_is_nf_ct_pointer(reg->type)) { + if (t == BPF_WRITE) { + verbose(env, "R%d cannot write into %s\n", + regno, reg_type_str[reg->type]); + return -EACCES; + } + err = check_nf_ct_access(env, insn_idx, regno, off, size, t); + if (!err && value_regno >= 0) + mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_TP_BUFFER) { err = check_tp_buffer_access(env, reg, regno, off, size); if (!err && t == BPF_READ && value_regno >= 0) @@ -3099,7 +3163,8 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins if (is_ctx_reg(env, insn->dst_reg) || is_pkt_reg(env, insn->dst_reg) || is_flow_key_reg(env, insn->dst_reg) || - is_sk_reg(env, insn->dst_reg)) { + is_sk_reg(env, insn->dst_reg) || + is_nf_ct_reg(env, insn->dst_reg)) { verbose(env, "BPF_XADD stores into R%d %s is not allowed\n", insn->dst_reg, reg_type_str[reg_state(env, insn->dst_reg)->type]); @@ -3501,6 +3566,19 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, regno); return -EACCES; } + } else if (arg_type == ARG_PTR_TO_NF_CONN) { + expected_type = PTR_TO_NF_CONN; + if (!type_is_nf_ct_pointer(type)) + goto err_type; + if (reg->ref_obj_id) { + if (meta->ref_obj_id) { + verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", + regno, reg->ref_obj_id, + meta->ref_obj_id); + return -EFAULT; + } + meta->ref_obj_id = reg->ref_obj_id; + } } else if (arg_type == ARG_PTR_TO_SPIN_LOCK) { if (meta->func_id == BPF_FUNC_spin_lock) { if (process_spin_lock(env, regno, true)) @@ -4368,6 +4446,10 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL; regs[BPF_REG_0].id = ++env->id_gen; + } else if (fn->ret_type == RET_PTR_TO_NF_CONN_OR_NULL) { + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_NF_CONN_OR_NULL; + regs[BPF_REG_0].id = ++env->id_gen; } else { verbose(env, "unknown return type %d of func %s#%d\n", fn->ret_type, func_id_name(func_id), func_id); @@ -4649,6 +4731,8 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, case PTR_TO_TCP_SOCK: case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: + case PTR_TO_NF_CONN: + case PTR_TO_NF_CONN_OR_NULL: verbose(env, "R%d pointer arithmetic on %s prohibited\n", dst, reg_type_str[ptr_reg->type]); return -EACCES; @@ -5915,6 +5999,8 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state, reg->type = PTR_TO_SOCK_COMMON; } else if (reg->type == PTR_TO_TCP_SOCK_OR_NULL) { reg->type = PTR_TO_TCP_SOCK; + } else if (reg->type == PTR_TO_NF_CONN_OR_NULL) { + reg->type = PTR_TO_NF_CONN; } if (is_null) { /* We don't need id and ref_obj_id from this point @@ -7232,6 +7318,8 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, case PTR_TO_TCP_SOCK: case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: + case PTR_TO_NF_CONN: + case PTR_TO_NF_CONN_OR_NULL: /* Only valid matches are exact, which memcmp() above * would have accepted */ @@ -7760,6 +7848,8 @@ static bool reg_type_mismatch_ok(enum bpf_reg_type type) case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: case PTR_TO_BTF_ID: + case PTR_TO_NF_CONN: + case PTR_TO_NF_CONN_OR_NULL: return false; default: return true; @@ -8867,6 +8957,9 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) return -EINVAL; } continue; + case PTR_TO_NF_CONN: + convert_ctx_access = bpf_nf_conn_convert_ctx_access; + break; default: continue; } diff --git a/net/core/filter.c b/net/core/filter.c index 17de674..39ba965 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -74,6 +74,12 @@ #include <net/ipv6_stubs.h> #include <net/bpf_sk_storage.h> +#if IS_BUILTIN(CONFIG_NF_CONNTRACK) +#include <net/netfilter/nf_conntrack_tuple.h> +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack.h> +#endif + /** * sk_filter_trim_cap - run a packet through a socket filter * @sk: sock associated with &sk_buff @@ -5122,6 +5128,253 @@ static void bpf_update_srh_state(struct sk_buff *skb) }; #endif /* CONFIG_IPV6_SEG6_BPF */ +#if IS_BUILTIN(CONFIG_NF_CONNTRACK) +bool bpf_nf_conn_is_valid_access(int off, int size, enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + if (off < 0 || off >= offsetofend(struct bpf_nf_conn, + timeout)) + return false; + + if (off % size != 0) + return false; + + return size == sizeof(__u32); +} + +u32 bpf_nf_conn_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, u32 *target_size) +{ + struct bpf_insn *insn = insn_buf; + + switch (si->off) { + case offsetof(struct bpf_nf_conn, cpu): + BUILD_BUG_ON(FIELD_SIZEOF(struct nf_conn, cpu) != 2); + + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, + offsetof(struct nf_conn, cpu)); + + break; + + case offsetof(struct bpf_nf_conn, mark): +#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) + BUILD_BUG_ON(FIELD_SIZEOF(struct nf_conn, mark) != 4); + + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, + offsetof(struct nf_conn, mark)); +#else + *target_size = 4; + *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); +#endif + break; + + case offsetof(struct bpf_nf_conn, status): + BUILD_BUG_ON(FIELD_SIZEOF(struct nf_conn, status) < 4 || + __IPS_MAX_BIT > 32); + + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, + offsetof(struct nf_conn, status)); + + break; + + case offsetof(struct bpf_nf_conn, timeout): + BUILD_BUG_ON(FIELD_SIZEOF(struct nf_conn, timeout) != 4); + + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, + offsetof(struct nf_conn, timeout)); + + break; + } + + return insn - insn_buf; +} + +static struct nf_conn * +ct_lookup(struct net *net, struct bpf_nf_conntrack_tuple *tuple, + u8 family, u8 proto) +{ + struct nf_conntrack_tuple_hash *hash; + struct nf_conntrack_tuple tup; + struct nf_conn *ct = NULL; + + memset(&tup, 0, sizeof(tup)); + + tup.dst.protonum = proto; + tup.src.l3num = family; + + if (family == AF_INET) { + tup.src.u3.ip = tuple->ipv4.saddr; + tup.dst.u3.ip = tuple->ipv4.daddr; + tup.src.u.tcp.port = tuple->ipv4.sport; + tup.dst.u.tcp.port = tuple->ipv4.dport; +#if IS_ENABLED(CONFIG_IPV6) + } else { + memcpy(tup.src.u3.ip6, tuple->ipv6.saddr, sizeof(tup.src.u3.ip6)); + memcpy(tup.dst.u3.ip6, tuple->ipv6.daddr, sizeof(tup.dst.u3.ip6)); + tup.src.u.tcp.port = tuple->ipv6.sport; + tup.dst.u.tcp.port = tuple->ipv6.dport; +#endif + } + + hash = nf_conntrack_find_get(net, &nf_ct_zone_dflt, &tup); + if (!hash) + goto out; + ct = nf_ct_tuplehash_to_ctrack(hash); + +out: + return ct; +} + +static struct nf_conn * +__bpf_ct_lookup(struct sk_buff *skb, struct bpf_nf_conntrack_tuple *tuple, u32 len, + struct net *caller_net, u8 proto, u64 netns_id, u64 flags) +{ + struct nf_conn *ct = NULL; + u8 family = AF_UNSPEC; + struct net *net; + + if (len == sizeof(tuple->ipv4)) + family = AF_INET; + else if (len == sizeof(tuple->ipv6)) + family = AF_INET6; + else + goto out; + + if (unlikely(family == AF_UNSPEC || flags || + !((s32)netns_id < 0 || netns_id <= S32_MAX))) + goto out; + + if ((s32)netns_id < 0) { + net = caller_net; + ct = ct_lookup(net, tuple, family, proto); + } else { + net = get_net_ns_by_id(caller_net, netns_id); + if (unlikely(!net)) + goto out; + ct = ct_lookup(net, tuple, family, proto); + put_net(net); + } + +out: + return ct; +} + +static struct nf_conn * +bpf_ct_lookup(struct sk_buff *skb, struct bpf_nf_conntrack_tuple *tuple, u32 len, + u8 proto, u64 netns_id, u64 flags) +{ + struct net *caller_net; + + if (skb->dev) { + caller_net = dev_net(skb->dev); + } else { + caller_net = sock_net(skb->sk); + } + + return __bpf_ct_lookup(skb, tuple, len, caller_net, proto, + netns_id, flags); +} + +BPF_CALL_5(bpf_ct_lookup_tcp, struct sk_buff *, skb, + struct bpf_nf_conntrack_tuple *, tuple, u32, len, u64, netns_id, + u64, flags) +{ + return (unsigned long)bpf_ct_lookup(skb, tuple, len, IPPROTO_TCP, + netns_id, flags); +} + +static const struct bpf_func_proto bpf_ct_lookup_tcp_proto = { + .func = bpf_ct_lookup_tcp, + .gpl_only = true, + .pkt_access = true, + .ret_type = RET_PTR_TO_NF_CONN_OR_NULL, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, +}; + +BPF_CALL_5(bpf_xdp_ct_lookup_tcp, struct xdp_buff *, ctx, + struct bpf_nf_conntrack_tuple *, tuple, u32, len, u32, netns_id, + u64, flags) +{ + struct net *caller_net = dev_net(ctx->rxq->dev); + + return (unsigned long)__bpf_ct_lookup(NULL, tuple, len, caller_net, + IPPROTO_TCP, netns_id, flags); +} + +static const struct bpf_func_proto bpf_xdp_ct_lookup_tcp_proto = { + .func = bpf_xdp_ct_lookup_tcp, + .gpl_only = true, + .pkt_access = true, + .ret_type = RET_PTR_TO_NF_CONN_OR_NULL, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, +}; + +BPF_CALL_5(bpf_ct_lookup_udp, struct sk_buff *, skb, + struct bpf_nf_conntrack_tuple *, tuple, u32, len, u64, netns_id, + u64, flags) +{ + return (unsigned long)bpf_ct_lookup(skb, tuple, len, IPPROTO_UDP, + netns_id, flags); +} + +static const struct bpf_func_proto bpf_ct_lookup_udp_proto = { + .func = bpf_ct_lookup_udp, + .gpl_only = true, + .pkt_access = true, + .ret_type = RET_PTR_TO_NF_CONN_OR_NULL, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, +}; + +BPF_CALL_5(bpf_xdp_ct_lookup_udp, struct xdp_buff *, ctx, + struct bpf_nf_conntrack_tuple *, tuple, u32, len, u32, netns_id, + u64, flags) +{ + struct net *caller_net = dev_net(ctx->rxq->dev); + + return (unsigned long)__bpf_ct_lookup(NULL, tuple, len, caller_net, + IPPROTO_UDP, netns_id, flags); +} + +static const struct bpf_func_proto bpf_xdp_ct_lookup_udp_proto = { + .func = bpf_xdp_ct_lookup_udp, + .gpl_only = true, + .pkt_access = true, + .ret_type = RET_PTR_TO_NF_CONN_OR_NULL, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, +}; + +BPF_CALL_1(bpf_ct_release, struct nf_conn *, ct) +{ + nf_conntrack_put(&ct->ct_general); + return 0; +} + +static const struct bpf_func_proto bpf_ct_release_proto = { + .func = bpf_ct_release, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_NF_CONN, +}; +#endif + #ifdef CONFIG_INET static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple, int dif, int sdif, u8 family, u8 proto) @@ -6139,6 +6392,14 @@ bool bpf_helper_changes_pkt_data(void *func) case BPF_FUNC_tcp_gen_syncookie: return &bpf_tcp_gen_syncookie_proto; #endif +#if IS_BUILTIN(CONFIG_NF_CONNTRACK) + case BPF_FUNC_ct_lookup_tcp: + return &bpf_ct_lookup_tcp_proto; + case BPF_FUNC_ct_lookup_udp: + return &bpf_ct_lookup_udp_proto; + case BPF_FUNC_ct_release: + return &bpf_ct_release_proto; +#endif default: return bpf_base_func_proto(func_id); } @@ -6180,6 +6441,14 @@ bool bpf_helper_changes_pkt_data(void *func) case BPF_FUNC_tcp_gen_syncookie: return &bpf_tcp_gen_syncookie_proto; #endif +#if IS_BUILTIN(CONFIG_NF_CONNTRACK) + case BPF_FUNC_ct_lookup_tcp: + return &bpf_xdp_ct_lookup_tcp_proto; + case BPF_FUNC_ct_lookup_udp: + return &bpf_xdp_ct_lookup_udp_proto; + case BPF_FUNC_ct_release: + return &bpf_ct_release_proto; +#endif default: return bpf_base_func_proto(func_id); } @@ -6284,6 +6553,14 @@ bool bpf_helper_changes_pkt_data(void *func) case BPF_FUNC_skc_lookup_tcp: return &bpf_skc_lookup_tcp_proto; #endif +#if IS_BUILTIN(CONFIG_NF_CONNTRACK) + case BPF_FUNC_ct_lookup_tcp: + return &bpf_ct_lookup_tcp_proto; + case BPF_FUNC_ct_lookup_udp: + return &bpf_ct_lookup_udp_proto; + case BPF_FUNC_ct_release: + return &bpf_ct_release_proto; +#endif default: return bpf_base_func_proto(func_id); } diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py index 90baf7d..26f0c2a 100755 --- a/scripts/bpf_helpers_doc.py +++ b/scripts/bpf_helpers_doc.py @@ -398,6 +398,8 @@ class PrinterHelpers(Printer): type_fwds = [ 'struct bpf_fib_lookup', + 'struct bpf_nf_conn', + 'struct bpf_nf_conntrack_tuple', 'struct bpf_perf_event_data', 'struct bpf_perf_event_value', 'struct bpf_sock', @@ -433,6 +435,8 @@ class PrinterHelpers(Printer): '__wsum', 'struct bpf_fib_lookup', + 'struct bpf_nf_conn', + 'struct bpf_nf_conntrack_tuple', 'struct bpf_perf_event_data', 'struct bpf_perf_event_value', 'struct bpf_sock', diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 033d90a..12e16ad 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2885,6 +2885,88 @@ struct bpf_stack_build_id { * **-EPERM** if no permission to send the *sig*. * * **-EAGAIN** if bpf program can try again. + * + * struct bpf_nf_conn *bpf_ct_lookup_tcp(void *ctx, struct bpf_nf_conntrack_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for TCP nf_conntrack entry matching *tuple*, optionally in + * a child network namespace *netns*. The return value must be + * checked, and if non-**NULL**, released via + * **bpf_ct_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or xdp_md (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 nf_conn. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 nf_conn. + * + * If the *netns* is a negative signed 32-bit integer, then the + * nf_conn lookup table in the netns associated with the *ctx* will + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For XDP hooks, this is the netns of the device in + * the xdp_md. If *netns* is any other signed 32-bit value greater + * than or equal to zero then it specifies the ID of the netns + * relative to the netns associated with the *ctx*. *netns* values + * beyond the range of 32-bit integers are reserved for future + * use. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NF_CONNTRACK=y** configuration option. + * Return + * Pointer to **struct bpf_nf_conn**, or **NULL** in case of + * failure. + * + * struct bpf_nf_conn *bpf_ct_lookup_udp(void *ctx, struct bpf_nf_conntrack_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for UDP nf_conntrack entry matching *tuple*, optionally in + * a child network namespace *netns*. The return value must be + * checked, and if non-**NULL**, released via + * **bpf_ct_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or xdp_md (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 nf_conn. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 nf_conn. + * + * If the *netns* is a negative signed 32-bit integer, then the + * nf_conn lookup table in the netns associated with the *ctx* will + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For XDP hooks, this is the netns of the device in + * the xdp_md. If *netns* is any other signed 32-bit value greater + * than or equal to zero then it specifies the ID of the netns + * relative to the netns associated with the *ctx*. *netns* values + * beyond the range of 32-bit integers are reserved for future + * use. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NF_CONNTRACK=y** configuration option. + * Return + * Pointer to **struct bpf_nf_conn**, or **NULL** in case of + * failure. + * + * int bpf_ct_release(struct bpf_nf_conn *ct) + * Description + * Release the reference held by *ct*. *ct* must be a + * non-**NULL** pointer that was returned from + * **bpf_ct_lookup_xxx**\ (). + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3004,7 +3086,10 @@ struct bpf_stack_build_id { FN(probe_read_user_str), \ FN(probe_read_kernel_str), \ FN(tcp_send_ack), \ - FN(send_signal_thread), + FN(send_signal_thread), \ + FN(ct_lookup_tcp), \ + FN(ct_lookup_udp), \ + FN(ct_release), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3278,6 +3363,30 @@ struct bpf_sock_tuple { }; }; +struct bpf_nf_conn { + __u32 cpu; + __u32 mark; + __u32 status; + __u32 timeout; +}; + +struct bpf_nf_conntrack_tuple { + union { + struct { + __be32 saddr; + __be32 daddr; + __be16 sport; + __be16 dport; + } ipv4; + struct { + __be32 saddr[4]; + __be32 daddr[4]; + __be16 sport; + __be16 dport; + } ipv6; + }; +}; + struct bpf_xdp_sock { __u32 queue_id; }; diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 87eaa49..7569db2 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -294,6 +294,24 @@ static void bpf_fill_scale(struct bpf_test *self) } } +/* BPF_CT_LOOKUP contains 13 instructions, if you need to fix up maps */ +#define BPF_CT_LOOKUP(func) \ + /* struct bpf_nf_conntrack_tuple tuple = {} */ \ + BPF_MOV64_IMM(BPF_REG_2, 0), \ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -8), \ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -16), \ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -24), \ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -32), \ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -40), \ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -48), \ + /* ct = func(ctx, &tuple, sizeof tuple, 0, 0) */ \ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), \ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -48), \ + BPF_MOV64_IMM(BPF_REG_3, sizeof(struct bpf_nf_conntrack_tuple)),\ + BPF_MOV64_IMM(BPF_REG_4, 0), \ + BPF_MOV64_IMM(BPF_REG_5, 0), \ + BPF_EMIT_CALL(BPF_FUNC_ ## func) + /* BPF_SK_LOOKUP contains 13 instructions, if you need to fix up maps */ #define BPF_SK_LOOKUP(func) \ /* struct bpf_sock_tuple tuple = {} */ \ diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c index 604b461..de5c550a 100644 --- a/tools/testing/selftests/bpf/verifier/ref_tracking.c +++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c @@ -21,6 +21,17 @@ .result = REJECT, }, { + "reference tracking: leak potential reference to nf_conn", + .insns = { + BPF_CT_LOOKUP(ct_lookup_tcp), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), /* leak reference */ + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "Unreleased reference", + .result = REJECT, +}, +{ "reference tracking: leak potential reference on stack", .insns = { BPF_SK_LOOKUP(sk_lookup_tcp), @@ -72,6 +83,17 @@ .result = REJECT, }, { + "reference tracking: zero potential reference to nf_conn", + .insns = { + BPF_CT_LOOKUP(ct_lookup_tcp), + BPF_MOV64_IMM(BPF_REG_0, 0), /* leak reference */ + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "Unreleased reference", + .result = REJECT, +}, +{ "reference tracking: copy and zero potential references", .insns = { BPF_SK_LOOKUP(sk_lookup_tcp), @@ -113,6 +135,20 @@ .result = REJECT, }, { + "reference tracking: release reference to nf_conn without check", + .insns = { + BPF_CT_LOOKUP(ct_lookup_tcp), + /* reference in r0 may be NULL */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_EMIT_CALL(BPF_FUNC_ct_release), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .errstr = "type=nf_conn_or_null expected=nf_conn", + .result = REJECT, +}, +{ "reference tracking: release reference", .insns = { BPF_SK_LOOKUP(sk_lookup_tcp), @@ -137,6 +173,18 @@ .result = ACCEPT, }, { + "reference tracking: release reference to nf_conn", + .insns = { + BPF_CT_LOOKUP(ct_lookup_tcp), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_EMIT_CALL(BPF_FUNC_ct_release), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, +}, +{ "reference tracking: release reference 2", .insns = { BPF_SK_LOOKUP(sk_lookup_tcp), -- 1.8.3.1

5 years, 3 months

6
14
0 0

[PATCH bpf 1/4] selftests: bpf: use a temporary file in test_sockmap

by Lorenz Bauer

Use a proper temporary file for sendpage tests. This means that running the tests doesn't clutter the working directory, and allows running the test on read-only filesystems. Signed-off-by: Lorenz Bauer <lmb(a)cloudflare.com> --- tools/testing/selftests/bpf/test_sockmap.c | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 4a851513c842..779e11da979c 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -331,7 +331,7 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt, FILE *file; int i, fp; - file = fopen(".sendpage_tst.tmp", "w+"); + file = tmpfile(); if (!file) { perror("create file for sendpage"); return 1; @@ -340,13 +340,8 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt, fwrite(&k, sizeof(char), 1, file); fflush(file); fseek(file, 0, SEEK_SET); - fclose(file); - fp = open(".sendpage_tst.tmp", O_RDONLY); - if (fp < 0) { - perror("reopen file for sendpage"); - return 1; - } + fp = fileno(file); clock_gettime(CLOCK_MONOTONIC, &s->start); for (i = 0; i < cnt; i++) { @@ -354,11 +349,11 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt, if (!drop && sent < 0) { perror("send loop error"); - close(fp); + fclose(file); return sent; } else if (drop && sent >= 0) { printf("sendpage loop error expected: %i\n", sent); - close(fp); + fclose(file); return -EIO; } @@ -366,7 +361,7 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt, s->bytes_sent += sent; } clock_gettime(CLOCK_MONOTONIC, &s->end); - close(fp); + fclose(file); return 0; } -- 2.20.1

5 years, 3 months

4
4
0 0

[PATCH bpf 3/4] selftests: bpf: make reuseport test output more legible

by Lorenz Bauer

Include the name of the mismatching result in human readable format when reporting an error. The new output looks like the following: unexpected result result: [1, 0, 0, 0, 0, 0] expected: [0, 0, 0, 0, 0, 0] mismatch on DROP_ERR_INNER_MAP (bpf_prog_linum:153) check_results:FAIL:382 Signed-off-by: Lorenz Bauer <lmb(a)cloudflare.com> --- .../bpf/prog_tests/select_reuseport.c | 30 ++++++++++++++++--- 1 file changed, 26 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c index 2c37ae7dc214..09a536af139a 100644 --- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c +++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c @@ -316,6 +316,28 @@ static void check_data(int type, sa_family_t family, const struct cmd *cmd, expected.len, result.len, get_linum()); } +static const char *result_to_str(enum result res) +{ + switch (res) { + case DROP_ERR_INNER_MAP: + return "DROP_ERR_INNER_MAP"; + case DROP_ERR_SKB_DATA: + return "DROP_ERR_SKB_DATA"; + case DROP_ERR_SK_SELECT_REUSEPORT: + return "DROP_ERR_SK_SELECT_REUSEPORT"; + case DROP_MISC: + return "DROP_MISC"; + case PASS: + return "PASS"; + case PASS_ERR_SK_SELECT_REUSEPORT: + return "PASS_ERR_SK_SELECT_REUSEPORT"; + case NR_RESULTS: + return "NR_RESULTS"; + default: + return "UNKNOWN"; + } +} + static void check_results(void) { __u32 results[NR_RESULTS]; @@ -351,10 +373,10 @@ static void check_results(void) printf(", %u", expected_results[i]); printf("]\n"); - RET_IF(expected_results[broken] != results[broken], - "unexpected result", - "expected_results[%u] != results[%u] bpf_prog_linum:%ld\n", - broken, broken, get_linum()); + printf("mismatch on %s (bpf_prog_linum:%ld)\n", result_to_str(broken), + get_linum()); + + CHECK_FAIL(true); } static int send_data(int type, sa_family_t family, void *data, size_t len, -- 2.20.1

5 years, 3 months

3
2
0 0

[PATCH bpf 2/4] selftests: bpf: ignore RST packets for reuseport tests

by Lorenz Bauer

The reuseport tests currently suffer from a race condition: RST packets count towards DROP_ERR_SKB_DATA, since they don't contain a valid struct cmd. Tests will spuriously fail depending on whether check_results is called before or after the RST is processed. Exit the BPF program early if FIN is set. Signed-off-by: Lorenz Bauer <lmb(a)cloudflare.com> --- .../selftests/bpf/progs/test_select_reuseport_kern.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c index d69a1f2bbbfd..26e77dcc7e91 100644 --- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c +++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c @@ -113,6 +113,12 @@ int _select_by_skb_data(struct sk_reuseport_md *reuse_md) data_check.skb_ports[0] = th->source; data_check.skb_ports[1] = th->dest; + if (th->fin) + /* The connection is being torn down at the end of a + * test. It can't contain a cmd, so return early. + */ + return SK_PASS; + if ((th->doff << 2) + sizeof(*cmd) > data_check.len) GOTO_DONE(DROP_ERR_SKB_DATA); if (bpf_skb_load_bytes(reuse_md, th->doff << 2, &cmd_copy, -- 2.20.1

5 years, 3 months

4
6
0 0

[PATCH bpf-next v2 4/4] selftests: bpf: reset global state between reuseport test runs

by Lorenz Bauer

Currently, there is a lot of false positives if a single reuseport test fails. This is because expected_results and the result map are not cleared. Zero both after individual test runs, which fixes the mentioned false positives. Signed-off-by: Lorenz Bauer <lmb(a)cloudflare.com> Fixes: 91134d849a0e ("bpf: Test BPF_PROG_TYPE_SK_REUSEPORT") --- .../selftests/bpf/prog_tests/select_reuseport.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c index e7e56929751c..098bcae5f827 100644 --- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c +++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c @@ -33,7 +33,7 @@ #define REUSEPORT_ARRAY_SIZE 32 static int result_map, tmp_index_ovr_map, linum_map, data_check_map; -static enum result expected_results[NR_RESULTS]; +static __u32 expected_results[NR_RESULTS]; static int sk_fds[REUSEPORT_ARRAY_SIZE]; static int reuseport_array = -1, outer_map = -1; static int select_by_skb_data_prog; @@ -697,7 +697,19 @@ static void setup_per_test(int type, sa_family_t family, bool inany, static void cleanup_per_test(bool no_inner_map) { - int i, err; + int i, err, zero = 0; + + memset(expected_results, 0, sizeof(expected_results)); + + for (i = 0; i < NR_RESULTS; i++) { + err = bpf_map_update_elem(result_map, &i, &zero, BPF_ANY); + RET_IF(err, "reset elem in result_map", + "i:%u err:%d errno:%d\n", i, err, errno); + } + + err = bpf_map_update_elem(linum_map, &zero, &zero, BPF_ANY); + RET_IF(err, "reset line number in linum_map", "err:%d errno:%d\n", + err, errno); for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++) close(sk_fds[i]); -- 2.20.1

5 years, 3 months

1
0
0 0

[PATCH bpf-next v2 3/4] selftests: bpf: make reuseport test output more legible

by Lorenz Bauer

Include the name of the mismatching result in human readable format when reporting an error. The new output looks like the following: unexpected result result: [1, 0, 0, 0, 0, 0] expected: [0, 0, 0, 0, 0, 0] mismatch on DROP_ERR_INNER_MAP (bpf_prog_linum:153) check_results:FAIL:382 Signed-off-by: Lorenz Bauer <lmb(a)cloudflare.com> --- .../bpf/prog_tests/select_reuseport.c | 28 ++++++++++++++++--- 1 file changed, 24 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c index 2c37ae7dc214..e7e56929751c 100644 --- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c +++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c @@ -316,6 +316,26 @@ static void check_data(int type, sa_family_t family, const struct cmd *cmd, expected.len, result.len, get_linum()); } +static const char *result_to_str(enum result res) +{ + switch (res) { + case DROP_ERR_INNER_MAP: + return "DROP_ERR_INNER_MAP"; + case DROP_ERR_SKB_DATA: + return "DROP_ERR_SKB_DATA"; + case DROP_ERR_SK_SELECT_REUSEPORT: + return "DROP_ERR_SK_SELECT_REUSEPORT"; + case DROP_MISC: + return "DROP_MISC"; + case PASS: + return "PASS"; + case PASS_ERR_SK_SELECT_REUSEPORT: + return "PASS_ERR_SK_SELECT_REUSEPORT"; + default: + return "UNKNOWN"; + } +} + static void check_results(void) { __u32 results[NR_RESULTS]; @@ -351,10 +371,10 @@ static void check_results(void) printf(", %u", expected_results[i]); printf("]\n"); - RET_IF(expected_results[broken] != results[broken], - "unexpected result", - "expected_results[%u] != results[%u] bpf_prog_linum:%ld\n", - broken, broken, get_linum()); + printf("mismatch on %s (bpf_prog_linum:%ld)\n", result_to_str(broken), + get_linum()); + + CHECK_FAIL(true); } static int send_data(int type, sa_family_t family, void *data, size_t len, -- 2.20.1

5 years, 3 months

1
0
0 0

[PATCH bpf-next v2 2/4] selftests: bpf: ignore FIN packets for reuseport tests

by Lorenz Bauer

The reuseport tests currently suffer from a race condition: FIN packets count towards DROP_ERR_SKB_DATA, since they don't contain a valid struct cmd. Tests will spuriously fail depending on whether check_results is called before or after the FIN is processed. Exit the BPF program early if FIN is set. Signed-off-by: Lorenz Bauer <lmb(a)cloudflare.com> Fixes: 91134d849a0e ("bpf: Test BPF_PROG_TYPE_SK_REUSEPORT") --- .../selftests/bpf/progs/test_select_reuseport_kern.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c index d69a1f2bbbfd..26e77dcc7e91 100644 --- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c +++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c @@ -113,6 +113,12 @@ int _select_by_skb_data(struct sk_reuseport_md *reuse_md) data_check.skb_ports[0] = th->source; data_check.skb_ports[1] = th->dest; + if (th->fin) + /* The connection is being torn down at the end of a + * test. It can't contain a cmd, so return early. + */ + return SK_PASS; + if ((th->doff << 2) + sizeof(*cmd) > data_check.len) GOTO_DONE(DROP_ERR_SKB_DATA); if (bpf_skb_load_bytes(reuse_md, th->doff << 2, &cmd_copy, -- 2.20.1

5 years, 3 months

1
0
0 0

[PATCH bpf-next v2 1/4] selftests: bpf: use a temporary file in test_sockmap

by Lorenz Bauer

Use a proper temporary file for sendpage tests. This means that running the tests doesn't clutter the working directory, and allows running the test on read-only filesystems. Signed-off-by: Lorenz Bauer <lmb(a)cloudflare.com> Fixes: 16962b2404ac ("bpf: sockmap, add selftests") --- tools/testing/selftests/bpf/test_sockmap.c | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 4a851513c842..779e11da979c 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -331,7 +331,7 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt, FILE *file; int i, fp; - file = fopen(".sendpage_tst.tmp", "w+"); + file = tmpfile(); if (!file) { perror("create file for sendpage"); return 1; @@ -340,13 +340,8 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt, fwrite(&k, sizeof(char), 1, file); fflush(file); fseek(file, 0, SEEK_SET); - fclose(file); - fp = open(".sendpage_tst.tmp", O_RDONLY); - if (fp < 0) { - perror("reopen file for sendpage"); - return 1; - } + fp = fileno(file); clock_gettime(CLOCK_MONOTONIC, &s->start); for (i = 0; i < cnt; i++) { @@ -354,11 +349,11 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt, if (!drop && sent < 0) { perror("send loop error"); - close(fp); + fclose(file); return sent; } else if (drop && sent >= 0) { printf("sendpage loop error expected: %i\n", sent); - close(fp); + fclose(file); return -EIO; } @@ -366,7 +361,7 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt, s->bytes_sent += sent; } clock_gettime(CLOCK_MONOTONIC, &s->end); - close(fp); + fclose(file); return 0; } -- 2.20.1

5 years, 3 months

1
0
0 0

[PATCH bpf 4/4] selftests: bpf: reset global state between reuseport test runs

by Lorenz Bauer

Currently, there is a lot of false positives if a single reuseport test fails. This is because expected_results and the result map are not cleared. Zero both after individual test runs, which fixes the mentioned false positives. Signed-off-by: Lorenz Bauer <lmb(a)cloudflare.com> --- .../selftests/bpf/prog_tests/select_reuseport.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c index 09a536af139a..0bab8b1ca1c3 100644 --- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c +++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c @@ -699,7 +699,19 @@ static void setup_per_test(int type, sa_family_t family, bool inany, static void cleanup_per_test(bool no_inner_map) { - int i, err; + int i, err, zero = 0; + + memset(expected_results, 0, sizeof(expected_results)); + + for (i = 0; i < NR_RESULTS; i++) { + err = bpf_map_update_elem(result_map, &i, &zero, BPF_ANY); + RET_IF(err, "reset elem in result_map", + "i:%u err:%d errno:%d\n", i, err, errno); + } + + err = bpf_map_update_elem(linum_map, &zero, &zero, BPF_ANY); + RET_IF(err, "reset line number in linum_map", "err:%d errno:%d\n", + err, errno); for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++) close(sk_fds[i]); -- 2.20.1

5 years, 3 months

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror